diff --git "a/log/debug_0.log" "b/log/debug_0.log"
--- "a/log/debug_0.log"
+++ "b/log/debug_0.log"
@@ -1,67805 +1,3 @@
-03/03/2022 12:50:35 - INFO - codeparrot_training - Distributed environment: TPU
-Num processes: 8
-Process index: 0
-Local process index: 0
-Device: xla:1
-Use FP16 precision: False
-
-03/03/2022 12:50:35 - WARNING - huggingface_hub.repository - Revision `fast-glitter-2` does not exist. Created and checked out branch `fast-glitter-2`.
-03/03/2022 12:50:35 - WARNING - huggingface_hub.repository - 
-03/03/2022 12:50:47 - INFO - datasets.data_files - Some files matched the pattern '/home/nathan/codeparrot-clean-train/**' at /home/nathan/codeparrot-clean-train but don't have valid data file extensions: [PosixPath('/home/nathan/codeparrot-clean-train/.git/description'), PosixPath('/home/nathan/codeparrot-clean-train/.git/logs/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/17/5e/175e7375d6f65993071aa653bdd4e8b117cc02d1d2353cd7bcdbaaf7fe8b3c9c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/55/b6/55b6989a41ae296337356153e6081c61484d0b6734b6905683823e7317d01c42'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/54/60/5460223b92bb118814a7777a939f4005b7426a7e4a068c193c10d1b86eeb862b'), PosixPath('/home/nathan/codeparrot-clean-train/.git/logs/refs/remotes/origin/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-commit'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-receive.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/2e/aa/2eaa21b832ed1496fb7f0b259666dbfc36ed483d81494d1e8705f9d601509c12'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/5a/5f/5a5fbc19e0e76787f668ada7235203c10b0cbcdea0ecf8f873f8ec281cfe3494'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ae/45/ae45741df674456bc63bad91374d2ba5ef988d33d6e2a322ef0a5ac8af040371'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/32/be/32beb30e381ff02fb71854b5534306f395ef00f51f02b62da1f027c8c7fab26f'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-rebase.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/50/38/503872def2ac44733fbefc2602ab16224caca0896aa1eba045025ef2d60efcdc'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/56/80/56803c607a19ccb576c90bdb10a02cfa7b3affc67dd150fa41b00cc22213b174'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/prepare-commit-msg.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/info/exclude'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/cc/58/cc58b22515c4fd7d891287ee717c2054290b20c17b1c34693fd8964ab730687b'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/60/41/604177fe5560efd99d93091fadab6293afe7cd7d12f81638c301de1c937c1583'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/df/08/df0840d1657530c8fa9f82864be5999c515f54341d926c430a82528a6bb83740'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-merge'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/f1/a7/f1a7a250e1f6164a7fb602131ff54b69deb305258792f2358075403769d58fe5'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/d0/02/d0024828eece6d4d1c25cb4e539328be97fa28ce66a3b8d2374a117711cfd520'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/5f/d1/5fd1bb56db810b65d1fd3866dc43d9c7b690c8f52b9ca8119b2a5f4c49d13eec'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/05/39/053944e1daead0b6de8e46ea2e0bc68b9247604c63a55d444ac3b9adb12e2cd2'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/74/31/7431977a8e3a6eb0348b821009495f85d9373c1f730f4a74b0db43326568f77d'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/90/a5/90a573501de640c3e0e6f1b3508306febc96faf6061bb33c67894c168a1879c6'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/commit-msg.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/a4/6b/a46b5c08d39691524b46fadf78eab5efefa29978edfee799ec3587d928dc1302'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/fa/e6/fae6b44a24c1c35f15053a19a6b2b2af5cc9fb8bdaf0da409068a2a1f333f28e'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/b6/ce/b6ce495492aedfc91b66efdfd214b2dfe44867c719d51590e1868e42f4e9b6dd'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/7c/0e/7c0ef87edb0e556939282c859c7c893a91b5b0f931394ca4cca4f4ec98a61951'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/0b/f3/0bf3cd1320065c163f47a112458dc107650e3e862094b703b76073bd0b68663d'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/3e/f2/3ef240d0b394384803ae1bbe3b30974e11eb9b1b6ad4f49afc2ed0f7c9eae0d6'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/73/73/737327c2b47693e00050aa3410c5eb402c66211a79740ab57f1c763a1e557563'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/37/26/3726a0239b5cb7d0ef3ea36886c533d0becc7404217763015559edb546d53c94'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-merge-commit.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/67/f1/67f1ff0d590fbf4aa9afa161c290fe9be17538d4b723278bb21fd6408b0e6a3e'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ee/c1/eec1a9546aac0444a706c09f6aab67cd64403940657417e30212b7ff1e16665c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/e6/48/e6484a578778beccab26c8549608ec13970e6bcdb9541cdccad20f4d984e8181'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-applypatch.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-checkout'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/applypatch-msg.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/f1/62/f162b06b5dca01aa85ef9a675d396c0fbab1d009b5bee1c5b7ea6b415c6f12a4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/17/96/1796f12729d0407cc57500c9c87959e0e7becd729f37374702868ed8765015f4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/15/ac/15ac016e4cd702bb184457cbf5674d71b632fc34c29611ba4de549b85c67acfb'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/86/0e/860eda34e90456533e9dd41a5c0fdb74c54dc8d9cf43d6c60b887b2c858be831'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-push.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/dc/ac/dcacb03d8f43f7879c5eab4422644d7b3797b47dbb0c9c84d88cbc85822d8306'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/9b/1b/9b1b8e52b9262f03f1719d3950dc8dfa2b9719dc2e273603023f6f329c1b2068'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/5d/42/5d42ba9f195510757a3699005a7c43ddede4b598caf8a5f2f8c84d1125fa6324'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/update.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-commit.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/cd/33/cd339656799518495d23aedf1503459be6d3086e22672e80edab8403d12ded1c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/refs/remotes/origin/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/logs/refs/heads/main'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/2f/62/2f628d890bceee216f87edb3c45d2e384ee2501ce41a4c4169efaa3363bef1d2'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ac/e3/ace3ac440b380d604ab198cf8e838a2a375e7b0a6b5699ec74a8c79648f4bab8'), PosixPath('/home/nathan/codeparrot-clean-train/.git/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/packed-refs'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ef/e1/efe1759837b74b5b5ed3df1a09d4c880f9ad20413d958f79d35bf1cb6a2a09d4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/b4/83/b4836655e350f0796acd2b1a206e657c2808d9f136afae095e0b94a790c704e1'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-update.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/fsmonitor-watchman.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/9f/7e/9f7e18a3980d4b3d5ed9469ab7a2d67b608e8aa6fff38d876f86719c8f2a7a82'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/0f/7a/0f7a67cd83c1c069995f0f2510ebf818dcc71d9658f189de1231d2b7aac8883c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/index'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/55/c9/55c9c0b2f26de96e0311ee43e8eaa78ad1af387d0c59a26f22c5ebd507dda321'), PosixPath('/home/nathan/codeparrot-clean-train/.git/objects/pack/pack-df5296c3b6443e668dc098dc5c59f854d9d79f0f.idx'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/14/08/14089cad26037080ee900bede2fd42d5cac70738b2e77402b36681e1d2a521f6'), PosixPath('/home/nathan/codeparrot-clean-train/.git/config'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ac/36/ac36d12d37c1dc8ee8d3b8f0eae93966ae73482ef725615bb1a715802ddd4dd4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/e7/a9/e7a9ccbfe6bd92476f83eba205c47ed23732ace4c1bd7458d76d666ebbba3b1c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-push'), PosixPath('/home/nathan/codeparrot-clean-train/.git/objects/pack/pack-df5296c3b6443e668dc098dc5c59f854d9d79f0f.pack'), PosixPath('/home/nathan/codeparrot-clean-train/.git/refs/heads/main'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/12/8d/128d56e09d9d741b2778d733e595838a50a5e82fdc9adbb0aa8645457716b97e'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/2a/7e/2a7e50bbdb90d6c4cec534c3f1dc7ec0e6a0dada15c07cfd94615940c632ce02'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/4e/39/4e392fcaae564652d234d07b4f71eeed90efe51b1b714831e39d77f3e537d3df'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/fb/84/fb84ca8000808f62718994e4b44e79d88a05b345e9638d9f6cf6c8a5472da01f'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/d4/9f/d49f1929644619c39cff677367ff2e18223a8046ec8f61e224954a10aa2ccf8f'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/b6/8a/b68a74f9784402dcb311f4db72a873035e47b98b185a1813ab2c1645cb7255a2')]
-03/03/2022 12:50:47 - WARNING - datasets.builder - Using custom data configuration codeparrot-clean-train-86fef7ac9fb06b05
-03/03/2022 12:50:49 - WARNING - datasets.builder - Using custom data configuration lvwerra--codeparrot-clean-valid-a800eb55c299abc0
-03/03/2022 12:51:29 - INFO - codeparrot_training - Step 0: {'lr': 0.0, 'samples': 512, 'steps': 0, 'loss/train': 10.075563430786133}
-03/03/2022 12:52:43 - INFO - codeparrot_training - Step 1: {'lr': 2.5e-07, 'samples': 1024, 'steps': 1, 'loss/train': 10.124848365783691}
-03/03/2022 12:52:43 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/03/2022 12:54:06 - INFO - codeparrot_training - Step 2: {'lr': 5e-07, 'samples': 1536, 'steps': 2, 'loss/train': 10.012473106384277}
-03/03/2022 12:54:09 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/03/2022 12:54:11 - INFO - codeparrot_training - Step 3: {'lr': 7.5e-07, 'samples': 2048, 'steps': 3, 'loss/train': 10.121092796325684}
-03/03/2022 12:54:14 - INFO - codeparrot_training - Step 4: {'lr': 1e-06, 'samples': 2560, 'steps': 4, 'loss/train': 10.095026016235352}
-03/03/2022 12:54:17 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/03/2022 12:54:20 - INFO - codeparrot_training - Step 5: {'lr': 1.25e-06, 'samples': 3072, 'steps': 5, 'loss/train': 9.843606948852539}
-03/03/2022 12:54:23 - INFO - codeparrot_training - Step 6: {'lr': 1.5e-06, 'samples': 3584, 'steps': 6, 'loss/train': 10.02976131439209}
-03/03/2022 12:54:26 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/03/2022 12:54:28 - INFO - codeparrot_training - Step 7: {'lr': 1.75e-06, 'samples': 4096, 'steps': 7, 'loss/train': 10.09312629699707}
-03/03/2022 12:54:32 - INFO - codeparrot_training - Step 8: {'lr': 2e-06, 'samples': 4608, 'steps': 8, 'loss/train': 9.968323707580566}
-03/03/2022 12:54:34 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/03/2022 12:54:37 - INFO - codeparrot_training - Step 9: {'lr': 2.25e-06, 'samples': 5120, 'steps': 9, 'loss/train': 9.982961654663086}
-03/03/2022 12:54:40 - INFO - codeparrot_training - Step 10: {'lr': 2.5e-06, 'samples': 5632, 'steps': 10, 'loss/train': 9.881282806396484}
-03/03/2022 12:54:43 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/03/2022 12:54:45 - INFO - codeparrot_training - Step 11: {'lr': 2.75e-06, 'samples': 6144, 'steps': 11, 'loss/train': 9.89371395111084}
-03/03/2022 12:54:49 - INFO - codeparrot_training - Step 12: {'lr': 3e-06, 'samples': 6656, 'steps': 12, 'loss/train': 9.743671417236328}
-03/03/2022 12:54:51 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/03/2022 12:54:54 - INFO - codeparrot_training - Step 13: {'lr': 3.25e-06, 'samples': 7168, 'steps': 13, 'loss/train': 9.71867847442627}
-03/03/2022 12:54:57 - INFO - codeparrot_training - Step 14: {'lr': 3.5e-06, 'samples': 7680, 'steps': 14, 'loss/train': 9.706364631652832}
-03/03/2022 12:55:01 - INFO - codeparrot_training - Step 15: {'lr': 3.75e-06, 'samples': 8192, 'steps': 15, 'loss/train': 9.625722885131836}
-03/03/2022 12:55:01 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/03/2022 12:55:06 - INFO - codeparrot_training - Step 16: {'lr': 4e-06, 'samples': 8704, 'steps': 16, 'loss/train': 9.538063049316406}
-03/03/2022 12:55:09 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/03/2022 12:55:11 - INFO - codeparrot_training - Step 17: {'lr': 4.250000000000001e-06, 'samples': 9216, 'steps': 17, 'loss/train': 9.547978401184082}
-03/03/2022 12:55:14 - INFO - codeparrot_training - Step 18: {'lr': 4.5e-06, 'samples': 9728, 'steps': 18, 'loss/train': 9.613702774047852}
-03/03/2022 12:55:17 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/03/2022 12:55:20 - INFO - codeparrot_training - Step 19: {'lr': 4.75e-06, 'samples': 10240, 'steps': 19, 'loss/train': 9.567453384399414}
-03/03/2022 12:55:23 - INFO - codeparrot_training - Step 20: {'lr': 5e-06, 'samples': 10752, 'steps': 20, 'loss/train': 9.41970443725586}
-03/03/2022 12:55:25 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/03/2022 12:55:28 - INFO - codeparrot_training - Step 21: {'lr': 5.2500000000000006e-06, 'samples': 11264, 'steps': 21, 'loss/train': 9.453089714050293}
-03/03/2022 12:55:31 - INFO - codeparrot_training - Step 22: {'lr': 5.5e-06, 'samples': 11776, 'steps': 22, 'loss/train': 9.410444259643555}
-03/03/2022 12:55:34 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/03/2022 12:55:37 - INFO - codeparrot_training - Step 23: {'lr': 5.75e-06, 'samples': 12288, 'steps': 23, 'loss/train': 8.90427303314209}
-03/03/2022 12:55:40 - INFO - codeparrot_training - Step 24: {'lr': 6e-06, 'samples': 12800, 'steps': 24, 'loss/train': 9.217617988586426}
-03/03/2022 12:55:42 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/03/2022 12:55:45 - INFO - codeparrot_training - Step 25: {'lr': 6.25e-06, 'samples': 13312, 'steps': 25, 'loss/train': 9.386109352111816}
-03/03/2022 12:55:48 - INFO - codeparrot_training - Step 26: {'lr': 6.5e-06, 'samples': 13824, 'steps': 26, 'loss/train': 8.986451148986816}
-03/03/2022 12:55:50 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/03/2022 12:55:54 - INFO - codeparrot_training - Step 27: {'lr': 6.75e-06, 'samples': 14336, 'steps': 27, 'loss/train': 9.02078914642334}
-03/03/2022 12:55:57 - INFO - codeparrot_training - Step 28: {'lr': 7e-06, 'samples': 14848, 'steps': 28, 'loss/train': 9.070732116699219}
-03/03/2022 12:55:58 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/03/2022 12:56:02 - INFO - codeparrot_training - Step 29: {'lr': 7.250000000000001e-06, 'samples': 15360, 'steps': 29, 'loss/train': 8.967691421508789}
-03/03/2022 12:56:05 - INFO - codeparrot_training - Step 30: {'lr': 7.5e-06, 'samples': 15872, 'steps': 30, 'loss/train': 8.433162689208984}
-03/03/2022 12:56:07 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/03/2022 12:56:11 - INFO - codeparrot_training - Step 31: {'lr': 7.75e-06, 'samples': 16384, 'steps': 31, 'loss/train': 9.051046371459961}
-03/03/2022 12:56:14 - INFO - codeparrot_training - Step 32: {'lr': 8e-06, 'samples': 16896, 'steps': 32, 'loss/train': 8.816210746765137}
-03/03/2022 12:56:15 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/03/2022 12:56:19 - INFO - codeparrot_training - Step 33: {'lr': 8.25e-06, 'samples': 17408, 'steps': 33, 'loss/train': 9.837918281555176}
-03/03/2022 12:56:22 - INFO - codeparrot_training - Step 34: {'lr': 8.500000000000002e-06, 'samples': 17920, 'steps': 34, 'loss/train': 9.328680992126465}
-03/03/2022 12:56:24 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/03/2022 12:56:28 - INFO - codeparrot_training - Step 35: {'lr': 8.750000000000001e-06, 'samples': 18432, 'steps': 35, 'loss/train': 8.939859390258789}
-03/03/2022 12:56:31 - INFO - codeparrot_training - Step 36: {'lr': 9e-06, 'samples': 18944, 'steps': 36, 'loss/train': 9.023159980773926}
-03/03/2022 12:56:32 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/03/2022 12:56:36 - INFO - codeparrot_training - Step 37: {'lr': 9.25e-06, 'samples': 19456, 'steps': 37, 'loss/train': 9.151119232177734}
-03/03/2022 12:56:39 - INFO - codeparrot_training - Step 38: {'lr': 9.5e-06, 'samples': 19968, 'steps': 38, 'loss/train': 8.467151641845703}
-03/03/2022 12:56:40 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/03/2022 12:56:45 - INFO - codeparrot_training - Step 39: {'lr': 9.75e-06, 'samples': 20480, 'steps': 39, 'loss/train': 8.554976463317871}
-03/03/2022 12:56:48 - INFO - codeparrot_training - Step 40: {'lr': 1e-05, 'samples': 20992, 'steps': 40, 'loss/train': 9.488030433654785}
-03/03/2022 12:56:48 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/03/2022 12:56:53 - INFO - codeparrot_training - Step 41: {'lr': 1.025e-05, 'samples': 21504, 'steps': 41, 'loss/train': 9.343393325805664}
-03/03/2022 12:56:56 - INFO - codeparrot_training - Step 42: {'lr': 1.0500000000000001e-05, 'samples': 22016, 'steps': 42, 'loss/train': 8.726397514343262}
-03/03/2022 12:56:57 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/03/2022 12:57:01 - INFO - codeparrot_training - Step 43: {'lr': 1.0749999999999999e-05, 'samples': 22528, 'steps': 43, 'loss/train': 8.832099914550781}
-03/03/2022 12:57:05 - INFO - codeparrot_training - Step 44: {'lr': 1.1e-05, 'samples': 23040, 'steps': 44, 'loss/train': 8.617071151733398}
-03/03/2022 12:57:05 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/03/2022 12:57:10 - INFO - codeparrot_training - Step 45: {'lr': 1.1249999999999999e-05, 'samples': 23552, 'steps': 45, 'loss/train': 8.621835708618164}
-03/03/2022 12:57:13 - INFO - codeparrot_training - Step 46: {'lr': 1.15e-05, 'samples': 24064, 'steps': 46, 'loss/train': 8.607819557189941}
-03/03/2022 12:57:13 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/03/2022 12:57:19 - INFO - codeparrot_training - Step 47: {'lr': 1.1750000000000001e-05, 'samples': 24576, 'steps': 47, 'loss/train': 8.41963005065918}
-03/03/2022 12:57:21 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/03/2022 12:57:24 - INFO - codeparrot_training - Step 48: {'lr': 1.2e-05, 'samples': 25088, 'steps': 48, 'loss/train': 8.563586235046387}
-03/03/2022 12:57:27 - INFO - codeparrot_training - Step 49: {'lr': 1.2250000000000001e-05, 'samples': 25600, 'steps': 49, 'loss/train': 9.081216812133789}
-03/03/2022 12:57:30 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/03/2022 12:57:32 - INFO - codeparrot_training - Step 50: {'lr': 1.25e-05, 'samples': 26112, 'steps': 50, 'loss/train': 8.793917655944824}
-03/03/2022 12:57:36 - INFO - codeparrot_training - Step 51: {'lr': 1.275e-05, 'samples': 26624, 'steps': 51, 'loss/train': 7.926756858825684}
-03/03/2022 12:57:38 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/03/2022 12:57:41 - INFO - codeparrot_training - Step 52: {'lr': 1.3e-05, 'samples': 27136, 'steps': 52, 'loss/train': 8.878251075744629}
-03/03/2022 12:57:44 - INFO - codeparrot_training - Step 53: {'lr': 1.325e-05, 'samples': 27648, 'steps': 53, 'loss/train': 8.69863224029541}
-03/03/2022 12:57:47 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/03/2022 12:57:50 - INFO - codeparrot_training - Step 54: {'lr': 1.35e-05, 'samples': 28160, 'steps': 54, 'loss/train': 8.32911205291748}
-03/03/2022 12:57:53 - INFO - codeparrot_training - Step 55: {'lr': 1.375e-05, 'samples': 28672, 'steps': 55, 'loss/train': 8.402761459350586}
-03/03/2022 12:57:55 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/03/2022 12:57:58 - INFO - codeparrot_training - Step 56: {'lr': 1.4e-05, 'samples': 29184, 'steps': 56, 'loss/train': 8.484271049499512}
-03/03/2022 12:58:01 - INFO - codeparrot_training - Step 57: {'lr': 1.425e-05, 'samples': 29696, 'steps': 57, 'loss/train': 8.7686767578125}
-03/03/2022 12:58:04 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/03/2022 12:58:07 - INFO - codeparrot_training - Step 58: {'lr': 1.4500000000000002e-05, 'samples': 30208, 'steps': 58, 'loss/train': 8.384221076965332}
-03/03/2022 12:58:10 - INFO - codeparrot_training - Step 59: {'lr': 1.475e-05, 'samples': 30720, 'steps': 59, 'loss/train': 8.519675254821777}
-03/03/2022 12:58:12 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/03/2022 12:58:15 - INFO - codeparrot_training - Step 60: {'lr': 1.5e-05, 'samples': 31232, 'steps': 60, 'loss/train': 8.939576148986816}
-03/03/2022 12:58:19 - INFO - codeparrot_training - Step 61: {'lr': 1.525e-05, 'samples': 31744, 'steps': 61, 'loss/train': 8.751921653747559}
-03/03/2022 12:58:21 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/03/2022 12:58:24 - INFO - codeparrot_training - Step 62: {'lr': 1.55e-05, 'samples': 32256, 'steps': 62, 'loss/train': 8.698548316955566}
-03/03/2022 12:58:27 - INFO - codeparrot_training - Step 63: {'lr': 1.575e-05, 'samples': 32768, 'steps': 63, 'loss/train': 8.578275680541992}
-03/03/2022 12:58:29 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/03/2022 12:58:32 - INFO - codeparrot_training - Step 64: {'lr': 1.6e-05, 'samples': 33280, 'steps': 64, 'loss/train': 8.510712623596191}
-03/03/2022 12:58:36 - INFO - codeparrot_training - Step 65: {'lr': 1.6250000000000002e-05, 'samples': 33792, 'steps': 65, 'loss/train': 8.645843505859375}
-03/03/2022 12:58:37 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/03/2022 12:58:41 - INFO - codeparrot_training - Step 66: {'lr': 1.65e-05, 'samples': 34304, 'steps': 66, 'loss/train': 8.519330024719238}
-03/03/2022 12:58:44 - INFO - codeparrot_training - Step 67: {'lr': 1.675e-05, 'samples': 34816, 'steps': 67, 'loss/train': 8.555344581604004}
-03/03/2022 12:58:46 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/03/2022 12:58:49 - INFO - codeparrot_training - Step 68: {'lr': 1.7000000000000003e-05, 'samples': 35328, 'steps': 68, 'loss/train': 8.772445678710938}
-03/03/2022 12:58:53 - INFO - codeparrot_training - Step 69: {'lr': 1.7250000000000003e-05, 'samples': 35840, 'steps': 69, 'loss/train': 8.694655418395996}
-03/03/2022 12:58:54 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/03/2022 12:58:58 - INFO - codeparrot_training - Step 70: {'lr': 1.7500000000000002e-05, 'samples': 36352, 'steps': 70, 'loss/train': 8.430862426757812}
-03/03/2022 12:59:01 - INFO - codeparrot_training - Step 71: {'lr': 1.7749999999999998e-05, 'samples': 36864, 'steps': 71, 'loss/train': 9.024465560913086}
-03/03/2022 12:59:02 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/03/2022 12:59:06 - INFO - codeparrot_training - Step 72: {'lr': 1.8e-05, 'samples': 37376, 'steps': 72, 'loss/train': 8.457487106323242}
-03/03/2022 12:59:10 - INFO - codeparrot_training - Step 73: {'lr': 1.825e-05, 'samples': 37888, 'steps': 73, 'loss/train': 8.562689781188965}
-03/03/2022 12:59:11 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/03/2022 12:59:15 - INFO - codeparrot_training - Step 74: {'lr': 1.85e-05, 'samples': 38400, 'steps': 74, 'loss/train': 8.607612609863281}
-03/03/2022 12:59:18 - INFO - codeparrot_training - Step 75: {'lr': 1.875e-05, 'samples': 38912, 'steps': 75, 'loss/train': 8.44783878326416}
-03/03/2022 12:59:19 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/03/2022 12:59:23 - INFO - codeparrot_training - Step 76: {'lr': 1.9e-05, 'samples': 39424, 'steps': 76, 'loss/train': 9.018163681030273}
-03/03/2022 12:59:27 - INFO - codeparrot_training - Step 77: {'lr': 1.925e-05, 'samples': 39936, 'steps': 77, 'loss/train': 8.568017959594727}
-03/03/2022 12:59:28 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/03/2022 12:59:32 - INFO - codeparrot_training - Step 78: {'lr': 1.95e-05, 'samples': 40448, 'steps': 78, 'loss/train': 8.524364471435547}
-03/03/2022 12:59:35 - INFO - codeparrot_training - Step 79: {'lr': 1.975e-05, 'samples': 40960, 'steps': 79, 'loss/train': 8.529118537902832}
-03/03/2022 12:59:36 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/03/2022 12:59:40 - INFO - codeparrot_training - Step 80: {'lr': 2e-05, 'samples': 41472, 'steps': 80, 'loss/train': 8.654486656188965}
-03/03/2022 12:59:44 - INFO - codeparrot_training - Step 81: {'lr': 2.025e-05, 'samples': 41984, 'steps': 81, 'loss/train': 8.813864707946777}
-03/03/2022 12:59:45 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/03/2022 12:59:49 - INFO - codeparrot_training - Step 82: {'lr': 2.05e-05, 'samples': 42496, 'steps': 82, 'loss/train': 8.502435684204102}
-03/03/2022 12:59:52 - INFO - codeparrot_training - Step 83: {'lr': 2.0750000000000003e-05, 'samples': 43008, 'steps': 83, 'loss/train': 9.020332336425781}
-03/03/2022 12:59:53 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/03/2022 12:59:58 - INFO - codeparrot_training - Step 84: {'lr': 2.1000000000000002e-05, 'samples': 43520, 'steps': 84, 'loss/train': 8.501923561096191}
-03/03/2022 13:00:01 - INFO - codeparrot_training - Step 85: {'lr': 2.125e-05, 'samples': 44032, 'steps': 85, 'loss/train': 8.312204360961914}
-03/03/2022 13:00:02 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/03/2022 13:00:06 - INFO - codeparrot_training - Step 86: {'lr': 2.1499999999999997e-05, 'samples': 44544, 'steps': 86, 'loss/train': 8.143906593322754}
-03/03/2022 13:00:10 - INFO - codeparrot_training - Step 87: {'lr': 2.175e-05, 'samples': 45056, 'steps': 87, 'loss/train': 8.643278121948242}
-03/03/2022 13:00:10 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/03/2022 13:00:15 - INFO - codeparrot_training - Step 88: {'lr': 2.2e-05, 'samples': 45568, 'steps': 88, 'loss/train': 8.471076011657715}
-03/03/2022 13:00:18 - INFO - codeparrot_training - Step 89: {'lr': 2.225e-05, 'samples': 46080, 'steps': 89, 'loss/train': 8.585366249084473}
-03/03/2022 13:00:19 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/03/2022 13:00:24 - INFO - codeparrot_training - Step 90: {'lr': 2.2499999999999998e-05, 'samples': 46592, 'steps': 90, 'loss/train': 8.756730079650879}
-03/03/2022 13:00:27 - INFO - codeparrot_training - Step 91: {'lr': 2.275e-05, 'samples': 47104, 'steps': 91, 'loss/train': 8.959531784057617}
-03/03/2022 13:00:27 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/03/2022 13:00:32 - INFO - codeparrot_training - Step 92: {'lr': 2.3e-05, 'samples': 47616, 'steps': 92, 'loss/train': 8.488385200500488}
-03/03/2022 13:00:35 - INFO - codeparrot_training - Step 93: {'lr': 2.325e-05, 'samples': 48128, 'steps': 93, 'loss/train': 8.548238754272461}
-03/03/2022 13:00:36 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/03/2022 13:00:40 - INFO - codeparrot_training - Step 94: {'lr': 2.3500000000000002e-05, 'samples': 48640, 'steps': 94, 'loss/train': 9.079781532287598}
-03/03/2022 13:00:44 - INFO - codeparrot_training - Step 95: {'lr': 2.375e-05, 'samples': 49152, 'steps': 95, 'loss/train': 8.213057518005371}
-03/03/2022 13:00:44 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/03/2022 13:00:49 - INFO - codeparrot_training - Step 96: {'lr': 2.4e-05, 'samples': 49664, 'steps': 96, 'loss/train': 9.193713188171387}
-03/03/2022 13:00:52 - INFO - codeparrot_training - Step 97: {'lr': 2.425e-05, 'samples': 50176, 'steps': 97, 'loss/train': 8.648150444030762}
-03/03/2022 13:00:52 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/03/2022 13:00:57 - INFO - codeparrot_training - Step 98: {'lr': 2.4500000000000003e-05, 'samples': 50688, 'steps': 98, 'loss/train': 8.951532363891602}
-03/03/2022 13:01:01 - INFO - codeparrot_training - Step 99: {'lr': 2.4750000000000002e-05, 'samples': 51200, 'steps': 99, 'loss/train': 8.602143287658691}
-03/03/2022 13:01:01 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/03/2022 13:01:06 - INFO - codeparrot_training - Step 100: {'lr': 2.5e-05, 'samples': 51712, 'steps': 100, 'loss/train': 8.64793586730957}
-03/03/2022 13:01:09 - INFO - codeparrot_training - Step 101: {'lr': 2.525e-05, 'samples': 52224, 'steps': 101, 'loss/train': 8.7129545211792}
-03/03/2022 13:01:09 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/03/2022 13:01:14 - INFO - codeparrot_training - Step 102: {'lr': 2.55e-05, 'samples': 52736, 'steps': 102, 'loss/train': 8.678922653198242}
-03/03/2022 13:01:17 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/03/2022 13:01:20 - INFO - codeparrot_training - Step 103: {'lr': 2.575e-05, 'samples': 53248, 'steps': 103, 'loss/train': 8.083718299865723}
-03/03/2022 13:01:23 - INFO - codeparrot_training - Step 104: {'lr': 2.6e-05, 'samples': 53760, 'steps': 104, 'loss/train': 8.35842227935791}
-03/03/2022 13:01:26 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/03/2022 13:01:28 - INFO - codeparrot_training - Step 105: {'lr': 2.625e-05, 'samples': 54272, 'steps': 105, 'loss/train': 8.159714698791504}
-03/03/2022 13:01:31 - INFO - codeparrot_training - Step 106: {'lr': 2.65e-05, 'samples': 54784, 'steps': 106, 'loss/train': 8.1396484375}
-03/03/2022 13:01:34 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/03/2022 13:01:37 - INFO - codeparrot_training - Step 107: {'lr': 2.675e-05, 'samples': 55296, 'steps': 107, 'loss/train': 8.233939170837402}
-03/03/2022 13:01:40 - INFO - codeparrot_training - Step 108: {'lr': 2.7e-05, 'samples': 55808, 'steps': 108, 'loss/train': 8.465450286865234}
-03/03/2022 13:01:42 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/03/2022 13:01:45 - INFO - codeparrot_training - Step 109: {'lr': 2.725e-05, 'samples': 56320, 'steps': 109, 'loss/train': 8.154802322387695}
-03/03/2022 13:01:48 - INFO - codeparrot_training - Step 110: {'lr': 2.75e-05, 'samples': 56832, 'steps': 110, 'loss/train': 8.17076301574707}
-03/03/2022 13:01:50 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/03/2022 13:01:54 - INFO - codeparrot_training - Step 111: {'lr': 2.775e-05, 'samples': 57344, 'steps': 111, 'loss/train': 8.381338119506836}
-03/03/2022 13:01:57 - INFO - codeparrot_training - Step 112: {'lr': 2.8e-05, 'samples': 57856, 'steps': 112, 'loss/train': 8.114055633544922}
-03/03/2022 13:01:59 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/03/2022 13:02:02 - INFO - codeparrot_training - Step 113: {'lr': 2.8250000000000002e-05, 'samples': 58368, 'steps': 113, 'loss/train': 7.933559894561768}
-03/03/2022 13:02:06 - INFO - codeparrot_training - Step 114: {'lr': 2.85e-05, 'samples': 58880, 'steps': 114, 'loss/train': 9.193424224853516}
-03/03/2022 13:02:08 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/03/2022 13:02:11 - INFO - codeparrot_training - Step 115: {'lr': 2.875e-05, 'samples': 59392, 'steps': 115, 'loss/train': 7.855266094207764}
-03/03/2022 13:02:14 - INFO - codeparrot_training - Step 116: {'lr': 2.9000000000000004e-05, 'samples': 59904, 'steps': 116, 'loss/train': 8.517616271972656}
-03/03/2022 13:02:16 - INFO - codeparrot_training - Skipping example with length 822 (seq_length=1024)
-03/03/2022 13:02:19 - INFO - codeparrot_training - Step 117: {'lr': 2.9250000000000003e-05, 'samples': 60416, 'steps': 117, 'loss/train': 8.036568641662598}
-03/03/2022 13:02:22 - INFO - codeparrot_training - Step 118: {'lr': 2.95e-05, 'samples': 60928, 'steps': 118, 'loss/train': 7.926286220550537}
-03/03/2022 13:02:24 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/03/2022 13:02:28 - INFO - codeparrot_training - Step 119: {'lr': 2.9749999999999998e-05, 'samples': 61440, 'steps': 119, 'loss/train': 8.040275573730469}
-03/03/2022 13:02:31 - INFO - codeparrot_training - Step 120: {'lr': 3e-05, 'samples': 61952, 'steps': 120, 'loss/train': 6.9734649658203125}
-03/03/2022 13:02:33 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/03/2022 13:02:37 - INFO - codeparrot_training - Step 121: {'lr': 3.025e-05, 'samples': 62464, 'steps': 121, 'loss/train': 8.224665641784668}
-03/03/2022 13:02:40 - INFO - codeparrot_training - Step 122: {'lr': 3.05e-05, 'samples': 62976, 'steps': 122, 'loss/train': 8.240490913391113}
-03/03/2022 13:02:41 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/03/2022 13:02:45 - INFO - codeparrot_training - Step 123: {'lr': 3.075e-05, 'samples': 63488, 'steps': 123, 'loss/train': 8.030046463012695}
-03/03/2022 13:02:48 - INFO - codeparrot_training - Step 124: {'lr': 3.1e-05, 'samples': 64000, 'steps': 124, 'loss/train': 7.976356029510498}
-03/03/2022 13:02:49 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/03/2022 13:02:54 - INFO - codeparrot_training - Step 125: {'lr': 3.125e-05, 'samples': 64512, 'steps': 125, 'loss/train': 8.348257064819336}
-03/03/2022 13:02:57 - INFO - codeparrot_training - Step 126: {'lr': 3.15e-05, 'samples': 65024, 'steps': 126, 'loss/train': 7.844707489013672}
-03/03/2022 13:02:58 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/03/2022 13:03:02 - INFO - codeparrot_training - Step 127: {'lr': 3.175e-05, 'samples': 65536, 'steps': 127, 'loss/train': 8.167869567871094}
-03/03/2022 13:03:05 - INFO - codeparrot_training - Step 128: {'lr': 3.2e-05, 'samples': 66048, 'steps': 128, 'loss/train': 7.930793762207031}
-03/03/2022 13:03:06 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/03/2022 13:03:11 - INFO - codeparrot_training - Step 129: {'lr': 3.2250000000000005e-05, 'samples': 66560, 'steps': 129, 'loss/train': 7.673683166503906}
-03/03/2022 13:03:14 - INFO - codeparrot_training - Step 130: {'lr': 3.2500000000000004e-05, 'samples': 67072, 'steps': 130, 'loss/train': 8.17394733428955}
-03/03/2022 13:03:14 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/03/2022 13:03:19 - INFO - codeparrot_training - Step 131: {'lr': 3.275e-05, 'samples': 67584, 'steps': 131, 'loss/train': 7.390617847442627}
-03/03/2022 13:03:22 - INFO - codeparrot_training - Step 132: {'lr': 3.3e-05, 'samples': 68096, 'steps': 132, 'loss/train': 7.104628562927246}
-03/03/2022 13:03:22 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/03/2022 13:03:28 - INFO - codeparrot_training - Step 133: {'lr': 3.325e-05, 'samples': 68608, 'steps': 133, 'loss/train': 8.078102111816406}
-03/03/2022 13:03:31 - INFO - codeparrot_training - Step 134: {'lr': 3.35e-05, 'samples': 69120, 'steps': 134, 'loss/train': 7.884213447570801}
-03/03/2022 13:03:31 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/03/2022 13:03:36 - INFO - codeparrot_training - Step 135: {'lr': 3.375e-05, 'samples': 69632, 'steps': 135, 'loss/train': 8.450540542602539}
-03/03/2022 13:03:39 - INFO - codeparrot_training - Step 136: {'lr': 3.4000000000000007e-05, 'samples': 70144, 'steps': 136, 'loss/train': 8.404011726379395}
-03/03/2022 13:03:39 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/03/2022 13:03:45 - INFO - codeparrot_training - Step 137: {'lr': 3.4250000000000006e-05, 'samples': 70656, 'steps': 137, 'loss/train': 7.6241350173950195}
-03/03/2022 13:03:48 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/03/2022 13:03:50 - INFO - codeparrot_training - Step 138: {'lr': 3.4500000000000005e-05, 'samples': 71168, 'steps': 138, 'loss/train': 7.530354022979736}
-03/03/2022 13:03:53 - INFO - codeparrot_training - Step 139: {'lr': 3.4750000000000004e-05, 'samples': 71680, 'steps': 139, 'loss/train': 8.152228355407715}
-03/03/2022 13:03:56 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/03/2022 13:03:58 - INFO - codeparrot_training - Step 140: {'lr': 3.5000000000000004e-05, 'samples': 72192, 'steps': 140, 'loss/train': 8.318809509277344}
-03/03/2022 13:04:01 - INFO - codeparrot_training - Step 141: {'lr': 3.5249999999999996e-05, 'samples': 72704, 'steps': 141, 'loss/train': 7.475725173950195}
-03/03/2022 13:04:04 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/03/2022 13:04:07 - INFO - codeparrot_training - Step 142: {'lr': 3.5499999999999996e-05, 'samples': 73216, 'steps': 142, 'loss/train': 7.176308631896973}
-03/03/2022 13:04:10 - INFO - codeparrot_training - Step 143: {'lr': 3.5749999999999995e-05, 'samples': 73728, 'steps': 143, 'loss/train': 8.0440034866333}
-03/03/2022 13:04:12 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/03/2022 13:04:15 - INFO - codeparrot_training - Step 144: {'lr': 3.6e-05, 'samples': 74240, 'steps': 144, 'loss/train': 8.216455459594727}
-03/03/2022 13:04:19 - INFO - codeparrot_training - Step 145: {'lr': 3.625e-05, 'samples': 74752, 'steps': 145, 'loss/train': 8.240697860717773}
-03/03/2022 13:04:21 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/03/2022 13:04:24 - INFO - codeparrot_training - Step 146: {'lr': 3.65e-05, 'samples': 75264, 'steps': 146, 'loss/train': 7.32492208480835}
-03/03/2022 13:04:27 - INFO - codeparrot_training - Step 147: {'lr': 3.675e-05, 'samples': 75776, 'steps': 147, 'loss/train': 7.730316162109375}
-03/03/2022 13:04:29 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/03/2022 13:04:32 - INFO - codeparrot_training - Step 148: {'lr': 3.7e-05, 'samples': 76288, 'steps': 148, 'loss/train': 7.661489009857178}
-03/03/2022 13:04:36 - INFO - codeparrot_training - Step 149: {'lr': 3.725e-05, 'samples': 76800, 'steps': 149, 'loss/train': 7.78841495513916}
-03/03/2022 13:04:38 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/03/2022 13:04:41 - INFO - codeparrot_training - Step 150: {'lr': 3.75e-05, 'samples': 77312, 'steps': 150, 'loss/train': 7.619410037994385}
-03/03/2022 13:04:44 - INFO - codeparrot_training - Step 151: {'lr': 3.775e-05, 'samples': 77824, 'steps': 151, 'loss/train': 8.464534759521484}
-03/03/2022 13:04:46 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/03/2022 13:04:49 - INFO - codeparrot_training - Step 152: {'lr': 3.8e-05, 'samples': 78336, 'steps': 152, 'loss/train': 7.549778461456299}
-03/03/2022 13:04:53 - INFO - codeparrot_training - Step 153: {'lr': 3.825e-05, 'samples': 78848, 'steps': 153, 'loss/train': 7.371613502502441}
-03/03/2022 13:04:54 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/03/2022 13:04:58 - INFO - codeparrot_training - Step 154: {'lr': 3.85e-05, 'samples': 79360, 'steps': 154, 'loss/train': 7.702090740203857}
-03/03/2022 13:05:01 - INFO - codeparrot_training - Step 155: {'lr': 3.875e-05, 'samples': 79872, 'steps': 155, 'loss/train': 7.848684787750244}
-03/03/2022 13:05:03 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/03/2022 13:05:07 - INFO - codeparrot_training - Step 156: {'lr': 3.9e-05, 'samples': 80384, 'steps': 156, 'loss/train': 7.010176181793213}
-03/03/2022 13:05:10 - INFO - codeparrot_training - Step 157: {'lr': 3.925e-05, 'samples': 80896, 'steps': 157, 'loss/train': 4.933742523193359}
-03/03/2022 13:05:13 - INFO - codeparrot_training - Step 158: {'lr': 3.95e-05, 'samples': 81408, 'steps': 158, 'loss/train': 8.188973426818848}
-03/03/2022 13:05:13 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/03/2022 13:05:19 - INFO - codeparrot_training - Step 159: {'lr': 3.9750000000000004e-05, 'samples': 81920, 'steps': 159, 'loss/train': 8.148823738098145}
-03/03/2022 13:05:21 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/03/2022 13:05:24 - INFO - codeparrot_training - Step 160: {'lr': 4e-05, 'samples': 82432, 'steps': 160, 'loss/train': 7.696084976196289}
-03/03/2022 13:05:27 - INFO - codeparrot_training - Step 161: {'lr': 4.025e-05, 'samples': 82944, 'steps': 161, 'loss/train': 8.04732608795166}
-03/03/2022 13:05:29 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 13:05:32 - INFO - codeparrot_training - Step 162: {'lr': 4.05e-05, 'samples': 83456, 'steps': 162, 'loss/train': 7.864019870758057}
-03/03/2022 13:05:36 - INFO - codeparrot_training - Step 163: {'lr': 4.075e-05, 'samples': 83968, 'steps': 163, 'loss/train': 7.568187713623047}
-03/03/2022 13:05:38 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/03/2022 13:05:41 - INFO - codeparrot_training - Step 164: {'lr': 4.1e-05, 'samples': 84480, 'steps': 164, 'loss/train': 7.4156365394592285}
-03/03/2022 13:05:44 - INFO - codeparrot_training - Step 165: {'lr': 4.125e-05, 'samples': 84992, 'steps': 165, 'loss/train': 8.103707313537598}
-03/03/2022 13:05:46 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/03/2022 13:05:50 - INFO - codeparrot_training - Step 166: {'lr': 4.1500000000000006e-05, 'samples': 85504, 'steps': 166, 'loss/train': 7.68804407119751}
-03/03/2022 13:05:53 - INFO - codeparrot_training - Step 167: {'lr': 4.1750000000000005e-05, 'samples': 86016, 'steps': 167, 'loss/train': 7.974943161010742}
-03/03/2022 13:05:55 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/03/2022 13:05:58 - INFO - codeparrot_training - Step 168: {'lr': 4.2000000000000004e-05, 'samples': 86528, 'steps': 168, 'loss/train': 5.833436012268066}
-03/03/2022 13:06:01 - INFO - codeparrot_training - Step 169: {'lr': 4.2250000000000004e-05, 'samples': 87040, 'steps': 169, 'loss/train': 7.7950568199157715}
-03/03/2022 13:06:03 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/03/2022 13:06:06 - INFO - codeparrot_training - Step 170: {'lr': 4.25e-05, 'samples': 87552, 'steps': 170, 'loss/train': 7.657891273498535}
-03/03/2022 13:06:10 - INFO - codeparrot_training - Step 171: {'lr': 4.275e-05, 'samples': 88064, 'steps': 171, 'loss/train': 7.877186298370361}
-03/03/2022 13:06:11 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/03/2022 13:06:15 - INFO - codeparrot_training - Step 172: {'lr': 4.2999999999999995e-05, 'samples': 88576, 'steps': 172, 'loss/train': 7.893576622009277}
-03/03/2022 13:06:18 - INFO - codeparrot_training - Step 173: {'lr': 4.325e-05, 'samples': 89088, 'steps': 173, 'loss/train': 7.6018571853637695}
-03/03/2022 13:06:20 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/03/2022 13:06:24 - INFO - codeparrot_training - Step 174: {'lr': 4.35e-05, 'samples': 89600, 'steps': 174, 'loss/train': 7.9183549880981445}
-03/03/2022 13:06:27 - INFO - codeparrot_training - Step 175: {'lr': 4.375e-05, 'samples': 90112, 'steps': 175, 'loss/train': 7.391948699951172}
-03/03/2022 13:06:28 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/03/2022 13:06:32 - INFO - codeparrot_training - Step 176: {'lr': 4.4e-05, 'samples': 90624, 'steps': 176, 'loss/train': 7.670172691345215}
-03/03/2022 13:06:35 - INFO - codeparrot_training - Step 177: {'lr': 4.425e-05, 'samples': 91136, 'steps': 177, 'loss/train': 7.4225029945373535}
-03/03/2022 13:06:37 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/03/2022 13:06:41 - INFO - codeparrot_training - Step 178: {'lr': 4.45e-05, 'samples': 91648, 'steps': 178, 'loss/train': 7.456734657287598}
-03/03/2022 13:06:44 - INFO - codeparrot_training - Step 179: {'lr': 4.475e-05, 'samples': 92160, 'steps': 179, 'loss/train': 8.120655059814453}
-03/03/2022 13:06:45 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/03/2022 13:06:49 - INFO - codeparrot_training - Step 180: {'lr': 4.4999999999999996e-05, 'samples': 92672, 'steps': 180, 'loss/train': 7.598281383514404}
-03/03/2022 13:06:52 - INFO - codeparrot_training - Step 181: {'lr': 4.525e-05, 'samples': 93184, 'steps': 181, 'loss/train': 8.022689819335938}
-03/03/2022 13:06:54 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/03/2022 13:06:58 - INFO - codeparrot_training - Step 182: {'lr': 4.55e-05, 'samples': 93696, 'steps': 182, 'loss/train': 7.102559566497803}
-03/03/2022 13:07:01 - INFO - codeparrot_training - Step 183: {'lr': 4.575e-05, 'samples': 94208, 'steps': 183, 'loss/train': 5.537654876708984}
-03/03/2022 13:07:03 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/03/2022 13:07:07 - INFO - codeparrot_training - Step 184: {'lr': 4.6e-05, 'samples': 94720, 'steps': 184, 'loss/train': 7.378385066986084}
-03/03/2022 13:07:10 - INFO - codeparrot_training - Step 185: {'lr': 4.625e-05, 'samples': 95232, 'steps': 185, 'loss/train': 7.413166046142578}
-03/03/2022 13:07:11 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/03/2022 13:07:15 - INFO - codeparrot_training - Step 186: {'lr': 4.65e-05, 'samples': 95744, 'steps': 186, 'loss/train': 7.445736885070801}
-03/03/2022 13:07:18 - INFO - codeparrot_training - Step 187: {'lr': 4.675e-05, 'samples': 96256, 'steps': 187, 'loss/train': 8.496750831604004}
-03/03/2022 13:07:19 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/03/2022 13:07:24 - INFO - codeparrot_training - Step 188: {'lr': 4.7000000000000004e-05, 'samples': 96768, 'steps': 188, 'loss/train': 7.747251033782959}
-03/03/2022 13:07:27 - INFO - codeparrot_training - Step 189: {'lr': 4.725e-05, 'samples': 97280, 'steps': 189, 'loss/train': 7.649470806121826}
-03/03/2022 13:07:28 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/03/2022 13:07:32 - INFO - codeparrot_training - Step 190: {'lr': 4.75e-05, 'samples': 97792, 'steps': 190, 'loss/train': 7.644663333892822}
-03/03/2022 13:07:35 - INFO - codeparrot_training - Step 191: {'lr': 4.775e-05, 'samples': 98304, 'steps': 191, 'loss/train': 8.062586784362793}
-03/03/2022 13:07:36 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/03/2022 13:07:40 - INFO - codeparrot_training - Step 192: {'lr': 4.8e-05, 'samples': 98816, 'steps': 192, 'loss/train': 7.344707489013672}
-03/03/2022 13:07:44 - INFO - codeparrot_training - Step 193: {'lr': 4.825e-05, 'samples': 99328, 'steps': 193, 'loss/train': 8.712090492248535}
-03/03/2022 13:07:44 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/03/2022 13:07:49 - INFO - codeparrot_training - Step 194: {'lr': 4.85e-05, 'samples': 99840, 'steps': 194, 'loss/train': 8.00727653503418}
-03/03/2022 13:07:52 - INFO - codeparrot_training - Step 195: {'lr': 4.8750000000000006e-05, 'samples': 100352, 'steps': 195, 'loss/train': 6.896945953369141}
-03/03/2022 13:07:52 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/03/2022 13:07:57 - INFO - codeparrot_training - Step 196: {'lr': 4.9000000000000005e-05, 'samples': 100864, 'steps': 196, 'loss/train': 7.245913028717041}
-03/03/2022 13:08:01 - INFO - codeparrot_training - Step 197: {'lr': 4.9250000000000004e-05, 'samples': 101376, 'steps': 197, 'loss/train': 7.287005424499512}
-03/03/2022 13:08:01 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/03/2022 13:08:06 - INFO - codeparrot_training - Step 198: {'lr': 4.9500000000000004e-05, 'samples': 101888, 'steps': 198, 'loss/train': 7.7306318283081055}
-03/03/2022 13:08:09 - INFO - codeparrot_training - Step 199: {'lr': 4.975e-05, 'samples': 102400, 'steps': 199, 'loss/train': 7.501760005950928}
-03/03/2022 13:08:09 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/03/2022 13:08:14 - INFO - codeparrot_training - Step 200: {'lr': 5e-05, 'samples': 102912, 'steps': 200, 'loss/train': 7.2059173583984375}
-03/03/2022 13:08:17 - INFO - codeparrot_training - Step 201: {'lr': 5.025e-05, 'samples': 103424, 'steps': 201, 'loss/train': 7.545304775238037}
-03/03/2022 13:08:18 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/03/2022 13:08:23 - INFO - codeparrot_training - Step 202: {'lr': 5.05e-05, 'samples': 103936, 'steps': 202, 'loss/train': 6.92850923538208}
-03/03/2022 13:08:26 - INFO - codeparrot_training - Step 203: {'lr': 5.075000000000001e-05, 'samples': 104448, 'steps': 203, 'loss/train': 7.187972068786621}
-03/03/2022 13:08:26 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/03/2022 13:08:31 - INFO - codeparrot_training - Step 204: {'lr': 5.1e-05, 'samples': 104960, 'steps': 204, 'loss/train': 7.582147121429443}
-03/03/2022 13:08:35 - INFO - codeparrot_training - Step 205: {'lr': 5.125e-05, 'samples': 105472, 'steps': 205, 'loss/train': 9.222358703613281}
-03/03/2022 13:08:35 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/03/2022 13:08:40 - INFO - codeparrot_training - Step 206: {'lr': 5.15e-05, 'samples': 105984, 'steps': 206, 'loss/train': 7.789576530456543}
-03/03/2022 13:08:43 - INFO - codeparrot_training - Step 207: {'lr': 5.175e-05, 'samples': 106496, 'steps': 207, 'loss/train': 7.880443572998047}
-03/03/2022 13:08:44 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/03/2022 13:08:48 - INFO - codeparrot_training - Step 208: {'lr': 5.2e-05, 'samples': 107008, 'steps': 208, 'loss/train': 7.160046100616455}
-03/03/2022 13:08:52 - INFO - codeparrot_training - Step 209: {'lr': 5.2249999999999996e-05, 'samples': 107520, 'steps': 209, 'loss/train': 8.04822063446045}
-03/03/2022 13:08:52 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/03/2022 13:08:57 - INFO - codeparrot_training - Step 210: {'lr': 5.25e-05, 'samples': 108032, 'steps': 210, 'loss/train': 7.374578475952148}
-03/03/2022 13:09:00 - INFO - codeparrot_training - Step 211: {'lr': 5.275e-05, 'samples': 108544, 'steps': 211, 'loss/train': 7.502261638641357}
-03/03/2022 13:09:00 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/03/2022 13:09:05 - INFO - codeparrot_training - Step 212: {'lr': 5.3e-05, 'samples': 109056, 'steps': 212, 'loss/train': 7.538562297821045}
-03/03/2022 13:09:09 - INFO - codeparrot_training - Step 213: {'lr': 5.325e-05, 'samples': 109568, 'steps': 213, 'loss/train': 8.062139511108398}
-03/03/2022 13:09:09 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/03/2022 13:09:14 - INFO - codeparrot_training - Step 214: {'lr': 5.35e-05, 'samples': 110080, 'steps': 214, 'loss/train': 7.754930019378662}
-03/03/2022 13:09:17 - INFO - codeparrot_training - Step 215: {'lr': 5.375e-05, 'samples': 110592, 'steps': 215, 'loss/train': 7.983520030975342}
-03/03/2022 13:09:17 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/03/2022 13:09:22 - INFO - codeparrot_training - Step 216: {'lr': 5.4e-05, 'samples': 111104, 'steps': 216, 'loss/train': 7.068185329437256}
-03/03/2022 13:09:25 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/03/2022 13:09:28 - INFO - codeparrot_training - Step 217: {'lr': 5.4250000000000004e-05, 'samples': 111616, 'steps': 217, 'loss/train': 7.8822760581970215}
-03/03/2022 13:09:31 - INFO - codeparrot_training - Step 218: {'lr': 5.45e-05, 'samples': 112128, 'steps': 218, 'loss/train': 7.853682518005371}
-03/03/2022 13:09:34 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/03/2022 13:09:36 - INFO - codeparrot_training - Step 219: {'lr': 5.475e-05, 'samples': 112640, 'steps': 219, 'loss/train': 7.099795818328857}
-03/03/2022 13:09:39 - INFO - codeparrot_training - Step 220: {'lr': 5.5e-05, 'samples': 113152, 'steps': 220, 'loss/train': 7.336885929107666}
-03/03/2022 13:09:42 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/03/2022 13:09:45 - INFO - codeparrot_training - Step 221: {'lr': 5.525e-05, 'samples': 113664, 'steps': 221, 'loss/train': 7.086932182312012}
-03/03/2022 13:09:48 - INFO - codeparrot_training - Step 222: {'lr': 5.55e-05, 'samples': 114176, 'steps': 222, 'loss/train': 7.5683746337890625}
-03/03/2022 13:09:51 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/03/2022 13:09:53 - INFO - codeparrot_training - Step 223: {'lr': 5.575e-05, 'samples': 114688, 'steps': 223, 'loss/train': 6.692105770111084}
-03/03/2022 13:09:56 - INFO - codeparrot_training - Step 224: {'lr': 5.6e-05, 'samples': 115200, 'steps': 224, 'loss/train': 7.558428764343262}
-03/03/2022 13:09:59 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/03/2022 13:10:02 - INFO - codeparrot_training - Step 225: {'lr': 5.6250000000000005e-05, 'samples': 115712, 'steps': 225, 'loss/train': 7.024529457092285}
-03/03/2022 13:10:05 - INFO - codeparrot_training - Step 226: {'lr': 5.6500000000000005e-05, 'samples': 116224, 'steps': 226, 'loss/train': 7.132439613342285}
-03/03/2022 13:10:07 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/03/2022 13:10:10 - INFO - codeparrot_training - Step 227: {'lr': 5.6750000000000004e-05, 'samples': 116736, 'steps': 227, 'loss/train': 7.505816459655762}
-03/03/2022 13:10:13 - INFO - codeparrot_training - Step 228: {'lr': 5.7e-05, 'samples': 117248, 'steps': 228, 'loss/train': 7.923880100250244}
-03/03/2022 13:10:16 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/03/2022 13:10:19 - INFO - codeparrot_training - Step 229: {'lr': 5.725e-05, 'samples': 117760, 'steps': 229, 'loss/train': 8.218132019042969}
-03/03/2022 13:10:22 - INFO - codeparrot_training - Step 230: {'lr': 5.75e-05, 'samples': 118272, 'steps': 230, 'loss/train': 6.376003742218018}
-03/03/2022 13:10:24 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/03/2022 13:10:28 - INFO - codeparrot_training - Step 231: {'lr': 5.775e-05, 'samples': 118784, 'steps': 231, 'loss/train': 7.3082990646362305}
-03/03/2022 13:10:31 - INFO - codeparrot_training - Step 232: {'lr': 5.800000000000001e-05, 'samples': 119296, 'steps': 232, 'loss/train': 7.335635662078857}
-03/03/2022 13:10:34 - INFO - codeparrot_training - Step 233: {'lr': 5.8250000000000006e-05, 'samples': 119808, 'steps': 233, 'loss/train': 6.83720064163208}
-03/03/2022 13:10:34 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/03/2022 13:10:40 - INFO - codeparrot_training - Step 234: {'lr': 5.8500000000000006e-05, 'samples': 120320, 'steps': 234, 'loss/train': 6.864739894866943}
-03/03/2022 13:10:43 - INFO - codeparrot_training - Step 235: {'lr': 5.875e-05, 'samples': 120832, 'steps': 235, 'loss/train': 8.335467338562012}
-03/03/2022 13:10:43 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 13:10:48 - INFO - codeparrot_training - Step 236: {'lr': 5.9e-05, 'samples': 121344, 'steps': 236, 'loss/train': 6.926678657531738}
-03/03/2022 13:10:51 - INFO - codeparrot_training - Step 237: {'lr': 5.925e-05, 'samples': 121856, 'steps': 237, 'loss/train': 6.76780891418457}
-03/03/2022 13:10:51 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/03/2022 13:10:56 - INFO - codeparrot_training - Step 238: {'lr': 5.9499999999999996e-05, 'samples': 122368, 'steps': 238, 'loss/train': 7.604316711425781}
-03/03/2022 13:11:00 - INFO - codeparrot_training - Step 239: {'lr': 5.9749999999999995e-05, 'samples': 122880, 'steps': 239, 'loss/train': 7.477373123168945}
-03/03/2022 13:11:00 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/03/2022 13:11:05 - INFO - codeparrot_training - Step 240: {'lr': 6e-05, 'samples': 123392, 'steps': 240, 'loss/train': 6.324827671051025}
-03/03/2022 13:11:08 - INFO - codeparrot_training - Step 241: {'lr': 6.025e-05, 'samples': 123904, 'steps': 241, 'loss/train': 7.703766822814941}
-03/03/2022 13:11:08 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/03/2022 13:11:13 - INFO - codeparrot_training - Step 242: {'lr': 6.05e-05, 'samples': 124416, 'steps': 242, 'loss/train': 7.568194389343262}
-03/03/2022 13:11:16 - INFO - codeparrot_training - Step 243: {'lr': 6.075e-05, 'samples': 124928, 'steps': 243, 'loss/train': 7.032049655914307}
-03/03/2022 13:11:17 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/03/2022 13:11:22 - INFO - codeparrot_training - Step 244: {'lr': 6.1e-05, 'samples': 125440, 'steps': 244, 'loss/train': 7.975718021392822}
-03/03/2022 13:11:25 - INFO - codeparrot_training - Step 245: {'lr': 6.125e-05, 'samples': 125952, 'steps': 245, 'loss/train': 9.234091758728027}
-03/03/2022 13:11:26 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/03/2022 13:11:30 - INFO - codeparrot_training - Step 246: {'lr': 6.15e-05, 'samples': 126464, 'steps': 246, 'loss/train': 7.30528450012207}
-03/03/2022 13:11:33 - INFO - codeparrot_training - Step 247: {'lr': 6.175e-05, 'samples': 126976, 'steps': 247, 'loss/train': 7.250826835632324}
-03/03/2022 13:11:34 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/03/2022 13:11:39 - INFO - codeparrot_training - Step 248: {'lr': 6.2e-05, 'samples': 127488, 'steps': 248, 'loss/train': 7.167181968688965}
-03/03/2022 13:11:42 - INFO - codeparrot_training - Step 249: {'lr': 6.225e-05, 'samples': 128000, 'steps': 249, 'loss/train': 7.492107391357422}
-03/03/2022 13:11:42 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/03/2022 13:11:47 - INFO - codeparrot_training - Step 250: {'lr': 6.25e-05, 'samples': 128512, 'steps': 250, 'loss/train': 7.4001617431640625}
-03/03/2022 13:11:50 - INFO - codeparrot_training - Step 251: {'lr': 6.275000000000001e-05, 'samples': 129024, 'steps': 251, 'loss/train': 7.7985920906066895}
-03/03/2022 13:11:51 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/03/2022 13:11:56 - INFO - codeparrot_training - Step 252: {'lr': 6.3e-05, 'samples': 129536, 'steps': 252, 'loss/train': 7.012681007385254}
-03/03/2022 13:11:59 - INFO - codeparrot_training - Step 253: {'lr': 6.325e-05, 'samples': 130048, 'steps': 253, 'loss/train': 7.037346839904785}
-03/03/2022 13:11:59 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/03/2022 13:12:04 - INFO - codeparrot_training - Step 254: {'lr': 6.35e-05, 'samples': 130560, 'steps': 254, 'loss/train': 6.874361991882324}
-03/03/2022 13:12:07 - INFO - codeparrot_training - Step 255: {'lr': 6.375e-05, 'samples': 131072, 'steps': 255, 'loss/train': 8.25483512878418}
-03/03/2022 13:12:08 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/03/2022 13:12:12 - INFO - codeparrot_training - Step 256: {'lr': 6.4e-05, 'samples': 131584, 'steps': 256, 'loss/train': 7.541172981262207}
-03/03/2022 13:12:16 - INFO - codeparrot_training - Step 257: {'lr': 6.425e-05, 'samples': 132096, 'steps': 257, 'loss/train': 7.457941055297852}
-03/03/2022 13:12:16 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/03/2022 13:12:21 - INFO - codeparrot_training - Step 258: {'lr': 6.450000000000001e-05, 'samples': 132608, 'steps': 258, 'loss/train': 7.014778137207031}
-03/03/2022 13:12:24 - INFO - codeparrot_training - Step 259: {'lr': 6.475e-05, 'samples': 133120, 'steps': 259, 'loss/train': 6.806115627288818}
-03/03/2022 13:12:24 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/03/2022 13:12:29 - INFO - codeparrot_training - Step 260: {'lr': 6.500000000000001e-05, 'samples': 133632, 'steps': 260, 'loss/train': 7.267054557800293}
-03/03/2022 13:12:32 - INFO - codeparrot_training - Step 261: {'lr': 6.525e-05, 'samples': 134144, 'steps': 261, 'loss/train': 6.713515758514404}
-03/03/2022 13:12:33 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/03/2022 13:12:38 - INFO - codeparrot_training - Step 262: {'lr': 6.55e-05, 'samples': 134656, 'steps': 262, 'loss/train': 7.091745853424072}
-03/03/2022 13:12:41 - INFO - codeparrot_training - Step 263: {'lr': 6.575e-05, 'samples': 135168, 'steps': 263, 'loss/train': 7.467846393585205}
-03/03/2022 13:12:41 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/03/2022 13:12:46 - INFO - codeparrot_training - Step 264: {'lr': 6.6e-05, 'samples': 135680, 'steps': 264, 'loss/train': 6.91502046585083}
-03/03/2022 13:12:49 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/03/2022 13:12:51 - INFO - codeparrot_training - Step 265: {'lr': 6.625000000000001e-05, 'samples': 136192, 'steps': 265, 'loss/train': 6.923452854156494}
-03/03/2022 13:12:55 - INFO - codeparrot_training - Step 266: {'lr': 6.65e-05, 'samples': 136704, 'steps': 266, 'loss/train': 7.499436378479004}
-03/03/2022 13:12:57 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/03/2022 13:13:00 - INFO - codeparrot_training - Step 267: {'lr': 6.675000000000001e-05, 'samples': 137216, 'steps': 267, 'loss/train': 7.343801975250244}
-03/03/2022 13:13:03 - INFO - codeparrot_training - Step 268: {'lr': 6.7e-05, 'samples': 137728, 'steps': 268, 'loss/train': 7.012816905975342}
-03/03/2022 13:13:06 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 13:13:08 - INFO - codeparrot_training - Step 269: {'lr': 6.725000000000001e-05, 'samples': 138240, 'steps': 269, 'loss/train': 7.881154537200928}
-03/03/2022 13:13:12 - INFO - codeparrot_training - Step 270: {'lr': 6.75e-05, 'samples': 138752, 'steps': 270, 'loss/train': 7.508479118347168}
-03/03/2022 13:13:14 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/03/2022 13:13:17 - INFO - codeparrot_training - Step 271: {'lr': 6.775000000000001e-05, 'samples': 139264, 'steps': 271, 'loss/train': 6.856858730316162}
-03/03/2022 13:13:20 - INFO - codeparrot_training - Step 272: {'lr': 6.800000000000001e-05, 'samples': 139776, 'steps': 272, 'loss/train': 7.2710041999816895}
-03/03/2022 13:13:23 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/03/2022 13:13:26 - INFO - codeparrot_training - Step 273: {'lr': 6.825e-05, 'samples': 140288, 'steps': 273, 'loss/train': 6.965377330780029}
-03/03/2022 13:13:29 - INFO - codeparrot_training - Step 274: {'lr': 6.850000000000001e-05, 'samples': 140800, 'steps': 274, 'loss/train': 6.166491985321045}
-03/03/2022 13:13:32 - INFO - codeparrot_training - Step 275: {'lr': 6.875e-05, 'samples': 141312, 'steps': 275, 'loss/train': 7.818729877471924}
-03/03/2022 13:13:34 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/03/2022 13:13:38 - INFO - codeparrot_training - Step 276: {'lr': 6.900000000000001e-05, 'samples': 141824, 'steps': 276, 'loss/train': 6.974045753479004}
-03/03/2022 13:13:41 - INFO - codeparrot_training - Step 277: {'lr': 6.925e-05, 'samples': 142336, 'steps': 277, 'loss/train': 6.823301792144775}
-03/03/2022 13:13:43 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/03/2022 13:13:46 - INFO - codeparrot_training - Step 278: {'lr': 6.950000000000001e-05, 'samples': 142848, 'steps': 278, 'loss/train': 7.374868392944336}
-03/03/2022 13:13:50 - INFO - codeparrot_training - Step 279: {'lr': 6.975e-05, 'samples': 143360, 'steps': 279, 'loss/train': 7.211111068725586}
-03/03/2022 13:13:51 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/03/2022 13:13:55 - INFO - codeparrot_training - Step 280: {'lr': 7.000000000000001e-05, 'samples': 143872, 'steps': 280, 'loss/train': 7.095859527587891}
-03/03/2022 13:13:58 - INFO - codeparrot_training - Step 281: {'lr': 7.025000000000001e-05, 'samples': 144384, 'steps': 281, 'loss/train': 6.3933634757995605}
-03/03/2022 13:14:00 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 13:14:04 - INFO - codeparrot_training - Step 282: {'lr': 7.049999999999999e-05, 'samples': 144896, 'steps': 282, 'loss/train': 8.225425720214844}
-03/03/2022 13:14:07 - INFO - codeparrot_training - Step 283: {'lr': 7.075e-05, 'samples': 145408, 'steps': 283, 'loss/train': 6.789872646331787}
-03/03/2022 13:14:08 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/03/2022 13:14:12 - INFO - codeparrot_training - Step 284: {'lr': 7.099999999999999e-05, 'samples': 145920, 'steps': 284, 'loss/train': 7.208834171295166}
-03/03/2022 13:14:15 - INFO - codeparrot_training - Step 285: {'lr': 7.125e-05, 'samples': 146432, 'steps': 285, 'loss/train': 5.778796672821045}
-03/03/2022 13:14:17 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/03/2022 13:14:21 - INFO - codeparrot_training - Step 286: {'lr': 7.149999999999999e-05, 'samples': 146944, 'steps': 286, 'loss/train': 6.7907490730285645}
-03/03/2022 13:14:24 - INFO - codeparrot_training - Step 287: {'lr': 7.175e-05, 'samples': 147456, 'steps': 287, 'loss/train': 6.667514801025391}
-03/03/2022 13:14:25 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/03/2022 13:14:29 - INFO - codeparrot_training - Step 288: {'lr': 7.2e-05, 'samples': 147968, 'steps': 288, 'loss/train': 7.220056533813477}
-03/03/2022 13:14:32 - INFO - codeparrot_training - Step 289: {'lr': 7.225e-05, 'samples': 148480, 'steps': 289, 'loss/train': 6.969030380249023}
-03/03/2022 13:14:33 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/03/2022 13:14:37 - INFO - codeparrot_training - Step 290: {'lr': 7.25e-05, 'samples': 148992, 'steps': 290, 'loss/train': 7.167079925537109}
-03/03/2022 13:14:41 - INFO - codeparrot_training - Step 291: {'lr': 7.274999999999999e-05, 'samples': 149504, 'steps': 291, 'loss/train': 7.262547016143799}
-03/03/2022 13:14:42 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/03/2022 13:14:46 - INFO - codeparrot_training - Step 292: {'lr': 7.3e-05, 'samples': 150016, 'steps': 292, 'loss/train': 7.280813694000244}
-03/03/2022 13:14:49 - INFO - codeparrot_training - Step 293: {'lr': 7.324999999999999e-05, 'samples': 150528, 'steps': 293, 'loss/train': 6.34620475769043}
-03/03/2022 13:14:50 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/03/2022 13:14:54 - INFO - codeparrot_training - Step 294: {'lr': 7.35e-05, 'samples': 151040, 'steps': 294, 'loss/train': 7.634270191192627}
-03/03/2022 13:14:58 - INFO - codeparrot_training - Step 295: {'lr': 7.375e-05, 'samples': 151552, 'steps': 295, 'loss/train': 4.9720330238342285}
-03/03/2022 13:15:00 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/03/2022 13:15:03 - INFO - codeparrot_training - Step 296: {'lr': 7.4e-05, 'samples': 152064, 'steps': 296, 'loss/train': 7.290252208709717}
-03/03/2022 13:15:06 - INFO - codeparrot_training - Step 297: {'lr': 7.425e-05, 'samples': 152576, 'steps': 297, 'loss/train': 7.179178237915039}
-03/03/2022 13:15:08 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/03/2022 13:15:11 - INFO - codeparrot_training - Step 298: {'lr': 7.45e-05, 'samples': 153088, 'steps': 298, 'loss/train': 8.177205085754395}
-03/03/2022 13:15:14 - INFO - codeparrot_training - Step 299: {'lr': 7.475e-05, 'samples': 153600, 'steps': 299, 'loss/train': 7.102594375610352}
-03/03/2022 13:15:16 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/03/2022 13:15:20 - INFO - codeparrot_training - Step 300: {'lr': 7.5e-05, 'samples': 154112, 'steps': 300, 'loss/train': 7.6582746505737305}
-03/03/2022 13:15:23 - INFO - codeparrot_training - Step 301: {'lr': 7.525e-05, 'samples': 154624, 'steps': 301, 'loss/train': 3.4812848567962646}
-03/03/2022 13:15:24 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/03/2022 13:15:28 - INFO - codeparrot_training - Step 302: {'lr': 7.55e-05, 'samples': 155136, 'steps': 302, 'loss/train': 6.857351779937744}
-03/03/2022 13:15:31 - INFO - codeparrot_training - Step 303: {'lr': 7.575e-05, 'samples': 155648, 'steps': 303, 'loss/train': 7.291689395904541}
-03/03/2022 13:15:32 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/03/2022 13:15:37 - INFO - codeparrot_training - Step 304: {'lr': 7.6e-05, 'samples': 156160, 'steps': 304, 'loss/train': 7.73492431640625}
-03/03/2022 13:15:40 - INFO - codeparrot_training - Step 305: {'lr': 7.625e-05, 'samples': 156672, 'steps': 305, 'loss/train': 7.737000942230225}
-03/03/2022 13:15:41 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/03/2022 13:15:45 - INFO - codeparrot_training - Step 306: {'lr': 7.65e-05, 'samples': 157184, 'steps': 306, 'loss/train': 6.85874605178833}
-03/03/2022 13:15:48 - INFO - codeparrot_training - Step 307: {'lr': 7.675e-05, 'samples': 157696, 'steps': 307, 'loss/train': 6.972065448760986}
-03/03/2022 13:15:50 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/03/2022 13:15:54 - INFO - codeparrot_training - Step 308: {'lr': 7.7e-05, 'samples': 158208, 'steps': 308, 'loss/train': 7.307086944580078}
-03/03/2022 13:15:57 - INFO - codeparrot_training - Step 309: {'lr': 7.725000000000001e-05, 'samples': 158720, 'steps': 309, 'loss/train': 7.4384050369262695}
-03/03/2022 13:15:58 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 13:16:02 - INFO - codeparrot_training - Step 310: {'lr': 7.75e-05, 'samples': 159232, 'steps': 310, 'loss/train': 7.601604461669922}
-03/03/2022 13:16:05 - INFO - codeparrot_training - Step 311: {'lr': 7.775e-05, 'samples': 159744, 'steps': 311, 'loss/train': 7.247878551483154}
-03/03/2022 13:16:06 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/03/2022 13:16:11 - INFO - codeparrot_training - Step 312: {'lr': 7.8e-05, 'samples': 160256, 'steps': 312, 'loss/train': 6.91134786605835}
-03/03/2022 13:16:14 - INFO - codeparrot_training - Step 313: {'lr': 7.825e-05, 'samples': 160768, 'steps': 313, 'loss/train': 7.499279499053955}
-03/03/2022 13:16:14 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/03/2022 13:16:19 - INFO - codeparrot_training - Step 314: {'lr': 7.85e-05, 'samples': 161280, 'steps': 314, 'loss/train': 7.371830463409424}
-03/03/2022 13:16:22 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/03/2022 13:16:25 - INFO - codeparrot_training - Step 315: {'lr': 7.875e-05, 'samples': 161792, 'steps': 315, 'loss/train': 7.107333660125732}
-03/03/2022 13:16:28 - INFO - codeparrot_training - Step 316: {'lr': 7.9e-05, 'samples': 162304, 'steps': 316, 'loss/train': 8.673299789428711}
-03/03/2022 13:16:31 - INFO - codeparrot_training - Step 317: {'lr': 7.925e-05, 'samples': 162816, 'steps': 317, 'loss/train': 7.807727813720703}
-03/03/2022 13:16:32 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/03/2022 13:16:36 - INFO - codeparrot_training - Step 318: {'lr': 7.950000000000001e-05, 'samples': 163328, 'steps': 318, 'loss/train': 7.118139266967773}
-03/03/2022 13:16:40 - INFO - codeparrot_training - Step 319: {'lr': 7.975e-05, 'samples': 163840, 'steps': 319, 'loss/train': 7.224991321563721}
-03/03/2022 13:16:41 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/03/2022 13:16:45 - INFO - codeparrot_training - Step 320: {'lr': 8e-05, 'samples': 164352, 'steps': 320, 'loss/train': 7.151127338409424}
-03/03/2022 13:16:48 - INFO - codeparrot_training - Step 321: {'lr': 8.025e-05, 'samples': 164864, 'steps': 321, 'loss/train': 6.802467346191406}
-03/03/2022 13:16:49 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/03/2022 13:16:53 - INFO - codeparrot_training - Step 322: {'lr': 8.05e-05, 'samples': 165376, 'steps': 322, 'loss/train': 7.11800479888916}
-03/03/2022 13:16:56 - INFO - codeparrot_training - Step 323: {'lr': 8.075e-05, 'samples': 165888, 'steps': 323, 'loss/train': 6.9256367683410645}
-03/03/2022 13:16:57 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/03/2022 13:17:02 - INFO - codeparrot_training - Step 324: {'lr': 8.1e-05, 'samples': 166400, 'steps': 324, 'loss/train': 5.947310924530029}
-03/03/2022 13:17:05 - INFO - codeparrot_training - Step 325: {'lr': 8.125000000000001e-05, 'samples': 166912, 'steps': 325, 'loss/train': 7.745260238647461}
-03/03/2022 13:17:07 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/03/2022 13:17:10 - INFO - codeparrot_training - Step 326: {'lr': 8.15e-05, 'samples': 167424, 'steps': 326, 'loss/train': 6.477266311645508}
-03/03/2022 13:17:13 - INFO - codeparrot_training - Step 327: {'lr': 8.175000000000001e-05, 'samples': 167936, 'steps': 327, 'loss/train': 7.103150844573975}
-03/03/2022 13:17:15 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/03/2022 13:17:19 - INFO - codeparrot_training - Step 328: {'lr': 8.2e-05, 'samples': 168448, 'steps': 328, 'loss/train': 7.210000991821289}
-03/03/2022 13:17:22 - INFO - codeparrot_training - Step 329: {'lr': 8.225000000000001e-05, 'samples': 168960, 'steps': 329, 'loss/train': 5.856969833374023}
-03/03/2022 13:17:23 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/03/2022 13:17:27 - INFO - codeparrot_training - Step 330: {'lr': 8.25e-05, 'samples': 169472, 'steps': 330, 'loss/train': 7.112217426300049}
-03/03/2022 13:17:30 - INFO - codeparrot_training - Step 331: {'lr': 8.275e-05, 'samples': 169984, 'steps': 331, 'loss/train': 7.2972517013549805}
-03/03/2022 13:17:32 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/03/2022 13:17:36 - INFO - codeparrot_training - Step 332: {'lr': 8.300000000000001e-05, 'samples': 170496, 'steps': 332, 'loss/train': 6.872681140899658}
-03/03/2022 13:17:39 - INFO - codeparrot_training - Step 333: {'lr': 8.325e-05, 'samples': 171008, 'steps': 333, 'loss/train': 6.879507064819336}
-03/03/2022 13:17:40 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/03/2022 13:17:44 - INFO - codeparrot_training - Step 334: {'lr': 8.350000000000001e-05, 'samples': 171520, 'steps': 334, 'loss/train': 7.25621223449707}
-03/03/2022 13:17:47 - INFO - codeparrot_training - Step 335: {'lr': 8.375e-05, 'samples': 172032, 'steps': 335, 'loss/train': 6.667304515838623}
-03/03/2022 13:17:48 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/03/2022 13:17:52 - INFO - codeparrot_training - Step 336: {'lr': 8.400000000000001e-05, 'samples': 172544, 'steps': 336, 'loss/train': 7.273214817047119}
-03/03/2022 13:17:56 - INFO - codeparrot_training - Step 337: {'lr': 8.425e-05, 'samples': 173056, 'steps': 337, 'loss/train': 7.189443588256836}
-03/03/2022 13:17:56 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/03/2022 13:18:01 - INFO - codeparrot_training - Step 338: {'lr': 8.450000000000001e-05, 'samples': 173568, 'steps': 338, 'loss/train': 6.605391025543213}
-03/03/2022 13:18:04 - INFO - codeparrot_training - Step 339: {'lr': 8.475000000000001e-05, 'samples': 174080, 'steps': 339, 'loss/train': 6.908782005310059}
-03/03/2022 13:18:05 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/03/2022 13:18:09 - INFO - codeparrot_training - Step 340: {'lr': 8.5e-05, 'samples': 174592, 'steps': 340, 'loss/train': 6.747285842895508}
-03/03/2022 13:18:12 - INFO - codeparrot_training - Step 341: {'lr': 8.525000000000001e-05, 'samples': 175104, 'steps': 341, 'loss/train': 6.820441246032715}
-03/03/2022 13:18:13 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/03/2022 13:18:18 - INFO - codeparrot_training - Step 342: {'lr': 8.55e-05, 'samples': 175616, 'steps': 342, 'loss/train': 7.335867404937744}
-03/03/2022 13:18:21 - INFO - codeparrot_training - Step 343: {'lr': 8.575000000000001e-05, 'samples': 176128, 'steps': 343, 'loss/train': 6.804535388946533}
-03/03/2022 13:18:22 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/03/2022 13:18:26 - INFO - codeparrot_training - Step 344: {'lr': 8.599999999999999e-05, 'samples': 176640, 'steps': 344, 'loss/train': 7.3406500816345215}
-03/03/2022 13:18:29 - INFO - codeparrot_training - Step 345: {'lr': 8.625e-05, 'samples': 177152, 'steps': 345, 'loss/train': 6.626857757568359}
-03/03/2022 13:18:30 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/03/2022 13:18:35 - INFO - codeparrot_training - Step 346: {'lr': 8.65e-05, 'samples': 177664, 'steps': 346, 'loss/train': 6.793419361114502}
-03/03/2022 13:18:38 - INFO - codeparrot_training - Step 347: {'lr': 8.675e-05, 'samples': 178176, 'steps': 347, 'loss/train': 6.759413242340088}
-03/03/2022 13:18:38 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/03/2022 13:18:43 - INFO - codeparrot_training - Step 348: {'lr': 8.7e-05, 'samples': 178688, 'steps': 348, 'loss/train': 6.160068035125732}
-03/03/2022 13:18:46 - INFO - codeparrot_training - Step 349: {'lr': 8.724999999999999e-05, 'samples': 179200, 'steps': 349, 'loss/train': 7.11178731918335}
-03/03/2022 13:18:46 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/03/2022 13:18:51 - INFO - codeparrot_training - Step 350: {'lr': 8.75e-05, 'samples': 179712, 'steps': 350, 'loss/train': 6.960474014282227}
-03/03/2022 13:18:54 - INFO - codeparrot_training - Step 351: {'lr': 8.774999999999999e-05, 'samples': 180224, 'steps': 351, 'loss/train': 7.643229961395264}
-03/03/2022 13:18:54 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/03/2022 13:19:00 - INFO - codeparrot_training - Step 352: {'lr': 8.8e-05, 'samples': 180736, 'steps': 352, 'loss/train': 6.8332319259643555}
-03/03/2022 13:19:03 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/03/2022 13:19:05 - INFO - codeparrot_training - Step 353: {'lr': 8.824999999999999e-05, 'samples': 181248, 'steps': 353, 'loss/train': 6.829087734222412}
-03/03/2022 13:19:08 - INFO - codeparrot_training - Step 354: {'lr': 8.85e-05, 'samples': 181760, 'steps': 354, 'loss/train': 6.977699279785156}
-03/03/2022 13:19:11 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/03/2022 13:19:13 - INFO - codeparrot_training - Step 355: {'lr': 8.875e-05, 'samples': 182272, 'steps': 355, 'loss/train': 7.036928653717041}
-03/03/2022 13:19:17 - INFO - codeparrot_training - Step 356: {'lr': 8.9e-05, 'samples': 182784, 'steps': 356, 'loss/train': 6.960824489593506}
-03/03/2022 13:19:19 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/03/2022 13:19:22 - INFO - codeparrot_training - Step 357: {'lr': 8.925e-05, 'samples': 183296, 'steps': 357, 'loss/train': 6.745418071746826}
-03/03/2022 13:19:25 - INFO - codeparrot_training - Step 358: {'lr': 8.95e-05, 'samples': 183808, 'steps': 358, 'loss/train': 6.919394493103027}
-03/03/2022 13:19:28 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/03/2022 13:19:30 - INFO - codeparrot_training - Step 359: {'lr': 8.975e-05, 'samples': 184320, 'steps': 359, 'loss/train': 6.71176815032959}
-03/03/2022 13:19:33 - INFO - codeparrot_training - Step 360: {'lr': 8.999999999999999e-05, 'samples': 184832, 'steps': 360, 'loss/train': 6.548521518707275}
-03/03/2022 13:19:36 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/03/2022 13:19:39 - INFO - codeparrot_training - Step 361: {'lr': 9.025e-05, 'samples': 185344, 'steps': 361, 'loss/train': 7.599088668823242}
-03/03/2022 13:19:42 - INFO - codeparrot_training - Step 362: {'lr': 9.05e-05, 'samples': 185856, 'steps': 362, 'loss/train': 6.143686294555664}
-03/03/2022 13:19:44 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/03/2022 13:19:47 - INFO - codeparrot_training - Step 363: {'lr': 9.075e-05, 'samples': 186368, 'steps': 363, 'loss/train': 7.022943019866943}
-03/03/2022 13:19:50 - INFO - codeparrot_training - Step 364: {'lr': 9.1e-05, 'samples': 186880, 'steps': 364, 'loss/train': 6.801090240478516}
-03/03/2022 13:19:52 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/03/2022 13:19:55 - INFO - codeparrot_training - Step 365: {'lr': 9.125e-05, 'samples': 187392, 'steps': 365, 'loss/train': 6.444828510284424}
-03/03/2022 13:19:59 - INFO - codeparrot_training - Step 366: {'lr': 9.15e-05, 'samples': 187904, 'steps': 366, 'loss/train': 5.071739673614502}
-03/03/2022 13:20:01 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/03/2022 13:20:04 - INFO - codeparrot_training - Step 367: {'lr': 9.175e-05, 'samples': 188416, 'steps': 367, 'loss/train': 7.660885334014893}
-03/03/2022 13:20:07 - INFO - codeparrot_training - Step 368: {'lr': 9.2e-05, 'samples': 188928, 'steps': 368, 'loss/train': 6.027246952056885}
-03/03/2022 13:20:10 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/03/2022 13:21:37 - INFO - codeparrot_training - Distributed environment: TPU
-Num processes: 8
-Process index: 0
-Local process index: 0
-Device: xla:1
-Use FP16 precision: False
-
-03/03/2022 13:21:38 - WARNING - huggingface_hub.repository - Revision `glowing-puddle-3` does not exist. Created and checked out branch `glowing-puddle-3`.
-03/03/2022 13:21:38 - WARNING - huggingface_hub.repository - 
-03/03/2022 13:21:49 - INFO - datasets.data_files - Some files matched the pattern '/home/nathan/codeparrot-clean-train/**' at /home/nathan/codeparrot-clean-train but don't have valid data file extensions: [PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/17/96/1796f12729d0407cc57500c9c87959e0e7becd729f37374702868ed8765015f4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/2e/aa/2eaa21b832ed1496fb7f0b259666dbfc36ed483d81494d1e8705f9d601509c12'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/7c/0e/7c0ef87edb0e556939282c859c7c893a91b5b0f931394ca4cca4f4ec98a61951'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/b6/ce/b6ce495492aedfc91b66efdfd214b2dfe44867c719d51590e1868e42f4e9b6dd'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/5d/42/5d42ba9f195510757a3699005a7c43ddede4b598caf8a5f2f8c84d1125fa6324'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/cd/33/cd339656799518495d23aedf1503459be6d3086e22672e80edab8403d12ded1c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ac/36/ac36d12d37c1dc8ee8d3b8f0eae93966ae73482ef725615bb1a715802ddd4dd4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/packed-refs'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/67/f1/67f1ff0d590fbf4aa9afa161c290fe9be17538d4b723278bb21fd6408b0e6a3e'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/90/a5/90a573501de640c3e0e6f1b3508306febc96faf6061bb33c67894c168a1879c6'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/2f/62/2f628d890bceee216f87edb3c45d2e384ee2501ce41a4c4169efaa3363bef1d2'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/prepare-commit-msg.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/index'), PosixPath('/home/nathan/codeparrot-clean-train/.git/objects/pack/pack-df5296c3b6443e668dc098dc5c59f854d9d79f0f.pack'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/74/31/7431977a8e3a6eb0348b821009495f85d9373c1f730f4a74b0db43326568f77d'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/17/5e/175e7375d6f65993071aa653bdd4e8b117cc02d1d2353cd7bcdbaaf7fe8b3c9c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/d0/02/d0024828eece6d4d1c25cb4e539328be97fa28ce66a3b8d2374a117711cfd520'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/15/ac/15ac016e4cd702bb184457cbf5674d71b632fc34c29611ba4de549b85c67acfb'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/32/be/32beb30e381ff02fb71854b5534306f395ef00f51f02b62da1f027c8c7fab26f'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/9f/7e/9f7e18a3980d4b3d5ed9469ab7a2d67b608e8aa6fff38d876f86719c8f2a7a82'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ee/c1/eec1a9546aac0444a706c09f6aab67cd64403940657417e30212b7ff1e16665c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ac/e3/ace3ac440b380d604ab198cf8e838a2a375e7b0a6b5699ec74a8c79648f4bab8'), PosixPath('/home/nathan/codeparrot-clean-train/.git/description'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-merge-commit.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/60/41/604177fe5560efd99d93091fadab6293afe7cd7d12f81638c301de1c937c1583'), PosixPath('/home/nathan/codeparrot-clean-train/.git/logs/refs/remotes/origin/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/update.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/cc/58/cc58b22515c4fd7d891287ee717c2054290b20c17b1c34693fd8964ab730687b'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/commit-msg.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/56/80/56803c607a19ccb576c90bdb10a02cfa7b3affc67dd150fa41b00cc22213b174'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/14/08/14089cad26037080ee900bede2fd42d5cac70738b2e77402b36681e1d2a521f6'), PosixPath('/home/nathan/codeparrot-clean-train/.git/refs/heads/main'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/f1/a7/f1a7a250e1f6164a7fb602131ff54b69deb305258792f2358075403769d58fe5'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/9b/1b/9b1b8e52b9262f03f1719d3950dc8dfa2b9719dc2e273603023f6f329c1b2068'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ef/e1/efe1759837b74b5b5ed3df1a09d4c880f9ad20413d958f79d35bf1cb6a2a09d4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/54/60/5460223b92bb118814a7777a939f4005b7426a7e4a068c193c10d1b86eeb862b'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-push'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/0b/f3/0bf3cd1320065c163f47a112458dc107650e3e862094b703b76073bd0b68663d'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/12/8d/128d56e09d9d741b2778d733e595838a50a5e82fdc9adbb0aa8645457716b97e'), PosixPath('/home/nathan/codeparrot-clean-train/.git/info/exclude'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-checkout'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/b4/83/b4836655e350f0796acd2b1a206e657c2808d9f136afae095e0b94a790c704e1'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/a4/6b/a46b5c08d39691524b46fadf78eab5efefa29978edfee799ec3587d928dc1302'), PosixPath('/home/nathan/codeparrot-clean-train/.git/logs/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/73/73/737327c2b47693e00050aa3410c5eb402c66211a79740ab57f1c763a1e557563'), PosixPath('/home/nathan/codeparrot-clean-train/.git/config'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/d4/9f/d49f1929644619c39cff677367ff2e18223a8046ec8f61e224954a10aa2ccf8f'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-push.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ae/45/ae45741df674456bc63bad91374d2ba5ef988d33d6e2a322ef0a5ac8af040371'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/e6/48/e6484a578778beccab26c8549608ec13970e6bcdb9541cdccad20f4d984e8181'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/4e/39/4e392fcaae564652d234d07b4f71eeed90efe51b1b714831e39d77f3e537d3df'), PosixPath('/home/nathan/codeparrot-clean-train/.git/objects/pack/pack-df5296c3b6443e668dc098dc5c59f854d9d79f0f.idx'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-commit'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/fsmonitor-watchman.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/5f/d1/5fd1bb56db810b65d1fd3866dc43d9c7b690c8f52b9ca8119b2a5f4c49d13eec'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-applypatch.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/2a/7e/2a7e50bbdb90d6c4cec534c3f1dc7ec0e6a0dada15c07cfd94615940c632ce02'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-rebase.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/55/c9/55c9c0b2f26de96e0311ee43e8eaa78ad1af387d0c59a26f22c5ebd507dda321'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/b6/8a/b68a74f9784402dcb311f4db72a873035e47b98b185a1813ab2c1645cb7255a2'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/e7/a9/e7a9ccbfe6bd92476f83eba205c47ed23732ace4c1bd7458d76d666ebbba3b1c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-commit.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-update.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/dc/ac/dcacb03d8f43f7879c5eab4422644d7b3797b47dbb0c9c84d88cbc85822d8306'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/5a/5f/5a5fbc19e0e76787f668ada7235203c10b0cbcdea0ecf8f873f8ec281cfe3494'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/fa/e6/fae6b44a24c1c35f15053a19a6b2b2af5cc9fb8bdaf0da409068a2a1f333f28e'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/df/08/df0840d1657530c8fa9f82864be5999c515f54341d926c430a82528a6bb83740'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/50/38/503872def2ac44733fbefc2602ab16224caca0896aa1eba045025ef2d60efcdc'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-receive.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/refs/remotes/origin/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-merge'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/f1/62/f162b06b5dca01aa85ef9a675d396c0fbab1d009b5bee1c5b7ea6b415c6f12a4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/0f/7a/0f7a67cd83c1c069995f0f2510ebf818dcc71d9658f189de1231d2b7aac8883c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/86/0e/860eda34e90456533e9dd41a5c0fdb74c54dc8d9cf43d6c60b887b2c858be831'), PosixPath('/home/nathan/codeparrot-clean-train/.git/logs/refs/heads/main'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/05/39/053944e1daead0b6de8e46ea2e0bc68b9247604c63a55d444ac3b9adb12e2cd2'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/55/b6/55b6989a41ae296337356153e6081c61484d0b6734b6905683823e7317d01c42'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/fb/84/fb84ca8000808f62718994e4b44e79d88a05b345e9638d9f6cf6c8a5472da01f'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/37/26/3726a0239b5cb7d0ef3ea36886c533d0becc7404217763015559edb546d53c94'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/applypatch-msg.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/3e/f2/3ef240d0b394384803ae1bbe3b30974e11eb9b1b6ad4f49afc2ed0f7c9eae0d6')]
-03/03/2022 13:21:49 - WARNING - datasets.builder - Using custom data configuration codeparrot-clean-train-86fef7ac9fb06b05
-03/03/2022 13:21:50 - INFO - datasets.data_files - Some files matched the pattern '/home/nathan/codeparrot-clean-train/**' at /home/nathan/codeparrot-clean-train but don't have valid data file extensions: [PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/17/96/1796f12729d0407cc57500c9c87959e0e7becd729f37374702868ed8765015f4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/2e/aa/2eaa21b832ed1496fb7f0b259666dbfc36ed483d81494d1e8705f9d601509c12'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/7c/0e/7c0ef87edb0e556939282c859c7c893a91b5b0f931394ca4cca4f4ec98a61951'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/b6/ce/b6ce495492aedfc91b66efdfd214b2dfe44867c719d51590e1868e42f4e9b6dd'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/5d/42/5d42ba9f195510757a3699005a7c43ddede4b598caf8a5f2f8c84d1125fa6324'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/cd/33/cd339656799518495d23aedf1503459be6d3086e22672e80edab8403d12ded1c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ac/36/ac36d12d37c1dc8ee8d3b8f0eae93966ae73482ef725615bb1a715802ddd4dd4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/packed-refs'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/67/f1/67f1ff0d590fbf4aa9afa161c290fe9be17538d4b723278bb21fd6408b0e6a3e'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/90/a5/90a573501de640c3e0e6f1b3508306febc96faf6061bb33c67894c168a1879c6'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/2f/62/2f628d890bceee216f87edb3c45d2e384ee2501ce41a4c4169efaa3363bef1d2'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/prepare-commit-msg.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/index'), PosixPath('/home/nathan/codeparrot-clean-train/.git/objects/pack/pack-df5296c3b6443e668dc098dc5c59f854d9d79f0f.pack'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/74/31/7431977a8e3a6eb0348b821009495f85d9373c1f730f4a74b0db43326568f77d'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/17/5e/175e7375d6f65993071aa653bdd4e8b117cc02d1d2353cd7bcdbaaf7fe8b3c9c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/d0/02/d0024828eece6d4d1c25cb4e539328be97fa28ce66a3b8d2374a117711cfd520'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/15/ac/15ac016e4cd702bb184457cbf5674d71b632fc34c29611ba4de549b85c67acfb'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/32/be/32beb30e381ff02fb71854b5534306f395ef00f51f02b62da1f027c8c7fab26f'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/9f/7e/9f7e18a3980d4b3d5ed9469ab7a2d67b608e8aa6fff38d876f86719c8f2a7a82'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ee/c1/eec1a9546aac0444a706c09f6aab67cd64403940657417e30212b7ff1e16665c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ac/e3/ace3ac440b380d604ab198cf8e838a2a375e7b0a6b5699ec74a8c79648f4bab8'), PosixPath('/home/nathan/codeparrot-clean-train/.git/description'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-merge-commit.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/60/41/604177fe5560efd99d93091fadab6293afe7cd7d12f81638c301de1c937c1583'), PosixPath('/home/nathan/codeparrot-clean-train/.git/logs/refs/remotes/origin/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/update.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/cc/58/cc58b22515c4fd7d891287ee717c2054290b20c17b1c34693fd8964ab730687b'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/commit-msg.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/56/80/56803c607a19ccb576c90bdb10a02cfa7b3affc67dd150fa41b00cc22213b174'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/14/08/14089cad26037080ee900bede2fd42d5cac70738b2e77402b36681e1d2a521f6'), PosixPath('/home/nathan/codeparrot-clean-train/.git/refs/heads/main'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/f1/a7/f1a7a250e1f6164a7fb602131ff54b69deb305258792f2358075403769d58fe5'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/9b/1b/9b1b8e52b9262f03f1719d3950dc8dfa2b9719dc2e273603023f6f329c1b2068'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ef/e1/efe1759837b74b5b5ed3df1a09d4c880f9ad20413d958f79d35bf1cb6a2a09d4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/54/60/5460223b92bb118814a7777a939f4005b7426a7e4a068c193c10d1b86eeb862b'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-push'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/0b/f3/0bf3cd1320065c163f47a112458dc107650e3e862094b703b76073bd0b68663d'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/12/8d/128d56e09d9d741b2778d733e595838a50a5e82fdc9adbb0aa8645457716b97e'), PosixPath('/home/nathan/codeparrot-clean-train/.git/info/exclude'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-checkout'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/b4/83/b4836655e350f0796acd2b1a206e657c2808d9f136afae095e0b94a790c704e1'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/a4/6b/a46b5c08d39691524b46fadf78eab5efefa29978edfee799ec3587d928dc1302'), PosixPath('/home/nathan/codeparrot-clean-train/.git/logs/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/73/73/737327c2b47693e00050aa3410c5eb402c66211a79740ab57f1c763a1e557563'), PosixPath('/home/nathan/codeparrot-clean-train/.git/config'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/d4/9f/d49f1929644619c39cff677367ff2e18223a8046ec8f61e224954a10aa2ccf8f'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-push.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/ae/45/ae45741df674456bc63bad91374d2ba5ef988d33d6e2a322ef0a5ac8af040371'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/e6/48/e6484a578778beccab26c8549608ec13970e6bcdb9541cdccad20f4d984e8181'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/4e/39/4e392fcaae564652d234d07b4f71eeed90efe51b1b714831e39d77f3e537d3df'), PosixPath('/home/nathan/codeparrot-clean-train/.git/objects/pack/pack-df5296c3b6443e668dc098dc5c59f854d9d79f0f.idx'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-commit'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/fsmonitor-watchman.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/5f/d1/5fd1bb56db810b65d1fd3866dc43d9c7b690c8f52b9ca8119b2a5f4c49d13eec'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-applypatch.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/2a/7e/2a7e50bbdb90d6c4cec534c3f1dc7ec0e6a0dada15c07cfd94615940c632ce02'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-rebase.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/55/c9/55c9c0b2f26de96e0311ee43e8eaa78ad1af387d0c59a26f22c5ebd507dda321'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/b6/8a/b68a74f9784402dcb311f4db72a873035e47b98b185a1813ab2c1645cb7255a2'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/e7/a9/e7a9ccbfe6bd92476f83eba205c47ed23732ace4c1bd7458d76d666ebbba3b1c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-commit.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-update.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/dc/ac/dcacb03d8f43f7879c5eab4422644d7b3797b47dbb0c9c84d88cbc85822d8306'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/5a/5f/5a5fbc19e0e76787f668ada7235203c10b0cbcdea0ecf8f873f8ec281cfe3494'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/fa/e6/fae6b44a24c1c35f15053a19a6b2b2af5cc9fb8bdaf0da409068a2a1f333f28e'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/df/08/df0840d1657530c8fa9f82864be5999c515f54341d926c430a82528a6bb83740'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/50/38/503872def2ac44733fbefc2602ab16224caca0896aa1eba045025ef2d60efcdc'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/pre-receive.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/refs/remotes/origin/HEAD'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/post-merge'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/f1/62/f162b06b5dca01aa85ef9a675d396c0fbab1d009b5bee1c5b7ea6b415c6f12a4'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/0f/7a/0f7a67cd83c1c069995f0f2510ebf818dcc71d9658f189de1231d2b7aac8883c'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/86/0e/860eda34e90456533e9dd41a5c0fdb74c54dc8d9cf43d6c60b887b2c858be831'), PosixPath('/home/nathan/codeparrot-clean-train/.git/logs/refs/heads/main'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/05/39/053944e1daead0b6de8e46ea2e0bc68b9247604c63a55d444ac3b9adb12e2cd2'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/55/b6/55b6989a41ae296337356153e6081c61484d0b6734b6905683823e7317d01c42'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/fb/84/fb84ca8000808f62718994e4b44e79d88a05b345e9638d9f6cf6c8a5472da01f'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/37/26/3726a0239b5cb7d0ef3ea36886c533d0becc7404217763015559edb546d53c94'), PosixPath('/home/nathan/codeparrot-clean-train/.git/hooks/applypatch-msg.sample'), PosixPath('/home/nathan/codeparrot-clean-train/.git/lfs/objects/3e/f2/3ef240d0b394384803ae1bbe3b30974e11eb9b1b6ad4f49afc2ed0f7c9eae0d6')]
-03/03/2022 13:22:11 - WARNING - datasets.builder - Using custom data configuration codeparrot-clean-train-86fef7ac9fb06b05
-03/03/2022 13:22:50 - INFO - codeparrot_training - Step 0: {'lr': 0.0, 'samples': 512, 'steps': 0, 'loss/train': 10.075563430786133}
-03/03/2022 13:24:05 - INFO - codeparrot_training - Step 1: {'lr': 2.5e-07, 'samples': 1024, 'steps': 1, 'loss/train': 10.124848365783691}
-03/03/2022 13:24:05 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/03/2022 13:25:24 - INFO - codeparrot_training - Step 2: {'lr': 5e-07, 'samples': 1536, 'steps': 2, 'loss/train': 10.012473106384277}
-03/03/2022 13:25:27 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/03/2022 13:25:29 - INFO - codeparrot_training - Step 3: {'lr': 7.5e-07, 'samples': 2048, 'steps': 3, 'loss/train': 10.121092796325684}
-03/03/2022 13:25:33 - INFO - codeparrot_training - Step 4: {'lr': 1e-06, 'samples': 2560, 'steps': 4, 'loss/train': 10.095026016235352}
-03/03/2022 13:25:35 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/03/2022 13:25:38 - INFO - codeparrot_training - Step 5: {'lr': 1.25e-06, 'samples': 3072, 'steps': 5, 'loss/train': 9.843606948852539}
-03/03/2022 13:25:41 - INFO - codeparrot_training - Step 6: {'lr': 1.5e-06, 'samples': 3584, 'steps': 6, 'loss/train': 10.02976131439209}
-03/03/2022 13:25:44 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/03/2022 13:25:47 - INFO - codeparrot_training - Step 7: {'lr': 1.75e-06, 'samples': 4096, 'steps': 7, 'loss/train': 10.09312629699707}
-03/03/2022 13:25:50 - INFO - codeparrot_training - Step 8: {'lr': 2e-06, 'samples': 4608, 'steps': 8, 'loss/train': 9.968323707580566}
-03/03/2022 13:25:53 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/03/2022 13:25:55 - INFO - codeparrot_training - Step 9: {'lr': 2.25e-06, 'samples': 5120, 'steps': 9, 'loss/train': 9.982961654663086}
-03/03/2022 13:25:58 - INFO - codeparrot_training - Step 10: {'lr': 2.5e-06, 'samples': 5632, 'steps': 10, 'loss/train': 9.881282806396484}
-03/03/2022 13:26:01 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/03/2022 13:26:03 - INFO - codeparrot_training - Step 11: {'lr': 2.75e-06, 'samples': 6144, 'steps': 11, 'loss/train': 9.89371395111084}
-03/03/2022 13:26:07 - INFO - codeparrot_training - Step 12: {'lr': 3e-06, 'samples': 6656, 'steps': 12, 'loss/train': 9.743671417236328}
-03/03/2022 13:26:09 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/03/2022 13:26:12 - INFO - codeparrot_training - Step 13: {'lr': 3.25e-06, 'samples': 7168, 'steps': 13, 'loss/train': 9.71867847442627}
-03/03/2022 13:26:15 - INFO - codeparrot_training - Step 14: {'lr': 3.5e-06, 'samples': 7680, 'steps': 14, 'loss/train': 9.706364631652832}
-03/03/2022 13:26:19 - INFO - codeparrot_training - Step 15: {'lr': 3.75e-06, 'samples': 8192, 'steps': 15, 'loss/train': 9.625722885131836}
-03/03/2022 13:26:19 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/03/2022 13:26:24 - INFO - codeparrot_training - Step 16: {'lr': 4e-06, 'samples': 8704, 'steps': 16, 'loss/train': 9.538063049316406}
-03/03/2022 13:26:27 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/03/2022 13:26:29 - INFO - codeparrot_training - Step 17: {'lr': 4.250000000000001e-06, 'samples': 9216, 'steps': 17, 'loss/train': 9.547978401184082}
-03/03/2022 13:26:32 - INFO - codeparrot_training - Step 18: {'lr': 4.5e-06, 'samples': 9728, 'steps': 18, 'loss/train': 9.613702774047852}
-03/03/2022 13:26:35 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/03/2022 13:26:38 - INFO - codeparrot_training - Step 19: {'lr': 4.75e-06, 'samples': 10240, 'steps': 19, 'loss/train': 9.567453384399414}
-03/03/2022 13:26:41 - INFO - codeparrot_training - Step 20: {'lr': 5e-06, 'samples': 10752, 'steps': 20, 'loss/train': 9.41970443725586}
-03/03/2022 13:26:43 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/03/2022 13:26:46 - INFO - codeparrot_training - Step 21: {'lr': 5.2500000000000006e-06, 'samples': 11264, 'steps': 21, 'loss/train': 9.453089714050293}
-03/03/2022 13:26:49 - INFO - codeparrot_training - Step 22: {'lr': 5.5e-06, 'samples': 11776, 'steps': 22, 'loss/train': 9.410444259643555}
-03/03/2022 13:26:51 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/03/2022 13:26:55 - INFO - codeparrot_training - Step 23: {'lr': 5.75e-06, 'samples': 12288, 'steps': 23, 'loss/train': 8.90427303314209}
-03/03/2022 13:26:58 - INFO - codeparrot_training - Step 24: {'lr': 6e-06, 'samples': 12800, 'steps': 24, 'loss/train': 9.217617988586426}
-03/03/2022 13:27:00 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/03/2022 13:27:03 - INFO - codeparrot_training - Step 25: {'lr': 6.25e-06, 'samples': 13312, 'steps': 25, 'loss/train': 9.386109352111816}
-03/03/2022 13:27:06 - INFO - codeparrot_training - Step 26: {'lr': 6.5e-06, 'samples': 13824, 'steps': 26, 'loss/train': 8.986451148986816}
-03/03/2022 13:27:08 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/03/2022 13:27:12 - INFO - codeparrot_training - Step 27: {'lr': 6.75e-06, 'samples': 14336, 'steps': 27, 'loss/train': 9.02078914642334}
-03/03/2022 13:27:15 - INFO - codeparrot_training - Step 28: {'lr': 7e-06, 'samples': 14848, 'steps': 28, 'loss/train': 9.070732116699219}
-03/03/2022 13:27:16 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/03/2022 13:27:20 - INFO - codeparrot_training - Step 29: {'lr': 7.250000000000001e-06, 'samples': 15360, 'steps': 29, 'loss/train': 8.967691421508789}
-03/03/2022 13:27:23 - INFO - codeparrot_training - Step 30: {'lr': 7.5e-06, 'samples': 15872, 'steps': 30, 'loss/train': 8.433162689208984}
-03/03/2022 13:27:25 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/03/2022 13:27:29 - INFO - codeparrot_training - Step 31: {'lr': 7.75e-06, 'samples': 16384, 'steps': 31, 'loss/train': 9.051046371459961}
-03/03/2022 13:27:32 - INFO - codeparrot_training - Step 32: {'lr': 8e-06, 'samples': 16896, 'steps': 32, 'loss/train': 8.816210746765137}
-03/03/2022 13:27:33 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/03/2022 13:27:37 - INFO - codeparrot_training - Step 33: {'lr': 8.25e-06, 'samples': 17408, 'steps': 33, 'loss/train': 9.837918281555176}
-03/03/2022 13:27:40 - INFO - codeparrot_training - Step 34: {'lr': 8.500000000000002e-06, 'samples': 17920, 'steps': 34, 'loss/train': 9.328680992126465}
-03/03/2022 13:27:41 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/03/2022 13:27:46 - INFO - codeparrot_training - Step 35: {'lr': 8.750000000000001e-06, 'samples': 18432, 'steps': 35, 'loss/train': 8.939859390258789}
-03/03/2022 13:27:49 - INFO - codeparrot_training - Step 36: {'lr': 9e-06, 'samples': 18944, 'steps': 36, 'loss/train': 9.023159980773926}
-03/03/2022 13:27:50 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/03/2022 13:27:54 - INFO - codeparrot_training - Step 37: {'lr': 9.25e-06, 'samples': 19456, 'steps': 37, 'loss/train': 9.151119232177734}
-03/03/2022 13:27:57 - INFO - codeparrot_training - Step 38: {'lr': 9.5e-06, 'samples': 19968, 'steps': 38, 'loss/train': 8.467151641845703}
-03/03/2022 13:27:58 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/03/2022 13:28:03 - INFO - codeparrot_training - Step 39: {'lr': 9.75e-06, 'samples': 20480, 'steps': 39, 'loss/train': 8.554976463317871}
-03/03/2022 13:28:06 - INFO - codeparrot_training - Step 40: {'lr': 1e-05, 'samples': 20992, 'steps': 40, 'loss/train': 9.488030433654785}
-03/03/2022 13:28:06 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/03/2022 13:28:11 - INFO - codeparrot_training - Step 41: {'lr': 1.025e-05, 'samples': 21504, 'steps': 41, 'loss/train': 9.343393325805664}
-03/03/2022 13:28:14 - INFO - codeparrot_training - Step 42: {'lr': 1.0500000000000001e-05, 'samples': 22016, 'steps': 42, 'loss/train': 8.726397514343262}
-03/03/2022 13:28:15 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/03/2022 13:28:20 - INFO - codeparrot_training - Step 43: {'lr': 1.0749999999999999e-05, 'samples': 22528, 'steps': 43, 'loss/train': 8.832099914550781}
-03/03/2022 13:28:23 - INFO - codeparrot_training - Step 44: {'lr': 1.1e-05, 'samples': 23040, 'steps': 44, 'loss/train': 8.617071151733398}
-03/03/2022 13:28:23 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/03/2022 13:28:28 - INFO - codeparrot_training - Step 45: {'lr': 1.1249999999999999e-05, 'samples': 23552, 'steps': 45, 'loss/train': 8.621835708618164}
-03/03/2022 13:28:31 - INFO - codeparrot_training - Step 46: {'lr': 1.15e-05, 'samples': 24064, 'steps': 46, 'loss/train': 8.607819557189941}
-03/03/2022 13:28:31 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/03/2022 13:28:37 - INFO - codeparrot_training - Step 47: {'lr': 1.1750000000000001e-05, 'samples': 24576, 'steps': 47, 'loss/train': 8.41963005065918}
-03/03/2022 13:28:39 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/03/2022 13:28:42 - INFO - codeparrot_training - Step 48: {'lr': 1.2e-05, 'samples': 25088, 'steps': 48, 'loss/train': 8.563586235046387}
-03/03/2022 13:28:45 - INFO - codeparrot_training - Step 49: {'lr': 1.2250000000000001e-05, 'samples': 25600, 'steps': 49, 'loss/train': 9.081216812133789}
-03/03/2022 13:28:48 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/03/2022 13:28:50 - INFO - codeparrot_training - Step 50: {'lr': 1.25e-05, 'samples': 26112, 'steps': 50, 'loss/train': 8.793917655944824}
-03/03/2022 13:28:54 - INFO - codeparrot_training - Step 51: {'lr': 1.275e-05, 'samples': 26624, 'steps': 51, 'loss/train': 7.926756858825684}
-03/03/2022 13:28:56 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/03/2022 13:28:59 - INFO - codeparrot_training - Step 52: {'lr': 1.3e-05, 'samples': 27136, 'steps': 52, 'loss/train': 8.878251075744629}
-03/03/2022 13:29:02 - INFO - codeparrot_training - Step 53: {'lr': 1.325e-05, 'samples': 27648, 'steps': 53, 'loss/train': 8.69863224029541}
-03/03/2022 13:29:04 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/03/2022 13:29:08 - INFO - codeparrot_training - Step 54: {'lr': 1.35e-05, 'samples': 28160, 'steps': 54, 'loss/train': 8.32911205291748}
-03/03/2022 13:29:11 - INFO - codeparrot_training - Step 55: {'lr': 1.375e-05, 'samples': 28672, 'steps': 55, 'loss/train': 8.402761459350586}
-03/03/2022 13:29:13 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/03/2022 13:29:16 - INFO - codeparrot_training - Step 56: {'lr': 1.4e-05, 'samples': 29184, 'steps': 56, 'loss/train': 8.484271049499512}
-03/03/2022 13:29:19 - INFO - codeparrot_training - Step 57: {'lr': 1.425e-05, 'samples': 29696, 'steps': 57, 'loss/train': 8.7686767578125}
-03/03/2022 13:29:22 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/03/2022 13:29:25 - INFO - codeparrot_training - Step 58: {'lr': 1.4500000000000002e-05, 'samples': 30208, 'steps': 58, 'loss/train': 8.384221076965332}
-03/03/2022 13:29:28 - INFO - codeparrot_training - Step 59: {'lr': 1.475e-05, 'samples': 30720, 'steps': 59, 'loss/train': 8.519675254821777}
-03/03/2022 13:29:30 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/03/2022 13:29:33 - INFO - codeparrot_training - Step 60: {'lr': 1.5e-05, 'samples': 31232, 'steps': 60, 'loss/train': 8.939576148986816}
-03/03/2022 13:29:36 - INFO - codeparrot_training - Step 61: {'lr': 1.525e-05, 'samples': 31744, 'steps': 61, 'loss/train': 8.751921653747559}
-03/03/2022 13:29:39 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/03/2022 13:29:42 - INFO - codeparrot_training - Step 62: {'lr': 1.55e-05, 'samples': 32256, 'steps': 62, 'loss/train': 8.698548316955566}
-03/03/2022 13:29:45 - INFO - codeparrot_training - Step 63: {'lr': 1.575e-05, 'samples': 32768, 'steps': 63, 'loss/train': 8.578275680541992}
-03/03/2022 13:29:47 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/03/2022 13:29:50 - INFO - codeparrot_training - Step 64: {'lr': 1.6e-05, 'samples': 33280, 'steps': 64, 'loss/train': 8.510712623596191}
-03/03/2022 13:29:53 - INFO - codeparrot_training - Step 65: {'lr': 1.6250000000000002e-05, 'samples': 33792, 'steps': 65, 'loss/train': 8.645843505859375}
-03/03/2022 13:29:55 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/03/2022 13:29:59 - INFO - codeparrot_training - Step 66: {'lr': 1.65e-05, 'samples': 34304, 'steps': 66, 'loss/train': 8.519330024719238}
-03/03/2022 13:30:02 - INFO - codeparrot_training - Step 67: {'lr': 1.675e-05, 'samples': 34816, 'steps': 67, 'loss/train': 8.555344581604004}
-03/03/2022 13:30:04 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/03/2022 13:30:07 - INFO - codeparrot_training - Step 68: {'lr': 1.7000000000000003e-05, 'samples': 35328, 'steps': 68, 'loss/train': 8.772445678710938}
-03/03/2022 13:30:10 - INFO - codeparrot_training - Step 69: {'lr': 1.7250000000000003e-05, 'samples': 35840, 'steps': 69, 'loss/train': 8.694655418395996}
-03/03/2022 13:30:12 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/03/2022 13:30:16 - INFO - codeparrot_training - Step 70: {'lr': 1.7500000000000002e-05, 'samples': 36352, 'steps': 70, 'loss/train': 8.430862426757812}
-03/03/2022 13:30:19 - INFO - codeparrot_training - Step 71: {'lr': 1.7749999999999998e-05, 'samples': 36864, 'steps': 71, 'loss/train': 9.024465560913086}
-03/03/2022 13:30:20 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/03/2022 13:30:24 - INFO - codeparrot_training - Step 72: {'lr': 1.8e-05, 'samples': 37376, 'steps': 72, 'loss/train': 8.457487106323242}
-03/03/2022 13:30:27 - INFO - codeparrot_training - Step 73: {'lr': 1.825e-05, 'samples': 37888, 'steps': 73, 'loss/train': 8.562689781188965}
-03/03/2022 13:30:28 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/03/2022 13:30:33 - INFO - codeparrot_training - Step 74: {'lr': 1.85e-05, 'samples': 38400, 'steps': 74, 'loss/train': 8.607612609863281}
-03/03/2022 13:30:36 - INFO - codeparrot_training - Step 75: {'lr': 1.875e-05, 'samples': 38912, 'steps': 75, 'loss/train': 8.44783878326416}
-03/03/2022 13:30:37 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/03/2022 13:30:41 - INFO - codeparrot_training - Step 76: {'lr': 1.9e-05, 'samples': 39424, 'steps': 76, 'loss/train': 9.018163681030273}
-03/03/2022 13:30:44 - INFO - codeparrot_training - Step 77: {'lr': 1.925e-05, 'samples': 39936, 'steps': 77, 'loss/train': 8.568017959594727}
-03/03/2022 13:30:45 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/03/2022 13:30:50 - INFO - codeparrot_training - Step 78: {'lr': 1.95e-05, 'samples': 40448, 'steps': 78, 'loss/train': 8.524364471435547}
-03/03/2022 13:30:53 - INFO - codeparrot_training - Step 79: {'lr': 1.975e-05, 'samples': 40960, 'steps': 79, 'loss/train': 8.529118537902832}
-03/03/2022 13:30:54 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/03/2022 13:30:58 - INFO - codeparrot_training - Step 80: {'lr': 2e-05, 'samples': 41472, 'steps': 80, 'loss/train': 8.654486656188965}
-03/03/2022 13:31:01 - INFO - codeparrot_training - Step 81: {'lr': 2.025e-05, 'samples': 41984, 'steps': 81, 'loss/train': 8.813864707946777}
-03/03/2022 13:31:02 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/03/2022 13:31:07 - INFO - codeparrot_training - Step 82: {'lr': 2.05e-05, 'samples': 42496, 'steps': 82, 'loss/train': 8.502435684204102}
-03/03/2022 13:31:10 - INFO - codeparrot_training - Step 83: {'lr': 2.0750000000000003e-05, 'samples': 43008, 'steps': 83, 'loss/train': 9.020332336425781}
-03/03/2022 13:31:10 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/03/2022 13:31:15 - INFO - codeparrot_training - Step 84: {'lr': 2.1000000000000002e-05, 'samples': 43520, 'steps': 84, 'loss/train': 8.501923561096191}
-03/03/2022 13:31:18 - INFO - codeparrot_training - Step 85: {'lr': 2.125e-05, 'samples': 44032, 'steps': 85, 'loss/train': 8.312204360961914}
-03/03/2022 13:31:19 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/03/2022 13:31:24 - INFO - codeparrot_training - Step 86: {'lr': 2.1499999999999997e-05, 'samples': 44544, 'steps': 86, 'loss/train': 8.143906593322754}
-03/03/2022 13:31:27 - INFO - codeparrot_training - Step 87: {'lr': 2.175e-05, 'samples': 45056, 'steps': 87, 'loss/train': 8.643278121948242}
-03/03/2022 13:31:28 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/03/2022 13:31:32 - INFO - codeparrot_training - Step 88: {'lr': 2.2e-05, 'samples': 45568, 'steps': 88, 'loss/train': 8.471076011657715}
-03/03/2022 13:31:36 - INFO - codeparrot_training - Step 89: {'lr': 2.225e-05, 'samples': 46080, 'steps': 89, 'loss/train': 8.585366249084473}
-03/03/2022 13:31:36 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/03/2022 13:31:41 - INFO - codeparrot_training - Step 90: {'lr': 2.2499999999999998e-05, 'samples': 46592, 'steps': 90, 'loss/train': 8.756730079650879}
-03/03/2022 13:31:44 - INFO - codeparrot_training - Step 91: {'lr': 2.275e-05, 'samples': 47104, 'steps': 91, 'loss/train': 8.959531784057617}
-03/03/2022 13:31:45 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/03/2022 13:31:49 - INFO - codeparrot_training - Step 92: {'lr': 2.3e-05, 'samples': 47616, 'steps': 92, 'loss/train': 8.488385200500488}
-03/03/2022 13:31:52 - INFO - codeparrot_training - Step 93: {'lr': 2.325e-05, 'samples': 48128, 'steps': 93, 'loss/train': 8.548238754272461}
-03/03/2022 13:31:53 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/03/2022 13:31:58 - INFO - codeparrot_training - Step 94: {'lr': 2.3500000000000002e-05, 'samples': 48640, 'steps': 94, 'loss/train': 9.079781532287598}
-03/03/2022 13:32:01 - INFO - codeparrot_training - Step 95: {'lr': 2.375e-05, 'samples': 49152, 'steps': 95, 'loss/train': 8.213057518005371}
-03/03/2022 13:32:01 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/03/2022 13:32:06 - INFO - codeparrot_training - Step 96: {'lr': 2.4e-05, 'samples': 49664, 'steps': 96, 'loss/train': 9.193713188171387}
-03/03/2022 13:32:09 - INFO - codeparrot_training - Step 97: {'lr': 2.425e-05, 'samples': 50176, 'steps': 97, 'loss/train': 8.648150444030762}
-03/03/2022 13:32:10 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/03/2022 13:32:15 - INFO - codeparrot_training - Step 98: {'lr': 2.4500000000000003e-05, 'samples': 50688, 'steps': 98, 'loss/train': 8.951532363891602}
-03/03/2022 13:32:18 - INFO - codeparrot_training - Step 99: {'lr': 2.4750000000000002e-05, 'samples': 51200, 'steps': 99, 'loss/train': 8.602143287658691}
-03/03/2022 13:32:18 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/03/2022 13:32:23 - INFO - codeparrot_training - Step 100: {'lr': 2.5e-05, 'samples': 51712, 'steps': 100, 'loss/train': 8.64793586730957}
-03/03/2022 13:32:26 - INFO - codeparrot_training - Step 101: {'lr': 2.525e-05, 'samples': 52224, 'steps': 101, 'loss/train': 8.7129545211792}
-03/03/2022 13:32:26 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/03/2022 13:32:32 - INFO - codeparrot_training - Step 102: {'lr': 2.55e-05, 'samples': 52736, 'steps': 102, 'loss/train': 8.678922653198242}
-03/03/2022 13:32:35 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/03/2022 13:32:37 - INFO - codeparrot_training - Step 103: {'lr': 2.575e-05, 'samples': 53248, 'steps': 103, 'loss/train': 8.083718299865723}
-03/03/2022 13:32:40 - INFO - codeparrot_training - Step 104: {'lr': 2.6e-05, 'samples': 53760, 'steps': 104, 'loss/train': 8.35842227935791}
-03/03/2022 13:32:43 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/03/2022 13:32:45 - INFO - codeparrot_training - Step 105: {'lr': 2.625e-05, 'samples': 54272, 'steps': 105, 'loss/train': 8.159714698791504}
-03/03/2022 13:32:49 - INFO - codeparrot_training - Step 106: {'lr': 2.65e-05, 'samples': 54784, 'steps': 106, 'loss/train': 8.1396484375}
-03/03/2022 13:32:51 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/03/2022 13:32:54 - INFO - codeparrot_training - Step 107: {'lr': 2.675e-05, 'samples': 55296, 'steps': 107, 'loss/train': 8.233939170837402}
-03/03/2022 13:32:57 - INFO - codeparrot_training - Step 108: {'lr': 2.7e-05, 'samples': 55808, 'steps': 108, 'loss/train': 8.465450286865234}
-03/03/2022 13:32:59 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/03/2022 13:33:02 - INFO - codeparrot_training - Step 109: {'lr': 2.725e-05, 'samples': 56320, 'steps': 109, 'loss/train': 8.154802322387695}
-03/03/2022 13:33:06 - INFO - codeparrot_training - Step 110: {'lr': 2.75e-05, 'samples': 56832, 'steps': 110, 'loss/train': 8.17076301574707}
-03/03/2022 13:33:08 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/03/2022 13:33:11 - INFO - codeparrot_training - Step 111: {'lr': 2.775e-05, 'samples': 57344, 'steps': 111, 'loss/train': 8.381338119506836}
-03/03/2022 13:33:14 - INFO - codeparrot_training - Step 112: {'lr': 2.8e-05, 'samples': 57856, 'steps': 112, 'loss/train': 8.114055633544922}
-03/03/2022 13:33:16 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/03/2022 13:33:20 - INFO - codeparrot_training - Step 113: {'lr': 2.8250000000000002e-05, 'samples': 58368, 'steps': 113, 'loss/train': 7.933559894561768}
-03/03/2022 13:33:23 - INFO - codeparrot_training - Step 114: {'lr': 2.85e-05, 'samples': 58880, 'steps': 114, 'loss/train': 9.193424224853516}
-03/03/2022 13:33:25 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/03/2022 13:33:28 - INFO - codeparrot_training - Step 115: {'lr': 2.875e-05, 'samples': 59392, 'steps': 115, 'loss/train': 7.855266094207764}
-03/03/2022 13:33:31 - INFO - codeparrot_training - Step 116: {'lr': 2.9000000000000004e-05, 'samples': 59904, 'steps': 116, 'loss/train': 8.517616271972656}
-03/03/2022 13:33:33 - INFO - codeparrot_training - Skipping example with length 822 (seq_length=1024)
-03/03/2022 13:33:36 - INFO - codeparrot_training - Step 117: {'lr': 2.9250000000000003e-05, 'samples': 60416, 'steps': 117, 'loss/train': 8.036568641662598}
-03/03/2022 13:33:40 - INFO - codeparrot_training - Step 118: {'lr': 2.95e-05, 'samples': 60928, 'steps': 118, 'loss/train': 7.926286220550537}
-03/03/2022 13:33:41 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/03/2022 13:33:45 - INFO - codeparrot_training - Step 119: {'lr': 2.9749999999999998e-05, 'samples': 61440, 'steps': 119, 'loss/train': 8.040275573730469}
-03/03/2022 13:33:48 - INFO - codeparrot_training - Step 120: {'lr': 3e-05, 'samples': 61952, 'steps': 120, 'loss/train': 6.9734649658203125}
-03/03/2022 13:33:50 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/03/2022 13:33:53 - INFO - codeparrot_training - Step 121: {'lr': 3.025e-05, 'samples': 62464, 'steps': 121, 'loss/train': 8.224665641784668}
-03/03/2022 13:33:57 - INFO - codeparrot_training - Step 122: {'lr': 3.05e-05, 'samples': 62976, 'steps': 122, 'loss/train': 8.240490913391113}
-03/03/2022 13:33:58 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/03/2022 13:34:02 - INFO - codeparrot_training - Step 123: {'lr': 3.075e-05, 'samples': 63488, 'steps': 123, 'loss/train': 8.030046463012695}
-03/03/2022 13:34:05 - INFO - codeparrot_training - Step 124: {'lr': 3.1e-05, 'samples': 64000, 'steps': 124, 'loss/train': 7.976356029510498}
-03/03/2022 13:34:06 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/03/2022 13:34:10 - INFO - codeparrot_training - Step 125: {'lr': 3.125e-05, 'samples': 64512, 'steps': 125, 'loss/train': 8.348257064819336}
-03/03/2022 13:34:13 - INFO - codeparrot_training - Step 126: {'lr': 3.15e-05, 'samples': 65024, 'steps': 126, 'loss/train': 7.844707489013672}
-03/03/2022 13:34:14 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/03/2022 13:34:19 - INFO - codeparrot_training - Step 127: {'lr': 3.175e-05, 'samples': 65536, 'steps': 127, 'loss/train': 8.167869567871094}
-03/03/2022 13:34:22 - INFO - codeparrot_training - Step 128: {'lr': 3.2e-05, 'samples': 66048, 'steps': 128, 'loss/train': 7.930793762207031}
-03/03/2022 13:34:22 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/03/2022 13:34:27 - INFO - codeparrot_training - Step 129: {'lr': 3.2250000000000005e-05, 'samples': 66560, 'steps': 129, 'loss/train': 7.673683166503906}
-03/03/2022 13:34:30 - INFO - codeparrot_training - Step 130: {'lr': 3.2500000000000004e-05, 'samples': 67072, 'steps': 130, 'loss/train': 8.17394733428955}
-03/03/2022 13:34:31 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/03/2022 13:34:36 - INFO - codeparrot_training - Step 131: {'lr': 3.275e-05, 'samples': 67584, 'steps': 131, 'loss/train': 7.390617847442627}
-03/03/2022 13:34:39 - INFO - codeparrot_training - Step 132: {'lr': 3.3e-05, 'samples': 68096, 'steps': 132, 'loss/train': 7.104628562927246}
-03/03/2022 13:34:39 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/03/2022 13:34:44 - INFO - codeparrot_training - Step 133: {'lr': 3.325e-05, 'samples': 68608, 'steps': 133, 'loss/train': 8.078102111816406}
-03/03/2022 13:34:47 - INFO - codeparrot_training - Step 134: {'lr': 3.35e-05, 'samples': 69120, 'steps': 134, 'loss/train': 7.884213447570801}
-03/03/2022 13:34:47 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/03/2022 13:34:53 - INFO - codeparrot_training - Step 135: {'lr': 3.375e-05, 'samples': 69632, 'steps': 135, 'loss/train': 8.450540542602539}
-03/03/2022 13:34:56 - INFO - codeparrot_training - Step 136: {'lr': 3.4000000000000007e-05, 'samples': 70144, 'steps': 136, 'loss/train': 8.404011726379395}
-03/03/2022 13:34:56 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/03/2022 13:35:01 - INFO - codeparrot_training - Step 137: {'lr': 3.4250000000000006e-05, 'samples': 70656, 'steps': 137, 'loss/train': 7.6241350173950195}
-03/03/2022 13:35:04 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/03/2022 13:35:06 - INFO - codeparrot_training - Step 138: {'lr': 3.4500000000000005e-05, 'samples': 71168, 'steps': 138, 'loss/train': 7.530354022979736}
-03/03/2022 13:35:09 - INFO - codeparrot_training - Step 139: {'lr': 3.4750000000000004e-05, 'samples': 71680, 'steps': 139, 'loss/train': 8.152228355407715}
-03/03/2022 13:35:12 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/03/2022 13:35:15 - INFO - codeparrot_training - Step 140: {'lr': 3.5000000000000004e-05, 'samples': 72192, 'steps': 140, 'loss/train': 8.318809509277344}
-03/03/2022 13:35:18 - INFO - codeparrot_training - Step 141: {'lr': 3.5249999999999996e-05, 'samples': 72704, 'steps': 141, 'loss/train': 7.475725173950195}
-03/03/2022 13:35:20 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/03/2022 13:35:23 - INFO - codeparrot_training - Step 142: {'lr': 3.5499999999999996e-05, 'samples': 73216, 'steps': 142, 'loss/train': 7.176308631896973}
-03/03/2022 13:35:26 - INFO - codeparrot_training - Step 143: {'lr': 3.5749999999999995e-05, 'samples': 73728, 'steps': 143, 'loss/train': 8.0440034866333}
-03/03/2022 13:35:29 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/03/2022 13:35:32 - INFO - codeparrot_training - Step 144: {'lr': 3.6e-05, 'samples': 74240, 'steps': 144, 'loss/train': 8.216455459594727}
-03/03/2022 13:35:35 - INFO - codeparrot_training - Step 145: {'lr': 3.625e-05, 'samples': 74752, 'steps': 145, 'loss/train': 8.240697860717773}
-03/03/2022 13:35:37 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/03/2022 13:35:40 - INFO - codeparrot_training - Step 146: {'lr': 3.65e-05, 'samples': 75264, 'steps': 146, 'loss/train': 7.32492208480835}
-03/03/2022 13:35:43 - INFO - codeparrot_training - Step 147: {'lr': 3.675e-05, 'samples': 75776, 'steps': 147, 'loss/train': 7.730316162109375}
-03/03/2022 13:35:45 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/03/2022 13:35:48 - INFO - codeparrot_training - Step 148: {'lr': 3.7e-05, 'samples': 76288, 'steps': 148, 'loss/train': 7.661489009857178}
-03/03/2022 13:35:52 - INFO - codeparrot_training - Step 149: {'lr': 3.725e-05, 'samples': 76800, 'steps': 149, 'loss/train': 7.78841495513916}
-03/03/2022 13:35:54 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/03/2022 13:35:57 - INFO - codeparrot_training - Step 150: {'lr': 3.75e-05, 'samples': 77312, 'steps': 150, 'loss/train': 7.619410037994385}
-03/03/2022 13:36:00 - INFO - codeparrot_training - Step 151: {'lr': 3.775e-05, 'samples': 77824, 'steps': 151, 'loss/train': 8.464534759521484}
-03/03/2022 13:36:02 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/03/2022 13:36:05 - INFO - codeparrot_training - Step 152: {'lr': 3.8e-05, 'samples': 78336, 'steps': 152, 'loss/train': 7.549778461456299}
-03/03/2022 13:36:09 - INFO - codeparrot_training - Step 153: {'lr': 3.825e-05, 'samples': 78848, 'steps': 153, 'loss/train': 7.371613502502441}
-03/03/2022 13:36:10 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/03/2022 13:36:14 - INFO - codeparrot_training - Step 154: {'lr': 3.85e-05, 'samples': 79360, 'steps': 154, 'loss/train': 7.702090740203857}
-03/03/2022 13:36:17 - INFO - codeparrot_training - Step 155: {'lr': 3.875e-05, 'samples': 79872, 'steps': 155, 'loss/train': 7.848684787750244}
-03/03/2022 13:36:19 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/03/2022 13:36:23 - INFO - codeparrot_training - Step 156: {'lr': 3.9e-05, 'samples': 80384, 'steps': 156, 'loss/train': 7.010176181793213}
-03/03/2022 13:36:26 - INFO - codeparrot_training - Step 157: {'lr': 3.925e-05, 'samples': 80896, 'steps': 157, 'loss/train': 4.933742523193359}
-03/03/2022 13:36:29 - INFO - codeparrot_training - Step 158: {'lr': 3.95e-05, 'samples': 81408, 'steps': 158, 'loss/train': 8.188973426818848}
-03/03/2022 13:36:29 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/03/2022 13:36:35 - INFO - codeparrot_training - Step 159: {'lr': 3.9750000000000004e-05, 'samples': 81920, 'steps': 159, 'loss/train': 8.148823738098145}
-03/03/2022 13:36:38 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/03/2022 13:36:40 - INFO - codeparrot_training - Step 160: {'lr': 4e-05, 'samples': 82432, 'steps': 160, 'loss/train': 7.696084976196289}
-03/03/2022 13:36:43 - INFO - codeparrot_training - Step 161: {'lr': 4.025e-05, 'samples': 82944, 'steps': 161, 'loss/train': 8.04732608795166}
-03/03/2022 13:36:46 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 13:36:48 - INFO - codeparrot_training - Step 162: {'lr': 4.05e-05, 'samples': 83456, 'steps': 162, 'loss/train': 7.864019870758057}
-03/03/2022 13:36:52 - INFO - codeparrot_training - Step 163: {'lr': 4.075e-05, 'samples': 83968, 'steps': 163, 'loss/train': 7.568187713623047}
-03/03/2022 13:36:54 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/03/2022 13:36:57 - INFO - codeparrot_training - Step 164: {'lr': 4.1e-05, 'samples': 84480, 'steps': 164, 'loss/train': 7.4156365394592285}
-03/03/2022 13:37:00 - INFO - codeparrot_training - Step 165: {'lr': 4.125e-05, 'samples': 84992, 'steps': 165, 'loss/train': 8.103707313537598}
-03/03/2022 13:37:02 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/03/2022 13:37:05 - INFO - codeparrot_training - Step 166: {'lr': 4.1500000000000006e-05, 'samples': 85504, 'steps': 166, 'loss/train': 7.68804407119751}
-03/03/2022 13:37:08 - INFO - codeparrot_training - Step 167: {'lr': 4.1750000000000005e-05, 'samples': 86016, 'steps': 167, 'loss/train': 7.974943161010742}
-03/03/2022 13:37:10 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/03/2022 13:37:14 - INFO - codeparrot_training - Step 168: {'lr': 4.2000000000000004e-05, 'samples': 86528, 'steps': 168, 'loss/train': 5.833436012268066}
-03/03/2022 13:37:17 - INFO - codeparrot_training - Step 169: {'lr': 4.2250000000000004e-05, 'samples': 87040, 'steps': 169, 'loss/train': 7.7950568199157715}
-03/03/2022 13:37:19 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/03/2022 13:37:22 - INFO - codeparrot_training - Step 170: {'lr': 4.25e-05, 'samples': 87552, 'steps': 170, 'loss/train': 7.657891273498535}
-03/03/2022 13:37:25 - INFO - codeparrot_training - Step 171: {'lr': 4.275e-05, 'samples': 88064, 'steps': 171, 'loss/train': 7.877186298370361}
-03/03/2022 13:37:27 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/03/2022 13:37:31 - INFO - codeparrot_training - Step 172: {'lr': 4.2999999999999995e-05, 'samples': 88576, 'steps': 172, 'loss/train': 7.893576622009277}
-03/03/2022 13:37:34 - INFO - codeparrot_training - Step 173: {'lr': 4.325e-05, 'samples': 89088, 'steps': 173, 'loss/train': 7.6018571853637695}
-03/03/2022 13:37:35 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/03/2022 13:37:39 - INFO - codeparrot_training - Step 174: {'lr': 4.35e-05, 'samples': 89600, 'steps': 174, 'loss/train': 7.9183549880981445}
-03/03/2022 13:37:42 - INFO - codeparrot_training - Step 175: {'lr': 4.375e-05, 'samples': 90112, 'steps': 175, 'loss/train': 7.391948699951172}
-03/03/2022 13:37:43 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/03/2022 13:37:47 - INFO - codeparrot_training - Step 176: {'lr': 4.4e-05, 'samples': 90624, 'steps': 176, 'loss/train': 7.670172691345215}
-03/03/2022 13:37:51 - INFO - codeparrot_training - Step 177: {'lr': 4.425e-05, 'samples': 91136, 'steps': 177, 'loss/train': 7.4225029945373535}
-03/03/2022 13:37:52 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/03/2022 13:37:56 - INFO - codeparrot_training - Step 178: {'lr': 4.45e-05, 'samples': 91648, 'steps': 178, 'loss/train': 7.456734657287598}
-03/03/2022 13:37:59 - INFO - codeparrot_training - Step 179: {'lr': 4.475e-05, 'samples': 92160, 'steps': 179, 'loss/train': 8.120655059814453}
-03/03/2022 13:38:00 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/03/2022 13:38:04 - INFO - codeparrot_training - Step 180: {'lr': 4.4999999999999996e-05, 'samples': 92672, 'steps': 180, 'loss/train': 7.598281383514404}
-03/03/2022 13:38:07 - INFO - codeparrot_training - Step 181: {'lr': 4.525e-05, 'samples': 93184, 'steps': 181, 'loss/train': 8.022689819335938}
-03/03/2022 13:38:08 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/03/2022 13:38:13 - INFO - codeparrot_training - Step 182: {'lr': 4.55e-05, 'samples': 93696, 'steps': 182, 'loss/train': 7.102559566497803}
-03/03/2022 13:38:16 - INFO - codeparrot_training - Step 183: {'lr': 4.575e-05, 'samples': 94208, 'steps': 183, 'loss/train': 5.537654876708984}
-03/03/2022 13:38:18 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/03/2022 13:38:21 - INFO - codeparrot_training - Step 184: {'lr': 4.6e-05, 'samples': 94720, 'steps': 184, 'loss/train': 7.378385066986084}
-03/03/2022 13:38:24 - INFO - codeparrot_training - Step 185: {'lr': 4.625e-05, 'samples': 95232, 'steps': 185, 'loss/train': 7.413166046142578}
-03/03/2022 13:38:25 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/03/2022 13:38:29 - INFO - codeparrot_training - Step 186: {'lr': 4.65e-05, 'samples': 95744, 'steps': 186, 'loss/train': 7.445736885070801}
-03/03/2022 13:38:32 - INFO - codeparrot_training - Step 187: {'lr': 4.675e-05, 'samples': 96256, 'steps': 187, 'loss/train': 8.496750831604004}
-03/03/2022 13:38:34 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/03/2022 13:38:38 - INFO - codeparrot_training - Step 188: {'lr': 4.7000000000000004e-05, 'samples': 96768, 'steps': 188, 'loss/train': 7.747251033782959}
-03/03/2022 13:38:41 - INFO - codeparrot_training - Step 189: {'lr': 4.725e-05, 'samples': 97280, 'steps': 189, 'loss/train': 7.649470806121826}
-03/03/2022 13:38:42 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/03/2022 13:38:46 - INFO - codeparrot_training - Step 190: {'lr': 4.75e-05, 'samples': 97792, 'steps': 190, 'loss/train': 7.644663333892822}
-03/03/2022 13:38:49 - INFO - codeparrot_training - Step 191: {'lr': 4.775e-05, 'samples': 98304, 'steps': 191, 'loss/train': 8.062586784362793}
-03/03/2022 13:38:50 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/03/2022 13:38:54 - INFO - codeparrot_training - Step 192: {'lr': 4.8e-05, 'samples': 98816, 'steps': 192, 'loss/train': 7.344707489013672}
-03/03/2022 13:38:58 - INFO - codeparrot_training - Step 193: {'lr': 4.825e-05, 'samples': 99328, 'steps': 193, 'loss/train': 8.712090492248535}
-03/03/2022 13:38:58 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/03/2022 13:39:03 - INFO - codeparrot_training - Step 194: {'lr': 4.85e-05, 'samples': 99840, 'steps': 194, 'loss/train': 8.00727653503418}
-03/03/2022 13:39:06 - INFO - codeparrot_training - Step 195: {'lr': 4.8750000000000006e-05, 'samples': 100352, 'steps': 195, 'loss/train': 6.896945953369141}
-03/03/2022 13:39:06 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/03/2022 13:39:11 - INFO - codeparrot_training - Step 196: {'lr': 4.9000000000000005e-05, 'samples': 100864, 'steps': 196, 'loss/train': 7.245913028717041}
-03/03/2022 13:39:15 - INFO - codeparrot_training - Step 197: {'lr': 4.9250000000000004e-05, 'samples': 101376, 'steps': 197, 'loss/train': 7.287005424499512}
-03/03/2022 13:39:15 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/03/2022 13:39:20 - INFO - codeparrot_training - Step 198: {'lr': 4.9500000000000004e-05, 'samples': 101888, 'steps': 198, 'loss/train': 7.7306318283081055}
-03/03/2022 13:39:23 - INFO - codeparrot_training - Step 199: {'lr': 4.975e-05, 'samples': 102400, 'steps': 199, 'loss/train': 7.501760005950928}
-03/03/2022 13:39:23 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/03/2022 13:39:28 - INFO - codeparrot_training - Step 200: {'lr': 5e-05, 'samples': 102912, 'steps': 200, 'loss/train': 7.2059173583984375}
-03/03/2022 13:39:31 - INFO - codeparrot_training - Step 201: {'lr': 5.025e-05, 'samples': 103424, 'steps': 201, 'loss/train': 7.545304775238037}
-03/03/2022 13:39:31 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/03/2022 13:39:37 - INFO - codeparrot_training - Step 202: {'lr': 5.05e-05, 'samples': 103936, 'steps': 202, 'loss/train': 6.92850923538208}
-03/03/2022 13:39:40 - INFO - codeparrot_training - Step 203: {'lr': 5.075000000000001e-05, 'samples': 104448, 'steps': 203, 'loss/train': 7.187972068786621}
-03/03/2022 13:39:40 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/03/2022 13:39:45 - INFO - codeparrot_training - Step 204: {'lr': 5.1e-05, 'samples': 104960, 'steps': 204, 'loss/train': 7.582147121429443}
-03/03/2022 13:39:48 - INFO - codeparrot_training - Step 205: {'lr': 5.125e-05, 'samples': 105472, 'steps': 205, 'loss/train': 9.222358703613281}
-03/03/2022 13:39:49 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/03/2022 13:39:53 - INFO - codeparrot_training - Step 206: {'lr': 5.15e-05, 'samples': 105984, 'steps': 206, 'loss/train': 7.789576530456543}
-03/03/2022 13:39:57 - INFO - codeparrot_training - Step 207: {'lr': 5.175e-05, 'samples': 106496, 'steps': 207, 'loss/train': 7.880443572998047}
-03/03/2022 13:39:57 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/03/2022 13:40:02 - INFO - codeparrot_training - Step 208: {'lr': 5.2e-05, 'samples': 107008, 'steps': 208, 'loss/train': 7.160046100616455}
-03/03/2022 13:40:05 - INFO - codeparrot_training - Step 209: {'lr': 5.2249999999999996e-05, 'samples': 107520, 'steps': 209, 'loss/train': 8.04822063446045}
-03/03/2022 13:40:06 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/03/2022 13:40:10 - INFO - codeparrot_training - Step 210: {'lr': 5.25e-05, 'samples': 108032, 'steps': 210, 'loss/train': 7.374578475952148}
-03/03/2022 13:40:13 - INFO - codeparrot_training - Step 211: {'lr': 5.275e-05, 'samples': 108544, 'steps': 211, 'loss/train': 7.502261638641357}
-03/03/2022 13:40:14 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/03/2022 13:40:19 - INFO - codeparrot_training - Step 212: {'lr': 5.3e-05, 'samples': 109056, 'steps': 212, 'loss/train': 7.538562297821045}
-03/03/2022 13:40:22 - INFO - codeparrot_training - Step 213: {'lr': 5.325e-05, 'samples': 109568, 'steps': 213, 'loss/train': 8.062139511108398}
-03/03/2022 13:40:22 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/03/2022 13:40:27 - INFO - codeparrot_training - Step 214: {'lr': 5.35e-05, 'samples': 110080, 'steps': 214, 'loss/train': 7.754930019378662}
-03/03/2022 13:40:30 - INFO - codeparrot_training - Step 215: {'lr': 5.375e-05, 'samples': 110592, 'steps': 215, 'loss/train': 7.983520030975342}
-03/03/2022 13:40:30 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/03/2022 13:40:35 - INFO - codeparrot_training - Step 216: {'lr': 5.4e-05, 'samples': 111104, 'steps': 216, 'loss/train': 7.068185329437256}
-03/03/2022 13:40:38 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/03/2022 13:40:41 - INFO - codeparrot_training - Step 217: {'lr': 5.4250000000000004e-05, 'samples': 111616, 'steps': 217, 'loss/train': 7.8822760581970215}
-03/03/2022 13:40:44 - INFO - codeparrot_training - Step 218: {'lr': 5.45e-05, 'samples': 112128, 'steps': 218, 'loss/train': 7.853682518005371}
-03/03/2022 13:40:46 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/03/2022 13:40:49 - INFO - codeparrot_training - Step 219: {'lr': 5.475e-05, 'samples': 112640, 'steps': 219, 'loss/train': 7.099795818328857}
-03/03/2022 13:40:52 - INFO - codeparrot_training - Step 220: {'lr': 5.5e-05, 'samples': 113152, 'steps': 220, 'loss/train': 7.336885929107666}
-03/03/2022 13:40:55 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/03/2022 13:40:58 - INFO - codeparrot_training - Step 221: {'lr': 5.525e-05, 'samples': 113664, 'steps': 221, 'loss/train': 7.086932182312012}
-03/03/2022 13:41:01 - INFO - codeparrot_training - Step 222: {'lr': 5.55e-05, 'samples': 114176, 'steps': 222, 'loss/train': 7.5683746337890625}
-03/03/2022 13:41:04 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/03/2022 13:41:06 - INFO - codeparrot_training - Step 223: {'lr': 5.575e-05, 'samples': 114688, 'steps': 223, 'loss/train': 6.692105770111084}
-03/03/2022 13:41:09 - INFO - codeparrot_training - Step 224: {'lr': 5.6e-05, 'samples': 115200, 'steps': 224, 'loss/train': 7.558428764343262}
-03/03/2022 13:41:12 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/03/2022 13:41:14 - INFO - codeparrot_training - Step 225: {'lr': 5.6250000000000005e-05, 'samples': 115712, 'steps': 225, 'loss/train': 7.024529457092285}
-03/03/2022 13:41:18 - INFO - codeparrot_training - Step 226: {'lr': 5.6500000000000005e-05, 'samples': 116224, 'steps': 226, 'loss/train': 7.132439613342285}
-03/03/2022 13:41:20 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/03/2022 13:41:23 - INFO - codeparrot_training - Step 227: {'lr': 5.6750000000000004e-05, 'samples': 116736, 'steps': 227, 'loss/train': 7.505816459655762}
-03/03/2022 13:41:26 - INFO - codeparrot_training - Step 228: {'lr': 5.7e-05, 'samples': 117248, 'steps': 228, 'loss/train': 7.923880100250244}
-03/03/2022 13:41:28 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/03/2022 13:41:31 - INFO - codeparrot_training - Step 229: {'lr': 5.725e-05, 'samples': 117760, 'steps': 229, 'loss/train': 8.218132019042969}
-03/03/2022 13:41:34 - INFO - codeparrot_training - Step 230: {'lr': 5.75e-05, 'samples': 118272, 'steps': 230, 'loss/train': 6.376003742218018}
-03/03/2022 13:41:37 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/03/2022 13:41:40 - INFO - codeparrot_training - Step 231: {'lr': 5.775e-05, 'samples': 118784, 'steps': 231, 'loss/train': 7.3082990646362305}
-03/03/2022 13:41:43 - INFO - codeparrot_training - Step 232: {'lr': 5.800000000000001e-05, 'samples': 119296, 'steps': 232, 'loss/train': 7.335635662078857}
-03/03/2022 13:41:46 - INFO - codeparrot_training - Step 233: {'lr': 5.8250000000000006e-05, 'samples': 119808, 'steps': 233, 'loss/train': 6.83720064163208}
-03/03/2022 13:41:46 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/03/2022 13:41:52 - INFO - codeparrot_training - Step 234: {'lr': 5.8500000000000006e-05, 'samples': 120320, 'steps': 234, 'loss/train': 6.864739894866943}
-03/03/2022 13:41:55 - INFO - codeparrot_training - Step 235: {'lr': 5.875e-05, 'samples': 120832, 'steps': 235, 'loss/train': 8.335467338562012}
-03/03/2022 13:41:55 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 13:42:00 - INFO - codeparrot_training - Step 236: {'lr': 5.9e-05, 'samples': 121344, 'steps': 236, 'loss/train': 6.926678657531738}
-03/03/2022 13:42:03 - INFO - codeparrot_training - Step 237: {'lr': 5.925e-05, 'samples': 121856, 'steps': 237, 'loss/train': 6.76780891418457}
-03/03/2022 13:42:03 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/03/2022 13:42:08 - INFO - codeparrot_training - Step 238: {'lr': 5.9499999999999996e-05, 'samples': 122368, 'steps': 238, 'loss/train': 7.604316711425781}
-03/03/2022 13:42:12 - INFO - codeparrot_training - Step 239: {'lr': 5.9749999999999995e-05, 'samples': 122880, 'steps': 239, 'loss/train': 7.477373123168945}
-03/03/2022 13:42:12 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/03/2022 13:42:17 - INFO - codeparrot_training - Step 240: {'lr': 6e-05, 'samples': 123392, 'steps': 240, 'loss/train': 6.324827671051025}
-03/03/2022 13:42:20 - INFO - codeparrot_training - Step 241: {'lr': 6.025e-05, 'samples': 123904, 'steps': 241, 'loss/train': 7.703766822814941}
-03/03/2022 13:42:20 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/03/2022 13:42:25 - INFO - codeparrot_training - Step 242: {'lr': 6.05e-05, 'samples': 124416, 'steps': 242, 'loss/train': 7.568194389343262}
-03/03/2022 13:42:28 - INFO - codeparrot_training - Step 243: {'lr': 6.075e-05, 'samples': 124928, 'steps': 243, 'loss/train': 7.032049655914307}
-03/03/2022 13:42:28 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/03/2022 13:42:34 - INFO - codeparrot_training - Step 244: {'lr': 6.1e-05, 'samples': 125440, 'steps': 244, 'loss/train': 7.975718021392822}
-03/03/2022 13:42:37 - INFO - codeparrot_training - Step 245: {'lr': 6.125e-05, 'samples': 125952, 'steps': 245, 'loss/train': 9.234091758728027}
-03/03/2022 13:42:37 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/03/2022 13:42:42 - INFO - codeparrot_training - Step 246: {'lr': 6.15e-05, 'samples': 126464, 'steps': 246, 'loss/train': 7.30528450012207}
-03/03/2022 13:42:45 - INFO - codeparrot_training - Step 247: {'lr': 6.175e-05, 'samples': 126976, 'steps': 247, 'loss/train': 7.250826835632324}
-03/03/2022 13:42:46 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/03/2022 13:42:50 - INFO - codeparrot_training - Step 248: {'lr': 6.2e-05, 'samples': 127488, 'steps': 248, 'loss/train': 7.167181968688965}
-03/03/2022 13:42:54 - INFO - codeparrot_training - Step 249: {'lr': 6.225e-05, 'samples': 128000, 'steps': 249, 'loss/train': 7.492107391357422}
-03/03/2022 13:42:54 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/03/2022 13:42:59 - INFO - codeparrot_training - Step 250: {'lr': 6.25e-05, 'samples': 128512, 'steps': 250, 'loss/train': 7.4001617431640625}
-03/03/2022 13:43:02 - INFO - codeparrot_training - Step 251: {'lr': 6.275000000000001e-05, 'samples': 129024, 'steps': 251, 'loss/train': 7.7985920906066895}
-03/03/2022 13:43:03 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/03/2022 13:43:07 - INFO - codeparrot_training - Step 252: {'lr': 6.3e-05, 'samples': 129536, 'steps': 252, 'loss/train': 7.012681007385254}
-03/03/2022 13:43:10 - INFO - codeparrot_training - Step 253: {'lr': 6.325e-05, 'samples': 130048, 'steps': 253, 'loss/train': 7.037346839904785}
-03/03/2022 13:43:11 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/03/2022 13:43:16 - INFO - codeparrot_training - Step 254: {'lr': 6.35e-05, 'samples': 130560, 'steps': 254, 'loss/train': 6.874361991882324}
-03/03/2022 13:43:19 - INFO - codeparrot_training - Step 255: {'lr': 6.375e-05, 'samples': 131072, 'steps': 255, 'loss/train': 8.25483512878418}
-03/03/2022 13:43:19 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/03/2022 13:43:24 - INFO - codeparrot_training - Step 256: {'lr': 6.4e-05, 'samples': 131584, 'steps': 256, 'loss/train': 7.541172981262207}
-03/03/2022 13:43:27 - INFO - codeparrot_training - Step 257: {'lr': 6.425e-05, 'samples': 132096, 'steps': 257, 'loss/train': 7.457941055297852}
-03/03/2022 13:43:28 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/03/2022 13:43:33 - INFO - codeparrot_training - Step 258: {'lr': 6.450000000000001e-05, 'samples': 132608, 'steps': 258, 'loss/train': 7.014778137207031}
-03/03/2022 13:43:36 - INFO - codeparrot_training - Step 259: {'lr': 6.475e-05, 'samples': 133120, 'steps': 259, 'loss/train': 6.806115627288818}
-03/03/2022 13:43:36 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/03/2022 13:43:41 - INFO - codeparrot_training - Step 260: {'lr': 6.500000000000001e-05, 'samples': 133632, 'steps': 260, 'loss/train': 7.267054557800293}
-03/03/2022 13:43:44 - INFO - codeparrot_training - Step 261: {'lr': 6.525e-05, 'samples': 134144, 'steps': 261, 'loss/train': 6.713515758514404}
-03/03/2022 13:43:44 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/03/2022 13:43:49 - INFO - codeparrot_training - Step 262: {'lr': 6.55e-05, 'samples': 134656, 'steps': 262, 'loss/train': 7.091745853424072}
-03/03/2022 13:43:52 - INFO - codeparrot_training - Step 263: {'lr': 6.575e-05, 'samples': 135168, 'steps': 263, 'loss/train': 7.467846393585205}
-03/03/2022 13:43:52 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/03/2022 13:43:58 - INFO - codeparrot_training - Step 264: {'lr': 6.6e-05, 'samples': 135680, 'steps': 264, 'loss/train': 6.91502046585083}
-03/03/2022 13:44:01 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/03/2022 13:44:03 - INFO - codeparrot_training - Step 265: {'lr': 6.625000000000001e-05, 'samples': 136192, 'steps': 265, 'loss/train': 6.923452854156494}
-03/03/2022 13:44:06 - INFO - codeparrot_training - Step 266: {'lr': 6.65e-05, 'samples': 136704, 'steps': 266, 'loss/train': 7.499436378479004}
-03/03/2022 13:44:09 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/03/2022 13:44:11 - INFO - codeparrot_training - Step 267: {'lr': 6.675000000000001e-05, 'samples': 137216, 'steps': 267, 'loss/train': 7.343801975250244}
-03/03/2022 13:44:15 - INFO - codeparrot_training - Step 268: {'lr': 6.7e-05, 'samples': 137728, 'steps': 268, 'loss/train': 7.012816905975342}
-03/03/2022 13:44:17 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 13:44:20 - INFO - codeparrot_training - Step 269: {'lr': 6.725000000000001e-05, 'samples': 138240, 'steps': 269, 'loss/train': 7.881154537200928}
-03/03/2022 13:44:23 - INFO - codeparrot_training - Step 270: {'lr': 6.75e-05, 'samples': 138752, 'steps': 270, 'loss/train': 7.508479118347168}
-03/03/2022 13:44:26 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/03/2022 13:44:28 - INFO - codeparrot_training - Step 271: {'lr': 6.775000000000001e-05, 'samples': 139264, 'steps': 271, 'loss/train': 6.856858730316162}
-03/03/2022 13:44:31 - INFO - codeparrot_training - Step 272: {'lr': 6.800000000000001e-05, 'samples': 139776, 'steps': 272, 'loss/train': 7.2710041999816895}
-03/03/2022 13:44:34 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/03/2022 13:44:37 - INFO - codeparrot_training - Step 273: {'lr': 6.825e-05, 'samples': 140288, 'steps': 273, 'loss/train': 6.965377330780029}
-03/03/2022 13:44:41 - INFO - codeparrot_training - Step 274: {'lr': 6.850000000000001e-05, 'samples': 140800, 'steps': 274, 'loss/train': 6.166491985321045}
-03/03/2022 13:44:44 - INFO - codeparrot_training - Step 275: {'lr': 6.875e-05, 'samples': 141312, 'steps': 275, 'loss/train': 7.818729877471924}
-03/03/2022 13:44:45 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/03/2022 13:44:49 - INFO - codeparrot_training - Step 276: {'lr': 6.900000000000001e-05, 'samples': 141824, 'steps': 276, 'loss/train': 6.974045753479004}
-03/03/2022 13:44:52 - INFO - codeparrot_training - Step 277: {'lr': 6.925e-05, 'samples': 142336, 'steps': 277, 'loss/train': 6.823301792144775}
-03/03/2022 13:44:54 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/03/2022 13:44:57 - INFO - codeparrot_training - Step 278: {'lr': 6.950000000000001e-05, 'samples': 142848, 'steps': 278, 'loss/train': 7.374868392944336}
-03/03/2022 13:45:01 - INFO - codeparrot_training - Step 279: {'lr': 6.975e-05, 'samples': 143360, 'steps': 279, 'loss/train': 7.211111068725586}
-03/03/2022 13:45:02 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/03/2022 13:45:06 - INFO - codeparrot_training - Step 280: {'lr': 7.000000000000001e-05, 'samples': 143872, 'steps': 280, 'loss/train': 7.095859527587891}
-03/03/2022 13:45:09 - INFO - codeparrot_training - Step 281: {'lr': 7.025000000000001e-05, 'samples': 144384, 'steps': 281, 'loss/train': 6.3933634757995605}
-03/03/2022 13:45:10 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 13:45:14 - INFO - codeparrot_training - Step 282: {'lr': 7.049999999999999e-05, 'samples': 144896, 'steps': 282, 'loss/train': 8.225425720214844}
-03/03/2022 13:45:17 - INFO - codeparrot_training - Step 283: {'lr': 7.075e-05, 'samples': 145408, 'steps': 283, 'loss/train': 6.789872646331787}
-03/03/2022 13:45:19 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/03/2022 13:45:23 - INFO - codeparrot_training - Step 284: {'lr': 7.099999999999999e-05, 'samples': 145920, 'steps': 284, 'loss/train': 7.208834171295166}
-03/03/2022 13:45:26 - INFO - codeparrot_training - Step 285: {'lr': 7.125e-05, 'samples': 146432, 'steps': 285, 'loss/train': 5.778796672821045}
-03/03/2022 13:45:27 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/03/2022 13:45:31 - INFO - codeparrot_training - Step 286: {'lr': 7.149999999999999e-05, 'samples': 146944, 'steps': 286, 'loss/train': 6.7907490730285645}
-03/03/2022 13:45:34 - INFO - codeparrot_training - Step 287: {'lr': 7.175e-05, 'samples': 147456, 'steps': 287, 'loss/train': 6.667514801025391}
-03/03/2022 13:45:35 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/03/2022 13:45:39 - INFO - codeparrot_training - Step 288: {'lr': 7.2e-05, 'samples': 147968, 'steps': 288, 'loss/train': 7.220056533813477}
-03/03/2022 13:45:43 - INFO - codeparrot_training - Step 289: {'lr': 7.225e-05, 'samples': 148480, 'steps': 289, 'loss/train': 6.969030380249023}
-03/03/2022 13:45:44 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/03/2022 13:45:48 - INFO - codeparrot_training - Step 290: {'lr': 7.25e-05, 'samples': 148992, 'steps': 290, 'loss/train': 7.167079925537109}
-03/03/2022 13:45:51 - INFO - codeparrot_training - Step 291: {'lr': 7.274999999999999e-05, 'samples': 149504, 'steps': 291, 'loss/train': 7.262547016143799}
-03/03/2022 13:45:52 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/03/2022 13:45:56 - INFO - codeparrot_training - Step 292: {'lr': 7.3e-05, 'samples': 150016, 'steps': 292, 'loss/train': 7.280813694000244}
-03/03/2022 13:45:59 - INFO - codeparrot_training - Step 293: {'lr': 7.324999999999999e-05, 'samples': 150528, 'steps': 293, 'loss/train': 6.34620475769043}
-03/03/2022 13:46:00 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/03/2022 13:46:05 - INFO - codeparrot_training - Step 294: {'lr': 7.35e-05, 'samples': 151040, 'steps': 294, 'loss/train': 7.634270191192627}
-03/03/2022 13:46:08 - INFO - codeparrot_training - Step 295: {'lr': 7.375e-05, 'samples': 151552, 'steps': 295, 'loss/train': 4.9720330238342285}
-03/03/2022 13:46:10 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/03/2022 13:46:13 - INFO - codeparrot_training - Step 296: {'lr': 7.4e-05, 'samples': 152064, 'steps': 296, 'loss/train': 7.290252208709717}
-03/03/2022 13:46:16 - INFO - codeparrot_training - Step 297: {'lr': 7.425e-05, 'samples': 152576, 'steps': 297, 'loss/train': 7.179178237915039}
-03/03/2022 13:46:18 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/03/2022 13:46:22 - INFO - codeparrot_training - Step 298: {'lr': 7.45e-05, 'samples': 153088, 'steps': 298, 'loss/train': 8.177205085754395}
-03/03/2022 13:46:25 - INFO - codeparrot_training - Step 299: {'lr': 7.475e-05, 'samples': 153600, 'steps': 299, 'loss/train': 7.102594375610352}
-03/03/2022 13:46:26 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/03/2022 13:46:30 - INFO - codeparrot_training - Step 300: {'lr': 7.5e-05, 'samples': 154112, 'steps': 300, 'loss/train': 7.6582746505737305}
-03/03/2022 13:46:33 - INFO - codeparrot_training - Step 301: {'lr': 7.525e-05, 'samples': 154624, 'steps': 301, 'loss/train': 3.4812848567962646}
-03/03/2022 13:46:34 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/03/2022 13:46:38 - INFO - codeparrot_training - Step 302: {'lr': 7.55e-05, 'samples': 155136, 'steps': 302, 'loss/train': 6.857351779937744}
-03/03/2022 13:46:42 - INFO - codeparrot_training - Step 303: {'lr': 7.575e-05, 'samples': 155648, 'steps': 303, 'loss/train': 7.291689395904541}
-03/03/2022 13:46:43 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/03/2022 13:46:47 - INFO - codeparrot_training - Step 304: {'lr': 7.6e-05, 'samples': 156160, 'steps': 304, 'loss/train': 7.73492431640625}
-03/03/2022 13:46:50 - INFO - codeparrot_training - Step 305: {'lr': 7.625e-05, 'samples': 156672, 'steps': 305, 'loss/train': 7.737000942230225}
-03/03/2022 13:46:51 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/03/2022 13:46:55 - INFO - codeparrot_training - Step 306: {'lr': 7.65e-05, 'samples': 157184, 'steps': 306, 'loss/train': 6.85874605178833}
-03/03/2022 13:46:58 - INFO - codeparrot_training - Step 307: {'lr': 7.675e-05, 'samples': 157696, 'steps': 307, 'loss/train': 6.972065448760986}
-03/03/2022 13:47:00 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/03/2022 13:47:04 - INFO - codeparrot_training - Step 308: {'lr': 7.7e-05, 'samples': 158208, 'steps': 308, 'loss/train': 7.307086944580078}
-03/03/2022 13:47:07 - INFO - codeparrot_training - Step 309: {'lr': 7.725000000000001e-05, 'samples': 158720, 'steps': 309, 'loss/train': 7.4384050369262695}
-03/03/2022 13:47:08 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 13:47:12 - INFO - codeparrot_training - Step 310: {'lr': 7.75e-05, 'samples': 159232, 'steps': 310, 'loss/train': 7.601604461669922}
-03/03/2022 13:47:15 - INFO - codeparrot_training - Step 311: {'lr': 7.775e-05, 'samples': 159744, 'steps': 311, 'loss/train': 7.247878551483154}
-03/03/2022 13:47:16 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/03/2022 13:47:20 - INFO - codeparrot_training - Step 312: {'lr': 7.8e-05, 'samples': 160256, 'steps': 312, 'loss/train': 6.91134786605835}
-03/03/2022 13:47:24 - INFO - codeparrot_training - Step 313: {'lr': 7.825e-05, 'samples': 160768, 'steps': 313, 'loss/train': 7.499279499053955}
-03/03/2022 13:47:24 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/03/2022 13:47:29 - INFO - codeparrot_training - Step 314: {'lr': 7.85e-05, 'samples': 161280, 'steps': 314, 'loss/train': 7.371830463409424}
-03/03/2022 13:47:32 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/03/2022 13:47:34 - INFO - codeparrot_training - Step 315: {'lr': 7.875e-05, 'samples': 161792, 'steps': 315, 'loss/train': 7.107333660125732}
-03/03/2022 13:47:38 - INFO - codeparrot_training - Step 316: {'lr': 7.9e-05, 'samples': 162304, 'steps': 316, 'loss/train': 8.673299789428711}
-03/03/2022 13:47:41 - INFO - codeparrot_training - Step 317: {'lr': 7.925e-05, 'samples': 162816, 'steps': 317, 'loss/train': 7.807727813720703}
-03/03/2022 13:47:42 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/03/2022 13:47:46 - INFO - codeparrot_training - Step 318: {'lr': 7.950000000000001e-05, 'samples': 163328, 'steps': 318, 'loss/train': 7.118139266967773}
-03/03/2022 13:47:49 - INFO - codeparrot_training - Step 319: {'lr': 7.975e-05, 'samples': 163840, 'steps': 319, 'loss/train': 7.224991321563721}
-03/03/2022 13:47:51 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/03/2022 13:47:55 - INFO - codeparrot_training - Step 320: {'lr': 8e-05, 'samples': 164352, 'steps': 320, 'loss/train': 7.151127338409424}
-03/03/2022 13:47:58 - INFO - codeparrot_training - Step 321: {'lr': 8.025e-05, 'samples': 164864, 'steps': 321, 'loss/train': 6.802467346191406}
-03/03/2022 13:47:59 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/03/2022 13:48:03 - INFO - codeparrot_training - Step 322: {'lr': 8.05e-05, 'samples': 165376, 'steps': 322, 'loss/train': 7.11800479888916}
-03/03/2022 13:48:06 - INFO - codeparrot_training - Step 323: {'lr': 8.075e-05, 'samples': 165888, 'steps': 323, 'loss/train': 6.9256367683410645}
-03/03/2022 13:48:07 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/03/2022 13:48:12 - INFO - codeparrot_training - Step 324: {'lr': 8.1e-05, 'samples': 166400, 'steps': 324, 'loss/train': 5.947310924530029}
-03/03/2022 13:48:15 - INFO - codeparrot_training - Step 325: {'lr': 8.125000000000001e-05, 'samples': 166912, 'steps': 325, 'loss/train': 7.745260238647461}
-03/03/2022 13:48:17 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/03/2022 13:48:20 - INFO - codeparrot_training - Step 326: {'lr': 8.15e-05, 'samples': 167424, 'steps': 326, 'loss/train': 6.477266311645508}
-03/03/2022 13:48:23 - INFO - codeparrot_training - Step 327: {'lr': 8.175000000000001e-05, 'samples': 167936, 'steps': 327, 'loss/train': 7.103150844573975}
-03/03/2022 13:48:25 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/03/2022 13:48:28 - INFO - codeparrot_training - Step 328: {'lr': 8.2e-05, 'samples': 168448, 'steps': 328, 'loss/train': 7.210000991821289}
-03/03/2022 13:48:31 - INFO - codeparrot_training - Step 329: {'lr': 8.225000000000001e-05, 'samples': 168960, 'steps': 329, 'loss/train': 5.856969833374023}
-03/03/2022 13:48:33 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/03/2022 13:48:37 - INFO - codeparrot_training - Step 330: {'lr': 8.25e-05, 'samples': 169472, 'steps': 330, 'loss/train': 7.112217426300049}
-03/03/2022 13:48:40 - INFO - codeparrot_training - Step 331: {'lr': 8.275e-05, 'samples': 169984, 'steps': 331, 'loss/train': 7.2972517013549805}
-03/03/2022 13:48:41 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/03/2022 13:48:45 - INFO - codeparrot_training - Step 332: {'lr': 8.300000000000001e-05, 'samples': 170496, 'steps': 332, 'loss/train': 6.872681140899658}
-03/03/2022 13:48:48 - INFO - codeparrot_training - Step 333: {'lr': 8.325e-05, 'samples': 171008, 'steps': 333, 'loss/train': 6.879507064819336}
-03/03/2022 13:48:49 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/03/2022 13:48:53 - INFO - codeparrot_training - Step 334: {'lr': 8.350000000000001e-05, 'samples': 171520, 'steps': 334, 'loss/train': 7.25621223449707}
-03/03/2022 13:48:56 - INFO - codeparrot_training - Step 335: {'lr': 8.375e-05, 'samples': 172032, 'steps': 335, 'loss/train': 6.667304515838623}
-03/03/2022 13:48:58 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/03/2022 13:49:02 - INFO - codeparrot_training - Step 336: {'lr': 8.400000000000001e-05, 'samples': 172544, 'steps': 336, 'loss/train': 7.273214817047119}
-03/03/2022 13:49:05 - INFO - codeparrot_training - Step 337: {'lr': 8.425e-05, 'samples': 173056, 'steps': 337, 'loss/train': 7.189443588256836}
-03/03/2022 13:49:06 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/03/2022 13:49:10 - INFO - codeparrot_training - Step 338: {'lr': 8.450000000000001e-05, 'samples': 173568, 'steps': 338, 'loss/train': 6.605391025543213}
-03/03/2022 13:49:13 - INFO - codeparrot_training - Step 339: {'lr': 8.475000000000001e-05, 'samples': 174080, 'steps': 339, 'loss/train': 6.908782005310059}
-03/03/2022 13:49:14 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/03/2022 13:49:18 - INFO - codeparrot_training - Step 340: {'lr': 8.5e-05, 'samples': 174592, 'steps': 340, 'loss/train': 6.747285842895508}
-03/03/2022 13:49:22 - INFO - codeparrot_training - Step 341: {'lr': 8.525000000000001e-05, 'samples': 175104, 'steps': 341, 'loss/train': 6.820441246032715}
-03/03/2022 13:49:22 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/03/2022 13:49:27 - INFO - codeparrot_training - Step 342: {'lr': 8.55e-05, 'samples': 175616, 'steps': 342, 'loss/train': 7.335867404937744}
-03/03/2022 13:49:30 - INFO - codeparrot_training - Step 343: {'lr': 8.575000000000001e-05, 'samples': 176128, 'steps': 343, 'loss/train': 6.804535388946533}
-03/03/2022 13:49:31 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/03/2022 13:49:35 - INFO - codeparrot_training - Step 344: {'lr': 8.599999999999999e-05, 'samples': 176640, 'steps': 344, 'loss/train': 7.3406500816345215}
-03/03/2022 13:49:38 - INFO - codeparrot_training - Step 345: {'lr': 8.625e-05, 'samples': 177152, 'steps': 345, 'loss/train': 6.626857757568359}
-03/03/2022 13:49:39 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/03/2022 13:49:44 - INFO - codeparrot_training - Step 346: {'lr': 8.65e-05, 'samples': 177664, 'steps': 346, 'loss/train': 6.793419361114502}
-03/03/2022 13:49:47 - INFO - codeparrot_training - Step 347: {'lr': 8.675e-05, 'samples': 178176, 'steps': 347, 'loss/train': 6.759413242340088}
-03/03/2022 13:49:47 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/03/2022 13:49:52 - INFO - codeparrot_training - Step 348: {'lr': 8.7e-05, 'samples': 178688, 'steps': 348, 'loss/train': 6.160068035125732}
-03/03/2022 13:49:55 - INFO - codeparrot_training - Step 349: {'lr': 8.724999999999999e-05, 'samples': 179200, 'steps': 349, 'loss/train': 7.11178731918335}
-03/03/2022 13:49:55 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/03/2022 13:50:00 - INFO - codeparrot_training - Step 350: {'lr': 8.75e-05, 'samples': 179712, 'steps': 350, 'loss/train': 6.960474014282227}
-03/03/2022 13:50:03 - INFO - codeparrot_training - Step 351: {'lr': 8.774999999999999e-05, 'samples': 180224, 'steps': 351, 'loss/train': 7.643229961395264}
-03/03/2022 13:50:04 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/03/2022 13:50:09 - INFO - codeparrot_training - Step 352: {'lr': 8.8e-05, 'samples': 180736, 'steps': 352, 'loss/train': 6.8332319259643555}
-03/03/2022 13:50:12 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/03/2022 13:50:14 - INFO - codeparrot_training - Step 353: {'lr': 8.824999999999999e-05, 'samples': 181248, 'steps': 353, 'loss/train': 6.829087734222412}
-03/03/2022 13:50:17 - INFO - codeparrot_training - Step 354: {'lr': 8.85e-05, 'samples': 181760, 'steps': 354, 'loss/train': 6.977699279785156}
-03/03/2022 13:50:20 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/03/2022 13:50:23 - INFO - codeparrot_training - Step 355: {'lr': 8.875e-05, 'samples': 182272, 'steps': 355, 'loss/train': 7.036928653717041}
-03/03/2022 13:50:26 - INFO - codeparrot_training - Step 356: {'lr': 8.9e-05, 'samples': 182784, 'steps': 356, 'loss/train': 6.960824489593506}
-03/03/2022 13:50:29 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/03/2022 13:50:31 - INFO - codeparrot_training - Step 357: {'lr': 8.925e-05, 'samples': 183296, 'steps': 357, 'loss/train': 6.745418071746826}
-03/03/2022 13:50:34 - INFO - codeparrot_training - Step 358: {'lr': 8.95e-05, 'samples': 183808, 'steps': 358, 'loss/train': 6.919394493103027}
-03/03/2022 13:50:37 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/03/2022 13:50:40 - INFO - codeparrot_training - Step 359: {'lr': 8.975e-05, 'samples': 184320, 'steps': 359, 'loss/train': 6.71176815032959}
-03/03/2022 13:50:43 - INFO - codeparrot_training - Step 360: {'lr': 8.999999999999999e-05, 'samples': 184832, 'steps': 360, 'loss/train': 6.548521518707275}
-03/03/2022 13:50:46 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/03/2022 13:50:48 - INFO - codeparrot_training - Step 361: {'lr': 9.025e-05, 'samples': 185344, 'steps': 361, 'loss/train': 7.599088668823242}
-03/03/2022 13:50:51 - INFO - codeparrot_training - Step 362: {'lr': 9.05e-05, 'samples': 185856, 'steps': 362, 'loss/train': 6.143686294555664}
-03/03/2022 13:50:54 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/03/2022 13:50:56 - INFO - codeparrot_training - Step 363: {'lr': 9.075e-05, 'samples': 186368, 'steps': 363, 'loss/train': 7.022943019866943}
-03/03/2022 13:51:00 - INFO - codeparrot_training - Step 364: {'lr': 9.1e-05, 'samples': 186880, 'steps': 364, 'loss/train': 6.801090240478516}
-03/03/2022 13:51:02 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/03/2022 13:51:05 - INFO - codeparrot_training - Step 365: {'lr': 9.125e-05, 'samples': 187392, 'steps': 365, 'loss/train': 6.444828510284424}
-03/03/2022 13:51:08 - INFO - codeparrot_training - Step 366: {'lr': 9.15e-05, 'samples': 187904, 'steps': 366, 'loss/train': 5.071739673614502}
-03/03/2022 13:51:10 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/03/2022 13:51:13 - INFO - codeparrot_training - Step 367: {'lr': 9.175e-05, 'samples': 188416, 'steps': 367, 'loss/train': 7.660885334014893}
-03/03/2022 13:51:17 - INFO - codeparrot_training - Step 368: {'lr': 9.2e-05, 'samples': 188928, 'steps': 368, 'loss/train': 6.027246952056885}
-03/03/2022 13:51:19 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/03/2022 13:51:22 - INFO - codeparrot_training - Step 369: {'lr': 9.225e-05, 'samples': 189440, 'steps': 369, 'loss/train': 7.053032398223877}
-03/03/2022 13:51:25 - INFO - codeparrot_training - Step 370: {'lr': 9.25e-05, 'samples': 189952, 'steps': 370, 'loss/train': 7.259976863861084}
-03/03/2022 13:51:27 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 13:51:30 - INFO - codeparrot_training - Step 371: {'lr': 9.275e-05, 'samples': 190464, 'steps': 371, 'loss/train': 3.8937602043151855}
-03/03/2022 13:51:33 - INFO - codeparrot_training - Step 372: {'lr': 9.3e-05, 'samples': 190976, 'steps': 372, 'loss/train': 6.874353408813477}
-03/03/2022 13:51:35 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/03/2022 13:51:38 - INFO - codeparrot_training - Step 373: {'lr': 9.325e-05, 'samples': 191488, 'steps': 373, 'loss/train': 6.929388523101807}
-03/03/2022 13:51:42 - INFO - codeparrot_training - Step 374: {'lr': 9.35e-05, 'samples': 192000, 'steps': 374, 'loss/train': 6.950829029083252}
-03/03/2022 13:51:44 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/03/2022 13:51:47 - INFO - codeparrot_training - Step 375: {'lr': 9.375e-05, 'samples': 192512, 'steps': 375, 'loss/train': 6.641457557678223}
-03/03/2022 13:51:50 - INFO - codeparrot_training - Step 376: {'lr': 9.400000000000001e-05, 'samples': 193024, 'steps': 376, 'loss/train': 4.135335445404053}
-03/03/2022 13:51:52 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/03/2022 13:51:55 - INFO - codeparrot_training - Step 377: {'lr': 9.425e-05, 'samples': 193536, 'steps': 377, 'loss/train': 6.767242908477783}
-03/03/2022 13:51:58 - INFO - codeparrot_training - Step 378: {'lr': 9.45e-05, 'samples': 194048, 'steps': 378, 'loss/train': 7.012984275817871}
-03/03/2022 13:52:00 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/03/2022 13:52:04 - INFO - codeparrot_training - Step 379: {'lr': 9.475e-05, 'samples': 194560, 'steps': 379, 'loss/train': 6.804805278778076}
-03/03/2022 13:52:07 - INFO - codeparrot_training - Step 380: {'lr': 9.5e-05, 'samples': 195072, 'steps': 380, 'loss/train': 7.384415626525879}
-03/03/2022 13:52:08 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/03/2022 13:52:12 - INFO - codeparrot_training - Step 381: {'lr': 9.525e-05, 'samples': 195584, 'steps': 381, 'loss/train': 8.17817211151123}
-03/03/2022 13:52:15 - INFO - codeparrot_training - Step 382: {'lr': 9.55e-05, 'samples': 196096, 'steps': 382, 'loss/train': 7.321182727813721}
-03/03/2022 13:52:16 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/03/2022 13:52:20 - INFO - codeparrot_training - Step 383: {'lr': 9.575000000000001e-05, 'samples': 196608, 'steps': 383, 'loss/train': 7.84943962097168}
-03/03/2022 13:52:24 - INFO - codeparrot_training - Step 384: {'lr': 9.6e-05, 'samples': 197120, 'steps': 384, 'loss/train': 3.7669484615325928}
-03/03/2022 13:52:25 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/03/2022 13:52:29 - INFO - codeparrot_training - Step 385: {'lr': 9.625000000000001e-05, 'samples': 197632, 'steps': 385, 'loss/train': 7.072676181793213}
-03/03/2022 13:52:32 - INFO - codeparrot_training - Step 386: {'lr': 9.65e-05, 'samples': 198144, 'steps': 386, 'loss/train': 6.100987434387207}
-03/03/2022 13:52:33 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/03/2022 13:52:37 - INFO - codeparrot_training - Step 387: {'lr': 9.675000000000001e-05, 'samples': 198656, 'steps': 387, 'loss/train': 7.215890407562256}
-03/03/2022 13:52:40 - INFO - codeparrot_training - Step 388: {'lr': 9.7e-05, 'samples': 199168, 'steps': 388, 'loss/train': 7.250863552093506}
-03/03/2022 13:52:42 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/03/2022 13:52:46 - INFO - codeparrot_training - Step 389: {'lr': 9.725e-05, 'samples': 199680, 'steps': 389, 'loss/train': 6.301525592803955}
-03/03/2022 13:52:49 - INFO - codeparrot_training - Step 390: {'lr': 9.750000000000001e-05, 'samples': 200192, 'steps': 390, 'loss/train': 5.155089855194092}
-03/03/2022 13:52:50 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/03/2022 13:52:54 - INFO - codeparrot_training - Step 391: {'lr': 9.775e-05, 'samples': 200704, 'steps': 391, 'loss/train': 6.642797470092773}
-03/03/2022 13:52:57 - INFO - codeparrot_training - Step 392: {'lr': 9.800000000000001e-05, 'samples': 201216, 'steps': 392, 'loss/train': 7.064353942871094}
-03/03/2022 13:52:58 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/03/2022 13:53:03 - INFO - codeparrot_training - Step 393: {'lr': 9.825e-05, 'samples': 201728, 'steps': 393, 'loss/train': 6.936179161071777}
-03/03/2022 13:53:06 - INFO - codeparrot_training - Step 394: {'lr': 9.850000000000001e-05, 'samples': 202240, 'steps': 394, 'loss/train': 7.061115264892578}
-03/03/2022 13:53:11 - INFO - codeparrot_training - Step 395: {'lr': 9.875e-05, 'samples': 202752, 'steps': 395, 'loss/train': 5.386733531951904}
-03/03/2022 13:53:14 - INFO - codeparrot_training - Step 396: {'lr': 9.900000000000001e-05, 'samples': 203264, 'steps': 396, 'loss/train': 3.390434503555298}
-03/03/2022 13:53:16 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/03/2022 13:53:20 - INFO - codeparrot_training - Step 397: {'lr': 9.925000000000001e-05, 'samples': 203776, 'steps': 397, 'loss/train': 6.450808048248291}
-03/03/2022 13:53:23 - INFO - codeparrot_training - Step 398: {'lr': 9.95e-05, 'samples': 204288, 'steps': 398, 'loss/train': 7.519935607910156}
-03/03/2022 13:53:23 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/03/2022 13:53:28 - INFO - codeparrot_training - Step 399: {'lr': 9.975000000000001e-05, 'samples': 204800, 'steps': 399, 'loss/train': 6.9697794914245605}
-03/03/2022 13:53:31 - INFO - codeparrot_training - Step 400: {'lr': 0.0001, 'samples': 205312, 'steps': 400, 'loss/train': 6.924061298370361}
-03/03/2022 13:53:32 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/03/2022 13:53:36 - INFO - codeparrot_training - Step 401: {'lr': 0.00010025000000000001, 'samples': 205824, 'steps': 401, 'loss/train': 6.575358867645264}
-03/03/2022 13:53:39 - INFO - codeparrot_training - Step 402: {'lr': 0.0001005, 'samples': 206336, 'steps': 402, 'loss/train': 6.773837566375732}
-03/03/2022 13:53:40 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/03/2022 13:53:45 - INFO - codeparrot_training - Step 403: {'lr': 0.00010075000000000001, 'samples': 206848, 'steps': 403, 'loss/train': 7.0787577629089355}
-03/03/2022 13:53:48 - INFO - codeparrot_training - Step 404: {'lr': 0.000101, 'samples': 207360, 'steps': 404, 'loss/train': 6.351315975189209}
-03/03/2022 13:53:48 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/03/2022 13:53:53 - INFO - codeparrot_training - Step 405: {'lr': 0.00010125000000000001, 'samples': 207872, 'steps': 405, 'loss/train': 6.846843719482422}
-03/03/2022 13:53:56 - INFO - codeparrot_training - Step 406: {'lr': 0.00010150000000000001, 'samples': 208384, 'steps': 406, 'loss/train': 6.861880302429199}
-03/03/2022 13:53:56 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/03/2022 13:54:01 - INFO - codeparrot_training - Step 407: {'lr': 0.00010174999999999999, 'samples': 208896, 'steps': 407, 'loss/train': 6.381140232086182}
-03/03/2022 13:54:05 - INFO - codeparrot_training - Step 408: {'lr': 0.000102, 'samples': 209408, 'steps': 408, 'loss/train': 4.809561729431152}
-03/03/2022 13:54:05 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/03/2022 13:54:10 - INFO - codeparrot_training - Step 409: {'lr': 0.00010224999999999999, 'samples': 209920, 'steps': 409, 'loss/train': 6.883728981018066}
-03/03/2022 13:54:13 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/03/2022 13:54:15 - INFO - codeparrot_training - Step 410: {'lr': 0.0001025, 'samples': 210432, 'steps': 410, 'loss/train': 6.608766078948975}
-03/03/2022 13:54:18 - INFO - codeparrot_training - Step 411: {'lr': 0.00010274999999999999, 'samples': 210944, 'steps': 411, 'loss/train': 7.535120487213135}
-03/03/2022 13:54:22 - INFO - codeparrot_training - Step 412: {'lr': 0.000103, 'samples': 211456, 'steps': 412, 'loss/train': 6.883657455444336}
-03/03/2022 13:54:22 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/03/2022 13:54:27 - INFO - codeparrot_training - Step 413: {'lr': 0.00010325, 'samples': 211968, 'steps': 413, 'loss/train': 7.207785129547119}
-03/03/2022 13:54:30 - INFO - codeparrot_training - Step 414: {'lr': 0.0001035, 'samples': 212480, 'steps': 414, 'loss/train': 6.686124324798584}
-03/03/2022 13:54:30 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/03/2022 13:54:35 - INFO - codeparrot_training - Step 415: {'lr': 0.00010375, 'samples': 212992, 'steps': 415, 'loss/train': 6.87024450302124}
-03/03/2022 13:54:38 - INFO - codeparrot_training - Step 416: {'lr': 0.000104, 'samples': 213504, 'steps': 416, 'loss/train': 6.131210803985596}
-03/03/2022 13:54:39 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/03/2022 13:54:44 - INFO - codeparrot_training - Step 417: {'lr': 0.00010425, 'samples': 214016, 'steps': 417, 'loss/train': 6.6527204513549805}
-03/03/2022 13:54:47 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/03/2022 13:54:49 - INFO - codeparrot_training - Step 418: {'lr': 0.00010449999999999999, 'samples': 214528, 'steps': 418, 'loss/train': 6.84839391708374}
-03/03/2022 13:54:52 - INFO - codeparrot_training - Step 419: {'lr': 0.00010475, 'samples': 215040, 'steps': 419, 'loss/train': 5.261308193206787}
-03/03/2022 13:54:55 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/03/2022 13:54:58 - INFO - codeparrot_training - Step 420: {'lr': 0.000105, 'samples': 215552, 'steps': 420, 'loss/train': 7.349946022033691}
-03/03/2022 13:55:01 - INFO - codeparrot_training - Step 421: {'lr': 0.00010525, 'samples': 216064, 'steps': 421, 'loss/train': 7.383358478546143}
-03/03/2022 13:55:03 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/03/2022 13:55:06 - INFO - codeparrot_training - Step 422: {'lr': 0.0001055, 'samples': 216576, 'steps': 422, 'loss/train': 7.277693271636963}
-03/03/2022 13:55:09 - INFO - codeparrot_training - Step 423: {'lr': 0.00010575, 'samples': 217088, 'steps': 423, 'loss/train': 7.099862098693848}
-03/03/2022 13:55:11 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/03/2022 13:55:15 - INFO - codeparrot_training - Step 424: {'lr': 0.000106, 'samples': 217600, 'steps': 424, 'loss/train': 7.674220561981201}
-03/03/2022 13:55:18 - INFO - codeparrot_training - Step 425: {'lr': 0.00010625, 'samples': 218112, 'steps': 425, 'loss/train': 6.961071014404297}
-03/03/2022 13:55:21 - INFO - codeparrot_training - Step 426: {'lr': 0.0001065, 'samples': 218624, 'steps': 426, 'loss/train': 7.311920642852783}
-03/03/2022 13:55:21 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/03/2022 13:55:26 - INFO - codeparrot_training - Step 427: {'lr': 0.00010675, 'samples': 219136, 'steps': 427, 'loss/train': 7.3586320877075195}
-03/03/2022 13:55:30 - INFO - codeparrot_training - Step 428: {'lr': 0.000107, 'samples': 219648, 'steps': 428, 'loss/train': 5.779116630554199}
-03/03/2022 13:55:30 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/03/2022 13:55:35 - INFO - codeparrot_training - Step 429: {'lr': 0.00010725, 'samples': 220160, 'steps': 429, 'loss/train': 7.076303005218506}
-03/03/2022 13:55:38 - INFO - codeparrot_training - Step 430: {'lr': 0.0001075, 'samples': 220672, 'steps': 430, 'loss/train': 7.492109298706055}
-03/03/2022 13:55:38 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/03/2022 13:55:43 - INFO - codeparrot_training - Step 431: {'lr': 0.00010775, 'samples': 221184, 'steps': 431, 'loss/train': 7.107940673828125}
-03/03/2022 13:55:46 - INFO - codeparrot_training - Step 432: {'lr': 0.000108, 'samples': 221696, 'steps': 432, 'loss/train': 6.590511322021484}
-03/03/2022 13:55:46 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/03/2022 13:55:52 - INFO - codeparrot_training - Step 433: {'lr': 0.00010825, 'samples': 222208, 'steps': 433, 'loss/train': 7.226790428161621}
-03/03/2022 13:55:54 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/03/2022 13:55:57 - INFO - codeparrot_training - Step 434: {'lr': 0.00010850000000000001, 'samples': 222720, 'steps': 434, 'loss/train': 5.3204731941223145}
-03/03/2022 13:56:00 - INFO - codeparrot_training - Step 435: {'lr': 0.00010875, 'samples': 223232, 'steps': 435, 'loss/train': 6.923895835876465}
-03/03/2022 13:56:03 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/03/2022 13:56:05 - INFO - codeparrot_training - Step 436: {'lr': 0.000109, 'samples': 223744, 'steps': 436, 'loss/train': 6.937617778778076}
-03/03/2022 13:56:08 - INFO - codeparrot_training - Step 437: {'lr': 0.00010925, 'samples': 224256, 'steps': 437, 'loss/train': 7.740363121032715}
-03/03/2022 13:56:11 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 13:56:14 - INFO - codeparrot_training - Step 438: {'lr': 0.0001095, 'samples': 224768, 'steps': 438, 'loss/train': 6.6068596839904785}
-03/03/2022 13:56:17 - INFO - codeparrot_training - Step 439: {'lr': 0.00010975, 'samples': 225280, 'steps': 439, 'loss/train': 6.751766204833984}
-03/03/2022 13:56:20 - INFO - codeparrot_training - Step 440: {'lr': 0.00011, 'samples': 225792, 'steps': 440, 'loss/train': 3.797227621078491}
-03/03/2022 13:56:20 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/03/2022 13:56:25 - INFO - codeparrot_training - Step 441: {'lr': 0.00011025, 'samples': 226304, 'steps': 441, 'loss/train': 6.906583309173584}
-03/03/2022 13:56:29 - INFO - codeparrot_training - Step 442: {'lr': 0.0001105, 'samples': 226816, 'steps': 442, 'loss/train': 6.599184036254883}
-03/03/2022 13:56:29 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/03/2022 13:56:34 - INFO - codeparrot_training - Step 443: {'lr': 0.00011075000000000001, 'samples': 227328, 'steps': 443, 'loss/train': 6.03370475769043}
-03/03/2022 13:56:37 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/03/2022 13:56:39 - INFO - codeparrot_training - Step 444: {'lr': 0.000111, 'samples': 227840, 'steps': 444, 'loss/train': 6.421036243438721}
-03/03/2022 13:56:42 - INFO - codeparrot_training - Step 445: {'lr': 0.00011125000000000001, 'samples': 228352, 'steps': 445, 'loss/train': 6.453313827514648}
-03/03/2022 13:56:45 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/03/2022 13:56:47 - INFO - codeparrot_training - Step 446: {'lr': 0.0001115, 'samples': 228864, 'steps': 446, 'loss/train': 6.5886664390563965}
-03/03/2022 13:56:51 - INFO - codeparrot_training - Step 447: {'lr': 0.00011175, 'samples': 229376, 'steps': 447, 'loss/train': 7.1440253257751465}
-03/03/2022 13:56:53 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/03/2022 13:56:56 - INFO - codeparrot_training - Step 448: {'lr': 0.000112, 'samples': 229888, 'steps': 448, 'loss/train': 6.501101016998291}
-03/03/2022 13:56:59 - INFO - codeparrot_training - Step 449: {'lr': 0.00011225, 'samples': 230400, 'steps': 449, 'loss/train': 6.9688544273376465}
-03/03/2022 13:57:02 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/03/2022 13:57:04 - INFO - codeparrot_training - Step 450: {'lr': 0.00011250000000000001, 'samples': 230912, 'steps': 450, 'loss/train': 7.000016689300537}
-03/03/2022 13:57:07 - INFO - codeparrot_training - Step 451: {'lr': 0.00011275, 'samples': 231424, 'steps': 451, 'loss/train': 6.349514961242676}
-03/03/2022 13:57:10 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/03/2022 13:57:13 - INFO - codeparrot_training - Step 452: {'lr': 0.00011300000000000001, 'samples': 231936, 'steps': 452, 'loss/train': 6.484461784362793}
-03/03/2022 13:57:16 - INFO - codeparrot_training - Step 453: {'lr': 0.00011325, 'samples': 232448, 'steps': 453, 'loss/train': 5.946240425109863}
-03/03/2022 13:57:18 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/03/2022 13:57:21 - INFO - codeparrot_training - Step 454: {'lr': 0.00011350000000000001, 'samples': 232960, 'steps': 454, 'loss/train': 6.402734756469727}
-03/03/2022 13:57:24 - INFO - codeparrot_training - Step 455: {'lr': 0.00011375, 'samples': 233472, 'steps': 455, 'loss/train': 6.981008052825928}
-03/03/2022 13:57:27 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/03/2022 13:57:30 - INFO - codeparrot_training - Step 456: {'lr': 0.000114, 'samples': 233984, 'steps': 456, 'loss/train': 7.203886032104492}
-03/03/2022 13:57:33 - INFO - codeparrot_training - Step 457: {'lr': 0.00011425000000000001, 'samples': 234496, 'steps': 457, 'loss/train': 6.602855205535889}
-03/03/2022 13:57:35 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/03/2022 13:57:38 - INFO - codeparrot_training - Step 458: {'lr': 0.0001145, 'samples': 235008, 'steps': 458, 'loss/train': 6.232977390289307}
-03/03/2022 13:57:41 - INFO - codeparrot_training - Step 459: {'lr': 0.00011475000000000001, 'samples': 235520, 'steps': 459, 'loss/train': 6.966612815856934}
-03/03/2022 13:57:43 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/03/2022 13:57:47 - INFO - codeparrot_training - Step 460: {'lr': 0.000115, 'samples': 236032, 'steps': 460, 'loss/train': 6.446167945861816}
-03/03/2022 13:57:50 - INFO - codeparrot_training - Step 461: {'lr': 0.00011525000000000001, 'samples': 236544, 'steps': 461, 'loss/train': 6.609718322753906}
-03/03/2022 13:57:52 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/03/2022 13:57:55 - INFO - codeparrot_training - Step 462: {'lr': 0.0001155, 'samples': 237056, 'steps': 462, 'loss/train': 6.4335174560546875}
-03/03/2022 13:57:58 - INFO - codeparrot_training - Step 463: {'lr': 0.00011575000000000001, 'samples': 237568, 'steps': 463, 'loss/train': 7.3489885330200195}
-03/03/2022 13:58:00 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/03/2022 13:58:04 - INFO - codeparrot_training - Step 464: {'lr': 0.00011600000000000001, 'samples': 238080, 'steps': 464, 'loss/train': 6.235637664794922}
-03/03/2022 13:58:07 - INFO - codeparrot_training - Step 465: {'lr': 0.00011625, 'samples': 238592, 'steps': 465, 'loss/train': 7.946732044219971}
-03/03/2022 13:58:08 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/03/2022 13:58:12 - INFO - codeparrot_training - Step 466: {'lr': 0.00011650000000000001, 'samples': 239104, 'steps': 466, 'loss/train': 6.125898361206055}
-03/03/2022 13:58:15 - INFO - codeparrot_training - Step 467: {'lr': 0.00011675, 'samples': 239616, 'steps': 467, 'loss/train': 6.891539573669434}
-03/03/2022 13:58:16 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/03/2022 13:58:20 - INFO - codeparrot_training - Step 468: {'lr': 0.00011700000000000001, 'samples': 240128, 'steps': 468, 'loss/train': 5.3264384269714355}
-03/03/2022 13:58:24 - INFO - codeparrot_training - Step 469: {'lr': 0.00011724999999999999, 'samples': 240640, 'steps': 469, 'loss/train': 7.1578264236450195}
-03/03/2022 13:58:25 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/03/2022 13:58:29 - INFO - codeparrot_training - Step 470: {'lr': 0.0001175, 'samples': 241152, 'steps': 470, 'loss/train': 6.831362724304199}
-03/03/2022 13:58:32 - INFO - codeparrot_training - Step 471: {'lr': 0.00011775, 'samples': 241664, 'steps': 471, 'loss/train': 5.362008571624756}
-03/03/2022 13:58:34 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/03/2022 13:58:37 - INFO - codeparrot_training - Step 472: {'lr': 0.000118, 'samples': 242176, 'steps': 472, 'loss/train': 6.215170383453369}
-03/03/2022 13:58:40 - INFO - codeparrot_training - Step 473: {'lr': 0.00011825, 'samples': 242688, 'steps': 473, 'loss/train': 6.0758161544799805}
-03/03/2022 13:58:42 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/03/2022 13:58:46 - INFO - codeparrot_training - Step 474: {'lr': 0.0001185, 'samples': 243200, 'steps': 474, 'loss/train': 6.737450122833252}
-03/03/2022 13:58:49 - INFO - codeparrot_training - Step 475: {'lr': 0.00011875, 'samples': 243712, 'steps': 475, 'loss/train': 7.72297477722168}
-03/03/2022 13:58:50 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/03/2022 13:58:54 - INFO - codeparrot_training - Step 476: {'lr': 0.00011899999999999999, 'samples': 244224, 'steps': 476, 'loss/train': 6.979861259460449}
-03/03/2022 13:58:57 - INFO - codeparrot_training - Step 477: {'lr': 0.00011925, 'samples': 244736, 'steps': 477, 'loss/train': 6.8633880615234375}
-03/03/2022 13:58:58 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/03/2022 13:59:02 - INFO - codeparrot_training - Step 478: {'lr': 0.00011949999999999999, 'samples': 245248, 'steps': 478, 'loss/train': 6.24032735824585}
-03/03/2022 13:59:06 - INFO - codeparrot_training - Step 479: {'lr': 0.00011975, 'samples': 245760, 'steps': 479, 'loss/train': 7.0863542556762695}
-03/03/2022 13:59:07 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/03/2022 13:59:11 - INFO - codeparrot_training - Step 480: {'lr': 0.00012, 'samples': 246272, 'steps': 480, 'loss/train': 6.356906414031982}
-03/03/2022 13:59:14 - INFO - codeparrot_training - Step 481: {'lr': 0.00012025, 'samples': 246784, 'steps': 481, 'loss/train': 6.802030563354492}
-03/03/2022 13:59:16 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/03/2022 13:59:19 - INFO - codeparrot_training - Step 482: {'lr': 0.0001205, 'samples': 247296, 'steps': 482, 'loss/train': 6.5732340812683105}
-03/03/2022 13:59:22 - INFO - codeparrot_training - Step 483: {'lr': 0.00012075, 'samples': 247808, 'steps': 483, 'loss/train': 6.947469234466553}
-03/03/2022 13:59:24 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/03/2022 13:59:28 - INFO - codeparrot_training - Step 484: {'lr': 0.000121, 'samples': 248320, 'steps': 484, 'loss/train': 6.745939254760742}
-03/03/2022 13:59:31 - INFO - codeparrot_training - Step 485: {'lr': 0.00012124999999999999, 'samples': 248832, 'steps': 485, 'loss/train': 6.2873687744140625}
-03/03/2022 13:59:33 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/03/2022 13:59:36 - INFO - codeparrot_training - Step 486: {'lr': 0.0001215, 'samples': 249344, 'steps': 486, 'loss/train': 6.63435697555542}
-03/03/2022 13:59:40 - INFO - codeparrot_training - Step 487: {'lr': 0.00012175, 'samples': 249856, 'steps': 487, 'loss/train': 6.722681999206543}
-03/03/2022 13:59:42 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/03/2022 13:59:45 - INFO - codeparrot_training - Step 488: {'lr': 0.000122, 'samples': 250368, 'steps': 488, 'loss/train': 6.130354404449463}
-03/03/2022 13:59:48 - INFO - codeparrot_training - Step 489: {'lr': 0.00012225, 'samples': 250880, 'steps': 489, 'loss/train': 6.676987171173096}
-03/03/2022 13:59:50 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/03/2022 13:59:54 - INFO - codeparrot_training - Step 490: {'lr': 0.0001225, 'samples': 251392, 'steps': 490, 'loss/train': 6.809943675994873}
-03/03/2022 13:59:57 - INFO - codeparrot_training - Step 491: {'lr': 0.00012275, 'samples': 251904, 'steps': 491, 'loss/train': 6.272919178009033}
-03/03/2022 14:00:00 - INFO - codeparrot_training - Step 492: {'lr': 0.000123, 'samples': 252416, 'steps': 492, 'loss/train': 6.649359226226807}
-03/03/2022 14:00:00 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/03/2022 14:00:05 - INFO - codeparrot_training - Step 493: {'lr': 0.00012325000000000001, 'samples': 252928, 'steps': 493, 'loss/train': 6.54364538192749}
-03/03/2022 14:00:08 - INFO - codeparrot_training - Step 494: {'lr': 0.0001235, 'samples': 253440, 'steps': 494, 'loss/train': 6.606354713439941}
-03/03/2022 14:00:08 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/03/2022 14:00:14 - INFO - codeparrot_training - Step 495: {'lr': 0.00012375, 'samples': 253952, 'steps': 495, 'loss/train': 6.029935836791992}
-03/03/2022 14:00:17 - INFO - codeparrot_training - Step 496: {'lr': 0.000124, 'samples': 254464, 'steps': 496, 'loss/train': 6.439375877380371}
-03/03/2022 14:00:17 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/03/2022 14:00:22 - INFO - codeparrot_training - Step 497: {'lr': 0.00012425, 'samples': 254976, 'steps': 497, 'loss/train': 6.189598083496094}
-03/03/2022 14:00:25 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/03/2022 14:00:27 - INFO - codeparrot_training - Step 498: {'lr': 0.0001245, 'samples': 255488, 'steps': 498, 'loss/train': 6.953388214111328}
-03/03/2022 14:00:31 - INFO - codeparrot_training - Step 499: {'lr': 0.00012475, 'samples': 256000, 'steps': 499, 'loss/train': 6.3105854988098145}
-03/03/2022 14:00:33 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/03/2022 14:00:36 - INFO - codeparrot_training - Step 500: {'lr': 0.000125, 'samples': 256512, 'steps': 500, 'loss/train': 7.2298760414123535}
-03/03/2022 14:00:39 - INFO - codeparrot_training - Step 501: {'lr': 0.00012525, 'samples': 257024, 'steps': 501, 'loss/train': 5.246858596801758}
-03/03/2022 14:00:41 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/03/2022 14:00:44 - INFO - codeparrot_training - Step 502: {'lr': 0.00012550000000000001, 'samples': 257536, 'steps': 502, 'loss/train': 6.187530517578125}
-03/03/2022 14:00:47 - INFO - codeparrot_training - Step 503: {'lr': 0.00012575, 'samples': 258048, 'steps': 503, 'loss/train': 3.552276611328125}
-03/03/2022 14:00:49 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/03/2022 14:00:52 - INFO - codeparrot_training - Step 504: {'lr': 0.000126, 'samples': 258560, 'steps': 504, 'loss/train': 7.031077861785889}
-03/03/2022 14:00:56 - INFO - codeparrot_training - Step 505: {'lr': 0.00012625, 'samples': 259072, 'steps': 505, 'loss/train': 6.204738616943359}
-03/03/2022 14:00:58 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/03/2022 14:01:01 - INFO - codeparrot_training - Step 506: {'lr': 0.0001265, 'samples': 259584, 'steps': 506, 'loss/train': 7.075988292694092}
-03/03/2022 14:01:04 - INFO - codeparrot_training - Step 507: {'lr': 0.00012675, 'samples': 260096, 'steps': 507, 'loss/train': 6.6335272789001465}
-03/03/2022 14:01:06 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/03/2022 14:01:09 - INFO - codeparrot_training - Step 508: {'lr': 0.000127, 'samples': 260608, 'steps': 508, 'loss/train': 6.588409423828125}
-03/03/2022 14:01:12 - INFO - codeparrot_training - Step 509: {'lr': 0.00012725, 'samples': 261120, 'steps': 509, 'loss/train': 7.296545028686523}
-03/03/2022 14:01:14 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/03/2022 14:01:18 - INFO - codeparrot_training - Step 510: {'lr': 0.0001275, 'samples': 261632, 'steps': 510, 'loss/train': 7.028717517852783}
-03/03/2022 14:01:21 - INFO - codeparrot_training - Step 511: {'lr': 0.00012775000000000002, 'samples': 262144, 'steps': 511, 'loss/train': 5.841274738311768}
-03/03/2022 14:01:22 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/03/2022 14:01:26 - INFO - codeparrot_training - Step 512: {'lr': 0.000128, 'samples': 262656, 'steps': 512, 'loss/train': 6.456965923309326}
-03/03/2022 14:01:29 - INFO - codeparrot_training - Step 513: {'lr': 0.00012825, 'samples': 263168, 'steps': 513, 'loss/train': 6.273007392883301}
-03/03/2022 14:01:35 - INFO - codeparrot_training - Step 514: {'lr': 0.0001285, 'samples': 263680, 'steps': 514, 'loss/train': 4.0798211097717285}
-03/03/2022 14:01:38 - INFO - codeparrot_training - Step 515: {'lr': 0.00012875, 'samples': 264192, 'steps': 515, 'loss/train': 6.905279159545898}
-03/03/2022 14:01:40 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/03/2022 14:01:43 - INFO - codeparrot_training - Step 516: {'lr': 0.00012900000000000002, 'samples': 264704, 'steps': 516, 'loss/train': 6.346916675567627}
-03/03/2022 14:01:46 - INFO - codeparrot_training - Step 517: {'lr': 0.00012925, 'samples': 265216, 'steps': 517, 'loss/train': 5.993963718414307}
-03/03/2022 14:01:48 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/03/2022 14:01:51 - INFO - codeparrot_training - Step 518: {'lr': 0.0001295, 'samples': 265728, 'steps': 518, 'loss/train': 8.08281135559082}
-03/03/2022 14:01:55 - INFO - codeparrot_training - Step 519: {'lr': 0.00012975, 'samples': 266240, 'steps': 519, 'loss/train': 5.490631580352783}
-03/03/2022 14:01:56 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/03/2022 14:02:00 - INFO - codeparrot_training - Step 520: {'lr': 0.00013000000000000002, 'samples': 266752, 'steps': 520, 'loss/train': 6.573332786560059}
-03/03/2022 14:02:03 - INFO - codeparrot_training - Step 521: {'lr': 0.00013025, 'samples': 267264, 'steps': 521, 'loss/train': 6.53049898147583}
-03/03/2022 14:02:04 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/03/2022 14:02:08 - INFO - codeparrot_training - Step 522: {'lr': 0.0001305, 'samples': 267776, 'steps': 522, 'loss/train': 6.454466819763184}
-03/03/2022 14:02:11 - INFO - codeparrot_training - Step 523: {'lr': 0.00013075, 'samples': 268288, 'steps': 523, 'loss/train': 6.2750749588012695}
-03/03/2022 14:02:12 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/03/2022 14:02:17 - INFO - codeparrot_training - Step 524: {'lr': 0.000131, 'samples': 268800, 'steps': 524, 'loss/train': 6.3301262855529785}
-03/03/2022 14:02:20 - INFO - codeparrot_training - Step 525: {'lr': 0.00013125000000000002, 'samples': 269312, 'steps': 525, 'loss/train': 6.276494979858398}
-03/03/2022 14:02:21 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/03/2022 14:02:25 - INFO - codeparrot_training - Step 526: {'lr': 0.0001315, 'samples': 269824, 'steps': 526, 'loss/train': 6.3546600341796875}
-03/03/2022 14:02:28 - INFO - codeparrot_training - Step 527: {'lr': 0.00013175, 'samples': 270336, 'steps': 527, 'loss/train': 6.923059463500977}
-03/03/2022 14:02:29 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/03/2022 14:02:33 - INFO - codeparrot_training - Step 528: {'lr': 0.000132, 'samples': 270848, 'steps': 528, 'loss/train': 7.054484844207764}
-03/03/2022 14:02:37 - INFO - codeparrot_training - Step 529: {'lr': 0.00013225000000000002, 'samples': 271360, 'steps': 529, 'loss/train': 6.102305889129639}
-03/03/2022 14:02:37 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/03/2022 14:02:42 - INFO - codeparrot_training - Step 530: {'lr': 0.00013250000000000002, 'samples': 271872, 'steps': 530, 'loss/train': 6.931844711303711}
-03/03/2022 14:02:45 - INFO - codeparrot_training - Step 531: {'lr': 0.00013275, 'samples': 272384, 'steps': 531, 'loss/train': 6.86146879196167}
-03/03/2022 14:02:46 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/03/2022 14:02:50 - INFO - codeparrot_training - Step 532: {'lr': 0.000133, 'samples': 272896, 'steps': 532, 'loss/train': 6.249301910400391}
-03/03/2022 14:02:53 - INFO - codeparrot_training - Step 533: {'lr': 0.00013325, 'samples': 273408, 'steps': 533, 'loss/train': 5.98560094833374}
-03/03/2022 14:02:54 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/03/2022 14:02:59 - INFO - codeparrot_training - Step 534: {'lr': 0.00013350000000000002, 'samples': 273920, 'steps': 534, 'loss/train': 5.897489547729492}
-03/03/2022 14:03:02 - INFO - codeparrot_training - Step 535: {'lr': 0.00013375, 'samples': 274432, 'steps': 535, 'loss/train': 5.953618049621582}
-03/03/2022 14:03:02 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/03/2022 14:03:07 - INFO - codeparrot_training - Step 536: {'lr': 0.000134, 'samples': 274944, 'steps': 536, 'loss/train': 5.412363052368164}
-03/03/2022 14:03:11 - INFO - codeparrot_training - Step 537: {'lr': 0.00013425, 'samples': 275456, 'steps': 537, 'loss/train': 6.587615013122559}
-03/03/2022 14:03:11 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/03/2022 14:03:16 - INFO - codeparrot_training - Step 538: {'lr': 0.00013450000000000002, 'samples': 275968, 'steps': 538, 'loss/train': 7.666083812713623}
-03/03/2022 14:03:19 - INFO - codeparrot_training - Step 539: {'lr': 0.00013475000000000002, 'samples': 276480, 'steps': 539, 'loss/train': 6.328266620635986}
-03/03/2022 14:03:19 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/03/2022 14:03:24 - INFO - codeparrot_training - Step 540: {'lr': 0.000135, 'samples': 276992, 'steps': 540, 'loss/train': 6.373903274536133}
-03/03/2022 14:03:27 - INFO - codeparrot_training - Step 541: {'lr': 0.00013525, 'samples': 277504, 'steps': 541, 'loss/train': 7.26821756362915}
-03/03/2022 14:03:28 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/03/2022 14:03:33 - INFO - codeparrot_training - Step 542: {'lr': 0.00013550000000000001, 'samples': 278016, 'steps': 542, 'loss/train': 6.584914207458496}
-03/03/2022 14:03:36 - INFO - codeparrot_training - Step 543: {'lr': 0.00013575000000000002, 'samples': 278528, 'steps': 543, 'loss/train': 5.7850165367126465}
-03/03/2022 14:03:36 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/03/2022 14:03:41 - INFO - codeparrot_training - Step 544: {'lr': 0.00013600000000000003, 'samples': 279040, 'steps': 544, 'loss/train': 6.242919921875}
-03/03/2022 14:03:44 - INFO - codeparrot_training - Step 545: {'lr': 0.00013625, 'samples': 279552, 'steps': 545, 'loss/train': 5.564044952392578}
-03/03/2022 14:03:44 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/03/2022 14:03:49 - INFO - codeparrot_training - Step 546: {'lr': 0.0001365, 'samples': 280064, 'steps': 546, 'loss/train': 6.581683158874512}
-03/03/2022 14:03:52 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/03/2022 14:03:55 - INFO - codeparrot_training - Step 547: {'lr': 0.00013675000000000002, 'samples': 280576, 'steps': 547, 'loss/train': 5.945650100708008}
-03/03/2022 14:03:58 - INFO - codeparrot_training - Step 548: {'lr': 0.00013700000000000002, 'samples': 281088, 'steps': 548, 'loss/train': 6.196447372436523}
-03/03/2022 14:04:01 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/03/2022 14:04:03 - INFO - codeparrot_training - Step 549: {'lr': 0.00013725, 'samples': 281600, 'steps': 549, 'loss/train': 6.543551921844482}
-03/03/2022 14:04:06 - INFO - codeparrot_training - Step 550: {'lr': 0.0001375, 'samples': 282112, 'steps': 550, 'loss/train': 6.2957539558410645}
-03/03/2022 14:04:09 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/03/2022 14:04:11 - INFO - codeparrot_training - Step 551: {'lr': 0.00013775000000000001, 'samples': 282624, 'steps': 551, 'loss/train': 6.463682651519775}
-03/03/2022 14:04:15 - INFO - codeparrot_training - Step 552: {'lr': 0.00013800000000000002, 'samples': 283136, 'steps': 552, 'loss/train': 6.8313374519348145}
-03/03/2022 14:04:17 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/03/2022 14:04:20 - INFO - codeparrot_training - Step 553: {'lr': 0.00013825000000000003, 'samples': 283648, 'steps': 553, 'loss/train': 7.100462913513184}
-03/03/2022 14:04:23 - INFO - codeparrot_training - Step 554: {'lr': 0.0001385, 'samples': 284160, 'steps': 554, 'loss/train': 6.060208797454834}
-03/03/2022 14:04:26 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/03/2022 14:04:28 - INFO - codeparrot_training - Step 555: {'lr': 0.00013875, 'samples': 284672, 'steps': 555, 'loss/train': 6.4385175704956055}
-03/03/2022 14:04:32 - INFO - codeparrot_training - Step 556: {'lr': 0.00013900000000000002, 'samples': 285184, 'steps': 556, 'loss/train': 6.447488307952881}
-03/03/2022 14:04:34 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/03/2022 14:04:37 - INFO - codeparrot_training - Step 557: {'lr': 0.00013925000000000002, 'samples': 285696, 'steps': 557, 'loss/train': 6.174968719482422}
-03/03/2022 14:04:40 - INFO - codeparrot_training - Step 558: {'lr': 0.0001395, 'samples': 286208, 'steps': 558, 'loss/train': 6.187171459197998}
-03/03/2022 14:04:43 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/03/2022 14:04:46 - INFO - codeparrot_training - Step 559: {'lr': 0.00013975, 'samples': 286720, 'steps': 559, 'loss/train': 5.922861099243164}
-03/03/2022 14:04:49 - INFO - codeparrot_training - Step 560: {'lr': 0.00014000000000000001, 'samples': 287232, 'steps': 560, 'loss/train': 6.676205158233643}
-03/03/2022 14:04:52 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/03/2022 14:04:54 - INFO - codeparrot_training - Step 561: {'lr': 0.00014025000000000002, 'samples': 287744, 'steps': 561, 'loss/train': 6.076144218444824}
-03/03/2022 14:04:57 - INFO - codeparrot_training - Step 562: {'lr': 0.00014050000000000003, 'samples': 288256, 'steps': 562, 'loss/train': 6.192407131195068}
-03/03/2022 14:05:00 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/03/2022 14:05:03 - INFO - codeparrot_training - Step 563: {'lr': 0.00014074999999999998, 'samples': 288768, 'steps': 563, 'loss/train': 5.674139976501465}
-03/03/2022 14:05:06 - INFO - codeparrot_training - Step 564: {'lr': 0.00014099999999999998, 'samples': 289280, 'steps': 564, 'loss/train': 6.117628574371338}
-03/03/2022 14:05:08 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/03/2022 14:05:11 - INFO - codeparrot_training - Step 565: {'lr': 0.00014125, 'samples': 289792, 'steps': 565, 'loss/train': 6.994811058044434}
-03/03/2022 14:05:14 - INFO - codeparrot_training - Step 566: {'lr': 0.0001415, 'samples': 290304, 'steps': 566, 'loss/train': 6.521088123321533}
-03/03/2022 14:05:17 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 14:05:19 - INFO - codeparrot_training - Step 567: {'lr': 0.00014175, 'samples': 290816, 'steps': 567, 'loss/train': 6.583520412445068}
-03/03/2022 14:05:23 - INFO - codeparrot_training - Step 568: {'lr': 0.00014199999999999998, 'samples': 291328, 'steps': 568, 'loss/train': 5.825527191162109}
-03/03/2022 14:05:25 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/03/2022 14:05:28 - INFO - codeparrot_training - Step 569: {'lr': 0.00014225, 'samples': 291840, 'steps': 569, 'loss/train': 6.117654323577881}
-03/03/2022 14:05:31 - INFO - codeparrot_training - Step 570: {'lr': 0.0001425, 'samples': 292352, 'steps': 570, 'loss/train': 6.853424072265625}
-03/03/2022 14:05:33 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/03/2022 14:05:36 - INFO - codeparrot_training - Step 571: {'lr': 0.00014275, 'samples': 292864, 'steps': 571, 'loss/train': 6.277547359466553}
-03/03/2022 14:05:39 - INFO - codeparrot_training - Step 572: {'lr': 0.00014299999999999998, 'samples': 293376, 'steps': 572, 'loss/train': 8.810072898864746}
-03/03/2022 14:05:41 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/03/2022 14:05:45 - INFO - codeparrot_training - Step 573: {'lr': 0.00014324999999999999, 'samples': 293888, 'steps': 573, 'loss/train': 5.866996765136719}
-03/03/2022 14:05:48 - INFO - codeparrot_training - Step 574: {'lr': 0.0001435, 'samples': 294400, 'steps': 574, 'loss/train': 6.329942226409912}
-03/03/2022 14:05:49 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/03/2022 14:05:53 - INFO - codeparrot_training - Step 575: {'lr': 0.00014375, 'samples': 294912, 'steps': 575, 'loss/train': 6.773353099822998}
-03/03/2022 14:05:56 - INFO - codeparrot_training - Step 576: {'lr': 0.000144, 'samples': 295424, 'steps': 576, 'loss/train': 7.22576904296875}
-03/03/2022 14:05:57 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/03/2022 14:06:01 - INFO - codeparrot_training - Step 577: {'lr': 0.00014424999999999998, 'samples': 295936, 'steps': 577, 'loss/train': 5.495701789855957}
-03/03/2022 14:06:05 - INFO - codeparrot_training - Step 578: {'lr': 0.0001445, 'samples': 296448, 'steps': 578, 'loss/train': 6.104785442352295}
-03/03/2022 14:06:05 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/03/2022 14:06:10 - INFO - codeparrot_training - Step 579: {'lr': 0.00014475, 'samples': 296960, 'steps': 579, 'loss/train': 6.159816741943359}
-03/03/2022 14:06:13 - INFO - codeparrot_training - Step 580: {'lr': 0.000145, 'samples': 297472, 'steps': 580, 'loss/train': 7.078535556793213}
-03/03/2022 14:06:14 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/03/2022 14:06:18 - INFO - codeparrot_training - Step 581: {'lr': 0.00014524999999999998, 'samples': 297984, 'steps': 581, 'loss/train': 5.665816307067871}
-03/03/2022 14:06:21 - INFO - codeparrot_training - Step 582: {'lr': 0.00014549999999999999, 'samples': 298496, 'steps': 582, 'loss/train': 6.4277167320251465}
-03/03/2022 14:06:23 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/03/2022 14:06:27 - INFO - codeparrot_training - Step 583: {'lr': 0.00014575, 'samples': 299008, 'steps': 583, 'loss/train': 6.36889123916626}
-03/03/2022 14:06:30 - INFO - codeparrot_training - Step 584: {'lr': 0.000146, 'samples': 299520, 'steps': 584, 'loss/train': 6.408004283905029}
-03/03/2022 14:06:31 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/03/2022 14:06:35 - INFO - codeparrot_training - Step 585: {'lr': 0.00014625, 'samples': 300032, 'steps': 585, 'loss/train': 6.266024112701416}
-03/03/2022 14:06:38 - INFO - codeparrot_training - Step 586: {'lr': 0.00014649999999999998, 'samples': 300544, 'steps': 586, 'loss/train': 6.211362838745117}
-03/03/2022 14:06:39 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/03/2022 14:06:43 - INFO - codeparrot_training - Step 587: {'lr': 0.00014675, 'samples': 301056, 'steps': 587, 'loss/train': 5.916329860687256}
-03/03/2022 14:06:47 - INFO - codeparrot_training - Step 588: {'lr': 0.000147, 'samples': 301568, 'steps': 588, 'loss/train': 6.630198955535889}
-03/03/2022 14:06:48 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/03/2022 14:06:52 - INFO - codeparrot_training - Step 589: {'lr': 0.00014725, 'samples': 302080, 'steps': 589, 'loss/train': 6.489871025085449}
-03/03/2022 14:06:55 - INFO - codeparrot_training - Step 590: {'lr': 0.0001475, 'samples': 302592, 'steps': 590, 'loss/train': 6.236913681030273}
-03/03/2022 14:06:56 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/03/2022 14:07:00 - INFO - codeparrot_training - Step 591: {'lr': 0.00014774999999999999, 'samples': 303104, 'steps': 591, 'loss/train': 7.031076431274414}
-03/03/2022 14:07:03 - INFO - codeparrot_training - Step 592: {'lr': 0.000148, 'samples': 303616, 'steps': 592, 'loss/train': 6.221190452575684}
-03/03/2022 14:07:04 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/03/2022 14:07:09 - INFO - codeparrot_training - Step 593: {'lr': 0.00014825, 'samples': 304128, 'steps': 593, 'loss/train': 2.855438232421875}
-03/03/2022 14:07:12 - INFO - codeparrot_training - Step 594: {'lr': 0.0001485, 'samples': 304640, 'steps': 594, 'loss/train': 5.569334983825684}
-03/03/2022 14:07:13 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/03/2022 14:07:17 - INFO - codeparrot_training - Step 595: {'lr': 0.00014874999999999998, 'samples': 305152, 'steps': 595, 'loss/train': 5.709835052490234}
-03/03/2022 14:07:20 - INFO - codeparrot_training - Step 596: {'lr': 0.000149, 'samples': 305664, 'steps': 596, 'loss/train': 5.010371685028076}
-03/03/2022 14:07:21 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/03/2022 14:07:26 - INFO - codeparrot_training - Step 597: {'lr': 0.00014925, 'samples': 306176, 'steps': 597, 'loss/train': 6.1854729652404785}
-03/03/2022 14:07:29 - INFO - codeparrot_training - Step 598: {'lr': 0.0001495, 'samples': 306688, 'steps': 598, 'loss/train': 5.076950550079346}
-03/03/2022 14:07:29 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/03/2022 14:07:34 - INFO - codeparrot_training - Step 599: {'lr': 0.00014975, 'samples': 307200, 'steps': 599, 'loss/train': 6.055659294128418}
-03/03/2022 14:07:37 - INFO - codeparrot_training - Step 600: {'lr': 0.00015, 'samples': 307712, 'steps': 600, 'loss/train': 6.123353481292725}
-03/03/2022 14:07:38 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/03/2022 14:07:42 - INFO - codeparrot_training - Step 601: {'lr': 0.00015025, 'samples': 308224, 'steps': 601, 'loss/train': 5.649929523468018}
-03/03/2022 14:07:46 - INFO - codeparrot_training - Step 602: {'lr': 0.0001505, 'samples': 308736, 'steps': 602, 'loss/train': 6.700413227081299}
-03/03/2022 14:07:46 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/03/2022 14:07:51 - INFO - codeparrot_training - Step 603: {'lr': 0.00015075, 'samples': 309248, 'steps': 603, 'loss/train': 6.63961124420166}
-03/03/2022 14:07:54 - INFO - codeparrot_training - Step 604: {'lr': 0.000151, 'samples': 309760, 'steps': 604, 'loss/train': 6.31554651260376}
-03/03/2022 14:07:55 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/03/2022 14:07:59 - INFO - codeparrot_training - Step 605: {'lr': 0.00015125, 'samples': 310272, 'steps': 605, 'loss/train': 3.064589738845825}
-03/03/2022 14:08:03 - INFO - codeparrot_training - Step 606: {'lr': 0.0001515, 'samples': 310784, 'steps': 606, 'loss/train': 6.4073166847229}
-03/03/2022 14:08:03 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/03/2022 14:08:08 - INFO - codeparrot_training - Step 607: {'lr': 0.00015175, 'samples': 311296, 'steps': 607, 'loss/train': 6.360343933105469}
-03/03/2022 14:08:11 - INFO - codeparrot_training - Step 608: {'lr': 0.000152, 'samples': 311808, 'steps': 608, 'loss/train': 6.431277275085449}
-03/03/2022 14:08:11 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/03/2022 14:08:16 - INFO - codeparrot_training - Step 609: {'lr': 0.00015225, 'samples': 312320, 'steps': 609, 'loss/train': 7.12800931930542}
-03/03/2022 14:08:19 - INFO - codeparrot_training - Step 610: {'lr': 0.0001525, 'samples': 312832, 'steps': 610, 'loss/train': 7.39421272277832}
-03/03/2022 14:08:20 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/03/2022 14:08:25 - INFO - codeparrot_training - Step 611: {'lr': 0.00015275, 'samples': 313344, 'steps': 611, 'loss/train': 6.497633934020996}
-03/03/2022 14:08:28 - INFO - codeparrot_training - Step 612: {'lr': 0.000153, 'samples': 313856, 'steps': 612, 'loss/train': 3.2339026927948}
-03/03/2022 14:08:28 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/03/2022 14:08:33 - INFO - codeparrot_training - Step 613: {'lr': 0.00015325, 'samples': 314368, 'steps': 613, 'loss/train': 5.780489444732666}
-03/03/2022 14:08:36 - INFO - codeparrot_training - Step 614: {'lr': 0.0001535, 'samples': 314880, 'steps': 614, 'loss/train': 6.6113176345825195}
-03/03/2022 14:08:36 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/03/2022 14:08:42 - INFO - codeparrot_training - Step 615: {'lr': 0.00015375, 'samples': 315392, 'steps': 615, 'loss/train': 5.941757678985596}
-03/03/2022 14:08:45 - INFO - codeparrot_training - Step 616: {'lr': 0.000154, 'samples': 315904, 'steps': 616, 'loss/train': 5.896623611450195}
-03/03/2022 14:08:47 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/03/2022 14:08:51 - INFO - codeparrot_training - Step 617: {'lr': 0.00015425, 'samples': 316416, 'steps': 617, 'loss/train': 6.162133693695068}
-03/03/2022 14:08:54 - INFO - codeparrot_training - Step 618: {'lr': 0.00015450000000000001, 'samples': 316928, 'steps': 618, 'loss/train': 6.68670129776001}
-03/03/2022 14:08:55 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/03/2022 14:08:59 - INFO - codeparrot_training - Step 619: {'lr': 0.00015475, 'samples': 317440, 'steps': 619, 'loss/train': 5.5909423828125}
-03/03/2022 14:09:02 - INFO - codeparrot_training - Step 620: {'lr': 0.000155, 'samples': 317952, 'steps': 620, 'loss/train': 5.869774341583252}
-03/03/2022 14:09:03 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/03/2022 14:09:07 - INFO - codeparrot_training - Step 621: {'lr': 0.00015525, 'samples': 318464, 'steps': 621, 'loss/train': 5.421020984649658}
-03/03/2022 14:09:11 - INFO - codeparrot_training - Step 622: {'lr': 0.0001555, 'samples': 318976, 'steps': 622, 'loss/train': 6.940159797668457}
-03/03/2022 14:09:11 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/03/2022 14:09:16 - INFO - codeparrot_training - Step 623: {'lr': 0.00015575, 'samples': 319488, 'steps': 623, 'loss/train': 6.464077949523926}
-03/03/2022 14:09:19 - INFO - codeparrot_training - Step 624: {'lr': 0.000156, 'samples': 320000, 'steps': 624, 'loss/train': 6.078533172607422}
-03/03/2022 14:09:20 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/03/2022 14:09:24 - INFO - codeparrot_training - Step 625: {'lr': 0.00015625, 'samples': 320512, 'steps': 625, 'loss/train': 6.872628211975098}
-03/03/2022 14:09:27 - INFO - codeparrot_training - Step 626: {'lr': 0.0001565, 'samples': 321024, 'steps': 626, 'loss/train': 5.479709148406982}
-03/03/2022 14:09:28 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/03/2022 14:09:33 - INFO - codeparrot_training - Step 627: {'lr': 0.00015675000000000002, 'samples': 321536, 'steps': 627, 'loss/train': 5.674254417419434}
-03/03/2022 14:09:36 - INFO - codeparrot_training - Step 628: {'lr': 0.000157, 'samples': 322048, 'steps': 628, 'loss/train': 6.159651756286621}
-03/03/2022 14:09:36 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/03/2022 14:09:41 - INFO - codeparrot_training - Step 629: {'lr': 0.00015725, 'samples': 322560, 'steps': 629, 'loss/train': 7.308654308319092}
-03/03/2022 14:09:44 - INFO - codeparrot_training - Step 630: {'lr': 0.0001575, 'samples': 323072, 'steps': 630, 'loss/train': 6.169018745422363}
-03/03/2022 14:09:44 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/03/2022 14:09:49 - INFO - codeparrot_training - Step 631: {'lr': 0.00015775, 'samples': 323584, 'steps': 631, 'loss/train': 5.524197578430176}
-03/03/2022 14:09:53 - INFO - codeparrot_training - Step 632: {'lr': 0.000158, 'samples': 324096, 'steps': 632, 'loss/train': 5.829387187957764}
-03/03/2022 14:09:53 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/03/2022 14:09:58 - INFO - codeparrot_training - Step 633: {'lr': 0.00015825, 'samples': 324608, 'steps': 633, 'loss/train': 6.475989818572998}
-03/03/2022 14:10:01 - INFO - codeparrot_training - Step 634: {'lr': 0.0001585, 'samples': 325120, 'steps': 634, 'loss/train': 6.106311798095703}
-03/03/2022 14:10:01 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/03/2022 14:10:06 - INFO - codeparrot_training - Step 635: {'lr': 0.00015875, 'samples': 325632, 'steps': 635, 'loss/train': 7.287618160247803}
-03/03/2022 14:10:09 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/03/2022 14:10:12 - INFO - codeparrot_training - Step 636: {'lr': 0.00015900000000000002, 'samples': 326144, 'steps': 636, 'loss/train': 6.331869125366211}
-03/03/2022 14:10:15 - INFO - codeparrot_training - Step 637: {'lr': 0.00015925, 'samples': 326656, 'steps': 637, 'loss/train': 5.934976577758789}
-03/03/2022 14:10:18 - INFO - codeparrot_training - Step 638: {'lr': 0.0001595, 'samples': 327168, 'steps': 638, 'loss/train': 6.335379600524902}
-03/03/2022 14:10:18 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/03/2022 14:10:23 - INFO - codeparrot_training - Step 639: {'lr': 0.00015975, 'samples': 327680, 'steps': 639, 'loss/train': 6.426903247833252}
-03/03/2022 14:10:26 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/03/2022 14:10:28 - INFO - codeparrot_training - Step 640: {'lr': 0.00016, 'samples': 328192, 'steps': 640, 'loss/train': 5.964064598083496}
-03/03/2022 14:10:32 - INFO - codeparrot_training - Step 641: {'lr': 0.00016025000000000002, 'samples': 328704, 'steps': 641, 'loss/train': 6.006753444671631}
-03/03/2022 14:10:35 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/03/2022 14:10:37 - INFO - codeparrot_training - Step 642: {'lr': 0.0001605, 'samples': 329216, 'steps': 642, 'loss/train': 6.466495513916016}
-03/03/2022 14:10:40 - INFO - codeparrot_training - Step 643: {'lr': 0.00016075, 'samples': 329728, 'steps': 643, 'loss/train': 5.993957996368408}
-03/03/2022 14:10:43 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/03/2022 14:10:45 - INFO - codeparrot_training - Step 644: {'lr': 0.000161, 'samples': 330240, 'steps': 644, 'loss/train': 5.594142913818359}
-03/03/2022 14:10:48 - INFO - codeparrot_training - Step 645: {'lr': 0.00016125000000000002, 'samples': 330752, 'steps': 645, 'loss/train': 6.494534492492676}
-03/03/2022 14:10:51 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/03/2022 14:10:54 - INFO - codeparrot_training - Step 646: {'lr': 0.0001615, 'samples': 331264, 'steps': 646, 'loss/train': 6.0859150886535645}
-03/03/2022 14:10:57 - INFO - codeparrot_training - Step 647: {'lr': 0.00016175, 'samples': 331776, 'steps': 647, 'loss/train': 5.9677557945251465}
-03/03/2022 14:10:59 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/03/2022 14:11:02 - INFO - codeparrot_training - Step 648: {'lr': 0.000162, 'samples': 332288, 'steps': 648, 'loss/train': 6.707947254180908}
-03/03/2022 14:11:05 - INFO - codeparrot_training - Step 649: {'lr': 0.00016225000000000001, 'samples': 332800, 'steps': 649, 'loss/train': 6.108962535858154}
-03/03/2022 14:11:07 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/03/2022 14:11:10 - INFO - codeparrot_training - Step 650: {'lr': 0.00016250000000000002, 'samples': 333312, 'steps': 650, 'loss/train': 6.814627170562744}
-03/03/2022 14:11:14 - INFO - codeparrot_training - Step 651: {'lr': 0.00016275, 'samples': 333824, 'steps': 651, 'loss/train': 5.893065452575684}
-03/03/2022 14:11:15 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/03/2022 14:11:19 - INFO - codeparrot_training - Step 652: {'lr': 0.000163, 'samples': 334336, 'steps': 652, 'loss/train': 6.324979305267334}
-03/03/2022 14:11:22 - INFO - codeparrot_training - Step 653: {'lr': 0.00016325, 'samples': 334848, 'steps': 653, 'loss/train': 6.214859485626221}
-03/03/2022 14:11:24 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/03/2022 14:11:28 - INFO - codeparrot_training - Step 654: {'lr': 0.00016350000000000002, 'samples': 335360, 'steps': 654, 'loss/train': 3.775311231613159}
-03/03/2022 14:11:31 - INFO - codeparrot_training - Step 655: {'lr': 0.00016375000000000002, 'samples': 335872, 'steps': 655, 'loss/train': 6.337494850158691}
-03/03/2022 14:11:34 - INFO - codeparrot_training - Step 656: {'lr': 0.000164, 'samples': 336384, 'steps': 656, 'loss/train': 5.7109694480896}
-03/03/2022 14:11:34 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/03/2022 14:11:40 - INFO - codeparrot_training - Step 657: {'lr': 0.00016425, 'samples': 336896, 'steps': 657, 'loss/train': 6.214146137237549}
-03/03/2022 14:11:43 - INFO - codeparrot_training - Step 658: {'lr': 0.00016450000000000001, 'samples': 337408, 'steps': 658, 'loss/train': 5.56549072265625}
-03/03/2022 14:11:43 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/03/2022 14:11:48 - INFO - codeparrot_training - Step 659: {'lr': 0.00016475000000000002, 'samples': 337920, 'steps': 659, 'loss/train': 6.0047454833984375}
-03/03/2022 14:11:51 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/03/2022 14:11:53 - INFO - codeparrot_training - Step 660: {'lr': 0.000165, 'samples': 338432, 'steps': 660, 'loss/train': 6.162009239196777}
-03/03/2022 14:11:56 - INFO - codeparrot_training - Step 661: {'lr': 0.00016525, 'samples': 338944, 'steps': 661, 'loss/train': 6.934346675872803}
-03/03/2022 14:11:59 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/03/2022 14:12:01 - INFO - codeparrot_training - Step 662: {'lr': 0.0001655, 'samples': 339456, 'steps': 662, 'loss/train': 5.5325775146484375}
-03/03/2022 14:12:05 - INFO - codeparrot_training - Step 663: {'lr': 0.00016575000000000002, 'samples': 339968, 'steps': 663, 'loss/train': 5.783498287200928}
-03/03/2022 14:12:07 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/03/2022 14:12:10 - INFO - codeparrot_training - Step 664: {'lr': 0.00016600000000000002, 'samples': 340480, 'steps': 664, 'loss/train': 5.984687805175781}
-03/03/2022 14:12:13 - INFO - codeparrot_training - Step 665: {'lr': 0.00016625, 'samples': 340992, 'steps': 665, 'loss/train': 6.424323558807373}
-03/03/2022 14:12:16 - INFO - codeparrot_training - Step 666: {'lr': 0.0001665, 'samples': 341504, 'steps': 666, 'loss/train': 5.984019756317139}
-03/03/2022 14:12:16 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/03/2022 14:12:22 - INFO - codeparrot_training - Step 667: {'lr': 0.00016675000000000001, 'samples': 342016, 'steps': 667, 'loss/train': 5.237941265106201}
-03/03/2022 14:12:24 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/03/2022 14:12:27 - INFO - codeparrot_training - Step 668: {'lr': 0.00016700000000000002, 'samples': 342528, 'steps': 668, 'loss/train': 5.912707805633545}
-03/03/2022 14:12:30 - INFO - codeparrot_training - Step 669: {'lr': 0.00016725000000000003, 'samples': 343040, 'steps': 669, 'loss/train': 4.301641464233398}
-03/03/2022 14:12:33 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/03/2022 14:12:35 - INFO - codeparrot_training - Step 670: {'lr': 0.0001675, 'samples': 343552, 'steps': 670, 'loss/train': 6.000380039215088}
-03/03/2022 14:12:39 - INFO - codeparrot_training - Step 671: {'lr': 0.00016775, 'samples': 344064, 'steps': 671, 'loss/train': 3.8122336864471436}
-03/03/2022 14:12:41 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/03/2022 14:12:44 - INFO - codeparrot_training - Step 672: {'lr': 0.00016800000000000002, 'samples': 344576, 'steps': 672, 'loss/train': 6.087907791137695}
-03/03/2022 14:12:47 - INFO - codeparrot_training - Step 673: {'lr': 0.00016825000000000002, 'samples': 345088, 'steps': 673, 'loss/train': 5.071622371673584}
-03/03/2022 14:12:50 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/03/2022 14:12:52 - INFO - codeparrot_training - Step 674: {'lr': 0.0001685, 'samples': 345600, 'steps': 674, 'loss/train': 2.5481441020965576}
-03/03/2022 14:12:55 - INFO - codeparrot_training - Step 675: {'lr': 0.00016875, 'samples': 346112, 'steps': 675, 'loss/train': 4.16834020614624}
-03/03/2022 14:12:58 - INFO - codeparrot_training - Skipping example with length 462 (seq_length=1024)
-03/03/2022 14:13:01 - INFO - codeparrot_training - Step 676: {'lr': 0.00016900000000000002, 'samples': 346624, 'steps': 676, 'loss/train': 6.831921577453613}
-03/03/2022 14:13:04 - INFO - codeparrot_training - Step 677: {'lr': 0.00016925000000000002, 'samples': 347136, 'steps': 677, 'loss/train': 5.582108020782471}
-03/03/2022 14:13:06 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/03/2022 14:13:09 - INFO - codeparrot_training - Step 678: {'lr': 0.00016950000000000003, 'samples': 347648, 'steps': 678, 'loss/train': 6.289055824279785}
-03/03/2022 14:13:12 - INFO - codeparrot_training - Step 679: {'lr': 0.00016975, 'samples': 348160, 'steps': 679, 'loss/train': 3.1966123580932617}
-03/03/2022 14:13:15 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/03/2022 14:13:18 - INFO - codeparrot_training - Step 680: {'lr': 0.00017, 'samples': 348672, 'steps': 680, 'loss/train': 6.146064281463623}
-03/03/2022 14:13:21 - INFO - codeparrot_training - Step 681: {'lr': 0.00017025000000000002, 'samples': 349184, 'steps': 681, 'loss/train': 6.17354679107666}
-03/03/2022 14:13:23 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/03/2022 14:13:26 - INFO - codeparrot_training - Step 682: {'lr': 0.00017050000000000002, 'samples': 349696, 'steps': 682, 'loss/train': 5.563101291656494}
-03/03/2022 14:13:29 - INFO - codeparrot_training - Step 683: {'lr': 0.00017075, 'samples': 350208, 'steps': 683, 'loss/train': 5.49904727935791}
-03/03/2022 14:13:31 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/03/2022 14:13:34 - INFO - codeparrot_training - Step 684: {'lr': 0.000171, 'samples': 350720, 'steps': 684, 'loss/train': 3.3620424270629883}
-03/03/2022 14:13:38 - INFO - codeparrot_training - Step 685: {'lr': 0.00017125000000000002, 'samples': 351232, 'steps': 685, 'loss/train': 6.645692825317383}
-03/03/2022 14:13:39 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/03/2022 14:13:43 - INFO - codeparrot_training - Step 686: {'lr': 0.00017150000000000002, 'samples': 351744, 'steps': 686, 'loss/train': 6.154056549072266}
-03/03/2022 14:13:46 - INFO - codeparrot_training - Step 687: {'lr': 0.00017175000000000003, 'samples': 352256, 'steps': 687, 'loss/train': 5.51598596572876}
-03/03/2022 14:13:48 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/03/2022 14:13:51 - INFO - codeparrot_training - Step 688: {'lr': 0.00017199999999999998, 'samples': 352768, 'steps': 688, 'loss/train': 5.821977615356445}
-03/03/2022 14:13:55 - INFO - codeparrot_training - Step 689: {'lr': 0.00017224999999999999, 'samples': 353280, 'steps': 689, 'loss/train': 6.13981819152832}
-03/03/2022 14:13:57 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/03/2022 14:14:00 - INFO - codeparrot_training - Step 690: {'lr': 0.0001725, 'samples': 353792, 'steps': 690, 'loss/train': 5.183568954467773}
-03/03/2022 14:14:03 - INFO - codeparrot_training - Step 691: {'lr': 0.00017275, 'samples': 354304, 'steps': 691, 'loss/train': 6.6873626708984375}
-03/03/2022 14:14:05 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/03/2022 14:14:08 - INFO - codeparrot_training - Step 692: {'lr': 0.000173, 'samples': 354816, 'steps': 692, 'loss/train': 6.312127590179443}
-03/03/2022 14:14:11 - INFO - codeparrot_training - Step 693: {'lr': 0.00017324999999999998, 'samples': 355328, 'steps': 693, 'loss/train': 8.582944869995117}
-03/03/2022 14:14:13 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/03/2022 14:14:17 - INFO - codeparrot_training - Step 694: {'lr': 0.0001735, 'samples': 355840, 'steps': 694, 'loss/train': 6.388099670410156}
-03/03/2022 14:14:20 - INFO - codeparrot_training - Step 695: {'lr': 0.00017375, 'samples': 356352, 'steps': 695, 'loss/train': 5.452615261077881}
-03/03/2022 14:14:22 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/03/2022 14:14:25 - INFO - codeparrot_training - Step 696: {'lr': 0.000174, 'samples': 356864, 'steps': 696, 'loss/train': 6.11560583114624}
-03/03/2022 14:14:28 - INFO - codeparrot_training - Step 697: {'lr': 0.00017424999999999998, 'samples': 357376, 'steps': 697, 'loss/train': 6.420699119567871}
-03/03/2022 14:14:30 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/03/2022 14:14:33 - INFO - codeparrot_training - Step 698: {'lr': 0.00017449999999999999, 'samples': 357888, 'steps': 698, 'loss/train': 5.491775035858154}
-03/03/2022 14:14:36 - INFO - codeparrot_training - Step 699: {'lr': 0.00017475, 'samples': 358400, 'steps': 699, 'loss/train': 5.5680084228515625}
-03/03/2022 14:14:38 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/03/2022 14:14:42 - INFO - codeparrot_training - Step 700: {'lr': 0.000175, 'samples': 358912, 'steps': 700, 'loss/train': 6.3367180824279785}
-03/03/2022 14:14:45 - INFO - codeparrot_training - Step 701: {'lr': 0.00017525, 'samples': 359424, 'steps': 701, 'loss/train': 5.854393482208252}
-03/03/2022 14:14:46 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/03/2022 14:14:50 - INFO - codeparrot_training - Step 702: {'lr': 0.00017549999999999998, 'samples': 359936, 'steps': 702, 'loss/train': 5.815999507904053}
-03/03/2022 14:14:53 - INFO - codeparrot_training - Step 703: {'lr': 0.00017575, 'samples': 360448, 'steps': 703, 'loss/train': 5.308962345123291}
-03/03/2022 14:14:54 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/03/2022 14:14:58 - INFO - codeparrot_training - Step 704: {'lr': 0.000176, 'samples': 360960, 'steps': 704, 'loss/train': 6.1263427734375}
-03/03/2022 14:15:02 - INFO - codeparrot_training - Step 705: {'lr': 0.00017625, 'samples': 361472, 'steps': 705, 'loss/train': 5.6121625900268555}
-03/03/2022 14:15:03 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/03/2022 14:15:07 - INFO - codeparrot_training - Step 706: {'lr': 0.00017649999999999998, 'samples': 361984, 'steps': 706, 'loss/train': 5.607957363128662}
-03/03/2022 14:15:10 - INFO - codeparrot_training - Step 707: {'lr': 0.00017675, 'samples': 362496, 'steps': 707, 'loss/train': 5.5100483894348145}
-03/03/2022 14:15:11 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/03/2022 14:15:15 - INFO - codeparrot_training - Step 708: {'lr': 0.000177, 'samples': 363008, 'steps': 708, 'loss/train': 5.424149990081787}
-03/03/2022 14:15:18 - INFO - codeparrot_training - Step 709: {'lr': 0.00017725, 'samples': 363520, 'steps': 709, 'loss/train': 5.624175071716309}
-03/03/2022 14:15:20 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/03/2022 14:15:24 - INFO - codeparrot_training - Step 710: {'lr': 0.0001775, 'samples': 364032, 'steps': 710, 'loss/train': 5.415778636932373}
-03/03/2022 14:15:27 - INFO - codeparrot_training - Step 711: {'lr': 0.00017774999999999998, 'samples': 364544, 'steps': 711, 'loss/train': 6.274073123931885}
-03/03/2022 14:15:28 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/03/2022 14:15:32 - INFO - codeparrot_training - Step 712: {'lr': 0.000178, 'samples': 365056, 'steps': 712, 'loss/train': 6.082661151885986}
-03/03/2022 14:15:35 - INFO - codeparrot_training - Step 713: {'lr': 0.00017825, 'samples': 365568, 'steps': 713, 'loss/train': 4.292624473571777}
-03/03/2022 14:15:36 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/03/2022 14:15:41 - INFO - codeparrot_training - Step 714: {'lr': 0.0001785, 'samples': 366080, 'steps': 714, 'loss/train': 5.6145453453063965}
-03/03/2022 14:15:44 - INFO - codeparrot_training - Step 715: {'lr': 0.00017875, 'samples': 366592, 'steps': 715, 'loss/train': 5.490015983581543}
-03/03/2022 14:15:45 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/03/2022 14:15:49 - INFO - codeparrot_training - Step 716: {'lr': 0.000179, 'samples': 367104, 'steps': 716, 'loss/train': 5.876565456390381}
-03/03/2022 14:15:52 - INFO - codeparrot_training - Step 717: {'lr': 0.00017925, 'samples': 367616, 'steps': 717, 'loss/train': 4.843731880187988}
-03/03/2022 14:15:53 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/03/2022 14:15:57 - INFO - codeparrot_training - Step 718: {'lr': 0.0001795, 'samples': 368128, 'steps': 718, 'loss/train': 5.822505474090576}
-03/03/2022 14:16:01 - INFO - codeparrot_training - Step 719: {'lr': 0.00017975, 'samples': 368640, 'steps': 719, 'loss/train': 6.161307334899902}
-03/03/2022 14:16:02 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/03/2022 14:16:06 - INFO - codeparrot_training - Step 720: {'lr': 0.00017999999999999998, 'samples': 369152, 'steps': 720, 'loss/train': 4.712026119232178}
-03/03/2022 14:16:09 - INFO - codeparrot_training - Step 721: {'lr': 0.00018025, 'samples': 369664, 'steps': 721, 'loss/train': 5.958030700683594}
-03/03/2022 14:16:12 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/03/2022 14:16:14 - INFO - codeparrot_training - Step 722: {'lr': 0.0001805, 'samples': 370176, 'steps': 722, 'loss/train': 7.373122692108154}
-03/03/2022 14:16:18 - INFO - codeparrot_training - Step 723: {'lr': 0.00018075, 'samples': 370688, 'steps': 723, 'loss/train': 5.89974308013916}
-03/03/2022 14:16:20 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/03/2022 14:16:23 - INFO - codeparrot_training - Step 724: {'lr': 0.000181, 'samples': 371200, 'steps': 724, 'loss/train': 5.497884273529053}
-03/03/2022 14:16:26 - INFO - codeparrot_training - Step 725: {'lr': 0.00018125, 'samples': 371712, 'steps': 725, 'loss/train': 6.3494696617126465}
-03/03/2022 14:16:28 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/03/2022 14:16:31 - INFO - codeparrot_training - Step 726: {'lr': 0.0001815, 'samples': 372224, 'steps': 726, 'loss/train': 7.18757438659668}
-03/03/2022 14:16:35 - INFO - codeparrot_training - Step 727: {'lr': 0.00018175, 'samples': 372736, 'steps': 727, 'loss/train': 5.6792120933532715}
-03/03/2022 14:16:37 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/03/2022 14:16:40 - INFO - codeparrot_training - Step 728: {'lr': 0.000182, 'samples': 373248, 'steps': 728, 'loss/train': 5.624897003173828}
-03/03/2022 14:16:43 - INFO - codeparrot_training - Step 729: {'lr': 0.00018225, 'samples': 373760, 'steps': 729, 'loss/train': 6.5129618644714355}
-03/03/2022 14:16:45 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/03/2022 14:16:48 - INFO - codeparrot_training - Step 730: {'lr': 0.0001825, 'samples': 374272, 'steps': 730, 'loss/train': 6.356884956359863}
-03/03/2022 14:16:51 - INFO - codeparrot_training - Step 731: {'lr': 0.00018275, 'samples': 374784, 'steps': 731, 'loss/train': 5.9126877784729}
-03/03/2022 14:16:53 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/03/2022 14:16:57 - INFO - codeparrot_training - Step 732: {'lr': 0.000183, 'samples': 375296, 'steps': 732, 'loss/train': 5.680290699005127}
-03/03/2022 14:17:00 - INFO - codeparrot_training - Step 733: {'lr': 0.00018325, 'samples': 375808, 'steps': 733, 'loss/train': 6.887684345245361}
-03/03/2022 14:17:01 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/03/2022 14:17:05 - INFO - codeparrot_training - Step 734: {'lr': 0.0001835, 'samples': 376320, 'steps': 734, 'loss/train': 6.368136882781982}
-03/03/2022 14:17:08 - INFO - codeparrot_training - Step 735: {'lr': 0.00018375, 'samples': 376832, 'steps': 735, 'loss/train': 6.857802391052246}
-03/03/2022 14:17:10 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/03/2022 14:17:14 - INFO - codeparrot_training - Step 736: {'lr': 0.000184, 'samples': 377344, 'steps': 736, 'loss/train': 5.284829616546631}
-03/03/2022 14:17:17 - INFO - codeparrot_training - Step 737: {'lr': 0.00018425, 'samples': 377856, 'steps': 737, 'loss/train': 5.682382583618164}
-03/03/2022 14:17:18 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/03/2022 14:17:22 - INFO - codeparrot_training - Step 738: {'lr': 0.0001845, 'samples': 378368, 'steps': 738, 'loss/train': 5.7081146240234375}
-03/03/2022 14:17:25 - INFO - codeparrot_training - Step 739: {'lr': 0.00018475, 'samples': 378880, 'steps': 739, 'loss/train': 5.002049446105957}
-03/03/2022 14:17:27 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/03/2022 14:17:30 - INFO - codeparrot_training - Step 740: {'lr': 0.000185, 'samples': 379392, 'steps': 740, 'loss/train': 5.609866142272949}
-03/03/2022 14:17:34 - INFO - codeparrot_training - Step 741: {'lr': 0.00018525, 'samples': 379904, 'steps': 741, 'loss/train': 5.849599361419678}
-03/03/2022 14:17:35 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/03/2022 14:17:39 - INFO - codeparrot_training - Step 742: {'lr': 0.0001855, 'samples': 380416, 'steps': 742, 'loss/train': 6.124844074249268}
-03/03/2022 14:17:42 - INFO - codeparrot_training - Step 743: {'lr': 0.00018575000000000002, 'samples': 380928, 'steps': 743, 'loss/train': 6.352612495422363}
-03/03/2022 14:17:43 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/03/2022 14:17:47 - INFO - codeparrot_training - Step 744: {'lr': 0.000186, 'samples': 381440, 'steps': 744, 'loss/train': 8.90346908569336}
-03/03/2022 14:17:50 - INFO - codeparrot_training - Step 745: {'lr': 0.00018625, 'samples': 381952, 'steps': 745, 'loss/train': 5.728419303894043}
-03/03/2022 14:17:52 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/03/2022 14:17:56 - INFO - codeparrot_training - Step 746: {'lr': 0.0001865, 'samples': 382464, 'steps': 746, 'loss/train': 6.3111186027526855}
-03/03/2022 14:17:59 - INFO - codeparrot_training - Step 747: {'lr': 0.00018675, 'samples': 382976, 'steps': 747, 'loss/train': 5.691380023956299}
-03/03/2022 14:18:00 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/03/2022 14:18:04 - INFO - codeparrot_training - Step 748: {'lr': 0.000187, 'samples': 383488, 'steps': 748, 'loss/train': 6.1752495765686035}
-03/03/2022 14:18:07 - INFO - codeparrot_training - Step 749: {'lr': 0.00018725, 'samples': 384000, 'steps': 749, 'loss/train': 6.014646053314209}
-03/03/2022 14:18:08 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/03/2022 14:18:12 - INFO - codeparrot_training - Step 750: {'lr': 0.0001875, 'samples': 384512, 'steps': 750, 'loss/train': 3.5758557319641113}
-03/03/2022 14:18:16 - INFO - codeparrot_training - Step 751: {'lr': 0.00018775, 'samples': 385024, 'steps': 751, 'loss/train': 6.044946670532227}
-03/03/2022 14:18:17 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/03/2022 14:18:21 - INFO - codeparrot_training - Step 752: {'lr': 0.00018800000000000002, 'samples': 385536, 'steps': 752, 'loss/train': 7.377934455871582}
-03/03/2022 14:18:24 - INFO - codeparrot_training - Step 753: {'lr': 0.00018825, 'samples': 386048, 'steps': 753, 'loss/train': 5.684968948364258}
-03/03/2022 14:18:26 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/03/2022 14:18:29 - INFO - codeparrot_training - Step 754: {'lr': 0.0001885, 'samples': 386560, 'steps': 754, 'loss/train': 5.705610275268555}
-03/03/2022 14:18:32 - INFO - codeparrot_training - Step 755: {'lr': 0.00018875, 'samples': 387072, 'steps': 755, 'loss/train': 5.378270149230957}
-03/03/2022 14:18:34 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/03/2022 14:18:38 - INFO - codeparrot_training - Step 756: {'lr': 0.000189, 'samples': 387584, 'steps': 756, 'loss/train': 2.837033987045288}
-03/03/2022 14:18:41 - INFO - codeparrot_training - Step 757: {'lr': 0.00018925, 'samples': 388096, 'steps': 757, 'loss/train': 2.5040268898010254}
-03/03/2022 14:18:42 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/03/2022 14:18:46 - INFO - codeparrot_training - Step 758: {'lr': 0.0001895, 'samples': 388608, 'steps': 758, 'loss/train': 2.4035027027130127}
-03/03/2022 14:18:49 - INFO - codeparrot_training - Step 759: {'lr': 0.00018975, 'samples': 389120, 'steps': 759, 'loss/train': 6.120370388031006}
-03/03/2022 14:18:50 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/03/2022 14:18:55 - INFO - codeparrot_training - Step 760: {'lr': 0.00019, 'samples': 389632, 'steps': 760, 'loss/train': 6.647356033325195}
-03/03/2022 14:18:58 - INFO - codeparrot_training - Step 761: {'lr': 0.00019025000000000002, 'samples': 390144, 'steps': 761, 'loss/train': 6.357416152954102}
-03/03/2022 14:18:59 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/03/2022 14:19:03 - INFO - codeparrot_training - Step 762: {'lr': 0.0001905, 'samples': 390656, 'steps': 762, 'loss/train': 5.767858028411865}
-03/03/2022 14:19:06 - INFO - codeparrot_training - Step 763: {'lr': 0.00019075, 'samples': 391168, 'steps': 763, 'loss/train': 5.526143550872803}
-03/03/2022 14:19:07 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/03/2022 14:19:12 - INFO - codeparrot_training - Step 764: {'lr': 0.000191, 'samples': 391680, 'steps': 764, 'loss/train': 5.360974311828613}
-03/03/2022 14:19:15 - INFO - codeparrot_training - Step 765: {'lr': 0.00019125000000000001, 'samples': 392192, 'steps': 765, 'loss/train': 6.272588729858398}
-03/03/2022 14:19:16 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/03/2022 14:19:20 - INFO - codeparrot_training - Step 766: {'lr': 0.00019150000000000002, 'samples': 392704, 'steps': 766, 'loss/train': 6.959072589874268}
-03/03/2022 14:19:23 - INFO - codeparrot_training - Step 767: {'lr': 0.00019175, 'samples': 393216, 'steps': 767, 'loss/train': 6.202326774597168}
-03/03/2022 14:19:24 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/03/2022 14:19:28 - INFO - codeparrot_training - Step 768: {'lr': 0.000192, 'samples': 393728, 'steps': 768, 'loss/train': 5.654978275299072}
-03/03/2022 14:19:32 - INFO - codeparrot_training - Step 769: {'lr': 0.00019225, 'samples': 394240, 'steps': 769, 'loss/train': 6.381503582000732}
-03/03/2022 14:19:33 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/03/2022 14:19:37 - INFO - codeparrot_training - Step 770: {'lr': 0.00019250000000000002, 'samples': 394752, 'steps': 770, 'loss/train': 6.107685565948486}
-03/03/2022 14:19:40 - INFO - codeparrot_training - Step 771: {'lr': 0.00019275, 'samples': 395264, 'steps': 771, 'loss/train': 5.950009822845459}
-03/03/2022 14:19:41 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/03/2022 14:19:45 - INFO - codeparrot_training - Step 772: {'lr': 0.000193, 'samples': 395776, 'steps': 772, 'loss/train': 5.617612361907959}
-03/03/2022 14:19:48 - INFO - codeparrot_training - Step 773: {'lr': 0.00019325, 'samples': 396288, 'steps': 773, 'loss/train': 6.658962249755859}
-03/03/2022 14:19:49 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/03/2022 14:19:54 - INFO - codeparrot_training - Step 774: {'lr': 0.00019350000000000001, 'samples': 396800, 'steps': 774, 'loss/train': 4.896778583526611}
-03/03/2022 14:19:57 - INFO - codeparrot_training - Step 775: {'lr': 0.00019375000000000002, 'samples': 397312, 'steps': 775, 'loss/train': 5.210784912109375}
-03/03/2022 14:19:58 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 14:20:02 - INFO - codeparrot_training - Step 776: {'lr': 0.000194, 'samples': 397824, 'steps': 776, 'loss/train': 6.26840353012085}
-03/03/2022 14:20:05 - INFO - codeparrot_training - Step 777: {'lr': 0.00019425, 'samples': 398336, 'steps': 777, 'loss/train': 5.268444061279297}
-03/03/2022 14:20:06 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/03/2022 14:20:11 - INFO - codeparrot_training - Step 778: {'lr': 0.0001945, 'samples': 398848, 'steps': 778, 'loss/train': 5.089536190032959}
-03/03/2022 14:20:14 - INFO - codeparrot_training - Step 779: {'lr': 0.00019475000000000002, 'samples': 399360, 'steps': 779, 'loss/train': 5.938715934753418}
-03/03/2022 14:20:14 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/03/2022 14:20:19 - INFO - codeparrot_training - Step 780: {'lr': 0.00019500000000000002, 'samples': 399872, 'steps': 780, 'loss/train': 2.5215647220611572}
-03/03/2022 14:20:22 - INFO - codeparrot_training - Step 781: {'lr': 0.00019525, 'samples': 400384, 'steps': 781, 'loss/train': 6.110848903656006}
-03/03/2022 14:20:22 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/03/2022 14:20:27 - INFO - codeparrot_training - Step 782: {'lr': 0.0001955, 'samples': 400896, 'steps': 782, 'loss/train': 5.539410591125488}
-03/03/2022 14:20:31 - INFO - codeparrot_training - Step 783: {'lr': 0.00019575000000000001, 'samples': 401408, 'steps': 783, 'loss/train': 5.276137828826904}
-03/03/2022 14:20:31 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/03/2022 14:20:36 - INFO - codeparrot_training - Step 784: {'lr': 0.00019600000000000002, 'samples': 401920, 'steps': 784, 'loss/train': 5.616477012634277}
-03/03/2022 14:20:39 - INFO - codeparrot_training - Step 785: {'lr': 0.00019625, 'samples': 402432, 'steps': 785, 'loss/train': 5.870465278625488}
-03/03/2022 14:20:40 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/03/2022 14:20:44 - INFO - codeparrot_training - Step 786: {'lr': 0.0001965, 'samples': 402944, 'steps': 786, 'loss/train': 5.635030746459961}
-03/03/2022 14:20:47 - INFO - codeparrot_training - Step 787: {'lr': 0.00019675, 'samples': 403456, 'steps': 787, 'loss/train': 6.045782566070557}
-03/03/2022 14:20:48 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/03/2022 14:20:53 - INFO - codeparrot_training - Step 788: {'lr': 0.00019700000000000002, 'samples': 403968, 'steps': 788, 'loss/train': 5.126619815826416}
-03/03/2022 14:20:56 - INFO - codeparrot_training - Step 789: {'lr': 0.00019725000000000002, 'samples': 404480, 'steps': 789, 'loss/train': 5.62884521484375}
-03/03/2022 14:20:56 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/03/2022 14:21:01 - INFO - codeparrot_training - Step 790: {'lr': 0.0001975, 'samples': 404992, 'steps': 790, 'loss/train': 6.909239768981934}
-03/03/2022 14:21:04 - INFO - codeparrot_training - Step 791: {'lr': 0.00019775, 'samples': 405504, 'steps': 791, 'loss/train': 6.068647861480713}
-03/03/2022 14:21:05 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/03/2022 14:21:09 - INFO - codeparrot_training - Step 792: {'lr': 0.00019800000000000002, 'samples': 406016, 'steps': 792, 'loss/train': 6.472655773162842}
-03/03/2022 14:21:12 - INFO - codeparrot_training - Step 793: {'lr': 0.00019825000000000002, 'samples': 406528, 'steps': 793, 'loss/train': 5.719446182250977}
-03/03/2022 14:21:12 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/03/2022 14:21:18 - INFO - codeparrot_training - Step 794: {'lr': 0.00019850000000000003, 'samples': 407040, 'steps': 794, 'loss/train': 6.148656368255615}
-03/03/2022 14:21:21 - INFO - codeparrot_training - Step 795: {'lr': 0.00019875, 'samples': 407552, 'steps': 795, 'loss/train': 5.593094348907471}
-03/03/2022 14:21:21 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/03/2022 14:21:26 - INFO - codeparrot_training - Step 796: {'lr': 0.000199, 'samples': 408064, 'steps': 796, 'loss/train': 6.0885443687438965}
-03/03/2022 14:21:29 - INFO - codeparrot_training - Step 797: {'lr': 0.00019925000000000002, 'samples': 408576, 'steps': 797, 'loss/train': 5.952763557434082}
-03/03/2022 14:21:29 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/03/2022 14:21:34 - INFO - codeparrot_training - Step 798: {'lr': 0.00019950000000000002, 'samples': 409088, 'steps': 798, 'loss/train': 5.247378826141357}
-03/03/2022 14:21:37 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/03/2022 14:21:40 - INFO - codeparrot_training - Step 799: {'lr': 0.00019975, 'samples': 409600, 'steps': 799, 'loss/train': 6.183495998382568}
-03/03/2022 14:21:43 - INFO - codeparrot_training - Step 800: {'lr': 0.0002, 'samples': 410112, 'steps': 800, 'loss/train': 6.045914649963379}
-03/03/2022 14:21:45 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/03/2022 14:21:48 - INFO - codeparrot_training - Step 801: {'lr': 0.00020025000000000002, 'samples': 410624, 'steps': 801, 'loss/train': 5.351278305053711}
-03/03/2022 14:21:51 - INFO - codeparrot_training - Step 802: {'lr': 0.00020050000000000002, 'samples': 411136, 'steps': 802, 'loss/train': 5.965078353881836}
-03/03/2022 14:21:53 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/03/2022 14:21:56 - INFO - codeparrot_training - Step 803: {'lr': 0.00020075000000000003, 'samples': 411648, 'steps': 803, 'loss/train': 5.071366310119629}
-03/03/2022 14:22:00 - INFO - codeparrot_training - Step 804: {'lr': 0.000201, 'samples': 412160, 'steps': 804, 'loss/train': 5.935673236846924}
-03/03/2022 14:22:02 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/03/2022 14:22:05 - INFO - codeparrot_training - Step 805: {'lr': 0.00020125, 'samples': 412672, 'steps': 805, 'loss/train': 5.727970600128174}
-03/03/2022 14:22:08 - INFO - codeparrot_training - Step 806: {'lr': 0.00020150000000000002, 'samples': 413184, 'steps': 806, 'loss/train': 5.5496931076049805}
-03/03/2022 14:22:10 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/03/2022 14:22:13 - INFO - codeparrot_training - Step 807: {'lr': 0.00020175000000000003, 'samples': 413696, 'steps': 807, 'loss/train': 6.029293060302734}
-03/03/2022 14:22:16 - INFO - codeparrot_training - Step 808: {'lr': 0.000202, 'samples': 414208, 'steps': 808, 'loss/train': 2.7012906074523926}
-03/03/2022 14:22:18 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/03/2022 14:22:22 - INFO - codeparrot_training - Step 809: {'lr': 0.00020225, 'samples': 414720, 'steps': 809, 'loss/train': 5.281220436096191}
-03/03/2022 14:22:25 - INFO - codeparrot_training - Step 810: {'lr': 0.00020250000000000002, 'samples': 415232, 'steps': 810, 'loss/train': 5.184370994567871}
-03/03/2022 14:22:26 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/03/2022 14:22:30 - INFO - codeparrot_training - Step 811: {'lr': 0.00020275000000000002, 'samples': 415744, 'steps': 811, 'loss/train': 6.637288570404053}
-03/03/2022 14:22:33 - INFO - codeparrot_training - Step 812: {'lr': 0.00020300000000000003, 'samples': 416256, 'steps': 812, 'loss/train': 4.509408473968506}
-03/03/2022 14:22:35 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/03/2022 14:22:38 - INFO - codeparrot_training - Step 813: {'lr': 0.00020324999999999998, 'samples': 416768, 'steps': 813, 'loss/train': 6.244888782501221}
-03/03/2022 14:22:42 - INFO - codeparrot_training - Step 814: {'lr': 0.00020349999999999999, 'samples': 417280, 'steps': 814, 'loss/train': 4.975861072540283}
-03/03/2022 14:22:43 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/03/2022 14:22:47 - INFO - codeparrot_training - Step 815: {'lr': 0.00020375, 'samples': 417792, 'steps': 815, 'loss/train': 5.894258975982666}
-03/03/2022 14:22:50 - INFO - codeparrot_training - Step 816: {'lr': 0.000204, 'samples': 418304, 'steps': 816, 'loss/train': 5.171676158905029}
-03/03/2022 14:22:51 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/03/2022 14:22:55 - INFO - codeparrot_training - Step 817: {'lr': 0.00020425, 'samples': 418816, 'steps': 817, 'loss/train': 6.164328098297119}
-03/03/2022 14:22:58 - INFO - codeparrot_training - Step 818: {'lr': 0.00020449999999999998, 'samples': 419328, 'steps': 818, 'loss/train': 4.458515167236328}
-03/03/2022 14:23:00 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/03/2022 14:23:04 - INFO - codeparrot_training - Step 819: {'lr': 0.00020475, 'samples': 419840, 'steps': 819, 'loss/train': 5.796923637390137}
-03/03/2022 14:23:07 - INFO - codeparrot_training - Step 820: {'lr': 0.000205, 'samples': 420352, 'steps': 820, 'loss/train': 5.776224613189697}
-03/03/2022 14:23:09 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/03/2022 14:23:12 - INFO - codeparrot_training - Step 821: {'lr': 0.00020525, 'samples': 420864, 'steps': 821, 'loss/train': 4.670717716217041}
-03/03/2022 14:23:15 - INFO - codeparrot_training - Step 822: {'lr': 0.00020549999999999998, 'samples': 421376, 'steps': 822, 'loss/train': 5.6624531745910645}
-03/03/2022 14:23:17 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/03/2022 14:23:20 - INFO - codeparrot_training - Step 823: {'lr': 0.00020575, 'samples': 421888, 'steps': 823, 'loss/train': 4.882242202758789}
-03/03/2022 14:23:24 - INFO - codeparrot_training - Step 824: {'lr': 0.000206, 'samples': 422400, 'steps': 824, 'loss/train': 5.353019714355469}
-03/03/2022 14:23:25 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/03/2022 14:23:29 - INFO - codeparrot_training - Step 825: {'lr': 0.00020625, 'samples': 422912, 'steps': 825, 'loss/train': 4.812110424041748}
-03/03/2022 14:23:32 - INFO - codeparrot_training - Step 826: {'lr': 0.0002065, 'samples': 423424, 'steps': 826, 'loss/train': 5.197993755340576}
-03/03/2022 14:23:33 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/03/2022 14:23:37 - INFO - codeparrot_training - Step 827: {'lr': 0.00020674999999999998, 'samples': 423936, 'steps': 827, 'loss/train': 6.301405906677246}
-03/03/2022 14:23:40 - INFO - codeparrot_training - Step 828: {'lr': 0.000207, 'samples': 424448, 'steps': 828, 'loss/train': 5.564136505126953}
-03/03/2022 14:23:41 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/03/2022 14:23:46 - INFO - codeparrot_training - Step 829: {'lr': 0.00020725, 'samples': 424960, 'steps': 829, 'loss/train': 4.753064155578613}
-03/03/2022 14:23:49 - INFO - codeparrot_training - Step 830: {'lr': 0.0002075, 'samples': 425472, 'steps': 830, 'loss/train': 4.964693546295166}
-03/03/2022 14:23:50 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/03/2022 14:23:54 - INFO - codeparrot_training - Step 831: {'lr': 0.00020774999999999998, 'samples': 425984, 'steps': 831, 'loss/train': 5.069149494171143}
-03/03/2022 14:23:57 - INFO - codeparrot_training - Step 832: {'lr': 0.000208, 'samples': 426496, 'steps': 832, 'loss/train': 5.400967597961426}
-03/03/2022 14:23:58 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/03/2022 14:24:03 - INFO - codeparrot_training - Step 833: {'lr': 0.00020825, 'samples': 427008, 'steps': 833, 'loss/train': 6.3588104248046875}
-03/03/2022 14:24:06 - INFO - codeparrot_training - Step 834: {'lr': 0.0002085, 'samples': 427520, 'steps': 834, 'loss/train': 5.880354404449463}
-03/03/2022 14:24:06 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/03/2022 14:24:11 - INFO - codeparrot_training - Step 835: {'lr': 0.00020875, 'samples': 428032, 'steps': 835, 'loss/train': 5.498161792755127}
-03/03/2022 14:24:14 - INFO - codeparrot_training - Step 836: {'lr': 0.00020899999999999998, 'samples': 428544, 'steps': 836, 'loss/train': 5.577434062957764}
-03/03/2022 14:24:15 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/03/2022 14:24:19 - INFO - codeparrot_training - Step 837: {'lr': 0.00020925, 'samples': 429056, 'steps': 837, 'loss/train': 5.179044723510742}
-03/03/2022 14:24:23 - INFO - codeparrot_training - Step 838: {'lr': 0.0002095, 'samples': 429568, 'steps': 838, 'loss/train': 5.296634197235107}
-03/03/2022 14:24:23 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/03/2022 14:24:28 - INFO - codeparrot_training - Step 839: {'lr': 0.00020975, 'samples': 430080, 'steps': 839, 'loss/train': 5.37893009185791}
-03/03/2022 14:24:31 - INFO - codeparrot_training - Step 840: {'lr': 0.00021, 'samples': 430592, 'steps': 840, 'loss/train': 5.557505130767822}
-03/03/2022 14:24:31 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/03/2022 14:24:36 - INFO - codeparrot_training - Step 841: {'lr': 0.00021025, 'samples': 431104, 'steps': 841, 'loss/train': 6.843445777893066}
-03/03/2022 14:24:39 - INFO - codeparrot_training - Step 842: {'lr': 0.0002105, 'samples': 431616, 'steps': 842, 'loss/train': 6.06321382522583}
-03/03/2022 14:24:40 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/03/2022 14:24:45 - INFO - codeparrot_training - Step 843: {'lr': 0.00021075, 'samples': 432128, 'steps': 843, 'loss/train': 5.441623210906982}
-03/03/2022 14:24:48 - INFO - codeparrot_training - Step 844: {'lr': 0.000211, 'samples': 432640, 'steps': 844, 'loss/train': 5.4186506271362305}
-03/03/2022 14:24:48 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/03/2022 14:24:53 - INFO - codeparrot_training - Step 845: {'lr': 0.00021124999999999998, 'samples': 433152, 'steps': 845, 'loss/train': 7.605123996734619}
-03/03/2022 14:24:57 - INFO - codeparrot_training - Step 846: {'lr': 0.0002115, 'samples': 433664, 'steps': 846, 'loss/train': 6.859156131744385}
-03/03/2022 14:24:58 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/03/2022 14:25:02 - INFO - codeparrot_training - Step 847: {'lr': 0.00021175, 'samples': 434176, 'steps': 847, 'loss/train': 4.927143573760986}
-03/03/2022 14:25:05 - INFO - codeparrot_training - Step 848: {'lr': 0.000212, 'samples': 434688, 'steps': 848, 'loss/train': 5.4894609451293945}
-03/03/2022 14:25:06 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/03/2022 14:25:10 - INFO - codeparrot_training - Step 849: {'lr': 0.00021225, 'samples': 435200, 'steps': 849, 'loss/train': 5.905498027801514}
-03/03/2022 14:25:13 - INFO - codeparrot_training - Step 850: {'lr': 0.0002125, 'samples': 435712, 'steps': 850, 'loss/train': 6.350372791290283}
-03/03/2022 14:25:15 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/03/2022 14:25:18 - INFO - codeparrot_training - Step 851: {'lr': 0.00021275, 'samples': 436224, 'steps': 851, 'loss/train': 5.40626859664917}
-03/03/2022 14:25:22 - INFO - codeparrot_training - Step 852: {'lr': 0.000213, 'samples': 436736, 'steps': 852, 'loss/train': 6.239688396453857}
-03/03/2022 14:25:23 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/03/2022 14:25:27 - INFO - codeparrot_training - Step 853: {'lr': 0.00021325, 'samples': 437248, 'steps': 853, 'loss/train': 6.076501369476318}
-03/03/2022 14:25:30 - INFO - codeparrot_training - Step 854: {'lr': 0.0002135, 'samples': 437760, 'steps': 854, 'loss/train': 4.657830715179443}
-03/03/2022 14:25:31 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/03/2022 14:25:35 - INFO - codeparrot_training - Step 855: {'lr': 0.00021375, 'samples': 438272, 'steps': 855, 'loss/train': 4.943812370300293}
-03/03/2022 14:25:39 - INFO - codeparrot_training - Step 856: {'lr': 0.000214, 'samples': 438784, 'steps': 856, 'loss/train': 6.044374942779541}
-03/03/2022 14:25:40 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/03/2022 14:25:44 - INFO - codeparrot_training - Step 857: {'lr': 0.00021425, 'samples': 439296, 'steps': 857, 'loss/train': 5.943901062011719}
-03/03/2022 14:25:47 - INFO - codeparrot_training - Step 858: {'lr': 0.0002145, 'samples': 439808, 'steps': 858, 'loss/train': 5.431617259979248}
-03/03/2022 14:25:50 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/03/2022 14:25:53 - INFO - codeparrot_training - Step 859: {'lr': 0.00021475, 'samples': 440320, 'steps': 859, 'loss/train': 6.063345432281494}
-03/03/2022 14:25:56 - INFO - codeparrot_training - Step 860: {'lr': 0.000215, 'samples': 440832, 'steps': 860, 'loss/train': 5.475767612457275}
-03/03/2022 14:25:58 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/03/2022 14:26:01 - INFO - codeparrot_training - Step 861: {'lr': 0.00021525, 'samples': 441344, 'steps': 861, 'loss/train': 5.581014633178711}
-03/03/2022 14:26:04 - INFO - codeparrot_training - Step 862: {'lr': 0.0002155, 'samples': 441856, 'steps': 862, 'loss/train': 5.2505784034729}
-03/03/2022 14:26:06 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/03/2022 14:26:09 - INFO - codeparrot_training - Step 863: {'lr': 0.00021575, 'samples': 442368, 'steps': 863, 'loss/train': 5.044404029846191}
-03/03/2022 14:26:13 - INFO - codeparrot_training - Step 864: {'lr': 0.000216, 'samples': 442880, 'steps': 864, 'loss/train': 5.825626850128174}
-03/03/2022 14:26:14 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/03/2022 14:26:18 - INFO - codeparrot_training - Step 865: {'lr': 0.00021625, 'samples': 443392, 'steps': 865, 'loss/train': 6.18358850479126}
-03/03/2022 14:26:21 - INFO - codeparrot_training - Step 866: {'lr': 0.0002165, 'samples': 443904, 'steps': 866, 'loss/train': 5.078124046325684}
-03/03/2022 14:26:23 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/03/2022 14:26:26 - INFO - codeparrot_training - Step 867: {'lr': 0.00021675, 'samples': 444416, 'steps': 867, 'loss/train': 5.569344997406006}
-03/03/2022 14:26:29 - INFO - codeparrot_training - Step 868: {'lr': 0.00021700000000000002, 'samples': 444928, 'steps': 868, 'loss/train': 4.874898433685303}
-03/03/2022 14:26:31 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/03/2022 14:26:35 - INFO - codeparrot_training - Step 869: {'lr': 0.00021725, 'samples': 445440, 'steps': 869, 'loss/train': 5.113021373748779}
-03/03/2022 14:26:38 - INFO - codeparrot_training - Step 870: {'lr': 0.0002175, 'samples': 445952, 'steps': 870, 'loss/train': 5.168470859527588}
-03/03/2022 14:26:39 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/03/2022 14:26:43 - INFO - codeparrot_training - Step 871: {'lr': 0.00021775, 'samples': 446464, 'steps': 871, 'loss/train': 5.251348495483398}
-03/03/2022 14:26:46 - INFO - codeparrot_training - Step 872: {'lr': 0.000218, 'samples': 446976, 'steps': 872, 'loss/train': 2.1578965187072754}
-03/03/2022 14:26:47 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/03/2022 14:26:51 - INFO - codeparrot_training - Step 873: {'lr': 0.00021825, 'samples': 447488, 'steps': 873, 'loss/train': 5.851541519165039}
-03/03/2022 14:26:55 - INFO - codeparrot_training - Step 874: {'lr': 0.0002185, 'samples': 448000, 'steps': 874, 'loss/train': 5.197221279144287}
-03/03/2022 14:26:56 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/03/2022 14:27:00 - INFO - codeparrot_training - Step 875: {'lr': 0.00021875, 'samples': 448512, 'steps': 875, 'loss/train': 4.8866286277771}
-03/03/2022 14:27:03 - INFO - codeparrot_training - Step 876: {'lr': 0.000219, 'samples': 449024, 'steps': 876, 'loss/train': 6.937936305999756}
-03/03/2022 14:27:04 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/03/2022 14:27:08 - INFO - codeparrot_training - Step 877: {'lr': 0.00021925000000000002, 'samples': 449536, 'steps': 877, 'loss/train': 6.003185749053955}
-03/03/2022 14:27:11 - INFO - codeparrot_training - Step 878: {'lr': 0.0002195, 'samples': 450048, 'steps': 878, 'loss/train': 5.534326076507568}
-03/03/2022 14:27:12 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/03/2022 14:27:17 - INFO - codeparrot_training - Step 879: {'lr': 0.00021975, 'samples': 450560, 'steps': 879, 'loss/train': 7.85198974609375}
-03/03/2022 14:27:20 - INFO - codeparrot_training - Step 880: {'lr': 0.00022, 'samples': 451072, 'steps': 880, 'loss/train': 5.007497787475586}
-03/03/2022 14:27:21 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/03/2022 14:27:25 - INFO - codeparrot_training - Step 881: {'lr': 0.00022025000000000001, 'samples': 451584, 'steps': 881, 'loss/train': 5.695184230804443}
-03/03/2022 14:27:28 - INFO - codeparrot_training - Step 882: {'lr': 0.0002205, 'samples': 452096, 'steps': 882, 'loss/train': 6.506006717681885}
-03/03/2022 14:27:29 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/03/2022 14:27:33 - INFO - codeparrot_training - Step 883: {'lr': 0.00022075, 'samples': 452608, 'steps': 883, 'loss/train': 4.965909957885742}
-03/03/2022 14:27:37 - INFO - codeparrot_training - Step 884: {'lr': 0.000221, 'samples': 453120, 'steps': 884, 'loss/train': 5.829873561859131}
-03/03/2022 14:27:37 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/03/2022 14:27:42 - INFO - codeparrot_training - Step 885: {'lr': 0.00022125, 'samples': 453632, 'steps': 885, 'loss/train': 5.798379421234131}
-03/03/2022 14:27:45 - INFO - codeparrot_training - Step 886: {'lr': 0.00022150000000000002, 'samples': 454144, 'steps': 886, 'loss/train': 5.840906143188477}
-03/03/2022 14:27:45 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/03/2022 14:27:50 - INFO - codeparrot_training - Step 887: {'lr': 0.00022175, 'samples': 454656, 'steps': 887, 'loss/train': 5.298375129699707}
-03/03/2022 14:27:53 - INFO - codeparrot_training - Step 888: {'lr': 0.000222, 'samples': 455168, 'steps': 888, 'loss/train': 5.826112747192383}
-03/03/2022 14:27:53 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/03/2022 14:27:58 - INFO - codeparrot_training - Step 889: {'lr': 0.00022225, 'samples': 455680, 'steps': 889, 'loss/train': 5.942397594451904}
-03/03/2022 14:28:02 - INFO - codeparrot_training - Step 890: {'lr': 0.00022250000000000001, 'samples': 456192, 'steps': 890, 'loss/train': 5.465619087219238}
-03/03/2022 14:28:02 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/03/2022 14:28:07 - INFO - codeparrot_training - Step 891: {'lr': 0.00022275000000000002, 'samples': 456704, 'steps': 891, 'loss/train': 5.768956661224365}
-03/03/2022 14:28:10 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/03/2022 14:28:12 - INFO - codeparrot_training - Step 892: {'lr': 0.000223, 'samples': 457216, 'steps': 892, 'loss/train': 6.329216957092285}
-03/03/2022 14:28:15 - INFO - codeparrot_training - Step 893: {'lr': 0.00022325, 'samples': 457728, 'steps': 893, 'loss/train': 5.524855613708496}
-03/03/2022 14:28:18 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/03/2022 14:28:21 - INFO - codeparrot_training - Step 894: {'lr': 0.0002235, 'samples': 458240, 'steps': 894, 'loss/train': 6.467149257659912}
-03/03/2022 14:28:24 - INFO - codeparrot_training - Step 895: {'lr': 0.00022375000000000002, 'samples': 458752, 'steps': 895, 'loss/train': 5.564155101776123}
-03/03/2022 14:28:26 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/03/2022 14:28:29 - INFO - codeparrot_training - Step 896: {'lr': 0.000224, 'samples': 459264, 'steps': 896, 'loss/train': 5.399448871612549}
-03/03/2022 14:28:32 - INFO - codeparrot_training - Step 897: {'lr': 0.00022425, 'samples': 459776, 'steps': 897, 'loss/train': 4.8847150802612305}
-03/03/2022 14:28:35 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/03/2022 14:28:37 - INFO - codeparrot_training - Step 898: {'lr': 0.0002245, 'samples': 460288, 'steps': 898, 'loss/train': 5.0721964836120605}
-03/03/2022 14:28:41 - INFO - codeparrot_training - Step 899: {'lr': 0.00022475000000000001, 'samples': 460800, 'steps': 899, 'loss/train': 5.297183990478516}
-03/03/2022 14:28:43 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/03/2022 14:28:46 - INFO - codeparrot_training - Step 900: {'lr': 0.00022500000000000002, 'samples': 461312, 'steps': 900, 'loss/train': 6.471324920654297}
-03/03/2022 14:28:49 - INFO - codeparrot_training - Step 901: {'lr': 0.00022525, 'samples': 461824, 'steps': 901, 'loss/train': 5.060986042022705}
-03/03/2022 14:28:51 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/03/2022 14:28:54 - INFO - codeparrot_training - Step 902: {'lr': 0.0002255, 'samples': 462336, 'steps': 902, 'loss/train': 5.69996452331543}
-03/03/2022 14:28:57 - INFO - codeparrot_training - Step 903: {'lr': 0.00022575, 'samples': 462848, 'steps': 903, 'loss/train': 6.508148193359375}
-03/03/2022 14:28:59 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/03/2022 14:29:02 - INFO - codeparrot_training - Step 904: {'lr': 0.00022600000000000002, 'samples': 463360, 'steps': 904, 'loss/train': 5.452254772186279}
-03/03/2022 14:29:06 - INFO - codeparrot_training - Step 905: {'lr': 0.00022625000000000002, 'samples': 463872, 'steps': 905, 'loss/train': 6.821559906005859}
-03/03/2022 14:29:07 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/03/2022 14:29:11 - INFO - codeparrot_training - Step 906: {'lr': 0.0002265, 'samples': 464384, 'steps': 906, 'loss/train': 5.089369773864746}
-03/03/2022 14:29:14 - INFO - codeparrot_training - Step 907: {'lr': 0.00022675, 'samples': 464896, 'steps': 907, 'loss/train': 4.6399054527282715}
-03/03/2022 14:29:15 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/03/2022 14:29:19 - INFO - codeparrot_training - Step 908: {'lr': 0.00022700000000000002, 'samples': 465408, 'steps': 908, 'loss/train': 5.006394863128662}
-03/03/2022 14:29:22 - INFO - codeparrot_training - Step 909: {'lr': 0.00022725000000000002, 'samples': 465920, 'steps': 909, 'loss/train': 5.468337059020996}
-03/03/2022 14:29:24 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/03/2022 14:29:28 - INFO - codeparrot_training - Step 910: {'lr': 0.0002275, 'samples': 466432, 'steps': 910, 'loss/train': 5.463813781738281}
-03/03/2022 14:29:31 - INFO - codeparrot_training - Step 911: {'lr': 0.00022775, 'samples': 466944, 'steps': 911, 'loss/train': 5.19062614440918}
-03/03/2022 14:29:32 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/03/2022 14:29:36 - INFO - codeparrot_training - Step 912: {'lr': 0.000228, 'samples': 467456, 'steps': 912, 'loss/train': 5.039602756500244}
-03/03/2022 14:29:39 - INFO - codeparrot_training - Step 913: {'lr': 0.00022825000000000002, 'samples': 467968, 'steps': 913, 'loss/train': 5.904970169067383}
-03/03/2022 14:29:41 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/03/2022 14:29:44 - INFO - codeparrot_training - Step 914: {'lr': 0.00022850000000000002, 'samples': 468480, 'steps': 914, 'loss/train': 5.654131889343262}
-03/03/2022 14:29:48 - INFO - codeparrot_training - Step 915: {'lr': 0.00022875, 'samples': 468992, 'steps': 915, 'loss/train': 5.448190689086914}
-03/03/2022 14:29:49 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/03/2022 14:29:53 - INFO - codeparrot_training - Step 916: {'lr': 0.000229, 'samples': 469504, 'steps': 916, 'loss/train': 5.636771202087402}
-03/03/2022 14:29:56 - INFO - codeparrot_training - Step 917: {'lr': 0.00022925000000000002, 'samples': 470016, 'steps': 917, 'loss/train': 5.562810897827148}
-03/03/2022 14:29:57 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/03/2022 14:30:01 - INFO - codeparrot_training - Step 918: {'lr': 0.00022950000000000002, 'samples': 470528, 'steps': 918, 'loss/train': 5.274580001831055}
-03/03/2022 14:30:04 - INFO - codeparrot_training - Step 919: {'lr': 0.00022975000000000003, 'samples': 471040, 'steps': 919, 'loss/train': 4.779916763305664}
-03/03/2022 14:30:05 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/03/2022 14:30:10 - INFO - codeparrot_training - Step 920: {'lr': 0.00023, 'samples': 471552, 'steps': 920, 'loss/train': 5.501857280731201}
-03/03/2022 14:30:13 - INFO - codeparrot_training - Step 921: {'lr': 0.00023025, 'samples': 472064, 'steps': 921, 'loss/train': 5.448602199554443}
-03/03/2022 14:30:14 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/03/2022 14:30:18 - INFO - codeparrot_training - Step 922: {'lr': 0.00023050000000000002, 'samples': 472576, 'steps': 922, 'loss/train': 2.3943774700164795}
-03/03/2022 14:30:21 - INFO - codeparrot_training - Step 923: {'lr': 0.00023075000000000003, 'samples': 473088, 'steps': 923, 'loss/train': 2.5441648960113525}
-03/03/2022 14:30:22 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/03/2022 14:30:26 - INFO - codeparrot_training - Step 924: {'lr': 0.000231, 'samples': 473600, 'steps': 924, 'loss/train': 5.14992094039917}
-03/03/2022 14:30:29 - INFO - codeparrot_training - Step 925: {'lr': 0.00023125, 'samples': 474112, 'steps': 925, 'loss/train': 5.638806343078613}
-03/03/2022 14:30:30 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/03/2022 14:30:35 - INFO - codeparrot_training - Step 926: {'lr': 0.00023150000000000002, 'samples': 474624, 'steps': 926, 'loss/train': 5.534430503845215}
-03/03/2022 14:30:38 - INFO - codeparrot_training - Step 927: {'lr': 0.00023175000000000002, 'samples': 475136, 'steps': 927, 'loss/train': 5.90189266204834}
-03/03/2022 14:30:39 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/03/2022 14:30:43 - INFO - codeparrot_training - Step 928: {'lr': 0.00023200000000000003, 'samples': 475648, 'steps': 928, 'loss/train': 4.602533340454102}
-03/03/2022 14:30:46 - INFO - codeparrot_training - Step 929: {'lr': 0.00023225, 'samples': 476160, 'steps': 929, 'loss/train': 5.524892330169678}
-03/03/2022 14:30:47 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/03/2022 14:30:51 - INFO - codeparrot_training - Step 930: {'lr': 0.0002325, 'samples': 476672, 'steps': 930, 'loss/train': 5.662743091583252}
-03/03/2022 14:30:55 - INFO - codeparrot_training - Step 931: {'lr': 0.00023275000000000002, 'samples': 477184, 'steps': 931, 'loss/train': 4.883127212524414}
-03/03/2022 14:30:55 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/03/2022 14:31:00 - INFO - codeparrot_training - Step 932: {'lr': 0.00023300000000000003, 'samples': 477696, 'steps': 932, 'loss/train': 5.51088809967041}
-03/03/2022 14:31:03 - INFO - codeparrot_training - Step 933: {'lr': 0.00023325, 'samples': 478208, 'steps': 933, 'loss/train': 4.705718517303467}
-03/03/2022 14:31:08 - INFO - codeparrot_training - Step 934: {'lr': 0.0002335, 'samples': 478720, 'steps': 934, 'loss/train': 5.287855625152588}
-03/03/2022 14:31:12 - INFO - codeparrot_training - Step 935: {'lr': 0.00023375000000000002, 'samples': 479232, 'steps': 935, 'loss/train': 3.7623660564422607}
-03/03/2022 14:31:12 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/03/2022 14:31:17 - INFO - codeparrot_training - Step 936: {'lr': 0.00023400000000000002, 'samples': 479744, 'steps': 936, 'loss/train': 4.8467183113098145}
-03/03/2022 14:31:20 - INFO - codeparrot_training - Step 937: {'lr': 0.00023425000000000003, 'samples': 480256, 'steps': 937, 'loss/train': 4.810800075531006}
-03/03/2022 14:31:20 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/03/2022 14:31:25 - INFO - codeparrot_training - Step 938: {'lr': 0.00023449999999999998, 'samples': 480768, 'steps': 938, 'loss/train': 5.6370368003845215}
-03/03/2022 14:31:28 - INFO - codeparrot_training - Step 939: {'lr': 0.00023475, 'samples': 481280, 'steps': 939, 'loss/train': 4.962849140167236}
-03/03/2022 14:31:28 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/03/2022 14:31:34 - INFO - codeparrot_training - Step 940: {'lr': 0.000235, 'samples': 481792, 'steps': 940, 'loss/train': 5.930874824523926}
-03/03/2022 14:31:37 - INFO - codeparrot_training - Step 941: {'lr': 0.00023525, 'samples': 482304, 'steps': 941, 'loss/train': 4.297204494476318}
-03/03/2022 14:31:37 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/03/2022 14:31:42 - INFO - codeparrot_training - Step 942: {'lr': 0.0002355, 'samples': 482816, 'steps': 942, 'loss/train': 4.700397968292236}
-03/03/2022 14:31:45 - INFO - codeparrot_training - Step 943: {'lr': 0.00023574999999999998, 'samples': 483328, 'steps': 943, 'loss/train': 8.059362411499023}
-03/03/2022 14:31:45 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/03/2022 14:31:51 - INFO - codeparrot_training - Step 944: {'lr': 0.000236, 'samples': 483840, 'steps': 944, 'loss/train': 5.662092208862305}
-03/03/2022 14:31:53 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/03/2022 14:31:56 - INFO - codeparrot_training - Step 945: {'lr': 0.00023625, 'samples': 484352, 'steps': 945, 'loss/train': 5.7917633056640625}
-03/03/2022 14:31:59 - INFO - codeparrot_training - Step 946: {'lr': 0.0002365, 'samples': 484864, 'steps': 946, 'loss/train': 6.147116184234619}
-03/03/2022 14:32:02 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/03/2022 14:32:04 - INFO - codeparrot_training - Step 947: {'lr': 0.00023674999999999998, 'samples': 485376, 'steps': 947, 'loss/train': 5.417236804962158}
-03/03/2022 14:32:07 - INFO - codeparrot_training - Step 948: {'lr': 0.000237, 'samples': 485888, 'steps': 948, 'loss/train': 4.750515937805176}
-03/03/2022 14:32:10 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/03/2022 14:32:13 - INFO - codeparrot_training - Step 949: {'lr': 0.00023725, 'samples': 486400, 'steps': 949, 'loss/train': 4.7533040046691895}
-03/03/2022 14:32:16 - INFO - codeparrot_training - Step 950: {'lr': 0.0002375, 'samples': 486912, 'steps': 950, 'loss/train': 5.379957675933838}
-03/03/2022 14:32:19 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/03/2022 14:32:21 - INFO - codeparrot_training - Step 951: {'lr': 0.00023775, 'samples': 487424, 'steps': 951, 'loss/train': 5.162179470062256}
-03/03/2022 14:32:24 - INFO - codeparrot_training - Step 952: {'lr': 0.00023799999999999998, 'samples': 487936, 'steps': 952, 'loss/train': 5.595740795135498}
-03/03/2022 14:32:27 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/03/2022 14:32:29 - INFO - codeparrot_training - Step 953: {'lr': 0.00023825, 'samples': 488448, 'steps': 953, 'loss/train': 4.310987949371338}
-03/03/2022 14:32:33 - INFO - codeparrot_training - Step 954: {'lr': 0.0002385, 'samples': 488960, 'steps': 954, 'loss/train': 5.940654277801514}
-03/03/2022 14:32:35 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/03/2022 14:32:38 - INFO - codeparrot_training - Step 955: {'lr': 0.00023875, 'samples': 489472, 'steps': 955, 'loss/train': 5.359099864959717}
-03/03/2022 14:32:41 - INFO - codeparrot_training - Step 956: {'lr': 0.00023899999999999998, 'samples': 489984, 'steps': 956, 'loss/train': 5.056358814239502}
-03/03/2022 14:32:44 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/03/2022 14:32:46 - INFO - codeparrot_training - Step 957: {'lr': 0.00023925, 'samples': 490496, 'steps': 957, 'loss/train': 5.649569034576416}
-03/03/2022 14:32:49 - INFO - codeparrot_training - Step 958: {'lr': 0.0002395, 'samples': 491008, 'steps': 958, 'loss/train': 5.705789089202881}
-03/03/2022 14:32:52 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/03/2022 14:32:55 - INFO - codeparrot_training - Step 959: {'lr': 0.00023975, 'samples': 491520, 'steps': 959, 'loss/train': 4.851657390594482}
-03/03/2022 14:32:58 - INFO - codeparrot_training - Step 960: {'lr': 0.00024, 'samples': 492032, 'steps': 960, 'loss/train': 4.245975017547607}
-03/03/2022 14:33:00 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/03/2022 14:33:03 - INFO - codeparrot_training - Step 961: {'lr': 0.00024024999999999999, 'samples': 492544, 'steps': 961, 'loss/train': 5.14569616317749}
-03/03/2022 14:33:06 - INFO - codeparrot_training - Step 962: {'lr': 0.0002405, 'samples': 493056, 'steps': 962, 'loss/train': 6.001979351043701}
-03/03/2022 14:33:08 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/03/2022 14:33:11 - INFO - codeparrot_training - Step 963: {'lr': 0.00024075, 'samples': 493568, 'steps': 963, 'loss/train': 4.987338066101074}
-03/03/2022 14:33:15 - INFO - codeparrot_training - Step 964: {'lr': 0.000241, 'samples': 494080, 'steps': 964, 'loss/train': 5.097022533416748}
-03/03/2022 14:33:16 - INFO - codeparrot_training - Skipping example with length 285 (seq_length=1024)
-03/03/2022 14:33:20 - INFO - codeparrot_training - Step 965: {'lr': 0.00024125, 'samples': 494592, 'steps': 965, 'loss/train': 6.025006294250488}
-03/03/2022 14:33:23 - INFO - codeparrot_training - Step 966: {'lr': 0.0002415, 'samples': 495104, 'steps': 966, 'loss/train': 5.418980121612549}
-03/03/2022 14:33:25 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/03/2022 14:33:29 - INFO - codeparrot_training - Step 967: {'lr': 0.00024175, 'samples': 495616, 'steps': 967, 'loss/train': 5.099531650543213}
-03/03/2022 14:33:32 - INFO - codeparrot_training - Step 968: {'lr': 0.000242, 'samples': 496128, 'steps': 968, 'loss/train': 5.151614665985107}
-03/03/2022 14:33:35 - INFO - codeparrot_training - Step 969: {'lr': 0.00024225, 'samples': 496640, 'steps': 969, 'loss/train': 5.159854888916016}
-03/03/2022 14:33:35 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/03/2022 14:33:40 - INFO - codeparrot_training - Step 970: {'lr': 0.00024249999999999999, 'samples': 497152, 'steps': 970, 'loss/train': 6.823923110961914}
-03/03/2022 14:33:43 - INFO - codeparrot_training - Step 971: {'lr': 0.00024275, 'samples': 497664, 'steps': 971, 'loss/train': 6.1451215744018555}
-03/03/2022 14:33:43 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/03/2022 14:33:49 - INFO - codeparrot_training - Step 972: {'lr': 0.000243, 'samples': 498176, 'steps': 972, 'loss/train': 5.431978225708008}
-03/03/2022 14:33:52 - INFO - codeparrot_training - Step 973: {'lr': 0.00024325, 'samples': 498688, 'steps': 973, 'loss/train': 4.159397125244141}
-03/03/2022 14:33:52 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/03/2022 14:33:57 - INFO - codeparrot_training - Step 974: {'lr': 0.0002435, 'samples': 499200, 'steps': 974, 'loss/train': 4.99053430557251}
-03/03/2022 14:34:00 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/03/2022 14:34:02 - INFO - codeparrot_training - Step 975: {'lr': 0.00024375, 'samples': 499712, 'steps': 975, 'loss/train': 5.461595058441162}
-03/03/2022 14:34:05 - INFO - codeparrot_training - Step 976: {'lr': 0.000244, 'samples': 500224, 'steps': 976, 'loss/train': 4.606551170349121}
-03/03/2022 14:34:08 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/03/2022 14:34:10 - INFO - codeparrot_training - Step 977: {'lr': 0.00024425, 'samples': 500736, 'steps': 977, 'loss/train': 4.558149814605713}
-03/03/2022 14:34:14 - INFO - codeparrot_training - Step 978: {'lr': 0.0002445, 'samples': 501248, 'steps': 978, 'loss/train': 5.859238147735596}
-03/03/2022 14:34:16 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/03/2022 14:34:19 - INFO - codeparrot_training - Step 979: {'lr': 0.00024475, 'samples': 501760, 'steps': 979, 'loss/train': 5.584682464599609}
-03/03/2022 14:34:22 - INFO - codeparrot_training - Step 980: {'lr': 0.000245, 'samples': 502272, 'steps': 980, 'loss/train': 4.898726463317871}
-03/03/2022 14:34:24 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/03/2022 14:34:27 - INFO - codeparrot_training - Step 981: {'lr': 0.00024525, 'samples': 502784, 'steps': 981, 'loss/train': 4.736696243286133}
-03/03/2022 14:34:30 - INFO - codeparrot_training - Step 982: {'lr': 0.0002455, 'samples': 503296, 'steps': 982, 'loss/train': 5.225622653961182}
-03/03/2022 14:34:33 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/03/2022 14:34:36 - INFO - codeparrot_training - Step 983: {'lr': 0.00024575, 'samples': 503808, 'steps': 983, 'loss/train': 5.422540664672852}
-03/03/2022 14:34:39 - INFO - codeparrot_training - Step 984: {'lr': 0.000246, 'samples': 504320, 'steps': 984, 'loss/train': 5.052621841430664}
-03/03/2022 14:34:41 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/03/2022 14:34:44 - INFO - codeparrot_training - Step 985: {'lr': 0.00024625, 'samples': 504832, 'steps': 985, 'loss/train': 4.097038269042969}
-03/03/2022 14:34:47 - INFO - codeparrot_training - Step 986: {'lr': 0.00024650000000000003, 'samples': 505344, 'steps': 986, 'loss/train': 5.570449352264404}
-03/03/2022 14:34:49 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/03/2022 14:34:52 - INFO - codeparrot_training - Step 987: {'lr': 0.00024675, 'samples': 505856, 'steps': 987, 'loss/train': 5.631117820739746}
-03/03/2022 14:34:56 - INFO - codeparrot_training - Step 988: {'lr': 0.000247, 'samples': 506368, 'steps': 988, 'loss/train': 4.260595798492432}
-03/03/2022 14:34:57 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/03/2022 14:35:01 - INFO - codeparrot_training - Step 989: {'lr': 0.00024725, 'samples': 506880, 'steps': 989, 'loss/train': 5.5409040451049805}
-03/03/2022 14:35:04 - INFO - codeparrot_training - Step 990: {'lr': 0.0002475, 'samples': 507392, 'steps': 990, 'loss/train': 5.684276580810547}
-03/03/2022 14:35:06 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/03/2022 14:35:10 - INFO - codeparrot_training - Step 991: {'lr': 0.00024775, 'samples': 507904, 'steps': 991, 'loss/train': 5.969166278839111}
-03/03/2022 14:35:13 - INFO - codeparrot_training - Step 992: {'lr': 0.000248, 'samples': 508416, 'steps': 992, 'loss/train': 4.652510166168213}
-03/03/2022 14:35:14 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/03/2022 14:35:18 - INFO - codeparrot_training - Step 993: {'lr': 0.00024825, 'samples': 508928, 'steps': 993, 'loss/train': 5.757342338562012}
-03/03/2022 14:35:22 - INFO - codeparrot_training - Step 994: {'lr': 0.0002485, 'samples': 509440, 'steps': 994, 'loss/train': 4.967216491699219}
-03/03/2022 14:35:24 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/03/2022 14:35:27 - INFO - codeparrot_training - Step 995: {'lr': 0.00024875, 'samples': 509952, 'steps': 995, 'loss/train': 6.8817057609558105}
-03/03/2022 14:35:30 - INFO - codeparrot_training - Step 996: {'lr': 0.000249, 'samples': 510464, 'steps': 996, 'loss/train': 5.365835666656494}
-03/03/2022 14:35:33 - INFO - codeparrot_training - Step 997: {'lr': 0.00024925, 'samples': 510976, 'steps': 997, 'loss/train': 5.559195041656494}
-03/03/2022 14:35:34 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/03/2022 14:35:39 - INFO - codeparrot_training - Step 998: {'lr': 0.0002495, 'samples': 511488, 'steps': 998, 'loss/train': 5.3885650634765625}
-03/03/2022 14:35:42 - INFO - codeparrot_training - Step 999: {'lr': 0.00024975, 'samples': 512000, 'steps': 999, 'loss/train': 5.635467052459717}
-03/03/2022 14:35:42 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/03/2022 14:35:47 - INFO - codeparrot_training - Step 1000: {'lr': 0.00025, 'samples': 512512, 'steps': 1000, 'loss/train': 5.574415683746338}
-03/03/2022 14:35:50 - INFO - codeparrot_training - Step 1001: {'lr': 0.00025025, 'samples': 513024, 'steps': 1001, 'loss/train': 5.000115394592285}
-03/03/2022 14:35:50 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/03/2022 14:35:56 - INFO - codeparrot_training - Step 1002: {'lr': 0.0002505, 'samples': 513536, 'steps': 1002, 'loss/train': 5.251387596130371}
-03/03/2022 14:35:59 - INFO - codeparrot_training - Step 1003: {'lr': 0.00025075, 'samples': 514048, 'steps': 1003, 'loss/train': 5.300058364868164}
-03/03/2022 14:35:59 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/03/2022 14:36:04 - INFO - codeparrot_training - Step 1004: {'lr': 0.00025100000000000003, 'samples': 514560, 'steps': 1004, 'loss/train': 5.120811462402344}
-03/03/2022 14:36:07 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/03/2022 14:36:09 - INFO - codeparrot_training - Step 1005: {'lr': 0.00025124999999999995, 'samples': 515072, 'steps': 1005, 'loss/train': 5.268819808959961}
-03/03/2022 14:36:12 - INFO - codeparrot_training - Step 1006: {'lr': 0.0002515, 'samples': 515584, 'steps': 1006, 'loss/train': 4.450544357299805}
-03/03/2022 14:36:15 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/03/2022 14:36:18 - INFO - codeparrot_training - Step 1007: {'lr': 0.00025174999999999997, 'samples': 516096, 'steps': 1007, 'loss/train': 4.952118873596191}
-03/03/2022 14:36:21 - INFO - codeparrot_training - Step 1008: {'lr': 0.000252, 'samples': 516608, 'steps': 1008, 'loss/train': 5.472934246063232}
-03/03/2022 14:36:24 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/03/2022 14:36:26 - INFO - codeparrot_training - Step 1009: {'lr': 0.00025225, 'samples': 517120, 'steps': 1009, 'loss/train': 6.064309120178223}
-03/03/2022 14:36:29 - INFO - codeparrot_training - Step 1010: {'lr': 0.0002525, 'samples': 517632, 'steps': 1010, 'loss/train': 5.658780574798584}
-03/03/2022 14:36:32 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/03/2022 14:36:34 - INFO - codeparrot_training - Step 1011: {'lr': 0.00025275, 'samples': 518144, 'steps': 1011, 'loss/train': 5.292049407958984}
-03/03/2022 14:36:38 - INFO - codeparrot_training - Step 1012: {'lr': 0.000253, 'samples': 518656, 'steps': 1012, 'loss/train': 4.9148993492126465}
-03/03/2022 14:36:40 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/03/2022 14:36:43 - INFO - codeparrot_training - Step 1013: {'lr': 0.00025325, 'samples': 519168, 'steps': 1013, 'loss/train': 5.79802942276001}
-03/03/2022 14:36:46 - INFO - codeparrot_training - Step 1014: {'lr': 0.0002535, 'samples': 519680, 'steps': 1014, 'loss/train': 4.049562454223633}
-03/03/2022 14:36:49 - INFO - codeparrot_training - Step 1015: {'lr': 0.00025374999999999996, 'samples': 520192, 'steps': 1015, 'loss/train': 2.8729851245880127}
-03/03/2022 14:36:49 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/03/2022 14:36:55 - INFO - codeparrot_training - Step 1016: {'lr': 0.000254, 'samples': 520704, 'steps': 1016, 'loss/train': 4.415850639343262}
-03/03/2022 14:36:57 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/03/2022 14:37:00 - INFO - codeparrot_training - Step 1017: {'lr': 0.00025425, 'samples': 521216, 'steps': 1017, 'loss/train': 4.908716678619385}
-03/03/2022 14:37:03 - INFO - codeparrot_training - Step 1018: {'lr': 0.0002545, 'samples': 521728, 'steps': 1018, 'loss/train': 3.306058168411255}
-03/03/2022 14:37:05 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/03/2022 14:37:08 - INFO - codeparrot_training - Step 1019: {'lr': 0.00025475, 'samples': 522240, 'steps': 1019, 'loss/train': 5.539009094238281}
-03/03/2022 14:37:11 - INFO - codeparrot_training - Step 1020: {'lr': 0.000255, 'samples': 522752, 'steps': 1020, 'loss/train': 4.003036975860596}
-03/03/2022 14:37:14 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/03/2022 14:37:16 - INFO - codeparrot_training - Step 1021: {'lr': 0.00025525, 'samples': 523264, 'steps': 1021, 'loss/train': 4.945549964904785}
-03/03/2022 14:37:20 - INFO - codeparrot_training - Step 1022: {'lr': 0.00025550000000000003, 'samples': 523776, 'steps': 1022, 'loss/train': 5.16744327545166}
-03/03/2022 14:37:22 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/03/2022 14:37:25 - INFO - codeparrot_training - Step 1023: {'lr': 0.00025575, 'samples': 524288, 'steps': 1023, 'loss/train': 4.918542861938477}
-03/03/2022 14:37:28 - INFO - codeparrot_training - Step 1024: {'lr': 0.000256, 'samples': 524800, 'steps': 1024, 'loss/train': 4.853889465332031}
-03/03/2022 14:37:30 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/03/2022 14:37:33 - INFO - codeparrot_training - Step 1025: {'lr': 0.00025624999999999997, 'samples': 525312, 'steps': 1025, 'loss/train': 4.4365997314453125}
-03/03/2022 14:37:37 - INFO - codeparrot_training - Step 1026: {'lr': 0.0002565, 'samples': 525824, 'steps': 1026, 'loss/train': 4.449159622192383}
-03/03/2022 14:37:39 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/03/2022 14:37:42 - INFO - codeparrot_training - Step 1027: {'lr': 0.00025675, 'samples': 526336, 'steps': 1027, 'loss/train': 5.204823970794678}
-03/03/2022 14:37:45 - INFO - codeparrot_training - Step 1028: {'lr': 0.000257, 'samples': 526848, 'steps': 1028, 'loss/train': 4.834066390991211}
-03/03/2022 14:37:47 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/03/2022 14:37:50 - INFO - codeparrot_training - Step 1029: {'lr': 0.00025725, 'samples': 527360, 'steps': 1029, 'loss/train': 5.412440299987793}
-03/03/2022 14:37:53 - INFO - codeparrot_training - Step 1030: {'lr': 0.0002575, 'samples': 527872, 'steps': 1030, 'loss/train': 4.39460563659668}
-03/03/2022 14:37:56 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/03/2022 14:37:59 - INFO - codeparrot_training - Step 1031: {'lr': 0.00025775, 'samples': 528384, 'steps': 1031, 'loss/train': 5.561583518981934}
-03/03/2022 14:38:02 - INFO - codeparrot_training - Step 1032: {'lr': 0.00025800000000000004, 'samples': 528896, 'steps': 1032, 'loss/train': 4.344091415405273}
-03/03/2022 14:38:04 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/03/2022 14:38:07 - INFO - codeparrot_training - Step 1033: {'lr': 0.00025824999999999996, 'samples': 529408, 'steps': 1033, 'loss/train': 5.726379871368408}
-03/03/2022 14:38:10 - INFO - codeparrot_training - Step 1034: {'lr': 0.0002585, 'samples': 529920, 'steps': 1034, 'loss/train': 5.306400299072266}
-03/03/2022 14:38:12 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/03/2022 14:38:15 - INFO - codeparrot_training - Step 1035: {'lr': 0.00025875, 'samples': 530432, 'steps': 1035, 'loss/train': 5.606037139892578}
-03/03/2022 14:38:18 - INFO - codeparrot_training - Step 1036: {'lr': 0.000259, 'samples': 530944, 'steps': 1036, 'loss/train': 6.034673690795898}
-03/03/2022 14:38:20 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/03/2022 14:38:24 - INFO - codeparrot_training - Step 1037: {'lr': 0.00025925, 'samples': 531456, 'steps': 1037, 'loss/train': 5.3619489669799805}
-03/03/2022 14:38:27 - INFO - codeparrot_training - Step 1038: {'lr': 0.0002595, 'samples': 531968, 'steps': 1038, 'loss/train': 5.350738525390625}
-03/03/2022 14:38:29 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/03/2022 14:38:32 - INFO - codeparrot_training - Step 1039: {'lr': 0.00025975, 'samples': 532480, 'steps': 1039, 'loss/train': 5.737588405609131}
-03/03/2022 14:38:35 - INFO - codeparrot_training - Step 1040: {'lr': 0.00026000000000000003, 'samples': 532992, 'steps': 1040, 'loss/train': 5.76760721206665}
-03/03/2022 14:38:37 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/03/2022 14:38:40 - INFO - codeparrot_training - Step 1041: {'lr': 0.00026025, 'samples': 533504, 'steps': 1041, 'loss/train': 4.5547614097595215}
-03/03/2022 14:38:44 - INFO - codeparrot_training - Step 1042: {'lr': 0.0002605, 'samples': 534016, 'steps': 1042, 'loss/train': 4.504413604736328}
-03/03/2022 14:38:45 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/03/2022 14:38:49 - INFO - codeparrot_training - Step 1043: {'lr': 0.00026074999999999997, 'samples': 534528, 'steps': 1043, 'loss/train': 6.240774154663086}
-03/03/2022 14:38:52 - INFO - codeparrot_training - Step 1044: {'lr': 0.000261, 'samples': 535040, 'steps': 1044, 'loss/train': 4.31958532333374}
-03/03/2022 14:38:53 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/03/2022 14:38:57 - INFO - codeparrot_training - Step 1045: {'lr': 0.00026125, 'samples': 535552, 'steps': 1045, 'loss/train': 5.091063022613525}
-03/03/2022 14:39:00 - INFO - codeparrot_training - Step 1046: {'lr': 0.0002615, 'samples': 536064, 'steps': 1046, 'loss/train': 6.172536373138428}
-03/03/2022 14:39:01 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/03/2022 14:39:06 - INFO - codeparrot_training - Step 1047: {'lr': 0.00026175, 'samples': 536576, 'steps': 1047, 'loss/train': 5.628197193145752}
-03/03/2022 14:39:09 - INFO - codeparrot_training - Step 1048: {'lr': 0.000262, 'samples': 537088, 'steps': 1048, 'loss/train': 5.0062174797058105}
-03/03/2022 14:39:10 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/03/2022 14:39:14 - INFO - codeparrot_training - Step 1049: {'lr': 0.00026225, 'samples': 537600, 'steps': 1049, 'loss/train': 4.725820541381836}
-03/03/2022 14:39:17 - INFO - codeparrot_training - Step 1050: {'lr': 0.00026250000000000004, 'samples': 538112, 'steps': 1050, 'loss/train': 4.617496013641357}
-03/03/2022 14:39:18 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/03/2022 14:39:22 - INFO - codeparrot_training - Step 1051: {'lr': 0.00026274999999999996, 'samples': 538624, 'steps': 1051, 'loss/train': 4.570369720458984}
-03/03/2022 14:39:26 - INFO - codeparrot_training - Step 1052: {'lr': 0.000263, 'samples': 539136, 'steps': 1052, 'loss/train': 4.43674898147583}
-03/03/2022 14:39:27 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/03/2022 14:39:31 - INFO - codeparrot_training - Step 1053: {'lr': 0.00026325, 'samples': 539648, 'steps': 1053, 'loss/train': 4.584609508514404}
-03/03/2022 14:39:34 - INFO - codeparrot_training - Step 1054: {'lr': 0.0002635, 'samples': 540160, 'steps': 1054, 'loss/train': 5.5938215255737305}
-03/03/2022 14:39:35 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/03/2022 14:39:40 - INFO - codeparrot_training - Step 1055: {'lr': 0.00026375, 'samples': 540672, 'steps': 1055, 'loss/train': 5.205827236175537}
-03/03/2022 14:39:43 - INFO - codeparrot_training - Step 1056: {'lr': 0.000264, 'samples': 541184, 'steps': 1056, 'loss/train': 4.771644592285156}
-03/03/2022 14:39:44 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/03/2022 14:39:48 - INFO - codeparrot_training - Step 1057: {'lr': 0.00026425, 'samples': 541696, 'steps': 1057, 'loss/train': 5.346999168395996}
-03/03/2022 14:39:51 - INFO - codeparrot_training - Step 1058: {'lr': 0.00026450000000000003, 'samples': 542208, 'steps': 1058, 'loss/train': 4.526518821716309}
-03/03/2022 14:39:52 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/03/2022 14:39:57 - INFO - codeparrot_training - Step 1059: {'lr': 0.00026475, 'samples': 542720, 'steps': 1059, 'loss/train': 4.452726364135742}
-03/03/2022 14:40:00 - INFO - codeparrot_training - Step 1060: {'lr': 0.00026500000000000004, 'samples': 543232, 'steps': 1060, 'loss/train': 4.657252788543701}
-03/03/2022 14:40:00 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/03/2022 14:40:05 - INFO - codeparrot_training - Step 1061: {'lr': 0.00026524999999999997, 'samples': 543744, 'steps': 1061, 'loss/train': 4.880711555480957}
-03/03/2022 14:40:08 - INFO - codeparrot_training - Step 1062: {'lr': 0.0002655, 'samples': 544256, 'steps': 1062, 'loss/train': 4.187632083892822}
-03/03/2022 14:40:09 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/03/2022 14:40:13 - INFO - codeparrot_training - Step 1063: {'lr': 0.00026575, 'samples': 544768, 'steps': 1063, 'loss/train': 4.795836448669434}
-03/03/2022 14:40:17 - INFO - codeparrot_training - Step 1064: {'lr': 0.000266, 'samples': 545280, 'steps': 1064, 'loss/train': 5.463798999786377}
-03/03/2022 14:40:17 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/03/2022 14:40:22 - INFO - codeparrot_training - Step 1065: {'lr': 0.00026625, 'samples': 545792, 'steps': 1065, 'loss/train': 4.310492038726807}
-03/03/2022 14:40:25 - INFO - codeparrot_training - Step 1066: {'lr': 0.0002665, 'samples': 546304, 'steps': 1066, 'loss/train': 5.243485927581787}
-03/03/2022 14:40:25 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/03/2022 14:40:30 - INFO - codeparrot_training - Step 1067: {'lr': 0.00026675, 'samples': 546816, 'steps': 1067, 'loss/train': 4.350306034088135}
-03/03/2022 14:40:34 - INFO - codeparrot_training - Step 1068: {'lr': 0.00026700000000000004, 'samples': 547328, 'steps': 1068, 'loss/train': 4.03434944152832}
-03/03/2022 14:40:34 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/03/2022 14:40:39 - INFO - codeparrot_training - Step 1069: {'lr': 0.00026725, 'samples': 547840, 'steps': 1069, 'loss/train': 1.940299391746521}
-03/03/2022 14:40:42 - INFO - codeparrot_training - Step 1070: {'lr': 0.0002675, 'samples': 548352, 'steps': 1070, 'loss/train': 6.076417922973633}
-03/03/2022 14:40:42 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/03/2022 14:40:47 - INFO - codeparrot_training - Step 1071: {'lr': 0.00026775, 'samples': 548864, 'steps': 1071, 'loss/train': 6.043127059936523}
-03/03/2022 14:40:50 - INFO - codeparrot_training - Step 1072: {'lr': 0.000268, 'samples': 549376, 'steps': 1072, 'loss/train': 4.990219593048096}
-03/03/2022 14:40:50 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/03/2022 14:40:56 - INFO - codeparrot_training - Step 1073: {'lr': 0.00026825, 'samples': 549888, 'steps': 1073, 'loss/train': 4.431066513061523}
-03/03/2022 14:40:58 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/03/2022 14:41:01 - INFO - codeparrot_training - Step 1074: {'lr': 0.0002685, 'samples': 550400, 'steps': 1074, 'loss/train': 5.25891637802124}
-03/03/2022 14:41:04 - INFO - codeparrot_training - Step 1075: {'lr': 0.00026875, 'samples': 550912, 'steps': 1075, 'loss/train': 5.475607395172119}
-03/03/2022 14:41:07 - INFO - codeparrot_training - Step 1076: {'lr': 0.00026900000000000003, 'samples': 551424, 'steps': 1076, 'loss/train': 3.9055325984954834}
-03/03/2022 14:41:07 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/03/2022 14:41:12 - INFO - codeparrot_training - Step 1077: {'lr': 0.00026925, 'samples': 551936, 'steps': 1077, 'loss/train': 4.2556915283203125}
-03/03/2022 14:41:16 - INFO - codeparrot_training - Step 1078: {'lr': 0.00026950000000000005, 'samples': 552448, 'steps': 1078, 'loss/train': 5.633589744567871}
-03/03/2022 14:41:16 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/03/2022 14:41:21 - INFO - codeparrot_training - Step 1079: {'lr': 0.00026974999999999997, 'samples': 552960, 'steps': 1079, 'loss/train': 4.919765949249268}
-03/03/2022 14:41:24 - INFO - codeparrot_training - Step 1080: {'lr': 0.00027, 'samples': 553472, 'steps': 1080, 'loss/train': 4.847507953643799}
-03/03/2022 14:41:24 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/03/2022 14:41:29 - INFO - codeparrot_training - Step 1081: {'lr': 0.00027025, 'samples': 553984, 'steps': 1081, 'loss/train': 5.138010025024414}
-03/03/2022 14:41:32 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/03/2022 14:41:35 - INFO - codeparrot_training - Step 1082: {'lr': 0.0002705, 'samples': 554496, 'steps': 1082, 'loss/train': 4.878818035125732}
-03/03/2022 14:41:38 - INFO - codeparrot_training - Step 1083: {'lr': 0.00027075, 'samples': 555008, 'steps': 1083, 'loss/train': 4.895986080169678}
-03/03/2022 14:41:41 - INFO - codeparrot_training - Step 1084: {'lr': 0.00027100000000000003, 'samples': 555520, 'steps': 1084, 'loss/train': 5.578668594360352}
-03/03/2022 14:41:41 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/03/2022 14:41:46 - INFO - codeparrot_training - Step 1085: {'lr': 0.00027125, 'samples': 556032, 'steps': 1085, 'loss/train': 4.8936004638671875}
-03/03/2022 14:41:49 - INFO - codeparrot_training - Step 1086: {'lr': 0.00027150000000000004, 'samples': 556544, 'steps': 1086, 'loss/train': 5.960999011993408}
-03/03/2022 14:41:49 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/03/2022 14:41:55 - INFO - codeparrot_training - Step 1087: {'lr': 0.00027175, 'samples': 557056, 'steps': 1087, 'loss/train': 5.246800899505615}
-03/03/2022 14:41:58 - INFO - codeparrot_training - Step 1088: {'lr': 0.00027200000000000005, 'samples': 557568, 'steps': 1088, 'loss/train': 5.126637935638428}
-03/03/2022 14:41:59 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/03/2022 14:42:03 - INFO - codeparrot_training - Step 1089: {'lr': 0.00027225, 'samples': 558080, 'steps': 1089, 'loss/train': 4.347425937652588}
-03/03/2022 14:42:07 - INFO - codeparrot_training - Step 1090: {'lr': 0.0002725, 'samples': 558592, 'steps': 1090, 'loss/train': 5.3398942947387695}
-03/03/2022 14:42:07 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/03/2022 14:42:12 - INFO - codeparrot_training - Step 1091: {'lr': 0.00027275, 'samples': 559104, 'steps': 1091, 'loss/train': 5.132818222045898}
-03/03/2022 14:42:15 - INFO - codeparrot_training - Step 1092: {'lr': 0.000273, 'samples': 559616, 'steps': 1092, 'loss/train': 4.986759662628174}
-03/03/2022 14:42:15 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/03/2022 14:42:20 - INFO - codeparrot_training - Step 1093: {'lr': 0.00027325, 'samples': 560128, 'steps': 1093, 'loss/train': 4.198845386505127}
-03/03/2022 14:42:23 - INFO - codeparrot_training - Step 1094: {'lr': 0.00027350000000000003, 'samples': 560640, 'steps': 1094, 'loss/train': 5.353718280792236}
-03/03/2022 14:42:24 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/03/2022 14:42:29 - INFO - codeparrot_training - Step 1095: {'lr': 0.00027375, 'samples': 561152, 'steps': 1095, 'loss/train': 5.235002517700195}
-03/03/2022 14:42:32 - INFO - codeparrot_training - Step 1096: {'lr': 0.00027400000000000005, 'samples': 561664, 'steps': 1096, 'loss/train': 3.0480704307556152}
-03/03/2022 14:42:32 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/03/2022 14:42:37 - INFO - codeparrot_training - Step 1097: {'lr': 0.00027425, 'samples': 562176, 'steps': 1097, 'loss/train': 4.792338848114014}
-03/03/2022 14:42:40 - INFO - codeparrot_training - Step 1098: {'lr': 0.0002745, 'samples': 562688, 'steps': 1098, 'loss/train': 5.226000785827637}
-03/03/2022 14:42:40 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/03/2022 14:42:45 - INFO - codeparrot_training - Step 1099: {'lr': 0.00027475, 'samples': 563200, 'steps': 1099, 'loss/train': 4.9972100257873535}
-03/03/2022 14:42:49 - INFO - codeparrot_training - Step 1100: {'lr': 0.000275, 'samples': 563712, 'steps': 1100, 'loss/train': 5.435189247131348}
-03/03/2022 14:42:49 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/03/2022 14:42:54 - INFO - codeparrot_training - Step 1101: {'lr': 0.00027525, 'samples': 564224, 'steps': 1101, 'loss/train': 4.584694862365723}
-03/03/2022 14:42:57 - INFO - codeparrot_training - Step 1102: {'lr': 0.00027550000000000003, 'samples': 564736, 'steps': 1102, 'loss/train': 4.522334098815918}
-03/03/2022 14:42:57 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/03/2022 14:43:02 - INFO - codeparrot_training - Step 1103: {'lr': 0.00027575, 'samples': 565248, 'steps': 1103, 'loss/train': 5.064010143280029}
-03/03/2022 14:43:05 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/03/2022 14:43:08 - INFO - codeparrot_training - Step 1104: {'lr': 0.00027600000000000004, 'samples': 565760, 'steps': 1104, 'loss/train': 5.038564682006836}
-03/03/2022 14:43:11 - INFO - codeparrot_training - Step 1105: {'lr': 0.00027625, 'samples': 566272, 'steps': 1105, 'loss/train': 4.567838668823242}
-03/03/2022 14:43:13 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/03/2022 14:43:16 - INFO - codeparrot_training - Step 1106: {'lr': 0.00027650000000000005, 'samples': 566784, 'steps': 1106, 'loss/train': 4.308528423309326}
-03/03/2022 14:43:19 - INFO - codeparrot_training - Step 1107: {'lr': 0.00027675, 'samples': 567296, 'steps': 1107, 'loss/train': 5.4389543533325195}
-03/03/2022 14:43:22 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/03/2022 14:43:24 - INFO - codeparrot_training - Step 1108: {'lr': 0.000277, 'samples': 567808, 'steps': 1108, 'loss/train': 4.216660022735596}
-03/03/2022 14:43:27 - INFO - codeparrot_training - Step 1109: {'lr': 0.00027725, 'samples': 568320, 'steps': 1109, 'loss/train': 3.7490479946136475}
-03/03/2022 14:43:30 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/03/2022 14:43:33 - INFO - codeparrot_training - Step 1110: {'lr': 0.0002775, 'samples': 568832, 'steps': 1110, 'loss/train': 6.123933792114258}
-03/03/2022 14:43:36 - INFO - codeparrot_training - Step 1111: {'lr': 0.00027775, 'samples': 569344, 'steps': 1111, 'loss/train': 5.457062244415283}
-03/03/2022 14:43:38 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/03/2022 14:43:41 - INFO - codeparrot_training - Step 1112: {'lr': 0.00027800000000000004, 'samples': 569856, 'steps': 1112, 'loss/train': 6.0718607902526855}
-03/03/2022 14:43:44 - INFO - codeparrot_training - Step 1113: {'lr': 0.00027825, 'samples': 570368, 'steps': 1113, 'loss/train': 6.278087139129639}
-03/03/2022 14:43:46 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/03/2022 14:43:49 - INFO - codeparrot_training - Step 1114: {'lr': 0.00027850000000000005, 'samples': 570880, 'steps': 1114, 'loss/train': 4.37136697769165}
-03/03/2022 14:43:53 - INFO - codeparrot_training - Step 1115: {'lr': 0.00027875, 'samples': 571392, 'steps': 1115, 'loss/train': 4.095114707946777}
-03/03/2022 14:43:54 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/03/2022 14:43:58 - INFO - codeparrot_training - Step 1116: {'lr': 0.000279, 'samples': 571904, 'steps': 1116, 'loss/train': 4.286388874053955}
-03/03/2022 14:44:01 - INFO - codeparrot_training - Step 1117: {'lr': 0.00027925, 'samples': 572416, 'steps': 1117, 'loss/train': 5.543516159057617}
-03/03/2022 14:44:02 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/03/2022 14:44:06 - INFO - codeparrot_training - Step 1118: {'lr': 0.0002795, 'samples': 572928, 'steps': 1118, 'loss/train': 6.064958095550537}
-03/03/2022 14:44:09 - INFO - codeparrot_training - Step 1119: {'lr': 0.00027975, 'samples': 573440, 'steps': 1119, 'loss/train': 5.2345452308654785}
-03/03/2022 14:44:11 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/03/2022 14:44:15 - INFO - codeparrot_training - Step 1120: {'lr': 0.00028000000000000003, 'samples': 573952, 'steps': 1120, 'loss/train': 4.6932501792907715}
-03/03/2022 14:44:18 - INFO - codeparrot_training - Step 1121: {'lr': 0.00028025, 'samples': 574464, 'steps': 1121, 'loss/train': 4.8953070640563965}
-03/03/2022 14:44:19 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 14:44:23 - INFO - codeparrot_training - Step 1122: {'lr': 0.00028050000000000004, 'samples': 574976, 'steps': 1122, 'loss/train': 5.5702924728393555}
-03/03/2022 14:44:26 - INFO - codeparrot_training - Step 1123: {'lr': 0.00028075, 'samples': 575488, 'steps': 1123, 'loss/train': 5.01413106918335}
-03/03/2022 14:44:27 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/03/2022 14:44:32 - INFO - codeparrot_training - Step 1124: {'lr': 0.00028100000000000005, 'samples': 576000, 'steps': 1124, 'loss/train': 4.616030216217041}
-03/03/2022 14:44:35 - INFO - codeparrot_training - Step 1125: {'lr': 0.00028125000000000003, 'samples': 576512, 'steps': 1125, 'loss/train': 4.766707420349121}
-03/03/2022 14:44:36 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/03/2022 14:44:40 - INFO - codeparrot_training - Step 1126: {'lr': 0.00028149999999999996, 'samples': 577024, 'steps': 1126, 'loss/train': 4.632814884185791}
-03/03/2022 14:44:43 - INFO - codeparrot_training - Step 1127: {'lr': 0.00028175, 'samples': 577536, 'steps': 1127, 'loss/train': 4.65377140045166}
-03/03/2022 14:44:44 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/03/2022 14:44:49 - INFO - codeparrot_training - Step 1128: {'lr': 0.00028199999999999997, 'samples': 578048, 'steps': 1128, 'loss/train': 4.634227275848389}
-03/03/2022 14:44:52 - INFO - codeparrot_training - Step 1129: {'lr': 0.00028225, 'samples': 578560, 'steps': 1129, 'loss/train': 5.282841682434082}
-03/03/2022 14:44:52 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/03/2022 14:44:57 - INFO - codeparrot_training - Step 1130: {'lr': 0.0002825, 'samples': 579072, 'steps': 1130, 'loss/train': 5.040492534637451}
-03/03/2022 14:45:00 - INFO - codeparrot_training - Step 1131: {'lr': 0.00028275, 'samples': 579584, 'steps': 1131, 'loss/train': 5.30776834487915}
-03/03/2022 14:45:00 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/03/2022 14:45:05 - INFO - codeparrot_training - Step 1132: {'lr': 0.000283, 'samples': 580096, 'steps': 1132, 'loss/train': 5.669086933135986}
-03/03/2022 14:45:09 - INFO - codeparrot_training - Step 1133: {'lr': 0.00028325000000000003, 'samples': 580608, 'steps': 1133, 'loss/train': 4.616725444793701}
-03/03/2022 14:45:09 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/03/2022 14:45:14 - INFO - codeparrot_training - Step 1134: {'lr': 0.0002835, 'samples': 581120, 'steps': 1134, 'loss/train': 4.028615951538086}
-03/03/2022 14:45:17 - INFO - codeparrot_training - Step 1135: {'lr': 0.00028375, 'samples': 581632, 'steps': 1135, 'loss/train': 4.0377726554870605}
-03/03/2022 14:45:17 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/03/2022 14:45:22 - INFO - codeparrot_training - Step 1136: {'lr': 0.00028399999999999996, 'samples': 582144, 'steps': 1136, 'loss/train': 5.683346271514893}
-03/03/2022 14:45:25 - INFO - codeparrot_training - Step 1137: {'lr': 0.00028425, 'samples': 582656, 'steps': 1137, 'loss/train': 6.318787574768066}
-03/03/2022 14:45:25 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/03/2022 14:45:31 - INFO - codeparrot_training - Step 1138: {'lr': 0.0002845, 'samples': 583168, 'steps': 1138, 'loss/train': 2.4034740924835205}
-03/03/2022 14:45:33 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/03/2022 14:45:36 - INFO - codeparrot_training - Step 1139: {'lr': 0.00028475, 'samples': 583680, 'steps': 1139, 'loss/train': 5.280616283416748}
-03/03/2022 14:45:39 - INFO - codeparrot_training - Step 1140: {'lr': 0.000285, 'samples': 584192, 'steps': 1140, 'loss/train': 7.985814571380615}
-03/03/2022 14:45:42 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/03/2022 14:45:44 - INFO - codeparrot_training - Step 1141: {'lr': 0.00028525, 'samples': 584704, 'steps': 1141, 'loss/train': 3.896122455596924}
-03/03/2022 14:45:48 - INFO - codeparrot_training - Step 1142: {'lr': 0.0002855, 'samples': 585216, 'steps': 1142, 'loss/train': 5.168213367462158}
-03/03/2022 14:45:50 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/03/2022 14:45:53 - INFO - codeparrot_training - Step 1143: {'lr': 0.00028575000000000003, 'samples': 585728, 'steps': 1143, 'loss/train': 5.325235843658447}
-03/03/2022 14:45:56 - INFO - codeparrot_training - Step 1144: {'lr': 0.00028599999999999996, 'samples': 586240, 'steps': 1144, 'loss/train': 5.025601863861084}
-03/03/2022 14:45:59 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/03/2022 14:46:01 - INFO - codeparrot_training - Step 1145: {'lr': 0.00028625, 'samples': 586752, 'steps': 1145, 'loss/train': 5.752750873565674}
-03/03/2022 14:46:04 - INFO - codeparrot_training - Step 1146: {'lr': 0.00028649999999999997, 'samples': 587264, 'steps': 1146, 'loss/train': 5.020471572875977}
-03/03/2022 14:46:07 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/03/2022 14:46:10 - INFO - codeparrot_training - Step 1147: {'lr': 0.00028675, 'samples': 587776, 'steps': 1147, 'loss/train': 4.9661946296691895}
-03/03/2022 14:46:13 - INFO - codeparrot_training - Step 1148: {'lr': 0.000287, 'samples': 588288, 'steps': 1148, 'loss/train': 5.066573619842529}
-03/03/2022 14:46:16 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/03/2022 14:46:19 - INFO - codeparrot_training - Step 1149: {'lr': 0.00028725, 'samples': 588800, 'steps': 1149, 'loss/train': 4.306407451629639}
-03/03/2022 14:46:22 - INFO - codeparrot_training - Step 1150: {'lr': 0.0002875, 'samples': 589312, 'steps': 1150, 'loss/train': 4.3311920166015625}
-03/03/2022 14:46:25 - INFO - codeparrot_training - Step 1151: {'lr': 0.00028775000000000003, 'samples': 589824, 'steps': 1151, 'loss/train': 2.07806396484375}
-03/03/2022 14:46:25 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/03/2022 14:46:30 - INFO - codeparrot_training - Step 1152: {'lr': 0.000288, 'samples': 590336, 'steps': 1152, 'loss/train': 4.967807769775391}
-03/03/2022 14:46:33 - INFO - codeparrot_training - Step 1153: {'lr': 0.00028825, 'samples': 590848, 'steps': 1153, 'loss/train': 4.149472236633301}
-03/03/2022 14:46:33 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/03/2022 14:46:39 - INFO - codeparrot_training - Step 1154: {'lr': 0.00028849999999999997, 'samples': 591360, 'steps': 1154, 'loss/train': 4.931750297546387}
-03/03/2022 14:46:42 - INFO - codeparrot_training - Step 1155: {'lr': 0.00028875, 'samples': 591872, 'steps': 1155, 'loss/train': 4.433856010437012}
-03/03/2022 14:46:42 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/03/2022 14:46:47 - INFO - codeparrot_training - Step 1156: {'lr': 0.000289, 'samples': 592384, 'steps': 1156, 'loss/train': 5.270572662353516}
-03/03/2022 14:46:51 - INFO - codeparrot_training - Step 1157: {'lr': 0.00028925, 'samples': 592896, 'steps': 1157, 'loss/train': 4.90167760848999}
-03/03/2022 14:46:51 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/03/2022 14:46:56 - INFO - codeparrot_training - Step 1158: {'lr': 0.0002895, 'samples': 593408, 'steps': 1158, 'loss/train': 4.335346221923828}
-03/03/2022 14:46:59 - INFO - codeparrot_training - Step 1159: {'lr': 0.00028975, 'samples': 593920, 'steps': 1159, 'loss/train': 4.507898330688477}
-03/03/2022 14:46:59 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/03/2022 14:47:04 - INFO - codeparrot_training - Step 1160: {'lr': 0.00029, 'samples': 594432, 'steps': 1160, 'loss/train': 5.678080081939697}
-03/03/2022 14:47:08 - INFO - codeparrot_training - Step 1161: {'lr': 0.00029025000000000003, 'samples': 594944, 'steps': 1161, 'loss/train': 4.063498497009277}
-03/03/2022 14:47:09 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/03/2022 14:47:13 - INFO - codeparrot_training - Step 1162: {'lr': 0.00029049999999999996, 'samples': 595456, 'steps': 1162, 'loss/train': 5.084910869598389}
-03/03/2022 14:47:16 - INFO - codeparrot_training - Step 1163: {'lr': 0.00029075, 'samples': 595968, 'steps': 1163, 'loss/train': 4.5967230796813965}
-03/03/2022 14:47:17 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/03/2022 14:47:21 - INFO - codeparrot_training - Step 1164: {'lr': 0.00029099999999999997, 'samples': 596480, 'steps': 1164, 'loss/train': 1.8424994945526123}
-03/03/2022 14:47:25 - INFO - codeparrot_training - Step 1165: {'lr': 0.00029125, 'samples': 596992, 'steps': 1165, 'loss/train': 4.506917953491211}
-03/03/2022 14:47:25 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/03/2022 14:47:30 - INFO - codeparrot_training - Step 1166: {'lr': 0.0002915, 'samples': 597504, 'steps': 1166, 'loss/train': 5.436644554138184}
-03/03/2022 14:47:33 - INFO - codeparrot_training - Step 1167: {'lr': 0.00029175, 'samples': 598016, 'steps': 1167, 'loss/train': 4.689492225646973}
-03/03/2022 14:47:34 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/03/2022 14:47:38 - INFO - codeparrot_training - Step 1168: {'lr': 0.000292, 'samples': 598528, 'steps': 1168, 'loss/train': 4.775059223175049}
-03/03/2022 14:47:41 - INFO - codeparrot_training - Step 1169: {'lr': 0.00029225000000000003, 'samples': 599040, 'steps': 1169, 'loss/train': 3.9990384578704834}
-03/03/2022 14:47:42 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/03/2022 14:47:47 - INFO - codeparrot_training - Step 1170: {'lr': 0.0002925, 'samples': 599552, 'steps': 1170, 'loss/train': 5.478631973266602}
-03/03/2022 14:47:50 - INFO - codeparrot_training - Step 1171: {'lr': 0.00029275000000000004, 'samples': 600064, 'steps': 1171, 'loss/train': 4.522140026092529}
-03/03/2022 14:47:51 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/03/2022 14:47:55 - INFO - codeparrot_training - Step 1172: {'lr': 0.00029299999999999997, 'samples': 600576, 'steps': 1172, 'loss/train': 4.634247779846191}
-03/03/2022 14:47:58 - INFO - codeparrot_training - Step 1173: {'lr': 0.00029325, 'samples': 601088, 'steps': 1173, 'loss/train': 4.749699592590332}
-03/03/2022 14:47:59 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/03/2022 14:48:03 - INFO - codeparrot_training - Step 1174: {'lr': 0.0002935, 'samples': 601600, 'steps': 1174, 'loss/train': 5.154363632202148}
-03/03/2022 14:48:07 - INFO - codeparrot_training - Step 1175: {'lr': 0.00029375, 'samples': 602112, 'steps': 1175, 'loss/train': 5.280133247375488}
-03/03/2022 14:48:07 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/03/2022 14:48:12 - INFO - codeparrot_training - Step 1176: {'lr': 0.000294, 'samples': 602624, 'steps': 1176, 'loss/train': 4.3173604011535645}
-03/03/2022 14:48:15 - INFO - codeparrot_training - Step 1177: {'lr': 0.00029425, 'samples': 603136, 'steps': 1177, 'loss/train': 5.089110851287842}
-03/03/2022 14:48:15 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/03/2022 14:48:20 - INFO - codeparrot_training - Step 1178: {'lr': 0.0002945, 'samples': 603648, 'steps': 1178, 'loss/train': 5.304769992828369}
-03/03/2022 14:48:23 - INFO - codeparrot_training - Step 1179: {'lr': 0.00029475000000000004, 'samples': 604160, 'steps': 1179, 'loss/train': 4.326340198516846}
-03/03/2022 14:48:23 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/03/2022 14:48:29 - INFO - codeparrot_training - Step 1180: {'lr': 0.000295, 'samples': 604672, 'steps': 1180, 'loss/train': 5.235725402832031}
-03/03/2022 14:48:32 - INFO - codeparrot_training - Step 1181: {'lr': 0.00029525, 'samples': 605184, 'steps': 1181, 'loss/train': 4.663435459136963}
-03/03/2022 14:48:32 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/03/2022 14:48:37 - INFO - codeparrot_training - Step 1182: {'lr': 0.00029549999999999997, 'samples': 605696, 'steps': 1182, 'loss/train': 4.434954643249512}
-03/03/2022 14:48:40 - INFO - codeparrot_training - Step 1183: {'lr': 0.00029575, 'samples': 606208, 'steps': 1183, 'loss/train': 4.7711710929870605}
-03/03/2022 14:48:40 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/03/2022 14:48:45 - INFO - codeparrot_training - Step 1184: {'lr': 0.000296, 'samples': 606720, 'steps': 1184, 'loss/train': 5.68754243850708}
-03/03/2022 14:48:49 - INFO - codeparrot_training - Step 1185: {'lr': 0.00029625, 'samples': 607232, 'steps': 1185, 'loss/train': 4.661207675933838}
-03/03/2022 14:48:49 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/03/2022 14:48:54 - INFO - codeparrot_training - Step 1186: {'lr': 0.0002965, 'samples': 607744, 'steps': 1186, 'loss/train': 5.469995021820068}
-03/03/2022 14:48:57 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/03/2022 14:48:59 - INFO - codeparrot_training - Step 1187: {'lr': 0.00029675000000000003, 'samples': 608256, 'steps': 1187, 'loss/train': 5.257544994354248}
-03/03/2022 14:49:02 - INFO - codeparrot_training - Step 1188: {'lr': 0.000297, 'samples': 608768, 'steps': 1188, 'loss/train': 3.3908140659332275}
-03/03/2022 14:49:05 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/03/2022 14:49:08 - INFO - codeparrot_training - Step 1189: {'lr': 0.00029725000000000004, 'samples': 609280, 'steps': 1189, 'loss/train': 5.660294055938721}
-03/03/2022 14:49:11 - INFO - codeparrot_training - Step 1190: {'lr': 0.00029749999999999997, 'samples': 609792, 'steps': 1190, 'loss/train': 4.143644332885742}
-03/03/2022 14:49:13 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/03/2022 14:49:16 - INFO - codeparrot_training - Step 1191: {'lr': 0.00029775, 'samples': 610304, 'steps': 1191, 'loss/train': 4.107789039611816}
-03/03/2022 14:49:19 - INFO - codeparrot_training - Step 1192: {'lr': 0.000298, 'samples': 610816, 'steps': 1192, 'loss/train': 3.876453399658203}
-03/03/2022 14:49:22 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/03/2022 14:49:25 - INFO - codeparrot_training - Step 1193: {'lr': 0.00029825, 'samples': 611328, 'steps': 1193, 'loss/train': 4.736563205718994}
-03/03/2022 14:49:28 - INFO - codeparrot_training - Step 1194: {'lr': 0.0002985, 'samples': 611840, 'steps': 1194, 'loss/train': 4.076013565063477}
-03/03/2022 14:49:31 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/03/2022 14:49:33 - INFO - codeparrot_training - Step 1195: {'lr': 0.00029875, 'samples': 612352, 'steps': 1195, 'loss/train': 5.8624067306518555}
-03/03/2022 14:49:36 - INFO - codeparrot_training - Step 1196: {'lr': 0.000299, 'samples': 612864, 'steps': 1196, 'loss/train': 5.197993278503418}
-03/03/2022 14:49:39 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/03/2022 14:49:41 - INFO - codeparrot_training - Step 1197: {'lr': 0.00029925000000000004, 'samples': 613376, 'steps': 1197, 'loss/train': 3.7101566791534424}
-03/03/2022 14:49:45 - INFO - codeparrot_training - Step 1198: {'lr': 0.0002995, 'samples': 613888, 'steps': 1198, 'loss/train': 4.696809768676758}
-03/03/2022 14:49:47 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/03/2022 14:49:50 - INFO - codeparrot_training - Step 1199: {'lr': 0.00029975000000000005, 'samples': 614400, 'steps': 1199, 'loss/train': 4.844315528869629}
-03/03/2022 14:49:53 - INFO - codeparrot_training - Step 1200: {'lr': 0.0003, 'samples': 614912, 'steps': 1200, 'loss/train': 4.472458839416504}
-03/03/2022 14:49:56 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/03/2022 14:49:58 - INFO - codeparrot_training - Step 1201: {'lr': 0.00030025, 'samples': 615424, 'steps': 1201, 'loss/train': 3.9490694999694824}
-03/03/2022 14:50:01 - INFO - codeparrot_training - Step 1202: {'lr': 0.0003005, 'samples': 615936, 'steps': 1202, 'loss/train': 3.626290798187256}
-03/03/2022 14:50:04 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/03/2022 14:50:07 - INFO - codeparrot_training - Step 1203: {'lr': 0.00030075, 'samples': 616448, 'steps': 1203, 'loss/train': 4.3813018798828125}
-03/03/2022 14:50:10 - INFO - codeparrot_training - Step 1204: {'lr': 0.000301, 'samples': 616960, 'steps': 1204, 'loss/train': 4.078187942504883}
-03/03/2022 14:50:12 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/03/2022 14:50:15 - INFO - codeparrot_training - Step 1205: {'lr': 0.00030125000000000003, 'samples': 617472, 'steps': 1205, 'loss/train': 4.892630577087402}
-03/03/2022 14:50:18 - INFO - codeparrot_training - Step 1206: {'lr': 0.0003015, 'samples': 617984, 'steps': 1206, 'loss/train': 4.29644775390625}
-03/03/2022 14:50:21 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/03/2022 14:50:23 - INFO - codeparrot_training - Step 1207: {'lr': 0.00030175000000000004, 'samples': 618496, 'steps': 1207, 'loss/train': 4.6893815994262695}
-03/03/2022 14:50:27 - INFO - codeparrot_training - Step 1208: {'lr': 0.000302, 'samples': 619008, 'steps': 1208, 'loss/train': 1.2830274105072021}
-03/03/2022 14:50:29 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/03/2022 14:50:32 - INFO - codeparrot_training - Step 1209: {'lr': 0.00030225, 'samples': 619520, 'steps': 1209, 'loss/train': 4.533934593200684}
-03/03/2022 14:50:35 - INFO - codeparrot_training - Step 1210: {'lr': 0.0003025, 'samples': 620032, 'steps': 1210, 'loss/train': 4.98966121673584}
-03/03/2022 14:50:38 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/03/2022 14:50:40 - INFO - codeparrot_training - Step 1211: {'lr': 0.00030275, 'samples': 620544, 'steps': 1211, 'loss/train': 4.9488630294799805}
-03/03/2022 14:50:44 - INFO - codeparrot_training - Step 1212: {'lr': 0.000303, 'samples': 621056, 'steps': 1212, 'loss/train': 4.870970249176025}
-03/03/2022 14:50:46 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/03/2022 14:50:49 - INFO - codeparrot_training - Step 1213: {'lr': 0.00030325, 'samples': 621568, 'steps': 1213, 'loss/train': 3.9525699615478516}
-03/03/2022 14:50:52 - INFO - codeparrot_training - Step 1214: {'lr': 0.0003035, 'samples': 622080, 'steps': 1214, 'loss/train': 3.038872003555298}
-03/03/2022 14:50:57 - INFO - codeparrot_training - Step 1215: {'lr': 0.00030375000000000004, 'samples': 622592, 'steps': 1215, 'loss/train': 4.5737481117248535}
-03/03/2022 14:51:00 - INFO - codeparrot_training - Step 1216: {'lr': 0.000304, 'samples': 623104, 'steps': 1216, 'loss/train': 4.942699432373047}
-03/03/2022 14:51:02 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/03/2022 14:51:06 - INFO - codeparrot_training - Step 1217: {'lr': 0.00030425000000000005, 'samples': 623616, 'steps': 1217, 'loss/train': 3.656524181365967}
-03/03/2022 14:51:09 - INFO - codeparrot_training - Step 1218: {'lr': 0.0003045, 'samples': 624128, 'steps': 1218, 'loss/train': 4.410141468048096}
-03/03/2022 14:51:11 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/03/2022 14:51:14 - INFO - codeparrot_training - Step 1219: {'lr': 0.00030475, 'samples': 624640, 'steps': 1219, 'loss/train': 4.2339558601379395}
-03/03/2022 14:51:17 - INFO - codeparrot_training - Step 1220: {'lr': 0.000305, 'samples': 625152, 'steps': 1220, 'loss/train': 4.279458999633789}
-03/03/2022 14:51:19 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/03/2022 14:51:22 - INFO - codeparrot_training - Step 1221: {'lr': 0.00030525, 'samples': 625664, 'steps': 1221, 'loss/train': 4.509191513061523}
-03/03/2022 14:51:26 - INFO - codeparrot_training - Step 1222: {'lr': 0.0003055, 'samples': 626176, 'steps': 1222, 'loss/train': 3.9416255950927734}
-03/03/2022 14:51:27 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/03/2022 14:51:31 - INFO - codeparrot_training - Step 1223: {'lr': 0.00030575000000000003, 'samples': 626688, 'steps': 1223, 'loss/train': 4.671177387237549}
-03/03/2022 14:51:34 - INFO - codeparrot_training - Step 1224: {'lr': 0.000306, 'samples': 627200, 'steps': 1224, 'loss/train': 5.080960273742676}
-03/03/2022 14:51:36 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/03/2022 14:51:39 - INFO - codeparrot_training - Step 1225: {'lr': 0.00030625000000000004, 'samples': 627712, 'steps': 1225, 'loss/train': 4.823641777038574}
-03/03/2022 14:51:42 - INFO - codeparrot_training - Step 1226: {'lr': 0.0003065, 'samples': 628224, 'steps': 1226, 'loss/train': 5.284897804260254}
-03/03/2022 14:51:44 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/03/2022 14:51:48 - INFO - codeparrot_training - Step 1227: {'lr': 0.00030675, 'samples': 628736, 'steps': 1227, 'loss/train': 4.29206657409668}
-03/03/2022 14:51:51 - INFO - codeparrot_training - Step 1228: {'lr': 0.000307, 'samples': 629248, 'steps': 1228, 'loss/train': 3.6068408489227295}
-03/03/2022 14:51:53 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/03/2022 14:51:56 - INFO - codeparrot_training - Step 1229: {'lr': 0.00030725, 'samples': 629760, 'steps': 1229, 'loss/train': 5.08143949508667}
-03/03/2022 14:51:59 - INFO - codeparrot_training - Step 1230: {'lr': 0.0003075, 'samples': 630272, 'steps': 1230, 'loss/train': 3.951544761657715}
-03/03/2022 14:52:01 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/03/2022 14:52:05 - INFO - codeparrot_training - Step 1231: {'lr': 0.00030775, 'samples': 630784, 'steps': 1231, 'loss/train': 4.961446285247803}
-03/03/2022 14:52:08 - INFO - codeparrot_training - Step 1232: {'lr': 0.000308, 'samples': 631296, 'steps': 1232, 'loss/train': 3.8938488960266113}
-03/03/2022 14:52:09 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/03/2022 14:52:13 - INFO - codeparrot_training - Step 1233: {'lr': 0.00030825000000000004, 'samples': 631808, 'steps': 1233, 'loss/train': 5.353794574737549}
-03/03/2022 14:52:16 - INFO - codeparrot_training - Step 1234: {'lr': 0.0003085, 'samples': 632320, 'steps': 1234, 'loss/train': 4.088746547698975}
-03/03/2022 14:52:18 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/03/2022 14:52:22 - INFO - codeparrot_training - Step 1235: {'lr': 0.00030875000000000005, 'samples': 632832, 'steps': 1235, 'loss/train': 3.818260669708252}
-03/03/2022 14:52:25 - INFO - codeparrot_training - Step 1236: {'lr': 0.00030900000000000003, 'samples': 633344, 'steps': 1236, 'loss/train': 5.052768707275391}
-03/03/2022 14:52:28 - INFO - codeparrot_training - Step 1237: {'lr': 0.00030925, 'samples': 633856, 'steps': 1237, 'loss/train': 4.26099967956543}
-03/03/2022 14:52:28 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/03/2022 14:52:33 - INFO - codeparrot_training - Step 1238: {'lr': 0.0003095, 'samples': 634368, 'steps': 1238, 'loss/train': 3.146836996078491}
-03/03/2022 14:52:36 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/03/2022 14:52:38 - INFO - codeparrot_training - Step 1239: {'lr': 0.00030975, 'samples': 634880, 'steps': 1239, 'loss/train': 4.403883457183838}
-03/03/2022 14:52:42 - INFO - codeparrot_training - Step 1240: {'lr': 0.00031, 'samples': 635392, 'steps': 1240, 'loss/train': 4.727677345275879}
-03/03/2022 14:52:45 - INFO - codeparrot_training - Step 1241: {'lr': 0.00031025000000000003, 'samples': 635904, 'steps': 1241, 'loss/train': 4.085188388824463}
-03/03/2022 14:52:45 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/03/2022 14:52:50 - INFO - codeparrot_training - Step 1242: {'lr': 0.0003105, 'samples': 636416, 'steps': 1242, 'loss/train': 4.715884685516357}
-03/03/2022 14:52:53 - INFO - codeparrot_training - Step 1243: {'lr': 0.00031075000000000005, 'samples': 636928, 'steps': 1243, 'loss/train': 4.942862033843994}
-03/03/2022 14:52:53 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/03/2022 14:52:59 - INFO - codeparrot_training - Step 1244: {'lr': 0.000311, 'samples': 637440, 'steps': 1244, 'loss/train': 4.894168853759766}
-03/03/2022 14:53:02 - INFO - codeparrot_training - Step 1245: {'lr': 0.00031125000000000006, 'samples': 637952, 'steps': 1245, 'loss/train': 4.579377174377441}
-03/03/2022 14:53:02 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/03/2022 14:53:07 - INFO - codeparrot_training - Step 1246: {'lr': 0.0003115, 'samples': 638464, 'steps': 1246, 'loss/train': 3.6056180000305176}
-03/03/2022 14:53:10 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/03/2022 14:53:12 - INFO - codeparrot_training - Step 1247: {'lr': 0.00031175, 'samples': 638976, 'steps': 1247, 'loss/train': 4.984847068786621}
-03/03/2022 14:53:15 - INFO - codeparrot_training - Step 1248: {'lr': 0.000312, 'samples': 639488, 'steps': 1248, 'loss/train': 3.766439437866211}
-03/03/2022 14:53:18 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/03/2022 14:53:21 - INFO - codeparrot_training - Step 1249: {'lr': 0.00031225000000000003, 'samples': 640000, 'steps': 1249, 'loss/train': 4.63666296005249}
-03/03/2022 14:53:24 - INFO - codeparrot_training - Step 1250: {'lr': 0.0003125, 'samples': 640512, 'steps': 1250, 'loss/train': 4.066371917724609}
-03/03/2022 14:53:27 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/03/2022 14:53:29 - INFO - codeparrot_training - Step 1251: {'lr': 0.00031275, 'samples': 641024, 'steps': 1251, 'loss/train': 4.966028213500977}
-03/03/2022 14:53:32 - INFO - codeparrot_training - Step 1252: {'lr': 0.000313, 'samples': 641536, 'steps': 1252, 'loss/train': 4.340587615966797}
-03/03/2022 14:53:35 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/03/2022 14:53:37 - INFO - codeparrot_training - Step 1253: {'lr': 0.00031325, 'samples': 642048, 'steps': 1253, 'loss/train': 4.897738933563232}
-03/03/2022 14:53:41 - INFO - codeparrot_training - Step 1254: {'lr': 0.00031350000000000003, 'samples': 642560, 'steps': 1254, 'loss/train': 4.782534122467041}
-03/03/2022 14:53:44 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/03/2022 14:53:46 - INFO - codeparrot_training - Step 1255: {'lr': 0.00031374999999999996, 'samples': 643072, 'steps': 1255, 'loss/train': 4.573090553283691}
-03/03/2022 14:53:49 - INFO - codeparrot_training - Step 1256: {'lr': 0.000314, 'samples': 643584, 'steps': 1256, 'loss/train': 4.770345211029053}
-03/03/2022 14:53:52 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/03/2022 14:53:55 - INFO - codeparrot_training - Step 1257: {'lr': 0.00031424999999999997, 'samples': 644096, 'steps': 1257, 'loss/train': 3.4803128242492676}
-03/03/2022 14:53:58 - INFO - codeparrot_training - Step 1258: {'lr': 0.0003145, 'samples': 644608, 'steps': 1258, 'loss/train': 2.8410775661468506}
-03/03/2022 14:54:00 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/03/2022 14:54:03 - INFO - codeparrot_training - Step 1259: {'lr': 0.00031475, 'samples': 645120, 'steps': 1259, 'loss/train': 4.5956902503967285}
-03/03/2022 14:54:06 - INFO - codeparrot_training - Step 1260: {'lr': 0.000315, 'samples': 645632, 'steps': 1260, 'loss/train': 3.090806722640991}
-03/03/2022 14:54:09 - INFO - codeparrot_training - Step 1261: {'lr': 0.00031525, 'samples': 646144, 'steps': 1261, 'loss/train': 3.7441775798797607}
-03/03/2022 14:54:09 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/03/2022 14:54:15 - INFO - codeparrot_training - Step 1262: {'lr': 0.0003155, 'samples': 646656, 'steps': 1262, 'loss/train': 4.384487152099609}
-03/03/2022 14:54:17 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/03/2022 14:54:20 - INFO - codeparrot_training - Step 1263: {'lr': 0.00031575, 'samples': 647168, 'steps': 1263, 'loss/train': 3.6381921768188477}
-03/03/2022 14:54:23 - INFO - codeparrot_training - Step 1264: {'lr': 0.000316, 'samples': 647680, 'steps': 1264, 'loss/train': 4.461718559265137}
-03/03/2022 14:54:26 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/03/2022 14:54:28 - INFO - codeparrot_training - Step 1265: {'lr': 0.00031624999999999996, 'samples': 648192, 'steps': 1265, 'loss/train': 4.316349983215332}
-03/03/2022 14:54:31 - INFO - codeparrot_training - Step 1266: {'lr': 0.0003165, 'samples': 648704, 'steps': 1266, 'loss/train': 3.2537786960601807}
-03/03/2022 14:54:34 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/03/2022 14:54:37 - INFO - codeparrot_training - Step 1267: {'lr': 0.00031675, 'samples': 649216, 'steps': 1267, 'loss/train': 4.303836345672607}
-03/03/2022 14:54:40 - INFO - codeparrot_training - Step 1268: {'lr': 0.000317, 'samples': 649728, 'steps': 1268, 'loss/train': 4.006771564483643}
-03/03/2022 14:54:42 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/03/2022 14:54:45 - INFO - codeparrot_training - Step 1269: {'lr': 0.00031725, 'samples': 650240, 'steps': 1269, 'loss/train': 4.61845064163208}
-03/03/2022 14:54:48 - INFO - codeparrot_training - Step 1270: {'lr': 0.0003175, 'samples': 650752, 'steps': 1270, 'loss/train': 4.1503729820251465}
-03/03/2022 14:54:50 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/03/2022 14:54:54 - INFO - codeparrot_training - Step 1271: {'lr': 0.00031775, 'samples': 651264, 'steps': 1271, 'loss/train': 4.021304130554199}
-03/03/2022 14:54:57 - INFO - codeparrot_training - Step 1272: {'lr': 0.00031800000000000003, 'samples': 651776, 'steps': 1272, 'loss/train': 4.838562488555908}
-03/03/2022 14:55:00 - INFO - codeparrot_training - Step 1273: {'lr': 0.00031825, 'samples': 652288, 'steps': 1273, 'loss/train': 5.103586673736572}
-03/03/2022 14:55:01 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/03/2022 14:55:05 - INFO - codeparrot_training - Step 1274: {'lr': 0.0003185, 'samples': 652800, 'steps': 1274, 'loss/train': 3.72918963432312}
-03/03/2022 14:55:09 - INFO - codeparrot_training - Step 1275: {'lr': 0.00031874999999999997, 'samples': 653312, 'steps': 1275, 'loss/train': 4.720226287841797}
-03/03/2022 14:55:09 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/03/2022 14:55:14 - INFO - codeparrot_training - Step 1276: {'lr': 0.000319, 'samples': 653824, 'steps': 1276, 'loss/train': 5.096245288848877}
-03/03/2022 14:55:17 - INFO - codeparrot_training - Step 1277: {'lr': 0.00031925, 'samples': 654336, 'steps': 1277, 'loss/train': 4.87737512588501}
-03/03/2022 14:55:18 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/03/2022 14:55:22 - INFO - codeparrot_training - Step 1278: {'lr': 0.0003195, 'samples': 654848, 'steps': 1278, 'loss/train': 4.559388637542725}
-03/03/2022 14:55:26 - INFO - codeparrot_training - Step 1279: {'lr': 0.00031975, 'samples': 655360, 'steps': 1279, 'loss/train': 4.643110752105713}
-03/03/2022 14:55:26 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/03/2022 14:55:31 - INFO - codeparrot_training - Step 1280: {'lr': 0.00032, 'samples': 655872, 'steps': 1280, 'loss/train': 5.080116271972656}
-03/03/2022 14:55:34 - INFO - codeparrot_training - Step 1281: {'lr': 0.00032025, 'samples': 656384, 'steps': 1281, 'loss/train': 4.069483280181885}
-03/03/2022 14:55:35 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/03/2022 14:55:40 - INFO - codeparrot_training - Step 1282: {'lr': 0.00032050000000000004, 'samples': 656896, 'steps': 1282, 'loss/train': 4.1711602210998535}
-03/03/2022 14:55:43 - INFO - codeparrot_training - Step 1283: {'lr': 0.00032074999999999996, 'samples': 657408, 'steps': 1283, 'loss/train': 8.397176742553711}
-03/03/2022 14:55:44 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/03/2022 14:55:48 - INFO - codeparrot_training - Step 1284: {'lr': 0.000321, 'samples': 657920, 'steps': 1284, 'loss/train': 4.191243648529053}
-03/03/2022 14:55:51 - INFO - codeparrot_training - Step 1285: {'lr': 0.00032125, 'samples': 658432, 'steps': 1285, 'loss/train': 3.708660840988159}
-03/03/2022 14:55:53 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 14:55:57 - INFO - codeparrot_training - Step 1286: {'lr': 0.0003215, 'samples': 658944, 'steps': 1286, 'loss/train': 4.2151970863342285}
-03/03/2022 14:56:00 - INFO - codeparrot_training - Step 1287: {'lr': 0.00032175, 'samples': 659456, 'steps': 1287, 'loss/train': 4.977806091308594}
-03/03/2022 14:56:01 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/03/2022 14:56:05 - INFO - codeparrot_training - Step 1288: {'lr': 0.000322, 'samples': 659968, 'steps': 1288, 'loss/train': 3.4825994968414307}
-03/03/2022 14:56:08 - INFO - codeparrot_training - Step 1289: {'lr': 0.00032225, 'samples': 660480, 'steps': 1289, 'loss/train': 4.8441691398620605}
-03/03/2022 14:56:09 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 14:56:13 - INFO - codeparrot_training - Step 1290: {'lr': 0.00032250000000000003, 'samples': 660992, 'steps': 1290, 'loss/train': 4.4799323081970215}
-03/03/2022 14:56:16 - INFO - codeparrot_training - Step 1291: {'lr': 0.00032275, 'samples': 661504, 'steps': 1291, 'loss/train': 4.314608573913574}
-03/03/2022 14:56:17 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/03/2022 14:56:22 - INFO - codeparrot_training - Step 1292: {'lr': 0.000323, 'samples': 662016, 'steps': 1292, 'loss/train': 4.211328983306885}
-03/03/2022 14:56:25 - INFO - codeparrot_training - Step 1293: {'lr': 0.00032324999999999997, 'samples': 662528, 'steps': 1293, 'loss/train': 4.245683670043945}
-03/03/2022 14:56:26 - INFO - codeparrot_training - Skipping example with length 1010 (seq_length=1024)
-03/03/2022 14:56:30 - INFO - codeparrot_training - Step 1294: {'lr': 0.0003235, 'samples': 663040, 'steps': 1294, 'loss/train': 4.791468620300293}
-03/03/2022 14:56:33 - INFO - codeparrot_training - Step 1295: {'lr': 0.00032375, 'samples': 663552, 'steps': 1295, 'loss/train': 4.671751499176025}
-03/03/2022 14:56:34 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/03/2022 14:56:38 - INFO - codeparrot_training - Step 1296: {'lr': 0.000324, 'samples': 664064, 'steps': 1296, 'loss/train': 1.9223575592041016}
-03/03/2022 14:56:42 - INFO - codeparrot_training - Step 1297: {'lr': 0.00032425, 'samples': 664576, 'steps': 1297, 'loss/train': 3.6483588218688965}
-03/03/2022 14:56:42 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/03/2022 14:56:47 - INFO - codeparrot_training - Step 1298: {'lr': 0.00032450000000000003, 'samples': 665088, 'steps': 1298, 'loss/train': 4.501202583312988}
-03/03/2022 14:56:50 - INFO - codeparrot_training - Step 1299: {'lr': 0.00032475, 'samples': 665600, 'steps': 1299, 'loss/train': 4.025876522064209}
-03/03/2022 14:56:50 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/03/2022 14:56:55 - INFO - codeparrot_training - Step 1300: {'lr': 0.00032500000000000004, 'samples': 666112, 'steps': 1300, 'loss/train': 3.9416229724884033}
-03/03/2022 14:56:58 - INFO - codeparrot_training - Step 1301: {'lr': 0.00032524999999999996, 'samples': 666624, 'steps': 1301, 'loss/train': 4.250044822692871}
-03/03/2022 14:56:58 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/03/2022 14:57:04 - INFO - codeparrot_training - Step 1302: {'lr': 0.0003255, 'samples': 667136, 'steps': 1302, 'loss/train': 4.65021276473999}
-03/03/2022 14:57:07 - INFO - codeparrot_training - Step 1303: {'lr': 0.00032575, 'samples': 667648, 'steps': 1303, 'loss/train': 5.90805721282959}
-03/03/2022 14:57:07 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/03/2022 14:57:12 - INFO - codeparrot_training - Step 1304: {'lr': 0.000326, 'samples': 668160, 'steps': 1304, 'loss/train': 1.5903449058532715}
-03/03/2022 14:57:15 - INFO - codeparrot_training - Step 1305: {'lr': 0.00032625, 'samples': 668672, 'steps': 1305, 'loss/train': 4.671641826629639}
-03/03/2022 14:57:15 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/03/2022 14:57:21 - INFO - codeparrot_training - Step 1306: {'lr': 0.0003265, 'samples': 669184, 'steps': 1306, 'loss/train': 2.0237982273101807}
-03/03/2022 14:57:23 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/03/2022 14:57:26 - INFO - codeparrot_training - Step 1307: {'lr': 0.00032675, 'samples': 669696, 'steps': 1307, 'loss/train': 3.784977674484253}
-03/03/2022 14:57:29 - INFO - codeparrot_training - Step 1308: {'lr': 0.00032700000000000003, 'samples': 670208, 'steps': 1308, 'loss/train': 4.29042387008667}
-03/03/2022 14:57:31 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/03/2022 14:57:34 - INFO - codeparrot_training - Step 1309: {'lr': 0.00032725, 'samples': 670720, 'steps': 1309, 'loss/train': 5.2600836753845215}
-03/03/2022 14:57:37 - INFO - codeparrot_training - Step 1310: {'lr': 0.00032750000000000005, 'samples': 671232, 'steps': 1310, 'loss/train': 4.140377044677734}
-03/03/2022 14:57:40 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/03/2022 14:57:43 - INFO - codeparrot_training - Step 1311: {'lr': 0.00032774999999999997, 'samples': 671744, 'steps': 1311, 'loss/train': 4.405689716339111}
-03/03/2022 14:57:46 - INFO - codeparrot_training - Step 1312: {'lr': 0.000328, 'samples': 672256, 'steps': 1312, 'loss/train': 4.767686367034912}
-03/03/2022 14:57:48 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/03/2022 14:57:51 - INFO - codeparrot_training - Step 1313: {'lr': 0.00032825, 'samples': 672768, 'steps': 1313, 'loss/train': 4.756639003753662}
-03/03/2022 14:57:54 - INFO - codeparrot_training - Step 1314: {'lr': 0.0003285, 'samples': 673280, 'steps': 1314, 'loss/train': 4.535913944244385}
-03/03/2022 14:57:56 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/03/2022 14:57:59 - INFO - codeparrot_training - Step 1315: {'lr': 0.00032875, 'samples': 673792, 'steps': 1315, 'loss/train': 8.396307945251465}
-03/03/2022 14:58:03 - INFO - codeparrot_training - Step 1316: {'lr': 0.00032900000000000003, 'samples': 674304, 'steps': 1316, 'loss/train': 3.8972136974334717}
-03/03/2022 14:58:05 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/03/2022 14:58:08 - INFO - codeparrot_training - Step 1317: {'lr': 0.00032925, 'samples': 674816, 'steps': 1317, 'loss/train': 4.135924339294434}
-03/03/2022 14:58:11 - INFO - codeparrot_training - Step 1318: {'lr': 0.00032950000000000004, 'samples': 675328, 'steps': 1318, 'loss/train': 4.443324565887451}
-03/03/2022 14:58:14 - INFO - codeparrot_training - Step 1319: {'lr': 0.00032975, 'samples': 675840, 'steps': 1319, 'loss/train': 4.235952854156494}
-03/03/2022 14:58:14 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/03/2022 14:58:20 - INFO - codeparrot_training - Step 1320: {'lr': 0.00033, 'samples': 676352, 'steps': 1320, 'loss/train': 2.607849597930908}
-03/03/2022 14:58:23 - INFO - codeparrot_training - Step 1321: {'lr': 0.00033025, 'samples': 676864, 'steps': 1321, 'loss/train': 4.970389366149902}
-03/03/2022 14:58:23 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/03/2022 14:58:28 - INFO - codeparrot_training - Step 1322: {'lr': 0.0003305, 'samples': 677376, 'steps': 1322, 'loss/train': 4.476796627044678}
-03/03/2022 14:58:31 - INFO - codeparrot_training - Step 1323: {'lr': 0.00033075, 'samples': 677888, 'steps': 1323, 'loss/train': 4.577625751495361}
-03/03/2022 14:58:31 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/03/2022 14:58:37 - INFO - codeparrot_training - Step 1324: {'lr': 0.000331, 'samples': 678400, 'steps': 1324, 'loss/train': 2.9740169048309326}
-03/03/2022 14:58:40 - INFO - codeparrot_training - Step 1325: {'lr': 0.00033125, 'samples': 678912, 'steps': 1325, 'loss/train': 4.472623348236084}
-03/03/2022 14:58:40 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/03/2022 14:58:45 - INFO - codeparrot_training - Step 1326: {'lr': 0.00033150000000000003, 'samples': 679424, 'steps': 1326, 'loss/train': 3.589266777038574}
-03/03/2022 14:58:48 - INFO - codeparrot_training - Step 1327: {'lr': 0.00033175, 'samples': 679936, 'steps': 1327, 'loss/train': 4.105099678039551}
-03/03/2022 14:58:48 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/03/2022 14:58:54 - INFO - codeparrot_training - Step 1328: {'lr': 0.00033200000000000005, 'samples': 680448, 'steps': 1328, 'loss/train': 4.997483253479004}
-03/03/2022 14:58:56 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/03/2022 14:58:59 - INFO - codeparrot_training - Step 1329: {'lr': 0.00033224999999999997, 'samples': 680960, 'steps': 1329, 'loss/train': 3.461973190307617}
-03/03/2022 14:59:02 - INFO - codeparrot_training - Step 1330: {'lr': 0.0003325, 'samples': 681472, 'steps': 1330, 'loss/train': 4.032837867736816}
-03/03/2022 14:59:06 - INFO - codeparrot_training - Step 1331: {'lr': 0.00033275, 'samples': 681984, 'steps': 1331, 'loss/train': 3.4902446269989014}
-03/03/2022 14:59:07 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/03/2022 14:59:11 - INFO - codeparrot_training - Step 1332: {'lr': 0.000333, 'samples': 682496, 'steps': 1332, 'loss/train': 3.956376791000366}
-03/03/2022 14:59:14 - INFO - codeparrot_training - Step 1333: {'lr': 0.00033325, 'samples': 683008, 'steps': 1333, 'loss/train': 4.723476886749268}
-03/03/2022 14:59:15 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/03/2022 14:59:19 - INFO - codeparrot_training - Step 1334: {'lr': 0.00033350000000000003, 'samples': 683520, 'steps': 1334, 'loss/train': 2.3966643810272217}
-03/03/2022 14:59:22 - INFO - codeparrot_training - Step 1335: {'lr': 0.00033375, 'samples': 684032, 'steps': 1335, 'loss/train': 3.550367593765259}
-03/03/2022 14:59:23 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/03/2022 14:59:28 - INFO - codeparrot_training - Step 1336: {'lr': 0.00033400000000000004, 'samples': 684544, 'steps': 1336, 'loss/train': 4.618042945861816}
-03/03/2022 14:59:31 - INFO - codeparrot_training - Step 1337: {'lr': 0.00033425, 'samples': 685056, 'steps': 1337, 'loss/train': 3.770845890045166}
-03/03/2022 14:59:31 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/03/2022 14:59:36 - INFO - codeparrot_training - Step 1338: {'lr': 0.00033450000000000005, 'samples': 685568, 'steps': 1338, 'loss/train': 3.7352075576782227}
-03/03/2022 14:59:39 - INFO - codeparrot_training - Step 1339: {'lr': 0.00033475, 'samples': 686080, 'steps': 1339, 'loss/train': 3.3929390907287598}
-03/03/2022 14:59:39 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/03/2022 14:59:44 - INFO - codeparrot_training - Step 1340: {'lr': 0.000335, 'samples': 686592, 'steps': 1340, 'loss/train': 4.196238994598389}
-03/03/2022 14:59:47 - INFO - codeparrot_training - Step 1341: {'lr': 0.00033525, 'samples': 687104, 'steps': 1341, 'loss/train': 3.144120216369629}
-03/03/2022 14:59:48 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/03/2022 14:59:53 - INFO - codeparrot_training - Step 1342: {'lr': 0.0003355, 'samples': 687616, 'steps': 1342, 'loss/train': 4.511755466461182}
-03/03/2022 14:59:56 - INFO - codeparrot_training - Step 1343: {'lr': 0.00033575, 'samples': 688128, 'steps': 1343, 'loss/train': 2.205004930496216}
-03/03/2022 14:59:56 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/03/2022 15:00:01 - INFO - codeparrot_training - Step 1344: {'lr': 0.00033600000000000004, 'samples': 688640, 'steps': 1344, 'loss/train': 4.689573764801025}
-03/03/2022 15:00:05 - INFO - codeparrot_training - Step 1345: {'lr': 0.00033625, 'samples': 689152, 'steps': 1345, 'loss/train': 3.897254705429077}
-03/03/2022 15:00:05 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/03/2022 15:00:10 - INFO - codeparrot_training - Step 1346: {'lr': 0.00033650000000000005, 'samples': 689664, 'steps': 1346, 'loss/train': 4.323125839233398}
-03/03/2022 15:00:13 - INFO - codeparrot_training - Step 1347: {'lr': 0.00033675, 'samples': 690176, 'steps': 1347, 'loss/train': 3.3169021606445312}
-03/03/2022 15:00:13 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/03/2022 15:00:18 - INFO - codeparrot_training - Step 1348: {'lr': 0.000337, 'samples': 690688, 'steps': 1348, 'loss/train': 4.208149433135986}
-03/03/2022 15:00:21 - INFO - codeparrot_training - Step 1349: {'lr': 0.00033725, 'samples': 691200, 'steps': 1349, 'loss/train': 4.077748775482178}
-03/03/2022 15:00:21 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/03/2022 15:00:27 - INFO - codeparrot_training - Step 1350: {'lr': 0.0003375, 'samples': 691712, 'steps': 1350, 'loss/train': 4.038091659545898}
-03/03/2022 15:00:30 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/03/2022 15:00:32 - INFO - codeparrot_training - Step 1351: {'lr': 0.00033775, 'samples': 692224, 'steps': 1351, 'loss/train': 4.951350688934326}
-03/03/2022 15:00:35 - INFO - codeparrot_training - Step 1352: {'lr': 0.00033800000000000003, 'samples': 692736, 'steps': 1352, 'loss/train': 4.2818803787231445}
-03/03/2022 15:00:38 - INFO - codeparrot_training - Step 1353: {'lr': 0.00033825, 'samples': 693248, 'steps': 1353, 'loss/train': 5.575289249420166}
-03/03/2022 15:00:38 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/03/2022 15:00:44 - INFO - codeparrot_training - Step 1354: {'lr': 0.00033850000000000004, 'samples': 693760, 'steps': 1354, 'loss/train': 4.848819255828857}
-03/03/2022 15:00:46 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/03/2022 15:00:49 - INFO - codeparrot_training - Step 1355: {'lr': 0.00033875, 'samples': 694272, 'steps': 1355, 'loss/train': 5.165854454040527}
-03/03/2022 15:00:52 - INFO - codeparrot_training - Step 1356: {'lr': 0.00033900000000000005, 'samples': 694784, 'steps': 1356, 'loss/train': 3.9726078510284424}
-03/03/2022 15:00:55 - INFO - codeparrot_training - Step 1357: {'lr': 0.00033925, 'samples': 695296, 'steps': 1357, 'loss/train': 3.788126230239868}
-03/03/2022 15:00:55 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/03/2022 15:01:01 - INFO - codeparrot_training - Step 1358: {'lr': 0.0003395, 'samples': 695808, 'steps': 1358, 'loss/train': 3.8103890419006348}
-03/03/2022 15:01:04 - INFO - codeparrot_training - Step 1359: {'lr': 0.00033975, 'samples': 696320, 'steps': 1359, 'loss/train': 4.306206703186035}
-03/03/2022 15:01:04 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/03/2022 15:01:09 - INFO - codeparrot_training - Step 1360: {'lr': 0.00034, 'samples': 696832, 'steps': 1360, 'loss/train': 4.6508870124816895}
-03/03/2022 15:01:12 - INFO - codeparrot_training - Step 1361: {'lr': 0.00034025, 'samples': 697344, 'steps': 1361, 'loss/train': 3.7625675201416016}
-03/03/2022 15:01:12 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/03/2022 15:01:17 - INFO - codeparrot_training - Step 1362: {'lr': 0.00034050000000000004, 'samples': 697856, 'steps': 1362, 'loss/train': 4.423110485076904}
-03/03/2022 15:01:20 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/03/2022 15:01:23 - INFO - codeparrot_training - Step 1363: {'lr': 0.00034075, 'samples': 698368, 'steps': 1363, 'loss/train': 3.479337692260742}
-03/03/2022 15:01:26 - INFO - codeparrot_training - Step 1364: {'lr': 0.00034100000000000005, 'samples': 698880, 'steps': 1364, 'loss/train': 3.825160503387451}
-03/03/2022 15:01:28 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/03/2022 15:01:31 - INFO - codeparrot_training - Step 1365: {'lr': 0.00034125000000000003, 'samples': 699392, 'steps': 1365, 'loss/train': 4.07443904876709}
-03/03/2022 15:01:34 - INFO - codeparrot_training - Step 1366: {'lr': 0.0003415, 'samples': 699904, 'steps': 1366, 'loss/train': 1.9652504920959473}
-03/03/2022 15:01:37 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/03/2022 15:01:39 - INFO - codeparrot_training - Step 1367: {'lr': 0.00034175, 'samples': 700416, 'steps': 1367, 'loss/train': 5.137356281280518}
-03/03/2022 15:01:42 - INFO - codeparrot_training - Step 1368: {'lr': 0.000342, 'samples': 700928, 'steps': 1368, 'loss/train': 4.848583698272705}
-03/03/2022 15:01:45 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/03/2022 15:01:48 - INFO - codeparrot_training - Step 1369: {'lr': 0.00034225, 'samples': 701440, 'steps': 1369, 'loss/train': 3.256547212600708}
-03/03/2022 15:01:51 - INFO - codeparrot_training - Step 1370: {'lr': 0.00034250000000000003, 'samples': 701952, 'steps': 1370, 'loss/train': 3.7308225631713867}
-03/03/2022 15:01:54 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/03/2022 15:01:56 - INFO - codeparrot_training - Step 1371: {'lr': 0.00034275, 'samples': 702464, 'steps': 1371, 'loss/train': 4.213438987731934}
-03/03/2022 15:01:59 - INFO - codeparrot_training - Step 1372: {'lr': 0.00034300000000000004, 'samples': 702976, 'steps': 1372, 'loss/train': 3.998389959335327}
-03/03/2022 15:02:02 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/03/2022 15:02:05 - INFO - codeparrot_training - Step 1373: {'lr': 0.00034325, 'samples': 703488, 'steps': 1373, 'loss/train': 4.89825963973999}
-03/03/2022 15:02:08 - INFO - codeparrot_training - Step 1374: {'lr': 0.00034350000000000006, 'samples': 704000, 'steps': 1374, 'loss/train': 4.995420455932617}
-03/03/2022 15:02:10 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/03/2022 15:02:13 - INFO - codeparrot_training - Step 1375: {'lr': 0.00034375, 'samples': 704512, 'steps': 1375, 'loss/train': 4.292768955230713}
-03/03/2022 15:02:16 - INFO - codeparrot_training - Step 1376: {'lr': 0.00034399999999999996, 'samples': 705024, 'steps': 1376, 'loss/train': 6.702393054962158}
-03/03/2022 15:02:19 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/03/2022 15:02:22 - INFO - codeparrot_training - Step 1377: {'lr': 0.00034425, 'samples': 705536, 'steps': 1377, 'loss/train': 3.957270622253418}
-03/03/2022 15:02:25 - INFO - codeparrot_training - Step 1378: {'lr': 0.00034449999999999997, 'samples': 706048, 'steps': 1378, 'loss/train': 5.051953315734863}
-03/03/2022 15:02:28 - INFO - codeparrot_training - Step 1379: {'lr': 0.00034475, 'samples': 706560, 'steps': 1379, 'loss/train': 4.340051174163818}
-03/03/2022 15:02:28 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/03/2022 15:02:33 - INFO - codeparrot_training - Step 1380: {'lr': 0.000345, 'samples': 707072, 'steps': 1380, 'loss/train': 4.199203968048096}
-03/03/2022 15:02:36 - INFO - codeparrot_training - Step 1381: {'lr': 0.00034525, 'samples': 707584, 'steps': 1381, 'loss/train': 4.896386623382568}
-03/03/2022 15:02:37 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/03/2022 15:02:42 - INFO - codeparrot_training - Step 1382: {'lr': 0.0003455, 'samples': 708096, 'steps': 1382, 'loss/train': 4.71715784072876}
-03/03/2022 15:02:45 - INFO - codeparrot_training - Step 1383: {'lr': 0.00034575000000000003, 'samples': 708608, 'steps': 1383, 'loss/train': 4.2592949867248535}
-03/03/2022 15:02:45 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/03/2022 15:02:50 - INFO - codeparrot_training - Step 1384: {'lr': 0.000346, 'samples': 709120, 'steps': 1384, 'loss/train': 4.287826061248779}
-03/03/2022 15:02:53 - INFO - codeparrot_training - Step 1385: {'lr': 0.00034625, 'samples': 709632, 'steps': 1385, 'loss/train': 4.505620002746582}
-03/03/2022 15:02:53 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/03/2022 15:02:58 - INFO - codeparrot_training - Step 1386: {'lr': 0.00034649999999999997, 'samples': 710144, 'steps': 1386, 'loss/train': 4.012139320373535}
-03/03/2022 15:03:02 - INFO - codeparrot_training - Step 1387: {'lr': 0.00034675, 'samples': 710656, 'steps': 1387, 'loss/train': 3.345623016357422}
-03/03/2022 15:03:02 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/03/2022 15:03:07 - INFO - codeparrot_training - Step 1388: {'lr': 0.000347, 'samples': 711168, 'steps': 1388, 'loss/train': 4.0962114334106445}
-03/03/2022 15:03:10 - INFO - codeparrot_training - Step 1389: {'lr': 0.00034725, 'samples': 711680, 'steps': 1389, 'loss/train': 3.7883925437927246}
-03/03/2022 15:03:10 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/03/2022 15:03:15 - INFO - codeparrot_training - Step 1390: {'lr': 0.0003475, 'samples': 712192, 'steps': 1390, 'loss/train': 4.1875529289245605}
-03/03/2022 15:03:18 - INFO - codeparrot_training - Step 1391: {'lr': 0.00034775, 'samples': 712704, 'steps': 1391, 'loss/train': 4.096395015716553}
-03/03/2022 15:03:18 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/03/2022 15:03:24 - INFO - codeparrot_training - Step 1392: {'lr': 0.000348, 'samples': 713216, 'steps': 1392, 'loss/train': 4.032371520996094}
-03/03/2022 15:03:27 - INFO - codeparrot_training - Step 1393: {'lr': 0.00034825000000000004, 'samples': 713728, 'steps': 1393, 'loss/train': 4.76602029800415}
-03/03/2022 15:03:27 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/03/2022 15:03:32 - INFO - codeparrot_training - Step 1394: {'lr': 0.00034849999999999996, 'samples': 714240, 'steps': 1394, 'loss/train': 3.944689989089966}
-03/03/2022 15:03:36 - INFO - codeparrot_training - Step 1395: {'lr': 0.00034875, 'samples': 714752, 'steps': 1395, 'loss/train': 1.1654375791549683}
-03/03/2022 15:03:36 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/03/2022 15:03:41 - INFO - codeparrot_training - Step 1396: {'lr': 0.00034899999999999997, 'samples': 715264, 'steps': 1396, 'loss/train': 5.171820640563965}
-03/03/2022 15:03:44 - INFO - codeparrot_training - Step 1397: {'lr': 0.00034925, 'samples': 715776, 'steps': 1397, 'loss/train': 4.422672748565674}
-03/03/2022 15:03:44 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/03/2022 15:03:49 - INFO - codeparrot_training - Step 1398: {'lr': 0.0003495, 'samples': 716288, 'steps': 1398, 'loss/train': 3.649049997329712}
-03/03/2022 15:03:52 - INFO - codeparrot_training - Step 1399: {'lr': 0.00034975, 'samples': 716800, 'steps': 1399, 'loss/train': 3.8000471591949463}
-03/03/2022 15:03:52 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/03/2022 15:03:57 - INFO - codeparrot_training - Step 1400: {'lr': 0.00035, 'samples': 717312, 'steps': 1400, 'loss/train': 3.921113967895508}
-03/03/2022 15:04:01 - INFO - codeparrot_training - Step 1401: {'lr': 0.00035025000000000003, 'samples': 717824, 'steps': 1401, 'loss/train': 3.2294576168060303}
-03/03/2022 15:04:01 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/03/2022 15:04:06 - INFO - codeparrot_training - Step 1402: {'lr': 0.0003505, 'samples': 718336, 'steps': 1402, 'loss/train': 4.519753932952881}
-03/03/2022 15:04:09 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/03/2022 15:04:11 - INFO - codeparrot_training - Step 1403: {'lr': 0.00035075, 'samples': 718848, 'steps': 1403, 'loss/train': 4.289191246032715}
-03/03/2022 15:04:14 - INFO - codeparrot_training - Step 1404: {'lr': 0.00035099999999999997, 'samples': 719360, 'steps': 1404, 'loss/train': 4.642714977264404}
-03/03/2022 15:04:17 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/03/2022 15:04:19 - INFO - codeparrot_training - Step 1405: {'lr': 0.00035125, 'samples': 719872, 'steps': 1405, 'loss/train': 5.213424205780029}
-03/03/2022 15:04:22 - INFO - codeparrot_training - Step 1406: {'lr': 0.0003515, 'samples': 720384, 'steps': 1406, 'loss/train': 4.356109142303467}
-03/03/2022 15:04:25 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/03/2022 15:04:28 - INFO - codeparrot_training - Step 1407: {'lr': 0.00035175, 'samples': 720896, 'steps': 1407, 'loss/train': 3.914952516555786}
-03/03/2022 15:04:31 - INFO - codeparrot_training - Step 1408: {'lr': 0.000352, 'samples': 721408, 'steps': 1408, 'loss/train': 6.220399856567383}
-03/03/2022 15:04:33 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/03/2022 15:04:36 - INFO - codeparrot_training - Step 1409: {'lr': 0.00035225, 'samples': 721920, 'steps': 1409, 'loss/train': 4.541872501373291}
-03/03/2022 15:04:39 - INFO - codeparrot_training - Step 1410: {'lr': 0.0003525, 'samples': 722432, 'steps': 1410, 'loss/train': 5.304427623748779}
-03/03/2022 15:04:41 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/03/2022 15:04:45 - INFO - codeparrot_training - Step 1411: {'lr': 0.00035275000000000004, 'samples': 722944, 'steps': 1411, 'loss/train': 3.934983253479004}
-03/03/2022 15:04:48 - INFO - codeparrot_training - Step 1412: {'lr': 0.00035299999999999996, 'samples': 723456, 'steps': 1412, 'loss/train': 3.3430862426757812}
-03/03/2022 15:04:50 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/03/2022 15:04:53 - INFO - codeparrot_training - Step 1413: {'lr': 0.00035325, 'samples': 723968, 'steps': 1413, 'loss/train': 4.663939952850342}
-03/03/2022 15:04:56 - INFO - codeparrot_training - Step 1414: {'lr': 0.0003535, 'samples': 724480, 'steps': 1414, 'loss/train': 2.632704019546509}
-03/03/2022 15:04:58 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/03/2022 15:05:02 - INFO - codeparrot_training - Step 1415: {'lr': 0.00035375, 'samples': 724992, 'steps': 1415, 'loss/train': 3.939199924468994}
-03/03/2022 15:05:05 - INFO - codeparrot_training - Step 1416: {'lr': 0.000354, 'samples': 725504, 'steps': 1416, 'loss/train': 3.894688606262207}
-03/03/2022 15:05:08 - INFO - codeparrot_training - Step 1417: {'lr': 0.00035425, 'samples': 726016, 'steps': 1417, 'loss/train': 3.548281669616699}
-03/03/2022 15:05:09 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/03/2022 15:05:13 - INFO - codeparrot_training - Step 1418: {'lr': 0.0003545, 'samples': 726528, 'steps': 1418, 'loss/train': 3.9033889770507812}
-03/03/2022 15:05:16 - INFO - codeparrot_training - Step 1419: {'lr': 0.00035475000000000003, 'samples': 727040, 'steps': 1419, 'loss/train': 4.490829944610596}
-03/03/2022 15:05:17 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/03/2022 15:05:22 - INFO - codeparrot_training - Step 1420: {'lr': 0.000355, 'samples': 727552, 'steps': 1420, 'loss/train': 3.8207790851593018}
-03/03/2022 15:05:25 - INFO - codeparrot_training - Step 1421: {'lr': 0.00035525000000000004, 'samples': 728064, 'steps': 1421, 'loss/train': 3.9344375133514404}
-03/03/2022 15:05:25 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/03/2022 15:05:30 - INFO - codeparrot_training - Step 1422: {'lr': 0.00035549999999999997, 'samples': 728576, 'steps': 1422, 'loss/train': 4.054946422576904}
-03/03/2022 15:05:33 - INFO - codeparrot_training - Step 1423: {'lr': 0.00035575, 'samples': 729088, 'steps': 1423, 'loss/train': 5.404002666473389}
-03/03/2022 15:05:33 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/03/2022 15:05:38 - INFO - codeparrot_training - Step 1424: {'lr': 0.000356, 'samples': 729600, 'steps': 1424, 'loss/train': 4.829292297363281}
-03/03/2022 15:05:41 - INFO - codeparrot_training - Step 1425: {'lr': 0.00035625, 'samples': 730112, 'steps': 1425, 'loss/train': 4.549272060394287}
-03/03/2022 15:05:41 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/03/2022 15:05:47 - INFO - codeparrot_training - Step 1426: {'lr': 0.0003565, 'samples': 730624, 'steps': 1426, 'loss/train': 4.292669296264648}
-03/03/2022 15:05:50 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/03/2022 15:05:52 - INFO - codeparrot_training - Step 1427: {'lr': 0.00035675, 'samples': 731136, 'steps': 1427, 'loss/train': 3.107365608215332}
-03/03/2022 15:05:55 - INFO - codeparrot_training - Step 1428: {'lr': 0.000357, 'samples': 731648, 'steps': 1428, 'loss/train': 4.563395023345947}
-03/03/2022 15:05:58 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/03/2022 15:06:00 - INFO - codeparrot_training - Step 1429: {'lr': 0.00035725000000000004, 'samples': 732160, 'steps': 1429, 'loss/train': 4.344968795776367}
-03/03/2022 15:06:04 - INFO - codeparrot_training - Step 1430: {'lr': 0.0003575, 'samples': 732672, 'steps': 1430, 'loss/train': 4.074631214141846}
-03/03/2022 15:06:06 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/03/2022 15:06:09 - INFO - codeparrot_training - Step 1431: {'lr': 0.00035775, 'samples': 733184, 'steps': 1431, 'loss/train': 3.411041498184204}
-03/03/2022 15:06:12 - INFO - codeparrot_training - Step 1432: {'lr': 0.000358, 'samples': 733696, 'steps': 1432, 'loss/train': 4.681650161743164}
-03/03/2022 15:06:15 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/03/2022 15:06:17 - INFO - codeparrot_training - Step 1433: {'lr': 0.00035825, 'samples': 734208, 'steps': 1433, 'loss/train': 3.564584732055664}
-03/03/2022 15:06:20 - INFO - codeparrot_training - Step 1434: {'lr': 0.0003585, 'samples': 734720, 'steps': 1434, 'loss/train': 4.753785610198975}
-03/03/2022 15:06:23 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/03/2022 15:06:26 - INFO - codeparrot_training - Step 1435: {'lr': 0.00035875, 'samples': 735232, 'steps': 1435, 'loss/train': 4.694465160369873}
-03/03/2022 15:06:29 - INFO - codeparrot_training - Step 1436: {'lr': 0.000359, 'samples': 735744, 'steps': 1436, 'loss/train': 3.8891234397888184}
-03/03/2022 15:06:34 - INFO - codeparrot_training - Step 1437: {'lr': 0.00035925000000000003, 'samples': 736256, 'steps': 1437, 'loss/train': 3.8811140060424805}
-03/03/2022 15:06:37 - INFO - codeparrot_training - Step 1438: {'lr': 0.0003595, 'samples': 736768, 'steps': 1438, 'loss/train': 3.0895650386810303}
-03/03/2022 15:06:40 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/03/2022 15:06:42 - INFO - codeparrot_training - Step 1439: {'lr': 0.00035975000000000004, 'samples': 737280, 'steps': 1439, 'loss/train': 4.115229606628418}
-03/03/2022 15:06:46 - INFO - codeparrot_training - Step 1440: {'lr': 0.00035999999999999997, 'samples': 737792, 'steps': 1440, 'loss/train': 4.0173187255859375}
-03/03/2022 15:06:48 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/03/2022 15:06:51 - INFO - codeparrot_training - Step 1441: {'lr': 0.00036025, 'samples': 738304, 'steps': 1441, 'loss/train': 4.3554840087890625}
-03/03/2022 15:06:54 - INFO - codeparrot_training - Step 1442: {'lr': 0.0003605, 'samples': 738816, 'steps': 1442, 'loss/train': 4.1994194984436035}
-03/03/2022 15:06:57 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/03/2022 15:06:59 - INFO - codeparrot_training - Step 1443: {'lr': 0.00036075, 'samples': 739328, 'steps': 1443, 'loss/train': 4.311388969421387}
-03/03/2022 15:07:03 - INFO - codeparrot_training - Step 1444: {'lr': 0.000361, 'samples': 739840, 'steps': 1444, 'loss/train': 4.153400421142578}
-03/03/2022 15:07:05 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/03/2022 15:07:08 - INFO - codeparrot_training - Step 1445: {'lr': 0.00036125, 'samples': 740352, 'steps': 1445, 'loss/train': 3.061067819595337}
-03/03/2022 15:07:11 - INFO - codeparrot_training - Step 1446: {'lr': 0.0003615, 'samples': 740864, 'steps': 1446, 'loss/train': 3.8438150882720947}
-03/03/2022 15:07:13 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 15:07:16 - INFO - codeparrot_training - Step 1447: {'lr': 0.00036175000000000004, 'samples': 741376, 'steps': 1447, 'loss/train': 4.005690574645996}
-03/03/2022 15:07:19 - INFO - codeparrot_training - Step 1448: {'lr': 0.000362, 'samples': 741888, 'steps': 1448, 'loss/train': 4.079996585845947}
-03/03/2022 15:07:22 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/03/2022 15:07:25 - INFO - codeparrot_training - Step 1449: {'lr': 0.00036225000000000005, 'samples': 742400, 'steps': 1449, 'loss/train': 4.334934711456299}
-03/03/2022 15:07:28 - INFO - codeparrot_training - Step 1450: {'lr': 0.0003625, 'samples': 742912, 'steps': 1450, 'loss/train': 4.11976432800293}
-03/03/2022 15:07:30 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/03/2022 15:07:33 - INFO - codeparrot_training - Step 1451: {'lr': 0.00036275, 'samples': 743424, 'steps': 1451, 'loss/train': 2.37908935546875}
-03/03/2022 15:07:36 - INFO - codeparrot_training - Step 1452: {'lr': 0.000363, 'samples': 743936, 'steps': 1452, 'loss/train': 3.74288010597229}
-03/03/2022 15:07:39 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/03/2022 15:07:42 - INFO - codeparrot_training - Step 1453: {'lr': 0.00036325, 'samples': 744448, 'steps': 1453, 'loss/train': 4.1216254234313965}
-03/03/2022 15:07:45 - INFO - codeparrot_training - Step 1454: {'lr': 0.0003635, 'samples': 744960, 'steps': 1454, 'loss/train': 4.451533317565918}
-03/03/2022 15:07:47 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/03/2022 15:07:50 - INFO - codeparrot_training - Step 1455: {'lr': 0.00036375000000000003, 'samples': 745472, 'steps': 1455, 'loss/train': 4.489429950714111}
-03/03/2022 15:07:53 - INFO - codeparrot_training - Step 1456: {'lr': 0.000364, 'samples': 745984, 'steps': 1456, 'loss/train': 4.745635032653809}
-03/03/2022 15:07:55 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/03/2022 15:07:58 - INFO - codeparrot_training - Step 1457: {'lr': 0.00036425000000000004, 'samples': 746496, 'steps': 1457, 'loss/train': 4.129570484161377}
-03/03/2022 15:08:01 - INFO - codeparrot_training - Step 1458: {'lr': 0.0003645, 'samples': 747008, 'steps': 1458, 'loss/train': 3.9060328006744385}
-03/03/2022 15:08:03 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/03/2022 15:08:07 - INFO - codeparrot_training - Step 1459: {'lr': 0.00036475, 'samples': 747520, 'steps': 1459, 'loss/train': 3.7146434783935547}
-03/03/2022 15:08:10 - INFO - codeparrot_training - Step 1460: {'lr': 0.000365, 'samples': 748032, 'steps': 1460, 'loss/train': 4.706860065460205}
-03/03/2022 15:08:12 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/03/2022 15:08:15 - INFO - codeparrot_training - Step 1461: {'lr': 0.00036525, 'samples': 748544, 'steps': 1461, 'loss/train': 4.445798873901367}
-03/03/2022 15:08:18 - INFO - codeparrot_training - Step 1462: {'lr': 0.0003655, 'samples': 749056, 'steps': 1462, 'loss/train': 4.539623737335205}
-03/03/2022 15:08:20 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/03/2022 15:08:23 - INFO - codeparrot_training - Step 1463: {'lr': 0.00036575, 'samples': 749568, 'steps': 1463, 'loss/train': 4.721151828765869}
-03/03/2022 15:08:27 - INFO - codeparrot_training - Step 1464: {'lr': 0.000366, 'samples': 750080, 'steps': 1464, 'loss/train': 4.6012797355651855}
-03/03/2022 15:08:28 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/03/2022 15:08:32 - INFO - codeparrot_training - Step 1465: {'lr': 0.00036625000000000004, 'samples': 750592, 'steps': 1465, 'loss/train': 4.169576644897461}
-03/03/2022 15:08:35 - INFO - codeparrot_training - Step 1466: {'lr': 0.0003665, 'samples': 751104, 'steps': 1466, 'loss/train': 3.8605988025665283}
-03/03/2022 15:08:36 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/03/2022 15:08:40 - INFO - codeparrot_training - Step 1467: {'lr': 0.00036675000000000005, 'samples': 751616, 'steps': 1467, 'loss/train': 4.078520774841309}
-03/03/2022 15:08:43 - INFO - codeparrot_training - Step 1468: {'lr': 0.000367, 'samples': 752128, 'steps': 1468, 'loss/train': 4.675118446350098}
-03/03/2022 15:08:44 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/03/2022 15:08:48 - INFO - codeparrot_training - Step 1469: {'lr': 0.00036725, 'samples': 752640, 'steps': 1469, 'loss/train': 4.158109188079834}
-03/03/2022 15:08:52 - INFO - codeparrot_training - Step 1470: {'lr': 0.0003675, 'samples': 753152, 'steps': 1470, 'loss/train': 3.894350528717041}
-03/03/2022 15:08:52 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/03/2022 15:08:57 - INFO - codeparrot_training - Step 1471: {'lr': 0.00036775, 'samples': 753664, 'steps': 1471, 'loss/train': 3.148911476135254}
-03/03/2022 15:09:00 - INFO - codeparrot_training - Step 1472: {'lr': 0.000368, 'samples': 754176, 'steps': 1472, 'loss/train': 2.4368736743927}
-03/03/2022 15:09:01 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/03/2022 15:09:05 - INFO - codeparrot_training - Step 1473: {'lr': 0.00036825000000000003, 'samples': 754688, 'steps': 1473, 'loss/train': 4.8750319480896}
-03/03/2022 15:09:08 - INFO - codeparrot_training - Step 1474: {'lr': 0.0003685, 'samples': 755200, 'steps': 1474, 'loss/train': 4.30271053314209}
-03/03/2022 15:09:09 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/03/2022 15:09:14 - INFO - codeparrot_training - Step 1475: {'lr': 0.00036875000000000005, 'samples': 755712, 'steps': 1475, 'loss/train': 3.941826581954956}
-03/03/2022 15:09:17 - INFO - codeparrot_training - Step 1476: {'lr': 0.000369, 'samples': 756224, 'steps': 1476, 'loss/train': 4.268701553344727}
-03/03/2022 15:09:17 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/03/2022 15:09:22 - INFO - codeparrot_training - Step 1477: {'lr': 0.00036925, 'samples': 756736, 'steps': 1477, 'loss/train': 4.079792499542236}
-03/03/2022 15:09:25 - INFO - codeparrot_training - Step 1478: {'lr': 0.0003695, 'samples': 757248, 'steps': 1478, 'loss/train': 3.1567745208740234}
-03/03/2022 15:09:26 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/03/2022 15:09:31 - INFO - codeparrot_training - Step 1479: {'lr': 0.00036975, 'samples': 757760, 'steps': 1479, 'loss/train': 3.982180595397949}
-03/03/2022 15:09:34 - INFO - codeparrot_training - Step 1480: {'lr': 0.00037, 'samples': 758272, 'steps': 1480, 'loss/train': 3.835810422897339}
-03/03/2022 15:09:34 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 15:09:39 - INFO - codeparrot_training - Step 1481: {'lr': 0.00037025000000000003, 'samples': 758784, 'steps': 1481, 'loss/train': 3.477461099624634}
-03/03/2022 15:09:42 - INFO - codeparrot_training - Step 1482: {'lr': 0.0003705, 'samples': 759296, 'steps': 1482, 'loss/train': 4.739671230316162}
-03/03/2022 15:09:42 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/03/2022 15:09:47 - INFO - codeparrot_training - Step 1483: {'lr': 0.00037075000000000004, 'samples': 759808, 'steps': 1483, 'loss/train': 3.8007612228393555}
-03/03/2022 15:09:51 - INFO - codeparrot_training - Step 1484: {'lr': 0.000371, 'samples': 760320, 'steps': 1484, 'loss/train': 4.528865814208984}
-03/03/2022 15:09:51 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/03/2022 15:09:56 - INFO - codeparrot_training - Step 1485: {'lr': 0.00037125000000000005, 'samples': 760832, 'steps': 1485, 'loss/train': 4.351111888885498}
-03/03/2022 15:09:59 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/03/2022 15:10:01 - INFO - codeparrot_training - Step 1486: {'lr': 0.00037150000000000003, 'samples': 761344, 'steps': 1486, 'loss/train': 4.2383904457092285}
-03/03/2022 15:10:04 - INFO - codeparrot_training - Step 1487: {'lr': 0.00037175, 'samples': 761856, 'steps': 1487, 'loss/train': 3.099395751953125}
-03/03/2022 15:10:07 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/03/2022 15:10:09 - INFO - codeparrot_training - Step 1488: {'lr': 0.000372, 'samples': 762368, 'steps': 1488, 'loss/train': 3.2797293663024902}
-03/03/2022 15:10:13 - INFO - codeparrot_training - Step 1489: {'lr': 0.00037225, 'samples': 762880, 'steps': 1489, 'loss/train': 3.8778297901153564}
-03/03/2022 15:10:15 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/03/2022 15:10:18 - INFO - codeparrot_training - Step 1490: {'lr': 0.0003725, 'samples': 763392, 'steps': 1490, 'loss/train': 3.4822680950164795}
-03/03/2022 15:10:21 - INFO - codeparrot_training - Step 1491: {'lr': 0.00037275000000000003, 'samples': 763904, 'steps': 1491, 'loss/train': 3.91239857673645}
-03/03/2022 15:10:23 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/03/2022 15:10:26 - INFO - codeparrot_training - Step 1492: {'lr': 0.000373, 'samples': 764416, 'steps': 1492, 'loss/train': 3.9077584743499756}
-03/03/2022 15:10:30 - INFO - codeparrot_training - Step 1493: {'lr': 0.00037325000000000005, 'samples': 764928, 'steps': 1493, 'loss/train': 4.385066032409668}
-03/03/2022 15:10:32 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/03/2022 15:10:35 - INFO - codeparrot_training - Step 1494: {'lr': 0.0003735, 'samples': 765440, 'steps': 1494, 'loss/train': 3.0124974250793457}
-03/03/2022 15:10:38 - INFO - codeparrot_training - Step 1495: {'lr': 0.00037375000000000006, 'samples': 765952, 'steps': 1495, 'loss/train': 2.8615899085998535}
-03/03/2022 15:10:40 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/03/2022 15:10:43 - INFO - codeparrot_training - Step 1496: {'lr': 0.000374, 'samples': 766464, 'steps': 1496, 'loss/train': 4.435169219970703}
-03/03/2022 15:10:46 - INFO - codeparrot_training - Step 1497: {'lr': 0.00037425, 'samples': 766976, 'steps': 1497, 'loss/train': 4.5539751052856445}
-03/03/2022 15:10:49 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/03/2022 15:10:52 - INFO - codeparrot_training - Step 1498: {'lr': 0.0003745, 'samples': 767488, 'steps': 1498, 'loss/train': 4.482819557189941}
-03/03/2022 15:10:55 - INFO - codeparrot_training - Step 1499: {'lr': 0.00037475000000000003, 'samples': 768000, 'steps': 1499, 'loss/train': 3.6092755794525146}
-03/03/2022 15:10:57 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/03/2022 15:11:00 - INFO - codeparrot_training - Step 1500: {'lr': 0.000375, 'samples': 768512, 'steps': 1500, 'loss/train': 3.235640287399292}
-03/03/2022 15:11:03 - INFO - codeparrot_training - Step 1501: {'lr': 0.00037525, 'samples': 769024, 'steps': 1501, 'loss/train': 3.5360376834869385}
-03/03/2022 15:11:06 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/03/2022 15:11:08 - INFO - codeparrot_training - Step 1502: {'lr': 0.0003755, 'samples': 769536, 'steps': 1502, 'loss/train': 2.3084657192230225}
-03/03/2022 15:11:11 - INFO - codeparrot_training - Step 1503: {'lr': 0.00037575, 'samples': 770048, 'steps': 1503, 'loss/train': 3.9656982421875}
-03/03/2022 15:11:14 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/03/2022 15:11:17 - INFO - codeparrot_training - Step 1504: {'lr': 0.00037600000000000003, 'samples': 770560, 'steps': 1504, 'loss/train': 4.816207408905029}
-03/03/2022 15:11:20 - INFO - codeparrot_training - Step 1505: {'lr': 0.00037624999999999996, 'samples': 771072, 'steps': 1505, 'loss/train': 3.7710113525390625}
-03/03/2022 15:11:22 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/03/2022 15:11:25 - INFO - codeparrot_training - Step 1506: {'lr': 0.0003765, 'samples': 771584, 'steps': 1506, 'loss/train': 3.916992664337158}
-03/03/2022 15:11:28 - INFO - codeparrot_training - Step 1507: {'lr': 0.00037674999999999997, 'samples': 772096, 'steps': 1507, 'loss/train': 3.842498302459717}
-03/03/2022 15:11:30 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/03/2022 15:11:34 - INFO - codeparrot_training - Step 1508: {'lr': 0.000377, 'samples': 772608, 'steps': 1508, 'loss/train': 3.632445812225342}
-03/03/2022 15:11:37 - INFO - codeparrot_training - Step 1509: {'lr': 0.00037725, 'samples': 773120, 'steps': 1509, 'loss/train': 4.604870796203613}
-03/03/2022 15:11:39 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/03/2022 15:11:42 - INFO - codeparrot_training - Step 1510: {'lr': 0.0003775, 'samples': 773632, 'steps': 1510, 'loss/train': 2.283200740814209}
-03/03/2022 15:11:45 - INFO - codeparrot_training - Step 1511: {'lr': 0.00037775, 'samples': 774144, 'steps': 1511, 'loss/train': 3.5791454315185547}
-03/03/2022 15:11:48 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/03/2022 15:11:51 - INFO - codeparrot_training - Step 1512: {'lr': 0.000378, 'samples': 774656, 'steps': 1512, 'loss/train': 3.285102605819702}
-03/03/2022 15:11:54 - INFO - codeparrot_training - Step 1513: {'lr': 0.00037825, 'samples': 775168, 'steps': 1513, 'loss/train': 4.37850284576416}
-03/03/2022 15:11:56 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/03/2022 15:11:59 - INFO - codeparrot_training - Step 1514: {'lr': 0.0003785, 'samples': 775680, 'steps': 1514, 'loss/train': 4.18479585647583}
-03/03/2022 15:12:02 - INFO - codeparrot_training - Step 1515: {'lr': 0.00037874999999999996, 'samples': 776192, 'steps': 1515, 'loss/train': 3.8053348064422607}
-03/03/2022 15:12:04 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/03/2022 15:12:08 - INFO - codeparrot_training - Step 1516: {'lr': 0.000379, 'samples': 776704, 'steps': 1516, 'loss/train': 4.5604987144470215}
-03/03/2022 15:12:11 - INFO - codeparrot_training - Step 1517: {'lr': 0.00037925, 'samples': 777216, 'steps': 1517, 'loss/train': 3.2770392894744873}
-03/03/2022 15:12:12 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/03/2022 15:12:16 - INFO - codeparrot_training - Step 1518: {'lr': 0.0003795, 'samples': 777728, 'steps': 1518, 'loss/train': 4.6869425773620605}
-03/03/2022 15:12:19 - INFO - codeparrot_training - Step 1519: {'lr': 0.00037975, 'samples': 778240, 'steps': 1519, 'loss/train': 4.943699359893799}
-03/03/2022 15:12:21 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/03/2022 15:12:24 - INFO - codeparrot_training - Step 1520: {'lr': 0.00038, 'samples': 778752, 'steps': 1520, 'loss/train': 4.5217742919921875}
-03/03/2022 15:12:27 - INFO - codeparrot_training - Step 1521: {'lr': 0.00038025, 'samples': 779264, 'steps': 1521, 'loss/train': 3.4776947498321533}
-03/03/2022 15:12:29 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/03/2022 15:12:33 - INFO - codeparrot_training - Step 1522: {'lr': 0.00038050000000000003, 'samples': 779776, 'steps': 1522, 'loss/train': 3.51460862159729}
-03/03/2022 15:12:36 - INFO - codeparrot_training - Step 1523: {'lr': 0.00038075, 'samples': 780288, 'steps': 1523, 'loss/train': 4.309046268463135}
-03/03/2022 15:12:37 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/03/2022 15:12:41 - INFO - codeparrot_training - Step 1524: {'lr': 0.000381, 'samples': 780800, 'steps': 1524, 'loss/train': 3.4880378246307373}
-03/03/2022 15:12:44 - INFO - codeparrot_training - Step 1525: {'lr': 0.00038124999999999997, 'samples': 781312, 'steps': 1525, 'loss/train': 3.7793219089508057}
-03/03/2022 15:12:46 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/03/2022 15:12:50 - INFO - codeparrot_training - Step 1526: {'lr': 0.0003815, 'samples': 781824, 'steps': 1526, 'loss/train': 3.9242136478424072}
-03/03/2022 15:12:53 - INFO - codeparrot_training - Step 1527: {'lr': 0.00038175, 'samples': 782336, 'steps': 1527, 'loss/train': 3.7659497261047363}
-03/03/2022 15:12:56 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/03/2022 15:12:58 - INFO - codeparrot_training - Step 1528: {'lr': 0.000382, 'samples': 782848, 'steps': 1528, 'loss/train': 4.0172271728515625}
-03/03/2022 15:13:01 - INFO - codeparrot_training - Step 1529: {'lr': 0.00038225, 'samples': 783360, 'steps': 1529, 'loss/train': 3.6876139640808105}
-03/03/2022 15:13:04 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/03/2022 15:13:07 - INFO - codeparrot_training - Step 1530: {'lr': 0.00038250000000000003, 'samples': 783872, 'steps': 1530, 'loss/train': 4.323005199432373}
-03/03/2022 15:13:10 - INFO - codeparrot_training - Step 1531: {'lr': 0.00038275, 'samples': 784384, 'steps': 1531, 'loss/train': 2.826673746109009}
-03/03/2022 15:13:12 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/03/2022 15:13:15 - INFO - codeparrot_training - Step 1532: {'lr': 0.00038300000000000004, 'samples': 784896, 'steps': 1532, 'loss/train': 4.546938419342041}
-03/03/2022 15:13:18 - INFO - codeparrot_training - Step 1533: {'lr': 0.00038324999999999996, 'samples': 785408, 'steps': 1533, 'loss/train': 3.795086145401001}
-03/03/2022 15:13:20 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/03/2022 15:13:24 - INFO - codeparrot_training - Step 1534: {'lr': 0.0003835, 'samples': 785920, 'steps': 1534, 'loss/train': 4.857752323150635}
-03/03/2022 15:13:27 - INFO - codeparrot_training - Step 1535: {'lr': 0.00038375, 'samples': 786432, 'steps': 1535, 'loss/train': 3.7344937324523926}
-03/03/2022 15:13:30 - INFO - codeparrot_training - Step 1536: {'lr': 0.000384, 'samples': 786944, 'steps': 1536, 'loss/train': 4.928196907043457}
-03/03/2022 15:13:30 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/03/2022 15:13:35 - INFO - codeparrot_training - Step 1537: {'lr': 0.00038425, 'samples': 787456, 'steps': 1537, 'loss/train': 3.9834160804748535}
-03/03/2022 15:13:38 - INFO - codeparrot_training - Step 1538: {'lr': 0.0003845, 'samples': 787968, 'steps': 1538, 'loss/train': 3.138561248779297}
-03/03/2022 15:13:38 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/03/2022 15:13:43 - INFO - codeparrot_training - Step 1539: {'lr': 0.00038475, 'samples': 788480, 'steps': 1539, 'loss/train': 3.554269313812256}
-03/03/2022 15:13:47 - INFO - codeparrot_training - Step 1540: {'lr': 0.00038500000000000003, 'samples': 788992, 'steps': 1540, 'loss/train': 4.217238903045654}
-03/03/2022 15:13:47 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/03/2022 15:13:52 - INFO - codeparrot_training - Step 1541: {'lr': 0.00038525, 'samples': 789504, 'steps': 1541, 'loss/train': 4.2638044357299805}
-03/03/2022 15:13:55 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/03/2022 15:13:57 - INFO - codeparrot_training - Step 1542: {'lr': 0.0003855, 'samples': 790016, 'steps': 1542, 'loss/train': 4.403471946716309}
-03/03/2022 15:14:00 - INFO - codeparrot_training - Step 1543: {'lr': 0.00038574999999999997, 'samples': 790528, 'steps': 1543, 'loss/train': 3.3588995933532715}
-03/03/2022 15:14:03 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/03/2022 15:14:05 - INFO - codeparrot_training - Step 1544: {'lr': 0.000386, 'samples': 791040, 'steps': 1544, 'loss/train': 4.109154224395752}
-03/03/2022 15:14:09 - INFO - codeparrot_training - Step 1545: {'lr': 0.00038625, 'samples': 791552, 'steps': 1545, 'loss/train': 3.2273197174072266}
-03/03/2022 15:14:11 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/03/2022 15:14:14 - INFO - codeparrot_training - Step 1546: {'lr': 0.0003865, 'samples': 792064, 'steps': 1546, 'loss/train': 4.201442241668701}
-03/03/2022 15:14:17 - INFO - codeparrot_training - Step 1547: {'lr': 0.00038675, 'samples': 792576, 'steps': 1547, 'loss/train': 1.5830601453781128}
-03/03/2022 15:14:20 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/03/2022 15:14:22 - INFO - codeparrot_training - Step 1548: {'lr': 0.00038700000000000003, 'samples': 793088, 'steps': 1548, 'loss/train': 4.204220294952393}
-03/03/2022 15:14:26 - INFO - codeparrot_training - Step 1549: {'lr': 0.00038725, 'samples': 793600, 'steps': 1549, 'loss/train': 3.021789312362671}
-03/03/2022 15:14:28 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/03/2022 15:14:31 - INFO - codeparrot_training - Step 1550: {'lr': 0.00038750000000000004, 'samples': 794112, 'steps': 1550, 'loss/train': 3.7322466373443604}
-03/03/2022 15:14:34 - INFO - codeparrot_training - Step 1551: {'lr': 0.00038774999999999997, 'samples': 794624, 'steps': 1551, 'loss/train': 3.2621359825134277}
-03/03/2022 15:14:37 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/03/2022 15:14:39 - INFO - codeparrot_training - Step 1552: {'lr': 0.000388, 'samples': 795136, 'steps': 1552, 'loss/train': 3.510321855545044}
-03/03/2022 15:14:42 - INFO - codeparrot_training - Step 1553: {'lr': 0.00038825, 'samples': 795648, 'steps': 1553, 'loss/train': 3.8624253273010254}
-03/03/2022 15:14:45 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/03/2022 15:14:48 - INFO - codeparrot_training - Step 1554: {'lr': 0.0003885, 'samples': 796160, 'steps': 1554, 'loss/train': 4.156026840209961}
-03/03/2022 15:14:51 - INFO - codeparrot_training - Step 1555: {'lr': 0.00038875, 'samples': 796672, 'steps': 1555, 'loss/train': 3.379423141479492}
-03/03/2022 15:14:53 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/03/2022 15:14:56 - INFO - codeparrot_training - Step 1556: {'lr': 0.000389, 'samples': 797184, 'steps': 1556, 'loss/train': 4.1558098793029785}
-03/03/2022 15:14:59 - INFO - codeparrot_training - Step 1557: {'lr': 0.00038925, 'samples': 797696, 'steps': 1557, 'loss/train': 3.1854405403137207}
-03/03/2022 15:15:01 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/03/2022 15:15:04 - INFO - codeparrot_training - Step 1558: {'lr': 0.00038950000000000003, 'samples': 798208, 'steps': 1558, 'loss/train': 4.045464515686035}
-03/03/2022 15:15:08 - INFO - codeparrot_training - Step 1559: {'lr': 0.00038975, 'samples': 798720, 'steps': 1559, 'loss/train': 7.381725311279297}
-03/03/2022 15:15:10 - INFO - codeparrot_training - Skipping example with length 385 (seq_length=1024)
-03/03/2022 15:15:13 - INFO - codeparrot_training - Step 1560: {'lr': 0.00039000000000000005, 'samples': 799232, 'steps': 1560, 'loss/train': 3.5645205974578857}
-03/03/2022 15:15:16 - INFO - codeparrot_training - Step 1561: {'lr': 0.00039024999999999997, 'samples': 799744, 'steps': 1561, 'loss/train': 2.3492555618286133}
-03/03/2022 15:15:18 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/03/2022 15:15:21 - INFO - codeparrot_training - Step 1562: {'lr': 0.0003905, 'samples': 800256, 'steps': 1562, 'loss/train': 4.596646785736084}
-03/03/2022 15:15:24 - INFO - codeparrot_training - Step 1563: {'lr': 0.00039075, 'samples': 800768, 'steps': 1563, 'loss/train': 3.2182395458221436}
-03/03/2022 15:15:27 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/03/2022 15:15:30 - INFO - codeparrot_training - Step 1564: {'lr': 0.000391, 'samples': 801280, 'steps': 1564, 'loss/train': 4.244230270385742}
-03/03/2022 15:15:33 - INFO - codeparrot_training - Step 1565: {'lr': 0.00039125, 'samples': 801792, 'steps': 1565, 'loss/train': 3.9040040969848633}
-03/03/2022 15:15:35 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/03/2022 15:15:38 - INFO - codeparrot_training - Step 1566: {'lr': 0.00039150000000000003, 'samples': 802304, 'steps': 1566, 'loss/train': 2.477119207382202}
-03/03/2022 15:15:41 - INFO - codeparrot_training - Step 1567: {'lr': 0.00039175, 'samples': 802816, 'steps': 1567, 'loss/train': 4.116785049438477}
-03/03/2022 15:15:43 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/03/2022 15:15:46 - INFO - codeparrot_training - Step 1568: {'lr': 0.00039200000000000004, 'samples': 803328, 'steps': 1568, 'loss/train': 3.90573787689209}
-03/03/2022 15:15:50 - INFO - codeparrot_training - Step 1569: {'lr': 0.00039225, 'samples': 803840, 'steps': 1569, 'loss/train': 2.4844870567321777}
-03/03/2022 15:15:51 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/03/2022 15:15:55 - INFO - codeparrot_training - Step 1570: {'lr': 0.0003925, 'samples': 804352, 'steps': 1570, 'loss/train': 3.338627338409424}
-03/03/2022 15:15:58 - INFO - codeparrot_training - Step 1571: {'lr': 0.00039275, 'samples': 804864, 'steps': 1571, 'loss/train': 1.1468610763549805}
-03/03/2022 15:16:00 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/03/2022 15:16:03 - INFO - codeparrot_training - Step 1572: {'lr': 0.000393, 'samples': 805376, 'steps': 1572, 'loss/train': 3.844975471496582}
-03/03/2022 15:16:06 - INFO - codeparrot_training - Step 1573: {'lr': 0.00039325, 'samples': 805888, 'steps': 1573, 'loss/train': 3.7398221492767334}
-03/03/2022 15:16:08 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/03/2022 15:16:12 - INFO - codeparrot_training - Step 1574: {'lr': 0.0003935, 'samples': 806400, 'steps': 1574, 'loss/train': 4.145874500274658}
-03/03/2022 15:16:15 - INFO - codeparrot_training - Step 1575: {'lr': 0.00039375, 'samples': 806912, 'steps': 1575, 'loss/train': 4.008064270019531}
-03/03/2022 15:16:16 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/03/2022 15:16:20 - INFO - codeparrot_training - Step 1576: {'lr': 0.00039400000000000004, 'samples': 807424, 'steps': 1576, 'loss/train': 3.282827615737915}
-03/03/2022 15:16:23 - INFO - codeparrot_training - Step 1577: {'lr': 0.00039425, 'samples': 807936, 'steps': 1577, 'loss/train': 3.2250897884368896}
-03/03/2022 15:16:25 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/03/2022 15:16:29 - INFO - codeparrot_training - Step 1578: {'lr': 0.00039450000000000005, 'samples': 808448, 'steps': 1578, 'loss/train': 3.2866814136505127}
-03/03/2022 15:16:32 - INFO - codeparrot_training - Step 1579: {'lr': 0.00039474999999999997, 'samples': 808960, 'steps': 1579, 'loss/train': 1.6143156290054321}
-03/03/2022 15:16:34 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/03/2022 15:16:37 - INFO - codeparrot_training - Step 1580: {'lr': 0.000395, 'samples': 809472, 'steps': 1580, 'loss/train': 4.0041704177856445}
-03/03/2022 15:16:40 - INFO - codeparrot_training - Step 1581: {'lr': 0.00039525, 'samples': 809984, 'steps': 1581, 'loss/train': 2.606600284576416}
-03/03/2022 15:16:42 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/03/2022 15:16:45 - INFO - codeparrot_training - Step 1582: {'lr': 0.0003955, 'samples': 810496, 'steps': 1582, 'loss/train': 4.103724479675293}
-03/03/2022 15:16:49 - INFO - codeparrot_training - Step 1583: {'lr': 0.00039575, 'samples': 811008, 'steps': 1583, 'loss/train': 3.899157762527466}
-03/03/2022 15:16:50 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/03/2022 15:16:54 - INFO - codeparrot_training - Step 1584: {'lr': 0.00039600000000000003, 'samples': 811520, 'steps': 1584, 'loss/train': 4.094735145568848}
-03/03/2022 15:16:57 - INFO - codeparrot_training - Step 1585: {'lr': 0.00039625, 'samples': 812032, 'steps': 1585, 'loss/train': 3.7360873222351074}
-03/03/2022 15:16:58 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/03/2022 15:17:02 - INFO - codeparrot_training - Step 1586: {'lr': 0.00039650000000000004, 'samples': 812544, 'steps': 1586, 'loss/train': 2.2661588191986084}
-03/03/2022 15:17:05 - INFO - codeparrot_training - Step 1587: {'lr': 0.00039675, 'samples': 813056, 'steps': 1587, 'loss/train': 4.081903457641602}
-03/03/2022 15:17:07 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/03/2022 15:17:11 - INFO - codeparrot_training - Step 1588: {'lr': 0.00039700000000000005, 'samples': 813568, 'steps': 1588, 'loss/train': 4.26978063583374}
-03/03/2022 15:17:14 - INFO - codeparrot_training - Step 1589: {'lr': 0.00039725, 'samples': 814080, 'steps': 1589, 'loss/train': 4.824879169464111}
-03/03/2022 15:17:15 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/03/2022 15:17:19 - INFO - codeparrot_training - Step 1590: {'lr': 0.0003975, 'samples': 814592, 'steps': 1590, 'loss/train': 3.480339527130127}
-03/03/2022 15:17:22 - INFO - codeparrot_training - Step 1591: {'lr': 0.00039775, 'samples': 815104, 'steps': 1591, 'loss/train': 4.108184337615967}
-03/03/2022 15:17:23 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/03/2022 15:17:28 - INFO - codeparrot_training - Step 1592: {'lr': 0.000398, 'samples': 815616, 'steps': 1592, 'loss/train': 4.285973072052002}
-03/03/2022 15:17:31 - INFO - codeparrot_training - Step 1593: {'lr': 0.00039825, 'samples': 816128, 'steps': 1593, 'loss/train': 3.275076150894165}
-03/03/2022 15:17:31 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/03/2022 15:17:36 - INFO - codeparrot_training - Step 1594: {'lr': 0.00039850000000000004, 'samples': 816640, 'steps': 1594, 'loss/train': 3.0879600048065186}
-03/03/2022 15:17:39 - INFO - codeparrot_training - Step 1595: {'lr': 0.00039875, 'samples': 817152, 'steps': 1595, 'loss/train': 3.174454927444458}
-03/03/2022 15:17:40 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/03/2022 15:17:44 - INFO - codeparrot_training - Step 1596: {'lr': 0.00039900000000000005, 'samples': 817664, 'steps': 1596, 'loss/train': 3.5130112171173096}
-03/03/2022 15:17:47 - INFO - codeparrot_training - Step 1597: {'lr': 0.00039925000000000003, 'samples': 818176, 'steps': 1597, 'loss/train': 3.571528911590576}
-03/03/2022 15:17:48 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/03/2022 15:17:53 - INFO - codeparrot_training - Step 1598: {'lr': 0.0003995, 'samples': 818688, 'steps': 1598, 'loss/train': 6.576632499694824}
-03/03/2022 15:17:56 - INFO - codeparrot_training - Step 1599: {'lr': 0.00039975, 'samples': 819200, 'steps': 1599, 'loss/train': 4.470029354095459}
-03/03/2022 15:17:58 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/03/2022 15:18:01 - INFO - codeparrot_training - Step 1600: {'lr': 0.0004, 'samples': 819712, 'steps': 1600, 'loss/train': 4.19922399520874}
-03/03/2022 15:18:05 - INFO - codeparrot_training - Step 1601: {'lr': 0.00040025, 'samples': 820224, 'steps': 1601, 'loss/train': 4.240340709686279}
-03/03/2022 15:18:06 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/03/2022 15:18:10 - INFO - codeparrot_training - Step 1602: {'lr': 0.00040050000000000003, 'samples': 820736, 'steps': 1602, 'loss/train': 3.719184398651123}
-03/03/2022 15:18:13 - INFO - codeparrot_training - Step 1603: {'lr': 0.00040075, 'samples': 821248, 'steps': 1603, 'loss/train': 4.493873596191406}
-03/03/2022 15:18:15 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/03/2022 15:18:18 - INFO - codeparrot_training - Step 1604: {'lr': 0.00040100000000000004, 'samples': 821760, 'steps': 1604, 'loss/train': 3.7419326305389404}
-03/03/2022 15:18:21 - INFO - codeparrot_training - Step 1605: {'lr': 0.00040125, 'samples': 822272, 'steps': 1605, 'loss/train': 4.254170894622803}
-03/03/2022 15:18:23 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/03/2022 15:18:27 - INFO - codeparrot_training - Step 1606: {'lr': 0.00040150000000000006, 'samples': 822784, 'steps': 1606, 'loss/train': 4.3019256591796875}
-03/03/2022 15:18:30 - INFO - codeparrot_training - Step 1607: {'lr': 0.00040175, 'samples': 823296, 'steps': 1607, 'loss/train': 4.238136291503906}
-03/03/2022 15:18:31 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/03/2022 15:18:35 - INFO - codeparrot_training - Step 1608: {'lr': 0.000402, 'samples': 823808, 'steps': 1608, 'loss/train': 3.7276854515075684}
-03/03/2022 15:18:38 - INFO - codeparrot_training - Step 1609: {'lr': 0.00040225, 'samples': 824320, 'steps': 1609, 'loss/train': 4.083951950073242}
-03/03/2022 15:18:40 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/03/2022 15:18:44 - INFO - codeparrot_training - Step 1610: {'lr': 0.0004025, 'samples': 824832, 'steps': 1610, 'loss/train': 4.121634483337402}
-03/03/2022 15:18:47 - INFO - codeparrot_training - Step 1611: {'lr': 0.00040275, 'samples': 825344, 'steps': 1611, 'loss/train': 3.4871816635131836}
-03/03/2022 15:18:50 - INFO - codeparrot_training - Step 1612: {'lr': 0.00040300000000000004, 'samples': 825856, 'steps': 1612, 'loss/train': 3.1121580600738525}
-03/03/2022 15:18:51 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/03/2022 15:18:56 - INFO - codeparrot_training - Step 1613: {'lr': 0.00040325, 'samples': 826368, 'steps': 1613, 'loss/train': 4.2109150886535645}
-03/03/2022 15:18:59 - INFO - codeparrot_training - Step 1614: {'lr': 0.00040350000000000005, 'samples': 826880, 'steps': 1614, 'loss/train': 4.267260551452637}
-03/03/2022 15:18:59 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/03/2022 15:19:04 - INFO - codeparrot_training - Step 1615: {'lr': 0.00040375000000000003, 'samples': 827392, 'steps': 1615, 'loss/train': 3.589965581893921}
-03/03/2022 15:19:07 - INFO - codeparrot_training - Step 1616: {'lr': 0.000404, 'samples': 827904, 'steps': 1616, 'loss/train': 3.9033656120300293}
-03/03/2022 15:19:07 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/03/2022 15:19:12 - INFO - codeparrot_training - Step 1617: {'lr': 0.00040425, 'samples': 828416, 'steps': 1617, 'loss/train': 4.371466159820557}
-03/03/2022 15:19:15 - INFO - codeparrot_training - Step 1618: {'lr': 0.0004045, 'samples': 828928, 'steps': 1618, 'loss/train': 3.589682102203369}
-03/03/2022 15:19:16 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/03/2022 15:19:21 - INFO - codeparrot_training - Step 1619: {'lr': 0.00040475, 'samples': 829440, 'steps': 1619, 'loss/train': 3.161203384399414}
-03/03/2022 15:19:24 - INFO - codeparrot_training - Step 1620: {'lr': 0.00040500000000000003, 'samples': 829952, 'steps': 1620, 'loss/train': 4.257823467254639}
-03/03/2022 15:19:24 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/03/2022 15:19:29 - INFO - codeparrot_training - Step 1621: {'lr': 0.00040525, 'samples': 830464, 'steps': 1621, 'loss/train': 4.098337650299072}
-03/03/2022 15:19:32 - INFO - codeparrot_training - Step 1622: {'lr': 0.00040550000000000004, 'samples': 830976, 'steps': 1622, 'loss/train': 3.2562239170074463}
-03/03/2022 15:19:32 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/03/2022 15:19:37 - INFO - codeparrot_training - Step 1623: {'lr': 0.00040575, 'samples': 831488, 'steps': 1623, 'loss/train': 3.4186604022979736}
-03/03/2022 15:19:41 - INFO - codeparrot_training - Step 1624: {'lr': 0.00040600000000000006, 'samples': 832000, 'steps': 1624, 'loss/train': 3.073575258255005}
-03/03/2022 15:19:41 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/03/2022 15:19:46 - INFO - codeparrot_training - Step 1625: {'lr': 0.00040625000000000004, 'samples': 832512, 'steps': 1625, 'loss/train': 3.647516965866089}
-03/03/2022 15:19:49 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/03/2022 15:19:51 - INFO - codeparrot_training - Step 1626: {'lr': 0.00040649999999999996, 'samples': 833024, 'steps': 1626, 'loss/train': 3.6062047481536865}
-03/03/2022 15:19:54 - INFO - codeparrot_training - Step 1627: {'lr': 0.00040675, 'samples': 833536, 'steps': 1627, 'loss/train': 3.5969531536102295}
-03/03/2022 15:19:57 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/03/2022 15:19:59 - INFO - codeparrot_training - Step 1628: {'lr': 0.00040699999999999997, 'samples': 834048, 'steps': 1628, 'loss/train': 3.4551644325256348}
-03/03/2022 15:20:03 - INFO - codeparrot_training - Step 1629: {'lr': 0.00040725, 'samples': 834560, 'steps': 1629, 'loss/train': 3.528550386428833}
-03/03/2022 15:20:05 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/03/2022 15:20:08 - INFO - codeparrot_training - Step 1630: {'lr': 0.0004075, 'samples': 835072, 'steps': 1630, 'loss/train': 3.4015955924987793}
-03/03/2022 15:20:11 - INFO - codeparrot_training - Step 1631: {'lr': 0.00040775, 'samples': 835584, 'steps': 1631, 'loss/train': 3.4129886627197266}
-03/03/2022 15:20:14 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/03/2022 15:20:16 - INFO - codeparrot_training - Step 1632: {'lr': 0.000408, 'samples': 836096, 'steps': 1632, 'loss/train': 3.9364919662475586}
-03/03/2022 15:20:19 - INFO - codeparrot_training - Step 1633: {'lr': 0.00040825000000000003, 'samples': 836608, 'steps': 1633, 'loss/train': 3.2710466384887695}
-03/03/2022 15:20:22 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/03/2022 15:20:24 - INFO - codeparrot_training - Step 1634: {'lr': 0.0004085, 'samples': 837120, 'steps': 1634, 'loss/train': 4.535517692565918}
-03/03/2022 15:20:28 - INFO - codeparrot_training - Step 1635: {'lr': 0.00040875, 'samples': 837632, 'steps': 1635, 'loss/train': 4.544247627258301}
-03/03/2022 15:20:30 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/03/2022 15:20:33 - INFO - codeparrot_training - Step 1636: {'lr': 0.00040899999999999997, 'samples': 838144, 'steps': 1636, 'loss/train': 4.110836505889893}
-03/03/2022 15:20:36 - INFO - codeparrot_training - Step 1637: {'lr': 0.00040925, 'samples': 838656, 'steps': 1637, 'loss/train': 1.8042603731155396}
-03/03/2022 15:20:38 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/03/2022 15:20:41 - INFO - codeparrot_training - Step 1638: {'lr': 0.0004095, 'samples': 839168, 'steps': 1638, 'loss/train': 4.259596347808838}
-03/03/2022 15:20:44 - INFO - codeparrot_training - Step 1639: {'lr': 0.00040975, 'samples': 839680, 'steps': 1639, 'loss/train': 4.155637264251709}
-03/03/2022 15:20:46 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/03/2022 15:20:50 - INFO - codeparrot_training - Step 1640: {'lr': 0.00041, 'samples': 840192, 'steps': 1640, 'loss/train': 2.8649520874023438}
-03/03/2022 15:20:53 - INFO - codeparrot_training - Step 1641: {'lr': 0.00041025, 'samples': 840704, 'steps': 1641, 'loss/train': 3.9086496829986572}
-03/03/2022 15:20:55 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/03/2022 15:20:58 - INFO - codeparrot_training - Step 1642: {'lr': 0.0004105, 'samples': 841216, 'steps': 1642, 'loss/train': 3.142146348953247}
-03/03/2022 15:21:01 - INFO - codeparrot_training - Step 1643: {'lr': 0.00041075000000000004, 'samples': 841728, 'steps': 1643, 'loss/train': 4.127035140991211}
-03/03/2022 15:21:03 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/03/2022 15:21:06 - INFO - codeparrot_training - Step 1644: {'lr': 0.00041099999999999996, 'samples': 842240, 'steps': 1644, 'loss/train': 1.2069125175476074}
-03/03/2022 15:21:10 - INFO - codeparrot_training - Step 1645: {'lr': 0.00041125, 'samples': 842752, 'steps': 1645, 'loss/train': 3.94893217086792}
-03/03/2022 15:21:11 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/03/2022 15:21:15 - INFO - codeparrot_training - Step 1646: {'lr': 0.0004115, 'samples': 843264, 'steps': 1646, 'loss/train': 2.6652512550354004}
-03/03/2022 15:21:18 - INFO - codeparrot_training - Step 1647: {'lr': 0.00041175, 'samples': 843776, 'steps': 1647, 'loss/train': 3.434938907623291}
-03/03/2022 15:21:20 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/03/2022 15:21:24 - INFO - codeparrot_training - Step 1648: {'lr': 0.000412, 'samples': 844288, 'steps': 1648, 'loss/train': 3.532137632369995}
-03/03/2022 15:21:27 - INFO - codeparrot_training - Step 1649: {'lr': 0.00041225, 'samples': 844800, 'steps': 1649, 'loss/train': 3.8914690017700195}
-03/03/2022 15:21:28 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/03/2022 15:21:32 - INFO - codeparrot_training - Step 1650: {'lr': 0.0004125, 'samples': 845312, 'steps': 1650, 'loss/train': 4.398185729980469}
-03/03/2022 15:21:35 - INFO - codeparrot_training - Step 1651: {'lr': 0.00041275000000000003, 'samples': 845824, 'steps': 1651, 'loss/train': 2.951935291290283}
-03/03/2022 15:21:37 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/03/2022 15:21:41 - INFO - codeparrot_training - Step 1652: {'lr': 0.000413, 'samples': 846336, 'steps': 1652, 'loss/train': 2.694889783859253}
-03/03/2022 15:21:44 - INFO - codeparrot_training - Step 1653: {'lr': 0.00041325, 'samples': 846848, 'steps': 1653, 'loss/train': 1.3546243906021118}
-03/03/2022 15:21:45 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/03/2022 15:21:49 - INFO - codeparrot_training - Step 1654: {'lr': 0.00041349999999999997, 'samples': 847360, 'steps': 1654, 'loss/train': 3.1578609943389893}
-03/03/2022 15:21:52 - INFO - codeparrot_training - Step 1655: {'lr': 0.00041375, 'samples': 847872, 'steps': 1655, 'loss/train': 3.9147822856903076}
-03/03/2022 15:21:54 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/03/2022 15:21:57 - INFO - codeparrot_training - Step 1656: {'lr': 0.000414, 'samples': 848384, 'steps': 1656, 'loss/train': 3.3651390075683594}
-03/03/2022 15:22:01 - INFO - codeparrot_training - Step 1657: {'lr': 0.00041425, 'samples': 848896, 'steps': 1657, 'loss/train': 4.778948783874512}
-03/03/2022 15:22:02 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/03/2022 15:22:06 - INFO - codeparrot_training - Step 1658: {'lr': 0.0004145, 'samples': 849408, 'steps': 1658, 'loss/train': 4.195247650146484}
-03/03/2022 15:22:09 - INFO - codeparrot_training - Step 1659: {'lr': 0.00041475, 'samples': 849920, 'steps': 1659, 'loss/train': 4.073681354522705}
-03/03/2022 15:22:11 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/03/2022 15:22:14 - INFO - codeparrot_training - Step 1660: {'lr': 0.000415, 'samples': 850432, 'steps': 1660, 'loss/train': 4.1907572746276855}
-03/03/2022 15:22:17 - INFO - codeparrot_training - Step 1661: {'lr': 0.00041525000000000004, 'samples': 850944, 'steps': 1661, 'loss/train': 4.558657169342041}
-03/03/2022 15:22:19 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/03/2022 15:22:23 - INFO - codeparrot_training - Step 1662: {'lr': 0.00041549999999999996, 'samples': 851456, 'steps': 1662, 'loss/train': 2.9788718223571777}
-03/03/2022 15:22:26 - INFO - codeparrot_training - Step 1663: {'lr': 0.00041575, 'samples': 851968, 'steps': 1663, 'loss/train': 3.6902568340301514}
-03/03/2022 15:22:29 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/03/2022 15:22:31 - INFO - codeparrot_training - Step 1664: {'lr': 0.000416, 'samples': 852480, 'steps': 1664, 'loss/train': 3.099257230758667}
-03/03/2022 15:22:34 - INFO - codeparrot_training - Step 1665: {'lr': 0.00041625, 'samples': 852992, 'steps': 1665, 'loss/train': 4.143247127532959}
-03/03/2022 15:22:37 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/03/2022 15:22:40 - INFO - codeparrot_training - Step 1666: {'lr': 0.0004165, 'samples': 853504, 'steps': 1666, 'loss/train': 3.5870015621185303}
-03/03/2022 15:22:43 - INFO - codeparrot_training - Step 1667: {'lr': 0.00041675, 'samples': 854016, 'steps': 1667, 'loss/train': 5.4092583656311035}
-03/03/2022 15:22:46 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/03/2022 15:22:48 - INFO - codeparrot_training - Step 1668: {'lr': 0.000417, 'samples': 854528, 'steps': 1668, 'loss/train': 3.9599406719207764}
-03/03/2022 15:22:51 - INFO - codeparrot_training - Step 1669: {'lr': 0.00041725000000000003, 'samples': 855040, 'steps': 1669, 'loss/train': 3.46134352684021}
-03/03/2022 15:22:54 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/03/2022 15:22:57 - INFO - codeparrot_training - Step 1670: {'lr': 0.0004175, 'samples': 855552, 'steps': 1670, 'loss/train': 5.154891490936279}
-03/03/2022 15:23:00 - INFO - codeparrot_training - Step 1671: {'lr': 0.00041775000000000004, 'samples': 856064, 'steps': 1671, 'loss/train': 3.756866931915283}
-03/03/2022 15:23:02 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/03/2022 15:23:05 - INFO - codeparrot_training - Step 1672: {'lr': 0.00041799999999999997, 'samples': 856576, 'steps': 1672, 'loss/train': 2.8966963291168213}
-03/03/2022 15:23:08 - INFO - codeparrot_training - Step 1673: {'lr': 0.00041825, 'samples': 857088, 'steps': 1673, 'loss/train': 4.114925861358643}
-03/03/2022 15:23:11 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/03/2022 15:23:13 - INFO - codeparrot_training - Step 1674: {'lr': 0.0004185, 'samples': 857600, 'steps': 1674, 'loss/train': 3.2051870822906494}
-03/03/2022 15:23:17 - INFO - codeparrot_training - Step 1675: {'lr': 0.00041875, 'samples': 858112, 'steps': 1675, 'loss/train': 3.4225378036499023}
-03/03/2022 15:23:19 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/03/2022 15:23:22 - INFO - codeparrot_training - Step 1676: {'lr': 0.000419, 'samples': 858624, 'steps': 1676, 'loss/train': 4.339293956756592}
-03/03/2022 15:23:25 - INFO - codeparrot_training - Step 1677: {'lr': 0.00041925, 'samples': 859136, 'steps': 1677, 'loss/train': 6.490478992462158}
-03/03/2022 15:23:28 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/03/2022 15:23:30 - INFO - codeparrot_training - Step 1678: {'lr': 0.0004195, 'samples': 859648, 'steps': 1678, 'loss/train': 3.74222731590271}
-03/03/2022 15:23:34 - INFO - codeparrot_training - Step 1679: {'lr': 0.00041975000000000004, 'samples': 860160, 'steps': 1679, 'loss/train': 3.736689567565918}
-03/03/2022 15:23:36 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/03/2022 15:23:39 - INFO - codeparrot_training - Step 1680: {'lr': 0.00042, 'samples': 860672, 'steps': 1680, 'loss/train': 3.611518144607544}
-03/03/2022 15:23:42 - INFO - codeparrot_training - Step 1681: {'lr': 0.00042025, 'samples': 861184, 'steps': 1681, 'loss/train': 4.2163801193237305}
-03/03/2022 15:23:44 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/03/2022 15:23:47 - INFO - codeparrot_training - Step 1682: {'lr': 0.0004205, 'samples': 861696, 'steps': 1682, 'loss/train': 3.356593132019043}
-03/03/2022 15:23:50 - INFO - codeparrot_training - Step 1683: {'lr': 0.00042075, 'samples': 862208, 'steps': 1683, 'loss/train': 4.491826057434082}
-03/03/2022 15:23:53 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/03/2022 15:23:56 - INFO - codeparrot_training - Step 1684: {'lr': 0.000421, 'samples': 862720, 'steps': 1684, 'loss/train': 3.3760108947753906}
-03/03/2022 15:23:59 - INFO - codeparrot_training - Step 1685: {'lr': 0.00042125, 'samples': 863232, 'steps': 1685, 'loss/train': 4.584646701812744}
-03/03/2022 15:24:01 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/03/2022 15:24:04 - INFO - codeparrot_training - Step 1686: {'lr': 0.0004215, 'samples': 863744, 'steps': 1686, 'loss/train': 3.885138511657715}
-03/03/2022 15:24:07 - INFO - codeparrot_training - Step 1687: {'lr': 0.00042175000000000003, 'samples': 864256, 'steps': 1687, 'loss/train': 3.71675968170166}
-03/03/2022 15:24:09 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/03/2022 15:24:12 - INFO - codeparrot_training - Step 1688: {'lr': 0.000422, 'samples': 864768, 'steps': 1688, 'loss/train': 4.1364850997924805}
-03/03/2022 15:24:15 - INFO - codeparrot_training - Step 1689: {'lr': 0.00042225000000000005, 'samples': 865280, 'steps': 1689, 'loss/train': 3.7608449459075928}
-03/03/2022 15:24:18 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/03/2022 15:24:21 - INFO - codeparrot_training - Step 1690: {'lr': 0.00042249999999999997, 'samples': 865792, 'steps': 1690, 'loss/train': 3.461235523223877}
-03/03/2022 15:24:24 - INFO - codeparrot_training - Step 1691: {'lr': 0.00042275, 'samples': 866304, 'steps': 1691, 'loss/train': 3.6422181129455566}
-03/03/2022 15:24:27 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/03/2022 15:24:29 - INFO - codeparrot_training - Step 1692: {'lr': 0.000423, 'samples': 866816, 'steps': 1692, 'loss/train': 3.8520140647888184}
-03/03/2022 15:24:32 - INFO - codeparrot_training - Step 1693: {'lr': 0.00042325, 'samples': 867328, 'steps': 1693, 'loss/train': 3.8769209384918213}
-03/03/2022 15:24:35 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/03/2022 15:24:38 - INFO - codeparrot_training - Step 1694: {'lr': 0.0004235, 'samples': 867840, 'steps': 1694, 'loss/train': 4.164051532745361}
-03/03/2022 15:24:41 - INFO - codeparrot_training - Step 1695: {'lr': 0.00042375000000000003, 'samples': 868352, 'steps': 1695, 'loss/train': 3.7627975940704346}
-03/03/2022 15:24:43 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/03/2022 15:24:46 - INFO - codeparrot_training - Step 1696: {'lr': 0.000424, 'samples': 868864, 'steps': 1696, 'loss/train': 3.3928215503692627}
-03/03/2022 15:24:49 - INFO - codeparrot_training - Step 1697: {'lr': 0.00042425000000000004, 'samples': 869376, 'steps': 1697, 'loss/train': 4.1996283531188965}
-03/03/2022 15:24:52 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/03/2022 15:24:55 - INFO - codeparrot_training - Step 1698: {'lr': 0.0004245, 'samples': 869888, 'steps': 1698, 'loss/train': 3.942244052886963}
-03/03/2022 15:24:58 - INFO - codeparrot_training - Step 1699: {'lr': 0.00042475000000000005, 'samples': 870400, 'steps': 1699, 'loss/train': 3.671191930770874}
-03/03/2022 15:25:00 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/03/2022 15:25:03 - INFO - codeparrot_training - Step 1700: {'lr': 0.000425, 'samples': 870912, 'steps': 1700, 'loss/train': 3.7079269886016846}
-03/03/2022 15:25:06 - INFO - codeparrot_training - Step 1701: {'lr': 0.00042525, 'samples': 871424, 'steps': 1701, 'loss/train': 5.224290370941162}
-03/03/2022 15:25:09 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/03/2022 15:25:11 - INFO - codeparrot_training - Step 1702: {'lr': 0.0004255, 'samples': 871936, 'steps': 1702, 'loss/train': 3.76531982421875}
-03/03/2022 15:25:14 - INFO - codeparrot_training - Step 1703: {'lr': 0.00042575, 'samples': 872448, 'steps': 1703, 'loss/train': 3.520569324493408}
-03/03/2022 15:25:17 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/03/2022 15:25:20 - INFO - codeparrot_training - Step 1704: {'lr': 0.000426, 'samples': 872960, 'steps': 1704, 'loss/train': 3.5026602745056152}
-03/03/2022 15:25:23 - INFO - codeparrot_training - Step 1705: {'lr': 0.00042625000000000003, 'samples': 873472, 'steps': 1705, 'loss/train': 3.4497320652008057}
-03/03/2022 15:25:25 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/03/2022 15:25:28 - INFO - codeparrot_training - Step 1706: {'lr': 0.0004265, 'samples': 873984, 'steps': 1706, 'loss/train': 3.317208766937256}
-03/03/2022 15:25:31 - INFO - codeparrot_training - Step 1707: {'lr': 0.00042675000000000005, 'samples': 874496, 'steps': 1707, 'loss/train': 3.737887382507324}
-03/03/2022 15:25:34 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/03/2022 15:25:37 - INFO - codeparrot_training - Step 1708: {'lr': 0.000427, 'samples': 875008, 'steps': 1708, 'loss/train': 4.25682258605957}
-03/03/2022 15:25:40 - INFO - codeparrot_training - Step 1709: {'lr': 0.00042725, 'samples': 875520, 'steps': 1709, 'loss/train': 4.29536771774292}
-03/03/2022 15:25:42 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/03/2022 15:25:45 - INFO - codeparrot_training - Step 1710: {'lr': 0.0004275, 'samples': 876032, 'steps': 1710, 'loss/train': 3.959855318069458}
-03/03/2022 15:25:48 - INFO - codeparrot_training - Step 1711: {'lr': 0.00042775, 'samples': 876544, 'steps': 1711, 'loss/train': 3.5018670558929443}
-03/03/2022 15:25:50 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/03/2022 15:25:53 - INFO - codeparrot_training - Step 1712: {'lr': 0.000428, 'samples': 877056, 'steps': 1712, 'loss/train': 3.536062479019165}
-03/03/2022 15:25:56 - INFO - codeparrot_training - Step 1713: {'lr': 0.00042825000000000003, 'samples': 877568, 'steps': 1713, 'loss/train': 2.2983222007751465}
-03/03/2022 15:25:59 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/03/2022 15:26:02 - INFO - codeparrot_training - Step 1714: {'lr': 0.0004285, 'samples': 878080, 'steps': 1714, 'loss/train': 3.3023159503936768}
-03/03/2022 15:26:05 - INFO - codeparrot_training - Step 1715: {'lr': 0.00042875000000000004, 'samples': 878592, 'steps': 1715, 'loss/train': 3.105361223220825}
-03/03/2022 15:26:07 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/03/2022 15:26:10 - INFO - codeparrot_training - Step 1716: {'lr': 0.000429, 'samples': 879104, 'steps': 1716, 'loss/train': 4.056852340698242}
-03/03/2022 15:26:13 - INFO - codeparrot_training - Step 1717: {'lr': 0.00042925000000000005, 'samples': 879616, 'steps': 1717, 'loss/train': 3.6304948329925537}
-03/03/2022 15:26:15 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/03/2022 15:26:19 - INFO - codeparrot_training - Step 1718: {'lr': 0.0004295, 'samples': 880128, 'steps': 1718, 'loss/train': 3.6288976669311523}
-03/03/2022 15:26:22 - INFO - codeparrot_training - Step 1719: {'lr': 0.00042975, 'samples': 880640, 'steps': 1719, 'loss/train': 4.1409525871276855}
-03/03/2022 15:26:24 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/03/2022 15:26:27 - INFO - codeparrot_training - Step 1720: {'lr': 0.00043, 'samples': 881152, 'steps': 1720, 'loss/train': 3.690675973892212}
-03/03/2022 15:26:30 - INFO - codeparrot_training - Step 1721: {'lr': 0.00043025, 'samples': 881664, 'steps': 1721, 'loss/train': 4.356791019439697}
-03/03/2022 15:26:32 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/03/2022 15:26:35 - INFO - codeparrot_training - Step 1722: {'lr': 0.0004305, 'samples': 882176, 'steps': 1722, 'loss/train': 2.7275469303131104}
-03/03/2022 15:26:38 - INFO - codeparrot_training - Step 1723: {'lr': 0.00043075000000000003, 'samples': 882688, 'steps': 1723, 'loss/train': 3.7212345600128174}
-03/03/2022 15:26:40 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/03/2022 15:26:44 - INFO - codeparrot_training - Step 1724: {'lr': 0.000431, 'samples': 883200, 'steps': 1724, 'loss/train': 3.3754706382751465}
-03/03/2022 15:26:47 - INFO - codeparrot_training - Step 1725: {'lr': 0.00043125000000000005, 'samples': 883712, 'steps': 1725, 'loss/train': 4.620190143585205}
-03/03/2022 15:26:48 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/03/2022 15:26:52 - INFO - codeparrot_training - Step 1726: {'lr': 0.0004315, 'samples': 884224, 'steps': 1726, 'loss/train': 4.098268032073975}
-03/03/2022 15:26:55 - INFO - codeparrot_training - Step 1727: {'lr': 0.00043175, 'samples': 884736, 'steps': 1727, 'loss/train': 8.18599796295166}
-03/03/2022 15:26:58 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/03/2022 15:27:01 - INFO - codeparrot_training - Step 1728: {'lr': 0.000432, 'samples': 885248, 'steps': 1728, 'loss/train': 3.496340274810791}
-03/03/2022 15:27:04 - INFO - codeparrot_training - Step 1729: {'lr': 0.00043225, 'samples': 885760, 'steps': 1729, 'loss/train': 3.5704078674316406}
-03/03/2022 15:27:06 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/03/2022 15:27:09 - INFO - codeparrot_training - Step 1730: {'lr': 0.0004325, 'samples': 886272, 'steps': 1730, 'loss/train': 3.9318318367004395}
-03/03/2022 15:27:13 - INFO - codeparrot_training - Step 1731: {'lr': 0.00043275000000000003, 'samples': 886784, 'steps': 1731, 'loss/train': 3.648881435394287}
-03/03/2022 15:27:15 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/03/2022 15:27:18 - INFO - codeparrot_training - Step 1732: {'lr': 0.000433, 'samples': 887296, 'steps': 1732, 'loss/train': 2.6858880519866943}
-03/03/2022 15:27:21 - INFO - codeparrot_training - Step 1733: {'lr': 0.00043325000000000004, 'samples': 887808, 'steps': 1733, 'loss/train': 3.021738052368164}
-03/03/2022 15:27:23 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/03/2022 15:27:27 - INFO - codeparrot_training - Step 1734: {'lr': 0.0004335, 'samples': 888320, 'steps': 1734, 'loss/train': 3.8737881183624268}
-03/03/2022 15:27:30 - INFO - codeparrot_training - Step 1735: {'lr': 0.00043375000000000005, 'samples': 888832, 'steps': 1735, 'loss/train': 4.361507892608643}
-03/03/2022 15:27:33 - INFO - codeparrot_training - Step 1736: {'lr': 0.00043400000000000003, 'samples': 889344, 'steps': 1736, 'loss/train': 3.647573947906494}
-03/03/2022 15:27:34 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/03/2022 15:27:38 - INFO - codeparrot_training - Step 1737: {'lr': 0.00043425, 'samples': 889856, 'steps': 1737, 'loss/train': 3.487705707550049}
-03/03/2022 15:27:41 - INFO - codeparrot_training - Step 1738: {'lr': 0.0004345, 'samples': 890368, 'steps': 1738, 'loss/train': 3.882735252380371}
-03/03/2022 15:27:42 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/03/2022 15:27:47 - INFO - codeparrot_training - Step 1739: {'lr': 0.00043475, 'samples': 890880, 'steps': 1739, 'loss/train': 3.165846586227417}
-03/03/2022 15:27:50 - INFO - codeparrot_training - Step 1740: {'lr': 0.000435, 'samples': 891392, 'steps': 1740, 'loss/train': 2.254725694656372}
-03/03/2022 15:27:50 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/03/2022 15:27:55 - INFO - codeparrot_training - Step 1741: {'lr': 0.00043525000000000004, 'samples': 891904, 'steps': 1741, 'loss/train': 2.0590782165527344}
-03/03/2022 15:27:58 - INFO - codeparrot_training - Step 1742: {'lr': 0.0004355, 'samples': 892416, 'steps': 1742, 'loss/train': 4.130198955535889}
-03/03/2022 15:27:58 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/03/2022 15:28:04 - INFO - codeparrot_training - Step 1743: {'lr': 0.00043575000000000005, 'samples': 892928, 'steps': 1743, 'loss/train': 3.8559696674346924}
-03/03/2022 15:28:06 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/03/2022 15:28:09 - INFO - codeparrot_training - Step 1744: {'lr': 0.000436, 'samples': 893440, 'steps': 1744, 'loss/train': 3.884993314743042}
-03/03/2022 15:28:12 - INFO - codeparrot_training - Step 1745: {'lr': 0.00043625000000000006, 'samples': 893952, 'steps': 1745, 'loss/train': 3.838776111602783}
-03/03/2022 15:28:15 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/03/2022 15:28:17 - INFO - codeparrot_training - Step 1746: {'lr': 0.0004365, 'samples': 894464, 'steps': 1746, 'loss/train': 3.2877955436706543}
-03/03/2022 15:28:20 - INFO - codeparrot_training - Step 1747: {'lr': 0.00043675, 'samples': 894976, 'steps': 1747, 'loss/train': 4.131059169769287}
-03/03/2022 15:28:23 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/03/2022 15:28:25 - INFO - codeparrot_training - Step 1748: {'lr': 0.000437, 'samples': 895488, 'steps': 1748, 'loss/train': 3.5058960914611816}
-03/03/2022 15:28:29 - INFO - codeparrot_training - Step 1749: {'lr': 0.00043725000000000003, 'samples': 896000, 'steps': 1749, 'loss/train': 3.5843958854675293}
-03/03/2022 15:28:31 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/03/2022 15:28:34 - INFO - codeparrot_training - Step 1750: {'lr': 0.0004375, 'samples': 896512, 'steps': 1750, 'loss/train': 3.9815938472747803}
-03/03/2022 15:28:37 - INFO - codeparrot_training - Step 1751: {'lr': 0.00043775, 'samples': 897024, 'steps': 1751, 'loss/train': 3.6060678958892822}
-03/03/2022 15:28:39 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/03/2022 15:28:42 - INFO - codeparrot_training - Step 1752: {'lr': 0.000438, 'samples': 897536, 'steps': 1752, 'loss/train': 3.5824193954467773}
-03/03/2022 15:28:46 - INFO - codeparrot_training - Step 1753: {'lr': 0.00043825, 'samples': 898048, 'steps': 1753, 'loss/train': 1.004949927330017}
-03/03/2022 15:28:48 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/03/2022 15:28:51 - INFO - codeparrot_training - Step 1754: {'lr': 0.00043850000000000003, 'samples': 898560, 'steps': 1754, 'loss/train': 2.629119396209717}
-03/03/2022 15:28:54 - INFO - codeparrot_training - Step 1755: {'lr': 0.00043874999999999996, 'samples': 899072, 'steps': 1755, 'loss/train': 4.202991008758545}
-03/03/2022 15:28:56 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/03/2022 15:28:59 - INFO - codeparrot_training - Step 1756: {'lr': 0.000439, 'samples': 899584, 'steps': 1756, 'loss/train': 3.62184476852417}
-03/03/2022 15:29:03 - INFO - codeparrot_training - Step 1757: {'lr': 0.00043924999999999997, 'samples': 900096, 'steps': 1757, 'loss/train': 3.039698600769043}
-03/03/2022 15:29:06 - INFO - codeparrot_training - Step 1758: {'lr': 0.0004395, 'samples': 900608, 'steps': 1758, 'loss/train': 2.670175313949585}
-03/03/2022 15:29:06 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/03/2022 15:29:11 - INFO - codeparrot_training - Step 1759: {'lr': 0.00043975, 'samples': 901120, 'steps': 1759, 'loss/train': 3.6741206645965576}
-03/03/2022 15:29:14 - INFO - codeparrot_training - Step 1760: {'lr': 0.00044, 'samples': 901632, 'steps': 1760, 'loss/train': 3.6410982608795166}
-03/03/2022 15:29:15 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/03/2022 15:29:20 - INFO - codeparrot_training - Step 1761: {'lr': 0.00044025, 'samples': 902144, 'steps': 1761, 'loss/train': 2.68424654006958}
-03/03/2022 15:29:23 - INFO - codeparrot_training - Step 1762: {'lr': 0.00044050000000000003, 'samples': 902656, 'steps': 1762, 'loss/train': 4.119108200073242}
-03/03/2022 15:29:24 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/03/2022 15:29:28 - INFO - codeparrot_training - Step 1763: {'lr': 0.00044075, 'samples': 903168, 'steps': 1763, 'loss/train': 3.399466037750244}
-03/03/2022 15:29:31 - INFO - codeparrot_training - Step 1764: {'lr': 0.000441, 'samples': 903680, 'steps': 1764, 'loss/train': 1.1867115497589111}
-03/03/2022 15:29:32 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/03/2022 15:29:37 - INFO - codeparrot_training - Step 1765: {'lr': 0.00044124999999999996, 'samples': 904192, 'steps': 1765, 'loss/train': 3.64756178855896}
-03/03/2022 15:29:40 - INFO - codeparrot_training - Step 1766: {'lr': 0.0004415, 'samples': 904704, 'steps': 1766, 'loss/train': 3.3465452194213867}
-03/03/2022 15:29:41 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/03/2022 15:29:45 - INFO - codeparrot_training - Step 1767: {'lr': 0.00044175, 'samples': 905216, 'steps': 1767, 'loss/train': 3.5711829662323}
-03/03/2022 15:29:48 - INFO - codeparrot_training - Step 1768: {'lr': 0.000442, 'samples': 905728, 'steps': 1768, 'loss/train': 4.265261650085449}
-03/03/2022 15:29:49 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/03/2022 15:29:53 - INFO - codeparrot_training - Step 1769: {'lr': 0.00044225, 'samples': 906240, 'steps': 1769, 'loss/train': 5.817237854003906}
-03/03/2022 15:29:56 - INFO - codeparrot_training - Step 1770: {'lr': 0.0004425, 'samples': 906752, 'steps': 1770, 'loss/train': 4.571526527404785}
-03/03/2022 15:29:57 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/03/2022 15:30:02 - INFO - codeparrot_training - Step 1771: {'lr': 0.00044275, 'samples': 907264, 'steps': 1771, 'loss/train': 3.680689573287964}
-03/03/2022 15:30:05 - INFO - codeparrot_training - Step 1772: {'lr': 0.00044300000000000003, 'samples': 907776, 'steps': 1772, 'loss/train': 4.107189655303955}
-03/03/2022 15:30:06 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/03/2022 15:30:10 - INFO - codeparrot_training - Step 1773: {'lr': 0.00044325, 'samples': 908288, 'steps': 1773, 'loss/train': 3.7640373706817627}
-03/03/2022 15:30:13 - INFO - codeparrot_training - Step 1774: {'lr': 0.0004435, 'samples': 908800, 'steps': 1774, 'loss/train': 3.4179940223693848}
-03/03/2022 15:30:14 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/03/2022 15:30:18 - INFO - codeparrot_training - Step 1775: {'lr': 0.00044374999999999997, 'samples': 909312, 'steps': 1775, 'loss/train': 1.0886516571044922}
-03/03/2022 15:30:22 - INFO - codeparrot_training - Step 1776: {'lr': 0.000444, 'samples': 909824, 'steps': 1776, 'loss/train': 4.729548931121826}
-03/03/2022 15:30:22 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/03/2022 15:30:27 - INFO - codeparrot_training - Step 1777: {'lr': 0.00044425, 'samples': 910336, 'steps': 1777, 'loss/train': 2.85425066947937}
-03/03/2022 15:30:30 - INFO - codeparrot_training - Step 1778: {'lr': 0.0004445, 'samples': 910848, 'steps': 1778, 'loss/train': 2.7307944297790527}
-03/03/2022 15:30:31 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/03/2022 15:30:35 - INFO - codeparrot_training - Step 1779: {'lr': 0.00044475, 'samples': 911360, 'steps': 1779, 'loss/train': 3.718137264251709}
-03/03/2022 15:30:39 - INFO - codeparrot_training - Step 1780: {'lr': 0.00044500000000000003, 'samples': 911872, 'steps': 1780, 'loss/train': 3.6661293506622314}
-03/03/2022 15:30:40 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/03/2022 15:30:44 - INFO - codeparrot_training - Step 1781: {'lr': 0.00044525, 'samples': 912384, 'steps': 1781, 'loss/train': 3.7645955085754395}
-03/03/2022 15:30:47 - INFO - codeparrot_training - Step 1782: {'lr': 0.00044550000000000004, 'samples': 912896, 'steps': 1782, 'loss/train': 3.7916455268859863}
-03/03/2022 15:30:48 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/03/2022 15:30:52 - INFO - codeparrot_training - Step 1783: {'lr': 0.00044574999999999997, 'samples': 913408, 'steps': 1783, 'loss/train': 3.211923837661743}
-03/03/2022 15:30:55 - INFO - codeparrot_training - Step 1784: {'lr': 0.000446, 'samples': 913920, 'steps': 1784, 'loss/train': 3.6987788677215576}
-03/03/2022 15:30:56 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/03/2022 15:31:01 - INFO - codeparrot_training - Step 1785: {'lr': 0.00044625, 'samples': 914432, 'steps': 1785, 'loss/train': 2.0741822719573975}
-03/03/2022 15:31:04 - INFO - codeparrot_training - Step 1786: {'lr': 0.0004465, 'samples': 914944, 'steps': 1786, 'loss/train': 2.637977123260498}
-03/03/2022 15:31:05 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/03/2022 15:31:09 - INFO - codeparrot_training - Step 1787: {'lr': 0.00044675, 'samples': 915456, 'steps': 1787, 'loss/train': 3.3176441192626953}
-03/03/2022 15:31:12 - INFO - codeparrot_training - Step 1788: {'lr': 0.000447, 'samples': 915968, 'steps': 1788, 'loss/train': 8.905036926269531}
-03/03/2022 15:31:14 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/03/2022 15:31:18 - INFO - codeparrot_training - Step 1789: {'lr': 0.00044725, 'samples': 916480, 'steps': 1789, 'loss/train': 4.793331146240234}
-03/03/2022 15:31:21 - INFO - codeparrot_training - Step 1790: {'lr': 0.00044750000000000004, 'samples': 916992, 'steps': 1790, 'loss/train': 3.2318222522735596}
-03/03/2022 15:31:23 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/03/2022 15:31:26 - INFO - codeparrot_training - Step 1791: {'lr': 0.00044775, 'samples': 917504, 'steps': 1791, 'loss/train': 1.2780442237854004}
-03/03/2022 15:31:29 - INFO - codeparrot_training - Step 1792: {'lr': 0.000448, 'samples': 918016, 'steps': 1792, 'loss/train': 4.4922099113464355}
-03/03/2022 15:31:31 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/03/2022 15:31:35 - INFO - codeparrot_training - Step 1793: {'lr': 0.00044824999999999997, 'samples': 918528, 'steps': 1793, 'loss/train': 5.961709022521973}
-03/03/2022 15:31:38 - INFO - codeparrot_training - Step 1794: {'lr': 0.0004485, 'samples': 919040, 'steps': 1794, 'loss/train': 4.271733283996582}
-03/03/2022 15:31:41 - INFO - codeparrot_training - Step 1795: {'lr': 0.00044875, 'samples': 919552, 'steps': 1795, 'loss/train': 4.202448844909668}
-03/03/2022 15:31:41 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 15:31:46 - INFO - codeparrot_training - Step 1796: {'lr': 0.000449, 'samples': 920064, 'steps': 1796, 'loss/train': 3.2963552474975586}
-03/03/2022 15:31:49 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/03/2022 15:31:52 - INFO - codeparrot_training - Step 1797: {'lr': 0.00044925, 'samples': 920576, 'steps': 1797, 'loss/train': 3.6156511306762695}
-03/03/2022 15:31:55 - INFO - codeparrot_training - Step 1798: {'lr': 0.00044950000000000003, 'samples': 921088, 'steps': 1798, 'loss/train': 3.8857486248016357}
-03/03/2022 15:31:58 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/03/2022 15:32:00 - INFO - codeparrot_training - Step 1799: {'lr': 0.00044975, 'samples': 921600, 'steps': 1799, 'loss/train': 3.9517669677734375}
-03/03/2022 15:32:03 - INFO - codeparrot_training - Step 1800: {'lr': 0.00045000000000000004, 'samples': 922112, 'steps': 1800, 'loss/train': 3.953028678894043}
-03/03/2022 15:32:06 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/03/2022 15:32:08 - INFO - codeparrot_training - Step 1801: {'lr': 0.00045024999999999997, 'samples': 922624, 'steps': 1801, 'loss/train': 5.343773365020752}
-03/03/2022 15:32:12 - INFO - codeparrot_training - Step 1802: {'lr': 0.0004505, 'samples': 923136, 'steps': 1802, 'loss/train': 3.9360623359680176}
-03/03/2022 15:32:14 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/03/2022 15:32:17 - INFO - codeparrot_training - Step 1803: {'lr': 0.00045075, 'samples': 923648, 'steps': 1803, 'loss/train': 3.6178886890411377}
-03/03/2022 15:32:20 - INFO - codeparrot_training - Step 1804: {'lr': 0.000451, 'samples': 924160, 'steps': 1804, 'loss/train': 3.321953535079956}
-03/03/2022 15:32:23 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/03/2022 15:32:25 - INFO - codeparrot_training - Step 1805: {'lr': 0.00045125, 'samples': 924672, 'steps': 1805, 'loss/train': 3.360380172729492}
-03/03/2022 15:32:28 - INFO - codeparrot_training - Step 1806: {'lr': 0.0004515, 'samples': 925184, 'steps': 1806, 'loss/train': 4.78564977645874}
-03/03/2022 15:32:31 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/03/2022 15:32:34 - INFO - codeparrot_training - Step 1807: {'lr': 0.00045175, 'samples': 925696, 'steps': 1807, 'loss/train': 3.573976993560791}
-03/03/2022 15:32:37 - INFO - codeparrot_training - Step 1808: {'lr': 0.00045200000000000004, 'samples': 926208, 'steps': 1808, 'loss/train': 4.651330947875977}
-03/03/2022 15:32:39 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/03/2022 15:32:42 - INFO - codeparrot_training - Step 1809: {'lr': 0.00045225, 'samples': 926720, 'steps': 1809, 'loss/train': 4.338063716888428}
-03/03/2022 15:32:46 - INFO - codeparrot_training - Step 1810: {'lr': 0.00045250000000000005, 'samples': 927232, 'steps': 1810, 'loss/train': 3.876124382019043}
-03/03/2022 15:32:48 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/03/2022 15:32:51 - INFO - codeparrot_training - Step 1811: {'lr': 0.00045275, 'samples': 927744, 'steps': 1811, 'loss/train': 3.58648419380188}
-03/03/2022 15:32:54 - INFO - codeparrot_training - Step 1812: {'lr': 0.000453, 'samples': 928256, 'steps': 1812, 'loss/train': 3.863163709640503}
-03/03/2022 15:32:57 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/03/2022 15:32:59 - INFO - codeparrot_training - Step 1813: {'lr': 0.00045325, 'samples': 928768, 'steps': 1813, 'loss/train': 3.511075496673584}
-03/03/2022 15:33:02 - INFO - codeparrot_training - Step 1814: {'lr': 0.0004535, 'samples': 929280, 'steps': 1814, 'loss/train': 3.8160760402679443}
-03/03/2022 15:33:05 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/03/2022 15:33:08 - INFO - codeparrot_training - Step 1815: {'lr': 0.00045375, 'samples': 929792, 'steps': 1815, 'loss/train': 3.687553644180298}
-03/03/2022 15:33:11 - INFO - codeparrot_training - Step 1816: {'lr': 0.00045400000000000003, 'samples': 930304, 'steps': 1816, 'loss/train': 3.6537318229675293}
-03/03/2022 15:33:13 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/03/2022 15:33:16 - INFO - codeparrot_training - Step 1817: {'lr': 0.00045425, 'samples': 930816, 'steps': 1817, 'loss/train': 2.836833953857422}
-03/03/2022 15:33:19 - INFO - codeparrot_training - Step 1818: {'lr': 0.00045450000000000004, 'samples': 931328, 'steps': 1818, 'loss/train': 3.969243049621582}
-03/03/2022 15:33:21 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/03/2022 15:33:25 - INFO - codeparrot_training - Step 1819: {'lr': 0.00045475, 'samples': 931840, 'steps': 1819, 'loss/train': 4.125191688537598}
-03/03/2022 15:33:28 - INFO - codeparrot_training - Step 1820: {'lr': 0.000455, 'samples': 932352, 'steps': 1820, 'loss/train': 3.797196865081787}
-03/03/2022 15:33:30 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/03/2022 15:33:33 - INFO - codeparrot_training - Step 1821: {'lr': 0.00045525, 'samples': 932864, 'steps': 1821, 'loss/train': 3.736868143081665}
-03/03/2022 15:33:36 - INFO - codeparrot_training - Step 1822: {'lr': 0.0004555, 'samples': 933376, 'steps': 1822, 'loss/train': 3.7333502769470215}
-03/03/2022 15:33:38 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/03/2022 15:33:41 - INFO - codeparrot_training - Step 1823: {'lr': 0.00045575, 'samples': 933888, 'steps': 1823, 'loss/train': 3.956984519958496}
-03/03/2022 15:33:45 - INFO - codeparrot_training - Step 1824: {'lr': 0.000456, 'samples': 934400, 'steps': 1824, 'loss/train': 4.5288310050964355}
-03/03/2022 15:33:47 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/03/2022 15:33:50 - INFO - codeparrot_training - Step 1825: {'lr': 0.00045625, 'samples': 934912, 'steps': 1825, 'loss/train': 4.2684783935546875}
-03/03/2022 15:33:53 - INFO - codeparrot_training - Step 1826: {'lr': 0.00045650000000000004, 'samples': 935424, 'steps': 1826, 'loss/train': 3.128011465072632}
-03/03/2022 15:33:56 - INFO - codeparrot_training - Step 1827: {'lr': 0.00045675, 'samples': 935936, 'steps': 1827, 'loss/train': 3.609135627746582}
-03/03/2022 15:33:56 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/03/2022 15:34:02 - INFO - codeparrot_training - Step 1828: {'lr': 0.00045700000000000005, 'samples': 936448, 'steps': 1828, 'loss/train': 3.369703769683838}
-03/03/2022 15:34:05 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/03/2022 15:34:07 - INFO - codeparrot_training - Step 1829: {'lr': 0.00045725, 'samples': 936960, 'steps': 1829, 'loss/train': 3.9321675300598145}
-03/03/2022 15:34:10 - INFO - codeparrot_training - Step 1830: {'lr': 0.0004575, 'samples': 937472, 'steps': 1830, 'loss/train': 3.8493857383728027}
-03/03/2022 15:34:12 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/03/2022 15:34:15 - INFO - codeparrot_training - Step 1831: {'lr': 0.00045775, 'samples': 937984, 'steps': 1831, 'loss/train': 4.316078186035156}
-03/03/2022 15:34:18 - INFO - codeparrot_training - Step 1832: {'lr': 0.000458, 'samples': 938496, 'steps': 1832, 'loss/train': 3.823058605194092}
-03/03/2022 15:34:21 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/03/2022 15:34:24 - INFO - codeparrot_training - Step 1833: {'lr': 0.00045825, 'samples': 939008, 'steps': 1833, 'loss/train': 3.4598371982574463}
-03/03/2022 15:34:27 - INFO - codeparrot_training - Step 1834: {'lr': 0.00045850000000000003, 'samples': 939520, 'steps': 1834, 'loss/train': 3.3389430046081543}
-03/03/2022 15:34:29 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/03/2022 15:34:32 - INFO - codeparrot_training - Step 1835: {'lr': 0.00045875, 'samples': 940032, 'steps': 1835, 'loss/train': 3.106158494949341}
-03/03/2022 15:34:35 - INFO - codeparrot_training - Step 1836: {'lr': 0.00045900000000000004, 'samples': 940544, 'steps': 1836, 'loss/train': 2.701791524887085}
-03/03/2022 15:34:37 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/03/2022 15:34:40 - INFO - codeparrot_training - Step 1837: {'lr': 0.00045925, 'samples': 941056, 'steps': 1837, 'loss/train': 3.407944679260254}
-03/03/2022 15:34:44 - INFO - codeparrot_training - Step 1838: {'lr': 0.00045950000000000006, 'samples': 941568, 'steps': 1838, 'loss/train': 4.242276191711426}
-03/03/2022 15:34:45 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/03/2022 15:34:49 - INFO - codeparrot_training - Step 1839: {'lr': 0.00045975, 'samples': 942080, 'steps': 1839, 'loss/train': 3.5122146606445312}
-03/03/2022 15:34:52 - INFO - codeparrot_training - Step 1840: {'lr': 0.00046, 'samples': 942592, 'steps': 1840, 'loss/train': 0.9950838088989258}
-03/03/2022 15:34:54 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/03/2022 15:34:57 - INFO - codeparrot_training - Step 1841: {'lr': 0.00046025, 'samples': 943104, 'steps': 1841, 'loss/train': 4.217216491699219}
-03/03/2022 15:35:00 - INFO - codeparrot_training - Step 1842: {'lr': 0.0004605, 'samples': 943616, 'steps': 1842, 'loss/train': 2.7910196781158447}
-03/03/2022 15:35:02 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/03/2022 15:35:06 - INFO - codeparrot_training - Step 1843: {'lr': 0.00046075, 'samples': 944128, 'steps': 1843, 'loss/train': 3.5309927463531494}
-03/03/2022 15:35:09 - INFO - codeparrot_training - Step 1844: {'lr': 0.00046100000000000004, 'samples': 944640, 'steps': 1844, 'loss/train': 3.6949799060821533}
-03/03/2022 15:35:10 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/03/2022 15:35:14 - INFO - codeparrot_training - Step 1845: {'lr': 0.00046125, 'samples': 945152, 'steps': 1845, 'loss/train': 3.1792454719543457}
-03/03/2022 15:35:17 - INFO - codeparrot_training - Step 1846: {'lr': 0.00046150000000000005, 'samples': 945664, 'steps': 1846, 'loss/train': 4.417724609375}
-03/03/2022 15:35:19 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/03/2022 15:35:23 - INFO - codeparrot_training - Step 1847: {'lr': 0.00046175000000000003, 'samples': 946176, 'steps': 1847, 'loss/train': 3.801145315170288}
-03/03/2022 15:35:26 - INFO - codeparrot_training - Step 1848: {'lr': 0.000462, 'samples': 946688, 'steps': 1848, 'loss/train': 3.8281137943267822}
-03/03/2022 15:35:27 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/03/2022 15:35:31 - INFO - codeparrot_training - Step 1849: {'lr': 0.00046225, 'samples': 947200, 'steps': 1849, 'loss/train': 4.239955425262451}
-03/03/2022 15:35:34 - INFO - codeparrot_training - Step 1850: {'lr': 0.0004625, 'samples': 947712, 'steps': 1850, 'loss/train': 2.9147355556488037}
-03/03/2022 15:35:35 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/03/2022 15:35:39 - INFO - codeparrot_training - Step 1851: {'lr': 0.00046275, 'samples': 948224, 'steps': 1851, 'loss/train': 4.109053611755371}
-03/03/2022 15:35:43 - INFO - codeparrot_training - Step 1852: {'lr': 0.00046300000000000003, 'samples': 948736, 'steps': 1852, 'loss/train': 3.623049736022949}
-03/03/2022 15:35:44 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/03/2022 15:35:48 - INFO - codeparrot_training - Step 1853: {'lr': 0.00046325, 'samples': 949248, 'steps': 1853, 'loss/train': 4.153678894042969}
-03/03/2022 15:35:51 - INFO - codeparrot_training - Step 1854: {'lr': 0.00046350000000000004, 'samples': 949760, 'steps': 1854, 'loss/train': 2.6546082496643066}
-03/03/2022 15:35:52 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/03/2022 15:35:56 - INFO - codeparrot_training - Step 1855: {'lr': 0.00046375, 'samples': 950272, 'steps': 1855, 'loss/train': 3.3636629581451416}
-03/03/2022 15:35:59 - INFO - codeparrot_training - Step 1856: {'lr': 0.00046400000000000006, 'samples': 950784, 'steps': 1856, 'loss/train': 3.988624095916748}
-03/03/2022 15:36:00 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/03/2022 15:36:05 - INFO - codeparrot_training - Step 1857: {'lr': 0.00046425, 'samples': 951296, 'steps': 1857, 'loss/train': 2.0212666988372803}
-03/03/2022 15:36:08 - INFO - codeparrot_training - Step 1858: {'lr': 0.0004645, 'samples': 951808, 'steps': 1858, 'loss/train': 2.6467761993408203}
-03/03/2022 15:36:09 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/03/2022 15:36:13 - INFO - codeparrot_training - Step 1859: {'lr': 0.00046475, 'samples': 952320, 'steps': 1859, 'loss/train': 2.9667983055114746}
-03/03/2022 15:36:17 - INFO - codeparrot_training - Step 1860: {'lr': 0.000465, 'samples': 952832, 'steps': 1860, 'loss/train': 2.7909224033355713}
-03/03/2022 15:36:17 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/03/2022 15:36:22 - INFO - codeparrot_training - Step 1861: {'lr': 0.00046525, 'samples': 953344, 'steps': 1861, 'loss/train': 1.7720826864242554}
-03/03/2022 15:36:25 - INFO - codeparrot_training - Step 1862: {'lr': 0.00046550000000000004, 'samples': 953856, 'steps': 1862, 'loss/train': 3.453448534011841}
-03/03/2022 15:36:26 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/03/2022 15:36:30 - INFO - codeparrot_training - Step 1863: {'lr': 0.00046575, 'samples': 954368, 'steps': 1863, 'loss/train': 2.8469836711883545}
-03/03/2022 15:36:33 - INFO - codeparrot_training - Step 1864: {'lr': 0.00046600000000000005, 'samples': 954880, 'steps': 1864, 'loss/train': 4.5493597984313965}
-03/03/2022 15:36:34 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/03/2022 15:36:39 - INFO - codeparrot_training - Step 1865: {'lr': 0.00046625000000000003, 'samples': 955392, 'steps': 1865, 'loss/train': 3.703514337539673}
-03/03/2022 15:36:42 - INFO - codeparrot_training - Step 1866: {'lr': 0.0004665, 'samples': 955904, 'steps': 1866, 'loss/train': 4.083889484405518}
-03/03/2022 15:36:43 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/03/2022 15:36:47 - INFO - codeparrot_training - Step 1867: {'lr': 0.00046675, 'samples': 956416, 'steps': 1867, 'loss/train': 2.603015422821045}
-03/03/2022 15:36:50 - INFO - codeparrot_training - Step 1868: {'lr': 0.000467, 'samples': 956928, 'steps': 1868, 'loss/train': 3.677750587463379}
-03/03/2022 15:36:51 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/03/2022 15:36:56 - INFO - codeparrot_training - Step 1869: {'lr': 0.00046725, 'samples': 957440, 'steps': 1869, 'loss/train': 3.587224006652832}
-03/03/2022 15:36:59 - INFO - codeparrot_training - Step 1870: {'lr': 0.00046750000000000003, 'samples': 957952, 'steps': 1870, 'loss/train': 3.7286808490753174}
-03/03/2022 15:36:59 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/03/2022 15:37:04 - INFO - codeparrot_training - Step 1871: {'lr': 0.00046775, 'samples': 958464, 'steps': 1871, 'loss/train': 3.8604061603546143}
-03/03/2022 15:37:07 - INFO - codeparrot_training - Step 1872: {'lr': 0.00046800000000000005, 'samples': 958976, 'steps': 1872, 'loss/train': 3.772135019302368}
-03/03/2022 15:37:08 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/03/2022 15:37:12 - INFO - codeparrot_training - Step 1873: {'lr': 0.00046825, 'samples': 959488, 'steps': 1873, 'loss/train': 3.236870050430298}
-03/03/2022 15:37:15 - INFO - codeparrot_training - Step 1874: {'lr': 0.00046850000000000006, 'samples': 960000, 'steps': 1874, 'loss/train': 3.809223175048828}
-03/03/2022 15:37:17 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/03/2022 15:37:21 - INFO - codeparrot_training - Step 1875: {'lr': 0.00046875, 'samples': 960512, 'steps': 1875, 'loss/train': 2.7865772247314453}
-03/03/2022 15:37:24 - INFO - codeparrot_training - Step 1876: {'lr': 0.00046899999999999996, 'samples': 961024, 'steps': 1876, 'loss/train': 2.8295211791992188}
-03/03/2022 15:37:26 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/03/2022 15:37:29 - INFO - codeparrot_training - Step 1877: {'lr': 0.00046925, 'samples': 961536, 'steps': 1877, 'loss/train': 3.8288679122924805}
-03/03/2022 15:37:32 - INFO - codeparrot_training - Step 1878: {'lr': 0.0004695, 'samples': 962048, 'steps': 1878, 'loss/train': 3.853792190551758}
-03/03/2022 15:37:34 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/03/2022 15:37:38 - INFO - codeparrot_training - Step 1879: {'lr': 0.00046975, 'samples': 962560, 'steps': 1879, 'loss/train': 3.69453501701355}
-03/03/2022 15:37:41 - INFO - codeparrot_training - Step 1880: {'lr': 0.00047, 'samples': 963072, 'steps': 1880, 'loss/train': 3.0930612087249756}
-03/03/2022 15:37:43 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/03/2022 15:37:46 - INFO - codeparrot_training - Step 1881: {'lr': 0.00047025, 'samples': 963584, 'steps': 1881, 'loss/train': 2.7312281131744385}
-03/03/2022 15:37:49 - INFO - codeparrot_training - Step 1882: {'lr': 0.0004705, 'samples': 964096, 'steps': 1882, 'loss/train': 2.825073480606079}
-03/03/2022 15:37:51 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/03/2022 15:37:54 - INFO - codeparrot_training - Step 1883: {'lr': 0.00047075000000000003, 'samples': 964608, 'steps': 1883, 'loss/train': 4.372594356536865}
-03/03/2022 15:37:58 - INFO - codeparrot_training - Step 1884: {'lr': 0.000471, 'samples': 965120, 'steps': 1884, 'loss/train': 2.83687424659729}
-03/03/2022 15:37:59 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/03/2022 15:38:03 - INFO - codeparrot_training - Step 1885: {'lr': 0.00047125, 'samples': 965632, 'steps': 1885, 'loss/train': 3.1486153602600098}
-03/03/2022 15:38:06 - INFO - codeparrot_training - Step 1886: {'lr': 0.00047149999999999997, 'samples': 966144, 'steps': 1886, 'loss/train': 4.076030731201172}
-03/03/2022 15:38:07 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/03/2022 15:38:11 - INFO - codeparrot_training - Step 1887: {'lr': 0.00047175, 'samples': 966656, 'steps': 1887, 'loss/train': 3.1757619380950928}
-03/03/2022 15:38:14 - INFO - codeparrot_training - Step 1888: {'lr': 0.000472, 'samples': 967168, 'steps': 1888, 'loss/train': 2.746028184890747}
-03/03/2022 15:38:16 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/03/2022 15:38:20 - INFO - codeparrot_training - Step 1889: {'lr': 0.00047225, 'samples': 967680, 'steps': 1889, 'loss/train': 3.2801096439361572}
-03/03/2022 15:38:23 - INFO - codeparrot_training - Step 1890: {'lr': 0.0004725, 'samples': 968192, 'steps': 1890, 'loss/train': 3.9361536502838135}
-03/03/2022 15:38:24 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/03/2022 15:38:28 - INFO - codeparrot_training - Step 1891: {'lr': 0.00047275, 'samples': 968704, 'steps': 1891, 'loss/train': 3.272562265396118}
-03/03/2022 15:38:31 - INFO - codeparrot_training - Step 1892: {'lr': 0.000473, 'samples': 969216, 'steps': 1892, 'loss/train': 3.3093371391296387}
-03/03/2022 15:38:32 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/03/2022 15:38:36 - INFO - codeparrot_training - Step 1893: {'lr': 0.00047325000000000004, 'samples': 969728, 'steps': 1893, 'loss/train': 3.352339744567871}
-03/03/2022 15:38:40 - INFO - codeparrot_training - Step 1894: {'lr': 0.00047349999999999996, 'samples': 970240, 'steps': 1894, 'loss/train': 2.718169689178467}
-03/03/2022 15:38:40 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/03/2022 15:38:45 - INFO - codeparrot_training - Step 1895: {'lr': 0.00047375, 'samples': 970752, 'steps': 1895, 'loss/train': 4.432314395904541}
-03/03/2022 15:38:48 - INFO - codeparrot_training - Step 1896: {'lr': 0.000474, 'samples': 971264, 'steps': 1896, 'loss/train': 3.4355528354644775}
-03/03/2022 15:38:49 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/03/2022 15:38:53 - INFO - codeparrot_training - Step 1897: {'lr': 0.00047425, 'samples': 971776, 'steps': 1897, 'loss/train': 3.9646997451782227}
-03/03/2022 15:38:57 - INFO - codeparrot_training - Step 1898: {'lr': 0.0004745, 'samples': 972288, 'steps': 1898, 'loss/train': 3.4262611865997314}
-03/03/2022 15:38:57 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/03/2022 15:39:02 - INFO - codeparrot_training - Step 1899: {'lr': 0.00047475, 'samples': 972800, 'steps': 1899, 'loss/train': 3.51899790763855}
-03/03/2022 15:39:05 - INFO - codeparrot_training - Step 1900: {'lr': 0.000475, 'samples': 973312, 'steps': 1900, 'loss/train': 2.787599563598633}
-03/03/2022 15:39:06 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/03/2022 15:39:10 - INFO - codeparrot_training - Step 1901: {'lr': 0.00047525000000000003, 'samples': 973824, 'steps': 1901, 'loss/train': 4.00376033782959}
-03/03/2022 15:39:14 - INFO - codeparrot_training - Step 1902: {'lr': 0.0004755, 'samples': 974336, 'steps': 1902, 'loss/train': 3.8105556964874268}
-03/03/2022 15:39:14 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/03/2022 15:39:19 - INFO - codeparrot_training - Step 1903: {'lr': 0.00047575, 'samples': 974848, 'steps': 1903, 'loss/train': 3.312718152999878}
-03/03/2022 15:39:22 - INFO - codeparrot_training - Step 1904: {'lr': 0.00047599999999999997, 'samples': 975360, 'steps': 1904, 'loss/train': 3.1530582904815674}
-03/03/2022 15:39:23 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 15:39:27 - INFO - codeparrot_training - Step 1905: {'lr': 0.00047625, 'samples': 975872, 'steps': 1905, 'loss/train': 2.0286476612091064}
-03/03/2022 15:39:31 - INFO - codeparrot_training - Step 1906: {'lr': 0.0004765, 'samples': 976384, 'steps': 1906, 'loss/train': 3.4532697200775146}
-03/03/2022 15:39:32 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/03/2022 15:39:36 - INFO - codeparrot_training - Step 1907: {'lr': 0.00047675, 'samples': 976896, 'steps': 1907, 'loss/train': 3.871291160583496}
-03/03/2022 15:39:39 - INFO - codeparrot_training - Step 1908: {'lr': 0.000477, 'samples': 977408, 'steps': 1908, 'loss/train': 3.295064926147461}
-03/03/2022 15:39:40 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/03/2022 15:39:44 - INFO - codeparrot_training - Step 1909: {'lr': 0.00047725, 'samples': 977920, 'steps': 1909, 'loss/train': 3.638679265975952}
-03/03/2022 15:39:47 - INFO - codeparrot_training - Step 1910: {'lr': 0.0004775, 'samples': 978432, 'steps': 1910, 'loss/train': 2.9031922817230225}
-03/03/2022 15:39:48 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/03/2022 15:39:53 - INFO - codeparrot_training - Step 1911: {'lr': 0.00047775000000000004, 'samples': 978944, 'steps': 1911, 'loss/train': 3.960149049758911}
-03/03/2022 15:39:56 - INFO - codeparrot_training - Step 1912: {'lr': 0.00047799999999999996, 'samples': 979456, 'steps': 1912, 'loss/train': 3.321589946746826}
-03/03/2022 15:39:57 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/03/2022 15:40:01 - INFO - codeparrot_training - Step 1913: {'lr': 0.00047825, 'samples': 979968, 'steps': 1913, 'loss/train': 3.246011734008789}
-03/03/2022 15:40:04 - INFO - codeparrot_training - Step 1914: {'lr': 0.0004785, 'samples': 980480, 'steps': 1914, 'loss/train': 2.6056430339813232}
-03/03/2022 15:40:05 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/03/2022 15:40:10 - INFO - codeparrot_training - Step 1915: {'lr': 0.00047875, 'samples': 980992, 'steps': 1915, 'loss/train': 3.8123860359191895}
-03/03/2022 15:40:13 - INFO - codeparrot_training - Step 1916: {'lr': 0.000479, 'samples': 981504, 'steps': 1916, 'loss/train': 0.8929714560508728}
-03/03/2022 15:40:14 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/03/2022 15:40:18 - INFO - codeparrot_training - Step 1917: {'lr': 0.00047925, 'samples': 982016, 'steps': 1917, 'loss/train': 3.048044204711914}
-03/03/2022 15:40:21 - INFO - codeparrot_training - Step 1918: {'lr': 0.0004795, 'samples': 982528, 'steps': 1918, 'loss/train': 3.6655707359313965}
-03/03/2022 15:40:26 - INFO - codeparrot_training - Step 1919: {'lr': 0.00047975000000000003, 'samples': 983040, 'steps': 1919, 'loss/train': 3.565509557723999}
-03/03/2022 15:40:30 - INFO - codeparrot_training - Step 1920: {'lr': 0.00048, 'samples': 983552, 'steps': 1920, 'loss/train': 2.7780985832214355}
-03/03/2022 15:40:30 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/03/2022 15:40:35 - INFO - codeparrot_training - Step 1921: {'lr': 0.00048025000000000005, 'samples': 984064, 'steps': 1921, 'loss/train': 3.146402597427368}
-03/03/2022 15:40:38 - INFO - codeparrot_training - Step 1922: {'lr': 0.00048049999999999997, 'samples': 984576, 'steps': 1922, 'loss/train': 4.333209991455078}
-03/03/2022 15:40:38 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/03/2022 15:40:43 - INFO - codeparrot_training - Step 1923: {'lr': 0.00048075, 'samples': 985088, 'steps': 1923, 'loss/train': 3.043414354324341}
-03/03/2022 15:40:46 - INFO - codeparrot_training - Step 1924: {'lr': 0.000481, 'samples': 985600, 'steps': 1924, 'loss/train': 3.5705604553222656}
-03/03/2022 15:40:47 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/03/2022 15:40:52 - INFO - codeparrot_training - Step 1925: {'lr': 0.00048125, 'samples': 986112, 'steps': 1925, 'loss/train': 3.69821834564209}
-03/03/2022 15:40:55 - INFO - codeparrot_training - Step 1926: {'lr': 0.0004815, 'samples': 986624, 'steps': 1926, 'loss/train': 3.1315064430236816}
-03/03/2022 15:40:55 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/03/2022 15:41:00 - INFO - codeparrot_training - Step 1927: {'lr': 0.00048175000000000003, 'samples': 987136, 'steps': 1927, 'loss/train': 3.3206987380981445}
-03/03/2022 15:41:03 - INFO - codeparrot_training - Step 1928: {'lr': 0.000482, 'samples': 987648, 'steps': 1928, 'loss/train': 2.5814661979675293}
-03/03/2022 15:41:03 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/03/2022 15:41:08 - INFO - codeparrot_training - Step 1929: {'lr': 0.00048225000000000004, 'samples': 988160, 'steps': 1929, 'loss/train': 2.912954807281494}
-03/03/2022 15:41:12 - INFO - codeparrot_training - Step 1930: {'lr': 0.0004825, 'samples': 988672, 'steps': 1930, 'loss/train': 4.695540904998779}
-03/03/2022 15:41:12 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/03/2022 15:41:17 - INFO - codeparrot_training - Step 1931: {'lr': 0.00048275, 'samples': 989184, 'steps': 1931, 'loss/train': 4.0926408767700195}
-03/03/2022 15:41:20 - INFO - codeparrot_training - Step 1932: {'lr': 0.000483, 'samples': 989696, 'steps': 1932, 'loss/train': 3.6458230018615723}
-03/03/2022 15:41:20 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/03/2022 15:41:25 - INFO - codeparrot_training - Step 1933: {'lr': 0.00048325, 'samples': 990208, 'steps': 1933, 'loss/train': 2.4986352920532227}
-03/03/2022 15:41:28 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/03/2022 15:41:30 - INFO - codeparrot_training - Step 1934: {'lr': 0.0004835, 'samples': 990720, 'steps': 1934, 'loss/train': 2.9695796966552734}
-03/03/2022 15:41:34 - INFO - codeparrot_training - Step 1935: {'lr': 0.00048375, 'samples': 991232, 'steps': 1935, 'loss/train': 3.8234856128692627}
-03/03/2022 15:41:36 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/03/2022 15:41:39 - INFO - codeparrot_training - Step 1936: {'lr': 0.000484, 'samples': 991744, 'steps': 1936, 'loss/train': 3.6123037338256836}
-03/03/2022 15:41:42 - INFO - codeparrot_training - Step 1937: {'lr': 0.00048425000000000003, 'samples': 992256, 'steps': 1937, 'loss/train': 3.1480844020843506}
-03/03/2022 15:41:45 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/03/2022 15:41:47 - INFO - codeparrot_training - Step 1938: {'lr': 0.0004845, 'samples': 992768, 'steps': 1938, 'loss/train': 2.5109102725982666}
-03/03/2022 15:41:50 - INFO - codeparrot_training - Step 1939: {'lr': 0.00048475000000000005, 'samples': 993280, 'steps': 1939, 'loss/train': 4.0779266357421875}
-03/03/2022 15:41:53 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/03/2022 15:41:56 - INFO - codeparrot_training - Step 1940: {'lr': 0.00048499999999999997, 'samples': 993792, 'steps': 1940, 'loss/train': 3.4988856315612793}
-03/03/2022 15:41:59 - INFO - codeparrot_training - Step 1941: {'lr': 0.00048525, 'samples': 994304, 'steps': 1941, 'loss/train': 2.108307123184204}
-03/03/2022 15:42:01 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/03/2022 15:42:04 - INFO - codeparrot_training - Step 1942: {'lr': 0.0004855, 'samples': 994816, 'steps': 1942, 'loss/train': 3.5938289165496826}
-03/03/2022 15:42:07 - INFO - codeparrot_training - Step 1943: {'lr': 0.00048575, 'samples': 995328, 'steps': 1943, 'loss/train': 2.5148792266845703}
-03/03/2022 15:42:10 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/03/2022 15:42:13 - INFO - codeparrot_training - Step 1944: {'lr': 0.000486, 'samples': 995840, 'steps': 1944, 'loss/train': 2.513195037841797}
-03/03/2022 15:42:16 - INFO - codeparrot_training - Step 1945: {'lr': 0.00048625000000000003, 'samples': 996352, 'steps': 1945, 'loss/train': 3.3820157051086426}
-03/03/2022 15:42:18 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/03/2022 15:42:21 - INFO - codeparrot_training - Step 1946: {'lr': 0.0004865, 'samples': 996864, 'steps': 1946, 'loss/train': 3.358319044113159}
-03/03/2022 15:42:24 - INFO - codeparrot_training - Step 1947: {'lr': 0.00048675000000000004, 'samples': 997376, 'steps': 1947, 'loss/train': 3.156923770904541}
-03/03/2022 15:42:26 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/03/2022 15:42:29 - INFO - codeparrot_training - Step 1948: {'lr': 0.000487, 'samples': 997888, 'steps': 1948, 'loss/train': 4.169747352600098}
-03/03/2022 15:42:33 - INFO - codeparrot_training - Step 1949: {'lr': 0.00048725000000000005, 'samples': 998400, 'steps': 1949, 'loss/train': 2.972259283065796}
-03/03/2022 15:42:34 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/03/2022 15:42:38 - INFO - codeparrot_training - Step 1950: {'lr': 0.0004875, 'samples': 998912, 'steps': 1950, 'loss/train': 4.1069865226745605}
-03/03/2022 15:42:41 - INFO - codeparrot_training - Step 1951: {'lr': 0.00048775, 'samples': 999424, 'steps': 1951, 'loss/train': 3.1483869552612305}
-03/03/2022 15:42:43 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/03/2022 15:42:46 - INFO - codeparrot_training - Step 1952: {'lr': 0.000488, 'samples': 999936, 'steps': 1952, 'loss/train': 2.917391538619995}
-03/03/2022 15:42:50 - INFO - codeparrot_training - Step 1953: {'lr': 0.00048825, 'samples': 1000448, 'steps': 1953, 'loss/train': 3.2499265670776367}
-03/03/2022 15:42:51 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/03/2022 15:42:55 - INFO - codeparrot_training - Step 1954: {'lr': 0.0004885, 'samples': 1000960, 'steps': 1954, 'loss/train': 4.028998851776123}
-03/03/2022 15:42:58 - INFO - codeparrot_training - Step 1955: {'lr': 0.00048875, 'samples': 1001472, 'steps': 1955, 'loss/train': 3.3478951454162598}
-03/03/2022 15:43:00 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/03/2022 15:43:03 - INFO - codeparrot_training - Step 1956: {'lr': 0.000489, 'samples': 1001984, 'steps': 1956, 'loss/train': 3.5914785861968994}
-03/03/2022 15:43:06 - INFO - codeparrot_training - Step 1957: {'lr': 0.00048925, 'samples': 1002496, 'steps': 1957, 'loss/train': 0.8406473398208618}
-03/03/2022 15:43:08 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/03/2022 15:43:12 - INFO - codeparrot_training - Step 1958: {'lr': 0.0004895, 'samples': 1003008, 'steps': 1958, 'loss/train': 4.742589473724365}
-03/03/2022 15:43:15 - INFO - codeparrot_training - Step 1959: {'lr': 0.0004897500000000001, 'samples': 1003520, 'steps': 1959, 'loss/train': 3.799579620361328}
-03/03/2022 15:43:16 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/03/2022 15:43:20 - INFO - codeparrot_training - Step 1960: {'lr': 0.00049, 'samples': 1004032, 'steps': 1960, 'loss/train': 0.8839002847671509}
-03/03/2022 15:43:23 - INFO - codeparrot_training - Step 1961: {'lr': 0.00049025, 'samples': 1004544, 'steps': 1961, 'loss/train': 3.562156915664673}
-03/03/2022 15:43:25 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/03/2022 15:43:29 - INFO - codeparrot_training - Step 1962: {'lr': 0.0004905, 'samples': 1005056, 'steps': 1962, 'loss/train': 3.1393496990203857}
-03/03/2022 15:43:32 - INFO - codeparrot_training - Step 1963: {'lr': 0.0004907500000000001, 'samples': 1005568, 'steps': 1963, 'loss/train': 3.6644341945648193}
-03/03/2022 15:43:33 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/03/2022 15:43:37 - INFO - codeparrot_training - Step 1964: {'lr': 0.000491, 'samples': 1006080, 'steps': 1964, 'loss/train': 3.0365798473358154}
-03/03/2022 15:43:40 - INFO - codeparrot_training - Step 1965: {'lr': 0.00049125, 'samples': 1006592, 'steps': 1965, 'loss/train': 3.524775743484497}
-03/03/2022 15:43:41 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/03/2022 15:43:45 - INFO - codeparrot_training - Step 1966: {'lr': 0.0004915, 'samples': 1007104, 'steps': 1966, 'loss/train': 5.5112457275390625}
-03/03/2022 15:43:48 - INFO - codeparrot_training - Step 1967: {'lr': 0.00049175, 'samples': 1007616, 'steps': 1967, 'loss/train': 2.93630313873291}
-03/03/2022 15:43:50 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/03/2022 15:43:54 - INFO - codeparrot_training - Step 1968: {'lr': 0.000492, 'samples': 1008128, 'steps': 1968, 'loss/train': 3.8050034046173096}
-03/03/2022 15:43:57 - INFO - codeparrot_training - Step 1969: {'lr': 0.0004922500000000001, 'samples': 1008640, 'steps': 1969, 'loss/train': 3.544528007507324}
-03/03/2022 15:43:58 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/03/2022 15:44:02 - INFO - codeparrot_training - Step 1970: {'lr': 0.0004925, 'samples': 1009152, 'steps': 1970, 'loss/train': 3.3061039447784424}
-03/03/2022 15:44:05 - INFO - codeparrot_training - Step 1971: {'lr': 0.00049275, 'samples': 1009664, 'steps': 1971, 'loss/train': 4.317564487457275}
-03/03/2022 15:44:06 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/03/2022 15:44:11 - INFO - codeparrot_training - Step 1972: {'lr': 0.0004930000000000001, 'samples': 1010176, 'steps': 1972, 'loss/train': 3.416768789291382}
-03/03/2022 15:44:14 - INFO - codeparrot_training - Step 1973: {'lr': 0.00049325, 'samples': 1010688, 'steps': 1973, 'loss/train': 3.5689117908477783}
-03/03/2022 15:44:15 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/03/2022 15:44:19 - INFO - codeparrot_training - Step 1974: {'lr': 0.0004935, 'samples': 1011200, 'steps': 1974, 'loss/train': 3.1128177642822266}
-03/03/2022 15:44:22 - INFO - codeparrot_training - Step 1975: {'lr': 0.00049375, 'samples': 1011712, 'steps': 1975, 'loss/train': 2.972442626953125}
-03/03/2022 15:44:23 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/03/2022 15:44:27 - INFO - codeparrot_training - Step 1976: {'lr': 0.000494, 'samples': 1012224, 'steps': 1976, 'loss/train': 3.124418258666992}
-03/03/2022 15:44:30 - INFO - codeparrot_training - Step 1977: {'lr': 0.00049425, 'samples': 1012736, 'steps': 1977, 'loss/train': 2.5030174255371094}
-03/03/2022 15:44:31 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/03/2022 15:44:36 - INFO - codeparrot_training - Step 1978: {'lr': 0.0004945, 'samples': 1013248, 'steps': 1978, 'loss/train': 1.2461376190185547}
-03/03/2022 15:44:39 - INFO - codeparrot_training - Step 1979: {'lr': 0.0004947500000000001, 'samples': 1013760, 'steps': 1979, 'loss/train': 2.7604634761810303}
-03/03/2022 15:44:39 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/03/2022 15:44:44 - INFO - codeparrot_training - Step 1980: {'lr': 0.000495, 'samples': 1014272, 'steps': 1980, 'loss/train': 4.329571723937988}
-03/03/2022 15:44:47 - INFO - codeparrot_training - Step 1981: {'lr': 0.00049525, 'samples': 1014784, 'steps': 1981, 'loss/train': 2.192009449005127}
-03/03/2022 15:44:48 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/03/2022 15:44:53 - INFO - codeparrot_training - Step 1982: {'lr': 0.0004955, 'samples': 1015296, 'steps': 1982, 'loss/train': 2.292438507080078}
-03/03/2022 15:44:56 - INFO - codeparrot_training - Step 1983: {'lr': 0.00049575, 'samples': 1015808, 'steps': 1983, 'loss/train': 3.9385428428649902}
-03/03/2022 15:44:56 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/03/2022 15:45:01 - INFO - codeparrot_training - Step 1984: {'lr': 0.000496, 'samples': 1016320, 'steps': 1984, 'loss/train': 2.4057044982910156}
-03/03/2022 15:45:04 - INFO - codeparrot_training - Step 1985: {'lr': 0.0004962500000000001, 'samples': 1016832, 'steps': 1985, 'loss/train': 3.314926862716675}
-03/03/2022 15:45:04 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/03/2022 15:45:09 - INFO - codeparrot_training - Step 1986: {'lr': 0.0004965, 'samples': 1017344, 'steps': 1986, 'loss/train': 3.1913468837738037}
-03/03/2022 15:45:13 - INFO - codeparrot_training - Step 1987: {'lr': 0.00049675, 'samples': 1017856, 'steps': 1987, 'loss/train': 3.137672185897827}
-03/03/2022 15:45:13 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/03/2022 15:45:18 - INFO - codeparrot_training - Step 1988: {'lr': 0.000497, 'samples': 1018368, 'steps': 1988, 'loss/train': 3.4764881134033203}
-03/03/2022 15:45:21 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/03/2022 15:45:23 - INFO - codeparrot_training - Step 1989: {'lr': 0.0004972500000000001, 'samples': 1018880, 'steps': 1989, 'loss/train': 2.392765522003174}
-03/03/2022 15:45:26 - INFO - codeparrot_training - Step 1990: {'lr': 0.0004975, 'samples': 1019392, 'steps': 1990, 'loss/train': 2.664504051208496}
-03/03/2022 15:45:29 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/03/2022 15:45:32 - INFO - codeparrot_training - Step 1991: {'lr': 0.00049775, 'samples': 1019904, 'steps': 1991, 'loss/train': 3.0546810626983643}
-03/03/2022 15:45:35 - INFO - codeparrot_training - Step 1992: {'lr': 0.000498, 'samples': 1020416, 'steps': 1992, 'loss/train': 2.8693273067474365}
-03/03/2022 15:45:38 - INFO - codeparrot_training - Step 1993: {'lr': 0.00049825, 'samples': 1020928, 'steps': 1993, 'loss/train': 2.8332624435424805}
-03/03/2022 15:45:39 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/03/2022 15:45:43 - INFO - codeparrot_training - Step 1994: {'lr': 0.0004985, 'samples': 1021440, 'steps': 1994, 'loss/train': 3.599762439727783}
-03/03/2022 15:45:46 - INFO - codeparrot_training - Step 1995: {'lr': 0.0004987500000000001, 'samples': 1021952, 'steps': 1995, 'loss/train': 2.9485690593719482}
-03/03/2022 15:45:47 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/03/2022 15:45:52 - INFO - codeparrot_training - Step 1996: {'lr': 0.000499, 'samples': 1022464, 'steps': 1996, 'loss/train': 2.9960310459136963}
-03/03/2022 15:45:55 - INFO - codeparrot_training - Step 1997: {'lr': 0.00049925, 'samples': 1022976, 'steps': 1997, 'loss/train': 3.438770294189453}
-03/03/2022 15:45:55 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/03/2022 15:46:00 - INFO - codeparrot_training - Step 1998: {'lr': 0.0004995, 'samples': 1023488, 'steps': 1998, 'loss/train': 3.730217933654785}
-03/03/2022 15:46:03 - INFO - codeparrot_training - Step 1999: {'lr': 0.0004997500000000001, 'samples': 1024000, 'steps': 1999, 'loss/train': 3.169341564178467}
-03/03/2022 15:46:04 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/03/2022 15:46:09 - INFO - codeparrot_training - Step 2000: {'lr': 0.0005, 'samples': 1024512, 'steps': 2000, 'loss/train': 3.9695992469787598}
-03/03/2022 15:46:12 - INFO - codeparrot_training - Step 2001: {'lr': 0.0004999999999436769, 'samples': 1025024, 'steps': 2001, 'loss/train': 2.9300379753112793}
-03/03/2022 15:46:13 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/03/2022 15:46:17 - INFO - codeparrot_training - Step 2002: {'lr': 0.0004999999997747077, 'samples': 1025536, 'steps': 2002, 'loss/train': 3.7071943283081055}
-03/03/2022 15:46:20 - INFO - codeparrot_training - Step 2003: {'lr': 0.0004999999994930923, 'samples': 1026048, 'steps': 2003, 'loss/train': 3.0697338581085205}
-03/03/2022 15:46:21 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/03/2022 15:46:25 - INFO - codeparrot_training - Step 2004: {'lr': 0.0004999999990988309, 'samples': 1026560, 'steps': 2004, 'loss/train': 4.035585403442383}
-03/03/2022 15:46:29 - INFO - codeparrot_training - Step 2005: {'lr': 0.0004999999985919232, 'samples': 1027072, 'steps': 2005, 'loss/train': 3.3016936779022217}
-03/03/2022 15:46:30 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/03/2022 15:46:34 - INFO - codeparrot_training - Step 2006: {'lr': 0.0004999999979723695, 'samples': 1027584, 'steps': 2006, 'loss/train': 4.132771968841553}
-03/03/2022 15:46:37 - INFO - codeparrot_training - Step 2007: {'lr': 0.0004999999972401696, 'samples': 1028096, 'steps': 2007, 'loss/train': 4.007197856903076}
-03/03/2022 15:46:38 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/03/2022 15:46:42 - INFO - codeparrot_training - Step 2008: {'lr': 0.0004999999963953234, 'samples': 1028608, 'steps': 2008, 'loss/train': 1.783637523651123}
-03/03/2022 15:46:45 - INFO - codeparrot_training - Step 2009: {'lr': 0.0004999999954378312, 'samples': 1029120, 'steps': 2009, 'loss/train': 3.6063473224639893}
-03/03/2022 15:46:46 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/03/2022 15:46:51 - INFO - codeparrot_training - Step 2010: {'lr': 0.000499999994367693, 'samples': 1029632, 'steps': 2010, 'loss/train': 2.82340407371521}
-03/03/2022 15:46:54 - INFO - codeparrot_training - Step 2011: {'lr': 0.0004999999931849084, 'samples': 1030144, 'steps': 2011, 'loss/train': 2.665566921234131}
-03/03/2022 15:46:54 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/03/2022 15:46:59 - INFO - codeparrot_training - Step 2012: {'lr': 0.0004999999918894778, 'samples': 1030656, 'steps': 2012, 'loss/train': 3.4019744396209717}
-03/03/2022 15:47:02 - INFO - codeparrot_training - Step 2013: {'lr': 0.000499999990481401, 'samples': 1031168, 'steps': 2013, 'loss/train': 3.7687528133392334}
-03/03/2022 15:47:02 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/03/2022 15:47:08 - INFO - codeparrot_training - Step 2014: {'lr': 0.0004999999889606781, 'samples': 1031680, 'steps': 2014, 'loss/train': 3.2895429134368896}
-03/03/2022 15:47:11 - INFO - codeparrot_training - Step 2015: {'lr': 0.0004999999873273091, 'samples': 1032192, 'steps': 2015, 'loss/train': 2.7207114696502686}
-03/03/2022 15:47:11 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/03/2022 15:47:16 - INFO - codeparrot_training - Step 2016: {'lr': 0.000499999985581294, 'samples': 1032704, 'steps': 2016, 'loss/train': 3.1622705459594727}
-03/03/2022 15:47:19 - INFO - codeparrot_training - Step 2017: {'lr': 0.0004999999837226326, 'samples': 1033216, 'steps': 2017, 'loss/train': 2.5284972190856934}
-03/03/2022 15:47:19 - INFO - codeparrot_training - Skipping example with length 285 (seq_length=1024)
-03/03/2022 15:47:25 - INFO - codeparrot_training - Step 2018: {'lr': 0.0004999999817513252, 'samples': 1033728, 'steps': 2018, 'loss/train': 4.827317714691162}
-03/03/2022 15:47:28 - INFO - codeparrot_training - Step 2019: {'lr': 0.0004999999796673716, 'samples': 1034240, 'steps': 2019, 'loss/train': 3.9731600284576416}
-03/03/2022 15:47:29 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/03/2022 15:47:33 - INFO - codeparrot_training - Step 2020: {'lr': 0.0004999999774707719, 'samples': 1034752, 'steps': 2020, 'loss/train': 3.6044795513153076}
-03/03/2022 15:47:37 - INFO - codeparrot_training - Step 2021: {'lr': 0.0004999999751615261, 'samples': 1035264, 'steps': 2021, 'loss/train': 5.511720180511475}
-03/03/2022 15:47:38 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/03/2022 15:47:42 - INFO - codeparrot_training - Step 2022: {'lr': 0.0004999999727396341, 'samples': 1035776, 'steps': 2022, 'loss/train': 4.11544942855835}
-03/03/2022 15:47:45 - INFO - codeparrot_training - Step 2023: {'lr': 0.0004999999702050959, 'samples': 1036288, 'steps': 2023, 'loss/train': 3.4344191551208496}
-03/03/2022 15:47:46 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/03/2022 15:47:50 - INFO - codeparrot_training - Step 2024: {'lr': 0.0004999999675579118, 'samples': 1036800, 'steps': 2024, 'loss/train': 3.58003306388855}
-03/03/2022 15:47:53 - INFO - codeparrot_training - Step 2025: {'lr': 0.0004999999647980814, 'samples': 1037312, 'steps': 2025, 'loss/train': 4.878102779388428}
-03/03/2022 15:47:54 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/03/2022 15:47:59 - INFO - codeparrot_training - Step 2026: {'lr': 0.0004999999619256049, 'samples': 1037824, 'steps': 2026, 'loss/train': 3.9710001945495605}
-03/03/2022 15:48:02 - INFO - codeparrot_training - Step 2027: {'lr': 0.0004999999589404822, 'samples': 1038336, 'steps': 2027, 'loss/train': 3.3915817737579346}
-03/03/2022 15:48:03 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/03/2022 15:48:07 - INFO - codeparrot_training - Step 2028: {'lr': 0.0004999999558427136, 'samples': 1038848, 'steps': 2028, 'loss/train': 3.528927803039551}
-03/03/2022 15:48:10 - INFO - codeparrot_training - Step 2029: {'lr': 0.0004999999526322987, 'samples': 1039360, 'steps': 2029, 'loss/train': 0.5144878625869751}
-03/03/2022 15:48:11 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/03/2022 15:48:16 - INFO - codeparrot_training - Step 2030: {'lr': 0.0004999999493092377, 'samples': 1039872, 'steps': 2030, 'loss/train': 4.147453784942627}
-03/03/2022 15:48:19 - INFO - codeparrot_training - Step 2031: {'lr': 0.0004999999458735306, 'samples': 1040384, 'steps': 2031, 'loss/train': 2.4205193519592285}
-03/03/2022 15:48:19 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/03/2022 15:48:24 - INFO - codeparrot_training - Step 2032: {'lr': 0.0004999999423251774, 'samples': 1040896, 'steps': 2032, 'loss/train': 3.421488046646118}
-03/03/2022 15:48:27 - INFO - codeparrot_training - Step 2033: {'lr': 0.0004999999386641781, 'samples': 1041408, 'steps': 2033, 'loss/train': 3.241138458251953}
-03/03/2022 15:48:28 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/03/2022 15:48:33 - INFO - codeparrot_training - Step 2034: {'lr': 0.0004999999348905326, 'samples': 1041920, 'steps': 2034, 'loss/train': 4.374093532562256}
-03/03/2022 15:48:36 - INFO - codeparrot_training - Step 2035: {'lr': 0.000499999931004241, 'samples': 1042432, 'steps': 2035, 'loss/train': 3.3062870502471924}
-03/03/2022 15:48:37 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/03/2022 15:48:41 - INFO - codeparrot_training - Step 2036: {'lr': 0.0004999999270053034, 'samples': 1042944, 'steps': 2036, 'loss/train': 3.2776246070861816}
-03/03/2022 15:48:44 - INFO - codeparrot_training - Step 2037: {'lr': 0.0004999999228937196, 'samples': 1043456, 'steps': 2037, 'loss/train': 3.5980310440063477}
-03/03/2022 15:48:46 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/03/2022 15:48:50 - INFO - codeparrot_training - Step 2038: {'lr': 0.0004999999186694897, 'samples': 1043968, 'steps': 2038, 'loss/train': 4.058172225952148}
-03/03/2022 15:48:53 - INFO - codeparrot_training - Step 2039: {'lr': 0.0004999999143326137, 'samples': 1044480, 'steps': 2039, 'loss/train': 3.7193925380706787}
-03/03/2022 15:48:54 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/03/2022 15:48:58 - INFO - codeparrot_training - Step 2040: {'lr': 0.0004999999098830916, 'samples': 1044992, 'steps': 2040, 'loss/train': 2.873699426651001}
-03/03/2022 15:49:01 - INFO - codeparrot_training - Step 2041: {'lr': 0.0004999999053209235, 'samples': 1045504, 'steps': 2041, 'loss/train': 3.7037858963012695}
-03/03/2022 15:49:03 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/03/2022 15:49:07 - INFO - codeparrot_training - Step 2042: {'lr': 0.0004999999006461091, 'samples': 1046016, 'steps': 2042, 'loss/train': 2.888669490814209}
-03/03/2022 15:49:10 - INFO - codeparrot_training - Step 2043: {'lr': 0.0004999998958586487, 'samples': 1046528, 'steps': 2043, 'loss/train': 4.662944793701172}
-03/03/2022 15:49:12 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/03/2022 15:49:15 - INFO - codeparrot_training - Step 2044: {'lr': 0.0004999998909585423, 'samples': 1047040, 'steps': 2044, 'loss/train': 3.401412010192871}
-03/03/2022 15:49:18 - INFO - codeparrot_training - Step 2045: {'lr': 0.0004999998859457896, 'samples': 1047552, 'steps': 2045, 'loss/train': 4.20189094543457}
-03/03/2022 15:49:20 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/03/2022 15:49:24 - INFO - codeparrot_training - Step 2046: {'lr': 0.0004999998808203909, 'samples': 1048064, 'steps': 2046, 'loss/train': 4.263084888458252}
-03/03/2022 15:49:27 - INFO - codeparrot_training - Step 2047: {'lr': 0.0004999998755823462, 'samples': 1048576, 'steps': 2047, 'loss/train': 2.259582042694092}
-03/03/2022 15:49:28 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/03/2022 15:49:32 - INFO - codeparrot_training - Step 2048: {'lr': 0.0004999998702316553, 'samples': 1049088, 'steps': 2048, 'loss/train': 1.4496164321899414}
-03/03/2022 15:49:35 - INFO - codeparrot_training - Step 2049: {'lr': 0.0004999998647683184, 'samples': 1049600, 'steps': 2049, 'loss/train': 3.107677936553955}
-03/03/2022 15:49:37 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/03/2022 15:49:40 - INFO - codeparrot_training - Step 2050: {'lr': 0.0004999998591923353, 'samples': 1050112, 'steps': 2050, 'loss/train': 3.494973659515381}
-03/03/2022 15:49:44 - INFO - codeparrot_training - Step 2051: {'lr': 0.0004999998535037063, 'samples': 1050624, 'steps': 2051, 'loss/train': 2.54117751121521}
-03/03/2022 15:49:45 - INFO - codeparrot_training - Skipping example with length 233 (seq_length=1024)
-03/03/2022 15:49:49 - INFO - codeparrot_training - Step 2052: {'lr': 0.0004999998477024311, 'samples': 1051136, 'steps': 2052, 'loss/train': 2.789486885070801}
-03/03/2022 15:49:52 - INFO - codeparrot_training - Step 2053: {'lr': 0.0004999998417885099, 'samples': 1051648, 'steps': 2053, 'loss/train': 3.0454747676849365}
-03/03/2022 15:49:53 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/03/2022 15:49:57 - INFO - codeparrot_training - Step 2054: {'lr': 0.0004999998357619425, 'samples': 1052160, 'steps': 2054, 'loss/train': 3.8502964973449707}
-03/03/2022 15:50:00 - INFO - codeparrot_training - Step 2055: {'lr': 0.0004999998296227291, 'samples': 1052672, 'steps': 2055, 'loss/train': 1.7430517673492432}
-03/03/2022 15:50:01 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/03/2022 15:50:06 - INFO - codeparrot_training - Step 2056: {'lr': 0.0004999998233708697, 'samples': 1053184, 'steps': 2056, 'loss/train': 3.429997444152832}
-03/03/2022 15:50:09 - INFO - codeparrot_training - Step 2057: {'lr': 0.0004999998170063642, 'samples': 1053696, 'steps': 2057, 'loss/train': 4.1132307052612305}
-03/03/2022 15:50:10 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/03/2022 15:50:14 - INFO - codeparrot_training - Step 2058: {'lr': 0.0004999998105292126, 'samples': 1054208, 'steps': 2058, 'loss/train': 3.997450828552246}
-03/03/2022 15:50:17 - INFO - codeparrot_training - Step 2059: {'lr': 0.000499999803939415, 'samples': 1054720, 'steps': 2059, 'loss/train': 3.3158175945281982}
-03/03/2022 15:50:18 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/03/2022 15:50:22 - INFO - codeparrot_training - Step 2060: {'lr': 0.0004999997972369713, 'samples': 1055232, 'steps': 2060, 'loss/train': 3.253645896911621}
-03/03/2022 15:50:26 - INFO - codeparrot_training - Step 2061: {'lr': 0.0004999997904218816, 'samples': 1055744, 'steps': 2061, 'loss/train': 3.3187222480773926}
-03/03/2022 15:50:27 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/03/2022 15:50:31 - INFO - codeparrot_training - Step 2062: {'lr': 0.0004999997834941459, 'samples': 1056256, 'steps': 2062, 'loss/train': 4.691457271575928}
-03/03/2022 15:50:34 - INFO - codeparrot_training - Step 2063: {'lr': 0.000499999776453764, 'samples': 1056768, 'steps': 2063, 'loss/train': 4.1678242683410645}
-03/03/2022 15:50:35 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/03/2022 15:50:39 - INFO - codeparrot_training - Step 2064: {'lr': 0.0004999997693007361, 'samples': 1057280, 'steps': 2064, 'loss/train': 3.9383790493011475}
-03/03/2022 15:50:43 - INFO - codeparrot_training - Step 2065: {'lr': 0.0004999997620350622, 'samples': 1057792, 'steps': 2065, 'loss/train': 3.684743881225586}
-03/03/2022 15:50:44 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/03/2022 15:50:48 - INFO - codeparrot_training - Step 2066: {'lr': 0.0004999997546567423, 'samples': 1058304, 'steps': 2066, 'loss/train': 2.53251314163208}
-03/03/2022 15:50:51 - INFO - codeparrot_training - Step 2067: {'lr': 0.0004999997471657763, 'samples': 1058816, 'steps': 2067, 'loss/train': 3.7877984046936035}
-03/03/2022 15:50:52 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/03/2022 15:50:56 - INFO - codeparrot_training - Step 2068: {'lr': 0.0004999997395621642, 'samples': 1059328, 'steps': 2068, 'loss/train': 1.0695316791534424}
-03/03/2022 15:51:00 - INFO - codeparrot_training - Step 2069: {'lr': 0.0004999997318459064, 'samples': 1059840, 'steps': 2069, 'loss/train': 4.3450703620910645}
-03/03/2022 15:51:00 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/03/2022 15:51:05 - INFO - codeparrot_training - Step 2070: {'lr': 0.0004999997240170023, 'samples': 1060352, 'steps': 2070, 'loss/train': 4.308434963226318}
-03/03/2022 15:51:08 - INFO - codeparrot_training - Step 2071: {'lr': 0.0004999997160754522, 'samples': 1060864, 'steps': 2071, 'loss/train': 2.7694506645202637}
-03/03/2022 15:51:09 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/03/2022 15:51:13 - INFO - codeparrot_training - Step 2072: {'lr': 0.0004999997080212561, 'samples': 1061376, 'steps': 2072, 'loss/train': 1.8834242820739746}
-03/03/2022 15:51:16 - INFO - codeparrot_training - Step 2073: {'lr': 0.000499999699854414, 'samples': 1061888, 'steps': 2073, 'loss/train': 3.068740129470825}
-03/03/2022 15:51:17 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/03/2022 15:51:22 - INFO - codeparrot_training - Step 2074: {'lr': 0.0004999996915749259, 'samples': 1062400, 'steps': 2074, 'loss/train': 4.012972354888916}
-03/03/2022 15:51:25 - INFO - codeparrot_training - Step 2075: {'lr': 0.0004999996831827918, 'samples': 1062912, 'steps': 2075, 'loss/train': 3.255206823348999}
-03/03/2022 15:51:26 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/03/2022 15:51:30 - INFO - codeparrot_training - Step 2076: {'lr': 0.0004999996746780117, 'samples': 1063424, 'steps': 2076, 'loss/train': 3.5504531860351562}
-03/03/2022 15:51:33 - INFO - codeparrot_training - Step 2077: {'lr': 0.0004999996660605856, 'samples': 1063936, 'steps': 2077, 'loss/train': 3.7585928440093994}
-03/03/2022 15:51:34 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/03/2022 15:51:38 - INFO - codeparrot_training - Step 2078: {'lr': 0.0004999996573305135, 'samples': 1064448, 'steps': 2078, 'loss/train': 2.2548882961273193}
-03/03/2022 15:51:42 - INFO - codeparrot_training - Step 2079: {'lr': 0.0004999996484877955, 'samples': 1064960, 'steps': 2079, 'loss/train': 4.103363990783691}
-03/03/2022 15:51:42 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/03/2022 15:51:47 - INFO - codeparrot_training - Step 2080: {'lr': 0.0004999996395324313, 'samples': 1065472, 'steps': 2080, 'loss/train': 3.4765408039093018}
-03/03/2022 15:51:50 - INFO - codeparrot_training - Step 2081: {'lr': 0.0004999996304644213, 'samples': 1065984, 'steps': 2081, 'loss/train': 3.9804258346557617}
-03/03/2022 15:51:50 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/03/2022 15:51:55 - INFO - codeparrot_training - Step 2082: {'lr': 0.0004999996212837653, 'samples': 1066496, 'steps': 2082, 'loss/train': 3.8717150688171387}
-03/03/2022 15:51:58 - INFO - codeparrot_training - Step 2083: {'lr': 0.0004999996119904633, 'samples': 1067008, 'steps': 2083, 'loss/train': 3.8754525184631348}
-03/03/2022 15:51:59 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/03/2022 15:52:04 - INFO - codeparrot_training - Step 2084: {'lr': 0.0004999996025845154, 'samples': 1067520, 'steps': 2084, 'loss/train': 3.614020824432373}
-03/03/2022 15:52:07 - INFO - codeparrot_training - Step 2085: {'lr': 0.0004999995930659215, 'samples': 1068032, 'steps': 2085, 'loss/train': 2.7679386138916016}
-03/03/2022 15:52:07 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/03/2022 15:52:12 - INFO - codeparrot_training - Step 2086: {'lr': 0.0004999995834346815, 'samples': 1068544, 'steps': 2086, 'loss/train': 3.5978920459747314}
-03/03/2022 15:52:15 - INFO - codeparrot_training - Step 2087: {'lr': 0.0004999995736907957, 'samples': 1069056, 'steps': 2087, 'loss/train': 3.90876841545105}
-03/03/2022 15:52:15 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/03/2022 15:52:20 - INFO - codeparrot_training - Step 2088: {'lr': 0.000499999563834264, 'samples': 1069568, 'steps': 2088, 'loss/train': 3.1678805351257324}
-03/03/2022 15:52:24 - INFO - codeparrot_training - Step 2089: {'lr': 0.0004999995538650862, 'samples': 1070080, 'steps': 2089, 'loss/train': 3.1336045265197754}
-03/03/2022 15:52:24 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/03/2022 15:52:29 - INFO - codeparrot_training - Step 2090: {'lr': 0.0004999995437832626, 'samples': 1070592, 'steps': 2090, 'loss/train': 3.454817295074463}
-03/03/2022 15:52:32 - INFO - codeparrot_training - Step 2091: {'lr': 0.0004999995335887929, 'samples': 1071104, 'steps': 2091, 'loss/train': 3.1001510620117188}
-03/03/2022 15:52:32 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/03/2022 15:52:37 - INFO - codeparrot_training - Step 2092: {'lr': 0.0004999995232816774, 'samples': 1071616, 'steps': 2092, 'loss/train': 3.782294511795044}
-03/03/2022 15:52:40 - INFO - codeparrot_training - Step 2093: {'lr': 0.000499999512861916, 'samples': 1072128, 'steps': 2093, 'loss/train': 3.420549154281616}
-03/03/2022 15:52:41 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/03/2022 15:52:46 - INFO - codeparrot_training - Step 2094: {'lr': 0.0004999995023295086, 'samples': 1072640, 'steps': 2094, 'loss/train': 3.2693636417388916}
-03/03/2022 15:52:49 - INFO - codeparrot_training - Step 2095: {'lr': 0.0004999994916844552, 'samples': 1073152, 'steps': 2095, 'loss/train': 2.378378391265869}
-03/03/2022 15:52:49 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/03/2022 15:52:54 - INFO - codeparrot_training - Step 2096: {'lr': 0.0004999994809267561, 'samples': 1073664, 'steps': 2096, 'loss/train': 3.894771099090576}
-03/03/2022 15:52:57 - INFO - codeparrot_training - Step 2097: {'lr': 0.0004999994700564109, 'samples': 1074176, 'steps': 2097, 'loss/train': 4.1221466064453125}
-03/03/2022 15:52:57 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/03/2022 15:53:02 - INFO - codeparrot_training - Step 2098: {'lr': 0.0004999994590734199, 'samples': 1074688, 'steps': 2098, 'loss/train': 4.020200252532959}
-03/03/2022 15:53:05 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/03/2022 15:53:08 - INFO - codeparrot_training - Step 2099: {'lr': 0.000499999447977783, 'samples': 1075200, 'steps': 2099, 'loss/train': 3.3252177238464355}
-03/03/2022 15:53:11 - INFO - codeparrot_training - Step 2100: {'lr': 0.0004999994367695001, 'samples': 1075712, 'steps': 2100, 'loss/train': 3.502760410308838}
-03/03/2022 15:53:14 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/03/2022 15:53:16 - INFO - codeparrot_training - Step 2101: {'lr': 0.0004999994254485714, 'samples': 1076224, 'steps': 2101, 'loss/train': 3.02009654045105}
-03/03/2022 15:53:19 - INFO - codeparrot_training - Step 2102: {'lr': 0.0004999994140149969, 'samples': 1076736, 'steps': 2102, 'loss/train': 3.3655712604522705}
-03/03/2022 15:53:22 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/03/2022 15:53:24 - INFO - codeparrot_training - Step 2103: {'lr': 0.0004999994024687764, 'samples': 1077248, 'steps': 2103, 'loss/train': 2.6672849655151367}
-03/03/2022 15:53:28 - INFO - codeparrot_training - Step 2104: {'lr': 0.00049999939080991, 'samples': 1077760, 'steps': 2104, 'loss/train': 3.3088254928588867}
-03/03/2022 15:53:30 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/03/2022 15:53:33 - INFO - codeparrot_training - Step 2105: {'lr': 0.0004999993790383978, 'samples': 1078272, 'steps': 2105, 'loss/train': 3.3820853233337402}
-03/03/2022 15:53:36 - INFO - codeparrot_training - Step 2106: {'lr': 0.0004999993671542397, 'samples': 1078784, 'steps': 2106, 'loss/train': 3.458866834640503}
-03/03/2022 15:53:39 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/03/2022 15:53:41 - INFO - codeparrot_training - Step 2107: {'lr': 0.0004999993551574358, 'samples': 1079296, 'steps': 2107, 'loss/train': 3.018770217895508}
-03/03/2022 15:53:45 - INFO - codeparrot_training - Step 2108: {'lr': 0.000499999343047986, 'samples': 1079808, 'steps': 2108, 'loss/train': 3.3291473388671875}
-03/03/2022 15:53:47 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/03/2022 15:53:50 - INFO - codeparrot_training - Step 2109: {'lr': 0.0004999993308258904, 'samples': 1080320, 'steps': 2109, 'loss/train': 3.4458365440368652}
-03/03/2022 15:53:53 - INFO - codeparrot_training - Step 2110: {'lr': 0.0004999993184911489, 'samples': 1080832, 'steps': 2110, 'loss/train': 2.906193733215332}
-03/03/2022 15:53:55 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/03/2022 15:53:58 - INFO - codeparrot_training - Step 2111: {'lr': 0.0004999993060437616, 'samples': 1081344, 'steps': 2111, 'loss/train': 3.3055806159973145}
-03/03/2022 15:54:02 - INFO - codeparrot_training - Step 2112: {'lr': 0.0004999992934837284, 'samples': 1081856, 'steps': 2112, 'loss/train': 8.058950424194336}
-03/03/2022 15:54:04 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/03/2022 15:54:07 - INFO - codeparrot_training - Step 2113: {'lr': 0.0004999992808110495, 'samples': 1082368, 'steps': 2113, 'loss/train': 3.8844070434570312}
-03/03/2022 15:54:10 - INFO - codeparrot_training - Step 2114: {'lr': 0.0004999992680257247, 'samples': 1082880, 'steps': 2114, 'loss/train': 6.860340118408203}
-03/03/2022 15:54:13 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/03/2022 15:54:15 - INFO - codeparrot_training - Step 2115: {'lr': 0.0004999992551277541, 'samples': 1083392, 'steps': 2115, 'loss/train': 2.7332510948181152}
-03/03/2022 15:54:18 - INFO - codeparrot_training - Step 2116: {'lr': 0.0004999992421171377, 'samples': 1083904, 'steps': 2116, 'loss/train': 3.278076171875}
-03/03/2022 15:54:21 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/03/2022 15:54:24 - INFO - codeparrot_training - Step 2117: {'lr': 0.0004999992289938755, 'samples': 1084416, 'steps': 2117, 'loss/train': 2.1812992095947266}
-03/03/2022 15:54:27 - INFO - codeparrot_training - Step 2118: {'lr': 0.0004999992157579676, 'samples': 1084928, 'steps': 2118, 'loss/train': 2.6568429470062256}
-03/03/2022 15:54:30 - INFO - codeparrot_training - Step 2119: {'lr': 0.0004999992024094138, 'samples': 1085440, 'steps': 2119, 'loss/train': 3.4700217247009277}
-03/03/2022 15:54:30 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/03/2022 15:54:36 - INFO - codeparrot_training - Step 2120: {'lr': 0.0004999991889482142, 'samples': 1085952, 'steps': 2120, 'loss/train': 4.040984153747559}
-03/03/2022 15:54:38 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/03/2022 15:54:41 - INFO - codeparrot_training - Step 2121: {'lr': 0.0004999991753743689, 'samples': 1086464, 'steps': 2121, 'loss/train': 2.9417686462402344}
-03/03/2022 15:54:44 - INFO - codeparrot_training - Step 2122: {'lr': 0.0004999991616878777, 'samples': 1086976, 'steps': 2122, 'loss/train': 3.1434085369110107}
-03/03/2022 15:54:47 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/03/2022 15:54:49 - INFO - codeparrot_training - Step 2123: {'lr': 0.0004999991478887409, 'samples': 1087488, 'steps': 2123, 'loss/train': 2.9659318923950195}
-03/03/2022 15:54:52 - INFO - codeparrot_training - Step 2124: {'lr': 0.0004999991339769582, 'samples': 1088000, 'steps': 2124, 'loss/train': 3.1472535133361816}
-03/03/2022 15:54:55 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/03/2022 15:54:57 - INFO - codeparrot_training - Step 2125: {'lr': 0.0004999991199525299, 'samples': 1088512, 'steps': 2125, 'loss/train': 2.6963629722595215}
-03/03/2022 15:55:01 - INFO - codeparrot_training - Step 2126: {'lr': 0.0004999991058154557, 'samples': 1089024, 'steps': 2126, 'loss/train': 3.4635300636291504}
-03/03/2022 15:55:03 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/03/2022 15:55:06 - INFO - codeparrot_training - Step 2127: {'lr': 0.0004999990915657359, 'samples': 1089536, 'steps': 2127, 'loss/train': 4.766872882843018}
-03/03/2022 15:55:09 - INFO - codeparrot_training - Step 2128: {'lr': 0.0004999990772033702, 'samples': 1090048, 'steps': 2128, 'loss/train': 2.3895936012268066}
-03/03/2022 15:55:11 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/03/2022 15:55:14 - INFO - codeparrot_training - Step 2129: {'lr': 0.000499999062728359, 'samples': 1090560, 'steps': 2129, 'loss/train': 3.4782779216766357}
-03/03/2022 15:55:17 - INFO - codeparrot_training - Step 2130: {'lr': 0.0004999990481407018, 'samples': 1091072, 'steps': 2130, 'loss/train': 2.4561641216278076}
-03/03/2022 15:55:19 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/03/2022 15:55:23 - INFO - codeparrot_training - Step 2131: {'lr': 0.0004999990334403991, 'samples': 1091584, 'steps': 2131, 'loss/train': 3.1402735710144043}
-03/03/2022 15:55:26 - INFO - codeparrot_training - Step 2132: {'lr': 0.0004999990186274506, 'samples': 1092096, 'steps': 2132, 'loss/train': 3.021862268447876}
-03/03/2022 15:55:28 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/03/2022 15:55:31 - INFO - codeparrot_training - Step 2133: {'lr': 0.0004999990037018564, 'samples': 1092608, 'steps': 2133, 'loss/train': 2.954002857208252}
-03/03/2022 15:55:34 - INFO - codeparrot_training - Step 2134: {'lr': 0.0004999989886636166, 'samples': 1093120, 'steps': 2134, 'loss/train': 3.399930715560913}
-03/03/2022 15:55:36 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/03/2022 15:55:40 - INFO - codeparrot_training - Step 2135: {'lr': 0.000499998973512731, 'samples': 1093632, 'steps': 2135, 'loss/train': 4.165732383728027}
-03/03/2022 15:55:43 - INFO - codeparrot_training - Step 2136: {'lr': 0.0004999989582491998, 'samples': 1094144, 'steps': 2136, 'loss/train': 2.960538864135742}
-03/03/2022 15:55:44 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/03/2022 15:55:48 - INFO - codeparrot_training - Step 2137: {'lr': 0.0004999989428730229, 'samples': 1094656, 'steps': 2137, 'loss/train': 3.5106186866760254}
-03/03/2022 15:55:51 - INFO - codeparrot_training - Step 2138: {'lr': 0.0004999989273842003, 'samples': 1095168, 'steps': 2138, 'loss/train': 4.432214260101318}
-03/03/2022 15:55:53 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/03/2022 15:55:57 - INFO - codeparrot_training - Step 2139: {'lr': 0.0004999989117827321, 'samples': 1095680, 'steps': 2139, 'loss/train': 2.837758779525757}
-03/03/2022 15:56:00 - INFO - codeparrot_training - Step 2140: {'lr': 0.0004999988960686182, 'samples': 1096192, 'steps': 2140, 'loss/train': 3.162780523300171}
-03/03/2022 15:56:02 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/03/2022 15:56:05 - INFO - codeparrot_training - Step 2141: {'lr': 0.0004999988802418587, 'samples': 1096704, 'steps': 2141, 'loss/train': 3.241360902786255}
-03/03/2022 15:56:08 - INFO - codeparrot_training - Step 2142: {'lr': 0.0004999988643024536, 'samples': 1097216, 'steps': 2142, 'loss/train': 3.9060487747192383}
-03/03/2022 15:56:10 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/03/2022 15:56:14 - INFO - codeparrot_training - Step 2143: {'lr': 0.0004999988482504027, 'samples': 1097728, 'steps': 2143, 'loss/train': 3.601203441619873}
-03/03/2022 15:56:17 - INFO - codeparrot_training - Step 2144: {'lr': 0.0004999988320857063, 'samples': 1098240, 'steps': 2144, 'loss/train': 1.9985949993133545}
-03/03/2022 15:56:18 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/03/2022 15:56:22 - INFO - codeparrot_training - Step 2145: {'lr': 0.0004999988158083643, 'samples': 1098752, 'steps': 2145, 'loss/train': 3.100428819656372}
-03/03/2022 15:56:25 - INFO - codeparrot_training - Step 2146: {'lr': 0.0004999987994183766, 'samples': 1099264, 'steps': 2146, 'loss/train': 2.8766708374023438}
-03/03/2022 15:56:27 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/03/2022 15:56:30 - INFO - codeparrot_training - Step 2147: {'lr': 0.0004999987829157434, 'samples': 1099776, 'steps': 2147, 'loss/train': 3.1598196029663086}
-03/03/2022 15:56:34 - INFO - codeparrot_training - Step 2148: {'lr': 0.0004999987663004646, 'samples': 1100288, 'steps': 2148, 'loss/train': 4.006170749664307}
-03/03/2022 15:56:35 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/03/2022 15:56:39 - INFO - codeparrot_training - Step 2149: {'lr': 0.0004999987495725401, 'samples': 1100800, 'steps': 2149, 'loss/train': 3.1935853958129883}
-03/03/2022 15:56:42 - INFO - codeparrot_training - Step 2150: {'lr': 0.0004999987327319701, 'samples': 1101312, 'steps': 2150, 'loss/train': 3.8682503700256348}
-03/03/2022 15:56:43 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/03/2022 15:56:47 - INFO - codeparrot_training - Step 2151: {'lr': 0.0004999987157787546, 'samples': 1101824, 'steps': 2151, 'loss/train': 3.1055119037628174}
-03/03/2022 15:56:50 - INFO - codeparrot_training - Step 2152: {'lr': 0.0004999986987128934, 'samples': 1102336, 'steps': 2152, 'loss/train': 3.349456310272217}
-03/03/2022 15:56:52 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/03/2022 15:56:56 - INFO - codeparrot_training - Step 2153: {'lr': 0.0004999986815343867, 'samples': 1102848, 'steps': 2153, 'loss/train': 3.3752105236053467}
-03/03/2022 15:56:59 - INFO - codeparrot_training - Step 2154: {'lr': 0.0004999986642432345, 'samples': 1103360, 'steps': 2154, 'loss/train': 3.236268997192383}
-03/03/2022 15:57:02 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/03/2022 15:57:04 - INFO - codeparrot_training - Step 2155: {'lr': 0.0004999986468394367, 'samples': 1103872, 'steps': 2155, 'loss/train': 4.51322603225708}
-03/03/2022 15:57:08 - INFO - codeparrot_training - Step 2156: {'lr': 0.0004999986293229934, 'samples': 1104384, 'steps': 2156, 'loss/train': 2.779130697250366}
-03/03/2022 15:57:10 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/03/2022 15:57:13 - INFO - codeparrot_training - Step 2157: {'lr': 0.0004999986116939045, 'samples': 1104896, 'steps': 2157, 'loss/train': 3.7786474227905273}
-03/03/2022 15:57:16 - INFO - codeparrot_training - Step 2158: {'lr': 0.0004999985939521702, 'samples': 1105408, 'steps': 2158, 'loss/train': 3.909266471862793}
-03/03/2022 15:57:18 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/03/2022 15:57:21 - INFO - codeparrot_training - Step 2159: {'lr': 0.0004999985760977903, 'samples': 1105920, 'steps': 2159, 'loss/train': 3.5279836654663086}
-03/03/2022 15:57:24 - INFO - codeparrot_training - Step 2160: {'lr': 0.000499998558130765, 'samples': 1106432, 'steps': 2160, 'loss/train': 2.9420106410980225}
-03/03/2022 15:57:26 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/03/2022 15:57:30 - INFO - codeparrot_training - Step 2161: {'lr': 0.0004999985400510941, 'samples': 1106944, 'steps': 2161, 'loss/train': 4.075507164001465}
-03/03/2022 15:57:33 - INFO - codeparrot_training - Step 2162: {'lr': 0.0004999985218587777, 'samples': 1107456, 'steps': 2162, 'loss/train': 3.7804722785949707}
-03/03/2022 15:57:34 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/03/2022 15:57:38 - INFO - codeparrot_training - Step 2163: {'lr': 0.0004999985035538159, 'samples': 1107968, 'steps': 2163, 'loss/train': 4.148641109466553}
-03/03/2022 15:57:41 - INFO - codeparrot_training - Step 2164: {'lr': 0.0004999984851362086, 'samples': 1108480, 'steps': 2164, 'loss/train': 4.1257781982421875}
-03/03/2022 15:57:43 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/03/2022 15:57:47 - INFO - codeparrot_training - Step 2165: {'lr': 0.0004999984666059559, 'samples': 1108992, 'steps': 2165, 'loss/train': 3.3074519634246826}
-03/03/2022 15:57:50 - INFO - codeparrot_training - Step 2166: {'lr': 0.0004999984479630577, 'samples': 1109504, 'steps': 2166, 'loss/train': 3.8513736724853516}
-03/03/2022 15:57:51 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/03/2022 15:57:55 - INFO - codeparrot_training - Step 2167: {'lr': 0.000499998429207514, 'samples': 1110016, 'steps': 2167, 'loss/train': 2.6395175457000732}
-03/03/2022 15:57:58 - INFO - codeparrot_training - Step 2168: {'lr': 0.000499998410339325, 'samples': 1110528, 'steps': 2168, 'loss/train': 2.7602648735046387}
-03/03/2022 15:58:00 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/03/2022 15:58:04 - INFO - codeparrot_training - Step 2169: {'lr': 0.0004999983913584904, 'samples': 1111040, 'steps': 2169, 'loss/train': 3.9304921627044678}
-03/03/2022 15:58:07 - INFO - codeparrot_training - Step 2170: {'lr': 0.0004999983722650106, 'samples': 1111552, 'steps': 2170, 'loss/train': 3.1235342025756836}
-03/03/2022 15:58:08 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/03/2022 15:58:12 - INFO - codeparrot_training - Step 2171: {'lr': 0.0004999983530588853, 'samples': 1112064, 'steps': 2171, 'loss/train': 3.3282878398895264}
-03/03/2022 15:58:15 - INFO - codeparrot_training - Step 2172: {'lr': 0.0004999983337401145, 'samples': 1112576, 'steps': 2172, 'loss/train': 1.258226990699768}
-03/03/2022 15:58:16 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/03/2022 15:58:20 - INFO - codeparrot_training - Step 2173: {'lr': 0.0004999983143086984, 'samples': 1113088, 'steps': 2173, 'loss/train': 3.6252224445343018}
-03/03/2022 15:58:24 - INFO - codeparrot_training - Step 2174: {'lr': 0.0004999982947646368, 'samples': 1113600, 'steps': 2174, 'loss/train': 4.8876729011535645}
-03/03/2022 15:58:25 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/03/2022 15:58:29 - INFO - codeparrot_training - Step 2175: {'lr': 0.00049999827510793, 'samples': 1114112, 'steps': 2175, 'loss/train': 3.379680633544922}
-03/03/2022 15:58:32 - INFO - codeparrot_training - Step 2176: {'lr': 0.0004999982553385778, 'samples': 1114624, 'steps': 2176, 'loss/train': 2.915555715560913}
-03/03/2022 15:58:33 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/03/2022 15:58:37 - INFO - codeparrot_training - Step 2177: {'lr': 0.0004999982354565802, 'samples': 1115136, 'steps': 2177, 'loss/train': 3.180706024169922}
-03/03/2022 15:58:41 - INFO - codeparrot_training - Step 2178: {'lr': 0.0004999982154619372, 'samples': 1115648, 'steps': 2178, 'loss/train': 2.8413264751434326}
-03/03/2022 15:58:42 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/03/2022 15:58:46 - INFO - codeparrot_training - Step 2179: {'lr': 0.000499998195354649, 'samples': 1116160, 'steps': 2179, 'loss/train': 3.075929641723633}
-03/03/2022 15:58:49 - INFO - codeparrot_training - Step 2180: {'lr': 0.0004999981751347153, 'samples': 1116672, 'steps': 2180, 'loss/train': 2.786820411682129}
-03/03/2022 15:58:50 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 15:58:54 - INFO - codeparrot_training - Step 2181: {'lr': 0.0004999981548021364, 'samples': 1117184, 'steps': 2181, 'loss/train': 3.5749623775482178}
-03/03/2022 15:58:57 - INFO - codeparrot_training - Step 2182: {'lr': 0.0004999981343569122, 'samples': 1117696, 'steps': 2182, 'loss/train': 1.6517219543457031}
-03/03/2022 15:58:59 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/03/2022 15:59:03 - INFO - codeparrot_training - Step 2183: {'lr': 0.0004999981137990425, 'samples': 1118208, 'steps': 2183, 'loss/train': 3.5469722747802734}
-03/03/2022 15:59:06 - INFO - codeparrot_training - Step 2184: {'lr': 0.0004999980931285278, 'samples': 1118720, 'steps': 2184, 'loss/train': 3.6124532222747803}
-03/03/2022 15:59:08 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/03/2022 15:59:11 - INFO - codeparrot_training - Step 2185: {'lr': 0.0004999980723453676, 'samples': 1119232, 'steps': 2185, 'loss/train': 4.047886848449707}
-03/03/2022 15:59:14 - INFO - codeparrot_training - Step 2186: {'lr': 0.0004999980514495623, 'samples': 1119744, 'steps': 2186, 'loss/train': 3.0435261726379395}
-03/03/2022 15:59:16 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/03/2022 15:59:20 - INFO - codeparrot_training - Step 2187: {'lr': 0.0004999980304411116, 'samples': 1120256, 'steps': 2187, 'loss/train': 3.721737861633301}
-03/03/2022 15:59:23 - INFO - codeparrot_training - Step 2188: {'lr': 0.0004999980093200157, 'samples': 1120768, 'steps': 2188, 'loss/train': 2.6698317527770996}
-03/03/2022 15:59:25 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/03/2022 15:59:28 - INFO - codeparrot_training - Step 2189: {'lr': 0.0004999979880862745, 'samples': 1121280, 'steps': 2189, 'loss/train': 2.596677541732788}
-03/03/2022 15:59:31 - INFO - codeparrot_training - Step 2190: {'lr': 0.0004999979667398882, 'samples': 1121792, 'steps': 2190, 'loss/train': 2.020834445953369}
-03/03/2022 15:59:34 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/03/2022 15:59:36 - INFO - codeparrot_training - Step 2191: {'lr': 0.0004999979452808565, 'samples': 1122304, 'steps': 2191, 'loss/train': 3.111593723297119}
-03/03/2022 15:59:40 - INFO - codeparrot_training - Step 2192: {'lr': 0.0004999979237091796, 'samples': 1122816, 'steps': 2192, 'loss/train': 2.8774466514587402}
-03/03/2022 15:59:42 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/03/2022 15:59:45 - INFO - codeparrot_training - Step 2193: {'lr': 0.0004999979020248577, 'samples': 1123328, 'steps': 2193, 'loss/train': 2.7346956729888916}
-03/03/2022 15:59:48 - INFO - codeparrot_training - Step 2194: {'lr': 0.0004999978802278904, 'samples': 1123840, 'steps': 2194, 'loss/train': 4.36392879486084}
-03/03/2022 15:59:51 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/03/2022 15:59:53 - INFO - codeparrot_training - Step 2195: {'lr': 0.000499997858318278, 'samples': 1124352, 'steps': 2195, 'loss/train': 3.296250104904175}
-03/03/2022 15:59:57 - INFO - codeparrot_training - Step 2196: {'lr': 0.0004999978362960204, 'samples': 1124864, 'steps': 2196, 'loss/train': 3.2620816230773926}
-03/03/2022 15:59:59 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/03/2022 16:00:02 - INFO - codeparrot_training - Step 2197: {'lr': 0.0004999978141611176, 'samples': 1125376, 'steps': 2197, 'loss/train': 3.448967933654785}
-03/03/2022 16:00:05 - INFO - codeparrot_training - Step 2198: {'lr': 0.0004999977919135696, 'samples': 1125888, 'steps': 2198, 'loss/train': 2.1470861434936523}
-03/03/2022 16:00:07 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/03/2022 16:00:10 - INFO - codeparrot_training - Step 2199: {'lr': 0.0004999977695533766, 'samples': 1126400, 'steps': 2199, 'loss/train': 2.2718451023101807}
-03/03/2022 16:00:13 - INFO - codeparrot_training - Step 2200: {'lr': 0.0004999977470805383, 'samples': 1126912, 'steps': 2200, 'loss/train': 3.131701946258545}
-03/03/2022 16:00:16 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/03/2022 16:00:19 - INFO - codeparrot_training - Step 2201: {'lr': 0.0004999977244950551, 'samples': 1127424, 'steps': 2201, 'loss/train': 3.7374184131622314}
-03/03/2022 16:00:22 - INFO - codeparrot_training - Step 2202: {'lr': 0.0004999977017969266, 'samples': 1127936, 'steps': 2202, 'loss/train': 8.167623519897461}
-03/03/2022 16:00:25 - INFO - codeparrot_training - Step 2203: {'lr': 0.000499997678986153, 'samples': 1128448, 'steps': 2203, 'loss/train': 1.47736656665802}
-03/03/2022 16:00:25 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/03/2022 16:00:30 - INFO - codeparrot_training - Step 2204: {'lr': 0.0004999976560627344, 'samples': 1128960, 'steps': 2204, 'loss/train': 2.690406560897827}
-03/03/2022 16:00:34 - INFO - codeparrot_training - Step 2205: {'lr': 0.0004999976330266707, 'samples': 1129472, 'steps': 2205, 'loss/train': 2.537095785140991}
-03/03/2022 16:00:34 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 16:00:39 - INFO - codeparrot_training - Step 2206: {'lr': 0.0004999976098779618, 'samples': 1129984, 'steps': 2206, 'loss/train': 3.085176944732666}
-03/03/2022 16:00:42 - INFO - codeparrot_training - Step 2207: {'lr': 0.0004999975866166079, 'samples': 1130496, 'steps': 2207, 'loss/train': 1.8430806398391724}
-03/03/2022 16:00:42 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/03/2022 16:00:47 - INFO - codeparrot_training - Step 2208: {'lr': 0.000499997563242609, 'samples': 1131008, 'steps': 2208, 'loss/train': 2.9553072452545166}
-03/03/2022 16:00:50 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/03/2022 16:00:53 - INFO - codeparrot_training - Step 2209: {'lr': 0.0004999975397559649, 'samples': 1131520, 'steps': 2209, 'loss/train': 2.7070538997650146}
-03/03/2022 16:00:56 - INFO - codeparrot_training - Step 2210: {'lr': 0.000499997516156676, 'samples': 1132032, 'steps': 2210, 'loss/train': 3.3697493076324463}
-03/03/2022 16:00:58 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/03/2022 16:01:01 - INFO - codeparrot_training - Step 2211: {'lr': 0.000499997492444742, 'samples': 1132544, 'steps': 2211, 'loss/train': 3.843799114227295}
-03/03/2022 16:01:04 - INFO - codeparrot_training - Step 2212: {'lr': 0.0004999974686201629, 'samples': 1133056, 'steps': 2212, 'loss/train': 3.4916319847106934}
-03/03/2022 16:01:06 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/03/2022 16:01:09 - INFO - codeparrot_training - Step 2213: {'lr': 0.0004999974446829389, 'samples': 1133568, 'steps': 2213, 'loss/train': 3.0537095069885254}
-03/03/2022 16:01:12 - INFO - codeparrot_training - Step 2214: {'lr': 0.0004999974206330698, 'samples': 1134080, 'steps': 2214, 'loss/train': 2.6437153816223145}
-03/03/2022 16:01:14 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/03/2022 16:01:18 - INFO - codeparrot_training - Step 2215: {'lr': 0.0004999973964705558, 'samples': 1134592, 'steps': 2215, 'loss/train': 2.0629634857177734}
-03/03/2022 16:01:21 - INFO - codeparrot_training - Step 2216: {'lr': 0.0004999973721953968, 'samples': 1135104, 'steps': 2216, 'loss/train': 3.6002323627471924}
-03/03/2022 16:01:23 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/03/2022 16:01:26 - INFO - codeparrot_training - Step 2217: {'lr': 0.0004999973478075928, 'samples': 1135616, 'steps': 2217, 'loss/train': 3.738161563873291}
-03/03/2022 16:01:29 - INFO - codeparrot_training - Step 2218: {'lr': 0.0004999973233071438, 'samples': 1136128, 'steps': 2218, 'loss/train': 2.3218307495117188}
-03/03/2022 16:01:32 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/03/2022 16:01:35 - INFO - codeparrot_training - Step 2219: {'lr': 0.00049999729869405, 'samples': 1136640, 'steps': 2219, 'loss/train': 2.759835720062256}
-03/03/2022 16:01:38 - INFO - codeparrot_training - Step 2220: {'lr': 0.0004999972739683113, 'samples': 1137152, 'steps': 2220, 'loss/train': 2.835109233856201}
-03/03/2022 16:01:40 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/03/2022 16:01:43 - INFO - codeparrot_training - Step 2221: {'lr': 0.0004999972491299276, 'samples': 1137664, 'steps': 2221, 'loss/train': 3.295903205871582}
-03/03/2022 16:01:46 - INFO - codeparrot_training - Step 2222: {'lr': 0.000499997224178899, 'samples': 1138176, 'steps': 2222, 'loss/train': 2.1122236251831055}
-03/03/2022 16:01:49 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/03/2022 16:01:52 - INFO - codeparrot_training - Step 2223: {'lr': 0.0004999971991152256, 'samples': 1138688, 'steps': 2223, 'loss/train': 2.486236333847046}
-03/03/2022 16:01:55 - INFO - codeparrot_training - Step 2224: {'lr': 0.0004999971739389072, 'samples': 1139200, 'steps': 2224, 'loss/train': 2.6111724376678467}
-03/03/2022 16:01:57 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/03/2022 16:02:00 - INFO - codeparrot_training - Step 2225: {'lr': 0.000499997148649944, 'samples': 1139712, 'steps': 2225, 'loss/train': 3.8881101608276367}
-03/03/2022 16:02:03 - INFO - codeparrot_training - Step 2226: {'lr': 0.0004999971232483359, 'samples': 1140224, 'steps': 2226, 'loss/train': 3.3411731719970703}
-03/03/2022 16:02:06 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/03/2022 16:02:08 - INFO - codeparrot_training - Step 2227: {'lr': 0.0004999970977340829, 'samples': 1140736, 'steps': 2227, 'loss/train': 3.3929550647735596}
-03/03/2022 16:02:12 - INFO - codeparrot_training - Step 2228: {'lr': 0.0004999970721071852, 'samples': 1141248, 'steps': 2228, 'loss/train': 3.846820831298828}
-03/03/2022 16:02:14 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/03/2022 16:02:17 - INFO - codeparrot_training - Step 2229: {'lr': 0.0004999970463676427, 'samples': 1141760, 'steps': 2229, 'loss/train': 3.200389862060547}
-03/03/2022 16:02:20 - INFO - codeparrot_training - Step 2230: {'lr': 0.0004999970205154553, 'samples': 1142272, 'steps': 2230, 'loss/train': 3.928372859954834}
-03/03/2022 16:02:22 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/03/2022 16:02:25 - INFO - codeparrot_training - Step 2231: {'lr': 0.000499996994550623, 'samples': 1142784, 'steps': 2231, 'loss/train': 3.8303329944610596}
-03/03/2022 16:02:29 - INFO - codeparrot_training - Step 2232: {'lr': 0.000499996968473146, 'samples': 1143296, 'steps': 2232, 'loss/train': 3.860849380493164}
-03/03/2022 16:02:31 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/03/2022 16:02:34 - INFO - codeparrot_training - Step 2233: {'lr': 0.0004999969422830242, 'samples': 1143808, 'steps': 2233, 'loss/train': 2.639922857284546}
-03/03/2022 16:02:37 - INFO - codeparrot_training - Step 2234: {'lr': 0.0004999969159802577, 'samples': 1144320, 'steps': 2234, 'loss/train': 4.099701404571533}
-03/03/2022 16:02:39 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/03/2022 16:02:42 - INFO - codeparrot_training - Step 2235: {'lr': 0.0004999968895648464, 'samples': 1144832, 'steps': 2235, 'loss/train': 3.855062246322632}
-03/03/2022 16:02:46 - INFO - codeparrot_training - Step 2236: {'lr': 0.0004999968630367905, 'samples': 1145344, 'steps': 2236, 'loss/train': 3.210245370864868}
-03/03/2022 16:02:48 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/03/2022 16:02:51 - INFO - codeparrot_training - Step 2237: {'lr': 0.0004999968363960897, 'samples': 1145856, 'steps': 2237, 'loss/train': 2.9591712951660156}
-03/03/2022 16:02:54 - INFO - codeparrot_training - Step 2238: {'lr': 0.0004999968096427443, 'samples': 1146368, 'steps': 2238, 'loss/train': 3.1449475288391113}
-03/03/2022 16:02:56 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/03/2022 16:02:59 - INFO - codeparrot_training - Step 2239: {'lr': 0.0004999967827767541, 'samples': 1146880, 'steps': 2239, 'loss/train': 3.80161714553833}
-03/03/2022 16:03:02 - INFO - codeparrot_training - Step 2240: {'lr': 0.0004999967557981192, 'samples': 1147392, 'steps': 2240, 'loss/train': 2.181140422821045}
-03/03/2022 16:03:04 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/03/2022 16:03:07 - INFO - codeparrot_training - Step 2241: {'lr': 0.0004999967287068396, 'samples': 1147904, 'steps': 2241, 'loss/train': 3.3080360889434814}
-03/03/2022 16:03:11 - INFO - codeparrot_training - Step 2242: {'lr': 0.0004999967015029155, 'samples': 1148416, 'steps': 2242, 'loss/train': 1.4108967781066895}
-03/03/2022 16:03:12 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/03/2022 16:03:16 - INFO - codeparrot_training - Step 2243: {'lr': 0.0004999966741863467, 'samples': 1148928, 'steps': 2243, 'loss/train': 3.116621971130371}
-03/03/2022 16:03:19 - INFO - codeparrot_training - Step 2244: {'lr': 0.000499996646757133, 'samples': 1149440, 'steps': 2244, 'loss/train': 3.128178119659424}
-03/03/2022 16:03:20 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/03/2022 16:03:24 - INFO - codeparrot_training - Step 2245: {'lr': 0.0004999966192152749, 'samples': 1149952, 'steps': 2245, 'loss/train': 3.1809072494506836}
-03/03/2022 16:03:27 - INFO - codeparrot_training - Step 2246: {'lr': 0.0004999965915607722, 'samples': 1150464, 'steps': 2246, 'loss/train': 3.7514734268188477}
-03/03/2022 16:03:29 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/03/2022 16:03:33 - INFO - codeparrot_training - Step 2247: {'lr': 0.0004999965637936248, 'samples': 1150976, 'steps': 2247, 'loss/train': 1.9753257036209106}
-03/03/2022 16:03:36 - INFO - codeparrot_training - Step 2248: {'lr': 0.0004999965359138329, 'samples': 1151488, 'steps': 2248, 'loss/train': 2.962155342102051}
-03/03/2022 16:03:37 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/03/2022 16:03:41 - INFO - codeparrot_training - Step 2249: {'lr': 0.0004999965079213964, 'samples': 1152000, 'steps': 2249, 'loss/train': 3.8691513538360596}
-03/03/2022 16:03:44 - INFO - codeparrot_training - Step 2250: {'lr': 0.0004999964798163152, 'samples': 1152512, 'steps': 2250, 'loss/train': 3.998168468475342}
-03/03/2022 16:03:45 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/03/2022 16:03:49 - INFO - codeparrot_training - Step 2251: {'lr': 0.0004999964515985896, 'samples': 1153024, 'steps': 2251, 'loss/train': 3.000925064086914}
-03/03/2022 16:03:53 - INFO - codeparrot_training - Step 2252: {'lr': 0.0004999964232682194, 'samples': 1153536, 'steps': 2252, 'loss/train': 2.8140668869018555}
-03/03/2022 16:03:54 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/03/2022 16:03:58 - INFO - codeparrot_training - Step 2253: {'lr': 0.0004999963948252046, 'samples': 1154048, 'steps': 2253, 'loss/train': 2.92730975151062}
-03/03/2022 16:04:01 - INFO - codeparrot_training - Step 2254: {'lr': 0.0004999963662695453, 'samples': 1154560, 'steps': 2254, 'loss/train': 2.7133889198303223}
-03/03/2022 16:04:02 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/03/2022 16:04:06 - INFO - codeparrot_training - Step 2255: {'lr': 0.0004999963376012416, 'samples': 1155072, 'steps': 2255, 'loss/train': 3.4704363346099854}
-03/03/2022 16:04:09 - INFO - codeparrot_training - Step 2256: {'lr': 0.0004999963088202934, 'samples': 1155584, 'steps': 2256, 'loss/train': 3.760922431945801}
-03/03/2022 16:04:10 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/03/2022 16:04:15 - INFO - codeparrot_training - Step 2257: {'lr': 0.0004999962799267006, 'samples': 1156096, 'steps': 2257, 'loss/train': 2.528806686401367}
-03/03/2022 16:04:18 - INFO - codeparrot_training - Step 2258: {'lr': 0.0004999962509204634, 'samples': 1156608, 'steps': 2258, 'loss/train': 2.3950648307800293}
-03/03/2022 16:04:19 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/03/2022 16:04:23 - INFO - codeparrot_training - Step 2259: {'lr': 0.0004999962218015818, 'samples': 1157120, 'steps': 2259, 'loss/train': 0.7431287169456482}
-03/03/2022 16:04:26 - INFO - codeparrot_training - Step 2260: {'lr': 0.0004999961925700557, 'samples': 1157632, 'steps': 2260, 'loss/train': 3.814455032348633}
-03/03/2022 16:04:27 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/03/2022 16:04:32 - INFO - codeparrot_training - Step 2261: {'lr': 0.0004999961632258851, 'samples': 1158144, 'steps': 2261, 'loss/train': 3.390331268310547}
-03/03/2022 16:04:35 - INFO - codeparrot_training - Step 2262: {'lr': 0.0004999961337690703, 'samples': 1158656, 'steps': 2262, 'loss/train': 3.006119728088379}
-03/03/2022 16:04:36 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/03/2022 16:04:40 - INFO - codeparrot_training - Step 2263: {'lr': 0.0004999961041996109, 'samples': 1159168, 'steps': 2263, 'loss/train': 2.743804454803467}
-03/03/2022 16:04:43 - INFO - codeparrot_training - Step 2264: {'lr': 0.0004999960745175071, 'samples': 1159680, 'steps': 2264, 'loss/train': 3.8200066089630127}
-03/03/2022 16:04:45 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/03/2022 16:04:49 - INFO - codeparrot_training - Step 2265: {'lr': 0.0004999960447227591, 'samples': 1160192, 'steps': 2265, 'loss/train': 3.8612003326416016}
-03/03/2022 16:04:52 - INFO - codeparrot_training - Step 2266: {'lr': 0.0004999960148153667, 'samples': 1160704, 'steps': 2266, 'loss/train': 3.1429362297058105}
-03/03/2022 16:04:54 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/03/2022 16:04:57 - INFO - codeparrot_training - Step 2267: {'lr': 0.0004999959847953299, 'samples': 1161216, 'steps': 2267, 'loss/train': 2.8557565212249756}
-03/03/2022 16:05:00 - INFO - codeparrot_training - Step 2268: {'lr': 0.0004999959546626487, 'samples': 1161728, 'steps': 2268, 'loss/train': 2.1531596183776855}
-03/03/2022 16:05:02 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/03/2022 16:05:06 - INFO - codeparrot_training - Step 2269: {'lr': 0.0004999959244173232, 'samples': 1162240, 'steps': 2269, 'loss/train': 3.010319948196411}
-03/03/2022 16:05:09 - INFO - codeparrot_training - Step 2270: {'lr': 0.0004999958940593535, 'samples': 1162752, 'steps': 2270, 'loss/train': 3.9224822521209717}
-03/03/2022 16:05:11 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/03/2022 16:05:14 - INFO - codeparrot_training - Step 2271: {'lr': 0.0004999958635887394, 'samples': 1163264, 'steps': 2271, 'loss/train': 3.962085008621216}
-03/03/2022 16:05:17 - INFO - codeparrot_training - Step 2272: {'lr': 0.0004999958330054811, 'samples': 1163776, 'steps': 2272, 'loss/train': 3.341320514678955}
-03/03/2022 16:05:19 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/03/2022 16:05:23 - INFO - codeparrot_training - Step 2273: {'lr': 0.0004999958023095785, 'samples': 1164288, 'steps': 2273, 'loss/train': 0.7658462524414062}
-03/03/2022 16:05:26 - INFO - codeparrot_training - Step 2274: {'lr': 0.0004999957715010317, 'samples': 1164800, 'steps': 2274, 'loss/train': 3.0417842864990234}
-03/03/2022 16:05:28 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/03/2022 16:05:31 - INFO - codeparrot_training - Step 2275: {'lr': 0.0004999957405798405, 'samples': 1165312, 'steps': 2275, 'loss/train': 3.515624761581421}
-03/03/2022 16:05:34 - INFO - codeparrot_training - Step 2276: {'lr': 0.0004999957095460052, 'samples': 1165824, 'steps': 2276, 'loss/train': 2.811504602432251}
-03/03/2022 16:05:36 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/03/2022 16:05:40 - INFO - codeparrot_training - Step 2277: {'lr': 0.0004999956783995257, 'samples': 1166336, 'steps': 2277, 'loss/train': 3.7728817462921143}
-03/03/2022 16:05:43 - INFO - codeparrot_training - Step 2278: {'lr': 0.0004999956471404021, 'samples': 1166848, 'steps': 2278, 'loss/train': 3.2592594623565674}
-03/03/2022 16:05:45 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/03/2022 16:05:48 - INFO - codeparrot_training - Step 2279: {'lr': 0.0004999956157686341, 'samples': 1167360, 'steps': 2279, 'loss/train': 3.566458225250244}
-03/03/2022 16:05:51 - INFO - codeparrot_training - Step 2280: {'lr': 0.0004999955842842222, 'samples': 1167872, 'steps': 2280, 'loss/train': 2.734273672103882}
-03/03/2022 16:05:53 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/03/2022 16:05:56 - INFO - codeparrot_training - Step 2281: {'lr': 0.0004999955526871659, 'samples': 1168384, 'steps': 2281, 'loss/train': 3.0264272689819336}
-03/03/2022 16:06:00 - INFO - codeparrot_training - Step 2282: {'lr': 0.0004999955209774656, 'samples': 1168896, 'steps': 2282, 'loss/train': 3.1493284702301025}
-03/03/2022 16:06:01 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/03/2022 16:06:05 - INFO - codeparrot_training - Step 2283: {'lr': 0.0004999954891551211, 'samples': 1169408, 'steps': 2283, 'loss/train': 1.7484716176986694}
-03/03/2022 16:06:08 - INFO - codeparrot_training - Step 2284: {'lr': 0.0004999954572201326, 'samples': 1169920, 'steps': 2284, 'loss/train': 3.4496495723724365}
-03/03/2022 16:06:09 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/03/2022 16:06:13 - INFO - codeparrot_training - Step 2285: {'lr': 0.0004999954251724999, 'samples': 1170432, 'steps': 2285, 'loss/train': 2.7517075538635254}
-03/03/2022 16:06:16 - INFO - codeparrot_training - Step 2286: {'lr': 0.0004999953930122231, 'samples': 1170944, 'steps': 2286, 'loss/train': 2.4651145935058594}
-03/03/2022 16:06:17 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/03/2022 16:06:22 - INFO - codeparrot_training - Step 2287: {'lr': 0.0004999953607393023, 'samples': 1171456, 'steps': 2287, 'loss/train': 3.3342177867889404}
-03/03/2022 16:06:25 - INFO - codeparrot_training - Step 2288: {'lr': 0.0004999953283537374, 'samples': 1171968, 'steps': 2288, 'loss/train': 4.049373626708984}
-03/03/2022 16:06:26 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/03/2022 16:06:30 - INFO - codeparrot_training - Step 2289: {'lr': 0.0004999952958555285, 'samples': 1172480, 'steps': 2289, 'loss/train': 3.1396403312683105}
-03/03/2022 16:06:33 - INFO - codeparrot_training - Step 2290: {'lr': 0.0004999952632446756, 'samples': 1172992, 'steps': 2290, 'loss/train': 2.876293420791626}
-03/03/2022 16:06:34 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/03/2022 16:06:38 - INFO - codeparrot_training - Step 2291: {'lr': 0.0004999952305211786, 'samples': 1173504, 'steps': 2291, 'loss/train': 3.5791354179382324}
-03/03/2022 16:06:42 - INFO - codeparrot_training - Step 2292: {'lr': 0.0004999951976850377, 'samples': 1174016, 'steps': 2292, 'loss/train': 2.5373010635375977}
-03/03/2022 16:06:42 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/03/2022 16:06:47 - INFO - codeparrot_training - Step 2293: {'lr': 0.0004999951647362527, 'samples': 1174528, 'steps': 2293, 'loss/train': 3.0804197788238525}
-03/03/2022 16:06:50 - INFO - codeparrot_training - Step 2294: {'lr': 0.0004999951316748239, 'samples': 1175040, 'steps': 2294, 'loss/train': 2.5079517364501953}
-03/03/2022 16:06:51 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/03/2022 16:06:55 - INFO - codeparrot_training - Step 2295: {'lr': 0.0004999950985007511, 'samples': 1175552, 'steps': 2295, 'loss/train': 2.9973175525665283}
-03/03/2022 16:06:58 - INFO - codeparrot_training - Step 2296: {'lr': 0.0004999950652140343, 'samples': 1176064, 'steps': 2296, 'loss/train': 4.560308933258057}
-03/03/2022 16:06:58 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/03/2022 16:07:04 - INFO - codeparrot_training - Step 2297: {'lr': 0.0004999950318146737, 'samples': 1176576, 'steps': 2297, 'loss/train': 2.290208101272583}
-03/03/2022 16:07:07 - INFO - codeparrot_training - Step 2298: {'lr': 0.0004999949983026691, 'samples': 1177088, 'steps': 2298, 'loss/train': 3.1492295265197754}
-03/03/2022 16:07:07 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/03/2022 16:07:12 - INFO - codeparrot_training - Step 2299: {'lr': 0.0004999949646780205, 'samples': 1177600, 'steps': 2299, 'loss/train': 3.4125776290893555}
-03/03/2022 16:07:15 - INFO - codeparrot_training - Step 2300: {'lr': 0.0004999949309407283, 'samples': 1178112, 'steps': 2300, 'loss/train': 3.329164981842041}
-03/03/2022 16:07:16 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/03/2022 16:07:20 - INFO - codeparrot_training - Step 2301: {'lr': 0.0004999948970907921, 'samples': 1178624, 'steps': 2301, 'loss/train': 3.2822911739349365}
-03/03/2022 16:07:24 - INFO - codeparrot_training - Step 2302: {'lr': 0.0004999948631282119, 'samples': 1179136, 'steps': 2302, 'loss/train': 2.9314568042755127}
-03/03/2022 16:07:24 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/03/2022 16:07:29 - INFO - codeparrot_training - Step 2303: {'lr': 0.0004999948290529881, 'samples': 1179648, 'steps': 2303, 'loss/train': 2.7405691146850586}
-03/03/2022 16:07:32 - INFO - codeparrot_training - Step 2304: {'lr': 0.0004999947948651204, 'samples': 1180160, 'steps': 2304, 'loss/train': 3.455448627471924}
-03/03/2022 16:07:32 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/03/2022 16:07:37 - INFO - codeparrot_training - Step 2305: {'lr': 0.0004999947605646089, 'samples': 1180672, 'steps': 2305, 'loss/train': 3.519378900527954}
-03/03/2022 16:07:40 - INFO - codeparrot_training - Step 2306: {'lr': 0.0004999947261514537, 'samples': 1181184, 'steps': 2306, 'loss/train': 2.651277780532837}
-03/03/2022 16:07:40 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/03/2022 16:07:46 - INFO - codeparrot_training - Step 2307: {'lr': 0.0004999946916256547, 'samples': 1181696, 'steps': 2307, 'loss/train': 2.6726553440093994}
-03/03/2022 16:07:49 - INFO - codeparrot_training - Step 2308: {'lr': 0.0004999946569872118, 'samples': 1182208, 'steps': 2308, 'loss/train': 3.4526588916778564}
-03/03/2022 16:07:49 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/03/2022 16:07:54 - INFO - codeparrot_training - Step 2309: {'lr': 0.0004999946222361254, 'samples': 1182720, 'steps': 2309, 'loss/train': 2.297178268432617}
-03/03/2022 16:07:57 - INFO - codeparrot_training - Step 2310: {'lr': 0.0004999945873723951, 'samples': 1183232, 'steps': 2310, 'loss/train': 1.8463554382324219}
-03/03/2022 16:07:57 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/03/2022 16:08:02 - INFO - codeparrot_training - Step 2311: {'lr': 0.0004999945523960212, 'samples': 1183744, 'steps': 2311, 'loss/train': 2.822561264038086}
-03/03/2022 16:08:05 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/03/2022 16:08:08 - INFO - codeparrot_training - Step 2312: {'lr': 0.0004999945173070035, 'samples': 1184256, 'steps': 2312, 'loss/train': 2.0279057025909424}
-03/03/2022 16:08:11 - INFO - codeparrot_training - Step 2313: {'lr': 0.0004999944821053422, 'samples': 1184768, 'steps': 2313, 'loss/train': 4.771055698394775}
-03/03/2022 16:08:14 - INFO - codeparrot_training - Step 2314: {'lr': 0.0004999944467910372, 'samples': 1185280, 'steps': 2314, 'loss/train': 2.7460744380950928}
-03/03/2022 16:08:15 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/03/2022 16:08:19 - INFO - codeparrot_training - Step 2315: {'lr': 0.0004999944113640887, 'samples': 1185792, 'steps': 2315, 'loss/train': 2.4521260261535645}
-03/03/2022 16:08:23 - INFO - codeparrot_training - Step 2316: {'lr': 0.0004999943758244964, 'samples': 1186304, 'steps': 2316, 'loss/train': 2.9871323108673096}
-03/03/2022 16:08:23 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/03/2022 16:08:28 - INFO - codeparrot_training - Step 2317: {'lr': 0.0004999943401722606, 'samples': 1186816, 'steps': 2317, 'loss/train': 3.333430290222168}
-03/03/2022 16:08:31 - INFO - codeparrot_training - Step 2318: {'lr': 0.0004999943044073813, 'samples': 1187328, 'steps': 2318, 'loss/train': 4.098447322845459}
-03/03/2022 16:08:31 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/03/2022 16:08:36 - INFO - codeparrot_training - Step 2319: {'lr': 0.0004999942685298582, 'samples': 1187840, 'steps': 2319, 'loss/train': 3.556797504425049}
-03/03/2022 16:08:39 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/03/2022 16:08:42 - INFO - codeparrot_training - Step 2320: {'lr': 0.0004999942325396916, 'samples': 1188352, 'steps': 2320, 'loss/train': 3.6084952354431152}
-03/03/2022 16:08:45 - INFO - codeparrot_training - Step 2321: {'lr': 0.0004999941964368817, 'samples': 1188864, 'steps': 2321, 'loss/train': 2.39994740486145}
-03/03/2022 16:08:47 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/03/2022 16:08:50 - INFO - codeparrot_training - Step 2322: {'lr': 0.000499994160221428, 'samples': 1189376, 'steps': 2322, 'loss/train': 3.695596933364868}
-03/03/2022 16:08:53 - INFO - codeparrot_training - Step 2323: {'lr': 0.0004999941238933308, 'samples': 1189888, 'steps': 2323, 'loss/train': 2.4125816822052}
-03/03/2022 16:08:56 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/03/2022 16:08:59 - INFO - codeparrot_training - Step 2324: {'lr': 0.0004999940874525902, 'samples': 1190400, 'steps': 2324, 'loss/train': 3.0763771533966064}
-03/03/2022 16:09:02 - INFO - codeparrot_training - Step 2325: {'lr': 0.0004999940508992061, 'samples': 1190912, 'steps': 2325, 'loss/train': 2.733271360397339}
-03/03/2022 16:09:05 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/03/2022 16:09:07 - INFO - codeparrot_training - Step 2326: {'lr': 0.0004999940142331785, 'samples': 1191424, 'steps': 2326, 'loss/train': 3.4050912857055664}
-03/03/2022 16:09:10 - INFO - codeparrot_training - Step 2327: {'lr': 0.0004999939774545074, 'samples': 1191936, 'steps': 2327, 'loss/train': 2.9216370582580566}
-03/03/2022 16:09:13 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/03/2022 16:09:16 - INFO - codeparrot_training - Step 2328: {'lr': 0.000499993940563193, 'samples': 1192448, 'steps': 2328, 'loss/train': 3.3163259029388428}
-03/03/2022 16:09:19 - INFO - codeparrot_training - Step 2329: {'lr': 0.0004999939035592351, 'samples': 1192960, 'steps': 2329, 'loss/train': 6.4422688484191895}
-03/03/2022 16:09:21 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/03/2022 16:09:24 - INFO - codeparrot_training - Step 2330: {'lr': 0.0004999938664426339, 'samples': 1193472, 'steps': 2330, 'loss/train': 3.1382224559783936}
-03/03/2022 16:09:27 - INFO - codeparrot_training - Step 2331: {'lr': 0.0004999938292133894, 'samples': 1193984, 'steps': 2331, 'loss/train': 3.230679750442505}
-03/03/2022 16:09:31 - INFO - codeparrot_training - Step 2332: {'lr': 0.0004999937918715013, 'samples': 1194496, 'steps': 2332, 'loss/train': 1.8205024003982544}
-03/03/2022 16:09:31 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/03/2022 16:09:36 - INFO - codeparrot_training - Step 2333: {'lr': 0.00049999375441697, 'samples': 1195008, 'steps': 2333, 'loss/train': 3.3296782970428467}
-03/03/2022 16:09:39 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/03/2022 16:09:41 - INFO - codeparrot_training - Step 2334: {'lr': 0.0004999937168497954, 'samples': 1195520, 'steps': 2334, 'loss/train': 3.1814863681793213}
-03/03/2022 16:09:44 - INFO - codeparrot_training - Step 2335: {'lr': 0.0004999936791699773, 'samples': 1196032, 'steps': 2335, 'loss/train': 3.746454954147339}
-03/03/2022 16:09:47 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/03/2022 16:09:50 - INFO - codeparrot_training - Step 2336: {'lr': 0.0004999936413775161, 'samples': 1196544, 'steps': 2336, 'loss/train': 4.3374152183532715}
-03/03/2022 16:09:53 - INFO - codeparrot_training - Step 2337: {'lr': 0.0004999936034724115, 'samples': 1197056, 'steps': 2337, 'loss/train': 3.145212173461914}
-03/03/2022 16:09:55 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/03/2022 16:09:58 - INFO - codeparrot_training - Step 2338: {'lr': 0.0004999935654546638, 'samples': 1197568, 'steps': 2338, 'loss/train': 3.6831605434417725}
-03/03/2022 16:10:01 - INFO - codeparrot_training - Step 2339: {'lr': 0.0004999935273242727, 'samples': 1198080, 'steps': 2339, 'loss/train': 2.7442963123321533}
-03/03/2022 16:10:04 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/03/2022 16:10:07 - INFO - codeparrot_training - Step 2340: {'lr': 0.0004999934890812384, 'samples': 1198592, 'steps': 2340, 'loss/train': 2.606112241744995}
-03/03/2022 16:10:10 - INFO - codeparrot_training - Step 2341: {'lr': 0.0004999934507255609, 'samples': 1199104, 'steps': 2341, 'loss/train': 2.9907941818237305}
-03/03/2022 16:10:12 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/03/2022 16:10:15 - INFO - codeparrot_training - Step 2342: {'lr': 0.0004999934122572403, 'samples': 1199616, 'steps': 2342, 'loss/train': 3.5362229347229004}
-03/03/2022 16:10:18 - INFO - codeparrot_training - Step 2343: {'lr': 0.0004999933736762763, 'samples': 1200128, 'steps': 2343, 'loss/train': 1.0581634044647217}
-03/03/2022 16:10:20 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/03/2022 16:10:23 - INFO - codeparrot_training - Step 2344: {'lr': 0.0004999933349826694, 'samples': 1200640, 'steps': 2344, 'loss/train': 3.1751739978790283}
-03/03/2022 16:10:27 - INFO - codeparrot_training - Step 2345: {'lr': 0.0004999932961764192, 'samples': 1201152, 'steps': 2345, 'loss/train': 3.5930683612823486}
-03/03/2022 16:10:29 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/03/2022 16:10:32 - INFO - codeparrot_training - Step 2346: {'lr': 0.000499993257257526, 'samples': 1201664, 'steps': 2346, 'loss/train': 2.397047758102417}
-03/03/2022 16:10:35 - INFO - codeparrot_training - Step 2347: {'lr': 0.0004999932182259897, 'samples': 1202176, 'steps': 2347, 'loss/train': 2.6743717193603516}
-03/03/2022 16:10:37 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/03/2022 16:10:40 - INFO - codeparrot_training - Step 2348: {'lr': 0.0004999931790818102, 'samples': 1202688, 'steps': 2348, 'loss/train': 0.2999705970287323}
-03/03/2022 16:10:44 - INFO - codeparrot_training - Step 2349: {'lr': 0.0004999931398249876, 'samples': 1203200, 'steps': 2349, 'loss/train': 4.60331916809082}
-03/03/2022 16:10:46 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/03/2022 16:10:49 - INFO - codeparrot_training - Step 2350: {'lr': 0.0004999931004555221, 'samples': 1203712, 'steps': 2350, 'loss/train': 3.645582675933838}
-03/03/2022 16:10:52 - INFO - codeparrot_training - Step 2351: {'lr': 0.0004999930609734135, 'samples': 1204224, 'steps': 2351, 'loss/train': 2.5348284244537354}
-03/03/2022 16:10:55 - INFO - codeparrot_training - Step 2352: {'lr': 0.0004999930213786619, 'samples': 1204736, 'steps': 2352, 'loss/train': 1.9799997806549072}
-03/03/2022 16:10:56 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/03/2022 16:11:01 - INFO - codeparrot_training - Step 2353: {'lr': 0.0004999929816712672, 'samples': 1205248, 'steps': 2353, 'loss/train': 2.9346108436584473}
-03/03/2022 16:11:04 - INFO - codeparrot_training - Step 2354: {'lr': 0.0004999929418512296, 'samples': 1205760, 'steps': 2354, 'loss/train': 2.96004581451416}
-03/03/2022 16:11:05 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/03/2022 16:11:09 - INFO - codeparrot_training - Step 2355: {'lr': 0.0004999929019185491, 'samples': 1206272, 'steps': 2355, 'loss/train': 2.9823479652404785}
-03/03/2022 16:11:12 - INFO - codeparrot_training - Step 2356: {'lr': 0.0004999928618732256, 'samples': 1206784, 'steps': 2356, 'loss/train': 2.6017024517059326}
-03/03/2022 16:11:13 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/03/2022 16:11:19 - INFO - codeparrot_training - Step 2357: {'lr': 0.0004999928217152591, 'samples': 1207296, 'steps': 2357, 'loss/train': 3.004572868347168}
-03/03/2022 16:11:22 - INFO - codeparrot_training - Step 2358: {'lr': 0.0004999927814446498, 'samples': 1207808, 'steps': 2358, 'loss/train': 3.047327995300293}
-03/03/2022 16:11:25 - INFO - codeparrot_training - Step 2359: {'lr': 0.0004999927410613975, 'samples': 1208320, 'steps': 2359, 'loss/train': 2.6660752296447754}
-03/03/2022 16:11:26 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/03/2022 16:11:30 - INFO - codeparrot_training - Step 2360: {'lr': 0.0004999927005655024, 'samples': 1208832, 'steps': 2360, 'loss/train': 5.5060224533081055}
-03/03/2022 16:11:33 - INFO - codeparrot_training - Step 2361: {'lr': 0.0004999926599569644, 'samples': 1209344, 'steps': 2361, 'loss/train': 3.2518301010131836}
-03/03/2022 16:11:34 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/03/2022 16:11:39 - INFO - codeparrot_training - Step 2362: {'lr': 0.0004999926192357836, 'samples': 1209856, 'steps': 2362, 'loss/train': 3.4132797718048096}
-03/03/2022 16:11:42 - INFO - codeparrot_training - Step 2363: {'lr': 0.00049999257840196, 'samples': 1210368, 'steps': 2363, 'loss/train': 3.439847230911255}
-03/03/2022 16:11:42 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/03/2022 16:11:47 - INFO - codeparrot_training - Step 2364: {'lr': 0.0004999925374554936, 'samples': 1210880, 'steps': 2364, 'loss/train': 2.345672130584717}
-03/03/2022 16:11:50 - INFO - codeparrot_training - Step 2365: {'lr': 0.0004999924963963845, 'samples': 1211392, 'steps': 2365, 'loss/train': 3.1876866817474365}
-03/03/2022 16:11:51 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/03/2022 16:11:55 - INFO - codeparrot_training - Step 2366: {'lr': 0.0004999924552246324, 'samples': 1211904, 'steps': 2366, 'loss/train': 3.294334650039673}
-03/03/2022 16:11:58 - INFO - codeparrot_training - Step 2367: {'lr': 0.0004999924139402378, 'samples': 1212416, 'steps': 2367, 'loss/train': 4.286800384521484}
-03/03/2022 16:11:59 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/03/2022 16:12:04 - INFO - codeparrot_training - Step 2368: {'lr': 0.0004999923725432004, 'samples': 1212928, 'steps': 2368, 'loss/train': 2.7459046840667725}
-03/03/2022 16:12:07 - INFO - codeparrot_training - Step 2369: {'lr': 0.0004999923310335202, 'samples': 1213440, 'steps': 2369, 'loss/train': 3.5260021686553955}
-03/03/2022 16:12:07 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/03/2022 16:12:12 - INFO - codeparrot_training - Step 2370: {'lr': 0.0004999922894111975, 'samples': 1213952, 'steps': 2370, 'loss/train': 3.4140329360961914}
-03/03/2022 16:12:15 - INFO - codeparrot_training - Step 2371: {'lr': 0.000499992247676232, 'samples': 1214464, 'steps': 2371, 'loss/train': 3.0296790599823}
-03/03/2022 16:12:16 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/03/2022 16:12:20 - INFO - codeparrot_training - Step 2372: {'lr': 0.0004999922058286238, 'samples': 1214976, 'steps': 2372, 'loss/train': 3.218442440032959}
-03/03/2022 16:12:24 - INFO - codeparrot_training - Step 2373: {'lr': 0.0004999921638683731, 'samples': 1215488, 'steps': 2373, 'loss/train': 2.8287227153778076}
-03/03/2022 16:12:24 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/03/2022 16:12:29 - INFO - codeparrot_training - Step 2374: {'lr': 0.0004999921217954797, 'samples': 1216000, 'steps': 2374, 'loss/train': 3.5401194095611572}
-03/03/2022 16:12:32 - INFO - codeparrot_training - Step 2375: {'lr': 0.0004999920796099437, 'samples': 1216512, 'steps': 2375, 'loss/train': 2.5211355686187744}
-03/03/2022 16:12:33 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/03/2022 16:12:37 - INFO - codeparrot_training - Step 2376: {'lr': 0.0004999920373117652, 'samples': 1217024, 'steps': 2376, 'loss/train': 2.916353940963745}
-03/03/2022 16:12:41 - INFO - codeparrot_training - Step 2377: {'lr': 0.0004999919949009442, 'samples': 1217536, 'steps': 2377, 'loss/train': 2.8482859134674072}
-03/03/2022 16:12:41 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/03/2022 16:12:46 - INFO - codeparrot_training - Step 2378: {'lr': 0.0004999919523774806, 'samples': 1218048, 'steps': 2378, 'loss/train': 3.3612005710601807}
-03/03/2022 16:12:49 - INFO - codeparrot_training - Step 2379: {'lr': 0.0004999919097413743, 'samples': 1218560, 'steps': 2379, 'loss/train': 4.168346881866455}
-03/03/2022 16:12:50 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/03/2022 16:12:54 - INFO - codeparrot_training - Step 2380: {'lr': 0.0004999918669926258, 'samples': 1219072, 'steps': 2380, 'loss/train': 4.019054412841797}
-03/03/2022 16:12:57 - INFO - codeparrot_training - Step 2381: {'lr': 0.0004999918241312346, 'samples': 1219584, 'steps': 2381, 'loss/train': 3.4647421836853027}
-03/03/2022 16:12:58 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/03/2022 16:13:03 - INFO - codeparrot_training - Step 2382: {'lr': 0.0004999917811572011, 'samples': 1220096, 'steps': 2382, 'loss/train': 3.70270037651062}
-03/03/2022 16:13:06 - INFO - codeparrot_training - Step 2383: {'lr': 0.000499991738070525, 'samples': 1220608, 'steps': 2383, 'loss/train': 3.242283582687378}
-03/03/2022 16:13:06 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/03/2022 16:13:11 - INFO - codeparrot_training - Step 2384: {'lr': 0.0004999916948712066, 'samples': 1221120, 'steps': 2384, 'loss/train': 4.30795955657959}
-03/03/2022 16:13:14 - INFO - codeparrot_training - Step 2385: {'lr': 0.0004999916515592458, 'samples': 1221632, 'steps': 2385, 'loss/train': 3.269681692123413}
-03/03/2022 16:13:15 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/03/2022 16:13:20 - INFO - codeparrot_training - Step 2386: {'lr': 0.0004999916081346426, 'samples': 1222144, 'steps': 2386, 'loss/train': 3.6740543842315674}
-03/03/2022 16:13:23 - INFO - codeparrot_training - Step 2387: {'lr': 0.000499991564597397, 'samples': 1222656, 'steps': 2387, 'loss/train': 2.9508981704711914}
-03/03/2022 16:13:23 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/03/2022 16:13:28 - INFO - codeparrot_training - Step 2388: {'lr': 0.0004999915209475091, 'samples': 1223168, 'steps': 2388, 'loss/train': 2.972585439682007}
-03/03/2022 16:13:31 - INFO - codeparrot_training - Step 2389: {'lr': 0.0004999914771849788, 'samples': 1223680, 'steps': 2389, 'loss/train': 3.5003321170806885}
-03/03/2022 16:13:31 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/03/2022 16:13:36 - INFO - codeparrot_training - Step 2390: {'lr': 0.0004999914333098063, 'samples': 1224192, 'steps': 2390, 'loss/train': 2.90128231048584}
-03/03/2022 16:13:39 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/03/2022 16:13:42 - INFO - codeparrot_training - Step 2391: {'lr': 0.0004999913893219915, 'samples': 1224704, 'steps': 2391, 'loss/train': 2.4618241786956787}
-03/03/2022 16:13:45 - INFO - codeparrot_training - Step 2392: {'lr': 0.0004999913452215345, 'samples': 1225216, 'steps': 2392, 'loss/train': 2.814356565475464}
-03/03/2022 16:13:48 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/03/2022 16:13:50 - INFO - codeparrot_training - Step 2393: {'lr': 0.0004999913010084351, 'samples': 1225728, 'steps': 2393, 'loss/train': 3.2441394329071045}
-03/03/2022 16:13:53 - INFO - codeparrot_training - Step 2394: {'lr': 0.0004999912566826935, 'samples': 1226240, 'steps': 2394, 'loss/train': 3.7821013927459717}
-03/03/2022 16:13:56 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/03/2022 16:13:58 - INFO - codeparrot_training - Step 2395: {'lr': 0.0004999912122443098, 'samples': 1226752, 'steps': 2395, 'loss/train': 2.7253780364990234}
-03/03/2022 16:14:01 - INFO - codeparrot_training - Step 2396: {'lr': 0.0004999911676932838, 'samples': 1227264, 'steps': 2396, 'loss/train': 2.9002113342285156}
-03/03/2022 16:14:04 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/03/2022 16:14:07 - INFO - codeparrot_training - Step 2397: {'lr': 0.0004999911230296158, 'samples': 1227776, 'steps': 2397, 'loss/train': 3.4079055786132812}
-03/03/2022 16:14:10 - INFO - codeparrot_training - Step 2398: {'lr': 0.0004999910782533055, 'samples': 1228288, 'steps': 2398, 'loss/train': 3.3085381984710693}
-03/03/2022 16:14:12 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/03/2022 16:14:15 - INFO - codeparrot_training - Step 2399: {'lr': 0.0004999910333643531, 'samples': 1228800, 'steps': 2399, 'loss/train': 3.7810471057891846}
-03/03/2022 16:14:18 - INFO - codeparrot_training - Step 2400: {'lr': 0.0004999909883627587, 'samples': 1229312, 'steps': 2400, 'loss/train': 2.359142780303955}
-03/03/2022 16:14:20 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/03/2022 16:14:24 - INFO - codeparrot_training - Step 2401: {'lr': 0.0004999909432485221, 'samples': 1229824, 'steps': 2401, 'loss/train': 2.2719218730926514}
-03/03/2022 16:14:27 - INFO - codeparrot_training - Step 2402: {'lr': 0.0004999908980216436, 'samples': 1230336, 'steps': 2402, 'loss/train': 2.815001964569092}
-03/03/2022 16:14:29 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/03/2022 16:14:32 - INFO - codeparrot_training - Step 2403: {'lr': 0.0004999908526821229, 'samples': 1230848, 'steps': 2403, 'loss/train': 3.1026618480682373}
-03/03/2022 16:14:35 - INFO - codeparrot_training - Step 2404: {'lr': 0.0004999908072299602, 'samples': 1231360, 'steps': 2404, 'loss/train': 2.900294542312622}
-03/03/2022 16:14:37 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/03/2022 16:14:40 - INFO - codeparrot_training - Step 2405: {'lr': 0.0004999907616651556, 'samples': 1231872, 'steps': 2405, 'loss/train': 2.3728840351104736}
-03/03/2022 16:14:43 - INFO - codeparrot_training - Step 2406: {'lr': 0.000499990715987709, 'samples': 1232384, 'steps': 2406, 'loss/train': 3.0262739658355713}
-03/03/2022 16:14:46 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/03/2022 16:14:49 - INFO - codeparrot_training - Step 2407: {'lr': 0.0004999906701976203, 'samples': 1232896, 'steps': 2407, 'loss/train': 2.347027063369751}
-03/03/2022 16:14:52 - INFO - codeparrot_training - Step 2408: {'lr': 0.0004999906242948898, 'samples': 1233408, 'steps': 2408, 'loss/train': 2.5089776515960693}
-03/03/2022 16:14:54 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/03/2022 16:14:57 - INFO - codeparrot_training - Step 2409: {'lr': 0.0004999905782795173, 'samples': 1233920, 'steps': 2409, 'loss/train': 3.1692869663238525}
-03/03/2022 16:15:00 - INFO - codeparrot_training - Step 2410: {'lr': 0.000499990532151503, 'samples': 1234432, 'steps': 2410, 'loss/train': 3.394524335861206}
-03/03/2022 16:15:02 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/03/2022 16:15:06 - INFO - codeparrot_training - Step 2411: {'lr': 0.0004999904859108467, 'samples': 1234944, 'steps': 2411, 'loss/train': 3.1552481651306152}
-03/03/2022 16:15:09 - INFO - codeparrot_training - Step 2412: {'lr': 0.0004999904395575486, 'samples': 1235456, 'steps': 2412, 'loss/train': 3.102290630340576}
-03/03/2022 16:15:11 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/03/2022 16:15:14 - INFO - codeparrot_training - Step 2413: {'lr': 0.0004999903930916087, 'samples': 1235968, 'steps': 2413, 'loss/train': 3.4390149116516113}
-03/03/2022 16:15:17 - INFO - codeparrot_training - Step 2414: {'lr': 0.000499990346513027, 'samples': 1236480, 'steps': 2414, 'loss/train': 2.2866628170013428}
-03/03/2022 16:15:19 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/03/2022 16:15:22 - INFO - codeparrot_training - Step 2415: {'lr': 0.0004999902998218034, 'samples': 1236992, 'steps': 2415, 'loss/train': 3.4210660457611084}
-03/03/2022 16:15:26 - INFO - codeparrot_training - Step 2416: {'lr': 0.000499990253017938, 'samples': 1237504, 'steps': 2416, 'loss/train': 1.953756332397461}
-03/03/2022 16:15:27 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/03/2022 16:15:31 - INFO - codeparrot_training - Step 2417: {'lr': 0.0004999902061014311, 'samples': 1238016, 'steps': 2417, 'loss/train': 2.254668712615967}
-03/03/2022 16:15:34 - INFO - codeparrot_training - Step 2418: {'lr': 0.0004999901590722823, 'samples': 1238528, 'steps': 2418, 'loss/train': 3.59061336517334}
-03/03/2022 16:15:35 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/03/2022 16:15:39 - INFO - codeparrot_training - Step 2419: {'lr': 0.0004999901119304919, 'samples': 1239040, 'steps': 2419, 'loss/train': 2.7408499717712402}
-03/03/2022 16:15:42 - INFO - codeparrot_training - Step 2420: {'lr': 0.0004999900646760597, 'samples': 1239552, 'steps': 2420, 'loss/train': 3.4129180908203125}
-03/03/2022 16:15:44 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/03/2022 16:15:47 - INFO - codeparrot_training - Step 2421: {'lr': 0.0004999900173089858, 'samples': 1240064, 'steps': 2421, 'loss/train': 3.2427544593811035}
-03/03/2022 16:15:51 - INFO - codeparrot_training - Step 2422: {'lr': 0.0004999899698292703, 'samples': 1240576, 'steps': 2422, 'loss/train': 3.2978503704071045}
-03/03/2022 16:15:52 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/03/2022 16:15:56 - INFO - codeparrot_training - Step 2423: {'lr': 0.0004999899222369132, 'samples': 1241088, 'steps': 2423, 'loss/train': 3.648098945617676}
-03/03/2022 16:15:59 - INFO - codeparrot_training - Step 2424: {'lr': 0.0004999898745319145, 'samples': 1241600, 'steps': 2424, 'loss/train': 2.8868560791015625}
-03/03/2022 16:16:00 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/03/2022 16:16:04 - INFO - codeparrot_training - Step 2425: {'lr': 0.0004999898267142741, 'samples': 1242112, 'steps': 2425, 'loss/train': 3.0442099571228027}
-03/03/2022 16:16:08 - INFO - codeparrot_training - Step 2426: {'lr': 0.0004999897787839923, 'samples': 1242624, 'steps': 2426, 'loss/train': 2.8172223567962646}
-03/03/2022 16:16:08 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/03/2022 16:16:13 - INFO - codeparrot_training - Step 2427: {'lr': 0.000499989730741069, 'samples': 1243136, 'steps': 2427, 'loss/train': 2.9016196727752686}
-03/03/2022 16:16:16 - INFO - codeparrot_training - Step 2428: {'lr': 0.000499989682585504, 'samples': 1243648, 'steps': 2428, 'loss/train': 2.6202454566955566}
-03/03/2022 16:16:17 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/03/2022 16:16:21 - INFO - codeparrot_training - Step 2429: {'lr': 0.0004999896343172976, 'samples': 1244160, 'steps': 2429, 'loss/train': 3.309250593185425}
-03/03/2022 16:16:24 - INFO - codeparrot_training - Step 2430: {'lr': 0.0004999895859364498, 'samples': 1244672, 'steps': 2430, 'loss/train': 3.224417209625244}
-03/03/2022 16:16:25 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/03/2022 16:16:30 - INFO - codeparrot_training - Step 2431: {'lr': 0.0004999895374429605, 'samples': 1245184, 'steps': 2431, 'loss/train': 2.3102617263793945}
-03/03/2022 16:16:33 - INFO - codeparrot_training - Step 2432: {'lr': 0.0004999894888368297, 'samples': 1245696, 'steps': 2432, 'loss/train': 3.905405282974243}
-03/03/2022 16:16:33 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 16:16:38 - INFO - codeparrot_training - Step 2433: {'lr': 0.0004999894401180576, 'samples': 1246208, 'steps': 2433, 'loss/train': 1.721686601638794}
-03/03/2022 16:16:41 - INFO - codeparrot_training - Step 2434: {'lr': 0.0004999893912866441, 'samples': 1246720, 'steps': 2434, 'loss/train': 2.388075828552246}
-03/03/2022 16:16:41 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/03/2022 16:16:46 - INFO - codeparrot_training - Step 2435: {'lr': 0.0004999893423425892, 'samples': 1247232, 'steps': 2435, 'loss/train': 2.9567904472351074}
-03/03/2022 16:16:50 - INFO - codeparrot_training - Step 2436: {'lr': 0.0004999892932858929, 'samples': 1247744, 'steps': 2436, 'loss/train': 1.9273074865341187}
-03/03/2022 16:16:50 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/03/2022 16:16:55 - INFO - codeparrot_training - Step 2437: {'lr': 0.0004999892441165554, 'samples': 1248256, 'steps': 2437, 'loss/train': 3.0093343257904053}
-03/03/2022 16:16:58 - INFO - codeparrot_training - Step 2438: {'lr': 0.0004999891948345765, 'samples': 1248768, 'steps': 2438, 'loss/train': 2.2821545600891113}
-03/03/2022 16:16:59 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/03/2022 16:17:03 - INFO - codeparrot_training - Step 2439: {'lr': 0.0004999891454399565, 'samples': 1249280, 'steps': 2439, 'loss/train': 3.1050679683685303}
-03/03/2022 16:17:07 - INFO - codeparrot_training - Step 2440: {'lr': 0.000499989095932695, 'samples': 1249792, 'steps': 2440, 'loss/train': 2.4375011920928955}
-03/03/2022 16:17:07 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/03/2022 16:17:12 - INFO - codeparrot_training - Step 2441: {'lr': 0.0004999890463127924, 'samples': 1250304, 'steps': 2441, 'loss/train': 2.7024149894714355}
-03/03/2022 16:17:15 - INFO - codeparrot_training - Step 2442: {'lr': 0.0004999889965802486, 'samples': 1250816, 'steps': 2442, 'loss/train': 3.8853774070739746}
-03/03/2022 16:17:16 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/03/2022 16:17:20 - INFO - codeparrot_training - Step 2443: {'lr': 0.0004999889467350636, 'samples': 1251328, 'steps': 2443, 'loss/train': 2.303218364715576}
-03/03/2022 16:17:24 - INFO - codeparrot_training - Step 2444: {'lr': 0.0004999888967772375, 'samples': 1251840, 'steps': 2444, 'loss/train': 2.5290753841400146}
-03/03/2022 16:17:24 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/03/2022 16:17:29 - INFO - codeparrot_training - Step 2445: {'lr': 0.0004999888467067702, 'samples': 1252352, 'steps': 2445, 'loss/train': 2.7982707023620605}
-03/03/2022 16:17:32 - INFO - codeparrot_training - Step 2446: {'lr': 0.0004999887965236617, 'samples': 1252864, 'steps': 2446, 'loss/train': 1.5639216899871826}
-03/03/2022 16:17:33 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/03/2022 16:17:37 - INFO - codeparrot_training - Step 2447: {'lr': 0.0004999887462279123, 'samples': 1253376, 'steps': 2447, 'loss/train': 3.469240188598633}
-03/03/2022 16:17:40 - INFO - codeparrot_training - Step 2448: {'lr': 0.0004999886958195216, 'samples': 1253888, 'steps': 2448, 'loss/train': 2.5281832218170166}
-03/03/2022 16:17:41 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/03/2022 16:17:46 - INFO - codeparrot_training - Step 2449: {'lr': 0.00049998864529849, 'samples': 1254400, 'steps': 2449, 'loss/train': 3.104919195175171}
-03/03/2022 16:17:49 - INFO - codeparrot_training - Step 2450: {'lr': 0.0004999885946648174, 'samples': 1254912, 'steps': 2450, 'loss/train': 2.9260053634643555}
-03/03/2022 16:17:49 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/03/2022 16:17:54 - INFO - codeparrot_training - Step 2451: {'lr': 0.0004999885439185037, 'samples': 1255424, 'steps': 2451, 'loss/train': 2.8842074871063232}
-03/03/2022 16:17:57 - INFO - codeparrot_training - Step 2452: {'lr': 0.0004999884930595491, 'samples': 1255936, 'steps': 2452, 'loss/train': 4.428753852844238}
-03/03/2022 16:17:58 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/03/2022 16:18:03 - INFO - codeparrot_training - Step 2453: {'lr': 0.0004999884420879534, 'samples': 1256448, 'steps': 2453, 'loss/train': 3.476101875305176}
-03/03/2022 16:18:06 - INFO - codeparrot_training - Step 2454: {'lr': 0.000499988391003717, 'samples': 1256960, 'steps': 2454, 'loss/train': 3.281400203704834}
-03/03/2022 16:18:06 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/03/2022 16:18:11 - INFO - codeparrot_training - Step 2455: {'lr': 0.0004999883398068396, 'samples': 1257472, 'steps': 2455, 'loss/train': 2.3167288303375244}
-03/03/2022 16:18:14 - INFO - codeparrot_training - Step 2456: {'lr': 0.0004999882884973212, 'samples': 1257984, 'steps': 2456, 'loss/train': 3.890521287918091}
-03/03/2022 16:18:14 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/03/2022 16:18:19 - INFO - codeparrot_training - Step 2457: {'lr': 0.000499988237075162, 'samples': 1258496, 'steps': 2457, 'loss/train': 0.8238630294799805}
-03/03/2022 16:18:23 - INFO - codeparrot_training - Step 2458: {'lr': 0.000499988185540362, 'samples': 1259008, 'steps': 2458, 'loss/train': 2.5662012100219727}
-03/03/2022 16:18:23 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/03/2022 16:18:28 - INFO - codeparrot_training - Step 2459: {'lr': 0.0004999881338929211, 'samples': 1259520, 'steps': 2459, 'loss/train': 2.84232497215271}
-03/03/2022 16:18:31 - INFO - codeparrot_training - Step 2460: {'lr': 0.0004999880821328395, 'samples': 1260032, 'steps': 2460, 'loss/train': 3.193075656890869}
-03/03/2022 16:18:31 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/03/2022 16:18:36 - INFO - codeparrot_training - Step 2461: {'lr': 0.000499988030260117, 'samples': 1260544, 'steps': 2461, 'loss/train': 3.0208098888397217}
-03/03/2022 16:18:40 - INFO - codeparrot_training - Step 2462: {'lr': 0.0004999879782747539, 'samples': 1261056, 'steps': 2462, 'loss/train': 2.596449851989746}
-03/03/2022 16:18:40 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/03/2022 16:18:46 - INFO - codeparrot_training - Step 2463: {'lr': 0.00049998792617675, 'samples': 1261568, 'steps': 2463, 'loss/train': 3.271831750869751}
-03/03/2022 16:18:49 - INFO - codeparrot_training - Step 2464: {'lr': 0.0004999878739661053, 'samples': 1262080, 'steps': 2464, 'loss/train': 3.159120798110962}
-03/03/2022 16:18:50 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/03/2022 16:18:54 - INFO - codeparrot_training - Step 2465: {'lr': 0.0004999878216428201, 'samples': 1262592, 'steps': 2465, 'loss/train': 2.5441982746124268}
-03/03/2022 16:18:57 - INFO - codeparrot_training - Step 2466: {'lr': 0.0004999877692068942, 'samples': 1263104, 'steps': 2466, 'loss/train': 2.4670543670654297}
-03/03/2022 16:18:59 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/03/2022 16:19:02 - INFO - codeparrot_training - Step 2467: {'lr': 0.0004999877166583276, 'samples': 1263616, 'steps': 2467, 'loss/train': 3.816309928894043}
-03/03/2022 16:19:06 - INFO - codeparrot_training - Step 2468: {'lr': 0.0004999876639971204, 'samples': 1264128, 'steps': 2468, 'loss/train': 2.9453892707824707}
-03/03/2022 16:19:07 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/03/2022 16:19:11 - INFO - codeparrot_training - Step 2469: {'lr': 0.0004999876112232726, 'samples': 1264640, 'steps': 2469, 'loss/train': 3.4072937965393066}
-03/03/2022 16:19:14 - INFO - codeparrot_training - Step 2470: {'lr': 0.0004999875583367844, 'samples': 1265152, 'steps': 2470, 'loss/train': 2.753385543823242}
-03/03/2022 16:19:15 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/03/2022 16:19:19 - INFO - codeparrot_training - Step 2471: {'lr': 0.0004999875053376555, 'samples': 1265664, 'steps': 2471, 'loss/train': 3.0363874435424805}
-03/03/2022 16:19:22 - INFO - codeparrot_training - Step 2472: {'lr': 0.0004999874522258861, 'samples': 1266176, 'steps': 2472, 'loss/train': 2.5519156455993652}
-03/03/2022 16:19:23 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/03/2022 16:19:28 - INFO - codeparrot_training - Step 2473: {'lr': 0.0004999873990014763, 'samples': 1266688, 'steps': 2473, 'loss/train': 3.166799545288086}
-03/03/2022 16:19:31 - INFO - codeparrot_training - Step 2474: {'lr': 0.0004999873456644259, 'samples': 1267200, 'steps': 2474, 'loss/train': 2.9901912212371826}
-03/03/2022 16:19:32 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/03/2022 16:19:37 - INFO - codeparrot_training - Step 2475: {'lr': 0.0004999872922147352, 'samples': 1267712, 'steps': 2475, 'loss/train': 2.8614206314086914}
-03/03/2022 16:19:40 - INFO - codeparrot_training - Step 2476: {'lr': 0.0004999872386524041, 'samples': 1268224, 'steps': 2476, 'loss/train': 2.3810527324676514}
-03/03/2022 16:19:43 - INFO - codeparrot_training - Step 2477: {'lr': 0.0004999871849774325, 'samples': 1268736, 'steps': 2477, 'loss/train': 3.614152669906616}
-03/03/2022 16:19:43 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/03/2022 16:19:48 - INFO - codeparrot_training - Step 2478: {'lr': 0.0004999871311898205, 'samples': 1269248, 'steps': 2478, 'loss/train': 3.7695107460021973}
-03/03/2022 16:19:51 - INFO - codeparrot_training - Step 2479: {'lr': 0.0004999870772895683, 'samples': 1269760, 'steps': 2479, 'loss/train': 2.80676007270813}
-03/03/2022 16:19:51 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/03/2022 16:19:57 - INFO - codeparrot_training - Step 2480: {'lr': 0.0004999870232766756, 'samples': 1270272, 'steps': 2480, 'loss/train': 2.938058376312256}
-03/03/2022 16:20:00 - INFO - codeparrot_training - Step 2481: {'lr': 0.0004999869691511428, 'samples': 1270784, 'steps': 2481, 'loss/train': 3.4740536212921143}
-03/03/2022 16:20:00 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/03/2022 16:20:05 - INFO - codeparrot_training - Step 2482: {'lr': 0.0004999869149129696, 'samples': 1271296, 'steps': 2482, 'loss/train': 3.245323657989502}
-03/03/2022 16:20:08 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/03/2022 16:20:10 - INFO - codeparrot_training - Step 2483: {'lr': 0.0004999868605621563, 'samples': 1271808, 'steps': 2483, 'loss/train': 3.025552749633789}
-03/03/2022 16:20:13 - INFO - codeparrot_training - Step 2484: {'lr': 0.0004999868060987027, 'samples': 1272320, 'steps': 2484, 'loss/train': 3.455415725708008}
-03/03/2022 16:20:17 - INFO - codeparrot_training - Step 2485: {'lr': 0.0004999867515226088, 'samples': 1272832, 'steps': 2485, 'loss/train': 2.180940866470337}
-03/03/2022 16:20:17 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/03/2022 16:20:22 - INFO - codeparrot_training - Step 2486: {'lr': 0.0004999866968338748, 'samples': 1273344, 'steps': 2486, 'loss/train': 0.6444083452224731}
-03/03/2022 16:20:25 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/03/2022 16:20:27 - INFO - codeparrot_training - Step 2487: {'lr': 0.0004999866420325006, 'samples': 1273856, 'steps': 2487, 'loss/train': 3.20237135887146}
-03/03/2022 16:20:30 - INFO - codeparrot_training - Step 2488: {'lr': 0.0004999865871184863, 'samples': 1274368, 'steps': 2488, 'loss/train': 4.782764911651611}
-03/03/2022 16:20:33 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/03/2022 16:20:36 - INFO - codeparrot_training - Step 2489: {'lr': 0.000499986532091832, 'samples': 1274880, 'steps': 2489, 'loss/train': 2.8954098224639893}
-03/03/2022 16:20:39 - INFO - codeparrot_training - Step 2490: {'lr': 0.0004999864769525375, 'samples': 1275392, 'steps': 2490, 'loss/train': 1.8068829774856567}
-03/03/2022 16:20:42 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/03/2022 16:20:44 - INFO - codeparrot_training - Step 2491: {'lr': 0.000499986421700603, 'samples': 1275904, 'steps': 2491, 'loss/train': 2.3099799156188965}
-03/03/2022 16:20:47 - INFO - codeparrot_training - Step 2492: {'lr': 0.0004999863663360285, 'samples': 1276416, 'steps': 2492, 'loss/train': 3.421651840209961}
-03/03/2022 16:20:50 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/03/2022 16:20:53 - INFO - codeparrot_training - Step 2493: {'lr': 0.000499986310858814, 'samples': 1276928, 'steps': 2493, 'loss/train': 3.2742176055908203}
-03/03/2022 16:20:56 - INFO - codeparrot_training - Step 2494: {'lr': 0.0004999862552689595, 'samples': 1277440, 'steps': 2494, 'loss/train': 2.8373236656188965}
-03/03/2022 16:20:58 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/03/2022 16:21:01 - INFO - codeparrot_training - Step 2495: {'lr': 0.000499986199566465, 'samples': 1277952, 'steps': 2495, 'loss/train': 2.910813093185425}
-03/03/2022 16:21:04 - INFO - codeparrot_training - Step 2496: {'lr': 0.0004999861437513306, 'samples': 1278464, 'steps': 2496, 'loss/train': 3.323831558227539}
-03/03/2022 16:21:06 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/03/2022 16:21:09 - INFO - codeparrot_training - Step 2497: {'lr': 0.0004999860878235564, 'samples': 1278976, 'steps': 2497, 'loss/train': 2.974306583404541}
-03/03/2022 16:21:13 - INFO - codeparrot_training - Step 2498: {'lr': 0.0004999860317831423, 'samples': 1279488, 'steps': 2498, 'loss/train': 3.1286723613739014}
-03/03/2022 16:21:14 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/03/2022 16:21:18 - INFO - codeparrot_training - Step 2499: {'lr': 0.0004999859756300883, 'samples': 1280000, 'steps': 2499, 'loss/train': 3.0235705375671387}
-03/03/2022 16:21:21 - INFO - codeparrot_training - Step 2500: {'lr': 0.0004999859193643945, 'samples': 1280512, 'steps': 2500, 'loss/train': 3.4169411659240723}
-03/03/2022 16:21:23 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/03/2022 16:21:26 - INFO - codeparrot_training - Step 2501: {'lr': 0.0004999858629860609, 'samples': 1281024, 'steps': 2501, 'loss/train': 2.4314191341400146}
-03/03/2022 16:21:29 - INFO - codeparrot_training - Step 2502: {'lr': 0.0004999858064950875, 'samples': 1281536, 'steps': 2502, 'loss/train': 2.833728313446045}
-03/03/2022 16:21:31 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/03/2022 16:21:35 - INFO - codeparrot_training - Step 2503: {'lr': 0.0004999857498914744, 'samples': 1282048, 'steps': 2503, 'loss/train': 3.0542643070220947}
-03/03/2022 16:21:38 - INFO - codeparrot_training - Step 2504: {'lr': 0.0004999856931752215, 'samples': 1282560, 'steps': 2504, 'loss/train': 4.078123569488525}
-03/03/2022 16:21:40 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/03/2022 16:21:43 - INFO - codeparrot_training - Step 2505: {'lr': 0.000499985636346329, 'samples': 1283072, 'steps': 2505, 'loss/train': 0.897447407245636}
-03/03/2022 16:21:46 - INFO - codeparrot_training - Step 2506: {'lr': 0.0004999855794047968, 'samples': 1283584, 'steps': 2506, 'loss/train': 3.264345645904541}
-03/03/2022 16:21:48 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/03/2022 16:21:52 - INFO - codeparrot_training - Step 2507: {'lr': 0.000499985522350625, 'samples': 1284096, 'steps': 2507, 'loss/train': 2.348832130432129}
-03/03/2022 16:21:55 - INFO - codeparrot_training - Step 2508: {'lr': 0.0004999854651838134, 'samples': 1284608, 'steps': 2508, 'loss/train': 3.6561119556427}
-03/03/2022 16:21:57 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/03/2022 16:22:00 - INFO - codeparrot_training - Step 2509: {'lr': 0.0004999854079043624, 'samples': 1285120, 'steps': 2509, 'loss/train': 4.345146179199219}
-03/03/2022 16:22:03 - INFO - codeparrot_training - Step 2510: {'lr': 0.0004999853505122718, 'samples': 1285632, 'steps': 2510, 'loss/train': 2.546726703643799}
-03/03/2022 16:22:05 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/03/2022 16:22:08 - INFO - codeparrot_training - Step 2511: {'lr': 0.0004999852930075416, 'samples': 1286144, 'steps': 2511, 'loss/train': 2.6213409900665283}
-03/03/2022 16:22:12 - INFO - codeparrot_training - Step 2512: {'lr': 0.0004999852353901719, 'samples': 1286656, 'steps': 2512, 'loss/train': 3.1558749675750732}
-03/03/2022 16:22:13 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/03/2022 16:22:17 - INFO - codeparrot_training - Step 2513: {'lr': 0.0004999851776601627, 'samples': 1287168, 'steps': 2513, 'loss/train': 3.087672233581543}
-03/03/2022 16:22:20 - INFO - codeparrot_training - Step 2514: {'lr': 0.0004999851198175141, 'samples': 1287680, 'steps': 2514, 'loss/train': 3.7087156772613525}
-03/03/2022 16:22:22 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/03/2022 16:22:25 - INFO - codeparrot_training - Step 2515: {'lr': 0.0004999850618622259, 'samples': 1288192, 'steps': 2515, 'loss/train': 0.6918866038322449}
-03/03/2022 16:22:28 - INFO - codeparrot_training - Step 2516: {'lr': 0.0004999850037942984, 'samples': 1288704, 'steps': 2516, 'loss/train': 6.471134662628174}
-03/03/2022 16:22:30 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/03/2022 16:22:34 - INFO - codeparrot_training - Step 2517: {'lr': 0.0004999849456137316, 'samples': 1289216, 'steps': 2517, 'loss/train': 3.3622610569000244}
-03/03/2022 16:22:37 - INFO - codeparrot_training - Step 2518: {'lr': 0.0004999848873205254, 'samples': 1289728, 'steps': 2518, 'loss/train': 3.737034559249878}
-03/03/2022 16:22:38 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/03/2022 16:22:42 - INFO - codeparrot_training - Step 2519: {'lr': 0.0004999848289146798, 'samples': 1290240, 'steps': 2519, 'loss/train': 2.79614520072937}
-03/03/2022 16:22:45 - INFO - codeparrot_training - Step 2520: {'lr': 0.0004999847703961948, 'samples': 1290752, 'steps': 2520, 'loss/train': 1.873476505279541}
-03/03/2022 16:22:47 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/03/2022 16:22:50 - INFO - codeparrot_training - Step 2521: {'lr': 0.0004999847117650708, 'samples': 1291264, 'steps': 2521, 'loss/train': 2.7374868392944336}
-03/03/2022 16:22:54 - INFO - codeparrot_training - Step 2522: {'lr': 0.0004999846530213074, 'samples': 1291776, 'steps': 2522, 'loss/train': 2.8232455253601074}
-03/03/2022 16:22:55 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/03/2022 16:22:59 - INFO - codeparrot_training - Step 2523: {'lr': 0.0004999845941649048, 'samples': 1292288, 'steps': 2523, 'loss/train': 2.8543264865875244}
-03/03/2022 16:23:02 - INFO - codeparrot_training - Step 2524: {'lr': 0.0004999845351958629, 'samples': 1292800, 'steps': 2524, 'loss/train': 2.803300619125366}
-03/03/2022 16:23:03 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/03/2022 16:23:07 - INFO - codeparrot_training - Step 2525: {'lr': 0.0004999844761141818, 'samples': 1293312, 'steps': 2525, 'loss/train': 3.112408399581909}
-03/03/2022 16:23:11 - INFO - codeparrot_training - Step 2526: {'lr': 0.0004999844169198617, 'samples': 1293824, 'steps': 2526, 'loss/train': 2.4133479595184326}
-03/03/2022 16:23:12 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/03/2022 16:23:16 - INFO - codeparrot_training - Step 2527: {'lr': 0.0004999843576129024, 'samples': 1294336, 'steps': 2527, 'loss/train': 3.1589486598968506}
-03/03/2022 16:23:19 - INFO - codeparrot_training - Step 2528: {'lr': 0.000499984298193304, 'samples': 1294848, 'steps': 2528, 'loss/train': 2.494608163833618}
-03/03/2022 16:23:20 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/03/2022 16:23:24 - INFO - codeparrot_training - Step 2529: {'lr': 0.0004999842386610666, 'samples': 1295360, 'steps': 2529, 'loss/train': 3.9454216957092285}
-03/03/2022 16:23:28 - INFO - codeparrot_training - Step 2530: {'lr': 0.0004999841790161901, 'samples': 1295872, 'steps': 2530, 'loss/train': 2.254082441329956}
-03/03/2022 16:23:29 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/03/2022 16:23:33 - INFO - codeparrot_training - Step 2531: {'lr': 0.0004999841192586746, 'samples': 1296384, 'steps': 2531, 'loss/train': 4.019567012786865}
-03/03/2022 16:23:36 - INFO - codeparrot_training - Step 2532: {'lr': 0.0004999840593885201, 'samples': 1296896, 'steps': 2532, 'loss/train': 3.2863903045654297}
-03/03/2022 16:23:37 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/03/2022 16:23:41 - INFO - codeparrot_training - Step 2533: {'lr': 0.0004999839994057266, 'samples': 1297408, 'steps': 2533, 'loss/train': 1.4264503717422485}
-03/03/2022 16:23:45 - INFO - codeparrot_training - Step 2534: {'lr': 0.0004999839393102943, 'samples': 1297920, 'steps': 2534, 'loss/train': 3.4209253787994385}
-03/03/2022 16:23:46 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/03/2022 16:23:50 - INFO - codeparrot_training - Step 2535: {'lr': 0.0004999838791022229, 'samples': 1298432, 'steps': 2535, 'loss/train': 3.1111221313476562}
-03/03/2022 16:23:53 - INFO - codeparrot_training - Step 2536: {'lr': 0.0004999838187815128, 'samples': 1298944, 'steps': 2536, 'loss/train': 3.1084094047546387}
-03/03/2022 16:23:54 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/03/2022 16:23:58 - INFO - codeparrot_training - Step 2537: {'lr': 0.0004999837583481638, 'samples': 1299456, 'steps': 2537, 'loss/train': 3.6611745357513428}
-03/03/2022 16:24:01 - INFO - codeparrot_training - Step 2538: {'lr': 0.000499983697802176, 'samples': 1299968, 'steps': 2538, 'loss/train': 3.2353146076202393}
-03/03/2022 16:24:03 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/03/2022 16:24:07 - INFO - codeparrot_training - Step 2539: {'lr': 0.0004999836371435494, 'samples': 1300480, 'steps': 2539, 'loss/train': 3.1310691833496094}
-03/03/2022 16:24:10 - INFO - codeparrot_training - Step 2540: {'lr': 0.000499983576372284, 'samples': 1300992, 'steps': 2540, 'loss/train': 3.1072871685028076}
-03/03/2022 16:24:11 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/03/2022 16:24:15 - INFO - codeparrot_training - Step 2541: {'lr': 0.0004999835154883798, 'samples': 1301504, 'steps': 2541, 'loss/train': 3.006399631500244}
-03/03/2022 16:24:18 - INFO - codeparrot_training - Step 2542: {'lr': 0.0004999834544918369, 'samples': 1302016, 'steps': 2542, 'loss/train': 3.5297250747680664}
-03/03/2022 16:24:19 - INFO - codeparrot_training - Skipping example with length 5 (seq_length=1024)
-03/03/2022 16:24:23 - INFO - codeparrot_training - Step 2543: {'lr': 0.0004999833933826554, 'samples': 1302528, 'steps': 2543, 'loss/train': 3.0366342067718506}
-03/03/2022 16:24:27 - INFO - codeparrot_training - Step 2544: {'lr': 0.0004999833321608351, 'samples': 1303040, 'steps': 2544, 'loss/train': 3.1857190132141113}
-03/03/2022 16:24:27 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/03/2022 16:24:32 - INFO - codeparrot_training - Step 2545: {'lr': 0.0004999832708263764, 'samples': 1303552, 'steps': 2545, 'loss/train': 3.755324363708496}
-03/03/2022 16:24:35 - INFO - codeparrot_training - Step 2546: {'lr': 0.000499983209379279, 'samples': 1304064, 'steps': 2546, 'loss/train': 3.7012033462524414}
-03/03/2022 16:24:36 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/03/2022 16:24:40 - INFO - codeparrot_training - Step 2547: {'lr': 0.0004999831478195429, 'samples': 1304576, 'steps': 2547, 'loss/train': 3.20994234085083}
-03/03/2022 16:24:43 - INFO - codeparrot_training - Step 2548: {'lr': 0.0004999830861471684, 'samples': 1305088, 'steps': 2548, 'loss/train': 0.6826435923576355}
-03/03/2022 16:24:44 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/03/2022 16:24:49 - INFO - codeparrot_training - Step 2549: {'lr': 0.0004999830243621553, 'samples': 1305600, 'steps': 2549, 'loss/train': 2.4455618858337402}
-03/03/2022 16:24:52 - INFO - codeparrot_training - Step 2550: {'lr': 0.0004999829624645037, 'samples': 1306112, 'steps': 2550, 'loss/train': 2.742499589920044}
-03/03/2022 16:24:52 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/03/2022 16:24:57 - INFO - codeparrot_training - Step 2551: {'lr': 0.0004999829004542136, 'samples': 1306624, 'steps': 2551, 'loss/train': 3.267723321914673}
-03/03/2022 16:25:00 - INFO - codeparrot_training - Step 2552: {'lr': 0.0004999828383312851, 'samples': 1307136, 'steps': 2552, 'loss/train': 3.2674925327301025}
-03/03/2022 16:25:01 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/03/2022 16:25:06 - INFO - codeparrot_training - Step 2553: {'lr': 0.0004999827760957182, 'samples': 1307648, 'steps': 2553, 'loss/train': 0.8292660117149353}
-03/03/2022 16:25:09 - INFO - codeparrot_training - Step 2554: {'lr': 0.000499982713747513, 'samples': 1308160, 'steps': 2554, 'loss/train': 3.120907783508301}
-03/03/2022 16:25:09 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/03/2022 16:25:14 - INFO - codeparrot_training - Step 2555: {'lr': 0.0004999826512866693, 'samples': 1308672, 'steps': 2555, 'loss/train': 3.702171564102173}
-03/03/2022 16:25:17 - INFO - codeparrot_training - Step 2556: {'lr': 0.0004999825887131874, 'samples': 1309184, 'steps': 2556, 'loss/train': 3.663010597229004}
-03/03/2022 16:25:18 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/03/2022 16:25:23 - INFO - codeparrot_training - Step 2557: {'lr': 0.0004999825260270671, 'samples': 1309696, 'steps': 2557, 'loss/train': 3.624185562133789}
-03/03/2022 16:25:26 - INFO - codeparrot_training - Step 2558: {'lr': 0.0004999824632283086, 'samples': 1310208, 'steps': 2558, 'loss/train': 2.0385353565216064}
-03/03/2022 16:25:26 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/03/2022 16:25:31 - INFO - codeparrot_training - Step 2559: {'lr': 0.0004999824003169119, 'samples': 1310720, 'steps': 2559, 'loss/train': 1.7916879653930664}
-03/03/2022 16:25:34 - INFO - codeparrot_training - Step 2560: {'lr': 0.000499982337292877, 'samples': 1311232, 'steps': 2560, 'loss/train': 1.947210431098938}
-03/03/2022 16:25:34 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/03/2022 16:25:39 - INFO - codeparrot_training - Step 2561: {'lr': 0.0004999822741562038, 'samples': 1311744, 'steps': 2561, 'loss/train': 2.9803450107574463}
-03/03/2022 16:25:43 - INFO - codeparrot_training - Step 2562: {'lr': 0.0004999822109068925, 'samples': 1312256, 'steps': 2562, 'loss/train': 1.7667006254196167}
-03/03/2022 16:25:43 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/03/2022 16:25:48 - INFO - codeparrot_training - Step 2563: {'lr': 0.000499982147544943, 'samples': 1312768, 'steps': 2563, 'loss/train': 3.544752836227417}
-03/03/2022 16:25:51 - INFO - codeparrot_training - Step 2564: {'lr': 0.0004999820840703554, 'samples': 1313280, 'steps': 2564, 'loss/train': 2.7020463943481445}
-03/03/2022 16:25:51 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/03/2022 16:25:56 - INFO - codeparrot_training - Step 2565: {'lr': 0.0004999820204831298, 'samples': 1313792, 'steps': 2565, 'loss/train': 2.3768131732940674}
-03/03/2022 16:25:59 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/03/2022 16:26:01 - INFO - codeparrot_training - Step 2566: {'lr': 0.0004999819567832661, 'samples': 1314304, 'steps': 2566, 'loss/train': 3.2334578037261963}
-03/03/2022 16:26:05 - INFO - codeparrot_training - Step 2567: {'lr': 0.0004999818929707645, 'samples': 1314816, 'steps': 2567, 'loss/train': 3.352979898452759}
-03/03/2022 16:26:07 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/03/2022 16:26:10 - INFO - codeparrot_training - Step 2568: {'lr': 0.0004999818290456249, 'samples': 1315328, 'steps': 2568, 'loss/train': 2.679513931274414}
-03/03/2022 16:26:13 - INFO - codeparrot_training - Step 2569: {'lr': 0.0004999817650078474, 'samples': 1315840, 'steps': 2569, 'loss/train': 2.85469126701355}
-03/03/2022 16:26:15 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 16:26:18 - INFO - codeparrot_training - Step 2570: {'lr': 0.0004999817008574318, 'samples': 1316352, 'steps': 2570, 'loss/train': 3.305773973464966}
-03/03/2022 16:26:21 - INFO - codeparrot_training - Step 2571: {'lr': 0.0004999816365943784, 'samples': 1316864, 'steps': 2571, 'loss/train': 2.1476075649261475}
-03/03/2022 16:26:24 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/03/2022 16:26:27 - INFO - codeparrot_training - Step 2572: {'lr': 0.000499981572218687, 'samples': 1317376, 'steps': 2572, 'loss/train': 2.854360342025757}
-03/03/2022 16:26:30 - INFO - codeparrot_training - Step 2573: {'lr': 0.0004999815077303579, 'samples': 1317888, 'steps': 2573, 'loss/train': 2.993514060974121}
-03/03/2022 16:26:32 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/03/2022 16:26:35 - INFO - codeparrot_training - Step 2574: {'lr': 0.000499981443129391, 'samples': 1318400, 'steps': 2574, 'loss/train': 3.482952356338501}
-03/03/2022 16:26:38 - INFO - codeparrot_training - Step 2575: {'lr': 0.0004999813784157863, 'samples': 1318912, 'steps': 2575, 'loss/train': 2.784579277038574}
-03/03/2022 16:26:40 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/03/2022 16:26:43 - INFO - codeparrot_training - Step 2576: {'lr': 0.0004999813135895438, 'samples': 1319424, 'steps': 2576, 'loss/train': 2.7337288856506348}
-03/03/2022 16:26:47 - INFO - codeparrot_training - Step 2577: {'lr': 0.0004999812486506637, 'samples': 1319936, 'steps': 2577, 'loss/train': 3.3158535957336426}
-03/03/2022 16:26:49 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/03/2022 16:26:52 - INFO - codeparrot_training - Step 2578: {'lr': 0.0004999811835991457, 'samples': 1320448, 'steps': 2578, 'loss/train': 0.747119128704071}
-03/03/2022 16:26:55 - INFO - codeparrot_training - Step 2579: {'lr': 0.0004999811184349902, 'samples': 1320960, 'steps': 2579, 'loss/train': 3.4974818229675293}
-03/03/2022 16:26:57 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/03/2022 16:27:00 - INFO - codeparrot_training - Step 2580: {'lr': 0.000499981053158197, 'samples': 1321472, 'steps': 2580, 'loss/train': 2.9436874389648438}
-03/03/2022 16:27:03 - INFO - codeparrot_training - Step 2581: {'lr': 0.0004999809877687662, 'samples': 1321984, 'steps': 2581, 'loss/train': 3.299527168273926}
-03/03/2022 16:27:06 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/03/2022 16:27:09 - INFO - codeparrot_training - Step 2582: {'lr': 0.0004999809222666978, 'samples': 1322496, 'steps': 2582, 'loss/train': 3.9506969451904297}
-03/03/2022 16:27:12 - INFO - codeparrot_training - Step 2583: {'lr': 0.0004999808566519919, 'samples': 1323008, 'steps': 2583, 'loss/train': 3.3544812202453613}
-03/03/2022 16:27:14 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/03/2022 16:27:17 - INFO - codeparrot_training - Step 2584: {'lr': 0.0004999807909246485, 'samples': 1323520, 'steps': 2584, 'loss/train': 3.4369499683380127}
-03/03/2022 16:27:20 - INFO - codeparrot_training - Step 2585: {'lr': 0.0004999807250846676, 'samples': 1324032, 'steps': 2585, 'loss/train': 1.846390724182129}
-03/03/2022 16:27:22 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/03/2022 16:27:26 - INFO - codeparrot_training - Step 2586: {'lr': 0.0004999806591320492, 'samples': 1324544, 'steps': 2586, 'loss/train': 3.332951307296753}
-03/03/2022 16:27:29 - INFO - codeparrot_training - Step 2587: {'lr': 0.0004999805930667934, 'samples': 1325056, 'steps': 2587, 'loss/train': 2.301896572113037}
-03/03/2022 16:27:31 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/03/2022 16:27:34 - INFO - codeparrot_training - Step 2588: {'lr': 0.0004999805268889003, 'samples': 1325568, 'steps': 2588, 'loss/train': 2.26432466506958}
-03/03/2022 16:27:37 - INFO - codeparrot_training - Step 2589: {'lr': 0.0004999804605983697, 'samples': 1326080, 'steps': 2589, 'loss/train': 1.6968886852264404}
-03/03/2022 16:27:39 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/03/2022 16:27:42 - INFO - codeparrot_training - Step 2590: {'lr': 0.0004999803941952018, 'samples': 1326592, 'steps': 2590, 'loss/train': 3.207984447479248}
-03/03/2022 16:27:46 - INFO - codeparrot_training - Step 2591: {'lr': 0.0004999803276793965, 'samples': 1327104, 'steps': 2591, 'loss/train': 3.6978676319122314}
-03/03/2022 16:27:47 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/03/2022 16:27:51 - INFO - codeparrot_training - Step 2592: {'lr': 0.0004999802610509541, 'samples': 1327616, 'steps': 2592, 'loss/train': 2.540597915649414}
-03/03/2022 16:27:54 - INFO - codeparrot_training - Step 2593: {'lr': 0.0004999801943098743, 'samples': 1328128, 'steps': 2593, 'loss/train': 3.3277461528778076}
-03/03/2022 16:27:56 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/03/2022 16:27:59 - INFO - codeparrot_training - Step 2594: {'lr': 0.0004999801274561573, 'samples': 1328640, 'steps': 2594, 'loss/train': 3.0864200592041016}
-03/03/2022 16:28:02 - INFO - codeparrot_training - Step 2595: {'lr': 0.0004999800604898032, 'samples': 1329152, 'steps': 2595, 'loss/train': 2.9830515384674072}
-03/03/2022 16:28:04 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/03/2022 16:28:08 - INFO - codeparrot_training - Step 2596: {'lr': 0.000499979993410812, 'samples': 1329664, 'steps': 2596, 'loss/train': 2.583662748336792}
-03/03/2022 16:28:11 - INFO - codeparrot_training - Step 2597: {'lr': 0.0004999799262191835, 'samples': 1330176, 'steps': 2597, 'loss/train': 3.0441434383392334}
-03/03/2022 16:28:12 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/03/2022 16:28:16 - INFO - codeparrot_training - Step 2598: {'lr': 0.0004999798589149179, 'samples': 1330688, 'steps': 2598, 'loss/train': 3.271484851837158}
-03/03/2022 16:28:19 - INFO - codeparrot_training - Step 2599: {'lr': 0.0004999797914980154, 'samples': 1331200, 'steps': 2599, 'loss/train': 2.115464448928833}
-03/03/2022 16:28:21 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 16:28:24 - INFO - codeparrot_training - Step 2600: {'lr': 0.0004999797239684757, 'samples': 1331712, 'steps': 2600, 'loss/train': 2.7303597927093506}
-03/03/2022 16:28:28 - INFO - codeparrot_training - Step 2601: {'lr': 0.0004999796563262991, 'samples': 1332224, 'steps': 2601, 'loss/train': 2.560098886489868}
-03/03/2022 16:28:29 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/03/2022 16:28:33 - INFO - codeparrot_training - Step 2602: {'lr': 0.0004999795885714855, 'samples': 1332736, 'steps': 2602, 'loss/train': 2.6737420558929443}
-03/03/2022 16:28:36 - INFO - codeparrot_training - Step 2603: {'lr': 0.0004999795207040349, 'samples': 1333248, 'steps': 2603, 'loss/train': 4.220717430114746}
-03/03/2022 16:28:37 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/03/2022 16:28:41 - INFO - codeparrot_training - Step 2604: {'lr': 0.0004999794527239474, 'samples': 1333760, 'steps': 2604, 'loss/train': 3.3827965259552}
-03/03/2022 16:28:44 - INFO - codeparrot_training - Step 2605: {'lr': 0.000499979384631223, 'samples': 1334272, 'steps': 2605, 'loss/train': 3.9132180213928223}
-03/03/2022 16:28:46 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/03/2022 16:28:50 - INFO - codeparrot_training - Step 2606: {'lr': 0.000499979316425862, 'samples': 1334784, 'steps': 2606, 'loss/train': 3.231592893600464}
-03/03/2022 16:28:53 - INFO - codeparrot_training - Step 2607: {'lr': 0.0004999792481078639, 'samples': 1335296, 'steps': 2607, 'loss/train': 2.7241311073303223}
-03/03/2022 16:28:54 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/03/2022 16:28:58 - INFO - codeparrot_training - Step 2608: {'lr': 0.000499979179677229, 'samples': 1335808, 'steps': 2608, 'loss/train': 2.4818124771118164}
-03/03/2022 16:29:01 - INFO - codeparrot_training - Step 2609: {'lr': 0.0004999791111339574, 'samples': 1336320, 'steps': 2609, 'loss/train': 1.6871732473373413}
-03/03/2022 16:29:02 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/03/2022 16:29:06 - INFO - codeparrot_training - Step 2610: {'lr': 0.0004999790424780492, 'samples': 1336832, 'steps': 2610, 'loss/train': 2.696526050567627}
-03/03/2022 16:29:10 - INFO - codeparrot_training - Step 2611: {'lr': 0.0004999789737095041, 'samples': 1337344, 'steps': 2611, 'loss/train': 2.5918705463409424}
-03/03/2022 16:29:11 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/03/2022 16:29:15 - INFO - codeparrot_training - Step 2612: {'lr': 0.0004999789048283224, 'samples': 1337856, 'steps': 2612, 'loss/train': 3.523407220840454}
-03/03/2022 16:29:18 - INFO - codeparrot_training - Step 2613: {'lr': 0.0004999788358345041, 'samples': 1338368, 'steps': 2613, 'loss/train': 3.5299386978149414}
-03/03/2022 16:29:19 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/03/2022 16:29:23 - INFO - codeparrot_training - Step 2614: {'lr': 0.0004999787667280492, 'samples': 1338880, 'steps': 2614, 'loss/train': 2.904710292816162}
-03/03/2022 16:29:27 - INFO - codeparrot_training - Step 2615: {'lr': 0.0004999786975089577, 'samples': 1339392, 'steps': 2615, 'loss/train': 3.1387832164764404}
-03/03/2022 16:29:28 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/03/2022 16:29:32 - INFO - codeparrot_training - Step 2616: {'lr': 0.0004999786281772296, 'samples': 1339904, 'steps': 2616, 'loss/train': 2.571301221847534}
-03/03/2022 16:29:35 - INFO - codeparrot_training - Step 2617: {'lr': 0.0004999785587328651, 'samples': 1340416, 'steps': 2617, 'loss/train': 3.431955337524414}
-03/03/2022 16:29:37 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/03/2022 16:29:40 - INFO - codeparrot_training - Step 2618: {'lr': 0.0004999784891758641, 'samples': 1340928, 'steps': 2618, 'loss/train': 3.766864538192749}
-03/03/2022 16:29:43 - INFO - codeparrot_training - Step 2619: {'lr': 0.0004999784195062266, 'samples': 1341440, 'steps': 2619, 'loss/train': 2.716116428375244}
-03/03/2022 16:29:45 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/03/2022 16:29:49 - INFO - codeparrot_training - Step 2620: {'lr': 0.0004999783497239526, 'samples': 1341952, 'steps': 2620, 'loss/train': 3.0643069744110107}
-03/03/2022 16:29:52 - INFO - codeparrot_training - Step 2621: {'lr': 0.0004999782798290424, 'samples': 1342464, 'steps': 2621, 'loss/train': 3.4522390365600586}
-03/03/2022 16:29:54 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/03/2022 16:29:57 - INFO - codeparrot_training - Step 2622: {'lr': 0.0004999782098214957, 'samples': 1342976, 'steps': 2622, 'loss/train': 3.551976442337036}
-03/03/2022 16:30:00 - INFO - codeparrot_training - Step 2623: {'lr': 0.0004999781397013127, 'samples': 1343488, 'steps': 2623, 'loss/train': 2.9192144870758057}
-03/03/2022 16:30:02 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/03/2022 16:30:06 - INFO - codeparrot_training - Step 2624: {'lr': 0.0004999780694684934, 'samples': 1344000, 'steps': 2624, 'loss/train': 2.217301607131958}
-03/03/2022 16:30:09 - INFO - codeparrot_training - Step 2625: {'lr': 0.000499977999123038, 'samples': 1344512, 'steps': 2625, 'loss/train': 2.3937151432037354}
-03/03/2022 16:30:11 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/03/2022 16:30:14 - INFO - codeparrot_training - Step 2626: {'lr': 0.0004999779286649461, 'samples': 1345024, 'steps': 2626, 'loss/train': 4.238019943237305}
-03/03/2022 16:30:17 - INFO - codeparrot_training - Step 2627: {'lr': 0.0004999778580942183, 'samples': 1345536, 'steps': 2627, 'loss/train': 1.5297744274139404}
-03/03/2022 16:30:19 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/03/2022 16:30:23 - INFO - codeparrot_training - Step 2628: {'lr': 0.000499977787410854, 'samples': 1346048, 'steps': 2628, 'loss/train': 2.5261788368225098}
-03/03/2022 16:30:26 - INFO - codeparrot_training - Step 2629: {'lr': 0.0004999777166148539, 'samples': 1346560, 'steps': 2629, 'loss/train': 2.9928596019744873}
-03/03/2022 16:30:28 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 16:30:31 - INFO - codeparrot_training - Step 2630: {'lr': 0.0004999776457062175, 'samples': 1347072, 'steps': 2630, 'loss/train': 2.845942258834839}
-03/03/2022 16:30:34 - INFO - codeparrot_training - Step 2631: {'lr': 0.0004999775746849451, 'samples': 1347584, 'steps': 2631, 'loss/train': 3.638514518737793}
-03/03/2022 16:30:36 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 16:30:39 - INFO - codeparrot_training - Step 2632: {'lr': 0.0004999775035510367, 'samples': 1348096, 'steps': 2632, 'loss/train': 3.0251049995422363}
-03/03/2022 16:30:43 - INFO - codeparrot_training - Step 2633: {'lr': 0.0004999774323044922, 'samples': 1348608, 'steps': 2633, 'loss/train': 2.5025033950805664}
-03/03/2022 16:30:45 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/03/2022 16:30:48 - INFO - codeparrot_training - Step 2634: {'lr': 0.0004999773609453118, 'samples': 1349120, 'steps': 2634, 'loss/train': 2.459221124649048}
-03/03/2022 16:30:51 - INFO - codeparrot_training - Step 2635: {'lr': 0.0004999772894734954, 'samples': 1349632, 'steps': 2635, 'loss/train': 3.168429136276245}
-03/03/2022 16:30:53 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/03/2022 16:30:56 - INFO - codeparrot_training - Step 2636: {'lr': 0.000499977217889043, 'samples': 1350144, 'steps': 2636, 'loss/train': 3.164872884750366}
-03/03/2022 16:31:00 - INFO - codeparrot_training - Step 2637: {'lr': 0.0004999771461919549, 'samples': 1350656, 'steps': 2637, 'loss/train': 3.768165111541748}
-03/03/2022 16:31:01 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/03/2022 16:31:05 - INFO - codeparrot_training - Step 2638: {'lr': 0.0004999770743822309, 'samples': 1351168, 'steps': 2638, 'loss/train': 1.4939980506896973}
-03/03/2022 16:31:08 - INFO - codeparrot_training - Step 2639: {'lr': 0.0004999770024598711, 'samples': 1351680, 'steps': 2639, 'loss/train': 2.271815538406372}
-03/03/2022 16:31:10 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/03/2022 16:31:13 - INFO - codeparrot_training - Step 2640: {'lr': 0.0004999769304248754, 'samples': 1352192, 'steps': 2640, 'loss/train': 3.0449881553649902}
-03/03/2022 16:31:17 - INFO - codeparrot_training - Step 2641: {'lr': 0.0004999768582772442, 'samples': 1352704, 'steps': 2641, 'loss/train': 2.447634220123291}
-03/03/2022 16:31:19 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/03/2022 16:31:22 - INFO - codeparrot_training - Step 2642: {'lr': 0.000499976786016977, 'samples': 1353216, 'steps': 2642, 'loss/train': 2.848057985305786}
-03/03/2022 16:31:25 - INFO - codeparrot_training - Step 2643: {'lr': 0.0004999767136440742, 'samples': 1353728, 'steps': 2643, 'loss/train': 4.213784694671631}
-03/03/2022 16:31:27 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/03/2022 16:31:30 - INFO - codeparrot_training - Step 2644: {'lr': 0.0004999766411585359, 'samples': 1354240, 'steps': 2644, 'loss/train': 3.698878288269043}
-03/03/2022 16:31:33 - INFO - codeparrot_training - Step 2645: {'lr': 0.0004999765685603618, 'samples': 1354752, 'steps': 2645, 'loss/train': 3.135502815246582}
-03/03/2022 16:31:35 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/03/2022 16:31:39 - INFO - codeparrot_training - Step 2646: {'lr': 0.0004999764958495522, 'samples': 1355264, 'steps': 2646, 'loss/train': 3.0132973194122314}
-03/03/2022 16:31:42 - INFO - codeparrot_training - Step 2647: {'lr': 0.0004999764230261072, 'samples': 1355776, 'steps': 2647, 'loss/train': 2.5124495029449463}
-03/03/2022 16:31:44 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/03/2022 16:31:47 - INFO - codeparrot_training - Step 2648: {'lr': 0.0004999763500900265, 'samples': 1356288, 'steps': 2648, 'loss/train': 3.5623955726623535}
-03/03/2022 16:31:50 - INFO - codeparrot_training - Step 2649: {'lr': 0.0004999762770413103, 'samples': 1356800, 'steps': 2649, 'loss/train': 2.7302751541137695}
-03/03/2022 16:31:52 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/03/2022 16:31:55 - INFO - codeparrot_training - Step 2650: {'lr': 0.0004999762038799587, 'samples': 1357312, 'steps': 2650, 'loss/train': 4.946469306945801}
-03/03/2022 16:31:59 - INFO - codeparrot_training - Step 2651: {'lr': 0.0004999761306059717, 'samples': 1357824, 'steps': 2651, 'loss/train': 2.629087448120117}
-03/03/2022 16:32:00 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/03/2022 16:32:04 - INFO - codeparrot_training - Step 2652: {'lr': 0.0004999760572193492, 'samples': 1358336, 'steps': 2652, 'loss/train': 2.986102819442749}
-03/03/2022 16:32:07 - INFO - codeparrot_training - Step 2653: {'lr': 0.0004999759837200914, 'samples': 1358848, 'steps': 2653, 'loss/train': 3.6453475952148438}
-03/03/2022 16:32:09 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/03/2022 16:32:12 - INFO - codeparrot_training - Step 2654: {'lr': 0.0004999759101081984, 'samples': 1359360, 'steps': 2654, 'loss/train': 2.356199026107788}
-03/03/2022 16:32:16 - INFO - codeparrot_training - Step 2655: {'lr': 0.0004999758363836701, 'samples': 1359872, 'steps': 2655, 'loss/train': 3.1962454319000244}
-03/03/2022 16:32:18 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/03/2022 16:32:21 - INFO - codeparrot_training - Step 2656: {'lr': 0.0004999757625465063, 'samples': 1360384, 'steps': 2656, 'loss/train': 3.558591604232788}
-03/03/2022 16:32:24 - INFO - codeparrot_training - Step 2657: {'lr': 0.0004999756885967075, 'samples': 1360896, 'steps': 2657, 'loss/train': 3.0056636333465576}
-03/03/2022 16:32:26 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/03/2022 16:32:29 - INFO - codeparrot_training - Step 2658: {'lr': 0.0004999756145342735, 'samples': 1361408, 'steps': 2658, 'loss/train': 1.05905020236969}
-03/03/2022 16:32:32 - INFO - codeparrot_training - Step 2659: {'lr': 0.0004999755403592043, 'samples': 1361920, 'steps': 2659, 'loss/train': 2.734844923019409}
-03/03/2022 16:32:34 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/03/2022 16:32:38 - INFO - codeparrot_training - Step 2660: {'lr': 0.0004999754660714999, 'samples': 1362432, 'steps': 2660, 'loss/train': 3.336033821105957}
-03/03/2022 16:32:41 - INFO - codeparrot_training - Step 2661: {'lr': 0.0004999753916711606, 'samples': 1362944, 'steps': 2661, 'loss/train': 2.3727469444274902}
-03/03/2022 16:32:43 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/03/2022 16:32:46 - INFO - codeparrot_training - Step 2662: {'lr': 0.0004999753171581862, 'samples': 1363456, 'steps': 2662, 'loss/train': 3.810101270675659}
-03/03/2022 16:32:49 - INFO - codeparrot_training - Step 2663: {'lr': 0.0004999752425325766, 'samples': 1363968, 'steps': 2663, 'loss/train': 3.6662099361419678}
-03/03/2022 16:32:52 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/03/2022 16:32:55 - INFO - codeparrot_training - Step 2664: {'lr': 0.0004999751677943322, 'samples': 1364480, 'steps': 2664, 'loss/train': 2.4257819652557373}
-03/03/2022 16:32:58 - INFO - codeparrot_training - Step 2665: {'lr': 0.0004999750929434527, 'samples': 1364992, 'steps': 2665, 'loss/train': 2.9750545024871826}
-03/03/2022 16:33:00 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/03/2022 16:33:03 - INFO - codeparrot_training - Step 2666: {'lr': 0.0004999750179799383, 'samples': 1365504, 'steps': 2666, 'loss/train': 3.2500622272491455}
-03/03/2022 16:33:06 - INFO - codeparrot_training - Step 2667: {'lr': 0.0004999749429037892, 'samples': 1366016, 'steps': 2667, 'loss/train': 2.81709885597229}
-03/03/2022 16:33:08 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/03/2022 16:33:12 - INFO - codeparrot_training - Step 2668: {'lr': 0.0004999748677150051, 'samples': 1366528, 'steps': 2668, 'loss/train': 3.947962522506714}
-03/03/2022 16:33:15 - INFO - codeparrot_training - Step 2669: {'lr': 0.0004999747924135862, 'samples': 1367040, 'steps': 2669, 'loss/train': 3.3503713607788086}
-03/03/2022 16:33:17 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/03/2022 16:33:20 - INFO - codeparrot_training - Step 2670: {'lr': 0.0004999747169995325, 'samples': 1367552, 'steps': 2670, 'loss/train': 2.945610284805298}
-03/03/2022 16:33:23 - INFO - codeparrot_training - Step 2671: {'lr': 0.0004999746414728441, 'samples': 1368064, 'steps': 2671, 'loss/train': 3.689152479171753}
-03/03/2022 16:33:25 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/03/2022 16:33:29 - INFO - codeparrot_training - Step 2672: {'lr': 0.0004999745658335209, 'samples': 1368576, 'steps': 2672, 'loss/train': 3.413879871368408}
-03/03/2022 16:33:32 - INFO - codeparrot_training - Step 2673: {'lr': 0.000499974490081563, 'samples': 1369088, 'steps': 2673, 'loss/train': 3.0831363201141357}
-03/03/2022 16:33:34 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/03/2022 16:33:37 - INFO - codeparrot_training - Step 2674: {'lr': 0.0004999744142169707, 'samples': 1369600, 'steps': 2674, 'loss/train': 3.054553747177124}
-03/03/2022 16:33:40 - INFO - codeparrot_training - Step 2675: {'lr': 0.0004999743382397435, 'samples': 1370112, 'steps': 2675, 'loss/train': 3.3434205055236816}
-03/03/2022 16:33:42 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/03/2022 16:33:45 - INFO - codeparrot_training - Step 2676: {'lr': 0.0004999742621498818, 'samples': 1370624, 'steps': 2676, 'loss/train': 1.5339998006820679}
-03/03/2022 16:33:49 - INFO - codeparrot_training - Step 2677: {'lr': 0.0004999741859473857, 'samples': 1371136, 'steps': 2677, 'loss/train': 3.1449472904205322}
-03/03/2022 16:33:50 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/03/2022 16:33:54 - INFO - codeparrot_training - Step 2678: {'lr': 0.0004999741096322549, 'samples': 1371648, 'steps': 2678, 'loss/train': 2.4214611053466797}
-03/03/2022 16:33:57 - INFO - codeparrot_training - Step 2679: {'lr': 0.0004999740332044898, 'samples': 1372160, 'steps': 2679, 'loss/train': 3.1184234619140625}
-03/03/2022 16:33:58 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/03/2022 16:34:02 - INFO - codeparrot_training - Step 2680: {'lr': 0.0004999739566640901, 'samples': 1372672, 'steps': 2680, 'loss/train': 2.306725263595581}
-03/03/2022 16:34:06 - INFO - codeparrot_training - Step 2681: {'lr': 0.000499973880011056, 'samples': 1373184, 'steps': 2681, 'loss/train': 1.848206639289856}
-03/03/2022 16:34:07 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/03/2022 16:34:11 - INFO - codeparrot_training - Step 2682: {'lr': 0.0004999738032453876, 'samples': 1373696, 'steps': 2682, 'loss/train': 2.607447862625122}
-03/03/2022 16:34:14 - INFO - codeparrot_training - Step 2683: {'lr': 0.0004999737263670848, 'samples': 1374208, 'steps': 2683, 'loss/train': 3.085094451904297}
-03/03/2022 16:34:15 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/03/2022 16:34:19 - INFO - codeparrot_training - Step 2684: {'lr': 0.0004999736493761477, 'samples': 1374720, 'steps': 2684, 'loss/train': 2.721832275390625}
-03/03/2022 16:34:22 - INFO - codeparrot_training - Step 2685: {'lr': 0.0004999735722725765, 'samples': 1375232, 'steps': 2685, 'loss/train': 2.966313600540161}
-03/03/2022 16:34:23 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/03/2022 16:34:28 - INFO - codeparrot_training - Step 2686: {'lr': 0.0004999734950563709, 'samples': 1375744, 'steps': 2686, 'loss/train': 0.4267406463623047}
-03/03/2022 16:34:31 - INFO - codeparrot_training - Step 2687: {'lr': 0.0004999734177275311, 'samples': 1376256, 'steps': 2687, 'loss/train': 2.8467860221862793}
-03/03/2022 16:34:32 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/03/2022 16:34:36 - INFO - codeparrot_training - Step 2688: {'lr': 0.0004999733402860572, 'samples': 1376768, 'steps': 2688, 'loss/train': 2.1725759506225586}
-03/03/2022 16:34:39 - INFO - codeparrot_training - Step 2689: {'lr': 0.0004999732627319491, 'samples': 1377280, 'steps': 2689, 'loss/train': 2.5292203426361084}
-03/03/2022 16:34:40 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/03/2022 16:34:44 - INFO - codeparrot_training - Step 2690: {'lr': 0.000499973185065207, 'samples': 1377792, 'steps': 2690, 'loss/train': 2.9473001956939697}
-03/03/2022 16:34:48 - INFO - codeparrot_training - Step 2691: {'lr': 0.0004999731072858307, 'samples': 1378304, 'steps': 2691, 'loss/train': 2.802412986755371}
-03/03/2022 16:34:49 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/03/2022 16:34:53 - INFO - codeparrot_training - Step 2692: {'lr': 0.0004999730293938205, 'samples': 1378816, 'steps': 2692, 'loss/train': 2.6749649047851562}
-03/03/2022 16:34:56 - INFO - codeparrot_training - Step 2693: {'lr': 0.0004999729513891762, 'samples': 1379328, 'steps': 2693, 'loss/train': 2.759756565093994}
-03/03/2022 16:34:57 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/03/2022 16:35:01 - INFO - codeparrot_training - Step 2694: {'lr': 0.000499972873271898, 'samples': 1379840, 'steps': 2694, 'loss/train': 2.8685598373413086}
-03/03/2022 16:35:04 - INFO - codeparrot_training - Step 2695: {'lr': 0.0004999727950419859, 'samples': 1380352, 'steps': 2695, 'loss/train': 3.7282521724700928}
-03/03/2022 16:35:06 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/03/2022 16:35:10 - INFO - codeparrot_training - Step 2696: {'lr': 0.0004999727166994399, 'samples': 1380864, 'steps': 2696, 'loss/train': 2.929319381713867}
-03/03/2022 16:35:13 - INFO - codeparrot_training - Step 2697: {'lr': 0.0004999726382442601, 'samples': 1381376, 'steps': 2697, 'loss/train': 3.113121509552002}
-03/03/2022 16:35:14 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/03/2022 16:35:18 - INFO - codeparrot_training - Step 2698: {'lr': 0.0004999725596764465, 'samples': 1381888, 'steps': 2698, 'loss/train': 2.7707581520080566}
-03/03/2022 16:35:21 - INFO - codeparrot_training - Step 2699: {'lr': 0.000499972480995999, 'samples': 1382400, 'steps': 2699, 'loss/train': 0.7133868932723999}
-03/03/2022 16:35:23 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/03/2022 16:35:27 - INFO - codeparrot_training - Step 2700: {'lr': 0.0004999724022029179, 'samples': 1382912, 'steps': 2700, 'loss/train': 1.3908557891845703}
-03/03/2022 16:35:30 - INFO - codeparrot_training - Step 2701: {'lr': 0.000499972323297203, 'samples': 1383424, 'steps': 2701, 'loss/train': 1.9161713123321533}
-03/03/2022 16:35:31 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/03/2022 16:35:35 - INFO - codeparrot_training - Step 2702: {'lr': 0.0004999722442788544, 'samples': 1383936, 'steps': 2702, 'loss/train': 2.9433400630950928}
-03/03/2022 16:35:38 - INFO - codeparrot_training - Step 2703: {'lr': 0.0004999721651478723, 'samples': 1384448, 'steps': 2703, 'loss/train': 2.624702215194702}
-03/03/2022 16:35:39 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/03/2022 16:35:43 - INFO - codeparrot_training - Step 2704: {'lr': 0.0004999720859042565, 'samples': 1384960, 'steps': 2704, 'loss/train': 3.163682222366333}
-03/03/2022 16:35:47 - INFO - codeparrot_training - Step 2705: {'lr': 0.0004999720065480071, 'samples': 1385472, 'steps': 2705, 'loss/train': 3.0142343044281006}
-03/03/2022 16:35:47 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/03/2022 16:35:52 - INFO - codeparrot_training - Step 2706: {'lr': 0.0004999719270791242, 'samples': 1385984, 'steps': 2706, 'loss/train': 2.339606761932373}
-03/03/2022 16:35:55 - INFO - codeparrot_training - Step 2707: {'lr': 0.0004999718474976078, 'samples': 1386496, 'steps': 2707, 'loss/train': 3.7225284576416016}
-03/03/2022 16:35:55 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/03/2022 16:36:01 - INFO - codeparrot_training - Step 2708: {'lr': 0.000499971767803458, 'samples': 1387008, 'steps': 2708, 'loss/train': 2.9600157737731934}
-03/03/2022 16:36:04 - INFO - codeparrot_training - Step 2709: {'lr': 0.0004999716879966747, 'samples': 1387520, 'steps': 2709, 'loss/train': 0.5095680952072144}
-03/03/2022 16:36:06 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/03/2022 16:36:09 - INFO - codeparrot_training - Step 2710: {'lr': 0.000499971608077258, 'samples': 1388032, 'steps': 2710, 'loss/train': 3.024923324584961}
-03/03/2022 16:36:12 - INFO - codeparrot_training - Step 2711: {'lr': 0.000499971528045208, 'samples': 1388544, 'steps': 2711, 'loss/train': 2.553765296936035}
-03/03/2022 16:36:14 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/03/2022 16:36:18 - INFO - codeparrot_training - Step 2712: {'lr': 0.0004999714479005248, 'samples': 1389056, 'steps': 2712, 'loss/train': 2.1832149028778076}
-03/03/2022 16:36:21 - INFO - codeparrot_training - Step 2713: {'lr': 0.0004999713676432082, 'samples': 1389568, 'steps': 2713, 'loss/train': 2.8498430252075195}
-03/03/2022 16:36:22 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/03/2022 16:36:26 - INFO - codeparrot_training - Step 2714: {'lr': 0.0004999712872732584, 'samples': 1390080, 'steps': 2714, 'loss/train': 3.45271372795105}
-03/03/2022 16:36:29 - INFO - codeparrot_training - Step 2715: {'lr': 0.0004999712067906754, 'samples': 1390592, 'steps': 2715, 'loss/train': 3.0970587730407715}
-03/03/2022 16:36:30 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/03/2022 16:36:34 - INFO - codeparrot_training - Step 2716: {'lr': 0.0004999711261954591, 'samples': 1391104, 'steps': 2716, 'loss/train': 2.373814105987549}
-03/03/2022 16:36:38 - INFO - codeparrot_training - Step 2717: {'lr': 0.0004999710454876099, 'samples': 1391616, 'steps': 2717, 'loss/train': 0.6093522906303406}
-03/03/2022 16:36:39 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/03/2022 16:36:43 - INFO - codeparrot_training - Step 2718: {'lr': 0.0004999709646671274, 'samples': 1392128, 'steps': 2718, 'loss/train': 2.97921085357666}
-03/03/2022 16:36:46 - INFO - codeparrot_training - Step 2719: {'lr': 0.0004999708837340119, 'samples': 1392640, 'steps': 2719, 'loss/train': 3.300020217895508}
-03/03/2022 16:36:47 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/03/2022 16:36:51 - INFO - codeparrot_training - Step 2720: {'lr': 0.0004999708026882635, 'samples': 1393152, 'steps': 2720, 'loss/train': 2.6183254718780518}
-03/03/2022 16:36:54 - INFO - codeparrot_training - Step 2721: {'lr': 0.000499970721529882, 'samples': 1393664, 'steps': 2721, 'loss/train': 3.246802806854248}
-03/03/2022 16:36:56 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/03/2022 16:37:00 - INFO - codeparrot_training - Step 2722: {'lr': 0.0004999706402588675, 'samples': 1394176, 'steps': 2722, 'loss/train': 1.8369256258010864}
-03/03/2022 16:37:03 - INFO - codeparrot_training - Step 2723: {'lr': 0.0004999705588752202, 'samples': 1394688, 'steps': 2723, 'loss/train': 3.219496726989746}
-03/03/2022 16:37:04 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/03/2022 16:37:08 - INFO - codeparrot_training - Step 2724: {'lr': 0.00049997047737894, 'samples': 1395200, 'steps': 2724, 'loss/train': 2.1128249168395996}
-03/03/2022 16:37:11 - INFO - codeparrot_training - Step 2725: {'lr': 0.0004999703957700269, 'samples': 1395712, 'steps': 2725, 'loss/train': 2.07346773147583}
-03/03/2022 16:37:13 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/03/2022 16:37:17 - INFO - codeparrot_training - Step 2726: {'lr': 0.000499970314048481, 'samples': 1396224, 'steps': 2726, 'loss/train': 3.2113945484161377}
-03/03/2022 16:37:20 - INFO - codeparrot_training - Step 2727: {'lr': 0.0004999702322143023, 'samples': 1396736, 'steps': 2727, 'loss/train': 3.701845169067383}
-03/03/2022 16:37:21 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/03/2022 16:37:25 - INFO - codeparrot_training - Step 2728: {'lr': 0.000499970150267491, 'samples': 1397248, 'steps': 2728, 'loss/train': 2.8003170490264893}
-03/03/2022 16:37:28 - INFO - codeparrot_training - Step 2729: {'lr': 0.0004999700682080469, 'samples': 1397760, 'steps': 2729, 'loss/train': 2.227933406829834}
-03/03/2022 16:37:29 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/03/2022 16:37:33 - INFO - codeparrot_training - Step 2730: {'lr': 0.0004999699860359702, 'samples': 1398272, 'steps': 2730, 'loss/train': 1.0050252676010132}
-03/03/2022 16:37:37 - INFO - codeparrot_training - Step 2731: {'lr': 0.0004999699037512608, 'samples': 1398784, 'steps': 2731, 'loss/train': 3.0615792274475098}
-03/03/2022 16:37:38 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/03/2022 16:37:42 - INFO - codeparrot_training - Step 2732: {'lr': 0.000499969821353919, 'samples': 1399296, 'steps': 2732, 'loss/train': 2.2257916927337646}
-03/03/2022 16:37:45 - INFO - codeparrot_training - Step 2733: {'lr': 0.0004999697388439444, 'samples': 1399808, 'steps': 2733, 'loss/train': 2.260690450668335}
-03/03/2022 16:37:46 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/03/2022 16:37:50 - INFO - codeparrot_training - Step 2734: {'lr': 0.0004999696562213375, 'samples': 1400320, 'steps': 2734, 'loss/train': 3.423987865447998}
-03/03/2022 16:37:53 - INFO - codeparrot_training - Step 2735: {'lr': 0.0004999695734860981, 'samples': 1400832, 'steps': 2735, 'loss/train': 2.2401645183563232}
-03/03/2022 16:37:54 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/03/2022 16:37:59 - INFO - codeparrot_training - Step 2736: {'lr': 0.0004999694906382262, 'samples': 1401344, 'steps': 2736, 'loss/train': 3.383301019668579}
-03/03/2022 16:38:02 - INFO - codeparrot_training - Step 2737: {'lr': 0.0004999694076777219, 'samples': 1401856, 'steps': 2737, 'loss/train': 2.5983786582946777}
-03/03/2022 16:38:02 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/03/2022 16:38:07 - INFO - codeparrot_training - Step 2738: {'lr': 0.0004999693246045854, 'samples': 1402368, 'steps': 2738, 'loss/train': 3.214512348175049}
-03/03/2022 16:38:10 - INFO - codeparrot_training - Step 2739: {'lr': 0.0004999692414188164, 'samples': 1402880, 'steps': 2739, 'loss/train': 3.0131938457489014}
-03/03/2022 16:38:11 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/03/2022 16:38:16 - INFO - codeparrot_training - Step 2740: {'lr': 0.0004999691581204152, 'samples': 1403392, 'steps': 2740, 'loss/train': 3.7400827407836914}
-03/03/2022 16:38:19 - INFO - codeparrot_training - Step 2741: {'lr': 0.0004999690747093816, 'samples': 1403904, 'steps': 2741, 'loss/train': 2.461756706237793}
-03/03/2022 16:38:19 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/03/2022 16:38:24 - INFO - codeparrot_training - Step 2742: {'lr': 0.000499968991185716, 'samples': 1404416, 'steps': 2742, 'loss/train': 2.7894327640533447}
-03/03/2022 16:38:27 - INFO - codeparrot_training - Step 2743: {'lr': 0.0004999689075494182, 'samples': 1404928, 'steps': 2743, 'loss/train': 2.5563488006591797}
-03/03/2022 16:38:27 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/03/2022 16:38:32 - INFO - codeparrot_training - Step 2744: {'lr': 0.0004999688238004882, 'samples': 1405440, 'steps': 2744, 'loss/train': 4.033098220825195}
-03/03/2022 16:38:36 - INFO - codeparrot_training - Step 2745: {'lr': 0.0004999687399389262, 'samples': 1405952, 'steps': 2745, 'loss/train': 2.51008939743042}
-03/03/2022 16:38:37 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/03/2022 16:38:41 - INFO - codeparrot_training - Step 2746: {'lr': 0.0004999686559647319, 'samples': 1406464, 'steps': 2746, 'loss/train': 0.8866392374038696}
-03/03/2022 16:38:44 - INFO - codeparrot_training - Step 2747: {'lr': 0.0004999685718779058, 'samples': 1406976, 'steps': 2747, 'loss/train': 3.109419345855713}
-03/03/2022 16:38:45 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/03/2022 16:38:49 - INFO - codeparrot_training - Step 2748: {'lr': 0.0004999684876784477, 'samples': 1407488, 'steps': 2748, 'loss/train': 3.017601251602173}
-03/03/2022 16:38:52 - INFO - codeparrot_training - Step 2749: {'lr': 0.0004999684033663576, 'samples': 1408000, 'steps': 2749, 'loss/train': 2.993380546569824}
-03/03/2022 16:38:53 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/03/2022 16:38:58 - INFO - codeparrot_training - Step 2750: {'lr': 0.0004999683189416356, 'samples': 1408512, 'steps': 2750, 'loss/train': 3.0072054862976074}
-03/03/2022 16:39:01 - INFO - codeparrot_training - Step 2751: {'lr': 0.0004999682344042817, 'samples': 1409024, 'steps': 2751, 'loss/train': 2.9468133449554443}
-03/03/2022 16:39:01 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/03/2022 16:39:06 - INFO - codeparrot_training - Step 2752: {'lr': 0.000499968149754296, 'samples': 1409536, 'steps': 2752, 'loss/train': 3.357618570327759}
-03/03/2022 16:39:09 - INFO - codeparrot_training - Step 2753: {'lr': 0.0004999680649916786, 'samples': 1410048, 'steps': 2753, 'loss/train': 2.3924074172973633}
-03/03/2022 16:39:09 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/03/2022 16:39:15 - INFO - codeparrot_training - Step 2754: {'lr': 0.0004999679801164295, 'samples': 1410560, 'steps': 2754, 'loss/train': 2.7252907752990723}
-03/03/2022 16:39:18 - INFO - codeparrot_training - Step 2755: {'lr': 0.0004999678951285485, 'samples': 1411072, 'steps': 2755, 'loss/train': 2.8945701122283936}
-03/03/2022 16:39:18 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/03/2022 16:39:23 - INFO - codeparrot_training - Step 2756: {'lr': 0.0004999678100280358, 'samples': 1411584, 'steps': 2756, 'loss/train': 0.596611499786377}
-03/03/2022 16:39:26 - INFO - codeparrot_training - Step 2757: {'lr': 0.0004999677248148916, 'samples': 1412096, 'steps': 2757, 'loss/train': 2.9982056617736816}
-03/03/2022 16:39:26 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/03/2022 16:39:32 - INFO - codeparrot_training - Step 2758: {'lr': 0.0004999676394891158, 'samples': 1412608, 'steps': 2758, 'loss/train': 3.010190486907959}
-03/03/2022 16:39:35 - INFO - codeparrot_training - Step 2759: {'lr': 0.0004999675540507083, 'samples': 1413120, 'steps': 2759, 'loss/train': 2.8700668811798096}
-03/03/2022 16:39:35 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/03/2022 16:39:40 - INFO - codeparrot_training - Step 2760: {'lr': 0.0004999674684996694, 'samples': 1413632, 'steps': 2760, 'loss/train': 3.8052008152008057}
-03/03/2022 16:39:43 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/03/2022 16:39:45 - INFO - codeparrot_training - Step 2761: {'lr': 0.0004999673828359989, 'samples': 1414144, 'steps': 2761, 'loss/train': 2.5783233642578125}
-03/03/2022 16:39:48 - INFO - codeparrot_training - Step 2762: {'lr': 0.0004999672970596971, 'samples': 1414656, 'steps': 2762, 'loss/train': 2.9074954986572266}
-03/03/2022 16:39:51 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/03/2022 16:39:54 - INFO - codeparrot_training - Step 2763: {'lr': 0.0004999672111707639, 'samples': 1415168, 'steps': 2763, 'loss/train': 3.0255846977233887}
-03/03/2022 16:39:57 - INFO - codeparrot_training - Step 2764: {'lr': 0.0004999671251691991, 'samples': 1415680, 'steps': 2764, 'loss/train': 2.850754737854004}
-03/03/2022 16:39:59 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/03/2022 16:40:02 - INFO - codeparrot_training - Step 2765: {'lr': 0.0004999670390550032, 'samples': 1416192, 'steps': 2765, 'loss/train': 0.5259968638420105}
-03/03/2022 16:40:05 - INFO - codeparrot_training - Step 2766: {'lr': 0.000499966952828176, 'samples': 1416704, 'steps': 2766, 'loss/train': 2.8810441493988037}
-03/03/2022 16:40:11 - INFO - codeparrot_training - Step 2767: {'lr': 0.0004999668664887175, 'samples': 1417216, 'steps': 2767, 'loss/train': 2.586190938949585}
-03/03/2022 16:40:14 - INFO - codeparrot_training - Step 2768: {'lr': 0.0004999667800366278, 'samples': 1417728, 'steps': 2768, 'loss/train': 3.123504161834717}
-03/03/2022 16:40:16 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/03/2022 16:40:19 - INFO - codeparrot_training - Step 2769: {'lr': 0.0004999666934719069, 'samples': 1418240, 'steps': 2769, 'loss/train': 2.135603427886963}
-03/03/2022 16:40:22 - INFO - codeparrot_training - Step 2770: {'lr': 0.0004999666067945548, 'samples': 1418752, 'steps': 2770, 'loss/train': 2.5394155979156494}
-03/03/2022 16:40:24 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/03/2022 16:40:28 - INFO - codeparrot_training - Step 2771: {'lr': 0.0004999665200045716, 'samples': 1419264, 'steps': 2771, 'loss/train': 2.546546459197998}
-03/03/2022 16:40:31 - INFO - codeparrot_training - Step 2772: {'lr': 0.0004999664331019574, 'samples': 1419776, 'steps': 2772, 'loss/train': 2.88893723487854}
-03/03/2022 16:40:33 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/03/2022 16:40:36 - INFO - codeparrot_training - Step 2773: {'lr': 0.0004999663460867123, 'samples': 1420288, 'steps': 2773, 'loss/train': 2.6379425525665283}
-03/03/2022 16:40:39 - INFO - codeparrot_training - Step 2774: {'lr': 0.000499966258958836, 'samples': 1420800, 'steps': 2774, 'loss/train': 2.9634621143341064}
-03/03/2022 16:40:41 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/03/2022 16:40:44 - INFO - codeparrot_training - Step 2775: {'lr': 0.000499966171718329, 'samples': 1421312, 'steps': 2775, 'loss/train': 2.962170124053955}
-03/03/2022 16:40:48 - INFO - codeparrot_training - Step 2776: {'lr': 0.000499966084365191, 'samples': 1421824, 'steps': 2776, 'loss/train': 2.5851809978485107}
-03/03/2022 16:40:49 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/03/2022 16:40:53 - INFO - codeparrot_training - Step 2777: {'lr': 0.0004999659968994221, 'samples': 1422336, 'steps': 2777, 'loss/train': 2.1692118644714355}
-03/03/2022 16:40:56 - INFO - codeparrot_training - Step 2778: {'lr': 0.0004999659093210223, 'samples': 1422848, 'steps': 2778, 'loss/train': 6.008566379547119}
-03/03/2022 16:40:58 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/03/2022 16:41:01 - INFO - codeparrot_training - Step 2779: {'lr': 0.0004999658216299919, 'samples': 1423360, 'steps': 2779, 'loss/train': 4.314851760864258}
-03/03/2022 16:41:04 - INFO - codeparrot_training - Step 2780: {'lr': 0.0004999657338263308, 'samples': 1423872, 'steps': 2780, 'loss/train': 3.9941909313201904}
-03/03/2022 16:41:06 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/03/2022 16:41:10 - INFO - codeparrot_training - Step 2781: {'lr': 0.0004999656459100388, 'samples': 1424384, 'steps': 2781, 'loss/train': 3.216099500656128}
-03/03/2022 16:41:13 - INFO - codeparrot_training - Step 2782: {'lr': 0.0004999655578811161, 'samples': 1424896, 'steps': 2782, 'loss/train': 2.0455474853515625}
-03/03/2022 16:41:14 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/03/2022 16:41:18 - INFO - codeparrot_training - Step 2783: {'lr': 0.0004999654697395629, 'samples': 1425408, 'steps': 2783, 'loss/train': 3.5764999389648438}
-03/03/2022 16:41:21 - INFO - codeparrot_training - Step 2784: {'lr': 0.0004999653814853791, 'samples': 1425920, 'steps': 2784, 'loss/train': 3.778637409210205}
-03/03/2022 16:41:23 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/03/2022 16:41:26 - INFO - codeparrot_training - Step 2785: {'lr': 0.0004999652931185648, 'samples': 1426432, 'steps': 2785, 'loss/train': 2.3404812812805176}
-03/03/2022 16:41:30 - INFO - codeparrot_training - Step 2786: {'lr': 0.00049996520463912, 'samples': 1426944, 'steps': 2786, 'loss/train': 2.825230360031128}
-03/03/2022 16:41:32 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/03/2022 16:41:35 - INFO - codeparrot_training - Step 2787: {'lr': 0.0004999651160470447, 'samples': 1427456, 'steps': 2787, 'loss/train': 2.9974162578582764}
-03/03/2022 16:41:38 - INFO - codeparrot_training - Step 2788: {'lr': 0.0004999650273423389, 'samples': 1427968, 'steps': 2788, 'loss/train': 3.308454990386963}
-03/03/2022 16:41:40 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/03/2022 16:41:43 - INFO - codeparrot_training - Step 2789: {'lr': 0.0004999649385250028, 'samples': 1428480, 'steps': 2789, 'loss/train': 2.9546446800231934}
-03/03/2022 16:41:46 - INFO - codeparrot_training - Step 2790: {'lr': 0.0004999648495950363, 'samples': 1428992, 'steps': 2790, 'loss/train': 3.3561437129974365}
-03/03/2022 16:41:48 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/03/2022 16:41:52 - INFO - codeparrot_training - Step 2791: {'lr': 0.0004999647605524396, 'samples': 1429504, 'steps': 2791, 'loss/train': 0.43039724230766296}
-03/03/2022 16:41:55 - INFO - codeparrot_training - Step 2792: {'lr': 0.0004999646713972126, 'samples': 1430016, 'steps': 2792, 'loss/train': 3.791672468185425}
-03/03/2022 16:41:56 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/03/2022 16:42:00 - INFO - codeparrot_training - Step 2793: {'lr': 0.0004999645821293552, 'samples': 1430528, 'steps': 2793, 'loss/train': 2.333115577697754}
-03/03/2022 16:42:03 - INFO - codeparrot_training - Step 2794: {'lr': 0.0004999644927488678, 'samples': 1431040, 'steps': 2794, 'loss/train': 2.9044437408447266}
-03/03/2022 16:42:05 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/03/2022 16:42:08 - INFO - codeparrot_training - Step 2795: {'lr': 0.0004999644032557503, 'samples': 1431552, 'steps': 2795, 'loss/train': 2.2309656143188477}
-03/03/2022 16:42:12 - INFO - codeparrot_training - Step 2796: {'lr': 0.0004999643136500027, 'samples': 1432064, 'steps': 2796, 'loss/train': 3.2770564556121826}
-03/03/2022 16:42:13 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/03/2022 16:42:17 - INFO - codeparrot_training - Step 2797: {'lr': 0.0004999642239316249, 'samples': 1432576, 'steps': 2797, 'loss/train': 3.998497247695923}
-03/03/2022 16:42:20 - INFO - codeparrot_training - Step 2798: {'lr': 0.000499964134100617, 'samples': 1433088, 'steps': 2798, 'loss/train': 3.8539581298828125}
-03/03/2022 16:42:21 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 16:42:25 - INFO - codeparrot_training - Step 2799: {'lr': 0.0004999640441569793, 'samples': 1433600, 'steps': 2799, 'loss/train': 3.7501556873321533}
-03/03/2022 16:42:28 - INFO - codeparrot_training - Step 2800: {'lr': 0.0004999639541007116, 'samples': 1434112, 'steps': 2800, 'loss/train': 2.857802152633667}
-03/03/2022 16:42:30 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/03/2022 16:42:34 - INFO - codeparrot_training - Step 2801: {'lr': 0.0004999638639318141, 'samples': 1434624, 'steps': 2801, 'loss/train': 1.9306632280349731}
-03/03/2022 16:42:37 - INFO - codeparrot_training - Step 2802: {'lr': 0.0004999637736502866, 'samples': 1435136, 'steps': 2802, 'loss/train': 2.8554866313934326}
-03/03/2022 16:42:38 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/03/2022 16:42:42 - INFO - codeparrot_training - Step 2803: {'lr': 0.0004999636832561293, 'samples': 1435648, 'steps': 2803, 'loss/train': 2.6029152870178223}
-03/03/2022 16:42:46 - INFO - codeparrot_training - Step 2804: {'lr': 0.0004999635927493423, 'samples': 1436160, 'steps': 2804, 'loss/train': 2.9625725746154785}
-03/03/2022 16:42:47 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/03/2022 16:42:51 - INFO - codeparrot_training - Step 2805: {'lr': 0.0004999635021299255, 'samples': 1436672, 'steps': 2805, 'loss/train': 2.49249267578125}
-03/03/2022 16:42:54 - INFO - codeparrot_training - Step 2806: {'lr': 0.0004999634113978791, 'samples': 1437184, 'steps': 2806, 'loss/train': 1.568454623222351}
-03/03/2022 16:42:56 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/03/2022 16:43:00 - INFO - codeparrot_training - Step 2807: {'lr': 0.0004999633205532029, 'samples': 1437696, 'steps': 2807, 'loss/train': 3.222116231918335}
-03/03/2022 16:43:03 - INFO - codeparrot_training - Step 2808: {'lr': 0.0004999632295958972, 'samples': 1438208, 'steps': 2808, 'loss/train': 3.8004493713378906}
-03/03/2022 16:43:04 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/03/2022 16:43:08 - INFO - codeparrot_training - Step 2809: {'lr': 0.0004999631385259617, 'samples': 1438720, 'steps': 2809, 'loss/train': 3.1872613430023193}
-03/03/2022 16:43:11 - INFO - codeparrot_training - Step 2810: {'lr': 0.000499963047343397, 'samples': 1439232, 'steps': 2810, 'loss/train': 2.936629056930542}
-03/03/2022 16:43:13 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/03/2022 16:43:17 - INFO - codeparrot_training - Step 2811: {'lr': 0.0004999629560482026, 'samples': 1439744, 'steps': 2811, 'loss/train': 2.819894790649414}
-03/03/2022 16:43:20 - INFO - codeparrot_training - Step 2812: {'lr': 0.0004999628646403788, 'samples': 1440256, 'steps': 2812, 'loss/train': 2.7867915630340576}
-03/03/2022 16:43:21 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/03/2022 16:43:25 - INFO - codeparrot_training - Step 2813: {'lr': 0.0004999627731199256, 'samples': 1440768, 'steps': 2813, 'loss/train': 2.9790804386138916}
-03/03/2022 16:43:28 - INFO - codeparrot_training - Step 2814: {'lr': 0.0004999626814868429, 'samples': 1441280, 'steps': 2814, 'loss/train': 3.0541512966156006}
-03/03/2022 16:43:29 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/03/2022 16:43:33 - INFO - codeparrot_training - Step 2815: {'lr': 0.0004999625897411311, 'samples': 1441792, 'steps': 2815, 'loss/train': 3.0761306285858154}
-03/03/2022 16:43:37 - INFO - codeparrot_training - Step 2816: {'lr': 0.0004999624978827899, 'samples': 1442304, 'steps': 2816, 'loss/train': 2.8112967014312744}
-03/03/2022 16:43:38 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/03/2022 16:43:42 - INFO - codeparrot_training - Step 2817: {'lr': 0.0004999624059118194, 'samples': 1442816, 'steps': 2817, 'loss/train': 3.1284847259521484}
-03/03/2022 16:43:45 - INFO - codeparrot_training - Step 2818: {'lr': 0.0004999623138282198, 'samples': 1443328, 'steps': 2818, 'loss/train': 3.0432567596435547}
-03/03/2022 16:43:46 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/03/2022 16:43:50 - INFO - codeparrot_training - Step 2819: {'lr': 0.000499962221631991, 'samples': 1443840, 'steps': 2819, 'loss/train': 2.4113528728485107}
-03/03/2022 16:43:53 - INFO - codeparrot_training - Step 2820: {'lr': 0.0004999621293231331, 'samples': 1444352, 'steps': 2820, 'loss/train': 2.8052361011505127}
-03/03/2022 16:43:54 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/03/2022 16:43:59 - INFO - codeparrot_training - Step 2821: {'lr': 0.0004999620369016461, 'samples': 1444864, 'steps': 2821, 'loss/train': 2.4694979190826416}
-03/03/2022 16:44:02 - INFO - codeparrot_training - Step 2822: {'lr': 0.00049996194436753, 'samples': 1445376, 'steps': 2822, 'loss/train': 3.619378089904785}
-03/03/2022 16:44:03 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/03/2022 16:44:07 - INFO - codeparrot_training - Step 2823: {'lr': 0.000499961851720785, 'samples': 1445888, 'steps': 2823, 'loss/train': 1.5173958539962769}
-03/03/2022 16:44:10 - INFO - codeparrot_training - Step 2824: {'lr': 0.000499961758961411, 'samples': 1446400, 'steps': 2824, 'loss/train': 1.1305230855941772}
-03/03/2022 16:44:11 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/03/2022 16:44:15 - INFO - codeparrot_training - Step 2825: {'lr': 0.0004999616660894081, 'samples': 1446912, 'steps': 2825, 'loss/train': 2.3258564472198486}
-03/03/2022 16:44:19 - INFO - codeparrot_training - Step 2826: {'lr': 0.0004999615731047762, 'samples': 1447424, 'steps': 2826, 'loss/train': 2.947964668273926}
-03/03/2022 16:44:19 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/03/2022 16:44:24 - INFO - codeparrot_training - Step 2827: {'lr': 0.0004999614800075158, 'samples': 1447936, 'steps': 2827, 'loss/train': 3.4644880294799805}
-03/03/2022 16:44:27 - INFO - codeparrot_training - Step 2828: {'lr': 0.0004999613867976264, 'samples': 1448448, 'steps': 2828, 'loss/train': 2.9566638469696045}
-03/03/2022 16:44:27 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/03/2022 16:44:32 - INFO - codeparrot_training - Step 2829: {'lr': 0.0004999612934751082, 'samples': 1448960, 'steps': 2829, 'loss/train': 3.086613416671753}
-03/03/2022 16:44:36 - INFO - codeparrot_training - Step 2830: {'lr': 0.0004999612000399614, 'samples': 1449472, 'steps': 2830, 'loss/train': 1.5432345867156982}
-03/03/2022 16:44:36 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/03/2022 16:44:41 - INFO - codeparrot_training - Step 2831: {'lr': 0.0004999611064921859, 'samples': 1449984, 'steps': 2831, 'loss/train': 3.0353586673736572}
-03/03/2022 16:44:44 - INFO - codeparrot_training - Step 2832: {'lr': 0.0004999610128317818, 'samples': 1450496, 'steps': 2832, 'loss/train': 3.705756902694702}
-03/03/2022 16:44:44 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/03/2022 16:44:49 - INFO - codeparrot_training - Step 2833: {'lr': 0.0004999609190587492, 'samples': 1451008, 'steps': 2833, 'loss/train': 2.6160504817962646}
-03/03/2022 16:44:52 - INFO - codeparrot_training - Step 2834: {'lr': 0.000499960825173088, 'samples': 1451520, 'steps': 2834, 'loss/train': 2.667778253555298}
-03/03/2022 16:44:53 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/03/2022 16:44:58 - INFO - codeparrot_training - Step 2835: {'lr': 0.0004999607311747983, 'samples': 1452032, 'steps': 2835, 'loss/train': 2.8666133880615234}
-03/03/2022 16:45:01 - INFO - codeparrot_training - Step 2836: {'lr': 0.0004999606370638801, 'samples': 1452544, 'steps': 2836, 'loss/train': 1.6883126497268677}
-03/03/2022 16:45:01 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/03/2022 16:45:06 - INFO - codeparrot_training - Step 2837: {'lr': 0.0004999605428403336, 'samples': 1453056, 'steps': 2837, 'loss/train': 2.7956125736236572}
-03/03/2022 16:45:09 - INFO - codeparrot_training - Step 2838: {'lr': 0.0004999604485041585, 'samples': 1453568, 'steps': 2838, 'loss/train': 0.4438847303390503}
-03/03/2022 16:45:09 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/03/2022 16:45:15 - INFO - codeparrot_training - Step 2839: {'lr': 0.0004999603540553554, 'samples': 1454080, 'steps': 2839, 'loss/train': 3.6946747303009033}
-03/03/2022 16:45:17 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/03/2022 16:45:20 - INFO - codeparrot_training - Step 2840: {'lr': 0.0004999602594939238, 'samples': 1454592, 'steps': 2840, 'loss/train': 2.51926589012146}
-03/03/2022 16:45:23 - INFO - codeparrot_training - Step 2841: {'lr': 0.0004999601648198641, 'samples': 1455104, 'steps': 2841, 'loss/train': 3.2881579399108887}
-03/03/2022 16:45:26 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/03/2022 16:45:28 - INFO - codeparrot_training - Step 2842: {'lr': 0.0004999600700331761, 'samples': 1455616, 'steps': 2842, 'loss/train': 2.6718385219573975}
-03/03/2022 16:45:31 - INFO - codeparrot_training - Step 2843: {'lr': 0.0004999599751338601, 'samples': 1456128, 'steps': 2843, 'loss/train': 2.1170666217803955}
-03/03/2022 16:45:34 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/03/2022 16:45:37 - INFO - codeparrot_training - Step 2844: {'lr': 0.0004999598801219158, 'samples': 1456640, 'steps': 2844, 'loss/train': 2.5187900066375732}
-03/03/2022 16:45:40 - INFO - codeparrot_training - Step 2845: {'lr': 0.0004999597849973435, 'samples': 1457152, 'steps': 2845, 'loss/train': 3.298952579498291}
-03/03/2022 16:45:42 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/03/2022 16:45:45 - INFO - codeparrot_training - Step 2846: {'lr': 0.0004999596897601432, 'samples': 1457664, 'steps': 2846, 'loss/train': 3.2442617416381836}
-03/03/2022 16:45:48 - INFO - codeparrot_training - Step 2847: {'lr': 0.0004999595944103149, 'samples': 1458176, 'steps': 2847, 'loss/train': 3.1593821048736572}
-03/03/2022 16:45:51 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/03/2022 16:45:54 - INFO - codeparrot_training - Step 2848: {'lr': 0.0004999594989478587, 'samples': 1458688, 'steps': 2848, 'loss/train': 2.7550294399261475}
-03/03/2022 16:45:57 - INFO - codeparrot_training - Step 2849: {'lr': 0.0004999594033727747, 'samples': 1459200, 'steps': 2849, 'loss/train': 2.896057605743408}
-03/03/2022 16:45:59 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/03/2022 16:46:02 - INFO - codeparrot_training - Step 2850: {'lr': 0.0004999593076850627, 'samples': 1459712, 'steps': 2850, 'loss/train': 0.38432011008262634}
-03/03/2022 16:46:05 - INFO - codeparrot_training - Step 2851: {'lr': 0.0004999592118847229, 'samples': 1460224, 'steps': 2851, 'loss/train': 2.7161507606506348}
-03/03/2022 16:46:07 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/03/2022 16:46:10 - INFO - codeparrot_training - Step 2852: {'lr': 0.0004999591159717554, 'samples': 1460736, 'steps': 2852, 'loss/train': 2.5032246112823486}
-03/03/2022 16:46:14 - INFO - codeparrot_training - Step 2853: {'lr': 0.0004999590199461602, 'samples': 1461248, 'steps': 2853, 'loss/train': 3.5437097549438477}
-03/03/2022 16:46:16 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/03/2022 16:46:19 - INFO - codeparrot_training - Step 2854: {'lr': 0.0004999589238079373, 'samples': 1461760, 'steps': 2854, 'loss/train': 2.760153293609619}
-03/03/2022 16:46:22 - INFO - codeparrot_training - Step 2855: {'lr': 0.0004999588275570868, 'samples': 1462272, 'steps': 2855, 'loss/train': 2.4435343742370605}
-03/03/2022 16:46:24 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/03/2022 16:46:27 - INFO - codeparrot_training - Step 2856: {'lr': 0.0004999587311936086, 'samples': 1462784, 'steps': 2856, 'loss/train': 2.5376758575439453}
-03/03/2022 16:46:30 - INFO - codeparrot_training - Step 2857: {'lr': 0.000499958634717503, 'samples': 1463296, 'steps': 2857, 'loss/train': 3.098510503768921}
-03/03/2022 16:46:32 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/03/2022 16:46:36 - INFO - codeparrot_training - Step 2858: {'lr': 0.0004999585381287696, 'samples': 1463808, 'steps': 2858, 'loss/train': 2.388951539993286}
-03/03/2022 16:46:39 - INFO - codeparrot_training - Step 2859: {'lr': 0.000499958441427409, 'samples': 1464320, 'steps': 2859, 'loss/train': 1.6173213720321655}
-03/03/2022 16:46:40 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/03/2022 16:46:44 - INFO - codeparrot_training - Step 2860: {'lr': 0.0004999583446134209, 'samples': 1464832, 'steps': 2860, 'loss/train': 3.3134214878082275}
-03/03/2022 16:46:47 - INFO - codeparrot_training - Step 2861: {'lr': 0.0004999582476868055, 'samples': 1465344, 'steps': 2861, 'loss/train': 2.238408088684082}
-03/03/2022 16:46:49 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/03/2022 16:46:53 - INFO - codeparrot_training - Step 2862: {'lr': 0.0004999581506475627, 'samples': 1465856, 'steps': 2862, 'loss/train': 2.844252109527588}
-03/03/2022 16:46:56 - INFO - codeparrot_training - Step 2863: {'lr': 0.0004999580534956927, 'samples': 1466368, 'steps': 2863, 'loss/train': 2.686821460723877}
-03/03/2022 16:46:57 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/03/2022 16:47:01 - INFO - codeparrot_training - Step 2864: {'lr': 0.0004999579562311953, 'samples': 1466880, 'steps': 2864, 'loss/train': 2.783883810043335}
-03/03/2022 16:47:04 - INFO - codeparrot_training - Step 2865: {'lr': 0.0004999578588540709, 'samples': 1467392, 'steps': 2865, 'loss/train': 2.1759700775146484}
-03/03/2022 16:47:06 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/03/2022 16:47:10 - INFO - codeparrot_training - Step 2866: {'lr': 0.0004999577613643192, 'samples': 1467904, 'steps': 2866, 'loss/train': 2.838135242462158}
-03/03/2022 16:47:13 - INFO - codeparrot_training - Step 2867: {'lr': 0.0004999576637619404, 'samples': 1468416, 'steps': 2867, 'loss/train': 2.4004790782928467}
-03/03/2022 16:47:15 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/03/2022 16:47:18 - INFO - codeparrot_training - Step 2868: {'lr': 0.0004999575660469347, 'samples': 1468928, 'steps': 2868, 'loss/train': 3.1228396892547607}
-03/03/2022 16:47:21 - INFO - codeparrot_training - Step 2869: {'lr': 0.0004999574682193017, 'samples': 1469440, 'steps': 2869, 'loss/train': 2.6474180221557617}
-03/03/2022 16:47:24 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/03/2022 16:47:26 - INFO - codeparrot_training - Step 2870: {'lr': 0.0004999573702790419, 'samples': 1469952, 'steps': 2870, 'loss/train': 2.027031183242798}
-03/03/2022 16:47:30 - INFO - codeparrot_training - Step 2871: {'lr': 0.0004999572722261551, 'samples': 1470464, 'steps': 2871, 'loss/train': 3.0093166828155518}
-03/03/2022 16:47:32 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/03/2022 16:47:35 - INFO - codeparrot_training - Step 2872: {'lr': 0.0004999571740606415, 'samples': 1470976, 'steps': 2872, 'loss/train': 2.5463478565216064}
-03/03/2022 16:47:38 - INFO - codeparrot_training - Step 2873: {'lr': 0.000499957075782501, 'samples': 1471488, 'steps': 2873, 'loss/train': 3.1903157234191895}
-03/03/2022 16:47:40 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/03/2022 16:47:43 - INFO - codeparrot_training - Step 2874: {'lr': 0.0004999569773917337, 'samples': 1472000, 'steps': 2874, 'loss/train': 2.2402002811431885}
-03/03/2022 16:47:46 - INFO - codeparrot_training - Step 2875: {'lr': 0.0004999568788883397, 'samples': 1472512, 'steps': 2875, 'loss/train': 1.9795204401016235}
-03/03/2022 16:47:49 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/03/2022 16:47:52 - INFO - codeparrot_training - Step 2876: {'lr': 0.0004999567802723188, 'samples': 1473024, 'steps': 2876, 'loss/train': 2.8544304370880127}
-03/03/2022 16:47:55 - INFO - codeparrot_training - Step 2877: {'lr': 0.0004999566815436715, 'samples': 1473536, 'steps': 2877, 'loss/train': 3.3672308921813965}
-03/03/2022 16:47:57 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/03/2022 16:48:00 - INFO - codeparrot_training - Step 2878: {'lr': 0.0004999565827023974, 'samples': 1474048, 'steps': 2878, 'loss/train': 2.9266796112060547}
-03/03/2022 16:48:03 - INFO - codeparrot_training - Step 2879: {'lr': 0.0004999564837484967, 'samples': 1474560, 'steps': 2879, 'loss/train': 2.1751248836517334}
-03/03/2022 16:48:05 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/03/2022 16:48:08 - INFO - codeparrot_training - Step 2880: {'lr': 0.0004999563846819696, 'samples': 1475072, 'steps': 2880, 'loss/train': 3.251425266265869}
-03/03/2022 16:48:12 - INFO - codeparrot_training - Step 2881: {'lr': 0.0004999562855028159, 'samples': 1475584, 'steps': 2881, 'loss/train': 2.9958724975585938}
-03/03/2022 16:48:13 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/03/2022 16:48:17 - INFO - codeparrot_training - Step 2882: {'lr': 0.0004999561862110358, 'samples': 1476096, 'steps': 2882, 'loss/train': 3.046231269836426}
-03/03/2022 16:48:20 - INFO - codeparrot_training - Step 2883: {'lr': 0.0004999560868066293, 'samples': 1476608, 'steps': 2883, 'loss/train': 3.035357713699341}
-03/03/2022 16:48:22 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/03/2022 16:48:25 - INFO - codeparrot_training - Step 2884: {'lr': 0.0004999559872895964, 'samples': 1477120, 'steps': 2884, 'loss/train': 2.7119312286376953}
-03/03/2022 16:48:28 - INFO - codeparrot_training - Step 2885: {'lr': 0.0004999558876599373, 'samples': 1477632, 'steps': 2885, 'loss/train': 2.8161816596984863}
-03/03/2022 16:48:30 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/03/2022 16:48:34 - INFO - codeparrot_training - Step 2886: {'lr': 0.0004999557879176518, 'samples': 1478144, 'steps': 2886, 'loss/train': 2.352759838104248}
-03/03/2022 16:48:37 - INFO - codeparrot_training - Step 2887: {'lr': 0.0004999556880627401, 'samples': 1478656, 'steps': 2887, 'loss/train': 2.4657838344573975}
-03/03/2022 16:48:38 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/03/2022 16:48:42 - INFO - codeparrot_training - Step 2888: {'lr': 0.0004999555880952023, 'samples': 1479168, 'steps': 2888, 'loss/train': 3.347620964050293}
-03/03/2022 16:48:45 - INFO - codeparrot_training - Step 2889: {'lr': 0.0004999554880150383, 'samples': 1479680, 'steps': 2889, 'loss/train': 1.623335599899292}
-03/03/2022 16:48:47 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/03/2022 16:48:50 - INFO - codeparrot_training - Step 2890: {'lr': 0.0004999553878222482, 'samples': 1480192, 'steps': 2890, 'loss/train': 2.8661653995513916}
-03/03/2022 16:48:54 - INFO - codeparrot_training - Step 2891: {'lr': 0.0004999552875168321, 'samples': 1480704, 'steps': 2891, 'loss/train': 3.1229605674743652}
-03/03/2022 16:48:55 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/03/2022 16:48:59 - INFO - codeparrot_training - Step 2892: {'lr': 0.0004999551870987901, 'samples': 1481216, 'steps': 2892, 'loss/train': 1.4061732292175293}
-03/03/2022 16:49:02 - INFO - codeparrot_training - Step 2893: {'lr': 0.000499955086568122, 'samples': 1481728, 'steps': 2893, 'loss/train': 3.0606513023376465}
-03/03/2022 16:49:04 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/03/2022 16:49:07 - INFO - codeparrot_training - Step 2894: {'lr': 0.000499954985924828, 'samples': 1482240, 'steps': 2894, 'loss/train': 1.5282270908355713}
-03/03/2022 16:49:10 - INFO - codeparrot_training - Step 2895: {'lr': 0.0004999548851689082, 'samples': 1482752, 'steps': 2895, 'loss/train': 2.9949023723602295}
-03/03/2022 16:49:12 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/03/2022 16:49:16 - INFO - codeparrot_training - Step 2896: {'lr': 0.0004999547843003627, 'samples': 1483264, 'steps': 2896, 'loss/train': 0.6338028907775879}
-03/03/2022 16:49:19 - INFO - codeparrot_training - Step 2897: {'lr': 0.0004999546833191912, 'samples': 1483776, 'steps': 2897, 'loss/train': 2.896749973297119}
-03/03/2022 16:49:21 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/03/2022 16:49:24 - INFO - codeparrot_training - Step 2898: {'lr': 0.0004999545822253941, 'samples': 1484288, 'steps': 2898, 'loss/train': 2.1511001586914062}
-03/03/2022 16:49:27 - INFO - codeparrot_training - Step 2899: {'lr': 0.0004999544810189713, 'samples': 1484800, 'steps': 2899, 'loss/train': 4.156933784484863}
-03/03/2022 16:49:30 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/03/2022 16:49:33 - INFO - codeparrot_training - Step 2900: {'lr': 0.0004999543796999228, 'samples': 1485312, 'steps': 2900, 'loss/train': 3.070873498916626}
-03/03/2022 16:49:36 - INFO - codeparrot_training - Step 2901: {'lr': 0.0004999542782682489, 'samples': 1485824, 'steps': 2901, 'loss/train': 2.656186580657959}
-03/03/2022 16:49:38 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/03/2022 16:49:41 - INFO - codeparrot_training - Step 2902: {'lr': 0.0004999541767239493, 'samples': 1486336, 'steps': 2902, 'loss/train': 1.978148102760315}
-03/03/2022 16:49:44 - INFO - codeparrot_training - Step 2903: {'lr': 0.0004999540750670243, 'samples': 1486848, 'steps': 2903, 'loss/train': 1.9795753955841064}
-03/03/2022 16:49:46 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/03/2022 16:49:50 - INFO - codeparrot_training - Step 2904: {'lr': 0.0004999539732974738, 'samples': 1487360, 'steps': 2904, 'loss/train': 6.763665199279785}
-03/03/2022 16:49:53 - INFO - codeparrot_training - Step 2905: {'lr': 0.0004999538714152978, 'samples': 1487872, 'steps': 2905, 'loss/train': 3.782104969024658}
-03/03/2022 16:49:56 - INFO - codeparrot_training - Step 2906: {'lr': 0.0004999537694204966, 'samples': 1488384, 'steps': 2906, 'loss/train': 1.9802603721618652}
-03/03/2022 16:49:56 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/03/2022 16:50:01 - INFO - codeparrot_training - Step 2907: {'lr': 0.0004999536673130701, 'samples': 1488896, 'steps': 2907, 'loss/train': 1.8991543054580688}
-03/03/2022 16:50:04 - INFO - codeparrot_training - Step 2908: {'lr': 0.0004999535650930182, 'samples': 1489408, 'steps': 2908, 'loss/train': 2.644139051437378}
-03/03/2022 16:50:05 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/03/2022 16:50:09 - INFO - codeparrot_training - Step 2909: {'lr': 0.0004999534627603411, 'samples': 1489920, 'steps': 2909, 'loss/train': 3.088216543197632}
-03/03/2022 16:50:13 - INFO - codeparrot_training - Step 2910: {'lr': 0.0004999533603150389, 'samples': 1490432, 'steps': 2910, 'loss/train': 3.5622875690460205}
-03/03/2022 16:50:13 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/03/2022 16:50:18 - INFO - codeparrot_training - Step 2911: {'lr': 0.0004999532577571116, 'samples': 1490944, 'steps': 2911, 'loss/train': 2.801483154296875}
-03/03/2022 16:50:21 - INFO - codeparrot_training - Step 2912: {'lr': 0.0004999531550865592, 'samples': 1491456, 'steps': 2912, 'loss/train': 2.2697737216949463}
-03/03/2022 16:50:21 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/03/2022 16:50:26 - INFO - codeparrot_training - Step 2913: {'lr': 0.0004999530523033817, 'samples': 1491968, 'steps': 2913, 'loss/train': 2.3897781372070312}
-03/03/2022 16:50:30 - INFO - codeparrot_training - Step 2914: {'lr': 0.0004999529494075792, 'samples': 1492480, 'steps': 2914, 'loss/train': 2.510364532470703}
-03/03/2022 16:50:30 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/03/2022 16:50:35 - INFO - codeparrot_training - Step 2915: {'lr': 0.0004999528463991518, 'samples': 1492992, 'steps': 2915, 'loss/train': 2.54477858543396}
-03/03/2022 16:50:37 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/03/2022 16:50:40 - INFO - codeparrot_training - Step 2916: {'lr': 0.0004999527432780995, 'samples': 1493504, 'steps': 2916, 'loss/train': 3.213799238204956}
-03/03/2022 16:50:43 - INFO - codeparrot_training - Step 2917: {'lr': 0.0004999526400444223, 'samples': 1494016, 'steps': 2917, 'loss/train': 2.6195068359375}
-03/03/2022 16:50:46 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/03/2022 16:50:48 - INFO - codeparrot_training - Step 2918: {'lr': 0.0004999525366981204, 'samples': 1494528, 'steps': 2918, 'loss/train': 2.4569740295410156}
-03/03/2022 16:50:52 - INFO - codeparrot_training - Step 2919: {'lr': 0.0004999524332391937, 'samples': 1495040, 'steps': 2919, 'loss/train': 2.6555092334747314}
-03/03/2022 16:50:54 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/03/2022 16:50:57 - INFO - codeparrot_training - Step 2920: {'lr': 0.0004999523296676423, 'samples': 1495552, 'steps': 2920, 'loss/train': 3.5851943492889404}
-03/03/2022 16:51:00 - INFO - codeparrot_training - Step 2921: {'lr': 0.0004999522259834662, 'samples': 1496064, 'steps': 2921, 'loss/train': 1.0952709913253784}
-03/03/2022 16:51:02 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/03/2022 16:51:05 - INFO - codeparrot_training - Step 2922: {'lr': 0.0004999521221866655, 'samples': 1496576, 'steps': 2922, 'loss/train': 2.8582754135131836}
-03/03/2022 16:51:09 - INFO - codeparrot_training - Step 2923: {'lr': 0.0004999520182772402, 'samples': 1497088, 'steps': 2923, 'loss/train': 0.3613796830177307}
-03/03/2022 16:51:11 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/03/2022 16:51:14 - INFO - codeparrot_training - Step 2924: {'lr': 0.0004999519142551905, 'samples': 1497600, 'steps': 2924, 'loss/train': 2.3661694526672363}
-03/03/2022 16:51:17 - INFO - codeparrot_training - Step 2925: {'lr': 0.0004999518101205162, 'samples': 1498112, 'steps': 2925, 'loss/train': 2.803722858428955}
-03/03/2022 16:51:19 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/03/2022 16:51:22 - INFO - codeparrot_training - Step 2926: {'lr': 0.0004999517058732175, 'samples': 1498624, 'steps': 2926, 'loss/train': 2.7775557041168213}
-03/03/2022 16:51:25 - INFO - codeparrot_training - Step 2927: {'lr': 0.0004999516015132945, 'samples': 1499136, 'steps': 2927, 'loss/train': 3.014251947402954}
-03/03/2022 16:51:27 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/03/2022 16:51:31 - INFO - codeparrot_training - Step 2928: {'lr': 0.0004999514970407471, 'samples': 1499648, 'steps': 2928, 'loss/train': 3.1578376293182373}
-03/03/2022 16:51:34 - INFO - codeparrot_training - Step 2929: {'lr': 0.0004999513924555754, 'samples': 1500160, 'steps': 2929, 'loss/train': 3.245116710662842}
-03/03/2022 16:51:36 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/03/2022 16:51:39 - INFO - codeparrot_training - Step 2930: {'lr': 0.0004999512877577794, 'samples': 1500672, 'steps': 2930, 'loss/train': 3.635124444961548}
-03/03/2022 16:51:42 - INFO - codeparrot_training - Step 2931: {'lr': 0.0004999511829473593, 'samples': 1501184, 'steps': 2931, 'loss/train': 3.4634807109832764}
-03/03/2022 16:51:44 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/03/2022 16:51:48 - INFO - codeparrot_training - Step 2932: {'lr': 0.0004999510780243151, 'samples': 1501696, 'steps': 2932, 'loss/train': 3.018321990966797}
-03/03/2022 16:51:51 - INFO - codeparrot_training - Step 2933: {'lr': 0.0004999509729886467, 'samples': 1502208, 'steps': 2933, 'loss/train': 1.8695935010910034}
-03/03/2022 16:51:53 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/03/2022 16:51:56 - INFO - codeparrot_training - Step 2934: {'lr': 0.0004999508678403542, 'samples': 1502720, 'steps': 2934, 'loss/train': 2.63712215423584}
-03/03/2022 16:51:59 - INFO - codeparrot_training - Step 2935: {'lr': 0.0004999507625794378, 'samples': 1503232, 'steps': 2935, 'loss/train': 2.7933175563812256}
-03/03/2022 16:52:01 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/03/2022 16:52:04 - INFO - codeparrot_training - Step 2936: {'lr': 0.0004999506572058974, 'samples': 1503744, 'steps': 2936, 'loss/train': 2.4611945152282715}
-03/03/2022 16:52:08 - INFO - codeparrot_training - Step 2937: {'lr': 0.0004999505517197331, 'samples': 1504256, 'steps': 2937, 'loss/train': 3.586103677749634}
-03/03/2022 16:52:09 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/03/2022 16:52:13 - INFO - codeparrot_training - Step 2938: {'lr': 0.000499950446120945, 'samples': 1504768, 'steps': 2938, 'loss/train': 1.9715590476989746}
-03/03/2022 16:52:16 - INFO - codeparrot_training - Step 2939: {'lr': 0.000499950340409533, 'samples': 1505280, 'steps': 2939, 'loss/train': 1.2664121389389038}
-03/03/2022 16:52:17 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/03/2022 16:52:21 - INFO - codeparrot_training - Step 2940: {'lr': 0.0004999502345854973, 'samples': 1505792, 'steps': 2940, 'loss/train': 2.706735134124756}
-03/03/2022 16:52:24 - INFO - codeparrot_training - Step 2941: {'lr': 0.0004999501286488378, 'samples': 1506304, 'steps': 2941, 'loss/train': 2.703542470932007}
-03/03/2022 16:52:26 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/03/2022 16:52:30 - INFO - codeparrot_training - Step 2942: {'lr': 0.0004999500225995547, 'samples': 1506816, 'steps': 2942, 'loss/train': 2.9381766319274902}
-03/03/2022 16:52:33 - INFO - codeparrot_training - Step 2943: {'lr': 0.000499949916437648, 'samples': 1507328, 'steps': 2943, 'loss/train': 2.9742491245269775}
-03/03/2022 16:52:34 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/03/2022 16:52:38 - INFO - codeparrot_training - Step 2944: {'lr': 0.0004999498101631177, 'samples': 1507840, 'steps': 2944, 'loss/train': 2.764361619949341}
-03/03/2022 16:52:41 - INFO - codeparrot_training - Step 2945: {'lr': 0.0004999497037759638, 'samples': 1508352, 'steps': 2945, 'loss/train': 2.016622304916382}
-03/03/2022 16:52:42 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/03/2022 16:52:46 - INFO - codeparrot_training - Step 2946: {'lr': 0.0004999495972761865, 'samples': 1508864, 'steps': 2946, 'loss/train': 2.1625781059265137}
-03/03/2022 16:52:50 - INFO - codeparrot_training - Step 2947: {'lr': 0.0004999494906637857, 'samples': 1509376, 'steps': 2947, 'loss/train': 1.55034339427948}
-03/03/2022 16:52:51 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/03/2022 16:52:55 - INFO - codeparrot_training - Step 2948: {'lr': 0.0004999493839387615, 'samples': 1509888, 'steps': 2948, 'loss/train': 2.8589117527008057}
-03/03/2022 16:52:58 - INFO - codeparrot_training - Step 2949: {'lr': 0.000499949277101114, 'samples': 1510400, 'steps': 2949, 'loss/train': 2.5486247539520264}
-03/03/2022 16:52:59 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/03/2022 16:53:03 - INFO - codeparrot_training - Step 2950: {'lr': 0.0004999491701508433, 'samples': 1510912, 'steps': 2950, 'loss/train': 2.798234224319458}
-03/03/2022 16:53:06 - INFO - codeparrot_training - Step 2951: {'lr': 0.0004999490630879493, 'samples': 1511424, 'steps': 2951, 'loss/train': 3.435621738433838}
-03/03/2022 16:53:07 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/03/2022 16:53:12 - INFO - codeparrot_training - Step 2952: {'lr': 0.0004999489559124321, 'samples': 1511936, 'steps': 2952, 'loss/train': 3.4545528888702393}
-03/03/2022 16:53:15 - INFO - codeparrot_training - Step 2953: {'lr': 0.0004999488486242918, 'samples': 1512448, 'steps': 2953, 'loss/train': 2.7492282390594482}
-03/03/2022 16:53:15 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/03/2022 16:53:20 - INFO - codeparrot_training - Step 2954: {'lr': 0.0004999487412235284, 'samples': 1512960, 'steps': 2954, 'loss/train': 2.9947216510772705}
-03/03/2022 16:53:23 - INFO - codeparrot_training - Step 2955: {'lr': 0.0004999486337101419, 'samples': 1513472, 'steps': 2955, 'loss/train': 1.8972951173782349}
-03/03/2022 16:53:24 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/03/2022 16:53:28 - INFO - codeparrot_training - Step 2956: {'lr': 0.0004999485260841324, 'samples': 1513984, 'steps': 2956, 'loss/train': 2.149407148361206}
-03/03/2022 16:53:32 - INFO - codeparrot_training - Step 2957: {'lr': 0.0004999484183455, 'samples': 1514496, 'steps': 2957, 'loss/train': 1.9423972368240356}
-03/03/2022 16:53:32 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/03/2022 16:53:37 - INFO - codeparrot_training - Step 2958: {'lr': 0.0004999483104942446, 'samples': 1515008, 'steps': 2958, 'loss/train': 3.0708155632019043}
-03/03/2022 16:53:40 - INFO - codeparrot_training - Step 2959: {'lr': 0.0004999482025303665, 'samples': 1515520, 'steps': 2959, 'loss/train': 3.2037572860717773}
-03/03/2022 16:53:40 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/03/2022 16:53:45 - INFO - codeparrot_training - Step 2960: {'lr': 0.0004999480944538655, 'samples': 1516032, 'steps': 2960, 'loss/train': 3.3366873264312744}
-03/03/2022 16:53:48 - INFO - codeparrot_training - Step 2961: {'lr': 0.0004999479862647417, 'samples': 1516544, 'steps': 2961, 'loss/train': 1.7511944770812988}
-03/03/2022 16:53:49 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/03/2022 16:53:54 - INFO - codeparrot_training - Step 2962: {'lr': 0.0004999478779629953, 'samples': 1517056, 'steps': 2962, 'loss/train': 0.9921990633010864}
-03/03/2022 16:53:57 - INFO - codeparrot_training - Step 2963: {'lr': 0.0004999477695486261, 'samples': 1517568, 'steps': 2963, 'loss/train': 3.249025583267212}
-03/03/2022 16:53:58 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/03/2022 16:54:02 - INFO - codeparrot_training - Step 2964: {'lr': 0.0004999476610216345, 'samples': 1518080, 'steps': 2964, 'loss/train': 3.530367612838745}
-03/03/2022 16:54:05 - INFO - codeparrot_training - Step 2965: {'lr': 0.0004999475523820203, 'samples': 1518592, 'steps': 2965, 'loss/train': 2.7569520473480225}
-03/03/2022 16:54:06 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/03/2022 16:54:11 - INFO - codeparrot_training - Step 2966: {'lr': 0.0004999474436297835, 'samples': 1519104, 'steps': 2966, 'loss/train': 2.4646494388580322}
-03/03/2022 16:54:14 - INFO - codeparrot_training - Step 2967: {'lr': 0.0004999473347649242, 'samples': 1519616, 'steps': 2967, 'loss/train': 2.6931183338165283}
-03/03/2022 16:54:15 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/03/2022 16:54:19 - INFO - codeparrot_training - Step 2968: {'lr': 0.0004999472257874426, 'samples': 1520128, 'steps': 2968, 'loss/train': 3.742434024810791}
-03/03/2022 16:54:22 - INFO - codeparrot_training - Step 2969: {'lr': 0.0004999471166973385, 'samples': 1520640, 'steps': 2969, 'loss/train': 2.9466493129730225}
-03/03/2022 16:54:23 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/03/2022 16:54:28 - INFO - codeparrot_training - Step 2970: {'lr': 0.0004999470074946122, 'samples': 1521152, 'steps': 2970, 'loss/train': 3.7005269527435303}
-03/03/2022 16:54:31 - INFO - codeparrot_training - Step 2971: {'lr': 0.0004999468981792636, 'samples': 1521664, 'steps': 2971, 'loss/train': 2.7872354984283447}
-03/03/2022 16:54:33 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/03/2022 16:54:36 - INFO - codeparrot_training - Step 2972: {'lr': 0.0004999467887512928, 'samples': 1522176, 'steps': 2972, 'loss/train': 2.5354108810424805}
-03/03/2022 16:54:39 - INFO - codeparrot_training - Step 2973: {'lr': 0.0004999466792106998, 'samples': 1522688, 'steps': 2973, 'loss/train': 3.665862798690796}
-03/03/2022 16:54:41 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/03/2022 16:54:44 - INFO - codeparrot_training - Step 2974: {'lr': 0.0004999465695574848, 'samples': 1523200, 'steps': 2974, 'loss/train': 2.738384485244751}
-03/03/2022 16:54:48 - INFO - codeparrot_training - Step 2975: {'lr': 0.0004999464597916476, 'samples': 1523712, 'steps': 2975, 'loss/train': 2.64980411529541}
-03/03/2022 16:54:49 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/03/2022 16:54:53 - INFO - codeparrot_training - Step 2976: {'lr': 0.0004999463499131884, 'samples': 1524224, 'steps': 2976, 'loss/train': 3.256869077682495}
-03/03/2022 16:54:56 - INFO - codeparrot_training - Step 2977: {'lr': 0.0004999462399221073, 'samples': 1524736, 'steps': 2977, 'loss/train': 0.622014582157135}
-03/03/2022 16:54:58 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/03/2022 16:55:01 - INFO - codeparrot_training - Step 2978: {'lr': 0.0004999461298184042, 'samples': 1525248, 'steps': 2978, 'loss/train': 2.186582088470459}
-03/03/2022 16:55:05 - INFO - codeparrot_training - Step 2979: {'lr': 0.0004999460196020793, 'samples': 1525760, 'steps': 2979, 'loss/train': 2.4215495586395264}
-03/03/2022 16:55:06 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/03/2022 16:55:10 - INFO - codeparrot_training - Step 2980: {'lr': 0.0004999459092731326, 'samples': 1526272, 'steps': 2980, 'loss/train': 3.043511390686035}
-03/03/2022 16:55:13 - INFO - codeparrot_training - Step 2981: {'lr': 0.000499945798831564, 'samples': 1526784, 'steps': 2981, 'loss/train': 0.34505370259284973}
-03/03/2022 16:55:15 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/03/2022 16:55:19 - INFO - codeparrot_training - Step 2982: {'lr': 0.0004999456882773737, 'samples': 1527296, 'steps': 2982, 'loss/train': 2.4173309803009033}
-03/03/2022 16:55:22 - INFO - codeparrot_training - Step 2983: {'lr': 0.0004999455776105618, 'samples': 1527808, 'steps': 2983, 'loss/train': 2.212392568588257}
-03/03/2022 16:55:24 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/03/2022 16:55:27 - INFO - codeparrot_training - Step 2984: {'lr': 0.0004999454668311283, 'samples': 1528320, 'steps': 2984, 'loss/train': 2.320594072341919}
-03/03/2022 16:55:30 - INFO - codeparrot_training - Step 2985: {'lr': 0.0004999453559390731, 'samples': 1528832, 'steps': 2985, 'loss/train': 3.268564224243164}
-03/03/2022 16:55:33 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/03/2022 16:55:36 - INFO - codeparrot_training - Step 2986: {'lr': 0.0004999452449343967, 'samples': 1529344, 'steps': 2986, 'loss/train': 2.425050973892212}
-03/03/2022 16:55:39 - INFO - codeparrot_training - Step 2987: {'lr': 0.0004999451338170985, 'samples': 1529856, 'steps': 2987, 'loss/train': 1.8262228965759277}
-03/03/2022 16:55:41 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/03/2022 16:55:44 - INFO - codeparrot_training - Step 2988: {'lr': 0.000499945022587179, 'samples': 1530368, 'steps': 2988, 'loss/train': 1.778611660003662}
-03/03/2022 16:55:47 - INFO - codeparrot_training - Step 2989: {'lr': 0.0004999449112446381, 'samples': 1530880, 'steps': 2989, 'loss/train': 2.0941693782806396}
-03/03/2022 16:55:49 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/03/2022 16:55:53 - INFO - codeparrot_training - Step 2990: {'lr': 0.000499944799789476, 'samples': 1531392, 'steps': 2990, 'loss/train': 0.45699453353881836}
-03/03/2022 16:55:56 - INFO - codeparrot_training - Step 2991: {'lr': 0.0004999446882216925, 'samples': 1531904, 'steps': 2991, 'loss/train': 3.459641218185425}
-03/03/2022 16:55:57 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/03/2022 16:56:01 - INFO - codeparrot_training - Step 2992: {'lr': 0.0004999445765412878, 'samples': 1532416, 'steps': 2992, 'loss/train': 2.763507127761841}
-03/03/2022 16:56:04 - INFO - codeparrot_training - Step 2993: {'lr': 0.0004999444647482619, 'samples': 1532928, 'steps': 2993, 'loss/train': 3.3254709243774414}
-03/03/2022 16:56:06 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/03/2022 16:56:09 - INFO - codeparrot_training - Step 2994: {'lr': 0.0004999443528426149, 'samples': 1533440, 'steps': 2994, 'loss/train': 3.735809087753296}
-03/03/2022 16:56:13 - INFO - codeparrot_training - Step 2995: {'lr': 0.0004999442408243469, 'samples': 1533952, 'steps': 2995, 'loss/train': 2.520660877227783}
-03/03/2022 16:56:14 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/03/2022 16:56:18 - INFO - codeparrot_training - Step 2996: {'lr': 0.0004999441286934578, 'samples': 1534464, 'steps': 2996, 'loss/train': 2.5852878093719482}
-03/03/2022 16:56:21 - INFO - codeparrot_training - Step 2997: {'lr': 0.0004999440164499478, 'samples': 1534976, 'steps': 2997, 'loss/train': 2.4575204849243164}
-03/03/2022 16:56:23 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/03/2022 16:56:26 - INFO - codeparrot_training - Step 2998: {'lr': 0.0004999439040938168, 'samples': 1535488, 'steps': 2998, 'loss/train': 2.7370760440826416}
-03/03/2022 16:56:29 - INFO - codeparrot_training - Step 2999: {'lr': 0.000499943791625065, 'samples': 1536000, 'steps': 2999, 'loss/train': 3.0840344429016113}
-03/03/2022 16:56:31 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/03/2022 16:56:35 - INFO - codeparrot_training - Step 3000: {'lr': 0.0004999436790436923, 'samples': 1536512, 'steps': 3000, 'loss/train': 2.73323130607605}
-03/03/2022 16:56:38 - INFO - codeparrot_training - Step 3001: {'lr': 0.000499943566349699, 'samples': 1537024, 'steps': 3001, 'loss/train': 3.658524751663208}
-03/03/2022 16:56:39 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/03/2022 16:56:44 - INFO - codeparrot_training - Step 3002: {'lr': 0.0004999434535430848, 'samples': 1537536, 'steps': 3002, 'loss/train': 2.86822772026062}
-03/03/2022 16:56:47 - INFO - codeparrot_training - Step 3003: {'lr': 0.0004999433406238501, 'samples': 1538048, 'steps': 3003, 'loss/train': 3.4883062839508057}
-03/03/2022 16:56:48 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/03/2022 16:56:52 - INFO - codeparrot_training - Step 3004: {'lr': 0.0004999432275919947, 'samples': 1538560, 'steps': 3004, 'loss/train': 3.6083505153656006}
-03/03/2022 16:56:55 - INFO - codeparrot_training - Step 3005: {'lr': 0.0004999431144475187, 'samples': 1539072, 'steps': 3005, 'loss/train': 3.043722152709961}
-03/03/2022 16:56:56 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/03/2022 16:57:00 - INFO - codeparrot_training - Step 3006: {'lr': 0.0004999430011904222, 'samples': 1539584, 'steps': 3006, 'loss/train': 1.712800145149231}
-03/03/2022 16:57:04 - INFO - codeparrot_training - Step 3007: {'lr': 0.0004999428878207054, 'samples': 1540096, 'steps': 3007, 'loss/train': 4.08502197265625}
-03/03/2022 16:57:05 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/03/2022 16:57:09 - INFO - codeparrot_training - Step 3008: {'lr': 0.000499942774338368, 'samples': 1540608, 'steps': 3008, 'loss/train': 2.389301061630249}
-03/03/2022 16:57:12 - INFO - codeparrot_training - Step 3009: {'lr': 0.0004999426607434104, 'samples': 1541120, 'steps': 3009, 'loss/train': 1.6993309259414673}
-03/03/2022 16:57:13 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/03/2022 16:57:17 - INFO - codeparrot_training - Step 3010: {'lr': 0.0004999425470358324, 'samples': 1541632, 'steps': 3010, 'loss/train': 2.3994078636169434}
-03/03/2022 16:57:20 - INFO - codeparrot_training - Step 3011: {'lr': 0.0004999424332156341, 'samples': 1542144, 'steps': 3011, 'loss/train': 2.4164786338806152}
-03/03/2022 16:57:22 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/03/2022 16:57:26 - INFO - codeparrot_training - Step 3012: {'lr': 0.0004999423192828156, 'samples': 1542656, 'steps': 3012, 'loss/train': 1.4398820400238037}
-03/03/2022 16:57:29 - INFO - codeparrot_training - Step 3013: {'lr': 0.0004999422052373771, 'samples': 1543168, 'steps': 3013, 'loss/train': 3.3699848651885986}
-03/03/2022 16:57:30 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/03/2022 16:57:34 - INFO - codeparrot_training - Step 3014: {'lr': 0.0004999420910793183, 'samples': 1543680, 'steps': 3014, 'loss/train': 3.2891273498535156}
-03/03/2022 16:57:37 - INFO - codeparrot_training - Step 3015: {'lr': 0.0004999419768086397, 'samples': 1544192, 'steps': 3015, 'loss/train': 2.9098665714263916}
-03/03/2022 16:57:38 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/03/2022 16:57:42 - INFO - codeparrot_training - Step 3016: {'lr': 0.0004999418624253408, 'samples': 1544704, 'steps': 3016, 'loss/train': 2.594470977783203}
-03/03/2022 16:57:46 - INFO - codeparrot_training - Step 3017: {'lr': 0.0004999417479294221, 'samples': 1545216, 'steps': 3017, 'loss/train': 3.1557273864746094}
-03/03/2022 16:57:46 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/03/2022 16:57:51 - INFO - codeparrot_training - Step 3018: {'lr': 0.0004999416333208835, 'samples': 1545728, 'steps': 3018, 'loss/train': 2.074286460876465}
-03/03/2022 16:57:54 - INFO - codeparrot_training - Step 3019: {'lr': 0.0004999415185997252, 'samples': 1546240, 'steps': 3019, 'loss/train': 2.579888105392456}
-03/03/2022 16:57:55 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/03/2022 16:57:59 - INFO - codeparrot_training - Step 3020: {'lr': 0.0004999414037659468, 'samples': 1546752, 'steps': 3020, 'loss/train': 3.6203603744506836}
-03/03/2022 16:58:02 - INFO - codeparrot_training - Step 3021: {'lr': 0.000499941288819549, 'samples': 1547264, 'steps': 3021, 'loss/train': 3.199841260910034}
-03/03/2022 16:58:03 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/03/2022 16:58:08 - INFO - codeparrot_training - Step 3022: {'lr': 0.0004999411737605313, 'samples': 1547776, 'steps': 3022, 'loss/train': 2.1176857948303223}
-03/03/2022 16:58:11 - INFO - codeparrot_training - Step 3023: {'lr': 0.000499941058588894, 'samples': 1548288, 'steps': 3023, 'loss/train': 1.9793611764907837}
-03/03/2022 16:58:11 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/03/2022 16:58:16 - INFO - codeparrot_training - Step 3024: {'lr': 0.0004999409433046371, 'samples': 1548800, 'steps': 3024, 'loss/train': 2.9934186935424805}
-03/03/2022 16:58:19 - INFO - codeparrot_training - Step 3025: {'lr': 0.0004999408279077607, 'samples': 1549312, 'steps': 3025, 'loss/train': 4.017479419708252}
-03/03/2022 16:58:20 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/03/2022 16:58:25 - INFO - codeparrot_training - Step 3026: {'lr': 0.0004999407123982649, 'samples': 1549824, 'steps': 3026, 'loss/train': 0.5607479214668274}
-03/03/2022 16:58:28 - INFO - codeparrot_training - Step 3027: {'lr': 0.0004999405967761495, 'samples': 1550336, 'steps': 3027, 'loss/train': 3.239078998565674}
-03/03/2022 16:58:28 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/03/2022 16:58:33 - INFO - codeparrot_training - Step 3028: {'lr': 0.0004999404810414149, 'samples': 1550848, 'steps': 3028, 'loss/train': 1.772896647453308}
-03/03/2022 16:58:36 - INFO - codeparrot_training - Step 3029: {'lr': 0.0004999403651940608, 'samples': 1551360, 'steps': 3029, 'loss/train': 2.721193790435791}
-03/03/2022 16:58:37 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/03/2022 16:58:42 - INFO - codeparrot_training - Step 3030: {'lr': 0.0004999402492340875, 'samples': 1551872, 'steps': 3030, 'loss/train': 2.8103930950164795}
-03/03/2022 16:58:45 - INFO - codeparrot_training - Step 3031: {'lr': 0.000499940133161495, 'samples': 1552384, 'steps': 3031, 'loss/train': 2.6185073852539062}
-03/03/2022 16:58:45 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/03/2022 16:58:50 - INFO - codeparrot_training - Step 3032: {'lr': 0.0004999400169762834, 'samples': 1552896, 'steps': 3032, 'loss/train': 2.8803467750549316}
-03/03/2022 16:58:53 - INFO - codeparrot_training - Step 3033: {'lr': 0.0004999399006784525, 'samples': 1553408, 'steps': 3033, 'loss/train': 3.338804244995117}
-03/03/2022 16:58:54 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/03/2022 16:58:59 - INFO - codeparrot_training - Step 3034: {'lr': 0.0004999397842680027, 'samples': 1553920, 'steps': 3034, 'loss/train': 3.1873862743377686}
-03/03/2022 16:59:02 - INFO - codeparrot_training - Step 3035: {'lr': 0.0004999396677449338, 'samples': 1554432, 'steps': 3035, 'loss/train': 3.9947705268859863}
-03/03/2022 16:59:03 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/03/2022 16:59:07 - INFO - codeparrot_training - Step 3036: {'lr': 0.000499939551109246, 'samples': 1554944, 'steps': 3036, 'loss/train': 3.17539119720459}
-03/03/2022 16:59:10 - INFO - codeparrot_training - Step 3037: {'lr': 0.0004999394343609393, 'samples': 1555456, 'steps': 3037, 'loss/train': 2.4144952297210693}
-03/03/2022 16:59:11 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/03/2022 16:59:16 - INFO - codeparrot_training - Step 3038: {'lr': 0.0004999393175000137, 'samples': 1555968, 'steps': 3038, 'loss/train': 0.7590366005897522}
-03/03/2022 16:59:19 - INFO - codeparrot_training - Step 3039: {'lr': 0.0004999392005264694, 'samples': 1556480, 'steps': 3039, 'loss/train': 3.3694674968719482}
-03/03/2022 16:59:19 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/03/2022 16:59:24 - INFO - codeparrot_training - Step 3040: {'lr': 0.0004999390834403062, 'samples': 1556992, 'steps': 3040, 'loss/train': 3.011796474456787}
-03/03/2022 16:59:27 - INFO - codeparrot_training - Step 3041: {'lr': 0.0004999389662415244, 'samples': 1557504, 'steps': 3041, 'loss/train': 2.1363580226898193}
-03/03/2022 16:59:27 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/03/2022 16:59:32 - INFO - codeparrot_training - Step 3042: {'lr': 0.000499938848930124, 'samples': 1558016, 'steps': 3042, 'loss/train': 2.9906158447265625}
-03/03/2022 16:59:36 - INFO - codeparrot_training - Step 3043: {'lr': 0.0004999387315061049, 'samples': 1558528, 'steps': 3043, 'loss/train': 2.3319952487945557}
-03/03/2022 16:59:36 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/03/2022 16:59:41 - INFO - codeparrot_training - Step 3044: {'lr': 0.0004999386139694673, 'samples': 1559040, 'steps': 3044, 'loss/train': 2.926527500152588}
-03/03/2022 16:59:44 - INFO - codeparrot_training - Step 3045: {'lr': 0.0004999384963202113, 'samples': 1559552, 'steps': 3045, 'loss/train': 3.160982847213745}
-03/03/2022 16:59:44 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/03/2022 16:59:49 - INFO - codeparrot_training - Step 3046: {'lr': 0.0004999383785583368, 'samples': 1560064, 'steps': 3046, 'loss/train': 2.948795795440674}
-03/03/2022 16:59:52 - INFO - codeparrot_training - Step 3047: {'lr': 0.0004999382606838439, 'samples': 1560576, 'steps': 3047, 'loss/train': 4.0511298179626465}
-03/03/2022 16:59:53 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/03/2022 16:59:58 - INFO - codeparrot_training - Step 3048: {'lr': 0.0004999381426967327, 'samples': 1561088, 'steps': 3048, 'loss/train': 3.3037965297698975}
-03/03/2022 17:00:01 - INFO - codeparrot_training - Step 3049: {'lr': 0.0004999380245970033, 'samples': 1561600, 'steps': 3049, 'loss/train': 3.782954692840576}
-03/03/2022 17:00:02 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/03/2022 17:00:06 - INFO - codeparrot_training - Step 3050: {'lr': 0.0004999379063846555, 'samples': 1562112, 'steps': 3050, 'loss/train': 2.4499409198760986}
-03/03/2022 17:00:10 - INFO - codeparrot_training - Step 3051: {'lr': 0.0004999377880596897, 'samples': 1562624, 'steps': 3051, 'loss/train': 3.1150593757629395}
-03/03/2022 17:00:11 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/03/2022 17:00:15 - INFO - codeparrot_training - Step 3052: {'lr': 0.0004999376696221057, 'samples': 1563136, 'steps': 3052, 'loss/train': 2.4729442596435547}
-03/03/2022 17:00:18 - INFO - codeparrot_training - Step 3053: {'lr': 0.0004999375510719037, 'samples': 1563648, 'steps': 3053, 'loss/train': 3.3743228912353516}
-03/03/2022 17:00:20 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/03/2022 17:00:23 - INFO - codeparrot_training - Step 3054: {'lr': 0.0004999374324090837, 'samples': 1564160, 'steps': 3054, 'loss/train': 2.0660548210144043}
-03/03/2022 17:00:26 - INFO - codeparrot_training - Step 3055: {'lr': 0.0004999373136336457, 'samples': 1564672, 'steps': 3055, 'loss/train': 2.4760117530822754}
-03/03/2022 17:00:28 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/03/2022 17:00:32 - INFO - codeparrot_training - Step 3056: {'lr': 0.0004999371947455899, 'samples': 1565184, 'steps': 3056, 'loss/train': 3.62672758102417}
-03/03/2022 17:00:35 - INFO - codeparrot_training - Step 3057: {'lr': 0.0004999370757449162, 'samples': 1565696, 'steps': 3057, 'loss/train': 2.5714051723480225}
-03/03/2022 17:00:36 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/03/2022 17:00:40 - INFO - codeparrot_training - Step 3058: {'lr': 0.0004999369566316247, 'samples': 1566208, 'steps': 3058, 'loss/train': 1.9593223333358765}
-03/03/2022 17:00:43 - INFO - codeparrot_training - Step 3059: {'lr': 0.0004999368374057155, 'samples': 1566720, 'steps': 3059, 'loss/train': 2.8943517208099365}
-03/03/2022 17:00:45 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/03/2022 17:00:49 - INFO - codeparrot_training - Step 3060: {'lr': 0.0004999367180671886, 'samples': 1567232, 'steps': 3060, 'loss/train': 2.2934627532958984}
-03/03/2022 17:00:52 - INFO - codeparrot_training - Step 3061: {'lr': 0.000499936598616044, 'samples': 1567744, 'steps': 3061, 'loss/train': 2.4961822032928467}
-03/03/2022 17:00:54 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/03/2022 17:00:57 - INFO - codeparrot_training - Step 3062: {'lr': 0.0004999364790522819, 'samples': 1568256, 'steps': 3062, 'loss/train': 2.7870068550109863}
-03/03/2022 17:01:00 - INFO - codeparrot_training - Step 3063: {'lr': 0.0004999363593759022, 'samples': 1568768, 'steps': 3063, 'loss/train': 2.2881481647491455}
-03/03/2022 17:01:02 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/03/2022 17:01:05 - INFO - codeparrot_training - Step 3064: {'lr': 0.0004999362395869052, 'samples': 1569280, 'steps': 3064, 'loss/train': 3.8400609493255615}
-03/03/2022 17:01:09 - INFO - codeparrot_training - Step 3065: {'lr': 0.0004999361196852906, 'samples': 1569792, 'steps': 3065, 'loss/train': 1.588464617729187}
-03/03/2022 17:01:10 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/03/2022 17:01:14 - INFO - codeparrot_training - Step 3066: {'lr': 0.0004999359996710588, 'samples': 1570304, 'steps': 3066, 'loss/train': 2.2829205989837646}
-03/03/2022 17:01:17 - INFO - codeparrot_training - Step 3067: {'lr': 0.0004999358795442096, 'samples': 1570816, 'steps': 3067, 'loss/train': 2.5555667877197266}
-03/03/2022 17:01:18 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/03/2022 17:01:22 - INFO - codeparrot_training - Step 3068: {'lr': 0.0004999357593047431, 'samples': 1571328, 'steps': 3068, 'loss/train': 2.7500314712524414}
-03/03/2022 17:01:25 - INFO - codeparrot_training - Step 3069: {'lr': 0.0004999356389526595, 'samples': 1571840, 'steps': 3069, 'loss/train': 2.743537664413452}
-03/03/2022 17:01:27 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/03/2022 17:01:31 - INFO - codeparrot_training - Step 3070: {'lr': 0.0004999355184879587, 'samples': 1572352, 'steps': 3070, 'loss/train': 3.9839508533477783}
-03/03/2022 17:01:34 - INFO - codeparrot_training - Step 3071: {'lr': 0.0004999353979106409, 'samples': 1572864, 'steps': 3071, 'loss/train': 1.6620782613754272}
-03/03/2022 17:01:35 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/03/2022 17:01:39 - INFO - codeparrot_training - Step 3072: {'lr': 0.000499935277220706, 'samples': 1573376, 'steps': 3072, 'loss/train': 3.1344823837280273}
-03/03/2022 17:01:42 - INFO - codeparrot_training - Step 3073: {'lr': 0.0004999351564181541, 'samples': 1573888, 'steps': 3073, 'loss/train': 1.925447702407837}
-03/03/2022 17:01:44 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/03/2022 17:01:47 - INFO - codeparrot_training - Step 3074: {'lr': 0.0004999350355029854, 'samples': 1574400, 'steps': 3074, 'loss/train': 3.8054072856903076}
-03/03/2022 17:01:51 - INFO - codeparrot_training - Step 3075: {'lr': 0.0004999349144751997, 'samples': 1574912, 'steps': 3075, 'loss/train': 3.0133216381073}
-03/03/2022 17:01:52 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/03/2022 17:01:56 - INFO - codeparrot_training - Step 3076: {'lr': 0.0004999347933347972, 'samples': 1575424, 'steps': 3076, 'loss/train': 2.225146770477295}
-03/03/2022 17:01:59 - INFO - codeparrot_training - Step 3077: {'lr': 0.0004999346720817779, 'samples': 1575936, 'steps': 3077, 'loss/train': 1.9959720373153687}
-03/03/2022 17:02:00 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/03/2022 17:02:04 - INFO - codeparrot_training - Step 3078: {'lr': 0.000499934550716142, 'samples': 1576448, 'steps': 3078, 'loss/train': 3.034642219543457}
-03/03/2022 17:02:08 - INFO - codeparrot_training - Step 3079: {'lr': 0.0004999344292378893, 'samples': 1576960, 'steps': 3079, 'loss/train': 2.573922634124756}
-03/03/2022 17:02:09 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/03/2022 17:02:13 - INFO - codeparrot_training - Step 3080: {'lr': 0.0004999343076470202, 'samples': 1577472, 'steps': 3080, 'loss/train': 2.871983051300049}
-03/03/2022 17:02:16 - INFO - codeparrot_training - Step 3081: {'lr': 0.0004999341859435345, 'samples': 1577984, 'steps': 3081, 'loss/train': 1.8925114870071411}
-03/03/2022 17:02:17 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/03/2022 17:02:21 - INFO - codeparrot_training - Step 3082: {'lr': 0.0004999340641274322, 'samples': 1578496, 'steps': 3082, 'loss/train': 3.5696139335632324}
-03/03/2022 17:02:24 - INFO - codeparrot_training - Step 3083: {'lr': 0.0004999339421987136, 'samples': 1579008, 'steps': 3083, 'loss/train': 2.7413642406463623}
-03/03/2022 17:02:25 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/03/2022 17:02:30 - INFO - codeparrot_training - Step 3084: {'lr': 0.0004999338201573786, 'samples': 1579520, 'steps': 3084, 'loss/train': 2.511333465576172}
-03/03/2022 17:02:33 - INFO - codeparrot_training - Step 3085: {'lr': 0.0004999336980034271, 'samples': 1580032, 'steps': 3085, 'loss/train': 3.681885242462158}
-03/03/2022 17:02:34 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/03/2022 17:02:38 - INFO - codeparrot_training - Step 3086: {'lr': 0.0004999335757368595, 'samples': 1580544, 'steps': 3086, 'loss/train': 3.395083427429199}
-03/03/2022 17:02:41 - INFO - codeparrot_training - Step 3087: {'lr': 0.0004999334533576757, 'samples': 1581056, 'steps': 3087, 'loss/train': 3.583638906478882}
-03/03/2022 17:02:42 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/03/2022 17:02:46 - INFO - codeparrot_training - Step 3088: {'lr': 0.0004999333308658756, 'samples': 1581568, 'steps': 3088, 'loss/train': 2.0097591876983643}
-03/03/2022 17:02:49 - INFO - codeparrot_training - Step 3089: {'lr': 0.0004999332082614597, 'samples': 1582080, 'steps': 3089, 'loss/train': 2.4555861949920654}
-03/03/2022 17:02:50 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/03/2022 17:02:55 - INFO - codeparrot_training - Step 3090: {'lr': 0.0004999330855444274, 'samples': 1582592, 'steps': 3090, 'loss/train': 2.084200382232666}
-03/03/2022 17:02:58 - INFO - codeparrot_training - Step 3091: {'lr': 0.0004999329627147792, 'samples': 1583104, 'steps': 3091, 'loss/train': 2.766651153564453}
-03/03/2022 17:02:59 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/03/2022 17:03:03 - INFO - codeparrot_training - Step 3092: {'lr': 0.0004999328397725152, 'samples': 1583616, 'steps': 3092, 'loss/train': 2.2201409339904785}
-03/03/2022 17:03:06 - INFO - codeparrot_training - Step 3093: {'lr': 0.0004999327167176352, 'samples': 1584128, 'steps': 3093, 'loss/train': 2.795578956604004}
-03/03/2022 17:03:07 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/03/2022 17:03:12 - INFO - codeparrot_training - Step 3094: {'lr': 0.0004999325935501395, 'samples': 1584640, 'steps': 3094, 'loss/train': 2.4546406269073486}
-03/03/2022 17:03:15 - INFO - codeparrot_training - Step 3095: {'lr': 0.0004999324702700279, 'samples': 1585152, 'steps': 3095, 'loss/train': 1.952446460723877}
-03/03/2022 17:03:16 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/03/2022 17:03:20 - INFO - codeparrot_training - Step 3096: {'lr': 0.0004999323468773007, 'samples': 1585664, 'steps': 3096, 'loss/train': 2.9668383598327637}
-03/03/2022 17:03:24 - INFO - codeparrot_training - Step 3097: {'lr': 0.0004999322233719578, 'samples': 1586176, 'steps': 3097, 'loss/train': 2.368140935897827}
-03/03/2022 17:03:26 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/03/2022 17:03:29 - INFO - codeparrot_training - Step 3098: {'lr': 0.0004999320997539992, 'samples': 1586688, 'steps': 3098, 'loss/train': 3.236647129058838}
-03/03/2022 17:03:32 - INFO - codeparrot_training - Step 3099: {'lr': 0.0004999319760234251, 'samples': 1587200, 'steps': 3099, 'loss/train': 3.8558356761932373}
-03/03/2022 17:03:35 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/03/2022 17:03:37 - INFO - codeparrot_training - Step 3100: {'lr': 0.0004999318521802356, 'samples': 1587712, 'steps': 3100, 'loss/train': 0.6512963175773621}
-03/03/2022 17:03:40 - INFO - codeparrot_training - Step 3101: {'lr': 0.0004999317282244305, 'samples': 1588224, 'steps': 3101, 'loss/train': 2.5115411281585693}
-03/03/2022 17:03:43 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/03/2022 17:03:46 - INFO - codeparrot_training - Step 3102: {'lr': 0.0004999316041560102, 'samples': 1588736, 'steps': 3102, 'loss/train': 2.5713682174682617}
-03/03/2022 17:03:49 - INFO - codeparrot_training - Step 3103: {'lr': 0.0004999314799749745, 'samples': 1589248, 'steps': 3103, 'loss/train': 2.4353208541870117}
-03/03/2022 17:03:51 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/03/2022 17:03:54 - INFO - codeparrot_training - Step 3104: {'lr': 0.0004999313556813235, 'samples': 1589760, 'steps': 3104, 'loss/train': 3.4859204292297363}
-03/03/2022 17:03:57 - INFO - codeparrot_training - Step 3105: {'lr': 0.0004999312312750573, 'samples': 1590272, 'steps': 3105, 'loss/train': 2.447747230529785}
-03/03/2022 17:03:59 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/03/2022 17:04:02 - INFO - codeparrot_training - Step 3106: {'lr': 0.000499931106756176, 'samples': 1590784, 'steps': 3106, 'loss/train': 2.5023605823516846}
-03/03/2022 17:04:06 - INFO - codeparrot_training - Step 3107: {'lr': 0.0004999309821246795, 'samples': 1591296, 'steps': 3107, 'loss/train': 3.1312501430511475}
-03/03/2022 17:04:07 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/03/2022 17:04:11 - INFO - codeparrot_training - Step 3108: {'lr': 0.000499930857380568, 'samples': 1591808, 'steps': 3108, 'loss/train': 3.1182613372802734}
-03/03/2022 17:04:14 - INFO - codeparrot_training - Step 3109: {'lr': 0.0004999307325238416, 'samples': 1592320, 'steps': 3109, 'loss/train': 2.5728583335876465}
-03/03/2022 17:04:16 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/03/2022 17:04:19 - INFO - codeparrot_training - Step 3110: {'lr': 0.0004999306075545002, 'samples': 1592832, 'steps': 3110, 'loss/train': 3.1181764602661133}
-03/03/2022 17:04:22 - INFO - codeparrot_training - Step 3111: {'lr': 0.0004999304824725439, 'samples': 1593344, 'steps': 3111, 'loss/train': 2.513261318206787}
-03/03/2022 17:04:24 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/03/2022 17:04:28 - INFO - codeparrot_training - Step 3112: {'lr': 0.0004999303572779727, 'samples': 1593856, 'steps': 3112, 'loss/train': 2.324193000793457}
-03/03/2022 17:04:31 - INFO - codeparrot_training - Step 3113: {'lr': 0.0004999302319707869, 'samples': 1594368, 'steps': 3113, 'loss/train': 3.271068811416626}
-03/03/2022 17:04:32 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/03/2022 17:04:36 - INFO - codeparrot_training - Step 3114: {'lr': 0.0004999301065509863, 'samples': 1594880, 'steps': 3114, 'loss/train': 3.3310585021972656}
-03/03/2022 17:04:39 - INFO - codeparrot_training - Step 3115: {'lr': 0.0004999299810185712, 'samples': 1595392, 'steps': 3115, 'loss/train': 1.0331887006759644}
-03/03/2022 17:04:41 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/03/2022 17:04:44 - INFO - codeparrot_training - Step 3116: {'lr': 0.0004999298553735413, 'samples': 1595904, 'steps': 3116, 'loss/train': 3.413482189178467}
-03/03/2022 17:04:48 - INFO - codeparrot_training - Step 3117: {'lr': 0.000499929729615897, 'samples': 1596416, 'steps': 3117, 'loss/train': 3.7765398025512695}
-03/03/2022 17:04:49 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/03/2022 17:04:53 - INFO - codeparrot_training - Step 3118: {'lr': 0.0004999296037456381, 'samples': 1596928, 'steps': 3118, 'loss/train': 1.8707209825515747}
-03/03/2022 17:04:56 - INFO - codeparrot_training - Step 3119: {'lr': 0.0004999294777627649, 'samples': 1597440, 'steps': 3119, 'loss/train': 1.862858772277832}
-03/03/2022 17:04:58 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/03/2022 17:05:02 - INFO - codeparrot_training - Step 3120: {'lr': 0.0004999293516672773, 'samples': 1597952, 'steps': 3120, 'loss/train': 2.5494027137756348}
-03/03/2022 17:05:05 - INFO - codeparrot_training - Step 3121: {'lr': 0.0004999292254591754, 'samples': 1598464, 'steps': 3121, 'loss/train': 7.465449333190918}
-03/03/2022 17:05:08 - INFO - codeparrot_training - Step 3122: {'lr': 0.0004999290991384591, 'samples': 1598976, 'steps': 3122, 'loss/train': 2.28774356842041}
-03/03/2022 17:05:08 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/03/2022 17:05:13 - INFO - codeparrot_training - Step 3123: {'lr': 0.0004999289727051289, 'samples': 1599488, 'steps': 3123, 'loss/train': 1.5419032573699951}
-03/03/2022 17:05:16 - INFO - codeparrot_training - Step 3124: {'lr': 0.0004999288461591842, 'samples': 1600000, 'steps': 3124, 'loss/train': 3.3454294204711914}
-03/03/2022 17:05:17 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/03/2022 17:05:22 - INFO - codeparrot_training - Step 3125: {'lr': 0.0004999287195006257, 'samples': 1600512, 'steps': 3125, 'loss/train': 3.6345365047454834}
-03/03/2022 17:05:25 - INFO - codeparrot_training - Step 3126: {'lr': 0.000499928592729453, 'samples': 1601024, 'steps': 3126, 'loss/train': 2.8627607822418213}
-03/03/2022 17:05:25 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/03/2022 17:05:30 - INFO - codeparrot_training - Step 3127: {'lr': 0.0004999284658456665, 'samples': 1601536, 'steps': 3127, 'loss/train': 1.328304648399353}
-03/03/2022 17:05:33 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/03/2022 17:05:36 - INFO - codeparrot_training - Step 3128: {'lr': 0.000499928338849266, 'samples': 1602048, 'steps': 3128, 'loss/train': 2.903782606124878}
-03/03/2022 17:05:39 - INFO - codeparrot_training - Step 3129: {'lr': 0.0004999282117402516, 'samples': 1602560, 'steps': 3129, 'loss/train': 3.107649087905884}
-03/03/2022 17:05:41 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/03/2022 17:05:44 - INFO - codeparrot_training - Step 3130: {'lr': 0.0004999280845186235, 'samples': 1603072, 'steps': 3130, 'loss/train': 4.006110668182373}
-03/03/2022 17:05:47 - INFO - codeparrot_training - Step 3131: {'lr': 0.0004999279571843816, 'samples': 1603584, 'steps': 3131, 'loss/train': 0.8248851895332336}
-03/03/2022 17:05:50 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/03/2022 17:05:53 - INFO - codeparrot_training - Step 3132: {'lr': 0.000499927829737526, 'samples': 1604096, 'steps': 3132, 'loss/train': 2.6746115684509277}
-03/03/2022 17:05:56 - INFO - codeparrot_training - Step 3133: {'lr': 0.0004999277021780569, 'samples': 1604608, 'steps': 3133, 'loss/train': 3.0486955642700195}
-03/03/2022 17:05:58 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/03/2022 17:06:01 - INFO - codeparrot_training - Step 3134: {'lr': 0.0004999275745059741, 'samples': 1605120, 'steps': 3134, 'loss/train': 3.2297000885009766}
-03/03/2022 17:06:04 - INFO - codeparrot_training - Step 3135: {'lr': 0.0004999274467212779, 'samples': 1605632, 'steps': 3135, 'loss/train': 2.3956644535064697}
-03/03/2022 17:06:07 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/03/2022 17:06:09 - INFO - codeparrot_training - Step 3136: {'lr': 0.0004999273188239681, 'samples': 1606144, 'steps': 3136, 'loss/train': 2.932687282562256}
-03/03/2022 17:06:13 - INFO - codeparrot_training - Step 3137: {'lr': 0.0004999271908140451, 'samples': 1606656, 'steps': 3137, 'loss/train': 2.4833178520202637}
-03/03/2022 17:06:16 - INFO - codeparrot_training - Step 3138: {'lr': 0.0004999270626915086, 'samples': 1607168, 'steps': 3138, 'loss/train': 2.874952793121338}
-03/03/2022 17:06:16 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/03/2022 17:06:21 - INFO - codeparrot_training - Step 3139: {'lr': 0.0004999269344563589, 'samples': 1607680, 'steps': 3139, 'loss/train': 2.971289873123169}
-03/03/2022 17:06:24 - INFO - codeparrot_training - Step 3140: {'lr': 0.0004999268061085959, 'samples': 1608192, 'steps': 3140, 'loss/train': 2.131265163421631}
-03/03/2022 17:06:25 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/03/2022 17:06:29 - INFO - codeparrot_training - Step 3141: {'lr': 0.0004999266776482199, 'samples': 1608704, 'steps': 3141, 'loss/train': 3.173490047454834}
-03/03/2022 17:06:33 - INFO - codeparrot_training - Step 3142: {'lr': 0.0004999265490752306, 'samples': 1609216, 'steps': 3142, 'loss/train': 2.1478161811828613}
-03/03/2022 17:06:33 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/03/2022 17:06:38 - INFO - codeparrot_training - Step 3143: {'lr': 0.0004999264203896284, 'samples': 1609728, 'steps': 3143, 'loss/train': 3.464094400405884}
-03/03/2022 17:06:41 - INFO - codeparrot_training - Step 3144: {'lr': 0.0004999262915914132, 'samples': 1610240, 'steps': 3144, 'loss/train': 3.17561411857605}
-03/03/2022 17:06:41 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/03/2022 17:06:46 - INFO - codeparrot_training - Step 3145: {'lr': 0.000499926162680585, 'samples': 1610752, 'steps': 3145, 'loss/train': 2.610203266143799}
-03/03/2022 17:06:49 - INFO - codeparrot_training - Step 3146: {'lr': 0.000499926033657144, 'samples': 1611264, 'steps': 3146, 'loss/train': 2.3648221492767334}
-03/03/2022 17:06:50 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/03/2022 17:06:55 - INFO - codeparrot_training - Step 3147: {'lr': 0.0004999259045210901, 'samples': 1611776, 'steps': 3147, 'loss/train': 3.393726348876953}
-03/03/2022 17:06:58 - INFO - codeparrot_training - Step 3148: {'lr': 0.0004999257752724234, 'samples': 1612288, 'steps': 3148, 'loss/train': 0.5157548785209656}
-03/03/2022 17:06:58 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/03/2022 17:07:03 - INFO - codeparrot_training - Step 3149: {'lr': 0.0004999256459111443, 'samples': 1612800, 'steps': 3149, 'loss/train': 2.7473878860473633}
-03/03/2022 17:07:06 - INFO - codeparrot_training - Step 3150: {'lr': 0.0004999255164372523, 'samples': 1613312, 'steps': 3150, 'loss/train': 1.5548590421676636}
-03/03/2022 17:07:07 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/03/2022 17:07:12 - INFO - codeparrot_training - Step 3151: {'lr': 0.0004999253868507476, 'samples': 1613824, 'steps': 3151, 'loss/train': 3.867713689804077}
-03/03/2022 17:07:15 - INFO - codeparrot_training - Step 3152: {'lr': 0.0004999252571516306, 'samples': 1614336, 'steps': 3152, 'loss/train': 2.6200544834136963}
-03/03/2022 17:07:15 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/03/2022 17:07:20 - INFO - codeparrot_training - Step 3153: {'lr': 0.0004999251273399011, 'samples': 1614848, 'steps': 3153, 'loss/train': 2.2708542346954346}
-03/03/2022 17:07:23 - INFO - codeparrot_training - Step 3154: {'lr': 0.0004999249974155592, 'samples': 1615360, 'steps': 3154, 'loss/train': 3.3140199184417725}
-03/03/2022 17:07:23 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/03/2022 17:07:28 - INFO - codeparrot_training - Step 3155: {'lr': 0.0004999248673786049, 'samples': 1615872, 'steps': 3155, 'loss/train': 3.1553444862365723}
-03/03/2022 17:07:31 - INFO - codeparrot_training - Step 3156: {'lr': 0.0004999247372290383, 'samples': 1616384, 'steps': 3156, 'loss/train': 2.6321499347686768}
-03/03/2022 17:07:32 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/03/2022 17:07:37 - INFO - codeparrot_training - Step 3157: {'lr': 0.0004999246069668596, 'samples': 1616896, 'steps': 3157, 'loss/train': 3.4026570320129395}
-03/03/2022 17:07:40 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/03/2022 17:07:42 - INFO - codeparrot_training - Step 3158: {'lr': 0.0004999244765920687, 'samples': 1617408, 'steps': 3158, 'loss/train': 0.6521148085594177}
-03/03/2022 17:07:45 - INFO - codeparrot_training - Step 3159: {'lr': 0.0004999243461046656, 'samples': 1617920, 'steps': 3159, 'loss/train': 4.805545330047607}
-03/03/2022 17:07:49 - INFO - codeparrot_training - Step 3160: {'lr': 0.0004999242155046504, 'samples': 1618432, 'steps': 3160, 'loss/train': 2.479771614074707}
-03/03/2022 17:07:49 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/03/2022 17:07:54 - INFO - codeparrot_training - Step 3161: {'lr': 0.0004999240847920233, 'samples': 1618944, 'steps': 3161, 'loss/train': 1.5201314687728882}
-03/03/2022 17:07:57 - INFO - codeparrot_training - Step 3162: {'lr': 0.0004999239539667842, 'samples': 1619456, 'steps': 3162, 'loss/train': 3.331648111343384}
-03/03/2022 17:07:57 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/03/2022 17:08:02 - INFO - codeparrot_training - Step 3163: {'lr': 0.0004999238230289333, 'samples': 1619968, 'steps': 3163, 'loss/train': 3.1433770656585693}
-03/03/2022 17:08:05 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/03/2022 17:08:07 - INFO - codeparrot_training - Step 3164: {'lr': 0.0004999236919784705, 'samples': 1620480, 'steps': 3164, 'loss/train': 2.3067240715026855}
-03/03/2022 17:08:11 - INFO - codeparrot_training - Step 3165: {'lr': 0.0004999235608153961, 'samples': 1620992, 'steps': 3165, 'loss/train': 2.0710079669952393}
-03/03/2022 17:08:13 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/03/2022 17:08:16 - INFO - codeparrot_training - Step 3166: {'lr': 0.0004999234295397098, 'samples': 1621504, 'steps': 3166, 'loss/train': 1.5704458951950073}
-03/03/2022 17:08:19 - INFO - codeparrot_training - Step 3167: {'lr': 0.000499923298151412, 'samples': 1622016, 'steps': 3167, 'loss/train': 2.52276349067688}
-03/03/2022 17:08:22 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/03/2022 17:08:24 - INFO - codeparrot_training - Step 3168: {'lr': 0.0004999231666505025, 'samples': 1622528, 'steps': 3168, 'loss/train': 3.7464592456817627}
-03/03/2022 17:08:27 - INFO - codeparrot_training - Step 3169: {'lr': 0.0004999230350369816, 'samples': 1623040, 'steps': 3169, 'loss/train': 2.637087106704712}
-03/03/2022 17:08:30 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/03/2022 17:08:33 - INFO - codeparrot_training - Step 3170: {'lr': 0.0004999229033108492, 'samples': 1623552, 'steps': 3170, 'loss/train': 2.5652010440826416}
-03/03/2022 17:08:36 - INFO - codeparrot_training - Step 3171: {'lr': 0.0004999227714721054, 'samples': 1624064, 'steps': 3171, 'loss/train': 2.8615496158599854}
-03/03/2022 17:08:38 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/03/2022 17:08:41 - INFO - codeparrot_training - Step 3172: {'lr': 0.0004999226395207501, 'samples': 1624576, 'steps': 3172, 'loss/train': 1.5188332796096802}
-03/03/2022 17:08:44 - INFO - codeparrot_training - Step 3173: {'lr': 0.0004999225074567837, 'samples': 1625088, 'steps': 3173, 'loss/train': 1.6403237581253052}
-03/03/2022 17:08:47 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/03/2022 17:08:49 - INFO - codeparrot_training - Step 3174: {'lr': 0.000499922375280206, 'samples': 1625600, 'steps': 3174, 'loss/train': 3.164886236190796}
-03/03/2022 17:08:53 - INFO - codeparrot_training - Step 3175: {'lr': 0.0004999222429910171, 'samples': 1626112, 'steps': 3175, 'loss/train': 2.994744300842285}
-03/03/2022 17:08:55 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/03/2022 17:08:58 - INFO - codeparrot_training - Step 3176: {'lr': 0.0004999221105892172, 'samples': 1626624, 'steps': 3176, 'loss/train': 3.450744390487671}
-03/03/2022 17:09:01 - INFO - codeparrot_training - Step 3177: {'lr': 0.0004999219780748062, 'samples': 1627136, 'steps': 3177, 'loss/train': 3.842543601989746}
-03/03/2022 17:09:04 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/03/2022 17:09:06 - INFO - codeparrot_training - Step 3178: {'lr': 0.0004999218454477843, 'samples': 1627648, 'steps': 3178, 'loss/train': 1.6521320343017578}
-03/03/2022 17:09:10 - INFO - codeparrot_training - Step 3179: {'lr': 0.0004999217127081514, 'samples': 1628160, 'steps': 3179, 'loss/train': 2.400299549102783}
-03/03/2022 17:09:12 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 17:09:15 - INFO - codeparrot_training - Step 3180: {'lr': 0.0004999215798559076, 'samples': 1628672, 'steps': 3180, 'loss/train': 2.1372478008270264}
-03/03/2022 17:09:18 - INFO - codeparrot_training - Step 3181: {'lr': 0.000499921446891053, 'samples': 1629184, 'steps': 3181, 'loss/train': 3.0301592350006104}
-03/03/2022 17:09:20 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/03/2022 17:09:23 - INFO - codeparrot_training - Step 3182: {'lr': 0.0004999213138135877, 'samples': 1629696, 'steps': 3182, 'loss/train': 3.164119005203247}
-03/03/2022 17:09:27 - INFO - codeparrot_training - Step 3183: {'lr': 0.0004999211806235117, 'samples': 1630208, 'steps': 3183, 'loss/train': 0.4649476110935211}
-03/03/2022 17:09:29 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/03/2022 17:09:32 - INFO - codeparrot_training - Step 3184: {'lr': 0.000499921047320825, 'samples': 1630720, 'steps': 3184, 'loss/train': 2.762665271759033}
-03/03/2022 17:09:35 - INFO - codeparrot_training - Step 3185: {'lr': 0.0004999209139055278, 'samples': 1631232, 'steps': 3185, 'loss/train': 3.1531805992126465}
-03/03/2022 17:09:37 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/03/2022 17:09:40 - INFO - codeparrot_training - Step 3186: {'lr': 0.0004999207803776201, 'samples': 1631744, 'steps': 3186, 'loss/train': 3.335547924041748}
-03/03/2022 17:09:43 - INFO - codeparrot_training - Step 3187: {'lr': 0.000499920646737102, 'samples': 1632256, 'steps': 3187, 'loss/train': 3.408154010772705}
-03/03/2022 17:09:46 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/03/2022 17:09:49 - INFO - codeparrot_training - Step 3188: {'lr': 0.0004999205129839734, 'samples': 1632768, 'steps': 3188, 'loss/train': 3.2741801738739014}
-03/03/2022 17:09:52 - INFO - codeparrot_training - Step 3189: {'lr': 0.0004999203791182345, 'samples': 1633280, 'steps': 3189, 'loss/train': 2.234330415725708}
-03/03/2022 17:09:54 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/03/2022 17:09:57 - INFO - codeparrot_training - Step 3190: {'lr': 0.0004999202451398853, 'samples': 1633792, 'steps': 3190, 'loss/train': 0.2653330862522125}
-03/03/2022 17:10:00 - INFO - codeparrot_training - Step 3191: {'lr': 0.000499920111048926, 'samples': 1634304, 'steps': 3191, 'loss/train': 2.2467868328094482}
-03/03/2022 17:10:02 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/03/2022 17:10:06 - INFO - codeparrot_training - Step 3192: {'lr': 0.0004999199768453565, 'samples': 1634816, 'steps': 3192, 'loss/train': 1.5938605070114136}
-03/03/2022 17:10:09 - INFO - codeparrot_training - Step 3193: {'lr': 0.0004999198425291769, 'samples': 1635328, 'steps': 3193, 'loss/train': 2.2746238708496094}
-03/03/2022 17:10:11 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/03/2022 17:10:14 - INFO - codeparrot_training - Step 3194: {'lr': 0.0004999197081003873, 'samples': 1635840, 'steps': 3194, 'loss/train': 2.664440155029297}
-03/03/2022 17:10:17 - INFO - codeparrot_training - Step 3195: {'lr': 0.0004999195735589877, 'samples': 1636352, 'steps': 3195, 'loss/train': 2.3604633808135986}
-03/03/2022 17:10:19 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/03/2022 17:10:22 - INFO - codeparrot_training - Step 3196: {'lr': 0.0004999194389049783, 'samples': 1636864, 'steps': 3196, 'loss/train': 3.0940935611724854}
-03/03/2022 17:10:25 - INFO - codeparrot_training - Step 3197: {'lr': 0.0004999193041383588, 'samples': 1637376, 'steps': 3197, 'loss/train': 3.4353840351104736}
-03/03/2022 17:10:27 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/03/2022 17:10:31 - INFO - codeparrot_training - Step 3198: {'lr': 0.0004999191692591299, 'samples': 1637888, 'steps': 3198, 'loss/train': 1.9620518684387207}
-03/03/2022 17:10:34 - INFO - codeparrot_training - Step 3199: {'lr': 0.000499919034267291, 'samples': 1638400, 'steps': 3199, 'loss/train': 2.629711389541626}
-03/03/2022 17:10:37 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/03/2022 17:10:39 - INFO - codeparrot_training - Step 3200: {'lr': 0.0004999188991628425, 'samples': 1638912, 'steps': 3200, 'loss/train': 2.821241855621338}
-03/03/2022 17:10:43 - INFO - codeparrot_training - Step 3201: {'lr': 0.0004999187639457844, 'samples': 1639424, 'steps': 3201, 'loss/train': 3.0432631969451904}
-03/03/2022 17:10:45 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/03/2022 17:10:48 - INFO - codeparrot_training - Step 3202: {'lr': 0.0004999186286161169, 'samples': 1639936, 'steps': 3202, 'loss/train': 3.304659128189087}
-03/03/2022 17:10:51 - INFO - codeparrot_training - Step 3203: {'lr': 0.0004999184931738397, 'samples': 1640448, 'steps': 3203, 'loss/train': 4.19053840637207}
-03/03/2022 17:10:54 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/03/2022 17:10:56 - INFO - codeparrot_training - Step 3204: {'lr': 0.0004999183576189532, 'samples': 1640960, 'steps': 3204, 'loss/train': 2.628227710723877}
-03/03/2022 17:10:59 - INFO - codeparrot_training - Step 3205: {'lr': 0.0004999182219514573, 'samples': 1641472, 'steps': 3205, 'loss/train': 3.6766059398651123}
-03/03/2022 17:11:02 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/03/2022 17:11:05 - INFO - codeparrot_training - Step 3206: {'lr': 0.0004999180861713522, 'samples': 1641984, 'steps': 3206, 'loss/train': 1.6787306070327759}
-03/03/2022 17:11:08 - INFO - codeparrot_training - Step 3207: {'lr': 0.0004999179502786377, 'samples': 1642496, 'steps': 3207, 'loss/train': 3.987818479537964}
-03/03/2022 17:11:11 - INFO - codeparrot_training - Step 3208: {'lr': 0.0004999178142733141, 'samples': 1643008, 'steps': 3208, 'loss/train': 4.15583610534668}
-03/03/2022 17:11:11 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/03/2022 17:11:16 - INFO - codeparrot_training - Step 3209: {'lr': 0.0004999176781553815, 'samples': 1643520, 'steps': 3209, 'loss/train': 3.3124165534973145}
-03/03/2022 17:11:19 - INFO - codeparrot_training - Step 3210: {'lr': 0.0004999175419248398, 'samples': 1644032, 'steps': 3210, 'loss/train': 2.627556562423706}
-03/03/2022 17:11:19 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/03/2022 17:11:25 - INFO - codeparrot_training - Step 3211: {'lr': 0.0004999174055816891, 'samples': 1644544, 'steps': 3211, 'loss/train': 2.08768892288208}
-03/03/2022 17:11:28 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/03/2022 17:11:30 - INFO - codeparrot_training - Step 3212: {'lr': 0.0004999172691259293, 'samples': 1645056, 'steps': 3212, 'loss/train': 2.2124674320220947}
-03/03/2022 17:11:33 - INFO - codeparrot_training - Step 3213: {'lr': 0.0004999171325575609, 'samples': 1645568, 'steps': 3213, 'loss/train': 2.686856985092163}
-03/03/2022 17:11:36 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/03/2022 17:11:38 - INFO - codeparrot_training - Step 3214: {'lr': 0.0004999169958765836, 'samples': 1646080, 'steps': 3214, 'loss/train': 2.803110361099243}
-03/03/2022 17:11:41 - INFO - codeparrot_training - Step 3215: {'lr': 0.0004999168590829975, 'samples': 1646592, 'steps': 3215, 'loss/train': 3.0305893421173096}
-03/03/2022 17:11:44 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/03/2022 17:11:47 - INFO - codeparrot_training - Step 3216: {'lr': 0.0004999167221768028, 'samples': 1647104, 'steps': 3216, 'loss/train': 2.773348093032837}
-03/03/2022 17:11:50 - INFO - codeparrot_training - Step 3217: {'lr': 0.0004999165851579994, 'samples': 1647616, 'steps': 3217, 'loss/train': 2.8608086109161377}
-03/03/2022 17:11:52 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/03/2022 17:11:55 - INFO - codeparrot_training - Step 3218: {'lr': 0.0004999164480265875, 'samples': 1648128, 'steps': 3218, 'loss/train': 2.5137412548065186}
-03/03/2022 17:11:58 - INFO - codeparrot_training - Step 3219: {'lr': 0.0004999163107825671, 'samples': 1648640, 'steps': 3219, 'loss/train': 2.9388837814331055}
-03/03/2022 17:12:00 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/03/2022 17:12:03 - INFO - codeparrot_training - Step 3220: {'lr': 0.0004999161734259383, 'samples': 1649152, 'steps': 3220, 'loss/train': 1.962165355682373}
-03/03/2022 17:12:07 - INFO - codeparrot_training - Step 3221: {'lr': 0.0004999160359567011, 'samples': 1649664, 'steps': 3221, 'loss/train': 2.2112157344818115}
-03/03/2022 17:12:08 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/03/2022 17:12:12 - INFO - codeparrot_training - Step 3222: {'lr': 0.0004999158983748555, 'samples': 1650176, 'steps': 3222, 'loss/train': 2.206014394760132}
-03/03/2022 17:12:15 - INFO - codeparrot_training - Step 3223: {'lr': 0.0004999157606804018, 'samples': 1650688, 'steps': 3223, 'loss/train': 1.0711002349853516}
-03/03/2022 17:12:17 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/03/2022 17:12:20 - INFO - codeparrot_training - Step 3224: {'lr': 0.0004999156228733398, 'samples': 1651200, 'steps': 3224, 'loss/train': 3.438539743423462}
-03/03/2022 17:12:23 - INFO - codeparrot_training - Step 3225: {'lr': 0.0004999154849536698, 'samples': 1651712, 'steps': 3225, 'loss/train': 2.9586122035980225}
-03/03/2022 17:12:25 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/03/2022 17:12:29 - INFO - codeparrot_training - Step 3226: {'lr': 0.0004999153469213917, 'samples': 1652224, 'steps': 3226, 'loss/train': 3.1565017700195312}
-03/03/2022 17:12:32 - INFO - codeparrot_training - Step 3227: {'lr': 0.0004999152087765055, 'samples': 1652736, 'steps': 3227, 'loss/train': 2.9213156700134277}
-03/03/2022 17:12:33 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/03/2022 17:12:37 - INFO - codeparrot_training - Step 3228: {'lr': 0.0004999150705190114, 'samples': 1653248, 'steps': 3228, 'loss/train': 3.5583932399749756}
-03/03/2022 17:12:40 - INFO - codeparrot_training - Step 3229: {'lr': 0.0004999149321489095, 'samples': 1653760, 'steps': 3229, 'loss/train': 1.9859654903411865}
-03/03/2022 17:12:41 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/03/2022 17:12:46 - INFO - codeparrot_training - Step 3230: {'lr': 0.0004999147936661997, 'samples': 1654272, 'steps': 3230, 'loss/train': 2.050604820251465}
-03/03/2022 17:12:49 - INFO - codeparrot_training - Step 3231: {'lr': 0.0004999146550708822, 'samples': 1654784, 'steps': 3231, 'loss/train': 2.4777016639709473}
-03/03/2022 17:12:52 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/03/2022 17:12:54 - INFO - codeparrot_training - Step 3232: {'lr': 0.000499914516362957, 'samples': 1655296, 'steps': 3232, 'loss/train': 2.9253621101379395}
-03/03/2022 17:12:57 - INFO - codeparrot_training - Step 3233: {'lr': 0.0004999143775424241, 'samples': 1655808, 'steps': 3233, 'loss/train': 3.603736162185669}
-03/03/2022 17:13:00 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/03/2022 17:13:02 - INFO - codeparrot_training - Step 3234: {'lr': 0.0004999142386092838, 'samples': 1656320, 'steps': 3234, 'loss/train': 3.0794525146484375}
-03/03/2022 17:13:06 - INFO - codeparrot_training - Step 3235: {'lr': 0.000499914099563536, 'samples': 1656832, 'steps': 3235, 'loss/train': 2.2751059532165527}
-03/03/2022 17:13:08 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/03/2022 17:13:11 - INFO - codeparrot_training - Step 3236: {'lr': 0.0004999139604051806, 'samples': 1657344, 'steps': 3236, 'loss/train': 2.004234552383423}
-03/03/2022 17:13:14 - INFO - codeparrot_training - Step 3237: {'lr': 0.0004999138211342179, 'samples': 1657856, 'steps': 3237, 'loss/train': 2.1669678688049316}
-03/03/2022 17:13:16 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/03/2022 17:13:19 - INFO - codeparrot_training - Step 3238: {'lr': 0.0004999136817506478, 'samples': 1658368, 'steps': 3238, 'loss/train': 3.01165509223938}
-03/03/2022 17:13:22 - INFO - codeparrot_training - Step 3239: {'lr': 0.0004999135422544707, 'samples': 1658880, 'steps': 3239, 'loss/train': 2.7612557411193848}
-03/03/2022 17:13:25 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/03/2022 17:13:28 - INFO - codeparrot_training - Step 3240: {'lr': 0.0004999134026456862, 'samples': 1659392, 'steps': 3240, 'loss/train': 1.7467108964920044}
-03/03/2022 17:13:31 - INFO - codeparrot_training - Step 3241: {'lr': 0.0004999132629242946, 'samples': 1659904, 'steps': 3241, 'loss/train': 2.286334753036499}
-03/03/2022 17:13:33 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/03/2022 17:13:36 - INFO - codeparrot_training - Step 3242: {'lr': 0.000499913123090296, 'samples': 1660416, 'steps': 3242, 'loss/train': 2.9461050033569336}
-03/03/2022 17:13:39 - INFO - codeparrot_training - Step 3243: {'lr': 0.0004999129831436904, 'samples': 1660928, 'steps': 3243, 'loss/train': 1.7647240161895752}
-03/03/2022 17:13:41 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/03/2022 17:13:44 - INFO - codeparrot_training - Step 3244: {'lr': 0.0004999128430844778, 'samples': 1661440, 'steps': 3244, 'loss/train': 2.9348437786102295}
-03/03/2022 17:13:48 - INFO - codeparrot_training - Step 3245: {'lr': 0.0004999127029126585, 'samples': 1661952, 'steps': 3245, 'loss/train': 2.5803918838500977}
-03/03/2022 17:13:50 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/03/2022 17:13:53 - INFO - codeparrot_training - Step 3246: {'lr': 0.0004999125626282322, 'samples': 1662464, 'steps': 3246, 'loss/train': 2.541604995727539}
-03/03/2022 17:13:56 - INFO - codeparrot_training - Step 3247: {'lr': 0.0004999124222311993, 'samples': 1662976, 'steps': 3247, 'loss/train': 4.035691261291504}
-03/03/2022 17:13:58 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/03/2022 17:14:01 - INFO - codeparrot_training - Step 3248: {'lr': 0.0004999122817215595, 'samples': 1663488, 'steps': 3248, 'loss/train': 3.107337236404419}
-03/03/2022 17:14:04 - INFO - codeparrot_training - Step 3249: {'lr': 0.0004999121410993133, 'samples': 1664000, 'steps': 3249, 'loss/train': 2.2093987464904785}
-03/03/2022 17:14:06 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/03/2022 17:14:10 - INFO - codeparrot_training - Step 3250: {'lr': 0.0004999120003644604, 'samples': 1664512, 'steps': 3250, 'loss/train': 2.8178553581237793}
-03/03/2022 17:14:13 - INFO - codeparrot_training - Step 3251: {'lr': 0.0004999118595170011, 'samples': 1665024, 'steps': 3251, 'loss/train': 3.4205546379089355}
-03/03/2022 17:14:15 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/03/2022 17:14:18 - INFO - codeparrot_training - Step 3252: {'lr': 0.0004999117185569354, 'samples': 1665536, 'steps': 3252, 'loss/train': 2.919506072998047}
-03/03/2022 17:14:21 - INFO - codeparrot_training - Step 3253: {'lr': 0.0004999115774842633, 'samples': 1666048, 'steps': 3253, 'loss/train': 3.2676570415496826}
-03/03/2022 17:14:23 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/03/2022 17:14:27 - INFO - codeparrot_training - Step 3254: {'lr': 0.0004999114362989849, 'samples': 1666560, 'steps': 3254, 'loss/train': 3.099179267883301}
-03/03/2022 17:14:30 - INFO - codeparrot_training - Step 3255: {'lr': 0.0004999112950011002, 'samples': 1667072, 'steps': 3255, 'loss/train': 2.8482823371887207}
-03/03/2022 17:14:35 - INFO - codeparrot_training - Step 3256: {'lr': 0.0004999111535906094, 'samples': 1667584, 'steps': 3256, 'loss/train': 2.8414599895477295}
-03/03/2022 17:14:38 - INFO - codeparrot_training - Step 3257: {'lr': 0.0004999110120675125, 'samples': 1668096, 'steps': 3257, 'loss/train': 2.3864519596099854}
-03/03/2022 17:14:40 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/03/2022 17:14:44 - INFO - codeparrot_training - Step 3258: {'lr': 0.0004999108704318095, 'samples': 1668608, 'steps': 3258, 'loss/train': 2.384385347366333}
-03/03/2022 17:14:47 - INFO - codeparrot_training - Step 3259: {'lr': 0.0004999107286835006, 'samples': 1669120, 'steps': 3259, 'loss/train': 2.52323317527771}
-03/03/2022 17:14:48 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/03/2022 17:14:52 - INFO - codeparrot_training - Step 3260: {'lr': 0.0004999105868225858, 'samples': 1669632, 'steps': 3260, 'loss/train': 1.8758745193481445}
-03/03/2022 17:14:55 - INFO - codeparrot_training - Step 3261: {'lr': 0.0004999104448490649, 'samples': 1670144, 'steps': 3261, 'loss/train': 3.7754602432250977}
-03/03/2022 17:14:56 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/03/2022 17:15:00 - INFO - codeparrot_training - Step 3262: {'lr': 0.0004999103027629384, 'samples': 1670656, 'steps': 3262, 'loss/train': 2.2947566509246826}
-03/03/2022 17:15:04 - INFO - codeparrot_training - Step 3263: {'lr': 0.0004999101605642061, 'samples': 1671168, 'steps': 3263, 'loss/train': 2.9705259799957275}
-03/03/2022 17:15:05 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/03/2022 17:15:09 - INFO - codeparrot_training - Step 3264: {'lr': 0.0004999100182528683, 'samples': 1671680, 'steps': 3264, 'loss/train': 2.902282476425171}
-03/03/2022 17:15:12 - INFO - codeparrot_training - Step 3265: {'lr': 0.0004999098758289248, 'samples': 1672192, 'steps': 3265, 'loss/train': 2.4553070068359375}
-03/03/2022 17:15:13 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/03/2022 17:15:17 - INFO - codeparrot_training - Step 3266: {'lr': 0.0004999097332923758, 'samples': 1672704, 'steps': 3266, 'loss/train': 2.07495379447937}
-03/03/2022 17:15:21 - INFO - codeparrot_training - Step 3267: {'lr': 0.0004999095906432213, 'samples': 1673216, 'steps': 3267, 'loss/train': 2.7839205265045166}
-03/03/2022 17:15:22 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/03/2022 17:15:26 - INFO - codeparrot_training - Step 3268: {'lr': 0.0004999094478814613, 'samples': 1673728, 'steps': 3268, 'loss/train': 2.388890027999878}
-03/03/2022 17:15:29 - INFO - codeparrot_training - Step 3269: {'lr': 0.0004999093050070961, 'samples': 1674240, 'steps': 3269, 'loss/train': 3.7101285457611084}
-03/03/2022 17:15:30 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/03/2022 17:15:34 - INFO - codeparrot_training - Step 3270: {'lr': 0.0004999091620201255, 'samples': 1674752, 'steps': 3270, 'loss/train': 3.1778390407562256}
-03/03/2022 17:15:37 - INFO - codeparrot_training - Step 3271: {'lr': 0.0004999090189205498, 'samples': 1675264, 'steps': 3271, 'loss/train': 3.498061180114746}
-03/03/2022 17:15:38 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/03/2022 17:15:43 - INFO - codeparrot_training - Step 3272: {'lr': 0.0004999088757083689, 'samples': 1675776, 'steps': 3272, 'loss/train': 2.9312329292297363}
-03/03/2022 17:15:46 - INFO - codeparrot_training - Step 3273: {'lr': 0.0004999087323835829, 'samples': 1676288, 'steps': 3273, 'loss/train': 3.227250576019287}
-03/03/2022 17:15:47 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/03/2022 17:15:51 - INFO - codeparrot_training - Step 3274: {'lr': 0.0004999085889461919, 'samples': 1676800, 'steps': 3274, 'loss/train': 2.545597791671753}
-03/03/2022 17:15:54 - INFO - codeparrot_training - Step 3275: {'lr': 0.0004999084453961959, 'samples': 1677312, 'steps': 3275, 'loss/train': 1.9713518619537354}
-03/03/2022 17:15:55 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/03/2022 17:15:59 - INFO - codeparrot_training - Step 3276: {'lr': 0.0004999083017335951, 'samples': 1677824, 'steps': 3276, 'loss/train': 3.0922610759735107}
-03/03/2022 17:16:03 - INFO - codeparrot_training - Step 3277: {'lr': 0.0004999081579583895, 'samples': 1678336, 'steps': 3277, 'loss/train': 1.9257805347442627}
-03/03/2022 17:16:03 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/03/2022 17:16:08 - INFO - codeparrot_training - Step 3278: {'lr': 0.0004999080140705791, 'samples': 1678848, 'steps': 3278, 'loss/train': 1.7623577117919922}
-03/03/2022 17:16:11 - INFO - codeparrot_training - Step 3279: {'lr': 0.0004999078700701639, 'samples': 1679360, 'steps': 3279, 'loss/train': 2.6713383197784424}
-03/03/2022 17:16:11 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/03/2022 17:16:16 - INFO - codeparrot_training - Step 3280: {'lr': 0.0004999077259571442, 'samples': 1679872, 'steps': 3280, 'loss/train': 3.537552833557129}
-03/03/2022 17:16:19 - INFO - codeparrot_training - Step 3281: {'lr': 0.0004999075817315199, 'samples': 1680384, 'steps': 3281, 'loss/train': 3.077975034713745}
-03/03/2022 17:16:20 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/03/2022 17:16:24 - INFO - codeparrot_training - Step 3282: {'lr': 0.0004999074373932911, 'samples': 1680896, 'steps': 3282, 'loss/train': 2.3269410133361816}
-03/03/2022 17:16:28 - INFO - codeparrot_training - Step 3283: {'lr': 0.0004999072929424579, 'samples': 1681408, 'steps': 3283, 'loss/train': 1.5639630556106567}
-03/03/2022 17:16:28 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/03/2022 17:16:33 - INFO - codeparrot_training - Step 3284: {'lr': 0.0004999071483790203, 'samples': 1681920, 'steps': 3284, 'loss/train': 2.3655848503112793}
-03/03/2022 17:16:36 - INFO - codeparrot_training - Step 3285: {'lr': 0.0004999070037029783, 'samples': 1682432, 'steps': 3285, 'loss/train': 3.358809232711792}
-03/03/2022 17:16:37 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/03/2022 17:16:41 - INFO - codeparrot_training - Step 3286: {'lr': 0.0004999068589143322, 'samples': 1682944, 'steps': 3286, 'loss/train': 0.729758620262146}
-03/03/2022 17:16:45 - INFO - codeparrot_training - Step 3287: {'lr': 0.0004999067140130819, 'samples': 1683456, 'steps': 3287, 'loss/train': 2.011780023574829}
-03/03/2022 17:16:45 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/03/2022 17:16:50 - INFO - codeparrot_training - Step 3288: {'lr': 0.0004999065689992273, 'samples': 1683968, 'steps': 3288, 'loss/train': 2.709617853164673}
-03/03/2022 17:16:53 - INFO - codeparrot_training - Step 3289: {'lr': 0.0004999064238727689, 'samples': 1684480, 'steps': 3289, 'loss/train': 3.4925050735473633}
-03/03/2022 17:16:53 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/03/2022 17:16:58 - INFO - codeparrot_training - Step 3290: {'lr': 0.0004999062786337064, 'samples': 1684992, 'steps': 3290, 'loss/train': 2.6360971927642822}
-03/03/2022 17:17:02 - INFO - codeparrot_training - Step 3291: {'lr': 0.0004999061332820401, 'samples': 1685504, 'steps': 3291, 'loss/train': 3.1296236515045166}
-03/03/2022 17:17:02 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/03/2022 17:17:07 - INFO - codeparrot_training - Step 3292: {'lr': 0.0004999059878177699, 'samples': 1686016, 'steps': 3292, 'loss/train': 3.0777924060821533}
-03/03/2022 17:17:10 - INFO - codeparrot_training - Step 3293: {'lr': 0.0004999058422408959, 'samples': 1686528, 'steps': 3293, 'loss/train': 2.3218016624450684}
-03/03/2022 17:17:10 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/03/2022 17:17:15 - INFO - codeparrot_training - Step 3294: {'lr': 0.0004999056965514181, 'samples': 1687040, 'steps': 3294, 'loss/train': 3.278587818145752}
-03/03/2022 17:17:18 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/03/2022 17:17:20 - INFO - codeparrot_training - Step 3295: {'lr': 0.0004999055507493368, 'samples': 1687552, 'steps': 3295, 'loss/train': 3.443573474884033}
-03/03/2022 17:17:24 - INFO - codeparrot_training - Step 3296: {'lr': 0.0004999054048346517, 'samples': 1688064, 'steps': 3296, 'loss/train': 2.9336061477661133}
-03/03/2022 17:17:26 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/03/2022 17:17:29 - INFO - codeparrot_training - Step 3297: {'lr': 0.0004999052588073633, 'samples': 1688576, 'steps': 3297, 'loss/train': 2.5668258666992188}
-03/03/2022 17:17:32 - INFO - codeparrot_training - Step 3298: {'lr': 0.0004999051126674714, 'samples': 1689088, 'steps': 3298, 'loss/train': 4.688945770263672}
-03/03/2022 17:17:35 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/03/2022 17:17:37 - INFO - codeparrot_training - Step 3299: {'lr': 0.0004999049664149761, 'samples': 1689600, 'steps': 3299, 'loss/train': 2.8824422359466553}
-03/03/2022 17:17:41 - INFO - codeparrot_training - Step 3300: {'lr': 0.0004999048200498774, 'samples': 1690112, 'steps': 3300, 'loss/train': 2.3504159450531006}
-03/03/2022 17:17:43 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/03/2022 17:17:46 - INFO - codeparrot_training - Step 3301: {'lr': 0.0004999046735721755, 'samples': 1690624, 'steps': 3301, 'loss/train': 2.3504092693328857}
-03/03/2022 17:17:49 - INFO - codeparrot_training - Step 3302: {'lr': 0.0004999045269818704, 'samples': 1691136, 'steps': 3302, 'loss/train': 1.819130301475525}
-03/03/2022 17:17:52 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/03/2022 17:17:54 - INFO - codeparrot_training - Step 3303: {'lr': 0.0004999043802789622, 'samples': 1691648, 'steps': 3303, 'loss/train': 3.09501314163208}
-03/03/2022 17:17:57 - INFO - codeparrot_training - Step 3304: {'lr': 0.000499904233463451, 'samples': 1692160, 'steps': 3304, 'loss/train': 3.1654160022735596}
-03/03/2022 17:18:00 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/03/2022 17:18:03 - INFO - codeparrot_training - Step 3305: {'lr': 0.0004999040865353367, 'samples': 1692672, 'steps': 3305, 'loss/train': 2.178650379180908}
-03/03/2022 17:18:06 - INFO - codeparrot_training - Step 3306: {'lr': 0.0004999039394946196, 'samples': 1693184, 'steps': 3306, 'loss/train': 2.0084445476531982}
-03/03/2022 17:18:08 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/03/2022 17:18:11 - INFO - codeparrot_training - Step 3307: {'lr': 0.0004999037923412995, 'samples': 1693696, 'steps': 3307, 'loss/train': 2.2655982971191406}
-03/03/2022 17:18:14 - INFO - codeparrot_training - Step 3308: {'lr': 0.0004999036450753767, 'samples': 1694208, 'steps': 3308, 'loss/train': 1.6685303449630737}
-03/03/2022 17:18:16 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/03/2022 17:18:20 - INFO - codeparrot_training - Step 3309: {'lr': 0.0004999034976968511, 'samples': 1694720, 'steps': 3309, 'loss/train': 2.7072291374206543}
-03/03/2022 17:18:23 - INFO - codeparrot_training - Step 3310: {'lr': 0.0004999033502057228, 'samples': 1695232, 'steps': 3310, 'loss/train': 3.3253469467163086}
-03/03/2022 17:18:26 - INFO - codeparrot_training - Step 3311: {'lr': 0.000499903202601992, 'samples': 1695744, 'steps': 3311, 'loss/train': 2.6117329597473145}
-03/03/2022 17:18:27 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/03/2022 17:18:31 - INFO - codeparrot_training - Step 3312: {'lr': 0.0004999030548856586, 'samples': 1696256, 'steps': 3312, 'loss/train': 3.7277019023895264}
-03/03/2022 17:18:34 - INFO - codeparrot_training - Step 3313: {'lr': 0.0004999029070567229, 'samples': 1696768, 'steps': 3313, 'loss/train': 2.4026546478271484}
-03/03/2022 17:18:35 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/03/2022 17:18:39 - INFO - codeparrot_training - Step 3314: {'lr': 0.0004999027591151847, 'samples': 1697280, 'steps': 3314, 'loss/train': 2.4240620136260986}
-03/03/2022 17:18:43 - INFO - codeparrot_training - Step 3315: {'lr': 0.0004999026110610442, 'samples': 1697792, 'steps': 3315, 'loss/train': 3.1103720664978027}
-03/03/2022 17:18:43 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/03/2022 17:18:48 - INFO - codeparrot_training - Step 3316: {'lr': 0.0004999024628943014, 'samples': 1698304, 'steps': 3316, 'loss/train': 2.6764280796051025}
-03/03/2022 17:18:51 - INFO - codeparrot_training - Step 3317: {'lr': 0.0004999023146149565, 'samples': 1698816, 'steps': 3317, 'loss/train': 3.0690629482269287}
-03/03/2022 17:18:51 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/03/2022 17:18:56 - INFO - codeparrot_training - Step 3318: {'lr': 0.0004999021662230093, 'samples': 1699328, 'steps': 3318, 'loss/train': 3.241624355316162}
-03/03/2022 17:18:59 - INFO - codeparrot_training - Step 3319: {'lr': 0.0004999020177184601, 'samples': 1699840, 'steps': 3319, 'loss/train': 2.1815922260284424}
-03/03/2022 17:19:00 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/03/2022 17:19:05 - INFO - codeparrot_training - Step 3320: {'lr': 0.000499901869101309, 'samples': 1700352, 'steps': 3320, 'loss/train': 2.7197413444519043}
-03/03/2022 17:19:08 - INFO - codeparrot_training - Step 3321: {'lr': 0.0004999017203715559, 'samples': 1700864, 'steps': 3321, 'loss/train': 2.1207735538482666}
-03/03/2022 17:19:08 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/03/2022 17:19:13 - INFO - codeparrot_training - Step 3322: {'lr': 0.000499901571529201, 'samples': 1701376, 'steps': 3322, 'loss/train': 0.3533053398132324}
-03/03/2022 17:19:17 - INFO - codeparrot_training - Step 3323: {'lr': 0.0004999014225742442, 'samples': 1701888, 'steps': 3323, 'loss/train': 1.6861681938171387}
-03/03/2022 17:19:17 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/03/2022 17:19:22 - INFO - codeparrot_training - Step 3324: {'lr': 0.0004999012735066858, 'samples': 1702400, 'steps': 3324, 'loss/train': 2.591144561767578}
-03/03/2022 17:19:25 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/03/2022 17:19:27 - INFO - codeparrot_training - Step 3325: {'lr': 0.0004999011243265257, 'samples': 1702912, 'steps': 3325, 'loss/train': 3.132512331008911}
-03/03/2022 17:19:30 - INFO - codeparrot_training - Step 3326: {'lr': 0.000499900975033764, 'samples': 1703424, 'steps': 3326, 'loss/train': 2.485368013381958}
-03/03/2022 17:19:33 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/03/2022 17:19:35 - INFO - codeparrot_training - Step 3327: {'lr': 0.0004999008256284008, 'samples': 1703936, 'steps': 3327, 'loss/train': 1.8475751876831055}
-03/03/2022 17:19:39 - INFO - codeparrot_training - Step 3328: {'lr': 0.0004999006761104361, 'samples': 1704448, 'steps': 3328, 'loss/train': 1.615195393562317}
-03/03/2022 17:19:41 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/03/2022 17:19:44 - INFO - codeparrot_training - Step 3329: {'lr': 0.0004999005264798701, 'samples': 1704960, 'steps': 3329, 'loss/train': 3.016690969467163}
-03/03/2022 17:19:47 - INFO - codeparrot_training - Step 3330: {'lr': 0.0004999003767367027, 'samples': 1705472, 'steps': 3330, 'loss/train': 2.9630043506622314}
-03/03/2022 17:19:50 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/03/2022 17:19:52 - INFO - codeparrot_training - Step 3331: {'lr': 0.0004999002268809339, 'samples': 1705984, 'steps': 3331, 'loss/train': 1.8617148399353027}
-03/03/2022 17:19:56 - INFO - codeparrot_training - Step 3332: {'lr': 0.0004999000769125642, 'samples': 1706496, 'steps': 3332, 'loss/train': 3.054851531982422}
-03/03/2022 17:19:58 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/03/2022 17:20:01 - INFO - codeparrot_training - Step 3333: {'lr': 0.0004998999268315932, 'samples': 1707008, 'steps': 3333, 'loss/train': 2.727586269378662}
-03/03/2022 17:20:04 - INFO - codeparrot_training - Step 3334: {'lr': 0.0004998997766380212, 'samples': 1707520, 'steps': 3334, 'loss/train': 2.11360239982605}
-03/03/2022 17:20:06 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/03/2022 17:20:09 - INFO - codeparrot_training - Step 3335: {'lr': 0.0004998996263318482, 'samples': 1708032, 'steps': 3335, 'loss/train': 2.2568912506103516}
-03/03/2022 17:20:12 - INFO - codeparrot_training - Step 3336: {'lr': 0.0004998994759130743, 'samples': 1708544, 'steps': 3336, 'loss/train': 2.80450439453125}
-03/03/2022 17:20:15 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/03/2022 17:20:18 - INFO - codeparrot_training - Step 3337: {'lr': 0.0004998993253816996, 'samples': 1709056, 'steps': 3337, 'loss/train': 2.2485573291778564}
-03/03/2022 17:20:21 - INFO - codeparrot_training - Step 3338: {'lr': 0.000499899174737724, 'samples': 1709568, 'steps': 3338, 'loss/train': 2.7095296382904053}
-03/03/2022 17:20:23 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/03/2022 17:20:26 - INFO - codeparrot_training - Step 3339: {'lr': 0.0004998990239811477, 'samples': 1710080, 'steps': 3339, 'loss/train': 0.8227948546409607}
-03/03/2022 17:20:29 - INFO - codeparrot_training - Step 3340: {'lr': 0.0004998988731119709, 'samples': 1710592, 'steps': 3340, 'loss/train': 1.7955102920532227}
-03/03/2022 17:20:31 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/03/2022 17:20:35 - INFO - codeparrot_training - Step 3341: {'lr': 0.0004998987221301935, 'samples': 1711104, 'steps': 3341, 'loss/train': 3.065826892852783}
-03/03/2022 17:20:38 - INFO - codeparrot_training - Step 3342: {'lr': 0.0004998985710358155, 'samples': 1711616, 'steps': 3342, 'loss/train': 2.9800052642822266}
-03/03/2022 17:20:39 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/03/2022 17:20:43 - INFO - codeparrot_training - Step 3343: {'lr': 0.0004998984198288371, 'samples': 1712128, 'steps': 3343, 'loss/train': 2.2378668785095215}
-03/03/2022 17:20:46 - INFO - codeparrot_training - Step 3344: {'lr': 0.0004998982685092583, 'samples': 1712640, 'steps': 3344, 'loss/train': 2.862046241760254}
-03/03/2022 17:20:48 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/03/2022 17:20:51 - INFO - codeparrot_training - Step 3345: {'lr': 0.0004998981170770792, 'samples': 1713152, 'steps': 3345, 'loss/train': 2.491856575012207}
-03/03/2022 17:20:55 - INFO - codeparrot_training - Step 3346: {'lr': 0.0004998979655323, 'samples': 1713664, 'steps': 3346, 'loss/train': 2.3223211765289307}
-03/03/2022 17:20:56 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/03/2022 17:21:00 - INFO - codeparrot_training - Step 3347: {'lr': 0.0004998978138749204, 'samples': 1714176, 'steps': 3347, 'loss/train': 2.613044023513794}
-03/03/2022 17:21:03 - INFO - codeparrot_training - Step 3348: {'lr': 0.0004998976621049408, 'samples': 1714688, 'steps': 3348, 'loss/train': 3.2470545768737793}
-03/03/2022 17:21:04 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/03/2022 17:21:08 - INFO - codeparrot_training - Step 3349: {'lr': 0.0004998975102223612, 'samples': 1715200, 'steps': 3349, 'loss/train': 2.890226364135742}
-03/03/2022 17:21:11 - INFO - codeparrot_training - Step 3350: {'lr': 0.0004998973582271817, 'samples': 1715712, 'steps': 3350, 'loss/train': 1.8736419677734375}
-03/03/2022 17:21:13 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/03/2022 17:21:17 - INFO - codeparrot_training - Step 3351: {'lr': 0.0004998972061194022, 'samples': 1716224, 'steps': 3351, 'loss/train': 2.136707067489624}
-03/03/2022 17:21:20 - INFO - codeparrot_training - Step 3352: {'lr': 0.0004998970538990228, 'samples': 1716736, 'steps': 3352, 'loss/train': 2.641378879547119}
-03/03/2022 17:21:21 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/03/2022 17:21:25 - INFO - codeparrot_training - Step 3353: {'lr': 0.0004998969015660438, 'samples': 1717248, 'steps': 3353, 'loss/train': 2.1359269618988037}
-03/03/2022 17:21:28 - INFO - codeparrot_training - Step 3354: {'lr': 0.0004998967491204651, 'samples': 1717760, 'steps': 3354, 'loss/train': 2.473081111907959}
-03/03/2022 17:21:29 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/03/2022 17:21:33 - INFO - codeparrot_training - Step 3355: {'lr': 0.0004998965965622867, 'samples': 1718272, 'steps': 3355, 'loss/train': 2.6167824268341064}
-03/03/2022 17:21:37 - INFO - codeparrot_training - Step 3356: {'lr': 0.0004998964438915088, 'samples': 1718784, 'steps': 3356, 'loss/train': 2.4331297874450684}
-03/03/2022 17:21:37 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/03/2022 17:21:42 - INFO - codeparrot_training - Step 3357: {'lr': 0.0004998962911081314, 'samples': 1719296, 'steps': 3357, 'loss/train': 2.593017101287842}
-03/03/2022 17:21:45 - INFO - codeparrot_training - Step 3358: {'lr': 0.0004998961382121546, 'samples': 1719808, 'steps': 3358, 'loss/train': 3.2228899002075195}
-03/03/2022 17:21:46 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/03/2022 17:21:50 - INFO - codeparrot_training - Step 3359: {'lr': 0.0004998959852035785, 'samples': 1720320, 'steps': 3359, 'loss/train': 2.2014858722686768}
-03/03/2022 17:21:53 - INFO - codeparrot_training - Step 3360: {'lr': 0.0004998958320824031, 'samples': 1720832, 'steps': 3360, 'loss/train': 2.5461223125457764}
-03/03/2022 17:21:54 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/03/2022 17:21:59 - INFO - codeparrot_training - Step 3361: {'lr': 0.0004998956788486284, 'samples': 1721344, 'steps': 3361, 'loss/train': 2.9290778636932373}
-03/03/2022 17:22:02 - INFO - codeparrot_training - Step 3362: {'lr': 0.0004998955255022547, 'samples': 1721856, 'steps': 3362, 'loss/train': 3.1084821224212646}
-03/03/2022 17:22:02 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/03/2022 17:22:07 - INFO - codeparrot_training - Step 3363: {'lr': 0.0004998953720432818, 'samples': 1722368, 'steps': 3363, 'loss/train': 3.2487435340881348}
-03/03/2022 17:22:10 - INFO - codeparrot_training - Step 3364: {'lr': 0.00049989521847171, 'samples': 1722880, 'steps': 3364, 'loss/train': 2.6276304721832275}
-03/03/2022 17:22:11 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/03/2022 17:22:15 - INFO - codeparrot_training - Step 3365: {'lr': 0.0004998950647875392, 'samples': 1723392, 'steps': 3365, 'loss/train': 3.2136082649230957}
-03/03/2022 17:22:18 - INFO - codeparrot_training - Step 3366: {'lr': 0.0004998949109907697, 'samples': 1723904, 'steps': 3366, 'loss/train': 2.3309714794158936}
-03/03/2022 17:22:19 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/03/2022 17:22:24 - INFO - codeparrot_training - Step 3367: {'lr': 0.0004998947570814012, 'samples': 1724416, 'steps': 3367, 'loss/train': 0.5572906136512756}
-03/03/2022 17:22:27 - INFO - codeparrot_training - Step 3368: {'lr': 0.0004998946030594341, 'samples': 1724928, 'steps': 3368, 'loss/train': 2.8445613384246826}
-03/03/2022 17:22:27 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/03/2022 17:22:32 - INFO - codeparrot_training - Step 3369: {'lr': 0.0004998944489248683, 'samples': 1725440, 'steps': 3369, 'loss/train': 2.5794687271118164}
-03/03/2022 17:22:35 - INFO - codeparrot_training - Step 3370: {'lr': 0.000499894294677704, 'samples': 1725952, 'steps': 3370, 'loss/train': 3.1697585582733154}
-03/03/2022 17:22:35 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/03/2022 17:22:41 - INFO - codeparrot_training - Step 3371: {'lr': 0.000499894140317941, 'samples': 1726464, 'steps': 3371, 'loss/train': 1.9900901317596436}
-03/03/2022 17:22:44 - INFO - codeparrot_training - Step 3372: {'lr': 0.0004998939858455798, 'samples': 1726976, 'steps': 3372, 'loss/train': 2.4157989025115967}
-03/03/2022 17:22:44 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/03/2022 17:22:49 - INFO - codeparrot_training - Step 3373: {'lr': 0.0004998938312606201, 'samples': 1727488, 'steps': 3373, 'loss/train': 2.314059019088745}
-03/03/2022 17:22:52 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/03/2022 17:22:54 - INFO - codeparrot_training - Step 3374: {'lr': 0.000499893676563062, 'samples': 1728000, 'steps': 3374, 'loss/train': 2.3428850173950195}
-03/03/2022 17:22:58 - INFO - codeparrot_training - Step 3375: {'lr': 0.0004998935217529058, 'samples': 1728512, 'steps': 3375, 'loss/train': 2.808596611022949}
-03/03/2022 17:23:00 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/03/2022 17:23:03 - INFO - codeparrot_training - Step 3376: {'lr': 0.0004998933668301514, 'samples': 1729024, 'steps': 3376, 'loss/train': 2.693678379058838}
-03/03/2022 17:23:06 - INFO - codeparrot_training - Step 3377: {'lr': 0.0004998932117947989, 'samples': 1729536, 'steps': 3377, 'loss/train': 3.662250518798828}
-03/03/2022 17:23:09 - INFO - codeparrot_training - Step 3378: {'lr': 0.0004998930566468484, 'samples': 1730048, 'steps': 3378, 'loss/train': 2.135911226272583}
-03/03/2022 17:23:09 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/03/2022 17:23:15 - INFO - codeparrot_training - Step 3379: {'lr': 0.0004998929013863, 'samples': 1730560, 'steps': 3379, 'loss/train': 3.202366352081299}
-03/03/2022 17:23:18 - INFO - codeparrot_training - Step 3380: {'lr': 0.0004998927460131535, 'samples': 1731072, 'steps': 3380, 'loss/train': 2.319014072418213}
-03/03/2022 17:23:18 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/03/2022 17:23:23 - INFO - codeparrot_training - Step 3381: {'lr': 0.0004998925905274094, 'samples': 1731584, 'steps': 3381, 'loss/train': 2.2633581161499023}
-03/03/2022 17:23:26 - INFO - codeparrot_training - Step 3382: {'lr': 0.0004998924349290674, 'samples': 1732096, 'steps': 3382, 'loss/train': 3.1386866569519043}
-03/03/2022 17:23:26 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/03/2022 17:23:31 - INFO - codeparrot_training - Step 3383: {'lr': 0.0004998922792181278, 'samples': 1732608, 'steps': 3383, 'loss/train': 2.434248447418213}
-03/03/2022 17:23:35 - INFO - codeparrot_training - Step 3384: {'lr': 0.0004998921233945907, 'samples': 1733120, 'steps': 3384, 'loss/train': 1.3909858465194702}
-03/03/2022 17:23:35 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/03/2022 17:23:40 - INFO - codeparrot_training - Step 3385: {'lr': 0.0004998919674584559, 'samples': 1733632, 'steps': 3385, 'loss/train': 4.128971576690674}
-03/03/2022 17:23:43 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/03/2022 17:23:45 - INFO - codeparrot_training - Step 3386: {'lr': 0.0004998918114097237, 'samples': 1734144, 'steps': 3386, 'loss/train': 2.916940450668335}
-03/03/2022 17:23:48 - INFO - codeparrot_training - Step 3387: {'lr': 0.0004998916552483941, 'samples': 1734656, 'steps': 3387, 'loss/train': 1.928485631942749}
-03/03/2022 17:23:51 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/03/2022 17:23:54 - INFO - codeparrot_training - Step 3388: {'lr': 0.0004998914989744671, 'samples': 1735168, 'steps': 3388, 'loss/train': 3.1142492294311523}
-03/03/2022 17:23:57 - INFO - codeparrot_training - Step 3389: {'lr': 0.000499891342587943, 'samples': 1735680, 'steps': 3389, 'loss/train': 4.308945655822754}
-03/03/2022 17:24:00 - INFO - codeparrot_training - Step 3390: {'lr': 0.0004998911860888217, 'samples': 1736192, 'steps': 3390, 'loss/train': 2.3879692554473877}
-03/03/2022 17:24:00 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/03/2022 17:24:05 - INFO - codeparrot_training - Step 3391: {'lr': 0.0004998910294771032, 'samples': 1736704, 'steps': 3391, 'loss/train': 2.4640536308288574}
-03/03/2022 17:24:08 - INFO - codeparrot_training - Step 3392: {'lr': 0.0004998908727527877, 'samples': 1737216, 'steps': 3392, 'loss/train': 2.474311590194702}
-03/03/2022 17:24:08 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/03/2022 17:24:14 - INFO - codeparrot_training - Step 3393: {'lr': 0.0004998907159158752, 'samples': 1737728, 'steps': 3393, 'loss/train': 0.6039132475852966}
-03/03/2022 17:24:17 - INFO - codeparrot_training - Step 3394: {'lr': 0.0004998905589663658, 'samples': 1738240, 'steps': 3394, 'loss/train': 2.794804096221924}
-03/03/2022 17:24:17 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/03/2022 17:24:22 - INFO - codeparrot_training - Step 3395: {'lr': 0.0004998904019042596, 'samples': 1738752, 'steps': 3395, 'loss/train': 2.3736462593078613}
-03/03/2022 17:24:25 - INFO - codeparrot_training - Step 3396: {'lr': 0.0004998902447295567, 'samples': 1739264, 'steps': 3396, 'loss/train': 3.3609683513641357}
-03/03/2022 17:24:25 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/03/2022 17:24:30 - INFO - codeparrot_training - Step 3397: {'lr': 0.000499890087442257, 'samples': 1739776, 'steps': 3397, 'loss/train': 1.1259238719940186}
-03/03/2022 17:24:34 - INFO - codeparrot_training - Step 3398: {'lr': 0.0004998899300423607, 'samples': 1740288, 'steps': 3398, 'loss/train': 4.190059661865234}
-03/03/2022 17:24:34 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/03/2022 17:24:39 - INFO - codeparrot_training - Step 3399: {'lr': 0.0004998897725298679, 'samples': 1740800, 'steps': 3399, 'loss/train': 0.8685932755470276}
-03/03/2022 17:24:42 - INFO - codeparrot_training - Step 3400: {'lr': 0.0004998896149047786, 'samples': 1741312, 'steps': 3400, 'loss/train': 2.2184441089630127}
-03/03/2022 17:24:42 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/03/2022 17:24:48 - INFO - codeparrot_training - Step 3401: {'lr': 0.0004998894571670929, 'samples': 1741824, 'steps': 3401, 'loss/train': 2.9940412044525146}
-03/03/2022 17:24:51 - INFO - codeparrot_training - Step 3402: {'lr': 0.0004998892993168109, 'samples': 1742336, 'steps': 3402, 'loss/train': 3.181220531463623}
-03/03/2022 17:24:53 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/03/2022 17:24:56 - INFO - codeparrot_training - Step 3403: {'lr': 0.0004998891413539326, 'samples': 1742848, 'steps': 3403, 'loss/train': 2.095587730407715}
-03/03/2022 17:24:59 - INFO - codeparrot_training - Step 3404: {'lr': 0.0004998889832784581, 'samples': 1743360, 'steps': 3404, 'loss/train': 3.191856622695923}
-03/03/2022 17:25:01 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/03/2022 17:25:05 - INFO - codeparrot_training - Step 3405: {'lr': 0.0004998888250903875, 'samples': 1743872, 'steps': 3405, 'loss/train': 3.3809690475463867}
-03/03/2022 17:25:08 - INFO - codeparrot_training - Step 3406: {'lr': 0.0004998886667897209, 'samples': 1744384, 'steps': 3406, 'loss/train': 2.7711968421936035}
-03/03/2022 17:25:09 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/03/2022 17:25:13 - INFO - codeparrot_training - Step 3407: {'lr': 0.0004998885083764582, 'samples': 1744896, 'steps': 3407, 'loss/train': 3.3071417808532715}
-03/03/2022 17:25:16 - INFO - codeparrot_training - Step 3408: {'lr': 0.0004998883498505996, 'samples': 1745408, 'steps': 3408, 'loss/train': 3.456636428833008}
-03/03/2022 17:25:18 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/03/2022 17:25:21 - INFO - codeparrot_training - Step 3409: {'lr': 0.0004998881912121453, 'samples': 1745920, 'steps': 3409, 'loss/train': 2.7034947872161865}
-03/03/2022 17:25:25 - INFO - codeparrot_training - Step 3410: {'lr': 0.0004998880324610952, 'samples': 1746432, 'steps': 3410, 'loss/train': 2.239018201828003}
-03/03/2022 17:25:26 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/03/2022 17:25:30 - INFO - codeparrot_training - Step 3411: {'lr': 0.0004998878735974493, 'samples': 1746944, 'steps': 3411, 'loss/train': 2.7509021759033203}
-03/03/2022 17:25:33 - INFO - codeparrot_training - Step 3412: {'lr': 0.0004998877146212079, 'samples': 1747456, 'steps': 3412, 'loss/train': 2.139158248901367}
-03/03/2022 17:25:34 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/03/2022 17:25:38 - INFO - codeparrot_training - Step 3413: {'lr': 0.0004998875555323708, 'samples': 1747968, 'steps': 3413, 'loss/train': 2.25270676612854}
-03/03/2022 17:25:41 - INFO - codeparrot_training - Step 3414: {'lr': 0.0004998873963309384, 'samples': 1748480, 'steps': 3414, 'loss/train': 3.3153390884399414}
-03/03/2022 17:25:42 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/03/2022 17:25:47 - INFO - codeparrot_training - Step 3415: {'lr': 0.0004998872370169105, 'samples': 1748992, 'steps': 3415, 'loss/train': 2.900937557220459}
-03/03/2022 17:25:50 - INFO - codeparrot_training - Step 3416: {'lr': 0.0004998870775902872, 'samples': 1749504, 'steps': 3416, 'loss/train': 1.87582528591156}
-03/03/2022 17:25:51 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/03/2022 17:25:55 - INFO - codeparrot_training - Step 3417: {'lr': 0.0004998869180510688, 'samples': 1750016, 'steps': 3417, 'loss/train': 3.2035417556762695}
-03/03/2022 17:25:58 - INFO - codeparrot_training - Step 3418: {'lr': 0.0004998867583992551, 'samples': 1750528, 'steps': 3418, 'loss/train': 2.7804815769195557}
-03/03/2022 17:25:59 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/03/2022 17:26:04 - INFO - codeparrot_training - Step 3419: {'lr': 0.0004998865986348464, 'samples': 1751040, 'steps': 3419, 'loss/train': 2.191013813018799}
-03/03/2022 17:26:07 - INFO - codeparrot_training - Step 3420: {'lr': 0.0004998864387578426, 'samples': 1751552, 'steps': 3420, 'loss/train': 1.1928843259811401}
-03/03/2022 17:26:07 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/03/2022 17:26:12 - INFO - codeparrot_training - Step 3421: {'lr': 0.0004998862787682438, 'samples': 1752064, 'steps': 3421, 'loss/train': 2.590466260910034}
-03/03/2022 17:26:15 - INFO - codeparrot_training - Step 3422: {'lr': 0.00049988611866605, 'samples': 1752576, 'steps': 3422, 'loss/train': 2.749896287918091}
-03/03/2022 17:26:17 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/03/2022 17:26:21 - INFO - codeparrot_training - Step 3423: {'lr': 0.0004998859584512615, 'samples': 1753088, 'steps': 3423, 'loss/train': 3.0882656574249268}
-03/03/2022 17:26:24 - INFO - codeparrot_training - Step 3424: {'lr': 0.0004998857981238782, 'samples': 1753600, 'steps': 3424, 'loss/train': 3.1641132831573486}
-03/03/2022 17:26:29 - INFO - codeparrot_training - Step 3425: {'lr': 0.0004998856376839003, 'samples': 1754112, 'steps': 3425, 'loss/train': 1.9951564073562622}
-03/03/2022 17:26:32 - INFO - codeparrot_training - Step 3426: {'lr': 0.0004998854771313277, 'samples': 1754624, 'steps': 3426, 'loss/train': 2.7978129386901855}
-03/03/2022 17:26:34 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/03/2022 17:26:38 - INFO - codeparrot_training - Step 3427: {'lr': 0.0004998853164661606, 'samples': 1755136, 'steps': 3427, 'loss/train': 2.788806438446045}
-03/03/2022 17:26:41 - INFO - codeparrot_training - Step 3428: {'lr': 0.000499885155688399, 'samples': 1755648, 'steps': 3428, 'loss/train': 2.3447115421295166}
-03/03/2022 17:26:42 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/03/2022 17:26:46 - INFO - codeparrot_training - Step 3429: {'lr': 0.000499884994798043, 'samples': 1756160, 'steps': 3429, 'loss/train': 3.077827215194702}
-03/03/2022 17:26:49 - INFO - codeparrot_training - Step 3430: {'lr': 0.0004998848337950927, 'samples': 1756672, 'steps': 3430, 'loss/train': 2.3189892768859863}
-03/03/2022 17:26:51 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/03/2022 17:26:54 - INFO - codeparrot_training - Step 3431: {'lr': 0.0004998846726795482, 'samples': 1757184, 'steps': 3431, 'loss/train': 2.3812575340270996}
-03/03/2022 17:26:58 - INFO - codeparrot_training - Step 3432: {'lr': 0.0004998845114514095, 'samples': 1757696, 'steps': 3432, 'loss/train': 1.064099669456482}
-03/03/2022 17:26:59 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/03/2022 17:27:03 - INFO - codeparrot_training - Step 3433: {'lr': 0.0004998843501106766, 'samples': 1758208, 'steps': 3433, 'loss/train': 3.1903083324432373}
-03/03/2022 17:27:06 - INFO - codeparrot_training - Step 3434: {'lr': 0.0004998841886573496, 'samples': 1758720, 'steps': 3434, 'loss/train': 2.3210856914520264}
-03/03/2022 17:27:08 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/03/2022 17:27:11 - INFO - codeparrot_training - Step 3435: {'lr': 0.0004998840270914288, 'samples': 1759232, 'steps': 3435, 'loss/train': 2.2028391361236572}
-03/03/2022 17:27:15 - INFO - codeparrot_training - Step 3436: {'lr': 0.0004998838654129142, 'samples': 1759744, 'steps': 3436, 'loss/train': 2.7622439861297607}
-03/03/2022 17:27:17 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/03/2022 17:27:20 - INFO - codeparrot_training - Step 3437: {'lr': 0.0004998837036218056, 'samples': 1760256, 'steps': 3437, 'loss/train': 2.1658856868743896}
-03/03/2022 17:27:23 - INFO - codeparrot_training - Step 3438: {'lr': 0.0004998835417181033, 'samples': 1760768, 'steps': 3438, 'loss/train': 2.2480814456939697}
-03/03/2022 17:27:25 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/03/2022 17:27:28 - INFO - codeparrot_training - Step 3439: {'lr': 0.0004998833797018074, 'samples': 1761280, 'steps': 3439, 'loss/train': 2.6411871910095215}
-03/03/2022 17:27:31 - INFO - codeparrot_training - Step 3440: {'lr': 0.0004998832175729179, 'samples': 1761792, 'steps': 3440, 'loss/train': 1.5373883247375488}
-03/03/2022 17:27:33 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/03/2022 17:27:37 - INFO - codeparrot_training - Step 3441: {'lr': 0.0004998830553314349, 'samples': 1762304, 'steps': 3441, 'loss/train': 2.9242169857025146}
-03/03/2022 17:27:40 - INFO - codeparrot_training - Step 3442: {'lr': 0.0004998828929773583, 'samples': 1762816, 'steps': 3442, 'loss/train': 2.364250659942627}
-03/03/2022 17:27:41 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/03/2022 17:27:45 - INFO - codeparrot_training - Step 3443: {'lr': 0.0004998827305106884, 'samples': 1763328, 'steps': 3443, 'loss/train': 2.7832021713256836}
-03/03/2022 17:27:48 - INFO - codeparrot_training - Step 3444: {'lr': 0.0004998825679314253, 'samples': 1763840, 'steps': 3444, 'loss/train': 2.560842514038086}
-03/03/2022 17:27:50 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/03/2022 17:27:53 - INFO - codeparrot_training - Step 3445: {'lr': 0.0004998824052395689, 'samples': 1764352, 'steps': 3445, 'loss/train': 2.861851930618286}
-03/03/2022 17:27:57 - INFO - codeparrot_training - Step 3446: {'lr': 0.0004998822424351193, 'samples': 1764864, 'steps': 3446, 'loss/train': 2.9265940189361572}
-03/03/2022 17:27:58 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/03/2022 17:28:02 - INFO - codeparrot_training - Step 3447: {'lr': 0.0004998820795180766, 'samples': 1765376, 'steps': 3447, 'loss/train': 1.185547113418579}
-03/03/2022 17:28:05 - INFO - codeparrot_training - Step 3448: {'lr': 0.000499881916488441, 'samples': 1765888, 'steps': 3448, 'loss/train': 2.6167521476745605}
-03/03/2022 17:28:06 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/03/2022 17:28:10 - INFO - codeparrot_training - Step 3449: {'lr': 0.0004998817533462123, 'samples': 1766400, 'steps': 3449, 'loss/train': 2.8428573608398438}
-03/03/2022 17:28:13 - INFO - codeparrot_training - Step 3450: {'lr': 0.0004998815900913909, 'samples': 1766912, 'steps': 3450, 'loss/train': 2.921534538269043}
-03/03/2022 17:28:15 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/03/2022 17:28:19 - INFO - codeparrot_training - Step 3451: {'lr': 0.0004998814267239767, 'samples': 1767424, 'steps': 3451, 'loss/train': 2.1076900959014893}
-03/03/2022 17:28:22 - INFO - codeparrot_training - Step 3452: {'lr': 0.0004998812632439697, 'samples': 1767936, 'steps': 3452, 'loss/train': 2.8642594814300537}
-03/03/2022 17:28:23 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/03/2022 17:28:27 - INFO - codeparrot_training - Step 3453: {'lr': 0.00049988109965137, 'samples': 1768448, 'steps': 3453, 'loss/train': 2.299715280532837}
-03/03/2022 17:28:30 - INFO - codeparrot_training - Step 3454: {'lr': 0.000499880935946178, 'samples': 1768960, 'steps': 3454, 'loss/train': 2.4853639602661133}
-03/03/2022 17:28:31 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/03/2022 17:28:36 - INFO - codeparrot_training - Step 3455: {'lr': 0.0004998807721283932, 'samples': 1769472, 'steps': 3455, 'loss/train': 0.5581620335578918}
-03/03/2022 17:28:39 - INFO - codeparrot_training - Step 3456: {'lr': 0.0004998806081980162, 'samples': 1769984, 'steps': 3456, 'loss/train': 2.44799542427063}
-03/03/2022 17:28:40 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/03/2022 17:28:44 - INFO - codeparrot_training - Step 3457: {'lr': 0.0004998804441550467, 'samples': 1770496, 'steps': 3457, 'loss/train': 2.511789083480835}
-03/03/2022 17:28:47 - INFO - codeparrot_training - Step 3458: {'lr': 0.000499880279999485, 'samples': 1771008, 'steps': 3458, 'loss/train': 2.9691922664642334}
-03/03/2022 17:28:48 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/03/2022 17:28:53 - INFO - codeparrot_training - Step 3459: {'lr': 0.0004998801157313311, 'samples': 1771520, 'steps': 3459, 'loss/train': 2.8180603981018066}
-03/03/2022 17:28:56 - INFO - codeparrot_training - Step 3460: {'lr': 0.0004998799513505851, 'samples': 1772032, 'steps': 3460, 'loss/train': 2.8695521354675293}
-03/03/2022 17:28:57 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/03/2022 17:29:01 - INFO - codeparrot_training - Step 3461: {'lr': 0.000499879786857247, 'samples': 1772544, 'steps': 3461, 'loss/train': 0.26493769884109497}
-03/03/2022 17:29:04 - INFO - codeparrot_training - Step 3462: {'lr': 0.0004998796222513169, 'samples': 1773056, 'steps': 3462, 'loss/train': 2.8650240898132324}
-03/03/2022 17:29:05 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/03/2022 17:29:09 - INFO - codeparrot_training - Step 3463: {'lr': 0.000499879457532795, 'samples': 1773568, 'steps': 3463, 'loss/train': 3.003499984741211}
-03/03/2022 17:29:13 - INFO - codeparrot_training - Step 3464: {'lr': 0.0004998792927016812, 'samples': 1774080, 'steps': 3464, 'loss/train': 2.320399045944214}
-03/03/2022 17:29:13 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/03/2022 17:29:18 - INFO - codeparrot_training - Step 3465: {'lr': 0.0004998791277579757, 'samples': 1774592, 'steps': 3465, 'loss/train': 3.08478045463562}
-03/03/2022 17:29:21 - INFO - codeparrot_training - Step 3466: {'lr': 0.0004998789627016784, 'samples': 1775104, 'steps': 3466, 'loss/train': 1.549597144126892}
-03/03/2022 17:29:22 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/03/2022 17:29:26 - INFO - codeparrot_training - Step 3467: {'lr': 0.0004998787975327896, 'samples': 1775616, 'steps': 3467, 'loss/train': 0.4559893012046814}
-03/03/2022 17:29:30 - INFO - codeparrot_training - Step 3468: {'lr': 0.0004998786322513093, 'samples': 1776128, 'steps': 3468, 'loss/train': 3.2301816940307617}
-03/03/2022 17:29:30 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/03/2022 17:29:35 - INFO - codeparrot_training - Step 3469: {'lr': 0.0004998784668572375, 'samples': 1776640, 'steps': 3469, 'loss/train': 2.6614420413970947}
-03/03/2022 17:29:38 - INFO - codeparrot_training - Step 3470: {'lr': 0.0004998783013505743, 'samples': 1777152, 'steps': 3470, 'loss/train': 2.472599983215332}
-03/03/2022 17:29:38 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/03/2022 17:29:43 - INFO - codeparrot_training - Step 3471: {'lr': 0.0004998781357313198, 'samples': 1777664, 'steps': 3471, 'loss/train': 2.3214733600616455}
-03/03/2022 17:29:46 - INFO - codeparrot_training - Step 3472: {'lr': 0.0004998779699994741, 'samples': 1778176, 'steps': 3472, 'loss/train': 3.0650954246520996}
-03/03/2022 17:29:47 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/03/2022 17:29:52 - INFO - codeparrot_training - Step 3473: {'lr': 0.0004998778041550372, 'samples': 1778688, 'steps': 3473, 'loss/train': 2.4158334732055664}
-03/03/2022 17:29:55 - INFO - codeparrot_training - Step 3474: {'lr': 0.0004998776381980092, 'samples': 1779200, 'steps': 3474, 'loss/train': 1.8305494785308838}
-03/03/2022 17:29:55 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/03/2022 17:30:00 - INFO - codeparrot_training - Step 3475: {'lr': 0.0004998774721283903, 'samples': 1779712, 'steps': 3475, 'loss/train': 1.4764806032180786}
-03/03/2022 17:30:03 - INFO - codeparrot_training - Step 3476: {'lr': 0.0004998773059461803, 'samples': 1780224, 'steps': 3476, 'loss/train': 2.9446611404418945}
-03/03/2022 17:30:05 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/03/2022 17:30:09 - INFO - codeparrot_training - Step 3477: {'lr': 0.0004998771396513796, 'samples': 1780736, 'steps': 3477, 'loss/train': 1.8397433757781982}
-03/03/2022 17:30:12 - INFO - codeparrot_training - Step 3478: {'lr': 0.000499876973243988, 'samples': 1781248, 'steps': 3478, 'loss/train': 1.8445950746536255}
-03/03/2022 17:30:13 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/03/2022 17:30:17 - INFO - codeparrot_training - Step 3479: {'lr': 0.0004998768067240059, 'samples': 1781760, 'steps': 3479, 'loss/train': 3.2472801208496094}
-03/03/2022 17:30:20 - INFO - codeparrot_training - Step 3480: {'lr': 0.0004998766400914329, 'samples': 1782272, 'steps': 3480, 'loss/train': 2.1465084552764893}
-03/03/2022 17:30:21 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/03/2022 17:30:26 - INFO - codeparrot_training - Step 3481: {'lr': 0.0004998764733462694, 'samples': 1782784, 'steps': 3481, 'loss/train': 2.122545003890991}
-03/03/2022 17:30:29 - INFO - codeparrot_training - Step 3482: {'lr': 0.0004998763064885155, 'samples': 1783296, 'steps': 3482, 'loss/train': 2.131110906600952}
-03/03/2022 17:30:30 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/03/2022 17:30:34 - INFO - codeparrot_training - Step 3483: {'lr': 0.0004998761395181712, 'samples': 1783808, 'steps': 3483, 'loss/train': 3.1917903423309326}
-03/03/2022 17:30:37 - INFO - codeparrot_training - Step 3484: {'lr': 0.0004998759724352365, 'samples': 1784320, 'steps': 3484, 'loss/train': 2.5262393951416016}
-03/03/2022 17:30:39 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/03/2022 17:30:42 - INFO - codeparrot_training - Step 3485: {'lr': 0.0004998758052397115, 'samples': 1784832, 'steps': 3485, 'loss/train': 3.0092735290527344}
-03/03/2022 17:30:46 - INFO - codeparrot_training - Step 3486: {'lr': 0.0004998756379315964, 'samples': 1785344, 'steps': 3486, 'loss/train': 1.8495444059371948}
-03/03/2022 17:30:47 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/03/2022 17:30:51 - INFO - codeparrot_training - Step 3487: {'lr': 0.0004998754705108912, 'samples': 1785856, 'steps': 3487, 'loss/train': 1.8278295993804932}
-03/03/2022 17:30:54 - INFO - codeparrot_training - Step 3488: {'lr': 0.000499875302977596, 'samples': 1786368, 'steps': 3488, 'loss/train': 1.983155369758606}
-03/03/2022 17:30:55 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/03/2022 17:30:59 - INFO - codeparrot_training - Step 3489: {'lr': 0.0004998751353317108, 'samples': 1786880, 'steps': 3489, 'loss/train': 3.1049907207489014}
-03/03/2022 17:31:02 - INFO - codeparrot_training - Step 3490: {'lr': 0.0004998749675732357, 'samples': 1787392, 'steps': 3490, 'loss/train': 3.100144863128662}
-03/03/2022 17:31:04 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/03/2022 17:31:08 - INFO - codeparrot_training - Step 3491: {'lr': 0.0004998747997021708, 'samples': 1787904, 'steps': 3491, 'loss/train': 2.7815253734588623}
-03/03/2022 17:31:11 - INFO - codeparrot_training - Step 3492: {'lr': 0.0004998746317185162, 'samples': 1788416, 'steps': 3492, 'loss/train': 1.3102047443389893}
-03/03/2022 17:31:12 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/03/2022 17:31:16 - INFO - codeparrot_training - Step 3493: {'lr': 0.000499874463622272, 'samples': 1788928, 'steps': 3493, 'loss/train': 2.865513324737549}
-03/03/2022 17:31:19 - INFO - codeparrot_training - Step 3494: {'lr': 0.000499874295413438, 'samples': 1789440, 'steps': 3494, 'loss/train': 3.174488067626953}
-03/03/2022 17:31:20 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/03/2022 17:31:25 - INFO - codeparrot_training - Step 3495: {'lr': 0.0004998741270920147, 'samples': 1789952, 'steps': 3495, 'loss/train': 1.6792330741882324}
-03/03/2022 17:31:28 - INFO - codeparrot_training - Step 3496: {'lr': 0.0004998739586580019, 'samples': 1790464, 'steps': 3496, 'loss/train': 2.017700672149658}
-03/03/2022 17:31:29 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/03/2022 17:31:33 - INFO - codeparrot_training - Step 3497: {'lr': 0.0004998737901113999, 'samples': 1790976, 'steps': 3497, 'loss/train': 2.2834866046905518}
-03/03/2022 17:31:36 - INFO - codeparrot_training - Step 3498: {'lr': 0.0004998736214522084, 'samples': 1791488, 'steps': 3498, 'loss/train': 2.2111284732818604}
-03/03/2022 17:31:37 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/03/2022 17:31:41 - INFO - codeparrot_training - Step 3499: {'lr': 0.0004998734526804278, 'samples': 1792000, 'steps': 3499, 'loss/train': 3.3585121631622314}
-03/03/2022 17:31:45 - INFO - codeparrot_training - Step 3500: {'lr': 0.0004998732837960581, 'samples': 1792512, 'steps': 3500, 'loss/train': 3.1115927696228027}
-03/03/2022 17:31:46 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/03/2022 17:31:50 - INFO - codeparrot_training - Step 3501: {'lr': 0.0004998731147990993, 'samples': 1793024, 'steps': 3501, 'loss/train': 2.718416452407837}
-03/03/2022 17:31:53 - INFO - codeparrot_training - Step 3502: {'lr': 0.0004998729456895516, 'samples': 1793536, 'steps': 3502, 'loss/train': 2.7886691093444824}
-03/03/2022 17:31:54 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/03/2022 17:31:58 - INFO - codeparrot_training - Step 3503: {'lr': 0.0004998727764674149, 'samples': 1794048, 'steps': 3503, 'loss/train': 3.472165584564209}
-03/03/2022 17:32:01 - INFO - codeparrot_training - Step 3504: {'lr': 0.0004998726071326896, 'samples': 1794560, 'steps': 3504, 'loss/train': 1.2720261812210083}
-03/03/2022 17:32:03 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/03/2022 17:32:07 - INFO - codeparrot_training - Step 3505: {'lr': 0.0004998724376853754, 'samples': 1795072, 'steps': 3505, 'loss/train': 2.7412705421447754}
-03/03/2022 17:32:10 - INFO - codeparrot_training - Step 3506: {'lr': 0.0004998722681254725, 'samples': 1795584, 'steps': 3506, 'loss/train': 2.27960205078125}
-03/03/2022 17:32:11 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/03/2022 17:32:15 - INFO - codeparrot_training - Step 3507: {'lr': 0.0004998720984529811, 'samples': 1796096, 'steps': 3507, 'loss/train': 3.05230450630188}
-03/03/2022 17:32:18 - INFO - codeparrot_training - Step 3508: {'lr': 0.0004998719286679011, 'samples': 1796608, 'steps': 3508, 'loss/train': 2.459235429763794}
-03/03/2022 17:32:19 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/03/2022 17:32:24 - INFO - codeparrot_training - Step 3509: {'lr': 0.0004998717587702328, 'samples': 1797120, 'steps': 3509, 'loss/train': 2.190256118774414}
-03/03/2022 17:32:27 - INFO - codeparrot_training - Step 3510: {'lr': 0.0004998715887599759, 'samples': 1797632, 'steps': 3510, 'loss/train': 2.57688307762146}
-03/03/2022 17:32:28 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/03/2022 17:32:32 - INFO - codeparrot_training - Step 3511: {'lr': 0.000499871418637131, 'samples': 1798144, 'steps': 3511, 'loss/train': 1.5449107885360718}
-03/03/2022 17:32:35 - INFO - codeparrot_training - Step 3512: {'lr': 0.0004998712484016977, 'samples': 1798656, 'steps': 3512, 'loss/train': 2.0804619789123535}
-03/03/2022 17:32:36 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/03/2022 17:32:40 - INFO - codeparrot_training - Step 3513: {'lr': 0.0004998710780536763, 'samples': 1799168, 'steps': 3513, 'loss/train': 1.6403422355651855}
-03/03/2022 17:32:44 - INFO - codeparrot_training - Step 3514: {'lr': 0.0004998709075930669, 'samples': 1799680, 'steps': 3514, 'loss/train': 2.2240114212036133}
-03/03/2022 17:32:44 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/03/2022 17:32:49 - INFO - codeparrot_training - Step 3515: {'lr': 0.0004998707370198695, 'samples': 1800192, 'steps': 3515, 'loss/train': 2.609682559967041}
-03/03/2022 17:32:52 - INFO - codeparrot_training - Step 3516: {'lr': 0.0004998705663340843, 'samples': 1800704, 'steps': 3516, 'loss/train': 2.486140012741089}
-03/03/2022 17:32:54 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/03/2022 17:32:58 - INFO - codeparrot_training - Step 3517: {'lr': 0.0004998703955357111, 'samples': 1801216, 'steps': 3517, 'loss/train': 2.108114242553711}
-03/03/2022 17:33:01 - INFO - codeparrot_training - Step 3518: {'lr': 0.0004998702246247502, 'samples': 1801728, 'steps': 3518, 'loss/train': 2.6833527088165283}
-03/03/2022 17:33:02 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/03/2022 17:33:06 - INFO - codeparrot_training - Step 3519: {'lr': 0.0004998700536012017, 'samples': 1802240, 'steps': 3519, 'loss/train': 2.221470355987549}
-03/03/2022 17:33:09 - INFO - codeparrot_training - Step 3520: {'lr': 0.0004998698824650655, 'samples': 1802752, 'steps': 3520, 'loss/train': 2.5528666973114014}
-03/03/2022 17:33:11 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/03/2022 17:33:14 - INFO - codeparrot_training - Step 3521: {'lr': 0.000499869711216342, 'samples': 1803264, 'steps': 3521, 'loss/train': 2.0246126651763916}
-03/03/2022 17:33:18 - INFO - codeparrot_training - Step 3522: {'lr': 0.0004998695398550309, 'samples': 1803776, 'steps': 3522, 'loss/train': 1.979175090789795}
-03/03/2022 17:33:19 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/03/2022 17:33:23 - INFO - codeparrot_training - Step 3523: {'lr': 0.0004998693683811325, 'samples': 1804288, 'steps': 3523, 'loss/train': 2.033844232559204}
-03/03/2022 17:33:26 - INFO - codeparrot_training - Step 3524: {'lr': 0.0004998691967946468, 'samples': 1804800, 'steps': 3524, 'loss/train': 2.557607412338257}
-03/03/2022 17:33:27 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/03/2022 17:33:31 - INFO - codeparrot_training - Step 3525: {'lr': 0.000499869025095574, 'samples': 1805312, 'steps': 3525, 'loss/train': 3.400775194168091}
-03/03/2022 17:33:35 - INFO - codeparrot_training - Step 3526: {'lr': 0.0004998688532839139, 'samples': 1805824, 'steps': 3526, 'loss/train': 2.724454879760742}
-03/03/2022 17:33:36 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/03/2022 17:33:40 - INFO - codeparrot_training - Step 3527: {'lr': 0.0004998686813596668, 'samples': 1806336, 'steps': 3527, 'loss/train': 2.373878240585327}
-03/03/2022 17:33:43 - INFO - codeparrot_training - Step 3528: {'lr': 0.0004998685093228327, 'samples': 1806848, 'steps': 3528, 'loss/train': 2.1089589595794678}
-03/03/2022 17:33:44 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/03/2022 17:33:48 - INFO - codeparrot_training - Step 3529: {'lr': 0.0004998683371734118, 'samples': 1807360, 'steps': 3529, 'loss/train': 2.7946763038635254}
-03/03/2022 17:33:51 - INFO - codeparrot_training - Step 3530: {'lr': 0.000499868164911404, 'samples': 1807872, 'steps': 3530, 'loss/train': 2.7737417221069336}
-03/03/2022 17:33:52 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/03/2022 17:33:57 - INFO - codeparrot_training - Step 3531: {'lr': 0.0004998679925368094, 'samples': 1808384, 'steps': 3531, 'loss/train': 2.004412889480591}
-03/03/2022 17:34:00 - INFO - codeparrot_training - Step 3532: {'lr': 0.0004998678200496283, 'samples': 1808896, 'steps': 3532, 'loss/train': 2.3877594470977783}
-03/03/2022 17:34:01 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/03/2022 17:34:05 - INFO - codeparrot_training - Step 3533: {'lr': 0.0004998676474498606, 'samples': 1809408, 'steps': 3533, 'loss/train': 1.9091302156448364}
-03/03/2022 17:34:08 - INFO - codeparrot_training - Step 3534: {'lr': 0.0004998674747375063, 'samples': 1809920, 'steps': 3534, 'loss/train': 2.0079824924468994}
-03/03/2022 17:34:09 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/03/2022 17:34:14 - INFO - codeparrot_training - Step 3535: {'lr': 0.0004998673019125657, 'samples': 1810432, 'steps': 3535, 'loss/train': 0.7680908441543579}
-03/03/2022 17:34:17 - INFO - codeparrot_training - Step 3536: {'lr': 0.0004998671289750386, 'samples': 1810944, 'steps': 3536, 'loss/train': 2.1504931449890137}
-03/03/2022 17:34:18 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/03/2022 17:34:22 - INFO - codeparrot_training - Step 3537: {'lr': 0.0004998669559249252, 'samples': 1811456, 'steps': 3537, 'loss/train': 1.0805754661560059}
-03/03/2022 17:34:25 - INFO - codeparrot_training - Step 3538: {'lr': 0.0004998667827622258, 'samples': 1811968, 'steps': 3538, 'loss/train': 3.1109695434570312}
-03/03/2022 17:34:26 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/03/2022 17:34:30 - INFO - codeparrot_training - Step 3539: {'lr': 0.0004998666094869402, 'samples': 1812480, 'steps': 3539, 'loss/train': 1.6236883401870728}
-03/03/2022 17:34:34 - INFO - codeparrot_training - Step 3540: {'lr': 0.0004998664360990685, 'samples': 1812992, 'steps': 3540, 'loss/train': 2.8824963569641113}
-03/03/2022 17:34:35 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/03/2022 17:34:39 - INFO - codeparrot_training - Step 3541: {'lr': 0.0004998662625986109, 'samples': 1813504, 'steps': 3541, 'loss/train': 1.8157204389572144}
-03/03/2022 17:34:42 - INFO - codeparrot_training - Step 3542: {'lr': 0.0004998660889855674, 'samples': 1814016, 'steps': 3542, 'loss/train': 2.892594337463379}
-03/03/2022 17:34:43 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/03/2022 17:34:47 - INFO - codeparrot_training - Step 3543: {'lr': 0.0004998659152599381, 'samples': 1814528, 'steps': 3543, 'loss/train': 2.030524253845215}
-03/03/2022 17:34:51 - INFO - codeparrot_training - Step 3544: {'lr': 0.000499865741421723, 'samples': 1815040, 'steps': 3544, 'loss/train': 3.1669063568115234}
-03/03/2022 17:34:51 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/03/2022 17:34:56 - INFO - codeparrot_training - Step 3545: {'lr': 0.0004998655674709224, 'samples': 1815552, 'steps': 3545, 'loss/train': 2.5481038093566895}
-03/03/2022 17:34:59 - INFO - codeparrot_training - Step 3546: {'lr': 0.0004998653934075361, 'samples': 1816064, 'steps': 3546, 'loss/train': 2.2129180431365967}
-03/03/2022 17:35:00 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/03/2022 17:35:04 - INFO - codeparrot_training - Step 3547: {'lr': 0.0004998652192315644, 'samples': 1816576, 'steps': 3547, 'loss/train': 2.811291456222534}
-03/03/2022 17:35:07 - INFO - codeparrot_training - Step 3548: {'lr': 0.0004998650449430073, 'samples': 1817088, 'steps': 3548, 'loss/train': 2.5717151165008545}
-03/03/2022 17:35:08 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/03/2022 17:35:13 - INFO - codeparrot_training - Step 3549: {'lr': 0.0004998648705418648, 'samples': 1817600, 'steps': 3549, 'loss/train': 3.0319743156433105}
-03/03/2022 17:35:16 - INFO - codeparrot_training - Step 3550: {'lr': 0.000499864696028137, 'samples': 1818112, 'steps': 3550, 'loss/train': 2.6602559089660645}
-03/03/2022 17:35:16 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/03/2022 17:35:21 - INFO - codeparrot_training - Step 3551: {'lr': 0.000499864521401824, 'samples': 1818624, 'steps': 3551, 'loss/train': 1.9295809268951416}
-03/03/2022 17:35:24 - INFO - codeparrot_training - Step 3552: {'lr': 0.000499864346662926, 'samples': 1819136, 'steps': 3552, 'loss/train': 3.327582359313965}
-03/03/2022 17:35:25 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/03/2022 17:35:30 - INFO - codeparrot_training - Step 3553: {'lr': 0.000499864171811443, 'samples': 1819648, 'steps': 3553, 'loss/train': 2.9110333919525146}
-03/03/2022 17:35:33 - INFO - codeparrot_training - Step 3554: {'lr': 0.0004998639968473751, 'samples': 1820160, 'steps': 3554, 'loss/train': 2.0936439037323}
-03/03/2022 17:35:34 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/03/2022 17:35:38 - INFO - codeparrot_training - Step 3555: {'lr': 0.0004998638217707222, 'samples': 1820672, 'steps': 3555, 'loss/train': 0.25007060170173645}
-03/03/2022 17:35:41 - INFO - codeparrot_training - Step 3556: {'lr': 0.0004998636465814846, 'samples': 1821184, 'steps': 3556, 'loss/train': 2.5801384449005127}
-03/03/2022 17:35:42 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/03/2022 17:35:47 - INFO - codeparrot_training - Step 3557: {'lr': 0.0004998634712796622, 'samples': 1821696, 'steps': 3557, 'loss/train': 2.2404232025146484}
-03/03/2022 17:35:50 - INFO - codeparrot_training - Step 3558: {'lr': 0.0004998632958652554, 'samples': 1822208, 'steps': 3558, 'loss/train': 3.1668248176574707}
-03/03/2022 17:35:50 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/03/2022 17:35:55 - INFO - codeparrot_training - Step 3559: {'lr': 0.0004998631203382639, 'samples': 1822720, 'steps': 3559, 'loss/train': 1.8602008819580078}
-03/03/2022 17:35:58 - INFO - codeparrot_training - Step 3560: {'lr': 0.0004998629446986879, 'samples': 1823232, 'steps': 3560, 'loss/train': 3.4576563835144043}
-03/03/2022 17:35:58 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/03/2022 17:36:03 - INFO - codeparrot_training - Step 3561: {'lr': 0.0004998627689465276, 'samples': 1823744, 'steps': 3561, 'loss/train': 2.7182540893554688}
-03/03/2022 17:36:07 - INFO - codeparrot_training - Step 3562: {'lr': 0.0004998625930817829, 'samples': 1824256, 'steps': 3562, 'loss/train': 2.6915667057037354}
-03/03/2022 17:36:07 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/03/2022 17:36:12 - INFO - codeparrot_training - Step 3563: {'lr': 0.0004998624171044541, 'samples': 1824768, 'steps': 3563, 'loss/train': 2.676105260848999}
-03/03/2022 17:36:15 - INFO - codeparrot_training - Step 3564: {'lr': 0.000499862241014541, 'samples': 1825280, 'steps': 3564, 'loss/train': 2.7108681201934814}
-03/03/2022 17:36:15 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/03/2022 17:36:20 - INFO - codeparrot_training - Step 3565: {'lr': 0.0004998620648120439, 'samples': 1825792, 'steps': 3565, 'loss/train': 2.5601260662078857}
-03/03/2022 17:36:24 - INFO - codeparrot_training - Step 3566: {'lr': 0.0004998618884969628, 'samples': 1826304, 'steps': 3566, 'loss/train': 2.4409899711608887}
-03/03/2022 17:36:24 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/03/2022 17:36:29 - INFO - codeparrot_training - Step 3567: {'lr': 0.0004998617120692977, 'samples': 1826816, 'steps': 3567, 'loss/train': 2.8623995780944824}
-03/03/2022 17:36:32 - INFO - codeparrot_training - Step 3568: {'lr': 0.0004998615355290489, 'samples': 1827328, 'steps': 3568, 'loss/train': 3.122307777404785}
-03/03/2022 17:36:32 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/03/2022 17:36:37 - INFO - codeparrot_training - Step 3569: {'lr': 0.0004998613588762163, 'samples': 1827840, 'steps': 3569, 'loss/train': 4.345600128173828}
-03/03/2022 17:36:40 - INFO - codeparrot_training - Step 3570: {'lr': 0.0004998611821108001, 'samples': 1828352, 'steps': 3570, 'loss/train': 3.649526357650757}
-03/03/2022 17:36:41 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/03/2022 17:36:46 - INFO - codeparrot_training - Step 3571: {'lr': 0.0004998610052328002, 'samples': 1828864, 'steps': 3571, 'loss/train': 2.1949987411499023}
-03/03/2022 17:36:49 - INFO - codeparrot_training - Step 3572: {'lr': 0.0004998608282422169, 'samples': 1829376, 'steps': 3572, 'loss/train': 2.33331561088562}
-03/03/2022 17:36:49 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/03/2022 17:36:54 - INFO - codeparrot_training - Step 3573: {'lr': 0.0004998606511390501, 'samples': 1829888, 'steps': 3573, 'loss/train': 2.4240610599517822}
-03/03/2022 17:36:57 - INFO - codeparrot_training - Step 3574: {'lr': 0.0004998604739232999, 'samples': 1830400, 'steps': 3574, 'loss/train': 2.1821587085723877}
-03/03/2022 17:36:57 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/03/2022 17:37:03 - INFO - codeparrot_training - Step 3575: {'lr': 0.0004998602965949664, 'samples': 1830912, 'steps': 3575, 'loss/train': 2.5694711208343506}
-03/03/2022 17:37:06 - INFO - codeparrot_training - Step 3576: {'lr': 0.0004998601191540499, 'samples': 1831424, 'steps': 3576, 'loss/train': 2.2584760189056396}
-03/03/2022 17:37:07 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/03/2022 17:37:11 - INFO - codeparrot_training - Step 3577: {'lr': 0.0004998599416005502, 'samples': 1831936, 'steps': 3577, 'loss/train': 2.4998300075531006}
-03/03/2022 17:37:15 - INFO - codeparrot_training - Step 3578: {'lr': 0.0004998597639344674, 'samples': 1832448, 'steps': 3578, 'loss/train': 4.368144512176514}
-03/03/2022 17:37:16 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/03/2022 17:37:20 - INFO - codeparrot_training - Step 3579: {'lr': 0.0004998595861558016, 'samples': 1832960, 'steps': 3579, 'loss/train': 2.849193572998047}
-03/03/2022 17:37:23 - INFO - codeparrot_training - Step 3580: {'lr': 0.000499859408264553, 'samples': 1833472, 'steps': 3580, 'loss/train': 2.3457655906677246}
-03/03/2022 17:37:24 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/03/2022 17:37:28 - INFO - codeparrot_training - Step 3581: {'lr': 0.0004998592302607217, 'samples': 1833984, 'steps': 3581, 'loss/train': 2.8259127140045166}
-03/03/2022 17:37:31 - INFO - codeparrot_training - Step 3582: {'lr': 0.0004998590521443075, 'samples': 1834496, 'steps': 3582, 'loss/train': 3.155935525894165}
-03/03/2022 17:37:33 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/03/2022 17:37:37 - INFO - codeparrot_training - Step 3583: {'lr': 0.0004998588739153108, 'samples': 1835008, 'steps': 3583, 'loss/train': 2.9264156818389893}
-03/03/2022 17:37:40 - INFO - codeparrot_training - Step 3584: {'lr': 0.0004998586955737316, 'samples': 1835520, 'steps': 3584, 'loss/train': 2.0631113052368164}
-03/03/2022 17:37:41 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/03/2022 17:37:45 - INFO - codeparrot_training - Step 3585: {'lr': 0.0004998585171195698, 'samples': 1836032, 'steps': 3585, 'loss/train': 2.686034917831421}
-03/03/2022 17:37:48 - INFO - codeparrot_training - Step 3586: {'lr': 0.0004998583385528256, 'samples': 1836544, 'steps': 3586, 'loss/train': 2.0968966484069824}
-03/03/2022 17:37:49 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/03/2022 17:37:53 - INFO - codeparrot_training - Step 3587: {'lr': 0.0004998581598734991, 'samples': 1837056, 'steps': 3587, 'loss/train': 2.2153120040893555}
-03/03/2022 17:37:57 - INFO - codeparrot_training - Step 3588: {'lr': 0.0004998579810815905, 'samples': 1837568, 'steps': 3588, 'loss/train': 2.6685640811920166}
-03/03/2022 17:37:58 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/03/2022 17:38:02 - INFO - codeparrot_training - Step 3589: {'lr': 0.0004998578021770995, 'samples': 1838080, 'steps': 3589, 'loss/train': 2.742213249206543}
-03/03/2022 17:38:05 - INFO - codeparrot_training - Step 3590: {'lr': 0.0004998576231600267, 'samples': 1838592, 'steps': 3590, 'loss/train': 3.1950418949127197}
-03/03/2022 17:38:07 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/03/2022 17:38:10 - INFO - codeparrot_training - Step 3591: {'lr': 0.0004998574440303718, 'samples': 1839104, 'steps': 3591, 'loss/train': 1.4914791584014893}
-03/03/2022 17:38:13 - INFO - codeparrot_training - Step 3592: {'lr': 0.0004998572647881349, 'samples': 1839616, 'steps': 3592, 'loss/train': 3.2210724353790283}
-03/03/2022 17:38:15 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/03/2022 17:38:19 - INFO - codeparrot_training - Step 3593: {'lr': 0.0004998570854333163, 'samples': 1840128, 'steps': 3593, 'loss/train': 2.1720919609069824}
-03/03/2022 17:38:22 - INFO - codeparrot_training - Step 3594: {'lr': 0.0004998569059659158, 'samples': 1840640, 'steps': 3594, 'loss/train': 3.3248465061187744}
-03/03/2022 17:38:23 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/03/2022 17:38:27 - INFO - codeparrot_training - Step 3595: {'lr': 0.0004998567263859338, 'samples': 1841152, 'steps': 3595, 'loss/train': 2.3522305488586426}
-03/03/2022 17:38:30 - INFO - codeparrot_training - Step 3596: {'lr': 0.0004998565466933702, 'samples': 1841664, 'steps': 3596, 'loss/train': 2.2768325805664062}
-03/03/2022 17:38:32 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/03/2022 17:38:36 - INFO - codeparrot_training - Step 3597: {'lr': 0.000499856366888225, 'samples': 1842176, 'steps': 3597, 'loss/train': 2.3901896476745605}
-03/03/2022 17:38:39 - INFO - codeparrot_training - Step 3598: {'lr': 0.0004998561869704983, 'samples': 1842688, 'steps': 3598, 'loss/train': 2.52305269241333}
-03/03/2022 17:38:40 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/03/2022 17:38:44 - INFO - codeparrot_training - Step 3599: {'lr': 0.0004998560069401905, 'samples': 1843200, 'steps': 3599, 'loss/train': 3.3277816772460938}
-03/03/2022 17:38:47 - INFO - codeparrot_training - Step 3600: {'lr': 0.0004998558267973013, 'samples': 1843712, 'steps': 3600, 'loss/train': 3.032680034637451}
-03/03/2022 17:38:48 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/03/2022 17:38:52 - INFO - codeparrot_training - Step 3601: {'lr': 0.0004998556465418309, 'samples': 1844224, 'steps': 3601, 'loss/train': 2.336735248565674}
-03/03/2022 17:38:56 - INFO - codeparrot_training - Step 3602: {'lr': 0.0004998554661737795, 'samples': 1844736, 'steps': 3602, 'loss/train': 2.719419002532959}
-03/03/2022 17:38:57 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/03/2022 17:39:01 - INFO - codeparrot_training - Step 3603: {'lr': 0.000499855285693147, 'samples': 1845248, 'steps': 3603, 'loss/train': 2.1824147701263428}
-03/03/2022 17:39:04 - INFO - codeparrot_training - Step 3604: {'lr': 0.0004998551050999336, 'samples': 1845760, 'steps': 3604, 'loss/train': 2.0732715129852295}
-03/03/2022 17:39:05 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/03/2022 17:39:09 - INFO - codeparrot_training - Step 3605: {'lr': 0.0004998549243941393, 'samples': 1846272, 'steps': 3605, 'loss/train': 2.9126882553100586}
-03/03/2022 17:39:12 - INFO - codeparrot_training - Step 3606: {'lr': 0.0004998547435757643, 'samples': 1846784, 'steps': 3606, 'loss/train': 3.208984613418579}
-03/03/2022 17:39:14 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/03/2022 17:39:18 - INFO - codeparrot_training - Step 3607: {'lr': 0.0004998545626448087, 'samples': 1847296, 'steps': 3607, 'loss/train': 2.5929415225982666}
-03/03/2022 17:39:21 - INFO - codeparrot_training - Step 3608: {'lr': 0.0004998543816012723, 'samples': 1847808, 'steps': 3608, 'loss/train': 1.4198228120803833}
-03/03/2022 17:39:22 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/03/2022 17:39:26 - INFO - codeparrot_training - Step 3609: {'lr': 0.0004998542004451554, 'samples': 1848320, 'steps': 3609, 'loss/train': 2.305907964706421}
-03/03/2022 17:39:29 - INFO - codeparrot_training - Step 3610: {'lr': 0.000499854019176458, 'samples': 1848832, 'steps': 3610, 'loss/train': 2.23753023147583}
-03/03/2022 17:39:30 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/03/2022 17:39:34 - INFO - codeparrot_training - Step 3611: {'lr': 0.0004998538377951803, 'samples': 1849344, 'steps': 3611, 'loss/train': 2.7183055877685547}
-03/03/2022 17:39:37 - INFO - codeparrot_training - Step 3612: {'lr': 0.0004998536563013224, 'samples': 1849856, 'steps': 3612, 'loss/train': 1.9926756620407104}
-03/03/2022 17:39:39 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/03/2022 17:39:43 - INFO - codeparrot_training - Step 3613: {'lr': 0.0004998534746948843, 'samples': 1850368, 'steps': 3613, 'loss/train': 2.6904778480529785}
-03/03/2022 17:39:46 - INFO - codeparrot_training - Step 3614: {'lr': 0.000499853292975866, 'samples': 1850880, 'steps': 3614, 'loss/train': 3.7864110469818115}
-03/03/2022 17:39:47 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/03/2022 17:39:51 - INFO - codeparrot_training - Step 3615: {'lr': 0.0004998531111442676, 'samples': 1851392, 'steps': 3615, 'loss/train': 2.306504487991333}
-03/03/2022 17:39:54 - INFO - codeparrot_training - Step 3616: {'lr': 0.0004998529292000893, 'samples': 1851904, 'steps': 3616, 'loss/train': 2.8009467124938965}
-03/03/2022 17:39:56 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/03/2022 17:39:59 - INFO - codeparrot_training - Step 3617: {'lr': 0.0004998527471433312, 'samples': 1852416, 'steps': 3617, 'loss/train': 2.683246612548828}
-03/03/2022 17:40:03 - INFO - codeparrot_training - Step 3618: {'lr': 0.0004998525649739932, 'samples': 1852928, 'steps': 3618, 'loss/train': 2.416942596435547}
-03/03/2022 17:40:04 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/03/2022 17:40:08 - INFO - codeparrot_training - Step 3619: {'lr': 0.0004998523826920756, 'samples': 1853440, 'steps': 3619, 'loss/train': 1.7753640413284302}
-03/03/2022 17:40:11 - INFO - codeparrot_training - Step 3620: {'lr': 0.0004998522002975783, 'samples': 1853952, 'steps': 3620, 'loss/train': 2.5840494632720947}
-03/03/2022 17:40:12 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/03/2022 17:40:16 - INFO - codeparrot_training - Step 3621: {'lr': 0.0004998520177905015, 'samples': 1854464, 'steps': 3621, 'loss/train': 2.44264817237854}
-03/03/2022 17:40:19 - INFO - codeparrot_training - Step 3622: {'lr': 0.0004998518351708452, 'samples': 1854976, 'steps': 3622, 'loss/train': 3.1505048274993896}
-03/03/2022 17:40:20 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/03/2022 17:40:25 - INFO - codeparrot_training - Step 3623: {'lr': 0.0004998516524386095, 'samples': 1855488, 'steps': 3623, 'loss/train': 2.8222768306732178}
-03/03/2022 17:40:28 - INFO - codeparrot_training - Step 3624: {'lr': 0.0004998514695937945, 'samples': 1856000, 'steps': 3624, 'loss/train': 2.9943392276763916}
-03/03/2022 17:40:29 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/03/2022 17:40:33 - INFO - codeparrot_training - Step 3625: {'lr': 0.0004998512866364003, 'samples': 1856512, 'steps': 3625, 'loss/train': 2.179144859313965}
-03/03/2022 17:40:36 - INFO - codeparrot_training - Step 3626: {'lr': 0.000499851103566427, 'samples': 1857024, 'steps': 3626, 'loss/train': 2.710876226425171}
-03/03/2022 17:40:37 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/03/2022 17:40:42 - INFO - codeparrot_training - Step 3627: {'lr': 0.0004998509203838746, 'samples': 1857536, 'steps': 3627, 'loss/train': 3.0475049018859863}
-03/03/2022 17:40:45 - INFO - codeparrot_training - Step 3628: {'lr': 0.0004998507370887433, 'samples': 1858048, 'steps': 3628, 'loss/train': 1.7123950719833374}
-03/03/2022 17:40:45 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/03/2022 17:40:50 - INFO - codeparrot_training - Step 3629: {'lr': 0.000499850553681033, 'samples': 1858560, 'steps': 3629, 'loss/train': 3.6757304668426514}
-03/03/2022 17:40:53 - INFO - codeparrot_training - Step 3630: {'lr': 0.000499850370160744, 'samples': 1859072, 'steps': 3630, 'loss/train': 3.588217258453369}
-03/03/2022 17:40:54 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/03/2022 17:40:59 - INFO - codeparrot_training - Step 3631: {'lr': 0.0004998501865278762, 'samples': 1859584, 'steps': 3631, 'loss/train': 3.2438197135925293}
-03/03/2022 17:41:02 - INFO - codeparrot_training - Step 3632: {'lr': 0.0004998500027824298, 'samples': 1860096, 'steps': 3632, 'loss/train': 2.3159561157226562}
-03/03/2022 17:41:02 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/03/2022 17:41:07 - INFO - codeparrot_training - Step 3633: {'lr': 0.0004998498189244049, 'samples': 1860608, 'steps': 3633, 'loss/train': 2.9345972537994385}
-03/03/2022 17:41:10 - INFO - codeparrot_training - Step 3634: {'lr': 0.0004998496349538015, 'samples': 1861120, 'steps': 3634, 'loss/train': 2.375861644744873}
-03/03/2022 17:41:10 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/03/2022 17:41:15 - INFO - codeparrot_training - Step 3635: {'lr': 0.0004998494508706196, 'samples': 1861632, 'steps': 3635, 'loss/train': 2.841984987258911}
-03/03/2022 17:41:19 - INFO - codeparrot_training - Step 3636: {'lr': 0.0004998492666748594, 'samples': 1862144, 'steps': 3636, 'loss/train': 2.4892513751983643}
-03/03/2022 17:41:19 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/03/2022 17:41:24 - INFO - codeparrot_training - Step 3637: {'lr': 0.0004998490823665211, 'samples': 1862656, 'steps': 3637, 'loss/train': 1.2803422212600708}
-03/03/2022 17:41:27 - INFO - codeparrot_training - Step 3638: {'lr': 0.0004998488979456046, 'samples': 1863168, 'steps': 3638, 'loss/train': 2.3221004009246826}
-03/03/2022 17:41:27 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/03/2022 17:41:32 - INFO - codeparrot_training - Step 3639: {'lr': 0.00049984871341211, 'samples': 1863680, 'steps': 3639, 'loss/train': 3.4515297412872314}
-03/03/2022 17:41:36 - INFO - codeparrot_training - Step 3640: {'lr': 0.0004998485287660375, 'samples': 1864192, 'steps': 3640, 'loss/train': 2.875380516052246}
-03/03/2022 17:41:36 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/03/2022 17:41:41 - INFO - codeparrot_training - Step 3641: {'lr': 0.0004998483440073871, 'samples': 1864704, 'steps': 3641, 'loss/train': 1.632257103919983}
-03/03/2022 17:41:44 - INFO - codeparrot_training - Step 3642: {'lr': 0.0004998481591361589, 'samples': 1865216, 'steps': 3642, 'loss/train': 1.3579598665237427}
-03/03/2022 17:41:45 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/03/2022 17:41:50 - INFO - codeparrot_training - Step 3643: {'lr': 0.000499847974152353, 'samples': 1865728, 'steps': 3643, 'loss/train': 2.599026918411255}
-03/03/2022 17:41:53 - INFO - codeparrot_training - Step 3644: {'lr': 0.0004998477890559693, 'samples': 1866240, 'steps': 3644, 'loss/train': 2.9226536750793457}
-03/03/2022 17:41:56 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/03/2022 17:41:58 - INFO - codeparrot_training - Step 3645: {'lr': 0.0004998476038470082, 'samples': 1866752, 'steps': 3645, 'loss/train': 2.3888001441955566}
-03/03/2022 17:42:01 - INFO - codeparrot_training - Step 3646: {'lr': 0.0004998474185254696, 'samples': 1867264, 'steps': 3646, 'loss/train': 2.4278995990753174}
-03/03/2022 17:42:04 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/03/2022 17:42:07 - INFO - codeparrot_training - Step 3647: {'lr': 0.0004998472330913535, 'samples': 1867776, 'steps': 3647, 'loss/train': 3.1469688415527344}
-03/03/2022 17:42:10 - INFO - codeparrot_training - Step 3648: {'lr': 0.0004998470475446603, 'samples': 1868288, 'steps': 3648, 'loss/train': 2.0364415645599365}
-03/03/2022 17:42:12 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/03/2022 17:42:15 - INFO - codeparrot_training - Step 3649: {'lr': 0.0004998468618853896, 'samples': 1868800, 'steps': 3649, 'loss/train': 2.8296844959259033}
-03/03/2022 17:42:19 - INFO - codeparrot_training - Step 3650: {'lr': 0.000499846676113542, 'samples': 1869312, 'steps': 3650, 'loss/train': 3.0041654109954834}
-03/03/2022 17:42:21 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/03/2022 17:42:24 - INFO - codeparrot_training - Step 3651: {'lr': 0.0004998464902291173, 'samples': 1869824, 'steps': 3651, 'loss/train': 1.721150279045105}
-03/03/2022 17:42:27 - INFO - codeparrot_training - Step 3652: {'lr': 0.0004998463042321155, 'samples': 1870336, 'steps': 3652, 'loss/train': 2.6826014518737793}
-03/03/2022 17:42:30 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/03/2022 17:42:32 - INFO - codeparrot_training - Step 3653: {'lr': 0.0004998461181225369, 'samples': 1870848, 'steps': 3653, 'loss/train': 3.217963695526123}
-03/03/2022 17:42:35 - INFO - codeparrot_training - Step 3654: {'lr': 0.0004998459319003815, 'samples': 1871360, 'steps': 3654, 'loss/train': 2.749781608581543}
-03/03/2022 17:42:38 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/03/2022 17:42:40 - INFO - codeparrot_training - Step 3655: {'lr': 0.0004998457455656493, 'samples': 1871872, 'steps': 3655, 'loss/train': 2.6557867527008057}
-03/03/2022 17:42:44 - INFO - codeparrot_training - Step 3656: {'lr': 0.0004998455591183406, 'samples': 1872384, 'steps': 3656, 'loss/train': 2.878848075866699}
-03/03/2022 17:42:46 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/03/2022 17:42:49 - INFO - codeparrot_training - Step 3657: {'lr': 0.0004998453725584552, 'samples': 1872896, 'steps': 3657, 'loss/train': 2.1072981357574463}
-03/03/2022 17:42:52 - INFO - codeparrot_training - Step 3658: {'lr': 0.0004998451858859934, 'samples': 1873408, 'steps': 3658, 'loss/train': 1.8208065032958984}
-03/03/2022 17:42:55 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/03/2022 17:42:57 - INFO - codeparrot_training - Step 3659: {'lr': 0.0004998449991009552, 'samples': 1873920, 'steps': 3659, 'loss/train': 2.472975730895996}
-03/03/2022 17:43:01 - INFO - codeparrot_training - Step 3660: {'lr': 0.0004998448122033408, 'samples': 1874432, 'steps': 3660, 'loss/train': 2.201519727706909}
-03/03/2022 17:43:03 - INFO - codeparrot_training - Skipping example with length 462 (seq_length=1024)
-03/03/2022 17:43:06 - INFO - codeparrot_training - Step 3661: {'lr': 0.00049984462519315, 'samples': 1874944, 'steps': 3661, 'loss/train': 2.484926700592041}
-03/03/2022 17:43:09 - INFO - codeparrot_training - Step 3662: {'lr': 0.0004998444380703832, 'samples': 1875456, 'steps': 3662, 'loss/train': 4.3101420402526855}
-03/03/2022 17:43:11 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/03/2022 17:43:14 - INFO - codeparrot_training - Step 3663: {'lr': 0.0004998442508350404, 'samples': 1875968, 'steps': 3663, 'loss/train': 3.4521312713623047}
-03/03/2022 17:43:18 - INFO - codeparrot_training - Step 3664: {'lr': 0.0004998440634871215, 'samples': 1876480, 'steps': 3664, 'loss/train': 2.967343807220459}
-03/03/2022 17:43:20 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/03/2022 17:43:23 - INFO - codeparrot_training - Step 3665: {'lr': 0.0004998438760266267, 'samples': 1876992, 'steps': 3665, 'loss/train': 2.482686758041382}
-03/03/2022 17:43:26 - INFO - codeparrot_training - Step 3666: {'lr': 0.0004998436884535562, 'samples': 1877504, 'steps': 3666, 'loss/train': 2.7415034770965576}
-03/03/2022 17:43:28 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/03/2022 17:43:31 - INFO - codeparrot_training - Step 3667: {'lr': 0.00049984350076791, 'samples': 1878016, 'steps': 3667, 'loss/train': 1.9611742496490479}
-03/03/2022 17:43:34 - INFO - codeparrot_training - Step 3668: {'lr': 0.0004998433129696882, 'samples': 1878528, 'steps': 3668, 'loss/train': 2.9182839393615723}
-03/03/2022 17:43:36 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/03/2022 17:43:40 - INFO - codeparrot_training - Step 3669: {'lr': 0.0004998431250588907, 'samples': 1879040, 'steps': 3669, 'loss/train': 3.628209352493286}
-03/03/2022 17:43:43 - INFO - codeparrot_training - Step 3670: {'lr': 0.0004998429370355179, 'samples': 1879552, 'steps': 3670, 'loss/train': 1.954303503036499}
-03/03/2022 17:43:45 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/03/2022 17:43:48 - INFO - codeparrot_training - Step 3671: {'lr': 0.0004998427488995697, 'samples': 1880064, 'steps': 3671, 'loss/train': 2.8552260398864746}
-03/03/2022 17:43:51 - INFO - codeparrot_training - Step 3672: {'lr': 0.0004998425606510461, 'samples': 1880576, 'steps': 3672, 'loss/train': 2.551632881164551}
-03/03/2022 17:43:54 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/03/2022 17:43:57 - INFO - codeparrot_training - Step 3673: {'lr': 0.0004998423722899475, 'samples': 1881088, 'steps': 3673, 'loss/train': 2.644566774368286}
-03/03/2022 17:44:00 - INFO - codeparrot_training - Step 3674: {'lr': 0.0004998421838162735, 'samples': 1881600, 'steps': 3674, 'loss/train': 2.391247272491455}
-03/03/2022 17:44:02 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/03/2022 17:44:05 - INFO - codeparrot_training - Step 3675: {'lr': 0.0004998419952300247, 'samples': 1882112, 'steps': 3675, 'loss/train': 3.183044195175171}
-03/03/2022 17:44:08 - INFO - codeparrot_training - Step 3676: {'lr': 0.0004998418065312009, 'samples': 1882624, 'steps': 3676, 'loss/train': 1.800328254699707}
-03/03/2022 17:44:10 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/03/2022 17:44:13 - INFO - codeparrot_training - Step 3677: {'lr': 0.0004998416177198022, 'samples': 1883136, 'steps': 3677, 'loss/train': 2.083582639694214}
-03/03/2022 17:44:17 - INFO - codeparrot_training - Step 3678: {'lr': 0.0004998414287958288, 'samples': 1883648, 'steps': 3678, 'loss/train': 1.6754897832870483}
-03/03/2022 17:44:18 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/03/2022 17:44:22 - INFO - codeparrot_training - Step 3679: {'lr': 0.0004998412397592807, 'samples': 1884160, 'steps': 3679, 'loss/train': 2.243828773498535}
-03/03/2022 17:44:25 - INFO - codeparrot_training - Step 3680: {'lr': 0.0004998410506101579, 'samples': 1884672, 'steps': 3680, 'loss/train': 2.387927293777466}
-03/03/2022 17:44:27 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/03/2022 17:44:30 - INFO - codeparrot_training - Step 3681: {'lr': 0.0004998408613484605, 'samples': 1885184, 'steps': 3681, 'loss/train': 3.237916946411133}
-03/03/2022 17:44:33 - INFO - codeparrot_training - Step 3682: {'lr': 0.0004998406719741888, 'samples': 1885696, 'steps': 3682, 'loss/train': 2.312106132507324}
-03/03/2022 17:44:35 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/03/2022 17:44:39 - INFO - codeparrot_training - Step 3683: {'lr': 0.0004998404824873428, 'samples': 1886208, 'steps': 3683, 'loss/train': 2.2623579502105713}
-03/03/2022 17:44:42 - INFO - codeparrot_training - Step 3684: {'lr': 0.0004998402928879225, 'samples': 1886720, 'steps': 3684, 'loss/train': 2.575990676879883}
-03/03/2022 17:44:43 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/03/2022 17:44:47 - INFO - codeparrot_training - Step 3685: {'lr': 0.000499840103175928, 'samples': 1887232, 'steps': 3685, 'loss/train': 3.730891227722168}
-03/03/2022 17:44:50 - INFO - codeparrot_training - Step 3686: {'lr': 0.0004998399133513594, 'samples': 1887744, 'steps': 3686, 'loss/train': 2.1866838932037354}
-03/03/2022 17:44:52 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/03/2022 17:44:56 - INFO - codeparrot_training - Step 3687: {'lr': 0.0004998397234142167, 'samples': 1888256, 'steps': 3687, 'loss/train': 2.3116037845611572}
-03/03/2022 17:44:59 - INFO - codeparrot_training - Step 3688: {'lr': 0.0004998395333645002, 'samples': 1888768, 'steps': 3688, 'loss/train': 2.7817230224609375}
-03/03/2022 17:45:00 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/03/2022 17:45:04 - INFO - codeparrot_training - Step 3689: {'lr': 0.0004998393432022098, 'samples': 1889280, 'steps': 3689, 'loss/train': 2.8956661224365234}
-03/03/2022 17:45:07 - INFO - codeparrot_training - Step 3690: {'lr': 0.0004998391529273457, 'samples': 1889792, 'steps': 3690, 'loss/train': 2.9790821075439453}
-03/03/2022 17:45:09 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/03/2022 17:45:12 - INFO - codeparrot_training - Step 3691: {'lr': 0.0004998389625399079, 'samples': 1890304, 'steps': 3691, 'loss/train': 2.958409309387207}
-03/03/2022 17:45:15 - INFO - codeparrot_training - Step 3692: {'lr': 0.0004998387720398965, 'samples': 1890816, 'steps': 3692, 'loss/train': 2.0681912899017334}
-03/03/2022 17:45:17 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/03/2022 17:45:21 - INFO - codeparrot_training - Step 3693: {'lr': 0.0004998385814273116, 'samples': 1891328, 'steps': 3693, 'loss/train': 2.9830071926116943}
-03/03/2022 17:45:24 - INFO - codeparrot_training - Step 3694: {'lr': 0.0004998383907021533, 'samples': 1891840, 'steps': 3694, 'loss/train': 2.9512157440185547}
-03/03/2022 17:45:25 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/03/2022 17:45:29 - INFO - codeparrot_training - Step 3695: {'lr': 0.0004998381998644217, 'samples': 1892352, 'steps': 3695, 'loss/train': 1.9748598337173462}
-03/03/2022 17:45:32 - INFO - codeparrot_training - Step 3696: {'lr': 0.0004998380089141169, 'samples': 1892864, 'steps': 3696, 'loss/train': 3.3202672004699707}
-03/03/2022 17:45:34 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/03/2022 17:45:38 - INFO - codeparrot_training - Step 3697: {'lr': 0.0004998378178512388, 'samples': 1893376, 'steps': 3697, 'loss/train': 2.688002347946167}
-03/03/2022 17:45:41 - INFO - codeparrot_training - Step 3698: {'lr': 0.0004998376266757878, 'samples': 1893888, 'steps': 3698, 'loss/train': 2.5726189613342285}
-03/03/2022 17:45:42 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/03/2022 17:45:46 - INFO - codeparrot_training - Step 3699: {'lr': 0.0004998374353877638, 'samples': 1894400, 'steps': 3699, 'loss/train': 1.4164992570877075}
-03/03/2022 17:45:49 - INFO - codeparrot_training - Step 3700: {'lr': 0.0004998372439871668, 'samples': 1894912, 'steps': 3700, 'loss/train': 1.0202736854553223}
-03/03/2022 17:45:50 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/03/2022 17:45:54 - INFO - codeparrot_training - Step 3701: {'lr': 0.000499837052473997, 'samples': 1895424, 'steps': 3701, 'loss/train': 2.804818868637085}
-03/03/2022 17:45:58 - INFO - codeparrot_training - Step 3702: {'lr': 0.0004998368608482546, 'samples': 1895936, 'steps': 3702, 'loss/train': 3.662398099899292}
-03/03/2022 17:45:59 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/03/2022 17:46:03 - INFO - codeparrot_training - Step 3703: {'lr': 0.0004998366691099395, 'samples': 1896448, 'steps': 3703, 'loss/train': 1.1836762428283691}
-03/03/2022 17:46:06 - INFO - codeparrot_training - Step 3704: {'lr': 0.0004998364772590518, 'samples': 1896960, 'steps': 3704, 'loss/train': 2.834601879119873}
-03/03/2022 17:46:07 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/03/2022 17:46:11 - INFO - codeparrot_training - Step 3705: {'lr': 0.0004998362852955918, 'samples': 1897472, 'steps': 3705, 'loss/train': 2.514988899230957}
-03/03/2022 17:46:14 - INFO - codeparrot_training - Step 3706: {'lr': 0.0004998360932195593, 'samples': 1897984, 'steps': 3706, 'loss/train': 3.4431533813476562}
-03/03/2022 17:46:16 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/03/2022 17:46:20 - INFO - codeparrot_training - Step 3707: {'lr': 0.0004998359010309544, 'samples': 1898496, 'steps': 3707, 'loss/train': 1.8733627796173096}
-03/03/2022 17:46:23 - INFO - codeparrot_training - Step 3708: {'lr': 0.0004998357087297775, 'samples': 1899008, 'steps': 3708, 'loss/train': 1.8023738861083984}
-03/03/2022 17:46:25 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/03/2022 17:46:28 - INFO - codeparrot_training - Step 3709: {'lr': 0.0004998355163160285, 'samples': 1899520, 'steps': 3709, 'loss/train': 2.1604526042938232}
-03/03/2022 17:46:32 - INFO - codeparrot_training - Step 3710: {'lr': 0.0004998353237897073, 'samples': 1900032, 'steps': 3710, 'loss/train': 2.415114641189575}
-03/03/2022 17:46:34 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/03/2022 17:46:37 - INFO - codeparrot_training - Step 3711: {'lr': 0.0004998351311508143, 'samples': 1900544, 'steps': 3711, 'loss/train': 1.8773698806762695}
-03/03/2022 17:46:40 - INFO - codeparrot_training - Step 3712: {'lr': 0.0004998349383993493, 'samples': 1901056, 'steps': 3712, 'loss/train': 2.5502567291259766}
-03/03/2022 17:46:42 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/03/2022 17:46:46 - INFO - codeparrot_training - Step 3713: {'lr': 0.0004998347455353126, 'samples': 1901568, 'steps': 3713, 'loss/train': 1.7980543375015259}
-03/03/2022 17:46:49 - INFO - codeparrot_training - Step 3714: {'lr': 0.0004998345525587042, 'samples': 1902080, 'steps': 3714, 'loss/train': 2.639075756072998}
-03/03/2022 17:46:51 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/03/2022 17:46:54 - INFO - codeparrot_training - Step 3715: {'lr': 0.0004998343594695242, 'samples': 1902592, 'steps': 3715, 'loss/train': 2.9284801483154297}
-03/03/2022 17:46:57 - INFO - codeparrot_training - Step 3716: {'lr': 0.0004998341662677728, 'samples': 1903104, 'steps': 3716, 'loss/train': 1.6907099485397339}
-03/03/2022 17:46:59 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/03/2022 17:47:03 - INFO - codeparrot_training - Step 3717: {'lr': 0.0004998339729534499, 'samples': 1903616, 'steps': 3717, 'loss/train': 2.285964012145996}
-03/03/2022 17:47:06 - INFO - codeparrot_training - Step 3718: {'lr': 0.0004998337795265557, 'samples': 1904128, 'steps': 3718, 'loss/train': 2.3662631511688232}
-03/03/2022 17:47:08 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/03/2022 17:47:11 - INFO - codeparrot_training - Step 3719: {'lr': 0.0004998335859870903, 'samples': 1904640, 'steps': 3719, 'loss/train': 1.7086601257324219}
-03/03/2022 17:47:14 - INFO - codeparrot_training - Step 3720: {'lr': 0.0004998333923350536, 'samples': 1905152, 'steps': 3720, 'loss/train': 1.6167089939117432}
-03/03/2022 17:47:16 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/03/2022 17:47:20 - INFO - codeparrot_training - Step 3721: {'lr': 0.000499833198570446, 'samples': 1905664, 'steps': 3721, 'loss/train': 2.410611629486084}
-03/03/2022 17:47:23 - INFO - codeparrot_training - Step 3722: {'lr': 0.0004998330046932672, 'samples': 1906176, 'steps': 3722, 'loss/train': 2.5066184997558594}
-03/03/2022 17:47:25 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/03/2022 17:47:28 - INFO - codeparrot_training - Step 3723: {'lr': 0.0004998328107035176, 'samples': 1906688, 'steps': 3723, 'loss/train': 3.44197154045105}
-03/03/2022 17:47:31 - INFO - codeparrot_training - Step 3724: {'lr': 0.0004998326166011973, 'samples': 1907200, 'steps': 3724, 'loss/train': 2.433289051055908}
-03/03/2022 17:47:34 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/03/2022 17:47:37 - INFO - codeparrot_training - Step 3725: {'lr': 0.0004998324223863061, 'samples': 1907712, 'steps': 3725, 'loss/train': 4.985229015350342}
-03/03/2022 17:47:40 - INFO - codeparrot_training - Step 3726: {'lr': 0.0004998322280588445, 'samples': 1908224, 'steps': 3726, 'loss/train': 1.6632026433944702}
-03/03/2022 17:47:42 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/03/2022 17:47:45 - INFO - codeparrot_training - Step 3727: {'lr': 0.0004998320336188121, 'samples': 1908736, 'steps': 3727, 'loss/train': 3.0993289947509766}
-03/03/2022 17:47:48 - INFO - codeparrot_training - Step 3728: {'lr': 0.0004998318390662095, 'samples': 1909248, 'steps': 3728, 'loss/train': 2.6630921363830566}
-03/03/2022 17:47:50 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/03/2022 17:47:54 - INFO - codeparrot_training - Step 3729: {'lr': 0.0004998316444010363, 'samples': 1909760, 'steps': 3729, 'loss/train': 0.6879110336303711}
-03/03/2022 17:47:57 - INFO - codeparrot_training - Step 3730: {'lr': 0.0004998314496232929, 'samples': 1910272, 'steps': 3730, 'loss/train': 2.419485092163086}
-03/03/2022 17:47:59 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/03/2022 17:48:02 - INFO - codeparrot_training - Step 3731: {'lr': 0.0004998312547329793, 'samples': 1910784, 'steps': 3731, 'loss/train': 2.544678211212158}
-03/03/2022 17:48:05 - INFO - codeparrot_training - Step 3732: {'lr': 0.0004998310597300956, 'samples': 1911296, 'steps': 3732, 'loss/train': 2.6967203617095947}
-03/03/2022 17:48:07 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/03/2022 17:48:10 - INFO - codeparrot_training - Step 3733: {'lr': 0.0004998308646146419, 'samples': 1911808, 'steps': 3733, 'loss/train': 1.7263741493225098}
-03/03/2022 17:48:14 - INFO - codeparrot_training - Step 3734: {'lr': 0.0004998306693866181, 'samples': 1912320, 'steps': 3734, 'loss/train': 2.4978933334350586}
-03/03/2022 17:48:16 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/03/2022 17:48:19 - INFO - codeparrot_training - Step 3735: {'lr': 0.0004998304740460247, 'samples': 1912832, 'steps': 3735, 'loss/train': 2.487455129623413}
-03/03/2022 17:48:22 - INFO - codeparrot_training - Step 3736: {'lr': 0.0004998302785928614, 'samples': 1913344, 'steps': 3736, 'loss/train': 1.291659951210022}
-03/03/2022 17:48:24 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/03/2022 17:48:27 - INFO - codeparrot_training - Step 3737: {'lr': 0.0004998300830271285, 'samples': 1913856, 'steps': 3737, 'loss/train': 2.6324472427368164}
-03/03/2022 17:48:30 - INFO - codeparrot_training - Step 3738: {'lr': 0.000499829887348826, 'samples': 1914368, 'steps': 3738, 'loss/train': 2.5330216884613037}
-03/03/2022 17:48:32 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/03/2022 17:48:36 - INFO - codeparrot_training - Step 3739: {'lr': 0.0004998296915579539, 'samples': 1914880, 'steps': 3739, 'loss/train': 2.3425724506378174}
-03/03/2022 17:48:39 - INFO - codeparrot_training - Step 3740: {'lr': 0.0004998294956545125, 'samples': 1915392, 'steps': 3740, 'loss/train': 3.2945218086242676}
-03/03/2022 17:48:41 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/03/2022 17:48:44 - INFO - codeparrot_training - Step 3741: {'lr': 0.0004998292996385019, 'samples': 1915904, 'steps': 3741, 'loss/train': 1.7640777826309204}
-03/03/2022 17:48:47 - INFO - codeparrot_training - Step 3742: {'lr': 0.0004998291035099219, 'samples': 1916416, 'steps': 3742, 'loss/train': 2.349073648452759}
-03/03/2022 17:48:49 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/03/2022 17:48:52 - INFO - codeparrot_training - Step 3743: {'lr': 0.0004998289072687728, 'samples': 1916928, 'steps': 3743, 'loss/train': 2.297445058822632}
-03/03/2022 17:48:56 - INFO - codeparrot_training - Step 3744: {'lr': 0.0004998287109150547, 'samples': 1917440, 'steps': 3744, 'loss/train': 2.437101125717163}
-03/03/2022 17:48:57 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/03/2022 17:49:01 - INFO - codeparrot_training - Step 3745: {'lr': 0.0004998285144487676, 'samples': 1917952, 'steps': 3745, 'loss/train': 2.081667423248291}
-03/03/2022 17:49:04 - INFO - codeparrot_training - Step 3746: {'lr': 0.0004998283178699116, 'samples': 1918464, 'steps': 3746, 'loss/train': 2.67838191986084}
-03/03/2022 17:49:06 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/03/2022 17:49:09 - INFO - codeparrot_training - Step 3747: {'lr': 0.0004998281211784869, 'samples': 1918976, 'steps': 3747, 'loss/train': 2.2773544788360596}
-03/03/2022 17:49:12 - INFO - codeparrot_training - Step 3748: {'lr': 0.0004998279243744934, 'samples': 1919488, 'steps': 3748, 'loss/train': 2.441211700439453}
-03/03/2022 17:49:14 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/03/2022 17:49:18 - INFO - codeparrot_training - Step 3749: {'lr': 0.0004998277274579313, 'samples': 1920000, 'steps': 3749, 'loss/train': 3.0278847217559814}
-03/03/2022 17:49:21 - INFO - codeparrot_training - Step 3750: {'lr': 0.0004998275304288007, 'samples': 1920512, 'steps': 3750, 'loss/train': 2.970712184906006}
-03/03/2022 17:49:22 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/03/2022 17:49:26 - INFO - codeparrot_training - Step 3751: {'lr': 0.0004998273332871017, 'samples': 1921024, 'steps': 3751, 'loss/train': 1.4337462186813354}
-03/03/2022 17:49:29 - INFO - codeparrot_training - Step 3752: {'lr': 0.0004998271360328344, 'samples': 1921536, 'steps': 3752, 'loss/train': 3.0126447677612305}
-03/03/2022 17:49:32 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/03/2022 17:49:35 - INFO - codeparrot_training - Step 3753: {'lr': 0.0004998269386659988, 'samples': 1922048, 'steps': 3753, 'loss/train': 2.8830173015594482}
-03/03/2022 17:49:38 - INFO - codeparrot_training - Step 3754: {'lr': 0.000499826741186595, 'samples': 1922560, 'steps': 3754, 'loss/train': 2.7315151691436768}
-03/03/2022 17:49:40 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/03/2022 17:49:43 - INFO - codeparrot_training - Step 3755: {'lr': 0.0004998265435946232, 'samples': 1923072, 'steps': 3755, 'loss/train': 2.9850118160247803}
-03/03/2022 17:49:46 - INFO - codeparrot_training - Step 3756: {'lr': 0.0004998263458900833, 'samples': 1923584, 'steps': 3756, 'loss/train': 2.8998255729675293}
-03/03/2022 17:49:49 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/03/2022 17:49:51 - INFO - codeparrot_training - Step 3757: {'lr': 0.0004998261480729755, 'samples': 1924096, 'steps': 3757, 'loss/train': 3.4218661785125732}
-03/03/2022 17:49:55 - INFO - codeparrot_training - Step 3758: {'lr': 0.0004998259501433, 'samples': 1924608, 'steps': 3758, 'loss/train': 2.27099609375}
-03/03/2022 17:49:57 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/03/2022 17:50:00 - INFO - codeparrot_training - Step 3759: {'lr': 0.0004998257521010567, 'samples': 1925120, 'steps': 3759, 'loss/train': 2.9374964237213135}
-03/03/2022 17:50:03 - INFO - codeparrot_training - Step 3760: {'lr': 0.0004998255539462459, 'samples': 1925632, 'steps': 3760, 'loss/train': 2.132153272628784}
-03/03/2022 17:50:05 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/03/2022 17:50:08 - INFO - codeparrot_training - Step 3761: {'lr': 0.0004998253556788675, 'samples': 1926144, 'steps': 3761, 'loss/train': 2.714040994644165}
-03/03/2022 17:50:12 - INFO - codeparrot_training - Step 3762: {'lr': 0.0004998251572989217, 'samples': 1926656, 'steps': 3762, 'loss/train': 2.861882448196411}
-03/03/2022 17:50:14 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/03/2022 17:50:17 - INFO - codeparrot_training - Step 3763: {'lr': 0.0004998249588064085, 'samples': 1927168, 'steps': 3763, 'loss/train': 3.266000509262085}
-03/03/2022 17:50:20 - INFO - codeparrot_training - Step 3764: {'lr': 0.0004998247602013278, 'samples': 1927680, 'steps': 3764, 'loss/train': 2.7360594272613525}
-03/03/2022 17:50:22 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/03/2022 17:50:25 - INFO - codeparrot_training - Step 3765: {'lr': 0.0004998245614836802, 'samples': 1928192, 'steps': 3765, 'loss/train': 2.908205270767212}
-03/03/2022 17:50:28 - INFO - codeparrot_training - Step 3766: {'lr': 0.0004998243626534655, 'samples': 1928704, 'steps': 3766, 'loss/train': 2.2812976837158203}
-03/03/2022 17:50:31 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/03/2022 17:50:34 - INFO - codeparrot_training - Step 3767: {'lr': 0.0004998241637106836, 'samples': 1929216, 'steps': 3767, 'loss/train': 2.5964865684509277}
-03/03/2022 17:50:37 - INFO - codeparrot_training - Step 3768: {'lr': 0.0004998239646553349, 'samples': 1929728, 'steps': 3768, 'loss/train': 2.180405616760254}
-03/03/2022 17:50:39 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/03/2022 17:50:43 - INFO - codeparrot_training - Step 3769: {'lr': 0.0004998237654874195, 'samples': 1930240, 'steps': 3769, 'loss/train': 3.5195956230163574}
-03/03/2022 17:50:46 - INFO - codeparrot_training - Step 3770: {'lr': 0.0004998235662069372, 'samples': 1930752, 'steps': 3770, 'loss/train': 1.7296557426452637}
-03/03/2022 17:50:49 - INFO - codeparrot_training - Step 3771: {'lr': 0.0004998233668138883, 'samples': 1931264, 'steps': 3771, 'loss/train': 2.9200501441955566}
-03/03/2022 17:50:52 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/03/2022 17:50:55 - INFO - codeparrot_training - Step 3772: {'lr': 0.0004998231673082729, 'samples': 1931776, 'steps': 3772, 'loss/train': 3.0159971714019775}
-03/03/2022 17:50:58 - INFO - codeparrot_training - Step 3773: {'lr': 0.000499822967690091, 'samples': 1932288, 'steps': 3773, 'loss/train': 2.8896706104278564}
-03/03/2022 17:51:00 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/03/2022 17:51:03 - INFO - codeparrot_training - Step 3774: {'lr': 0.0004998227679593426, 'samples': 1932800, 'steps': 3774, 'loss/train': 2.543423652648926}
-03/03/2022 17:51:06 - INFO - codeparrot_training - Step 3775: {'lr': 0.0004998225681160281, 'samples': 1933312, 'steps': 3775, 'loss/train': 2.5930213928222656}
-03/03/2022 17:51:09 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/03/2022 17:51:11 - INFO - codeparrot_training - Step 3776: {'lr': 0.0004998223681601474, 'samples': 1933824, 'steps': 3776, 'loss/train': 2.8261871337890625}
-03/03/2022 17:51:15 - INFO - codeparrot_training - Step 3777: {'lr': 0.0004998221680917004, 'samples': 1934336, 'steps': 3777, 'loss/train': 1.3928354978561401}
-03/03/2022 17:51:18 - INFO - codeparrot_training - Step 3778: {'lr': 0.0004998219679106876, 'samples': 1934848, 'steps': 3778, 'loss/train': 2.0770843029022217}
-03/03/2022 17:51:18 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/03/2022 17:51:23 - INFO - codeparrot_training - Step 3779: {'lr': 0.0004998217676171088, 'samples': 1935360, 'steps': 3779, 'loss/train': 2.2479074001312256}
-03/03/2022 17:51:26 - INFO - codeparrot_training - Step 3780: {'lr': 0.0004998215672109641, 'samples': 1935872, 'steps': 3780, 'loss/train': 2.635571002960205}
-03/03/2022 17:51:26 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/03/2022 17:51:32 - INFO - codeparrot_training - Step 3781: {'lr': 0.0004998213666922537, 'samples': 1936384, 'steps': 3781, 'loss/train': 2.527639627456665}
-03/03/2022 17:51:34 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/03/2022 17:51:37 - INFO - codeparrot_training - Step 3782: {'lr': 0.0004998211660609777, 'samples': 1936896, 'steps': 3782, 'loss/train': 2.7919180393218994}
-03/03/2022 17:51:40 - INFO - codeparrot_training - Step 3783: {'lr': 0.0004998209653171361, 'samples': 1937408, 'steps': 3783, 'loss/train': 2.786320209503174}
-03/03/2022 17:51:42 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/03/2022 17:51:46 - INFO - codeparrot_training - Step 3784: {'lr': 0.0004998207644607291, 'samples': 1937920, 'steps': 3784, 'loss/train': 1.423477053642273}
-03/03/2022 17:51:49 - INFO - codeparrot_training - Step 3785: {'lr': 0.0004998205634917566, 'samples': 1938432, 'steps': 3785, 'loss/train': 2.622469663619995}
-03/03/2022 17:51:52 - INFO - codeparrot_training - Step 3786: {'lr': 0.0004998203624102188, 'samples': 1938944, 'steps': 3786, 'loss/train': 2.874709367752075}
-03/03/2022 17:51:52 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/03/2022 17:51:57 - INFO - codeparrot_training - Step 3787: {'lr': 0.0004998201612161159, 'samples': 1939456, 'steps': 3787, 'loss/train': 2.402019500732422}
-03/03/2022 17:52:00 - INFO - codeparrot_training - Step 3788: {'lr': 0.0004998199599094478, 'samples': 1939968, 'steps': 3788, 'loss/train': 2.9784326553344727}
-03/03/2022 17:52:01 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/03/2022 17:52:05 - INFO - codeparrot_training - Step 3789: {'lr': 0.0004998197584902147, 'samples': 1940480, 'steps': 3789, 'loss/train': 2.2643918991088867}
-03/03/2022 17:52:09 - INFO - codeparrot_training - Step 3790: {'lr': 0.0004998195569584168, 'samples': 1940992, 'steps': 3790, 'loss/train': 2.488447666168213}
-03/03/2022 17:52:09 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/03/2022 17:52:14 - INFO - codeparrot_training - Step 3791: {'lr': 0.0004998193553140539, 'samples': 1941504, 'steps': 3791, 'loss/train': 2.5369577407836914}
-03/03/2022 17:52:17 - INFO - codeparrot_training - Step 3792: {'lr': 0.0004998191535571264, 'samples': 1942016, 'steps': 3792, 'loss/train': 3.69472336769104}
-03/03/2022 17:52:17 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/03/2022 17:52:22 - INFO - codeparrot_training - Step 3793: {'lr': 0.0004998189516876342, 'samples': 1942528, 'steps': 3793, 'loss/train': 2.4994587898254395}
-03/03/2022 17:52:25 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/03/2022 17:52:28 - INFO - codeparrot_training - Step 3794: {'lr': 0.0004998187497055773, 'samples': 1943040, 'steps': 3794, 'loss/train': 3.082371234893799}
-03/03/2022 17:52:31 - INFO - codeparrot_training - Step 3795: {'lr': 0.000499818547610956, 'samples': 1943552, 'steps': 3795, 'loss/train': 3.0740747451782227}
-03/03/2022 17:52:34 - INFO - codeparrot_training - Step 3796: {'lr': 0.0004998183454037703, 'samples': 1944064, 'steps': 3796, 'loss/train': 2.5580010414123535}
-03/03/2022 17:52:34 - INFO - codeparrot_training - Skipping example with length 158 (seq_length=1024)
-03/03/2022 17:52:39 - INFO - codeparrot_training - Step 3797: {'lr': 0.0004998181430840204, 'samples': 1944576, 'steps': 3797, 'loss/train': 2.9097588062286377}
-03/03/2022 17:52:42 - INFO - codeparrot_training - Step 3798: {'lr': 0.0004998179406517063, 'samples': 1945088, 'steps': 3798, 'loss/train': 2.571601152420044}
-03/03/2022 17:52:43 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/03/2022 17:52:48 - INFO - codeparrot_training - Step 3799: {'lr': 0.000499817738106828, 'samples': 1945600, 'steps': 3799, 'loss/train': 2.3581387996673584}
-03/03/2022 17:52:51 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/03/2022 17:52:53 - INFO - codeparrot_training - Step 3800: {'lr': 0.0004998175354493857, 'samples': 1946112, 'steps': 3800, 'loss/train': 3.021977186203003}
-03/03/2022 17:52:56 - INFO - codeparrot_training - Step 3801: {'lr': 0.0004998173326793795, 'samples': 1946624, 'steps': 3801, 'loss/train': 3.525871515274048}
-03/03/2022 17:52:59 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/03/2022 17:53:02 - INFO - codeparrot_training - Step 3802: {'lr': 0.0004998171297968095, 'samples': 1947136, 'steps': 3802, 'loss/train': 1.9012943506240845}
-03/03/2022 17:53:05 - INFO - codeparrot_training - Step 3803: {'lr': 0.0004998169268016757, 'samples': 1947648, 'steps': 3803, 'loss/train': 1.8721492290496826}
-03/03/2022 17:53:08 - INFO - codeparrot_training - Step 3804: {'lr': 0.0004998167236939783, 'samples': 1948160, 'steps': 3804, 'loss/train': 3.524681806564331}
-03/03/2022 17:53:08 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/03/2022 17:53:13 - INFO - codeparrot_training - Step 3805: {'lr': 0.0004998165204737173, 'samples': 1948672, 'steps': 3805, 'loss/train': 2.6027891635894775}
-03/03/2022 17:53:16 - INFO - codeparrot_training - Step 3806: {'lr': 0.0004998163171408928, 'samples': 1949184, 'steps': 3806, 'loss/train': 2.059025287628174}
-03/03/2022 17:53:16 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/03/2022 17:53:21 - INFO - codeparrot_training - Step 3807: {'lr': 0.000499816113695505, 'samples': 1949696, 'steps': 3807, 'loss/train': 2.747498035430908}
-03/03/2022 17:53:25 - INFO - codeparrot_training - Step 3808: {'lr': 0.0004998159101375538, 'samples': 1950208, 'steps': 3808, 'loss/train': 3.2909584045410156}
-03/03/2022 17:53:25 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 17:53:30 - INFO - codeparrot_training - Step 3809: {'lr': 0.0004998157064670395, 'samples': 1950720, 'steps': 3809, 'loss/train': 2.8653724193573}
-03/03/2022 17:53:33 - INFO - codeparrot_training - Step 3810: {'lr': 0.0004998155026839621, 'samples': 1951232, 'steps': 3810, 'loss/train': 2.820488214492798}
-03/03/2022 17:53:34 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/03/2022 17:53:38 - INFO - codeparrot_training - Step 3811: {'lr': 0.0004998152987883217, 'samples': 1951744, 'steps': 3811, 'loss/train': 2.5435593128204346}
-03/03/2022 17:53:41 - INFO - codeparrot_training - Step 3812: {'lr': 0.0004998150947801182, 'samples': 1952256, 'steps': 3812, 'loss/train': 1.3595515489578247}
-03/03/2022 17:53:42 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/03/2022 17:53:47 - INFO - codeparrot_training - Step 3813: {'lr': 0.000499814890659352, 'samples': 1952768, 'steps': 3813, 'loss/train': 1.7683148384094238}
-03/03/2022 17:53:50 - INFO - codeparrot_training - Step 3814: {'lr': 0.0004998146864260231, 'samples': 1953280, 'steps': 3814, 'loss/train': 2.640709638595581}
-03/03/2022 17:53:50 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/03/2022 17:53:55 - INFO - codeparrot_training - Step 3815: {'lr': 0.0004998144820801316, 'samples': 1953792, 'steps': 3815, 'loss/train': 2.3973660469055176}
-03/03/2022 17:53:58 - INFO - codeparrot_training - Step 3816: {'lr': 0.0004998142776216775, 'samples': 1954304, 'steps': 3816, 'loss/train': 3.3172028064727783}
-03/03/2022 17:53:59 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/03/2022 17:54:04 - INFO - codeparrot_training - Step 3817: {'lr': 0.0004998140730506609, 'samples': 1954816, 'steps': 3817, 'loss/train': 3.212907314300537}
-03/03/2022 17:54:07 - INFO - codeparrot_training - Step 3818: {'lr': 0.000499813868367082, 'samples': 1955328, 'steps': 3818, 'loss/train': 2.394165277481079}
-03/03/2022 17:54:08 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/03/2022 17:54:12 - INFO - codeparrot_training - Step 3819: {'lr': 0.0004998136635709408, 'samples': 1955840, 'steps': 3819, 'loss/train': 2.162062406539917}
-03/03/2022 17:54:15 - INFO - codeparrot_training - Step 3820: {'lr': 0.0004998134586622374, 'samples': 1956352, 'steps': 3820, 'loss/train': 2.444108724594116}
-03/03/2022 17:54:17 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/03/2022 17:54:21 - INFO - codeparrot_training - Step 3821: {'lr': 0.0004998132536409718, 'samples': 1956864, 'steps': 3821, 'loss/train': 2.7850687503814697}
-03/03/2022 17:54:24 - INFO - codeparrot_training - Step 3822: {'lr': 0.0004998130485071444, 'samples': 1957376, 'steps': 3822, 'loss/train': 3.0810601711273193}
-03/03/2022 17:54:25 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/03/2022 17:54:29 - INFO - codeparrot_training - Step 3823: {'lr': 0.000499812843260755, 'samples': 1957888, 'steps': 3823, 'loss/train': 3.0379748344421387}
-03/03/2022 17:54:32 - INFO - codeparrot_training - Step 3824: {'lr': 0.0004998126379018038, 'samples': 1958400, 'steps': 3824, 'loss/train': 2.047121524810791}
-03/03/2022 17:54:33 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/03/2022 17:54:37 - INFO - codeparrot_training - Step 3825: {'lr': 0.000499812432430291, 'samples': 1958912, 'steps': 3825, 'loss/train': 0.3185496926307678}
-03/03/2022 17:54:41 - INFO - codeparrot_training - Step 3826: {'lr': 0.0004998122268462164, 'samples': 1959424, 'steps': 3826, 'loss/train': 1.8392993211746216}
-03/03/2022 17:54:42 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/03/2022 17:54:46 - INFO - codeparrot_training - Step 3827: {'lr': 0.0004998120211495803, 'samples': 1959936, 'steps': 3827, 'loss/train': 2.8945508003234863}
-03/03/2022 17:54:49 - INFO - codeparrot_training - Step 3828: {'lr': 0.0004998118153403827, 'samples': 1960448, 'steps': 3828, 'loss/train': 3.3008294105529785}
-03/03/2022 17:54:50 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/03/2022 17:54:54 - INFO - codeparrot_training - Step 3829: {'lr': 0.0004998116094186239, 'samples': 1960960, 'steps': 3829, 'loss/train': 2.9008419513702393}
-03/03/2022 17:54:57 - INFO - codeparrot_training - Step 3830: {'lr': 0.0004998114033843038, 'samples': 1961472, 'steps': 3830, 'loss/train': 2.5601296424865723}
-03/03/2022 17:54:59 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/03/2022 17:55:03 - INFO - codeparrot_training - Step 3831: {'lr': 0.0004998111972374225, 'samples': 1961984, 'steps': 3831, 'loss/train': 2.9485204219818115}
-03/03/2022 17:55:06 - INFO - codeparrot_training - Step 3832: {'lr': 0.0004998109909779801, 'samples': 1962496, 'steps': 3832, 'loss/train': 3.3430233001708984}
-03/03/2022 17:55:07 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/03/2022 17:55:11 - INFO - codeparrot_training - Step 3833: {'lr': 0.0004998107846059768, 'samples': 1963008, 'steps': 3833, 'loss/train': 2.8167989253997803}
-03/03/2022 17:55:14 - INFO - codeparrot_training - Step 3834: {'lr': 0.0004998105781214126, 'samples': 1963520, 'steps': 3834, 'loss/train': 2.5883312225341797}
-03/03/2022 17:55:15 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/03/2022 17:55:20 - INFO - codeparrot_training - Step 3835: {'lr': 0.0004998103715242875, 'samples': 1964032, 'steps': 3835, 'loss/train': 1.0971472263336182}
-03/03/2022 17:55:23 - INFO - codeparrot_training - Step 3836: {'lr': 0.0004998101648146018, 'samples': 1964544, 'steps': 3836, 'loss/train': 2.96157169342041}
-03/03/2022 17:55:24 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/03/2022 17:55:28 - INFO - codeparrot_training - Step 3837: {'lr': 0.0004998099579923555, 'samples': 1965056, 'steps': 3837, 'loss/train': 3.068044662475586}
-03/03/2022 17:55:31 - INFO - codeparrot_training - Step 3838: {'lr': 0.0004998097510575487, 'samples': 1965568, 'steps': 3838, 'loss/train': 3.1705379486083984}
-03/03/2022 17:55:32 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/03/2022 17:55:36 - INFO - codeparrot_training - Step 3839: {'lr': 0.0004998095440101815, 'samples': 1966080, 'steps': 3839, 'loss/train': 2.1022558212280273}
-03/03/2022 17:55:40 - INFO - codeparrot_training - Step 3840: {'lr': 0.0004998093368502539, 'samples': 1966592, 'steps': 3840, 'loss/train': 1.828479528427124}
-03/03/2022 17:55:40 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/03/2022 17:55:45 - INFO - codeparrot_training - Step 3841: {'lr': 0.000499809129577766, 'samples': 1967104, 'steps': 3841, 'loss/train': 3.0751326084136963}
-03/03/2022 17:55:48 - INFO - codeparrot_training - Step 3842: {'lr': 0.0004998089221927182, 'samples': 1967616, 'steps': 3842, 'loss/train': 3.1886119842529297}
-03/03/2022 17:55:49 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/03/2022 17:55:53 - INFO - codeparrot_training - Step 3843: {'lr': 0.0004998087146951101, 'samples': 1968128, 'steps': 3843, 'loss/train': 2.654568910598755}
-03/03/2022 17:55:56 - INFO - codeparrot_training - Step 3844: {'lr': 0.0004998085070849422, 'samples': 1968640, 'steps': 3844, 'loss/train': 2.970553398132324}
-03/03/2022 17:55:57 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/03/2022 17:56:02 - INFO - codeparrot_training - Step 3845: {'lr': 0.0004998082993622144, 'samples': 1969152, 'steps': 3845, 'loss/train': 2.4194540977478027}
-03/03/2022 17:56:05 - INFO - codeparrot_training - Step 3846: {'lr': 0.0004998080915269268, 'samples': 1969664, 'steps': 3846, 'loss/train': 2.6159262657165527}
-03/03/2022 17:56:05 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/03/2022 17:56:10 - INFO - codeparrot_training - Step 3847: {'lr': 0.0004998078835790796, 'samples': 1970176, 'steps': 3847, 'loss/train': 2.8778598308563232}
-03/03/2022 17:56:13 - INFO - codeparrot_training - Step 3848: {'lr': 0.0004998076755186727, 'samples': 1970688, 'steps': 3848, 'loss/train': 1.1561795473098755}
-03/03/2022 17:56:14 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/03/2022 17:56:18 - INFO - codeparrot_training - Step 3849: {'lr': 0.0004998074673457064, 'samples': 1971200, 'steps': 3849, 'loss/train': 2.9131720066070557}
-03/03/2022 17:56:22 - INFO - codeparrot_training - Step 3850: {'lr': 0.0004998072590601808, 'samples': 1971712, 'steps': 3850, 'loss/train': 2.3436501026153564}
-03/03/2022 17:56:22 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/03/2022 17:56:27 - INFO - codeparrot_training - Step 3851: {'lr': 0.0004998070506620957, 'samples': 1972224, 'steps': 3851, 'loss/train': 3.272664785385132}
-03/03/2022 17:56:30 - INFO - codeparrot_training - Step 3852: {'lr': 0.0004998068421514515, 'samples': 1972736, 'steps': 3852, 'loss/train': 1.823011040687561}
-03/03/2022 17:56:30 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/03/2022 17:56:35 - INFO - codeparrot_training - Step 3853: {'lr': 0.0004998066335282483, 'samples': 1973248, 'steps': 3853, 'loss/train': 2.1942403316497803}
-03/03/2022 17:56:39 - INFO - codeparrot_training - Step 3854: {'lr': 0.0004998064247924859, 'samples': 1973760, 'steps': 3854, 'loss/train': 2.3646399974823}
-03/03/2022 17:56:39 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/03/2022 17:56:44 - INFO - codeparrot_training - Step 3855: {'lr': 0.0004998062159441648, 'samples': 1974272, 'steps': 3855, 'loss/train': 2.4217517375946045}
-03/03/2022 17:56:47 - INFO - codeparrot_training - Step 3856: {'lr': 0.0004998060069832846, 'samples': 1974784, 'steps': 3856, 'loss/train': 2.312204599380493}
-03/03/2022 17:56:47 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/03/2022 17:56:53 - INFO - codeparrot_training - Step 3857: {'lr': 0.0004998057979098459, 'samples': 1975296, 'steps': 3857, 'loss/train': 2.196375608444214}
-03/03/2022 17:56:56 - INFO - codeparrot_training - Step 3858: {'lr': 0.0004998055887238485, 'samples': 1975808, 'steps': 3858, 'loss/train': 2.5646989345550537}
-03/03/2022 17:56:56 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/03/2022 17:57:01 - INFO - codeparrot_training - Step 3859: {'lr': 0.0004998053794252925, 'samples': 1976320, 'steps': 3859, 'loss/train': 2.4142074584960938}
-03/03/2022 17:57:04 - INFO - codeparrot_training - Step 3860: {'lr': 0.0004998051700141781, 'samples': 1976832, 'steps': 3860, 'loss/train': 1.6763968467712402}
-03/03/2022 17:57:05 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/03/2022 17:57:09 - INFO - codeparrot_training - Step 3861: {'lr': 0.0004998049604905052, 'samples': 1977344, 'steps': 3861, 'loss/train': 2.0136899948120117}
-03/03/2022 17:57:13 - INFO - codeparrot_training - Step 3862: {'lr': 0.0004998047508542742, 'samples': 1977856, 'steps': 3862, 'loss/train': 2.0031094551086426}
-03/03/2022 17:57:13 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/03/2022 17:57:18 - INFO - codeparrot_training - Step 3863: {'lr': 0.000499804541105485, 'samples': 1978368, 'steps': 3863, 'loss/train': 2.8693439960479736}
-03/03/2022 17:57:21 - INFO - codeparrot_training - Step 3864: {'lr': 0.0004998043312441378, 'samples': 1978880, 'steps': 3864, 'loss/train': 1.8378208875656128}
-03/03/2022 17:57:21 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/03/2022 17:57:26 - INFO - codeparrot_training - Step 3865: {'lr': 0.0004998041212702325, 'samples': 1979392, 'steps': 3865, 'loss/train': 3.6412179470062256}
-03/03/2022 17:57:29 - INFO - codeparrot_training - Step 3866: {'lr': 0.0004998039111837694, 'samples': 1979904, 'steps': 3866, 'loss/train': 3.0094830989837646}
-03/03/2022 17:57:30 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/03/2022 17:57:35 - INFO - codeparrot_training - Step 3867: {'lr': 0.0004998037009847485, 'samples': 1980416, 'steps': 3867, 'loss/train': 2.71376895904541}
-03/03/2022 17:57:38 - INFO - codeparrot_training - Step 3868: {'lr': 0.0004998034906731699, 'samples': 1980928, 'steps': 3868, 'loss/train': 1.7196274995803833}
-03/03/2022 17:57:38 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/03/2022 17:57:43 - INFO - codeparrot_training - Step 3869: {'lr': 0.0004998032802490337, 'samples': 1981440, 'steps': 3869, 'loss/train': 3.5652031898498535}
-03/03/2022 17:57:46 - INFO - codeparrot_training - Step 3870: {'lr': 0.0004998030697123399, 'samples': 1981952, 'steps': 3870, 'loss/train': 2.986319065093994}
-03/03/2022 17:57:47 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/03/2022 17:57:52 - INFO - codeparrot_training - Step 3871: {'lr': 0.0004998028590630887, 'samples': 1982464, 'steps': 3871, 'loss/train': 3.1613736152648926}
-03/03/2022 17:57:55 - INFO - codeparrot_training - Step 3872: {'lr': 0.0004998026483012803, 'samples': 1982976, 'steps': 3872, 'loss/train': 2.6749696731567383}
-03/03/2022 17:57:56 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/03/2022 17:58:00 - INFO - codeparrot_training - Step 3873: {'lr': 0.0004998024374269147, 'samples': 1983488, 'steps': 3873, 'loss/train': 3.0051774978637695}
-03/03/2022 17:58:03 - INFO - codeparrot_training - Step 3874: {'lr': 0.000499802226439992, 'samples': 1984000, 'steps': 3874, 'loss/train': 1.8445782661437988}
-03/03/2022 17:58:04 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/03/2022 17:58:09 - INFO - codeparrot_training - Step 3875: {'lr': 0.0004998020153405121, 'samples': 1984512, 'steps': 3875, 'loss/train': 2.854663848876953}
-03/03/2022 17:58:12 - INFO - codeparrot_training - Step 3876: {'lr': 0.0004998018041284754, 'samples': 1985024, 'steps': 3876, 'loss/train': 2.5668838024139404}
-03/03/2022 17:58:13 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/03/2022 17:58:17 - INFO - codeparrot_training - Step 3877: {'lr': 0.0004998015928038819, 'samples': 1985536, 'steps': 3877, 'loss/train': 2.474461317062378}
-03/03/2022 17:58:20 - INFO - codeparrot_training - Step 3878: {'lr': 0.0004998013813667315, 'samples': 1986048, 'steps': 3878, 'loss/train': 2.9251227378845215}
-03/03/2022 17:58:21 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/03/2022 17:58:26 - INFO - codeparrot_training - Step 3879: {'lr': 0.0004998011698170245, 'samples': 1986560, 'steps': 3879, 'loss/train': 0.40676942467689514}
-03/03/2022 17:58:29 - INFO - codeparrot_training - Step 3880: {'lr': 0.000499800958154761, 'samples': 1987072, 'steps': 3880, 'loss/train': 2.4557044506073}
-03/03/2022 17:58:29 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/03/2022 17:58:34 - INFO - codeparrot_training - Step 3881: {'lr': 0.000499800746379941, 'samples': 1987584, 'steps': 3881, 'loss/train': 2.256380796432495}
-03/03/2022 17:58:37 - INFO - codeparrot_training - Step 3882: {'lr': 0.0004998005344925647, 'samples': 1988096, 'steps': 3882, 'loss/train': 2.2377755641937256}
-03/03/2022 17:58:38 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 17:58:42 - INFO - codeparrot_training - Step 3883: {'lr': 0.0004998003224926321, 'samples': 1988608, 'steps': 3883, 'loss/train': 0.9866228103637695}
-03/03/2022 17:58:46 - INFO - codeparrot_training - Step 3884: {'lr': 0.0004998001103801433, 'samples': 1989120, 'steps': 3884, 'loss/train': 2.723963499069214}
-03/03/2022 17:58:46 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/03/2022 17:58:51 - INFO - codeparrot_training - Step 3885: {'lr': 0.0004997998981550985, 'samples': 1989632, 'steps': 3885, 'loss/train': 2.6290078163146973}
-03/03/2022 17:58:54 - INFO - codeparrot_training - Step 3886: {'lr': 0.0004997996858174976, 'samples': 1990144, 'steps': 3886, 'loss/train': 2.634025812149048}
-03/03/2022 17:58:54 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/03/2022 17:58:59 - INFO - codeparrot_training - Step 3887: {'lr': 0.0004997994733673409, 'samples': 1990656, 'steps': 3887, 'loss/train': 2.3399627208709717}
-03/03/2022 17:59:02 - INFO - codeparrot_training - Step 3888: {'lr': 0.0004997992608046283, 'samples': 1991168, 'steps': 3888, 'loss/train': 2.6446616649627686}
-03/03/2022 17:59:03 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/03/2022 17:59:08 - INFO - codeparrot_training - Step 3889: {'lr': 0.0004997990481293602, 'samples': 1991680, 'steps': 3889, 'loss/train': 2.5382840633392334}
-03/03/2022 17:59:11 - INFO - codeparrot_training - Step 3890: {'lr': 0.0004997988353415364, 'samples': 1992192, 'steps': 3890, 'loss/train': 2.7250001430511475}
-03/03/2022 17:59:11 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/03/2022 17:59:16 - INFO - codeparrot_training - Step 3891: {'lr': 0.0004997986224411571, 'samples': 1992704, 'steps': 3891, 'loss/train': 2.8453969955444336}
-03/03/2022 17:59:19 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/03/2022 17:59:21 - INFO - codeparrot_training - Step 3892: {'lr': 0.0004997984094282224, 'samples': 1993216, 'steps': 3892, 'loss/train': 3.0485970973968506}
-03/03/2022 17:59:25 - INFO - codeparrot_training - Step 3893: {'lr': 0.0004997981963027324, 'samples': 1993728, 'steps': 3893, 'loss/train': 2.819335460662842}
-03/03/2022 17:59:27 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/03/2022 17:59:30 - INFO - codeparrot_training - Step 3894: {'lr': 0.0004997979830646871, 'samples': 1994240, 'steps': 3894, 'loss/train': 2.3712048530578613}
-03/03/2022 17:59:33 - INFO - codeparrot_training - Step 3895: {'lr': 0.0004997977697140868, 'samples': 1994752, 'steps': 3895, 'loss/train': 3.0491459369659424}
-03/03/2022 17:59:36 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/03/2022 17:59:38 - INFO - codeparrot_training - Step 3896: {'lr': 0.0004997975562509315, 'samples': 1995264, 'steps': 3896, 'loss/train': 2.762273073196411}
-03/03/2022 17:59:41 - INFO - codeparrot_training - Step 3897: {'lr': 0.0004997973426752212, 'samples': 1995776, 'steps': 3897, 'loss/train': 2.7730660438537598}
-03/03/2022 17:59:44 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/03/2022 17:59:47 - INFO - codeparrot_training - Step 3898: {'lr': 0.0004997971289869561, 'samples': 1996288, 'steps': 3898, 'loss/train': 2.130523204803467}
-03/03/2022 17:59:50 - INFO - codeparrot_training - Step 3899: {'lr': 0.0004997969151861362, 'samples': 1996800, 'steps': 3899, 'loss/train': 2.766228199005127}
-03/03/2022 17:59:52 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/03/2022 17:59:55 - INFO - codeparrot_training - Step 3900: {'lr': 0.0004997967012727618, 'samples': 1997312, 'steps': 3900, 'loss/train': 2.325099468231201}
-03/03/2022 17:59:58 - INFO - codeparrot_training - Step 3901: {'lr': 0.0004997964872468327, 'samples': 1997824, 'steps': 3901, 'loss/train': 3.279083490371704}
-03/03/2022 18:00:01 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/03/2022 18:00:04 - INFO - codeparrot_training - Step 3902: {'lr': 0.0004997962731083492, 'samples': 1998336, 'steps': 3902, 'loss/train': 2.196179151535034}
-03/03/2022 18:00:07 - INFO - codeparrot_training - Step 3903: {'lr': 0.0004997960588573115, 'samples': 1998848, 'steps': 3903, 'loss/train': 2.9831697940826416}
-03/03/2022 18:00:09 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/03/2022 18:00:12 - INFO - codeparrot_training - Step 3904: {'lr': 0.0004997958444937193, 'samples': 1999360, 'steps': 3904, 'loss/train': 2.906731128692627}
-03/03/2022 18:00:15 - INFO - codeparrot_training - Step 3905: {'lr': 0.0004997956300175732, 'samples': 1999872, 'steps': 3905, 'loss/train': 2.383371114730835}
-03/03/2022 18:00:18 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/03/2022 18:00:21 - INFO - codeparrot_training - Step 3906: {'lr': 0.000499795415428873, 'samples': 2000384, 'steps': 3906, 'loss/train': 3.246926784515381}
-03/03/2022 18:00:24 - INFO - codeparrot_training - Step 3907: {'lr': 0.0004997952007276187, 'samples': 2000896, 'steps': 3907, 'loss/train': 3.258622407913208}
-03/03/2022 18:00:26 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/03/2022 18:00:29 - INFO - codeparrot_training - Step 3908: {'lr': 0.0004997949859138106, 'samples': 2001408, 'steps': 3908, 'loss/train': 2.2974727153778076}
-03/03/2022 18:00:32 - INFO - codeparrot_training - Step 3909: {'lr': 0.0004997947709874487, 'samples': 2001920, 'steps': 3909, 'loss/train': 2.8245277404785156}
-03/03/2022 18:00:34 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/03/2022 18:00:37 - INFO - codeparrot_training - Step 3910: {'lr': 0.0004997945559485333, 'samples': 2002432, 'steps': 3910, 'loss/train': 2.5938360691070557}
-03/03/2022 18:00:41 - INFO - codeparrot_training - Step 3911: {'lr': 0.0004997943407970642, 'samples': 2002944, 'steps': 3911, 'loss/train': 2.3936986923217773}
-03/03/2022 18:00:43 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/03/2022 18:00:46 - INFO - codeparrot_training - Step 3912: {'lr': 0.0004997941255330416, 'samples': 2003456, 'steps': 3912, 'loss/train': 2.5845417976379395}
-03/03/2022 18:00:49 - INFO - codeparrot_training - Step 3913: {'lr': 0.0004997939101564656, 'samples': 2003968, 'steps': 3913, 'loss/train': 2.7111804485321045}
-03/03/2022 18:00:52 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/03/2022 18:00:55 - INFO - codeparrot_training - Step 3914: {'lr': 0.0004997936946673365, 'samples': 2004480, 'steps': 3914, 'loss/train': 2.2483110427856445}
-03/03/2022 18:00:58 - INFO - codeparrot_training - Step 3915: {'lr': 0.000499793479065654, 'samples': 2004992, 'steps': 3915, 'loss/train': 2.495793342590332}
-03/03/2022 18:01:00 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/03/2022 18:01:03 - INFO - codeparrot_training - Step 3916: {'lr': 0.0004997932633514185, 'samples': 2005504, 'steps': 3916, 'loss/train': 2.491365671157837}
-03/03/2022 18:01:06 - INFO - codeparrot_training - Step 3917: {'lr': 0.00049979304752463, 'samples': 2006016, 'steps': 3917, 'loss/train': 2.1895015239715576}
-03/03/2022 18:01:09 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/03/2022 18:01:11 - INFO - codeparrot_training - Step 3918: {'lr': 0.0004997928315852887, 'samples': 2006528, 'steps': 3918, 'loss/train': 2.1218948364257812}
-03/03/2022 18:01:15 - INFO - codeparrot_training - Step 3919: {'lr': 0.0004997926155333944, 'samples': 2007040, 'steps': 3919, 'loss/train': 3.1267402172088623}
-03/03/2022 18:01:17 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/03/2022 18:01:20 - INFO - codeparrot_training - Step 3920: {'lr': 0.0004997923993689476, 'samples': 2007552, 'steps': 3920, 'loss/train': 1.7067797183990479}
-03/03/2022 18:01:23 - INFO - codeparrot_training - Step 3921: {'lr': 0.0004997921830919481, 'samples': 2008064, 'steps': 3921, 'loss/train': 3.328880548477173}
-03/03/2022 18:01:26 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/03/2022 18:01:28 - INFO - codeparrot_training - Step 3922: {'lr': 0.0004997919667023962, 'samples': 2008576, 'steps': 3922, 'loss/train': 1.8148462772369385}
-03/03/2022 18:01:32 - INFO - codeparrot_training - Step 3923: {'lr': 0.0004997917502002917, 'samples': 2009088, 'steps': 3923, 'loss/train': 3.037026882171631}
-03/03/2022 18:01:34 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/03/2022 18:01:37 - INFO - codeparrot_training - Step 3924: {'lr': 0.000499791533585635, 'samples': 2009600, 'steps': 3924, 'loss/train': 1.572440505027771}
-03/03/2022 18:01:40 - INFO - codeparrot_training - Step 3925: {'lr': 0.0004997913168584262, 'samples': 2010112, 'steps': 3925, 'loss/train': 2.2495689392089844}
-03/03/2022 18:01:43 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/03/2022 18:01:45 - INFO - codeparrot_training - Step 3926: {'lr': 0.0004997911000186651, 'samples': 2010624, 'steps': 3926, 'loss/train': 2.544018268585205}
-03/03/2022 18:01:49 - INFO - codeparrot_training - Step 3927: {'lr': 0.0004997908830663521, 'samples': 2011136, 'steps': 3927, 'loss/train': 2.3300535678863525}
-03/03/2022 18:01:51 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/03/2022 18:01:54 - INFO - codeparrot_training - Step 3928: {'lr': 0.0004997906660014871, 'samples': 2011648, 'steps': 3928, 'loss/train': 2.1153769493103027}
-03/03/2022 18:01:57 - INFO - codeparrot_training - Step 3929: {'lr': 0.0004997904488240704, 'samples': 2012160, 'steps': 3929, 'loss/train': 2.5201823711395264}
-03/03/2022 18:02:00 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/03/2022 18:02:02 - INFO - codeparrot_training - Step 3930: {'lr': 0.0004997902315341019, 'samples': 2012672, 'steps': 3930, 'loss/train': 3.689603567123413}
-03/03/2022 18:02:06 - INFO - codeparrot_training - Step 3931: {'lr': 0.0004997900141315817, 'samples': 2013184, 'steps': 3931, 'loss/train': 3.0747292041778564}
-03/03/2022 18:02:08 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/03/2022 18:02:11 - INFO - codeparrot_training - Step 3932: {'lr': 0.0004997897966165101, 'samples': 2013696, 'steps': 3932, 'loss/train': 3.1622369289398193}
-03/03/2022 18:02:14 - INFO - codeparrot_training - Step 3933: {'lr': 0.000499789578988887, 'samples': 2014208, 'steps': 3933, 'loss/train': 2.250472068786621}
-03/03/2022 18:02:16 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/03/2022 18:02:19 - INFO - codeparrot_training - Step 3934: {'lr': 0.0004997893612487126, 'samples': 2014720, 'steps': 3934, 'loss/train': 2.3587052822113037}
-03/03/2022 18:02:22 - INFO - codeparrot_training - Step 3935: {'lr': 0.000499789143395987, 'samples': 2015232, 'steps': 3935, 'loss/train': 2.693073272705078}
-03/03/2022 18:02:24 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/03/2022 18:02:28 - INFO - codeparrot_training - Step 3936: {'lr': 0.0004997889254307103, 'samples': 2015744, 'steps': 3936, 'loss/train': 2.833967447280884}
-03/03/2022 18:02:31 - INFO - codeparrot_training - Step 3937: {'lr': 0.0004997887073528825, 'samples': 2016256, 'steps': 3937, 'loss/train': 1.5553349256515503}
-03/03/2022 18:02:33 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/03/2022 18:02:36 - INFO - codeparrot_training - Step 3938: {'lr': 0.0004997884891625037, 'samples': 2016768, 'steps': 3938, 'loss/train': 2.2556614875793457}
-03/03/2022 18:02:39 - INFO - codeparrot_training - Step 3939: {'lr': 0.0004997882708595742, 'samples': 2017280, 'steps': 3939, 'loss/train': 2.909503698348999}
-03/03/2022 18:02:41 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/03/2022 18:02:45 - INFO - codeparrot_training - Step 3940: {'lr': 0.0004997880524440939, 'samples': 2017792, 'steps': 3940, 'loss/train': 2.662753105163574}
-03/03/2022 18:02:48 - INFO - codeparrot_training - Step 3941: {'lr': 0.0004997878339160628, 'samples': 2018304, 'steps': 3941, 'loss/train': 2.884737253189087}
-03/03/2022 18:02:51 - INFO - codeparrot_training - Step 3942: {'lr': 0.0004997876152754814, 'samples': 2018816, 'steps': 3942, 'loss/train': 3.0503275394439697}
-03/03/2022 18:02:52 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/03/2022 18:02:58 - INFO - codeparrot_training - Step 3943: {'lr': 0.0004997873965223495, 'samples': 2019328, 'steps': 3943, 'loss/train': 2.9102585315704346}
-03/03/2022 18:03:01 - INFO - codeparrot_training - Step 3944: {'lr': 0.0004997871776566672, 'samples': 2019840, 'steps': 3944, 'loss/train': 3.42290997505188}
-03/03/2022 18:03:04 - INFO - codeparrot_training - Step 3945: {'lr': 0.0004997869586784346, 'samples': 2020352, 'steps': 3945, 'loss/train': 1.8006359338760376}
-03/03/2022 18:03:05 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/03/2022 18:03:09 - INFO - codeparrot_training - Step 3946: {'lr': 0.0004997867395876519, 'samples': 2020864, 'steps': 3946, 'loss/train': 3.318176031112671}
-03/03/2022 18:03:12 - INFO - codeparrot_training - Step 3947: {'lr': 0.0004997865203843192, 'samples': 2021376, 'steps': 3947, 'loss/train': 2.8333096504211426}
-03/03/2022 18:03:13 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/03/2022 18:03:17 - INFO - codeparrot_training - Step 3948: {'lr': 0.0004997863010684365, 'samples': 2021888, 'steps': 3948, 'loss/train': 3.0892834663391113}
-03/03/2022 18:03:21 - INFO - codeparrot_training - Step 3949: {'lr': 0.0004997860816400039, 'samples': 2022400, 'steps': 3949, 'loss/train': 4.059104919433594}
-03/03/2022 18:03:21 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/03/2022 18:03:26 - INFO - codeparrot_training - Step 3950: {'lr': 0.0004997858620990217, 'samples': 2022912, 'steps': 3950, 'loss/train': 3.6839346885681152}
-03/03/2022 18:03:29 - INFO - codeparrot_training - Step 3951: {'lr': 0.0004997856424454897, 'samples': 2023424, 'steps': 3951, 'loss/train': 2.158196210861206}
-03/03/2022 18:03:32 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/03/2022 18:03:34 - INFO - codeparrot_training - Step 3952: {'lr': 0.0004997854226794082, 'samples': 2023936, 'steps': 3952, 'loss/train': 3.6836612224578857}
-03/03/2022 18:03:38 - INFO - codeparrot_training - Step 3953: {'lr': 0.0004997852028007772, 'samples': 2024448, 'steps': 3953, 'loss/train': 2.3645546436309814}
-03/03/2022 18:03:40 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/03/2022 18:03:43 - INFO - codeparrot_training - Step 3954: {'lr': 0.0004997849828095969, 'samples': 2024960, 'steps': 3954, 'loss/train': 2.4522507190704346}
-03/03/2022 18:03:46 - INFO - codeparrot_training - Step 3955: {'lr': 0.0004997847627058673, 'samples': 2025472, 'steps': 3955, 'loss/train': 2.9364266395568848}
-03/03/2022 18:03:48 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/03/2022 18:03:51 - INFO - codeparrot_training - Step 3956: {'lr': 0.0004997845424895886, 'samples': 2025984, 'steps': 3956, 'loss/train': 4.080404758453369}
-03/03/2022 18:03:54 - INFO - codeparrot_training - Step 3957: {'lr': 0.0004997843221607607, 'samples': 2026496, 'steps': 3957, 'loss/train': 1.346103310585022}
-03/03/2022 18:03:57 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/03/2022 18:04:00 - INFO - codeparrot_training - Step 3958: {'lr': 0.0004997841017193841, 'samples': 2027008, 'steps': 3958, 'loss/train': 2.2125799655914307}
-03/03/2022 18:04:03 - INFO - codeparrot_training - Step 3959: {'lr': 0.0004997838811654584, 'samples': 2027520, 'steps': 3959, 'loss/train': 2.544726848602295}
-03/03/2022 18:04:05 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/03/2022 18:04:08 - INFO - codeparrot_training - Step 3960: {'lr': 0.000499783660498984, 'samples': 2028032, 'steps': 3960, 'loss/train': 2.5979676246643066}
-03/03/2022 18:04:11 - INFO - codeparrot_training - Step 3961: {'lr': 0.0004997834397199609, 'samples': 2028544, 'steps': 3961, 'loss/train': 2.790780544281006}
-03/03/2022 18:04:13 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/03/2022 18:04:17 - INFO - codeparrot_training - Step 3962: {'lr': 0.0004997832188283893, 'samples': 2029056, 'steps': 3962, 'loss/train': 3.1926486492156982}
-03/03/2022 18:04:20 - INFO - codeparrot_training - Step 3963: {'lr': 0.0004997829978242693, 'samples': 2029568, 'steps': 3963, 'loss/train': 1.3696067333221436}
-03/03/2022 18:04:21 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/03/2022 18:04:25 - INFO - codeparrot_training - Step 3964: {'lr': 0.0004997827767076008, 'samples': 2030080, 'steps': 3964, 'loss/train': 2.9188528060913086}
-03/03/2022 18:04:28 - INFO - codeparrot_training - Step 3965: {'lr': 0.0004997825554783841, 'samples': 2030592, 'steps': 3965, 'loss/train': 2.740131378173828}
-03/03/2022 18:04:30 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/03/2022 18:04:33 - INFO - codeparrot_training - Step 3966: {'lr': 0.0004997823341366192, 'samples': 2031104, 'steps': 3966, 'loss/train': 2.3014016151428223}
-03/03/2022 18:04:37 - INFO - codeparrot_training - Step 3967: {'lr': 0.0004997821126823062, 'samples': 2031616, 'steps': 3967, 'loss/train': 2.4409942626953125}
-03/03/2022 18:04:38 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/03/2022 18:04:42 - INFO - codeparrot_training - Step 3968: {'lr': 0.0004997818911154454, 'samples': 2032128, 'steps': 3968, 'loss/train': 2.6989142894744873}
-03/03/2022 18:04:45 - INFO - codeparrot_training - Step 3969: {'lr': 0.0004997816694360367, 'samples': 2032640, 'steps': 3969, 'loss/train': 3.1979548931121826}
-03/03/2022 18:04:47 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/03/2022 18:04:50 - INFO - codeparrot_training - Step 3970: {'lr': 0.00049978144764408, 'samples': 2033152, 'steps': 3970, 'loss/train': 2.3690061569213867}
-03/03/2022 18:04:53 - INFO - codeparrot_training - Step 3971: {'lr': 0.0004997812257395758, 'samples': 2033664, 'steps': 3971, 'loss/train': 2.812025547027588}
-03/03/2022 18:04:55 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/03/2022 18:04:59 - INFO - codeparrot_training - Step 3972: {'lr': 0.0004997810037225241, 'samples': 2034176, 'steps': 3972, 'loss/train': 3.2775442600250244}
-03/03/2022 18:05:02 - INFO - codeparrot_training - Step 3973: {'lr': 0.0004997807815929248, 'samples': 2034688, 'steps': 3973, 'loss/train': 2.1329185962677}
-03/03/2022 18:05:04 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/03/2022 18:05:07 - INFO - codeparrot_training - Step 3974: {'lr': 0.0004997805593507783, 'samples': 2035200, 'steps': 3974, 'loss/train': 2.7244060039520264}
-03/03/2022 18:05:10 - INFO - codeparrot_training - Step 3975: {'lr': 0.0004997803369960844, 'samples': 2035712, 'steps': 3975, 'loss/train': 1.5863265991210938}
-03/03/2022 18:05:13 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/03/2022 18:05:16 - INFO - codeparrot_training - Step 3976: {'lr': 0.0004997801145288433, 'samples': 2036224, 'steps': 3976, 'loss/train': 2.3796982765197754}
-03/03/2022 18:05:19 - INFO - codeparrot_training - Step 3977: {'lr': 0.0004997798919490553, 'samples': 2036736, 'steps': 3977, 'loss/train': 2.716003894805908}
-03/03/2022 18:05:21 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/03/2022 18:05:24 - INFO - codeparrot_training - Step 3978: {'lr': 0.0004997796692567202, 'samples': 2037248, 'steps': 3978, 'loss/train': 2.5770249366760254}
-03/03/2022 18:05:27 - INFO - codeparrot_training - Step 3979: {'lr': 0.0004997794464518383, 'samples': 2037760, 'steps': 3979, 'loss/train': 1.193472981452942}
-03/03/2022 18:05:29 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/03/2022 18:05:33 - INFO - codeparrot_training - Step 3980: {'lr': 0.0004997792235344096, 'samples': 2038272, 'steps': 3980, 'loss/train': 1.7371487617492676}
-03/03/2022 18:05:36 - INFO - codeparrot_training - Step 3981: {'lr': 0.0004997790005044343, 'samples': 2038784, 'steps': 3981, 'loss/train': 3.5910770893096924}
-03/03/2022 18:05:38 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/03/2022 18:05:41 - INFO - codeparrot_training - Step 3982: {'lr': 0.0004997787773619123, 'samples': 2039296, 'steps': 3982, 'loss/train': 3.1053221225738525}
-03/03/2022 18:05:44 - INFO - codeparrot_training - Step 3983: {'lr': 0.0004997785541068439, 'samples': 2039808, 'steps': 3983, 'loss/train': 2.070878744125366}
-03/03/2022 18:05:46 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/03/2022 18:05:49 - INFO - codeparrot_training - Step 3984: {'lr': 0.0004997783307392292, 'samples': 2040320, 'steps': 3984, 'loss/train': 2.9818992614746094}
-03/03/2022 18:05:52 - INFO - codeparrot_training - Step 3985: {'lr': 0.0004997781072590683, 'samples': 2040832, 'steps': 3985, 'loss/train': 2.1180307865142822}
-03/03/2022 18:05:55 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/03/2022 18:05:58 - INFO - codeparrot_training - Step 3986: {'lr': 0.000499777883666361, 'samples': 2041344, 'steps': 3986, 'loss/train': 3.313664436340332}
-03/03/2022 18:06:01 - INFO - codeparrot_training - Step 3987: {'lr': 0.0004997776599611078, 'samples': 2041856, 'steps': 3987, 'loss/train': 2.0892179012298584}
-03/03/2022 18:06:03 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/03/2022 18:06:06 - INFO - codeparrot_training - Step 3988: {'lr': 0.0004997774361433086, 'samples': 2042368, 'steps': 3988, 'loss/train': 2.44980788230896}
-03/03/2022 18:06:09 - INFO - codeparrot_training - Step 3989: {'lr': 0.0004997772122129635, 'samples': 2042880, 'steps': 3989, 'loss/train': 2.897059202194214}
-03/03/2022 18:06:11 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/03/2022 18:06:14 - INFO - codeparrot_training - Step 3990: {'lr': 0.0004997769881700727, 'samples': 2043392, 'steps': 3990, 'loss/train': 2.5682404041290283}
-03/03/2022 18:06:18 - INFO - codeparrot_training - Step 3991: {'lr': 0.0004997767640146363, 'samples': 2043904, 'steps': 3991, 'loss/train': 3.12326717376709}
-03/03/2022 18:06:19 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/03/2022 18:06:23 - INFO - codeparrot_training - Step 3992: {'lr': 0.0004997765397466543, 'samples': 2044416, 'steps': 3992, 'loss/train': 2.292527914047241}
-03/03/2022 18:06:26 - INFO - codeparrot_training - Step 3993: {'lr': 0.0004997763153661269, 'samples': 2044928, 'steps': 3993, 'loss/train': 1.6879278421401978}
-03/03/2022 18:06:27 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/03/2022 18:06:31 - INFO - codeparrot_training - Step 3994: {'lr': 0.000499776090873054, 'samples': 2045440, 'steps': 3994, 'loss/train': 2.0581037998199463}
-03/03/2022 18:06:34 - INFO - codeparrot_training - Step 3995: {'lr': 0.000499775866267436, 'samples': 2045952, 'steps': 3995, 'loss/train': 2.7551822662353516}
-03/03/2022 18:06:35 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/03/2022 18:06:40 - INFO - codeparrot_training - Step 3996: {'lr': 0.0004997756415492727, 'samples': 2046464, 'steps': 3996, 'loss/train': 1.3939646482467651}
-03/03/2022 18:06:43 - INFO - codeparrot_training - Step 3997: {'lr': 0.0004997754167185644, 'samples': 2046976, 'steps': 3997, 'loss/train': 2.505709409713745}
-03/03/2022 18:06:44 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/03/2022 18:06:48 - INFO - codeparrot_training - Step 3998: {'lr': 0.0004997751917753113, 'samples': 2047488, 'steps': 3998, 'loss/train': 3.190295934677124}
-03/03/2022 18:06:51 - INFO - codeparrot_training - Step 3999: {'lr': 0.0004997749667195132, 'samples': 2048000, 'steps': 3999, 'loss/train': 3.65911602973938}
-03/03/2022 18:06:53 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/03/2022 18:06:56 - INFO - codeparrot_training - Step 4000: {'lr': 0.0004997747415511704, 'samples': 2048512, 'steps': 4000, 'loss/train': 3.273041009902954}
-03/03/2022 18:07:00 - INFO - codeparrot_training - Step 4001: {'lr': 0.000499774516270283, 'samples': 2049024, 'steps': 4001, 'loss/train': 0.6735871434211731}
-03/03/2022 18:07:01 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/03/2022 18:07:05 - INFO - codeparrot_training - Step 4002: {'lr': 0.0004997742908768508, 'samples': 2049536, 'steps': 4002, 'loss/train': 3.193909168243408}
-03/03/2022 18:07:08 - INFO - codeparrot_training - Step 4003: {'lr': 0.0004997740653708744, 'samples': 2050048, 'steps': 4003, 'loss/train': 1.8106073141098022}
-03/03/2022 18:07:09 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/03/2022 18:07:13 - INFO - codeparrot_training - Step 4004: {'lr': 0.0004997738397523537, 'samples': 2050560, 'steps': 4004, 'loss/train': 2.9387056827545166}
-03/03/2022 18:07:16 - INFO - codeparrot_training - Step 4005: {'lr': 0.0004997736140212887, 'samples': 2051072, 'steps': 4005, 'loss/train': 2.4872539043426514}
-03/03/2022 18:07:17 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/03/2022 18:07:22 - INFO - codeparrot_training - Step 4006: {'lr': 0.0004997733881776796, 'samples': 2051584, 'steps': 4006, 'loss/train': 3.0138444900512695}
-03/03/2022 18:07:25 - INFO - codeparrot_training - Step 4007: {'lr': 0.0004997731622215264, 'samples': 2052096, 'steps': 4007, 'loss/train': 3.176285743713379}
-03/03/2022 18:07:26 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/03/2022 18:07:30 - INFO - codeparrot_training - Step 4008: {'lr': 0.0004997729361528292, 'samples': 2052608, 'steps': 4008, 'loss/train': 2.647770881652832}
-03/03/2022 18:07:33 - INFO - codeparrot_training - Step 4009: {'lr': 0.0004997727099715882, 'samples': 2053120, 'steps': 4009, 'loss/train': 2.273289442062378}
-03/03/2022 18:07:34 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/03/2022 18:07:38 - INFO - codeparrot_training - Step 4010: {'lr': 0.0004997724836778036, 'samples': 2053632, 'steps': 4010, 'loss/train': 2.4431509971618652}
-03/03/2022 18:07:41 - INFO - codeparrot_training - Step 4011: {'lr': 0.0004997722572714753, 'samples': 2054144, 'steps': 4011, 'loss/train': 3.5274946689605713}
-03/03/2022 18:07:42 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/03/2022 18:07:47 - INFO - codeparrot_training - Step 4012: {'lr': 0.0004997720307526034, 'samples': 2054656, 'steps': 4012, 'loss/train': 2.285733222961426}
-03/03/2022 18:07:50 - INFO - codeparrot_training - Step 4013: {'lr': 0.0004997718041211881, 'samples': 2055168, 'steps': 4013, 'loss/train': 3.925359010696411}
-03/03/2022 18:07:50 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/03/2022 18:07:55 - INFO - codeparrot_training - Step 4014: {'lr': 0.0004997715773772296, 'samples': 2055680, 'steps': 4014, 'loss/train': 2.8097586631774902}
-03/03/2022 18:07:58 - INFO - codeparrot_training - Step 4015: {'lr': 0.0004997713505207278, 'samples': 2056192, 'steps': 4015, 'loss/train': 2.6443235874176025}
-03/03/2022 18:07:58 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/03/2022 18:08:04 - INFO - codeparrot_training - Step 4016: {'lr': 0.0004997711235516829, 'samples': 2056704, 'steps': 4016, 'loss/train': 2.697261333465576}
-03/03/2022 18:08:07 - INFO - codeparrot_training - Step 4017: {'lr': 0.000499770896470095, 'samples': 2057216, 'steps': 4017, 'loss/train': 2.3651421070098877}
-03/03/2022 18:08:07 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/03/2022 18:08:12 - INFO - codeparrot_training - Step 4018: {'lr': 0.0004997706692759642, 'samples': 2057728, 'steps': 4018, 'loss/train': 2.331338405609131}
-03/03/2022 18:08:15 - INFO - codeparrot_training - Step 4019: {'lr': 0.0004997704419692905, 'samples': 2058240, 'steps': 4019, 'loss/train': 2.53157114982605}
-03/03/2022 18:08:16 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/03/2022 18:08:21 - INFO - codeparrot_training - Step 4020: {'lr': 0.0004997702145500741, 'samples': 2058752, 'steps': 4020, 'loss/train': 1.9059734344482422}
-03/03/2022 18:08:24 - INFO - codeparrot_training - Step 4021: {'lr': 0.0004997699870183151, 'samples': 2059264, 'steps': 4021, 'loss/train': 1.3047473430633545}
-03/03/2022 18:08:24 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/03/2022 18:08:29 - INFO - codeparrot_training - Step 4022: {'lr': 0.0004997697593740137, 'samples': 2059776, 'steps': 4022, 'loss/train': 2.946004629135132}
-03/03/2022 18:08:32 - INFO - codeparrot_training - Step 4023: {'lr': 0.0004997695316171698, 'samples': 2060288, 'steps': 4023, 'loss/train': 1.339981198310852}
-03/03/2022 18:08:33 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/03/2022 18:08:37 - INFO - codeparrot_training - Step 4024: {'lr': 0.0004997693037477837, 'samples': 2060800, 'steps': 4024, 'loss/train': 2.8004448413848877}
-03/03/2022 18:08:41 - INFO - codeparrot_training - Step 4025: {'lr': 0.0004997690757658552, 'samples': 2061312, 'steps': 4025, 'loss/train': 2.155595541000366}
-03/03/2022 18:08:41 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/03/2022 18:08:46 - INFO - codeparrot_training - Step 4026: {'lr': 0.0004997688476713848, 'samples': 2061824, 'steps': 4026, 'loss/train': 2.260622024536133}
-03/03/2022 18:08:49 - INFO - codeparrot_training - Step 4027: {'lr': 0.0004997686194643724, 'samples': 2062336, 'steps': 4027, 'loss/train': 2.6317644119262695}
-03/03/2022 18:08:49 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/03/2022 18:08:54 - INFO - codeparrot_training - Step 4028: {'lr': 0.0004997683911448181, 'samples': 2062848, 'steps': 4028, 'loss/train': 2.65738582611084}
-03/03/2022 18:08:57 - INFO - codeparrot_training - Step 4029: {'lr': 0.000499768162712722, 'samples': 2063360, 'steps': 4029, 'loss/train': 2.319352865219116}
-03/03/2022 18:08:58 - INFO - codeparrot_training - Skipping example with length 385 (seq_length=1024)
-03/03/2022 18:09:03 - INFO - codeparrot_training - Step 4030: {'lr': 0.0004997679341680843, 'samples': 2063872, 'steps': 4030, 'loss/train': 2.180222272872925}
-03/03/2022 18:09:06 - INFO - codeparrot_training - Step 4031: {'lr': 0.0004997677055109049, 'samples': 2064384, 'steps': 4031, 'loss/train': 3.0376524925231934}
-03/03/2022 18:09:06 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/03/2022 18:09:11 - INFO - codeparrot_training - Step 4032: {'lr': 0.0004997674767411841, 'samples': 2064896, 'steps': 4032, 'loss/train': 2.1492767333984375}
-03/03/2022 18:09:14 - INFO - codeparrot_training - Step 4033: {'lr': 0.0004997672478589219, 'samples': 2065408, 'steps': 4033, 'loss/train': 2.4172158241271973}
-03/03/2022 18:09:14 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 18:09:20 - INFO - codeparrot_training - Step 4034: {'lr': 0.0004997670188641183, 'samples': 2065920, 'steps': 4034, 'loss/train': 2.6885666847229004}
-03/03/2022 18:09:23 - INFO - codeparrot_training - Step 4035: {'lr': 0.0004997667897567738, 'samples': 2066432, 'steps': 4035, 'loss/train': 3.269563913345337}
-03/03/2022 18:09:23 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/03/2022 18:09:28 - INFO - codeparrot_training - Step 4036: {'lr': 0.0004997665605368881, 'samples': 2066944, 'steps': 4036, 'loss/train': 2.86141037940979}
-03/03/2022 18:09:31 - INFO - codeparrot_training - Step 4037: {'lr': 0.0004997663312044614, 'samples': 2067456, 'steps': 4037, 'loss/train': 2.443502187728882}
-03/03/2022 18:09:31 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/03/2022 18:09:36 - INFO - codeparrot_training - Step 4038: {'lr': 0.0004997661017594939, 'samples': 2067968, 'steps': 4038, 'loss/train': 2.5220706462860107}
-03/03/2022 18:09:40 - INFO - codeparrot_training - Step 4039: {'lr': 0.0004997658722019857, 'samples': 2068480, 'steps': 4039, 'loss/train': 2.915877103805542}
-03/03/2022 18:09:40 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/03/2022 18:09:45 - INFO - codeparrot_training - Step 4040: {'lr': 0.0004997656425319367, 'samples': 2068992, 'steps': 4040, 'loss/train': 2.5245325565338135}
-03/03/2022 18:09:48 - INFO - codeparrot_training - Step 4041: {'lr': 0.0004997654127493473, 'samples': 2069504, 'steps': 4041, 'loss/train': 2.562852382659912}
-03/03/2022 18:09:48 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/03/2022 18:09:53 - INFO - codeparrot_training - Step 4042: {'lr': 0.0004997651828542173, 'samples': 2070016, 'steps': 4042, 'loss/train': 2.7951602935791016}
-03/03/2022 18:09:56 - INFO - codeparrot_training - Step 4043: {'lr': 0.0004997649528465471, 'samples': 2070528, 'steps': 4043, 'loss/train': 2.896421432495117}
-03/03/2022 18:09:56 - INFO - codeparrot_training - Skipping example with length 7 (seq_length=1024)
-03/03/2022 18:10:02 - INFO - codeparrot_training - Step 4044: {'lr': 0.0004997647227263367, 'samples': 2071040, 'steps': 4044, 'loss/train': 2.4040536880493164}
-03/03/2022 18:10:05 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/03/2022 18:10:07 - INFO - codeparrot_training - Step 4045: {'lr': 0.000499764492493586, 'samples': 2071552, 'steps': 4045, 'loss/train': 2.78424334526062}
-03/03/2022 18:10:10 - INFO - codeparrot_training - Step 4046: {'lr': 0.0004997642621482955, 'samples': 2072064, 'steps': 4046, 'loss/train': 1.5856965780258179}
-03/03/2022 18:10:13 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/03/2022 18:10:15 - INFO - codeparrot_training - Step 4047: {'lr': 0.0004997640316904649, 'samples': 2072576, 'steps': 4047, 'loss/train': 2.806013584136963}
-03/03/2022 18:10:19 - INFO - codeparrot_training - Step 4048: {'lr': 0.0004997638011200946, 'samples': 2073088, 'steps': 4048, 'loss/train': 1.2127141952514648}
-03/03/2022 18:10:21 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/03/2022 18:10:24 - INFO - codeparrot_training - Step 4049: {'lr': 0.0004997635704371844, 'samples': 2073600, 'steps': 4049, 'loss/train': 3.2219486236572266}
-03/03/2022 18:10:27 - INFO - codeparrot_training - Step 4050: {'lr': 0.0004997633396417348, 'samples': 2074112, 'steps': 4050, 'loss/train': 3.620973825454712}
-03/03/2022 18:10:30 - INFO - codeparrot_training - Step 4051: {'lr': 0.0004997631087337456, 'samples': 2074624, 'steps': 4051, 'loss/train': 2.690335988998413}
-03/03/2022 18:10:31 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/03/2022 18:10:36 - INFO - codeparrot_training - Step 4052: {'lr': 0.000499762877713217, 'samples': 2075136, 'steps': 4052, 'loss/train': 2.6117894649505615}
-03/03/2022 18:10:39 - INFO - codeparrot_training - Step 4053: {'lr': 0.0004997626465801492, 'samples': 2075648, 'steps': 4053, 'loss/train': 2.7060298919677734}
-03/03/2022 18:10:39 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/03/2022 18:10:44 - INFO - codeparrot_training - Step 4054: {'lr': 0.000499762415334542, 'samples': 2076160, 'steps': 4054, 'loss/train': 1.8638306856155396}
-03/03/2022 18:10:47 - INFO - codeparrot_training - Step 4055: {'lr': 0.0004997621839763958, 'samples': 2076672, 'steps': 4055, 'loss/train': 2.9767332077026367}
-03/03/2022 18:10:48 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/03/2022 18:10:52 - INFO - codeparrot_training - Step 4056: {'lr': 0.0004997619525057106, 'samples': 2077184, 'steps': 4056, 'loss/train': 2.5807266235351562}
-03/03/2022 18:10:56 - INFO - codeparrot_training - Step 4057: {'lr': 0.0004997617209224866, 'samples': 2077696, 'steps': 4057, 'loss/train': 2.995727062225342}
-03/03/2022 18:10:56 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/03/2022 18:11:01 - INFO - codeparrot_training - Step 4058: {'lr': 0.0004997614892267238, 'samples': 2078208, 'steps': 4058, 'loss/train': 2.310736656188965}
-03/03/2022 18:11:04 - INFO - codeparrot_training - Step 4059: {'lr': 0.0004997612574184223, 'samples': 2078720, 'steps': 4059, 'loss/train': 2.6918468475341797}
-03/03/2022 18:11:05 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/03/2022 18:11:09 - INFO - codeparrot_training - Step 4060: {'lr': 0.0004997610254975823, 'samples': 2079232, 'steps': 4060, 'loss/train': 3.2785415649414062}
-03/03/2022 18:11:12 - INFO - codeparrot_training - Step 4061: {'lr': 0.0004997607934642038, 'samples': 2079744, 'steps': 4061, 'loss/train': 2.231865406036377}
-03/03/2022 18:11:13 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/03/2022 18:11:18 - INFO - codeparrot_training - Step 4062: {'lr': 0.0004997605613182868, 'samples': 2080256, 'steps': 4062, 'loss/train': 2.827054977416992}
-03/03/2022 18:11:21 - INFO - codeparrot_training - Step 4063: {'lr': 0.0004997603290598317, 'samples': 2080768, 'steps': 4063, 'loss/train': 2.4032063484191895}
-03/03/2022 18:11:22 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/03/2022 18:11:26 - INFO - codeparrot_training - Step 4064: {'lr': 0.0004997600966888384, 'samples': 2081280, 'steps': 4064, 'loss/train': 2.884215831756592}
-03/03/2022 18:11:29 - INFO - codeparrot_training - Step 4065: {'lr': 0.000499759864205307, 'samples': 2081792, 'steps': 4065, 'loss/train': 2.158616781234741}
-03/03/2022 18:11:30 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/03/2022 18:11:35 - INFO - codeparrot_training - Step 4066: {'lr': 0.0004997596316092378, 'samples': 2082304, 'steps': 4066, 'loss/train': 2.028759241104126}
-03/03/2022 18:11:38 - INFO - codeparrot_training - Step 4067: {'lr': 0.0004997593989006306, 'samples': 2082816, 'steps': 4067, 'loss/train': 2.340603828430176}
-03/03/2022 18:11:38 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/03/2022 18:11:43 - INFO - codeparrot_training - Step 4068: {'lr': 0.0004997591660794858, 'samples': 2083328, 'steps': 4068, 'loss/train': 2.3579812049865723}
-03/03/2022 18:11:46 - INFO - codeparrot_training - Step 4069: {'lr': 0.0004997589331458034, 'samples': 2083840, 'steps': 4069, 'loss/train': 2.315962553024292}
-03/03/2022 18:11:46 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/03/2022 18:11:52 - INFO - codeparrot_training - Step 4070: {'lr': 0.0004997587000995833, 'samples': 2084352, 'steps': 4070, 'loss/train': 2.3112103939056396}
-03/03/2022 18:11:55 - INFO - codeparrot_training - Step 4071: {'lr': 0.000499758466940826, 'samples': 2084864, 'steps': 4071, 'loss/train': 3.152911901473999}
-03/03/2022 18:11:55 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/03/2022 18:12:00 - INFO - codeparrot_training - Step 4072: {'lr': 0.0004997582336695312, 'samples': 2085376, 'steps': 4072, 'loss/train': 2.1941304206848145}
-03/03/2022 18:12:03 - INFO - codeparrot_training - Step 4073: {'lr': 0.0004997580002856993, 'samples': 2085888, 'steps': 4073, 'loss/train': 2.8319485187530518}
-03/03/2022 18:12:03 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/03/2022 18:12:08 - INFO - codeparrot_training - Step 4074: {'lr': 0.0004997577667893303, 'samples': 2086400, 'steps': 4074, 'loss/train': 2.8888895511627197}
-03/03/2022 18:12:11 - INFO - codeparrot_training - Step 4075: {'lr': 0.0004997575331804243, 'samples': 2086912, 'steps': 4075, 'loss/train': 2.258307695388794}
-03/03/2022 18:12:12 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/03/2022 18:12:17 - INFO - codeparrot_training - Step 4076: {'lr': 0.0004997572994589812, 'samples': 2087424, 'steps': 4076, 'loss/train': 2.183765172958374}
-03/03/2022 18:12:20 - INFO - codeparrot_training - Step 4077: {'lr': 0.0004997570656250016, 'samples': 2087936, 'steps': 4077, 'loss/train': 3.7469561100006104}
-03/03/2022 18:12:20 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/03/2022 18:12:25 - INFO - codeparrot_training - Step 4078: {'lr': 0.0004997568316784852, 'samples': 2088448, 'steps': 4078, 'loss/train': 2.8327484130859375}
-03/03/2022 18:12:28 - INFO - codeparrot_training - Step 4079: {'lr': 0.0004997565976194323, 'samples': 2088960, 'steps': 4079, 'loss/train': 2.171255111694336}
-03/03/2022 18:12:29 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/03/2022 18:12:34 - INFO - codeparrot_training - Step 4080: {'lr': 0.0004997563634478429, 'samples': 2089472, 'steps': 4080, 'loss/train': 1.2639844417572021}
-03/03/2022 18:12:37 - INFO - codeparrot_training - Step 4081: {'lr': 0.000499756129163717, 'samples': 2089984, 'steps': 4081, 'loss/train': 3.2736730575561523}
-03/03/2022 18:12:37 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/03/2022 18:12:42 - INFO - codeparrot_training - Step 4082: {'lr': 0.000499755894767055, 'samples': 2090496, 'steps': 4082, 'loss/train': 2.5604846477508545}
-03/03/2022 18:12:45 - INFO - codeparrot_training - Step 4083: {'lr': 0.0004997556602578568, 'samples': 2091008, 'steps': 4083, 'loss/train': 2.595517873764038}
-03/03/2022 18:12:46 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/03/2022 18:12:50 - INFO - codeparrot_training - Step 4084: {'lr': 0.0004997554256361225, 'samples': 2091520, 'steps': 4084, 'loss/train': 2.2262682914733887}
-03/03/2022 18:12:54 - INFO - codeparrot_training - Step 4085: {'lr': 0.0004997551909018524, 'samples': 2092032, 'steps': 4085, 'loss/train': 1.6804790496826172}
-03/03/2022 18:12:54 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/03/2022 18:12:59 - INFO - codeparrot_training - Step 4086: {'lr': 0.0004997549560550464, 'samples': 2092544, 'steps': 4086, 'loss/train': 2.4673213958740234}
-03/03/2022 18:13:02 - INFO - codeparrot_training - Step 4087: {'lr': 0.0004997547210957047, 'samples': 2093056, 'steps': 4087, 'loss/train': 0.6997495889663696}
-03/03/2022 18:13:02 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/03/2022 18:13:07 - INFO - codeparrot_training - Step 4088: {'lr': 0.0004997544860238272, 'samples': 2093568, 'steps': 4088, 'loss/train': 1.7764511108398438}
-03/03/2022 18:13:10 - INFO - codeparrot_training - Step 4089: {'lr': 0.0004997542508394144, 'samples': 2094080, 'steps': 4089, 'loss/train': 1.9796948432922363}
-03/03/2022 18:13:10 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/03/2022 18:13:16 - INFO - codeparrot_training - Step 4090: {'lr': 0.000499754015542466, 'samples': 2094592, 'steps': 4090, 'loss/train': 3.0019431114196777}
-03/03/2022 18:13:19 - INFO - codeparrot_training - Step 4091: {'lr': 0.0004997537801329824, 'samples': 2095104, 'steps': 4091, 'loss/train': 1.7092125415802002}
-03/03/2022 18:13:19 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/03/2022 18:13:24 - INFO - codeparrot_training - Step 4092: {'lr': 0.0004997535446109637, 'samples': 2095616, 'steps': 4092, 'loss/train': 2.9902400970458984}
-03/03/2022 18:13:27 - INFO - codeparrot_training - Step 4093: {'lr': 0.0004997533089764097, 'samples': 2096128, 'steps': 4093, 'loss/train': 2.423766613006592}
-03/03/2022 18:13:28 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/03/2022 18:13:33 - INFO - codeparrot_training - Step 4094: {'lr': 0.0004997530732293209, 'samples': 2096640, 'steps': 4094, 'loss/train': 1.3834996223449707}
-03/03/2022 18:13:36 - INFO - codeparrot_training - Step 4095: {'lr': 0.000499752837369697, 'samples': 2097152, 'steps': 4095, 'loss/train': 2.4921278953552246}
-03/03/2022 18:13:37 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/03/2022 18:13:41 - INFO - codeparrot_training - Step 4096: {'lr': 0.0004997526013975385, 'samples': 2097664, 'steps': 4096, 'loss/train': 2.3582775592803955}
-03/03/2022 18:13:44 - INFO - codeparrot_training - Step 4097: {'lr': 0.0004997523653128453, 'samples': 2098176, 'steps': 4097, 'loss/train': 2.5054030418395996}
-03/03/2022 18:13:45 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/03/2022 18:13:49 - INFO - codeparrot_training - Step 4098: {'lr': 0.0004997521291156175, 'samples': 2098688, 'steps': 4098, 'loss/train': 2.687840700149536}
-03/03/2022 18:13:53 - INFO - codeparrot_training - Step 4099: {'lr': 0.0004997518928058553, 'samples': 2099200, 'steps': 4099, 'loss/train': 2.318593978881836}
-03/03/2022 18:13:54 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/03/2022 18:13:58 - INFO - codeparrot_training - Step 4100: {'lr': 0.0004997516563835587, 'samples': 2099712, 'steps': 4100, 'loss/train': 3.0710105895996094}
-03/03/2022 18:14:01 - INFO - codeparrot_training - Step 4101: {'lr': 0.0004997514198487279, 'samples': 2100224, 'steps': 4101, 'loss/train': 2.9276015758514404}
-03/03/2022 18:14:02 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/03/2022 18:14:06 - INFO - codeparrot_training - Step 4102: {'lr': 0.0004997511832013629, 'samples': 2100736, 'steps': 4102, 'loss/train': 2.666696548461914}
-03/03/2022 18:14:09 - INFO - codeparrot_training - Step 4103: {'lr': 0.0004997509464414639, 'samples': 2101248, 'steps': 4103, 'loss/train': 3.1703107357025146}
-03/03/2022 18:14:10 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/03/2022 18:14:15 - INFO - codeparrot_training - Step 4104: {'lr': 0.000499750709569031, 'samples': 2101760, 'steps': 4104, 'loss/train': 0.9635540843009949}
-03/03/2022 18:14:18 - INFO - codeparrot_training - Step 4105: {'lr': 0.0004997504725840644, 'samples': 2102272, 'steps': 4105, 'loss/train': 1.584394097328186}
-03/03/2022 18:14:20 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/03/2022 18:14:23 - INFO - codeparrot_training - Step 4106: {'lr': 0.0004997502354865639, 'samples': 2102784, 'steps': 4106, 'loss/train': 2.15683913230896}
-03/03/2022 18:14:26 - INFO - codeparrot_training - Step 4107: {'lr': 0.0004997499982765299, 'samples': 2103296, 'steps': 4107, 'loss/train': 2.5185112953186035}
-03/03/2022 18:14:28 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/03/2022 18:14:32 - INFO - codeparrot_training - Step 4108: {'lr': 0.0004997497609539623, 'samples': 2103808, 'steps': 4108, 'loss/train': 2.416644811630249}
-03/03/2022 18:14:35 - INFO - codeparrot_training - Step 4109: {'lr': 0.0004997495235188614, 'samples': 2104320, 'steps': 4109, 'loss/train': 2.281923770904541}
-03/03/2022 18:14:36 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/03/2022 18:14:40 - INFO - codeparrot_training - Step 4110: {'lr': 0.0004997492859712272, 'samples': 2104832, 'steps': 4110, 'loss/train': 1.5101902484893799}
-03/03/2022 18:14:43 - INFO - codeparrot_training - Step 4111: {'lr': 0.0004997490483110599, 'samples': 2105344, 'steps': 4111, 'loss/train': 0.526434600353241}
-03/03/2022 18:14:44 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/03/2022 18:14:48 - INFO - codeparrot_training - Step 4112: {'lr': 0.0004997488105383594, 'samples': 2105856, 'steps': 4112, 'loss/train': 1.918593168258667}
-03/03/2022 18:14:52 - INFO - codeparrot_training - Step 4113: {'lr': 0.000499748572653126, 'samples': 2106368, 'steps': 4113, 'loss/train': 2.5217132568359375}
-03/03/2022 18:14:53 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/03/2022 18:14:57 - INFO - codeparrot_training - Step 4114: {'lr': 0.0004997483346553597, 'samples': 2106880, 'steps': 4114, 'loss/train': 2.4129765033721924}
-03/03/2022 18:15:00 - INFO - codeparrot_training - Step 4115: {'lr': 0.0004997480965450607, 'samples': 2107392, 'steps': 4115, 'loss/train': 2.6270291805267334}
-03/03/2022 18:15:01 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/03/2022 18:15:05 - INFO - codeparrot_training - Step 4116: {'lr': 0.0004997478583222291, 'samples': 2107904, 'steps': 4116, 'loss/train': 1.7648855447769165}
-03/03/2022 18:15:08 - INFO - codeparrot_training - Step 4117: {'lr': 0.0004997476199868649, 'samples': 2108416, 'steps': 4117, 'loss/train': 1.9991642236709595}
-03/03/2022 18:15:09 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/03/2022 18:15:14 - INFO - codeparrot_training - Step 4118: {'lr': 0.0004997473815389683, 'samples': 2108928, 'steps': 4118, 'loss/train': 2.1075313091278076}
-03/03/2022 18:15:17 - INFO - codeparrot_training - Step 4119: {'lr': 0.0004997471429785394, 'samples': 2109440, 'steps': 4119, 'loss/train': 1.0505720376968384}
-03/03/2022 18:15:18 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/03/2022 18:15:22 - INFO - codeparrot_training - Step 4120: {'lr': 0.0004997469043055784, 'samples': 2109952, 'steps': 4120, 'loss/train': 2.572298049926758}
-03/03/2022 18:15:26 - INFO - codeparrot_training - Step 4121: {'lr': 0.000499746665520085, 'samples': 2110464, 'steps': 4121, 'loss/train': 2.1575143337249756}
-03/03/2022 18:15:27 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/03/2022 18:15:31 - INFO - codeparrot_training - Step 4122: {'lr': 0.0004997464266220599, 'samples': 2110976, 'steps': 4122, 'loss/train': 2.810858964920044}
-03/03/2022 18:15:34 - INFO - codeparrot_training - Step 4123: {'lr': 0.0004997461876115029, 'samples': 2111488, 'steps': 4123, 'loss/train': 2.393360137939453}
-03/03/2022 18:15:35 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/03/2022 18:15:39 - INFO - codeparrot_training - Step 4124: {'lr': 0.0004997459484884139, 'samples': 2112000, 'steps': 4124, 'loss/train': 2.3642711639404297}
-03/03/2022 18:15:42 - INFO - codeparrot_training - Step 4125: {'lr': 0.0004997457092527934, 'samples': 2112512, 'steps': 4125, 'loss/train': 1.894789695739746}
-03/03/2022 18:15:43 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/03/2022 18:15:48 - INFO - codeparrot_training - Step 4126: {'lr': 0.0004997454699046412, 'samples': 2113024, 'steps': 4126, 'loss/train': 3.0609028339385986}
-03/03/2022 18:15:51 - INFO - codeparrot_training - Step 4127: {'lr': 0.0004997452304439577, 'samples': 2113536, 'steps': 4127, 'loss/train': 2.4769256114959717}
-03/03/2022 18:15:53 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/03/2022 18:15:56 - INFO - codeparrot_training - Step 4128: {'lr': 0.0004997449908707428, 'samples': 2114048, 'steps': 4128, 'loss/train': 2.600919246673584}
-03/03/2022 18:15:59 - INFO - codeparrot_training - Step 4129: {'lr': 0.0004997447511849966, 'samples': 2114560, 'steps': 4129, 'loss/train': 2.6774415969848633}
-03/03/2022 18:16:01 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/03/2022 18:16:05 - INFO - codeparrot_training - Step 4130: {'lr': 0.0004997445113867193, 'samples': 2115072, 'steps': 4130, 'loss/train': 3.0764505863189697}
-03/03/2022 18:16:08 - INFO - codeparrot_training - Step 4131: {'lr': 0.000499744271475911, 'samples': 2115584, 'steps': 4131, 'loss/train': 1.4300533533096313}
-03/03/2022 18:16:09 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/03/2022 18:16:13 - INFO - codeparrot_training - Step 4132: {'lr': 0.0004997440314525718, 'samples': 2116096, 'steps': 4132, 'loss/train': 3.59360408782959}
-03/03/2022 18:16:16 - INFO - codeparrot_training - Step 4133: {'lr': 0.0004997437913167018, 'samples': 2116608, 'steps': 4133, 'loss/train': 1.883839726448059}
-03/03/2022 18:16:18 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/03/2022 18:16:22 - INFO - codeparrot_training - Step 4134: {'lr': 0.0004997435510683011, 'samples': 2117120, 'steps': 4134, 'loss/train': 2.075192451477051}
-03/03/2022 18:16:25 - INFO - codeparrot_training - Step 4135: {'lr': 0.0004997433107073697, 'samples': 2117632, 'steps': 4135, 'loss/train': 2.5948169231414795}
-03/03/2022 18:16:26 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/03/2022 18:16:30 - INFO - codeparrot_training - Step 4136: {'lr': 0.000499743070233908, 'samples': 2118144, 'steps': 4136, 'loss/train': 2.7506139278411865}
-03/03/2022 18:16:33 - INFO - codeparrot_training - Step 4137: {'lr': 0.0004997428296479158, 'samples': 2118656, 'steps': 4137, 'loss/train': 2.5044801235198975}
-03/03/2022 18:16:35 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/03/2022 18:16:39 - INFO - codeparrot_training - Step 4138: {'lr': 0.0004997425889493933, 'samples': 2119168, 'steps': 4138, 'loss/train': 2.9602603912353516}
-03/03/2022 18:16:42 - INFO - codeparrot_training - Step 4139: {'lr': 0.0004997423481383407, 'samples': 2119680, 'steps': 4139, 'loss/train': 3.964172124862671}
-03/03/2022 18:16:43 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/03/2022 18:16:47 - INFO - codeparrot_training - Step 4140: {'lr': 0.0004997421072147581, 'samples': 2120192, 'steps': 4140, 'loss/train': 2.4455370903015137}
-03/03/2022 18:16:50 - INFO - codeparrot_training - Step 4141: {'lr': 0.0004997418661786455, 'samples': 2120704, 'steps': 4141, 'loss/train': 1.569913387298584}
-03/03/2022 18:16:52 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/03/2022 18:16:56 - INFO - codeparrot_training - Step 4142: {'lr': 0.0004997416250300031, 'samples': 2121216, 'steps': 4142, 'loss/train': 1.0883207321166992}
-03/03/2022 18:16:59 - INFO - codeparrot_training - Step 4143: {'lr': 0.0004997413837688309, 'samples': 2121728, 'steps': 4143, 'loss/train': 2.9094440937042236}
-03/03/2022 18:17:00 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/03/2022 18:17:04 - INFO - codeparrot_training - Step 4144: {'lr': 0.0004997411423951292, 'samples': 2122240, 'steps': 4144, 'loss/train': 2.9646050930023193}
-03/03/2022 18:17:07 - INFO - codeparrot_training - Step 4145: {'lr': 0.0004997409009088979, 'samples': 2122752, 'steps': 4145, 'loss/train': 2.3445956707000732}
-03/03/2022 18:17:09 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/03/2022 18:17:13 - INFO - codeparrot_training - Step 4146: {'lr': 0.0004997406593101373, 'samples': 2123264, 'steps': 4146, 'loss/train': 1.9361507892608643}
-03/03/2022 18:17:16 - INFO - codeparrot_training - Step 4147: {'lr': 0.0004997404175988474, 'samples': 2123776, 'steps': 4147, 'loss/train': 2.9918205738067627}
-03/03/2022 18:17:17 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/03/2022 18:17:21 - INFO - codeparrot_training - Step 4148: {'lr': 0.0004997401757750282, 'samples': 2124288, 'steps': 4148, 'loss/train': 2.99582839012146}
-03/03/2022 18:17:24 - INFO - codeparrot_training - Step 4149: {'lr': 0.00049973993383868, 'samples': 2124800, 'steps': 4149, 'loss/train': 3.0628974437713623}
-03/03/2022 18:17:26 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/03/2022 18:17:30 - INFO - codeparrot_training - Step 4150: {'lr': 0.0004997396917898029, 'samples': 2125312, 'steps': 4150, 'loss/train': 3.2338919639587402}
-03/03/2022 18:17:33 - INFO - codeparrot_training - Step 4151: {'lr': 0.0004997394496283969, 'samples': 2125824, 'steps': 4151, 'loss/train': 2.5238869190216064}
-03/03/2022 18:17:34 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/03/2022 18:17:38 - INFO - codeparrot_training - Step 4152: {'lr': 0.0004997392073544622, 'samples': 2126336, 'steps': 4152, 'loss/train': 3.1680476665496826}
-03/03/2022 18:17:41 - INFO - codeparrot_training - Step 4153: {'lr': 0.0004997389649679987, 'samples': 2126848, 'steps': 4153, 'loss/train': 1.4233876466751099}
-03/03/2022 18:17:42 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/03/2022 18:17:46 - INFO - codeparrot_training - Step 4154: {'lr': 0.0004997387224690068, 'samples': 2127360, 'steps': 4154, 'loss/train': 2.5396082401275635}
-03/03/2022 18:17:49 - INFO - codeparrot_training - Step 4155: {'lr': 0.0004997384798574865, 'samples': 2127872, 'steps': 4155, 'loss/train': 2.4975132942199707}
-03/03/2022 18:17:50 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/03/2022 18:17:55 - INFO - codeparrot_training - Step 4156: {'lr': 0.0004997382371334379, 'samples': 2128384, 'steps': 4156, 'loss/train': 3.6286377906799316}
-03/03/2022 18:17:58 - INFO - codeparrot_training - Step 4157: {'lr': 0.0004997379942968611, 'samples': 2128896, 'steps': 4157, 'loss/train': 2.523087501525879}
-03/03/2022 18:17:59 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/03/2022 18:18:03 - INFO - codeparrot_training - Step 4158: {'lr': 0.0004997377513477562, 'samples': 2129408, 'steps': 4158, 'loss/train': 3.208761215209961}
-03/03/2022 18:18:06 - INFO - codeparrot_training - Step 4159: {'lr': 0.0004997375082861234, 'samples': 2129920, 'steps': 4159, 'loss/train': 0.6377323865890503}
-03/03/2022 18:18:07 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/03/2022 18:18:11 - INFO - codeparrot_training - Step 4160: {'lr': 0.0004997372651119626, 'samples': 2130432, 'steps': 4160, 'loss/train': 2.6335766315460205}
-03/03/2022 18:18:15 - INFO - codeparrot_training - Step 4161: {'lr': 0.0004997370218252741, 'samples': 2130944, 'steps': 4161, 'loss/train': 2.5048093795776367}
-03/03/2022 18:18:15 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/03/2022 18:18:20 - INFO - codeparrot_training - Step 4162: {'lr': 0.000499736778426058, 'samples': 2131456, 'steps': 4162, 'loss/train': 2.977962017059326}
-03/03/2022 18:18:23 - INFO - codeparrot_training - Step 4163: {'lr': 0.0004997365349143142, 'samples': 2131968, 'steps': 4163, 'loss/train': 0.8089989423751831}
-03/03/2022 18:18:24 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 18:18:29 - INFO - codeparrot_training - Step 4164: {'lr': 0.0004997362912900432, 'samples': 2132480, 'steps': 4164, 'loss/train': 0.4729238450527191}
-03/03/2022 18:18:32 - INFO - codeparrot_training - Step 4165: {'lr': 0.0004997360475532447, 'samples': 2132992, 'steps': 4165, 'loss/train': 2.9363718032836914}
-03/03/2022 18:18:32 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/03/2022 18:18:37 - INFO - codeparrot_training - Step 4166: {'lr': 0.000499735803703919, 'samples': 2133504, 'steps': 4166, 'loss/train': 1.6260018348693848}
-03/03/2022 18:18:40 - INFO - codeparrot_training - Step 4167: {'lr': 0.0004997355597420663, 'samples': 2134016, 'steps': 4167, 'loss/train': 2.8573882579803467}
-03/03/2022 18:18:41 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/03/2022 18:18:45 - INFO - codeparrot_training - Step 4168: {'lr': 0.0004997353156676866, 'samples': 2134528, 'steps': 4168, 'loss/train': 2.9690592288970947}
-03/03/2022 18:18:48 - INFO - codeparrot_training - Step 4169: {'lr': 0.0004997350714807799, 'samples': 2135040, 'steps': 4169, 'loss/train': 2.972532272338867}
-03/03/2022 18:18:49 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/03/2022 18:18:54 - INFO - codeparrot_training - Step 4170: {'lr': 0.0004997348271813466, 'samples': 2135552, 'steps': 4170, 'loss/train': 3.199317455291748}
-03/03/2022 18:18:57 - INFO - codeparrot_training - Step 4171: {'lr': 0.0004997345827693865, 'samples': 2136064, 'steps': 4171, 'loss/train': 2.829935073852539}
-03/03/2022 18:18:57 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/03/2022 18:19:02 - INFO - codeparrot_training - Step 4172: {'lr': 0.0004997343382448999, 'samples': 2136576, 'steps': 4172, 'loss/train': 2.5150444507598877}
-03/03/2022 18:19:05 - INFO - codeparrot_training - Step 4173: {'lr': 0.0004997340936078869, 'samples': 2137088, 'steps': 4173, 'loss/train': 2.6708381175994873}
-03/03/2022 18:19:05 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/03/2022 18:19:10 - INFO - codeparrot_training - Step 4174: {'lr': 0.0004997338488583475, 'samples': 2137600, 'steps': 4174, 'loss/train': 1.084150791168213}
-03/03/2022 18:19:14 - INFO - codeparrot_training - Step 4175: {'lr': 0.000499733603996282, 'samples': 2138112, 'steps': 4175, 'loss/train': 3.284475326538086}
-03/03/2022 18:19:14 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/03/2022 18:19:19 - INFO - codeparrot_training - Step 4176: {'lr': 0.0004997333590216902, 'samples': 2138624, 'steps': 4176, 'loss/train': 2.739633798599243}
-03/03/2022 18:19:22 - INFO - codeparrot_training - Step 4177: {'lr': 0.0004997331139345725, 'samples': 2139136, 'steps': 4177, 'loss/train': 3.0070743560791016}
-03/03/2022 18:19:22 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/03/2022 18:19:27 - INFO - codeparrot_training - Step 4178: {'lr': 0.000499732868734929, 'samples': 2139648, 'steps': 4178, 'loss/train': 1.8760261535644531}
-03/03/2022 18:19:30 - INFO - codeparrot_training - Step 4179: {'lr': 0.0004997326234227596, 'samples': 2140160, 'steps': 4179, 'loss/train': 1.5933669805526733}
-03/03/2022 18:19:31 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/03/2022 18:19:36 - INFO - codeparrot_training - Step 4180: {'lr': 0.0004997323779980646, 'samples': 2140672, 'steps': 4180, 'loss/train': 2.30065655708313}
-03/03/2022 18:19:39 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/03/2022 18:19:41 - INFO - codeparrot_training - Step 4181: {'lr': 0.0004997321324608441, 'samples': 2141184, 'steps': 4181, 'loss/train': 2.3813674449920654}
-03/03/2022 18:19:44 - INFO - codeparrot_training - Step 4182: {'lr': 0.0004997318868110981, 'samples': 2141696, 'steps': 4182, 'loss/train': 1.6555471420288086}
-03/03/2022 18:19:48 - INFO - codeparrot_training - Step 4183: {'lr': 0.0004997316410488267, 'samples': 2142208, 'steps': 4183, 'loss/train': 1.8753160238265991}
-03/03/2022 18:19:48 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/03/2022 18:19:53 - INFO - codeparrot_training - Step 4184: {'lr': 0.0004997313951740301, 'samples': 2142720, 'steps': 4184, 'loss/train': 2.5217244625091553}
-03/03/2022 18:19:56 - INFO - codeparrot_training - Step 4185: {'lr': 0.0004997311491867083, 'samples': 2143232, 'steps': 4185, 'loss/train': 1.9755817651748657}
-03/03/2022 18:19:56 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/03/2022 18:20:01 - INFO - codeparrot_training - Step 4186: {'lr': 0.0004997309030868617, 'samples': 2143744, 'steps': 4186, 'loss/train': 2.2549116611480713}
-03/03/2022 18:20:05 - INFO - codeparrot_training - Step 4187: {'lr': 0.0004997306568744901, 'samples': 2144256, 'steps': 4187, 'loss/train': 0.9781758189201355}
-03/03/2022 18:20:05 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/03/2022 18:20:10 - INFO - codeparrot_training - Step 4188: {'lr': 0.0004997304105495938, 'samples': 2144768, 'steps': 4188, 'loss/train': 3.3931400775909424}
-03/03/2022 18:20:13 - INFO - codeparrot_training - Step 4189: {'lr': 0.0004997301641121727, 'samples': 2145280, 'steps': 4189, 'loss/train': 1.42490816116333}
-03/03/2022 18:20:13 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/03/2022 18:20:18 - INFO - codeparrot_training - Step 4190: {'lr': 0.0004997299175622271, 'samples': 2145792, 'steps': 4190, 'loss/train': 1.298801064491272}
-03/03/2022 18:20:21 - INFO - codeparrot_training - Step 4191: {'lr': 0.000499729670899757, 'samples': 2146304, 'steps': 4191, 'loss/train': 0.4252501428127289}
-03/03/2022 18:20:22 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/03/2022 18:20:27 - INFO - codeparrot_training - Step 4192: {'lr': 0.0004997294241247627, 'samples': 2146816, 'steps': 4192, 'loss/train': 2.6930501461029053}
-03/03/2022 18:20:30 - INFO - codeparrot_training - Step 4193: {'lr': 0.0004997291772372441, 'samples': 2147328, 'steps': 4193, 'loss/train': 2.5323684215545654}
-03/03/2022 18:20:31 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/03/2022 18:20:35 - INFO - codeparrot_training - Step 4194: {'lr': 0.0004997289302372014, 'samples': 2147840, 'steps': 4194, 'loss/train': 2.235337257385254}
-03/03/2022 18:20:38 - INFO - codeparrot_training - Step 4195: {'lr': 0.0004997286831246347, 'samples': 2148352, 'steps': 4195, 'loss/train': 1.4446816444396973}
-03/03/2022 18:20:39 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/03/2022 18:20:44 - INFO - codeparrot_training - Step 4196: {'lr': 0.0004997284358995441, 'samples': 2148864, 'steps': 4196, 'loss/train': 2.681225299835205}
-03/03/2022 18:20:47 - INFO - codeparrot_training - Step 4197: {'lr': 0.0004997281885619297, 'samples': 2149376, 'steps': 4197, 'loss/train': 3.0499494075775146}
-03/03/2022 18:20:47 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/03/2022 18:20:52 - INFO - codeparrot_training - Step 4198: {'lr': 0.0004997279411117916, 'samples': 2149888, 'steps': 4198, 'loss/train': 2.9221158027648926}
-03/03/2022 18:20:55 - INFO - codeparrot_training - Step 4199: {'lr': 0.00049972769354913, 'samples': 2150400, 'steps': 4199, 'loss/train': 2.7829251289367676}
-03/03/2022 18:20:56 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/03/2022 18:21:00 - INFO - codeparrot_training - Step 4200: {'lr': 0.0004997274458739449, 'samples': 2150912, 'steps': 4200, 'loss/train': 2.388589382171631}
-03/03/2022 18:21:04 - INFO - codeparrot_training - Step 4201: {'lr': 0.0004997271980862366, 'samples': 2151424, 'steps': 4201, 'loss/train': 2.827019214630127}
-03/03/2022 18:21:04 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/03/2022 18:21:09 - INFO - codeparrot_training - Step 4202: {'lr': 0.000499726950186005, 'samples': 2151936, 'steps': 4202, 'loss/train': 1.8681377172470093}
-03/03/2022 18:21:12 - INFO - codeparrot_training - Step 4203: {'lr': 0.0004997267021732502, 'samples': 2152448, 'steps': 4203, 'loss/train': 2.7481272220611572}
-03/03/2022 18:21:13 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/03/2022 18:21:17 - INFO - codeparrot_training - Step 4204: {'lr': 0.0004997264540479724, 'samples': 2152960, 'steps': 4204, 'loss/train': 2.2508490085601807}
-03/03/2022 18:21:21 - INFO - codeparrot_training - Step 4205: {'lr': 0.0004997262058101719, 'samples': 2153472, 'steps': 4205, 'loss/train': 2.915381908416748}
-03/03/2022 18:21:22 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/03/2022 18:21:26 - INFO - codeparrot_training - Step 4206: {'lr': 0.0004997259574598485, 'samples': 2153984, 'steps': 4206, 'loss/train': 2.1661908626556396}
-03/03/2022 18:21:29 - INFO - codeparrot_training - Step 4207: {'lr': 0.0004997257089970024, 'samples': 2154496, 'steps': 4207, 'loss/train': 2.371553421020508}
-03/03/2022 18:21:30 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/03/2022 18:21:34 - INFO - codeparrot_training - Step 4208: {'lr': 0.0004997254604216338, 'samples': 2155008, 'steps': 4208, 'loss/train': 2.215244770050049}
-03/03/2022 18:21:37 - INFO - codeparrot_training - Step 4209: {'lr': 0.0004997252117337428, 'samples': 2155520, 'steps': 4209, 'loss/train': 2.8784711360931396}
-03/03/2022 18:21:38 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/03/2022 18:21:43 - INFO - codeparrot_training - Step 4210: {'lr': 0.0004997249629333294, 'samples': 2156032, 'steps': 4210, 'loss/train': 1.9061493873596191}
-03/03/2022 18:21:46 - INFO - codeparrot_training - Step 4211: {'lr': 0.0004997247140203939, 'samples': 2156544, 'steps': 4211, 'loss/train': 2.4784083366394043}
-03/03/2022 18:21:46 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/03/2022 18:21:51 - INFO - codeparrot_training - Step 4212: {'lr': 0.0004997244649949362, 'samples': 2157056, 'steps': 4212, 'loss/train': 2.107531785964966}
-03/03/2022 18:21:54 - INFO - codeparrot_training - Step 4213: {'lr': 0.0004997242158569564, 'samples': 2157568, 'steps': 4213, 'loss/train': 3.0238053798675537}
-03/03/2022 18:21:55 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/03/2022 18:21:59 - INFO - codeparrot_training - Step 4214: {'lr': 0.0004997239666064549, 'samples': 2158080, 'steps': 4214, 'loss/train': 2.926823377609253}
-03/03/2022 18:22:03 - INFO - codeparrot_training - Step 4215: {'lr': 0.0004997237172434316, 'samples': 2158592, 'steps': 4215, 'loss/train': 2.6826536655426025}
-03/03/2022 18:22:04 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/03/2022 18:22:08 - INFO - codeparrot_training - Step 4216: {'lr': 0.0004997234677678867, 'samples': 2159104, 'steps': 4216, 'loss/train': 1.9293338060379028}
-03/03/2022 18:22:11 - INFO - codeparrot_training - Step 4217: {'lr': 0.0004997232181798201, 'samples': 2159616, 'steps': 4217, 'loss/train': 2.3123693466186523}
-03/03/2022 18:22:12 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/03/2022 18:22:16 - INFO - codeparrot_training - Step 4218: {'lr': 0.0004997229684792322, 'samples': 2160128, 'steps': 4218, 'loss/train': 2.6831119060516357}
-03/03/2022 18:22:19 - INFO - codeparrot_training - Step 4219: {'lr': 0.000499722718666123, 'samples': 2160640, 'steps': 4219, 'loss/train': 2.3265035152435303}
-03/03/2022 18:22:20 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/03/2022 18:22:25 - INFO - codeparrot_training - Step 4220: {'lr': 0.0004997224687404926, 'samples': 2161152, 'steps': 4220, 'loss/train': 3.8408584594726562}
-03/03/2022 18:22:28 - INFO - codeparrot_training - Step 4221: {'lr': 0.0004997222187023409, 'samples': 2161664, 'steps': 4221, 'loss/train': 2.347179651260376}
-03/03/2022 18:22:28 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/03/2022 18:22:33 - INFO - codeparrot_training - Step 4222: {'lr': 0.0004997219685516684, 'samples': 2162176, 'steps': 4222, 'loss/train': 0.5493170619010925}
-03/03/2022 18:22:36 - INFO - codeparrot_training - Step 4223: {'lr': 0.000499721718288475, 'samples': 2162688, 'steps': 4223, 'loss/train': 3.4518625736236572}
-03/03/2022 18:22:36 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/03/2022 18:22:41 - INFO - codeparrot_training - Step 4224: {'lr': 0.0004997214679127609, 'samples': 2163200, 'steps': 4224, 'loss/train': 7.402772903442383}
-03/03/2022 18:22:45 - INFO - codeparrot_training - Step 4225: {'lr': 0.000499721217424526, 'samples': 2163712, 'steps': 4225, 'loss/train': 1.6710703372955322}
-03/03/2022 18:22:46 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/03/2022 18:22:50 - INFO - codeparrot_training - Step 4226: {'lr': 0.0004997209668237707, 'samples': 2164224, 'steps': 4226, 'loss/train': 2.7258856296539307}
-03/03/2022 18:22:53 - INFO - codeparrot_training - Step 4227: {'lr': 0.0004997207161104951, 'samples': 2164736, 'steps': 4227, 'loss/train': 3.111036777496338}
-03/03/2022 18:22:54 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/03/2022 18:22:58 - INFO - codeparrot_training - Step 4228: {'lr': 0.0004997204652846991, 'samples': 2165248, 'steps': 4228, 'loss/train': 2.2086572647094727}
-03/03/2022 18:23:02 - INFO - codeparrot_training - Step 4229: {'lr': 0.0004997202143463828, 'samples': 2165760, 'steps': 4229, 'loss/train': 1.5683060884475708}
-03/03/2022 18:23:02 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/03/2022 18:23:07 - INFO - codeparrot_training - Step 4230: {'lr': 0.0004997199632955464, 'samples': 2166272, 'steps': 4230, 'loss/train': 1.8688592910766602}
-03/03/2022 18:23:10 - INFO - codeparrot_training - Step 4231: {'lr': 0.0004997197121321903, 'samples': 2166784, 'steps': 4231, 'loss/train': 2.0556914806365967}
-03/03/2022 18:23:10 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/03/2022 18:23:15 - INFO - codeparrot_training - Step 4232: {'lr': 0.0004997194608563142, 'samples': 2167296, 'steps': 4232, 'loss/train': 2.1599605083465576}
-03/03/2022 18:23:18 - INFO - codeparrot_training - Step 4233: {'lr': 0.0004997192094679183, 'samples': 2167808, 'steps': 4233, 'loss/train': 7.5924601554870605}
-03/03/2022 18:23:20 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/03/2022 18:23:24 - INFO - codeparrot_training - Step 4234: {'lr': 0.0004997189579670028, 'samples': 2168320, 'steps': 4234, 'loss/train': 1.3628270626068115}
-03/03/2022 18:23:28 - INFO - codeparrot_training - Step 4235: {'lr': 0.0004997187063535679, 'samples': 2168832, 'steps': 4235, 'loss/train': 3.244776725769043}
-03/03/2022 18:23:31 - INFO - codeparrot_training - Step 4236: {'lr': 0.0004997184546276135, 'samples': 2169344, 'steps': 4236, 'loss/train': 3.347801685333252}
-03/03/2022 18:23:31 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/03/2022 18:23:36 - INFO - codeparrot_training - Step 4237: {'lr': 0.0004997182027891399, 'samples': 2169856, 'steps': 4237, 'loss/train': 2.7080979347229004}
-03/03/2022 18:23:39 - INFO - codeparrot_training - Step 4238: {'lr': 0.000499717950838147, 'samples': 2170368, 'steps': 4238, 'loss/train': 2.261035203933716}
-03/03/2022 18:23:40 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/03/2022 18:23:45 - INFO - codeparrot_training - Step 4239: {'lr': 0.0004997176987746352, 'samples': 2170880, 'steps': 4239, 'loss/train': 0.747605562210083}
-03/03/2022 18:23:48 - INFO - codeparrot_training - Step 4240: {'lr': 0.0004997174465986043, 'samples': 2171392, 'steps': 4240, 'loss/train': 1.8044626712799072}
-03/03/2022 18:23:49 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/03/2022 18:23:53 - INFO - codeparrot_training - Step 4241: {'lr': 0.0004997171943100547, 'samples': 2171904, 'steps': 4241, 'loss/train': 2.823612928390503}
-03/03/2022 18:23:56 - INFO - codeparrot_training - Step 4242: {'lr': 0.0004997169419089863, 'samples': 2172416, 'steps': 4242, 'loss/train': 1.7056597471237183}
-03/03/2022 18:23:57 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/03/2022 18:24:01 - INFO - codeparrot_training - Step 4243: {'lr': 0.0004997166893953994, 'samples': 2172928, 'steps': 4243, 'loss/train': 2.243332624435425}
-03/03/2022 18:24:04 - INFO - codeparrot_training - Step 4244: {'lr': 0.000499716436769294, 'samples': 2173440, 'steps': 4244, 'loss/train': 2.3363187313079834}
-03/03/2022 18:24:05 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/03/2022 18:24:10 - INFO - codeparrot_training - Step 4245: {'lr': 0.0004997161840306701, 'samples': 2173952, 'steps': 4245, 'loss/train': 2.5776519775390625}
-03/03/2022 18:24:13 - INFO - codeparrot_training - Step 4246: {'lr': 0.0004997159311795281, 'samples': 2174464, 'steps': 4246, 'loss/train': 2.3468308448791504}
-03/03/2022 18:24:13 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/03/2022 18:24:18 - INFO - codeparrot_training - Step 4247: {'lr': 0.0004997156782158679, 'samples': 2174976, 'steps': 4247, 'loss/train': 2.2870025634765625}
-03/03/2022 18:24:21 - INFO - codeparrot_training - Step 4248: {'lr': 0.0004997154251396896, 'samples': 2175488, 'steps': 4248, 'loss/train': 3.344219207763672}
-03/03/2022 18:24:21 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/03/2022 18:24:27 - INFO - codeparrot_training - Step 4249: {'lr': 0.0004997151719509935, 'samples': 2176000, 'steps': 4249, 'loss/train': 1.333770990371704}
-03/03/2022 18:24:30 - INFO - codeparrot_training - Step 4250: {'lr': 0.0004997149186497795, 'samples': 2176512, 'steps': 4250, 'loss/train': 2.816612958908081}
-03/03/2022 18:24:30 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/03/2022 18:24:35 - INFO - codeparrot_training - Step 4251: {'lr': 0.0004997146652360478, 'samples': 2177024, 'steps': 4251, 'loss/train': 2.37959885597229}
-03/03/2022 18:24:38 - INFO - codeparrot_training - Step 4252: {'lr': 0.0004997144117097986, 'samples': 2177536, 'steps': 4252, 'loss/train': 2.9103994369506836}
-03/03/2022 18:24:39 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/03/2022 18:24:43 - INFO - codeparrot_training - Step 4253: {'lr': 0.0004997141580710318, 'samples': 2178048, 'steps': 4253, 'loss/train': 2.08974289894104}
-03/03/2022 18:24:47 - INFO - codeparrot_training - Step 4254: {'lr': 0.0004997139043197478, 'samples': 2178560, 'steps': 4254, 'loss/train': 2.9145236015319824}
-03/03/2022 18:24:47 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 18:24:52 - INFO - codeparrot_training - Step 4255: {'lr': 0.0004997136504559465, 'samples': 2179072, 'steps': 4255, 'loss/train': 2.6321043968200684}
-03/03/2022 18:24:55 - INFO - codeparrot_training - Step 4256: {'lr': 0.0004997133964796281, 'samples': 2179584, 'steps': 4256, 'loss/train': 2.3172450065612793}
-03/03/2022 18:24:55 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/03/2022 18:25:01 - INFO - codeparrot_training - Step 4257: {'lr': 0.0004997131423907927, 'samples': 2180096, 'steps': 4257, 'loss/train': 3.576275110244751}
-03/03/2022 18:25:04 - INFO - codeparrot_training - Step 4258: {'lr': 0.0004997128881894404, 'samples': 2180608, 'steps': 4258, 'loss/train': 3.177367687225342}
-03/03/2022 18:25:06 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/03/2022 18:25:09 - INFO - codeparrot_training - Step 4259: {'lr': 0.0004997126338755714, 'samples': 2181120, 'steps': 4259, 'loss/train': 3.177424669265747}
-03/03/2022 18:25:13 - INFO - codeparrot_training - Step 4260: {'lr': 0.0004997123794491856, 'samples': 2181632, 'steps': 4260, 'loss/train': 1.8041192293167114}
-03/03/2022 18:25:14 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/03/2022 18:25:18 - INFO - codeparrot_training - Step 4261: {'lr': 0.0004997121249102834, 'samples': 2182144, 'steps': 4261, 'loss/train': 2.2417562007904053}
-03/03/2022 18:25:21 - INFO - codeparrot_training - Step 4262: {'lr': 0.0004997118702588647, 'samples': 2182656, 'steps': 4262, 'loss/train': 2.5560426712036133}
-03/03/2022 18:25:23 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/03/2022 18:25:26 - INFO - codeparrot_training - Step 4263: {'lr': 0.0004997116154949297, 'samples': 2183168, 'steps': 4263, 'loss/train': 2.5086123943328857}
-03/03/2022 18:25:29 - INFO - codeparrot_training - Step 4264: {'lr': 0.0004997113606184785, 'samples': 2183680, 'steps': 4264, 'loss/train': 3.7005512714385986}
-03/03/2022 18:25:31 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/03/2022 18:25:35 - INFO - codeparrot_training - Step 4265: {'lr': 0.0004997111056295111, 'samples': 2184192, 'steps': 4265, 'loss/train': 2.2525722980499268}
-03/03/2022 18:25:38 - INFO - codeparrot_training - Step 4266: {'lr': 0.0004997108505280279, 'samples': 2184704, 'steps': 4266, 'loss/train': 2.904784917831421}
-03/03/2022 18:25:39 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/03/2022 18:25:43 - INFO - codeparrot_training - Step 4267: {'lr': 0.0004997105953140288, 'samples': 2185216, 'steps': 4267, 'loss/train': 2.262169361114502}
-03/03/2022 18:25:46 - INFO - codeparrot_training - Step 4268: {'lr': 0.0004997103399875139, 'samples': 2185728, 'steps': 4268, 'loss/train': 2.8045146465301514}
-03/03/2022 18:25:47 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/03/2022 18:25:51 - INFO - codeparrot_training - Step 4269: {'lr': 0.0004997100845484834, 'samples': 2186240, 'steps': 4269, 'loss/train': 2.2560219764709473}
-03/03/2022 18:25:55 - INFO - codeparrot_training - Step 4270: {'lr': 0.0004997098289969374, 'samples': 2186752, 'steps': 4270, 'loss/train': 2.0662131309509277}
-03/03/2022 18:25:56 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/03/2022 18:26:00 - INFO - codeparrot_training - Step 4271: {'lr': 0.0004997095733328761, 'samples': 2187264, 'steps': 4271, 'loss/train': 1.531733751296997}
-03/03/2022 18:26:03 - INFO - codeparrot_training - Step 4272: {'lr': 0.0004997093175562994, 'samples': 2187776, 'steps': 4272, 'loss/train': 2.7360663414001465}
-03/03/2022 18:26:04 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/03/2022 18:26:08 - INFO - codeparrot_training - Step 4273: {'lr': 0.0004997090616672076, 'samples': 2188288, 'steps': 4273, 'loss/train': 2.1304633617401123}
-03/03/2022 18:26:11 - INFO - codeparrot_training - Step 4274: {'lr': 0.0004997088056656006, 'samples': 2188800, 'steps': 4274, 'loss/train': 2.0623817443847656}
-03/03/2022 18:26:12 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/03/2022 18:26:17 - INFO - codeparrot_training - Step 4275: {'lr': 0.0004997085495514788, 'samples': 2189312, 'steps': 4275, 'loss/train': 2.2538864612579346}
-03/03/2022 18:26:20 - INFO - codeparrot_training - Step 4276: {'lr': 0.0004997082933248421, 'samples': 2189824, 'steps': 4276, 'loss/train': 3.050964832305908}
-03/03/2022 18:26:21 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/03/2022 18:26:25 - INFO - codeparrot_training - Step 4277: {'lr': 0.0004997080369856907, 'samples': 2190336, 'steps': 4277, 'loss/train': 2.590604066848755}
-03/03/2022 18:26:28 - INFO - codeparrot_training - Step 4278: {'lr': 0.0004997077805340248, 'samples': 2190848, 'steps': 4278, 'loss/train': 0.72682785987854}
-03/03/2022 18:26:29 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/03/2022 18:26:34 - INFO - codeparrot_training - Step 4279: {'lr': 0.0004997075239698445, 'samples': 2191360, 'steps': 4279, 'loss/train': 1.6795930862426758}
-03/03/2022 18:26:37 - INFO - codeparrot_training - Step 4280: {'lr': 0.0004997072672931497, 'samples': 2191872, 'steps': 4280, 'loss/train': 0.8268131017684937}
-03/03/2022 18:26:38 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/03/2022 18:26:42 - INFO - codeparrot_training - Step 4281: {'lr': 0.0004997070105039407, 'samples': 2192384, 'steps': 4281, 'loss/train': 2.489441394805908}
-03/03/2022 18:26:45 - INFO - codeparrot_training - Step 4282: {'lr': 0.0004997067536022176, 'samples': 2192896, 'steps': 4282, 'loss/train': 2.314330577850342}
-03/03/2022 18:26:46 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/03/2022 18:26:51 - INFO - codeparrot_training - Step 4283: {'lr': 0.0004997064965879804, 'samples': 2193408, 'steps': 4283, 'loss/train': 2.8974599838256836}
-03/03/2022 18:26:54 - INFO - codeparrot_training - Step 4284: {'lr': 0.0004997062394612293, 'samples': 2193920, 'steps': 4284, 'loss/train': 1.5091400146484375}
-03/03/2022 18:26:55 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/03/2022 18:26:59 - INFO - codeparrot_training - Step 4285: {'lr': 0.0004997059822219645, 'samples': 2194432, 'steps': 4285, 'loss/train': 1.181900143623352}
-03/03/2022 18:27:02 - INFO - codeparrot_training - Step 4286: {'lr': 0.000499705724870186, 'samples': 2194944, 'steps': 4286, 'loss/train': 2.6882920265197754}
-03/03/2022 18:27:03 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/03/2022 18:27:07 - INFO - codeparrot_training - Step 4287: {'lr': 0.0004997054674058941, 'samples': 2195456, 'steps': 4287, 'loss/train': 2.496251344680786}
-03/03/2022 18:27:11 - INFO - codeparrot_training - Step 4288: {'lr': 0.0004997052098290886, 'samples': 2195968, 'steps': 4288, 'loss/train': 2.141219139099121}
-03/03/2022 18:27:11 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/03/2022 18:27:16 - INFO - codeparrot_training - Step 4289: {'lr': 0.0004997049521397698, 'samples': 2196480, 'steps': 4289, 'loss/train': 3.410372495651245}
-03/03/2022 18:27:19 - INFO - codeparrot_training - Step 4290: {'lr': 0.0004997046943379379, 'samples': 2196992, 'steps': 4290, 'loss/train': 2.416654348373413}
-03/03/2022 18:27:20 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/03/2022 18:27:24 - INFO - codeparrot_training - Step 4291: {'lr': 0.0004997044364235928, 'samples': 2197504, 'steps': 4291, 'loss/train': 1.5918540954589844}
-03/03/2022 18:27:27 - INFO - codeparrot_training - Step 4292: {'lr': 0.0004997041783967348, 'samples': 2198016, 'steps': 4292, 'loss/train': 2.547029733657837}
-03/03/2022 18:27:28 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/03/2022 18:27:33 - INFO - codeparrot_training - Step 4293: {'lr': 0.0004997039202573639, 'samples': 2198528, 'steps': 4293, 'loss/train': 0.7370705604553223}
-03/03/2022 18:27:36 - INFO - codeparrot_training - Step 4294: {'lr': 0.0004997036620054803, 'samples': 2199040, 'steps': 4294, 'loss/train': 3.696993350982666}
-03/03/2022 18:27:41 - INFO - codeparrot_training - Step 4295: {'lr': 0.0004997034036410841, 'samples': 2199552, 'steps': 4295, 'loss/train': 3.2373900413513184}
-03/03/2022 18:27:44 - INFO - codeparrot_training - Step 4296: {'lr': 0.0004997031451641754, 'samples': 2200064, 'steps': 4296, 'loss/train': 2.544260025024414}
-03/03/2022 18:27:45 - INFO - codeparrot_training - Skipping example with length 285 (seq_length=1024)
-03/03/2022 18:27:49 - INFO - codeparrot_training - Step 4297: {'lr': 0.0004997028865747542, 'samples': 2200576, 'steps': 4297, 'loss/train': 2.820240020751953}
-03/03/2022 18:27:53 - INFO - codeparrot_training - Step 4298: {'lr': 0.0004997026278728209, 'samples': 2201088, 'steps': 4298, 'loss/train': 2.4059300422668457}
-03/03/2022 18:27:53 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/03/2022 18:27:58 - INFO - codeparrot_training - Step 4299: {'lr': 0.0004997023690583753, 'samples': 2201600, 'steps': 4299, 'loss/train': 2.955502986907959}
-03/03/2022 18:28:01 - INFO - codeparrot_training - Step 4300: {'lr': 0.0004997021101314179, 'samples': 2202112, 'steps': 4300, 'loss/train': 1.7855418920516968}
-03/03/2022 18:28:01 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/03/2022 18:28:06 - INFO - codeparrot_training - Step 4301: {'lr': 0.0004997018510919483, 'samples': 2202624, 'steps': 4301, 'loss/train': 1.8956694602966309}
-03/03/2022 18:28:09 - INFO - codeparrot_training - Step 4302: {'lr': 0.0004997015919399671, 'samples': 2203136, 'steps': 4302, 'loss/train': 2.6902828216552734}
-03/03/2022 18:28:09 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/03/2022 18:28:15 - INFO - codeparrot_training - Step 4303: {'lr': 0.0004997013326754742, 'samples': 2203648, 'steps': 4303, 'loss/train': 2.759458541870117}
-03/03/2022 18:28:18 - INFO - codeparrot_training - Step 4304: {'lr': 0.0004997010732984696, 'samples': 2204160, 'steps': 4304, 'loss/train': 2.708376884460449}
-03/03/2022 18:28:18 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/03/2022 18:28:23 - INFO - codeparrot_training - Step 4305: {'lr': 0.0004997008138089536, 'samples': 2204672, 'steps': 4305, 'loss/train': 2.6910762786865234}
-03/03/2022 18:28:26 - INFO - codeparrot_training - Step 4306: {'lr': 0.0004997005542069263, 'samples': 2205184, 'steps': 4306, 'loss/train': 2.1699793338775635}
-03/03/2022 18:28:26 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/03/2022 18:28:31 - INFO - codeparrot_training - Step 4307: {'lr': 0.0004997002944923878, 'samples': 2205696, 'steps': 4307, 'loss/train': 3.3660695552825928}
-03/03/2022 18:28:35 - INFO - codeparrot_training - Step 4308: {'lr': 0.0004997000346653381, 'samples': 2206208, 'steps': 4308, 'loss/train': 2.6844048500061035}
-03/03/2022 18:28:35 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/03/2022 18:28:40 - INFO - codeparrot_training - Step 4309: {'lr': 0.0004996997747257775, 'samples': 2206720, 'steps': 4309, 'loss/train': 3.1445083618164062}
-03/03/2022 18:28:43 - INFO - codeparrot_training - Step 4310: {'lr': 0.000499699514673706, 'samples': 2207232, 'steps': 4310, 'loss/train': 4.650846481323242}
-03/03/2022 18:28:48 - INFO - codeparrot_training - Step 4311: {'lr': 0.0004996992545091239, 'samples': 2207744, 'steps': 4311, 'loss/train': 2.638298988342285}
-03/03/2022 18:28:52 - INFO - codeparrot_training - Step 4312: {'lr': 0.000499698994232031, 'samples': 2208256, 'steps': 4312, 'loss/train': 2.455766439437866}
-03/03/2022 18:28:52 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/03/2022 18:28:57 - INFO - codeparrot_training - Step 4313: {'lr': 0.0004996987338424276, 'samples': 2208768, 'steps': 4313, 'loss/train': 2.582677125930786}
-03/03/2022 18:29:00 - INFO - codeparrot_training - Step 4314: {'lr': 0.0004996984733403138, 'samples': 2209280, 'steps': 4314, 'loss/train': 2.7016289234161377}
-03/03/2022 18:29:00 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/03/2022 18:29:05 - INFO - codeparrot_training - Step 4315: {'lr': 0.0004996982127256898, 'samples': 2209792, 'steps': 4315, 'loss/train': 2.1626553535461426}
-03/03/2022 18:29:08 - INFO - codeparrot_training - Step 4316: {'lr': 0.0004996979519985556, 'samples': 2210304, 'steps': 4316, 'loss/train': 1.4530099630355835}
-03/03/2022 18:29:09 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/03/2022 18:29:14 - INFO - codeparrot_training - Step 4317: {'lr': 0.0004996976911589114, 'samples': 2210816, 'steps': 4317, 'loss/train': 1.4317450523376465}
-03/03/2022 18:29:17 - INFO - codeparrot_training - Step 4318: {'lr': 0.0004996974302067572, 'samples': 2211328, 'steps': 4318, 'loss/train': 2.0460665225982666}
-03/03/2022 18:29:17 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/03/2022 18:29:22 - INFO - codeparrot_training - Step 4319: {'lr': 0.0004996971691420931, 'samples': 2211840, 'steps': 4319, 'loss/train': 2.122131824493408}
-03/03/2022 18:29:25 - INFO - codeparrot_training - Step 4320: {'lr': 0.0004996969079649195, 'samples': 2212352, 'steps': 4320, 'loss/train': 2.228632926940918}
-03/03/2022 18:29:25 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/03/2022 18:29:30 - INFO - codeparrot_training - Step 4321: {'lr': 0.0004996966466752362, 'samples': 2212864, 'steps': 4321, 'loss/train': 2.2341220378875732}
-03/03/2022 18:29:34 - INFO - codeparrot_training - Step 4322: {'lr': 0.0004996963852730436, 'samples': 2213376, 'steps': 4322, 'loss/train': 3.526921510696411}
-03/03/2022 18:29:34 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/03/2022 18:29:39 - INFO - codeparrot_training - Step 4323: {'lr': 0.0004996961237583415, 'samples': 2213888, 'steps': 4323, 'loss/train': 2.496530294418335}
-03/03/2022 18:29:42 - INFO - codeparrot_training - Step 4324: {'lr': 0.0004996958621311302, 'samples': 2214400, 'steps': 4324, 'loss/train': 3.1492295265197754}
-03/03/2022 18:29:42 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/03/2022 18:29:47 - INFO - codeparrot_training - Step 4325: {'lr': 0.00049969560039141, 'samples': 2214912, 'steps': 4325, 'loss/train': 1.7919201850891113}
-03/03/2022 18:29:51 - INFO - codeparrot_training - Step 4326: {'lr': 0.0004996953385391806, 'samples': 2215424, 'steps': 4326, 'loss/train': 2.5024709701538086}
-03/03/2022 18:29:51 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/03/2022 18:29:56 - INFO - codeparrot_training - Step 4327: {'lr': 0.0004996950765744424, 'samples': 2215936, 'steps': 4327, 'loss/train': 2.5253944396972656}
-03/03/2022 18:29:59 - INFO - codeparrot_training - Step 4328: {'lr': 0.0004996948144971953, 'samples': 2216448, 'steps': 4328, 'loss/train': 0.5469165444374084}
-03/03/2022 18:29:59 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/03/2022 18:30:05 - INFO - codeparrot_training - Step 4329: {'lr': 0.0004996945523074398, 'samples': 2216960, 'steps': 4329, 'loss/train': 2.994957208633423}
-03/03/2022 18:30:08 - INFO - codeparrot_training - Step 4330: {'lr': 0.0004996942900051757, 'samples': 2217472, 'steps': 4330, 'loss/train': 2.8696177005767822}
-03/03/2022 18:30:08 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/03/2022 18:30:13 - INFO - codeparrot_training - Step 4331: {'lr': 0.0004996940275904031, 'samples': 2217984, 'steps': 4331, 'loss/train': 2.6124939918518066}
-03/03/2022 18:30:16 - INFO - codeparrot_training - Step 4332: {'lr': 0.0004996937650631224, 'samples': 2218496, 'steps': 4332, 'loss/train': 1.142934799194336}
-03/03/2022 18:30:16 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/03/2022 18:30:22 - INFO - codeparrot_training - Step 4333: {'lr': 0.0004996935024233335, 'samples': 2219008, 'steps': 4333, 'loss/train': 2.541126012802124}
-03/03/2022 18:30:25 - INFO - codeparrot_training - Step 4334: {'lr': 0.0004996932396710365, 'samples': 2219520, 'steps': 4334, 'loss/train': 2.222437858581543}
-03/03/2022 18:30:25 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/03/2022 18:30:30 - INFO - codeparrot_training - Step 4335: {'lr': 0.0004996929768062316, 'samples': 2220032, 'steps': 4335, 'loss/train': 1.3417575359344482}
-03/03/2022 18:30:33 - INFO - codeparrot_training - Step 4336: {'lr': 0.0004996927138289189, 'samples': 2220544, 'steps': 4336, 'loss/train': 2.144819736480713}
-03/03/2022 18:30:33 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/03/2022 18:30:38 - INFO - codeparrot_training - Step 4337: {'lr': 0.0004996924507390985, 'samples': 2221056, 'steps': 4337, 'loss/train': 3.5478854179382324}
-03/03/2022 18:30:42 - INFO - codeparrot_training - Step 4338: {'lr': 0.0004996921875367705, 'samples': 2221568, 'steps': 4338, 'loss/train': 1.6496244668960571}
-03/03/2022 18:30:42 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/03/2022 18:30:47 - INFO - codeparrot_training - Step 4339: {'lr': 0.0004996919242219352, 'samples': 2222080, 'steps': 4339, 'loss/train': 2.7958552837371826}
-03/03/2022 18:30:50 - INFO - codeparrot_training - Step 4340: {'lr': 0.0004996916607945925, 'samples': 2222592, 'steps': 4340, 'loss/train': 2.4317195415496826}
-03/03/2022 18:30:51 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/03/2022 18:30:55 - INFO - codeparrot_training - Step 4341: {'lr': 0.0004996913972547426, 'samples': 2223104, 'steps': 4341, 'loss/train': 2.8689799308776855}
-03/03/2022 18:30:59 - INFO - codeparrot_training - Step 4342: {'lr': 0.0004996911336023855, 'samples': 2223616, 'steps': 4342, 'loss/train': 2.3515217304229736}
-03/03/2022 18:30:59 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/03/2022 18:31:04 - INFO - codeparrot_training - Step 4343: {'lr': 0.0004996908698375216, 'samples': 2224128, 'steps': 4343, 'loss/train': 2.992849111557007}
-03/03/2022 18:31:07 - INFO - codeparrot_training - Step 4344: {'lr': 0.0004996906059601507, 'samples': 2224640, 'steps': 4344, 'loss/train': 2.367928981781006}
-03/03/2022 18:31:07 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/03/2022 18:31:12 - INFO - codeparrot_training - Step 4345: {'lr': 0.0004996903419702731, 'samples': 2225152, 'steps': 4345, 'loss/train': 1.823011875152588}
-03/03/2022 18:31:15 - INFO - codeparrot_training - Step 4346: {'lr': 0.0004996900778678889, 'samples': 2225664, 'steps': 4346, 'loss/train': 2.4864914417266846}
-03/03/2022 18:31:16 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/03/2022 18:31:21 - INFO - codeparrot_training - Step 4347: {'lr': 0.0004996898136529982, 'samples': 2226176, 'steps': 4347, 'loss/train': 2.3876285552978516}
-03/03/2022 18:31:24 - INFO - codeparrot_training - Step 4348: {'lr': 0.0004996895493256012, 'samples': 2226688, 'steps': 4348, 'loss/train': 2.6978161334991455}
-03/03/2022 18:31:25 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/03/2022 18:31:29 - INFO - codeparrot_training - Step 4349: {'lr': 0.0004996892848856978, 'samples': 2227200, 'steps': 4349, 'loss/train': 2.39406418800354}
-03/03/2022 18:31:32 - INFO - codeparrot_training - Step 4350: {'lr': 0.0004996890203332883, 'samples': 2227712, 'steps': 4350, 'loss/train': 2.8484408855438232}
-03/03/2022 18:31:33 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/03/2022 18:31:37 - INFO - codeparrot_training - Step 4351: {'lr': 0.0004996887556683729, 'samples': 2228224, 'steps': 4351, 'loss/train': 2.828001022338867}
-03/03/2022 18:31:41 - INFO - codeparrot_training - Step 4352: {'lr': 0.0004996884908909515, 'samples': 2228736, 'steps': 4352, 'loss/train': 2.1774840354919434}
-03/03/2022 18:31:41 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/03/2022 18:31:46 - INFO - codeparrot_training - Step 4353: {'lr': 0.0004996882260010243, 'samples': 2229248, 'steps': 4353, 'loss/train': 3.037933349609375}
-03/03/2022 18:31:49 - INFO - codeparrot_training - Step 4354: {'lr': 0.0004996879609985915, 'samples': 2229760, 'steps': 4354, 'loss/train': 2.3908474445343018}
-03/03/2022 18:31:49 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/03/2022 18:31:54 - INFO - codeparrot_training - Step 4355: {'lr': 0.0004996876958836532, 'samples': 2230272, 'steps': 4355, 'loss/train': 2.869760513305664}
-03/03/2022 18:31:57 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/03/2022 18:32:00 - INFO - codeparrot_training - Step 4356: {'lr': 0.0004996874306562093, 'samples': 2230784, 'steps': 4356, 'loss/train': 2.3235960006713867}
-03/03/2022 18:32:03 - INFO - codeparrot_training - Step 4357: {'lr': 0.0004996871653162602, 'samples': 2231296, 'steps': 4357, 'loss/train': 2.08998441696167}
-03/03/2022 18:32:06 - INFO - codeparrot_training - Step 4358: {'lr': 0.0004996868998638059, 'samples': 2231808, 'steps': 4358, 'loss/train': 2.722283363342285}
-03/03/2022 18:32:06 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/03/2022 18:32:11 - INFO - codeparrot_training - Step 4359: {'lr': 0.0004996866342988467, 'samples': 2232320, 'steps': 4359, 'loss/train': 1.4162204265594482}
-03/03/2022 18:32:15 - INFO - codeparrot_training - Step 4360: {'lr': 0.0004996863686213823, 'samples': 2232832, 'steps': 4360, 'loss/train': 0.8815621137619019}
-03/03/2022 18:32:15 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/03/2022 18:32:20 - INFO - codeparrot_training - Step 4361: {'lr': 0.0004996861028314133, 'samples': 2233344, 'steps': 4361, 'loss/train': 2.506401300430298}
-03/03/2022 18:32:23 - INFO - codeparrot_training - Step 4362: {'lr': 0.0004996858369289394, 'samples': 2233856, 'steps': 4362, 'loss/train': 2.2106435298919678}
-03/03/2022 18:32:23 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/03/2022 18:32:28 - INFO - codeparrot_training - Step 4363: {'lr': 0.000499685570913961, 'samples': 2234368, 'steps': 4363, 'loss/train': 0.6344096660614014}
-03/03/2022 18:32:31 - INFO - codeparrot_training - Step 4364: {'lr': 0.0004996853047864781, 'samples': 2234880, 'steps': 4364, 'loss/train': 2.9758496284484863}
-03/03/2022 18:32:32 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/03/2022 18:32:37 - INFO - codeparrot_training - Step 4365: {'lr': 0.0004996850385464909, 'samples': 2235392, 'steps': 4365, 'loss/train': 1.7241847515106201}
-03/03/2022 18:32:40 - INFO - codeparrot_training - Step 4366: {'lr': 0.0004996847721939994, 'samples': 2235904, 'steps': 4366, 'loss/train': 1.9942525625228882}
-03/03/2022 18:32:40 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/03/2022 18:32:45 - INFO - codeparrot_training - Step 4367: {'lr': 0.0004996845057290039, 'samples': 2236416, 'steps': 4367, 'loss/train': 2.5172691345214844}
-03/03/2022 18:32:48 - INFO - codeparrot_training - Step 4368: {'lr': 0.0004996842391515044, 'samples': 2236928, 'steps': 4368, 'loss/train': 1.4673107862472534}
-03/03/2022 18:32:48 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/03/2022 18:32:54 - INFO - codeparrot_training - Step 4369: {'lr': 0.000499683972461501, 'samples': 2237440, 'steps': 4369, 'loss/train': 2.821680784225464}
-03/03/2022 18:32:57 - INFO - codeparrot_training - Step 4370: {'lr': 0.0004996837056589938, 'samples': 2237952, 'steps': 4370, 'loss/train': 2.858996868133545}
-03/03/2022 18:32:59 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/03/2022 18:33:02 - INFO - codeparrot_training - Step 4371: {'lr': 0.0004996834387439831, 'samples': 2238464, 'steps': 4371, 'loss/train': 3.237086772918701}
-03/03/2022 18:33:05 - INFO - codeparrot_training - Step 4372: {'lr': 0.0004996831717164689, 'samples': 2238976, 'steps': 4372, 'loss/train': 1.8775861263275146}
-03/03/2022 18:33:07 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/03/2022 18:33:11 - INFO - codeparrot_training - Step 4373: {'lr': 0.0004996829045764512, 'samples': 2239488, 'steps': 4373, 'loss/train': 2.146308183670044}
-03/03/2022 18:33:14 - INFO - codeparrot_training - Step 4374: {'lr': 0.0004996826373239303, 'samples': 2240000, 'steps': 4374, 'loss/train': 2.7931647300720215}
-03/03/2022 18:33:15 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/03/2022 18:33:19 - INFO - codeparrot_training - Step 4375: {'lr': 0.0004996823699589062, 'samples': 2240512, 'steps': 4375, 'loss/train': 2.416057825088501}
-03/03/2022 18:33:22 - INFO - codeparrot_training - Step 4376: {'lr': 0.0004996821024813791, 'samples': 2241024, 'steps': 4376, 'loss/train': 3.0219902992248535}
-03/03/2022 18:33:23 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/03/2022 18:33:27 - INFO - codeparrot_training - Step 4377: {'lr': 0.0004996818348913491, 'samples': 2241536, 'steps': 4377, 'loss/train': 1.6127864122390747}
-03/03/2022 18:33:31 - INFO - codeparrot_training - Step 4378: {'lr': 0.0004996815671888163, 'samples': 2242048, 'steps': 4378, 'loss/train': 2.1656272411346436}
-03/03/2022 18:33:32 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/03/2022 18:33:36 - INFO - codeparrot_training - Step 4379: {'lr': 0.000499681299373781, 'samples': 2242560, 'steps': 4379, 'loss/train': 2.604130506515503}
-03/03/2022 18:33:39 - INFO - codeparrot_training - Step 4380: {'lr': 0.0004996810314462429, 'samples': 2243072, 'steps': 4380, 'loss/train': 3.3166394233703613}
-03/03/2022 18:33:40 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/03/2022 18:33:44 - INFO - codeparrot_training - Step 4381: {'lr': 0.0004996807634062025, 'samples': 2243584, 'steps': 4381, 'loss/train': 2.961524724960327}
-03/03/2022 18:33:47 - INFO - codeparrot_training - Step 4382: {'lr': 0.0004996804952536599, 'samples': 2244096, 'steps': 4382, 'loss/train': 1.5539356470108032}
-03/03/2022 18:33:48 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/03/2022 18:33:53 - INFO - codeparrot_training - Step 4383: {'lr': 0.0004996802269886149, 'samples': 2244608, 'steps': 4383, 'loss/train': 1.9402815103530884}
-03/03/2022 18:33:56 - INFO - codeparrot_training - Step 4384: {'lr': 0.0004996799586110681, 'samples': 2245120, 'steps': 4384, 'loss/train': 1.4335135221481323}
-03/03/2022 18:33:57 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/03/2022 18:34:01 - INFO - codeparrot_training - Step 4385: {'lr': 0.0004996796901210192, 'samples': 2245632, 'steps': 4385, 'loss/train': 3.063713550567627}
-03/03/2022 18:34:04 - INFO - codeparrot_training - Step 4386: {'lr': 0.0004996794215184685, 'samples': 2246144, 'steps': 4386, 'loss/train': 2.110746145248413}
-03/03/2022 18:34:05 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/03/2022 18:34:10 - INFO - codeparrot_training - Step 4387: {'lr': 0.0004996791528034161, 'samples': 2246656, 'steps': 4387, 'loss/train': 2.998420000076294}
-03/03/2022 18:34:13 - INFO - codeparrot_training - Step 4388: {'lr': 0.0004996788839758622, 'samples': 2247168, 'steps': 4388, 'loss/train': 2.4892635345458984}
-03/03/2022 18:34:14 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/03/2022 18:34:18 - INFO - codeparrot_training - Step 4389: {'lr': 0.0004996786150358068, 'samples': 2247680, 'steps': 4389, 'loss/train': 4.476348876953125}
-03/03/2022 18:34:21 - INFO - codeparrot_training - Step 4390: {'lr': 0.00049967834598325, 'samples': 2248192, 'steps': 4390, 'loss/train': 2.510578155517578}
-03/03/2022 18:34:22 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/03/2022 18:34:26 - INFO - codeparrot_training - Step 4391: {'lr': 0.0004996780768181921, 'samples': 2248704, 'steps': 4391, 'loss/train': 1.3088515996932983}
-03/03/2022 18:34:30 - INFO - codeparrot_training - Step 4392: {'lr': 0.0004996778075406331, 'samples': 2249216, 'steps': 4392, 'loss/train': 2.9308276176452637}
-03/03/2022 18:34:30 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/03/2022 18:34:35 - INFO - codeparrot_training - Step 4393: {'lr': 0.0004996775381505731, 'samples': 2249728, 'steps': 4393, 'loss/train': 2.195002555847168}
-03/03/2022 18:34:38 - INFO - codeparrot_training - Step 4394: {'lr': 0.0004996772686480122, 'samples': 2250240, 'steps': 4394, 'loss/train': 2.6623852252960205}
-03/03/2022 18:34:39 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/03/2022 18:34:43 - INFO - codeparrot_training - Step 4395: {'lr': 0.0004996769990329507, 'samples': 2250752, 'steps': 4395, 'loss/train': 2.9987738132476807}
-03/03/2022 18:34:46 - INFO - codeparrot_training - Step 4396: {'lr': 0.0004996767293053885, 'samples': 2251264, 'steps': 4396, 'loss/train': 2.5764143466949463}
-03/03/2022 18:34:47 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/03/2022 18:34:52 - INFO - codeparrot_training - Step 4397: {'lr': 0.0004996764594653258, 'samples': 2251776, 'steps': 4397, 'loss/train': 2.5048840045928955}
-03/03/2022 18:34:55 - INFO - codeparrot_training - Step 4398: {'lr': 0.0004996761895127628, 'samples': 2252288, 'steps': 4398, 'loss/train': 2.230863332748413}
-03/03/2022 18:34:55 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/03/2022 18:35:00 - INFO - codeparrot_training - Step 4399: {'lr': 0.0004996759194476996, 'samples': 2252800, 'steps': 4399, 'loss/train': 2.132049560546875}
-03/03/2022 18:35:03 - INFO - codeparrot_training - Step 4400: {'lr': 0.0004996756492701362, 'samples': 2253312, 'steps': 4400, 'loss/train': 2.3715033531188965}
-03/03/2022 18:35:03 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/03/2022 18:35:08 - INFO - codeparrot_training - Step 4401: {'lr': 0.0004996753789800729, 'samples': 2253824, 'steps': 4401, 'loss/train': 3.0586087703704834}
-03/03/2022 18:35:12 - INFO - codeparrot_training - Step 4402: {'lr': 0.0004996751085775096, 'samples': 2254336, 'steps': 4402, 'loss/train': 2.5790276527404785}
-03/03/2022 18:35:12 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/03/2022 18:35:17 - INFO - codeparrot_training - Step 4403: {'lr': 0.0004996748380624467, 'samples': 2254848, 'steps': 4403, 'loss/train': 2.3327598571777344}
-03/03/2022 18:35:20 - INFO - codeparrot_training - Step 4404: {'lr': 0.000499674567434884, 'samples': 2255360, 'steps': 4404, 'loss/train': 2.396493434906006}
-03/03/2022 18:35:20 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/03/2022 18:35:25 - INFO - codeparrot_training - Step 4405: {'lr': 0.0004996742966948219, 'samples': 2255872, 'steps': 4405, 'loss/train': 2.6866250038146973}
-03/03/2022 18:35:29 - INFO - codeparrot_training - Step 4406: {'lr': 0.0004996740258422604, 'samples': 2256384, 'steps': 4406, 'loss/train': 2.257866859436035}
-03/03/2022 18:35:29 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/03/2022 18:35:34 - INFO - codeparrot_training - Step 4407: {'lr': 0.0004996737548771997, 'samples': 2256896, 'steps': 4407, 'loss/train': 2.4264907836914062}
-03/03/2022 18:35:37 - INFO - codeparrot_training - Step 4408: {'lr': 0.0004996734837996397, 'samples': 2257408, 'steps': 4408, 'loss/train': 2.066406726837158}
-03/03/2022 18:35:37 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/03/2022 18:35:43 - INFO - codeparrot_training - Step 4409: {'lr': 0.0004996732126095807, 'samples': 2257920, 'steps': 4409, 'loss/train': 3.6866579055786133}
-03/03/2022 18:35:46 - INFO - codeparrot_training - Step 4410: {'lr': 0.0004996729413070229, 'samples': 2258432, 'steps': 4410, 'loss/train': 2.640519618988037}
-03/03/2022 18:35:46 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/03/2022 18:35:51 - INFO - codeparrot_training - Step 4411: {'lr': 0.0004996726698919664, 'samples': 2258944, 'steps': 4411, 'loss/train': 2.6126174926757812}
-03/03/2022 18:35:54 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/03/2022 18:35:56 - INFO - codeparrot_training - Step 4412: {'lr': 0.0004996723983644112, 'samples': 2259456, 'steps': 4412, 'loss/train': 2.0176353454589844}
-03/03/2022 18:35:59 - INFO - codeparrot_training - Step 4413: {'lr': 0.0004996721267243573, 'samples': 2259968, 'steps': 4413, 'loss/train': 2.9792444705963135}
-03/03/2022 18:36:02 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/03/2022 18:36:05 - INFO - codeparrot_training - Step 4414: {'lr': 0.0004996718549718051, 'samples': 2260480, 'steps': 4414, 'loss/train': 1.6411380767822266}
-03/03/2022 18:36:08 - INFO - codeparrot_training - Step 4415: {'lr': 0.0004996715831067546, 'samples': 2260992, 'steps': 4415, 'loss/train': 2.9626359939575195}
-03/03/2022 18:36:10 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/03/2022 18:36:13 - INFO - codeparrot_training - Step 4416: {'lr': 0.000499671311129206, 'samples': 2261504, 'steps': 4416, 'loss/train': 2.6969351768493652}
-03/03/2022 18:36:16 - INFO - codeparrot_training - Step 4417: {'lr': 0.0004996710390391593, 'samples': 2262016, 'steps': 4417, 'loss/train': 2.5846803188323975}
-03/03/2022 18:36:19 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/03/2022 18:36:21 - INFO - codeparrot_training - Step 4418: {'lr': 0.0004996707668366147, 'samples': 2262528, 'steps': 4418, 'loss/train': 1.8627187013626099}
-03/03/2022 18:36:25 - INFO - codeparrot_training - Step 4419: {'lr': 0.0004996704945215724, 'samples': 2263040, 'steps': 4419, 'loss/train': 2.7960450649261475}
-03/03/2022 18:36:27 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/03/2022 18:36:30 - INFO - codeparrot_training - Step 4420: {'lr': 0.0004996702220940322, 'samples': 2263552, 'steps': 4420, 'loss/train': 2.8446831703186035}
-03/03/2022 18:36:33 - INFO - codeparrot_training - Step 4421: {'lr': 0.0004996699495539947, 'samples': 2264064, 'steps': 4421, 'loss/train': 1.2441693544387817}
-03/03/2022 18:36:37 - INFO - codeparrot_training - Step 4422: {'lr': 0.0004996696769014596, 'samples': 2264576, 'steps': 4422, 'loss/train': 2.26054048538208}
-03/03/2022 18:36:37 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/03/2022 18:36:42 - INFO - codeparrot_training - Step 4423: {'lr': 0.0004996694041364272, 'samples': 2265088, 'steps': 4423, 'loss/train': 1.3591479063034058}
-03/03/2022 18:36:45 - INFO - codeparrot_training - Step 4424: {'lr': 0.0004996691312588977, 'samples': 2265600, 'steps': 4424, 'loss/train': 2.7090351581573486}
-03/03/2022 18:36:45 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/03/2022 18:36:50 - INFO - codeparrot_training - Step 4425: {'lr': 0.0004996688582688711, 'samples': 2266112, 'steps': 4425, 'loss/train': 1.4263428449630737}
-03/03/2022 18:36:53 - INFO - codeparrot_training - Step 4426: {'lr': 0.0004996685851663477, 'samples': 2266624, 'steps': 4426, 'loss/train': 3.3216335773468018}
-03/03/2022 18:36:54 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/03/2022 18:36:59 - INFO - codeparrot_training - Step 4427: {'lr': 0.0004996683119513274, 'samples': 2267136, 'steps': 4427, 'loss/train': 2.856020450592041}
-03/03/2022 18:37:02 - INFO - codeparrot_training - Step 4428: {'lr': 0.0004996680386238103, 'samples': 2267648, 'steps': 4428, 'loss/train': 2.2716636657714844}
-03/03/2022 18:37:03 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/03/2022 18:37:07 - INFO - codeparrot_training - Step 4429: {'lr': 0.0004996677651837967, 'samples': 2268160, 'steps': 4429, 'loss/train': 2.9824678897857666}
-03/03/2022 18:37:11 - INFO - codeparrot_training - Step 4430: {'lr': 0.0004996674916312867, 'samples': 2268672, 'steps': 4430, 'loss/train': 2.500814437866211}
-03/03/2022 18:37:11 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/03/2022 18:37:16 - INFO - codeparrot_training - Step 4431: {'lr': 0.0004996672179662803, 'samples': 2269184, 'steps': 4431, 'loss/train': 2.5786080360412598}
-03/03/2022 18:37:19 - INFO - codeparrot_training - Step 4432: {'lr': 0.0004996669441887778, 'samples': 2269696, 'steps': 4432, 'loss/train': 2.8381242752075195}
-03/03/2022 18:37:20 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/03/2022 18:37:24 - INFO - codeparrot_training - Step 4433: {'lr': 0.0004996666702987791, 'samples': 2270208, 'steps': 4433, 'loss/train': 1.6283460855484009}
-03/03/2022 18:37:27 - INFO - codeparrot_training - Step 4434: {'lr': 0.0004996663962962846, 'samples': 2270720, 'steps': 4434, 'loss/train': 3.303316831588745}
-03/03/2022 18:37:28 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/03/2022 18:37:33 - INFO - codeparrot_training - Step 4435: {'lr': 0.0004996661221812942, 'samples': 2271232, 'steps': 4435, 'loss/train': 3.173570156097412}
-03/03/2022 18:37:36 - INFO - codeparrot_training - Step 4436: {'lr': 0.0004996658479538081, 'samples': 2271744, 'steps': 4436, 'loss/train': 1.5844521522521973}
-03/03/2022 18:37:36 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/03/2022 18:37:41 - INFO - codeparrot_training - Step 4437: {'lr': 0.0004996655736138265, 'samples': 2272256, 'steps': 4437, 'loss/train': 1.9391813278198242}
-03/03/2022 18:37:44 - INFO - codeparrot_training - Step 4438: {'lr': 0.0004996652991613494, 'samples': 2272768, 'steps': 4438, 'loss/train': 2.306976795196533}
-03/03/2022 18:37:45 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/03/2022 18:37:49 - INFO - codeparrot_training - Step 4439: {'lr': 0.0004996650245963768, 'samples': 2273280, 'steps': 4439, 'loss/train': 2.8830103874206543}
-03/03/2022 18:37:52 - INFO - codeparrot_training - Step 4440: {'lr': 0.0004996647499189092, 'samples': 2273792, 'steps': 4440, 'loss/train': 2.678385019302368}
-03/03/2022 18:37:53 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/03/2022 18:37:58 - INFO - codeparrot_training - Step 4441: {'lr': 0.0004996644751289464, 'samples': 2274304, 'steps': 4441, 'loss/train': 2.832144260406494}
-03/03/2022 18:38:01 - INFO - codeparrot_training - Step 4442: {'lr': 0.0004996642002264887, 'samples': 2274816, 'steps': 4442, 'loss/train': 2.8010382652282715}
-03/03/2022 18:38:01 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/03/2022 18:38:06 - INFO - codeparrot_training - Step 4443: {'lr': 0.0004996639252115362, 'samples': 2275328, 'steps': 4443, 'loss/train': 1.863884449005127}
-03/03/2022 18:38:09 - INFO - codeparrot_training - Step 4444: {'lr': 0.000499663650084089, 'samples': 2275840, 'steps': 4444, 'loss/train': 1.97604238986969}
-03/03/2022 18:38:10 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/03/2022 18:38:15 - INFO - codeparrot_training - Step 4445: {'lr': 0.0004996633748441472, 'samples': 2276352, 'steps': 4445, 'loss/train': 3.2015700340270996}
-03/03/2022 18:38:18 - INFO - codeparrot_training - Step 4446: {'lr': 0.0004996630994917108, 'samples': 2276864, 'steps': 4446, 'loss/train': 3.1272215843200684}
-03/03/2022 18:38:18 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/03/2022 18:38:23 - INFO - codeparrot_training - Step 4447: {'lr': 0.0004996628240267802, 'samples': 2277376, 'steps': 4447, 'loss/train': 1.6743178367614746}
-03/03/2022 18:38:26 - INFO - codeparrot_training - Step 4448: {'lr': 0.0004996625484493554, 'samples': 2277888, 'steps': 4448, 'loss/train': 2.4432613849639893}
-03/03/2022 18:38:27 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/03/2022 18:38:31 - INFO - codeparrot_training - Step 4449: {'lr': 0.0004996622727594363, 'samples': 2278400, 'steps': 4449, 'loss/train': 2.6805787086486816}
-03/03/2022 18:38:35 - INFO - codeparrot_training - Step 4450: {'lr': 0.0004996619969570234, 'samples': 2278912, 'steps': 4450, 'loss/train': 2.8536782264709473}
-03/03/2022 18:38:35 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/03/2022 18:38:40 - INFO - codeparrot_training - Step 4451: {'lr': 0.0004996617210421166, 'samples': 2279424, 'steps': 4451, 'loss/train': 2.7872047424316406}
-03/03/2022 18:38:43 - INFO - codeparrot_training - Step 4452: {'lr': 0.0004996614450147161, 'samples': 2279936, 'steps': 4452, 'loss/train': 1.790632963180542}
-03/03/2022 18:38:43 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/03/2022 18:38:48 - INFO - codeparrot_training - Step 4453: {'lr': 0.0004996611688748221, 'samples': 2280448, 'steps': 4453, 'loss/train': 1.1693707704544067}
-03/03/2022 18:38:52 - INFO - codeparrot_training - Step 4454: {'lr': 0.0004996608926224345, 'samples': 2280960, 'steps': 4454, 'loss/train': 3.115797519683838}
-03/03/2022 18:38:52 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/03/2022 18:38:57 - INFO - codeparrot_training - Step 4455: {'lr': 0.0004996606162575536, 'samples': 2281472, 'steps': 4455, 'loss/train': 2.2257065773010254}
-03/03/2022 18:39:00 - INFO - codeparrot_training - Step 4456: {'lr': 0.0004996603397801795, 'samples': 2281984, 'steps': 4456, 'loss/train': 2.2013580799102783}
-03/03/2022 18:39:00 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/03/2022 18:39:05 - INFO - codeparrot_training - Step 4457: {'lr': 0.0004996600631903123, 'samples': 2282496, 'steps': 4457, 'loss/train': 2.145881414413452}
-03/03/2022 18:39:09 - INFO - codeparrot_training - Step 4458: {'lr': 0.0004996597864879521, 'samples': 2283008, 'steps': 4458, 'loss/train': 0.4779275059700012}
-03/03/2022 18:39:09 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/03/2022 18:39:14 - INFO - codeparrot_training - Step 4459: {'lr': 0.000499659509673099, 'samples': 2283520, 'steps': 4459, 'loss/train': 3.163132905960083}
-03/03/2022 18:39:17 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/03/2022 18:39:19 - INFO - codeparrot_training - Step 4460: {'lr': 0.0004996592327457533, 'samples': 2284032, 'steps': 4460, 'loss/train': 1.8647692203521729}
-03/03/2022 18:39:22 - INFO - codeparrot_training - Step 4461: {'lr': 0.000499658955705915, 'samples': 2284544, 'steps': 4461, 'loss/train': 2.1909308433532715}
-03/03/2022 18:39:25 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/03/2022 18:39:27 - INFO - codeparrot_training - Step 4462: {'lr': 0.0004996586785535841, 'samples': 2285056, 'steps': 4462, 'loss/train': 2.2605512142181396}
-03/03/2022 18:39:31 - INFO - codeparrot_training - Step 4463: {'lr': 0.000499658401288761, 'samples': 2285568, 'steps': 4463, 'loss/train': 2.2403509616851807}
-03/03/2022 18:39:33 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/03/2022 18:39:36 - INFO - codeparrot_training - Step 4464: {'lr': 0.0004996581239114456, 'samples': 2286080, 'steps': 4464, 'loss/train': 1.7435789108276367}
-03/03/2022 18:39:39 - INFO - codeparrot_training - Step 4465: {'lr': 0.0004996578464216381, 'samples': 2286592, 'steps': 4465, 'loss/train': 2.196474552154541}
-03/03/2022 18:39:41 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/03/2022 18:39:44 - INFO - codeparrot_training - Step 4466: {'lr': 0.0004996575688193386, 'samples': 2287104, 'steps': 4466, 'loss/train': 2.4311423301696777}
-03/03/2022 18:39:48 - INFO - codeparrot_training - Step 4467: {'lr': 0.0004996572911045473, 'samples': 2287616, 'steps': 4467, 'loss/train': 2.4050772190093994}
-03/03/2022 18:39:50 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/03/2022 18:39:53 - INFO - codeparrot_training - Step 4468: {'lr': 0.0004996570132772642, 'samples': 2288128, 'steps': 4468, 'loss/train': 0.3285658359527588}
-03/03/2022 18:39:56 - INFO - codeparrot_training - Step 4469: {'lr': 0.0004996567353374896, 'samples': 2288640, 'steps': 4469, 'loss/train': 1.9346344470977783}
-03/03/2022 18:39:59 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/03/2022 18:40:01 - INFO - codeparrot_training - Step 4470: {'lr': 0.0004996564572852235, 'samples': 2289152, 'steps': 4470, 'loss/train': 1.9485158920288086}
-03/03/2022 18:40:05 - INFO - codeparrot_training - Step 4471: {'lr': 0.000499656179120466, 'samples': 2289664, 'steps': 4471, 'loss/train': 1.926476240158081}
-03/03/2022 18:40:08 - INFO - codeparrot_training - Step 4472: {'lr': 0.0004996559008432173, 'samples': 2290176, 'steps': 4472, 'loss/train': 0.333122581243515}
-03/03/2022 18:40:08 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/03/2022 18:40:13 - INFO - codeparrot_training - Step 4473: {'lr': 0.0004996556224534776, 'samples': 2290688, 'steps': 4473, 'loss/train': 2.306248903274536}
-03/03/2022 18:40:16 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/03/2022 18:40:18 - INFO - codeparrot_training - Step 4474: {'lr': 0.0004996553439512468, 'samples': 2291200, 'steps': 4474, 'loss/train': 2.319051742553711}
-03/03/2022 18:40:21 - INFO - codeparrot_training - Step 4475: {'lr': 0.0004996550653365253, 'samples': 2291712, 'steps': 4475, 'loss/train': 1.7853162288665771}
-03/03/2022 18:40:24 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/03/2022 18:40:27 - INFO - codeparrot_training - Step 4476: {'lr': 0.0004996547866093129, 'samples': 2292224, 'steps': 4476, 'loss/train': 3.0089235305786133}
-03/03/2022 18:40:30 - INFO - codeparrot_training - Step 4477: {'lr': 0.00049965450776961, 'samples': 2292736, 'steps': 4477, 'loss/train': 2.5537867546081543}
-03/03/2022 18:40:33 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/03/2022 18:40:35 - INFO - codeparrot_training - Step 4478: {'lr': 0.0004996542288174166, 'samples': 2293248, 'steps': 4478, 'loss/train': 2.556941509246826}
-03/03/2022 18:40:38 - INFO - codeparrot_training - Step 4479: {'lr': 0.0004996539497527329, 'samples': 2293760, 'steps': 4479, 'loss/train': 2.5110392570495605}
-03/03/2022 18:40:41 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/03/2022 18:40:44 - INFO - codeparrot_training - Step 4480: {'lr': 0.000499653670575559, 'samples': 2294272, 'steps': 4480, 'loss/train': 2.400174140930176}
-03/03/2022 18:40:47 - INFO - codeparrot_training - Step 4481: {'lr': 0.0004996533912858949, 'samples': 2294784, 'steps': 4481, 'loss/train': 4.368938446044922}
-03/03/2022 18:40:50 - INFO - codeparrot_training - Step 4482: {'lr': 0.000499653111883741, 'samples': 2295296, 'steps': 4482, 'loss/train': 2.521679162979126}
-03/03/2022 18:40:51 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/03/2022 18:40:55 - INFO - codeparrot_training - Step 4483: {'lr': 0.0004996528323690971, 'samples': 2295808, 'steps': 4483, 'loss/train': 2.7446067333221436}
-03/03/2022 18:40:59 - INFO - codeparrot_training - Step 4484: {'lr': 0.0004996525527419636, 'samples': 2296320, 'steps': 4484, 'loss/train': 2.9803435802459717}
-03/03/2022 18:40:59 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/03/2022 18:41:04 - INFO - codeparrot_training - Step 4485: {'lr': 0.0004996522730023404, 'samples': 2296832, 'steps': 4485, 'loss/train': 2.4842233657836914}
-03/03/2022 18:41:07 - INFO - codeparrot_training - Step 4486: {'lr': 0.0004996519931502279, 'samples': 2297344, 'steps': 4486, 'loss/train': 2.374891996383667}
-03/03/2022 18:41:09 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/03/2022 18:41:13 - INFO - codeparrot_training - Step 4487: {'lr': 0.0004996517131856259, 'samples': 2297856, 'steps': 4487, 'loss/train': 2.179633855819702}
-03/03/2022 18:41:16 - INFO - codeparrot_training - Step 4488: {'lr': 0.0004996514331085348, 'samples': 2298368, 'steps': 4488, 'loss/train': 2.2711615562438965}
-03/03/2022 18:41:18 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/03/2022 18:41:21 - INFO - codeparrot_training - Step 4489: {'lr': 0.0004996511529189546, 'samples': 2298880, 'steps': 4489, 'loss/train': 2.0145022869110107}
-03/03/2022 18:41:24 - INFO - codeparrot_training - Step 4490: {'lr': 0.0004996508726168854, 'samples': 2299392, 'steps': 4490, 'loss/train': 3.5286483764648438}
-03/03/2022 18:41:26 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/03/2022 18:41:30 - INFO - codeparrot_training - Step 4491: {'lr': 0.0004996505922023274, 'samples': 2299904, 'steps': 4491, 'loss/train': 3.4150900840759277}
-03/03/2022 18:41:33 - INFO - codeparrot_training - Step 4492: {'lr': 0.0004996503116752807, 'samples': 2300416, 'steps': 4492, 'loss/train': 0.40494608879089355}
-03/03/2022 18:41:35 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/03/2022 18:41:38 - INFO - codeparrot_training - Step 4493: {'lr': 0.0004996500310357454, 'samples': 2300928, 'steps': 4493, 'loss/train': 2.3771004676818848}
-03/03/2022 18:41:41 - INFO - codeparrot_training - Step 4494: {'lr': 0.0004996497502837217, 'samples': 2301440, 'steps': 4494, 'loss/train': 4.1367387771606445}
-03/03/2022 18:41:44 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/03/2022 18:41:47 - INFO - codeparrot_training - Step 4495: {'lr': 0.0004996494694192096, 'samples': 2301952, 'steps': 4495, 'loss/train': 2.4400084018707275}
-03/03/2022 18:41:50 - INFO - codeparrot_training - Step 4496: {'lr': 0.0004996491884422092, 'samples': 2302464, 'steps': 4496, 'loss/train': 2.199230909347534}
-03/03/2022 18:41:53 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/03/2022 18:41:55 - INFO - codeparrot_training - Step 4497: {'lr': 0.0004996489073527208, 'samples': 2302976, 'steps': 4497, 'loss/train': 3.448881149291992}
-03/03/2022 18:41:58 - INFO - codeparrot_training - Step 4498: {'lr': 0.0004996486261507445, 'samples': 2303488, 'steps': 4498, 'loss/train': 2.253598213195801}
-03/03/2022 18:42:01 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/03/2022 18:42:04 - INFO - codeparrot_training - Step 4499: {'lr': 0.0004996483448362805, 'samples': 2304000, 'steps': 4499, 'loss/train': 3.679954767227173}
-03/03/2022 18:42:07 - INFO - codeparrot_training - Step 4500: {'lr': 0.0004996480634093287, 'samples': 2304512, 'steps': 4500, 'loss/train': 2.651301383972168}
-03/03/2022 18:42:10 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/03/2022 18:42:12 - INFO - codeparrot_training - Step 4501: {'lr': 0.0004996477818698893, 'samples': 2305024, 'steps': 4501, 'loss/train': 2.139702320098877}
-03/03/2022 18:42:15 - INFO - codeparrot_training - Step 4502: {'lr': 0.0004996475002179625, 'samples': 2305536, 'steps': 4502, 'loss/train': 0.20497223734855652}
-03/03/2022 18:42:18 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/03/2022 18:42:20 - INFO - codeparrot_training - Step 4503: {'lr': 0.0004996472184535484, 'samples': 2306048, 'steps': 4503, 'loss/train': 2.7946314811706543}
-03/03/2022 18:42:24 - INFO - codeparrot_training - Step 4504: {'lr': 0.0004996469365766471, 'samples': 2306560, 'steps': 4504, 'loss/train': 2.1938178539276123}
-03/03/2022 18:42:26 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/03/2022 18:42:29 - INFO - codeparrot_training - Step 4505: {'lr': 0.0004996466545872588, 'samples': 2307072, 'steps': 4505, 'loss/train': 2.826042890548706}
-03/03/2022 18:42:32 - INFO - codeparrot_training - Step 4506: {'lr': 0.0004996463724853834, 'samples': 2307584, 'steps': 4506, 'loss/train': 2.7833034992218018}
-03/03/2022 18:42:34 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/03/2022 18:42:37 - INFO - codeparrot_training - Step 4507: {'lr': 0.0004996460902710214, 'samples': 2308096, 'steps': 4507, 'loss/train': 2.5797717571258545}
-03/03/2022 18:42:40 - INFO - codeparrot_training - Step 4508: {'lr': 0.0004996458079441727, 'samples': 2308608, 'steps': 4508, 'loss/train': 1.3006548881530762}
-03/03/2022 18:42:43 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/03/2022 18:42:46 - INFO - codeparrot_training - Step 4509: {'lr': 0.0004996455255048373, 'samples': 2309120, 'steps': 4509, 'loss/train': 2.9387824535369873}
-03/03/2022 18:42:49 - INFO - codeparrot_training - Step 4510: {'lr': 0.0004996452429530156, 'samples': 2309632, 'steps': 4510, 'loss/train': 2.245065689086914}
-03/03/2022 18:42:52 - INFO - codeparrot_training - Step 4511: {'lr': 0.0004996449602887075, 'samples': 2310144, 'steps': 4511, 'loss/train': 2.9967188835144043}
-03/03/2022 18:42:52 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/03/2022 18:42:58 - INFO - codeparrot_training - Step 4512: {'lr': 0.0004996446775119134, 'samples': 2310656, 'steps': 4512, 'loss/train': 2.7684106826782227}
-03/03/2022 18:43:01 - INFO - codeparrot_training - Step 4513: {'lr': 0.0004996443946226331, 'samples': 2311168, 'steps': 4513, 'loss/train': 1.9037456512451172}
-03/03/2022 18:43:01 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/03/2022 18:43:06 - INFO - codeparrot_training - Step 4514: {'lr': 0.000499644111620867, 'samples': 2311680, 'steps': 4514, 'loss/train': 1.1991430521011353}
-03/03/2022 18:43:09 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/03/2022 18:43:11 - INFO - codeparrot_training - Step 4515: {'lr': 0.000499643828506615, 'samples': 2312192, 'steps': 4515, 'loss/train': 2.886251449584961}
-03/03/2022 18:43:14 - INFO - codeparrot_training - Step 4516: {'lr': 0.0004996435452798775, 'samples': 2312704, 'steps': 4516, 'loss/train': 2.7607433795928955}
-03/03/2022 18:43:17 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/03/2022 18:43:20 - INFO - codeparrot_training - Step 4517: {'lr': 0.0004996432619406543, 'samples': 2313216, 'steps': 4517, 'loss/train': 2.562838554382324}
-03/03/2022 18:43:23 - INFO - codeparrot_training - Step 4518: {'lr': 0.0004996429784889458, 'samples': 2313728, 'steps': 4518, 'loss/train': 2.6622464656829834}
-03/03/2022 18:43:26 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/03/2022 18:43:28 - INFO - codeparrot_training - Step 4519: {'lr': 0.000499642694924752, 'samples': 2314240, 'steps': 4519, 'loss/train': 1.2066340446472168}
-03/03/2022 18:43:31 - INFO - codeparrot_training - Step 4520: {'lr': 0.000499642411248073, 'samples': 2314752, 'steps': 4520, 'loss/train': 1.6766794919967651}
-03/03/2022 18:43:34 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/03/2022 18:43:36 - INFO - codeparrot_training - Step 4521: {'lr': 0.0004996421274589091, 'samples': 2315264, 'steps': 4521, 'loss/train': 3.1136581897735596}
-03/03/2022 18:43:40 - INFO - codeparrot_training - Step 4522: {'lr': 0.0004996418435572603, 'samples': 2315776, 'steps': 4522, 'loss/train': 1.0299172401428223}
-03/03/2022 18:43:42 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/03/2022 18:43:45 - INFO - codeparrot_training - Step 4523: {'lr': 0.0004996415595431267, 'samples': 2316288, 'steps': 4523, 'loss/train': 3.028358221054077}
-03/03/2022 18:43:48 - INFO - codeparrot_training - Step 4524: {'lr': 0.0004996412754165084, 'samples': 2316800, 'steps': 4524, 'loss/train': 2.931763172149658}
-03/03/2022 18:43:51 - INFO - codeparrot_training - Step 4525: {'lr': 0.0004996409911774056, 'samples': 2317312, 'steps': 4525, 'loss/train': 2.7905900478363037}
-03/03/2022 18:43:51 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/03/2022 18:43:57 - INFO - codeparrot_training - Step 4526: {'lr': 0.0004996407068258186, 'samples': 2317824, 'steps': 4526, 'loss/train': 2.5149190425872803}
-03/03/2022 18:43:59 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/03/2022 18:44:02 - INFO - codeparrot_training - Step 4527: {'lr': 0.0004996404223617471, 'samples': 2318336, 'steps': 4527, 'loss/train': 1.9550740718841553}
-03/03/2022 18:44:05 - INFO - codeparrot_training - Step 4528: {'lr': 0.0004996401377851917, 'samples': 2318848, 'steps': 4528, 'loss/train': 2.70468807220459}
-03/03/2022 18:44:07 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/03/2022 18:44:10 - INFO - codeparrot_training - Step 4529: {'lr': 0.0004996398530961522, 'samples': 2319360, 'steps': 4529, 'loss/train': 2.895120143890381}
-03/03/2022 18:44:13 - INFO - codeparrot_training - Step 4530: {'lr': 0.0004996395682946288, 'samples': 2319872, 'steps': 4530, 'loss/train': 1.2683780193328857}
-03/03/2022 18:44:16 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/03/2022 18:44:18 - INFO - codeparrot_training - Step 4531: {'lr': 0.0004996392833806217, 'samples': 2320384, 'steps': 4531, 'loss/train': 2.7207252979278564}
-03/03/2022 18:44:22 - INFO - codeparrot_training - Step 4532: {'lr': 0.000499638998354131, 'samples': 2320896, 'steps': 4532, 'loss/train': 2.7755935192108154}
-03/03/2022 18:44:24 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/03/2022 18:44:27 - INFO - codeparrot_training - Step 4533: {'lr': 0.0004996387132151567, 'samples': 2321408, 'steps': 4533, 'loss/train': 3.1805593967437744}
-03/03/2022 18:44:30 - INFO - codeparrot_training - Step 4534: {'lr': 0.0004996384279636993, 'samples': 2321920, 'steps': 4534, 'loss/train': 1.7802833318710327}
-03/03/2022 18:44:33 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/03/2022 18:44:35 - INFO - codeparrot_training - Step 4535: {'lr': 0.0004996381425997584, 'samples': 2322432, 'steps': 4535, 'loss/train': 2.9403076171875}
-03/03/2022 18:44:39 - INFO - codeparrot_training - Step 4536: {'lr': 0.0004996378571233347, 'samples': 2322944, 'steps': 4536, 'loss/train': 1.889412522315979}
-03/03/2022 18:44:41 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/03/2022 18:44:44 - INFO - codeparrot_training - Step 4537: {'lr': 0.0004996375715344278, 'samples': 2323456, 'steps': 4537, 'loss/train': 2.134777069091797}
-03/03/2022 18:44:47 - INFO - codeparrot_training - Step 4538: {'lr': 0.0004996372858330382, 'samples': 2323968, 'steps': 4538, 'loss/train': 3.698913812637329}
-03/03/2022 18:44:49 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/03/2022 18:44:52 - INFO - codeparrot_training - Step 4539: {'lr': 0.0004996370000191657, 'samples': 2324480, 'steps': 4539, 'loss/train': 2.852271556854248}
-03/03/2022 18:44:56 - INFO - codeparrot_training - Step 4540: {'lr': 0.0004996367140928107, 'samples': 2324992, 'steps': 4540, 'loss/train': 2.746784210205078}
-03/03/2022 18:44:58 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/03/2022 18:45:01 - INFO - codeparrot_training - Step 4541: {'lr': 0.0004996364280539734, 'samples': 2325504, 'steps': 4541, 'loss/train': 1.9466984272003174}
-03/03/2022 18:45:04 - INFO - codeparrot_training - Step 4542: {'lr': 0.0004996361419026537, 'samples': 2326016, 'steps': 4542, 'loss/train': 2.6892871856689453}
-03/03/2022 18:45:07 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/03/2022 18:45:09 - INFO - codeparrot_training - Step 4543: {'lr': 0.0004996358556388518, 'samples': 2326528, 'steps': 4543, 'loss/train': 1.1311993598937988}
-03/03/2022 18:45:12 - INFO - codeparrot_training - Step 4544: {'lr': 0.0004996355692625678, 'samples': 2327040, 'steps': 4544, 'loss/train': 2.6714491844177246}
-03/03/2022 18:45:15 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/03/2022 18:45:18 - INFO - codeparrot_training - Step 4545: {'lr': 0.0004996352827738018, 'samples': 2327552, 'steps': 4545, 'loss/train': 1.9413790702819824}
-03/03/2022 18:45:21 - INFO - codeparrot_training - Step 4546: {'lr': 0.0004996349961725542, 'samples': 2328064, 'steps': 4546, 'loss/train': 2.4526164531707764}
-03/03/2022 18:45:24 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/03/2022 18:45:26 - INFO - codeparrot_training - Step 4547: {'lr': 0.0004996347094588247, 'samples': 2328576, 'steps': 4547, 'loss/train': 2.6600139141082764}
-03/03/2022 18:45:29 - INFO - codeparrot_training - Step 4548: {'lr': 0.0004996344226326137, 'samples': 2329088, 'steps': 4548, 'loss/train': 1.528720498085022}
-03/03/2022 18:45:32 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 18:45:35 - INFO - codeparrot_training - Step 4549: {'lr': 0.0004996341356939214, 'samples': 2329600, 'steps': 4549, 'loss/train': 2.263441562652588}
-03/03/2022 18:45:38 - INFO - codeparrot_training - Step 4550: {'lr': 0.0004996338486427477, 'samples': 2330112, 'steps': 4550, 'loss/train': 2.2804174423217773}
-03/03/2022 18:45:40 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/03/2022 18:45:43 - INFO - codeparrot_training - Step 4551: {'lr': 0.0004996335614790929, 'samples': 2330624, 'steps': 4551, 'loss/train': 2.821113109588623}
-03/03/2022 18:45:46 - INFO - codeparrot_training - Step 4552: {'lr': 0.0004996332742029571, 'samples': 2331136, 'steps': 4552, 'loss/train': 2.5891807079315186}
-03/03/2022 18:45:48 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/03/2022 18:45:51 - INFO - codeparrot_training - Step 4553: {'lr': 0.0004996329868143404, 'samples': 2331648, 'steps': 4553, 'loss/train': 2.240842342376709}
-03/03/2022 18:45:54 - INFO - codeparrot_training - Step 4554: {'lr': 0.0004996326993132428, 'samples': 2332160, 'steps': 4554, 'loss/train': 3.165534019470215}
-03/03/2022 18:45:56 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/03/2022 18:46:00 - INFO - codeparrot_training - Step 4555: {'lr': 0.0004996324116996647, 'samples': 2332672, 'steps': 4555, 'loss/train': 2.1791093349456787}
-03/03/2022 18:46:03 - INFO - codeparrot_training - Step 4556: {'lr': 0.0004996321239736059, 'samples': 2333184, 'steps': 4556, 'loss/train': 1.8402019739151}
-03/03/2022 18:46:05 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/03/2022 18:46:08 - INFO - codeparrot_training - Step 4557: {'lr': 0.000499631836135067, 'samples': 2333696, 'steps': 4557, 'loss/train': 2.265331745147705}
-03/03/2022 18:46:12 - INFO - codeparrot_training - Step 4558: {'lr': 0.0004996315481840476, 'samples': 2334208, 'steps': 4558, 'loss/train': 2.242522716522217}
-03/03/2022 18:46:13 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/03/2022 18:46:17 - INFO - codeparrot_training - Step 4559: {'lr': 0.0004996312601205482, 'samples': 2334720, 'steps': 4559, 'loss/train': 3.1619279384613037}
-03/03/2022 18:46:20 - INFO - codeparrot_training - Step 4560: {'lr': 0.0004996309719445687, 'samples': 2335232, 'steps': 4560, 'loss/train': 1.8038603067398071}
-03/03/2022 18:46:22 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/03/2022 18:46:25 - INFO - codeparrot_training - Step 4561: {'lr': 0.0004996306836561094, 'samples': 2335744, 'steps': 4561, 'loss/train': 2.522491216659546}
-03/03/2022 18:46:28 - INFO - codeparrot_training - Step 4562: {'lr': 0.0004996303952551704, 'samples': 2336256, 'steps': 4562, 'loss/train': 1.6704250574111938}
-03/03/2022 18:46:30 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/03/2022 18:46:33 - INFO - codeparrot_training - Step 4563: {'lr': 0.0004996301067417517, 'samples': 2336768, 'steps': 4563, 'loss/train': 1.854622721672058}
-03/03/2022 18:46:37 - INFO - codeparrot_training - Step 4564: {'lr': 0.0004996298181158536, 'samples': 2337280, 'steps': 4564, 'loss/train': 2.4415104389190674}
-03/03/2022 18:46:38 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/03/2022 18:46:42 - INFO - codeparrot_training - Step 4565: {'lr': 0.0004996295293774762, 'samples': 2337792, 'steps': 4565, 'loss/train': 1.9747360944747925}
-03/03/2022 18:46:45 - INFO - codeparrot_training - Step 4566: {'lr': 0.0004996292405266195, 'samples': 2338304, 'steps': 4566, 'loss/train': 2.942199468612671}
-03/03/2022 18:46:46 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/03/2022 18:46:50 - INFO - codeparrot_training - Step 4567: {'lr': 0.0004996289515632838, 'samples': 2338816, 'steps': 4567, 'loss/train': 2.2934954166412354}
-03/03/2022 18:46:54 - INFO - codeparrot_training - Step 4568: {'lr': 0.0004996286624874691, 'samples': 2339328, 'steps': 4568, 'loss/train': 3.1125307083129883}
-03/03/2022 18:46:55 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/03/2022 18:46:59 - INFO - codeparrot_training - Step 4569: {'lr': 0.0004996283732991755, 'samples': 2339840, 'steps': 4569, 'loss/train': 2.3876988887786865}
-03/03/2022 18:47:02 - INFO - codeparrot_training - Step 4570: {'lr': 0.0004996280839984033, 'samples': 2340352, 'steps': 4570, 'loss/train': 2.622971773147583}
-03/03/2022 18:47:03 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/03/2022 18:47:07 - INFO - codeparrot_training - Step 4571: {'lr': 0.0004996277945851525, 'samples': 2340864, 'steps': 4571, 'loss/train': 2.5220556259155273}
-03/03/2022 18:47:10 - INFO - codeparrot_training - Step 4572: {'lr': 0.0004996275050594233, 'samples': 2341376, 'steps': 4572, 'loss/train': 1.807889461517334}
-03/03/2022 18:47:11 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/03/2022 18:47:16 - INFO - codeparrot_training - Step 4573: {'lr': 0.0004996272154212158, 'samples': 2341888, 'steps': 4573, 'loss/train': 2.5448601245880127}
-03/03/2022 18:47:19 - INFO - codeparrot_training - Step 4574: {'lr': 0.0004996269256705301, 'samples': 2342400, 'steps': 4574, 'loss/train': 4.194021701812744}
-03/03/2022 18:47:22 - INFO - codeparrot_training - Step 4575: {'lr': 0.0004996266358073664, 'samples': 2342912, 'steps': 4575, 'loss/train': 2.7334179878234863}
-03/03/2022 18:47:24 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/03/2022 18:47:28 - INFO - codeparrot_training - Step 4576: {'lr': 0.0004996263458317248, 'samples': 2343424, 'steps': 4576, 'loss/train': 3.9706997871398926}
-03/03/2022 18:47:31 - INFO - codeparrot_training - Step 4577: {'lr': 0.0004996260557436053, 'samples': 2343936, 'steps': 4577, 'loss/train': 2.762892246246338}
-03/03/2022 18:47:33 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/03/2022 18:47:36 - INFO - codeparrot_training - Step 4578: {'lr': 0.0004996257655430083, 'samples': 2344448, 'steps': 4578, 'loss/train': 2.164797306060791}
-03/03/2022 18:47:39 - INFO - codeparrot_training - Step 4579: {'lr': 0.0004996254752299337, 'samples': 2344960, 'steps': 4579, 'loss/train': 2.627582311630249}
-03/03/2022 18:47:41 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/03/2022 18:47:44 - INFO - codeparrot_training - Step 4580: {'lr': 0.0004996251848043817, 'samples': 2345472, 'steps': 4580, 'loss/train': 1.6247608661651611}
-03/03/2022 18:47:48 - INFO - codeparrot_training - Step 4581: {'lr': 0.0004996248942663525, 'samples': 2345984, 'steps': 4581, 'loss/train': 2.698594808578491}
-03/03/2022 18:47:49 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/03/2022 18:47:53 - INFO - codeparrot_training - Step 4582: {'lr': 0.000499624603615846, 'samples': 2346496, 'steps': 4582, 'loss/train': 2.708056688308716}
-03/03/2022 18:47:56 - INFO - codeparrot_training - Step 4583: {'lr': 0.0004996243128528628, 'samples': 2347008, 'steps': 4583, 'loss/train': 1.2114841938018799}
-03/03/2022 18:47:58 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/03/2022 18:48:01 - INFO - codeparrot_training - Step 4584: {'lr': 0.0004996240219774025, 'samples': 2347520, 'steps': 4584, 'loss/train': 3.1986730098724365}
-03/03/2022 18:48:04 - INFO - codeparrot_training - Step 4585: {'lr': 0.0004996237309894656, 'samples': 2348032, 'steps': 4585, 'loss/train': 3.2915306091308594}
-03/03/2022 18:48:06 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/03/2022 18:48:10 - INFO - codeparrot_training - Step 4586: {'lr': 0.0004996234398890521, 'samples': 2348544, 'steps': 4586, 'loss/train': 3.125734567642212}
-03/03/2022 18:48:13 - INFO - codeparrot_training - Step 4587: {'lr': 0.000499623148676162, 'samples': 2349056, 'steps': 4587, 'loss/train': 1.5774887800216675}
-03/03/2022 18:48:14 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/03/2022 18:48:18 - INFO - codeparrot_training - Step 4588: {'lr': 0.0004996228573507957, 'samples': 2349568, 'steps': 4588, 'loss/train': 2.4835472106933594}
-03/03/2022 18:48:21 - INFO - codeparrot_training - Step 4589: {'lr': 0.0004996225659129531, 'samples': 2350080, 'steps': 4589, 'loss/train': 1.9856977462768555}
-03/03/2022 18:48:23 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/03/2022 18:48:27 - INFO - codeparrot_training - Step 4590: {'lr': 0.0004996222743626345, 'samples': 2350592, 'steps': 4590, 'loss/train': 2.5355513095855713}
-03/03/2022 18:48:30 - INFO - codeparrot_training - Step 4591: {'lr': 0.0004996219826998399, 'samples': 2351104, 'steps': 4591, 'loss/train': 2.6369247436523438}
-03/03/2022 18:48:32 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/03/2022 18:48:35 - INFO - codeparrot_training - Step 4592: {'lr': 0.0004996216909245695, 'samples': 2351616, 'steps': 4592, 'loss/train': 2.4580135345458984}
-03/03/2022 18:48:38 - INFO - codeparrot_training - Step 4593: {'lr': 0.0004996213990368234, 'samples': 2352128, 'steps': 4593, 'loss/train': 1.5065810680389404}
-03/03/2022 18:48:40 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/03/2022 18:48:43 - INFO - codeparrot_training - Step 4594: {'lr': 0.0004996211070366018, 'samples': 2352640, 'steps': 4594, 'loss/train': 3.6997439861297607}
-03/03/2022 18:48:47 - INFO - codeparrot_training - Step 4595: {'lr': 0.0004996208149239047, 'samples': 2353152, 'steps': 4595, 'loss/train': 2.375065326690674}
-03/03/2022 18:48:48 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/03/2022 18:48:52 - INFO - codeparrot_training - Step 4596: {'lr': 0.0004996205226987324, 'samples': 2353664, 'steps': 4596, 'loss/train': 2.5042741298675537}
-03/03/2022 18:48:55 - INFO - codeparrot_training - Step 4597: {'lr': 0.0004996202303610849, 'samples': 2354176, 'steps': 4597, 'loss/train': 2.3357157707214355}
-03/03/2022 18:48:57 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/03/2022 18:49:00 - INFO - codeparrot_training - Step 4598: {'lr': 0.0004996199379109624, 'samples': 2354688, 'steps': 4598, 'loss/train': 2.4726715087890625}
-03/03/2022 18:49:04 - INFO - codeparrot_training - Step 4599: {'lr': 0.000499619645348365, 'samples': 2355200, 'steps': 4599, 'loss/train': 1.3293640613555908}
-03/03/2022 18:49:06 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/03/2022 18:49:09 - INFO - codeparrot_training - Step 4600: {'lr': 0.0004996193526732929, 'samples': 2355712, 'steps': 4600, 'loss/train': 2.5870630741119385}
-03/03/2022 18:49:12 - INFO - codeparrot_training - Step 4601: {'lr': 0.0004996190598857461, 'samples': 2356224, 'steps': 4601, 'loss/train': 2.7861487865448}
-03/03/2022 18:49:15 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/03/2022 18:49:17 - INFO - codeparrot_training - Step 4602: {'lr': 0.0004996187669857247, 'samples': 2356736, 'steps': 4602, 'loss/train': 2.3623220920562744}
-03/03/2022 18:49:21 - INFO - codeparrot_training - Step 4603: {'lr': 0.0004996184739732291, 'samples': 2357248, 'steps': 4603, 'loss/train': 3.0617871284484863}
-03/03/2022 18:49:23 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/03/2022 18:49:26 - INFO - codeparrot_training - Step 4604: {'lr': 0.0004996181808482592, 'samples': 2357760, 'steps': 4604, 'loss/train': 2.1376233100891113}
-03/03/2022 18:49:29 - INFO - codeparrot_training - Step 4605: {'lr': 0.0004996178876108152, 'samples': 2358272, 'steps': 4605, 'loss/train': 2.2154245376586914}
-03/03/2022 18:49:32 - INFO - codeparrot_training - Step 4606: {'lr': 0.0004996175942608973, 'samples': 2358784, 'steps': 4606, 'loss/train': 3.100008010864258}
-03/03/2022 18:49:32 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/03/2022 18:49:37 - INFO - codeparrot_training - Step 4607: {'lr': 0.0004996173007985055, 'samples': 2359296, 'steps': 4607, 'loss/train': 2.7818808555603027}
-03/03/2022 18:49:41 - INFO - codeparrot_training - Step 4608: {'lr': 0.00049961700722364, 'samples': 2359808, 'steps': 4608, 'loss/train': 2.177035093307495}
-03/03/2022 18:49:41 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/03/2022 18:49:46 - INFO - codeparrot_training - Step 4609: {'lr': 0.0004996167135363009, 'samples': 2360320, 'steps': 4609, 'loss/train': 0.4171116352081299}
-03/03/2022 18:49:49 - INFO - codeparrot_training - Step 4610: {'lr': 0.0004996164197364884, 'samples': 2360832, 'steps': 4610, 'loss/train': 2.6499948501586914}
-03/03/2022 18:49:49 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/03/2022 18:49:54 - INFO - codeparrot_training - Step 4611: {'lr': 0.0004996161258242025, 'samples': 2361344, 'steps': 4611, 'loss/train': 2.4323244094848633}
-03/03/2022 18:49:57 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/03/2022 18:50:00 - INFO - codeparrot_training - Step 4612: {'lr': 0.0004996158317994436, 'samples': 2361856, 'steps': 4612, 'loss/train': 2.278235673904419}
-03/03/2022 18:50:03 - INFO - codeparrot_training - Step 4613: {'lr': 0.0004996155376622115, 'samples': 2362368, 'steps': 4613, 'loss/train': 2.5719165802001953}
-03/03/2022 18:50:05 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/03/2022 18:50:08 - INFO - codeparrot_training - Step 4614: {'lr': 0.0004996152434125066, 'samples': 2362880, 'steps': 4614, 'loss/train': 2.966566324234009}
-03/03/2022 18:50:11 - INFO - codeparrot_training - Step 4615: {'lr': 0.0004996149490503289, 'samples': 2363392, 'steps': 4615, 'loss/train': 2.5710880756378174}
-03/03/2022 18:50:14 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/03/2022 18:50:17 - INFO - codeparrot_training - Step 4616: {'lr': 0.0004996146545756786, 'samples': 2363904, 'steps': 4616, 'loss/train': 2.8298099040985107}
-03/03/2022 18:50:20 - INFO - codeparrot_training - Step 4617: {'lr': 0.0004996143599885557, 'samples': 2364416, 'steps': 4617, 'loss/train': 2.8046791553497314}
-03/03/2022 18:50:22 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/03/2022 18:50:25 - INFO - codeparrot_training - Step 4618: {'lr': 0.0004996140652889603, 'samples': 2364928, 'steps': 4618, 'loss/train': 2.1006786823272705}
-03/03/2022 18:50:28 - INFO - codeparrot_training - Step 4619: {'lr': 0.0004996137704768929, 'samples': 2365440, 'steps': 4619, 'loss/train': 2.9494175910949707}
-03/03/2022 18:50:31 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/03/2022 18:50:33 - INFO - codeparrot_training - Step 4620: {'lr': 0.0004996134755523532, 'samples': 2365952, 'steps': 4620, 'loss/train': 1.224858045578003}
-03/03/2022 18:50:37 - INFO - codeparrot_training - Step 4621: {'lr': 0.0004996131805153417, 'samples': 2366464, 'steps': 4621, 'loss/train': 2.76505184173584}
-03/03/2022 18:50:39 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/03/2022 18:50:42 - INFO - codeparrot_training - Step 4622: {'lr': 0.0004996128853658583, 'samples': 2366976, 'steps': 4622, 'loss/train': 3.0009052753448486}
-03/03/2022 18:50:45 - INFO - codeparrot_training - Step 4623: {'lr': 0.0004996125901039031, 'samples': 2367488, 'steps': 4623, 'loss/train': 2.5275073051452637}
-03/03/2022 18:50:47 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/03/2022 18:50:51 - INFO - codeparrot_training - Step 4624: {'lr': 0.0004996122947294764, 'samples': 2368000, 'steps': 4624, 'loss/train': 2.499239921569824}
-03/03/2022 18:50:54 - INFO - codeparrot_training - Step 4625: {'lr': 0.0004996119992425782, 'samples': 2368512, 'steps': 4625, 'loss/train': 5.90408182144165}
-03/03/2022 18:50:56 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/03/2022 18:50:59 - INFO - codeparrot_training - Step 4626: {'lr': 0.0004996117036432087, 'samples': 2369024, 'steps': 4626, 'loss/train': 2.400402307510376}
-03/03/2022 18:51:02 - INFO - codeparrot_training - Step 4627: {'lr': 0.000499611407931368, 'samples': 2369536, 'steps': 4627, 'loss/train': 2.334341526031494}
-03/03/2022 18:51:04 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/03/2022 18:51:07 - INFO - codeparrot_training - Step 4628: {'lr': 0.0004996111121070562, 'samples': 2370048, 'steps': 4628, 'loss/train': 2.2049238681793213}
-03/03/2022 18:51:10 - INFO - codeparrot_training - Step 4629: {'lr': 0.0004996108161702736, 'samples': 2370560, 'steps': 4629, 'loss/train': 2.459738254547119}
-03/03/2022 18:51:12 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/03/2022 18:51:16 - INFO - codeparrot_training - Step 4630: {'lr': 0.0004996105201210202, 'samples': 2371072, 'steps': 4630, 'loss/train': 2.579355478286743}
-03/03/2022 18:51:19 - INFO - codeparrot_training - Step 4631: {'lr': 0.0004996102239592961, 'samples': 2371584, 'steps': 4631, 'loss/train': 3.162139892578125}
-03/03/2022 18:51:21 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/03/2022 18:51:24 - INFO - codeparrot_training - Step 4632: {'lr': 0.0004996099276851015, 'samples': 2372096, 'steps': 4632, 'loss/train': 1.9149963855743408}
-03/03/2022 18:51:28 - INFO - codeparrot_training - Step 4633: {'lr': 0.0004996096312984365, 'samples': 2372608, 'steps': 4633, 'loss/train': 1.9362866878509521}
-03/03/2022 18:51:33 - INFO - codeparrot_training - Step 4634: {'lr': 0.0004996093347993013, 'samples': 2373120, 'steps': 4634, 'loss/train': 2.3835883140563965}
-03/03/2022 18:51:36 - INFO - codeparrot_training - Step 4635: {'lr': 0.000499609038187696, 'samples': 2373632, 'steps': 4635, 'loss/train': 1.4204899072647095}
-03/03/2022 18:51:38 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/03/2022 18:51:42 - INFO - codeparrot_training - Step 4636: {'lr': 0.0004996087414636207, 'samples': 2374144, 'steps': 4636, 'loss/train': 2.190681219100952}
-03/03/2022 18:51:45 - INFO - codeparrot_training - Step 4637: {'lr': 0.0004996084446270755, 'samples': 2374656, 'steps': 4637, 'loss/train': 2.3916056156158447}
-03/03/2022 18:51:47 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/03/2022 18:51:50 - INFO - codeparrot_training - Step 4638: {'lr': 0.0004996081476780607, 'samples': 2375168, 'steps': 4638, 'loss/train': 1.886127233505249}
-03/03/2022 18:51:53 - INFO - codeparrot_training - Step 4639: {'lr': 0.0004996078506165762, 'samples': 2375680, 'steps': 4639, 'loss/train': 2.6743874549865723}
-03/03/2022 18:51:55 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/03/2022 18:51:58 - INFO - codeparrot_training - Step 4640: {'lr': 0.0004996075534426222, 'samples': 2376192, 'steps': 4640, 'loss/train': 2.8635878562927246}
-03/03/2022 18:52:02 - INFO - codeparrot_training - Step 4641: {'lr': 0.000499607256156199, 'samples': 2376704, 'steps': 4641, 'loss/train': 2.204378128051758}
-03/03/2022 18:52:03 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/03/2022 18:52:07 - INFO - codeparrot_training - Step 4642: {'lr': 0.0004996069587573067, 'samples': 2377216, 'steps': 4642, 'loss/train': 2.8208365440368652}
-03/03/2022 18:52:10 - INFO - codeparrot_training - Step 4643: {'lr': 0.0004996066612459452, 'samples': 2377728, 'steps': 4643, 'loss/train': 2.909043550491333}
-03/03/2022 18:52:11 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/03/2022 18:52:15 - INFO - codeparrot_training - Step 4644: {'lr': 0.0004996063636221148, 'samples': 2378240, 'steps': 4644, 'loss/train': 3.126006603240967}
-03/03/2022 18:52:18 - INFO - codeparrot_training - Step 4645: {'lr': 0.0004996060658858158, 'samples': 2378752, 'steps': 4645, 'loss/train': 2.2166192531585693}
-03/03/2022 18:52:20 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/03/2022 18:52:24 - INFO - codeparrot_training - Step 4646: {'lr': 0.000499605768037048, 'samples': 2379264, 'steps': 4646, 'loss/train': 1.477970004081726}
-03/03/2022 18:52:27 - INFO - codeparrot_training - Step 4647: {'lr': 0.0004996054700758117, 'samples': 2379776, 'steps': 4647, 'loss/train': 2.9668641090393066}
-03/03/2022 18:52:28 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/03/2022 18:52:32 - INFO - codeparrot_training - Step 4648: {'lr': 0.0004996051720021071, 'samples': 2380288, 'steps': 4648, 'loss/train': 2.741767406463623}
-03/03/2022 18:52:35 - INFO - codeparrot_training - Step 4649: {'lr': 0.0004996048738159342, 'samples': 2380800, 'steps': 4649, 'loss/train': 2.473820924758911}
-03/03/2022 18:52:36 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/03/2022 18:52:41 - INFO - codeparrot_training - Step 4650: {'lr': 0.0004996045755172932, 'samples': 2381312, 'steps': 4650, 'loss/train': 3.226134777069092}
-03/03/2022 18:52:44 - INFO - codeparrot_training - Step 4651: {'lr': 0.0004996042771061843, 'samples': 2381824, 'steps': 4651, 'loss/train': 2.2292158603668213}
-03/03/2022 18:52:45 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/03/2022 18:52:49 - INFO - codeparrot_training - Step 4652: {'lr': 0.0004996039785826075, 'samples': 2382336, 'steps': 4652, 'loss/train': 2.717466354370117}
-03/03/2022 18:52:53 - INFO - codeparrot_training - Step 4653: {'lr': 0.000499603679946563, 'samples': 2382848, 'steps': 4653, 'loss/train': 1.880379557609558}
-03/03/2022 18:52:55 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/03/2022 18:52:58 - INFO - codeparrot_training - Step 4654: {'lr': 0.0004996033811980509, 'samples': 2383360, 'steps': 4654, 'loss/train': 2.5817008018493652}
-03/03/2022 18:53:01 - INFO - codeparrot_training - Step 4655: {'lr': 0.0004996030823370715, 'samples': 2383872, 'steps': 4655, 'loss/train': 2.0912535190582275}
-03/03/2022 18:53:03 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/03/2022 18:53:06 - INFO - codeparrot_training - Step 4656: {'lr': 0.0004996027833636247, 'samples': 2384384, 'steps': 4656, 'loss/train': 2.473559856414795}
-03/03/2022 18:53:09 - INFO - codeparrot_training - Step 4657: {'lr': 0.0004996024842777106, 'samples': 2384896, 'steps': 4657, 'loss/train': 3.0933618545532227}
-03/03/2022 18:53:12 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/03/2022 18:53:15 - INFO - codeparrot_training - Step 4658: {'lr': 0.0004996021850793297, 'samples': 2385408, 'steps': 4658, 'loss/train': 1.241376280784607}
-03/03/2022 18:53:18 - INFO - codeparrot_training - Step 4659: {'lr': 0.0004996018857684818, 'samples': 2385920, 'steps': 4659, 'loss/train': 2.125493049621582}
-03/03/2022 18:53:20 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/03/2022 18:53:23 - INFO - codeparrot_training - Step 4660: {'lr': 0.0004996015863451672, 'samples': 2386432, 'steps': 4660, 'loss/train': 2.280150890350342}
-03/03/2022 18:53:26 - INFO - codeparrot_training - Step 4661: {'lr': 0.0004996012868093859, 'samples': 2386944, 'steps': 4661, 'loss/train': 2.247298002243042}
-03/03/2022 18:53:29 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 18:53:32 - INFO - codeparrot_training - Step 4662: {'lr': 0.0004996009871611382, 'samples': 2387456, 'steps': 4662, 'loss/train': 2.3099477291107178}
-03/03/2022 18:53:35 - INFO - codeparrot_training - Step 4663: {'lr': 0.0004996006874004241, 'samples': 2387968, 'steps': 4663, 'loss/train': 2.141946792602539}
-03/03/2022 18:53:37 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/03/2022 18:53:40 - INFO - codeparrot_training - Step 4664: {'lr': 0.0004996003875272438, 'samples': 2388480, 'steps': 4664, 'loss/train': 2.521242141723633}
-03/03/2022 18:53:43 - INFO - codeparrot_training - Step 4665: {'lr': 0.0004996000875415973, 'samples': 2388992, 'steps': 4665, 'loss/train': 2.3308358192443848}
-03/03/2022 18:53:45 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/03/2022 18:53:48 - INFO - codeparrot_training - Step 4666: {'lr': 0.000499599787443485, 'samples': 2389504, 'steps': 4666, 'loss/train': 2.503063440322876}
-03/03/2022 18:53:52 - INFO - codeparrot_training - Step 4667: {'lr': 0.0004995994872329069, 'samples': 2390016, 'steps': 4667, 'loss/train': 2.1684467792510986}
-03/03/2022 18:53:54 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/03/2022 18:53:57 - INFO - codeparrot_training - Step 4668: {'lr': 0.000499599186909863, 'samples': 2390528, 'steps': 4668, 'loss/train': 1.9804948568344116}
-03/03/2022 18:54:00 - INFO - codeparrot_training - Step 4669: {'lr': 0.0004995988864743536, 'samples': 2391040, 'steps': 4669, 'loss/train': 2.4766082763671875}
-03/03/2022 18:54:02 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/03/2022 18:54:05 - INFO - codeparrot_training - Step 4670: {'lr': 0.0004995985859263789, 'samples': 2391552, 'steps': 4670, 'loss/train': 2.580853223800659}
-03/03/2022 18:54:08 - INFO - codeparrot_training - Step 4671: {'lr': 0.0004995982852659388, 'samples': 2392064, 'steps': 4671, 'loss/train': 1.9907152652740479}
-03/03/2022 18:54:10 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/03/2022 18:54:14 - INFO - codeparrot_training - Step 4672: {'lr': 0.0004995979844930336, 'samples': 2392576, 'steps': 4672, 'loss/train': 2.404788017272949}
-03/03/2022 18:54:17 - INFO - codeparrot_training - Step 4673: {'lr': 0.0004995976836076635, 'samples': 2393088, 'steps': 4673, 'loss/train': 2.285843849182129}
-03/03/2022 18:54:19 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/03/2022 18:54:22 - INFO - codeparrot_training - Step 4674: {'lr': 0.0004995973826098283, 'samples': 2393600, 'steps': 4674, 'loss/train': 1.7763363122940063}
-03/03/2022 18:54:25 - INFO - codeparrot_training - Step 4675: {'lr': 0.0004995970814995285, 'samples': 2394112, 'steps': 4675, 'loss/train': 2.27932071685791}
-03/03/2022 18:54:27 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/03/2022 18:54:31 - INFO - codeparrot_training - Step 4676: {'lr': 0.0004995967802767641, 'samples': 2394624, 'steps': 4676, 'loss/train': 2.321117401123047}
-03/03/2022 18:54:34 - INFO - codeparrot_training - Step 4677: {'lr': 0.0004995964789415353, 'samples': 2395136, 'steps': 4677, 'loss/train': 2.4822885990142822}
-03/03/2022 18:54:35 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/03/2022 18:54:39 - INFO - codeparrot_training - Step 4678: {'lr': 0.0004995961774938423, 'samples': 2395648, 'steps': 4678, 'loss/train': 2.2400808334350586}
-03/03/2022 18:54:42 - INFO - codeparrot_training - Step 4679: {'lr': 0.0004995958759336849, 'samples': 2396160, 'steps': 4679, 'loss/train': 1.6393972635269165}
-03/03/2022 18:54:43 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/03/2022 18:54:47 - INFO - codeparrot_training - Step 4680: {'lr': 0.0004995955742610635, 'samples': 2396672, 'steps': 4680, 'loss/train': 2.05308198928833}
-03/03/2022 18:54:50 - INFO - codeparrot_training - Step 4681: {'lr': 0.0004995952724759781, 'samples': 2397184, 'steps': 4681, 'loss/train': 2.454460859298706}
-03/03/2022 18:54:52 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/03/2022 18:54:56 - INFO - codeparrot_training - Step 4682: {'lr': 0.0004995949705784291, 'samples': 2397696, 'steps': 4682, 'loss/train': 3.408576250076294}
-03/03/2022 18:54:59 - INFO - codeparrot_training - Step 4683: {'lr': 0.0004995946685684164, 'samples': 2398208, 'steps': 4683, 'loss/train': 0.8699386715888977}
-03/03/2022 18:55:00 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/03/2022 18:55:04 - INFO - codeparrot_training - Step 4684: {'lr': 0.0004995943664459401, 'samples': 2398720, 'steps': 4684, 'loss/train': 2.600980281829834}
-03/03/2022 18:55:07 - INFO - codeparrot_training - Step 4685: {'lr': 0.0004995940642110005, 'samples': 2399232, 'steps': 4685, 'loss/train': 2.7256598472595215}
-03/03/2022 18:55:08 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/03/2022 18:55:12 - INFO - codeparrot_training - Step 4686: {'lr': 0.0004995937618635977, 'samples': 2399744, 'steps': 4686, 'loss/train': 2.7518720626831055}
-03/03/2022 18:55:16 - INFO - codeparrot_training - Step 4687: {'lr': 0.0004995934594037316, 'samples': 2400256, 'steps': 4687, 'loss/train': 2.600630283355713}
-03/03/2022 18:55:16 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/03/2022 18:55:21 - INFO - codeparrot_training - Step 4688: {'lr': 0.0004995931568314028, 'samples': 2400768, 'steps': 4688, 'loss/train': 2.7087504863739014}
-03/03/2022 18:55:24 - INFO - codeparrot_training - Step 4689: {'lr': 0.0004995928541466111, 'samples': 2401280, 'steps': 4689, 'loss/train': 1.108820915222168}
-03/03/2022 18:55:25 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/03/2022 18:55:29 - INFO - codeparrot_training - Step 4690: {'lr': 0.0004995925513493567, 'samples': 2401792, 'steps': 4690, 'loss/train': 3.3378891944885254}
-03/03/2022 18:55:32 - INFO - codeparrot_training - Step 4691: {'lr': 0.0004995922484396397, 'samples': 2402304, 'steps': 4691, 'loss/train': 2.256744861602783}
-03/03/2022 18:55:34 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/03/2022 18:55:38 - INFO - codeparrot_training - Step 4692: {'lr': 0.0004995919454174603, 'samples': 2402816, 'steps': 4692, 'loss/train': 2.5554239749908447}
-03/03/2022 18:55:41 - INFO - codeparrot_training - Step 4693: {'lr': 0.0004995916422828187, 'samples': 2403328, 'steps': 4693, 'loss/train': 2.00566029548645}
-03/03/2022 18:55:42 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/03/2022 18:55:46 - INFO - codeparrot_training - Step 4694: {'lr': 0.0004995913390357148, 'samples': 2403840, 'steps': 4694, 'loss/train': 1.5068752765655518}
-03/03/2022 18:55:49 - INFO - codeparrot_training - Step 4695: {'lr': 0.0004995910356761491, 'samples': 2404352, 'steps': 4695, 'loss/train': 2.8116512298583984}
-03/03/2022 18:55:50 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/03/2022 18:55:55 - INFO - codeparrot_training - Step 4696: {'lr': 0.0004995907322041214, 'samples': 2404864, 'steps': 4696, 'loss/train': 2.4675779342651367}
-03/03/2022 18:55:58 - INFO - codeparrot_training - Step 4697: {'lr': 0.000499590428619632, 'samples': 2405376, 'steps': 4697, 'loss/train': 2.3261730670928955}
-03/03/2022 18:55:59 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/03/2022 18:56:03 - INFO - codeparrot_training - Step 4698: {'lr': 0.000499590124922681, 'samples': 2405888, 'steps': 4698, 'loss/train': 1.7899770736694336}
-03/03/2022 18:56:06 - INFO - codeparrot_training - Step 4699: {'lr': 0.0004995898211132685, 'samples': 2406400, 'steps': 4699, 'loss/train': 1.6092798709869385}
-03/03/2022 18:56:07 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/03/2022 18:56:11 - INFO - codeparrot_training - Step 4700: {'lr': 0.0004995895171913947, 'samples': 2406912, 'steps': 4700, 'loss/train': 2.0648248195648193}
-03/03/2022 18:56:15 - INFO - codeparrot_training - Step 4701: {'lr': 0.0004995892131570598, 'samples': 2407424, 'steps': 4701, 'loss/train': 1.7186914682388306}
-03/03/2022 18:56:15 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/03/2022 18:56:20 - INFO - codeparrot_training - Step 4702: {'lr': 0.0004995889090102638, 'samples': 2407936, 'steps': 4702, 'loss/train': 0.5497411489486694}
-03/03/2022 18:56:23 - INFO - codeparrot_training - Step 4703: {'lr': 0.0004995886047510068, 'samples': 2408448, 'steps': 4703, 'loss/train': 2.1507561206817627}
-03/03/2022 18:56:24 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/03/2022 18:56:28 - INFO - codeparrot_training - Step 4704: {'lr': 0.0004995883003792891, 'samples': 2408960, 'steps': 4704, 'loss/train': 1.8343905210494995}
-03/03/2022 18:56:32 - INFO - codeparrot_training - Step 4705: {'lr': 0.0004995879958951107, 'samples': 2409472, 'steps': 4705, 'loss/train': 2.727137565612793}
-03/03/2022 18:56:32 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/03/2022 18:56:37 - INFO - codeparrot_training - Step 4706: {'lr': 0.0004995876912984719, 'samples': 2409984, 'steps': 4706, 'loss/train': 2.7634663581848145}
-03/03/2022 18:56:40 - INFO - codeparrot_training - Step 4707: {'lr': 0.0004995873865893727, 'samples': 2410496, 'steps': 4707, 'loss/train': 1.4441975355148315}
-03/03/2022 18:56:43 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/03/2022 18:56:46 - INFO - codeparrot_training - Step 4708: {'lr': 0.0004995870817678133, 'samples': 2411008, 'steps': 4708, 'loss/train': 2.786498546600342}
-03/03/2022 18:56:49 - INFO - codeparrot_training - Step 4709: {'lr': 0.0004995867768337938, 'samples': 2411520, 'steps': 4709, 'loss/train': 2.1342484951019287}
-03/03/2022 18:56:51 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/03/2022 18:56:54 - INFO - codeparrot_training - Step 4710: {'lr': 0.0004995864717873143, 'samples': 2412032, 'steps': 4710, 'loss/train': 2.513976573944092}
-03/03/2022 18:56:57 - INFO - codeparrot_training - Step 4711: {'lr': 0.000499586166628375, 'samples': 2412544, 'steps': 4711, 'loss/train': 1.603917121887207}
-03/03/2022 18:57:00 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/03/2022 18:57:03 - INFO - codeparrot_training - Step 4712: {'lr': 0.0004995858613569761, 'samples': 2413056, 'steps': 4712, 'loss/train': 1.8005483150482178}
-03/03/2022 18:57:06 - INFO - codeparrot_training - Step 4713: {'lr': 0.0004995855559731176, 'samples': 2413568, 'steps': 4713, 'loss/train': 2.355597734451294}
-03/03/2022 18:57:08 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/03/2022 18:57:11 - INFO - codeparrot_training - Step 4714: {'lr': 0.0004995852504767997, 'samples': 2414080, 'steps': 4714, 'loss/train': 2.3837673664093018}
-03/03/2022 18:57:14 - INFO - codeparrot_training - Step 4715: {'lr': 0.0004995849448680225, 'samples': 2414592, 'steps': 4715, 'loss/train': 3.0911576747894287}
-03/03/2022 18:57:16 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/03/2022 18:57:19 - INFO - codeparrot_training - Step 4716: {'lr': 0.0004995846391467862, 'samples': 2415104, 'steps': 4716, 'loss/train': 1.7520031929016113}
-03/03/2022 18:57:23 - INFO - codeparrot_training - Step 4717: {'lr': 0.000499584333313091, 'samples': 2415616, 'steps': 4717, 'loss/train': 2.256087303161621}
-03/03/2022 18:57:24 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/03/2022 18:57:28 - INFO - codeparrot_training - Step 4718: {'lr': 0.0004995840273669369, 'samples': 2416128, 'steps': 4718, 'loss/train': 2.5394482612609863}
-03/03/2022 18:57:31 - INFO - codeparrot_training - Step 4719: {'lr': 0.0004995837213083241, 'samples': 2416640, 'steps': 4719, 'loss/train': 2.3791534900665283}
-03/03/2022 18:57:33 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/03/2022 18:57:36 - INFO - codeparrot_training - Step 4720: {'lr': 0.0004995834151372526, 'samples': 2417152, 'steps': 4720, 'loss/train': 2.025820255279541}
-03/03/2022 18:57:39 - INFO - codeparrot_training - Step 4721: {'lr': 0.0004995831088537229, 'samples': 2417664, 'steps': 4721, 'loss/train': 0.9099211096763611}
-03/03/2022 18:57:41 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/03/2022 18:57:45 - INFO - codeparrot_training - Step 4722: {'lr': 0.0004995828024577346, 'samples': 2418176, 'steps': 4722, 'loss/train': 2.8879313468933105}
-03/03/2022 18:57:48 - INFO - codeparrot_training - Step 4723: {'lr': 0.0004995824959492884, 'samples': 2418688, 'steps': 4723, 'loss/train': 1.881589651107788}
-03/03/2022 18:57:49 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/03/2022 18:57:53 - INFO - codeparrot_training - Step 4724: {'lr': 0.0004995821893283841, 'samples': 2419200, 'steps': 4724, 'loss/train': 1.7407132387161255}
-03/03/2022 18:57:56 - INFO - codeparrot_training - Step 4725: {'lr': 0.0004995818825950218, 'samples': 2419712, 'steps': 4725, 'loss/train': 2.2677977085113525}
-03/03/2022 18:57:58 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/03/2022 18:58:01 - INFO - codeparrot_training - Step 4726: {'lr': 0.0004995815757492019, 'samples': 2420224, 'steps': 4726, 'loss/train': 0.9499351382255554}
-03/03/2022 18:58:05 - INFO - codeparrot_training - Step 4727: {'lr': 0.0004995812687909243, 'samples': 2420736, 'steps': 4727, 'loss/train': 2.478179693222046}
-03/03/2022 18:58:06 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/03/2022 18:58:10 - INFO - codeparrot_training - Step 4728: {'lr': 0.0004995809617201894, 'samples': 2421248, 'steps': 4728, 'loss/train': 2.4390244483947754}
-03/03/2022 18:58:13 - INFO - codeparrot_training - Step 4729: {'lr': 0.000499580654536997, 'samples': 2421760, 'steps': 4729, 'loss/train': 1.2902790307998657}
-03/03/2022 18:58:15 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/03/2022 18:58:18 - INFO - codeparrot_training - Step 4730: {'lr': 0.0004995803472413474, 'samples': 2422272, 'steps': 4730, 'loss/train': 2.216912031173706}
-03/03/2022 18:58:22 - INFO - codeparrot_training - Step 4731: {'lr': 0.0004995800398332409, 'samples': 2422784, 'steps': 4731, 'loss/train': 1.9274173974990845}
-03/03/2022 18:58:23 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/03/2022 18:58:27 - INFO - codeparrot_training - Step 4732: {'lr': 0.0004995797323126774, 'samples': 2423296, 'steps': 4732, 'loss/train': 2.1699960231781006}
-03/03/2022 18:58:30 - INFO - codeparrot_training - Step 4733: {'lr': 0.0004995794246796571, 'samples': 2423808, 'steps': 4733, 'loss/train': 2.2564847469329834}
-03/03/2022 18:58:31 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/03/2022 18:58:35 - INFO - codeparrot_training - Step 4734: {'lr': 0.0004995791169341801, 'samples': 2424320, 'steps': 4734, 'loss/train': 2.8803675174713135}
-03/03/2022 18:58:39 - INFO - codeparrot_training - Step 4735: {'lr': 0.0004995788090762467, 'samples': 2424832, 'steps': 4735, 'loss/train': 2.483232021331787}
-03/03/2022 18:58:40 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/03/2022 18:58:44 - INFO - codeparrot_training - Step 4736: {'lr': 0.000499578501105857, 'samples': 2425344, 'steps': 4736, 'loss/train': 1.0061744451522827}
-03/03/2022 18:58:47 - INFO - codeparrot_training - Step 4737: {'lr': 0.000499578193023011, 'samples': 2425856, 'steps': 4737, 'loss/train': 1.9147300720214844}
-03/03/2022 18:58:48 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/03/2022 18:58:52 - INFO - codeparrot_training - Step 4738: {'lr': 0.0004995778848277088, 'samples': 2426368, 'steps': 4738, 'loss/train': 1.797553539276123}
-03/03/2022 18:58:55 - INFO - codeparrot_training - Step 4739: {'lr': 0.0004995775765199509, 'samples': 2426880, 'steps': 4739, 'loss/train': 2.743924856185913}
-03/03/2022 18:58:57 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/03/2022 18:59:01 - INFO - codeparrot_training - Step 4740: {'lr': 0.000499577268099737, 'samples': 2427392, 'steps': 4740, 'loss/train': 1.9076218605041504}
-03/03/2022 18:59:04 - INFO - codeparrot_training - Step 4741: {'lr': 0.0004995769595670675, 'samples': 2427904, 'steps': 4741, 'loss/train': 3.0042145252227783}
-03/03/2022 18:59:05 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/03/2022 18:59:09 - INFO - codeparrot_training - Step 4742: {'lr': 0.0004995766509219425, 'samples': 2428416, 'steps': 4742, 'loss/train': 2.3705785274505615}
-03/03/2022 18:59:12 - INFO - codeparrot_training - Step 4743: {'lr': 0.0004995763421643621, 'samples': 2428928, 'steps': 4743, 'loss/train': 2.731111526489258}
-03/03/2022 18:59:13 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/03/2022 18:59:17 - INFO - codeparrot_training - Step 4744: {'lr': 0.0004995760332943264, 'samples': 2429440, 'steps': 4744, 'loss/train': 2.951591730117798}
-03/03/2022 18:59:21 - INFO - codeparrot_training - Step 4745: {'lr': 0.0004995757243118356, 'samples': 2429952, 'steps': 4745, 'loss/train': 1.689826250076294}
-03/03/2022 18:59:22 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/03/2022 18:59:26 - INFO - codeparrot_training - Step 4746: {'lr': 0.0004995754152168899, 'samples': 2430464, 'steps': 4746, 'loss/train': 5.022709846496582}
-03/03/2022 18:59:29 - INFO - codeparrot_training - Step 4747: {'lr': 0.0004995751060094893, 'samples': 2430976, 'steps': 4747, 'loss/train': 1.5847760438919067}
-03/03/2022 18:59:30 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/03/2022 18:59:34 - INFO - codeparrot_training - Step 4748: {'lr': 0.000499574796689634, 'samples': 2431488, 'steps': 4748, 'loss/train': 1.7551151514053345}
-03/03/2022 18:59:37 - INFO - codeparrot_training - Step 4749: {'lr': 0.0004995744872573242, 'samples': 2432000, 'steps': 4749, 'loss/train': 4.218952655792236}
-03/03/2022 18:59:39 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/03/2022 18:59:43 - INFO - codeparrot_training - Step 4750: {'lr': 0.00049957417771256, 'samples': 2432512, 'steps': 4750, 'loss/train': 2.422407388687134}
-03/03/2022 18:59:46 - INFO - codeparrot_training - Step 4751: {'lr': 0.0004995738680553415, 'samples': 2433024, 'steps': 4751, 'loss/train': 2.4572670459747314}
-03/03/2022 18:59:47 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/03/2022 18:59:51 - INFO - codeparrot_training - Step 4752: {'lr': 0.0004995735582856689, 'samples': 2433536, 'steps': 4752, 'loss/train': 2.680219888687134}
-03/03/2022 18:59:54 - INFO - codeparrot_training - Step 4753: {'lr': 0.0004995732484035422, 'samples': 2434048, 'steps': 4753, 'loss/train': 1.9186408519744873}
-03/03/2022 18:59:55 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/03/2022 19:00:00 - INFO - codeparrot_training - Step 4754: {'lr': 0.0004995729384089618, 'samples': 2434560, 'steps': 4754, 'loss/train': 2.4876461029052734}
-03/03/2022 19:00:03 - INFO - codeparrot_training - Step 4755: {'lr': 0.0004995726283019275, 'samples': 2435072, 'steps': 4755, 'loss/train': 2.374783754348755}
-03/03/2022 19:00:05 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/03/2022 19:00:08 - INFO - codeparrot_training - Step 4756: {'lr': 0.0004995723180824397, 'samples': 2435584, 'steps': 4756, 'loss/train': 2.2229275703430176}
-03/03/2022 19:00:11 - INFO - codeparrot_training - Step 4757: {'lr': 0.0004995720077504986, 'samples': 2436096, 'steps': 4757, 'loss/train': 2.4879696369171143}
-03/03/2022 19:00:13 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/03/2022 19:00:16 - INFO - codeparrot_training - Step 4758: {'lr': 0.0004995716973061041, 'samples': 2436608, 'steps': 4758, 'loss/train': 0.3748067021369934}
-03/03/2022 19:00:20 - INFO - codeparrot_training - Step 4759: {'lr': 0.0004995713867492564, 'samples': 2437120, 'steps': 4759, 'loss/train': 7.180379867553711}
-03/03/2022 19:00:21 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/03/2022 19:00:25 - INFO - codeparrot_training - Step 4760: {'lr': 0.0004995710760799557, 'samples': 2437632, 'steps': 4760, 'loss/train': 2.4887943267822266}
-03/03/2022 19:00:28 - INFO - codeparrot_training - Step 4761: {'lr': 0.0004995707652982022, 'samples': 2438144, 'steps': 4761, 'loss/train': 1.8410297632217407}
-03/03/2022 19:00:30 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/03/2022 19:00:33 - INFO - codeparrot_training - Step 4762: {'lr': 0.0004995704544039958, 'samples': 2438656, 'steps': 4762, 'loss/train': 2.4743151664733887}
-03/03/2022 19:00:36 - INFO - codeparrot_training - Step 4763: {'lr': 0.0004995701433973369, 'samples': 2439168, 'steps': 4763, 'loss/train': 2.673358917236328}
-03/03/2022 19:00:38 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/03/2022 19:00:42 - INFO - codeparrot_training - Step 4764: {'lr': 0.0004995698322782257, 'samples': 2439680, 'steps': 4764, 'loss/train': 2.596189022064209}
-03/03/2022 19:00:45 - INFO - codeparrot_training - Step 4765: {'lr': 0.0004995695210466619, 'samples': 2440192, 'steps': 4765, 'loss/train': 2.173036575317383}
-03/03/2022 19:00:46 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/03/2022 19:00:50 - INFO - codeparrot_training - Step 4766: {'lr': 0.0004995692097026461, 'samples': 2440704, 'steps': 4766, 'loss/train': 1.7914903163909912}
-03/03/2022 19:00:53 - INFO - codeparrot_training - Step 4767: {'lr': 0.0004995688982461783, 'samples': 2441216, 'steps': 4767, 'loss/train': 3.139613628387451}
-03/03/2022 19:00:54 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/03/2022 19:00:58 - INFO - codeparrot_training - Step 4768: {'lr': 0.0004995685866772586, 'samples': 2441728, 'steps': 4768, 'loss/train': 2.7471354007720947}
-03/03/2022 19:01:02 - INFO - codeparrot_training - Step 4769: {'lr': 0.000499568274995887, 'samples': 2442240, 'steps': 4769, 'loss/train': 1.7421013116836548}
-03/03/2022 19:01:02 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/03/2022 19:01:07 - INFO - codeparrot_training - Step 4770: {'lr': 0.0004995679632020639, 'samples': 2442752, 'steps': 4770, 'loss/train': 2.3011398315429688}
-03/03/2022 19:01:10 - INFO - codeparrot_training - Step 4771: {'lr': 0.0004995676512957892, 'samples': 2443264, 'steps': 4771, 'loss/train': 1.4951660633087158}
-03/03/2022 19:01:10 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/03/2022 19:01:16 - INFO - codeparrot_training - Step 4772: {'lr': 0.0004995673392770634, 'samples': 2443776, 'steps': 4772, 'loss/train': 1.858750343322754}
-03/03/2022 19:01:19 - INFO - codeparrot_training - Step 4773: {'lr': 0.0004995670271458863, 'samples': 2444288, 'steps': 4773, 'loss/train': 2.9087467193603516}
-03/03/2022 19:01:21 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 19:01:24 - INFO - codeparrot_training - Step 4774: {'lr': 0.0004995667149022581, 'samples': 2444800, 'steps': 4774, 'loss/train': 3.1615138053894043}
-03/03/2022 19:01:27 - INFO - codeparrot_training - Step 4775: {'lr': 0.000499566402546179, 'samples': 2445312, 'steps': 4775, 'loss/train': 2.610400915145874}
-03/03/2022 19:01:30 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/03/2022 19:01:33 - INFO - codeparrot_training - Step 4776: {'lr': 0.0004995660900776491, 'samples': 2445824, 'steps': 4776, 'loss/train': 1.832546353340149}
-03/03/2022 19:01:36 - INFO - codeparrot_training - Step 4777: {'lr': 0.0004995657774966686, 'samples': 2446336, 'steps': 4777, 'loss/train': 1.2755085229873657}
-03/03/2022 19:01:38 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/03/2022 19:01:41 - INFO - codeparrot_training - Step 4778: {'lr': 0.0004995654648032377, 'samples': 2446848, 'steps': 4778, 'loss/train': 2.5259299278259277}
-03/03/2022 19:01:44 - INFO - codeparrot_training - Step 4779: {'lr': 0.0004995651519973563, 'samples': 2447360, 'steps': 4779, 'loss/train': 1.94992196559906}
-03/03/2022 19:01:46 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/03/2022 19:01:49 - INFO - codeparrot_training - Step 4780: {'lr': 0.0004995648390790249, 'samples': 2447872, 'steps': 4780, 'loss/train': 1.9459383487701416}
-03/03/2022 19:01:52 - INFO - codeparrot_training - Step 4781: {'lr': 0.0004995645260482432, 'samples': 2448384, 'steps': 4781, 'loss/train': 2.969061851501465}
-03/03/2022 19:01:54 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/03/2022 19:01:58 - INFO - codeparrot_training - Step 4782: {'lr': 0.0004995642129050117, 'samples': 2448896, 'steps': 4782, 'loss/train': 2.0243520736694336}
-03/03/2022 19:02:01 - INFO - codeparrot_training - Step 4783: {'lr': 0.0004995638996493304, 'samples': 2449408, 'steps': 4783, 'loss/train': 2.1596310138702393}
-03/03/2022 19:02:03 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/03/2022 19:02:06 - INFO - codeparrot_training - Step 4784: {'lr': 0.0004995635862811994, 'samples': 2449920, 'steps': 4784, 'loss/train': 3.034994125366211}
-03/03/2022 19:02:09 - INFO - codeparrot_training - Step 4785: {'lr': 0.000499563272800619, 'samples': 2450432, 'steps': 4785, 'loss/train': 0.6463490724563599}
-03/03/2022 19:02:11 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/03/2022 19:02:15 - INFO - codeparrot_training - Step 4786: {'lr': 0.0004995629592075892, 'samples': 2450944, 'steps': 4786, 'loss/train': 2.113098382949829}
-03/03/2022 19:02:18 - INFO - codeparrot_training - Step 4787: {'lr': 0.0004995626455021101, 'samples': 2451456, 'steps': 4787, 'loss/train': 3.029111385345459}
-03/03/2022 19:02:19 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/03/2022 19:02:23 - INFO - codeparrot_training - Step 4788: {'lr': 0.0004995623316841821, 'samples': 2451968, 'steps': 4788, 'loss/train': 3.180652379989624}
-03/03/2022 19:02:26 - INFO - codeparrot_training - Step 4789: {'lr': 0.0004995620177538051, 'samples': 2452480, 'steps': 4789, 'loss/train': 7.288547992706299}
-03/03/2022 19:02:29 - INFO - codeparrot_training - Skipping example with length 7 (seq_length=1024)
-03/03/2022 19:02:32 - INFO - codeparrot_training - Step 4790: {'lr': 0.0004995617037109792, 'samples': 2452992, 'steps': 4790, 'loss/train': 2.0536251068115234}
-03/03/2022 19:02:35 - INFO - codeparrot_training - Step 4791: {'lr': 0.0004995613895557048, 'samples': 2453504, 'steps': 4791, 'loss/train': 2.681994676589966}
-03/03/2022 19:02:37 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/03/2022 19:02:40 - INFO - codeparrot_training - Step 4792: {'lr': 0.0004995610752879818, 'samples': 2454016, 'steps': 4792, 'loss/train': 2.03291654586792}
-03/03/2022 19:02:43 - INFO - codeparrot_training - Step 4793: {'lr': 0.0004995607609078104, 'samples': 2454528, 'steps': 4793, 'loss/train': 2.808248519897461}
-03/03/2022 19:02:45 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/03/2022 19:02:48 - INFO - codeparrot_training - Step 4794: {'lr': 0.0004995604464151908, 'samples': 2455040, 'steps': 4794, 'loss/train': 2.305968999862671}
-03/03/2022 19:02:52 - INFO - codeparrot_training - Step 4795: {'lr': 0.0004995601318101231, 'samples': 2455552, 'steps': 4795, 'loss/train': 1.9428397417068481}
-03/03/2022 19:02:53 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/03/2022 19:02:57 - INFO - codeparrot_training - Step 4796: {'lr': 0.0004995598170926074, 'samples': 2456064, 'steps': 4796, 'loss/train': 2.3756942749023438}
-03/03/2022 19:03:00 - INFO - codeparrot_training - Step 4797: {'lr': 0.000499559502262644, 'samples': 2456576, 'steps': 4797, 'loss/train': 7.142023086547852}
-03/03/2022 19:03:04 - INFO - codeparrot_training - Step 4798: {'lr': 0.000499559187320233, 'samples': 2457088, 'steps': 4798, 'loss/train': 2.333749771118164}
-03/03/2022 19:03:04 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/03/2022 19:03:09 - INFO - codeparrot_training - Step 4799: {'lr': 0.0004995588722653743, 'samples': 2457600, 'steps': 4799, 'loss/train': 5.182779312133789}
-03/03/2022 19:03:12 - INFO - codeparrot_training - Step 4800: {'lr': 0.0004995585570980684, 'samples': 2458112, 'steps': 4800, 'loss/train': 2.502042770385742}
-03/03/2022 19:03:12 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/03/2022 19:03:17 - INFO - codeparrot_training - Step 4801: {'lr': 0.0004995582418183151, 'samples': 2458624, 'steps': 4801, 'loss/train': 2.4904863834381104}
-03/03/2022 19:03:21 - INFO - codeparrot_training - Step 4802: {'lr': 0.0004995579264261148, 'samples': 2459136, 'steps': 4802, 'loss/train': 2.4681832790374756}
-03/03/2022 19:03:22 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/03/2022 19:03:26 - INFO - codeparrot_training - Step 4803: {'lr': 0.0004995576109214676, 'samples': 2459648, 'steps': 4803, 'loss/train': 2.12237548828125}
-03/03/2022 19:03:29 - INFO - codeparrot_training - Step 4804: {'lr': 0.0004995572953043736, 'samples': 2460160, 'steps': 4804, 'loss/train': 2.4620602130889893}
-03/03/2022 19:03:30 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/03/2022 19:03:34 - INFO - codeparrot_training - Step 4805: {'lr': 0.0004995569795748328, 'samples': 2460672, 'steps': 4805, 'loss/train': 3.420135259628296}
-03/03/2022 19:03:38 - INFO - codeparrot_training - Step 4806: {'lr': 0.0004995566637328456, 'samples': 2461184, 'steps': 4806, 'loss/train': 2.24116587638855}
-03/03/2022 19:03:39 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/03/2022 19:03:43 - INFO - codeparrot_training - Step 4807: {'lr': 0.0004995563477784119, 'samples': 2461696, 'steps': 4807, 'loss/train': 2.304032802581787}
-03/03/2022 19:03:46 - INFO - codeparrot_training - Step 4808: {'lr': 0.000499556031711532, 'samples': 2462208, 'steps': 4808, 'loss/train': 3.5310094356536865}
-03/03/2022 19:03:48 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/03/2022 19:03:51 - INFO - codeparrot_training - Step 4809: {'lr': 0.000499555715532206, 'samples': 2462720, 'steps': 4809, 'loss/train': 1.3793209791183472}
-03/03/2022 19:03:55 - INFO - codeparrot_training - Step 4810: {'lr': 0.0004995553992404342, 'samples': 2463232, 'steps': 4810, 'loss/train': 2.970479965209961}
-03/03/2022 19:03:57 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/03/2022 19:04:00 - INFO - codeparrot_training - Step 4811: {'lr': 0.0004995550828362163, 'samples': 2463744, 'steps': 4811, 'loss/train': 2.346778392791748}
-03/03/2022 19:04:03 - INFO - codeparrot_training - Step 4812: {'lr': 0.000499554766319553, 'samples': 2464256, 'steps': 4812, 'loss/train': 2.7982091903686523}
-03/03/2022 19:04:08 - INFO - codeparrot_training - Step 4813: {'lr': 0.0004995544496904441, 'samples': 2464768, 'steps': 4813, 'loss/train': 2.5287725925445557}
-03/03/2022 19:04:11 - INFO - codeparrot_training - Step 4814: {'lr': 0.0004995541329488897, 'samples': 2465280, 'steps': 4814, 'loss/train': 3.1618282794952393}
-03/03/2022 19:04:13 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/03/2022 19:04:17 - INFO - codeparrot_training - Step 4815: {'lr': 0.0004995538160948901, 'samples': 2465792, 'steps': 4815, 'loss/train': 3.0996172428131104}
-03/03/2022 19:04:20 - INFO - codeparrot_training - Step 4816: {'lr': 0.0004995534991284455, 'samples': 2466304, 'steps': 4816, 'loss/train': 2.564525842666626}
-03/03/2022 19:04:22 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/03/2022 19:04:25 - INFO - codeparrot_training - Step 4817: {'lr': 0.0004995531820495559, 'samples': 2466816, 'steps': 4817, 'loss/train': 2.790700912475586}
-03/03/2022 19:04:28 - INFO - codeparrot_training - Step 4818: {'lr': 0.0004995528648582214, 'samples': 2467328, 'steps': 4818, 'loss/train': 2.151323080062866}
-03/03/2022 19:04:30 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/03/2022 19:04:33 - INFO - codeparrot_training - Step 4819: {'lr': 0.0004995525475544423, 'samples': 2467840, 'steps': 4819, 'loss/train': 2.2183685302734375}
-03/03/2022 19:04:37 - INFO - codeparrot_training - Step 4820: {'lr': 0.0004995522301382187, 'samples': 2468352, 'steps': 4820, 'loss/train': 2.680931806564331}
-03/03/2022 19:04:38 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/03/2022 19:04:42 - INFO - codeparrot_training - Step 4821: {'lr': 0.0004995519126095506, 'samples': 2468864, 'steps': 4821, 'loss/train': 2.698070764541626}
-03/03/2022 19:04:45 - INFO - codeparrot_training - Step 4822: {'lr': 0.0004995515949684384, 'samples': 2469376, 'steps': 4822, 'loss/train': 3.038058042526245}
-03/03/2022 19:04:47 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/03/2022 19:04:50 - INFO - codeparrot_training - Step 4823: {'lr': 0.000499551277214882, 'samples': 2469888, 'steps': 4823, 'loss/train': 2.282282590866089}
-03/03/2022 19:04:54 - INFO - codeparrot_training - Step 4824: {'lr': 0.0004995509593488818, 'samples': 2470400, 'steps': 4824, 'loss/train': 3.021301746368408}
-03/03/2022 19:04:56 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/03/2022 19:04:59 - INFO - codeparrot_training - Step 4825: {'lr': 0.0004995506413704376, 'samples': 2470912, 'steps': 4825, 'loss/train': 0.31424516439437866}
-03/03/2022 19:05:02 - INFO - codeparrot_training - Step 4826: {'lr': 0.0004995503232795498, 'samples': 2471424, 'steps': 4826, 'loss/train': 2.6228997707366943}
-03/03/2022 19:05:04 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/03/2022 19:05:07 - INFO - codeparrot_training - Step 4827: {'lr': 0.0004995500050762185, 'samples': 2471936, 'steps': 4827, 'loss/train': 1.3924195766448975}
-03/03/2022 19:05:10 - INFO - codeparrot_training - Step 4828: {'lr': 0.0004995496867604438, 'samples': 2472448, 'steps': 4828, 'loss/train': 2.4656717777252197}
-03/03/2022 19:05:12 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/03/2022 19:05:16 - INFO - codeparrot_training - Step 4829: {'lr': 0.0004995493683322259, 'samples': 2472960, 'steps': 4829, 'loss/train': 2.274223804473877}
-03/03/2022 19:05:19 - INFO - codeparrot_training - Step 4830: {'lr': 0.0004995490497915649, 'samples': 2473472, 'steps': 4830, 'loss/train': 2.323464870452881}
-03/03/2022 19:05:21 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/03/2022 19:05:24 - INFO - codeparrot_training - Step 4831: {'lr': 0.0004995487311384609, 'samples': 2473984, 'steps': 4831, 'loss/train': 2.9853515625}
-03/03/2022 19:05:27 - INFO - codeparrot_training - Step 4832: {'lr': 0.0004995484123729141, 'samples': 2474496, 'steps': 4832, 'loss/train': 1.8002382516860962}
-03/03/2022 19:05:30 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/03/2022 19:05:33 - INFO - codeparrot_training - Step 4833: {'lr': 0.0004995480934949247, 'samples': 2475008, 'steps': 4833, 'loss/train': 2.5132851600646973}
-03/03/2022 19:05:36 - INFO - codeparrot_training - Step 4834: {'lr': 0.0004995477745044927, 'samples': 2475520, 'steps': 4834, 'loss/train': 1.5053669214248657}
-03/03/2022 19:05:38 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/03/2022 19:05:41 - INFO - codeparrot_training - Step 4835: {'lr': 0.0004995474554016184, 'samples': 2476032, 'steps': 4835, 'loss/train': 1.6865235567092896}
-03/03/2022 19:05:44 - INFO - codeparrot_training - Step 4836: {'lr': 0.0004995471361863017, 'samples': 2476544, 'steps': 4836, 'loss/train': 2.26845383644104}
-03/03/2022 19:05:46 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/03/2022 19:05:49 - INFO - codeparrot_training - Step 4837: {'lr': 0.0004995468168585431, 'samples': 2477056, 'steps': 4837, 'loss/train': 3.041250467300415}
-03/03/2022 19:05:53 - INFO - codeparrot_training - Step 4838: {'lr': 0.0004995464974183424, 'samples': 2477568, 'steps': 4838, 'loss/train': 1.528280258178711}
-03/03/2022 19:05:55 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/03/2022 19:05:58 - INFO - codeparrot_training - Step 4839: {'lr': 0.0004995461778657002, 'samples': 2478080, 'steps': 4839, 'loss/train': 1.6582547426223755}
-03/03/2022 19:06:01 - INFO - codeparrot_training - Step 4840: {'lr': 0.000499545858200616, 'samples': 2478592, 'steps': 4840, 'loss/train': 1.2643731832504272}
-03/03/2022 19:06:03 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/03/2022 19:06:06 - INFO - codeparrot_training - Step 4841: {'lr': 0.0004995455384230904, 'samples': 2479104, 'steps': 4841, 'loss/train': 3.444776773452759}
-03/03/2022 19:06:09 - INFO - codeparrot_training - Step 4842: {'lr': 0.0004995452185331235, 'samples': 2479616, 'steps': 4842, 'loss/train': 3.337554693222046}
-03/03/2022 19:06:11 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/03/2022 19:06:15 - INFO - codeparrot_training - Step 4843: {'lr': 0.0004995448985307153, 'samples': 2480128, 'steps': 4843, 'loss/train': 2.9425690174102783}
-03/03/2022 19:06:18 - INFO - codeparrot_training - Step 4844: {'lr': 0.0004995445784158661, 'samples': 2480640, 'steps': 4844, 'loss/train': 2.7902324199676514}
-03/03/2022 19:06:20 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/03/2022 19:06:24 - INFO - codeparrot_training - Step 4845: {'lr': 0.0004995442581885759, 'samples': 2481152, 'steps': 4845, 'loss/train': 1.8444856405258179}
-03/03/2022 19:06:27 - INFO - codeparrot_training - Step 4846: {'lr': 0.0004995439378488449, 'samples': 2481664, 'steps': 4846, 'loss/train': 1.2752681970596313}
-03/03/2022 19:06:29 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/03/2022 19:06:32 - INFO - codeparrot_training - Step 4847: {'lr': 0.0004995436173966733, 'samples': 2482176, 'steps': 4847, 'loss/train': 2.3915936946868896}
-03/03/2022 19:06:35 - INFO - codeparrot_training - Step 4848: {'lr': 0.0004995432968320611, 'samples': 2482688, 'steps': 4848, 'loss/train': 2.089434862136841}
-03/03/2022 19:06:38 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/03/2022 19:06:40 - INFO - codeparrot_training - Step 4849: {'lr': 0.0004995429761550086, 'samples': 2483200, 'steps': 4849, 'loss/train': 2.34389066696167}
-03/03/2022 19:06:44 - INFO - codeparrot_training - Step 4850: {'lr': 0.0004995426553655159, 'samples': 2483712, 'steps': 4850, 'loss/train': 1.768385648727417}
-03/03/2022 19:06:46 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/03/2022 19:06:49 - INFO - codeparrot_training - Step 4851: {'lr': 0.0004995423344635831, 'samples': 2484224, 'steps': 4851, 'loss/train': 2.706448793411255}
-03/03/2022 19:06:52 - INFO - codeparrot_training - Step 4852: {'lr': 0.0004995420134492105, 'samples': 2484736, 'steps': 4852, 'loss/train': 2.4971652030944824}
-03/03/2022 19:06:54 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/03/2022 19:06:57 - INFO - codeparrot_training - Step 4853: {'lr': 0.0004995416923223979, 'samples': 2485248, 'steps': 4853, 'loss/train': 2.418558120727539}
-03/03/2022 19:07:00 - INFO - codeparrot_training - Step 4854: {'lr': 0.0004995413710831458, 'samples': 2485760, 'steps': 4854, 'loss/train': 2.712454319000244}
-03/03/2022 19:07:02 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/03/2022 19:07:06 - INFO - codeparrot_training - Step 4855: {'lr': 0.0004995410497314542, 'samples': 2486272, 'steps': 4855, 'loss/train': 3.9014358520507812}
-03/03/2022 19:07:09 - INFO - codeparrot_training - Step 4856: {'lr': 0.0004995407282673232, 'samples': 2486784, 'steps': 4856, 'loss/train': 1.6873059272766113}
-03/03/2022 19:07:10 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/03/2022 19:07:14 - INFO - codeparrot_training - Step 4857: {'lr': 0.000499540406690753, 'samples': 2487296, 'steps': 4857, 'loss/train': 2.746579885482788}
-03/03/2022 19:07:17 - INFO - codeparrot_training - Step 4858: {'lr': 0.0004995400850017438, 'samples': 2487808, 'steps': 4858, 'loss/train': 1.8538373708724976}
-03/03/2022 19:07:19 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/03/2022 19:07:22 - INFO - codeparrot_training - Step 4859: {'lr': 0.0004995397632002957, 'samples': 2488320, 'steps': 4859, 'loss/train': 2.714437246322632}
-03/03/2022 19:07:26 - INFO - codeparrot_training - Step 4860: {'lr': 0.0004995394412864088, 'samples': 2488832, 'steps': 4860, 'loss/train': 2.37245512008667}
-03/03/2022 19:07:28 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/03/2022 19:07:31 - INFO - codeparrot_training - Step 4861: {'lr': 0.0004995391192600834, 'samples': 2489344, 'steps': 4861, 'loss/train': 2.2520837783813477}
-03/03/2022 19:07:34 - INFO - codeparrot_training - Step 4862: {'lr': 0.0004995387971213194, 'samples': 2489856, 'steps': 4862, 'loss/train': 3.3185737133026123}
-03/03/2022 19:07:36 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/03/2022 19:07:39 - INFO - codeparrot_training - Step 4863: {'lr': 0.000499538474870117, 'samples': 2490368, 'steps': 4863, 'loss/train': 2.0023157596588135}
-03/03/2022 19:07:43 - INFO - codeparrot_training - Step 4864: {'lr': 0.0004995381525064765, 'samples': 2490880, 'steps': 4864, 'loss/train': 2.583448886871338}
-03/03/2022 19:07:44 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/03/2022 19:07:48 - INFO - codeparrot_training - Step 4865: {'lr': 0.0004995378300303979, 'samples': 2491392, 'steps': 4865, 'loss/train': 2.6357576847076416}
-03/03/2022 19:07:51 - INFO - codeparrot_training - Step 4866: {'lr': 0.0004995375074418815, 'samples': 2491904, 'steps': 4866, 'loss/train': 2.7243049144744873}
-03/03/2022 19:07:53 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/03/2022 19:07:56 - INFO - codeparrot_training - Step 4867: {'lr': 0.0004995371847409273, 'samples': 2492416, 'steps': 4867, 'loss/train': 2.1891427040100098}
-03/03/2022 19:07:59 - INFO - codeparrot_training - Step 4868: {'lr': 0.0004995368619275355, 'samples': 2492928, 'steps': 4868, 'loss/train': 2.1025922298431396}
-03/03/2022 19:08:01 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/03/2022 19:08:05 - INFO - codeparrot_training - Step 4869: {'lr': 0.0004995365390017062, 'samples': 2493440, 'steps': 4869, 'loss/train': 2.3074140548706055}
-03/03/2022 19:08:08 - INFO - codeparrot_training - Step 4870: {'lr': 0.0004995362159634396, 'samples': 2493952, 'steps': 4870, 'loss/train': 2.1589725017547607}
-03/03/2022 19:08:10 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/03/2022 19:08:13 - INFO - codeparrot_training - Step 4871: {'lr': 0.0004995358928127359, 'samples': 2494464, 'steps': 4871, 'loss/train': 2.175736665725708}
-03/03/2022 19:08:16 - INFO - codeparrot_training - Step 4872: {'lr': 0.0004995355695495952, 'samples': 2494976, 'steps': 4872, 'loss/train': 1.2226284742355347}
-03/03/2022 19:08:18 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/03/2022 19:08:22 - INFO - codeparrot_training - Step 4873: {'lr': 0.0004995352461740174, 'samples': 2495488, 'steps': 4873, 'loss/train': 2.1534829139709473}
-03/03/2022 19:08:25 - INFO - codeparrot_training - Step 4874: {'lr': 0.0004995349226860031, 'samples': 2496000, 'steps': 4874, 'loss/train': 2.9266910552978516}
-03/03/2022 19:08:26 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/03/2022 19:08:30 - INFO - codeparrot_training - Step 4875: {'lr': 0.0004995345990855522, 'samples': 2496512, 'steps': 4875, 'loss/train': 3.0570971965789795}
-03/03/2022 19:08:33 - INFO - codeparrot_training - Step 4876: {'lr': 0.0004995342753726647, 'samples': 2497024, 'steps': 4876, 'loss/train': 2.609173536300659}
-03/03/2022 19:08:35 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/03/2022 19:08:38 - INFO - codeparrot_training - Step 4877: {'lr': 0.0004995339515473411, 'samples': 2497536, 'steps': 4877, 'loss/train': 2.687882900238037}
-03/03/2022 19:08:42 - INFO - codeparrot_training - Step 4878: {'lr': 0.0004995336276095812, 'samples': 2498048, 'steps': 4878, 'loss/train': 3.0205888748168945}
-03/03/2022 19:08:43 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/03/2022 19:08:47 - INFO - codeparrot_training - Step 4879: {'lr': 0.0004995333035593853, 'samples': 2498560, 'steps': 4879, 'loss/train': 2.140230178833008}
-03/03/2022 19:08:50 - INFO - codeparrot_training - Step 4880: {'lr': 0.0004995329793967537, 'samples': 2499072, 'steps': 4880, 'loss/train': 1.8657763004302979}
-03/03/2022 19:08:52 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/03/2022 19:08:55 - INFO - codeparrot_training - Step 4881: {'lr': 0.0004995326551216862, 'samples': 2499584, 'steps': 4881, 'loss/train': 2.8468210697174072}
-03/03/2022 19:08:58 - INFO - codeparrot_training - Step 4882: {'lr': 0.0004995323307341832, 'samples': 2500096, 'steps': 4882, 'loss/train': 2.36456036567688}
-03/03/2022 19:09:00 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/03/2022 19:09:04 - INFO - codeparrot_training - Step 4883: {'lr': 0.0004995320062342449, 'samples': 2500608, 'steps': 4883, 'loss/train': 1.5441758632659912}
-03/03/2022 19:09:07 - INFO - codeparrot_training - Step 4884: {'lr': 0.0004995316816218712, 'samples': 2501120, 'steps': 4884, 'loss/train': 2.314457893371582}
-03/03/2022 19:09:08 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/03/2022 19:09:12 - INFO - codeparrot_training - Step 4885: {'lr': 0.0004995313568970625, 'samples': 2501632, 'steps': 4885, 'loss/train': 2.21091628074646}
-03/03/2022 19:09:15 - INFO - codeparrot_training - Step 4886: {'lr': 0.0004995310320598187, 'samples': 2502144, 'steps': 4886, 'loss/train': 2.2402615547180176}
-03/03/2022 19:09:17 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/03/2022 19:09:21 - INFO - codeparrot_training - Step 4887: {'lr': 0.0004995307071101401, 'samples': 2502656, 'steps': 4887, 'loss/train': 2.9875502586364746}
-03/03/2022 19:09:24 - INFO - codeparrot_training - Step 4888: {'lr': 0.0004995303820480268, 'samples': 2503168, 'steps': 4888, 'loss/train': 2.417663812637329}
-03/03/2022 19:09:25 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/03/2022 19:09:29 - INFO - codeparrot_training - Step 4889: {'lr': 0.000499530056873479, 'samples': 2503680, 'steps': 4889, 'loss/train': 2.6566038131713867}
-03/03/2022 19:09:32 - INFO - codeparrot_training - Step 4890: {'lr': 0.0004995297315864968, 'samples': 2504192, 'steps': 4890, 'loss/train': 2.1093435287475586}
-03/03/2022 19:09:34 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/03/2022 19:09:37 - INFO - codeparrot_training - Step 4891: {'lr': 0.0004995294061870802, 'samples': 2504704, 'steps': 4891, 'loss/train': 2.0911667346954346}
-03/03/2022 19:09:41 - INFO - codeparrot_training - Step 4892: {'lr': 0.0004995290806752297, 'samples': 2505216, 'steps': 4892, 'loss/train': 3.0593526363372803}
-03/03/2022 19:09:42 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/03/2022 19:09:46 - INFO - codeparrot_training - Step 4893: {'lr': 0.0004995287550509452, 'samples': 2505728, 'steps': 4893, 'loss/train': 3.0033910274505615}
-03/03/2022 19:09:49 - INFO - codeparrot_training - Step 4894: {'lr': 0.0004995284293142268, 'samples': 2506240, 'steps': 4894, 'loss/train': 1.8219630718231201}
-03/03/2022 19:09:50 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/03/2022 19:09:54 - INFO - codeparrot_training - Step 4895: {'lr': 0.0004995281034650748, 'samples': 2506752, 'steps': 4895, 'loss/train': 2.043574333190918}
-03/03/2022 19:09:57 - INFO - codeparrot_training - Step 4896: {'lr': 0.0004995277775034894, 'samples': 2507264, 'steps': 4896, 'loss/train': 3.157118320465088}
-03/03/2022 19:09:59 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/03/2022 19:10:03 - INFO - codeparrot_training - Step 4897: {'lr': 0.0004995274514294706, 'samples': 2507776, 'steps': 4897, 'loss/train': 3.0801634788513184}
-03/03/2022 19:10:06 - INFO - codeparrot_training - Step 4898: {'lr': 0.0004995271252430184, 'samples': 2508288, 'steps': 4898, 'loss/train': 0.7655453085899353}
-03/03/2022 19:10:07 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/03/2022 19:10:11 - INFO - codeparrot_training - Step 4899: {'lr': 0.0004995267989441332, 'samples': 2508800, 'steps': 4899, 'loss/train': 1.375827431678772}
-03/03/2022 19:10:14 - INFO - codeparrot_training - Step 4900: {'lr': 0.0004995264725328151, 'samples': 2509312, 'steps': 4900, 'loss/train': 2.1573596000671387}
-03/03/2022 19:10:15 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/03/2022 19:10:19 - INFO - codeparrot_training - Step 4901: {'lr': 0.0004995261460090644, 'samples': 2509824, 'steps': 4901, 'loss/train': 2.4019925594329834}
-03/03/2022 19:10:22 - INFO - codeparrot_training - Step 4902: {'lr': 0.0004995258193728809, 'samples': 2510336, 'steps': 4902, 'loss/train': 2.480454683303833}
-03/03/2022 19:10:23 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/03/2022 19:10:28 - INFO - codeparrot_training - Step 4903: {'lr': 0.0004995254926242649, 'samples': 2510848, 'steps': 4903, 'loss/train': 2.215315341949463}
-03/03/2022 19:10:31 - INFO - codeparrot_training - Step 4904: {'lr': 0.0004995251657632165, 'samples': 2511360, 'steps': 4904, 'loss/train': 2.805739164352417}
-03/03/2022 19:10:32 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/03/2022 19:10:36 - INFO - codeparrot_training - Step 4905: {'lr': 0.000499524838789736, 'samples': 2511872, 'steps': 4905, 'loss/train': 1.9561092853546143}
-03/03/2022 19:10:39 - INFO - codeparrot_training - Step 4906: {'lr': 0.0004995245117038235, 'samples': 2512384, 'steps': 4906, 'loss/train': 1.8768481016159058}
-03/03/2022 19:10:40 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/03/2022 19:10:45 - INFO - codeparrot_training - Step 4907: {'lr': 0.0004995241845054791, 'samples': 2512896, 'steps': 4907, 'loss/train': 2.1988232135772705}
-03/03/2022 19:10:48 - INFO - codeparrot_training - Step 4908: {'lr': 0.0004995238571947029, 'samples': 2513408, 'steps': 4908, 'loss/train': 2.6251220703125}
-03/03/2022 19:10:48 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/03/2022 19:10:53 - INFO - codeparrot_training - Step 4909: {'lr': 0.0004995235297714951, 'samples': 2513920, 'steps': 4909, 'loss/train': 2.3381741046905518}
-03/03/2022 19:10:56 - INFO - codeparrot_training - Step 4910: {'lr': 0.0004995232022358559, 'samples': 2514432, 'steps': 4910, 'loss/train': 1.9262293577194214}
-03/03/2022 19:10:57 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/03/2022 19:11:01 - INFO - codeparrot_training - Step 4911: {'lr': 0.0004995228745877853, 'samples': 2514944, 'steps': 4911, 'loss/train': 2.5077426433563232}
-03/03/2022 19:11:05 - INFO - codeparrot_training - Step 4912: {'lr': 0.0004995225468272836, 'samples': 2515456, 'steps': 4912, 'loss/train': 2.658615827560425}
-03/03/2022 19:11:05 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/03/2022 19:11:10 - INFO - codeparrot_training - Step 4913: {'lr': 0.0004995222189543509, 'samples': 2515968, 'steps': 4913, 'loss/train': 0.8045946955680847}
-03/03/2022 19:11:13 - INFO - codeparrot_training - Step 4914: {'lr': 0.0004995218909689873, 'samples': 2516480, 'steps': 4914, 'loss/train': 2.7647016048431396}
-03/03/2022 19:11:13 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/03/2022 19:11:18 - INFO - codeparrot_training - Step 4915: {'lr': 0.0004995215628711931, 'samples': 2516992, 'steps': 4915, 'loss/train': 2.483281373977661}
-03/03/2022 19:11:22 - INFO - codeparrot_training - Step 4916: {'lr': 0.0004995212346609682, 'samples': 2517504, 'steps': 4916, 'loss/train': 2.2260591983795166}
-03/03/2022 19:11:22 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/03/2022 19:11:27 - INFO - codeparrot_training - Step 4917: {'lr': 0.0004995209063383129, 'samples': 2518016, 'steps': 4917, 'loss/train': 2.569035530090332}
-03/03/2022 19:11:30 - INFO - codeparrot_training - Step 4918: {'lr': 0.0004995205779032274, 'samples': 2518528, 'steps': 4918, 'loss/train': 2.897451877593994}
-03/03/2022 19:11:30 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/03/2022 19:11:35 - INFO - codeparrot_training - Step 4919: {'lr': 0.0004995202493557118, 'samples': 2519040, 'steps': 4919, 'loss/train': 3.023164987564087}
-03/03/2022 19:11:38 - INFO - codeparrot_training - Step 4920: {'lr': 0.0004995199206957662, 'samples': 2519552, 'steps': 4920, 'loss/train': 1.6149410009384155}
-03/03/2022 19:11:39 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/03/2022 19:11:44 - INFO - codeparrot_training - Step 4921: {'lr': 0.0004995195919233906, 'samples': 2520064, 'steps': 4921, 'loss/train': 1.6233185529708862}
-03/03/2022 19:11:46 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/03/2022 19:11:49 - INFO - codeparrot_training - Step 4922: {'lr': 0.0004995192630385855, 'samples': 2520576, 'steps': 4922, 'loss/train': 2.3325858116149902}
-03/03/2022 19:11:52 - INFO - codeparrot_training - Step 4923: {'lr': 0.0004995189340413509, 'samples': 2521088, 'steps': 4923, 'loss/train': 3.023954153060913}
-03/03/2022 19:11:55 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/03/2022 19:11:57 - INFO - codeparrot_training - Step 4924: {'lr': 0.0004995186049316868, 'samples': 2521600, 'steps': 4924, 'loss/train': 2.960425615310669}
-03/03/2022 19:12:01 - INFO - codeparrot_training - Step 4925: {'lr': 0.0004995182757095935, 'samples': 2522112, 'steps': 4925, 'loss/train': 2.6881051063537598}
-03/03/2022 19:12:03 - INFO - codeparrot_training - Skipping example with length 553 (seq_length=1024)
-03/03/2022 19:12:06 - INFO - codeparrot_training - Step 4926: {'lr': 0.0004995179463750712, 'samples': 2522624, 'steps': 4926, 'loss/train': 2.5338778495788574}
-03/03/2022 19:12:09 - INFO - codeparrot_training - Step 4927: {'lr': 0.0004995176169281199, 'samples': 2523136, 'steps': 4927, 'loss/train': 2.42183518409729}
-03/03/2022 19:12:12 - INFO - codeparrot_training - Step 4928: {'lr': 0.0004995172873687398, 'samples': 2523648, 'steps': 4928, 'loss/train': 2.3432347774505615}
-03/03/2022 19:12:13 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/03/2022 19:12:18 - INFO - codeparrot_training - Step 4929: {'lr': 0.0004995169576969311, 'samples': 2524160, 'steps': 4929, 'loss/train': 0.531111478805542}
-03/03/2022 19:12:21 - INFO - codeparrot_training - Step 4930: {'lr': 0.0004995166279126938, 'samples': 2524672, 'steps': 4930, 'loss/train': 2.643454074859619}
-03/03/2022 19:12:21 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/03/2022 19:12:26 - INFO - codeparrot_training - Step 4931: {'lr': 0.0004995162980160283, 'samples': 2525184, 'steps': 4931, 'loss/train': 2.7847843170166016}
-03/03/2022 19:12:30 - INFO - codeparrot_training - Step 4932: {'lr': 0.0004995159680069346, 'samples': 2525696, 'steps': 4932, 'loss/train': 1.917352318763733}
-03/03/2022 19:12:30 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/03/2022 19:12:35 - INFO - codeparrot_training - Step 4933: {'lr': 0.0004995156378854127, 'samples': 2526208, 'steps': 4933, 'loss/train': 2.3337295055389404}
-03/03/2022 19:12:38 - INFO - codeparrot_training - Step 4934: {'lr': 0.000499515307651463, 'samples': 2526720, 'steps': 4934, 'loss/train': 2.6071813106536865}
-03/03/2022 19:12:40 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/03/2022 19:12:43 - INFO - codeparrot_training - Step 4935: {'lr': 0.0004995149773050857, 'samples': 2527232, 'steps': 4935, 'loss/train': 2.3921566009521484}
-03/03/2022 19:12:47 - INFO - codeparrot_training - Step 4936: {'lr': 0.0004995146468462806, 'samples': 2527744, 'steps': 4936, 'loss/train': 2.373450756072998}
-03/03/2022 19:12:48 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/03/2022 19:12:52 - INFO - codeparrot_training - Step 4937: {'lr': 0.0004995143162750481, 'samples': 2528256, 'steps': 4937, 'loss/train': 2.156949520111084}
-03/03/2022 19:12:55 - INFO - codeparrot_training - Step 4938: {'lr': 0.0004995139855913883, 'samples': 2528768, 'steps': 4938, 'loss/train': 2.20689058303833}
-03/03/2022 19:12:56 - INFO - codeparrot_training - Skipping example with length 233 (seq_length=1024)
-03/03/2022 19:13:00 - INFO - codeparrot_training - Step 4939: {'lr': 0.0004995136547953014, 'samples': 2529280, 'steps': 4939, 'loss/train': 2.0212583541870117}
-03/03/2022 19:13:04 - INFO - codeparrot_training - Step 4940: {'lr': 0.0004995133238867874, 'samples': 2529792, 'steps': 4940, 'loss/train': 2.652263879776001}
-03/03/2022 19:13:05 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/03/2022 19:13:09 - INFO - codeparrot_training - Step 4941: {'lr': 0.0004995129928658466, 'samples': 2530304, 'steps': 4941, 'loss/train': 2.6729049682617188}
-03/03/2022 19:13:12 - INFO - codeparrot_training - Step 4942: {'lr': 0.0004995126617324791, 'samples': 2530816, 'steps': 4942, 'loss/train': 2.372443675994873}
-03/03/2022 19:13:14 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/03/2022 19:13:18 - INFO - codeparrot_training - Step 4943: {'lr': 0.000499512330486685, 'samples': 2531328, 'steps': 4943, 'loss/train': 1.6827476024627686}
-03/03/2022 19:13:21 - INFO - codeparrot_training - Step 4944: {'lr': 0.0004995119991284645, 'samples': 2531840, 'steps': 4944, 'loss/train': 1.4622911214828491}
-03/03/2022 19:13:22 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/03/2022 19:13:26 - INFO - codeparrot_training - Step 4945: {'lr': 0.0004995116676578178, 'samples': 2532352, 'steps': 4945, 'loss/train': 1.1457879543304443}
-03/03/2022 19:13:29 - INFO - codeparrot_training - Step 4946: {'lr': 0.000499511336074745, 'samples': 2532864, 'steps': 4946, 'loss/train': 2.403461217880249}
-03/03/2022 19:13:30 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/03/2022 19:13:34 - INFO - codeparrot_training - Step 4947: {'lr': 0.0004995110043792462, 'samples': 2533376, 'steps': 4947, 'loss/train': 1.7617229223251343}
-03/03/2022 19:13:38 - INFO - codeparrot_training - Step 4948: {'lr': 0.0004995106725713217, 'samples': 2533888, 'steps': 4948, 'loss/train': 2.4262309074401855}
-03/03/2022 19:13:39 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/03/2022 19:13:43 - INFO - codeparrot_training - Step 4949: {'lr': 0.0004995103406509713, 'samples': 2534400, 'steps': 4949, 'loss/train': 2.4595015048980713}
-03/03/2022 19:13:46 - INFO - codeparrot_training - Step 4950: {'lr': 0.0004995100086181957, 'samples': 2534912, 'steps': 4950, 'loss/train': 2.8011679649353027}
-03/03/2022 19:13:47 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/03/2022 19:13:51 - INFO - codeparrot_training - Step 4951: {'lr': 0.0004995096764729945, 'samples': 2535424, 'steps': 4951, 'loss/train': 1.997688889503479}
-03/03/2022 19:13:55 - INFO - codeparrot_training - Step 4952: {'lr': 0.0004995093442153681, 'samples': 2535936, 'steps': 4952, 'loss/train': 2.8641645908355713}
-03/03/2022 19:13:56 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/03/2022 19:14:00 - INFO - codeparrot_training - Step 4953: {'lr': 0.0004995090118453167, 'samples': 2536448, 'steps': 4953, 'loss/train': 1.8954434394836426}
-03/03/2022 19:14:03 - INFO - codeparrot_training - Step 4954: {'lr': 0.0004995086793628405, 'samples': 2536960, 'steps': 4954, 'loss/train': 2.0424671173095703}
-03/03/2022 19:14:04 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/03/2022 19:14:08 - INFO - codeparrot_training - Step 4955: {'lr': 0.0004995083467679394, 'samples': 2537472, 'steps': 4955, 'loss/train': 2.7899105548858643}
-03/03/2022 19:14:11 - INFO - codeparrot_training - Step 4956: {'lr': 0.0004995080140606137, 'samples': 2537984, 'steps': 4956, 'loss/train': 2.1049716472625732}
-03/03/2022 19:14:13 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/03/2022 19:14:17 - INFO - codeparrot_training - Step 4957: {'lr': 0.0004995076812408636, 'samples': 2538496, 'steps': 4957, 'loss/train': 2.0607383251190186}
-03/03/2022 19:14:20 - INFO - codeparrot_training - Step 4958: {'lr': 0.0004995073483086891, 'samples': 2539008, 'steps': 4958, 'loss/train': 1.9795573949813843}
-03/03/2022 19:14:21 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/03/2022 19:14:25 - INFO - codeparrot_training - Step 4959: {'lr': 0.0004995070152640905, 'samples': 2539520, 'steps': 4959, 'loss/train': 2.205944061279297}
-03/03/2022 19:14:28 - INFO - codeparrot_training - Step 4960: {'lr': 0.0004995066821070679, 'samples': 2540032, 'steps': 4960, 'loss/train': 1.8774482011795044}
-03/03/2022 19:14:31 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/03/2022 19:14:34 - INFO - codeparrot_training - Step 4961: {'lr': 0.0004995063488376214, 'samples': 2540544, 'steps': 4961, 'loss/train': 2.5545992851257324}
-03/03/2022 19:14:37 - INFO - codeparrot_training - Step 4962: {'lr': 0.0004995060154557513, 'samples': 2541056, 'steps': 4962, 'loss/train': 2.2972452640533447}
-03/03/2022 19:14:39 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/03/2022 19:14:42 - INFO - codeparrot_training - Step 4963: {'lr': 0.0004995056819614575, 'samples': 2541568, 'steps': 4963, 'loss/train': 2.35840106010437}
-03/03/2022 19:14:45 - INFO - codeparrot_training - Step 4964: {'lr': 0.0004995053483547404, 'samples': 2542080, 'steps': 4964, 'loss/train': 2.625316858291626}
-03/03/2022 19:14:47 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/03/2022 19:14:50 - INFO - codeparrot_training - Step 4965: {'lr': 0.0004995050146355999, 'samples': 2542592, 'steps': 4965, 'loss/train': 3.5701122283935547}
-03/03/2022 19:14:53 - INFO - codeparrot_training - Step 4966: {'lr': 0.0004995046808040363, 'samples': 2543104, 'steps': 4966, 'loss/train': 2.6742842197418213}
-03/03/2022 19:14:55 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/03/2022 19:14:59 - INFO - codeparrot_training - Step 4967: {'lr': 0.0004995043468600499, 'samples': 2543616, 'steps': 4967, 'loss/train': 2.32631516456604}
-03/03/2022 19:15:02 - INFO - codeparrot_training - Step 4968: {'lr': 0.0004995040128036405, 'samples': 2544128, 'steps': 4968, 'loss/train': 2.5201194286346436}
-03/03/2022 19:15:03 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/03/2022 19:15:07 - INFO - codeparrot_training - Step 4969: {'lr': 0.0004995036786348086, 'samples': 2544640, 'steps': 4969, 'loss/train': 1.6076056957244873}
-03/03/2022 19:15:10 - INFO - codeparrot_training - Step 4970: {'lr': 0.0004995033443535541, 'samples': 2545152, 'steps': 4970, 'loss/train': 1.6770422458648682}
-03/03/2022 19:15:11 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/03/2022 19:15:15 - INFO - codeparrot_training - Step 4971: {'lr': 0.0004995030099598773, 'samples': 2545664, 'steps': 4971, 'loss/train': 1.7019637823104858}
-03/03/2022 19:15:18 - INFO - codeparrot_training - Step 4972: {'lr': 0.0004995026754537783, 'samples': 2546176, 'steps': 4972, 'loss/train': 0.24787460267543793}
-03/03/2022 19:15:20 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/03/2022 19:15:24 - INFO - codeparrot_training - Step 4973: {'lr': 0.0004995023408352572, 'samples': 2546688, 'steps': 4973, 'loss/train': 2.1225314140319824}
-03/03/2022 19:15:27 - INFO - codeparrot_training - Step 4974: {'lr': 0.0004995020061043142, 'samples': 2547200, 'steps': 4974, 'loss/train': 2.090137481689453}
-03/03/2022 19:15:28 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 19:15:32 - INFO - codeparrot_training - Step 4975: {'lr': 0.0004995016712609495, 'samples': 2547712, 'steps': 4975, 'loss/train': 3.2171671390533447}
-03/03/2022 19:15:35 - INFO - codeparrot_training - Step 4976: {'lr': 0.0004995013363051631, 'samples': 2548224, 'steps': 4976, 'loss/train': 1.3078683614730835}
-03/03/2022 19:15:36 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/03/2022 19:15:41 - INFO - codeparrot_training - Step 4977: {'lr': 0.0004995010012369554, 'samples': 2548736, 'steps': 4977, 'loss/train': 2.4288623332977295}
-03/03/2022 19:15:44 - INFO - codeparrot_training - Step 4978: {'lr': 0.0004995006660563262, 'samples': 2549248, 'steps': 4978, 'loss/train': 0.9987608194351196}
-03/03/2022 19:15:45 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/03/2022 19:15:49 - INFO - codeparrot_training - Step 4979: {'lr': 0.000499500330763276, 'samples': 2549760, 'steps': 4979, 'loss/train': 2.5851078033447266}
-03/03/2022 19:15:52 - INFO - codeparrot_training - Step 4980: {'lr': 0.0004994999953578048, 'samples': 2550272, 'steps': 4980, 'loss/train': 3.1460390090942383}
-03/03/2022 19:15:53 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/03/2022 19:15:57 - INFO - codeparrot_training - Step 4981: {'lr': 0.0004994996598399127, 'samples': 2550784, 'steps': 4981, 'loss/train': 2.649510622024536}
-03/03/2022 19:16:01 - INFO - codeparrot_training - Step 4982: {'lr': 0.0004994993242095999, 'samples': 2551296, 'steps': 4982, 'loss/train': 2.756120443344116}
-03/03/2022 19:16:02 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/03/2022 19:16:06 - INFO - codeparrot_training - Step 4983: {'lr': 0.0004994989884668665, 'samples': 2551808, 'steps': 4983, 'loss/train': 2.4659817218780518}
-03/03/2022 19:16:09 - INFO - codeparrot_training - Step 4984: {'lr': 0.0004994986526117127, 'samples': 2552320, 'steps': 4984, 'loss/train': 2.997540235519409}
-03/03/2022 19:16:10 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/03/2022 19:16:14 - INFO - codeparrot_training - Step 4985: {'lr': 0.0004994983166441388, 'samples': 2552832, 'steps': 4985, 'loss/train': 3.7428548336029053}
-03/03/2022 19:16:17 - INFO - codeparrot_training - Step 4986: {'lr': 0.0004994979805641448, 'samples': 2553344, 'steps': 4986, 'loss/train': 2.352506160736084}
-03/03/2022 19:16:19 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/03/2022 19:16:23 - INFO - codeparrot_training - Step 4987: {'lr': 0.0004994976443717308, 'samples': 2553856, 'steps': 4987, 'loss/train': 2.735555410385132}
-03/03/2022 19:16:26 - INFO - codeparrot_training - Step 4988: {'lr': 0.000499497308066897, 'samples': 2554368, 'steps': 4988, 'loss/train': 2.138292074203491}
-03/03/2022 19:16:27 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/03/2022 19:16:31 - INFO - codeparrot_training - Step 4989: {'lr': 0.0004994969716496435, 'samples': 2554880, 'steps': 4989, 'loss/train': 2.1425745487213135}
-03/03/2022 19:16:34 - INFO - codeparrot_training - Step 4990: {'lr': 0.0004994966351199706, 'samples': 2555392, 'steps': 4990, 'loss/train': 2.332216739654541}
-03/03/2022 19:16:35 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/03/2022 19:16:39 - INFO - codeparrot_training - Step 4991: {'lr': 0.0004994962984778784, 'samples': 2555904, 'steps': 4991, 'loss/train': 2.833285331726074}
-03/03/2022 19:16:43 - INFO - codeparrot_training - Step 4992: {'lr': 0.0004994959617233669, 'samples': 2556416, 'steps': 4992, 'loss/train': 1.6718634366989136}
-03/03/2022 19:16:43 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/03/2022 19:16:48 - INFO - codeparrot_training - Step 4993: {'lr': 0.0004994956248564364, 'samples': 2556928, 'steps': 4993, 'loss/train': 2.1394989490509033}
-03/03/2022 19:16:51 - INFO - codeparrot_training - Step 4994: {'lr': 0.000499495287877087, 'samples': 2557440, 'steps': 4994, 'loss/train': 2.591257333755493}
-03/03/2022 19:16:52 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/03/2022 19:16:56 - INFO - codeparrot_training - Step 4995: {'lr': 0.000499494950785319, 'samples': 2557952, 'steps': 4995, 'loss/train': 2.4716546535491943}
-03/03/2022 19:17:00 - INFO - codeparrot_training - Step 4996: {'lr': 0.0004994946135811324, 'samples': 2558464, 'steps': 4996, 'loss/train': 1.958532452583313}
-03/03/2022 19:17:01 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/03/2022 19:17:05 - INFO - codeparrot_training - Step 4997: {'lr': 0.0004994942762645274, 'samples': 2558976, 'steps': 4997, 'loss/train': 1.6212142705917358}
-03/03/2022 19:17:08 - INFO - codeparrot_training - Step 4998: {'lr': 0.000499493938835504, 'samples': 2559488, 'steps': 4998, 'loss/train': 2.0565834045410156}
-03/03/2022 19:17:09 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/03/2022 19:17:13 - INFO - codeparrot_training - Step 4999: {'lr': 0.0004994936012940626, 'samples': 2560000, 'steps': 4999, 'loss/train': 2.9388248920440674}
-03/03/2022 19:17:13 - INFO - codeparrot_training - Evaluating and saving model checkpoint
-03/03/2022 19:19:05 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/cm_code_clippy
- * [new branch]      glowing-puddle-3 -> glowing-puddle-3
-
-03/03/2022 19:20:22 - INFO - codeparrot_training - Step 5000: {'lr': 0.0004994932636402031, 'samples': 2560512, 'steps': 5000, 'loss/train': 3.0460309982299805}
-03/03/2022 19:20:23 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/03/2022 19:20:27 - INFO - codeparrot_training - Step 5001: {'lr': 0.000499492925873926, 'samples': 2561024, 'steps': 5001, 'loss/train': 2.23679780960083}
-03/03/2022 19:20:30 - INFO - codeparrot_training - Step 5002: {'lr': 0.000499492587995231, 'samples': 2561536, 'steps': 5002, 'loss/train': 2.865057945251465}
-03/03/2022 19:20:31 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/03/2022 19:20:35 - INFO - codeparrot_training - Step 5003: {'lr': 0.0004994922500041186, 'samples': 2562048, 'steps': 5003, 'loss/train': 1.63614022731781}
-03/03/2022 19:20:39 - INFO - codeparrot_training - Step 5004: {'lr': 0.0004994919119005888, 'samples': 2562560, 'steps': 5004, 'loss/train': 2.3504772186279297}
-03/03/2022 19:20:40 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/03/2022 19:20:44 - INFO - codeparrot_training - Step 5005: {'lr': 0.0004994915736846418, 'samples': 2563072, 'steps': 5005, 'loss/train': 2.7518062591552734}
-03/03/2022 19:20:47 - INFO - codeparrot_training - Step 5006: {'lr': 0.0004994912353562778, 'samples': 2563584, 'steps': 5006, 'loss/train': 2.842783212661743}
-03/03/2022 19:20:48 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/03/2022 19:20:52 - INFO - codeparrot_training - Step 5007: {'lr': 0.0004994908969154968, 'samples': 2564096, 'steps': 5007, 'loss/train': 2.3222877979278564}
-03/03/2022 19:20:56 - INFO - codeparrot_training - Step 5008: {'lr': 0.0004994905583622992, 'samples': 2564608, 'steps': 5008, 'loss/train': 2.4588587284088135}
-03/03/2022 19:20:56 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/03/2022 19:21:01 - INFO - codeparrot_training - Step 5009: {'lr': 0.000499490219696685, 'samples': 2565120, 'steps': 5009, 'loss/train': 2.0287551879882812}
-03/03/2022 19:21:04 - INFO - codeparrot_training - Step 5010: {'lr': 0.0004994898809186542, 'samples': 2565632, 'steps': 5010, 'loss/train': 2.5666322708129883}
-03/03/2022 19:21:05 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/03/2022 19:21:09 - INFO - codeparrot_training - Step 5011: {'lr': 0.0004994895420282072, 'samples': 2566144, 'steps': 5011, 'loss/train': 2.432098388671875}
-03/03/2022 19:21:12 - INFO - codeparrot_training - Step 5012: {'lr': 0.000499489203025344, 'samples': 2566656, 'steps': 5012, 'loss/train': 2.5167064666748047}
-03/03/2022 19:21:13 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/03/2022 19:21:18 - INFO - codeparrot_training - Step 5013: {'lr': 0.000499488863910065, 'samples': 2567168, 'steps': 5013, 'loss/train': 2.699950695037842}
-03/03/2022 19:21:21 - INFO - codeparrot_training - Step 5014: {'lr': 0.00049948852468237, 'samples': 2567680, 'steps': 5014, 'loss/train': 1.9226880073547363}
-03/03/2022 19:21:21 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/03/2022 19:21:27 - INFO - codeparrot_training - Step 5015: {'lr': 0.0004994881853422594, 'samples': 2568192, 'steps': 5015, 'loss/train': 2.6642770767211914}
-03/03/2022 19:21:30 - INFO - codeparrot_training - Step 5016: {'lr': 0.0004994878458897332, 'samples': 2568704, 'steps': 5016, 'loss/train': 2.5897555351257324}
-03/03/2022 19:21:33 - INFO - codeparrot_training - Step 5017: {'lr': 0.0004994875063247916, 'samples': 2569216, 'steps': 5017, 'loss/train': 6.936600685119629}
-03/03/2022 19:21:34 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/03/2022 19:21:39 - INFO - codeparrot_training - Step 5018: {'lr': 0.0004994871666474348, 'samples': 2569728, 'steps': 5018, 'loss/train': 2.017627000808716}
-03/03/2022 19:21:42 - INFO - codeparrot_training - Step 5019: {'lr': 0.000499486826857663, 'samples': 2570240, 'steps': 5019, 'loss/train': 2.4500107765197754}
-03/03/2022 19:21:42 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/03/2022 19:21:47 - INFO - codeparrot_training - Step 5020: {'lr': 0.0004994864869554763, 'samples': 2570752, 'steps': 5020, 'loss/train': 2.344092607498169}
-03/03/2022 19:21:50 - INFO - codeparrot_training - Step 5021: {'lr': 0.0004994861469408748, 'samples': 2571264, 'steps': 5021, 'loss/train': 2.9482834339141846}
-03/03/2022 19:21:51 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/03/2022 19:21:56 - INFO - codeparrot_training - Step 5022: {'lr': 0.0004994858068138587, 'samples': 2571776, 'steps': 5022, 'loss/train': 1.1966572999954224}
-03/03/2022 19:21:59 - INFO - codeparrot_training - Step 5023: {'lr': 0.0004994854665744282, 'samples': 2572288, 'steps': 5023, 'loss/train': 0.32042545080184937}
-03/03/2022 19:22:00 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/03/2022 19:22:05 - INFO - codeparrot_training - Step 5024: {'lr': 0.0004994851262225832, 'samples': 2572800, 'steps': 5024, 'loss/train': 2.004913568496704}
-03/03/2022 19:22:08 - INFO - codeparrot_training - Step 5025: {'lr': 0.0004994847857583242, 'samples': 2573312, 'steps': 5025, 'loss/train': 2.4744327068328857}
-03/03/2022 19:22:08 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/03/2022 19:22:13 - INFO - codeparrot_training - Step 5026: {'lr': 0.0004994844451816512, 'samples': 2573824, 'steps': 5026, 'loss/train': 2.660691499710083}
-03/03/2022 19:22:16 - INFO - codeparrot_training - Step 5027: {'lr': 0.0004994841044925644, 'samples': 2574336, 'steps': 5027, 'loss/train': 2.379913568496704}
-03/03/2022 19:22:18 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/03/2022 19:22:22 - INFO - codeparrot_training - Step 5028: {'lr': 0.0004994837636910638, 'samples': 2574848, 'steps': 5028, 'loss/train': 2.7498207092285156}
-03/03/2022 19:22:25 - INFO - codeparrot_training - Step 5029: {'lr': 0.0004994834227771498, 'samples': 2575360, 'steps': 5029, 'loss/train': 2.5037271976470947}
-03/03/2022 19:22:26 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/03/2022 19:22:30 - INFO - codeparrot_training - Step 5030: {'lr': 0.0004994830817508224, 'samples': 2575872, 'steps': 5030, 'loss/train': 1.647642731666565}
-03/03/2022 19:22:33 - INFO - codeparrot_training - Step 5031: {'lr': 0.0004994827406120816, 'samples': 2576384, 'steps': 5031, 'loss/train': 2.3455419540405273}
-03/03/2022 19:22:35 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/03/2022 19:22:39 - INFO - codeparrot_training - Step 5032: {'lr': 0.0004994823993609279, 'samples': 2576896, 'steps': 5032, 'loss/train': 2.8462307453155518}
-03/03/2022 19:22:42 - INFO - codeparrot_training - Step 5033: {'lr': 0.0004994820579973612, 'samples': 2577408, 'steps': 5033, 'loss/train': 3.4109208583831787}
-03/03/2022 19:22:43 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/03/2022 19:22:47 - INFO - codeparrot_training - Step 5034: {'lr': 0.0004994817165213817, 'samples': 2577920, 'steps': 5034, 'loss/train': 2.4346659183502197}
-03/03/2022 19:22:50 - INFO - codeparrot_training - Step 5035: {'lr': 0.0004994813749329897, 'samples': 2578432, 'steps': 5035, 'loss/train': 2.360734224319458}
-03/03/2022 19:22:52 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/03/2022 19:22:56 - INFO - codeparrot_training - Step 5036: {'lr': 0.0004994810332321852, 'samples': 2578944, 'steps': 5036, 'loss/train': 2.0953283309936523}
-03/03/2022 19:22:59 - INFO - codeparrot_training - Step 5037: {'lr': 0.0004994806914189684, 'samples': 2579456, 'steps': 5037, 'loss/train': 2.6066956520080566}
-03/03/2022 19:23:01 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/03/2022 19:23:04 - INFO - codeparrot_training - Step 5038: {'lr': 0.0004994803494933394, 'samples': 2579968, 'steps': 5038, 'loss/train': 1.9902102947235107}
-03/03/2022 19:23:08 - INFO - codeparrot_training - Step 5039: {'lr': 0.0004994800074552985, 'samples': 2580480, 'steps': 5039, 'loss/train': 1.8753236532211304}
-03/03/2022 19:23:09 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/03/2022 19:23:13 - INFO - codeparrot_training - Step 5040: {'lr': 0.0004994796653048457, 'samples': 2580992, 'steps': 5040, 'loss/train': 1.5438320636749268}
-03/03/2022 19:23:16 - INFO - codeparrot_training - Step 5041: {'lr': 0.0004994793230419812, 'samples': 2581504, 'steps': 5041, 'loss/train': 2.3258049488067627}
-03/03/2022 19:23:18 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/03/2022 19:23:21 - INFO - codeparrot_training - Step 5042: {'lr': 0.0004994789806667052, 'samples': 2582016, 'steps': 5042, 'loss/train': 2.5006954669952393}
-03/03/2022 19:23:24 - INFO - codeparrot_training - Step 5043: {'lr': 0.0004994786381790178, 'samples': 2582528, 'steps': 5043, 'loss/train': 2.862854242324829}
-03/03/2022 19:23:27 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/03/2022 19:23:30 - INFO - codeparrot_training - Step 5044: {'lr': 0.0004994782955789191, 'samples': 2583040, 'steps': 5044, 'loss/train': 2.7308852672576904}
-03/03/2022 19:23:33 - INFO - codeparrot_training - Step 5045: {'lr': 0.0004994779528664095, 'samples': 2583552, 'steps': 5045, 'loss/train': 2.0793960094451904}
-03/03/2022 19:23:35 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/03/2022 19:23:38 - INFO - codeparrot_training - Step 5046: {'lr': 0.0004994776100414888, 'samples': 2584064, 'steps': 5046, 'loss/train': 2.9539031982421875}
-03/03/2022 19:23:41 - INFO - codeparrot_training - Step 5047: {'lr': 0.0004994772671041575, 'samples': 2584576, 'steps': 5047, 'loss/train': 2.6762776374816895}
-03/03/2022 19:23:43 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/03/2022 19:23:47 - INFO - codeparrot_training - Step 5048: {'lr': 0.0004994769240544155, 'samples': 2585088, 'steps': 5048, 'loss/train': 2.4125888347625732}
-03/03/2022 19:23:50 - INFO - codeparrot_training - Step 5049: {'lr': 0.000499476580892263, 'samples': 2585600, 'steps': 5049, 'loss/train': 2.323589324951172}
-03/03/2022 19:23:52 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/03/2022 19:23:55 - INFO - codeparrot_training - Step 5050: {'lr': 0.0004994762376177004, 'samples': 2586112, 'steps': 5050, 'loss/train': 0.6720583438873291}
-03/03/2022 19:23:58 - INFO - codeparrot_training - Step 5051: {'lr': 0.0004994758942307274, 'samples': 2586624, 'steps': 5051, 'loss/train': 1.8223439455032349}
-03/03/2022 19:24:00 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/03/2022 19:24:04 - INFO - codeparrot_training - Step 5052: {'lr': 0.0004994755507313446, 'samples': 2587136, 'steps': 5052, 'loss/train': 2.2067017555236816}
-03/03/2022 19:24:07 - INFO - codeparrot_training - Step 5053: {'lr': 0.000499475207119552, 'samples': 2587648, 'steps': 5053, 'loss/train': 2.7322683334350586}
-03/03/2022 19:24:08 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/03/2022 19:24:12 - INFO - codeparrot_training - Step 5054: {'lr': 0.0004994748633953495, 'samples': 2588160, 'steps': 5054, 'loss/train': 2.2969210147857666}
-03/03/2022 19:24:15 - INFO - codeparrot_training - Step 5055: {'lr': 0.0004994745195587376, 'samples': 2588672, 'steps': 5055, 'loss/train': 2.4367618560791016}
-03/03/2022 19:24:17 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/03/2022 19:24:21 - INFO - codeparrot_training - Step 5056: {'lr': 0.0004994741756097164, 'samples': 2589184, 'steps': 5056, 'loss/train': 1.9506793022155762}
-03/03/2022 19:24:24 - INFO - codeparrot_training - Step 5057: {'lr': 0.0004994738315482859, 'samples': 2589696, 'steps': 5057, 'loss/train': 3.0796713829040527}
-03/03/2022 19:24:26 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/03/2022 19:24:29 - INFO - codeparrot_training - Step 5058: {'lr': 0.0004994734873744464, 'samples': 2590208, 'steps': 5058, 'loss/train': 2.559769868850708}
-03/03/2022 19:24:32 - INFO - codeparrot_training - Step 5059: {'lr': 0.0004994731430881979, 'samples': 2590720, 'steps': 5059, 'loss/train': 2.450498580932617}
-03/03/2022 19:24:34 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/03/2022 19:24:38 - INFO - codeparrot_training - Step 5060: {'lr': 0.0004994727986895408, 'samples': 2591232, 'steps': 5060, 'loss/train': 2.743480682373047}
-03/03/2022 19:24:41 - INFO - codeparrot_training - Step 5061: {'lr': 0.0004994724541784749, 'samples': 2591744, 'steps': 5061, 'loss/train': 2.6996638774871826}
-03/03/2022 19:24:44 - INFO - codeparrot_training - Step 5062: {'lr': 0.0004994721095550008, 'samples': 2592256, 'steps': 5062, 'loss/train': 2.7072131633758545}
-03/03/2022 19:24:44 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/03/2022 19:24:49 - INFO - codeparrot_training - Step 5063: {'lr': 0.0004994717648191182, 'samples': 2592768, 'steps': 5063, 'loss/train': 2.512293577194214}
-03/03/2022 19:24:52 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/03/2022 19:24:55 - INFO - codeparrot_training - Step 5064: {'lr': 0.0004994714199708276, 'samples': 2593280, 'steps': 5064, 'loss/train': 3.636714220046997}
-03/03/2022 19:24:58 - INFO - codeparrot_training - Step 5065: {'lr': 0.000499471075010129, 'samples': 2593792, 'steps': 5065, 'loss/train': 2.5831925868988037}
-03/03/2022 19:25:00 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/03/2022 19:25:03 - INFO - codeparrot_training - Step 5066: {'lr': 0.0004994707299370226, 'samples': 2594304, 'steps': 5066, 'loss/train': 1.9154324531555176}
-03/03/2022 19:25:06 - INFO - codeparrot_training - Step 5067: {'lr': 0.0004994703847515084, 'samples': 2594816, 'steps': 5067, 'loss/train': 3.05000376701355}
-03/03/2022 19:25:08 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/03/2022 19:25:11 - INFO - codeparrot_training - Step 5068: {'lr': 0.0004994700394535869, 'samples': 2595328, 'steps': 5068, 'loss/train': 1.94434654712677}
-03/03/2022 19:25:15 - INFO - codeparrot_training - Step 5069: {'lr': 0.000499469694043258, 'samples': 2595840, 'steps': 5069, 'loss/train': 1.7838891744613647}
-03/03/2022 19:25:17 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/03/2022 19:25:20 - INFO - codeparrot_training - Step 5070: {'lr': 0.0004994693485205218, 'samples': 2596352, 'steps': 5070, 'loss/train': 7.3783464431762695}
-03/03/2022 19:25:23 - INFO - codeparrot_training - Step 5071: {'lr': 0.0004994690028853787, 'samples': 2596864, 'steps': 5071, 'loss/train': 3.204770803451538}
-03/03/2022 19:25:26 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/03/2022 19:25:29 - INFO - codeparrot_training - Step 5072: {'lr': 0.0004994686571378286, 'samples': 2597376, 'steps': 5072, 'loss/train': 3.2831037044525146}
-03/03/2022 19:25:32 - INFO - codeparrot_training - Step 5073: {'lr': 0.0004994683112778718, 'samples': 2597888, 'steps': 5073, 'loss/train': 3.029533863067627}
-03/03/2022 19:25:35 - INFO - codeparrot_training - Step 5074: {'lr': 0.0004994679653055085, 'samples': 2598400, 'steps': 5074, 'loss/train': 2.79117751121521}
-03/03/2022 19:25:37 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/03/2022 19:25:41 - INFO - codeparrot_training - Step 5075: {'lr': 0.0004994676192207387, 'samples': 2598912, 'steps': 5075, 'loss/train': 2.192655563354492}
-03/03/2022 19:25:44 - INFO - codeparrot_training - Step 5076: {'lr': 0.0004994672730235626, 'samples': 2599424, 'steps': 5076, 'loss/train': 0.3328442871570587}
-03/03/2022 19:25:46 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/03/2022 19:25:49 - INFO - codeparrot_training - Step 5077: {'lr': 0.0004994669267139806, 'samples': 2599936, 'steps': 5077, 'loss/train': 2.1333651542663574}
-03/03/2022 19:25:52 - INFO - codeparrot_training - Step 5078: {'lr': 0.0004994665802919925, 'samples': 2600448, 'steps': 5078, 'loss/train': 1.5804290771484375}
-03/03/2022 19:25:54 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/03/2022 19:25:58 - INFO - codeparrot_training - Step 5079: {'lr': 0.0004994662337575986, 'samples': 2600960, 'steps': 5079, 'loss/train': 2.2463886737823486}
-03/03/2022 19:26:01 - INFO - codeparrot_training - Step 5080: {'lr': 0.000499465887110799, 'samples': 2601472, 'steps': 5080, 'loss/train': 2.27553653717041}
-03/03/2022 19:26:02 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/03/2022 19:26:06 - INFO - codeparrot_training - Step 5081: {'lr': 0.0004994655403515941, 'samples': 2601984, 'steps': 5081, 'loss/train': 2.0227997303009033}
-03/03/2022 19:26:09 - INFO - codeparrot_training - Step 5082: {'lr': 0.0004994651934799837, 'samples': 2602496, 'steps': 5082, 'loss/train': 2.5096731185913086}
-03/03/2022 19:26:11 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/03/2022 19:26:15 - INFO - codeparrot_training - Step 5083: {'lr': 0.0004994648464959683, 'samples': 2603008, 'steps': 5083, 'loss/train': 3.1929025650024414}
-03/03/2022 19:26:18 - INFO - codeparrot_training - Step 5084: {'lr': 0.0004994644993995478, 'samples': 2603520, 'steps': 5084, 'loss/train': 2.1664586067199707}
-03/03/2022 19:26:20 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 19:26:23 - INFO - codeparrot_training - Step 5085: {'lr': 0.0004994641521907224, 'samples': 2604032, 'steps': 5085, 'loss/train': 2.5118143558502197}
-03/03/2022 19:26:26 - INFO - codeparrot_training - Step 5086: {'lr': 0.0004994638048694924, 'samples': 2604544, 'steps': 5086, 'loss/train': 3.0080678462982178}
-03/03/2022 19:26:28 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/03/2022 19:26:31 - INFO - codeparrot_training - Step 5087: {'lr': 0.0004994634574358579, 'samples': 2605056, 'steps': 5087, 'loss/train': 2.118664026260376}
-03/03/2022 19:26:35 - INFO - codeparrot_training - Step 5088: {'lr': 0.0004994631098898188, 'samples': 2605568, 'steps': 5088, 'loss/train': 1.4126542806625366}
-03/03/2022 19:26:36 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/03/2022 19:26:40 - INFO - codeparrot_training - Step 5089: {'lr': 0.0004994627622313757, 'samples': 2606080, 'steps': 5089, 'loss/train': 2.1706860065460205}
-03/03/2022 19:26:43 - INFO - codeparrot_training - Step 5090: {'lr': 0.0004994624144605284, 'samples': 2606592, 'steps': 5090, 'loss/train': 2.864316940307617}
-03/03/2022 19:26:44 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/03/2022 19:26:48 - INFO - codeparrot_training - Step 5091: {'lr': 0.0004994620665772772, 'samples': 2607104, 'steps': 5091, 'loss/train': 2.9692564010620117}
-03/03/2022 19:26:51 - INFO - codeparrot_training - Step 5092: {'lr': 0.0004994617185816222, 'samples': 2607616, 'steps': 5092, 'loss/train': 2.6895411014556885}
-03/03/2022 19:26:57 - INFO - codeparrot_training - Step 5093: {'lr': 0.0004994613704735638, 'samples': 2608128, 'steps': 5093, 'loss/train': 2.8580820560455322}
-03/03/2022 19:27:00 - INFO - codeparrot_training - Step 5094: {'lr': 0.0004994610222531018, 'samples': 2608640, 'steps': 5094, 'loss/train': 2.258488416671753}
-03/03/2022 19:27:01 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/03/2022 19:27:05 - INFO - codeparrot_training - Step 5095: {'lr': 0.0004994606739202365, 'samples': 2609152, 'steps': 5095, 'loss/train': 1.5070934295654297}
-03/03/2022 19:27:08 - INFO - codeparrot_training - Step 5096: {'lr': 0.0004994603254749681, 'samples': 2609664, 'steps': 5096, 'loss/train': 2.37096905708313}
-03/03/2022 19:27:09 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/03/2022 19:27:13 - INFO - codeparrot_training - Step 5097: {'lr': 0.0004994599769172967, 'samples': 2610176, 'steps': 5097, 'loss/train': 0.5367571115493774}
-03/03/2022 19:27:17 - INFO - codeparrot_training - Step 5098: {'lr': 0.0004994596282472225, 'samples': 2610688, 'steps': 5098, 'loss/train': 0.589159369468689}
-03/03/2022 19:27:18 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/03/2022 19:27:22 - INFO - codeparrot_training - Step 5099: {'lr': 0.0004994592794647457, 'samples': 2611200, 'steps': 5099, 'loss/train': 2.4816935062408447}
-03/03/2022 19:27:25 - INFO - codeparrot_training - Step 5100: {'lr': 0.0004994589305698663, 'samples': 2611712, 'steps': 5100, 'loss/train': 2.68294620513916}
-03/03/2022 19:27:26 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/03/2022 19:27:30 - INFO - codeparrot_training - Step 5101: {'lr': 0.0004994585815625847, 'samples': 2612224, 'steps': 5101, 'loss/train': 0.31972774863243103}
-03/03/2022 19:27:33 - INFO - codeparrot_training - Step 5102: {'lr': 0.0004994582324429008, 'samples': 2612736, 'steps': 5102, 'loss/train': 2.3067450523376465}
-03/03/2022 19:27:34 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/03/2022 19:27:39 - INFO - codeparrot_training - Step 5103: {'lr': 0.0004994578832108148, 'samples': 2613248, 'steps': 5103, 'loss/train': 1.6985063552856445}
-03/03/2022 19:27:42 - INFO - codeparrot_training - Step 5104: {'lr': 0.000499457533866327, 'samples': 2613760, 'steps': 5104, 'loss/train': 2.3719987869262695}
-03/03/2022 19:27:43 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/03/2022 19:27:47 - INFO - codeparrot_training - Step 5105: {'lr': 0.0004994571844094375, 'samples': 2614272, 'steps': 5105, 'loss/train': 2.782482147216797}
-03/03/2022 19:27:50 - INFO - codeparrot_training - Step 5106: {'lr': 0.0004994568348401466, 'samples': 2614784, 'steps': 5106, 'loss/train': 0.5865107178688049}
-03/03/2022 19:27:51 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/03/2022 19:27:56 - INFO - codeparrot_training - Step 5107: {'lr': 0.0004994564851584541, 'samples': 2615296, 'steps': 5107, 'loss/train': 2.5509848594665527}
-03/03/2022 19:27:59 - INFO - codeparrot_training - Step 5108: {'lr': 0.0004994561353643604, 'samples': 2615808, 'steps': 5108, 'loss/train': 2.023597478866577}
-03/03/2022 19:28:00 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/03/2022 19:28:04 - INFO - codeparrot_training - Step 5109: {'lr': 0.0004994557854578656, 'samples': 2616320, 'steps': 5109, 'loss/train': 1.766840934753418}
-03/03/2022 19:28:07 - INFO - codeparrot_training - Step 5110: {'lr': 0.0004994554354389699, 'samples': 2616832, 'steps': 5110, 'loss/train': 2.793339967727661}
-03/03/2022 19:28:08 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/03/2022 19:28:12 - INFO - codeparrot_training - Step 5111: {'lr': 0.0004994550853076734, 'samples': 2617344, 'steps': 5111, 'loss/train': 1.992292046546936}
-03/03/2022 19:28:16 - INFO - codeparrot_training - Step 5112: {'lr': 0.0004994547350639764, 'samples': 2617856, 'steps': 5112, 'loss/train': 0.8648834228515625}
-03/03/2022 19:28:17 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/03/2022 19:28:21 - INFO - codeparrot_training - Step 5113: {'lr': 0.0004994543847078787, 'samples': 2618368, 'steps': 5113, 'loss/train': 2.3021597862243652}
-03/03/2022 19:28:24 - INFO - codeparrot_training - Step 5114: {'lr': 0.000499454034239381, 'samples': 2618880, 'steps': 5114, 'loss/train': 1.9001699686050415}
-03/03/2022 19:28:29 - INFO - codeparrot_training - Step 5115: {'lr': 0.000499453683658483, 'samples': 2619392, 'steps': 5115, 'loss/train': 2.9070277214050293}
-03/03/2022 19:28:33 - INFO - codeparrot_training - Step 5116: {'lr': 0.0004994533329651849, 'samples': 2619904, 'steps': 5116, 'loss/train': 0.9729158282279968}
-03/03/2022 19:28:33 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/03/2022 19:28:38 - INFO - codeparrot_training - Step 5117: {'lr': 0.0004994529821594872, 'samples': 2620416, 'steps': 5117, 'loss/train': 2.207848072052002}
-03/03/2022 19:28:41 - INFO - codeparrot_training - Step 5118: {'lr': 0.0004994526312413897, 'samples': 2620928, 'steps': 5118, 'loss/train': 2.188880443572998}
-03/03/2022 19:28:42 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/03/2022 19:28:46 - INFO - codeparrot_training - Step 5119: {'lr': 0.0004994522802108927, 'samples': 2621440, 'steps': 5119, 'loss/train': 2.159708261489868}
-03/03/2022 19:28:49 - INFO - codeparrot_training - Step 5120: {'lr': 0.0004994519290679964, 'samples': 2621952, 'steps': 5120, 'loss/train': 1.650704264640808}
-03/03/2022 19:28:50 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/03/2022 19:28:55 - INFO - codeparrot_training - Step 5121: {'lr': 0.0004994515778127009, 'samples': 2622464, 'steps': 5121, 'loss/train': 2.014159679412842}
-03/03/2022 19:28:58 - INFO - codeparrot_training - Step 5122: {'lr': 0.0004994512264450064, 'samples': 2622976, 'steps': 5122, 'loss/train': 1.7527045011520386}
-03/03/2022 19:28:58 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/03/2022 19:29:03 - INFO - codeparrot_training - Step 5123: {'lr': 0.000499450874964913, 'samples': 2623488, 'steps': 5123, 'loss/train': 0.4601464867591858}
-03/03/2022 19:29:06 - INFO - codeparrot_training - Step 5124: {'lr': 0.000499450523372421, 'samples': 2624000, 'steps': 5124, 'loss/train': 2.504192352294922}
-03/03/2022 19:29:07 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/03/2022 19:29:12 - INFO - codeparrot_training - Step 5125: {'lr': 0.0004994501716675303, 'samples': 2624512, 'steps': 5125, 'loss/train': 2.7127413749694824}
-03/03/2022 19:29:15 - INFO - codeparrot_training - Step 5126: {'lr': 0.0004994498198502412, 'samples': 2625024, 'steps': 5126, 'loss/train': 1.3175290822982788}
-03/03/2022 19:29:16 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/03/2022 19:29:20 - INFO - codeparrot_training - Step 5127: {'lr': 0.0004994494679205539, 'samples': 2625536, 'steps': 5127, 'loss/train': 2.3006210327148438}
-03/03/2022 19:29:23 - INFO - codeparrot_training - Step 5128: {'lr': 0.0004994491158784684, 'samples': 2626048, 'steps': 5128, 'loss/train': 3.0349273681640625}
-03/03/2022 19:29:24 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/03/2022 19:29:29 - INFO - codeparrot_training - Step 5129: {'lr': 0.0004994487637239851, 'samples': 2626560, 'steps': 5129, 'loss/train': 3.989762306213379}
-03/03/2022 19:29:32 - INFO - codeparrot_training - Step 5130: {'lr': 0.0004994484114571041, 'samples': 2627072, 'steps': 5130, 'loss/train': 2.310811758041382}
-03/03/2022 19:29:32 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/03/2022 19:29:37 - INFO - codeparrot_training - Step 5131: {'lr': 0.0004994480590778254, 'samples': 2627584, 'steps': 5131, 'loss/train': 3.2333245277404785}
-03/03/2022 19:29:40 - INFO - codeparrot_training - Step 5132: {'lr': 0.0004994477065861493, 'samples': 2628096, 'steps': 5132, 'loss/train': 2.1058878898620605}
-03/03/2022 19:29:41 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/03/2022 19:29:46 - INFO - codeparrot_training - Step 5133: {'lr': 0.0004994473539820758, 'samples': 2628608, 'steps': 5133, 'loss/train': 2.252570867538452}
-03/03/2022 19:29:49 - INFO - codeparrot_training - Step 5134: {'lr': 0.0004994470012656052, 'samples': 2629120, 'steps': 5134, 'loss/train': 2.629795551300049}
-03/03/2022 19:29:50 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/03/2022 19:29:54 - INFO - codeparrot_training - Step 5135: {'lr': 0.0004994466484367378, 'samples': 2629632, 'steps': 5135, 'loss/train': 2.8312888145446777}
-03/03/2022 19:29:58 - INFO - codeparrot_training - Step 5136: {'lr': 0.0004994462954954734, 'samples': 2630144, 'steps': 5136, 'loss/train': 2.7224185466766357}
-03/03/2022 19:29:58 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/03/2022 19:30:03 - INFO - codeparrot_training - Step 5137: {'lr': 0.0004994459424418125, 'samples': 2630656, 'steps': 5137, 'loss/train': 1.2517436742782593}
-03/03/2022 19:30:06 - INFO - codeparrot_training - Step 5138: {'lr': 0.000499445589275755, 'samples': 2631168, 'steps': 5138, 'loss/train': 1.9751428365707397}
-03/03/2022 19:30:07 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/03/2022 19:30:11 - INFO - codeparrot_training - Step 5139: {'lr': 0.0004994452359973012, 'samples': 2631680, 'steps': 5139, 'loss/train': 3.008371114730835}
-03/03/2022 19:30:15 - INFO - codeparrot_training - Step 5140: {'lr': 0.0004994448826064512, 'samples': 2632192, 'steps': 5140, 'loss/train': 2.84537672996521}
-03/03/2022 19:30:15 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/03/2022 19:30:20 - INFO - codeparrot_training - Step 5141: {'lr': 0.0004994445291032053, 'samples': 2632704, 'steps': 5141, 'loss/train': 2.3178791999816895}
-03/03/2022 19:30:23 - INFO - codeparrot_training - Step 5142: {'lr': 0.0004994441754875634, 'samples': 2633216, 'steps': 5142, 'loss/train': 1.15286386013031}
-03/03/2022 19:30:23 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/03/2022 19:30:28 - INFO - codeparrot_training - Step 5143: {'lr': 0.0004994438217595259, 'samples': 2633728, 'steps': 5143, 'loss/train': 1.7607184648513794}
-03/03/2022 19:30:32 - INFO - codeparrot_training - Step 5144: {'lr': 0.0004994434679190928, 'samples': 2634240, 'steps': 5144, 'loss/train': 2.3556323051452637}
-03/03/2022 19:30:32 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/03/2022 19:30:37 - INFO - codeparrot_training - Step 5145: {'lr': 0.0004994431139662643, 'samples': 2634752, 'steps': 5145, 'loss/train': 2.623178482055664}
-03/03/2022 19:30:40 - INFO - codeparrot_training - Step 5146: {'lr': 0.0004994427599010406, 'samples': 2635264, 'steps': 5146, 'loss/train': 2.1137962341308594}
-03/03/2022 19:30:40 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/03/2022 19:30:45 - INFO - codeparrot_training - Step 5147: {'lr': 0.0004994424057234219, 'samples': 2635776, 'steps': 5147, 'loss/train': 2.243248224258423}
-03/03/2022 19:30:48 - INFO - codeparrot_training - Step 5148: {'lr': 0.0004994420514334082, 'samples': 2636288, 'steps': 5148, 'loss/train': 2.3315842151641846}
-03/03/2022 19:30:48 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/03/2022 19:30:54 - INFO - codeparrot_training - Step 5149: {'lr': 0.0004994416970309999, 'samples': 2636800, 'steps': 5149, 'loss/train': 2.2571158409118652}
-03/03/2022 19:30:57 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/03/2022 19:30:59 - INFO - codeparrot_training - Step 5150: {'lr': 0.0004994413425161969, 'samples': 2637312, 'steps': 5150, 'loss/train': 2.290959119796753}
-03/03/2022 19:31:02 - INFO - codeparrot_training - Step 5151: {'lr': 0.0004994409878889995, 'samples': 2637824, 'steps': 5151, 'loss/train': 2.105710506439209}
-03/03/2022 19:31:05 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/03/2022 19:31:08 - INFO - codeparrot_training - Step 5152: {'lr': 0.0004994406331494079, 'samples': 2638336, 'steps': 5152, 'loss/train': 2.4309487342834473}
-03/03/2022 19:31:11 - INFO - codeparrot_training - Step 5153: {'lr': 0.0004994402782974222, 'samples': 2638848, 'steps': 5153, 'loss/train': 2.447695255279541}
-03/03/2022 19:31:14 - INFO - codeparrot_training - Step 5154: {'lr': 0.0004994399233330426, 'samples': 2639360, 'steps': 5154, 'loss/train': 1.8564012050628662}
-03/03/2022 19:31:14 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/03/2022 19:31:19 - INFO - codeparrot_training - Step 5155: {'lr': 0.000499439568256269, 'samples': 2639872, 'steps': 5155, 'loss/train': 2.3590826988220215}
-03/03/2022 19:31:22 - INFO - codeparrot_training - Step 5156: {'lr': 0.000499439213067102, 'samples': 2640384, 'steps': 5156, 'loss/train': 2.786942958831787}
-03/03/2022 19:31:23 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/03/2022 19:31:28 - INFO - codeparrot_training - Step 5157: {'lr': 0.0004994388577655415, 'samples': 2640896, 'steps': 5157, 'loss/train': 2.790937662124634}
-03/03/2022 19:31:31 - INFO - codeparrot_training - Step 5158: {'lr': 0.0004994385023515876, 'samples': 2641408, 'steps': 5158, 'loss/train': 2.169804573059082}
-03/03/2022 19:31:31 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/03/2022 19:31:36 - INFO - codeparrot_training - Step 5159: {'lr': 0.0004994381468252406, 'samples': 2641920, 'steps': 5159, 'loss/train': 2.722163438796997}
-03/03/2022 19:31:39 - INFO - codeparrot_training - Step 5160: {'lr': 0.0004994377911865007, 'samples': 2642432, 'steps': 5160, 'loss/train': 2.745609998703003}
-03/03/2022 19:31:39 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/03/2022 19:31:45 - INFO - codeparrot_training - Step 5161: {'lr': 0.0004994374354353679, 'samples': 2642944, 'steps': 5161, 'loss/train': 2.759655714035034}
-03/03/2022 19:31:48 - INFO - codeparrot_training - Step 5162: {'lr': 0.0004994370795718425, 'samples': 2643456, 'steps': 5162, 'loss/train': 2.347574472427368}
-03/03/2022 19:31:48 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/03/2022 19:31:53 - INFO - codeparrot_training - Step 5163: {'lr': 0.0004994367235959245, 'samples': 2643968, 'steps': 5163, 'loss/train': 1.4747453927993774}
-03/03/2022 19:31:56 - INFO - codeparrot_training - Step 5164: {'lr': 0.0004994363675076143, 'samples': 2644480, 'steps': 5164, 'loss/train': 2.4393460750579834}
-03/03/2022 19:31:57 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/03/2022 19:32:02 - INFO - codeparrot_training - Step 5165: {'lr': 0.0004994360113069118, 'samples': 2644992, 'steps': 5165, 'loss/train': 2.225006341934204}
-03/03/2022 19:32:05 - INFO - codeparrot_training - Step 5166: {'lr': 0.0004994356549938173, 'samples': 2645504, 'steps': 5166, 'loss/train': 2.66904878616333}
-03/03/2022 19:32:06 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/03/2022 19:32:10 - INFO - codeparrot_training - Step 5167: {'lr': 0.000499435298568331, 'samples': 2646016, 'steps': 5167, 'loss/train': 2.762289524078369}
-03/03/2022 19:32:13 - INFO - codeparrot_training - Step 5168: {'lr': 0.000499434942030453, 'samples': 2646528, 'steps': 5168, 'loss/train': 2.150148391723633}
-03/03/2022 19:32:14 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/03/2022 19:32:19 - INFO - codeparrot_training - Step 5169: {'lr': 0.0004994345853801834, 'samples': 2647040, 'steps': 5169, 'loss/train': 2.7302920818328857}
-03/03/2022 19:32:22 - INFO - codeparrot_training - Step 5170: {'lr': 0.0004994342286175225, 'samples': 2647552, 'steps': 5170, 'loss/train': 2.2401463985443115}
-03/03/2022 19:32:23 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/03/2022 19:32:27 - INFO - codeparrot_training - Step 5171: {'lr': 0.0004994338717424704, 'samples': 2648064, 'steps': 5171, 'loss/train': 1.4216365814208984}
-03/03/2022 19:32:30 - INFO - codeparrot_training - Step 5172: {'lr': 0.0004994335147550272, 'samples': 2648576, 'steps': 5172, 'loss/train': 3.195286750793457}
-03/03/2022 19:32:31 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/03/2022 19:32:36 - INFO - codeparrot_training - Step 5173: {'lr': 0.0004994331576551931, 'samples': 2649088, 'steps': 5173, 'loss/train': 2.9391777515411377}
-03/03/2022 19:32:39 - INFO - codeparrot_training - Step 5174: {'lr': 0.0004994328004429683, 'samples': 2649600, 'steps': 5174, 'loss/train': 2.2299697399139404}
-03/03/2022 19:32:39 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/03/2022 19:32:44 - INFO - codeparrot_training - Step 5175: {'lr': 0.000499432443118353, 'samples': 2650112, 'steps': 5175, 'loss/train': 1.9682414531707764}
-03/03/2022 19:32:47 - INFO - codeparrot_training - Step 5176: {'lr': 0.0004994320856813471, 'samples': 2650624, 'steps': 5176, 'loss/train': 2.4742555618286133}
-03/03/2022 19:32:48 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/03/2022 19:32:52 - INFO - codeparrot_training - Step 5177: {'lr': 0.000499431728131951, 'samples': 2651136, 'steps': 5177, 'loss/train': 1.9927133321762085}
-03/03/2022 19:32:56 - INFO - codeparrot_training - Step 5178: {'lr': 0.0004994313704701648, 'samples': 2651648, 'steps': 5178, 'loss/train': 1.981155514717102}
-03/03/2022 19:32:56 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/03/2022 19:33:01 - INFO - codeparrot_training - Step 5179: {'lr': 0.0004994310126959887, 'samples': 2652160, 'steps': 5179, 'loss/train': 2.291635036468506}
-03/03/2022 19:33:05 - INFO - codeparrot_training - Step 5180: {'lr': 0.000499430654809423, 'samples': 2652672, 'steps': 5180, 'loss/train': 3.0425634384155273}
-03/03/2022 19:33:06 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/03/2022 19:33:10 - INFO - codeparrot_training - Step 5181: {'lr': 0.0004994302968104675, 'samples': 2653184, 'steps': 5181, 'loss/train': 2.2724032402038574}
-03/03/2022 19:33:13 - INFO - codeparrot_training - Step 5182: {'lr': 0.0004994299386991227, 'samples': 2653696, 'steps': 5182, 'loss/train': 3.801602840423584}
-03/03/2022 19:33:14 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/03/2022 19:33:18 - INFO - codeparrot_training - Step 5183: {'lr': 0.0004994295804753885, 'samples': 2654208, 'steps': 5183, 'loss/train': 2.0476343631744385}
-03/03/2022 19:33:21 - INFO - codeparrot_training - Step 5184: {'lr': 0.0004994292221392652, 'samples': 2654720, 'steps': 5184, 'loss/train': 3.317721366882324}
-03/03/2022 19:33:23 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/03/2022 19:33:27 - INFO - codeparrot_training - Step 5185: {'lr': 0.000499428863690753, 'samples': 2655232, 'steps': 5185, 'loss/train': 2.2468631267547607}
-03/03/2022 19:33:30 - INFO - codeparrot_training - Step 5186: {'lr': 0.0004994285051298519, 'samples': 2655744, 'steps': 5186, 'loss/train': 2.9777371883392334}
-03/03/2022 19:33:31 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/03/2022 19:33:35 - INFO - codeparrot_training - Step 5187: {'lr': 0.0004994281464565623, 'samples': 2656256, 'steps': 5187, 'loss/train': 2.721832036972046}
-03/03/2022 19:33:39 - INFO - codeparrot_training - Step 5188: {'lr': 0.0004994277876708841, 'samples': 2656768, 'steps': 5188, 'loss/train': 1.1594135761260986}
-03/03/2022 19:33:40 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/03/2022 19:33:44 - INFO - codeparrot_training - Step 5189: {'lr': 0.0004994274287728177, 'samples': 2657280, 'steps': 5189, 'loss/train': 2.874072790145874}
-03/03/2022 19:33:47 - INFO - codeparrot_training - Step 5190: {'lr': 0.0004994270697623631, 'samples': 2657792, 'steps': 5190, 'loss/train': 2.509965419769287}
-03/03/2022 19:33:49 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/03/2022 19:33:52 - INFO - codeparrot_training - Step 5191: {'lr': 0.0004994267106395205, 'samples': 2658304, 'steps': 5191, 'loss/train': 2.675917625427246}
-03/03/2022 19:33:56 - INFO - codeparrot_training - Step 5192: {'lr': 0.0004994263514042901, 'samples': 2658816, 'steps': 5192, 'loss/train': 2.7220232486724854}
-03/03/2022 19:33:57 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/03/2022 19:34:01 - INFO - codeparrot_training - Step 5193: {'lr': 0.0004994259920566719, 'samples': 2659328, 'steps': 5193, 'loss/train': 1.8324002027511597}
-03/03/2022 19:34:04 - INFO - codeparrot_training - Step 5194: {'lr': 0.0004994256325966663, 'samples': 2659840, 'steps': 5194, 'loss/train': 2.6217238903045654}
-03/03/2022 19:34:05 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/03/2022 19:34:09 - INFO - codeparrot_training - Step 5195: {'lr': 0.0004994252730242734, 'samples': 2660352, 'steps': 5195, 'loss/train': 1.4100428819656372}
-03/03/2022 19:34:12 - INFO - codeparrot_training - Step 5196: {'lr': 0.0004994249133394933, 'samples': 2660864, 'steps': 5196, 'loss/train': 3.0563085079193115}
-03/03/2022 19:34:14 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/03/2022 19:34:18 - INFO - codeparrot_training - Step 5197: {'lr': 0.0004994245535423262, 'samples': 2661376, 'steps': 5197, 'loss/train': 2.1499035358428955}
-03/03/2022 19:34:21 - INFO - codeparrot_training - Step 5198: {'lr': 0.0004994241936327722, 'samples': 2661888, 'steps': 5198, 'loss/train': 2.5570154190063477}
-03/03/2022 19:34:22 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/03/2022 19:34:26 - INFO - codeparrot_training - Step 5199: {'lr': 0.0004994238336108315, 'samples': 2662400, 'steps': 5199, 'loss/train': 3.1555683612823486}
-03/03/2022 19:34:29 - INFO - codeparrot_training - Step 5200: {'lr': 0.0004994234734765043, 'samples': 2662912, 'steps': 5200, 'loss/train': 2.7426838874816895}
-03/03/2022 19:34:30 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/03/2022 19:34:35 - INFO - codeparrot_training - Step 5201: {'lr': 0.0004994231132297907, 'samples': 2663424, 'steps': 5201, 'loss/train': 0.3698074519634247}
-03/03/2022 19:34:38 - INFO - codeparrot_training - Step 5202: {'lr': 0.0004994227528706909, 'samples': 2663936, 'steps': 5202, 'loss/train': 2.433607816696167}
-03/03/2022 19:34:39 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/03/2022 19:34:43 - INFO - codeparrot_training - Step 5203: {'lr': 0.0004994223923992052, 'samples': 2664448, 'steps': 5203, 'loss/train': 3.5757534503936768}
-03/03/2022 19:34:46 - INFO - codeparrot_training - Step 5204: {'lr': 0.0004994220318153334, 'samples': 2664960, 'steps': 5204, 'loss/train': 2.672785520553589}
-03/03/2022 19:34:48 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/03/2022 19:34:52 - INFO - codeparrot_training - Step 5205: {'lr': 0.000499421671119076, 'samples': 2665472, 'steps': 5205, 'loss/train': 1.7021936178207397}
-03/03/2022 19:34:55 - INFO - codeparrot_training - Step 5206: {'lr': 0.0004994213103104331, 'samples': 2665984, 'steps': 5206, 'loss/train': 2.5880351066589355}
-03/03/2022 19:34:56 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/03/2022 19:35:00 - INFO - codeparrot_training - Step 5207: {'lr': 0.0004994209493894046, 'samples': 2666496, 'steps': 5207, 'loss/train': 2.3896536827087402}
-03/03/2022 19:35:03 - INFO - codeparrot_training - Step 5208: {'lr': 0.000499420588355991, 'samples': 2667008, 'steps': 5208, 'loss/train': 1.988041639328003}
-03/03/2022 19:35:04 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/03/2022 19:35:09 - INFO - codeparrot_training - Step 5209: {'lr': 0.0004994202272101923, 'samples': 2667520, 'steps': 5209, 'loss/train': 2.061920642852783}
-03/03/2022 19:35:12 - INFO - codeparrot_training - Step 5210: {'lr': 0.0004994198659520087, 'samples': 2668032, 'steps': 5210, 'loss/train': 2.628566265106201}
-03/03/2022 19:35:13 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/03/2022 19:35:17 - INFO - codeparrot_training - Step 5211: {'lr': 0.0004994195045814404, 'samples': 2668544, 'steps': 5211, 'loss/train': 3.0805084705352783}
-03/03/2022 19:35:20 - INFO - codeparrot_training - Step 5212: {'lr': 0.0004994191430984876, 'samples': 2669056, 'steps': 5212, 'loss/train': 2.4303274154663086}
-03/03/2022 19:35:21 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/03/2022 19:35:25 - INFO - codeparrot_training - Step 5213: {'lr': 0.0004994187815031502, 'samples': 2669568, 'steps': 5213, 'loss/train': 2.6312990188598633}
-03/03/2022 19:35:29 - INFO - codeparrot_training - Step 5214: {'lr': 0.0004994184197954286, 'samples': 2670080, 'steps': 5214, 'loss/train': 2.661597728729248}
-03/03/2022 19:35:29 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/03/2022 19:35:34 - INFO - codeparrot_training - Step 5215: {'lr': 0.000499418057975323, 'samples': 2670592, 'steps': 5215, 'loss/train': 1.6887311935424805}
-03/03/2022 19:35:37 - INFO - codeparrot_training - Step 5216: {'lr': 0.0004994176960428333, 'samples': 2671104, 'steps': 5216, 'loss/train': 1.822649598121643}
-03/03/2022 19:35:42 - INFO - codeparrot_training - Step 5217: {'lr': 0.00049941733399796, 'samples': 2671616, 'steps': 5217, 'loss/train': 1.4654819965362549}
-03/03/2022 19:35:46 - INFO - codeparrot_training - Step 5218: {'lr': 0.000499416971840703, 'samples': 2672128, 'steps': 5218, 'loss/train': 1.9819905757904053}
-03/03/2022 19:35:47 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/03/2022 19:35:51 - INFO - codeparrot_training - Step 5219: {'lr': 0.0004994166095710626, 'samples': 2672640, 'steps': 5219, 'loss/train': 2.7181589603424072}
-03/03/2022 19:35:54 - INFO - codeparrot_training - Step 5220: {'lr': 0.000499416247189039, 'samples': 2673152, 'steps': 5220, 'loss/train': 2.628739595413208}
-03/03/2022 19:35:56 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/03/2022 19:35:59 - INFO - codeparrot_training - Step 5221: {'lr': 0.0004994158846946321, 'samples': 2673664, 'steps': 5221, 'loss/train': 1.904496669769287}
-03/03/2022 19:36:02 - INFO - codeparrot_training - Step 5222: {'lr': 0.0004994155220878425, 'samples': 2674176, 'steps': 5222, 'loss/train': 0.949457585811615}
-03/03/2022 19:36:04 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/03/2022 19:36:08 - INFO - codeparrot_training - Step 5223: {'lr': 0.0004994151593686699, 'samples': 2674688, 'steps': 5223, 'loss/train': 2.297633409500122}
-03/03/2022 19:36:11 - INFO - codeparrot_training - Step 5224: {'lr': 0.0004994147965371147, 'samples': 2675200, 'steps': 5224, 'loss/train': 2.4084510803222656}
-03/03/2022 19:36:13 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/03/2022 19:36:16 - INFO - codeparrot_training - Step 5225: {'lr': 0.0004994144335931772, 'samples': 2675712, 'steps': 5225, 'loss/train': 2.732233762741089}
-03/03/2022 19:36:19 - INFO - codeparrot_training - Step 5226: {'lr': 0.0004994140705368573, 'samples': 2676224, 'steps': 5226, 'loss/train': 2.4543049335479736}
-03/03/2022 19:36:21 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/03/2022 19:36:25 - INFO - codeparrot_training - Step 5227: {'lr': 0.0004994137073681552, 'samples': 2676736, 'steps': 5227, 'loss/train': 2.65755558013916}
-03/03/2022 19:36:28 - INFO - codeparrot_training - Step 5228: {'lr': 0.0004994133440870712, 'samples': 2677248, 'steps': 5228, 'loss/train': 2.4328832626342773}
-03/03/2022 19:36:29 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/03/2022 19:36:34 - INFO - codeparrot_training - Step 5229: {'lr': 0.0004994129806936054, 'samples': 2677760, 'steps': 5229, 'loss/train': 5.896612167358398}
-03/03/2022 19:36:37 - INFO - codeparrot_training - Step 5230: {'lr': 0.000499412617187758, 'samples': 2678272, 'steps': 5230, 'loss/train': 2.5086236000061035}
-03/03/2022 19:36:40 - INFO - codeparrot_training - Step 5231: {'lr': 0.0004994122535695291, 'samples': 2678784, 'steps': 5231, 'loss/train': 2.5102438926696777}
-03/03/2022 19:36:42 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 19:36:46 - INFO - codeparrot_training - Step 5232: {'lr': 0.0004994118898389189, 'samples': 2679296, 'steps': 5232, 'loss/train': 2.4384167194366455}
-03/03/2022 19:36:49 - INFO - codeparrot_training - Step 5233: {'lr': 0.0004994115259959274, 'samples': 2679808, 'steps': 5233, 'loss/train': 1.9448119401931763}
-03/03/2022 19:36:50 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/03/2022 19:36:54 - INFO - codeparrot_training - Step 5234: {'lr': 0.0004994111620405551, 'samples': 2680320, 'steps': 5234, 'loss/train': 1.9878569841384888}
-03/03/2022 19:36:57 - INFO - codeparrot_training - Step 5235: {'lr': 0.0004994107979728019, 'samples': 2680832, 'steps': 5235, 'loss/train': 2.2734568119049072}
-03/03/2022 19:36:59 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/03/2022 19:37:02 - INFO - codeparrot_training - Step 5236: {'lr': 0.0004994104337926681, 'samples': 2681344, 'steps': 5236, 'loss/train': 2.3742494583129883}
-03/03/2022 19:37:06 - INFO - codeparrot_training - Step 5237: {'lr': 0.0004994100695001537, 'samples': 2681856, 'steps': 5237, 'loss/train': 2.849242687225342}
-03/03/2022 19:37:08 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/03/2022 19:37:11 - INFO - codeparrot_training - Step 5238: {'lr': 0.0004994097050952591, 'samples': 2682368, 'steps': 5238, 'loss/train': 2.722480058670044}
-03/03/2022 19:37:14 - INFO - codeparrot_training - Step 5239: {'lr': 0.0004994093405779842, 'samples': 2682880, 'steps': 5239, 'loss/train': 2.82173228263855}
-03/03/2022 19:37:16 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/03/2022 19:37:19 - INFO - codeparrot_training - Step 5240: {'lr': 0.0004994089759483294, 'samples': 2683392, 'steps': 5240, 'loss/train': 1.3399664163589478}
-03/03/2022 19:37:22 - INFO - codeparrot_training - Step 5241: {'lr': 0.0004994086112062948, 'samples': 2683904, 'steps': 5241, 'loss/train': 2.648019313812256}
-03/03/2022 19:37:24 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/03/2022 19:37:28 - INFO - codeparrot_training - Step 5242: {'lr': 0.0004994082463518804, 'samples': 2684416, 'steps': 5242, 'loss/train': 2.319596290588379}
-03/03/2022 19:37:31 - INFO - codeparrot_training - Step 5243: {'lr': 0.0004994078813850865, 'samples': 2684928, 'steps': 5243, 'loss/train': 6.898748397827148}
-03/03/2022 19:37:33 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/03/2022 19:37:37 - INFO - codeparrot_training - Step 5244: {'lr': 0.0004994075163059134, 'samples': 2685440, 'steps': 5244, 'loss/train': 2.924379348754883}
-03/03/2022 19:37:40 - INFO - codeparrot_training - Step 5245: {'lr': 0.0004994071511143609, 'samples': 2685952, 'steps': 5245, 'loss/train': 2.20320200920105}
-03/03/2022 19:37:43 - INFO - codeparrot_training - Step 5246: {'lr': 0.0004994067858104296, 'samples': 2686464, 'steps': 5246, 'loss/train': 2.5707643032073975}
-03/03/2022 19:37:45 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 19:37:49 - INFO - codeparrot_training - Step 5247: {'lr': 0.0004994064203941195, 'samples': 2686976, 'steps': 5247, 'loss/train': 1.7394828796386719}
-03/03/2022 19:37:52 - INFO - codeparrot_training - Step 5248: {'lr': 0.0004994060548654304, 'samples': 2687488, 'steps': 5248, 'loss/train': 2.853119373321533}
-03/03/2022 19:37:54 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/03/2022 19:37:57 - INFO - codeparrot_training - Step 5249: {'lr': 0.000499405689224363, 'samples': 2688000, 'steps': 5249, 'loss/train': 2.919081211090088}
-03/03/2022 19:38:00 - INFO - codeparrot_training - Step 5250: {'lr': 0.0004994053234709172, 'samples': 2688512, 'steps': 5250, 'loss/train': 2.9274139404296875}
-03/03/2022 19:38:02 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/03/2022 19:38:05 - INFO - codeparrot_training - Step 5251: {'lr': 0.0004994049576050933, 'samples': 2689024, 'steps': 5251, 'loss/train': 1.9506653547286987}
-03/03/2022 19:38:09 - INFO - codeparrot_training - Step 5252: {'lr': 0.0004994045916268913, 'samples': 2689536, 'steps': 5252, 'loss/train': 2.3377904891967773}
-03/03/2022 19:38:10 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/03/2022 19:38:14 - INFO - codeparrot_training - Step 5253: {'lr': 0.0004994042255363115, 'samples': 2690048, 'steps': 5253, 'loss/train': 1.587653636932373}
-03/03/2022 19:38:17 - INFO - codeparrot_training - Step 5254: {'lr': 0.0004994038593333539, 'samples': 2690560, 'steps': 5254, 'loss/train': 2.217925548553467}
-03/03/2022 19:38:19 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/03/2022 19:38:22 - INFO - codeparrot_training - Step 5255: {'lr': 0.0004994034930180188, 'samples': 2691072, 'steps': 5255, 'loss/train': 2.587345838546753}
-03/03/2022 19:38:26 - INFO - codeparrot_training - Step 5256: {'lr': 0.0004994031265903063, 'samples': 2691584, 'steps': 5256, 'loss/train': 2.8096261024475098}
-03/03/2022 19:38:27 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/03/2022 19:38:31 - INFO - codeparrot_training - Step 5257: {'lr': 0.0004994027600502167, 'samples': 2692096, 'steps': 5257, 'loss/train': 2.1362149715423584}
-03/03/2022 19:38:34 - INFO - codeparrot_training - Step 5258: {'lr': 0.00049940239339775, 'samples': 2692608, 'steps': 5258, 'loss/train': 2.3198091983795166}
-03/03/2022 19:38:36 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/03/2022 19:38:39 - INFO - codeparrot_training - Step 5259: {'lr': 0.0004994020266329064, 'samples': 2693120, 'steps': 5259, 'loss/train': 2.6840476989746094}
-03/03/2022 19:38:43 - INFO - codeparrot_training - Step 5260: {'lr': 0.0004994016597556862, 'samples': 2693632, 'steps': 5260, 'loss/train': 2.7879974842071533}
-03/03/2022 19:38:45 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/03/2022 19:38:48 - INFO - codeparrot_training - Step 5261: {'lr': 0.0004994012927660894, 'samples': 2694144, 'steps': 5261, 'loss/train': 2.332946300506592}
-03/03/2022 19:38:52 - INFO - codeparrot_training - Step 5262: {'lr': 0.0004994009256641162, 'samples': 2694656, 'steps': 5262, 'loss/train': 2.95039963722229}
-03/03/2022 19:38:55 - INFO - codeparrot_training - Step 5263: {'lr': 0.0004994005584497667, 'samples': 2695168, 'steps': 5263, 'loss/train': 1.5046664476394653}
-03/03/2022 19:38:55 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/03/2022 19:39:00 - INFO - codeparrot_training - Step 5264: {'lr': 0.0004994001911230413, 'samples': 2695680, 'steps': 5264, 'loss/train': 2.139968156814575}
-03/03/2022 19:39:03 - INFO - codeparrot_training - Step 5265: {'lr': 0.00049939982368394, 'samples': 2696192, 'steps': 5265, 'loss/train': 2.4453606605529785}
-03/03/2022 19:39:03 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/03/2022 19:39:09 - INFO - codeparrot_training - Step 5266: {'lr': 0.000499399456132463, 'samples': 2696704, 'steps': 5266, 'loss/train': 2.1664235591888428}
-03/03/2022 19:39:11 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/03/2022 19:39:14 - INFO - codeparrot_training - Step 5267: {'lr': 0.0004993990884686105, 'samples': 2697216, 'steps': 5267, 'loss/train': 3.8769497871398926}
-03/03/2022 19:39:17 - INFO - codeparrot_training - Step 5268: {'lr': 0.0004993987206923825, 'samples': 2697728, 'steps': 5268, 'loss/train': 2.6145453453063965}
-03/03/2022 19:39:20 - INFO - codeparrot_training - Step 5269: {'lr': 0.0004993983528037793, 'samples': 2698240, 'steps': 5269, 'loss/train': 2.271522045135498}
-03/03/2022 19:39:21 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 19:39:26 - INFO - codeparrot_training - Step 5270: {'lr': 0.0004993979848028011, 'samples': 2698752, 'steps': 5270, 'loss/train': 1.5036842823028564}
-03/03/2022 19:39:29 - INFO - codeparrot_training - Step 5271: {'lr': 0.000499397616689448, 'samples': 2699264, 'steps': 5271, 'loss/train': 2.091313362121582}
-03/03/2022 19:39:29 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/03/2022 19:39:34 - INFO - codeparrot_training - Step 5272: {'lr': 0.0004993972484637202, 'samples': 2699776, 'steps': 5272, 'loss/train': 3.0317471027374268}
-03/03/2022 19:39:37 - INFO - codeparrot_training - Step 5273: {'lr': 0.0004993968801256178, 'samples': 2700288, 'steps': 5273, 'loss/train': 2.004610300064087}
-03/03/2022 19:39:37 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/03/2022 19:39:43 - INFO - codeparrot_training - Step 5274: {'lr': 0.0004993965116751411, 'samples': 2700800, 'steps': 5274, 'loss/train': 1.9966332912445068}
-03/03/2022 19:39:45 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/03/2022 19:39:48 - INFO - codeparrot_training - Step 5275: {'lr': 0.0004993961431122901, 'samples': 2701312, 'steps': 5275, 'loss/train': 2.285527229309082}
-03/03/2022 19:39:51 - INFO - codeparrot_training - Step 5276: {'lr': 0.0004993957744370651, 'samples': 2701824, 'steps': 5276, 'loss/train': 0.8534480333328247}
-03/03/2022 19:39:54 - INFO - codeparrot_training - Step 5277: {'lr': 0.0004993954056494662, 'samples': 2702336, 'steps': 5277, 'loss/train': 2.042626142501831}
-03/03/2022 19:39:54 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/03/2022 19:39:59 - INFO - codeparrot_training - Step 5278: {'lr': 0.0004993950367494936, 'samples': 2702848, 'steps': 5278, 'loss/train': 2.1774723529815674}
-03/03/2022 19:40:02 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/03/2022 19:40:05 - INFO - codeparrot_training - Step 5279: {'lr': 0.0004993946677371474, 'samples': 2703360, 'steps': 5279, 'loss/train': 2.0460457801818848}
-03/03/2022 19:40:08 - INFO - codeparrot_training - Step 5280: {'lr': 0.0004993942986124278, 'samples': 2703872, 'steps': 5280, 'loss/train': 3.328972339630127}
-03/03/2022 19:40:11 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/03/2022 19:40:13 - INFO - codeparrot_training - Step 5281: {'lr': 0.000499393929375335, 'samples': 2704384, 'steps': 5281, 'loss/train': 2.6549875736236572}
-03/03/2022 19:40:16 - INFO - codeparrot_training - Step 5282: {'lr': 0.0004993935600258691, 'samples': 2704896, 'steps': 5282, 'loss/train': 2.127960681915283}
-03/03/2022 19:40:19 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/03/2022 19:40:21 - INFO - codeparrot_training - Step 5283: {'lr': 0.0004993931905640305, 'samples': 2705408, 'steps': 5283, 'loss/train': 1.7595709562301636}
-03/03/2022 19:40:25 - INFO - codeparrot_training - Step 5284: {'lr': 0.000499392820989819, 'samples': 2705920, 'steps': 5284, 'loss/train': 1.7066619396209717}
-03/03/2022 19:40:28 - INFO - codeparrot_training - Step 5285: {'lr': 0.0004993924513032349, 'samples': 2706432, 'steps': 5285, 'loss/train': 2.640768051147461}
-03/03/2022 19:40:28 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/03/2022 19:40:33 - INFO - codeparrot_training - Step 5286: {'lr': 0.0004993920815042785, 'samples': 2706944, 'steps': 5286, 'loss/train': 2.375947952270508}
-03/03/2022 19:40:36 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/03/2022 19:40:38 - INFO - codeparrot_training - Step 5287: {'lr': 0.0004993917115929498, 'samples': 2707456, 'steps': 5287, 'loss/train': 2.2410829067230225}
-03/03/2022 19:40:42 - INFO - codeparrot_training - Step 5288: {'lr': 0.0004993913415692492, 'samples': 2707968, 'steps': 5288, 'loss/train': 2.094351291656494}
-03/03/2022 19:40:44 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/03/2022 19:40:47 - INFO - codeparrot_training - Step 5289: {'lr': 0.0004993909714331766, 'samples': 2708480, 'steps': 5289, 'loss/train': 2.3177478313446045}
-03/03/2022 19:40:50 - INFO - codeparrot_training - Step 5290: {'lr': 0.0004993906011847323, 'samples': 2708992, 'steps': 5290, 'loss/train': 1.9940495491027832}
-03/03/2022 19:40:53 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/03/2022 19:40:55 - INFO - codeparrot_training - Step 5291: {'lr': 0.0004993902308239164, 'samples': 2709504, 'steps': 5291, 'loss/train': 3.122563362121582}
-03/03/2022 19:40:58 - INFO - codeparrot_training - Step 5292: {'lr': 0.0004993898603507292, 'samples': 2710016, 'steps': 5292, 'loss/train': 2.3241806030273438}
-03/03/2022 19:41:02 - INFO - codeparrot_training - Step 5293: {'lr': 0.0004993894897651706, 'samples': 2710528, 'steps': 5293, 'loss/train': 2.9302752017974854}
-03/03/2022 19:41:02 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/03/2022 19:41:07 - INFO - codeparrot_training - Step 5294: {'lr': 0.0004993891190672411, 'samples': 2711040, 'steps': 5294, 'loss/train': 2.881843328475952}
-03/03/2022 19:41:10 - INFO - codeparrot_training - Step 5295: {'lr': 0.0004993887482569407, 'samples': 2711552, 'steps': 5295, 'loss/train': 2.7882561683654785}
-03/03/2022 19:41:10 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/03/2022 19:41:15 - INFO - codeparrot_training - Step 5296: {'lr': 0.0004993883773342695, 'samples': 2712064, 'steps': 5296, 'loss/train': 2.483201265335083}
-03/03/2022 19:41:18 - INFO - codeparrot_training - Step 5297: {'lr': 0.0004993880062992279, 'samples': 2712576, 'steps': 5297, 'loss/train': 1.6947877407073975}
-03/03/2022 19:41:19 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/03/2022 19:41:24 - INFO - codeparrot_training - Step 5298: {'lr': 0.0004993876351518157, 'samples': 2713088, 'steps': 5298, 'loss/train': 1.4849185943603516}
-03/03/2022 19:41:27 - INFO - codeparrot_training - Step 5299: {'lr': 0.0004993872638920335, 'samples': 2713600, 'steps': 5299, 'loss/train': 2.435993194580078}
-03/03/2022 19:41:27 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/03/2022 19:41:32 - INFO - codeparrot_training - Step 5300: {'lr': 0.0004993868925198811, 'samples': 2714112, 'steps': 5300, 'loss/train': 2.6581473350524902}
-03/03/2022 19:41:35 - INFO - codeparrot_training - Step 5301: {'lr': 0.0004993865210353588, 'samples': 2714624, 'steps': 5301, 'loss/train': 2.9962143898010254}
-03/03/2022 19:41:35 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/03/2022 19:41:41 - INFO - codeparrot_training - Step 5302: {'lr': 0.0004993861494384669, 'samples': 2715136, 'steps': 5302, 'loss/train': 2.736924409866333}
-03/03/2022 19:41:44 - INFO - codeparrot_training - Step 5303: {'lr': 0.0004993857777292053, 'samples': 2715648, 'steps': 5303, 'loss/train': 2.7132856845855713}
-03/03/2022 19:41:44 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/03/2022 19:41:49 - INFO - codeparrot_training - Step 5304: {'lr': 0.0004993854059075745, 'samples': 2716160, 'steps': 5304, 'loss/train': 2.5812222957611084}
-03/03/2022 19:41:52 - INFO - codeparrot_training - Step 5305: {'lr': 0.0004993850339735744, 'samples': 2716672, 'steps': 5305, 'loss/train': 1.7333853244781494}
-03/03/2022 19:41:52 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/03/2022 19:41:57 - INFO - codeparrot_training - Step 5306: {'lr': 0.0004993846619272052, 'samples': 2717184, 'steps': 5306, 'loss/train': 3.980846643447876}
-03/03/2022 19:42:00 - INFO - codeparrot_training - Step 5307: {'lr': 0.0004993842897684672, 'samples': 2717696, 'steps': 5307, 'loss/train': 2.036579132080078}
-03/03/2022 19:42:00 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/03/2022 19:42:06 - INFO - codeparrot_training - Step 5308: {'lr': 0.0004993839174973604, 'samples': 2718208, 'steps': 5308, 'loss/train': 2.3481671810150146}
-03/03/2022 19:42:09 - INFO - codeparrot_training - Step 5309: {'lr': 0.0004993835451138851, 'samples': 2718720, 'steps': 5309, 'loss/train': 2.3158981800079346}
-03/03/2022 19:42:09 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/03/2022 19:42:14 - INFO - codeparrot_training - Step 5310: {'lr': 0.0004993831726180414, 'samples': 2719232, 'steps': 5310, 'loss/train': 2.0033133029937744}
-03/03/2022 19:42:17 - INFO - codeparrot_training - Step 5311: {'lr': 0.0004993828000098296, 'samples': 2719744, 'steps': 5311, 'loss/train': 2.42049241065979}
-03/03/2022 19:42:17 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/03/2022 19:42:23 - INFO - codeparrot_training - Step 5312: {'lr': 0.0004993824272892497, 'samples': 2720256, 'steps': 5312, 'loss/train': 2.4189958572387695}
-03/03/2022 19:42:26 - INFO - codeparrot_training - Step 5313: {'lr': 0.0004993820544563018, 'samples': 2720768, 'steps': 5313, 'loss/train': 1.1844935417175293}
-03/03/2022 19:42:26 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/03/2022 19:42:31 - INFO - codeparrot_training - Step 5314: {'lr': 0.0004993816815109863, 'samples': 2721280, 'steps': 5314, 'loss/train': 2.0622851848602295}
-03/03/2022 19:42:34 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/03/2022 19:42:36 - INFO - codeparrot_training - Step 5315: {'lr': 0.0004993813084533033, 'samples': 2721792, 'steps': 5315, 'loss/train': 2.540081739425659}
-03/03/2022 19:42:40 - INFO - codeparrot_training - Step 5316: {'lr': 0.0004993809352832529, 'samples': 2722304, 'steps': 5316, 'loss/train': 2.215466022491455}
-03/03/2022 19:42:42 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/03/2022 19:42:45 - INFO - codeparrot_training - Step 5317: {'lr': 0.0004993805620008353, 'samples': 2722816, 'steps': 5317, 'loss/train': 2.1779439449310303}
-03/03/2022 19:42:48 - INFO - codeparrot_training - Step 5318: {'lr': 0.0004993801886060506, 'samples': 2723328, 'steps': 5318, 'loss/train': 0.7105789184570312}
-03/03/2022 19:42:51 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/03/2022 19:42:53 - INFO - codeparrot_training - Step 5319: {'lr': 0.0004993798150988991, 'samples': 2723840, 'steps': 5319, 'loss/train': 1.145135760307312}
-03/03/2022 19:42:56 - INFO - codeparrot_training - Step 5320: {'lr': 0.0004993794414793808, 'samples': 2724352, 'steps': 5320, 'loss/train': 2.324669361114502}
-03/03/2022 19:42:59 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/03/2022 19:43:02 - INFO - codeparrot_training - Step 5321: {'lr': 0.0004993790677474962, 'samples': 2724864, 'steps': 5321, 'loss/train': 2.588136911392212}
-03/03/2022 19:43:05 - INFO - codeparrot_training - Step 5322: {'lr': 0.0004993786939032451, 'samples': 2725376, 'steps': 5322, 'loss/train': 2.5738983154296875}
-03/03/2022 19:43:08 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/03/2022 19:43:10 - INFO - codeparrot_training - Step 5323: {'lr': 0.0004993783199466278, 'samples': 2725888, 'steps': 5323, 'loss/train': 2.3066420555114746}
-03/03/2022 19:43:13 - INFO - codeparrot_training - Step 5324: {'lr': 0.0004993779458776444, 'samples': 2726400, 'steps': 5324, 'loss/train': 1.3887360095977783}
-03/03/2022 19:43:16 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/03/2022 19:43:19 - INFO - codeparrot_training - Step 5325: {'lr': 0.0004993775716962953, 'samples': 2726912, 'steps': 5325, 'loss/train': 2.832693099975586}
-03/03/2022 19:43:22 - INFO - codeparrot_training - Step 5326: {'lr': 0.0004993771974025805, 'samples': 2727424, 'steps': 5326, 'loss/train': 1.9181170463562012}
-03/03/2022 19:43:24 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/03/2022 19:43:27 - INFO - codeparrot_training - Step 5327: {'lr': 0.0004993768229965001, 'samples': 2727936, 'steps': 5327, 'loss/train': 2.3992226123809814}
-03/03/2022 19:43:30 - INFO - codeparrot_training - Step 5328: {'lr': 0.0004993764484780543, 'samples': 2728448, 'steps': 5328, 'loss/train': 2.304861545562744}
-03/03/2022 19:43:33 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/03/2022 19:43:36 - INFO - codeparrot_training - Step 5329: {'lr': 0.0004993760738472435, 'samples': 2728960, 'steps': 5329, 'loss/train': 2.623361349105835}
-03/03/2022 19:43:39 - INFO - codeparrot_training - Step 5330: {'lr': 0.0004993756991040675, 'samples': 2729472, 'steps': 5330, 'loss/train': 2.436741590499878}
-03/03/2022 19:43:41 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/03/2022 19:43:44 - INFO - codeparrot_training - Step 5331: {'lr': 0.0004993753242485268, 'samples': 2729984, 'steps': 5331, 'loss/train': 2.223642110824585}
-03/03/2022 19:43:47 - INFO - codeparrot_training - Step 5332: {'lr': 0.0004993749492806214, 'samples': 2730496, 'steps': 5332, 'loss/train': 2.2259137630462646}
-03/03/2022 19:43:50 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/03/2022 19:43:53 - INFO - codeparrot_training - Step 5333: {'lr': 0.0004993745742003515, 'samples': 2731008, 'steps': 5333, 'loss/train': 2.377250909805298}
-03/03/2022 19:43:56 - INFO - codeparrot_training - Step 5334: {'lr': 0.0004993741990077172, 'samples': 2731520, 'steps': 5334, 'loss/train': 2.027240753173828}
-03/03/2022 19:43:58 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/03/2022 19:44:01 - INFO - codeparrot_training - Step 5335: {'lr': 0.0004993738237027188, 'samples': 2732032, 'steps': 5335, 'loss/train': 2.6697769165039062}
-03/03/2022 19:44:04 - INFO - codeparrot_training - Step 5336: {'lr': 0.0004993734482853563, 'samples': 2732544, 'steps': 5336, 'loss/train': 2.0539636611938477}
-03/03/2022 19:44:06 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/03/2022 19:44:10 - INFO - codeparrot_training - Step 5337: {'lr': 0.0004993730727556301, 'samples': 2733056, 'steps': 5337, 'loss/train': 2.457719564437866}
-03/03/2022 19:44:13 - INFO - codeparrot_training - Step 5338: {'lr': 0.0004993726971135402, 'samples': 2733568, 'steps': 5338, 'loss/train': 2.46217942237854}
-03/03/2022 19:44:15 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/03/2022 19:44:18 - INFO - codeparrot_training - Step 5339: {'lr': 0.0004993723213590868, 'samples': 2734080, 'steps': 5339, 'loss/train': 3.21539568901062}
-03/03/2022 19:44:21 - INFO - codeparrot_training - Step 5340: {'lr': 0.0004993719454922701, 'samples': 2734592, 'steps': 5340, 'loss/train': 2.2701408863067627}
-03/03/2022 19:44:23 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/03/2022 19:44:27 - INFO - codeparrot_training - Step 5341: {'lr': 0.0004993715695130902, 'samples': 2735104, 'steps': 5341, 'loss/train': 2.731882095336914}
-03/03/2022 19:44:30 - INFO - codeparrot_training - Step 5342: {'lr': 0.0004993711934215473, 'samples': 2735616, 'steps': 5342, 'loss/train': 2.188723087310791}
-03/03/2022 19:44:32 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/03/2022 19:44:35 - INFO - codeparrot_training - Step 5343: {'lr': 0.0004993708172176417, 'samples': 2736128, 'steps': 5343, 'loss/train': 2.4973511695861816}
-03/03/2022 19:44:38 - INFO - codeparrot_training - Step 5344: {'lr': 0.0004993704409013734, 'samples': 2736640, 'steps': 5344, 'loss/train': 2.376894474029541}
-03/03/2022 19:44:40 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/03/2022 19:44:43 - INFO - codeparrot_training - Step 5345: {'lr': 0.0004993700644727425, 'samples': 2737152, 'steps': 5345, 'loss/train': 1.4223265647888184}
-03/03/2022 19:44:47 - INFO - codeparrot_training - Step 5346: {'lr': 0.0004993696879317495, 'samples': 2737664, 'steps': 5346, 'loss/train': 2.024421215057373}
-03/03/2022 19:44:49 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/03/2022 19:44:52 - INFO - codeparrot_training - Step 5347: {'lr': 0.0004993693112783943, 'samples': 2738176, 'steps': 5347, 'loss/train': 2.9702537059783936}
-03/03/2022 19:44:55 - INFO - codeparrot_training - Step 5348: {'lr': 0.0004993689345126771, 'samples': 2738688, 'steps': 5348, 'loss/train': 3.660630941390991}
-03/03/2022 19:44:57 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/03/2022 19:45:00 - INFO - codeparrot_training - Step 5349: {'lr': 0.0004993685576345981, 'samples': 2739200, 'steps': 5349, 'loss/train': 2.515071153640747}
-03/03/2022 19:45:04 - INFO - codeparrot_training - Step 5350: {'lr': 0.0004993681806441575, 'samples': 2739712, 'steps': 5350, 'loss/train': 3.0928404331207275}
-03/03/2022 19:45:05 - INFO - codeparrot_training - Skipping example with length 385 (seq_length=1024)
-03/03/2022 19:45:09 - INFO - codeparrot_training - Step 5351: {'lr': 0.0004993678035413554, 'samples': 2740224, 'steps': 5351, 'loss/train': 1.4746264219284058}
-03/03/2022 19:45:12 - INFO - codeparrot_training - Step 5352: {'lr': 0.0004993674263261921, 'samples': 2740736, 'steps': 5352, 'loss/train': 2.0110671520233154}
-03/03/2022 19:45:13 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/03/2022 19:45:17 - INFO - codeparrot_training - Step 5353: {'lr': 0.0004993670489986677, 'samples': 2741248, 'steps': 5353, 'loss/train': 2.889194965362549}
-03/03/2022 19:45:20 - INFO - codeparrot_training - Step 5354: {'lr': 0.0004993666715587823, 'samples': 2741760, 'steps': 5354, 'loss/train': 2.524496078491211}
-03/03/2022 19:45:22 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/03/2022 19:45:26 - INFO - codeparrot_training - Step 5355: {'lr': 0.0004993662940065361, 'samples': 2742272, 'steps': 5355, 'loss/train': 2.762558698654175}
-03/03/2022 19:45:29 - INFO - codeparrot_training - Step 5356: {'lr': 0.0004993659163419294, 'samples': 2742784, 'steps': 5356, 'loss/train': 2.251805305480957}
-03/03/2022 19:45:31 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/03/2022 19:45:34 - INFO - codeparrot_training - Step 5357: {'lr': 0.0004993655385649621, 'samples': 2743296, 'steps': 5357, 'loss/train': 2.434264898300171}
-03/03/2022 19:45:38 - INFO - codeparrot_training - Step 5358: {'lr': 0.0004993651606756347, 'samples': 2743808, 'steps': 5358, 'loss/train': 1.9009076356887817}
-03/03/2022 19:45:39 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/03/2022 19:45:43 - INFO - codeparrot_training - Step 5359: {'lr': 0.0004993647826739471, 'samples': 2744320, 'steps': 5359, 'loss/train': 2.1590158939361572}
-03/03/2022 19:45:46 - INFO - codeparrot_training - Step 5360: {'lr': 0.0004993644045598997, 'samples': 2744832, 'steps': 5360, 'loss/train': 1.7679582834243774}
-03/03/2022 19:45:48 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/03/2022 19:45:51 - INFO - codeparrot_training - Step 5361: {'lr': 0.0004993640263334924, 'samples': 2745344, 'steps': 5361, 'loss/train': 1.8674119710922241}
-03/03/2022 19:45:54 - INFO - codeparrot_training - Step 5362: {'lr': 0.0004993636479947256, 'samples': 2745856, 'steps': 5362, 'loss/train': 2.6179707050323486}
-03/03/2022 19:45:56 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/03/2022 19:46:00 - INFO - codeparrot_training - Step 5363: {'lr': 0.0004993632695435993, 'samples': 2746368, 'steps': 5363, 'loss/train': 2.5757389068603516}
-03/03/2022 19:46:03 - INFO - codeparrot_training - Step 5364: {'lr': 0.0004993628909801138, 'samples': 2746880, 'steps': 5364, 'loss/train': 1.791359305381775}
-03/03/2022 19:46:05 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/03/2022 19:46:08 - INFO - codeparrot_training - Step 5365: {'lr': 0.0004993625123042694, 'samples': 2747392, 'steps': 5365, 'loss/train': 1.8913182020187378}
-03/03/2022 19:46:11 - INFO - codeparrot_training - Step 5366: {'lr': 0.0004993621335160659, 'samples': 2747904, 'steps': 5366, 'loss/train': 2.661086320877075}
-03/03/2022 19:46:13 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/03/2022 19:46:17 - INFO - codeparrot_training - Step 5367: {'lr': 0.0004993617546155037, 'samples': 2748416, 'steps': 5367, 'loss/train': 1.9424711465835571}
-03/03/2022 19:46:20 - INFO - codeparrot_training - Step 5368: {'lr': 0.000499361375602583, 'samples': 2748928, 'steps': 5368, 'loss/train': 2.0849246978759766}
-03/03/2022 19:46:21 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/03/2022 19:46:25 - INFO - codeparrot_training - Step 5369: {'lr': 0.0004993609964773039, 'samples': 2749440, 'steps': 5369, 'loss/train': 2.1598944664001465}
-03/03/2022 19:46:28 - INFO - codeparrot_training - Step 5370: {'lr': 0.0004993606172396665, 'samples': 2749952, 'steps': 5370, 'loss/train': 2.3109383583068848}
-03/03/2022 19:46:30 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/03/2022 19:46:33 - INFO - codeparrot_training - Step 5371: {'lr': 0.0004993602378896712, 'samples': 2750464, 'steps': 5371, 'loss/train': 2.3190996646881104}
-03/03/2022 19:46:37 - INFO - codeparrot_training - Step 5372: {'lr': 0.0004993598584273179, 'samples': 2750976, 'steps': 5372, 'loss/train': 2.6669466495513916}
-03/03/2022 19:46:38 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/03/2022 19:46:42 - INFO - codeparrot_training - Step 5373: {'lr': 0.0004993594788526069, 'samples': 2751488, 'steps': 5373, 'loss/train': 1.776182770729065}
-03/03/2022 19:46:45 - INFO - codeparrot_training - Step 5374: {'lr': 0.0004993590991655384, 'samples': 2752000, 'steps': 5374, 'loss/train': 2.1268608570098877}
-03/03/2022 19:46:47 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/03/2022 19:46:50 - INFO - codeparrot_training - Step 5375: {'lr': 0.0004993587193661126, 'samples': 2752512, 'steps': 5375, 'loss/train': 2.747736692428589}
-03/03/2022 19:46:53 - INFO - codeparrot_training - Step 5376: {'lr': 0.0004993583394543295, 'samples': 2753024, 'steps': 5376, 'loss/train': 2.547006368637085}
-03/03/2022 19:46:55 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/03/2022 19:46:59 - INFO - codeparrot_training - Step 5377: {'lr': 0.0004993579594301895, 'samples': 2753536, 'steps': 5377, 'loss/train': 1.6675543785095215}
-03/03/2022 19:47:02 - INFO - codeparrot_training - Step 5378: {'lr': 0.0004993575792936925, 'samples': 2754048, 'steps': 5378, 'loss/train': 2.9604556560516357}
-03/03/2022 19:47:03 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/03/2022 19:47:07 - INFO - codeparrot_training - Step 5379: {'lr': 0.000499357199044839, 'samples': 2754560, 'steps': 5379, 'loss/train': 2.7012462615966797}
-03/03/2022 19:47:11 - INFO - codeparrot_training - Step 5380: {'lr': 0.0004993568186836288, 'samples': 2755072, 'steps': 5380, 'loss/train': 1.2840118408203125}
-03/03/2022 19:47:12 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/03/2022 19:47:16 - INFO - codeparrot_training - Step 5381: {'lr': 0.0004993564382100624, 'samples': 2755584, 'steps': 5381, 'loss/train': 2.378167152404785}
-03/03/2022 19:47:19 - INFO - codeparrot_training - Step 5382: {'lr': 0.0004993560576241398, 'samples': 2756096, 'steps': 5382, 'loss/train': 2.228374481201172}
-03/03/2022 19:47:21 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/03/2022 19:47:25 - INFO - codeparrot_training - Step 5383: {'lr': 0.0004993556769258612, 'samples': 2756608, 'steps': 5383, 'loss/train': 2.629227638244629}
-03/03/2022 19:47:28 - INFO - codeparrot_training - Step 5384: {'lr': 0.0004993552961152268, 'samples': 2757120, 'steps': 5384, 'loss/train': 0.3719097375869751}
-03/03/2022 19:47:30 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/03/2022 19:47:33 - INFO - codeparrot_training - Step 5385: {'lr': 0.0004993549151922367, 'samples': 2757632, 'steps': 5385, 'loss/train': 2.9531352519989014}
-03/03/2022 19:47:36 - INFO - codeparrot_training - Step 5386: {'lr': 0.0004993545341568912, 'samples': 2758144, 'steps': 5386, 'loss/train': 2.062544107437134}
-03/03/2022 19:47:39 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/03/2022 19:47:41 - INFO - codeparrot_training - Step 5387: {'lr': 0.0004993541530091903, 'samples': 2758656, 'steps': 5387, 'loss/train': 2.6875438690185547}
-03/03/2022 19:47:44 - INFO - codeparrot_training - Step 5388: {'lr': 0.0004993537717491343, 'samples': 2759168, 'steps': 5388, 'loss/train': 2.16750431060791}
-03/03/2022 19:47:47 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/03/2022 19:47:50 - INFO - codeparrot_training - Step 5389: {'lr': 0.0004993533903767235, 'samples': 2759680, 'steps': 5389, 'loss/train': 2.2989330291748047}
-03/03/2022 19:47:53 - INFO - codeparrot_training - Step 5390: {'lr': 0.0004993530088919577, 'samples': 2760192, 'steps': 5390, 'loss/train': 1.9228806495666504}
-03/03/2022 19:47:55 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/03/2022 19:47:58 - INFO - codeparrot_training - Step 5391: {'lr': 0.0004993526272948374, 'samples': 2760704, 'steps': 5391, 'loss/train': 3.083970308303833}
-03/03/2022 19:48:01 - INFO - codeparrot_training - Step 5392: {'lr': 0.0004993522455853626, 'samples': 2761216, 'steps': 5392, 'loss/train': 1.9624916315078735}
-03/03/2022 19:48:03 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/03/2022 19:48:07 - INFO - codeparrot_training - Step 5393: {'lr': 0.0004993518637635334, 'samples': 2761728, 'steps': 5393, 'loss/train': 2.2643535137176514}
-03/03/2022 19:48:10 - INFO - codeparrot_training - Step 5394: {'lr': 0.0004993514818293503, 'samples': 2762240, 'steps': 5394, 'loss/train': 2.873499870300293}
-03/03/2022 19:48:12 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/03/2022 19:48:15 - INFO - codeparrot_training - Step 5395: {'lr': 0.0004993510997828132, 'samples': 2762752, 'steps': 5395, 'loss/train': 2.112417459487915}
-03/03/2022 19:48:18 - INFO - codeparrot_training - Step 5396: {'lr': 0.0004993507176239224, 'samples': 2763264, 'steps': 5396, 'loss/train': 3.2508904933929443}
-03/03/2022 19:48:20 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/03/2022 19:48:23 - INFO - codeparrot_training - Step 5397: {'lr': 0.0004993503353526779, 'samples': 2763776, 'steps': 5397, 'loss/train': 2.334263324737549}
-03/03/2022 19:48:27 - INFO - codeparrot_training - Step 5398: {'lr': 0.0004993499529690801, 'samples': 2764288, 'steps': 5398, 'loss/train': 0.23353344202041626}
-03/03/2022 19:48:29 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/03/2022 19:48:32 - INFO - codeparrot_training - Step 5399: {'lr': 0.000499349570473129, 'samples': 2764800, 'steps': 5399, 'loss/train': 2.687574863433838}
-03/03/2022 19:48:35 - INFO - codeparrot_training - Step 5400: {'lr': 0.0004993491878648249, 'samples': 2765312, 'steps': 5400, 'loss/train': 1.8534095287322998}
-03/03/2022 19:48:38 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/03/2022 19:48:41 - INFO - codeparrot_training - Step 5401: {'lr': 0.0004993488051441677, 'samples': 2765824, 'steps': 5401, 'loss/train': 1.8499391078948975}
-03/03/2022 19:48:44 - INFO - codeparrot_training - Step 5402: {'lr': 0.000499348422311158, 'samples': 2766336, 'steps': 5402, 'loss/train': 1.8635329008102417}
-03/03/2022 19:48:46 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/03/2022 19:48:49 - INFO - codeparrot_training - Step 5403: {'lr': 0.0004993480393657956, 'samples': 2766848, 'steps': 5403, 'loss/train': 2.618917465209961}
-03/03/2022 19:48:52 - INFO - codeparrot_training - Step 5404: {'lr': 0.0004993476563080809, 'samples': 2767360, 'steps': 5404, 'loss/train': 2.455942153930664}
-03/03/2022 19:48:54 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/03/2022 19:48:58 - INFO - codeparrot_training - Step 5405: {'lr': 0.000499347273138014, 'samples': 2767872, 'steps': 5405, 'loss/train': 1.7579269409179688}
-03/03/2022 19:49:01 - INFO - codeparrot_training - Step 5406: {'lr': 0.000499346889855595, 'samples': 2768384, 'steps': 5406, 'loss/train': 1.71574866771698}
-03/03/2022 19:49:03 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/03/2022 19:49:06 - INFO - codeparrot_training - Step 5407: {'lr': 0.0004993465064608242, 'samples': 2768896, 'steps': 5407, 'loss/train': 2.1226017475128174}
-03/03/2022 19:49:09 - INFO - codeparrot_training - Step 5408: {'lr': 0.0004993461229537017, 'samples': 2769408, 'steps': 5408, 'loss/train': 2.327568292617798}
-03/03/2022 19:49:12 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/03/2022 19:49:14 - INFO - codeparrot_training - Step 5409: {'lr': 0.0004993457393342276, 'samples': 2769920, 'steps': 5409, 'loss/train': 2.4674551486968994}
-03/03/2022 19:49:18 - INFO - codeparrot_training - Step 5410: {'lr': 0.0004993453556024023, 'samples': 2770432, 'steps': 5410, 'loss/train': 2.3855679035186768}
-03/03/2022 19:49:20 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/03/2022 19:49:23 - INFO - codeparrot_training - Step 5411: {'lr': 0.0004993449717582258, 'samples': 2770944, 'steps': 5411, 'loss/train': 2.037806272506714}
-03/03/2022 19:49:26 - INFO - codeparrot_training - Step 5412: {'lr': 0.0004993445878016982, 'samples': 2771456, 'steps': 5412, 'loss/train': 3.0086143016815186}
-03/03/2022 19:49:29 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/03/2022 19:49:31 - INFO - codeparrot_training - Step 5413: {'lr': 0.0004993442037328199, 'samples': 2771968, 'steps': 5413, 'loss/train': 2.1714775562286377}
-03/03/2022 19:49:35 - INFO - codeparrot_training - Step 5414: {'lr': 0.0004993438195515909, 'samples': 2772480, 'steps': 5414, 'loss/train': 1.8221074342727661}
-03/03/2022 19:49:37 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/03/2022 19:49:40 - INFO - codeparrot_training - Step 5415: {'lr': 0.0004993434352580115, 'samples': 2772992, 'steps': 5415, 'loss/train': 1.5437082052230835}
-03/03/2022 19:49:43 - INFO - codeparrot_training - Step 5416: {'lr': 0.0004993430508520816, 'samples': 2773504, 'steps': 5416, 'loss/train': 1.8315552473068237}
-03/03/2022 19:49:45 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/03/2022 19:49:48 - INFO - codeparrot_training - Step 5417: {'lr': 0.0004993426663338018, 'samples': 2774016, 'steps': 5417, 'loss/train': 2.991011619567871}
-03/03/2022 19:49:51 - INFO - codeparrot_training - Step 5418: {'lr': 0.0004993422817031719, 'samples': 2774528, 'steps': 5418, 'loss/train': 1.3490928411483765}
-03/03/2022 19:49:54 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/03/2022 19:49:57 - INFO - codeparrot_training - Step 5419: {'lr': 0.0004993418969601921, 'samples': 2775040, 'steps': 5419, 'loss/train': 2.7507355213165283}
-03/03/2022 19:50:00 - INFO - codeparrot_training - Step 5420: {'lr': 0.0004993415121048629, 'samples': 2775552, 'steps': 5420, 'loss/train': 1.8808454275131226}
-03/03/2022 19:50:02 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/03/2022 19:50:05 - INFO - codeparrot_training - Step 5421: {'lr': 0.0004993411271371842, 'samples': 2776064, 'steps': 5421, 'loss/train': 2.252434730529785}
-03/03/2022 19:50:08 - INFO - codeparrot_training - Step 5422: {'lr': 0.0004993407420571563, 'samples': 2776576, 'steps': 5422, 'loss/train': 1.9535220861434937}
-03/03/2022 19:50:11 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/03/2022 19:50:14 - INFO - codeparrot_training - Step 5423: {'lr': 0.0004993403568647792, 'samples': 2777088, 'steps': 5423, 'loss/train': 2.2977166175842285}
-03/03/2022 19:50:17 - INFO - codeparrot_training - Step 5424: {'lr': 0.0004993399715600531, 'samples': 2777600, 'steps': 5424, 'loss/train': 2.4810147285461426}
-03/03/2022 19:50:19 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/03/2022 19:50:22 - INFO - codeparrot_training - Step 5425: {'lr': 0.0004993395861429785, 'samples': 2778112, 'steps': 5425, 'loss/train': 1.7641781568527222}
-03/03/2022 19:50:25 - INFO - codeparrot_training - Step 5426: {'lr': 0.0004993392006135552, 'samples': 2778624, 'steps': 5426, 'loss/train': 2.528172016143799}
-03/03/2022 19:50:28 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/03/2022 19:50:31 - INFO - codeparrot_training - Step 5427: {'lr': 0.0004993388149717834, 'samples': 2779136, 'steps': 5427, 'loss/train': 2.9187514781951904}
-03/03/2022 19:50:34 - INFO - codeparrot_training - Step 5428: {'lr': 0.0004993384292176636, 'samples': 2779648, 'steps': 5428, 'loss/train': 3.100329637527466}
-03/03/2022 19:50:36 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/03/2022 19:50:39 - INFO - codeparrot_training - Step 5429: {'lr': 0.0004993380433511956, 'samples': 2780160, 'steps': 5429, 'loss/train': 2.2120885848999023}
-03/03/2022 19:50:42 - INFO - codeparrot_training - Step 5430: {'lr': 0.0004993376573723798, 'samples': 2780672, 'steps': 5430, 'loss/train': 2.560666799545288}
-03/03/2022 19:50:45 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/03/2022 19:50:48 - INFO - codeparrot_training - Step 5431: {'lr': 0.0004993372712812162, 'samples': 2781184, 'steps': 5431, 'loss/train': 2.0579278469085693}
-03/03/2022 19:50:51 - INFO - codeparrot_training - Step 5432: {'lr': 0.0004993368850777052, 'samples': 2781696, 'steps': 5432, 'loss/train': 2.545896053314209}
-03/03/2022 19:50:53 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/03/2022 19:50:56 - INFO - codeparrot_training - Step 5433: {'lr': 0.0004993364987618468, 'samples': 2782208, 'steps': 5433, 'loss/train': 2.3555805683135986}
-03/03/2022 19:50:59 - INFO - codeparrot_training - Step 5434: {'lr': 0.0004993361123336412, 'samples': 2782720, 'steps': 5434, 'loss/train': 2.4304447174072266}
-03/03/2022 19:51:01 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/03/2022 19:51:05 - INFO - codeparrot_training - Step 5435: {'lr': 0.0004993357257930887, 'samples': 2783232, 'steps': 5435, 'loss/train': 2.659261465072632}
-03/03/2022 19:51:08 - INFO - codeparrot_training - Step 5436: {'lr': 0.0004993353391401892, 'samples': 2783744, 'steps': 5436, 'loss/train': 2.7309205532073975}
-03/03/2022 19:51:10 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/03/2022 19:51:13 - INFO - codeparrot_training - Step 5437: {'lr': 0.0004993349523749431, 'samples': 2784256, 'steps': 5437, 'loss/train': 1.9009641408920288}
-03/03/2022 19:51:16 - INFO - codeparrot_training - Step 5438: {'lr': 0.0004993345654973505, 'samples': 2784768, 'steps': 5438, 'loss/train': 2.29182505607605}
-03/03/2022 19:51:18 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/03/2022 19:51:21 - INFO - codeparrot_training - Step 5439: {'lr': 0.0004993341785074116, 'samples': 2785280, 'steps': 5439, 'loss/train': 2.4964182376861572}
-03/03/2022 19:51:25 - INFO - codeparrot_training - Step 5440: {'lr': 0.0004993337914051266, 'samples': 2785792, 'steps': 5440, 'loss/train': 2.9504287242889404}
-03/03/2022 19:51:26 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/03/2022 19:51:30 - INFO - codeparrot_training - Step 5441: {'lr': 0.0004993334041904957, 'samples': 2786304, 'steps': 5441, 'loss/train': 2.826967477798462}
-03/03/2022 19:51:33 - INFO - codeparrot_training - Step 5442: {'lr': 0.0004993330168635189, 'samples': 2786816, 'steps': 5442, 'loss/train': 2.3300163745880127}
-03/03/2022 19:51:34 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/03/2022 19:51:38 - INFO - codeparrot_training - Step 5443: {'lr': 0.0004993326294241966, 'samples': 2787328, 'steps': 5443, 'loss/train': 1.1911982297897339}
-03/03/2022 19:51:41 - INFO - codeparrot_training - Step 5444: {'lr': 0.0004993322418725286, 'samples': 2787840, 'steps': 5444, 'loss/train': 2.194857120513916}
-03/03/2022 19:51:43 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/03/2022 19:51:47 - INFO - codeparrot_training - Step 5445: {'lr': 0.0004993318542085157, 'samples': 2788352, 'steps': 5445, 'loss/train': 2.4158711433410645}
-03/03/2022 19:51:50 - INFO - codeparrot_training - Step 5446: {'lr': 0.0004993314664321575, 'samples': 2788864, 'steps': 5446, 'loss/train': 2.0690410137176514}
-03/03/2022 19:51:51 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/03/2022 19:51:55 - INFO - codeparrot_training - Step 5447: {'lr': 0.0004993310785434544, 'samples': 2789376, 'steps': 5447, 'loss/train': 1.3384076356887817}
-03/03/2022 19:51:58 - INFO - codeparrot_training - Step 5448: {'lr': 0.0004993306905424067, 'samples': 2789888, 'steps': 5448, 'loss/train': 1.6024459600448608}
-03/03/2022 19:52:00 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/03/2022 19:52:04 - INFO - codeparrot_training - Step 5449: {'lr': 0.0004993303024290143, 'samples': 2790400, 'steps': 5449, 'loss/train': 1.6629639863967896}
-03/03/2022 19:52:07 - INFO - codeparrot_training - Step 5450: {'lr': 0.0004993299142032776, 'samples': 2790912, 'steps': 5450, 'loss/train': 2.004060745239258}
-03/03/2022 19:52:08 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/03/2022 19:52:12 - INFO - codeparrot_training - Step 5451: {'lr': 0.0004993295258651966, 'samples': 2791424, 'steps': 5451, 'loss/train': 1.640705943107605}
-03/03/2022 19:52:15 - INFO - codeparrot_training - Step 5452: {'lr': 0.0004993291374147716, 'samples': 2791936, 'steps': 5452, 'loss/train': 1.2085177898406982}
-03/03/2022 19:52:17 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/03/2022 19:52:21 - INFO - codeparrot_training - Step 5453: {'lr': 0.0004993287488520027, 'samples': 2792448, 'steps': 5453, 'loss/train': 2.4406557083129883}
-03/03/2022 19:52:24 - INFO - codeparrot_training - Step 5454: {'lr': 0.0004993283601768902, 'samples': 2792960, 'steps': 5454, 'loss/train': 1.2845011949539185}
-03/03/2022 19:52:25 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/03/2022 19:52:29 - INFO - codeparrot_training - Step 5455: {'lr': 0.0004993279713894342, 'samples': 2793472, 'steps': 5455, 'loss/train': 2.4415886402130127}
-03/03/2022 19:52:32 - INFO - codeparrot_training - Step 5456: {'lr': 0.0004993275824896348, 'samples': 2793984, 'steps': 5456, 'loss/train': 2.3902504444122314}
-03/03/2022 19:52:34 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/03/2022 19:52:37 - INFO - codeparrot_training - Step 5457: {'lr': 0.0004993271934774922, 'samples': 2794496, 'steps': 5457, 'loss/train': 2.694479465484619}
-03/03/2022 19:52:41 - INFO - codeparrot_training - Step 5458: {'lr': 0.0004993268043530067, 'samples': 2795008, 'steps': 5458, 'loss/train': 2.9109439849853516}
-03/03/2022 19:52:42 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/03/2022 19:52:46 - INFO - codeparrot_training - Step 5459: {'lr': 0.0004993264151161783, 'samples': 2795520, 'steps': 5459, 'loss/train': 2.6735360622406006}
-03/03/2022 19:52:50 - INFO - codeparrot_training - Step 5460: {'lr': 0.0004993260257670074, 'samples': 2796032, 'steps': 5460, 'loss/train': 1.494610071182251}
-03/03/2022 19:52:53 - INFO - codeparrot_training - Step 5461: {'lr': 0.000499325636305494, 'samples': 2796544, 'steps': 5461, 'loss/train': 2.651712656021118}
-03/03/2022 19:52:53 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/03/2022 19:52:58 - INFO - codeparrot_training - Step 5462: {'lr': 0.0004993252467316382, 'samples': 2797056, 'steps': 5462, 'loss/train': 2.3470165729522705}
-03/03/2022 19:53:01 - INFO - codeparrot_training - Step 5463: {'lr': 0.0004993248570454404, 'samples': 2797568, 'steps': 5463, 'loss/train': 2.5574257373809814}
-03/03/2022 19:53:01 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/03/2022 19:53:06 - INFO - codeparrot_training - Step 5464: {'lr': 0.0004993244672469007, 'samples': 2798080, 'steps': 5464, 'loss/train': 2.0790576934814453}
-03/03/2022 19:53:10 - INFO - codeparrot_training - Step 5465: {'lr': 0.000499324077336019, 'samples': 2798592, 'steps': 5465, 'loss/train': 2.5823538303375244}
-03/03/2022 19:53:10 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/03/2022 19:53:15 - INFO - codeparrot_training - Step 5466: {'lr': 0.000499323687312796, 'samples': 2799104, 'steps': 5466, 'loss/train': 2.097334146499634}
-03/03/2022 19:53:18 - INFO - codeparrot_training - Step 5467: {'lr': 0.0004993232971772315, 'samples': 2799616, 'steps': 5467, 'loss/train': 2.2272653579711914}
-03/03/2022 19:53:18 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/03/2022 19:53:23 - INFO - codeparrot_training - Step 5468: {'lr': 0.0004993229069293257, 'samples': 2800128, 'steps': 5468, 'loss/train': 2.8724734783172607}
-03/03/2022 19:53:27 - INFO - codeparrot_training - Step 5469: {'lr': 0.0004993225165690789, 'samples': 2800640, 'steps': 5469, 'loss/train': 1.3314955234527588}
-03/03/2022 19:53:27 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/03/2022 19:53:32 - INFO - codeparrot_training - Step 5470: {'lr': 0.0004993221260964912, 'samples': 2801152, 'steps': 5470, 'loss/train': 0.5634737610816956}
-03/03/2022 19:53:35 - INFO - codeparrot_training - Step 5471: {'lr': 0.0004993217355115628, 'samples': 2801664, 'steps': 5471, 'loss/train': 1.6151244640350342}
-03/03/2022 19:53:36 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/03/2022 19:53:40 - INFO - codeparrot_training - Step 5472: {'lr': 0.0004993213448142939, 'samples': 2802176, 'steps': 5472, 'loss/train': 2.7478010654449463}
-03/03/2022 19:53:43 - INFO - codeparrot_training - Step 5473: {'lr': 0.0004993209540046846, 'samples': 2802688, 'steps': 5473, 'loss/train': 2.524498462677002}
-03/03/2022 19:53:44 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/03/2022 19:53:49 - INFO - codeparrot_training - Step 5474: {'lr': 0.0004993205630827352, 'samples': 2803200, 'steps': 5474, 'loss/train': 2.5200064182281494}
-03/03/2022 19:53:52 - INFO - codeparrot_training - Step 5475: {'lr': 0.0004993201720484458, 'samples': 2803712, 'steps': 5475, 'loss/train': 2.001699447631836}
-03/03/2022 19:53:52 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/03/2022 19:53:57 - INFO - codeparrot_training - Step 5476: {'lr': 0.0004993197809018165, 'samples': 2804224, 'steps': 5476, 'loss/train': 2.2075905799865723}
-03/03/2022 19:54:00 - INFO - codeparrot_training - Step 5477: {'lr': 0.0004993193896428476, 'samples': 2804736, 'steps': 5477, 'loss/train': 2.3260233402252197}
-03/03/2022 19:54:00 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/03/2022 19:54:05 - INFO - codeparrot_training - Step 5478: {'lr': 0.0004993189982715392, 'samples': 2805248, 'steps': 5478, 'loss/train': 2.651952028274536}
-03/03/2022 19:54:09 - INFO - codeparrot_training - Step 5479: {'lr': 0.0004993186067878916, 'samples': 2805760, 'steps': 5479, 'loss/train': 1.2404234409332275}
-03/03/2022 19:54:09 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/03/2022 19:54:14 - INFO - codeparrot_training - Step 5480: {'lr': 0.0004993182151919049, 'samples': 2806272, 'steps': 5480, 'loss/train': 2.4023468494415283}
-03/03/2022 19:54:17 - INFO - codeparrot_training - Step 5481: {'lr': 0.0004993178234835792, 'samples': 2806784, 'steps': 5481, 'loss/train': 2.530648708343506}
-03/03/2022 19:54:17 - INFO - codeparrot_training - Skipping example with length 5 (seq_length=1024)
-03/03/2022 19:54:22 - INFO - codeparrot_training - Step 5482: {'lr': 0.0004993174316629146, 'samples': 2807296, 'steps': 5482, 'loss/train': 2.2001686096191406}
-03/03/2022 19:54:25 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/03/2022 19:54:28 - INFO - codeparrot_training - Step 5483: {'lr': 0.0004993170397299116, 'samples': 2807808, 'steps': 5483, 'loss/train': 4.1833930015563965}
-03/03/2022 19:54:31 - INFO - codeparrot_training - Step 5484: {'lr': 0.0004993166476845701, 'samples': 2808320, 'steps': 5484, 'loss/train': 2.293292999267578}
-03/03/2022 19:54:34 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/03/2022 19:54:36 - INFO - codeparrot_training - Step 5485: {'lr': 0.0004993162555268903, 'samples': 2808832, 'steps': 5485, 'loss/train': 2.0530989170074463}
-03/03/2022 19:54:39 - INFO - codeparrot_training - Step 5486: {'lr': 0.0004993158632568726, 'samples': 2809344, 'steps': 5486, 'loss/train': 2.292264699935913}
-03/03/2022 19:54:42 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/03/2022 19:54:45 - INFO - codeparrot_training - Step 5487: {'lr': 0.000499315470874517, 'samples': 2809856, 'steps': 5487, 'loss/train': 2.2603161334991455}
-03/03/2022 19:54:48 - INFO - codeparrot_training - Step 5488: {'lr': 0.0004993150783798236, 'samples': 2810368, 'steps': 5488, 'loss/train': 3.016301155090332}
-03/03/2022 19:54:50 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/03/2022 19:54:53 - INFO - codeparrot_training - Step 5489: {'lr': 0.0004993146857727927, 'samples': 2810880, 'steps': 5489, 'loss/train': 2.0685524940490723}
-03/03/2022 19:54:56 - INFO - codeparrot_training - Step 5490: {'lr': 0.0004993142930534245, 'samples': 2811392, 'steps': 5490, 'loss/train': 2.355656147003174}
-03/03/2022 19:54:58 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/03/2022 19:55:01 - INFO - codeparrot_training - Step 5491: {'lr': 0.000499313900221719, 'samples': 2811904, 'steps': 5491, 'loss/train': 1.762961506843567}
-03/03/2022 19:55:05 - INFO - codeparrot_training - Step 5492: {'lr': 0.0004993135072776766, 'samples': 2812416, 'steps': 5492, 'loss/train': 2.7785162925720215}
-03/03/2022 19:55:07 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/03/2022 19:55:10 - INFO - codeparrot_training - Step 5493: {'lr': 0.0004993131142212974, 'samples': 2812928, 'steps': 5493, 'loss/train': 2.5308609008789062}
-03/03/2022 19:55:13 - INFO - codeparrot_training - Step 5494: {'lr': 0.0004993127210525815, 'samples': 2813440, 'steps': 5494, 'loss/train': 2.734100580215454}
-03/03/2022 19:55:15 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/03/2022 19:55:19 - INFO - codeparrot_training - Step 5495: {'lr': 0.0004993123277715292, 'samples': 2813952, 'steps': 5495, 'loss/train': 1.9065457582473755}
-03/03/2022 19:55:22 - INFO - codeparrot_training - Step 5496: {'lr': 0.0004993119343781406, 'samples': 2814464, 'steps': 5496, 'loss/train': 2.237927198410034}
-03/03/2022 19:55:24 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/03/2022 19:55:27 - INFO - codeparrot_training - Step 5497: {'lr': 0.0004993115408724159, 'samples': 2814976, 'steps': 5497, 'loss/train': 2.0627002716064453}
-03/03/2022 19:55:30 - INFO - codeparrot_training - Step 5498: {'lr': 0.0004993111472543552, 'samples': 2815488, 'steps': 5498, 'loss/train': 2.9814679622650146}
-03/03/2022 19:55:32 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/03/2022 19:55:36 - INFO - codeparrot_training - Step 5499: {'lr': 0.0004993107535239588, 'samples': 2816000, 'steps': 5499, 'loss/train': 3.789454936981201}
-03/03/2022 19:55:39 - INFO - codeparrot_training - Step 5500: {'lr': 0.0004993103596812267, 'samples': 2816512, 'steps': 5500, 'loss/train': 2.2764742374420166}
-03/03/2022 19:55:41 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/03/2022 19:55:44 - INFO - codeparrot_training - Step 5501: {'lr': 0.0004993099657261594, 'samples': 2817024, 'steps': 5501, 'loss/train': 2.979717969894409}
-03/03/2022 19:55:47 - INFO - codeparrot_training - Step 5502: {'lr': 0.0004993095716587568, 'samples': 2817536, 'steps': 5502, 'loss/train': 1.4812233448028564}
-03/03/2022 19:55:49 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/03/2022 19:55:52 - INFO - codeparrot_training - Step 5503: {'lr': 0.0004993091774790191, 'samples': 2818048, 'steps': 5503, 'loss/train': 2.2033133506774902}
-03/03/2022 19:55:56 - INFO - codeparrot_training - Step 5504: {'lr': 0.0004993087831869466, 'samples': 2818560, 'steps': 5504, 'loss/train': 1.2456215620040894}
-03/03/2022 19:55:58 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/03/2022 19:56:01 - INFO - codeparrot_training - Step 5505: {'lr': 0.0004993083887825393, 'samples': 2819072, 'steps': 5505, 'loss/train': 1.877539873123169}
-03/03/2022 19:56:04 - INFO - codeparrot_training - Step 5506: {'lr': 0.0004993079942657976, 'samples': 2819584, 'steps': 5506, 'loss/train': 3.0588128566741943}
-03/03/2022 19:56:06 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/03/2022 19:56:09 - INFO - codeparrot_training - Step 5507: {'lr': 0.0004993075996367215, 'samples': 2820096, 'steps': 5507, 'loss/train': 2.3265936374664307}
-03/03/2022 19:56:13 - INFO - codeparrot_training - Step 5508: {'lr': 0.0004993072048953113, 'samples': 2820608, 'steps': 5508, 'loss/train': 2.220080614089966}
-03/03/2022 19:56:14 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/03/2022 19:56:18 - INFO - codeparrot_training - Step 5509: {'lr': 0.0004993068100415671, 'samples': 2821120, 'steps': 5509, 'loss/train': 0.5468441247940063}
-03/03/2022 19:56:21 - INFO - codeparrot_training - Step 5510: {'lr': 0.000499306415075489, 'samples': 2821632, 'steps': 5510, 'loss/train': 2.2533411979675293}
-03/03/2022 19:56:23 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/03/2022 19:56:26 - INFO - codeparrot_training - Step 5511: {'lr': 0.0004993060199970774, 'samples': 2822144, 'steps': 5511, 'loss/train': 2.590324640274048}
-03/03/2022 19:56:30 - INFO - codeparrot_training - Step 5512: {'lr': 0.0004993056248063323, 'samples': 2822656, 'steps': 5512, 'loss/train': 0.7862648963928223}
-03/03/2022 19:56:31 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/03/2022 19:56:35 - INFO - codeparrot_training - Step 5513: {'lr': 0.000499305229503254, 'samples': 2823168, 'steps': 5513, 'loss/train': 2.6166036128997803}
-03/03/2022 19:56:38 - INFO - codeparrot_training - Step 5514: {'lr': 0.0004993048340878425, 'samples': 2823680, 'steps': 5514, 'loss/train': 3.154320240020752}
-03/03/2022 19:56:40 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/03/2022 19:56:43 - INFO - codeparrot_training - Step 5515: {'lr': 0.0004993044385600982, 'samples': 2824192, 'steps': 5515, 'loss/train': 2.045004367828369}
-03/03/2022 19:56:46 - INFO - codeparrot_training - Step 5516: {'lr': 0.0004993040429200211, 'samples': 2824704, 'steps': 5516, 'loss/train': 2.3369338512420654}
-03/03/2022 19:56:48 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/03/2022 19:56:52 - INFO - codeparrot_training - Step 5517: {'lr': 0.0004993036471676115, 'samples': 2825216, 'steps': 5517, 'loss/train': 2.341843843460083}
-03/03/2022 19:56:55 - INFO - codeparrot_training - Step 5518: {'lr': 0.0004993032513028695, 'samples': 2825728, 'steps': 5518, 'loss/train': 2.051394462585449}
-03/03/2022 19:56:57 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/03/2022 19:57:00 - INFO - codeparrot_training - Step 5519: {'lr': 0.0004993028553257952, 'samples': 2826240, 'steps': 5519, 'loss/train': 0.27756497263908386}
-03/03/2022 19:57:04 - INFO - codeparrot_training - Step 5520: {'lr': 0.000499302459236389, 'samples': 2826752, 'steps': 5520, 'loss/train': 2.2509424686431885}
-03/03/2022 19:57:06 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/03/2022 19:57:09 - INFO - codeparrot_training - Step 5521: {'lr': 0.0004993020630346509, 'samples': 2827264, 'steps': 5521, 'loss/train': 2.3559389114379883}
-03/03/2022 19:57:12 - INFO - codeparrot_training - Step 5522: {'lr': 0.0004993016667205812, 'samples': 2827776, 'steps': 5522, 'loss/train': 1.4165676832199097}
-03/03/2022 19:57:14 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/03/2022 19:57:17 - INFO - codeparrot_training - Step 5523: {'lr': 0.0004993012702941799, 'samples': 2828288, 'steps': 5523, 'loss/train': 2.070472240447998}
-03/03/2022 19:57:20 - INFO - codeparrot_training - Step 5524: {'lr': 0.0004993008737554474, 'samples': 2828800, 'steps': 5524, 'loss/train': 2.679405689239502}
-03/03/2022 19:57:23 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/03/2022 19:57:26 - INFO - codeparrot_training - Step 5525: {'lr': 0.0004993004771043837, 'samples': 2829312, 'steps': 5525, 'loss/train': 4.190662860870361}
-03/03/2022 19:57:29 - INFO - codeparrot_training - Step 5526: {'lr': 0.0004993000803409891, 'samples': 2829824, 'steps': 5526, 'loss/train': 2.30087947845459}
-03/03/2022 19:57:31 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/03/2022 19:57:34 - INFO - codeparrot_training - Step 5527: {'lr': 0.0004992996834652638, 'samples': 2830336, 'steps': 5527, 'loss/train': 1.992434024810791}
-03/03/2022 19:57:38 - INFO - codeparrot_training - Step 5528: {'lr': 0.0004992992864772079, 'samples': 2830848, 'steps': 5528, 'loss/train': 2.4812815189361572}
-03/03/2022 19:57:39 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/03/2022 19:57:43 - INFO - codeparrot_training - Step 5529: {'lr': 0.0004992988893768214, 'samples': 2831360, 'steps': 5529, 'loss/train': 2.3919646739959717}
-03/03/2022 19:57:46 - INFO - codeparrot_training - Step 5530: {'lr': 0.0004992984921641048, 'samples': 2831872, 'steps': 5530, 'loss/train': 2.071770668029785}
-03/03/2022 19:57:48 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/03/2022 19:57:52 - INFO - codeparrot_training - Step 5531: {'lr': 0.0004992980948390582, 'samples': 2832384, 'steps': 5531, 'loss/train': 2.7434420585632324}
-03/03/2022 19:57:55 - INFO - codeparrot_training - Step 5532: {'lr': 0.0004992976974016817, 'samples': 2832896, 'steps': 5532, 'loss/train': 2.46907901763916}
-03/03/2022 19:57:57 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 19:58:00 - INFO - codeparrot_training - Step 5533: {'lr': 0.0004992972998519755, 'samples': 2833408, 'steps': 5533, 'loss/train': 2.9336040019989014}
-03/03/2022 19:58:03 - INFO - codeparrot_training - Step 5534: {'lr': 0.0004992969021899397, 'samples': 2833920, 'steps': 5534, 'loss/train': 4.879209041595459}
-03/03/2022 19:58:05 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/03/2022 19:58:08 - INFO - codeparrot_training - Step 5535: {'lr': 0.0004992965044155746, 'samples': 2834432, 'steps': 5535, 'loss/train': 2.8662595748901367}
-03/03/2022 19:58:11 - INFO - codeparrot_training - Step 5536: {'lr': 0.0004992961065288803, 'samples': 2834944, 'steps': 5536, 'loss/train': 2.356239080429077}
-03/03/2022 19:58:13 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/03/2022 19:58:17 - INFO - codeparrot_training - Step 5537: {'lr': 0.0004992957085298571, 'samples': 2835456, 'steps': 5537, 'loss/train': 2.857304811477661}
-03/03/2022 19:58:20 - INFO - codeparrot_training - Step 5538: {'lr': 0.0004992953104185052, 'samples': 2835968, 'steps': 5538, 'loss/train': 0.9075473546981812}
-03/03/2022 19:58:21 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/03/2022 19:58:25 - INFO - codeparrot_training - Step 5539: {'lr': 0.0004992949121948245, 'samples': 2836480, 'steps': 5539, 'loss/train': 2.309558153152466}
-03/03/2022 19:58:28 - INFO - codeparrot_training - Step 5540: {'lr': 0.0004992945138588154, 'samples': 2836992, 'steps': 5540, 'loss/train': 2.7095115184783936}
-03/03/2022 19:58:29 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/03/2022 19:58:34 - INFO - codeparrot_training - Step 5541: {'lr': 0.0004992941154104781, 'samples': 2837504, 'steps': 5541, 'loss/train': 2.2827095985412598}
-03/03/2022 19:58:37 - INFO - codeparrot_training - Step 5542: {'lr': 0.0004992937168498126, 'samples': 2838016, 'steps': 5542, 'loss/train': 2.255387544631958}
-03/03/2022 19:58:38 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/03/2022 19:58:42 - INFO - codeparrot_training - Step 5543: {'lr': 0.0004992933181768194, 'samples': 2838528, 'steps': 5543, 'loss/train': 2.9200925827026367}
-03/03/2022 19:58:45 - INFO - codeparrot_training - Step 5544: {'lr': 0.0004992929193914983, 'samples': 2839040, 'steps': 5544, 'loss/train': 3.0747873783111572}
-03/03/2022 19:58:47 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/03/2022 19:58:51 - INFO - codeparrot_training - Step 5545: {'lr': 0.0004992925204938498, 'samples': 2839552, 'steps': 5545, 'loss/train': 1.7392839193344116}
-03/03/2022 19:58:54 - INFO - codeparrot_training - Step 5546: {'lr': 0.0004992921214838738, 'samples': 2840064, 'steps': 5546, 'loss/train': 2.7661900520324707}
-03/03/2022 19:58:55 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/03/2022 19:58:59 - INFO - codeparrot_training - Step 5547: {'lr': 0.0004992917223615706, 'samples': 2840576, 'steps': 5547, 'loss/train': 2.1570746898651123}
-03/03/2022 19:59:02 - INFO - codeparrot_training - Step 5548: {'lr': 0.0004992913231269405, 'samples': 2841088, 'steps': 5548, 'loss/train': 2.630202054977417}
-03/03/2022 19:59:04 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/03/2022 19:59:07 - INFO - codeparrot_training - Step 5549: {'lr': 0.0004992909237799835, 'samples': 2841600, 'steps': 5549, 'loss/train': 2.9823992252349854}
-03/03/2022 19:59:10 - INFO - codeparrot_training - Step 5550: {'lr': 0.0004992905243206999, 'samples': 2842112, 'steps': 5550, 'loss/train': 1.8402634859085083}
-03/03/2022 19:59:12 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/03/2022 19:59:16 - INFO - codeparrot_training - Step 5551: {'lr': 0.0004992901247490899, 'samples': 2842624, 'steps': 5551, 'loss/train': 1.042776107788086}
-03/03/2022 19:59:19 - INFO - codeparrot_training - Step 5552: {'lr': 0.0004992897250651535, 'samples': 2843136, 'steps': 5552, 'loss/train': 2.9105257987976074}
-03/03/2022 19:59:20 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/03/2022 19:59:24 - INFO - codeparrot_training - Step 5553: {'lr': 0.000499289325268891, 'samples': 2843648, 'steps': 5553, 'loss/train': 2.137089252471924}
-03/03/2022 19:59:27 - INFO - codeparrot_training - Step 5554: {'lr': 0.0004992889253603027, 'samples': 2844160, 'steps': 5554, 'loss/train': 1.655928373336792}
-03/03/2022 19:59:29 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/03/2022 19:59:33 - INFO - codeparrot_training - Step 5555: {'lr': 0.0004992885253393885, 'samples': 2844672, 'steps': 5555, 'loss/train': 2.971435308456421}
-03/03/2022 19:59:36 - INFO - codeparrot_training - Step 5556: {'lr': 0.0004992881252061489, 'samples': 2845184, 'steps': 5556, 'loss/train': 2.221475601196289}
-03/03/2022 19:59:37 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/03/2022 19:59:41 - INFO - codeparrot_training - Step 5557: {'lr': 0.0004992877249605838, 'samples': 2845696, 'steps': 5557, 'loss/train': 1.9447883367538452}
-03/03/2022 19:59:44 - INFO - codeparrot_training - Step 5558: {'lr': 0.0004992873246026935, 'samples': 2846208, 'steps': 5558, 'loss/train': 2.186023712158203}
-03/03/2022 19:59:45 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/03/2022 19:59:49 - INFO - codeparrot_training - Step 5559: {'lr': 0.0004992869241324783, 'samples': 2846720, 'steps': 5559, 'loss/train': 1.811285138130188}
-03/03/2022 19:59:53 - INFO - codeparrot_training - Step 5560: {'lr': 0.000499286523549938, 'samples': 2847232, 'steps': 5560, 'loss/train': 1.7861405611038208}
-03/03/2022 19:59:54 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/03/2022 19:59:58 - INFO - codeparrot_training - Step 5561: {'lr': 0.0004992861228550733, 'samples': 2847744, 'steps': 5561, 'loss/train': 1.433838963508606}
-03/03/2022 20:00:01 - INFO - codeparrot_training - Step 5562: {'lr': 0.0004992857220478841, 'samples': 2848256, 'steps': 5562, 'loss/train': 2.961399793624878}
-03/03/2022 20:00:02 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/03/2022 20:00:06 - INFO - codeparrot_training - Step 5563: {'lr': 0.0004992853211283705, 'samples': 2848768, 'steps': 5563, 'loss/train': 2.3659443855285645}
-03/03/2022 20:00:10 - INFO - codeparrot_training - Step 5564: {'lr': 0.0004992849200965327, 'samples': 2849280, 'steps': 5564, 'loss/train': 2.3556458950042725}
-03/03/2022 20:00:11 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/03/2022 20:00:15 - INFO - codeparrot_training - Step 5565: {'lr': 0.0004992845189523711, 'samples': 2849792, 'steps': 5565, 'loss/train': 1.045914888381958}
-03/03/2022 20:00:18 - INFO - codeparrot_training - Step 5566: {'lr': 0.0004992841176958858, 'samples': 2850304, 'steps': 5566, 'loss/train': 1.8003307580947876}
-03/03/2022 20:00:20 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/03/2022 20:00:23 - INFO - codeparrot_training - Step 5567: {'lr': 0.0004992837163270769, 'samples': 2850816, 'steps': 5567, 'loss/train': 2.848031759262085}
-03/03/2022 20:00:27 - INFO - codeparrot_training - Step 5568: {'lr': 0.0004992833148459445, 'samples': 2851328, 'steps': 5568, 'loss/train': 1.6439998149871826}
-03/03/2022 20:00:28 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/03/2022 20:00:32 - INFO - codeparrot_training - Step 5569: {'lr': 0.0004992829132524889, 'samples': 2851840, 'steps': 5569, 'loss/train': 2.0344183444976807}
-03/03/2022 20:00:35 - INFO - codeparrot_training - Step 5570: {'lr': 0.0004992825115467102, 'samples': 2852352, 'steps': 5570, 'loss/train': 2.250645160675049}
-03/03/2022 20:00:37 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/03/2022 20:00:40 - INFO - codeparrot_training - Step 5571: {'lr': 0.0004992821097286088, 'samples': 2852864, 'steps': 5571, 'loss/train': 1.6863971948623657}
-03/03/2022 20:00:43 - INFO - codeparrot_training - Step 5572: {'lr': 0.0004992817077981846, 'samples': 2853376, 'steps': 5572, 'loss/train': 1.6129095554351807}
-03/03/2022 20:00:45 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/03/2022 20:00:49 - INFO - codeparrot_training - Step 5573: {'lr': 0.000499281305755438, 'samples': 2853888, 'steps': 5573, 'loss/train': 2.290914535522461}
-03/03/2022 20:00:52 - INFO - codeparrot_training - Step 5574: {'lr': 0.0004992809036003691, 'samples': 2854400, 'steps': 5574, 'loss/train': 2.818641185760498}
-03/03/2022 20:00:54 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/03/2022 20:00:57 - INFO - codeparrot_training - Step 5575: {'lr': 0.000499280501332978, 'samples': 2854912, 'steps': 5575, 'loss/train': 2.867481231689453}
-03/03/2022 20:01:00 - INFO - codeparrot_training - Step 5576: {'lr': 0.000499280098953265, 'samples': 2855424, 'steps': 5576, 'loss/train': 2.3137269020080566}
-03/03/2022 20:01:02 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/03/2022 20:01:06 - INFO - codeparrot_training - Step 5577: {'lr': 0.0004992796964612302, 'samples': 2855936, 'steps': 5577, 'loss/train': 2.052978277206421}
-03/03/2022 20:01:09 - INFO - codeparrot_training - Step 5578: {'lr': 0.0004992792938568739, 'samples': 2856448, 'steps': 5578, 'loss/train': 2.6349778175354004}
-03/03/2022 20:01:10 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/03/2022 20:01:14 - INFO - codeparrot_training - Step 5579: {'lr': 0.0004992788911401961, 'samples': 2856960, 'steps': 5579, 'loss/train': 2.1473894119262695}
-03/03/2022 20:01:17 - INFO - codeparrot_training - Step 5580: {'lr': 0.0004992784883111972, 'samples': 2857472, 'steps': 5580, 'loss/train': 2.6922192573547363}
-03/03/2022 20:01:19 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/03/2022 20:01:23 - INFO - codeparrot_training - Step 5581: {'lr': 0.0004992780853698771, 'samples': 2857984, 'steps': 5581, 'loss/train': 1.9614667892456055}
-03/03/2022 20:01:26 - INFO - codeparrot_training - Step 5582: {'lr': 0.0004992776823162362, 'samples': 2858496, 'steps': 5582, 'loss/train': 3.588679075241089}
-03/03/2022 20:01:27 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/03/2022 20:01:31 - INFO - codeparrot_training - Step 5583: {'lr': 0.0004992772791502746, 'samples': 2859008, 'steps': 5583, 'loss/train': 1.1389610767364502}
-03/03/2022 20:01:34 - INFO - codeparrot_training - Step 5584: {'lr': 0.0004992768758719926, 'samples': 2859520, 'steps': 5584, 'loss/train': 0.5867039561271667}
-03/03/2022 20:01:36 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/03/2022 20:01:40 - INFO - codeparrot_training - Step 5585: {'lr': 0.0004992764724813902, 'samples': 2860032, 'steps': 5585, 'loss/train': 2.2633919715881348}
-03/03/2022 20:01:43 - INFO - codeparrot_training - Step 5586: {'lr': 0.0004992760689784677, 'samples': 2860544, 'steps': 5586, 'loss/train': 3.4240405559539795}
-03/03/2022 20:01:46 - INFO - codeparrot_training - Step 5587: {'lr': 0.0004992756653632252, 'samples': 2861056, 'steps': 5587, 'loss/train': 2.871314287185669}
-03/03/2022 20:01:46 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/03/2022 20:01:51 - INFO - codeparrot_training - Step 5588: {'lr': 0.0004992752616356631, 'samples': 2861568, 'steps': 5588, 'loss/train': 2.1604952812194824}
-03/03/2022 20:01:54 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/03/2022 20:01:57 - INFO - codeparrot_training - Step 5589: {'lr': 0.0004992748577957812, 'samples': 2862080, 'steps': 5589, 'loss/train': 2.481191635131836}
-03/03/2022 20:02:00 - INFO - codeparrot_training - Step 5590: {'lr': 0.00049927445384358, 'samples': 2862592, 'steps': 5590, 'loss/train': 1.7941190004348755}
-03/03/2022 20:02:03 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/03/2022 20:02:05 - INFO - codeparrot_training - Step 5591: {'lr': 0.0004992740497790595, 'samples': 2863104, 'steps': 5591, 'loss/train': 3.185790777206421}
-03/03/2022 20:02:08 - INFO - codeparrot_training - Step 5592: {'lr': 0.0004992736456022201, 'samples': 2863616, 'steps': 5592, 'loss/train': 2.6233701705932617}
-03/03/2022 20:02:11 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/03/2022 20:02:14 - INFO - codeparrot_training - Step 5593: {'lr': 0.0004992732413130617, 'samples': 2864128, 'steps': 5593, 'loss/train': 2.355231523513794}
-03/03/2022 20:02:17 - INFO - codeparrot_training - Step 5594: {'lr': 0.0004992728369115848, 'samples': 2864640, 'steps': 5594, 'loss/train': 2.430454730987549}
-03/03/2022 20:02:19 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/03/2022 20:02:22 - INFO - codeparrot_training - Step 5595: {'lr': 0.0004992724323977893, 'samples': 2865152, 'steps': 5595, 'loss/train': 3.6668453216552734}
-03/03/2022 20:02:25 - INFO - codeparrot_training - Step 5596: {'lr': 0.0004992720277716755, 'samples': 2865664, 'steps': 5596, 'loss/train': 1.8903814554214478}
-03/03/2022 20:02:28 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/03/2022 20:02:31 - INFO - codeparrot_training - Step 5597: {'lr': 0.0004992716230332435, 'samples': 2866176, 'steps': 5597, 'loss/train': 2.4556100368499756}
-03/03/2022 20:02:34 - INFO - codeparrot_training - Step 5598: {'lr': 0.0004992712181824936, 'samples': 2866688, 'steps': 5598, 'loss/train': 7.173145294189453}
-03/03/2022 20:02:37 - INFO - codeparrot_training - Step 5599: {'lr': 0.0004992708132194259, 'samples': 2867200, 'steps': 5599, 'loss/train': 2.529099941253662}
-03/03/2022 20:02:37 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/03/2022 20:02:42 - INFO - codeparrot_training - Step 5600: {'lr': 0.0004992704081440407, 'samples': 2867712, 'steps': 5600, 'loss/train': 3.1005959510803223}
-03/03/2022 20:02:45 - INFO - codeparrot_training - Step 5601: {'lr': 0.0004992700029563381, 'samples': 2868224, 'steps': 5601, 'loss/train': 2.6172378063201904}
-03/03/2022 20:02:46 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/03/2022 20:02:51 - INFO - codeparrot_training - Step 5602: {'lr': 0.0004992695976563182, 'samples': 2868736, 'steps': 5602, 'loss/train': 3.174105167388916}
-03/03/2022 20:02:54 - INFO - codeparrot_training - Step 5603: {'lr': 0.0004992691922439814, 'samples': 2869248, 'steps': 5603, 'loss/train': 2.334345579147339}
-03/03/2022 20:02:54 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/03/2022 20:02:59 - INFO - codeparrot_training - Step 5604: {'lr': 0.0004992687867193277, 'samples': 2869760, 'steps': 5604, 'loss/train': 2.0459935665130615}
-03/03/2022 20:03:02 - INFO - codeparrot_training - Step 5605: {'lr': 0.0004992683810823572, 'samples': 2870272, 'steps': 5605, 'loss/train': 2.3363492488861084}
-03/03/2022 20:03:03 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/03/2022 20:03:08 - INFO - codeparrot_training - Step 5606: {'lr': 0.0004992679753330703, 'samples': 2870784, 'steps': 5606, 'loss/train': 2.8916099071502686}
-03/03/2022 20:03:11 - INFO - codeparrot_training - Step 5607: {'lr': 0.0004992675694714671, 'samples': 2871296, 'steps': 5607, 'loss/train': 0.9907640814781189}
-03/03/2022 20:03:11 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/03/2022 20:03:16 - INFO - codeparrot_training - Step 5608: {'lr': 0.0004992671634975477, 'samples': 2871808, 'steps': 5608, 'loss/train': 2.1052982807159424}
-03/03/2022 20:03:19 - INFO - codeparrot_training - Step 5609: {'lr': 0.0004992667574113125, 'samples': 2872320, 'steps': 5609, 'loss/train': 2.8142309188842773}
-03/03/2022 20:03:19 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/03/2022 20:03:24 - INFO - codeparrot_training - Step 5610: {'lr': 0.0004992663512127615, 'samples': 2872832, 'steps': 5610, 'loss/train': 2.8171682357788086}
-03/03/2022 20:03:28 - INFO - codeparrot_training - Step 5611: {'lr': 0.0004992659449018949, 'samples': 2873344, 'steps': 5611, 'loss/train': 2.7851486206054688}
-03/03/2022 20:03:28 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/03/2022 20:03:33 - INFO - codeparrot_training - Step 5612: {'lr': 0.0004992655384787129, 'samples': 2873856, 'steps': 5612, 'loss/train': 1.1926709413528442}
-03/03/2022 20:03:36 - INFO - codeparrot_training - Step 5613: {'lr': 0.0004992651319432157, 'samples': 2874368, 'steps': 5613, 'loss/train': 1.9587130546569824}
-03/03/2022 20:03:36 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/03/2022 20:03:41 - INFO - codeparrot_training - Step 5614: {'lr': 0.0004992647252954035, 'samples': 2874880, 'steps': 5614, 'loss/train': 2.437626600265503}
-03/03/2022 20:03:44 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/03/2022 20:03:47 - INFO - codeparrot_training - Step 5615: {'lr': 0.0004992643185352765, 'samples': 2875392, 'steps': 5615, 'loss/train': 2.86002254486084}
-03/03/2022 20:03:50 - INFO - codeparrot_training - Step 5616: {'lr': 0.0004992639116628349, 'samples': 2875904, 'steps': 5616, 'loss/train': 2.0767064094543457}
-03/03/2022 20:03:53 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/03/2022 20:03:55 - INFO - codeparrot_training - Step 5617: {'lr': 0.0004992635046780786, 'samples': 2876416, 'steps': 5617, 'loss/train': 1.9573410749435425}
-03/03/2022 20:03:58 - INFO - codeparrot_training - Step 5618: {'lr': 0.0004992630975810083, 'samples': 2876928, 'steps': 5618, 'loss/train': 2.53548526763916}
-03/03/2022 20:04:01 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/03/2022 20:04:04 - INFO - codeparrot_training - Step 5619: {'lr': 0.0004992626903716237, 'samples': 2877440, 'steps': 5619, 'loss/train': 2.92912220954895}
-03/03/2022 20:04:07 - INFO - codeparrot_training - Step 5620: {'lr': 0.0004992622830499252, 'samples': 2877952, 'steps': 5620, 'loss/train': 0.5348357558250427}
-03/03/2022 20:04:10 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/03/2022 20:04:12 - INFO - codeparrot_training - Step 5621: {'lr': 0.000499261875615913, 'samples': 2878464, 'steps': 5621, 'loss/train': 2.0007851123809814}
-03/03/2022 20:04:15 - INFO - codeparrot_training - Step 5622: {'lr': 0.0004992614680695872, 'samples': 2878976, 'steps': 5622, 'loss/train': 3.0650634765625}
-03/03/2022 20:04:18 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/03/2022 20:04:21 - INFO - codeparrot_training - Step 5623: {'lr': 0.0004992610604109481, 'samples': 2879488, 'steps': 5623, 'loss/train': 2.6133792400360107}
-03/03/2022 20:04:24 - INFO - codeparrot_training - Step 5624: {'lr': 0.0004992606526399957, 'samples': 2880000, 'steps': 5624, 'loss/train': 2.2933554649353027}
-03/03/2022 20:04:27 - INFO - codeparrot_training - Step 5625: {'lr': 0.0004992602447567304, 'samples': 2880512, 'steps': 5625, 'loss/train': 2.7632405757904053}
-03/03/2022 20:04:27 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/03/2022 20:04:32 - INFO - codeparrot_training - Step 5626: {'lr': 0.0004992598367611523, 'samples': 2881024, 'steps': 5626, 'loss/train': 2.1835503578186035}
-03/03/2022 20:04:36 - INFO - codeparrot_training - Step 5627: {'lr': 0.0004992594286532615, 'samples': 2881536, 'steps': 5627, 'loss/train': 2.9436309337615967}
-03/03/2022 20:04:36 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/03/2022 20:04:41 - INFO - codeparrot_training - Step 5628: {'lr': 0.0004992590204330583, 'samples': 2882048, 'steps': 5628, 'loss/train': 2.462250232696533}
-03/03/2022 20:04:44 - INFO - codeparrot_training - Step 5629: {'lr': 0.0004992586121005427, 'samples': 2882560, 'steps': 5629, 'loss/train': 2.4165806770324707}
-03/03/2022 20:04:44 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/03/2022 20:04:49 - INFO - codeparrot_training - Step 5630: {'lr': 0.0004992582036557152, 'samples': 2883072, 'steps': 5630, 'loss/train': 3.0161855220794678}
-03/03/2022 20:04:52 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/03/2022 20:04:55 - INFO - codeparrot_training - Step 5631: {'lr': 0.0004992577950985757, 'samples': 2883584, 'steps': 5631, 'loss/train': 2.351439952850342}
-03/03/2022 20:04:58 - INFO - codeparrot_training - Step 5632: {'lr': 0.0004992573864291244, 'samples': 2884096, 'steps': 5632, 'loss/train': 2.421457052230835}
-03/03/2022 20:05:01 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/03/2022 20:05:03 - INFO - codeparrot_training - Step 5633: {'lr': 0.0004992569776473616, 'samples': 2884608, 'steps': 5633, 'loss/train': 2.242201089859009}
-03/03/2022 20:05:06 - INFO - codeparrot_training - Step 5634: {'lr': 0.0004992565687532875, 'samples': 2885120, 'steps': 5634, 'loss/train': 1.4035123586654663}
-03/03/2022 20:05:09 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/03/2022 20:05:12 - INFO - codeparrot_training - Step 5635: {'lr': 0.0004992561597469023, 'samples': 2885632, 'steps': 5635, 'loss/train': 2.1347765922546387}
-03/03/2022 20:05:15 - INFO - codeparrot_training - Step 5636: {'lr': 0.0004992557506282061, 'samples': 2886144, 'steps': 5636, 'loss/train': 1.236997127532959}
-03/03/2022 20:05:17 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/03/2022 20:05:20 - INFO - codeparrot_training - Step 5637: {'lr': 0.0004992553413971991, 'samples': 2886656, 'steps': 5637, 'loss/train': 1.825696349143982}
-03/03/2022 20:05:23 - INFO - codeparrot_training - Step 5638: {'lr': 0.0004992549320538814, 'samples': 2887168, 'steps': 5638, 'loss/train': 2.462958335876465}
-03/03/2022 20:05:26 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/03/2022 20:05:28 - INFO - codeparrot_training - Step 5639: {'lr': 0.0004992545225982533, 'samples': 2887680, 'steps': 5639, 'loss/train': 2.0675575733184814}
-03/03/2022 20:05:32 - INFO - codeparrot_training - Step 5640: {'lr': 0.000499254113030315, 'samples': 2888192, 'steps': 5640, 'loss/train': 2.6591603755950928}
-03/03/2022 20:05:35 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/03/2022 20:05:37 - INFO - codeparrot_training - Step 5641: {'lr': 0.0004992537033500667, 'samples': 2888704, 'steps': 5641, 'loss/train': 2.4082233905792236}
-03/03/2022 20:05:40 - INFO - codeparrot_training - Step 5642: {'lr': 0.0004992532935575084, 'samples': 2889216, 'steps': 5642, 'loss/train': 2.2549397945404053}
-03/03/2022 20:05:43 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/03/2022 20:05:45 - INFO - codeparrot_training - Step 5643: {'lr': 0.0004992528836526405, 'samples': 2889728, 'steps': 5643, 'loss/train': 1.5324019193649292}
-03/03/2022 20:05:48 - INFO - codeparrot_training - Step 5644: {'lr': 0.0004992524736354631, 'samples': 2890240, 'steps': 5644, 'loss/train': 3.0483133792877197}
-03/03/2022 20:05:51 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/03/2022 20:05:54 - INFO - codeparrot_training - Step 5645: {'lr': 0.0004992520635059762, 'samples': 2890752, 'steps': 5645, 'loss/train': 1.5884685516357422}
-03/03/2022 20:05:57 - INFO - codeparrot_training - Step 5646: {'lr': 0.0004992516532641804, 'samples': 2891264, 'steps': 5646, 'loss/train': 2.3586485385894775}
-03/03/2022 20:05:59 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/03/2022 20:06:02 - INFO - codeparrot_training - Step 5647: {'lr': 0.0004992512429100757, 'samples': 2891776, 'steps': 5647, 'loss/train': 2.6773769855499268}
-03/03/2022 20:06:05 - INFO - codeparrot_training - Step 5648: {'lr': 0.000499250832443662, 'samples': 2892288, 'steps': 5648, 'loss/train': 2.468430519104004}
-03/03/2022 20:06:08 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/03/2022 20:06:11 - INFO - codeparrot_training - Step 5649: {'lr': 0.0004992504218649398, 'samples': 2892800, 'steps': 5649, 'loss/train': 2.2052032947540283}
-03/03/2022 20:06:14 - INFO - codeparrot_training - Step 5650: {'lr': 0.0004992500111739093, 'samples': 2893312, 'steps': 5650, 'loss/train': 0.8484160304069519}
-03/03/2022 20:06:17 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/03/2022 20:06:19 - INFO - codeparrot_training - Step 5651: {'lr': 0.0004992496003705705, 'samples': 2893824, 'steps': 5651, 'loss/train': 2.444758653640747}
-03/03/2022 20:06:22 - INFO - codeparrot_training - Step 5652: {'lr': 0.0004992491894549236, 'samples': 2894336, 'steps': 5652, 'loss/train': 1.8507602214813232}
-03/03/2022 20:06:25 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/03/2022 20:06:27 - INFO - codeparrot_training - Step 5653: {'lr': 0.000499248778426969, 'samples': 2894848, 'steps': 5653, 'loss/train': 2.121119260787964}
-03/03/2022 20:06:31 - INFO - codeparrot_training - Step 5654: {'lr': 0.0004992483672867068, 'samples': 2895360, 'steps': 5654, 'loss/train': 1.9111272096633911}
-03/03/2022 20:06:33 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/03/2022 20:06:36 - INFO - codeparrot_training - Step 5655: {'lr': 0.000499247956034137, 'samples': 2895872, 'steps': 5655, 'loss/train': 2.7765393257141113}
-03/03/2022 20:06:39 - INFO - codeparrot_training - Step 5656: {'lr': 0.00049924754466926, 'samples': 2896384, 'steps': 5656, 'loss/train': 2.7348365783691406}
-03/03/2022 20:06:41 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 20:06:44 - INFO - codeparrot_training - Step 5657: {'lr': 0.0004992471331920758, 'samples': 2896896, 'steps': 5657, 'loss/train': 2.317481756210327}
-03/03/2022 20:06:48 - INFO - codeparrot_training - Step 5658: {'lr': 0.0004992467216025848, 'samples': 2897408, 'steps': 5658, 'loss/train': 1.1522691249847412}
-03/03/2022 20:06:50 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/03/2022 20:06:53 - INFO - codeparrot_training - Step 5659: {'lr': 0.0004992463099007871, 'samples': 2897920, 'steps': 5659, 'loss/train': 2.3600940704345703}
-03/03/2022 20:06:56 - INFO - codeparrot_training - Step 5660: {'lr': 0.0004992458980866827, 'samples': 2898432, 'steps': 5660, 'loss/train': 2.074622869491577}
-03/03/2022 20:06:58 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/03/2022 20:07:01 - INFO - codeparrot_training - Step 5661: {'lr': 0.000499245486160272, 'samples': 2898944, 'steps': 5661, 'loss/train': 2.0390093326568604}
-03/03/2022 20:07:04 - INFO - codeparrot_training - Step 5662: {'lr': 0.0004992450741215552, 'samples': 2899456, 'steps': 5662, 'loss/train': 2.0128273963928223}
-03/03/2022 20:07:07 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/03/2022 20:07:10 - INFO - codeparrot_training - Step 5663: {'lr': 0.0004992446619705324, 'samples': 2899968, 'steps': 5663, 'loss/train': 1.6087396144866943}
-03/03/2022 20:07:13 - INFO - codeparrot_training - Step 5664: {'lr': 0.0004992442497072037, 'samples': 2900480, 'steps': 5664, 'loss/train': 2.6386642456054688}
-03/03/2022 20:07:15 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/03/2022 20:07:18 - INFO - codeparrot_training - Step 5665: {'lr': 0.0004992438373315694, 'samples': 2900992, 'steps': 5665, 'loss/train': 1.6578105688095093}
-03/03/2022 20:07:21 - INFO - codeparrot_training - Step 5666: {'lr': 0.0004992434248436298, 'samples': 2901504, 'steps': 5666, 'loss/train': 2.7225534915924072}
-03/03/2022 20:07:23 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/03/2022 20:07:27 - INFO - codeparrot_training - Step 5667: {'lr': 0.0004992430122433848, 'samples': 2902016, 'steps': 5667, 'loss/train': 1.327860951423645}
-03/03/2022 20:07:30 - INFO - codeparrot_training - Step 5668: {'lr': 0.0004992425995308349, 'samples': 2902528, 'steps': 5668, 'loss/train': 2.063884735107422}
-03/03/2022 20:07:32 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/03/2022 20:07:35 - INFO - codeparrot_training - Step 5669: {'lr': 0.0004992421867059801, 'samples': 2903040, 'steps': 5669, 'loss/train': 2.427093744277954}
-03/03/2022 20:07:38 - INFO - codeparrot_training - Step 5670: {'lr': 0.0004992417737688206, 'samples': 2903552, 'steps': 5670, 'loss/train': 2.9169578552246094}
-03/03/2022 20:07:40 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/03/2022 20:07:43 - INFO - codeparrot_training - Step 5671: {'lr': 0.0004992413607193566, 'samples': 2904064, 'steps': 5671, 'loss/train': 2.2099223136901855}
-03/03/2022 20:07:47 - INFO - codeparrot_training - Step 5672: {'lr': 0.0004992409475575882, 'samples': 2904576, 'steps': 5672, 'loss/train': 3.1845593452453613}
-03/03/2022 20:07:48 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/03/2022 20:07:52 - INFO - codeparrot_training - Step 5673: {'lr': 0.0004992405342835158, 'samples': 2905088, 'steps': 5673, 'loss/train': 1.7366174459457397}
-03/03/2022 20:07:55 - INFO - codeparrot_training - Step 5674: {'lr': 0.0004992401208971394, 'samples': 2905600, 'steps': 5674, 'loss/train': 2.138404369354248}
-03/03/2022 20:07:57 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/03/2022 20:08:00 - INFO - codeparrot_training - Step 5675: {'lr': 0.0004992397073984592, 'samples': 2906112, 'steps': 5675, 'loss/train': 0.42639994621276855}
-03/03/2022 20:08:03 - INFO - codeparrot_training - Step 5676: {'lr': 0.0004992392937874755, 'samples': 2906624, 'steps': 5676, 'loss/train': 2.3922808170318604}
-03/03/2022 20:08:09 - INFO - codeparrot_training - Step 5677: {'lr': 0.0004992388800641885, 'samples': 2907136, 'steps': 5677, 'loss/train': 2.536113977432251}
-03/03/2022 20:08:12 - INFO - codeparrot_training - Step 5678: {'lr': 0.0004992384662285981, 'samples': 2907648, 'steps': 5678, 'loss/train': 1.8391480445861816}
-03/03/2022 20:08:14 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/03/2022 20:08:17 - INFO - codeparrot_training - Step 5679: {'lr': 0.0004992380522807049, 'samples': 2908160, 'steps': 5679, 'loss/train': 1.652300238609314}
-03/03/2022 20:08:21 - INFO - codeparrot_training - Step 5680: {'lr': 0.0004992376382205088, 'samples': 2908672, 'steps': 5680, 'loss/train': 0.9023103713989258}
-03/03/2022 20:08:23 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/03/2022 20:08:26 - INFO - codeparrot_training - Step 5681: {'lr': 0.00049923722404801, 'samples': 2909184, 'steps': 5681, 'loss/train': 2.9388997554779053}
-03/03/2022 20:08:29 - INFO - codeparrot_training - Step 5682: {'lr': 0.0004992368097632089, 'samples': 2909696, 'steps': 5682, 'loss/train': 2.197835683822632}
-03/03/2022 20:08:32 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/03/2022 20:08:34 - INFO - codeparrot_training - Step 5683: {'lr': 0.0004992363953661054, 'samples': 2910208, 'steps': 5683, 'loss/train': 1.699796199798584}
-03/03/2022 20:08:38 - INFO - codeparrot_training - Step 5684: {'lr': 0.0004992359808566999, 'samples': 2910720, 'steps': 5684, 'loss/train': 2.7553751468658447}
-03/03/2022 20:08:40 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/03/2022 20:08:43 - INFO - codeparrot_training - Step 5685: {'lr': 0.0004992355662349925, 'samples': 2911232, 'steps': 5685, 'loss/train': 1.9863051176071167}
-03/03/2022 20:08:46 - INFO - codeparrot_training - Step 5686: {'lr': 0.0004992351515009833, 'samples': 2911744, 'steps': 5686, 'loss/train': 1.2422163486480713}
-03/03/2022 20:08:48 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/03/2022 20:08:51 - INFO - codeparrot_training - Step 5687: {'lr': 0.0004992347366546727, 'samples': 2912256, 'steps': 5687, 'loss/train': 2.236273765563965}
-03/03/2022 20:08:54 - INFO - codeparrot_training - Step 5688: {'lr': 0.0004992343216960607, 'samples': 2912768, 'steps': 5688, 'loss/train': 1.884190320968628}
-03/03/2022 20:08:57 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/03/2022 20:09:00 - INFO - codeparrot_training - Step 5689: {'lr': 0.0004992339066251476, 'samples': 2913280, 'steps': 5689, 'loss/train': 2.690807580947876}
-03/03/2022 20:09:03 - INFO - codeparrot_training - Step 5690: {'lr': 0.0004992334914419337, 'samples': 2913792, 'steps': 5690, 'loss/train': 2.487916946411133}
-03/03/2022 20:09:05 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/03/2022 20:09:08 - INFO - codeparrot_training - Step 5691: {'lr': 0.0004992330761464188, 'samples': 2914304, 'steps': 5691, 'loss/train': 2.298241376876831}
-03/03/2022 20:09:11 - INFO - codeparrot_training - Step 5692: {'lr': 0.0004992326607386034, 'samples': 2914816, 'steps': 5692, 'loss/train': 3.15874981880188}
-03/03/2022 20:09:13 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/03/2022 20:09:17 - INFO - codeparrot_training - Step 5693: {'lr': 0.0004992322452184876, 'samples': 2915328, 'steps': 5693, 'loss/train': 3.073209285736084}
-03/03/2022 20:09:20 - INFO - codeparrot_training - Step 5694: {'lr': 0.0004992318295860718, 'samples': 2915840, 'steps': 5694, 'loss/train': 2.575552225112915}
-03/03/2022 20:09:22 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/03/2022 20:09:25 - INFO - codeparrot_training - Step 5695: {'lr': 0.0004992314138413557, 'samples': 2916352, 'steps': 5695, 'loss/train': 2.9204483032226562}
-03/03/2022 20:09:28 - INFO - codeparrot_training - Step 5696: {'lr': 0.0004992309979843398, 'samples': 2916864, 'steps': 5696, 'loss/train': 2.850261688232422}
-03/03/2022 20:09:30 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/03/2022 20:09:33 - INFO - codeparrot_training - Step 5697: {'lr': 0.0004992305820150243, 'samples': 2917376, 'steps': 5697, 'loss/train': 2.585024833679199}
-03/03/2022 20:09:37 - INFO - codeparrot_training - Step 5698: {'lr': 0.0004992301659334095, 'samples': 2917888, 'steps': 5698, 'loss/train': 2.018657684326172}
-03/03/2022 20:09:39 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/03/2022 20:09:42 - INFO - codeparrot_training - Step 5699: {'lr': 0.0004992297497394953, 'samples': 2918400, 'steps': 5699, 'loss/train': 2.6443819999694824}
-03/03/2022 20:09:45 - INFO - codeparrot_training - Step 5700: {'lr': 0.000499229333433282, 'samples': 2918912, 'steps': 5700, 'loss/train': 1.3883994817733765}
-03/03/2022 20:09:47 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/03/2022 20:09:50 - INFO - codeparrot_training - Step 5701: {'lr': 0.0004992289170147699, 'samples': 2919424, 'steps': 5701, 'loss/train': 2.934410333633423}
-03/03/2022 20:09:54 - INFO - codeparrot_training - Step 5702: {'lr': 0.000499228500483959, 'samples': 2919936, 'steps': 5702, 'loss/train': 2.2119483947753906}
-03/03/2022 20:09:56 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/03/2022 20:09:59 - INFO - codeparrot_training - Step 5703: {'lr': 0.0004992280838408496, 'samples': 2920448, 'steps': 5703, 'loss/train': 1.6338988542556763}
-03/03/2022 20:10:02 - INFO - codeparrot_training - Step 5704: {'lr': 0.0004992276670854419, 'samples': 2920960, 'steps': 5704, 'loss/train': 2.8224339485168457}
-03/03/2022 20:10:05 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/03/2022 20:10:07 - INFO - codeparrot_training - Step 5705: {'lr': 0.000499227250217736, 'samples': 2921472, 'steps': 5705, 'loss/train': 1.0985503196716309}
-03/03/2022 20:10:11 - INFO - codeparrot_training - Step 5706: {'lr': 0.0004992268332377323, 'samples': 2921984, 'steps': 5706, 'loss/train': 2.0969533920288086}
-03/03/2022 20:10:13 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/03/2022 20:10:16 - INFO - codeparrot_training - Step 5707: {'lr': 0.0004992264161454306, 'samples': 2922496, 'steps': 5707, 'loss/train': 3.0460386276245117}
-03/03/2022 20:10:19 - INFO - codeparrot_training - Step 5708: {'lr': 0.0004992259989408316, 'samples': 2923008, 'steps': 5708, 'loss/train': 2.655797004699707}
-03/03/2022 20:10:21 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/03/2022 20:10:24 - INFO - codeparrot_training - Step 5709: {'lr': 0.000499225581623935, 'samples': 2923520, 'steps': 5709, 'loss/train': 1.974186658859253}
-03/03/2022 20:10:27 - INFO - codeparrot_training - Step 5710: {'lr': 0.0004992251641947412, 'samples': 2924032, 'steps': 5710, 'loss/train': 2.9552478790283203}
-03/03/2022 20:10:30 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/03/2022 20:10:33 - INFO - codeparrot_training - Step 5711: {'lr': 0.0004992247466532504, 'samples': 2924544, 'steps': 5711, 'loss/train': 2.9786429405212402}
-03/03/2022 20:10:36 - INFO - codeparrot_training - Step 5712: {'lr': 0.0004992243289994629, 'samples': 2925056, 'steps': 5712, 'loss/train': 1.8652312755584717}
-03/03/2022 20:10:38 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/03/2022 20:10:41 - INFO - codeparrot_training - Step 5713: {'lr': 0.0004992239112333787, 'samples': 2925568, 'steps': 5713, 'loss/train': 2.7099170684814453}
-03/03/2022 20:10:44 - INFO - codeparrot_training - Step 5714: {'lr': 0.000499223493354998, 'samples': 2926080, 'steps': 5714, 'loss/train': 2.152007579803467}
-03/03/2022 20:10:46 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/03/2022 20:10:49 - INFO - codeparrot_training - Step 5715: {'lr': 0.0004992230753643211, 'samples': 2926592, 'steps': 5715, 'loss/train': 1.1377310752868652}
-03/03/2022 20:10:52 - INFO - codeparrot_training - Step 5716: {'lr': 0.0004992226572613481, 'samples': 2927104, 'steps': 5716, 'loss/train': 1.4547109603881836}
-03/03/2022 20:10:54 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/03/2022 20:10:58 - INFO - codeparrot_training - Step 5717: {'lr': 0.0004992222390460792, 'samples': 2927616, 'steps': 5717, 'loss/train': 1.9422509670257568}
-03/03/2022 20:11:01 - INFO - codeparrot_training - Step 5718: {'lr': 0.0004992218207185146, 'samples': 2928128, 'steps': 5718, 'loss/train': 2.0686657428741455}
-03/03/2022 20:11:03 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/03/2022 20:11:06 - INFO - codeparrot_training - Step 5719: {'lr': 0.0004992214022786546, 'samples': 2928640, 'steps': 5719, 'loss/train': 3.3030896186828613}
-03/03/2022 20:11:09 - INFO - codeparrot_training - Step 5720: {'lr': 0.0004992209837264991, 'samples': 2929152, 'steps': 5720, 'loss/train': 2.673290967941284}
-03/03/2022 20:11:11 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/03/2022 20:11:15 - INFO - codeparrot_training - Step 5721: {'lr': 0.0004992205650620487, 'samples': 2929664, 'steps': 5721, 'loss/train': 2.603482484817505}
-03/03/2022 20:11:18 - INFO - codeparrot_training - Step 5722: {'lr': 0.0004992201462853032, 'samples': 2930176, 'steps': 5722, 'loss/train': 2.4817676544189453}
-03/03/2022 20:11:20 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/03/2022 20:11:23 - INFO - codeparrot_training - Step 5723: {'lr': 0.000499219727396263, 'samples': 2930688, 'steps': 5723, 'loss/train': 1.286218523979187}
-03/03/2022 20:11:26 - INFO - codeparrot_training - Step 5724: {'lr': 0.0004992193083949282, 'samples': 2931200, 'steps': 5724, 'loss/train': 2.439889669418335}
-03/03/2022 20:11:28 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/03/2022 20:11:32 - INFO - codeparrot_training - Step 5725: {'lr': 0.000499218889281299, 'samples': 2931712, 'steps': 5725, 'loss/train': 2.041982412338257}
-03/03/2022 20:11:35 - INFO - codeparrot_training - Step 5726: {'lr': 0.0004992184700553756, 'samples': 2932224, 'steps': 5726, 'loss/train': 2.642778158187866}
-03/03/2022 20:11:36 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/03/2022 20:11:40 - INFO - codeparrot_training - Step 5727: {'lr': 0.0004992180507171583, 'samples': 2932736, 'steps': 5727, 'loss/train': 2.460667610168457}
-03/03/2022 20:11:43 - INFO - codeparrot_training - Step 5728: {'lr': 0.0004992176312666472, 'samples': 2933248, 'steps': 5728, 'loss/train': 2.105905294418335}
-03/03/2022 20:11:45 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/03/2022 20:11:48 - INFO - codeparrot_training - Step 5729: {'lr': 0.0004992172117038424, 'samples': 2933760, 'steps': 5729, 'loss/train': 1.8113102912902832}
-03/03/2022 20:11:52 - INFO - codeparrot_training - Step 5730: {'lr': 0.0004992167920287443, 'samples': 2934272, 'steps': 5730, 'loss/train': 1.3979978561401367}
-03/03/2022 20:11:53 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/03/2022 20:11:57 - INFO - codeparrot_training - Step 5731: {'lr': 0.0004992163722413528, 'samples': 2934784, 'steps': 5731, 'loss/train': 2.1343207359313965}
-03/03/2022 20:12:00 - INFO - codeparrot_training - Step 5732: {'lr': 0.0004992159523416683, 'samples': 2935296, 'steps': 5732, 'loss/train': 2.6359500885009766}
-03/03/2022 20:12:03 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/03/2022 20:12:06 - INFO - codeparrot_training - Step 5733: {'lr': 0.000499215532329691, 'samples': 2935808, 'steps': 5733, 'loss/train': 1.6450474262237549}
-03/03/2022 20:12:09 - INFO - codeparrot_training - Step 5734: {'lr': 0.000499215112205421, 'samples': 2936320, 'steps': 5734, 'loss/train': 3.1189236640930176}
-03/03/2022 20:12:11 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/03/2022 20:12:14 - INFO - codeparrot_training - Step 5735: {'lr': 0.0004992146919688584, 'samples': 2936832, 'steps': 5735, 'loss/train': 2.2444891929626465}
-03/03/2022 20:12:17 - INFO - codeparrot_training - Step 5736: {'lr': 0.0004992142716200036, 'samples': 2937344, 'steps': 5736, 'loss/train': 2.573068618774414}
-03/03/2022 20:12:19 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/03/2022 20:12:22 - INFO - codeparrot_training - Step 5737: {'lr': 0.0004992138511588567, 'samples': 2937856, 'steps': 5737, 'loss/train': 2.3672077655792236}
-03/03/2022 20:12:26 - INFO - codeparrot_training - Step 5738: {'lr': 0.0004992134305854179, 'samples': 2938368, 'steps': 5738, 'loss/train': 2.217325210571289}
-03/03/2022 20:12:28 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/03/2022 20:12:31 - INFO - codeparrot_training - Step 5739: {'lr': 0.0004992130098996873, 'samples': 2938880, 'steps': 5739, 'loss/train': 2.772453546524048}
-03/03/2022 20:12:34 - INFO - codeparrot_training - Step 5740: {'lr': 0.0004992125891016652, 'samples': 2939392, 'steps': 5740, 'loss/train': 1.2921020984649658}
-03/03/2022 20:12:37 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/03/2022 20:12:39 - INFO - codeparrot_training - Step 5741: {'lr': 0.0004992121681913518, 'samples': 2939904, 'steps': 5741, 'loss/train': 2.1990532875061035}
-03/03/2022 20:12:42 - INFO - codeparrot_training - Step 5742: {'lr': 0.0004992117471687472, 'samples': 2940416, 'steps': 5742, 'loss/train': 3.019498586654663}
-03/03/2022 20:12:45 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/03/2022 20:12:48 - INFO - codeparrot_training - Step 5743: {'lr': 0.0004992113260338517, 'samples': 2940928, 'steps': 5743, 'loss/train': 2.5764527320861816}
-03/03/2022 20:12:51 - INFO - codeparrot_training - Step 5744: {'lr': 0.0004992109047866653, 'samples': 2941440, 'steps': 5744, 'loss/train': 2.4547290802001953}
-03/03/2022 20:12:53 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 20:12:56 - INFO - codeparrot_training - Step 5745: {'lr': 0.0004992104834271884, 'samples': 2941952, 'steps': 5745, 'loss/train': 2.8805325031280518}
-03/03/2022 20:12:59 - INFO - codeparrot_training - Step 5746: {'lr': 0.0004992100619554211, 'samples': 2942464, 'steps': 5746, 'loss/train': 1.5804237127304077}
-03/03/2022 20:13:02 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/03/2022 20:13:05 - INFO - codeparrot_training - Step 5747: {'lr': 0.0004992096403713635, 'samples': 2942976, 'steps': 5747, 'loss/train': 1.5942389965057373}
-03/03/2022 20:13:08 - INFO - codeparrot_training - Step 5748: {'lr': 0.000499209218675016, 'samples': 2943488, 'steps': 5748, 'loss/train': 1.8277983665466309}
-03/03/2022 20:13:10 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/03/2022 20:13:13 - INFO - codeparrot_training - Step 5749: {'lr': 0.0004992087968663786, 'samples': 2944000, 'steps': 5749, 'loss/train': 3.275791645050049}
-03/03/2022 20:13:16 - INFO - codeparrot_training - Step 5750: {'lr': 0.0004992083749454515, 'samples': 2944512, 'steps': 5750, 'loss/train': 1.5790818929672241}
-03/03/2022 20:13:18 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 20:13:21 - INFO - codeparrot_training - Step 5751: {'lr': 0.0004992079529122351, 'samples': 2945024, 'steps': 5751, 'loss/train': 2.4959263801574707}
-03/03/2022 20:13:24 - INFO - codeparrot_training - Step 5752: {'lr': 0.0004992075307667294, 'samples': 2945536, 'steps': 5752, 'loss/train': 1.5803793668746948}
-03/03/2022 20:13:27 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/03/2022 20:13:30 - INFO - codeparrot_training - Step 5753: {'lr': 0.0004992071085089346, 'samples': 2946048, 'steps': 5753, 'loss/train': 2.5526013374328613}
-03/03/2022 20:13:33 - INFO - codeparrot_training - Step 5754: {'lr': 0.0004992066861388509, 'samples': 2946560, 'steps': 5754, 'loss/train': 2.5843729972839355}
-03/03/2022 20:13:35 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/03/2022 20:13:38 - INFO - codeparrot_training - Step 5755: {'lr': 0.0004992062636564786, 'samples': 2947072, 'steps': 5755, 'loss/train': 2.8588778972625732}
-03/03/2022 20:13:41 - INFO - codeparrot_training - Step 5756: {'lr': 0.0004992058410618177, 'samples': 2947584, 'steps': 5756, 'loss/train': 2.558549642562866}
-03/03/2022 20:13:44 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/03/2022 20:13:47 - INFO - codeparrot_training - Step 5757: {'lr': 0.0004992054183548685, 'samples': 2948096, 'steps': 5757, 'loss/train': 2.224818229675293}
-03/03/2022 20:13:50 - INFO - codeparrot_training - Step 5758: {'lr': 0.0004992049955356313, 'samples': 2948608, 'steps': 5758, 'loss/train': 2.375624179840088}
-03/03/2022 20:13:52 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/03/2022 20:13:55 - INFO - codeparrot_training - Step 5759: {'lr': 0.0004992045726041061, 'samples': 2949120, 'steps': 5759, 'loss/train': 1.9546352624893188}
-03/03/2022 20:13:58 - INFO - codeparrot_training - Step 5760: {'lr': 0.0004992041495602931, 'samples': 2949632, 'steps': 5760, 'loss/train': 2.2301321029663086}
-03/03/2022 20:14:01 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/03/2022 20:14:04 - INFO - codeparrot_training - Step 5761: {'lr': 0.0004992037264041927, 'samples': 2950144, 'steps': 5761, 'loss/train': 1.7626627683639526}
-03/03/2022 20:14:07 - INFO - codeparrot_training - Step 5762: {'lr': 0.0004992033031358048, 'samples': 2950656, 'steps': 5762, 'loss/train': 1.9319103956222534}
-03/03/2022 20:14:09 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/03/2022 20:14:12 - INFO - codeparrot_training - Step 5763: {'lr': 0.0004992028797551298, 'samples': 2951168, 'steps': 5763, 'loss/train': 2.968773603439331}
-03/03/2022 20:14:15 - INFO - codeparrot_training - Step 5764: {'lr': 0.0004992024562621678, 'samples': 2951680, 'steps': 5764, 'loss/train': 2.514869213104248}
-03/03/2022 20:14:18 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/03/2022 20:14:20 - INFO - codeparrot_training - Step 5765: {'lr': 0.0004992020326569191, 'samples': 2952192, 'steps': 5765, 'loss/train': 1.8313456773757935}
-03/03/2022 20:14:24 - INFO - codeparrot_training - Step 5766: {'lr': 0.0004992016089393837, 'samples': 2952704, 'steps': 5766, 'loss/train': 2.675210952758789}
-03/03/2022 20:14:26 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/03/2022 20:14:29 - INFO - codeparrot_training - Step 5767: {'lr': 0.000499201185109562, 'samples': 2953216, 'steps': 5767, 'loss/train': 2.528242826461792}
-03/03/2022 20:14:32 - INFO - codeparrot_training - Step 5768: {'lr': 0.000499200761167454, 'samples': 2953728, 'steps': 5768, 'loss/train': 1.9571810960769653}
-03/03/2022 20:14:34 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/03/2022 20:14:37 - INFO - codeparrot_training - Step 5769: {'lr': 0.0004992003371130601, 'samples': 2954240, 'steps': 5769, 'loss/train': 2.2963640689849854}
-03/03/2022 20:14:40 - INFO - codeparrot_training - Step 5770: {'lr': 0.0004991999129463803, 'samples': 2954752, 'steps': 5770, 'loss/train': 2.9433257579803467}
-03/03/2022 20:14:43 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/03/2022 20:14:46 - INFO - codeparrot_training - Step 5771: {'lr': 0.0004991994886674148, 'samples': 2955264, 'steps': 5771, 'loss/train': 3.447805881500244}
-03/03/2022 20:14:49 - INFO - codeparrot_training - Step 5772: {'lr': 0.000499199064276164, 'samples': 2955776, 'steps': 5772, 'loss/train': 2.7041802406311035}
-03/03/2022 20:14:51 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/03/2022 20:14:54 - INFO - codeparrot_training - Step 5773: {'lr': 0.0004991986397726278, 'samples': 2956288, 'steps': 5773, 'loss/train': 1.6550157070159912}
-03/03/2022 20:14:57 - INFO - codeparrot_training - Step 5774: {'lr': 0.0004991982151568066, 'samples': 2956800, 'steps': 5774, 'loss/train': 2.296875238418579}
-03/03/2022 20:15:00 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/03/2022 20:15:03 - INFO - codeparrot_training - Step 5775: {'lr': 0.0004991977904287006, 'samples': 2957312, 'steps': 5775, 'loss/train': 3.090951681137085}
-03/03/2022 20:15:06 - INFO - codeparrot_training - Step 5776: {'lr': 0.0004991973655883099, 'samples': 2957824, 'steps': 5776, 'loss/train': 2.684974431991577}
-03/03/2022 20:15:08 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/03/2022 20:15:11 - INFO - codeparrot_training - Step 5777: {'lr': 0.0004991969406356346, 'samples': 2958336, 'steps': 5777, 'loss/train': 2.0642988681793213}
-03/03/2022 20:15:14 - INFO - codeparrot_training - Step 5778: {'lr': 0.0004991965155706752, 'samples': 2958848, 'steps': 5778, 'loss/train': 2.0922763347625732}
-03/03/2022 20:15:17 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/03/2022 20:15:19 - INFO - codeparrot_training - Step 5779: {'lr': 0.0004991960903934315, 'samples': 2959360, 'steps': 5779, 'loss/train': 2.1305553913116455}
-03/03/2022 20:15:23 - INFO - codeparrot_training - Step 5780: {'lr': 0.0004991956651039039, 'samples': 2959872, 'steps': 5780, 'loss/train': 1.9724007844924927}
-03/03/2022 20:15:25 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/03/2022 20:15:28 - INFO - codeparrot_training - Step 5781: {'lr': 0.0004991952397020927, 'samples': 2960384, 'steps': 5781, 'loss/train': 1.7005136013031006}
-03/03/2022 20:15:31 - INFO - codeparrot_training - Step 5782: {'lr': 0.0004991948141879978, 'samples': 2960896, 'steps': 5782, 'loss/train': 2.086486339569092}
-03/03/2022 20:15:33 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/03/2022 20:15:37 - INFO - codeparrot_training - Step 5783: {'lr': 0.0004991943885616198, 'samples': 2961408, 'steps': 5783, 'loss/train': 1.137892484664917}
-03/03/2022 20:15:40 - INFO - codeparrot_training - Step 5784: {'lr': 0.0004991939628229585, 'samples': 2961920, 'steps': 5784, 'loss/train': 1.6072392463684082}
-03/03/2022 20:15:42 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/03/2022 20:15:45 - INFO - codeparrot_training - Step 5785: {'lr': 0.0004991935369720143, 'samples': 2962432, 'steps': 5785, 'loss/train': 2.811178684234619}
-03/03/2022 20:15:48 - INFO - codeparrot_training - Step 5786: {'lr': 0.0004991931110087873, 'samples': 2962944, 'steps': 5786, 'loss/train': 2.162135362625122}
-03/03/2022 20:15:50 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/03/2022 20:15:53 - INFO - codeparrot_training - Step 5787: {'lr': 0.0004991926849332777, 'samples': 2963456, 'steps': 5787, 'loss/train': 1.878846526145935}
-03/03/2022 20:15:57 - INFO - codeparrot_training - Step 5788: {'lr': 0.0004991922587454858, 'samples': 2963968, 'steps': 5788, 'loss/train': 2.715374231338501}
-03/03/2022 20:15:59 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/03/2022 20:16:02 - INFO - codeparrot_training - Step 5789: {'lr': 0.0004991918324454117, 'samples': 2964480, 'steps': 5789, 'loss/train': 2.7309842109680176}
-03/03/2022 20:16:05 - INFO - codeparrot_training - Step 5790: {'lr': 0.0004991914060330556, 'samples': 2964992, 'steps': 5790, 'loss/train': 2.722963333129883}
-03/03/2022 20:16:07 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/03/2022 20:16:10 - INFO - codeparrot_training - Step 5791: {'lr': 0.0004991909795084177, 'samples': 2965504, 'steps': 5791, 'loss/train': 1.7974615097045898}
-03/03/2022 20:16:13 - INFO - codeparrot_training - Step 5792: {'lr': 0.0004991905528714981, 'samples': 2966016, 'steps': 5792, 'loss/train': 2.367002248764038}
-03/03/2022 20:16:16 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/03/2022 20:16:19 - INFO - codeparrot_training - Step 5793: {'lr': 0.0004991901261222971, 'samples': 2966528, 'steps': 5793, 'loss/train': 2.9921653270721436}
-03/03/2022 20:16:22 - INFO - codeparrot_training - Step 5794: {'lr': 0.000499189699260815, 'samples': 2967040, 'steps': 5794, 'loss/train': 1.9011017084121704}
-03/03/2022 20:16:24 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/03/2022 20:16:27 - INFO - codeparrot_training - Step 5795: {'lr': 0.0004991892722870517, 'samples': 2967552, 'steps': 5795, 'loss/train': 1.953097939491272}
-03/03/2022 20:16:30 - INFO - codeparrot_training - Step 5796: {'lr': 0.0004991888452010076, 'samples': 2968064, 'steps': 5796, 'loss/train': 2.6730921268463135}
-03/03/2022 20:16:36 - INFO - codeparrot_training - Step 5797: {'lr': 0.000499188418002683, 'samples': 2968576, 'steps': 5797, 'loss/train': 1.9038772583007812}
-03/03/2022 20:16:39 - INFO - codeparrot_training - Step 5798: {'lr': 0.0004991879906920779, 'samples': 2969088, 'steps': 5798, 'loss/train': 3.4297916889190674}
-03/03/2022 20:16:40 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/03/2022 20:16:44 - INFO - codeparrot_training - Step 5799: {'lr': 0.0004991875632691924, 'samples': 2969600, 'steps': 5799, 'loss/train': 2.6671106815338135}
-03/03/2022 20:16:47 - INFO - codeparrot_training - Step 5800: {'lr': 0.0004991871357340269, 'samples': 2970112, 'steps': 5800, 'loss/train': 1.943176507949829}
-03/03/2022 20:16:49 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/03/2022 20:16:53 - INFO - codeparrot_training - Step 5801: {'lr': 0.0004991867080865815, 'samples': 2970624, 'steps': 5801, 'loss/train': 2.39719557762146}
-03/03/2022 20:16:56 - INFO - codeparrot_training - Step 5802: {'lr': 0.0004991862803268564, 'samples': 2971136, 'steps': 5802, 'loss/train': 1.6217094659805298}
-03/03/2022 20:16:58 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/03/2022 20:17:01 - INFO - codeparrot_training - Step 5803: {'lr': 0.0004991858524548519, 'samples': 2971648, 'steps': 5803, 'loss/train': 2.338548183441162}
-03/03/2022 20:17:04 - INFO - codeparrot_training - Step 5804: {'lr': 0.000499185424470568, 'samples': 2972160, 'steps': 5804, 'loss/train': 2.3442978858947754}
-03/03/2022 20:17:06 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/03/2022 20:17:09 - INFO - codeparrot_training - Step 5805: {'lr': 0.0004991849963740052, 'samples': 2972672, 'steps': 5805, 'loss/train': 1.6334532499313354}
-03/03/2022 20:17:13 - INFO - codeparrot_training - Step 5806: {'lr': 0.0004991845681651632, 'samples': 2973184, 'steps': 5806, 'loss/train': 2.731915235519409}
-03/03/2022 20:17:14 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/03/2022 20:17:18 - INFO - codeparrot_training - Step 5807: {'lr': 0.0004991841398440427, 'samples': 2973696, 'steps': 5807, 'loss/train': 0.9844439625740051}
-03/03/2022 20:17:21 - INFO - codeparrot_training - Step 5808: {'lr': 0.0004991837114106436, 'samples': 2974208, 'steps': 5808, 'loss/train': 3.379225730895996}
-03/03/2022 20:17:23 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/03/2022 20:17:26 - INFO - codeparrot_training - Step 5809: {'lr': 0.0004991832828649661, 'samples': 2974720, 'steps': 5809, 'loss/train': 2.5770163536071777}
-03/03/2022 20:17:29 - INFO - codeparrot_training - Step 5810: {'lr': 0.0004991828542070105, 'samples': 2975232, 'steps': 5810, 'loss/train': 2.6871721744537354}
-03/03/2022 20:17:31 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/03/2022 20:17:35 - INFO - codeparrot_training - Step 5811: {'lr': 0.000499182425436777, 'samples': 2975744, 'steps': 5811, 'loss/train': 2.363396167755127}
-03/03/2022 20:17:38 - INFO - codeparrot_training - Step 5812: {'lr': 0.0004991819965542657, 'samples': 2976256, 'steps': 5812, 'loss/train': 2.493880271911621}
-03/03/2022 20:17:39 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/03/2022 20:17:43 - INFO - codeparrot_training - Step 5813: {'lr': 0.0004991815675594768, 'samples': 2976768, 'steps': 5813, 'loss/train': 2.9711742401123047}
-03/03/2022 20:17:46 - INFO - codeparrot_training - Step 5814: {'lr': 0.0004991811384524106, 'samples': 2977280, 'steps': 5814, 'loss/train': 2.3836889266967773}
-03/03/2022 20:17:47 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/03/2022 20:17:52 - INFO - codeparrot_training - Step 5815: {'lr': 0.0004991807092330671, 'samples': 2977792, 'steps': 5815, 'loss/train': 2.1700212955474854}
-03/03/2022 20:17:55 - INFO - codeparrot_training - Step 5816: {'lr': 0.0004991802799014467, 'samples': 2978304, 'steps': 5816, 'loss/train': 2.1088767051696777}
-03/03/2022 20:17:56 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/03/2022 20:18:00 - INFO - codeparrot_training - Step 5817: {'lr': 0.0004991798504575495, 'samples': 2978816, 'steps': 5817, 'loss/train': 2.6108298301696777}
-03/03/2022 20:18:03 - INFO - codeparrot_training - Step 5818: {'lr': 0.0004991794209013758, 'samples': 2979328, 'steps': 5818, 'loss/train': 2.317534923553467}
-03/03/2022 20:18:05 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/03/2022 20:18:09 - INFO - codeparrot_training - Step 5819: {'lr': 0.0004991789912329257, 'samples': 2979840, 'steps': 5819, 'loss/train': 2.4180362224578857}
-03/03/2022 20:18:12 - INFO - codeparrot_training - Step 5820: {'lr': 0.0004991785614521993, 'samples': 2980352, 'steps': 5820, 'loss/train': 2.5777440071105957}
-03/03/2022 20:18:13 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/03/2022 20:18:17 - INFO - codeparrot_training - Step 5821: {'lr': 0.0004991781315591969, 'samples': 2980864, 'steps': 5821, 'loss/train': 1.4525799751281738}
-03/03/2022 20:18:20 - INFO - codeparrot_training - Step 5822: {'lr': 0.0004991777015539186, 'samples': 2981376, 'steps': 5822, 'loss/train': 2.238250732421875}
-03/03/2022 20:18:21 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/03/2022 20:18:25 - INFO - codeparrot_training - Step 5823: {'lr': 0.0004991772714363649, 'samples': 2981888, 'steps': 5823, 'loss/train': 2.4229869842529297}
-03/03/2022 20:18:29 - INFO - codeparrot_training - Step 5824: {'lr': 0.0004991768412065355, 'samples': 2982400, 'steps': 5824, 'loss/train': 2.0351951122283936}
-03/03/2022 20:18:30 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/03/2022 20:18:34 - INFO - codeparrot_training - Step 5825: {'lr': 0.000499176410864431, 'samples': 2982912, 'steps': 5825, 'loss/train': 2.352614402770996}
-03/03/2022 20:18:37 - INFO - codeparrot_training - Step 5826: {'lr': 0.0004991759804100515, 'samples': 2983424, 'steps': 5826, 'loss/train': 3.4629626274108887}
-03/03/2022 20:18:38 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/03/2022 20:18:42 - INFO - codeparrot_training - Step 5827: {'lr': 0.000499175549843397, 'samples': 2983936, 'steps': 5827, 'loss/train': 2.217637062072754}
-03/03/2022 20:18:46 - INFO - codeparrot_training - Step 5828: {'lr': 0.0004991751191644679, 'samples': 2984448, 'steps': 5828, 'loss/train': 2.01352596282959}
-03/03/2022 20:18:46 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/03/2022 20:18:51 - INFO - codeparrot_training - Step 5829: {'lr': 0.0004991746883732644, 'samples': 2984960, 'steps': 5829, 'loss/train': 2.156876802444458}
-03/03/2022 20:18:54 - INFO - codeparrot_training - Step 5830: {'lr': 0.0004991742574697866, 'samples': 2985472, 'steps': 5830, 'loss/train': 1.9501721858978271}
-03/03/2022 20:18:54 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/03/2022 20:18:59 - INFO - codeparrot_training - Step 5831: {'lr': 0.0004991738264540347, 'samples': 2985984, 'steps': 5831, 'loss/train': 2.144679546356201}
-03/03/2022 20:19:02 - INFO - codeparrot_training - Step 5832: {'lr': 0.0004991733953260089, 'samples': 2986496, 'steps': 5832, 'loss/train': 1.878254771232605}
-03/03/2022 20:19:03 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/03/2022 20:19:08 - INFO - codeparrot_training - Step 5833: {'lr': 0.0004991729640857095, 'samples': 2987008, 'steps': 5833, 'loss/train': 2.771721363067627}
-03/03/2022 20:19:11 - INFO - codeparrot_training - Step 5834: {'lr': 0.0004991725327331366, 'samples': 2987520, 'steps': 5834, 'loss/train': 2.0923335552215576}
-03/03/2022 20:19:11 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/03/2022 20:19:16 - INFO - codeparrot_training - Step 5835: {'lr': 0.0004991721012682903, 'samples': 2988032, 'steps': 5835, 'loss/train': 0.7280183434486389}
-03/03/2022 20:19:19 - INFO - codeparrot_training - Step 5836: {'lr': 0.0004991716696911709, 'samples': 2988544, 'steps': 5836, 'loss/train': 2.930368661880493}
-03/03/2022 20:19:19 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/03/2022 20:19:25 - INFO - codeparrot_training - Step 5837: {'lr': 0.0004991712380017786, 'samples': 2989056, 'steps': 5837, 'loss/train': 5.677929401397705}
-03/03/2022 20:19:28 - INFO - codeparrot_training - Step 5838: {'lr': 0.0004991708062001137, 'samples': 2989568, 'steps': 5838, 'loss/train': 2.210714817047119}
-03/03/2022 20:19:29 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/03/2022 20:19:33 - INFO - codeparrot_training - Step 5839: {'lr': 0.0004991703742861762, 'samples': 2990080, 'steps': 5839, 'loss/train': 1.7000540494918823}
-03/03/2022 20:19:36 - INFO - codeparrot_training - Step 5840: {'lr': 0.0004991699422599664, 'samples': 2990592, 'steps': 5840, 'loss/train': 2.226290702819824}
-03/03/2022 20:19:37 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/03/2022 20:19:42 - INFO - codeparrot_training - Step 5841: {'lr': 0.0004991695101214844, 'samples': 2991104, 'steps': 5841, 'loss/train': 1.8866174221038818}
-03/03/2022 20:19:45 - INFO - codeparrot_training - Step 5842: {'lr': 0.0004991690778707305, 'samples': 2991616, 'steps': 5842, 'loss/train': 1.1542831659317017}
-03/03/2022 20:19:45 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/03/2022 20:19:50 - INFO - codeparrot_training - Step 5843: {'lr': 0.0004991686455077049, 'samples': 2992128, 'steps': 5843, 'loss/train': 2.321244239807129}
-03/03/2022 20:19:53 - INFO - codeparrot_training - Step 5844: {'lr': 0.0004991682130324078, 'samples': 2992640, 'steps': 5844, 'loss/train': 1.8309962749481201}
-03/03/2022 20:19:54 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/03/2022 20:19:58 - INFO - codeparrot_training - Step 5845: {'lr': 0.0004991677804448392, 'samples': 2993152, 'steps': 5845, 'loss/train': 1.5339628458023071}
-03/03/2022 20:20:02 - INFO - codeparrot_training - Step 5846: {'lr': 0.0004991673477449995, 'samples': 2993664, 'steps': 5846, 'loss/train': 2.579681396484375}
-03/03/2022 20:20:02 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/03/2022 20:20:07 - INFO - codeparrot_training - Step 5847: {'lr': 0.0004991669149328889, 'samples': 2994176, 'steps': 5847, 'loss/train': 2.5707852840423584}
-03/03/2022 20:20:10 - INFO - codeparrot_training - Step 5848: {'lr': 0.0004991664820085074, 'samples': 2994688, 'steps': 5848, 'loss/train': 1.3428655862808228}
-03/03/2022 20:20:11 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/03/2022 20:20:15 - INFO - codeparrot_training - Step 5849: {'lr': 0.0004991660489718554, 'samples': 2995200, 'steps': 5849, 'loss/train': 2.079094886779785}
-03/03/2022 20:20:19 - INFO - codeparrot_training - Step 5850: {'lr': 0.0004991656158229331, 'samples': 2995712, 'steps': 5850, 'loss/train': 2.123070001602173}
-03/03/2022 20:20:19 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/03/2022 20:20:24 - INFO - codeparrot_training - Step 5851: {'lr': 0.0004991651825617406, 'samples': 2996224, 'steps': 5851, 'loss/train': 0.5251814126968384}
-03/03/2022 20:20:27 - INFO - codeparrot_training - Step 5852: {'lr': 0.000499164749188278, 'samples': 2996736, 'steps': 5852, 'loss/train': 1.9478353261947632}
-03/03/2022 20:20:29 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/03/2022 20:20:33 - INFO - codeparrot_training - Step 5853: {'lr': 0.0004991643157025458, 'samples': 2997248, 'steps': 5853, 'loss/train': 2.916975259780884}
-03/03/2022 20:20:36 - INFO - codeparrot_training - Step 5854: {'lr': 0.0004991638821045439, 'samples': 2997760, 'steps': 5854, 'loss/train': 2.572099447250366}
-03/03/2022 20:20:38 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/03/2022 20:20:41 - INFO - codeparrot_training - Step 5855: {'lr': 0.0004991634483942725, 'samples': 2998272, 'steps': 5855, 'loss/train': 2.7367806434631348}
-03/03/2022 20:20:45 - INFO - codeparrot_training - Step 5856: {'lr': 0.000499163014571732, 'samples': 2998784, 'steps': 5856, 'loss/train': 2.6219279766082764}
-03/03/2022 20:20:48 - INFO - codeparrot_training - Step 5857: {'lr': 0.0004991625806369225, 'samples': 2999296, 'steps': 5857, 'loss/train': 0.6578152179718018}
-03/03/2022 20:20:48 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/03/2022 20:20:53 - INFO - codeparrot_training - Step 5858: {'lr': 0.0004991621465898441, 'samples': 2999808, 'steps': 5858, 'loss/train': 1.6125941276550293}
-03/03/2022 20:20:56 - INFO - codeparrot_training - Step 5859: {'lr': 0.0004991617124304971, 'samples': 3000320, 'steps': 5859, 'loss/train': 2.785588502883911}
-03/03/2022 20:20:56 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/03/2022 20:21:01 - INFO - codeparrot_training - Step 5860: {'lr': 0.0004991612781588818, 'samples': 3000832, 'steps': 5860, 'loss/train': 2.7747256755828857}
-03/03/2022 20:21:05 - INFO - codeparrot_training - Step 5861: {'lr': 0.0004991608437749981, 'samples': 3001344, 'steps': 5861, 'loss/train': 2.5884170532226562}
-03/03/2022 20:21:05 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 20:21:10 - INFO - codeparrot_training - Step 5862: {'lr': 0.0004991604092788465, 'samples': 3001856, 'steps': 5862, 'loss/train': 2.620652675628662}
-03/03/2022 20:21:13 - INFO - codeparrot_training - Step 5863: {'lr': 0.000499159974670427, 'samples': 3002368, 'steps': 5863, 'loss/train': 2.471514940261841}
-03/03/2022 20:21:13 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/03/2022 20:21:18 - INFO - codeparrot_training - Step 5864: {'lr': 0.00049915953994974, 'samples': 3002880, 'steps': 5864, 'loss/train': 2.461578369140625}
-03/03/2022 20:21:21 - INFO - codeparrot_training - Step 5865: {'lr': 0.0004991591051167853, 'samples': 3003392, 'steps': 5865, 'loss/train': 2.7467806339263916}
-03/03/2022 20:21:21 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/03/2022 20:21:26 - INFO - codeparrot_training - Step 5866: {'lr': 0.0004991586701715635, 'samples': 3003904, 'steps': 5866, 'loss/train': 1.9692384004592896}
-03/03/2022 20:21:30 - INFO - codeparrot_training - Step 5867: {'lr': 0.0004991582351140747, 'samples': 3004416, 'steps': 5867, 'loss/train': 2.7073347568511963}
-03/03/2022 20:21:30 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/03/2022 20:21:35 - INFO - codeparrot_training - Step 5868: {'lr': 0.000499157799944319, 'samples': 3004928, 'steps': 5868, 'loss/train': 6.741950035095215}
-03/03/2022 20:21:38 - INFO - codeparrot_training - Step 5869: {'lr': 0.0004991573646622965, 'samples': 3005440, 'steps': 5869, 'loss/train': 2.5303797721862793}
-03/03/2022 20:21:39 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/03/2022 20:21:44 - INFO - codeparrot_training - Step 5870: {'lr': 0.0004991569292680078, 'samples': 3005952, 'steps': 5870, 'loss/train': 3.012598991394043}
-03/03/2022 20:21:47 - INFO - codeparrot_training - Step 5871: {'lr': 0.0004991564937614526, 'samples': 3006464, 'steps': 5871, 'loss/train': 1.3312768936157227}
-03/03/2022 20:21:48 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/03/2022 20:21:52 - INFO - codeparrot_training - Step 5872: {'lr': 0.0004991560581426314, 'samples': 3006976, 'steps': 5872, 'loss/train': 2.824981927871704}
-03/03/2022 20:21:55 - INFO - codeparrot_training - Step 5873: {'lr': 0.0004991556224115444, 'samples': 3007488, 'steps': 5873, 'loss/train': 2.024332284927368}
-03/03/2022 20:21:56 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/03/2022 20:22:00 - INFO - codeparrot_training - Step 5874: {'lr': 0.0004991551865681916, 'samples': 3008000, 'steps': 5874, 'loss/train': 3.169869899749756}
-03/03/2022 20:22:03 - INFO - codeparrot_training - Step 5875: {'lr': 0.0004991547506125734, 'samples': 3008512, 'steps': 5875, 'loss/train': 2.2459731101989746}
-03/03/2022 20:22:04 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/03/2022 20:22:09 - INFO - codeparrot_training - Step 5876: {'lr': 0.0004991543145446899, 'samples': 3009024, 'steps': 5876, 'loss/train': 1.785586953163147}
-03/03/2022 20:22:12 - INFO - codeparrot_training - Step 5877: {'lr': 0.0004991538783645413, 'samples': 3009536, 'steps': 5877, 'loss/train': 0.6023777723312378}
-03/03/2022 20:22:12 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/03/2022 20:22:17 - INFO - codeparrot_training - Step 5878: {'lr': 0.0004991534420721278, 'samples': 3010048, 'steps': 5878, 'loss/train': 3.1541190147399902}
-03/03/2022 20:22:20 - INFO - codeparrot_training - Step 5879: {'lr': 0.0004991530056674496, 'samples': 3010560, 'steps': 5879, 'loss/train': 2.6373844146728516}
-03/03/2022 20:22:20 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/03/2022 20:22:26 - INFO - codeparrot_training - Step 5880: {'lr': 0.000499152569150507, 'samples': 3011072, 'steps': 5880, 'loss/train': 2.7928617000579834}
-03/03/2022 20:22:29 - INFO - codeparrot_training - Step 5881: {'lr': 0.0004991521325213, 'samples': 3011584, 'steps': 5881, 'loss/train': 1.8833165168762207}
-03/03/2022 20:22:29 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/03/2022 20:22:34 - INFO - codeparrot_training - Step 5882: {'lr': 0.0004991516957798289, 'samples': 3012096, 'steps': 5882, 'loss/train': 1.2574199438095093}
-03/03/2022 20:22:37 - INFO - codeparrot_training - Step 5883: {'lr': 0.0004991512589260939, 'samples': 3012608, 'steps': 5883, 'loss/train': 0.2981458902359009}
-03/03/2022 20:22:37 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/03/2022 20:22:43 - INFO - codeparrot_training - Step 5884: {'lr': 0.0004991508219600952, 'samples': 3013120, 'steps': 5884, 'loss/train': 4.122183799743652}
-03/03/2022 20:22:45 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/03/2022 20:22:48 - INFO - codeparrot_training - Step 5885: {'lr': 0.000499150384881833, 'samples': 3013632, 'steps': 5885, 'loss/train': 3.146188259124756}
-03/03/2022 20:22:51 - INFO - codeparrot_training - Step 5886: {'lr': 0.0004991499476913074, 'samples': 3014144, 'steps': 5886, 'loss/train': 2.100738763809204}
-03/03/2022 20:22:54 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 20:22:56 - INFO - codeparrot_training - Step 5887: {'lr': 0.0004991495103885187, 'samples': 3014656, 'steps': 5887, 'loss/train': 2.522759199142456}
-03/03/2022 20:22:59 - INFO - codeparrot_training - Step 5888: {'lr': 0.0004991490729734672, 'samples': 3015168, 'steps': 5888, 'loss/train': 2.1798276901245117}
-03/03/2022 20:23:03 - INFO - codeparrot_training - Step 5889: {'lr': 0.0004991486354461528, 'samples': 3015680, 'steps': 5889, 'loss/train': 2.3707680702209473}
-03/03/2022 20:23:03 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/03/2022 20:23:08 - INFO - codeparrot_training - Step 5890: {'lr': 0.000499148197806576, 'samples': 3016192, 'steps': 5890, 'loss/train': 2.263777494430542}
-03/03/2022 20:23:11 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/03/2022 20:23:13 - INFO - codeparrot_training - Step 5891: {'lr': 0.0004991477600547367, 'samples': 3016704, 'steps': 5891, 'loss/train': 2.327378511428833}
-03/03/2022 20:23:16 - INFO - codeparrot_training - Step 5892: {'lr': 0.0004991473221906354, 'samples': 3017216, 'steps': 5892, 'loss/train': 2.7881836891174316}
-03/03/2022 20:23:19 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/03/2022 20:23:22 - INFO - codeparrot_training - Step 5893: {'lr': 0.0004991468842142722, 'samples': 3017728, 'steps': 5893, 'loss/train': 2.1302874088287354}
-03/03/2022 20:23:25 - INFO - codeparrot_training - Step 5894: {'lr': 0.0004991464461256472, 'samples': 3018240, 'steps': 5894, 'loss/train': 1.8025484085083008}
-03/03/2022 20:23:28 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/03/2022 20:23:30 - INFO - codeparrot_training - Step 5895: {'lr': 0.0004991460079247606, 'samples': 3018752, 'steps': 5895, 'loss/train': 2.7407751083374023}
-03/03/2022 20:23:33 - INFO - codeparrot_training - Step 5896: {'lr': 0.0004991455696116128, 'samples': 3019264, 'steps': 5896, 'loss/train': 0.1673123687505722}
-03/03/2022 20:23:36 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/03/2022 20:23:38 - INFO - codeparrot_training - Step 5897: {'lr': 0.0004991451311862037, 'samples': 3019776, 'steps': 5897, 'loss/train': 2.2674899101257324}
-03/03/2022 20:23:42 - INFO - codeparrot_training - Step 5898: {'lr': 0.0004991446926485337, 'samples': 3020288, 'steps': 5898, 'loss/train': 1.6101255416870117}
-03/03/2022 20:23:44 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/03/2022 20:23:47 - INFO - codeparrot_training - Step 5899: {'lr': 0.0004991442539986029, 'samples': 3020800, 'steps': 5899, 'loss/train': 2.671097993850708}
-03/03/2022 20:23:50 - INFO - codeparrot_training - Step 5900: {'lr': 0.0004991438152364117, 'samples': 3021312, 'steps': 5900, 'loss/train': 2.284365653991699}
-03/03/2022 20:23:52 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/03/2022 20:23:55 - INFO - codeparrot_training - Step 5901: {'lr': 0.0004991433763619599, 'samples': 3021824, 'steps': 5901, 'loss/train': 2.154289484024048}
-03/03/2022 20:23:58 - INFO - codeparrot_training - Step 5902: {'lr': 0.0004991429373752482, 'samples': 3022336, 'steps': 5902, 'loss/train': 2.4048495292663574}
-03/03/2022 20:24:01 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/03/2022 20:24:03 - INFO - codeparrot_training - Step 5903: {'lr': 0.0004991424982762763, 'samples': 3022848, 'steps': 5903, 'loss/train': 3.426903009414673}
-03/03/2022 20:24:07 - INFO - codeparrot_training - Step 5904: {'lr': 0.0004991420590650448, 'samples': 3023360, 'steps': 5904, 'loss/train': 2.7910776138305664}
-03/03/2022 20:24:09 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/03/2022 20:24:12 - INFO - codeparrot_training - Step 5905: {'lr': 0.0004991416197415537, 'samples': 3023872, 'steps': 5905, 'loss/train': 1.9132165908813477}
-03/03/2022 20:24:15 - INFO - codeparrot_training - Step 5906: {'lr': 0.0004991411803058032, 'samples': 3024384, 'steps': 5906, 'loss/train': 1.756943941116333}
-03/03/2022 20:24:17 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/03/2022 20:24:20 - INFO - codeparrot_training - Step 5907: {'lr': 0.0004991407407577936, 'samples': 3024896, 'steps': 5907, 'loss/train': 2.7177062034606934}
-03/03/2022 20:24:23 - INFO - codeparrot_training - Step 5908: {'lr': 0.0004991403010975249, 'samples': 3025408, 'steps': 5908, 'loss/train': 2.002141237258911}
-03/03/2022 20:24:25 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/03/2022 20:24:29 - INFO - codeparrot_training - Step 5909: {'lr': 0.0004991398613249976, 'samples': 3025920, 'steps': 5909, 'loss/train': 2.292219638824463}
-03/03/2022 20:24:32 - INFO - codeparrot_training - Step 5910: {'lr': 0.0004991394214402115, 'samples': 3026432, 'steps': 5910, 'loss/train': 3.036072015762329}
-03/03/2022 20:24:34 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/03/2022 20:24:37 - INFO - codeparrot_training - Step 5911: {'lr': 0.0004991389814431672, 'samples': 3026944, 'steps': 5911, 'loss/train': 1.8513215780258179}
-03/03/2022 20:24:40 - INFO - codeparrot_training - Step 5912: {'lr': 0.0004991385413338646, 'samples': 3027456, 'steps': 5912, 'loss/train': 1.8595123291015625}
-03/03/2022 20:24:42 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/03/2022 20:24:45 - INFO - codeparrot_training - Step 5913: {'lr': 0.0004991381011123041, 'samples': 3027968, 'steps': 5913, 'loss/train': 3.236508846282959}
-03/03/2022 20:24:49 - INFO - codeparrot_training - Step 5914: {'lr': 0.0004991376607784857, 'samples': 3028480, 'steps': 5914, 'loss/train': 2.6897635459899902}
-03/03/2022 20:24:50 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/03/2022 20:24:54 - INFO - codeparrot_training - Step 5915: {'lr': 0.0004991372203324098, 'samples': 3028992, 'steps': 5915, 'loss/train': 2.4515328407287598}
-03/03/2022 20:24:57 - INFO - codeparrot_training - Step 5916: {'lr': 0.0004991367797740765, 'samples': 3029504, 'steps': 5916, 'loss/train': 2.8639373779296875}
-03/03/2022 20:24:59 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/03/2022 20:25:02 - INFO - codeparrot_training - Step 5917: {'lr': 0.0004991363391034861, 'samples': 3030016, 'steps': 5917, 'loss/train': 2.399662494659424}
-03/03/2022 20:25:06 - INFO - codeparrot_training - Step 5918: {'lr': 0.0004991358983206386, 'samples': 3030528, 'steps': 5918, 'loss/train': 1.982954740524292}
-03/03/2022 20:25:07 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/03/2022 20:25:11 - INFO - codeparrot_training - Step 5919: {'lr': 0.0004991354574255344, 'samples': 3031040, 'steps': 5919, 'loss/train': 2.981220006942749}
-03/03/2022 20:25:14 - INFO - codeparrot_training - Step 5920: {'lr': 0.0004991350164181735, 'samples': 3031552, 'steps': 5920, 'loss/train': 0.7791263461112976}
-03/03/2022 20:25:15 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/03/2022 20:25:19 - INFO - codeparrot_training - Step 5921: {'lr': 0.0004991345752985563, 'samples': 3032064, 'steps': 5921, 'loss/train': 2.117980718612671}
-03/03/2022 20:25:23 - INFO - codeparrot_training - Step 5922: {'lr': 0.0004991341340666828, 'samples': 3032576, 'steps': 5922, 'loss/train': 7.184759616851807}
-03/03/2022 20:25:25 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/03/2022 20:25:28 - INFO - codeparrot_training - Step 5923: {'lr': 0.0004991336927225534, 'samples': 3033088, 'steps': 5923, 'loss/train': 1.5445551872253418}
-03/03/2022 20:25:31 - INFO - codeparrot_training - Step 5924: {'lr': 0.0004991332512661682, 'samples': 3033600, 'steps': 5924, 'loss/train': 0.5544155836105347}
-03/03/2022 20:25:33 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/03/2022 20:25:37 - INFO - codeparrot_training - Step 5925: {'lr': 0.0004991328096975273, 'samples': 3034112, 'steps': 5925, 'loss/train': 2.348832368850708}
-03/03/2022 20:25:40 - INFO - codeparrot_training - Step 5926: {'lr': 0.0004991323680166312, 'samples': 3034624, 'steps': 5926, 'loss/train': 0.17776928842067719}
-03/03/2022 20:25:42 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/03/2022 20:25:45 - INFO - codeparrot_training - Step 5927: {'lr': 0.0004991319262234797, 'samples': 3035136, 'steps': 5927, 'loss/train': 2.847273588180542}
-03/03/2022 20:25:48 - INFO - codeparrot_training - Step 5928: {'lr': 0.0004991314843180733, 'samples': 3035648, 'steps': 5928, 'loss/train': 2.023456335067749}
-03/03/2022 20:25:50 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/03/2022 20:25:53 - INFO - codeparrot_training - Step 5929: {'lr': 0.0004991310423004121, 'samples': 3036160, 'steps': 5929, 'loss/train': 2.657038450241089}
-03/03/2022 20:25:57 - INFO - codeparrot_training - Step 5930: {'lr': 0.0004991306001704962, 'samples': 3036672, 'steps': 5930, 'loss/train': 2.789397954940796}
-03/03/2022 20:25:59 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/03/2022 20:26:02 - INFO - codeparrot_training - Step 5931: {'lr': 0.000499130157928326, 'samples': 3037184, 'steps': 5931, 'loss/train': 1.292098879814148}
-03/03/2022 20:26:05 - INFO - codeparrot_training - Step 5932: {'lr': 0.0004991297155739015, 'samples': 3037696, 'steps': 5932, 'loss/train': 2.8151638507843018}
-03/03/2022 20:26:07 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/03/2022 20:26:11 - INFO - codeparrot_training - Step 5933: {'lr': 0.0004991292731072231, 'samples': 3038208, 'steps': 5933, 'loss/train': 2.270427703857422}
-03/03/2022 20:26:14 - INFO - codeparrot_training - Step 5934: {'lr': 0.0004991288305282908, 'samples': 3038720, 'steps': 5934, 'loss/train': 2.5849227905273438}
-03/03/2022 20:26:16 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/03/2022 20:26:19 - INFO - codeparrot_training - Step 5935: {'lr': 0.0004991283878371049, 'samples': 3039232, 'steps': 5935, 'loss/train': 2.04127836227417}
-03/03/2022 20:26:22 - INFO - codeparrot_training - Step 5936: {'lr': 0.0004991279450336656, 'samples': 3039744, 'steps': 5936, 'loss/train': 3.40488600730896}
-03/03/2022 20:26:25 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/03/2022 20:26:27 - INFO - codeparrot_training - Step 5937: {'lr': 0.0004991275021179732, 'samples': 3040256, 'steps': 5937, 'loss/train': 2.299351215362549}
-03/03/2022 20:26:30 - INFO - codeparrot_training - Step 5938: {'lr': 0.0004991270590900277, 'samples': 3040768, 'steps': 5938, 'loss/train': 2.660971164703369}
-03/03/2022 20:26:33 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/03/2022 20:26:36 - INFO - codeparrot_training - Step 5939: {'lr': 0.0004991266159498294, 'samples': 3041280, 'steps': 5939, 'loss/train': 2.1659200191497803}
-03/03/2022 20:26:39 - INFO - codeparrot_training - Step 5940: {'lr': 0.0004991261726973784, 'samples': 3041792, 'steps': 5940, 'loss/train': 2.5608344078063965}
-03/03/2022 20:26:42 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/03/2022 20:26:44 - INFO - codeparrot_training - Step 5941: {'lr': 0.0004991257293326752, 'samples': 3042304, 'steps': 5941, 'loss/train': 2.222609281539917}
-03/03/2022 20:26:47 - INFO - codeparrot_training - Step 5942: {'lr': 0.0004991252858557196, 'samples': 3042816, 'steps': 5942, 'loss/train': 1.9575656652450562}
-03/03/2022 20:26:50 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/03/2022 20:26:53 - INFO - codeparrot_training - Step 5943: {'lr': 0.0004991248422665122, 'samples': 3043328, 'steps': 5943, 'loss/train': 1.6798070669174194}
-03/03/2022 20:26:56 - INFO - codeparrot_training - Step 5944: {'lr': 0.0004991243985650528, 'samples': 3043840, 'steps': 5944, 'loss/train': 2.3228254318237305}
-03/03/2022 20:26:58 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/03/2022 20:27:01 - INFO - codeparrot_training - Step 5945: {'lr': 0.0004991239547513419, 'samples': 3044352, 'steps': 5945, 'loss/train': 2.9737420082092285}
-03/03/2022 20:27:04 - INFO - codeparrot_training - Step 5946: {'lr': 0.0004991235108253795, 'samples': 3044864, 'steps': 5946, 'loss/train': 2.0720551013946533}
-03/03/2022 20:27:06 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/03/2022 20:27:09 - INFO - codeparrot_training - Step 5947: {'lr': 0.0004991230667871659, 'samples': 3045376, 'steps': 5947, 'loss/train': 1.700006127357483}
-03/03/2022 20:27:13 - INFO - codeparrot_training - Step 5948: {'lr': 0.0004991226226367013, 'samples': 3045888, 'steps': 5948, 'loss/train': 2.1544928550720215}
-03/03/2022 20:27:15 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/03/2022 20:27:18 - INFO - codeparrot_training - Step 5949: {'lr': 0.0004991221783739859, 'samples': 3046400, 'steps': 5949, 'loss/train': 1.954289197921753}
-03/03/2022 20:27:21 - INFO - codeparrot_training - Step 5950: {'lr': 0.0004991217339990199, 'samples': 3046912, 'steps': 5950, 'loss/train': 1.8064900636672974}
-03/03/2022 20:27:23 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/03/2022 20:27:26 - INFO - codeparrot_training - Step 5951: {'lr': 0.0004991212895118035, 'samples': 3047424, 'steps': 5951, 'loss/train': 4.5229411125183105}
-03/03/2022 20:27:29 - INFO - codeparrot_training - Step 5952: {'lr': 0.0004991208449123369, 'samples': 3047936, 'steps': 5952, 'loss/train': 1.5722763538360596}
-03/03/2022 20:27:31 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/03/2022 20:27:34 - INFO - codeparrot_training - Step 5953: {'lr': 0.0004991204002006203, 'samples': 3048448, 'steps': 5953, 'loss/train': 1.7541601657867432}
-03/03/2022 20:27:38 - INFO - codeparrot_training - Step 5954: {'lr': 0.0004991199553766538, 'samples': 3048960, 'steps': 5954, 'loss/train': 2.426776647567749}
-03/03/2022 20:27:39 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/03/2022 20:27:43 - INFO - codeparrot_training - Step 5955: {'lr': 0.0004991195104404378, 'samples': 3049472, 'steps': 5955, 'loss/train': 1.927330732345581}
-03/03/2022 20:27:46 - INFO - codeparrot_training - Step 5956: {'lr': 0.0004991190653919723, 'samples': 3049984, 'steps': 5956, 'loss/train': 1.9182006120681763}
-03/03/2022 20:27:48 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/03/2022 20:27:51 - INFO - codeparrot_training - Step 5957: {'lr': 0.0004991186202312576, 'samples': 3050496, 'steps': 5957, 'loss/train': 2.9977004528045654}
-03/03/2022 20:27:55 - INFO - codeparrot_training - Step 5958: {'lr': 0.0004991181749582941, 'samples': 3051008, 'steps': 5958, 'loss/train': 2.103074073791504}
-03/03/2022 20:27:57 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/03/2022 20:28:00 - INFO - codeparrot_training - Step 5959: {'lr': 0.0004991177295730815, 'samples': 3051520, 'steps': 5959, 'loss/train': 2.230144500732422}
-03/03/2022 20:28:03 - INFO - codeparrot_training - Step 5960: {'lr': 0.0004991172840756204, 'samples': 3052032, 'steps': 5960, 'loss/train': 2.2944867610931396}
-03/03/2022 20:28:05 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/03/2022 20:28:08 - INFO - codeparrot_training - Step 5961: {'lr': 0.000499116838465911, 'samples': 3052544, 'steps': 5961, 'loss/train': 2.684199094772339}
-03/03/2022 20:28:11 - INFO - codeparrot_training - Step 5962: {'lr': 0.0004991163927439533, 'samples': 3053056, 'steps': 5962, 'loss/train': 1.5158330202102661}
-03/03/2022 20:28:13 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/03/2022 20:28:17 - INFO - codeparrot_training - Step 5963: {'lr': 0.0004991159469097476, 'samples': 3053568, 'steps': 5963, 'loss/train': 2.673222541809082}
-03/03/2022 20:28:20 - INFO - codeparrot_training - Step 5964: {'lr': 0.0004991155009632941, 'samples': 3054080, 'steps': 5964, 'loss/train': 2.467852830886841}
-03/03/2022 20:28:22 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/03/2022 20:28:25 - INFO - codeparrot_training - Step 5965: {'lr': 0.0004991150549045931, 'samples': 3054592, 'steps': 5965, 'loss/train': 2.2372024059295654}
-03/03/2022 20:28:28 - INFO - codeparrot_training - Step 5966: {'lr': 0.0004991146087336446, 'samples': 3055104, 'steps': 5966, 'loss/train': 1.4726967811584473}
-03/03/2022 20:28:30 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/03/2022 20:28:33 - INFO - codeparrot_training - Step 5967: {'lr': 0.0004991141624504489, 'samples': 3055616, 'steps': 5967, 'loss/train': 2.289726972579956}
-03/03/2022 20:28:37 - INFO - codeparrot_training - Step 5968: {'lr': 0.0004991137160550062, 'samples': 3056128, 'steps': 5968, 'loss/train': 2.4521987438201904}
-03/03/2022 20:28:39 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/03/2022 20:28:42 - INFO - codeparrot_training - Step 5969: {'lr': 0.0004991132695473167, 'samples': 3056640, 'steps': 5969, 'loss/train': 2.3085923194885254}
-03/03/2022 20:28:45 - INFO - codeparrot_training - Step 5970: {'lr': 0.0004991128229273807, 'samples': 3057152, 'steps': 5970, 'loss/train': 2.405261516571045}
-03/03/2022 20:28:47 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/03/2022 20:28:50 - INFO - codeparrot_training - Step 5971: {'lr': 0.0004991123761951982, 'samples': 3057664, 'steps': 5971, 'loss/train': 2.7527971267700195}
-03/03/2022 20:28:53 - INFO - codeparrot_training - Step 5972: {'lr': 0.0004991119293507695, 'samples': 3058176, 'steps': 5972, 'loss/train': 2.5099852085113525}
-03/03/2022 20:28:56 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/03/2022 20:28:59 - INFO - codeparrot_training - Step 5973: {'lr': 0.0004991114823940948, 'samples': 3058688, 'steps': 5973, 'loss/train': 2.9311931133270264}
-03/03/2022 20:29:02 - INFO - codeparrot_training - Step 5974: {'lr': 0.0004991110353251744, 'samples': 3059200, 'steps': 5974, 'loss/train': 2.143594980239868}
-03/03/2022 20:29:04 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/03/2022 20:29:07 - INFO - codeparrot_training - Step 5975: {'lr': 0.0004991105881440084, 'samples': 3059712, 'steps': 5975, 'loss/train': 2.347439765930176}
-03/03/2022 20:29:10 - INFO - codeparrot_training - Step 5976: {'lr': 0.000499110140850597, 'samples': 3060224, 'steps': 5976, 'loss/train': 0.41311874985694885}
-03/03/2022 20:29:12 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/03/2022 20:29:15 - INFO - codeparrot_training - Step 5977: {'lr': 0.0004991096934449404, 'samples': 3060736, 'steps': 5977, 'loss/train': 2.24841570854187}
-03/03/2022 20:29:19 - INFO - codeparrot_training - Step 5978: {'lr': 0.0004991092459270388, 'samples': 3061248, 'steps': 5978, 'loss/train': 1.9941514730453491}
-03/03/2022 20:29:20 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/03/2022 20:29:24 - INFO - codeparrot_training - Step 5979: {'lr': 0.0004991087982968924, 'samples': 3061760, 'steps': 5979, 'loss/train': 2.12906551361084}
-03/03/2022 20:29:27 - INFO - codeparrot_training - Step 5980: {'lr': 0.0004991083505545014, 'samples': 3062272, 'steps': 5980, 'loss/train': 3.3764865398406982}
-03/03/2022 20:29:29 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/03/2022 20:29:32 - INFO - codeparrot_training - Step 5981: {'lr': 0.0004991079026998662, 'samples': 3062784, 'steps': 5981, 'loss/train': 3.8224642276763916}
-03/03/2022 20:29:35 - INFO - codeparrot_training - Step 5982: {'lr': 0.0004991074547329867, 'samples': 3063296, 'steps': 5982, 'loss/train': 1.9127687215805054}
-03/03/2022 20:29:37 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/03/2022 20:29:41 - INFO - codeparrot_training - Step 5983: {'lr': 0.0004991070066538632, 'samples': 3063808, 'steps': 5983, 'loss/train': 2.583160400390625}
-03/03/2022 20:29:44 - INFO - codeparrot_training - Step 5984: {'lr': 0.0004991065584624959, 'samples': 3064320, 'steps': 5984, 'loss/train': 0.7335283160209656}
-03/03/2022 20:29:46 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/03/2022 20:29:49 - INFO - codeparrot_training - Step 5985: {'lr': 0.0004991061101588851, 'samples': 3064832, 'steps': 5985, 'loss/train': 1.793200135231018}
-03/03/2022 20:29:52 - INFO - codeparrot_training - Step 5986: {'lr': 0.0004991056617430308, 'samples': 3065344, 'steps': 5986, 'loss/train': 2.4399266242980957}
-03/03/2022 20:29:54 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/03/2022 20:29:58 - INFO - codeparrot_training - Step 5987: {'lr': 0.0004991052132149336, 'samples': 3065856, 'steps': 5987, 'loss/train': 2.4067862033843994}
-03/03/2022 20:30:01 - INFO - codeparrot_training - Step 5988: {'lr': 0.0004991047645745932, 'samples': 3066368, 'steps': 5988, 'loss/train': 1.7631402015686035}
-03/03/2022 20:30:03 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/03/2022 20:30:06 - INFO - codeparrot_training - Step 5989: {'lr': 0.0004991043158220101, 'samples': 3066880, 'steps': 5989, 'loss/train': 2.21980881690979}
-03/03/2022 20:30:09 - INFO - codeparrot_training - Step 5990: {'lr': 0.0004991038669571844, 'samples': 3067392, 'steps': 5990, 'loss/train': 3.0790963172912598}
-03/03/2022 20:30:12 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/03/2022 20:30:15 - INFO - codeparrot_training - Step 5991: {'lr': 0.0004991034179801165, 'samples': 3067904, 'steps': 5991, 'loss/train': 2.485940933227539}
-03/03/2022 20:30:18 - INFO - codeparrot_training - Step 5992: {'lr': 0.0004991029688908063, 'samples': 3068416, 'steps': 5992, 'loss/train': 2.1920077800750732}
-03/03/2022 20:30:20 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/03/2022 20:30:23 - INFO - codeparrot_training - Step 5993: {'lr': 0.0004991025196892542, 'samples': 3068928, 'steps': 5993, 'loss/train': 2.2069289684295654}
-03/03/2022 20:30:26 - INFO - codeparrot_training - Step 5994: {'lr': 0.0004991020703754603, 'samples': 3069440, 'steps': 5994, 'loss/train': 2.6836657524108887}
-03/03/2022 20:30:28 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/03/2022 20:30:32 - INFO - codeparrot_training - Step 5995: {'lr': 0.0004991016209494249, 'samples': 3069952, 'steps': 5995, 'loss/train': 2.4205801486968994}
-03/03/2022 20:30:35 - INFO - codeparrot_training - Step 5996: {'lr': 0.000499101171411148, 'samples': 3070464, 'steps': 5996, 'loss/train': 2.8049941062927246}
-03/03/2022 20:30:37 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/03/2022 20:30:40 - INFO - codeparrot_training - Step 5997: {'lr': 0.0004991007217606303, 'samples': 3070976, 'steps': 5997, 'loss/train': 3.0415985584259033}
-03/03/2022 20:30:43 - INFO - codeparrot_training - Step 5998: {'lr': 0.0004991002719978713, 'samples': 3071488, 'steps': 5998, 'loss/train': 2.6887707710266113}
-03/03/2022 20:30:45 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/03/2022 20:30:48 - INFO - codeparrot_training - Step 5999: {'lr': 0.0004990998221228718, 'samples': 3072000, 'steps': 5999, 'loss/train': 2.388474225997925}
-03/03/2022 20:30:52 - INFO - codeparrot_training - Step 6000: {'lr': 0.0004990993721356316, 'samples': 3072512, 'steps': 6000, 'loss/train': 3.1334824562072754}
-03/03/2022 20:30:54 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/03/2022 20:30:57 - INFO - codeparrot_training - Step 6001: {'lr': 0.0004990989220361511, 'samples': 3073024, 'steps': 6001, 'loss/train': 1.9719607830047607}
-03/03/2022 20:31:00 - INFO - codeparrot_training - Step 6002: {'lr': 0.0004990984718244306, 'samples': 3073536, 'steps': 6002, 'loss/train': 2.268338680267334}
-03/03/2022 20:31:03 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/03/2022 20:31:05 - INFO - codeparrot_training - Step 6003: {'lr': 0.00049909802150047, 'samples': 3074048, 'steps': 6003, 'loss/train': 2.2719171047210693}
-03/03/2022 20:31:09 - INFO - codeparrot_training - Step 6004: {'lr': 0.0004990975710642699, 'samples': 3074560, 'steps': 6004, 'loss/train': 2.0334343910217285}
-03/03/2022 20:31:11 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/03/2022 20:31:14 - INFO - codeparrot_training - Step 6005: {'lr': 0.0004990971205158301, 'samples': 3075072, 'steps': 6005, 'loss/train': 2.820753574371338}
-03/03/2022 20:31:17 - INFO - codeparrot_training - Step 6006: {'lr': 0.000499096669855151, 'samples': 3075584, 'steps': 6006, 'loss/train': 2.1361453533172607}
-03/03/2022 20:31:19 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/03/2022 20:31:22 - INFO - codeparrot_training - Step 6007: {'lr': 0.0004990962190822328, 'samples': 3076096, 'steps': 6007, 'loss/train': 1.8038440942764282}
-03/03/2022 20:31:25 - INFO - codeparrot_training - Step 6008: {'lr': 0.0004990957681970757, 'samples': 3076608, 'steps': 6008, 'loss/train': 2.157381296157837}
-03/03/2022 20:31:28 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/03/2022 20:31:31 - INFO - codeparrot_training - Step 6009: {'lr': 0.0004990953171996798, 'samples': 3077120, 'steps': 6009, 'loss/train': 2.3332808017730713}
-03/03/2022 20:31:34 - INFO - codeparrot_training - Step 6010: {'lr': 0.0004990948660900455, 'samples': 3077632, 'steps': 6010, 'loss/train': 2.531421184539795}
-03/03/2022 20:31:36 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/03/2022 20:31:39 - INFO - codeparrot_training - Step 6011: {'lr': 0.0004990944148681729, 'samples': 3078144, 'steps': 6011, 'loss/train': 2.042480945587158}
-03/03/2022 20:31:42 - INFO - codeparrot_training - Step 6012: {'lr': 0.0004990939635340621, 'samples': 3078656, 'steps': 6012, 'loss/train': 2.654365062713623}
-03/03/2022 20:31:45 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/03/2022 20:31:48 - INFO - codeparrot_training - Step 6013: {'lr': 0.0004990935120877136, 'samples': 3079168, 'steps': 6013, 'loss/train': 3.610926628112793}
-03/03/2022 20:31:51 - INFO - codeparrot_training - Step 6014: {'lr': 0.0004990930605291272, 'samples': 3079680, 'steps': 6014, 'loss/train': 1.69937002658844}
-03/03/2022 20:31:54 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/03/2022 20:31:56 - INFO - codeparrot_training - Step 6015: {'lr': 0.0004990926088583034, 'samples': 3080192, 'steps': 6015, 'loss/train': 2.5746405124664307}
-03/03/2022 20:31:59 - INFO - codeparrot_training - Step 6016: {'lr': 0.0004990921570752424, 'samples': 3080704, 'steps': 6016, 'loss/train': 1.7964903116226196}
-03/03/2022 20:32:02 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/03/2022 20:32:04 - INFO - codeparrot_training - Step 6017: {'lr': 0.0004990917051799442, 'samples': 3081216, 'steps': 6017, 'loss/train': 2.706967830657959}
-03/03/2022 20:32:08 - INFO - codeparrot_training - Step 6018: {'lr': 0.0004990912531724092, 'samples': 3081728, 'steps': 6018, 'loss/train': 2.7476706504821777}
-03/03/2022 20:32:10 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/03/2022 20:32:13 - INFO - codeparrot_training - Step 6019: {'lr': 0.0004990908010526374, 'samples': 3082240, 'steps': 6019, 'loss/train': 0.8592450022697449}
-03/03/2022 20:32:16 - INFO - codeparrot_training - Step 6020: {'lr': 0.0004990903488206292, 'samples': 3082752, 'steps': 6020, 'loss/train': 2.3802523612976074}
-03/03/2022 20:32:19 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/03/2022 20:32:21 - INFO - codeparrot_training - Step 6021: {'lr': 0.0004990898964763847, 'samples': 3083264, 'steps': 6021, 'loss/train': 2.428510904312134}
-03/03/2022 20:32:25 - INFO - codeparrot_training - Step 6022: {'lr': 0.0004990894440199042, 'samples': 3083776, 'steps': 6022, 'loss/train': 2.889967203140259}
-03/03/2022 20:32:27 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/03/2022 20:32:30 - INFO - codeparrot_training - Step 6023: {'lr': 0.0004990889914511878, 'samples': 3084288, 'steps': 6023, 'loss/train': 2.289975881576538}
-03/03/2022 20:32:33 - INFO - codeparrot_training - Step 6024: {'lr': 0.0004990885387702357, 'samples': 3084800, 'steps': 6024, 'loss/train': 2.2280101776123047}
-03/03/2022 20:32:35 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/03/2022 20:32:38 - INFO - codeparrot_training - Step 6025: {'lr': 0.0004990880859770483, 'samples': 3085312, 'steps': 6025, 'loss/train': 1.4783647060394287}
-03/03/2022 20:32:42 - INFO - codeparrot_training - Step 6026: {'lr': 0.0004990876330716256, 'samples': 3085824, 'steps': 6026, 'loss/train': 2.4260175228118896}
-03/03/2022 20:32:44 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/03/2022 20:32:47 - INFO - codeparrot_training - Step 6027: {'lr': 0.0004990871800539677, 'samples': 3086336, 'steps': 6027, 'loss/train': 2.993468761444092}
-03/03/2022 20:32:50 - INFO - codeparrot_training - Step 6028: {'lr': 0.0004990867269240751, 'samples': 3086848, 'steps': 6028, 'loss/train': 2.275043249130249}
-03/03/2022 20:32:52 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/03/2022 20:32:55 - INFO - codeparrot_training - Step 6029: {'lr': 0.0004990862736819478, 'samples': 3087360, 'steps': 6029, 'loss/train': 2.3293895721435547}
-03/03/2022 20:32:58 - INFO - codeparrot_training - Step 6030: {'lr': 0.000499085820327586, 'samples': 3087872, 'steps': 6030, 'loss/train': 2.558720827102661}
-03/03/2022 20:33:00 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/03/2022 20:33:04 - INFO - codeparrot_training - Step 6031: {'lr': 0.0004990853668609902, 'samples': 3088384, 'steps': 6031, 'loss/train': 2.050902843475342}
-03/03/2022 20:33:07 - INFO - codeparrot_training - Step 6032: {'lr': 0.0004990849132821602, 'samples': 3088896, 'steps': 6032, 'loss/train': 2.907649517059326}
-03/03/2022 20:33:10 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/03/2022 20:33:12 - INFO - codeparrot_training - Step 6033: {'lr': 0.0004990844595910965, 'samples': 3089408, 'steps': 6033, 'loss/train': 2.7963056564331055}
-03/03/2022 20:33:16 - INFO - codeparrot_training - Step 6034: {'lr': 0.0004990840057877991, 'samples': 3089920, 'steps': 6034, 'loss/train': 1.4967728853225708}
-03/03/2022 20:33:18 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/03/2022 20:33:21 - INFO - codeparrot_training - Step 6035: {'lr': 0.0004990835518722683, 'samples': 3090432, 'steps': 6035, 'loss/train': 2.017116069793701}
-03/03/2022 20:33:24 - INFO - codeparrot_training - Step 6036: {'lr': 0.0004990830978445043, 'samples': 3090944, 'steps': 6036, 'loss/train': 2.741785764694214}
-03/03/2022 20:33:27 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/03/2022 20:33:29 - INFO - codeparrot_training - Step 6037: {'lr': 0.0004990826437045073, 'samples': 3091456, 'steps': 6037, 'loss/train': 1.831255555152893}
-03/03/2022 20:33:32 - INFO - codeparrot_training - Step 6038: {'lr': 0.0004990821894522775, 'samples': 3091968, 'steps': 6038, 'loss/train': 1.652116298675537}
-03/03/2022 20:33:35 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/03/2022 20:33:38 - INFO - codeparrot_training - Step 6039: {'lr': 0.0004990817350878152, 'samples': 3092480, 'steps': 6039, 'loss/train': 1.946101188659668}
-03/03/2022 20:33:41 - INFO - codeparrot_training - Step 6040: {'lr': 0.0004990812806111205, 'samples': 3092992, 'steps': 6040, 'loss/train': 2.4598729610443115}
-03/03/2022 20:33:44 - INFO - codeparrot_training - Step 6041: {'lr': 0.0004990808260221934, 'samples': 3093504, 'steps': 6041, 'loss/train': 2.025970697402954}
-03/03/2022 20:33:45 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/03/2022 20:33:50 - INFO - codeparrot_training - Step 6042: {'lr': 0.0004990803713210345, 'samples': 3094016, 'steps': 6042, 'loss/train': 1.9241267442703247}
-03/03/2022 20:33:53 - INFO - codeparrot_training - Step 6043: {'lr': 0.0004990799165076438, 'samples': 3094528, 'steps': 6043, 'loss/train': 2.2200257778167725}
-03/03/2022 20:33:53 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/03/2022 20:33:58 - INFO - codeparrot_training - Step 6044: {'lr': 0.0004990794615820216, 'samples': 3095040, 'steps': 6044, 'loss/train': 0.4130382239818573}
-03/03/2022 20:34:01 - INFO - codeparrot_training - Step 6045: {'lr': 0.0004990790065441679, 'samples': 3095552, 'steps': 6045, 'loss/train': 2.3483567237854004}
-03/03/2022 20:34:02 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/03/2022 20:34:06 - INFO - codeparrot_training - Step 6046: {'lr': 0.0004990785513940832, 'samples': 3096064, 'steps': 6046, 'loss/train': 1.6067311763763428}
-03/03/2022 20:34:10 - INFO - codeparrot_training - Step 6047: {'lr': 0.0004990780961317674, 'samples': 3096576, 'steps': 6047, 'loss/train': 1.731894850730896}
-03/03/2022 20:34:10 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/03/2022 20:34:15 - INFO - codeparrot_training - Step 6048: {'lr': 0.0004990776407572209, 'samples': 3097088, 'steps': 6048, 'loss/train': 2.3042149543762207}
-03/03/2022 20:34:18 - INFO - codeparrot_training - Step 6049: {'lr': 0.000499077185270444, 'samples': 3097600, 'steps': 6049, 'loss/train': 2.5658321380615234}
-03/03/2022 20:34:18 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/03/2022 20:34:23 - INFO - codeparrot_training - Step 6050: {'lr': 0.0004990767296714365, 'samples': 3098112, 'steps': 6050, 'loss/train': 1.9273736476898193}
-03/03/2022 20:34:26 - INFO - codeparrot_training - Step 6051: {'lr': 0.000499076273960199, 'samples': 3098624, 'steps': 6051, 'loss/train': 2.3754098415374756}
-03/03/2022 20:34:26 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/03/2022 20:34:32 - INFO - codeparrot_training - Step 6052: {'lr': 0.0004990758181367316, 'samples': 3099136, 'steps': 6052, 'loss/train': 2.2411000728607178}
-03/03/2022 20:34:35 - INFO - codeparrot_training - Step 6053: {'lr': 0.0004990753622010345, 'samples': 3099648, 'steps': 6053, 'loss/train': 2.187779188156128}
-03/03/2022 20:34:35 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/03/2022 20:34:40 - INFO - codeparrot_training - Step 6054: {'lr': 0.0004990749061531079, 'samples': 3100160, 'steps': 6054, 'loss/train': 4.033575534820557}
-03/03/2022 20:34:43 - INFO - codeparrot_training - Step 6055: {'lr': 0.0004990744499929519, 'samples': 3100672, 'steps': 6055, 'loss/train': 2.439326286315918}
-03/03/2022 20:34:43 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/03/2022 20:34:48 - INFO - codeparrot_training - Step 6056: {'lr': 0.0004990739937205668, 'samples': 3101184, 'steps': 6056, 'loss/train': 2.5789523124694824}
-03/03/2022 20:34:51 - INFO - codeparrot_training - Step 6057: {'lr': 0.0004990735373359529, 'samples': 3101696, 'steps': 6057, 'loss/train': 2.659201145172119}
-03/03/2022 20:34:52 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/03/2022 20:34:57 - INFO - codeparrot_training - Step 6058: {'lr': 0.0004990730808391102, 'samples': 3102208, 'steps': 6058, 'loss/train': 2.1385912895202637}
-03/03/2022 20:35:00 - INFO - codeparrot_training - Step 6059: {'lr': 0.0004990726242300391, 'samples': 3102720, 'steps': 6059, 'loss/train': 2.532478094100952}
-03/03/2022 20:35:00 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/03/2022 20:35:05 - INFO - codeparrot_training - Step 6060: {'lr': 0.0004990721675087397, 'samples': 3103232, 'steps': 6060, 'loss/train': 1.6165353059768677}
-03/03/2022 20:35:08 - INFO - codeparrot_training - Step 6061: {'lr': 0.0004990717106752122, 'samples': 3103744, 'steps': 6061, 'loss/train': 2.6129236221313477}
-03/03/2022 20:35:08 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/03/2022 20:35:14 - INFO - codeparrot_training - Step 6062: {'lr': 0.0004990712537294568, 'samples': 3104256, 'steps': 6062, 'loss/train': 2.672260046005249}
-03/03/2022 20:35:16 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/03/2022 20:35:19 - INFO - codeparrot_training - Step 6063: {'lr': 0.0004990707966714738, 'samples': 3104768, 'steps': 6063, 'loss/train': 1.3979791402816772}
-03/03/2022 20:35:22 - INFO - codeparrot_training - Step 6064: {'lr': 0.0004990703395012634, 'samples': 3105280, 'steps': 6064, 'loss/train': 2.2856409549713135}
-03/03/2022 20:35:25 - INFO - codeparrot_training - Skipping example with length 996 (seq_length=1024)
-03/03/2022 20:35:27 - INFO - codeparrot_training - Step 6065: {'lr': 0.0004990698822188255, 'samples': 3105792, 'steps': 6065, 'loss/train': 1.9129084348678589}
-03/03/2022 20:35:31 - INFO - codeparrot_training - Step 6066: {'lr': 0.0004990694248241608, 'samples': 3106304, 'steps': 6066, 'loss/train': 0.8776193857192993}
-03/03/2022 20:35:33 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/03/2022 20:35:36 - INFO - codeparrot_training - Step 6067: {'lr': 0.0004990689673172691, 'samples': 3106816, 'steps': 6067, 'loss/train': 2.10901141166687}
-03/03/2022 20:35:39 - INFO - codeparrot_training - Step 6068: {'lr': 0.000499068509698151, 'samples': 3107328, 'steps': 6068, 'loss/train': 1.1147937774658203}
-03/03/2022 20:35:42 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/03/2022 20:35:44 - INFO - codeparrot_training - Step 6069: {'lr': 0.0004990680519668063, 'samples': 3107840, 'steps': 6069, 'loss/train': 2.429788827896118}
-03/03/2022 20:35:48 - INFO - codeparrot_training - Step 6070: {'lr': 0.0004990675941232354, 'samples': 3108352, 'steps': 6070, 'loss/train': 2.612416982650757}
-03/03/2022 20:35:50 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/03/2022 20:35:53 - INFO - codeparrot_training - Step 6071: {'lr': 0.0004990671361674384, 'samples': 3108864, 'steps': 6071, 'loss/train': 2.221101760864258}
-03/03/2022 20:35:56 - INFO - codeparrot_training - Step 6072: {'lr': 0.0004990666780994156, 'samples': 3109376, 'steps': 6072, 'loss/train': 3.2366702556610107}
-03/03/2022 20:35:59 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/03/2022 20:36:01 - INFO - codeparrot_training - Step 6073: {'lr': 0.0004990662199191673, 'samples': 3109888, 'steps': 6073, 'loss/train': 2.2891993522644043}
-03/03/2022 20:36:04 - INFO - codeparrot_training - Step 6074: {'lr': 0.0004990657616266936, 'samples': 3110400, 'steps': 6074, 'loss/train': 2.7009429931640625}
-03/03/2022 20:36:07 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/03/2022 20:36:10 - INFO - codeparrot_training - Step 6075: {'lr': 0.0004990653032219947, 'samples': 3110912, 'steps': 6075, 'loss/train': 1.3422727584838867}
-03/03/2022 20:36:13 - INFO - codeparrot_training - Step 6076: {'lr': 0.0004990648447050709, 'samples': 3111424, 'steps': 6076, 'loss/train': 2.073990821838379}
-03/03/2022 20:36:16 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/03/2022 20:36:18 - INFO - codeparrot_training - Step 6077: {'lr': 0.0004990643860759222, 'samples': 3111936, 'steps': 6077, 'loss/train': 2.5653774738311768}
-03/03/2022 20:36:21 - INFO - codeparrot_training - Step 6078: {'lr': 0.0004990639273345489, 'samples': 3112448, 'steps': 6078, 'loss/train': 1.839238166809082}
-03/03/2022 20:36:24 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/03/2022 20:36:27 - INFO - codeparrot_training - Step 6079: {'lr': 0.0004990634684809513, 'samples': 3112960, 'steps': 6079, 'loss/train': 2.380758762359619}
-03/03/2022 20:36:30 - INFO - codeparrot_training - Step 6080: {'lr': 0.0004990630095151296, 'samples': 3113472, 'steps': 6080, 'loss/train': 2.962515354156494}
-03/03/2022 20:36:33 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/03/2022 20:36:35 - INFO - codeparrot_training - Step 6081: {'lr': 0.0004990625504370838, 'samples': 3113984, 'steps': 6081, 'loss/train': 1.839558482170105}
-03/03/2022 20:36:38 - INFO - codeparrot_training - Step 6082: {'lr': 0.0004990620912468143, 'samples': 3114496, 'steps': 6082, 'loss/train': 1.1834748983383179}
-03/03/2022 20:36:41 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/03/2022 20:36:43 - INFO - codeparrot_training - Step 6083: {'lr': 0.0004990616319443214, 'samples': 3115008, 'steps': 6083, 'loss/train': 1.4061524868011475}
-03/03/2022 20:36:47 - INFO - codeparrot_training - Step 6084: {'lr': 0.0004990611725296052, 'samples': 3115520, 'steps': 6084, 'loss/train': 1.0135161876678467}
-03/03/2022 20:36:49 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/03/2022 20:36:52 - INFO - codeparrot_training - Step 6085: {'lr': 0.0004990607130026657, 'samples': 3116032, 'steps': 6085, 'loss/train': 2.2130720615386963}
-03/03/2022 20:36:55 - INFO - codeparrot_training - Step 6086: {'lr': 0.0004990602533635033, 'samples': 3116544, 'steps': 6086, 'loss/train': 2.44204044342041}
-03/03/2022 20:36:58 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/03/2022 20:37:00 - INFO - codeparrot_training - Step 6087: {'lr': 0.0004990597936121182, 'samples': 3117056, 'steps': 6087, 'loss/train': 2.4025394916534424}
-03/03/2022 20:37:03 - INFO - codeparrot_training - Step 6088: {'lr': 0.0004990593337485108, 'samples': 3117568, 'steps': 6088, 'loss/train': 2.3128902912139893}
-03/03/2022 20:37:06 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/03/2022 20:37:09 - INFO - codeparrot_training - Step 6089: {'lr': 0.0004990588737726809, 'samples': 3118080, 'steps': 6089, 'loss/train': 2.6144371032714844}
-03/03/2022 20:37:12 - INFO - codeparrot_training - Step 6090: {'lr': 0.0004990584136846289, 'samples': 3118592, 'steps': 6090, 'loss/train': 3.1101460456848145}
-03/03/2022 20:37:14 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/03/2022 20:37:17 - INFO - codeparrot_training - Step 6091: {'lr': 0.0004990579534843551, 'samples': 3119104, 'steps': 6091, 'loss/train': 2.1446735858917236}
-03/03/2022 20:37:20 - INFO - codeparrot_training - Step 6092: {'lr': 0.0004990574931718597, 'samples': 3119616, 'steps': 6092, 'loss/train': 1.3154057264328003}
-03/03/2022 20:37:22 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/03/2022 20:37:26 - INFO - codeparrot_training - Step 6093: {'lr': 0.0004990570327471427, 'samples': 3120128, 'steps': 6093, 'loss/train': 2.62119197845459}
-03/03/2022 20:37:29 - INFO - codeparrot_training - Step 6094: {'lr': 0.0004990565722102045, 'samples': 3120640, 'steps': 6094, 'loss/train': 2.402252674102783}
-03/03/2022 20:37:31 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/03/2022 20:37:34 - INFO - codeparrot_training - Step 6095: {'lr': 0.0004990561115610452, 'samples': 3121152, 'steps': 6095, 'loss/train': 1.610294222831726}
-03/03/2022 20:37:37 - INFO - codeparrot_training - Step 6096: {'lr': 0.0004990556507996652, 'samples': 3121664, 'steps': 6096, 'loss/train': 2.4509434700012207}
-03/03/2022 20:37:40 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/03/2022 20:37:43 - INFO - codeparrot_training - Step 6097: {'lr': 0.0004990551899260644, 'samples': 3122176, 'steps': 6097, 'loss/train': 3.0909366607666016}
-03/03/2022 20:37:46 - INFO - codeparrot_training - Step 6098: {'lr': 0.0004990547289402433, 'samples': 3122688, 'steps': 6098, 'loss/train': 2.4374639987945557}
-03/03/2022 20:37:49 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/03/2022 20:37:51 - INFO - codeparrot_training - Step 6099: {'lr': 0.0004990542678422019, 'samples': 3123200, 'steps': 6099, 'loss/train': 2.3251841068267822}
-03/03/2022 20:37:54 - INFO - codeparrot_training - Step 6100: {'lr': 0.0004990538066319406, 'samples': 3123712, 'steps': 6100, 'loss/train': 3.1538405418395996}
-03/03/2022 20:37:57 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/03/2022 20:37:59 - INFO - codeparrot_training - Step 6101: {'lr': 0.0004990533453094594, 'samples': 3124224, 'steps': 6101, 'loss/train': 2.216449737548828}
-03/03/2022 20:38:02 - INFO - codeparrot_training - Step 6102: {'lr': 0.0004990528838747586, 'samples': 3124736, 'steps': 6102, 'loss/train': 2.383004665374756}
-03/03/2022 20:38:05 - INFO - codeparrot_training - Skipping example with length 233 (seq_length=1024)
-03/03/2022 20:38:08 - INFO - codeparrot_training - Step 6103: {'lr': 0.0004990524223278384, 'samples': 3125248, 'steps': 6103, 'loss/train': 2.4571712017059326}
-03/03/2022 20:38:11 - INFO - codeparrot_training - Step 6104: {'lr': 0.0004990519606686991, 'samples': 3125760, 'steps': 6104, 'loss/train': 3.328603982925415}
-03/03/2022 20:38:13 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/03/2022 20:38:16 - INFO - codeparrot_training - Step 6105: {'lr': 0.0004990514988973408, 'samples': 3126272, 'steps': 6105, 'loss/train': 2.560626268386841}
-03/03/2022 20:38:19 - INFO - codeparrot_training - Step 6106: {'lr': 0.0004990510370137637, 'samples': 3126784, 'steps': 6106, 'loss/train': 2.240696668624878}
-03/03/2022 20:38:22 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/03/2022 20:38:25 - INFO - codeparrot_training - Step 6107: {'lr': 0.0004990505750179682, 'samples': 3127296, 'steps': 6107, 'loss/train': 1.4208271503448486}
-03/03/2022 20:38:28 - INFO - codeparrot_training - Step 6108: {'lr': 0.0004990501129099542, 'samples': 3127808, 'steps': 6108, 'loss/train': 1.6336369514465332}
-03/03/2022 20:38:30 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/03/2022 20:38:33 - INFO - codeparrot_training - Step 6109: {'lr': 0.000499049650689722, 'samples': 3128320, 'steps': 6109, 'loss/train': 1.59865140914917}
-03/03/2022 20:38:36 - INFO - codeparrot_training - Step 6110: {'lr': 0.000499049188357272, 'samples': 3128832, 'steps': 6110, 'loss/train': 2.16554594039917}
-03/03/2022 20:38:38 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/03/2022 20:38:41 - INFO - codeparrot_training - Step 6111: {'lr': 0.0004990487259126043, 'samples': 3129344, 'steps': 6111, 'loss/train': 2.4684855937957764}
-03/03/2022 20:38:45 - INFO - codeparrot_training - Step 6112: {'lr': 0.0004990482633557189, 'samples': 3129856, 'steps': 6112, 'loss/train': 2.173975706100464}
-03/03/2022 20:38:46 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/03/2022 20:38:50 - INFO - codeparrot_training - Step 6113: {'lr': 0.0004990478006866165, 'samples': 3130368, 'steps': 6113, 'loss/train': 2.3319904804229736}
-03/03/2022 20:38:53 - INFO - codeparrot_training - Step 6114: {'lr': 0.0004990473379052968, 'samples': 3130880, 'steps': 6114, 'loss/train': 2.169363260269165}
-03/03/2022 20:38:55 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/03/2022 20:38:58 - INFO - codeparrot_training - Step 6115: {'lr': 0.0004990468750117602, 'samples': 3131392, 'steps': 6115, 'loss/train': 1.6112982034683228}
-03/03/2022 20:39:01 - INFO - codeparrot_training - Step 6116: {'lr': 0.000499046412006007, 'samples': 3131904, 'steps': 6116, 'loss/train': 1.9523159265518188}
-03/03/2022 20:39:03 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/03/2022 20:39:07 - INFO - codeparrot_training - Step 6117: {'lr': 0.0004990459488880372, 'samples': 3132416, 'steps': 6117, 'loss/train': 2.6416213512420654}
-03/03/2022 20:39:10 - INFO - codeparrot_training - Step 6118: {'lr': 0.0004990454856578513, 'samples': 3132928, 'steps': 6118, 'loss/train': 4.58054256439209}
-03/03/2022 20:39:11 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/03/2022 20:39:15 - INFO - codeparrot_training - Step 6119: {'lr': 0.0004990450223154492, 'samples': 3133440, 'steps': 6119, 'loss/train': 2.313155174255371}
-03/03/2022 20:39:18 - INFO - codeparrot_training - Step 6120: {'lr': 0.0004990445588608313, 'samples': 3133952, 'steps': 6120, 'loss/train': 1.8611916303634644}
-03/03/2022 20:39:20 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/03/2022 20:39:24 - INFO - codeparrot_training - Step 6121: {'lr': 0.0004990440952939979, 'samples': 3134464, 'steps': 6121, 'loss/train': 1.082181692123413}
-03/03/2022 20:39:27 - INFO - codeparrot_training - Step 6122: {'lr': 0.0004990436316149489, 'samples': 3134976, 'steps': 6122, 'loss/train': 1.6546484231948853}
-03/03/2022 20:39:28 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/03/2022 20:39:32 - INFO - codeparrot_training - Step 6123: {'lr': 0.0004990431678236849, 'samples': 3135488, 'steps': 6123, 'loss/train': 2.0677356719970703}
-03/03/2022 20:39:35 - INFO - codeparrot_training - Step 6124: {'lr': 0.0004990427039202057, 'samples': 3136000, 'steps': 6124, 'loss/train': 2.1187832355499268}
-03/03/2022 20:39:37 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/03/2022 20:39:40 - INFO - codeparrot_training - Step 6125: {'lr': 0.0004990422399045117, 'samples': 3136512, 'steps': 6125, 'loss/train': 1.5722014904022217}
-03/03/2022 20:39:44 - INFO - codeparrot_training - Step 6126: {'lr': 0.0004990417757766031, 'samples': 3137024, 'steps': 6126, 'loss/train': 2.4145758152008057}
-03/03/2022 20:39:45 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/03/2022 20:39:49 - INFO - codeparrot_training - Step 6127: {'lr': 0.0004990413115364803, 'samples': 3137536, 'steps': 6127, 'loss/train': 1.5929666757583618}
-03/03/2022 20:39:52 - INFO - codeparrot_training - Step 6128: {'lr': 0.0004990408471841431, 'samples': 3138048, 'steps': 6128, 'loss/train': 2.5493223667144775}
-03/03/2022 20:39:54 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/03/2022 20:39:57 - INFO - codeparrot_training - Step 6129: {'lr': 0.0004990403827195921, 'samples': 3138560, 'steps': 6129, 'loss/train': 1.4510996341705322}
-03/03/2022 20:40:00 - INFO - codeparrot_training - Step 6130: {'lr': 0.0004990399181428273, 'samples': 3139072, 'steps': 6130, 'loss/train': 2.341653823852539}
-03/03/2022 20:40:02 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/03/2022 20:40:06 - INFO - codeparrot_training - Step 6131: {'lr': 0.000499039453453849, 'samples': 3139584, 'steps': 6131, 'loss/train': 2.4958479404449463}
-03/03/2022 20:40:09 - INFO - codeparrot_training - Step 6132: {'lr': 0.0004990389886526573, 'samples': 3140096, 'steps': 6132, 'loss/train': 2.4059855937957764}
-03/03/2022 20:40:10 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/03/2022 20:40:14 - INFO - codeparrot_training - Step 6133: {'lr': 0.0004990385237392524, 'samples': 3140608, 'steps': 6133, 'loss/train': 2.3298754692077637}
-03/03/2022 20:40:17 - INFO - codeparrot_training - Step 6134: {'lr': 0.0004990380587136347, 'samples': 3141120, 'steps': 6134, 'loss/train': 2.1944379806518555}
-03/03/2022 20:40:18 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/03/2022 20:40:23 - INFO - codeparrot_training - Step 6135: {'lr': 0.0004990375935758042, 'samples': 3141632, 'steps': 6135, 'loss/train': 2.539621353149414}
-03/03/2022 20:40:26 - INFO - codeparrot_training - Step 6136: {'lr': 0.0004990371283257613, 'samples': 3142144, 'steps': 6136, 'loss/train': 2.325387954711914}
-03/03/2022 20:40:27 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/03/2022 20:40:31 - INFO - codeparrot_training - Step 6137: {'lr': 0.0004990366629635062, 'samples': 3142656, 'steps': 6137, 'loss/train': 2.857353448867798}
-03/03/2022 20:40:34 - INFO - codeparrot_training - Step 6138: {'lr': 0.0004990361974890388, 'samples': 3143168, 'steps': 6138, 'loss/train': 3.382521867752075}
-03/03/2022 20:40:35 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/03/2022 20:40:39 - INFO - codeparrot_training - Step 6139: {'lr': 0.0004990357319023597, 'samples': 3143680, 'steps': 6139, 'loss/train': 2.7787623405456543}
-03/03/2022 20:40:42 - INFO - codeparrot_training - Step 6140: {'lr': 0.0004990352662034689, 'samples': 3144192, 'steps': 6140, 'loss/train': 2.1473872661590576}
-03/03/2022 20:40:43 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/03/2022 20:40:48 - INFO - codeparrot_training - Step 6141: {'lr': 0.0004990348003923665, 'samples': 3144704, 'steps': 6141, 'loss/train': 1.4186909198760986}
-03/03/2022 20:40:51 - INFO - codeparrot_training - Step 6142: {'lr': 0.000499034334469053, 'samples': 3145216, 'steps': 6142, 'loss/train': 2.46630859375}
-03/03/2022 20:40:51 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/03/2022 20:40:56 - INFO - codeparrot_training - Step 6143: {'lr': 0.0004990338684335285, 'samples': 3145728, 'steps': 6143, 'loss/train': 1.4823112487792969}
-03/03/2022 20:40:59 - INFO - codeparrot_training - Step 6144: {'lr': 0.0004990334022857932, 'samples': 3146240, 'steps': 6144, 'loss/train': 3.3315718173980713}
-03/03/2022 20:41:00 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/03/2022 20:41:05 - INFO - codeparrot_training - Step 6145: {'lr': 0.0004990329360258472, 'samples': 3146752, 'steps': 6145, 'loss/train': 1.2205897569656372}
-03/03/2022 20:41:08 - INFO - codeparrot_training - Step 6146: {'lr': 0.0004990324696536908, 'samples': 3147264, 'steps': 6146, 'loss/train': 2.6050679683685303}
-03/03/2022 20:41:09 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/03/2022 20:41:13 - INFO - codeparrot_training - Step 6147: {'lr': 0.0004990320031693242, 'samples': 3147776, 'steps': 6147, 'loss/train': 1.2663359642028809}
-03/03/2022 20:41:16 - INFO - codeparrot_training - Step 6148: {'lr': 0.0004990315365727476, 'samples': 3148288, 'steps': 6148, 'loss/train': 2.66029691696167}
-03/03/2022 20:41:17 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/03/2022 20:41:22 - INFO - codeparrot_training - Step 6149: {'lr': 0.0004990310698639614, 'samples': 3148800, 'steps': 6149, 'loss/train': 2.322422742843628}
-03/03/2022 20:41:25 - INFO - codeparrot_training - Step 6150: {'lr': 0.0004990306030429655, 'samples': 3149312, 'steps': 6150, 'loss/train': 1.3951808214187622}
-03/03/2022 20:41:26 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/03/2022 20:41:30 - INFO - codeparrot_training - Step 6151: {'lr': 0.0004990301361097603, 'samples': 3149824, 'steps': 6151, 'loss/train': 2.1604785919189453}
-03/03/2022 20:41:33 - INFO - codeparrot_training - Step 6152: {'lr': 0.000499029669064346, 'samples': 3150336, 'steps': 6152, 'loss/train': 2.4002790451049805}
-03/03/2022 20:41:34 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/03/2022 20:41:39 - INFO - codeparrot_training - Step 6153: {'lr': 0.0004990292019067227, 'samples': 3150848, 'steps': 6153, 'loss/train': 1.8125666379928589}
-03/03/2022 20:41:42 - INFO - codeparrot_training - Step 6154: {'lr': 0.0004990287346368908, 'samples': 3151360, 'steps': 6154, 'loss/train': 2.290818929672241}
-03/03/2022 20:41:43 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/03/2022 20:41:47 - INFO - codeparrot_training - Step 6155: {'lr': 0.0004990282672548503, 'samples': 3151872, 'steps': 6155, 'loss/train': 2.790431261062622}
-03/03/2022 20:41:50 - INFO - codeparrot_training - Step 6156: {'lr': 0.0004990277997606016, 'samples': 3152384, 'steps': 6156, 'loss/train': 2.475104331970215}
-03/03/2022 20:41:51 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/03/2022 20:41:55 - INFO - codeparrot_training - Step 6157: {'lr': 0.0004990273321541447, 'samples': 3152896, 'steps': 6157, 'loss/train': 2.6607179641723633}
-03/03/2022 20:41:59 - INFO - codeparrot_training - Step 6158: {'lr': 0.0004990268644354799, 'samples': 3153408, 'steps': 6158, 'loss/train': 2.102003335952759}
-03/03/2022 20:42:00 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/03/2022 20:42:04 - INFO - codeparrot_training - Step 6159: {'lr': 0.0004990263966046075, 'samples': 3153920, 'steps': 6159, 'loss/train': 2.4390130043029785}
-03/03/2022 20:42:07 - INFO - codeparrot_training - Step 6160: {'lr': 0.0004990259286615276, 'samples': 3154432, 'steps': 6160, 'loss/train': 2.9616611003875732}
-03/03/2022 20:42:08 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/03/2022 20:42:12 - INFO - codeparrot_training - Step 6161: {'lr': 0.0004990254606062406, 'samples': 3154944, 'steps': 6161, 'loss/train': 2.303395986557007}
-03/03/2022 20:42:15 - INFO - codeparrot_training - Step 6162: {'lr': 0.0004990249924387465, 'samples': 3155456, 'steps': 6162, 'loss/train': 2.0225024223327637}
-03/03/2022 20:42:16 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/03/2022 20:42:21 - INFO - codeparrot_training - Step 6163: {'lr': 0.0004990245241590455, 'samples': 3155968, 'steps': 6163, 'loss/train': 2.366856336593628}
-03/03/2022 20:42:24 - INFO - codeparrot_training - Step 6164: {'lr': 0.0004990240557671379, 'samples': 3156480, 'steps': 6164, 'loss/train': 2.588548183441162}
-03/03/2022 20:42:25 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/03/2022 20:42:29 - INFO - codeparrot_training - Step 6165: {'lr': 0.000499023587263024, 'samples': 3156992, 'steps': 6165, 'loss/train': 2.3634512424468994}
-03/03/2022 20:42:32 - INFO - codeparrot_training - Step 6166: {'lr': 0.0004990231186467039, 'samples': 3157504, 'steps': 6166, 'loss/train': 2.240680694580078}
-03/03/2022 20:42:33 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/03/2022 20:42:37 - INFO - codeparrot_training - Step 6167: {'lr': 0.0004990226499181778, 'samples': 3158016, 'steps': 6167, 'loss/train': 1.8625762462615967}
-03/03/2022 20:42:40 - INFO - codeparrot_training - Step 6168: {'lr': 0.0004990221810774459, 'samples': 3158528, 'steps': 6168, 'loss/train': 1.7640515565872192}
-03/03/2022 20:42:41 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/03/2022 20:42:46 - INFO - codeparrot_training - Step 6169: {'lr': 0.0004990217121245084, 'samples': 3159040, 'steps': 6169, 'loss/train': 2.017077684402466}
-03/03/2022 20:42:49 - INFO - codeparrot_training - Step 6170: {'lr': 0.0004990212430593657, 'samples': 3159552, 'steps': 6170, 'loss/train': 2.2277987003326416}
-03/03/2022 20:42:50 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/03/2022 20:42:54 - INFO - codeparrot_training - Step 6171: {'lr': 0.0004990207738820178, 'samples': 3160064, 'steps': 6171, 'loss/train': 2.885401964187622}
-03/03/2022 20:42:57 - INFO - codeparrot_training - Step 6172: {'lr': 0.000499020304592465, 'samples': 3160576, 'steps': 6172, 'loss/train': 2.3335936069488525}
-03/03/2022 20:42:59 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/03/2022 20:43:03 - INFO - codeparrot_training - Step 6173: {'lr': 0.0004990198351907075, 'samples': 3161088, 'steps': 6173, 'loss/train': 2.3390843868255615}
-03/03/2022 20:43:06 - INFO - codeparrot_training - Step 6174: {'lr': 0.0004990193656767455, 'samples': 3161600, 'steps': 6174, 'loss/train': 1.890399694442749}
-03/03/2022 20:43:07 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/03/2022 20:43:11 - INFO - codeparrot_training - Step 6175: {'lr': 0.0004990188960505792, 'samples': 3162112, 'steps': 6175, 'loss/train': 2.4247286319732666}
-03/03/2022 20:43:14 - INFO - codeparrot_training - Step 6176: {'lr': 0.0004990184263122088, 'samples': 3162624, 'steps': 6176, 'loss/train': 1.743934988975525}
-03/03/2022 20:43:16 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/03/2022 20:43:20 - INFO - codeparrot_training - Step 6177: {'lr': 0.0004990179564616346, 'samples': 3163136, 'steps': 6177, 'loss/train': 2.547590494155884}
-03/03/2022 20:43:23 - INFO - codeparrot_training - Step 6178: {'lr': 0.0004990174864988566, 'samples': 3163648, 'steps': 6178, 'loss/train': 2.761498212814331}
-03/03/2022 20:43:24 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/03/2022 20:43:28 - INFO - codeparrot_training - Step 6179: {'lr': 0.0004990170164238754, 'samples': 3164160, 'steps': 6179, 'loss/train': 1.5033832788467407}
-03/03/2022 20:43:31 - INFO - codeparrot_training - Step 6180: {'lr': 0.0004990165462366909, 'samples': 3164672, 'steps': 6180, 'loss/train': 2.975973606109619}
-03/03/2022 20:43:33 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/03/2022 20:43:36 - INFO - codeparrot_training - Step 6181: {'lr': 0.0004990160759373033, 'samples': 3165184, 'steps': 6181, 'loss/train': 1.7505279779434204}
-03/03/2022 20:43:39 - INFO - codeparrot_training - Step 6182: {'lr': 0.0004990156055257129, 'samples': 3165696, 'steps': 6182, 'loss/train': 2.9290771484375}
-03/03/2022 20:43:41 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/03/2022 20:43:45 - INFO - codeparrot_training - Step 6183: {'lr': 0.00049901513500192, 'samples': 3166208, 'steps': 6183, 'loss/train': 1.7924516201019287}
-03/03/2022 20:43:48 - INFO - codeparrot_training - Step 6184: {'lr': 0.0004990146643659247, 'samples': 3166720, 'steps': 6184, 'loss/train': 2.166120767593384}
-03/03/2022 20:43:50 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/03/2022 20:43:53 - INFO - codeparrot_training - Step 6185: {'lr': 0.0004990141936177272, 'samples': 3167232, 'steps': 6185, 'loss/train': 2.3524818420410156}
-03/03/2022 20:43:57 - INFO - codeparrot_training - Step 6186: {'lr': 0.0004990137227573278, 'samples': 3167744, 'steps': 6186, 'loss/train': 5.472201347351074}
-03/03/2022 20:43:59 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/03/2022 20:44:02 - INFO - codeparrot_training - Step 6187: {'lr': 0.0004990132517847266, 'samples': 3168256, 'steps': 6187, 'loss/train': 2.4853029251098633}
-03/03/2022 20:44:05 - INFO - codeparrot_training - Step 6188: {'lr': 0.0004990127806999239, 'samples': 3168768, 'steps': 6188, 'loss/train': 2.4280920028686523}
-03/03/2022 20:44:07 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/03/2022 20:44:10 - INFO - codeparrot_training - Step 6189: {'lr': 0.0004990123095029199, 'samples': 3169280, 'steps': 6189, 'loss/train': 1.0468168258666992}
-03/03/2022 20:44:13 - INFO - codeparrot_training - Step 6190: {'lr': 0.0004990118381937148, 'samples': 3169792, 'steps': 6190, 'loss/train': 1.8569896221160889}
-03/03/2022 20:44:16 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/03/2022 20:44:19 - INFO - codeparrot_training - Step 6191: {'lr': 0.0004990113667723088, 'samples': 3170304, 'steps': 6191, 'loss/train': 1.6002891063690186}
-03/03/2022 20:44:22 - INFO - codeparrot_training - Step 6192: {'lr': 0.000499010895238702, 'samples': 3170816, 'steps': 6192, 'loss/train': 1.2694172859191895}
-03/03/2022 20:44:24 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/03/2022 20:44:27 - INFO - codeparrot_training - Step 6193: {'lr': 0.0004990104235928948, 'samples': 3171328, 'steps': 6193, 'loss/train': 2.949695110321045}
-03/03/2022 20:44:30 - INFO - codeparrot_training - Step 6194: {'lr': 0.0004990099518348874, 'samples': 3171840, 'steps': 6194, 'loss/train': 0.3340945541858673}
-03/03/2022 20:44:32 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/03/2022 20:44:35 - INFO - codeparrot_training - Step 6195: {'lr': 0.00049900947996468, 'samples': 3172352, 'steps': 6195, 'loss/train': 1.7109606266021729}
-03/03/2022 20:44:39 - INFO - codeparrot_training - Step 6196: {'lr': 0.0004990090079822726, 'samples': 3172864, 'steps': 6196, 'loss/train': 1.863486409187317}
-03/03/2022 20:44:41 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/03/2022 20:44:44 - INFO - codeparrot_training - Step 6197: {'lr': 0.0004990085358876658, 'samples': 3173376, 'steps': 6197, 'loss/train': 2.488806962966919}
-03/03/2022 20:44:47 - INFO - codeparrot_training - Step 6198: {'lr': 0.0004990080636808595, 'samples': 3173888, 'steps': 6198, 'loss/train': 1.76291024684906}
-03/03/2022 20:44:49 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/03/2022 20:44:52 - INFO - codeparrot_training - Step 6199: {'lr': 0.000499007591361854, 'samples': 3174400, 'steps': 6199, 'loss/train': 1.75571608543396}
-03/03/2022 20:44:56 - INFO - codeparrot_training - Step 6200: {'lr': 0.0004990071189306495, 'samples': 3174912, 'steps': 6200, 'loss/train': 2.1356711387634277}
-03/03/2022 20:44:58 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/03/2022 20:45:01 - INFO - codeparrot_training - Step 6201: {'lr': 0.0004990066463872462, 'samples': 3175424, 'steps': 6201, 'loss/train': 2.347768783569336}
-03/03/2022 20:45:04 - INFO - codeparrot_training - Step 6202: {'lr': 0.0004990061737316445, 'samples': 3175936, 'steps': 6202, 'loss/train': 3.0325467586517334}
-03/03/2022 20:45:06 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/03/2022 20:45:09 - INFO - codeparrot_training - Step 6203: {'lr': 0.0004990057009638443, 'samples': 3176448, 'steps': 6203, 'loss/train': 1.2428457736968994}
-03/03/2022 20:45:12 - INFO - codeparrot_training - Step 6204: {'lr': 0.000499005228083846, 'samples': 3176960, 'steps': 6204, 'loss/train': 1.9620559215545654}
-03/03/2022 20:45:14 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/03/2022 20:45:18 - INFO - codeparrot_training - Step 6205: {'lr': 0.0004990047550916498, 'samples': 3177472, 'steps': 6205, 'loss/train': 2.2380502223968506}
-03/03/2022 20:45:21 - INFO - codeparrot_training - Step 6206: {'lr': 0.000499004281987256, 'samples': 3177984, 'steps': 6206, 'loss/train': 1.8200596570968628}
-03/03/2022 20:45:22 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/03/2022 20:45:27 - INFO - codeparrot_training - Step 6207: {'lr': 0.0004990038087706646, 'samples': 3178496, 'steps': 6207, 'loss/train': 2.309845447540283}
-03/03/2022 20:45:30 - INFO - codeparrot_training - Step 6208: {'lr': 0.000499003335441876, 'samples': 3179008, 'steps': 6208, 'loss/train': 2.4606990814208984}
-03/03/2022 20:45:33 - INFO - codeparrot_training - Step 6209: {'lr': 0.0004990028620008903, 'samples': 3179520, 'steps': 6209, 'loss/train': 0.6190854907035828}
-03/03/2022 20:45:34 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/03/2022 20:45:38 - INFO - codeparrot_training - Step 6210: {'lr': 0.0004990023884477077, 'samples': 3180032, 'steps': 6210, 'loss/train': 2.516733169555664}
-03/03/2022 20:45:41 - INFO - codeparrot_training - Step 6211: {'lr': 0.0004990019147823286, 'samples': 3180544, 'steps': 6211, 'loss/train': 2.574686288833618}
-03/03/2022 20:45:42 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/03/2022 20:45:47 - INFO - codeparrot_training - Step 6212: {'lr': 0.000499001441004753, 'samples': 3181056, 'steps': 6212, 'loss/train': 2.2475485801696777}
-03/03/2022 20:45:50 - INFO - codeparrot_training - Step 6213: {'lr': 0.0004990009671149811, 'samples': 3181568, 'steps': 6213, 'loss/train': 1.3603183031082153}
-03/03/2022 20:45:50 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/03/2022 20:45:55 - INFO - codeparrot_training - Step 6214: {'lr': 0.0004990004931130133, 'samples': 3182080, 'steps': 6214, 'loss/train': 2.2715370655059814}
-03/03/2022 20:45:58 - INFO - codeparrot_training - Step 6215: {'lr': 0.0004990000189988497, 'samples': 3182592, 'steps': 6215, 'loss/train': 2.16569447517395}
-03/03/2022 20:46:00 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/03/2022 20:46:04 - INFO - codeparrot_training - Step 6216: {'lr': 0.0004989995447724907, 'samples': 3183104, 'steps': 6216, 'loss/train': 1.7781529426574707}
-03/03/2022 20:46:07 - INFO - codeparrot_training - Step 6217: {'lr': 0.0004989990704339361, 'samples': 3183616, 'steps': 6217, 'loss/train': 2.19779372215271}
-03/03/2022 20:46:08 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/03/2022 20:46:12 - INFO - codeparrot_training - Step 6218: {'lr': 0.0004989985959831865, 'samples': 3184128, 'steps': 6218, 'loss/train': 1.8604223728179932}
-03/03/2022 20:46:15 - INFO - codeparrot_training - Step 6219: {'lr': 0.0004989981214202419, 'samples': 3184640, 'steps': 6219, 'loss/train': 2.2405221462249756}
-03/03/2022 20:46:16 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/03/2022 20:46:20 - INFO - codeparrot_training - Step 6220: {'lr': 0.0004989976467451026, 'samples': 3185152, 'steps': 6220, 'loss/train': 1.3860856294631958}
-03/03/2022 20:46:24 - INFO - codeparrot_training - Step 6221: {'lr': 0.0004989971719577688, 'samples': 3185664, 'steps': 6221, 'loss/train': 2.661895275115967}
-03/03/2022 20:46:25 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/03/2022 20:46:29 - INFO - codeparrot_training - Step 6222: {'lr': 0.0004989966970582408, 'samples': 3186176, 'steps': 6222, 'loss/train': 1.8178315162658691}
-03/03/2022 20:46:32 - INFO - codeparrot_training - Step 6223: {'lr': 0.0004989962220465187, 'samples': 3186688, 'steps': 6223, 'loss/train': 2.84269380569458}
-03/03/2022 20:46:33 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/03/2022 20:46:37 - INFO - codeparrot_training - Step 6224: {'lr': 0.0004989957469226027, 'samples': 3187200, 'steps': 6224, 'loss/train': 1.939148187637329}
-03/03/2022 20:46:40 - INFO - codeparrot_training - Step 6225: {'lr': 0.0004989952716864931, 'samples': 3187712, 'steps': 6225, 'loss/train': 1.3357027769088745}
-03/03/2022 20:46:41 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/03/2022 20:46:46 - INFO - codeparrot_training - Step 6226: {'lr': 0.00049899479633819, 'samples': 3188224, 'steps': 6226, 'loss/train': 2.10903263092041}
-03/03/2022 20:46:49 - INFO - codeparrot_training - Step 6227: {'lr': 0.0004989943208776938, 'samples': 3188736, 'steps': 6227, 'loss/train': 2.34142804145813}
-03/03/2022 20:46:50 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/03/2022 20:46:54 - INFO - codeparrot_training - Step 6228: {'lr': 0.0004989938453050045, 'samples': 3189248, 'steps': 6228, 'loss/train': 2.0133254528045654}
-03/03/2022 20:46:57 - INFO - codeparrot_training - Step 6229: {'lr': 0.0004989933696201225, 'samples': 3189760, 'steps': 6229, 'loss/train': 1.966806173324585}
-03/03/2022 20:46:58 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/03/2022 20:47:03 - INFO - codeparrot_training - Step 6230: {'lr': 0.0004989928938230478, 'samples': 3190272, 'steps': 6230, 'loss/train': 2.6973683834075928}
-03/03/2022 20:47:06 - INFO - codeparrot_training - Step 6231: {'lr': 0.0004989924179137808, 'samples': 3190784, 'steps': 6231, 'loss/train': 2.023390293121338}
-03/03/2022 20:47:06 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/03/2022 20:47:11 - INFO - codeparrot_training - Step 6232: {'lr': 0.0004989919418923218, 'samples': 3191296, 'steps': 6232, 'loss/train': 2.773195505142212}
-03/03/2022 20:47:14 - INFO - codeparrot_training - Step 6233: {'lr': 0.0004989914657586707, 'samples': 3191808, 'steps': 6233, 'loss/train': 2.968630313873291}
-03/03/2022 20:47:15 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/03/2022 20:47:19 - INFO - codeparrot_training - Step 6234: {'lr': 0.000498990989512828, 'samples': 3192320, 'steps': 6234, 'loss/train': 2.444758176803589}
-03/03/2022 20:47:23 - INFO - codeparrot_training - Step 6235: {'lr': 0.0004989905131547937, 'samples': 3192832, 'steps': 6235, 'loss/train': 2.308685064315796}
-03/03/2022 20:47:23 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/03/2022 20:47:28 - INFO - codeparrot_training - Step 6236: {'lr': 0.0004989900366845682, 'samples': 3193344, 'steps': 6236, 'loss/train': 1.9745601415634155}
-03/03/2022 20:47:31 - INFO - codeparrot_training - Step 6237: {'lr': 0.0004989895601021515, 'samples': 3193856, 'steps': 6237, 'loss/train': 2.3285651206970215}
-03/03/2022 20:47:31 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/03/2022 20:47:36 - INFO - codeparrot_training - Step 6238: {'lr': 0.0004989890834075441, 'samples': 3194368, 'steps': 6238, 'loss/train': 2.5154190063476562}
-03/03/2022 20:47:39 - INFO - codeparrot_training - Step 6239: {'lr': 0.000498988606600746, 'samples': 3194880, 'steps': 6239, 'loss/train': 2.003972291946411}
-03/03/2022 20:47:40 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/03/2022 20:47:45 - INFO - codeparrot_training - Step 6240: {'lr': 0.0004989881296817575, 'samples': 3195392, 'steps': 6240, 'loss/train': 1.8350917100906372}
-03/03/2022 20:47:48 - INFO - codeparrot_training - Step 6241: {'lr': 0.0004989876526505788, 'samples': 3195904, 'steps': 6241, 'loss/train': 2.4774680137634277}
-03/03/2022 20:47:48 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/03/2022 20:47:53 - INFO - codeparrot_training - Step 6242: {'lr': 0.0004989871755072101, 'samples': 3196416, 'steps': 6242, 'loss/train': 2.8453733921051025}
-03/03/2022 20:47:56 - INFO - codeparrot_training - Step 6243: {'lr': 0.0004989866982516516, 'samples': 3196928, 'steps': 6243, 'loss/train': 2.4675402641296387}
-03/03/2022 20:47:56 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/03/2022 20:48:01 - INFO - codeparrot_training - Step 6244: {'lr': 0.0004989862208839035, 'samples': 3197440, 'steps': 6244, 'loss/train': 1.8095650672912598}
-03/03/2022 20:48:05 - INFO - codeparrot_training - Step 6245: {'lr': 0.0004989857434039661, 'samples': 3197952, 'steps': 6245, 'loss/train': 1.4806510210037231}
-03/03/2022 20:48:05 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/03/2022 20:48:10 - INFO - codeparrot_training - Step 6246: {'lr': 0.0004989852658118395, 'samples': 3198464, 'steps': 6246, 'loss/train': 1.498329520225525}
-03/03/2022 20:48:13 - INFO - codeparrot_training - Step 6247: {'lr': 0.000498984788107524, 'samples': 3198976, 'steps': 6247, 'loss/train': 1.2733428478240967}
-03/03/2022 20:48:13 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/03/2022 20:48:18 - INFO - codeparrot_training - Step 6248: {'lr': 0.0004989843102910198, 'samples': 3199488, 'steps': 6248, 'loss/train': 2.2006962299346924}
-03/03/2022 20:48:21 - INFO - codeparrot_training - Step 6249: {'lr': 0.0004989838323623272, 'samples': 3200000, 'steps': 6249, 'loss/train': 2.5182676315307617}
-03/03/2022 20:48:21 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/03/2022 20:48:27 - INFO - codeparrot_training - Step 6250: {'lr': 0.0004989833543214463, 'samples': 3200512, 'steps': 6250, 'loss/train': 2.6438395977020264}
-03/03/2022 20:48:29 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/03/2022 20:48:32 - INFO - codeparrot_training - Step 6251: {'lr': 0.0004989828761683774, 'samples': 3201024, 'steps': 6251, 'loss/train': 2.4378700256347656}
-03/03/2022 20:48:35 - INFO - codeparrot_training - Step 6252: {'lr': 0.0004989823979031205, 'samples': 3201536, 'steps': 6252, 'loss/train': 1.1644235849380493}
-03/03/2022 20:48:38 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/03/2022 20:48:41 - INFO - codeparrot_training - Step 6253: {'lr': 0.000498981919525676, 'samples': 3202048, 'steps': 6253, 'loss/train': 2.055468797683716}
-03/03/2022 20:48:44 - INFO - codeparrot_training - Step 6254: {'lr': 0.0004989814410360442, 'samples': 3202560, 'steps': 6254, 'loss/train': 0.54622483253479}
-03/03/2022 20:48:47 - INFO - codeparrot_training - Step 6255: {'lr': 0.0004989809624342251, 'samples': 3203072, 'steps': 6255, 'loss/train': 2.520233392715454}
-03/03/2022 20:48:47 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/03/2022 20:48:52 - INFO - codeparrot_training - Step 6256: {'lr': 0.000498980483720219, 'samples': 3203584, 'steps': 6256, 'loss/train': 0.594938337802887}
-03/03/2022 20:48:55 - INFO - codeparrot_training - Step 6257: {'lr': 0.0004989800048940263, 'samples': 3204096, 'steps': 6257, 'loss/train': 2.121999979019165}
-03/03/2022 20:48:55 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/03/2022 20:49:01 - INFO - codeparrot_training - Step 6258: {'lr': 0.0004989795259556469, 'samples': 3204608, 'steps': 6258, 'loss/train': 1.4344321489334106}
-03/03/2022 20:49:04 - INFO - codeparrot_training - Step 6259: {'lr': 0.0004989790469050813, 'samples': 3205120, 'steps': 6259, 'loss/train': 1.7187665700912476}
-03/03/2022 20:49:04 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/03/2022 20:49:09 - INFO - codeparrot_training - Step 6260: {'lr': 0.0004989785677423295, 'samples': 3205632, 'steps': 6260, 'loss/train': 2.6005735397338867}
-03/03/2022 20:49:12 - INFO - codeparrot_training - Step 6261: {'lr': 0.0004989780884673917, 'samples': 3206144, 'steps': 6261, 'loss/train': 1.5735480785369873}
-03/03/2022 20:49:12 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/03/2022 20:49:18 - INFO - codeparrot_training - Step 6262: {'lr': 0.0004989776090802683, 'samples': 3206656, 'steps': 6262, 'loss/train': 2.7277681827545166}
-03/03/2022 20:49:21 - INFO - codeparrot_training - Step 6263: {'lr': 0.0004989771295809594, 'samples': 3207168, 'steps': 6263, 'loss/train': 0.2897016406059265}
-03/03/2022 20:49:22 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/03/2022 20:49:26 - INFO - codeparrot_training - Step 6264: {'lr': 0.0004989766499694653, 'samples': 3207680, 'steps': 6264, 'loss/train': 1.3964729309082031}
-03/03/2022 20:49:29 - INFO - codeparrot_training - Step 6265: {'lr': 0.0004989761702457862, 'samples': 3208192, 'steps': 6265, 'loss/train': 1.7696070671081543}
-03/03/2022 20:49:30 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/03/2022 20:49:35 - INFO - codeparrot_training - Step 6266: {'lr': 0.0004989756904099222, 'samples': 3208704, 'steps': 6266, 'loss/train': 2.3840949535369873}
-03/03/2022 20:49:38 - INFO - codeparrot_training - Step 6267: {'lr': 0.0004989752104618736, 'samples': 3209216, 'steps': 6267, 'loss/train': 2.610339879989624}
-03/03/2022 20:49:38 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/03/2022 20:49:43 - INFO - codeparrot_training - Step 6268: {'lr': 0.0004989747304016407, 'samples': 3209728, 'steps': 6268, 'loss/train': 2.4580748081207275}
-03/03/2022 20:49:47 - INFO - codeparrot_training - Step 6269: {'lr': 0.0004989742502292235, 'samples': 3210240, 'steps': 6269, 'loss/train': 1.9429395198822021}
-03/03/2022 20:49:48 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/03/2022 20:49:52 - INFO - codeparrot_training - Step 6270: {'lr': 0.0004989737699446225, 'samples': 3210752, 'steps': 6270, 'loss/train': 1.7609734535217285}
-03/03/2022 20:49:55 - INFO - codeparrot_training - Step 6271: {'lr': 0.0004989732895478376, 'samples': 3211264, 'steps': 6271, 'loss/train': 2.2751927375793457}
-03/03/2022 20:49:57 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/03/2022 20:50:00 - INFO - codeparrot_training - Step 6272: {'lr': 0.0004989728090388693, 'samples': 3211776, 'steps': 6272, 'loss/train': 2.660163164138794}
-03/03/2022 20:50:04 - INFO - codeparrot_training - Step 6273: {'lr': 0.0004989723284177177, 'samples': 3212288, 'steps': 6273, 'loss/train': 1.9132641553878784}
-03/03/2022 20:50:05 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/03/2022 20:50:09 - INFO - codeparrot_training - Step 6274: {'lr': 0.0004989718476843828, 'samples': 3212800, 'steps': 6274, 'loss/train': 2.6534976959228516}
-03/03/2022 20:50:12 - INFO - codeparrot_training - Step 6275: {'lr': 0.0004989713668388652, 'samples': 3213312, 'steps': 6275, 'loss/train': 1.7986778020858765}
-03/03/2022 20:50:13 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/03/2022 20:50:17 - INFO - codeparrot_training - Step 6276: {'lr': 0.000498970885881165, 'samples': 3213824, 'steps': 6276, 'loss/train': 1.0925991535186768}
-03/03/2022 20:50:20 - INFO - codeparrot_training - Step 6277: {'lr': 0.0004989704048112823, 'samples': 3214336, 'steps': 6277, 'loss/train': 2.5122032165527344}
-03/03/2022 20:50:21 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/03/2022 20:50:26 - INFO - codeparrot_training - Step 6278: {'lr': 0.0004989699236292173, 'samples': 3214848, 'steps': 6278, 'loss/train': 1.8825292587280273}
-03/03/2022 20:50:29 - INFO - codeparrot_training - Step 6279: {'lr': 0.0004989694423349704, 'samples': 3215360, 'steps': 6279, 'loss/train': 2.7423291206359863}
-03/03/2022 20:50:30 - INFO - codeparrot_training - Skipping example with length 158 (seq_length=1024)
-03/03/2022 20:50:34 - INFO - codeparrot_training - Step 6280: {'lr': 0.0004989689609285417, 'samples': 3215872, 'steps': 6280, 'loss/train': 2.369450092315674}
-03/03/2022 20:50:37 - INFO - codeparrot_training - Step 6281: {'lr': 0.0004989684794099314, 'samples': 3216384, 'steps': 6281, 'loss/train': 0.4095604419708252}
-03/03/2022 20:50:39 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/03/2022 20:50:43 - INFO - codeparrot_training - Step 6282: {'lr': 0.0004989679977791397, 'samples': 3216896, 'steps': 6282, 'loss/train': 2.5520012378692627}
-03/03/2022 20:50:46 - INFO - codeparrot_training - Step 6283: {'lr': 0.0004989675160361669, 'samples': 3217408, 'steps': 6283, 'loss/train': 1.8052716255187988}
-03/03/2022 20:50:47 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/03/2022 20:50:51 - INFO - codeparrot_training - Step 6284: {'lr': 0.0004989670341810132, 'samples': 3217920, 'steps': 6284, 'loss/train': 2.254209518432617}
-03/03/2022 20:50:54 - INFO - codeparrot_training - Step 6285: {'lr': 0.0004989665522136789, 'samples': 3218432, 'steps': 6285, 'loss/train': 2.8164684772491455}
-03/03/2022 20:50:55 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/03/2022 20:51:00 - INFO - codeparrot_training - Step 6286: {'lr': 0.0004989660701341639, 'samples': 3218944, 'steps': 6286, 'loss/train': 2.2199132442474365}
-03/03/2022 20:51:03 - INFO - codeparrot_training - Step 6287: {'lr': 0.0004989655879424687, 'samples': 3219456, 'steps': 6287, 'loss/train': 2.906851291656494}
-03/03/2022 20:51:04 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/03/2022 20:51:08 - INFO - codeparrot_training - Step 6288: {'lr': 0.0004989651056385936, 'samples': 3219968, 'steps': 6288, 'loss/train': 2.132782459259033}
-03/03/2022 20:51:11 - INFO - codeparrot_training - Step 6289: {'lr': 0.0004989646232225384, 'samples': 3220480, 'steps': 6289, 'loss/train': 2.5209827423095703}
-03/03/2022 20:51:12 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/03/2022 20:51:17 - INFO - codeparrot_training - Step 6290: {'lr': 0.0004989641406943037, 'samples': 3220992, 'steps': 6290, 'loss/train': 2.2728652954101562}
-03/03/2022 20:51:20 - INFO - codeparrot_training - Step 6291: {'lr': 0.0004989636580538896, 'samples': 3221504, 'steps': 6291, 'loss/train': 1.4274194240570068}
-03/03/2022 20:51:20 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/03/2022 20:51:25 - INFO - codeparrot_training - Step 6292: {'lr': 0.0004989631753012964, 'samples': 3222016, 'steps': 6292, 'loss/train': 2.4618029594421387}
-03/03/2022 20:51:28 - INFO - codeparrot_training - Step 6293: {'lr': 0.0004989626924365242, 'samples': 3222528, 'steps': 6293, 'loss/train': 1.735193133354187}
-03/03/2022 20:51:29 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/03/2022 20:51:33 - INFO - codeparrot_training - Step 6294: {'lr': 0.0004989622094595733, 'samples': 3223040, 'steps': 6294, 'loss/train': 1.353961706161499}
-03/03/2022 20:51:37 - INFO - codeparrot_training - Step 6295: {'lr': 0.0004989617263704437, 'samples': 3223552, 'steps': 6295, 'loss/train': 2.509711265563965}
-03/03/2022 20:51:37 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/03/2022 20:51:42 - INFO - codeparrot_training - Step 6296: {'lr': 0.0004989612431691359, 'samples': 3224064, 'steps': 6296, 'loss/train': 2.173008680343628}
-03/03/2022 20:51:45 - INFO - codeparrot_training - Step 6297: {'lr': 0.0004989607598556501, 'samples': 3224576, 'steps': 6297, 'loss/train': 2.2157702445983887}
-03/03/2022 20:51:47 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/03/2022 20:51:50 - INFO - codeparrot_training - Step 6298: {'lr': 0.0004989602764299862, 'samples': 3225088, 'steps': 6298, 'loss/train': 2.2234725952148438}
-03/03/2022 20:51:54 - INFO - codeparrot_training - Step 6299: {'lr': 0.0004989597928921447, 'samples': 3225600, 'steps': 6299, 'loss/train': 2.833264112472534}
-03/03/2022 20:51:55 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/03/2022 20:51:59 - INFO - codeparrot_training - Step 6300: {'lr': 0.0004989593092421258, 'samples': 3226112, 'steps': 6300, 'loss/train': 1.5827668905258179}
-03/03/2022 20:52:02 - INFO - codeparrot_training - Step 6301: {'lr': 0.0004989588254799297, 'samples': 3226624, 'steps': 6301, 'loss/train': 1.3944989442825317}
-03/03/2022 20:52:04 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/03/2022 20:52:07 - INFO - codeparrot_training - Step 6302: {'lr': 0.0004989583416055566, 'samples': 3227136, 'steps': 6302, 'loss/train': 1.6838620901107788}
-03/03/2022 20:52:10 - INFO - codeparrot_training - Step 6303: {'lr': 0.0004989578576190068, 'samples': 3227648, 'steps': 6303, 'loss/train': 2.046480655670166}
-03/03/2022 20:52:12 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/03/2022 20:52:16 - INFO - codeparrot_training - Step 6304: {'lr': 0.0004989573735202802, 'samples': 3228160, 'steps': 6304, 'loss/train': 2.666475534439087}
-03/03/2022 20:52:19 - INFO - codeparrot_training - Step 6305: {'lr': 0.0004989568893093774, 'samples': 3228672, 'steps': 6305, 'loss/train': 1.9173630475997925}
-03/03/2022 20:52:21 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/03/2022 20:52:24 - INFO - codeparrot_training - Step 6306: {'lr': 0.0004989564049862986, 'samples': 3229184, 'steps': 6306, 'loss/train': 1.8658738136291504}
-03/03/2022 20:52:27 - INFO - codeparrot_training - Step 6307: {'lr': 0.0004989559205510436, 'samples': 3229696, 'steps': 6307, 'loss/train': 1.6403448581695557}
-03/03/2022 20:52:29 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/03/2022 20:52:33 - INFO - codeparrot_training - Step 6308: {'lr': 0.000498955436003613, 'samples': 3230208, 'steps': 6308, 'loss/train': 2.517967700958252}
-03/03/2022 20:52:36 - INFO - codeparrot_training - Step 6309: {'lr': 0.0004989549513440071, 'samples': 3230720, 'steps': 6309, 'loss/train': 1.9568941593170166}
-03/03/2022 20:52:40 - INFO - codeparrot_training - Step 6310: {'lr': 0.0004989544665722258, 'samples': 3231232, 'steps': 6310, 'loss/train': 2.225344657897949}
-03/03/2022 20:52:40 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/03/2022 20:52:45 - INFO - codeparrot_training - Step 6311: {'lr': 0.0004989539816882694, 'samples': 3231744, 'steps': 6311, 'loss/train': 2.7504515647888184}
-03/03/2022 20:52:48 - INFO - codeparrot_training - Step 6312: {'lr': 0.0004989534966921382, 'samples': 3232256, 'steps': 6312, 'loss/train': 2.835761547088623}
-03/03/2022 20:52:48 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/03/2022 20:52:53 - INFO - codeparrot_training - Step 6313: {'lr': 0.0004989530115838324, 'samples': 3232768, 'steps': 6313, 'loss/train': 2.5851900577545166}
-03/03/2022 20:52:56 - INFO - codeparrot_training - Step 6314: {'lr': 0.0004989525263633523, 'samples': 3233280, 'steps': 6314, 'loss/train': 2.7130343914031982}
-03/03/2022 20:52:56 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/03/2022 20:53:02 - INFO - codeparrot_training - Step 6315: {'lr': 0.0004989520410306979, 'samples': 3233792, 'steps': 6315, 'loss/train': 2.321082353591919}
-03/03/2022 20:53:05 - INFO - codeparrot_training - Step 6316: {'lr': 0.0004989515555858697, 'samples': 3234304, 'steps': 6316, 'loss/train': 2.282355785369873}
-03/03/2022 20:53:05 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/03/2022 20:53:10 - INFO - codeparrot_training - Step 6317: {'lr': 0.0004989510700288678, 'samples': 3234816, 'steps': 6317, 'loss/train': 1.7323476076126099}
-03/03/2022 20:53:13 - INFO - codeparrot_training - Step 6318: {'lr': 0.0004989505843596922, 'samples': 3235328, 'steps': 6318, 'loss/train': 2.418456554412842}
-03/03/2022 20:53:14 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/03/2022 20:53:19 - INFO - codeparrot_training - Step 6319: {'lr': 0.0004989500985783434, 'samples': 3235840, 'steps': 6319, 'loss/train': 2.0950729846954346}
-03/03/2022 20:53:22 - INFO - codeparrot_training - Step 6320: {'lr': 0.0004989496126848215, 'samples': 3236352, 'steps': 6320, 'loss/train': 3.01448917388916}
-03/03/2022 20:53:22 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/03/2022 20:53:27 - INFO - codeparrot_training - Step 6321: {'lr': 0.0004989491266791268, 'samples': 3236864, 'steps': 6321, 'loss/train': 2.0360255241394043}
-03/03/2022 20:53:30 - INFO - codeparrot_training - Step 6322: {'lr': 0.0004989486405612595, 'samples': 3237376, 'steps': 6322, 'loss/train': 2.921435832977295}
-03/03/2022 20:53:31 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/03/2022 20:53:35 - INFO - codeparrot_training - Step 6323: {'lr': 0.0004989481543312196, 'samples': 3237888, 'steps': 6323, 'loss/train': 2.461198568344116}
-03/03/2022 20:53:39 - INFO - codeparrot_training - Step 6324: {'lr': 0.0004989476679890077, 'samples': 3238400, 'steps': 6324, 'loss/train': 2.3816514015197754}
-03/03/2022 20:53:39 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/03/2022 20:53:44 - INFO - codeparrot_training - Step 6325: {'lr': 0.0004989471815346237, 'samples': 3238912, 'steps': 6325, 'loss/train': 2.5134196281433105}
-03/03/2022 20:53:47 - INFO - codeparrot_training - Step 6326: {'lr': 0.000498946694968068, 'samples': 3239424, 'steps': 6326, 'loss/train': 1.547459602355957}
-03/03/2022 20:53:47 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/03/2022 20:53:52 - INFO - codeparrot_training - Step 6327: {'lr': 0.0004989462082893407, 'samples': 3239936, 'steps': 6327, 'loss/train': 2.3911352157592773}
-03/03/2022 20:53:55 - INFO - codeparrot_training - Step 6328: {'lr': 0.0004989457214984421, 'samples': 3240448, 'steps': 6328, 'loss/train': 1.7608788013458252}
-03/03/2022 20:53:56 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/03/2022 20:54:00 - INFO - codeparrot_training - Step 6329: {'lr': 0.0004989452345953725, 'samples': 3240960, 'steps': 6329, 'loss/train': 2.50258469581604}
-03/03/2022 20:54:04 - INFO - codeparrot_training - Step 6330: {'lr': 0.000498944747580132, 'samples': 3241472, 'steps': 6330, 'loss/train': 2.9317729473114014}
-03/03/2022 20:54:04 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/03/2022 20:54:09 - INFO - codeparrot_training - Step 6331: {'lr': 0.0004989442604527208, 'samples': 3241984, 'steps': 6331, 'loss/train': 1.9183944463729858}
-03/03/2022 20:54:12 - INFO - codeparrot_training - Step 6332: {'lr': 0.0004989437732131391, 'samples': 3242496, 'steps': 6332, 'loss/train': 2.6084985733032227}
-03/03/2022 20:54:13 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/03/2022 20:54:17 - INFO - codeparrot_training - Step 6333: {'lr': 0.0004989432858613873, 'samples': 3243008, 'steps': 6333, 'loss/train': 2.279674530029297}
-03/03/2022 20:54:21 - INFO - codeparrot_training - Step 6334: {'lr': 0.0004989427983974653, 'samples': 3243520, 'steps': 6334, 'loss/train': 3.049919843673706}
-03/03/2022 20:54:22 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/03/2022 20:54:26 - INFO - codeparrot_training - Step 6335: {'lr': 0.0004989423108213737, 'samples': 3244032, 'steps': 6335, 'loss/train': 1.798612356185913}
-03/03/2022 20:54:29 - INFO - codeparrot_training - Step 6336: {'lr': 0.0004989418231331124, 'samples': 3244544, 'steps': 6336, 'loss/train': 2.038389205932617}
-03/03/2022 20:54:30 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/03/2022 20:54:34 - INFO - codeparrot_training - Step 6337: {'lr': 0.0004989413353326818, 'samples': 3245056, 'steps': 6337, 'loss/train': 2.7541017532348633}
-03/03/2022 20:54:37 - INFO - codeparrot_training - Step 6338: {'lr': 0.0004989408474200821, 'samples': 3245568, 'steps': 6338, 'loss/train': 2.3827993869781494}
-03/03/2022 20:54:38 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/03/2022 20:54:43 - INFO - codeparrot_training - Step 6339: {'lr': 0.0004989403593953135, 'samples': 3246080, 'steps': 6339, 'loss/train': 2.6063408851623535}
-03/03/2022 20:54:46 - INFO - codeparrot_training - Step 6340: {'lr': 0.0004989398712583762, 'samples': 3246592, 'steps': 6340, 'loss/train': 0.8572320938110352}
-03/03/2022 20:54:46 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/03/2022 20:54:51 - INFO - codeparrot_training - Step 6341: {'lr': 0.0004989393830092705, 'samples': 3247104, 'steps': 6341, 'loss/train': 1.365817904472351}
-03/03/2022 20:54:55 - INFO - codeparrot_training - Step 6342: {'lr': 0.0004989388946479965, 'samples': 3247616, 'steps': 6342, 'loss/train': 2.2927989959716797}
-03/03/2022 20:54:55 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/03/2022 20:55:00 - INFO - codeparrot_training - Step 6343: {'lr': 0.0004989384061745545, 'samples': 3248128, 'steps': 6343, 'loss/train': 1.7848299741744995}
-03/03/2022 20:55:03 - INFO - codeparrot_training - Step 6344: {'lr': 0.0004989379175889447, 'samples': 3248640, 'steps': 6344, 'loss/train': 1.6363615989685059}
-03/03/2022 20:55:04 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 20:55:08 - INFO - codeparrot_training - Step 6345: {'lr': 0.0004989374288911672, 'samples': 3249152, 'steps': 6345, 'loss/train': 2.3525941371917725}
-03/03/2022 20:55:12 - INFO - codeparrot_training - Step 6346: {'lr': 0.0004989369400812225, 'samples': 3249664, 'steps': 6346, 'loss/train': 2.33884859085083}
-03/03/2022 20:55:12 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/03/2022 20:55:17 - INFO - codeparrot_training - Step 6347: {'lr': 0.0004989364511591106, 'samples': 3250176, 'steps': 6347, 'loss/train': 2.168365240097046}
-03/03/2022 20:55:20 - INFO - codeparrot_training - Step 6348: {'lr': 0.0004989359621248317, 'samples': 3250688, 'steps': 6348, 'loss/train': 1.8395603895187378}
-03/03/2022 20:55:21 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/03/2022 20:55:25 - INFO - codeparrot_training - Step 6349: {'lr': 0.0004989354729783861, 'samples': 3251200, 'steps': 6349, 'loss/train': 0.9847726821899414}
-03/03/2022 20:55:29 - INFO - codeparrot_training - Step 6350: {'lr': 0.0004989349837197742, 'samples': 3251712, 'steps': 6350, 'loss/train': 2.5253071784973145}
-03/03/2022 20:55:29 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/03/2022 20:55:34 - INFO - codeparrot_training - Step 6351: {'lr': 0.0004989344943489958, 'samples': 3252224, 'steps': 6351, 'loss/train': 2.7136709690093994}
-03/03/2022 20:55:37 - INFO - codeparrot_training - Step 6352: {'lr': 0.0004989340048660515, 'samples': 3252736, 'steps': 6352, 'loss/train': 3.0683774948120117}
-03/03/2022 20:55:37 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/03/2022 20:55:42 - INFO - codeparrot_training - Step 6353: {'lr': 0.0004989335152709414, 'samples': 3253248, 'steps': 6353, 'loss/train': 2.0051560401916504}
-03/03/2022 20:55:45 - INFO - codeparrot_training - Step 6354: {'lr': 0.0004989330255636656, 'samples': 3253760, 'steps': 6354, 'loss/train': 0.977173924446106}
-03/03/2022 20:55:46 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/03/2022 20:55:51 - INFO - codeparrot_training - Step 6355: {'lr': 0.0004989325357442245, 'samples': 3254272, 'steps': 6355, 'loss/train': 1.7195558547973633}
-03/03/2022 20:55:54 - INFO - codeparrot_training - Step 6356: {'lr': 0.0004989320458126182, 'samples': 3254784, 'steps': 6356, 'loss/train': 1.902896523475647}
-03/03/2022 20:55:54 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/03/2022 20:55:59 - INFO - codeparrot_training - Step 6357: {'lr': 0.0004989315557688469, 'samples': 3255296, 'steps': 6357, 'loss/train': 1.7432458400726318}
-03/03/2022 20:56:02 - INFO - codeparrot_training - Step 6358: {'lr': 0.000498931065612911, 'samples': 3255808, 'steps': 6358, 'loss/train': 2.299485206604004}
-03/03/2022 20:56:02 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/03/2022 20:56:07 - INFO - codeparrot_training - Step 6359: {'lr': 0.0004989305753448106, 'samples': 3256320, 'steps': 6359, 'loss/train': 2.411892890930176}
-03/03/2022 20:56:11 - INFO - codeparrot_training - Step 6360: {'lr': 0.0004989300849645459, 'samples': 3256832, 'steps': 6360, 'loss/train': 2.0981500148773193}
-03/03/2022 20:56:16 - INFO - codeparrot_training - Step 6361: {'lr': 0.0004989295944721171, 'samples': 3257344, 'steps': 6361, 'loss/train': 0.9874047636985779}
-03/03/2022 20:56:19 - INFO - codeparrot_training - Step 6362: {'lr': 0.0004989291038675245, 'samples': 3257856, 'steps': 6362, 'loss/train': 1.4530138969421387}
-03/03/2022 20:56:24 - INFO - codeparrot_training - Step 6363: {'lr': 0.0004989286131507682, 'samples': 3258368, 'steps': 6363, 'loss/train': 2.370424270629883}
-03/03/2022 20:56:27 - INFO - codeparrot_training - Step 6364: {'lr': 0.0004989281223218486, 'samples': 3258880, 'steps': 6364, 'loss/train': 1.8056330680847168}
-03/03/2022 20:56:27 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/03/2022 20:56:33 - INFO - codeparrot_training - Step 6365: {'lr': 0.0004989276313807658, 'samples': 3259392, 'steps': 6365, 'loss/train': 2.306715488433838}
-03/03/2022 20:56:36 - INFO - codeparrot_training - Step 6366: {'lr': 0.00049892714032752, 'samples': 3259904, 'steps': 6366, 'loss/train': 2.6462624073028564}
-03/03/2022 20:56:36 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/03/2022 20:56:41 - INFO - codeparrot_training - Step 6367: {'lr': 0.0004989266491621117, 'samples': 3260416, 'steps': 6367, 'loss/train': 2.6080658435821533}
-03/03/2022 20:56:44 - INFO - codeparrot_training - Step 6368: {'lr': 0.0004989261578845406, 'samples': 3260928, 'steps': 6368, 'loss/train': 2.320617198944092}
-03/03/2022 20:56:44 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/03/2022 20:56:50 - INFO - codeparrot_training - Step 6369: {'lr': 0.0004989256664948073, 'samples': 3261440, 'steps': 6369, 'loss/train': 1.9459302425384521}
-03/03/2022 20:56:55 - INFO - codeparrot_training - Step 6370: {'lr': 0.000498925174992912, 'samples': 3261952, 'steps': 6370, 'loss/train': 1.8763095140457153}
-03/03/2022 20:56:58 - INFO - codeparrot_training - Step 6371: {'lr': 0.0004989246833788549, 'samples': 3262464, 'steps': 6371, 'loss/train': 2.7081735134124756}
-03/03/2022 20:57:01 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/03/2022 20:57:03 - INFO - codeparrot_training - Step 6372: {'lr': 0.000498924191652636, 'samples': 3262976, 'steps': 6372, 'loss/train': 2.470444440841675}
-03/03/2022 20:57:07 - INFO - codeparrot_training - Step 6373: {'lr': 0.0004989236998142559, 'samples': 3263488, 'steps': 6373, 'loss/train': 2.508986473083496}
-03/03/2022 20:57:09 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/03/2022 20:57:12 - INFO - codeparrot_training - Step 6374: {'lr': 0.0004989232078637145, 'samples': 3264000, 'steps': 6374, 'loss/train': 2.1937944889068604}
-03/03/2022 20:57:15 - INFO - codeparrot_training - Step 6375: {'lr': 0.0004989227158010123, 'samples': 3264512, 'steps': 6375, 'loss/train': 2.5120134353637695}
-03/03/2022 20:57:17 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/03/2022 20:57:20 - INFO - codeparrot_training - Step 6376: {'lr': 0.0004989222236261491, 'samples': 3265024, 'steps': 6376, 'loss/train': 1.675296425819397}
-03/03/2022 20:57:23 - INFO - codeparrot_training - Step 6377: {'lr': 0.0004989217313391256, 'samples': 3265536, 'steps': 6377, 'loss/train': 2.3533177375793457}
-03/03/2022 20:57:26 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/03/2022 20:57:29 - INFO - codeparrot_training - Step 6378: {'lr': 0.0004989212389399417, 'samples': 3266048, 'steps': 6378, 'loss/train': 1.963186502456665}
-03/03/2022 20:57:32 - INFO - codeparrot_training - Step 6379: {'lr': 0.0004989207464285978, 'samples': 3266560, 'steps': 6379, 'loss/train': 1.6243599653244019}
-03/03/2022 20:57:35 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/03/2022 20:57:37 - INFO - codeparrot_training - Step 6380: {'lr': 0.0004989202538050939, 'samples': 3267072, 'steps': 6380, 'loss/train': 1.8548487424850464}
-03/03/2022 20:57:40 - INFO - codeparrot_training - Step 6381: {'lr': 0.0004989197610694306, 'samples': 3267584, 'steps': 6381, 'loss/train': 2.368461847305298}
-03/03/2022 20:57:43 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/03/2022 20:57:45 - INFO - codeparrot_training - Step 6382: {'lr': 0.0004989192682216078, 'samples': 3268096, 'steps': 6382, 'loss/train': 2.5637025833129883}
-03/03/2022 20:57:49 - INFO - codeparrot_training - Step 6383: {'lr': 0.0004989187752616258, 'samples': 3268608, 'steps': 6383, 'loss/train': 1.9119150638580322}
-03/03/2022 20:57:51 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/03/2022 20:57:54 - INFO - codeparrot_training - Step 6384: {'lr': 0.0004989182821894849, 'samples': 3269120, 'steps': 6384, 'loss/train': 2.1735973358154297}
-03/03/2022 20:57:57 - INFO - codeparrot_training - Step 6385: {'lr': 0.0004989177890051852, 'samples': 3269632, 'steps': 6385, 'loss/train': 2.672121047973633}
-03/03/2022 20:57:59 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/03/2022 20:58:02 - INFO - codeparrot_training - Step 6386: {'lr': 0.000498917295708727, 'samples': 3270144, 'steps': 6386, 'loss/train': 2.968601703643799}
-03/03/2022 20:58:05 - INFO - codeparrot_training - Step 6387: {'lr': 0.0004989168023001105, 'samples': 3270656, 'steps': 6387, 'loss/train': 1.856918454170227}
-03/03/2022 20:58:08 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/03/2022 20:58:11 - INFO - codeparrot_training - Step 6388: {'lr': 0.0004989163087793359, 'samples': 3271168, 'steps': 6388, 'loss/train': 2.516350269317627}
-03/03/2022 20:58:14 - INFO - codeparrot_training - Step 6389: {'lr': 0.0004989158151464036, 'samples': 3271680, 'steps': 6389, 'loss/train': 2.8001089096069336}
-03/03/2022 20:58:17 - INFO - codeparrot_training - Step 6390: {'lr': 0.0004989153214013135, 'samples': 3272192, 'steps': 6390, 'loss/train': 2.4537477493286133}
-03/03/2022 20:58:17 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/03/2022 20:58:22 - INFO - codeparrot_training - Step 6391: {'lr': 0.0004989148275440661, 'samples': 3272704, 'steps': 6391, 'loss/train': 1.5718554258346558}
-03/03/2022 20:58:25 - INFO - codeparrot_training - Step 6392: {'lr': 0.0004989143335746614, 'samples': 3273216, 'steps': 6392, 'loss/train': 2.789022207260132}
-03/03/2022 20:58:26 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/03/2022 20:58:31 - INFO - codeparrot_training - Step 6393: {'lr': 0.0004989138394930998, 'samples': 3273728, 'steps': 6393, 'loss/train': 2.7695538997650146}
-03/03/2022 20:58:34 - INFO - codeparrot_training - Step 6394: {'lr': 0.0004989133452993816, 'samples': 3274240, 'steps': 6394, 'loss/train': 2.67276668548584}
-03/03/2022 20:58:34 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/03/2022 20:58:39 - INFO - codeparrot_training - Step 6395: {'lr': 0.0004989128509935068, 'samples': 3274752, 'steps': 6395, 'loss/train': 2.4885854721069336}
-03/03/2022 20:58:42 - INFO - codeparrot_training - Step 6396: {'lr': 0.0004989123565754756, 'samples': 3275264, 'steps': 6396, 'loss/train': 2.1067821979522705}
-03/03/2022 20:58:42 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/03/2022 20:58:48 - INFO - codeparrot_training - Step 6397: {'lr': 0.0004989118620452884, 'samples': 3275776, 'steps': 6397, 'loss/train': 1.192299246788025}
-03/03/2022 20:58:51 - INFO - codeparrot_training - Step 6398: {'lr': 0.0004989113674029454, 'samples': 3276288, 'steps': 6398, 'loss/train': 2.2594637870788574}
-03/03/2022 20:58:51 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/03/2022 20:58:56 - INFO - codeparrot_training - Step 6399: {'lr': 0.0004989108726484469, 'samples': 3276800, 'steps': 6399, 'loss/train': 2.3479182720184326}
-03/03/2022 20:58:59 - INFO - codeparrot_training - Step 6400: {'lr': 0.0004989103777817928, 'samples': 3277312, 'steps': 6400, 'loss/train': 2.3107264041900635}
-03/03/2022 20:58:59 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/03/2022 20:59:05 - INFO - codeparrot_training - Step 6401: {'lr': 0.0004989098828029836, 'samples': 3277824, 'steps': 6401, 'loss/train': 1.7044341564178467}
-03/03/2022 20:59:08 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/03/2022 20:59:10 - INFO - codeparrot_training - Step 6402: {'lr': 0.0004989093877120194, 'samples': 3278336, 'steps': 6402, 'loss/train': 1.9980262517929077}
-03/03/2022 20:59:13 - INFO - codeparrot_training - Step 6403: {'lr': 0.0004989088925089005, 'samples': 3278848, 'steps': 6403, 'loss/train': 2.8343803882598877}
-03/03/2022 20:59:16 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/03/2022 20:59:18 - INFO - codeparrot_training - Step 6404: {'lr': 0.0004989083971936271, 'samples': 3279360, 'steps': 6404, 'loss/train': 2.7451746463775635}
-03/03/2022 20:59:22 - INFO - codeparrot_training - Step 6405: {'lr': 0.0004989079017661994, 'samples': 3279872, 'steps': 6405, 'loss/train': 1.9217240810394287}
-03/03/2022 20:59:24 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/03/2022 20:59:27 - INFO - codeparrot_training - Step 6406: {'lr': 0.0004989074062266177, 'samples': 3280384, 'steps': 6406, 'loss/train': 1.9594695568084717}
-03/03/2022 20:59:30 - INFO - codeparrot_training - Step 6407: {'lr': 0.0004989069105748821, 'samples': 3280896, 'steps': 6407, 'loss/train': 2.1456735134124756}
-03/03/2022 20:59:33 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/03/2022 20:59:35 - INFO - codeparrot_training - Step 6408: {'lr': 0.0004989064148109929, 'samples': 3281408, 'steps': 6408, 'loss/train': 1.8808311223983765}
-03/03/2022 20:59:38 - INFO - codeparrot_training - Step 6409: {'lr': 0.0004989059189349503, 'samples': 3281920, 'steps': 6409, 'loss/train': 1.9036916494369507}
-03/03/2022 20:59:41 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/03/2022 20:59:44 - INFO - codeparrot_training - Step 6410: {'lr': 0.0004989054229467546, 'samples': 3282432, 'steps': 6410, 'loss/train': 1.1947904825210571}
-03/03/2022 20:59:47 - INFO - codeparrot_training - Step 6411: {'lr': 0.0004989049268464058, 'samples': 3282944, 'steps': 6411, 'loss/train': 6.999931812286377}
-03/03/2022 20:59:50 - INFO - codeparrot_training - Step 6412: {'lr': 0.0004989044306339044, 'samples': 3283456, 'steps': 6412, 'loss/train': 1.2371643781661987}
-03/03/2022 20:59:50 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/03/2022 20:59:55 - INFO - codeparrot_training - Step 6413: {'lr': 0.0004989039343092505, 'samples': 3283968, 'steps': 6413, 'loss/train': 2.622718095779419}
-03/03/2022 20:59:58 - INFO - codeparrot_training - Step 6414: {'lr': 0.0004989034378724443, 'samples': 3284480, 'steps': 6414, 'loss/train': 2.3205511569976807}
-03/03/2022 20:59:58 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/03/2022 21:00:04 - INFO - codeparrot_training - Step 6415: {'lr': 0.0004989029413234861, 'samples': 3284992, 'steps': 6415, 'loss/train': 1.6952251195907593}
-03/03/2022 21:00:07 - INFO - codeparrot_training - Step 6416: {'lr': 0.000498902444662376, 'samples': 3285504, 'steps': 6416, 'loss/train': 2.7979843616485596}
-03/03/2022 21:00:07 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/03/2022 21:00:12 - INFO - codeparrot_training - Step 6417: {'lr': 0.0004989019478891144, 'samples': 3286016, 'steps': 6417, 'loss/train': 1.4823482036590576}
-03/03/2022 21:00:15 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/03/2022 21:00:18 - INFO - codeparrot_training - Step 6418: {'lr': 0.0004989014510037013, 'samples': 3286528, 'steps': 6418, 'loss/train': 1.928804874420166}
-03/03/2022 21:00:21 - INFO - codeparrot_training - Step 6419: {'lr': 0.0004989009540061373, 'samples': 3287040, 'steps': 6419, 'loss/train': 1.870906949043274}
-03/03/2022 21:00:24 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/03/2022 21:00:26 - INFO - codeparrot_training - Step 6420: {'lr': 0.0004989004568964221, 'samples': 3287552, 'steps': 6420, 'loss/train': 2.060333013534546}
-03/03/2022 21:00:29 - INFO - codeparrot_training - Step 6421: {'lr': 0.0004988999596745562, 'samples': 3288064, 'steps': 6421, 'loss/train': 1.9893051385879517}
-03/03/2022 21:00:33 - INFO - codeparrot_training - Step 6422: {'lr': 0.00049889946234054, 'samples': 3288576, 'steps': 6422, 'loss/train': 2.5777547359466553}
-03/03/2022 21:00:33 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/03/2022 21:00:38 - INFO - codeparrot_training - Step 6423: {'lr': 0.0004988989648943734, 'samples': 3289088, 'steps': 6423, 'loss/train': 1.5791939496994019}
-03/03/2022 21:00:41 - INFO - codeparrot_training - Step 6424: {'lr': 0.0004988984673360568, 'samples': 3289600, 'steps': 6424, 'loss/train': 1.523354411125183}
-03/03/2022 21:00:41 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/03/2022 21:00:46 - INFO - codeparrot_training - Step 6425: {'lr': 0.0004988979696655904, 'samples': 3290112, 'steps': 6425, 'loss/train': 2.619152069091797}
-03/03/2022 21:00:50 - INFO - codeparrot_training - Step 6426: {'lr': 0.0004988974718829744, 'samples': 3290624, 'steps': 6426, 'loss/train': 1.3865485191345215}
-03/03/2022 21:00:50 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/03/2022 21:00:55 - INFO - codeparrot_training - Step 6427: {'lr': 0.0004988969739882091, 'samples': 3291136, 'steps': 6427, 'loss/train': 1.883314609527588}
-03/03/2022 21:00:58 - INFO - codeparrot_training - Step 6428: {'lr': 0.0004988964759812946, 'samples': 3291648, 'steps': 6428, 'loss/train': 2.4664769172668457}
-03/03/2022 21:00:58 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/03/2022 21:01:03 - INFO - codeparrot_training - Step 6429: {'lr': 0.0004988959778622313, 'samples': 3292160, 'steps': 6429, 'loss/train': 1.7429019212722778}
-03/03/2022 21:01:06 - INFO - codeparrot_training - Step 6430: {'lr': 0.0004988954796310191, 'samples': 3292672, 'steps': 6430, 'loss/train': 2.9246394634246826}
-03/03/2022 21:01:06 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/03/2022 21:01:12 - INFO - codeparrot_training - Step 6431: {'lr': 0.0004988949812876586, 'samples': 3293184, 'steps': 6431, 'loss/train': 1.8939025402069092}
-03/03/2022 21:01:15 - INFO - codeparrot_training - Step 6432: {'lr': 0.0004988944828321499, 'samples': 3293696, 'steps': 6432, 'loss/train': 2.013906717300415}
-03/03/2022 21:01:15 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/03/2022 21:01:20 - INFO - codeparrot_training - Step 6433: {'lr': 0.0004988939842644931, 'samples': 3294208, 'steps': 6433, 'loss/train': 2.9599008560180664}
-03/03/2022 21:01:23 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/03/2022 21:01:25 - INFO - codeparrot_training - Step 6434: {'lr': 0.0004988934855846885, 'samples': 3294720, 'steps': 6434, 'loss/train': 1.8178502321243286}
-03/03/2022 21:01:29 - INFO - codeparrot_training - Step 6435: {'lr': 0.0004988929867927363, 'samples': 3295232, 'steps': 6435, 'loss/train': 1.914137363433838}
-03/03/2022 21:01:31 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/03/2022 21:01:34 - INFO - codeparrot_training - Step 6436: {'lr': 0.0004988924878886368, 'samples': 3295744, 'steps': 6436, 'loss/train': 2.2263500690460205}
-03/03/2022 21:01:37 - INFO - codeparrot_training - Step 6437: {'lr': 0.0004988919888723902, 'samples': 3296256, 'steps': 6437, 'loss/train': 1.768996000289917}
-03/03/2022 21:01:40 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/03/2022 21:01:43 - INFO - codeparrot_training - Step 6438: {'lr': 0.0004988914897439968, 'samples': 3296768, 'steps': 6438, 'loss/train': 2.1612155437469482}
-03/03/2022 21:01:46 - INFO - codeparrot_training - Step 6439: {'lr': 0.0004988909905034566, 'samples': 3297280, 'steps': 6439, 'loss/train': 1.267844319343567}
-03/03/2022 21:01:48 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/03/2022 21:01:51 - INFO - codeparrot_training - Step 6440: {'lr': 0.00049889049115077, 'samples': 3297792, 'steps': 6440, 'loss/train': 1.0336602926254272}
-03/03/2022 21:01:54 - INFO - codeparrot_training - Step 6441: {'lr': 0.0004988899916859372, 'samples': 3298304, 'steps': 6441, 'loss/train': 3.233128309249878}
-03/03/2022 21:01:57 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/03/2022 21:02:00 - INFO - codeparrot_training - Step 6442: {'lr': 0.0004988894921089584, 'samples': 3298816, 'steps': 6442, 'loss/train': 1.4633071422576904}
-03/03/2022 21:02:03 - INFO - codeparrot_training - Step 6443: {'lr': 0.0004988889924198339, 'samples': 3299328, 'steps': 6443, 'loss/train': 2.26615834236145}
-03/03/2022 21:02:05 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/03/2022 21:02:08 - INFO - codeparrot_training - Step 6444: {'lr': 0.0004988884926185637, 'samples': 3299840, 'steps': 6444, 'loss/train': 2.764521837234497}
-03/03/2022 21:02:11 - INFO - codeparrot_training - Step 6445: {'lr': 0.0004988879927051484, 'samples': 3300352, 'steps': 6445, 'loss/train': 1.925256371498108}
-03/03/2022 21:02:14 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/03/2022 21:02:17 - INFO - codeparrot_training - Step 6446: {'lr': 0.0004988874926795878, 'samples': 3300864, 'steps': 6446, 'loss/train': 2.451085090637207}
-03/03/2022 21:02:20 - INFO - codeparrot_training - Step 6447: {'lr': 0.0004988869925418825, 'samples': 3301376, 'steps': 6447, 'loss/train': 2.4380507469177246}
-03/03/2022 21:02:22 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/03/2022 21:02:25 - INFO - codeparrot_training - Step 6448: {'lr': 0.0004988864922920325, 'samples': 3301888, 'steps': 6448, 'loss/train': 0.9805120825767517}
-03/03/2022 21:02:28 - INFO - codeparrot_training - Step 6449: {'lr': 0.000498885991930038, 'samples': 3302400, 'steps': 6449, 'loss/train': 0.24303893744945526}
-03/03/2022 21:02:31 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/03/2022 21:02:33 - INFO - codeparrot_training - Step 6450: {'lr': 0.0004988854914558994, 'samples': 3302912, 'steps': 6450, 'loss/train': 1.9996763467788696}
-03/03/2022 21:02:36 - INFO - codeparrot_training - Step 6451: {'lr': 0.0004988849908696169, 'samples': 3303424, 'steps': 6451, 'loss/train': 2.553051471710205}
-03/03/2022 21:02:39 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/03/2022 21:02:42 - INFO - codeparrot_training - Step 6452: {'lr': 0.0004988844901711905, 'samples': 3303936, 'steps': 6452, 'loss/train': 2.4464914798736572}
-03/03/2022 21:02:45 - INFO - codeparrot_training - Step 6453: {'lr': 0.0004988839893606208, 'samples': 3304448, 'steps': 6453, 'loss/train': 2.4733078479766846}
-03/03/2022 21:02:47 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/03/2022 21:02:50 - INFO - codeparrot_training - Step 6454: {'lr': 0.0004988834884379076, 'samples': 3304960, 'steps': 6454, 'loss/train': 2.495654582977295}
-03/03/2022 21:02:53 - INFO - codeparrot_training - Step 6455: {'lr': 0.0004988829874030514, 'samples': 3305472, 'steps': 6455, 'loss/train': 2.550448417663574}
-03/03/2022 21:02:56 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/03/2022 21:02:59 - INFO - codeparrot_training - Step 6456: {'lr': 0.0004988824862560525, 'samples': 3305984, 'steps': 6456, 'loss/train': 2.2732746601104736}
-03/03/2022 21:03:02 - INFO - codeparrot_training - Step 6457: {'lr': 0.0004988819849969109, 'samples': 3306496, 'steps': 6457, 'loss/train': 2.1804237365722656}
-03/03/2022 21:03:05 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/03/2022 21:03:07 - INFO - codeparrot_training - Step 6458: {'lr': 0.0004988814836256269, 'samples': 3307008, 'steps': 6458, 'loss/train': 1.1961863040924072}
-03/03/2022 21:03:10 - INFO - codeparrot_training - Step 6459: {'lr': 0.0004988809821422008, 'samples': 3307520, 'steps': 6459, 'loss/train': 1.8975602388381958}
-03/03/2022 21:03:14 - INFO - codeparrot_training - Step 6460: {'lr': 0.0004988804805466327, 'samples': 3308032, 'steps': 6460, 'loss/train': 2.4054148197174072}
-03/03/2022 21:03:14 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/03/2022 21:03:19 - INFO - codeparrot_training - Step 6461: {'lr': 0.000498879978838923, 'samples': 3308544, 'steps': 6461, 'loss/train': 2.3226969242095947}
-03/03/2022 21:03:22 - INFO - codeparrot_training - Step 6462: {'lr': 0.0004988794770190717, 'samples': 3309056, 'steps': 6462, 'loss/train': 2.69224214553833}
-03/03/2022 21:03:23 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/03/2022 21:03:28 - INFO - codeparrot_training - Step 6463: {'lr': 0.0004988789750870792, 'samples': 3309568, 'steps': 6463, 'loss/train': 2.6305108070373535}
-03/03/2022 21:03:31 - INFO - codeparrot_training - Step 6464: {'lr': 0.0004988784730429457, 'samples': 3310080, 'steps': 6464, 'loss/train': 2.4213852882385254}
-03/03/2022 21:03:32 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/03/2022 21:03:36 - INFO - codeparrot_training - Step 6465: {'lr': 0.0004988779708866714, 'samples': 3310592, 'steps': 6465, 'loss/train': 2.8825879096984863}
-03/03/2022 21:03:39 - INFO - codeparrot_training - Step 6466: {'lr': 0.0004988774686182564, 'samples': 3311104, 'steps': 6466, 'loss/train': 1.7672717571258545}
-03/03/2022 21:03:40 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/03/2022 21:03:44 - INFO - codeparrot_training - Step 6467: {'lr': 0.0004988769662377013, 'samples': 3311616, 'steps': 6467, 'loss/train': 2.7845757007598877}
-03/03/2022 21:03:48 - INFO - codeparrot_training - Step 6468: {'lr': 0.0004988764637450058, 'samples': 3312128, 'steps': 6468, 'loss/train': 1.8784935474395752}
-03/03/2022 21:03:49 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/03/2022 21:03:53 - INFO - codeparrot_training - Step 6469: {'lr': 0.0004988759611401706, 'samples': 3312640, 'steps': 6469, 'loss/train': 2.107921838760376}
-03/03/2022 21:03:56 - INFO - codeparrot_training - Step 6470: {'lr': 0.0004988754584231957, 'samples': 3313152, 'steps': 6470, 'loss/train': 2.1971731185913086}
-03/03/2022 21:03:57 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/03/2022 21:04:01 - INFO - codeparrot_training - Step 6471: {'lr': 0.0004988749555940814, 'samples': 3313664, 'steps': 6471, 'loss/train': 3.4534313678741455}
-03/03/2022 21:04:04 - INFO - codeparrot_training - Step 6472: {'lr': 0.0004988744526528277, 'samples': 3314176, 'steps': 6472, 'loss/train': 3.0255205631256104}
-03/03/2022 21:04:05 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/03/2022 21:04:10 - INFO - codeparrot_training - Step 6473: {'lr': 0.0004988739495994352, 'samples': 3314688, 'steps': 6473, 'loss/train': 2.5638561248779297}
-03/03/2022 21:04:13 - INFO - codeparrot_training - Step 6474: {'lr': 0.0004988734464339038, 'samples': 3315200, 'steps': 6474, 'loss/train': 2.2296833992004395}
-03/03/2022 21:04:14 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/03/2022 21:04:18 - INFO - codeparrot_training - Step 6475: {'lr': 0.0004988729431562339, 'samples': 3315712, 'steps': 6475, 'loss/train': 0.6018031239509583}
-03/03/2022 21:04:21 - INFO - codeparrot_training - Step 6476: {'lr': 0.0004988724397664258, 'samples': 3316224, 'steps': 6476, 'loss/train': 2.8655710220336914}
-03/03/2022 21:04:22 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/03/2022 21:04:27 - INFO - codeparrot_training - Step 6477: {'lr': 0.0004988719362644795, 'samples': 3316736, 'steps': 6477, 'loss/train': 0.9072401523590088}
-03/03/2022 21:04:30 - INFO - codeparrot_training - Step 6478: {'lr': 0.0004988714326503953, 'samples': 3317248, 'steps': 6478, 'loss/train': 2.519273519515991}
-03/03/2022 21:04:31 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/03/2022 21:04:35 - INFO - codeparrot_training - Step 6479: {'lr': 0.0004988709289241736, 'samples': 3317760, 'steps': 6479, 'loss/train': 3.018913507461548}
-03/03/2022 21:04:38 - INFO - codeparrot_training - Step 6480: {'lr': 0.0004988704250858145, 'samples': 3318272, 'steps': 6480, 'loss/train': 2.2635140419006348}
-03/03/2022 21:04:39 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/03/2022 21:04:43 - INFO - codeparrot_training - Step 6481: {'lr': 0.0004988699211353182, 'samples': 3318784, 'steps': 6481, 'loss/train': 3.144435167312622}
-03/03/2022 21:04:47 - INFO - codeparrot_training - Step 6482: {'lr': 0.000498869417072685, 'samples': 3319296, 'steps': 6482, 'loss/train': 1.9408161640167236}
-03/03/2022 21:04:48 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/03/2022 21:04:52 - INFO - codeparrot_training - Step 6483: {'lr': 0.000498868912897915, 'samples': 3319808, 'steps': 6483, 'loss/train': 1.8240959644317627}
-03/03/2022 21:04:55 - INFO - codeparrot_training - Step 6484: {'lr': 0.0004988684086110085, 'samples': 3320320, 'steps': 6484, 'loss/train': 1.2873865365982056}
-03/03/2022 21:04:56 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/03/2022 21:05:00 - INFO - codeparrot_training - Step 6485: {'lr': 0.0004988679042119658, 'samples': 3320832, 'steps': 6485, 'loss/train': 3.0930018424987793}
-03/03/2022 21:05:03 - INFO - codeparrot_training - Step 6486: {'lr': 0.000498867399700787, 'samples': 3321344, 'steps': 6486, 'loss/train': 2.4545767307281494}
-03/03/2022 21:05:04 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/03/2022 21:05:09 - INFO - codeparrot_training - Step 6487: {'lr': 0.0004988668950774724, 'samples': 3321856, 'steps': 6487, 'loss/train': 2.4992291927337646}
-03/03/2022 21:05:12 - INFO - codeparrot_training - Step 6488: {'lr': 0.0004988663903420222, 'samples': 3322368, 'steps': 6488, 'loss/train': 2.5385584831237793}
-03/03/2022 21:05:12 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/03/2022 21:05:17 - INFO - codeparrot_training - Step 6489: {'lr': 0.0004988658854944367, 'samples': 3322880, 'steps': 6489, 'loss/train': 1.6518436670303345}
-03/03/2022 21:05:20 - INFO - codeparrot_training - Step 6490: {'lr': 0.0004988653805347161, 'samples': 3323392, 'steps': 6490, 'loss/train': 1.293764591217041}
-03/03/2022 21:05:21 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/03/2022 21:05:25 - INFO - codeparrot_training - Step 6491: {'lr': 0.0004988648754628605, 'samples': 3323904, 'steps': 6491, 'loss/train': 2.647922992706299}
-03/03/2022 21:05:29 - INFO - codeparrot_training - Step 6492: {'lr': 0.0004988643702788703, 'samples': 3324416, 'steps': 6492, 'loss/train': 1.901336908340454}
-03/03/2022 21:05:29 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/03/2022 21:05:34 - INFO - codeparrot_training - Step 6493: {'lr': 0.0004988638649827456, 'samples': 3324928, 'steps': 6493, 'loss/train': 1.9603252410888672}
-03/03/2022 21:05:37 - INFO - codeparrot_training - Step 6494: {'lr': 0.0004988633595744867, 'samples': 3325440, 'steps': 6494, 'loss/train': 2.6891472339630127}
-03/03/2022 21:05:38 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/03/2022 21:05:42 - INFO - codeparrot_training - Step 6495: {'lr': 0.0004988628540540939, 'samples': 3325952, 'steps': 6495, 'loss/train': 1.7432398796081543}
-03/03/2022 21:05:45 - INFO - codeparrot_training - Step 6496: {'lr': 0.0004988623484215673, 'samples': 3326464, 'steps': 6496, 'loss/train': 1.6818630695343018}
-03/03/2022 21:05:46 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/03/2022 21:05:51 - INFO - codeparrot_training - Step 6497: {'lr': 0.0004988618426769071, 'samples': 3326976, 'steps': 6497, 'loss/train': 2.7220098972320557}
-03/03/2022 21:05:54 - INFO - codeparrot_training - Step 6498: {'lr': 0.0004988613368201135, 'samples': 3327488, 'steps': 6498, 'loss/train': 1.2131065130233765}
-03/03/2022 21:05:54 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/03/2022 21:05:59 - INFO - codeparrot_training - Step 6499: {'lr': 0.0004988608308511871, 'samples': 3328000, 'steps': 6499, 'loss/train': 2.3366036415100098}
-03/03/2022 21:06:02 - INFO - codeparrot_training - Step 6500: {'lr': 0.0004988603247701276, 'samples': 3328512, 'steps': 6500, 'loss/train': 2.074669599533081}
-03/03/2022 21:06:02 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/03/2022 21:06:07 - INFO - codeparrot_training - Step 6501: {'lr': 0.0004988598185769357, 'samples': 3329024, 'steps': 6501, 'loss/train': 2.1880767345428467}
-03/03/2022 21:06:10 - INFO - codeparrot_training - Step 6502: {'lr': 0.0004988593122716112, 'samples': 3329536, 'steps': 6502, 'loss/train': 2.2384355068206787}
-03/03/2022 21:06:11 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/03/2022 21:06:16 - INFO - codeparrot_training - Step 6503: {'lr': 0.0004988588058541547, 'samples': 3330048, 'steps': 6503, 'loss/train': 1.9511898756027222}
-03/03/2022 21:06:19 - INFO - codeparrot_training - Step 6504: {'lr': 0.0004988582993245661, 'samples': 3330560, 'steps': 6504, 'loss/train': 3.008357048034668}
-03/03/2022 21:06:19 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/03/2022 21:06:24 - INFO - codeparrot_training - Step 6505: {'lr': 0.0004988577926828459, 'samples': 3331072, 'steps': 6505, 'loss/train': 2.2622764110565186}
-03/03/2022 21:06:27 - INFO - codeparrot_training - Step 6506: {'lr': 0.0004988572859289941, 'samples': 3331584, 'steps': 6506, 'loss/train': 2.4097535610198975}
-03/03/2022 21:06:28 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/03/2022 21:06:33 - INFO - codeparrot_training - Step 6507: {'lr': 0.0004988567790630111, 'samples': 3332096, 'steps': 6507, 'loss/train': 2.304816246032715}
-03/03/2022 21:06:36 - INFO - codeparrot_training - Step 6508: {'lr': 0.0004988562720848973, 'samples': 3332608, 'steps': 6508, 'loss/train': 2.602184295654297}
-03/03/2022 21:06:36 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/03/2022 21:06:41 - INFO - codeparrot_training - Step 6509: {'lr': 0.0004988557649946525, 'samples': 3333120, 'steps': 6509, 'loss/train': 1.6131110191345215}
-03/03/2022 21:06:44 - INFO - codeparrot_training - Step 6510: {'lr': 0.000498855257792277, 'samples': 3333632, 'steps': 6510, 'loss/train': 2.5564444065093994}
-03/03/2022 21:06:44 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/03/2022 21:06:49 - INFO - codeparrot_training - Step 6511: {'lr': 0.0004988547504777714, 'samples': 3334144, 'steps': 6511, 'loss/train': 2.538755416870117}
-03/03/2022 21:06:53 - INFO - codeparrot_training - Step 6512: {'lr': 0.0004988542430511356, 'samples': 3334656, 'steps': 6512, 'loss/train': 2.201091766357422}
-03/03/2022 21:06:54 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/03/2022 21:06:58 - INFO - codeparrot_training - Step 6513: {'lr': 0.0004988537355123699, 'samples': 3335168, 'steps': 6513, 'loss/train': 2.574005126953125}
-03/03/2022 21:07:01 - INFO - codeparrot_training - Step 6514: {'lr': 0.0004988532278614745, 'samples': 3335680, 'steps': 6514, 'loss/train': 2.514988899230957}
-03/03/2022 21:07:02 - INFO - codeparrot_training - Skipping example with length 996 (seq_length=1024)
-03/03/2022 21:07:06 - INFO - codeparrot_training - Step 6515: {'lr': 0.0004988527200984498, 'samples': 3336192, 'steps': 6515, 'loss/train': 2.146331548690796}
-03/03/2022 21:07:09 - INFO - codeparrot_training - Step 6516: {'lr': 0.0004988522122232958, 'samples': 3336704, 'steps': 6516, 'loss/train': 2.369011402130127}
-03/03/2022 21:07:10 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/03/2022 21:07:15 - INFO - codeparrot_training - Step 6517: {'lr': 0.0004988517042360128, 'samples': 3337216, 'steps': 6517, 'loss/train': 1.9399923086166382}
-03/03/2022 21:07:18 - INFO - codeparrot_training - Step 6518: {'lr': 0.0004988511961366012, 'samples': 3337728, 'steps': 6518, 'loss/train': 2.620999813079834}
-03/03/2022 21:07:19 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/03/2022 21:07:23 - INFO - codeparrot_training - Step 6519: {'lr': 0.000498850687925061, 'samples': 3338240, 'steps': 6519, 'loss/train': 2.343343496322632}
-03/03/2022 21:07:26 - INFO - codeparrot_training - Step 6520: {'lr': 0.0004988501796013926, 'samples': 3338752, 'steps': 6520, 'loss/train': 1.8620699644088745}
-03/03/2022 21:07:27 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/03/2022 21:07:31 - INFO - codeparrot_training - Step 6521: {'lr': 0.0004988496711655961, 'samples': 3339264, 'steps': 6521, 'loss/train': 1.744204044342041}
-03/03/2022 21:07:35 - INFO - codeparrot_training - Step 6522: {'lr': 0.0004988491626176718, 'samples': 3339776, 'steps': 6522, 'loss/train': 1.8044859170913696}
-03/03/2022 21:07:35 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/03/2022 21:07:40 - INFO - codeparrot_training - Step 6523: {'lr': 0.0004988486539576198, 'samples': 3340288, 'steps': 6523, 'loss/train': 1.9109277725219727}
-03/03/2022 21:07:43 - INFO - codeparrot_training - Step 6524: {'lr': 0.0004988481451854406, 'samples': 3340800, 'steps': 6524, 'loss/train': 2.171459197998047}
-03/03/2022 21:07:44 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/03/2022 21:07:48 - INFO - codeparrot_training - Step 6525: {'lr': 0.0004988476363011341, 'samples': 3341312, 'steps': 6525, 'loss/train': 1.9778205156326294}
-03/03/2022 21:07:52 - INFO - codeparrot_training - Step 6526: {'lr': 0.0004988471273047008, 'samples': 3341824, 'steps': 6526, 'loss/train': 1.862902283668518}
-03/03/2022 21:07:52 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/03/2022 21:07:57 - INFO - codeparrot_training - Step 6527: {'lr': 0.0004988466181961408, 'samples': 3342336, 'steps': 6527, 'loss/train': 2.067506790161133}
-03/03/2022 21:08:00 - INFO - codeparrot_training - Step 6528: {'lr': 0.0004988461089754544, 'samples': 3342848, 'steps': 6528, 'loss/train': 2.1913199424743652}
-03/03/2022 21:08:01 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/03/2022 21:08:05 - INFO - codeparrot_training - Step 6529: {'lr': 0.0004988455996426418, 'samples': 3343360, 'steps': 6529, 'loss/train': 1.3450466394424438}
-03/03/2022 21:08:09 - INFO - codeparrot_training - Step 6530: {'lr': 0.0004988450901977031, 'samples': 3343872, 'steps': 6530, 'loss/train': 2.311232805252075}
-03/03/2022 21:08:09 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/03/2022 21:08:14 - INFO - codeparrot_training - Step 6531: {'lr': 0.0004988445806406387, 'samples': 3344384, 'steps': 6531, 'loss/train': 2.6677675247192383}
-03/03/2022 21:08:17 - INFO - codeparrot_training - Step 6532: {'lr': 0.0004988440709714487, 'samples': 3344896, 'steps': 6532, 'loss/train': 1.536584496498108}
-03/03/2022 21:08:18 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/03/2022 21:08:22 - INFO - codeparrot_training - Step 6533: {'lr': 0.0004988435611901335, 'samples': 3345408, 'steps': 6533, 'loss/train': 1.4507062435150146}
-03/03/2022 21:08:25 - INFO - codeparrot_training - Step 6534: {'lr': 0.0004988430512966932, 'samples': 3345920, 'steps': 6534, 'loss/train': 2.429377794265747}
-03/03/2022 21:08:27 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/03/2022 21:08:31 - INFO - codeparrot_training - Step 6535: {'lr': 0.000498842541291128, 'samples': 3346432, 'steps': 6535, 'loss/train': 2.557305335998535}
-03/03/2022 21:08:34 - INFO - codeparrot_training - Step 6536: {'lr': 0.0004988420311734383, 'samples': 3346944, 'steps': 6536, 'loss/train': 2.038231372833252}
-03/03/2022 21:08:35 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/03/2022 21:08:39 - INFO - codeparrot_training - Step 6537: {'lr': 0.0004988415209436243, 'samples': 3347456, 'steps': 6537, 'loss/train': 2.269022226333618}
-03/03/2022 21:08:42 - INFO - codeparrot_training - Step 6538: {'lr': 0.000498841010601686, 'samples': 3347968, 'steps': 6538, 'loss/train': 2.460724353790283}
-03/03/2022 21:08:43 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/03/2022 21:08:47 - INFO - codeparrot_training - Step 6539: {'lr': 0.0004988405001476237, 'samples': 3348480, 'steps': 6539, 'loss/train': 1.9588154554367065}
-03/03/2022 21:08:51 - INFO - codeparrot_training - Step 6540: {'lr': 0.0004988399895814378, 'samples': 3348992, 'steps': 6540, 'loss/train': 1.551700472831726}
-03/03/2022 21:08:51 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/03/2022 21:08:56 - INFO - codeparrot_training - Step 6541: {'lr': 0.0004988394789031286, 'samples': 3349504, 'steps': 6541, 'loss/train': 2.023022174835205}
-03/03/2022 21:08:59 - INFO - codeparrot_training - Step 6542: {'lr': 0.000498838968112696, 'samples': 3350016, 'steps': 6542, 'loss/train': 2.2320499420166016}
-03/03/2022 21:08:59 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/03/2022 21:09:04 - INFO - codeparrot_training - Step 6543: {'lr': 0.0004988384572101403, 'samples': 3350528, 'steps': 6543, 'loss/train': 2.893156051635742}
-03/03/2022 21:09:08 - INFO - codeparrot_training - Step 6544: {'lr': 0.000498837946195462, 'samples': 3351040, 'steps': 6544, 'loss/train': 2.1429500579833984}
-03/03/2022 21:09:09 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/03/2022 21:09:13 - INFO - codeparrot_training - Step 6545: {'lr': 0.0004988374350686611, 'samples': 3351552, 'steps': 6545, 'loss/train': 2.2390708923339844}
-03/03/2022 21:09:16 - INFO - codeparrot_training - Step 6546: {'lr': 0.000498836923829738, 'samples': 3352064, 'steps': 6546, 'loss/train': 2.7015621662139893}
-03/03/2022 21:09:19 - INFO - codeparrot_training - Step 6547: {'lr': 0.0004988364124786927, 'samples': 3352576, 'steps': 6547, 'loss/train': 1.8767491579055786}
-03/03/2022 21:09:20 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/03/2022 21:09:25 - INFO - codeparrot_training - Step 6548: {'lr': 0.0004988359010155255, 'samples': 3353088, 'steps': 6548, 'loss/train': 2.5802431106567383}
-03/03/2022 21:09:28 - INFO - codeparrot_training - Step 6549: {'lr': 0.0004988353894402368, 'samples': 3353600, 'steps': 6549, 'loss/train': 1.757941484451294}
-03/03/2022 21:09:28 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/03/2022 21:09:33 - INFO - codeparrot_training - Step 6550: {'lr': 0.0004988348777528267, 'samples': 3354112, 'steps': 6550, 'loss/train': 1.991750955581665}
-03/03/2022 21:09:37 - INFO - codeparrot_training - Step 6551: {'lr': 0.0004988343659532954, 'samples': 3354624, 'steps': 6551, 'loss/train': 1.9630433320999146}
-03/03/2022 21:09:37 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/03/2022 21:09:42 - INFO - codeparrot_training - Step 6552: {'lr': 0.0004988338540416432, 'samples': 3355136, 'steps': 6552, 'loss/train': 2.395146608352661}
-03/03/2022 21:09:45 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/03/2022 21:09:47 - INFO - codeparrot_training - Step 6553: {'lr': 0.0004988333420178704, 'samples': 3355648, 'steps': 6553, 'loss/train': 2.117727041244507}
-03/03/2022 21:09:50 - INFO - codeparrot_training - Step 6554: {'lr': 0.000498832829881977, 'samples': 3356160, 'steps': 6554, 'loss/train': 2.5915939807891846}
-03/03/2022 21:09:53 - INFO - codeparrot_training - Step 6555: {'lr': 0.0004988323176339633, 'samples': 3356672, 'steps': 6555, 'loss/train': 2.3809609413146973}
-03/03/2022 21:09:53 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/03/2022 21:09:59 - INFO - codeparrot_training - Step 6556: {'lr': 0.0004988318052738298, 'samples': 3357184, 'steps': 6556, 'loss/train': 1.6205410957336426}
-03/03/2022 21:10:02 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/03/2022 21:10:04 - INFO - codeparrot_training - Step 6557: {'lr': 0.0004988312928015763, 'samples': 3357696, 'steps': 6557, 'loss/train': 1.523863434791565}
-03/03/2022 21:10:07 - INFO - codeparrot_training - Step 6558: {'lr': 0.0004988307802172035, 'samples': 3358208, 'steps': 6558, 'loss/train': 1.161320686340332}
-03/03/2022 21:10:10 - INFO - codeparrot_training - Step 6559: {'lr': 0.0004988302675207112, 'samples': 3358720, 'steps': 6559, 'loss/train': 1.4041107892990112}
-03/03/2022 21:10:10 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/03/2022 21:10:16 - INFO - codeparrot_training - Step 6560: {'lr': 0.0004988297547121, 'samples': 3359232, 'steps': 6560, 'loss/train': 2.476445436477661}
-03/03/2022 21:10:18 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/03/2022 21:10:21 - INFO - codeparrot_training - Step 6561: {'lr': 0.0004988292417913698, 'samples': 3359744, 'steps': 6561, 'loss/train': 2.0442745685577393}
-03/03/2022 21:10:24 - INFO - codeparrot_training - Step 6562: {'lr': 0.0004988287287585211, 'samples': 3360256, 'steps': 6562, 'loss/train': 2.49768328666687}
-03/03/2022 21:10:27 - INFO - codeparrot_training - Step 6563: {'lr': 0.0004988282156135539, 'samples': 3360768, 'steps': 6563, 'loss/train': 0.47885796427726746}
-03/03/2022 21:10:27 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/03/2022 21:10:33 - INFO - codeparrot_training - Step 6564: {'lr': 0.0004988277023564685, 'samples': 3361280, 'steps': 6564, 'loss/train': 3.287323474884033}
-03/03/2022 21:10:35 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/03/2022 21:10:38 - INFO - codeparrot_training - Step 6565: {'lr': 0.0004988271889872654, 'samples': 3361792, 'steps': 6565, 'loss/train': 1.6442556381225586}
-03/03/2022 21:10:41 - INFO - codeparrot_training - Step 6566: {'lr': 0.0004988266755059444, 'samples': 3362304, 'steps': 6566, 'loss/train': 2.435594081878662}
-03/03/2022 21:10:44 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/03/2022 21:10:46 - INFO - codeparrot_training - Step 6567: {'lr': 0.000498826161912506, 'samples': 3362816, 'steps': 6567, 'loss/train': 2.116987705230713}
-03/03/2022 21:10:49 - INFO - codeparrot_training - Step 6568: {'lr': 0.0004988256482069505, 'samples': 3363328, 'steps': 6568, 'loss/train': 2.60686993598938}
-03/03/2022 21:10:53 - INFO - codeparrot_training - Step 6569: {'lr': 0.0004988251343892779, 'samples': 3363840, 'steps': 6569, 'loss/train': 2.045839786529541}
-03/03/2022 21:10:53 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/03/2022 21:10:58 - INFO - codeparrot_training - Step 6570: {'lr': 0.0004988246204594885, 'samples': 3364352, 'steps': 6570, 'loss/train': 2.1735448837280273}
-03/03/2022 21:11:01 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/03/2022 21:11:03 - INFO - codeparrot_training - Step 6571: {'lr': 0.0004988241064175826, 'samples': 3364864, 'steps': 6571, 'loss/train': 2.0926365852355957}
-03/03/2022 21:11:06 - INFO - codeparrot_training - Step 6572: {'lr': 0.0004988235922635604, 'samples': 3365376, 'steps': 6572, 'loss/train': 1.367182970046997}
-03/03/2022 21:11:09 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/03/2022 21:11:11 - INFO - codeparrot_training - Step 6573: {'lr': 0.0004988230779974221, 'samples': 3365888, 'steps': 6573, 'loss/train': 1.5925177335739136}
-03/03/2022 21:11:15 - INFO - codeparrot_training - Step 6574: {'lr': 0.000498822563619168, 'samples': 3366400, 'steps': 6574, 'loss/train': 2.362691879272461}
-03/03/2022 21:11:17 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/03/2022 21:11:20 - INFO - codeparrot_training - Step 6575: {'lr': 0.0004988220491287983, 'samples': 3366912, 'steps': 6575, 'loss/train': 2.2567930221557617}
-03/03/2022 21:11:23 - INFO - codeparrot_training - Step 6576: {'lr': 0.0004988215345263132, 'samples': 3367424, 'steps': 6576, 'loss/train': 2.8819925785064697}
-03/03/2022 21:11:25 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/03/2022 21:11:28 - INFO - codeparrot_training - Step 6577: {'lr': 0.0004988210198117129, 'samples': 3367936, 'steps': 6577, 'loss/train': 1.6718159914016724}
-03/03/2022 21:11:31 - INFO - codeparrot_training - Step 6578: {'lr': 0.0004988205049849978, 'samples': 3368448, 'steps': 6578, 'loss/train': 1.4955260753631592}
-03/03/2022 21:11:34 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/03/2022 21:11:37 - INFO - codeparrot_training - Step 6579: {'lr': 0.0004988199900461679, 'samples': 3368960, 'steps': 6579, 'loss/train': 2.2238399982452393}
-03/03/2022 21:11:40 - INFO - codeparrot_training - Step 6580: {'lr': 0.0004988194749952237, 'samples': 3369472, 'steps': 6580, 'loss/train': 1.8757917881011963}
-03/03/2022 21:11:43 - INFO - codeparrot_training - Step 6581: {'lr': 0.0004988189598321652, 'samples': 3369984, 'steps': 6581, 'loss/train': 1.6384801864624023}
-03/03/2022 21:11:43 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/03/2022 21:11:49 - INFO - codeparrot_training - Step 6582: {'lr': 0.0004988184445569926, 'samples': 3370496, 'steps': 6582, 'loss/train': 2.63874888420105}
-03/03/2022 21:11:52 - INFO - codeparrot_training - Step 6583: {'lr': 0.0004988179291697064, 'samples': 3371008, 'steps': 6583, 'loss/train': 2.98421573638916}
-03/03/2022 21:11:52 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/03/2022 21:11:57 - INFO - codeparrot_training - Step 6584: {'lr': 0.0004988174136703066, 'samples': 3371520, 'steps': 6584, 'loss/train': 2.3455967903137207}
-03/03/2022 21:12:00 - INFO - codeparrot_training - Step 6585: {'lr': 0.0004988168980587936, 'samples': 3372032, 'steps': 6585, 'loss/train': 2.678478479385376}
-03/03/2022 21:12:00 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/03/2022 21:12:06 - INFO - codeparrot_training - Step 6586: {'lr': 0.0004988163823351676, 'samples': 3372544, 'steps': 6586, 'loss/train': 1.668660044670105}
-03/03/2022 21:12:08 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/03/2022 21:12:11 - INFO - codeparrot_training - Step 6587: {'lr': 0.0004988158664994286, 'samples': 3373056, 'steps': 6587, 'loss/train': 2.1577322483062744}
-03/03/2022 21:12:14 - INFO - codeparrot_training - Step 6588: {'lr': 0.0004988153505515771, 'samples': 3373568, 'steps': 6588, 'loss/train': 2.1791064739227295}
-03/03/2022 21:12:17 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/03/2022 21:12:19 - INFO - codeparrot_training - Step 6589: {'lr': 0.0004988148344916133, 'samples': 3374080, 'steps': 6589, 'loss/train': 2.038213014602661}
-03/03/2022 21:12:22 - INFO - codeparrot_training - Step 6590: {'lr': 0.0004988143183195373, 'samples': 3374592, 'steps': 6590, 'loss/train': 2.0964183807373047}
-03/03/2022 21:12:25 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/03/2022 21:12:28 - INFO - codeparrot_training - Step 6591: {'lr': 0.0004988138020353493, 'samples': 3375104, 'steps': 6591, 'loss/train': 2.2094545364379883}
-03/03/2022 21:12:31 - INFO - codeparrot_training - Step 6592: {'lr': 0.0004988132856390498, 'samples': 3375616, 'steps': 6592, 'loss/train': 2.6354236602783203}
-03/03/2022 21:12:33 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/03/2022 21:12:36 - INFO - codeparrot_training - Step 6593: {'lr': 0.0004988127691306388, 'samples': 3376128, 'steps': 6593, 'loss/train': 2.19405198097229}
-03/03/2022 21:12:39 - INFO - codeparrot_training - Step 6594: {'lr': 0.0004988122525101166, 'samples': 3376640, 'steps': 6594, 'loss/train': 1.6483142375946045}
-03/03/2022 21:12:43 - INFO - codeparrot_training - Step 6595: {'lr': 0.0004988117357774835, 'samples': 3377152, 'steps': 6595, 'loss/train': 2.0559792518615723}
-03/03/2022 21:12:43 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/03/2022 21:12:48 - INFO - codeparrot_training - Step 6596: {'lr': 0.0004988112189327397, 'samples': 3377664, 'steps': 6596, 'loss/train': 1.3848752975463867}
-03/03/2022 21:12:51 - INFO - codeparrot_training - Step 6597: {'lr': 0.0004988107019758853, 'samples': 3378176, 'steps': 6597, 'loss/train': 0.7391183376312256}
-03/03/2022 21:12:51 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/03/2022 21:12:56 - INFO - codeparrot_training - Step 6598: {'lr': 0.0004988101849069208, 'samples': 3378688, 'steps': 6598, 'loss/train': 2.278961658477783}
-03/03/2022 21:12:59 - INFO - codeparrot_training - Step 6599: {'lr': 0.0004988096677258461, 'samples': 3379200, 'steps': 6599, 'loss/train': 3.022095203399658}
-03/03/2022 21:13:00 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/03/2022 21:13:05 - INFO - codeparrot_training - Step 6600: {'lr': 0.0004988091504326616, 'samples': 3379712, 'steps': 6600, 'loss/train': 2.0845117568969727}
-03/03/2022 21:13:08 - INFO - codeparrot_training - Step 6601: {'lr': 0.0004988086330273676, 'samples': 3380224, 'steps': 6601, 'loss/train': 2.482897996902466}
-03/03/2022 21:13:08 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/03/2022 21:13:13 - INFO - codeparrot_training - Step 6602: {'lr': 0.0004988081155099643, 'samples': 3380736, 'steps': 6602, 'loss/train': 2.7341067790985107}
-03/03/2022 21:13:16 - INFO - codeparrot_training - Step 6603: {'lr': 0.0004988075978804518, 'samples': 3381248, 'steps': 6603, 'loss/train': 2.716170310974121}
-03/03/2022 21:13:16 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/03/2022 21:13:21 - INFO - codeparrot_training - Step 6604: {'lr': 0.0004988070801388306, 'samples': 3381760, 'steps': 6604, 'loss/train': 2.448582172393799}
-03/03/2022 21:13:25 - INFO - codeparrot_training - Step 6605: {'lr': 0.0004988065622851006, 'samples': 3382272, 'steps': 6605, 'loss/train': 2.0948257446289062}
-03/03/2022 21:13:25 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/03/2022 21:13:30 - INFO - codeparrot_training - Step 6606: {'lr': 0.0004988060443192623, 'samples': 3382784, 'steps': 6606, 'loss/train': 1.8325560092926025}
-03/03/2022 21:13:33 - INFO - codeparrot_training - Step 6607: {'lr': 0.0004988055262413158, 'samples': 3383296, 'steps': 6607, 'loss/train': 2.312236785888672}
-03/03/2022 21:13:33 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/03/2022 21:13:38 - INFO - codeparrot_training - Step 6608: {'lr': 0.0004988050080512614, 'samples': 3383808, 'steps': 6608, 'loss/train': 1.8086998462677002}
-03/03/2022 21:13:41 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/03/2022 21:13:44 - INFO - codeparrot_training - Step 6609: {'lr': 0.0004988044897490993, 'samples': 3384320, 'steps': 6609, 'loss/train': 2.415382146835327}
-03/03/2022 21:13:47 - INFO - codeparrot_training - Step 6610: {'lr': 0.0004988039713348297, 'samples': 3384832, 'steps': 6610, 'loss/train': 2.296203136444092}
-03/03/2022 21:13:50 - INFO - codeparrot_training - Step 6611: {'lr': 0.0004988034528084529, 'samples': 3385344, 'steps': 6611, 'loss/train': 0.7161005735397339}
-03/03/2022 21:13:55 - INFO - codeparrot_training - Step 6612: {'lr': 0.000498802934169969, 'samples': 3385856, 'steps': 6612, 'loss/train': 2.8337013721466064}
-03/03/2022 21:13:58 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/03/2022 21:14:01 - INFO - codeparrot_training - Step 6613: {'lr': 0.0004988024154193785, 'samples': 3386368, 'steps': 6613, 'loss/train': 2.3530170917510986}
-03/03/2022 21:14:04 - INFO - codeparrot_training - Step 6614: {'lr': 0.0004988018965566814, 'samples': 3386880, 'steps': 6614, 'loss/train': 0.3959251344203949}
-03/03/2022 21:14:06 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/03/2022 21:14:09 - INFO - codeparrot_training - Step 6615: {'lr': 0.000498801377581878, 'samples': 3387392, 'steps': 6615, 'loss/train': 1.7760858535766602}
-03/03/2022 21:14:12 - INFO - codeparrot_training - Step 6616: {'lr': 0.0004988008584949686, 'samples': 3387904, 'steps': 6616, 'loss/train': 2.349846839904785}
-03/03/2022 21:14:15 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/03/2022 21:14:18 - INFO - codeparrot_training - Step 6617: {'lr': 0.0004988003392959533, 'samples': 3388416, 'steps': 6617, 'loss/train': 2.1081113815307617}
-03/03/2022 21:14:21 - INFO - codeparrot_training - Step 6618: {'lr': 0.0004987998199848324, 'samples': 3388928, 'steps': 6618, 'loss/train': 1.1254477500915527}
-03/03/2022 21:14:23 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/03/2022 21:14:26 - INFO - codeparrot_training - Step 6619: {'lr': 0.0004987993005616061, 'samples': 3389440, 'steps': 6619, 'loss/train': 2.7877416610717773}
-03/03/2022 21:14:29 - INFO - codeparrot_training - Step 6620: {'lr': 0.0004987987810262747, 'samples': 3389952, 'steps': 6620, 'loss/train': 2.387789726257324}
-03/03/2022 21:14:32 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/03/2022 21:14:34 - INFO - codeparrot_training - Step 6621: {'lr': 0.0004987982613788384, 'samples': 3390464, 'steps': 6621, 'loss/train': 2.8375375270843506}
-03/03/2022 21:14:38 - INFO - codeparrot_training - Step 6622: {'lr': 0.0004987977416192976, 'samples': 3390976, 'steps': 6622, 'loss/train': 2.255270481109619}
-03/03/2022 21:14:40 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/03/2022 21:14:43 - INFO - codeparrot_training - Step 6623: {'lr': 0.0004987972217476523, 'samples': 3391488, 'steps': 6623, 'loss/train': 2.783151388168335}
-03/03/2022 21:14:46 - INFO - codeparrot_training - Step 6624: {'lr': 0.0004987967017639027, 'samples': 3392000, 'steps': 6624, 'loss/train': 2.765425443649292}
-03/03/2022 21:14:49 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/03/2022 21:14:51 - INFO - codeparrot_training - Step 6625: {'lr': 0.0004987961816680492, 'samples': 3392512, 'steps': 6625, 'loss/train': 2.1472458839416504}
-03/03/2022 21:14:54 - INFO - codeparrot_training - Step 6626: {'lr': 0.000498795661460092, 'samples': 3393024, 'steps': 6626, 'loss/train': 3.1198878288269043}
-03/03/2022 21:14:57 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/03/2022 21:15:00 - INFO - codeparrot_training - Step 6627: {'lr': 0.0004987951411400313, 'samples': 3393536, 'steps': 6627, 'loss/train': 2.3755342960357666}
-03/03/2022 21:15:03 - INFO - codeparrot_training - Step 6628: {'lr': 0.0004987946207078674, 'samples': 3394048, 'steps': 6628, 'loss/train': 2.364553689956665}
-03/03/2022 21:15:06 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/03/2022 21:15:08 - INFO - codeparrot_training - Step 6629: {'lr': 0.0004987941001636004, 'samples': 3394560, 'steps': 6629, 'loss/train': 2.2832438945770264}
-03/03/2022 21:15:11 - INFO - codeparrot_training - Step 6630: {'lr': 0.0004987935795072307, 'samples': 3395072, 'steps': 6630, 'loss/train': 2.2533905506134033}
-03/03/2022 21:15:14 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/03/2022 21:15:16 - INFO - codeparrot_training - Step 6631: {'lr': 0.0004987930587387584, 'samples': 3395584, 'steps': 6631, 'loss/train': 2.4387776851654053}
-03/03/2022 21:15:20 - INFO - codeparrot_training - Step 6632: {'lr': 0.0004987925378581838, 'samples': 3396096, 'steps': 6632, 'loss/train': 1.355211615562439}
-03/03/2022 21:15:22 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 21:15:25 - INFO - codeparrot_training - Step 6633: {'lr': 0.0004987920168655071, 'samples': 3396608, 'steps': 6633, 'loss/train': 0.9741966724395752}
-03/03/2022 21:15:28 - INFO - codeparrot_training - Step 6634: {'lr': 0.0004987914957607286, 'samples': 3397120, 'steps': 6634, 'loss/train': 2.362170696258545}
-03/03/2022 21:15:31 - INFO - codeparrot_training - Step 6635: {'lr': 0.0004987909745438484, 'samples': 3397632, 'steps': 6635, 'loss/train': 2.4472336769104004}
-03/03/2022 21:15:31 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/03/2022 21:15:36 - INFO - codeparrot_training - Step 6636: {'lr': 0.000498790453214867, 'samples': 3398144, 'steps': 6636, 'loss/train': 1.8781784772872925}
-03/03/2022 21:15:39 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/03/2022 21:15:42 - INFO - codeparrot_training - Step 6637: {'lr': 0.0004987899317737843, 'samples': 3398656, 'steps': 6637, 'loss/train': 1.7845933437347412}
-03/03/2022 21:15:45 - INFO - codeparrot_training - Step 6638: {'lr': 0.0004987894102206008, 'samples': 3399168, 'steps': 6638, 'loss/train': 2.1783177852630615}
-03/03/2022 21:15:48 - INFO - codeparrot_training - Step 6639: {'lr': 0.0004987888885553166, 'samples': 3399680, 'steps': 6639, 'loss/train': 2.5326104164123535}
-03/03/2022 21:15:48 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/03/2022 21:15:53 - INFO - codeparrot_training - Step 6640: {'lr': 0.0004987883667779319, 'samples': 3400192, 'steps': 6640, 'loss/train': 2.0752081871032715}
-03/03/2022 21:15:56 - INFO - codeparrot_training - Step 6641: {'lr': 0.0004987878448884471, 'samples': 3400704, 'steps': 6641, 'loss/train': 2.309004783630371}
-03/03/2022 21:15:57 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/03/2022 21:16:02 - INFO - codeparrot_training - Step 6642: {'lr': 0.0004987873228868622, 'samples': 3401216, 'steps': 6642, 'loss/train': 2.414719581604004}
-03/03/2022 21:16:05 - INFO - codeparrot_training - Step 6643: {'lr': 0.0004987868007731778, 'samples': 3401728, 'steps': 6643, 'loss/train': 1.543851613998413}
-03/03/2022 21:16:05 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/03/2022 21:16:10 - INFO - codeparrot_training - Step 6644: {'lr': 0.0004987862785473937, 'samples': 3402240, 'steps': 6644, 'loss/train': 1.197468876838684}
-03/03/2022 21:16:13 - INFO - codeparrot_training - Step 6645: {'lr': 0.0004987857562095103, 'samples': 3402752, 'steps': 6645, 'loss/train': 1.9216934442520142}
-03/03/2022 21:16:14 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/03/2022 21:16:19 - INFO - codeparrot_training - Step 6646: {'lr': 0.0004987852337595281, 'samples': 3403264, 'steps': 6646, 'loss/train': 2.2784621715545654}
-03/03/2022 21:16:22 - INFO - codeparrot_training - Step 6647: {'lr': 0.0004987847111974469, 'samples': 3403776, 'steps': 6647, 'loss/train': 4.230886936187744}
-03/03/2022 21:16:23 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/03/2022 21:16:27 - INFO - codeparrot_training - Step 6648: {'lr': 0.0004987841885232674, 'samples': 3404288, 'steps': 6648, 'loss/train': 2.5676259994506836}
-03/03/2022 21:16:30 - INFO - codeparrot_training - Step 6649: {'lr': 0.0004987836657369893, 'samples': 3404800, 'steps': 6649, 'loss/train': 2.004595994949341}
-03/03/2022 21:16:31 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/03/2022 21:16:36 - INFO - codeparrot_training - Step 6650: {'lr': 0.0004987831428386133, 'samples': 3405312, 'steps': 6650, 'loss/train': 1.1893446445465088}
-03/03/2022 21:16:39 - INFO - codeparrot_training - Step 6651: {'lr': 0.0004987826198281394, 'samples': 3405824, 'steps': 6651, 'loss/train': 2.5959925651550293}
-03/03/2022 21:16:40 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/03/2022 21:16:44 - INFO - codeparrot_training - Step 6652: {'lr': 0.0004987820967055678, 'samples': 3406336, 'steps': 6652, 'loss/train': 1.7475553750991821}
-03/03/2022 21:16:47 - INFO - codeparrot_training - Step 6653: {'lr': 0.000498781573470899, 'samples': 3406848, 'steps': 6653, 'loss/train': 2.179630994796753}
-03/03/2022 21:16:49 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/03/2022 21:16:52 - INFO - codeparrot_training - Step 6654: {'lr': 0.000498781050124133, 'samples': 3407360, 'steps': 6654, 'loss/train': 1.9992166757583618}
-03/03/2022 21:16:56 - INFO - codeparrot_training - Step 6655: {'lr': 0.0004987805266652701, 'samples': 3407872, 'steps': 6655, 'loss/train': 2.7943973541259766}
-03/03/2022 21:16:57 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/03/2022 21:17:01 - INFO - codeparrot_training - Step 6656: {'lr': 0.0004987800030943105, 'samples': 3408384, 'steps': 6656, 'loss/train': 2.1573326587677}
-03/03/2022 21:17:04 - INFO - codeparrot_training - Step 6657: {'lr': 0.0004987794794112545, 'samples': 3408896, 'steps': 6657, 'loss/train': 2.4007070064544678}
-03/03/2022 21:17:05 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/03/2022 21:17:09 - INFO - codeparrot_training - Step 6658: {'lr': 0.0004987789556161022, 'samples': 3409408, 'steps': 6658, 'loss/train': 2.3588547706604004}
-03/03/2022 21:17:13 - INFO - codeparrot_training - Step 6659: {'lr': 0.0004987784317088541, 'samples': 3409920, 'steps': 6659, 'loss/train': 2.5929458141326904}
-03/03/2022 21:17:14 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/03/2022 21:17:18 - INFO - codeparrot_training - Step 6660: {'lr': 0.0004987779076895102, 'samples': 3410432, 'steps': 6660, 'loss/train': 1.8974653482437134}
-03/03/2022 21:17:21 - INFO - codeparrot_training - Step 6661: {'lr': 0.0004987773835580708, 'samples': 3410944, 'steps': 6661, 'loss/train': 1.9501618146896362}
-03/03/2022 21:17:22 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/03/2022 21:17:26 - INFO - codeparrot_training - Step 6662: {'lr': 0.0004987768593145362, 'samples': 3411456, 'steps': 6662, 'loss/train': 2.0681278705596924}
-03/03/2022 21:17:29 - INFO - codeparrot_training - Step 6663: {'lr': 0.0004987763349589065, 'samples': 3411968, 'steps': 6663, 'loss/train': 2.2317280769348145}
-03/03/2022 21:17:31 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/03/2022 21:17:35 - INFO - codeparrot_training - Step 6664: {'lr': 0.0004987758104911821, 'samples': 3412480, 'steps': 6664, 'loss/train': 2.6085164546966553}
-03/03/2022 21:17:38 - INFO - codeparrot_training - Step 6665: {'lr': 0.0004987752859113631, 'samples': 3412992, 'steps': 6665, 'loss/train': 2.4163970947265625}
-03/03/2022 21:17:39 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/03/2022 21:17:43 - INFO - codeparrot_training - Step 6666: {'lr': 0.0004987747612194499, 'samples': 3413504, 'steps': 6666, 'loss/train': 1.5085796117782593}
-03/03/2022 21:17:46 - INFO - codeparrot_training - Step 6667: {'lr': 0.0004987742364154425, 'samples': 3414016, 'steps': 6667, 'loss/train': 4.192680835723877}
-03/03/2022 21:17:48 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/03/2022 21:17:52 - INFO - codeparrot_training - Step 6668: {'lr': 0.0004987737114993413, 'samples': 3414528, 'steps': 6668, 'loss/train': 1.9824097156524658}
-03/03/2022 21:17:55 - INFO - codeparrot_training - Step 6669: {'lr': 0.0004987731864711466, 'samples': 3415040, 'steps': 6669, 'loss/train': 2.2919654846191406}
-03/03/2022 21:17:56 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/03/2022 21:18:00 - INFO - codeparrot_training - Step 6670: {'lr': 0.0004987726613308584, 'samples': 3415552, 'steps': 6670, 'loss/train': 2.129175901412964}
-03/03/2022 21:18:03 - INFO - codeparrot_training - Step 6671: {'lr': 0.0004987721360784772, 'samples': 3416064, 'steps': 6671, 'loss/train': 1.9380806684494019}
-03/03/2022 21:18:05 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/03/2022 21:18:08 - INFO - codeparrot_training - Step 6672: {'lr': 0.0004987716107140031, 'samples': 3416576, 'steps': 6672, 'loss/train': 2.3678579330444336}
-03/03/2022 21:18:11 - INFO - codeparrot_training - Step 6673: {'lr': 0.0004987710852374363, 'samples': 3417088, 'steps': 6673, 'loss/train': 2.7991175651550293}
-03/03/2022 21:18:13 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/03/2022 21:18:17 - INFO - codeparrot_training - Step 6674: {'lr': 0.0004987705596487771, 'samples': 3417600, 'steps': 6674, 'loss/train': 7.057065963745117}
-03/03/2022 21:18:20 - INFO - codeparrot_training - Step 6675: {'lr': 0.0004987700339480258, 'samples': 3418112, 'steps': 6675, 'loss/train': 1.78252112865448}
-03/03/2022 21:18:22 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/03/2022 21:18:25 - INFO - codeparrot_training - Step 6676: {'lr': 0.0004987695081351824, 'samples': 3418624, 'steps': 6676, 'loss/train': 1.600085973739624}
-03/03/2022 21:18:28 - INFO - codeparrot_training - Step 6677: {'lr': 0.0004987689822102474, 'samples': 3419136, 'steps': 6677, 'loss/train': 2.5810797214508057}
-03/03/2022 21:18:30 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/03/2022 21:18:34 - INFO - codeparrot_training - Step 6678: {'lr': 0.000498768456173221, 'samples': 3419648, 'steps': 6678, 'loss/train': 3.5913732051849365}
-03/03/2022 21:18:37 - INFO - codeparrot_training - Step 6679: {'lr': 0.0004987679300241033, 'samples': 3420160, 'steps': 6679, 'loss/train': 2.2962145805358887}
-03/03/2022 21:18:42 - INFO - codeparrot_training - Step 6680: {'lr': 0.0004987674037628945, 'samples': 3420672, 'steps': 6680, 'loss/train': 1.628814935684204}
-03/03/2022 21:18:46 - INFO - codeparrot_training - Step 6681: {'lr': 0.0004987668773895951, 'samples': 3421184, 'steps': 6681, 'loss/train': 2.413447141647339}
-03/03/2022 21:18:48 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/03/2022 21:18:51 - INFO - codeparrot_training - Step 6682: {'lr': 0.0004987663509042052, 'samples': 3421696, 'steps': 6682, 'loss/train': 1.90993070602417}
-03/03/2022 21:18:54 - INFO - codeparrot_training - Step 6683: {'lr': 0.000498765824306725, 'samples': 3422208, 'steps': 6683, 'loss/train': 3.1311042308807373}
-03/03/2022 21:18:57 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/03/2022 21:18:59 - INFO - codeparrot_training - Step 6684: {'lr': 0.0004987652975971546, 'samples': 3422720, 'steps': 6684, 'loss/train': 0.44367966055870056}
-03/03/2022 21:19:03 - INFO - codeparrot_training - Step 6685: {'lr': 0.0004987647707754945, 'samples': 3423232, 'steps': 6685, 'loss/train': 1.6944084167480469}
-03/03/2022 21:19:05 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/03/2022 21:19:08 - INFO - codeparrot_training - Step 6686: {'lr': 0.0004987642438417449, 'samples': 3423744, 'steps': 6686, 'loss/train': 2.1665282249450684}
-03/03/2022 21:19:11 - INFO - codeparrot_training - Step 6687: {'lr': 0.0004987637167959059, 'samples': 3424256, 'steps': 6687, 'loss/train': 2.052201747894287}
-03/03/2022 21:19:14 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/03/2022 21:19:16 - INFO - codeparrot_training - Step 6688: {'lr': 0.0004987631896379779, 'samples': 3424768, 'steps': 6688, 'loss/train': 1.7995684146881104}
-03/03/2022 21:19:19 - INFO - codeparrot_training - Step 6689: {'lr': 0.0004987626623679609, 'samples': 3425280, 'steps': 6689, 'loss/train': 2.6371946334838867}
-03/03/2022 21:19:22 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/03/2022 21:19:25 - INFO - codeparrot_training - Step 6690: {'lr': 0.0004987621349858553, 'samples': 3425792, 'steps': 6690, 'loss/train': 1.817025065422058}
-03/03/2022 21:19:28 - INFO - codeparrot_training - Step 6691: {'lr': 0.0004987616074916615, 'samples': 3426304, 'steps': 6691, 'loss/train': 0.4158846437931061}
-03/03/2022 21:19:30 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/03/2022 21:19:33 - INFO - codeparrot_training - Step 6692: {'lr': 0.0004987610798853794, 'samples': 3426816, 'steps': 6692, 'loss/train': 2.4107015132904053}
-03/03/2022 21:19:36 - INFO - codeparrot_training - Step 6693: {'lr': 0.0004987605521670094, 'samples': 3427328, 'steps': 6693, 'loss/train': 2.709824800491333}
-03/03/2022 21:19:39 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/03/2022 21:19:42 - INFO - codeparrot_training - Step 6694: {'lr': 0.0004987600243365518, 'samples': 3427840, 'steps': 6694, 'loss/train': 1.5638453960418701}
-03/03/2022 21:19:45 - INFO - codeparrot_training - Step 6695: {'lr': 0.0004987594963940066, 'samples': 3428352, 'steps': 6695, 'loss/train': 2.105537176132202}
-03/03/2022 21:19:47 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/03/2022 21:19:50 - INFO - codeparrot_training - Step 6696: {'lr': 0.0004987589683393744, 'samples': 3428864, 'steps': 6696, 'loss/train': 1.1718361377716064}
-03/03/2022 21:19:53 - INFO - codeparrot_training - Step 6697: {'lr': 0.0004987584401726552, 'samples': 3429376, 'steps': 6697, 'loss/train': 2.1249680519104004}
-03/03/2022 21:19:55 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/03/2022 21:19:58 - INFO - codeparrot_training - Step 6698: {'lr': 0.0004987579118938492, 'samples': 3429888, 'steps': 6698, 'loss/train': 2.961479663848877}
-03/03/2022 21:20:02 - INFO - codeparrot_training - Step 6699: {'lr': 0.0004987573835029569, 'samples': 3430400, 'steps': 6699, 'loss/train': 2.4648895263671875}
-03/03/2022 21:20:04 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/03/2022 21:20:07 - INFO - codeparrot_training - Step 6700: {'lr': 0.0004987568549999782, 'samples': 3430912, 'steps': 6700, 'loss/train': 2.822676420211792}
-03/03/2022 21:20:10 - INFO - codeparrot_training - Step 6701: {'lr': 0.0004987563263849136, 'samples': 3431424, 'steps': 6701, 'loss/train': 1.4478466510772705}
-03/03/2022 21:20:12 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/03/2022 21:20:15 - INFO - codeparrot_training - Step 6702: {'lr': 0.0004987557976577632, 'samples': 3431936, 'steps': 6702, 'loss/train': 2.244169235229492}
-03/03/2022 21:20:19 - INFO - codeparrot_training - Step 6703: {'lr': 0.0004987552688185273, 'samples': 3432448, 'steps': 6703, 'loss/train': 2.1037826538085938}
-03/03/2022 21:20:20 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/03/2022 21:20:24 - INFO - codeparrot_training - Step 6704: {'lr': 0.0004987547398672061, 'samples': 3432960, 'steps': 6704, 'loss/train': 2.2544660568237305}
-03/03/2022 21:20:27 - INFO - codeparrot_training - Step 6705: {'lr': 0.0004987542108037998, 'samples': 3433472, 'steps': 6705, 'loss/train': 2.0992417335510254}
-03/03/2022 21:20:29 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/03/2022 21:20:32 - INFO - codeparrot_training - Step 6706: {'lr': 0.0004987536816283087, 'samples': 3433984, 'steps': 6706, 'loss/train': 2.79413104057312}
-03/03/2022 21:20:36 - INFO - codeparrot_training - Step 6707: {'lr': 0.0004987531523407331, 'samples': 3434496, 'steps': 6707, 'loss/train': 0.7833665013313293}
-03/03/2022 21:20:38 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/03/2022 21:20:41 - INFO - codeparrot_training - Step 6708: {'lr': 0.0004987526229410732, 'samples': 3435008, 'steps': 6708, 'loss/train': 2.008840560913086}
-03/03/2022 21:20:44 - INFO - codeparrot_training - Step 6709: {'lr': 0.000498752093429329, 'samples': 3435520, 'steps': 6709, 'loss/train': 2.8811843395233154}
-03/03/2022 21:20:46 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/03/2022 21:20:49 - INFO - codeparrot_training - Step 6710: {'lr': 0.0004987515638055012, 'samples': 3436032, 'steps': 6710, 'loss/train': 2.2996904850006104}
-03/03/2022 21:20:52 - INFO - codeparrot_training - Step 6711: {'lr': 0.0004987510340695896, 'samples': 3436544, 'steps': 6711, 'loss/train': 3.0161945819854736}
-03/03/2022 21:20:54 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/03/2022 21:20:57 - INFO - codeparrot_training - Step 6712: {'lr': 0.0004987505042215948, 'samples': 3437056, 'steps': 6712, 'loss/train': 0.9653955698013306}
-03/03/2022 21:21:01 - INFO - codeparrot_training - Step 6713: {'lr': 0.0004987499742615167, 'samples': 3437568, 'steps': 6713, 'loss/train': 2.642169952392578}
-03/03/2022 21:21:02 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/03/2022 21:21:06 - INFO - codeparrot_training - Step 6714: {'lr': 0.0004987494441893557, 'samples': 3438080, 'steps': 6714, 'loss/train': 0.8056423664093018}
-03/03/2022 21:21:09 - INFO - codeparrot_training - Step 6715: {'lr': 0.0004987489140051121, 'samples': 3438592, 'steps': 6715, 'loss/train': 1.7560700178146362}
-03/03/2022 21:21:11 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/03/2022 21:21:14 - INFO - codeparrot_training - Step 6716: {'lr': 0.000498748383708786, 'samples': 3439104, 'steps': 6716, 'loss/train': 2.845957040786743}
-03/03/2022 21:21:18 - INFO - codeparrot_training - Step 6717: {'lr': 0.0004987478533003779, 'samples': 3439616, 'steps': 6717, 'loss/train': 3.336688756942749}
-03/03/2022 21:21:20 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/03/2022 21:21:23 - INFO - codeparrot_training - Step 6718: {'lr': 0.0004987473227798877, 'samples': 3440128, 'steps': 6718, 'loss/train': 1.769804835319519}
-03/03/2022 21:21:26 - INFO - codeparrot_training - Step 6719: {'lr': 0.0004987467921473157, 'samples': 3440640, 'steps': 6719, 'loss/train': 1.7384952306747437}
-03/03/2022 21:21:28 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/03/2022 21:21:31 - INFO - codeparrot_training - Step 6720: {'lr': 0.0004987462614026624, 'samples': 3441152, 'steps': 6720, 'loss/train': 2.669689416885376}
-03/03/2022 21:21:34 - INFO - codeparrot_training - Step 6721: {'lr': 0.0004987457305459279, 'samples': 3441664, 'steps': 6721, 'loss/train': 3.2196624279022217}
-03/03/2022 21:21:36 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/03/2022 21:21:40 - INFO - codeparrot_training - Step 6722: {'lr': 0.0004987451995771124, 'samples': 3442176, 'steps': 6722, 'loss/train': 2.459155559539795}
-03/03/2022 21:21:43 - INFO - codeparrot_training - Step 6723: {'lr': 0.000498744668496216, 'samples': 3442688, 'steps': 6723, 'loss/train': 1.986860990524292}
-03/03/2022 21:21:45 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/03/2022 21:21:48 - INFO - codeparrot_training - Step 6724: {'lr': 0.0004987441373032393, 'samples': 3443200, 'steps': 6724, 'loss/train': 2.112771511077881}
-03/03/2022 21:21:51 - INFO - codeparrot_training - Step 6725: {'lr': 0.0004987436059981821, 'samples': 3443712, 'steps': 6725, 'loss/train': 2.389969825744629}
-03/03/2022 21:21:53 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/03/2022 21:21:57 - INFO - codeparrot_training - Step 6726: {'lr': 0.0004987430745810451, 'samples': 3444224, 'steps': 6726, 'loss/train': 1.934665560722351}
-03/03/2022 21:22:00 - INFO - codeparrot_training - Step 6727: {'lr': 0.0004987425430518282, 'samples': 3444736, 'steps': 6727, 'loss/train': 1.4264556169509888}
-03/03/2022 21:22:02 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/03/2022 21:22:05 - INFO - codeparrot_training - Step 6728: {'lr': 0.0004987420114105317, 'samples': 3445248, 'steps': 6728, 'loss/train': 2.3938167095184326}
-03/03/2022 21:22:08 - INFO - codeparrot_training - Step 6729: {'lr': 0.000498741479657156, 'samples': 3445760, 'steps': 6729, 'loss/train': 1.9414899349212646}
-03/03/2022 21:22:11 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/03/2022 21:22:14 - INFO - codeparrot_training - Step 6730: {'lr': 0.0004987409477917011, 'samples': 3446272, 'steps': 6730, 'loss/train': 2.640099287033081}
-03/03/2022 21:22:17 - INFO - codeparrot_training - Step 6731: {'lr': 0.0004987404158141675, 'samples': 3446784, 'steps': 6731, 'loss/train': 2.0074474811553955}
-03/03/2022 21:22:19 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/03/2022 21:22:22 - INFO - codeparrot_training - Step 6732: {'lr': 0.0004987398837245552, 'samples': 3447296, 'steps': 6732, 'loss/train': 2.4899535179138184}
-03/03/2022 21:22:25 - INFO - codeparrot_training - Step 6733: {'lr': 0.0004987393515228646, 'samples': 3447808, 'steps': 6733, 'loss/train': 1.5913223028182983}
-03/03/2022 21:22:27 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/03/2022 21:22:31 - INFO - codeparrot_training - Step 6734: {'lr': 0.0004987388192090959, 'samples': 3448320, 'steps': 6734, 'loss/train': 2.468355655670166}
-03/03/2022 21:22:34 - INFO - codeparrot_training - Step 6735: {'lr': 0.0004987382867832493, 'samples': 3448832, 'steps': 6735, 'loss/train': 2.4399631023406982}
-03/03/2022 21:22:37 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/03/2022 21:22:39 - INFO - codeparrot_training - Step 6736: {'lr': 0.0004987377542453251, 'samples': 3449344, 'steps': 6736, 'loss/train': 2.0118348598480225}
-03/03/2022 21:22:42 - INFO - codeparrot_training - Step 6737: {'lr': 0.0004987372215953234, 'samples': 3449856, 'steps': 6737, 'loss/train': 2.6319167613983154}
-03/03/2022 21:22:45 - INFO - codeparrot_training - Step 6738: {'lr': 0.0004987366888332446, 'samples': 3450368, 'steps': 6738, 'loss/train': 2.1187939643859863}
-03/03/2022 21:22:45 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/03/2022 21:22:51 - INFO - codeparrot_training - Step 6739: {'lr': 0.0004987361559590889, 'samples': 3450880, 'steps': 6739, 'loss/train': 2.8827309608459473}
-03/03/2022 21:22:54 - INFO - codeparrot_training - Step 6740: {'lr': 0.0004987356229728566, 'samples': 3451392, 'steps': 6740, 'loss/train': 2.579463481903076}
-03/03/2022 21:22:55 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/03/2022 21:23:00 - INFO - codeparrot_training - Step 6741: {'lr': 0.0004987350898745477, 'samples': 3451904, 'steps': 6741, 'loss/train': 2.390681028366089}
-03/03/2022 21:23:03 - INFO - codeparrot_training - Step 6742: {'lr': 0.0004987345566641628, 'samples': 3452416, 'steps': 6742, 'loss/train': 2.1626625061035156}
-03/03/2022 21:23:04 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/03/2022 21:23:08 - INFO - codeparrot_training - Step 6743: {'lr': 0.0004987340233417019, 'samples': 3452928, 'steps': 6743, 'loss/train': 2.406765937805176}
-03/03/2022 21:23:11 - INFO - codeparrot_training - Step 6744: {'lr': 0.0004987334899071652, 'samples': 3453440, 'steps': 6744, 'loss/train': 2.206580877304077}
-03/03/2022 21:23:13 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/03/2022 21:23:16 - INFO - codeparrot_training - Step 6745: {'lr': 0.000498732956360553, 'samples': 3453952, 'steps': 6745, 'loss/train': 1.9166637659072876}
-03/03/2022 21:23:20 - INFO - codeparrot_training - Step 6746: {'lr': 0.0004987324227018657, 'samples': 3454464, 'steps': 6746, 'loss/train': 2.352651357650757}
-03/03/2022 21:23:21 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/03/2022 21:23:25 - INFO - codeparrot_training - Step 6747: {'lr': 0.0004987318889311033, 'samples': 3454976, 'steps': 6747, 'loss/train': 2.239023447036743}
-03/03/2022 21:23:28 - INFO - codeparrot_training - Step 6748: {'lr': 0.0004987313550482663, 'samples': 3455488, 'steps': 6748, 'loss/train': 1.6585386991500854}
-03/03/2022 21:23:30 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/03/2022 21:23:33 - INFO - codeparrot_training - Step 6749: {'lr': 0.0004987308210533546, 'samples': 3456000, 'steps': 6749, 'loss/train': 2.284125566482544}
-03/03/2022 21:23:37 - INFO - codeparrot_training - Step 6750: {'lr': 0.0004987302869463686, 'samples': 3456512, 'steps': 6750, 'loss/train': 2.203669309616089}
-03/03/2022 21:23:38 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/03/2022 21:23:42 - INFO - codeparrot_training - Step 6751: {'lr': 0.0004987297527273088, 'samples': 3457024, 'steps': 6751, 'loss/train': 3.5302624702453613}
-03/03/2022 21:23:45 - INFO - codeparrot_training - Step 6752: {'lr': 0.0004987292183961751, 'samples': 3457536, 'steps': 6752, 'loss/train': 2.5507113933563232}
-03/03/2022 21:23:46 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/03/2022 21:23:50 - INFO - codeparrot_training - Step 6753: {'lr': 0.0004987286839529679, 'samples': 3458048, 'steps': 6753, 'loss/train': 2.668405532836914}
-03/03/2022 21:23:53 - INFO - codeparrot_training - Step 6754: {'lr': 0.0004987281493976873, 'samples': 3458560, 'steps': 6754, 'loss/train': 1.6651816368103027}
-03/03/2022 21:23:55 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/03/2022 21:23:59 - INFO - codeparrot_training - Step 6755: {'lr': 0.0004987276147303337, 'samples': 3459072, 'steps': 6755, 'loss/train': 1.0844314098358154}
-03/03/2022 21:24:02 - INFO - codeparrot_training - Step 6756: {'lr': 0.0004987270799509071, 'samples': 3459584, 'steps': 6756, 'loss/train': 1.4416041374206543}
-03/03/2022 21:24:04 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/03/2022 21:24:07 - INFO - codeparrot_training - Step 6757: {'lr': 0.0004987265450594082, 'samples': 3460096, 'steps': 6757, 'loss/train': 3.3601250648498535}
-03/03/2022 21:24:10 - INFO - codeparrot_training - Step 6758: {'lr': 0.0004987260100558368, 'samples': 3460608, 'steps': 6758, 'loss/train': 2.541935920715332}
-03/03/2022 21:24:12 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/03/2022 21:24:15 - INFO - codeparrot_training - Step 6759: {'lr': 0.0004987254749401933, 'samples': 3461120, 'steps': 6759, 'loss/train': 2.7169296741485596}
-03/03/2022 21:24:19 - INFO - codeparrot_training - Step 6760: {'lr': 0.000498724939712478, 'samples': 3461632, 'steps': 6760, 'loss/train': 2.1377720832824707}
-03/03/2022 21:24:21 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/03/2022 21:24:24 - INFO - codeparrot_training - Step 6761: {'lr': 0.000498724404372691, 'samples': 3462144, 'steps': 6761, 'loss/train': 2.6957499980926514}
-03/03/2022 21:24:27 - INFO - codeparrot_training - Step 6762: {'lr': 0.0004987238689208327, 'samples': 3462656, 'steps': 6762, 'loss/train': 1.656937837600708}
-03/03/2022 21:24:29 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/03/2022 21:24:32 - INFO - codeparrot_training - Step 6763: {'lr': 0.0004987233333569031, 'samples': 3463168, 'steps': 6763, 'loss/train': 2.106895923614502}
-03/03/2022 21:24:36 - INFO - codeparrot_training - Step 6764: {'lr': 0.0004987227976809028, 'samples': 3463680, 'steps': 6764, 'loss/train': 0.7531761527061462}
-03/03/2022 21:24:38 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/03/2022 21:24:41 - INFO - codeparrot_training - Step 6765: {'lr': 0.0004987222618928318, 'samples': 3464192, 'steps': 6765, 'loss/train': 1.7572160959243774}
-03/03/2022 21:24:44 - INFO - codeparrot_training - Step 6766: {'lr': 0.0004987217259926904, 'samples': 3464704, 'steps': 6766, 'loss/train': 2.4418036937713623}
-03/03/2022 21:24:46 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/03/2022 21:24:49 - INFO - codeparrot_training - Step 6767: {'lr': 0.0004987211899804788, 'samples': 3465216, 'steps': 6767, 'loss/train': 1.942525863647461}
-03/03/2022 21:24:52 - INFO - codeparrot_training - Step 6768: {'lr': 0.0004987206538561972, 'samples': 3465728, 'steps': 6768, 'loss/train': 2.565329074859619}
-03/03/2022 21:24:58 - INFO - codeparrot_training - Step 6769: {'lr': 0.000498720117619846, 'samples': 3466240, 'steps': 6769, 'loss/train': 3.114542007446289}
-03/03/2022 21:25:01 - INFO - codeparrot_training - Step 6770: {'lr': 0.0004987195812714252, 'samples': 3466752, 'steps': 6770, 'loss/train': 2.7954719066619873}
-03/03/2022 21:25:03 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/03/2022 21:25:06 - INFO - codeparrot_training - Step 6771: {'lr': 0.0004987190448109354, 'samples': 3467264, 'steps': 6771, 'loss/train': 2.086214303970337}
-03/03/2022 21:25:09 - INFO - codeparrot_training - Step 6772: {'lr': 0.0004987185082383765, 'samples': 3467776, 'steps': 6772, 'loss/train': 2.9632959365844727}
-03/03/2022 21:25:11 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/03/2022 21:25:14 - INFO - codeparrot_training - Step 6773: {'lr': 0.000498717971553749, 'samples': 3468288, 'steps': 6773, 'loss/train': 2.5668179988861084}
-03/03/2022 21:25:18 - INFO - codeparrot_training - Step 6774: {'lr': 0.0004987174347570529, 'samples': 3468800, 'steps': 6774, 'loss/train': 2.425973415374756}
-03/03/2022 21:25:19 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/03/2022 21:25:23 - INFO - codeparrot_training - Step 6775: {'lr': 0.0004987168978482886, 'samples': 3469312, 'steps': 6775, 'loss/train': 2.999485731124878}
-03/03/2022 21:25:26 - INFO - codeparrot_training - Step 6776: {'lr': 0.0004987163608274564, 'samples': 3469824, 'steps': 6776, 'loss/train': 1.6665650606155396}
-03/03/2022 21:25:27 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/03/2022 21:25:31 - INFO - codeparrot_training - Step 6777: {'lr': 0.0004987158236945563, 'samples': 3470336, 'steps': 6777, 'loss/train': 1.6300115585327148}
-03/03/2022 21:25:34 - INFO - codeparrot_training - Step 6778: {'lr': 0.0004987152864495887, 'samples': 3470848, 'steps': 6778, 'loss/train': 0.4091637432575226}
-03/03/2022 21:25:35 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/03/2022 21:25:39 - INFO - codeparrot_training - Step 6779: {'lr': 0.000498714749092554, 'samples': 3471360, 'steps': 6779, 'loss/train': 1.523059606552124}
-03/03/2022 21:25:43 - INFO - codeparrot_training - Step 6780: {'lr': 0.0004987142116234521, 'samples': 3471872, 'steps': 6780, 'loss/train': 3.4042916297912598}
-03/03/2022 21:25:44 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/03/2022 21:25:48 - INFO - codeparrot_training - Step 6781: {'lr': 0.0004987136740422835, 'samples': 3472384, 'steps': 6781, 'loss/train': 2.024282932281494}
-03/03/2022 21:25:51 - INFO - codeparrot_training - Step 6782: {'lr': 0.0004987131363490483, 'samples': 3472896, 'steps': 6782, 'loss/train': 2.8448855876922607}
-03/03/2022 21:25:52 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/03/2022 21:25:56 - INFO - codeparrot_training - Step 6783: {'lr': 0.0004987125985437468, 'samples': 3473408, 'steps': 6783, 'loss/train': 0.5981308817863464}
-03/03/2022 21:25:59 - INFO - codeparrot_training - Step 6784: {'lr': 0.0004987120606263794, 'samples': 3473920, 'steps': 6784, 'loss/train': 2.2287464141845703}
-03/03/2022 21:26:00 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/03/2022 21:26:05 - INFO - codeparrot_training - Step 6785: {'lr': 0.000498711522596946, 'samples': 3474432, 'steps': 6785, 'loss/train': 1.9245777130126953}
-03/03/2022 21:26:08 - INFO - codeparrot_training - Step 6786: {'lr': 0.000498710984455447, 'samples': 3474944, 'steps': 6786, 'loss/train': 1.7811850309371948}
-03/03/2022 21:26:09 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/03/2022 21:26:13 - INFO - codeparrot_training - Step 6787: {'lr': 0.0004987104462018828, 'samples': 3475456, 'steps': 6787, 'loss/train': 2.9378325939178467}
-03/03/2022 21:26:16 - INFO - codeparrot_training - Step 6788: {'lr': 0.0004987099078362534, 'samples': 3475968, 'steps': 6788, 'loss/train': 2.616314172744751}
-03/03/2022 21:26:18 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/03/2022 21:26:21 - INFO - codeparrot_training - Step 6789: {'lr': 0.0004987093693585591, 'samples': 3476480, 'steps': 6789, 'loss/train': 3.1996402740478516}
-03/03/2022 21:26:25 - INFO - codeparrot_training - Step 6790: {'lr': 0.0004987088307688004, 'samples': 3476992, 'steps': 6790, 'loss/train': 2.6407759189605713}
-03/03/2022 21:26:27 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 21:26:30 - INFO - codeparrot_training - Step 6791: {'lr': 0.0004987082920669772, 'samples': 3477504, 'steps': 6791, 'loss/train': 0.5626809000968933}
-03/03/2022 21:26:33 - INFO - codeparrot_training - Step 6792: {'lr': 0.0004987077532530899, 'samples': 3478016, 'steps': 6792, 'loss/train': 2.006357431411743}
-03/03/2022 21:26:35 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/03/2022 21:26:38 - INFO - codeparrot_training - Step 6793: {'lr': 0.0004987072143271388, 'samples': 3478528, 'steps': 6793, 'loss/train': 2.039405584335327}
-03/03/2022 21:26:42 - INFO - codeparrot_training - Step 6794: {'lr': 0.000498706675289124, 'samples': 3479040, 'steps': 6794, 'loss/train': 1.3640847206115723}
-03/03/2022 21:26:44 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/03/2022 21:26:47 - INFO - codeparrot_training - Step 6795: {'lr': 0.0004987061361390458, 'samples': 3479552, 'steps': 6795, 'loss/train': 2.380962610244751}
-03/03/2022 21:26:50 - INFO - codeparrot_training - Step 6796: {'lr': 0.0004987055968769045, 'samples': 3480064, 'steps': 6796, 'loss/train': 2.9457716941833496}
-03/03/2022 21:26:52 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/03/2022 21:26:55 - INFO - codeparrot_training - Step 6797: {'lr': 0.0004987050575027002, 'samples': 3480576, 'steps': 6797, 'loss/train': 2.8917484283447266}
-03/03/2022 21:26:58 - INFO - codeparrot_training - Step 6798: {'lr': 0.0004987045180164333, 'samples': 3481088, 'steps': 6798, 'loss/train': 1.6963046789169312}
-03/03/2022 21:27:00 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/03/2022 21:27:04 - INFO - codeparrot_training - Step 6799: {'lr': 0.0004987039784181041, 'samples': 3481600, 'steps': 6799, 'loss/train': 2.159863233566284}
-03/03/2022 21:27:07 - INFO - codeparrot_training - Step 6800: {'lr': 0.0004987034387077126, 'samples': 3482112, 'steps': 6800, 'loss/train': 2.387751340866089}
-03/03/2022 21:27:09 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/03/2022 21:27:12 - INFO - codeparrot_training - Step 6801: {'lr': 0.0004987028988852592, 'samples': 3482624, 'steps': 6801, 'loss/train': 1.971797227859497}
-03/03/2022 21:27:15 - INFO - codeparrot_training - Step 6802: {'lr': 0.0004987023589507441, 'samples': 3483136, 'steps': 6802, 'loss/train': 1.9435499906539917}
-03/03/2022 21:27:17 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/03/2022 21:27:20 - INFO - codeparrot_training - Step 6803: {'lr': 0.0004987018189041675, 'samples': 3483648, 'steps': 6803, 'loss/train': 2.5782699584960938}
-03/03/2022 21:27:24 - INFO - codeparrot_training - Step 6804: {'lr': 0.0004987012787455297, 'samples': 3484160, 'steps': 6804, 'loss/train': 2.0360288619995117}
-03/03/2022 21:27:25 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/03/2022 21:27:29 - INFO - codeparrot_training - Step 6805: {'lr': 0.000498700738474831, 'samples': 3484672, 'steps': 6805, 'loss/train': 2.3903958797454834}
-03/03/2022 21:27:32 - INFO - codeparrot_training - Step 6806: {'lr': 0.0004987001980920716, 'samples': 3485184, 'steps': 6806, 'loss/train': 2.0052883625030518}
-03/03/2022 21:27:34 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/03/2022 21:27:37 - INFO - codeparrot_training - Step 6807: {'lr': 0.0004986996575972517, 'samples': 3485696, 'steps': 6807, 'loss/train': 1.676969289779663}
-03/03/2022 21:27:41 - INFO - codeparrot_training - Step 6808: {'lr': 0.0004986991169903716, 'samples': 3486208, 'steps': 6808, 'loss/train': 2.380641460418701}
-03/03/2022 21:27:42 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/03/2022 21:27:46 - INFO - codeparrot_training - Step 6809: {'lr': 0.0004986985762714314, 'samples': 3486720, 'steps': 6809, 'loss/train': 2.460646152496338}
-03/03/2022 21:27:49 - INFO - codeparrot_training - Step 6810: {'lr': 0.0004986980354404316, 'samples': 3487232, 'steps': 6810, 'loss/train': 1.66378653049469}
-03/03/2022 21:27:50 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/03/2022 21:27:54 - INFO - codeparrot_training - Step 6811: {'lr': 0.0004986974944973723, 'samples': 3487744, 'steps': 6811, 'loss/train': 0.24321404099464417}
-03/03/2022 21:27:57 - INFO - codeparrot_training - Step 6812: {'lr': 0.0004986969534422537, 'samples': 3488256, 'steps': 6812, 'loss/train': 2.4638781547546387}
-03/03/2022 21:27:59 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/03/2022 21:28:03 - INFO - codeparrot_training - Step 6813: {'lr': 0.000498696412275076, 'samples': 3488768, 'steps': 6813, 'loss/train': 3.173372745513916}
-03/03/2022 21:28:06 - INFO - codeparrot_training - Step 6814: {'lr': 0.0004986958709958396, 'samples': 3489280, 'steps': 6814, 'loss/train': 1.4501720666885376}
-03/03/2022 21:28:07 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/03/2022 21:28:11 - INFO - codeparrot_training - Step 6815: {'lr': 0.0004986953296045448, 'samples': 3489792, 'steps': 6815, 'loss/train': 2.101694345474243}
-03/03/2022 21:28:14 - INFO - codeparrot_training - Step 6816: {'lr': 0.0004986947881011917, 'samples': 3490304, 'steps': 6816, 'loss/train': 1.615058422088623}
-03/03/2022 21:28:15 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/03/2022 21:28:20 - INFO - codeparrot_training - Step 6817: {'lr': 0.0004986942464857804, 'samples': 3490816, 'steps': 6817, 'loss/train': 2.0266780853271484}
-03/03/2022 21:28:23 - INFO - codeparrot_training - Step 6818: {'lr': 0.0004986937047583114, 'samples': 3491328, 'steps': 6818, 'loss/train': 1.6252596378326416}
-03/03/2022 21:28:23 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/03/2022 21:28:28 - INFO - codeparrot_training - Step 6819: {'lr': 0.0004986931629187848, 'samples': 3491840, 'steps': 6819, 'loss/train': 2.156341075897217}
-03/03/2022 21:28:32 - INFO - codeparrot_training - Step 6820: {'lr': 0.0004986926209672011, 'samples': 3492352, 'steps': 6820, 'loss/train': 2.0958845615386963}
-03/03/2022 21:28:33 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/03/2022 21:28:37 - INFO - codeparrot_training - Step 6821: {'lr': 0.0004986920789035601, 'samples': 3492864, 'steps': 6821, 'loss/train': 2.387030601501465}
-03/03/2022 21:28:40 - INFO - codeparrot_training - Step 6822: {'lr': 0.0004986915367278623, 'samples': 3493376, 'steps': 6822, 'loss/train': 2.092315196990967}
-03/03/2022 21:28:41 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/03/2022 21:28:45 - INFO - codeparrot_training - Step 6823: {'lr': 0.0004986909944401082, 'samples': 3493888, 'steps': 6823, 'loss/train': 2.1108481884002686}
-03/03/2022 21:28:48 - INFO - codeparrot_training - Step 6824: {'lr': 0.0004986904520402975, 'samples': 3494400, 'steps': 6824, 'loss/train': 2.1470775604248047}
-03/03/2022 21:28:50 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/03/2022 21:28:54 - INFO - codeparrot_training - Step 6825: {'lr': 0.0004986899095284308, 'samples': 3494912, 'steps': 6825, 'loss/train': 1.897873878479004}
-03/03/2022 21:28:57 - INFO - codeparrot_training - Step 6826: {'lr': 0.0004986893669045083, 'samples': 3495424, 'steps': 6826, 'loss/train': 2.275609016418457}
-03/03/2022 21:28:58 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/03/2022 21:29:02 - INFO - codeparrot_training - Step 6827: {'lr': 0.0004986888241685301, 'samples': 3495936, 'steps': 6827, 'loss/train': 2.9432077407836914}
-03/03/2022 21:29:05 - INFO - codeparrot_training - Step 6828: {'lr': 0.0004986882813204967, 'samples': 3496448, 'steps': 6828, 'loss/train': 1.7387393712997437}
-03/03/2022 21:29:06 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/03/2022 21:29:10 - INFO - codeparrot_training - Step 6829: {'lr': 0.0004986877383604081, 'samples': 3496960, 'steps': 6829, 'loss/train': 2.4692158699035645}
-03/03/2022 21:29:14 - INFO - codeparrot_training - Step 6830: {'lr': 0.0004986871952882647, 'samples': 3497472, 'steps': 6830, 'loss/train': 1.7806075811386108}
-03/03/2022 21:29:15 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/03/2022 21:29:19 - INFO - codeparrot_training - Step 6831: {'lr': 0.0004986866521040666, 'samples': 3497984, 'steps': 6831, 'loss/train': 0.3496260941028595}
-03/03/2022 21:29:22 - INFO - codeparrot_training - Step 6832: {'lr': 0.0004986861088078142, 'samples': 3498496, 'steps': 6832, 'loss/train': 1.9755407571792603}
-03/03/2022 21:29:24 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/03/2022 21:29:27 - INFO - codeparrot_training - Step 6833: {'lr': 0.0004986855653995077, 'samples': 3499008, 'steps': 6833, 'loss/train': 2.3313028812408447}
-03/03/2022 21:29:31 - INFO - codeparrot_training - Step 6834: {'lr': 0.0004986850218791474, 'samples': 3499520, 'steps': 6834, 'loss/train': 1.7042518854141235}
-03/03/2022 21:29:32 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/03/2022 21:29:36 - INFO - codeparrot_training - Step 6835: {'lr': 0.0004986844782467332, 'samples': 3500032, 'steps': 6835, 'loss/train': 2.3490593433380127}
-03/03/2022 21:29:39 - INFO - codeparrot_training - Step 6836: {'lr': 0.0004986839345022658, 'samples': 3500544, 'steps': 6836, 'loss/train': 0.8928526043891907}
-03/03/2022 21:29:41 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/03/2022 21:29:44 - INFO - codeparrot_training - Step 6837: {'lr': 0.0004986833906457453, 'samples': 3501056, 'steps': 6837, 'loss/train': 2.7300074100494385}
-03/03/2022 21:29:47 - INFO - codeparrot_training - Step 6838: {'lr': 0.0004986828466771718, 'samples': 3501568, 'steps': 6838, 'loss/train': 2.774456739425659}
-03/03/2022 21:29:49 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/03/2022 21:29:53 - INFO - codeparrot_training - Step 6839: {'lr': 0.0004986823025965457, 'samples': 3502080, 'steps': 6839, 'loss/train': 2.0952649116516113}
-03/03/2022 21:29:56 - INFO - codeparrot_training - Step 6840: {'lr': 0.0004986817584038671, 'samples': 3502592, 'steps': 6840, 'loss/train': 2.057116985321045}
-03/03/2022 21:29:57 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/03/2022 21:30:01 - INFO - codeparrot_training - Step 6841: {'lr': 0.0004986812140991365, 'samples': 3503104, 'steps': 6841, 'loss/train': 1.9791481494903564}
-03/03/2022 21:30:04 - INFO - codeparrot_training - Step 6842: {'lr': 0.0004986806696823538, 'samples': 3503616, 'steps': 6842, 'loss/train': 1.7820173501968384}
-03/03/2022 21:30:06 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/03/2022 21:30:09 - INFO - codeparrot_training - Step 6843: {'lr': 0.0004986801251535195, 'samples': 3504128, 'steps': 6843, 'loss/train': 2.18415904045105}
-03/03/2022 21:30:13 - INFO - codeparrot_training - Step 6844: {'lr': 0.0004986795805126339, 'samples': 3504640, 'steps': 6844, 'loss/train': 1.6860193014144897}
-03/03/2022 21:30:14 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/03/2022 21:30:18 - INFO - codeparrot_training - Step 6845: {'lr': 0.000498679035759697, 'samples': 3505152, 'steps': 6845, 'loss/train': 2.0105478763580322}
-03/03/2022 21:30:21 - INFO - codeparrot_training - Step 6846: {'lr': 0.0004986784908947091, 'samples': 3505664, 'steps': 6846, 'loss/train': 3.076463222503662}
-03/03/2022 21:30:22 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/03/2022 21:30:26 - INFO - codeparrot_training - Step 6847: {'lr': 0.0004986779459176706, 'samples': 3506176, 'steps': 6847, 'loss/train': 2.155893087387085}
-03/03/2022 21:30:29 - INFO - codeparrot_training - Step 6848: {'lr': 0.0004986774008285816, 'samples': 3506688, 'steps': 6848, 'loss/train': 2.057210683822632}
-03/03/2022 21:30:30 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/03/2022 21:30:35 - INFO - codeparrot_training - Step 6849: {'lr': 0.0004986768556274425, 'samples': 3507200, 'steps': 6849, 'loss/train': 1.1500989198684692}
-03/03/2022 21:30:38 - INFO - codeparrot_training - Step 6850: {'lr': 0.0004986763103142533, 'samples': 3507712, 'steps': 6850, 'loss/train': 2.3173422813415527}
-03/03/2022 21:30:39 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/03/2022 21:30:43 - INFO - codeparrot_training - Step 6851: {'lr': 0.0004986757648890145, 'samples': 3508224, 'steps': 6851, 'loss/train': 2.4321138858795166}
-03/03/2022 21:30:46 - INFO - codeparrot_training - Step 6852: {'lr': 0.0004986752193517262, 'samples': 3508736, 'steps': 6852, 'loss/train': 1.4917738437652588}
-03/03/2022 21:30:47 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/03/2022 21:30:52 - INFO - codeparrot_training - Step 6853: {'lr': 0.0004986746737023887, 'samples': 3509248, 'steps': 6853, 'loss/train': 2.5534253120422363}
-03/03/2022 21:30:55 - INFO - codeparrot_training - Step 6854: {'lr': 0.0004986741279410023, 'samples': 3509760, 'steps': 6854, 'loss/train': 1.5591965913772583}
-03/03/2022 21:30:56 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/03/2022 21:31:00 - INFO - codeparrot_training - Step 6855: {'lr': 0.000498673582067567, 'samples': 3510272, 'steps': 6855, 'loss/train': 1.5678901672363281}
-03/03/2022 21:31:03 - INFO - codeparrot_training - Step 6856: {'lr': 0.0004986730360820833, 'samples': 3510784, 'steps': 6856, 'loss/train': 2.5142946243286133}
-03/03/2022 21:31:04 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/03/2022 21:31:08 - INFO - codeparrot_training - Step 6857: {'lr': 0.0004986724899845514, 'samples': 3511296, 'steps': 6857, 'loss/train': 2.0910236835479736}
-03/03/2022 21:31:12 - INFO - codeparrot_training - Step 6858: {'lr': 0.0004986719437749716, 'samples': 3511808, 'steps': 6858, 'loss/train': 1.9607782363891602}
-03/03/2022 21:31:13 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/03/2022 21:31:17 - INFO - codeparrot_training - Step 6859: {'lr': 0.0004986713974533439, 'samples': 3512320, 'steps': 6859, 'loss/train': 2.0046603679656982}
-03/03/2022 21:31:20 - INFO - codeparrot_training - Step 6860: {'lr': 0.0004986708510196688, 'samples': 3512832, 'steps': 6860, 'loss/train': 2.010556697845459}
-03/03/2022 21:31:22 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/03/2022 21:31:26 - INFO - codeparrot_training - Step 6861: {'lr': 0.0004986703044739464, 'samples': 3513344, 'steps': 6861, 'loss/train': 1.9213942289352417}
-03/03/2022 21:31:29 - INFO - codeparrot_training - Step 6862: {'lr': 0.000498669757816177, 'samples': 3513856, 'steps': 6862, 'loss/train': 2.743450880050659}
-03/03/2022 21:31:30 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/03/2022 21:31:34 - INFO - codeparrot_training - Step 6863: {'lr': 0.0004986692110463609, 'samples': 3514368, 'steps': 6863, 'loss/train': 2.363306999206543}
-03/03/2022 21:31:37 - INFO - codeparrot_training - Step 6864: {'lr': 0.0004986686641644982, 'samples': 3514880, 'steps': 6864, 'loss/train': 2.731900930404663}
-03/03/2022 21:31:39 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/03/2022 21:31:43 - INFO - codeparrot_training - Step 6865: {'lr': 0.0004986681171705893, 'samples': 3515392, 'steps': 6865, 'loss/train': 3.6986632347106934}
-03/03/2022 21:31:46 - INFO - codeparrot_training - Step 6866: {'lr': 0.0004986675700646343, 'samples': 3515904, 'steps': 6866, 'loss/train': 1.5044022798538208}
-03/03/2022 21:31:49 - INFO - codeparrot_training - Step 6867: {'lr': 0.0004986670228466337, 'samples': 3516416, 'steps': 6867, 'loss/train': 2.1581037044525146}
-03/03/2022 21:31:50 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/03/2022 21:31:54 - INFO - codeparrot_training - Step 6868: {'lr': 0.0004986664755165874, 'samples': 3516928, 'steps': 6868, 'loss/train': 2.559419631958008}
-03/03/2022 21:31:58 - INFO - codeparrot_training - Step 6869: {'lr': 0.000498665928074496, 'samples': 3517440, 'steps': 6869, 'loss/train': 2.110976219177246}
-03/03/2022 21:31:58 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/03/2022 21:32:03 - INFO - codeparrot_training - Step 6870: {'lr': 0.0004986653805203594, 'samples': 3517952, 'steps': 6870, 'loss/train': 0.7082364559173584}
-03/03/2022 21:32:06 - INFO - codeparrot_training - Step 6871: {'lr': 0.0004986648328541781, 'samples': 3518464, 'steps': 6871, 'loss/train': 3.1217029094696045}
-03/03/2022 21:32:06 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/03/2022 21:32:11 - INFO - codeparrot_training - Step 6872: {'lr': 0.0004986642850759522, 'samples': 3518976, 'steps': 6872, 'loss/train': 2.3569579124450684}
-03/03/2022 21:32:14 - INFO - codeparrot_training - Step 6873: {'lr': 0.0004986637371856822, 'samples': 3519488, 'steps': 6873, 'loss/train': 1.4964041709899902}
-03/03/2022 21:32:15 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/03/2022 21:32:20 - INFO - codeparrot_training - Step 6874: {'lr': 0.000498663189183368, 'samples': 3520000, 'steps': 6874, 'loss/train': 1.3676902055740356}
-03/03/2022 21:32:23 - INFO - codeparrot_training - Step 6875: {'lr': 0.0004986626410690099, 'samples': 3520512, 'steps': 6875, 'loss/train': 1.8205302953720093}
-03/03/2022 21:32:23 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/03/2022 21:32:28 - INFO - codeparrot_training - Step 6876: {'lr': 0.0004986620928426085, 'samples': 3521024, 'steps': 6876, 'loss/train': 1.6614139080047607}
-03/03/2022 21:32:31 - INFO - codeparrot_training - Step 6877: {'lr': 0.0004986615445041636, 'samples': 3521536, 'steps': 6877, 'loss/train': 2.2430837154388428}
-03/03/2022 21:32:32 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/03/2022 21:32:36 - INFO - codeparrot_training - Step 6878: {'lr': 0.0004986609960536757, 'samples': 3522048, 'steps': 6878, 'loss/train': 2.5667996406555176}
-03/03/2022 21:32:40 - INFO - codeparrot_training - Step 6879: {'lr': 0.000498660447491145, 'samples': 3522560, 'steps': 6879, 'loss/train': 1.4604930877685547}
-03/03/2022 21:32:40 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/03/2022 21:32:45 - INFO - codeparrot_training - Step 6880: {'lr': 0.0004986598988165718, 'samples': 3523072, 'steps': 6880, 'loss/train': 1.2783658504486084}
-03/03/2022 21:32:48 - INFO - codeparrot_training - Step 6881: {'lr': 0.0004986593500299562, 'samples': 3523584, 'steps': 6881, 'loss/train': 2.04534649848938}
-03/03/2022 21:32:48 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/03/2022 21:32:53 - INFO - codeparrot_training - Step 6882: {'lr': 0.0004986588011312986, 'samples': 3524096, 'steps': 6882, 'loss/train': 1.8227248191833496}
-03/03/2022 21:32:56 - INFO - codeparrot_training - Step 6883: {'lr': 0.0004986582521205992, 'samples': 3524608, 'steps': 6883, 'loss/train': 2.7530195713043213}
-03/03/2022 21:32:56 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/03/2022 21:33:02 - INFO - codeparrot_training - Step 6884: {'lr': 0.0004986577029978581, 'samples': 3525120, 'steps': 6884, 'loss/train': 0.9089296460151672}
-03/03/2022 21:33:05 - INFO - codeparrot_training - Step 6885: {'lr': 0.0004986571537630757, 'samples': 3525632, 'steps': 6885, 'loss/train': 1.7144075632095337}
-03/03/2022 21:33:10 - INFO - codeparrot_training - Step 6886: {'lr': 0.0004986566044162523, 'samples': 3526144, 'steps': 6886, 'loss/train': 2.524937868118286}
-03/03/2022 21:33:13 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/03/2022 21:33:15 - INFO - codeparrot_training - Step 6887: {'lr': 0.0004986560549573881, 'samples': 3526656, 'steps': 6887, 'loss/train': 2.253796339035034}
-03/03/2022 21:33:19 - INFO - codeparrot_training - Step 6888: {'lr': 0.0004986555053864833, 'samples': 3527168, 'steps': 6888, 'loss/train': 1.4887548685073853}
-03/03/2022 21:33:21 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/03/2022 21:33:24 - INFO - codeparrot_training - Step 6889: {'lr': 0.0004986549557035381, 'samples': 3527680, 'steps': 6889, 'loss/train': 1.0315910577774048}
-03/03/2022 21:33:27 - INFO - codeparrot_training - Step 6890: {'lr': 0.0004986544059085528, 'samples': 3528192, 'steps': 6890, 'loss/train': 2.51275634765625}
-03/03/2022 21:33:30 - INFO - codeparrot_training - Step 6891: {'lr': 0.0004986538560015277, 'samples': 3528704, 'steps': 6891, 'loss/train': 1.689903736114502}
-03/03/2022 21:33:30 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/03/2022 21:33:36 - INFO - codeparrot_training - Step 6892: {'lr': 0.000498653305982463, 'samples': 3529216, 'steps': 6892, 'loss/train': 2.067504644393921}
-03/03/2022 21:33:39 - INFO - codeparrot_training - Step 6893: {'lr': 0.0004986527558513591, 'samples': 3529728, 'steps': 6893, 'loss/train': 1.8673765659332275}
-03/03/2022 21:33:39 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/03/2022 21:33:44 - INFO - codeparrot_training - Step 6894: {'lr': 0.0004986522056082159, 'samples': 3530240, 'steps': 6894, 'loss/train': 2.642000436782837}
-03/03/2022 21:33:47 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/03/2022 21:33:49 - INFO - codeparrot_training - Step 6895: {'lr': 0.0004986516552530339, 'samples': 3530752, 'steps': 6895, 'loss/train': 2.0790274143218994}
-03/03/2022 21:33:52 - INFO - codeparrot_training - Step 6896: {'lr': 0.0004986511047858134, 'samples': 3531264, 'steps': 6896, 'loss/train': 1.4543057680130005}
-03/03/2022 21:33:55 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/03/2022 21:33:58 - INFO - codeparrot_training - Step 6897: {'lr': 0.0004986505542065545, 'samples': 3531776, 'steps': 6897, 'loss/train': 1.7770870923995972}
-03/03/2022 21:34:01 - INFO - codeparrot_training - Step 6898: {'lr': 0.0004986500035152574, 'samples': 3532288, 'steps': 6898, 'loss/train': 2.6416494846343994}
-03/03/2022 21:34:04 - INFO - codeparrot_training - Step 6899: {'lr': 0.0004986494527119226, 'samples': 3532800, 'steps': 6899, 'loss/train': 1.2631943225860596}
-03/03/2022 21:34:04 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/03/2022 21:34:09 - INFO - codeparrot_training - Step 6900: {'lr': 0.0004986489017965501, 'samples': 3533312, 'steps': 6900, 'loss/train': 1.980369210243225}
-03/03/2022 21:34:12 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/03/2022 21:34:15 - INFO - codeparrot_training - Step 6901: {'lr': 0.0004986483507691403, 'samples': 3533824, 'steps': 6901, 'loss/train': 2.792217254638672}
-03/03/2022 21:34:18 - INFO - codeparrot_training - Step 6902: {'lr': 0.0004986477996296934, 'samples': 3534336, 'steps': 6902, 'loss/train': 1.3373469114303589}
-03/03/2022 21:34:21 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/03/2022 21:34:23 - INFO - codeparrot_training - Step 6903: {'lr': 0.0004986472483782096, 'samples': 3534848, 'steps': 6903, 'loss/train': 2.2768588066101074}
-03/03/2022 21:34:26 - INFO - codeparrot_training - Step 6904: {'lr': 0.0004986466970146891, 'samples': 3535360, 'steps': 6904, 'loss/train': 3.1243975162506104}
-03/03/2022 21:34:29 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/03/2022 21:34:32 - INFO - codeparrot_training - Step 6905: {'lr': 0.0004986461455391323, 'samples': 3535872, 'steps': 6905, 'loss/train': 2.8986916542053223}
-03/03/2022 21:34:35 - INFO - codeparrot_training - Step 6906: {'lr': 0.0004986455939515395, 'samples': 3536384, 'steps': 6906, 'loss/train': 0.9313284158706665}
-03/03/2022 21:34:37 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/03/2022 21:34:40 - INFO - codeparrot_training - Step 6907: {'lr': 0.0004986450422519107, 'samples': 3536896, 'steps': 6907, 'loss/train': 2.318638563156128}
-03/03/2022 21:34:43 - INFO - codeparrot_training - Step 6908: {'lr': 0.0004986444904402463, 'samples': 3537408, 'steps': 6908, 'loss/train': 2.614058256149292}
-03/03/2022 21:34:46 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/03/2022 21:34:49 - INFO - codeparrot_training - Step 6909: {'lr': 0.0004986439385165464, 'samples': 3537920, 'steps': 6909, 'loss/train': 2.3841147422790527}
-03/03/2022 21:34:52 - INFO - codeparrot_training - Step 6910: {'lr': 0.0004986433864808115, 'samples': 3538432, 'steps': 6910, 'loss/train': 2.029212474822998}
-03/03/2022 21:34:55 - INFO - codeparrot_training - Step 6911: {'lr': 0.0004986428343330418, 'samples': 3538944, 'steps': 6911, 'loss/train': 2.8509140014648438}
-03/03/2022 21:34:55 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/03/2022 21:35:00 - INFO - codeparrot_training - Step 6912: {'lr': 0.0004986422820732375, 'samples': 3539456, 'steps': 6912, 'loss/train': 2.558742046356201}
-03/03/2022 21:35:04 - INFO - codeparrot_training - Step 6913: {'lr': 0.0004986417297013987, 'samples': 3539968, 'steps': 6913, 'loss/train': 2.003805637359619}
-03/03/2022 21:35:04 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/03/2022 21:35:09 - INFO - codeparrot_training - Step 6914: {'lr': 0.0004986411772175258, 'samples': 3540480, 'steps': 6914, 'loss/train': 1.6886675357818604}
-03/03/2022 21:35:12 - INFO - codeparrot_training - Step 6915: {'lr': 0.000498640624621619, 'samples': 3540992, 'steps': 6915, 'loss/train': 2.2344326972961426}
-03/03/2022 21:35:12 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/03/2022 21:35:18 - INFO - codeparrot_training - Step 6916: {'lr': 0.0004986400719136786, 'samples': 3541504, 'steps': 6916, 'loss/train': 2.619713544845581}
-03/03/2022 21:35:21 - INFO - codeparrot_training - Step 6917: {'lr': 0.0004986395190937048, 'samples': 3542016, 'steps': 6917, 'loss/train': 1.8155237436294556}
-03/03/2022 21:35:21 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/03/2022 21:35:26 - INFO - codeparrot_training - Step 6918: {'lr': 0.000498638966161698, 'samples': 3542528, 'steps': 6918, 'loss/train': 2.05880069732666}
-03/03/2022 21:35:29 - INFO - codeparrot_training - Step 6919: {'lr': 0.0004986384131176583, 'samples': 3543040, 'steps': 6919, 'loss/train': 3.166419267654419}
-03/03/2022 21:35:29 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/03/2022 21:35:34 - INFO - codeparrot_training - Step 6920: {'lr': 0.0004986378599615858, 'samples': 3543552, 'steps': 6920, 'loss/train': 1.695467472076416}
-03/03/2022 21:35:38 - INFO - codeparrot_training - Step 6921: {'lr': 0.000498637306693481, 'samples': 3544064, 'steps': 6921, 'loss/train': 2.3357343673706055}
-03/03/2022 21:35:38 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/03/2022 21:35:43 - INFO - codeparrot_training - Step 6922: {'lr': 0.0004986367533133441, 'samples': 3544576, 'steps': 6922, 'loss/train': 1.7700395584106445}
-03/03/2022 21:35:46 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/03/2022 21:35:48 - INFO - codeparrot_training - Step 6923: {'lr': 0.0004986361998211752, 'samples': 3545088, 'steps': 6923, 'loss/train': 2.5598840713500977}
-03/03/2022 21:35:51 - INFO - codeparrot_training - Step 6924: {'lr': 0.0004986356462169748, 'samples': 3545600, 'steps': 6924, 'loss/train': 2.1603970527648926}
-03/03/2022 21:35:54 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/03/2022 21:35:56 - INFO - codeparrot_training - Step 6925: {'lr': 0.0004986350925007429, 'samples': 3546112, 'steps': 6925, 'loss/train': 2.3810391426086426}
-03/03/2022 21:36:00 - INFO - codeparrot_training - Step 6926: {'lr': 0.00049863453867248, 'samples': 3546624, 'steps': 6926, 'loss/train': 2.652094841003418}
-03/03/2022 21:36:02 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/03/2022 21:36:05 - INFO - codeparrot_training - Step 6927: {'lr': 0.0004986339847321862, 'samples': 3547136, 'steps': 6927, 'loss/train': 2.689277410507202}
-03/03/2022 21:36:08 - INFO - codeparrot_training - Step 6928: {'lr': 0.0004986334306798616, 'samples': 3547648, 'steps': 6928, 'loss/train': 2.4475128650665283}
-03/03/2022 21:36:10 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/03/2022 21:36:14 - INFO - codeparrot_training - Step 6929: {'lr': 0.0004986328765155068, 'samples': 3548160, 'steps': 6929, 'loss/train': 1.6806471347808838}
-03/03/2022 21:36:17 - INFO - codeparrot_training - Step 6930: {'lr': 0.0004986323222391217, 'samples': 3548672, 'steps': 6930, 'loss/train': 2.0962157249450684}
-03/03/2022 21:36:20 - INFO - codeparrot_training - Step 6931: {'lr': 0.0004986317678507069, 'samples': 3549184, 'steps': 6931, 'loss/train': 2.009881019592285}
-03/03/2022 21:36:20 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/03/2022 21:36:25 - INFO - codeparrot_training - Step 6932: {'lr': 0.0004986312133502623, 'samples': 3549696, 'steps': 6932, 'loss/train': 2.841398000717163}
-03/03/2022 21:36:28 - INFO - codeparrot_training - Step 6933: {'lr': 0.0004986306587377884, 'samples': 3550208, 'steps': 6933, 'loss/train': 2.1095314025878906}
-03/03/2022 21:36:29 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/03/2022 21:36:34 - INFO - codeparrot_training - Step 6934: {'lr': 0.0004986301040132853, 'samples': 3550720, 'steps': 6934, 'loss/train': 2.8218188285827637}
-03/03/2022 21:36:37 - INFO - codeparrot_training - Step 6935: {'lr': 0.0004986295491767533, 'samples': 3551232, 'steps': 6935, 'loss/train': 2.2977161407470703}
-03/03/2022 21:36:37 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/03/2022 21:36:42 - INFO - codeparrot_training - Step 6936: {'lr': 0.0004986289942281927, 'samples': 3551744, 'steps': 6936, 'loss/train': 2.498239040374756}
-03/03/2022 21:36:45 - INFO - codeparrot_training - Step 6937: {'lr': 0.0004986284391676037, 'samples': 3552256, 'steps': 6937, 'loss/train': 0.8468458652496338}
-03/03/2022 21:36:45 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/03/2022 21:36:50 - INFO - codeparrot_training - Step 6938: {'lr': 0.0004986278839949866, 'samples': 3552768, 'steps': 6938, 'loss/train': 1.8566230535507202}
-03/03/2022 21:36:53 - INFO - codeparrot_training - Step 6939: {'lr': 0.0004986273287103416, 'samples': 3553280, 'steps': 6939, 'loss/train': 1.5630115270614624}
-03/03/2022 21:36:54 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/03/2022 21:36:59 - INFO - codeparrot_training - Step 6940: {'lr': 0.0004986267733136689, 'samples': 3553792, 'steps': 6940, 'loss/train': 3.1008193492889404}
-03/03/2022 21:37:02 - INFO - codeparrot_training - Step 6941: {'lr': 0.0004986262178049689, 'samples': 3554304, 'steps': 6941, 'loss/train': 2.336400270462036}
-03/03/2022 21:37:02 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/03/2022 21:37:08 - INFO - codeparrot_training - Step 6942: {'lr': 0.0004986256621842417, 'samples': 3554816, 'steps': 6942, 'loss/train': 1.7941025495529175}
-03/03/2022 21:37:11 - INFO - codeparrot_training - Step 6943: {'lr': 0.0004986251064514878, 'samples': 3555328, 'steps': 6943, 'loss/train': 1.642065405845642}
-03/03/2022 21:37:12 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/03/2022 21:37:16 - INFO - codeparrot_training - Step 6944: {'lr': 0.000498624550606707, 'samples': 3555840, 'steps': 6944, 'loss/train': 2.2676498889923096}
-03/03/2022 21:37:19 - INFO - codeparrot_training - Step 6945: {'lr': 0.0004986239946498999, 'samples': 3556352, 'steps': 6945, 'loss/train': 3.3242783546447754}
-03/03/2022 21:37:21 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/03/2022 21:37:25 - INFO - codeparrot_training - Step 6946: {'lr': 0.0004986234385810668, 'samples': 3556864, 'steps': 6946, 'loss/train': 2.0731842517852783}
-03/03/2022 21:37:28 - INFO - codeparrot_training - Step 6947: {'lr': 0.0004986228824002076, 'samples': 3557376, 'steps': 6947, 'loss/train': 1.7203031778335571}
-03/03/2022 21:37:29 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/03/2022 21:37:33 - INFO - codeparrot_training - Step 6948: {'lr': 0.0004986223261073228, 'samples': 3557888, 'steps': 6948, 'loss/train': 0.8343364596366882}
-03/03/2022 21:37:36 - INFO - codeparrot_training - Step 6949: {'lr': 0.0004986217697024128, 'samples': 3558400, 'steps': 6949, 'loss/train': 2.534794569015503}
-03/03/2022 21:37:38 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/03/2022 21:37:42 - INFO - codeparrot_training - Step 6950: {'lr': 0.0004986212131854775, 'samples': 3558912, 'steps': 6950, 'loss/train': 1.3837968111038208}
-03/03/2022 21:37:45 - INFO - codeparrot_training - Step 6951: {'lr': 0.0004986206565565173, 'samples': 3559424, 'steps': 6951, 'loss/train': 1.647481918334961}
-03/03/2022 21:37:46 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/03/2022 21:37:50 - INFO - codeparrot_training - Step 6952: {'lr': 0.0004986200998155325, 'samples': 3559936, 'steps': 6952, 'loss/train': 2.440647840499878}
-03/03/2022 21:37:53 - INFO - codeparrot_training - Step 6953: {'lr': 0.0004986195429625234, 'samples': 3560448, 'steps': 6953, 'loss/train': 2.9817192554473877}
-03/03/2022 21:37:54 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/03/2022 21:37:58 - INFO - codeparrot_training - Step 6954: {'lr': 0.0004986189859974901, 'samples': 3560960, 'steps': 6954, 'loss/train': 1.6298425197601318}
-03/03/2022 21:38:02 - INFO - codeparrot_training - Step 6955: {'lr': 0.000498618428920433, 'samples': 3561472, 'steps': 6955, 'loss/train': 1.734562873840332}
-03/03/2022 21:38:02 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/03/2022 21:38:07 - INFO - codeparrot_training - Step 6956: {'lr': 0.0004986178717313522, 'samples': 3561984, 'steps': 6956, 'loss/train': 2.3774709701538086}
-03/03/2022 21:38:10 - INFO - codeparrot_training - Step 6957: {'lr': 0.000498617314430248, 'samples': 3562496, 'steps': 6957, 'loss/train': 2.629561424255371}
-03/03/2022 21:38:13 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/03/2022 21:38:16 - INFO - codeparrot_training - Step 6958: {'lr': 0.0004986167570171208, 'samples': 3563008, 'steps': 6958, 'loss/train': 2.154327392578125}
-03/03/2022 21:38:19 - INFO - codeparrot_training - Step 6959: {'lr': 0.0004986161994919706, 'samples': 3563520, 'steps': 6959, 'loss/train': 1.624696969985962}
-03/03/2022 21:38:21 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/03/2022 21:38:24 - INFO - codeparrot_training - Step 6960: {'lr': 0.0004986156418547978, 'samples': 3564032, 'steps': 6960, 'loss/train': 2.4273369312286377}
-03/03/2022 21:38:27 - INFO - codeparrot_training - Step 6961: {'lr': 0.0004986150841056027, 'samples': 3564544, 'steps': 6961, 'loss/train': 2.930265426635742}
-03/03/2022 21:38:29 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/03/2022 21:38:33 - INFO - codeparrot_training - Step 6962: {'lr': 0.0004986145262443854, 'samples': 3565056, 'steps': 6962, 'loss/train': 3.4959800243377686}
-03/03/2022 21:38:36 - INFO - codeparrot_training - Step 6963: {'lr': 0.0004986139682711463, 'samples': 3565568, 'steps': 6963, 'loss/train': 2.9480080604553223}
-03/03/2022 21:38:37 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/03/2022 21:38:41 - INFO - codeparrot_training - Step 6964: {'lr': 0.0004986134101858854, 'samples': 3566080, 'steps': 6964, 'loss/train': 2.7538416385650635}
-03/03/2022 21:38:44 - INFO - codeparrot_training - Step 6965: {'lr': 0.0004986128519886033, 'samples': 3566592, 'steps': 6965, 'loss/train': 2.5103702545166016}
-03/03/2022 21:38:46 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/03/2022 21:38:49 - INFO - codeparrot_training - Step 6966: {'lr': 0.0004986122936793, 'samples': 3567104, 'steps': 6966, 'loss/train': 1.5963984727859497}
-03/03/2022 21:38:53 - INFO - codeparrot_training - Step 6967: {'lr': 0.000498611735257976, 'samples': 3567616, 'steps': 6967, 'loss/train': 2.6583046913146973}
-03/03/2022 21:38:54 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/03/2022 21:38:58 - INFO - codeparrot_training - Step 6968: {'lr': 0.0004986111767246313, 'samples': 3568128, 'steps': 6968, 'loss/train': 2.6736676692962646}
-03/03/2022 21:39:01 - INFO - codeparrot_training - Step 6969: {'lr': 0.0004986106180792662, 'samples': 3568640, 'steps': 6969, 'loss/train': 2.3903555870056152}
-03/03/2022 21:39:02 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/03/2022 21:39:06 - INFO - codeparrot_training - Step 6970: {'lr': 0.000498610059321881, 'samples': 3569152, 'steps': 6970, 'loss/train': 2.7536544799804688}
-03/03/2022 21:39:09 - INFO - codeparrot_training - Step 6971: {'lr': 0.000498609500452476, 'samples': 3569664, 'steps': 6971, 'loss/train': 2.695479393005371}
-03/03/2022 21:39:11 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/03/2022 21:39:15 - INFO - codeparrot_training - Step 6972: {'lr': 0.0004986089414710513, 'samples': 3570176, 'steps': 6972, 'loss/train': 3.254647731781006}
-03/03/2022 21:39:18 - INFO - codeparrot_training - Step 6973: {'lr': 0.0004986083823776073, 'samples': 3570688, 'steps': 6973, 'loss/train': 2.285315990447998}
-03/03/2022 21:39:19 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/03/2022 21:39:23 - INFO - codeparrot_training - Step 6974: {'lr': 0.0004986078231721443, 'samples': 3571200, 'steps': 6974, 'loss/train': 2.7025766372680664}
-03/03/2022 21:39:26 - INFO - codeparrot_training - Step 6975: {'lr': 0.0004986072638546623, 'samples': 3571712, 'steps': 6975, 'loss/train': 2.3361661434173584}
-03/03/2022 21:39:27 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/03/2022 21:39:31 - INFO - codeparrot_training - Step 6976: {'lr': 0.0004986067044251617, 'samples': 3572224, 'steps': 6976, 'loss/train': 2.1565442085266113}
-03/03/2022 21:39:35 - INFO - codeparrot_training - Step 6977: {'lr': 0.0004986061448836428, 'samples': 3572736, 'steps': 6977, 'loss/train': 2.534627914428711}
-03/03/2022 21:39:36 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/03/2022 21:39:40 - INFO - codeparrot_training - Step 6978: {'lr': 0.0004986055852301058, 'samples': 3573248, 'steps': 6978, 'loss/train': 2.315654993057251}
-03/03/2022 21:39:43 - INFO - codeparrot_training - Step 6979: {'lr': 0.000498605025464551, 'samples': 3573760, 'steps': 6979, 'loss/train': 1.9599231481552124}
-03/03/2022 21:39:44 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/03/2022 21:39:48 - INFO - codeparrot_training - Step 6980: {'lr': 0.0004986044655869786, 'samples': 3574272, 'steps': 6980, 'loss/train': 1.5966154336929321}
-03/03/2022 21:39:51 - INFO - codeparrot_training - Step 6981: {'lr': 0.0004986039055973889, 'samples': 3574784, 'steps': 6981, 'loss/train': 1.894195795059204}
-03/03/2022 21:39:52 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/03/2022 21:39:57 - INFO - codeparrot_training - Step 6982: {'lr': 0.000498603345495782, 'samples': 3575296, 'steps': 6982, 'loss/train': 2.0614988803863525}
-03/03/2022 21:40:00 - INFO - codeparrot_training - Step 6983: {'lr': 0.0004986027852821583, 'samples': 3575808, 'steps': 6983, 'loss/train': 1.488608479499817}
-03/03/2022 21:40:01 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/03/2022 21:40:05 - INFO - codeparrot_training - Step 6984: {'lr': 0.000498602224956518, 'samples': 3576320, 'steps': 6984, 'loss/train': 1.0302248001098633}
-03/03/2022 21:40:08 - INFO - codeparrot_training - Step 6985: {'lr': 0.0004986016645188615, 'samples': 3576832, 'steps': 6985, 'loss/train': 2.331852436065674}
-03/03/2022 21:40:09 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/03/2022 21:40:14 - INFO - codeparrot_training - Step 6986: {'lr': 0.0004986011039691889, 'samples': 3577344, 'steps': 6986, 'loss/train': 2.7414307594299316}
-03/03/2022 21:40:17 - INFO - codeparrot_training - Step 6987: {'lr': 0.0004986005433075004, 'samples': 3577856, 'steps': 6987, 'loss/train': 2.5615487098693848}
-03/03/2022 21:40:17 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/03/2022 21:40:23 - INFO - codeparrot_training - Step 6988: {'lr': 0.0004985999825337964, 'samples': 3578368, 'steps': 6988, 'loss/train': 1.5982303619384766}
-03/03/2022 21:40:26 - INFO - codeparrot_training - Step 6989: {'lr': 0.000498599421648077, 'samples': 3578880, 'steps': 6989, 'loss/train': 2.2695677280426025}
-03/03/2022 21:40:29 - INFO - codeparrot_training - Step 6990: {'lr': 0.0004985988606503426, 'samples': 3579392, 'steps': 6990, 'loss/train': 1.5967553853988647}
-03/03/2022 21:40:29 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/03/2022 21:40:34 - INFO - codeparrot_training - Step 6991: {'lr': 0.0004985982995405933, 'samples': 3579904, 'steps': 6991, 'loss/train': 2.6944682598114014}
-03/03/2022 21:40:37 - INFO - codeparrot_training - Step 6992: {'lr': 0.0004985977383188296, 'samples': 3580416, 'steps': 6992, 'loss/train': 2.849491596221924}
-03/03/2022 21:40:38 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/03/2022 21:40:43 - INFO - codeparrot_training - Step 6993: {'lr': 0.0004985971769850515, 'samples': 3580928, 'steps': 6993, 'loss/train': 2.6614692211151123}
-03/03/2022 21:40:46 - INFO - codeparrot_training - Step 6994: {'lr': 0.0004985966155392593, 'samples': 3581440, 'steps': 6994, 'loss/train': 1.833506464958191}
-03/03/2022 21:40:46 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/03/2022 21:40:51 - INFO - codeparrot_training - Step 6995: {'lr': 0.0004985960539814534, 'samples': 3581952, 'steps': 6995, 'loss/train': 0.6043466925621033}
-03/03/2022 21:40:54 - INFO - codeparrot_training - Step 6996: {'lr': 0.000498595492311634, 'samples': 3582464, 'steps': 6996, 'loss/train': 2.468519449234009}
-03/03/2022 21:40:55 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/03/2022 21:41:00 - INFO - codeparrot_training - Step 6997: {'lr': 0.0004985949305298012, 'samples': 3582976, 'steps': 6997, 'loss/train': 3.042823076248169}
-03/03/2022 21:41:03 - INFO - codeparrot_training - Step 6998: {'lr': 0.0004985943686359554, 'samples': 3583488, 'steps': 6998, 'loss/train': 1.4480152130126953}
-03/03/2022 21:41:03 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/03/2022 21:41:08 - INFO - codeparrot_training - Step 6999: {'lr': 0.0004985938066300968, 'samples': 3584000, 'steps': 6999, 'loss/train': 2.0852127075195312}
-03/03/2022 21:41:11 - INFO - codeparrot_training - Step 7000: {'lr': 0.0004985932445122257, 'samples': 3584512, 'steps': 7000, 'loss/train': 2.7117300033569336}
-03/03/2022 21:41:11 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/03/2022 21:41:16 - INFO - codeparrot_training - Step 7001: {'lr': 0.0004985926822823422, 'samples': 3585024, 'steps': 7001, 'loss/train': 2.3185582160949707}
-03/03/2022 21:41:19 - INFO - codeparrot_training - Step 7002: {'lr': 0.0004985921199404467, 'samples': 3585536, 'steps': 7002, 'loss/train': 2.597712993621826}
-03/03/2022 21:41:20 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/03/2022 21:41:25 - INFO - codeparrot_training - Step 7003: {'lr': 0.0004985915574865395, 'samples': 3586048, 'steps': 7003, 'loss/train': 2.839611768722534}
-03/03/2022 21:41:28 - INFO - codeparrot_training - Step 7004: {'lr': 0.0004985909949206209, 'samples': 3586560, 'steps': 7004, 'loss/train': 2.8143370151519775}
-03/03/2022 21:41:28 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/03/2022 21:41:33 - INFO - codeparrot_training - Step 7005: {'lr': 0.0004985904322426909, 'samples': 3587072, 'steps': 7005, 'loss/train': 2.2023117542266846}
-03/03/2022 21:41:36 - INFO - codeparrot_training - Step 7006: {'lr': 0.0004985898694527498, 'samples': 3587584, 'steps': 7006, 'loss/train': 1.3122498989105225}
-03/03/2022 21:41:37 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/03/2022 21:41:42 - INFO - codeparrot_training - Step 7007: {'lr': 0.000498589306550798, 'samples': 3588096, 'steps': 7007, 'loss/train': 2.7977468967437744}
-03/03/2022 21:41:45 - INFO - codeparrot_training - Step 7008: {'lr': 0.0004985887435368357, 'samples': 3588608, 'steps': 7008, 'loss/train': 2.095107316970825}
-03/03/2022 21:41:45 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/03/2022 21:41:50 - INFO - codeparrot_training - Step 7009: {'lr': 0.0004985881804108632, 'samples': 3589120, 'steps': 7009, 'loss/train': 3.1803476810455322}
-03/03/2022 21:41:53 - INFO - codeparrot_training - Step 7010: {'lr': 0.0004985876171728807, 'samples': 3589632, 'steps': 7010, 'loss/train': 2.8384780883789062}
-03/03/2022 21:41:54 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/03/2022 21:41:59 - INFO - codeparrot_training - Step 7011: {'lr': 0.0004985870538228884, 'samples': 3590144, 'steps': 7011, 'loss/train': 1.4130407571792603}
-03/03/2022 21:42:02 - INFO - codeparrot_training - Step 7012: {'lr': 0.0004985864903608866, 'samples': 3590656, 'steps': 7012, 'loss/train': 0.31241706013679504}
-03/03/2022 21:42:02 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/03/2022 21:42:07 - INFO - codeparrot_training - Step 7013: {'lr': 0.0004985859267868756, 'samples': 3591168, 'steps': 7013, 'loss/train': 1.4659441709518433}
-03/03/2022 21:42:10 - INFO - codeparrot_training - Step 7014: {'lr': 0.0004985853631008557, 'samples': 3591680, 'steps': 7014, 'loss/train': 1.5463563203811646}
-03/03/2022 21:42:10 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/03/2022 21:42:16 - INFO - codeparrot_training - Step 7015: {'lr': 0.000498584799302827, 'samples': 3592192, 'steps': 7015, 'loss/train': 2.321715831756592}
-03/03/2022 21:42:19 - INFO - codeparrot_training - Step 7016: {'lr': 0.0004985842353927897, 'samples': 3592704, 'steps': 7016, 'loss/train': 1.987141728401184}
-03/03/2022 21:42:24 - INFO - codeparrot_training - Step 7017: {'lr': 0.0004985836713707443, 'samples': 3593216, 'steps': 7017, 'loss/train': 1.1007112264633179}
-03/03/2022 21:42:27 - INFO - codeparrot_training - Step 7018: {'lr': 0.000498583107236691, 'samples': 3593728, 'steps': 7018, 'loss/train': 1.4406578540802002}
-03/03/2022 21:42:28 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/03/2022 21:42:32 - INFO - codeparrot_training - Step 7019: {'lr': 0.0004985825429906299, 'samples': 3594240, 'steps': 7019, 'loss/train': 1.83169686794281}
-03/03/2022 21:42:36 - INFO - codeparrot_training - Step 7020: {'lr': 0.0004985819786325614, 'samples': 3594752, 'steps': 7020, 'loss/train': 2.8888087272644043}
-03/03/2022 21:42:36 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/03/2022 21:42:41 - INFO - codeparrot_training - Step 7021: {'lr': 0.0004985814141624856, 'samples': 3595264, 'steps': 7021, 'loss/train': 2.0024964809417725}
-03/03/2022 21:42:44 - INFO - codeparrot_training - Step 7022: {'lr': 0.000498580849580403, 'samples': 3595776, 'steps': 7022, 'loss/train': 1.7092065811157227}
-03/03/2022 21:42:44 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/03/2022 21:42:49 - INFO - codeparrot_training - Step 7023: {'lr': 0.0004985802848863135, 'samples': 3596288, 'steps': 7023, 'loss/train': 2.5228967666625977}
-03/03/2022 21:42:52 - INFO - codeparrot_training - Step 7024: {'lr': 0.0004985797200802176, 'samples': 3596800, 'steps': 7024, 'loss/train': 1.8910293579101562}
-03/03/2022 21:42:53 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/03/2022 21:42:58 - INFO - codeparrot_training - Step 7025: {'lr': 0.0004985791551621158, 'samples': 3597312, 'steps': 7025, 'loss/train': 2.2118945121765137}
-03/03/2022 21:43:01 - INFO - codeparrot_training - Step 7026: {'lr': 0.0004985785901320078, 'samples': 3597824, 'steps': 7026, 'loss/train': 2.315464973449707}
-03/03/2022 21:43:01 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/03/2022 21:43:06 - INFO - codeparrot_training - Step 7027: {'lr': 0.0004985780249898941, 'samples': 3598336, 'steps': 7027, 'loss/train': 1.411247968673706}
-03/03/2022 21:43:09 - INFO - codeparrot_training - Step 7028: {'lr': 0.0004985774597357751, 'samples': 3598848, 'steps': 7028, 'loss/train': 2.9359753131866455}
-03/03/2022 21:43:09 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/03/2022 21:43:15 - INFO - codeparrot_training - Step 7029: {'lr': 0.0004985768943696509, 'samples': 3599360, 'steps': 7029, 'loss/train': 2.7751822471618652}
-03/03/2022 21:43:17 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/03/2022 21:43:20 - INFO - codeparrot_training - Step 7030: {'lr': 0.0004985763288915217, 'samples': 3599872, 'steps': 7030, 'loss/train': 2.2026727199554443}
-03/03/2022 21:43:23 - INFO - codeparrot_training - Step 7031: {'lr': 0.0004985757633013879, 'samples': 3600384, 'steps': 7031, 'loss/train': 1.1224991083145142}
-03/03/2022 21:43:26 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/03/2022 21:43:28 - INFO - codeparrot_training - Step 7032: {'lr': 0.0004985751975992497, 'samples': 3600896, 'steps': 7032, 'loss/train': 1.5102639198303223}
-03/03/2022 21:43:31 - INFO - codeparrot_training - Step 7033: {'lr': 0.0004985746317851074, 'samples': 3601408, 'steps': 7033, 'loss/train': 2.071038007736206}
-03/03/2022 21:43:34 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/03/2022 21:43:37 - INFO - codeparrot_training - Step 7034: {'lr': 0.0004985740658589612, 'samples': 3601920, 'steps': 7034, 'loss/train': 2.2184393405914307}
-03/03/2022 21:43:40 - INFO - codeparrot_training - Step 7035: {'lr': 0.0004985734998208112, 'samples': 3602432, 'steps': 7035, 'loss/train': 2.8509626388549805}
-03/03/2022 21:43:42 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/03/2022 21:43:45 - INFO - codeparrot_training - Step 7036: {'lr': 0.000498572933670658, 'samples': 3602944, 'steps': 7036, 'loss/train': 1.2124779224395752}
-03/03/2022 21:43:48 - INFO - codeparrot_training - Step 7037: {'lr': 0.0004985723674085016, 'samples': 3603456, 'steps': 7037, 'loss/train': 1.3882131576538086}
-03/03/2022 21:43:52 - INFO - codeparrot_training - Step 7038: {'lr': 0.0004985718010343424, 'samples': 3603968, 'steps': 7038, 'loss/train': 1.2735610008239746}
-03/03/2022 21:43:52 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/03/2022 21:43:57 - INFO - codeparrot_training - Step 7039: {'lr': 0.0004985712345481805, 'samples': 3604480, 'steps': 7039, 'loss/train': 1.7831660509109497}
-03/03/2022 21:44:00 - INFO - codeparrot_training - Step 7040: {'lr': 0.0004985706679500163, 'samples': 3604992, 'steps': 7040, 'loss/train': 2.4551289081573486}
-03/03/2022 21:44:00 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/03/2022 21:44:05 - INFO - codeparrot_training - Step 7041: {'lr': 0.0004985701012398499, 'samples': 3605504, 'steps': 7041, 'loss/train': 1.3309341669082642}
-03/03/2022 21:44:09 - INFO - codeparrot_training - Step 7042: {'lr': 0.0004985695344176817, 'samples': 3606016, 'steps': 7042, 'loss/train': 2.500018835067749}
-03/03/2022 21:44:09 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/03/2022 21:44:14 - INFO - codeparrot_training - Step 7043: {'lr': 0.0004985689674835119, 'samples': 3606528, 'steps': 7043, 'loss/train': 1.193724274635315}
-03/03/2022 21:44:16 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/03/2022 21:44:19 - INFO - codeparrot_training - Step 7044: {'lr': 0.0004985684004373409, 'samples': 3607040, 'steps': 7044, 'loss/train': 2.3250532150268555}
-03/03/2022 21:44:22 - INFO - codeparrot_training - Step 7045: {'lr': 0.0004985678332791686, 'samples': 3607552, 'steps': 7045, 'loss/train': 6.9712677001953125}
-03/03/2022 21:44:25 - INFO - codeparrot_training - Step 7046: {'lr': 0.0004985672660089956, 'samples': 3608064, 'steps': 7046, 'loss/train': 2.703394651412964}
-03/03/2022 21:44:26 - INFO - codeparrot_training - Skipping example with length 983 (seq_length=1024)
-03/03/2022 21:44:31 - INFO - codeparrot_training - Step 7047: {'lr': 0.000498566698626822, 'samples': 3608576, 'steps': 7047, 'loss/train': 2.608208179473877}
-03/03/2022 21:44:34 - INFO - codeparrot_training - Step 7048: {'lr': 0.000498566131132648, 'samples': 3609088, 'steps': 7048, 'loss/train': 2.494962215423584}
-03/03/2022 21:44:34 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/03/2022 21:44:39 - INFO - codeparrot_training - Step 7049: {'lr': 0.0004985655635264739, 'samples': 3609600, 'steps': 7049, 'loss/train': 2.18489146232605}
-03/03/2022 21:44:42 - INFO - codeparrot_training - Step 7050: {'lr': 0.0004985649958083001, 'samples': 3610112, 'steps': 7050, 'loss/train': 2.142348527908325}
-03/03/2022 21:44:42 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/03/2022 21:44:48 - INFO - codeparrot_training - Step 7051: {'lr': 0.0004985644279781268, 'samples': 3610624, 'steps': 7051, 'loss/train': 2.4523794651031494}
-03/03/2022 21:44:51 - INFO - codeparrot_training - Step 7052: {'lr': 0.0004985638600359542, 'samples': 3611136, 'steps': 7052, 'loss/train': 2.655094623565674}
-03/03/2022 21:44:52 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/03/2022 21:44:56 - INFO - codeparrot_training - Step 7053: {'lr': 0.0004985632919817824, 'samples': 3611648, 'steps': 7053, 'loss/train': 1.539817214012146}
-03/03/2022 21:44:59 - INFO - codeparrot_training - Step 7054: {'lr': 0.000498562723815612, 'samples': 3612160, 'steps': 7054, 'loss/train': 2.063246488571167}
-03/03/2022 21:45:01 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/03/2022 21:45:05 - INFO - codeparrot_training - Step 7055: {'lr': 0.000498562155537443, 'samples': 3612672, 'steps': 7055, 'loss/train': 1.643097996711731}
-03/03/2022 21:45:08 - INFO - codeparrot_training - Step 7056: {'lr': 0.0004985615871472757, 'samples': 3613184, 'steps': 7056, 'loss/train': 1.7393503189086914}
-03/03/2022 21:45:13 - INFO - codeparrot_training - Step 7057: {'lr': 0.0004985610186451104, 'samples': 3613696, 'steps': 7057, 'loss/train': 1.9542322158813477}
-03/03/2022 21:45:16 - INFO - codeparrot_training - Step 7058: {'lr': 0.0004985604500309473, 'samples': 3614208, 'steps': 7058, 'loss/train': 3.0557169914245605}
-03/03/2022 21:45:17 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/03/2022 21:45:21 - INFO - codeparrot_training - Step 7059: {'lr': 0.0004985598813047868, 'samples': 3614720, 'steps': 7059, 'loss/train': 1.0942376852035522}
-03/03/2022 21:45:24 - INFO - codeparrot_training - Step 7060: {'lr': 0.000498559312466629, 'samples': 3615232, 'steps': 7060, 'loss/train': 1.4864863157272339}
-03/03/2022 21:45:25 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/03/2022 21:45:30 - INFO - codeparrot_training - Step 7061: {'lr': 0.0004985587435164742, 'samples': 3615744, 'steps': 7061, 'loss/train': 2.2452688217163086}
-03/03/2022 21:45:33 - INFO - codeparrot_training - Step 7062: {'lr': 0.0004985581744543226, 'samples': 3616256, 'steps': 7062, 'loss/train': 1.91667640209198}
-03/03/2022 21:45:34 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/03/2022 21:45:38 - INFO - codeparrot_training - Step 7063: {'lr': 0.0004985576052801747, 'samples': 3616768, 'steps': 7063, 'loss/train': 2.1245017051696777}
-03/03/2022 21:45:41 - INFO - codeparrot_training - Step 7064: {'lr': 0.0004985570359940304, 'samples': 3617280, 'steps': 7064, 'loss/train': 2.3706607818603516}
-03/03/2022 21:45:42 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/03/2022 21:45:47 - INFO - codeparrot_training - Step 7065: {'lr': 0.0004985564665958901, 'samples': 3617792, 'steps': 7065, 'loss/train': 1.8195856809616089}
-03/03/2022 21:45:50 - INFO - codeparrot_training - Step 7066: {'lr': 0.0004985558970857543, 'samples': 3618304, 'steps': 7066, 'loss/train': 2.524890899658203}
-03/03/2022 21:45:50 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/03/2022 21:45:55 - INFO - codeparrot_training - Step 7067: {'lr': 0.000498555327463623, 'samples': 3618816, 'steps': 7067, 'loss/train': 0.9142712354660034}
-03/03/2022 21:45:59 - INFO - codeparrot_training - Step 7068: {'lr': 0.0004985547577294963, 'samples': 3619328, 'steps': 7068, 'loss/train': 2.721813917160034}
-03/03/2022 21:45:59 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/03/2022 21:46:04 - INFO - codeparrot_training - Step 7069: {'lr': 0.0004985541878833749, 'samples': 3619840, 'steps': 7069, 'loss/train': 2.32293963432312}
-03/03/2022 21:46:07 - INFO - codeparrot_training - Step 7070: {'lr': 0.0004985536179252587, 'samples': 3620352, 'steps': 7070, 'loss/train': 2.8374626636505127}
-03/03/2022 21:46:08 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/03/2022 21:46:12 - INFO - codeparrot_training - Step 7071: {'lr': 0.0004985530478551481, 'samples': 3620864, 'steps': 7071, 'loss/train': 2.282701253890991}
-03/03/2022 21:46:15 - INFO - codeparrot_training - Step 7072: {'lr': 0.0004985524776730434, 'samples': 3621376, 'steps': 7072, 'loss/train': 2.3422515392303467}
-03/03/2022 21:46:16 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/03/2022 21:46:21 - INFO - codeparrot_training - Step 7073: {'lr': 0.0004985519073789447, 'samples': 3621888, 'steps': 7073, 'loss/train': 0.1379852592945099}
-03/03/2022 21:46:24 - INFO - codeparrot_training - Step 7074: {'lr': 0.0004985513369728524, 'samples': 3622400, 'steps': 7074, 'loss/train': 2.533241033554077}
-03/03/2022 21:46:27 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/03/2022 21:46:29 - INFO - codeparrot_training - Step 7075: {'lr': 0.0004985507664547666, 'samples': 3622912, 'steps': 7075, 'loss/train': 2.0152015686035156}
-03/03/2022 21:46:33 - INFO - codeparrot_training - Step 7076: {'lr': 0.0004985501958246878, 'samples': 3623424, 'steps': 7076, 'loss/train': 2.1825411319732666}
-03/03/2022 21:46:35 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/03/2022 21:46:38 - INFO - codeparrot_training - Step 7077: {'lr': 0.000498549625082616, 'samples': 3623936, 'steps': 7077, 'loss/train': 2.183351993560791}
-03/03/2022 21:46:41 - INFO - codeparrot_training - Step 7078: {'lr': 0.0004985490542285516, 'samples': 3624448, 'steps': 7078, 'loss/train': 3.4817683696746826}
-03/03/2022 21:46:44 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/03/2022 21:46:46 - INFO - codeparrot_training - Step 7079: {'lr': 0.0004985484832624949, 'samples': 3624960, 'steps': 7079, 'loss/train': 3.1246883869171143}
-03/03/2022 21:46:50 - INFO - codeparrot_training - Step 7080: {'lr': 0.000498547912184446, 'samples': 3625472, 'steps': 7080, 'loss/train': 1.9132784605026245}
-03/03/2022 21:46:52 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/03/2022 21:46:55 - INFO - codeparrot_training - Step 7081: {'lr': 0.0004985473409944054, 'samples': 3625984, 'steps': 7081, 'loss/train': 2.35677433013916}
-03/03/2022 21:46:58 - INFO - codeparrot_training - Step 7082: {'lr': 0.000498546769692373, 'samples': 3626496, 'steps': 7082, 'loss/train': 2.3986053466796875}
-03/03/2022 21:47:00 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/03/2022 21:47:03 - INFO - codeparrot_training - Step 7083: {'lr': 0.0004985461982783494, 'samples': 3627008, 'steps': 7083, 'loss/train': 2.2899091243743896}
-03/03/2022 21:47:06 - INFO - codeparrot_training - Step 7084: {'lr': 0.0004985456267523346, 'samples': 3627520, 'steps': 7084, 'loss/train': 2.2331976890563965}
-03/03/2022 21:47:09 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/03/2022 21:47:12 - INFO - codeparrot_training - Step 7085: {'lr': 0.0004985450551143291, 'samples': 3628032, 'steps': 7085, 'loss/train': 1.831786036491394}
-03/03/2022 21:47:15 - INFO - codeparrot_training - Step 7086: {'lr': 0.000498544483364333, 'samples': 3628544, 'steps': 7086, 'loss/train': 2.339641571044922}
-03/03/2022 21:47:17 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/03/2022 21:47:20 - INFO - codeparrot_training - Step 7087: {'lr': 0.0004985439115023465, 'samples': 3629056, 'steps': 7087, 'loss/train': 2.4696474075317383}
-03/03/2022 21:47:23 - INFO - codeparrot_training - Step 7088: {'lr': 0.0004985433395283701, 'samples': 3629568, 'steps': 7088, 'loss/train': 2.3370609283447266}
-03/03/2022 21:47:25 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/03/2022 21:47:28 - INFO - codeparrot_training - Step 7089: {'lr': 0.0004985427674424038, 'samples': 3630080, 'steps': 7089, 'loss/train': 2.1709792613983154}
-03/03/2022 21:47:32 - INFO - codeparrot_training - Step 7090: {'lr': 0.000498542195244448, 'samples': 3630592, 'steps': 7090, 'loss/train': 1.569879412651062}
-03/03/2022 21:47:34 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/03/2022 21:47:37 - INFO - codeparrot_training - Step 7091: {'lr': 0.0004985416229345029, 'samples': 3631104, 'steps': 7091, 'loss/train': 2.5935912132263184}
-03/03/2022 21:47:40 - INFO - codeparrot_training - Step 7092: {'lr': 0.0004985410505125689, 'samples': 3631616, 'steps': 7092, 'loss/train': 3.2731564044952393}
-03/03/2022 21:47:42 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/03/2022 21:47:45 - INFO - codeparrot_training - Step 7093: {'lr': 0.0004985404779786459, 'samples': 3632128, 'steps': 7093, 'loss/train': 3.098583459854126}
-03/03/2022 21:47:48 - INFO - codeparrot_training - Step 7094: {'lr': 0.0004985399053327346, 'samples': 3632640, 'steps': 7094, 'loss/train': 2.640101194381714}
-03/03/2022 21:47:50 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/03/2022 21:47:54 - INFO - codeparrot_training - Step 7095: {'lr': 0.000498539332574835, 'samples': 3633152, 'steps': 7095, 'loss/train': 2.308123826980591}
-03/03/2022 21:47:57 - INFO - codeparrot_training - Step 7096: {'lr': 0.0004985387597049474, 'samples': 3633664, 'steps': 7096, 'loss/train': 2.5262434482574463}
-03/03/2022 21:47:59 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/03/2022 21:48:02 - INFO - codeparrot_training - Step 7097: {'lr': 0.0004985381867230721, 'samples': 3634176, 'steps': 7097, 'loss/train': 2.205275774002075}
-03/03/2022 21:48:06 - INFO - codeparrot_training - Step 7098: {'lr': 0.0004985376136292093, 'samples': 3634688, 'steps': 7098, 'loss/train': 2.170966386795044}
-03/03/2022 21:48:08 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/03/2022 21:48:11 - INFO - codeparrot_training - Step 7099: {'lr': 0.0004985370404233592, 'samples': 3635200, 'steps': 7099, 'loss/train': 2.4115099906921387}
-03/03/2022 21:48:14 - INFO - codeparrot_training - Step 7100: {'lr': 0.0004985364671055223, 'samples': 3635712, 'steps': 7100, 'loss/train': 1.300326943397522}
-03/03/2022 21:48:16 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/03/2022 21:48:19 - INFO - codeparrot_training - Step 7101: {'lr': 0.0004985358936756985, 'samples': 3636224, 'steps': 7101, 'loss/train': 3.2375106811523438}
-03/03/2022 21:48:22 - INFO - codeparrot_training - Step 7102: {'lr': 0.0004985353201338885, 'samples': 3636736, 'steps': 7102, 'loss/train': 2.4185190200805664}
-03/03/2022 21:48:25 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/03/2022 21:48:28 - INFO - codeparrot_training - Step 7103: {'lr': 0.0004985347464800921, 'samples': 3637248, 'steps': 7103, 'loss/train': 2.8296611309051514}
-03/03/2022 21:48:31 - INFO - codeparrot_training - Step 7104: {'lr': 0.0004985341727143099, 'samples': 3637760, 'steps': 7104, 'loss/train': 2.7894253730773926}
-03/03/2022 21:48:34 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/03/2022 21:48:36 - INFO - codeparrot_training - Step 7105: {'lr': 0.000498533598836542, 'samples': 3638272, 'steps': 7105, 'loss/train': 2.300063133239746}
-03/03/2022 21:48:39 - INFO - codeparrot_training - Step 7106: {'lr': 0.0004985330248467888, 'samples': 3638784, 'steps': 7106, 'loss/train': 2.1254117488861084}
-03/03/2022 21:48:42 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/03/2022 21:48:45 - INFO - codeparrot_training - Step 7107: {'lr': 0.0004985324507450504, 'samples': 3639296, 'steps': 7107, 'loss/train': 1.306634545326233}
-03/03/2022 21:48:48 - INFO - codeparrot_training - Step 7108: {'lr': 0.000498531876531327, 'samples': 3639808, 'steps': 7108, 'loss/train': 2.668778419494629}
-03/03/2022 21:48:51 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/03/2022 21:48:53 - INFO - codeparrot_training - Step 7109: {'lr': 0.0004985313022056191, 'samples': 3640320, 'steps': 7109, 'loss/train': 1.4376705884933472}
-03/03/2022 21:48:56 - INFO - codeparrot_training - Step 7110: {'lr': 0.0004985307277679267, 'samples': 3640832, 'steps': 7110, 'loss/train': 2.4055910110473633}
-03/03/2022 21:48:59 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/03/2022 21:49:02 - INFO - codeparrot_training - Step 7111: {'lr': 0.0004985301532182503, 'samples': 3641344, 'steps': 7111, 'loss/train': 2.304910182952881}
-03/03/2022 21:49:05 - INFO - codeparrot_training - Step 7112: {'lr': 0.0004985295785565901, 'samples': 3641856, 'steps': 7112, 'loss/train': 2.2207283973693848}
-03/03/2022 21:49:07 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/03/2022 21:49:10 - INFO - codeparrot_training - Step 7113: {'lr': 0.0004985290037829462, 'samples': 3642368, 'steps': 7113, 'loss/train': 2.508676290512085}
-03/03/2022 21:49:13 - INFO - codeparrot_training - Step 7114: {'lr': 0.000498528428897319, 'samples': 3642880, 'steps': 7114, 'loss/train': 2.260922431945801}
-03/03/2022 21:49:16 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/03/2022 21:49:19 - INFO - codeparrot_training - Step 7115: {'lr': 0.0004985278538997088, 'samples': 3643392, 'steps': 7115, 'loss/train': 2.5813026428222656}
-03/03/2022 21:49:22 - INFO - codeparrot_training - Step 7116: {'lr': 0.0004985272787901156, 'samples': 3643904, 'steps': 7116, 'loss/train': 1.8330262899398804}
-03/03/2022 21:49:25 - INFO - codeparrot_training - Step 7117: {'lr': 0.00049852670356854, 'samples': 3644416, 'steps': 7117, 'loss/train': 1.1878914833068848}
-03/03/2022 21:49:26 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 21:49:31 - INFO - codeparrot_training - Step 7118: {'lr': 0.000498526128234982, 'samples': 3644928, 'steps': 7118, 'loss/train': 2.7181015014648438}
-03/03/2022 21:49:34 - INFO - codeparrot_training - Step 7119: {'lr': 0.000498525552789442, 'samples': 3645440, 'steps': 7119, 'loss/train': 2.1698169708251953}
-03/03/2022 21:49:35 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/03/2022 21:49:39 - INFO - codeparrot_training - Step 7120: {'lr': 0.0004985249772319202, 'samples': 3645952, 'steps': 7120, 'loss/train': 2.2428197860717773}
-03/03/2022 21:49:43 - INFO - codeparrot_training - Step 7121: {'lr': 0.000498524401562417, 'samples': 3646464, 'steps': 7121, 'loss/train': 2.0897068977355957}
-03/03/2022 21:49:45 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/03/2022 21:49:48 - INFO - codeparrot_training - Step 7122: {'lr': 0.0004985238257809325, 'samples': 3646976, 'steps': 7122, 'loss/train': 2.0368943214416504}
-03/03/2022 21:49:51 - INFO - codeparrot_training - Step 7123: {'lr': 0.0004985232498874669, 'samples': 3647488, 'steps': 7123, 'loss/train': 2.842752456665039}
-03/03/2022 21:49:54 - INFO - codeparrot_training - Step 7124: {'lr': 0.0004985226738820207, 'samples': 3648000, 'steps': 7124, 'loss/train': 1.0608751773834229}
-03/03/2022 21:49:54 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/03/2022 21:50:00 - INFO - codeparrot_training - Step 7125: {'lr': 0.0004985220977645939, 'samples': 3648512, 'steps': 7125, 'loss/train': 2.0615720748901367}
-03/03/2022 21:50:03 - INFO - codeparrot_training - Step 7126: {'lr': 0.0004985215215351869, 'samples': 3649024, 'steps': 7126, 'loss/train': 2.515315532684326}
-03/03/2022 21:50:03 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/03/2022 21:50:08 - INFO - codeparrot_training - Step 7127: {'lr': 0.0004985209451937999, 'samples': 3649536, 'steps': 7127, 'loss/train': 2.3688299655914307}
-03/03/2022 21:50:11 - INFO - codeparrot_training - Step 7128: {'lr': 0.0004985203687404333, 'samples': 3650048, 'steps': 7128, 'loss/train': 2.4516162872314453}
-03/03/2022 21:50:11 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/03/2022 21:50:17 - INFO - codeparrot_training - Step 7129: {'lr': 0.0004985197921750871, 'samples': 3650560, 'steps': 7129, 'loss/train': 1.6078310012817383}
-03/03/2022 21:50:19 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/03/2022 21:50:22 - INFO - codeparrot_training - Step 7130: {'lr': 0.0004985192154977619, 'samples': 3651072, 'steps': 7130, 'loss/train': 2.627983808517456}
-03/03/2022 21:50:25 - INFO - codeparrot_training - Step 7131: {'lr': 0.0004985186387084577, 'samples': 3651584, 'steps': 7131, 'loss/train': 1.8354936838150024}
-03/03/2022 21:50:28 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/03/2022 21:50:30 - INFO - codeparrot_training - Step 7132: {'lr': 0.0004985180618071748, 'samples': 3652096, 'steps': 7132, 'loss/train': 1.659487009048462}
-03/03/2022 21:50:33 - INFO - codeparrot_training - Step 7133: {'lr': 0.0004985174847939135, 'samples': 3652608, 'steps': 7133, 'loss/train': 3.160731554031372}
-03/03/2022 21:50:36 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/03/2022 21:50:39 - INFO - codeparrot_training - Step 7134: {'lr': 0.0004985169076686741, 'samples': 3653120, 'steps': 7134, 'loss/train': 2.5577330589294434}
-03/03/2022 21:50:42 - INFO - codeparrot_training - Step 7135: {'lr': 0.0004985163304314568, 'samples': 3653632, 'steps': 7135, 'loss/train': 2.4117088317871094}
-03/03/2022 21:50:45 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/03/2022 21:50:47 - INFO - codeparrot_training - Step 7136: {'lr': 0.0004985157530822619, 'samples': 3654144, 'steps': 7136, 'loss/train': 2.0734689235687256}
-03/03/2022 21:50:50 - INFO - codeparrot_training - Step 7137: {'lr': 0.0004985151756210897, 'samples': 3654656, 'steps': 7137, 'loss/train': 2.46134614944458}
-03/03/2022 21:50:53 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/03/2022 21:50:56 - INFO - codeparrot_training - Step 7138: {'lr': 0.0004985145980479402, 'samples': 3655168, 'steps': 7138, 'loss/train': 2.0842390060424805}
-03/03/2022 21:50:59 - INFO - codeparrot_training - Step 7139: {'lr': 0.000498514020362814, 'samples': 3655680, 'steps': 7139, 'loss/train': 2.914644479751587}
-03/03/2022 21:51:02 - INFO - codeparrot_training - Step 7140: {'lr': 0.0004985134425657111, 'samples': 3656192, 'steps': 7140, 'loss/train': 3.2542436122894287}
-03/03/2022 21:51:02 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/03/2022 21:51:07 - INFO - codeparrot_training - Step 7141: {'lr': 0.000498512864656632, 'samples': 3656704, 'steps': 7141, 'loss/train': 2.6879544258117676}
-03/03/2022 21:51:11 - INFO - codeparrot_training - Step 7142: {'lr': 0.0004985122866355768, 'samples': 3657216, 'steps': 7142, 'loss/train': 2.70522403717041}
-03/03/2022 21:51:11 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/03/2022 21:51:16 - INFO - codeparrot_training - Step 7143: {'lr': 0.0004985117085025458, 'samples': 3657728, 'steps': 7143, 'loss/train': 1.2782477140426636}
-03/03/2022 21:51:19 - INFO - codeparrot_training - Step 7144: {'lr': 0.0004985111302575392, 'samples': 3658240, 'steps': 7144, 'loss/train': 1.94239342212677}
-03/03/2022 21:51:19 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/03/2022 21:51:24 - INFO - codeparrot_training - Step 7145: {'lr': 0.0004985105519005573, 'samples': 3658752, 'steps': 7145, 'loss/train': 2.642774820327759}
-03/03/2022 21:51:28 - INFO - codeparrot_training - Step 7146: {'lr': 0.0004985099734316006, 'samples': 3659264, 'steps': 7146, 'loss/train': 1.7015753984451294}
-03/03/2022 21:51:28 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/03/2022 21:51:33 - INFO - codeparrot_training - Step 7147: {'lr': 0.0004985093948506689, 'samples': 3659776, 'steps': 7147, 'loss/train': 2.9914886951446533}
-03/03/2022 21:51:36 - INFO - codeparrot_training - Step 7148: {'lr': 0.0004985088161577628, 'samples': 3660288, 'steps': 7148, 'loss/train': 1.7612049579620361}
-03/03/2022 21:51:36 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/03/2022 21:51:41 - INFO - codeparrot_training - Step 7149: {'lr': 0.0004985082373528825, 'samples': 3660800, 'steps': 7149, 'loss/train': 1.2198141813278198}
-03/03/2022 21:51:44 - INFO - codeparrot_training - Step 7150: {'lr': 0.0004985076584360282, 'samples': 3661312, 'steps': 7150, 'loss/train': 2.2028980255126953}
-03/03/2022 21:51:44 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/03/2022 21:51:50 - INFO - codeparrot_training - Step 7151: {'lr': 0.0004985070794072002, 'samples': 3661824, 'steps': 7151, 'loss/train': 2.0808491706848145}
-03/03/2022 21:51:53 - INFO - codeparrot_training - Step 7152: {'lr': 0.0004985065002663986, 'samples': 3662336, 'steps': 7152, 'loss/train': 2.583050012588501}
-03/03/2022 21:51:53 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/03/2022 21:51:58 - INFO - codeparrot_training - Step 7153: {'lr': 0.000498505921013624, 'samples': 3662848, 'steps': 7153, 'loss/train': 2.88801646232605}
-03/03/2022 21:52:01 - INFO - codeparrot_training - Step 7154: {'lr': 0.0004985053416488764, 'samples': 3663360, 'steps': 7154, 'loss/train': 2.432429790496826}
-03/03/2022 21:52:02 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/03/2022 21:52:07 - INFO - codeparrot_training - Step 7155: {'lr': 0.0004985047621721561, 'samples': 3663872, 'steps': 7155, 'loss/train': 2.1299901008605957}
-03/03/2022 21:52:10 - INFO - codeparrot_training - Step 7156: {'lr': 0.0004985041825834634, 'samples': 3664384, 'steps': 7156, 'loss/train': 0.4625830352306366}
-03/03/2022 21:52:10 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/03/2022 21:52:15 - INFO - codeparrot_training - Step 7157: {'lr': 0.0004985036028827986, 'samples': 3664896, 'steps': 7157, 'loss/train': 2.412371873855591}
-03/03/2022 21:52:18 - INFO - codeparrot_training - Step 7158: {'lr': 0.0004985030230701619, 'samples': 3665408, 'steps': 7158, 'loss/train': 1.8945930004119873}
-03/03/2022 21:52:18 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/03/2022 21:52:24 - INFO - codeparrot_training - Step 7159: {'lr': 0.0004985024431455534, 'samples': 3665920, 'steps': 7159, 'loss/train': 2.1369123458862305}
-03/03/2022 21:52:27 - INFO - codeparrot_training - Step 7160: {'lr': 0.0004985018631089738, 'samples': 3666432, 'steps': 7160, 'loss/train': 1.8390858173370361}
-03/03/2022 21:52:28 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/03/2022 21:52:32 - INFO - codeparrot_training - Step 7161: {'lr': 0.0004985012829604228, 'samples': 3666944, 'steps': 7161, 'loss/train': 2.372748851776123}
-03/03/2022 21:52:36 - INFO - codeparrot_training - Step 7162: {'lr': 0.0004985007026999011, 'samples': 3667456, 'steps': 7162, 'loss/train': 1.384495735168457}
-03/03/2022 21:52:37 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/03/2022 21:52:41 - INFO - codeparrot_training - Step 7163: {'lr': 0.0004985001223274089, 'samples': 3667968, 'steps': 7163, 'loss/train': 2.442805767059326}
-03/03/2022 21:52:44 - INFO - codeparrot_training - Step 7164: {'lr': 0.0004984995418429463, 'samples': 3668480, 'steps': 7164, 'loss/train': 3.0166187286376953}
-03/03/2022 21:52:45 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/03/2022 21:52:49 - INFO - codeparrot_training - Step 7165: {'lr': 0.0004984989612465137, 'samples': 3668992, 'steps': 7165, 'loss/train': 2.193398952484131}
-03/03/2022 21:52:52 - INFO - codeparrot_training - Step 7166: {'lr': 0.0004984983805381112, 'samples': 3669504, 'steps': 7166, 'loss/train': 1.31244957447052}
-03/03/2022 21:52:53 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/03/2022 21:52:57 - INFO - codeparrot_training - Step 7167: {'lr': 0.0004984977997177393, 'samples': 3670016, 'steps': 7167, 'loss/train': 2.07912278175354}
-03/03/2022 21:53:01 - INFO - codeparrot_training - Step 7168: {'lr': 0.000498497218785398, 'samples': 3670528, 'steps': 7168, 'loss/train': 3.592130422592163}
-03/03/2022 21:53:01 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/03/2022 21:53:06 - INFO - codeparrot_training - Step 7169: {'lr': 0.0004984966377410878, 'samples': 3671040, 'steps': 7169, 'loss/train': 1.0404008626937866}
-03/03/2022 21:53:10 - INFO - codeparrot_training - Step 7170: {'lr': 0.0004984960565848086, 'samples': 3671552, 'steps': 7170, 'loss/train': 2.396916151046753}
-03/03/2022 21:53:11 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/03/2022 21:53:15 - INFO - codeparrot_training - Step 7171: {'lr': 0.0004984954753165612, 'samples': 3672064, 'steps': 7171, 'loss/train': 3.4840896129608154}
-03/03/2022 21:53:18 - INFO - codeparrot_training - Step 7172: {'lr': 0.0004984948939363455, 'samples': 3672576, 'steps': 7172, 'loss/train': 2.318190813064575}
-03/03/2022 21:53:20 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/03/2022 21:53:23 - INFO - codeparrot_training - Step 7173: {'lr': 0.0004984943124441617, 'samples': 3673088, 'steps': 7173, 'loss/train': 1.9499636888504028}
-03/03/2022 21:53:26 - INFO - codeparrot_training - Step 7174: {'lr': 0.0004984937308400104, 'samples': 3673600, 'steps': 7174, 'loss/train': 2.3934130668640137}
-03/03/2022 21:53:28 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/03/2022 21:53:32 - INFO - codeparrot_training - Step 7175: {'lr': 0.0004984931491238915, 'samples': 3674112, 'steps': 7175, 'loss/train': 2.4518942832946777}
-03/03/2022 21:53:35 - INFO - codeparrot_training - Step 7176: {'lr': 0.0004984925672958055, 'samples': 3674624, 'steps': 7176, 'loss/train': 1.325639247894287}
-03/03/2022 21:53:38 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/03/2022 21:53:40 - INFO - codeparrot_training - Step 7177: {'lr': 0.0004984919853557526, 'samples': 3675136, 'steps': 7177, 'loss/train': 2.7360355854034424}
-03/03/2022 21:53:43 - INFO - codeparrot_training - Step 7178: {'lr': 0.000498491403303733, 'samples': 3675648, 'steps': 7178, 'loss/train': 1.718960165977478}
-03/03/2022 21:53:46 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/03/2022 21:53:49 - INFO - codeparrot_training - Step 7179: {'lr': 0.000498490821139747, 'samples': 3676160, 'steps': 7179, 'loss/train': 2.4697418212890625}
-03/03/2022 21:53:52 - INFO - codeparrot_training - Step 7180: {'lr': 0.0004984902388637949, 'samples': 3676672, 'steps': 7180, 'loss/train': 2.397927761077881}
-03/03/2022 21:53:54 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/03/2022 21:53:57 - INFO - codeparrot_training - Step 7181: {'lr': 0.000498489656475877, 'samples': 3677184, 'steps': 7181, 'loss/train': 0.3688555061817169}
-03/03/2022 21:54:00 - INFO - codeparrot_training - Step 7182: {'lr': 0.0004984890739759934, 'samples': 3677696, 'steps': 7182, 'loss/train': 2.644429922103882}
-03/03/2022 21:54:03 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/03/2022 21:54:06 - INFO - codeparrot_training - Step 7183: {'lr': 0.0004984884913641444, 'samples': 3678208, 'steps': 7183, 'loss/train': 1.4851897954940796}
-03/03/2022 21:54:09 - INFO - codeparrot_training - Step 7184: {'lr': 0.0004984879086403304, 'samples': 3678720, 'steps': 7184, 'loss/train': 2.2392303943634033}
-03/03/2022 21:54:11 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/03/2022 21:54:14 - INFO - codeparrot_training - Step 7185: {'lr': 0.0004984873258045517, 'samples': 3679232, 'steps': 7185, 'loss/train': 1.756821870803833}
-03/03/2022 21:54:17 - INFO - codeparrot_training - Step 7186: {'lr': 0.0004984867428568083, 'samples': 3679744, 'steps': 7186, 'loss/train': 2.758599042892456}
-03/03/2022 21:54:19 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/03/2022 21:54:22 - INFO - codeparrot_training - Step 7187: {'lr': 0.0004984861597971006, 'samples': 3680256, 'steps': 7187, 'loss/train': 0.4920683801174164}
-03/03/2022 21:54:26 - INFO - codeparrot_training - Step 7188: {'lr': 0.000498485576625429, 'samples': 3680768, 'steps': 7188, 'loss/train': 2.62923264503479}
-03/03/2022 21:54:28 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/03/2022 21:54:31 - INFO - codeparrot_training - Step 7189: {'lr': 0.0004984849933417935, 'samples': 3681280, 'steps': 7189, 'loss/train': 6.068812847137451}
-03/03/2022 21:54:34 - INFO - codeparrot_training - Step 7190: {'lr': 0.0004984844099461945, 'samples': 3681792, 'steps': 7190, 'loss/train': 2.209019422531128}
-03/03/2022 21:54:36 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/03/2022 21:54:39 - INFO - codeparrot_training - Step 7191: {'lr': 0.0004984838264386322, 'samples': 3682304, 'steps': 7191, 'loss/train': 1.910298228263855}
-03/03/2022 21:54:42 - INFO - codeparrot_training - Step 7192: {'lr': 0.000498483242819107, 'samples': 3682816, 'steps': 7192, 'loss/train': 2.018994092941284}
-03/03/2022 21:54:45 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/03/2022 21:54:48 - INFO - codeparrot_training - Step 7193: {'lr': 0.0004984826590876192, 'samples': 3683328, 'steps': 7193, 'loss/train': 2.0348966121673584}
-03/03/2022 21:54:51 - INFO - codeparrot_training - Step 7194: {'lr': 0.0004984820752441688, 'samples': 3683840, 'steps': 7194, 'loss/train': 2.6908111572265625}
-03/03/2022 21:54:53 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/03/2022 21:54:56 - INFO - codeparrot_training - Step 7195: {'lr': 0.0004984814912887563, 'samples': 3684352, 'steps': 7195, 'loss/train': 2.5057804584503174}
-03/03/2022 21:54:59 - INFO - codeparrot_training - Step 7196: {'lr': 0.0004984809072213818, 'samples': 3684864, 'steps': 7196, 'loss/train': 2.4015491008758545}
-03/03/2022 21:55:01 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/03/2022 21:55:05 - INFO - codeparrot_training - Step 7197: {'lr': 0.0004984803230420457, 'samples': 3685376, 'steps': 7197, 'loss/train': 2.1309444904327393}
-03/03/2022 21:55:08 - INFO - codeparrot_training - Step 7198: {'lr': 0.0004984797387507481, 'samples': 3685888, 'steps': 7198, 'loss/train': 0.2656606137752533}
-03/03/2022 21:55:10 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/03/2022 21:55:13 - INFO - codeparrot_training - Step 7199: {'lr': 0.0004984791543474896, 'samples': 3686400, 'steps': 7199, 'loss/train': 2.4497315883636475}
-03/03/2022 21:55:16 - INFO - codeparrot_training - Step 7200: {'lr': 0.0004984785698322699, 'samples': 3686912, 'steps': 7200, 'loss/train': 2.4007627964019775}
-03/03/2022 21:55:18 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/03/2022 21:55:21 - INFO - codeparrot_training - Step 7201: {'lr': 0.0004984779852050898, 'samples': 3687424, 'steps': 7201, 'loss/train': 1.488333821296692}
-03/03/2022 21:55:25 - INFO - codeparrot_training - Step 7202: {'lr': 0.0004984774004659493, 'samples': 3687936, 'steps': 7202, 'loss/train': 1.9636294841766357}
-03/03/2022 21:55:27 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/03/2022 21:55:30 - INFO - codeparrot_training - Step 7203: {'lr': 0.0004984768156148489, 'samples': 3688448, 'steps': 7203, 'loss/train': 2.771916151046753}
-03/03/2022 21:55:33 - INFO - codeparrot_training - Step 7204: {'lr': 0.0004984762306517883, 'samples': 3688960, 'steps': 7204, 'loss/train': 2.5820200443267822}
-03/03/2022 21:55:35 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/03/2022 21:55:39 - INFO - codeparrot_training - Step 7205: {'lr': 0.0004984756455767684, 'samples': 3689472, 'steps': 7205, 'loss/train': 1.6169904470443726}
-03/03/2022 21:55:43 - INFO - codeparrot_training - Step 7206: {'lr': 0.0004984750603897892, 'samples': 3689984, 'steps': 7206, 'loss/train': 2.133303165435791}
-03/03/2022 21:55:46 - INFO - codeparrot_training - Step 7207: {'lr': 0.0004984744750908509, 'samples': 3690496, 'steps': 7207, 'loss/train': 1.9619688987731934}
-03/03/2022 21:55:48 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/03/2022 21:55:51 - INFO - codeparrot_training - Step 7208: {'lr': 0.0004984738896799539, 'samples': 3691008, 'steps': 7208, 'loss/train': 2.450359344482422}
-03/03/2022 21:55:54 - INFO - codeparrot_training - Step 7209: {'lr': 0.0004984733041570983, 'samples': 3691520, 'steps': 7209, 'loss/train': 2.2211790084838867}
-03/03/2022 21:55:57 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/03/2022 21:56:00 - INFO - codeparrot_training - Step 7210: {'lr': 0.0004984727185222846, 'samples': 3692032, 'steps': 7210, 'loss/train': 1.8664277791976929}
-03/03/2022 21:56:03 - INFO - codeparrot_training - Step 7211: {'lr': 0.0004984721327755128, 'samples': 3692544, 'steps': 7211, 'loss/train': 2.190072536468506}
-03/03/2022 21:56:05 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/03/2022 21:56:08 - INFO - codeparrot_training - Step 7212: {'lr': 0.0004984715469167835, 'samples': 3693056, 'steps': 7212, 'loss/train': 1.9506304264068604}
-03/03/2022 21:56:11 - INFO - codeparrot_training - Step 7213: {'lr': 0.0004984709609460966, 'samples': 3693568, 'steps': 7213, 'loss/train': 1.8072618246078491}
-03/03/2022 21:56:14 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/03/2022 21:56:17 - INFO - codeparrot_training - Step 7214: {'lr': 0.0004984703748634524, 'samples': 3694080, 'steps': 7214, 'loss/train': 2.0216469764709473}
-03/03/2022 21:56:20 - INFO - codeparrot_training - Step 7215: {'lr': 0.0004984697886688514, 'samples': 3694592, 'steps': 7215, 'loss/train': 2.65387225151062}
-03/03/2022 21:56:22 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/03/2022 21:56:25 - INFO - codeparrot_training - Step 7216: {'lr': 0.0004984692023622938, 'samples': 3695104, 'steps': 7216, 'loss/train': 2.4451467990875244}
-03/03/2022 21:56:28 - INFO - codeparrot_training - Step 7217: {'lr': 0.0004984686159437798, 'samples': 3695616, 'steps': 7217, 'loss/train': 1.868168830871582}
-03/03/2022 21:56:31 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/03/2022 21:56:34 - INFO - codeparrot_training - Step 7218: {'lr': 0.0004984680294133096, 'samples': 3696128, 'steps': 7218, 'loss/train': 2.23280930519104}
-03/03/2022 21:56:37 - INFO - codeparrot_training - Step 7219: {'lr': 0.0004984674427708836, 'samples': 3696640, 'steps': 7219, 'loss/train': 2.662015199661255}
-03/03/2022 21:56:40 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/03/2022 21:56:42 - INFO - codeparrot_training - Step 7220: {'lr': 0.000498466856016502, 'samples': 3697152, 'steps': 7220, 'loss/train': 1.8936930894851685}
-03/03/2022 21:56:45 - INFO - codeparrot_training - Step 7221: {'lr': 0.000498466269150165, 'samples': 3697664, 'steps': 7221, 'loss/train': 0.9877169728279114}
-03/03/2022 21:56:49 - INFO - codeparrot_training - Step 7222: {'lr': 0.000498465682171873, 'samples': 3698176, 'steps': 7222, 'loss/train': 3.1990301609039307}
-03/03/2022 21:56:49 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/03/2022 21:56:54 - INFO - codeparrot_training - Step 7223: {'lr': 0.0004984650950816262, 'samples': 3698688, 'steps': 7223, 'loss/train': 2.3495259284973145}
-03/03/2022 21:56:57 - INFO - codeparrot_training - Step 7224: {'lr': 0.0004984645078794248, 'samples': 3699200, 'steps': 7224, 'loss/train': 1.4248151779174805}
-03/03/2022 21:56:57 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/03/2022 21:57:02 - INFO - codeparrot_training - Step 7225: {'lr': 0.0004984639205652692, 'samples': 3699712, 'steps': 7225, 'loss/train': 2.1439151763916016}
-03/03/2022 21:57:06 - INFO - codeparrot_training - Step 7226: {'lr': 0.0004984633331391596, 'samples': 3700224, 'steps': 7226, 'loss/train': 1.3991724252700806}
-03/03/2022 21:57:06 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/03/2022 21:57:11 - INFO - codeparrot_training - Step 7227: {'lr': 0.0004984627456010962, 'samples': 3700736, 'steps': 7227, 'loss/train': 2.4202117919921875}
-03/03/2022 21:57:14 - INFO - codeparrot_training - Step 7228: {'lr': 0.0004984621579510794, 'samples': 3701248, 'steps': 7228, 'loss/train': 2.373892068862915}
-03/03/2022 21:57:14 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/03/2022 21:57:19 - INFO - codeparrot_training - Step 7229: {'lr': 0.0004984615701891093, 'samples': 3701760, 'steps': 7229, 'loss/train': 1.4373005628585815}
-03/03/2022 21:57:22 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/03/2022 21:57:25 - INFO - codeparrot_training - Step 7230: {'lr': 0.0004984609823151863, 'samples': 3702272, 'steps': 7230, 'loss/train': 2.6135687828063965}
-03/03/2022 21:57:28 - INFO - codeparrot_training - Step 7231: {'lr': 0.0004984603943293106, 'samples': 3702784, 'steps': 7231, 'loss/train': 2.2621564865112305}
-03/03/2022 21:57:31 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/03/2022 21:57:33 - INFO - codeparrot_training - Step 7232: {'lr': 0.0004984598062314824, 'samples': 3703296, 'steps': 7232, 'loss/train': 1.7559220790863037}
-03/03/2022 21:57:37 - INFO - codeparrot_training - Step 7233: {'lr': 0.0004984592180217022, 'samples': 3703808, 'steps': 7233, 'loss/train': 2.9056661128997803}
-03/03/2022 21:57:40 - INFO - codeparrot_training - Step 7234: {'lr': 0.00049845862969997, 'samples': 3704320, 'steps': 7234, 'loss/train': 3.0132837295532227}
-03/03/2022 21:57:40 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/03/2022 21:57:45 - INFO - codeparrot_training - Step 7235: {'lr': 0.0004984580412662862, 'samples': 3704832, 'steps': 7235, 'loss/train': 2.6029515266418457}
-03/03/2022 21:57:48 - INFO - codeparrot_training - Step 7236: {'lr': 0.000498457452720651, 'samples': 3705344, 'steps': 7236, 'loss/train': 2.6147830486297607}
-03/03/2022 21:57:49 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/03/2022 21:57:54 - INFO - codeparrot_training - Step 7237: {'lr': 0.0004984568640630648, 'samples': 3705856, 'steps': 7237, 'loss/train': 1.0409111976623535}
-03/03/2022 21:57:57 - INFO - codeparrot_training - Step 7238: {'lr': 0.0004984562752935278, 'samples': 3706368, 'steps': 7238, 'loss/train': 2.442427635192871}
-03/03/2022 21:57:58 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/03/2022 21:58:02 - INFO - codeparrot_training - Step 7239: {'lr': 0.0004984556864120401, 'samples': 3706880, 'steps': 7239, 'loss/train': 2.407686471939087}
-03/03/2022 21:58:05 - INFO - codeparrot_training - Step 7240: {'lr': 0.0004984550974186021, 'samples': 3707392, 'steps': 7240, 'loss/train': 2.468179702758789}
-03/03/2022 21:58:06 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/03/2022 21:58:10 - INFO - codeparrot_training - Step 7241: {'lr': 0.0004984545083132142, 'samples': 3707904, 'steps': 7241, 'loss/train': 2.501140832901001}
-03/03/2022 21:58:14 - INFO - codeparrot_training - Step 7242: {'lr': 0.0004984539190958765, 'samples': 3708416, 'steps': 7242, 'loss/train': 1.80500066280365}
-03/03/2022 21:58:14 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/03/2022 21:58:19 - INFO - codeparrot_training - Step 7243: {'lr': 0.0004984533297665892, 'samples': 3708928, 'steps': 7243, 'loss/train': 1.8550621271133423}
-03/03/2022 21:58:22 - INFO - codeparrot_training - Step 7244: {'lr': 0.0004984527403253527, 'samples': 3709440, 'steps': 7244, 'loss/train': 1.6399954557418823}
-03/03/2022 21:58:23 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/03/2022 21:58:27 - INFO - codeparrot_training - Step 7245: {'lr': 0.0004984521507721672, 'samples': 3709952, 'steps': 7245, 'loss/train': 2.5676887035369873}
-03/03/2022 21:58:30 - INFO - codeparrot_training - Step 7246: {'lr': 0.0004984515611070331, 'samples': 3710464, 'steps': 7246, 'loss/train': 2.2363853454589844}
-03/03/2022 21:58:32 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/03/2022 21:58:36 - INFO - codeparrot_training - Step 7247: {'lr': 0.0004984509713299505, 'samples': 3710976, 'steps': 7247, 'loss/train': 2.039759635925293}
-03/03/2022 21:58:39 - INFO - codeparrot_training - Step 7248: {'lr': 0.0004984503814409198, 'samples': 3711488, 'steps': 7248, 'loss/train': 2.6374738216400146}
-03/03/2022 21:58:40 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/03/2022 21:58:44 - INFO - codeparrot_training - Step 7249: {'lr': 0.000498449791439941, 'samples': 3712000, 'steps': 7249, 'loss/train': 2.610713243484497}
-03/03/2022 21:58:47 - INFO - codeparrot_training - Step 7250: {'lr': 0.0004984492013270147, 'samples': 3712512, 'steps': 7250, 'loss/train': 1.7372400760650635}
-03/03/2022 21:58:49 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/03/2022 21:58:53 - INFO - codeparrot_training - Step 7251: {'lr': 0.0004984486111021411, 'samples': 3713024, 'steps': 7251, 'loss/train': 1.363546371459961}
-03/03/2022 21:58:56 - INFO - codeparrot_training - Step 7252: {'lr': 0.0004984480207653202, 'samples': 3713536, 'steps': 7252, 'loss/train': 2.338947296142578}
-03/03/2022 21:58:57 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/03/2022 21:59:01 - INFO - codeparrot_training - Step 7253: {'lr': 0.0004984474303165526, 'samples': 3714048, 'steps': 7253, 'loss/train': 2.58141827583313}
-03/03/2022 21:59:04 - INFO - codeparrot_training - Step 7254: {'lr': 0.0004984468397558384, 'samples': 3714560, 'steps': 7254, 'loss/train': 0.44333094358444214}
-03/03/2022 21:59:09 - INFO - codeparrot_training - Step 7255: {'lr': 0.0004984462490831778, 'samples': 3715072, 'steps': 7255, 'loss/train': 1.7508095502853394}
-03/03/2022 21:59:12 - INFO - codeparrot_training - Step 7256: {'lr': 0.0004984456582985713, 'samples': 3715584, 'steps': 7256, 'loss/train': 2.330861806869507}
-03/03/2022 21:59:13 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/03/2022 21:59:18 - INFO - codeparrot_training - Step 7257: {'lr': 0.0004984450674020189, 'samples': 3716096, 'steps': 7257, 'loss/train': 2.0861291885375977}
-03/03/2022 21:59:21 - INFO - codeparrot_training - Step 7258: {'lr': 0.000498444476393521, 'samples': 3716608, 'steps': 7258, 'loss/train': 1.9695208072662354}
-03/03/2022 21:59:22 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/03/2022 21:59:26 - INFO - codeparrot_training - Step 7259: {'lr': 0.0004984438852730779, 'samples': 3717120, 'steps': 7259, 'loss/train': 2.197638750076294}
-03/03/2022 21:59:29 - INFO - codeparrot_training - Step 7260: {'lr': 0.0004984432940406898, 'samples': 3717632, 'steps': 7260, 'loss/train': 1.0056401491165161}
-03/03/2022 21:59:30 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/03/2022 21:59:35 - INFO - codeparrot_training - Step 7261: {'lr': 0.0004984427026963569, 'samples': 3718144, 'steps': 7261, 'loss/train': 2.861586093902588}
-03/03/2022 21:59:38 - INFO - codeparrot_training - Step 7262: {'lr': 0.0004984421112400796, 'samples': 3718656, 'steps': 7262, 'loss/train': 1.5465716123580933}
-03/03/2022 21:59:38 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 21:59:43 - INFO - codeparrot_training - Step 7263: {'lr': 0.0004984415196718582, 'samples': 3719168, 'steps': 7263, 'loss/train': 1.9683340787887573}
-03/03/2022 21:59:46 - INFO - codeparrot_training - Step 7264: {'lr': 0.0004984409279916929, 'samples': 3719680, 'steps': 7264, 'loss/train': 1.7974759340286255}
-03/03/2022 21:59:47 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/03/2022 21:59:51 - INFO - codeparrot_training - Step 7265: {'lr': 0.0004984403361995839, 'samples': 3720192, 'steps': 7265, 'loss/train': 2.9650652408599854}
-03/03/2022 21:59:54 - INFO - codeparrot_training - Step 7266: {'lr': 0.0004984397442955315, 'samples': 3720704, 'steps': 7266, 'loss/train': 2.1038131713867188}
-03/03/2022 21:59:55 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/03/2022 22:00:00 - INFO - codeparrot_training - Step 7267: {'lr': 0.0004984391522795359, 'samples': 3721216, 'steps': 7267, 'loss/train': 2.484480381011963}
-03/03/2022 22:00:03 - INFO - codeparrot_training - Step 7268: {'lr': 0.0004984385601515977, 'samples': 3721728, 'steps': 7268, 'loss/train': 1.9324984550476074}
-03/03/2022 22:00:03 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/03/2022 22:00:08 - INFO - codeparrot_training - Step 7269: {'lr': 0.0004984379679117166, 'samples': 3722240, 'steps': 7269, 'loss/train': 2.4324469566345215}
-03/03/2022 22:00:11 - INFO - codeparrot_training - Step 7270: {'lr': 0.0004984373755598934, 'samples': 3722752, 'steps': 7270, 'loss/train': 1.4821780920028687}
-03/03/2022 22:00:17 - INFO - codeparrot_training - Step 7271: {'lr': 0.0004984367830961281, 'samples': 3723264, 'steps': 7271, 'loss/train': 1.9279727935791016}
-03/03/2022 22:00:20 - INFO - codeparrot_training - Step 7272: {'lr': 0.0004984361905204209, 'samples': 3723776, 'steps': 7272, 'loss/train': 1.5824328660964966}
-03/03/2022 22:00:20 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/03/2022 22:00:25 - INFO - codeparrot_training - Step 7273: {'lr': 0.0004984355978327724, 'samples': 3724288, 'steps': 7273, 'loss/train': 2.5660898685455322}
-03/03/2022 22:00:28 - INFO - codeparrot_training - Step 7274: {'lr': 0.0004984350050331826, 'samples': 3724800, 'steps': 7274, 'loss/train': 2.041095733642578}
-03/03/2022 22:00:29 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/03/2022 22:00:34 - INFO - codeparrot_training - Step 7275: {'lr': 0.0004984344121216518, 'samples': 3725312, 'steps': 7275, 'loss/train': 1.034005880355835}
-03/03/2022 22:00:37 - INFO - codeparrot_training - Step 7276: {'lr': 0.0004984338190981802, 'samples': 3725824, 'steps': 7276, 'loss/train': 2.747615098953247}
-03/03/2022 22:00:38 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/03/2022 22:00:42 - INFO - codeparrot_training - Step 7277: {'lr': 0.0004984332259627682, 'samples': 3726336, 'steps': 7277, 'loss/train': 0.7829840183258057}
-03/03/2022 22:00:45 - INFO - codeparrot_training - Step 7278: {'lr': 0.000498432632715416, 'samples': 3726848, 'steps': 7278, 'loss/train': 2.1211130619049072}
-03/03/2022 22:00:46 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/03/2022 22:00:50 - INFO - codeparrot_training - Step 7279: {'lr': 0.000498432039356124, 'samples': 3727360, 'steps': 7279, 'loss/train': 2.481004238128662}
-03/03/2022 22:00:54 - INFO - codeparrot_training - Step 7280: {'lr': 0.0004984314458848923, 'samples': 3727872, 'steps': 7280, 'loss/train': 1.8976250886917114}
-03/03/2022 22:00:54 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/03/2022 22:00:59 - INFO - codeparrot_training - Step 7281: {'lr': 0.0004984308523017212, 'samples': 3728384, 'steps': 7281, 'loss/train': 2.4603562355041504}
-03/03/2022 22:01:02 - INFO - codeparrot_training - Step 7282: {'lr': 0.000498430258606611, 'samples': 3728896, 'steps': 7282, 'loss/train': 1.8097604513168335}
-03/03/2022 22:01:03 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/03/2022 22:01:08 - INFO - codeparrot_training - Step 7283: {'lr': 0.000498429664799562, 'samples': 3729408, 'steps': 7283, 'loss/train': 2.106017589569092}
-03/03/2022 22:01:11 - INFO - codeparrot_training - Step 7284: {'lr': 0.0004984290708805743, 'samples': 3729920, 'steps': 7284, 'loss/train': 1.9437434673309326}
-03/03/2022 22:01:12 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/03/2022 22:01:16 - INFO - codeparrot_training - Step 7285: {'lr': 0.0004984284768496484, 'samples': 3730432, 'steps': 7285, 'loss/train': 2.2688283920288086}
-03/03/2022 22:01:19 - INFO - codeparrot_training - Step 7286: {'lr': 0.0004984278827067844, 'samples': 3730944, 'steps': 7286, 'loss/train': 3.0569396018981934}
-03/03/2022 22:01:20 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/03/2022 22:01:24 - INFO - codeparrot_training - Step 7287: {'lr': 0.0004984272884519827, 'samples': 3731456, 'steps': 7287, 'loss/train': 2.1611342430114746}
-03/03/2022 22:01:28 - INFO - codeparrot_training - Step 7288: {'lr': 0.0004984266940852434, 'samples': 3731968, 'steps': 7288, 'loss/train': 2.292142868041992}
-03/03/2022 22:01:28 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/03/2022 22:01:33 - INFO - codeparrot_training - Step 7289: {'lr': 0.0004984260996065671, 'samples': 3732480, 'steps': 7289, 'loss/train': 2.796261787414551}
-03/03/2022 22:01:36 - INFO - codeparrot_training - Step 7290: {'lr': 0.0004984255050159536, 'samples': 3732992, 'steps': 7290, 'loss/train': 2.550050735473633}
-03/03/2022 22:01:37 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/03/2022 22:01:41 - INFO - codeparrot_training - Step 7291: {'lr': 0.0004984249103134035, 'samples': 3733504, 'steps': 7291, 'loss/train': 2.431447744369507}
-03/03/2022 22:01:45 - INFO - codeparrot_training - Step 7292: {'lr': 0.0004984243154989168, 'samples': 3734016, 'steps': 7292, 'loss/train': 2.1206798553466797}
-03/03/2022 22:01:46 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/03/2022 22:01:50 - INFO - codeparrot_training - Step 7293: {'lr': 0.0004984237205724942, 'samples': 3734528, 'steps': 7293, 'loss/train': 2.5739519596099854}
-03/03/2022 22:01:53 - INFO - codeparrot_training - Step 7294: {'lr': 0.0004984231255341355, 'samples': 3735040, 'steps': 7294, 'loss/train': 1.8535830974578857}
-03/03/2022 22:01:55 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/03/2022 22:01:58 - INFO - codeparrot_training - Step 7295: {'lr': 0.0004984225303838413, 'samples': 3735552, 'steps': 7295, 'loss/train': 2.1932015419006348}
-03/03/2022 22:02:02 - INFO - codeparrot_training - Step 7296: {'lr': 0.0004984219351216116, 'samples': 3736064, 'steps': 7296, 'loss/train': 2.8696095943450928}
-03/03/2022 22:02:07 - INFO - codeparrot_training - Step 7297: {'lr': 0.000498421339747447, 'samples': 3736576, 'steps': 7297, 'loss/train': 1.2009354829788208}
-03/03/2022 22:02:10 - INFO - codeparrot_training - Step 7298: {'lr': 0.0004984207442613474, 'samples': 3737088, 'steps': 7298, 'loss/train': 2.095829486846924}
-03/03/2022 22:02:11 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/03/2022 22:02:15 - INFO - codeparrot_training - Step 7299: {'lr': 0.0004984201486633134, 'samples': 3737600, 'steps': 7299, 'loss/train': 1.8965965509414673}
-03/03/2022 22:02:18 - INFO - codeparrot_training - Step 7300: {'lr': 0.0004984195529533451, 'samples': 3738112, 'steps': 7300, 'loss/train': 2.7916316986083984}
-03/03/2022 22:02:20 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/03/2022 22:02:24 - INFO - codeparrot_training - Step 7301: {'lr': 0.0004984189571314426, 'samples': 3738624, 'steps': 7301, 'loss/train': 3.3244645595550537}
-03/03/2022 22:02:27 - INFO - codeparrot_training - Step 7302: {'lr': 0.0004984183611976065, 'samples': 3739136, 'steps': 7302, 'loss/train': 1.8908076286315918}
-03/03/2022 22:02:28 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/03/2022 22:02:32 - INFO - codeparrot_training - Step 7303: {'lr': 0.0004984177651518369, 'samples': 3739648, 'steps': 7303, 'loss/train': 2.0345242023468018}
-03/03/2022 22:02:35 - INFO - codeparrot_training - Step 7304: {'lr': 0.0004984171689941341, 'samples': 3740160, 'steps': 7304, 'loss/train': 2.0889699459075928}
-03/03/2022 22:02:36 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/03/2022 22:02:40 - INFO - codeparrot_training - Step 7305: {'lr': 0.0004984165727244984, 'samples': 3740672, 'steps': 7305, 'loss/train': 3.333667755126953}
-03/03/2022 22:02:44 - INFO - codeparrot_training - Step 7306: {'lr': 0.0004984159763429299, 'samples': 3741184, 'steps': 7306, 'loss/train': 1.425711750984192}
-03/03/2022 22:02:45 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/03/2022 22:02:49 - INFO - codeparrot_training - Step 7307: {'lr': 0.0004984153798494291, 'samples': 3741696, 'steps': 7307, 'loss/train': 0.30586734414100647}
-03/03/2022 22:02:52 - INFO - codeparrot_training - Step 7308: {'lr': 0.000498414783243996, 'samples': 3742208, 'steps': 7308, 'loss/train': 2.732069253921509}
-03/03/2022 22:02:53 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/03/2022 22:02:58 - INFO - codeparrot_training - Step 7309: {'lr': 0.0004984141865266312, 'samples': 3742720, 'steps': 7309, 'loss/train': 2.3263514041900635}
-03/03/2022 22:03:01 - INFO - codeparrot_training - Step 7310: {'lr': 0.0004984135896973348, 'samples': 3743232, 'steps': 7310, 'loss/train': 2.3599307537078857}
-03/03/2022 22:03:05 - INFO - codeparrot_training - Step 7311: {'lr': 0.000498412992756107, 'samples': 3743744, 'steps': 7311, 'loss/train': 2.1396732330322266}
-03/03/2022 22:03:05 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/03/2022 22:03:10 - INFO - codeparrot_training - Step 7312: {'lr': 0.0004984123957029482, 'samples': 3744256, 'steps': 7312, 'loss/train': 1.5825265645980835}
-03/03/2022 22:03:13 - INFO - codeparrot_training - Step 7313: {'lr': 0.0004984117985378586, 'samples': 3744768, 'steps': 7313, 'loss/train': 2.3656163215637207}
-03/03/2022 22:03:13 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/03/2022 22:03:18 - INFO - codeparrot_training - Step 7314: {'lr': 0.0004984112012608384, 'samples': 3745280, 'steps': 7314, 'loss/train': 1.6877021789550781}
-03/03/2022 22:03:21 - INFO - codeparrot_training - Step 7315: {'lr': 0.000498410603871888, 'samples': 3745792, 'steps': 7315, 'loss/train': 2.254337787628174}
-03/03/2022 22:03:22 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/03/2022 22:03:27 - INFO - codeparrot_training - Step 7316: {'lr': 0.0004984100063710076, 'samples': 3746304, 'steps': 7316, 'loss/train': 2.5470774173736572}
-03/03/2022 22:03:30 - INFO - codeparrot_training - Step 7317: {'lr': 0.0004984094087581975, 'samples': 3746816, 'steps': 7317, 'loss/train': 2.8101253509521484}
-03/03/2022 22:03:31 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/03/2022 22:03:35 - INFO - codeparrot_training - Step 7318: {'lr': 0.0004984088110334579, 'samples': 3747328, 'steps': 7318, 'loss/train': 1.4874564409255981}
-03/03/2022 22:03:38 - INFO - codeparrot_training - Step 7319: {'lr': 0.0004984082131967892, 'samples': 3747840, 'steps': 7319, 'loss/train': 0.9595170617103577}
-03/03/2022 22:03:39 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/03/2022 22:03:44 - INFO - codeparrot_training - Step 7320: {'lr': 0.0004984076152481916, 'samples': 3748352, 'steps': 7320, 'loss/train': 0.7493976950645447}
-03/03/2022 22:03:47 - INFO - codeparrot_training - Step 7321: {'lr': 0.0004984070171876653, 'samples': 3748864, 'steps': 7321, 'loss/train': 2.800023078918457}
-03/03/2022 22:03:47 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/03/2022 22:03:52 - INFO - codeparrot_training - Step 7322: {'lr': 0.0004984064190152106, 'samples': 3749376, 'steps': 7322, 'loss/train': 2.34143328666687}
-03/03/2022 22:03:55 - INFO - codeparrot_training - Step 7323: {'lr': 0.0004984058207308279, 'samples': 3749888, 'steps': 7323, 'loss/train': 2.405593156814575}
-03/03/2022 22:03:56 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 22:04:01 - INFO - codeparrot_training - Step 7324: {'lr': 0.0004984052223345174, 'samples': 3750400, 'steps': 7324, 'loss/train': 2.022209644317627}
-03/03/2022 22:04:04 - INFO - codeparrot_training - Step 7325: {'lr': 0.0004984046238262792, 'samples': 3750912, 'steps': 7325, 'loss/train': 3.1848466396331787}
-03/03/2022 22:04:05 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/03/2022 22:04:09 - INFO - codeparrot_training - Step 7326: {'lr': 0.0004984040252061137, 'samples': 3751424, 'steps': 7326, 'loss/train': 1.536909818649292}
-03/03/2022 22:04:12 - INFO - codeparrot_training - Step 7327: {'lr': 0.0004984034264740213, 'samples': 3751936, 'steps': 7327, 'loss/train': 1.7153797149658203}
-03/03/2022 22:04:13 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/03/2022 22:04:17 - INFO - codeparrot_training - Step 7328: {'lr': 0.0004984028276300021, 'samples': 3752448, 'steps': 7328, 'loss/train': 2.036565065383911}
-03/03/2022 22:04:21 - INFO - codeparrot_training - Step 7329: {'lr': 0.0004984022286740565, 'samples': 3752960, 'steps': 7329, 'loss/train': 2.2849996089935303}
-03/03/2022 22:04:22 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/03/2022 22:04:26 - INFO - codeparrot_training - Step 7330: {'lr': 0.0004984016296061846, 'samples': 3753472, 'steps': 7330, 'loss/train': 1.6593283414840698}
-03/03/2022 22:04:29 - INFO - codeparrot_training - Step 7331: {'lr': 0.0004984010304263868, 'samples': 3753984, 'steps': 7331, 'loss/train': 2.262352705001831}
-03/03/2022 22:04:30 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/03/2022 22:04:34 - INFO - codeparrot_training - Step 7332: {'lr': 0.0004984004311346632, 'samples': 3754496, 'steps': 7332, 'loss/train': 1.3110219240188599}
-03/03/2022 22:04:38 - INFO - codeparrot_training - Step 7333: {'lr': 0.0004983998317310143, 'samples': 3755008, 'steps': 7333, 'loss/train': 2.3796498775482178}
-03/03/2022 22:04:38 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/03/2022 22:04:43 - INFO - codeparrot_training - Step 7334: {'lr': 0.0004983992322154403, 'samples': 3755520, 'steps': 7334, 'loss/train': 2.311729907989502}
-03/03/2022 22:04:46 - INFO - codeparrot_training - Step 7335: {'lr': 0.0004983986325879414, 'samples': 3756032, 'steps': 7335, 'loss/train': 2.4587934017181396}
-03/03/2022 22:04:47 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/03/2022 22:04:51 - INFO - codeparrot_training - Step 7336: {'lr': 0.0004983980328485179, 'samples': 3756544, 'steps': 7336, 'loss/train': 1.6067967414855957}
-03/03/2022 22:04:54 - INFO - codeparrot_training - Step 7337: {'lr': 0.0004983974329971702, 'samples': 3757056, 'steps': 7337, 'loss/train': 1.6323025226593018}
-03/03/2022 22:04:55 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/03/2022 22:05:00 - INFO - codeparrot_training - Step 7338: {'lr': 0.0004983968330338983, 'samples': 3757568, 'steps': 7338, 'loss/train': 1.9658719301223755}
-03/03/2022 22:05:03 - INFO - codeparrot_training - Step 7339: {'lr': 0.0004983962329587026, 'samples': 3758080, 'steps': 7339, 'loss/train': 2.3265175819396973}
-03/03/2022 22:05:04 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/03/2022 22:05:08 - INFO - codeparrot_training - Step 7340: {'lr': 0.0004983956327715835, 'samples': 3758592, 'steps': 7340, 'loss/train': 1.8171507120132446}
-03/03/2022 22:05:11 - INFO - codeparrot_training - Step 7341: {'lr': 0.000498395032472541, 'samples': 3759104, 'steps': 7341, 'loss/train': 1.925044059753418}
-03/03/2022 22:05:12 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/03/2022 22:05:16 - INFO - codeparrot_training - Step 7342: {'lr': 0.0004983944320615757, 'samples': 3759616, 'steps': 7342, 'loss/train': 3.075350046157837}
-03/03/2022 22:05:20 - INFO - codeparrot_training - Step 7343: {'lr': 0.0004983938315386877, 'samples': 3760128, 'steps': 7343, 'loss/train': 2.125178337097168}
-03/03/2022 22:05:20 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/03/2022 22:05:25 - INFO - codeparrot_training - Step 7344: {'lr': 0.0004983932309038773, 'samples': 3760640, 'steps': 7344, 'loss/train': 1.345078945159912}
-03/03/2022 22:05:28 - INFO - codeparrot_training - Step 7345: {'lr': 0.0004983926301571445, 'samples': 3761152, 'steps': 7345, 'loss/train': 2.3415260314941406}
-03/03/2022 22:05:29 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/03/2022 22:05:34 - INFO - codeparrot_training - Step 7346: {'lr': 0.00049839202929849, 'samples': 3761664, 'steps': 7346, 'loss/train': 3.4427270889282227}
-03/03/2022 22:05:37 - INFO - codeparrot_training - Step 7347: {'lr': 0.0004983914283279139, 'samples': 3762176, 'steps': 7347, 'loss/train': 1.7252973318099976}
-03/03/2022 22:05:37 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/03/2022 22:05:42 - INFO - codeparrot_training - Step 7348: {'lr': 0.0004983908272454164, 'samples': 3762688, 'steps': 7348, 'loss/train': 2.4148459434509277}
-03/03/2022 22:05:45 - INFO - codeparrot_training - Step 7349: {'lr': 0.0004983902260509978, 'samples': 3763200, 'steps': 7349, 'loss/train': 2.1424460411071777}
-03/03/2022 22:05:46 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/03/2022 22:05:51 - INFO - codeparrot_training - Step 7350: {'lr': 0.0004983896247446585, 'samples': 3763712, 'steps': 7350, 'loss/train': 1.4684991836547852}
-03/03/2022 22:05:54 - INFO - codeparrot_training - Step 7351: {'lr': 0.0004983890233263986, 'samples': 3764224, 'steps': 7351, 'loss/train': 2.375582218170166}
-03/03/2022 22:05:54 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/03/2022 22:05:59 - INFO - codeparrot_training - Step 7352: {'lr': 0.0004983884217962185, 'samples': 3764736, 'steps': 7352, 'loss/train': 2.201841354370117}
-03/03/2022 22:06:02 - INFO - codeparrot_training - Step 7353: {'lr': 0.0004983878201541183, 'samples': 3765248, 'steps': 7353, 'loss/train': 1.8637255430221558}
-03/03/2022 22:06:02 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/03/2022 22:06:07 - INFO - codeparrot_training - Step 7354: {'lr': 0.0004983872184000984, 'samples': 3765760, 'steps': 7354, 'loss/train': 2.4036705493927}
-03/03/2022 22:06:10 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/03/2022 22:06:13 - INFO - codeparrot_training - Step 7355: {'lr': 0.0004983866165341592, 'samples': 3766272, 'steps': 7355, 'loss/train': 2.659757375717163}
-03/03/2022 22:06:16 - INFO - codeparrot_training - Step 7356: {'lr': 0.0004983860145563006, 'samples': 3766784, 'steps': 7356, 'loss/train': 1.5560582876205444}
-03/03/2022 22:06:19 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/03/2022 22:06:21 - INFO - codeparrot_training - Step 7357: {'lr': 0.0004983854124665232, 'samples': 3767296, 'steps': 7357, 'loss/train': 2.098149299621582}
-03/03/2022 22:06:24 - INFO - codeparrot_training - Step 7358: {'lr': 0.0004983848102648273, 'samples': 3767808, 'steps': 7358, 'loss/train': 2.3351800441741943}
-03/03/2022 22:06:27 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/03/2022 22:06:29 - INFO - codeparrot_training - Step 7359: {'lr': 0.0004983842079512128, 'samples': 3768320, 'steps': 7359, 'loss/train': 1.0122400522232056}
-03/03/2022 22:06:33 - INFO - codeparrot_training - Step 7360: {'lr': 0.0004983836055256804, 'samples': 3768832, 'steps': 7360, 'loss/train': 2.593264102935791}
-03/03/2022 22:06:35 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/03/2022 22:06:38 - INFO - codeparrot_training - Step 7361: {'lr': 0.0004983830029882301, 'samples': 3769344, 'steps': 7361, 'loss/train': 3.1197452545166016}
-03/03/2022 22:06:41 - INFO - codeparrot_training - Step 7362: {'lr': 0.0004983824003388622, 'samples': 3769856, 'steps': 7362, 'loss/train': 1.6577184200286865}
-03/03/2022 22:06:44 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/03/2022 22:06:46 - INFO - codeparrot_training - Step 7363: {'lr': 0.0004983817975775771, 'samples': 3770368, 'steps': 7363, 'loss/train': 2.285875082015991}
-03/03/2022 22:06:49 - INFO - codeparrot_training - Step 7364: {'lr': 0.000498381194704375, 'samples': 3770880, 'steps': 7364, 'loss/train': 3.670233726501465}
-03/03/2022 22:06:52 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/03/2022 22:06:55 - INFO - codeparrot_training - Step 7365: {'lr': 0.000498380591719256, 'samples': 3771392, 'steps': 7365, 'loss/train': 2.7014548778533936}
-03/03/2022 22:06:58 - INFO - codeparrot_training - Step 7366: {'lr': 0.0004983799886222207, 'samples': 3771904, 'steps': 7366, 'loss/train': 1.7740437984466553}
-03/03/2022 22:07:00 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/03/2022 22:07:03 - INFO - codeparrot_training - Step 7367: {'lr': 0.0004983793854132693, 'samples': 3772416, 'steps': 7367, 'loss/train': 2.3124866485595703}
-03/03/2022 22:07:06 - INFO - codeparrot_training - Step 7368: {'lr': 0.0004983787820924019, 'samples': 3772928, 'steps': 7368, 'loss/train': 1.9625624418258667}
-03/03/2022 22:07:09 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/03/2022 22:07:11 - INFO - codeparrot_training - Step 7369: {'lr': 0.0004983781786596187, 'samples': 3773440, 'steps': 7369, 'loss/train': 2.536102771759033}
-03/03/2022 22:07:15 - INFO - codeparrot_training - Step 7370: {'lr': 0.0004983775751149204, 'samples': 3773952, 'steps': 7370, 'loss/train': 1.7574046850204468}
-03/03/2022 22:07:17 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/03/2022 22:07:20 - INFO - codeparrot_training - Step 7371: {'lr': 0.0004983769714583067, 'samples': 3774464, 'steps': 7371, 'loss/train': 2.3057050704956055}
-03/03/2022 22:07:23 - INFO - codeparrot_training - Step 7372: {'lr': 0.0004983763676897784, 'samples': 3774976, 'steps': 7372, 'loss/train': 2.1173312664031982}
-03/03/2022 22:07:25 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/03/2022 22:07:28 - INFO - codeparrot_training - Step 7373: {'lr': 0.0004983757638093355, 'samples': 3775488, 'steps': 7373, 'loss/train': 2.1158761978149414}
-03/03/2022 22:07:31 - INFO - codeparrot_training - Step 7374: {'lr': 0.0004983751598169781, 'samples': 3776000, 'steps': 7374, 'loss/train': 2.1608119010925293}
-03/03/2022 22:07:34 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/03/2022 22:07:37 - INFO - codeparrot_training - Step 7375: {'lr': 0.000498374555712707, 'samples': 3776512, 'steps': 7375, 'loss/train': 2.4123358726501465}
-03/03/2022 22:07:40 - INFO - codeparrot_training - Step 7376: {'lr': 0.000498373951496522, 'samples': 3777024, 'steps': 7376, 'loss/train': 1.9087380170822144}
-03/03/2022 22:07:42 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/03/2022 22:07:45 - INFO - codeparrot_training - Step 7377: {'lr': 0.0004983733471684234, 'samples': 3777536, 'steps': 7377, 'loss/train': 2.3966221809387207}
-03/03/2022 22:07:48 - INFO - codeparrot_training - Step 7378: {'lr': 0.0004983727427284118, 'samples': 3778048, 'steps': 7378, 'loss/train': 1.7830125093460083}
-03/03/2022 22:07:50 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/03/2022 22:07:53 - INFO - codeparrot_training - Step 7379: {'lr': 0.0004983721381764873, 'samples': 3778560, 'steps': 7379, 'loss/train': 1.231453776359558}
-03/03/2022 22:07:57 - INFO - codeparrot_training - Step 7380: {'lr': 0.00049837153351265, 'samples': 3779072, 'steps': 7380, 'loss/train': 2.2516331672668457}
-03/03/2022 22:07:59 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/03/2022 22:08:02 - INFO - codeparrot_training - Step 7381: {'lr': 0.0004983709287369004, 'samples': 3779584, 'steps': 7381, 'loss/train': 2.3460209369659424}
-03/03/2022 22:08:05 - INFO - codeparrot_training - Step 7382: {'lr': 0.0004983703238492386, 'samples': 3780096, 'steps': 7382, 'loss/train': 2.115123748779297}
-03/03/2022 22:08:07 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/03/2022 22:08:10 - INFO - codeparrot_training - Step 7383: {'lr': 0.000498369718849665, 'samples': 3780608, 'steps': 7383, 'loss/train': 2.0533480644226074}
-03/03/2022 22:08:14 - INFO - codeparrot_training - Step 7384: {'lr': 0.00049836911373818, 'samples': 3781120, 'steps': 7384, 'loss/train': 1.9288259744644165}
-03/03/2022 22:08:16 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/03/2022 22:08:19 - INFO - codeparrot_training - Step 7385: {'lr': 0.0004983685085147836, 'samples': 3781632, 'steps': 7385, 'loss/train': 2.4254682064056396}
-03/03/2022 22:08:22 - INFO - codeparrot_training - Step 7386: {'lr': 0.0004983679031794762, 'samples': 3782144, 'steps': 7386, 'loss/train': 2.099838972091675}
-03/03/2022 22:08:24 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/03/2022 22:08:27 - INFO - codeparrot_training - Step 7387: {'lr': 0.000498367297732258, 'samples': 3782656, 'steps': 7387, 'loss/train': 2.3637404441833496}
-03/03/2022 22:08:31 - INFO - codeparrot_training - Step 7388: {'lr': 0.0004983666921731293, 'samples': 3783168, 'steps': 7388, 'loss/train': 2.8274621963500977}
-03/03/2022 22:08:33 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/03/2022 22:08:36 - INFO - codeparrot_training - Step 7389: {'lr': 0.0004983660865020905, 'samples': 3783680, 'steps': 7389, 'loss/train': 2.378376007080078}
-03/03/2022 22:08:39 - INFO - codeparrot_training - Step 7390: {'lr': 0.0004983654807191418, 'samples': 3784192, 'steps': 7390, 'loss/train': 2.0745160579681396}
-03/03/2022 22:08:41 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/03/2022 22:08:44 - INFO - codeparrot_training - Step 7391: {'lr': 0.0004983648748242833, 'samples': 3784704, 'steps': 7391, 'loss/train': 2.142728328704834}
-03/03/2022 22:08:47 - INFO - codeparrot_training - Step 7392: {'lr': 0.0004983642688175155, 'samples': 3785216, 'steps': 7392, 'loss/train': 2.3912856578826904}
-03/03/2022 22:08:49 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/03/2022 22:08:53 - INFO - codeparrot_training - Step 7393: {'lr': 0.0004983636626988386, 'samples': 3785728, 'steps': 7393, 'loss/train': 2.599656343460083}
-03/03/2022 22:08:56 - INFO - codeparrot_training - Step 7394: {'lr': 0.0004983630564682529, 'samples': 3786240, 'steps': 7394, 'loss/train': 1.7877693176269531}
-03/03/2022 22:08:57 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/03/2022 22:09:01 - INFO - codeparrot_training - Step 7395: {'lr': 0.0004983624501257585, 'samples': 3786752, 'steps': 7395, 'loss/train': 2.1153440475463867}
-03/03/2022 22:09:04 - INFO - codeparrot_training - Step 7396: {'lr': 0.000498361843671356, 'samples': 3787264, 'steps': 7396, 'loss/train': 2.558076858520508}
-03/03/2022 22:09:06 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/03/2022 22:09:09 - INFO - codeparrot_training - Step 7397: {'lr': 0.0004983612371050453, 'samples': 3787776, 'steps': 7397, 'loss/train': 2.484280824661255}
-03/03/2022 22:09:13 - INFO - codeparrot_training - Step 7398: {'lr': 0.000498360630426827, 'samples': 3788288, 'steps': 7398, 'loss/train': 2.156252861022949}
-03/03/2022 22:09:14 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/03/2022 22:09:18 - INFO - codeparrot_training - Step 7399: {'lr': 0.0004983600236367012, 'samples': 3788800, 'steps': 7399, 'loss/train': 1.694176197052002}
-03/03/2022 22:09:21 - INFO - codeparrot_training - Step 7400: {'lr': 0.0004983594167346681, 'samples': 3789312, 'steps': 7400, 'loss/train': 2.3508870601654053}
-03/03/2022 22:09:22 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/03/2022 22:09:26 - INFO - codeparrot_training - Step 7401: {'lr': 0.0004983588097207283, 'samples': 3789824, 'steps': 7401, 'loss/train': 2.306267261505127}
-03/03/2022 22:09:29 - INFO - codeparrot_training - Step 7402: {'lr': 0.0004983582025948816, 'samples': 3790336, 'steps': 7402, 'loss/train': 3.1826202869415283}
-03/03/2022 22:09:31 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/03/2022 22:09:35 - INFO - codeparrot_training - Step 7403: {'lr': 0.0004983575953571287, 'samples': 3790848, 'steps': 7403, 'loss/train': 3.070699691772461}
-03/03/2022 22:09:38 - INFO - codeparrot_training - Step 7404: {'lr': 0.0004983569880074696, 'samples': 3791360, 'steps': 7404, 'loss/train': 2.0291011333465576}
-03/03/2022 22:09:39 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/03/2022 22:09:43 - INFO - codeparrot_training - Step 7405: {'lr': 0.0004983563805459048, 'samples': 3791872, 'steps': 7405, 'loss/train': 2.607405662536621}
-03/03/2022 22:09:46 - INFO - codeparrot_training - Step 7406: {'lr': 0.0004983557729724343, 'samples': 3792384, 'steps': 7406, 'loss/train': 2.326472282409668}
-03/03/2022 22:09:47 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/03/2022 22:09:52 - INFO - codeparrot_training - Step 7407: {'lr': 0.0004983551652870586, 'samples': 3792896, 'steps': 7407, 'loss/train': 2.3073441982269287}
-03/03/2022 22:09:55 - INFO - codeparrot_training - Step 7408: {'lr': 0.000498354557489778, 'samples': 3793408, 'steps': 7408, 'loss/train': 2.0637543201446533}
-03/03/2022 22:09:56 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/03/2022 22:10:00 - INFO - codeparrot_training - Step 7409: {'lr': 0.0004983539495805925, 'samples': 3793920, 'steps': 7409, 'loss/train': 1.934357762336731}
-03/03/2022 22:10:03 - INFO - codeparrot_training - Step 7410: {'lr': 0.0004983533415595026, 'samples': 3794432, 'steps': 7410, 'loss/train': 2.0447027683258057}
-03/03/2022 22:10:04 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/03/2022 22:10:08 - INFO - codeparrot_training - Step 7411: {'lr': 0.0004983527334265085, 'samples': 3794944, 'steps': 7411, 'loss/train': 1.0474672317504883}
-03/03/2022 22:10:12 - INFO - codeparrot_training - Step 7412: {'lr': 0.0004983521251816105, 'samples': 3795456, 'steps': 7412, 'loss/train': 2.0189931392669678}
-03/03/2022 22:10:12 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/03/2022 22:10:17 - INFO - codeparrot_training - Step 7413: {'lr': 0.0004983515168248088, 'samples': 3795968, 'steps': 7413, 'loss/train': 2.6024725437164307}
-03/03/2022 22:10:20 - INFO - codeparrot_training - Step 7414: {'lr': 0.0004983509083561038, 'samples': 3796480, 'steps': 7414, 'loss/train': 1.2033450603485107}
-03/03/2022 22:10:21 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/03/2022 22:10:25 - INFO - codeparrot_training - Step 7415: {'lr': 0.0004983502997754958, 'samples': 3796992, 'steps': 7415, 'loss/train': 2.0498175621032715}
-03/03/2022 22:10:28 - INFO - codeparrot_training - Step 7416: {'lr': 0.0004983496910829849, 'samples': 3797504, 'steps': 7416, 'loss/train': 2.4201912879943848}
-03/03/2022 22:10:29 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/03/2022 22:10:34 - INFO - codeparrot_training - Step 7417: {'lr': 0.0004983490822785715, 'samples': 3798016, 'steps': 7417, 'loss/train': 2.1596386432647705}
-03/03/2022 22:10:37 - INFO - codeparrot_training - Step 7418: {'lr': 0.0004983484733622558, 'samples': 3798528, 'steps': 7418, 'loss/train': 1.6040740013122559}
-03/03/2022 22:10:38 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/03/2022 22:10:42 - INFO - codeparrot_training - Step 7419: {'lr': 0.0004983478643340382, 'samples': 3799040, 'steps': 7419, 'loss/train': 2.782097816467285}
-03/03/2022 22:10:45 - INFO - codeparrot_training - Step 7420: {'lr': 0.0004983472551939186, 'samples': 3799552, 'steps': 7420, 'loss/train': 4.190113067626953}
-03/03/2022 22:10:46 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/03/2022 22:10:50 - INFO - codeparrot_training - Step 7421: {'lr': 0.0004983466459418978, 'samples': 3800064, 'steps': 7421, 'loss/train': 2.8575360774993896}
-03/03/2022 22:10:54 - INFO - codeparrot_training - Step 7422: {'lr': 0.0004983460365779759, 'samples': 3800576, 'steps': 7422, 'loss/train': 2.0481345653533936}
-03/03/2022 22:10:54 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/03/2022 22:10:59 - INFO - codeparrot_training - Step 7423: {'lr': 0.0004983454271021529, 'samples': 3801088, 'steps': 7423, 'loss/train': 2.741654872894287}
-03/03/2022 22:11:02 - INFO - codeparrot_training - Step 7424: {'lr': 0.0004983448175144294, 'samples': 3801600, 'steps': 7424, 'loss/train': 2.3963704109191895}
-03/03/2022 22:11:03 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/03/2022 22:11:07 - INFO - codeparrot_training - Step 7425: {'lr': 0.0004983442078148056, 'samples': 3802112, 'steps': 7425, 'loss/train': 1.4324650764465332}
-03/03/2022 22:11:10 - INFO - codeparrot_training - Step 7426: {'lr': 0.0004983435980032817, 'samples': 3802624, 'steps': 7426, 'loss/train': 2.284802198410034}
-03/03/2022 22:11:11 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/03/2022 22:11:16 - INFO - codeparrot_training - Step 7427: {'lr': 0.0004983429880798579, 'samples': 3803136, 'steps': 7427, 'loss/train': 2.7886297702789307}
-03/03/2022 22:11:19 - INFO - codeparrot_training - Step 7428: {'lr': 0.0004983423780445346, 'samples': 3803648, 'steps': 7428, 'loss/train': 2.2120018005371094}
-03/03/2022 22:11:19 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/03/2022 22:11:24 - INFO - codeparrot_training - Step 7429: {'lr': 0.0004983417678973123, 'samples': 3804160, 'steps': 7429, 'loss/train': 1.56194007396698}
-03/03/2022 22:11:27 - INFO - codeparrot_training - Step 7430: {'lr': 0.0004983411576381907, 'samples': 3804672, 'steps': 7430, 'loss/train': 2.15836763381958}
-03/03/2022 22:11:27 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/03/2022 22:11:33 - INFO - codeparrot_training - Step 7431: {'lr': 0.0004983405472671706, 'samples': 3805184, 'steps': 7431, 'loss/train': 2.45102858543396}
-03/03/2022 22:11:36 - INFO - codeparrot_training - Step 7432: {'lr': 0.000498339936784252, 'samples': 3805696, 'steps': 7432, 'loss/train': 2.4777121543884277}
-03/03/2022 22:11:36 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/03/2022 22:11:41 - INFO - codeparrot_training - Step 7433: {'lr': 0.0004983393261894354, 'samples': 3806208, 'steps': 7433, 'loss/train': 1.5287753343582153}
-03/03/2022 22:11:44 - INFO - codeparrot_training - Step 7434: {'lr': 0.0004983387154827208, 'samples': 3806720, 'steps': 7434, 'loss/train': 2.181509494781494}
-03/03/2022 22:11:44 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/03/2022 22:11:49 - INFO - codeparrot_training - Step 7435: {'lr': 0.0004983381046641085, 'samples': 3807232, 'steps': 7435, 'loss/train': 2.021204710006714}
-03/03/2022 22:11:52 - INFO - codeparrot_training - Step 7436: {'lr': 0.0004983374937335991, 'samples': 3807744, 'steps': 7436, 'loss/train': 2.5058555603027344}
-03/03/2022 22:11:52 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/03/2022 22:11:58 - INFO - codeparrot_training - Step 7437: {'lr': 0.0004983368826911926, 'samples': 3808256, 'steps': 7437, 'loss/train': 2.6141538619995117}
-03/03/2022 22:12:01 - INFO - codeparrot_training - Step 7438: {'lr': 0.0004983362715368893, 'samples': 3808768, 'steps': 7438, 'loss/train': 1.8340306282043457}
-03/03/2022 22:12:01 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/03/2022 22:12:06 - INFO - codeparrot_training - Step 7439: {'lr': 0.0004983356602706895, 'samples': 3809280, 'steps': 7439, 'loss/train': 1.9229141473770142}
-03/03/2022 22:12:09 - INFO - codeparrot_training - Step 7440: {'lr': 0.0004983350488925936, 'samples': 3809792, 'steps': 7440, 'loss/train': 2.4868876934051514}
-03/03/2022 22:12:09 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/03/2022 22:12:15 - INFO - codeparrot_training - Step 7441: {'lr': 0.0004983344374026016, 'samples': 3810304, 'steps': 7441, 'loss/train': 1.5875455141067505}
-03/03/2022 22:12:18 - INFO - codeparrot_training - Step 7442: {'lr': 0.0004983338258007139, 'samples': 3810816, 'steps': 7442, 'loss/train': 2.088980197906494}
-03/03/2022 22:12:18 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/03/2022 22:12:23 - INFO - codeparrot_training - Step 7443: {'lr': 0.0004983332140869309, 'samples': 3811328, 'steps': 7443, 'loss/train': 2.0238828659057617}
-03/03/2022 22:12:26 - INFO - codeparrot_training - Step 7444: {'lr': 0.0004983326022612528, 'samples': 3811840, 'steps': 7444, 'loss/train': 1.9434449672698975}
-03/03/2022 22:12:27 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/03/2022 22:12:32 - INFO - codeparrot_training - Step 7445: {'lr': 0.0004983319903236799, 'samples': 3812352, 'steps': 7445, 'loss/train': 2.211383104324341}
-03/03/2022 22:12:35 - INFO - codeparrot_training - Step 7446: {'lr': 0.0004983313782742124, 'samples': 3812864, 'steps': 7446, 'loss/train': 2.0946333408355713}
-03/03/2022 22:12:35 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/03/2022 22:12:40 - INFO - codeparrot_training - Step 7447: {'lr': 0.0004983307661128505, 'samples': 3813376, 'steps': 7447, 'loss/train': 2.0594518184661865}
-03/03/2022 22:12:43 - INFO - codeparrot_training - Step 7448: {'lr': 0.0004983301538395948, 'samples': 3813888, 'steps': 7448, 'loss/train': 2.0438663959503174}
-03/03/2022 22:12:43 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/03/2022 22:12:49 - INFO - codeparrot_training - Step 7449: {'lr': 0.0004983295414544452, 'samples': 3814400, 'steps': 7449, 'loss/train': 2.6232635974884033}
-03/03/2022 22:12:52 - INFO - codeparrot_training - Step 7450: {'lr': 0.0004983289289574022, 'samples': 3814912, 'steps': 7450, 'loss/train': 2.654139518737793}
-03/03/2022 22:12:52 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/03/2022 22:12:58 - INFO - codeparrot_training - Step 7451: {'lr': 0.000498328316348466, 'samples': 3815424, 'steps': 7451, 'loss/train': 1.911876916885376}
-03/03/2022 22:13:01 - INFO - codeparrot_training - Step 7452: {'lr': 0.0004983277036276369, 'samples': 3815936, 'steps': 7452, 'loss/train': 3.2137255668640137}
-03/03/2022 22:13:03 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 22:13:06 - INFO - codeparrot_training - Step 7453: {'lr': 0.0004983270907949152, 'samples': 3816448, 'steps': 7453, 'loss/train': 2.4177188873291016}
-03/03/2022 22:13:09 - INFO - codeparrot_training - Step 7454: {'lr': 0.0004983264778503011, 'samples': 3816960, 'steps': 7454, 'loss/train': 1.5166256427764893}
-03/03/2022 22:13:11 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/03/2022 22:13:14 - INFO - codeparrot_training - Step 7455: {'lr': 0.0004983258647937949, 'samples': 3817472, 'steps': 7455, 'loss/train': 2.168363094329834}
-03/03/2022 22:13:17 - INFO - codeparrot_training - Step 7456: {'lr': 0.0004983252516253969, 'samples': 3817984, 'steps': 7456, 'loss/train': 1.9578068256378174}
-03/03/2022 22:13:19 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/03/2022 22:13:23 - INFO - codeparrot_training - Step 7457: {'lr': 0.0004983246383451074, 'samples': 3818496, 'steps': 7457, 'loss/train': 2.07273006439209}
-03/03/2022 22:13:26 - INFO - codeparrot_training - Step 7458: {'lr': 0.0004983240249529267, 'samples': 3819008, 'steps': 7458, 'loss/train': 2.1634275913238525}
-03/03/2022 22:13:27 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/03/2022 22:13:31 - INFO - codeparrot_training - Step 7459: {'lr': 0.000498323411448855, 'samples': 3819520, 'steps': 7459, 'loss/train': 2.0790181159973145}
-03/03/2022 22:13:34 - INFO - codeparrot_training - Step 7460: {'lr': 0.0004983227978328926, 'samples': 3820032, 'steps': 7460, 'loss/train': 2.2802298069000244}
-03/03/2022 22:13:35 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/03/2022 22:13:40 - INFO - codeparrot_training - Step 7461: {'lr': 0.0004983221841050397, 'samples': 3820544, 'steps': 7461, 'loss/train': 0.40919721126556396}
-03/03/2022 22:13:43 - INFO - codeparrot_training - Step 7462: {'lr': 0.0004983215702652968, 'samples': 3821056, 'steps': 7462, 'loss/train': 1.33407461643219}
-03/03/2022 22:13:44 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/03/2022 22:13:48 - INFO - codeparrot_training - Step 7463: {'lr': 0.0004983209563136639, 'samples': 3821568, 'steps': 7463, 'loss/train': 2.280904769897461}
-03/03/2022 22:13:51 - INFO - codeparrot_training - Step 7464: {'lr': 0.0004983203422501414, 'samples': 3822080, 'steps': 7464, 'loss/train': 1.7631570100784302}
-03/03/2022 22:13:52 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/03/2022 22:13:56 - INFO - codeparrot_training - Step 7465: {'lr': 0.0004983197280747297, 'samples': 3822592, 'steps': 7465, 'loss/train': 2.0701324939727783}
-03/03/2022 22:13:59 - INFO - codeparrot_training - Step 7466: {'lr': 0.0004983191137874289, 'samples': 3823104, 'steps': 7466, 'loss/train': 1.8878905773162842}
-03/03/2022 22:14:01 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/03/2022 22:14:05 - INFO - codeparrot_training - Step 7467: {'lr': 0.0004983184993882394, 'samples': 3823616, 'steps': 7467, 'loss/train': 2.338683605194092}
-03/03/2022 22:14:08 - INFO - codeparrot_training - Step 7468: {'lr': 0.0004983178848771613, 'samples': 3824128, 'steps': 7468, 'loss/train': 2.134814977645874}
-03/03/2022 22:14:09 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/03/2022 22:14:13 - INFO - codeparrot_training - Step 7469: {'lr': 0.0004983172702541951, 'samples': 3824640, 'steps': 7469, 'loss/train': 2.1899449825286865}
-03/03/2022 22:14:16 - INFO - codeparrot_training - Step 7470: {'lr': 0.0004983166555193409, 'samples': 3825152, 'steps': 7470, 'loss/train': 1.7084014415740967}
-03/03/2022 22:14:17 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/03/2022 22:14:22 - INFO - codeparrot_training - Step 7471: {'lr': 0.000498316040672599, 'samples': 3825664, 'steps': 7471, 'loss/train': 2.553222179412842}
-03/03/2022 22:14:25 - INFO - codeparrot_training - Step 7472: {'lr': 0.00049831542571397, 'samples': 3826176, 'steps': 7472, 'loss/train': 2.6460018157958984}
-03/03/2022 22:14:26 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/03/2022 22:14:30 - INFO - codeparrot_training - Step 7473: {'lr': 0.0004983148106434536, 'samples': 3826688, 'steps': 7473, 'loss/train': 0.7476562261581421}
-03/03/2022 22:14:33 - INFO - codeparrot_training - Step 7474: {'lr': 0.0004983141954610505, 'samples': 3827200, 'steps': 7474, 'loss/train': 2.1923229694366455}
-03/03/2022 22:14:34 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/03/2022 22:14:38 - INFO - codeparrot_training - Step 7475: {'lr': 0.0004983135801667608, 'samples': 3827712, 'steps': 7475, 'loss/train': 3.1024515628814697}
-03/03/2022 22:14:41 - INFO - codeparrot_training - Step 7476: {'lr': 0.0004983129647605849, 'samples': 3828224, 'steps': 7476, 'loss/train': 2.6651828289031982}
-03/03/2022 22:14:42 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/03/2022 22:14:47 - INFO - codeparrot_training - Step 7477: {'lr': 0.0004983123492425229, 'samples': 3828736, 'steps': 7477, 'loss/train': 1.9132497310638428}
-03/03/2022 22:14:50 - INFO - codeparrot_training - Step 7478: {'lr': 0.0004983117336125753, 'samples': 3829248, 'steps': 7478, 'loss/train': 1.7544050216674805}
-03/03/2022 22:14:50 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/03/2022 22:14:55 - INFO - codeparrot_training - Step 7479: {'lr': 0.0004983111178707422, 'samples': 3829760, 'steps': 7479, 'loss/train': 2.6354732513427734}
-03/03/2022 22:14:58 - INFO - codeparrot_training - Step 7480: {'lr': 0.0004983105020170239, 'samples': 3830272, 'steps': 7480, 'loss/train': 2.280963897705078}
-03/03/2022 22:14:59 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/03/2022 22:15:03 - INFO - codeparrot_training - Step 7481: {'lr': 0.0004983098860514209, 'samples': 3830784, 'steps': 7481, 'loss/train': 1.2665616273880005}
-03/03/2022 22:15:07 - INFO - codeparrot_training - Step 7482: {'lr': 0.0004983092699739331, 'samples': 3831296, 'steps': 7482, 'loss/train': 1.8827710151672363}
-03/03/2022 22:15:07 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/03/2022 22:15:12 - INFO - codeparrot_training - Step 7483: {'lr': 0.0004983086537845611, 'samples': 3831808, 'steps': 7483, 'loss/train': 2.3932905197143555}
-03/03/2022 22:15:15 - INFO - codeparrot_training - Step 7484: {'lr': 0.000498308037483305, 'samples': 3832320, 'steps': 7484, 'loss/train': 1.8791015148162842}
-03/03/2022 22:15:15 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/03/2022 22:15:20 - INFO - codeparrot_training - Step 7485: {'lr': 0.0004983074210701651, 'samples': 3832832, 'steps': 7485, 'loss/train': 2.1207027435302734}
-03/03/2022 22:15:23 - INFO - codeparrot_training - Step 7486: {'lr': 0.0004983068045451418, 'samples': 3833344, 'steps': 7486, 'loss/train': 1.3779315948486328}
-03/03/2022 22:15:24 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/03/2022 22:15:29 - INFO - codeparrot_training - Step 7487: {'lr': 0.0004983061879082352, 'samples': 3833856, 'steps': 7487, 'loss/train': 2.6396350860595703}
-03/03/2022 22:15:32 - INFO - codeparrot_training - Step 7488: {'lr': 0.0004983055711594458, 'samples': 3834368, 'steps': 7488, 'loss/train': 1.8798844814300537}
-03/03/2022 22:15:32 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/03/2022 22:15:37 - INFO - codeparrot_training - Step 7489: {'lr': 0.0004983049542987736, 'samples': 3834880, 'steps': 7489, 'loss/train': 2.197601795196533}
-03/03/2022 22:15:40 - INFO - codeparrot_training - Step 7490: {'lr': 0.000498304337326219, 'samples': 3835392, 'steps': 7490, 'loss/train': 2.2823398113250732}
-03/03/2022 22:15:41 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/03/2022 22:15:46 - INFO - codeparrot_training - Step 7491: {'lr': 0.0004983037202417824, 'samples': 3835904, 'steps': 7491, 'loss/train': 2.5793397426605225}
-03/03/2022 22:15:49 - INFO - codeparrot_training - Step 7492: {'lr': 0.0004983031030454639, 'samples': 3836416, 'steps': 7492, 'loss/train': 1.0827505588531494}
-03/03/2022 22:15:49 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/03/2022 22:15:54 - INFO - codeparrot_training - Step 7493: {'lr': 0.0004983024857372639, 'samples': 3836928, 'steps': 7493, 'loss/train': 1.3931479454040527}
-03/03/2022 22:15:57 - INFO - codeparrot_training - Step 7494: {'lr': 0.0004983018683171826, 'samples': 3837440, 'steps': 7494, 'loss/train': 3.0513315200805664}
-03/03/2022 22:15:58 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/03/2022 22:16:03 - INFO - codeparrot_training - Step 7495: {'lr': 0.0004983012507852203, 'samples': 3837952, 'steps': 7495, 'loss/train': 2.34309458732605}
-03/03/2022 22:16:06 - INFO - codeparrot_training - Step 7496: {'lr': 0.0004983006331413773, 'samples': 3838464, 'steps': 7496, 'loss/train': 3.133439540863037}
-03/03/2022 22:16:08 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/03/2022 22:16:12 - INFO - codeparrot_training - Step 7497: {'lr': 0.0004983000153856539, 'samples': 3838976, 'steps': 7497, 'loss/train': 2.3805289268493652}
-03/03/2022 22:16:15 - INFO - codeparrot_training - Step 7498: {'lr': 0.0004982993975180504, 'samples': 3839488, 'steps': 7498, 'loss/train': 2.194275379180908}
-03/03/2022 22:16:17 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/03/2022 22:16:20 - INFO - codeparrot_training - Step 7499: {'lr': 0.0004982987795385669, 'samples': 3840000, 'steps': 7499, 'loss/train': 2.6609225273132324}
-03/03/2022 22:16:23 - INFO - codeparrot_training - Step 7500: {'lr': 0.0004982981614472039, 'samples': 3840512, 'steps': 7500, 'loss/train': 0.5045119524002075}
-03/03/2022 22:16:25 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/03/2022 22:16:28 - INFO - codeparrot_training - Step 7501: {'lr': 0.0004982975432439615, 'samples': 3841024, 'steps': 7501, 'loss/train': 0.9827750325202942}
-03/03/2022 22:16:32 - INFO - codeparrot_training - Step 7502: {'lr': 0.0004982969249288401, 'samples': 3841536, 'steps': 7502, 'loss/train': 3.4702115058898926}
-03/03/2022 22:16:34 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/03/2022 22:16:37 - INFO - codeparrot_training - Step 7503: {'lr': 0.0004982963065018399, 'samples': 3842048, 'steps': 7503, 'loss/train': 1.9491949081420898}
-03/03/2022 22:16:40 - INFO - codeparrot_training - Step 7504: {'lr': 0.0004982956879629612, 'samples': 3842560, 'steps': 7504, 'loss/train': 2.109457015991211}
-03/03/2022 22:16:42 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/03/2022 22:16:46 - INFO - codeparrot_training - Step 7505: {'lr': 0.0004982950693122044, 'samples': 3843072, 'steps': 7505, 'loss/train': 2.057065010070801}
-03/03/2022 22:16:49 - INFO - codeparrot_training - Step 7506: {'lr': 0.0004982944505495696, 'samples': 3843584, 'steps': 7506, 'loss/train': 1.799087643623352}
-03/03/2022 22:16:52 - INFO - codeparrot_training - Step 7507: {'lr': 0.0004982938316750572, 'samples': 3844096, 'steps': 7507, 'loss/train': 3.4144575595855713}
-03/03/2022 22:16:53 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/03/2022 22:16:57 - INFO - codeparrot_training - Step 7508: {'lr': 0.0004982932126886674, 'samples': 3844608, 'steps': 7508, 'loss/train': 2.432258367538452}
-03/03/2022 22:17:00 - INFO - codeparrot_training - Step 7509: {'lr': 0.0004982925935904004, 'samples': 3845120, 'steps': 7509, 'loss/train': 1.6999790668487549}
-03/03/2022 22:17:01 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/03/2022 22:17:06 - INFO - codeparrot_training - Step 7510: {'lr': 0.0004982919743802567, 'samples': 3845632, 'steps': 7510, 'loss/train': 2.601149797439575}
-03/03/2022 22:17:09 - INFO - codeparrot_training - Step 7511: {'lr': 0.0004982913550582364, 'samples': 3846144, 'steps': 7511, 'loss/train': 2.596205472946167}
-03/03/2022 22:17:10 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/03/2022 22:17:14 - INFO - codeparrot_training - Step 7512: {'lr': 0.00049829073562434, 'samples': 3846656, 'steps': 7512, 'loss/train': 2.80031156539917}
-03/03/2022 22:17:17 - INFO - codeparrot_training - Step 7513: {'lr': 0.0004982901160785675, 'samples': 3847168, 'steps': 7513, 'loss/train': 2.2549965381622314}
-03/03/2022 22:17:18 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/03/2022 22:17:23 - INFO - codeparrot_training - Step 7514: {'lr': 0.0004982894964209193, 'samples': 3847680, 'steps': 7514, 'loss/train': 1.935840129852295}
-03/03/2022 22:17:26 - INFO - codeparrot_training - Step 7515: {'lr': 0.0004982888766513957, 'samples': 3848192, 'steps': 7515, 'loss/train': 1.621408224105835}
-03/03/2022 22:17:26 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/03/2022 22:17:31 - INFO - codeparrot_training - Step 7516: {'lr': 0.000498288256769997, 'samples': 3848704, 'steps': 7516, 'loss/train': 2.416687250137329}
-03/03/2022 22:17:34 - INFO - codeparrot_training - Step 7517: {'lr': 0.0004982876367767234, 'samples': 3849216, 'steps': 7517, 'loss/train': 1.867643117904663}
-03/03/2022 22:17:35 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/03/2022 22:17:39 - INFO - codeparrot_training - Step 7518: {'lr': 0.0004982870166715753, 'samples': 3849728, 'steps': 7518, 'loss/train': 1.7029914855957031}
-03/03/2022 22:17:42 - INFO - codeparrot_training - Step 7519: {'lr': 0.0004982863964545529, 'samples': 3850240, 'steps': 7519, 'loss/train': 2.07961368560791}
-03/03/2022 22:17:43 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/03/2022 22:17:48 - INFO - codeparrot_training - Step 7520: {'lr': 0.0004982857761256564, 'samples': 3850752, 'steps': 7520, 'loss/train': 1.336991548538208}
-03/03/2022 22:17:51 - INFO - codeparrot_training - Step 7521: {'lr': 0.0004982851556848861, 'samples': 3851264, 'steps': 7521, 'loss/train': 2.1610989570617676}
-03/03/2022 22:17:52 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/03/2022 22:17:56 - INFO - codeparrot_training - Step 7522: {'lr': 0.0004982845351322424, 'samples': 3851776, 'steps': 7522, 'loss/train': 1.3341115713119507}
-03/03/2022 22:17:59 - INFO - codeparrot_training - Step 7523: {'lr': 0.0004982839144677257, 'samples': 3852288, 'steps': 7523, 'loss/train': 1.7269660234451294}
-03/03/2022 22:18:00 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/03/2022 22:18:05 - INFO - codeparrot_training - Step 7524: {'lr': 0.0004982832936913359, 'samples': 3852800, 'steps': 7524, 'loss/train': 1.2029355764389038}
-03/03/2022 22:18:08 - INFO - codeparrot_training - Step 7525: {'lr': 0.0004982826728030735, 'samples': 3853312, 'steps': 7525, 'loss/train': 1.5659838914871216}
-03/03/2022 22:18:08 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/03/2022 22:18:13 - INFO - codeparrot_training - Step 7526: {'lr': 0.0004982820518029387, 'samples': 3853824, 'steps': 7526, 'loss/train': 2.6561384201049805}
-03/03/2022 22:18:16 - INFO - codeparrot_training - Step 7527: {'lr': 0.000498281430690932, 'samples': 3854336, 'steps': 7527, 'loss/train': 2.3333654403686523}
-03/03/2022 22:18:17 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/03/2022 22:18:21 - INFO - codeparrot_training - Step 7528: {'lr': 0.0004982808094670534, 'samples': 3854848, 'steps': 7528, 'loss/train': 1.9632936716079712}
-03/03/2022 22:18:25 - INFO - codeparrot_training - Step 7529: {'lr': 0.0004982801881313034, 'samples': 3855360, 'steps': 7529, 'loss/train': 2.4315171241760254}
-03/03/2022 22:18:25 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/03/2022 22:18:30 - INFO - codeparrot_training - Step 7530: {'lr': 0.0004982795666836821, 'samples': 3855872, 'steps': 7530, 'loss/train': 2.081352472305298}
-03/03/2022 22:18:33 - INFO - codeparrot_training - Step 7531: {'lr': 0.00049827894512419, 'samples': 3856384, 'steps': 7531, 'loss/train': 2.2347116470336914}
-03/03/2022 22:18:33 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/03/2022 22:18:38 - INFO - codeparrot_training - Step 7532: {'lr': 0.000498278323452827, 'samples': 3856896, 'steps': 7532, 'loss/train': 2.052608013153076}
-03/03/2022 22:18:42 - INFO - codeparrot_training - Step 7533: {'lr': 0.0004982777016695937, 'samples': 3857408, 'steps': 7533, 'loss/train': 1.9700623750686646}
-03/03/2022 22:18:42 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/03/2022 22:18:47 - INFO - codeparrot_training - Step 7534: {'lr': 0.0004982770797744904, 'samples': 3857920, 'steps': 7534, 'loss/train': 2.57554292678833}
-03/03/2022 22:18:50 - INFO - codeparrot_training - Step 7535: {'lr': 0.0004982764577675172, 'samples': 3858432, 'steps': 7535, 'loss/train': 1.9659578800201416}
-03/03/2022 22:18:50 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/03/2022 22:18:55 - INFO - codeparrot_training - Step 7536: {'lr': 0.0004982758356486746, 'samples': 3858944, 'steps': 7536, 'loss/train': 2.163060426712036}
-03/03/2022 22:18:58 - INFO - codeparrot_training - Step 7537: {'lr': 0.0004982752134179624, 'samples': 3859456, 'steps': 7537, 'loss/train': 2.375545024871826}
-03/03/2022 22:18:59 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/03/2022 22:19:04 - INFO - codeparrot_training - Step 7538: {'lr': 0.0004982745910753815, 'samples': 3859968, 'steps': 7538, 'loss/train': 2.3121418952941895}
-03/03/2022 22:19:07 - INFO - codeparrot_training - Step 7539: {'lr': 0.0004982739686209319, 'samples': 3860480, 'steps': 7539, 'loss/train': 1.4646954536437988}
-03/03/2022 22:19:07 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/03/2022 22:19:12 - INFO - codeparrot_training - Step 7540: {'lr': 0.0004982733460546138, 'samples': 3860992, 'steps': 7540, 'loss/train': 1.8687047958374023}
-03/03/2022 22:19:15 - INFO - codeparrot_training - Step 7541: {'lr': 0.0004982727233764276, 'samples': 3861504, 'steps': 7541, 'loss/train': 1.7323505878448486}
-03/03/2022 22:19:16 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/03/2022 22:19:21 - INFO - codeparrot_training - Step 7542: {'lr': 0.0004982721005863734, 'samples': 3862016, 'steps': 7542, 'loss/train': 1.7337188720703125}
-03/03/2022 22:19:24 - INFO - codeparrot_training - Step 7543: {'lr': 0.0004982714776844518, 'samples': 3862528, 'steps': 7543, 'loss/train': 1.8992286920547485}
-03/03/2022 22:19:24 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/03/2022 22:19:29 - INFO - codeparrot_training - Step 7544: {'lr': 0.0004982708546706628, 'samples': 3863040, 'steps': 7544, 'loss/train': 2.207428455352783}
-03/03/2022 22:19:32 - INFO - codeparrot_training - Step 7545: {'lr': 0.0004982702315450068, 'samples': 3863552, 'steps': 7545, 'loss/train': 2.1269078254699707}
-03/03/2022 22:19:37 - INFO - codeparrot_training - Step 7546: {'lr': 0.0004982696083074841, 'samples': 3864064, 'steps': 7546, 'loss/train': 2.9079830646514893}
-03/03/2022 22:19:40 - INFO - codeparrot_training - Step 7547: {'lr': 0.0004982689849580951, 'samples': 3864576, 'steps': 7547, 'loss/train': 1.878933072090149}
-03/03/2022 22:19:41 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/03/2022 22:19:46 - INFO - codeparrot_training - Step 7548: {'lr': 0.0004982683614968396, 'samples': 3865088, 'steps': 7548, 'loss/train': 2.210392475128174}
-03/03/2022 22:19:49 - INFO - codeparrot_training - Step 7549: {'lr': 0.0004982677379237185, 'samples': 3865600, 'steps': 7549, 'loss/train': 2.6015496253967285}
-03/03/2022 22:19:49 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/03/2022 22:19:54 - INFO - codeparrot_training - Step 7550: {'lr': 0.0004982671142387316, 'samples': 3866112, 'steps': 7550, 'loss/train': 2.1620523929595947}
-03/03/2022 22:19:57 - INFO - codeparrot_training - Step 7551: {'lr': 0.0004982664904418794, 'samples': 3866624, 'steps': 7551, 'loss/train': 2.2674660682678223}
-03/03/2022 22:19:58 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/03/2022 22:20:03 - INFO - codeparrot_training - Step 7552: {'lr': 0.0004982658665331622, 'samples': 3867136, 'steps': 7552, 'loss/train': 1.775516152381897}
-03/03/2022 22:20:06 - INFO - codeparrot_training - Step 7553: {'lr': 0.0004982652425125802, 'samples': 3867648, 'steps': 7553, 'loss/train': 5.174736022949219}
-03/03/2022 22:20:07 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/03/2022 22:20:11 - INFO - codeparrot_training - Step 7554: {'lr': 0.0004982646183801337, 'samples': 3868160, 'steps': 7554, 'loss/train': 2.1186742782592773}
-03/03/2022 22:20:14 - INFO - codeparrot_training - Step 7555: {'lr': 0.000498263994135823, 'samples': 3868672, 'steps': 7555, 'loss/train': 3.325895071029663}
-03/03/2022 22:20:16 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/03/2022 22:20:20 - INFO - codeparrot_training - Step 7556: {'lr': 0.0004982633697796484, 'samples': 3869184, 'steps': 7556, 'loss/train': 2.989715337753296}
-03/03/2022 22:20:23 - INFO - codeparrot_training - Step 7557: {'lr': 0.0004982627453116102, 'samples': 3869696, 'steps': 7557, 'loss/train': 2.7991225719451904}
-03/03/2022 22:20:24 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/03/2022 22:20:28 - INFO - codeparrot_training - Step 7558: {'lr': 0.0004982621207317086, 'samples': 3870208, 'steps': 7558, 'loss/train': 2.763843536376953}
-03/03/2022 22:20:31 - INFO - codeparrot_training - Step 7559: {'lr': 0.0004982614960399439, 'samples': 3870720, 'steps': 7559, 'loss/train': 2.6502304077148438}
-03/03/2022 22:20:32 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/03/2022 22:20:37 - INFO - codeparrot_training - Step 7560: {'lr': 0.0004982608712363163, 'samples': 3871232, 'steps': 7560, 'loss/train': 2.291632890701294}
-03/03/2022 22:20:40 - INFO - codeparrot_training - Step 7561: {'lr': 0.0004982602463208263, 'samples': 3871744, 'steps': 7561, 'loss/train': 2.2336020469665527}
-03/03/2022 22:20:41 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/03/2022 22:20:45 - INFO - codeparrot_training - Step 7562: {'lr': 0.0004982596212934742, 'samples': 3872256, 'steps': 7562, 'loss/train': 2.2434751987457275}
-03/03/2022 22:20:48 - INFO - codeparrot_training - Step 7563: {'lr': 0.00049825899615426, 'samples': 3872768, 'steps': 7563, 'loss/train': 2.167595624923706}
-03/03/2022 22:20:49 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/03/2022 22:20:54 - INFO - codeparrot_training - Step 7564: {'lr': 0.000498258370903184, 'samples': 3873280, 'steps': 7564, 'loss/train': 2.080955743789673}
-03/03/2022 22:20:57 - INFO - codeparrot_training - Step 7565: {'lr': 0.0004982577455402467, 'samples': 3873792, 'steps': 7565, 'loss/train': 1.1383239030838013}
-03/03/2022 22:20:58 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/03/2022 22:21:02 - INFO - codeparrot_training - Step 7566: {'lr': 0.0004982571200654485, 'samples': 3874304, 'steps': 7566, 'loss/train': 2.4489269256591797}
-03/03/2022 22:21:05 - INFO - codeparrot_training - Step 7567: {'lr': 0.0004982564944787892, 'samples': 3874816, 'steps': 7567, 'loss/train': 2.529792070388794}
-03/03/2022 22:21:07 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/03/2022 22:21:11 - INFO - codeparrot_training - Step 7568: {'lr': 0.0004982558687802695, 'samples': 3875328, 'steps': 7568, 'loss/train': 1.098523497581482}
-03/03/2022 22:21:14 - INFO - codeparrot_training - Step 7569: {'lr': 0.0004982552429698894, 'samples': 3875840, 'steps': 7569, 'loss/train': 2.1162359714508057}
-03/03/2022 22:21:15 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/03/2022 22:21:19 - INFO - codeparrot_training - Step 7570: {'lr': 0.0004982546170476494, 'samples': 3876352, 'steps': 7570, 'loss/train': 2.532811164855957}
-03/03/2022 22:21:22 - INFO - codeparrot_training - Step 7571: {'lr': 0.0004982539910135497, 'samples': 3876864, 'steps': 7571, 'loss/train': 2.6700363159179688}
-03/03/2022 22:21:24 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/03/2022 22:21:28 - INFO - codeparrot_training - Step 7572: {'lr': 0.0004982533648675906, 'samples': 3877376, 'steps': 7572, 'loss/train': 2.1258368492126465}
-03/03/2022 22:21:31 - INFO - codeparrot_training - Step 7573: {'lr': 0.0004982527386097723, 'samples': 3877888, 'steps': 7573, 'loss/train': 1.671513319015503}
-03/03/2022 22:21:32 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/03/2022 22:21:36 - INFO - codeparrot_training - Step 7574: {'lr': 0.0004982521122400953, 'samples': 3878400, 'steps': 7574, 'loss/train': 2.11077880859375}
-03/03/2022 22:21:39 - INFO - codeparrot_training - Step 7575: {'lr': 0.0004982514857585596, 'samples': 3878912, 'steps': 7575, 'loss/train': 1.8361563682556152}
-03/03/2022 22:21:41 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/03/2022 22:21:45 - INFO - codeparrot_training - Step 7576: {'lr': 0.0004982508591651657, 'samples': 3879424, 'steps': 7576, 'loss/train': 1.390911340713501}
-03/03/2022 22:21:48 - INFO - codeparrot_training - Step 7577: {'lr': 0.0004982502324599137, 'samples': 3879936, 'steps': 7577, 'loss/train': 3.970707416534424}
-03/03/2022 22:21:51 - INFO - codeparrot_training - Step 7578: {'lr': 0.000498249605642804, 'samples': 3880448, 'steps': 7578, 'loss/train': 2.2579405307769775}
-03/03/2022 22:21:51 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/03/2022 22:21:57 - INFO - codeparrot_training - Step 7579: {'lr': 0.0004982489787138369, 'samples': 3880960, 'steps': 7579, 'loss/train': 1.377278208732605}
-03/03/2022 22:21:59 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/03/2022 22:22:02 - INFO - codeparrot_training - Step 7580: {'lr': 0.0004982483516730126, 'samples': 3881472, 'steps': 7580, 'loss/train': 2.1606485843658447}
-03/03/2022 22:22:05 - INFO - codeparrot_training - Step 7581: {'lr': 0.0004982477245203314, 'samples': 3881984, 'steps': 7581, 'loss/train': 2.0498650074005127}
-03/03/2022 22:22:10 - INFO - codeparrot_training - Step 7582: {'lr': 0.0004982470972557936, 'samples': 3882496, 'steps': 7582, 'loss/train': 2.4195215702056885}
-03/03/2022 22:22:13 - INFO - codeparrot_training - Step 7583: {'lr': 0.0004982464698793995, 'samples': 3883008, 'steps': 7583, 'loss/train': 2.154205560684204}
-03/03/2022 22:22:16 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/03/2022 22:22:19 - INFO - codeparrot_training - Step 7584: {'lr': 0.0004982458423911495, 'samples': 3883520, 'steps': 7584, 'loss/train': 2.4892842769622803}
-03/03/2022 22:22:22 - INFO - codeparrot_training - Step 7585: {'lr': 0.0004982452147910437, 'samples': 3884032, 'steps': 7585, 'loss/train': 2.8978686332702637}
-03/03/2022 22:22:25 - INFO - codeparrot_training - Step 7586: {'lr': 0.0004982445870790823, 'samples': 3884544, 'steps': 7586, 'loss/train': 1.8809679746627808}
-03/03/2022 22:22:26 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/03/2022 22:22:31 - INFO - codeparrot_training - Step 7587: {'lr': 0.0004982439592552658, 'samples': 3885056, 'steps': 7587, 'loss/train': 1.7346333265304565}
-03/03/2022 22:22:34 - INFO - codeparrot_training - Step 7588: {'lr': 0.0004982433313195945, 'samples': 3885568, 'steps': 7588, 'loss/train': 2.6471967697143555}
-03/03/2022 22:22:37 - INFO - codeparrot_training - Step 7589: {'lr': 0.0004982427032720685, 'samples': 3886080, 'steps': 7589, 'loss/train': 6.726057052612305}
-03/03/2022 22:22:38 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/03/2022 22:22:43 - INFO - codeparrot_training - Step 7590: {'lr': 0.0004982420751126882, 'samples': 3886592, 'steps': 7590, 'loss/train': 1.5871622562408447}
-03/03/2022 22:22:46 - INFO - codeparrot_training - Step 7591: {'lr': 0.0004982414468414538, 'samples': 3887104, 'steps': 7591, 'loss/train': 2.148817539215088}
-03/03/2022 22:22:47 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/03/2022 22:22:51 - INFO - codeparrot_training - Step 7592: {'lr': 0.0004982408184583656, 'samples': 3887616, 'steps': 7592, 'loss/train': 1.915030598640442}
-03/03/2022 22:22:54 - INFO - codeparrot_training - Step 7593: {'lr': 0.000498240189963424, 'samples': 3888128, 'steps': 7593, 'loss/train': 1.5032256841659546}
-03/03/2022 22:22:55 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/03/2022 22:22:59 - INFO - codeparrot_training - Step 7594: {'lr': 0.0004982395613566291, 'samples': 3888640, 'steps': 7594, 'loss/train': 1.934615135192871}
-03/03/2022 22:23:03 - INFO - codeparrot_training - Step 7595: {'lr': 0.0004982389326379814, 'samples': 3889152, 'steps': 7595, 'loss/train': 1.349902629852295}
-03/03/2022 22:23:04 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/03/2022 22:23:08 - INFO - codeparrot_training - Step 7596: {'lr': 0.000498238303807481, 'samples': 3889664, 'steps': 7596, 'loss/train': 2.5006701946258545}
-03/03/2022 22:23:11 - INFO - codeparrot_training - Step 7597: {'lr': 0.0004982376748651283, 'samples': 3890176, 'steps': 7597, 'loss/train': 2.101569175720215}
-03/03/2022 22:23:12 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/03/2022 22:23:16 - INFO - codeparrot_training - Step 7598: {'lr': 0.0004982370458109235, 'samples': 3890688, 'steps': 7598, 'loss/train': 1.0840299129486084}
-03/03/2022 22:23:20 - INFO - codeparrot_training - Step 7599: {'lr': 0.0004982364166448669, 'samples': 3891200, 'steps': 7599, 'loss/train': 1.2396388053894043}
-03/03/2022 22:23:21 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/03/2022 22:23:25 - INFO - codeparrot_training - Step 7600: {'lr': 0.0004982357873669588, 'samples': 3891712, 'steps': 7600, 'loss/train': 1.593888282775879}
-03/03/2022 22:23:28 - INFO - codeparrot_training - Step 7601: {'lr': 0.0004982351579771995, 'samples': 3892224, 'steps': 7601, 'loss/train': 2.995624542236328}
-03/03/2022 22:23:29 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/03/2022 22:23:34 - INFO - codeparrot_training - Step 7602: {'lr': 0.0004982345284755893, 'samples': 3892736, 'steps': 7602, 'loss/train': 2.385066270828247}
-03/03/2022 22:23:37 - INFO - codeparrot_training - Step 7603: {'lr': 0.0004982338988621284, 'samples': 3893248, 'steps': 7603, 'loss/train': 2.6181087493896484}
-03/03/2022 22:23:40 - INFO - codeparrot_training - Step 7604: {'lr': 0.0004982332691368172, 'samples': 3893760, 'steps': 7604, 'loss/train': 2.08571457862854}
-03/03/2022 22:23:40 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/03/2022 22:23:45 - INFO - codeparrot_training - Step 7605: {'lr': 0.0004982326392996559, 'samples': 3894272, 'steps': 7605, 'loss/train': 2.3120768070220947}
-03/03/2022 22:23:49 - INFO - codeparrot_training - Step 7606: {'lr': 0.0004982320093506449, 'samples': 3894784, 'steps': 7606, 'loss/train': 2.4958598613739014}
-03/03/2022 22:23:49 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/03/2022 22:23:54 - INFO - codeparrot_training - Step 7607: {'lr': 0.0004982313792897843, 'samples': 3895296, 'steps': 7607, 'loss/train': 2.1436586380004883}
-03/03/2022 22:23:57 - INFO - codeparrot_training - Step 7608: {'lr': 0.0004982307491170744, 'samples': 3895808, 'steps': 7608, 'loss/train': 0.9320490956306458}
-03/03/2022 22:23:57 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/03/2022 22:24:02 - INFO - codeparrot_training - Step 7609: {'lr': 0.0004982301188325156, 'samples': 3896320, 'steps': 7609, 'loss/train': 2.217963933944702}
-03/03/2022 22:24:06 - INFO - codeparrot_training - Step 7610: {'lr': 0.0004982294884361081, 'samples': 3896832, 'steps': 7610, 'loss/train': 2.57059645652771}
-03/03/2022 22:24:06 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/03/2022 22:24:11 - INFO - codeparrot_training - Step 7611: {'lr': 0.0004982288579278522, 'samples': 3897344, 'steps': 7611, 'loss/train': 1.142482876777649}
-03/03/2022 22:24:14 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/03/2022 22:24:16 - INFO - codeparrot_training - Step 7612: {'lr': 0.0004982282273077483, 'samples': 3897856, 'steps': 7612, 'loss/train': 2.1639838218688965}
-03/03/2022 22:24:19 - INFO - codeparrot_training - Step 7613: {'lr': 0.0004982275965757965, 'samples': 3898368, 'steps': 7613, 'loss/train': 1.9559534788131714}
-03/03/2022 22:24:23 - INFO - codeparrot_training - Step 7614: {'lr': 0.0004982269657319974, 'samples': 3898880, 'steps': 7614, 'loss/train': 2.8634440898895264}
-03/03/2022 22:24:23 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/03/2022 22:24:28 - INFO - codeparrot_training - Step 7615: {'lr': 0.0004982263347763508, 'samples': 3899392, 'steps': 7615, 'loss/train': 2.972719430923462}
-03/03/2022 22:24:31 - INFO - codeparrot_training - Step 7616: {'lr': 0.0004982257037088574, 'samples': 3899904, 'steps': 7616, 'loss/train': 2.064697265625}
-03/03/2022 22:24:32 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/03/2022 22:24:36 - INFO - codeparrot_training - Step 7617: {'lr': 0.0004982250725295173, 'samples': 3900416, 'steps': 7617, 'loss/train': 2.908677101135254}
-03/03/2022 22:24:40 - INFO - codeparrot_training - Step 7618: {'lr': 0.0004982244412383307, 'samples': 3900928, 'steps': 7618, 'loss/train': 1.7776557207107544}
-03/03/2022 22:24:40 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/03/2022 22:24:45 - INFO - codeparrot_training - Step 7619: {'lr': 0.0004982238098352981, 'samples': 3901440, 'steps': 7619, 'loss/train': 2.0980663299560547}
-03/03/2022 22:24:48 - INFO - codeparrot_training - Step 7620: {'lr': 0.0004982231783204196, 'samples': 3901952, 'steps': 7620, 'loss/train': 2.2709853649139404}
-03/03/2022 22:24:49 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/03/2022 22:24:53 - INFO - codeparrot_training - Step 7621: {'lr': 0.0004982225466936957, 'samples': 3902464, 'steps': 7621, 'loss/train': 2.501005172729492}
-03/03/2022 22:24:56 - INFO - codeparrot_training - Step 7622: {'lr': 0.0004982219149551265, 'samples': 3902976, 'steps': 7622, 'loss/train': 2.4740359783172607}
-03/03/2022 22:24:57 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/03/2022 22:25:02 - INFO - codeparrot_training - Step 7623: {'lr': 0.0004982212831047123, 'samples': 3903488, 'steps': 7623, 'loss/train': 2.925180435180664}
-03/03/2022 22:25:05 - INFO - codeparrot_training - Step 7624: {'lr': 0.0004982206511424534, 'samples': 3904000, 'steps': 7624, 'loss/train': 2.473062038421631}
-03/03/2022 22:25:05 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/03/2022 22:25:10 - INFO - codeparrot_training - Step 7625: {'lr': 0.0004982200190683502, 'samples': 3904512, 'steps': 7625, 'loss/train': 2.0527472496032715}
-03/03/2022 22:25:13 - INFO - codeparrot_training - Step 7626: {'lr': 0.0004982193868824028, 'samples': 3905024, 'steps': 7626, 'loss/train': 1.984508752822876}
-03/03/2022 22:25:14 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/03/2022 22:25:18 - INFO - codeparrot_training - Step 7627: {'lr': 0.0004982187545846116, 'samples': 3905536, 'steps': 7627, 'loss/train': 1.2554486989974976}
-03/03/2022 22:25:22 - INFO - codeparrot_training - Step 7628: {'lr': 0.0004982181221749769, 'samples': 3906048, 'steps': 7628, 'loss/train': 1.7409878969192505}
-03/03/2022 22:25:22 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/03/2022 22:25:27 - INFO - codeparrot_training - Step 7629: {'lr': 0.0004982174896534989, 'samples': 3906560, 'steps': 7629, 'loss/train': 1.7162071466445923}
-03/03/2022 22:25:30 - INFO - codeparrot_training - Step 7630: {'lr': 0.0004982168570201779, 'samples': 3907072, 'steps': 7630, 'loss/train': 1.6033097505569458}
-03/03/2022 22:25:31 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/03/2022 22:25:35 - INFO - codeparrot_training - Step 7631: {'lr': 0.0004982162242750143, 'samples': 3907584, 'steps': 7631, 'loss/train': 4.240904808044434}
-03/03/2022 22:25:38 - INFO - codeparrot_training - Step 7632: {'lr': 0.0004982155914180082, 'samples': 3908096, 'steps': 7632, 'loss/train': 1.8338608741760254}
-03/03/2022 22:25:39 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/03/2022 22:25:44 - INFO - codeparrot_training - Step 7633: {'lr': 0.0004982149584491601, 'samples': 3908608, 'steps': 7633, 'loss/train': 1.8554128408432007}
-03/03/2022 22:25:47 - INFO - codeparrot_training - Step 7634: {'lr': 0.0004982143253684701, 'samples': 3909120, 'steps': 7634, 'loss/train': 2.3872828483581543}
-03/03/2022 22:25:47 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/03/2022 22:25:52 - INFO - codeparrot_training - Step 7635: {'lr': 0.0004982136921759385, 'samples': 3909632, 'steps': 7635, 'loss/train': 2.662606716156006}
-03/03/2022 22:25:55 - INFO - codeparrot_training - Step 7636: {'lr': 0.0004982130588715657, 'samples': 3910144, 'steps': 7636, 'loss/train': 1.6110111474990845}
-03/03/2022 22:25:56 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/03/2022 22:26:00 - INFO - codeparrot_training - Step 7637: {'lr': 0.000498212425455352, 'samples': 3910656, 'steps': 7637, 'loss/train': 2.0314414501190186}
-03/03/2022 22:26:04 - INFO - codeparrot_training - Step 7638: {'lr': 0.0004982117919272975, 'samples': 3911168, 'steps': 7638, 'loss/train': 2.031074047088623}
-03/03/2022 22:26:04 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/03/2022 22:26:09 - INFO - codeparrot_training - Step 7639: {'lr': 0.0004982111582874026, 'samples': 3911680, 'steps': 7639, 'loss/train': 2.2564446926116943}
-03/03/2022 22:26:12 - INFO - codeparrot_training - Step 7640: {'lr': 0.0004982105245356676, 'samples': 3912192, 'steps': 7640, 'loss/train': 2.4305784702301025}
-03/03/2022 22:26:13 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/03/2022 22:26:17 - INFO - codeparrot_training - Step 7641: {'lr': 0.0004982098906720928, 'samples': 3912704, 'steps': 7641, 'loss/train': 1.784283995628357}
-03/03/2022 22:26:20 - INFO - codeparrot_training - Step 7642: {'lr': 0.0004982092566966785, 'samples': 3913216, 'steps': 7642, 'loss/train': 2.5047216415405273}
-03/03/2022 22:26:21 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/03/2022 22:26:26 - INFO - codeparrot_training - Step 7643: {'lr': 0.0004982086226094248, 'samples': 3913728, 'steps': 7643, 'loss/train': 1.633302927017212}
-03/03/2022 22:26:29 - INFO - codeparrot_training - Step 7644: {'lr': 0.0004982079884103322, 'samples': 3914240, 'steps': 7644, 'loss/train': 2.171318292617798}
-03/03/2022 22:26:29 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/03/2022 22:26:34 - INFO - codeparrot_training - Step 7645: {'lr': 0.0004982073540994009, 'samples': 3914752, 'steps': 7645, 'loss/train': 0.21044030785560608}
-03/03/2022 22:26:37 - INFO - codeparrot_training - Step 7646: {'lr': 0.0004982067196766312, 'samples': 3915264, 'steps': 7646, 'loss/train': 2.035041332244873}
-03/03/2022 22:26:38 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/03/2022 22:26:42 - INFO - codeparrot_training - Step 7647: {'lr': 0.0004982060851420235, 'samples': 3915776, 'steps': 7647, 'loss/train': 2.2511231899261475}
-03/03/2022 22:26:46 - INFO - codeparrot_training - Step 7648: {'lr': 0.0004982054504955778, 'samples': 3916288, 'steps': 7648, 'loss/train': 2.215299129486084}
-03/03/2022 22:26:46 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/03/2022 22:26:51 - INFO - codeparrot_training - Step 7649: {'lr': 0.0004982048157372946, 'samples': 3916800, 'steps': 7649, 'loss/train': 1.817892074584961}
-03/03/2022 22:26:54 - INFO - codeparrot_training - Step 7650: {'lr': 0.0004982041808671741, 'samples': 3917312, 'steps': 7650, 'loss/train': 2.0650010108947754}
-03/03/2022 22:26:54 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/03/2022 22:26:59 - INFO - codeparrot_training - Step 7651: {'lr': 0.0004982035458852168, 'samples': 3917824, 'steps': 7651, 'loss/train': 0.41459500789642334}
-03/03/2022 22:27:02 - INFO - codeparrot_training - Step 7652: {'lr': 0.0004982029107914226, 'samples': 3918336, 'steps': 7652, 'loss/train': 2.8926727771759033}
-03/03/2022 22:27:03 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/03/2022 22:27:08 - INFO - codeparrot_training - Step 7653: {'lr': 0.0004982022755857921, 'samples': 3918848, 'steps': 7653, 'loss/train': 2.0406606197357178}
-03/03/2022 22:27:11 - INFO - codeparrot_training - Step 7654: {'lr': 0.0004982016402683255, 'samples': 3919360, 'steps': 7654, 'loss/train': 1.8060544729232788}
-03/03/2022 22:27:11 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/03/2022 22:27:16 - INFO - codeparrot_training - Step 7655: {'lr': 0.000498201004839023, 'samples': 3919872, 'steps': 7655, 'loss/train': 2.0891170501708984}
-03/03/2022 22:27:19 - INFO - codeparrot_training - Step 7656: {'lr': 0.000498200369297885, 'samples': 3920384, 'steps': 7656, 'loss/train': 1.569249153137207}
-03/03/2022 22:27:20 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/03/2022 22:27:25 - INFO - codeparrot_training - Step 7657: {'lr': 0.0004981997336449118, 'samples': 3920896, 'steps': 7657, 'loss/train': 2.7454071044921875}
-03/03/2022 22:27:28 - INFO - codeparrot_training - Step 7658: {'lr': 0.0004981990978801035, 'samples': 3921408, 'steps': 7658, 'loss/train': 1.3490196466445923}
-03/03/2022 22:27:29 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/03/2022 22:27:33 - INFO - codeparrot_training - Step 7659: {'lr': 0.0004981984620034606, 'samples': 3921920, 'steps': 7659, 'loss/train': 2.0519046783447266}
-03/03/2022 22:27:37 - INFO - codeparrot_training - Step 7660: {'lr': 0.0004981978260149833, 'samples': 3922432, 'steps': 7660, 'loss/train': 0.7957608699798584}
-03/03/2022 22:27:37 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/03/2022 22:27:42 - INFO - codeparrot_training - Step 7661: {'lr': 0.0004981971899146719, 'samples': 3922944, 'steps': 7661, 'loss/train': 1.7505239248275757}
-03/03/2022 22:27:45 - INFO - codeparrot_training - Step 7662: {'lr': 0.0004981965537025267, 'samples': 3923456, 'steps': 7662, 'loss/train': 1.9670664072036743}
-03/03/2022 22:27:46 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/03/2022 22:27:50 - INFO - codeparrot_training - Step 7663: {'lr': 0.000498195917378548, 'samples': 3923968, 'steps': 7663, 'loss/train': 2.0899288654327393}
-03/03/2022 22:27:53 - INFO - codeparrot_training - Step 7664: {'lr': 0.0004981952809427359, 'samples': 3924480, 'steps': 7664, 'loss/train': 2.024052619934082}
-03/03/2022 22:27:54 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/03/2022 22:27:59 - INFO - codeparrot_training - Step 7665: {'lr': 0.0004981946443950909, 'samples': 3924992, 'steps': 7665, 'loss/train': 2.593583106994629}
-03/03/2022 22:28:02 - INFO - codeparrot_training - Step 7666: {'lr': 0.0004981940077356132, 'samples': 3925504, 'steps': 7666, 'loss/train': 2.3332724571228027}
-03/03/2022 22:28:02 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/03/2022 22:28:07 - INFO - codeparrot_training - Step 7667: {'lr': 0.0004981933709643032, 'samples': 3926016, 'steps': 7667, 'loss/train': 2.4239296913146973}
-03/03/2022 22:28:10 - INFO - codeparrot_training - Step 7668: {'lr': 0.000498192734081161, 'samples': 3926528, 'steps': 7668, 'loss/train': 1.6799849271774292}
-03/03/2022 22:28:11 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/03/2022 22:28:16 - INFO - codeparrot_training - Step 7669: {'lr': 0.000498192097086187, 'samples': 3927040, 'steps': 7669, 'loss/train': 2.4123501777648926}
-03/03/2022 22:28:19 - INFO - codeparrot_training - Step 7670: {'lr': 0.0004981914599793816, 'samples': 3927552, 'steps': 7670, 'loss/train': 2.9757277965545654}
-03/03/2022 22:28:20 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/03/2022 22:28:24 - INFO - codeparrot_training - Step 7671: {'lr': 0.0004981908227607448, 'samples': 3928064, 'steps': 7671, 'loss/train': 1.8859120607376099}
-03/03/2022 22:28:27 - INFO - codeparrot_training - Step 7672: {'lr': 0.0004981901854302771, 'samples': 3928576, 'steps': 7672, 'loss/train': 1.754683017730713}
-03/03/2022 22:28:29 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/03/2022 22:28:33 - INFO - codeparrot_training - Step 7673: {'lr': 0.0004981895479879787, 'samples': 3929088, 'steps': 7673, 'loss/train': 0.8753159046173096}
-03/03/2022 22:28:36 - INFO - codeparrot_training - Step 7674: {'lr': 0.0004981889104338499, 'samples': 3929600, 'steps': 7674, 'loss/train': 2.1626338958740234}
-03/03/2022 22:28:38 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/03/2022 22:28:41 - INFO - codeparrot_training - Step 7675: {'lr': 0.0004981882727678912, 'samples': 3930112, 'steps': 7675, 'loss/train': 1.7066890001296997}
-03/03/2022 22:28:44 - INFO - codeparrot_training - Step 7676: {'lr': 0.0004981876349901025, 'samples': 3930624, 'steps': 7676, 'loss/train': 1.7553153038024902}
-03/03/2022 22:28:47 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/03/2022 22:28:50 - INFO - codeparrot_training - Step 7677: {'lr': 0.0004981869971004843, 'samples': 3931136, 'steps': 7677, 'loss/train': 0.9302951693534851}
-03/03/2022 22:28:53 - INFO - codeparrot_training - Step 7678: {'lr': 0.0004981863590990369, 'samples': 3931648, 'steps': 7678, 'loss/train': 1.8904857635498047}
-03/03/2022 22:28:55 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/03/2022 22:28:58 - INFO - codeparrot_training - Step 7679: {'lr': 0.0004981857209857605, 'samples': 3932160, 'steps': 7679, 'loss/train': 2.8859825134277344}
-03/03/2022 22:29:01 - INFO - codeparrot_training - Step 7680: {'lr': 0.0004981850827606556, 'samples': 3932672, 'steps': 7680, 'loss/train': 2.510852336883545}
-03/03/2022 22:29:03 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/03/2022 22:29:07 - INFO - codeparrot_training - Step 7681: {'lr': 0.0004981844444237223, 'samples': 3933184, 'steps': 7681, 'loss/train': 1.062875509262085}
-03/03/2022 22:29:10 - INFO - codeparrot_training - Step 7682: {'lr': 0.0004981838059749607, 'samples': 3933696, 'steps': 7682, 'loss/train': 2.7275772094726562}
-03/03/2022 22:29:11 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/03/2022 22:29:15 - INFO - codeparrot_training - Step 7683: {'lr': 0.0004981831674143716, 'samples': 3934208, 'steps': 7683, 'loss/train': 1.2240326404571533}
-03/03/2022 22:29:18 - INFO - codeparrot_training - Step 7684: {'lr': 0.0004981825287419549, 'samples': 3934720, 'steps': 7684, 'loss/train': 1.2858436107635498}
-03/03/2022 22:29:20 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/03/2022 22:29:23 - INFO - codeparrot_training - Step 7685: {'lr': 0.0004981818899577108, 'samples': 3935232, 'steps': 7685, 'loss/train': 1.7200510501861572}
-03/03/2022 22:29:27 - INFO - codeparrot_training - Step 7686: {'lr': 0.0004981812510616399, 'samples': 3935744, 'steps': 7686, 'loss/train': 2.173506259918213}
-03/03/2022 22:29:28 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/03/2022 22:29:32 - INFO - codeparrot_training - Step 7687: {'lr': 0.0004981806120537424, 'samples': 3936256, 'steps': 7687, 'loss/train': 2.087646722793579}
-03/03/2022 22:29:35 - INFO - codeparrot_training - Step 7688: {'lr': 0.0004981799729340185, 'samples': 3936768, 'steps': 7688, 'loss/train': 2.3247852325439453}
-03/03/2022 22:29:37 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/03/2022 22:29:40 - INFO - codeparrot_training - Step 7689: {'lr': 0.0004981793337024685, 'samples': 3937280, 'steps': 7689, 'loss/train': 3.0797860622406006}
-03/03/2022 22:29:44 - INFO - codeparrot_training - Step 7690: {'lr': 0.0004981786943590928, 'samples': 3937792, 'steps': 7690, 'loss/train': 2.518376111984253}
-03/03/2022 22:29:45 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/03/2022 22:29:49 - INFO - codeparrot_training - Step 7691: {'lr': 0.0004981780549038916, 'samples': 3938304, 'steps': 7691, 'loss/train': 1.739656686782837}
-03/03/2022 22:29:52 - INFO - codeparrot_training - Step 7692: {'lr': 0.0004981774153368651, 'samples': 3938816, 'steps': 7692, 'loss/train': 2.6167917251586914}
-03/03/2022 22:29:53 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/03/2022 22:29:57 - INFO - codeparrot_training - Step 7693: {'lr': 0.0004981767756580138, 'samples': 3939328, 'steps': 7693, 'loss/train': 2.380770206451416}
-03/03/2022 22:30:00 - INFO - codeparrot_training - Step 7694: {'lr': 0.0004981761358673378, 'samples': 3939840, 'steps': 7694, 'loss/train': 0.8536055088043213}
-03/03/2022 22:30:02 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/03/2022 22:30:06 - INFO - codeparrot_training - Step 7695: {'lr': 0.0004981754959648376, 'samples': 3940352, 'steps': 7695, 'loss/train': 2.5073533058166504}
-03/03/2022 22:30:09 - INFO - codeparrot_training - Step 7696: {'lr': 0.0004981748559505131, 'samples': 3940864, 'steps': 7696, 'loss/train': 6.9878387451171875}
-03/03/2022 22:30:12 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/03/2022 22:30:14 - INFO - codeparrot_training - Step 7697: {'lr': 0.0004981742158243651, 'samples': 3941376, 'steps': 7697, 'loss/train': 0.9906011819839478}
-03/03/2022 22:30:17 - INFO - codeparrot_training - Step 7698: {'lr': 0.0004981735755863934, 'samples': 3941888, 'steps': 7698, 'loss/train': 2.3180084228515625}
-03/03/2022 22:30:21 - INFO - codeparrot_training - Step 7699: {'lr': 0.0004981729352365986, 'samples': 3942400, 'steps': 7699, 'loss/train': 0.31057536602020264}
-03/03/2022 22:30:21 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/03/2022 22:30:26 - INFO - codeparrot_training - Step 7700: {'lr': 0.0004981722947749811, 'samples': 3942912, 'steps': 7700, 'loss/train': 1.7250936031341553}
-03/03/2022 22:30:29 - INFO - codeparrot_training - Step 7701: {'lr': 0.0004981716542015408, 'samples': 3943424, 'steps': 7701, 'loss/train': 2.417224168777466}
-03/03/2022 22:30:29 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/03/2022 22:30:34 - INFO - codeparrot_training - Step 7702: {'lr': 0.0004981710135162781, 'samples': 3943936, 'steps': 7702, 'loss/train': 1.0266000032424927}
-03/03/2022 22:30:38 - INFO - codeparrot_training - Step 7703: {'lr': 0.0004981703727191935, 'samples': 3944448, 'steps': 7703, 'loss/train': 1.8224023580551147}
-03/03/2022 22:30:38 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/03/2022 22:30:43 - INFO - codeparrot_training - Step 7704: {'lr': 0.0004981697318102872, 'samples': 3944960, 'steps': 7704, 'loss/train': 3.2608094215393066}
-03/03/2022 22:30:46 - INFO - codeparrot_training - Step 7705: {'lr': 0.0004981690907895594, 'samples': 3945472, 'steps': 7705, 'loss/train': 2.516427516937256}
-03/03/2022 22:30:46 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/03/2022 22:30:52 - INFO - codeparrot_training - Step 7706: {'lr': 0.0004981684496570104, 'samples': 3945984, 'steps': 7706, 'loss/train': 1.6285040378570557}
-03/03/2022 22:30:55 - INFO - codeparrot_training - Step 7707: {'lr': 0.0004981678084126405, 'samples': 3946496, 'steps': 7707, 'loss/train': 2.723060131072998}
-03/03/2022 22:30:55 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/03/2022 22:31:00 - INFO - codeparrot_training - Step 7708: {'lr': 0.0004981671670564502, 'samples': 3947008, 'steps': 7708, 'loss/train': 2.2069430351257324}
-03/03/2022 22:31:03 - INFO - codeparrot_training - Step 7709: {'lr': 0.0004981665255884394, 'samples': 3947520, 'steps': 7709, 'loss/train': 1.6104531288146973}
-03/03/2022 22:31:03 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/03/2022 22:31:08 - INFO - codeparrot_training - Step 7710: {'lr': 0.0004981658840086087, 'samples': 3948032, 'steps': 7710, 'loss/train': 0.6510537266731262}
-03/03/2022 22:31:11 - INFO - codeparrot_training - Step 7711: {'lr': 0.0004981652423169582, 'samples': 3948544, 'steps': 7711, 'loss/train': 1.9765191078186035}
-03/03/2022 22:31:11 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 22:31:17 - INFO - codeparrot_training - Step 7712: {'lr': 0.0004981646005134884, 'samples': 3949056, 'steps': 7712, 'loss/train': 2.572314500808716}
-03/03/2022 22:31:20 - INFO - codeparrot_training - Step 7713: {'lr': 0.0004981639585981993, 'samples': 3949568, 'steps': 7713, 'loss/train': 2.3746886253356934}
-03/03/2022 22:31:20 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/03/2022 22:31:25 - INFO - codeparrot_training - Step 7714: {'lr': 0.0004981633165710914, 'samples': 3950080, 'steps': 7714, 'loss/train': 2.3653604984283447}
-03/03/2022 22:31:28 - INFO - codeparrot_training - Step 7715: {'lr': 0.000498162674432165, 'samples': 3950592, 'steps': 7715, 'loss/train': 2.2049129009246826}
-03/03/2022 22:31:29 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/03/2022 22:31:34 - INFO - codeparrot_training - Step 7716: {'lr': 0.0004981620321814203, 'samples': 3951104, 'steps': 7716, 'loss/train': 2.5657296180725098}
-03/03/2022 22:31:37 - INFO - codeparrot_training - Step 7717: {'lr': 0.0004981613898188576, 'samples': 3951616, 'steps': 7717, 'loss/train': 1.7940800189971924}
-03/03/2022 22:31:37 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/03/2022 22:31:42 - INFO - codeparrot_training - Step 7718: {'lr': 0.0004981607473444772, 'samples': 3952128, 'steps': 7718, 'loss/train': 2.41029691696167}
-03/03/2022 22:31:46 - INFO - codeparrot_training - Step 7719: {'lr': 0.0004981601047582794, 'samples': 3952640, 'steps': 7719, 'loss/train': 1.7852938175201416}
-03/03/2022 22:31:47 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/03/2022 22:31:51 - INFO - codeparrot_training - Step 7720: {'lr': 0.0004981594620602645, 'samples': 3953152, 'steps': 7720, 'loss/train': 2.4265871047973633}
-03/03/2022 22:31:54 - INFO - codeparrot_training - Step 7721: {'lr': 0.0004981588192504329, 'samples': 3953664, 'steps': 7721, 'loss/train': 1.7088927030563354}
-03/03/2022 22:31:55 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/03/2022 22:31:59 - INFO - codeparrot_training - Step 7722: {'lr': 0.0004981581763287845, 'samples': 3954176, 'steps': 7722, 'loss/train': 2.4132113456726074}
-03/03/2022 22:32:03 - INFO - codeparrot_training - Step 7723: {'lr': 0.0004981575332953201, 'samples': 3954688, 'steps': 7723, 'loss/train': 2.2091028690338135}
-03/03/2022 22:32:04 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/03/2022 22:32:08 - INFO - codeparrot_training - Step 7724: {'lr': 0.0004981568901500396, 'samples': 3955200, 'steps': 7724, 'loss/train': 2.1756722927093506}
-03/03/2022 22:32:11 - INFO - codeparrot_training - Step 7725: {'lr': 0.0004981562468929435, 'samples': 3955712, 'steps': 7725, 'loss/train': 2.846879005432129}
-03/03/2022 22:32:12 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/03/2022 22:32:16 - INFO - codeparrot_training - Step 7726: {'lr': 0.000498155603524032, 'samples': 3956224, 'steps': 7726, 'loss/train': 2.904846429824829}
-03/03/2022 22:32:20 - INFO - codeparrot_training - Step 7727: {'lr': 0.0004981549600433054, 'samples': 3956736, 'steps': 7727, 'loss/train': 1.886224627494812}
-03/03/2022 22:32:21 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/03/2022 22:32:25 - INFO - codeparrot_training - Step 7728: {'lr': 0.000498154316450764, 'samples': 3957248, 'steps': 7728, 'loss/train': 2.8088321685791016}
-03/03/2022 22:32:28 - INFO - codeparrot_training - Step 7729: {'lr': 0.0004981536727464082, 'samples': 3957760, 'steps': 7729, 'loss/train': 2.115401268005371}
-03/03/2022 22:32:30 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/03/2022 22:32:33 - INFO - codeparrot_training - Step 7730: {'lr': 0.0004981530289302381, 'samples': 3958272, 'steps': 7730, 'loss/train': 2.4919090270996094}
-03/03/2022 22:32:37 - INFO - codeparrot_training - Step 7731: {'lr': 0.000498152385002254, 'samples': 3958784, 'steps': 7731, 'loss/train': 1.7270822525024414}
-03/03/2022 22:32:38 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/03/2022 22:32:42 - INFO - codeparrot_training - Step 7732: {'lr': 0.0004981517409624564, 'samples': 3959296, 'steps': 7732, 'loss/train': 2.1263318061828613}
-03/03/2022 22:32:45 - INFO - codeparrot_training - Step 7733: {'lr': 0.0004981510968108453, 'samples': 3959808, 'steps': 7733, 'loss/train': 3.0273001194000244}
-03/03/2022 22:32:46 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/03/2022 22:32:50 - INFO - codeparrot_training - Step 7734: {'lr': 0.0004981504525474214, 'samples': 3960320, 'steps': 7734, 'loss/train': 2.135021924972534}
-03/03/2022 22:32:53 - INFO - codeparrot_training - Step 7735: {'lr': 0.0004981498081721845, 'samples': 3960832, 'steps': 7735, 'loss/train': 0.9534957408905029}
-03/03/2022 22:32:54 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/03/2022 22:32:59 - INFO - codeparrot_training - Step 7736: {'lr': 0.0004981491636851351, 'samples': 3961344, 'steps': 7736, 'loss/train': 2.323019504547119}
-03/03/2022 22:33:02 - INFO - codeparrot_training - Step 7737: {'lr': 0.0004981485190862737, 'samples': 3961856, 'steps': 7737, 'loss/train': 1.120634913444519}
-03/03/2022 22:33:02 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/03/2022 22:33:07 - INFO - codeparrot_training - Step 7738: {'lr': 0.0004981478743756004, 'samples': 3962368, 'steps': 7738, 'loss/train': 2.9454965591430664}
-03/03/2022 22:33:10 - INFO - codeparrot_training - Step 7739: {'lr': 0.0004981472295531153, 'samples': 3962880, 'steps': 7739, 'loss/train': 1.8958581686019897}
-03/03/2022 22:33:11 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/03/2022 22:33:16 - INFO - codeparrot_training - Step 7740: {'lr': 0.000498146584618819, 'samples': 3963392, 'steps': 7740, 'loss/train': 1.6936705112457275}
-03/03/2022 22:33:19 - INFO - codeparrot_training - Step 7741: {'lr': 0.0004981459395727117, 'samples': 3963904, 'steps': 7741, 'loss/train': 3.1925861835479736}
-03/03/2022 22:33:21 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/03/2022 22:33:24 - INFO - codeparrot_training - Step 7742: {'lr': 0.0004981452944147937, 'samples': 3964416, 'steps': 7742, 'loss/train': 2.077404260635376}
-03/03/2022 22:33:27 - INFO - codeparrot_training - Step 7743: {'lr': 0.0004981446491450652, 'samples': 3964928, 'steps': 7743, 'loss/train': 0.9913235902786255}
-03/03/2022 22:33:29 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/03/2022 22:33:33 - INFO - codeparrot_training - Step 7744: {'lr': 0.0004981440037635266, 'samples': 3965440, 'steps': 7744, 'loss/train': 2.3759658336639404}
-03/03/2022 22:33:36 - INFO - codeparrot_training - Step 7745: {'lr': 0.0004981433582701781, 'samples': 3965952, 'steps': 7745, 'loss/train': 2.5732390880584717}
-03/03/2022 22:33:37 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/03/2022 22:33:41 - INFO - codeparrot_training - Step 7746: {'lr': 0.00049814271266502, 'samples': 3966464, 'steps': 7746, 'loss/train': 1.4498164653778076}
-03/03/2022 22:33:44 - INFO - codeparrot_training - Step 7747: {'lr': 0.0004981420669480526, 'samples': 3966976, 'steps': 7747, 'loss/train': 2.5896782875061035}
-03/03/2022 22:33:46 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/03/2022 22:33:49 - INFO - codeparrot_training - Step 7748: {'lr': 0.0004981414211192763, 'samples': 3967488, 'steps': 7748, 'loss/train': 2.3900582790374756}
-03/03/2022 22:33:53 - INFO - codeparrot_training - Step 7749: {'lr': 0.0004981407751786913, 'samples': 3968000, 'steps': 7749, 'loss/train': 2.6067817211151123}
-03/03/2022 22:33:54 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/03/2022 22:33:58 - INFO - codeparrot_training - Step 7750: {'lr': 0.0004981401291262979, 'samples': 3968512, 'steps': 7750, 'loss/train': 2.3859171867370605}
-03/03/2022 22:34:01 - INFO - codeparrot_training - Step 7751: {'lr': 0.0004981394829620963, 'samples': 3969024, 'steps': 7751, 'loss/train': 0.31109851598739624}
-03/03/2022 22:34:02 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/03/2022 22:34:06 - INFO - codeparrot_training - Step 7752: {'lr': 0.0004981388366860869, 'samples': 3969536, 'steps': 7752, 'loss/train': 0.735283374786377}
-03/03/2022 22:34:09 - INFO - codeparrot_training - Step 7753: {'lr': 0.0004981381902982702, 'samples': 3970048, 'steps': 7753, 'loss/train': 2.0195083618164062}
-03/03/2022 22:34:11 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/03/2022 22:34:15 - INFO - codeparrot_training - Step 7754: {'lr': 0.0004981375437986459, 'samples': 3970560, 'steps': 7754, 'loss/train': 2.0483181476593018}
-03/03/2022 22:34:18 - INFO - codeparrot_training - Step 7755: {'lr': 0.0004981368971872149, 'samples': 3971072, 'steps': 7755, 'loss/train': 1.9750837087631226}
-03/03/2022 22:34:20 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/03/2022 22:34:23 - INFO - codeparrot_training - Step 7756: {'lr': 0.0004981362504639772, 'samples': 3971584, 'steps': 7756, 'loss/train': 1.910295009613037}
-03/03/2022 22:34:26 - INFO - codeparrot_training - Step 7757: {'lr': 0.0004981356036289331, 'samples': 3972096, 'steps': 7757, 'loss/train': 1.2834193706512451}
-03/03/2022 22:34:28 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/03/2022 22:34:32 - INFO - codeparrot_training - Step 7758: {'lr': 0.0004981349566820828, 'samples': 3972608, 'steps': 7758, 'loss/train': 2.418184995651245}
-03/03/2022 22:34:35 - INFO - codeparrot_training - Step 7759: {'lr': 0.0004981343096234268, 'samples': 3973120, 'steps': 7759, 'loss/train': 2.8824234008789062}
-03/03/2022 22:34:36 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/03/2022 22:34:40 - INFO - codeparrot_training - Step 7760: {'lr': 0.0004981336624529654, 'samples': 3973632, 'steps': 7760, 'loss/train': 2.0623998641967773}
-03/03/2022 22:34:43 - INFO - codeparrot_training - Step 7761: {'lr': 0.0004981330151706988, 'samples': 3974144, 'steps': 7761, 'loss/train': 1.7933262586593628}
-03/03/2022 22:34:45 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/03/2022 22:34:49 - INFO - codeparrot_training - Step 7762: {'lr': 0.0004981323677766273, 'samples': 3974656, 'steps': 7762, 'loss/train': 0.6427942514419556}
-03/03/2022 22:34:52 - INFO - codeparrot_training - Step 7763: {'lr': 0.000498131720270751, 'samples': 3975168, 'steps': 7763, 'loss/train': 2.48492693901062}
-03/03/2022 22:34:53 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/03/2022 22:34:57 - INFO - codeparrot_training - Step 7764: {'lr': 0.0004981310726530706, 'samples': 3975680, 'steps': 7764, 'loss/train': 1.8147282600402832}
-03/03/2022 22:35:00 - INFO - codeparrot_training - Step 7765: {'lr': 0.0004981304249235861, 'samples': 3976192, 'steps': 7765, 'loss/train': 1.105262279510498}
-03/03/2022 22:35:02 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/03/2022 22:35:05 - INFO - codeparrot_training - Step 7766: {'lr': 0.0004981297770822977, 'samples': 3976704, 'steps': 7766, 'loss/train': 2.364194631576538}
-03/03/2022 22:35:09 - INFO - codeparrot_training - Step 7767: {'lr': 0.0004981291291292061, 'samples': 3977216, 'steps': 7767, 'loss/train': 2.413670063018799}
-03/03/2022 22:35:10 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/03/2022 22:35:14 - INFO - codeparrot_training - Step 7768: {'lr': 0.0004981284810643112, 'samples': 3977728, 'steps': 7768, 'loss/train': 2.022392988204956}
-03/03/2022 22:35:17 - INFO - codeparrot_training - Step 7769: {'lr': 0.0004981278328876134, 'samples': 3978240, 'steps': 7769, 'loss/train': 1.2894985675811768}
-03/03/2022 22:35:18 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/03/2022 22:35:22 - INFO - codeparrot_training - Step 7770: {'lr': 0.0004981271845991131, 'samples': 3978752, 'steps': 7770, 'loss/train': 1.7252044677734375}
-03/03/2022 22:35:25 - INFO - codeparrot_training - Step 7771: {'lr': 0.0004981265361988105, 'samples': 3979264, 'steps': 7771, 'loss/train': 1.554517149925232}
-03/03/2022 22:35:27 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/03/2022 22:35:31 - INFO - codeparrot_training - Step 7772: {'lr': 0.000498125887686706, 'samples': 3979776, 'steps': 7772, 'loss/train': 2.1656408309936523}
-03/03/2022 22:35:34 - INFO - codeparrot_training - Step 7773: {'lr': 0.0004981252390627997, 'samples': 3980288, 'steps': 7773, 'loss/train': 2.4124021530151367}
-03/03/2022 22:35:35 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/03/2022 22:35:39 - INFO - codeparrot_training - Step 7774: {'lr': 0.000498124590327092, 'samples': 3980800, 'steps': 7774, 'loss/train': 2.4785802364349365}
-03/03/2022 22:35:42 - INFO - codeparrot_training - Step 7775: {'lr': 0.0004981239414795832, 'samples': 3981312, 'steps': 7775, 'loss/train': 2.763418674468994}
-03/03/2022 22:35:44 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/03/2022 22:35:47 - INFO - codeparrot_training - Step 7776: {'lr': 0.0004981232925202736, 'samples': 3981824, 'steps': 7776, 'loss/train': 1.3017243146896362}
-03/03/2022 22:35:51 - INFO - codeparrot_training - Step 7777: {'lr': 0.0004981226434491635, 'samples': 3982336, 'steps': 7777, 'loss/train': 2.195108413696289}
-03/03/2022 22:35:52 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/03/2022 22:35:56 - INFO - codeparrot_training - Step 7778: {'lr': 0.000498121994266253, 'samples': 3982848, 'steps': 7778, 'loss/train': 2.06007719039917}
-03/03/2022 22:35:59 - INFO - codeparrot_training - Step 7779: {'lr': 0.0004981213449715427, 'samples': 3983360, 'steps': 7779, 'loss/train': 0.395641952753067}
-03/03/2022 22:36:00 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/03/2022 22:36:04 - INFO - codeparrot_training - Step 7780: {'lr': 0.0004981206955650328, 'samples': 3983872, 'steps': 7780, 'loss/train': 2.358372688293457}
-03/03/2022 22:36:07 - INFO - codeparrot_training - Step 7781: {'lr': 0.0004981200460467234, 'samples': 3984384, 'steps': 7781, 'loss/train': 1.962768316268921}
-03/03/2022 22:36:09 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/03/2022 22:36:13 - INFO - codeparrot_training - Step 7782: {'lr': 0.0004981193964166151, 'samples': 3984896, 'steps': 7782, 'loss/train': 2.0002570152282715}
-03/03/2022 22:36:16 - INFO - codeparrot_training - Step 7783: {'lr': 0.0004981187466747079, 'samples': 3985408, 'steps': 7783, 'loss/train': 1.0280886888504028}
-03/03/2022 22:36:17 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/03/2022 22:36:21 - INFO - codeparrot_training - Step 7784: {'lr': 0.0004981180968210023, 'samples': 3985920, 'steps': 7784, 'loss/train': 2.192945718765259}
-03/03/2022 22:36:24 - INFO - codeparrot_training - Step 7785: {'lr': 0.0004981174468554984, 'samples': 3986432, 'steps': 7785, 'loss/train': 2.280186414718628}
-03/03/2022 22:36:25 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/03/2022 22:36:29 - INFO - codeparrot_training - Step 7786: {'lr': 0.0004981167967781968, 'samples': 3986944, 'steps': 7786, 'loss/train': 1.9852923154830933}
-03/03/2022 22:36:33 - INFO - codeparrot_training - Step 7787: {'lr': 0.0004981161465890975, 'samples': 3987456, 'steps': 7787, 'loss/train': 2.1647822856903076}
-03/03/2022 22:36:34 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/03/2022 22:36:38 - INFO - codeparrot_training - Step 7788: {'lr': 0.0004981154962882008, 'samples': 3987968, 'steps': 7788, 'loss/train': 2.1083121299743652}
-03/03/2022 22:36:41 - INFO - codeparrot_training - Step 7789: {'lr': 0.0004981148458755071, 'samples': 3988480, 'steps': 7789, 'loss/train': 1.6614187955856323}
-03/03/2022 22:36:42 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/03/2022 22:36:46 - INFO - codeparrot_training - Step 7790: {'lr': 0.0004981141953510169, 'samples': 3988992, 'steps': 7790, 'loss/train': 2.522430181503296}
-03/03/2022 22:36:50 - INFO - codeparrot_training - Step 7791: {'lr': 0.00049811354471473, 'samples': 3989504, 'steps': 7791, 'loss/train': 2.7258951663970947}
-03/03/2022 22:36:50 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/03/2022 22:36:55 - INFO - codeparrot_training - Step 7792: {'lr': 0.0004981128939666471, 'samples': 3990016, 'steps': 7792, 'loss/train': 1.6624678373336792}
-03/03/2022 22:36:59 - INFO - codeparrot_training - Step 7793: {'lr': 0.0004981122431067683, 'samples': 3990528, 'steps': 7793, 'loss/train': 6.616742134094238}
-03/03/2022 22:37:02 - INFO - codeparrot_training - Step 7794: {'lr': 0.0004981115921350941, 'samples': 3991040, 'steps': 7794, 'loss/train': 6.778143405914307}
-03/03/2022 22:37:02 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/03/2022 22:37:07 - INFO - codeparrot_training - Step 7795: {'lr': 0.0004981109410516245, 'samples': 3991552, 'steps': 7795, 'loss/train': 2.2218127250671387}
-03/03/2022 22:37:10 - INFO - codeparrot_training - Step 7796: {'lr': 0.00049811028985636, 'samples': 3992064, 'steps': 7796, 'loss/train': 2.727476119995117}
-03/03/2022 22:37:11 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/03/2022 22:37:15 - INFO - codeparrot_training - Step 7797: {'lr': 0.0004981096385493007, 'samples': 3992576, 'steps': 7797, 'loss/train': 1.1949512958526611}
-03/03/2022 22:37:19 - INFO - codeparrot_training - Step 7798: {'lr': 0.0004981089871304472, 'samples': 3993088, 'steps': 7798, 'loss/train': 1.3587391376495361}
-03/03/2022 22:37:19 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/03/2022 22:37:24 - INFO - codeparrot_training - Step 7799: {'lr': 0.0004981083355997995, 'samples': 3993600, 'steps': 7799, 'loss/train': 2.0859458446502686}
-03/03/2022 22:37:27 - INFO - codeparrot_training - Step 7800: {'lr': 0.0004981076839573581, 'samples': 3994112, 'steps': 7800, 'loss/train': 2.7274415493011475}
-03/03/2022 22:37:27 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/03/2022 22:37:32 - INFO - codeparrot_training - Step 7801: {'lr': 0.0004981070322031231, 'samples': 3994624, 'steps': 7801, 'loss/train': 2.922389030456543}
-03/03/2022 22:37:35 - INFO - codeparrot_training - Step 7802: {'lr': 0.000498106380337095, 'samples': 3995136, 'steps': 7802, 'loss/train': 2.3124821186065674}
-03/03/2022 22:37:35 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/03/2022 22:37:41 - INFO - codeparrot_training - Step 7803: {'lr': 0.000498105728359274, 'samples': 3995648, 'steps': 7803, 'loss/train': 1.909959077835083}
-03/03/2022 22:37:44 - INFO - codeparrot_training - Step 7804: {'lr': 0.0004981050762696604, 'samples': 3996160, 'steps': 7804, 'loss/train': 2.2218737602233887}
-03/03/2022 22:37:44 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/03/2022 22:37:49 - INFO - codeparrot_training - Step 7805: {'lr': 0.0004981044240682544, 'samples': 3996672, 'steps': 7805, 'loss/train': 2.033613681793213}
-03/03/2022 22:37:53 - INFO - codeparrot_training - Step 7806: {'lr': 0.0004981037717550564, 'samples': 3997184, 'steps': 7806, 'loss/train': 1.922459602355957}
-03/03/2022 22:37:53 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/03/2022 22:37:58 - INFO - codeparrot_training - Step 7807: {'lr': 0.0004981031193300667, 'samples': 3997696, 'steps': 7807, 'loss/train': 2.040133237838745}
-03/03/2022 22:38:01 - INFO - codeparrot_training - Step 7808: {'lr': 0.0004981024667932855, 'samples': 3998208, 'steps': 7808, 'loss/train': 1.5629459619522095}
-03/03/2022 22:38:01 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/03/2022 22:38:07 - INFO - codeparrot_training - Step 7809: {'lr': 0.0004981018141447133, 'samples': 3998720, 'steps': 7809, 'loss/train': 2.27059268951416}
-03/03/2022 22:38:10 - INFO - codeparrot_training - Step 7810: {'lr': 0.00049810116138435, 'samples': 3999232, 'steps': 7810, 'loss/train': 1.4644389152526855}
-03/03/2022 22:38:10 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/03/2022 22:38:15 - INFO - codeparrot_training - Step 7811: {'lr': 0.0004981005085121963, 'samples': 3999744, 'steps': 7811, 'loss/train': 1.8287733793258667}
-03/03/2022 22:38:18 - INFO - codeparrot_training - Step 7812: {'lr': 0.0004980998555282524, 'samples': 4000256, 'steps': 7812, 'loss/train': 2.0887911319732666}
-03/03/2022 22:38:19 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/03/2022 22:38:23 - INFO - codeparrot_training - Step 7813: {'lr': 0.0004980992024325185, 'samples': 4000768, 'steps': 7813, 'loss/train': 2.7556748390197754}
-03/03/2022 22:38:27 - INFO - codeparrot_training - Step 7814: {'lr': 0.0004980985492249949, 'samples': 4001280, 'steps': 7814, 'loss/train': 2.1264169216156006}
-03/03/2022 22:38:27 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/03/2022 22:38:32 - INFO - codeparrot_training - Step 7815: {'lr': 0.0004980978959056819, 'samples': 4001792, 'steps': 7815, 'loss/train': 2.3098292350769043}
-03/03/2022 22:38:35 - INFO - codeparrot_training - Step 7816: {'lr': 0.0004980972424745798, 'samples': 4002304, 'steps': 7816, 'loss/train': 2.537721633911133}
-03/03/2022 22:38:35 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/03/2022 22:38:40 - INFO - codeparrot_training - Step 7817: {'lr': 0.000498096588931689, 'samples': 4002816, 'steps': 7817, 'loss/train': 0.2760595977306366}
-03/03/2022 22:38:44 - INFO - codeparrot_training - Step 7818: {'lr': 0.0004980959352770095, 'samples': 4003328, 'steps': 7818, 'loss/train': 2.940796375274658}
-03/03/2022 22:38:44 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/03/2022 22:38:49 - INFO - codeparrot_training - Step 7819: {'lr': 0.000498095281510542, 'samples': 4003840, 'steps': 7819, 'loss/train': 1.662781834602356}
-03/03/2022 22:38:52 - INFO - codeparrot_training - Step 7820: {'lr': 0.0004980946276322866, 'samples': 4004352, 'steps': 7820, 'loss/train': 1.8951302766799927}
-03/03/2022 22:38:52 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/03/2022 22:38:57 - INFO - codeparrot_training - Step 7821: {'lr': 0.0004980939736422436, 'samples': 4004864, 'steps': 7821, 'loss/train': 2.0265986919403076}
-03/03/2022 22:39:01 - INFO - codeparrot_training - Step 7822: {'lr': 0.0004980933195404131, 'samples': 4005376, 'steps': 7822, 'loss/train': 1.478345513343811}
-03/03/2022 22:39:01 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/03/2022 22:39:06 - INFO - codeparrot_training - Step 7823: {'lr': 0.0004980926653267957, 'samples': 4005888, 'steps': 7823, 'loss/train': 2.161310911178589}
-03/03/2022 22:39:09 - INFO - codeparrot_training - Step 7824: {'lr': 0.0004980920110013915, 'samples': 4006400, 'steps': 7824, 'loss/train': 1.9173293113708496}
-03/03/2022 22:39:09 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/03/2022 22:39:15 - INFO - codeparrot_training - Step 7825: {'lr': 0.000498091356564201, 'samples': 4006912, 'steps': 7825, 'loss/train': 0.9024561047554016}
-03/03/2022 22:39:18 - INFO - codeparrot_training - Step 7826: {'lr': 0.0004980907020152242, 'samples': 4007424, 'steps': 7826, 'loss/train': 0.43131986260414124}
-03/03/2022 22:39:18 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/03/2022 22:39:23 - INFO - codeparrot_training - Step 7827: {'lr': 0.0004980900473544617, 'samples': 4007936, 'steps': 7827, 'loss/train': 2.0252933502197266}
-03/03/2022 22:39:26 - INFO - codeparrot_training - Step 7828: {'lr': 0.0004980893925819137, 'samples': 4008448, 'steps': 7828, 'loss/train': 2.359254837036133}
-03/03/2022 22:39:27 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/03/2022 22:39:31 - INFO - codeparrot_training - Step 7829: {'lr': 0.0004980887376975804, 'samples': 4008960, 'steps': 7829, 'loss/train': 1.8614397048950195}
-03/03/2022 22:39:34 - INFO - codeparrot_training - Step 7830: {'lr': 0.000498088082701462, 'samples': 4009472, 'steps': 7830, 'loss/train': 1.629737377166748}
-03/03/2022 22:39:35 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/03/2022 22:39:40 - INFO - codeparrot_training - Step 7831: {'lr': 0.0004980874275935591, 'samples': 4009984, 'steps': 7831, 'loss/train': 1.5358115434646606}
-03/03/2022 22:39:43 - INFO - codeparrot_training - Step 7832: {'lr': 0.0004980867723738717, 'samples': 4010496, 'steps': 7832, 'loss/train': 2.641648292541504}
-03/03/2022 22:39:43 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/03/2022 22:39:48 - INFO - codeparrot_training - Step 7833: {'lr': 0.0004980861170424003, 'samples': 4011008, 'steps': 7833, 'loss/train': 2.714769124984741}
-03/03/2022 22:39:51 - INFO - codeparrot_training - Step 7834: {'lr': 0.0004980854615991452, 'samples': 4011520, 'steps': 7834, 'loss/train': 1.9993295669555664}
-03/03/2022 22:39:52 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/03/2022 22:39:57 - INFO - codeparrot_training - Step 7835: {'lr': 0.0004980848060441064, 'samples': 4012032, 'steps': 7835, 'loss/train': 2.858363389968872}
-03/03/2022 22:40:00 - INFO - codeparrot_training - Step 7836: {'lr': 0.0004980841503772846, 'samples': 4012544, 'steps': 7836, 'loss/train': 1.4894678592681885}
-03/03/2022 22:40:00 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/03/2022 22:40:05 - INFO - codeparrot_training - Step 7837: {'lr': 0.0004980834945986799, 'samples': 4013056, 'steps': 7837, 'loss/train': 1.9590983390808105}
-03/03/2022 22:40:08 - INFO - codeparrot_training - Step 7838: {'lr': 0.0004980828387082925, 'samples': 4013568, 'steps': 7838, 'loss/train': 2.4944980144500732}
-03/03/2022 22:40:08 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/03/2022 22:40:13 - INFO - codeparrot_training - Step 7839: {'lr': 0.000498082182706123, 'samples': 4014080, 'steps': 7839, 'loss/train': 1.920353651046753}
-03/03/2022 22:40:17 - INFO - codeparrot_training - Step 7840: {'lr': 0.0004980815265921713, 'samples': 4014592, 'steps': 7840, 'loss/train': 2.7325563430786133}
-03/03/2022 22:40:17 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/03/2022 22:40:22 - INFO - codeparrot_training - Step 7841: {'lr': 0.000498080870366438, 'samples': 4015104, 'steps': 7841, 'loss/train': 1.436686635017395}
-03/03/2022 22:40:25 - INFO - codeparrot_training - Step 7842: {'lr': 0.0004980802140289232, 'samples': 4015616, 'steps': 7842, 'loss/train': 1.936387538909912}
-03/03/2022 22:40:25 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/03/2022 22:40:30 - INFO - codeparrot_training - Step 7843: {'lr': 0.0004980795575796273, 'samples': 4016128, 'steps': 7843, 'loss/train': 3.390139102935791}
-03/03/2022 22:40:33 - INFO - codeparrot_training - Step 7844: {'lr': 0.0004980789010185507, 'samples': 4016640, 'steps': 7844, 'loss/train': 2.170727014541626}
-03/03/2022 22:40:34 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/03/2022 22:40:39 - INFO - codeparrot_training - Step 7845: {'lr': 0.0004980782443456935, 'samples': 4017152, 'steps': 7845, 'loss/train': 2.125541925430298}
-03/03/2022 22:40:42 - INFO - codeparrot_training - Step 7846: {'lr': 0.000498077587561056, 'samples': 4017664, 'steps': 7846, 'loss/train': 1.7234255075454712}
-03/03/2022 22:40:42 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/03/2022 22:40:47 - INFO - codeparrot_training - Step 7847: {'lr': 0.0004980769306646386, 'samples': 4018176, 'steps': 7847, 'loss/train': 1.7404478788375854}
-03/03/2022 22:40:50 - INFO - codeparrot_training - Step 7848: {'lr': 0.0004980762736564417, 'samples': 4018688, 'steps': 7848, 'loss/train': 2.2275173664093018}
-03/03/2022 22:40:52 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/03/2022 22:40:56 - INFO - codeparrot_training - Step 7849: {'lr': 0.0004980756165364653, 'samples': 4019200, 'steps': 7849, 'loss/train': 2.459423065185547}
-03/03/2022 22:40:59 - INFO - codeparrot_training - Step 7850: {'lr': 0.0004980749593047099, 'samples': 4019712, 'steps': 7850, 'loss/train': 0.6653178930282593}
-03/03/2022 22:41:00 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/03/2022 22:41:04 - INFO - codeparrot_training - Step 7851: {'lr': 0.0004980743019611757, 'samples': 4020224, 'steps': 7851, 'loss/train': 1.5660041570663452}
-03/03/2022 22:41:07 - INFO - codeparrot_training - Step 7852: {'lr': 0.0004980736445058631, 'samples': 4020736, 'steps': 7852, 'loss/train': 2.4269285202026367}
-03/03/2022 22:41:09 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/03/2022 22:41:13 - INFO - codeparrot_training - Step 7853: {'lr': 0.0004980729869387724, 'samples': 4021248, 'steps': 7853, 'loss/train': 2.524017333984375}
-03/03/2022 22:41:16 - INFO - codeparrot_training - Step 7854: {'lr': 0.0004980723292599037, 'samples': 4021760, 'steps': 7854, 'loss/train': 1.815609335899353}
-03/03/2022 22:41:18 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/03/2022 22:41:21 - INFO - codeparrot_training - Step 7855: {'lr': 0.0004980716714692576, 'samples': 4022272, 'steps': 7855, 'loss/train': 2.0021913051605225}
-03/03/2022 22:41:24 - INFO - codeparrot_training - Step 7856: {'lr': 0.0004980710135668342, 'samples': 4022784, 'steps': 7856, 'loss/train': 0.3109484314918518}
-03/03/2022 22:41:26 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/03/2022 22:41:29 - INFO - codeparrot_training - Step 7857: {'lr': 0.0004980703555526338, 'samples': 4023296, 'steps': 7857, 'loss/train': 1.844609022140503}
-03/03/2022 22:41:33 - INFO - codeparrot_training - Step 7858: {'lr': 0.0004980696974266566, 'samples': 4023808, 'steps': 7858, 'loss/train': 2.3330838680267334}
-03/03/2022 22:41:34 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/03/2022 22:41:38 - INFO - codeparrot_training - Step 7859: {'lr': 0.0004980690391889033, 'samples': 4024320, 'steps': 7859, 'loss/train': 2.8672077655792236}
-03/03/2022 22:41:41 - INFO - codeparrot_training - Step 7860: {'lr': 0.0004980683808393737, 'samples': 4024832, 'steps': 7860, 'loss/train': 2.1966168880462646}
-03/03/2022 22:41:43 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/03/2022 22:41:46 - INFO - codeparrot_training - Step 7861: {'lr': 0.0004980677223780683, 'samples': 4025344, 'steps': 7861, 'loss/train': 1.7677654027938843}
-03/03/2022 22:41:50 - INFO - codeparrot_training - Step 7862: {'lr': 0.0004980670638049875, 'samples': 4025856, 'steps': 7862, 'loss/train': 2.3129703998565674}
-03/03/2022 22:41:51 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/03/2022 22:41:55 - INFO - codeparrot_training - Step 7863: {'lr': 0.0004980664051201315, 'samples': 4026368, 'steps': 7863, 'loss/train': 2.4807751178741455}
-03/03/2022 22:41:58 - INFO - codeparrot_training - Step 7864: {'lr': 0.0004980657463235006, 'samples': 4026880, 'steps': 7864, 'loss/train': 2.3751587867736816}
-03/03/2022 22:41:59 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/03/2022 22:42:03 - INFO - codeparrot_training - Step 7865: {'lr': 0.0004980650874150951, 'samples': 4027392, 'steps': 7865, 'loss/train': 1.8108818531036377}
-03/03/2022 22:42:06 - INFO - codeparrot_training - Step 7866: {'lr': 0.0004980644283949152, 'samples': 4027904, 'steps': 7866, 'loss/train': 1.941157341003418}
-03/03/2022 22:42:08 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/03/2022 22:42:12 - INFO - codeparrot_training - Step 7867: {'lr': 0.0004980637692629615, 'samples': 4028416, 'steps': 7867, 'loss/train': 0.9785838723182678}
-03/03/2022 22:42:15 - INFO - codeparrot_training - Step 7868: {'lr': 0.0004980631100192339, 'samples': 4028928, 'steps': 7868, 'loss/train': 3.0194318294525146}
-03/03/2022 22:42:17 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/03/2022 22:42:20 - INFO - codeparrot_training - Step 7869: {'lr': 0.000498062450663733, 'samples': 4029440, 'steps': 7869, 'loss/train': 2.006136894226074}
-03/03/2022 22:42:23 - INFO - codeparrot_training - Step 7870: {'lr': 0.000498061791196459, 'samples': 4029952, 'steps': 7870, 'loss/train': 2.19747257232666}
-03/03/2022 22:42:26 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/03/2022 22:42:29 - INFO - codeparrot_training - Step 7871: {'lr': 0.0004980611316174122, 'samples': 4030464, 'steps': 7871, 'loss/train': 1.1705409288406372}
-03/03/2022 22:42:32 - INFO - codeparrot_training - Step 7872: {'lr': 0.0004980604719265928, 'samples': 4030976, 'steps': 7872, 'loss/train': 2.6730358600616455}
-03/03/2022 22:42:34 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/03/2022 22:42:37 - INFO - codeparrot_training - Step 7873: {'lr': 0.0004980598121240012, 'samples': 4031488, 'steps': 7873, 'loss/train': 1.9113178253173828}
-03/03/2022 22:42:40 - INFO - codeparrot_training - Step 7874: {'lr': 0.0004980591522096377, 'samples': 4032000, 'steps': 7874, 'loss/train': 0.8522165417671204}
-03/03/2022 22:42:42 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/03/2022 22:42:46 - INFO - codeparrot_training - Step 7875: {'lr': 0.0004980584921835025, 'samples': 4032512, 'steps': 7875, 'loss/train': 1.798514485359192}
-03/03/2022 22:42:49 - INFO - codeparrot_training - Step 7876: {'lr': 0.000498057832045596, 'samples': 4033024, 'steps': 7876, 'loss/train': 2.237656831741333}
-03/03/2022 22:42:51 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/03/2022 22:42:54 - INFO - codeparrot_training - Step 7877: {'lr': 0.0004980571717959186, 'samples': 4033536, 'steps': 7877, 'loss/train': 1.7910765409469604}
-03/03/2022 22:42:57 - INFO - codeparrot_training - Step 7878: {'lr': 0.0004980565114344704, 'samples': 4034048, 'steps': 7878, 'loss/train': 2.180840492248535}
-03/03/2022 22:43:00 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/03/2022 22:43:02 - INFO - codeparrot_training - Step 7879: {'lr': 0.0004980558509612516, 'samples': 4034560, 'steps': 7879, 'loss/train': 2.140592336654663}
-03/03/2022 22:43:06 - INFO - codeparrot_training - Step 7880: {'lr': 0.0004980551903762629, 'samples': 4035072, 'steps': 7880, 'loss/train': 2.3882291316986084}
-03/03/2022 22:43:08 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/03/2022 22:43:11 - INFO - codeparrot_training - Step 7881: {'lr': 0.0004980545296795043, 'samples': 4035584, 'steps': 7881, 'loss/train': 0.7737988233566284}
-03/03/2022 22:43:14 - INFO - codeparrot_training - Step 7882: {'lr': 0.0004980538688709761, 'samples': 4036096, 'steps': 7882, 'loss/train': 2.951653003692627}
-03/03/2022 22:43:16 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/03/2022 22:43:19 - INFO - codeparrot_training - Step 7883: {'lr': 0.0004980532079506786, 'samples': 4036608, 'steps': 7883, 'loss/train': 1.809651255607605}
-03/03/2022 22:43:23 - INFO - codeparrot_training - Step 7884: {'lr': 0.0004980525469186122, 'samples': 4037120, 'steps': 7884, 'loss/train': 2.5668089389801025}
-03/03/2022 22:43:25 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/03/2022 22:43:28 - INFO - codeparrot_training - Step 7885: {'lr': 0.0004980518857747772, 'samples': 4037632, 'steps': 7885, 'loss/train': 1.3657901287078857}
-03/03/2022 22:43:31 - INFO - codeparrot_training - Step 7886: {'lr': 0.0004980512245191738, 'samples': 4038144, 'steps': 7886, 'loss/train': 2.0322535037994385}
-03/03/2022 22:43:33 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/03/2022 22:43:36 - INFO - codeparrot_training - Step 7887: {'lr': 0.0004980505631518023, 'samples': 4038656, 'steps': 7887, 'loss/train': 2.0633511543273926}
-03/03/2022 22:43:39 - INFO - codeparrot_training - Step 7888: {'lr': 0.0004980499016726632, 'samples': 4039168, 'steps': 7888, 'loss/train': 1.983452558517456}
-03/03/2022 22:43:41 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/03/2022 22:43:45 - INFO - codeparrot_training - Step 7889: {'lr': 0.0004980492400817564, 'samples': 4039680, 'steps': 7889, 'loss/train': 2.514518976211548}
-03/03/2022 22:43:48 - INFO - codeparrot_training - Step 7890: {'lr': 0.0004980485783790827, 'samples': 4040192, 'steps': 7890, 'loss/train': 2.354811191558838}
-03/03/2022 22:43:50 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/03/2022 22:43:53 - INFO - codeparrot_training - Step 7891: {'lr': 0.0004980479165646419, 'samples': 4040704, 'steps': 7891, 'loss/train': 1.633600115776062}
-03/03/2022 22:43:56 - INFO - codeparrot_training - Step 7892: {'lr': 0.0004980472546384347, 'samples': 4041216, 'steps': 7892, 'loss/train': 1.7882723808288574}
-03/03/2022 22:43:58 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/03/2022 22:44:02 - INFO - codeparrot_training - Step 7893: {'lr': 0.0004980465926004613, 'samples': 4041728, 'steps': 7893, 'loss/train': 2.7215986251831055}
-03/03/2022 22:44:05 - INFO - codeparrot_training - Step 7894: {'lr': 0.0004980459304507218, 'samples': 4042240, 'steps': 7894, 'loss/train': 1.419953465461731}
-03/03/2022 22:44:06 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/03/2022 22:44:10 - INFO - codeparrot_training - Step 7895: {'lr': 0.0004980452681892166, 'samples': 4042752, 'steps': 7895, 'loss/train': 2.3586981296539307}
-03/03/2022 22:44:13 - INFO - codeparrot_training - Step 7896: {'lr': 0.0004980446058159461, 'samples': 4043264, 'steps': 7896, 'loss/train': 2.2252748012542725}
-03/03/2022 22:44:15 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 22:44:19 - INFO - codeparrot_training - Step 7897: {'lr': 0.0004980439433309106, 'samples': 4043776, 'steps': 7897, 'loss/train': 0.8914100527763367}
-03/03/2022 22:44:22 - INFO - codeparrot_training - Step 7898: {'lr': 0.0004980432807341102, 'samples': 4044288, 'steps': 7898, 'loss/train': 2.79447340965271}
-03/03/2022 22:44:23 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/03/2022 22:44:27 - INFO - codeparrot_training - Step 7899: {'lr': 0.0004980426180255453, 'samples': 4044800, 'steps': 7899, 'loss/train': 2.205747604370117}
-03/03/2022 22:44:30 - INFO - codeparrot_training - Step 7900: {'lr': 0.0004980419552052163, 'samples': 4045312, 'steps': 7900, 'loss/train': 1.4753681421279907}
-03/03/2022 22:44:31 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/03/2022 22:44:35 - INFO - codeparrot_training - Step 7901: {'lr': 0.0004980412922731234, 'samples': 4045824, 'steps': 7901, 'loss/train': 2.0411691665649414}
-03/03/2022 22:44:38 - INFO - codeparrot_training - Step 7902: {'lr': 0.0004980406292292669, 'samples': 4046336, 'steps': 7902, 'loss/train': 2.006497383117676}
-03/03/2022 22:44:39 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/03/2022 22:44:44 - INFO - codeparrot_training - Step 7903: {'lr': 0.0004980399660736472, 'samples': 4046848, 'steps': 7903, 'loss/train': 2.8913097381591797}
-03/03/2022 22:44:47 - INFO - codeparrot_training - Step 7904: {'lr': 0.0004980393028062646, 'samples': 4047360, 'steps': 7904, 'loss/train': 2.685441255569458}
-03/03/2022 22:44:52 - INFO - codeparrot_training - Step 7905: {'lr': 0.0004980386394271191, 'samples': 4047872, 'steps': 7905, 'loss/train': 1.541205883026123}
-03/03/2022 22:44:55 - INFO - codeparrot_training - Step 7906: {'lr': 0.0004980379759362113, 'samples': 4048384, 'steps': 7906, 'loss/train': 0.19294053316116333}
-03/03/2022 22:44:56 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/03/2022 22:45:01 - INFO - codeparrot_training - Step 7907: {'lr': 0.0004980373123335414, 'samples': 4048896, 'steps': 7907, 'loss/train': 2.5745086669921875}
-03/03/2022 22:45:05 - INFO - codeparrot_training - Step 7908: {'lr': 0.0004980366486191098, 'samples': 4049408, 'steps': 7908, 'loss/train': 1.5865901708602905}
-03/03/2022 22:45:08 - INFO - codeparrot_training - Step 7909: {'lr': 0.0004980359847929167, 'samples': 4049920, 'steps': 7909, 'loss/train': 1.74272882938385}
-03/03/2022 22:45:08 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/03/2022 22:45:13 - INFO - codeparrot_training - Step 7910: {'lr': 0.0004980353208549623, 'samples': 4050432, 'steps': 7910, 'loss/train': 2.951294183731079}
-03/03/2022 22:45:16 - INFO - codeparrot_training - Step 7911: {'lr': 0.0004980346568052471, 'samples': 4050944, 'steps': 7911, 'loss/train': 2.418741226196289}
-03/03/2022 22:45:16 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/03/2022 22:45:21 - INFO - codeparrot_training - Step 7912: {'lr': 0.0004980339926437713, 'samples': 4051456, 'steps': 7912, 'loss/train': 1.8984222412109375}
-03/03/2022 22:45:24 - INFO - codeparrot_training - Step 7913: {'lr': 0.0004980333283705351, 'samples': 4051968, 'steps': 7913, 'loss/train': 0.8675585389137268}
-03/03/2022 22:45:25 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/03/2022 22:45:30 - INFO - codeparrot_training - Step 7914: {'lr': 0.000498032663985539, 'samples': 4052480, 'steps': 7914, 'loss/train': 2.906721591949463}
-03/03/2022 22:45:33 - INFO - codeparrot_training - Step 7915: {'lr': 0.0004980319994887833, 'samples': 4052992, 'steps': 7915, 'loss/train': 2.209902286529541}
-03/03/2022 22:45:33 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/03/2022 22:45:38 - INFO - codeparrot_training - Step 7916: {'lr': 0.0004980313348802681, 'samples': 4053504, 'steps': 7916, 'loss/train': 1.9589853286743164}
-03/03/2022 22:45:41 - INFO - codeparrot_training - Step 7917: {'lr': 0.0004980306701599938, 'samples': 4054016, 'steps': 7917, 'loss/train': 2.4769604206085205}
-03/03/2022 22:45:42 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/03/2022 22:45:47 - INFO - codeparrot_training - Step 7918: {'lr': 0.0004980300053279607, 'samples': 4054528, 'steps': 7918, 'loss/train': 2.3516008853912354}
-03/03/2022 22:45:50 - INFO - codeparrot_training - Step 7919: {'lr': 0.0004980293403841693, 'samples': 4055040, 'steps': 7919, 'loss/train': 2.3929545879364014}
-03/03/2022 22:45:50 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/03/2022 22:45:55 - INFO - codeparrot_training - Step 7920: {'lr': 0.0004980286753286195, 'samples': 4055552, 'steps': 7920, 'loss/train': 2.2550625801086426}
-03/03/2022 22:45:58 - INFO - codeparrot_training - Step 7921: {'lr': 0.0004980280101613119, 'samples': 4056064, 'steps': 7921, 'loss/train': 1.675788164138794}
-03/03/2022 22:45:59 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/03/2022 22:46:04 - INFO - codeparrot_training - Step 7922: {'lr': 0.0004980273448822466, 'samples': 4056576, 'steps': 7922, 'loss/train': 2.257800817489624}
-03/03/2022 22:46:07 - INFO - codeparrot_training - Step 7923: {'lr': 0.000498026679491424, 'samples': 4057088, 'steps': 7923, 'loss/train': 2.074152708053589}
-03/03/2022 22:46:07 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/03/2022 22:46:12 - INFO - codeparrot_training - Step 7924: {'lr': 0.0004980260139888445, 'samples': 4057600, 'steps': 7924, 'loss/train': 1.7451777458190918}
-03/03/2022 22:46:15 - INFO - codeparrot_training - Step 7925: {'lr': 0.0004980253483745083, 'samples': 4058112, 'steps': 7925, 'loss/train': 2.585397720336914}
-03/03/2022 22:46:16 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/03/2022 22:46:20 - INFO - codeparrot_training - Step 7926: {'lr': 0.0004980246826484157, 'samples': 4058624, 'steps': 7926, 'loss/train': 2.226684331893921}
-03/03/2022 22:46:24 - INFO - codeparrot_training - Step 7927: {'lr': 0.000498024016810567, 'samples': 4059136, 'steps': 7927, 'loss/train': 2.359164237976074}
-03/03/2022 22:46:24 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/03/2022 22:46:29 - INFO - codeparrot_training - Step 7928: {'lr': 0.0004980233508609625, 'samples': 4059648, 'steps': 7928, 'loss/train': 1.8588862419128418}
-03/03/2022 22:46:32 - INFO - codeparrot_training - Step 7929: {'lr': 0.0004980226847996025, 'samples': 4060160, 'steps': 7929, 'loss/train': 2.6843645572662354}
-03/03/2022 22:46:33 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/03/2022 22:46:37 - INFO - codeparrot_training - Step 7930: {'lr': 0.0004980220186264874, 'samples': 4060672, 'steps': 7930, 'loss/train': 2.1167166233062744}
-03/03/2022 22:46:40 - INFO - codeparrot_training - Step 7931: {'lr': 0.0004980213523416172, 'samples': 4061184, 'steps': 7931, 'loss/train': 1.9698742628097534}
-03/03/2022 22:46:41 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/03/2022 22:46:46 - INFO - codeparrot_training - Step 7932: {'lr': 0.0004980206859449926, 'samples': 4061696, 'steps': 7932, 'loss/train': 2.330437660217285}
-03/03/2022 22:46:49 - INFO - codeparrot_training - Step 7933: {'lr': 0.0004980200194366136, 'samples': 4062208, 'steps': 7933, 'loss/train': 2.287994623184204}
-03/03/2022 22:46:49 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/03/2022 22:46:54 - INFO - codeparrot_training - Step 7934: {'lr': 0.0004980193528164806, 'samples': 4062720, 'steps': 7934, 'loss/train': 1.9035929441452026}
-03/03/2022 22:46:57 - INFO - codeparrot_training - Step 7935: {'lr': 0.0004980186860845939, 'samples': 4063232, 'steps': 7935, 'loss/train': 2.054844856262207}
-03/03/2022 22:46:58 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/03/2022 22:47:03 - INFO - codeparrot_training - Step 7936: {'lr': 0.0004980180192409539, 'samples': 4063744, 'steps': 7936, 'loss/train': 1.1750470399856567}
-03/03/2022 22:47:06 - INFO - codeparrot_training - Step 7937: {'lr': 0.0004980173522855608, 'samples': 4064256, 'steps': 7937, 'loss/train': 2.480867862701416}
-03/03/2022 22:47:07 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/03/2022 22:47:11 - INFO - codeparrot_training - Step 7938: {'lr': 0.0004980166852184148, 'samples': 4064768, 'steps': 7938, 'loss/train': 1.783907413482666}
-03/03/2022 22:47:14 - INFO - codeparrot_training - Step 7939: {'lr': 0.0004980160180395164, 'samples': 4065280, 'steps': 7939, 'loss/train': 2.3457419872283936}
-03/03/2022 22:47:15 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/03/2022 22:47:20 - INFO - codeparrot_training - Step 7940: {'lr': 0.0004980153507488657, 'samples': 4065792, 'steps': 7940, 'loss/train': 1.7605726718902588}
-03/03/2022 22:47:23 - INFO - codeparrot_training - Step 7941: {'lr': 0.0004980146833464633, 'samples': 4066304, 'steps': 7941, 'loss/train': 2.3586106300354004}
-03/03/2022 22:47:24 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/03/2022 22:47:28 - INFO - codeparrot_training - Step 7942: {'lr': 0.0004980140158323092, 'samples': 4066816, 'steps': 7942, 'loss/train': 2.0137739181518555}
-03/03/2022 22:47:31 - INFO - codeparrot_training - Step 7943: {'lr': 0.0004980133482064038, 'samples': 4067328, 'steps': 7943, 'loss/train': 3.067110776901245}
-03/03/2022 22:47:32 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/03/2022 22:47:36 - INFO - codeparrot_training - Step 7944: {'lr': 0.0004980126804687474, 'samples': 4067840, 'steps': 7944, 'loss/train': 2.058706283569336}
-03/03/2022 22:47:39 - INFO - codeparrot_training - Step 7945: {'lr': 0.0004980120126193403, 'samples': 4068352, 'steps': 7945, 'loss/train': 1.5643137693405151}
-03/03/2022 22:47:40 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/03/2022 22:47:45 - INFO - codeparrot_training - Step 7946: {'lr': 0.0004980113446581829, 'samples': 4068864, 'steps': 7946, 'loss/train': 2.922792434692383}
-03/03/2022 22:47:48 - INFO - codeparrot_training - Step 7947: {'lr': 0.0004980106765852753, 'samples': 4069376, 'steps': 7947, 'loss/train': 1.6312873363494873}
-03/03/2022 22:47:49 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/03/2022 22:47:53 - INFO - codeparrot_training - Step 7948: {'lr': 0.0004980100084006181, 'samples': 4069888, 'steps': 7948, 'loss/train': 2.73068904876709}
-03/03/2022 22:47:56 - INFO - codeparrot_training - Step 7949: {'lr': 0.0004980093401042113, 'samples': 4070400, 'steps': 7949, 'loss/train': 2.415375232696533}
-03/03/2022 22:47:57 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/03/2022 22:48:02 - INFO - codeparrot_training - Step 7950: {'lr': 0.0004980086716960552, 'samples': 4070912, 'steps': 7950, 'loss/train': 2.265270709991455}
-03/03/2022 22:48:05 - INFO - codeparrot_training - Step 7951: {'lr': 0.0004980080031761504, 'samples': 4071424, 'steps': 7951, 'loss/train': 2.527747631072998}
-03/03/2022 22:48:05 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/03/2022 22:48:10 - INFO - codeparrot_training - Step 7952: {'lr': 0.000498007334544497, 'samples': 4071936, 'steps': 7952, 'loss/train': 2.2149083614349365}
-03/03/2022 22:48:13 - INFO - codeparrot_training - Step 7953: {'lr': 0.0004980066658010952, 'samples': 4072448, 'steps': 7953, 'loss/train': 2.0914366245269775}
-03/03/2022 22:48:14 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/03/2022 22:48:18 - INFO - codeparrot_training - Step 7954: {'lr': 0.0004980059969459455, 'samples': 4072960, 'steps': 7954, 'loss/train': 3.1984305381774902}
-03/03/2022 22:48:21 - INFO - codeparrot_training - Step 7955: {'lr': 0.0004980053279790481, 'samples': 4073472, 'steps': 7955, 'loss/train': 1.4285567998886108}
-03/03/2022 22:48:22 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/03/2022 22:48:27 - INFO - codeparrot_training - Step 7956: {'lr': 0.0004980046589004034, 'samples': 4073984, 'steps': 7956, 'loss/train': 2.427269697189331}
-03/03/2022 22:48:30 - INFO - codeparrot_training - Step 7957: {'lr': 0.0004980039897100115, 'samples': 4074496, 'steps': 7957, 'loss/train': 2.4859092235565186}
-03/03/2022 22:48:30 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/03/2022 22:48:35 - INFO - codeparrot_training - Step 7958: {'lr': 0.000498003320407873, 'samples': 4075008, 'steps': 7958, 'loss/train': 0.7277880311012268}
-03/03/2022 22:48:38 - INFO - codeparrot_training - Step 7959: {'lr': 0.000498002650993988, 'samples': 4075520, 'steps': 7959, 'loss/train': 2.5554046630859375}
-03/03/2022 22:48:38 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/03/2022 22:48:43 - INFO - codeparrot_training - Step 7960: {'lr': 0.0004980019814683568, 'samples': 4076032, 'steps': 7960, 'loss/train': 1.456191062927246}
-03/03/2022 22:48:47 - INFO - codeparrot_training - Step 7961: {'lr': 0.0004980013118309796, 'samples': 4076544, 'steps': 7961, 'loss/train': 2.256951093673706}
-03/03/2022 22:48:47 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/03/2022 22:48:52 - INFO - codeparrot_training - Step 7962: {'lr': 0.000498000642081857, 'samples': 4077056, 'steps': 7962, 'loss/train': 1.2533564567565918}
-03/03/2022 22:48:55 - INFO - codeparrot_training - Step 7963: {'lr': 0.0004979999722209891, 'samples': 4077568, 'steps': 7963, 'loss/train': 2.5389294624328613}
-03/03/2022 22:48:55 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/03/2022 22:49:00 - INFO - codeparrot_training - Step 7964: {'lr': 0.0004979993022483762, 'samples': 4078080, 'steps': 7964, 'loss/train': 1.2795096635818481}
-03/03/2022 22:49:04 - INFO - codeparrot_training - Step 7965: {'lr': 0.0004979986321640187, 'samples': 4078592, 'steps': 7965, 'loss/train': 2.2165520191192627}
-03/03/2022 22:49:04 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/03/2022 22:49:09 - INFO - codeparrot_training - Step 7966: {'lr': 0.0004979979619679168, 'samples': 4079104, 'steps': 7966, 'loss/train': 1.2948708534240723}
-03/03/2022 22:49:12 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/03/2022 22:49:14 - INFO - codeparrot_training - Step 7967: {'lr': 0.0004979972916600708, 'samples': 4079616, 'steps': 7967, 'loss/train': 2.444138526916504}
-03/03/2022 22:49:17 - INFO - codeparrot_training - Step 7968: {'lr': 0.0004979966212404812, 'samples': 4080128, 'steps': 7968, 'loss/train': 0.9918586015701294}
-03/03/2022 22:49:20 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/03/2022 22:49:22 - INFO - codeparrot_training - Step 7969: {'lr': 0.0004979959507091479, 'samples': 4080640, 'steps': 7969, 'loss/train': 1.2283567190170288}
-03/03/2022 22:49:26 - INFO - codeparrot_training - Step 7970: {'lr': 0.0004979952800660717, 'samples': 4081152, 'steps': 7970, 'loss/train': 1.5238083600997925}
-03/03/2022 22:49:28 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/03/2022 22:49:31 - INFO - codeparrot_training - Step 7971: {'lr': 0.0004979946093112525, 'samples': 4081664, 'steps': 7971, 'loss/train': 1.590092420578003}
-03/03/2022 22:49:34 - INFO - codeparrot_training - Step 7972: {'lr': 0.0004979939384446908, 'samples': 4082176, 'steps': 7972, 'loss/train': 2.8864643573760986}
-03/03/2022 22:49:37 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/03/2022 22:49:39 - INFO - codeparrot_training - Step 7973: {'lr': 0.0004979932674663869, 'samples': 4082688, 'steps': 7973, 'loss/train': 0.38644498586654663}
-03/03/2022 22:49:42 - INFO - codeparrot_training - Step 7974: {'lr': 0.000497992596376341, 'samples': 4083200, 'steps': 7974, 'loss/train': 2.139150381088257}
-03/03/2022 22:49:45 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/03/2022 22:49:48 - INFO - codeparrot_training - Step 7975: {'lr': 0.0004979919251745535, 'samples': 4083712, 'steps': 7975, 'loss/train': 2.6292829513549805}
-03/03/2022 22:49:51 - INFO - codeparrot_training - Step 7976: {'lr': 0.0004979912538610247, 'samples': 4084224, 'steps': 7976, 'loss/train': 2.1279101371765137}
-03/03/2022 22:49:53 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/03/2022 22:49:56 - INFO - codeparrot_training - Step 7977: {'lr': 0.0004979905824357548, 'samples': 4084736, 'steps': 7977, 'loss/train': 2.0057599544525146}
-03/03/2022 22:49:59 - INFO - codeparrot_training - Step 7978: {'lr': 0.0004979899108987442, 'samples': 4085248, 'steps': 7978, 'loss/train': 2.5160720348358154}
-03/03/2022 22:50:02 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/03/2022 22:50:05 - INFO - codeparrot_training - Step 7979: {'lr': 0.0004979892392499932, 'samples': 4085760, 'steps': 7979, 'loss/train': 1.1950947046279907}
-03/03/2022 22:50:08 - INFO - codeparrot_training - Step 7980: {'lr': 0.0004979885674895021, 'samples': 4086272, 'steps': 7980, 'loss/train': 1.634260892868042}
-03/03/2022 22:50:10 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/03/2022 22:50:13 - INFO - codeparrot_training - Step 7981: {'lr': 0.0004979878956172711, 'samples': 4086784, 'steps': 7981, 'loss/train': 2.43411922454834}
-03/03/2022 22:50:16 - INFO - codeparrot_training - Step 7982: {'lr': 0.0004979872236333005, 'samples': 4087296, 'steps': 7982, 'loss/train': 1.8721474409103394}
-03/03/2022 22:50:19 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/03/2022 22:50:22 - INFO - codeparrot_training - Step 7983: {'lr': 0.0004979865515375908, 'samples': 4087808, 'steps': 7983, 'loss/train': 2.1979329586029053}
-03/03/2022 22:50:25 - INFO - codeparrot_training - Step 7984: {'lr': 0.0004979858793301422, 'samples': 4088320, 'steps': 7984, 'loss/train': 1.8868659734725952}
-03/03/2022 22:50:27 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/03/2022 22:50:30 - INFO - codeparrot_training - Step 7985: {'lr': 0.000497985207010955, 'samples': 4088832, 'steps': 7985, 'loss/train': 2.733327627182007}
-03/03/2022 22:50:33 - INFO - codeparrot_training - Step 7986: {'lr': 0.0004979845345800294, 'samples': 4089344, 'steps': 7986, 'loss/train': 2.5203638076782227}
-03/03/2022 22:50:36 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/03/2022 22:50:39 - INFO - codeparrot_training - Step 7987: {'lr': 0.0004979838620373659, 'samples': 4089856, 'steps': 7987, 'loss/train': 2.158017873764038}
-03/03/2022 22:50:42 - INFO - codeparrot_training - Step 7988: {'lr': 0.0004979831893829646, 'samples': 4090368, 'steps': 7988, 'loss/train': 0.8565701842308044}
-03/03/2022 22:50:44 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/03/2022 22:50:47 - INFO - codeparrot_training - Step 7989: {'lr': 0.0004979825166168259, 'samples': 4090880, 'steps': 7989, 'loss/train': 1.1284630298614502}
-03/03/2022 22:50:50 - INFO - codeparrot_training - Step 7990: {'lr': 0.0004979818437389502, 'samples': 4091392, 'steps': 7990, 'loss/train': 1.483588695526123}
-03/03/2022 22:50:52 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/03/2022 22:50:56 - INFO - codeparrot_training - Step 7991: {'lr': 0.0004979811707493377, 'samples': 4091904, 'steps': 7991, 'loss/train': 2.39544415473938}
-03/03/2022 22:50:59 - INFO - codeparrot_training - Step 7992: {'lr': 0.0004979804976479887, 'samples': 4092416, 'steps': 7992, 'loss/train': 2.687185049057007}
-03/03/2022 22:51:01 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/03/2022 22:51:04 - INFO - codeparrot_training - Step 7993: {'lr': 0.0004979798244349034, 'samples': 4092928, 'steps': 7993, 'loss/train': 1.8900809288024902}
-03/03/2022 22:51:07 - INFO - codeparrot_training - Step 7994: {'lr': 0.0004979791511100823, 'samples': 4093440, 'steps': 7994, 'loss/train': 2.3498384952545166}
-03/03/2022 22:51:09 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/03/2022 22:51:12 - INFO - codeparrot_training - Step 7995: {'lr': 0.0004979784776735257, 'samples': 4093952, 'steps': 7995, 'loss/train': 2.7974820137023926}
-03/03/2022 22:51:16 - INFO - codeparrot_training - Step 7996: {'lr': 0.0004979778041252338, 'samples': 4094464, 'steps': 7996, 'loss/train': 1.6391628980636597}
-03/03/2022 22:51:17 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/03/2022 22:51:21 - INFO - codeparrot_training - Step 7997: {'lr': 0.0004979771304652068, 'samples': 4094976, 'steps': 7997, 'loss/train': 4.133335590362549}
-03/03/2022 22:51:24 - INFO - codeparrot_training - Step 7998: {'lr': 0.0004979764566934452, 'samples': 4095488, 'steps': 7998, 'loss/train': 2.249850034713745}
-03/03/2022 22:51:26 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/03/2022 22:51:29 - INFO - codeparrot_training - Step 7999: {'lr': 0.0004979757828099492, 'samples': 4096000, 'steps': 7999, 'loss/train': 2.1044538021087646}
-03/03/2022 22:51:32 - INFO - codeparrot_training - Step 8000: {'lr': 0.0004979751088147192, 'samples': 4096512, 'steps': 8000, 'loss/train': 1.9982476234436035}
-03/03/2022 22:51:34 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/03/2022 22:51:38 - INFO - codeparrot_training - Step 8001: {'lr': 0.0004979744347077555, 'samples': 4097024, 'steps': 8001, 'loss/train': 2.4670486450195312}
-03/03/2022 22:51:41 - INFO - codeparrot_training - Step 8002: {'lr': 0.0004979737604890582, 'samples': 4097536, 'steps': 8002, 'loss/train': 2.2623140811920166}
-03/03/2022 22:51:42 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/03/2022 22:51:46 - INFO - codeparrot_training - Step 8003: {'lr': 0.0004979730861586278, 'samples': 4098048, 'steps': 8003, 'loss/train': 2.2917399406433105}
-03/03/2022 22:51:49 - INFO - codeparrot_training - Step 8004: {'lr': 0.0004979724117164646, 'samples': 4098560, 'steps': 8004, 'loss/train': 2.3379952907562256}
-03/03/2022 22:51:51 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/03/2022 22:51:54 - INFO - codeparrot_training - Step 8005: {'lr': 0.0004979717371625689, 'samples': 4099072, 'steps': 8005, 'loss/train': 1.7642571926116943}
-03/03/2022 22:51:58 - INFO - codeparrot_training - Step 8006: {'lr': 0.0004979710624969408, 'samples': 4099584, 'steps': 8006, 'loss/train': 1.901035189628601}
-03/03/2022 22:51:59 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/03/2022 22:52:03 - INFO - codeparrot_training - Step 8007: {'lr': 0.000497970387719581, 'samples': 4100096, 'steps': 8007, 'loss/train': 1.8496527671813965}
-03/03/2022 22:52:06 - INFO - codeparrot_training - Step 8008: {'lr': 0.0004979697128304893, 'samples': 4100608, 'steps': 8008, 'loss/train': 2.362468957901001}
-03/03/2022 22:52:07 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/03/2022 22:52:11 - INFO - codeparrot_training - Step 8009: {'lr': 0.0004979690378296665, 'samples': 4101120, 'steps': 8009, 'loss/train': 2.2264511585235596}
-03/03/2022 22:52:14 - INFO - codeparrot_training - Step 8010: {'lr': 0.0004979683627171125, 'samples': 4101632, 'steps': 8010, 'loss/train': 2.171347141265869}
-03/03/2022 22:52:16 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/03/2022 22:52:20 - INFO - codeparrot_training - Step 8011: {'lr': 0.0004979676874928278, 'samples': 4102144, 'steps': 8011, 'loss/train': 1.1991887092590332}
-03/03/2022 22:52:23 - INFO - codeparrot_training - Step 8012: {'lr': 0.0004979670121568129, 'samples': 4102656, 'steps': 8012, 'loss/train': 1.3763562440872192}
-03/03/2022 22:52:24 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/03/2022 22:52:28 - INFO - codeparrot_training - Step 8013: {'lr': 0.0004979663367090676, 'samples': 4103168, 'steps': 8013, 'loss/train': 2.9905943870544434}
-03/03/2022 22:52:32 - INFO - codeparrot_training - Step 8014: {'lr': 0.0004979656611495927, 'samples': 4103680, 'steps': 8014, 'loss/train': 1.688880205154419}
-03/03/2022 22:52:34 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/03/2022 22:52:37 - INFO - codeparrot_training - Step 8015: {'lr': 0.0004979649854783883, 'samples': 4104192, 'steps': 8015, 'loss/train': 2.47381329536438}
-03/03/2022 22:52:40 - INFO - codeparrot_training - Step 8016: {'lr': 0.0004979643096954545, 'samples': 4104704, 'steps': 8016, 'loss/train': 2.2354953289031982}
-03/03/2022 22:52:42 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/03/2022 22:52:45 - INFO - codeparrot_training - Step 8017: {'lr': 0.000497963633800792, 'samples': 4105216, 'steps': 8017, 'loss/train': 1.6777698993682861}
-03/03/2022 22:52:49 - INFO - codeparrot_training - Step 8018: {'lr': 0.0004979629577944009, 'samples': 4105728, 'steps': 8018, 'loss/train': 1.972312331199646}
-03/03/2022 22:52:50 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/03/2022 22:52:54 - INFO - codeparrot_training - Step 8019: {'lr': 0.0004979622816762815, 'samples': 4106240, 'steps': 8019, 'loss/train': 3.6460654735565186}
-03/03/2022 22:52:57 - INFO - codeparrot_training - Step 8020: {'lr': 0.0004979616054464341, 'samples': 4106752, 'steps': 8020, 'loss/train': 2.0080604553222656}
-03/03/2022 22:52:58 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/03/2022 22:53:02 - INFO - codeparrot_training - Step 8021: {'lr': 0.000497960929104859, 'samples': 4107264, 'steps': 8021, 'loss/train': 2.189729690551758}
-03/03/2022 22:53:05 - INFO - codeparrot_training - Step 8022: {'lr': 0.0004979602526515566, 'samples': 4107776, 'steps': 8022, 'loss/train': 2.664393186569214}
-03/03/2022 22:53:07 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/03/2022 22:53:10 - INFO - codeparrot_training - Step 8023: {'lr': 0.0004979595760865271, 'samples': 4108288, 'steps': 8023, 'loss/train': 1.624901294708252}
-03/03/2022 22:53:14 - INFO - codeparrot_training - Step 8024: {'lr': 0.0004979588994097708, 'samples': 4108800, 'steps': 8024, 'loss/train': 1.6296113729476929}
-03/03/2022 22:53:15 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/03/2022 22:53:19 - INFO - codeparrot_training - Step 8025: {'lr': 0.0004979582226212881, 'samples': 4109312, 'steps': 8025, 'loss/train': 0.7124961018562317}
-03/03/2022 22:53:22 - INFO - codeparrot_training - Step 8026: {'lr': 0.0004979575457210792, 'samples': 4109824, 'steps': 8026, 'loss/train': 1.988480806350708}
-03/03/2022 22:53:23 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/03/2022 22:53:27 - INFO - codeparrot_training - Step 8027: {'lr': 0.0004979568687091446, 'samples': 4110336, 'steps': 8027, 'loss/train': 1.9786367416381836}
-03/03/2022 22:53:31 - INFO - codeparrot_training - Step 8028: {'lr': 0.0004979561915854843, 'samples': 4110848, 'steps': 8028, 'loss/train': 2.5870184898376465}
-03/03/2022 22:53:32 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/03/2022 22:53:36 - INFO - codeparrot_training - Step 8029: {'lr': 0.0004979555143500988, 'samples': 4111360, 'steps': 8029, 'loss/train': 1.027693271636963}
-03/03/2022 22:53:39 - INFO - codeparrot_training - Step 8030: {'lr': 0.0004979548370029884, 'samples': 4111872, 'steps': 8030, 'loss/train': 3.8049376010894775}
-03/03/2022 22:53:41 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/03/2022 22:53:45 - INFO - codeparrot_training - Step 8031: {'lr': 0.0004979541595441534, 'samples': 4112384, 'steps': 8031, 'loss/train': 1.631392478942871}
-03/03/2022 22:53:48 - INFO - codeparrot_training - Step 8032: {'lr': 0.000497953481973594, 'samples': 4112896, 'steps': 8032, 'loss/train': 1.9221714735031128}
-03/03/2022 22:53:50 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 22:53:53 - INFO - codeparrot_training - Step 8033: {'lr': 0.0004979528042913106, 'samples': 4113408, 'steps': 8033, 'loss/train': 2.099982738494873}
-03/03/2022 22:53:56 - INFO - codeparrot_training - Step 8034: {'lr': 0.0004979521264973036, 'samples': 4113920, 'steps': 8034, 'loss/train': 4.7173237800598145}
-03/03/2022 22:53:59 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/03/2022 22:54:02 - INFO - codeparrot_training - Step 8035: {'lr': 0.0004979514485915731, 'samples': 4114432, 'steps': 8035, 'loss/train': 2.682152271270752}
-03/03/2022 22:54:05 - INFO - codeparrot_training - Step 8036: {'lr': 0.0004979507705741195, 'samples': 4114944, 'steps': 8036, 'loss/train': 1.8634788990020752}
-03/03/2022 22:54:08 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/03/2022 22:54:10 - INFO - codeparrot_training - Step 8037: {'lr': 0.0004979500924449431, 'samples': 4115456, 'steps': 8037, 'loss/train': 2.56097149848938}
-03/03/2022 22:54:13 - INFO - codeparrot_training - Step 8038: {'lr': 0.0004979494142040444, 'samples': 4115968, 'steps': 8038, 'loss/train': 2.3708510398864746}
-03/03/2022 22:54:16 - INFO - codeparrot_training - Step 8039: {'lr': 0.0004979487358514233, 'samples': 4116480, 'steps': 8039, 'loss/train': 2.235276222229004}
-03/03/2022 22:54:16 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/03/2022 22:54:22 - INFO - codeparrot_training - Step 8040: {'lr': 0.0004979480573870803, 'samples': 4116992, 'steps': 8040, 'loss/train': 2.7747910022735596}
-03/03/2022 22:54:25 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/03/2022 22:54:27 - INFO - codeparrot_training - Step 8041: {'lr': 0.000497947378811016, 'samples': 4117504, 'steps': 8041, 'loss/train': 2.152933359146118}
-03/03/2022 22:54:30 - INFO - codeparrot_training - Step 8042: {'lr': 0.0004979467001232302, 'samples': 4118016, 'steps': 8042, 'loss/train': 1.5761042833328247}
-03/03/2022 22:54:33 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/03/2022 22:54:35 - INFO - codeparrot_training - Step 8043: {'lr': 0.0004979460213237235, 'samples': 4118528, 'steps': 8043, 'loss/train': 2.585252046585083}
-03/03/2022 22:54:39 - INFO - codeparrot_training - Step 8044: {'lr': 0.0004979453424124961, 'samples': 4119040, 'steps': 8044, 'loss/train': 1.7613083124160767}
-03/03/2022 22:54:41 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/03/2022 22:54:44 - INFO - codeparrot_training - Step 8045: {'lr': 0.0004979446633895484, 'samples': 4119552, 'steps': 8045, 'loss/train': 2.5397720336914062}
-03/03/2022 22:54:47 - INFO - codeparrot_training - Step 8046: {'lr': 0.0004979439842548808, 'samples': 4120064, 'steps': 8046, 'loss/train': 1.4934889078140259}
-03/03/2022 22:54:50 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/03/2022 22:54:53 - INFO - codeparrot_training - Step 8047: {'lr': 0.0004979433050084933, 'samples': 4120576, 'steps': 8047, 'loss/train': 2.1392288208007812}
-03/03/2022 22:54:56 - INFO - codeparrot_training - Step 8048: {'lr': 0.0004979426256503863, 'samples': 4121088, 'steps': 8048, 'loss/train': 1.6545960903167725}
-03/03/2022 22:54:58 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/03/2022 22:55:01 - INFO - codeparrot_training - Step 8049: {'lr': 0.0004979419461805603, 'samples': 4121600, 'steps': 8049, 'loss/train': 2.4363317489624023}
-03/03/2022 22:55:04 - INFO - codeparrot_training - Step 8050: {'lr': 0.0004979412665990156, 'samples': 4122112, 'steps': 8050, 'loss/train': 2.743967056274414}
-03/03/2022 22:55:07 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/03/2022 22:55:09 - INFO - codeparrot_training - Step 8051: {'lr': 0.0004979405869057522, 'samples': 4122624, 'steps': 8051, 'loss/train': 2.1840758323669434}
-03/03/2022 22:55:13 - INFO - codeparrot_training - Step 8052: {'lr': 0.0004979399071007707, 'samples': 4123136, 'steps': 8052, 'loss/train': 2.7776780128479004}
-03/03/2022 22:55:15 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/03/2022 22:55:18 - INFO - codeparrot_training - Step 8053: {'lr': 0.0004979392271840712, 'samples': 4123648, 'steps': 8053, 'loss/train': 2.2273974418640137}
-03/03/2022 22:55:21 - INFO - codeparrot_training - Step 8054: {'lr': 0.0004979385471556542, 'samples': 4124160, 'steps': 8054, 'loss/train': 1.9799525737762451}
-03/03/2022 22:55:24 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/03/2022 22:55:26 - INFO - codeparrot_training - Step 8055: {'lr': 0.00049793786701552, 'samples': 4124672, 'steps': 8055, 'loss/train': 0.9017079472541809}
-03/03/2022 22:55:30 - INFO - codeparrot_training - Step 8056: {'lr': 0.0004979371867636687, 'samples': 4125184, 'steps': 8056, 'loss/train': 1.6523048877716064}
-03/03/2022 22:55:32 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/03/2022 22:55:35 - INFO - codeparrot_training - Step 8057: {'lr': 0.0004979365064001007, 'samples': 4125696, 'steps': 8057, 'loss/train': 2.246040105819702}
-03/03/2022 22:55:38 - INFO - codeparrot_training - Step 8058: {'lr': 0.0004979358259248164, 'samples': 4126208, 'steps': 8058, 'loss/train': 2.2230541706085205}
-03/03/2022 22:55:40 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/03/2022 22:55:43 - INFO - codeparrot_training - Step 8059: {'lr': 0.000497935145337816, 'samples': 4126720, 'steps': 8059, 'loss/train': 2.125211715698242}
-03/03/2022 22:55:47 - INFO - codeparrot_training - Step 8060: {'lr': 0.0004979344646390999, 'samples': 4127232, 'steps': 8060, 'loss/train': 2.478351593017578}
-03/03/2022 22:55:49 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/03/2022 22:55:52 - INFO - codeparrot_training - Step 8061: {'lr': 0.0004979337838286684, 'samples': 4127744, 'steps': 8061, 'loss/train': 2.106102466583252}
-03/03/2022 22:55:55 - INFO - codeparrot_training - Step 8062: {'lr': 0.0004979331029065216, 'samples': 4128256, 'steps': 8062, 'loss/train': 2.436164379119873}
-03/03/2022 22:55:57 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/03/2022 22:56:00 - INFO - codeparrot_training - Step 8063: {'lr': 0.00049793242187266, 'samples': 4128768, 'steps': 8063, 'loss/train': 2.7479686737060547}
-03/03/2022 22:56:03 - INFO - codeparrot_training - Step 8064: {'lr': 0.000497931740727084, 'samples': 4129280, 'steps': 8064, 'loss/train': 1.6955811977386475}
-03/03/2022 22:56:05 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/03/2022 22:56:09 - INFO - codeparrot_training - Step 8065: {'lr': 0.0004979310594697937, 'samples': 4129792, 'steps': 8065, 'loss/train': 1.2456464767456055}
-03/03/2022 22:56:12 - INFO - codeparrot_training - Step 8066: {'lr': 0.0004979303781007896, 'samples': 4130304, 'steps': 8066, 'loss/train': 1.9238649606704712}
-03/03/2022 22:56:13 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/03/2022 22:56:17 - INFO - codeparrot_training - Step 8067: {'lr': 0.0004979296966200718, 'samples': 4130816, 'steps': 8067, 'loss/train': 2.0303738117218018}
-03/03/2022 22:56:20 - INFO - codeparrot_training - Step 8068: {'lr': 0.0004979290150276407, 'samples': 4131328, 'steps': 8068, 'loss/train': 1.76505446434021}
-03/03/2022 22:56:22 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/03/2022 22:56:26 - INFO - codeparrot_training - Step 8069: {'lr': 0.0004979283333234966, 'samples': 4131840, 'steps': 8069, 'loss/train': 1.8597348928451538}
-03/03/2022 22:56:29 - INFO - codeparrot_training - Step 8070: {'lr': 0.0004979276515076399, 'samples': 4132352, 'steps': 8070, 'loss/train': 2.9375388622283936}
-03/03/2022 22:56:31 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/03/2022 22:56:34 - INFO - codeparrot_training - Step 8071: {'lr': 0.0004979269695800707, 'samples': 4132864, 'steps': 8071, 'loss/train': 2.0005099773406982}
-03/03/2022 22:56:37 - INFO - codeparrot_training - Step 8072: {'lr': 0.0004979262875407896, 'samples': 4133376, 'steps': 8072, 'loss/train': 2.8727641105651855}
-03/03/2022 22:56:39 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/03/2022 22:56:43 - INFO - codeparrot_training - Step 8073: {'lr': 0.0004979256053897966, 'samples': 4133888, 'steps': 8073, 'loss/train': 1.1399204730987549}
-03/03/2022 22:56:46 - INFO - codeparrot_training - Step 8074: {'lr': 0.0004979249231270923, 'samples': 4134400, 'steps': 8074, 'loss/train': 2.0332558155059814}
-03/03/2022 22:56:48 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/03/2022 22:56:51 - INFO - codeparrot_training - Step 8075: {'lr': 0.0004979242407526766, 'samples': 4134912, 'steps': 8075, 'loss/train': 2.5863115787506104}
-03/03/2022 22:56:54 - INFO - codeparrot_training - Step 8076: {'lr': 0.0004979235582665503, 'samples': 4135424, 'steps': 8076, 'loss/train': 2.8098056316375732}
-03/03/2022 22:56:56 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/03/2022 22:56:59 - INFO - codeparrot_training - Step 8077: {'lr': 0.0004979228756687135, 'samples': 4135936, 'steps': 8077, 'loss/train': 1.5659335851669312}
-03/03/2022 22:57:02 - INFO - codeparrot_training - Step 8078: {'lr': 0.0004979221929591663, 'samples': 4136448, 'steps': 8078, 'loss/train': 1.8927503824234009}
-03/03/2022 22:57:08 - INFO - codeparrot_training - Step 8079: {'lr': 0.0004979215101379093, 'samples': 4136960, 'steps': 8079, 'loss/train': 1.8156390190124512}
-03/03/2022 22:57:11 - INFO - codeparrot_training - Step 8080: {'lr': 0.0004979208272049426, 'samples': 4137472, 'steps': 8080, 'loss/train': 5.175743103027344}
-03/03/2022 22:57:13 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/03/2022 22:57:16 - INFO - codeparrot_training - Step 8081: {'lr': 0.0004979201441602665, 'samples': 4137984, 'steps': 8081, 'loss/train': 1.7585148811340332}
-03/03/2022 22:57:19 - INFO - codeparrot_training - Step 8082: {'lr': 0.0004979194610038816, 'samples': 4138496, 'steps': 8082, 'loss/train': 2.3044378757476807}
-03/03/2022 22:57:21 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/03/2022 22:57:25 - INFO - codeparrot_training - Step 8083: {'lr': 0.000497918777735788, 'samples': 4139008, 'steps': 8083, 'loss/train': 1.5257017612457275}
-03/03/2022 22:57:28 - INFO - codeparrot_training - Step 8084: {'lr': 0.000497918094355986, 'samples': 4139520, 'steps': 8084, 'loss/train': 2.0540482997894287}
-03/03/2022 22:57:30 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/03/2022 22:57:34 - INFO - codeparrot_training - Step 8085: {'lr': 0.000497917410864476, 'samples': 4140032, 'steps': 8085, 'loss/train': 0.4346829950809479}
-03/03/2022 22:57:37 - INFO - codeparrot_training - Step 8086: {'lr': 0.0004979167272612581, 'samples': 4140544, 'steps': 8086, 'loss/train': 0.3601745367050171}
-03/03/2022 22:57:40 - INFO - codeparrot_training - Step 8087: {'lr': 0.0004979160435463328, 'samples': 4141056, 'steps': 8087, 'loss/train': 1.467118263244629}
-03/03/2022 22:57:41 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/03/2022 22:57:45 - INFO - codeparrot_training - Step 8088: {'lr': 0.0004979153597197003, 'samples': 4141568, 'steps': 8088, 'loss/train': 2.436453104019165}
-03/03/2022 22:57:49 - INFO - codeparrot_training - Step 8089: {'lr': 0.0004979146757813611, 'samples': 4142080, 'steps': 8089, 'loss/train': 1.9858006238937378}
-03/03/2022 22:57:50 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/03/2022 22:57:54 - INFO - codeparrot_training - Step 8090: {'lr': 0.0004979139917313153, 'samples': 4142592, 'steps': 8090, 'loss/train': 1.1570111513137817}
-03/03/2022 22:57:57 - INFO - codeparrot_training - Step 8091: {'lr': 0.0004979133075695634, 'samples': 4143104, 'steps': 8091, 'loss/train': 2.903770923614502}
-03/03/2022 22:57:58 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/03/2022 22:58:02 - INFO - codeparrot_training - Step 8092: {'lr': 0.0004979126232961054, 'samples': 4143616, 'steps': 8092, 'loss/train': 2.60371994972229}
-03/03/2022 22:58:06 - INFO - codeparrot_training - Step 8093: {'lr': 0.0004979119389109419, 'samples': 4144128, 'steps': 8093, 'loss/train': 3.1345131397247314}
-03/03/2022 22:58:06 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/03/2022 22:58:11 - INFO - codeparrot_training - Step 8094: {'lr': 0.000497911254414073, 'samples': 4144640, 'steps': 8094, 'loss/train': 2.468526601791382}
-03/03/2022 22:58:14 - INFO - codeparrot_training - Step 8095: {'lr': 0.0004979105698054992, 'samples': 4145152, 'steps': 8095, 'loss/train': 2.097252607345581}
-03/03/2022 22:58:15 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/03/2022 22:58:19 - INFO - codeparrot_training - Step 8096: {'lr': 0.0004979098850852208, 'samples': 4145664, 'steps': 8096, 'loss/train': 3.217926025390625}
-03/03/2022 22:58:22 - INFO - codeparrot_training - Step 8097: {'lr': 0.0004979092002532379, 'samples': 4146176, 'steps': 8097, 'loss/train': 1.6880582571029663}
-03/03/2022 22:58:23 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/03/2022 22:58:28 - INFO - codeparrot_training - Step 8098: {'lr': 0.0004979085153095509, 'samples': 4146688, 'steps': 8098, 'loss/train': 1.119328498840332}
-03/03/2022 22:58:31 - INFO - codeparrot_training - Step 8099: {'lr': 0.0004979078302541604, 'samples': 4147200, 'steps': 8099, 'loss/train': 2.260218620300293}
-03/03/2022 22:58:31 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/03/2022 22:58:36 - INFO - codeparrot_training - Step 8100: {'lr': 0.0004979071450870662, 'samples': 4147712, 'steps': 8100, 'loss/train': 2.0611443519592285}
-03/03/2022 22:58:39 - INFO - codeparrot_training - Step 8101: {'lr': 0.0004979064598082689, 'samples': 4148224, 'steps': 8101, 'loss/train': 2.333263635635376}
-03/03/2022 22:58:40 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/03/2022 22:58:44 - INFO - codeparrot_training - Step 8102: {'lr': 0.0004979057744177689, 'samples': 4148736, 'steps': 8102, 'loss/train': 1.9020397663116455}
-03/03/2022 22:58:47 - INFO - codeparrot_training - Step 8103: {'lr': 0.0004979050889155663, 'samples': 4149248, 'steps': 8103, 'loss/train': 2.3179030418395996}
-03/03/2022 22:58:48 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/03/2022 22:58:53 - INFO - codeparrot_training - Step 8104: {'lr': 0.0004979044033016616, 'samples': 4149760, 'steps': 8104, 'loss/train': 2.2731804847717285}
-03/03/2022 22:58:56 - INFO - codeparrot_training - Step 8105: {'lr': 0.0004979037175760548, 'samples': 4150272, 'steps': 8105, 'loss/train': 2.6590769290924072}
-03/03/2022 22:58:58 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/03/2022 22:59:02 - INFO - codeparrot_training - Step 8106: {'lr': 0.0004979030317387466, 'samples': 4150784, 'steps': 8106, 'loss/train': 2.166933298110962}
-03/03/2022 22:59:05 - INFO - codeparrot_training - Step 8107: {'lr': 0.0004979023457897371, 'samples': 4151296, 'steps': 8107, 'loss/train': 2.1427242755889893}
-03/03/2022 22:59:06 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/03/2022 22:59:10 - INFO - codeparrot_training - Step 8108: {'lr': 0.0004979016597290264, 'samples': 4151808, 'steps': 8108, 'loss/train': 2.0150084495544434}
-03/03/2022 22:59:13 - INFO - codeparrot_training - Step 8109: {'lr': 0.0004979009735566152, 'samples': 4152320, 'steps': 8109, 'loss/train': 1.6503459215164185}
-03/03/2022 22:59:14 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/03/2022 22:59:18 - INFO - codeparrot_training - Step 8110: {'lr': 0.0004979002872725037, 'samples': 4152832, 'steps': 8110, 'loss/train': 2.3260855674743652}
-03/03/2022 22:59:21 - INFO - codeparrot_training - Step 8111: {'lr': 0.0004978996008766922, 'samples': 4153344, 'steps': 8111, 'loss/train': 1.0980503559112549}
-03/03/2022 22:59:23 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/03/2022 22:59:27 - INFO - codeparrot_training - Step 8112: {'lr': 0.0004978989143691808, 'samples': 4153856, 'steps': 8112, 'loss/train': 3.084331750869751}
-03/03/2022 22:59:30 - INFO - codeparrot_training - Step 8113: {'lr': 0.00049789822774997, 'samples': 4154368, 'steps': 8113, 'loss/train': 2.26532244682312}
-03/03/2022 22:59:31 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/03/2022 22:59:35 - INFO - codeparrot_training - Step 8114: {'lr': 0.0004978975410190601, 'samples': 4154880, 'steps': 8114, 'loss/train': 2.5077929496765137}
-03/03/2022 22:59:39 - INFO - codeparrot_training - Step 8115: {'lr': 0.0004978968541764515, 'samples': 4155392, 'steps': 8115, 'loss/train': 2.2625439167022705}
-03/03/2022 22:59:41 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/03/2022 22:59:44 - INFO - codeparrot_training - Step 8116: {'lr': 0.0004978961672221444, 'samples': 4155904, 'steps': 8116, 'loss/train': 1.579458475112915}
-03/03/2022 22:59:47 - INFO - codeparrot_training - Step 8117: {'lr': 0.000497895480156139, 'samples': 4156416, 'steps': 8117, 'loss/train': 1.171578288078308}
-03/03/2022 22:59:49 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/03/2022 22:59:52 - INFO - codeparrot_training - Step 8118: {'lr': 0.0004978947929784358, 'samples': 4156928, 'steps': 8118, 'loss/train': 2.538341522216797}
-03/03/2022 22:59:56 - INFO - codeparrot_training - Step 8119: {'lr': 0.0004978941056890349, 'samples': 4157440, 'steps': 8119, 'loss/train': 2.1212620735168457}
-03/03/2022 22:59:58 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/03/2022 23:00:01 - INFO - codeparrot_training - Step 8120: {'lr': 0.0004978934182879369, 'samples': 4157952, 'steps': 8120, 'loss/train': 1.7903887033462524}
-03/03/2022 23:00:04 - INFO - codeparrot_training - Step 8121: {'lr': 0.0004978927307751419, 'samples': 4158464, 'steps': 8121, 'loss/train': 2.744810104370117}
-03/03/2022 23:00:06 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/03/2022 23:00:09 - INFO - codeparrot_training - Step 8122: {'lr': 0.0004978920431506501, 'samples': 4158976, 'steps': 8122, 'loss/train': 2.362727403640747}
-03/03/2022 23:00:12 - INFO - codeparrot_training - Step 8123: {'lr': 0.0004978913554144623, 'samples': 4159488, 'steps': 8123, 'loss/train': 2.8642570972442627}
-03/03/2022 23:00:14 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/03/2022 23:00:18 - INFO - codeparrot_training - Step 8124: {'lr': 0.0004978906675665782, 'samples': 4160000, 'steps': 8124, 'loss/train': 2.0109260082244873}
-03/03/2022 23:00:21 - INFO - codeparrot_training - Step 8125: {'lr': 0.0004978899796069985, 'samples': 4160512, 'steps': 8125, 'loss/train': 3.095813512802124}
-03/03/2022 23:00:23 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/03/2022 23:00:26 - INFO - codeparrot_training - Step 8126: {'lr': 0.0004978892915357234, 'samples': 4161024, 'steps': 8126, 'loss/train': 1.7495702505111694}
-03/03/2022 23:00:29 - INFO - codeparrot_training - Step 8127: {'lr': 0.0004978886033527532, 'samples': 4161536, 'steps': 8127, 'loss/train': 1.4775800704956055}
-03/03/2022 23:00:31 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/03/2022 23:00:35 - INFO - codeparrot_training - Step 8128: {'lr': 0.0004978879150580882, 'samples': 4162048, 'steps': 8128, 'loss/train': 1.5684502124786377}
-03/03/2022 23:00:38 - INFO - codeparrot_training - Step 8129: {'lr': 0.0004978872266517288, 'samples': 4162560, 'steps': 8129, 'loss/train': 1.3381588459014893}
-03/03/2022 23:00:40 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/03/2022 23:00:43 - INFO - codeparrot_training - Step 8130: {'lr': 0.0004978865381336752, 'samples': 4163072, 'steps': 8130, 'loss/train': 0.5315456986427307}
-03/03/2022 23:00:46 - INFO - codeparrot_training - Step 8131: {'lr': 0.0004978858495039277, 'samples': 4163584, 'steps': 8131, 'loss/train': 2.6284613609313965}
-03/03/2022 23:00:48 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/03/2022 23:00:51 - INFO - codeparrot_training - Step 8132: {'lr': 0.0004978851607624867, 'samples': 4164096, 'steps': 8132, 'loss/train': 1.9801090955734253}
-03/03/2022 23:00:55 - INFO - codeparrot_training - Step 8133: {'lr': 0.0004978844719093525, 'samples': 4164608, 'steps': 8133, 'loss/train': 2.065821647644043}
-03/03/2022 23:00:56 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/03/2022 23:01:00 - INFO - codeparrot_training - Step 8134: {'lr': 0.0004978837829445254, 'samples': 4165120, 'steps': 8134, 'loss/train': 2.0343308448791504}
-03/03/2022 23:01:03 - INFO - codeparrot_training - Step 8135: {'lr': 0.0004978830938680056, 'samples': 4165632, 'steps': 8135, 'loss/train': 2.240384101867676}
-03/03/2022 23:01:05 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/03/2022 23:01:08 - INFO - codeparrot_training - Step 8136: {'lr': 0.0004978824046797935, 'samples': 4166144, 'steps': 8136, 'loss/train': 0.2598593533039093}
-03/03/2022 23:01:11 - INFO - codeparrot_training - Step 8137: {'lr': 0.0004978817153798895, 'samples': 4166656, 'steps': 8137, 'loss/train': 1.9990391731262207}
-03/03/2022 23:01:14 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/03/2022 23:01:17 - INFO - codeparrot_training - Step 8138: {'lr': 0.0004978810259682939, 'samples': 4167168, 'steps': 8138, 'loss/train': 2.5676701068878174}
-03/03/2022 23:01:20 - INFO - codeparrot_training - Step 8139: {'lr': 0.0004978803364450068, 'samples': 4167680, 'steps': 8139, 'loss/train': 2.5269851684570312}
-03/03/2022 23:01:22 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/03/2022 23:01:25 - INFO - codeparrot_training - Step 8140: {'lr': 0.0004978796468100286, 'samples': 4168192, 'steps': 8140, 'loss/train': 1.9048619270324707}
-03/03/2022 23:01:28 - INFO - codeparrot_training - Step 8141: {'lr': 0.0004978789570633598, 'samples': 4168704, 'steps': 8141, 'loss/train': 2.2653346061706543}
-03/03/2022 23:01:30 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/03/2022 23:01:33 - INFO - codeparrot_training - Step 8142: {'lr': 0.0004978782672050004, 'samples': 4169216, 'steps': 8142, 'loss/train': 1.7477989196777344}
-03/03/2022 23:01:37 - INFO - codeparrot_training - Step 8143: {'lr': 0.000497877577234951, 'samples': 4169728, 'steps': 8143, 'loss/train': 1.9532959461212158}
-03/03/2022 23:01:38 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/03/2022 23:01:42 - INFO - codeparrot_training - Step 8144: {'lr': 0.0004978768871532117, 'samples': 4170240, 'steps': 8144, 'loss/train': 1.4285939931869507}
-03/03/2022 23:01:45 - INFO - codeparrot_training - Step 8145: {'lr': 0.0004978761969597831, 'samples': 4170752, 'steps': 8145, 'loss/train': 2.0202813148498535}
-03/03/2022 23:01:47 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/03/2022 23:01:50 - INFO - codeparrot_training - Step 8146: {'lr': 0.0004978755066546651, 'samples': 4171264, 'steps': 8146, 'loss/train': 1.9631118774414062}
-03/03/2022 23:01:53 - INFO - codeparrot_training - Step 8147: {'lr': 0.0004978748162378583, 'samples': 4171776, 'steps': 8147, 'loss/train': 3.3999078273773193}
-03/03/2022 23:01:55 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/03/2022 23:01:59 - INFO - codeparrot_training - Step 8148: {'lr': 0.0004978741257093629, 'samples': 4172288, 'steps': 8148, 'loss/train': 2.159604072570801}
-03/03/2022 23:02:02 - INFO - codeparrot_training - Step 8149: {'lr': 0.0004978734350691793, 'samples': 4172800, 'steps': 8149, 'loss/train': 1.8655242919921875}
-03/03/2022 23:02:05 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/03/2022 23:02:07 - INFO - codeparrot_training - Step 8150: {'lr': 0.0004978727443173077, 'samples': 4173312, 'steps': 8150, 'loss/train': 4.280555725097656}
-03/03/2022 23:02:10 - INFO - codeparrot_training - Step 8151: {'lr': 0.0004978720534537485, 'samples': 4173824, 'steps': 8151, 'loss/train': 2.5109477043151855}
-03/03/2022 23:02:13 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/03/2022 23:02:16 - INFO - codeparrot_training - Step 8152: {'lr': 0.000497871362478502, 'samples': 4174336, 'steps': 8152, 'loss/train': 2.225389003753662}
-03/03/2022 23:02:19 - INFO - codeparrot_training - Step 8153: {'lr': 0.0004978706713915684, 'samples': 4174848, 'steps': 8153, 'loss/train': 2.0503034591674805}
-03/03/2022 23:02:21 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/03/2022 23:02:24 - INFO - codeparrot_training - Step 8154: {'lr': 0.0004978699801929481, 'samples': 4175360, 'steps': 8154, 'loss/train': 2.7034006118774414}
-03/03/2022 23:02:27 - INFO - codeparrot_training - Step 8155: {'lr': 0.0004978692888826415, 'samples': 4175872, 'steps': 8155, 'loss/train': 1.5243817567825317}
-03/03/2022 23:02:30 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/03/2022 23:02:32 - INFO - codeparrot_training - Step 8156: {'lr': 0.0004978685974606488, 'samples': 4176384, 'steps': 8156, 'loss/train': 1.6821690797805786}
-03/03/2022 23:02:36 - INFO - codeparrot_training - Step 8157: {'lr': 0.0004978679059269704, 'samples': 4176896, 'steps': 8157, 'loss/train': 2.01422381401062}
-03/03/2022 23:02:38 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/03/2022 23:02:41 - INFO - codeparrot_training - Step 8158: {'lr': 0.0004978672142816064, 'samples': 4177408, 'steps': 8158, 'loss/train': 2.309589147567749}
-03/03/2022 23:02:44 - INFO - codeparrot_training - Step 8159: {'lr': 0.0004978665225245573, 'samples': 4177920, 'steps': 8159, 'loss/train': 2.0150539875030518}
-03/03/2022 23:02:46 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/03/2022 23:02:49 - INFO - codeparrot_training - Step 8160: {'lr': 0.0004978658306558234, 'samples': 4178432, 'steps': 8160, 'loss/train': 1.9900379180908203}
-03/03/2022 23:02:52 - INFO - codeparrot_training - Step 8161: {'lr': 0.000497865138675405, 'samples': 4178944, 'steps': 8161, 'loss/train': 2.677856206893921}
-03/03/2022 23:02:54 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/03/2022 23:02:58 - INFO - codeparrot_training - Step 8162: {'lr': 0.0004978644465833024, 'samples': 4179456, 'steps': 8162, 'loss/train': 2.1394386291503906}
-03/03/2022 23:03:01 - INFO - codeparrot_training - Step 8163: {'lr': 0.000497863754379516, 'samples': 4179968, 'steps': 8163, 'loss/train': 2.377396821975708}
-03/03/2022 23:03:02 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/03/2022 23:03:06 - INFO - codeparrot_training - Step 8164: {'lr': 0.0004978630620640458, 'samples': 4180480, 'steps': 8164, 'loss/train': 1.636565089225769}
-03/03/2022 23:03:09 - INFO - codeparrot_training - Step 8165: {'lr': 0.0004978623696368924, 'samples': 4180992, 'steps': 8165, 'loss/train': 2.482028007507324}
-03/03/2022 23:03:11 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/03/2022 23:03:14 - INFO - codeparrot_training - Step 8166: {'lr': 0.0004978616770980561, 'samples': 4181504, 'steps': 8166, 'loss/train': 1.9079967737197876}
-03/03/2022 23:03:18 - INFO - codeparrot_training - Step 8167: {'lr': 0.0004978609844475371, 'samples': 4182016, 'steps': 8167, 'loss/train': 2.297579765319824}
-03/03/2022 23:03:19 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/03/2022 23:03:23 - INFO - codeparrot_training - Step 8168: {'lr': 0.0004978602916853359, 'samples': 4182528, 'steps': 8168, 'loss/train': 1.8337795734405518}
-03/03/2022 23:03:26 - INFO - codeparrot_training - Step 8169: {'lr': 0.0004978595988114525, 'samples': 4183040, 'steps': 8169, 'loss/train': 2.022766590118408}
-03/03/2022 23:03:27 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/03/2022 23:03:31 - INFO - codeparrot_training - Step 8170: {'lr': 0.0004978589058258874, 'samples': 4183552, 'steps': 8170, 'loss/train': 2.5012011528015137}
-03/03/2022 23:03:34 - INFO - codeparrot_training - Step 8171: {'lr': 0.0004978582127286409, 'samples': 4184064, 'steps': 8171, 'loss/train': 2.251767635345459}
-03/03/2022 23:03:36 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/03/2022 23:03:40 - INFO - codeparrot_training - Step 8172: {'lr': 0.0004978575195197135, 'samples': 4184576, 'steps': 8172, 'loss/train': 2.1803767681121826}
-03/03/2022 23:03:43 - INFO - codeparrot_training - Step 8173: {'lr': 0.0004978568261991051, 'samples': 4185088, 'steps': 8173, 'loss/train': 2.5617454051971436}
-03/03/2022 23:03:44 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/03/2022 23:03:48 - INFO - codeparrot_training - Step 8174: {'lr': 0.0004978561327668164, 'samples': 4185600, 'steps': 8174, 'loss/train': 2.3106889724731445}
-03/03/2022 23:03:51 - INFO - codeparrot_training - Step 8175: {'lr': 0.0004978554392228475, 'samples': 4186112, 'steps': 8175, 'loss/train': 1.9366906881332397}
-03/03/2022 23:03:54 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/03/2022 23:03:57 - INFO - codeparrot_training - Step 8176: {'lr': 0.0004978547455671986, 'samples': 4186624, 'steps': 8176, 'loss/train': 1.8139770030975342}
-03/03/2022 23:04:00 - INFO - codeparrot_training - Step 8177: {'lr': 0.0004978540517998704, 'samples': 4187136, 'steps': 8177, 'loss/train': 1.8323479890823364}
-03/03/2022 23:04:02 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/03/2022 23:04:05 - INFO - codeparrot_training - Step 8178: {'lr': 0.0004978533579208629, 'samples': 4187648, 'steps': 8178, 'loss/train': 1.714663028717041}
-03/03/2022 23:04:08 - INFO - codeparrot_training - Step 8179: {'lr': 0.0004978526639301766, 'samples': 4188160, 'steps': 8179, 'loss/train': 1.6271787881851196}
-03/03/2022 23:04:10 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/03/2022 23:04:13 - INFO - codeparrot_training - Step 8180: {'lr': 0.0004978519698278116, 'samples': 4188672, 'steps': 8180, 'loss/train': 2.368666887283325}
-03/03/2022 23:04:17 - INFO - codeparrot_training - Step 8181: {'lr': 0.0004978512756137684, 'samples': 4189184, 'steps': 8181, 'loss/train': 1.9006967544555664}
-03/03/2022 23:04:19 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/03/2022 23:04:22 - INFO - codeparrot_training - Step 8182: {'lr': 0.0004978505812880472, 'samples': 4189696, 'steps': 8182, 'loss/train': 2.5535972118377686}
-03/03/2022 23:04:25 - INFO - codeparrot_training - Step 8183: {'lr': 0.0004978498868506483, 'samples': 4190208, 'steps': 8183, 'loss/train': 2.0157148838043213}
-03/03/2022 23:04:27 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/03/2022 23:04:30 - INFO - codeparrot_training - Step 8184: {'lr': 0.0004978491923015721, 'samples': 4190720, 'steps': 8184, 'loss/train': 2.4077699184417725}
-03/03/2022 23:04:33 - INFO - codeparrot_training - Step 8185: {'lr': 0.0004978484976408189, 'samples': 4191232, 'steps': 8185, 'loss/train': 2.14156174659729}
-03/03/2022 23:04:35 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/03/2022 23:04:39 - INFO - codeparrot_training - Step 8186: {'lr': 0.000497847802868389, 'samples': 4191744, 'steps': 8186, 'loss/train': 2.1312577724456787}
-03/03/2022 23:04:42 - INFO - codeparrot_training - Step 8187: {'lr': 0.0004978471079842827, 'samples': 4192256, 'steps': 8187, 'loss/train': 7.821470737457275}
-03/03/2022 23:04:44 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 23:04:47 - INFO - codeparrot_training - Step 8188: {'lr': 0.0004978464129885003, 'samples': 4192768, 'steps': 8188, 'loss/train': 1.95905601978302}
-03/03/2022 23:04:50 - INFO - codeparrot_training - Step 8189: {'lr': 0.0004978457178810422, 'samples': 4193280, 'steps': 8189, 'loss/train': 2.4757161140441895}
-03/03/2022 23:04:52 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/03/2022 23:04:56 - INFO - codeparrot_training - Step 8190: {'lr': 0.0004978450226619085, 'samples': 4193792, 'steps': 8190, 'loss/train': 1.2356693744659424}
-03/03/2022 23:04:59 - INFO - codeparrot_training - Step 8191: {'lr': 0.0004978443273310997, 'samples': 4194304, 'steps': 8191, 'loss/train': 2.3572044372558594}
-03/03/2022 23:05:01 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/03/2022 23:05:04 - INFO - codeparrot_training - Step 8192: {'lr': 0.0004978436318886162, 'samples': 4194816, 'steps': 8192, 'loss/train': 2.7510948181152344}
-03/03/2022 23:05:07 - INFO - codeparrot_training - Step 8193: {'lr': 0.0004978429363344581, 'samples': 4195328, 'steps': 8193, 'loss/train': 2.125868082046509}
-03/03/2022 23:05:09 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/03/2022 23:05:13 - INFO - codeparrot_training - Step 8194: {'lr': 0.0004978422406686257, 'samples': 4195840, 'steps': 8194, 'loss/train': 2.0764782428741455}
-03/03/2022 23:05:16 - INFO - codeparrot_training - Step 8195: {'lr': 0.0004978415448911196, 'samples': 4196352, 'steps': 8195, 'loss/train': 1.8582093715667725}
-03/03/2022 23:05:17 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/03/2022 23:05:21 - INFO - codeparrot_training - Step 8196: {'lr': 0.0004978408490019398, 'samples': 4196864, 'steps': 8196, 'loss/train': 3.0263657569885254}
-03/03/2022 23:05:24 - INFO - codeparrot_training - Step 8197: {'lr': 0.0004978401530010868, 'samples': 4197376, 'steps': 8197, 'loss/train': 0.5265577435493469}
-03/03/2022 23:05:26 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/03/2022 23:05:29 - INFO - codeparrot_training - Step 8198: {'lr': 0.0004978394568885608, 'samples': 4197888, 'steps': 8198, 'loss/train': 1.8764965534210205}
-03/03/2022 23:05:33 - INFO - codeparrot_training - Step 8199: {'lr': 0.0004978387606643621, 'samples': 4198400, 'steps': 8199, 'loss/train': 2.1351585388183594}
-03/03/2022 23:05:34 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/03/2022 23:05:38 - INFO - codeparrot_training - Step 8200: {'lr': 0.0004978380643284912, 'samples': 4198912, 'steps': 8200, 'loss/train': 1.6137721538543701}
-03/03/2022 23:05:41 - INFO - codeparrot_training - Step 8201: {'lr': 0.0004978373678809482, 'samples': 4199424, 'steps': 8201, 'loss/train': 1.9004510641098022}
-03/03/2022 23:05:42 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/03/2022 23:05:46 - INFO - codeparrot_training - Step 8202: {'lr': 0.0004978366713217336, 'samples': 4199936, 'steps': 8202, 'loss/train': 1.0219368934631348}
-03/03/2022 23:05:50 - INFO - codeparrot_training - Step 8203: {'lr': 0.0004978359746508476, 'samples': 4200448, 'steps': 8203, 'loss/train': 2.7305781841278076}
-03/03/2022 23:05:51 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/03/2022 23:05:55 - INFO - codeparrot_training - Step 8204: {'lr': 0.0004978352778682905, 'samples': 4200960, 'steps': 8204, 'loss/train': 2.5579938888549805}
-03/03/2022 23:05:58 - INFO - codeparrot_training - Step 8205: {'lr': 0.0004978345809740626, 'samples': 4201472, 'steps': 8205, 'loss/train': 2.8068699836730957}
-03/03/2022 23:05:59 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/03/2022 23:06:03 - INFO - codeparrot_training - Step 8206: {'lr': 0.0004978338839681644, 'samples': 4201984, 'steps': 8206, 'loss/train': 2.427255392074585}
-03/03/2022 23:06:06 - INFO - codeparrot_training - Step 8207: {'lr': 0.000497833186850596, 'samples': 4202496, 'steps': 8207, 'loss/train': 1.453963041305542}
-03/03/2022 23:06:07 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/03/2022 23:06:12 - INFO - codeparrot_training - Step 8208: {'lr': 0.0004978324896213577, 'samples': 4203008, 'steps': 8208, 'loss/train': 2.2242040634155273}
-03/03/2022 23:06:15 - INFO - codeparrot_training - Step 8209: {'lr': 0.00049783179228045, 'samples': 4203520, 'steps': 8209, 'loss/train': 2.2926037311553955}
-03/03/2022 23:06:16 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/03/2022 23:06:20 - INFO - codeparrot_training - Step 8210: {'lr': 0.0004978310948278731, 'samples': 4204032, 'steps': 8210, 'loss/train': 2.9512462615966797}
-03/03/2022 23:06:23 - INFO - codeparrot_training - Step 8211: {'lr': 0.0004978303972636275, 'samples': 4204544, 'steps': 8211, 'loss/train': 2.3878045082092285}
-03/03/2022 23:06:25 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/03/2022 23:06:29 - INFO - codeparrot_training - Step 8212: {'lr': 0.0004978296995877132, 'samples': 4205056, 'steps': 8212, 'loss/train': 1.9260692596435547}
-03/03/2022 23:06:32 - INFO - codeparrot_training - Step 8213: {'lr': 0.0004978290018001306, 'samples': 4205568, 'steps': 8213, 'loss/train': 1.128262996673584}
-03/03/2022 23:06:33 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/03/2022 23:06:37 - INFO - codeparrot_training - Step 8214: {'lr': 0.0004978283039008801, 'samples': 4206080, 'steps': 8214, 'loss/train': 1.5935310125350952}
-03/03/2022 23:06:40 - INFO - codeparrot_training - Step 8215: {'lr': 0.000497827605889962, 'samples': 4206592, 'steps': 8215, 'loss/train': 1.930238127708435}
-03/03/2022 23:06:41 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/03/2022 23:06:45 - INFO - codeparrot_training - Step 8216: {'lr': 0.0004978269077673766, 'samples': 4207104, 'steps': 8216, 'loss/train': 2.0291271209716797}
-03/03/2022 23:06:49 - INFO - codeparrot_training - Step 8217: {'lr': 0.0004978262095331243, 'samples': 4207616, 'steps': 8217, 'loss/train': 1.3775007724761963}
-03/03/2022 23:06:49 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/03/2022 23:06:54 - INFO - codeparrot_training - Step 8218: {'lr': 0.0004978255111872053, 'samples': 4208128, 'steps': 8218, 'loss/train': 1.5547370910644531}
-03/03/2022 23:06:57 - INFO - codeparrot_training - Step 8219: {'lr': 0.0004978248127296198, 'samples': 4208640, 'steps': 8219, 'loss/train': 2.436781644821167}
-03/03/2022 23:06:58 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/03/2022 23:07:02 - INFO - codeparrot_training - Step 8220: {'lr': 0.0004978241141603685, 'samples': 4209152, 'steps': 8220, 'loss/train': 2.490488052368164}
-03/03/2022 23:07:06 - INFO - codeparrot_training - Step 8221: {'lr': 0.0004978234154794514, 'samples': 4209664, 'steps': 8221, 'loss/train': 2.385573387145996}
-03/03/2022 23:07:06 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/03/2022 23:07:11 - INFO - codeparrot_training - Step 8222: {'lr': 0.0004978227166868689, 'samples': 4210176, 'steps': 8222, 'loss/train': 2.518580198287964}
-03/03/2022 23:07:14 - INFO - codeparrot_training - Step 8223: {'lr': 0.0004978220177826212, 'samples': 4210688, 'steps': 8223, 'loss/train': 1.3057185411453247}
-03/03/2022 23:07:15 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/03/2022 23:07:19 - INFO - codeparrot_training - Step 8224: {'lr': 0.0004978213187667087, 'samples': 4211200, 'steps': 8224, 'loss/train': 2.5559186935424805}
-03/03/2022 23:07:22 - INFO - codeparrot_training - Step 8225: {'lr': 0.0004978206196391319, 'samples': 4211712, 'steps': 8225, 'loss/train': 2.4747416973114014}
-03/03/2022 23:07:23 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/03/2022 23:07:28 - INFO - codeparrot_training - Step 8226: {'lr': 0.0004978199203998909, 'samples': 4212224, 'steps': 8226, 'loss/train': 1.9003686904907227}
-03/03/2022 23:07:31 - INFO - codeparrot_training - Step 8227: {'lr': 0.0004978192210489861, 'samples': 4212736, 'steps': 8227, 'loss/train': 2.2485740184783936}
-03/03/2022 23:07:32 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/03/2022 23:07:36 - INFO - codeparrot_training - Step 8228: {'lr': 0.0004978185215864177, 'samples': 4213248, 'steps': 8228, 'loss/train': 1.9319219589233398}
-03/03/2022 23:07:39 - INFO - codeparrot_training - Step 8229: {'lr': 0.0004978178220121862, 'samples': 4213760, 'steps': 8229, 'loss/train': 1.6679941415786743}
-03/03/2022 23:07:40 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/03/2022 23:07:44 - INFO - codeparrot_training - Step 8230: {'lr': 0.0004978171223262917, 'samples': 4214272, 'steps': 8230, 'loss/train': 0.8790209293365479}
-03/03/2022 23:07:48 - INFO - codeparrot_training - Step 8231: {'lr': 0.0004978164225287346, 'samples': 4214784, 'steps': 8231, 'loss/train': 2.251675605773926}
-03/03/2022 23:07:48 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/03/2022 23:07:53 - INFO - codeparrot_training - Step 8232: {'lr': 0.0004978157226195153, 'samples': 4215296, 'steps': 8232, 'loss/train': 1.9175379276275635}
-03/03/2022 23:07:56 - INFO - codeparrot_training - Step 8233: {'lr': 0.0004978150225986342, 'samples': 4215808, 'steps': 8233, 'loss/train': 0.21706286072731018}
-03/03/2022 23:07:56 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/03/2022 23:08:01 - INFO - codeparrot_training - Step 8234: {'lr': 0.0004978143224660913, 'samples': 4216320, 'steps': 8234, 'loss/train': 2.4448297023773193}
-03/03/2022 23:08:05 - INFO - codeparrot_training - Step 8235: {'lr': 0.0004978136222218872, 'samples': 4216832, 'steps': 8235, 'loss/train': 2.002997398376465}
-03/03/2022 23:08:05 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/03/2022 23:08:10 - INFO - codeparrot_training - Step 8236: {'lr': 0.000497812921866022, 'samples': 4217344, 'steps': 8236, 'loss/train': 2.4145545959472656}
-03/03/2022 23:08:13 - INFO - codeparrot_training - Step 8237: {'lr': 0.0004978122213984961, 'samples': 4217856, 'steps': 8237, 'loss/train': 1.244879961013794}
-03/03/2022 23:08:13 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/03/2022 23:08:18 - INFO - codeparrot_training - Step 8238: {'lr': 0.00049781152081931, 'samples': 4218368, 'steps': 8238, 'loss/train': 2.337374210357666}
-03/03/2022 23:08:21 - INFO - codeparrot_training - Step 8239: {'lr': 0.0004978108201284638, 'samples': 4218880, 'steps': 8239, 'loss/train': 2.0194735527038574}
-03/03/2022 23:08:21 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/03/2022 23:08:27 - INFO - codeparrot_training - Step 8240: {'lr': 0.0004978101193259578, 'samples': 4219392, 'steps': 8240, 'loss/train': 2.3225631713867188}
-03/03/2022 23:08:30 - INFO - codeparrot_training - Step 8241: {'lr': 0.0004978094184117924, 'samples': 4219904, 'steps': 8241, 'loss/train': 1.1764671802520752}
-03/03/2022 23:08:30 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/03/2022 23:08:35 - INFO - codeparrot_training - Step 8242: {'lr': 0.0004978087173859679, 'samples': 4220416, 'steps': 8242, 'loss/train': 2.042708158493042}
-03/03/2022 23:08:38 - INFO - codeparrot_training - Step 8243: {'lr': 0.0004978080162484846, 'samples': 4220928, 'steps': 8243, 'loss/train': 2.570389986038208}
-03/03/2022 23:08:38 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/03/2022 23:08:43 - INFO - codeparrot_training - Step 8244: {'lr': 0.000497807314999343, 'samples': 4221440, 'steps': 8244, 'loss/train': 1.5794016122817993}
-03/03/2022 23:08:46 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/03/2022 23:08:48 - INFO - codeparrot_training - Step 8245: {'lr': 0.000497806613638543, 'samples': 4221952, 'steps': 8245, 'loss/train': 1.425133228302002}
-03/03/2022 23:08:52 - INFO - codeparrot_training - Step 8246: {'lr': 0.0004978059121660853, 'samples': 4222464, 'steps': 8246, 'loss/train': 2.4832029342651367}
-03/03/2022 23:08:54 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/03/2022 23:08:57 - INFO - codeparrot_training - Step 8247: {'lr': 0.0004978052105819701, 'samples': 4222976, 'steps': 8247, 'loss/train': 1.806008219718933}
-03/03/2022 23:09:00 - INFO - codeparrot_training - Step 8248: {'lr': 0.0004978045088861976, 'samples': 4223488, 'steps': 8248, 'loss/train': 2.0923404693603516}
-03/03/2022 23:09:03 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/03/2022 23:09:05 - INFO - codeparrot_training - Step 8249: {'lr': 0.0004978038070787683, 'samples': 4224000, 'steps': 8249, 'loss/train': 2.631331205368042}
-03/03/2022 23:09:09 - INFO - codeparrot_training - Step 8250: {'lr': 0.0004978031051596824, 'samples': 4224512, 'steps': 8250, 'loss/train': 2.38735294342041}
-03/03/2022 23:09:11 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/03/2022 23:09:14 - INFO - codeparrot_training - Step 8251: {'lr': 0.0004978024031289402, 'samples': 4225024, 'steps': 8251, 'loss/train': 2.020573377609253}
-03/03/2022 23:09:18 - INFO - codeparrot_training - Step 8252: {'lr': 0.0004978017009865421, 'samples': 4225536, 'steps': 8252, 'loss/train': 0.3764154314994812}
-03/03/2022 23:09:21 - INFO - codeparrot_training - Step 8253: {'lr': 0.0004978009987324884, 'samples': 4226048, 'steps': 8253, 'loss/train': 1.1399481296539307}
-03/03/2022 23:09:21 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/03/2022 23:09:26 - INFO - codeparrot_training - Step 8254: {'lr': 0.0004978002963667794, 'samples': 4226560, 'steps': 8254, 'loss/train': 2.4722044467926025}
-03/03/2022 23:09:30 - INFO - codeparrot_training - Step 8255: {'lr': 0.0004977995938894153, 'samples': 4227072, 'steps': 8255, 'loss/train': 1.1716208457946777}
-03/03/2022 23:09:30 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/03/2022 23:09:35 - INFO - codeparrot_training - Step 8256: {'lr': 0.0004977988913003966, 'samples': 4227584, 'steps': 8256, 'loss/train': 1.2050586938858032}
-03/03/2022 23:09:38 - INFO - codeparrot_training - Step 8257: {'lr': 0.0004977981885997235, 'samples': 4228096, 'steps': 8257, 'loss/train': 2.673396348953247}
-03/03/2022 23:09:39 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/03/2022 23:09:43 - INFO - codeparrot_training - Step 8258: {'lr': 0.0004977974857873964, 'samples': 4228608, 'steps': 8258, 'loss/train': 2.5595240592956543}
-03/03/2022 23:09:46 - INFO - codeparrot_training - Step 8259: {'lr': 0.0004977967828634157, 'samples': 4229120, 'steps': 8259, 'loss/train': 1.433173656463623}
-03/03/2022 23:09:47 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/03/2022 23:09:52 - INFO - codeparrot_training - Step 8260: {'lr': 0.0004977960798277814, 'samples': 4229632, 'steps': 8260, 'loss/train': 2.055312156677246}
-03/03/2022 23:09:55 - INFO - codeparrot_training - Step 8261: {'lr': 0.0004977953766804941, 'samples': 4230144, 'steps': 8261, 'loss/train': 1.9901210069656372}
-03/03/2022 23:09:55 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/03/2022 23:10:00 - INFO - codeparrot_training - Step 8262: {'lr': 0.0004977946734215541, 'samples': 4230656, 'steps': 8262, 'loss/train': 2.372833251953125}
-03/03/2022 23:10:03 - INFO - codeparrot_training - Step 8263: {'lr': 0.0004977939700509615, 'samples': 4231168, 'steps': 8263, 'loss/train': 2.287796974182129}
-03/03/2022 23:10:04 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/03/2022 23:10:08 - INFO - codeparrot_training - Step 8264: {'lr': 0.0004977932665687168, 'samples': 4231680, 'steps': 8264, 'loss/train': 1.3463122844696045}
-03/03/2022 23:10:12 - INFO - codeparrot_training - Step 8265: {'lr': 0.0004977925629748203, 'samples': 4232192, 'steps': 8265, 'loss/train': 1.570595145225525}
-03/03/2022 23:10:12 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/03/2022 23:10:17 - INFO - codeparrot_training - Step 8266: {'lr': 0.0004977918592692723, 'samples': 4232704, 'steps': 8266, 'loss/train': 2.189985513687134}
-03/03/2022 23:10:20 - INFO - codeparrot_training - Step 8267: {'lr': 0.0004977911554520731, 'samples': 4233216, 'steps': 8267, 'loss/train': 1.9091918468475342}
-03/03/2022 23:10:20 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/03/2022 23:10:25 - INFO - codeparrot_training - Step 8268: {'lr': 0.000497790451523223, 'samples': 4233728, 'steps': 8268, 'loss/train': 2.1992082595825195}
-03/03/2022 23:10:28 - INFO - codeparrot_training - Step 8269: {'lr': 0.0004977897474827224, 'samples': 4234240, 'steps': 8269, 'loss/train': 2.0774455070495605}
-03/03/2022 23:10:29 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/03/2022 23:10:34 - INFO - codeparrot_training - Step 8270: {'lr': 0.0004977890433305716, 'samples': 4234752, 'steps': 8270, 'loss/train': 2.5709707736968994}
-03/03/2022 23:10:37 - INFO - codeparrot_training - Step 8271: {'lr': 0.0004977883390667707, 'samples': 4235264, 'steps': 8271, 'loss/train': 2.006803512573242}
-03/03/2022 23:10:37 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/03/2022 23:10:42 - INFO - codeparrot_training - Step 8272: {'lr': 0.0004977876346913204, 'samples': 4235776, 'steps': 8272, 'loss/train': 2.164858818054199}
-03/03/2022 23:10:45 - INFO - codeparrot_training - Step 8273: {'lr': 0.0004977869302042207, 'samples': 4236288, 'steps': 8273, 'loss/train': 2.4893245697021484}
-03/03/2022 23:10:47 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/03/2022 23:10:51 - INFO - codeparrot_training - Step 8274: {'lr': 0.0004977862256054721, 'samples': 4236800, 'steps': 8274, 'loss/train': 2.248753786087036}
-03/03/2022 23:10:54 - INFO - codeparrot_training - Step 8275: {'lr': 0.0004977855208950748, 'samples': 4237312, 'steps': 8275, 'loss/train': 3.6827797889709473}
-03/03/2022 23:10:55 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/03/2022 23:10:59 - INFO - codeparrot_training - Step 8276: {'lr': 0.0004977848160730292, 'samples': 4237824, 'steps': 8276, 'loss/train': 1.9510807991027832}
-03/03/2022 23:11:02 - INFO - codeparrot_training - Step 8277: {'lr': 0.0004977841111393356, 'samples': 4238336, 'steps': 8277, 'loss/train': 2.1127421855926514}
-03/03/2022 23:11:04 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/03/2022 23:11:08 - INFO - codeparrot_training - Step 8278: {'lr': 0.0004977834060939943, 'samples': 4238848, 'steps': 8278, 'loss/train': 0.5322605967521667}
-03/03/2022 23:11:11 - INFO - codeparrot_training - Step 8279: {'lr': 0.0004977827009370056, 'samples': 4239360, 'steps': 8279, 'loss/train': 2.3732454776763916}
-03/03/2022 23:11:12 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/03/2022 23:11:16 - INFO - codeparrot_training - Step 8280: {'lr': 0.0004977819956683698, 'samples': 4239872, 'steps': 8280, 'loss/train': 1.928144931793213}
-03/03/2022 23:11:19 - INFO - codeparrot_training - Step 8281: {'lr': 0.0004977812902880873, 'samples': 4240384, 'steps': 8281, 'loss/train': 1.495331048965454}
-03/03/2022 23:11:20 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/03/2022 23:11:24 - INFO - codeparrot_training - Step 8282: {'lr': 0.0004977805847961584, 'samples': 4240896, 'steps': 8282, 'loss/train': 2.202878952026367}
-03/03/2022 23:11:27 - INFO - codeparrot_training - Step 8283: {'lr': 0.0004977798791925834, 'samples': 4241408, 'steps': 8283, 'loss/train': 2.848619222640991}
-03/03/2022 23:11:28 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/03/2022 23:11:33 - INFO - codeparrot_training - Step 8284: {'lr': 0.0004977791734773624, 'samples': 4241920, 'steps': 8284, 'loss/train': 1.3246815204620361}
-03/03/2022 23:11:36 - INFO - codeparrot_training - Step 8285: {'lr': 0.0004977784676504962, 'samples': 4242432, 'steps': 8285, 'loss/train': 1.8503108024597168}
-03/03/2022 23:11:37 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/03/2022 23:11:41 - INFO - codeparrot_training - Step 8286: {'lr': 0.0004977777617119847, 'samples': 4242944, 'steps': 8286, 'loss/train': 2.0031790733337402}
-03/03/2022 23:11:44 - INFO - codeparrot_training - Step 8287: {'lr': 0.0004977770556618284, 'samples': 4243456, 'steps': 8287, 'loss/train': 2.5379302501678467}
-03/03/2022 23:11:45 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/03/2022 23:11:50 - INFO - codeparrot_training - Step 8288: {'lr': 0.0004977763495000276, 'samples': 4243968, 'steps': 8288, 'loss/train': 1.6805524826049805}
-03/03/2022 23:11:53 - INFO - codeparrot_training - Step 8289: {'lr': 0.0004977756432265827, 'samples': 4244480, 'steps': 8289, 'loss/train': 2.772423028945923}
-03/03/2022 23:11:53 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/03/2022 23:11:58 - INFO - codeparrot_training - Step 8290: {'lr': 0.0004977749368414937, 'samples': 4244992, 'steps': 8290, 'loss/train': 1.0448238849639893}
-03/03/2022 23:12:01 - INFO - codeparrot_training - Step 8291: {'lr': 0.0004977742303447613, 'samples': 4245504, 'steps': 8291, 'loss/train': 1.8603436946868896}
-03/03/2022 23:12:02 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/03/2022 23:12:06 - INFO - codeparrot_training - Step 8292: {'lr': 0.0004977735237363855, 'samples': 4246016, 'steps': 8292, 'loss/train': 1.463528037071228}
-03/03/2022 23:12:10 - INFO - codeparrot_training - Step 8293: {'lr': 0.0004977728170163669, 'samples': 4246528, 'steps': 8293, 'loss/train': 2.476374626159668}
-03/03/2022 23:12:10 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/03/2022 23:12:15 - INFO - codeparrot_training - Step 8294: {'lr': 0.0004977721101847057, 'samples': 4247040, 'steps': 8294, 'loss/train': 6.961005687713623}
-03/03/2022 23:12:18 - INFO - codeparrot_training - Step 8295: {'lr': 0.0004977714032414021, 'samples': 4247552, 'steps': 8295, 'loss/train': 2.286019802093506}
-03/03/2022 23:12:19 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/03/2022 23:12:23 - INFO - codeparrot_training - Step 8296: {'lr': 0.0004977706961864566, 'samples': 4248064, 'steps': 8296, 'loss/train': 2.0636227130889893}
-03/03/2022 23:12:26 - INFO - codeparrot_training - Step 8297: {'lr': 0.0004977699890198695, 'samples': 4248576, 'steps': 8297, 'loss/train': 2.0436134338378906}
-03/03/2022 23:12:27 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/03/2022 23:12:32 - INFO - codeparrot_training - Step 8298: {'lr': 0.0004977692817416411, 'samples': 4249088, 'steps': 8298, 'loss/train': 2.0133986473083496}
-03/03/2022 23:12:35 - INFO - codeparrot_training - Step 8299: {'lr': 0.0004977685743517715, 'samples': 4249600, 'steps': 8299, 'loss/train': 2.1515610218048096}
-03/03/2022 23:12:35 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/03/2022 23:12:40 - INFO - codeparrot_training - Step 8300: {'lr': 0.0004977678668502614, 'samples': 4250112, 'steps': 8300, 'loss/train': 2.118053674697876}
-03/03/2022 23:12:43 - INFO - codeparrot_training - Step 8301: {'lr': 0.0004977671592371108, 'samples': 4250624, 'steps': 8301, 'loss/train': 2.2494590282440186}
-03/03/2022 23:12:44 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/03/2022 23:12:49 - INFO - codeparrot_training - Step 8302: {'lr': 0.0004977664515123201, 'samples': 4251136, 'steps': 8302, 'loss/train': 2.3440020084381104}
-03/03/2022 23:12:52 - INFO - codeparrot_training - Step 8303: {'lr': 0.0004977657436758898, 'samples': 4251648, 'steps': 8303, 'loss/train': 1.6744577884674072}
-03/03/2022 23:12:52 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/03/2022 23:12:57 - INFO - codeparrot_training - Step 8304: {'lr': 0.00049776503572782, 'samples': 4252160, 'steps': 8304, 'loss/train': 1.8551243543624878}
-03/03/2022 23:13:00 - INFO - codeparrot_training - Step 8305: {'lr': 0.0004977643276681111, 'samples': 4252672, 'steps': 8305, 'loss/train': 2.5027432441711426}
-03/03/2022 23:13:01 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/03/2022 23:13:05 - INFO - codeparrot_training - Step 8306: {'lr': 0.0004977636194967634, 'samples': 4253184, 'steps': 8306, 'loss/train': 2.196126937866211}
-03/03/2022 23:13:09 - INFO - codeparrot_training - Step 8307: {'lr': 0.0004977629112137773, 'samples': 4253696, 'steps': 8307, 'loss/train': 1.9784653186798096}
-03/03/2022 23:13:09 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/03/2022 23:13:14 - INFO - codeparrot_training - Step 8308: {'lr': 0.000497762202819153, 'samples': 4254208, 'steps': 8308, 'loss/train': 1.474435806274414}
-03/03/2022 23:13:17 - INFO - codeparrot_training - Step 8309: {'lr': 0.0004977614943128909, 'samples': 4254720, 'steps': 8309, 'loss/train': 2.2540440559387207}
-03/03/2022 23:13:17 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/03/2022 23:13:22 - INFO - codeparrot_training - Step 8310: {'lr': 0.0004977607856949913, 'samples': 4255232, 'steps': 8310, 'loss/train': 2.20745587348938}
-03/03/2022 23:13:25 - INFO - codeparrot_training - Step 8311: {'lr': 0.0004977600769654545, 'samples': 4255744, 'steps': 8311, 'loss/train': 2.9684677124023438}
-03/03/2022 23:13:26 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/03/2022 23:13:31 - INFO - codeparrot_training - Step 8312: {'lr': 0.0004977593681242808, 'samples': 4256256, 'steps': 8312, 'loss/train': 2.313978910446167}
-03/03/2022 23:13:34 - INFO - codeparrot_training - Step 8313: {'lr': 0.0004977586591714706, 'samples': 4256768, 'steps': 8313, 'loss/train': 1.6253421306610107}
-03/03/2022 23:13:34 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/03/2022 23:13:39 - INFO - codeparrot_training - Step 8314: {'lr': 0.0004977579501070241, 'samples': 4257280, 'steps': 8314, 'loss/train': 2.509859561920166}
-03/03/2022 23:13:42 - INFO - codeparrot_training - Step 8315: {'lr': 0.0004977572409309418, 'samples': 4257792, 'steps': 8315, 'loss/train': 2.045926094055176}
-03/03/2022 23:13:43 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/03/2022 23:13:48 - INFO - codeparrot_training - Step 8316: {'lr': 0.0004977565316432238, 'samples': 4258304, 'steps': 8316, 'loss/train': 2.5680274963378906}
-03/03/2022 23:13:51 - INFO - codeparrot_training - Step 8317: {'lr': 0.0004977558222438707, 'samples': 4258816, 'steps': 8317, 'loss/train': 2.0393552780151367}
-03/03/2022 23:13:51 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/03/2022 23:13:56 - INFO - codeparrot_training - Step 8318: {'lr': 0.0004977551127328824, 'samples': 4259328, 'steps': 8318, 'loss/train': 1.3196247816085815}
-03/03/2022 23:13:59 - INFO - codeparrot_training - Step 8319: {'lr': 0.0004977544031102597, 'samples': 4259840, 'steps': 8319, 'loss/train': 2.3605144023895264}
-03/03/2022 23:14:00 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/03/2022 23:14:04 - INFO - codeparrot_training - Step 8320: {'lr': 0.0004977536933760025, 'samples': 4260352, 'steps': 8320, 'loss/train': 0.2744183838367462}
-03/03/2022 23:14:08 - INFO - codeparrot_training - Step 8321: {'lr': 0.0004977529835301115, 'samples': 4260864, 'steps': 8321, 'loss/train': 1.9816244840621948}
-03/03/2022 23:14:08 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/03/2022 23:14:13 - INFO - codeparrot_training - Step 8322: {'lr': 0.0004977522735725866, 'samples': 4261376, 'steps': 8322, 'loss/train': 2.072136402130127}
-03/03/2022 23:14:16 - INFO - codeparrot_training - Step 8323: {'lr': 0.0004977515635034285, 'samples': 4261888, 'steps': 8323, 'loss/train': 2.571654796600342}
-03/03/2022 23:14:16 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/03/2022 23:14:21 - INFO - codeparrot_training - Step 8324: {'lr': 0.0004977508533226374, 'samples': 4262400, 'steps': 8324, 'loss/train': 2.2528016567230225}
-03/03/2022 23:14:24 - INFO - codeparrot_training - Step 8325: {'lr': 0.0004977501430302136, 'samples': 4262912, 'steps': 8325, 'loss/train': 1.9176405668258667}
-03/03/2022 23:14:25 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/03/2022 23:14:30 - INFO - codeparrot_training - Step 8326: {'lr': 0.0004977494326261573, 'samples': 4263424, 'steps': 8326, 'loss/train': 2.507146120071411}
-03/03/2022 23:14:33 - INFO - codeparrot_training - Step 8327: {'lr': 0.000497748722110469, 'samples': 4263936, 'steps': 8327, 'loss/train': 2.011274576187134}
-03/03/2022 23:14:33 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/03/2022 23:14:38 - INFO - codeparrot_training - Step 8328: {'lr': 0.0004977480114831489, 'samples': 4264448, 'steps': 8328, 'loss/train': 1.7366331815719604}
-03/03/2022 23:14:41 - INFO - codeparrot_training - Step 8329: {'lr': 0.0004977473007441973, 'samples': 4264960, 'steps': 8329, 'loss/train': 2.247609853744507}
-03/03/2022 23:14:42 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/03/2022 23:14:47 - INFO - codeparrot_training - Step 8330: {'lr': 0.0004977465898936147, 'samples': 4265472, 'steps': 8330, 'loss/train': 0.8084855675697327}
-03/03/2022 23:14:50 - INFO - codeparrot_training - Step 8331: {'lr': 0.0004977458789314014, 'samples': 4265984, 'steps': 8331, 'loss/train': 1.2733776569366455}
-03/03/2022 23:14:51 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/03/2022 23:14:55 - INFO - codeparrot_training - Step 8332: {'lr': 0.0004977451678575575, 'samples': 4266496, 'steps': 8332, 'loss/train': 1.5702471733093262}
-03/03/2022 23:14:58 - INFO - codeparrot_training - Step 8333: {'lr': 0.0004977444566720834, 'samples': 4267008, 'steps': 8333, 'loss/train': 1.7563356161117554}
-03/03/2022 23:15:00 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/03/2022 23:15:04 - INFO - codeparrot_training - Step 8334: {'lr': 0.0004977437453749795, 'samples': 4267520, 'steps': 8334, 'loss/train': 2.137308359146118}
-03/03/2022 23:15:07 - INFO - codeparrot_training - Step 8335: {'lr': 0.0004977430339662462, 'samples': 4268032, 'steps': 8335, 'loss/train': 2.286761522293091}
-03/03/2022 23:15:08 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/03/2022 23:15:12 - INFO - codeparrot_training - Step 8336: {'lr': 0.0004977423224458837, 'samples': 4268544, 'steps': 8336, 'loss/train': 2.583296298980713}
-03/03/2022 23:15:15 - INFO - codeparrot_training - Step 8337: {'lr': 0.0004977416108138922, 'samples': 4269056, 'steps': 8337, 'loss/train': 2.3785476684570312}
-03/03/2022 23:15:17 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/03/2022 23:15:21 - INFO - codeparrot_training - Step 8338: {'lr': 0.0004977408990702722, 'samples': 4269568, 'steps': 8338, 'loss/train': 2.3671278953552246}
-03/03/2022 23:15:24 - INFO - codeparrot_training - Step 8339: {'lr': 0.0004977401872150241, 'samples': 4270080, 'steps': 8339, 'loss/train': 2.2259342670440674}
-03/03/2022 23:15:25 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/03/2022 23:15:29 - INFO - codeparrot_training - Step 8340: {'lr': 0.000497739475248148, 'samples': 4270592, 'steps': 8340, 'loss/train': 2.3748931884765625}
-03/03/2022 23:15:32 - INFO - codeparrot_training - Step 8341: {'lr': 0.0004977387631696443, 'samples': 4271104, 'steps': 8341, 'loss/train': 2.5052592754364014}
-03/03/2022 23:15:34 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/03/2022 23:15:37 - INFO - codeparrot_training - Step 8342: {'lr': 0.0004977380509795133, 'samples': 4271616, 'steps': 8342, 'loss/train': 2.614178419113159}
-03/03/2022 23:15:41 - INFO - codeparrot_training - Step 8343: {'lr': 0.0004977373386777554, 'samples': 4272128, 'steps': 8343, 'loss/train': 1.7164456844329834}
-03/03/2022 23:15:42 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/03/2022 23:15:46 - INFO - codeparrot_training - Step 8344: {'lr': 0.0004977366262643709, 'samples': 4272640, 'steps': 8344, 'loss/train': 2.0701494216918945}
-03/03/2022 23:15:49 - INFO - codeparrot_training - Step 8345: {'lr': 0.0004977359137393601, 'samples': 4273152, 'steps': 8345, 'loss/train': 2.1992287635803223}
-03/03/2022 23:15:50 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/03/2022 23:15:54 - INFO - codeparrot_training - Step 8346: {'lr': 0.0004977352011027233, 'samples': 4273664, 'steps': 8346, 'loss/train': 1.8857239484786987}
-03/03/2022 23:15:57 - INFO - codeparrot_training - Step 8347: {'lr': 0.0004977344883544608, 'samples': 4274176, 'steps': 8347, 'loss/train': 1.9311935901641846}
-03/03/2022 23:15:59 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/03/2022 23:16:03 - INFO - codeparrot_training - Step 8348: {'lr': 0.0004977337754945731, 'samples': 4274688, 'steps': 8348, 'loss/train': 1.2234306335449219}
-03/03/2022 23:16:06 - INFO - codeparrot_training - Step 8349: {'lr': 0.0004977330625230603, 'samples': 4275200, 'steps': 8349, 'loss/train': 1.7517521381378174}
-03/03/2022 23:16:07 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/03/2022 23:16:11 - INFO - codeparrot_training - Step 8350: {'lr': 0.0004977323494399227, 'samples': 4275712, 'steps': 8350, 'loss/train': 1.872991681098938}
-03/03/2022 23:16:14 - INFO - codeparrot_training - Step 8351: {'lr': 0.0004977316362451608, 'samples': 4276224, 'steps': 8351, 'loss/train': 2.1858325004577637}
-03/03/2022 23:16:15 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/03/2022 23:16:20 - INFO - codeparrot_training - Step 8352: {'lr': 0.0004977309229387749, 'samples': 4276736, 'steps': 8352, 'loss/train': 1.7339273691177368}
-03/03/2022 23:16:23 - INFO - codeparrot_training - Step 8353: {'lr': 0.0004977302095207653, 'samples': 4277248, 'steps': 8353, 'loss/train': 2.4890639781951904}
-03/03/2022 23:16:24 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/03/2022 23:16:28 - INFO - codeparrot_training - Step 8354: {'lr': 0.0004977294959911322, 'samples': 4277760, 'steps': 8354, 'loss/train': 2.2571189403533936}
-03/03/2022 23:16:31 - INFO - codeparrot_training - Step 8355: {'lr': 0.0004977287823498761, 'samples': 4278272, 'steps': 8355, 'loss/train': 1.3341747522354126}
-03/03/2022 23:16:32 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/03/2022 23:16:36 - INFO - codeparrot_training - Step 8356: {'lr': 0.0004977280685969971, 'samples': 4278784, 'steps': 8356, 'loss/train': 2.084646224975586}
-03/03/2022 23:16:40 - INFO - codeparrot_training - Step 8357: {'lr': 0.0004977273547324958, 'samples': 4279296, 'steps': 8357, 'loss/train': 2.8275270462036133}
-03/03/2022 23:16:40 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/03/2022 23:16:45 - INFO - codeparrot_training - Step 8358: {'lr': 0.0004977266407563722, 'samples': 4279808, 'steps': 8358, 'loss/train': 2.0460166931152344}
-03/03/2022 23:16:48 - INFO - codeparrot_training - Step 8359: {'lr': 0.0004977259266686269, 'samples': 4280320, 'steps': 8359, 'loss/train': 1.9855483770370483}
-03/03/2022 23:16:48 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/03/2022 23:16:53 - INFO - codeparrot_training - Step 8360: {'lr': 0.0004977252124692601, 'samples': 4280832, 'steps': 8360, 'loss/train': 2.6218667030334473}
-03/03/2022 23:16:56 - INFO - codeparrot_training - Step 8361: {'lr': 0.0004977244981582723, 'samples': 4281344, 'steps': 8361, 'loss/train': 0.22633935511112213}
-03/03/2022 23:16:57 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/03/2022 23:17:02 - INFO - codeparrot_training - Step 8362: {'lr': 0.0004977237837356634, 'samples': 4281856, 'steps': 8362, 'loss/train': 1.9012571573257446}
-03/03/2022 23:17:05 - INFO - codeparrot_training - Step 8363: {'lr': 0.0004977230692014341, 'samples': 4282368, 'steps': 8363, 'loss/train': 2.313596725463867}
-03/03/2022 23:17:06 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/03/2022 23:17:10 - INFO - codeparrot_training - Step 8364: {'lr': 0.0004977223545555847, 'samples': 4282880, 'steps': 8364, 'loss/train': 2.2615795135498047}
-03/03/2022 23:17:13 - INFO - codeparrot_training - Step 8365: {'lr': 0.0004977216397981153, 'samples': 4283392, 'steps': 8365, 'loss/train': 0.3176412880420685}
-03/03/2022 23:17:14 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/03/2022 23:17:19 - INFO - codeparrot_training - Step 8366: {'lr': 0.0004977209249290264, 'samples': 4283904, 'steps': 8366, 'loss/train': 2.5636465549468994}
-03/03/2022 23:17:22 - INFO - codeparrot_training - Step 8367: {'lr': 0.0004977202099483184, 'samples': 4284416, 'steps': 8367, 'loss/train': 1.212020754814148}
-03/03/2022 23:17:23 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/03/2022 23:17:27 - INFO - codeparrot_training - Step 8368: {'lr': 0.0004977194948559913, 'samples': 4284928, 'steps': 8368, 'loss/train': 2.3729734420776367}
-03/03/2022 23:17:30 - INFO - codeparrot_training - Step 8369: {'lr': 0.0004977187796520457, 'samples': 4285440, 'steps': 8369, 'loss/train': 2.550067186355591}
-03/03/2022 23:17:31 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/03/2022 23:17:36 - INFO - codeparrot_training - Step 8370: {'lr': 0.0004977180643364819, 'samples': 4285952, 'steps': 8370, 'loss/train': 1.8557915687561035}
-03/03/2022 23:17:39 - INFO - codeparrot_training - Step 8371: {'lr': 0.0004977173489093, 'samples': 4286464, 'steps': 8371, 'loss/train': 1.5092228651046753}
-03/03/2022 23:17:40 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/03/2022 23:17:44 - INFO - codeparrot_training - Step 8372: {'lr': 0.0004977166333705005, 'samples': 4286976, 'steps': 8372, 'loss/train': 1.8986730575561523}
-03/03/2022 23:17:47 - INFO - codeparrot_training - Step 8373: {'lr': 0.0004977159177200839, 'samples': 4287488, 'steps': 8373, 'loss/train': 2.535759210586548}
-03/03/2022 23:17:48 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/03/2022 23:17:53 - INFO - codeparrot_training - Step 8374: {'lr': 0.0004977152019580502, 'samples': 4288000, 'steps': 8374, 'loss/train': 1.7295931577682495}
-03/03/2022 23:17:56 - INFO - codeparrot_training - Step 8375: {'lr': 0.0004977144860843998, 'samples': 4288512, 'steps': 8375, 'loss/train': 2.228574752807617}
-03/03/2022 23:17:57 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/03/2022 23:18:01 - INFO - codeparrot_training - Step 8376: {'lr': 0.0004977137700991332, 'samples': 4289024, 'steps': 8376, 'loss/train': 2.8498876094818115}
-03/03/2022 23:18:04 - INFO - codeparrot_training - Step 8377: {'lr': 0.0004977130540022506, 'samples': 4289536, 'steps': 8377, 'loss/train': 1.3288966417312622}
-03/03/2022 23:18:05 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/03/2022 23:18:09 - INFO - codeparrot_training - Step 8378: {'lr': 0.0004977123377937523, 'samples': 4290048, 'steps': 8378, 'loss/train': 2.2387278079986572}
-03/03/2022 23:18:12 - INFO - codeparrot_training - Step 8379: {'lr': 0.0004977116214736385, 'samples': 4290560, 'steps': 8379, 'loss/train': 2.3723511695861816}
-03/03/2022 23:18:13 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/03/2022 23:18:18 - INFO - codeparrot_training - Step 8380: {'lr': 0.0004977109050419097, 'samples': 4291072, 'steps': 8380, 'loss/train': 2.7465953826904297}
-03/03/2022 23:18:21 - INFO - codeparrot_training - Step 8381: {'lr': 0.0004977101884985663, 'samples': 4291584, 'steps': 8381, 'loss/train': 1.806462049484253}
-03/03/2022 23:18:22 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/03/2022 23:18:26 - INFO - codeparrot_training - Step 8382: {'lr': 0.0004977094718436085, 'samples': 4292096, 'steps': 8382, 'loss/train': 1.9363406896591187}
-03/03/2022 23:18:29 - INFO - codeparrot_training - Step 8383: {'lr': 0.0004977087550770366, 'samples': 4292608, 'steps': 8383, 'loss/train': 2.3096730709075928}
-03/03/2022 23:18:30 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/03/2022 23:18:34 - INFO - codeparrot_training - Step 8384: {'lr': 0.000497708038198851, 'samples': 4293120, 'steps': 8384, 'loss/train': 1.9298535585403442}
-03/03/2022 23:18:38 - INFO - codeparrot_training - Step 8385: {'lr': 0.0004977073212090519, 'samples': 4293632, 'steps': 8385, 'loss/train': 1.8535418510437012}
-03/03/2022 23:18:38 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/03/2022 23:18:43 - INFO - codeparrot_training - Step 8386: {'lr': 0.0004977066041076398, 'samples': 4294144, 'steps': 8386, 'loss/train': 1.6937059164047241}
-03/03/2022 23:18:46 - INFO - codeparrot_training - Step 8387: {'lr': 0.0004977058868946148, 'samples': 4294656, 'steps': 8387, 'loss/train': 1.4639008045196533}
-03/03/2022 23:18:47 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/03/2022 23:18:51 - INFO - codeparrot_training - Step 8388: {'lr': 0.0004977051695699775, 'samples': 4295168, 'steps': 8388, 'loss/train': 2.34855055809021}
-03/03/2022 23:18:54 - INFO - codeparrot_training - Step 8389: {'lr': 0.000497704452133728, 'samples': 4295680, 'steps': 8389, 'loss/train': 2.2176573276519775}
-03/03/2022 23:18:55 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/03/2022 23:19:00 - INFO - codeparrot_training - Step 8390: {'lr': 0.0004977037345858667, 'samples': 4296192, 'steps': 8390, 'loss/train': 1.8044193983078003}
-03/03/2022 23:19:03 - INFO - codeparrot_training - Step 8391: {'lr': 0.0004977030169263938, 'samples': 4296704, 'steps': 8391, 'loss/train': 2.2587411403656006}
-03/03/2022 23:19:04 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/03/2022 23:19:08 - INFO - codeparrot_training - Step 8392: {'lr': 0.0004977022991553099, 'samples': 4297216, 'steps': 8392, 'loss/train': 2.2206802368164062}
-03/03/2022 23:19:11 - INFO - codeparrot_training - Step 8393: {'lr': 0.0004977015812726151, 'samples': 4297728, 'steps': 8393, 'loss/train': 2.1944570541381836}
-03/03/2022 23:19:12 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/03/2022 23:19:17 - INFO - codeparrot_training - Step 8394: {'lr': 0.0004977008632783098, 'samples': 4298240, 'steps': 8394, 'loss/train': 2.2308928966522217}
-03/03/2022 23:19:20 - INFO - codeparrot_training - Step 8395: {'lr': 0.0004977001451723944, 'samples': 4298752, 'steps': 8395, 'loss/train': 2.8940327167510986}
-03/03/2022 23:19:21 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/03/2022 23:19:25 - INFO - codeparrot_training - Step 8396: {'lr': 0.000497699426954869, 'samples': 4299264, 'steps': 8396, 'loss/train': 2.326432228088379}
-03/03/2022 23:19:28 - INFO - codeparrot_training - Step 8397: {'lr': 0.0004976987086257342, 'samples': 4299776, 'steps': 8397, 'loss/train': 2.076282262802124}
-03/03/2022 23:19:29 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/03/2022 23:19:33 - INFO - codeparrot_training - Step 8398: {'lr': 0.0004976979901849901, 'samples': 4300288, 'steps': 8398, 'loss/train': 2.433126926422119}
-03/03/2022 23:19:36 - INFO - codeparrot_training - Step 8399: {'lr': 0.000497697271632637, 'samples': 4300800, 'steps': 8399, 'loss/train': 1.9160780906677246}
-03/03/2022 23:19:37 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/03/2022 23:19:42 - INFO - codeparrot_training - Step 8400: {'lr': 0.0004976965529686756, 'samples': 4301312, 'steps': 8400, 'loss/train': 1.7640479803085327}
-03/03/2022 23:19:45 - INFO - codeparrot_training - Step 8401: {'lr': 0.0004976958341931057, 'samples': 4301824, 'steps': 8401, 'loss/train': 2.0372872352600098}
-03/03/2022 23:19:47 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/03/2022 23:19:51 - INFO - codeparrot_training - Step 8402: {'lr': 0.000497695115305928, 'samples': 4302336, 'steps': 8402, 'loss/train': 1.1116116046905518}
-03/03/2022 23:19:54 - INFO - codeparrot_training - Step 8403: {'lr': 0.0004976943963071426, 'samples': 4302848, 'steps': 8403, 'loss/train': 2.37918758392334}
-03/03/2022 23:19:55 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/03/2022 23:19:59 - INFO - codeparrot_training - Step 8404: {'lr': 0.0004976936771967501, 'samples': 4303360, 'steps': 8404, 'loss/train': 0.3165260851383209}
-03/03/2022 23:20:02 - INFO - codeparrot_training - Step 8405: {'lr': 0.0004976929579747505, 'samples': 4303872, 'steps': 8405, 'loss/train': 1.8105621337890625}
-03/03/2022 23:20:04 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/03/2022 23:20:08 - INFO - codeparrot_training - Step 8406: {'lr': 0.0004976922386411444, 'samples': 4304384, 'steps': 8406, 'loss/train': 0.4474862813949585}
-03/03/2022 23:20:11 - INFO - codeparrot_training - Step 8407: {'lr': 0.0004976915191959319, 'samples': 4304896, 'steps': 8407, 'loss/train': 2.1898717880249023}
-03/03/2022 23:20:13 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/03/2022 23:20:16 - INFO - codeparrot_training - Step 8408: {'lr': 0.0004976907996391135, 'samples': 4305408, 'steps': 8408, 'loss/train': 2.2610347270965576}
-03/03/2022 23:20:19 - INFO - codeparrot_training - Step 8409: {'lr': 0.0004976900799706894, 'samples': 4305920, 'steps': 8409, 'loss/train': 2.371469020843506}
-03/03/2022 23:20:22 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/03/2022 23:20:24 - INFO - codeparrot_training - Step 8410: {'lr': 0.00049768936019066, 'samples': 4306432, 'steps': 8410, 'loss/train': 1.7692152261734009}
-03/03/2022 23:20:28 - INFO - codeparrot_training - Step 8411: {'lr': 0.0004976886402990255, 'samples': 4306944, 'steps': 8411, 'loss/train': 1.9091641902923584}
-03/03/2022 23:20:30 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/03/2022 23:20:33 - INFO - codeparrot_training - Step 8412: {'lr': 0.0004976879202957864, 'samples': 4307456, 'steps': 8412, 'loss/train': 3.125584840774536}
-03/03/2022 23:20:36 - INFO - codeparrot_training - Step 8413: {'lr': 0.000497687200180943, 'samples': 4307968, 'steps': 8413, 'loss/train': 2.38472580909729}
-03/03/2022 23:20:39 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/03/2022 23:20:41 - INFO - codeparrot_training - Step 8414: {'lr': 0.0004976864799544954, 'samples': 4308480, 'steps': 8414, 'loss/train': 2.6215381622314453}
-03/03/2022 23:20:44 - INFO - codeparrot_training - Step 8415: {'lr': 0.0004976857596164443, 'samples': 4308992, 'steps': 8415, 'loss/train': 2.422793388366699}
-03/03/2022 23:20:47 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/03/2022 23:20:50 - INFO - codeparrot_training - Step 8416: {'lr': 0.0004976850391667897, 'samples': 4309504, 'steps': 8416, 'loss/train': 1.652942419052124}
-03/03/2022 23:20:53 - INFO - codeparrot_training - Step 8417: {'lr': 0.0004976843186055321, 'samples': 4310016, 'steps': 8417, 'loss/train': 2.009974479675293}
-03/03/2022 23:20:55 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/03/2022 23:20:58 - INFO - codeparrot_training - Step 8418: {'lr': 0.0004976835979326718, 'samples': 4310528, 'steps': 8418, 'loss/train': 1.647745966911316}
-03/03/2022 23:21:01 - INFO - codeparrot_training - Step 8419: {'lr': 0.0004976828771482089, 'samples': 4311040, 'steps': 8419, 'loss/train': 2.0219156742095947}
-03/03/2022 23:21:03 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/03/2022 23:21:06 - INFO - codeparrot_training - Step 8420: {'lr': 0.0004976821562521441, 'samples': 4311552, 'steps': 8420, 'loss/train': 2.377408742904663}
-03/03/2022 23:21:10 - INFO - codeparrot_training - Step 8421: {'lr': 0.0004976814352444775, 'samples': 4312064, 'steps': 8421, 'loss/train': 1.8613158464431763}
-03/03/2022 23:21:12 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/03/2022 23:21:15 - INFO - codeparrot_training - Step 8422: {'lr': 0.0004976807141252094, 'samples': 4312576, 'steps': 8422, 'loss/train': 2.886425733566284}
-03/03/2022 23:21:18 - INFO - codeparrot_training - Step 8423: {'lr': 0.0004976799928943403, 'samples': 4313088, 'steps': 8423, 'loss/train': 1.702304482460022}
-03/03/2022 23:21:20 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/03/2022 23:21:23 - INFO - codeparrot_training - Step 8424: {'lr': 0.0004976792715518703, 'samples': 4313600, 'steps': 8424, 'loss/train': 2.0346603393554688}
-03/03/2022 23:21:27 - INFO - codeparrot_training - Step 8425: {'lr': 0.0004976785500978, 'samples': 4314112, 'steps': 8425, 'loss/train': 2.168598175048828}
-03/03/2022 23:21:29 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/03/2022 23:21:32 - INFO - codeparrot_training - Step 8426: {'lr': 0.0004976778285321294, 'samples': 4314624, 'steps': 8426, 'loss/train': 1.124597191810608}
-03/03/2022 23:21:35 - INFO - codeparrot_training - Step 8427: {'lr': 0.0004976771068548591, 'samples': 4315136, 'steps': 8427, 'loss/train': 1.3434709310531616}
-03/03/2022 23:21:37 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/03/2022 23:21:40 - INFO - codeparrot_training - Step 8428: {'lr': 0.0004976763850659893, 'samples': 4315648, 'steps': 8428, 'loss/train': 2.0667340755462646}
-03/03/2022 23:21:43 - INFO - codeparrot_training - Step 8429: {'lr': 0.0004976756631655203, 'samples': 4316160, 'steps': 8429, 'loss/train': 1.8767743110656738}
-03/03/2022 23:21:45 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/03/2022 23:21:49 - INFO - codeparrot_training - Step 8430: {'lr': 0.0004976749411534525, 'samples': 4316672, 'steps': 8430, 'loss/train': 2.1256628036499023}
-03/03/2022 23:21:52 - INFO - codeparrot_training - Step 8431: {'lr': 0.0004976742190297862, 'samples': 4317184, 'steps': 8431, 'loss/train': 2.365405559539795}
-03/03/2022 23:21:54 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/03/2022 23:21:57 - INFO - codeparrot_training - Step 8432: {'lr': 0.0004976734967945217, 'samples': 4317696, 'steps': 8432, 'loss/train': 2.2794883251190186}
-03/03/2022 23:22:00 - INFO - codeparrot_training - Step 8433: {'lr': 0.0004976727744476593, 'samples': 4318208, 'steps': 8433, 'loss/train': 2.3836560249328613}
-03/03/2022 23:22:02 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/03/2022 23:22:06 - INFO - codeparrot_training - Step 8434: {'lr': 0.0004976720519891994, 'samples': 4318720, 'steps': 8434, 'loss/train': 1.978493094444275}
-03/03/2022 23:22:09 - INFO - codeparrot_training - Step 8435: {'lr': 0.0004976713294191423, 'samples': 4319232, 'steps': 8435, 'loss/train': 2.246249198913574}
-03/03/2022 23:22:10 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/03/2022 23:22:14 - INFO - codeparrot_training - Step 8436: {'lr': 0.0004976706067374885, 'samples': 4319744, 'steps': 8436, 'loss/train': 2.7400028705596924}
-03/03/2022 23:22:17 - INFO - codeparrot_training - Step 8437: {'lr': 0.0004976698839442379, 'samples': 4320256, 'steps': 8437, 'loss/train': 0.7532373070716858}
-03/03/2022 23:22:18 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/03/2022 23:22:22 - INFO - codeparrot_training - Step 8438: {'lr': 0.0004976691610393911, 'samples': 4320768, 'steps': 8438, 'loss/train': 2.4438529014587402}
-03/03/2022 23:22:25 - INFO - codeparrot_training - Step 8439: {'lr': 0.0004976684380229485, 'samples': 4321280, 'steps': 8439, 'loss/train': 1.917314052581787}
-03/03/2022 23:22:27 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/03/2022 23:22:31 - INFO - codeparrot_training - Step 8440: {'lr': 0.0004976677148949102, 'samples': 4321792, 'steps': 8440, 'loss/train': 0.8096176981925964}
-03/03/2022 23:22:34 - INFO - codeparrot_training - Step 8441: {'lr': 0.0004976669916552768, 'samples': 4322304, 'steps': 8441, 'loss/train': 1.715502142906189}
-03/03/2022 23:22:36 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/03/2022 23:22:39 - INFO - codeparrot_training - Step 8442: {'lr': 0.0004976662683040484, 'samples': 4322816, 'steps': 8442, 'loss/train': 2.2405283451080322}
-03/03/2022 23:22:42 - INFO - codeparrot_training - Step 8443: {'lr': 0.0004976655448412254, 'samples': 4323328, 'steps': 8443, 'loss/train': 1.5312166213989258}
-03/03/2022 23:22:44 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/03/2022 23:22:48 - INFO - codeparrot_training - Step 8444: {'lr': 0.0004976648212668081, 'samples': 4323840, 'steps': 8444, 'loss/train': 2.2313499450683594}
-03/03/2022 23:22:51 - INFO - codeparrot_training - Step 8445: {'lr': 0.0004976640975807969, 'samples': 4324352, 'steps': 8445, 'loss/train': 2.386481761932373}
-03/03/2022 23:22:52 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/03/2022 23:22:56 - INFO - codeparrot_training - Step 8446: {'lr': 0.0004976633737831921, 'samples': 4324864, 'steps': 8446, 'loss/train': 2.3802876472473145}
-03/03/2022 23:22:59 - INFO - codeparrot_training - Step 8447: {'lr': 0.000497662649873994, 'samples': 4325376, 'steps': 8447, 'loss/train': 2.9355671405792236}
-03/03/2022 23:23:01 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/03/2022 23:23:05 - INFO - codeparrot_training - Step 8448: {'lr': 0.0004976619258532029, 'samples': 4325888, 'steps': 8448, 'loss/train': 2.548635959625244}
-03/03/2022 23:23:08 - INFO - codeparrot_training - Step 8449: {'lr': 0.0004976612017208191, 'samples': 4326400, 'steps': 8449, 'loss/train': 2.3804898262023926}
-03/03/2022 23:23:11 - INFO - codeparrot_training - Step 8450: {'lr': 0.000497660477476843, 'samples': 4326912, 'steps': 8450, 'loss/train': 1.767702341079712}
-03/03/2022 23:23:11 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/03/2022 23:23:17 - INFO - codeparrot_training - Step 8451: {'lr': 0.000497659753121275, 'samples': 4327424, 'steps': 8451, 'loss/train': 2.0308055877685547}
-03/03/2022 23:23:20 - INFO - codeparrot_training - Step 8452: {'lr': 0.0004976590286541152, 'samples': 4327936, 'steps': 8452, 'loss/train': 2.112783193588257}
-03/03/2022 23:23:20 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/03/2022 23:23:25 - INFO - codeparrot_training - Step 8453: {'lr': 0.0004976583040753643, 'samples': 4328448, 'steps': 8453, 'loss/train': 2.434246301651001}
-03/03/2022 23:23:28 - INFO - codeparrot_training - Step 8454: {'lr': 0.0004976575793850223, 'samples': 4328960, 'steps': 8454, 'loss/train': 2.454705238342285}
-03/03/2022 23:23:28 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/03/2022 23:23:33 - INFO - codeparrot_training - Step 8455: {'lr': 0.0004976568545830894, 'samples': 4329472, 'steps': 8455, 'loss/train': 2.375504970550537}
-03/03/2022 23:23:37 - INFO - codeparrot_training - Step 8456: {'lr': 0.0004976561296695663, 'samples': 4329984, 'steps': 8456, 'loss/train': 2.413057804107666}
-03/03/2022 23:23:37 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/03/2022 23:23:42 - INFO - codeparrot_training - Step 8457: {'lr': 0.0004976554046444532, 'samples': 4330496, 'steps': 8457, 'loss/train': 2.4651386737823486}
-03/03/2022 23:23:45 - INFO - codeparrot_training - Step 8458: {'lr': 0.0004976546795077503, 'samples': 4331008, 'steps': 8458, 'loss/train': 2.1767802238464355}
-03/03/2022 23:23:45 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/03/2022 23:23:50 - INFO - codeparrot_training - Step 8459: {'lr': 0.0004976539542594582, 'samples': 4331520, 'steps': 8459, 'loss/train': 1.7549782991409302}
-03/03/2022 23:23:53 - INFO - codeparrot_training - Step 8460: {'lr': 0.0004976532288995768, 'samples': 4332032, 'steps': 8460, 'loss/train': 2.424506187438965}
-03/03/2022 23:23:53 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/03/2022 23:23:59 - INFO - codeparrot_training - Step 8461: {'lr': 0.0004976525034281069, 'samples': 4332544, 'steps': 8461, 'loss/train': 1.9917365312576294}
-03/03/2022 23:24:02 - INFO - codeparrot_training - Step 8462: {'lr': 0.0004976517778450486, 'samples': 4333056, 'steps': 8462, 'loss/train': 2.329604148864746}
-03/03/2022 23:24:02 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/03/2022 23:24:07 - INFO - codeparrot_training - Step 8463: {'lr': 0.000497651052150402, 'samples': 4333568, 'steps': 8463, 'loss/train': 2.188375473022461}
-03/03/2022 23:24:10 - INFO - codeparrot_training - Step 8464: {'lr': 0.0004976503263441679, 'samples': 4334080, 'steps': 8464, 'loss/train': 2.5061044692993164}
-03/03/2022 23:24:10 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/03/2022 23:24:16 - INFO - codeparrot_training - Step 8465: {'lr': 0.0004976496004263463, 'samples': 4334592, 'steps': 8465, 'loss/train': 2.2121481895446777}
-03/03/2022 23:24:19 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/03/2022 23:24:21 - INFO - codeparrot_training - Step 8466: {'lr': 0.0004976488743969376, 'samples': 4335104, 'steps': 8466, 'loss/train': 1.8825784921646118}
-03/03/2022 23:24:24 - INFO - codeparrot_training - Step 8467: {'lr': 0.0004976481482559421, 'samples': 4335616, 'steps': 8467, 'loss/train': 1.7710628509521484}
-03/03/2022 23:24:27 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/03/2022 23:24:29 - INFO - codeparrot_training - Step 8468: {'lr': 0.0004976474220033602, 'samples': 4336128, 'steps': 8468, 'loss/train': 2.097548723220825}
-03/03/2022 23:24:33 - INFO - codeparrot_training - Step 8469: {'lr': 0.0004976466956391922, 'samples': 4336640, 'steps': 8469, 'loss/train': 1.7065820693969727}
-03/03/2022 23:24:36 - INFO - codeparrot_training - Step 8470: {'lr': 0.0004976459691634384, 'samples': 4337152, 'steps': 8470, 'loss/train': 3.24946665763855}
-03/03/2022 23:24:36 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/03/2022 23:24:41 - INFO - codeparrot_training - Step 8471: {'lr': 0.0004976452425760992, 'samples': 4337664, 'steps': 8471, 'loss/train': 2.2326724529266357}
-03/03/2022 23:24:44 - INFO - codeparrot_training - Step 8472: {'lr': 0.0004976445158771748, 'samples': 4338176, 'steps': 8472, 'loss/train': 1.6927385330200195}
-03/03/2022 23:24:44 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/03/2022 23:24:50 - INFO - codeparrot_training - Step 8473: {'lr': 0.0004976437890666657, 'samples': 4338688, 'steps': 8473, 'loss/train': 2.409126043319702}
-03/03/2022 23:24:53 - INFO - codeparrot_training - Step 8474: {'lr': 0.0004976430621445721, 'samples': 4339200, 'steps': 8474, 'loss/train': 1.795730471611023}
-03/03/2022 23:24:53 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/03/2022 23:24:59 - INFO - codeparrot_training - Step 8475: {'lr': 0.0004976423351108943, 'samples': 4339712, 'steps': 8475, 'loss/train': 2.809605121612549}
-03/03/2022 23:25:02 - INFO - codeparrot_training - Step 8476: {'lr': 0.0004976416079656328, 'samples': 4340224, 'steps': 8476, 'loss/train': 2.0301578044891357}
-03/03/2022 23:25:04 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/03/2022 23:25:07 - INFO - codeparrot_training - Step 8477: {'lr': 0.0004976408807087876, 'samples': 4340736, 'steps': 8477, 'loss/train': 1.8263821601867676}
-03/03/2022 23:25:10 - INFO - codeparrot_training - Step 8478: {'lr': 0.0004976401533403594, 'samples': 4341248, 'steps': 8478, 'loss/train': 2.0921363830566406}
-03/03/2022 23:25:12 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/03/2022 23:25:15 - INFO - codeparrot_training - Step 8479: {'lr': 0.0004976394258603484, 'samples': 4341760, 'steps': 8479, 'loss/train': 2.914506435394287}
-03/03/2022 23:25:18 - INFO - codeparrot_training - Step 8480: {'lr': 0.0004976386982687549, 'samples': 4342272, 'steps': 8480, 'loss/train': 2.7591521739959717}
-03/03/2022 23:25:20 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/03/2022 23:25:24 - INFO - codeparrot_training - Step 8481: {'lr': 0.0004976379705655791, 'samples': 4342784, 'steps': 8481, 'loss/train': 2.2470264434814453}
-03/03/2022 23:25:27 - INFO - codeparrot_training - Step 8482: {'lr': 0.0004976372427508215, 'samples': 4343296, 'steps': 8482, 'loss/train': 1.713437795639038}
-03/03/2022 23:25:29 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/03/2022 23:25:32 - INFO - codeparrot_training - Step 8483: {'lr': 0.0004976365148244824, 'samples': 4343808, 'steps': 8483, 'loss/train': 2.665875196456909}
-03/03/2022 23:25:36 - INFO - codeparrot_training - Step 8484: {'lr': 0.0004976357867865621, 'samples': 4344320, 'steps': 8484, 'loss/train': 2.733461856842041}
-03/03/2022 23:25:37 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/03/2022 23:25:41 - INFO - codeparrot_training - Step 8485: {'lr': 0.0004976350586370609, 'samples': 4344832, 'steps': 8485, 'loss/train': 1.9216703176498413}
-03/03/2022 23:25:44 - INFO - codeparrot_training - Step 8486: {'lr': 0.0004976343303759792, 'samples': 4345344, 'steps': 8486, 'loss/train': 2.4110560417175293}
-03/03/2022 23:25:45 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/03/2022 23:25:49 - INFO - codeparrot_training - Step 8487: {'lr': 0.0004976336020033174, 'samples': 4345856, 'steps': 8487, 'loss/train': 1.234717607498169}
-03/03/2022 23:25:53 - INFO - codeparrot_training - Step 8488: {'lr': 0.0004976328735190755, 'samples': 4346368, 'steps': 8488, 'loss/train': 1.0402491092681885}
-03/03/2022 23:25:54 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/03/2022 23:25:58 - INFO - codeparrot_training - Step 8489: {'lr': 0.0004976321449232542, 'samples': 4346880, 'steps': 8489, 'loss/train': 2.452604055404663}
-03/03/2022 23:26:01 - INFO - codeparrot_training - Step 8490: {'lr': 0.0004976314162158536, 'samples': 4347392, 'steps': 8490, 'loss/train': 1.207759141921997}
-03/03/2022 23:26:02 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 23:26:06 - INFO - codeparrot_training - Step 8491: {'lr': 0.0004976306873968741, 'samples': 4347904, 'steps': 8491, 'loss/train': 1.6370569467544556}
-03/03/2022 23:26:09 - INFO - codeparrot_training - Step 8492: {'lr': 0.0004976299584663161, 'samples': 4348416, 'steps': 8492, 'loss/train': 2.5653088092803955}
-03/03/2022 23:26:11 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/03/2022 23:26:15 - INFO - codeparrot_training - Step 8493: {'lr': 0.0004976292294241798, 'samples': 4348928, 'steps': 8493, 'loss/train': 1.8038333654403687}
-03/03/2022 23:26:18 - INFO - codeparrot_training - Step 8494: {'lr': 0.0004976285002704656, 'samples': 4349440, 'steps': 8494, 'loss/train': 2.341813325881958}
-03/03/2022 23:26:19 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/03/2022 23:26:23 - INFO - codeparrot_training - Step 8495: {'lr': 0.0004976277710051739, 'samples': 4349952, 'steps': 8495, 'loss/train': 2.331671714782715}
-03/03/2022 23:26:26 - INFO - codeparrot_training - Step 8496: {'lr': 0.0004976270416283049, 'samples': 4350464, 'steps': 8496, 'loss/train': 2.454941987991333}
-03/03/2022 23:26:27 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/03/2022 23:26:31 - INFO - codeparrot_training - Step 8497: {'lr': 0.000497626312139859, 'samples': 4350976, 'steps': 8497, 'loss/train': 2.547337293624878}
-03/03/2022 23:26:35 - INFO - codeparrot_training - Step 8498: {'lr': 0.0004976255825398365, 'samples': 4351488, 'steps': 8498, 'loss/train': 1.7312095165252686}
-03/03/2022 23:26:36 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/03/2022 23:26:40 - INFO - codeparrot_training - Step 8499: {'lr': 0.0004976248528282376, 'samples': 4352000, 'steps': 8499, 'loss/train': 1.7939234972000122}
-03/03/2022 23:26:43 - INFO - codeparrot_training - Step 8500: {'lr': 0.000497624123005063, 'samples': 4352512, 'steps': 8500, 'loss/train': 1.0816125869750977}
-03/03/2022 23:26:44 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/03/2022 23:26:48 - INFO - codeparrot_training - Step 8501: {'lr': 0.0004976233930703126, 'samples': 4353024, 'steps': 8501, 'loss/train': 1.043839693069458}
-03/03/2022 23:26:51 - INFO - codeparrot_training - Step 8502: {'lr': 0.000497622663023987, 'samples': 4353536, 'steps': 8502, 'loss/train': 2.2077507972717285}
-03/03/2022 23:26:52 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/03/2022 23:26:57 - INFO - codeparrot_training - Step 8503: {'lr': 0.0004976219328660864, 'samples': 4354048, 'steps': 8503, 'loss/train': 1.8096017837524414}
-03/03/2022 23:27:00 - INFO - codeparrot_training - Step 8504: {'lr': 0.0004976212025966112, 'samples': 4354560, 'steps': 8504, 'loss/train': 1.6166117191314697}
-03/03/2022 23:27:00 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/03/2022 23:27:05 - INFO - codeparrot_training - Step 8505: {'lr': 0.0004976204722155617, 'samples': 4355072, 'steps': 8505, 'loss/train': 1.9247839450836182}
-03/03/2022 23:27:09 - INFO - codeparrot_training - Step 8506: {'lr': 0.0004976197417229383, 'samples': 4355584, 'steps': 8506, 'loss/train': 2.0564146041870117}
-03/03/2022 23:27:10 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/03/2022 23:27:14 - INFO - codeparrot_training - Step 8507: {'lr': 0.0004976190111187412, 'samples': 4356096, 'steps': 8507, 'loss/train': 1.7926018238067627}
-03/03/2022 23:27:17 - INFO - codeparrot_training - Step 8508: {'lr': 0.0004976182804029708, 'samples': 4356608, 'steps': 8508, 'loss/train': 2.7728638648986816}
-03/03/2022 23:27:18 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/03/2022 23:27:22 - INFO - codeparrot_training - Step 8509: {'lr': 0.0004976175495756274, 'samples': 4357120, 'steps': 8509, 'loss/train': 2.4297778606414795}
-03/03/2022 23:27:25 - INFO - codeparrot_training - Step 8510: {'lr': 0.0004976168186367115, 'samples': 4357632, 'steps': 8510, 'loss/train': 1.8919037580490112}
-03/03/2022 23:27:26 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/03/2022 23:27:31 - INFO - codeparrot_training - Step 8511: {'lr': 0.0004976160875862231, 'samples': 4358144, 'steps': 8511, 'loss/train': 1.2046473026275635}
-03/03/2022 23:27:34 - INFO - codeparrot_training - Step 8512: {'lr': 0.0004976153564241628, 'samples': 4358656, 'steps': 8512, 'loss/train': 2.1641712188720703}
-03/03/2022 23:27:35 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/03/2022 23:27:39 - INFO - codeparrot_training - Step 8513: {'lr': 0.0004976146251505309, 'samples': 4359168, 'steps': 8513, 'loss/train': 1.6681970357894897}
-03/03/2022 23:27:42 - INFO - codeparrot_training - Step 8514: {'lr': 0.0004976138937653275, 'samples': 4359680, 'steps': 8514, 'loss/train': 2.609405994415283}
-03/03/2022 23:27:43 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/03/2022 23:27:47 - INFO - codeparrot_training - Step 8515: {'lr': 0.0004976131622685532, 'samples': 4360192, 'steps': 8515, 'loss/train': 2.5371198654174805}
-03/03/2022 23:27:50 - INFO - codeparrot_training - Step 8516: {'lr': 0.0004976124306602083, 'samples': 4360704, 'steps': 8516, 'loss/train': 1.4526430368423462}
-03/03/2022 23:27:51 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/03/2022 23:27:56 - INFO - codeparrot_training - Step 8517: {'lr': 0.0004976116989402929, 'samples': 4361216, 'steps': 8517, 'loss/train': 2.344277858734131}
-03/03/2022 23:27:59 - INFO - codeparrot_training - Step 8518: {'lr': 0.0004976109671088076, 'samples': 4361728, 'steps': 8518, 'loss/train': 2.580416202545166}
-03/03/2022 23:28:00 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/03/2022 23:28:04 - INFO - codeparrot_training - Step 8519: {'lr': 0.0004976102351657526, 'samples': 4362240, 'steps': 8519, 'loss/train': 2.180964946746826}
-03/03/2022 23:28:07 - INFO - codeparrot_training - Step 8520: {'lr': 0.0004976095031111283, 'samples': 4362752, 'steps': 8520, 'loss/train': 1.8358632326126099}
-03/03/2022 23:28:08 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/03/2022 23:28:13 - INFO - codeparrot_training - Step 8521: {'lr': 0.0004976087709449348, 'samples': 4363264, 'steps': 8521, 'loss/train': 2.674999952316284}
-03/03/2022 23:28:16 - INFO - codeparrot_training - Step 8522: {'lr': 0.0004976080386671728, 'samples': 4363776, 'steps': 8522, 'loss/train': 2.4748284816741943}
-03/03/2022 23:28:16 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/03/2022 23:28:21 - INFO - codeparrot_training - Step 8523: {'lr': 0.0004976073062778423, 'samples': 4364288, 'steps': 8523, 'loss/train': 1.219373106956482}
-03/03/2022 23:28:24 - INFO - codeparrot_training - Step 8524: {'lr': 0.0004976065737769439, 'samples': 4364800, 'steps': 8524, 'loss/train': 2.0267672538757324}
-03/03/2022 23:28:24 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/03/2022 23:28:29 - INFO - codeparrot_training - Step 8525: {'lr': 0.0004976058411644777, 'samples': 4365312, 'steps': 8525, 'loss/train': 1.40473210811615}
-03/03/2022 23:28:32 - INFO - codeparrot_training - Step 8526: {'lr': 0.0004976051084404443, 'samples': 4365824, 'steps': 8526, 'loss/train': 1.8831573724746704}
-03/03/2022 23:28:33 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/03/2022 23:28:38 - INFO - codeparrot_training - Step 8527: {'lr': 0.0004976043756048436, 'samples': 4366336, 'steps': 8527, 'loss/train': 1.7794365882873535}
-03/03/2022 23:28:41 - INFO - codeparrot_training - Step 8528: {'lr': 0.0004976036426576763, 'samples': 4366848, 'steps': 8528, 'loss/train': 2.550095319747925}
-03/03/2022 23:28:41 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/03/2022 23:28:46 - INFO - codeparrot_training - Step 8529: {'lr': 0.0004976029095989427, 'samples': 4367360, 'steps': 8529, 'loss/train': 1.1749022006988525}
-03/03/2022 23:28:49 - INFO - codeparrot_training - Step 8530: {'lr': 0.000497602176428643, 'samples': 4367872, 'steps': 8530, 'loss/train': 2.0656399726867676}
-03/03/2022 23:28:49 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/03/2022 23:28:55 - INFO - codeparrot_training - Step 8531: {'lr': 0.0004976014431467775, 'samples': 4368384, 'steps': 8531, 'loss/train': 2.084627151489258}
-03/03/2022 23:28:58 - INFO - codeparrot_training - Step 8532: {'lr': 0.0004976007097533467, 'samples': 4368896, 'steps': 8532, 'loss/train': 2.363006830215454}
-03/03/2022 23:28:58 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/03/2022 23:29:03 - INFO - codeparrot_training - Step 8533: {'lr': 0.0004975999762483509, 'samples': 4369408, 'steps': 8533, 'loss/train': 2.726539134979248}
-03/03/2022 23:29:06 - INFO - codeparrot_training - Step 8534: {'lr': 0.0004975992426317902, 'samples': 4369920, 'steps': 8534, 'loss/train': 1.547489881515503}
-03/03/2022 23:29:06 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/03/2022 23:29:12 - INFO - codeparrot_training - Step 8535: {'lr': 0.0004975985089036652, 'samples': 4370432, 'steps': 8535, 'loss/train': 1.8607453107833862}
-03/03/2022 23:29:14 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/03/2022 23:29:17 - INFO - codeparrot_training - Step 8536: {'lr': 0.0004975977750639761, 'samples': 4370944, 'steps': 8536, 'loss/train': 2.990778684616089}
-03/03/2022 23:29:20 - INFO - codeparrot_training - Step 8537: {'lr': 0.0004975970411127233, 'samples': 4371456, 'steps': 8537, 'loss/train': 2.2980430126190186}
-03/03/2022 23:29:23 - INFO - codeparrot_training - Step 8538: {'lr': 0.0004975963070499071, 'samples': 4371968, 'steps': 8538, 'loss/train': 1.737725019454956}
-03/03/2022 23:29:23 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/03/2022 23:29:29 - INFO - codeparrot_training - Step 8539: {'lr': 0.0004975955728755277, 'samples': 4372480, 'steps': 8539, 'loss/train': 1.6278846263885498}
-03/03/2022 23:29:32 - INFO - codeparrot_training - Step 8540: {'lr': 0.0004975948385895858, 'samples': 4372992, 'steps': 8540, 'loss/train': 2.256767749786377}
-03/03/2022 23:29:32 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/03/2022 23:29:37 - INFO - codeparrot_training - Step 8541: {'lr': 0.0004975941041920813, 'samples': 4373504, 'steps': 8541, 'loss/train': 2.2388601303100586}
-03/03/2022 23:29:40 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/03/2022 23:29:42 - INFO - codeparrot_training - Step 8542: {'lr': 0.0004975933696830147, 'samples': 4374016, 'steps': 8542, 'loss/train': 3.159362316131592}
-03/03/2022 23:29:45 - INFO - codeparrot_training - Step 8543: {'lr': 0.0004975926350623864, 'samples': 4374528, 'steps': 8543, 'loss/train': 1.6996358633041382}
-03/03/2022 23:29:48 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/03/2022 23:29:51 - INFO - codeparrot_training - Step 8544: {'lr': 0.0004975919003301967, 'samples': 4375040, 'steps': 8544, 'loss/train': 2.141484022140503}
-03/03/2022 23:29:54 - INFO - codeparrot_training - Step 8545: {'lr': 0.0004975911654864459, 'samples': 4375552, 'steps': 8545, 'loss/train': 2.544144868850708}
-03/03/2022 23:29:57 - INFO - codeparrot_training - Step 8546: {'lr': 0.0004975904305311344, 'samples': 4376064, 'steps': 8546, 'loss/train': 1.7544958591461182}
-03/03/2022 23:29:57 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/03/2022 23:30:02 - INFO - codeparrot_training - Step 8547: {'lr': 0.0004975896954642623, 'samples': 4376576, 'steps': 8547, 'loss/train': 0.46599289774894714}
-03/03/2022 23:30:06 - INFO - codeparrot_training - Step 8548: {'lr': 0.0004975889602858303, 'samples': 4377088, 'steps': 8548, 'loss/train': 2.5512311458587646}
-03/03/2022 23:30:06 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/03/2022 23:30:11 - INFO - codeparrot_training - Step 8549: {'lr': 0.0004975882249958385, 'samples': 4377600, 'steps': 8549, 'loss/train': 2.1173627376556396}
-03/03/2022 23:30:14 - INFO - codeparrot_training - Step 8550: {'lr': 0.0004975874895942872, 'samples': 4378112, 'steps': 8550, 'loss/train': 1.9867159128189087}
-03/03/2022 23:30:14 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/03/2022 23:30:19 - INFO - codeparrot_training - Step 8551: {'lr': 0.0004975867540811768, 'samples': 4378624, 'steps': 8551, 'loss/train': 2.0904812812805176}
-03/03/2022 23:30:22 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/03/2022 23:30:25 - INFO - codeparrot_training - Step 8552: {'lr': 0.0004975860184565076, 'samples': 4379136, 'steps': 8552, 'loss/train': 2.0864601135253906}
-03/03/2022 23:30:28 - INFO - codeparrot_training - Step 8553: {'lr': 0.0004975852827202801, 'samples': 4379648, 'steps': 8553, 'loss/train': 1.7809739112854004}
-03/03/2022 23:30:30 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/03/2022 23:30:33 - INFO - codeparrot_training - Step 8554: {'lr': 0.0004975845468724944, 'samples': 4380160, 'steps': 8554, 'loss/train': 1.9034217596054077}
-03/03/2022 23:30:36 - INFO - codeparrot_training - Step 8555: {'lr': 0.0004975838109131509, 'samples': 4380672, 'steps': 8555, 'loss/train': 2.4111487865448}
-03/03/2022 23:30:39 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/03/2022 23:30:41 - INFO - codeparrot_training - Step 8556: {'lr': 0.0004975830748422499, 'samples': 4381184, 'steps': 8556, 'loss/train': 2.0705790519714355}
-03/03/2022 23:30:44 - INFO - codeparrot_training - Step 8557: {'lr': 0.0004975823386597918, 'samples': 4381696, 'steps': 8557, 'loss/train': 1.592627763748169}
-03/03/2022 23:30:47 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/03/2022 23:30:50 - INFO - codeparrot_training - Step 8558: {'lr': 0.000497581602365777, 'samples': 4382208, 'steps': 8558, 'loss/train': 2.127572774887085}
-03/03/2022 23:30:53 - INFO - codeparrot_training - Step 8559: {'lr': 0.0004975808659602058, 'samples': 4382720, 'steps': 8559, 'loss/train': 2.1885862350463867}
-03/03/2022 23:30:56 - INFO - codeparrot_training - Step 8560: {'lr': 0.0004975801294430784, 'samples': 4383232, 'steps': 8560, 'loss/train': 1.9921766519546509}
-03/03/2022 23:30:57 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/03/2022 23:31:01 - INFO - codeparrot_training - Step 8561: {'lr': 0.0004975793928143952, 'samples': 4383744, 'steps': 8561, 'loss/train': 2.665879964828491}
-03/03/2022 23:31:05 - INFO - codeparrot_training - Step 8562: {'lr': 0.0004975786560741566, 'samples': 4384256, 'steps': 8562, 'loss/train': 0.8980951309204102}
-03/03/2022 23:31:10 - INFO - codeparrot_training - Step 8563: {'lr': 0.0004975779192223629, 'samples': 4384768, 'steps': 8563, 'loss/train': 2.356776237487793}
-03/03/2022 23:31:13 - INFO - codeparrot_training - Step 8564: {'lr': 0.0004975771822590143, 'samples': 4385280, 'steps': 8564, 'loss/train': 2.1440420150756836}
-03/03/2022 23:31:14 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/03/2022 23:31:18 - INFO - codeparrot_training - Step 8565: {'lr': 0.0004975764451841114, 'samples': 4385792, 'steps': 8565, 'loss/train': 2.018719434738159}
-03/03/2022 23:31:21 - INFO - codeparrot_training - Step 8566: {'lr': 0.0004975757079976542, 'samples': 4386304, 'steps': 8566, 'loss/train': 1.663474202156067}
-03/03/2022 23:31:22 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/03/2022 23:31:27 - INFO - codeparrot_training - Step 8567: {'lr': 0.0004975749706996433, 'samples': 4386816, 'steps': 8567, 'loss/train': 1.7948946952819824}
-03/03/2022 23:31:30 - INFO - codeparrot_training - Step 8568: {'lr': 0.0004975742332900789, 'samples': 4387328, 'steps': 8568, 'loss/train': 2.6362433433532715}
-03/03/2022 23:31:30 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/03/2022 23:31:35 - INFO - codeparrot_training - Step 8569: {'lr': 0.0004975734957689614, 'samples': 4387840, 'steps': 8569, 'loss/train': 2.7712655067443848}
-03/03/2022 23:31:38 - INFO - codeparrot_training - Step 8570: {'lr': 0.0004975727581362911, 'samples': 4388352, 'steps': 8570, 'loss/train': 1.9175224304199219}
-03/03/2022 23:31:38 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/03/2022 23:31:43 - INFO - codeparrot_training - Step 8571: {'lr': 0.0004975720203920683, 'samples': 4388864, 'steps': 8571, 'loss/train': 2.578338861465454}
-03/03/2022 23:31:47 - INFO - codeparrot_training - Step 8572: {'lr': 0.0004975712825362934, 'samples': 4389376, 'steps': 8572, 'loss/train': 1.9836405515670776}
-03/03/2022 23:31:47 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/03/2022 23:31:52 - INFO - codeparrot_training - Step 8573: {'lr': 0.0004975705445689668, 'samples': 4389888, 'steps': 8573, 'loss/train': 2.013310194015503}
-03/03/2022 23:31:55 - INFO - codeparrot_training - Step 8574: {'lr': 0.0004975698064900886, 'samples': 4390400, 'steps': 8574, 'loss/train': 2.626272201538086}
-03/03/2022 23:31:55 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/03/2022 23:32:00 - INFO - codeparrot_training - Step 8575: {'lr': 0.0004975690682996592, 'samples': 4390912, 'steps': 8575, 'loss/train': 2.4620683193206787}
-03/03/2022 23:32:04 - INFO - codeparrot_training - Step 8576: {'lr': 0.0004975683299976791, 'samples': 4391424, 'steps': 8576, 'loss/train': 2.2737104892730713}
-03/03/2022 23:32:04 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/03/2022 23:32:09 - INFO - codeparrot_training - Step 8577: {'lr': 0.0004975675915841485, 'samples': 4391936, 'steps': 8577, 'loss/train': 2.284379005432129}
-03/03/2022 23:32:12 - INFO - codeparrot_training - Step 8578: {'lr': 0.0004975668530590679, 'samples': 4392448, 'steps': 8578, 'loss/train': 1.4472514390945435}
-03/03/2022 23:32:12 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/03/2022 23:32:17 - INFO - codeparrot_training - Step 8579: {'lr': 0.0004975661144224374, 'samples': 4392960, 'steps': 8579, 'loss/train': 1.2153924703598022}
-03/03/2022 23:32:20 - INFO - codeparrot_training - Step 8580: {'lr': 0.0004975653756742574, 'samples': 4393472, 'steps': 8580, 'loss/train': 2.2728331089019775}
-03/03/2022 23:32:21 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/03/2022 23:32:26 - INFO - codeparrot_training - Step 8581: {'lr': 0.0004975646368145282, 'samples': 4393984, 'steps': 8581, 'loss/train': 2.5746471881866455}
-03/03/2022 23:32:29 - INFO - codeparrot_training - Step 8582: {'lr': 0.0004975638978432503, 'samples': 4394496, 'steps': 8582, 'loss/train': 1.6844048500061035}
-03/03/2022 23:32:29 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/03/2022 23:32:34 - INFO - codeparrot_training - Step 8583: {'lr': 0.0004975631587604239, 'samples': 4395008, 'steps': 8583, 'loss/train': 1.7200723886489868}
-03/03/2022 23:32:37 - INFO - codeparrot_training - Step 8584: {'lr': 0.0004975624195660494, 'samples': 4395520, 'steps': 8584, 'loss/train': 1.7621732950210571}
-03/03/2022 23:32:37 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/03/2022 23:32:42 - INFO - codeparrot_training - Step 8585: {'lr': 0.0004975616802601271, 'samples': 4396032, 'steps': 8585, 'loss/train': 1.9271119832992554}
-03/03/2022 23:32:46 - INFO - codeparrot_training - Step 8586: {'lr': 0.0004975609408426572, 'samples': 4396544, 'steps': 8586, 'loss/train': 2.4138731956481934}
-03/03/2022 23:32:46 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/03/2022 23:32:51 - INFO - codeparrot_training - Step 8587: {'lr': 0.0004975602013136403, 'samples': 4397056, 'steps': 8587, 'loss/train': 2.055150032043457}
-03/03/2022 23:32:54 - INFO - codeparrot_training - Step 8588: {'lr': 0.0004975594616730766, 'samples': 4397568, 'steps': 8588, 'loss/train': 1.833652138710022}
-03/03/2022 23:32:54 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/03/2022 23:32:59 - INFO - codeparrot_training - Step 8589: {'lr': 0.0004975587219209663, 'samples': 4398080, 'steps': 8589, 'loss/train': 1.913150668144226}
-03/03/2022 23:33:02 - INFO - codeparrot_training - Step 8590: {'lr': 0.0004975579820573099, 'samples': 4398592, 'steps': 8590, 'loss/train': 1.507430911064148}
-03/03/2022 23:33:03 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/03/2022 23:33:08 - INFO - codeparrot_training - Step 8591: {'lr': 0.0004975572420821078, 'samples': 4399104, 'steps': 8591, 'loss/train': 2.64015531539917}
-03/03/2022 23:33:11 - INFO - codeparrot_training - Step 8592: {'lr': 0.0004975565019953601, 'samples': 4399616, 'steps': 8592, 'loss/train': 1.2169023752212524}
-03/03/2022 23:33:11 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/03/2022 23:33:16 - INFO - codeparrot_training - Step 8593: {'lr': 0.0004975557617970673, 'samples': 4400128, 'steps': 8593, 'loss/train': 1.7407909631729126}
-03/03/2022 23:33:19 - INFO - codeparrot_training - Step 8594: {'lr': 0.0004975550214872296, 'samples': 4400640, 'steps': 8594, 'loss/train': 1.3724608421325684}
-03/03/2022 23:33:20 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/03/2022 23:33:25 - INFO - codeparrot_training - Step 8595: {'lr': 0.0004975542810658476, 'samples': 4401152, 'steps': 8595, 'loss/train': 1.6591908931732178}
-03/03/2022 23:33:28 - INFO - codeparrot_training - Step 8596: {'lr': 0.0004975535405329213, 'samples': 4401664, 'steps': 8596, 'loss/train': 2.29133939743042}
-03/03/2022 23:33:28 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/03/2022 23:33:33 - INFO - codeparrot_training - Step 8597: {'lr': 0.0004975527998884513, 'samples': 4402176, 'steps': 8597, 'loss/train': 3.256826877593994}
-03/03/2022 23:33:36 - INFO - codeparrot_training - Step 8598: {'lr': 0.0004975520591324378, 'samples': 4402688, 'steps': 8598, 'loss/train': 1.3493393659591675}
-03/03/2022 23:33:36 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/03/2022 23:33:41 - INFO - codeparrot_training - Step 8599: {'lr': 0.0004975513182648812, 'samples': 4403200, 'steps': 8599, 'loss/train': 1.8076725006103516}
-03/03/2022 23:33:44 - INFO - codeparrot_training - Step 8600: {'lr': 0.0004975505772857818, 'samples': 4403712, 'steps': 8600, 'loss/train': 1.853676199913025}
-03/03/2022 23:33:45 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/03/2022 23:33:50 - INFO - codeparrot_training - Step 8601: {'lr': 0.0004975498361951398, 'samples': 4404224, 'steps': 8601, 'loss/train': 0.7719811797142029}
-03/03/2022 23:33:53 - INFO - codeparrot_training - Step 8602: {'lr': 0.0004975490949929558, 'samples': 4404736, 'steps': 8602, 'loss/train': 2.2545902729034424}
-03/03/2022 23:33:53 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/03/2022 23:33:59 - INFO - codeparrot_training - Step 8603: {'lr': 0.00049754835367923, 'samples': 4405248, 'steps': 8603, 'loss/train': 2.2370758056640625}
-03/03/2022 23:34:02 - INFO - codeparrot_training - Step 8604: {'lr': 0.0004975476122539627, 'samples': 4405760, 'steps': 8604, 'loss/train': 2.1304242610931396}
-03/03/2022 23:34:03 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/03/2022 23:34:07 - INFO - codeparrot_training - Step 8605: {'lr': 0.0004975468707171542, 'samples': 4406272, 'steps': 8605, 'loss/train': 1.7687084674835205}
-03/03/2022 23:34:10 - INFO - codeparrot_training - Step 8606: {'lr': 0.000497546129068805, 'samples': 4406784, 'steps': 8606, 'loss/train': 2.1115710735321045}
-03/03/2022 23:34:11 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/03/2022 23:34:15 - INFO - codeparrot_training - Step 8607: {'lr': 0.0004975453873089153, 'samples': 4407296, 'steps': 8607, 'loss/train': 2.5781409740448}
-03/03/2022 23:34:19 - INFO - codeparrot_training - Step 8608: {'lr': 0.0004975446454374854, 'samples': 4407808, 'steps': 8608, 'loss/train': 2.167065382003784}
-03/03/2022 23:34:19 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/03/2022 23:34:24 - INFO - codeparrot_training - Step 8609: {'lr': 0.0004975439034545158, 'samples': 4408320, 'steps': 8609, 'loss/train': 2.9868388175964355}
-03/03/2022 23:34:27 - INFO - codeparrot_training - Step 8610: {'lr': 0.0004975431613600067, 'samples': 4408832, 'steps': 8610, 'loss/train': 0.47359707951545715}
-03/03/2022 23:34:28 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/03/2022 23:34:32 - INFO - codeparrot_training - Step 8611: {'lr': 0.0004975424191539585, 'samples': 4409344, 'steps': 8611, 'loss/train': 2.18105411529541}
-03/03/2022 23:34:36 - INFO - codeparrot_training - Step 8612: {'lr': 0.0004975416768363715, 'samples': 4409856, 'steps': 8612, 'loss/train': 2.406921625137329}
-03/03/2022 23:34:37 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/03/2022 23:34:41 - INFO - codeparrot_training - Step 8613: {'lr': 0.0004975409344072459, 'samples': 4410368, 'steps': 8613, 'loss/train': 2.245800733566284}
-03/03/2022 23:34:44 - INFO - codeparrot_training - Step 8614: {'lr': 0.0004975401918665823, 'samples': 4410880, 'steps': 8614, 'loss/train': 1.6691192388534546}
-03/03/2022 23:34:45 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/03/2022 23:34:49 - INFO - codeparrot_training - Step 8615: {'lr': 0.0004975394492143808, 'samples': 4411392, 'steps': 8615, 'loss/train': 1.426339030265808}
-03/03/2022 23:34:52 - INFO - codeparrot_training - Step 8616: {'lr': 0.0004975387064506421, 'samples': 4411904, 'steps': 8616, 'loss/train': 1.29306960105896}
-03/03/2022 23:34:53 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/03/2022 23:34:57 - INFO - codeparrot_training - Step 8617: {'lr': 0.000497537963575366, 'samples': 4412416, 'steps': 8617, 'loss/train': 1.6632466316223145}
-03/03/2022 23:35:01 - INFO - codeparrot_training - Step 8618: {'lr': 0.0004975372205885533, 'samples': 4412928, 'steps': 8618, 'loss/train': 2.031140089035034}
-03/03/2022 23:35:01 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/03/2022 23:35:06 - INFO - codeparrot_training - Step 8619: {'lr': 0.0004975364774902041, 'samples': 4413440, 'steps': 8619, 'loss/train': 1.5191601514816284}
-03/03/2022 23:35:09 - INFO - codeparrot_training - Step 8620: {'lr': 0.0004975357342803187, 'samples': 4413952, 'steps': 8620, 'loss/train': 1.9551352262496948}
-03/03/2022 23:35:09 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/03/2022 23:35:14 - INFO - codeparrot_training - Step 8621: {'lr': 0.0004975349909588976, 'samples': 4414464, 'steps': 8621, 'loss/train': 2.1666903495788574}
-03/03/2022 23:35:17 - INFO - codeparrot_training - Step 8622: {'lr': 0.000497534247525941, 'samples': 4414976, 'steps': 8622, 'loss/train': 1.807737112045288}
-03/03/2022 23:35:18 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/03/2022 23:35:23 - INFO - codeparrot_training - Step 8623: {'lr': 0.0004975335039814493, 'samples': 4415488, 'steps': 8623, 'loss/train': 2.768618583679199}
-03/03/2022 23:35:26 - INFO - codeparrot_training - Step 8624: {'lr': 0.0004975327603254229, 'samples': 4416000, 'steps': 8624, 'loss/train': 1.6468424797058105}
-03/03/2022 23:35:26 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/03/2022 23:35:31 - INFO - codeparrot_training - Step 8625: {'lr': 0.000497532016557862, 'samples': 4416512, 'steps': 8625, 'loss/train': 2.1786344051361084}
-03/03/2022 23:35:34 - INFO - codeparrot_training - Step 8626: {'lr': 0.0004975312726787671, 'samples': 4417024, 'steps': 8626, 'loss/train': 2.126168727874756}
-03/03/2022 23:35:35 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/03/2022 23:35:40 - INFO - codeparrot_training - Step 8627: {'lr': 0.0004975305286881383, 'samples': 4417536, 'steps': 8627, 'loss/train': 3.1245484352111816}
-03/03/2022 23:35:43 - INFO - codeparrot_training - Step 8628: {'lr': 0.0004975297845859761, 'samples': 4418048, 'steps': 8628, 'loss/train': 2.080662965774536}
-03/03/2022 23:35:43 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/03/2022 23:35:48 - INFO - codeparrot_training - Step 8629: {'lr': 0.0004975290403722807, 'samples': 4418560, 'steps': 8629, 'loss/train': 1.949702501296997}
-03/03/2022 23:35:51 - INFO - codeparrot_training - Step 8630: {'lr': 0.0004975282960470527, 'samples': 4419072, 'steps': 8630, 'loss/train': 1.9127442836761475}
-03/03/2022 23:35:52 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/03/2022 23:35:56 - INFO - codeparrot_training - Step 8631: {'lr': 0.0004975275516102922, 'samples': 4419584, 'steps': 8631, 'loss/train': 2.6513895988464355}
-03/03/2022 23:35:59 - INFO - codeparrot_training - Step 8632: {'lr': 0.0004975268070619996, 'samples': 4420096, 'steps': 8632, 'loss/train': 1.7231444120407104}
-03/03/2022 23:36:00 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/03/2022 23:36:05 - INFO - codeparrot_training - Step 8633: {'lr': 0.0004975260624021752, 'samples': 4420608, 'steps': 8633, 'loss/train': 2.093153238296509}
-03/03/2022 23:36:08 - INFO - codeparrot_training - Step 8634: {'lr': 0.0004975253176308194, 'samples': 4421120, 'steps': 8634, 'loss/train': 2.5245909690856934}
-03/03/2022 23:36:08 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/03/2022 23:36:13 - INFO - codeparrot_training - Step 8635: {'lr': 0.0004975245727479325, 'samples': 4421632, 'steps': 8635, 'loss/train': 1.8935472965240479}
-03/03/2022 23:36:16 - INFO - codeparrot_training - Step 8636: {'lr': 0.0004975238277535149, 'samples': 4422144, 'steps': 8636, 'loss/train': 2.09806752204895}
-03/03/2022 23:36:16 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/03/2022 23:36:21 - INFO - codeparrot_training - Step 8637: {'lr': 0.0004975230826475669, 'samples': 4422656, 'steps': 8637, 'loss/train': 1.9920990467071533}
-03/03/2022 23:36:25 - INFO - codeparrot_training - Step 8638: {'lr': 0.0004975223374300887, 'samples': 4423168, 'steps': 8638, 'loss/train': 1.9672785997390747}
-03/03/2022 23:36:25 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/03/2022 23:36:30 - INFO - codeparrot_training - Step 8639: {'lr': 0.0004975215921010808, 'samples': 4423680, 'steps': 8639, 'loss/train': 2.4270200729370117}
-03/03/2022 23:36:33 - INFO - codeparrot_training - Step 8640: {'lr': 0.0004975208466605435, 'samples': 4424192, 'steps': 8640, 'loss/train': 1.5435935258865356}
-03/03/2022 23:36:33 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/03/2022 23:36:38 - INFO - codeparrot_training - Step 8641: {'lr': 0.0004975201011084773, 'samples': 4424704, 'steps': 8641, 'loss/train': 1.5562968254089355}
-03/03/2022 23:36:41 - INFO - codeparrot_training - Step 8642: {'lr': 0.0004975193554448821, 'samples': 4425216, 'steps': 8642, 'loss/train': 2.1791114807128906}
-03/03/2022 23:36:41 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/03/2022 23:36:47 - INFO - codeparrot_training - Step 8643: {'lr': 0.0004975186096697585, 'samples': 4425728, 'steps': 8643, 'loss/train': 2.543915033340454}
-03/03/2022 23:36:50 - INFO - codeparrot_training - Step 8644: {'lr': 0.000497517863783107, 'samples': 4426240, 'steps': 8644, 'loss/train': 2.2008578777313232}
-03/03/2022 23:36:50 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/03/2022 23:36:55 - INFO - codeparrot_training - Step 8645: {'lr': 0.0004975171177849277, 'samples': 4426752, 'steps': 8645, 'loss/train': 6.673060894012451}
-03/03/2022 23:36:58 - INFO - codeparrot_training - Step 8646: {'lr': 0.000497516371675221, 'samples': 4427264, 'steps': 8646, 'loss/train': 2.144001007080078}
-03/03/2022 23:36:59 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/03/2022 23:37:04 - INFO - codeparrot_training - Step 8647: {'lr': 0.0004975156254539873, 'samples': 4427776, 'steps': 8647, 'loss/train': 2.186833143234253}
-03/03/2022 23:37:07 - INFO - codeparrot_training - Step 8648: {'lr': 0.0004975148791212269, 'samples': 4428288, 'steps': 8648, 'loss/train': 1.8771220445632935}
-03/03/2022 23:37:07 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/03/2022 23:37:12 - INFO - codeparrot_training - Step 8649: {'lr': 0.00049751413267694, 'samples': 4428800, 'steps': 8649, 'loss/train': 1.9925810098648071}
-03/03/2022 23:37:15 - INFO - codeparrot_training - Step 8650: {'lr': 0.000497513386121127, 'samples': 4429312, 'steps': 8650, 'loss/train': 2.2858805656433105}
-03/03/2022 23:37:16 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/03/2022 23:37:20 - INFO - codeparrot_training - Step 8651: {'lr': 0.0004975126394537884, 'samples': 4429824, 'steps': 8651, 'loss/train': 1.9893391132354736}
-03/03/2022 23:37:24 - INFO - codeparrot_training - Step 8652: {'lr': 0.0004975118926749245, 'samples': 4430336, 'steps': 8652, 'loss/train': 3.1702373027801514}
-03/03/2022 23:37:24 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/03/2022 23:37:29 - INFO - codeparrot_training - Step 8653: {'lr': 0.0004975111457845354, 'samples': 4430848, 'steps': 8653, 'loss/train': 2.084091901779175}
-03/03/2022 23:37:32 - INFO - codeparrot_training - Step 8654: {'lr': 0.0004975103987826217, 'samples': 4431360, 'steps': 8654, 'loss/train': 1.345037817955017}
-03/03/2022 23:37:32 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/03/2022 23:37:37 - INFO - codeparrot_training - Step 8655: {'lr': 0.0004975096516691836, 'samples': 4431872, 'steps': 8655, 'loss/train': 1.985263466835022}
-03/03/2022 23:37:40 - INFO - codeparrot_training - Step 8656: {'lr': 0.0004975089044442215, 'samples': 4432384, 'steps': 8656, 'loss/train': 2.9642913341522217}
-03/03/2022 23:37:41 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/03/2022 23:37:46 - INFO - codeparrot_training - Step 8657: {'lr': 0.0004975081571077357, 'samples': 4432896, 'steps': 8657, 'loss/train': 2.535926103591919}
-03/03/2022 23:37:49 - INFO - codeparrot_training - Step 8658: {'lr': 0.0004975074096597265, 'samples': 4433408, 'steps': 8658, 'loss/train': 1.9013389348983765}
-03/03/2022 23:37:49 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/03/2022 23:37:54 - INFO - codeparrot_training - Step 8659: {'lr': 0.0004975066621001943, 'samples': 4433920, 'steps': 8659, 'loss/train': 1.6550710201263428}
-03/03/2022 23:37:57 - INFO - codeparrot_training - Step 8660: {'lr': 0.0004975059144291394, 'samples': 4434432, 'steps': 8660, 'loss/train': 2.0921401977539062}
-03/03/2022 23:37:57 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/03/2022 23:38:03 - INFO - codeparrot_training - Step 8661: {'lr': 0.0004975051666465622, 'samples': 4434944, 'steps': 8661, 'loss/train': 1.5678551197052002}
-03/03/2022 23:38:06 - INFO - codeparrot_training - Step 8662: {'lr': 0.0004975044187524629, 'samples': 4435456, 'steps': 8662, 'loss/train': 2.2054617404937744}
-03/03/2022 23:38:07 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/03/2022 23:38:11 - INFO - codeparrot_training - Step 8663: {'lr': 0.000497503670746842, 'samples': 4435968, 'steps': 8663, 'loss/train': 1.4855926036834717}
-03/03/2022 23:38:14 - INFO - codeparrot_training - Step 8664: {'lr': 0.0004975029226296998, 'samples': 4436480, 'steps': 8664, 'loss/train': 2.527010917663574}
-03/03/2022 23:38:15 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/03/2022 23:38:20 - INFO - codeparrot_training - Step 8665: {'lr': 0.0004975021744010365, 'samples': 4436992, 'steps': 8665, 'loss/train': 2.1621201038360596}
-03/03/2022 23:38:23 - INFO - codeparrot_training - Step 8666: {'lr': 0.0004975014260608527, 'samples': 4437504, 'steps': 8666, 'loss/train': 1.8416367769241333}
-03/03/2022 23:38:23 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/03/2022 23:38:28 - INFO - codeparrot_training - Step 8667: {'lr': 0.0004975006776091484, 'samples': 4438016, 'steps': 8667, 'loss/train': 2.391775608062744}
-03/03/2022 23:38:31 - INFO - codeparrot_training - Step 8668: {'lr': 0.0004974999290459243, 'samples': 4438528, 'steps': 8668, 'loss/train': 1.4248090982437134}
-03/03/2022 23:38:31 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/03/2022 23:38:36 - INFO - codeparrot_training - Step 8669: {'lr': 0.0004974991803711803, 'samples': 4439040, 'steps': 8669, 'loss/train': 2.3064043521881104}
-03/03/2022 23:38:40 - INFO - codeparrot_training - Step 8670: {'lr': 0.0004974984315849172, 'samples': 4439552, 'steps': 8670, 'loss/train': 2.0174665451049805}
-03/03/2022 23:38:40 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/03/2022 23:38:45 - INFO - codeparrot_training - Step 8671: {'lr': 0.000497497682687135, 'samples': 4440064, 'steps': 8671, 'loss/train': 2.048124074935913}
-03/03/2022 23:38:48 - INFO - codeparrot_training - Step 8672: {'lr': 0.0004974969336778343, 'samples': 4440576, 'steps': 8672, 'loss/train': 2.17170786857605}
-03/03/2022 23:38:49 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/03/2022 23:38:54 - INFO - codeparrot_training - Step 8673: {'lr': 0.0004974961845570152, 'samples': 4441088, 'steps': 8673, 'loss/train': 0.7575506567955017}
-03/03/2022 23:38:57 - INFO - codeparrot_training - Step 8674: {'lr': 0.0004974954353246781, 'samples': 4441600, 'steps': 8674, 'loss/train': 2.5376527309417725}
-03/03/2022 23:38:57 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/03/2022 23:39:02 - INFO - codeparrot_training - Step 8675: {'lr': 0.0004974946859808235, 'samples': 4442112, 'steps': 8675, 'loss/train': 2.2967138290405273}
-03/03/2022 23:39:05 - INFO - codeparrot_training - Step 8676: {'lr': 0.0004974939365254515, 'samples': 4442624, 'steps': 8676, 'loss/train': 2.8941142559051514}
-03/03/2022 23:39:05 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/03/2022 23:39:10 - INFO - codeparrot_training - Step 8677: {'lr': 0.0004974931869585626, 'samples': 4443136, 'steps': 8677, 'loss/train': 1.9112153053283691}
-03/03/2022 23:39:14 - INFO - codeparrot_training - Step 8678: {'lr': 0.0004974924372801572, 'samples': 4443648, 'steps': 8678, 'loss/train': 1.7010036706924438}
-03/03/2022 23:39:14 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/03/2022 23:39:19 - INFO - codeparrot_training - Step 8679: {'lr': 0.0004974916874902353, 'samples': 4444160, 'steps': 8679, 'loss/train': 2.577451467514038}
-03/03/2022 23:39:22 - INFO - codeparrot_training - Step 8680: {'lr': 0.0004974909375887976, 'samples': 4444672, 'steps': 8680, 'loss/train': 1.3795115947723389}
-03/03/2022 23:39:22 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/03/2022 23:39:27 - INFO - codeparrot_training - Step 8681: {'lr': 0.0004974901875758444, 'samples': 4445184, 'steps': 8681, 'loss/train': 2.165842294692993}
-03/03/2022 23:39:30 - INFO - codeparrot_training - Step 8682: {'lr': 0.0004974894374513757, 'samples': 4445696, 'steps': 8682, 'loss/train': 2.086031198501587}
-03/03/2022 23:39:30 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/03/2022 23:39:36 - INFO - codeparrot_training - Step 8683: {'lr': 0.0004974886872153922, 'samples': 4446208, 'steps': 8683, 'loss/train': 2.570136070251465}
-03/03/2022 23:39:39 - INFO - codeparrot_training - Step 8684: {'lr': 0.0004974879368678942, 'samples': 4446720, 'steps': 8684, 'loss/train': 2.2630457878112793}
-03/03/2022 23:39:39 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/03/2022 23:39:44 - INFO - codeparrot_training - Step 8685: {'lr': 0.0004974871864088818, 'samples': 4447232, 'steps': 8685, 'loss/train': 1.6466584205627441}
-03/03/2022 23:39:47 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/03/2022 23:39:49 - INFO - codeparrot_training - Step 8686: {'lr': 0.0004974864358383555, 'samples': 4447744, 'steps': 8686, 'loss/train': 2.2082338333129883}
-03/03/2022 23:39:53 - INFO - codeparrot_training - Step 8687: {'lr': 0.0004974856851563158, 'samples': 4448256, 'steps': 8687, 'loss/train': 2.1419451236724854}
-03/03/2022 23:39:55 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/03/2022 23:39:58 - INFO - codeparrot_training - Step 8688: {'lr': 0.0004974849343627628, 'samples': 4448768, 'steps': 8688, 'loss/train': 1.871909499168396}
-03/03/2022 23:40:01 - INFO - codeparrot_training - Step 8689: {'lr': 0.0004974841834576968, 'samples': 4449280, 'steps': 8689, 'loss/train': 2.0364668369293213}
-03/03/2022 23:40:04 - INFO - codeparrot_training - Step 8690: {'lr': 0.0004974834324411183, 'samples': 4449792, 'steps': 8690, 'loss/train': 1.41515052318573}
-03/03/2022 23:40:04 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/03/2022 23:40:10 - INFO - codeparrot_training - Step 8691: {'lr': 0.0004974826813130276, 'samples': 4450304, 'steps': 8691, 'loss/train': 2.0623888969421387}
-03/03/2022 23:40:12 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/03/2022 23:40:15 - INFO - codeparrot_training - Step 8692: {'lr': 0.000497481930073425, 'samples': 4450816, 'steps': 8692, 'loss/train': 1.6584738492965698}
-03/03/2022 23:40:18 - INFO - codeparrot_training - Step 8693: {'lr': 0.000497481178722311, 'samples': 4451328, 'steps': 8693, 'loss/train': 2.9793617725372314}
-03/03/2022 23:40:21 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/03/2022 23:40:23 - INFO - codeparrot_training - Step 8694: {'lr': 0.0004974804272596857, 'samples': 4451840, 'steps': 8694, 'loss/train': 1.9432551860809326}
-03/03/2022 23:40:26 - INFO - codeparrot_training - Step 8695: {'lr': 0.0004974796756855494, 'samples': 4452352, 'steps': 8695, 'loss/train': 0.13267189264297485}
-03/03/2022 23:40:29 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/03/2022 23:40:32 - INFO - codeparrot_training - Step 8696: {'lr': 0.0004974789239999027, 'samples': 4452864, 'steps': 8696, 'loss/train': 2.0519790649414062}
-03/03/2022 23:40:35 - INFO - codeparrot_training - Step 8697: {'lr': 0.0004974781722027459, 'samples': 4453376, 'steps': 8697, 'loss/train': 2.221073627471924}
-03/03/2022 23:40:37 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/03/2022 23:40:40 - INFO - codeparrot_training - Step 8698: {'lr': 0.0004974774202940791, 'samples': 4453888, 'steps': 8698, 'loss/train': 1.7054628133773804}
-03/03/2022 23:40:43 - INFO - codeparrot_training - Step 8699: {'lr': 0.000497476668273903, 'samples': 4454400, 'steps': 8699, 'loss/train': 2.838787317276001}
-03/03/2022 23:40:45 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/03/2022 23:40:48 - INFO - codeparrot_training - Step 8700: {'lr': 0.0004974759161422175, 'samples': 4454912, 'steps': 8700, 'loss/train': 1.4311803579330444}
-03/03/2022 23:40:52 - INFO - codeparrot_training - Step 8701: {'lr': 0.0004974751638990233, 'samples': 4455424, 'steps': 8701, 'loss/train': 2.282252788543701}
-03/03/2022 23:40:54 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/03/2022 23:40:57 - INFO - codeparrot_training - Step 8702: {'lr': 0.0004974744115443206, 'samples': 4455936, 'steps': 8702, 'loss/train': 2.465113639831543}
-03/03/2022 23:41:00 - INFO - codeparrot_training - Step 8703: {'lr': 0.0004974736590781097, 'samples': 4456448, 'steps': 8703, 'loss/train': 2.443077802658081}
-03/03/2022 23:41:02 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/03/2022 23:41:05 - INFO - codeparrot_training - Step 8704: {'lr': 0.000497472906500391, 'samples': 4456960, 'steps': 8704, 'loss/train': 2.244424343109131}
-03/03/2022 23:41:09 - INFO - codeparrot_training - Step 8705: {'lr': 0.0004974721538111649, 'samples': 4457472, 'steps': 8705, 'loss/train': 2.076237678527832}
-03/03/2022 23:41:11 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/03/2022 23:41:14 - INFO - codeparrot_training - Step 8706: {'lr': 0.0004974714010104315, 'samples': 4457984, 'steps': 8706, 'loss/train': 2.8815627098083496}
-03/03/2022 23:41:17 - INFO - codeparrot_training - Step 8707: {'lr': 0.0004974706480981914, 'samples': 4458496, 'steps': 8707, 'loss/train': 2.0272915363311768}
-03/03/2022 23:41:19 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/03/2022 23:41:22 - INFO - codeparrot_training - Step 8708: {'lr': 0.0004974698950744449, 'samples': 4459008, 'steps': 8708, 'loss/train': 2.3526198863983154}
-03/03/2022 23:41:25 - INFO - codeparrot_training - Step 8709: {'lr': 0.0004974691419391922, 'samples': 4459520, 'steps': 8709, 'loss/train': 1.946083426475525}
-03/03/2022 23:41:27 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/03/2022 23:41:31 - INFO - codeparrot_training - Step 8710: {'lr': 0.0004974683886924339, 'samples': 4460032, 'steps': 8710, 'loss/train': 1.539597749710083}
-03/03/2022 23:41:34 - INFO - codeparrot_training - Step 8711: {'lr': 0.00049746763533417, 'samples': 4460544, 'steps': 8711, 'loss/train': 1.6748210191726685}
-03/03/2022 23:41:36 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/03/2022 23:41:39 - INFO - codeparrot_training - Step 8712: {'lr': 0.000497466881864401, 'samples': 4461056, 'steps': 8712, 'loss/train': 2.4543297290802}
-03/03/2022 23:41:42 - INFO - codeparrot_training - Step 8713: {'lr': 0.0004974661282831272, 'samples': 4461568, 'steps': 8713, 'loss/train': 2.0060057640075684}
-03/03/2022 23:41:44 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/03/2022 23:41:48 - INFO - codeparrot_training - Step 8714: {'lr': 0.0004974653745903491, 'samples': 4462080, 'steps': 8714, 'loss/train': 2.376300811767578}
-03/03/2022 23:41:51 - INFO - codeparrot_training - Step 8715: {'lr': 0.0004974646207860668, 'samples': 4462592, 'steps': 8715, 'loss/train': 1.759137511253357}
-03/03/2022 23:41:53 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/03/2022 23:41:56 - INFO - codeparrot_training - Step 8716: {'lr': 0.0004974638668702809, 'samples': 4463104, 'steps': 8716, 'loss/train': 2.1779935359954834}
-03/03/2022 23:41:59 - INFO - codeparrot_training - Step 8717: {'lr': 0.0004974631128429915, 'samples': 4463616, 'steps': 8717, 'loss/train': 2.4776453971862793}
-03/03/2022 23:42:01 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/03/2022 23:42:05 - INFO - codeparrot_training - Step 8718: {'lr': 0.0004974623587041991, 'samples': 4464128, 'steps': 8718, 'loss/train': 2.57810378074646}
-03/03/2022 23:42:08 - INFO - codeparrot_training - Step 8719: {'lr': 0.000497461604453904, 'samples': 4464640, 'steps': 8719, 'loss/train': 1.7656874656677246}
-03/03/2022 23:42:09 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/03/2022 23:42:13 - INFO - codeparrot_training - Step 8720: {'lr': 0.0004974608500921064, 'samples': 4465152, 'steps': 8720, 'loss/train': 2.231416940689087}
-03/03/2022 23:42:16 - INFO - codeparrot_training - Step 8721: {'lr': 0.0004974600956188068, 'samples': 4465664, 'steps': 8721, 'loss/train': 1.83579421043396}
-03/03/2022 23:42:18 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/03/2022 23:42:21 - INFO - codeparrot_training - Step 8722: {'lr': 0.0004974593410340056, 'samples': 4466176, 'steps': 8722, 'loss/train': 2.7408857345581055}
-03/03/2022 23:42:25 - INFO - codeparrot_training - Step 8723: {'lr': 0.000497458586337703, 'samples': 4466688, 'steps': 8723, 'loss/train': 1.4220331907272339}
-03/03/2022 23:42:26 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/03/2022 23:42:30 - INFO - codeparrot_training - Step 8724: {'lr': 0.0004974578315298993, 'samples': 4467200, 'steps': 8724, 'loss/train': 2.2747979164123535}
-03/03/2022 23:42:33 - INFO - codeparrot_training - Step 8725: {'lr': 0.000497457076610595, 'samples': 4467712, 'steps': 8725, 'loss/train': 1.6153664588928223}
-03/03/2022 23:42:35 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/03/2022 23:42:38 - INFO - codeparrot_training - Step 8726: {'lr': 0.0004974563215797903, 'samples': 4468224, 'steps': 8726, 'loss/train': 1.6802927255630493}
-03/03/2022 23:42:41 - INFO - codeparrot_training - Step 8727: {'lr': 0.0004974555664374857, 'samples': 4468736, 'steps': 8727, 'loss/train': 2.5705792903900146}
-03/03/2022 23:42:43 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/03/2022 23:42:47 - INFO - codeparrot_training - Step 8728: {'lr': 0.0004974548111836812, 'samples': 4469248, 'steps': 8728, 'loss/train': 2.2762577533721924}
-03/03/2022 23:42:50 - INFO - codeparrot_training - Step 8729: {'lr': 0.0004974540558183776, 'samples': 4469760, 'steps': 8729, 'loss/train': 1.7342562675476074}
-03/03/2022 23:42:52 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/03/2022 23:42:55 - INFO - codeparrot_training - Step 8730: {'lr': 0.0004974533003415751, 'samples': 4470272, 'steps': 8730, 'loss/train': 2.3794968128204346}
-03/03/2022 23:42:59 - INFO - codeparrot_training - Step 8731: {'lr': 0.0004974525447532737, 'samples': 4470784, 'steps': 8731, 'loss/train': 2.3619940280914307}
-03/03/2022 23:43:01 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/03/2022 23:43:04 - INFO - codeparrot_training - Step 8732: {'lr': 0.0004974517890534742, 'samples': 4471296, 'steps': 8732, 'loss/train': 2.1940698623657227}
-03/03/2022 23:43:07 - INFO - codeparrot_training - Step 8733: {'lr': 0.0004974510332421767, 'samples': 4471808, 'steps': 8733, 'loss/train': 2.6220908164978027}
-03/03/2022 23:43:09 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/03/2022 23:43:12 - INFO - codeparrot_training - Step 8734: {'lr': 0.0004974502773193815, 'samples': 4472320, 'steps': 8734, 'loss/train': 1.9672349691390991}
-03/03/2022 23:43:15 - INFO - codeparrot_training - Step 8735: {'lr': 0.0004974495212850892, 'samples': 4472832, 'steps': 8735, 'loss/train': 1.8588497638702393}
-03/03/2022 23:43:17 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/03/2022 23:43:21 - INFO - codeparrot_training - Step 8736: {'lr': 0.0004974487651392998, 'samples': 4473344, 'steps': 8736, 'loss/train': 2.0066657066345215}
-03/03/2022 23:43:24 - INFO - codeparrot_training - Step 8737: {'lr': 0.0004974480088820139, 'samples': 4473856, 'steps': 8737, 'loss/train': 2.3459062576293945}
-03/03/2022 23:43:26 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/03/2022 23:43:29 - INFO - codeparrot_training - Step 8738: {'lr': 0.0004974472525132316, 'samples': 4474368, 'steps': 8738, 'loss/train': 1.941752314567566}
-03/03/2022 23:43:32 - INFO - codeparrot_training - Step 8739: {'lr': 0.0004974464960329536, 'samples': 4474880, 'steps': 8739, 'loss/train': 1.8554022312164307}
-03/03/2022 23:43:34 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/03/2022 23:43:37 - INFO - codeparrot_training - Step 8740: {'lr': 0.0004974457394411798, 'samples': 4475392, 'steps': 8740, 'loss/train': 2.216106414794922}
-03/03/2022 23:43:41 - INFO - codeparrot_training - Step 8741: {'lr': 0.0004974449827379109, 'samples': 4475904, 'steps': 8741, 'loss/train': 1.783923864364624}
-03/03/2022 23:43:42 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/03/2022 23:43:46 - INFO - codeparrot_training - Step 8742: {'lr': 0.000497444225923147, 'samples': 4476416, 'steps': 8742, 'loss/train': 0.4987519681453705}
-03/03/2022 23:43:49 - INFO - codeparrot_training - Step 8743: {'lr': 0.0004974434689968887, 'samples': 4476928, 'steps': 8743, 'loss/train': 1.368293285369873}
-03/03/2022 23:43:51 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/03/2022 23:43:54 - INFO - codeparrot_training - Step 8744: {'lr': 0.0004974427119591361, 'samples': 4477440, 'steps': 8744, 'loss/train': 2.1872262954711914}
-03/03/2022 23:43:57 - INFO - codeparrot_training - Step 8745: {'lr': 0.0004974419548098897, 'samples': 4477952, 'steps': 8745, 'loss/train': 1.8068444728851318}
-03/03/2022 23:43:59 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/03/2022 23:44:03 - INFO - codeparrot_training - Step 8746: {'lr': 0.0004974411975491498, 'samples': 4478464, 'steps': 8746, 'loss/train': 2.484234094619751}
-03/03/2022 23:44:06 - INFO - codeparrot_training - Step 8747: {'lr': 0.0004974404401769167, 'samples': 4478976, 'steps': 8747, 'loss/train': 2.1123433113098145}
-03/03/2022 23:44:08 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/03/2022 23:44:11 - INFO - codeparrot_training - Step 8748: {'lr': 0.0004974396826931906, 'samples': 4479488, 'steps': 8748, 'loss/train': 1.3889349699020386}
-03/03/2022 23:44:14 - INFO - codeparrot_training - Step 8749: {'lr': 0.0004974389250979722, 'samples': 4480000, 'steps': 8749, 'loss/train': 2.7238047122955322}
-03/03/2022 23:44:16 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/03/2022 23:44:20 - INFO - codeparrot_training - Step 8750: {'lr': 0.0004974381673912614, 'samples': 4480512, 'steps': 8750, 'loss/train': 1.853975534439087}
-03/03/2022 23:44:23 - INFO - codeparrot_training - Step 8751: {'lr': 0.000497437409573059, 'samples': 4481024, 'steps': 8751, 'loss/train': 1.8131722211837769}
-03/03/2022 23:44:25 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/03/2022 23:44:28 - INFO - codeparrot_training - Step 8752: {'lr': 0.000497436651643365, 'samples': 4481536, 'steps': 8752, 'loss/train': 2.2619762420654297}
-03/03/2022 23:44:31 - INFO - codeparrot_training - Step 8753: {'lr': 0.00049743589360218, 'samples': 4482048, 'steps': 8753, 'loss/train': 1.7274298667907715}
-03/03/2022 23:44:33 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/03/2022 23:44:37 - INFO - codeparrot_training - Step 8754: {'lr': 0.0004974351354495041, 'samples': 4482560, 'steps': 8754, 'loss/train': 2.141019821166992}
-03/03/2022 23:44:40 - INFO - codeparrot_training - Step 8755: {'lr': 0.0004974343771853377, 'samples': 4483072, 'steps': 8755, 'loss/train': 2.4395627975463867}
-03/03/2022 23:44:43 - INFO - codeparrot_training - Step 8756: {'lr': 0.0004974336188096813, 'samples': 4483584, 'steps': 8756, 'loss/train': 2.2689411640167236}
-03/03/2022 23:44:43 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/03/2022 23:44:48 - INFO - codeparrot_training - Step 8757: {'lr': 0.0004974328603225351, 'samples': 4484096, 'steps': 8757, 'loss/train': 1.1091245412826538}
-03/03/2022 23:44:51 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/03/2022 23:44:54 - INFO - codeparrot_training - Step 8758: {'lr': 0.0004974321017238994, 'samples': 4484608, 'steps': 8758, 'loss/train': 3.5274293422698975}
-03/03/2022 23:44:57 - INFO - codeparrot_training - Step 8759: {'lr': 0.0004974313430137747, 'samples': 4485120, 'steps': 8759, 'loss/train': 1.9889346361160278}
-03/03/2022 23:45:00 - INFO - codeparrot_training - Step 8760: {'lr': 0.0004974305841921612, 'samples': 4485632, 'steps': 8760, 'loss/train': 1.4890096187591553}
-03/03/2022 23:45:00 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/03/2022 23:45:05 - INFO - codeparrot_training - Step 8761: {'lr': 0.0004974298252590593, 'samples': 4486144, 'steps': 8761, 'loss/train': 0.456327885389328}
-03/03/2022 23:45:08 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/03/2022 23:45:11 - INFO - codeparrot_training - Step 8762: {'lr': 0.0004974290662144694, 'samples': 4486656, 'steps': 8762, 'loss/train': 1.7229273319244385}
-03/03/2022 23:45:14 - INFO - codeparrot_training - Step 8763: {'lr': 0.0004974283070583917, 'samples': 4487168, 'steps': 8763, 'loss/train': 1.3866420984268188}
-03/03/2022 23:45:17 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/03/2022 23:45:19 - INFO - codeparrot_training - Step 8764: {'lr': 0.0004974275477908266, 'samples': 4487680, 'steps': 8764, 'loss/train': 2.1512181758880615}
-03/03/2022 23:45:22 - INFO - codeparrot_training - Step 8765: {'lr': 0.0004974267884117746, 'samples': 4488192, 'steps': 8765, 'loss/train': 1.1083457469940186}
-03/03/2022 23:45:25 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/03/2022 23:45:28 - INFO - codeparrot_training - Step 8766: {'lr': 0.0004974260289212358, 'samples': 4488704, 'steps': 8766, 'loss/train': 2.6813321113586426}
-03/03/2022 23:45:31 - INFO - codeparrot_training - Step 8767: {'lr': 0.0004974252693192106, 'samples': 4489216, 'steps': 8767, 'loss/train': 2.495685338973999}
-03/03/2022 23:45:33 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/03/2022 23:45:36 - INFO - codeparrot_training - Step 8768: {'lr': 0.0004974245096056995, 'samples': 4489728, 'steps': 8768, 'loss/train': 1.7796331644058228}
-03/03/2022 23:45:39 - INFO - codeparrot_training - Step 8769: {'lr': 0.0004974237497807027, 'samples': 4490240, 'steps': 8769, 'loss/train': 2.4701106548309326}
-03/03/2022 23:45:42 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/03/2022 23:45:44 - INFO - codeparrot_training - Step 8770: {'lr': 0.0004974229898442207, 'samples': 4490752, 'steps': 8770, 'loss/train': 1.975693941116333}
-03/03/2022 23:45:48 - INFO - codeparrot_training - Step 8771: {'lr': 0.0004974222297962535, 'samples': 4491264, 'steps': 8771, 'loss/train': 2.05080246925354}
-03/03/2022 23:45:50 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/03/2022 23:45:53 - INFO - codeparrot_training - Step 8772: {'lr': 0.0004974214696368017, 'samples': 4491776, 'steps': 8772, 'loss/train': 1.7907085418701172}
-03/03/2022 23:45:56 - INFO - codeparrot_training - Step 8773: {'lr': 0.0004974207093658657, 'samples': 4492288, 'steps': 8773, 'loss/train': 2.5980589389801025}
-03/03/2022 23:45:59 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/03/2022 23:46:01 - INFO - codeparrot_training - Step 8774: {'lr': 0.0004974199489834457, 'samples': 4492800, 'steps': 8774, 'loss/train': 2.4223697185516357}
-03/03/2022 23:46:04 - INFO - codeparrot_training - Step 8775: {'lr': 0.0004974191884895421, 'samples': 4493312, 'steps': 8775, 'loss/train': 1.8699702024459839}
-03/03/2022 23:46:07 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/03/2022 23:46:10 - INFO - codeparrot_training - Step 8776: {'lr': 0.0004974184278841552, 'samples': 4493824, 'steps': 8776, 'loss/train': 2.4611337184906006}
-03/03/2022 23:46:13 - INFO - codeparrot_training - Step 8777: {'lr': 0.0004974176671672854, 'samples': 4494336, 'steps': 8777, 'loss/train': 1.8152709007263184}
-03/03/2022 23:46:15 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/03/2022 23:46:18 - INFO - codeparrot_training - Step 8778: {'lr': 0.000497416906338933, 'samples': 4494848, 'steps': 8778, 'loss/train': 2.405359983444214}
-03/03/2022 23:46:21 - INFO - codeparrot_training - Step 8779: {'lr': 0.0004974161453990985, 'samples': 4495360, 'steps': 8779, 'loss/train': 1.6990026235580444}
-03/03/2022 23:46:23 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/03/2022 23:46:26 - INFO - codeparrot_training - Step 8780: {'lr': 0.0004974153843477819, 'samples': 4495872, 'steps': 8780, 'loss/train': 1.169724702835083}
-03/03/2022 23:46:30 - INFO - codeparrot_training - Step 8781: {'lr': 0.0004974146231849838, 'samples': 4496384, 'steps': 8781, 'loss/train': 2.102581739425659}
-03/03/2022 23:46:33 - INFO - codeparrot_training - Step 8782: {'lr': 0.0004974138619107046, 'samples': 4496896, 'steps': 8782, 'loss/train': 2.3456978797912598}
-03/03/2022 23:46:33 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/03/2022 23:46:38 - INFO - codeparrot_training - Step 8783: {'lr': 0.0004974131005249444, 'samples': 4497408, 'steps': 8783, 'loss/train': 2.396493911743164}
-03/03/2022 23:46:41 - INFO - codeparrot_training - Step 8784: {'lr': 0.0004974123390277037, 'samples': 4497920, 'steps': 8784, 'loss/train': 2.3656468391418457}
-03/03/2022 23:46:42 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/03/2022 23:46:47 - INFO - codeparrot_training - Step 8785: {'lr': 0.0004974115774189829, 'samples': 4498432, 'steps': 8785, 'loss/train': 2.795692205429077}
-03/03/2022 23:46:50 - INFO - codeparrot_training - Step 8786: {'lr': 0.0004974108156987822, 'samples': 4498944, 'steps': 8786, 'loss/train': 2.337641477584839}
-03/03/2022 23:46:50 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/03/2022 23:46:55 - INFO - codeparrot_training - Step 8787: {'lr': 0.000497410053867102, 'samples': 4499456, 'steps': 8787, 'loss/train': 3.1082582473754883}
-03/03/2022 23:46:58 - INFO - codeparrot_training - Step 8788: {'lr': 0.0004974092919239427, 'samples': 4499968, 'steps': 8788, 'loss/train': 1.839972972869873}
-03/03/2022 23:46:58 - INFO - codeparrot_training - Skipping example with length 285 (seq_length=1024)
-03/03/2022 23:47:03 - INFO - codeparrot_training - Step 8789: {'lr': 0.0004974085298693045, 'samples': 4500480, 'steps': 8789, 'loss/train': 2.1275243759155273}
-03/03/2022 23:47:06 - INFO - codeparrot_training - Step 8790: {'lr': 0.0004974077677031879, 'samples': 4500992, 'steps': 8790, 'loss/train': 2.144296407699585}
-03/03/2022 23:47:07 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/03/2022 23:47:12 - INFO - codeparrot_training - Step 8791: {'lr': 0.0004974070054255932, 'samples': 4501504, 'steps': 8791, 'loss/train': 1.8665461540222168}
-03/03/2022 23:47:15 - INFO - codeparrot_training - Step 8792: {'lr': 0.0004974062430365206, 'samples': 4502016, 'steps': 8792, 'loss/train': 2.120469570159912}
-03/03/2022 23:47:15 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/03/2022 23:47:20 - INFO - codeparrot_training - Step 8793: {'lr': 0.0004974054805359706, 'samples': 4502528, 'steps': 8793, 'loss/train': 2.3594186305999756}
-03/03/2022 23:47:23 - INFO - codeparrot_training - Step 8794: {'lr': 0.0004974047179239436, 'samples': 4503040, 'steps': 8794, 'loss/train': 2.694377899169922}
-03/03/2022 23:47:23 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/03/2022 23:47:28 - INFO - codeparrot_training - Step 8795: {'lr': 0.0004974039552004398, 'samples': 4503552, 'steps': 8795, 'loss/train': 1.8364300727844238}
-03/03/2022 23:47:32 - INFO - codeparrot_training - Step 8796: {'lr': 0.0004974031923654596, 'samples': 4504064, 'steps': 8796, 'loss/train': 1.9296945333480835}
-03/03/2022 23:47:32 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/03/2022 23:47:37 - INFO - codeparrot_training - Step 8797: {'lr': 0.0004974024294190034, 'samples': 4504576, 'steps': 8797, 'loss/train': 2.3840346336364746}
-03/03/2022 23:47:40 - INFO - codeparrot_training - Step 8798: {'lr': 0.0004974016663610713, 'samples': 4505088, 'steps': 8798, 'loss/train': 2.378912925720215}
-03/03/2022 23:47:40 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/03/2022 23:47:45 - INFO - codeparrot_training - Step 8799: {'lr': 0.000497400903191664, 'samples': 4505600, 'steps': 8799, 'loss/train': 2.5544185638427734}
-03/03/2022 23:47:49 - INFO - codeparrot_training - Step 8800: {'lr': 0.0004974001399107816, 'samples': 4506112, 'steps': 8800, 'loss/train': 1.8372185230255127}
-03/03/2022 23:47:49 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/03/2022 23:47:54 - INFO - codeparrot_training - Step 8801: {'lr': 0.0004973993765184246, 'samples': 4506624, 'steps': 8801, 'loss/train': 1.812842845916748}
-03/03/2022 23:47:57 - INFO - codeparrot_training - Step 8802: {'lr': 0.0004973986130145931, 'samples': 4507136, 'steps': 8802, 'loss/train': 2.035083293914795}
-03/03/2022 23:47:57 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/03/2022 23:48:02 - INFO - codeparrot_training - Step 8803: {'lr': 0.0004973978493992877, 'samples': 4507648, 'steps': 8803, 'loss/train': 2.0764503479003906}
-03/03/2022 23:48:06 - INFO - codeparrot_training - Step 8804: {'lr': 0.0004973970856725086, 'samples': 4508160, 'steps': 8804, 'loss/train': 2.3924639225006104}
-03/03/2022 23:48:06 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/03/2022 23:48:11 - INFO - codeparrot_training - Step 8805: {'lr': 0.0004973963218342563, 'samples': 4508672, 'steps': 8805, 'loss/train': 2.8238513469696045}
-03/03/2022 23:48:14 - INFO - codeparrot_training - Step 8806: {'lr': 0.000497395557884531, 'samples': 4509184, 'steps': 8806, 'loss/train': 1.5542482137680054}
-03/03/2022 23:48:15 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/03/2022 23:48:19 - INFO - codeparrot_training - Step 8807: {'lr': 0.000497394793823333, 'samples': 4509696, 'steps': 8807, 'loss/train': 2.2402331829071045}
-03/03/2022 23:48:23 - INFO - codeparrot_training - Step 8808: {'lr': 0.0004973940296506627, 'samples': 4510208, 'steps': 8808, 'loss/train': 2.653635025024414}
-03/03/2022 23:48:23 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/03/2022 23:48:28 - INFO - codeparrot_training - Step 8809: {'lr': 0.0004973932653665206, 'samples': 4510720, 'steps': 8809, 'loss/train': 1.3610491752624512}
-03/03/2022 23:48:31 - INFO - codeparrot_training - Step 8810: {'lr': 0.0004973925009709068, 'samples': 4511232, 'steps': 8810, 'loss/train': 2.046902894973755}
-03/03/2022 23:48:31 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/03/2022 23:48:36 - INFO - codeparrot_training - Step 8811: {'lr': 0.0004973917364638218, 'samples': 4511744, 'steps': 8811, 'loss/train': 2.2245144844055176}
-03/03/2022 23:48:39 - INFO - codeparrot_training - Step 8812: {'lr': 0.0004973909718452659, 'samples': 4512256, 'steps': 8812, 'loss/train': 2.2018630504608154}
-03/03/2022 23:48:40 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/03/2022 23:48:45 - INFO - codeparrot_training - Step 8813: {'lr': 0.0004973902071152396, 'samples': 4512768, 'steps': 8813, 'loss/train': 2.0799641609191895}
-03/03/2022 23:48:48 - INFO - codeparrot_training - Step 8814: {'lr': 0.0004973894422737428, 'samples': 4513280, 'steps': 8814, 'loss/train': 1.827638864517212}
-03/03/2022 23:48:48 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/03/2022 23:48:53 - INFO - codeparrot_training - Step 8815: {'lr': 0.0004973886773207763, 'samples': 4513792, 'steps': 8815, 'loss/train': 2.1208674907684326}
-03/03/2022 23:48:56 - INFO - codeparrot_training - Step 8816: {'lr': 0.0004973879122563403, 'samples': 4514304, 'steps': 8816, 'loss/train': 2.161292552947998}
-03/03/2022 23:48:57 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/03/2022 23:49:02 - INFO - codeparrot_training - Step 8817: {'lr': 0.000497387147080435, 'samples': 4514816, 'steps': 8817, 'loss/train': 2.209043502807617}
-03/03/2022 23:49:05 - INFO - codeparrot_training - Step 8818: {'lr': 0.000497386381793061, 'samples': 4515328, 'steps': 8818, 'loss/train': 1.9854415655136108}
-03/03/2022 23:49:05 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/03/2022 23:49:10 - INFO - codeparrot_training - Step 8819: {'lr': 0.0004973856163942185, 'samples': 4515840, 'steps': 8819, 'loss/train': 2.5299463272094727}
-03/03/2022 23:49:13 - INFO - codeparrot_training - Step 8820: {'lr': 0.0004973848508839077, 'samples': 4516352, 'steps': 8820, 'loss/train': 2.195162296295166}
-03/03/2022 23:49:13 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/03/2022 23:49:19 - INFO - codeparrot_training - Step 8821: {'lr': 0.0004973840852621293, 'samples': 4516864, 'steps': 8821, 'loss/train': 2.430168390274048}
-03/03/2022 23:49:22 - INFO - codeparrot_training - Step 8822: {'lr': 0.0004973833195288834, 'samples': 4517376, 'steps': 8822, 'loss/train': 2.6853129863739014}
-03/03/2022 23:49:23 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/03/2022 23:49:27 - INFO - codeparrot_training - Step 8823: {'lr': 0.0004973825536841703, 'samples': 4517888, 'steps': 8823, 'loss/train': 1.0593323707580566}
-03/03/2022 23:49:30 - INFO - codeparrot_training - Step 8824: {'lr': 0.0004973817877279906, 'samples': 4518400, 'steps': 8824, 'loss/train': 1.9365980625152588}
-03/03/2022 23:49:31 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/03/2022 23:49:36 - INFO - codeparrot_training - Step 8825: {'lr': 0.0004973810216603443, 'samples': 4518912, 'steps': 8825, 'loss/train': 2.564321994781494}
-03/03/2022 23:49:39 - INFO - codeparrot_training - Step 8826: {'lr': 0.000497380255481232, 'samples': 4519424, 'steps': 8826, 'loss/train': 2.497718095779419}
-03/03/2022 23:49:40 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/03/2022 23:49:44 - INFO - codeparrot_training - Step 8827: {'lr': 0.000497379489190654, 'samples': 4519936, 'steps': 8827, 'loss/train': 1.4043513536453247}
-03/03/2022 23:49:47 - INFO - codeparrot_training - Step 8828: {'lr': 0.0004973787227886106, 'samples': 4520448, 'steps': 8828, 'loss/train': 1.871717095375061}
-03/03/2022 23:49:48 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/03/2022 23:49:52 - INFO - codeparrot_training - Step 8829: {'lr': 0.0004973779562751022, 'samples': 4520960, 'steps': 8829, 'loss/train': 2.0771424770355225}
-03/03/2022 23:49:56 - INFO - codeparrot_training - Step 8830: {'lr': 0.0004973771896501292, 'samples': 4521472, 'steps': 8830, 'loss/train': 2.476667642593384}
-03/03/2022 23:49:56 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/03/2022 23:50:01 - INFO - codeparrot_training - Step 8831: {'lr': 0.0004973764229136917, 'samples': 4521984, 'steps': 8831, 'loss/train': 1.3692796230316162}
-03/03/2022 23:50:04 - INFO - codeparrot_training - Step 8832: {'lr': 0.0004973756560657901, 'samples': 4522496, 'steps': 8832, 'loss/train': 2.4923956394195557}
-03/03/2022 23:50:05 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/03/2022 23:50:09 - INFO - codeparrot_training - Step 8833: {'lr': 0.0004973748891064251, 'samples': 4523008, 'steps': 8833, 'loss/train': 1.5309537649154663}
-03/03/2022 23:50:12 - INFO - codeparrot_training - Step 8834: {'lr': 0.0004973741220355967, 'samples': 4523520, 'steps': 8834, 'loss/train': 1.4684662818908691}
-03/03/2022 23:50:13 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/03/2022 23:50:18 - INFO - codeparrot_training - Step 8835: {'lr': 0.0004973733548533052, 'samples': 4524032, 'steps': 8835, 'loss/train': 1.9438376426696777}
-03/03/2022 23:50:21 - INFO - codeparrot_training - Step 8836: {'lr': 0.0004973725875595513, 'samples': 4524544, 'steps': 8836, 'loss/train': 2.2001819610595703}
-03/03/2022 23:50:21 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/03/2022 23:50:26 - INFO - codeparrot_training - Step 8837: {'lr': 0.000497371820154335, 'samples': 4525056, 'steps': 8837, 'loss/train': 2.2422304153442383}
-03/03/2022 23:50:29 - INFO - codeparrot_training - Step 8838: {'lr': 0.0004973710526376569, 'samples': 4525568, 'steps': 8838, 'loss/train': 3.090958595275879}
-03/03/2022 23:50:30 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/03/2022 23:50:34 - INFO - codeparrot_training - Step 8839: {'lr': 0.000497370285009517, 'samples': 4526080, 'steps': 8839, 'loss/train': 1.7944730520248413}
-03/03/2022 23:50:38 - INFO - codeparrot_training - Step 8840: {'lr': 0.000497369517269916, 'samples': 4526592, 'steps': 8840, 'loss/train': 3.0183372497558594}
-03/03/2022 23:50:38 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/03/2022 23:50:43 - INFO - codeparrot_training - Step 8841: {'lr': 0.0004973687494188541, 'samples': 4527104, 'steps': 8841, 'loss/train': 1.9969971179962158}
-03/03/2022 23:50:46 - INFO - codeparrot_training - Step 8842: {'lr': 0.0004973679814563318, 'samples': 4527616, 'steps': 8842, 'loss/train': 2.8572113513946533}
-03/03/2022 23:50:47 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/03/2022 23:50:51 - INFO - codeparrot_training - Step 8843: {'lr': 0.0004973672133823491, 'samples': 4528128, 'steps': 8843, 'loss/train': 1.899039626121521}
-03/03/2022 23:50:55 - INFO - codeparrot_training - Step 8844: {'lr': 0.0004973664451969066, 'samples': 4528640, 'steps': 8844, 'loss/train': 6.808200359344482}
-03/03/2022 23:50:56 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/03/2022 23:51:00 - INFO - codeparrot_training - Step 8845: {'lr': 0.0004973656769000046, 'samples': 4529152, 'steps': 8845, 'loss/train': 2.432969093322754}
-03/03/2022 23:51:03 - INFO - codeparrot_training - Step 8846: {'lr': 0.0004973649084916435, 'samples': 4529664, 'steps': 8846, 'loss/train': 1.9928280115127563}
-03/03/2022 23:51:04 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/03/2022 23:51:08 - INFO - codeparrot_training - Step 8847: {'lr': 0.0004973641399718236, 'samples': 4530176, 'steps': 8847, 'loss/train': 1.7495628595352173}
-03/03/2022 23:51:11 - INFO - codeparrot_training - Step 8848: {'lr': 0.0004973633713405451, 'samples': 4530688, 'steps': 8848, 'loss/train': 1.8631535768508911}
-03/03/2022 23:51:12 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/03/2022 23:51:17 - INFO - codeparrot_training - Step 8849: {'lr': 0.0004973626025978086, 'samples': 4531200, 'steps': 8849, 'loss/train': 2.3899316787719727}
-03/03/2022 23:51:20 - INFO - codeparrot_training - Step 8850: {'lr': 0.0004973618337436143, 'samples': 4531712, 'steps': 8850, 'loss/train': 1.921309471130371}
-03/03/2022 23:51:21 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/03/2022 23:51:25 - INFO - codeparrot_training - Step 8851: {'lr': 0.0004973610647779626, 'samples': 4532224, 'steps': 8851, 'loss/train': 1.9840190410614014}
-03/03/2022 23:51:28 - INFO - codeparrot_training - Step 8852: {'lr': 0.0004973602957008537, 'samples': 4532736, 'steps': 8852, 'loss/train': 1.967504620552063}
-03/03/2022 23:51:29 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/03/2022 23:51:33 - INFO - codeparrot_training - Step 8853: {'lr': 0.0004973595265122883, 'samples': 4533248, 'steps': 8853, 'loss/train': 2.650303602218628}
-03/03/2022 23:51:36 - INFO - codeparrot_training - Step 8854: {'lr': 0.0004973587572122663, 'samples': 4533760, 'steps': 8854, 'loss/train': 2.5531888008117676}
-03/03/2022 23:51:37 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/03/2022 23:51:42 - INFO - codeparrot_training - Step 8855: {'lr': 0.0004973579878007884, 'samples': 4534272, 'steps': 8855, 'loss/train': 2.6756913661956787}
-03/03/2022 23:51:45 - INFO - codeparrot_training - Step 8856: {'lr': 0.0004973572182778546, 'samples': 4534784, 'steps': 8856, 'loss/train': 2.6757888793945312}
-03/03/2022 23:51:46 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/03/2022 23:51:50 - INFO - codeparrot_training - Step 8857: {'lr': 0.0004973564486434656, 'samples': 4535296, 'steps': 8857, 'loss/train': 1.7606362104415894}
-03/03/2022 23:51:53 - INFO - codeparrot_training - Step 8858: {'lr': 0.0004973556788976217, 'samples': 4535808, 'steps': 8858, 'loss/train': 3.115241765975952}
-03/03/2022 23:51:54 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/03/2022 23:51:59 - INFO - codeparrot_training - Step 8859: {'lr': 0.000497354909040323, 'samples': 4536320, 'steps': 8859, 'loss/train': 2.4368560314178467}
-03/03/2022 23:52:02 - INFO - codeparrot_training - Step 8860: {'lr': 0.00049735413907157, 'samples': 4536832, 'steps': 8860, 'loss/train': 2.3073229789733887}
-03/03/2022 23:52:04 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/03/2022 23:52:07 - INFO - codeparrot_training - Step 8861: {'lr': 0.0004973533689913631, 'samples': 4537344, 'steps': 8861, 'loss/train': 2.250687837600708}
-03/03/2022 23:52:11 - INFO - codeparrot_training - Step 8862: {'lr': 0.0004973525987997026, 'samples': 4537856, 'steps': 8862, 'loss/train': 2.0300450325012207}
-03/03/2022 23:52:12 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/03/2022 23:52:16 - INFO - codeparrot_training - Step 8863: {'lr': 0.0004973518284965888, 'samples': 4538368, 'steps': 8863, 'loss/train': 1.741579294204712}
-03/03/2022 23:52:19 - INFO - codeparrot_training - Step 8864: {'lr': 0.0004973510580820221, 'samples': 4538880, 'steps': 8864, 'loss/train': 1.6872000694274902}
-03/03/2022 23:52:21 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/03/2022 23:52:24 - INFO - codeparrot_training - Step 8865: {'lr': 0.0004973502875560028, 'samples': 4539392, 'steps': 8865, 'loss/train': 1.5403385162353516}
-03/03/2022 23:52:28 - INFO - codeparrot_training - Step 8866: {'lr': 0.0004973495169185313, 'samples': 4539904, 'steps': 8866, 'loss/train': 2.2712769508361816}
-03/03/2022 23:52:30 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/03/2022 23:52:33 - INFO - codeparrot_training - Step 8867: {'lr': 0.0004973487461696079, 'samples': 4540416, 'steps': 8867, 'loss/train': 2.110077142715454}
-03/03/2022 23:52:36 - INFO - codeparrot_training - Step 8868: {'lr': 0.000497347975309233, 'samples': 4540928, 'steps': 8868, 'loss/train': 1.970211386680603}
-03/03/2022 23:52:38 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/03/2022 23:52:41 - INFO - codeparrot_training - Step 8869: {'lr': 0.0004973472043374069, 'samples': 4541440, 'steps': 8869, 'loss/train': 2.603158473968506}
-03/03/2022 23:52:44 - INFO - codeparrot_training - Step 8870: {'lr': 0.00049734643325413, 'samples': 4541952, 'steps': 8870, 'loss/train': 1.1087627410888672}
-03/03/2022 23:52:46 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/03/2022 23:52:50 - INFO - codeparrot_training - Step 8871: {'lr': 0.0004973456620594026, 'samples': 4542464, 'steps': 8871, 'loss/train': 2.3660590648651123}
-03/03/2022 23:52:53 - INFO - codeparrot_training - Step 8872: {'lr': 0.0004973448907532251, 'samples': 4542976, 'steps': 8872, 'loss/train': 2.210852861404419}
-03/03/2022 23:52:54 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/03/2022 23:52:58 - INFO - codeparrot_training - Step 8873: {'lr': 0.0004973441193355978, 'samples': 4543488, 'steps': 8873, 'loss/train': 2.2355575561523438}
-03/03/2022 23:53:01 - INFO - codeparrot_training - Step 8874: {'lr': 0.0004973433478065209, 'samples': 4544000, 'steps': 8874, 'loss/train': 2.6774606704711914}
-03/03/2022 23:53:03 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/03/2022 23:53:06 - INFO - codeparrot_training - Step 8875: {'lr': 0.0004973425761659951, 'samples': 4544512, 'steps': 8875, 'loss/train': 2.39446759223938}
-03/03/2022 23:53:10 - INFO - codeparrot_training - Step 8876: {'lr': 0.0004973418044140204, 'samples': 4545024, 'steps': 8876, 'loss/train': 2.2812297344207764}
-03/03/2022 23:53:11 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/03/2022 23:53:15 - INFO - codeparrot_training - Step 8877: {'lr': 0.0004973410325505974, 'samples': 4545536, 'steps': 8877, 'loss/train': 2.0934576988220215}
-03/03/2022 23:53:18 - INFO - codeparrot_training - Step 8878: {'lr': 0.0004973402605757263, 'samples': 4546048, 'steps': 8878, 'loss/train': 3.3849527835845947}
-03/03/2022 23:53:19 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/03/2022 23:53:23 - INFO - codeparrot_training - Step 8879: {'lr': 0.0004973394884894075, 'samples': 4546560, 'steps': 8879, 'loss/train': 1.7654329538345337}
-03/03/2022 23:53:26 - INFO - codeparrot_training - Step 8880: {'lr': 0.0004973387162916415, 'samples': 4547072, 'steps': 8880, 'loss/train': 2.0768730640411377}
-03/03/2022 23:53:28 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/03/2022 23:53:32 - INFO - codeparrot_training - Step 8881: {'lr': 0.0004973379439824283, 'samples': 4547584, 'steps': 8881, 'loss/train': 0.73219233751297}
-03/03/2022 23:53:35 - INFO - codeparrot_training - Step 8882: {'lr': 0.0004973371715617685, 'samples': 4548096, 'steps': 8882, 'loss/train': 2.192439079284668}
-03/03/2022 23:53:36 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/03/2022 23:53:40 - INFO - codeparrot_training - Step 8883: {'lr': 0.0004973363990296624, 'samples': 4548608, 'steps': 8883, 'loss/train': 2.119690418243408}
-03/03/2022 23:53:43 - INFO - codeparrot_training - Step 8884: {'lr': 0.0004973356263861103, 'samples': 4549120, 'steps': 8884, 'loss/train': 2.252858877182007}
-03/03/2022 23:53:44 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/03/2022 23:53:48 - INFO - codeparrot_training - Step 8885: {'lr': 0.0004973348536311126, 'samples': 4549632, 'steps': 8885, 'loss/train': 1.9926657676696777}
-03/03/2022 23:53:52 - INFO - codeparrot_training - Step 8886: {'lr': 0.0004973340807646696, 'samples': 4550144, 'steps': 8886, 'loss/train': 1.8674349784851074}
-03/03/2022 23:53:52 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/03/2022 23:53:57 - INFO - codeparrot_training - Step 8887: {'lr': 0.0004973333077867817, 'samples': 4550656, 'steps': 8887, 'loss/train': 2.275048017501831}
-03/03/2022 23:54:00 - INFO - codeparrot_training - Step 8888: {'lr': 0.0004973325346974493, 'samples': 4551168, 'steps': 8888, 'loss/train': 2.3664841651916504}
-03/03/2022 23:54:01 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/03/2022 23:54:05 - INFO - codeparrot_training - Step 8889: {'lr': 0.0004973317614966726, 'samples': 4551680, 'steps': 8889, 'loss/train': 1.290902018547058}
-03/03/2022 23:54:08 - INFO - codeparrot_training - Step 8890: {'lr': 0.000497330988184452, 'samples': 4552192, 'steps': 8890, 'loss/train': 2.0892324447631836}
-03/03/2022 23:54:09 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/03/2022 23:54:14 - INFO - codeparrot_training - Step 8891: {'lr': 0.000497330214760788, 'samples': 4552704, 'steps': 8891, 'loss/train': 2.1964478492736816}
-03/03/2022 23:54:17 - INFO - codeparrot_training - Step 8892: {'lr': 0.0004973294412256807, 'samples': 4553216, 'steps': 8892, 'loss/train': 2.0984604358673096}
-03/03/2022 23:54:17 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/03/2022 23:54:22 - INFO - codeparrot_training - Step 8893: {'lr': 0.0004973286675791305, 'samples': 4553728, 'steps': 8893, 'loss/train': 2.2619824409484863}
-03/03/2022 23:54:25 - INFO - codeparrot_training - Step 8894: {'lr': 0.000497327893821138, 'samples': 4554240, 'steps': 8894, 'loss/train': 3.379472255706787}
-03/03/2022 23:54:26 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/03/2022 23:54:31 - INFO - codeparrot_training - Step 8895: {'lr': 0.0004973271199517033, 'samples': 4554752, 'steps': 8895, 'loss/train': 1.9199522733688354}
-03/03/2022 23:54:34 - INFO - codeparrot_training - Step 8896: {'lr': 0.0004973263459708268, 'samples': 4555264, 'steps': 8896, 'loss/train': 1.4214882850646973}
-03/03/2022 23:54:34 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/03/2022 23:54:39 - INFO - codeparrot_training - Step 8897: {'lr': 0.0004973255718785088, 'samples': 4555776, 'steps': 8897, 'loss/train': 1.3366233110427856}
-03/03/2022 23:54:42 - INFO - codeparrot_training - Step 8898: {'lr': 0.0004973247976747499, 'samples': 4556288, 'steps': 8898, 'loss/train': 0.7685533761978149}
-03/03/2022 23:54:44 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/03/2022 23:54:47 - INFO - codeparrot_training - Step 8899: {'lr': 0.00049732402335955, 'samples': 4556800, 'steps': 8899, 'loss/train': 2.19913387298584}
-03/03/2022 23:54:51 - INFO - codeparrot_training - Step 8900: {'lr': 0.0004973232489329099, 'samples': 4557312, 'steps': 8900, 'loss/train': 1.3622500896453857}
-03/03/2022 23:54:52 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/03/2022 23:54:56 - INFO - codeparrot_training - Step 8901: {'lr': 0.0004973224743948298, 'samples': 4557824, 'steps': 8901, 'loss/train': 2.3100342750549316}
-03/03/2022 23:54:59 - INFO - codeparrot_training - Step 8902: {'lr': 0.00049732169974531, 'samples': 4558336, 'steps': 8902, 'loss/train': 1.8107950687408447}
-03/03/2022 23:55:00 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/03/2022 23:55:05 - INFO - codeparrot_training - Step 8903: {'lr': 0.0004973209249843507, 'samples': 4558848, 'steps': 8903, 'loss/train': 0.4462875425815582}
-03/03/2022 23:55:08 - INFO - codeparrot_training - Step 8904: {'lr': 0.0004973201501119525, 'samples': 4559360, 'steps': 8904, 'loss/train': 1.708825707435608}
-03/03/2022 23:55:09 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/03/2022 23:55:13 - INFO - codeparrot_training - Step 8905: {'lr': 0.0004973193751281156, 'samples': 4559872, 'steps': 8905, 'loss/train': 2.2673497200012207}
-03/03/2022 23:55:16 - INFO - codeparrot_training - Step 8906: {'lr': 0.0004973186000328405, 'samples': 4560384, 'steps': 8906, 'loss/train': 2.521711826324463}
-03/03/2022 23:55:17 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/03/2022 23:55:21 - INFO - codeparrot_training - Step 8907: {'lr': 0.0004973178248261274, 'samples': 4560896, 'steps': 8907, 'loss/train': 2.0080792903900146}
-03/03/2022 23:55:25 - INFO - codeparrot_training - Step 8908: {'lr': 0.0004973170495079768, 'samples': 4561408, 'steps': 8908, 'loss/train': 1.92903733253479}
-03/03/2022 23:55:26 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/03/2022 23:55:30 - INFO - codeparrot_training - Step 8909: {'lr': 0.0004973162740783888, 'samples': 4561920, 'steps': 8909, 'loss/train': 2.0803587436676025}
-03/03/2022 23:55:33 - INFO - codeparrot_training - Step 8910: {'lr': 0.000497315498537364, 'samples': 4562432, 'steps': 8910, 'loss/train': 2.3051106929779053}
-03/03/2022 23:55:34 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/03/2022 23:55:38 - INFO - codeparrot_training - Step 8911: {'lr': 0.0004973147228849027, 'samples': 4562944, 'steps': 8911, 'loss/train': 2.454385995864868}
-03/03/2022 23:55:41 - INFO - codeparrot_training - Step 8912: {'lr': 0.0004973139471210051, 'samples': 4563456, 'steps': 8912, 'loss/train': 2.089282751083374}
-03/03/2022 23:55:43 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/03/2022 23:55:47 - INFO - codeparrot_training - Step 8913: {'lr': 0.0004973131712456717, 'samples': 4563968, 'steps': 8913, 'loss/train': 1.664138913154602}
-03/03/2022 23:55:50 - INFO - codeparrot_training - Step 8914: {'lr': 0.0004973123952589027, 'samples': 4564480, 'steps': 8914, 'loss/train': 1.2609494924545288}
-03/03/2022 23:55:51 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/03/2022 23:55:55 - INFO - codeparrot_training - Step 8915: {'lr': 0.0004973116191606987, 'samples': 4564992, 'steps': 8915, 'loss/train': 2.382627010345459}
-03/03/2022 23:55:58 - INFO - codeparrot_training - Step 8916: {'lr': 0.0004973108429510598, 'samples': 4565504, 'steps': 8916, 'loss/train': 2.804083824157715}
-03/03/2022 23:56:00 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/03/2022 23:56:04 - INFO - codeparrot_training - Step 8917: {'lr': 0.0004973100666299864, 'samples': 4566016, 'steps': 8917, 'loss/train': 2.1057841777801514}
-03/03/2022 23:56:07 - INFO - codeparrot_training - Step 8918: {'lr': 0.000497309290197479, 'samples': 4566528, 'steps': 8918, 'loss/train': 2.2271811962127686}
-03/03/2022 23:56:08 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/03/2022 23:56:12 - INFO - codeparrot_training - Step 8919: {'lr': 0.0004973085136535379, 'samples': 4567040, 'steps': 8919, 'loss/train': 2.294034957885742}
-03/03/2022 23:56:15 - INFO - codeparrot_training - Step 8920: {'lr': 0.0004973077369981633, 'samples': 4567552, 'steps': 8920, 'loss/train': 2.602604627609253}
-03/03/2022 23:56:16 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/03/2022 23:56:20 - INFO - codeparrot_training - Step 8921: {'lr': 0.0004973069602313557, 'samples': 4568064, 'steps': 8921, 'loss/train': 1.4479656219482422}
-03/03/2022 23:56:23 - INFO - codeparrot_training - Step 8922: {'lr': 0.0004973061833531154, 'samples': 4568576, 'steps': 8922, 'loss/train': 1.569603681564331}
-03/03/2022 23:56:25 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/03/2022 23:56:29 - INFO - codeparrot_training - Step 8923: {'lr': 0.0004973054063634428, 'samples': 4569088, 'steps': 8923, 'loss/train': 2.1005702018737793}
-03/03/2022 23:56:32 - INFO - codeparrot_training - Step 8924: {'lr': 0.0004973046292623382, 'samples': 4569600, 'steps': 8924, 'loss/train': 1.4551528692245483}
-03/03/2022 23:56:33 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/03/2022 23:56:37 - INFO - codeparrot_training - Step 8925: {'lr': 0.0004973038520498017, 'samples': 4570112, 'steps': 8925, 'loss/train': 1.0624005794525146}
-03/03/2022 23:56:40 - INFO - codeparrot_training - Step 8926: {'lr': 0.0004973030747258342, 'samples': 4570624, 'steps': 8926, 'loss/train': 2.3850247859954834}
-03/03/2022 23:56:41 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/03/2022 23:56:45 - INFO - codeparrot_training - Step 8927: {'lr': 0.0004973022972904356, 'samples': 4571136, 'steps': 8927, 'loss/train': 2.151336669921875}
-03/03/2022 23:56:49 - INFO - codeparrot_training - Step 8928: {'lr': 0.0004973015197436063, 'samples': 4571648, 'steps': 8928, 'loss/train': 1.6686655282974243}
-03/03/2022 23:56:49 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/03/2022 23:56:54 - INFO - codeparrot_training - Step 8929: {'lr': 0.0004973007420853471, 'samples': 4572160, 'steps': 8929, 'loss/train': 2.2062840461730957}
-03/03/2022 23:56:57 - INFO - codeparrot_training - Step 8930: {'lr': 0.0004972999643156577, 'samples': 4572672, 'steps': 8930, 'loss/train': 2.0811409950256348}
-03/03/2022 23:56:58 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/03/2022 23:57:02 - INFO - codeparrot_training - Step 8931: {'lr': 0.0004972991864345389, 'samples': 4573184, 'steps': 8931, 'loss/train': 1.6888874769210815}
-03/03/2022 23:57:05 - INFO - codeparrot_training - Step 8932: {'lr': 0.0004972984084419908, 'samples': 4573696, 'steps': 8932, 'loss/train': 1.2967243194580078}
-03/03/2022 23:57:06 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/03/2022 23:57:11 - INFO - codeparrot_training - Step 8933: {'lr': 0.0004972976303380139, 'samples': 4574208, 'steps': 8933, 'loss/train': 2.677203893661499}
-03/03/2022 23:57:14 - INFO - codeparrot_training - Step 8934: {'lr': 0.0004972968521226085, 'samples': 4574720, 'steps': 8934, 'loss/train': 1.2691309452056885}
-03/03/2022 23:57:15 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/03/2022 23:57:19 - INFO - codeparrot_training - Step 8935: {'lr': 0.0004972960737957749, 'samples': 4575232, 'steps': 8935, 'loss/train': 1.4065243005752563}
-03/03/2022 23:57:22 - INFO - codeparrot_training - Step 8936: {'lr': 0.0004972952953575136, 'samples': 4575744, 'steps': 8936, 'loss/train': 1.2138535976409912}
-03/03/2022 23:57:23 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/03/2022 23:57:28 - INFO - codeparrot_training - Step 8937: {'lr': 0.0004972945168078248, 'samples': 4576256, 'steps': 8937, 'loss/train': 1.7846009731292725}
-03/03/2022 23:57:31 - INFO - codeparrot_training - Step 8938: {'lr': 0.000497293738146709, 'samples': 4576768, 'steps': 8938, 'loss/train': 1.1449830532073975}
-03/03/2022 23:57:32 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/03/2022 23:57:36 - INFO - codeparrot_training - Step 8939: {'lr': 0.0004972929593741662, 'samples': 4577280, 'steps': 8939, 'loss/train': 0.28163251280784607}
-03/03/2022 23:57:39 - INFO - codeparrot_training - Step 8940: {'lr': 0.0004972921804901973, 'samples': 4577792, 'steps': 8940, 'loss/train': 2.851638078689575}
-03/03/2022 23:57:40 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/03/2022 23:57:44 - INFO - codeparrot_training - Step 8941: {'lr': 0.0004972914014948023, 'samples': 4578304, 'steps': 8941, 'loss/train': 0.45671090483665466}
-03/03/2022 23:57:47 - INFO - codeparrot_training - Step 8942: {'lr': 0.0004972906223879815, 'samples': 4578816, 'steps': 8942, 'loss/train': 2.593719720840454}
-03/03/2022 23:57:48 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/03/2022 23:57:53 - INFO - codeparrot_training - Step 8943: {'lr': 0.0004972898431697355, 'samples': 4579328, 'steps': 8943, 'loss/train': 2.2557358741760254}
-03/03/2022 23:57:56 - INFO - codeparrot_training - Step 8944: {'lr': 0.0004972890638400644, 'samples': 4579840, 'steps': 8944, 'loss/train': 2.0867719650268555}
-03/03/2022 23:57:57 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/03/2022 23:58:01 - INFO - codeparrot_training - Step 8945: {'lr': 0.0004972882843989687, 'samples': 4580352, 'steps': 8945, 'loss/train': 1.8348740339279175}
-03/03/2022 23:58:04 - INFO - codeparrot_training - Step 8946: {'lr': 0.0004972875048464487, 'samples': 4580864, 'steps': 8946, 'loss/train': 1.8259434700012207}
-03/03/2022 23:58:05 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/03/2022 23:58:09 - INFO - codeparrot_training - Step 8947: {'lr': 0.0004972867251825048, 'samples': 4581376, 'steps': 8947, 'loss/train': 1.4776051044464111}
-03/03/2022 23:58:13 - INFO - codeparrot_training - Step 8948: {'lr': 0.0004972859454071373, 'samples': 4581888, 'steps': 8948, 'loss/train': 2.0622408390045166}
-03/03/2022 23:58:13 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/03/2022 23:58:18 - INFO - codeparrot_training - Step 8949: {'lr': 0.0004972851655203465, 'samples': 4582400, 'steps': 8949, 'loss/train': 1.044212818145752}
-03/03/2022 23:58:21 - INFO - codeparrot_training - Step 8950: {'lr': 0.000497284385522133, 'samples': 4582912, 'steps': 8950, 'loss/train': 1.8687134981155396}
-03/03/2022 23:58:23 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/03/2022 23:58:27 - INFO - codeparrot_training - Step 8951: {'lr': 0.0004972836054124968, 'samples': 4583424, 'steps': 8951, 'loss/train': 1.7495005130767822}
-03/03/2022 23:58:30 - INFO - codeparrot_training - Step 8952: {'lr': 0.0004972828251914384, 'samples': 4583936, 'steps': 8952, 'loss/train': 1.2585889101028442}
-03/03/2022 23:58:31 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/03/2022 23:58:35 - INFO - codeparrot_training - Step 8953: {'lr': 0.0004972820448589584, 'samples': 4584448, 'steps': 8953, 'loss/train': 1.5238910913467407}
-03/03/2022 23:58:38 - INFO - codeparrot_training - Step 8954: {'lr': 0.0004972812644150567, 'samples': 4584960, 'steps': 8954, 'loss/train': 0.3156850039958954}
-03/03/2022 23:58:39 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/03/2022 23:58:43 - INFO - codeparrot_training - Step 8955: {'lr': 0.000497280483859734, 'samples': 4585472, 'steps': 8955, 'loss/train': 2.273796558380127}
-03/03/2022 23:58:47 - INFO - codeparrot_training - Step 8956: {'lr': 0.0004972797031929904, 'samples': 4585984, 'steps': 8956, 'loss/train': 1.3232872486114502}
-03/03/2022 23:58:48 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/03/2022 23:58:52 - INFO - codeparrot_training - Step 8957: {'lr': 0.0004972789224148266, 'samples': 4586496, 'steps': 8957, 'loss/train': 2.533845901489258}
-03/03/2022 23:58:55 - INFO - codeparrot_training - Step 8958: {'lr': 0.0004972781415252426, 'samples': 4587008, 'steps': 8958, 'loss/train': 2.670914649963379}
-03/03/2022 23:58:56 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/03/2022 23:59:01 - INFO - codeparrot_training - Step 8959: {'lr': 0.0004972773605242388, 'samples': 4587520, 'steps': 8959, 'loss/train': 2.371537923812866}
-03/03/2022 23:59:04 - INFO - codeparrot_training - Step 8960: {'lr': 0.0004972765794118158, 'samples': 4588032, 'steps': 8960, 'loss/train': 2.2361440658569336}
-03/03/2022 23:59:07 - INFO - codeparrot_training - Step 8961: {'lr': 0.0004972757981879737, 'samples': 4588544, 'steps': 8961, 'loss/train': 2.5704667568206787}
-03/03/2022 23:59:08 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/03/2022 23:59:13 - INFO - codeparrot_training - Step 8962: {'lr': 0.000497275016852713, 'samples': 4589056, 'steps': 8962, 'loss/train': 1.6365630626678467}
-03/03/2022 23:59:16 - INFO - codeparrot_training - Step 8963: {'lr': 0.0004972742354060339, 'samples': 4589568, 'steps': 8963, 'loss/train': 1.8814820051193237}
-03/03/2022 23:59:17 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/03/2022 23:59:21 - INFO - codeparrot_training - Step 8964: {'lr': 0.0004972734538479369, 'samples': 4590080, 'steps': 8964, 'loss/train': 2.529332399368286}
-03/03/2022 23:59:24 - INFO - codeparrot_training - Step 8965: {'lr': 0.0004972726721784223, 'samples': 4590592, 'steps': 8965, 'loss/train': 1.104833722114563}
-03/03/2022 23:59:25 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/03/2022 23:59:29 - INFO - codeparrot_training - Step 8966: {'lr': 0.0004972718903974904, 'samples': 4591104, 'steps': 8966, 'loss/train': 2.6811728477478027}
-03/03/2022 23:59:33 - INFO - codeparrot_training - Step 8967: {'lr': 0.0004972711085051417, 'samples': 4591616, 'steps': 8967, 'loss/train': 2.9047980308532715}
-03/03/2022 23:59:34 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/03/2022 23:59:38 - INFO - codeparrot_training - Step 8968: {'lr': 0.0004972703265013764, 'samples': 4592128, 'steps': 8968, 'loss/train': 1.003009557723999}
-03/03/2022 23:59:41 - INFO - codeparrot_training - Step 8969: {'lr': 0.0004972695443861949, 'samples': 4592640, 'steps': 8969, 'loss/train': 3.0056166648864746}
-03/03/2022 23:59:43 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/03/2022 23:59:46 - INFO - codeparrot_training - Step 8970: {'lr': 0.0004972687621595975, 'samples': 4593152, 'steps': 8970, 'loss/train': 2.5545177459716797}
-03/03/2022 23:59:50 - INFO - codeparrot_training - Step 8971: {'lr': 0.0004972679798215847, 'samples': 4593664, 'steps': 8971, 'loss/train': 2.0704238414764404}
-03/03/2022 23:59:51 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/03/2022 23:59:55 - INFO - codeparrot_training - Step 8972: {'lr': 0.0004972671973721567, 'samples': 4594176, 'steps': 8972, 'loss/train': 2.5335302352905273}
-03/03/2022 23:59:58 - INFO - codeparrot_training - Step 8973: {'lr': 0.000497266414811314, 'samples': 4594688, 'steps': 8973, 'loss/train': 2.5110273361206055}
-03/03/2022 23:59:59 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 00:00:03 - INFO - codeparrot_training - Step 8974: {'lr': 0.0004972656321390568, 'samples': 4595200, 'steps': 8974, 'loss/train': 2.6526801586151123}
-03/04/2022 00:00:07 - INFO - codeparrot_training - Step 8975: {'lr': 0.0004972648493553856, 'samples': 4595712, 'steps': 8975, 'loss/train': 1.9700356721878052}
-03/04/2022 00:00:08 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 00:00:12 - INFO - codeparrot_training - Step 8976: {'lr': 0.0004972640664603006, 'samples': 4596224, 'steps': 8976, 'loss/train': 2.0826072692871094}
-03/04/2022 00:00:15 - INFO - codeparrot_training - Step 8977: {'lr': 0.0004972632834538023, 'samples': 4596736, 'steps': 8977, 'loss/train': 1.3655916452407837}
-03/04/2022 00:00:16 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 00:00:20 - INFO - codeparrot_training - Step 8978: {'lr': 0.0004972625003358908, 'samples': 4597248, 'steps': 8978, 'loss/train': 2.1000115871429443}
-03/04/2022 00:00:23 - INFO - codeparrot_training - Step 8979: {'lr': 0.0004972617171065668, 'samples': 4597760, 'steps': 8979, 'loss/train': 2.590733051300049}
-03/04/2022 00:00:24 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 00:00:29 - INFO - codeparrot_training - Step 8980: {'lr': 0.0004972609337658305, 'samples': 4598272, 'steps': 8980, 'loss/train': 6.915347099304199}
-03/04/2022 00:00:32 - INFO - codeparrot_training - Step 8981: {'lr': 0.0004972601503136822, 'samples': 4598784, 'steps': 8981, 'loss/train': 2.2558696269989014}
-03/04/2022 00:00:33 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 00:00:37 - INFO - codeparrot_training - Step 8982: {'lr': 0.0004972593667501222, 'samples': 4599296, 'steps': 8982, 'loss/train': 2.219912528991699}
-03/04/2022 00:00:40 - INFO - codeparrot_training - Step 8983: {'lr': 0.0004972585830751511, 'samples': 4599808, 'steps': 8983, 'loss/train': 2.293651580810547}
-03/04/2022 00:00:42 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/04/2022 00:00:46 - INFO - codeparrot_training - Step 8984: {'lr': 0.0004972577992887689, 'samples': 4600320, 'steps': 8984, 'loss/train': 1.7191730737686157}
-03/04/2022 00:00:49 - INFO - codeparrot_training - Step 8985: {'lr': 0.0004972570153909763, 'samples': 4600832, 'steps': 8985, 'loss/train': 1.8866649866104126}
-03/04/2022 00:00:51 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/04/2022 00:00:54 - INFO - codeparrot_training - Step 8986: {'lr': 0.0004972562313817735, 'samples': 4601344, 'steps': 8986, 'loss/train': 2.704766273498535}
-03/04/2022 00:00:57 - INFO - codeparrot_training - Step 8987: {'lr': 0.0004972554472611609, 'samples': 4601856, 'steps': 8987, 'loss/train': 2.2413125038146973}
-03/04/2022 00:00:59 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 00:01:03 - INFO - codeparrot_training - Step 8988: {'lr': 0.0004972546630291387, 'samples': 4602368, 'steps': 8988, 'loss/train': 2.3253941535949707}
-03/04/2022 00:01:06 - INFO - codeparrot_training - Step 8989: {'lr': 0.0004972538786857073, 'samples': 4602880, 'steps': 8989, 'loss/train': 2.6403563022613525}
-03/04/2022 00:01:08 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/04/2022 00:01:11 - INFO - codeparrot_training - Step 8990: {'lr': 0.0004972530942308673, 'samples': 4603392, 'steps': 8990, 'loss/train': 2.2609291076660156}
-03/04/2022 00:01:14 - INFO - codeparrot_training - Step 8991: {'lr': 0.0004972523096646188, 'samples': 4603904, 'steps': 8991, 'loss/train': 2.1980526447296143}
-03/04/2022 00:01:17 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 00:01:20 - INFO - codeparrot_training - Step 8992: {'lr': 0.0004972515249869622, 'samples': 4604416, 'steps': 8992, 'loss/train': 1.718159556388855}
-03/04/2022 00:01:23 - INFO - codeparrot_training - Step 8993: {'lr': 0.000497250740197898, 'samples': 4604928, 'steps': 8993, 'loss/train': 1.185468077659607}
-03/04/2022 00:01:25 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/04/2022 00:01:28 - INFO - codeparrot_training - Step 8994: {'lr': 0.0004972499552974263, 'samples': 4605440, 'steps': 8994, 'loss/train': 2.4599251747131348}
-03/04/2022 00:01:31 - INFO - codeparrot_training - Step 8995: {'lr': 0.0004972491702855477, 'samples': 4605952, 'steps': 8995, 'loss/train': 1.7005133628845215}
-03/04/2022 00:01:33 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/04/2022 00:01:37 - INFO - codeparrot_training - Step 8996: {'lr': 0.0004972483851622623, 'samples': 4606464, 'steps': 8996, 'loss/train': 2.0989480018615723}
-03/04/2022 00:01:40 - INFO - codeparrot_training - Step 8997: {'lr': 0.0004972475999275707, 'samples': 4606976, 'steps': 8997, 'loss/train': 1.4816687107086182}
-03/04/2022 00:01:43 - INFO - codeparrot_training - Step 8998: {'lr': 0.0004972468145814729, 'samples': 4607488, 'steps': 8998, 'loss/train': 1.337216854095459}
-03/04/2022 00:01:43 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/04/2022 00:01:48 - INFO - codeparrot_training - Step 8999: {'lr': 0.0004972460291239697, 'samples': 4608000, 'steps': 8999, 'loss/train': 2.579653024673462}
-03/04/2022 00:01:51 - INFO - codeparrot_training - Step 9000: {'lr': 0.0004972452435550613, 'samples': 4608512, 'steps': 9000, 'loss/train': 1.8396145105361938}
-03/04/2022 00:01:52 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 00:01:57 - INFO - codeparrot_training - Step 9001: {'lr': 0.000497244457874748, 'samples': 4609024, 'steps': 9001, 'loss/train': 2.5854663848876953}
-03/04/2022 00:02:00 - INFO - codeparrot_training - Step 9002: {'lr': 0.0004972436720830301, 'samples': 4609536, 'steps': 9002, 'loss/train': 2.121323823928833}
-03/04/2022 00:02:00 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/04/2022 00:02:05 - INFO - codeparrot_training - Step 9003: {'lr': 0.000497242886179908, 'samples': 4610048, 'steps': 9003, 'loss/train': 3.3667681217193604}
-03/04/2022 00:02:08 - INFO - codeparrot_training - Step 9004: {'lr': 0.0004972421001653822, 'samples': 4610560, 'steps': 9004, 'loss/train': 1.5536354780197144}
-03/04/2022 00:02:08 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 00:02:14 - INFO - codeparrot_training - Step 9005: {'lr': 0.0004972413140394528, 'samples': 4611072, 'steps': 9005, 'loss/train': 2.7773475646972656}
-03/04/2022 00:02:17 - INFO - codeparrot_training - Step 9006: {'lr': 0.0004972405278021203, 'samples': 4611584, 'steps': 9006, 'loss/train': 2.4572625160217285}
-03/04/2022 00:02:17 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/04/2022 00:02:22 - INFO - codeparrot_training - Step 9007: {'lr': 0.000497239741453385, 'samples': 4612096, 'steps': 9007, 'loss/train': 1.6892445087432861}
-03/04/2022 00:02:25 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/04/2022 00:02:27 - INFO - codeparrot_training - Step 9008: {'lr': 0.0004972389549932473, 'samples': 4612608, 'steps': 9008, 'loss/train': 2.6916863918304443}
-03/04/2022 00:02:30 - INFO - codeparrot_training - Step 9009: {'lr': 0.0004972381684217077, 'samples': 4613120, 'steps': 9009, 'loss/train': 2.2734436988830566}
-03/04/2022 00:02:34 - INFO - codeparrot_training - Step 9010: {'lr': 0.0004972373817387662, 'samples': 4613632, 'steps': 9010, 'loss/train': 0.7273611426353455}
-03/04/2022 00:02:34 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/04/2022 00:02:39 - INFO - codeparrot_training - Step 9011: {'lr': 0.0004972365949444234, 'samples': 4614144, 'steps': 9011, 'loss/train': 2.0393879413604736}
-03/04/2022 00:02:42 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/04/2022 00:02:44 - INFO - codeparrot_training - Step 9012: {'lr': 0.0004972358080386796, 'samples': 4614656, 'steps': 9012, 'loss/train': 2.3545138835906982}
-03/04/2022 00:02:47 - INFO - codeparrot_training - Step 9013: {'lr': 0.0004972350210215353, 'samples': 4615168, 'steps': 9013, 'loss/train': 2.3259756565093994}
-03/04/2022 00:02:50 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/04/2022 00:02:53 - INFO - codeparrot_training - Step 9014: {'lr': 0.0004972342338929906, 'samples': 4615680, 'steps': 9014, 'loss/train': 1.4579530954360962}
-03/04/2022 00:02:56 - INFO - codeparrot_training - Step 9015: {'lr': 0.000497233446653046, 'samples': 4616192, 'steps': 9015, 'loss/train': 2.094773292541504}
-03/04/2022 00:02:59 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/04/2022 00:03:01 - INFO - codeparrot_training - Step 9016: {'lr': 0.0004972326593017017, 'samples': 4616704, 'steps': 9016, 'loss/train': 2.7726006507873535}
-03/04/2022 00:03:04 - INFO - codeparrot_training - Step 9017: {'lr': 0.0004972318718389583, 'samples': 4617216, 'steps': 9017, 'loss/train': 2.352724075317383}
-03/04/2022 00:03:07 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 00:03:09 - INFO - codeparrot_training - Step 9018: {'lr': 0.000497231084264816, 'samples': 4617728, 'steps': 9018, 'loss/train': 3.0550310611724854}
-03/04/2022 00:03:13 - INFO - codeparrot_training - Step 9019: {'lr': 0.0004972302965792752, 'samples': 4618240, 'steps': 9019, 'loss/train': 0.2650966942310333}
-03/04/2022 00:03:15 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 00:03:18 - INFO - codeparrot_training - Step 9020: {'lr': 0.0004972295087823362, 'samples': 4618752, 'steps': 9020, 'loss/train': 1.9747211933135986}
-03/04/2022 00:03:21 - INFO - codeparrot_training - Step 9021: {'lr': 0.0004972287208739995, 'samples': 4619264, 'steps': 9021, 'loss/train': 1.5798276662826538}
-03/04/2022 00:03:24 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 00:03:26 - INFO - codeparrot_training - Step 9022: {'lr': 0.0004972279328542652, 'samples': 4619776, 'steps': 9022, 'loss/train': 1.9499232769012451}
-03/04/2022 00:03:30 - INFO - codeparrot_training - Step 9023: {'lr': 0.000497227144723134, 'samples': 4620288, 'steps': 9023, 'loss/train': 2.2091829776763916}
-03/04/2022 00:03:32 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 00:03:35 - INFO - codeparrot_training - Step 9024: {'lr': 0.0004972263564806059, 'samples': 4620800, 'steps': 9024, 'loss/train': 2.5814900398254395}
-03/04/2022 00:03:38 - INFO - codeparrot_training - Step 9025: {'lr': 0.0004972255681266816, 'samples': 4621312, 'steps': 9025, 'loss/train': 2.5704336166381836}
-03/04/2022 00:03:41 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/04/2022 00:03:43 - INFO - codeparrot_training - Step 9026: {'lr': 0.0004972247796613611, 'samples': 4621824, 'steps': 9026, 'loss/train': 2.3188209533691406}
-03/04/2022 00:03:46 - INFO - codeparrot_training - Step 9027: {'lr': 0.000497223991084645, 'samples': 4622336, 'steps': 9027, 'loss/train': 1.8715304136276245}
-03/04/2022 00:03:49 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 00:03:52 - INFO - codeparrot_training - Step 9028: {'lr': 0.0004972232023965335, 'samples': 4622848, 'steps': 9028, 'loss/train': 2.255889415740967}
-03/04/2022 00:03:55 - INFO - codeparrot_training - Step 9029: {'lr': 0.0004972224135970271, 'samples': 4623360, 'steps': 9029, 'loss/train': 1.9368693828582764}
-03/04/2022 00:03:57 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/04/2022 00:04:00 - INFO - codeparrot_training - Step 9030: {'lr': 0.0004972216246861262, 'samples': 4623872, 'steps': 9030, 'loss/train': 2.859152317047119}
-03/04/2022 00:04:03 - INFO - codeparrot_training - Step 9031: {'lr': 0.0004972208356638309, 'samples': 4624384, 'steps': 9031, 'loss/train': 2.1196961402893066}
-03/04/2022 00:04:06 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/04/2022 00:04:08 - INFO - codeparrot_training - Step 9032: {'lr': 0.0004972200465301418, 'samples': 4624896, 'steps': 9032, 'loss/train': 1.498255968093872}
-03/04/2022 00:04:12 - INFO - codeparrot_training - Step 9033: {'lr': 0.0004972192572850592, 'samples': 4625408, 'steps': 9033, 'loss/train': 1.9365074634552002}
-03/04/2022 00:04:14 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 00:04:17 - INFO - codeparrot_training - Step 9034: {'lr': 0.0004972184679285833, 'samples': 4625920, 'steps': 9034, 'loss/train': 2.234527826309204}
-03/04/2022 00:04:20 - INFO - codeparrot_training - Step 9035: {'lr': 0.0004972176784607146, 'samples': 4626432, 'steps': 9035, 'loss/train': 2.251316785812378}
-03/04/2022 00:04:22 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 00:04:25 - INFO - codeparrot_training - Step 9036: {'lr': 0.0004972168888814533, 'samples': 4626944, 'steps': 9036, 'loss/train': 1.0023348331451416}
-03/04/2022 00:04:28 - INFO - codeparrot_training - Step 9037: {'lr': 0.0004972160991908001, 'samples': 4627456, 'steps': 9037, 'loss/train': 2.4653167724609375}
-03/04/2022 00:04:31 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 00:04:34 - INFO - codeparrot_training - Step 9038: {'lr': 0.0004972153093887551, 'samples': 4627968, 'steps': 9038, 'loss/train': 2.2996695041656494}
-03/04/2022 00:04:37 - INFO - codeparrot_training - Step 9039: {'lr': 0.0004972145194753186, 'samples': 4628480, 'steps': 9039, 'loss/train': 2.157262086868286}
-03/04/2022 00:04:40 - INFO - codeparrot_training - Step 9040: {'lr': 0.0004972137294504912, 'samples': 4628992, 'steps': 9040, 'loss/train': 2.4803836345672607}
-03/04/2022 00:04:42 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/04/2022 00:04:46 - INFO - codeparrot_training - Step 9041: {'lr': 0.000497212939314273, 'samples': 4629504, 'steps': 9041, 'loss/train': 1.807188630104065}
-03/04/2022 00:04:49 - INFO - codeparrot_training - Step 9042: {'lr': 0.0004972121490666644, 'samples': 4630016, 'steps': 9042, 'loss/train': 1.9781190156936646}
-03/04/2022 00:04:50 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 00:04:54 - INFO - codeparrot_training - Step 9043: {'lr': 0.000497211358707666, 'samples': 4630528, 'steps': 9043, 'loss/train': 0.9175982475280762}
-03/04/2022 00:04:57 - INFO - codeparrot_training - Step 9044: {'lr': 0.0004972105682372779, 'samples': 4631040, 'steps': 9044, 'loss/train': 1.8851444721221924}
-03/04/2022 00:04:59 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 00:05:03 - INFO - codeparrot_training - Step 9045: {'lr': 0.0004972097776555005, 'samples': 4631552, 'steps': 9045, 'loss/train': 1.9969651699066162}
-03/04/2022 00:05:06 - INFO - codeparrot_training - Step 9046: {'lr': 0.0004972089869623342, 'samples': 4632064, 'steps': 9046, 'loss/train': 1.4956594705581665}
-03/04/2022 00:05:07 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 00:05:11 - INFO - codeparrot_training - Step 9047: {'lr': 0.0004972081961577793, 'samples': 4632576, 'steps': 9047, 'loss/train': 1.6623129844665527}
-03/04/2022 00:05:14 - INFO - codeparrot_training - Step 9048: {'lr': 0.0004972074052418363, 'samples': 4633088, 'steps': 9048, 'loss/train': 2.2070302963256836}
-03/04/2022 00:05:16 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/04/2022 00:05:19 - INFO - codeparrot_training - Step 9049: {'lr': 0.0004972066142145055, 'samples': 4633600, 'steps': 9049, 'loss/train': 2.2197089195251465}
-03/04/2022 00:05:23 - INFO - codeparrot_training - Step 9050: {'lr': 0.0004972058230757871, 'samples': 4634112, 'steps': 9050, 'loss/train': 2.5924291610717773}
-03/04/2022 00:05:24 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/04/2022 00:05:28 - INFO - codeparrot_training - Step 9051: {'lr': 0.0004972050318256815, 'samples': 4634624, 'steps': 9051, 'loss/train': 2.251307487487793}
-03/04/2022 00:05:31 - INFO - codeparrot_training - Step 9052: {'lr': 0.0004972042404641893, 'samples': 4635136, 'steps': 9052, 'loss/train': 1.6020134687423706}
-03/04/2022 00:05:33 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 00:05:36 - INFO - codeparrot_training - Step 9053: {'lr': 0.0004972034489913106, 'samples': 4635648, 'steps': 9053, 'loss/train': 2.2249650955200195}
-03/04/2022 00:05:39 - INFO - codeparrot_training - Step 9054: {'lr': 0.0004972026574070459, 'samples': 4636160, 'steps': 9054, 'loss/train': 2.982018232345581}
-03/04/2022 00:05:41 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 00:05:45 - INFO - codeparrot_training - Step 9055: {'lr': 0.0004972018657113953, 'samples': 4636672, 'steps': 9055, 'loss/train': 1.0131844282150269}
-03/04/2022 00:05:48 - INFO - codeparrot_training - Step 9056: {'lr': 0.0004972010739043596, 'samples': 4637184, 'steps': 9056, 'loss/train': 1.5396931171417236}
-03/04/2022 00:05:50 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/04/2022 00:05:54 - INFO - codeparrot_training - Step 9057: {'lr': 0.0004972002819859388, 'samples': 4637696, 'steps': 9057, 'loss/train': 0.406387060880661}
-03/04/2022 00:05:57 - INFO - codeparrot_training - Step 9058: {'lr': 0.0004971994899561334, 'samples': 4638208, 'steps': 9058, 'loss/train': 2.848292589187622}
-03/04/2022 00:06:00 - INFO - codeparrot_training - Step 9059: {'lr': 0.0004971986978149437, 'samples': 4638720, 'steps': 9059, 'loss/train': 1.79661226272583}
-03/04/2022 00:06:00 - INFO - codeparrot_training - Skipping example with length 1010 (seq_length=1024)
-03/04/2022 00:06:05 - INFO - codeparrot_training - Step 9060: {'lr': 0.0004971979055623701, 'samples': 4639232, 'steps': 9060, 'loss/train': 1.8307733535766602}
-03/04/2022 00:06:08 - INFO - codeparrot_training - Step 9061: {'lr': 0.0004971971131984129, 'samples': 4639744, 'steps': 9061, 'loss/train': 2.1219799518585205}
-03/04/2022 00:06:09 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 00:06:13 - INFO - codeparrot_training - Step 9062: {'lr': 0.0004971963207230725, 'samples': 4640256, 'steps': 9062, 'loss/train': 2.801114797592163}
-03/04/2022 00:06:17 - INFO - codeparrot_training - Step 9063: {'lr': 0.0004971955281363493, 'samples': 4640768, 'steps': 9063, 'loss/train': 2.0024948120117188}
-03/04/2022 00:06:17 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/04/2022 00:06:22 - INFO - codeparrot_training - Step 9064: {'lr': 0.0004971947354382436, 'samples': 4641280, 'steps': 9064, 'loss/train': 2.601198673248291}
-03/04/2022 00:06:25 - INFO - codeparrot_training - Step 9065: {'lr': 0.0004971939426287557, 'samples': 4641792, 'steps': 9065, 'loss/train': 2.105930805206299}
-03/04/2022 00:06:25 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/04/2022 00:06:30 - INFO - codeparrot_training - Step 9066: {'lr': 0.0004971931497078861, 'samples': 4642304, 'steps': 9066, 'loss/train': 2.0523157119750977}
-03/04/2022 00:06:33 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/04/2022 00:06:36 - INFO - codeparrot_training - Step 9067: {'lr': 0.000497192356675635, 'samples': 4642816, 'steps': 9067, 'loss/train': 2.0319736003875732}
-03/04/2022 00:06:39 - INFO - codeparrot_training - Step 9068: {'lr': 0.0004971915635320029, 'samples': 4643328, 'steps': 9068, 'loss/train': 2.136533498764038}
-03/04/2022 00:06:41 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 00:06:45 - INFO - codeparrot_training - Step 9069: {'lr': 0.0004971907702769901, 'samples': 4643840, 'steps': 9069, 'loss/train': 2.6957836151123047}
-03/04/2022 00:06:48 - INFO - codeparrot_training - Step 9070: {'lr': 0.000497189976910597, 'samples': 4644352, 'steps': 9070, 'loss/train': 2.472384452819824}
-03/04/2022 00:06:51 - INFO - codeparrot_training - Step 9071: {'lr': 0.0004971891834328238, 'samples': 4644864, 'steps': 9071, 'loss/train': 2.325106620788574}
-03/04/2022 00:06:53 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/04/2022 00:06:57 - INFO - codeparrot_training - Step 9072: {'lr': 0.000497188389843671, 'samples': 4645376, 'steps': 9072, 'loss/train': 2.6898906230926514}
-03/04/2022 00:07:00 - INFO - codeparrot_training - Step 9073: {'lr': 0.0004971875961431389, 'samples': 4645888, 'steps': 9073, 'loss/train': 2.790247678756714}
-03/04/2022 00:07:02 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/04/2022 00:07:05 - INFO - codeparrot_training - Step 9074: {'lr': 0.000497186802331228, 'samples': 4646400, 'steps': 9074, 'loss/train': 2.1303107738494873}
-03/04/2022 00:07:08 - INFO - codeparrot_training - Step 9075: {'lr': 0.0004971860084079385, 'samples': 4646912, 'steps': 9075, 'loss/train': 1.9852224588394165}
-03/04/2022 00:07:10 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 00:07:13 - INFO - codeparrot_training - Step 9076: {'lr': 0.0004971852143732707, 'samples': 4647424, 'steps': 9076, 'loss/train': 2.0250940322875977}
-03/04/2022 00:07:16 - INFO - codeparrot_training - Step 9077: {'lr': 0.0004971844202272251, 'samples': 4647936, 'steps': 9077, 'loss/train': 1.8596994876861572}
-03/04/2022 00:07:19 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 00:07:22 - INFO - codeparrot_training - Step 9078: {'lr': 0.000497183625969802, 'samples': 4648448, 'steps': 9078, 'loss/train': 1.6442407369613647}
-03/04/2022 00:07:25 - INFO - codeparrot_training - Step 9079: {'lr': 0.0004971828316010019, 'samples': 4648960, 'steps': 9079, 'loss/train': 2.421541452407837}
-03/04/2022 00:07:27 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 00:07:30 - INFO - codeparrot_training - Step 9080: {'lr': 0.0004971820371208248, 'samples': 4649472, 'steps': 9080, 'loss/train': 2.352616786956787}
-03/04/2022 00:07:33 - INFO - codeparrot_training - Step 9081: {'lr': 0.0004971812425292716, 'samples': 4649984, 'steps': 9081, 'loss/train': 2.5102672576904297}
-03/04/2022 00:07:36 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/04/2022 00:07:39 - INFO - codeparrot_training - Step 9082: {'lr': 0.000497180447826342, 'samples': 4650496, 'steps': 9082, 'loss/train': 2.235490322113037}
-03/04/2022 00:07:42 - INFO - codeparrot_training - Step 9083: {'lr': 0.0004971796530120371, 'samples': 4651008, 'steps': 9083, 'loss/train': 2.053041458129883}
-03/04/2022 00:07:44 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/04/2022 00:07:47 - INFO - codeparrot_training - Step 9084: {'lr': 0.0004971788580863566, 'samples': 4651520, 'steps': 9084, 'loss/train': 1.9689538478851318}
-03/04/2022 00:07:50 - INFO - codeparrot_training - Step 9085: {'lr': 0.0004971780630493012, 'samples': 4652032, 'steps': 9085, 'loss/train': 2.6735646724700928}
-03/04/2022 00:07:52 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/04/2022 00:07:55 - INFO - codeparrot_training - Step 9086: {'lr': 0.000497177267900871, 'samples': 4652544, 'steps': 9086, 'loss/train': 3.3302242755889893}
-03/04/2022 00:07:59 - INFO - codeparrot_training - Step 9087: {'lr': 0.0004971764726410668, 'samples': 4653056, 'steps': 9087, 'loss/train': 1.9385889768600464}
-03/04/2022 00:08:00 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/04/2022 00:08:04 - INFO - codeparrot_training - Step 9088: {'lr': 0.0004971756772698886, 'samples': 4653568, 'steps': 9088, 'loss/train': 1.9992214441299438}
-03/04/2022 00:08:07 - INFO - codeparrot_training - Step 9089: {'lr': 0.0004971748817873367, 'samples': 4654080, 'steps': 9089, 'loss/train': 1.7595837116241455}
-03/04/2022 00:08:09 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 00:08:12 - INFO - codeparrot_training - Step 9090: {'lr': 0.0004971740861934117, 'samples': 4654592, 'steps': 9090, 'loss/train': 2.2323944568634033}
-03/04/2022 00:08:16 - INFO - codeparrot_training - Step 9091: {'lr': 0.000497173290488114, 'samples': 4655104, 'steps': 9091, 'loss/train': 2.270265817642212}
-03/04/2022 00:08:17 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 00:08:21 - INFO - codeparrot_training - Step 9092: {'lr': 0.0004971724946714437, 'samples': 4655616, 'steps': 9092, 'loss/train': 1.8248450756072998}
-03/04/2022 00:08:24 - INFO - codeparrot_training - Step 9093: {'lr': 0.0004971716987434014, 'samples': 4656128, 'steps': 9093, 'loss/train': 2.175438404083252}
-03/04/2022 00:08:26 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 00:08:29 - INFO - codeparrot_training - Step 9094: {'lr': 0.0004971709027039872, 'samples': 4656640, 'steps': 9094, 'loss/train': 1.9532558917999268}
-03/04/2022 00:08:32 - INFO - codeparrot_training - Step 9095: {'lr': 0.0004971701065532017, 'samples': 4657152, 'steps': 9095, 'loss/train': 1.5464744567871094}
-03/04/2022 00:08:34 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/04/2022 00:08:38 - INFO - codeparrot_training - Step 9096: {'lr': 0.0004971693102910451, 'samples': 4657664, 'steps': 9096, 'loss/train': 1.8456026315689087}
-03/04/2022 00:08:41 - INFO - codeparrot_training - Step 9097: {'lr': 0.0004971685139175179, 'samples': 4658176, 'steps': 9097, 'loss/train': 0.9368131756782532}
-03/04/2022 00:08:43 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 00:08:46 - INFO - codeparrot_training - Step 9098: {'lr': 0.0004971677174326204, 'samples': 4658688, 'steps': 9098, 'loss/train': 2.611689329147339}
-03/04/2022 00:08:49 - INFO - codeparrot_training - Step 9099: {'lr': 0.0004971669208363529, 'samples': 4659200, 'steps': 9099, 'loss/train': 2.718707799911499}
-03/04/2022 00:08:51 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/04/2022 00:08:54 - INFO - codeparrot_training - Step 9100: {'lr': 0.0004971661241287157, 'samples': 4659712, 'steps': 9100, 'loss/train': 2.494258403778076}
-03/04/2022 00:08:58 - INFO - codeparrot_training - Step 9101: {'lr': 0.0004971653273097094, 'samples': 4660224, 'steps': 9101, 'loss/train': 1.6545171737670898}
-03/04/2022 00:08:59 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/04/2022 00:09:03 - INFO - codeparrot_training - Step 9102: {'lr': 0.0004971645303793342, 'samples': 4660736, 'steps': 9102, 'loss/train': 2.688467502593994}
-03/04/2022 00:09:06 - INFO - codeparrot_training - Step 9103: {'lr': 0.0004971637333375904, 'samples': 4661248, 'steps': 9103, 'loss/train': 1.412266731262207}
-03/04/2022 00:09:07 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/04/2022 00:09:11 - INFO - codeparrot_training - Step 9104: {'lr': 0.0004971629361844785, 'samples': 4661760, 'steps': 9104, 'loss/train': 2.8501226902008057}
-03/04/2022 00:09:15 - INFO - codeparrot_training - Step 9105: {'lr': 0.0004971621389199988, 'samples': 4662272, 'steps': 9105, 'loss/train': 2.5824766159057617}
-03/04/2022 00:09:17 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/04/2022 00:09:20 - INFO - codeparrot_training - Step 9106: {'lr': 0.0004971613415441516, 'samples': 4662784, 'steps': 9106, 'loss/train': 2.467329263687134}
-03/04/2022 00:09:23 - INFO - codeparrot_training - Step 9107: {'lr': 0.0004971605440569374, 'samples': 4663296, 'steps': 9107, 'loss/train': 2.4916627407073975}
-03/04/2022 00:09:25 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/04/2022 00:09:28 - INFO - codeparrot_training - Step 9108: {'lr': 0.0004971597464583563, 'samples': 4663808, 'steps': 9108, 'loss/train': 2.517822027206421}
-03/04/2022 00:09:31 - INFO - codeparrot_training - Step 9109: {'lr': 0.0004971589487484091, 'samples': 4664320, 'steps': 9109, 'loss/train': 1.6906667947769165}
-03/04/2022 00:09:34 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/04/2022 00:09:37 - INFO - codeparrot_training - Step 9110: {'lr': 0.0004971581509270956, 'samples': 4664832, 'steps': 9110, 'loss/train': 2.519517660140991}
-03/04/2022 00:09:40 - INFO - codeparrot_training - Step 9111: {'lr': 0.0004971573529944167, 'samples': 4665344, 'steps': 9111, 'loss/train': 2.5152361392974854}
-03/04/2022 00:09:42 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 00:09:45 - INFO - codeparrot_training - Step 9112: {'lr': 0.0004971565549503723, 'samples': 4665856, 'steps': 9112, 'loss/train': 2.3143529891967773}
-03/04/2022 00:09:48 - INFO - codeparrot_training - Step 9113: {'lr': 0.0004971557567949631, 'samples': 4666368, 'steps': 9113, 'loss/train': 2.0240516662597656}
-03/04/2022 00:09:50 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 00:09:54 - INFO - codeparrot_training - Step 9114: {'lr': 0.0004971549585281893, 'samples': 4666880, 'steps': 9114, 'loss/train': 2.446852684020996}
-03/04/2022 00:09:57 - INFO - codeparrot_training - Step 9115: {'lr': 0.0004971541601500513, 'samples': 4667392, 'steps': 9115, 'loss/train': 2.324359178543091}
-03/04/2022 00:09:59 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/04/2022 00:10:02 - INFO - codeparrot_training - Step 9116: {'lr': 0.0004971533616605495, 'samples': 4667904, 'steps': 9116, 'loss/train': 2.1932291984558105}
-03/04/2022 00:10:05 - INFO - codeparrot_training - Step 9117: {'lr': 0.0004971525630596841, 'samples': 4668416, 'steps': 9117, 'loss/train': 1.7494590282440186}
-03/04/2022 00:10:07 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/04/2022 00:10:10 - INFO - codeparrot_training - Step 9118: {'lr': 0.0004971517643474556, 'samples': 4668928, 'steps': 9118, 'loss/train': 1.6420814990997314}
-03/04/2022 00:10:14 - INFO - codeparrot_training - Step 9119: {'lr': 0.0004971509655238643, 'samples': 4669440, 'steps': 9119, 'loss/train': 1.1768712997436523}
-03/04/2022 00:10:15 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/04/2022 00:10:19 - INFO - codeparrot_training - Step 9120: {'lr': 0.0004971501665889107, 'samples': 4669952, 'steps': 9120, 'loss/train': 1.7133654356002808}
-03/04/2022 00:10:22 - INFO - codeparrot_training - Step 9121: {'lr': 0.000497149367542595, 'samples': 4670464, 'steps': 9121, 'loss/train': 1.8094708919525146}
-03/04/2022 00:10:24 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/04/2022 00:10:27 - INFO - codeparrot_training - Step 9122: {'lr': 0.0004971485683849176, 'samples': 4670976, 'steps': 9122, 'loss/train': 1.9677802324295044}
-03/04/2022 00:10:31 - INFO - codeparrot_training - Step 9123: {'lr': 0.0004971477691158788, 'samples': 4671488, 'steps': 9123, 'loss/train': 2.506824016571045}
-03/04/2022 00:10:32 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 00:10:36 - INFO - codeparrot_training - Step 9124: {'lr': 0.0004971469697354792, 'samples': 4672000, 'steps': 9124, 'loss/train': 2.3262240886688232}
-03/04/2022 00:10:39 - INFO - codeparrot_training - Step 9125: {'lr': 0.0004971461702437188, 'samples': 4672512, 'steps': 9125, 'loss/train': 2.210357427597046}
-03/04/2022 00:10:41 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 00:10:44 - INFO - codeparrot_training - Step 9126: {'lr': 0.0004971453706405981, 'samples': 4673024, 'steps': 9126, 'loss/train': 1.2480789422988892}
-03/04/2022 00:10:47 - INFO - codeparrot_training - Step 9127: {'lr': 0.0004971445709261177, 'samples': 4673536, 'steps': 9127, 'loss/train': 2.470043420791626}
-03/04/2022 00:10:49 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/04/2022 00:10:53 - INFO - codeparrot_training - Step 9128: {'lr': 0.0004971437711002777, 'samples': 4674048, 'steps': 9128, 'loss/train': 1.7962679862976074}
-03/04/2022 00:10:56 - INFO - codeparrot_training - Step 9129: {'lr': 0.0004971429711630786, 'samples': 4674560, 'steps': 9129, 'loss/train': 1.5672799348831177}
-03/04/2022 00:10:57 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/04/2022 00:11:01 - INFO - codeparrot_training - Step 9130: {'lr': 0.0004971421711145207, 'samples': 4675072, 'steps': 9130, 'loss/train': 2.732600688934326}
-03/04/2022 00:11:04 - INFO - codeparrot_training - Step 9131: {'lr': 0.0004971413709546043, 'samples': 4675584, 'steps': 9131, 'loss/train': 1.8835409879684448}
-03/04/2022 00:11:05 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/04/2022 00:11:10 - INFO - codeparrot_training - Step 9132: {'lr': 0.0004971405706833297, 'samples': 4676096, 'steps': 9132, 'loss/train': 2.5379555225372314}
-03/04/2022 00:11:13 - INFO - codeparrot_training - Step 9133: {'lr': 0.0004971397703006974, 'samples': 4676608, 'steps': 9133, 'loss/train': 1.6221462488174438}
-03/04/2022 00:11:14 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 00:11:18 - INFO - codeparrot_training - Step 9134: {'lr': 0.0004971389698067079, 'samples': 4677120, 'steps': 9134, 'loss/train': 2.777493476867676}
-03/04/2022 00:11:21 - INFO - codeparrot_training - Step 9135: {'lr': 0.0004971381692013612, 'samples': 4677632, 'steps': 9135, 'loss/train': 0.2916344702243805}
-03/04/2022 00:11:22 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 00:11:26 - INFO - codeparrot_training - Step 9136: {'lr': 0.000497137368484658, 'samples': 4678144, 'steps': 9136, 'loss/train': 2.402660608291626}
-03/04/2022 00:11:30 - INFO - codeparrot_training - Step 9137: {'lr': 0.0004971365676565984, 'samples': 4678656, 'steps': 9137, 'loss/train': 2.206514596939087}
-03/04/2022 00:11:30 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 00:11:35 - INFO - codeparrot_training - Step 9138: {'lr': 0.000497135766717183, 'samples': 4679168, 'steps': 9138, 'loss/train': 1.5953739881515503}
-03/04/2022 00:11:38 - INFO - codeparrot_training - Step 9139: {'lr': 0.000497134965666412, 'samples': 4679680, 'steps': 9139, 'loss/train': 1.4503148794174194}
-03/04/2022 00:11:39 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 00:11:43 - INFO - codeparrot_training - Step 9140: {'lr': 0.0004971341645042857, 'samples': 4680192, 'steps': 9140, 'loss/train': 1.2308696508407593}
-03/04/2022 00:11:46 - INFO - codeparrot_training - Step 9141: {'lr': 0.0004971333632308047, 'samples': 4680704, 'steps': 9141, 'loss/train': 1.908644676208496}
-03/04/2022 00:11:48 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/04/2022 00:11:52 - INFO - codeparrot_training - Step 9142: {'lr': 0.0004971325618459691, 'samples': 4681216, 'steps': 9142, 'loss/train': 1.8476554155349731}
-03/04/2022 00:11:55 - INFO - codeparrot_training - Step 9143: {'lr': 0.0004971317603497795, 'samples': 4681728, 'steps': 9143, 'loss/train': 1.950243353843689}
-03/04/2022 00:11:56 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 00:12:00 - INFO - codeparrot_training - Step 9144: {'lr': 0.000497130958742236, 'samples': 4682240, 'steps': 9144, 'loss/train': 1.6114853620529175}
-03/04/2022 00:12:03 - INFO - codeparrot_training - Step 9145: {'lr': 0.0004971301570233392, 'samples': 4682752, 'steps': 9145, 'loss/train': 1.9855722188949585}
-03/04/2022 00:12:04 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 00:12:08 - INFO - codeparrot_training - Step 9146: {'lr': 0.0004971293551930894, 'samples': 4683264, 'steps': 9146, 'loss/train': 2.1744041442871094}
-03/04/2022 00:12:12 - INFO - codeparrot_training - Step 9147: {'lr': 0.0004971285532514868, 'samples': 4683776, 'steps': 9147, 'loss/train': 1.295291543006897}
-03/04/2022 00:12:13 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 00:12:17 - INFO - codeparrot_training - Step 9148: {'lr': 0.000497127751198532, 'samples': 4684288, 'steps': 9148, 'loss/train': 2.1508522033691406}
-03/04/2022 00:12:20 - INFO - codeparrot_training - Step 9149: {'lr': 0.0004971269490342252, 'samples': 4684800, 'steps': 9149, 'loss/train': 2.9311535358428955}
-03/04/2022 00:12:21 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 00:12:25 - INFO - codeparrot_training - Step 9150: {'lr': 0.0004971261467585669, 'samples': 4685312, 'steps': 9150, 'loss/train': 2.5363738536834717}
-03/04/2022 00:12:29 - INFO - codeparrot_training - Step 9151: {'lr': 0.0004971253443715572, 'samples': 4685824, 'steps': 9151, 'loss/train': 2.5854365825653076}
-03/04/2022 00:12:30 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 00:12:34 - INFO - codeparrot_training - Step 9152: {'lr': 0.0004971245418731966, 'samples': 4686336, 'steps': 9152, 'loss/train': 1.6187406778335571}
-03/04/2022 00:12:37 - INFO - codeparrot_training - Step 9153: {'lr': 0.0004971237392634857, 'samples': 4686848, 'steps': 9153, 'loss/train': 2.5293545722961426}
-03/04/2022 00:12:38 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 00:12:42 - INFO - codeparrot_training - Step 9154: {'lr': 0.0004971229365424246, 'samples': 4687360, 'steps': 9154, 'loss/train': 2.0076918601989746}
-03/04/2022 00:12:45 - INFO - codeparrot_training - Step 9155: {'lr': 0.0004971221337100137, 'samples': 4687872, 'steps': 9155, 'loss/train': 0.9001452922821045}
-03/04/2022 00:12:46 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/04/2022 00:12:51 - INFO - codeparrot_training - Step 9156: {'lr': 0.0004971213307662534, 'samples': 4688384, 'steps': 9156, 'loss/train': 1.1213743686676025}
-03/04/2022 00:12:54 - INFO - codeparrot_training - Step 9157: {'lr': 0.000497120527711144, 'samples': 4688896, 'steps': 9157, 'loss/train': 3.577561855316162}
-03/04/2022 00:12:55 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/04/2022 00:12:59 - INFO - codeparrot_training - Step 9158: {'lr': 0.0004971197245446859, 'samples': 4689408, 'steps': 9158, 'loss/train': 1.4750983715057373}
-03/04/2022 00:13:03 - INFO - codeparrot_training - Step 9159: {'lr': 0.0004971189212668794, 'samples': 4689920, 'steps': 9159, 'loss/train': 1.5602471828460693}
-03/04/2022 00:13:03 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/04/2022 00:13:08 - INFO - codeparrot_training - Step 9160: {'lr': 0.0004971181178777251, 'samples': 4690432, 'steps': 9160, 'loss/train': 1.3662967681884766}
-03/04/2022 00:13:11 - INFO - codeparrot_training - Step 9161: {'lr': 0.0004971173143772231, 'samples': 4690944, 'steps': 9161, 'loss/train': 0.6085817813873291}
-03/04/2022 00:13:12 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/04/2022 00:13:16 - INFO - codeparrot_training - Step 9162: {'lr': 0.0004971165107653738, 'samples': 4691456, 'steps': 9162, 'loss/train': 1.4687438011169434}
-03/04/2022 00:13:19 - INFO - codeparrot_training - Step 9163: {'lr': 0.0004971157070421776, 'samples': 4691968, 'steps': 9163, 'loss/train': 3.961289882659912}
-03/04/2022 00:13:20 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/04/2022 00:13:25 - INFO - codeparrot_training - Step 9164: {'lr': 0.000497114903207635, 'samples': 4692480, 'steps': 9164, 'loss/train': 1.9571070671081543}
-03/04/2022 00:13:28 - INFO - codeparrot_training - Step 9165: {'lr': 0.0004971140992617462, 'samples': 4692992, 'steps': 9165, 'loss/train': 1.742238998413086}
-03/04/2022 00:13:29 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/04/2022 00:13:33 - INFO - codeparrot_training - Step 9166: {'lr': 0.0004971132952045115, 'samples': 4693504, 'steps': 9166, 'loss/train': 1.7008261680603027}
-03/04/2022 00:13:36 - INFO - codeparrot_training - Step 9167: {'lr': 0.0004971124910359315, 'samples': 4694016, 'steps': 9167, 'loss/train': 1.4614546298980713}
-03/04/2022 00:13:37 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/04/2022 00:13:41 - INFO - codeparrot_training - Step 9168: {'lr': 0.0004971116867560064, 'samples': 4694528, 'steps': 9168, 'loss/train': 2.392585039138794}
-03/04/2022 00:13:45 - INFO - codeparrot_training - Step 9169: {'lr': 0.0004971108823647365, 'samples': 4695040, 'steps': 9169, 'loss/train': 1.2194643020629883}
-03/04/2022 00:13:45 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/04/2022 00:13:51 - INFO - codeparrot_training - Step 9170: {'lr': 0.0004971100778621223, 'samples': 4695552, 'steps': 9170, 'loss/train': 2.100058078765869}
-03/04/2022 00:13:54 - INFO - codeparrot_training - Step 9171: {'lr': 0.0004971092732481641, 'samples': 4696064, 'steps': 9171, 'loss/train': 2.31742525100708}
-03/04/2022 00:13:57 - INFO - codeparrot_training - Step 9172: {'lr': 0.0004971084685228623, 'samples': 4696576, 'steps': 9172, 'loss/train': 2.2657110691070557}
-03/04/2022 00:13:57 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/04/2022 00:14:02 - INFO - codeparrot_training - Step 9173: {'lr': 0.0004971076636862172, 'samples': 4697088, 'steps': 9173, 'loss/train': 2.2101705074310303}
-03/04/2022 00:14:06 - INFO - codeparrot_training - Step 9174: {'lr': 0.0004971068587382293, 'samples': 4697600, 'steps': 9174, 'loss/train': 2.2633016109466553}
-03/04/2022 00:14:06 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 00:14:11 - INFO - codeparrot_training - Step 9175: {'lr': 0.0004971060536788988, 'samples': 4698112, 'steps': 9175, 'loss/train': 2.8278207778930664}
-03/04/2022 00:14:14 - INFO - codeparrot_training - Step 9176: {'lr': 0.000497105248508226, 'samples': 4698624, 'steps': 9176, 'loss/train': 0.6010805368423462}
-03/04/2022 00:14:14 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/04/2022 00:14:19 - INFO - codeparrot_training - Step 9177: {'lr': 0.0004971044432262115, 'samples': 4699136, 'steps': 9177, 'loss/train': 2.6464905738830566}
-03/04/2022 00:14:22 - INFO - codeparrot_training - Step 9178: {'lr': 0.0004971036378328556, 'samples': 4699648, 'steps': 9178, 'loss/train': 2.3429369926452637}
-03/04/2022 00:14:22 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 00:14:28 - INFO - codeparrot_training - Step 9179: {'lr': 0.0004971028323281586, 'samples': 4700160, 'steps': 9179, 'loss/train': 2.190965414047241}
-03/04/2022 00:14:31 - INFO - codeparrot_training - Step 9180: {'lr': 0.0004971020267121208, 'samples': 4700672, 'steps': 9180, 'loss/train': 1.3457450866699219}
-03/04/2022 00:14:31 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/04/2022 00:14:36 - INFO - codeparrot_training - Step 9181: {'lr': 0.0004971012209847427, 'samples': 4701184, 'steps': 9181, 'loss/train': 2.2540998458862305}
-03/04/2022 00:14:39 - INFO - codeparrot_training - Step 9182: {'lr': 0.0004971004151460245, 'samples': 4701696, 'steps': 9182, 'loss/train': 2.4382646083831787}
-03/04/2022 00:14:40 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/04/2022 00:14:45 - INFO - codeparrot_training - Step 9183: {'lr': 0.0004970996091959668, 'samples': 4702208, 'steps': 9183, 'loss/train': 1.7381292581558228}
-03/04/2022 00:14:48 - INFO - codeparrot_training - Step 9184: {'lr': 0.0004970988031345698, 'samples': 4702720, 'steps': 9184, 'loss/train': 2.7366058826446533}
-03/04/2022 00:14:48 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/04/2022 00:14:53 - INFO - codeparrot_training - Step 9185: {'lr': 0.0004970979969618338, 'samples': 4703232, 'steps': 9185, 'loss/train': 2.515939474105835}
-03/04/2022 00:14:56 - INFO - codeparrot_training - Step 9186: {'lr': 0.0004970971906777593, 'samples': 4703744, 'steps': 9186, 'loss/train': 2.388364315032959}
-03/04/2022 00:14:57 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/04/2022 00:15:02 - INFO - codeparrot_training - Step 9187: {'lr': 0.0004970963842823468, 'samples': 4704256, 'steps': 9187, 'loss/train': 1.4862236976623535}
-03/04/2022 00:15:05 - INFO - codeparrot_training - Step 9188: {'lr': 0.0004970955777755963, 'samples': 4704768, 'steps': 9188, 'loss/train': 2.1836283206939697}
-03/04/2022 00:15:05 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 00:15:10 - INFO - codeparrot_training - Step 9189: {'lr': 0.0004970947711575083, 'samples': 4705280, 'steps': 9189, 'loss/train': 2.6094751358032227}
-03/04/2022 00:15:13 - INFO - codeparrot_training - Step 9190: {'lr': 0.0004970939644280833, 'samples': 4705792, 'steps': 9190, 'loss/train': 1.682536244392395}
-03/04/2022 00:15:13 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 00:15:18 - INFO - codeparrot_training - Step 9191: {'lr': 0.0004970931575873215, 'samples': 4706304, 'steps': 9191, 'loss/train': 2.2799313068389893}
-03/04/2022 00:15:22 - INFO - codeparrot_training - Step 9192: {'lr': 0.0004970923506352234, 'samples': 4706816, 'steps': 9192, 'loss/train': 1.7466835975646973}
-03/04/2022 00:15:22 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/04/2022 00:15:27 - INFO - codeparrot_training - Step 9193: {'lr': 0.0004970915435717893, 'samples': 4707328, 'steps': 9193, 'loss/train': 0.9434108138084412}
-03/04/2022 00:15:30 - INFO - codeparrot_training - Step 9194: {'lr': 0.0004970907363970196, 'samples': 4707840, 'steps': 9194, 'loss/train': 2.391308546066284}
-03/04/2022 00:15:30 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 00:15:35 - INFO - codeparrot_training - Step 9195: {'lr': 0.0004970899291109145, 'samples': 4708352, 'steps': 9195, 'loss/train': 1.7782832384109497}
-03/04/2022 00:15:38 - INFO - codeparrot_training - Step 9196: {'lr': 0.0004970891217134746, 'samples': 4708864, 'steps': 9196, 'loss/train': 2.1954612731933594}
-03/04/2022 00:15:39 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/04/2022 00:15:44 - INFO - codeparrot_training - Step 9197: {'lr': 0.0004970883142047001, 'samples': 4709376, 'steps': 9197, 'loss/train': 1.8747104406356812}
-03/04/2022 00:15:47 - INFO - codeparrot_training - Step 9198: {'lr': 0.0004970875065845914, 'samples': 4709888, 'steps': 9198, 'loss/train': 2.3433029651641846}
-03/04/2022 00:15:47 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/04/2022 00:15:52 - INFO - codeparrot_training - Step 9199: {'lr': 0.000497086698853149, 'samples': 4710400, 'steps': 9199, 'loss/train': 1.7029879093170166}
-03/04/2022 00:15:55 - INFO - codeparrot_training - Step 9200: {'lr': 0.0004970858910103731, 'samples': 4710912, 'steps': 9200, 'loss/train': 1.414724349975586}
-03/04/2022 00:15:55 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/04/2022 00:16:01 - INFO - codeparrot_training - Step 9201: {'lr': 0.0004970850830562641, 'samples': 4711424, 'steps': 9201, 'loss/train': 2.1999356746673584}
-03/04/2022 00:16:04 - INFO - codeparrot_training - Step 9202: {'lr': 0.0004970842749908223, 'samples': 4711936, 'steps': 9202, 'loss/train': 2.368300199508667}
-03/04/2022 00:16:04 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 00:16:09 - INFO - codeparrot_training - Step 9203: {'lr': 0.0004970834668140482, 'samples': 4712448, 'steps': 9203, 'loss/train': 1.7902599573135376}
-03/04/2022 00:16:12 - INFO - codeparrot_training - Step 9204: {'lr': 0.0004970826585259421, 'samples': 4712960, 'steps': 9204, 'loss/train': 2.272139072418213}
-03/04/2022 00:16:12 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/04/2022 00:16:18 - INFO - codeparrot_training - Step 9205: {'lr': 0.0004970818501265044, 'samples': 4713472, 'steps': 9205, 'loss/train': 1.9960461854934692}
-03/04/2022 00:16:21 - INFO - codeparrot_training - Step 9206: {'lr': 0.0004970810416157354, 'samples': 4713984, 'steps': 9206, 'loss/train': 2.0456316471099854}
-03/04/2022 00:16:21 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/04/2022 00:16:26 - INFO - codeparrot_training - Step 9207: {'lr': 0.0004970802329936355, 'samples': 4714496, 'steps': 9207, 'loss/train': 2.7987544536590576}
-03/04/2022 00:16:29 - INFO - codeparrot_training - Step 9208: {'lr': 0.000497079424260205, 'samples': 4715008, 'steps': 9208, 'loss/train': 1.6508510112762451}
-03/04/2022 00:16:29 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/04/2022 00:16:34 - INFO - codeparrot_training - Step 9209: {'lr': 0.0004970786154154444, 'samples': 4715520, 'steps': 9209, 'loss/train': 2.237428665161133}
-03/04/2022 00:16:38 - INFO - codeparrot_training - Step 9210: {'lr': 0.000497077806459354, 'samples': 4716032, 'steps': 9210, 'loss/train': 4.445390701293945}
-03/04/2022 00:16:38 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/04/2022 00:16:43 - INFO - codeparrot_training - Step 9211: {'lr': 0.0004970769973919341, 'samples': 4716544, 'steps': 9211, 'loss/train': 1.8816496133804321}
-03/04/2022 00:16:46 - INFO - codeparrot_training - Step 9212: {'lr': 0.0004970761882131851, 'samples': 4717056, 'steps': 9212, 'loss/train': 0.6402844190597534}
-03/04/2022 00:16:48 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/04/2022 00:16:52 - INFO - codeparrot_training - Step 9213: {'lr': 0.0004970753789231074, 'samples': 4717568, 'steps': 9213, 'loss/train': 2.277432441711426}
-03/04/2022 00:16:55 - INFO - codeparrot_training - Step 9214: {'lr': 0.0004970745695217014, 'samples': 4718080, 'steps': 9214, 'loss/train': 2.170677661895752}
-03/04/2022 00:16:57 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/04/2022 00:17:00 - INFO - codeparrot_training - Step 9215: {'lr': 0.0004970737600089673, 'samples': 4718592, 'steps': 9215, 'loss/train': 2.0315778255462646}
-03/04/2022 00:17:03 - INFO - codeparrot_training - Step 9216: {'lr': 0.0004970729503849057, 'samples': 4719104, 'steps': 9216, 'loss/train': 2.474964141845703}
-03/04/2022 00:17:09 - INFO - codeparrot_training - Step 9217: {'lr': 0.0004970721406495168, 'samples': 4719616, 'steps': 9217, 'loss/train': 2.2011396884918213}
-03/04/2022 00:17:12 - INFO - codeparrot_training - Step 9218: {'lr': 0.000497071330802801, 'samples': 4720128, 'steps': 9218, 'loss/train': 2.806875228881836}
-03/04/2022 00:17:14 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/04/2022 00:17:17 - INFO - codeparrot_training - Step 9219: {'lr': 0.0004970705208447587, 'samples': 4720640, 'steps': 9219, 'loss/train': 1.679822564125061}
-03/04/2022 00:17:20 - INFO - codeparrot_training - Step 9220: {'lr': 0.0004970697107753902, 'samples': 4721152, 'steps': 9220, 'loss/train': 2.9331207275390625}
-03/04/2022 00:17:22 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/04/2022 00:17:25 - INFO - codeparrot_training - Step 9221: {'lr': 0.0004970689005946959, 'samples': 4721664, 'steps': 9221, 'loss/train': 2.383516311645508}
-03/04/2022 00:17:28 - INFO - codeparrot_training - Step 9222: {'lr': 0.0004970680903026762, 'samples': 4722176, 'steps': 9222, 'loss/train': 2.5934903621673584}
-03/04/2022 00:17:30 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 00:17:34 - INFO - codeparrot_training - Step 9223: {'lr': 0.0004970672798993313, 'samples': 4722688, 'steps': 9223, 'loss/train': 1.7145789861679077}
-03/04/2022 00:17:37 - INFO - codeparrot_training - Step 9224: {'lr': 0.0004970664693846618, 'samples': 4723200, 'steps': 9224, 'loss/train': 1.5762252807617188}
-03/04/2022 00:17:39 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/04/2022 00:17:42 - INFO - codeparrot_training - Step 9225: {'lr': 0.000497065658758668, 'samples': 4723712, 'steps': 9225, 'loss/train': 1.9914144277572632}
-03/04/2022 00:17:45 - INFO - codeparrot_training - Step 9226: {'lr': 0.0004970648480213502, 'samples': 4724224, 'steps': 9226, 'loss/train': 1.2915936708450317}
-03/04/2022 00:17:47 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/04/2022 00:17:51 - INFO - codeparrot_training - Step 9227: {'lr': 0.0004970640371727088, 'samples': 4724736, 'steps': 9227, 'loss/train': 2.5447065830230713}
-03/04/2022 00:17:54 - INFO - codeparrot_training - Step 9228: {'lr': 0.0004970632262127441, 'samples': 4725248, 'steps': 9228, 'loss/train': 3.404654026031494}
-03/04/2022 00:17:56 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 00:17:59 - INFO - codeparrot_training - Step 9229: {'lr': 0.0004970624151414565, 'samples': 4725760, 'steps': 9229, 'loss/train': 2.1074564456939697}
-03/04/2022 00:18:02 - INFO - codeparrot_training - Step 9230: {'lr': 0.0004970616039588465, 'samples': 4726272, 'steps': 9230, 'loss/train': 1.3759716749191284}
-03/04/2022 00:18:04 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 00:18:07 - INFO - codeparrot_training - Step 9231: {'lr': 0.0004970607926649143, 'samples': 4726784, 'steps': 9231, 'loss/train': 1.9464250802993774}
-03/04/2022 00:18:11 - INFO - codeparrot_training - Step 9232: {'lr': 0.0004970599812596603, 'samples': 4727296, 'steps': 9232, 'loss/train': 2.0122931003570557}
-03/04/2022 00:18:12 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 00:18:16 - INFO - codeparrot_training - Step 9233: {'lr': 0.0004970591697430849, 'samples': 4727808, 'steps': 9233, 'loss/train': 1.8454934358596802}
-03/04/2022 00:18:19 - INFO - codeparrot_training - Step 9234: {'lr': 0.0004970583581151885, 'samples': 4728320, 'steps': 9234, 'loss/train': 2.156947135925293}
-03/04/2022 00:18:21 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 00:18:24 - INFO - codeparrot_training - Step 9235: {'lr': 0.0004970575463759713, 'samples': 4728832, 'steps': 9235, 'loss/train': 1.9525824785232544}
-03/04/2022 00:18:27 - INFO - codeparrot_training - Step 9236: {'lr': 0.0004970567345254339, 'samples': 4729344, 'steps': 9236, 'loss/train': 1.4112294912338257}
-03/04/2022 00:18:29 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 00:18:33 - INFO - codeparrot_training - Step 9237: {'lr': 0.0004970559225635765, 'samples': 4729856, 'steps': 9237, 'loss/train': 2.2906088829040527}
-03/04/2022 00:18:36 - INFO - codeparrot_training - Step 9238: {'lr': 0.0004970551104903995, 'samples': 4730368, 'steps': 9238, 'loss/train': 2.0219225883483887}
-03/04/2022 00:18:38 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/04/2022 00:18:41 - INFO - codeparrot_training - Step 9239: {'lr': 0.0004970542983059033, 'samples': 4730880, 'steps': 9239, 'loss/train': 1.4626861810684204}
-03/04/2022 00:18:44 - INFO - codeparrot_training - Step 9240: {'lr': 0.0004970534860100883, 'samples': 4731392, 'steps': 9240, 'loss/train': 3.867217540740967}
-03/04/2022 00:18:46 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 00:18:50 - INFO - codeparrot_training - Step 9241: {'lr': 0.0004970526736029547, 'samples': 4731904, 'steps': 9241, 'loss/train': 1.9512522220611572}
-03/04/2022 00:18:53 - INFO - codeparrot_training - Step 9242: {'lr': 0.000497051861084503, 'samples': 4732416, 'steps': 9242, 'loss/train': 1.9243724346160889}
-03/04/2022 00:18:54 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 00:18:58 - INFO - codeparrot_training - Step 9243: {'lr': 0.0004970510484547336, 'samples': 4732928, 'steps': 9243, 'loss/train': 2.347126007080078}
-03/04/2022 00:19:01 - INFO - codeparrot_training - Step 9244: {'lr': 0.0004970502357136468, 'samples': 4733440, 'steps': 9244, 'loss/train': 1.599075436592102}
-03/04/2022 00:19:03 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 00:19:06 - INFO - codeparrot_training - Step 9245: {'lr': 0.0004970494228612429, 'samples': 4733952, 'steps': 9245, 'loss/train': 1.787596344947815}
-03/04/2022 00:19:10 - INFO - codeparrot_training - Step 9246: {'lr': 0.0004970486098975224, 'samples': 4734464, 'steps': 9246, 'loss/train': 1.0341893434524536}
-03/04/2022 00:19:11 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/04/2022 00:19:15 - INFO - codeparrot_training - Step 9247: {'lr': 0.0004970477968224856, 'samples': 4734976, 'steps': 9247, 'loss/train': 1.8887896537780762}
-03/04/2022 00:19:18 - INFO - codeparrot_training - Step 9248: {'lr': 0.000497046983636133, 'samples': 4735488, 'steps': 9248, 'loss/train': 2.0090067386627197}
-03/04/2022 00:19:20 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/04/2022 00:19:23 - INFO - codeparrot_training - Step 9249: {'lr': 0.0004970461703384647, 'samples': 4736000, 'steps': 9249, 'loss/train': 2.44071102142334}
-03/04/2022 00:19:27 - INFO - codeparrot_training - Step 9250: {'lr': 0.0004970453569294812, 'samples': 4736512, 'steps': 9250, 'loss/train': 3.9413931369781494}
-03/04/2022 00:19:28 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/04/2022 00:19:32 - INFO - codeparrot_training - Step 9251: {'lr': 0.000497044543409183, 'samples': 4737024, 'steps': 9251, 'loss/train': 2.264601469039917}
-03/04/2022 00:19:35 - INFO - codeparrot_training - Step 9252: {'lr': 0.0004970437297775702, 'samples': 4737536, 'steps': 9252, 'loss/train': 2.2360942363739014}
-03/04/2022 00:19:37 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/04/2022 00:19:40 - INFO - codeparrot_training - Step 9253: {'lr': 0.0004970429160346433, 'samples': 4738048, 'steps': 9253, 'loss/train': 1.2192975282669067}
-03/04/2022 00:19:43 - INFO - codeparrot_training - Step 9254: {'lr': 0.0004970421021804027, 'samples': 4738560, 'steps': 9254, 'loss/train': 1.4102015495300293}
-03/04/2022 00:19:45 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/04/2022 00:19:49 - INFO - codeparrot_training - Step 9255: {'lr': 0.0004970412882148488, 'samples': 4739072, 'steps': 9255, 'loss/train': 1.5091540813446045}
-03/04/2022 00:19:52 - INFO - codeparrot_training - Step 9256: {'lr': 0.0004970404741379818, 'samples': 4739584, 'steps': 9256, 'loss/train': 1.7671935558319092}
-03/04/2022 00:19:53 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 00:19:57 - INFO - codeparrot_training - Step 9257: {'lr': 0.0004970396599498023, 'samples': 4740096, 'steps': 9257, 'loss/train': 3.678755521774292}
-03/04/2022 00:20:00 - INFO - codeparrot_training - Step 9258: {'lr': 0.0004970388456503105, 'samples': 4740608, 'steps': 9258, 'loss/train': 1.641787052154541}
-03/04/2022 00:20:02 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/04/2022 00:20:06 - INFO - codeparrot_training - Step 9259: {'lr': 0.0004970380312395069, 'samples': 4741120, 'steps': 9259, 'loss/train': 2.212752342224121}
-03/04/2022 00:20:09 - INFO - codeparrot_training - Step 9260: {'lr': 0.0004970372167173915, 'samples': 4741632, 'steps': 9260, 'loss/train': 2.047858953475952}
-03/04/2022 00:20:11 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 00:20:14 - INFO - codeparrot_training - Step 9261: {'lr': 0.0004970364020839652, 'samples': 4742144, 'steps': 9261, 'loss/train': 1.0924831628799438}
-03/04/2022 00:20:17 - INFO - codeparrot_training - Step 9262: {'lr': 0.0004970355873392281, 'samples': 4742656, 'steps': 9262, 'loss/train': 2.271946907043457}
-03/04/2022 00:20:19 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/04/2022 00:20:23 - INFO - codeparrot_training - Step 9263: {'lr': 0.0004970347724831804, 'samples': 4743168, 'steps': 9263, 'loss/train': 2.140127658843994}
-03/04/2022 00:20:26 - INFO - codeparrot_training - Step 9264: {'lr': 0.0004970339575158228, 'samples': 4743680, 'steps': 9264, 'loss/train': 2.1219871044158936}
-03/04/2022 00:20:28 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 00:20:31 - INFO - codeparrot_training - Step 9265: {'lr': 0.0004970331424371555, 'samples': 4744192, 'steps': 9265, 'loss/train': 1.4368001222610474}
-03/04/2022 00:20:34 - INFO - codeparrot_training - Step 9266: {'lr': 0.0004970323272471788, 'samples': 4744704, 'steps': 9266, 'loss/train': 2.362663507461548}
-03/04/2022 00:20:36 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 00:20:40 - INFO - codeparrot_training - Step 9267: {'lr': 0.0004970315119458931, 'samples': 4745216, 'steps': 9267, 'loss/train': 1.8366397619247437}
-03/04/2022 00:20:43 - INFO - codeparrot_training - Step 9268: {'lr': 0.000497030696533299, 'samples': 4745728, 'steps': 9268, 'loss/train': 1.1185053586959839}
-03/04/2022 00:20:45 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/04/2022 00:20:48 - INFO - codeparrot_training - Step 9269: {'lr': 0.0004970298810093965, 'samples': 4746240, 'steps': 9269, 'loss/train': 2.2684872150421143}
-03/04/2022 00:20:51 - INFO - codeparrot_training - Step 9270: {'lr': 0.0004970290653741863, 'samples': 4746752, 'steps': 9270, 'loss/train': 2.063366174697876}
-03/04/2022 00:20:53 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/04/2022 00:20:56 - INFO - codeparrot_training - Step 9271: {'lr': 0.0004970282496276684, 'samples': 4747264, 'steps': 9271, 'loss/train': 1.5706888437271118}
-03/04/2022 00:21:00 - INFO - codeparrot_training - Step 9272: {'lr': 0.0004970274337698436, 'samples': 4747776, 'steps': 9272, 'loss/train': 1.9959155321121216}
-03/04/2022 00:21:01 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 00:21:05 - INFO - codeparrot_training - Step 9273: {'lr': 0.000497026617800712, 'samples': 4748288, 'steps': 9273, 'loss/train': 2.1690211296081543}
-03/04/2022 00:21:08 - INFO - codeparrot_training - Step 9274: {'lr': 0.0004970258017202739, 'samples': 4748800, 'steps': 9274, 'loss/train': 2.5509018898010254}
-03/04/2022 00:21:10 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/04/2022 00:21:13 - INFO - codeparrot_training - Step 9275: {'lr': 0.00049702498552853, 'samples': 4749312, 'steps': 9275, 'loss/train': 1.6842625141143799}
-03/04/2022 00:21:16 - INFO - codeparrot_training - Step 9276: {'lr': 0.0004970241692254803, 'samples': 4749824, 'steps': 9276, 'loss/train': 2.622404098510742}
-03/04/2022 00:21:18 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 00:21:22 - INFO - codeparrot_training - Step 9277: {'lr': 0.0004970233528111253, 'samples': 4750336, 'steps': 9277, 'loss/train': 1.707533836364746}
-03/04/2022 00:21:25 - INFO - codeparrot_training - Step 9278: {'lr': 0.0004970225362854654, 'samples': 4750848, 'steps': 9278, 'loss/train': 2.510222911834717}
-03/04/2022 00:21:26 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 00:21:30 - INFO - codeparrot_training - Step 9279: {'lr': 0.0004970217196485011, 'samples': 4751360, 'steps': 9279, 'loss/train': 1.6768842935562134}
-03/04/2022 00:21:33 - INFO - codeparrot_training - Step 9280: {'lr': 0.0004970209029002325, 'samples': 4751872, 'steps': 9280, 'loss/train': 2.1488513946533203}
-03/04/2022 00:21:35 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/04/2022 00:21:39 - INFO - codeparrot_training - Step 9281: {'lr': 0.0004970200860406601, 'samples': 4752384, 'steps': 9281, 'loss/train': 2.2413086891174316}
-03/04/2022 00:21:42 - INFO - codeparrot_training - Step 9282: {'lr': 0.0004970192690697843, 'samples': 4752896, 'steps': 9282, 'loss/train': 1.694206953048706}
-03/04/2022 00:21:43 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/04/2022 00:21:47 - INFO - codeparrot_training - Step 9283: {'lr': 0.0004970184519876053, 'samples': 4753408, 'steps': 9283, 'loss/train': 2.450477123260498}
-03/04/2022 00:21:50 - INFO - codeparrot_training - Step 9284: {'lr': 0.0004970176347941237, 'samples': 4753920, 'steps': 9284, 'loss/train': 2.5103492736816406}
-03/04/2022 00:21:51 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/04/2022 00:21:55 - INFO - codeparrot_training - Step 9285: {'lr': 0.0004970168174893398, 'samples': 4754432, 'steps': 9285, 'loss/train': 1.9510722160339355}
-03/04/2022 00:21:59 - INFO - codeparrot_training - Step 9286: {'lr': 0.0004970160000732539, 'samples': 4754944, 'steps': 9286, 'loss/train': 1.975756287574768}
-03/04/2022 00:22:00 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/04/2022 00:22:04 - INFO - codeparrot_training - Step 9287: {'lr': 0.0004970151825458664, 'samples': 4755456, 'steps': 9287, 'loss/train': 2.815267324447632}
-03/04/2022 00:22:07 - INFO - codeparrot_training - Step 9288: {'lr': 0.0004970143649071777, 'samples': 4755968, 'steps': 9288, 'loss/train': 2.0085487365722656}
-03/04/2022 00:22:08 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/04/2022 00:22:12 - INFO - codeparrot_training - Step 9289: {'lr': 0.0004970135471571881, 'samples': 4756480, 'steps': 9289, 'loss/train': 2.022035837173462}
-03/04/2022 00:22:15 - INFO - codeparrot_training - Step 9290: {'lr': 0.000497012729295898, 'samples': 4756992, 'steps': 9290, 'loss/train': 1.7716857194900513}
-03/04/2022 00:22:16 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/04/2022 00:22:21 - INFO - codeparrot_training - Step 9291: {'lr': 0.0004970119113233078, 'samples': 4757504, 'steps': 9291, 'loss/train': 2.3153960704803467}
-03/04/2022 00:22:24 - INFO - codeparrot_training - Step 9292: {'lr': 0.0004970110932394178, 'samples': 4758016, 'steps': 9292, 'loss/train': 0.7145670652389526}
-03/04/2022 00:22:25 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 00:22:29 - INFO - codeparrot_training - Step 9293: {'lr': 0.0004970102750442285, 'samples': 4758528, 'steps': 9293, 'loss/train': 1.2610514163970947}
-03/04/2022 00:22:32 - INFO - codeparrot_training - Step 9294: {'lr': 0.0004970094567377402, 'samples': 4759040, 'steps': 9294, 'loss/train': 1.347022294998169}
-03/04/2022 00:22:33 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/04/2022 00:22:38 - INFO - codeparrot_training - Step 9295: {'lr': 0.0004970086383199532, 'samples': 4759552, 'steps': 9295, 'loss/train': 1.016806721687317}
-03/04/2022 00:22:41 - INFO - codeparrot_training - Step 9296: {'lr': 0.0004970078197908678, 'samples': 4760064, 'steps': 9296, 'loss/train': 1.7867577075958252}
-03/04/2022 00:22:41 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/04/2022 00:22:46 - INFO - codeparrot_training - Step 9297: {'lr': 0.0004970070011504846, 'samples': 4760576, 'steps': 9297, 'loss/train': 2.4803245067596436}
-03/04/2022 00:22:49 - INFO - codeparrot_training - Step 9298: {'lr': 0.0004970061823988038, 'samples': 4761088, 'steps': 9298, 'loss/train': 2.1638824939727783}
-03/04/2022 00:22:49 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 00:22:54 - INFO - codeparrot_training - Step 9299: {'lr': 0.0004970053635358259, 'samples': 4761600, 'steps': 9299, 'loss/train': 1.9695347547531128}
-03/04/2022 00:22:58 - INFO - codeparrot_training - Step 9300: {'lr': 0.0004970045445615512, 'samples': 4762112, 'steps': 9300, 'loss/train': 0.792893648147583}
-03/04/2022 00:22:58 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/04/2022 00:23:03 - INFO - codeparrot_training - Step 9301: {'lr': 0.00049700372547598, 'samples': 4762624, 'steps': 9301, 'loss/train': 1.8270759582519531}
-03/04/2022 00:23:06 - INFO - codeparrot_training - Step 9302: {'lr': 0.0004970029062791128, 'samples': 4763136, 'steps': 9302, 'loss/train': 3.0586040019989014}
-03/04/2022 00:23:07 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/04/2022 00:23:11 - INFO - codeparrot_training - Step 9303: {'lr': 0.0004970020869709498, 'samples': 4763648, 'steps': 9303, 'loss/train': 0.6404932737350464}
-03/04/2022 00:23:15 - INFO - codeparrot_training - Step 9304: {'lr': 0.0004970012675514915, 'samples': 4764160, 'steps': 9304, 'loss/train': 2.0313425064086914}
-03/04/2022 00:23:15 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/04/2022 00:23:20 - INFO - codeparrot_training - Step 9305: {'lr': 0.0004970004480207384, 'samples': 4764672, 'steps': 9305, 'loss/train': 2.139754056930542}
-03/04/2022 00:23:23 - INFO - codeparrot_training - Step 9306: {'lr': 0.0004969996283786905, 'samples': 4765184, 'steps': 9306, 'loss/train': 3.55971622467041}
-03/04/2022 00:23:24 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 00:23:28 - INFO - codeparrot_training - Step 9307: {'lr': 0.0004969988086253486, 'samples': 4765696, 'steps': 9307, 'loss/train': 2.209859609603882}
-03/04/2022 00:23:32 - INFO - codeparrot_training - Step 9308: {'lr': 0.0004969979887607125, 'samples': 4766208, 'steps': 9308, 'loss/train': 2.3805248737335205}
-03/04/2022 00:23:33 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/04/2022 00:23:37 - INFO - codeparrot_training - Step 9309: {'lr': 0.0004969971687847832, 'samples': 4766720, 'steps': 9309, 'loss/train': 2.0122547149658203}
-03/04/2022 00:23:40 - INFO - codeparrot_training - Step 9310: {'lr': 0.0004969963486975607, 'samples': 4767232, 'steps': 9310, 'loss/train': 1.860993504524231}
-03/04/2022 00:23:42 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/04/2022 00:23:45 - INFO - codeparrot_training - Step 9311: {'lr': 0.0004969955284990455, 'samples': 4767744, 'steps': 9311, 'loss/train': 1.7991127967834473}
-03/04/2022 00:23:49 - INFO - codeparrot_training - Step 9312: {'lr': 0.0004969947081892379, 'samples': 4768256, 'steps': 9312, 'loss/train': 1.5165636539459229}
-03/04/2022 00:23:50 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/04/2022 00:23:54 - INFO - codeparrot_training - Step 9313: {'lr': 0.0004969938877681383, 'samples': 4768768, 'steps': 9313, 'loss/train': 1.3378909826278687}
-03/04/2022 00:23:57 - INFO - codeparrot_training - Step 9314: {'lr': 0.0004969930672357471, 'samples': 4769280, 'steps': 9314, 'loss/train': 2.308391571044922}
-03/04/2022 00:23:58 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/04/2022 00:24:02 - INFO - codeparrot_training - Step 9315: {'lr': 0.0004969922465920645, 'samples': 4769792, 'steps': 9315, 'loss/train': 1.7607795000076294}
-03/04/2022 00:24:05 - INFO - codeparrot_training - Step 9316: {'lr': 0.0004969914258370912, 'samples': 4770304, 'steps': 9316, 'loss/train': 2.600834846496582}
-03/04/2022 00:24:07 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/04/2022 00:24:11 - INFO - codeparrot_training - Step 9317: {'lr': 0.0004969906049708272, 'samples': 4770816, 'steps': 9317, 'loss/train': 1.8892019987106323}
-03/04/2022 00:24:14 - INFO - codeparrot_training - Step 9318: {'lr': 0.0004969897839932732, 'samples': 4771328, 'steps': 9318, 'loss/train': 2.666290044784546}
-03/04/2022 00:24:15 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/04/2022 00:24:20 - INFO - codeparrot_training - Step 9319: {'lr': 0.0004969889629044293, 'samples': 4771840, 'steps': 9319, 'loss/train': 2.347083330154419}
-03/04/2022 00:24:23 - INFO - codeparrot_training - Step 9320: {'lr': 0.000496988141704296, 'samples': 4772352, 'steps': 9320, 'loss/train': 2.256254196166992}
-03/04/2022 00:24:25 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/04/2022 00:24:28 - INFO - codeparrot_training - Step 9321: {'lr': 0.0004969873203928737, 'samples': 4772864, 'steps': 9321, 'loss/train': 3.565995216369629}
-03/04/2022 00:24:31 - INFO - codeparrot_training - Step 9322: {'lr': 0.0004969864989701626, 'samples': 4773376, 'steps': 9322, 'loss/train': 2.1767306327819824}
-03/04/2022 00:24:34 - INFO - codeparrot_training - Step 9323: {'lr': 0.0004969856774361634, 'samples': 4773888, 'steps': 9323, 'loss/train': 1.63206148147583}
-03/04/2022 00:24:34 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 00:24:40 - INFO - codeparrot_training - Step 9324: {'lr': 0.0004969848557908761, 'samples': 4774400, 'steps': 9324, 'loss/train': 2.10014009475708}
-03/04/2022 00:24:43 - INFO - codeparrot_training - Step 9325: {'lr': 0.0004969840340343013, 'samples': 4774912, 'steps': 9325, 'loss/train': 2.198864459991455}
-03/04/2022 00:24:43 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 00:24:48 - INFO - codeparrot_training - Step 9326: {'lr': 0.0004969832121664394, 'samples': 4775424, 'steps': 9326, 'loss/train': 1.5971044301986694}
-03/04/2022 00:24:51 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/04/2022 00:24:53 - INFO - codeparrot_training - Step 9327: {'lr': 0.0004969823901872906, 'samples': 4775936, 'steps': 9327, 'loss/train': 2.6636059284210205}
-03/04/2022 00:24:57 - INFO - codeparrot_training - Step 9328: {'lr': 0.0004969815680968552, 'samples': 4776448, 'steps': 9328, 'loss/train': 2.2101144790649414}
-03/04/2022 00:24:59 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/04/2022 00:25:02 - INFO - codeparrot_training - Step 9329: {'lr': 0.0004969807458951339, 'samples': 4776960, 'steps': 9329, 'loss/train': 2.098296880722046}
-03/04/2022 00:25:05 - INFO - codeparrot_training - Step 9330: {'lr': 0.0004969799235821268, 'samples': 4777472, 'steps': 9330, 'loss/train': 0.42353692650794983}
-03/04/2022 00:25:08 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 00:25:10 - INFO - codeparrot_training - Step 9331: {'lr': 0.0004969791011578344, 'samples': 4777984, 'steps': 9331, 'loss/train': 1.774045705795288}
-03/04/2022 00:25:13 - INFO - codeparrot_training - Step 9332: {'lr': 0.000496978278622257, 'samples': 4778496, 'steps': 9332, 'loss/train': 1.9441579580307007}
-03/04/2022 00:25:16 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/04/2022 00:25:19 - INFO - codeparrot_training - Step 9333: {'lr': 0.000496977455975395, 'samples': 4779008, 'steps': 9333, 'loss/train': 2.586926221847534}
-03/04/2022 00:25:22 - INFO - codeparrot_training - Step 9334: {'lr': 0.0004969766332172488, 'samples': 4779520, 'steps': 9334, 'loss/train': 2.1848747730255127}
-03/04/2022 00:25:24 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 00:25:27 - INFO - codeparrot_training - Step 9335: {'lr': 0.0004969758103478187, 'samples': 4780032, 'steps': 9335, 'loss/train': 2.5201826095581055}
-03/04/2022 00:25:30 - INFO - codeparrot_training - Step 9336: {'lr': 0.0004969749873671051, 'samples': 4780544, 'steps': 9336, 'loss/train': 2.613105058670044}
-03/04/2022 00:25:32 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 00:25:36 - INFO - codeparrot_training - Step 9337: {'lr': 0.0004969741642751085, 'samples': 4781056, 'steps': 9337, 'loss/train': 1.4727146625518799}
-03/04/2022 00:25:39 - INFO - codeparrot_training - Step 9338: {'lr': 0.000496973341071829, 'samples': 4781568, 'steps': 9338, 'loss/train': 2.137810468673706}
-03/04/2022 00:25:41 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 00:25:44 - INFO - codeparrot_training - Step 9339: {'lr': 0.0004969725177572672, 'samples': 4782080, 'steps': 9339, 'loss/train': 2.167529344558716}
-03/04/2022 00:25:47 - INFO - codeparrot_training - Step 9340: {'lr': 0.0004969716943314234, 'samples': 4782592, 'steps': 9340, 'loss/train': 2.05704927444458}
-03/04/2022 00:25:49 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/04/2022 00:25:52 - INFO - codeparrot_training - Step 9341: {'lr': 0.0004969708707942979, 'samples': 4783104, 'steps': 9341, 'loss/train': 1.680745244026184}
-03/04/2022 00:25:56 - INFO - codeparrot_training - Step 9342: {'lr': 0.0004969700471458913, 'samples': 4783616, 'steps': 9342, 'loss/train': 1.5547224283218384}
-03/04/2022 00:25:57 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/04/2022 00:26:01 - INFO - codeparrot_training - Step 9343: {'lr': 0.0004969692233862036, 'samples': 4784128, 'steps': 9343, 'loss/train': 2.006702423095703}
-03/04/2022 00:26:04 - INFO - codeparrot_training - Step 9344: {'lr': 0.0004969683995152355, 'samples': 4784640, 'steps': 9344, 'loss/train': 1.6919599771499634}
-03/04/2022 00:26:06 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/04/2022 00:26:09 - INFO - codeparrot_training - Step 9345: {'lr': 0.0004969675755329872, 'samples': 4785152, 'steps': 9345, 'loss/train': 1.750630259513855}
-03/04/2022 00:26:12 - INFO - codeparrot_training - Step 9346: {'lr': 0.0004969667514394592, 'samples': 4785664, 'steps': 9346, 'loss/train': 2.172159194946289}
-03/04/2022 00:26:14 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 00:26:18 - INFO - codeparrot_training - Step 9347: {'lr': 0.0004969659272346517, 'samples': 4786176, 'steps': 9347, 'loss/train': 1.8471778631210327}
-03/04/2022 00:26:21 - INFO - codeparrot_training - Step 9348: {'lr': 0.0004969651029185652, 'samples': 4786688, 'steps': 9348, 'loss/train': 0.859277606010437}
-03/04/2022 00:26:22 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/04/2022 00:26:26 - INFO - codeparrot_training - Step 9349: {'lr': 0.0004969642784912001, 'samples': 4787200, 'steps': 9349, 'loss/train': 2.0257177352905273}
-03/04/2022 00:26:29 - INFO - codeparrot_training - Step 9350: {'lr': 0.0004969634539525566, 'samples': 4787712, 'steps': 9350, 'loss/train': 2.2364070415496826}
-03/04/2022 00:26:31 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/04/2022 00:26:35 - INFO - codeparrot_training - Step 9351: {'lr': 0.0004969626293026353, 'samples': 4788224, 'steps': 9351, 'loss/train': 2.2528672218322754}
-03/04/2022 00:26:38 - INFO - codeparrot_training - Step 9352: {'lr': 0.0004969618045414363, 'samples': 4788736, 'steps': 9352, 'loss/train': 1.7282065153121948}
-03/04/2022 00:26:39 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/04/2022 00:26:43 - INFO - codeparrot_training - Step 9353: {'lr': 0.0004969609796689602, 'samples': 4789248, 'steps': 9353, 'loss/train': 2.6577558517456055}
-03/04/2022 00:26:46 - INFO - codeparrot_training - Step 9354: {'lr': 0.0004969601546852073, 'samples': 4789760, 'steps': 9354, 'loss/train': 1.7998780012130737}
-03/04/2022 00:26:48 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/04/2022 00:26:52 - INFO - codeparrot_training - Step 9355: {'lr': 0.0004969593295901779, 'samples': 4790272, 'steps': 9355, 'loss/train': 2.6118204593658447}
-03/04/2022 00:26:55 - INFO - codeparrot_training - Step 9356: {'lr': 0.0004969585043838725, 'samples': 4790784, 'steps': 9356, 'loss/train': 1.64167320728302}
-03/04/2022 00:26:57 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 00:27:00 - INFO - codeparrot_training - Step 9357: {'lr': 0.0004969576790662914, 'samples': 4791296, 'steps': 9357, 'loss/train': 1.8587745428085327}
-03/04/2022 00:27:03 - INFO - codeparrot_training - Step 9358: {'lr': 0.0004969568536374349, 'samples': 4791808, 'steps': 9358, 'loss/train': 1.79141366481781}
-03/04/2022 00:27:05 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/04/2022 00:27:08 - INFO - codeparrot_training - Step 9359: {'lr': 0.0004969560280973036, 'samples': 4792320, 'steps': 9359, 'loss/train': 1.5209577083587646}
-03/04/2022 00:27:12 - INFO - codeparrot_training - Step 9360: {'lr': 0.0004969552024458976, 'samples': 4792832, 'steps': 9360, 'loss/train': 2.063656806945801}
-03/04/2022 00:27:13 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/04/2022 00:27:17 - INFO - codeparrot_training - Step 9361: {'lr': 0.0004969543766832176, 'samples': 4793344, 'steps': 9361, 'loss/train': 1.9431846141815186}
-03/04/2022 00:27:20 - INFO - codeparrot_training - Step 9362: {'lr': 0.0004969535508092635, 'samples': 4793856, 'steps': 9362, 'loss/train': 1.9243184328079224}
-03/04/2022 00:27:22 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/04/2022 00:27:26 - INFO - codeparrot_training - Step 9363: {'lr': 0.0004969527248240361, 'samples': 4794368, 'steps': 9363, 'loss/train': 2.03132700920105}
-03/04/2022 00:27:29 - INFO - codeparrot_training - Step 9364: {'lr': 0.0004969518987275356, 'samples': 4794880, 'steps': 9364, 'loss/train': 2.0294554233551025}
-03/04/2022 00:27:30 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 00:27:34 - INFO - codeparrot_training - Step 9365: {'lr': 0.0004969510725197624, 'samples': 4795392, 'steps': 9365, 'loss/train': 2.390209674835205}
-03/04/2022 00:27:37 - INFO - codeparrot_training - Step 9366: {'lr': 0.0004969502462007167, 'samples': 4795904, 'steps': 9366, 'loss/train': 1.9419209957122803}
-03/04/2022 00:27:39 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/04/2022 00:27:42 - INFO - codeparrot_training - Step 9367: {'lr': 0.0004969494197703992, 'samples': 4796416, 'steps': 9367, 'loss/train': 2.140375852584839}
-03/04/2022 00:27:46 - INFO - codeparrot_training - Step 9368: {'lr': 0.00049694859322881, 'samples': 4796928, 'steps': 9368, 'loss/train': 1.6186391115188599}
-03/04/2022 00:27:47 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/04/2022 00:27:51 - INFO - codeparrot_training - Step 9369: {'lr': 0.0004969477665759496, 'samples': 4797440, 'steps': 9369, 'loss/train': 2.4997425079345703}
-03/04/2022 00:27:54 - INFO - codeparrot_training - Step 9370: {'lr': 0.0004969469398118184, 'samples': 4797952, 'steps': 9370, 'loss/train': 2.0232834815979004}
-03/04/2022 00:27:56 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/04/2022 00:27:59 - INFO - codeparrot_training - Step 9371: {'lr': 0.0004969461129364167, 'samples': 4798464, 'steps': 9371, 'loss/train': 1.8240901231765747}
-03/04/2022 00:28:02 - INFO - codeparrot_training - Step 9372: {'lr': 0.0004969452859497449, 'samples': 4798976, 'steps': 9372, 'loss/train': 1.8963757753372192}
-03/04/2022 00:28:04 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/04/2022 00:28:08 - INFO - codeparrot_training - Step 9373: {'lr': 0.0004969444588518034, 'samples': 4799488, 'steps': 9373, 'loss/train': 0.46346187591552734}
-03/04/2022 00:28:11 - INFO - codeparrot_training - Step 9374: {'lr': 0.0004969436316425924, 'samples': 4800000, 'steps': 9374, 'loss/train': 2.3830065727233887}
-03/04/2022 00:28:13 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/04/2022 00:28:16 - INFO - codeparrot_training - Step 9375: {'lr': 0.0004969428043221125, 'samples': 4800512, 'steps': 9375, 'loss/train': 2.1842851638793945}
-03/04/2022 00:28:19 - INFO - codeparrot_training - Step 9376: {'lr': 0.000496941976890364, 'samples': 4801024, 'steps': 9376, 'loss/train': 1.9400200843811035}
-03/04/2022 00:28:22 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/04/2022 00:28:25 - INFO - codeparrot_training - Step 9377: {'lr': 0.0004969411493473472, 'samples': 4801536, 'steps': 9377, 'loss/train': 1.911213994026184}
-03/04/2022 00:28:28 - INFO - codeparrot_training - Step 9378: {'lr': 0.0004969403216930626, 'samples': 4802048, 'steps': 9378, 'loss/train': 1.9731336832046509}
-03/04/2022 00:28:30 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/04/2022 00:28:33 - INFO - codeparrot_training - Step 9379: {'lr': 0.0004969394939275105, 'samples': 4802560, 'steps': 9379, 'loss/train': 0.9933723211288452}
-03/04/2022 00:28:36 - INFO - codeparrot_training - Step 9380: {'lr': 0.0004969386660506912, 'samples': 4803072, 'steps': 9380, 'loss/train': 3.0256595611572266}
-03/04/2022 00:28:38 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/04/2022 00:28:41 - INFO - codeparrot_training - Step 9381: {'lr': 0.0004969378380626051, 'samples': 4803584, 'steps': 9381, 'loss/train': 1.2253140211105347}
-03/04/2022 00:28:45 - INFO - codeparrot_training - Step 9382: {'lr': 0.0004969370099632528, 'samples': 4804096, 'steps': 9382, 'loss/train': 1.058750867843628}
-03/04/2022 00:28:46 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/04/2022 00:28:50 - INFO - codeparrot_training - Step 9383: {'lr': 0.0004969361817526343, 'samples': 4804608, 'steps': 9383, 'loss/train': 1.388999342918396}
-03/04/2022 00:28:53 - INFO - codeparrot_training - Step 9384: {'lr': 0.0004969353534307504, 'samples': 4805120, 'steps': 9384, 'loss/train': 2.9054644107818604}
-03/04/2022 00:28:55 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/04/2022 00:28:58 - INFO - codeparrot_training - Step 9385: {'lr': 0.000496934524997601, 'samples': 4805632, 'steps': 9385, 'loss/train': 2.3359055519104004}
-03/04/2022 00:29:01 - INFO - codeparrot_training - Step 9386: {'lr': 0.0004969336964531869, 'samples': 4806144, 'steps': 9386, 'loss/train': 2.108344793319702}
-03/04/2022 00:29:03 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/04/2022 00:29:07 - INFO - codeparrot_training - Step 9387: {'lr': 0.0004969328677975083, 'samples': 4806656, 'steps': 9387, 'loss/train': 2.9150266647338867}
-03/04/2022 00:29:10 - INFO - codeparrot_training - Step 9388: {'lr': 0.0004969320390305654, 'samples': 4807168, 'steps': 9388, 'loss/train': 2.6685492992401123}
-03/04/2022 00:29:11 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/04/2022 00:29:15 - INFO - codeparrot_training - Step 9389: {'lr': 0.0004969312101523588, 'samples': 4807680, 'steps': 9389, 'loss/train': 2.131688356399536}
-03/04/2022 00:29:18 - INFO - codeparrot_training - Step 9390: {'lr': 0.0004969303811628888, 'samples': 4808192, 'steps': 9390, 'loss/train': 1.6583664417266846}
-03/04/2022 00:29:20 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/04/2022 00:29:24 - INFO - codeparrot_training - Step 9391: {'lr': 0.0004969295520621558, 'samples': 4808704, 'steps': 9391, 'loss/train': 0.6723400354385376}
-03/04/2022 00:29:27 - INFO - codeparrot_training - Step 9392: {'lr': 0.0004969287228501602, 'samples': 4809216, 'steps': 9392, 'loss/train': 1.80280339717865}
-03/04/2022 00:29:29 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/04/2022 00:29:32 - INFO - codeparrot_training - Step 9393: {'lr': 0.0004969278935269022, 'samples': 4809728, 'steps': 9393, 'loss/train': 1.7996078729629517}
-03/04/2022 00:29:35 - INFO - codeparrot_training - Step 9394: {'lr': 0.0004969270640923823, 'samples': 4810240, 'steps': 9394, 'loss/train': 2.1940624713897705}
-03/04/2022 00:29:37 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 00:29:40 - INFO - codeparrot_training - Step 9395: {'lr': 0.0004969262345466011, 'samples': 4810752, 'steps': 9395, 'loss/train': 1.834141731262207}
-03/04/2022 00:29:44 - INFO - codeparrot_training - Step 9396: {'lr': 0.0004969254048895585, 'samples': 4811264, 'steps': 9396, 'loss/train': 2.4291672706604004}
-03/04/2022 00:29:46 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/04/2022 00:29:49 - INFO - codeparrot_training - Step 9397: {'lr': 0.0004969245751212552, 'samples': 4811776, 'steps': 9397, 'loss/train': 2.7013962268829346}
-03/04/2022 00:29:52 - INFO - codeparrot_training - Step 9398: {'lr': 0.0004969237452416915, 'samples': 4812288, 'steps': 9398, 'loss/train': 2.1772146224975586}
-03/04/2022 00:29:54 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 00:29:57 - INFO - codeparrot_training - Step 9399: {'lr': 0.0004969229152508678, 'samples': 4812800, 'steps': 9399, 'loss/train': 1.6844329833984375}
-03/04/2022 00:30:00 - INFO - codeparrot_training - Step 9400: {'lr': 0.0004969220851487844, 'samples': 4813312, 'steps': 9400, 'loss/train': 4.317879676818848}
-03/04/2022 00:30:03 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/04/2022 00:30:06 - INFO - codeparrot_training - Step 9401: {'lr': 0.0004969212549354418, 'samples': 4813824, 'steps': 9401, 'loss/train': 2.121548652648926}
-03/04/2022 00:30:09 - INFO - codeparrot_training - Step 9402: {'lr': 0.0004969204246108402, 'samples': 4814336, 'steps': 9402, 'loss/train': 2.108516216278076}
-03/04/2022 00:30:12 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/04/2022 00:30:15 - INFO - codeparrot_training - Step 9403: {'lr': 0.0004969195941749801, 'samples': 4814848, 'steps': 9403, 'loss/train': 2.408137559890747}
-03/04/2022 00:30:18 - INFO - codeparrot_training - Step 9404: {'lr': 0.000496918763627862, 'samples': 4815360, 'steps': 9404, 'loss/train': 1.1676183938980103}
-03/04/2022 00:30:20 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/04/2022 00:30:23 - INFO - codeparrot_training - Step 9405: {'lr': 0.0004969179329694859, 'samples': 4815872, 'steps': 9405, 'loss/train': 1.235658884048462}
-03/04/2022 00:30:26 - INFO - codeparrot_training - Step 9406: {'lr': 0.0004969171021998525, 'samples': 4816384, 'steps': 9406, 'loss/train': 1.969468355178833}
-03/04/2022 00:30:28 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/04/2022 00:30:31 - INFO - codeparrot_training - Step 9407: {'lr': 0.0004969162713189619, 'samples': 4816896, 'steps': 9407, 'loss/train': 2.4382126331329346}
-03/04/2022 00:30:35 - INFO - codeparrot_training - Step 9408: {'lr': 0.0004969154403268148, 'samples': 4817408, 'steps': 9408, 'loss/train': 1.6237094402313232}
-03/04/2022 00:30:37 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/04/2022 00:30:40 - INFO - codeparrot_training - Step 9409: {'lr': 0.0004969146092234114, 'samples': 4817920, 'steps': 9409, 'loss/train': 2.2292580604553223}
-03/04/2022 00:30:43 - INFO - codeparrot_training - Step 9410: {'lr': 0.000496913778008752, 'samples': 4818432, 'steps': 9410, 'loss/train': 2.403337240219116}
-03/04/2022 00:30:45 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/04/2022 00:30:48 - INFO - codeparrot_training - Step 9411: {'lr': 0.0004969129466828371, 'samples': 4818944, 'steps': 9411, 'loss/train': 1.7882981300354004}
-03/04/2022 00:30:51 - INFO - codeparrot_training - Step 9412: {'lr': 0.0004969121152456671, 'samples': 4819456, 'steps': 9412, 'loss/train': 2.3978376388549805}
-03/04/2022 00:30:54 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 00:30:57 - INFO - codeparrot_training - Step 9413: {'lr': 0.0004969112836972423, 'samples': 4819968, 'steps': 9413, 'loss/train': 2.4667444229125977}
-03/04/2022 00:31:00 - INFO - codeparrot_training - Step 9414: {'lr': 0.000496910452037563, 'samples': 4820480, 'steps': 9414, 'loss/train': 1.9384560585021973}
-03/04/2022 00:31:03 - INFO - codeparrot_training - Step 9415: {'lr': 0.0004969096202666297, 'samples': 4820992, 'steps': 9415, 'loss/train': 0.7469903826713562}
-03/04/2022 00:31:03 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 00:31:09 - INFO - codeparrot_training - Step 9416: {'lr': 0.0004969087883844428, 'samples': 4821504, 'steps': 9416, 'loss/train': 1.8591722249984741}
-03/04/2022 00:31:12 - INFO - codeparrot_training - Step 9417: {'lr': 0.0004969079563910025, 'samples': 4822016, 'steps': 9417, 'loss/train': 2.517551898956299}
-03/04/2022 00:31:12 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 00:31:17 - INFO - codeparrot_training - Step 9418: {'lr': 0.0004969071242863093, 'samples': 4822528, 'steps': 9418, 'loss/train': 2.076690435409546}
-03/04/2022 00:31:20 - INFO - codeparrot_training - Step 9419: {'lr': 0.0004969062920703636, 'samples': 4823040, 'steps': 9419, 'loss/train': 2.6893818378448486}
-03/04/2022 00:31:20 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/04/2022 00:31:25 - INFO - codeparrot_training - Step 9420: {'lr': 0.0004969054597431658, 'samples': 4823552, 'steps': 9420, 'loss/train': 2.2071785926818848}
-03/04/2022 00:31:29 - INFO - codeparrot_training - Step 9421: {'lr': 0.0004969046273047161, 'samples': 4824064, 'steps': 9421, 'loss/train': 1.9289647340774536}
-03/04/2022 00:31:29 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 00:31:34 - INFO - codeparrot_training - Step 9422: {'lr': 0.0004969037947550151, 'samples': 4824576, 'steps': 9422, 'loss/train': 1.738171935081482}
-03/04/2022 00:31:37 - INFO - codeparrot_training - Step 9423: {'lr': 0.000496902962094063, 'samples': 4825088, 'steps': 9423, 'loss/train': 1.7243582010269165}
-03/04/2022 00:31:37 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 00:31:42 - INFO - codeparrot_training - Step 9424: {'lr': 0.0004969021293218602, 'samples': 4825600, 'steps': 9424, 'loss/train': 2.2511281967163086}
-03/04/2022 00:31:45 - INFO - codeparrot_training - Step 9425: {'lr': 0.0004969012964384071, 'samples': 4826112, 'steps': 9425, 'loss/train': 1.975115180015564}
-03/04/2022 00:31:46 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 00:31:51 - INFO - codeparrot_training - Step 9426: {'lr': 0.0004969004634437042, 'samples': 4826624, 'steps': 9426, 'loss/train': 1.2808715105056763}
-03/04/2022 00:31:54 - INFO - codeparrot_training - Step 9427: {'lr': 0.0004968996303377517, 'samples': 4827136, 'steps': 9427, 'loss/train': 1.2937530279159546}
-03/04/2022 00:31:54 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/04/2022 00:31:59 - INFO - codeparrot_training - Step 9428: {'lr': 0.00049689879712055, 'samples': 4827648, 'steps': 9428, 'loss/train': 2.0437510013580322}
-03/04/2022 00:32:02 - INFO - codeparrot_training - Step 9429: {'lr': 0.0004968979637920995, 'samples': 4828160, 'steps': 9429, 'loss/train': 1.9897499084472656}
-03/04/2022 00:32:02 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 00:32:07 - INFO - codeparrot_training - Step 9430: {'lr': 0.0004968971303524007, 'samples': 4828672, 'steps': 9430, 'loss/train': 1.5960872173309326}
-03/04/2022 00:32:11 - INFO - codeparrot_training - Step 9431: {'lr': 0.0004968962968014537, 'samples': 4829184, 'steps': 9431, 'loss/train': 1.7921273708343506}
-03/04/2022 00:32:11 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 00:32:16 - INFO - codeparrot_training - Step 9432: {'lr': 0.0004968954631392592, 'samples': 4829696, 'steps': 9432, 'loss/train': 2.0871338844299316}
-03/04/2022 00:32:19 - INFO - codeparrot_training - Step 9433: {'lr': 0.0004968946293658173, 'samples': 4830208, 'steps': 9433, 'loss/train': 1.0890638828277588}
-03/04/2022 00:32:20 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/04/2022 00:32:24 - INFO - codeparrot_training - Step 9434: {'lr': 0.0004968937954811284, 'samples': 4830720, 'steps': 9434, 'loss/train': 2.121004819869995}
-03/04/2022 00:32:27 - INFO - codeparrot_training - Step 9435: {'lr': 0.0004968929614851932, 'samples': 4831232, 'steps': 9435, 'loss/train': 2.441525459289551}
-03/04/2022 00:32:28 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/04/2022 00:32:33 - INFO - codeparrot_training - Step 9436: {'lr': 0.0004968921273780118, 'samples': 4831744, 'steps': 9436, 'loss/train': 2.7010936737060547}
-03/04/2022 00:32:36 - INFO - codeparrot_training - Step 9437: {'lr': 0.0004968912931595845, 'samples': 4832256, 'steps': 9437, 'loss/train': 1.804986596107483}
-03/04/2022 00:32:37 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 00:32:41 - INFO - codeparrot_training - Step 9438: {'lr': 0.0004968904588299118, 'samples': 4832768, 'steps': 9438, 'loss/train': 1.5100337266921997}
-03/04/2022 00:32:44 - INFO - codeparrot_training - Step 9439: {'lr': 0.0004968896243889941, 'samples': 4833280, 'steps': 9439, 'loss/train': 1.9713486433029175}
-03/04/2022 00:32:45 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/04/2022 00:32:50 - INFO - codeparrot_training - Step 9440: {'lr': 0.0004968887898368318, 'samples': 4833792, 'steps': 9440, 'loss/train': 1.4198898077011108}
-03/04/2022 00:32:53 - INFO - codeparrot_training - Step 9441: {'lr': 0.0004968879551734252, 'samples': 4834304, 'steps': 9441, 'loss/train': 1.918537974357605}
-03/04/2022 00:32:53 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/04/2022 00:32:58 - INFO - codeparrot_training - Step 9442: {'lr': 0.0004968871203987746, 'samples': 4834816, 'steps': 9442, 'loss/train': 2.167947769165039}
-03/04/2022 00:33:01 - INFO - codeparrot_training - Step 9443: {'lr': 0.0004968862855128806, 'samples': 4835328, 'steps': 9443, 'loss/train': 1.5821834802627563}
-03/04/2022 00:33:02 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/04/2022 00:33:07 - INFO - codeparrot_training - Step 9444: {'lr': 0.0004968854505157434, 'samples': 4835840, 'steps': 9444, 'loss/train': 0.9527313113212585}
-03/04/2022 00:33:10 - INFO - codeparrot_training - Step 9445: {'lr': 0.0004968846154073634, 'samples': 4836352, 'steps': 9445, 'loss/train': 2.152228832244873}
-03/04/2022 00:33:11 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/04/2022 00:33:15 - INFO - codeparrot_training - Step 9446: {'lr': 0.0004968837801877411, 'samples': 4836864, 'steps': 9446, 'loss/train': 2.441094160079956}
-03/04/2022 00:33:18 - INFO - codeparrot_training - Step 9447: {'lr': 0.0004968829448568766, 'samples': 4837376, 'steps': 9447, 'loss/train': 1.5246760845184326}
-03/04/2022 00:33:19 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/04/2022 00:33:23 - INFO - codeparrot_training - Step 9448: {'lr': 0.0004968821094147706, 'samples': 4837888, 'steps': 9448, 'loss/train': 1.1669124364852905}
-03/04/2022 00:33:27 - INFO - codeparrot_training - Step 9449: {'lr': 0.0004968812738614232, 'samples': 4838400, 'steps': 9449, 'loss/train': 2.122530460357666}
-03/04/2022 00:33:28 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 00:33:32 - INFO - codeparrot_training - Step 9450: {'lr': 0.000496880438196835, 'samples': 4838912, 'steps': 9450, 'loss/train': 2.6251614093780518}
-03/04/2022 00:33:35 - INFO - codeparrot_training - Step 9451: {'lr': 0.0004968796024210064, 'samples': 4839424, 'steps': 9451, 'loss/train': 1.9538345336914062}
-03/04/2022 00:33:36 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 00:33:40 - INFO - codeparrot_training - Step 9452: {'lr': 0.0004968787665339375, 'samples': 4839936, 'steps': 9452, 'loss/train': 2.258701801300049}
-03/04/2022 00:33:44 - INFO - codeparrot_training - Step 9453: {'lr': 0.0004968779305356289, 'samples': 4840448, 'steps': 9453, 'loss/train': 2.2284696102142334}
-03/04/2022 00:33:44 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 00:33:49 - INFO - codeparrot_training - Step 9454: {'lr': 0.0004968770944260808, 'samples': 4840960, 'steps': 9454, 'loss/train': 1.9267702102661133}
-03/04/2022 00:33:52 - INFO - codeparrot_training - Step 9455: {'lr': 0.0004968762582052938, 'samples': 4841472, 'steps': 9455, 'loss/train': 1.3459590673446655}
-03/04/2022 00:33:53 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/04/2022 00:33:57 - INFO - codeparrot_training - Step 9456: {'lr': 0.0004968754218732682, 'samples': 4841984, 'steps': 9456, 'loss/train': 0.8432947397232056}
-03/04/2022 00:34:01 - INFO - codeparrot_training - Step 9457: {'lr': 0.0004968745854300043, 'samples': 4842496, 'steps': 9457, 'loss/train': 3.7386224269866943}
-03/04/2022 00:34:01 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 00:34:06 - INFO - codeparrot_training - Step 9458: {'lr': 0.0004968737488755025, 'samples': 4843008, 'steps': 9458, 'loss/train': 2.6406099796295166}
-03/04/2022 00:34:09 - INFO - codeparrot_training - Step 9459: {'lr': 0.0004968729122097632, 'samples': 4843520, 'steps': 9459, 'loss/train': 1.8009206056594849}
-03/04/2022 00:34:10 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 00:34:14 - INFO - codeparrot_training - Step 9460: {'lr': 0.0004968720754327867, 'samples': 4844032, 'steps': 9460, 'loss/train': 2.096625328063965}
-03/04/2022 00:34:18 - INFO - codeparrot_training - Step 9461: {'lr': 0.0004968712385445737, 'samples': 4844544, 'steps': 9461, 'loss/train': 1.8695555925369263}
-03/04/2022 00:34:18 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 00:34:23 - INFO - codeparrot_training - Step 9462: {'lr': 0.0004968704015451241, 'samples': 4845056, 'steps': 9462, 'loss/train': 2.0349457263946533}
-03/04/2022 00:34:26 - INFO - codeparrot_training - Step 9463: {'lr': 0.0004968695644344387, 'samples': 4845568, 'steps': 9463, 'loss/train': 2.344014883041382}
-03/04/2022 00:34:26 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/04/2022 00:34:31 - INFO - codeparrot_training - Step 9464: {'lr': 0.0004968687272125174, 'samples': 4846080, 'steps': 9464, 'loss/train': 1.897958755493164}
-03/04/2022 00:34:34 - INFO - codeparrot_training - Step 9465: {'lr': 0.0004968678898793611, 'samples': 4846592, 'steps': 9465, 'loss/train': 1.4412239789962769}
-03/04/2022 00:34:34 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/04/2022 00:34:39 - INFO - codeparrot_training - Step 9466: {'lr': 0.0004968670524349699, 'samples': 4847104, 'steps': 9466, 'loss/train': 3.165051221847534}
-03/04/2022 00:34:43 - INFO - codeparrot_training - Step 9467: {'lr': 0.0004968662148793441, 'samples': 4847616, 'steps': 9467, 'loss/train': 1.4344590902328491}
-03/04/2022 00:34:43 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/04/2022 00:34:48 - INFO - codeparrot_training - Step 9468: {'lr': 0.0004968653772124843, 'samples': 4848128, 'steps': 9468, 'loss/train': 2.6629891395568848}
-03/04/2022 00:34:51 - INFO - codeparrot_training - Step 9469: {'lr': 0.0004968645394343908, 'samples': 4848640, 'steps': 9469, 'loss/train': 2.776944398880005}
-03/04/2022 00:34:51 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/04/2022 00:34:56 - INFO - codeparrot_training - Step 9470: {'lr': 0.0004968637015450639, 'samples': 4849152, 'steps': 9470, 'loss/train': 2.292492389678955}
-03/04/2022 00:35:00 - INFO - codeparrot_training - Step 9471: {'lr': 0.000496862863544504, 'samples': 4849664, 'steps': 9471, 'loss/train': 4.312722682952881}
-03/04/2022 00:35:00 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 00:35:05 - INFO - codeparrot_training - Step 9472: {'lr': 0.0004968620254327114, 'samples': 4850176, 'steps': 9472, 'loss/train': 2.252903699874878}
-03/04/2022 00:35:08 - INFO - codeparrot_training - Step 9473: {'lr': 0.0004968611872096868, 'samples': 4850688, 'steps': 9473, 'loss/train': 2.1082425117492676}
-03/04/2022 00:35:08 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 00:35:13 - INFO - codeparrot_training - Step 9474: {'lr': 0.0004968603488754302, 'samples': 4851200, 'steps': 9474, 'loss/train': 0.9737374782562256}
-03/04/2022 00:35:17 - INFO - codeparrot_training - Step 9475: {'lr': 0.0004968595104299422, 'samples': 4851712, 'steps': 9475, 'loss/train': 2.2869069576263428}
-03/04/2022 00:35:17 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/04/2022 00:35:22 - INFO - codeparrot_training - Step 9476: {'lr': 0.000496858671873223, 'samples': 4852224, 'steps': 9476, 'loss/train': 2.1089420318603516}
-03/04/2022 00:35:25 - INFO - codeparrot_training - Step 9477: {'lr': 0.0004968578332052733, 'samples': 4852736, 'steps': 9477, 'loss/train': 2.167332649230957}
-03/04/2022 00:35:25 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/04/2022 00:35:30 - INFO - codeparrot_training - Step 9478: {'lr': 0.0004968569944260932, 'samples': 4853248, 'steps': 9478, 'loss/train': 1.6837676763534546}
-03/04/2022 00:35:33 - INFO - codeparrot_training - Step 9479: {'lr': 0.0004968561555356831, 'samples': 4853760, 'steps': 9479, 'loss/train': 1.6462342739105225}
-03/04/2022 00:35:33 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 00:35:39 - INFO - codeparrot_training - Step 9480: {'lr': 0.0004968553165340435, 'samples': 4854272, 'steps': 9480, 'loss/train': 2.3664462566375732}
-03/04/2022 00:35:42 - INFO - codeparrot_training - Step 9481: {'lr': 0.0004968544774211746, 'samples': 4854784, 'steps': 9481, 'loss/train': 2.173189163208008}
-03/04/2022 00:35:42 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/04/2022 00:35:47 - INFO - codeparrot_training - Step 9482: {'lr': 0.0004968536381970769, 'samples': 4855296, 'steps': 9482, 'loss/train': 2.0238335132598877}
-03/04/2022 00:35:51 - INFO - codeparrot_training - Step 9483: {'lr': 0.0004968527988617508, 'samples': 4855808, 'steps': 9483, 'loss/train': 2.1865737438201904}
-03/04/2022 00:35:51 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 00:35:56 - INFO - codeparrot_training - Step 9484: {'lr': 0.0004968519594151966, 'samples': 4856320, 'steps': 9484, 'loss/train': 1.967576503753662}
-03/04/2022 00:35:59 - INFO - codeparrot_training - Step 9485: {'lr': 0.0004968511198574147, 'samples': 4856832, 'steps': 9485, 'loss/train': 2.1977994441986084}
-03/04/2022 00:35:59 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 00:36:04 - INFO - codeparrot_training - Step 9486: {'lr': 0.0004968502801884056, 'samples': 4857344, 'steps': 9486, 'loss/train': 1.9620847702026367}
-03/04/2022 00:36:07 - INFO - codeparrot_training - Step 9487: {'lr': 0.0004968494404081695, 'samples': 4857856, 'steps': 9487, 'loss/train': 2.1325061321258545}
-03/04/2022 00:36:08 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/04/2022 00:36:13 - INFO - codeparrot_training - Step 9488: {'lr': 0.0004968486005167069, 'samples': 4858368, 'steps': 9488, 'loss/train': 2.671093702316284}
-03/04/2022 00:36:16 - INFO - codeparrot_training - Step 9489: {'lr': 0.000496847760514018, 'samples': 4858880, 'steps': 9489, 'loss/train': 1.625858187675476}
-03/04/2022 00:36:16 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 00:36:22 - INFO - codeparrot_training - Step 9490: {'lr': 0.0004968469204001035, 'samples': 4859392, 'steps': 9490, 'loss/train': 2.1902425289154053}
-03/04/2022 00:36:25 - INFO - codeparrot_training - Step 9491: {'lr': 0.0004968460801749635, 'samples': 4859904, 'steps': 9491, 'loss/train': 1.71737802028656}
-03/04/2022 00:36:28 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/04/2022 00:36:31 - INFO - codeparrot_training - Step 9492: {'lr': 0.0004968452398385984, 'samples': 4860416, 'steps': 9492, 'loss/train': 0.564765453338623}
-03/04/2022 00:36:34 - INFO - codeparrot_training - Step 9493: {'lr': 0.0004968443993910086, 'samples': 4860928, 'steps': 9493, 'loss/train': 2.317901134490967}
-03/04/2022 00:36:37 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/04/2022 00:36:39 - INFO - codeparrot_training - Step 9494: {'lr': 0.0004968435588321947, 'samples': 4861440, 'steps': 9494, 'loss/train': 2.1557700634002686}
-03/04/2022 00:36:42 - INFO - codeparrot_training - Step 9495: {'lr': 0.0004968427181621567, 'samples': 4861952, 'steps': 9495, 'loss/train': 1.7499632835388184}
-03/04/2022 00:36:45 - INFO - codeparrot_training - Step 9496: {'lr': 0.0004968418773808954, 'samples': 4862464, 'steps': 9496, 'loss/train': 2.714104413986206}
-03/04/2022 00:36:45 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/04/2022 00:36:51 - INFO - codeparrot_training - Step 9497: {'lr': 0.0004968410364884109, 'samples': 4862976, 'steps': 9497, 'loss/train': 2.8083295822143555}
-03/04/2022 00:36:54 - INFO - codeparrot_training - Step 9498: {'lr': 0.0004968401954847035, 'samples': 4863488, 'steps': 9498, 'loss/train': 1.8996977806091309}
-03/04/2022 00:36:54 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 00:36:59 - INFO - codeparrot_training - Step 9499: {'lr': 0.0004968393543697739, 'samples': 4864000, 'steps': 9499, 'loss/train': 2.8358747959136963}
-03/04/2022 00:37:02 - INFO - codeparrot_training - Step 9500: {'lr': 0.0004968385131436222, 'samples': 4864512, 'steps': 9500, 'loss/train': 1.9860872030258179}
-03/04/2022 00:37:03 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 00:37:08 - INFO - codeparrot_training - Step 9501: {'lr': 0.0004968376718062488, 'samples': 4865024, 'steps': 9501, 'loss/train': 2.6315510272979736}
-03/04/2022 00:37:11 - INFO - codeparrot_training - Step 9502: {'lr': 0.0004968368303576542, 'samples': 4865536, 'steps': 9502, 'loss/train': 1.681376338005066}
-03/04/2022 00:37:11 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 00:37:16 - INFO - codeparrot_training - Step 9503: {'lr': 0.0004968359887978389, 'samples': 4866048, 'steps': 9503, 'loss/train': 1.4849839210510254}
-03/04/2022 00:37:19 - INFO - codeparrot_training - Step 9504: {'lr': 0.0004968351471268029, 'samples': 4866560, 'steps': 9504, 'loss/train': 2.5436618328094482}
-03/04/2022 00:37:19 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 00:37:25 - INFO - codeparrot_training - Step 9505: {'lr': 0.0004968343053445469, 'samples': 4867072, 'steps': 9505, 'loss/train': 2.815591335296631}
-03/04/2022 00:37:27 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 00:37:30 - INFO - codeparrot_training - Step 9506: {'lr': 0.0004968334634510712, 'samples': 4867584, 'steps': 9506, 'loss/train': 1.7926026582717896}
-03/04/2022 00:37:33 - INFO - codeparrot_training - Step 9507: {'lr': 0.000496832621446376, 'samples': 4868096, 'steps': 9507, 'loss/train': 2.1979565620422363}
-03/04/2022 00:37:36 - INFO - codeparrot_training - Step 9508: {'lr': 0.000496831779330462, 'samples': 4868608, 'steps': 9508, 'loss/train': 1.546596884727478}
-03/04/2022 00:37:36 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 00:37:41 - INFO - codeparrot_training - Step 9509: {'lr': 0.0004968309371033293, 'samples': 4869120, 'steps': 9509, 'loss/train': 0.6592910885810852}
-03/04/2022 00:37:45 - INFO - codeparrot_training - Step 9510: {'lr': 0.0004968300947649784, 'samples': 4869632, 'steps': 9510, 'loss/train': 2.760103225708008}
-03/04/2022 00:37:45 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/04/2022 00:37:50 - INFO - codeparrot_training - Step 9511: {'lr': 0.0004968292523154096, 'samples': 4870144, 'steps': 9511, 'loss/train': 2.448528289794922}
-03/04/2022 00:37:53 - INFO - codeparrot_training - Step 9512: {'lr': 0.0004968284097546235, 'samples': 4870656, 'steps': 9512, 'loss/train': 1.964250922203064}
-03/04/2022 00:37:53 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/04/2022 00:37:58 - INFO - codeparrot_training - Step 9513: {'lr': 0.0004968275670826204, 'samples': 4871168, 'steps': 9513, 'loss/train': 2.6569101810455322}
-03/04/2022 00:38:02 - INFO - codeparrot_training - Step 9514: {'lr': 0.0004968267242994003, 'samples': 4871680, 'steps': 9514, 'loss/train': 1.8165651559829712}
-03/04/2022 00:38:02 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/04/2022 00:38:07 - INFO - codeparrot_training - Step 9515: {'lr': 0.0004968258814049641, 'samples': 4872192, 'steps': 9515, 'loss/train': 1.8110647201538086}
-03/04/2022 00:38:10 - INFO - codeparrot_training - Step 9516: {'lr': 0.0004968250383993119, 'samples': 4872704, 'steps': 9516, 'loss/train': 2.248514413833618}
-03/04/2022 00:38:11 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/04/2022 00:38:15 - INFO - codeparrot_training - Step 9517: {'lr': 0.0004968241952824442, 'samples': 4873216, 'steps': 9517, 'loss/train': 2.102259635925293}
-03/04/2022 00:38:19 - INFO - codeparrot_training - Step 9518: {'lr': 0.0004968233520543613, 'samples': 4873728, 'steps': 9518, 'loss/train': 2.685593366622925}
-03/04/2022 00:38:19 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/04/2022 00:38:24 - INFO - codeparrot_training - Step 9519: {'lr': 0.0004968225087150636, 'samples': 4874240, 'steps': 9519, 'loss/train': 1.8476786613464355}
-03/04/2022 00:38:27 - INFO - codeparrot_training - Step 9520: {'lr': 0.0004968216652645515, 'samples': 4874752, 'steps': 9520, 'loss/train': 1.2701572179794312}
-03/04/2022 00:38:28 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/04/2022 00:38:32 - INFO - codeparrot_training - Step 9521: {'lr': 0.0004968208217028254, 'samples': 4875264, 'steps': 9521, 'loss/train': 1.497576355934143}
-03/04/2022 00:38:35 - INFO - codeparrot_training - Step 9522: {'lr': 0.0004968199780298855, 'samples': 4875776, 'steps': 9522, 'loss/train': 1.9628808498382568}
-03/04/2022 00:38:36 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/04/2022 00:38:41 - INFO - codeparrot_training - Step 9523: {'lr': 0.0004968191342457325, 'samples': 4876288, 'steps': 9523, 'loss/train': 2.142526865005493}
-03/04/2022 00:38:44 - INFO - codeparrot_training - Step 9524: {'lr': 0.0004968182903503665, 'samples': 4876800, 'steps': 9524, 'loss/train': 2.5150575637817383}
-03/04/2022 00:38:44 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/04/2022 00:38:49 - INFO - codeparrot_training - Step 9525: {'lr': 0.0004968174463437881, 'samples': 4877312, 'steps': 9525, 'loss/train': 2.4731318950653076}
-03/04/2022 00:38:52 - INFO - codeparrot_training - Step 9526: {'lr': 0.0004968166022259974, 'samples': 4877824, 'steps': 9526, 'loss/train': 1.18587064743042}
-03/04/2022 00:38:53 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/04/2022 00:38:58 - INFO - codeparrot_training - Step 9527: {'lr': 0.0004968157579969951, 'samples': 4878336, 'steps': 9527, 'loss/train': 2.2344629764556885}
-03/04/2022 00:39:01 - INFO - codeparrot_training - Step 9528: {'lr': 0.0004968149136567814, 'samples': 4878848, 'steps': 9528, 'loss/train': 2.078866720199585}
-03/04/2022 00:39:01 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/04/2022 00:39:06 - INFO - codeparrot_training - Step 9529: {'lr': 0.0004968140692053567, 'samples': 4879360, 'steps': 9529, 'loss/train': 1.736314058303833}
-03/04/2022 00:39:09 - INFO - codeparrot_training - Step 9530: {'lr': 0.0004968132246427212, 'samples': 4879872, 'steps': 9530, 'loss/train': 2.0500097274780273}
-03/04/2022 00:39:10 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/04/2022 00:39:15 - INFO - codeparrot_training - Step 9531: {'lr': 0.0004968123799688757, 'samples': 4880384, 'steps': 9531, 'loss/train': 2.2536776065826416}
-03/04/2022 00:39:18 - INFO - codeparrot_training - Step 9532: {'lr': 0.0004968115351838203, 'samples': 4880896, 'steps': 9532, 'loss/train': 0.6317681670188904}
-03/04/2022 00:39:20 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 00:39:23 - INFO - codeparrot_training - Step 9533: {'lr': 0.0004968106902875554, 'samples': 4881408, 'steps': 9533, 'loss/train': 2.410860061645508}
-03/04/2022 00:39:27 - INFO - codeparrot_training - Step 9534: {'lr': 0.0004968098452800815, 'samples': 4881920, 'steps': 9534, 'loss/train': 2.1852591037750244}
-03/04/2022 00:39:29 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/04/2022 00:39:32 - INFO - codeparrot_training - Step 9535: {'lr': 0.0004968090001613987, 'samples': 4882432, 'steps': 9535, 'loss/train': 1.8829210996627808}
-03/04/2022 00:39:35 - INFO - codeparrot_training - Step 9536: {'lr': 0.0004968081549315078, 'samples': 4882944, 'steps': 9536, 'loss/train': 1.0233794450759888}
-03/04/2022 00:39:38 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 00:39:41 - INFO - codeparrot_training - Step 9537: {'lr': 0.0004968073095904088, 'samples': 4883456, 'steps': 9537, 'loss/train': 2.8556461334228516}
-03/04/2022 00:39:44 - INFO - codeparrot_training - Step 9538: {'lr': 0.0004968064641381022, 'samples': 4883968, 'steps': 9538, 'loss/train': 1.9632902145385742}
-03/04/2022 00:39:46 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 00:39:49 - INFO - codeparrot_training - Step 9539: {'lr': 0.0004968056185745886, 'samples': 4884480, 'steps': 9539, 'loss/train': 2.0075912475585938}
-03/04/2022 00:39:52 - INFO - codeparrot_training - Step 9540: {'lr': 0.000496804772899868, 'samples': 4884992, 'steps': 9540, 'loss/train': 2.0008034706115723}
-03/04/2022 00:39:54 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/04/2022 00:39:57 - INFO - codeparrot_training - Step 9541: {'lr': 0.0004968039271139412, 'samples': 4885504, 'steps': 9541, 'loss/train': 1.7014408111572266}
-03/04/2022 00:40:00 - INFO - codeparrot_training - Step 9542: {'lr': 0.0004968030812168082, 'samples': 4886016, 'steps': 9542, 'loss/train': 2.687669515609741}
-03/04/2022 00:40:03 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 00:40:06 - INFO - codeparrot_training - Step 9543: {'lr': 0.0004968022352084695, 'samples': 4886528, 'steps': 9543, 'loss/train': 2.5983126163482666}
-03/04/2022 00:40:09 - INFO - codeparrot_training - Step 9544: {'lr': 0.0004968013890889256, 'samples': 4887040, 'steps': 9544, 'loss/train': 2.38220477104187}
-03/04/2022 00:40:11 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/04/2022 00:40:14 - INFO - codeparrot_training - Step 9545: {'lr': 0.0004968005428581767, 'samples': 4887552, 'steps': 9545, 'loss/train': 2.110363245010376}
-03/04/2022 00:40:17 - INFO - codeparrot_training - Step 9546: {'lr': 0.0004967996965162235, 'samples': 4888064, 'steps': 9546, 'loss/train': 1.9195976257324219}
-03/04/2022 00:40:19 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/04/2022 00:40:22 - INFO - codeparrot_training - Step 9547: {'lr': 0.0004967988500630661, 'samples': 4888576, 'steps': 9547, 'loss/train': 2.3879871368408203}
-03/04/2022 00:40:26 - INFO - codeparrot_training - Step 9548: {'lr': 0.0004967980034987048, 'samples': 4889088, 'steps': 9548, 'loss/train': 1.8188672065734863}
-03/04/2022 00:40:27 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 00:40:31 - INFO - codeparrot_training - Step 9549: {'lr': 0.0004967971568231402, 'samples': 4889600, 'steps': 9549, 'loss/train': 1.7223682403564453}
-03/04/2022 00:40:34 - INFO - codeparrot_training - Step 9550: {'lr': 0.0004967963100363726, 'samples': 4890112, 'steps': 9550, 'loss/train': 1.4196245670318604}
-03/04/2022 00:40:36 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 00:40:39 - INFO - codeparrot_training - Step 9551: {'lr': 0.0004967954631384025, 'samples': 4890624, 'steps': 9551, 'loss/train': 1.467057466506958}
-03/04/2022 00:40:42 - INFO - codeparrot_training - Step 9552: {'lr': 0.00049679461612923, 'samples': 4891136, 'steps': 9552, 'loss/train': 2.4690639972686768}
-03/04/2022 00:40:44 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/04/2022 00:40:48 - INFO - codeparrot_training - Step 9553: {'lr': 0.0004967937690088558, 'samples': 4891648, 'steps': 9553, 'loss/train': 2.4236629009246826}
-03/04/2022 00:40:51 - INFO - codeparrot_training - Step 9554: {'lr': 0.0004967929217772801, 'samples': 4892160, 'steps': 9554, 'loss/train': 1.6976436376571655}
-03/04/2022 00:40:53 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/04/2022 00:40:56 - INFO - codeparrot_training - Step 9555: {'lr': 0.0004967920744345033, 'samples': 4892672, 'steps': 9555, 'loss/train': 1.0452837944030762}
-03/04/2022 00:40:59 - INFO - codeparrot_training - Step 9556: {'lr': 0.0004967912269805257, 'samples': 4893184, 'steps': 9556, 'loss/train': 2.2211079597473145}
-03/04/2022 00:41:01 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/04/2022 00:41:04 - INFO - codeparrot_training - Step 9557: {'lr': 0.000496790379415348, 'samples': 4893696, 'steps': 9557, 'loss/train': 2.0902838706970215}
-03/04/2022 00:41:08 - INFO - codeparrot_training - Step 9558: {'lr': 0.0004967895317389702, 'samples': 4894208, 'steps': 9558, 'loss/train': 2.115816593170166}
-03/04/2022 00:41:09 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/04/2022 00:41:14 - INFO - codeparrot_training - Step 9559: {'lr': 0.0004967886839513929, 'samples': 4894720, 'steps': 9559, 'loss/train': 0.59293532371521}
-03/04/2022 00:41:17 - INFO - codeparrot_training - Step 9560: {'lr': 0.0004967878360526163, 'samples': 4895232, 'steps': 9560, 'loss/train': 2.325099229812622}
-03/04/2022 00:41:20 - INFO - codeparrot_training - Step 9561: {'lr': 0.0004967869880426411, 'samples': 4895744, 'steps': 9561, 'loss/train': 2.1006710529327393}
-03/04/2022 00:41:21 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/04/2022 00:41:25 - INFO - codeparrot_training - Step 9562: {'lr': 0.0004967861399214674, 'samples': 4896256, 'steps': 9562, 'loss/train': 2.603506565093994}
-03/04/2022 00:41:29 - INFO - codeparrot_training - Step 9563: {'lr': 0.0004967852916890958, 'samples': 4896768, 'steps': 9563, 'loss/train': 2.4387764930725098}
-03/04/2022 00:41:30 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/04/2022 00:41:34 - INFO - codeparrot_training - Step 9564: {'lr': 0.0004967844433455263, 'samples': 4897280, 'steps': 9564, 'loss/train': 2.811279058456421}
-03/04/2022 00:41:37 - INFO - codeparrot_training - Step 9565: {'lr': 0.0004967835948907598, 'samples': 4897792, 'steps': 9565, 'loss/train': 2.046402931213379}
-03/04/2022 00:41:39 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/04/2022 00:41:42 - INFO - codeparrot_training - Step 9566: {'lr': 0.0004967827463247962, 'samples': 4898304, 'steps': 9566, 'loss/train': 1.4415860176086426}
-03/04/2022 00:41:46 - INFO - codeparrot_training - Step 9567: {'lr': 0.0004967818976476363, 'samples': 4898816, 'steps': 9567, 'loss/train': 2.1431519985198975}
-03/04/2022 00:41:47 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/04/2022 00:41:51 - INFO - codeparrot_training - Step 9568: {'lr': 0.0004967810488592801, 'samples': 4899328, 'steps': 9568, 'loss/train': 1.6261354684829712}
-03/04/2022 00:41:54 - INFO - codeparrot_training - Step 9569: {'lr': 0.0004967801999597283, 'samples': 4899840, 'steps': 9569, 'loss/train': 2.212268590927124}
-03/04/2022 00:41:56 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 00:41:59 - INFO - codeparrot_training - Step 9570: {'lr': 0.0004967793509489811, 'samples': 4900352, 'steps': 9570, 'loss/train': 2.0487263202667236}
-03/04/2022 00:42:03 - INFO - codeparrot_training - Step 9571: {'lr': 0.0004967785018270389, 'samples': 4900864, 'steps': 9571, 'loss/train': 1.601386547088623}
-03/04/2022 00:42:04 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/04/2022 00:42:08 - INFO - codeparrot_training - Step 9572: {'lr': 0.0004967776525939022, 'samples': 4901376, 'steps': 9572, 'loss/train': 1.314338207244873}
-03/04/2022 00:42:11 - INFO - codeparrot_training - Step 9573: {'lr': 0.0004967768032495712, 'samples': 4901888, 'steps': 9573, 'loss/train': 2.565357208251953}
-03/04/2022 00:42:12 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/04/2022 00:42:16 - INFO - codeparrot_training - Step 9574: {'lr': 0.0004967759537940464, 'samples': 4902400, 'steps': 9574, 'loss/train': 2.869141101837158}
-03/04/2022 00:42:19 - INFO - codeparrot_training - Step 9575: {'lr': 0.0004967751042273282, 'samples': 4902912, 'steps': 9575, 'loss/train': 0.7147121429443359}
-03/04/2022 00:42:21 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/04/2022 00:42:25 - INFO - codeparrot_training - Step 9576: {'lr': 0.000496774254549417, 'samples': 4903424, 'steps': 9576, 'loss/train': 1.2526428699493408}
-03/04/2022 00:42:28 - INFO - codeparrot_training - Step 9577: {'lr': 0.0004967734047603131, 'samples': 4903936, 'steps': 9577, 'loss/train': 2.233748435974121}
-03/04/2022 00:42:29 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 00:42:33 - INFO - codeparrot_training - Step 9578: {'lr': 0.0004967725548600168, 'samples': 4904448, 'steps': 9578, 'loss/train': 2.0573878288269043}
-03/04/2022 00:42:36 - INFO - codeparrot_training - Step 9579: {'lr': 0.0004967717048485287, 'samples': 4904960, 'steps': 9579, 'loss/train': 2.2105846405029297}
-03/04/2022 00:42:37 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 00:42:41 - INFO - codeparrot_training - Step 9580: {'lr': 0.000496770854725849, 'samples': 4905472, 'steps': 9580, 'loss/train': 1.6177091598510742}
-03/04/2022 00:42:45 - INFO - codeparrot_training - Step 9581: {'lr': 0.0004967700044919783, 'samples': 4905984, 'steps': 9581, 'loss/train': 1.5262093544006348}
-03/04/2022 00:42:46 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 00:42:50 - INFO - codeparrot_training - Step 9582: {'lr': 0.0004967691541469167, 'samples': 4906496, 'steps': 9582, 'loss/train': 1.8251086473464966}
-03/04/2022 00:42:53 - INFO - codeparrot_training - Step 9583: {'lr': 0.0004967683036906648, 'samples': 4907008, 'steps': 9583, 'loss/train': 2.273956537246704}
-03/04/2022 00:42:54 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 00:42:58 - INFO - codeparrot_training - Step 9584: {'lr': 0.0004967674531232229, 'samples': 4907520, 'steps': 9584, 'loss/train': 0.7185317873954773}
-03/04/2022 00:43:01 - INFO - codeparrot_training - Step 9585: {'lr': 0.0004967666024445913, 'samples': 4908032, 'steps': 9585, 'loss/train': 2.7002198696136475}
-03/04/2022 00:43:02 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/04/2022 00:43:07 - INFO - codeparrot_training - Step 9586: {'lr': 0.0004967657516547707, 'samples': 4908544, 'steps': 9586, 'loss/train': 1.7451812028884888}
-03/04/2022 00:43:10 - INFO - codeparrot_training - Step 9587: {'lr': 0.0004967649007537611, 'samples': 4909056, 'steps': 9587, 'loss/train': 0.3285052478313446}
-03/04/2022 00:43:11 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 00:43:15 - INFO - codeparrot_training - Step 9588: {'lr': 0.0004967640497415631, 'samples': 4909568, 'steps': 9588, 'loss/train': 2.140354871749878}
-03/04/2022 00:43:18 - INFO - codeparrot_training - Step 9589: {'lr': 0.000496763198618177, 'samples': 4910080, 'steps': 9589, 'loss/train': 1.663657307624817}
-03/04/2022 00:43:19 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 00:43:24 - INFO - codeparrot_training - Step 9590: {'lr': 0.0004967623473836032, 'samples': 4910592, 'steps': 9590, 'loss/train': 2.026175022125244}
-03/04/2022 00:43:27 - INFO - codeparrot_training - Step 9591: {'lr': 0.0004967614960378421, 'samples': 4911104, 'steps': 9591, 'loss/train': 2.060040235519409}
-03/04/2022 00:43:28 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/04/2022 00:43:32 - INFO - codeparrot_training - Step 9592: {'lr': 0.000496760644580894, 'samples': 4911616, 'steps': 9592, 'loss/train': 1.8972113132476807}
-03/04/2022 00:43:35 - INFO - codeparrot_training - Step 9593: {'lr': 0.0004967597930127595, 'samples': 4912128, 'steps': 9593, 'loss/train': 6.752726078033447}
-03/04/2022 00:43:37 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/04/2022 00:43:40 - INFO - codeparrot_training - Step 9594: {'lr': 0.0004967589413334387, 'samples': 4912640, 'steps': 9594, 'loss/train': 2.449861764907837}
-03/04/2022 00:43:43 - INFO - codeparrot_training - Step 9595: {'lr': 0.0004967580895429322, 'samples': 4913152, 'steps': 9595, 'loss/train': 0.8782254457473755}
-03/04/2022 00:43:45 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/04/2022 00:43:49 - INFO - codeparrot_training - Step 9596: {'lr': 0.0004967572376412405, 'samples': 4913664, 'steps': 9596, 'loss/train': 1.883131980895996}
-03/04/2022 00:43:52 - INFO - codeparrot_training - Step 9597: {'lr': 0.0004967563856283636, 'samples': 4914176, 'steps': 9597, 'loss/train': 1.630464792251587}
-03/04/2022 00:43:55 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 00:43:57 - INFO - codeparrot_training - Step 9598: {'lr': 0.000496755533504302, 'samples': 4914688, 'steps': 9598, 'loss/train': 1.7774181365966797}
-03/04/2022 00:44:01 - INFO - codeparrot_training - Step 9599: {'lr': 0.0004967546812690563, 'samples': 4915200, 'steps': 9599, 'loss/train': 2.096942186355591}
-03/04/2022 00:44:03 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 00:44:06 - INFO - codeparrot_training - Step 9600: {'lr': 0.0004967538289226267, 'samples': 4915712, 'steps': 9600, 'loss/train': 2.920328140258789}
-03/04/2022 00:44:09 - INFO - codeparrot_training - Step 9601: {'lr': 0.0004967529764650137, 'samples': 4916224, 'steps': 9601, 'loss/train': 2.5053904056549072}
-03/04/2022 00:44:11 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/04/2022 00:44:14 - INFO - codeparrot_training - Step 9602: {'lr': 0.0004967521238962175, 'samples': 4916736, 'steps': 9602, 'loss/train': 2.53083872795105}
-03/04/2022 00:44:17 - INFO - codeparrot_training - Step 9603: {'lr': 0.0004967512712162387, 'samples': 4917248, 'steps': 9603, 'loss/train': 6.753556728363037}
-03/04/2022 00:44:20 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/04/2022 00:44:23 - INFO - codeparrot_training - Step 9604: {'lr': 0.0004967504184250775, 'samples': 4917760, 'steps': 9604, 'loss/train': 2.7096641063690186}
-03/04/2022 00:44:26 - INFO - codeparrot_training - Step 9605: {'lr': 0.0004967495655227344, 'samples': 4918272, 'steps': 9605, 'loss/train': 1.9136613607406616}
-03/04/2022 00:44:29 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/04/2022 00:44:31 - INFO - codeparrot_training - Step 9606: {'lr': 0.0004967487125092098, 'samples': 4918784, 'steps': 9606, 'loss/train': 3.109259843826294}
-03/04/2022 00:44:34 - INFO - codeparrot_training - Step 9607: {'lr': 0.0004967478593845041, 'samples': 4919296, 'steps': 9607, 'loss/train': 2.157491683959961}
-03/04/2022 00:44:38 - INFO - codeparrot_training - Step 9608: {'lr': 0.0004967470061486175, 'samples': 4919808, 'steps': 9608, 'loss/train': 1.6616406440734863}
-03/04/2022 00:44:38 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 00:44:43 - INFO - codeparrot_training - Step 9609: {'lr': 0.0004967461528015506, 'samples': 4920320, 'steps': 9609, 'loss/train': 2.0364255905151367}
-03/04/2022 00:44:46 - INFO - codeparrot_training - Step 9610: {'lr': 0.0004967452993433036, 'samples': 4920832, 'steps': 9610, 'loss/train': 1.5748155117034912}
-03/04/2022 00:44:46 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 00:44:51 - INFO - codeparrot_training - Step 9611: {'lr': 0.0004967444457738769, 'samples': 4921344, 'steps': 9611, 'loss/train': 1.064194679260254}
-03/04/2022 00:44:54 - INFO - codeparrot_training - Step 9612: {'lr': 0.0004967435920932711, 'samples': 4921856, 'steps': 9612, 'loss/train': 1.7130125761032104}
-03/04/2022 00:44:54 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/04/2022 00:45:00 - INFO - codeparrot_training - Step 9613: {'lr': 0.0004967427383014865, 'samples': 4922368, 'steps': 9613, 'loss/train': 1.8592005968093872}
-03/04/2022 00:45:03 - INFO - codeparrot_training - Step 9614: {'lr': 0.0004967418843985233, 'samples': 4922880, 'steps': 9614, 'loss/train': 2.3043153285980225}
-03/04/2022 00:45:03 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/04/2022 00:45:08 - INFO - codeparrot_training - Step 9615: {'lr': 0.0004967410303843821, 'samples': 4923392, 'steps': 9615, 'loss/train': 1.2858731746673584}
-03/04/2022 00:45:11 - INFO - codeparrot_training - Step 9616: {'lr': 0.0004967401762590631, 'samples': 4923904, 'steps': 9616, 'loss/train': 2.175881862640381}
-03/04/2022 00:45:12 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 00:45:17 - INFO - codeparrot_training - Step 9617: {'lr': 0.0004967393220225668, 'samples': 4924416, 'steps': 9617, 'loss/train': 1.2664209604263306}
-03/04/2022 00:45:20 - INFO - codeparrot_training - Step 9618: {'lr': 0.0004967384676748936, 'samples': 4924928, 'steps': 9618, 'loss/train': 2.1853225231170654}
-03/04/2022 00:45:20 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 00:45:25 - INFO - codeparrot_training - Step 9619: {'lr': 0.0004967376132160438, 'samples': 4925440, 'steps': 9619, 'loss/train': 2.158809185028076}
-03/04/2022 00:45:28 - INFO - codeparrot_training - Step 9620: {'lr': 0.000496736758646018, 'samples': 4925952, 'steps': 9620, 'loss/train': 2.1541757583618164}
-03/04/2022 00:45:29 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 00:45:33 - INFO - codeparrot_training - Step 9621: {'lr': 0.0004967359039648163, 'samples': 4926464, 'steps': 9621, 'loss/train': 1.92568039894104}
-03/04/2022 00:45:37 - INFO - codeparrot_training - Step 9622: {'lr': 0.0004967350491724392, 'samples': 4926976, 'steps': 9622, 'loss/train': 1.919762372970581}
-03/04/2022 00:45:38 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/04/2022 00:45:42 - INFO - codeparrot_training - Step 9623: {'lr': 0.0004967341942688872, 'samples': 4927488, 'steps': 9623, 'loss/train': 1.312420129776001}
-03/04/2022 00:45:45 - INFO - codeparrot_training - Step 9624: {'lr': 0.0004967333392541604, 'samples': 4928000, 'steps': 9624, 'loss/train': 1.2794549465179443}
-03/04/2022 00:45:46 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/04/2022 00:45:50 - INFO - codeparrot_training - Step 9625: {'lr': 0.0004967324841282596, 'samples': 4928512, 'steps': 9625, 'loss/train': 1.9090526103973389}
-03/04/2022 00:45:54 - INFO - codeparrot_training - Step 9626: {'lr': 0.0004967316288911847, 'samples': 4929024, 'steps': 9626, 'loss/train': 2.1528213024139404}
-03/04/2022 00:45:55 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 00:45:59 - INFO - codeparrot_training - Step 9627: {'lr': 0.0004967307735429365, 'samples': 4929536, 'steps': 9627, 'loss/train': 1.4030603170394897}
-03/04/2022 00:46:02 - INFO - codeparrot_training - Step 9628: {'lr': 0.0004967299180835153, 'samples': 4930048, 'steps': 9628, 'loss/train': 2.1087422370910645}
-03/04/2022 00:46:04 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/04/2022 00:46:07 - INFO - codeparrot_training - Step 9629: {'lr': 0.0004967290625129212, 'samples': 4930560, 'steps': 9629, 'loss/train': 1.4201582670211792}
-03/04/2022 00:46:11 - INFO - codeparrot_training - Step 9630: {'lr': 0.0004967282068311548, 'samples': 4931072, 'steps': 9630, 'loss/train': 1.1378644704818726}
-03/04/2022 00:46:12 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/04/2022 00:46:16 - INFO - codeparrot_training - Step 9631: {'lr': 0.0004967273510382166, 'samples': 4931584, 'steps': 9631, 'loss/train': 1.5853846073150635}
-03/04/2022 00:46:19 - INFO - codeparrot_training - Step 9632: {'lr': 0.0004967264951341069, 'samples': 4932096, 'steps': 9632, 'loss/train': 2.013780355453491}
-03/04/2022 00:46:21 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/04/2022 00:46:24 - INFO - codeparrot_training - Step 9633: {'lr': 0.0004967256391188258, 'samples': 4932608, 'steps': 9633, 'loss/train': 1.63016676902771}
-03/04/2022 00:46:27 - INFO - codeparrot_training - Step 9634: {'lr': 0.0004967247829923742, 'samples': 4933120, 'steps': 9634, 'loss/train': 1.2924201488494873}
-03/04/2022 00:46:29 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/04/2022 00:46:33 - INFO - codeparrot_training - Step 9635: {'lr': 0.0004967239267547521, 'samples': 4933632, 'steps': 9635, 'loss/train': 2.9405267238616943}
-03/04/2022 00:46:36 - INFO - codeparrot_training - Step 9636: {'lr': 0.00049672307040596, 'samples': 4934144, 'steps': 9636, 'loss/train': 1.7964622974395752}
-03/04/2022 00:46:37 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/04/2022 00:46:41 - INFO - codeparrot_training - Step 9637: {'lr': 0.0004967222139459983, 'samples': 4934656, 'steps': 9637, 'loss/train': 1.2276360988616943}
-03/04/2022 00:46:44 - INFO - codeparrot_training - Step 9638: {'lr': 0.0004967213573748674, 'samples': 4935168, 'steps': 9638, 'loss/train': 1.3267978429794312}
-03/04/2022 00:46:46 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/04/2022 00:46:50 - INFO - codeparrot_training - Step 9639: {'lr': 0.0004967205006925677, 'samples': 4935680, 'steps': 9639, 'loss/train': 2.221067190170288}
-03/04/2022 00:46:53 - INFO - codeparrot_training - Step 9640: {'lr': 0.0004967196438990995, 'samples': 4936192, 'steps': 9640, 'loss/train': 1.730214238166809}
-03/04/2022 00:46:54 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/04/2022 00:46:58 - INFO - codeparrot_training - Step 9641: {'lr': 0.0004967187869944632, 'samples': 4936704, 'steps': 9641, 'loss/train': 2.1015915870666504}
-03/04/2022 00:47:01 - INFO - codeparrot_training - Step 9642: {'lr': 0.0004967179299786593, 'samples': 4937216, 'steps': 9642, 'loss/train': 1.4041988849639893}
-03/04/2022 00:47:02 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 00:47:06 - INFO - codeparrot_training - Step 9643: {'lr': 0.000496717072851688, 'samples': 4937728, 'steps': 9643, 'loss/train': 1.7595795392990112}
-03/04/2022 00:47:10 - INFO - codeparrot_training - Step 9644: {'lr': 0.0004967162156135499, 'samples': 4938240, 'steps': 9644, 'loss/train': 1.7758655548095703}
-03/04/2022 00:47:11 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 00:47:15 - INFO - codeparrot_training - Step 9645: {'lr': 0.0004967153582642452, 'samples': 4938752, 'steps': 9645, 'loss/train': 2.9916088581085205}
-03/04/2022 00:47:18 - INFO - codeparrot_training - Step 9646: {'lr': 0.0004967145008037744, 'samples': 4939264, 'steps': 9646, 'loss/train': 1.5226919651031494}
-03/04/2022 00:47:19 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/04/2022 00:47:23 - INFO - codeparrot_training - Step 9647: {'lr': 0.000496713643232138, 'samples': 4939776, 'steps': 9647, 'loss/train': 2.0108842849731445}
-03/04/2022 00:47:26 - INFO - codeparrot_training - Step 9648: {'lr': 0.000496712785549336, 'samples': 4940288, 'steps': 9648, 'loss/train': 2.426023483276367}
-03/04/2022 00:47:27 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/04/2022 00:47:32 - INFO - codeparrot_training - Step 9649: {'lr': 0.0004967119277553692, 'samples': 4940800, 'steps': 9649, 'loss/train': 2.0691511631011963}
-03/04/2022 00:47:35 - INFO - codeparrot_training - Step 9650: {'lr': 0.0004967110698502377, 'samples': 4941312, 'steps': 9650, 'loss/train': 2.0493593215942383}
-03/04/2022 00:47:36 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/04/2022 00:47:40 - INFO - codeparrot_training - Step 9651: {'lr': 0.000496710211833942, 'samples': 4941824, 'steps': 9651, 'loss/train': 2.4240219593048096}
-03/04/2022 00:47:43 - INFO - codeparrot_training - Step 9652: {'lr': 0.0004967093537064825, 'samples': 4942336, 'steps': 9652, 'loss/train': 2.14263653755188}
-03/04/2022 00:47:44 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 00:47:49 - INFO - codeparrot_training - Step 9653: {'lr': 0.0004967084954678597, 'samples': 4942848, 'steps': 9653, 'loss/train': 3.1776158809661865}
-03/04/2022 00:47:52 - INFO - codeparrot_training - Step 9654: {'lr': 0.0004967076371180738, 'samples': 4943360, 'steps': 9654, 'loss/train': 1.5291380882263184}
-03/04/2022 00:47:52 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 00:47:57 - INFO - codeparrot_training - Step 9655: {'lr': 0.0004967067786571251, 'samples': 4943872, 'steps': 9655, 'loss/train': 1.5102802515029907}
-03/04/2022 00:48:00 - INFO - codeparrot_training - Step 9656: {'lr': 0.0004967059200850142, 'samples': 4944384, 'steps': 9656, 'loss/train': 0.9593333005905151}
-03/04/2022 00:48:01 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/04/2022 00:48:05 - INFO - codeparrot_training - Step 9657: {'lr': 0.0004967050614017415, 'samples': 4944896, 'steps': 9657, 'loss/train': 2.0514566898345947}
-03/04/2022 00:48:09 - INFO - codeparrot_training - Step 9658: {'lr': 0.0004967042026073073, 'samples': 4945408, 'steps': 9658, 'loss/train': 1.6471874713897705}
-03/04/2022 00:48:09 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 00:48:14 - INFO - codeparrot_training - Step 9659: {'lr': 0.000496703343701712, 'samples': 4945920, 'steps': 9659, 'loss/train': 2.1582694053649902}
-03/04/2022 00:48:17 - INFO - codeparrot_training - Step 9660: {'lr': 0.0004967024846849558, 'samples': 4946432, 'steps': 9660, 'loss/train': 1.8561187982559204}
-03/04/2022 00:48:18 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/04/2022 00:48:22 - INFO - codeparrot_training - Step 9661: {'lr': 0.0004967016255570394, 'samples': 4946944, 'steps': 9661, 'loss/train': 3.0760934352874756}
-03/04/2022 00:48:25 - INFO - codeparrot_training - Step 9662: {'lr': 0.0004967007663179632, 'samples': 4947456, 'steps': 9662, 'loss/train': 2.143228054046631}
-03/04/2022 00:48:26 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 00:48:31 - INFO - codeparrot_training - Step 9663: {'lr': 0.0004966999069677272, 'samples': 4947968, 'steps': 9663, 'loss/train': 1.6132124662399292}
-03/04/2022 00:48:34 - INFO - codeparrot_training - Step 9664: {'lr': 0.0004966990475063321, 'samples': 4948480, 'steps': 9664, 'loss/train': 2.082979202270508}
-03/04/2022 00:48:35 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/04/2022 00:48:39 - INFO - codeparrot_training - Step 9665: {'lr': 0.0004966981879337783, 'samples': 4948992, 'steps': 9665, 'loss/train': 3.1348249912261963}
-03/04/2022 00:48:42 - INFO - codeparrot_training - Step 9666: {'lr': 0.0004966973282500661, 'samples': 4949504, 'steps': 9666, 'loss/train': 1.059910774230957}
-03/04/2022 00:48:43 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/04/2022 00:48:48 - INFO - codeparrot_training - Step 9667: {'lr': 0.0004966964684551958, 'samples': 4950016, 'steps': 9667, 'loss/train': 1.8938552141189575}
-03/04/2022 00:48:51 - INFO - codeparrot_training - Step 9668: {'lr': 0.0004966956085491679, 'samples': 4950528, 'steps': 9668, 'loss/train': 2.3577616214752197}
-03/04/2022 00:48:52 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 00:48:56 - INFO - codeparrot_training - Step 9669: {'lr': 0.0004966947485319828, 'samples': 4951040, 'steps': 9669, 'loss/train': 1.7677127122879028}
-03/04/2022 00:49:00 - INFO - codeparrot_training - Step 9670: {'lr': 0.0004966938884036408, 'samples': 4951552, 'steps': 9670, 'loss/train': 1.9134465456008911}
-03/04/2022 00:49:00 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 00:49:05 - INFO - codeparrot_training - Step 9671: {'lr': 0.0004966930281641423, 'samples': 4952064, 'steps': 9671, 'loss/train': 2.0702359676361084}
-03/04/2022 00:49:08 - INFO - codeparrot_training - Step 9672: {'lr': 0.0004966921678134879, 'samples': 4952576, 'steps': 9672, 'loss/train': 1.5176559686660767}
-03/04/2022 00:49:09 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 00:49:13 - INFO - codeparrot_training - Step 9673: {'lr': 0.0004966913073516777, 'samples': 4953088, 'steps': 9673, 'loss/train': 1.3105825185775757}
-03/04/2022 00:49:16 - INFO - codeparrot_training - Step 9674: {'lr': 0.0004966904467787123, 'samples': 4953600, 'steps': 9674, 'loss/train': 2.418856143951416}
-03/04/2022 00:49:17 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/04/2022 00:49:22 - INFO - codeparrot_training - Step 9675: {'lr': 0.0004966895860945918, 'samples': 4954112, 'steps': 9675, 'loss/train': 1.9436956644058228}
-03/04/2022 00:49:25 - INFO - codeparrot_training - Step 9676: {'lr': 0.0004966887252993169, 'samples': 4954624, 'steps': 9676, 'loss/train': 2.3913064002990723}
-03/04/2022 00:49:26 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 00:49:30 - INFO - codeparrot_training - Step 9677: {'lr': 0.0004966878643928879, 'samples': 4955136, 'steps': 9677, 'loss/train': 2.421880006790161}
-03/04/2022 00:49:33 - INFO - codeparrot_training - Step 9678: {'lr': 0.0004966870033753051, 'samples': 4955648, 'steps': 9678, 'loss/train': 2.0838992595672607}
-03/04/2022 00:49:34 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 00:49:39 - INFO - codeparrot_training - Step 9679: {'lr': 0.0004966861422465689, 'samples': 4956160, 'steps': 9679, 'loss/train': 2.5098118782043457}
-03/04/2022 00:49:42 - INFO - codeparrot_training - Step 9680: {'lr': 0.0004966852810066798, 'samples': 4956672, 'steps': 9680, 'loss/train': 1.8561182022094727}
-03/04/2022 00:49:43 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/04/2022 00:49:47 - INFO - codeparrot_training - Step 9681: {'lr': 0.0004966844196556382, 'samples': 4957184, 'steps': 9681, 'loss/train': 1.9006702899932861}
-03/04/2022 00:49:50 - INFO - codeparrot_training - Step 9682: {'lr': 0.0004966835581934442, 'samples': 4957696, 'steps': 9682, 'loss/train': 1.5665302276611328}
-03/04/2022 00:49:51 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/04/2022 00:49:55 - INFO - codeparrot_training - Step 9683: {'lr': 0.0004966826966200985, 'samples': 4958208, 'steps': 9683, 'loss/train': 2.5289604663848877}
-03/04/2022 00:49:59 - INFO - codeparrot_training - Step 9684: {'lr': 0.0004966818349356015, 'samples': 4958720, 'steps': 9684, 'loss/train': 2.008021354675293}
-03/04/2022 00:49:59 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/04/2022 00:50:04 - INFO - codeparrot_training - Step 9685: {'lr': 0.0004966809731399533, 'samples': 4959232, 'steps': 9685, 'loss/train': 1.6297798156738281}
-03/04/2022 00:50:07 - INFO - codeparrot_training - Step 9686: {'lr': 0.0004966801112331545, 'samples': 4959744, 'steps': 9686, 'loss/train': 0.2804538607597351}
-03/04/2022 00:50:08 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/04/2022 00:50:12 - INFO - codeparrot_training - Step 9687: {'lr': 0.0004966792492152054, 'samples': 4960256, 'steps': 9687, 'loss/train': 2.400810956954956}
-03/04/2022 00:50:15 - INFO - codeparrot_training - Step 9688: {'lr': 0.0004966783870861066, 'samples': 4960768, 'steps': 9688, 'loss/train': 0.21915817260742188}
-03/04/2022 00:50:16 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/04/2022 00:50:21 - INFO - codeparrot_training - Step 9689: {'lr': 0.0004966775248458582, 'samples': 4961280, 'steps': 9689, 'loss/train': 1.8352218866348267}
-03/04/2022 00:50:24 - INFO - codeparrot_training - Step 9690: {'lr': 0.0004966766624944607, 'samples': 4961792, 'steps': 9690, 'loss/train': 1.4555763006210327}
-03/04/2022 00:50:24 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/04/2022 00:50:29 - INFO - codeparrot_training - Step 9691: {'lr': 0.0004966758000319147, 'samples': 4962304, 'steps': 9691, 'loss/train': 2.219468593597412}
-03/04/2022 00:50:32 - INFO - codeparrot_training - Step 9692: {'lr': 0.0004966749374582202, 'samples': 4962816, 'steps': 9692, 'loss/train': 1.015545129776001}
-03/04/2022 00:50:33 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/04/2022 00:50:38 - INFO - codeparrot_training - Step 9693: {'lr': 0.0004966740747733778, 'samples': 4963328, 'steps': 9693, 'loss/train': 1.8794748783111572}
-03/04/2022 00:50:41 - INFO - codeparrot_training - Step 9694: {'lr': 0.0004966732119773879, 'samples': 4963840, 'steps': 9694, 'loss/train': 1.598037838935852}
-03/04/2022 00:50:41 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/04/2022 00:50:46 - INFO - codeparrot_training - Step 9695: {'lr': 0.0004966723490702509, 'samples': 4964352, 'steps': 9695, 'loss/train': 2.7766895294189453}
-03/04/2022 00:50:49 - INFO - codeparrot_training - Step 9696: {'lr': 0.000496671486051967, 'samples': 4964864, 'steps': 9696, 'loss/train': 1.8934247493743896}
-03/04/2022 00:50:50 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/04/2022 00:50:54 - INFO - codeparrot_training - Step 9697: {'lr': 0.0004966706229225368, 'samples': 4965376, 'steps': 9697, 'loss/train': 1.997854471206665}
-03/04/2022 00:50:58 - INFO - codeparrot_training - Step 9698: {'lr': 0.0004966697596819607, 'samples': 4965888, 'steps': 9698, 'loss/train': 2.1659088134765625}
-03/04/2022 00:50:58 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/04/2022 00:51:03 - INFO - codeparrot_training - Step 9699: {'lr': 0.0004966688963302389, 'samples': 4966400, 'steps': 9699, 'loss/train': 2.6019914150238037}
-03/04/2022 00:51:06 - INFO - codeparrot_training - Step 9700: {'lr': 0.000496668032867372, 'samples': 4966912, 'steps': 9700, 'loss/train': 1.0836254358291626}
-03/04/2022 00:51:07 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/04/2022 00:51:11 - INFO - codeparrot_training - Step 9701: {'lr': 0.0004966671692933603, 'samples': 4967424, 'steps': 9701, 'loss/train': 1.8340905904769897}
-03/04/2022 00:51:14 - INFO - codeparrot_training - Step 9702: {'lr': 0.0004966663056082041, 'samples': 4967936, 'steps': 9702, 'loss/train': 1.0506649017333984}
-03/04/2022 00:51:15 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 00:51:20 - INFO - codeparrot_training - Step 9703: {'lr': 0.0004966654418119039, 'samples': 4968448, 'steps': 9703, 'loss/train': 1.8752719163894653}
-03/04/2022 00:51:23 - INFO - codeparrot_training - Step 9704: {'lr': 0.00049666457790446, 'samples': 4968960, 'steps': 9704, 'loss/train': 2.249958038330078}
-03/04/2022 00:51:23 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 00:51:28 - INFO - codeparrot_training - Step 9705: {'lr': 0.000496663713885873, 'samples': 4969472, 'steps': 9705, 'loss/train': 2.188457489013672}
-03/04/2022 00:51:31 - INFO - codeparrot_training - Step 9706: {'lr': 0.0004966628497561431, 'samples': 4969984, 'steps': 9706, 'loss/train': 2.5966386795043945}
-03/04/2022 00:51:32 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 00:51:37 - INFO - codeparrot_training - Step 9707: {'lr': 0.0004966619855152706, 'samples': 4970496, 'steps': 9707, 'loss/train': 1.2433583736419678}
-03/04/2022 00:51:40 - INFO - codeparrot_training - Step 9708: {'lr': 0.0004966611211632561, 'samples': 4971008, 'steps': 9708, 'loss/train': 1.9119778871536255}
-03/04/2022 00:51:40 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/04/2022 00:51:45 - INFO - codeparrot_training - Step 9709: {'lr': 0.0004966602567000999, 'samples': 4971520, 'steps': 9709, 'loss/train': 2.0539004802703857}
-03/04/2022 00:51:48 - INFO - codeparrot_training - Step 9710: {'lr': 0.0004966593921258023, 'samples': 4972032, 'steps': 9710, 'loss/train': 2.394622325897217}
-03/04/2022 00:51:49 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/04/2022 00:51:53 - INFO - codeparrot_training - Step 9711: {'lr': 0.000496658527440364, 'samples': 4972544, 'steps': 9711, 'loss/train': 0.722159206867218}
-03/04/2022 00:51:57 - INFO - codeparrot_training - Step 9712: {'lr': 0.000496657662643785, 'samples': 4973056, 'steps': 9712, 'loss/train': 2.643284559249878}
-03/04/2022 00:51:57 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/04/2022 00:52:02 - INFO - codeparrot_training - Step 9713: {'lr': 0.000496656797736066, 'samples': 4973568, 'steps': 9713, 'loss/train': 0.8162844777107239}
-03/04/2022 00:52:05 - INFO - codeparrot_training - Step 9714: {'lr': 0.0004966559327172071, 'samples': 4974080, 'steps': 9714, 'loss/train': 1.8675732612609863}
-03/04/2022 00:52:06 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 00:52:10 - INFO - codeparrot_training - Step 9715: {'lr': 0.0004966550675872089, 'samples': 4974592, 'steps': 9715, 'loss/train': 2.2929961681365967}
-03/04/2022 00:52:13 - INFO - codeparrot_training - Step 9716: {'lr': 0.0004966542023460718, 'samples': 4975104, 'steps': 9716, 'loss/train': 2.27500581741333}
-03/04/2022 00:52:14 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/04/2022 00:52:19 - INFO - codeparrot_training - Step 9717: {'lr': 0.000496653336993796, 'samples': 4975616, 'steps': 9717, 'loss/train': 2.6018996238708496}
-03/04/2022 00:52:22 - INFO - codeparrot_training - Step 9718: {'lr': 0.0004966524715303821, 'samples': 4976128, 'steps': 9718, 'loss/train': 2.045502185821533}
-03/04/2022 00:52:23 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 00:52:27 - INFO - codeparrot_training - Step 9719: {'lr': 0.0004966516059558304, 'samples': 4976640, 'steps': 9719, 'loss/train': 1.6117914915084839}
-03/04/2022 00:52:31 - INFO - codeparrot_training - Step 9720: {'lr': 0.0004966507402701413, 'samples': 4977152, 'steps': 9720, 'loss/train': 2.948491334915161}
-03/04/2022 00:52:33 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 00:52:36 - INFO - codeparrot_training - Step 9721: {'lr': 0.0004966498744733151, 'samples': 4977664, 'steps': 9721, 'loss/train': 2.676602363586426}
-03/04/2022 00:52:39 - INFO - codeparrot_training - Step 9722: {'lr': 0.0004966490085653523, 'samples': 4978176, 'steps': 9722, 'loss/train': 2.1988155841827393}
-03/04/2022 00:52:41 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 00:52:44 - INFO - codeparrot_training - Step 9723: {'lr': 0.0004966481425462533, 'samples': 4978688, 'steps': 9723, 'loss/train': 3.0331132411956787}
-03/04/2022 00:52:47 - INFO - codeparrot_training - Step 9724: {'lr': 0.0004966472764160183, 'samples': 4979200, 'steps': 9724, 'loss/train': 2.883615016937256}
-03/04/2022 00:52:50 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/04/2022 00:52:53 - INFO - codeparrot_training - Step 9725: {'lr': 0.000496646410174648, 'samples': 4979712, 'steps': 9725, 'loss/train': 2.0729360580444336}
-03/04/2022 00:52:56 - INFO - codeparrot_training - Step 9726: {'lr': 0.0004966455438221427, 'samples': 4980224, 'steps': 9726, 'loss/train': 2.3541762828826904}
-03/04/2022 00:52:59 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/04/2022 00:53:01 - INFO - codeparrot_training - Step 9727: {'lr': 0.0004966446773585026, 'samples': 4980736, 'steps': 9727, 'loss/train': 2.571898937225342}
-03/04/2022 00:53:05 - INFO - codeparrot_training - Step 9728: {'lr': 0.0004966438107837283, 'samples': 4981248, 'steps': 9728, 'loss/train': 2.9030110836029053}
-03/04/2022 00:53:07 - INFO - codeparrot_training - Skipping example with length 5 (seq_length=1024)
-03/04/2022 00:53:10 - INFO - codeparrot_training - Step 9729: {'lr': 0.00049664294409782, 'samples': 4981760, 'steps': 9729, 'loss/train': 1.7598012685775757}
-03/04/2022 00:53:13 - INFO - codeparrot_training - Step 9730: {'lr': 0.0004966420773007782, 'samples': 4982272, 'steps': 9730, 'loss/train': 1.8192925453186035}
-03/04/2022 00:53:16 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/04/2022 00:53:18 - INFO - codeparrot_training - Step 9731: {'lr': 0.0004966412103926034, 'samples': 4982784, 'steps': 9731, 'loss/train': 1.5644546747207642}
-03/04/2022 00:53:21 - INFO - codeparrot_training - Step 9732: {'lr': 0.0004966403433732958, 'samples': 4983296, 'steps': 9732, 'loss/train': 2.9438791275024414}
-03/04/2022 00:53:24 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/04/2022 00:53:27 - INFO - codeparrot_training - Step 9733: {'lr': 0.0004966394762428559, 'samples': 4983808, 'steps': 9733, 'loss/train': 2.1694729328155518}
-03/04/2022 00:53:30 - INFO - codeparrot_training - Step 9734: {'lr': 0.0004966386090012841, 'samples': 4984320, 'steps': 9734, 'loss/train': 2.2033066749572754}
-03/04/2022 00:53:32 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 00:53:35 - INFO - codeparrot_training - Step 9735: {'lr': 0.0004966377416485806, 'samples': 4984832, 'steps': 9735, 'loss/train': 2.212477207183838}
-03/04/2022 00:53:38 - INFO - codeparrot_training - Step 9736: {'lr': 0.0004966368741847461, 'samples': 4985344, 'steps': 9736, 'loss/train': 2.83300518989563}
-03/04/2022 00:53:40 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/04/2022 00:53:44 - INFO - codeparrot_training - Step 9737: {'lr': 0.0004966360066097807, 'samples': 4985856, 'steps': 9737, 'loss/train': 1.5519559383392334}
-03/04/2022 00:53:47 - INFO - codeparrot_training - Step 9738: {'lr': 0.0004966351389236851, 'samples': 4986368, 'steps': 9738, 'loss/train': 0.8999736905097961}
-03/04/2022 00:53:52 - INFO - codeparrot_training - Step 9739: {'lr': 0.0004966342711264593, 'samples': 4986880, 'steps': 9739, 'loss/train': 2.440338611602783}
-03/04/2022 00:53:55 - INFO - codeparrot_training - Step 9740: {'lr': 0.000496633403218104, 'samples': 4987392, 'steps': 9740, 'loss/train': 2.034283399581909}
-03/04/2022 00:53:57 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/04/2022 00:54:00 - INFO - codeparrot_training - Step 9741: {'lr': 0.0004966325351986195, 'samples': 4987904, 'steps': 9741, 'loss/train': 2.25520396232605}
-03/04/2022 00:54:04 - INFO - codeparrot_training - Step 9742: {'lr': 0.0004966316670680062, 'samples': 4988416, 'steps': 9742, 'loss/train': 1.9686247110366821}
-03/04/2022 00:54:06 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/04/2022 00:54:09 - INFO - codeparrot_training - Step 9743: {'lr': 0.0004966307988262644, 'samples': 4988928, 'steps': 9743, 'loss/train': 2.500173330307007}
-03/04/2022 00:54:12 - INFO - codeparrot_training - Step 9744: {'lr': 0.0004966299304733947, 'samples': 4989440, 'steps': 9744, 'loss/train': 1.4887388944625854}
-03/04/2022 00:54:14 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 00:54:17 - INFO - codeparrot_training - Step 9745: {'lr': 0.0004966290620093972, 'samples': 4989952, 'steps': 9745, 'loss/train': 1.5371779203414917}
-03/04/2022 00:54:20 - INFO - codeparrot_training - Step 9746: {'lr': 0.0004966281934342725, 'samples': 4990464, 'steps': 9746, 'loss/train': 2.6349451541900635}
-03/04/2022 00:54:23 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 00:54:26 - INFO - codeparrot_training - Step 9747: {'lr': 0.000496627324748021, 'samples': 4990976, 'steps': 9747, 'loss/train': 1.1569976806640625}
-03/04/2022 00:54:29 - INFO - codeparrot_training - Step 9748: {'lr': 0.000496626455950643, 'samples': 4991488, 'steps': 9748, 'loss/train': 1.702919363975525}
-03/04/2022 00:54:31 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/04/2022 00:54:34 - INFO - codeparrot_training - Step 9749: {'lr': 0.000496625587042139, 'samples': 4992000, 'steps': 9749, 'loss/train': 2.5896353721618652}
-03/04/2022 00:54:37 - INFO - codeparrot_training - Step 9750: {'lr': 0.0004966247180225092, 'samples': 4992512, 'steps': 9750, 'loss/train': 1.371558427810669}
-03/04/2022 00:54:39 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/04/2022 00:54:42 - INFO - codeparrot_training - Step 9751: {'lr': 0.0004966238488917542, 'samples': 4993024, 'steps': 9751, 'loss/train': 2.7432737350463867}
-03/04/2022 00:54:46 - INFO - codeparrot_training - Step 9752: {'lr': 0.0004966229796498742, 'samples': 4993536, 'steps': 9752, 'loss/train': 1.9661883115768433}
-03/04/2022 00:54:48 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/04/2022 00:54:51 - INFO - codeparrot_training - Step 9753: {'lr': 0.0004966221102968698, 'samples': 4994048, 'steps': 9753, 'loss/train': 2.1745524406433105}
-03/04/2022 00:54:54 - INFO - codeparrot_training - Step 9754: {'lr': 0.0004966212408327412, 'samples': 4994560, 'steps': 9754, 'loss/train': 2.305514097213745}
-03/04/2022 00:54:56 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/04/2022 00:54:59 - INFO - codeparrot_training - Step 9755: {'lr': 0.0004966203712574889, 'samples': 4995072, 'steps': 9755, 'loss/train': 1.971542239189148}
-03/04/2022 00:55:02 - INFO - codeparrot_training - Step 9756: {'lr': 0.0004966195015711132, 'samples': 4995584, 'steps': 9756, 'loss/train': 1.834297776222229}
-03/04/2022 00:55:04 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/04/2022 00:55:08 - INFO - codeparrot_training - Step 9757: {'lr': 0.0004966186317736146, 'samples': 4996096, 'steps': 9757, 'loss/train': 2.081338405609131}
-03/04/2022 00:55:11 - INFO - codeparrot_training - Step 9758: {'lr': 0.0004966177618649935, 'samples': 4996608, 'steps': 9758, 'loss/train': 1.9412819147109985}
-03/04/2022 00:55:13 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 00:55:16 - INFO - codeparrot_training - Step 9759: {'lr': 0.0004966168918452503, 'samples': 4997120, 'steps': 9759, 'loss/train': 0.5438695549964905}
-03/04/2022 00:55:19 - INFO - codeparrot_training - Step 9760: {'lr': 0.0004966160217143852, 'samples': 4997632, 'steps': 9760, 'loss/train': 2.555182456970215}
-03/04/2022 00:55:21 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/04/2022 00:55:25 - INFO - codeparrot_training - Step 9761: {'lr': 0.0004966151514723988, 'samples': 4998144, 'steps': 9761, 'loss/train': 2.504145383834839}
-03/04/2022 00:55:28 - INFO - codeparrot_training - Step 9762: {'lr': 0.0004966142811192914, 'samples': 4998656, 'steps': 9762, 'loss/train': 2.4950156211853027}
-03/04/2022 00:55:29 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/04/2022 00:55:33 - INFO - codeparrot_training - Step 9763: {'lr': 0.0004966134106550634, 'samples': 4999168, 'steps': 9763, 'loss/train': 2.393664836883545}
-03/04/2022 00:55:36 - INFO - codeparrot_training - Step 9764: {'lr': 0.0004966125400797152, 'samples': 4999680, 'steps': 9764, 'loss/train': 1.7134050130844116}
-03/04/2022 00:55:38 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 00:55:42 - INFO - codeparrot_training - Step 9765: {'lr': 0.0004966116693932472, 'samples': 5000192, 'steps': 9765, 'loss/train': 1.9905145168304443}
-03/04/2022 00:55:45 - INFO - codeparrot_training - Step 9766: {'lr': 0.0004966107985956598, 'samples': 5000704, 'steps': 9766, 'loss/train': 2.2625930309295654}
-03/04/2022 00:55:46 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/04/2022 00:55:50 - INFO - codeparrot_training - Step 9767: {'lr': 0.0004966099276869534, 'samples': 5001216, 'steps': 9767, 'loss/train': 2.0338761806488037}
-03/04/2022 00:55:53 - INFO - codeparrot_training - Step 9768: {'lr': 0.0004966090566671283, 'samples': 5001728, 'steps': 9768, 'loss/train': 2.1703922748565674}
-03/04/2022 00:55:54 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/04/2022 00:55:59 - INFO - codeparrot_training - Step 9769: {'lr': 0.000496608185536185, 'samples': 5002240, 'steps': 9769, 'loss/train': 1.9879202842712402}
-03/04/2022 00:56:02 - INFO - codeparrot_training - Step 9770: {'lr': 0.0004966073142941239, 'samples': 5002752, 'steps': 9770, 'loss/train': 1.8792105913162231}
-03/04/2022 00:56:03 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/04/2022 00:56:07 - INFO - codeparrot_training - Step 9771: {'lr': 0.0004966064429409452, 'samples': 5003264, 'steps': 9771, 'loss/train': 2.2431507110595703}
-03/04/2022 00:56:10 - INFO - codeparrot_training - Step 9772: {'lr': 0.0004966055714766496, 'samples': 5003776, 'steps': 9772, 'loss/train': 2.3215181827545166}
-03/04/2022 00:56:11 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/04/2022 00:56:15 - INFO - codeparrot_training - Step 9773: {'lr': 0.0004966046999012373, 'samples': 5004288, 'steps': 9773, 'loss/train': 0.9315041899681091}
-03/04/2022 00:56:18 - INFO - codeparrot_training - Step 9774: {'lr': 0.0004966038282147087, 'samples': 5004800, 'steps': 9774, 'loss/train': 1.7906105518341064}
-03/04/2022 00:56:19 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/04/2022 00:56:24 - INFO - codeparrot_training - Step 9775: {'lr': 0.0004966029564170643, 'samples': 5005312, 'steps': 9775, 'loss/train': 1.548601508140564}
-03/04/2022 00:56:27 - INFO - codeparrot_training - Step 9776: {'lr': 0.0004966020845083044, 'samples': 5005824, 'steps': 9776, 'loss/train': 2.1807124614715576}
-03/04/2022 00:56:28 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/04/2022 00:56:32 - INFO - codeparrot_training - Step 9777: {'lr': 0.0004966012124884292, 'samples': 5006336, 'steps': 9777, 'loss/train': 2.179013252258301}
-03/04/2022 00:56:35 - INFO - codeparrot_training - Step 9778: {'lr': 0.0004966003403574395, 'samples': 5006848, 'steps': 9778, 'loss/train': 2.518173933029175}
-03/04/2022 00:56:36 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 00:56:41 - INFO - codeparrot_training - Step 9779: {'lr': 0.0004965994681153355, 'samples': 5007360, 'steps': 9779, 'loss/train': 1.8613401651382446}
-03/04/2022 00:56:44 - INFO - codeparrot_training - Step 9780: {'lr': 0.0004965985957621175, 'samples': 5007872, 'steps': 9780, 'loss/train': 1.585761308670044}
-03/04/2022 00:56:44 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/04/2022 00:56:49 - INFO - codeparrot_training - Step 9781: {'lr': 0.0004965977232977861, 'samples': 5008384, 'steps': 9781, 'loss/train': 1.4326900243759155}
-03/04/2022 00:56:52 - INFO - codeparrot_training - Step 9782: {'lr': 0.0004965968507223414, 'samples': 5008896, 'steps': 9782, 'loss/train': 1.2286152839660645}
-03/04/2022 00:56:53 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/04/2022 00:56:57 - INFO - codeparrot_training - Step 9783: {'lr': 0.000496595978035784, 'samples': 5009408, 'steps': 9783, 'loss/train': 2.074004650115967}
-03/04/2022 00:57:00 - INFO - codeparrot_training - Step 9784: {'lr': 0.0004965951052381144, 'samples': 5009920, 'steps': 9784, 'loss/train': 2.0841004848480225}
-03/04/2022 00:57:01 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/04/2022 00:57:06 - INFO - codeparrot_training - Step 9785: {'lr': 0.0004965942323293328, 'samples': 5010432, 'steps': 9785, 'loss/train': 2.0685346126556396}
-03/04/2022 00:57:09 - INFO - codeparrot_training - Step 9786: {'lr': 0.0004965933593094395, 'samples': 5010944, 'steps': 9786, 'loss/train': 0.31235867738723755}
-03/04/2022 00:57:09 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/04/2022 00:57:14 - INFO - codeparrot_training - Step 9787: {'lr': 0.0004965924861784352, 'samples': 5011456, 'steps': 9787, 'loss/train': 1.508164882659912}
-03/04/2022 00:57:17 - INFO - codeparrot_training - Step 9788: {'lr': 0.0004965916129363201, 'samples': 5011968, 'steps': 9788, 'loss/train': 2.419098138809204}
-03/04/2022 00:57:18 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 00:57:23 - INFO - codeparrot_training - Step 9789: {'lr': 0.0004965907395830945, 'samples': 5012480, 'steps': 9789, 'loss/train': 2.2198429107666016}
-03/04/2022 00:57:26 - INFO - codeparrot_training - Step 9790: {'lr': 0.000496589866118759, 'samples': 5012992, 'steps': 9790, 'loss/train': 2.093820333480835}
-03/04/2022 00:57:26 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/04/2022 00:57:31 - INFO - codeparrot_training - Step 9791: {'lr': 0.000496588992543314, 'samples': 5013504, 'steps': 9791, 'loss/train': 1.6372634172439575}
-03/04/2022 00:57:34 - INFO - codeparrot_training - Step 9792: {'lr': 0.0004965881188567597, 'samples': 5014016, 'steps': 9792, 'loss/train': 2.712958335876465}
-03/04/2022 00:57:35 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/04/2022 00:57:40 - INFO - codeparrot_training - Step 9793: {'lr': 0.0004965872450590965, 'samples': 5014528, 'steps': 9793, 'loss/train': 2.179353713989258}
-03/04/2022 00:57:43 - INFO - codeparrot_training - Step 9794: {'lr': 0.0004965863711503251, 'samples': 5015040, 'steps': 9794, 'loss/train': 1.5191844701766968}
-03/04/2022 00:57:43 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/04/2022 00:57:48 - INFO - codeparrot_training - Step 9795: {'lr': 0.0004965854971304457, 'samples': 5015552, 'steps': 9795, 'loss/train': 2.022156238555908}
-03/04/2022 00:57:51 - INFO - codeparrot_training - Step 9796: {'lr': 0.0004965846229994586, 'samples': 5016064, 'steps': 9796, 'loss/train': 1.4898881912231445}
-03/04/2022 00:57:51 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 00:57:56 - INFO - codeparrot_training - Step 9797: {'lr': 0.0004965837487573641, 'samples': 5016576, 'steps': 9797, 'loss/train': 1.6645845174789429}
-03/04/2022 00:58:00 - INFO - codeparrot_training - Step 9798: {'lr': 0.000496582874404163, 'samples': 5017088, 'steps': 9798, 'loss/train': 3.0579349994659424}
-03/04/2022 00:58:00 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 00:58:05 - INFO - codeparrot_training - Step 9799: {'lr': 0.0004965819999398554, 'samples': 5017600, 'steps': 9799, 'loss/train': 1.5816550254821777}
-03/04/2022 00:58:08 - INFO - codeparrot_training - Step 9800: {'lr': 0.0004965811253644418, 'samples': 5018112, 'steps': 9800, 'loss/train': 2.212721347808838}
-03/04/2022 00:58:09 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/04/2022 00:58:13 - INFO - codeparrot_training - Step 9801: {'lr': 0.0004965802506779225, 'samples': 5018624, 'steps': 9801, 'loss/train': 1.672013282775879}
-03/04/2022 00:58:16 - INFO - codeparrot_training - Step 9802: {'lr': 0.0004965793758802978, 'samples': 5019136, 'steps': 9802, 'loss/train': 2.238560199737549}
-03/04/2022 00:58:17 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 00:58:22 - INFO - codeparrot_training - Step 9803: {'lr': 0.0004965785009715684, 'samples': 5019648, 'steps': 9803, 'loss/train': 1.6156691312789917}
-03/04/2022 00:58:25 - INFO - codeparrot_training - Step 9804: {'lr': 0.0004965776259517345, 'samples': 5020160, 'steps': 9804, 'loss/train': 3.0978496074676514}
-03/04/2022 00:58:25 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 00:58:30 - INFO - codeparrot_training - Step 9805: {'lr': 0.0004965767508207966, 'samples': 5020672, 'steps': 9805, 'loss/train': 1.9526034593582153}
-03/04/2022 00:58:33 - INFO - codeparrot_training - Step 9806: {'lr': 0.000496575875578755, 'samples': 5021184, 'steps': 9806, 'loss/train': 1.6606930494308472}
-03/04/2022 00:58:33 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 00:58:38 - INFO - codeparrot_training - Step 9807: {'lr': 0.00049657500022561, 'samples': 5021696, 'steps': 9807, 'loss/train': 1.9442684650421143}
-03/04/2022 00:58:42 - INFO - codeparrot_training - Step 9808: {'lr': 0.0004965741247613622, 'samples': 5022208, 'steps': 9808, 'loss/train': 0.7763559818267822}
-03/04/2022 00:58:42 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/04/2022 00:58:47 - INFO - codeparrot_training - Step 9809: {'lr': 0.0004965732491860119, 'samples': 5022720, 'steps': 9809, 'loss/train': 2.2803761959075928}
-03/04/2022 00:58:50 - INFO - codeparrot_training - Step 9810: {'lr': 0.0004965723734995594, 'samples': 5023232, 'steps': 9810, 'loss/train': 1.7107775211334229}
-03/04/2022 00:58:50 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/04/2022 00:58:55 - INFO - codeparrot_training - Step 9811: {'lr': 0.0004965714977020053, 'samples': 5023744, 'steps': 9811, 'loss/train': 1.8541780710220337}
-03/04/2022 00:58:58 - INFO - codeparrot_training - Step 9812: {'lr': 0.0004965706217933499, 'samples': 5024256, 'steps': 9812, 'loss/train': 1.7790476083755493}
-03/04/2022 00:58:58 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 00:59:04 - INFO - codeparrot_training - Step 9813: {'lr': 0.0004965697457735936, 'samples': 5024768, 'steps': 9813, 'loss/train': 2.0051631927490234}
-03/04/2022 00:59:07 - INFO - codeparrot_training - Step 9814: {'lr': 0.0004965688696427366, 'samples': 5025280, 'steps': 9814, 'loss/train': 2.1995418071746826}
-03/04/2022 00:59:07 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/04/2022 00:59:12 - INFO - codeparrot_training - Step 9815: {'lr': 0.0004965679934007797, 'samples': 5025792, 'steps': 9815, 'loss/train': 3.134788751602173}
-03/04/2022 00:59:15 - INFO - codeparrot_training - Step 9816: {'lr': 0.0004965671170477229, 'samples': 5026304, 'steps': 9816, 'loss/train': 2.14760422706604}
-03/04/2022 00:59:15 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/04/2022 00:59:21 - INFO - codeparrot_training - Step 9817: {'lr': 0.0004965662405835668, 'samples': 5026816, 'steps': 9817, 'loss/train': 1.940858006477356}
-03/04/2022 00:59:24 - INFO - codeparrot_training - Step 9818: {'lr': 0.0004965653640083118, 'samples': 5027328, 'steps': 9818, 'loss/train': 1.5848132371902466}
-03/04/2022 00:59:24 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/04/2022 00:59:30 - INFO - codeparrot_training - Step 9819: {'lr': 0.0004965644873219583, 'samples': 5027840, 'steps': 9819, 'loss/train': 2.4746086597442627}
-03/04/2022 00:59:33 - INFO - codeparrot_training - Step 9820: {'lr': 0.0004965636105245066, 'samples': 5028352, 'steps': 9820, 'loss/train': 1.936943531036377}
-03/04/2022 00:59:33 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 00:59:38 - INFO - codeparrot_training - Step 9821: {'lr': 0.000496562733615957, 'samples': 5028864, 'steps': 9821, 'loss/train': 0.8381040692329407}
-03/04/2022 00:59:41 - INFO - codeparrot_training - Step 9822: {'lr': 0.0004965618565963102, 'samples': 5029376, 'steps': 9822, 'loss/train': 1.9791618585586548}
-03/04/2022 00:59:42 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 00:59:47 - INFO - codeparrot_training - Step 9823: {'lr': 0.0004965609794655664, 'samples': 5029888, 'steps': 9823, 'loss/train': 1.0048564672470093}
-03/04/2022 00:59:50 - INFO - codeparrot_training - Step 9824: {'lr': 0.0004965601022237261, 'samples': 5030400, 'steps': 9824, 'loss/train': 2.201611042022705}
-03/04/2022 00:59:51 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/04/2022 00:59:55 - INFO - codeparrot_training - Step 9825: {'lr': 0.0004965592248707895, 'samples': 5030912, 'steps': 9825, 'loss/train': 2.5664620399475098}
-03/04/2022 00:59:58 - INFO - codeparrot_training - Step 9826: {'lr': 0.0004965583474067571, 'samples': 5031424, 'steps': 9826, 'loss/train': 2.426342248916626}
-03/04/2022 00:59:59 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 01:00:04 - INFO - codeparrot_training - Step 9827: {'lr': 0.0004965574698316294, 'samples': 5031936, 'steps': 9827, 'loss/train': 1.9686388969421387}
-03/04/2022 01:00:07 - INFO - codeparrot_training - Step 9828: {'lr': 0.0004965565921454067, 'samples': 5032448, 'steps': 9828, 'loss/train': 1.6906119585037231}
-03/04/2022 01:00:07 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/04/2022 01:00:12 - INFO - codeparrot_training - Step 9829: {'lr': 0.0004965557143480893, 'samples': 5032960, 'steps': 9829, 'loss/train': 1.9653816223144531}
-03/04/2022 01:00:15 - INFO - codeparrot_training - Step 9830: {'lr': 0.0004965548364396779, 'samples': 5033472, 'steps': 9830, 'loss/train': 2.004708766937256}
-03/04/2022 01:00:15 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/04/2022 01:00:20 - INFO - codeparrot_training - Step 9831: {'lr': 0.0004965539584201725, 'samples': 5033984, 'steps': 9831, 'loss/train': 2.2701356410980225}
-03/04/2022 01:00:23 - INFO - codeparrot_training - Step 9832: {'lr': 0.0004965530802895738, 'samples': 5034496, 'steps': 9832, 'loss/train': 2.6190950870513916}
-03/04/2022 01:00:24 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/04/2022 01:00:29 - INFO - codeparrot_training - Step 9833: {'lr': 0.000496552202047882, 'samples': 5035008, 'steps': 9833, 'loss/train': 2.466892719268799}
-03/04/2022 01:00:32 - INFO - codeparrot_training - Step 9834: {'lr': 0.0004965513236950977, 'samples': 5035520, 'steps': 9834, 'loss/train': 2.3707668781280518}
-03/04/2022 01:00:32 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 01:00:38 - INFO - codeparrot_training - Step 9835: {'lr': 0.0004965504452312211, 'samples': 5036032, 'steps': 9835, 'loss/train': 1.9158480167388916}
-03/04/2022 01:00:41 - INFO - codeparrot_training - Step 9836: {'lr': 0.0004965495666562527, 'samples': 5036544, 'steps': 9836, 'loss/train': 1.7678165435791016}
-03/04/2022 01:00:42 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/04/2022 01:00:46 - INFO - codeparrot_training - Step 9837: {'lr': 0.0004965486879701928, 'samples': 5037056, 'steps': 9837, 'loss/train': 2.141289234161377}
-03/04/2022 01:00:49 - INFO - codeparrot_training - Step 9838: {'lr': 0.000496547809173042, 'samples': 5037568, 'steps': 9838, 'loss/train': 1.810383677482605}
-03/04/2022 01:00:50 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/04/2022 01:00:55 - INFO - codeparrot_training - Step 9839: {'lr': 0.0004965469302648005, 'samples': 5038080, 'steps': 9839, 'loss/train': 2.3254547119140625}
-03/04/2022 01:00:58 - INFO - codeparrot_training - Step 9840: {'lr': 0.0004965460512454688, 'samples': 5038592, 'steps': 9840, 'loss/train': 2.835005044937134}
-03/04/2022 01:00:59 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 01:01:03 - INFO - codeparrot_training - Step 9841: {'lr': 0.0004965451721150471, 'samples': 5039104, 'steps': 9841, 'loss/train': 1.101873517036438}
-03/04/2022 01:01:06 - INFO - codeparrot_training - Step 9842: {'lr': 0.0004965442928735361, 'samples': 5039616, 'steps': 9842, 'loss/train': 1.9083094596862793}
-03/04/2022 01:01:08 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/04/2022 01:01:12 - INFO - codeparrot_training - Step 9843: {'lr': 0.000496543413520936, 'samples': 5040128, 'steps': 9843, 'loss/train': 2.0625627040863037}
-03/04/2022 01:01:15 - INFO - codeparrot_training - Step 9844: {'lr': 0.0004965425340572472, 'samples': 5040640, 'steps': 9844, 'loss/train': 2.32600998878479}
-03/04/2022 01:01:16 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 01:01:20 - INFO - codeparrot_training - Step 9845: {'lr': 0.0004965416544824703, 'samples': 5041152, 'steps': 9845, 'loss/train': 0.8871047496795654}
-03/04/2022 01:01:23 - INFO - codeparrot_training - Step 9846: {'lr': 0.0004965407747966053, 'samples': 5041664, 'steps': 9846, 'loss/train': 1.7204105854034424}
-03/04/2022 01:01:25 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/04/2022 01:01:28 - INFO - codeparrot_training - Step 9847: {'lr': 0.000496539894999653, 'samples': 5042176, 'steps': 9847, 'loss/train': 2.48307728767395}
-03/04/2022 01:01:32 - INFO - codeparrot_training - Step 9848: {'lr': 0.0004965390150916136, 'samples': 5042688, 'steps': 9848, 'loss/train': 1.530869722366333}
-03/04/2022 01:01:33 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/04/2022 01:01:37 - INFO - codeparrot_training - Step 9849: {'lr': 0.0004965381350724874, 'samples': 5043200, 'steps': 9849, 'loss/train': 2.4296414852142334}
-03/04/2022 01:01:40 - INFO - codeparrot_training - Step 9850: {'lr': 0.000496537254942275, 'samples': 5043712, 'steps': 9850, 'loss/train': 1.6431478261947632}
-03/04/2022 01:01:42 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/04/2022 01:01:45 - INFO - codeparrot_training - Step 9851: {'lr': 0.0004965363747009767, 'samples': 5044224, 'steps': 9851, 'loss/train': 2.045677661895752}
-03/04/2022 01:01:49 - INFO - codeparrot_training - Step 9852: {'lr': 0.000496535494348593, 'samples': 5044736, 'steps': 9852, 'loss/train': 0.6411229372024536}
-03/04/2022 01:01:50 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/04/2022 01:01:54 - INFO - codeparrot_training - Step 9853: {'lr': 0.0004965346138851241, 'samples': 5045248, 'steps': 9853, 'loss/train': 1.997883677482605}
-03/04/2022 01:01:57 - INFO - codeparrot_training - Step 9854: {'lr': 0.0004965337333105706, 'samples': 5045760, 'steps': 9854, 'loss/train': 1.1622333526611328}
-03/04/2022 01:01:58 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 01:02:02 - INFO - codeparrot_training - Step 9855: {'lr': 0.0004965328526249328, 'samples': 5046272, 'steps': 9855, 'loss/train': 0.2546631991863251}
-03/04/2022 01:02:06 - INFO - codeparrot_training - Step 9856: {'lr': 0.000496531971828211, 'samples': 5046784, 'steps': 9856, 'loss/train': 2.2985119819641113}
-03/04/2022 01:02:07 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/04/2022 01:02:11 - INFO - codeparrot_training - Step 9857: {'lr': 0.0004965310909204058, 'samples': 5047296, 'steps': 9857, 'loss/train': 2.2152764797210693}
-03/04/2022 01:02:14 - INFO - codeparrot_training - Step 9858: {'lr': 0.0004965302099015175, 'samples': 5047808, 'steps': 9858, 'loss/train': 1.4783189296722412}
-03/04/2022 01:02:15 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/04/2022 01:02:19 - INFO - codeparrot_training - Step 9859: {'lr': 0.0004965293287715464, 'samples': 5048320, 'steps': 9859, 'loss/train': 2.2579171657562256}
-03/04/2022 01:02:22 - INFO - codeparrot_training - Step 9860: {'lr': 0.0004965284475304931, 'samples': 5048832, 'steps': 9860, 'loss/train': 2.1098239421844482}
-03/04/2022 01:02:24 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/04/2022 01:02:28 - INFO - codeparrot_training - Step 9861: {'lr': 0.0004965275661783579, 'samples': 5049344, 'steps': 9861, 'loss/train': 1.7854526042938232}
-03/04/2022 01:02:31 - INFO - codeparrot_training - Step 9862: {'lr': 0.0004965266847151411, 'samples': 5049856, 'steps': 9862, 'loss/train': 1.9357014894485474}
-03/04/2022 01:02:32 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 01:02:36 - INFO - codeparrot_training - Step 9863: {'lr': 0.0004965258031408432, 'samples': 5050368, 'steps': 9863, 'loss/train': 2.294837474822998}
-03/04/2022 01:02:39 - INFO - codeparrot_training - Step 9864: {'lr': 0.0004965249214554645, 'samples': 5050880, 'steps': 9864, 'loss/train': 2.355905055999756}
-03/04/2022 01:02:41 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/04/2022 01:02:45 - INFO - codeparrot_training - Step 9865: {'lr': 0.0004965240396590055, 'samples': 5051392, 'steps': 9865, 'loss/train': 2.0358128547668457}
-03/04/2022 01:02:48 - INFO - codeparrot_training - Step 9866: {'lr': 0.0004965231577514666, 'samples': 5051904, 'steps': 9866, 'loss/train': 1.9688925743103027}
-03/04/2022 01:02:50 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/04/2022 01:02:53 - INFO - codeparrot_training - Step 9867: {'lr': 0.0004965222757328482, 'samples': 5052416, 'steps': 9867, 'loss/train': 2.2432453632354736}
-03/04/2022 01:02:57 - INFO - codeparrot_training - Step 9868: {'lr': 0.0004965213936031507, 'samples': 5052928, 'steps': 9868, 'loss/train': 2.2730493545532227}
-03/04/2022 01:02:59 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/04/2022 01:03:02 - INFO - codeparrot_training - Step 9869: {'lr': 0.0004965205113623744, 'samples': 5053440, 'steps': 9869, 'loss/train': 2.252506971359253}
-03/04/2022 01:03:05 - INFO - codeparrot_training - Step 9870: {'lr': 0.0004965196290105197, 'samples': 5053952, 'steps': 9870, 'loss/train': 2.7616405487060547}
-03/04/2022 01:03:07 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/04/2022 01:03:10 - INFO - codeparrot_training - Step 9871: {'lr': 0.0004965187465475873, 'samples': 5054464, 'steps': 9871, 'loss/train': 2.3302433490753174}
-03/04/2022 01:03:14 - INFO - codeparrot_training - Step 9872: {'lr': 0.0004965178639735772, 'samples': 5054976, 'steps': 9872, 'loss/train': 0.36212822794914246}
-03/04/2022 01:03:15 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/04/2022 01:03:19 - INFO - codeparrot_training - Step 9873: {'lr': 0.0004965169812884898, 'samples': 5055488, 'steps': 9873, 'loss/train': 1.995645523071289}
-03/04/2022 01:03:22 - INFO - codeparrot_training - Step 9874: {'lr': 0.0004965160984923259, 'samples': 5056000, 'steps': 9874, 'loss/train': 2.354241132736206}
-03/04/2022 01:03:24 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 01:03:28 - INFO - codeparrot_training - Step 9875: {'lr': 0.0004965152155850855, 'samples': 5056512, 'steps': 9875, 'loss/train': 0.17354834079742432}
-03/04/2022 01:03:31 - INFO - codeparrot_training - Step 9876: {'lr': 0.0004965143325667692, 'samples': 5057024, 'steps': 9876, 'loss/train': 2.026106119155884}
-03/04/2022 01:03:34 - INFO - codeparrot_training - Step 9877: {'lr': 0.0004965134494373773, 'samples': 5057536, 'steps': 9877, 'loss/train': 1.7016199827194214}
-03/04/2022 01:03:34 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/04/2022 01:03:39 - INFO - codeparrot_training - Step 9878: {'lr': 0.0004965125661969103, 'samples': 5058048, 'steps': 9878, 'loss/train': 1.6046018600463867}
-03/04/2022 01:03:42 - INFO - codeparrot_training - Step 9879: {'lr': 0.0004965116828453685, 'samples': 5058560, 'steps': 9879, 'loss/train': 2.37345027923584}
-03/04/2022 01:03:42 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/04/2022 01:03:48 - INFO - codeparrot_training - Step 9880: {'lr': 0.0004965107993827524, 'samples': 5059072, 'steps': 9880, 'loss/train': 2.4400362968444824}
-03/04/2022 01:03:51 - INFO - codeparrot_training - Step 9881: {'lr': 0.0004965099158090624, 'samples': 5059584, 'steps': 9881, 'loss/train': 2.2184786796569824}
-03/04/2022 01:03:51 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 01:03:56 - INFO - codeparrot_training - Step 9882: {'lr': 0.0004965090321242987, 'samples': 5060096, 'steps': 9882, 'loss/train': 2.0129549503326416}
-03/04/2022 01:03:59 - INFO - codeparrot_training - Step 9883: {'lr': 0.0004965081483284618, 'samples': 5060608, 'steps': 9883, 'loss/train': 2.280752420425415}
-03/04/2022 01:03:59 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/04/2022 01:04:04 - INFO - codeparrot_training - Step 9884: {'lr': 0.0004965072644215522, 'samples': 5061120, 'steps': 9884, 'loss/train': 2.193077325820923}
-03/04/2022 01:04:08 - INFO - codeparrot_training - Step 9885: {'lr': 0.0004965063804035703, 'samples': 5061632, 'steps': 9885, 'loss/train': 1.4708805084228516}
-03/04/2022 01:04:08 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/04/2022 01:04:13 - INFO - codeparrot_training - Step 9886: {'lr': 0.0004965054962745163, 'samples': 5062144, 'steps': 9886, 'loss/train': 1.9063116312026978}
-03/04/2022 01:04:16 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/04/2022 01:04:18 - INFO - codeparrot_training - Step 9887: {'lr': 0.0004965046120343908, 'samples': 5062656, 'steps': 9887, 'loss/train': 2.097261667251587}
-03/04/2022 01:04:21 - INFO - codeparrot_training - Step 9888: {'lr': 0.0004965037276831942, 'samples': 5063168, 'steps': 9888, 'loss/train': 1.574524998664856}
-03/04/2022 01:04:24 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/04/2022 01:04:27 - INFO - codeparrot_training - Step 9889: {'lr': 0.0004965028432209267, 'samples': 5063680, 'steps': 9889, 'loss/train': 1.9116672277450562}
-03/04/2022 01:04:30 - INFO - codeparrot_training - Step 9890: {'lr': 0.0004965019586475888, 'samples': 5064192, 'steps': 9890, 'loss/train': 1.7044099569320679}
-03/04/2022 01:04:33 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/04/2022 01:04:35 - INFO - codeparrot_training - Step 9891: {'lr': 0.000496501073963181, 'samples': 5064704, 'steps': 9891, 'loss/train': 3.0048296451568604}
-03/04/2022 01:04:38 - INFO - codeparrot_training - Step 9892: {'lr': 0.0004965001891677037, 'samples': 5065216, 'steps': 9892, 'loss/train': 1.8783395290374756}
-03/04/2022 01:04:41 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 01:04:43 - INFO - codeparrot_training - Step 9893: {'lr': 0.000496499304261157, 'samples': 5065728, 'steps': 9893, 'loss/train': 1.3737525939941406}
-03/04/2022 01:04:47 - INFO - codeparrot_training - Step 9894: {'lr': 0.0004964984192435417, 'samples': 5066240, 'steps': 9894, 'loss/train': 1.9996510744094849}
-03/04/2022 01:04:49 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 01:04:52 - INFO - codeparrot_training - Step 9895: {'lr': 0.000496497534114858, 'samples': 5066752, 'steps': 9895, 'loss/train': 2.471384286880493}
-03/04/2022 01:04:55 - INFO - codeparrot_training - Step 9896: {'lr': 0.0004964966488751062, 'samples': 5067264, 'steps': 9896, 'loss/train': 2.7210819721221924}
-03/04/2022 01:04:58 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/04/2022 01:05:00 - INFO - codeparrot_training - Step 9897: {'lr': 0.000496495763524287, 'samples': 5067776, 'steps': 9897, 'loss/train': 2.639136552810669}
-03/04/2022 01:05:03 - INFO - codeparrot_training - Step 9898: {'lr': 0.0004964948780624005, 'samples': 5068288, 'steps': 9898, 'loss/train': 1.9088807106018066}
-03/04/2022 01:05:06 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 01:05:09 - INFO - codeparrot_training - Step 9899: {'lr': 0.0004964939924894472, 'samples': 5068800, 'steps': 9899, 'loss/train': 2.209688901901245}
-03/04/2022 01:05:12 - INFO - codeparrot_training - Step 9900: {'lr': 0.0004964931068054274, 'samples': 5069312, 'steps': 9900, 'loss/train': 0.8381728529930115}
-03/04/2022 01:05:14 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 01:05:17 - INFO - codeparrot_training - Step 9901: {'lr': 0.0004964922210103418, 'samples': 5069824, 'steps': 9901, 'loss/train': 2.254610061645508}
-03/04/2022 01:05:20 - INFO - codeparrot_training - Step 9902: {'lr': 0.0004964913351041905, 'samples': 5070336, 'steps': 9902, 'loss/train': 1.9585366249084473}
-03/04/2022 01:05:23 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/04/2022 01:05:25 - INFO - codeparrot_training - Step 9903: {'lr': 0.000496490449086974, 'samples': 5070848, 'steps': 9903, 'loss/train': 2.1285948753356934}
-03/04/2022 01:05:29 - INFO - codeparrot_training - Step 9904: {'lr': 0.0004964895629586928, 'samples': 5071360, 'steps': 9904, 'loss/train': 2.6710705757141113}
-03/04/2022 01:05:31 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/04/2022 01:05:34 - INFO - codeparrot_training - Step 9905: {'lr': 0.0004964886767193471, 'samples': 5071872, 'steps': 9905, 'loss/train': 1.877553939819336}
-03/04/2022 01:05:37 - INFO - codeparrot_training - Step 9906: {'lr': 0.0004964877903689375, 'samples': 5072384, 'steps': 9906, 'loss/train': 1.7125228643417358}
-03/04/2022 01:05:39 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/04/2022 01:05:43 - INFO - codeparrot_training - Step 9907: {'lr': 0.0004964869039074643, 'samples': 5072896, 'steps': 9907, 'loss/train': 1.2054733037948608}
-03/04/2022 01:05:46 - INFO - codeparrot_training - Step 9908: {'lr': 0.000496486017334928, 'samples': 5073408, 'steps': 9908, 'loss/train': 1.7200857400894165}
-03/04/2022 01:05:49 - INFO - codeparrot_training - Step 9909: {'lr': 0.0004964851306513287, 'samples': 5073920, 'steps': 9909, 'loss/train': 1.9994122982025146}
-03/04/2022 01:05:49 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 01:05:55 - INFO - codeparrot_training - Step 9910: {'lr': 0.0004964842438566671, 'samples': 5074432, 'steps': 9910, 'loss/train': 1.9451518058776855}
-03/04/2022 01:05:58 - INFO - codeparrot_training - Step 9911: {'lr': 0.0004964833569509434, 'samples': 5074944, 'steps': 9911, 'loss/train': 0.9880871176719666}
-03/04/2022 01:05:58 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 01:06:03 - INFO - codeparrot_training - Step 9912: {'lr': 0.0004964824699341582, 'samples': 5075456, 'steps': 9912, 'loss/train': 2.1186060905456543}
-03/04/2022 01:06:06 - INFO - codeparrot_training - Step 9913: {'lr': 0.0004964815828063118, 'samples': 5075968, 'steps': 9913, 'loss/train': 2.58925199508667}
-03/04/2022 01:06:06 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 01:06:11 - INFO - codeparrot_training - Step 9914: {'lr': 0.0004964806955674046, 'samples': 5076480, 'steps': 9914, 'loss/train': 2.267503261566162}
-03/04/2022 01:06:14 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/04/2022 01:06:17 - INFO - codeparrot_training - Step 9915: {'lr': 0.0004964798082174371, 'samples': 5076992, 'steps': 9915, 'loss/train': 1.9332432746887207}
-03/04/2022 01:06:20 - INFO - codeparrot_training - Step 9916: {'lr': 0.0004964789207564094, 'samples': 5077504, 'steps': 9916, 'loss/train': 1.8723968267440796}
-03/04/2022 01:06:23 - INFO - codeparrot_training - Step 9917: {'lr': 0.0004964780331843223, 'samples': 5078016, 'steps': 9917, 'loss/train': 0.9434875249862671}
-03/04/2022 01:06:23 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/04/2022 01:06:28 - INFO - codeparrot_training - Step 9918: {'lr': 0.0004964771455011758, 'samples': 5078528, 'steps': 9918, 'loss/train': 2.6616156101226807}
-03/04/2022 01:06:31 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 01:06:34 - INFO - codeparrot_training - Step 9919: {'lr': 0.0004964762577069707, 'samples': 5079040, 'steps': 9919, 'loss/train': 0.9996391534805298}
-03/04/2022 01:06:37 - INFO - codeparrot_training - Step 9920: {'lr': 0.0004964753698017071, 'samples': 5079552, 'steps': 9920, 'loss/train': 1.9432462453842163}
-03/04/2022 01:06:39 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/04/2022 01:06:42 - INFO - codeparrot_training - Step 9921: {'lr': 0.0004964744817853855, 'samples': 5080064, 'steps': 9921, 'loss/train': 2.0114808082580566}
-03/04/2022 01:06:45 - INFO - codeparrot_training - Step 9922: {'lr': 0.0004964735936580063, 'samples': 5080576, 'steps': 9922, 'loss/train': 2.1414833068847656}
-03/04/2022 01:06:49 - INFO - codeparrot_training - Step 9923: {'lr': 0.00049647270541957, 'samples': 5081088, 'steps': 9923, 'loss/train': 1.5720939636230469}
-03/04/2022 01:06:49 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/04/2022 01:06:54 - INFO - codeparrot_training - Step 9924: {'lr': 0.0004964718170700767, 'samples': 5081600, 'steps': 9924, 'loss/train': 2.1838934421539307}
-03/04/2022 01:06:58 - INFO - codeparrot_training - Step 9925: {'lr': 0.0004964709286095271, 'samples': 5082112, 'steps': 9925, 'loss/train': 2.510479211807251}
-03/04/2022 01:07:00 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/04/2022 01:07:03 - INFO - codeparrot_training - Step 9926: {'lr': 0.0004964700400379215, 'samples': 5082624, 'steps': 9926, 'loss/train': 2.6055216789245605}
-03/04/2022 01:07:06 - INFO - codeparrot_training - Step 9927: {'lr': 0.0004964691513552604, 'samples': 5083136, 'steps': 9927, 'loss/train': 2.1633386611938477}
-03/04/2022 01:07:08 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 01:07:11 - INFO - codeparrot_training - Step 9928: {'lr': 0.000496468262561544, 'samples': 5083648, 'steps': 9928, 'loss/train': 2.099353790283203}
-03/04/2022 01:07:14 - INFO - codeparrot_training - Step 9929: {'lr': 0.0004964673736567728, 'samples': 5084160, 'steps': 9929, 'loss/train': 3.1872010231018066}
-03/04/2022 01:07:17 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/04/2022 01:07:20 - INFO - codeparrot_training - Step 9930: {'lr': 0.0004964664846409473, 'samples': 5084672, 'steps': 9930, 'loss/train': 1.8783421516418457}
-03/04/2022 01:07:23 - INFO - codeparrot_training - Step 9931: {'lr': 0.0004964655955140677, 'samples': 5085184, 'steps': 9931, 'loss/train': 2.124354124069214}
-03/04/2022 01:07:25 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 01:07:28 - INFO - codeparrot_training - Step 9932: {'lr': 0.0004964647062761345, 'samples': 5085696, 'steps': 9932, 'loss/train': 1.627461314201355}
-03/04/2022 01:07:31 - INFO - codeparrot_training - Step 9933: {'lr': 0.0004964638169271482, 'samples': 5086208, 'steps': 9933, 'loss/train': 4.023478984832764}
-03/04/2022 01:07:33 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 01:07:37 - INFO - codeparrot_training - Step 9934: {'lr': 0.0004964629274671091, 'samples': 5086720, 'steps': 9934, 'loss/train': 1.8596861362457275}
-03/04/2022 01:07:40 - INFO - codeparrot_training - Step 9935: {'lr': 0.0004964620378960175, 'samples': 5087232, 'steps': 9935, 'loss/train': 1.9703986644744873}
-03/04/2022 01:07:42 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/04/2022 01:07:45 - INFO - codeparrot_training - Step 9936: {'lr': 0.000496461148213874, 'samples': 5087744, 'steps': 9936, 'loss/train': 1.9980274438858032}
-03/04/2022 01:07:48 - INFO - codeparrot_training - Step 9937: {'lr': 0.0004964602584206788, 'samples': 5088256, 'steps': 9937, 'loss/train': 2.374887704849243}
-03/04/2022 01:07:50 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/04/2022 01:07:54 - INFO - codeparrot_training - Step 9938: {'lr': 0.0004964593685164326, 'samples': 5088768, 'steps': 9938, 'loss/train': 1.9601705074310303}
-03/04/2022 01:07:57 - INFO - codeparrot_training - Step 9939: {'lr': 0.0004964584785011355, 'samples': 5089280, 'steps': 9939, 'loss/train': 2.4802534580230713}
-03/04/2022 01:07:58 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/04/2022 01:08:02 - INFO - codeparrot_training - Step 9940: {'lr': 0.000496457588374788, 'samples': 5089792, 'steps': 9940, 'loss/train': 1.152922511100769}
-03/04/2022 01:08:05 - INFO - codeparrot_training - Step 9941: {'lr': 0.0004964566981373905, 'samples': 5090304, 'steps': 9941, 'loss/train': 1.9862251281738281}
-03/04/2022 01:08:06 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 01:08:10 - INFO - codeparrot_training - Step 9942: {'lr': 0.0004964558077889435, 'samples': 5090816, 'steps': 9942, 'loss/train': 2.4304513931274414}
-03/04/2022 01:08:13 - INFO - codeparrot_training - Step 9943: {'lr': 0.0004964549173294472, 'samples': 5091328, 'steps': 9943, 'loss/train': 2.398019552230835}
-03/04/2022 01:08:15 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 01:08:19 - INFO - codeparrot_training - Step 9944: {'lr': 0.0004964540267589023, 'samples': 5091840, 'steps': 9944, 'loss/train': 2.664921522140503}
-03/04/2022 01:08:22 - INFO - codeparrot_training - Step 9945: {'lr': 0.0004964531360773088, 'samples': 5092352, 'steps': 9945, 'loss/train': 1.9628243446350098}
-03/04/2022 01:08:23 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/04/2022 01:08:27 - INFO - codeparrot_training - Step 9946: {'lr': 0.0004964522452846675, 'samples': 5092864, 'steps': 9946, 'loss/train': 1.4097998142242432}
-03/04/2022 01:08:30 - INFO - codeparrot_training - Step 9947: {'lr': 0.0004964513543809785, 'samples': 5093376, 'steps': 9947, 'loss/train': 1.8197489976882935}
-03/04/2022 01:08:31 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/04/2022 01:08:35 - INFO - codeparrot_training - Step 9948: {'lr': 0.0004964504633662424, 'samples': 5093888, 'steps': 9948, 'loss/train': 2.3827290534973145}
-03/04/2022 01:08:39 - INFO - codeparrot_training - Step 9949: {'lr': 0.0004964495722404595, 'samples': 5094400, 'steps': 9949, 'loss/train': 2.2148826122283936}
-03/04/2022 01:08:40 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/04/2022 01:08:44 - INFO - codeparrot_training - Step 9950: {'lr': 0.0004964486810036301, 'samples': 5094912, 'steps': 9950, 'loss/train': 2.290003538131714}
-03/04/2022 01:08:47 - INFO - codeparrot_training - Step 9951: {'lr': 0.000496447789655755, 'samples': 5095424, 'steps': 9951, 'loss/train': 1.2416306734085083}
-03/04/2022 01:08:48 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/04/2022 01:08:52 - INFO - codeparrot_training - Step 9952: {'lr': 0.0004964468981968341, 'samples': 5095936, 'steps': 9952, 'loss/train': 2.4451820850372314}
-03/04/2022 01:08:56 - INFO - codeparrot_training - Step 9953: {'lr': 0.0004964460066268681, 'samples': 5096448, 'steps': 9953, 'loss/train': 1.9909477233886719}
-03/04/2022 01:08:57 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/04/2022 01:09:01 - INFO - codeparrot_training - Step 9954: {'lr': 0.0004964451149458573, 'samples': 5096960, 'steps': 9954, 'loss/train': 2.6534407138824463}
-03/04/2022 01:09:04 - INFO - codeparrot_training - Step 9955: {'lr': 0.0004964442231538023, 'samples': 5097472, 'steps': 9955, 'loss/train': 2.493816375732422}
-03/04/2022 01:09:05 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 01:09:09 - INFO - codeparrot_training - Step 9956: {'lr': 0.000496443331250703, 'samples': 5097984, 'steps': 9956, 'loss/train': 2.721750020980835}
-03/04/2022 01:09:12 - INFO - codeparrot_training - Step 9957: {'lr': 0.0004964424392365604, 'samples': 5098496, 'steps': 9957, 'loss/train': 2.308534860610962}
-03/04/2022 01:09:14 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/04/2022 01:09:18 - INFO - codeparrot_training - Step 9958: {'lr': 0.0004964415471113747, 'samples': 5099008, 'steps': 9958, 'loss/train': 2.389284372329712}
-03/04/2022 01:09:21 - INFO - codeparrot_training - Step 9959: {'lr': 0.0004964406548751461, 'samples': 5099520, 'steps': 9959, 'loss/train': 1.4672110080718994}
-03/04/2022 01:09:22 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/04/2022 01:09:26 - INFO - codeparrot_training - Step 9960: {'lr': 0.0004964397625278751, 'samples': 5100032, 'steps': 9960, 'loss/train': 0.5506435632705688}
-03/04/2022 01:09:29 - INFO - codeparrot_training - Step 9961: {'lr': 0.0004964388700695623, 'samples': 5100544, 'steps': 9961, 'loss/train': 2.3670527935028076}
-03/04/2022 01:09:31 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 01:09:35 - INFO - codeparrot_training - Step 9962: {'lr': 0.0004964379775002078, 'samples': 5101056, 'steps': 9962, 'loss/train': 2.224139928817749}
-03/04/2022 01:09:38 - INFO - codeparrot_training - Step 9963: {'lr': 0.0004964370848198122, 'samples': 5101568, 'steps': 9963, 'loss/train': 2.511046886444092}
-03/04/2022 01:09:39 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 01:09:43 - INFO - codeparrot_training - Step 9964: {'lr': 0.0004964361920283759, 'samples': 5102080, 'steps': 9964, 'loss/train': 2.3923168182373047}
-03/04/2022 01:09:46 - INFO - codeparrot_training - Step 9965: {'lr': 0.0004964352991258992, 'samples': 5102592, 'steps': 9965, 'loss/train': 2.1878538131713867}
-03/04/2022 01:09:48 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 01:09:52 - INFO - codeparrot_training - Step 9966: {'lr': 0.0004964344061123826, 'samples': 5103104, 'steps': 9966, 'loss/train': 1.1337790489196777}
-03/04/2022 01:09:55 - INFO - codeparrot_training - Step 9967: {'lr': 0.0004964335129878264, 'samples': 5103616, 'steps': 9967, 'loss/train': 1.9141911268234253}
-03/04/2022 01:09:56 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 01:10:00 - INFO - codeparrot_training - Step 9968: {'lr': 0.0004964326197522311, 'samples': 5104128, 'steps': 9968, 'loss/train': 1.5790385007858276}
-03/04/2022 01:10:03 - INFO - codeparrot_training - Step 9969: {'lr': 0.0004964317264055971, 'samples': 5104640, 'steps': 9969, 'loss/train': 2.5033884048461914}
-03/04/2022 01:10:04 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 01:10:08 - INFO - codeparrot_training - Step 9970: {'lr': 0.0004964308329479247, 'samples': 5105152, 'steps': 9970, 'loss/train': 2.4281930923461914}
-03/04/2022 01:10:12 - INFO - codeparrot_training - Step 9971: {'lr': 0.0004964299393792143, 'samples': 5105664, 'steps': 9971, 'loss/train': 2.0501372814178467}
-03/04/2022 01:10:13 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/04/2022 01:10:17 - INFO - codeparrot_training - Step 9972: {'lr': 0.0004964290456994666, 'samples': 5106176, 'steps': 9972, 'loss/train': 2.4355180263519287}
-03/04/2022 01:10:20 - INFO - codeparrot_training - Step 9973: {'lr': 0.0004964281519086816, 'samples': 5106688, 'steps': 9973, 'loss/train': 1.9356586933135986}
-03/04/2022 01:10:22 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/04/2022 01:10:25 - INFO - codeparrot_training - Step 9974: {'lr': 0.0004964272580068599, 'samples': 5107200, 'steps': 9974, 'loss/train': 2.3336453437805176}
-03/04/2022 01:10:29 - INFO - codeparrot_training - Step 9975: {'lr': 0.0004964263639940018, 'samples': 5107712, 'steps': 9975, 'loss/train': 3.4474148750305176}
-03/04/2022 01:10:30 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/04/2022 01:10:34 - INFO - codeparrot_training - Step 9976: {'lr': 0.000496425469870108, 'samples': 5108224, 'steps': 9976, 'loss/train': 2.3510260581970215}
-03/04/2022 01:10:37 - INFO - codeparrot_training - Step 9977: {'lr': 0.0004964245756351786, 'samples': 5108736, 'steps': 9977, 'loss/train': 1.2664912939071655}
-03/04/2022 01:10:39 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/04/2022 01:10:42 - INFO - codeparrot_training - Step 9978: {'lr': 0.000496423681289214, 'samples': 5109248, 'steps': 9978, 'loss/train': 1.1809712648391724}
-03/04/2022 01:10:45 - INFO - codeparrot_training - Step 9979: {'lr': 0.0004964227868322148, 'samples': 5109760, 'steps': 9979, 'loss/train': 2.0207509994506836}
-03/04/2022 01:10:47 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/04/2022 01:10:51 - INFO - codeparrot_training - Step 9980: {'lr': 0.0004964218922641812, 'samples': 5110272, 'steps': 9980, 'loss/train': 1.691293716430664}
-03/04/2022 01:10:54 - INFO - codeparrot_training - Step 9981: {'lr': 0.0004964209975851137, 'samples': 5110784, 'steps': 9981, 'loss/train': 1.3812135457992554}
-03/04/2022 01:10:55 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 01:10:59 - INFO - codeparrot_training - Step 9982: {'lr': 0.0004964201027950129, 'samples': 5111296, 'steps': 9982, 'loss/train': 1.7478327751159668}
-03/04/2022 01:11:02 - INFO - codeparrot_training - Step 9983: {'lr': 0.0004964192078938788, 'samples': 5111808, 'steps': 9983, 'loss/train': 1.5581258535385132}
-03/04/2022 01:11:04 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 01:11:08 - INFO - codeparrot_training - Step 9984: {'lr': 0.0004964183128817121, 'samples': 5112320, 'steps': 9984, 'loss/train': 2.501147508621216}
-03/04/2022 01:11:11 - INFO - codeparrot_training - Step 9985: {'lr': 0.000496417417758513, 'samples': 5112832, 'steps': 9985, 'loss/train': 1.6870720386505127}
-03/04/2022 01:11:13 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/04/2022 01:11:16 - INFO - codeparrot_training - Step 9986: {'lr': 0.000496416522524282, 'samples': 5113344, 'steps': 9986, 'loss/train': 2.105055809020996}
-03/04/2022 01:11:19 - INFO - codeparrot_training - Step 9987: {'lr': 0.0004964156271790197, 'samples': 5113856, 'steps': 9987, 'loss/train': 2.321324110031128}
-03/04/2022 01:11:21 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 01:11:25 - INFO - codeparrot_training - Step 9988: {'lr': 0.0004964147317227262, 'samples': 5114368, 'steps': 9988, 'loss/train': 2.198530435562134}
-03/04/2022 01:11:28 - INFO - codeparrot_training - Step 9989: {'lr': 0.000496413836155402, 'samples': 5114880, 'steps': 9989, 'loss/train': 2.320115804672241}
-03/04/2022 01:11:29 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 01:11:33 - INFO - codeparrot_training - Step 9990: {'lr': 0.0004964129404770476, 'samples': 5115392, 'steps': 9990, 'loss/train': 1.4627163410186768}
-03/04/2022 01:11:36 - INFO - codeparrot_training - Step 9991: {'lr': 0.0004964120446876633, 'samples': 5115904, 'steps': 9991, 'loss/train': 1.03004789352417}
-03/04/2022 01:11:38 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 01:11:41 - INFO - codeparrot_training - Step 9992: {'lr': 0.0004964111487872495, 'samples': 5116416, 'steps': 9992, 'loss/train': 2.431847095489502}
-03/04/2022 01:11:45 - INFO - codeparrot_training - Step 9993: {'lr': 0.0004964102527758067, 'samples': 5116928, 'steps': 9993, 'loss/train': 1.9636104106903076}
-03/04/2022 01:11:46 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/04/2022 01:11:50 - INFO - codeparrot_training - Step 9994: {'lr': 0.0004964093566533352, 'samples': 5117440, 'steps': 9994, 'loss/train': 1.9263129234313965}
-03/04/2022 01:11:53 - INFO - codeparrot_training - Step 9995: {'lr': 0.0004964084604198354, 'samples': 5117952, 'steps': 9995, 'loss/train': 2.670535087585449}
-03/04/2022 01:11:55 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 01:11:58 - INFO - codeparrot_training - Step 9996: {'lr': 0.0004964075640753079, 'samples': 5118464, 'steps': 9996, 'loss/train': 1.4525158405303955}
-03/04/2022 01:12:02 - INFO - codeparrot_training - Step 9997: {'lr': 0.0004964066676197528, 'samples': 5118976, 'steps': 9997, 'loss/train': 1.5431400537490845}
-03/04/2022 01:12:04 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 01:12:07 - INFO - codeparrot_training - Step 9998: {'lr': 0.0004964057710531707, 'samples': 5119488, 'steps': 9998, 'loss/train': 1.9265028238296509}
-03/04/2022 01:12:10 - INFO - codeparrot_training - Step 9999: {'lr': 0.0004964048743755621, 'samples': 5120000, 'steps': 9999, 'loss/train': 1.569541573524475}
-03/04/2022 01:12:10 - INFO - codeparrot_training - Evaluating and saving model checkpoint
-03/04/2022 01:12:24 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
-03/04/2022 01:12:24 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
-03/04/2022 01:12:47 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/cm_code_clippy
-   5367894..ad512a7  glowing-puddle-3 -> glowing-puddle-3
-
-03/04/2022 01:12:50 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 01:12:53 - INFO - codeparrot_training - Step 10000: {'lr': 0.0004964039775869272, 'samples': 5120512, 'steps': 10000, 'loss/train': 2.7054004669189453}
-03/04/2022 01:12:56 - INFO - codeparrot_training - Step 10001: {'lr': 0.0004964030806872664, 'samples': 5121024, 'steps': 10001, 'loss/train': 2.386148452758789}
-03/04/2022 01:12:59 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/04/2022 01:13:02 - INFO - codeparrot_training - Step 10002: {'lr': 0.0004964021836765802, 'samples': 5121536, 'steps': 10002, 'loss/train': 2.3926291465759277}
-03/04/2022 01:13:05 - INFO - codeparrot_training - Step 10003: {'lr': 0.000496401286554869, 'samples': 5122048, 'steps': 10003, 'loss/train': 3.121417999267578}
-03/04/2022 01:13:07 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 01:13:10 - INFO - codeparrot_training - Step 10004: {'lr': 0.000496400389322133, 'samples': 5122560, 'steps': 10004, 'loss/train': 2.7392852306365967}
-03/04/2022 01:13:13 - INFO - codeparrot_training - Step 10005: {'lr': 0.000496399491978373, 'samples': 5123072, 'steps': 10005, 'loss/train': 1.6927242279052734}
-03/04/2022 01:13:15 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/04/2022 01:13:18 - INFO - codeparrot_training - Step 10006: {'lr': 0.0004963985945235891, 'samples': 5123584, 'steps': 10006, 'loss/train': 2.2901015281677246}
-03/04/2022 01:13:22 - INFO - codeparrot_training - Step 10007: {'lr': 0.0004963976969577819, 'samples': 5124096, 'steps': 10007, 'loss/train': 1.7426347732543945}
-03/04/2022 01:13:23 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/04/2022 01:13:27 - INFO - codeparrot_training - Step 10008: {'lr': 0.0004963967992809516, 'samples': 5124608, 'steps': 10008, 'loss/train': 2.1490797996520996}
-03/04/2022 01:13:30 - INFO - codeparrot_training - Step 10009: {'lr': 0.0004963959014930988, 'samples': 5125120, 'steps': 10009, 'loss/train': 2.471665143966675}
-03/04/2022 01:13:32 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/04/2022 01:13:35 - INFO - codeparrot_training - Step 10010: {'lr': 0.0004963950035942237, 'samples': 5125632, 'steps': 10010, 'loss/train': 2.3149590492248535}
-03/04/2022 01:13:39 - INFO - codeparrot_training - Step 10011: {'lr': 0.0004963941055843268, 'samples': 5126144, 'steps': 10011, 'loss/train': 1.8563871383666992}
-03/04/2022 01:13:41 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/04/2022 01:13:44 - INFO - codeparrot_training - Step 10012: {'lr': 0.0004963932074634087, 'samples': 5126656, 'steps': 10012, 'loss/train': 1.654968023300171}
-03/04/2022 01:13:47 - INFO - codeparrot_training - Step 10013: {'lr': 0.0004963923092314694, 'samples': 5127168, 'steps': 10013, 'loss/train': 1.8349374532699585}
-03/04/2022 01:13:49 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/04/2022 01:13:52 - INFO - codeparrot_training - Step 10014: {'lr': 0.0004963914108885097, 'samples': 5127680, 'steps': 10014, 'loss/train': 2.8493165969848633}
-03/04/2022 01:13:55 - INFO - codeparrot_training - Step 10015: {'lr': 0.0004963905124345297, 'samples': 5128192, 'steps': 10015, 'loss/train': 2.129498243331909}
-03/04/2022 01:13:57 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 01:14:01 - INFO - codeparrot_training - Step 10016: {'lr': 0.00049638961386953, 'samples': 5128704, 'steps': 10016, 'loss/train': 1.8765392303466797}
-03/04/2022 01:14:04 - INFO - codeparrot_training - Step 10017: {'lr': 0.000496388715193511, 'samples': 5129216, 'steps': 10017, 'loss/train': 1.8089972734451294}
-03/04/2022 01:14:06 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 01:14:09 - INFO - codeparrot_training - Step 10018: {'lr': 0.000496387816406473, 'samples': 5129728, 'steps': 10018, 'loss/train': 1.8908095359802246}
-03/04/2022 01:14:13 - INFO - codeparrot_training - Step 10019: {'lr': 0.0004963869175084164, 'samples': 5130240, 'steps': 10019, 'loss/train': 6.803772449493408}
-03/04/2022 01:14:16 - INFO - codeparrot_training - Step 10020: {'lr': 0.0004963860184993416, 'samples': 5130752, 'steps': 10020, 'loss/train': 2.5223305225372314}
-03/04/2022 01:14:16 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/04/2022 01:14:21 - INFO - codeparrot_training - Step 10021: {'lr': 0.0004963851193792492, 'samples': 5131264, 'steps': 10021, 'loss/train': 2.280441999435425}
-03/04/2022 01:14:24 - INFO - codeparrot_training - Step 10022: {'lr': 0.0004963842201481394, 'samples': 5131776, 'steps': 10022, 'loss/train': 1.5774993896484375}
-03/04/2022 01:14:24 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/04/2022 01:14:29 - INFO - codeparrot_training - Step 10023: {'lr': 0.0004963833208060128, 'samples': 5132288, 'steps': 10023, 'loss/train': 1.798959493637085}
-03/04/2022 01:14:32 - INFO - codeparrot_training - Step 10024: {'lr': 0.0004963824213528696, 'samples': 5132800, 'steps': 10024, 'loss/train': 1.2590854167938232}
-03/04/2022 01:14:32 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 01:14:38 - INFO - codeparrot_training - Step 10025: {'lr': 0.0004963815217887102, 'samples': 5133312, 'steps': 10025, 'loss/train': 1.5060218572616577}
-03/04/2022 01:14:41 - INFO - codeparrot_training - Step 10026: {'lr': 0.0004963806221135351, 'samples': 5133824, 'steps': 10026, 'loss/train': 1.5951515436172485}
-03/04/2022 01:14:41 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 01:14:46 - INFO - codeparrot_training - Step 10027: {'lr': 0.0004963797223273448, 'samples': 5134336, 'steps': 10027, 'loss/train': 1.8339555263519287}
-03/04/2022 01:14:50 - INFO - codeparrot_training - Step 10028: {'lr': 0.0004963788224301395, 'samples': 5134848, 'steps': 10028, 'loss/train': 1.6873542070388794}
-03/04/2022 01:14:50 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/04/2022 01:14:55 - INFO - codeparrot_training - Step 10029: {'lr': 0.0004963779224219197, 'samples': 5135360, 'steps': 10029, 'loss/train': 1.8056470155715942}
-03/04/2022 01:14:58 - INFO - codeparrot_training - Step 10030: {'lr': 0.0004963770223026858, 'samples': 5135872, 'steps': 10030, 'loss/train': 1.9166560173034668}
-03/04/2022 01:14:58 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/04/2022 01:15:03 - INFO - codeparrot_training - Step 10031: {'lr': 0.0004963761220724384, 'samples': 5136384, 'steps': 10031, 'loss/train': 2.3387153148651123}
-03/04/2022 01:15:07 - INFO - codeparrot_training - Step 10032: {'lr': 0.0004963752217311775, 'samples': 5136896, 'steps': 10032, 'loss/train': 2.5383927822113037}
-03/04/2022 01:15:07 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/04/2022 01:15:12 - INFO - codeparrot_training - Step 10033: {'lr': 0.0004963743212789038, 'samples': 5137408, 'steps': 10033, 'loss/train': 1.312104344367981}
-03/04/2022 01:15:15 - INFO - codeparrot_training - Step 10034: {'lr': 0.0004963734207156178, 'samples': 5137920, 'steps': 10034, 'loss/train': 1.535056471824646}
-03/04/2022 01:15:15 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/04/2022 01:15:20 - INFO - codeparrot_training - Step 10035: {'lr': 0.0004963725200413195, 'samples': 5138432, 'steps': 10035, 'loss/train': 1.9126865863800049}
-03/04/2022 01:15:23 - INFO - codeparrot_training - Step 10036: {'lr': 0.0004963716192560097, 'samples': 5138944, 'steps': 10036, 'loss/train': 0.7345311641693115}
-03/04/2022 01:15:23 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 01:15:29 - INFO - codeparrot_training - Step 10037: {'lr': 0.0004963707183596885, 'samples': 5139456, 'steps': 10037, 'loss/train': 0.20626306533813477}
-03/04/2022 01:15:32 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/04/2022 01:15:34 - INFO - codeparrot_training - Step 10038: {'lr': 0.0004963698173523566, 'samples': 5139968, 'steps': 10038, 'loss/train': 2.267681360244751}
-03/04/2022 01:15:37 - INFO - codeparrot_training - Step 10039: {'lr': 0.0004963689162340142, 'samples': 5140480, 'steps': 10039, 'loss/train': 2.0021586418151855}
-03/04/2022 01:15:40 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 01:15:43 - INFO - codeparrot_training - Step 10040: {'lr': 0.0004963680150046618, 'samples': 5140992, 'steps': 10040, 'loss/train': 2.3071045875549316}
-03/04/2022 01:15:46 - INFO - codeparrot_training - Step 10041: {'lr': 0.0004963671136642997, 'samples': 5141504, 'steps': 10041, 'loss/train': 1.4833779335021973}
-03/04/2022 01:15:48 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/04/2022 01:15:51 - INFO - codeparrot_training - Step 10042: {'lr': 0.0004963662122129284, 'samples': 5142016, 'steps': 10042, 'loss/train': 2.2766082286834717}
-03/04/2022 01:15:54 - INFO - codeparrot_training - Step 10043: {'lr': 0.0004963653106505483, 'samples': 5142528, 'steps': 10043, 'loss/train': 2.457775354385376}
-03/04/2022 01:15:57 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 01:15:59 - INFO - codeparrot_training - Step 10044: {'lr': 0.0004963644089771598, 'samples': 5143040, 'steps': 10044, 'loss/train': 1.2299882173538208}
-03/04/2022 01:16:03 - INFO - codeparrot_training - Step 10045: {'lr': 0.0004963635071927633, 'samples': 5143552, 'steps': 10045, 'loss/train': 2.305612325668335}
-03/04/2022 01:16:05 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 01:16:08 - INFO - codeparrot_training - Step 10046: {'lr': 0.0004963626052973592, 'samples': 5144064, 'steps': 10046, 'loss/train': 1.8316534757614136}
-03/04/2022 01:16:11 - INFO - codeparrot_training - Step 10047: {'lr': 0.0004963617032909479, 'samples': 5144576, 'steps': 10047, 'loss/train': 2.9595587253570557}
-03/04/2022 01:16:14 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 01:16:16 - INFO - codeparrot_training - Step 10048: {'lr': 0.0004963608011735298, 'samples': 5145088, 'steps': 10048, 'loss/train': 1.9260903596878052}
-03/04/2022 01:16:19 - INFO - codeparrot_training - Step 10049: {'lr': 0.0004963598989451053, 'samples': 5145600, 'steps': 10049, 'loss/train': 2.6370177268981934}
-03/04/2022 01:16:22 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 01:16:25 - INFO - codeparrot_training - Step 10050: {'lr': 0.000496358996605675, 'samples': 5146112, 'steps': 10050, 'loss/train': 2.4773261547088623}
-03/04/2022 01:16:28 - INFO - codeparrot_training - Step 10051: {'lr': 0.0004963580941552391, 'samples': 5146624, 'steps': 10051, 'loss/train': 2.2527692317962646}
-03/04/2022 01:16:30 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/04/2022 01:16:33 - INFO - codeparrot_training - Step 10052: {'lr': 0.0004963571915937979, 'samples': 5147136, 'steps': 10052, 'loss/train': 2.142387866973877}
-03/04/2022 01:16:37 - INFO - codeparrot_training - Step 10053: {'lr': 0.000496356288921352, 'samples': 5147648, 'steps': 10053, 'loss/train': 1.9207566976547241}
-03/04/2022 01:16:39 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/04/2022 01:16:42 - INFO - codeparrot_training - Step 10054: {'lr': 0.0004963553861379018, 'samples': 5148160, 'steps': 10054, 'loss/train': 1.9962279796600342}
-03/04/2022 01:16:45 - INFO - codeparrot_training - Step 10055: {'lr': 0.0004963544832434476, 'samples': 5148672, 'steps': 10055, 'loss/train': 1.4771034717559814}
-03/04/2022 01:16:48 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 01:16:50 - INFO - codeparrot_training - Step 10056: {'lr': 0.00049635358023799, 'samples': 5149184, 'steps': 10056, 'loss/train': 1.2532058954238892}
-03/04/2022 01:16:53 - INFO - codeparrot_training - Step 10057: {'lr': 0.0004963526771215291, 'samples': 5149696, 'steps': 10057, 'loss/train': 1.7736119031906128}
-03/04/2022 01:16:56 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 01:16:59 - INFO - codeparrot_training - Step 10058: {'lr': 0.0004963517738940656, 'samples': 5150208, 'steps': 10058, 'loss/train': 2.1222622394561768}
-03/04/2022 01:17:02 - INFO - codeparrot_training - Step 10059: {'lr': 0.0004963508705555998, 'samples': 5150720, 'steps': 10059, 'loss/train': 1.6434558629989624}
-03/04/2022 01:17:05 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/04/2022 01:17:07 - INFO - codeparrot_training - Step 10060: {'lr': 0.000496349967106132, 'samples': 5151232, 'steps': 10060, 'loss/train': 0.6979081630706787}
-03/04/2022 01:17:10 - INFO - codeparrot_training - Step 10061: {'lr': 0.0004963490635456629, 'samples': 5151744, 'steps': 10061, 'loss/train': 2.0004374980926514}
-03/04/2022 01:17:13 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 01:17:15 - INFO - codeparrot_training - Step 10062: {'lr': 0.0004963481598741925, 'samples': 5152256, 'steps': 10062, 'loss/train': 2.5339818000793457}
-03/04/2022 01:17:19 - INFO - codeparrot_training - Step 10063: {'lr': 0.0004963472560917216, 'samples': 5152768, 'steps': 10063, 'loss/train': 1.4920767545700073}
-03/04/2022 01:17:22 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/04/2022 01:17:24 - INFO - codeparrot_training - Step 10064: {'lr': 0.0004963463521982503, 'samples': 5153280, 'steps': 10064, 'loss/train': 2.8751204013824463}
-03/04/2022 01:17:28 - INFO - codeparrot_training - Step 10065: {'lr': 0.0004963454481937791, 'samples': 5153792, 'steps': 10065, 'loss/train': 1.4077054262161255}
-03/04/2022 01:17:30 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/04/2022 01:17:33 - INFO - codeparrot_training - Step 10066: {'lr': 0.0004963445440783086, 'samples': 5154304, 'steps': 10066, 'loss/train': 2.3938260078430176}
-03/04/2022 01:17:36 - INFO - codeparrot_training - Step 10067: {'lr': 0.0004963436398518389, 'samples': 5154816, 'steps': 10067, 'loss/train': 1.1299691200256348}
-03/04/2022 01:17:39 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/04/2022 01:17:41 - INFO - codeparrot_training - Step 10068: {'lr': 0.0004963427355143706, 'samples': 5155328, 'steps': 10068, 'loss/train': 1.3280311822891235}
-03/04/2022 01:17:45 - INFO - codeparrot_training - Step 10069: {'lr': 0.0004963418310659041, 'samples': 5155840, 'steps': 10069, 'loss/train': 2.648113965988159}
-03/04/2022 01:17:47 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/04/2022 01:17:50 - INFO - codeparrot_training - Step 10070: {'lr': 0.0004963409265064398, 'samples': 5156352, 'steps': 10070, 'loss/train': 2.2365965843200684}
-03/04/2022 01:17:53 - INFO - codeparrot_training - Step 10071: {'lr': 0.0004963400218359781, 'samples': 5156864, 'steps': 10071, 'loss/train': 2.2701432704925537}
-03/04/2022 01:17:56 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 01:17:59 - INFO - codeparrot_training - Step 10072: {'lr': 0.0004963391170545193, 'samples': 5157376, 'steps': 10072, 'loss/train': 1.6658799648284912}
-03/04/2022 01:18:02 - INFO - codeparrot_training - Step 10073: {'lr': 0.0004963382121620639, 'samples': 5157888, 'steps': 10073, 'loss/train': 2.2780585289001465}
-03/04/2022 01:18:04 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 01:18:07 - INFO - codeparrot_training - Step 10074: {'lr': 0.0004963373071586123, 'samples': 5158400, 'steps': 10074, 'loss/train': 2.0430550575256348}
-03/04/2022 01:18:10 - INFO - codeparrot_training - Step 10075: {'lr': 0.000496336402044165, 'samples': 5158912, 'steps': 10075, 'loss/train': 2.067502737045288}
-03/04/2022 01:18:12 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/04/2022 01:18:15 - INFO - codeparrot_training - Step 10076: {'lr': 0.0004963354968187222, 'samples': 5159424, 'steps': 10076, 'loss/train': 1.4974254369735718}
-03/04/2022 01:18:19 - INFO - codeparrot_training - Step 10077: {'lr': 0.0004963345914822845, 'samples': 5159936, 'steps': 10077, 'loss/train': 2.1241042613983154}
-03/04/2022 01:18:21 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/04/2022 01:18:24 - INFO - codeparrot_training - Step 10078: {'lr': 0.0004963336860348521, 'samples': 5160448, 'steps': 10078, 'loss/train': 2.1292102336883545}
-03/04/2022 01:18:27 - INFO - codeparrot_training - Step 10079: {'lr': 0.0004963327804764257, 'samples': 5160960, 'steps': 10079, 'loss/train': 1.9226638078689575}
-03/04/2022 01:18:29 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/04/2022 01:18:32 - INFO - codeparrot_training - Step 10080: {'lr': 0.0004963318748070056, 'samples': 5161472, 'steps': 10080, 'loss/train': 1.846144437789917}
-03/04/2022 01:18:35 - INFO - codeparrot_training - Step 10081: {'lr': 0.0004963309690265921, 'samples': 5161984, 'steps': 10081, 'loss/train': 2.1630589962005615}
-03/04/2022 01:18:37 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 01:18:41 - INFO - codeparrot_training - Step 10082: {'lr': 0.0004963300631351856, 'samples': 5162496, 'steps': 10082, 'loss/train': 1.428920030593872}
-03/04/2022 01:18:44 - INFO - codeparrot_training - Step 10083: {'lr': 0.0004963291571327866, 'samples': 5163008, 'steps': 10083, 'loss/train': 2.2344727516174316}
-03/04/2022 01:18:46 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/04/2022 01:18:49 - INFO - codeparrot_training - Step 10084: {'lr': 0.0004963282510193955, 'samples': 5163520, 'steps': 10084, 'loss/train': 2.1185145378112793}
-03/04/2022 01:18:52 - INFO - codeparrot_training - Step 10085: {'lr': 0.0004963273447950126, 'samples': 5164032, 'steps': 10085, 'loss/train': 2.23928165435791}
-03/04/2022 01:18:54 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/04/2022 01:18:57 - INFO - codeparrot_training - Step 10086: {'lr': 0.0004963264384596386, 'samples': 5164544, 'steps': 10086, 'loss/train': 2.1578891277313232}
-03/04/2022 01:19:01 - INFO - codeparrot_training - Step 10087: {'lr': 0.0004963255320132735, 'samples': 5165056, 'steps': 10087, 'loss/train': 2.229902505874634}
-03/04/2022 01:19:03 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/04/2022 01:19:06 - INFO - codeparrot_training - Step 10088: {'lr': 0.0004963246254559181, 'samples': 5165568, 'steps': 10088, 'loss/train': 1.711485505104065}
-03/04/2022 01:19:09 - INFO - codeparrot_training - Step 10089: {'lr': 0.0004963237187875724, 'samples': 5166080, 'steps': 10089, 'loss/train': 1.6769945621490479}
-03/04/2022 01:19:11 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/04/2022 01:19:14 - INFO - codeparrot_training - Step 10090: {'lr': 0.0004963228120082372, 'samples': 5166592, 'steps': 10090, 'loss/train': 2.533996343612671}
-03/04/2022 01:19:18 - INFO - codeparrot_training - Step 10091: {'lr': 0.0004963219051179127, 'samples': 5167104, 'steps': 10091, 'loss/train': 1.1508548259735107}
-03/04/2022 01:19:20 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/04/2022 01:19:23 - INFO - codeparrot_training - Step 10092: {'lr': 0.0004963209981165993, 'samples': 5167616, 'steps': 10092, 'loss/train': 2.1553616523742676}
-03/04/2022 01:19:26 - INFO - codeparrot_training - Step 10093: {'lr': 0.0004963200910042976, 'samples': 5168128, 'steps': 10093, 'loss/train': 2.0644679069519043}
-03/04/2022 01:19:28 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 01:19:31 - INFO - codeparrot_training - Step 10094: {'lr': 0.0004963191837810077, 'samples': 5168640, 'steps': 10094, 'loss/train': 2.2740283012390137}
-03/04/2022 01:19:34 - INFO - codeparrot_training - Step 10095: {'lr': 0.0004963182764467303, 'samples': 5169152, 'steps': 10095, 'loss/train': 2.219679594039917}
-03/04/2022 01:19:36 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 01:19:40 - INFO - codeparrot_training - Step 10096: {'lr': 0.0004963173690014656, 'samples': 5169664, 'steps': 10096, 'loss/train': 2.7698402404785156}
-03/04/2022 01:19:43 - INFO - codeparrot_training - Step 10097: {'lr': 0.0004963164614452142, 'samples': 5170176, 'steps': 10097, 'loss/train': 2.3920981884002686}
-03/04/2022 01:19:45 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/04/2022 01:19:48 - INFO - codeparrot_training - Step 10098: {'lr': 0.0004963155537779764, 'samples': 5170688, 'steps': 10098, 'loss/train': 1.5103355646133423}
-03/04/2022 01:19:51 - INFO - codeparrot_training - Step 10099: {'lr': 0.0004963146459997525, 'samples': 5171200, 'steps': 10099, 'loss/train': 1.44295334815979}
-03/04/2022 01:19:53 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 01:19:56 - INFO - codeparrot_training - Step 10100: {'lr': 0.0004963137381105431, 'samples': 5171712, 'steps': 10100, 'loss/train': 2.2126107215881348}
-03/04/2022 01:20:00 - INFO - codeparrot_training - Step 10101: {'lr': 0.0004963128301103485, 'samples': 5172224, 'steps': 10101, 'loss/train': 0.9914646148681641}
-03/04/2022 01:20:01 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/04/2022 01:20:05 - INFO - codeparrot_training - Step 10102: {'lr': 0.0004963119219991691, 'samples': 5172736, 'steps': 10102, 'loss/train': 1.518932819366455}
-03/04/2022 01:20:08 - INFO - codeparrot_training - Step 10103: {'lr': 0.0004963110137770054, 'samples': 5173248, 'steps': 10103, 'loss/train': 1.8555675745010376}
-03/04/2022 01:20:09 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 01:20:13 - INFO - codeparrot_training - Step 10104: {'lr': 0.0004963101054438578, 'samples': 5173760, 'steps': 10104, 'loss/train': 3.0083141326904297}
-03/04/2022 01:20:16 - INFO - codeparrot_training - Step 10105: {'lr': 0.0004963091969997265, 'samples': 5174272, 'steps': 10105, 'loss/train': 2.520541191101074}
-03/04/2022 01:20:18 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/04/2022 01:20:22 - INFO - codeparrot_training - Step 10106: {'lr': 0.0004963082884446123, 'samples': 5174784, 'steps': 10106, 'loss/train': 1.4287632703781128}
-03/04/2022 01:20:25 - INFO - codeparrot_training - Step 10107: {'lr': 0.0004963073797785153, 'samples': 5175296, 'steps': 10107, 'loss/train': 1.9222538471221924}
-03/04/2022 01:20:30 - INFO - codeparrot_training - Step 10108: {'lr': 0.000496306471001436, 'samples': 5175808, 'steps': 10108, 'loss/train': 1.9472159147262573}
-03/04/2022 01:20:33 - INFO - codeparrot_training - Step 10109: {'lr': 0.0004963055621133748, 'samples': 5176320, 'steps': 10109, 'loss/train': 3.513185501098633}
-03/04/2022 01:20:36 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/04/2022 01:20:39 - INFO - codeparrot_training - Step 10110: {'lr': 0.0004963046531143321, 'samples': 5176832, 'steps': 10110, 'loss/train': 2.4224624633789062}
-03/04/2022 01:20:42 - INFO - codeparrot_training - Step 10111: {'lr': 0.0004963037440043083, 'samples': 5177344, 'steps': 10111, 'loss/train': 2.5721304416656494}
-03/04/2022 01:20:44 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/04/2022 01:20:47 - INFO - codeparrot_training - Step 10112: {'lr': 0.0004963028347833038, 'samples': 5177856, 'steps': 10112, 'loss/train': 2.4852426052093506}
-03/04/2022 01:20:50 - INFO - codeparrot_training - Step 10113: {'lr': 0.0004963019254513191, 'samples': 5178368, 'steps': 10113, 'loss/train': 2.61362886428833}
-03/04/2022 01:20:52 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/04/2022 01:20:55 - INFO - codeparrot_training - Step 10114: {'lr': 0.0004963010160083546, 'samples': 5178880, 'steps': 10114, 'loss/train': 2.1371073722839355}
-03/04/2022 01:20:59 - INFO - codeparrot_training - Step 10115: {'lr': 0.0004963001064544106, 'samples': 5179392, 'steps': 10115, 'loss/train': 1.170562982559204}
-03/04/2022 01:21:01 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/04/2022 01:21:04 - INFO - codeparrot_training - Step 10116: {'lr': 0.0004962991967894876, 'samples': 5179904, 'steps': 10116, 'loss/train': 2.1411163806915283}
-03/04/2022 01:21:07 - INFO - codeparrot_training - Step 10117: {'lr': 0.0004962982870135859, 'samples': 5180416, 'steps': 10117, 'loss/train': 2.1393160820007324}
-03/04/2022 01:21:09 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/04/2022 01:21:12 - INFO - codeparrot_training - Step 10118: {'lr': 0.0004962973771267061, 'samples': 5180928, 'steps': 10118, 'loss/train': 2.1511082649230957}
-03/04/2022 01:21:15 - INFO - codeparrot_training - Step 10119: {'lr': 0.0004962964671288484, 'samples': 5181440, 'steps': 10119, 'loss/train': 2.0182018280029297}
-03/04/2022 01:21:17 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 01:21:21 - INFO - codeparrot_training - Step 10120: {'lr': 0.0004962955570200135, 'samples': 5181952, 'steps': 10120, 'loss/train': 1.8704547882080078}
-03/04/2022 01:21:24 - INFO - codeparrot_training - Step 10121: {'lr': 0.0004962946468002014, 'samples': 5182464, 'steps': 10121, 'loss/train': 1.670318603515625}
-03/04/2022 01:21:27 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/04/2022 01:21:29 - INFO - codeparrot_training - Step 10122: {'lr': 0.0004962937364694129, 'samples': 5182976, 'steps': 10122, 'loss/train': 2.7219207286834717}
-03/04/2022 01:21:32 - INFO - codeparrot_training - Step 10123: {'lr': 0.0004962928260276481, 'samples': 5183488, 'steps': 10123, 'loss/train': 1.8149610757827759}
-03/04/2022 01:21:35 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 01:21:38 - INFO - codeparrot_training - Step 10124: {'lr': 0.0004962919154749077, 'samples': 5184000, 'steps': 10124, 'loss/train': 1.9766426086425781}
-03/04/2022 01:21:41 - INFO - codeparrot_training - Step 10125: {'lr': 0.0004962910048111919, 'samples': 5184512, 'steps': 10125, 'loss/train': 1.8453524112701416}
-03/04/2022 01:21:43 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/04/2022 01:21:46 - INFO - codeparrot_training - Step 10126: {'lr': 0.0004962900940365012, 'samples': 5185024, 'steps': 10126, 'loss/train': 2.1142630577087402}
-03/04/2022 01:21:49 - INFO - codeparrot_training - Step 10127: {'lr': 0.0004962891831508359, 'samples': 5185536, 'steps': 10127, 'loss/train': 1.9081979990005493}
-03/04/2022 01:21:52 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/04/2022 01:21:54 - INFO - codeparrot_training - Step 10128: {'lr': 0.0004962882721541965, 'samples': 5186048, 'steps': 10128, 'loss/train': 1.225365161895752}
-03/04/2022 01:21:58 - INFO - codeparrot_training - Step 10129: {'lr': 0.0004962873610465835, 'samples': 5186560, 'steps': 10129, 'loss/train': 2.396451711654663}
-03/04/2022 01:22:00 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/04/2022 01:22:03 - INFO - codeparrot_training - Step 10130: {'lr': 0.0004962864498279972, 'samples': 5187072, 'steps': 10130, 'loss/train': 1.59169602394104}
-03/04/2022 01:22:06 - INFO - codeparrot_training - Step 10131: {'lr': 0.000496285538498438, 'samples': 5187584, 'steps': 10131, 'loss/train': 2.051694393157959}
-03/04/2022 01:22:08 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/04/2022 01:22:11 - INFO - codeparrot_training - Step 10132: {'lr': 0.0004962846270579062, 'samples': 5188096, 'steps': 10132, 'loss/train': 0.6558986902236938}
-03/04/2022 01:22:14 - INFO - codeparrot_training - Step 10133: {'lr': 0.0004962837155064025, 'samples': 5188608, 'steps': 10133, 'loss/train': 2.1037094593048096}
-03/04/2022 01:22:16 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/04/2022 01:22:20 - INFO - codeparrot_training - Step 10134: {'lr': 0.0004962828038439272, 'samples': 5189120, 'steps': 10134, 'loss/train': 2.5245566368103027}
-03/04/2022 01:22:23 - INFO - codeparrot_training - Step 10135: {'lr': 0.0004962818920704805, 'samples': 5189632, 'steps': 10135, 'loss/train': 2.1831233501434326}
-03/04/2022 01:22:25 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/04/2022 01:22:28 - INFO - codeparrot_training - Step 10136: {'lr': 0.0004962809801860632, 'samples': 5190144, 'steps': 10136, 'loss/train': 1.6414083242416382}
-03/04/2022 01:22:31 - INFO - codeparrot_training - Step 10137: {'lr': 0.0004962800681906753, 'samples': 5190656, 'steps': 10137, 'loss/train': 1.610076904296875}
-03/04/2022 01:22:33 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/04/2022 01:22:37 - INFO - codeparrot_training - Step 10138: {'lr': 0.0004962791560843175, 'samples': 5191168, 'steps': 10138, 'loss/train': 1.8915430307388306}
-03/04/2022 01:22:40 - INFO - codeparrot_training - Step 10139: {'lr': 0.00049627824386699, 'samples': 5191680, 'steps': 10139, 'loss/train': 1.1795215606689453}
-03/04/2022 01:22:41 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/04/2022 01:22:45 - INFO - codeparrot_training - Step 10140: {'lr': 0.0004962773315386935, 'samples': 5192192, 'steps': 10140, 'loss/train': 2.4558184146881104}
-03/04/2022 01:22:48 - INFO - codeparrot_training - Step 10141: {'lr': 0.0004962764190994282, 'samples': 5192704, 'steps': 10141, 'loss/train': 3.3578994274139404}
-03/04/2022 01:22:50 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 01:22:53 - INFO - codeparrot_training - Step 10142: {'lr': 0.0004962755065491944, 'samples': 5193216, 'steps': 10142, 'loss/train': 2.324578285217285}
-03/04/2022 01:22:56 - INFO - codeparrot_training - Step 10143: {'lr': 0.0004962745938879928, 'samples': 5193728, 'steps': 10143, 'loss/train': 2.301095962524414}
-03/04/2022 01:22:58 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 01:23:02 - INFO - codeparrot_training - Step 10144: {'lr': 0.0004962736811158236, 'samples': 5194240, 'steps': 10144, 'loss/train': 1.6866047382354736}
-03/04/2022 01:23:05 - INFO - codeparrot_training - Step 10145: {'lr': 0.0004962727682326873, 'samples': 5194752, 'steps': 10145, 'loss/train': 2.3322951793670654}
-03/04/2022 01:23:06 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 01:23:10 - INFO - codeparrot_training - Step 10146: {'lr': 0.0004962718552385843, 'samples': 5195264, 'steps': 10146, 'loss/train': 2.936373233795166}
-03/04/2022 01:23:14 - INFO - codeparrot_training - Step 10147: {'lr': 0.000496270942133515, 'samples': 5195776, 'steps': 10147, 'loss/train': 2.448733329772949}
-03/04/2022 01:23:15 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/04/2022 01:23:19 - INFO - codeparrot_training - Step 10148: {'lr': 0.0004962700289174798, 'samples': 5196288, 'steps': 10148, 'loss/train': 1.7620385885238647}
-03/04/2022 01:23:22 - INFO - codeparrot_training - Step 10149: {'lr': 0.0004962691155904791, 'samples': 5196800, 'steps': 10149, 'loss/train': 1.962834358215332}
-03/04/2022 01:23:23 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 01:23:27 - INFO - codeparrot_training - Step 10150: {'lr': 0.0004962682021525134, 'samples': 5197312, 'steps': 10150, 'loss/train': 2.008275032043457}
-03/04/2022 01:23:30 - INFO - codeparrot_training - Step 10151: {'lr': 0.000496267288603583, 'samples': 5197824, 'steps': 10151, 'loss/train': 2.2338931560516357}
-03/04/2022 01:23:32 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/04/2022 01:23:36 - INFO - codeparrot_training - Step 10152: {'lr': 0.0004962663749436883, 'samples': 5198336, 'steps': 10152, 'loss/train': 0.48422005772590637}
-03/04/2022 01:23:39 - INFO - codeparrot_training - Step 10153: {'lr': 0.0004962654611728299, 'samples': 5198848, 'steps': 10153, 'loss/train': 2.4198577404022217}
-03/04/2022 01:23:41 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/04/2022 01:23:44 - INFO - codeparrot_training - Step 10154: {'lr': 0.000496264547291008, 'samples': 5199360, 'steps': 10154, 'loss/train': 2.434828758239746}
-03/04/2022 01:23:47 - INFO - codeparrot_training - Step 10155: {'lr': 0.0004962636332982232, 'samples': 5199872, 'steps': 10155, 'loss/train': 2.0595335960388184}
-03/04/2022 01:23:50 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 01:23:53 - INFO - codeparrot_training - Step 10156: {'lr': 0.0004962627191944756, 'samples': 5200384, 'steps': 10156, 'loss/train': 1.4180576801300049}
-03/04/2022 01:23:56 - INFO - codeparrot_training - Step 10157: {'lr': 0.000496261804979766, 'samples': 5200896, 'steps': 10157, 'loss/train': 2.508254289627075}
-03/04/2022 01:23:58 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/04/2022 01:24:01 - INFO - codeparrot_training - Step 10158: {'lr': 0.0004962608906540946, 'samples': 5201408, 'steps': 10158, 'loss/train': 1.9529987573623657}
-03/04/2022 01:24:04 - INFO - codeparrot_training - Step 10159: {'lr': 0.0004962599762174618, 'samples': 5201920, 'steps': 10159, 'loss/train': 1.840614914894104}
-03/04/2022 01:24:07 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 01:24:10 - INFO - codeparrot_training - Step 10160: {'lr': 0.0004962590616698681, 'samples': 5202432, 'steps': 10160, 'loss/train': 1.8269257545471191}
-03/04/2022 01:24:13 - INFO - codeparrot_training - Step 10161: {'lr': 0.0004962581470113138, 'samples': 5202944, 'steps': 10161, 'loss/train': 1.4094518423080444}
-03/04/2022 01:24:15 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/04/2022 01:24:18 - INFO - codeparrot_training - Step 10162: {'lr': 0.0004962572322417994, 'samples': 5203456, 'steps': 10162, 'loss/train': 1.859686017036438}
-03/04/2022 01:24:21 - INFO - codeparrot_training - Step 10163: {'lr': 0.0004962563173613254, 'samples': 5203968, 'steps': 10163, 'loss/train': 2.5345962047576904}
-03/04/2022 01:24:24 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 01:24:27 - INFO - codeparrot_training - Step 10164: {'lr': 0.000496255402369892, 'samples': 5204480, 'steps': 10164, 'loss/train': 2.6166117191314697}
-03/04/2022 01:24:30 - INFO - codeparrot_training - Step 10165: {'lr': 0.0004962544872674997, 'samples': 5204992, 'steps': 10165, 'loss/train': 0.3910056948661804}
-03/04/2022 01:24:33 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/04/2022 01:24:35 - INFO - codeparrot_training - Step 10166: {'lr': 0.000496253572054149, 'samples': 5205504, 'steps': 10166, 'loss/train': 2.293327569961548}
-03/04/2022 01:24:38 - INFO - codeparrot_training - Step 10167: {'lr': 0.0004962526567298402, 'samples': 5206016, 'steps': 10167, 'loss/train': 2.027409076690674}
-03/04/2022 01:24:41 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/04/2022 01:24:44 - INFO - codeparrot_training - Step 10168: {'lr': 0.0004962517412945738, 'samples': 5206528, 'steps': 10168, 'loss/train': 2.4747772216796875}
-03/04/2022 01:24:47 - INFO - codeparrot_training - Step 10169: {'lr': 0.00049625082574835, 'samples': 5207040, 'steps': 10169, 'loss/train': 1.6675478219985962}
-03/04/2022 01:24:49 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 01:24:52 - INFO - codeparrot_training - Step 10170: {'lr': 0.0004962499100911696, 'samples': 5207552, 'steps': 10170, 'loss/train': 3.1076340675354004}
-03/04/2022 01:24:55 - INFO - codeparrot_training - Step 10171: {'lr': 0.0004962489943230326, 'samples': 5208064, 'steps': 10171, 'loss/train': 1.3046464920043945}
-03/04/2022 01:24:57 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 01:25:00 - INFO - codeparrot_training - Step 10172: {'lr': 0.0004962480784439397, 'samples': 5208576, 'steps': 10172, 'loss/train': 1.1539356708526611}
-03/04/2022 01:25:04 - INFO - codeparrot_training - Step 10173: {'lr': 0.0004962471624538913, 'samples': 5209088, 'steps': 10173, 'loss/train': 2.014951467514038}
-03/04/2022 01:25:06 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/04/2022 01:25:09 - INFO - codeparrot_training - Step 10174: {'lr': 0.0004962462463528875, 'samples': 5209600, 'steps': 10174, 'loss/train': 1.5303465127944946}
-03/04/2022 01:25:12 - INFO - codeparrot_training - Step 10175: {'lr': 0.0004962453301409291, 'samples': 5210112, 'steps': 10175, 'loss/train': 2.509937286376953}
-03/04/2022 01:25:14 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 01:25:17 - INFO - codeparrot_training - Step 10176: {'lr': 0.0004962444138180164, 'samples': 5210624, 'steps': 10176, 'loss/train': 1.4165807962417603}
-03/04/2022 01:25:20 - INFO - codeparrot_training - Step 10177: {'lr': 0.0004962434973841497, 'samples': 5211136, 'steps': 10177, 'loss/train': 2.342956781387329}
-03/04/2022 01:25:23 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 01:25:26 - INFO - codeparrot_training - Step 10178: {'lr': 0.0004962425808393295, 'samples': 5211648, 'steps': 10178, 'loss/train': 1.866863489151001}
-03/04/2022 01:25:29 - INFO - codeparrot_training - Step 10179: {'lr': 0.000496241664183556, 'samples': 5212160, 'steps': 10179, 'loss/train': 2.358876943588257}
-03/04/2022 01:25:31 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 01:25:34 - INFO - codeparrot_training - Step 10180: {'lr': 0.0004962407474168301, 'samples': 5212672, 'steps': 10180, 'loss/train': 1.7871580123901367}
-03/04/2022 01:25:37 - INFO - codeparrot_training - Step 10181: {'lr': 0.0004962398305391518, 'samples': 5213184, 'steps': 10181, 'loss/train': 2.4106335639953613}
-03/04/2022 01:25:39 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 01:25:43 - INFO - codeparrot_training - Step 10182: {'lr': 0.0004962389135505217, 'samples': 5213696, 'steps': 10182, 'loss/train': 1.053757905960083}
-03/04/2022 01:25:46 - INFO - codeparrot_training - Step 10183: {'lr': 0.00049623799645094, 'samples': 5214208, 'steps': 10183, 'loss/train': 1.2378393411636353}
-03/04/2022 01:25:48 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 01:25:51 - INFO - codeparrot_training - Step 10184: {'lr': 0.0004962370792404073, 'samples': 5214720, 'steps': 10184, 'loss/train': 2.873457193374634}
-03/04/2022 01:25:54 - INFO - codeparrot_training - Step 10185: {'lr': 0.000496236161918924, 'samples': 5215232, 'steps': 10185, 'loss/train': 2.8000364303588867}
-03/04/2022 01:25:56 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 01:25:59 - INFO - codeparrot_training - Step 10186: {'lr': 0.0004962352444864904, 'samples': 5215744, 'steps': 10186, 'loss/train': 2.55173659324646}
-03/04/2022 01:26:03 - INFO - codeparrot_training - Step 10187: {'lr': 0.0004962343269431072, 'samples': 5216256, 'steps': 10187, 'loss/train': 2.1425538063049316}
-03/04/2022 01:26:05 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/04/2022 01:26:08 - INFO - codeparrot_training - Step 10188: {'lr': 0.0004962334092887744, 'samples': 5216768, 'steps': 10188, 'loss/train': 1.6605470180511475}
-03/04/2022 01:26:11 - INFO - codeparrot_training - Step 10189: {'lr': 0.0004962324915234928, 'samples': 5217280, 'steps': 10189, 'loss/train': 2.5664758682250977}
-03/04/2022 01:26:13 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 01:26:16 - INFO - codeparrot_training - Step 10190: {'lr': 0.0004962315736472626, 'samples': 5217792, 'steps': 10190, 'loss/train': 1.2507072687149048}
-03/04/2022 01:26:19 - INFO - codeparrot_training - Step 10191: {'lr': 0.0004962306556600842, 'samples': 5218304, 'steps': 10191, 'loss/train': 1.918250322341919}
-03/04/2022 01:26:21 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 01:26:25 - INFO - codeparrot_training - Step 10192: {'lr': 0.0004962297375619581, 'samples': 5218816, 'steps': 10192, 'loss/train': 2.2674410343170166}
-03/04/2022 01:26:28 - INFO - codeparrot_training - Step 10193: {'lr': 0.0004962288193528846, 'samples': 5219328, 'steps': 10193, 'loss/train': 0.9237266778945923}
-03/04/2022 01:26:30 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/04/2022 01:26:33 - INFO - codeparrot_training - Step 10194: {'lr': 0.0004962279010328642, 'samples': 5219840, 'steps': 10194, 'loss/train': 2.3095011711120605}
-03/04/2022 01:26:36 - INFO - codeparrot_training - Step 10195: {'lr': 0.0004962269826018974, 'samples': 5220352, 'steps': 10195, 'loss/train': 3.611412763595581}
-03/04/2022 01:26:39 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 01:26:42 - INFO - codeparrot_training - Step 10196: {'lr': 0.0004962260640599845, 'samples': 5220864, 'steps': 10196, 'loss/train': 1.597129225730896}
-03/04/2022 01:26:45 - INFO - codeparrot_training - Step 10197: {'lr': 0.0004962251454071259, 'samples': 5221376, 'steps': 10197, 'loss/train': 2.5819883346557617}
-03/04/2022 01:26:47 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/04/2022 01:26:50 - INFO - codeparrot_training - Step 10198: {'lr': 0.0004962242266433221, 'samples': 5221888, 'steps': 10198, 'loss/train': 2.6653947830200195}
-03/04/2022 01:26:53 - INFO - codeparrot_training - Step 10199: {'lr': 0.0004962233077685734, 'samples': 5222400, 'steps': 10199, 'loss/train': 1.106989860534668}
-03/04/2022 01:26:55 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 01:26:59 - INFO - codeparrot_training - Step 10200: {'lr': 0.0004962223887828803, 'samples': 5222912, 'steps': 10200, 'loss/train': 0.8341485261917114}
-03/04/2022 01:27:02 - INFO - codeparrot_training - Step 10201: {'lr': 0.0004962214696862432, 'samples': 5223424, 'steps': 10201, 'loss/train': 2.7840943336486816}
-03/04/2022 01:27:04 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/04/2022 01:27:07 - INFO - codeparrot_training - Step 10202: {'lr': 0.0004962205504786626, 'samples': 5223936, 'steps': 10202, 'loss/train': 1.1235381364822388}
-03/04/2022 01:27:10 - INFO - codeparrot_training - Step 10203: {'lr': 0.0004962196311601386, 'samples': 5224448, 'steps': 10203, 'loss/train': 2.2590906620025635}
-03/04/2022 01:27:12 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/04/2022 01:27:15 - INFO - codeparrot_training - Step 10204: {'lr': 0.000496218711730672, 'samples': 5224960, 'steps': 10204, 'loss/train': 2.0889995098114014}
-03/04/2022 01:27:19 - INFO - codeparrot_training - Step 10205: {'lr': 0.000496217792190263, 'samples': 5225472, 'steps': 10205, 'loss/train': 2.0763704776763916}
-03/04/2022 01:27:21 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/04/2022 01:27:24 - INFO - codeparrot_training - Step 10206: {'lr': 0.0004962168725389121, 'samples': 5225984, 'steps': 10206, 'loss/train': 1.1714017391204834}
-03/04/2022 01:27:27 - INFO - codeparrot_training - Step 10207: {'lr': 0.0004962159527766196, 'samples': 5226496, 'steps': 10207, 'loss/train': 1.7864981889724731}
-03/04/2022 01:27:30 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/04/2022 01:27:32 - INFO - codeparrot_training - Step 10208: {'lr': 0.000496215032903386, 'samples': 5227008, 'steps': 10208, 'loss/train': 2.149974822998047}
-03/04/2022 01:27:35 - INFO - codeparrot_training - Step 10209: {'lr': 0.0004962141129192118, 'samples': 5227520, 'steps': 10209, 'loss/train': 1.9302829504013062}
-03/04/2022 01:27:38 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 01:27:41 - INFO - codeparrot_training - Step 10210: {'lr': 0.0004962131928240972, 'samples': 5228032, 'steps': 10210, 'loss/train': 2.0956714153289795}
-03/04/2022 01:27:44 - INFO - codeparrot_training - Step 10211: {'lr': 0.0004962122726180428, 'samples': 5228544, 'steps': 10211, 'loss/train': 3.31294846534729}
-03/04/2022 01:27:46 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 01:27:49 - INFO - codeparrot_training - Step 10212: {'lr': 0.000496211352301049, 'samples': 5229056, 'steps': 10212, 'loss/train': 2.649291515350342}
-03/04/2022 01:27:52 - INFO - codeparrot_training - Step 10213: {'lr': 0.0004962104318731161, 'samples': 5229568, 'steps': 10213, 'loss/train': 2.261939287185669}
-03/04/2022 01:27:55 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/04/2022 01:27:58 - INFO - codeparrot_training - Step 10214: {'lr': 0.0004962095113342445, 'samples': 5230080, 'steps': 10214, 'loss/train': 1.4092388153076172}
-03/04/2022 01:28:01 - INFO - codeparrot_training - Step 10215: {'lr': 0.0004962085906844348, 'samples': 5230592, 'steps': 10215, 'loss/train': 2.632321357727051}
-03/04/2022 01:28:03 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/04/2022 01:28:06 - INFO - codeparrot_training - Step 10216: {'lr': 0.0004962076699236873, 'samples': 5231104, 'steps': 10216, 'loss/train': 0.352029949426651}
-03/04/2022 01:28:09 - INFO - codeparrot_training - Step 10217: {'lr': 0.0004962067490520024, 'samples': 5231616, 'steps': 10217, 'loss/train': 2.113161563873291}
-03/04/2022 01:28:11 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/04/2022 01:28:14 - INFO - codeparrot_training - Step 10218: {'lr': 0.0004962058280693805, 'samples': 5232128, 'steps': 10218, 'loss/train': 2.173856019973755}
-03/04/2022 01:28:18 - INFO - codeparrot_training - Step 10219: {'lr': 0.0004962049069758221, 'samples': 5232640, 'steps': 10219, 'loss/train': 1.6805450916290283}
-03/04/2022 01:28:20 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 01:28:23 - INFO - codeparrot_training - Step 10220: {'lr': 0.0004962039857713276, 'samples': 5233152, 'steps': 10220, 'loss/train': 2.1895742416381836}
-03/04/2022 01:28:26 - INFO - codeparrot_training - Step 10221: {'lr': 0.0004962030644558974, 'samples': 5233664, 'steps': 10221, 'loss/train': 2.8434019088745117}
-03/04/2022 01:28:28 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 01:28:31 - INFO - codeparrot_training - Step 10222: {'lr': 0.0004962021430295319, 'samples': 5234176, 'steps': 10222, 'loss/train': 1.7353239059448242}
-03/04/2022 01:28:34 - INFO - codeparrot_training - Step 10223: {'lr': 0.0004962012214922314, 'samples': 5234688, 'steps': 10223, 'loss/train': 2.289041757583618}
-03/04/2022 01:28:37 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/04/2022 01:28:40 - INFO - codeparrot_training - Step 10224: {'lr': 0.0004962002998439966, 'samples': 5235200, 'steps': 10224, 'loss/train': 2.3871846199035645}
-03/04/2022 01:28:43 - INFO - codeparrot_training - Step 10225: {'lr': 0.0004961993780848276, 'samples': 5235712, 'steps': 10225, 'loss/train': 1.7101603746414185}
-03/04/2022 01:28:45 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 01:28:48 - INFO - codeparrot_training - Step 10226: {'lr': 0.000496198456214725, 'samples': 5236224, 'steps': 10226, 'loss/train': 1.9845290184020996}
-03/04/2022 01:28:51 - INFO - codeparrot_training - Step 10227: {'lr': 0.0004961975342336891, 'samples': 5236736, 'steps': 10227, 'loss/train': 1.8696235418319702}
-03/04/2022 01:28:54 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 01:28:57 - INFO - codeparrot_training - Step 10228: {'lr': 0.0004961966121417204, 'samples': 5237248, 'steps': 10228, 'loss/train': 2.1427693367004395}
-03/04/2022 01:29:00 - INFO - codeparrot_training - Step 10229: {'lr': 0.0004961956899388195, 'samples': 5237760, 'steps': 10229, 'loss/train': 2.4092659950256348}
-03/04/2022 01:29:02 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/04/2022 01:29:05 - INFO - codeparrot_training - Step 10230: {'lr': 0.0004961947676249864, 'samples': 5238272, 'steps': 10230, 'loss/train': 2.210362672805786}
-03/04/2022 01:29:08 - INFO - codeparrot_training - Step 10231: {'lr': 0.0004961938452002218, 'samples': 5238784, 'steps': 10231, 'loss/train': 0.9548380374908447}
-03/04/2022 01:29:11 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/04/2022 01:29:14 - INFO - codeparrot_training - Step 10232: {'lr': 0.0004961929226645261, 'samples': 5239296, 'steps': 10232, 'loss/train': 1.6920570135116577}
-03/04/2022 01:29:17 - INFO - codeparrot_training - Step 10233: {'lr': 0.0004961920000178996, 'samples': 5239808, 'steps': 10233, 'loss/train': 1.0970784425735474}
-03/04/2022 01:29:20 - INFO - codeparrot_training - Step 10234: {'lr': 0.0004961910772603429, 'samples': 5240320, 'steps': 10234, 'loss/train': 2.893232822418213}
-03/04/2022 01:29:21 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/04/2022 01:29:25 - INFO - codeparrot_training - Step 10235: {'lr': 0.0004961901543918563, 'samples': 5240832, 'steps': 10235, 'loss/train': 2.4686028957366943}
-03/04/2022 01:29:29 - INFO - codeparrot_training - Step 10236: {'lr': 0.0004961892314124401, 'samples': 5241344, 'steps': 10236, 'loss/train': 2.3109817504882812}
-03/04/2022 01:29:29 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/04/2022 01:29:34 - INFO - codeparrot_training - Step 10237: {'lr': 0.0004961883083220948, 'samples': 5241856, 'steps': 10237, 'loss/train': 1.648911476135254}
-03/04/2022 01:29:37 - INFO - codeparrot_training - Step 10238: {'lr': 0.0004961873851208209, 'samples': 5242368, 'steps': 10238, 'loss/train': 2.5285720825195312}
-03/04/2022 01:29:37 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/04/2022 01:29:42 - INFO - codeparrot_training - Step 10239: {'lr': 0.0004961864618086188, 'samples': 5242880, 'steps': 10239, 'loss/train': 2.2485039234161377}
-03/04/2022 01:29:45 - INFO - codeparrot_training - Step 10240: {'lr': 0.0004961855383854889, 'samples': 5243392, 'steps': 10240, 'loss/train': 1.8197580575942993}
-03/04/2022 01:29:46 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/04/2022 01:29:51 - INFO - codeparrot_training - Step 10241: {'lr': 0.0004961846148514315, 'samples': 5243904, 'steps': 10241, 'loss/train': 2.7031514644622803}
-03/04/2022 01:29:54 - INFO - codeparrot_training - Step 10242: {'lr': 0.0004961836912064472, 'samples': 5244416, 'steps': 10242, 'loss/train': 1.5401023626327515}
-03/04/2022 01:29:54 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 01:29:59 - INFO - codeparrot_training - Step 10243: {'lr': 0.0004961827674505363, 'samples': 5244928, 'steps': 10243, 'loss/train': 2.7292370796203613}
-03/04/2022 01:30:02 - INFO - codeparrot_training - Step 10244: {'lr': 0.0004961818435836993, 'samples': 5245440, 'steps': 10244, 'loss/train': 2.0974738597869873}
-03/04/2022 01:30:02 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 01:30:08 - INFO - codeparrot_training - Step 10245: {'lr': 0.0004961809196059365, 'samples': 5245952, 'steps': 10245, 'loss/train': 2.419736862182617}
-03/04/2022 01:30:11 - INFO - codeparrot_training - Step 10246: {'lr': 0.0004961799955172483, 'samples': 5246464, 'steps': 10246, 'loss/train': 2.888096809387207}
-03/04/2022 01:30:11 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/04/2022 01:30:16 - INFO - codeparrot_training - Step 10247: {'lr': 0.0004961790713176353, 'samples': 5246976, 'steps': 10247, 'loss/train': 1.6266064643859863}
-03/04/2022 01:30:19 - INFO - codeparrot_training - Step 10248: {'lr': 0.0004961781470070978, 'samples': 5247488, 'steps': 10248, 'loss/train': 1.999554991722107}
-03/04/2022 01:30:20 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 01:30:25 - INFO - codeparrot_training - Step 10249: {'lr': 0.0004961772225856362, 'samples': 5248000, 'steps': 10249, 'loss/train': 2.333379030227661}
-03/04/2022 01:30:28 - INFO - codeparrot_training - Step 10250: {'lr': 0.0004961762980532509, 'samples': 5248512, 'steps': 10250, 'loss/train': 2.2103054523468018}
-03/04/2022 01:30:29 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/04/2022 01:30:33 - INFO - codeparrot_training - Step 10251: {'lr': 0.0004961753734099425, 'samples': 5249024, 'steps': 10251, 'loss/train': 1.7748688459396362}
-03/04/2022 01:30:36 - INFO - codeparrot_training - Step 10252: {'lr': 0.0004961744486557112, 'samples': 5249536, 'steps': 10252, 'loss/train': 2.707486152648926}
-03/04/2022 01:30:37 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/04/2022 01:30:42 - INFO - codeparrot_training - Step 10253: {'lr': 0.0004961735237905574, 'samples': 5250048, 'steps': 10253, 'loss/train': 2.532809257507324}
-03/04/2022 01:30:45 - INFO - codeparrot_training - Step 10254: {'lr': 0.0004961725988144816, 'samples': 5250560, 'steps': 10254, 'loss/train': 2.4545788764953613}
-03/04/2022 01:30:46 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 01:30:50 - INFO - codeparrot_training - Step 10255: {'lr': 0.0004961716737274844, 'samples': 5251072, 'steps': 10255, 'loss/train': 2.1584312915802}
-03/04/2022 01:30:53 - INFO - codeparrot_training - Step 10256: {'lr': 0.0004961707485295659, 'samples': 5251584, 'steps': 10256, 'loss/train': 1.4507354497909546}
-03/04/2022 01:30:54 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/04/2022 01:30:58 - INFO - codeparrot_training - Step 10257: {'lr': 0.0004961698232207268, 'samples': 5252096, 'steps': 10257, 'loss/train': 2.572611093521118}
-03/04/2022 01:31:02 - INFO - codeparrot_training - Step 10258: {'lr': 0.0004961688978009672, 'samples': 5252608, 'steps': 10258, 'loss/train': 1.6306365728378296}
-03/04/2022 01:31:03 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 01:31:07 - INFO - codeparrot_training - Step 10259: {'lr': 0.0004961679722702879, 'samples': 5253120, 'steps': 10259, 'loss/train': 1.8390499353408813}
-03/04/2022 01:31:10 - INFO - codeparrot_training - Step 10260: {'lr': 0.0004961670466286889, 'samples': 5253632, 'steps': 10260, 'loss/train': 2.085096597671509}
-03/04/2022 01:31:12 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 01:31:15 - INFO - codeparrot_training - Step 10261: {'lr': 0.000496166120876171, 'samples': 5254144, 'steps': 10261, 'loss/train': 2.448634624481201}
-03/04/2022 01:31:19 - INFO - codeparrot_training - Step 10262: {'lr': 0.0004961651950127343, 'samples': 5254656, 'steps': 10262, 'loss/train': 1.5979037284851074}
-03/04/2022 01:31:20 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 01:31:24 - INFO - codeparrot_training - Step 10263: {'lr': 0.0004961642690383794, 'samples': 5255168, 'steps': 10263, 'loss/train': 1.9150021076202393}
-03/04/2022 01:31:27 - INFO - codeparrot_training - Step 10264: {'lr': 0.0004961633429531068, 'samples': 5255680, 'steps': 10264, 'loss/train': 2.4854722023010254}
-03/04/2022 01:31:29 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 01:31:32 - INFO - codeparrot_training - Step 10265: {'lr': 0.0004961624167569166, 'samples': 5256192, 'steps': 10265, 'loss/train': 2.4486243724823}
-03/04/2022 01:31:36 - INFO - codeparrot_training - Step 10266: {'lr': 0.0004961614904498095, 'samples': 5256704, 'steps': 10266, 'loss/train': 1.8469502925872803}
-03/04/2022 01:31:37 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/04/2022 01:31:41 - INFO - codeparrot_training - Step 10267: {'lr': 0.0004961605640317858, 'samples': 5257216, 'steps': 10267, 'loss/train': 1.0912269353866577}
-03/04/2022 01:31:44 - INFO - codeparrot_training - Step 10268: {'lr': 0.0004961596375028461, 'samples': 5257728, 'steps': 10268, 'loss/train': 2.059016466140747}
-03/04/2022 01:31:45 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 01:31:49 - INFO - codeparrot_training - Step 10269: {'lr': 0.0004961587108629906, 'samples': 5258240, 'steps': 10269, 'loss/train': 2.278813600540161}
-03/04/2022 01:31:52 - INFO - codeparrot_training - Step 10270: {'lr': 0.0004961577841122197, 'samples': 5258752, 'steps': 10270, 'loss/train': 2.555562973022461}
-03/04/2022 01:31:54 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/04/2022 01:31:58 - INFO - codeparrot_training - Step 10271: {'lr': 0.000496156857250534, 'samples': 5259264, 'steps': 10271, 'loss/train': 2.1649246215820312}
-03/04/2022 01:32:01 - INFO - codeparrot_training - Step 10272: {'lr': 0.0004961559302779338, 'samples': 5259776, 'steps': 10272, 'loss/train': 1.2951374053955078}
-03/04/2022 01:32:02 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/04/2022 01:32:06 - INFO - codeparrot_training - Step 10273: {'lr': 0.0004961550031944194, 'samples': 5260288, 'steps': 10273, 'loss/train': 2.193466901779175}
-03/04/2022 01:32:09 - INFO - codeparrot_training - Step 10274: {'lr': 0.0004961540759999914, 'samples': 5260800, 'steps': 10274, 'loss/train': 2.2901253700256348}
-03/04/2022 01:32:11 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/04/2022 01:32:14 - INFO - codeparrot_training - Step 10275: {'lr': 0.0004961531486946502, 'samples': 5261312, 'steps': 10275, 'loss/train': 1.7461727857589722}
-03/04/2022 01:32:18 - INFO - codeparrot_training - Step 10276: {'lr': 0.0004961522212783962, 'samples': 5261824, 'steps': 10276, 'loss/train': 1.5857878923416138}
-03/04/2022 01:32:19 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/04/2022 01:32:23 - INFO - codeparrot_training - Step 10277: {'lr': 0.00049615129375123, 'samples': 5262336, 'steps': 10277, 'loss/train': 2.549603223800659}
-03/04/2022 01:32:26 - INFO - codeparrot_training - Step 10278: {'lr': 0.0004961503661131515, 'samples': 5262848, 'steps': 10278, 'loss/train': 2.1548240184783936}
-03/04/2022 01:32:27 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 01:32:31 - INFO - codeparrot_training - Step 10279: {'lr': 0.0004961494383641616, 'samples': 5263360, 'steps': 10279, 'loss/train': 1.802629828453064}
-03/04/2022 01:32:34 - INFO - codeparrot_training - Step 10280: {'lr': 0.0004961485105042606, 'samples': 5263872, 'steps': 10280, 'loss/train': 2.680495500564575}
-03/04/2022 01:32:35 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 01:32:40 - INFO - codeparrot_training - Step 10281: {'lr': 0.0004961475825334488, 'samples': 5264384, 'steps': 10281, 'loss/train': 1.9595175981521606}
-03/04/2022 01:32:43 - INFO - codeparrot_training - Step 10282: {'lr': 0.0004961466544517267, 'samples': 5264896, 'steps': 10282, 'loss/train': 1.6287789344787598}
-03/04/2022 01:32:44 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 01:32:48 - INFO - codeparrot_training - Step 10283: {'lr': 0.0004961457262590948, 'samples': 5265408, 'steps': 10283, 'loss/train': 2.0094950199127197}
-03/04/2022 01:32:51 - INFO - codeparrot_training - Step 10284: {'lr': 0.0004961447979555533, 'samples': 5265920, 'steps': 10284, 'loss/train': 2.1571712493896484}
-03/04/2022 01:32:52 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/04/2022 01:32:56 - INFO - codeparrot_training - Step 10285: {'lr': 0.000496143869541103, 'samples': 5266432, 'steps': 10285, 'loss/train': 1.8179244995117188}
-03/04/2022 01:33:00 - INFO - codeparrot_training - Step 10286: {'lr': 0.0004961429410157437, 'samples': 5266944, 'steps': 10286, 'loss/train': 2.141650915145874}
-03/04/2022 01:33:01 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/04/2022 01:33:05 - INFO - codeparrot_training - Step 10287: {'lr': 0.0004961420123794764, 'samples': 5267456, 'steps': 10287, 'loss/train': 1.411373496055603}
-03/04/2022 01:33:08 - INFO - codeparrot_training - Step 10288: {'lr': 0.0004961410836323014, 'samples': 5267968, 'steps': 10288, 'loss/train': 2.3285012245178223}
-03/04/2022 01:33:09 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/04/2022 01:33:13 - INFO - codeparrot_training - Step 10289: {'lr': 0.0004961401547742189, 'samples': 5268480, 'steps': 10289, 'loss/train': 2.3265087604522705}
-03/04/2022 01:33:16 - INFO - codeparrot_training - Step 10290: {'lr': 0.0004961392258052294, 'samples': 5268992, 'steps': 10290, 'loss/train': 2.0842132568359375}
-03/04/2022 01:33:17 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/04/2022 01:33:22 - INFO - codeparrot_training - Step 10291: {'lr': 0.0004961382967253335, 'samples': 5269504, 'steps': 10291, 'loss/train': 2.4990074634552}
-03/04/2022 01:33:25 - INFO - codeparrot_training - Step 10292: {'lr': 0.0004961373675345315, 'samples': 5270016, 'steps': 10292, 'loss/train': 1.721420168876648}
-03/04/2022 01:33:25 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 01:33:30 - INFO - codeparrot_training - Step 10293: {'lr': 0.0004961364382328236, 'samples': 5270528, 'steps': 10293, 'loss/train': 1.9417506456375122}
-03/04/2022 01:33:33 - INFO - codeparrot_training - Step 10294: {'lr': 0.0004961355088202106, 'samples': 5271040, 'steps': 10294, 'loss/train': 1.973968505859375}
-03/04/2022 01:33:34 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/04/2022 01:33:39 - INFO - codeparrot_training - Step 10295: {'lr': 0.0004961345792966926, 'samples': 5271552, 'steps': 10295, 'loss/train': 2.648123264312744}
-03/04/2022 01:33:42 - INFO - codeparrot_training - Step 10296: {'lr': 0.0004961336496622702, 'samples': 5272064, 'steps': 10296, 'loss/train': 2.3955423831939697}
-03/04/2022 01:33:42 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 01:33:47 - INFO - codeparrot_training - Step 10297: {'lr': 0.0004961327199169438, 'samples': 5272576, 'steps': 10297, 'loss/train': 2.3170382976531982}
-03/04/2022 01:33:50 - INFO - codeparrot_training - Step 10298: {'lr': 0.0004961317900607138, 'samples': 5273088, 'steps': 10298, 'loss/train': 1.8138214349746704}
-03/04/2022 01:33:51 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/04/2022 01:33:55 - INFO - codeparrot_training - Step 10299: {'lr': 0.0004961308600935807, 'samples': 5273600, 'steps': 10299, 'loss/train': 1.6626830101013184}
-03/04/2022 01:33:59 - INFO - codeparrot_training - Step 10300: {'lr': 0.0004961299300155446, 'samples': 5274112, 'steps': 10300, 'loss/train': 2.3149263858795166}
-03/04/2022 01:33:59 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/04/2022 01:34:04 - INFO - codeparrot_training - Step 10301: {'lr': 0.0004961289998266064, 'samples': 5274624, 'steps': 10301, 'loss/train': 2.0838985443115234}
-03/04/2022 01:34:07 - INFO - codeparrot_training - Step 10302: {'lr': 0.0004961280695267662, 'samples': 5275136, 'steps': 10302, 'loss/train': 2.9536428451538086}
-03/04/2022 01:34:08 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/04/2022 01:34:12 - INFO - codeparrot_training - Step 10303: {'lr': 0.0004961271391160243, 'samples': 5275648, 'steps': 10303, 'loss/train': 2.120999574661255}
-03/04/2022 01:34:16 - INFO - codeparrot_training - Step 10304: {'lr': 0.0004961262085943815, 'samples': 5276160, 'steps': 10304, 'loss/train': 1.6760084629058838}
-03/04/2022 01:34:16 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 01:34:21 - INFO - codeparrot_training - Step 10305: {'lr': 0.000496125277961838, 'samples': 5276672, 'steps': 10305, 'loss/train': 3.0307188034057617}
-03/04/2022 01:34:24 - INFO - codeparrot_training - Step 10306: {'lr': 0.0004961243472183942, 'samples': 5277184, 'steps': 10306, 'loss/train': 1.65351140499115}
-03/04/2022 01:34:24 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/04/2022 01:34:29 - INFO - codeparrot_training - Step 10307: {'lr': 0.0004961234163640507, 'samples': 5277696, 'steps': 10307, 'loss/train': 2.3354883193969727}
-03/04/2022 01:34:32 - INFO - codeparrot_training - Step 10308: {'lr': 0.0004961224853988076, 'samples': 5278208, 'steps': 10308, 'loss/train': 2.5512590408325195}
-03/04/2022 01:34:33 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/04/2022 01:34:38 - INFO - codeparrot_training - Step 10309: {'lr': 0.0004961215543226657, 'samples': 5278720, 'steps': 10309, 'loss/train': 1.8565610647201538}
-03/04/2022 01:34:41 - INFO - codeparrot_training - Step 10310: {'lr': 0.0004961206231356251, 'samples': 5279232, 'steps': 10310, 'loss/train': 1.8529667854309082}
-03/04/2022 01:34:41 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/04/2022 01:34:46 - INFO - codeparrot_training - Step 10311: {'lr': 0.0004961196918376864, 'samples': 5279744, 'steps': 10311, 'loss/train': 2.2696969509124756}
-03/04/2022 01:34:49 - INFO - codeparrot_training - Step 10312: {'lr': 0.0004961187604288498, 'samples': 5280256, 'steps': 10312, 'loss/train': 2.132204532623291}
-03/04/2022 01:34:49 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 01:34:55 - INFO - codeparrot_training - Step 10313: {'lr': 0.0004961178289091161, 'samples': 5280768, 'steps': 10313, 'loss/train': 1.5930033922195435}
-03/04/2022 01:34:58 - INFO - codeparrot_training - Step 10314: {'lr': 0.0004961168972784855, 'samples': 5281280, 'steps': 10314, 'loss/train': 2.3534128665924072}
-03/04/2022 01:34:58 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/04/2022 01:35:03 - INFO - codeparrot_training - Step 10315: {'lr': 0.0004961159655369582, 'samples': 5281792, 'steps': 10315, 'loss/train': 1.8856700658798218}
-03/04/2022 01:35:06 - INFO - codeparrot_training - Step 10316: {'lr': 0.0004961150336845351, 'samples': 5282304, 'steps': 10316, 'loss/train': 2.0004987716674805}
-03/04/2022 01:35:06 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/04/2022 01:35:12 - INFO - codeparrot_training - Step 10317: {'lr': 0.0004961141017212162, 'samples': 5282816, 'steps': 10317, 'loss/train': 2.0642623901367188}
-03/04/2022 01:35:15 - INFO - codeparrot_training - Step 10318: {'lr': 0.0004961131696470021, 'samples': 5283328, 'steps': 10318, 'loss/train': 2.310941696166992}
-03/04/2022 01:35:18 - INFO - codeparrot_training - Step 10319: {'lr': 0.0004961122374618933, 'samples': 5283840, 'steps': 10319, 'loss/train': 1.261130928993225}
-03/04/2022 01:35:18 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 01:35:24 - INFO - codeparrot_training - Step 10320: {'lr': 0.00049611130516589, 'samples': 5284352, 'steps': 10320, 'loss/train': 2.3533647060394287}
-03/04/2022 01:35:27 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 01:35:29 - INFO - codeparrot_training - Step 10321: {'lr': 0.0004961103727589929, 'samples': 5284864, 'steps': 10321, 'loss/train': 1.6718052625656128}
-03/04/2022 01:35:32 - INFO - codeparrot_training - Step 10322: {'lr': 0.0004961094402412021, 'samples': 5285376, 'steps': 10322, 'loss/train': 1.9106241464614868}
-03/04/2022 01:35:35 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 01:35:38 - INFO - codeparrot_training - Step 10323: {'lr': 0.0004961085076125182, 'samples': 5285888, 'steps': 10323, 'loss/train': 1.955513596534729}
-03/04/2022 01:35:41 - INFO - codeparrot_training - Step 10324: {'lr': 0.0004961075748729418, 'samples': 5286400, 'steps': 10324, 'loss/train': 2.8882102966308594}
-03/04/2022 01:35:44 - INFO - codeparrot_training - Step 10325: {'lr': 0.0004961066420224729, 'samples': 5286912, 'steps': 10325, 'loss/train': 0.8266063332557678}
-03/04/2022 01:35:44 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/04/2022 01:35:49 - INFO - codeparrot_training - Step 10326: {'lr': 0.0004961057090611123, 'samples': 5287424, 'steps': 10326, 'loss/train': 3.1908257007598877}
-03/04/2022 01:35:52 - INFO - codeparrot_training - Step 10327: {'lr': 0.0004961047759888601, 'samples': 5287936, 'steps': 10327, 'loss/train': 2.6867690086364746}
-03/04/2022 01:35:53 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 01:35:58 - INFO - codeparrot_training - Step 10328: {'lr': 0.000496103842805717, 'samples': 5288448, 'steps': 10328, 'loss/train': 2.0629916191101074}
-03/04/2022 01:36:01 - INFO - codeparrot_training - Step 10329: {'lr': 0.0004961029095116833, 'samples': 5288960, 'steps': 10329, 'loss/train': 2.085078001022339}
-03/04/2022 01:36:01 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/04/2022 01:36:06 - INFO - codeparrot_training - Step 10330: {'lr': 0.0004961019761067594, 'samples': 5289472, 'steps': 10330, 'loss/train': 2.8349733352661133}
-03/04/2022 01:36:09 - INFO - codeparrot_training - Step 10331: {'lr': 0.0004961010425909458, 'samples': 5289984, 'steps': 10331, 'loss/train': 2.2977187633514404}
-03/04/2022 01:36:09 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/04/2022 01:36:15 - INFO - codeparrot_training - Step 10332: {'lr': 0.0004961001089642428, 'samples': 5290496, 'steps': 10332, 'loss/train': 2.625804901123047}
-03/04/2022 01:36:18 - INFO - codeparrot_training - Step 10333: {'lr': 0.000496099175226651, 'samples': 5291008, 'steps': 10333, 'loss/train': 2.286292314529419}
-03/04/2022 01:36:18 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 01:36:23 - INFO - codeparrot_training - Step 10334: {'lr': 0.0004960982413781705, 'samples': 5291520, 'steps': 10334, 'loss/train': 2.2102694511413574}
-03/04/2022 01:36:26 - INFO - codeparrot_training - Step 10335: {'lr': 0.0004960973074188021, 'samples': 5292032, 'steps': 10335, 'loss/train': 2.1920552253723145}
-03/04/2022 01:36:27 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/04/2022 01:36:32 - INFO - codeparrot_training - Step 10336: {'lr': 0.000496096373348546, 'samples': 5292544, 'steps': 10336, 'loss/train': 1.0377882719039917}
-03/04/2022 01:36:35 - INFO - codeparrot_training - Step 10337: {'lr': 0.0004960954391674026, 'samples': 5293056, 'steps': 10337, 'loss/train': 1.8825520277023315}
-03/04/2022 01:36:35 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 01:36:40 - INFO - codeparrot_training - Step 10338: {'lr': 0.0004960945048753725, 'samples': 5293568, 'steps': 10338, 'loss/train': 1.8532012701034546}
-03/04/2022 01:36:43 - INFO - codeparrot_training - Step 10339: {'lr': 0.000496093570472456, 'samples': 5294080, 'steps': 10339, 'loss/train': 2.406942367553711}
-03/04/2022 01:36:43 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 01:36:48 - INFO - codeparrot_training - Step 10340: {'lr': 0.0004960926359586535, 'samples': 5294592, 'steps': 10340, 'loss/train': 1.2913141250610352}
-03/04/2022 01:36:51 - INFO - codeparrot_training - Step 10341: {'lr': 0.0004960917013339656, 'samples': 5295104, 'steps': 10341, 'loss/train': 0.9698938727378845}
-03/04/2022 01:36:52 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/04/2022 01:36:57 - INFO - codeparrot_training - Step 10342: {'lr': 0.0004960907665983923, 'samples': 5295616, 'steps': 10342, 'loss/train': 2.4703457355499268}
-03/04/2022 01:37:00 - INFO - codeparrot_training - Step 10343: {'lr': 0.0004960898317519345, 'samples': 5296128, 'steps': 10343, 'loss/train': 1.3037439584732056}
-03/04/2022 01:37:00 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/04/2022 01:37:05 - INFO - codeparrot_training - Step 10344: {'lr': 0.0004960888967945924, 'samples': 5296640, 'steps': 10344, 'loss/train': 3.8414697647094727}
-03/04/2022 01:37:08 - INFO - codeparrot_training - Step 10345: {'lr': 0.0004960879617263664, 'samples': 5297152, 'steps': 10345, 'loss/train': 2.451632261276245}
-03/04/2022 01:37:09 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 01:37:14 - INFO - codeparrot_training - Step 10346: {'lr': 0.000496087026547257, 'samples': 5297664, 'steps': 10346, 'loss/train': 1.506468415260315}
-03/04/2022 01:37:17 - INFO - codeparrot_training - Step 10347: {'lr': 0.0004960860912572645, 'samples': 5298176, 'steps': 10347, 'loss/train': 2.649533271789551}
-03/04/2022 01:37:19 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/04/2022 01:37:22 - INFO - codeparrot_training - Step 10348: {'lr': 0.0004960851558563895, 'samples': 5298688, 'steps': 10348, 'loss/train': 1.7366150617599487}
-03/04/2022 01:37:26 - INFO - codeparrot_training - Step 10349: {'lr': 0.0004960842203446322, 'samples': 5299200, 'steps': 10349, 'loss/train': 1.542008399963379}
-03/04/2022 01:37:27 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/04/2022 01:37:31 - INFO - codeparrot_training - Step 10350: {'lr': 0.0004960832847219933, 'samples': 5299712, 'steps': 10350, 'loss/train': 1.9412659406661987}
-03/04/2022 01:37:34 - INFO - codeparrot_training - Step 10351: {'lr': 0.000496082348988473, 'samples': 5300224, 'steps': 10351, 'loss/train': 2.0753188133239746}
-03/04/2022 01:37:35 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/04/2022 01:37:39 - INFO - codeparrot_training - Step 10352: {'lr': 0.0004960814131440717, 'samples': 5300736, 'steps': 10352, 'loss/train': 2.6924362182617188}
-03/04/2022 01:37:42 - INFO - codeparrot_training - Step 10353: {'lr': 0.0004960804771887901, 'samples': 5301248, 'steps': 10353, 'loss/train': 2.067129135131836}
-03/04/2022 01:37:45 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/04/2022 01:37:48 - INFO - codeparrot_training - Step 10354: {'lr': 0.0004960795411226283, 'samples': 5301760, 'steps': 10354, 'loss/train': 2.1636574268341064}
-03/04/2022 01:37:51 - INFO - codeparrot_training - Step 10355: {'lr': 0.0004960786049455868, 'samples': 5302272, 'steps': 10355, 'loss/train': 2.281994581222534}
-03/04/2022 01:37:53 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 01:37:56 - INFO - codeparrot_training - Step 10356: {'lr': 0.0004960776686576663, 'samples': 5302784, 'steps': 10356, 'loss/train': 1.6504979133605957}
-03/04/2022 01:37:59 - INFO - codeparrot_training - Step 10357: {'lr': 0.0004960767322588668, 'samples': 5303296, 'steps': 10357, 'loss/train': 1.5302289724349976}
-03/04/2022 01:38:01 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/04/2022 01:38:05 - INFO - codeparrot_training - Step 10358: {'lr': 0.000496075795749189, 'samples': 5303808, 'steps': 10358, 'loss/train': 2.458610773086548}
-03/04/2022 01:38:08 - INFO - codeparrot_training - Step 10359: {'lr': 0.0004960748591286332, 'samples': 5304320, 'steps': 10359, 'loss/train': 1.9734442234039307}
-03/04/2022 01:38:10 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 01:38:13 - INFO - codeparrot_training - Step 10360: {'lr': 0.0004960739223971999, 'samples': 5304832, 'steps': 10360, 'loss/train': 1.039385199546814}
-03/04/2022 01:38:16 - INFO - codeparrot_training - Step 10361: {'lr': 0.0004960729855548895, 'samples': 5305344, 'steps': 10361, 'loss/train': 2.488582134246826}
-03/04/2022 01:38:18 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/04/2022 01:38:22 - INFO - codeparrot_training - Step 10362: {'lr': 0.0004960720486017025, 'samples': 5305856, 'steps': 10362, 'loss/train': 1.9658275842666626}
-03/04/2022 01:38:25 - INFO - codeparrot_training - Step 10363: {'lr': 0.0004960711115376391, 'samples': 5306368, 'steps': 10363, 'loss/train': 2.43153977394104}
-03/04/2022 01:38:27 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/04/2022 01:38:30 - INFO - codeparrot_training - Step 10364: {'lr': 0.0004960701743626999, 'samples': 5306880, 'steps': 10364, 'loss/train': 1.522040843963623}
-03/04/2022 01:38:33 - INFO - codeparrot_training - Step 10365: {'lr': 0.0004960692370768853, 'samples': 5307392, 'steps': 10365, 'loss/train': 1.9161990880966187}
-03/04/2022 01:38:35 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/04/2022 01:38:39 - INFO - codeparrot_training - Step 10366: {'lr': 0.0004960682996801956, 'samples': 5307904, 'steps': 10366, 'loss/train': 2.1422502994537354}
-03/04/2022 01:38:42 - INFO - codeparrot_training - Step 10367: {'lr': 0.0004960673621726314, 'samples': 5308416, 'steps': 10367, 'loss/train': 2.073662519454956}
-03/04/2022 01:38:44 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/04/2022 01:38:47 - INFO - codeparrot_training - Step 10368: {'lr': 0.000496066424554193, 'samples': 5308928, 'steps': 10368, 'loss/train': 2.2021048069000244}
-03/04/2022 01:38:50 - INFO - codeparrot_training - Step 10369: {'lr': 0.0004960654868248809, 'samples': 5309440, 'steps': 10369, 'loss/train': 2.3290538787841797}
-03/04/2022 01:38:52 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/04/2022 01:38:55 - INFO - codeparrot_training - Step 10370: {'lr': 0.0004960645489846955, 'samples': 5309952, 'steps': 10370, 'loss/train': 2.1899237632751465}
-03/04/2022 01:38:59 - INFO - codeparrot_training - Step 10371: {'lr': 0.0004960636110336371, 'samples': 5310464, 'steps': 10371, 'loss/train': 2.689967393875122}
-03/04/2022 01:39:01 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/04/2022 01:39:04 - INFO - codeparrot_training - Step 10372: {'lr': 0.0004960626729717064, 'samples': 5310976, 'steps': 10372, 'loss/train': 0.841082751750946}
-03/04/2022 01:39:07 - INFO - codeparrot_training - Step 10373: {'lr': 0.0004960617347989036, 'samples': 5311488, 'steps': 10373, 'loss/train': 2.6612446308135986}
-03/04/2022 01:39:09 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/04/2022 01:39:13 - INFO - codeparrot_training - Step 10374: {'lr': 0.0004960607965152292, 'samples': 5312000, 'steps': 10374, 'loss/train': 1.7042899131774902}
-03/04/2022 01:39:16 - INFO - codeparrot_training - Step 10375: {'lr': 0.0004960598581206835, 'samples': 5312512, 'steps': 10375, 'loss/train': 2.6556363105773926}
-03/04/2022 01:39:19 - INFO - codeparrot_training - Step 10376: {'lr': 0.000496058919615267, 'samples': 5313024, 'steps': 10376, 'loss/train': 2.1054913997650146}
-03/04/2022 01:39:20 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/04/2022 01:39:24 - INFO - codeparrot_training - Step 10377: {'lr': 0.0004960579809989803, 'samples': 5313536, 'steps': 10377, 'loss/train': 2.4716012477874756}
-03/04/2022 01:39:27 - INFO - codeparrot_training - Step 10378: {'lr': 0.0004960570422718237, 'samples': 5314048, 'steps': 10378, 'loss/train': 1.9205008745193481}
-03/04/2022 01:39:28 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 01:39:33 - INFO - codeparrot_training - Step 10379: {'lr': 0.0004960561034337975, 'samples': 5314560, 'steps': 10379, 'loss/train': 2.277218818664551}
-03/04/2022 01:39:36 - INFO - codeparrot_training - Step 10380: {'lr': 0.0004960551644849022, 'samples': 5315072, 'steps': 10380, 'loss/train': 1.915366768836975}
-03/04/2022 01:39:37 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/04/2022 01:39:41 - INFO - codeparrot_training - Step 10381: {'lr': 0.0004960542254251382, 'samples': 5315584, 'steps': 10381, 'loss/train': 2.0849928855895996}
-03/04/2022 01:39:44 - INFO - codeparrot_training - Step 10382: {'lr': 0.0004960532862545061, 'samples': 5316096, 'steps': 10382, 'loss/train': 2.801764965057373}
-03/04/2022 01:39:45 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/04/2022 01:39:49 - INFO - codeparrot_training - Step 10383: {'lr': 0.0004960523469730061, 'samples': 5316608, 'steps': 10383, 'loss/train': 2.6314799785614014}
-03/04/2022 01:39:53 - INFO - codeparrot_training - Step 10384: {'lr': 0.0004960514075806387, 'samples': 5317120, 'steps': 10384, 'loss/train': 2.270421028137207}
-03/04/2022 01:39:53 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/04/2022 01:39:58 - INFO - codeparrot_training - Step 10385: {'lr': 0.0004960504680774043, 'samples': 5317632, 'steps': 10385, 'loss/train': 2.3248207569122314}
-03/04/2022 01:40:01 - INFO - codeparrot_training - Step 10386: {'lr': 0.0004960495284633034, 'samples': 5318144, 'steps': 10386, 'loss/train': 2.064502239227295}
-03/04/2022 01:40:02 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/04/2022 01:40:06 - INFO - codeparrot_training - Step 10387: {'lr': 0.0004960485887383363, 'samples': 5318656, 'steps': 10387, 'loss/train': 2.972984552383423}
-03/04/2022 01:40:09 - INFO - codeparrot_training - Step 10388: {'lr': 0.0004960476489025037, 'samples': 5319168, 'steps': 10388, 'loss/train': 1.8586816787719727}
-03/04/2022 01:40:10 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 01:40:15 - INFO - codeparrot_training - Step 10389: {'lr': 0.0004960467089558057, 'samples': 5319680, 'steps': 10389, 'loss/train': 1.7712984085083008}
-03/04/2022 01:40:18 - INFO - codeparrot_training - Step 10390: {'lr': 0.0004960457688982428, 'samples': 5320192, 'steps': 10390, 'loss/train': 1.9060018062591553}
-03/04/2022 01:40:18 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/04/2022 01:40:23 - INFO - codeparrot_training - Step 10391: {'lr': 0.0004960448287298156, 'samples': 5320704, 'steps': 10391, 'loss/train': 1.1376224756240845}
-03/04/2022 01:40:26 - INFO - codeparrot_training - Step 10392: {'lr': 0.0004960438884505242, 'samples': 5321216, 'steps': 10392, 'loss/train': 1.4639347791671753}
-03/04/2022 01:40:26 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/04/2022 01:40:32 - INFO - codeparrot_training - Step 10393: {'lr': 0.0004960429480603694, 'samples': 5321728, 'steps': 10393, 'loss/train': 2.182008981704712}
-03/04/2022 01:40:35 - INFO - codeparrot_training - Step 10394: {'lr': 0.0004960420075593515, 'samples': 5322240, 'steps': 10394, 'loss/train': 1.7019970417022705}
-03/04/2022 01:40:35 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/04/2022 01:40:40 - INFO - codeparrot_training - Step 10395: {'lr': 0.0004960410669474708, 'samples': 5322752, 'steps': 10395, 'loss/train': 2.576894521713257}
-03/04/2022 01:40:43 - INFO - codeparrot_training - Step 10396: {'lr': 0.0004960401262247277, 'samples': 5323264, 'steps': 10396, 'loss/train': 2.644033670425415}
-03/04/2022 01:40:43 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/04/2022 01:40:48 - INFO - codeparrot_training - Step 10397: {'lr': 0.0004960391853911228, 'samples': 5323776, 'steps': 10397, 'loss/train': 2.420576333999634}
-03/04/2022 01:40:52 - INFO - codeparrot_training - Step 10398: {'lr': 0.0004960382444466564, 'samples': 5324288, 'steps': 10398, 'loss/train': 1.5511449575424194}
-03/04/2022 01:40:52 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/04/2022 01:40:57 - INFO - codeparrot_training - Step 10399: {'lr': 0.0004960373033913289, 'samples': 5324800, 'steps': 10399, 'loss/train': 2.7830753326416016}
-03/04/2022 01:41:00 - INFO - codeparrot_training - Step 10400: {'lr': 0.0004960363622251409, 'samples': 5325312, 'steps': 10400, 'loss/train': 2.542900323867798}
-03/04/2022 01:41:03 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/04/2022 01:41:06 - INFO - codeparrot_training - Step 10401: {'lr': 0.0004960354209480927, 'samples': 5325824, 'steps': 10401, 'loss/train': 1.637619972229004}
-03/04/2022 01:41:09 - INFO - codeparrot_training - Step 10402: {'lr': 0.0004960344795601847, 'samples': 5326336, 'steps': 10402, 'loss/train': 1.8998197317123413}
-03/04/2022 01:41:11 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/04/2022 01:41:14 - INFO - codeparrot_training - Step 10403: {'lr': 0.0004960335380614174, 'samples': 5326848, 'steps': 10403, 'loss/train': 1.958505392074585}
-03/04/2022 01:41:17 - INFO - codeparrot_training - Step 10404: {'lr': 0.0004960325964517912, 'samples': 5327360, 'steps': 10404, 'loss/train': 2.663156509399414}
-03/04/2022 01:41:19 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/04/2022 01:41:22 - INFO - codeparrot_training - Step 10405: {'lr': 0.0004960316547313064, 'samples': 5327872, 'steps': 10405, 'loss/train': 2.5299766063690186}
-03/04/2022 01:41:25 - INFO - codeparrot_training - Step 10406: {'lr': 0.0004960307128999636, 'samples': 5328384, 'steps': 10406, 'loss/train': 1.0516951084136963}
-03/04/2022 01:41:28 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/04/2022 01:41:31 - INFO - codeparrot_training - Step 10407: {'lr': 0.0004960297709577632, 'samples': 5328896, 'steps': 10407, 'loss/train': 1.25321364402771}
-03/04/2022 01:41:34 - INFO - codeparrot_training - Step 10408: {'lr': 0.0004960288289047054, 'samples': 5329408, 'steps': 10408, 'loss/train': 2.468123435974121}
-03/04/2022 01:41:37 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 01:41:39 - INFO - codeparrot_training - Step 10409: {'lr': 0.000496027886740791, 'samples': 5329920, 'steps': 10409, 'loss/train': 1.5571171045303345}
-03/04/2022 01:41:42 - INFO - codeparrot_training - Step 10410: {'lr': 0.0004960269444660201, 'samples': 5330432, 'steps': 10410, 'loss/train': 1.5610740184783936}
-03/04/2022 01:41:45 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/04/2022 01:41:48 - INFO - codeparrot_training - Step 10411: {'lr': 0.0004960260020803934, 'samples': 5330944, 'steps': 10411, 'loss/train': 1.7723541259765625}
-03/04/2022 01:41:51 - INFO - codeparrot_training - Step 10412: {'lr': 0.0004960250595839111, 'samples': 5331456, 'steps': 10412, 'loss/train': 2.6952223777770996}
-03/04/2022 01:41:53 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 01:41:56 - INFO - codeparrot_training - Step 10413: {'lr': 0.0004960241169765737, 'samples': 5331968, 'steps': 10413, 'loss/train': 2.83984637260437}
-03/04/2022 01:41:59 - INFO - codeparrot_training - Step 10414: {'lr': 0.0004960231742583817, 'samples': 5332480, 'steps': 10414, 'loss/train': 2.1348469257354736}
-03/04/2022 01:42:01 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/04/2022 01:42:04 - INFO - codeparrot_training - Step 10415: {'lr': 0.0004960222314293354, 'samples': 5332992, 'steps': 10415, 'loss/train': 1.8361222743988037}
-03/04/2022 01:42:08 - INFO - codeparrot_training - Step 10416: {'lr': 0.0004960212884894353, 'samples': 5333504, 'steps': 10416, 'loss/train': 1.6424466371536255}
-03/04/2022 01:42:10 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 01:42:13 - INFO - codeparrot_training - Step 10417: {'lr': 0.0004960203454386817, 'samples': 5334016, 'steps': 10417, 'loss/train': 1.7389724254608154}
-03/04/2022 01:42:16 - INFO - codeparrot_training - Step 10418: {'lr': 0.0004960194022770753, 'samples': 5334528, 'steps': 10418, 'loss/train': 1.9152166843414307}
-03/04/2022 01:42:18 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/04/2022 01:42:21 - INFO - codeparrot_training - Step 10419: {'lr': 0.0004960184590046162, 'samples': 5335040, 'steps': 10419, 'loss/train': 1.9002435207366943}
-03/04/2022 01:42:24 - INFO - codeparrot_training - Step 10420: {'lr': 0.0004960175156213051, 'samples': 5335552, 'steps': 10420, 'loss/train': 3.1533095836639404}
-03/04/2022 01:42:28 - INFO - codeparrot_training - Step 10421: {'lr': 0.0004960165721271422, 'samples': 5336064, 'steps': 10421, 'loss/train': 2.079596996307373}
-03/04/2022 01:42:28 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 01:42:33 - INFO - codeparrot_training - Step 10422: {'lr': 0.000496015628522128, 'samples': 5336576, 'steps': 10422, 'loss/train': 1.1853842735290527}
-03/04/2022 01:42:36 - INFO - codeparrot_training - Step 10423: {'lr': 0.000496014684806263, 'samples': 5337088, 'steps': 10423, 'loss/train': 3.1712725162506104}
-03/04/2022 01:42:36 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/04/2022 01:42:42 - INFO - codeparrot_training - Step 10424: {'lr': 0.0004960137409795477, 'samples': 5337600, 'steps': 10424, 'loss/train': 1.776940107345581}
-03/04/2022 01:42:45 - INFO - codeparrot_training - Step 10425: {'lr': 0.0004960127970419822, 'samples': 5338112, 'steps': 10425, 'loss/train': 1.2551759481430054}
-03/04/2022 01:42:45 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/04/2022 01:42:50 - INFO - codeparrot_training - Step 10426: {'lr': 0.0004960118529935674, 'samples': 5338624, 'steps': 10426, 'loss/train': 2.304603338241577}
-03/04/2022 01:42:53 - INFO - codeparrot_training - Step 10427: {'lr': 0.0004960109088343032, 'samples': 5339136, 'steps': 10427, 'loss/train': 2.2271759510040283}
-03/04/2022 01:42:53 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/04/2022 01:42:58 - INFO - codeparrot_training - Step 10428: {'lr': 0.0004960099645641903, 'samples': 5339648, 'steps': 10428, 'loss/train': 1.6713790893554688}
-03/04/2022 01:43:02 - INFO - codeparrot_training - Step 10429: {'lr': 0.0004960090201832293, 'samples': 5340160, 'steps': 10429, 'loss/train': 2.1042377948760986}
-03/04/2022 01:43:02 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/04/2022 01:43:07 - INFO - codeparrot_training - Step 10430: {'lr': 0.0004960080756914203, 'samples': 5340672, 'steps': 10430, 'loss/train': 1.7672436237335205}
-03/04/2022 01:43:10 - INFO - codeparrot_training - Step 10431: {'lr': 0.0004960071310887638, 'samples': 5341184, 'steps': 10431, 'loss/train': 1.7937709093093872}
-03/04/2022 01:43:10 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 01:43:15 - INFO - codeparrot_training - Step 10432: {'lr': 0.0004960061863752604, 'samples': 5341696, 'steps': 10432, 'loss/train': 2.1659090518951416}
-03/04/2022 01:43:18 - INFO - codeparrot_training - Step 10433: {'lr': 0.0004960052415509103, 'samples': 5342208, 'steps': 10433, 'loss/train': 1.7079628705978394}
-03/04/2022 01:43:18 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 01:43:24 - INFO - codeparrot_training - Step 10434: {'lr': 0.0004960042966157141, 'samples': 5342720, 'steps': 10434, 'loss/train': 1.9270389080047607}
-03/04/2022 01:43:27 - INFO - codeparrot_training - Step 10435: {'lr': 0.0004960033515696722, 'samples': 5343232, 'steps': 10435, 'loss/train': 2.095689058303833}
-03/04/2022 01:43:27 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 01:43:32 - INFO - codeparrot_training - Step 10436: {'lr': 0.0004960024064127849, 'samples': 5343744, 'steps': 10436, 'loss/train': 2.423034906387329}
-03/04/2022 01:43:35 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/04/2022 01:43:37 - INFO - codeparrot_training - Step 10437: {'lr': 0.0004960014611450527, 'samples': 5344256, 'steps': 10437, 'loss/train': 2.0698516368865967}
-03/04/2022 01:43:41 - INFO - codeparrot_training - Step 10438: {'lr': 0.0004960005157664762, 'samples': 5344768, 'steps': 10438, 'loss/train': 2.1725919246673584}
-03/04/2022 01:43:43 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 01:43:46 - INFO - codeparrot_training - Step 10439: {'lr': 0.0004959995702770555, 'samples': 5345280, 'steps': 10439, 'loss/train': 1.6542595624923706}
-03/04/2022 01:43:49 - INFO - codeparrot_training - Step 10440: {'lr': 0.0004959986246767913, 'samples': 5345792, 'steps': 10440, 'loss/train': 2.6591031551361084}
-03/04/2022 01:43:52 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/04/2022 01:43:54 - INFO - codeparrot_training - Step 10441: {'lr': 0.0004959976789656838, 'samples': 5346304, 'steps': 10441, 'loss/train': 1.2482213973999023}
-03/04/2022 01:43:57 - INFO - codeparrot_training - Step 10442: {'lr': 0.0004959967331437336, 'samples': 5346816, 'steps': 10442, 'loss/train': 2.090012788772583}
-03/04/2022 01:44:00 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/04/2022 01:44:03 - INFO - codeparrot_training - Step 10443: {'lr': 0.0004959957872109411, 'samples': 5347328, 'steps': 10443, 'loss/train': 0.7640123963356018}
-03/04/2022 01:44:06 - INFO - codeparrot_training - Step 10444: {'lr': 0.0004959948411673066, 'samples': 5347840, 'steps': 10444, 'loss/train': 1.193550705909729}
-03/04/2022 01:44:08 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/04/2022 01:44:11 - INFO - codeparrot_training - Step 10445: {'lr': 0.0004959938950128308, 'samples': 5348352, 'steps': 10445, 'loss/train': 2.3168931007385254}
-03/04/2022 01:44:14 - INFO - codeparrot_training - Step 10446: {'lr': 0.0004959929487475138, 'samples': 5348864, 'steps': 10446, 'loss/train': 2.2355217933654785}
-03/04/2022 01:44:17 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 01:44:19 - INFO - codeparrot_training - Step 10447: {'lr': 0.0004959920023713563, 'samples': 5349376, 'steps': 10447, 'loss/train': 1.7253608703613281}
-03/04/2022 01:44:23 - INFO - codeparrot_training - Step 10448: {'lr': 0.0004959910558843584, 'samples': 5349888, 'steps': 10448, 'loss/train': 1.3192853927612305}
-03/04/2022 01:44:25 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 01:44:28 - INFO - codeparrot_training - Step 10449: {'lr': 0.0004959901092865208, 'samples': 5350400, 'steps': 10449, 'loss/train': 1.7864630222320557}
-03/04/2022 01:44:31 - INFO - codeparrot_training - Step 10450: {'lr': 0.0004959891625778438, 'samples': 5350912, 'steps': 10450, 'loss/train': 2.226651430130005}
-03/04/2022 01:44:33 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 01:44:36 - INFO - codeparrot_training - Step 10451: {'lr': 0.0004959882157583281, 'samples': 5351424, 'steps': 10451, 'loss/train': 2.3313121795654297}
-03/04/2022 01:44:39 - INFO - codeparrot_training - Step 10452: {'lr': 0.0004959872688279737, 'samples': 5351936, 'steps': 10452, 'loss/train': 1.9649200439453125}
-03/04/2022 01:44:41 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/04/2022 01:44:45 - INFO - codeparrot_training - Step 10453: {'lr': 0.0004959863217867814, 'samples': 5352448, 'steps': 10453, 'loss/train': 1.8584046363830566}
-03/04/2022 01:44:48 - INFO - codeparrot_training - Step 10454: {'lr': 0.0004959853746347513, 'samples': 5352960, 'steps': 10454, 'loss/train': 1.2407747507095337}
-03/04/2022 01:44:50 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/04/2022 01:44:53 - INFO - codeparrot_training - Step 10455: {'lr': 0.0004959844273718841, 'samples': 5353472, 'steps': 10455, 'loss/train': 2.1681325435638428}
-03/04/2022 01:44:56 - INFO - codeparrot_training - Step 10456: {'lr': 0.00049598347999818, 'samples': 5353984, 'steps': 10456, 'loss/train': 1.7916539907455444}
-03/04/2022 01:44:58 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 01:45:01 - INFO - codeparrot_training - Step 10457: {'lr': 0.0004959825325136396, 'samples': 5354496, 'steps': 10457, 'loss/train': 2.18612003326416}
-03/04/2022 01:45:05 - INFO - codeparrot_training - Step 10458: {'lr': 0.0004959815849182633, 'samples': 5355008, 'steps': 10458, 'loss/train': 2.306271553039551}
-03/04/2022 01:45:07 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/04/2022 01:45:10 - INFO - codeparrot_training - Step 10459: {'lr': 0.0004959806372120515, 'samples': 5355520, 'steps': 10459, 'loss/train': 2.3321847915649414}
-03/04/2022 01:45:13 - INFO - codeparrot_training - Step 10460: {'lr': 0.0004959796893950045, 'samples': 5356032, 'steps': 10460, 'loss/train': 2.6459383964538574}
-03/04/2022 01:45:15 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 01:45:18 - INFO - codeparrot_training - Step 10461: {'lr': 0.0004959787414671229, 'samples': 5356544, 'steps': 10461, 'loss/train': 2.177137851715088}
-03/04/2022 01:45:21 - INFO - codeparrot_training - Step 10462: {'lr': 0.000495977793428407, 'samples': 5357056, 'steps': 10462, 'loss/train': 2.825188398361206}
-03/04/2022 01:45:23 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/04/2022 01:45:27 - INFO - codeparrot_training - Step 10463: {'lr': 0.0004959768452788575, 'samples': 5357568, 'steps': 10463, 'loss/train': 2.075127363204956}
-03/04/2022 01:45:30 - INFO - codeparrot_training - Step 10464: {'lr': 0.0004959758970184745, 'samples': 5358080, 'steps': 10464, 'loss/train': 2.106503963470459}
-03/04/2022 01:45:32 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/04/2022 01:45:35 - INFO - codeparrot_training - Step 10465: {'lr': 0.0004959749486472587, 'samples': 5358592, 'steps': 10465, 'loss/train': 1.5483318567276}
-03/04/2022 01:45:38 - INFO - codeparrot_training - Step 10466: {'lr': 0.0004959740001652102, 'samples': 5359104, 'steps': 10466, 'loss/train': 2.33366060256958}
-03/04/2022 01:45:40 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 01:45:44 - INFO - codeparrot_training - Step 10467: {'lr': 0.0004959730515723298, 'samples': 5359616, 'steps': 10467, 'loss/train': 2.435391902923584}
-03/04/2022 01:45:47 - INFO - codeparrot_training - Step 10468: {'lr': 0.0004959721028686175, 'samples': 5360128, 'steps': 10468, 'loss/train': 2.2590553760528564}
-03/04/2022 01:45:49 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/04/2022 01:45:52 - INFO - codeparrot_training - Step 10469: {'lr': 0.0004959711540540741, 'samples': 5360640, 'steps': 10469, 'loss/train': 2.0317537784576416}
-03/04/2022 01:45:55 - INFO - codeparrot_training - Step 10470: {'lr': 0.0004959702051286999, 'samples': 5361152, 'steps': 10470, 'loss/train': 2.6492207050323486}
-03/04/2022 01:45:57 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/04/2022 01:46:00 - INFO - codeparrot_training - Step 10471: {'lr': 0.0004959692560924954, 'samples': 5361664, 'steps': 10471, 'loss/train': 1.2326165437698364}
-03/04/2022 01:46:04 - INFO - codeparrot_training - Step 10472: {'lr': 0.0004959683069454608, 'samples': 5362176, 'steps': 10472, 'loss/train': 2.442915439605713}
-03/04/2022 01:46:05 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 01:46:09 - INFO - codeparrot_training - Step 10473: {'lr': 0.0004959673576875967, 'samples': 5362688, 'steps': 10473, 'loss/train': 2.657141923904419}
-03/04/2022 01:46:12 - INFO - codeparrot_training - Step 10474: {'lr': 0.0004959664083189035, 'samples': 5363200, 'steps': 10474, 'loss/train': 2.3843865394592285}
-03/04/2022 01:46:14 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/04/2022 01:46:17 - INFO - codeparrot_training - Step 10475: {'lr': 0.0004959654588393818, 'samples': 5363712, 'steps': 10475, 'loss/train': 2.575812339782715}
-03/04/2022 01:46:21 - INFO - codeparrot_training - Step 10476: {'lr': 0.0004959645092490316, 'samples': 5364224, 'steps': 10476, 'loss/train': 1.7825956344604492}
-03/04/2022 01:46:22 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/04/2022 01:46:26 - INFO - codeparrot_training - Step 10477: {'lr': 0.0004959635595478537, 'samples': 5364736, 'steps': 10477, 'loss/train': 1.3601545095443726}
-03/04/2022 01:46:29 - INFO - codeparrot_training - Step 10478: {'lr': 0.0004959626097358485, 'samples': 5365248, 'steps': 10478, 'loss/train': 1.171661615371704}
-03/04/2022 01:46:31 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 01:46:34 - INFO - codeparrot_training - Step 10479: {'lr': 0.0004959616598130162, 'samples': 5365760, 'steps': 10479, 'loss/train': 1.8682208061218262}
-03/04/2022 01:46:37 - INFO - codeparrot_training - Step 10480: {'lr': 0.0004959607097793575, 'samples': 5366272, 'steps': 10480, 'loss/train': 2.1681783199310303}
-03/04/2022 01:46:39 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/04/2022 01:46:43 - INFO - codeparrot_training - Step 10481: {'lr': 0.0004959597596348726, 'samples': 5366784, 'steps': 10481, 'loss/train': 2.215993881225586}
-03/04/2022 01:46:46 - INFO - codeparrot_training - Step 10482: {'lr': 0.0004959588093795621, 'samples': 5367296, 'steps': 10482, 'loss/train': 2.075479507446289}
-03/04/2022 01:46:47 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/04/2022 01:46:51 - INFO - codeparrot_training - Step 10483: {'lr': 0.0004959578590134262, 'samples': 5367808, 'steps': 10483, 'loss/train': 1.8520556688308716}
-03/04/2022 01:46:54 - INFO - codeparrot_training - Step 10484: {'lr': 0.0004959569085364657, 'samples': 5368320, 'steps': 10484, 'loss/train': 2.6680643558502197}
-03/04/2022 01:46:56 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 01:46:59 - INFO - codeparrot_training - Step 10485: {'lr': 0.0004959559579486807, 'samples': 5368832, 'steps': 10485, 'loss/train': 2.8451640605926514}
-03/04/2022 01:47:03 - INFO - codeparrot_training - Step 10486: {'lr': 0.0004959550072500718, 'samples': 5369344, 'steps': 10486, 'loss/train': 2.162782907485962}
-03/04/2022 01:47:04 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/04/2022 01:47:08 - INFO - codeparrot_training - Step 10487: {'lr': 0.0004959540564406393, 'samples': 5369856, 'steps': 10487, 'loss/train': 2.184424877166748}
-03/04/2022 01:47:11 - INFO - codeparrot_training - Step 10488: {'lr': 0.0004959531055203837, 'samples': 5370368, 'steps': 10488, 'loss/train': 1.885429859161377}
-03/04/2022 01:47:12 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 01:47:16 - INFO - codeparrot_training - Step 10489: {'lr': 0.0004959521544893055, 'samples': 5370880, 'steps': 10489, 'loss/train': 1.6078791618347168}
-03/04/2022 01:47:19 - INFO - codeparrot_training - Step 10490: {'lr': 0.000495951203347405, 'samples': 5371392, 'steps': 10490, 'loss/train': 1.2909163236618042}
-03/04/2022 01:47:21 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/04/2022 01:47:25 - INFO - codeparrot_training - Step 10491: {'lr': 0.0004959502520946827, 'samples': 5371904, 'steps': 10491, 'loss/train': 2.2858617305755615}
-03/04/2022 01:47:28 - INFO - codeparrot_training - Step 10492: {'lr': 0.000495949300731139, 'samples': 5372416, 'steps': 10492, 'loss/train': 2.058260202407837}
-03/04/2022 01:47:29 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/04/2022 01:47:33 - INFO - codeparrot_training - Step 10493: {'lr': 0.0004959483492567744, 'samples': 5372928, 'steps': 10493, 'loss/train': 1.6616758108139038}
-03/04/2022 01:47:36 - INFO - codeparrot_training - Step 10494: {'lr': 0.0004959473976715892, 'samples': 5373440, 'steps': 10494, 'loss/train': 2.470019817352295}
-03/04/2022 01:47:38 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 01:47:42 - INFO - codeparrot_training - Step 10495: {'lr': 0.0004959464459755839, 'samples': 5373952, 'steps': 10495, 'loss/train': 2.081951141357422}
-03/04/2022 01:47:45 - INFO - codeparrot_training - Step 10496: {'lr': 0.0004959454941687589, 'samples': 5374464, 'steps': 10496, 'loss/train': 2.187267780303955}
-03/04/2022 01:47:47 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 01:47:50 - INFO - codeparrot_training - Step 10497: {'lr': 0.0004959445422511148, 'samples': 5374976, 'steps': 10497, 'loss/train': 2.2763919830322266}
-03/04/2022 01:47:53 - INFO - codeparrot_training - Step 10498: {'lr': 0.0004959435902226517, 'samples': 5375488, 'steps': 10498, 'loss/train': 2.3536930084228516}
-03/04/2022 01:47:55 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/04/2022 01:47:59 - INFO - codeparrot_training - Step 10499: {'lr': 0.0004959426380833703, 'samples': 5376000, 'steps': 10499, 'loss/train': 1.2243125438690186}
-03/04/2022 01:48:02 - INFO - codeparrot_training - Step 10500: {'lr': 0.0004959416858332709, 'samples': 5376512, 'steps': 10500, 'loss/train': 1.3671414852142334}
-03/04/2022 01:48:03 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/04/2022 01:48:07 - INFO - codeparrot_training - Step 10501: {'lr': 0.000495940733472354, 'samples': 5377024, 'steps': 10501, 'loss/train': 2.2374634742736816}
-03/04/2022 01:48:10 - INFO - codeparrot_training - Step 10502: {'lr': 0.00049593978100062, 'samples': 5377536, 'steps': 10502, 'loss/train': 1.0416338443756104}
-03/04/2022 01:48:12 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/04/2022 01:48:15 - INFO - codeparrot_training - Step 10503: {'lr': 0.0004959388284180694, 'samples': 5378048, 'steps': 10503, 'loss/train': 2.0234129428863525}
-03/04/2022 01:48:18 - INFO - codeparrot_training - Step 10504: {'lr': 0.0004959378757247024, 'samples': 5378560, 'steps': 10504, 'loss/train': 2.3636202812194824}
-03/04/2022 01:48:20 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/04/2022 01:48:24 - INFO - codeparrot_training - Step 10505: {'lr': 0.0004959369229205197, 'samples': 5379072, 'steps': 10505, 'loss/train': 2.241831064224243}
-03/04/2022 01:48:27 - INFO - codeparrot_training - Step 10506: {'lr': 0.0004959359700055216, 'samples': 5379584, 'steps': 10506, 'loss/train': 2.2243456840515137}
-03/04/2022 01:48:29 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/04/2022 01:48:32 - INFO - codeparrot_training - Step 10507: {'lr': 0.0004959350169797085, 'samples': 5380096, 'steps': 10507, 'loss/train': 1.149512529373169}
-03/04/2022 01:48:35 - INFO - codeparrot_training - Step 10508: {'lr': 0.000495934063843081, 'samples': 5380608, 'steps': 10508, 'loss/train': 1.4563003778457642}
-03/04/2022 01:48:37 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/04/2022 01:48:41 - INFO - codeparrot_training - Step 10509: {'lr': 0.0004959331105956393, 'samples': 5381120, 'steps': 10509, 'loss/train': 2.7796456813812256}
-03/04/2022 01:48:44 - INFO - codeparrot_training - Step 10510: {'lr': 0.000495932157237384, 'samples': 5381632, 'steps': 10510, 'loss/train': 2.827526807785034}
-03/04/2022 01:48:45 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 01:48:49 - INFO - codeparrot_training - Step 10511: {'lr': 0.0004959312037683154, 'samples': 5382144, 'steps': 10511, 'loss/train': 1.279037356376648}
-03/04/2022 01:48:52 - INFO - codeparrot_training - Step 10512: {'lr': 0.0004959302501884341, 'samples': 5382656, 'steps': 10512, 'loss/train': 2.352128744125366}
-03/04/2022 01:48:54 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/04/2022 01:48:57 - INFO - codeparrot_training - Step 10513: {'lr': 0.0004959292964977403, 'samples': 5383168, 'steps': 10513, 'loss/train': 2.366727590560913}
-03/04/2022 01:49:01 - INFO - codeparrot_training - Step 10514: {'lr': 0.0004959283426962345, 'samples': 5383680, 'steps': 10514, 'loss/train': 2.139610528945923}
-03/04/2022 01:49:02 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 01:49:06 - INFO - codeparrot_training - Step 10515: {'lr': 0.0004959273887839175, 'samples': 5384192, 'steps': 10515, 'loss/train': 2.2094473838806152}
-03/04/2022 01:49:09 - INFO - codeparrot_training - Step 10516: {'lr': 0.000495926434760789, 'samples': 5384704, 'steps': 10516, 'loss/train': 4.065138816833496}
-03/04/2022 01:49:11 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/04/2022 01:49:14 - INFO - codeparrot_training - Step 10517: {'lr': 0.0004959254806268501, 'samples': 5385216, 'steps': 10517, 'loss/train': 0.7853817939758301}
-03/04/2022 01:49:18 - INFO - codeparrot_training - Step 10518: {'lr': 0.0004959245263821009, 'samples': 5385728, 'steps': 10518, 'loss/train': 2.3481969833374023}
-03/04/2022 01:49:19 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/04/2022 01:49:23 - INFO - codeparrot_training - Step 10519: {'lr': 0.0004959235720265419, 'samples': 5386240, 'steps': 10519, 'loss/train': 2.684281826019287}
-03/04/2022 01:49:26 - INFO - codeparrot_training - Step 10520: {'lr': 0.0004959226175601736, 'samples': 5386752, 'steps': 10520, 'loss/train': 1.3688074350357056}
-03/04/2022 01:49:28 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/04/2022 01:49:31 - INFO - codeparrot_training - Step 10521: {'lr': 0.0004959216629829964, 'samples': 5387264, 'steps': 10521, 'loss/train': 2.0596096515655518}
-03/04/2022 01:49:34 - INFO - codeparrot_training - Step 10522: {'lr': 0.0004959207082950105, 'samples': 5387776, 'steps': 10522, 'loss/train': 2.1102452278137207}
-03/04/2022 01:49:36 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 01:49:40 - INFO - codeparrot_training - Step 10523: {'lr': 0.0004959197534962166, 'samples': 5388288, 'steps': 10523, 'loss/train': 1.8596584796905518}
-03/04/2022 01:49:43 - INFO - codeparrot_training - Step 10524: {'lr': 0.0004959187985866152, 'samples': 5388800, 'steps': 10524, 'loss/train': 0.8472693562507629}
-03/04/2022 01:49:44 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/04/2022 01:49:48 - INFO - codeparrot_training - Step 10525: {'lr': 0.0004959178435662064, 'samples': 5389312, 'steps': 10525, 'loss/train': 1.2161988019943237}
-03/04/2022 01:49:51 - INFO - codeparrot_training - Step 10526: {'lr': 0.0004959168884349909, 'samples': 5389824, 'steps': 10526, 'loss/train': 1.853462815284729}
-03/04/2022 01:49:53 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 01:49:57 - INFO - codeparrot_training - Step 10527: {'lr': 0.0004959159331929691, 'samples': 5390336, 'steps': 10527, 'loss/train': 1.6686232089996338}
-03/04/2022 01:50:00 - INFO - codeparrot_training - Step 10528: {'lr': 0.0004959149778401412, 'samples': 5390848, 'steps': 10528, 'loss/train': 1.4679720401763916}
-03/04/2022 01:50:04 - INFO - codeparrot_training - Step 10529: {'lr': 0.000495914022376508, 'samples': 5391360, 'steps': 10529, 'loss/train': 1.3539973497390747}
-03/04/2022 01:50:05 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/04/2022 01:50:09 - INFO - codeparrot_training - Step 10530: {'lr': 0.0004959130668020696, 'samples': 5391872, 'steps': 10530, 'loss/train': 1.772189974784851}
-03/04/2022 01:50:12 - INFO - codeparrot_training - Step 10531: {'lr': 0.0004959121111168266, 'samples': 5392384, 'steps': 10531, 'loss/train': 2.0685105323791504}
-03/04/2022 01:50:13 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/04/2022 01:50:18 - INFO - codeparrot_training - Step 10532: {'lr': 0.0004959111553207794, 'samples': 5392896, 'steps': 10532, 'loss/train': 2.1656975746154785}
-03/04/2022 01:50:21 - INFO - codeparrot_training - Step 10533: {'lr': 0.0004959101994139284, 'samples': 5393408, 'steps': 10533, 'loss/train': 1.1822839975357056}
-03/04/2022 01:50:22 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/04/2022 01:50:26 - INFO - codeparrot_training - Step 10534: {'lr': 0.0004959092433962742, 'samples': 5393920, 'steps': 10534, 'loss/train': 2.006685495376587}
-03/04/2022 01:50:29 - INFO - codeparrot_training - Step 10535: {'lr': 0.0004959082872678169, 'samples': 5394432, 'steps': 10535, 'loss/train': 2.9116697311401367}
-03/04/2022 01:50:31 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/04/2022 01:50:35 - INFO - codeparrot_training - Step 10536: {'lr': 0.0004959073310285572, 'samples': 5394944, 'steps': 10536, 'loss/train': 1.6549111604690552}
-03/04/2022 01:50:38 - INFO - codeparrot_training - Step 10537: {'lr': 0.0004959063746784955, 'samples': 5395456, 'steps': 10537, 'loss/train': 2.2436842918395996}
-03/04/2022 01:50:39 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/04/2022 01:50:43 - INFO - codeparrot_training - Step 10538: {'lr': 0.0004959054182176321, 'samples': 5395968, 'steps': 10538, 'loss/train': 2.210660457611084}
-03/04/2022 01:50:46 - INFO - codeparrot_training - Step 10539: {'lr': 0.0004959044616459676, 'samples': 5396480, 'steps': 10539, 'loss/train': 1.6054424047470093}
-03/04/2022 01:50:47 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/04/2022 01:50:51 - INFO - codeparrot_training - Step 10540: {'lr': 0.0004959035049635023, 'samples': 5396992, 'steps': 10540, 'loss/train': 2.0034432411193848}
-03/04/2022 01:50:55 - INFO - codeparrot_training - Step 10541: {'lr': 0.0004959025481702366, 'samples': 5397504, 'steps': 10541, 'loss/train': 1.3128067255020142}
-03/04/2022 01:50:56 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/04/2022 01:51:00 - INFO - codeparrot_training - Step 10542: {'lr': 0.0004959015912661712, 'samples': 5398016, 'steps': 10542, 'loss/train': 1.9860185384750366}
-03/04/2022 01:51:03 - INFO - codeparrot_training - Step 10543: {'lr': 0.0004959006342513062, 'samples': 5398528, 'steps': 10543, 'loss/train': 2.394944906234741}
-03/04/2022 01:51:04 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 01:51:08 - INFO - codeparrot_training - Step 10544: {'lr': 0.0004958996771256422, 'samples': 5399040, 'steps': 10544, 'loss/train': 2.007140874862671}
-03/04/2022 01:51:11 - INFO - codeparrot_training - Step 10545: {'lr': 0.0004958987198891796, 'samples': 5399552, 'steps': 10545, 'loss/train': 2.2795300483703613}
-03/04/2022 01:51:12 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 01:51:17 - INFO - codeparrot_training - Step 10546: {'lr': 0.0004958977625419187, 'samples': 5400064, 'steps': 10546, 'loss/train': 1.1054856777191162}
-03/04/2022 01:51:20 - INFO - codeparrot_training - Step 10547: {'lr': 0.0004958968050838603, 'samples': 5400576, 'steps': 10547, 'loss/train': 1.6331467628479004}
-03/04/2022 01:51:21 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/04/2022 01:51:25 - INFO - codeparrot_training - Step 10548: {'lr': 0.0004958958475150044, 'samples': 5401088, 'steps': 10548, 'loss/train': 3.021273136138916}
-03/04/2022 01:51:28 - INFO - codeparrot_training - Step 10549: {'lr': 0.0004958948898353516, 'samples': 5401600, 'steps': 10549, 'loss/train': 6.56338357925415}
-03/04/2022 01:51:30 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/04/2022 01:51:34 - INFO - codeparrot_training - Step 10550: {'lr': 0.0004958939320449026, 'samples': 5402112, 'steps': 10550, 'loss/train': 1.552001714706421}
-03/04/2022 01:51:37 - INFO - codeparrot_training - Step 10551: {'lr': 0.0004958929741436574, 'samples': 5402624, 'steps': 10551, 'loss/train': 1.656683087348938}
-03/04/2022 01:51:38 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 01:51:42 - INFO - codeparrot_training - Step 10552: {'lr': 0.0004958920161316167, 'samples': 5403136, 'steps': 10552, 'loss/train': 2.4628217220306396}
-03/04/2022 01:51:45 - INFO - codeparrot_training - Step 10553: {'lr': 0.0004958910580087808, 'samples': 5403648, 'steps': 10553, 'loss/train': 1.8717976808547974}
-03/04/2022 01:51:47 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/04/2022 01:51:51 - INFO - codeparrot_training - Step 10554: {'lr': 0.0004958900997751502, 'samples': 5404160, 'steps': 10554, 'loss/train': 1.5418851375579834}
-03/04/2022 01:51:54 - INFO - codeparrot_training - Step 10555: {'lr': 0.0004958891414307253, 'samples': 5404672, 'steps': 10555, 'loss/train': 2.451423406600952}
-03/04/2022 01:51:55 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/04/2022 01:51:59 - INFO - codeparrot_training - Step 10556: {'lr': 0.0004958881829755066, 'samples': 5405184, 'steps': 10556, 'loss/train': 2.338414430618286}
-03/04/2022 01:52:02 - INFO - codeparrot_training - Step 10557: {'lr': 0.0004958872244094944, 'samples': 5405696, 'steps': 10557, 'loss/train': 2.0169613361358643}
-03/04/2022 01:52:03 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/04/2022 01:52:07 - INFO - codeparrot_training - Step 10558: {'lr': 0.0004958862657326893, 'samples': 5406208, 'steps': 10558, 'loss/train': 2.3720874786376953}
-03/04/2022 01:52:11 - INFO - codeparrot_training - Step 10559: {'lr': 0.0004958853069450916, 'samples': 5406720, 'steps': 10559, 'loss/train': 2.385089635848999}
-03/04/2022 01:52:12 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/04/2022 01:52:16 - INFO - codeparrot_training - Step 10560: {'lr': 0.0004958843480467017, 'samples': 5407232, 'steps': 10560, 'loss/train': 3.598007917404175}
-03/04/2022 01:52:19 - INFO - codeparrot_training - Step 10561: {'lr': 0.0004958833890375202, 'samples': 5407744, 'steps': 10561, 'loss/train': 1.3646764755249023}
-03/04/2022 01:52:20 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 01:52:24 - INFO - codeparrot_training - Step 10562: {'lr': 0.0004958824299175474, 'samples': 5408256, 'steps': 10562, 'loss/train': 1.7945477962493896}
-03/04/2022 01:52:27 - INFO - codeparrot_training - Step 10563: {'lr': 0.0004958814706867838, 'samples': 5408768, 'steps': 10563, 'loss/train': 2.424677848815918}
-03/04/2022 01:52:28 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/04/2022 01:52:33 - INFO - codeparrot_training - Step 10564: {'lr': 0.0004958805113452298, 'samples': 5409280, 'steps': 10564, 'loss/train': 0.9650500416755676}
-03/04/2022 01:52:36 - INFO - codeparrot_training - Step 10565: {'lr': 0.0004958795518928858, 'samples': 5409792, 'steps': 10565, 'loss/train': 2.1226603984832764}
-03/04/2022 01:52:37 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 01:52:41 - INFO - codeparrot_training - Step 10566: {'lr': 0.0004958785923297522, 'samples': 5410304, 'steps': 10566, 'loss/train': 1.454102635383606}
-03/04/2022 01:52:44 - INFO - codeparrot_training - Step 10567: {'lr': 0.0004958776326558298, 'samples': 5410816, 'steps': 10567, 'loss/train': 2.546680212020874}
-03/04/2022 01:52:45 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/04/2022 01:52:49 - INFO - codeparrot_training - Step 10568: {'lr': 0.0004958766728711184, 'samples': 5411328, 'steps': 10568, 'loss/train': 0.46300551295280457}
-03/04/2022 01:52:53 - INFO - codeparrot_training - Step 10569: {'lr': 0.000495875712975619, 'samples': 5411840, 'steps': 10569, 'loss/train': 2.2930190563201904}
-03/04/2022 01:52:53 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/04/2022 01:52:58 - INFO - codeparrot_training - Step 10570: {'lr': 0.0004958747529693316, 'samples': 5412352, 'steps': 10570, 'loss/train': 1.1675193309783936}
-03/04/2022 01:53:01 - INFO - codeparrot_training - Step 10571: {'lr': 0.000495873792852257, 'samples': 5412864, 'steps': 10571, 'loss/train': 2.1324870586395264}
-03/04/2022 01:53:02 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/04/2022 01:53:06 - INFO - codeparrot_training - Step 10572: {'lr': 0.0004958728326243954, 'samples': 5413376, 'steps': 10572, 'loss/train': 1.8561588525772095}
-03/04/2022 01:53:09 - INFO - codeparrot_training - Step 10573: {'lr': 0.0004958718722857473, 'samples': 5413888, 'steps': 10573, 'loss/train': 2.609839916229248}
-03/04/2022 01:53:10 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/04/2022 01:53:15 - INFO - codeparrot_training - Step 10574: {'lr': 0.0004958709118363131, 'samples': 5414400, 'steps': 10574, 'loss/train': 1.6611632108688354}
-03/04/2022 01:53:18 - INFO - codeparrot_training - Step 10575: {'lr': 0.0004958699512760933, 'samples': 5414912, 'steps': 10575, 'loss/train': 2.283799886703491}
-03/04/2022 01:53:19 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/04/2022 01:53:23 - INFO - codeparrot_training - Step 10576: {'lr': 0.0004958689906050882, 'samples': 5415424, 'steps': 10576, 'loss/train': 2.406794786453247}
-03/04/2022 01:53:26 - INFO - codeparrot_training - Step 10577: {'lr': 0.0004958680298232983, 'samples': 5415936, 'steps': 10577, 'loss/train': 1.601876974105835}
-03/04/2022 01:53:27 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/04/2022 01:53:32 - INFO - codeparrot_training - Step 10578: {'lr': 0.0004958670689307242, 'samples': 5416448, 'steps': 10578, 'loss/train': 2.229090452194214}
-03/04/2022 01:53:35 - INFO - codeparrot_training - Step 10579: {'lr': 0.0004958661079273662, 'samples': 5416960, 'steps': 10579, 'loss/train': 2.6903793811798096}
-03/04/2022 01:53:35 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/04/2022 01:53:41 - INFO - codeparrot_training - Step 10580: {'lr': 0.0004958651468132246, 'samples': 5417472, 'steps': 10580, 'loss/train': 3.40809965133667}
-03/04/2022 01:53:44 - INFO - codeparrot_training - Step 10581: {'lr': 0.0004958641855883001, 'samples': 5417984, 'steps': 10581, 'loss/train': 2.069220781326294}
-03/04/2022 01:53:47 - INFO - codeparrot_training - Step 10582: {'lr': 0.0004958632242525929, 'samples': 5418496, 'steps': 10582, 'loss/train': 6.563566207885742}
-03/04/2022 01:53:49 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/04/2022 01:53:52 - INFO - codeparrot_training - Step 10583: {'lr': 0.0004958622628061035, 'samples': 5419008, 'steps': 10583, 'loss/train': 1.9548124074935913}
-03/04/2022 01:53:56 - INFO - codeparrot_training - Step 10584: {'lr': 0.0004958613012488324, 'samples': 5419520, 'steps': 10584, 'loss/train': 2.043030023574829}
-03/04/2022 01:53:57 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/04/2022 01:54:01 - INFO - codeparrot_training - Step 10585: {'lr': 0.00049586033958078, 'samples': 5420032, 'steps': 10585, 'loss/train': 2.337904930114746}
-03/04/2022 01:54:04 - INFO - codeparrot_training - Step 10586: {'lr': 0.0004958593778019468, 'samples': 5420544, 'steps': 10586, 'loss/train': 1.015315294265747}
-03/04/2022 01:54:05 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/04/2022 01:54:09 - INFO - codeparrot_training - Step 10587: {'lr': 0.0004958584159123331, 'samples': 5421056, 'steps': 10587, 'loss/train': 2.109485387802124}
-03/04/2022 01:54:13 - INFO - codeparrot_training - Step 10588: {'lr': 0.0004958574539119392, 'samples': 5421568, 'steps': 10588, 'loss/train': 1.7120180130004883}
-03/04/2022 01:54:14 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/04/2022 01:54:18 - INFO - codeparrot_training - Step 10589: {'lr': 0.0004958564918007659, 'samples': 5422080, 'steps': 10589, 'loss/train': 6.797205924987793}
-03/04/2022 01:54:21 - INFO - codeparrot_training - Step 10590: {'lr': 0.0004958555295788135, 'samples': 5422592, 'steps': 10590, 'loss/train': 2.775228500366211}
-03/04/2022 01:54:23 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/04/2022 01:54:26 - INFO - codeparrot_training - Step 10591: {'lr': 0.0004958545672460824, 'samples': 5423104, 'steps': 10591, 'loss/train': 1.996220588684082}
-03/04/2022 01:54:29 - INFO - codeparrot_training - Step 10592: {'lr': 0.0004958536048025729, 'samples': 5423616, 'steps': 10592, 'loss/train': 2.6298253536224365}
-03/04/2022 01:54:31 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/04/2022 01:54:35 - INFO - codeparrot_training - Step 10593: {'lr': 0.0004958526422482857, 'samples': 5424128, 'steps': 10593, 'loss/train': 1.7652747631072998}
-03/04/2022 01:54:38 - INFO - codeparrot_training - Step 10594: {'lr': 0.000495851679583221, 'samples': 5424640, 'steps': 10594, 'loss/train': 2.4268288612365723}
-03/04/2022 01:54:39 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/04/2022 01:54:43 - INFO - codeparrot_training - Step 10595: {'lr': 0.0004958507168073793, 'samples': 5425152, 'steps': 10595, 'loss/train': 2.3161401748657227}
-03/04/2022 01:54:46 - INFO - codeparrot_training - Step 10596: {'lr': 0.0004958497539207611, 'samples': 5425664, 'steps': 10596, 'loss/train': 2.2215232849121094}
-03/04/2022 01:54:48 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 01:54:51 - INFO - codeparrot_training - Step 10597: {'lr': 0.0004958487909233669, 'samples': 5426176, 'steps': 10597, 'loss/train': 1.9235715866088867}
-03/04/2022 01:54:55 - INFO - codeparrot_training - Step 10598: {'lr': 0.0004958478278151969, 'samples': 5426688, 'steps': 10598, 'loss/train': 1.2024927139282227}
-03/04/2022 01:54:57 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 01:55:00 - INFO - codeparrot_training - Step 10599: {'lr': 0.0004958468645962517, 'samples': 5427200, 'steps': 10599, 'loss/train': 1.8292399644851685}
-03/04/2022 01:55:03 - INFO - codeparrot_training - Step 10600: {'lr': 0.0004958459012665317, 'samples': 5427712, 'steps': 10600, 'loss/train': 1.9221516847610474}
-03/04/2022 01:55:05 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 01:55:08 - INFO - codeparrot_training - Step 10601: {'lr': 0.0004958449378260374, 'samples': 5428224, 'steps': 10601, 'loss/train': 1.689666509628296}
-03/04/2022 01:55:12 - INFO - codeparrot_training - Step 10602: {'lr': 0.000495843974274769, 'samples': 5428736, 'steps': 10602, 'loss/train': 1.870345950126648}
-03/04/2022 01:55:13 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 01:55:17 - INFO - codeparrot_training - Step 10603: {'lr': 0.0004958430106127272, 'samples': 5429248, 'steps': 10603, 'loss/train': 1.7850191593170166}
-03/04/2022 01:55:20 - INFO - codeparrot_training - Step 10604: {'lr': 0.0004958420468399123, 'samples': 5429760, 'steps': 10604, 'loss/train': 2.393386125564575}
-03/04/2022 01:55:23 - INFO - codeparrot_training - Step 10605: {'lr': 0.0004958410829563248, 'samples': 5430272, 'steps': 10605, 'loss/train': 2.347989082336426}
-03/04/2022 01:55:23 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/04/2022 01:55:29 - INFO - codeparrot_training - Step 10606: {'lr': 0.0004958401189619652, 'samples': 5430784, 'steps': 10606, 'loss/train': 1.9187920093536377}
-03/04/2022 01:55:32 - INFO - codeparrot_training - Step 10607: {'lr': 0.0004958391548568336, 'samples': 5431296, 'steps': 10607, 'loss/train': 2.003504991531372}
-03/04/2022 01:55:37 - INFO - codeparrot_training - Step 10608: {'lr': 0.0004958381906409308, 'samples': 5431808, 'steps': 10608, 'loss/train': 2.2030866146087646}
-03/04/2022 01:55:40 - INFO - codeparrot_training - Step 10609: {'lr': 0.0004958372263142571, 'samples': 5432320, 'steps': 10609, 'loss/train': 1.9384557008743286}
-03/04/2022 01:55:40 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/04/2022 01:55:46 - INFO - codeparrot_training - Step 10610: {'lr': 0.0004958362618768129, 'samples': 5432832, 'steps': 10610, 'loss/train': 1.646248698234558}
-03/04/2022 01:55:48 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 01:55:51 - INFO - codeparrot_training - Step 10611: {'lr': 0.0004958352973285987, 'samples': 5433344, 'steps': 10611, 'loss/train': 2.3049402236938477}
-03/04/2022 01:55:54 - INFO - codeparrot_training - Step 10612: {'lr': 0.000495834332669615, 'samples': 5433856, 'steps': 10612, 'loss/train': 1.5009077787399292}
-03/04/2022 01:55:57 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 01:55:59 - INFO - codeparrot_training - Step 10613: {'lr': 0.0004958333678998622, 'samples': 5434368, 'steps': 10613, 'loss/train': 2.131100654602051}
-03/04/2022 01:56:03 - INFO - codeparrot_training - Step 10614: {'lr': 0.0004958324030193404, 'samples': 5434880, 'steps': 10614, 'loss/train': 2.083742618560791}
-03/04/2022 01:56:06 - INFO - codeparrot_training - Step 10615: {'lr': 0.0004958314380280504, 'samples': 5435392, 'steps': 10615, 'loss/train': 1.4476739168167114}
-03/04/2022 01:56:06 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 01:56:11 - INFO - codeparrot_training - Step 10616: {'lr': 0.0004958304729259927, 'samples': 5435904, 'steps': 10616, 'loss/train': 2.1258597373962402}
-03/04/2022 01:56:14 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 01:56:16 - INFO - codeparrot_training - Step 10617: {'lr': 0.0004958295077131674, 'samples': 5436416, 'steps': 10617, 'loss/train': 2.106584310531616}
-03/04/2022 01:56:19 - INFO - codeparrot_training - Step 10618: {'lr': 0.0004958285423895752, 'samples': 5436928, 'steps': 10618, 'loss/train': 2.38088321685791}
-03/04/2022 01:56:22 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/04/2022 01:56:25 - INFO - codeparrot_training - Step 10619: {'lr': 0.0004958275769552165, 'samples': 5437440, 'steps': 10619, 'loss/train': 2.535269021987915}
-03/04/2022 01:56:28 - INFO - codeparrot_training - Step 10620: {'lr': 0.0004958266114100917, 'samples': 5437952, 'steps': 10620, 'loss/train': 1.3506956100463867}
-03/04/2022 01:56:30 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 01:56:33 - INFO - codeparrot_training - Step 10621: {'lr': 0.0004958256457542011, 'samples': 5438464, 'steps': 10621, 'loss/train': 1.5093923807144165}
-03/04/2022 01:56:36 - INFO - codeparrot_training - Step 10622: {'lr': 0.0004958246799875453, 'samples': 5438976, 'steps': 10622, 'loss/train': 3.0312857627868652}
-03/04/2022 01:56:39 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/04/2022 01:56:41 - INFO - codeparrot_training - Step 10623: {'lr': 0.0004958237141101247, 'samples': 5439488, 'steps': 10623, 'loss/train': 2.2625253200531006}
-03/04/2022 01:56:45 - INFO - codeparrot_training - Step 10624: {'lr': 0.0004958227481219399, 'samples': 5440000, 'steps': 10624, 'loss/train': 1.6480133533477783}
-03/04/2022 01:56:47 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/04/2022 01:56:50 - INFO - codeparrot_training - Step 10625: {'lr': 0.0004958217820229909, 'samples': 5440512, 'steps': 10625, 'loss/train': 2.4295873641967773}
-03/04/2022 01:56:53 - INFO - codeparrot_training - Step 10626: {'lr': 0.0004958208158132785, 'samples': 5441024, 'steps': 10626, 'loss/train': 1.7835277318954468}
-03/04/2022 01:56:55 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 01:56:58 - INFO - codeparrot_training - Step 10627: {'lr': 0.000495819849492803, 'samples': 5441536, 'steps': 10627, 'loss/train': 1.4037607908248901}
-03/04/2022 01:57:01 - INFO - codeparrot_training - Step 10628: {'lr': 0.0004958188830615649, 'samples': 5442048, 'steps': 10628, 'loss/train': 2.095954418182373}
-03/04/2022 01:57:04 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/04/2022 01:57:07 - INFO - codeparrot_training - Step 10629: {'lr': 0.0004958179165195646, 'samples': 5442560, 'steps': 10629, 'loss/train': 0.9942908883094788}
-03/04/2022 01:57:10 - INFO - codeparrot_training - Step 10630: {'lr': 0.0004958169498668026, 'samples': 5443072, 'steps': 10630, 'loss/train': 1.3246077299118042}
-03/04/2022 01:57:12 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/04/2022 01:57:15 - INFO - codeparrot_training - Step 10631: {'lr': 0.0004958159831032793, 'samples': 5443584, 'steps': 10631, 'loss/train': 1.6574488878250122}
-03/04/2022 01:57:18 - INFO - codeparrot_training - Step 10632: {'lr': 0.000495815016228995, 'samples': 5444096, 'steps': 10632, 'loss/train': 1.992861270904541}
-03/04/2022 01:57:20 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/04/2022 01:57:24 - INFO - codeparrot_training - Step 10633: {'lr': 0.0004958140492439502, 'samples': 5444608, 'steps': 10633, 'loss/train': 2.710862636566162}
-03/04/2022 01:57:27 - INFO - codeparrot_training - Step 10634: {'lr': 0.0004958130821481455, 'samples': 5445120, 'steps': 10634, 'loss/train': 2.357656240463257}
-03/04/2022 01:57:29 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/04/2022 01:57:32 - INFO - codeparrot_training - Step 10635: {'lr': 0.0004958121149415812, 'samples': 5445632, 'steps': 10635, 'loss/train': 2.158921957015991}
-03/04/2022 01:57:35 - INFO - codeparrot_training - Step 10636: {'lr': 0.0004958111476242577, 'samples': 5446144, 'steps': 10636, 'loss/train': 1.9161875247955322}
-03/04/2022 01:57:37 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/04/2022 01:57:40 - INFO - codeparrot_training - Step 10637: {'lr': 0.0004958101801961755, 'samples': 5446656, 'steps': 10637, 'loss/train': 2.5610647201538086}
-03/04/2022 01:57:44 - INFO - codeparrot_training - Step 10638: {'lr': 0.0004958092126573352, 'samples': 5447168, 'steps': 10638, 'loss/train': 2.6862120628356934}
-03/04/2022 01:57:45 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 01:57:49 - INFO - codeparrot_training - Step 10639: {'lr': 0.0004958082450077369, 'samples': 5447680, 'steps': 10639, 'loss/train': 2.259371519088745}
-03/04/2022 01:57:52 - INFO - codeparrot_training - Step 10640: {'lr': 0.0004958072772473812, 'samples': 5448192, 'steps': 10640, 'loss/train': 2.432982921600342}
-03/04/2022 01:57:54 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/04/2022 01:57:57 - INFO - codeparrot_training - Step 10641: {'lr': 0.0004958063093762684, 'samples': 5448704, 'steps': 10641, 'loss/train': 0.8223580121994019}
-03/04/2022 01:58:00 - INFO - codeparrot_training - Step 10642: {'lr': 0.0004958053413943993, 'samples': 5449216, 'steps': 10642, 'loss/train': 2.058396577835083}
-03/04/2022 01:58:02 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 01:58:06 - INFO - codeparrot_training - Step 10643: {'lr': 0.0004958043733017741, 'samples': 5449728, 'steps': 10643, 'loss/train': 1.9458457231521606}
-03/04/2022 01:58:09 - INFO - codeparrot_training - Step 10644: {'lr': 0.0004958034050983932, 'samples': 5450240, 'steps': 10644, 'loss/train': 1.4334794282913208}
-03/04/2022 01:58:10 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 01:58:14 - INFO - codeparrot_training - Step 10645: {'lr': 0.0004958024367842569, 'samples': 5450752, 'steps': 10645, 'loss/train': 2.565812826156616}
-03/04/2022 01:58:17 - INFO - codeparrot_training - Step 10646: {'lr': 0.000495801468359366, 'samples': 5451264, 'steps': 10646, 'loss/train': 1.6176496744155884}
-03/04/2022 01:58:19 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/04/2022 01:58:23 - INFO - codeparrot_training - Step 10647: {'lr': 0.0004958004998237207, 'samples': 5451776, 'steps': 10647, 'loss/train': 0.9641431570053101}
-03/04/2022 01:58:26 - INFO - codeparrot_training - Step 10648: {'lr': 0.0004957995311773215, 'samples': 5452288, 'steps': 10648, 'loss/train': 2.2807812690734863}
-03/04/2022 01:58:27 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/04/2022 01:58:31 - INFO - codeparrot_training - Step 10649: {'lr': 0.0004957985624201688, 'samples': 5452800, 'steps': 10649, 'loss/train': 1.7071278095245361}
-03/04/2022 01:58:34 - INFO - codeparrot_training - Step 10650: {'lr': 0.0004957975935522632, 'samples': 5453312, 'steps': 10650, 'loss/train': 2.3000872135162354}
-03/04/2022 01:58:35 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/04/2022 01:58:39 - INFO - codeparrot_training - Step 10651: {'lr': 0.0004957966245736048, 'samples': 5453824, 'steps': 10651, 'loss/train': 2.4410200119018555}
-03/04/2022 01:58:42 - INFO - codeparrot_training - Step 10652: {'lr': 0.0004957956554841943, 'samples': 5454336, 'steps': 10652, 'loss/train': 2.0947039127349854}
-03/04/2022 01:58:44 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/04/2022 01:58:48 - INFO - codeparrot_training - Step 10653: {'lr': 0.0004957946862840321, 'samples': 5454848, 'steps': 10653, 'loss/train': 2.1588850021362305}
-03/04/2022 01:58:51 - INFO - codeparrot_training - Step 10654: {'lr': 0.0004957937169731186, 'samples': 5455360, 'steps': 10654, 'loss/train': 2.207274913787842}
-03/04/2022 01:58:52 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/04/2022 01:58:56 - INFO - codeparrot_training - Step 10655: {'lr': 0.0004957927475514542, 'samples': 5455872, 'steps': 10655, 'loss/train': 3.358046054840088}
-03/04/2022 01:58:59 - INFO - codeparrot_training - Step 10656: {'lr': 0.0004957917780190395, 'samples': 5456384, 'steps': 10656, 'loss/train': 2.151348829269409}
-03/04/2022 01:59:00 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 01:59:05 - INFO - codeparrot_training - Step 10657: {'lr': 0.0004957908083758747, 'samples': 5456896, 'steps': 10657, 'loss/train': 2.1442697048187256}
-03/04/2022 01:59:08 - INFO - codeparrot_training - Step 10658: {'lr': 0.0004957898386219603, 'samples': 5457408, 'steps': 10658, 'loss/train': 1.453822374343872}
-03/04/2022 01:59:09 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 01:59:13 - INFO - codeparrot_training - Step 10659: {'lr': 0.000495788868757297, 'samples': 5457920, 'steps': 10659, 'loss/train': 2.2848920822143555}
-03/04/2022 01:59:16 - INFO - codeparrot_training - Step 10660: {'lr': 0.0004957878987818849, 'samples': 5458432, 'steps': 10660, 'loss/train': 2.8234879970550537}
-03/04/2022 01:59:18 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 01:59:22 - INFO - codeparrot_training - Step 10661: {'lr': 0.0004957869286957246, 'samples': 5458944, 'steps': 10661, 'loss/train': 0.8955574631690979}
-03/04/2022 01:59:25 - INFO - codeparrot_training - Step 10662: {'lr': 0.0004957859584988164, 'samples': 5459456, 'steps': 10662, 'loss/train': 1.5499465465545654}
-03/04/2022 01:59:26 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 01:59:30 - INFO - codeparrot_training - Step 10663: {'lr': 0.0004957849881911609, 'samples': 5459968, 'steps': 10663, 'loss/train': 2.2173874378204346}
-03/04/2022 01:59:33 - INFO - codeparrot_training - Step 10664: {'lr': 0.0004957840177727585, 'samples': 5460480, 'steps': 10664, 'loss/train': 2.173292875289917}
-03/04/2022 01:59:35 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/04/2022 01:59:38 - INFO - codeparrot_training - Step 10665: {'lr': 0.0004957830472436097, 'samples': 5460992, 'steps': 10665, 'loss/train': 1.5483757257461548}
-03/04/2022 01:59:42 - INFO - codeparrot_training - Step 10666: {'lr': 0.0004957820766037147, 'samples': 5461504, 'steps': 10666, 'loss/train': 1.7994019985198975}
-03/04/2022 01:59:43 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/04/2022 01:59:47 - INFO - codeparrot_training - Step 10667: {'lr': 0.0004957811058530742, 'samples': 5462016, 'steps': 10667, 'loss/train': 2.1035094261169434}
-03/04/2022 01:59:50 - INFO - codeparrot_training - Step 10668: {'lr': 0.0004957801349916884, 'samples': 5462528, 'steps': 10668, 'loss/train': 1.9135798215866089}
-03/04/2022 01:59:52 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/04/2022 01:59:55 - INFO - codeparrot_training - Step 10669: {'lr': 0.000495779164019558, 'samples': 5463040, 'steps': 10669, 'loss/train': 1.6206706762313843}
-03/04/2022 01:59:58 - INFO - codeparrot_training - Step 10670: {'lr': 0.0004957781929366832, 'samples': 5463552, 'steps': 10670, 'loss/train': 1.6697887182235718}
-03/04/2022 02:00:00 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/04/2022 02:00:04 - INFO - codeparrot_training - Step 10671: {'lr': 0.0004957772217430646, 'samples': 5464064, 'steps': 10671, 'loss/train': 1.1337910890579224}
-03/04/2022 02:00:07 - INFO - codeparrot_training - Step 10672: {'lr': 0.0004957762504387025, 'samples': 5464576, 'steps': 10672, 'loss/train': 1.766867995262146}
-03/04/2022 02:00:09 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/04/2022 02:00:12 - INFO - codeparrot_training - Step 10673: {'lr': 0.0004957752790235976, 'samples': 5465088, 'steps': 10673, 'loss/train': 1.1882761716842651}
-03/04/2022 02:00:15 - INFO - codeparrot_training - Step 10674: {'lr': 0.00049577430749775, 'samples': 5465600, 'steps': 10674, 'loss/train': 1.9343080520629883}
-03/04/2022 02:00:17 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/04/2022 02:00:21 - INFO - codeparrot_training - Step 10675: {'lr': 0.0004957733358611602, 'samples': 5466112, 'steps': 10675, 'loss/train': 2.183427333831787}
-03/04/2022 02:00:24 - INFO - codeparrot_training - Step 10676: {'lr': 0.0004957723641138289, 'samples': 5466624, 'steps': 10676, 'loss/train': 1.1590439081192017}
-03/04/2022 02:00:26 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/04/2022 02:00:29 - INFO - codeparrot_training - Step 10677: {'lr': 0.0004957713922557563, 'samples': 5467136, 'steps': 10677, 'loss/train': 1.7829095125198364}
-03/04/2022 02:00:32 - INFO - codeparrot_training - Step 10678: {'lr': 0.0004957704202869429, 'samples': 5467648, 'steps': 10678, 'loss/train': 0.9866939187049866}
-03/04/2022 02:00:34 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/04/2022 02:00:38 - INFO - codeparrot_training - Step 10679: {'lr': 0.0004957694482073891, 'samples': 5468160, 'steps': 10679, 'loss/train': 1.6826626062393188}
-03/04/2022 02:00:41 - INFO - codeparrot_training - Step 10680: {'lr': 0.0004957684760170955, 'samples': 5468672, 'steps': 10680, 'loss/train': 1.719638705253601}
-03/04/2022 02:00:43 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 02:00:46 - INFO - codeparrot_training - Step 10681: {'lr': 0.0004957675037160624, 'samples': 5469184, 'steps': 10681, 'loss/train': 0.8894862532615662}
-03/04/2022 02:00:49 - INFO - codeparrot_training - Step 10682: {'lr': 0.0004957665313042902, 'samples': 5469696, 'steps': 10682, 'loss/train': 2.3598761558532715}
-03/04/2022 02:00:51 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/04/2022 02:00:54 - INFO - codeparrot_training - Step 10683: {'lr': 0.0004957655587817793, 'samples': 5470208, 'steps': 10683, 'loss/train': 2.1068339347839355}
-03/04/2022 02:00:58 - INFO - codeparrot_training - Step 10684: {'lr': 0.0004957645861485304, 'samples': 5470720, 'steps': 10684, 'loss/train': 1.7490874528884888}
-03/04/2022 02:01:00 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/04/2022 02:01:03 - INFO - codeparrot_training - Step 10685: {'lr': 0.0004957636134045437, 'samples': 5471232, 'steps': 10685, 'loss/train': 1.3920416831970215}
-03/04/2022 02:01:06 - INFO - codeparrot_training - Step 10686: {'lr': 0.0004957626405498196, 'samples': 5471744, 'steps': 10686, 'loss/train': 0.7068358063697815}
-03/04/2022 02:01:08 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/04/2022 02:01:11 - INFO - codeparrot_training - Step 10687: {'lr': 0.0004957616675843588, 'samples': 5472256, 'steps': 10687, 'loss/train': 1.2424932718276978}
-03/04/2022 02:01:14 - INFO - codeparrot_training - Step 10688: {'lr': 0.0004957606945081615, 'samples': 5472768, 'steps': 10688, 'loss/train': 1.7228553295135498}
-03/04/2022 02:01:16 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 02:01:20 - INFO - codeparrot_training - Step 10689: {'lr': 0.0004957597213212284, 'samples': 5473280, 'steps': 10689, 'loss/train': 1.9883280992507935}
-03/04/2022 02:01:23 - INFO - codeparrot_training - Step 10690: {'lr': 0.0004957587480235595, 'samples': 5473792, 'steps': 10690, 'loss/train': 1.5236384868621826}
-03/04/2022 02:01:26 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/04/2022 02:01:28 - INFO - codeparrot_training - Step 10691: {'lr': 0.0004957577746151556, 'samples': 5474304, 'steps': 10691, 'loss/train': 2.0887959003448486}
-03/04/2022 02:01:32 - INFO - codeparrot_training - Step 10692: {'lr': 0.0004957568010960171, 'samples': 5474816, 'steps': 10692, 'loss/train': 1.9694064855575562}
-03/04/2022 02:01:34 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 02:01:37 - INFO - codeparrot_training - Step 10693: {'lr': 0.0004957558274661444, 'samples': 5475328, 'steps': 10693, 'loss/train': 1.999935269355774}
-03/04/2022 02:01:40 - INFO - codeparrot_training - Step 10694: {'lr': 0.0004957548537255378, 'samples': 5475840, 'steps': 10694, 'loss/train': 2.4967427253723145}
-03/04/2022 02:01:43 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/04/2022 02:01:45 - INFO - codeparrot_training - Step 10695: {'lr': 0.000495753879874198, 'samples': 5476352, 'steps': 10695, 'loss/train': 0.4786219000816345}
-03/04/2022 02:01:48 - INFO - codeparrot_training - Step 10696: {'lr': 0.0004957529059121251, 'samples': 5476864, 'steps': 10696, 'loss/train': 0.40303730964660645}
-03/04/2022 02:01:51 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/04/2022 02:01:54 - INFO - codeparrot_training - Step 10697: {'lr': 0.0004957519318393199, 'samples': 5477376, 'steps': 10697, 'loss/train': 2.660936117172241}
-03/04/2022 02:01:57 - INFO - codeparrot_training - Step 10698: {'lr': 0.0004957509576557826, 'samples': 5477888, 'steps': 10698, 'loss/train': 2.320849657058716}
-03/04/2022 02:01:59 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/04/2022 02:02:02 - INFO - codeparrot_training - Step 10699: {'lr': 0.0004957499833615137, 'samples': 5478400, 'steps': 10699, 'loss/train': 2.7550883293151855}
-03/04/2022 02:02:05 - INFO - codeparrot_training - Step 10700: {'lr': 0.0004957490089565137, 'samples': 5478912, 'steps': 10700, 'loss/train': 1.6033227443695068}
-03/04/2022 02:02:08 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 02:02:11 - INFO - codeparrot_training - Step 10701: {'lr': 0.0004957480344407829, 'samples': 5479424, 'steps': 10701, 'loss/train': 1.936754584312439}
-03/04/2022 02:02:14 - INFO - codeparrot_training - Step 10702: {'lr': 0.0004957470598143218, 'samples': 5479936, 'steps': 10702, 'loss/train': 1.837061882019043}
-03/04/2022 02:02:16 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 02:02:19 - INFO - codeparrot_training - Step 10703: {'lr': 0.000495746085077131, 'samples': 5480448, 'steps': 10703, 'loss/train': 2.517876148223877}
-03/04/2022 02:02:22 - INFO - codeparrot_training - Step 10704: {'lr': 0.0004957451102292108, 'samples': 5480960, 'steps': 10704, 'loss/train': 0.9593729972839355}
-03/04/2022 02:02:25 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 02:02:28 - INFO - codeparrot_training - Step 10705: {'lr': 0.0004957441352705616, 'samples': 5481472, 'steps': 10705, 'loss/train': 1.7178514003753662}
-03/04/2022 02:02:31 - INFO - codeparrot_training - Step 10706: {'lr': 0.0004957431602011839, 'samples': 5481984, 'steps': 10706, 'loss/train': 2.3520569801330566}
-03/04/2022 02:02:33 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 02:02:36 - INFO - codeparrot_training - Step 10707: {'lr': 0.0004957421850210781, 'samples': 5482496, 'steps': 10707, 'loss/train': 1.0600298643112183}
-03/04/2022 02:02:39 - INFO - codeparrot_training - Step 10708: {'lr': 0.0004957412097302446, 'samples': 5483008, 'steps': 10708, 'loss/train': 1.7855854034423828}
-03/04/2022 02:02:42 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/04/2022 02:02:44 - INFO - codeparrot_training - Step 10709: {'lr': 0.000495740234328684, 'samples': 5483520, 'steps': 10709, 'loss/train': 2.5099246501922607}
-03/04/2022 02:02:48 - INFO - codeparrot_training - Step 10710: {'lr': 0.0004957392588163967, 'samples': 5484032, 'steps': 10710, 'loss/train': 1.6597493886947632}
-03/04/2022 02:02:50 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/04/2022 02:02:53 - INFO - codeparrot_training - Step 10711: {'lr': 0.000495738283193383, 'samples': 5484544, 'steps': 10711, 'loss/train': 2.152169704437256}
-03/04/2022 02:02:56 - INFO - codeparrot_training - Step 10712: {'lr': 0.0004957373074596434, 'samples': 5485056, 'steps': 10712, 'loss/train': 2.286994457244873}
-03/04/2022 02:02:59 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/04/2022 02:03:01 - INFO - codeparrot_training - Step 10713: {'lr': 0.0004957363316151784, 'samples': 5485568, 'steps': 10713, 'loss/train': 3.626992702484131}
-03/04/2022 02:03:04 - INFO - codeparrot_training - Step 10714: {'lr': 0.0004957353556599884, 'samples': 5486080, 'steps': 10714, 'loss/train': 1.8550586700439453}
-03/04/2022 02:03:07 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 02:03:10 - INFO - codeparrot_training - Step 10715: {'lr': 0.0004957343795940738, 'samples': 5486592, 'steps': 10715, 'loss/train': 1.9623488187789917}
-03/04/2022 02:03:13 - INFO - codeparrot_training - Step 10716: {'lr': 0.0004957334034174351, 'samples': 5487104, 'steps': 10716, 'loss/train': 1.4668956995010376}
-03/04/2022 02:03:16 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/04/2022 02:03:18 - INFO - codeparrot_training - Step 10717: {'lr': 0.0004957324271300728, 'samples': 5487616, 'steps': 10717, 'loss/train': 2.3713936805725098}
-03/04/2022 02:03:21 - INFO - codeparrot_training - Step 10718: {'lr': 0.0004957314507319871, 'samples': 5488128, 'steps': 10718, 'loss/train': 2.626802682876587}
-03/04/2022 02:03:24 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 02:03:26 - INFO - codeparrot_training - Step 10719: {'lr': 0.0004957304742231787, 'samples': 5488640, 'steps': 10719, 'loss/train': 1.894382357597351}
-03/04/2022 02:03:30 - INFO - codeparrot_training - Step 10720: {'lr': 0.0004957294976036479, 'samples': 5489152, 'steps': 10720, 'loss/train': 2.8600306510925293}
-03/04/2022 02:03:32 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/04/2022 02:03:35 - INFO - codeparrot_training - Step 10721: {'lr': 0.0004957285208733953, 'samples': 5489664, 'steps': 10721, 'loss/train': 1.7849513292312622}
-03/04/2022 02:03:38 - INFO - codeparrot_training - Step 10722: {'lr': 0.0004957275440324211, 'samples': 5490176, 'steps': 10722, 'loss/train': 3.529677152633667}
-03/04/2022 02:03:40 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 02:03:43 - INFO - codeparrot_training - Step 10723: {'lr': 0.0004957265670807258, 'samples': 5490688, 'steps': 10723, 'loss/train': 1.8667669296264648}
-03/04/2022 02:03:46 - INFO - codeparrot_training - Step 10724: {'lr': 0.0004957255900183101, 'samples': 5491200, 'steps': 10724, 'loss/train': 2.129270553588867}
-03/04/2022 02:03:49 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 02:03:52 - INFO - codeparrot_training - Step 10725: {'lr': 0.000495724612845174, 'samples': 5491712, 'steps': 10725, 'loss/train': 2.5538582801818848}
-03/04/2022 02:03:55 - INFO - codeparrot_training - Step 10726: {'lr': 0.0004957236355613184, 'samples': 5492224, 'steps': 10726, 'loss/train': 1.809093713760376}
-03/04/2022 02:03:57 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/04/2022 02:04:00 - INFO - codeparrot_training - Step 10727: {'lr': 0.0004957226581667434, 'samples': 5492736, 'steps': 10727, 'loss/train': 2.1390180587768555}
-03/04/2022 02:04:03 - INFO - codeparrot_training - Step 10728: {'lr': 0.0004957216806614496, 'samples': 5493248, 'steps': 10728, 'loss/train': 2.053955316543579}
-03/04/2022 02:04:06 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/04/2022 02:04:09 - INFO - codeparrot_training - Step 10729: {'lr': 0.0004957207030454374, 'samples': 5493760, 'steps': 10729, 'loss/train': 2.2138242721557617}
-03/04/2022 02:04:12 - INFO - codeparrot_training - Step 10730: {'lr': 0.0004957197253187073, 'samples': 5494272, 'steps': 10730, 'loss/train': 1.7236958742141724}
-03/04/2022 02:04:14 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 02:04:17 - INFO - codeparrot_training - Step 10731: {'lr': 0.0004957187474812595, 'samples': 5494784, 'steps': 10731, 'loss/train': 1.9581893682479858}
-03/04/2022 02:04:20 - INFO - codeparrot_training - Step 10732: {'lr': 0.0004957177695330948, 'samples': 5495296, 'steps': 10732, 'loss/train': 1.8239161968231201}
-03/04/2022 02:04:22 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/04/2022 02:04:25 - INFO - codeparrot_training - Step 10733: {'lr': 0.0004957167914742134, 'samples': 5495808, 'steps': 10733, 'loss/train': 1.7108983993530273}
-03/04/2022 02:04:29 - INFO - codeparrot_training - Step 10734: {'lr': 0.0004957158133046158, 'samples': 5496320, 'steps': 10734, 'loss/train': 2.8996787071228027}
-03/04/2022 02:04:31 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 02:04:34 - INFO - codeparrot_training - Step 10735: {'lr': 0.0004957148350243025, 'samples': 5496832, 'steps': 10735, 'loss/train': 2.040114164352417}
-03/04/2022 02:04:37 - INFO - codeparrot_training - Step 10736: {'lr': 0.0004957138566332738, 'samples': 5497344, 'steps': 10736, 'loss/train': 1.3795182704925537}
-03/04/2022 02:04:39 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 02:04:42 - INFO - codeparrot_training - Step 10737: {'lr': 0.0004957128781315303, 'samples': 5497856, 'steps': 10737, 'loss/train': 1.5398565530776978}
-03/04/2022 02:04:46 - INFO - codeparrot_training - Step 10738: {'lr': 0.0004957118995190723, 'samples': 5498368, 'steps': 10738, 'loss/train': 1.7778714895248413}
-03/04/2022 02:04:47 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/04/2022 02:04:51 - INFO - codeparrot_training - Step 10739: {'lr': 0.0004957109207959004, 'samples': 5498880, 'steps': 10739, 'loss/train': 2.108497142791748}
-03/04/2022 02:04:54 - INFO - codeparrot_training - Step 10740: {'lr': 0.0004957099419620149, 'samples': 5499392, 'steps': 10740, 'loss/train': 2.097221612930298}
-03/04/2022 02:04:56 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/04/2022 02:04:59 - INFO - codeparrot_training - Step 10741: {'lr': 0.0004957089630174163, 'samples': 5499904, 'steps': 10741, 'loss/train': 1.6599109172821045}
-03/04/2022 02:05:03 - INFO - codeparrot_training - Step 10742: {'lr': 0.0004957079839621051, 'samples': 5500416, 'steps': 10742, 'loss/train': 2.0373494625091553}
-03/04/2022 02:05:05 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/04/2022 02:05:08 - INFO - codeparrot_training - Step 10743: {'lr': 0.0004957070047960816, 'samples': 5500928, 'steps': 10743, 'loss/train': 1.6002565622329712}
-03/04/2022 02:05:11 - INFO - codeparrot_training - Step 10744: {'lr': 0.0004957060255193462, 'samples': 5501440, 'steps': 10744, 'loss/train': 2.1309826374053955}
-03/04/2022 02:05:13 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/04/2022 02:05:16 - INFO - codeparrot_training - Step 10745: {'lr': 0.0004957050461318997, 'samples': 5501952, 'steps': 10745, 'loss/train': 2.3428125381469727}
-03/04/2022 02:05:19 - INFO - codeparrot_training - Step 10746: {'lr': 0.0004957040666337422, 'samples': 5502464, 'steps': 10746, 'loss/train': 1.693940281867981}
-03/04/2022 02:05:22 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 02:05:25 - INFO - codeparrot_training - Step 10747: {'lr': 0.0004957030870248742, 'samples': 5502976, 'steps': 10747, 'loss/train': 1.0533723831176758}
-03/04/2022 02:05:28 - INFO - codeparrot_training - Step 10748: {'lr': 0.0004957021073052962, 'samples': 5503488, 'steps': 10748, 'loss/train': 2.4155125617980957}
-03/04/2022 02:05:30 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/04/2022 02:05:33 - INFO - codeparrot_training - Step 10749: {'lr': 0.0004957011274750086, 'samples': 5504000, 'steps': 10749, 'loss/train': 1.7411093711853027}
-03/04/2022 02:05:36 - INFO - codeparrot_training - Step 10750: {'lr': 0.0004957001475340119, 'samples': 5504512, 'steps': 10750, 'loss/train': 2.5288445949554443}
-03/04/2022 02:05:39 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 02:05:42 - INFO - codeparrot_training - Step 10751: {'lr': 0.0004956991674823065, 'samples': 5505024, 'steps': 10751, 'loss/train': 1.9677953720092773}
-03/04/2022 02:05:45 - INFO - codeparrot_training - Step 10752: {'lr': 0.0004956981873198928, 'samples': 5505536, 'steps': 10752, 'loss/train': 1.072310447692871}
-03/04/2022 02:05:47 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 02:05:50 - INFO - codeparrot_training - Step 10753: {'lr': 0.0004956972070467712, 'samples': 5506048, 'steps': 10753, 'loss/train': 1.9278968572616577}
-03/04/2022 02:05:53 - INFO - codeparrot_training - Step 10754: {'lr': 0.0004956962266629424, 'samples': 5506560, 'steps': 10754, 'loss/train': 2.3376381397247314}
-03/04/2022 02:05:56 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/04/2022 02:05:58 - INFO - codeparrot_training - Step 10755: {'lr': 0.0004956952461684066, 'samples': 5507072, 'steps': 10755, 'loss/train': 2.1176674365997314}
-03/04/2022 02:06:02 - INFO - codeparrot_training - Step 10756: {'lr': 0.0004956942655631644, 'samples': 5507584, 'steps': 10756, 'loss/train': 2.506089687347412}
-03/04/2022 02:06:04 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 02:06:07 - INFO - codeparrot_training - Step 10757: {'lr': 0.0004956932848472161, 'samples': 5508096, 'steps': 10757, 'loss/train': 2.116818428039551}
-03/04/2022 02:06:10 - INFO - codeparrot_training - Step 10758: {'lr': 0.0004956923040205622, 'samples': 5508608, 'steps': 10758, 'loss/train': 2.195216178894043}
-03/04/2022 02:06:12 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/04/2022 02:06:15 - INFO - codeparrot_training - Step 10759: {'lr': 0.0004956913230832031, 'samples': 5509120, 'steps': 10759, 'loss/train': 2.287726402282715}
-03/04/2022 02:06:19 - INFO - codeparrot_training - Step 10760: {'lr': 0.0004956903420351393, 'samples': 5509632, 'steps': 10760, 'loss/train': 1.3105416297912598}
-03/04/2022 02:06:21 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/04/2022 02:06:24 - INFO - codeparrot_training - Step 10761: {'lr': 0.0004956893608763713, 'samples': 5510144, 'steps': 10761, 'loss/train': 2.159395456314087}
-03/04/2022 02:06:27 - INFO - codeparrot_training - Step 10762: {'lr': 0.0004956883796068993, 'samples': 5510656, 'steps': 10762, 'loss/train': 2.145653247833252}
-03/04/2022 02:06:29 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 02:06:32 - INFO - codeparrot_training - Step 10763: {'lr': 0.000495687398226724, 'samples': 5511168, 'steps': 10763, 'loss/train': 1.7933704853057861}
-03/04/2022 02:06:36 - INFO - codeparrot_training - Step 10764: {'lr': 0.0004956864167358458, 'samples': 5511680, 'steps': 10764, 'loss/train': 1.9918205738067627}
-03/04/2022 02:06:38 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/04/2022 02:06:41 - INFO - codeparrot_training - Step 10765: {'lr': 0.000495685435134265, 'samples': 5512192, 'steps': 10765, 'loss/train': 2.6888427734375}
-03/04/2022 02:06:44 - INFO - codeparrot_training - Step 10766: {'lr': 0.0004956844534219822, 'samples': 5512704, 'steps': 10766, 'loss/train': 0.34207335114479065}
-03/04/2022 02:06:46 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/04/2022 02:06:49 - INFO - codeparrot_training - Step 10767: {'lr': 0.0004956834715989977, 'samples': 5513216, 'steps': 10767, 'loss/train': 1.7596063613891602}
-03/04/2022 02:06:53 - INFO - codeparrot_training - Step 10768: {'lr': 0.0004956824896653122, 'samples': 5513728, 'steps': 10768, 'loss/train': 2.085240125656128}
-03/04/2022 02:06:55 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 02:06:58 - INFO - codeparrot_training - Step 10769: {'lr': 0.0004956815076209257, 'samples': 5514240, 'steps': 10769, 'loss/train': 1.6744803190231323}
-03/04/2022 02:07:01 - INFO - codeparrot_training - Step 10770: {'lr': 0.0004956805254658391, 'samples': 5514752, 'steps': 10770, 'loss/train': 2.3470373153686523}
-03/04/2022 02:07:03 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/04/2022 02:07:06 - INFO - codeparrot_training - Step 10771: {'lr': 0.0004956795432000526, 'samples': 5515264, 'steps': 10771, 'loss/train': 1.7115046977996826}
-03/04/2022 02:07:09 - INFO - codeparrot_training - Step 10772: {'lr': 0.0004956785608235667, 'samples': 5515776, 'steps': 10772, 'loss/train': 2.195122480392456}
-03/04/2022 02:07:12 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/04/2022 02:07:15 - INFO - codeparrot_training - Step 10773: {'lr': 0.0004956775783363817, 'samples': 5516288, 'steps': 10773, 'loss/train': 1.8885084390640259}
-03/04/2022 02:07:18 - INFO - codeparrot_training - Step 10774: {'lr': 0.0004956765957384984, 'samples': 5516800, 'steps': 10774, 'loss/train': 1.5861122608184814}
-03/04/2022 02:07:20 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 02:07:23 - INFO - codeparrot_training - Step 10775: {'lr': 0.0004956756130299169, 'samples': 5517312, 'steps': 10775, 'loss/train': 1.8489737510681152}
-03/04/2022 02:07:26 - INFO - codeparrot_training - Step 10776: {'lr': 0.0004956746302106378, 'samples': 5517824, 'steps': 10776, 'loss/train': 2.1926889419555664}
-03/04/2022 02:07:28 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/04/2022 02:07:32 - INFO - codeparrot_training - Step 10777: {'lr': 0.0004956736472806614, 'samples': 5518336, 'steps': 10777, 'loss/train': 1.6781893968582153}
-03/04/2022 02:07:35 - INFO - codeparrot_training - Step 10778: {'lr': 0.0004956726642399883, 'samples': 5518848, 'steps': 10778, 'loss/train': 1.5832960605621338}
-03/04/2022 02:07:37 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/04/2022 02:07:40 - INFO - codeparrot_training - Step 10779: {'lr': 0.0004956716810886189, 'samples': 5519360, 'steps': 10779, 'loss/train': 1.4306352138519287}
-03/04/2022 02:07:43 - INFO - codeparrot_training - Step 10780: {'lr': 0.0004956706978265536, 'samples': 5519872, 'steps': 10780, 'loss/train': 2.490340232849121}
-03/04/2022 02:07:45 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 02:07:49 - INFO - codeparrot_training - Step 10781: {'lr': 0.0004956697144537929, 'samples': 5520384, 'steps': 10781, 'loss/train': 1.7320886850357056}
-03/04/2022 02:07:52 - INFO - codeparrot_training - Step 10782: {'lr': 0.0004956687309703372, 'samples': 5520896, 'steps': 10782, 'loss/train': 1.7626025676727295}
-03/04/2022 02:07:54 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/04/2022 02:07:57 - INFO - codeparrot_training - Step 10783: {'lr': 0.0004956677473761871, 'samples': 5521408, 'steps': 10783, 'loss/train': 2.138209104537964}
-03/04/2022 02:08:00 - INFO - codeparrot_training - Step 10784: {'lr': 0.0004956667636713427, 'samples': 5521920, 'steps': 10784, 'loss/train': 1.7787814140319824}
-03/04/2022 02:08:02 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 02:08:05 - INFO - codeparrot_training - Step 10785: {'lr': 0.0004956657798558047, 'samples': 5522432, 'steps': 10785, 'loss/train': 2.1338815689086914}
-03/04/2022 02:08:08 - INFO - codeparrot_training - Step 10786: {'lr': 0.0004956647959295735, 'samples': 5522944, 'steps': 10786, 'loss/train': 2.2905375957489014}
-03/04/2022 02:08:10 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/04/2022 02:08:14 - INFO - codeparrot_training - Step 10787: {'lr': 0.0004956638118926495, 'samples': 5523456, 'steps': 10787, 'loss/train': 2.8871796131134033}
-03/04/2022 02:08:17 - INFO - codeparrot_training - Step 10788: {'lr': 0.0004956628277450333, 'samples': 5523968, 'steps': 10788, 'loss/train': 1.8406869173049927}
-03/04/2022 02:08:19 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 02:08:22 - INFO - codeparrot_training - Step 10789: {'lr': 0.0004956618434867251, 'samples': 5524480, 'steps': 10789, 'loss/train': 0.8711960315704346}
-03/04/2022 02:08:25 - INFO - codeparrot_training - Step 10790: {'lr': 0.0004956608591177256, 'samples': 5524992, 'steps': 10790, 'loss/train': 2.3519954681396484}
-03/04/2022 02:08:27 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/04/2022 02:08:31 - INFO - codeparrot_training - Step 10791: {'lr': 0.0004956598746380349, 'samples': 5525504, 'steps': 10791, 'loss/train': 1.9175174236297607}
-03/04/2022 02:08:34 - INFO - codeparrot_training - Step 10792: {'lr': 0.0004956588900476538, 'samples': 5526016, 'steps': 10792, 'loss/train': 2.2520241737365723}
-03/04/2022 02:08:35 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 02:08:39 - INFO - codeparrot_training - Step 10793: {'lr': 0.0004956579053465826, 'samples': 5526528, 'steps': 10793, 'loss/train': 1.5429221391677856}
-03/04/2022 02:08:42 - INFO - codeparrot_training - Step 10794: {'lr': 0.0004956569205348217, 'samples': 5527040, 'steps': 10794, 'loss/train': 2.034994125366211}
-03/04/2022 02:08:44 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/04/2022 02:08:48 - INFO - codeparrot_training - Step 10795: {'lr': 0.0004956559356123717, 'samples': 5527552, 'steps': 10795, 'loss/train': 1.5804805755615234}
-03/04/2022 02:08:51 - INFO - codeparrot_training - Step 10796: {'lr': 0.0004956549505792327, 'samples': 5528064, 'steps': 10796, 'loss/train': 2.0603950023651123}
-03/04/2022 02:08:53 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 02:08:56 - INFO - codeparrot_training - Step 10797: {'lr': 0.0004956539654354055, 'samples': 5528576, 'steps': 10797, 'loss/train': 2.0351076126098633}
-03/04/2022 02:08:59 - INFO - codeparrot_training - Step 10798: {'lr': 0.0004956529801808904, 'samples': 5529088, 'steps': 10798, 'loss/train': 2.0418198108673096}
-03/04/2022 02:09:01 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 02:09:04 - INFO - codeparrot_training - Step 10799: {'lr': 0.0004956519948156879, 'samples': 5529600, 'steps': 10799, 'loss/train': 2.402442455291748}
-03/04/2022 02:09:08 - INFO - codeparrot_training - Step 10800: {'lr': 0.0004956510093397983, 'samples': 5530112, 'steps': 10800, 'loss/train': 2.28849720954895}
-03/04/2022 02:09:09 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/04/2022 02:09:13 - INFO - codeparrot_training - Step 10801: {'lr': 0.0004956500237532222, 'samples': 5530624, 'steps': 10801, 'loss/train': 1.868476390838623}
-03/04/2022 02:09:16 - INFO - codeparrot_training - Step 10802: {'lr': 0.0004956490380559601, 'samples': 5531136, 'steps': 10802, 'loss/train': 2.5059666633605957}
-03/04/2022 02:09:18 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 02:09:21 - INFO - codeparrot_training - Step 10803: {'lr': 0.0004956480522480121, 'samples': 5531648, 'steps': 10803, 'loss/train': 2.5483882427215576}
-03/04/2022 02:09:24 - INFO - codeparrot_training - Step 10804: {'lr': 0.000495647066329379, 'samples': 5532160, 'steps': 10804, 'loss/train': 1.6829454898834229}
-03/04/2022 02:09:26 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 02:09:30 - INFO - codeparrot_training - Step 10805: {'lr': 0.0004956460803000612, 'samples': 5532672, 'steps': 10805, 'loss/train': 1.8953760862350464}
-03/04/2022 02:09:33 - INFO - codeparrot_training - Step 10806: {'lr': 0.0004956450941600589, 'samples': 5533184, 'steps': 10806, 'loss/train': 2.2772810459136963}
-03/04/2022 02:09:34 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 02:09:38 - INFO - codeparrot_training - Step 10807: {'lr': 0.0004956441079093729, 'samples': 5533696, 'steps': 10807, 'loss/train': 2.034257411956787}
-03/04/2022 02:09:42 - INFO - codeparrot_training - Step 10808: {'lr': 0.0004956431215480034, 'samples': 5534208, 'steps': 10808, 'loss/train': 1.5291701555252075}
-03/04/2022 02:09:43 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/04/2022 02:09:47 - INFO - codeparrot_training - Step 10809: {'lr': 0.0004956421350759508, 'samples': 5534720, 'steps': 10809, 'loss/train': 1.7730073928833008}
-03/04/2022 02:09:50 - INFO - codeparrot_training - Step 10810: {'lr': 0.0004956411484932158, 'samples': 5535232, 'steps': 10810, 'loss/train': 1.2574745416641235}
-03/04/2022 02:09:51 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/04/2022 02:09:55 - INFO - codeparrot_training - Step 10811: {'lr': 0.0004956401617997985, 'samples': 5535744, 'steps': 10811, 'loss/train': 1.3677854537963867}
-03/04/2022 02:09:58 - INFO - codeparrot_training - Step 10812: {'lr': 0.0004956391749956997, 'samples': 5536256, 'steps': 10812, 'loss/train': 2.191715955734253}
-03/04/2022 02:10:00 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 02:10:04 - INFO - codeparrot_training - Step 10813: {'lr': 0.0004956381880809195, 'samples': 5536768, 'steps': 10813, 'loss/train': 2.874713897705078}
-03/04/2022 02:10:07 - INFO - codeparrot_training - Step 10814: {'lr': 0.0004956372010554587, 'samples': 5537280, 'steps': 10814, 'loss/train': 2.114142417907715}
-03/04/2022 02:10:10 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/04/2022 02:10:12 - INFO - codeparrot_training - Step 10815: {'lr': 0.0004956362139193174, 'samples': 5537792, 'steps': 10815, 'loss/train': 1.3084907531738281}
-03/04/2022 02:10:15 - INFO - codeparrot_training - Step 10816: {'lr': 0.0004956352266724964, 'samples': 5538304, 'steps': 10816, 'loss/train': 2.2423648834228516}
-03/04/2022 02:10:18 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 02:10:21 - INFO - codeparrot_training - Step 10817: {'lr': 0.0004956342393149959, 'samples': 5538816, 'steps': 10817, 'loss/train': 1.9394056797027588}
-03/04/2022 02:10:24 - INFO - codeparrot_training - Step 10818: {'lr': 0.0004956332518468163, 'samples': 5539328, 'steps': 10818, 'loss/train': 1.8198119401931763}
-03/04/2022 02:10:27 - INFO - codeparrot_training - Step 10819: {'lr': 0.0004956322642679583, 'samples': 5539840, 'steps': 10819, 'loss/train': 1.4178721904754639}
-03/04/2022 02:10:27 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/04/2022 02:10:32 - INFO - codeparrot_training - Step 10820: {'lr': 0.000495631276578422, 'samples': 5540352, 'steps': 10820, 'loss/train': 1.1400337219238281}
-03/04/2022 02:10:35 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/04/2022 02:10:38 - INFO - codeparrot_training - Step 10821: {'lr': 0.0004956302887782082, 'samples': 5540864, 'steps': 10821, 'loss/train': 2.2689013481140137}
-03/04/2022 02:10:41 - INFO - codeparrot_training - Step 10822: {'lr': 0.0004956293008673172, 'samples': 5541376, 'steps': 10822, 'loss/train': 1.0719020366668701}
-03/04/2022 02:10:44 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/04/2022 02:10:46 - INFO - codeparrot_training - Step 10823: {'lr': 0.0004956283128457493, 'samples': 5541888, 'steps': 10823, 'loss/train': 2.399083137512207}
-03/04/2022 02:10:49 - INFO - codeparrot_training - Step 10824: {'lr': 0.0004956273247135051, 'samples': 5542400, 'steps': 10824, 'loss/train': 2.7312610149383545}
-03/04/2022 02:10:52 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/04/2022 02:10:54 - INFO - codeparrot_training - Step 10825: {'lr': 0.0004956263364705851, 'samples': 5542912, 'steps': 10825, 'loss/train': 2.6377720832824707}
-03/04/2022 02:10:58 - INFO - codeparrot_training - Step 10826: {'lr': 0.0004956253481169895, 'samples': 5543424, 'steps': 10826, 'loss/train': 4.411136627197266}
-03/04/2022 02:11:00 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/04/2022 02:11:03 - INFO - codeparrot_training - Step 10827: {'lr': 0.0004956243596527191, 'samples': 5543936, 'steps': 10827, 'loss/train': 3.1901133060455322}
-03/04/2022 02:11:06 - INFO - codeparrot_training - Step 10828: {'lr': 0.000495623371077774, 'samples': 5544448, 'steps': 10828, 'loss/train': 2.1595239639282227}
-03/04/2022 02:11:08 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 02:11:11 - INFO - codeparrot_training - Step 10829: {'lr': 0.000495622382392155, 'samples': 5544960, 'steps': 10829, 'loss/train': 1.6992822885513306}
-03/04/2022 02:11:14 - INFO - codeparrot_training - Step 10830: {'lr': 0.0004956213935958621, 'samples': 5545472, 'steps': 10830, 'loss/train': 1.8572438955307007}
-03/04/2022 02:11:17 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/04/2022 02:11:20 - INFO - codeparrot_training - Step 10831: {'lr': 0.0004956204046888961, 'samples': 5545984, 'steps': 10831, 'loss/train': 1.912796139717102}
-03/04/2022 02:11:23 - INFO - codeparrot_training - Step 10832: {'lr': 0.0004956194156712574, 'samples': 5546496, 'steps': 10832, 'loss/train': 2.482403516769409}
-03/04/2022 02:11:25 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 02:11:28 - INFO - codeparrot_training - Step 10833: {'lr': 0.0004956184265429463, 'samples': 5547008, 'steps': 10833, 'loss/train': 1.535658836364746}
-03/04/2022 02:11:31 - INFO - codeparrot_training - Step 10834: {'lr': 0.0004956174373039634, 'samples': 5547520, 'steps': 10834, 'loss/train': 2.039088249206543}
-03/04/2022 02:11:33 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 02:11:37 - INFO - codeparrot_training - Step 10835: {'lr': 0.0004956164479543089, 'samples': 5548032, 'steps': 10835, 'loss/train': 2.710886240005493}
-03/04/2022 02:11:40 - INFO - codeparrot_training - Step 10836: {'lr': 0.0004956154584939836, 'samples': 5548544, 'steps': 10836, 'loss/train': 2.072680950164795}
-03/04/2022 02:11:42 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 02:11:45 - INFO - codeparrot_training - Step 10837: {'lr': 0.0004956144689229877, 'samples': 5549056, 'steps': 10837, 'loss/train': 1.5039139986038208}
-03/04/2022 02:11:48 - INFO - codeparrot_training - Step 10838: {'lr': 0.0004956134792413218, 'samples': 5549568, 'steps': 10838, 'loss/train': 1.568171739578247}
-03/04/2022 02:11:51 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 02:11:54 - INFO - codeparrot_training - Step 10839: {'lr': 0.0004956124894489861, 'samples': 5550080, 'steps': 10839, 'loss/train': 2.3636186122894287}
-03/04/2022 02:11:57 - INFO - codeparrot_training - Step 10840: {'lr': 0.0004956114995459813, 'samples': 5550592, 'steps': 10840, 'loss/train': 2.2164738178253174}
-03/04/2022 02:11:59 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 02:12:02 - INFO - codeparrot_training - Step 10841: {'lr': 0.0004956105095323077, 'samples': 5551104, 'steps': 10841, 'loss/train': 2.2003390789031982}
-03/04/2022 02:12:05 - INFO - codeparrot_training - Step 10842: {'lr': 0.0004956095194079658, 'samples': 5551616, 'steps': 10842, 'loss/train': 1.3054766654968262}
-03/04/2022 02:12:08 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 02:12:11 - INFO - codeparrot_training - Step 10843: {'lr': 0.000495608529172956, 'samples': 5552128, 'steps': 10843, 'loss/train': 1.7898786067962646}
-03/04/2022 02:12:14 - INFO - codeparrot_training - Step 10844: {'lr': 0.0004956075388272789, 'samples': 5552640, 'steps': 10844, 'loss/train': 1.9637031555175781}
-03/04/2022 02:12:16 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 02:12:19 - INFO - codeparrot_training - Step 10845: {'lr': 0.0004956065483709348, 'samples': 5553152, 'steps': 10845, 'loss/train': 1.961297869682312}
-03/04/2022 02:12:22 - INFO - codeparrot_training - Step 10846: {'lr': 0.0004956055578039241, 'samples': 5553664, 'steps': 10846, 'loss/train': 2.6749002933502197}
-03/04/2022 02:12:25 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/04/2022 02:12:27 - INFO - codeparrot_training - Step 10847: {'lr': 0.0004956045671262475, 'samples': 5554176, 'steps': 10847, 'loss/train': 0.7306432127952576}
-03/04/2022 02:12:31 - INFO - codeparrot_training - Step 10848: {'lr': 0.0004956035763379051, 'samples': 5554688, 'steps': 10848, 'loss/train': 1.746829628944397}
-03/04/2022 02:12:34 - INFO - codeparrot_training - Step 10849: {'lr': 0.0004956025854388976, 'samples': 5555200, 'steps': 10849, 'loss/train': 2.2327773571014404}
-03/04/2022 02:12:34 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 02:12:39 - INFO - codeparrot_training - Step 10850: {'lr': 0.0004956015944292253, 'samples': 5555712, 'steps': 10850, 'loss/train': 2.2380411624908447}
-03/04/2022 02:12:42 - INFO - codeparrot_training - Step 10851: {'lr': 0.0004956006033088888, 'samples': 5556224, 'steps': 10851, 'loss/train': 1.7610666751861572}
-03/04/2022 02:12:43 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 02:12:48 - INFO - codeparrot_training - Step 10852: {'lr': 0.0004955996120778884, 'samples': 5556736, 'steps': 10852, 'loss/train': 2.450223207473755}
-03/04/2022 02:12:51 - INFO - codeparrot_training - Step 10853: {'lr': 0.0004955986207362246, 'samples': 5557248, 'steps': 10853, 'loss/train': 0.6424915790557861}
-03/04/2022 02:12:52 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 02:12:56 - INFO - codeparrot_training - Step 10854: {'lr': 0.0004955976292838979, 'samples': 5557760, 'steps': 10854, 'loss/train': 2.450427770614624}
-03/04/2022 02:12:59 - INFO - codeparrot_training - Step 10855: {'lr': 0.0004955966377209086, 'samples': 5558272, 'steps': 10855, 'loss/train': 2.1425132751464844}
-03/04/2022 02:13:00 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 02:13:05 - INFO - codeparrot_training - Step 10856: {'lr': 0.0004955956460472573, 'samples': 5558784, 'steps': 10856, 'loss/train': 2.132314682006836}
-03/04/2022 02:13:08 - INFO - codeparrot_training - Step 10857: {'lr': 0.0004955946542629444, 'samples': 5559296, 'steps': 10857, 'loss/train': 2.2836368083953857}
-03/04/2022 02:13:13 - INFO - codeparrot_training - Step 10858: {'lr': 0.0004955936623679703, 'samples': 5559808, 'steps': 10858, 'loss/train': 1.7825231552124023}
-03/04/2022 02:13:16 - INFO - codeparrot_training - Step 10859: {'lr': 0.0004955926703623356, 'samples': 5560320, 'steps': 10859, 'loss/train': 1.7648108005523682}
-03/04/2022 02:13:17 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 02:13:22 - INFO - codeparrot_training - Step 10860: {'lr': 0.0004955916782460405, 'samples': 5560832, 'steps': 10860, 'loss/train': 2.1755788326263428}
-03/04/2022 02:13:25 - INFO - codeparrot_training - Step 10861: {'lr': 0.0004955906860190857, 'samples': 5561344, 'steps': 10861, 'loss/train': 2.418787717819214}
-03/04/2022 02:13:25 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 02:13:30 - INFO - codeparrot_training - Step 10862: {'lr': 0.0004955896936814714, 'samples': 5561856, 'steps': 10862, 'loss/train': 1.8414795398712158}
-03/04/2022 02:13:33 - INFO - codeparrot_training - Step 10863: {'lr': 0.0004955887012331982, 'samples': 5562368, 'steps': 10863, 'loss/train': 2.020426034927368}
-03/04/2022 02:13:34 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/04/2022 02:13:39 - INFO - codeparrot_training - Step 10864: {'lr': 0.0004955877086742666, 'samples': 5562880, 'steps': 10864, 'loss/train': 2.301015853881836}
-03/04/2022 02:13:42 - INFO - codeparrot_training - Step 10865: {'lr': 0.0004955867160046769, 'samples': 5563392, 'steps': 10865, 'loss/train': 1.7131156921386719}
-03/04/2022 02:13:42 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/04/2022 02:13:47 - INFO - codeparrot_training - Step 10866: {'lr': 0.0004955857232244297, 'samples': 5563904, 'steps': 10866, 'loss/train': 2.1478116512298584}
-03/04/2022 02:13:50 - INFO - codeparrot_training - Step 10867: {'lr': 0.0004955847303335253, 'samples': 5564416, 'steps': 10867, 'loss/train': 2.1242682933807373}
-03/04/2022 02:13:50 - INFO - codeparrot_training - Skipping example with length 553 (seq_length=1024)
-03/04/2022 02:13:55 - INFO - codeparrot_training - Step 10868: {'lr': 0.0004955837373319641, 'samples': 5564928, 'steps': 10868, 'loss/train': 2.532041072845459}
-03/04/2022 02:13:58 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/04/2022 02:14:01 - INFO - codeparrot_training - Step 10869: {'lr': 0.0004955827442197468, 'samples': 5565440, 'steps': 10869, 'loss/train': 2.5061867237091064}
-03/04/2022 02:14:04 - INFO - codeparrot_training - Step 10870: {'lr': 0.0004955817509968737, 'samples': 5565952, 'steps': 10870, 'loss/train': 2.4076385498046875}
-03/04/2022 02:14:07 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/04/2022 02:14:09 - INFO - codeparrot_training - Step 10871: {'lr': 0.0004955807576633452, 'samples': 5566464, 'steps': 10871, 'loss/train': 2.472597122192383}
-03/04/2022 02:14:12 - INFO - codeparrot_training - Step 10872: {'lr': 0.0004955797642191618, 'samples': 5566976, 'steps': 10872, 'loss/train': 2.0048067569732666}
-03/04/2022 02:14:15 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 02:14:18 - INFO - codeparrot_training - Step 10873: {'lr': 0.000495578770664324, 'samples': 5567488, 'steps': 10873, 'loss/train': 2.0100929737091064}
-03/04/2022 02:14:21 - INFO - codeparrot_training - Step 10874: {'lr': 0.0004955777769988322, 'samples': 5568000, 'steps': 10874, 'loss/train': 2.1989846229553223}
-03/04/2022 02:14:24 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/04/2022 02:14:26 - INFO - codeparrot_training - Step 10875: {'lr': 0.0004955767832226868, 'samples': 5568512, 'steps': 10875, 'loss/train': 1.7551888227462769}
-03/04/2022 02:14:29 - INFO - codeparrot_training - Step 10876: {'lr': 0.0004955757893358884, 'samples': 5569024, 'steps': 10876, 'loss/train': 1.399301528930664}
-03/04/2022 02:14:32 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 02:14:34 - INFO - codeparrot_training - Step 10877: {'lr': 0.0004955747953384372, 'samples': 5569536, 'steps': 10877, 'loss/train': 2.365567684173584}
-03/04/2022 02:14:38 - INFO - codeparrot_training - Step 10878: {'lr': 0.0004955738012303338, 'samples': 5570048, 'steps': 10878, 'loss/train': 2.398531913757324}
-03/04/2022 02:14:40 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 02:14:43 - INFO - codeparrot_training - Step 10879: {'lr': 0.0004955728070115787, 'samples': 5570560, 'steps': 10879, 'loss/train': 1.98537278175354}
-03/04/2022 02:14:46 - INFO - codeparrot_training - Step 10880: {'lr': 0.0004955718126821722, 'samples': 5571072, 'steps': 10880, 'loss/train': 2.6577847003936768}
-03/04/2022 02:14:49 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 02:14:51 - INFO - codeparrot_training - Step 10881: {'lr': 0.0004955708182421149, 'samples': 5571584, 'steps': 10881, 'loss/train': 1.743513822555542}
-03/04/2022 02:14:54 - INFO - codeparrot_training - Step 10882: {'lr': 0.0004955698236914071, 'samples': 5572096, 'steps': 10882, 'loss/train': 0.7536628842353821}
-03/04/2022 02:14:57 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/04/2022 02:15:00 - INFO - codeparrot_training - Step 10883: {'lr': 0.0004955688290300494, 'samples': 5572608, 'steps': 10883, 'loss/train': 2.1723220348358154}
-03/04/2022 02:15:03 - INFO - codeparrot_training - Step 10884: {'lr': 0.0004955678342580421, 'samples': 5573120, 'steps': 10884, 'loss/train': 1.7218499183654785}
-03/04/2022 02:15:05 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/04/2022 02:15:08 - INFO - codeparrot_training - Step 10885: {'lr': 0.0004955668393753858, 'samples': 5573632, 'steps': 10885, 'loss/train': 2.392829179763794}
-03/04/2022 02:15:11 - INFO - codeparrot_training - Step 10886: {'lr': 0.0004955658443820809, 'samples': 5574144, 'steps': 10886, 'loss/train': 2.367236852645874}
-03/04/2022 02:15:14 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/04/2022 02:15:17 - INFO - codeparrot_training - Step 10887: {'lr': 0.0004955648492781277, 'samples': 5574656, 'steps': 10887, 'loss/train': 1.557206153869629}
-03/04/2022 02:15:20 - INFO - codeparrot_training - Step 10888: {'lr': 0.0004955638540635269, 'samples': 5575168, 'steps': 10888, 'loss/train': 1.3662751913070679}
-03/04/2022 02:15:22 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/04/2022 02:15:25 - INFO - codeparrot_training - Step 10889: {'lr': 0.0004955628587382788, 'samples': 5575680, 'steps': 10889, 'loss/train': 2.2754039764404297}
-03/04/2022 02:15:28 - INFO - codeparrot_training - Step 10890: {'lr': 0.0004955618633023837, 'samples': 5576192, 'steps': 10890, 'loss/train': 1.9397677183151245}
-03/04/2022 02:15:31 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/04/2022 02:15:33 - INFO - codeparrot_training - Step 10891: {'lr': 0.0004955608677558424, 'samples': 5576704, 'steps': 10891, 'loss/train': 2.160358190536499}
-03/04/2022 02:15:37 - INFO - codeparrot_training - Step 10892: {'lr': 0.0004955598720986551, 'samples': 5577216, 'steps': 10892, 'loss/train': 1.937512993812561}
-03/04/2022 02:15:39 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/04/2022 02:15:42 - INFO - codeparrot_training - Step 10893: {'lr': 0.0004955588763308223, 'samples': 5577728, 'steps': 10893, 'loss/train': 2.313086986541748}
-03/04/2022 02:15:45 - INFO - codeparrot_training - Step 10894: {'lr': 0.0004955578804523445, 'samples': 5578240, 'steps': 10894, 'loss/train': 1.1499723196029663}
-03/04/2022 02:15:47 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/04/2022 02:15:50 - INFO - codeparrot_training - Step 10895: {'lr': 0.000495556884463222, 'samples': 5578752, 'steps': 10895, 'loss/train': 2.1322133541107178}
-03/04/2022 02:15:53 - INFO - codeparrot_training - Step 10896: {'lr': 0.0004955558883634555, 'samples': 5579264, 'steps': 10896, 'loss/train': 2.557964563369751}
-03/04/2022 02:15:56 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/04/2022 02:15:59 - INFO - codeparrot_training - Step 10897: {'lr': 0.0004955548921530452, 'samples': 5579776, 'steps': 10897, 'loss/train': 2.1311357021331787}
-03/04/2022 02:16:02 - INFO - codeparrot_training - Step 10898: {'lr': 0.0004955538958319917, 'samples': 5580288, 'steps': 10898, 'loss/train': 2.2009847164154053}
-03/04/2022 02:16:04 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/04/2022 02:16:07 - INFO - codeparrot_training - Step 10899: {'lr': 0.0004955528994002954, 'samples': 5580800, 'steps': 10899, 'loss/train': 1.8354178667068481}
-03/04/2022 02:16:10 - INFO - codeparrot_training - Step 10900: {'lr': 0.0004955519028579568, 'samples': 5581312, 'steps': 10900, 'loss/train': 2.399726629257202}
-03/04/2022 02:16:12 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/04/2022 02:16:15 - INFO - codeparrot_training - Step 10901: {'lr': 0.0004955509062049763, 'samples': 5581824, 'steps': 10901, 'loss/train': 1.792883038520813}
-03/04/2022 02:16:19 - INFO - codeparrot_training - Step 10902: {'lr': 0.0004955499094413542, 'samples': 5582336, 'steps': 10902, 'loss/train': 2.3845443725585938}
-03/04/2022 02:16:21 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/04/2022 02:16:24 - INFO - codeparrot_training - Step 10903: {'lr': 0.0004955489125670912, 'samples': 5582848, 'steps': 10903, 'loss/train': 2.287273645401001}
-03/04/2022 02:16:27 - INFO - codeparrot_training - Step 10904: {'lr': 0.0004955479155821877, 'samples': 5583360, 'steps': 10904, 'loss/train': 0.6858166456222534}
-03/04/2022 02:16:29 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/04/2022 02:16:32 - INFO - codeparrot_training - Step 10905: {'lr': 0.000495546918486644, 'samples': 5583872, 'steps': 10905, 'loss/train': 1.247170329093933}
-03/04/2022 02:16:36 - INFO - codeparrot_training - Step 10906: {'lr': 0.0004955459212804607, 'samples': 5584384, 'steps': 10906, 'loss/train': 2.0372579097747803}
-03/04/2022 02:16:38 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/04/2022 02:16:41 - INFO - codeparrot_training - Step 10907: {'lr': 0.0004955449239636382, 'samples': 5584896, 'steps': 10907, 'loss/train': 2.4999096393585205}
-03/04/2022 02:16:44 - INFO - codeparrot_training - Step 10908: {'lr': 0.000495543926536177, 'samples': 5585408, 'steps': 10908, 'loss/train': 1.677860975265503}
-03/04/2022 02:16:46 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 02:16:49 - INFO - codeparrot_training - Step 10909: {'lr': 0.0004955429289980774, 'samples': 5585920, 'steps': 10909, 'loss/train': 1.5301157236099243}
-03/04/2022 02:16:52 - INFO - codeparrot_training - Step 10910: {'lr': 0.00049554193134934, 'samples': 5586432, 'steps': 10910, 'loss/train': 1.9400027990341187}
-03/04/2022 02:16:54 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/04/2022 02:16:58 - INFO - codeparrot_training - Step 10911: {'lr': 0.0004955409335899651, 'samples': 5586944, 'steps': 10911, 'loss/train': 1.8089643716812134}
-03/04/2022 02:17:01 - INFO - codeparrot_training - Step 10912: {'lr': 0.0004955399357199534, 'samples': 5587456, 'steps': 10912, 'loss/train': 2.170149326324463}
-03/04/2022 02:17:03 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/04/2022 02:17:06 - INFO - codeparrot_training - Step 10913: {'lr': 0.0004955389377393051, 'samples': 5587968, 'steps': 10913, 'loss/train': 1.0649663209915161}
-03/04/2022 02:17:09 - INFO - codeparrot_training - Step 10914: {'lr': 0.0004955379396480207, 'samples': 5588480, 'steps': 10914, 'loss/train': 2.072058916091919}
-03/04/2022 02:17:11 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/04/2022 02:17:15 - INFO - codeparrot_training - Step 10915: {'lr': 0.0004955369414461007, 'samples': 5588992, 'steps': 10915, 'loss/train': 2.2287304401397705}
-03/04/2022 02:17:18 - INFO - codeparrot_training - Step 10916: {'lr': 0.0004955359431335456, 'samples': 5589504, 'steps': 10916, 'loss/train': 2.1436634063720703}
-03/04/2022 02:17:20 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/04/2022 02:17:23 - INFO - codeparrot_training - Step 10917: {'lr': 0.0004955349447103559, 'samples': 5590016, 'steps': 10917, 'loss/train': 1.2862766981124878}
-03/04/2022 02:17:26 - INFO - codeparrot_training - Step 10918: {'lr': 0.0004955339461765318, 'samples': 5590528, 'steps': 10918, 'loss/train': 1.8307185173034668}
-03/04/2022 02:17:28 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 02:17:31 - INFO - codeparrot_training - Step 10919: {'lr': 0.0004955329475320739, 'samples': 5591040, 'steps': 10919, 'loss/train': 1.8749300241470337}
-03/04/2022 02:17:35 - INFO - codeparrot_training - Step 10920: {'lr': 0.0004955319487769827, 'samples': 5591552, 'steps': 10920, 'loss/train': 1.322008490562439}
-03/04/2022 02:17:37 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 02:17:40 - INFO - codeparrot_training - Step 10921: {'lr': 0.0004955309499112586, 'samples': 5592064, 'steps': 10921, 'loss/train': 1.54649817943573}
-03/04/2022 02:17:43 - INFO - codeparrot_training - Step 10922: {'lr': 0.000495529950934902, 'samples': 5592576, 'steps': 10922, 'loss/train': 1.8213759660720825}
-03/04/2022 02:17:46 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/04/2022 02:17:49 - INFO - codeparrot_training - Step 10923: {'lr': 0.0004955289518479134, 'samples': 5593088, 'steps': 10923, 'loss/train': 2.286979913711548}
-03/04/2022 02:17:52 - INFO - codeparrot_training - Step 10924: {'lr': 0.0004955279526502931, 'samples': 5593600, 'steps': 10924, 'loss/train': 2.982553005218506}
-03/04/2022 02:17:55 - INFO - codeparrot_training - Step 10925: {'lr': 0.0004955269533420419, 'samples': 5594112, 'steps': 10925, 'loss/train': 2.0138895511627197}
-03/04/2022 02:17:57 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/04/2022 02:18:01 - INFO - codeparrot_training - Step 10926: {'lr': 0.00049552595392316, 'samples': 5594624, 'steps': 10926, 'loss/train': 2.0752761363983154}
-03/04/2022 02:18:04 - INFO - codeparrot_training - Step 10927: {'lr': 0.0004955249543936479, 'samples': 5595136, 'steps': 10927, 'loss/train': 2.408475160598755}
-03/04/2022 02:18:06 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 02:18:09 - INFO - codeparrot_training - Step 10928: {'lr': 0.000495523954753506, 'samples': 5595648, 'steps': 10928, 'loss/train': 1.659650206565857}
-03/04/2022 02:18:12 - INFO - codeparrot_training - Step 10929: {'lr': 0.0004955229550027347, 'samples': 5596160, 'steps': 10929, 'loss/train': 2.0684568881988525}
-03/04/2022 02:18:14 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/04/2022 02:18:18 - INFO - codeparrot_training - Step 10930: {'lr': 0.0004955219551413347, 'samples': 5596672, 'steps': 10930, 'loss/train': 2.2282440662384033}
-03/04/2022 02:18:21 - INFO - codeparrot_training - Step 10931: {'lr': 0.0004955209551693063, 'samples': 5597184, 'steps': 10931, 'loss/train': 2.311058759689331}
-03/04/2022 02:18:23 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/04/2022 02:18:26 - INFO - codeparrot_training - Step 10932: {'lr': 0.0004955199550866498, 'samples': 5597696, 'steps': 10932, 'loss/train': 2.0307416915893555}
-03/04/2022 02:18:29 - INFO - codeparrot_training - Step 10933: {'lr': 0.000495518954893366, 'samples': 5598208, 'steps': 10933, 'loss/train': 2.1588892936706543}
-03/04/2022 02:18:31 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/04/2022 02:18:35 - INFO - codeparrot_training - Step 10934: {'lr': 0.000495517954589455, 'samples': 5598720, 'steps': 10934, 'loss/train': 1.981829285621643}
-03/04/2022 02:18:38 - INFO - codeparrot_training - Step 10935: {'lr': 0.0004955169541749173, 'samples': 5599232, 'steps': 10935, 'loss/train': 2.5131425857543945}
-03/04/2022 02:18:40 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 02:18:43 - INFO - codeparrot_training - Step 10936: {'lr': 0.0004955159536497536, 'samples': 5599744, 'steps': 10936, 'loss/train': 1.9648710489273071}
-03/04/2022 02:18:46 - INFO - codeparrot_training - Step 10937: {'lr': 0.0004955149530139643, 'samples': 5600256, 'steps': 10937, 'loss/train': 1.5572162866592407}
-03/04/2022 02:18:49 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 02:18:51 - INFO - codeparrot_training - Step 10938: {'lr': 0.0004955139522675496, 'samples': 5600768, 'steps': 10938, 'loss/train': 2.567257881164551}
-03/04/2022 02:18:55 - INFO - codeparrot_training - Step 10939: {'lr': 0.0004955129514105101, 'samples': 5601280, 'steps': 10939, 'loss/train': 0.46980899572372437}
-03/04/2022 02:18:57 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/04/2022 02:19:00 - INFO - codeparrot_training - Step 10940: {'lr': 0.0004955119504428464, 'samples': 5601792, 'steps': 10940, 'loss/train': 1.7140202522277832}
-03/04/2022 02:19:03 - INFO - codeparrot_training - Step 10941: {'lr': 0.0004955109493645587, 'samples': 5602304, 'steps': 10941, 'loss/train': 1.9371583461761475}
-03/04/2022 02:19:06 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/04/2022 02:19:08 - INFO - codeparrot_training - Step 10942: {'lr': 0.0004955099481756475, 'samples': 5602816, 'steps': 10942, 'loss/train': 2.3241119384765625}
-03/04/2022 02:19:11 - INFO - codeparrot_training - Step 10943: {'lr': 0.0004955089468761133, 'samples': 5603328, 'steps': 10943, 'loss/train': 3.224862813949585}
-03/04/2022 02:19:14 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 02:19:17 - INFO - codeparrot_training - Step 10944: {'lr': 0.0004955079454659567, 'samples': 5603840, 'steps': 10944, 'loss/train': 2.236396074295044}
-03/04/2022 02:19:20 - INFO - codeparrot_training - Step 10945: {'lr': 0.0004955069439451778, 'samples': 5604352, 'steps': 10945, 'loss/train': 1.578511357307434}
-03/04/2022 02:19:22 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 02:19:25 - INFO - codeparrot_training - Step 10946: {'lr': 0.0004955059423137774, 'samples': 5604864, 'steps': 10946, 'loss/train': 2.3046019077301025}
-03/04/2022 02:19:28 - INFO - codeparrot_training - Step 10947: {'lr': 0.0004955049405717558, 'samples': 5605376, 'steps': 10947, 'loss/train': 1.8547589778900146}
-03/04/2022 02:19:30 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 02:19:33 - INFO - codeparrot_training - Step 10948: {'lr': 0.0004955039387191135, 'samples': 5605888, 'steps': 10948, 'loss/train': 2.571202278137207}
-03/04/2022 02:19:37 - INFO - codeparrot_training - Step 10949: {'lr': 0.0004955029367558508, 'samples': 5606400, 'steps': 10949, 'loss/train': 1.8650946617126465}
-03/04/2022 02:19:39 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/04/2022 02:19:42 - INFO - codeparrot_training - Step 10950: {'lr': 0.0004955019346819684, 'samples': 5606912, 'steps': 10950, 'loss/train': 1.1819202899932861}
-03/04/2022 02:19:45 - INFO - codeparrot_training - Step 10951: {'lr': 0.0004955009324974666, 'samples': 5607424, 'steps': 10951, 'loss/train': 1.8149409294128418}
-03/04/2022 02:19:47 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/04/2022 02:19:50 - INFO - codeparrot_training - Step 10952: {'lr': 0.0004954999302023458, 'samples': 5607936, 'steps': 10952, 'loss/train': 3.0659334659576416}
-03/04/2022 02:19:53 - INFO - codeparrot_training - Step 10953: {'lr': 0.0004954989277966064, 'samples': 5608448, 'steps': 10953, 'loss/train': 1.9981465339660645}
-03/04/2022 02:19:55 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/04/2022 02:19:59 - INFO - codeparrot_training - Step 10954: {'lr': 0.0004954979252802491, 'samples': 5608960, 'steps': 10954, 'loss/train': 1.6878935098648071}
-03/04/2022 02:20:02 - INFO - codeparrot_training - Step 10955: {'lr': 0.0004954969226532743, 'samples': 5609472, 'steps': 10955, 'loss/train': 2.1103761196136475}
-03/04/2022 02:20:04 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/04/2022 02:20:07 - INFO - codeparrot_training - Step 10956: {'lr': 0.0004954959199156824, 'samples': 5609984, 'steps': 10956, 'loss/train': 1.9259955883026123}
-03/04/2022 02:20:10 - INFO - codeparrot_training - Step 10957: {'lr': 0.0004954949170674736, 'samples': 5610496, 'steps': 10957, 'loss/train': 1.9187884330749512}
-03/04/2022 02:20:12 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 02:20:16 - INFO - codeparrot_training - Step 10958: {'lr': 0.0004954939141086488, 'samples': 5611008, 'steps': 10958, 'loss/train': 1.3611406087875366}
-03/04/2022 02:20:19 - INFO - codeparrot_training - Step 10959: {'lr': 0.0004954929110392081, 'samples': 5611520, 'steps': 10959, 'loss/train': 2.9131956100463867}
-03/04/2022 02:20:21 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/04/2022 02:20:24 - INFO - codeparrot_training - Step 10960: {'lr': 0.0004954919078591521, 'samples': 5612032, 'steps': 10960, 'loss/train': 1.039778232574463}
-03/04/2022 02:20:28 - INFO - codeparrot_training - Step 10961: {'lr': 0.0004954909045684812, 'samples': 5612544, 'steps': 10961, 'loss/train': 1.3834952116012573}
-03/04/2022 02:20:31 - INFO - codeparrot_training - Step 10962: {'lr': 0.000495489901167196, 'samples': 5613056, 'steps': 10962, 'loss/train': 0.7584623694419861}
-03/04/2022 02:20:31 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 02:20:36 - INFO - codeparrot_training - Step 10963: {'lr': 0.0004954888976552968, 'samples': 5613568, 'steps': 10963, 'loss/train': 2.89015531539917}
-03/04/2022 02:20:39 - INFO - codeparrot_training - Step 10964: {'lr': 0.0004954878940327841, 'samples': 5614080, 'steps': 10964, 'loss/train': 2.1556854248046875}
-03/04/2022 02:20:39 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/04/2022 02:20:44 - INFO - codeparrot_training - Step 10965: {'lr': 0.0004954868902996582, 'samples': 5614592, 'steps': 10965, 'loss/train': 2.0677640438079834}
-03/04/2022 02:20:48 - INFO - codeparrot_training - Step 10966: {'lr': 0.0004954858864559199, 'samples': 5615104, 'steps': 10966, 'loss/train': 1.9733927249908447}
-03/04/2022 02:20:48 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/04/2022 02:20:53 - INFO - codeparrot_training - Step 10967: {'lr': 0.0004954848825015694, 'samples': 5615616, 'steps': 10967, 'loss/train': 0.19943493604660034}
-03/04/2022 02:20:56 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/04/2022 02:20:58 - INFO - codeparrot_training - Step 10968: {'lr': 0.0004954838784366071, 'samples': 5616128, 'steps': 10968, 'loss/train': 1.38599693775177}
-03/04/2022 02:21:01 - INFO - codeparrot_training - Step 10969: {'lr': 0.0004954828742610336, 'samples': 5616640, 'steps': 10969, 'loss/train': 1.5525113344192505}
-03/04/2022 02:21:04 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 02:21:07 - INFO - codeparrot_training - Step 10970: {'lr': 0.0004954818699748493, 'samples': 5617152, 'steps': 10970, 'loss/train': 1.9588727951049805}
-03/04/2022 02:21:10 - INFO - codeparrot_training - Step 10971: {'lr': 0.0004954808655780546, 'samples': 5617664, 'steps': 10971, 'loss/train': 2.6807494163513184}
-03/04/2022 02:21:12 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 02:21:15 - INFO - codeparrot_training - Step 10972: {'lr': 0.0004954798610706502, 'samples': 5618176, 'steps': 10972, 'loss/train': 1.7457486391067505}
-03/04/2022 02:21:19 - INFO - codeparrot_training - Step 10973: {'lr': 0.0004954788564526362, 'samples': 5618688, 'steps': 10973, 'loss/train': 3.0490710735321045}
-03/04/2022 02:21:22 - INFO - codeparrot_training - Step 10974: {'lr': 0.0004954778517240133, 'samples': 5619200, 'steps': 10974, 'loss/train': 2.2590253353118896}
-03/04/2022 02:21:23 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/04/2022 02:21:28 - INFO - codeparrot_training - Step 10975: {'lr': 0.0004954768468847818, 'samples': 5619712, 'steps': 10975, 'loss/train': 1.3115782737731934}
-03/04/2022 02:21:31 - INFO - codeparrot_training - Step 10976: {'lr': 0.0004954758419349422, 'samples': 5620224, 'steps': 10976, 'loss/train': 2.072587251663208}
-03/04/2022 02:21:32 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 02:21:36 - INFO - codeparrot_training - Step 10977: {'lr': 0.000495474836874495, 'samples': 5620736, 'steps': 10977, 'loss/train': 2.310091018676758}
-03/04/2022 02:21:39 - INFO - codeparrot_training - Step 10978: {'lr': 0.0004954738317034408, 'samples': 5621248, 'steps': 10978, 'loss/train': 1.7965638637542725}
-03/04/2022 02:21:41 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/04/2022 02:21:45 - INFO - codeparrot_training - Step 10979: {'lr': 0.0004954728264217796, 'samples': 5621760, 'steps': 10979, 'loss/train': 1.866182804107666}
-03/04/2022 02:21:48 - INFO - codeparrot_training - Step 10980: {'lr': 0.0004954718210295123, 'samples': 5622272, 'steps': 10980, 'loss/train': 1.2996926307678223}
-03/04/2022 02:21:49 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 02:21:53 - INFO - codeparrot_training - Step 10981: {'lr': 0.0004954708155266392, 'samples': 5622784, 'steps': 10981, 'loss/train': 2.292687177658081}
-03/04/2022 02:21:56 - INFO - codeparrot_training - Step 10982: {'lr': 0.0004954698099131606, 'samples': 5623296, 'steps': 10982, 'loss/train': 2.0971691608428955}
-03/04/2022 02:21:57 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 02:22:02 - INFO - codeparrot_training - Step 10983: {'lr': 0.0004954688041890772, 'samples': 5623808, 'steps': 10983, 'loss/train': 1.9754130840301514}
-03/04/2022 02:22:05 - INFO - codeparrot_training - Step 10984: {'lr': 0.0004954677983543893, 'samples': 5624320, 'steps': 10984, 'loss/train': 6.193536758422852}
-03/04/2022 02:22:08 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 02:22:10 - INFO - codeparrot_training - Step 10985: {'lr': 0.0004954667924090974, 'samples': 5624832, 'steps': 10985, 'loss/train': 1.2701234817504883}
-03/04/2022 02:22:13 - INFO - codeparrot_training - Step 10986: {'lr': 0.000495465786353202, 'samples': 5625344, 'steps': 10986, 'loss/train': 2.0692079067230225}
-03/04/2022 02:22:16 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 02:22:19 - INFO - codeparrot_training - Step 10987: {'lr': 0.0004954647801867035, 'samples': 5625856, 'steps': 10987, 'loss/train': 3.07651686668396}
-03/04/2022 02:22:22 - INFO - codeparrot_training - Step 10988: {'lr': 0.0004954637739096023, 'samples': 5626368, 'steps': 10988, 'loss/train': 1.8048628568649292}
-03/04/2022 02:22:24 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/04/2022 02:22:27 - INFO - codeparrot_training - Step 10989: {'lr': 0.0004954627675218989, 'samples': 5626880, 'steps': 10989, 'loss/train': 1.93551766872406}
-03/04/2022 02:22:30 - INFO - codeparrot_training - Step 10990: {'lr': 0.0004954617610235939, 'samples': 5627392, 'steps': 10990, 'loss/train': 1.6918847560882568}
-03/04/2022 02:22:33 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/04/2022 02:22:35 - INFO - codeparrot_training - Step 10991: {'lr': 0.0004954607544146875, 'samples': 5627904, 'steps': 10991, 'loss/train': 2.2075822353363037}
-03/04/2022 02:22:38 - INFO - codeparrot_training - Step 10992: {'lr': 0.0004954597476951804, 'samples': 5628416, 'steps': 10992, 'loss/train': 2.0948057174682617}
-03/04/2022 02:22:41 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 02:22:44 - INFO - codeparrot_training - Step 10993: {'lr': 0.0004954587408650727, 'samples': 5628928, 'steps': 10993, 'loss/train': 2.4511032104492188}
-03/04/2022 02:22:47 - INFO - codeparrot_training - Step 10994: {'lr': 0.0004954577339243652, 'samples': 5629440, 'steps': 10994, 'loss/train': 1.5915918350219727}
-03/04/2022 02:22:49 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 02:22:52 - INFO - codeparrot_training - Step 10995: {'lr': 0.0004954567268730582, 'samples': 5629952, 'steps': 10995, 'loss/train': 1.8461724519729614}
-03/04/2022 02:22:55 - INFO - codeparrot_training - Step 10996: {'lr': 0.0004954557197111522, 'samples': 5630464, 'steps': 10996, 'loss/train': 2.5654656887054443}
-03/04/2022 02:22:58 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 02:23:01 - INFO - codeparrot_training - Step 10997: {'lr': 0.0004954547124386477, 'samples': 5630976, 'steps': 10997, 'loss/train': 2.2958121299743652}
-03/04/2022 02:23:04 - INFO - codeparrot_training - Step 10998: {'lr': 0.0004954537050555451, 'samples': 5631488, 'steps': 10998, 'loss/train': 1.8009968996047974}
-03/04/2022 02:23:07 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/04/2022 02:23:09 - INFO - codeparrot_training - Step 10999: {'lr': 0.0004954526975618447, 'samples': 5632000, 'steps': 10999, 'loss/train': 2.7336997985839844}
-03/04/2022 02:23:12 - INFO - codeparrot_training - Step 11000: {'lr': 0.0004954516899575473, 'samples': 5632512, 'steps': 11000, 'loss/train': 2.4718573093414307}
-03/04/2022 02:23:15 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/04/2022 02:23:17 - INFO - codeparrot_training - Step 11001: {'lr': 0.000495450682242653, 'samples': 5633024, 'steps': 11001, 'loss/train': 1.7458832263946533}
-03/04/2022 02:23:21 - INFO - codeparrot_training - Step 11002: {'lr': 0.0004954496744171624, 'samples': 5633536, 'steps': 11002, 'loss/train': 1.2365106344223022}
-03/04/2022 02:23:24 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 02:23:26 - INFO - codeparrot_training - Step 11003: {'lr': 0.0004954486664810762, 'samples': 5634048, 'steps': 11003, 'loss/train': 1.4638330936431885}
-03/04/2022 02:23:29 - INFO - codeparrot_training - Step 11004: {'lr': 0.0004954476584343945, 'samples': 5634560, 'steps': 11004, 'loss/train': 2.546274185180664}
-03/04/2022 02:23:32 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 02:23:34 - INFO - codeparrot_training - Step 11005: {'lr': 0.0004954466502771178, 'samples': 5635072, 'steps': 11005, 'loss/train': 2.396332263946533}
-03/04/2022 02:23:38 - INFO - codeparrot_training - Step 11006: {'lr': 0.0004954456420092466, 'samples': 5635584, 'steps': 11006, 'loss/train': 1.9442449808120728}
-03/04/2022 02:23:40 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/04/2022 02:23:43 - INFO - codeparrot_training - Step 11007: {'lr': 0.0004954446336307814, 'samples': 5636096, 'steps': 11007, 'loss/train': 2.4084839820861816}
-03/04/2022 02:23:46 - INFO - codeparrot_training - Step 11008: {'lr': 0.0004954436251417227, 'samples': 5636608, 'steps': 11008, 'loss/train': 1.5389796495437622}
-03/04/2022 02:23:49 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/04/2022 02:23:51 - INFO - codeparrot_training - Step 11009: {'lr': 0.0004954426165420709, 'samples': 5637120, 'steps': 11009, 'loss/train': 1.4605859518051147}
-03/04/2022 02:23:55 - INFO - codeparrot_training - Step 11010: {'lr': 0.0004954416078318263, 'samples': 5637632, 'steps': 11010, 'loss/train': 2.814195156097412}
-03/04/2022 02:23:58 - INFO - codeparrot_training - Step 11011: {'lr': 0.0004954405990109897, 'samples': 5638144, 'steps': 11011, 'loss/train': 6.864246368408203}
-03/04/2022 02:23:58 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 02:24:03 - INFO - codeparrot_training - Step 11012: {'lr': 0.0004954395900795611, 'samples': 5638656, 'steps': 11012, 'loss/train': 2.7609753608703613}
-03/04/2022 02:24:06 - INFO - codeparrot_training - Step 11013: {'lr': 0.0004954385810375415, 'samples': 5639168, 'steps': 11013, 'loss/train': 2.4438745975494385}
-03/04/2022 02:24:06 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/04/2022 02:24:12 - INFO - codeparrot_training - Step 11014: {'lr': 0.0004954375718849308, 'samples': 5639680, 'steps': 11014, 'loss/train': 1.5098779201507568}
-03/04/2022 02:24:15 - INFO - codeparrot_training - Step 11015: {'lr': 0.0004954365626217299, 'samples': 5640192, 'steps': 11015, 'loss/train': 1.7130277156829834}
-03/04/2022 02:24:15 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 02:24:20 - INFO - codeparrot_training - Step 11016: {'lr': 0.0004954355532479391, 'samples': 5640704, 'steps': 11016, 'loss/train': 2.3505961894989014}
-03/04/2022 02:24:23 - INFO - codeparrot_training - Step 11017: {'lr': 0.0004954345437635587, 'samples': 5641216, 'steps': 11017, 'loss/train': 2.4672882556915283}
-03/04/2022 02:24:23 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/04/2022 02:24:29 - INFO - codeparrot_training - Step 11018: {'lr': 0.0004954335341685893, 'samples': 5641728, 'steps': 11018, 'loss/train': 2.2711217403411865}
-03/04/2022 02:24:32 - INFO - codeparrot_training - Step 11019: {'lr': 0.0004954325244630315, 'samples': 5642240, 'steps': 11019, 'loss/train': 1.5650464296340942}
-03/04/2022 02:24:32 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 02:24:37 - INFO - codeparrot_training - Step 11020: {'lr': 0.0004954315146468854, 'samples': 5642752, 'steps': 11020, 'loss/train': 2.3162362575531006}
-03/04/2022 02:24:40 - INFO - codeparrot_training - Step 11021: {'lr': 0.0004954305047201517, 'samples': 5643264, 'steps': 11021, 'loss/train': 2.2504723072052}
-03/04/2022 02:24:40 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/04/2022 02:24:45 - INFO - codeparrot_training - Step 11022: {'lr': 0.0004954294946828308, 'samples': 5643776, 'steps': 11022, 'loss/train': 2.329416036605835}
-03/04/2022 02:24:49 - INFO - codeparrot_training - Step 11023: {'lr': 0.0004954284845349232, 'samples': 5644288, 'steps': 11023, 'loss/train': 2.243703603744507}
-03/04/2022 02:24:49 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/04/2022 02:24:54 - INFO - codeparrot_training - Step 11024: {'lr': 0.0004954274742764292, 'samples': 5644800, 'steps': 11024, 'loss/train': 2.1406023502349854}
-03/04/2022 02:24:57 - INFO - codeparrot_training - Step 11025: {'lr': 0.0004954264639073495, 'samples': 5645312, 'steps': 11025, 'loss/train': 2.226254940032959}
-03/04/2022 02:24:57 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/04/2022 02:25:02 - INFO - codeparrot_training - Step 11026: {'lr': 0.0004954254534276843, 'samples': 5645824, 'steps': 11026, 'loss/train': 2.061476469039917}
-03/04/2022 02:25:06 - INFO - codeparrot_training - Step 11027: {'lr': 0.0004954244428374343, 'samples': 5646336, 'steps': 11027, 'loss/train': 2.038874864578247}
-03/04/2022 02:25:06 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/04/2022 02:25:11 - INFO - codeparrot_training - Step 11028: {'lr': 0.0004954234321365998, 'samples': 5646848, 'steps': 11028, 'loss/train': 2.728978395462036}
-03/04/2022 02:25:14 - INFO - codeparrot_training - Step 11029: {'lr': 0.0004954224213251813, 'samples': 5647360, 'steps': 11029, 'loss/train': 2.702738046646118}
-03/04/2022 02:25:14 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 02:25:19 - INFO - codeparrot_training - Step 11030: {'lr': 0.0004954214104031791, 'samples': 5647872, 'steps': 11030, 'loss/train': 3.030433416366577}
-03/04/2022 02:25:22 - INFO - codeparrot_training - Step 11031: {'lr': 0.0004954203993705939, 'samples': 5648384, 'steps': 11031, 'loss/train': 2.5519235134124756}
-03/04/2022 02:25:23 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/04/2022 02:25:28 - INFO - codeparrot_training - Step 11032: {'lr': 0.0004954193882274261, 'samples': 5648896, 'steps': 11032, 'loss/train': 1.5737206935882568}
-03/04/2022 02:25:31 - INFO - codeparrot_training - Step 11033: {'lr': 0.000495418376973676, 'samples': 5649408, 'steps': 11033, 'loss/train': 2.0909364223480225}
-03/04/2022 02:25:32 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/04/2022 02:25:36 - INFO - codeparrot_training - Step 11034: {'lr': 0.0004954173656093443, 'samples': 5649920, 'steps': 11034, 'loss/train': 2.1410677433013916}
-03/04/2022 02:25:40 - INFO - codeparrot_training - Step 11035: {'lr': 0.0004954163541344312, 'samples': 5650432, 'steps': 11035, 'loss/train': 1.7754294872283936}
-03/04/2022 02:25:40 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/04/2022 02:25:45 - INFO - codeparrot_training - Step 11036: {'lr': 0.0004954153425489374, 'samples': 5650944, 'steps': 11036, 'loss/train': 2.3967373371124268}
-03/04/2022 02:25:48 - INFO - codeparrot_training - Step 11037: {'lr': 0.0004954143308528631, 'samples': 5651456, 'steps': 11037, 'loss/train': 0.6427550911903381}
-03/04/2022 02:25:49 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 02:25:53 - INFO - codeparrot_training - Step 11038: {'lr': 0.000495413319046209, 'samples': 5651968, 'steps': 11038, 'loss/train': 2.0008623600006104}
-03/04/2022 02:25:56 - INFO - codeparrot_training - Step 11039: {'lr': 0.0004954123071289754, 'samples': 5652480, 'steps': 11039, 'loss/train': 1.7895829677581787}
-03/04/2022 02:25:57 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/04/2022 02:26:02 - INFO - codeparrot_training - Step 11040: {'lr': 0.0004954112951011628, 'samples': 5652992, 'steps': 11040, 'loss/train': 2.6958372592926025}
-03/04/2022 02:26:05 - INFO - codeparrot_training - Step 11041: {'lr': 0.0004954102829627717, 'samples': 5653504, 'steps': 11041, 'loss/train': 1.788671612739563}
-03/04/2022 02:26:05 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/04/2022 02:26:10 - INFO - codeparrot_training - Step 11042: {'lr': 0.0004954092707138024, 'samples': 5654016, 'steps': 11042, 'loss/train': 2.048844337463379}
-03/04/2022 02:26:13 - INFO - codeparrot_training - Step 11043: {'lr': 0.0004954082583542557, 'samples': 5654528, 'steps': 11043, 'loss/train': 2.219526529312134}
-03/04/2022 02:26:14 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 02:26:19 - INFO - codeparrot_training - Step 11044: {'lr': 0.0004954072458841315, 'samples': 5655040, 'steps': 11044, 'loss/train': 1.8512377738952637}
-03/04/2022 02:26:22 - INFO - codeparrot_training - Step 11045: {'lr': 0.0004954062333034308, 'samples': 5655552, 'steps': 11045, 'loss/train': 2.2142961025238037}
-03/04/2022 02:26:22 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/04/2022 02:26:27 - INFO - codeparrot_training - Step 11046: {'lr': 0.0004954052206121538, 'samples': 5656064, 'steps': 11046, 'loss/train': 2.4284608364105225}
-03/04/2022 02:26:30 - INFO - codeparrot_training - Step 11047: {'lr': 0.000495404207810301, 'samples': 5656576, 'steps': 11047, 'loss/train': 2.2168240547180176}
-03/04/2022 02:26:30 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 02:26:35 - INFO - codeparrot_training - Step 11048: {'lr': 0.0004954031948978729, 'samples': 5657088, 'steps': 11048, 'loss/train': 0.222852885723114}
-03/04/2022 02:26:39 - INFO - codeparrot_training - Step 11049: {'lr': 0.0004954021818748698, 'samples': 5657600, 'steps': 11049, 'loss/train': 2.079723834991455}
-03/04/2022 02:26:39 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/04/2022 02:26:44 - INFO - codeparrot_training - Step 11050: {'lr': 0.0004954011687412923, 'samples': 5658112, 'steps': 11050, 'loss/train': 1.5761903524398804}
-03/04/2022 02:26:47 - INFO - codeparrot_training - Step 11051: {'lr': 0.0004954001554971409, 'samples': 5658624, 'steps': 11051, 'loss/train': 1.919529914855957}
-03/04/2022 02:26:47 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/04/2022 02:26:52 - INFO - codeparrot_training - Step 11052: {'lr': 0.0004953991421424159, 'samples': 5659136, 'steps': 11052, 'loss/train': 1.5261369943618774}
-03/04/2022 02:26:55 - INFO - codeparrot_training - Step 11053: {'lr': 0.0004953981286771178, 'samples': 5659648, 'steps': 11053, 'loss/train': 2.1116554737091064}
-03/04/2022 02:26:55 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 02:27:01 - INFO - codeparrot_training - Step 11054: {'lr': 0.0004953971151012471, 'samples': 5660160, 'steps': 11054, 'loss/train': 2.0603742599487305}
-03/04/2022 02:27:04 - INFO - codeparrot_training - Step 11055: {'lr': 0.0004953961014148043, 'samples': 5660672, 'steps': 11055, 'loss/train': 1.3595341444015503}
-03/04/2022 02:27:04 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 02:27:09 - INFO - codeparrot_training - Step 11056: {'lr': 0.0004953950876177897, 'samples': 5661184, 'steps': 11056, 'loss/train': 1.0721499919891357}
-03/04/2022 02:27:12 - INFO - codeparrot_training - Step 11057: {'lr': 0.000495394073710204, 'samples': 5661696, 'steps': 11057, 'loss/train': 2.2999682426452637}
-03/04/2022 02:27:12 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 02:27:18 - INFO - codeparrot_training - Step 11058: {'lr': 0.0004953930596920474, 'samples': 5662208, 'steps': 11058, 'loss/train': 0.8147758841514587}
-03/04/2022 02:27:20 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/04/2022 02:27:23 - INFO - codeparrot_training - Step 11059: {'lr': 0.0004953920455633206, 'samples': 5662720, 'steps': 11059, 'loss/train': 2.244130849838257}
-03/04/2022 02:27:26 - INFO - codeparrot_training - Step 11060: {'lr': 0.0004953910313240239, 'samples': 5663232, 'steps': 11060, 'loss/train': 1.6613484621047974}
-03/04/2022 02:27:28 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/04/2022 02:27:31 - INFO - codeparrot_training - Step 11061: {'lr': 0.0004953900169741577, 'samples': 5663744, 'steps': 11061, 'loss/train': 1.5399154424667358}
-03/04/2022 02:27:34 - INFO - codeparrot_training - Step 11062: {'lr': 0.0004953890025137226, 'samples': 5664256, 'steps': 11062, 'loss/train': 2.451777696609497}
-03/04/2022 02:27:37 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/04/2022 02:27:40 - INFO - codeparrot_training - Step 11063: {'lr': 0.000495387987942719, 'samples': 5664768, 'steps': 11063, 'loss/train': 2.5924322605133057}
-03/04/2022 02:27:43 - INFO - codeparrot_training - Step 11064: {'lr': 0.0004953869732611474, 'samples': 5665280, 'steps': 11064, 'loss/train': 1.277001976966858}
-03/04/2022 02:27:45 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/04/2022 02:27:48 - INFO - codeparrot_training - Step 11065: {'lr': 0.0004953859584690081, 'samples': 5665792, 'steps': 11065, 'loss/train': 2.0807480812072754}
-03/04/2022 02:27:51 - INFO - codeparrot_training - Step 11066: {'lr': 0.0004953849435663018, 'samples': 5666304, 'steps': 11066, 'loss/train': 2.389115571975708}
-03/04/2022 02:27:53 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/04/2022 02:27:56 - INFO - codeparrot_training - Step 11067: {'lr': 0.0004953839285530287, 'samples': 5666816, 'steps': 11067, 'loss/train': 2.303805351257324}
-03/04/2022 02:27:59 - INFO - codeparrot_training - Step 11068: {'lr': 0.0004953829134291895, 'samples': 5667328, 'steps': 11068, 'loss/train': 1.9022901058197021}
-03/04/2022 02:28:01 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 02:28:05 - INFO - codeparrot_training - Step 11069: {'lr': 0.0004953818981947845, 'samples': 5667840, 'steps': 11069, 'loss/train': 2.1040124893188477}
-03/04/2022 02:28:08 - INFO - codeparrot_training - Step 11070: {'lr': 0.0004953808828498142, 'samples': 5668352, 'steps': 11070, 'loss/train': 1.4955428838729858}
-03/04/2022 02:28:10 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/04/2022 02:28:13 - INFO - codeparrot_training - Step 11071: {'lr': 0.0004953798673942791, 'samples': 5668864, 'steps': 11071, 'loss/train': 1.1247268915176392}
-03/04/2022 02:28:16 - INFO - codeparrot_training - Step 11072: {'lr': 0.0004953788518281796, 'samples': 5669376, 'steps': 11072, 'loss/train': 0.7129000425338745}
-03/04/2022 02:28:18 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 02:28:21 - INFO - codeparrot_training - Step 11073: {'lr': 0.0004953778361515163, 'samples': 5669888, 'steps': 11073, 'loss/train': 2.0775434970855713}
-03/04/2022 02:28:25 - INFO - codeparrot_training - Step 11074: {'lr': 0.0004953768203642893, 'samples': 5670400, 'steps': 11074, 'loss/train': 1.4718437194824219}
-03/04/2022 02:28:27 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/04/2022 02:28:30 - INFO - codeparrot_training - Step 11075: {'lr': 0.0004953758044664994, 'samples': 5670912, 'steps': 11075, 'loss/train': 1.8248767852783203}
-03/04/2022 02:28:33 - INFO - codeparrot_training - Step 11076: {'lr': 0.0004953747884581469, 'samples': 5671424, 'steps': 11076, 'loss/train': 2.2770791053771973}
-03/04/2022 02:28:35 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/04/2022 02:28:38 - INFO - codeparrot_training - Step 11077: {'lr': 0.0004953737723392324, 'samples': 5671936, 'steps': 11077, 'loss/train': 2.103163719177246}
-03/04/2022 02:28:41 - INFO - codeparrot_training - Step 11078: {'lr': 0.0004953727561097562, 'samples': 5672448, 'steps': 11078, 'loss/train': 1.3436322212219238}
-03/04/2022 02:28:43 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/04/2022 02:28:47 - INFO - codeparrot_training - Step 11079: {'lr': 0.0004953717397697189, 'samples': 5672960, 'steps': 11079, 'loss/train': 2.890839099884033}
-03/04/2022 02:28:50 - INFO - codeparrot_training - Step 11080: {'lr': 0.0004953707233191207, 'samples': 5673472, 'steps': 11080, 'loss/train': 2.3875961303710938}
-03/04/2022 02:28:52 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/04/2022 02:28:55 - INFO - codeparrot_training - Step 11081: {'lr': 0.0004953697067579624, 'samples': 5673984, 'steps': 11081, 'loss/train': 2.233677625656128}
-03/04/2022 02:28:58 - INFO - codeparrot_training - Step 11082: {'lr': 0.0004953686900862442, 'samples': 5674496, 'steps': 11082, 'loss/train': 2.578596830368042}
-03/04/2022 02:29:01 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 02:29:04 - INFO - codeparrot_training - Step 11083: {'lr': 0.0004953676733039668, 'samples': 5675008, 'steps': 11083, 'loss/train': 1.4893068075180054}
-03/04/2022 02:29:07 - INFO - codeparrot_training - Step 11084: {'lr': 0.0004953666564111303, 'samples': 5675520, 'steps': 11084, 'loss/train': 1.7881871461868286}
-03/04/2022 02:29:09 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 02:29:12 - INFO - codeparrot_training - Step 11085: {'lr': 0.0004953656394077355, 'samples': 5676032, 'steps': 11085, 'loss/train': 1.2727372646331787}
-03/04/2022 02:29:15 - INFO - codeparrot_training - Step 11086: {'lr': 0.0004953646222937828, 'samples': 5676544, 'steps': 11086, 'loss/train': 2.3022429943084717}
-03/04/2022 02:29:17 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 02:29:20 - INFO - codeparrot_training - Step 11087: {'lr': 0.0004953636050692724, 'samples': 5677056, 'steps': 11087, 'loss/train': 1.7491674423217773}
-03/04/2022 02:29:23 - INFO - codeparrot_training - Step 11088: {'lr': 0.0004953625877342051, 'samples': 5677568, 'steps': 11088, 'loss/train': 1.5814584493637085}
-03/04/2022 02:29:25 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/04/2022 02:29:29 - INFO - codeparrot_training - Step 11089: {'lr': 0.0004953615702885812, 'samples': 5678080, 'steps': 11089, 'loss/train': 3.1218109130859375}
-03/04/2022 02:29:32 - INFO - codeparrot_training - Step 11090: {'lr': 0.0004953605527324011, 'samples': 5678592, 'steps': 11090, 'loss/train': 2.4180407524108887}
-03/04/2022 02:29:34 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/04/2022 02:29:37 - INFO - codeparrot_training - Step 11091: {'lr': 0.0004953595350656653, 'samples': 5679104, 'steps': 11091, 'loss/train': 2.570727825164795}
-03/04/2022 02:29:40 - INFO - codeparrot_training - Step 11092: {'lr': 0.0004953585172883743, 'samples': 5679616, 'steps': 11092, 'loss/train': 1.95209538936615}
-03/04/2022 02:29:42 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/04/2022 02:29:45 - INFO - codeparrot_training - Step 11093: {'lr': 0.0004953574994005286, 'samples': 5680128, 'steps': 11093, 'loss/train': 2.0264179706573486}
-03/04/2022 02:29:49 - INFO - codeparrot_training - Step 11094: {'lr': 0.0004953564814021285, 'samples': 5680640, 'steps': 11094, 'loss/train': 0.6891264319419861}
-03/04/2022 02:29:50 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 02:29:54 - INFO - codeparrot_training - Step 11095: {'lr': 0.0004953554632931746, 'samples': 5681152, 'steps': 11095, 'loss/train': 1.7578492164611816}
-03/04/2022 02:29:57 - INFO - codeparrot_training - Step 11096: {'lr': 0.0004953544450736674, 'samples': 5681664, 'steps': 11096, 'loss/train': 2.295470714569092}
-03/04/2022 02:29:59 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 02:30:02 - INFO - codeparrot_training - Step 11097: {'lr': 0.0004953534267436072, 'samples': 5682176, 'steps': 11097, 'loss/train': 1.9339631795883179}
-03/04/2022 02:30:05 - INFO - codeparrot_training - Step 11098: {'lr': 0.0004953524083029945, 'samples': 5682688, 'steps': 11098, 'loss/train': 2.6899890899658203}
-03/04/2022 02:30:07 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/04/2022 02:30:11 - INFO - codeparrot_training - Step 11099: {'lr': 0.0004953513897518298, 'samples': 5683200, 'steps': 11099, 'loss/train': 2.5413308143615723}
-03/04/2022 02:30:14 - INFO - codeparrot_training - Step 11100: {'lr': 0.0004953503710901136, 'samples': 5683712, 'steps': 11100, 'loss/train': 0.41597655415534973}
-03/04/2022 02:30:15 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/04/2022 02:30:19 - INFO - codeparrot_training - Step 11101: {'lr': 0.0004953493523178463, 'samples': 5684224, 'steps': 11101, 'loss/train': 2.280217409133911}
-03/04/2022 02:30:22 - INFO - codeparrot_training - Step 11102: {'lr': 0.0004953483334350283, 'samples': 5684736, 'steps': 11102, 'loss/train': 2.889157772064209}
-03/04/2022 02:30:24 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 02:30:28 - INFO - codeparrot_training - Step 11103: {'lr': 0.0004953473144416602, 'samples': 5685248, 'steps': 11103, 'loss/train': 2.357424736022949}
-03/04/2022 02:30:31 - INFO - codeparrot_training - Step 11104: {'lr': 0.0004953462953377424, 'samples': 5685760, 'steps': 11104, 'loss/train': 0.2892550528049469}
-03/04/2022 02:30:32 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 02:30:36 - INFO - codeparrot_training - Step 11105: {'lr': 0.0004953452761232753, 'samples': 5686272, 'steps': 11105, 'loss/train': 2.176851511001587}
-03/04/2022 02:30:39 - INFO - codeparrot_training - Step 11106: {'lr': 0.0004953442567982593, 'samples': 5686784, 'steps': 11106, 'loss/train': 1.826312780380249}
-03/04/2022 02:30:41 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 02:30:45 - INFO - codeparrot_training - Step 11107: {'lr': 0.0004953432373626951, 'samples': 5687296, 'steps': 11107, 'loss/train': 0.31202566623687744}
-03/04/2022 02:30:48 - INFO - codeparrot_training - Step 11108: {'lr': 0.0004953422178165831, 'samples': 5687808, 'steps': 11108, 'loss/train': 1.0822575092315674}
-03/04/2022 02:30:49 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/04/2022 02:30:53 - INFO - codeparrot_training - Step 11109: {'lr': 0.0004953411981599235, 'samples': 5688320, 'steps': 11109, 'loss/train': 2.445741891860962}
-03/04/2022 02:30:56 - INFO - codeparrot_training - Step 11110: {'lr': 0.0004953401783927171, 'samples': 5688832, 'steps': 11110, 'loss/train': 2.874934196472168}
-03/04/2022 02:30:58 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/04/2022 02:31:02 - INFO - codeparrot_training - Step 11111: {'lr': 0.000495339158514964, 'samples': 5689344, 'steps': 11111, 'loss/train': 0.6573690176010132}
-03/04/2022 02:31:05 - INFO - codeparrot_training - Step 11112: {'lr': 0.0004953381385266651, 'samples': 5689856, 'steps': 11112, 'loss/train': 2.825122356414795}
-03/04/2022 02:31:06 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/04/2022 02:31:10 - INFO - codeparrot_training - Step 11113: {'lr': 0.0004953371184278205, 'samples': 5690368, 'steps': 11113, 'loss/train': 1.3714829683303833}
-03/04/2022 02:31:13 - INFO - codeparrot_training - Step 11114: {'lr': 0.0004953360982184308, 'samples': 5690880, 'steps': 11114, 'loss/train': 2.1553235054016113}
-03/04/2022 02:31:15 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 02:31:19 - INFO - codeparrot_training - Step 11115: {'lr': 0.0004953350778984963, 'samples': 5691392, 'steps': 11115, 'loss/train': 1.4544442892074585}
-03/04/2022 02:31:22 - INFO - codeparrot_training - Step 11116: {'lr': 0.0004953340574680177, 'samples': 5691904, 'steps': 11116, 'loss/train': 2.0752062797546387}
-03/04/2022 02:31:24 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/04/2022 02:31:27 - INFO - codeparrot_training - Step 11117: {'lr': 0.0004953330369269955, 'samples': 5692416, 'steps': 11117, 'loss/train': 1.8881880044937134}
-03/04/2022 02:31:30 - INFO - codeparrot_training - Step 11118: {'lr': 0.0004953320162754298, 'samples': 5692928, 'steps': 11118, 'loss/train': 1.6067360639572144}
-03/04/2022 02:31:33 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/04/2022 02:31:36 - INFO - codeparrot_training - Step 11119: {'lr': 0.0004953309955133214, 'samples': 5693440, 'steps': 11119, 'loss/train': 2.0763604640960693}
-03/04/2022 02:31:39 - INFO - codeparrot_training - Step 11120: {'lr': 0.0004953299746406707, 'samples': 5693952, 'steps': 11120, 'loss/train': 1.7344839572906494}
-03/04/2022 02:31:41 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 02:31:44 - INFO - codeparrot_training - Step 11121: {'lr': 0.000495328953657478, 'samples': 5694464, 'steps': 11121, 'loss/train': 1.4920724630355835}
-03/04/2022 02:31:47 - INFO - codeparrot_training - Step 11122: {'lr': 0.0004953279325637438, 'samples': 5694976, 'steps': 11122, 'loss/train': 1.775839924812317}
-03/04/2022 02:31:50 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/04/2022 02:31:53 - INFO - codeparrot_training - Step 11123: {'lr': 0.0004953269113594687, 'samples': 5695488, 'steps': 11123, 'loss/train': 1.6402783393859863}
-03/04/2022 02:31:56 - INFO - codeparrot_training - Step 11124: {'lr': 0.0004953258900446531, 'samples': 5696000, 'steps': 11124, 'loss/train': 2.011571168899536}
-03/04/2022 02:31:58 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/04/2022 02:32:01 - INFO - codeparrot_training - Step 11125: {'lr': 0.0004953248686192975, 'samples': 5696512, 'steps': 11125, 'loss/train': 1.9590978622436523}
-03/04/2022 02:32:04 - INFO - codeparrot_training - Step 11126: {'lr': 0.0004953238470834022, 'samples': 5697024, 'steps': 11126, 'loss/train': 2.6305477619171143}
-03/04/2022 02:32:06 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/04/2022 02:32:09 - INFO - codeparrot_training - Step 11127: {'lr': 0.0004953228254369677, 'samples': 5697536, 'steps': 11127, 'loss/train': 1.6830698251724243}
-03/04/2022 02:32:13 - INFO - codeparrot_training - Step 11128: {'lr': 0.0004953218036799946, 'samples': 5698048, 'steps': 11128, 'loss/train': 0.6896191239356995}
-03/04/2022 02:32:14 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 02:32:18 - INFO - codeparrot_training - Step 11129: {'lr': 0.0004953207818124833, 'samples': 5698560, 'steps': 11129, 'loss/train': 2.0145792961120605}
-03/04/2022 02:32:21 - INFO - codeparrot_training - Step 11130: {'lr': 0.0004953197598344342, 'samples': 5699072, 'steps': 11130, 'loss/train': 2.624255418777466}
-03/04/2022 02:32:23 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/04/2022 02:32:26 - INFO - codeparrot_training - Step 11131: {'lr': 0.0004953187377458478, 'samples': 5699584, 'steps': 11131, 'loss/train': 2.5627598762512207}
-03/04/2022 02:32:29 - INFO - codeparrot_training - Step 11132: {'lr': 0.0004953177155467246, 'samples': 5700096, 'steps': 11132, 'loss/train': 1.900253176689148}
-03/04/2022 02:32:31 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/04/2022 02:32:35 - INFO - codeparrot_training - Step 11133: {'lr': 0.0004953166932370651, 'samples': 5700608, 'steps': 11133, 'loss/train': 2.439917802810669}
-03/04/2022 02:32:38 - INFO - codeparrot_training - Step 11134: {'lr': 0.0004953156708168695, 'samples': 5701120, 'steps': 11134, 'loss/train': 2.4809305667877197}
-03/04/2022 02:32:39 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 02:32:43 - INFO - codeparrot_training - Step 11135: {'lr': 0.0004953146482861385, 'samples': 5701632, 'steps': 11135, 'loss/train': 2.541729688644409}
-03/04/2022 02:32:46 - INFO - codeparrot_training - Step 11136: {'lr': 0.0004953136256448725, 'samples': 5702144, 'steps': 11136, 'loss/train': 2.2312419414520264}
-03/04/2022 02:32:48 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/04/2022 02:32:51 - INFO - codeparrot_training - Step 11137: {'lr': 0.0004953126028930721, 'samples': 5702656, 'steps': 11137, 'loss/train': 3.0025877952575684}
-03/04/2022 02:32:54 - INFO - codeparrot_training - Step 11138: {'lr': 0.0004953115800307375, 'samples': 5703168, 'steps': 11138, 'loss/train': 1.6982700824737549}
-03/04/2022 02:32:56 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 02:33:00 - INFO - codeparrot_training - Step 11139: {'lr': 0.0004953105570578693, 'samples': 5703680, 'steps': 11139, 'loss/train': 2.19528865814209}
-03/04/2022 02:33:03 - INFO - codeparrot_training - Step 11140: {'lr': 0.000495309533974468, 'samples': 5704192, 'steps': 11140, 'loss/train': 2.070652484893799}
-03/04/2022 02:33:05 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 02:33:08 - INFO - codeparrot_training - Step 11141: {'lr': 0.0004953085107805339, 'samples': 5704704, 'steps': 11141, 'loss/train': 1.8369160890579224}
-03/04/2022 02:33:11 - INFO - codeparrot_training - Step 11142: {'lr': 0.0004953074874760677, 'samples': 5705216, 'steps': 11142, 'loss/train': 0.544563353061676}
-03/04/2022 02:33:13 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/04/2022 02:33:16 - INFO - codeparrot_training - Step 11143: {'lr': 0.0004953064640610697, 'samples': 5705728, 'steps': 11143, 'loss/train': 1.7906570434570312}
-03/04/2022 02:33:20 - INFO - codeparrot_training - Step 11144: {'lr': 0.0004953054405355404, 'samples': 5706240, 'steps': 11144, 'loss/train': 1.8548258543014526}
-03/04/2022 02:33:21 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 02:33:25 - INFO - codeparrot_training - Step 11145: {'lr': 0.0004953044168994802, 'samples': 5706752, 'steps': 11145, 'loss/train': 1.9179859161376953}
-03/04/2022 02:33:28 - INFO - codeparrot_training - Step 11146: {'lr': 0.0004953033931528897, 'samples': 5707264, 'steps': 11146, 'loss/train': 1.660319447517395}
-03/04/2022 02:33:29 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/04/2022 02:33:34 - INFO - codeparrot_training - Step 11147: {'lr': 0.0004953023692957691, 'samples': 5707776, 'steps': 11147, 'loss/train': 1.6597265005111694}
-03/04/2022 02:33:37 - INFO - codeparrot_training - Step 11148: {'lr': 0.0004953013453281193, 'samples': 5708288, 'steps': 11148, 'loss/train': 2.372680425643921}
-03/04/2022 02:33:40 - INFO - codeparrot_training - Step 11149: {'lr': 0.0004953003212499403, 'samples': 5708800, 'steps': 11149, 'loss/train': 1.171568751335144}
-03/04/2022 02:33:40 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 02:33:45 - INFO - codeparrot_training - Step 11150: {'lr': 0.0004952992970612328, 'samples': 5709312, 'steps': 11150, 'loss/train': 1.4368237257003784}
-03/04/2022 02:33:48 - INFO - codeparrot_training - Step 11151: {'lr': 0.0004952982727619973, 'samples': 5709824, 'steps': 11151, 'loss/train': 1.857055425643921}
-03/04/2022 02:33:48 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/04/2022 02:33:54 - INFO - codeparrot_training - Step 11152: {'lr': 0.000495297248352234, 'samples': 5710336, 'steps': 11152, 'loss/train': 2.6147871017456055}
-03/04/2022 02:33:57 - INFO - codeparrot_training - Step 11153: {'lr': 0.0004952962238319436, 'samples': 5710848, 'steps': 11153, 'loss/train': 2.6010148525238037}
-03/04/2022 02:33:57 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/04/2022 02:34:02 - INFO - codeparrot_training - Step 11154: {'lr': 0.0004952951992011266, 'samples': 5711360, 'steps': 11154, 'loss/train': 0.9707528948783875}
-03/04/2022 02:34:05 - INFO - codeparrot_training - Step 11155: {'lr': 0.0004952941744597834, 'samples': 5711872, 'steps': 11155, 'loss/train': 2.1747946739196777}
-03/04/2022 02:34:05 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/04/2022 02:34:10 - INFO - codeparrot_training - Step 11156: {'lr': 0.0004952931496079143, 'samples': 5712384, 'steps': 11156, 'loss/train': 1.4870094060897827}
-03/04/2022 02:34:13 - INFO - codeparrot_training - Step 11157: {'lr': 0.00049529212464552, 'samples': 5712896, 'steps': 11157, 'loss/train': 2.432145833969116}
-03/04/2022 02:34:19 - INFO - codeparrot_training - Step 11158: {'lr': 0.0004952910995726008, 'samples': 5713408, 'steps': 11158, 'loss/train': 2.3354668617248535}
-03/04/2022 02:34:22 - INFO - codeparrot_training - Step 11159: {'lr': 0.0004952900743891573, 'samples': 5713920, 'steps': 11159, 'loss/train': 2.4650630950927734}
-03/04/2022 02:34:22 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/04/2022 02:34:28 - INFO - codeparrot_training - Step 11160: {'lr': 0.0004952890490951898, 'samples': 5714432, 'steps': 11160, 'loss/train': 4.0759663581848145}
-03/04/2022 02:34:31 - INFO - codeparrot_training - Step 11161: {'lr': 0.0004952880236906988, 'samples': 5714944, 'steps': 11161, 'loss/train': 0.9733386635780334}
-03/04/2022 02:34:33 - INFO - codeparrot_training - Skipping example with length 285 (seq_length=1024)
-03/04/2022 02:34:36 - INFO - codeparrot_training - Step 11162: {'lr': 0.0004952869981756848, 'samples': 5715456, 'steps': 11162, 'loss/train': 1.6242282390594482}
-03/04/2022 02:34:39 - INFO - codeparrot_training - Step 11163: {'lr': 0.0004952859725501484, 'samples': 5715968, 'steps': 11163, 'loss/train': 2.2260732650756836}
-03/04/2022 02:34:42 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/04/2022 02:34:45 - INFO - codeparrot_training - Step 11164: {'lr': 0.0004952849468140898, 'samples': 5716480, 'steps': 11164, 'loss/train': 1.9180376529693604}
-03/04/2022 02:34:48 - INFO - codeparrot_training - Step 11165: {'lr': 0.0004952839209675096, 'samples': 5716992, 'steps': 11165, 'loss/train': 2.3834493160247803}
-03/04/2022 02:34:50 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/04/2022 02:34:53 - INFO - codeparrot_training - Step 11166: {'lr': 0.0004952828950104083, 'samples': 5717504, 'steps': 11166, 'loss/train': 4.275144100189209}
-03/04/2022 02:34:56 - INFO - codeparrot_training - Step 11167: {'lr': 0.0004952818689427863, 'samples': 5718016, 'steps': 11167, 'loss/train': 1.361333966255188}
-03/04/2022 02:34:59 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/04/2022 02:35:02 - INFO - codeparrot_training - Step 11168: {'lr': 0.0004952808427646441, 'samples': 5718528, 'steps': 11168, 'loss/train': 2.7288529872894287}
-03/04/2022 02:35:05 - INFO - codeparrot_training - Step 11169: {'lr': 0.000495279816475982, 'samples': 5719040, 'steps': 11169, 'loss/train': 1.1726274490356445}
-03/04/2022 02:35:08 - INFO - codeparrot_training - Step 11170: {'lr': 0.0004952787900768008, 'samples': 5719552, 'steps': 11170, 'loss/train': 2.483983278274536}
-03/04/2022 02:35:08 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 02:35:13 - INFO - codeparrot_training - Step 11171: {'lr': 0.0004952777635671006, 'samples': 5720064, 'steps': 11171, 'loss/train': 1.9130308628082275}
-03/04/2022 02:35:16 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/04/2022 02:35:18 - INFO - codeparrot_training - Step 11172: {'lr': 0.0004952767369468821, 'samples': 5720576, 'steps': 11172, 'loss/train': 3.14817476272583}
-03/04/2022 02:35:22 - INFO - codeparrot_training - Step 11173: {'lr': 0.0004952757102161457, 'samples': 5721088, 'steps': 11173, 'loss/train': 2.276033639907837}
-03/04/2022 02:35:24 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/04/2022 02:35:27 - INFO - codeparrot_training - Step 11174: {'lr': 0.0004952746833748918, 'samples': 5721600, 'steps': 11174, 'loss/train': 1.9582786560058594}
-03/04/2022 02:35:30 - INFO - codeparrot_training - Step 11175: {'lr': 0.0004952736564231209, 'samples': 5722112, 'steps': 11175, 'loss/train': 2.2286651134490967}
-03/04/2022 02:35:33 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/04/2022 02:35:35 - INFO - codeparrot_training - Step 11176: {'lr': 0.0004952726293608335, 'samples': 5722624, 'steps': 11176, 'loss/train': 0.9811001420021057}
-03/04/2022 02:35:39 - INFO - codeparrot_training - Step 11177: {'lr': 0.0004952716021880301, 'samples': 5723136, 'steps': 11177, 'loss/train': 2.6960432529449463}
-03/04/2022 02:35:41 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 02:35:44 - INFO - codeparrot_training - Step 11178: {'lr': 0.0004952705749047111, 'samples': 5723648, 'steps': 11178, 'loss/train': 1.8753528594970703}
-03/04/2022 02:35:47 - INFO - codeparrot_training - Step 11179: {'lr': 0.0004952695475108768, 'samples': 5724160, 'steps': 11179, 'loss/train': 1.1887571811676025}
-03/04/2022 02:35:49 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/04/2022 02:35:52 - INFO - codeparrot_training - Step 11180: {'lr': 0.000495268520006528, 'samples': 5724672, 'steps': 11180, 'loss/train': 0.15248490869998932}
-03/04/2022 02:35:56 - INFO - codeparrot_training - Step 11181: {'lr': 0.000495267492391665, 'samples': 5725184, 'steps': 11181, 'loss/train': 2.3137121200561523}
-03/04/2022 02:35:58 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 02:36:01 - INFO - codeparrot_training - Step 11182: {'lr': 0.0004952664646662882, 'samples': 5725696, 'steps': 11182, 'loss/train': 2.209827184677124}
-03/04/2022 02:36:04 - INFO - codeparrot_training - Step 11183: {'lr': 0.000495265436830398, 'samples': 5726208, 'steps': 11183, 'loss/train': 2.6519031524658203}
-03/04/2022 02:36:07 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/04/2022 02:36:09 - INFO - codeparrot_training - Step 11184: {'lr': 0.0004952644088839951, 'samples': 5726720, 'steps': 11184, 'loss/train': 2.6906495094299316}
-03/04/2022 02:36:12 - INFO - codeparrot_training - Step 11185: {'lr': 0.0004952633808270797, 'samples': 5727232, 'steps': 11185, 'loss/train': 2.136082649230957}
-03/04/2022 02:36:15 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 02:36:18 - INFO - codeparrot_training - Step 11186: {'lr': 0.0004952623526596526, 'samples': 5727744, 'steps': 11186, 'loss/train': 1.6300045251846313}
-03/04/2022 02:36:21 - INFO - codeparrot_training - Step 11187: {'lr': 0.000495261324381714, 'samples': 5728256, 'steps': 11187, 'loss/train': 1.7539879083633423}
-03/04/2022 02:36:23 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/04/2022 02:36:26 - INFO - codeparrot_training - Step 11188: {'lr': 0.0004952602959932644, 'samples': 5728768, 'steps': 11188, 'loss/train': 2.0819482803344727}
-03/04/2022 02:36:29 - INFO - codeparrot_training - Step 11189: {'lr': 0.0004952592674943043, 'samples': 5729280, 'steps': 11189, 'loss/train': 1.7621289491653442}
-03/04/2022 02:36:32 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/04/2022 02:36:34 - INFO - codeparrot_training - Step 11190: {'lr': 0.0004952582388848343, 'samples': 5729792, 'steps': 11190, 'loss/train': 2.410393714904785}
-03/04/2022 02:36:38 - INFO - codeparrot_training - Step 11191: {'lr': 0.0004952572101648545, 'samples': 5730304, 'steps': 11191, 'loss/train': 1.8467302322387695}
-03/04/2022 02:36:40 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 02:36:43 - INFO - codeparrot_training - Step 11192: {'lr': 0.0004952561813343657, 'samples': 5730816, 'steps': 11192, 'loss/train': 2.2078230381011963}
-03/04/2022 02:36:46 - INFO - codeparrot_training - Step 11193: {'lr': 0.0004952551523933682, 'samples': 5731328, 'steps': 11193, 'loss/train': 2.0544021129608154}
-03/04/2022 02:36:48 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/04/2022 02:36:51 - INFO - codeparrot_training - Step 11194: {'lr': 0.0004952541233418626, 'samples': 5731840, 'steps': 11194, 'loss/train': 1.828432321548462}
-03/04/2022 02:36:54 - INFO - codeparrot_training - Step 11195: {'lr': 0.0004952530941798492, 'samples': 5732352, 'steps': 11195, 'loss/train': 1.920011043548584}
-03/04/2022 02:36:57 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 02:37:00 - INFO - codeparrot_training - Step 11196: {'lr': 0.0004952520649073286, 'samples': 5732864, 'steps': 11196, 'loss/train': 2.2979331016540527}
-03/04/2022 02:37:03 - INFO - codeparrot_training - Step 11197: {'lr': 0.0004952510355243012, 'samples': 5733376, 'steps': 11197, 'loss/train': 1.93985915184021}
-03/04/2022 02:37:05 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/04/2022 02:37:08 - INFO - codeparrot_training - Step 11198: {'lr': 0.0004952500060307674, 'samples': 5733888, 'steps': 11198, 'loss/train': 1.2506581544876099}
-03/04/2022 02:37:11 - INFO - codeparrot_training - Step 11199: {'lr': 0.0004952489764267278, 'samples': 5734400, 'steps': 11199, 'loss/train': 1.9552369117736816}
-03/04/2022 02:37:14 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 02:37:17 - INFO - codeparrot_training - Step 11200: {'lr': 0.0004952479467121827, 'samples': 5734912, 'steps': 11200, 'loss/train': 2.088730812072754}
-03/04/2022 02:37:20 - INFO - codeparrot_training - Step 11201: {'lr': 0.0004952469168871327, 'samples': 5735424, 'steps': 11201, 'loss/train': 2.0601842403411865}
-03/04/2022 02:37:22 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 02:37:25 - INFO - codeparrot_training - Step 11202: {'lr': 0.0004952458869515782, 'samples': 5735936, 'steps': 11202, 'loss/train': 1.849044919013977}
-03/04/2022 02:37:28 - INFO - codeparrot_training - Step 11203: {'lr': 0.0004952448569055198, 'samples': 5736448, 'steps': 11203, 'loss/train': 1.9205960035324097}
-03/04/2022 02:37:30 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/04/2022 02:37:33 - INFO - codeparrot_training - Step 11204: {'lr': 0.0004952438267489578, 'samples': 5736960, 'steps': 11204, 'loss/train': 2.28802752494812}
-03/04/2022 02:37:37 - INFO - codeparrot_training - Step 11205: {'lr': 0.0004952427964818927, 'samples': 5737472, 'steps': 11205, 'loss/train': 2.2029762268066406}
-03/04/2022 02:37:39 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/04/2022 02:37:42 - INFO - codeparrot_training - Step 11206: {'lr': 0.0004952417661043249, 'samples': 5737984, 'steps': 11206, 'loss/train': 1.3541291952133179}
-03/04/2022 02:37:45 - INFO - codeparrot_training - Step 11207: {'lr': 0.0004952407356162551, 'samples': 5738496, 'steps': 11207, 'loss/train': 2.011591672897339}
-03/04/2022 02:37:47 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/04/2022 02:37:50 - INFO - codeparrot_training - Step 11208: {'lr': 0.0004952397050176835, 'samples': 5739008, 'steps': 11208, 'loss/train': 1.5874117612838745}
-03/04/2022 02:37:53 - INFO - codeparrot_training - Step 11209: {'lr': 0.0004952386743086107, 'samples': 5739520, 'steps': 11209, 'loss/train': 1.7382162809371948}
-03/04/2022 02:37:55 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/04/2022 02:37:58 - INFO - codeparrot_training - Step 11210: {'lr': 0.0004952376434890372, 'samples': 5740032, 'steps': 11210, 'loss/train': 1.4774041175842285}
-03/04/2022 02:38:02 - INFO - codeparrot_training - Step 11211: {'lr': 0.0004952366125589633, 'samples': 5740544, 'steps': 11211, 'loss/train': 2.500736713409424}
-03/04/2022 02:38:04 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 02:38:07 - INFO - codeparrot_training - Step 11212: {'lr': 0.0004952355815183897, 'samples': 5741056, 'steps': 11212, 'loss/train': 1.7526956796646118}
-03/04/2022 02:38:10 - INFO - codeparrot_training - Step 11213: {'lr': 0.0004952345503673166, 'samples': 5741568, 'steps': 11213, 'loss/train': 2.7722558975219727}
-03/04/2022 02:38:12 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/04/2022 02:38:15 - INFO - codeparrot_training - Step 11214: {'lr': 0.0004952335191057447, 'samples': 5742080, 'steps': 11214, 'loss/train': 2.785006046295166}
-03/04/2022 02:38:18 - INFO - codeparrot_training - Step 11215: {'lr': 0.0004952324877336743, 'samples': 5742592, 'steps': 11215, 'loss/train': 1.843305230140686}
-03/04/2022 02:38:21 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/04/2022 02:38:24 - INFO - codeparrot_training - Step 11216: {'lr': 0.0004952314562511059, 'samples': 5743104, 'steps': 11216, 'loss/train': 2.2548372745513916}
-03/04/2022 02:38:27 - INFO - codeparrot_training - Step 11217: {'lr': 0.00049523042465804, 'samples': 5743616, 'steps': 11217, 'loss/train': 2.047668218612671}
-03/04/2022 02:38:29 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 02:38:32 - INFO - codeparrot_training - Step 11218: {'lr': 0.0004952293929544771, 'samples': 5744128, 'steps': 11218, 'loss/train': 1.7748026847839355}
-03/04/2022 02:38:35 - INFO - codeparrot_training - Step 11219: {'lr': 0.0004952283611404176, 'samples': 5744640, 'steps': 11219, 'loss/train': 2.2858903408050537}
-03/04/2022 02:38:38 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/04/2022 02:38:41 - INFO - codeparrot_training - Step 11220: {'lr': 0.0004952273292158619, 'samples': 5745152, 'steps': 11220, 'loss/train': 2.4718053340911865}
-03/04/2022 02:38:44 - INFO - codeparrot_training - Step 11221: {'lr': 0.0004952262971808106, 'samples': 5745664, 'steps': 11221, 'loss/train': 1.2888673543930054}
-03/04/2022 02:38:46 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 02:38:49 - INFO - codeparrot_training - Step 11222: {'lr': 0.0004952252650352642, 'samples': 5746176, 'steps': 11222, 'loss/train': 1.8336998224258423}
-03/04/2022 02:38:52 - INFO - codeparrot_training - Step 11223: {'lr': 0.000495224232779223, 'samples': 5746688, 'steps': 11223, 'loss/train': 2.5415778160095215}
-03/04/2022 02:38:55 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/04/2022 02:38:57 - INFO - codeparrot_training - Step 11224: {'lr': 0.0004952232004126876, 'samples': 5747200, 'steps': 11224, 'loss/train': 1.7256208658218384}
-03/04/2022 02:39:01 - INFO - codeparrot_training - Step 11225: {'lr': 0.0004952221679356583, 'samples': 5747712, 'steps': 11225, 'loss/train': 1.790377140045166}
-03/04/2022 02:39:03 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/04/2022 02:39:06 - INFO - codeparrot_training - Step 11226: {'lr': 0.0004952211353481358, 'samples': 5748224, 'steps': 11226, 'loss/train': 1.6135106086730957}
-03/04/2022 02:39:09 - INFO - codeparrot_training - Step 11227: {'lr': 0.0004952201026501204, 'samples': 5748736, 'steps': 11227, 'loss/train': 2.3976993560791016}
-03/04/2022 02:39:11 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/04/2022 02:39:14 - INFO - codeparrot_training - Step 11228: {'lr': 0.0004952190698416126, 'samples': 5749248, 'steps': 11228, 'loss/train': 1.7863116264343262}
-03/04/2022 02:39:17 - INFO - codeparrot_training - Step 11229: {'lr': 0.0004952180369226129, 'samples': 5749760, 'steps': 11229, 'loss/train': 1.7516558170318604}
-03/04/2022 02:39:20 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/04/2022 02:39:23 - INFO - codeparrot_training - Step 11230: {'lr': 0.0004952170038931217, 'samples': 5750272, 'steps': 11230, 'loss/train': 1.5073243379592896}
-03/04/2022 02:39:26 - INFO - codeparrot_training - Step 11231: {'lr': 0.0004952159707531395, 'samples': 5750784, 'steps': 11231, 'loss/train': 1.3982683420181274}
-03/04/2022 02:39:28 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 02:39:31 - INFO - codeparrot_training - Step 11232: {'lr': 0.0004952149375026668, 'samples': 5751296, 'steps': 11232, 'loss/train': 2.3263297080993652}
-03/04/2022 02:39:34 - INFO - codeparrot_training - Step 11233: {'lr': 0.000495213904141704, 'samples': 5751808, 'steps': 11233, 'loss/train': 1.5038890838623047}
-03/04/2022 02:39:37 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 02:39:40 - INFO - codeparrot_training - Step 11234: {'lr': 0.0004952128706702516, 'samples': 5752320, 'steps': 11234, 'loss/train': 2.072160482406616}
-03/04/2022 02:39:43 - INFO - codeparrot_training - Step 11235: {'lr': 0.0004952118370883101, 'samples': 5752832, 'steps': 11235, 'loss/train': 2.0143909454345703}
-03/04/2022 02:39:45 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 02:39:48 - INFO - codeparrot_training - Step 11236: {'lr': 0.0004952108033958798, 'samples': 5753344, 'steps': 11236, 'loss/train': 1.8952912092208862}
-03/04/2022 02:39:51 - INFO - codeparrot_training - Step 11237: {'lr': 0.0004952097695929614, 'samples': 5753856, 'steps': 11237, 'loss/train': 2.0428271293640137}
-03/04/2022 02:39:54 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 02:39:57 - INFO - codeparrot_training - Step 11238: {'lr': 0.0004952087356795553, 'samples': 5754368, 'steps': 11238, 'loss/train': 2.0041675567626953}
-03/04/2022 02:40:00 - INFO - codeparrot_training - Step 11239: {'lr': 0.0004952077016556619, 'samples': 5754880, 'steps': 11239, 'loss/train': 2.019737482070923}
-03/04/2022 02:40:02 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/04/2022 02:40:05 - INFO - codeparrot_training - Step 11240: {'lr': 0.0004952066675212816, 'samples': 5755392, 'steps': 11240, 'loss/train': 1.3366011381149292}
-03/04/2022 02:40:08 - INFO - codeparrot_training - Step 11241: {'lr': 0.0004952056332764151, 'samples': 5755904, 'steps': 11241, 'loss/train': 0.9197573661804199}
-03/04/2022 02:40:10 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/04/2022 02:40:14 - INFO - codeparrot_training - Step 11242: {'lr': 0.0004952045989210627, 'samples': 5756416, 'steps': 11242, 'loss/train': 2.039655923843384}
-03/04/2022 02:40:17 - INFO - codeparrot_training - Step 11243: {'lr': 0.0004952035644552249, 'samples': 5756928, 'steps': 11243, 'loss/train': 1.617625117301941}
-03/04/2022 02:40:19 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/04/2022 02:40:22 - INFO - codeparrot_training - Step 11244: {'lr': 0.000495202529878902, 'samples': 5757440, 'steps': 11244, 'loss/train': 2.0388519763946533}
-03/04/2022 02:40:25 - INFO - codeparrot_training - Step 11245: {'lr': 0.0004952014951920948, 'samples': 5757952, 'steps': 11245, 'loss/train': 1.9361705780029297}
-03/04/2022 02:40:27 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/04/2022 02:40:30 - INFO - codeparrot_training - Step 11246: {'lr': 0.0004952004603948034, 'samples': 5758464, 'steps': 11246, 'loss/train': 1.57736074924469}
-03/04/2022 02:40:34 - INFO - codeparrot_training - Step 11247: {'lr': 0.0004951994254870286, 'samples': 5758976, 'steps': 11247, 'loss/train': 1.5552852153778076}
-03/04/2022 02:40:39 - INFO - codeparrot_training - Step 11248: {'lr': 0.0004951983904687708, 'samples': 5759488, 'steps': 11248, 'loss/train': 3.018592357635498}
-03/04/2022 02:40:42 - INFO - codeparrot_training - Step 11249: {'lr': 0.0004951973553400303, 'samples': 5760000, 'steps': 11249, 'loss/train': 2.4584782123565674}
-03/04/2022 02:40:44 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 02:40:47 - INFO - codeparrot_training - Step 11250: {'lr': 0.0004951963201008077, 'samples': 5760512, 'steps': 11250, 'loss/train': 1.6484700441360474}
-03/04/2022 02:40:51 - INFO - codeparrot_training - Step 11251: {'lr': 0.0004951952847511033, 'samples': 5761024, 'steps': 11251, 'loss/train': 1.7705020904541016}
-03/04/2022 02:40:52 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/04/2022 02:40:56 - INFO - codeparrot_training - Step 11252: {'lr': 0.0004951942492909177, 'samples': 5761536, 'steps': 11252, 'loss/train': 0.865785539150238}
-03/04/2022 02:40:59 - INFO - codeparrot_training - Step 11253: {'lr': 0.0004951932137202515, 'samples': 5762048, 'steps': 11253, 'loss/train': 2.0996906757354736}
-03/04/2022 02:41:01 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 02:41:04 - INFO - codeparrot_training - Step 11254: {'lr': 0.0004951921780391049, 'samples': 5762560, 'steps': 11254, 'loss/train': 2.8265018463134766}
-03/04/2022 02:41:07 - INFO - codeparrot_training - Step 11255: {'lr': 0.0004951911422474785, 'samples': 5763072, 'steps': 11255, 'loss/train': 2.4857747554779053}
-03/04/2022 02:41:09 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 02:41:13 - INFO - codeparrot_training - Step 11256: {'lr': 0.0004951901063453728, 'samples': 5763584, 'steps': 11256, 'loss/train': 1.2867388725280762}
-03/04/2022 02:41:16 - INFO - codeparrot_training - Step 11257: {'lr': 0.0004951890703327883, 'samples': 5764096, 'steps': 11257, 'loss/train': 1.8290073871612549}
-03/04/2022 02:41:18 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 02:41:21 - INFO - codeparrot_training - Step 11258: {'lr': 0.0004951880342097251, 'samples': 5764608, 'steps': 11258, 'loss/train': 1.237672209739685}
-03/04/2022 02:41:24 - INFO - codeparrot_training - Step 11259: {'lr': 0.0004951869979761842, 'samples': 5765120, 'steps': 11259, 'loss/train': 1.6717393398284912}
-03/04/2022 02:41:26 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 02:41:30 - INFO - codeparrot_training - Step 11260: {'lr': 0.0004951859616321658, 'samples': 5765632, 'steps': 11260, 'loss/train': 2.5727834701538086}
-03/04/2022 02:41:33 - INFO - codeparrot_training - Step 11261: {'lr': 0.0004951849251776703, 'samples': 5766144, 'steps': 11261, 'loss/train': 1.8266003131866455}
-03/04/2022 02:41:34 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/04/2022 02:41:38 - INFO - codeparrot_training - Step 11262: {'lr': 0.0004951838886126983, 'samples': 5766656, 'steps': 11262, 'loss/train': 2.1316051483154297}
-03/04/2022 02:41:41 - INFO - codeparrot_training - Step 11263: {'lr': 0.0004951828519372503, 'samples': 5767168, 'steps': 11263, 'loss/train': 2.2922656536102295}
-03/04/2022 02:41:43 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 02:41:47 - INFO - codeparrot_training - Step 11264: {'lr': 0.0004951818151513267, 'samples': 5767680, 'steps': 11264, 'loss/train': 1.9110157489776611}
-03/04/2022 02:41:50 - INFO - codeparrot_training - Step 11265: {'lr': 0.0004951807782549277, 'samples': 5768192, 'steps': 11265, 'loss/train': 1.7973095178604126}
-03/04/2022 02:41:51 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/04/2022 02:41:55 - INFO - codeparrot_training - Step 11266: {'lr': 0.0004951797412480544, 'samples': 5768704, 'steps': 11266, 'loss/train': 1.2867294549942017}
-03/04/2022 02:41:58 - INFO - codeparrot_training - Step 11267: {'lr': 0.0004951787041307066, 'samples': 5769216, 'steps': 11267, 'loss/train': 2.9769105911254883}
-03/04/2022 02:41:59 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/04/2022 02:42:03 - INFO - codeparrot_training - Step 11268: {'lr': 0.0004951776669028851, 'samples': 5769728, 'steps': 11268, 'loss/train': 2.2209317684173584}
-03/04/2022 02:42:06 - INFO - codeparrot_training - Step 11269: {'lr': 0.0004951766295645904, 'samples': 5770240, 'steps': 11269, 'loss/train': 2.305417060852051}
-03/04/2022 02:42:08 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 02:42:12 - INFO - codeparrot_training - Step 11270: {'lr': 0.000495175592115823, 'samples': 5770752, 'steps': 11270, 'loss/train': 2.27886700630188}
-03/04/2022 02:42:15 - INFO - codeparrot_training - Step 11271: {'lr': 0.0004951745545565831, 'samples': 5771264, 'steps': 11271, 'loss/train': 2.1052608489990234}
-03/04/2022 02:42:16 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/04/2022 02:42:20 - INFO - codeparrot_training - Step 11272: {'lr': 0.0004951735168868713, 'samples': 5771776, 'steps': 11272, 'loss/train': 2.5045125484466553}
-03/04/2022 02:42:23 - INFO - codeparrot_training - Step 11273: {'lr': 0.0004951724791066881, 'samples': 5772288, 'steps': 11273, 'loss/train': 2.4157955646514893}
-03/04/2022 02:42:24 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/04/2022 02:42:28 - INFO - codeparrot_training - Step 11274: {'lr': 0.0004951714412160342, 'samples': 5772800, 'steps': 11274, 'loss/train': 2.06203293800354}
-03/04/2022 02:42:32 - INFO - codeparrot_training - Step 11275: {'lr': 0.0004951704032149096, 'samples': 5773312, 'steps': 11275, 'loss/train': 2.2310595512390137}
-03/04/2022 02:42:33 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/04/2022 02:42:37 - INFO - codeparrot_training - Step 11276: {'lr': 0.000495169365103315, 'samples': 5773824, 'steps': 11276, 'loss/train': 3.338721990585327}
-03/04/2022 02:42:40 - INFO - codeparrot_training - Step 11277: {'lr': 0.0004951683268812511, 'samples': 5774336, 'steps': 11277, 'loss/train': 2.152776002883911}
-03/04/2022 02:42:41 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 02:42:45 - INFO - codeparrot_training - Step 11278: {'lr': 0.0004951672885487178, 'samples': 5774848, 'steps': 11278, 'loss/train': 2.0512430667877197}
-03/04/2022 02:42:49 - INFO - codeparrot_training - Step 11279: {'lr': 0.0004951662501057161, 'samples': 5775360, 'steps': 11279, 'loss/train': 0.9998580813407898}
-03/04/2022 02:42:49 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 02:42:54 - INFO - codeparrot_training - Step 11280: {'lr': 0.0004951652115522462, 'samples': 5775872, 'steps': 11280, 'loss/train': 1.7038886547088623}
-03/04/2022 02:42:57 - INFO - codeparrot_training - Step 11281: {'lr': 0.0004951641728883087, 'samples': 5776384, 'steps': 11281, 'loss/train': 2.397307872772217}
-03/04/2022 02:42:58 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/04/2022 02:43:02 - INFO - codeparrot_training - Step 11282: {'lr': 0.000495163134113904, 'samples': 5776896, 'steps': 11282, 'loss/train': 2.6692593097686768}
-03/04/2022 02:43:05 - INFO - codeparrot_training - Step 11283: {'lr': 0.0004951620952290325, 'samples': 5777408, 'steps': 11283, 'loss/train': 2.4542763233184814}
-03/04/2022 02:43:06 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/04/2022 02:43:11 - INFO - codeparrot_training - Step 11284: {'lr': 0.0004951610562336949, 'samples': 5777920, 'steps': 11284, 'loss/train': 2.777100086212158}
-03/04/2022 02:43:14 - INFO - codeparrot_training - Step 11285: {'lr': 0.0004951600171278914, 'samples': 5778432, 'steps': 11285, 'loss/train': 2.2806947231292725}
-03/04/2022 02:43:15 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/04/2022 02:43:19 - INFO - codeparrot_training - Step 11286: {'lr': 0.0004951589779116225, 'samples': 5778944, 'steps': 11286, 'loss/train': 1.8671694993972778}
-03/04/2022 02:43:22 - INFO - codeparrot_training - Step 11287: {'lr': 0.0004951579385848889, 'samples': 5779456, 'steps': 11287, 'loss/train': 2.4853742122650146}
-03/04/2022 02:43:23 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/04/2022 02:43:28 - INFO - codeparrot_training - Step 11288: {'lr': 0.0004951568991476908, 'samples': 5779968, 'steps': 11288, 'loss/train': 1.9988011121749878}
-03/04/2022 02:43:31 - INFO - codeparrot_training - Step 11289: {'lr': 0.0004951558596000289, 'samples': 5780480, 'steps': 11289, 'loss/train': 1.9698506593704224}
-03/04/2022 02:43:34 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/04/2022 02:43:37 - INFO - codeparrot_training - Step 11290: {'lr': 0.0004951548199419035, 'samples': 5780992, 'steps': 11290, 'loss/train': 1.3418155908584595}
-03/04/2022 02:43:40 - INFO - codeparrot_training - Step 11291: {'lr': 0.0004951537801733152, 'samples': 5781504, 'steps': 11291, 'loss/train': 1.8345218896865845}
-03/04/2022 02:43:42 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/04/2022 02:43:45 - INFO - codeparrot_training - Step 11292: {'lr': 0.0004951527402942643, 'samples': 5782016, 'steps': 11292, 'loss/train': 1.6774760484695435}
-03/04/2022 02:43:48 - INFO - codeparrot_training - Step 11293: {'lr': 0.0004951517003047512, 'samples': 5782528, 'steps': 11293, 'loss/train': 2.405294895172119}
-03/04/2022 02:43:51 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/04/2022 02:43:54 - INFO - codeparrot_training - Step 11294: {'lr': 0.0004951506602047767, 'samples': 5783040, 'steps': 11294, 'loss/train': 1.7105237245559692}
-03/04/2022 02:43:57 - INFO - codeparrot_training - Step 11295: {'lr': 0.0004951496199943412, 'samples': 5783552, 'steps': 11295, 'loss/train': 1.859265923500061}
-03/04/2022 02:43:59 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 02:44:02 - INFO - codeparrot_training - Step 11296: {'lr': 0.0004951485796734448, 'samples': 5784064, 'steps': 11296, 'loss/train': 2.098013162612915}
-03/04/2022 02:44:05 - INFO - codeparrot_training - Step 11297: {'lr': 0.0004951475392420884, 'samples': 5784576, 'steps': 11297, 'loss/train': 1.9995200634002686}
-03/04/2022 02:44:08 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 02:44:10 - INFO - codeparrot_training - Step 11298: {'lr': 0.0004951464987002724, 'samples': 5785088, 'steps': 11298, 'loss/train': 2.054032802581787}
-03/04/2022 02:44:14 - INFO - codeparrot_training - Step 11299: {'lr': 0.000495145458047997, 'samples': 5785600, 'steps': 11299, 'loss/train': 2.168767213821411}
-03/04/2022 02:44:16 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/04/2022 02:44:19 - INFO - codeparrot_training - Step 11300: {'lr': 0.0004951444172852629, 'samples': 5786112, 'steps': 11300, 'loss/train': 2.2628238201141357}
-03/04/2022 02:44:22 - INFO - codeparrot_training - Step 11301: {'lr': 0.0004951433764120705, 'samples': 5786624, 'steps': 11301, 'loss/train': 1.8129819631576538}
-03/04/2022 02:44:24 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/04/2022 02:44:27 - INFO - codeparrot_training - Step 11302: {'lr': 0.0004951423354284202, 'samples': 5787136, 'steps': 11302, 'loss/train': 1.668750286102295}
-03/04/2022 02:44:31 - INFO - codeparrot_training - Step 11303: {'lr': 0.0004951412943343126, 'samples': 5787648, 'steps': 11303, 'loss/train': 1.4239728450775146}
-03/04/2022 02:44:33 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/04/2022 02:44:36 - INFO - codeparrot_training - Step 11304: {'lr': 0.0004951402531297482, 'samples': 5788160, 'steps': 11304, 'loss/train': 1.9406639337539673}
-03/04/2022 02:44:39 - INFO - codeparrot_training - Step 11305: {'lr': 0.0004951392118147273, 'samples': 5788672, 'steps': 11305, 'loss/train': 2.1471657752990723}
-03/04/2022 02:44:42 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 02:44:44 - INFO - codeparrot_training - Step 11306: {'lr': 0.0004951381703892506, 'samples': 5789184, 'steps': 11306, 'loss/train': 1.822750210762024}
-03/04/2022 02:44:48 - INFO - codeparrot_training - Step 11307: {'lr': 0.0004951371288533182, 'samples': 5789696, 'steps': 11307, 'loss/train': 2.3776299953460693}
-03/04/2022 02:44:50 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/04/2022 02:44:53 - INFO - codeparrot_training - Step 11308: {'lr': 0.0004951360872069309, 'samples': 5790208, 'steps': 11308, 'loss/train': 2.201988935470581}
-03/04/2022 02:44:56 - INFO - codeparrot_training - Step 11309: {'lr': 0.0004951350454500891, 'samples': 5790720, 'steps': 11309, 'loss/train': 2.91813325881958}
-03/04/2022 02:44:59 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 02:45:01 - INFO - codeparrot_training - Step 11310: {'lr': 0.0004951340035827932, 'samples': 5791232, 'steps': 11310, 'loss/train': 1.7318075895309448}
-03/04/2022 02:45:04 - INFO - codeparrot_training - Step 11311: {'lr': 0.0004951329616050437, 'samples': 5791744, 'steps': 11311, 'loss/train': 2.464484214782715}
-03/04/2022 02:45:07 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/04/2022 02:45:10 - INFO - codeparrot_training - Step 11312: {'lr': 0.000495131919516841, 'samples': 5792256, 'steps': 11312, 'loss/train': 3.635925054550171}
-03/04/2022 02:45:13 - INFO - codeparrot_training - Step 11313: {'lr': 0.0004951308773181856, 'samples': 5792768, 'steps': 11313, 'loss/train': 2.322739839553833}
-03/04/2022 02:45:15 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/04/2022 02:45:18 - INFO - codeparrot_training - Step 11314: {'lr': 0.0004951298350090782, 'samples': 5793280, 'steps': 11314, 'loss/train': 2.492480754852295}
-03/04/2022 02:45:21 - INFO - codeparrot_training - Step 11315: {'lr': 0.000495128792589519, 'samples': 5793792, 'steps': 11315, 'loss/train': 1.6156117916107178}
-03/04/2022 02:45:24 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/04/2022 02:45:27 - INFO - codeparrot_training - Step 11316: {'lr': 0.0004951277500595085, 'samples': 5794304, 'steps': 11316, 'loss/train': 0.8841123580932617}
-03/04/2022 02:45:30 - INFO - codeparrot_training - Step 11317: {'lr': 0.0004951267074190473, 'samples': 5794816, 'steps': 11317, 'loss/train': 1.4303086996078491}
-03/04/2022 02:45:32 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 02:45:35 - INFO - codeparrot_training - Step 11318: {'lr': 0.0004951256646681356, 'samples': 5795328, 'steps': 11318, 'loss/train': 2.2522201538085938}
-03/04/2022 02:45:38 - INFO - codeparrot_training - Step 11319: {'lr': 0.0004951246218067744, 'samples': 5795840, 'steps': 11319, 'loss/train': 2.0813004970550537}
-03/04/2022 02:45:41 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 02:45:44 - INFO - codeparrot_training - Step 11320: {'lr': 0.0004951235788349636, 'samples': 5796352, 'steps': 11320, 'loss/train': 2.1453630924224854}
-03/04/2022 02:45:47 - INFO - codeparrot_training - Step 11321: {'lr': 0.0004951225357527038, 'samples': 5796864, 'steps': 11321, 'loss/train': 0.9554771184921265}
-03/04/2022 02:45:49 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/04/2022 02:45:52 - INFO - codeparrot_training - Step 11322: {'lr': 0.0004951214925599957, 'samples': 5797376, 'steps': 11322, 'loss/train': 1.9490646123886108}
-03/04/2022 02:45:55 - INFO - codeparrot_training - Step 11323: {'lr': 0.0004951204492568397, 'samples': 5797888, 'steps': 11323, 'loss/train': 1.49001145362854}
-03/04/2022 02:45:58 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 02:46:01 - INFO - codeparrot_training - Step 11324: {'lr': 0.0004951194058432361, 'samples': 5798400, 'steps': 11324, 'loss/train': 2.122540235519409}
-03/04/2022 02:46:04 - INFO - codeparrot_training - Step 11325: {'lr': 0.0004951183623191855, 'samples': 5798912, 'steps': 11325, 'loss/train': 0.9603897929191589}
-03/04/2022 02:46:07 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/04/2022 02:46:09 - INFO - codeparrot_training - Step 11326: {'lr': 0.0004951173186846884, 'samples': 5799424, 'steps': 11326, 'loss/train': 1.8562790155410767}
-03/04/2022 02:46:12 - INFO - codeparrot_training - Step 11327: {'lr': 0.0004951162749397452, 'samples': 5799936, 'steps': 11327, 'loss/train': 2.8074252605438232}
-03/04/2022 02:46:15 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/04/2022 02:46:18 - INFO - codeparrot_training - Step 11328: {'lr': 0.0004951152310843564, 'samples': 5800448, 'steps': 11328, 'loss/train': 2.228306293487549}
-03/04/2022 02:46:21 - INFO - codeparrot_training - Step 11329: {'lr': 0.0004951141871185224, 'samples': 5800960, 'steps': 11329, 'loss/train': 2.1717870235443115}
-03/04/2022 02:46:24 - INFO - codeparrot_training - Step 11330: {'lr': 0.0004951131430422438, 'samples': 5801472, 'steps': 11330, 'loss/train': 2.229158878326416}
-03/04/2022 02:46:24 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/04/2022 02:46:29 - INFO - codeparrot_training - Step 11331: {'lr': 0.0004951120988555209, 'samples': 5801984, 'steps': 11331, 'loss/train': 1.9189364910125732}
-03/04/2022 02:46:32 - INFO - codeparrot_training - Step 11332: {'lr': 0.0004951110545583543, 'samples': 5802496, 'steps': 11332, 'loss/train': 2.1101701259613037}
-03/04/2022 02:46:33 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/04/2022 02:46:38 - INFO - codeparrot_training - Step 11333: {'lr': 0.0004951100101507445, 'samples': 5803008, 'steps': 11333, 'loss/train': 1.9441951513290405}
-03/04/2022 02:46:41 - INFO - codeparrot_training - Step 11334: {'lr': 0.0004951089656326919, 'samples': 5803520, 'steps': 11334, 'loss/train': 1.9222077131271362}
-03/04/2022 02:46:42 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/04/2022 02:46:46 - INFO - codeparrot_training - Step 11335: {'lr': 0.0004951079210041969, 'samples': 5804032, 'steps': 11335, 'loss/train': 2.22025728225708}
-03/04/2022 02:46:49 - INFO - codeparrot_training - Step 11336: {'lr': 0.0004951068762652602, 'samples': 5804544, 'steps': 11336, 'loss/train': 1.8315181732177734}
-03/04/2022 02:46:50 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/04/2022 02:46:55 - INFO - codeparrot_training - Step 11337: {'lr': 0.000495105831415882, 'samples': 5805056, 'steps': 11337, 'loss/train': 2.37078857421875}
-03/04/2022 02:46:58 - INFO - codeparrot_training - Step 11338: {'lr': 0.0004951047864560629, 'samples': 5805568, 'steps': 11338, 'loss/train': 2.753077983856201}
-03/04/2022 02:46:58 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 02:47:03 - INFO - codeparrot_training - Step 11339: {'lr': 0.0004951037413858034, 'samples': 5806080, 'steps': 11339, 'loss/train': 1.6632039546966553}
-03/04/2022 02:47:06 - INFO - codeparrot_training - Step 11340: {'lr': 0.000495102696205104, 'samples': 5806592, 'steps': 11340, 'loss/train': 1.0515999794006348}
-03/04/2022 02:47:07 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/04/2022 02:47:12 - INFO - codeparrot_training - Step 11341: {'lr': 0.000495101650913965, 'samples': 5807104, 'steps': 11341, 'loss/train': 1.672569990158081}
-03/04/2022 02:47:15 - INFO - codeparrot_training - Step 11342: {'lr': 0.000495100605512387, 'samples': 5807616, 'steps': 11342, 'loss/train': 1.6460658311843872}
-03/04/2022 02:47:16 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 02:47:20 - INFO - codeparrot_training - Step 11343: {'lr': 0.0004950995600003705, 'samples': 5808128, 'steps': 11343, 'loss/train': 1.675374150276184}
-03/04/2022 02:47:23 - INFO - codeparrot_training - Step 11344: {'lr': 0.0004950985143779159, 'samples': 5808640, 'steps': 11344, 'loss/train': 0.8782656192779541}
-03/04/2022 02:47:24 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/04/2022 02:47:29 - INFO - codeparrot_training - Step 11345: {'lr': 0.0004950974686450237, 'samples': 5809152, 'steps': 11345, 'loss/train': 0.9638344645500183}
-03/04/2022 02:47:32 - INFO - codeparrot_training - Step 11346: {'lr': 0.0004950964228016944, 'samples': 5809664, 'steps': 11346, 'loss/train': 1.669893741607666}
-03/04/2022 02:47:33 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 02:47:37 - INFO - codeparrot_training - Step 11347: {'lr': 0.0004950953768479284, 'samples': 5810176, 'steps': 11347, 'loss/train': 1.7923882007598877}
-03/04/2022 02:47:40 - INFO - codeparrot_training - Step 11348: {'lr': 0.0004950943307837261, 'samples': 5810688, 'steps': 11348, 'loss/train': 2.347135066986084}
-03/04/2022 02:47:41 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 02:47:45 - INFO - codeparrot_training - Step 11349: {'lr': 0.0004950932846090882, 'samples': 5811200, 'steps': 11349, 'loss/train': 2.6140012741088867}
-03/04/2022 02:47:49 - INFO - codeparrot_training - Step 11350: {'lr': 0.000495092238324015, 'samples': 5811712, 'steps': 11350, 'loss/train': 3.280545234680176}
-03/04/2022 02:47:50 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 02:47:54 - INFO - codeparrot_training - Step 11351: {'lr': 0.0004950911919285071, 'samples': 5812224, 'steps': 11351, 'loss/train': 2.0582079887390137}
-03/04/2022 02:47:57 - INFO - codeparrot_training - Step 11352: {'lr': 0.0004950901454225647, 'samples': 5812736, 'steps': 11352, 'loss/train': 1.4220012426376343}
-03/04/2022 02:47:58 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/04/2022 02:48:02 - INFO - codeparrot_training - Step 11353: {'lr': 0.0004950890988061886, 'samples': 5813248, 'steps': 11353, 'loss/train': 1.465509057044983}
-03/04/2022 02:48:05 - INFO - codeparrot_training - Step 11354: {'lr': 0.0004950880520793791, 'samples': 5813760, 'steps': 11354, 'loss/train': 2.5300817489624023}
-03/04/2022 02:48:06 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/04/2022 02:48:11 - INFO - codeparrot_training - Step 11355: {'lr': 0.0004950870052421368, 'samples': 5814272, 'steps': 11355, 'loss/train': 2.2636899948120117}
-03/04/2022 02:48:14 - INFO - codeparrot_training - Step 11356: {'lr': 0.000495085958294462, 'samples': 5814784, 'steps': 11356, 'loss/train': 2.9745829105377197}
-03/04/2022 02:48:15 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/04/2022 02:48:19 - INFO - codeparrot_training - Step 11357: {'lr': 0.0004950849112363553, 'samples': 5815296, 'steps': 11357, 'loss/train': 2.144902467727661}
-03/04/2022 02:48:22 - INFO - codeparrot_training - Step 11358: {'lr': 0.000495083864067817, 'samples': 5815808, 'steps': 11358, 'loss/train': 1.752659559249878}
-03/04/2022 02:48:23 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 02:48:28 - INFO - codeparrot_training - Step 11359: {'lr': 0.0004950828167888478, 'samples': 5816320, 'steps': 11359, 'loss/train': 1.5829908847808838}
-03/04/2022 02:48:31 - INFO - codeparrot_training - Step 11360: {'lr': 0.0004950817693994481, 'samples': 5816832, 'steps': 11360, 'loss/train': 1.410300374031067}
-03/04/2022 02:48:32 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/04/2022 02:48:36 - INFO - codeparrot_training - Step 11361: {'lr': 0.0004950807218996182, 'samples': 5817344, 'steps': 11361, 'loss/train': 1.9713153839111328}
-03/04/2022 02:48:39 - INFO - codeparrot_training - Step 11362: {'lr': 0.0004950796742893588, 'samples': 5817856, 'steps': 11362, 'loss/train': 1.8342188596725464}
-03/04/2022 02:48:40 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/04/2022 02:48:45 - INFO - codeparrot_training - Step 11363: {'lr': 0.0004950786265686702, 'samples': 5818368, 'steps': 11363, 'loss/train': 2.235292434692383}
-03/04/2022 02:48:48 - INFO - codeparrot_training - Step 11364: {'lr': 0.000495077578737553, 'samples': 5818880, 'steps': 11364, 'loss/train': 1.7966774702072144}
-03/04/2022 02:48:48 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/04/2022 02:48:53 - INFO - codeparrot_training - Step 11365: {'lr': 0.0004950765307960076, 'samples': 5819392, 'steps': 11365, 'loss/train': 1.8991668224334717}
-03/04/2022 02:48:56 - INFO - codeparrot_training - Step 11366: {'lr': 0.0004950754827440346, 'samples': 5819904, 'steps': 11366, 'loss/train': 1.491937518119812}
-03/04/2022 02:48:57 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/04/2022 02:49:01 - INFO - codeparrot_training - Step 11367: {'lr': 0.0004950744345816342, 'samples': 5820416, 'steps': 11367, 'loss/train': 1.8257251977920532}
-03/04/2022 02:49:05 - INFO - codeparrot_training - Step 11368: {'lr': 0.0004950733863088072, 'samples': 5820928, 'steps': 11368, 'loss/train': 2.485506296157837}
-03/04/2022 02:49:05 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 02:49:10 - INFO - codeparrot_training - Step 11369: {'lr': 0.0004950723379255538, 'samples': 5821440, 'steps': 11369, 'loss/train': 2.3012800216674805}
-03/04/2022 02:49:13 - INFO - codeparrot_training - Step 11370: {'lr': 0.0004950712894318748, 'samples': 5821952, 'steps': 11370, 'loss/train': 2.1101114749908447}
-03/04/2022 02:49:14 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 02:49:18 - INFO - codeparrot_training - Step 11371: {'lr': 0.0004950702408277702, 'samples': 5822464, 'steps': 11371, 'loss/train': 2.2388980388641357}
-03/04/2022 02:49:21 - INFO - codeparrot_training - Step 11372: {'lr': 0.0004950691921132409, 'samples': 5822976, 'steps': 11372, 'loss/train': 1.9054118394851685}
-03/04/2022 02:49:22 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 02:49:27 - INFO - codeparrot_training - Step 11373: {'lr': 0.000495068143288287, 'samples': 5823488, 'steps': 11373, 'loss/train': 1.775472640991211}
-03/04/2022 02:49:30 - INFO - codeparrot_training - Step 11374: {'lr': 0.0004950670943529094, 'samples': 5824000, 'steps': 11374, 'loss/train': 1.9309412240982056}
-03/04/2022 02:49:31 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/04/2022 02:49:35 - INFO - codeparrot_training - Step 11375: {'lr': 0.0004950660453071082, 'samples': 5824512, 'steps': 11375, 'loss/train': 1.9866368770599365}
-03/04/2022 02:49:38 - INFO - codeparrot_training - Step 11376: {'lr': 0.0004950649961508841, 'samples': 5825024, 'steps': 11376, 'loss/train': 2.274261951446533}
-03/04/2022 02:49:39 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/04/2022 02:49:44 - INFO - codeparrot_training - Step 11377: {'lr': 0.0004950639468842375, 'samples': 5825536, 'steps': 11377, 'loss/train': 1.7216862440109253}
-03/04/2022 02:49:47 - INFO - codeparrot_training - Step 11378: {'lr': 0.0004950628975071688, 'samples': 5826048, 'steps': 11378, 'loss/train': 2.88529109954834}
-03/04/2022 02:49:47 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/04/2022 02:49:52 - INFO - codeparrot_training - Step 11379: {'lr': 0.0004950618480196785, 'samples': 5826560, 'steps': 11379, 'loss/train': 2.1383862495422363}
-03/04/2022 02:49:55 - INFO - codeparrot_training - Step 11380: {'lr': 0.0004950607984217674, 'samples': 5827072, 'steps': 11380, 'loss/train': 1.3180614709854126}
-03/04/2022 02:49:56 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/04/2022 02:50:01 - INFO - codeparrot_training - Step 11381: {'lr': 0.0004950597487134354, 'samples': 5827584, 'steps': 11381, 'loss/train': 1.581518292427063}
-03/04/2022 02:50:04 - INFO - codeparrot_training - Step 11382: {'lr': 0.0004950586988946834, 'samples': 5828096, 'steps': 11382, 'loss/train': 0.37211737036705017}
-03/04/2022 02:50:05 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/04/2022 02:50:09 - INFO - codeparrot_training - Step 11383: {'lr': 0.0004950576489655116, 'samples': 5828608, 'steps': 11383, 'loss/train': 1.8162553310394287}
-03/04/2022 02:50:12 - INFO - codeparrot_training - Step 11384: {'lr': 0.0004950565989259207, 'samples': 5829120, 'steps': 11384, 'loss/train': 1.7785922288894653}
-03/04/2022 02:50:13 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 02:50:17 - INFO - codeparrot_training - Step 11385: {'lr': 0.000495055548775911, 'samples': 5829632, 'steps': 11385, 'loss/train': 2.4240243434906006}
-03/04/2022 02:50:21 - INFO - codeparrot_training - Step 11386: {'lr': 0.0004950544985154831, 'samples': 5830144, 'steps': 11386, 'loss/train': 2.6584534645080566}
-03/04/2022 02:50:22 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 02:50:27 - INFO - codeparrot_training - Step 11387: {'lr': 0.0004950534481446375, 'samples': 5830656, 'steps': 11387, 'loss/train': 1.8273019790649414}
-03/04/2022 02:50:30 - INFO - codeparrot_training - Step 11388: {'lr': 0.0004950523976633745, 'samples': 5831168, 'steps': 11388, 'loss/train': 2.118731737136841}
-03/04/2022 02:50:33 - INFO - codeparrot_training - Step 11389: {'lr': 0.0004950513470716947, 'samples': 5831680, 'steps': 11389, 'loss/train': 1.4908641576766968}
-03/04/2022 02:50:33 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/04/2022 02:50:38 - INFO - codeparrot_training - Step 11390: {'lr': 0.0004950502963695985, 'samples': 5832192, 'steps': 11390, 'loss/train': 2.691563844680786}
-03/04/2022 02:50:41 - INFO - codeparrot_training - Step 11391: {'lr': 0.0004950492455570865, 'samples': 5832704, 'steps': 11391, 'loss/train': 1.5551756620407104}
-03/04/2022 02:50:42 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/04/2022 02:50:47 - INFO - codeparrot_training - Step 11392: {'lr': 0.000495048194634159, 'samples': 5833216, 'steps': 11392, 'loss/train': 2.1293411254882812}
-03/04/2022 02:50:50 - INFO - codeparrot_training - Step 11393: {'lr': 0.0004950471436008167, 'samples': 5833728, 'steps': 11393, 'loss/train': 2.80547833442688}
-03/04/2022 02:50:50 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 02:50:55 - INFO - codeparrot_training - Step 11394: {'lr': 0.0004950460924570598, 'samples': 5834240, 'steps': 11394, 'loss/train': 2.1500117778778076}
-03/04/2022 02:50:58 - INFO - codeparrot_training - Step 11395: {'lr': 0.0004950450412028889, 'samples': 5834752, 'steps': 11395, 'loss/train': 2.2875914573669434}
-03/04/2022 02:51:03 - INFO - codeparrot_training - Step 11396: {'lr': 0.0004950439898383047, 'samples': 5835264, 'steps': 11396, 'loss/train': 1.9954620599746704}
-03/04/2022 02:51:07 - INFO - codeparrot_training - Step 11397: {'lr': 0.0004950429383633073, 'samples': 5835776, 'steps': 11397, 'loss/train': 1.7092058658599854}
-03/04/2022 02:51:07 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 02:51:12 - INFO - codeparrot_training - Step 11398: {'lr': 0.0004950418867778973, 'samples': 5836288, 'steps': 11398, 'loss/train': 1.0233262777328491}
-03/04/2022 02:51:15 - INFO - codeparrot_training - Step 11399: {'lr': 0.0004950408350820752, 'samples': 5836800, 'steps': 11399, 'loss/train': 2.693960666656494}
-03/04/2022 02:51:16 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 02:51:21 - INFO - codeparrot_training - Step 11400: {'lr': 0.0004950397832758415, 'samples': 5837312, 'steps': 11400, 'loss/train': 0.8508654832839966}
-03/04/2022 02:51:24 - INFO - codeparrot_training - Step 11401: {'lr': 0.0004950387313591968, 'samples': 5837824, 'steps': 11401, 'loss/train': 3.3026928901672363}
-03/04/2022 02:51:24 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/04/2022 02:51:29 - INFO - codeparrot_training - Step 11402: {'lr': 0.0004950376793321413, 'samples': 5838336, 'steps': 11402, 'loss/train': 1.5183002948760986}
-03/04/2022 02:51:32 - INFO - codeparrot_training - Step 11403: {'lr': 0.0004950366271946756, 'samples': 5838848, 'steps': 11403, 'loss/train': 1.7573102712631226}
-03/04/2022 02:51:33 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/04/2022 02:51:38 - INFO - codeparrot_training - Step 11404: {'lr': 0.0004950355749468001, 'samples': 5839360, 'steps': 11404, 'loss/train': 1.8564908504486084}
-03/04/2022 02:51:41 - INFO - codeparrot_training - Step 11405: {'lr': 0.0004950345225885155, 'samples': 5839872, 'steps': 11405, 'loss/train': 2.7300302982330322}
-03/04/2022 02:51:41 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/04/2022 02:51:46 - INFO - codeparrot_training - Step 11406: {'lr': 0.0004950334701198222, 'samples': 5840384, 'steps': 11406, 'loss/train': 0.8739398121833801}
-03/04/2022 02:51:49 - INFO - codeparrot_training - Step 11407: {'lr': 0.0004950324175407204, 'samples': 5840896, 'steps': 11407, 'loss/train': 2.387773036956787}
-03/04/2022 02:51:50 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/04/2022 02:51:54 - INFO - codeparrot_training - Step 11408: {'lr': 0.0004950313648512108, 'samples': 5841408, 'steps': 11408, 'loss/train': 1.3492298126220703}
-03/04/2022 02:51:58 - INFO - codeparrot_training - Step 11409: {'lr': 0.0004950303120512939, 'samples': 5841920, 'steps': 11409, 'loss/train': 1.7231335639953613}
-03/04/2022 02:51:58 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 02:52:03 - INFO - codeparrot_training - Step 11410: {'lr': 0.0004950292591409701, 'samples': 5842432, 'steps': 11410, 'loss/train': 2.4498674869537354}
-03/04/2022 02:52:06 - INFO - codeparrot_training - Step 11411: {'lr': 0.0004950282061202399, 'samples': 5842944, 'steps': 11411, 'loss/train': 1.7673053741455078}
-03/04/2022 02:52:06 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/04/2022 02:52:11 - INFO - codeparrot_training - Step 11412: {'lr': 0.0004950271529891038, 'samples': 5843456, 'steps': 11412, 'loss/train': 1.7455240488052368}
-03/04/2022 02:52:14 - INFO - codeparrot_training - Step 11413: {'lr': 0.0004950260997475623, 'samples': 5843968, 'steps': 11413, 'loss/train': 2.1445958614349365}
-03/04/2022 02:52:15 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 02:52:20 - INFO - codeparrot_training - Step 11414: {'lr': 0.0004950250463956157, 'samples': 5844480, 'steps': 11414, 'loss/train': 3.003795862197876}
-03/04/2022 02:52:23 - INFO - codeparrot_training - Step 11415: {'lr': 0.0004950239929332646, 'samples': 5844992, 'steps': 11415, 'loss/train': 1.769853949546814}
-03/04/2022 02:52:23 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/04/2022 02:52:28 - INFO - codeparrot_training - Step 11416: {'lr': 0.0004950229393605095, 'samples': 5845504, 'steps': 11416, 'loss/train': 2.3665482997894287}
-03/04/2022 02:52:31 - INFO - codeparrot_training - Step 11417: {'lr': 0.0004950218856773509, 'samples': 5846016, 'steps': 11417, 'loss/train': 2.1198863983154297}
-03/04/2022 02:52:32 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 02:52:36 - INFO - codeparrot_training - Step 11418: {'lr': 0.0004950208318837892, 'samples': 5846528, 'steps': 11418, 'loss/train': 2.4724152088165283}
-03/04/2022 02:52:40 - INFO - codeparrot_training - Step 11419: {'lr': 0.0004950197779798248, 'samples': 5847040, 'steps': 11419, 'loss/train': 1.6796585321426392}
-03/04/2022 02:52:40 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 02:52:45 - INFO - codeparrot_training - Step 11420: {'lr': 0.0004950187239654584, 'samples': 5847552, 'steps': 11420, 'loss/train': 2.2944703102111816}
-03/04/2022 02:52:48 - INFO - codeparrot_training - Step 11421: {'lr': 0.0004950176698406903, 'samples': 5848064, 'steps': 11421, 'loss/train': 1.6750644445419312}
-03/04/2022 02:52:49 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/04/2022 02:52:53 - INFO - codeparrot_training - Step 11422: {'lr': 0.000495016615605521, 'samples': 5848576, 'steps': 11422, 'loss/train': 1.116534948348999}
-03/04/2022 02:52:57 - INFO - codeparrot_training - Step 11423: {'lr': 0.0004950155612599511, 'samples': 5849088, 'steps': 11423, 'loss/train': 1.6102540493011475}
-03/04/2022 02:52:57 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/04/2022 02:53:02 - INFO - codeparrot_training - Step 11424: {'lr': 0.0004950145068039808, 'samples': 5849600, 'steps': 11424, 'loss/train': 1.6181268692016602}
-03/04/2022 02:53:05 - INFO - codeparrot_training - Step 11425: {'lr': 0.0004950134522376108, 'samples': 5850112, 'steps': 11425, 'loss/train': 1.8845092058181763}
-03/04/2022 02:53:06 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 02:53:10 - INFO - codeparrot_training - Step 11426: {'lr': 0.0004950123975608415, 'samples': 5850624, 'steps': 11426, 'loss/train': 1.0858399868011475}
-03/04/2022 02:53:14 - INFO - codeparrot_training - Step 11427: {'lr': 0.0004950113427736734, 'samples': 5851136, 'steps': 11427, 'loss/train': 2.099745988845825}
-03/04/2022 02:53:14 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/04/2022 02:53:19 - INFO - codeparrot_training - Step 11428: {'lr': 0.000495010287876107, 'samples': 5851648, 'steps': 11428, 'loss/train': 0.34927311539649963}
-03/04/2022 02:53:22 - INFO - codeparrot_training - Step 11429: {'lr': 0.0004950092328681428, 'samples': 5852160, 'steps': 11429, 'loss/train': 2.385000467300415}
-03/04/2022 02:53:27 - INFO - codeparrot_training - Step 11430: {'lr': 0.0004950081777497812, 'samples': 5852672, 'steps': 11430, 'loss/train': 1.4526489973068237}
-03/04/2022 02:53:30 - INFO - codeparrot_training - Step 11431: {'lr': 0.0004950071225210226, 'samples': 5853184, 'steps': 11431, 'loss/train': 1.9911754131317139}
-03/04/2022 02:53:31 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 02:53:36 - INFO - codeparrot_training - Step 11432: {'lr': 0.0004950060671818676, 'samples': 5853696, 'steps': 11432, 'loss/train': 1.7601603269577026}
-03/04/2022 02:53:39 - INFO - codeparrot_training - Step 11433: {'lr': 0.0004950050117323167, 'samples': 5854208, 'steps': 11433, 'loss/train': 1.5266648530960083}
-03/04/2022 02:53:39 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/04/2022 02:53:44 - INFO - codeparrot_training - Step 11434: {'lr': 0.0004950039561723703, 'samples': 5854720, 'steps': 11434, 'loss/train': 2.1422247886657715}
-03/04/2022 02:53:47 - INFO - codeparrot_training - Step 11435: {'lr': 0.0004950029005020289, 'samples': 5855232, 'steps': 11435, 'loss/train': 1.8992335796356201}
-03/04/2022 02:53:48 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 02:53:53 - INFO - codeparrot_training - Step 11436: {'lr': 0.0004950018447212929, 'samples': 5855744, 'steps': 11436, 'loss/train': 1.1293758153915405}
-03/04/2022 02:53:56 - INFO - codeparrot_training - Step 11437: {'lr': 0.000495000788830163, 'samples': 5856256, 'steps': 11437, 'loss/train': 1.6458505392074585}
-03/04/2022 02:53:56 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 02:54:01 - INFO - codeparrot_training - Step 11438: {'lr': 0.0004949997328286394, 'samples': 5856768, 'steps': 11438, 'loss/train': 2.382223606109619}
-03/04/2022 02:54:04 - INFO - codeparrot_training - Step 11439: {'lr': 0.0004949986767167228, 'samples': 5857280, 'steps': 11439, 'loss/train': 2.174687623977661}
-03/04/2022 02:54:04 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/04/2022 02:54:09 - INFO - codeparrot_training - Step 11440: {'lr': 0.0004949976204944135, 'samples': 5857792, 'steps': 11440, 'loss/train': 2.3895578384399414}
-03/04/2022 02:54:12 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/04/2022 02:54:15 - INFO - codeparrot_training - Step 11441: {'lr': 0.0004949965641617121, 'samples': 5858304, 'steps': 11441, 'loss/train': 1.9591467380523682}
-03/04/2022 02:54:18 - INFO - codeparrot_training - Step 11442: {'lr': 0.000494995507718619, 'samples': 5858816, 'steps': 11442, 'loss/train': 2.223659038543701}
-03/04/2022 02:54:21 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/04/2022 02:54:23 - INFO - codeparrot_training - Step 11443: {'lr': 0.0004949944511651347, 'samples': 5859328, 'steps': 11443, 'loss/train': 1.150763988494873}
-03/04/2022 02:54:26 - INFO - codeparrot_training - Step 11444: {'lr': 0.0004949933945012597, 'samples': 5859840, 'steps': 11444, 'loss/train': 1.7951979637145996}
-03/04/2022 02:54:29 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 02:54:32 - INFO - codeparrot_training - Step 11445: {'lr': 0.0004949923377269945, 'samples': 5860352, 'steps': 11445, 'loss/train': 2.709084987640381}
-03/04/2022 02:54:35 - INFO - codeparrot_training - Step 11446: {'lr': 0.0004949912808423394, 'samples': 5860864, 'steps': 11446, 'loss/train': 2.068047285079956}
-03/04/2022 02:54:38 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/04/2022 02:54:40 - INFO - codeparrot_training - Step 11447: {'lr': 0.000494990223847295, 'samples': 5861376, 'steps': 11447, 'loss/train': 2.2984941005706787}
-03/04/2022 02:54:43 - INFO - codeparrot_training - Step 11448: {'lr': 0.000494989166741862, 'samples': 5861888, 'steps': 11448, 'loss/train': 2.335369348526001}
-03/04/2022 02:54:46 - INFO - codeparrot_training - Step 11449: {'lr': 0.0004949881095260405, 'samples': 5862400, 'steps': 11449, 'loss/train': 2.1747872829437256}
-03/04/2022 02:54:46 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/04/2022 02:54:52 - INFO - codeparrot_training - Step 11450: {'lr': 0.0004949870521998312, 'samples': 5862912, 'steps': 11450, 'loss/train': 2.0578794479370117}
-03/04/2022 02:54:55 - INFO - codeparrot_training - Step 11451: {'lr': 0.0004949859947632344, 'samples': 5863424, 'steps': 11451, 'loss/train': 0.9360964298248291}
-03/04/2022 02:54:56 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 02:55:00 - INFO - codeparrot_training - Step 11452: {'lr': 0.0004949849372162509, 'samples': 5863936, 'steps': 11452, 'loss/train': 1.0002542734146118}
-03/04/2022 02:55:03 - INFO - codeparrot_training - Step 11453: {'lr': 0.0004949838795588808, 'samples': 5864448, 'steps': 11453, 'loss/train': 1.6152405738830566}
-03/04/2022 02:55:04 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 02:55:09 - INFO - codeparrot_training - Step 11454: {'lr': 0.0004949828217911248, 'samples': 5864960, 'steps': 11454, 'loss/train': 1.7018425464630127}
-03/04/2022 02:55:12 - INFO - codeparrot_training - Step 11455: {'lr': 0.0004949817639129832, 'samples': 5865472, 'steps': 11455, 'loss/train': 1.5160770416259766}
-03/04/2022 02:55:12 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/04/2022 02:55:17 - INFO - codeparrot_training - Step 11456: {'lr': 0.0004949807059244568, 'samples': 5865984, 'steps': 11456, 'loss/train': 1.887303352355957}
-03/04/2022 02:55:20 - INFO - codeparrot_training - Step 11457: {'lr': 0.0004949796478255458, 'samples': 5866496, 'steps': 11457, 'loss/train': 0.8376293778419495}
-03/04/2022 02:55:21 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/04/2022 02:55:25 - INFO - codeparrot_training - Step 11458: {'lr': 0.0004949785896162507, 'samples': 5867008, 'steps': 11458, 'loss/train': 1.2115075588226318}
-03/04/2022 02:55:29 - INFO - codeparrot_training - Step 11459: {'lr': 0.0004949775312965721, 'samples': 5867520, 'steps': 11459, 'loss/train': 2.369598150253296}
-03/04/2022 02:55:29 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 02:55:34 - INFO - codeparrot_training - Step 11460: {'lr': 0.0004949764728665103, 'samples': 5868032, 'steps': 11460, 'loss/train': 2.062044858932495}
-03/04/2022 02:55:37 - INFO - codeparrot_training - Step 11461: {'lr': 0.000494975414326066, 'samples': 5868544, 'steps': 11461, 'loss/train': 1.870645523071289}
-03/04/2022 02:55:37 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/04/2022 02:55:42 - INFO - codeparrot_training - Step 11462: {'lr': 0.0004949743556752395, 'samples': 5869056, 'steps': 11462, 'loss/train': 1.8585872650146484}
-03/04/2022 02:55:45 - INFO - codeparrot_training - Step 11463: {'lr': 0.0004949732969140313, 'samples': 5869568, 'steps': 11463, 'loss/train': 1.6863374710083008}
-03/04/2022 02:55:45 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/04/2022 02:55:51 - INFO - codeparrot_training - Step 11464: {'lr': 0.000494972238042442, 'samples': 5870080, 'steps': 11464, 'loss/train': 1.9283332824707031}
-03/04/2022 02:55:54 - INFO - codeparrot_training - Step 11465: {'lr': 0.0004949711790604719, 'samples': 5870592, 'steps': 11465, 'loss/train': 2.027095317840576}
-03/04/2022 02:55:54 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/04/2022 02:55:59 - INFO - codeparrot_training - Step 11466: {'lr': 0.0004949701199681217, 'samples': 5871104, 'steps': 11466, 'loss/train': 1.6801702976226807}
-03/04/2022 02:56:02 - INFO - codeparrot_training - Step 11467: {'lr': 0.0004949690607653916, 'samples': 5871616, 'steps': 11467, 'loss/train': 1.8477801084518433}
-03/04/2022 02:56:02 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 02:56:08 - INFO - codeparrot_training - Step 11468: {'lr': 0.0004949680014522822, 'samples': 5872128, 'steps': 11468, 'loss/train': 1.0960875749588013}
-03/04/2022 02:56:11 - INFO - codeparrot_training - Step 11469: {'lr': 0.0004949669420287941, 'samples': 5872640, 'steps': 11469, 'loss/train': 2.676546573638916}
-03/04/2022 02:56:11 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/04/2022 02:56:16 - INFO - codeparrot_training - Step 11470: {'lr': 0.0004949658824949277, 'samples': 5873152, 'steps': 11470, 'loss/train': 2.1046700477600098}
-03/04/2022 02:56:19 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/04/2022 02:56:21 - INFO - codeparrot_training - Step 11471: {'lr': 0.0004949648228506834, 'samples': 5873664, 'steps': 11471, 'loss/train': 1.789638638496399}
-03/04/2022 02:56:25 - INFO - codeparrot_training - Step 11472: {'lr': 0.0004949637630960618, 'samples': 5874176, 'steps': 11472, 'loss/train': 1.8244413137435913}
-03/04/2022 02:56:27 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/04/2022 02:56:30 - INFO - codeparrot_training - Step 11473: {'lr': 0.0004949627032310632, 'samples': 5874688, 'steps': 11473, 'loss/train': 1.7825852632522583}
-03/04/2022 02:56:33 - INFO - codeparrot_training - Step 11474: {'lr': 0.0004949616432556882, 'samples': 5875200, 'steps': 11474, 'loss/train': 2.1177830696105957}
-03/04/2022 02:56:35 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 02:56:38 - INFO - codeparrot_training - Step 11475: {'lr': 0.0004949605831699373, 'samples': 5875712, 'steps': 11475, 'loss/train': 1.043126106262207}
-03/04/2022 02:56:41 - INFO - codeparrot_training - Step 11476: {'lr': 0.000494959522973811, 'samples': 5876224, 'steps': 11476, 'loss/train': 1.186636209487915}
-03/04/2022 02:56:44 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 02:56:47 - INFO - codeparrot_training - Step 11477: {'lr': 0.0004949584626673096, 'samples': 5876736, 'steps': 11477, 'loss/train': 1.3582688570022583}
-03/04/2022 02:56:50 - INFO - codeparrot_training - Step 11478: {'lr': 0.0004949574022504338, 'samples': 5877248, 'steps': 11478, 'loss/train': 2.184967279434204}
-03/04/2022 02:56:52 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 02:56:55 - INFO - codeparrot_training - Step 11479: {'lr': 0.0004949563417231838, 'samples': 5877760, 'steps': 11479, 'loss/train': 2.3330013751983643}
-03/04/2022 02:56:58 - INFO - codeparrot_training - Step 11480: {'lr': 0.0004949552810855605, 'samples': 5878272, 'steps': 11480, 'loss/train': 2.525736093521118}
-03/04/2022 02:57:01 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 02:57:03 - INFO - codeparrot_training - Step 11481: {'lr': 0.000494954220337564, 'samples': 5878784, 'steps': 11481, 'loss/train': 1.1714533567428589}
-03/04/2022 02:57:07 - INFO - codeparrot_training - Step 11482: {'lr': 0.0004949531594791948, 'samples': 5879296, 'steps': 11482, 'loss/train': 1.595099687576294}
-03/04/2022 02:57:09 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 02:57:12 - INFO - codeparrot_training - Step 11483: {'lr': 0.0004949520985104536, 'samples': 5879808, 'steps': 11483, 'loss/train': 1.1254149675369263}
-03/04/2022 02:57:15 - INFO - codeparrot_training - Step 11484: {'lr': 0.0004949510374313409, 'samples': 5880320, 'steps': 11484, 'loss/train': 2.181283473968506}
-03/04/2022 02:57:18 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 02:57:20 - INFO - codeparrot_training - Step 11485: {'lr': 0.0004949499762418568, 'samples': 5880832, 'steps': 11485, 'loss/train': 1.8552964925765991}
-03/04/2022 02:57:24 - INFO - codeparrot_training - Step 11486: {'lr': 0.0004949489149420021, 'samples': 5881344, 'steps': 11486, 'loss/train': 2.0036134719848633}
-03/04/2022 02:57:26 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/04/2022 02:57:29 - INFO - codeparrot_training - Step 11487: {'lr': 0.0004949478535317773, 'samples': 5881856, 'steps': 11487, 'loss/train': 1.8444030284881592}
-03/04/2022 02:57:32 - INFO - codeparrot_training - Step 11488: {'lr': 0.0004949467920111827, 'samples': 5882368, 'steps': 11488, 'loss/train': 0.7153424024581909}
-03/04/2022 02:57:34 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/04/2022 02:57:38 - INFO - codeparrot_training - Step 11489: {'lr': 0.0004949457303802189, 'samples': 5882880, 'steps': 11489, 'loss/train': 1.5576757192611694}
-03/04/2022 02:57:41 - INFO - codeparrot_training - Step 11490: {'lr': 0.0004949446686388862, 'samples': 5883392, 'steps': 11490, 'loss/train': 1.5312178134918213}
-03/04/2022 02:57:44 - INFO - codeparrot_training - Step 11491: {'lr': 0.0004949436067871854, 'samples': 5883904, 'steps': 11491, 'loss/train': 6.120165824890137}
-03/04/2022 02:57:46 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/04/2022 02:57:49 - INFO - codeparrot_training - Step 11492: {'lr': 0.0004949425448251166, 'samples': 5884416, 'steps': 11492, 'loss/train': 2.0319085121154785}
-03/04/2022 02:57:53 - INFO - codeparrot_training - Step 11493: {'lr': 0.0004949414827526805, 'samples': 5884928, 'steps': 11493, 'loss/train': 1.9280370473861694}
-03/04/2022 02:57:55 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/04/2022 02:57:58 - INFO - codeparrot_training - Step 11494: {'lr': 0.0004949404205698777, 'samples': 5885440, 'steps': 11494, 'loss/train': 2.2932183742523193}
-03/04/2022 02:58:01 - INFO - codeparrot_training - Step 11495: {'lr': 0.0004949393582767084, 'samples': 5885952, 'steps': 11495, 'loss/train': 1.2868527173995972}
-03/04/2022 02:58:03 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/04/2022 02:58:06 - INFO - codeparrot_training - Step 11496: {'lr': 0.0004949382958731733, 'samples': 5886464, 'steps': 11496, 'loss/train': 1.940618634223938}
-03/04/2022 02:58:09 - INFO - codeparrot_training - Step 11497: {'lr': 0.0004949372333592728, 'samples': 5886976, 'steps': 11497, 'loss/train': 1.5938959121704102}
-03/04/2022 02:58:11 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 02:58:15 - INFO - codeparrot_training - Step 11498: {'lr': 0.0004949361707350072, 'samples': 5887488, 'steps': 11498, 'loss/train': 1.7904692888259888}
-03/04/2022 02:58:18 - INFO - codeparrot_training - Step 11499: {'lr': 0.0004949351080003773, 'samples': 5888000, 'steps': 11499, 'loss/train': 2.2594189643859863}
-03/04/2022 02:58:19 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/04/2022 02:58:23 - INFO - codeparrot_training - Step 11500: {'lr': 0.0004949340451553833, 'samples': 5888512, 'steps': 11500, 'loss/train': 1.5803719758987427}
-03/04/2022 02:58:26 - INFO - codeparrot_training - Step 11501: {'lr': 0.0004949329822000259, 'samples': 5889024, 'steps': 11501, 'loss/train': 1.6315033435821533}
-03/04/2022 02:58:28 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 02:58:31 - INFO - codeparrot_training - Step 11502: {'lr': 0.0004949319191343053, 'samples': 5889536, 'steps': 11502, 'loss/train': 1.6308059692382812}
-03/04/2022 02:58:35 - INFO - codeparrot_training - Step 11503: {'lr': 0.0004949308559582224, 'samples': 5890048, 'steps': 11503, 'loss/train': 1.7364963293075562}
-03/04/2022 02:58:36 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 02:58:40 - INFO - codeparrot_training - Step 11504: {'lr': 0.0004949297926717772, 'samples': 5890560, 'steps': 11504, 'loss/train': 1.7409566640853882}
-03/04/2022 02:58:43 - INFO - codeparrot_training - Step 11505: {'lr': 0.0004949287292749705, 'samples': 5891072, 'steps': 11505, 'loss/train': 2.1251139640808105}
-03/04/2022 02:58:45 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 02:58:48 - INFO - codeparrot_training - Step 11506: {'lr': 0.0004949276657678028, 'samples': 5891584, 'steps': 11506, 'loss/train': 0.5948353409767151}
-03/04/2022 02:58:52 - INFO - codeparrot_training - Step 11507: {'lr': 0.0004949266021502744, 'samples': 5892096, 'steps': 11507, 'loss/train': 1.9328842163085938}
-03/04/2022 02:58:54 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/04/2022 02:58:57 - INFO - codeparrot_training - Step 11508: {'lr': 0.0004949255384223859, 'samples': 5892608, 'steps': 11508, 'loss/train': 1.483596920967102}
-03/04/2022 02:59:00 - INFO - codeparrot_training - Step 11509: {'lr': 0.0004949244745841377, 'samples': 5893120, 'steps': 11509, 'loss/train': 2.3045616149902344}
-03/04/2022 02:59:02 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/04/2022 02:59:05 - INFO - codeparrot_training - Step 11510: {'lr': 0.0004949234106355302, 'samples': 5893632, 'steps': 11510, 'loss/train': 2.1582350730895996}
-03/04/2022 02:59:08 - INFO - codeparrot_training - Step 11511: {'lr': 0.0004949223465765642, 'samples': 5894144, 'steps': 11511, 'loss/train': 2.2699391841888428}
-03/04/2022 02:59:10 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 02:59:14 - INFO - codeparrot_training - Step 11512: {'lr': 0.0004949212824072398, 'samples': 5894656, 'steps': 11512, 'loss/train': 2.3212180137634277}
-03/04/2022 02:59:17 - INFO - codeparrot_training - Step 11513: {'lr': 0.0004949202181275577, 'samples': 5895168, 'steps': 11513, 'loss/train': 2.2416977882385254}
-03/04/2022 02:59:19 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/04/2022 02:59:22 - INFO - codeparrot_training - Step 11514: {'lr': 0.0004949191537375184, 'samples': 5895680, 'steps': 11514, 'loss/train': 2.292236328125}
-03/04/2022 02:59:25 - INFO - codeparrot_training - Step 11515: {'lr': 0.0004949180892371223, 'samples': 5896192, 'steps': 11515, 'loss/train': 1.9876725673675537}
-03/04/2022 02:59:27 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/04/2022 02:59:31 - INFO - codeparrot_training - Step 11516: {'lr': 0.0004949170246263697, 'samples': 5896704, 'steps': 11516, 'loss/train': 1.6755095720291138}
-03/04/2022 02:59:34 - INFO - codeparrot_training - Step 11517: {'lr': 0.0004949159599052614, 'samples': 5897216, 'steps': 11517, 'loss/train': 2.0148138999938965}
-03/04/2022 02:59:36 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/04/2022 02:59:39 - INFO - codeparrot_training - Step 11518: {'lr': 0.0004949148950737978, 'samples': 5897728, 'steps': 11518, 'loss/train': 1.7050495147705078}
-03/04/2022 02:59:42 - INFO - codeparrot_training - Step 11519: {'lr': 0.0004949138301319793, 'samples': 5898240, 'steps': 11519, 'loss/train': 2.2729926109313965}
-03/04/2022 02:59:44 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 02:59:47 - INFO - codeparrot_training - Step 11520: {'lr': 0.0004949127650798063, 'samples': 5898752, 'steps': 11520, 'loss/train': 1.9640165567398071}
-03/04/2022 02:59:51 - INFO - codeparrot_training - Step 11521: {'lr': 0.0004949116999172795, 'samples': 5899264, 'steps': 11521, 'loss/train': 2.1405515670776367}
-03/04/2022 02:59:52 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/04/2022 02:59:56 - INFO - codeparrot_training - Step 11522: {'lr': 0.0004949106346443992, 'samples': 5899776, 'steps': 11522, 'loss/train': 1.9825764894485474}
-03/04/2022 02:59:59 - INFO - codeparrot_training - Step 11523: {'lr': 0.0004949095692611661, 'samples': 5900288, 'steps': 11523, 'loss/train': 1.4735362529754639}
-03/04/2022 03:00:01 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 03:00:04 - INFO - codeparrot_training - Step 11524: {'lr': 0.0004949085037675803, 'samples': 5900800, 'steps': 11524, 'loss/train': 1.8501663208007812}
-03/04/2022 03:00:08 - INFO - codeparrot_training - Step 11525: {'lr': 0.0004949074381636427, 'samples': 5901312, 'steps': 11525, 'loss/train': 1.6573477983474731}
-03/04/2022 03:00:09 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 03:00:13 - INFO - codeparrot_training - Step 11526: {'lr': 0.0004949063724493534, 'samples': 5901824, 'steps': 11526, 'loss/train': 3.4238059520721436}
-03/04/2022 03:00:16 - INFO - codeparrot_training - Step 11527: {'lr': 0.0004949053066247133, 'samples': 5902336, 'steps': 11527, 'loss/train': 2.420275926589966}
-03/04/2022 03:00:18 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/04/2022 03:00:21 - INFO - codeparrot_training - Step 11528: {'lr': 0.0004949042406897225, 'samples': 5902848, 'steps': 11528, 'loss/train': 1.391237497329712}
-03/04/2022 03:00:25 - INFO - codeparrot_training - Step 11529: {'lr': 0.0004949031746443816, 'samples': 5903360, 'steps': 11529, 'loss/train': 1.986375093460083}
-03/04/2022 03:00:26 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 03:00:30 - INFO - codeparrot_training - Step 11530: {'lr': 0.0004949021084886912, 'samples': 5903872, 'steps': 11530, 'loss/train': 1.8078958988189697}
-03/04/2022 03:00:33 - INFO - codeparrot_training - Step 11531: {'lr': 0.0004949010422226517, 'samples': 5904384, 'steps': 11531, 'loss/train': 2.0162129402160645}
-03/04/2022 03:00:34 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 03:00:38 - INFO - codeparrot_training - Step 11532: {'lr': 0.0004948999758462634, 'samples': 5904896, 'steps': 11532, 'loss/train': 1.6205432415008545}
-03/04/2022 03:00:41 - INFO - codeparrot_training - Step 11533: {'lr': 0.000494898909359527, 'samples': 5905408, 'steps': 11533, 'loss/train': 1.6554938554763794}
-03/04/2022 03:00:43 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 03:00:47 - INFO - codeparrot_training - Step 11534: {'lr': 0.0004948978427624431, 'samples': 5905920, 'steps': 11534, 'loss/train': 2.0881056785583496}
-03/04/2022 03:00:50 - INFO - codeparrot_training - Step 11535: {'lr': 0.0004948967760550119, 'samples': 5906432, 'steps': 11535, 'loss/train': 1.7711690664291382}
-03/04/2022 03:00:51 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/04/2022 03:00:55 - INFO - codeparrot_training - Step 11536: {'lr': 0.000494895709237234, 'samples': 5906944, 'steps': 11536, 'loss/train': 1.2979214191436768}
-03/04/2022 03:00:58 - INFO - codeparrot_training - Step 11537: {'lr': 0.0004948946423091099, 'samples': 5907456, 'steps': 11537, 'loss/train': 2.493164300918579}
-03/04/2022 03:01:00 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 03:01:04 - INFO - codeparrot_training - Step 11538: {'lr': 0.0004948935752706401, 'samples': 5907968, 'steps': 11538, 'loss/train': 2.0837044715881348}
-03/04/2022 03:01:07 - INFO - codeparrot_training - Step 11539: {'lr': 0.0004948925081218248, 'samples': 5908480, 'steps': 11539, 'loss/train': 2.31705641746521}
-03/04/2022 03:01:08 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/04/2022 03:01:12 - INFO - codeparrot_training - Step 11540: {'lr': 0.000494891440862665, 'samples': 5908992, 'steps': 11540, 'loss/train': 1.6177177429199219}
-03/04/2022 03:01:15 - INFO - codeparrot_training - Step 11541: {'lr': 0.0004948903734931608, 'samples': 5909504, 'steps': 11541, 'loss/train': 1.3401626348495483}
-03/04/2022 03:01:16 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 03:01:20 - INFO - codeparrot_training - Step 11542: {'lr': 0.0004948893060133128, 'samples': 5910016, 'steps': 11542, 'loss/train': 2.2573347091674805}
-03/04/2022 03:01:24 - INFO - codeparrot_training - Step 11543: {'lr': 0.0004948882384231213, 'samples': 5910528, 'steps': 11543, 'loss/train': 2.153003454208374}
-03/04/2022 03:01:25 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/04/2022 03:01:29 - INFO - codeparrot_training - Step 11544: {'lr': 0.0004948871707225871, 'samples': 5911040, 'steps': 11544, 'loss/train': 3.4383554458618164}
-03/04/2022 03:01:32 - INFO - codeparrot_training - Step 11545: {'lr': 0.0004948861029117104, 'samples': 5911552, 'steps': 11545, 'loss/train': 2.6691339015960693}
-03/04/2022 03:01:33 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 03:01:37 - INFO - codeparrot_training - Step 11546: {'lr': 0.0004948850349904919, 'samples': 5912064, 'steps': 11546, 'loss/train': 2.554306745529175}
-03/04/2022 03:01:40 - INFO - codeparrot_training - Step 11547: {'lr': 0.0004948839669589319, 'samples': 5912576, 'steps': 11547, 'loss/train': 3.3093109130859375}
-03/04/2022 03:01:41 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/04/2022 03:01:46 - INFO - codeparrot_training - Step 11548: {'lr': 0.000494882898817031, 'samples': 5913088, 'steps': 11548, 'loss/train': 1.1594634056091309}
-03/04/2022 03:01:49 - INFO - codeparrot_training - Step 11549: {'lr': 0.0004948818305647897, 'samples': 5913600, 'steps': 11549, 'loss/train': 1.6179701089859009}
-03/04/2022 03:01:50 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/04/2022 03:01:54 - INFO - codeparrot_training - Step 11550: {'lr': 0.0004948807622022083, 'samples': 5914112, 'steps': 11550, 'loss/train': 2.3539161682128906}
-03/04/2022 03:01:57 - INFO - codeparrot_training - Step 11551: {'lr': 0.0004948796937292875, 'samples': 5914624, 'steps': 11551, 'loss/train': 2.299813747406006}
-03/04/2022 03:01:58 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/04/2022 03:02:03 - INFO - codeparrot_training - Step 11552: {'lr': 0.0004948786251460277, 'samples': 5915136, 'steps': 11552, 'loss/train': 2.193788528442383}
-03/04/2022 03:02:06 - INFO - codeparrot_training - Step 11553: {'lr': 0.0004948775564524294, 'samples': 5915648, 'steps': 11553, 'loss/train': 2.8459014892578125}
-03/04/2022 03:02:07 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 03:02:11 - INFO - codeparrot_training - Step 11554: {'lr': 0.000494876487648493, 'samples': 5916160, 'steps': 11554, 'loss/train': 2.3574554920196533}
-03/04/2022 03:02:14 - INFO - codeparrot_training - Step 11555: {'lr': 0.0004948754187342189, 'samples': 5916672, 'steps': 11555, 'loss/train': 2.2432751655578613}
-03/04/2022 03:02:15 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/04/2022 03:02:19 - INFO - codeparrot_training - Step 11556: {'lr': 0.0004948743497096079, 'samples': 5917184, 'steps': 11556, 'loss/train': 1.5705468654632568}
-03/04/2022 03:02:23 - INFO - codeparrot_training - Step 11557: {'lr': 0.0004948732805746604, 'samples': 5917696, 'steps': 11557, 'loss/train': 1.7277424335479736}
-03/04/2022 03:02:23 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 03:02:28 - INFO - codeparrot_training - Step 11558: {'lr': 0.0004948722113293766, 'samples': 5918208, 'steps': 11558, 'loss/train': 1.5121195316314697}
-03/04/2022 03:02:31 - INFO - codeparrot_training - Step 11559: {'lr': 0.000494871141973757, 'samples': 5918720, 'steps': 11559, 'loss/train': 2.0180530548095703}
-03/04/2022 03:02:31 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 03:02:36 - INFO - codeparrot_training - Step 11560: {'lr': 0.0004948700725078025, 'samples': 5919232, 'steps': 11560, 'loss/train': 2.0309414863586426}
-03/04/2022 03:02:39 - INFO - codeparrot_training - Step 11561: {'lr': 0.0004948690029315133, 'samples': 5919744, 'steps': 11561, 'loss/train': 1.856102466583252}
-03/04/2022 03:02:40 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/04/2022 03:02:45 - INFO - codeparrot_training - Step 11562: {'lr': 0.0004948679332448899, 'samples': 5920256, 'steps': 11562, 'loss/train': 1.6812392473220825}
-03/04/2022 03:02:48 - INFO - codeparrot_training - Step 11563: {'lr': 0.0004948668634479327, 'samples': 5920768, 'steps': 11563, 'loss/train': 2.0313878059387207}
-03/04/2022 03:02:48 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/04/2022 03:02:53 - INFO - codeparrot_training - Step 11564: {'lr': 0.0004948657935406423, 'samples': 5921280, 'steps': 11564, 'loss/train': 2.0386128425598145}
-03/04/2022 03:02:56 - INFO - codeparrot_training - Step 11565: {'lr': 0.0004948647235230192, 'samples': 5921792, 'steps': 11565, 'loss/train': 1.640358567237854}
-03/04/2022 03:02:56 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 03:03:01 - INFO - codeparrot_training - Step 11566: {'lr': 0.0004948636533950638, 'samples': 5922304, 'steps': 11566, 'loss/train': 1.5209227800369263}
-03/04/2022 03:03:05 - INFO - codeparrot_training - Step 11567: {'lr': 0.0004948625831567766, 'samples': 5922816, 'steps': 11567, 'loss/train': 1.2962641716003418}
-03/04/2022 03:03:05 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/04/2022 03:03:10 - INFO - codeparrot_training - Step 11568: {'lr': 0.000494861512808158, 'samples': 5923328, 'steps': 11568, 'loss/train': 2.3705520629882812}
-03/04/2022 03:03:13 - INFO - codeparrot_training - Step 11569: {'lr': 0.0004948604423492088, 'samples': 5923840, 'steps': 11569, 'loss/train': 2.498039484024048}
-03/04/2022 03:03:13 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/04/2022 03:03:18 - INFO - codeparrot_training - Step 11570: {'lr': 0.0004948593717799292, 'samples': 5924352, 'steps': 11570, 'loss/train': 1.3324341773986816}
-03/04/2022 03:03:21 - INFO - codeparrot_training - Step 11571: {'lr': 0.0004948583011003196, 'samples': 5924864, 'steps': 11571, 'loss/train': 1.4495586156845093}
-03/04/2022 03:03:22 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 03:03:27 - INFO - codeparrot_training - Step 11572: {'lr': 0.0004948572303103808, 'samples': 5925376, 'steps': 11572, 'loss/train': 1.8290897607803345}
-03/04/2022 03:03:30 - INFO - codeparrot_training - Step 11573: {'lr': 0.0004948561594101129, 'samples': 5925888, 'steps': 11573, 'loss/train': 1.713706374168396}
-03/04/2022 03:03:30 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 03:03:35 - INFO - codeparrot_training - Step 11574: {'lr': 0.0004948550883995168, 'samples': 5926400, 'steps': 11574, 'loss/train': 1.8483715057373047}
-03/04/2022 03:03:38 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 03:03:40 - INFO - codeparrot_training - Step 11575: {'lr': 0.0004948540172785927, 'samples': 5926912, 'steps': 11575, 'loss/train': 2.425795793533325}
-03/04/2022 03:03:44 - INFO - codeparrot_training - Step 11576: {'lr': 0.0004948529460473412, 'samples': 5927424, 'steps': 11576, 'loss/train': 2.1973721981048584}
-03/04/2022 03:03:46 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 03:03:49 - INFO - codeparrot_training - Step 11577: {'lr': 0.0004948518747057626, 'samples': 5927936, 'steps': 11577, 'loss/train': 2.160959482192993}
-03/04/2022 03:03:52 - INFO - codeparrot_training - Step 11578: {'lr': 0.0004948508032538578, 'samples': 5928448, 'steps': 11578, 'loss/train': 1.5780832767486572}
-03/04/2022 03:03:55 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/04/2022 03:03:57 - INFO - codeparrot_training - Step 11579: {'lr': 0.0004948497316916267, 'samples': 5928960, 'steps': 11579, 'loss/train': 1.8998733758926392}
-03/04/2022 03:04:00 - INFO - codeparrot_training - Step 11580: {'lr': 0.0004948486600190702, 'samples': 5929472, 'steps': 11580, 'loss/train': 1.744592547416687}
-03/04/2022 03:04:03 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/04/2022 03:04:06 - INFO - codeparrot_training - Step 11581: {'lr': 0.0004948475882361888, 'samples': 5929984, 'steps': 11581, 'loss/train': 1.903274416923523}
-03/04/2022 03:04:09 - INFO - codeparrot_training - Step 11582: {'lr': 0.0004948465163429828, 'samples': 5930496, 'steps': 11582, 'loss/train': 2.4456427097320557}
-03/04/2022 03:04:12 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/04/2022 03:04:14 - INFO - codeparrot_training - Step 11583: {'lr': 0.0004948454443394527, 'samples': 5931008, 'steps': 11583, 'loss/train': 0.8127695322036743}
-03/04/2022 03:04:17 - INFO - codeparrot_training - Step 11584: {'lr': 0.000494844372225599, 'samples': 5931520, 'steps': 11584, 'loss/train': 1.7838609218597412}
-03/04/2022 03:04:21 - INFO - codeparrot_training - Step 11585: {'lr': 0.0004948433000014222, 'samples': 5932032, 'steps': 11585, 'loss/train': 2.226008176803589}
-03/04/2022 03:04:21 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 03:04:26 - INFO - codeparrot_training - Step 11586: {'lr': 0.0004948422276669228, 'samples': 5932544, 'steps': 11586, 'loss/train': 1.246334433555603}
-03/04/2022 03:04:29 - INFO - codeparrot_training - Step 11587: {'lr': 0.0004948411552221012, 'samples': 5933056, 'steps': 11587, 'loss/train': 2.4928059577941895}
-03/04/2022 03:04:29 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/04/2022 03:04:34 - INFO - codeparrot_training - Step 11588: {'lr': 0.000494840082666958, 'samples': 5933568, 'steps': 11588, 'loss/train': 1.8613654375076294}
-03/04/2022 03:04:37 - INFO - codeparrot_training - Step 11589: {'lr': 0.0004948390100014937, 'samples': 5934080, 'steps': 11589, 'loss/train': 1.7215684652328491}
-03/04/2022 03:04:38 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/04/2022 03:04:43 - INFO - codeparrot_training - Step 11590: {'lr': 0.0004948379372257086, 'samples': 5934592, 'steps': 11590, 'loss/train': 2.0129575729370117}
-03/04/2022 03:04:46 - INFO - codeparrot_training - Step 11591: {'lr': 0.0004948368643396035, 'samples': 5935104, 'steps': 11591, 'loss/train': 1.1371886730194092}
-03/04/2022 03:04:46 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/04/2022 03:04:51 - INFO - codeparrot_training - Step 11592: {'lr': 0.0004948357913431786, 'samples': 5935616, 'steps': 11592, 'loss/train': 1.166799783706665}
-03/04/2022 03:04:54 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 03:04:56 - INFO - codeparrot_training - Step 11593: {'lr': 0.0004948347182364344, 'samples': 5936128, 'steps': 11593, 'loss/train': 2.0736474990844727}
-03/04/2022 03:05:00 - INFO - codeparrot_training - Step 11594: {'lr': 0.0004948336450193715, 'samples': 5936640, 'steps': 11594, 'loss/train': 1.7606743574142456}
-03/04/2022 03:05:03 - INFO - codeparrot_training - Step 11595: {'lr': 0.0004948325716919904, 'samples': 5937152, 'steps': 11595, 'loss/train': 2.012493848800659}
-03/04/2022 03:05:03 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 03:05:08 - INFO - codeparrot_training - Step 11596: {'lr': 0.0004948314982542914, 'samples': 5937664, 'steps': 11596, 'loss/train': 2.1304562091827393}
-03/04/2022 03:05:11 - INFO - codeparrot_training - Step 11597: {'lr': 0.0004948304247062752, 'samples': 5938176, 'steps': 11597, 'loss/train': 2.3172852993011475}
-03/04/2022 03:05:11 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 03:05:17 - INFO - codeparrot_training - Step 11598: {'lr': 0.0004948293510479421, 'samples': 5938688, 'steps': 11598, 'loss/train': 1.316510558128357}
-03/04/2022 03:05:20 - INFO - codeparrot_training - Step 11599: {'lr': 0.0004948282772792927, 'samples': 5939200, 'steps': 11599, 'loss/train': 2.4569716453552246}
-03/04/2022 03:05:20 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 03:05:25 - INFO - codeparrot_training - Step 11600: {'lr': 0.0004948272034003275, 'samples': 5939712, 'steps': 11600, 'loss/train': 2.2728495597839355}
-03/04/2022 03:05:28 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/04/2022 03:05:30 - INFO - codeparrot_training - Step 11601: {'lr': 0.000494826129411047, 'samples': 5940224, 'steps': 11601, 'loss/train': 1.2059463262557983}
-03/04/2022 03:05:33 - INFO - codeparrot_training - Step 11602: {'lr': 0.0004948250553114516, 'samples': 5940736, 'steps': 11602, 'loss/train': 1.426198124885559}
-03/04/2022 03:05:36 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 03:05:39 - INFO - codeparrot_training - Step 11603: {'lr': 0.0004948239811015416, 'samples': 5941248, 'steps': 11603, 'loss/train': 2.3624093532562256}
-03/04/2022 03:05:42 - INFO - codeparrot_training - Step 11604: {'lr': 0.0004948229067813179, 'samples': 5941760, 'steps': 11604, 'loss/train': 2.313213348388672}
-03/04/2022 03:05:44 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/04/2022 03:05:47 - INFO - codeparrot_training - Step 11605: {'lr': 0.0004948218323507807, 'samples': 5942272, 'steps': 11605, 'loss/train': 2.334223508834839}
-03/04/2022 03:05:50 - INFO - codeparrot_training - Step 11606: {'lr': 0.0004948207578099306, 'samples': 5942784, 'steps': 11606, 'loss/train': 1.6964770555496216}
-03/04/2022 03:05:53 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/04/2022 03:05:56 - INFO - codeparrot_training - Step 11607: {'lr': 0.000494819683158768, 'samples': 5943296, 'steps': 11607, 'loss/train': 1.2323893308639526}
-03/04/2022 03:05:59 - INFO - codeparrot_training - Step 11608: {'lr': 0.0004948186083972934, 'samples': 5943808, 'steps': 11608, 'loss/train': 1.6982035636901855}
-03/04/2022 03:06:02 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/04/2022 03:06:04 - INFO - codeparrot_training - Step 11609: {'lr': 0.0004948175335255075, 'samples': 5944320, 'steps': 11609, 'loss/train': 2.2013068199157715}
-03/04/2022 03:06:07 - INFO - codeparrot_training - Step 11610: {'lr': 0.0004948164585434104, 'samples': 5944832, 'steps': 11610, 'loss/train': 2.846935510635376}
-03/04/2022 03:06:10 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/04/2022 03:06:12 - INFO - codeparrot_training - Step 11611: {'lr': 0.0004948153834510028, 'samples': 5945344, 'steps': 11611, 'loss/train': 0.6468235850334167}
-03/04/2022 03:06:15 - INFO - codeparrot_training - Step 11612: {'lr': 0.0004948143082482852, 'samples': 5945856, 'steps': 11612, 'loss/train': 2.0306482315063477}
-03/04/2022 03:06:18 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 03:06:21 - INFO - codeparrot_training - Step 11613: {'lr': 0.0004948132329352582, 'samples': 5946368, 'steps': 11613, 'loss/train': 1.7743967771530151}
-03/04/2022 03:06:24 - INFO - codeparrot_training - Step 11614: {'lr': 0.0004948121575119219, 'samples': 5946880, 'steps': 11614, 'loss/train': 1.855497121810913}
-03/04/2022 03:06:26 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/04/2022 03:06:29 - INFO - codeparrot_training - Step 11615: {'lr': 0.0004948110819782771, 'samples': 5947392, 'steps': 11615, 'loss/train': 2.051239490509033}
-03/04/2022 03:06:32 - INFO - codeparrot_training - Step 11616: {'lr': 0.0004948100063343243, 'samples': 5947904, 'steps': 11616, 'loss/train': 1.5288314819335938}
-03/04/2022 03:06:34 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/04/2022 03:06:38 - INFO - codeparrot_training - Step 11617: {'lr': 0.0004948089305800638, 'samples': 5948416, 'steps': 11617, 'loss/train': 2.512665271759033}
-03/04/2022 03:06:41 - INFO - codeparrot_training - Step 11618: {'lr': 0.0004948078547154962, 'samples': 5948928, 'steps': 11618, 'loss/train': 6.584039688110352}
-03/04/2022 03:06:43 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 03:06:46 - INFO - codeparrot_training - Step 11619: {'lr': 0.0004948067787406219, 'samples': 5949440, 'steps': 11619, 'loss/train': 2.1151626110076904}
-03/04/2022 03:06:49 - INFO - codeparrot_training - Step 11620: {'lr': 0.0004948057026554415, 'samples': 5949952, 'steps': 11620, 'loss/train': 1.6025198698043823}
-03/04/2022 03:06:51 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/04/2022 03:06:55 - INFO - codeparrot_training - Step 11621: {'lr': 0.0004948046264599554, 'samples': 5950464, 'steps': 11621, 'loss/train': 2.7027735710144043}
-03/04/2022 03:06:58 - INFO - codeparrot_training - Step 11622: {'lr': 0.0004948035501541641, 'samples': 5950976, 'steps': 11622, 'loss/train': 1.3692829608917236}
-03/04/2022 03:07:00 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/04/2022 03:07:03 - INFO - codeparrot_training - Step 11623: {'lr': 0.0004948024737380681, 'samples': 5951488, 'steps': 11623, 'loss/train': 1.620924472808838}
-03/04/2022 03:07:06 - INFO - codeparrot_training - Step 11624: {'lr': 0.000494801397211668, 'samples': 5952000, 'steps': 11624, 'loss/train': 1.9997014999389648}
-03/04/2022 03:07:08 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 03:07:11 - INFO - codeparrot_training - Step 11625: {'lr': 0.000494800320574964, 'samples': 5952512, 'steps': 11625, 'loss/train': 1.527510166168213}
-03/04/2022 03:07:15 - INFO - codeparrot_training - Step 11626: {'lr': 0.0004947992438279568, 'samples': 5953024, 'steps': 11626, 'loss/train': 2.3223485946655273}
-03/04/2022 03:07:17 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/04/2022 03:07:20 - INFO - codeparrot_training - Step 11627: {'lr': 0.0004947981669706469, 'samples': 5953536, 'steps': 11627, 'loss/train': 0.5641062259674072}
-03/04/2022 03:07:23 - INFO - codeparrot_training - Step 11628: {'lr': 0.0004947970900030346, 'samples': 5954048, 'steps': 11628, 'loss/train': 2.432230234146118}
-03/04/2022 03:07:25 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/04/2022 03:07:28 - INFO - codeparrot_training - Step 11629: {'lr': 0.0004947960129251206, 'samples': 5954560, 'steps': 11629, 'loss/train': 1.595378041267395}
-03/04/2022 03:07:32 - INFO - codeparrot_training - Step 11630: {'lr': 0.0004947949357369054, 'samples': 5955072, 'steps': 11630, 'loss/train': 2.119819164276123}
-03/04/2022 03:07:34 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/04/2022 03:07:37 - INFO - codeparrot_training - Step 11631: {'lr': 0.0004947938584383892, 'samples': 5955584, 'steps': 11631, 'loss/train': 1.6703479290008545}
-03/04/2022 03:07:40 - INFO - codeparrot_training - Step 11632: {'lr': 0.0004947927810295728, 'samples': 5956096, 'steps': 11632, 'loss/train': 2.024939775466919}
-03/04/2022 03:07:42 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/04/2022 03:07:45 - INFO - codeparrot_training - Step 11633: {'lr': 0.0004947917035104564, 'samples': 5956608, 'steps': 11633, 'loss/train': 2.3097803592681885}
-03/04/2022 03:07:48 - INFO - codeparrot_training - Step 11634: {'lr': 0.0004947906258810407, 'samples': 5957120, 'steps': 11634, 'loss/train': 2.0543746948242188}
-03/04/2022 03:07:50 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 03:07:54 - INFO - codeparrot_training - Step 11635: {'lr': 0.0004947895481413262, 'samples': 5957632, 'steps': 11635, 'loss/train': 2.007568120956421}
-03/04/2022 03:07:57 - INFO - codeparrot_training - Step 11636: {'lr': 0.0004947884702913133, 'samples': 5958144, 'steps': 11636, 'loss/train': 1.350721001625061}
-03/04/2022 03:07:59 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 03:08:02 - INFO - codeparrot_training - Step 11637: {'lr': 0.0004947873923310024, 'samples': 5958656, 'steps': 11637, 'loss/train': 1.615991234779358}
-03/04/2022 03:08:05 - INFO - codeparrot_training - Step 11638: {'lr': 0.0004947863142603941, 'samples': 5959168, 'steps': 11638, 'loss/train': 1.9464746713638306}
-03/04/2022 03:08:07 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 03:08:11 - INFO - codeparrot_training - Step 11639: {'lr': 0.0004947852360794889, 'samples': 5959680, 'steps': 11639, 'loss/train': 1.775571346282959}
-03/04/2022 03:08:14 - INFO - codeparrot_training - Step 11640: {'lr': 0.0004947841577882873, 'samples': 5960192, 'steps': 11640, 'loss/train': 1.9966723918914795}
-03/04/2022 03:08:16 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/04/2022 03:08:19 - INFO - codeparrot_training - Step 11641: {'lr': 0.0004947830793867896, 'samples': 5960704, 'steps': 11641, 'loss/train': 2.558562994003296}
-03/04/2022 03:08:22 - INFO - codeparrot_training - Step 11642: {'lr': 0.0004947820008749965, 'samples': 5961216, 'steps': 11642, 'loss/train': 1.3499159812927246}
-03/04/2022 03:08:24 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/04/2022 03:08:28 - INFO - codeparrot_training - Step 11643: {'lr': 0.0004947809222529084, 'samples': 5961728, 'steps': 11643, 'loss/train': 1.7272683382034302}
-03/04/2022 03:08:31 - INFO - codeparrot_training - Step 11644: {'lr': 0.0004947798435205258, 'samples': 5962240, 'steps': 11644, 'loss/train': 1.8699201345443726}
-03/04/2022 03:08:33 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/04/2022 03:08:36 - INFO - codeparrot_training - Step 11645: {'lr': 0.0004947787646778491, 'samples': 5962752, 'steps': 11645, 'loss/train': 1.848620057106018}
-03/04/2022 03:08:39 - INFO - codeparrot_training - Step 11646: {'lr': 0.0004947776857248791, 'samples': 5963264, 'steps': 11646, 'loss/train': 1.3437302112579346}
-03/04/2022 03:08:42 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/04/2022 03:08:44 - INFO - codeparrot_training - Step 11647: {'lr': 0.0004947766066616157, 'samples': 5963776, 'steps': 11647, 'loss/train': 2.354464530944824}
-03/04/2022 03:08:48 - INFO - codeparrot_training - Step 11648: {'lr': 0.00049477552748806, 'samples': 5964288, 'steps': 11648, 'loss/train': 2.2810583114624023}
-03/04/2022 03:08:50 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/04/2022 03:08:53 - INFO - codeparrot_training - Step 11649: {'lr': 0.0004947744482042122, 'samples': 5964800, 'steps': 11649, 'loss/train': 2.1040890216827393}
-03/04/2022 03:08:56 - INFO - codeparrot_training - Step 11650: {'lr': 0.0004947733688100728, 'samples': 5965312, 'steps': 11650, 'loss/train': 1.9814682006835938}
-03/04/2022 03:08:59 - INFO - codeparrot_training - Step 11651: {'lr': 0.0004947722893056423, 'samples': 5965824, 'steps': 11651, 'loss/train': 2.1278419494628906}
-03/04/2022 03:09:00 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/04/2022 03:09:05 - INFO - codeparrot_training - Step 11652: {'lr': 0.0004947712096909211, 'samples': 5966336, 'steps': 11652, 'loss/train': 1.8935948610305786}
-03/04/2022 03:09:08 - INFO - codeparrot_training - Step 11653: {'lr': 0.0004947701299659097, 'samples': 5966848, 'steps': 11653, 'loss/train': 1.9682180881500244}
-03/04/2022 03:09:08 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 03:09:13 - INFO - codeparrot_training - Step 11654: {'lr': 0.0004947690501306088, 'samples': 5967360, 'steps': 11654, 'loss/train': 2.626002550125122}
-03/04/2022 03:09:16 - INFO - codeparrot_training - Step 11655: {'lr': 0.0004947679701850187, 'samples': 5967872, 'steps': 11655, 'loss/train': 1.8014708757400513}
-03/04/2022 03:09:17 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/04/2022 03:09:22 - INFO - codeparrot_training - Step 11656: {'lr': 0.00049476689012914, 'samples': 5968384, 'steps': 11656, 'loss/train': 1.8062599897384644}
-03/04/2022 03:09:25 - INFO - codeparrot_training - Step 11657: {'lr': 0.0004947658099629731, 'samples': 5968896, 'steps': 11657, 'loss/train': 2.0634520053863525}
-03/04/2022 03:09:26 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/04/2022 03:09:30 - INFO - codeparrot_training - Step 11658: {'lr': 0.0004947647296865184, 'samples': 5969408, 'steps': 11658, 'loss/train': 1.9357049465179443}
-03/04/2022 03:09:33 - INFO - codeparrot_training - Step 11659: {'lr': 0.0004947636492997765, 'samples': 5969920, 'steps': 11659, 'loss/train': 2.1368188858032227}
-03/04/2022 03:09:34 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/04/2022 03:09:38 - INFO - codeparrot_training - Step 11660: {'lr': 0.0004947625688027479, 'samples': 5970432, 'steps': 11660, 'loss/train': 2.7752747535705566}
-03/04/2022 03:09:42 - INFO - codeparrot_training - Step 11661: {'lr': 0.0004947614881954332, 'samples': 5970944, 'steps': 11661, 'loss/train': 1.8393367528915405}
-03/04/2022 03:09:42 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 03:09:47 - INFO - codeparrot_training - Step 11662: {'lr': 0.0004947604074778325, 'samples': 5971456, 'steps': 11662, 'loss/train': 1.9850189685821533}
-03/04/2022 03:09:50 - INFO - codeparrot_training - Step 11663: {'lr': 0.0004947593266499468, 'samples': 5971968, 'steps': 11663, 'loss/train': 2.1426806449890137}
-03/04/2022 03:09:51 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/04/2022 03:09:55 - INFO - codeparrot_training - Step 11664: {'lr': 0.0004947582457117762, 'samples': 5972480, 'steps': 11664, 'loss/train': 2.588552951812744}
-03/04/2022 03:09:59 - INFO - codeparrot_training - Step 11665: {'lr': 0.0004947571646633214, 'samples': 5972992, 'steps': 11665, 'loss/train': 1.6639705896377563}
-03/04/2022 03:09:59 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 03:10:04 - INFO - codeparrot_training - Step 11666: {'lr': 0.0004947560835045826, 'samples': 5973504, 'steps': 11666, 'loss/train': 1.525505781173706}
-03/04/2022 03:10:07 - INFO - codeparrot_training - Step 11667: {'lr': 0.0004947550022355606, 'samples': 5974016, 'steps': 11667, 'loss/train': 1.867533564567566}
-03/04/2022 03:10:08 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/04/2022 03:10:12 - INFO - codeparrot_training - Step 11668: {'lr': 0.0004947539208562558, 'samples': 5974528, 'steps': 11668, 'loss/train': 1.7864381074905396}
-03/04/2022 03:10:15 - INFO - codeparrot_training - Step 11669: {'lr': 0.0004947528393666686, 'samples': 5975040, 'steps': 11669, 'loss/train': 1.8139450550079346}
-03/04/2022 03:10:16 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/04/2022 03:10:21 - INFO - codeparrot_training - Step 11670: {'lr': 0.0004947517577667996, 'samples': 5975552, 'steps': 11670, 'loss/train': 1.5856164693832397}
-03/04/2022 03:10:24 - INFO - codeparrot_training - Step 11671: {'lr': 0.0004947506760566492, 'samples': 5976064, 'steps': 11671, 'loss/train': 2.2024357318878174}
-03/04/2022 03:10:24 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 03:10:29 - INFO - codeparrot_training - Step 11672: {'lr': 0.0004947495942362179, 'samples': 5976576, 'steps': 11672, 'loss/train': 1.8798083066940308}
-03/04/2022 03:10:32 - INFO - codeparrot_training - Step 11673: {'lr': 0.0004947485123055063, 'samples': 5977088, 'steps': 11673, 'loss/train': 1.8232066631317139}
-03/04/2022 03:10:33 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/04/2022 03:10:38 - INFO - codeparrot_training - Step 11674: {'lr': 0.0004947474302645147, 'samples': 5977600, 'steps': 11674, 'loss/train': 1.8135814666748047}
-03/04/2022 03:10:41 - INFO - codeparrot_training - Step 11675: {'lr': 0.0004947463481132438, 'samples': 5978112, 'steps': 11675, 'loss/train': 1.4569389820098877}
-03/04/2022 03:10:42 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/04/2022 03:10:46 - INFO - codeparrot_training - Step 11676: {'lr': 0.0004947452658516938, 'samples': 5978624, 'steps': 11676, 'loss/train': 1.8785301446914673}
-03/04/2022 03:10:49 - INFO - codeparrot_training - Step 11677: {'lr': 0.0004947441834798655, 'samples': 5979136, 'steps': 11677, 'loss/train': 1.9131892919540405}
-03/04/2022 03:10:50 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/04/2022 03:10:54 - INFO - codeparrot_training - Step 11678: {'lr': 0.0004947431009977592, 'samples': 5979648, 'steps': 11678, 'loss/train': 2.541980028152466}
-03/04/2022 03:10:58 - INFO - codeparrot_training - Step 11679: {'lr': 0.0004947420184053755, 'samples': 5980160, 'steps': 11679, 'loss/train': 2.1012518405914307}
-03/04/2022 03:10:58 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 03:11:03 - INFO - codeparrot_training - Step 11680: {'lr': 0.0004947409357027148, 'samples': 5980672, 'steps': 11680, 'loss/train': 2.1147336959838867}
-03/04/2022 03:11:06 - INFO - codeparrot_training - Step 11681: {'lr': 0.0004947398528897775, 'samples': 5981184, 'steps': 11681, 'loss/train': 1.888668417930603}
-03/04/2022 03:11:07 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 03:11:12 - INFO - codeparrot_training - Step 11682: {'lr': 0.0004947387699665643, 'samples': 5981696, 'steps': 11682, 'loss/train': 2.1424975395202637}
-03/04/2022 03:11:15 - INFO - codeparrot_training - Step 11683: {'lr': 0.0004947376869330755, 'samples': 5982208, 'steps': 11683, 'loss/train': 2.606992244720459}
-03/04/2022 03:11:17 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 03:11:20 - INFO - codeparrot_training - Step 11684: {'lr': 0.0004947366037893118, 'samples': 5982720, 'steps': 11684, 'loss/train': 2.074744462966919}
-03/04/2022 03:11:23 - INFO - codeparrot_training - Step 11685: {'lr': 0.0004947355205352735, 'samples': 5983232, 'steps': 11685, 'loss/train': 1.2753627300262451}
-03/04/2022 03:11:25 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/04/2022 03:11:28 - INFO - codeparrot_training - Step 11686: {'lr': 0.0004947344371709611, 'samples': 5983744, 'steps': 11686, 'loss/train': 2.1307642459869385}
-03/04/2022 03:11:32 - INFO - codeparrot_training - Step 11687: {'lr': 0.0004947333536963753, 'samples': 5984256, 'steps': 11687, 'loss/train': 2.9204351902008057}
-03/04/2022 03:11:34 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 03:11:37 - INFO - codeparrot_training - Step 11688: {'lr': 0.0004947322701115163, 'samples': 5984768, 'steps': 11688, 'loss/train': 2.0357203483581543}
-03/04/2022 03:11:40 - INFO - codeparrot_training - Step 11689: {'lr': 0.0004947311864163847, 'samples': 5985280, 'steps': 11689, 'loss/train': 1.3272794485092163}
-03/04/2022 03:11:43 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 03:11:45 - INFO - codeparrot_training - Step 11690: {'lr': 0.000494730102610981, 'samples': 5985792, 'steps': 11690, 'loss/train': 1.3070952892303467}
-03/04/2022 03:11:49 - INFO - codeparrot_training - Step 11691: {'lr': 0.0004947290186953057, 'samples': 5986304, 'steps': 11691, 'loss/train': 2.191918134689331}
-03/04/2022 03:11:51 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 03:11:54 - INFO - codeparrot_training - Step 11692: {'lr': 0.0004947279346693594, 'samples': 5986816, 'steps': 11692, 'loss/train': 2.3469812870025635}
-03/04/2022 03:11:57 - INFO - codeparrot_training - Step 11693: {'lr': 0.0004947268505331424, 'samples': 5987328, 'steps': 11693, 'loss/train': 1.7096296548843384}
-03/04/2022 03:12:00 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/04/2022 03:12:02 - INFO - codeparrot_training - Step 11694: {'lr': 0.0004947257662866551, 'samples': 5987840, 'steps': 11694, 'loss/train': 2.188605546951294}
-03/04/2022 03:12:06 - INFO - codeparrot_training - Step 11695: {'lr': 0.0004947246819298984, 'samples': 5988352, 'steps': 11695, 'loss/train': 2.317871570587158}
-03/04/2022 03:12:08 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/04/2022 03:12:11 - INFO - codeparrot_training - Step 11696: {'lr': 0.0004947235974628723, 'samples': 5988864, 'steps': 11696, 'loss/train': 2.2691915035247803}
-03/04/2022 03:12:14 - INFO - codeparrot_training - Step 11697: {'lr': 0.0004947225128855777, 'samples': 5989376, 'steps': 11697, 'loss/train': 1.655196189880371}
-03/04/2022 03:12:16 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/04/2022 03:12:19 - INFO - codeparrot_training - Step 11698: {'lr': 0.0004947214281980149, 'samples': 5989888, 'steps': 11698, 'loss/train': 2.126302719116211}
-03/04/2022 03:12:22 - INFO - codeparrot_training - Step 11699: {'lr': 0.0004947203434001843, 'samples': 5990400, 'steps': 11699, 'loss/train': 1.9038232564926147}
-03/04/2022 03:12:25 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 03:12:28 - INFO - codeparrot_training - Step 11700: {'lr': 0.0004947192584920866, 'samples': 5990912, 'steps': 11700, 'loss/train': 2.1300878524780273}
-03/04/2022 03:12:31 - INFO - codeparrot_training - Step 11701: {'lr': 0.000494718173473722, 'samples': 5991424, 'steps': 11701, 'loss/train': 2.364041328430176}
-03/04/2022 03:12:33 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/04/2022 03:12:36 - INFO - codeparrot_training - Step 11702: {'lr': 0.0004947170883450913, 'samples': 5991936, 'steps': 11702, 'loss/train': 1.8591800928115845}
-03/04/2022 03:12:39 - INFO - codeparrot_training - Step 11703: {'lr': 0.000494716003106195, 'samples': 5992448, 'steps': 11703, 'loss/train': 1.884285569190979}
-03/04/2022 03:12:42 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/04/2022 03:12:45 - INFO - codeparrot_training - Step 11704: {'lr': 0.0004947149177570332, 'samples': 5992960, 'steps': 11704, 'loss/train': 1.105050802230835}
-03/04/2022 03:12:48 - INFO - codeparrot_training - Step 11705: {'lr': 0.0004947138322976067, 'samples': 5993472, 'steps': 11705, 'loss/train': 1.4291744232177734}
-03/04/2022 03:12:51 - INFO - codeparrot_training - Step 11706: {'lr': 0.000494712746727916, 'samples': 5993984, 'steps': 11706, 'loss/train': 2.472663402557373}
-03/04/2022 03:12:51 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/04/2022 03:12:56 - INFO - codeparrot_training - Step 11707: {'lr': 0.0004947116610479614, 'samples': 5994496, 'steps': 11707, 'loss/train': 1.7642221450805664}
-03/04/2022 03:12:59 - INFO - codeparrot_training - Step 11708: {'lr': 0.0004947105752577436, 'samples': 5995008, 'steps': 11708, 'loss/train': 2.659099817276001}
-03/04/2022 03:12:59 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 03:13:05 - INFO - codeparrot_training - Step 11709: {'lr': 0.0004947094893572629, 'samples': 5995520, 'steps': 11709, 'loss/train': 2.087855815887451}
-03/04/2022 03:13:08 - INFO - codeparrot_training - Step 11710: {'lr': 0.00049470840334652, 'samples': 5996032, 'steps': 11710, 'loss/train': 2.2359912395477295}
-03/04/2022 03:13:08 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/04/2022 03:13:13 - INFO - codeparrot_training - Step 11711: {'lr': 0.0004947073172255151, 'samples': 5996544, 'steps': 11711, 'loss/train': 0.5515193939208984}
-03/04/2022 03:13:16 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/04/2022 03:13:19 - INFO - codeparrot_training - Step 11712: {'lr': 0.000494706230994249, 'samples': 5997056, 'steps': 11712, 'loss/train': 2.118574857711792}
-03/04/2022 03:13:22 - INFO - codeparrot_training - Step 11713: {'lr': 0.000494705144652722, 'samples': 5997568, 'steps': 11713, 'loss/train': 1.8649550676345825}
-03/04/2022 03:13:24 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/04/2022 03:13:27 - INFO - codeparrot_training - Step 11714: {'lr': 0.0004947040582009346, 'samples': 5998080, 'steps': 11714, 'loss/train': 1.726132869720459}
-03/04/2022 03:13:30 - INFO - codeparrot_training - Step 11715: {'lr': 0.0004947029716388875, 'samples': 5998592, 'steps': 11715, 'loss/train': 3.681741714477539}
-03/04/2022 03:13:33 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 03:13:36 - INFO - codeparrot_training - Step 11716: {'lr': 0.0004947018849665809, 'samples': 5999104, 'steps': 11716, 'loss/train': 1.8598088026046753}
-03/04/2022 03:13:39 - INFO - codeparrot_training - Step 11717: {'lr': 0.0004947007981840153, 'samples': 5999616, 'steps': 11717, 'loss/train': 2.0602378845214844}
-03/04/2022 03:13:41 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 03:13:44 - INFO - codeparrot_training - Step 11718: {'lr': 0.0004946997112911914, 'samples': 6000128, 'steps': 11718, 'loss/train': 2.092210531234741}
-03/04/2022 03:13:47 - INFO - codeparrot_training - Step 11719: {'lr': 0.0004946986242881096, 'samples': 6000640, 'steps': 11719, 'loss/train': 3.182192325592041}
-03/04/2022 03:13:50 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/04/2022 03:13:53 - INFO - codeparrot_training - Step 11720: {'lr': 0.0004946975371747704, 'samples': 6001152, 'steps': 11720, 'loss/train': 2.3983752727508545}
-03/04/2022 03:13:56 - INFO - codeparrot_training - Step 11721: {'lr': 0.0004946964499511742, 'samples': 6001664, 'steps': 11721, 'loss/train': 0.4542219936847687}
-03/04/2022 03:13:58 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 03:14:01 - INFO - codeparrot_training - Step 11722: {'lr': 0.0004946953626173216, 'samples': 6002176, 'steps': 11722, 'loss/train': 1.4975265264511108}
-03/04/2022 03:14:04 - INFO - codeparrot_training - Step 11723: {'lr': 0.0004946942751732129, 'samples': 6002688, 'steps': 11723, 'loss/train': 6.744487285614014}
-03/04/2022 03:14:07 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/04/2022 03:14:10 - INFO - codeparrot_training - Step 11724: {'lr': 0.000494693187618849, 'samples': 6003200, 'steps': 11724, 'loss/train': 1.0294462442398071}
-03/04/2022 03:14:13 - INFO - codeparrot_training - Step 11725: {'lr': 0.0004946920999542299, 'samples': 6003712, 'steps': 11725, 'loss/train': 1.7147597074508667}
-03/04/2022 03:14:16 - INFO - codeparrot_training - Step 11726: {'lr': 0.0004946910121793564, 'samples': 6004224, 'steps': 11726, 'loss/train': 2.4622950553894043}
-03/04/2022 03:14:16 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/04/2022 03:14:21 - INFO - codeparrot_training - Step 11727: {'lr': 0.0004946899242942289, 'samples': 6004736, 'steps': 11727, 'loss/train': 2.3665590286254883}
-03/04/2022 03:14:24 - INFO - codeparrot_training - Step 11728: {'lr': 0.000494688836298848, 'samples': 6005248, 'steps': 11728, 'loss/train': 2.265429735183716}
-03/04/2022 03:14:24 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 03:14:30 - INFO - codeparrot_training - Step 11729: {'lr': 0.0004946877481932139, 'samples': 6005760, 'steps': 11729, 'loss/train': 2.16703724861145}
-03/04/2022 03:14:33 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/04/2022 03:14:35 - INFO - codeparrot_training - Step 11730: {'lr': 0.0004946866599773274, 'samples': 6006272, 'steps': 11730, 'loss/train': 2.610690116882324}
-03/04/2022 03:14:38 - INFO - codeparrot_training - Step 11731: {'lr': 0.0004946855716511888, 'samples': 6006784, 'steps': 11731, 'loss/train': 2.4835379123687744}
-03/04/2022 03:14:41 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/04/2022 03:14:43 - INFO - codeparrot_training - Step 11732: {'lr': 0.0004946844832147987, 'samples': 6007296, 'steps': 11732, 'loss/train': 1.5910751819610596}
-03/04/2022 03:14:47 - INFO - codeparrot_training - Step 11733: {'lr': 0.0004946833946681575, 'samples': 6007808, 'steps': 11733, 'loss/train': 1.5752335786819458}
-03/04/2022 03:14:49 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/04/2022 03:14:52 - INFO - codeparrot_training - Step 11734: {'lr': 0.0004946823060112658, 'samples': 6008320, 'steps': 11734, 'loss/train': 2.8870394229888916}
-03/04/2022 03:14:55 - INFO - codeparrot_training - Step 11735: {'lr': 0.000494681217244124, 'samples': 6008832, 'steps': 11735, 'loss/train': 2.12750244140625}
-03/04/2022 03:14:58 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/04/2022 03:15:01 - INFO - codeparrot_training - Step 11736: {'lr': 0.0004946801283667326, 'samples': 6009344, 'steps': 11736, 'loss/train': 1.1686149835586548}
-03/04/2022 03:15:04 - INFO - codeparrot_training - Step 11737: {'lr': 0.0004946790393790921, 'samples': 6009856, 'steps': 11737, 'loss/train': 2.016576051712036}
-03/04/2022 03:15:07 - INFO - codeparrot_training - Step 11738: {'lr': 0.0004946779502812031, 'samples': 6010368, 'steps': 11738, 'loss/train': 2.1066548824310303}
-03/04/2022 03:15:07 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 03:15:12 - INFO - codeparrot_training - Step 11739: {'lr': 0.0004946768610730659, 'samples': 6010880, 'steps': 11739, 'loss/train': 2.3113629817962646}
-03/04/2022 03:15:16 - INFO - codeparrot_training - Step 11740: {'lr': 0.0004946757717546812, 'samples': 6011392, 'steps': 11740, 'loss/train': 1.5239843130111694}
-03/04/2022 03:15:16 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/04/2022 03:15:21 - INFO - codeparrot_training - Step 11741: {'lr': 0.0004946746823260491, 'samples': 6011904, 'steps': 11741, 'loss/train': 2.000196933746338}
-03/04/2022 03:15:24 - INFO - codeparrot_training - Step 11742: {'lr': 0.0004946735927871706, 'samples': 6012416, 'steps': 11742, 'loss/train': 1.3032910823822021}
-03/04/2022 03:15:24 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/04/2022 03:15:30 - INFO - codeparrot_training - Step 11743: {'lr': 0.0004946725031380459, 'samples': 6012928, 'steps': 11743, 'loss/train': 1.4232947826385498}
-03/04/2022 03:15:33 - INFO - codeparrot_training - Step 11744: {'lr': 0.0004946714133786756, 'samples': 6013440, 'steps': 11744, 'loss/train': 0.6736693382263184}
-03/04/2022 03:15:33 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/04/2022 03:15:38 - INFO - codeparrot_training - Step 11745: {'lr': 0.00049467032350906, 'samples': 6013952, 'steps': 11745, 'loss/train': 2.4404804706573486}
-03/04/2022 03:15:41 - INFO - codeparrot_training - Step 11746: {'lr': 0.0004946692335291999, 'samples': 6014464, 'steps': 11746, 'loss/train': 0.8412255644798279}
-03/04/2022 03:15:41 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/04/2022 03:15:46 - INFO - codeparrot_training - Step 11747: {'lr': 0.0004946681434390955, 'samples': 6014976, 'steps': 11747, 'loss/train': 0.7771939635276794}
-03/04/2022 03:15:50 - INFO - codeparrot_training - Step 11748: {'lr': 0.0004946670532387474, 'samples': 6015488, 'steps': 11748, 'loss/train': 1.395177960395813}
-03/04/2022 03:15:50 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 03:15:55 - INFO - codeparrot_training - Step 11749: {'lr': 0.0004946659629281561, 'samples': 6016000, 'steps': 11749, 'loss/train': 2.0985875129699707}
-03/04/2022 03:15:58 - INFO - codeparrot_training - Step 11750: {'lr': 0.0004946648725073222, 'samples': 6016512, 'steps': 11750, 'loss/train': 1.2280323505401611}
-03/04/2022 03:15:58 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/04/2022 03:16:03 - INFO - codeparrot_training - Step 11751: {'lr': 0.0004946637819762459, 'samples': 6017024, 'steps': 11751, 'loss/train': 2.949972152709961}
-03/04/2022 03:16:06 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/04/2022 03:16:09 - INFO - codeparrot_training - Step 11752: {'lr': 0.000494662691334928, 'samples': 6017536, 'steps': 11752, 'loss/train': 2.826047897338867}
-03/04/2022 03:16:12 - INFO - codeparrot_training - Step 11753: {'lr': 0.0004946616005833689, 'samples': 6018048, 'steps': 11753, 'loss/train': 1.9433826208114624}
-03/04/2022 03:16:15 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/04/2022 03:16:17 - INFO - codeparrot_training - Step 11754: {'lr': 0.0004946605097215691, 'samples': 6018560, 'steps': 11754, 'loss/train': 2.3915722370147705}
-03/04/2022 03:16:20 - INFO - codeparrot_training - Step 11755: {'lr': 0.0004946594187495289, 'samples': 6019072, 'steps': 11755, 'loss/train': 2.1543564796447754}
-03/04/2022 03:16:23 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/04/2022 03:16:25 - INFO - codeparrot_training - Step 11756: {'lr': 0.0004946583276672489, 'samples': 6019584, 'steps': 11756, 'loss/train': 1.5275945663452148}
-03/04/2022 03:16:29 - INFO - codeparrot_training - Step 11757: {'lr': 0.0004946572364747298, 'samples': 6020096, 'steps': 11757, 'loss/train': 2.363659381866455}
-03/04/2022 03:16:31 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/04/2022 03:16:34 - INFO - codeparrot_training - Step 11758: {'lr': 0.0004946561451719719, 'samples': 6020608, 'steps': 11758, 'loss/train': 1.849278211593628}
-03/04/2022 03:16:37 - INFO - codeparrot_training - Step 11759: {'lr': 0.0004946550537589757, 'samples': 6021120, 'steps': 11759, 'loss/train': 1.4709974527359009}
-03/04/2022 03:16:40 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/04/2022 03:16:42 - INFO - codeparrot_training - Step 11760: {'lr': 0.0004946539622357417, 'samples': 6021632, 'steps': 11760, 'loss/train': 2.125964403152466}
-03/04/2022 03:16:46 - INFO - codeparrot_training - Step 11761: {'lr': 0.0004946528706022703, 'samples': 6022144, 'steps': 11761, 'loss/train': 2.108844041824341}
-03/04/2022 03:16:48 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 03:16:51 - INFO - codeparrot_training - Step 11762: {'lr': 0.0004946517788585622, 'samples': 6022656, 'steps': 11762, 'loss/train': 2.148332118988037}
-03/04/2022 03:16:54 - INFO - codeparrot_training - Step 11763: {'lr': 0.0004946506870046178, 'samples': 6023168, 'steps': 11763, 'loss/train': 2.3718271255493164}
-03/04/2022 03:16:57 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 03:16:59 - INFO - codeparrot_training - Step 11764: {'lr': 0.0004946495950404375, 'samples': 6023680, 'steps': 11764, 'loss/train': 2.3746888637542725}
-03/04/2022 03:17:03 - INFO - codeparrot_training - Step 11765: {'lr': 0.0004946485029660219, 'samples': 6024192, 'steps': 11765, 'loss/train': 2.0444443225860596}
-03/04/2022 03:17:06 - INFO - codeparrot_training - Step 11766: {'lr': 0.0004946474107813715, 'samples': 6024704, 'steps': 11766, 'loss/train': 2.8323097229003906}
-03/04/2022 03:17:06 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/04/2022 03:17:11 - INFO - codeparrot_training - Step 11767: {'lr': 0.0004946463184864867, 'samples': 6025216, 'steps': 11767, 'loss/train': 2.4797186851501465}
-03/04/2022 03:17:15 - INFO - codeparrot_training - Step 11768: {'lr': 0.000494645226081368, 'samples': 6025728, 'steps': 11768, 'loss/train': 1.5113987922668457}
-03/04/2022 03:17:16 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/04/2022 03:17:20 - INFO - codeparrot_training - Step 11769: {'lr': 0.000494644133566016, 'samples': 6026240, 'steps': 11769, 'loss/train': 2.770507335662842}
-03/04/2022 03:17:23 - INFO - codeparrot_training - Step 11770: {'lr': 0.0004946430409404311, 'samples': 6026752, 'steps': 11770, 'loss/train': 3.3343873023986816}
-03/04/2022 03:17:24 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/04/2022 03:17:28 - INFO - codeparrot_training - Step 11771: {'lr': 0.0004946419482046139, 'samples': 6027264, 'steps': 11771, 'loss/train': 0.863908588886261}
-03/04/2022 03:17:32 - INFO - codeparrot_training - Step 11772: {'lr': 0.0004946408553585648, 'samples': 6027776, 'steps': 11772, 'loss/train': 1.6273177862167358}
-03/04/2022 03:17:33 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 03:17:37 - INFO - codeparrot_training - Step 11773: {'lr': 0.0004946397624022843, 'samples': 6028288, 'steps': 11773, 'loss/train': 2.735278844833374}
-03/04/2022 03:17:40 - INFO - codeparrot_training - Step 11774: {'lr': 0.0004946386693357728, 'samples': 6028800, 'steps': 11774, 'loss/train': 2.16176438331604}
-03/04/2022 03:17:41 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/04/2022 03:17:45 - INFO - codeparrot_training - Step 11775: {'lr': 0.0004946375761590309, 'samples': 6029312, 'steps': 11775, 'loss/train': 6.671604156494141}
-03/04/2022 03:17:48 - INFO - codeparrot_training - Step 11776: {'lr': 0.0004946364828720592, 'samples': 6029824, 'steps': 11776, 'loss/train': 1.7948395013809204}
-03/04/2022 03:17:50 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/04/2022 03:17:54 - INFO - codeparrot_training - Step 11777: {'lr': 0.000494635389474858, 'samples': 6030336, 'steps': 11777, 'loss/train': 2.2073051929473877}
-03/04/2022 03:17:57 - INFO - codeparrot_training - Step 11778: {'lr': 0.0004946342959674278, 'samples': 6030848, 'steps': 11778, 'loss/train': 2.1324517726898193}
-03/04/2022 03:17:58 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/04/2022 03:18:02 - INFO - codeparrot_training - Step 11779: {'lr': 0.0004946332023497693, 'samples': 6031360, 'steps': 11779, 'loss/train': 1.8324729204177856}
-03/04/2022 03:18:05 - INFO - codeparrot_training - Step 11780: {'lr': 0.0004946321086218828, 'samples': 6031872, 'steps': 11780, 'loss/train': 1.4254385232925415}
-03/04/2022 03:18:06 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/04/2022 03:18:11 - INFO - codeparrot_training - Step 11781: {'lr': 0.0004946310147837689, 'samples': 6032384, 'steps': 11781, 'loss/train': 1.9257586002349854}
-03/04/2022 03:18:14 - INFO - codeparrot_training - Step 11782: {'lr': 0.0004946299208354279, 'samples': 6032896, 'steps': 11782, 'loss/train': 2.138476610183716}
-03/04/2022 03:18:15 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 03:18:19 - INFO - codeparrot_training - Step 11783: {'lr': 0.0004946288267768605, 'samples': 6033408, 'steps': 11783, 'loss/train': 2.464582920074463}
-03/04/2022 03:18:22 - INFO - codeparrot_training - Step 11784: {'lr': 0.0004946277326080672, 'samples': 6033920, 'steps': 11784, 'loss/train': 1.7435630559921265}
-03/04/2022 03:18:23 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/04/2022 03:18:27 - INFO - codeparrot_training - Step 11785: {'lr': 0.0004946266383290483, 'samples': 6034432, 'steps': 11785, 'loss/train': 2.2966129779815674}
-03/04/2022 03:18:31 - INFO - codeparrot_training - Step 11786: {'lr': 0.0004946255439398045, 'samples': 6034944, 'steps': 11786, 'loss/train': 1.8287135362625122}
-03/04/2022 03:18:31 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/04/2022 03:18:36 - INFO - codeparrot_training - Step 11787: {'lr': 0.0004946244494403361, 'samples': 6035456, 'steps': 11787, 'loss/train': 1.9028756618499756}
-03/04/2022 03:18:39 - INFO - codeparrot_training - Step 11788: {'lr': 0.0004946233548306438, 'samples': 6035968, 'steps': 11788, 'loss/train': 2.575775623321533}
-03/04/2022 03:18:40 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/04/2022 03:18:44 - INFO - codeparrot_training - Step 11789: {'lr': 0.000494622260110728, 'samples': 6036480, 'steps': 11789, 'loss/train': 1.3244400024414062}
-03/04/2022 03:18:47 - INFO - codeparrot_training - Step 11790: {'lr': 0.0004946211652805891, 'samples': 6036992, 'steps': 11790, 'loss/train': 1.809003233909607}
-03/04/2022 03:18:48 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/04/2022 03:18:53 - INFO - codeparrot_training - Step 11791: {'lr': 0.0004946200703402278, 'samples': 6037504, 'steps': 11791, 'loss/train': 2.618291139602661}
-03/04/2022 03:18:56 - INFO - codeparrot_training - Step 11792: {'lr': 0.0004946189752896443, 'samples': 6038016, 'steps': 11792, 'loss/train': 1.739932894706726}
-03/04/2022 03:18:58 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/04/2022 03:19:02 - INFO - codeparrot_training - Step 11793: {'lr': 0.0004946178801288394, 'samples': 6038528, 'steps': 11793, 'loss/train': 1.5415972471237183}
-03/04/2022 03:19:05 - INFO - codeparrot_training - Step 11794: {'lr': 0.0004946167848578134, 'samples': 6039040, 'steps': 11794, 'loss/train': 1.8117008209228516}
-03/04/2022 03:19:07 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/04/2022 03:19:10 - INFO - codeparrot_training - Step 11795: {'lr': 0.0004946156894765669, 'samples': 6039552, 'steps': 11795, 'loss/train': 2.599088191986084}
-03/04/2022 03:19:13 - INFO - codeparrot_training - Step 11796: {'lr': 0.0004946145939851004, 'samples': 6040064, 'steps': 11796, 'loss/train': 4.590936660766602}
-03/04/2022 03:19:15 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/04/2022 03:19:19 - INFO - codeparrot_training - Step 11797: {'lr': 0.0004946134983834142, 'samples': 6040576, 'steps': 11797, 'loss/train': 1.0269355773925781}
-03/04/2022 03:19:22 - INFO - codeparrot_training - Step 11798: {'lr': 0.0004946124026715089, 'samples': 6041088, 'steps': 11798, 'loss/train': 2.8989644050598145}
-03/04/2022 03:19:25 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 03:19:27 - INFO - codeparrot_training - Step 11799: {'lr': 0.0004946113068493851, 'samples': 6041600, 'steps': 11799, 'loss/train': 1.835639476776123}
-03/04/2022 03:19:30 - INFO - codeparrot_training - Step 11800: {'lr': 0.0004946102109170433, 'samples': 6042112, 'steps': 11800, 'loss/train': 3.037527084350586}
-03/04/2022 03:19:33 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/04/2022 03:19:36 - INFO - codeparrot_training - Step 11801: {'lr': 0.0004946091148744838, 'samples': 6042624, 'steps': 11801, 'loss/train': 2.3110077381134033}
-03/04/2022 03:19:39 - INFO - codeparrot_training - Step 11802: {'lr': 0.0004946080187217072, 'samples': 6043136, 'steps': 11802, 'loss/train': 2.4717373847961426}
-03/04/2022 03:19:41 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 03:19:44 - INFO - codeparrot_training - Step 11803: {'lr': 0.0004946069224587141, 'samples': 6043648, 'steps': 11803, 'loss/train': 2.031247615814209}
-03/04/2022 03:19:47 - INFO - codeparrot_training - Step 11804: {'lr': 0.0004946058260855049, 'samples': 6044160, 'steps': 11804, 'loss/train': 2.1726253032684326}
-03/04/2022 03:19:50 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/04/2022 03:19:52 - INFO - codeparrot_training - Step 11805: {'lr': 0.00049460472960208, 'samples': 6044672, 'steps': 11805, 'loss/train': 2.334925413131714}
-03/04/2022 03:19:56 - INFO - codeparrot_training - Step 11806: {'lr': 0.00049460363300844, 'samples': 6045184, 'steps': 11806, 'loss/train': 2.1793899536132812}
-03/04/2022 03:19:58 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 03:20:01 - INFO - codeparrot_training - Step 11807: {'lr': 0.0004946025363045854, 'samples': 6045696, 'steps': 11807, 'loss/train': 2.6041617393493652}
-03/04/2022 03:20:04 - INFO - codeparrot_training - Step 11808: {'lr': 0.0004946014394905167, 'samples': 6046208, 'steps': 11808, 'loss/train': 1.496350884437561}
-03/04/2022 03:20:07 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/04/2022 03:20:09 - INFO - codeparrot_training - Step 11809: {'lr': 0.0004946003425662343, 'samples': 6046720, 'steps': 11809, 'loss/train': 1.5074448585510254}
-03/04/2022 03:20:12 - INFO - codeparrot_training - Step 11810: {'lr': 0.0004945992455317389, 'samples': 6047232, 'steps': 11810, 'loss/train': 1.8214595317840576}
-03/04/2022 03:20:15 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/04/2022 03:20:18 - INFO - codeparrot_training - Step 11811: {'lr': 0.0004945981483870307, 'samples': 6047744, 'steps': 11811, 'loss/train': 1.6098524332046509}
-03/04/2022 03:20:21 - INFO - codeparrot_training - Step 11812: {'lr': 0.0004945970511321104, 'samples': 6048256, 'steps': 11812, 'loss/train': 1.9906209707260132}
-03/04/2022 03:20:23 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/04/2022 03:20:26 - INFO - codeparrot_training - Step 11813: {'lr': 0.0004945959537669784, 'samples': 6048768, 'steps': 11813, 'loss/train': 1.34119713306427}
-03/04/2022 03:20:29 - INFO - codeparrot_training - Step 11814: {'lr': 0.0004945948562916353, 'samples': 6049280, 'steps': 11814, 'loss/train': 1.6972978115081787}
-03/04/2022 03:20:32 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/04/2022 03:20:35 - INFO - codeparrot_training - Step 11815: {'lr': 0.0004945937587060815, 'samples': 6049792, 'steps': 11815, 'loss/train': 2.1402807235717773}
-03/04/2022 03:20:38 - INFO - codeparrot_training - Step 11816: {'lr': 0.0004945926610103175, 'samples': 6050304, 'steps': 11816, 'loss/train': 1.6462830305099487}
-03/04/2022 03:20:41 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/04/2022 03:20:43 - INFO - codeparrot_training - Step 11817: {'lr': 0.0004945915632043439, 'samples': 6050816, 'steps': 11817, 'loss/train': 2.665799140930176}
-03/04/2022 03:20:46 - INFO - codeparrot_training - Step 11818: {'lr': 0.0004945904652881611, 'samples': 6051328, 'steps': 11818, 'loss/train': 2.2569386959075928}
-03/04/2022 03:20:49 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/04/2022 03:20:52 - INFO - codeparrot_training - Step 11819: {'lr': 0.0004945893672617695, 'samples': 6051840, 'steps': 11819, 'loss/train': 2.4117813110351562}
-03/04/2022 03:20:55 - INFO - codeparrot_training - Step 11820: {'lr': 0.0004945882691251699, 'samples': 6052352, 'steps': 11820, 'loss/train': 1.7262266874313354}
-03/04/2022 03:20:57 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/04/2022 03:21:00 - INFO - codeparrot_training - Step 11821: {'lr': 0.0004945871708783625, 'samples': 6052864, 'steps': 11821, 'loss/train': 1.6434522867202759}
-03/04/2022 03:21:03 - INFO - codeparrot_training - Step 11822: {'lr': 0.0004945860725213477, 'samples': 6053376, 'steps': 11822, 'loss/train': 1.45069420337677}
-03/04/2022 03:21:06 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 03:21:08 - INFO - codeparrot_training - Step 11823: {'lr': 0.0004945849740541265, 'samples': 6053888, 'steps': 11823, 'loss/train': 1.5899266004562378}
-03/04/2022 03:21:12 - INFO - codeparrot_training - Step 11824: {'lr': 0.000494583875476699, 'samples': 6054400, 'steps': 11824, 'loss/train': 1.5530508756637573}
-03/04/2022 03:21:14 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 03:21:17 - INFO - codeparrot_training - Step 11825: {'lr': 0.0004945827767890657, 'samples': 6054912, 'steps': 11825, 'loss/train': 1.18204665184021}
-03/04/2022 03:21:20 - INFO - codeparrot_training - Step 11826: {'lr': 0.0004945816779912272, 'samples': 6055424, 'steps': 11826, 'loss/train': 2.1296029090881348}
-03/04/2022 03:21:23 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/04/2022 03:21:25 - INFO - codeparrot_training - Step 11827: {'lr': 0.000494580579083184, 'samples': 6055936, 'steps': 11827, 'loss/train': 0.9548342227935791}
-03/04/2022 03:21:29 - INFO - codeparrot_training - Step 11828: {'lr': 0.0004945794800649366, 'samples': 6056448, 'steps': 11828, 'loss/train': 2.129260301589966}
-03/04/2022 03:21:31 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/04/2022 03:21:34 - INFO - codeparrot_training - Step 11829: {'lr': 0.0004945783809364853, 'samples': 6056960, 'steps': 11829, 'loss/train': 2.105114221572876}
-03/04/2022 03:21:37 - INFO - codeparrot_training - Step 11830: {'lr': 0.0004945772816978309, 'samples': 6057472, 'steps': 11830, 'loss/train': 2.903532028198242}
-03/04/2022 03:21:39 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/04/2022 03:21:42 - INFO - codeparrot_training - Step 11831: {'lr': 0.0004945761823489737, 'samples': 6057984, 'steps': 11831, 'loss/train': 1.2571446895599365}
-03/04/2022 03:21:45 - INFO - codeparrot_training - Step 11832: {'lr': 0.0004945750828899144, 'samples': 6058496, 'steps': 11832, 'loss/train': 1.8392815589904785}
-03/04/2022 03:21:48 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/04/2022 03:21:51 - INFO - codeparrot_training - Step 11833: {'lr': 0.0004945739833206531, 'samples': 6059008, 'steps': 11833, 'loss/train': 1.6349468231201172}
-03/04/2022 03:21:54 - INFO - codeparrot_training - Step 11834: {'lr': 0.0004945728836411907, 'samples': 6059520, 'steps': 11834, 'loss/train': 2.017778158187866}
-03/04/2022 03:21:56 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/04/2022 03:21:59 - INFO - codeparrot_training - Step 11835: {'lr': 0.0004945717838515275, 'samples': 6060032, 'steps': 11835, 'loss/train': 0.5772780179977417}
-03/04/2022 03:22:02 - INFO - codeparrot_training - Step 11836: {'lr': 0.0004945706839516639, 'samples': 6060544, 'steps': 11836, 'loss/train': 1.9016187191009521}
-03/04/2022 03:22:04 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/04/2022 03:22:08 - INFO - codeparrot_training - Step 11837: {'lr': 0.0004945695839416006, 'samples': 6061056, 'steps': 11837, 'loss/train': 1.5418466329574585}
-03/04/2022 03:22:11 - INFO - codeparrot_training - Step 11838: {'lr': 0.0004945684838213382, 'samples': 6061568, 'steps': 11838, 'loss/train': 2.407442808151245}
-03/04/2022 03:22:13 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/04/2022 03:22:16 - INFO - codeparrot_training - Step 11839: {'lr': 0.0004945673835908767, 'samples': 6062080, 'steps': 11839, 'loss/train': 2.3057985305786133}
-03/04/2022 03:22:19 - INFO - codeparrot_training - Step 11840: {'lr': 0.0004945662832502171, 'samples': 6062592, 'steps': 11840, 'loss/train': 1.654412031173706}
-03/04/2022 03:22:21 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/04/2022 03:22:24 - INFO - codeparrot_training - Step 11841: {'lr': 0.0004945651827993597, 'samples': 6063104, 'steps': 11841, 'loss/train': 2.48502779006958}
-03/04/2022 03:22:28 - INFO - codeparrot_training - Step 11842: {'lr': 0.000494564082238305, 'samples': 6063616, 'steps': 11842, 'loss/train': 1.8905714750289917}
-03/04/2022 03:22:30 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/04/2022 03:22:33 - INFO - codeparrot_training - Step 11843: {'lr': 0.0004945629815670535, 'samples': 6064128, 'steps': 11843, 'loss/train': 2.964888095855713}
-03/04/2022 03:22:36 - INFO - codeparrot_training - Step 11844: {'lr': 0.0004945618807856056, 'samples': 6064640, 'steps': 11844, 'loss/train': 0.3255341649055481}
-03/04/2022 03:22:38 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/04/2022 03:22:41 - INFO - codeparrot_training - Step 11845: {'lr': 0.000494560779893962, 'samples': 6065152, 'steps': 11845, 'loss/train': 1.4515554904937744}
-03/04/2022 03:22:45 - INFO - codeparrot_training - Step 11846: {'lr': 0.0004945596788921231, 'samples': 6065664, 'steps': 11846, 'loss/train': 1.4483325481414795}
-03/04/2022 03:22:46 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 03:22:50 - INFO - codeparrot_training - Step 11847: {'lr': 0.0004945585777800893, 'samples': 6066176, 'steps': 11847, 'loss/train': 1.757810115814209}
-03/04/2022 03:22:53 - INFO - codeparrot_training - Step 11848: {'lr': 0.0004945574765578612, 'samples': 6066688, 'steps': 11848, 'loss/train': 2.5027244091033936}
-03/04/2022 03:22:55 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/04/2022 03:22:58 - INFO - codeparrot_training - Step 11849: {'lr': 0.0004945563752254393, 'samples': 6067200, 'steps': 11849, 'loss/train': 2.3880996704101562}
-03/04/2022 03:23:02 - INFO - codeparrot_training - Step 11850: {'lr': 0.000494555273782824, 'samples': 6067712, 'steps': 11850, 'loss/train': 2.1988883018493652}
-03/04/2022 03:23:04 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 03:23:07 - INFO - codeparrot_training - Step 11851: {'lr': 0.000494554172230016, 'samples': 6068224, 'steps': 11851, 'loss/train': 2.285205364227295}
-03/04/2022 03:23:10 - INFO - codeparrot_training - Step 11852: {'lr': 0.0004945530705670156, 'samples': 6068736, 'steps': 11852, 'loss/train': 2.3756229877471924}
-03/04/2022 03:23:12 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 03:23:15 - INFO - codeparrot_training - Step 11853: {'lr': 0.0004945519687938234, 'samples': 6069248, 'steps': 11853, 'loss/train': 2.043999671936035}
-03/04/2022 03:23:18 - INFO - codeparrot_training - Step 11854: {'lr': 0.0004945508669104397, 'samples': 6069760, 'steps': 11854, 'loss/train': 2.462625503540039}
-03/04/2022 03:23:21 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/04/2022 03:23:24 - INFO - codeparrot_training - Step 11855: {'lr': 0.0004945497649168654, 'samples': 6070272, 'steps': 11855, 'loss/train': 2.1539855003356934}
-03/04/2022 03:23:27 - INFO - codeparrot_training - Step 11856: {'lr': 0.0004945486628131006, 'samples': 6070784, 'steps': 11856, 'loss/train': 2.3442108631134033}
-03/04/2022 03:23:32 - INFO - codeparrot_training - Step 11857: {'lr': 0.0004945475605991459, 'samples': 6071296, 'steps': 11857, 'loss/train': 1.710718035697937}
-03/04/2022 03:23:35 - INFO - codeparrot_training - Step 11858: {'lr': 0.0004945464582750019, 'samples': 6071808, 'steps': 11858, 'loss/train': 2.28558349609375}
-03/04/2022 03:23:37 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/04/2022 03:23:41 - INFO - codeparrot_training - Step 11859: {'lr': 0.000494545355840669, 'samples': 6072320, 'steps': 11859, 'loss/train': 1.3152351379394531}
-03/04/2022 03:23:44 - INFO - codeparrot_training - Step 11860: {'lr': 0.0004945442532961478, 'samples': 6072832, 'steps': 11860, 'loss/train': 3.0074727535247803}
-03/04/2022 03:23:46 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 03:23:49 - INFO - codeparrot_training - Step 11861: {'lr': 0.0004945431506414386, 'samples': 6073344, 'steps': 11861, 'loss/train': 1.31696617603302}
-03/04/2022 03:23:52 - INFO - codeparrot_training - Step 11862: {'lr': 0.0004945420478765422, 'samples': 6073856, 'steps': 11862, 'loss/train': 0.671810507774353}
-03/04/2022 03:23:54 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/04/2022 03:23:57 - INFO - codeparrot_training - Step 11863: {'lr': 0.0004945409450014588, 'samples': 6074368, 'steps': 11863, 'loss/train': 2.5137767791748047}
-03/04/2022 03:24:01 - INFO - codeparrot_training - Step 11864: {'lr': 0.0004945398420161892, 'samples': 6074880, 'steps': 11864, 'loss/train': 1.5095854997634888}
-03/04/2022 03:24:02 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/04/2022 03:24:06 - INFO - codeparrot_training - Step 11865: {'lr': 0.0004945387389207335, 'samples': 6075392, 'steps': 11865, 'loss/train': 1.6500303745269775}
-03/04/2022 03:24:09 - INFO - codeparrot_training - Step 11866: {'lr': 0.0004945376357150926, 'samples': 6075904, 'steps': 11866, 'loss/train': 1.6986870765686035}
-03/04/2022 03:24:11 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/04/2022 03:24:15 - INFO - codeparrot_training - Step 11867: {'lr': 0.0004945365323992668, 'samples': 6076416, 'steps': 11867, 'loss/train': 1.9465668201446533}
-03/04/2022 03:24:18 - INFO - codeparrot_training - Step 11868: {'lr': 0.0004945354289732565, 'samples': 6076928, 'steps': 11868, 'loss/train': 2.259317398071289}
-03/04/2022 03:24:21 - INFO - codeparrot_training - Step 11869: {'lr': 0.0004945343254370623, 'samples': 6077440, 'steps': 11869, 'loss/train': 2.125157356262207}
-03/04/2022 03:24:21 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 03:24:26 - INFO - codeparrot_training - Step 11870: {'lr': 0.0004945332217906848, 'samples': 6077952, 'steps': 11870, 'loss/train': 1.203208565711975}
-03/04/2022 03:24:29 - INFO - codeparrot_training - Step 11871: {'lr': 0.0004945321180341244, 'samples': 6078464, 'steps': 11871, 'loss/train': 1.2442357540130615}
-03/04/2022 03:24:29 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/04/2022 03:24:35 - INFO - codeparrot_training - Step 11872: {'lr': 0.0004945310141673816, 'samples': 6078976, 'steps': 11872, 'loss/train': 2.1183688640594482}
-03/04/2022 03:24:38 - INFO - codeparrot_training - Step 11873: {'lr': 0.0004945299101904568, 'samples': 6079488, 'steps': 11873, 'loss/train': 1.9943679571151733}
-03/04/2022 03:24:38 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/04/2022 03:24:43 - INFO - codeparrot_training - Step 11874: {'lr': 0.0004945288061033507, 'samples': 6080000, 'steps': 11874, 'loss/train': 1.4602240324020386}
-03/04/2022 03:24:46 - INFO - codeparrot_training - Step 11875: {'lr': 0.0004945277019060637, 'samples': 6080512, 'steps': 11875, 'loss/train': 2.509385347366333}
-03/04/2022 03:24:46 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/04/2022 03:24:52 - INFO - codeparrot_training - Step 11876: {'lr': 0.0004945265975985962, 'samples': 6081024, 'steps': 11876, 'loss/train': 2.2011756896972656}
-03/04/2022 03:24:55 - INFO - codeparrot_training - Step 11877: {'lr': 0.0004945254931809489, 'samples': 6081536, 'steps': 11877, 'loss/train': 1.9972912073135376}
-03/04/2022 03:24:55 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/04/2022 03:25:00 - INFO - codeparrot_training - Step 11878: {'lr': 0.000494524388653122, 'samples': 6082048, 'steps': 11878, 'loss/train': 2.1584086418151855}
-03/04/2022 03:25:03 - INFO - codeparrot_training - Step 11879: {'lr': 0.0004945232840151164, 'samples': 6082560, 'steps': 11879, 'loss/train': 2.5077009201049805}
-03/04/2022 03:25:03 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/04/2022 03:25:09 - INFO - codeparrot_training - Step 11880: {'lr': 0.0004945221792669322, 'samples': 6083072, 'steps': 11880, 'loss/train': 2.401440382003784}
-03/04/2022 03:25:12 - INFO - codeparrot_training - Step 11881: {'lr': 0.0004945210744085702, 'samples': 6083584, 'steps': 11881, 'loss/train': 1.013098120689392}
-03/04/2022 03:25:12 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 03:25:17 - INFO - codeparrot_training - Step 11882: {'lr': 0.0004945199694400308, 'samples': 6084096, 'steps': 11882, 'loss/train': 1.9623987674713135}
-03/04/2022 03:25:21 - INFO - codeparrot_training - Step 11883: {'lr': 0.0004945188643613144, 'samples': 6084608, 'steps': 11883, 'loss/train': 1.2972995042800903}
-03/04/2022 03:25:22 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 03:25:26 - INFO - codeparrot_training - Step 11884: {'lr': 0.0004945177591724216, 'samples': 6085120, 'steps': 11884, 'loss/train': 1.090961217880249}
-03/04/2022 03:25:29 - INFO - codeparrot_training - Step 11885: {'lr': 0.0004945166538733529, 'samples': 6085632, 'steps': 11885, 'loss/train': 1.2215876579284668}
-03/04/2022 03:25:30 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/04/2022 03:25:35 - INFO - codeparrot_training - Step 11886: {'lr': 0.0004945155484641087, 'samples': 6086144, 'steps': 11886, 'loss/train': 2.9218575954437256}
-03/04/2022 03:25:38 - INFO - codeparrot_training - Step 11887: {'lr': 0.0004945144429446897, 'samples': 6086656, 'steps': 11887, 'loss/train': 1.931677222251892}
-03/04/2022 03:25:39 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/04/2022 03:25:43 - INFO - codeparrot_training - Step 11888: {'lr': 0.000494513337315096, 'samples': 6087168, 'steps': 11888, 'loss/train': 1.3029483556747437}
-03/04/2022 03:25:46 - INFO - codeparrot_training - Step 11889: {'lr': 0.0004945122315753286, 'samples': 6087680, 'steps': 11889, 'loss/train': 1.9341002702713013}
-03/04/2022 03:25:47 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/04/2022 03:25:51 - INFO - codeparrot_training - Step 11890: {'lr': 0.0004945111257253877, 'samples': 6088192, 'steps': 11890, 'loss/train': 2.45115327835083}
-03/04/2022 03:25:54 - INFO - codeparrot_training - Step 11891: {'lr': 0.0004945100197652738, 'samples': 6088704, 'steps': 11891, 'loss/train': 2.2618274688720703}
-03/04/2022 03:25:55 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/04/2022 03:26:00 - INFO - codeparrot_training - Step 11892: {'lr': 0.0004945089136949876, 'samples': 6089216, 'steps': 11892, 'loss/train': 2.0957939624786377}
-03/04/2022 03:26:03 - INFO - codeparrot_training - Step 11893: {'lr': 0.0004945078075145292, 'samples': 6089728, 'steps': 11893, 'loss/train': 1.9102096557617188}
-03/04/2022 03:26:04 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 03:26:08 - INFO - codeparrot_training - Step 11894: {'lr': 0.0004945067012238996, 'samples': 6090240, 'steps': 11894, 'loss/train': 2.3287875652313232}
-03/04/2022 03:26:11 - INFO - codeparrot_training - Step 11895: {'lr': 0.000494505594823099, 'samples': 6090752, 'steps': 11895, 'loss/train': 2.1894466876983643}
-03/04/2022 03:26:12 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/04/2022 03:26:17 - INFO - codeparrot_training - Step 11896: {'lr': 0.0004945044883121279, 'samples': 6091264, 'steps': 11896, 'loss/train': 2.1138594150543213}
-03/04/2022 03:26:20 - INFO - codeparrot_training - Step 11897: {'lr': 0.0004945033816909868, 'samples': 6091776, 'steps': 11897, 'loss/train': 2.434361219406128}
-03/04/2022 03:26:21 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/04/2022 03:26:25 - INFO - codeparrot_training - Step 11898: {'lr': 0.0004945022749596764, 'samples': 6092288, 'steps': 11898, 'loss/train': 1.5553808212280273}
-03/04/2022 03:26:28 - INFO - codeparrot_training - Step 11899: {'lr': 0.000494501168118197, 'samples': 6092800, 'steps': 11899, 'loss/train': 8.913430213928223}
-03/04/2022 03:26:30 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 03:26:34 - INFO - codeparrot_training - Step 11900: {'lr': 0.0004945000611665491, 'samples': 6093312, 'steps': 11900, 'loss/train': 1.879787802696228}
-03/04/2022 03:26:37 - INFO - codeparrot_training - Step 11901: {'lr': 0.0004944989541047333, 'samples': 6093824, 'steps': 11901, 'loss/train': 2.4063010215759277}
-03/04/2022 03:26:39 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 03:26:42 - INFO - codeparrot_training - Step 11902: {'lr': 0.0004944978469327499, 'samples': 6094336, 'steps': 11902, 'loss/train': 1.859255075454712}
-03/04/2022 03:26:45 - INFO - codeparrot_training - Step 11903: {'lr': 0.0004944967396505998, 'samples': 6094848, 'steps': 11903, 'loss/train': 2.87579607963562}
-03/04/2022 03:26:47 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/04/2022 03:26:51 - INFO - codeparrot_training - Step 11904: {'lr': 0.000494495632258283, 'samples': 6095360, 'steps': 11904, 'loss/train': 2.19199275970459}
-03/04/2022 03:26:54 - INFO - codeparrot_training - Step 11905: {'lr': 0.0004944945247558004, 'samples': 6095872, 'steps': 11905, 'loss/train': 2.509045362472534}
-03/04/2022 03:26:55 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 03:26:59 - INFO - codeparrot_training - Step 11906: {'lr': 0.0004944934171431522, 'samples': 6096384, 'steps': 11906, 'loss/train': 1.6697165966033936}
-03/04/2022 03:27:02 - INFO - codeparrot_training - Step 11907: {'lr': 0.0004944923094203391, 'samples': 6096896, 'steps': 11907, 'loss/train': 2.231931209564209}
-03/04/2022 03:27:08 - INFO - codeparrot_training - Step 11908: {'lr': 0.0004944912015873616, 'samples': 6097408, 'steps': 11908, 'loss/train': 1.2279280424118042}
-03/04/2022 03:27:11 - INFO - codeparrot_training - Step 11909: {'lr': 0.0004944900936442201, 'samples': 6097920, 'steps': 11909, 'loss/train': 0.9242122173309326}
-03/04/2022 03:27:12 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/04/2022 03:27:16 - INFO - codeparrot_training - Step 11910: {'lr': 0.000494488985590915, 'samples': 6098432, 'steps': 11910, 'loss/train': 1.2993826866149902}
-03/04/2022 03:27:19 - INFO - codeparrot_training - Step 11911: {'lr': 0.0004944878774274472, 'samples': 6098944, 'steps': 11911, 'loss/train': 2.663564682006836}
-03/04/2022 03:27:21 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 03:27:24 - INFO - codeparrot_training - Step 11912: {'lr': 0.0004944867691538167, 'samples': 6099456, 'steps': 11912, 'loss/train': 2.6009700298309326}
-03/04/2022 03:27:28 - INFO - codeparrot_training - Step 11913: {'lr': 0.0004944856607700243, 'samples': 6099968, 'steps': 11913, 'loss/train': 1.9607141017913818}
-03/04/2022 03:27:29 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 03:27:33 - INFO - codeparrot_training - Step 11914: {'lr': 0.0004944845522760706, 'samples': 6100480, 'steps': 11914, 'loss/train': 1.7037131786346436}
-03/04/2022 03:27:36 - INFO - codeparrot_training - Step 11915: {'lr': 0.0004944834436719557, 'samples': 6100992, 'steps': 11915, 'loss/train': 1.4337451457977295}
-03/04/2022 03:27:38 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 03:27:41 - INFO - codeparrot_training - Step 11916: {'lr': 0.0004944823349576805, 'samples': 6101504, 'steps': 11916, 'loss/train': 1.8570888042449951}
-03/04/2022 03:27:45 - INFO - codeparrot_training - Step 11917: {'lr': 0.0004944812261332452, 'samples': 6102016, 'steps': 11917, 'loss/train': 1.8511340618133545}
-03/04/2022 03:27:47 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/04/2022 03:27:50 - INFO - codeparrot_training - Step 11918: {'lr': 0.0004944801171986505, 'samples': 6102528, 'steps': 11918, 'loss/train': 1.6404627561569214}
-03/04/2022 03:27:53 - INFO - codeparrot_training - Step 11919: {'lr': 0.0004944790081538969, 'samples': 6103040, 'steps': 11919, 'loss/train': 1.8909838199615479}
-03/04/2022 03:27:55 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 03:27:58 - INFO - codeparrot_training - Step 11920: {'lr': 0.0004944778989989847, 'samples': 6103552, 'steps': 11920, 'loss/train': 2.502392292022705}
-03/04/2022 03:28:02 - INFO - codeparrot_training - Step 11921: {'lr': 0.0004944767897339146, 'samples': 6104064, 'steps': 11921, 'loss/train': 1.06792414188385}
-03/04/2022 03:28:04 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/04/2022 03:28:07 - INFO - codeparrot_training - Step 11922: {'lr': 0.000494475680358687, 'samples': 6104576, 'steps': 11922, 'loss/train': 2.028285503387451}
-03/04/2022 03:28:10 - INFO - codeparrot_training - Step 11923: {'lr': 0.0004944745708733025, 'samples': 6105088, 'steps': 11923, 'loss/train': 2.6781973838806152}
-03/04/2022 03:28:12 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/04/2022 03:28:15 - INFO - codeparrot_training - Step 11924: {'lr': 0.0004944734612777615, 'samples': 6105600, 'steps': 11924, 'loss/train': 2.1399459838867188}
-03/04/2022 03:28:18 - INFO - codeparrot_training - Step 11925: {'lr': 0.0004944723515720645, 'samples': 6106112, 'steps': 11925, 'loss/train': 2.2076635360717773}
-03/04/2022 03:28:20 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 03:28:24 - INFO - codeparrot_training - Step 11926: {'lr': 0.000494471241756212, 'samples': 6106624, 'steps': 11926, 'loss/train': 2.124689817428589}
-03/04/2022 03:28:27 - INFO - codeparrot_training - Step 11927: {'lr': 0.0004944701318302046, 'samples': 6107136, 'steps': 11927, 'loss/train': 1.677828311920166}
-03/04/2022 03:28:29 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/04/2022 03:28:32 - INFO - codeparrot_training - Step 11928: {'lr': 0.0004944690217940427, 'samples': 6107648, 'steps': 11928, 'loss/train': 1.339243769645691}
-03/04/2022 03:28:35 - INFO - codeparrot_training - Step 11929: {'lr': 0.0004944679116477269, 'samples': 6108160, 'steps': 11929, 'loss/train': 2.066533327102661}
-03/04/2022 03:28:40 - INFO - codeparrot_training - Step 11930: {'lr': 0.0004944668013912575, 'samples': 6108672, 'steps': 11930, 'loss/train': 1.319860816001892}
-03/04/2022 03:28:44 - INFO - codeparrot_training - Step 11931: {'lr': 0.0004944656910246352, 'samples': 6109184, 'steps': 11931, 'loss/train': 1.5740594863891602}
-03/04/2022 03:28:45 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/04/2022 03:28:49 - INFO - codeparrot_training - Step 11932: {'lr': 0.0004944645805478605, 'samples': 6109696, 'steps': 11932, 'loss/train': 2.8329527378082275}
-03/04/2022 03:28:52 - INFO - codeparrot_training - Step 11933: {'lr': 0.0004944634699609338, 'samples': 6110208, 'steps': 11933, 'loss/train': 2.242119550704956}
-03/04/2022 03:28:54 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 03:28:58 - INFO - codeparrot_training - Step 11934: {'lr': 0.0004944623592638555, 'samples': 6110720, 'steps': 11934, 'loss/train': 0.8278563022613525}
-03/04/2022 03:29:01 - INFO - codeparrot_training - Step 11935: {'lr': 0.0004944612484566263, 'samples': 6111232, 'steps': 11935, 'loss/train': 2.124986410140991}
-03/04/2022 03:29:03 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/04/2022 03:29:06 - INFO - codeparrot_training - Step 11936: {'lr': 0.0004944601375392467, 'samples': 6111744, 'steps': 11936, 'loss/train': 0.28044095635414124}
-03/04/2022 03:29:09 - INFO - codeparrot_training - Step 11937: {'lr': 0.000494459026511717, 'samples': 6112256, 'steps': 11937, 'loss/train': 0.6552304029464722}
-03/04/2022 03:29:11 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/04/2022 03:29:14 - INFO - codeparrot_training - Step 11938: {'lr': 0.000494457915374038, 'samples': 6112768, 'steps': 11938, 'loss/train': 2.2140820026397705}
-03/04/2022 03:29:18 - INFO - codeparrot_training - Step 11939: {'lr': 0.00049445680412621, 'samples': 6113280, 'steps': 11939, 'loss/train': 2.468625068664551}
-03/04/2022 03:29:19 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/04/2022 03:29:23 - INFO - codeparrot_training - Step 11940: {'lr': 0.0004944556927682335, 'samples': 6113792, 'steps': 11940, 'loss/train': 1.285072684288025}
-03/04/2022 03:29:26 - INFO - codeparrot_training - Step 11941: {'lr': 0.000494454581300109, 'samples': 6114304, 'steps': 11941, 'loss/train': 1.5860658884048462}
-03/04/2022 03:29:28 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/04/2022 03:29:31 - INFO - codeparrot_training - Step 11942: {'lr': 0.0004944534697218371, 'samples': 6114816, 'steps': 11942, 'loss/train': 2.0108180046081543}
-03/04/2022 03:29:35 - INFO - codeparrot_training - Step 11943: {'lr': 0.0004944523580334183, 'samples': 6115328, 'steps': 11943, 'loss/train': 1.8567811250686646}
-03/04/2022 03:29:36 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 03:29:40 - INFO - codeparrot_training - Step 11944: {'lr': 0.0004944512462348528, 'samples': 6115840, 'steps': 11944, 'loss/train': 1.5801866054534912}
-03/04/2022 03:29:43 - INFO - codeparrot_training - Step 11945: {'lr': 0.0004944501343261416, 'samples': 6116352, 'steps': 11945, 'loss/train': 1.873104214668274}
-03/04/2022 03:29:44 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 03:29:48 - INFO - codeparrot_training - Step 11946: {'lr': 0.0004944490223072848, 'samples': 6116864, 'steps': 11946, 'loss/train': 2.223787307739258}
-03/04/2022 03:29:51 - INFO - codeparrot_training - Step 11947: {'lr': 0.0004944479101782831, 'samples': 6117376, 'steps': 11947, 'loss/train': 2.0818262100219727}
-03/04/2022 03:29:53 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/04/2022 03:29:57 - INFO - codeparrot_training - Step 11948: {'lr': 0.0004944467979391369, 'samples': 6117888, 'steps': 11948, 'loss/train': 1.5047500133514404}
-03/04/2022 03:30:00 - INFO - codeparrot_training - Step 11949: {'lr': 0.0004944456855898469, 'samples': 6118400, 'steps': 11949, 'loss/train': 2.0856308937072754}
-03/04/2022 03:30:02 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 03:30:05 - INFO - codeparrot_training - Step 11950: {'lr': 0.0004944445731304133, 'samples': 6118912, 'steps': 11950, 'loss/train': 3.0710370540618896}
-03/04/2022 03:30:08 - INFO - codeparrot_training - Step 11951: {'lr': 0.0004944434605608367, 'samples': 6119424, 'steps': 11951, 'loss/train': 2.004324197769165}
-03/04/2022 03:30:11 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 03:30:14 - INFO - codeparrot_training - Step 11952: {'lr': 0.0004944423478811177, 'samples': 6119936, 'steps': 11952, 'loss/train': 1.5884199142456055}
-03/04/2022 03:30:17 - INFO - codeparrot_training - Step 11953: {'lr': 0.0004944412350912567, 'samples': 6120448, 'steps': 11953, 'loss/train': 3.4422130584716797}
-03/04/2022 03:30:20 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/04/2022 03:30:22 - INFO - codeparrot_training - Step 11954: {'lr': 0.0004944401221912544, 'samples': 6120960, 'steps': 11954, 'loss/train': 1.6557979583740234}
-03/04/2022 03:30:25 - INFO - codeparrot_training - Step 11955: {'lr': 0.0004944390091811111, 'samples': 6121472, 'steps': 11955, 'loss/train': 1.8109768629074097}
-03/04/2022 03:30:28 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/04/2022 03:30:31 - INFO - codeparrot_training - Step 11956: {'lr': 0.0004944378960608272, 'samples': 6121984, 'steps': 11956, 'loss/train': 2.447239875793457}
-03/04/2022 03:30:34 - INFO - codeparrot_training - Step 11957: {'lr': 0.0004944367828304035, 'samples': 6122496, 'steps': 11957, 'loss/train': 1.82314133644104}
-03/04/2022 03:30:36 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/04/2022 03:30:39 - INFO - codeparrot_training - Step 11958: {'lr': 0.0004944356694898404, 'samples': 6123008, 'steps': 11958, 'loss/train': 3.0943737030029297}
-03/04/2022 03:30:43 - INFO - codeparrot_training - Step 11959: {'lr': 0.0004944345560391382, 'samples': 6123520, 'steps': 11959, 'loss/train': 2.3014090061187744}
-03/04/2022 03:30:46 - INFO - codeparrot_training - Step 11960: {'lr': 0.0004944334424782977, 'samples': 6124032, 'steps': 11960, 'loss/train': 1.5287530422210693}
-03/04/2022 03:30:47 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 03:30:51 - INFO - codeparrot_training - Step 11961: {'lr': 0.0004944323288073192, 'samples': 6124544, 'steps': 11961, 'loss/train': 2.891096353530884}
-03/04/2022 03:30:54 - INFO - codeparrot_training - Step 11962: {'lr': 0.0004944312150262033, 'samples': 6125056, 'steps': 11962, 'loss/train': 1.8728413581848145}
-03/04/2022 03:30:55 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/04/2022 03:30:59 - INFO - codeparrot_training - Step 11963: {'lr': 0.0004944301011349505, 'samples': 6125568, 'steps': 11963, 'loss/train': 1.9108372926712036}
-03/04/2022 03:31:03 - INFO - codeparrot_training - Step 11964: {'lr': 0.0004944289871335612, 'samples': 6126080, 'steps': 11964, 'loss/train': 2.813878059387207}
-03/04/2022 03:31:03 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/04/2022 03:31:08 - INFO - codeparrot_training - Step 11965: {'lr': 0.0004944278730220359, 'samples': 6126592, 'steps': 11965, 'loss/train': 1.9451085329055786}
-03/04/2022 03:31:11 - INFO - codeparrot_training - Step 11966: {'lr': 0.0004944267588003754, 'samples': 6127104, 'steps': 11966, 'loss/train': 0.856791079044342}
-03/04/2022 03:31:11 - INFO - codeparrot_training - Skipping example with length 86 (seq_length=1024)
-03/04/2022 03:31:16 - INFO - codeparrot_training - Step 11967: {'lr': 0.0004944256444685798, 'samples': 6127616, 'steps': 11967, 'loss/train': 3.046508312225342}
-03/04/2022 03:31:19 - INFO - codeparrot_training - Step 11968: {'lr': 0.0004944245300266498, 'samples': 6128128, 'steps': 11968, 'loss/train': 2.166978359222412}
-03/04/2022 03:31:20 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 03:31:25 - INFO - codeparrot_training - Step 11969: {'lr': 0.0004944234154745859, 'samples': 6128640, 'steps': 11969, 'loss/train': 1.6930383443832397}
-03/04/2022 03:31:28 - INFO - codeparrot_training - Step 11970: {'lr': 0.0004944223008123886, 'samples': 6129152, 'steps': 11970, 'loss/train': 2.4436867237091064}
-03/04/2022 03:31:28 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/04/2022 03:31:33 - INFO - codeparrot_training - Step 11971: {'lr': 0.0004944211860400582, 'samples': 6129664, 'steps': 11971, 'loss/train': 1.510438323020935}
-03/04/2022 03:31:36 - INFO - codeparrot_training - Step 11972: {'lr': 0.0004944200711575956, 'samples': 6130176, 'steps': 11972, 'loss/train': 2.380444288253784}
-03/04/2022 03:31:36 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/04/2022 03:31:41 - INFO - codeparrot_training - Step 11973: {'lr': 0.0004944189561650011, 'samples': 6130688, 'steps': 11973, 'loss/train': 1.843109130859375}
-03/04/2022 03:31:45 - INFO - codeparrot_training - Step 11974: {'lr': 0.0004944178410622751, 'samples': 6131200, 'steps': 11974, 'loss/train': 2.125847339630127}
-03/04/2022 03:31:45 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 03:31:50 - INFO - codeparrot_training - Step 11975: {'lr': 0.0004944167258494181, 'samples': 6131712, 'steps': 11975, 'loss/train': 1.6390478610992432}
-03/04/2022 03:31:53 - INFO - codeparrot_training - Step 11976: {'lr': 0.0004944156105264308, 'samples': 6132224, 'steps': 11976, 'loss/train': 2.4061758518218994}
-03/04/2022 03:31:53 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/04/2022 03:31:58 - INFO - codeparrot_training - Step 11977: {'lr': 0.0004944144950933137, 'samples': 6132736, 'steps': 11977, 'loss/train': 1.6477320194244385}
-03/04/2022 03:32:01 - INFO - codeparrot_training - Step 11978: {'lr': 0.000494413379550067, 'samples': 6133248, 'steps': 11978, 'loss/train': 2.3641443252563477}
-03/04/2022 03:32:01 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 03:32:07 - INFO - codeparrot_training - Step 11979: {'lr': 0.0004944122638966916, 'samples': 6133760, 'steps': 11979, 'loss/train': 1.8153048753738403}
-03/04/2022 03:32:10 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/04/2022 03:32:12 - INFO - codeparrot_training - Step 11980: {'lr': 0.0004944111481331876, 'samples': 6134272, 'steps': 11980, 'loss/train': 2.3443028926849365}
-03/04/2022 03:32:15 - INFO - codeparrot_training - Step 11981: {'lr': 0.0004944100322595558, 'samples': 6134784, 'steps': 11981, 'loss/train': 2.781273603439331}
-03/04/2022 03:32:18 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/04/2022 03:32:20 - INFO - codeparrot_training - Step 11982: {'lr': 0.0004944089162757968, 'samples': 6135296, 'steps': 11982, 'loss/train': 1.6650642156600952}
-03/04/2022 03:32:24 - INFO - codeparrot_training - Step 11983: {'lr': 0.0004944078001819106, 'samples': 6135808, 'steps': 11983, 'loss/train': 2.2784039974212646}
-03/04/2022 03:32:26 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 03:32:29 - INFO - codeparrot_training - Step 11984: {'lr': 0.0004944066839778983, 'samples': 6136320, 'steps': 11984, 'loss/train': 1.9370466470718384}
-03/04/2022 03:32:32 - INFO - codeparrot_training - Step 11985: {'lr': 0.0004944055676637599, 'samples': 6136832, 'steps': 11985, 'loss/train': 2.505388021469116}
-03/04/2022 03:32:34 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/04/2022 03:32:37 - INFO - codeparrot_training - Step 11986: {'lr': 0.0004944044512394962, 'samples': 6137344, 'steps': 11986, 'loss/train': 1.9311918020248413}
-03/04/2022 03:32:40 - INFO - codeparrot_training - Step 11987: {'lr': 0.0004944033347051076, 'samples': 6137856, 'steps': 11987, 'loss/train': 1.9244431257247925}
-03/04/2022 03:32:42 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 03:32:46 - INFO - codeparrot_training - Step 11988: {'lr': 0.0004944022180605947, 'samples': 6138368, 'steps': 11988, 'loss/train': 1.8630146980285645}
-03/04/2022 03:32:49 - INFO - codeparrot_training - Step 11989: {'lr': 0.0004944011013059579, 'samples': 6138880, 'steps': 11989, 'loss/train': 2.123609781265259}
-03/04/2022 03:32:51 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 03:32:54 - INFO - codeparrot_training - Step 11990: {'lr': 0.0004943999844411977, 'samples': 6139392, 'steps': 11990, 'loss/train': 2.084296464920044}
-03/04/2022 03:32:57 - INFO - codeparrot_training - Step 11991: {'lr': 0.0004943988674663147, 'samples': 6139904, 'steps': 11991, 'loss/train': 1.8142518997192383}
-03/04/2022 03:32:59 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/04/2022 03:33:02 - INFO - codeparrot_training - Step 11992: {'lr': 0.0004943977503813092, 'samples': 6140416, 'steps': 11992, 'loss/train': 2.143765687942505}
-03/04/2022 03:33:06 - INFO - codeparrot_training - Step 11993: {'lr': 0.000494396633186182, 'samples': 6140928, 'steps': 11993, 'loss/train': 2.740461587905884}
-03/04/2022 03:33:07 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 03:33:11 - INFO - codeparrot_training - Step 11994: {'lr': 0.0004943955158809334, 'samples': 6141440, 'steps': 11994, 'loss/train': 2.406925916671753}
-03/04/2022 03:33:14 - INFO - codeparrot_training - Step 11995: {'lr': 0.0004943943984655639, 'samples': 6141952, 'steps': 11995, 'loss/train': 1.383545160293579}
-03/04/2022 03:33:15 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 03:33:19 - INFO - codeparrot_training - Step 11996: {'lr': 0.0004943932809400741, 'samples': 6142464, 'steps': 11996, 'loss/train': 0.2069779485464096}
-03/04/2022 03:33:22 - INFO - codeparrot_training - Step 11997: {'lr': 0.0004943921633044644, 'samples': 6142976, 'steps': 11997, 'loss/train': 1.7499136924743652}
-03/04/2022 03:33:24 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 03:33:28 - INFO - codeparrot_training - Step 11998: {'lr': 0.0004943910455587354, 'samples': 6143488, 'steps': 11998, 'loss/train': 2.267611265182495}
-03/04/2022 03:33:31 - INFO - codeparrot_training - Step 11999: {'lr': 0.0004943899277028877, 'samples': 6144000, 'steps': 11999, 'loss/train': 1.5085662603378296}
-03/04/2022 03:33:32 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/04/2022 03:33:36 - INFO - codeparrot_training - Step 12000: {'lr': 0.0004943888097369216, 'samples': 6144512, 'steps': 12000, 'loss/train': 2.243253469467163}
-03/04/2022 03:33:39 - INFO - codeparrot_training - Step 12001: {'lr': 0.0004943876916608375, 'samples': 6145024, 'steps': 12001, 'loss/train': 2.4054319858551025}
-03/04/2022 03:33:41 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/04/2022 03:33:44 - INFO - codeparrot_training - Step 12002: {'lr': 0.0004943865734746364, 'samples': 6145536, 'steps': 12002, 'loss/train': 0.9181418418884277}
-03/04/2022 03:33:48 - INFO - codeparrot_training - Step 12003: {'lr': 0.0004943854551783182, 'samples': 6146048, 'steps': 12003, 'loss/train': 2.3391261100769043}
-03/04/2022 03:33:49 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/04/2022 03:33:53 - INFO - codeparrot_training - Step 12004: {'lr': 0.0004943843367718838, 'samples': 6146560, 'steps': 12004, 'loss/train': 2.395664691925049}
-03/04/2022 03:33:56 - INFO - codeparrot_training - Step 12005: {'lr': 0.0004943832182553336, 'samples': 6147072, 'steps': 12005, 'loss/train': 2.171281099319458}
-03/04/2022 03:33:58 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/04/2022 03:34:02 - INFO - codeparrot_training - Step 12006: {'lr': 0.000494382099628668, 'samples': 6147584, 'steps': 12006, 'loss/train': 1.9690418243408203}
-03/04/2022 03:34:05 - INFO - codeparrot_training - Step 12007: {'lr': 0.0004943809808918877, 'samples': 6148096, 'steps': 12007, 'loss/train': 1.8443026542663574}
-03/04/2022 03:34:06 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 03:34:10 - INFO - codeparrot_training - Step 12008: {'lr': 0.000494379862044993, 'samples': 6148608, 'steps': 12008, 'loss/train': 1.6588070392608643}
-03/04/2022 03:34:13 - INFO - codeparrot_training - Step 12009: {'lr': 0.0004943787430879846, 'samples': 6149120, 'steps': 12009, 'loss/train': 1.7586036920547485}
-03/04/2022 03:34:15 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/04/2022 03:34:18 - INFO - codeparrot_training - Step 12010: {'lr': 0.0004943776240208628, 'samples': 6149632, 'steps': 12010, 'loss/train': 2.329418420791626}
-03/04/2022 03:34:22 - INFO - codeparrot_training - Step 12011: {'lr': 0.0004943765048436283, 'samples': 6150144, 'steps': 12011, 'loss/train': 2.2322394847869873}
-03/04/2022 03:34:23 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 03:34:27 - INFO - codeparrot_training - Step 12012: {'lr': 0.0004943753855562815, 'samples': 6150656, 'steps': 12012, 'loss/train': 1.9393218755722046}
-03/04/2022 03:34:30 - INFO - codeparrot_training - Step 12013: {'lr': 0.000494374266158823, 'samples': 6151168, 'steps': 12013, 'loss/train': 1.2713837623596191}
-03/04/2022 03:34:32 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/04/2022 03:34:35 - INFO - codeparrot_training - Step 12014: {'lr': 0.0004943731466512531, 'samples': 6151680, 'steps': 12014, 'loss/train': 2.2755227088928223}
-03/04/2022 03:34:39 - INFO - codeparrot_training - Step 12015: {'lr': 0.0004943720270335724, 'samples': 6152192, 'steps': 12015, 'loss/train': 2.4260306358337402}
-03/04/2022 03:34:40 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 03:34:44 - INFO - codeparrot_training - Step 12016: {'lr': 0.0004943709073057816, 'samples': 6152704, 'steps': 12016, 'loss/train': 1.6642426252365112}
-03/04/2022 03:34:47 - INFO - codeparrot_training - Step 12017: {'lr': 0.000494369787467881, 'samples': 6153216, 'steps': 12017, 'loss/train': 2.0409631729125977}
-03/04/2022 03:34:49 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/04/2022 03:34:52 - INFO - codeparrot_training - Step 12018: {'lr': 0.000494368667519871, 'samples': 6153728, 'steps': 12018, 'loss/train': 1.381190299987793}
-03/04/2022 03:34:55 - INFO - codeparrot_training - Step 12019: {'lr': 0.0004943675474617524, 'samples': 6154240, 'steps': 12019, 'loss/train': 2.7217915058135986}
-03/04/2022 03:34:57 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 03:35:01 - INFO - codeparrot_training - Step 12020: {'lr': 0.0004943664272935255, 'samples': 6154752, 'steps': 12020, 'loss/train': 2.499005079269409}
-03/04/2022 03:35:04 - INFO - codeparrot_training - Step 12021: {'lr': 0.0004943653070151909, 'samples': 6155264, 'steps': 12021, 'loss/train': 3.5025124549865723}
-03/04/2022 03:35:07 - INFO - codeparrot_training - Step 12022: {'lr': 0.000494364186626749, 'samples': 6155776, 'steps': 12022, 'loss/train': 1.8158777952194214}
-03/04/2022 03:35:08 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 03:35:13 - INFO - codeparrot_training - Step 12023: {'lr': 0.0004943630661282004, 'samples': 6156288, 'steps': 12023, 'loss/train': 2.4539570808410645}
-03/04/2022 03:35:16 - INFO - codeparrot_training - Step 12024: {'lr': 0.0004943619455195456, 'samples': 6156800, 'steps': 12024, 'loss/train': 1.7781996726989746}
-03/04/2022 03:35:17 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/04/2022 03:35:21 - INFO - codeparrot_training - Step 12025: {'lr': 0.000494360824800785, 'samples': 6157312, 'steps': 12025, 'loss/train': 2.3477706909179688}
-03/04/2022 03:35:24 - INFO - codeparrot_training - Step 12026: {'lr': 0.0004943597039719192, 'samples': 6157824, 'steps': 12026, 'loss/train': 2.1413660049438477}
-03/04/2022 03:35:25 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/04/2022 03:35:30 - INFO - codeparrot_training - Step 12027: {'lr': 0.0004943585830329487, 'samples': 6158336, 'steps': 12027, 'loss/train': 2.1783554553985596}
-03/04/2022 03:35:33 - INFO - codeparrot_training - Step 12028: {'lr': 0.0004943574619838741, 'samples': 6158848, 'steps': 12028, 'loss/train': 1.5946907997131348}
-03/04/2022 03:35:33 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 03:35:38 - INFO - codeparrot_training - Step 12029: {'lr': 0.0004943563408246957, 'samples': 6159360, 'steps': 12029, 'loss/train': 1.910249948501587}
-03/04/2022 03:35:41 - INFO - codeparrot_training - Step 12030: {'lr': 0.000494355219555414, 'samples': 6159872, 'steps': 12030, 'loss/train': 1.6205307245254517}
-03/04/2022 03:35:41 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/04/2022 03:35:46 - INFO - codeparrot_training - Step 12031: {'lr': 0.0004943540981760298, 'samples': 6160384, 'steps': 12031, 'loss/train': 4.984691619873047}
-03/04/2022 03:35:50 - INFO - codeparrot_training - Step 12032: {'lr': 0.0004943529766865434, 'samples': 6160896, 'steps': 12032, 'loss/train': 1.7213685512542725}
-03/04/2022 03:35:50 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/04/2022 03:35:55 - INFO - codeparrot_training - Step 12033: {'lr': 0.0004943518550869552, 'samples': 6161408, 'steps': 12033, 'loss/train': 1.7279452085494995}
-03/04/2022 03:35:58 - INFO - codeparrot_training - Step 12034: {'lr': 0.0004943507333772659, 'samples': 6161920, 'steps': 12034, 'loss/train': 2.1987173557281494}
-03/04/2022 03:36:00 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/04/2022 03:36:03 - INFO - codeparrot_training - Step 12035: {'lr': 0.0004943496115574758, 'samples': 6162432, 'steps': 12035, 'loss/train': 0.8294306993484497}
-03/04/2022 03:36:07 - INFO - codeparrot_training - Step 12036: {'lr': 0.0004943484896275857, 'samples': 6162944, 'steps': 12036, 'loss/train': 2.0815250873565674}
-03/04/2022 03:36:08 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 03:36:12 - INFO - codeparrot_training - Step 12037: {'lr': 0.0004943473675875959, 'samples': 6163456, 'steps': 12037, 'loss/train': 0.9434368014335632}
-03/04/2022 03:36:15 - INFO - codeparrot_training - Step 12038: {'lr': 0.0004943462454375069, 'samples': 6163968, 'steps': 12038, 'loss/train': 2.397144317626953}
-03/04/2022 03:36:16 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/04/2022 03:36:21 - INFO - codeparrot_training - Step 12039: {'lr': 0.0004943451231773192, 'samples': 6164480, 'steps': 12039, 'loss/train': 2.1818652153015137}
-03/04/2022 03:36:24 - INFO - codeparrot_training - Step 12040: {'lr': 0.0004943440008070336, 'samples': 6164992, 'steps': 12040, 'loss/train': 1.518899917602539}
-03/04/2022 03:36:26 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 03:36:29 - INFO - codeparrot_training - Step 12041: {'lr': 0.0004943428783266502, 'samples': 6165504, 'steps': 12041, 'loss/train': 1.9233722686767578}
-03/04/2022 03:36:32 - INFO - codeparrot_training - Step 12042: {'lr': 0.0004943417557361696, 'samples': 6166016, 'steps': 12042, 'loss/train': 2.597496271133423}
-03/04/2022 03:36:35 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/04/2022 03:36:37 - INFO - codeparrot_training - Step 12043: {'lr': 0.0004943406330355925, 'samples': 6166528, 'steps': 12043, 'loss/train': 1.3040406703948975}
-03/04/2022 03:36:41 - INFO - codeparrot_training - Step 12044: {'lr': 0.0004943395102249192, 'samples': 6167040, 'steps': 12044, 'loss/train': 2.345353126525879}
-03/04/2022 03:36:43 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 03:36:46 - INFO - codeparrot_training - Step 12045: {'lr': 0.0004943383873041503, 'samples': 6167552, 'steps': 12045, 'loss/train': 1.7922472953796387}
-03/04/2022 03:36:49 - INFO - codeparrot_training - Step 12046: {'lr': 0.0004943372642732864, 'samples': 6168064, 'steps': 12046, 'loss/train': 1.8749282360076904}
-03/04/2022 03:36:51 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/04/2022 03:36:54 - INFO - codeparrot_training - Step 12047: {'lr': 0.0004943361411323277, 'samples': 6168576, 'steps': 12047, 'loss/train': 1.6905783414840698}
-03/04/2022 03:36:57 - INFO - codeparrot_training - Step 12048: {'lr': 0.0004943350178812751, 'samples': 6169088, 'steps': 12048, 'loss/train': 1.8724652528762817}
-03/04/2022 03:37:00 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/04/2022 03:37:03 - INFO - codeparrot_training - Step 12049: {'lr': 0.0004943338945201288, 'samples': 6169600, 'steps': 12049, 'loss/train': 1.953090786933899}
-03/04/2022 03:37:06 - INFO - codeparrot_training - Step 12050: {'lr': 0.0004943327710488894, 'samples': 6170112, 'steps': 12050, 'loss/train': 0.9785449504852295}
-03/04/2022 03:37:08 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/04/2022 03:37:11 - INFO - codeparrot_training - Step 12051: {'lr': 0.0004943316474675575, 'samples': 6170624, 'steps': 12051, 'loss/train': 2.3269553184509277}
-03/04/2022 03:37:14 - INFO - codeparrot_training - Step 12052: {'lr': 0.0004943305237761335, 'samples': 6171136, 'steps': 12052, 'loss/train': 2.296334981918335}
-03/04/2022 03:37:16 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 03:37:20 - INFO - codeparrot_training - Step 12053: {'lr': 0.0004943293999746179, 'samples': 6171648, 'steps': 12053, 'loss/train': 1.7404853105545044}
-03/04/2022 03:37:23 - INFO - codeparrot_training - Step 12054: {'lr': 0.0004943282760630114, 'samples': 6172160, 'steps': 12054, 'loss/train': 2.072338342666626}
-03/04/2022 03:37:25 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/04/2022 03:37:28 - INFO - codeparrot_training - Step 12055: {'lr': 0.0004943271520413141, 'samples': 6172672, 'steps': 12055, 'loss/train': 2.2130722999572754}
-03/04/2022 03:37:31 - INFO - codeparrot_training - Step 12056: {'lr': 0.0004943260279095269, 'samples': 6173184, 'steps': 12056, 'loss/train': 1.9371775388717651}
-03/04/2022 03:37:33 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/04/2022 03:37:37 - INFO - codeparrot_training - Step 12057: {'lr': 0.0004943249036676501, 'samples': 6173696, 'steps': 12057, 'loss/train': 1.6613370180130005}
-03/04/2022 03:37:40 - INFO - codeparrot_training - Step 12058: {'lr': 0.0004943237793156844, 'samples': 6174208, 'steps': 12058, 'loss/train': 2.2272322177886963}
-03/04/2022 03:37:42 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/04/2022 03:37:45 - INFO - codeparrot_training - Step 12059: {'lr': 0.00049432265485363, 'samples': 6174720, 'steps': 12059, 'loss/train': 2.0762453079223633}
-03/04/2022 03:37:48 - INFO - codeparrot_training - Step 12060: {'lr': 0.0004943215302814877, 'samples': 6175232, 'steps': 12060, 'loss/train': 0.972357451915741}
-03/04/2022 03:37:50 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/04/2022 03:37:54 - INFO - codeparrot_training - Step 12061: {'lr': 0.0004943204055992579, 'samples': 6175744, 'steps': 12061, 'loss/train': 2.0728800296783447}
-03/04/2022 03:37:57 - INFO - codeparrot_training - Step 12062: {'lr': 0.0004943192808069411, 'samples': 6176256, 'steps': 12062, 'loss/train': 2.0355224609375}
-03/04/2022 03:37:59 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/04/2022 03:38:02 - INFO - codeparrot_training - Step 12063: {'lr': 0.0004943181559045378, 'samples': 6176768, 'steps': 12063, 'loss/train': 1.1221709251403809}
-03/04/2022 03:38:05 - INFO - codeparrot_training - Step 12064: {'lr': 0.0004943170308920483, 'samples': 6177280, 'steps': 12064, 'loss/train': 0.8936078548431396}
-03/04/2022 03:38:07 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/04/2022 03:38:11 - INFO - codeparrot_training - Step 12065: {'lr': 0.0004943159057694736, 'samples': 6177792, 'steps': 12065, 'loss/train': 1.691752552986145}
-03/04/2022 03:38:14 - INFO - codeparrot_training - Step 12066: {'lr': 0.0004943147805368138, 'samples': 6178304, 'steps': 12066, 'loss/train': 1.1367202997207642}
-03/04/2022 03:38:16 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 03:38:19 - INFO - codeparrot_training - Step 12067: {'lr': 0.0004943136551940695, 'samples': 6178816, 'steps': 12067, 'loss/train': 2.3155195713043213}
-03/04/2022 03:38:22 - INFO - codeparrot_training - Step 12068: {'lr': 0.0004943125297412413, 'samples': 6179328, 'steps': 12068, 'loss/train': 1.4536081552505493}
-03/04/2022 03:38:24 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/04/2022 03:38:27 - INFO - codeparrot_training - Step 12069: {'lr': 0.0004943114041783296, 'samples': 6179840, 'steps': 12069, 'loss/train': 1.7667850255966187}
-03/04/2022 03:38:31 - INFO - codeparrot_training - Step 12070: {'lr': 0.000494310278505335, 'samples': 6180352, 'steps': 12070, 'loss/train': 2.1298701763153076}
-03/04/2022 03:38:32 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/04/2022 03:38:36 - INFO - codeparrot_training - Step 12071: {'lr': 0.0004943091527222579, 'samples': 6180864, 'steps': 12071, 'loss/train': 1.1757603883743286}
-03/04/2022 03:38:39 - INFO - codeparrot_training - Step 12072: {'lr': 0.0004943080268290989, 'samples': 6181376, 'steps': 12072, 'loss/train': 1.6603306531906128}
-03/04/2022 03:38:41 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 03:38:44 - INFO - codeparrot_training - Step 12073: {'lr': 0.0004943069008258584, 'samples': 6181888, 'steps': 12073, 'loss/train': 2.355236053466797}
-03/04/2022 03:38:48 - INFO - codeparrot_training - Step 12074: {'lr': 0.0004943057747125371, 'samples': 6182400, 'steps': 12074, 'loss/train': 2.1466104984283447}
-03/04/2022 03:38:50 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/04/2022 03:38:53 - INFO - codeparrot_training - Step 12075: {'lr': 0.0004943046484891352, 'samples': 6182912, 'steps': 12075, 'loss/train': 1.8228473663330078}
-03/04/2022 03:38:56 - INFO - codeparrot_training - Step 12076: {'lr': 0.0004943035221556536, 'samples': 6183424, 'steps': 12076, 'loss/train': 1.6619998216629028}
-03/04/2022 03:38:59 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 03:39:01 - INFO - codeparrot_training - Step 12077: {'lr': 0.0004943023957120926, 'samples': 6183936, 'steps': 12077, 'loss/train': 1.6451656818389893}
-03/04/2022 03:39:04 - INFO - codeparrot_training - Step 12078: {'lr': 0.0004943012691584526, 'samples': 6184448, 'steps': 12078, 'loss/train': 1.9576202630996704}
-03/04/2022 03:39:07 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 03:39:10 - INFO - codeparrot_training - Step 12079: {'lr': 0.0004943001424947343, 'samples': 6184960, 'steps': 12079, 'loss/train': 1.401702880859375}
-03/04/2022 03:39:13 - INFO - codeparrot_training - Step 12080: {'lr': 0.000494299015720938, 'samples': 6185472, 'steps': 12080, 'loss/train': 0.8594290018081665}
-03/04/2022 03:39:15 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/04/2022 03:39:18 - INFO - codeparrot_training - Step 12081: {'lr': 0.0004942978888370645, 'samples': 6185984, 'steps': 12081, 'loss/train': 2.1032092571258545}
-03/04/2022 03:39:21 - INFO - codeparrot_training - Step 12082: {'lr': 0.000494296761843114, 'samples': 6186496, 'steps': 12082, 'loss/train': 1.6682459115982056}
-03/04/2022 03:39:23 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/04/2022 03:39:27 - INFO - codeparrot_training - Step 12083: {'lr': 0.0004942956347390872, 'samples': 6187008, 'steps': 12083, 'loss/train': 1.3562787771224976}
-03/04/2022 03:39:30 - INFO - codeparrot_training - Step 12084: {'lr': 0.0004942945075249845, 'samples': 6187520, 'steps': 12084, 'loss/train': 2.4643077850341797}
-03/04/2022 03:39:32 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/04/2022 03:39:35 - INFO - codeparrot_training - Step 12085: {'lr': 0.0004942933802008066, 'samples': 6188032, 'steps': 12085, 'loss/train': 2.435213565826416}
-03/04/2022 03:39:38 - INFO - codeparrot_training - Step 12086: {'lr': 0.0004942922527665538, 'samples': 6188544, 'steps': 12086, 'loss/train': 1.9849286079406738}
-03/04/2022 03:39:40 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 03:39:44 - INFO - codeparrot_training - Step 12087: {'lr': 0.0004942911252222267, 'samples': 6189056, 'steps': 12087, 'loss/train': 1.9537636041641235}
-03/04/2022 03:39:47 - INFO - codeparrot_training - Step 12088: {'lr': 0.0004942899975678257, 'samples': 6189568, 'steps': 12088, 'loss/train': 2.4453907012939453}
-03/04/2022 03:39:50 - INFO - codeparrot_training - Step 12089: {'lr': 0.0004942888698033515, 'samples': 6190080, 'steps': 12089, 'loss/train': 1.4449876546859741}
-03/04/2022 03:39:52 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 03:39:56 - INFO - codeparrot_training - Step 12090: {'lr': 0.0004942877419288045, 'samples': 6190592, 'steps': 12090, 'loss/train': 1.555604338645935}
-03/04/2022 03:39:59 - INFO - codeparrot_training - Step 12091: {'lr': 0.0004942866139441851, 'samples': 6191104, 'steps': 12091, 'loss/train': 2.023286819458008}
-03/04/2022 03:40:00 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/04/2022 03:40:04 - INFO - codeparrot_training - Step 12092: {'lr': 0.0004942854858494941, 'samples': 6191616, 'steps': 12092, 'loss/train': 1.9384578466415405}
-03/04/2022 03:40:07 - INFO - codeparrot_training - Step 12093: {'lr': 0.0004942843576447316, 'samples': 6192128, 'steps': 12093, 'loss/train': 1.241581916809082}
-03/04/2022 03:40:08 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/04/2022 03:40:13 - INFO - codeparrot_training - Step 12094: {'lr': 0.0004942832293298986, 'samples': 6192640, 'steps': 12094, 'loss/train': 1.832603096961975}
-03/04/2022 03:40:16 - INFO - codeparrot_training - Step 12095: {'lr': 0.0004942821009049952, 'samples': 6193152, 'steps': 12095, 'loss/train': 1.9057698249816895}
-03/04/2022 03:40:18 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 03:40:21 - INFO - codeparrot_training - Step 12096: {'lr': 0.0004942809723700221, 'samples': 6193664, 'steps': 12096, 'loss/train': 0.9104661345481873}
-03/04/2022 03:40:24 - INFO - codeparrot_training - Step 12097: {'lr': 0.0004942798437249797, 'samples': 6194176, 'steps': 12097, 'loss/train': 2.244004249572754}
-03/04/2022 03:40:26 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/04/2022 03:40:30 - INFO - codeparrot_training - Step 12098: {'lr': 0.0004942787149698687, 'samples': 6194688, 'steps': 12098, 'loss/train': 2.94197940826416}
-03/04/2022 03:40:33 - INFO - codeparrot_training - Step 12099: {'lr': 0.0004942775861046893, 'samples': 6195200, 'steps': 12099, 'loss/train': 2.2096760272979736}
-03/04/2022 03:40:35 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/04/2022 03:40:38 - INFO - codeparrot_training - Step 12100: {'lr': 0.0004942764571294422, 'samples': 6195712, 'steps': 12100, 'loss/train': 2.46877121925354}
-03/04/2022 03:40:41 - INFO - codeparrot_training - Step 12101: {'lr': 0.0004942753280441281, 'samples': 6196224, 'steps': 12101, 'loss/train': 1.9930899143218994}
-03/04/2022 03:40:43 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 03:40:47 - INFO - codeparrot_training - Step 12102: {'lr': 0.0004942741988487471, 'samples': 6196736, 'steps': 12102, 'loss/train': 2.423459053039551}
-03/04/2022 03:40:50 - INFO - codeparrot_training - Step 12103: {'lr': 0.0004942730695433001, 'samples': 6197248, 'steps': 12103, 'loss/train': 1.426580786705017}
-03/04/2022 03:40:51 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 03:40:55 - INFO - codeparrot_training - Step 12104: {'lr': 0.0004942719401277873, 'samples': 6197760, 'steps': 12104, 'loss/train': 1.5121821165084839}
-03/04/2022 03:40:58 - INFO - codeparrot_training - Step 12105: {'lr': 0.0004942708106022094, 'samples': 6198272, 'steps': 12105, 'loss/train': 1.370443344116211}
-03/04/2022 03:40:59 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/04/2022 03:41:03 - INFO - codeparrot_training - Step 12106: {'lr': 0.0004942696809665668, 'samples': 6198784, 'steps': 12106, 'loss/train': 1.1947721242904663}
-03/04/2022 03:41:07 - INFO - codeparrot_training - Step 12107: {'lr': 0.0004942685512208599, 'samples': 6199296, 'steps': 12107, 'loss/train': 1.6886621713638306}
-03/04/2022 03:41:08 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/04/2022 03:41:12 - INFO - codeparrot_training - Step 12108: {'lr': 0.0004942674213650896, 'samples': 6199808, 'steps': 12108, 'loss/train': 2.6254818439483643}
-03/04/2022 03:41:15 - INFO - codeparrot_training - Step 12109: {'lr': 0.000494266291399256, 'samples': 6200320, 'steps': 12109, 'loss/train': 1.5949275493621826}
-03/04/2022 03:41:16 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 03:41:20 - INFO - codeparrot_training - Step 12110: {'lr': 0.0004942651613233599, 'samples': 6200832, 'steps': 12110, 'loss/train': 0.9691089391708374}
-03/04/2022 03:41:24 - INFO - codeparrot_training - Step 12111: {'lr': 0.0004942640311374017, 'samples': 6201344, 'steps': 12111, 'loss/train': 2.1271541118621826}
-03/04/2022 03:41:25 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/04/2022 03:41:29 - INFO - codeparrot_training - Step 12112: {'lr': 0.0004942629008413818, 'samples': 6201856, 'steps': 12112, 'loss/train': 1.910529613494873}
-03/04/2022 03:41:32 - INFO - codeparrot_training - Step 12113: {'lr': 0.0004942617704353008, 'samples': 6202368, 'steps': 12113, 'loss/train': 2.024667978286743}
-03/04/2022 03:41:33 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 03:41:37 - INFO - codeparrot_training - Step 12114: {'lr': 0.0004942606399191593, 'samples': 6202880, 'steps': 12114, 'loss/train': 2.2221927642822266}
-03/04/2022 03:41:41 - INFO - codeparrot_training - Step 12115: {'lr': 0.0004942595092929577, 'samples': 6203392, 'steps': 12115, 'loss/train': 1.9122850894927979}
-03/04/2022 03:41:42 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/04/2022 03:41:46 - INFO - codeparrot_training - Step 12116: {'lr': 0.0004942583785566965, 'samples': 6203904, 'steps': 12116, 'loss/train': 1.8833056688308716}
-03/04/2022 03:41:49 - INFO - codeparrot_training - Step 12117: {'lr': 0.0004942572477103763, 'samples': 6204416, 'steps': 12117, 'loss/train': 2.0781705379486084}
-03/04/2022 03:41:50 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 03:41:54 - INFO - codeparrot_training - Step 12118: {'lr': 0.0004942561167539975, 'samples': 6204928, 'steps': 12118, 'loss/train': 1.9488282203674316}
-03/04/2022 03:41:57 - INFO - codeparrot_training - Step 12119: {'lr': 0.0004942549856875606, 'samples': 6205440, 'steps': 12119, 'loss/train': 1.5692694187164307}
-03/04/2022 03:41:59 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/04/2022 03:42:03 - INFO - codeparrot_training - Step 12120: {'lr': 0.0004942538545110663, 'samples': 6205952, 'steps': 12120, 'loss/train': 1.4167113304138184}
-03/04/2022 03:42:06 - INFO - codeparrot_training - Step 12121: {'lr': 0.0004942527232245149, 'samples': 6206464, 'steps': 12121, 'loss/train': 1.935840129852295}
-03/04/2022 03:42:09 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/04/2022 03:42:11 - INFO - codeparrot_training - Step 12122: {'lr': 0.0004942515918279071, 'samples': 6206976, 'steps': 12122, 'loss/train': 1.322951316833496}
-03/04/2022 03:42:15 - INFO - codeparrot_training - Step 12123: {'lr': 0.0004942504603212433, 'samples': 6207488, 'steps': 12123, 'loss/train': 2.1638259887695312}
-03/04/2022 03:42:17 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/04/2022 03:42:20 - INFO - codeparrot_training - Step 12124: {'lr': 0.0004942493287045239, 'samples': 6208000, 'steps': 12124, 'loss/train': 2.2370660305023193}
-03/04/2022 03:42:23 - INFO - codeparrot_training - Step 12125: {'lr': 0.0004942481969777495, 'samples': 6208512, 'steps': 12125, 'loss/train': 2.149630546569824}
-03/04/2022 03:42:25 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 03:42:28 - INFO - codeparrot_training - Step 12126: {'lr': 0.0004942470651409207, 'samples': 6209024, 'steps': 12126, 'loss/train': 1.3946620225906372}
-03/04/2022 03:42:31 - INFO - codeparrot_training - Step 12127: {'lr': 0.000494245933194038, 'samples': 6209536, 'steps': 12127, 'loss/train': 1.5792100429534912}
-03/04/2022 03:42:33 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/04/2022 03:42:37 - INFO - codeparrot_training - Step 12128: {'lr': 0.0004942448011371018, 'samples': 6210048, 'steps': 12128, 'loss/train': 2.1143932342529297}
-03/04/2022 03:42:40 - INFO - codeparrot_training - Step 12129: {'lr': 0.0004942436689701126, 'samples': 6210560, 'steps': 12129, 'loss/train': 2.1139426231384277}
-03/04/2022 03:42:42 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/04/2022 03:42:45 - INFO - codeparrot_training - Step 12130: {'lr': 0.000494242536693071, 'samples': 6211072, 'steps': 12130, 'loss/train': 1.478929042816162}
-03/04/2022 03:42:48 - INFO - codeparrot_training - Step 12131: {'lr': 0.0004942414043059776, 'samples': 6211584, 'steps': 12131, 'loss/train': 2.327753782272339}
-03/04/2022 03:42:51 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/04/2022 03:42:54 - INFO - codeparrot_training - Step 12132: {'lr': 0.0004942402718088326, 'samples': 6212096, 'steps': 12132, 'loss/train': 3.136725664138794}
-03/04/2022 03:42:57 - INFO - codeparrot_training - Step 12133: {'lr': 0.0004942391392016368, 'samples': 6212608, 'steps': 12133, 'loss/train': 2.3416078090667725}
-03/04/2022 03:42:59 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 03:43:02 - INFO - codeparrot_training - Step 12134: {'lr': 0.0004942380064843906, 'samples': 6213120, 'steps': 12134, 'loss/train': 2.626411199569702}
-03/04/2022 03:43:06 - INFO - codeparrot_training - Step 12135: {'lr': 0.0004942368736570946, 'samples': 6213632, 'steps': 12135, 'loss/train': 3.492173194885254}
-03/04/2022 03:43:09 - INFO - codeparrot_training - Step 12136: {'lr': 0.0004942357407197491, 'samples': 6214144, 'steps': 12136, 'loss/train': 2.523864269256592}
-03/04/2022 03:43:09 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/04/2022 03:43:14 - INFO - codeparrot_training - Step 12137: {'lr': 0.0004942346076723548, 'samples': 6214656, 'steps': 12137, 'loss/train': 1.8645073175430298}
-03/04/2022 03:43:17 - INFO - codeparrot_training - Step 12138: {'lr': 0.0004942334745149122, 'samples': 6215168, 'steps': 12138, 'loss/train': 2.3248260021209717}
-03/04/2022 03:43:17 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 03:43:22 - INFO - codeparrot_training - Step 12139: {'lr': 0.0004942323412474218, 'samples': 6215680, 'steps': 12139, 'loss/train': 2.7465267181396484}
-03/04/2022 03:43:26 - INFO - codeparrot_training - Step 12140: {'lr': 0.000494231207869884, 'samples': 6216192, 'steps': 12140, 'loss/train': 2.2037510871887207}
-03/04/2022 03:43:26 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 03:43:31 - INFO - codeparrot_training - Step 12141: {'lr': 0.0004942300743822993, 'samples': 6216704, 'steps': 12141, 'loss/train': 1.9799076318740845}
-03/04/2022 03:43:34 - INFO - codeparrot_training - Step 12142: {'lr': 0.0004942289407846684, 'samples': 6217216, 'steps': 12142, 'loss/train': 2.4319982528686523}
-03/04/2022 03:43:35 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/04/2022 03:43:39 - INFO - codeparrot_training - Step 12143: {'lr': 0.0004942278070769917, 'samples': 6217728, 'steps': 12143, 'loss/train': 1.8928574323654175}
-03/04/2022 03:43:43 - INFO - codeparrot_training - Step 12144: {'lr': 0.0004942266732592697, 'samples': 6218240, 'steps': 12144, 'loss/train': 1.9013221263885498}
-03/04/2022 03:43:43 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/04/2022 03:43:48 - INFO - codeparrot_training - Step 12145: {'lr': 0.0004942255393315029, 'samples': 6218752, 'steps': 12145, 'loss/train': 2.0664584636688232}
-03/04/2022 03:43:51 - INFO - codeparrot_training - Step 12146: {'lr': 0.000494224405293692, 'samples': 6219264, 'steps': 12146, 'loss/train': 1.4545437097549438}
-03/04/2022 03:43:51 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/04/2022 03:43:56 - INFO - codeparrot_training - Step 12147: {'lr': 0.0004942232711458372, 'samples': 6219776, 'steps': 12147, 'loss/train': 2.752082347869873}
-03/04/2022 03:43:59 - INFO - codeparrot_training - Step 12148: {'lr': 0.0004942221368879391, 'samples': 6220288, 'steps': 12148, 'loss/train': 1.1165239810943604}
-03/04/2022 03:44:00 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 03:44:05 - INFO - codeparrot_training - Step 12149: {'lr': 0.0004942210025199985, 'samples': 6220800, 'steps': 12149, 'loss/train': 2.178917407989502}
-03/04/2022 03:44:08 - INFO - codeparrot_training - Step 12150: {'lr': 0.0004942198680420155, 'samples': 6221312, 'steps': 12150, 'loss/train': 2.3659939765930176}
-03/04/2022 03:44:08 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/04/2022 03:44:13 - INFO - codeparrot_training - Step 12151: {'lr': 0.0004942187334539908, 'samples': 6221824, 'steps': 12151, 'loss/train': 1.8828375339508057}
-03/04/2022 03:44:16 - INFO - codeparrot_training - Step 12152: {'lr': 0.0004942175987559251, 'samples': 6222336, 'steps': 12152, 'loss/train': 1.3835642337799072}
-03/04/2022 03:44:17 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/04/2022 03:44:22 - INFO - codeparrot_training - Step 12153: {'lr': 0.0004942164639478185, 'samples': 6222848, 'steps': 12153, 'loss/train': 2.2626776695251465}
-03/04/2022 03:44:25 - INFO - codeparrot_training - Step 12154: {'lr': 0.0004942153290296718, 'samples': 6223360, 'steps': 12154, 'loss/train': 1.4052191972732544}
-03/04/2022 03:44:25 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/04/2022 03:44:30 - INFO - codeparrot_training - Step 12155: {'lr': 0.0004942141940014854, 'samples': 6223872, 'steps': 12155, 'loss/train': 2.105341672897339}
-03/04/2022 03:44:33 - INFO - codeparrot_training - Step 12156: {'lr': 0.0004942130588632599, 'samples': 6224384, 'steps': 12156, 'loss/train': 2.6023738384246826}
-03/04/2022 03:44:34 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 03:44:38 - INFO - codeparrot_training - Step 12157: {'lr': 0.0004942119236149958, 'samples': 6224896, 'steps': 12157, 'loss/train': 2.400094509124756}
-03/04/2022 03:44:42 - INFO - codeparrot_training - Step 12158: {'lr': 0.0004942107882566936, 'samples': 6225408, 'steps': 12158, 'loss/train': 1.7243704795837402}
-03/04/2022 03:44:42 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/04/2022 03:44:47 - INFO - codeparrot_training - Step 12159: {'lr': 0.0004942096527883538, 'samples': 6225920, 'steps': 12159, 'loss/train': 1.9389047622680664}
-03/04/2022 03:44:50 - INFO - codeparrot_training - Step 12160: {'lr': 0.0004942085172099768, 'samples': 6226432, 'steps': 12160, 'loss/train': 2.3042900562286377}
-03/04/2022 03:44:51 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/04/2022 03:44:56 - INFO - codeparrot_training - Step 12161: {'lr': 0.0004942073815215632, 'samples': 6226944, 'steps': 12161, 'loss/train': 2.384212017059326}
-03/04/2022 03:44:59 - INFO - codeparrot_training - Step 12162: {'lr': 0.0004942062457231136, 'samples': 6227456, 'steps': 12162, 'loss/train': 2.335422992706299}
-03/04/2022 03:45:00 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/04/2022 03:45:04 - INFO - codeparrot_training - Step 12163: {'lr': 0.0004942051098146284, 'samples': 6227968, 'steps': 12163, 'loss/train': 1.8559346199035645}
-03/04/2022 03:45:07 - INFO - codeparrot_training - Step 12164: {'lr': 0.0004942039737961081, 'samples': 6228480, 'steps': 12164, 'loss/train': 0.6034234166145325}
-03/04/2022 03:45:09 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 03:45:13 - INFO - codeparrot_training - Step 12165: {'lr': 0.0004942028376675533, 'samples': 6228992, 'steps': 12165, 'loss/train': 3.5670108795166016}
-03/04/2022 03:45:16 - INFO - codeparrot_training - Step 12166: {'lr': 0.0004942017014289645, 'samples': 6229504, 'steps': 12166, 'loss/train': 2.6598763465881348}
-03/04/2022 03:45:17 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/04/2022 03:45:21 - INFO - codeparrot_training - Step 12167: {'lr': 0.0004942005650803421, 'samples': 6230016, 'steps': 12167, 'loss/train': 2.6022465229034424}
-03/04/2022 03:45:24 - INFO - codeparrot_training - Step 12168: {'lr': 0.0004941994286216867, 'samples': 6230528, 'steps': 12168, 'loss/train': 1.472205400466919}
-03/04/2022 03:45:25 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 03:45:30 - INFO - codeparrot_training - Step 12169: {'lr': 0.0004941982920529989, 'samples': 6231040, 'steps': 12169, 'loss/train': 0.8966507315635681}
-03/04/2022 03:45:33 - INFO - codeparrot_training - Step 12170: {'lr': 0.0004941971553742791, 'samples': 6231552, 'steps': 12170, 'loss/train': 1.3815165758132935}
-03/04/2022 03:45:34 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/04/2022 03:45:38 - INFO - codeparrot_training - Step 12171: {'lr': 0.0004941960185855278, 'samples': 6232064, 'steps': 12171, 'loss/train': 1.6053200960159302}
-03/04/2022 03:45:41 - INFO - codeparrot_training - Step 12172: {'lr': 0.0004941948816867455, 'samples': 6232576, 'steps': 12172, 'loss/train': 2.976531744003296}
-03/04/2022 03:45:42 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 03:45:46 - INFO - codeparrot_training - Step 12173: {'lr': 0.0004941937446779328, 'samples': 6233088, 'steps': 12173, 'loss/train': 2.1570045948028564}
-03/04/2022 03:45:50 - INFO - codeparrot_training - Step 12174: {'lr': 0.0004941926075590901, 'samples': 6233600, 'steps': 12174, 'loss/train': 2.11708927154541}
-03/04/2022 03:45:51 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 03:45:55 - INFO - codeparrot_training - Step 12175: {'lr': 0.0004941914703302181, 'samples': 6234112, 'steps': 12175, 'loss/train': 1.6426892280578613}
-03/04/2022 03:45:58 - INFO - codeparrot_training - Step 12176: {'lr': 0.0004941903329913172, 'samples': 6234624, 'steps': 12176, 'loss/train': 2.6554160118103027}
-03/04/2022 03:45:59 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/04/2022 03:46:03 - INFO - codeparrot_training - Step 12177: {'lr': 0.0004941891955423878, 'samples': 6235136, 'steps': 12177, 'loss/train': 1.944838523864746}
-03/04/2022 03:46:07 - INFO - codeparrot_training - Step 12178: {'lr': 0.0004941880579834306, 'samples': 6235648, 'steps': 12178, 'loss/train': 2.6790666580200195}
-03/04/2022 03:46:07 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 03:46:12 - INFO - codeparrot_training - Step 12179: {'lr': 0.0004941869203144459, 'samples': 6236160, 'steps': 12179, 'loss/train': 1.5305496454238892}
-03/04/2022 03:46:15 - INFO - codeparrot_training - Step 12180: {'lr': 0.0004941857825354344, 'samples': 6236672, 'steps': 12180, 'loss/train': 1.8799502849578857}
-03/04/2022 03:46:16 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/04/2022 03:46:20 - INFO - codeparrot_training - Step 12181: {'lr': 0.0004941846446463966, 'samples': 6237184, 'steps': 12181, 'loss/train': 1.5620465278625488}
-03/04/2022 03:46:23 - INFO - codeparrot_training - Step 12182: {'lr': 0.000494183506647333, 'samples': 6237696, 'steps': 12182, 'loss/train': 1.7868486642837524}
-03/04/2022 03:46:24 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/04/2022 03:46:29 - INFO - codeparrot_training - Step 12183: {'lr': 0.000494182368538244, 'samples': 6238208, 'steps': 12183, 'loss/train': 1.9662210941314697}
-03/04/2022 03:46:32 - INFO - codeparrot_training - Step 12184: {'lr': 0.0004941812303191302, 'samples': 6238720, 'steps': 12184, 'loss/train': 2.5472617149353027}
-03/04/2022 03:46:32 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/04/2022 03:46:37 - INFO - codeparrot_training - Step 12185: {'lr': 0.0004941800919899921, 'samples': 6239232, 'steps': 12185, 'loss/train': 2.1766905784606934}
-03/04/2022 03:46:40 - INFO - codeparrot_training - Step 12186: {'lr': 0.0004941789535508303, 'samples': 6239744, 'steps': 12186, 'loss/train': 1.7258800268173218}
-03/04/2022 03:46:40 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/04/2022 03:46:46 - INFO - codeparrot_training - Step 12187: {'lr': 0.0004941778150016451, 'samples': 6240256, 'steps': 12187, 'loss/train': 1.6102582216262817}
-03/04/2022 03:46:49 - INFO - codeparrot_training - Step 12188: {'lr': 0.0004941766763424373, 'samples': 6240768, 'steps': 12188, 'loss/train': 2.250436782836914}
-03/04/2022 03:46:50 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/04/2022 03:46:54 - INFO - codeparrot_training - Step 12189: {'lr': 0.0004941755375732071, 'samples': 6241280, 'steps': 12189, 'loss/train': 1.2459954023361206}
-03/04/2022 03:46:57 - INFO - codeparrot_training - Step 12190: {'lr': 0.0004941743986939553, 'samples': 6241792, 'steps': 12190, 'loss/train': 1.713884949684143}
-03/04/2022 03:46:59 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/04/2022 03:47:02 - INFO - codeparrot_training - Step 12191: {'lr': 0.0004941732597046822, 'samples': 6242304, 'steps': 12191, 'loss/train': 2.079183340072632}
-03/04/2022 03:47:06 - INFO - codeparrot_training - Step 12192: {'lr': 0.0004941721206053885, 'samples': 6242816, 'steps': 12192, 'loss/train': 2.0133438110351562}
-03/04/2022 03:47:07 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/04/2022 03:47:11 - INFO - codeparrot_training - Step 12193: {'lr': 0.0004941709813960745, 'samples': 6243328, 'steps': 12193, 'loss/train': 2.4969708919525146}
-03/04/2022 03:47:14 - INFO - codeparrot_training - Step 12194: {'lr': 0.0004941698420767408, 'samples': 6243840, 'steps': 12194, 'loss/train': 2.2921812534332275}
-03/04/2022 03:47:15 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/04/2022 03:47:19 - INFO - codeparrot_training - Step 12195: {'lr': 0.0004941687026473881, 'samples': 6244352, 'steps': 12195, 'loss/train': 1.7735059261322021}
-03/04/2022 03:47:22 - INFO - codeparrot_training - Step 12196: {'lr': 0.0004941675631080166, 'samples': 6244864, 'steps': 12196, 'loss/train': 2.0735926628112793}
-03/04/2022 03:47:24 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 03:47:28 - INFO - codeparrot_training - Step 12197: {'lr': 0.000494166423458627, 'samples': 6245376, 'steps': 12197, 'loss/train': 1.777213215827942}
-03/04/2022 03:47:31 - INFO - codeparrot_training - Step 12198: {'lr': 0.0004941652836992198, 'samples': 6245888, 'steps': 12198, 'loss/train': 1.744695782661438}
-03/04/2022 03:47:32 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/04/2022 03:47:36 - INFO - codeparrot_training - Step 12199: {'lr': 0.0004941641438297955, 'samples': 6246400, 'steps': 12199, 'loss/train': 1.959958791732788}
-03/04/2022 03:47:39 - INFO - codeparrot_training - Step 12200: {'lr': 0.0004941630038503545, 'samples': 6246912, 'steps': 12200, 'loss/train': 0.4555242359638214}
-03/04/2022 03:47:40 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/04/2022 03:47:45 - INFO - codeparrot_training - Step 12201: {'lr': 0.0004941618637608976, 'samples': 6247424, 'steps': 12201, 'loss/train': 1.9820151329040527}
-03/04/2022 03:47:48 - INFO - codeparrot_training - Step 12202: {'lr': 0.000494160723561425, 'samples': 6247936, 'steps': 12202, 'loss/train': 2.2938504219055176}
-03/04/2022 03:47:51 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 03:47:53 - INFO - codeparrot_training - Step 12203: {'lr': 0.0004941595832519374, 'samples': 6248448, 'steps': 12203, 'loss/train': 1.0317176580429077}
-03/04/2022 03:47:57 - INFO - codeparrot_training - Step 12204: {'lr': 0.0004941584428324352, 'samples': 6248960, 'steps': 12204, 'loss/train': 1.8070744276046753}
-03/04/2022 03:47:59 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 03:48:02 - INFO - codeparrot_training - Step 12205: {'lr': 0.000494157302302919, 'samples': 6249472, 'steps': 12205, 'loss/train': 2.080244302749634}
-03/04/2022 03:48:05 - INFO - codeparrot_training - Step 12206: {'lr': 0.0004941561616633893, 'samples': 6249984, 'steps': 12206, 'loss/train': 1.1921499967575073}
-03/04/2022 03:48:07 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/04/2022 03:48:10 - INFO - codeparrot_training - Step 12207: {'lr': 0.0004941550209138466, 'samples': 6250496, 'steps': 12207, 'loss/train': 2.6391239166259766}
-03/04/2022 03:48:13 - INFO - codeparrot_training - Step 12208: {'lr': 0.0004941538800542915, 'samples': 6251008, 'steps': 12208, 'loss/train': 1.8224527835845947}
-03/04/2022 03:48:16 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/04/2022 03:48:19 - INFO - codeparrot_training - Step 12209: {'lr': 0.0004941527390847243, 'samples': 6251520, 'steps': 12209, 'loss/train': 2.3393681049346924}
-03/04/2022 03:48:22 - INFO - codeparrot_training - Step 12210: {'lr': 0.0004941515980051457, 'samples': 6252032, 'steps': 12210, 'loss/train': 2.2963342666625977}
-03/04/2022 03:48:24 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 03:48:27 - INFO - codeparrot_training - Step 12211: {'lr': 0.0004941504568155561, 'samples': 6252544, 'steps': 12211, 'loss/train': 2.093208074569702}
-03/04/2022 03:48:30 - INFO - codeparrot_training - Step 12212: {'lr': 0.0004941493155159562, 'samples': 6253056, 'steps': 12212, 'loss/train': 0.9560303092002869}
-03/04/2022 03:48:33 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/04/2022 03:48:36 - INFO - codeparrot_training - Step 12213: {'lr': 0.0004941481741063462, 'samples': 6253568, 'steps': 12213, 'loss/train': 2.076265573501587}
-03/04/2022 03:48:39 - INFO - codeparrot_training - Step 12214: {'lr': 0.000494147032586727, 'samples': 6254080, 'steps': 12214, 'loss/train': 1.9093055725097656}
-03/04/2022 03:48:41 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/04/2022 03:48:44 - INFO - codeparrot_training - Step 12215: {'lr': 0.0004941458909570988, 'samples': 6254592, 'steps': 12215, 'loss/train': 0.8343489766120911}
-03/04/2022 03:48:48 - INFO - codeparrot_training - Step 12216: {'lr': 0.0004941447492174622, 'samples': 6255104, 'steps': 12216, 'loss/train': 1.4834624528884888}
-03/04/2022 03:48:51 - INFO - codeparrot_training - Step 12217: {'lr': 0.0004941436073678179, 'samples': 6255616, 'steps': 12217, 'loss/train': 1.6135668754577637}
-03/04/2022 03:48:51 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 03:48:56 - INFO - codeparrot_training - Step 12218: {'lr': 0.0004941424654081661, 'samples': 6256128, 'steps': 12218, 'loss/train': 1.0759183168411255}
-03/04/2022 03:48:59 - INFO - codeparrot_training - Step 12219: {'lr': 0.0004941413233385075, 'samples': 6256640, 'steps': 12219, 'loss/train': 1.305092692375183}
-03/04/2022 03:48:59 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 03:49:04 - INFO - codeparrot_training - Step 12220: {'lr': 0.0004941401811588426, 'samples': 6257152, 'steps': 12220, 'loss/train': 1.9695143699645996}
-03/04/2022 03:49:07 - INFO - codeparrot_training - Step 12221: {'lr': 0.0004941390388691719, 'samples': 6257664, 'steps': 12221, 'loss/train': 2.182399272918701}
-03/04/2022 03:49:08 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 03:49:13 - INFO - codeparrot_training - Step 12222: {'lr': 0.0004941378964694959, 'samples': 6258176, 'steps': 12222, 'loss/train': 2.5187315940856934}
-03/04/2022 03:49:16 - INFO - codeparrot_training - Step 12223: {'lr': 0.0004941367539598152, 'samples': 6258688, 'steps': 12223, 'loss/train': 2.313103437423706}
-03/04/2022 03:49:16 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/04/2022 03:49:21 - INFO - codeparrot_training - Step 12224: {'lr': 0.0004941356113401301, 'samples': 6259200, 'steps': 12224, 'loss/train': 1.7699977159500122}
-03/04/2022 03:49:24 - INFO - codeparrot_training - Step 12225: {'lr': 0.0004941344686104414, 'samples': 6259712, 'steps': 12225, 'loss/train': 7.5813889503479}
-03/04/2022 03:49:25 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/04/2022 03:49:30 - INFO - codeparrot_training - Step 12226: {'lr': 0.0004941333257707495, 'samples': 6260224, 'steps': 12226, 'loss/train': 2.804943561553955}
-03/04/2022 03:49:33 - INFO - codeparrot_training - Step 12227: {'lr': 0.0004941321828210548, 'samples': 6260736, 'steps': 12227, 'loss/train': 1.7117035388946533}
-03/04/2022 03:49:34 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 03:49:38 - INFO - codeparrot_training - Step 12228: {'lr': 0.000494131039761358, 'samples': 6261248, 'steps': 12228, 'loss/train': 2.591120719909668}
-03/04/2022 03:49:41 - INFO - codeparrot_training - Step 12229: {'lr': 0.0004941298965916594, 'samples': 6261760, 'steps': 12229, 'loss/train': 2.1482412815093994}
-03/04/2022 03:49:42 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 03:49:46 - INFO - codeparrot_training - Step 12230: {'lr': 0.0004941287533119597, 'samples': 6262272, 'steps': 12230, 'loss/train': 1.3047024011611938}
-03/04/2022 03:49:50 - INFO - codeparrot_training - Step 12231: {'lr': 0.0004941276099222593, 'samples': 6262784, 'steps': 12231, 'loss/train': 1.5277434587478638}
-03/04/2022 03:49:50 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 03:49:55 - INFO - codeparrot_training - Step 12232: {'lr': 0.0004941264664225589, 'samples': 6263296, 'steps': 12232, 'loss/train': 2.6832096576690674}
-03/04/2022 03:49:58 - INFO - codeparrot_training - Step 12233: {'lr': 0.0004941253228128588, 'samples': 6263808, 'steps': 12233, 'loss/train': 1.2677549123764038}
-03/04/2022 03:49:59 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/04/2022 03:50:03 - INFO - codeparrot_training - Step 12234: {'lr': 0.0004941241790931595, 'samples': 6264320, 'steps': 12234, 'loss/train': 1.9978408813476562}
-03/04/2022 03:50:06 - INFO - codeparrot_training - Step 12235: {'lr': 0.0004941230352634617, 'samples': 6264832, 'steps': 12235, 'loss/train': 2.5733330249786377}
-03/04/2022 03:50:07 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 03:50:12 - INFO - codeparrot_training - Step 12236: {'lr': 0.0004941218913237658, 'samples': 6265344, 'steps': 12236, 'loss/train': 2.139822244644165}
-03/04/2022 03:50:15 - INFO - codeparrot_training - Step 12237: {'lr': 0.0004941207472740724, 'samples': 6265856, 'steps': 12237, 'loss/train': 1.8793123960494995}
-03/04/2022 03:50:15 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 03:50:20 - INFO - codeparrot_training - Step 12238: {'lr': 0.000494119603114382, 'samples': 6266368, 'steps': 12238, 'loss/train': 1.1283913850784302}
-03/04/2022 03:50:23 - INFO - codeparrot_training - Step 12239: {'lr': 0.000494118458844695, 'samples': 6266880, 'steps': 12239, 'loss/train': 1.1194052696228027}
-03/04/2022 03:50:23 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 03:50:29 - INFO - codeparrot_training - Step 12240: {'lr': 0.0004941173144650119, 'samples': 6267392, 'steps': 12240, 'loss/train': 1.462682843208313}
-03/04/2022 03:50:32 - INFO - codeparrot_training - Step 12241: {'lr': 0.0004941161699753335, 'samples': 6267904, 'steps': 12241, 'loss/train': 1.6473337411880493}
-03/04/2022 03:50:32 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/04/2022 03:50:37 - INFO - codeparrot_training - Step 12242: {'lr': 0.00049411502537566, 'samples': 6268416, 'steps': 12242, 'loss/train': 1.6664069890975952}
-03/04/2022 03:50:40 - INFO - codeparrot_training - Step 12243: {'lr': 0.0004941138806659921, 'samples': 6268928, 'steps': 12243, 'loss/train': 1.677563190460205}
-03/04/2022 03:50:41 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/04/2022 03:50:46 - INFO - codeparrot_training - Step 12244: {'lr': 0.00049411273584633, 'samples': 6269440, 'steps': 12244, 'loss/train': 2.7476909160614014}
-03/04/2022 03:50:49 - INFO - codeparrot_training - Step 12245: {'lr': 0.0004941115909166748, 'samples': 6269952, 'steps': 12245, 'loss/train': 2.1026999950408936}
-03/04/2022 03:50:49 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/04/2022 03:50:54 - INFO - codeparrot_training - Step 12246: {'lr': 0.0004941104458770266, 'samples': 6270464, 'steps': 12246, 'loss/train': 2.323906898498535}
-03/04/2022 03:50:57 - INFO - codeparrot_training - Step 12247: {'lr': 0.0004941093007273859, 'samples': 6270976, 'steps': 12247, 'loss/train': 2.273655414581299}
-03/04/2022 03:50:57 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 03:51:03 - INFO - codeparrot_training - Step 12248: {'lr': 0.0004941081554677534, 'samples': 6271488, 'steps': 12248, 'loss/train': 0.7717595100402832}
-03/04/2022 03:51:06 - INFO - codeparrot_training - Step 12249: {'lr': 0.0004941070100981295, 'samples': 6272000, 'steps': 12249, 'loss/train': 2.4975333213806152}
-03/04/2022 03:51:06 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/04/2022 03:51:11 - INFO - codeparrot_training - Step 12250: {'lr': 0.0004941058646185148, 'samples': 6272512, 'steps': 12250, 'loss/train': 1.8468669652938843}
-03/04/2022 03:51:14 - INFO - codeparrot_training - Step 12251: {'lr': 0.0004941047190289096, 'samples': 6273024, 'steps': 12251, 'loss/train': 1.771658182144165}
-03/04/2022 03:51:14 - INFO - codeparrot_training - Skipping example with length 285 (seq_length=1024)
-03/04/2022 03:51:20 - INFO - codeparrot_training - Step 12252: {'lr': 0.0004941035733293148, 'samples': 6273536, 'steps': 12252, 'loss/train': 1.5909385681152344}
-03/04/2022 03:51:22 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 03:51:25 - INFO - codeparrot_training - Step 12253: {'lr': 0.0004941024275197305, 'samples': 6274048, 'steps': 12253, 'loss/train': 3.0440585613250732}
-03/04/2022 03:51:28 - INFO - codeparrot_training - Step 12254: {'lr': 0.0004941012816001575, 'samples': 6274560, 'steps': 12254, 'loss/train': 2.414552688598633}
-03/04/2022 03:51:31 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/04/2022 03:51:33 - INFO - codeparrot_training - Step 12255: {'lr': 0.0004941001355705963, 'samples': 6275072, 'steps': 12255, 'loss/train': 1.907523512840271}
-03/04/2022 03:51:36 - INFO - codeparrot_training - Step 12256: {'lr': 0.0004940989894310473, 'samples': 6275584, 'steps': 12256, 'loss/train': 2.125051498413086}
-03/04/2022 03:51:39 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/04/2022 03:51:42 - INFO - codeparrot_training - Step 12257: {'lr': 0.000494097843181511, 'samples': 6276096, 'steps': 12257, 'loss/train': 2.485992670059204}
-03/04/2022 03:51:45 - INFO - codeparrot_training - Step 12258: {'lr': 0.0004940966968219881, 'samples': 6276608, 'steps': 12258, 'loss/train': 1.930901050567627}
-03/04/2022 03:51:48 - INFO - codeparrot_training - Step 12259: {'lr': 0.0004940955503524789, 'samples': 6277120, 'steps': 12259, 'loss/train': 6.916227340698242}
-03/04/2022 03:51:48 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/04/2022 03:51:53 - INFO - codeparrot_training - Step 12260: {'lr': 0.000494094403772984, 'samples': 6277632, 'steps': 12260, 'loss/train': 1.629210352897644}
-03/04/2022 03:51:56 - INFO - codeparrot_training - Step 12261: {'lr': 0.0004940932570835039, 'samples': 6278144, 'steps': 12261, 'loss/train': 1.267179250717163}
-03/04/2022 03:51:57 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/04/2022 03:52:02 - INFO - codeparrot_training - Step 12262: {'lr': 0.0004940921102840393, 'samples': 6278656, 'steps': 12262, 'loss/train': 1.6838592290878296}
-03/04/2022 03:52:05 - INFO - codeparrot_training - Step 12263: {'lr': 0.0004940909633745905, 'samples': 6279168, 'steps': 12263, 'loss/train': 2.409581184387207}
-03/04/2022 03:52:06 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/04/2022 03:52:10 - INFO - codeparrot_training - Step 12264: {'lr': 0.000494089816355158, 'samples': 6279680, 'steps': 12264, 'loss/train': 2.5500950813293457}
-03/04/2022 03:52:13 - INFO - codeparrot_training - Step 12265: {'lr': 0.0004940886692257424, 'samples': 6280192, 'steps': 12265, 'loss/train': 1.4550005197525024}
-03/04/2022 03:52:14 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/04/2022 03:52:19 - INFO - codeparrot_training - Step 12266: {'lr': 0.0004940875219863443, 'samples': 6280704, 'steps': 12266, 'loss/train': 0.7512443661689758}
-03/04/2022 03:52:22 - INFO - codeparrot_training - Step 12267: {'lr': 0.0004940863746369641, 'samples': 6281216, 'steps': 12267, 'loss/train': 3.285449743270874}
-03/04/2022 03:52:23 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/04/2022 03:52:27 - INFO - codeparrot_training - Step 12268: {'lr': 0.0004940852271776023, 'samples': 6281728, 'steps': 12268, 'loss/train': 1.9938149452209473}
-03/04/2022 03:52:30 - INFO - codeparrot_training - Step 12269: {'lr': 0.0004940840796082594, 'samples': 6282240, 'steps': 12269, 'loss/train': 1.0065401792526245}
-03/04/2022 03:52:31 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/04/2022 03:52:36 - INFO - codeparrot_training - Step 12270: {'lr': 0.0004940829319289361, 'samples': 6282752, 'steps': 12270, 'loss/train': 1.3080910444259644}
-03/04/2022 03:52:39 - INFO - codeparrot_training - Step 12271: {'lr': 0.0004940817841396327, 'samples': 6283264, 'steps': 12271, 'loss/train': 1.860456943511963}
-03/04/2022 03:52:39 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 03:52:44 - INFO - codeparrot_training - Step 12272: {'lr': 0.0004940806362403499, 'samples': 6283776, 'steps': 12272, 'loss/train': 0.4915159046649933}
-03/04/2022 03:52:47 - INFO - codeparrot_training - Step 12273: {'lr': 0.0004940794882310882, 'samples': 6284288, 'steps': 12273, 'loss/train': 2.029668092727661}
-03/04/2022 03:52:47 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/04/2022 03:52:52 - INFO - codeparrot_training - Step 12274: {'lr': 0.000494078340111848, 'samples': 6284800, 'steps': 12274, 'loss/train': 1.145411491394043}
-03/04/2022 03:52:56 - INFO - codeparrot_training - Step 12275: {'lr': 0.0004940771918826298, 'samples': 6285312, 'steps': 12275, 'loss/train': 2.9439666271209717}
-03/04/2022 03:52:56 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 03:53:01 - INFO - codeparrot_training - Step 12276: {'lr': 0.0004940760435434341, 'samples': 6285824, 'steps': 12276, 'loss/train': 2.9917795658111572}
-03/04/2022 03:53:04 - INFO - codeparrot_training - Step 12277: {'lr': 0.0004940748950942618, 'samples': 6286336, 'steps': 12277, 'loss/train': 1.8634028434753418}
-03/04/2022 03:53:04 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 03:53:09 - INFO - codeparrot_training - Step 12278: {'lr': 0.0004940737465351128, 'samples': 6286848, 'steps': 12278, 'loss/train': 1.361487865447998}
-03/04/2022 03:53:13 - INFO - codeparrot_training - Step 12279: {'lr': 0.0004940725978659881, 'samples': 6287360, 'steps': 12279, 'loss/train': 2.06390643119812}
-03/04/2022 03:53:13 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/04/2022 03:53:18 - INFO - codeparrot_training - Step 12280: {'lr': 0.000494071449086888, 'samples': 6287872, 'steps': 12280, 'loss/train': 2.2499866485595703}
-03/04/2022 03:53:21 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/04/2022 03:53:23 - INFO - codeparrot_training - Step 12281: {'lr': 0.0004940703001978131, 'samples': 6288384, 'steps': 12281, 'loss/train': 2.3206863403320312}
-03/04/2022 03:53:26 - INFO - codeparrot_training - Step 12282: {'lr': 0.0004940691511987639, 'samples': 6288896, 'steps': 12282, 'loss/train': 1.7331637144088745}
-03/04/2022 03:53:29 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/04/2022 03:53:31 - INFO - codeparrot_training - Step 12283: {'lr': 0.0004940680020897409, 'samples': 6289408, 'steps': 12283, 'loss/train': 1.612983226776123}
-03/04/2022 03:53:35 - INFO - codeparrot_training - Step 12284: {'lr': 0.0004940668528707446, 'samples': 6289920, 'steps': 12284, 'loss/train': 1.951785683631897}
-03/04/2022 03:53:37 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/04/2022 03:53:40 - INFO - codeparrot_training - Step 12285: {'lr': 0.0004940657035417755, 'samples': 6290432, 'steps': 12285, 'loss/train': 0.5810708403587341}
-03/04/2022 03:53:43 - INFO - codeparrot_training - Step 12286: {'lr': 0.0004940645541028343, 'samples': 6290944, 'steps': 12286, 'loss/train': 2.0440220832824707}
-03/04/2022 03:53:46 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 03:53:48 - INFO - codeparrot_training - Step 12287: {'lr': 0.0004940634045539213, 'samples': 6291456, 'steps': 12287, 'loss/train': 1.6517256498336792}
-03/04/2022 03:53:52 - INFO - codeparrot_training - Step 12288: {'lr': 0.000494062254895037, 'samples': 6291968, 'steps': 12288, 'loss/train': 2.1103475093841553}
-03/04/2022 03:53:54 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/04/2022 03:53:57 - INFO - codeparrot_training - Step 12289: {'lr': 0.0004940611051261822, 'samples': 6292480, 'steps': 12289, 'loss/train': 2.078685998916626}
-03/04/2022 03:54:00 - INFO - codeparrot_training - Step 12290: {'lr': 0.000494059955247357, 'samples': 6292992, 'steps': 12290, 'loss/train': 3.0220227241516113}
-03/04/2022 03:54:02 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 03:54:05 - INFO - codeparrot_training - Step 12291: {'lr': 0.0004940588052585624, 'samples': 6293504, 'steps': 12291, 'loss/train': 2.04994535446167}
-03/04/2022 03:54:09 - INFO - codeparrot_training - Step 12292: {'lr': 0.0004940576551597985, 'samples': 6294016, 'steps': 12292, 'loss/train': 1.8091754913330078}
-03/04/2022 03:54:11 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/04/2022 03:54:14 - INFO - codeparrot_training - Step 12293: {'lr': 0.000494056504951066, 'samples': 6294528, 'steps': 12293, 'loss/train': 2.0929174423217773}
-03/04/2022 03:54:17 - INFO - codeparrot_training - Step 12294: {'lr': 0.0004940553546323655, 'samples': 6295040, 'steps': 12294, 'loss/train': 1.8597064018249512}
-03/04/2022 03:54:19 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 03:54:22 - INFO - codeparrot_training - Step 12295: {'lr': 0.0004940542042036974, 'samples': 6295552, 'steps': 12295, 'loss/train': 2.139482021331787}
-03/04/2022 03:54:25 - INFO - codeparrot_training - Step 12296: {'lr': 0.0004940530536650621, 'samples': 6296064, 'steps': 12296, 'loss/train': 2.4797627925872803}
-03/04/2022 03:54:27 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/04/2022 03:54:31 - INFO - codeparrot_training - Step 12297: {'lr': 0.0004940519030164605, 'samples': 6296576, 'steps': 12297, 'loss/train': 1.9556150436401367}
-03/04/2022 03:54:34 - INFO - codeparrot_training - Step 12298: {'lr': 0.0004940507522578927, 'samples': 6297088, 'steps': 12298, 'loss/train': 2.3551628589630127}
-03/04/2022 03:54:36 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/04/2022 03:54:39 - INFO - codeparrot_training - Step 12299: {'lr': 0.0004940496013893594, 'samples': 6297600, 'steps': 12299, 'loss/train': 1.2697772979736328}
-03/04/2022 03:54:42 - INFO - codeparrot_training - Step 12300: {'lr': 0.0004940484504108612, 'samples': 6298112, 'steps': 12300, 'loss/train': 2.3285739421844482}
-03/04/2022 03:54:44 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/04/2022 03:54:47 - INFO - codeparrot_training - Step 12301: {'lr': 0.0004940472993223985, 'samples': 6298624, 'steps': 12301, 'loss/train': 1.825376033782959}
-03/04/2022 03:54:50 - INFO - codeparrot_training - Step 12302: {'lr': 0.0004940461481239719, 'samples': 6299136, 'steps': 12302, 'loss/train': 1.9857462644577026}
-03/04/2022 03:54:52 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/04/2022 03:54:56 - INFO - codeparrot_training - Step 12303: {'lr': 0.0004940449968155818, 'samples': 6299648, 'steps': 12303, 'loss/train': 1.9105727672576904}
-03/04/2022 03:54:59 - INFO - codeparrot_training - Step 12304: {'lr': 0.0004940438453972288, 'samples': 6300160, 'steps': 12304, 'loss/train': 2.691019296646118}
-03/04/2022 03:55:01 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 03:55:04 - INFO - codeparrot_training - Step 12305: {'lr': 0.0004940426938689135, 'samples': 6300672, 'steps': 12305, 'loss/train': 1.700567603111267}
-03/04/2022 03:55:07 - INFO - codeparrot_training - Step 12306: {'lr': 0.0004940415422306361, 'samples': 6301184, 'steps': 12306, 'loss/train': 1.7585598230361938}
-03/04/2022 03:55:10 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 03:55:13 - INFO - codeparrot_training - Step 12307: {'lr': 0.0004940403904823976, 'samples': 6301696, 'steps': 12307, 'loss/train': 2.2564311027526855}
-03/04/2022 03:55:16 - INFO - codeparrot_training - Step 12308: {'lr': 0.0004940392386241981, 'samples': 6302208, 'steps': 12308, 'loss/train': 2.9760794639587402}
-03/04/2022 03:55:18 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 03:55:21 - INFO - codeparrot_training - Step 12309: {'lr': 0.0004940380866560384, 'samples': 6302720, 'steps': 12309, 'loss/train': 2.2545013427734375}
-03/04/2022 03:55:24 - INFO - codeparrot_training - Step 12310: {'lr': 0.0004940369345779187, 'samples': 6303232, 'steps': 12310, 'loss/train': 1.597861409187317}
-03/04/2022 03:55:27 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 03:55:29 - INFO - codeparrot_training - Step 12311: {'lr': 0.00049403578238984, 'samples': 6303744, 'steps': 12311, 'loss/train': 1.7764699459075928}
-03/04/2022 03:55:33 - INFO - codeparrot_training - Step 12312: {'lr': 0.0004940346300918024, 'samples': 6304256, 'steps': 12312, 'loss/train': 1.805821418762207}
-03/04/2022 03:55:35 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 03:55:38 - INFO - codeparrot_training - Step 12313: {'lr': 0.0004940334776838065, 'samples': 6304768, 'steps': 12313, 'loss/train': 2.3095593452453613}
-03/04/2022 03:55:41 - INFO - codeparrot_training - Step 12314: {'lr': 0.000494032325165853, 'samples': 6305280, 'steps': 12314, 'loss/train': 1.981085181236267}
-03/04/2022 03:55:43 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/04/2022 03:55:46 - INFO - codeparrot_training - Step 12315: {'lr': 0.0004940311725379423, 'samples': 6305792, 'steps': 12315, 'loss/train': 1.9131314754486084}
-03/04/2022 03:55:49 - INFO - codeparrot_training - Step 12316: {'lr': 0.0004940300198000748, 'samples': 6306304, 'steps': 12316, 'loss/train': 2.1476917266845703}
-03/04/2022 03:55:52 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/04/2022 03:55:55 - INFO - codeparrot_training - Step 12317: {'lr': 0.0004940288669522513, 'samples': 6306816, 'steps': 12317, 'loss/train': 1.7534115314483643}
-03/04/2022 03:55:58 - INFO - codeparrot_training - Step 12318: {'lr': 0.000494027713994472, 'samples': 6307328, 'steps': 12318, 'loss/train': 1.9982801675796509}
-03/04/2022 03:56:00 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/04/2022 03:56:03 - INFO - codeparrot_training - Step 12319: {'lr': 0.0004940265609267377, 'samples': 6307840, 'steps': 12319, 'loss/train': 2.0932304859161377}
-03/04/2022 03:56:06 - INFO - codeparrot_training - Step 12320: {'lr': 0.0004940254077490487, 'samples': 6308352, 'steps': 12320, 'loss/train': 2.005237102508545}
-03/04/2022 03:56:08 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 03:56:11 - INFO - codeparrot_training - Step 12321: {'lr': 0.0004940242544614056, 'samples': 6308864, 'steps': 12321, 'loss/train': 2.6503710746765137}
-03/04/2022 03:56:14 - INFO - codeparrot_training - Step 12322: {'lr': 0.0004940231010638091, 'samples': 6309376, 'steps': 12322, 'loss/train': 3.027527093887329}
-03/04/2022 03:56:16 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/04/2022 03:56:20 - INFO - codeparrot_training - Step 12323: {'lr': 0.0004940219475562593, 'samples': 6309888, 'steps': 12323, 'loss/train': 1.9916706085205078}
-03/04/2022 03:56:23 - INFO - codeparrot_training - Step 12324: {'lr': 0.0004940207939387573, 'samples': 6310400, 'steps': 12324, 'loss/train': 2.3556604385375977}
-03/04/2022 03:56:26 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/04/2022 03:56:28 - INFO - codeparrot_training - Step 12325: {'lr': 0.0004940196402113031, 'samples': 6310912, 'steps': 12325, 'loss/train': 2.0983388423919678}
-03/04/2022 03:56:32 - INFO - codeparrot_training - Step 12326: {'lr': 0.0004940184863738975, 'samples': 6311424, 'steps': 12326, 'loss/train': 2.150965929031372}
-03/04/2022 03:56:34 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 03:56:37 - INFO - codeparrot_training - Step 12327: {'lr': 0.0004940173324265407, 'samples': 6311936, 'steps': 12327, 'loss/train': 1.1329957246780396}
-03/04/2022 03:56:40 - INFO - codeparrot_training - Step 12328: {'lr': 0.0004940161783692338, 'samples': 6312448, 'steps': 12328, 'loss/train': 1.9311937093734741}
-03/04/2022 03:56:43 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/04/2022 03:56:45 - INFO - codeparrot_training - Step 12329: {'lr': 0.0004940150242019768, 'samples': 6312960, 'steps': 12329, 'loss/train': 2.0558245182037354}
-03/04/2022 03:56:48 - INFO - codeparrot_training - Step 12330: {'lr': 0.0004940138699247704, 'samples': 6313472, 'steps': 12330, 'loss/train': 1.6154032945632935}
-03/04/2022 03:56:51 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/04/2022 03:56:54 - INFO - codeparrot_training - Step 12331: {'lr': 0.0004940127155376151, 'samples': 6313984, 'steps': 12331, 'loss/train': 1.624493956565857}
-03/04/2022 03:56:57 - INFO - codeparrot_training - Step 12332: {'lr': 0.0004940115610405114, 'samples': 6314496, 'steps': 12332, 'loss/train': 1.2650067806243896}
-03/04/2022 03:56:59 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 03:57:02 - INFO - codeparrot_training - Step 12333: {'lr': 0.0004940104064334599, 'samples': 6315008, 'steps': 12333, 'loss/train': 2.228001832962036}
-03/04/2022 03:57:05 - INFO - codeparrot_training - Step 12334: {'lr': 0.0004940092517164612, 'samples': 6315520, 'steps': 12334, 'loss/train': 2.9843051433563232}
-03/04/2022 03:57:08 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/04/2022 03:57:10 - INFO - codeparrot_training - Step 12335: {'lr': 0.0004940080968895155, 'samples': 6316032, 'steps': 12335, 'loss/train': 2.634920358657837}
-03/04/2022 03:57:14 - INFO - codeparrot_training - Step 12336: {'lr': 0.0004940069419526236, 'samples': 6316544, 'steps': 12336, 'loss/train': 1.702589988708496}
-03/04/2022 03:57:16 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/04/2022 03:57:19 - INFO - codeparrot_training - Step 12337: {'lr': 0.0004940057869057859, 'samples': 6317056, 'steps': 12337, 'loss/train': 2.4835851192474365}
-03/04/2022 03:57:22 - INFO - codeparrot_training - Step 12338: {'lr': 0.000494004631749003, 'samples': 6317568, 'steps': 12338, 'loss/train': 1.6956075429916382}
-03/04/2022 03:57:25 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 03:57:27 - INFO - codeparrot_training - Step 12339: {'lr': 0.0004940034764822754, 'samples': 6318080, 'steps': 12339, 'loss/train': 2.1956660747528076}
-03/04/2022 03:57:31 - INFO - codeparrot_training - Step 12340: {'lr': 0.0004940023211056036, 'samples': 6318592, 'steps': 12340, 'loss/train': 1.6652321815490723}
-03/04/2022 03:57:33 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 03:57:36 - INFO - codeparrot_training - Step 12341: {'lr': 0.0004940011656189881, 'samples': 6319104, 'steps': 12341, 'loss/train': 1.7812010049819946}
-03/04/2022 03:57:39 - INFO - codeparrot_training - Step 12342: {'lr': 0.0004940000100224295, 'samples': 6319616, 'steps': 12342, 'loss/train': 1.8769304752349854}
-03/04/2022 03:57:42 - INFO - codeparrot_training - Step 12343: {'lr': 0.0004939988543159282, 'samples': 6320128, 'steps': 12343, 'loss/train': 2.2435359954833984}
-03/04/2022 03:57:43 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/04/2022 03:57:47 - INFO - codeparrot_training - Step 12344: {'lr': 0.0004939976984994847, 'samples': 6320640, 'steps': 12344, 'loss/train': 1.7324087619781494}
-03/04/2022 03:57:51 - INFO - codeparrot_training - Step 12345: {'lr': 0.0004939965425730996, 'samples': 6321152, 'steps': 12345, 'loss/train': 2.492574691772461}
-03/04/2022 03:57:51 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/04/2022 03:57:56 - INFO - codeparrot_training - Step 12346: {'lr': 0.0004939953865367735, 'samples': 6321664, 'steps': 12346, 'loss/train': 2.2993197441101074}
-03/04/2022 03:57:59 - INFO - codeparrot_training - Step 12347: {'lr': 0.0004939942303905069, 'samples': 6322176, 'steps': 12347, 'loss/train': 1.8215986490249634}
-03/04/2022 03:57:59 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 03:58:04 - INFO - codeparrot_training - Step 12348: {'lr': 0.0004939930741343002, 'samples': 6322688, 'steps': 12348, 'loss/train': 1.8798006772994995}
-03/04/2022 03:58:07 - INFO - codeparrot_training - Step 12349: {'lr': 0.000493991917768154, 'samples': 6323200, 'steps': 12349, 'loss/train': 1.118522047996521}
-03/04/2022 03:58:08 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/04/2022 03:58:13 - INFO - codeparrot_training - Step 12350: {'lr': 0.0004939907612920688, 'samples': 6323712, 'steps': 12350, 'loss/train': 1.779026985168457}
-03/04/2022 03:58:16 - INFO - codeparrot_training - Step 12351: {'lr': 0.0004939896047060451, 'samples': 6324224, 'steps': 12351, 'loss/train': 2.074723958969116}
-03/04/2022 03:58:17 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/04/2022 03:58:21 - INFO - codeparrot_training - Step 12352: {'lr': 0.0004939884480100836, 'samples': 6324736, 'steps': 12352, 'loss/train': 2.146552085876465}
-03/04/2022 03:58:24 - INFO - codeparrot_training - Step 12353: {'lr': 0.0004939872912041844, 'samples': 6325248, 'steps': 12353, 'loss/train': 2.2881460189819336}
-03/04/2022 03:58:25 - INFO - codeparrot_training - Skipping example with length 462 (seq_length=1024)
-03/04/2022 03:58:30 - INFO - codeparrot_training - Step 12354: {'lr': 0.0004939861342883485, 'samples': 6325760, 'steps': 12354, 'loss/train': 0.13915489614009857}
-03/04/2022 03:58:33 - INFO - codeparrot_training - Step 12355: {'lr': 0.0004939849772625761, 'samples': 6326272, 'steps': 12355, 'loss/train': 1.4622353315353394}
-03/04/2022 03:58:33 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/04/2022 03:58:38 - INFO - codeparrot_training - Step 12356: {'lr': 0.0004939838201268679, 'samples': 6326784, 'steps': 12356, 'loss/train': 2.3242294788360596}
-03/04/2022 03:58:41 - INFO - codeparrot_training - Step 12357: {'lr': 0.0004939826628812244, 'samples': 6327296, 'steps': 12357, 'loss/train': 1.8587992191314697}
-03/04/2022 03:58:42 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/04/2022 03:58:47 - INFO - codeparrot_training - Step 12358: {'lr': 0.000493981505525646, 'samples': 6327808, 'steps': 12358, 'loss/train': 2.1968064308166504}
-03/04/2022 03:58:50 - INFO - codeparrot_training - Step 12359: {'lr': 0.0004939803480601333, 'samples': 6328320, 'steps': 12359, 'loss/train': 2.9223945140838623}
-03/04/2022 03:58:51 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/04/2022 03:58:55 - INFO - codeparrot_training - Step 12360: {'lr': 0.0004939791904846869, 'samples': 6328832, 'steps': 12360, 'loss/train': 1.999904990196228}
-03/04/2022 03:58:58 - INFO - codeparrot_training - Step 12361: {'lr': 0.0004939780327993072, 'samples': 6329344, 'steps': 12361, 'loss/train': 2.0244951248168945}
-03/04/2022 03:58:59 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/04/2022 03:59:04 - INFO - codeparrot_training - Step 12362: {'lr': 0.0004939768750039946, 'samples': 6329856, 'steps': 12362, 'loss/train': 2.1743087768554688}
-03/04/2022 03:59:07 - INFO - codeparrot_training - Step 12363: {'lr': 0.00049397571709875, 'samples': 6330368, 'steps': 12363, 'loss/train': 1.6480920314788818}
-03/04/2022 03:59:08 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 03:59:12 - INFO - codeparrot_training - Step 12364: {'lr': 0.0004939745590835736, 'samples': 6330880, 'steps': 12364, 'loss/train': 2.135227680206299}
-03/04/2022 03:59:15 - INFO - codeparrot_training - Step 12365: {'lr': 0.0004939734009584661, 'samples': 6331392, 'steps': 12365, 'loss/train': 1.8095201253890991}
-03/04/2022 03:59:16 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 03:59:21 - INFO - codeparrot_training - Step 12366: {'lr': 0.0004939722427234279, 'samples': 6331904, 'steps': 12366, 'loss/train': 2.039086103439331}
-03/04/2022 03:59:24 - INFO - codeparrot_training - Step 12367: {'lr': 0.0004939710843784596, 'samples': 6332416, 'steps': 12367, 'loss/train': 2.204895257949829}
-03/04/2022 03:59:25 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/04/2022 03:59:29 - INFO - codeparrot_training - Step 12368: {'lr': 0.0004939699259235617, 'samples': 6332928, 'steps': 12368, 'loss/train': 1.1877654790878296}
-03/04/2022 03:59:32 - INFO - codeparrot_training - Step 12369: {'lr': 0.0004939687673587346, 'samples': 6333440, 'steps': 12369, 'loss/train': 1.9052115678787231}
-03/04/2022 03:59:33 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/04/2022 03:59:38 - INFO - codeparrot_training - Step 12370: {'lr': 0.0004939676086839791, 'samples': 6333952, 'steps': 12370, 'loss/train': 2.24784255027771}
-03/04/2022 03:59:41 - INFO - codeparrot_training - Step 12371: {'lr': 0.0004939664498992955, 'samples': 6334464, 'steps': 12371, 'loss/train': 2.2066378593444824}
-03/04/2022 03:59:42 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/04/2022 03:59:46 - INFO - codeparrot_training - Step 12372: {'lr': 0.0004939652910046844, 'samples': 6334976, 'steps': 12372, 'loss/train': 2.384751081466675}
-03/04/2022 03:59:49 - INFO - codeparrot_training - Step 12373: {'lr': 0.0004939641320001462, 'samples': 6335488, 'steps': 12373, 'loss/train': 1.2630975246429443}
-03/04/2022 03:59:50 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/04/2022 03:59:54 - INFO - codeparrot_training - Step 12374: {'lr': 0.0004939629728856817, 'samples': 6336000, 'steps': 12374, 'loss/train': 1.9857022762298584}
-03/04/2022 03:59:58 - INFO - codeparrot_training - Step 12375: {'lr': 0.0004939618136612911, 'samples': 6336512, 'steps': 12375, 'loss/train': 2.1729331016540527}
-03/04/2022 03:59:58 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 04:00:03 - INFO - codeparrot_training - Step 12376: {'lr': 0.0004939606543269751, 'samples': 6337024, 'steps': 12376, 'loss/train': 1.023248553276062}
-03/04/2022 04:00:06 - INFO - codeparrot_training - Step 12377: {'lr': 0.0004939594948827343, 'samples': 6337536, 'steps': 12377, 'loss/train': 1.1613410711288452}
-03/04/2022 04:00:07 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/04/2022 04:00:11 - INFO - codeparrot_training - Step 12378: {'lr': 0.000493958335328569, 'samples': 6338048, 'steps': 12378, 'loss/train': 2.3953018188476562}
-03/04/2022 04:00:14 - INFO - codeparrot_training - Step 12379: {'lr': 0.0004939571756644799, 'samples': 6338560, 'steps': 12379, 'loss/train': 2.1344504356384277}
-03/04/2022 04:00:15 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/04/2022 04:00:20 - INFO - codeparrot_training - Step 12380: {'lr': 0.0004939560158904675, 'samples': 6339072, 'steps': 12380, 'loss/train': 2.239839553833008}
-03/04/2022 04:00:23 - INFO - codeparrot_training - Step 12381: {'lr': 0.0004939548560065322, 'samples': 6339584, 'steps': 12381, 'loss/train': 2.0437276363372803}
-03/04/2022 04:00:24 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/04/2022 04:00:28 - INFO - codeparrot_training - Step 12382: {'lr': 0.0004939536960126746, 'samples': 6340096, 'steps': 12382, 'loss/train': 0.47742700576782227}
-03/04/2022 04:00:32 - INFO - codeparrot_training - Step 12383: {'lr': 0.0004939525359088953, 'samples': 6340608, 'steps': 12383, 'loss/train': 2.301020383834839}
-03/04/2022 04:00:32 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 04:00:37 - INFO - codeparrot_training - Step 12384: {'lr': 0.0004939513756951946, 'samples': 6341120, 'steps': 12384, 'loss/train': 2.183336019515991}
-03/04/2022 04:00:40 - INFO - codeparrot_training - Step 12385: {'lr': 0.0004939502153715733, 'samples': 6341632, 'steps': 12385, 'loss/train': 2.0443994998931885}
-03/04/2022 04:00:41 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/04/2022 04:00:46 - INFO - codeparrot_training - Step 12386: {'lr': 0.0004939490549380318, 'samples': 6342144, 'steps': 12386, 'loss/train': 2.7484397888183594}
-03/04/2022 04:00:49 - INFO - codeparrot_training - Step 12387: {'lr': 0.0004939478943945706, 'samples': 6342656, 'steps': 12387, 'loss/train': 1.965118646621704}
-03/04/2022 04:00:49 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/04/2022 04:00:54 - INFO - codeparrot_training - Step 12388: {'lr': 0.0004939467337411903, 'samples': 6343168, 'steps': 12388, 'loss/train': 2.3900890350341797}
-03/04/2022 04:00:57 - INFO - codeparrot_training - Step 12389: {'lr': 0.0004939455729778912, 'samples': 6343680, 'steps': 12389, 'loss/train': 1.6856324672698975}
-03/04/2022 04:00:58 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/04/2022 04:01:02 - INFO - codeparrot_training - Step 12390: {'lr': 0.0004939444121046741, 'samples': 6344192, 'steps': 12390, 'loss/train': 1.953634262084961}
-03/04/2022 04:01:06 - INFO - codeparrot_training - Step 12391: {'lr': 0.0004939432511215395, 'samples': 6344704, 'steps': 12391, 'loss/train': 2.1373443603515625}
-03/04/2022 04:01:06 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 04:01:11 - INFO - codeparrot_training - Step 12392: {'lr': 0.0004939420900284876, 'samples': 6345216, 'steps': 12392, 'loss/train': 0.3212927281856537}
-03/04/2022 04:01:14 - INFO - codeparrot_training - Step 12393: {'lr': 0.0004939409288255194, 'samples': 6345728, 'steps': 12393, 'loss/train': 1.238450527191162}
-03/04/2022 04:01:14 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 04:01:19 - INFO - codeparrot_training - Step 12394: {'lr': 0.000493939767512635, 'samples': 6346240, 'steps': 12394, 'loss/train': 1.262951135635376}
-03/04/2022 04:01:23 - INFO - codeparrot_training - Step 12395: {'lr': 0.0004939386060898353, 'samples': 6346752, 'steps': 12395, 'loss/train': 4.3567304611206055}
-03/04/2022 04:01:23 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 04:01:28 - INFO - codeparrot_training - Step 12396: {'lr': 0.0004939374445571206, 'samples': 6347264, 'steps': 12396, 'loss/train': 2.267542600631714}
-03/04/2022 04:01:31 - INFO - codeparrot_training - Step 12397: {'lr': 0.0004939362829144913, 'samples': 6347776, 'steps': 12397, 'loss/train': 2.3234927654266357}
-03/04/2022 04:01:32 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 04:01:36 - INFO - codeparrot_training - Step 12398: {'lr': 0.0004939351211619481, 'samples': 6348288, 'steps': 12398, 'loss/train': 2.1934704780578613}
-03/04/2022 04:01:40 - INFO - codeparrot_training - Step 12399: {'lr': 0.0004939339592994916, 'samples': 6348800, 'steps': 12399, 'loss/train': 1.5704193115234375}
-03/04/2022 04:01:40 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/04/2022 04:01:45 - INFO - codeparrot_training - Step 12400: {'lr': 0.0004939327973271222, 'samples': 6349312, 'steps': 12400, 'loss/train': 2.3688952922821045}
-03/04/2022 04:01:48 - INFO - codeparrot_training - Step 12401: {'lr': 0.0004939316352448403, 'samples': 6349824, 'steps': 12401, 'loss/train': 1.6438751220703125}
-03/04/2022 04:01:49 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/04/2022 04:01:53 - INFO - codeparrot_training - Step 12402: {'lr': 0.0004939304730526467, 'samples': 6350336, 'steps': 12402, 'loss/train': 2.074937582015991}
-03/04/2022 04:01:56 - INFO - codeparrot_training - Step 12403: {'lr': 0.0004939293107505418, 'samples': 6350848, 'steps': 12403, 'loss/train': 2.114600658416748}
-03/04/2022 04:01:57 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 04:02:02 - INFO - codeparrot_training - Step 12404: {'lr': 0.0004939281483385261, 'samples': 6351360, 'steps': 12404, 'loss/train': 2.731788396835327}
-03/04/2022 04:02:05 - INFO - codeparrot_training - Step 12405: {'lr': 0.0004939269858166001, 'samples': 6351872, 'steps': 12405, 'loss/train': 1.6979811191558838}
-03/04/2022 04:02:05 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 04:02:10 - INFO - codeparrot_training - Step 12406: {'lr': 0.0004939258231847644, 'samples': 6352384, 'steps': 12406, 'loss/train': 2.1703081130981445}
-03/04/2022 04:02:13 - INFO - codeparrot_training - Step 12407: {'lr': 0.0004939246604430195, 'samples': 6352896, 'steps': 12407, 'loss/train': 1.3597805500030518}
-03/04/2022 04:02:14 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 04:02:18 - INFO - codeparrot_training - Step 12408: {'lr': 0.0004939234975913659, 'samples': 6353408, 'steps': 12408, 'loss/train': 2.3359270095825195}
-03/04/2022 04:02:22 - INFO - codeparrot_training - Step 12409: {'lr': 0.0004939223346298042, 'samples': 6353920, 'steps': 12409, 'loss/train': 2.464503049850464}
-03/04/2022 04:02:22 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 04:02:27 - INFO - codeparrot_training - Step 12410: {'lr': 0.0004939211715583347, 'samples': 6354432, 'steps': 12410, 'loss/train': 2.5479044914245605}
-03/04/2022 04:02:30 - INFO - codeparrot_training - Step 12411: {'lr': 0.0004939200083769582, 'samples': 6354944, 'steps': 12411, 'loss/train': 1.4501802921295166}
-03/04/2022 04:02:30 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 04:02:35 - INFO - codeparrot_training - Step 12412: {'lr': 0.000493918845085675, 'samples': 6355456, 'steps': 12412, 'loss/train': 1.7912031412124634}
-03/04/2022 04:02:38 - INFO - codeparrot_training - Step 12413: {'lr': 0.000493917681684486, 'samples': 6355968, 'steps': 12413, 'loss/train': 1.1345477104187012}
-03/04/2022 04:02:39 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 04:02:44 - INFO - codeparrot_training - Step 12414: {'lr': 0.0004939165181733911, 'samples': 6356480, 'steps': 12414, 'loss/train': 1.9190690517425537}
-03/04/2022 04:02:47 - INFO - codeparrot_training - Step 12415: {'lr': 0.0004939153545523914, 'samples': 6356992, 'steps': 12415, 'loss/train': 0.3913619816303253}
-03/04/2022 04:02:47 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/04/2022 04:02:52 - INFO - codeparrot_training - Step 12416: {'lr': 0.0004939141908214871, 'samples': 6357504, 'steps': 12416, 'loss/train': 2.260406732559204}
-03/04/2022 04:02:55 - INFO - codeparrot_training - Step 12417: {'lr': 0.000493913026980679, 'samples': 6358016, 'steps': 12417, 'loss/train': 1.8138582706451416}
-03/04/2022 04:02:55 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 04:03:00 - INFO - codeparrot_training - Step 12418: {'lr': 0.0004939118630299672, 'samples': 6358528, 'steps': 12418, 'loss/train': 1.8188549280166626}
-03/04/2022 04:03:04 - INFO - codeparrot_training - Step 12419: {'lr': 0.0004939106989693527, 'samples': 6359040, 'steps': 12419, 'loss/train': 1.2892504930496216}
-03/04/2022 04:03:04 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/04/2022 04:03:09 - INFO - codeparrot_training - Step 12420: {'lr': 0.0004939095347988357, 'samples': 6359552, 'steps': 12420, 'loss/train': 2.1804449558258057}
-03/04/2022 04:03:12 - INFO - codeparrot_training - Step 12421: {'lr': 0.0004939083705184169, 'samples': 6360064, 'steps': 12421, 'loss/train': 1.3285592794418335}
-03/04/2022 04:03:12 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 04:03:17 - INFO - codeparrot_training - Step 12422: {'lr': 0.0004939072061280967, 'samples': 6360576, 'steps': 12422, 'loss/train': 2.6347062587738037}
-03/04/2022 04:03:20 - INFO - codeparrot_training - Step 12423: {'lr': 0.0004939060416278756, 'samples': 6361088, 'steps': 12423, 'loss/train': 2.314620018005371}
-03/04/2022 04:03:20 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/04/2022 04:03:26 - INFO - codeparrot_training - Step 12424: {'lr': 0.0004939048770177543, 'samples': 6361600, 'steps': 12424, 'loss/train': 1.873328685760498}
-03/04/2022 04:03:29 - INFO - codeparrot_training - Step 12425: {'lr': 0.0004939037122977332, 'samples': 6362112, 'steps': 12425, 'loss/train': 1.5324583053588867}
-03/04/2022 04:03:29 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 04:03:34 - INFO - codeparrot_training - Step 12426: {'lr': 0.0004939025474678129, 'samples': 6362624, 'steps': 12426, 'loss/train': 2.3478732109069824}
-03/04/2022 04:03:37 - INFO - codeparrot_training - Step 12427: {'lr': 0.0004939013825279939, 'samples': 6363136, 'steps': 12427, 'loss/train': 2.111711263656616}
-03/04/2022 04:03:37 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/04/2022 04:03:43 - INFO - codeparrot_training - Step 12428: {'lr': 0.0004939002174782766, 'samples': 6363648, 'steps': 12428, 'loss/train': 1.662144422531128}
-03/04/2022 04:03:46 - INFO - codeparrot_training - Step 12429: {'lr': 0.0004938990523186616, 'samples': 6364160, 'steps': 12429, 'loss/train': 3.0739850997924805}
-03/04/2022 04:03:46 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/04/2022 04:03:51 - INFO - codeparrot_training - Step 12430: {'lr': 0.0004938978870491495, 'samples': 6364672, 'steps': 12430, 'loss/train': 1.8361999988555908}
-03/04/2022 04:03:54 - INFO - codeparrot_training - Step 12431: {'lr': 0.0004938967216697409, 'samples': 6365184, 'steps': 12431, 'loss/train': 1.9083008766174316}
-03/04/2022 04:03:54 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 04:04:00 - INFO - codeparrot_training - Step 12432: {'lr': 0.0004938955561804361, 'samples': 6365696, 'steps': 12432, 'loss/train': 1.3136857748031616}
-03/04/2022 04:04:03 - INFO - codeparrot_training - Step 12433: {'lr': 0.0004938943905812357, 'samples': 6366208, 'steps': 12433, 'loss/train': 1.8504594564437866}
-03/04/2022 04:04:03 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/04/2022 04:04:08 - INFO - codeparrot_training - Step 12434: {'lr': 0.0004938932248721401, 'samples': 6366720, 'steps': 12434, 'loss/train': 1.5309101343154907}
-03/04/2022 04:04:11 - INFO - codeparrot_training - Step 12435: {'lr': 0.0004938920590531503, 'samples': 6367232, 'steps': 12435, 'loss/train': 1.9192602634429932}
-03/04/2022 04:04:11 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 04:04:17 - INFO - codeparrot_training - Step 12436: {'lr': 0.0004938908931242663, 'samples': 6367744, 'steps': 12436, 'loss/train': 2.4847145080566406}
-03/04/2022 04:04:20 - INFO - codeparrot_training - Step 12437: {'lr': 0.0004938897270854889, 'samples': 6368256, 'steps': 12437, 'loss/train': 2.842585563659668}
-03/04/2022 04:04:20 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/04/2022 04:04:25 - INFO - codeparrot_training - Step 12438: {'lr': 0.0004938885609368184, 'samples': 6368768, 'steps': 12438, 'loss/train': 2.817427158355713}
-03/04/2022 04:04:28 - INFO - codeparrot_training - Step 12439: {'lr': 0.0004938873946782557, 'samples': 6369280, 'steps': 12439, 'loss/train': 2.286048650741577}
-03/04/2022 04:04:28 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 04:04:33 - INFO - codeparrot_training - Step 12440: {'lr': 0.000493886228309801, 'samples': 6369792, 'steps': 12440, 'loss/train': 0.3222823739051819}
-03/04/2022 04:04:37 - INFO - codeparrot_training - Step 12441: {'lr': 0.0004938850618314549, 'samples': 6370304, 'steps': 12441, 'loss/train': 2.0084681510925293}
-03/04/2022 04:04:37 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 04:04:42 - INFO - codeparrot_training - Step 12442: {'lr': 0.000493883895243218, 'samples': 6370816, 'steps': 12442, 'loss/train': 1.512912631034851}
-03/04/2022 04:04:45 - INFO - codeparrot_training - Step 12443: {'lr': 0.0004938827285450908, 'samples': 6371328, 'steps': 12443, 'loss/train': 1.760497808456421}
-03/04/2022 04:04:45 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/04/2022 04:04:50 - INFO - codeparrot_training - Step 12444: {'lr': 0.0004938815617370737, 'samples': 6371840, 'steps': 12444, 'loss/train': 1.4318413734436035}
-03/04/2022 04:04:53 - INFO - codeparrot_training - Step 12445: {'lr': 0.0004938803948191674, 'samples': 6372352, 'steps': 12445, 'loss/train': 1.2158786058425903}
-03/04/2022 04:04:54 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 04:04:59 - INFO - codeparrot_training - Step 12446: {'lr': 0.0004938792277913724, 'samples': 6372864, 'steps': 12446, 'loss/train': 1.0152033567428589}
-03/04/2022 04:05:02 - INFO - codeparrot_training - Step 12447: {'lr': 0.0004938780606536891, 'samples': 6373376, 'steps': 12447, 'loss/train': 2.2681260108947754}
-03/04/2022 04:05:02 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/04/2022 04:05:07 - INFO - codeparrot_training - Step 12448: {'lr': 0.0004938768934061182, 'samples': 6373888, 'steps': 12448, 'loss/train': 2.5132718086242676}
-03/04/2022 04:05:10 - INFO - codeparrot_training - Step 12449: {'lr': 0.0004938757260486601, 'samples': 6374400, 'steps': 12449, 'loss/train': 1.2012889385223389}
-03/04/2022 04:05:10 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/04/2022 04:05:15 - INFO - codeparrot_training - Step 12450: {'lr': 0.0004938745585813153, 'samples': 6374912, 'steps': 12450, 'loss/train': 1.4677178859710693}
-03/04/2022 04:05:19 - INFO - codeparrot_training - Step 12451: {'lr': 0.0004938733910040845, 'samples': 6375424, 'steps': 12451, 'loss/train': 2.073477268218994}
-03/04/2022 04:05:19 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/04/2022 04:05:24 - INFO - codeparrot_training - Step 12452: {'lr': 0.000493872223316968, 'samples': 6375936, 'steps': 12452, 'loss/train': 1.9273240566253662}
-03/04/2022 04:05:27 - INFO - codeparrot_training - Step 12453: {'lr': 0.0004938710555199664, 'samples': 6376448, 'steps': 12453, 'loss/train': 1.578502893447876}
-03/04/2022 04:05:27 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/04/2022 04:05:33 - INFO - codeparrot_training - Step 12454: {'lr': 0.0004938698876130804, 'samples': 6376960, 'steps': 12454, 'loss/train': 2.211289405822754}
-03/04/2022 04:05:36 - INFO - codeparrot_training - Step 12455: {'lr': 0.0004938687195963104, 'samples': 6377472, 'steps': 12455, 'loss/train': 2.142150640487671}
-03/04/2022 04:05:36 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 04:05:41 - INFO - codeparrot_training - Step 12456: {'lr': 0.0004938675514696569, 'samples': 6377984, 'steps': 12456, 'loss/train': 2.534574031829834}
-03/04/2022 04:05:44 - INFO - codeparrot_training - Step 12457: {'lr': 0.0004938663832331204, 'samples': 6378496, 'steps': 12457, 'loss/train': 0.8754456043243408}
-03/04/2022 04:05:45 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 04:05:49 - INFO - codeparrot_training - Step 12458: {'lr': 0.0004938652148867014, 'samples': 6379008, 'steps': 12458, 'loss/train': 1.9527645111083984}
-03/04/2022 04:05:53 - INFO - codeparrot_training - Step 12459: {'lr': 0.0004938640464304006, 'samples': 6379520, 'steps': 12459, 'loss/train': 1.761090874671936}
-03/04/2022 04:05:53 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/04/2022 04:05:58 - INFO - codeparrot_training - Step 12460: {'lr': 0.0004938628778642185, 'samples': 6380032, 'steps': 12460, 'loss/train': 1.3012336492538452}
-03/04/2022 04:06:01 - INFO - codeparrot_training - Step 12461: {'lr': 0.0004938617091881554, 'samples': 6380544, 'steps': 12461, 'loss/train': 1.9659305810928345}
-03/04/2022 04:06:01 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/04/2022 04:06:06 - INFO - codeparrot_training - Step 12462: {'lr': 0.000493860540402212, 'samples': 6381056, 'steps': 12462, 'loss/train': 1.7323269844055176}
-03/04/2022 04:06:10 - INFO - codeparrot_training - Step 12463: {'lr': 0.0004938593715063888, 'samples': 6381568, 'steps': 12463, 'loss/train': 2.4715957641601562}
-03/04/2022 04:06:10 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/04/2022 04:06:15 - INFO - codeparrot_training - Step 12464: {'lr': 0.0004938582025006864, 'samples': 6382080, 'steps': 12464, 'loss/train': 2.4073357582092285}
-03/04/2022 04:06:18 - INFO - codeparrot_training - Step 12465: {'lr': 0.0004938570333851052, 'samples': 6382592, 'steps': 12465, 'loss/train': 1.1311379671096802}
-03/04/2022 04:06:18 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/04/2022 04:06:23 - INFO - codeparrot_training - Step 12466: {'lr': 0.0004938558641596458, 'samples': 6383104, 'steps': 12466, 'loss/train': 0.19529254734516144}
-03/04/2022 04:06:26 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/04/2022 04:06:29 - INFO - codeparrot_training - Step 12467: {'lr': 0.0004938546948243087, 'samples': 6383616, 'steps': 12467, 'loss/train': 2.2132771015167236}
-03/04/2022 04:06:32 - INFO - codeparrot_training - Step 12468: {'lr': 0.0004938535253790944, 'samples': 6384128, 'steps': 12468, 'loss/train': 0.4306240677833557}
-03/04/2022 04:06:35 - INFO - codeparrot_training - Step 12469: {'lr': 0.0004938523558240035, 'samples': 6384640, 'steps': 12469, 'loss/train': 0.8565812706947327}
-03/04/2022 04:06:35 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/04/2022 04:06:41 - INFO - codeparrot_training - Step 12470: {'lr': 0.0004938511861590365, 'samples': 6385152, 'steps': 12470, 'loss/train': 1.3075567483901978}
-03/04/2022 04:06:44 - INFO - codeparrot_training - Step 12471: {'lr': 0.000493850016384194, 'samples': 6385664, 'steps': 12471, 'loss/train': 0.05941513925790787}
-03/04/2022 04:06:45 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/04/2022 04:06:49 - INFO - codeparrot_training - Step 12472: {'lr': 0.0004938488464994764, 'samples': 6386176, 'steps': 12472, 'loss/train': 2.2693963050842285}
-03/04/2022 04:06:52 - INFO - codeparrot_training - Step 12473: {'lr': 0.0004938476765048842, 'samples': 6386688, 'steps': 12473, 'loss/train': 1.5557637214660645}
-03/04/2022 04:06:53 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 04:06:57 - INFO - codeparrot_training - Step 12474: {'lr': 0.0004938465064004181, 'samples': 6387200, 'steps': 12474, 'loss/train': 2.391190767288208}
-03/04/2022 04:07:01 - INFO - codeparrot_training - Step 12475: {'lr': 0.0004938453361860785, 'samples': 6387712, 'steps': 12475, 'loss/train': 1.6993238925933838}
-03/04/2022 04:07:02 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 04:07:06 - INFO - codeparrot_training - Step 12476: {'lr': 0.0004938441658618659, 'samples': 6388224, 'steps': 12476, 'loss/train': 0.6503628492355347}
-03/04/2022 04:07:09 - INFO - codeparrot_training - Step 12477: {'lr': 0.0004938429954277809, 'samples': 6388736, 'steps': 12477, 'loss/train': 1.48712956905365}
-03/04/2022 04:07:10 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/04/2022 04:07:14 - INFO - codeparrot_training - Step 12478: {'lr': 0.000493841824883824, 'samples': 6389248, 'steps': 12478, 'loss/train': 1.7248928546905518}
-03/04/2022 04:07:18 - INFO - codeparrot_training - Step 12479: {'lr': 0.0004938406542299956, 'samples': 6389760, 'steps': 12479, 'loss/train': 1.7987912893295288}
-03/04/2022 04:07:19 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 04:07:23 - INFO - codeparrot_training - Step 12480: {'lr': 0.0004938394834662966, 'samples': 6390272, 'steps': 12480, 'loss/train': 5.994378566741943}
-03/04/2022 04:07:26 - INFO - codeparrot_training - Step 12481: {'lr': 0.0004938383125927272, 'samples': 6390784, 'steps': 12481, 'loss/train': 2.2883589267730713}
-03/04/2022 04:07:28 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 04:07:31 - INFO - codeparrot_training - Step 12482: {'lr': 0.0004938371416092881, 'samples': 6391296, 'steps': 12482, 'loss/train': 0.9795070886611938}
-03/04/2022 04:07:35 - INFO - codeparrot_training - Step 12483: {'lr': 0.0004938359705159796, 'samples': 6391808, 'steps': 12483, 'loss/train': 1.521217942237854}
-03/04/2022 04:07:37 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 04:07:40 - INFO - codeparrot_training - Step 12484: {'lr': 0.0004938347993128025, 'samples': 6392320, 'steps': 12484, 'loss/train': 2.45192289352417}
-03/04/2022 04:07:43 - INFO - codeparrot_training - Step 12485: {'lr': 0.0004938336279997571, 'samples': 6392832, 'steps': 12485, 'loss/train': 1.4944818019866943}
-03/04/2022 04:07:45 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/04/2022 04:07:48 - INFO - codeparrot_training - Step 12486: {'lr': 0.0004938324565768441, 'samples': 6393344, 'steps': 12486, 'loss/train': 1.9147992134094238}
-03/04/2022 04:07:52 - INFO - codeparrot_training - Step 12487: {'lr': 0.0004938312850440639, 'samples': 6393856, 'steps': 12487, 'loss/train': 0.5219863653182983}
-03/04/2022 04:07:54 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 04:07:57 - INFO - codeparrot_training - Step 12488: {'lr': 0.0004938301134014172, 'samples': 6394368, 'steps': 12488, 'loss/train': 2.0147666931152344}
-03/04/2022 04:08:00 - INFO - codeparrot_training - Step 12489: {'lr': 0.0004938289416489042, 'samples': 6394880, 'steps': 12489, 'loss/train': 1.6430000066757202}
-03/04/2022 04:08:03 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/04/2022 04:08:05 - INFO - codeparrot_training - Step 12490: {'lr': 0.0004938277697865259, 'samples': 6395392, 'steps': 12490, 'loss/train': 1.502362608909607}
-03/04/2022 04:08:09 - INFO - codeparrot_training - Step 12491: {'lr': 0.0004938265978142824, 'samples': 6395904, 'steps': 12491, 'loss/train': 2.634202480316162}
-03/04/2022 04:08:11 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 04:08:14 - INFO - codeparrot_training - Step 12492: {'lr': 0.0004938254257321745, 'samples': 6396416, 'steps': 12492, 'loss/train': 2.1807382106781006}
-03/04/2022 04:08:17 - INFO - codeparrot_training - Step 12493: {'lr': 0.0004938242535402025, 'samples': 6396928, 'steps': 12493, 'loss/train': 2.3079886436462402}
-03/04/2022 04:08:20 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/04/2022 04:08:23 - INFO - codeparrot_training - Step 12494: {'lr': 0.0004938230812383672, 'samples': 6397440, 'steps': 12494, 'loss/train': 2.4599924087524414}
-03/04/2022 04:08:26 - INFO - codeparrot_training - Step 12495: {'lr': 0.0004938219088266688, 'samples': 6397952, 'steps': 12495, 'loss/train': 0.3307672441005707}
-03/04/2022 04:08:29 - INFO - codeparrot_training - Step 12496: {'lr': 0.0004938207363051082, 'samples': 6398464, 'steps': 12496, 'loss/train': 0.2940671443939209}
-03/04/2022 04:08:29 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/04/2022 04:08:34 - INFO - codeparrot_training - Step 12497: {'lr': 0.0004938195636736857, 'samples': 6398976, 'steps': 12497, 'loss/train': 1.899673342704773}
-03/04/2022 04:08:37 - INFO - codeparrot_training - Step 12498: {'lr': 0.0004938183909324017, 'samples': 6399488, 'steps': 12498, 'loss/train': 1.5749696493148804}
-03/04/2022 04:08:37 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/04/2022 04:08:42 - INFO - codeparrot_training - Step 12499: {'lr': 0.0004938172180812571, 'samples': 6400000, 'steps': 12499, 'loss/train': 2.1069884300231934}
-03/04/2022 04:08:46 - INFO - codeparrot_training - Step 12500: {'lr': 0.000493816045120252, 'samples': 6400512, 'steps': 12500, 'loss/train': 2.782066822052002}
-03/04/2022 04:08:46 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 04:08:51 - INFO - codeparrot_training - Step 12501: {'lr': 0.0004938148720493873, 'samples': 6401024, 'steps': 12501, 'loss/train': 0.1543787717819214}
-03/04/2022 04:08:54 - INFO - codeparrot_training - Step 12502: {'lr': 0.0004938136988686634, 'samples': 6401536, 'steps': 12502, 'loss/train': 1.681043267250061}
-03/04/2022 04:08:54 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/04/2022 04:08:59 - INFO - codeparrot_training - Step 12503: {'lr': 0.0004938125255780808, 'samples': 6402048, 'steps': 12503, 'loss/train': 2.5274932384490967}
-03/04/2022 04:09:02 - INFO - codeparrot_training - Step 12504: {'lr': 0.0004938113521776401, 'samples': 6402560, 'steps': 12504, 'loss/train': 1.68303644657135}
-03/04/2022 04:09:03 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 04:09:08 - INFO - codeparrot_training - Step 12505: {'lr': 0.0004938101786673416, 'samples': 6403072, 'steps': 12505, 'loss/train': 1.969153881072998}
-03/04/2022 04:09:11 - INFO - codeparrot_training - Step 12506: {'lr': 0.0004938090050471861, 'samples': 6403584, 'steps': 12506, 'loss/train': 0.18106774985790253}
-03/04/2022 04:09:11 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 04:09:16 - INFO - codeparrot_training - Step 12507: {'lr': 0.000493807831317174, 'samples': 6404096, 'steps': 12507, 'loss/train': 2.113755464553833}
-03/04/2022 04:09:20 - INFO - codeparrot_training - Step 12508: {'lr': 0.0004938066574773058, 'samples': 6404608, 'steps': 12508, 'loss/train': 1.0178709030151367}
-03/04/2022 04:09:20 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/04/2022 04:09:25 - INFO - codeparrot_training - Step 12509: {'lr': 0.0004938054835275822, 'samples': 6405120, 'steps': 12509, 'loss/train': 2.2888691425323486}
-03/04/2022 04:09:28 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 04:09:30 - INFO - codeparrot_training - Step 12510: {'lr': 0.0004938043094680036, 'samples': 6405632, 'steps': 12510, 'loss/train': 1.7411179542541504}
-03/04/2022 04:09:33 - INFO - codeparrot_training - Step 12511: {'lr': 0.0004938031352985704, 'samples': 6406144, 'steps': 12511, 'loss/train': 2.068453311920166}
-03/04/2022 04:09:36 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 04:09:38 - INFO - codeparrot_training - Step 12512: {'lr': 0.0004938019610192835, 'samples': 6406656, 'steps': 12512, 'loss/train': 1.638498306274414}
-03/04/2022 04:09:42 - INFO - codeparrot_training - Step 12513: {'lr': 0.0004938007866301429, 'samples': 6407168, 'steps': 12513, 'loss/train': 2.212902307510376}
-03/04/2022 04:09:44 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 04:09:47 - INFO - codeparrot_training - Step 12514: {'lr': 0.0004937996121311496, 'samples': 6407680, 'steps': 12514, 'loss/train': 1.8160544633865356}
-03/04/2022 04:09:50 - INFO - codeparrot_training - Step 12515: {'lr': 0.000493798437522304, 'samples': 6408192, 'steps': 12515, 'loss/train': 2.174184799194336}
-03/04/2022 04:09:52 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 04:09:55 - INFO - codeparrot_training - Step 12516: {'lr': 0.0004937972628036065, 'samples': 6408704, 'steps': 12516, 'loss/train': 1.8764872550964355}
-03/04/2022 04:09:58 - INFO - codeparrot_training - Step 12517: {'lr': 0.0004937960879750578, 'samples': 6409216, 'steps': 12517, 'loss/train': 1.88340425491333}
-03/04/2022 04:10:00 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 04:10:04 - INFO - codeparrot_training - Step 12518: {'lr': 0.0004937949130366582, 'samples': 6409728, 'steps': 12518, 'loss/train': 2.705294132232666}
-03/04/2022 04:10:07 - INFO - codeparrot_training - Step 12519: {'lr': 0.0004937937379884085, 'samples': 6410240, 'steps': 12519, 'loss/train': 1.846946120262146}
-03/04/2022 04:10:09 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 04:10:12 - INFO - codeparrot_training - Step 12520: {'lr': 0.0004937925628303091, 'samples': 6410752, 'steps': 12520, 'loss/train': 2.98946475982666}
-03/04/2022 04:10:15 - INFO - codeparrot_training - Step 12521: {'lr': 0.0004937913875623605, 'samples': 6411264, 'steps': 12521, 'loss/train': 0.16015347838401794}
-03/04/2022 04:10:17 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/04/2022 04:10:20 - INFO - codeparrot_training - Step 12522: {'lr': 0.0004937902121845633, 'samples': 6411776, 'steps': 12522, 'loss/train': 2.0454366207122803}
-03/04/2022 04:10:24 - INFO - codeparrot_training - Step 12523: {'lr': 0.000493789036696918, 'samples': 6412288, 'steps': 12523, 'loss/train': 2.446851968765259}
-03/04/2022 04:10:26 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/04/2022 04:10:29 - INFO - codeparrot_training - Step 12524: {'lr': 0.000493787861099425, 'samples': 6412800, 'steps': 12524, 'loss/train': 1.8460068702697754}
-03/04/2022 04:10:32 - INFO - codeparrot_training - Step 12525: {'lr': 0.0004937866853920851, 'samples': 6413312, 'steps': 12525, 'loss/train': 0.544565737247467}
-03/04/2022 04:10:34 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/04/2022 04:10:37 - INFO - codeparrot_training - Step 12526: {'lr': 0.0004937855095748985, 'samples': 6413824, 'steps': 12526, 'loss/train': 2.109978199005127}
-03/04/2022 04:10:41 - INFO - codeparrot_training - Step 12527: {'lr': 0.0004937843336478661, 'samples': 6414336, 'steps': 12527, 'loss/train': 1.41877019405365}
-03/04/2022 04:10:43 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/04/2022 04:10:46 - INFO - codeparrot_training - Step 12528: {'lr': 0.0004937831576109881, 'samples': 6414848, 'steps': 12528, 'loss/train': 1.9349935054779053}
-03/04/2022 04:10:49 - INFO - codeparrot_training - Step 12529: {'lr': 0.0004937819814642653, 'samples': 6415360, 'steps': 12529, 'loss/train': 1.7061610221862793}
-03/04/2022 04:10:51 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 04:10:54 - INFO - codeparrot_training - Step 12530: {'lr': 0.000493780805207698, 'samples': 6415872, 'steps': 12530, 'loss/train': 1.8309141397476196}
-03/04/2022 04:10:57 - INFO - codeparrot_training - Step 12531: {'lr': 0.000493779628841287, 'samples': 6416384, 'steps': 12531, 'loss/train': 1.8642724752426147}
-03/04/2022 04:10:59 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/04/2022 04:11:03 - INFO - codeparrot_training - Step 12532: {'lr': 0.0004937784523650324, 'samples': 6416896, 'steps': 12532, 'loss/train': 1.7323118448257446}
-03/04/2022 04:11:06 - INFO - codeparrot_training - Step 12533: {'lr': 0.0004937772757789352, 'samples': 6417408, 'steps': 12533, 'loss/train': 1.4834022521972656}
-03/04/2022 04:11:08 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 04:11:11 - INFO - codeparrot_training - Step 12534: {'lr': 0.0004937760990829956, 'samples': 6417920, 'steps': 12534, 'loss/train': 2.439255714416504}
-03/04/2022 04:11:14 - INFO - codeparrot_training - Step 12535: {'lr': 0.0004937749222772143, 'samples': 6418432, 'steps': 12535, 'loss/train': 1.8143073320388794}
-03/04/2022 04:11:16 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/04/2022 04:11:20 - INFO - codeparrot_training - Step 12536: {'lr': 0.0004937737453615918, 'samples': 6418944, 'steps': 12536, 'loss/train': 2.406381130218506}
-03/04/2022 04:11:23 - INFO - codeparrot_training - Step 12537: {'lr': 0.0004937725683361286, 'samples': 6419456, 'steps': 12537, 'loss/train': 1.9618265628814697}
-03/04/2022 04:11:24 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 04:11:28 - INFO - codeparrot_training - Step 12538: {'lr': 0.0004937713912008252, 'samples': 6419968, 'steps': 12538, 'loss/train': 1.6362576484680176}
-03/04/2022 04:11:31 - INFO - codeparrot_training - Step 12539: {'lr': 0.0004937702139556822, 'samples': 6420480, 'steps': 12539, 'loss/train': 1.5960031747817993}
-03/04/2022 04:11:32 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/04/2022 04:11:36 - INFO - codeparrot_training - Step 12540: {'lr': 0.0004937690366007, 'samples': 6420992, 'steps': 12540, 'loss/train': 1.912274718284607}
-03/04/2022 04:11:40 - INFO - codeparrot_training - Step 12541: {'lr': 0.0004937678591358794, 'samples': 6421504, 'steps': 12541, 'loss/train': 2.3184173107147217}
-03/04/2022 04:11:41 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 04:11:45 - INFO - codeparrot_training - Step 12542: {'lr': 0.0004937666815612207, 'samples': 6422016, 'steps': 12542, 'loss/train': 2.0902514457702637}
-03/04/2022 04:11:48 - INFO - codeparrot_training - Step 12543: {'lr': 0.0004937655038767245, 'samples': 6422528, 'steps': 12543, 'loss/train': 1.9629223346710205}
-03/04/2022 04:11:49 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 04:11:53 - INFO - codeparrot_training - Step 12544: {'lr': 0.0004937643260823914, 'samples': 6423040, 'steps': 12544, 'loss/train': 1.5997259616851807}
-03/04/2022 04:11:56 - INFO - codeparrot_training - Step 12545: {'lr': 0.0004937631481782218, 'samples': 6423552, 'steps': 12545, 'loss/train': 1.717268705368042}
-03/04/2022 04:11:57 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/04/2022 04:12:02 - INFO - codeparrot_training - Step 12546: {'lr': 0.0004937619701642162, 'samples': 6424064, 'steps': 12546, 'loss/train': 1.6590653657913208}
-03/04/2022 04:12:05 - INFO - codeparrot_training - Step 12547: {'lr': 0.0004937607920403752, 'samples': 6424576, 'steps': 12547, 'loss/train': 2.2082390785217285}
-03/04/2022 04:12:05 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/04/2022 04:12:10 - INFO - codeparrot_training - Step 12548: {'lr': 0.0004937596138066996, 'samples': 6425088, 'steps': 12548, 'loss/train': 2.3458240032196045}
-03/04/2022 04:12:13 - INFO - codeparrot_training - Step 12549: {'lr': 0.0004937584354631894, 'samples': 6425600, 'steps': 12549, 'loss/train': 1.944685459136963}
-03/04/2022 04:12:14 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/04/2022 04:12:18 - INFO - codeparrot_training - Step 12550: {'lr': 0.0004937572570098455, 'samples': 6426112, 'steps': 12550, 'loss/train': 1.8410332202911377}
-03/04/2022 04:12:22 - INFO - codeparrot_training - Step 12551: {'lr': 0.0004937560784466685, 'samples': 6426624, 'steps': 12551, 'loss/train': 2.2368273735046387}
-03/04/2022 04:12:22 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/04/2022 04:12:27 - INFO - codeparrot_training - Step 12552: {'lr': 0.0004937548997736586, 'samples': 6427136, 'steps': 12552, 'loss/train': 1.931161880493164}
-03/04/2022 04:12:30 - INFO - codeparrot_training - Step 12553: {'lr': 0.0004937537209908165, 'samples': 6427648, 'steps': 12553, 'loss/train': 2.4355380535125732}
-03/04/2022 04:12:30 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/04/2022 04:12:35 - INFO - codeparrot_training - Step 12554: {'lr': 0.0004937525420981428, 'samples': 6428160, 'steps': 12554, 'loss/train': 1.6242002248764038}
-03/04/2022 04:12:38 - INFO - codeparrot_training - Step 12555: {'lr': 0.0004937513630956379, 'samples': 6428672, 'steps': 12555, 'loss/train': 2.0886824131011963}
-03/04/2022 04:12:39 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 04:12:44 - INFO - codeparrot_training - Step 12556: {'lr': 0.0004937501839833024, 'samples': 6429184, 'steps': 12556, 'loss/train': 2.014866828918457}
-03/04/2022 04:12:47 - INFO - codeparrot_training - Step 12557: {'lr': 0.0004937490047611369, 'samples': 6429696, 'steps': 12557, 'loss/train': 2.285909652709961}
-03/04/2022 04:12:48 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 04:12:52 - INFO - codeparrot_training - Step 12558: {'lr': 0.0004937478254291418, 'samples': 6430208, 'steps': 12558, 'loss/train': 2.220921516418457}
-03/04/2022 04:12:55 - INFO - codeparrot_training - Step 12559: {'lr': 0.0004937466459873178, 'samples': 6430720, 'steps': 12559, 'loss/train': 1.2846139669418335}
-03/04/2022 04:12:56 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 04:13:01 - INFO - codeparrot_training - Step 12560: {'lr': 0.0004937454664356652, 'samples': 6431232, 'steps': 12560, 'loss/train': 2.3978288173675537}
-03/04/2022 04:13:04 - INFO - codeparrot_training - Step 12561: {'lr': 0.0004937442867741848, 'samples': 6431744, 'steps': 12561, 'loss/train': 0.43925127387046814}
-03/04/2022 04:13:04 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/04/2022 04:13:09 - INFO - codeparrot_training - Step 12562: {'lr': 0.0004937431070028768, 'samples': 6432256, 'steps': 12562, 'loss/train': 2.1444091796875}
-03/04/2022 04:13:12 - INFO - codeparrot_training - Step 12563: {'lr': 0.0004937419271217419, 'samples': 6432768, 'steps': 12563, 'loss/train': 0.781940758228302}
-03/04/2022 04:13:13 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/04/2022 04:13:17 - INFO - codeparrot_training - Step 12564: {'lr': 0.0004937407471307807, 'samples': 6433280, 'steps': 12564, 'loss/train': 2.2024078369140625}
-03/04/2022 04:13:20 - INFO - codeparrot_training - Step 12565: {'lr': 0.0004937395670299938, 'samples': 6433792, 'steps': 12565, 'loss/train': 1.3668262958526611}
-03/04/2022 04:13:21 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/04/2022 04:13:26 - INFO - codeparrot_training - Step 12566: {'lr': 0.0004937383868193815, 'samples': 6434304, 'steps': 12566, 'loss/train': 2.1564064025878906}
-03/04/2022 04:13:29 - INFO - codeparrot_training - Step 12567: {'lr': 0.0004937372064989445, 'samples': 6434816, 'steps': 12567, 'loss/train': 1.5440365076065063}
-03/04/2022 04:13:29 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/04/2022 04:13:34 - INFO - codeparrot_training - Step 12568: {'lr': 0.0004937360260686833, 'samples': 6435328, 'steps': 12568, 'loss/train': 2.2566068172454834}
-03/04/2022 04:13:37 - INFO - codeparrot_training - Step 12569: {'lr': 0.0004937348455285983, 'samples': 6435840, 'steps': 12569, 'loss/train': 1.9924196004867554}
-03/04/2022 04:13:37 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 04:13:43 - INFO - codeparrot_training - Step 12570: {'lr': 0.0004937336648786903, 'samples': 6436352, 'steps': 12570, 'loss/train': 2.5081071853637695}
-03/04/2022 04:13:46 - INFO - codeparrot_training - Step 12571: {'lr': 0.0004937324841189595, 'samples': 6436864, 'steps': 12571, 'loss/train': 1.7875117063522339}
-03/04/2022 04:13:46 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 04:13:51 - INFO - codeparrot_training - Step 12572: {'lr': 0.0004937313032494068, 'samples': 6437376, 'steps': 12572, 'loss/train': 1.8438423871994019}
-03/04/2022 04:13:54 - INFO - codeparrot_training - Step 12573: {'lr': 0.0004937301222700324, 'samples': 6437888, 'steps': 12573, 'loss/train': 1.2368096113204956}
-03/04/2022 04:13:54 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 04:14:00 - INFO - codeparrot_training - Step 12574: {'lr': 0.0004937289411808369, 'samples': 6438400, 'steps': 12574, 'loss/train': 2.206202268600464}
-03/04/2022 04:14:03 - INFO - codeparrot_training - Step 12575: {'lr': 0.000493727759981821, 'samples': 6438912, 'steps': 12575, 'loss/train': 4.715102195739746}
-03/04/2022 04:14:05 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 04:14:08 - INFO - codeparrot_training - Step 12576: {'lr': 0.0004937265786729851, 'samples': 6439424, 'steps': 12576, 'loss/train': 1.5330569744110107}
-03/04/2022 04:14:12 - INFO - codeparrot_training - Step 12577: {'lr': 0.0004937253972543298, 'samples': 6439936, 'steps': 12577, 'loss/train': 6.787627220153809}
-03/04/2022 04:14:15 - INFO - codeparrot_training - Step 12578: {'lr': 0.0004937242157258555, 'samples': 6440448, 'steps': 12578, 'loss/train': 2.1969659328460693}
-03/04/2022 04:14:15 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/04/2022 04:14:20 - INFO - codeparrot_training - Step 12579: {'lr': 0.000493723034087563, 'samples': 6440960, 'steps': 12579, 'loss/train': 2.106642246246338}
-03/04/2022 04:14:23 - INFO - codeparrot_training - Step 12580: {'lr': 0.0004937218523394525, 'samples': 6441472, 'steps': 12580, 'loss/train': 1.8632020950317383}
-03/04/2022 04:14:23 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 04:14:29 - INFO - codeparrot_training - Step 12581: {'lr': 0.0004937206704815248, 'samples': 6441984, 'steps': 12581, 'loss/train': 1.9335122108459473}
-03/04/2022 04:14:31 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/04/2022 04:14:34 - INFO - codeparrot_training - Step 12582: {'lr': 0.0004937194885137803, 'samples': 6442496, 'steps': 12582, 'loss/train': 4.093890190124512}
-03/04/2022 04:14:37 - INFO - codeparrot_training - Step 12583: {'lr': 0.0004937183064362196, 'samples': 6443008, 'steps': 12583, 'loss/train': 1.8997818231582642}
-03/04/2022 04:14:40 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/04/2022 04:14:42 - INFO - codeparrot_training - Step 12584: {'lr': 0.0004937171242488431, 'samples': 6443520, 'steps': 12584, 'loss/train': 0.9982216358184814}
-03/04/2022 04:14:45 - INFO - codeparrot_training - Step 12585: {'lr': 0.0004937159419516515, 'samples': 6444032, 'steps': 12585, 'loss/train': 1.4910268783569336}
-03/04/2022 04:14:48 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/04/2022 04:14:51 - INFO - codeparrot_training - Step 12586: {'lr': 0.0004937147595446452, 'samples': 6444544, 'steps': 12586, 'loss/train': 2.1496427059173584}
-03/04/2022 04:14:54 - INFO - codeparrot_training - Step 12587: {'lr': 0.0004937135770278248, 'samples': 6445056, 'steps': 12587, 'loss/train': 3.047008514404297}
-03/04/2022 04:14:57 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/04/2022 04:14:59 - INFO - codeparrot_training - Step 12588: {'lr': 0.0004937123944011908, 'samples': 6445568, 'steps': 12588, 'loss/train': 2.0736377239227295}
-03/04/2022 04:15:02 - INFO - codeparrot_training - Step 12589: {'lr': 0.0004937112116647439, 'samples': 6446080, 'steps': 12589, 'loss/train': 2.1699635982513428}
-03/04/2022 04:15:05 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/04/2022 04:15:08 - INFO - codeparrot_training - Step 12590: {'lr': 0.0004937100288184843, 'samples': 6446592, 'steps': 12590, 'loss/train': 2.5799665451049805}
-03/04/2022 04:15:11 - INFO - codeparrot_training - Step 12591: {'lr': 0.0004937088458624128, 'samples': 6447104, 'steps': 12591, 'loss/train': 2.1055891513824463}
-03/04/2022 04:15:13 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/04/2022 04:15:16 - INFO - codeparrot_training - Step 12592: {'lr': 0.0004937076627965299, 'samples': 6447616, 'steps': 12592, 'loss/train': 1.7517974376678467}
-03/04/2022 04:15:19 - INFO - codeparrot_training - Step 12593: {'lr': 0.000493706479620836, 'samples': 6448128, 'steps': 12593, 'loss/train': 2.1463427543640137}
-03/04/2022 04:15:22 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 04:15:25 - INFO - codeparrot_training - Step 12594: {'lr': 0.0004937052963353318, 'samples': 6448640, 'steps': 12594, 'loss/train': 2.2173666954040527}
-03/04/2022 04:15:28 - INFO - codeparrot_training - Step 12595: {'lr': 0.0004937041129400177, 'samples': 6449152, 'steps': 12595, 'loss/train': 0.35085487365722656}
-03/04/2022 04:15:30 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/04/2022 04:15:33 - INFO - codeparrot_training - Step 12596: {'lr': 0.0004937029294348943, 'samples': 6449664, 'steps': 12596, 'loss/train': 1.9160735607147217}
-03/04/2022 04:15:36 - INFO - codeparrot_training - Step 12597: {'lr': 0.0004937017458199621, 'samples': 6450176, 'steps': 12597, 'loss/train': 2.3085482120513916}
-03/04/2022 04:15:38 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 04:15:42 - INFO - codeparrot_training - Step 12598: {'lr': 0.0004937005620952217, 'samples': 6450688, 'steps': 12598, 'loss/train': 2.2095961570739746}
-03/04/2022 04:15:45 - INFO - codeparrot_training - Step 12599: {'lr': 0.0004936993782606735, 'samples': 6451200, 'steps': 12599, 'loss/train': 2.271198272705078}
-03/04/2022 04:15:48 - INFO - codeparrot_training - Step 12600: {'lr': 0.0004936981943163182, 'samples': 6451712, 'steps': 12600, 'loss/train': 2.1437370777130127}
-03/04/2022 04:15:48 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/04/2022 04:15:53 - INFO - codeparrot_training - Step 12601: {'lr': 0.0004936970102621563, 'samples': 6452224, 'steps': 12601, 'loss/train': 2.355184316635132}
-03/04/2022 04:15:57 - INFO - codeparrot_training - Step 12602: {'lr': 0.0004936958260981883, 'samples': 6452736, 'steps': 12602, 'loss/train': 1.6819303035736084}
-03/04/2022 04:15:57 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/04/2022 04:16:02 - INFO - codeparrot_training - Step 12603: {'lr': 0.0004936946418244146, 'samples': 6453248, 'steps': 12603, 'loss/train': 2.2676069736480713}
-03/04/2022 04:16:05 - INFO - codeparrot_training - Step 12604: {'lr': 0.000493693457440836, 'samples': 6453760, 'steps': 12604, 'loss/train': 2.158519744873047}
-03/04/2022 04:16:06 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/04/2022 04:16:10 - INFO - codeparrot_training - Step 12605: {'lr': 0.0004936922729474526, 'samples': 6454272, 'steps': 12605, 'loss/train': 2.095198392868042}
-03/04/2022 04:16:13 - INFO - codeparrot_training - Step 12606: {'lr': 0.0004936910883442655, 'samples': 6454784, 'steps': 12606, 'loss/train': 2.3570797443389893}
-03/04/2022 04:16:14 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/04/2022 04:16:19 - INFO - codeparrot_training - Step 12607: {'lr': 0.0004936899036312749, 'samples': 6455296, 'steps': 12607, 'loss/train': 2.071423292160034}
-03/04/2022 04:16:22 - INFO - codeparrot_training - Step 12608: {'lr': 0.0004936887188084813, 'samples': 6455808, 'steps': 12608, 'loss/train': 2.089841365814209}
-03/04/2022 04:16:27 - INFO - codeparrot_training - Step 12609: {'lr': 0.0004936875338758855, 'samples': 6456320, 'steps': 12609, 'loss/train': 2.1677892208099365}
-03/04/2022 04:16:30 - INFO - codeparrot_training - Step 12610: {'lr': 0.0004936863488334877, 'samples': 6456832, 'steps': 12610, 'loss/train': 0.9106287360191345}
-03/04/2022 04:16:31 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 04:16:35 - INFO - codeparrot_training - Step 12611: {'lr': 0.0004936851636812886, 'samples': 6457344, 'steps': 12611, 'loss/train': 1.6832093000411987}
-03/04/2022 04:16:39 - INFO - codeparrot_training - Step 12612: {'lr': 0.0004936839784192888, 'samples': 6457856, 'steps': 12612, 'loss/train': 2.182908773422241}
-03/04/2022 04:16:39 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/04/2022 04:16:44 - INFO - codeparrot_training - Step 12613: {'lr': 0.0004936827930474887, 'samples': 6458368, 'steps': 12613, 'loss/train': 2.207611560821533}
-03/04/2022 04:16:47 - INFO - codeparrot_training - Step 12614: {'lr': 0.0004936816075658889, 'samples': 6458880, 'steps': 12614, 'loss/train': 2.611319065093994}
-03/04/2022 04:16:48 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/04/2022 04:16:52 - INFO - codeparrot_training - Step 12615: {'lr': 0.00049368042197449, 'samples': 6459392, 'steps': 12615, 'loss/train': 0.5744017958641052}
-03/04/2022 04:16:56 - INFO - codeparrot_training - Step 12616: {'lr': 0.0004936792362732924, 'samples': 6459904, 'steps': 12616, 'loss/train': 2.6973752975463867}
-03/04/2022 04:16:56 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/04/2022 04:17:01 - INFO - codeparrot_training - Step 12617: {'lr': 0.0004936780504622967, 'samples': 6460416, 'steps': 12617, 'loss/train': 2.3782169818878174}
-03/04/2022 04:17:04 - INFO - codeparrot_training - Step 12618: {'lr': 0.0004936768645415033, 'samples': 6460928, 'steps': 12618, 'loss/train': 2.3767309188842773}
-03/04/2022 04:17:05 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/04/2022 04:17:10 - INFO - codeparrot_training - Step 12619: {'lr': 0.0004936756785109131, 'samples': 6461440, 'steps': 12619, 'loss/train': 2.819331645965576}
-03/04/2022 04:17:13 - INFO - codeparrot_training - Step 12620: {'lr': 0.0004936744923705263, 'samples': 6461952, 'steps': 12620, 'loss/train': 2.130498170852661}
-03/04/2022 04:17:14 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/04/2022 04:17:18 - INFO - codeparrot_training - Step 12621: {'lr': 0.0004936733061203435, 'samples': 6462464, 'steps': 12621, 'loss/train': 1.9140150547027588}
-03/04/2022 04:17:21 - INFO - codeparrot_training - Step 12622: {'lr': 0.0004936721197603653, 'samples': 6462976, 'steps': 12622, 'loss/train': 2.330173969268799}
-03/04/2022 04:17:22 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 04:17:27 - INFO - codeparrot_training - Step 12623: {'lr': 0.0004936709332905923, 'samples': 6463488, 'steps': 12623, 'loss/train': 2.197289228439331}
-03/04/2022 04:17:30 - INFO - codeparrot_training - Step 12624: {'lr': 0.0004936697467110248, 'samples': 6464000, 'steps': 12624, 'loss/train': 2.41207218170166}
-03/04/2022 04:17:31 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 04:17:35 - INFO - codeparrot_training - Step 12625: {'lr': 0.0004936685600216635, 'samples': 6464512, 'steps': 12625, 'loss/train': 1.7583719491958618}
-03/04/2022 04:17:38 - INFO - codeparrot_training - Step 12626: {'lr': 0.0004936673732225088, 'samples': 6465024, 'steps': 12626, 'loss/train': 2.026775598526001}
-03/04/2022 04:17:39 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 04:17:43 - INFO - codeparrot_training - Step 12627: {'lr': 0.0004936661863135615, 'samples': 6465536, 'steps': 12627, 'loss/train': 0.7749806046485901}
-03/04/2022 04:17:47 - INFO - codeparrot_training - Step 12628: {'lr': 0.000493664999294822, 'samples': 6466048, 'steps': 12628, 'loss/train': 1.7964006662368774}
-03/04/2022 04:17:48 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 04:17:52 - INFO - codeparrot_training - Step 12629: {'lr': 0.0004936638121662908, 'samples': 6466560, 'steps': 12629, 'loss/train': 3.5135691165924072}
-03/04/2022 04:17:55 - INFO - codeparrot_training - Step 12630: {'lr': 0.0004936626249279683, 'samples': 6467072, 'steps': 12630, 'loss/train': 0.9751428961753845}
-03/04/2022 04:17:56 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/04/2022 04:18:00 - INFO - codeparrot_training - Step 12631: {'lr': 0.0004936614375798553, 'samples': 6467584, 'steps': 12631, 'loss/train': 1.5094530582427979}
-03/04/2022 04:18:03 - INFO - codeparrot_training - Step 12632: {'lr': 0.0004936602501219522, 'samples': 6468096, 'steps': 12632, 'loss/train': 1.7489773035049438}
-03/04/2022 04:18:05 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 04:18:09 - INFO - codeparrot_training - Step 12633: {'lr': 0.0004936590625542595, 'samples': 6468608, 'steps': 12633, 'loss/train': 1.6242650747299194}
-03/04/2022 04:18:12 - INFO - codeparrot_training - Step 12634: {'lr': 0.0004936578748767779, 'samples': 6469120, 'steps': 12634, 'loss/train': 1.5198529958724976}
-03/04/2022 04:18:13 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/04/2022 04:18:18 - INFO - codeparrot_training - Step 12635: {'lr': 0.0004936566870895078, 'samples': 6469632, 'steps': 12635, 'loss/train': 2.1568479537963867}
-03/04/2022 04:18:21 - INFO - codeparrot_training - Step 12636: {'lr': 0.0004936554991924496, 'samples': 6470144, 'steps': 12636, 'loss/train': 1.92460036277771}
-03/04/2022 04:18:24 - INFO - codeparrot_training - Step 12637: {'lr': 0.0004936543111856041, 'samples': 6470656, 'steps': 12637, 'loss/train': 2.2580182552337646}
-03/04/2022 04:18:25 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/04/2022 04:18:29 - INFO - codeparrot_training - Step 12638: {'lr': 0.0004936531230689717, 'samples': 6471168, 'steps': 12638, 'loss/train': 1.7452608346939087}
-03/04/2022 04:18:33 - INFO - codeparrot_training - Step 12639: {'lr': 0.000493651934842553, 'samples': 6471680, 'steps': 12639, 'loss/train': 1.468324065208435}
-03/04/2022 04:18:34 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/04/2022 04:18:38 - INFO - codeparrot_training - Step 12640: {'lr': 0.0004936507465063486, 'samples': 6472192, 'steps': 12640, 'loss/train': 2.0991663932800293}
-03/04/2022 04:18:41 - INFO - codeparrot_training - Step 12641: {'lr': 0.0004936495580603588, 'samples': 6472704, 'steps': 12641, 'loss/train': 1.9780066013336182}
-03/04/2022 04:18:42 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 04:18:46 - INFO - codeparrot_training - Step 12642: {'lr': 0.0004936483695045842, 'samples': 6473216, 'steps': 12642, 'loss/train': 2.493678569793701}
-03/04/2022 04:18:49 - INFO - codeparrot_training - Step 12643: {'lr': 0.0004936471808390254, 'samples': 6473728, 'steps': 12643, 'loss/train': 2.0757224559783936}
-03/04/2022 04:18:51 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 04:18:55 - INFO - codeparrot_training - Step 12644: {'lr': 0.0004936459920636832, 'samples': 6474240, 'steps': 12644, 'loss/train': 1.6291682720184326}
-03/04/2022 04:18:58 - INFO - codeparrot_training - Step 12645: {'lr': 0.0004936448031785576, 'samples': 6474752, 'steps': 12645, 'loss/train': 1.2606345415115356}
-03/04/2022 04:18:59 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 04:19:03 - INFO - codeparrot_training - Step 12646: {'lr': 0.0004936436141836496, 'samples': 6475264, 'steps': 12646, 'loss/train': 2.1142935752868652}
-03/04/2022 04:19:06 - INFO - codeparrot_training - Step 12647: {'lr': 0.0004936424250789594, 'samples': 6475776, 'steps': 12647, 'loss/train': 2.67962908744812}
-03/04/2022 04:19:07 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/04/2022 04:19:11 - INFO - codeparrot_training - Step 12648: {'lr': 0.0004936412358644878, 'samples': 6476288, 'steps': 12648, 'loss/train': 1.8164267539978027}
-03/04/2022 04:19:15 - INFO - codeparrot_training - Step 12649: {'lr': 0.0004936400465402351, 'samples': 6476800, 'steps': 12649, 'loss/train': 2.94624400138855}
-03/04/2022 04:19:16 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/04/2022 04:19:20 - INFO - codeparrot_training - Step 12650: {'lr': 0.0004936388571062021, 'samples': 6477312, 'steps': 12650, 'loss/train': 1.836888313293457}
-03/04/2022 04:19:23 - INFO - codeparrot_training - Step 12651: {'lr': 0.0004936376675623892, 'samples': 6477824, 'steps': 12651, 'loss/train': 2.6672286987304688}
-03/04/2022 04:19:24 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/04/2022 04:19:28 - INFO - codeparrot_training - Step 12652: {'lr': 0.0004936364779087967, 'samples': 6478336, 'steps': 12652, 'loss/train': 1.7388650178909302}
-03/04/2022 04:19:31 - INFO - codeparrot_training - Step 12653: {'lr': 0.0004936352881454256, 'samples': 6478848, 'steps': 12653, 'loss/train': 2.5869481563568115}
-03/04/2022 04:19:33 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/04/2022 04:19:37 - INFO - codeparrot_training - Step 12654: {'lr': 0.000493634098272276, 'samples': 6479360, 'steps': 12654, 'loss/train': 2.002232789993286}
-03/04/2022 04:19:40 - INFO - codeparrot_training - Step 12655: {'lr': 0.0004936329082893488, 'samples': 6479872, 'steps': 12655, 'loss/train': 1.129018783569336}
-03/04/2022 04:19:41 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/04/2022 04:19:45 - INFO - codeparrot_training - Step 12656: {'lr': 0.0004936317181966443, 'samples': 6480384, 'steps': 12656, 'loss/train': 1.76931893825531}
-03/04/2022 04:19:48 - INFO - codeparrot_training - Step 12657: {'lr': 0.000493630527994163, 'samples': 6480896, 'steps': 12657, 'loss/train': 1.5363266468048096}
-03/04/2022 04:19:49 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/04/2022 04:19:54 - INFO - codeparrot_training - Step 12658: {'lr': 0.0004936293376819058, 'samples': 6481408, 'steps': 12658, 'loss/train': 1.5522655248641968}
-03/04/2022 04:19:57 - INFO - codeparrot_training - Step 12659: {'lr': 0.0004936281472598728, 'samples': 6481920, 'steps': 12659, 'loss/train': 1.432882308959961}
-03/04/2022 04:19:58 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 04:20:02 - INFO - codeparrot_training - Step 12660: {'lr': 0.0004936269567280648, 'samples': 6482432, 'steps': 12660, 'loss/train': 1.9478416442871094}
-03/04/2022 04:20:05 - INFO - codeparrot_training - Step 12661: {'lr': 0.0004936257660864822, 'samples': 6482944, 'steps': 12661, 'loss/train': 2.137281894683838}
-03/04/2022 04:20:06 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/04/2022 04:20:10 - INFO - codeparrot_training - Step 12662: {'lr': 0.0004936245753351256, 'samples': 6483456, 'steps': 12662, 'loss/train': 1.0395640134811401}
-03/04/2022 04:20:14 - INFO - codeparrot_training - Step 12663: {'lr': 0.0004936233844739955, 'samples': 6483968, 'steps': 12663, 'loss/train': 2.1839962005615234}
-03/04/2022 04:20:14 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 04:20:19 - INFO - codeparrot_training - Step 12664: {'lr': 0.0004936221935030924, 'samples': 6484480, 'steps': 12664, 'loss/train': 2.086862087249756}
-03/04/2022 04:20:22 - INFO - codeparrot_training - Step 12665: {'lr': 0.000493621002422417, 'samples': 6484992, 'steps': 12665, 'loss/train': 1.9809684753417969}
-03/04/2022 04:20:22 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 04:20:27 - INFO - codeparrot_training - Step 12666: {'lr': 0.0004936198112319698, 'samples': 6485504, 'steps': 12666, 'loss/train': 1.9668333530426025}
-03/04/2022 04:20:30 - INFO - codeparrot_training - Step 12667: {'lr': 0.0004936186199317511, 'samples': 6486016, 'steps': 12667, 'loss/train': 2.559011459350586}
-03/04/2022 04:20:31 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/04/2022 04:20:36 - INFO - codeparrot_training - Step 12668: {'lr': 0.0004936174285217618, 'samples': 6486528, 'steps': 12668, 'loss/train': 1.9804596900939941}
-03/04/2022 04:20:39 - INFO - codeparrot_training - Step 12669: {'lr': 0.0004936162370020021, 'samples': 6487040, 'steps': 12669, 'loss/train': 1.5521483421325684}
-03/04/2022 04:20:39 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/04/2022 04:20:44 - INFO - codeparrot_training - Step 12670: {'lr': 0.0004936150453724727, 'samples': 6487552, 'steps': 12670, 'loss/train': 1.4730144739151}
-03/04/2022 04:20:47 - INFO - codeparrot_training - Step 12671: {'lr': 0.0004936138536331742, 'samples': 6488064, 'steps': 12671, 'loss/train': 2.770387649536133}
-03/04/2022 04:20:47 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 04:20:52 - INFO - codeparrot_training - Step 12672: {'lr': 0.000493612661784107, 'samples': 6488576, 'steps': 12672, 'loss/train': 2.113713264465332}
-03/04/2022 04:20:56 - INFO - codeparrot_training - Step 12673: {'lr': 0.0004936114698252717, 'samples': 6489088, 'steps': 12673, 'loss/train': 1.6132450103759766}
-03/04/2022 04:20:56 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/04/2022 04:21:01 - INFO - codeparrot_training - Step 12674: {'lr': 0.0004936102777566688, 'samples': 6489600, 'steps': 12674, 'loss/train': 1.5662363767623901}
-03/04/2022 04:21:04 - INFO - codeparrot_training - Step 12675: {'lr': 0.0004936090855782989, 'samples': 6490112, 'steps': 12675, 'loss/train': 1.8140974044799805}
-03/04/2022 04:21:04 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 04:21:09 - INFO - codeparrot_training - Step 12676: {'lr': 0.0004936078932901625, 'samples': 6490624, 'steps': 12676, 'loss/train': 1.9631303548812866}
-03/04/2022 04:21:12 - INFO - codeparrot_training - Step 12677: {'lr': 0.0004936067008922602, 'samples': 6491136, 'steps': 12677, 'loss/train': 2.080972671508789}
-03/04/2022 04:21:13 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 04:21:18 - INFO - codeparrot_training - Step 12678: {'lr': 0.0004936055083845924, 'samples': 6491648, 'steps': 12678, 'loss/train': 2.7485058307647705}
-03/04/2022 04:21:21 - INFO - codeparrot_training - Step 12679: {'lr': 0.0004936043157671597, 'samples': 6492160, 'steps': 12679, 'loss/train': 2.14570951461792}
-03/04/2022 04:21:21 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/04/2022 04:21:26 - INFO - codeparrot_training - Step 12680: {'lr': 0.0004936031230399628, 'samples': 6492672, 'steps': 12680, 'loss/train': 1.482016682624817}
-03/04/2022 04:21:29 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/04/2022 04:21:32 - INFO - codeparrot_training - Step 12681: {'lr': 0.000493601930203002, 'samples': 6493184, 'steps': 12681, 'loss/train': 1.7530367374420166}
-03/04/2022 04:21:35 - INFO - codeparrot_training - Step 12682: {'lr': 0.0004936007372562778, 'samples': 6493696, 'steps': 12682, 'loss/train': 1.5697993040084839}
-03/04/2022 04:21:38 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 04:21:40 - INFO - codeparrot_training - Step 12683: {'lr': 0.0004935995441997911, 'samples': 6494208, 'steps': 12683, 'loss/train': 2.679781198501587}
-03/04/2022 04:21:44 - INFO - codeparrot_training - Step 12684: {'lr': 0.000493598351033542, 'samples': 6494720, 'steps': 12684, 'loss/train': 1.6817128658294678}
-03/04/2022 04:21:47 - INFO - codeparrot_training - Step 12685: {'lr': 0.0004935971577575313, 'samples': 6495232, 'steps': 12685, 'loss/train': 1.9391961097717285}
-03/04/2022 04:21:47 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/04/2022 04:21:52 - INFO - codeparrot_training - Step 12686: {'lr': 0.0004935959643717595, 'samples': 6495744, 'steps': 12686, 'loss/train': 2.3060622215270996}
-03/04/2022 04:21:55 - INFO - codeparrot_training - Step 12687: {'lr': 0.0004935947708762272, 'samples': 6496256, 'steps': 12687, 'loss/train': 1.7743350267410278}
-03/04/2022 04:21:56 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/04/2022 04:22:00 - INFO - codeparrot_training - Step 12688: {'lr': 0.0004935935772709348, 'samples': 6496768, 'steps': 12688, 'loss/train': 1.1759097576141357}
-03/04/2022 04:22:04 - INFO - codeparrot_training - Step 12689: {'lr': 0.0004935923835558829, 'samples': 6497280, 'steps': 12689, 'loss/train': 1.9956955909729004}
-03/04/2022 04:22:04 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/04/2022 04:22:09 - INFO - codeparrot_training - Step 12690: {'lr': 0.0004935911897310719, 'samples': 6497792, 'steps': 12690, 'loss/train': 1.6251095533370972}
-03/04/2022 04:22:12 - INFO - codeparrot_training - Step 12691: {'lr': 0.0004935899957965027, 'samples': 6498304, 'steps': 12691, 'loss/train': 1.7358126640319824}
-03/04/2022 04:22:13 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 04:22:17 - INFO - codeparrot_training - Step 12692: {'lr': 0.0004935888017521754, 'samples': 6498816, 'steps': 12692, 'loss/train': 2.570549726486206}
-03/04/2022 04:22:20 - INFO - codeparrot_training - Step 12693: {'lr': 0.0004935876075980908, 'samples': 6499328, 'steps': 12693, 'loss/train': 2.3149847984313965}
-03/04/2022 04:22:21 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 04:22:26 - INFO - codeparrot_training - Step 12694: {'lr': 0.0004935864133342495, 'samples': 6499840, 'steps': 12694, 'loss/train': 0.7651524543762207}
-03/04/2022 04:22:29 - INFO - codeparrot_training - Step 12695: {'lr': 0.0004935852189606517, 'samples': 6500352, 'steps': 12695, 'loss/train': 2.4453890323638916}
-03/04/2022 04:22:33 - INFO - codeparrot_training - Step 12696: {'lr': 0.0004935840244772984, 'samples': 6500864, 'steps': 12696, 'loss/train': 2.4584670066833496}
-03/04/2022 04:22:33 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 04:22:38 - INFO - codeparrot_training - Step 12697: {'lr': 0.0004935828298841898, 'samples': 6501376, 'steps': 12697, 'loss/train': 2.2843289375305176}
-03/04/2022 04:22:41 - INFO - codeparrot_training - Step 12698: {'lr': 0.0004935816351813265, 'samples': 6501888, 'steps': 12698, 'loss/train': 2.432528495788574}
-03/04/2022 04:22:41 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 04:22:46 - INFO - codeparrot_training - Step 12699: {'lr': 0.0004935804403687091, 'samples': 6502400, 'steps': 12699, 'loss/train': 0.24816182255744934}
-03/04/2022 04:22:49 - INFO - codeparrot_training - Step 12700: {'lr': 0.0004935792454463381, 'samples': 6502912, 'steps': 12700, 'loss/train': 2.195107936859131}
-03/04/2022 04:22:49 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/04/2022 04:22:55 - INFO - codeparrot_training - Step 12701: {'lr': 0.000493578050414214, 'samples': 6503424, 'steps': 12701, 'loss/train': 2.306432008743286}
-03/04/2022 04:22:58 - INFO - codeparrot_training - Step 12702: {'lr': 0.0004935768552723375, 'samples': 6503936, 'steps': 12702, 'loss/train': 1.4910392761230469}
-03/04/2022 04:22:58 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/04/2022 04:23:03 - INFO - codeparrot_training - Step 12703: {'lr': 0.000493575660020709, 'samples': 6504448, 'steps': 12703, 'loss/train': 1.6783604621887207}
-03/04/2022 04:23:06 - INFO - codeparrot_training - Step 12704: {'lr': 0.000493574464659329, 'samples': 6504960, 'steps': 12704, 'loss/train': 2.255127429962158}
-03/04/2022 04:23:06 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/04/2022 04:23:11 - INFO - codeparrot_training - Step 12705: {'lr': 0.0004935732691881981, 'samples': 6505472, 'steps': 12705, 'loss/train': 2.270594596862793}
-03/04/2022 04:23:15 - INFO - codeparrot_training - Step 12706: {'lr': 0.0004935720736073169, 'samples': 6505984, 'steps': 12706, 'loss/train': 0.3772483170032501}
-03/04/2022 04:23:15 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/04/2022 04:23:20 - INFO - codeparrot_training - Step 12707: {'lr': 0.0004935708779166859, 'samples': 6506496, 'steps': 12707, 'loss/train': 0.9934217929840088}
-03/04/2022 04:23:23 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/04/2022 04:23:25 - INFO - codeparrot_training - Step 12708: {'lr': 0.0004935696821163056, 'samples': 6507008, 'steps': 12708, 'loss/train': 1.6736646890640259}
-03/04/2022 04:23:28 - INFO - codeparrot_training - Step 12709: {'lr': 0.0004935684862061766, 'samples': 6507520, 'steps': 12709, 'loss/train': 1.9654148817062378}
-03/04/2022 04:23:31 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/04/2022 04:23:34 - INFO - codeparrot_training - Step 12710: {'lr': 0.0004935672901862993, 'samples': 6508032, 'steps': 12710, 'loss/train': 2.421780824661255}
-03/04/2022 04:23:37 - INFO - codeparrot_training - Step 12711: {'lr': 0.0004935660940566744, 'samples': 6508544, 'steps': 12711, 'loss/train': 2.3809282779693604}
-03/04/2022 04:23:40 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 04:23:42 - INFO - codeparrot_training - Step 12712: {'lr': 0.0004935648978173024, 'samples': 6509056, 'steps': 12712, 'loss/train': 1.5225189924240112}
-03/04/2022 04:23:45 - INFO - codeparrot_training - Step 12713: {'lr': 0.0004935637014681837, 'samples': 6509568, 'steps': 12713, 'loss/train': 2.5576019287109375}
-03/04/2022 04:23:48 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/04/2022 04:23:50 - INFO - codeparrot_training - Step 12714: {'lr': 0.0004935625050093191, 'samples': 6510080, 'steps': 12714, 'loss/train': 1.6767605543136597}
-03/04/2022 04:23:54 - INFO - codeparrot_training - Step 12715: {'lr': 0.000493561308440709, 'samples': 6510592, 'steps': 12715, 'loss/train': 2.0629842281341553}
-03/04/2022 04:23:56 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/04/2022 04:23:59 - INFO - codeparrot_training - Step 12716: {'lr': 0.0004935601117623538, 'samples': 6511104, 'steps': 12716, 'loss/train': 2.2415945529937744}
-03/04/2022 04:24:02 - INFO - codeparrot_training - Step 12717: {'lr': 0.0004935589149742542, 'samples': 6511616, 'steps': 12717, 'loss/train': 1.4218863248825073}
-03/04/2022 04:24:05 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 04:24:07 - INFO - codeparrot_training - Step 12718: {'lr': 0.0004935577180764108, 'samples': 6512128, 'steps': 12718, 'loss/train': 0.6211639642715454}
-03/04/2022 04:24:11 - INFO - codeparrot_training - Step 12719: {'lr': 0.000493556521068824, 'samples': 6512640, 'steps': 12719, 'loss/train': 2.0466134548187256}
-03/04/2022 04:24:13 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 04:24:16 - INFO - codeparrot_training - Step 12720: {'lr': 0.0004935553239514943, 'samples': 6513152, 'steps': 12720, 'loss/train': 0.9712135195732117}
-03/04/2022 04:24:19 - INFO - codeparrot_training - Step 12721: {'lr': 0.0004935541267244225, 'samples': 6513664, 'steps': 12721, 'loss/train': 1.7078291177749634}
-03/04/2022 04:24:22 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/04/2022 04:24:24 - INFO - codeparrot_training - Step 12722: {'lr': 0.0004935529293876088, 'samples': 6514176, 'steps': 12722, 'loss/train': 2.2501487731933594}
-03/04/2022 04:24:27 - INFO - codeparrot_training - Step 12723: {'lr': 0.000493551731941054, 'samples': 6514688, 'steps': 12723, 'loss/train': 2.141996383666992}
-03/04/2022 04:24:31 - INFO - codeparrot_training - Step 12724: {'lr': 0.0004935505343847586, 'samples': 6515200, 'steps': 12724, 'loss/train': 1.449387788772583}
-03/04/2022 04:24:31 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 04:24:36 - INFO - codeparrot_training - Step 12725: {'lr': 0.000493549336718723, 'samples': 6515712, 'steps': 12725, 'loss/train': 1.412919521331787}
-03/04/2022 04:24:39 - INFO - codeparrot_training - Step 12726: {'lr': 0.0004935481389429479, 'samples': 6516224, 'steps': 12726, 'loss/train': 1.9244425296783447}
-03/04/2022 04:24:39 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 04:24:44 - INFO - codeparrot_training - Step 12727: {'lr': 0.0004935469410574337, 'samples': 6516736, 'steps': 12727, 'loss/train': 6.122863292694092}
-03/04/2022 04:24:48 - INFO - codeparrot_training - Step 12728: {'lr': 0.000493545743062181, 'samples': 6517248, 'steps': 12728, 'loss/train': 2.5233781337738037}
-03/04/2022 04:24:49 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/04/2022 04:24:53 - INFO - codeparrot_training - Step 12729: {'lr': 0.0004935445449571903, 'samples': 6517760, 'steps': 12729, 'loss/train': 1.9022235870361328}
-03/04/2022 04:24:56 - INFO - codeparrot_training - Step 12730: {'lr': 0.0004935433467424624, 'samples': 6518272, 'steps': 12730, 'loss/train': 1.1086763143539429}
-03/04/2022 04:24:58 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/04/2022 04:25:02 - INFO - codeparrot_training - Step 12731: {'lr': 0.0004935421484179974, 'samples': 6518784, 'steps': 12731, 'loss/train': 1.4788905382156372}
-03/04/2022 04:25:05 - INFO - codeparrot_training - Step 12732: {'lr': 0.0004935409499837962, 'samples': 6519296, 'steps': 12732, 'loss/train': 2.3095755577087402}
-03/04/2022 04:25:07 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 04:25:10 - INFO - codeparrot_training - Step 12733: {'lr': 0.0004935397514398591, 'samples': 6519808, 'steps': 12733, 'loss/train': 2.3942220211029053}
-03/04/2022 04:25:13 - INFO - codeparrot_training - Step 12734: {'lr': 0.0004935385527861869, 'samples': 6520320, 'steps': 12734, 'loss/train': 2.2465720176696777}
-03/04/2022 04:25:15 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/04/2022 04:25:18 - INFO - codeparrot_training - Step 12735: {'lr': 0.0004935373540227798, 'samples': 6520832, 'steps': 12735, 'loss/train': 2.197955846786499}
-03/04/2022 04:25:22 - INFO - codeparrot_training - Step 12736: {'lr': 0.0004935361551496387, 'samples': 6521344, 'steps': 12736, 'loss/train': 1.780476450920105}
-03/04/2022 04:25:23 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 04:25:27 - INFO - codeparrot_training - Step 12737: {'lr': 0.0004935349561667638, 'samples': 6521856, 'steps': 12737, 'loss/train': 1.5530238151550293}
-03/04/2022 04:25:30 - INFO - codeparrot_training - Step 12738: {'lr': 0.000493533757074156, 'samples': 6522368, 'steps': 12738, 'loss/train': 2.4209506511688232}
-03/04/2022 04:25:32 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/04/2022 04:25:35 - INFO - codeparrot_training - Step 12739: {'lr': 0.0004935325578718155, 'samples': 6522880, 'steps': 12739, 'loss/train': 2.0248353481292725}
-03/04/2022 04:25:38 - INFO - codeparrot_training - Step 12740: {'lr': 0.000493531358559743, 'samples': 6523392, 'steps': 12740, 'loss/train': 2.20406174659729}
-03/04/2022 04:25:40 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/04/2022 04:25:44 - INFO - codeparrot_training - Step 12741: {'lr': 0.0004935301591379391, 'samples': 6523904, 'steps': 12741, 'loss/train': 2.454343795776367}
-03/04/2022 04:25:47 - INFO - codeparrot_training - Step 12742: {'lr': 0.0004935289596064042, 'samples': 6524416, 'steps': 12742, 'loss/train': 2.499458074569702}
-03/04/2022 04:25:48 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 04:25:52 - INFO - codeparrot_training - Step 12743: {'lr': 0.0004935277599651389, 'samples': 6524928, 'steps': 12743, 'loss/train': 1.6476699113845825}
-03/04/2022 04:25:55 - INFO - codeparrot_training - Step 12744: {'lr': 0.0004935265602141437, 'samples': 6525440, 'steps': 12744, 'loss/train': 1.3443914651870728}
-03/04/2022 04:25:57 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/04/2022 04:26:00 - INFO - codeparrot_training - Step 12745: {'lr': 0.0004935253603534193, 'samples': 6525952, 'steps': 12745, 'loss/train': 2.7698588371276855}
-03/04/2022 04:26:04 - INFO - codeparrot_training - Step 12746: {'lr': 0.0004935241603829661, 'samples': 6526464, 'steps': 12746, 'loss/train': 1.8636095523834229}
-03/04/2022 04:26:05 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/04/2022 04:26:09 - INFO - codeparrot_training - Step 12747: {'lr': 0.0004935229603027847, 'samples': 6526976, 'steps': 12747, 'loss/train': 2.0277040004730225}
-03/04/2022 04:26:12 - INFO - codeparrot_training - Step 12748: {'lr': 0.0004935217601128755, 'samples': 6527488, 'steps': 12748, 'loss/train': 2.1625733375549316}
-03/04/2022 04:26:13 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 04:26:17 - INFO - codeparrot_training - Step 12749: {'lr': 0.0004935205598132393, 'samples': 6528000, 'steps': 12749, 'loss/train': 1.5745259523391724}
-03/04/2022 04:26:20 - INFO - codeparrot_training - Step 12750: {'lr': 0.0004935193594038764, 'samples': 6528512, 'steps': 12750, 'loss/train': 1.8203521966934204}
-03/04/2022 04:26:22 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 04:26:26 - INFO - codeparrot_training - Step 12751: {'lr': 0.0004935181588847876, 'samples': 6529024, 'steps': 12751, 'loss/train': 2.079998016357422}
-03/04/2022 04:26:29 - INFO - codeparrot_training - Step 12752: {'lr': 0.0004935169582559731, 'samples': 6529536, 'steps': 12752, 'loss/train': 1.4038704633712769}
-03/04/2022 04:26:30 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 04:26:34 - INFO - codeparrot_training - Step 12753: {'lr': 0.0004935157575174336, 'samples': 6530048, 'steps': 12753, 'loss/train': 2.218096971511841}
-03/04/2022 04:26:37 - INFO - codeparrot_training - Step 12754: {'lr': 0.0004935145566691698, 'samples': 6530560, 'steps': 12754, 'loss/train': 1.5549348592758179}
-03/04/2022 04:26:38 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 04:26:42 - INFO - codeparrot_training - Step 12755: {'lr': 0.000493513355711182, 'samples': 6531072, 'steps': 12755, 'loss/train': 1.9340242147445679}
-03/04/2022 04:26:46 - INFO - codeparrot_training - Step 12756: {'lr': 0.0004935121546434708, 'samples': 6531584, 'steps': 12756, 'loss/train': 0.5391159653663635}
-03/04/2022 04:26:47 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 04:26:51 - INFO - codeparrot_training - Step 12757: {'lr': 0.0004935109534660368, 'samples': 6532096, 'steps': 12757, 'loss/train': 2.2920689582824707}
-03/04/2022 04:26:54 - INFO - codeparrot_training - Step 12758: {'lr': 0.0004935097521788805, 'samples': 6532608, 'steps': 12758, 'loss/train': 2.6860945224761963}
-03/04/2022 04:26:55 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/04/2022 04:26:59 - INFO - codeparrot_training - Step 12759: {'lr': 0.0004935085507820026, 'samples': 6533120, 'steps': 12759, 'loss/train': 1.694554328918457}
-03/04/2022 04:27:02 - INFO - codeparrot_training - Step 12760: {'lr': 0.0004935073492754034, 'samples': 6533632, 'steps': 12760, 'loss/train': 2.041459798812866}
-03/04/2022 04:27:03 - INFO - codeparrot_training - Skipping example with length 158 (seq_length=1024)
-03/04/2022 04:27:08 - INFO - codeparrot_training - Step 12761: {'lr': 0.0004935061476590835, 'samples': 6534144, 'steps': 12761, 'loss/train': 1.678067684173584}
-03/04/2022 04:27:11 - INFO - codeparrot_training - Step 12762: {'lr': 0.0004935049459330437, 'samples': 6534656, 'steps': 12762, 'loss/train': 1.5365288257598877}
-03/04/2022 04:27:11 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/04/2022 04:27:16 - INFO - codeparrot_training - Step 12763: {'lr': 0.0004935037440972841, 'samples': 6535168, 'steps': 12763, 'loss/train': 2.8315958976745605}
-03/04/2022 04:27:19 - INFO - codeparrot_training - Step 12764: {'lr': 0.0004935025421518056, 'samples': 6535680, 'steps': 12764, 'loss/train': 2.2074975967407227}
-03/04/2022 04:27:20 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 04:27:24 - INFO - codeparrot_training - Step 12765: {'lr': 0.0004935013400966086, 'samples': 6536192, 'steps': 12765, 'loss/train': 0.7049955129623413}
-03/04/2022 04:27:27 - INFO - codeparrot_training - Step 12766: {'lr': 0.0004935001379316935, 'samples': 6536704, 'steps': 12766, 'loss/train': 1.881868600845337}
-03/04/2022 04:27:28 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/04/2022 04:27:33 - INFO - codeparrot_training - Step 12767: {'lr': 0.0004934989356570611, 'samples': 6537216, 'steps': 12767, 'loss/train': 1.9435499906539917}
-03/04/2022 04:27:36 - INFO - codeparrot_training - Step 12768: {'lr': 0.0004934977332727118, 'samples': 6537728, 'steps': 12768, 'loss/train': 2.110252857208252}
-03/04/2022 04:27:37 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 04:27:41 - INFO - codeparrot_training - Step 12769: {'lr': 0.0004934965307786464, 'samples': 6538240, 'steps': 12769, 'loss/train': 1.9647458791732788}
-03/04/2022 04:27:44 - INFO - codeparrot_training - Step 12770: {'lr': 0.0004934953281748649, 'samples': 6538752, 'steps': 12770, 'loss/train': 2.308789014816284}
-03/04/2022 04:27:45 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/04/2022 04:27:50 - INFO - codeparrot_training - Step 12771: {'lr': 0.0004934941254613684, 'samples': 6539264, 'steps': 12771, 'loss/train': 1.9724485874176025}
-03/04/2022 04:27:53 - INFO - codeparrot_training - Step 12772: {'lr': 0.0004934929226381572, 'samples': 6539776, 'steps': 12772, 'loss/train': 1.6419013738632202}
-03/04/2022 04:27:53 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 04:27:58 - INFO - codeparrot_training - Step 12773: {'lr': 0.0004934917197052317, 'samples': 6540288, 'steps': 12773, 'loss/train': 1.6504061222076416}
-03/04/2022 04:28:01 - INFO - codeparrot_training - Step 12774: {'lr': 0.0004934905166625926, 'samples': 6540800, 'steps': 12774, 'loss/train': 2.382019281387329}
-03/04/2022 04:28:02 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/04/2022 04:28:06 - INFO - codeparrot_training - Step 12775: {'lr': 0.0004934893135102405, 'samples': 6541312, 'steps': 12775, 'loss/train': 2.0183069705963135}
-03/04/2022 04:28:10 - INFO - codeparrot_training - Step 12776: {'lr': 0.0004934881102481759, 'samples': 6541824, 'steps': 12776, 'loss/train': 1.9957581758499146}
-03/04/2022 04:28:10 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 04:28:15 - INFO - codeparrot_training - Step 12777: {'lr': 0.0004934869068763992, 'samples': 6542336, 'steps': 12777, 'loss/train': 1.437056303024292}
-03/04/2022 04:28:18 - INFO - codeparrot_training - Step 12778: {'lr': 0.0004934857033949112, 'samples': 6542848, 'steps': 12778, 'loss/train': 1.200946569442749}
-03/04/2022 04:28:19 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/04/2022 04:28:23 - INFO - codeparrot_training - Step 12779: {'lr': 0.0004934844998037122, 'samples': 6543360, 'steps': 12779, 'loss/train': 1.1979596614837646}
-03/04/2022 04:28:27 - INFO - codeparrot_training - Step 12780: {'lr': 0.0004934832961028028, 'samples': 6543872, 'steps': 12780, 'loss/train': 2.241852283477783}
-03/04/2022 04:28:27 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/04/2022 04:28:32 - INFO - codeparrot_training - Step 12781: {'lr': 0.0004934820922921836, 'samples': 6544384, 'steps': 12781, 'loss/train': 2.6587319374084473}
-03/04/2022 04:28:35 - INFO - codeparrot_training - Step 12782: {'lr': 0.0004934808883718553, 'samples': 6544896, 'steps': 12782, 'loss/train': 2.3522863388061523}
-03/04/2022 04:28:35 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 04:28:40 - INFO - codeparrot_training - Step 12783: {'lr': 0.0004934796843418181, 'samples': 6545408, 'steps': 12783, 'loss/train': 2.475278377532959}
-03/04/2022 04:28:43 - INFO - codeparrot_training - Step 12784: {'lr': 0.0004934784802020728, 'samples': 6545920, 'steps': 12784, 'loss/train': 2.145671844482422}
-03/04/2022 04:28:44 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/04/2022 04:28:49 - INFO - codeparrot_training - Step 12785: {'lr': 0.0004934772759526198, 'samples': 6546432, 'steps': 12785, 'loss/train': 2.2203269004821777}
-03/04/2022 04:28:52 - INFO - codeparrot_training - Step 12786: {'lr': 0.0004934760715934597, 'samples': 6546944, 'steps': 12786, 'loss/train': 2.3994784355163574}
-03/04/2022 04:28:54 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/04/2022 04:28:58 - INFO - codeparrot_training - Step 12787: {'lr': 0.0004934748671245931, 'samples': 6547456, 'steps': 12787, 'loss/train': 2.037107229232788}
-03/04/2022 04:29:01 - INFO - codeparrot_training - Step 12788: {'lr': 0.0004934736625460203, 'samples': 6547968, 'steps': 12788, 'loss/train': 1.7449066638946533}
-03/04/2022 04:29:03 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 04:29:06 - INFO - codeparrot_training - Step 12789: {'lr': 0.0004934724578577422, 'samples': 6548480, 'steps': 12789, 'loss/train': 2.1591532230377197}
-03/04/2022 04:29:10 - INFO - codeparrot_training - Step 12790: {'lr': 0.0004934712530597591, 'samples': 6548992, 'steps': 12790, 'loss/train': 1.929029107093811}
-03/04/2022 04:29:12 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 04:29:15 - INFO - codeparrot_training - Step 12791: {'lr': 0.0004934700481520717, 'samples': 6549504, 'steps': 12791, 'loss/train': 1.996983528137207}
-03/04/2022 04:29:18 - INFO - codeparrot_training - Step 12792: {'lr': 0.0004934688431346804, 'samples': 6550016, 'steps': 12792, 'loss/train': 2.1153554916381836}
-03/04/2022 04:29:20 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/04/2022 04:29:24 - INFO - codeparrot_training - Step 12793: {'lr': 0.0004934676380075857, 'samples': 6550528, 'steps': 12793, 'loss/train': 0.6961735486984253}
-03/04/2022 04:29:27 - INFO - codeparrot_training - Step 12794: {'lr': 0.0004934664327707884, 'samples': 6551040, 'steps': 12794, 'loss/train': 1.8047001361846924}
-03/04/2022 04:29:29 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/04/2022 04:29:32 - INFO - codeparrot_training - Step 12795: {'lr': 0.0004934652274242888, 'samples': 6551552, 'steps': 12795, 'loss/train': 1.6523401737213135}
-03/04/2022 04:29:35 - INFO - codeparrot_training - Step 12796: {'lr': 0.0004934640219680875, 'samples': 6552064, 'steps': 12796, 'loss/train': 1.7321748733520508}
-03/04/2022 04:29:37 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/04/2022 04:29:40 - INFO - codeparrot_training - Step 12797: {'lr': 0.0004934628164021851, 'samples': 6552576, 'steps': 12797, 'loss/train': 1.7954273223876953}
-03/04/2022 04:29:44 - INFO - codeparrot_training - Step 12798: {'lr': 0.0004934616107265821, 'samples': 6553088, 'steps': 12798, 'loss/train': 2.088909387588501}
-03/04/2022 04:29:45 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 04:29:49 - INFO - codeparrot_training - Step 12799: {'lr': 0.0004934604049412791, 'samples': 6553600, 'steps': 12799, 'loss/train': 2.0505998134613037}
-03/04/2022 04:29:52 - INFO - codeparrot_training - Step 12800: {'lr': 0.0004934591990462766, 'samples': 6554112, 'steps': 12800, 'loss/train': 1.9778379201889038}
-03/04/2022 04:29:54 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/04/2022 04:29:57 - INFO - codeparrot_training - Step 12801: {'lr': 0.0004934579930415751, 'samples': 6554624, 'steps': 12801, 'loss/train': 0.43504270911216736}
-03/04/2022 04:30:00 - INFO - codeparrot_training - Step 12802: {'lr': 0.0004934567869271751, 'samples': 6555136, 'steps': 12802, 'loss/train': 1.701705813407898}
-03/04/2022 04:30:02 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 04:30:06 - INFO - codeparrot_training - Step 12803: {'lr': 0.0004934555807030774, 'samples': 6555648, 'steps': 12803, 'loss/train': 2.6298270225524902}
-03/04/2022 04:30:09 - INFO - codeparrot_training - Step 12804: {'lr': 0.0004934543743692822, 'samples': 6556160, 'steps': 12804, 'loss/train': 2.146831512451172}
-03/04/2022 04:30:10 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 04:30:14 - INFO - codeparrot_training - Step 12805: {'lr': 0.0004934531679257903, 'samples': 6556672, 'steps': 12805, 'loss/train': 2.0420894622802734}
-03/04/2022 04:30:17 - INFO - codeparrot_training - Step 12806: {'lr': 0.0004934519613726022, 'samples': 6557184, 'steps': 12806, 'loss/train': 1.4632279872894287}
-03/04/2022 04:30:19 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 04:30:22 - INFO - codeparrot_training - Step 12807: {'lr': 0.0004934507547097183, 'samples': 6557696, 'steps': 12807, 'loss/train': 0.5704853534698486}
-03/04/2022 04:30:26 - INFO - codeparrot_training - Step 12808: {'lr': 0.0004934495479371393, 'samples': 6558208, 'steps': 12808, 'loss/train': 1.8006798028945923}
-03/04/2022 04:30:27 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 04:30:31 - INFO - codeparrot_training - Step 12809: {'lr': 0.0004934483410548658, 'samples': 6558720, 'steps': 12809, 'loss/train': 1.8783762454986572}
-03/04/2022 04:30:34 - INFO - codeparrot_training - Step 12810: {'lr': 0.0004934471340628981, 'samples': 6559232, 'steps': 12810, 'loss/train': 1.1781071424484253}
-03/04/2022 04:30:36 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/04/2022 04:30:39 - INFO - codeparrot_training - Step 12811: {'lr': 0.000493445926961237, 'samples': 6559744, 'steps': 12811, 'loss/train': 1.5750994682312012}
-03/04/2022 04:30:42 - INFO - codeparrot_training - Step 12812: {'lr': 0.0004934447197498828, 'samples': 6560256, 'steps': 12812, 'loss/train': 2.2006592750549316}
-03/04/2022 04:30:44 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/04/2022 04:30:48 - INFO - codeparrot_training - Step 12813: {'lr': 0.0004934435124288362, 'samples': 6560768, 'steps': 12813, 'loss/train': 0.7883157134056091}
-03/04/2022 04:30:51 - INFO - codeparrot_training - Step 12814: {'lr': 0.0004934423049980977, 'samples': 6561280, 'steps': 12814, 'loss/train': 2.207902669906616}
-03/04/2022 04:30:53 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/04/2022 04:30:56 - INFO - codeparrot_training - Step 12815: {'lr': 0.0004934410974576679, 'samples': 6561792, 'steps': 12815, 'loss/train': 2.053633213043213}
-03/04/2022 04:30:59 - INFO - codeparrot_training - Step 12816: {'lr': 0.0004934398898075472, 'samples': 6562304, 'steps': 12816, 'loss/train': 0.4529396593570709}
-03/04/2022 04:31:01 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/04/2022 04:31:05 - INFO - codeparrot_training - Step 12817: {'lr': 0.0004934386820477363, 'samples': 6562816, 'steps': 12817, 'loss/train': 2.3005571365356445}
-03/04/2022 04:31:08 - INFO - codeparrot_training - Step 12818: {'lr': 0.0004934374741782357, 'samples': 6563328, 'steps': 12818, 'loss/train': 1.9348663091659546}
-03/04/2022 04:31:10 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/04/2022 04:31:13 - INFO - codeparrot_training - Step 12819: {'lr': 0.000493436266199046, 'samples': 6563840, 'steps': 12819, 'loss/train': 1.6032766103744507}
-03/04/2022 04:31:16 - INFO - codeparrot_training - Step 12820: {'lr': 0.0004934350581101676, 'samples': 6564352, 'steps': 12820, 'loss/train': 1.7226588726043701}
-03/04/2022 04:31:18 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/04/2022 04:31:22 - INFO - codeparrot_training - Step 12821: {'lr': 0.0004934338499116011, 'samples': 6564864, 'steps': 12821, 'loss/train': 1.989188313484192}
-03/04/2022 04:31:25 - INFO - codeparrot_training - Step 12822: {'lr': 0.0004934326416033471, 'samples': 6565376, 'steps': 12822, 'loss/train': 2.3481345176696777}
-03/04/2022 04:31:26 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/04/2022 04:31:30 - INFO - codeparrot_training - Step 12823: {'lr': 0.0004934314331854061, 'samples': 6565888, 'steps': 12823, 'loss/train': 1.498224139213562}
-03/04/2022 04:31:33 - INFO - codeparrot_training - Step 12824: {'lr': 0.0004934302246577786, 'samples': 6566400, 'steps': 12824, 'loss/train': 1.8888201713562012}
-03/04/2022 04:31:35 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/04/2022 04:31:39 - INFO - codeparrot_training - Step 12825: {'lr': 0.0004934290160204652, 'samples': 6566912, 'steps': 12825, 'loss/train': 2.2589938640594482}
-03/04/2022 04:31:42 - INFO - codeparrot_training - Step 12826: {'lr': 0.0004934278072734666, 'samples': 6567424, 'steps': 12826, 'loss/train': 1.554665446281433}
-03/04/2022 04:31:47 - INFO - codeparrot_training - Step 12827: {'lr': 0.000493426598416783, 'samples': 6567936, 'steps': 12827, 'loss/train': 1.8552343845367432}
-03/04/2022 04:31:50 - INFO - codeparrot_training - Step 12828: {'lr': 0.0004934253894504152, 'samples': 6568448, 'steps': 12828, 'loss/train': 1.7493047714233398}
-03/04/2022 04:31:53 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/04/2022 04:31:56 - INFO - codeparrot_training - Step 12829: {'lr': 0.0004934241803743637, 'samples': 6568960, 'steps': 12829, 'loss/train': 4.251925468444824}
-03/04/2022 04:31:59 - INFO - codeparrot_training - Step 12830: {'lr': 0.000493422971188629, 'samples': 6569472, 'steps': 12830, 'loss/train': 2.2255771160125732}
-03/04/2022 04:32:01 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 04:32:04 - INFO - codeparrot_training - Step 12831: {'lr': 0.0004934217618932117, 'samples': 6569984, 'steps': 12831, 'loss/train': 1.406860113143921}
-03/04/2022 04:32:07 - INFO - codeparrot_training - Step 12832: {'lr': 0.0004934205524881123, 'samples': 6570496, 'steps': 12832, 'loss/train': 3.1514105796813965}
-03/04/2022 04:32:09 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/04/2022 04:32:13 - INFO - codeparrot_training - Step 12833: {'lr': 0.0004934193429733312, 'samples': 6571008, 'steps': 12833, 'loss/train': 2.31135630607605}
-03/04/2022 04:32:16 - INFO - codeparrot_training - Step 12834: {'lr': 0.0004934181333488693, 'samples': 6571520, 'steps': 12834, 'loss/train': 2.5668933391571045}
-03/04/2022 04:32:19 - INFO - codeparrot_training - Step 12835: {'lr': 0.0004934169236147268, 'samples': 6572032, 'steps': 12835, 'loss/train': 1.128472089767456}
-03/04/2022 04:32:19 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/04/2022 04:32:24 - INFO - codeparrot_training - Step 12836: {'lr': 0.0004934157137709044, 'samples': 6572544, 'steps': 12836, 'loss/train': 1.9851511716842651}
-03/04/2022 04:32:27 - INFO - codeparrot_training - Step 12837: {'lr': 0.0004934145038174028, 'samples': 6573056, 'steps': 12837, 'loss/train': 2.440800666809082}
-03/04/2022 04:32:27 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 04:32:33 - INFO - codeparrot_training - Step 12838: {'lr': 0.0004934132937542223, 'samples': 6573568, 'steps': 12838, 'loss/train': 2.115483283996582}
-03/04/2022 04:32:35 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/04/2022 04:32:38 - INFO - codeparrot_training - Step 12839: {'lr': 0.0004934120835813634, 'samples': 6574080, 'steps': 12839, 'loss/train': 1.3223178386688232}
-03/04/2022 04:32:41 - INFO - codeparrot_training - Step 12840: {'lr': 0.0004934108732988269, 'samples': 6574592, 'steps': 12840, 'loss/train': 1.7152312994003296}
-03/04/2022 04:32:44 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/04/2022 04:32:46 - INFO - codeparrot_training - Step 12841: {'lr': 0.0004934096629066133, 'samples': 6575104, 'steps': 12841, 'loss/train': 1.7090893983840942}
-03/04/2022 04:32:49 - INFO - codeparrot_training - Step 12842: {'lr': 0.0004934084524047229, 'samples': 6575616, 'steps': 12842, 'loss/train': 1.5715233087539673}
-03/04/2022 04:32:52 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/04/2022 04:32:55 - INFO - codeparrot_training - Step 12843: {'lr': 0.0004934072417931564, 'samples': 6576128, 'steps': 12843, 'loss/train': 1.9935400485992432}
-03/04/2022 04:32:58 - INFO - codeparrot_training - Step 12844: {'lr': 0.0004934060310719145, 'samples': 6576640, 'steps': 12844, 'loss/train': 2.178008556365967}
-03/04/2022 04:33:01 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/04/2022 04:33:03 - INFO - codeparrot_training - Step 12845: {'lr': 0.0004934048202409974, 'samples': 6577152, 'steps': 12845, 'loss/train': 1.7132335901260376}
-03/04/2022 04:33:06 - INFO - codeparrot_training - Step 12846: {'lr': 0.000493403609300406, 'samples': 6577664, 'steps': 12846, 'loss/train': 2.4094674587249756}
-03/04/2022 04:33:09 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/04/2022 04:33:11 - INFO - codeparrot_training - Step 12847: {'lr': 0.0004934023982501406, 'samples': 6578176, 'steps': 12847, 'loss/train': 1.4585354328155518}
-03/04/2022 04:33:15 - INFO - codeparrot_training - Step 12848: {'lr': 0.000493401187090202, 'samples': 6578688, 'steps': 12848, 'loss/train': 1.8142168521881104}
-03/04/2022 04:33:17 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 04:33:20 - INFO - codeparrot_training - Step 12849: {'lr': 0.0004933999758205904, 'samples': 6579200, 'steps': 12849, 'loss/train': 1.8432506322860718}
-03/04/2022 04:33:23 - INFO - codeparrot_training - Step 12850: {'lr': 0.0004933987644413066, 'samples': 6579712, 'steps': 12850, 'loss/train': 2.0411834716796875}
-03/04/2022 04:33:25 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/04/2022 04:33:28 - INFO - codeparrot_training - Step 12851: {'lr': 0.0004933975529523511, 'samples': 6580224, 'steps': 12851, 'loss/train': 1.9608439207077026}
-03/04/2022 04:33:31 - INFO - codeparrot_training - Step 12852: {'lr': 0.0004933963413537244, 'samples': 6580736, 'steps': 12852, 'loss/train': 2.233844041824341}
-03/04/2022 04:33:34 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/04/2022 04:33:37 - INFO - codeparrot_training - Step 12853: {'lr': 0.000493395129645427, 'samples': 6581248, 'steps': 12853, 'loss/train': 1.5477029085159302}
-03/04/2022 04:33:40 - INFO - codeparrot_training - Step 12854: {'lr': 0.0004933939178274596, 'samples': 6581760, 'steps': 12854, 'loss/train': 1.648119330406189}
-03/04/2022 04:33:43 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 04:33:45 - INFO - codeparrot_training - Step 12855: {'lr': 0.0004933927058998226, 'samples': 6582272, 'steps': 12855, 'loss/train': 1.4178813695907593}
-03/04/2022 04:33:48 - INFO - codeparrot_training - Step 12856: {'lr': 0.0004933914938625166, 'samples': 6582784, 'steps': 12856, 'loss/train': 1.4213637113571167}
-03/04/2022 04:33:51 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/04/2022 04:33:54 - INFO - codeparrot_training - Step 12857: {'lr': 0.0004933902817155422, 'samples': 6583296, 'steps': 12857, 'loss/train': 2.23958420753479}
-03/04/2022 04:33:57 - INFO - codeparrot_training - Step 12858: {'lr': 0.0004933890694588998, 'samples': 6583808, 'steps': 12858, 'loss/train': 1.9892728328704834}
-03/04/2022 04:33:59 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 04:34:02 - INFO - codeparrot_training - Step 12859: {'lr': 0.0004933878570925901, 'samples': 6584320, 'steps': 12859, 'loss/train': 1.0209859609603882}
-03/04/2022 04:34:05 - INFO - codeparrot_training - Step 12860: {'lr': 0.0004933866446166136, 'samples': 6584832, 'steps': 12860, 'loss/train': 3.1946799755096436}
-03/04/2022 04:34:08 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/04/2022 04:34:11 - INFO - codeparrot_training - Step 12861: {'lr': 0.0004933854320309708, 'samples': 6585344, 'steps': 12861, 'loss/train': 2.011786460876465}
-03/04/2022 04:34:14 - INFO - codeparrot_training - Step 12862: {'lr': 0.0004933842193356624, 'samples': 6585856, 'steps': 12862, 'loss/train': 2.295060157775879}
-03/04/2022 04:34:16 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 04:34:19 - INFO - codeparrot_training - Step 12863: {'lr': 0.0004933830065306887, 'samples': 6586368, 'steps': 12863, 'loss/train': 2.274444341659546}
-03/04/2022 04:34:22 - INFO - codeparrot_training - Step 12864: {'lr': 0.0004933817936160504, 'samples': 6586880, 'steps': 12864, 'loss/train': 2.1784865856170654}
-03/04/2022 04:34:25 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/04/2022 04:34:27 - INFO - codeparrot_training - Step 12865: {'lr': 0.0004933805805917479, 'samples': 6587392, 'steps': 12865, 'loss/train': 2.0693254470825195}
-03/04/2022 04:34:31 - INFO - codeparrot_training - Step 12866: {'lr': 0.000493379367457782, 'samples': 6587904, 'steps': 12866, 'loss/train': 2.1016342639923096}
-03/04/2022 04:34:33 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/04/2022 04:34:36 - INFO - codeparrot_training - Step 12867: {'lr': 0.0004933781542141532, 'samples': 6588416, 'steps': 12867, 'loss/train': 1.7604612112045288}
-03/04/2022 04:34:39 - INFO - codeparrot_training - Step 12868: {'lr': 0.0004933769408608618, 'samples': 6588928, 'steps': 12868, 'loss/train': 1.8627222776412964}
-03/04/2022 04:34:41 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/04/2022 04:34:44 - INFO - codeparrot_training - Step 12869: {'lr': 0.0004933757273979086, 'samples': 6589440, 'steps': 12869, 'loss/train': 1.3295230865478516}
-03/04/2022 04:34:48 - INFO - codeparrot_training - Step 12870: {'lr': 0.0004933745138252939, 'samples': 6589952, 'steps': 12870, 'loss/train': 1.1703587770462036}
-03/04/2022 04:34:50 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 04:34:53 - INFO - codeparrot_training - Step 12871: {'lr': 0.0004933733001430186, 'samples': 6590464, 'steps': 12871, 'loss/train': 1.7727546691894531}
-03/04/2022 04:34:56 - INFO - codeparrot_training - Step 12872: {'lr': 0.000493372086351083, 'samples': 6590976, 'steps': 12872, 'loss/train': 1.7542883157730103}
-03/04/2022 04:34:58 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 04:35:01 - INFO - codeparrot_training - Step 12873: {'lr': 0.0004933708724494877, 'samples': 6591488, 'steps': 12873, 'loss/train': 1.7273575067520142}
-03/04/2022 04:35:05 - INFO - codeparrot_training - Step 12874: {'lr': 0.0004933696584382331, 'samples': 6592000, 'steps': 12874, 'loss/train': 0.5252533555030823}
-03/04/2022 04:35:07 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/04/2022 04:35:10 - INFO - codeparrot_training - Step 12875: {'lr': 0.00049336844431732, 'samples': 6592512, 'steps': 12875, 'loss/train': 1.5745391845703125}
-03/04/2022 04:35:13 - INFO - codeparrot_training - Step 12876: {'lr': 0.0004933672300867488, 'samples': 6593024, 'steps': 12876, 'loss/train': 2.5030148029327393}
-03/04/2022 04:35:15 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/04/2022 04:35:18 - INFO - codeparrot_training - Step 12877: {'lr': 0.0004933660157465202, 'samples': 6593536, 'steps': 12877, 'loss/train': 1.8256441354751587}
-03/04/2022 04:35:21 - INFO - codeparrot_training - Step 12878: {'lr': 0.0004933648012966344, 'samples': 6594048, 'steps': 12878, 'loss/train': 1.2067747116088867}
-03/04/2022 04:35:24 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 04:35:27 - INFO - codeparrot_training - Step 12879: {'lr': 0.0004933635867370923, 'samples': 6594560, 'steps': 12879, 'loss/train': 1.680674433708191}
-03/04/2022 04:35:30 - INFO - codeparrot_training - Step 12880: {'lr': 0.0004933623720678944, 'samples': 6595072, 'steps': 12880, 'loss/train': 1.5086877346038818}
-03/04/2022 04:35:33 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/04/2022 04:35:35 - INFO - codeparrot_training - Step 12881: {'lr': 0.000493361157289041, 'samples': 6595584, 'steps': 12881, 'loss/train': 2.2118802070617676}
-03/04/2022 04:35:39 - INFO - codeparrot_training - Step 12882: {'lr': 0.000493359942400533, 'samples': 6596096, 'steps': 12882, 'loss/train': 1.1844966411590576}
-03/04/2022 04:35:42 - INFO - codeparrot_training - Step 12883: {'lr': 0.0004933587274023706, 'samples': 6596608, 'steps': 12883, 'loss/train': 2.0892674922943115}
-03/04/2022 04:35:47 - INFO - codeparrot_training - Step 12884: {'lr': 0.0004933575122945547, 'samples': 6597120, 'steps': 12884, 'loss/train': 2.174311399459839}
-03/04/2022 04:35:50 - INFO - codeparrot_training - Step 12885: {'lr': 0.0004933562970770855, 'samples': 6597632, 'steps': 12885, 'loss/train': 2.5617806911468506}
-03/04/2022 04:35:50 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/04/2022 04:35:56 - INFO - codeparrot_training - Step 12886: {'lr': 0.0004933550817499638, 'samples': 6598144, 'steps': 12886, 'loss/train': 1.3905504941940308}
-03/04/2022 04:35:59 - INFO - codeparrot_training - Step 12887: {'lr': 0.00049335386631319, 'samples': 6598656, 'steps': 12887, 'loss/train': 2.0406973361968994}
-03/04/2022 04:35:59 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/04/2022 04:36:04 - INFO - codeparrot_training - Step 12888: {'lr': 0.0004933526507667648, 'samples': 6599168, 'steps': 12888, 'loss/train': 1.827602505683899}
-03/04/2022 04:36:07 - INFO - codeparrot_training - Step 12889: {'lr': 0.0004933514351106885, 'samples': 6599680, 'steps': 12889, 'loss/train': 2.221069097518921}
-03/04/2022 04:36:07 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/04/2022 04:36:12 - INFO - codeparrot_training - Step 12890: {'lr': 0.0004933502193449618, 'samples': 6600192, 'steps': 12890, 'loss/train': 2.3854448795318604}
-03/04/2022 04:36:16 - INFO - codeparrot_training - Step 12891: {'lr': 0.0004933490034695853, 'samples': 6600704, 'steps': 12891, 'loss/train': 2.579716682434082}
-03/04/2022 04:36:16 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 04:36:21 - INFO - codeparrot_training - Step 12892: {'lr': 0.0004933477874845595, 'samples': 6601216, 'steps': 12892, 'loss/train': 1.934211254119873}
-03/04/2022 04:36:24 - INFO - codeparrot_training - Step 12893: {'lr': 0.000493346571389885, 'samples': 6601728, 'steps': 12893, 'loss/train': 1.9434469938278198}
-03/04/2022 04:36:24 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/04/2022 04:36:29 - INFO - codeparrot_training - Step 12894: {'lr': 0.0004933453551855622, 'samples': 6602240, 'steps': 12894, 'loss/train': 1.627199649810791}
-03/04/2022 04:36:32 - INFO - codeparrot_training - Step 12895: {'lr': 0.0004933441388715919, 'samples': 6602752, 'steps': 12895, 'loss/train': 2.0862014293670654}
-03/04/2022 04:36:32 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 04:36:38 - INFO - codeparrot_training - Step 12896: {'lr': 0.0004933429224479743, 'samples': 6603264, 'steps': 12896, 'loss/train': 1.6021559238433838}
-03/04/2022 04:36:41 - INFO - codeparrot_training - Step 12897: {'lr': 0.0004933417059147102, 'samples': 6603776, 'steps': 12897, 'loss/train': 1.725085735321045}
-03/04/2022 04:36:41 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/04/2022 04:36:46 - INFO - codeparrot_training - Step 12898: {'lr': 0.0004933404892718, 'samples': 6604288, 'steps': 12898, 'loss/train': 1.9168329238891602}
-03/04/2022 04:36:49 - INFO - codeparrot_training - Step 12899: {'lr': 0.0004933392725192444, 'samples': 6604800, 'steps': 12899, 'loss/train': 1.3135086297988892}
-03/04/2022 04:36:49 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 04:36:55 - INFO - codeparrot_training - Step 12900: {'lr': 0.000493338055657044, 'samples': 6605312, 'steps': 12900, 'loss/train': 1.724927544593811}
-03/04/2022 04:36:58 - INFO - codeparrot_training - Step 12901: {'lr': 0.0004933368386851991, 'samples': 6605824, 'steps': 12901, 'loss/train': 2.2891767024993896}
-03/04/2022 04:36:58 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 04:37:03 - INFO - codeparrot_training - Step 12902: {'lr': 0.0004933356216037104, 'samples': 6606336, 'steps': 12902, 'loss/train': 2.730241060256958}
-03/04/2022 04:37:06 - INFO - codeparrot_training - Step 12903: {'lr': 0.0004933344044125784, 'samples': 6606848, 'steps': 12903, 'loss/train': 2.142174482345581}
-03/04/2022 04:37:07 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/04/2022 04:37:12 - INFO - codeparrot_training - Step 12904: {'lr': 0.0004933331871118037, 'samples': 6607360, 'steps': 12904, 'loss/train': 0.6146966218948364}
-03/04/2022 04:37:15 - INFO - codeparrot_training - Step 12905: {'lr': 0.0004933319697013869, 'samples': 6607872, 'steps': 12905, 'loss/train': 2.2878804206848145}
-03/04/2022 04:37:15 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/04/2022 04:37:20 - INFO - codeparrot_training - Step 12906: {'lr': 0.0004933307521813282, 'samples': 6608384, 'steps': 12906, 'loss/train': 1.6942219734191895}
-03/04/2022 04:37:23 - INFO - codeparrot_training - Step 12907: {'lr': 0.0004933295345516287, 'samples': 6608896, 'steps': 12907, 'loss/train': 2.0319643020629883}
-03/04/2022 04:37:24 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 04:37:29 - INFO - codeparrot_training - Step 12908: {'lr': 0.0004933283168122886, 'samples': 6609408, 'steps': 12908, 'loss/train': 1.6664246320724487}
-03/04/2022 04:37:32 - INFO - codeparrot_training - Step 12909: {'lr': 0.0004933270989633084, 'samples': 6609920, 'steps': 12909, 'loss/train': 2.460160493850708}
-03/04/2022 04:37:33 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 04:37:37 - INFO - codeparrot_training - Step 12910: {'lr': 0.0004933258810046889, 'samples': 6610432, 'steps': 12910, 'loss/train': 2.4940032958984375}
-03/04/2022 04:37:40 - INFO - codeparrot_training - Step 12911: {'lr': 0.0004933246629364304, 'samples': 6610944, 'steps': 12911, 'loss/train': 2.414705991744995}
-03/04/2022 04:37:41 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/04/2022 04:37:46 - INFO - codeparrot_training - Step 12912: {'lr': 0.0004933234447585337, 'samples': 6611456, 'steps': 12912, 'loss/train': 1.2825961112976074}
-03/04/2022 04:37:49 - INFO - codeparrot_training - Step 12913: {'lr': 0.0004933222264709991, 'samples': 6611968, 'steps': 12913, 'loss/train': 1.9127964973449707}
-03/04/2022 04:37:50 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/04/2022 04:37:54 - INFO - codeparrot_training - Step 12914: {'lr': 0.0004933210080738273, 'samples': 6612480, 'steps': 12914, 'loss/train': 2.0163421630859375}
-03/04/2022 04:37:57 - INFO - codeparrot_training - Step 12915: {'lr': 0.0004933197895670187, 'samples': 6612992, 'steps': 12915, 'loss/train': 3.0988082885742188}
-03/04/2022 04:37:58 - INFO - codeparrot_training - Skipping example with length 524 (seq_length=1024)
-03/04/2022 04:38:02 - INFO - codeparrot_training - Step 12916: {'lr': 0.0004933185709505741, 'samples': 6613504, 'steps': 12916, 'loss/train': 1.4913616180419922}
-03/04/2022 04:38:06 - INFO - codeparrot_training - Step 12917: {'lr': 0.0004933173522244939, 'samples': 6614016, 'steps': 12917, 'loss/train': 1.5365358591079712}
-03/04/2022 04:38:07 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 04:38:11 - INFO - codeparrot_training - Step 12918: {'lr': 0.0004933161333887786, 'samples': 6614528, 'steps': 12918, 'loss/train': 2.0867223739624023}
-03/04/2022 04:38:14 - INFO - codeparrot_training - Step 12919: {'lr': 0.0004933149144434288, 'samples': 6615040, 'steps': 12919, 'loss/train': 1.6441669464111328}
-03/04/2022 04:38:15 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/04/2022 04:38:19 - INFO - codeparrot_training - Step 12920: {'lr': 0.0004933136953884451, 'samples': 6615552, 'steps': 12920, 'loss/train': 1.87692391872406}
-03/04/2022 04:38:22 - INFO - codeparrot_training - Step 12921: {'lr': 0.0004933124762238279, 'samples': 6616064, 'steps': 12921, 'loss/train': 2.392404794692993}
-03/04/2022 04:38:24 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 04:38:28 - INFO - codeparrot_training - Step 12922: {'lr': 0.000493311256949578, 'samples': 6616576, 'steps': 12922, 'loss/train': 2.4540815353393555}
-03/04/2022 04:38:31 - INFO - codeparrot_training - Step 12923: {'lr': 0.0004933100375656957, 'samples': 6617088, 'steps': 12923, 'loss/train': 1.8394889831542969}
-03/04/2022 04:38:32 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/04/2022 04:38:36 - INFO - codeparrot_training - Step 12924: {'lr': 0.0004933088180721817, 'samples': 6617600, 'steps': 12924, 'loss/train': 2.743861436843872}
-03/04/2022 04:38:39 - INFO - codeparrot_training - Step 12925: {'lr': 0.0004933075984690365, 'samples': 6618112, 'steps': 12925, 'loss/train': 2.126891613006592}
-03/04/2022 04:38:40 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/04/2022 04:38:45 - INFO - codeparrot_training - Step 12926: {'lr': 0.0004933063787562606, 'samples': 6618624, 'steps': 12926, 'loss/train': 4.998426914215088}
-03/04/2022 04:38:48 - INFO - codeparrot_training - Step 12927: {'lr': 0.0004933051589338547, 'samples': 6619136, 'steps': 12927, 'loss/train': 0.938148021697998}
-03/04/2022 04:38:48 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/04/2022 04:38:53 - INFO - codeparrot_training - Step 12928: {'lr': 0.0004933039390018192, 'samples': 6619648, 'steps': 12928, 'loss/train': 2.4533751010894775}
-03/04/2022 04:38:56 - INFO - codeparrot_training - Step 12929: {'lr': 0.0004933027189601547, 'samples': 6620160, 'steps': 12929, 'loss/train': 1.8757903575897217}
-03/04/2022 04:38:57 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/04/2022 04:39:01 - INFO - codeparrot_training - Step 12930: {'lr': 0.0004933014988088616, 'samples': 6620672, 'steps': 12930, 'loss/train': 1.0247012376785278}
-03/04/2022 04:39:04 - INFO - codeparrot_training - Step 12931: {'lr': 0.0004933002785479408, 'samples': 6621184, 'steps': 12931, 'loss/train': 2.9174320697784424}
-03/04/2022 04:39:05 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 04:39:10 - INFO - codeparrot_training - Step 12932: {'lr': 0.0004932990581773926, 'samples': 6621696, 'steps': 12932, 'loss/train': 6.21317195892334}
-03/04/2022 04:39:13 - INFO - codeparrot_training - Step 12933: {'lr': 0.0004932978376972175, 'samples': 6622208, 'steps': 12933, 'loss/train': 2.214327812194824}
-03/04/2022 04:39:14 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 04:39:18 - INFO - codeparrot_training - Step 12934: {'lr': 0.0004932966171074163, 'samples': 6622720, 'steps': 12934, 'loss/train': 2.142599582672119}
-03/04/2022 04:39:21 - INFO - codeparrot_training - Step 12935: {'lr': 0.0004932953964079893, 'samples': 6623232, 'steps': 12935, 'loss/train': 1.986877202987671}
-03/04/2022 04:39:22 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 04:39:27 - INFO - codeparrot_training - Step 12936: {'lr': 0.0004932941755989372, 'samples': 6623744, 'steps': 12936, 'loss/train': 2.291424512863159}
-03/04/2022 04:39:30 - INFO - codeparrot_training - Step 12937: {'lr': 0.0004932929546802605, 'samples': 6624256, 'steps': 12937, 'loss/train': 1.5338454246520996}
-03/04/2022 04:39:30 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/04/2022 04:39:35 - INFO - codeparrot_training - Step 12938: {'lr': 0.0004932917336519597, 'samples': 6624768, 'steps': 12938, 'loss/train': 1.8447595834732056}
-03/04/2022 04:39:38 - INFO - codeparrot_training - Step 12939: {'lr': 0.0004932905125140354, 'samples': 6625280, 'steps': 12939, 'loss/train': 1.2736032009124756}
-03/04/2022 04:39:39 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/04/2022 04:39:44 - INFO - codeparrot_training - Step 12940: {'lr': 0.0004932892912664882, 'samples': 6625792, 'steps': 12940, 'loss/train': 1.0110121965408325}
-03/04/2022 04:39:47 - INFO - codeparrot_training - Step 12941: {'lr': 0.0004932880699093186, 'samples': 6626304, 'steps': 12941, 'loss/train': 2.40796160697937}
-03/04/2022 04:39:49 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/04/2022 04:39:52 - INFO - codeparrot_training - Step 12942: {'lr': 0.0004932868484425271, 'samples': 6626816, 'steps': 12942, 'loss/train': 1.81626296043396}
-03/04/2022 04:39:55 - INFO - codeparrot_training - Step 12943: {'lr': 0.0004932856268661143, 'samples': 6627328, 'steps': 12943, 'loss/train': 1.9715402126312256}
-03/04/2022 04:39:57 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 04:40:01 - INFO - codeparrot_training - Step 12944: {'lr': 0.0004932844051800808, 'samples': 6627840, 'steps': 12944, 'loss/train': 2.159313678741455}
-03/04/2022 04:40:04 - INFO - codeparrot_training - Step 12945: {'lr': 0.000493283183384427, 'samples': 6628352, 'steps': 12945, 'loss/train': 1.8143243789672852}
-03/04/2022 04:40:06 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 04:40:09 - INFO - codeparrot_training - Step 12946: {'lr': 0.0004932819614791537, 'samples': 6628864, 'steps': 12946, 'loss/train': 2.6106338500976562}
-03/04/2022 04:40:12 - INFO - codeparrot_training - Step 12947: {'lr': 0.0004932807394642612, 'samples': 6629376, 'steps': 12947, 'loss/train': 1.5840368270874023}
-03/04/2022 04:40:14 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 04:40:18 - INFO - codeparrot_training - Step 12948: {'lr': 0.0004932795173397501, 'samples': 6629888, 'steps': 12948, 'loss/train': 2.5313560962677}
-03/04/2022 04:40:21 - INFO - codeparrot_training - Step 12949: {'lr': 0.0004932782951056211, 'samples': 6630400, 'steps': 12949, 'loss/train': 2.0478739738464355}
-03/04/2022 04:40:22 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/04/2022 04:40:26 - INFO - codeparrot_training - Step 12950: {'lr': 0.0004932770727618747, 'samples': 6630912, 'steps': 12950, 'loss/train': 2.465897560119629}
-03/04/2022 04:40:29 - INFO - codeparrot_training - Step 12951: {'lr': 0.0004932758503085114, 'samples': 6631424, 'steps': 12951, 'loss/train': 1.8947851657867432}
-03/04/2022 04:40:31 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/04/2022 04:40:35 - INFO - codeparrot_training - Step 12952: {'lr': 0.0004932746277455317, 'samples': 6631936, 'steps': 12952, 'loss/train': 2.7147650718688965}
-03/04/2022 04:40:38 - INFO - codeparrot_training - Step 12953: {'lr': 0.0004932734050729362, 'samples': 6632448, 'steps': 12953, 'loss/train': 2.639646053314209}
-03/04/2022 04:40:39 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/04/2022 04:40:43 - INFO - codeparrot_training - Step 12954: {'lr': 0.0004932721822907255, 'samples': 6632960, 'steps': 12954, 'loss/train': 2.4213736057281494}
-03/04/2022 04:40:46 - INFO - codeparrot_training - Step 12955: {'lr': 0.0004932709593989, 'samples': 6633472, 'steps': 12955, 'loss/train': 1.9431591033935547}
-03/04/2022 04:40:48 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/04/2022 04:40:51 - INFO - codeparrot_training - Step 12956: {'lr': 0.0004932697363974604, 'samples': 6633984, 'steps': 12956, 'loss/train': 1.1635124683380127}
-03/04/2022 04:40:55 - INFO - codeparrot_training - Step 12957: {'lr': 0.0004932685132864072, 'samples': 6634496, 'steps': 12957, 'loss/train': 1.6751128435134888}
-03/04/2022 04:40:56 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 04:41:00 - INFO - codeparrot_training - Step 12958: {'lr': 0.0004932672900657411, 'samples': 6635008, 'steps': 12958, 'loss/train': 0.8928879499435425}
-03/04/2022 04:41:03 - INFO - codeparrot_training - Step 12959: {'lr': 0.0004932660667354623, 'samples': 6635520, 'steps': 12959, 'loss/train': 1.4285473823547363}
-03/04/2022 04:41:05 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/04/2022 04:41:08 - INFO - codeparrot_training - Step 12960: {'lr': 0.0004932648432955717, 'samples': 6636032, 'steps': 12960, 'loss/train': 1.522325038909912}
-03/04/2022 04:41:11 - INFO - codeparrot_training - Step 12961: {'lr': 0.0004932636197460698, 'samples': 6636544, 'steps': 12961, 'loss/train': 1.5130969285964966}
-03/04/2022 04:41:13 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/04/2022 04:41:17 - INFO - codeparrot_training - Step 12962: {'lr': 0.0004932623960869569, 'samples': 6637056, 'steps': 12962, 'loss/train': 2.111562728881836}
-03/04/2022 04:41:20 - INFO - codeparrot_training - Step 12963: {'lr': 0.0004932611723182338, 'samples': 6637568, 'steps': 12963, 'loss/train': 2.1328866481781006}
-03/04/2022 04:41:22 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 04:41:25 - INFO - codeparrot_training - Step 12964: {'lr': 0.000493259948439901, 'samples': 6638080, 'steps': 12964, 'loss/train': 1.8974369764328003}
-03/04/2022 04:41:28 - INFO - codeparrot_training - Step 12965: {'lr': 0.0004932587244519589, 'samples': 6638592, 'steps': 12965, 'loss/train': 1.5194343328475952}
-03/04/2022 04:41:30 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 04:41:34 - INFO - codeparrot_training - Step 12966: {'lr': 0.0004932575003544083, 'samples': 6639104, 'steps': 12966, 'loss/train': 1.2920864820480347}
-03/04/2022 04:41:37 - INFO - codeparrot_training - Step 12967: {'lr': 0.0004932562761472496, 'samples': 6639616, 'steps': 12967, 'loss/train': 1.3235058784484863}
-03/04/2022 04:41:39 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/04/2022 04:41:42 - INFO - codeparrot_training - Step 12968: {'lr': 0.0004932550518304833, 'samples': 6640128, 'steps': 12968, 'loss/train': 2.195288896560669}
-03/04/2022 04:41:45 - INFO - codeparrot_training - Step 12969: {'lr': 0.0004932538274041101, 'samples': 6640640, 'steps': 12969, 'loss/train': 0.7049352526664734}
-03/04/2022 04:41:47 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/04/2022 04:41:51 - INFO - codeparrot_training - Step 12970: {'lr': 0.0004932526028681304, 'samples': 6641152, 'steps': 12970, 'loss/train': 1.8024041652679443}
-03/04/2022 04:41:54 - INFO - codeparrot_training - Step 12971: {'lr': 0.0004932513782225449, 'samples': 6641664, 'steps': 12971, 'loss/train': 1.2112094163894653}
-03/04/2022 04:41:56 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 04:41:59 - INFO - codeparrot_training - Step 12972: {'lr': 0.000493250153467354, 'samples': 6642176, 'steps': 12972, 'loss/train': 1.583093285560608}
-03/04/2022 04:42:02 - INFO - codeparrot_training - Step 12973: {'lr': 0.0004932489286025584, 'samples': 6642688, 'steps': 12973, 'loss/train': 1.4423128366470337}
-03/04/2022 04:42:04 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/04/2022 04:42:07 - INFO - codeparrot_training - Step 12974: {'lr': 0.0004932477036281586, 'samples': 6643200, 'steps': 12974, 'loss/train': 1.9401452541351318}
-03/04/2022 04:42:11 - INFO - codeparrot_training - Step 12975: {'lr': 0.0004932464785441552, 'samples': 6643712, 'steps': 12975, 'loss/train': 2.1395375728607178}
-03/04/2022 04:42:13 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/04/2022 04:42:16 - INFO - codeparrot_training - Step 12976: {'lr': 0.0004932452533505486, 'samples': 6644224, 'steps': 12976, 'loss/train': 2.268666982650757}
-03/04/2022 04:42:19 - INFO - codeparrot_training - Step 12977: {'lr': 0.0004932440280473395, 'samples': 6644736, 'steps': 12977, 'loss/train': 2.021160840988159}
-03/04/2022 04:42:21 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 04:42:24 - INFO - codeparrot_training - Step 12978: {'lr': 0.0004932428026345282, 'samples': 6645248, 'steps': 12978, 'loss/train': 2.164365768432617}
-03/04/2022 04:42:28 - INFO - codeparrot_training - Step 12979: {'lr': 0.0004932415771121157, 'samples': 6645760, 'steps': 12979, 'loss/train': 2.9760961532592773}
-03/04/2022 04:42:29 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/04/2022 04:42:33 - INFO - codeparrot_training - Step 12980: {'lr': 0.0004932403514801021, 'samples': 6646272, 'steps': 12980, 'loss/train': 1.778461217880249}
-03/04/2022 04:42:36 - INFO - codeparrot_training - Step 12981: {'lr': 0.0004932391257384883, 'samples': 6646784, 'steps': 12981, 'loss/train': 2.0656774044036865}
-03/04/2022 04:42:38 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/04/2022 04:42:41 - INFO - codeparrot_training - Step 12982: {'lr': 0.0004932378998872746, 'samples': 6647296, 'steps': 12982, 'loss/train': 2.1452627182006836}
-03/04/2022 04:42:44 - INFO - codeparrot_training - Step 12983: {'lr': 0.0004932366739264618, 'samples': 6647808, 'steps': 12983, 'loss/train': 1.7387524843215942}
-03/04/2022 04:42:46 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/04/2022 04:42:50 - INFO - codeparrot_training - Step 12984: {'lr': 0.0004932354478560502, 'samples': 6648320, 'steps': 12984, 'loss/train': 0.3790569007396698}
-03/04/2022 04:42:53 - INFO - codeparrot_training - Step 12985: {'lr': 0.0004932342216760405, 'samples': 6648832, 'steps': 12985, 'loss/train': 1.8079087734222412}
-03/04/2022 04:42:55 - INFO - codeparrot_training - Skipping example with length 553 (seq_length=1024)
-03/04/2022 04:42:58 - INFO - codeparrot_training - Step 12986: {'lr': 0.0004932329953864331, 'samples': 6649344, 'steps': 12986, 'loss/train': 1.381874918937683}
-03/04/2022 04:43:01 - INFO - codeparrot_training - Step 12987: {'lr': 0.0004932317689872287, 'samples': 6649856, 'steps': 12987, 'loss/train': 1.9242007732391357}
-03/04/2022 04:43:03 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 04:43:07 - INFO - codeparrot_training - Step 12988: {'lr': 0.000493230542478428, 'samples': 6650368, 'steps': 12988, 'loss/train': 2.565944194793701}
-03/04/2022 04:43:10 - INFO - codeparrot_training - Step 12989: {'lr': 0.0004932293158600312, 'samples': 6650880, 'steps': 12989, 'loss/train': 2.0136804580688477}
-03/04/2022 04:43:12 - INFO - codeparrot_training - Skipping example with length 920 (seq_length=1024)
-03/04/2022 04:43:15 - INFO - codeparrot_training - Step 12990: {'lr': 0.0004932280891320391, 'samples': 6651392, 'steps': 12990, 'loss/train': 1.6188536882400513}
-03/04/2022 04:43:18 - INFO - codeparrot_training - Step 12991: {'lr': 0.0004932268622944521, 'samples': 6651904, 'steps': 12991, 'loss/train': 2.2674241065979004}
-03/04/2022 04:43:20 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/04/2022 04:43:23 - INFO - codeparrot_training - Step 12992: {'lr': 0.0004932256353472709, 'samples': 6652416, 'steps': 12992, 'loss/train': 1.222720980644226}
-03/04/2022 04:43:27 - INFO - codeparrot_training - Step 12993: {'lr': 0.0004932244082904959, 'samples': 6652928, 'steps': 12993, 'loss/train': 3.324889898300171}
-03/04/2022 04:43:29 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 04:43:32 - INFO - codeparrot_training - Step 12994: {'lr': 0.0004932231811241278, 'samples': 6653440, 'steps': 12994, 'loss/train': 1.8361763954162598}
-03/04/2022 04:43:35 - INFO - codeparrot_training - Step 12995: {'lr': 0.0004932219538481672, 'samples': 6653952, 'steps': 12995, 'loss/train': 1.7789030075073242}
-03/04/2022 04:43:38 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 04:43:40 - INFO - codeparrot_training - Step 12996: {'lr': 0.0004932207264626143, 'samples': 6654464, 'steps': 12996, 'loss/train': 2.452918291091919}
-03/04/2022 04:43:43 - INFO - codeparrot_training - Step 12997: {'lr': 0.00049321949896747, 'samples': 6654976, 'steps': 12997, 'loss/train': 3.0657784938812256}
-03/04/2022 04:43:46 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/04/2022 04:43:49 - INFO - codeparrot_training - Step 12998: {'lr': 0.0004932182713627348, 'samples': 6655488, 'steps': 12998, 'loss/train': 1.7082043886184692}
-03/04/2022 04:43:52 - INFO - codeparrot_training - Step 12999: {'lr': 0.0004932170436484091, 'samples': 6656000, 'steps': 12999, 'loss/train': 1.9123408794403076}
-03/04/2022 04:43:54 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 04:43:58 - INFO - codeparrot_training - Step 13000: {'lr': 0.0004932158158244937, 'samples': 6656512, 'steps': 13000, 'loss/train': 2.356668710708618}
-03/04/2022 04:44:01 - INFO - codeparrot_training - Step 13001: {'lr': 0.0004932145878909889, 'samples': 6657024, 'steps': 13001, 'loss/train': 2.458933115005493}
-03/04/2022 04:44:04 - INFO - codeparrot_training - Step 13002: {'lr': 0.0004932133598478953, 'samples': 6657536, 'steps': 13002, 'loss/train': 2.1191232204437256}
-03/04/2022 04:44:06 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 04:44:09 - INFO - codeparrot_training - Step 13003: {'lr': 0.0004932121316952136, 'samples': 6658048, 'steps': 13003, 'loss/train': 1.8868825435638428}
-03/04/2022 04:44:13 - INFO - codeparrot_training - Step 13004: {'lr': 0.0004932109034329442, 'samples': 6658560, 'steps': 13004, 'loss/train': 1.3820722103118896}
-03/04/2022 04:44:14 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 04:44:18 - INFO - codeparrot_training - Step 13005: {'lr': 0.0004932096750610879, 'samples': 6659072, 'steps': 13005, 'loss/train': 1.3076400756835938}
-03/04/2022 04:44:21 - INFO - codeparrot_training - Step 13006: {'lr': 0.0004932084465796449, 'samples': 6659584, 'steps': 13006, 'loss/train': 2.3257687091827393}
-03/04/2022 04:44:23 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/04/2022 04:44:26 - INFO - codeparrot_training - Step 13007: {'lr': 0.000493207217988616, 'samples': 6660096, 'steps': 13007, 'loss/train': 2.5296640396118164}
-03/04/2022 04:44:30 - INFO - codeparrot_training - Step 13008: {'lr': 0.0004932059892880016, 'samples': 6660608, 'steps': 13008, 'loss/train': 1.8345355987548828}
-03/04/2022 04:44:31 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/04/2022 04:44:35 - INFO - codeparrot_training - Step 13009: {'lr': 0.0004932047604778025, 'samples': 6661120, 'steps': 13009, 'loss/train': 1.686922311782837}
-03/04/2022 04:44:38 - INFO - codeparrot_training - Step 13010: {'lr': 0.0004932035315580188, 'samples': 6661632, 'steps': 13010, 'loss/train': 2.2182228565216064}
-03/04/2022 04:44:40 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 04:44:43 - INFO - codeparrot_training - Step 13011: {'lr': 0.0004932023025286516, 'samples': 6662144, 'steps': 13011, 'loss/train': 1.7188853025436401}
-03/04/2022 04:44:47 - INFO - codeparrot_training - Step 13012: {'lr': 0.0004932010733897012, 'samples': 6662656, 'steps': 13012, 'loss/train': 1.19495689868927}
-03/04/2022 04:44:48 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/04/2022 04:44:52 - INFO - codeparrot_training - Step 13013: {'lr': 0.000493199844141168, 'samples': 6663168, 'steps': 13013, 'loss/train': 1.7534539699554443}
-03/04/2022 04:44:55 - INFO - codeparrot_training - Step 13014: {'lr': 0.0004931986147830527, 'samples': 6663680, 'steps': 13014, 'loss/train': 1.6574273109436035}
-03/04/2022 04:44:56 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/04/2022 04:45:00 - INFO - codeparrot_training - Step 13015: {'lr': 0.000493197385315356, 'samples': 6664192, 'steps': 13015, 'loss/train': 1.9045538902282715}
-03/04/2022 04:45:03 - INFO - codeparrot_training - Step 13016: {'lr': 0.0004931961557380782, 'samples': 6664704, 'steps': 13016, 'loss/train': 2.185796022415161}
-03/04/2022 04:45:04 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/04/2022 04:45:09 - INFO - codeparrot_training - Step 13017: {'lr': 0.00049319492605122, 'samples': 6665216, 'steps': 13017, 'loss/train': 2.5011308193206787}
-03/04/2022 04:45:12 - INFO - codeparrot_training - Step 13018: {'lr': 0.000493193696254782, 'samples': 6665728, 'steps': 13018, 'loss/train': 2.4322144985198975}
-03/04/2022 04:45:12 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/04/2022 04:45:17 - INFO - codeparrot_training - Step 13019: {'lr': 0.0004931924663487646, 'samples': 6666240, 'steps': 13019, 'loss/train': 2.03501033782959}
-03/04/2022 04:45:20 - INFO - codeparrot_training - Step 13020: {'lr': 0.0004931912363331683, 'samples': 6666752, 'steps': 13020, 'loss/train': 0.7634372115135193}
-03/04/2022 04:45:21 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 04:45:25 - INFO - codeparrot_training - Step 13021: {'lr': 0.000493190006207994, 'samples': 6667264, 'steps': 13021, 'loss/train': 1.930714726448059}
-03/04/2022 04:45:28 - INFO - codeparrot_training - Step 13022: {'lr': 0.0004931887759732419, 'samples': 6667776, 'steps': 13022, 'loss/train': 2.4688990116119385}
-03/04/2022 04:45:29 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/04/2022 04:45:34 - INFO - codeparrot_training - Step 13023: {'lr': 0.0004931875456289128, 'samples': 6668288, 'steps': 13023, 'loss/train': 2.3624370098114014}
-03/04/2022 04:45:37 - INFO - codeparrot_training - Step 13024: {'lr': 0.000493186315175007, 'samples': 6668800, 'steps': 13024, 'loss/train': 2.6104118824005127}
-03/04/2022 04:45:38 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/04/2022 04:45:42 - INFO - codeparrot_training - Step 13025: {'lr': 0.0004931850846115253, 'samples': 6669312, 'steps': 13025, 'loss/train': 2.412381649017334}
-03/04/2022 04:45:46 - INFO - codeparrot_training - Step 13026: {'lr': 0.0004931838539384681, 'samples': 6669824, 'steps': 13026, 'loss/train': 2.2750113010406494}
-03/04/2022 04:45:47 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/04/2022 04:45:51 - INFO - codeparrot_training - Step 13027: {'lr': 0.0004931826231558361, 'samples': 6670336, 'steps': 13027, 'loss/train': 2.3127024173736572}
-03/04/2022 04:45:54 - INFO - codeparrot_training - Step 13028: {'lr': 0.0004931813922636297, 'samples': 6670848, 'steps': 13028, 'loss/train': 2.262516975402832}
-03/04/2022 04:45:55 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/04/2022 04:45:59 - INFO - codeparrot_training - Step 13029: {'lr': 0.0004931801612618494, 'samples': 6671360, 'steps': 13029, 'loss/train': 1.8127553462982178}
-03/04/2022 04:46:03 - INFO - codeparrot_training - Step 13030: {'lr': 0.0004931789301504961, 'samples': 6671872, 'steps': 13030, 'loss/train': 1.8857855796813965}
-03/04/2022 04:46:04 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/04/2022 04:46:08 - INFO - codeparrot_training - Step 13031: {'lr': 0.00049317769892957, 'samples': 6672384, 'steps': 13031, 'loss/train': 1.8495044708251953}
-03/04/2022 04:46:11 - INFO - codeparrot_training - Step 13032: {'lr': 0.0004931764675990718, 'samples': 6672896, 'steps': 13032, 'loss/train': 1.5869532823562622}
-03/04/2022 04:46:13 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/04/2022 04:46:16 - INFO - codeparrot_training - Step 13033: {'lr': 0.000493175236159002, 'samples': 6673408, 'steps': 13033, 'loss/train': 2.5857622623443604}
-03/04/2022 04:46:19 - INFO - codeparrot_training - Step 13034: {'lr': 0.0004931740046093612, 'samples': 6673920, 'steps': 13034, 'loss/train': 1.833348035812378}
-03/04/2022 04:46:20 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 04:46:25 - INFO - codeparrot_training - Step 13035: {'lr': 0.0004931727729501499, 'samples': 6674432, 'steps': 13035, 'loss/train': 1.9378812313079834}
-03/04/2022 04:46:28 - INFO - codeparrot_training - Step 13036: {'lr': 0.0004931715411813689, 'samples': 6674944, 'steps': 13036, 'loss/train': 6.495112419128418}
-03/04/2022 04:46:29 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/04/2022 04:46:33 - INFO - codeparrot_training - Step 13037: {'lr': 0.0004931703093030183, 'samples': 6675456, 'steps': 13037, 'loss/train': 1.5328007936477661}
-03/04/2022 04:46:36 - INFO - codeparrot_training - Step 13038: {'lr': 0.0004931690773150991, 'samples': 6675968, 'steps': 13038, 'loss/train': 2.1614878177642822}
-03/04/2022 04:46:37 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/04/2022 04:46:42 - INFO - codeparrot_training - Step 13039: {'lr': 0.0004931678452176116, 'samples': 6676480, 'steps': 13039, 'loss/train': 2.1284496784210205}
-03/04/2022 04:46:45 - INFO - codeparrot_training - Step 13040: {'lr': 0.0004931666130105563, 'samples': 6676992, 'steps': 13040, 'loss/train': 1.8892273902893066}
-03/04/2022 04:46:46 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 04:46:50 - INFO - codeparrot_training - Step 13041: {'lr': 0.0004931653806939341, 'samples': 6677504, 'steps': 13041, 'loss/train': 2.6189019680023193}
-03/04/2022 04:46:53 - INFO - codeparrot_training - Step 13042: {'lr': 0.0004931641482677452, 'samples': 6678016, 'steps': 13042, 'loss/train': 2.2841389179229736}
-03/04/2022 04:46:56 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 04:46:59 - INFO - codeparrot_training - Step 13043: {'lr': 0.0004931629157319904, 'samples': 6678528, 'steps': 13043, 'loss/train': 2.223841667175293}
-03/04/2022 04:47:02 - INFO - codeparrot_training - Step 13044: {'lr': 0.00049316168308667, 'samples': 6679040, 'steps': 13044, 'loss/train': 1.8374766111373901}
-03/04/2022 04:47:04 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/04/2022 04:47:07 - INFO - codeparrot_training - Step 13045: {'lr': 0.0004931604503317846, 'samples': 6679552, 'steps': 13045, 'loss/train': 2.441460371017456}
-03/04/2022 04:47:10 - INFO - codeparrot_training - Step 13046: {'lr': 0.0004931592174673351, 'samples': 6680064, 'steps': 13046, 'loss/train': 1.5849570035934448}
-03/04/2022 04:47:13 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/04/2022 04:47:16 - INFO - codeparrot_training - Step 13047: {'lr': 0.0004931579844933218, 'samples': 6680576, 'steps': 13047, 'loss/train': 2.41269588470459}
-03/04/2022 04:47:19 - INFO - codeparrot_training - Step 13048: {'lr': 0.0004931567514097451, 'samples': 6681088, 'steps': 13048, 'loss/train': 1.248486876487732}
-03/04/2022 04:47:21 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 04:47:24 - INFO - codeparrot_training - Step 13049: {'lr': 0.0004931555182166059, 'samples': 6681600, 'steps': 13049, 'loss/train': 1.459876537322998}
-03/04/2022 04:47:27 - INFO - codeparrot_training - Step 13050: {'lr': 0.0004931542849139044, 'samples': 6682112, 'steps': 13050, 'loss/train': 1.5182164907455444}
-03/04/2022 04:47:30 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/04/2022 04:47:33 - INFO - codeparrot_training - Step 13051: {'lr': 0.0004931530515016415, 'samples': 6682624, 'steps': 13051, 'loss/train': 2.364231824874878}
-03/04/2022 04:47:36 - INFO - codeparrot_training - Step 13052: {'lr': 0.0004931518179798175, 'samples': 6683136, 'steps': 13052, 'loss/train': 2.7719979286193848}
-03/04/2022 04:47:39 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 04:47:41 - INFO - codeparrot_training - Step 13053: {'lr': 0.000493150584348433, 'samples': 6683648, 'steps': 13053, 'loss/train': 2.293806791305542}
-03/04/2022 04:47:44 - INFO - codeparrot_training - Step 13054: {'lr': 0.0004931493506074886, 'samples': 6684160, 'steps': 13054, 'loss/train': 0.7397919297218323}
-03/04/2022 04:47:47 - INFO - codeparrot_training - Step 13055: {'lr': 0.0004931481167569849, 'samples': 6684672, 'steps': 13055, 'loss/train': 1.845484733581543}
-03/04/2022 04:47:47 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/04/2022 04:47:53 - INFO - codeparrot_training - Step 13056: {'lr': 0.0004931468827969223, 'samples': 6685184, 'steps': 13056, 'loss/train': 1.206874132156372}
-03/04/2022 04:47:56 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/04/2022 04:47:58 - INFO - codeparrot_training - Step 13057: {'lr': 0.0004931456487273017, 'samples': 6685696, 'steps': 13057, 'loss/train': 1.9216636419296265}
-03/04/2022 04:48:01 - INFO - codeparrot_training - Step 13058: {'lr': 0.0004931444145481233, 'samples': 6686208, 'steps': 13058, 'loss/train': 2.084033250808716}
-03/04/2022 04:48:04 - INFO - codeparrot_training - Skipping example with length 553 (seq_length=1024)
-03/04/2022 04:48:06 - INFO - codeparrot_training - Step 13059: {'lr': 0.0004931431802593877, 'samples': 6686720, 'steps': 13059, 'loss/train': 2.4302406311035156}
-03/04/2022 04:48:10 - INFO - codeparrot_training - Step 13060: {'lr': 0.0004931419458610956, 'samples': 6687232, 'steps': 13060, 'loss/train': 1.1606098413467407}
-03/04/2022 04:48:12 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/04/2022 04:48:15 - INFO - codeparrot_training - Step 13061: {'lr': 0.0004931407113532476, 'samples': 6687744, 'steps': 13061, 'loss/train': 2.402040719985962}
-03/04/2022 04:48:18 - INFO - codeparrot_training - Step 13062: {'lr': 0.000493139476735844, 'samples': 6688256, 'steps': 13062, 'loss/train': 2.6548843383789062}
-03/04/2022 04:48:21 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/04/2022 04:48:23 - INFO - codeparrot_training - Step 13063: {'lr': 0.0004931382420088855, 'samples': 6688768, 'steps': 13063, 'loss/train': 2.1598565578460693}
-03/04/2022 04:48:27 - INFO - codeparrot_training - Step 13064: {'lr': 0.0004931370071723728, 'samples': 6689280, 'steps': 13064, 'loss/train': 1.9783592224121094}
-03/04/2022 04:48:30 - INFO - codeparrot_training - Step 13065: {'lr': 0.0004931357722263061, 'samples': 6689792, 'steps': 13065, 'loss/train': 1.011223316192627}
-03/04/2022 04:48:30 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 04:48:35 - INFO - codeparrot_training - Step 13066: {'lr': 0.0004931345371706863, 'samples': 6690304, 'steps': 13066, 'loss/train': 2.394782781600952}
-03/04/2022 04:48:38 - INFO - codeparrot_training - Step 13067: {'lr': 0.0004931333020055139, 'samples': 6690816, 'steps': 13067, 'loss/train': 2.0652265548706055}
-03/04/2022 04:48:38 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/04/2022 04:48:44 - INFO - codeparrot_training - Step 13068: {'lr': 0.0004931320667307893, 'samples': 6691328, 'steps': 13068, 'loss/train': 2.139577865600586}
-03/04/2022 04:48:47 - INFO - codeparrot_training - Step 13069: {'lr': 0.0004931308313465132, 'samples': 6691840, 'steps': 13069, 'loss/train': 2.2279767990112305}
-03/04/2022 04:48:47 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/04/2022 04:48:52 - INFO - codeparrot_training - Step 13070: {'lr': 0.000493129595852686, 'samples': 6692352, 'steps': 13070, 'loss/train': 1.0295850038528442}
-03/04/2022 04:48:55 - INFO - codeparrot_training - Step 13071: {'lr': 0.0004931283602493084, 'samples': 6692864, 'steps': 13071, 'loss/train': 2.1095640659332275}
-03/04/2022 04:48:55 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 04:49:00 - INFO - codeparrot_training - Step 13072: {'lr': 0.0004931271245363809, 'samples': 6693376, 'steps': 13072, 'loss/train': 2.1850006580352783}
-03/04/2022 04:49:04 - INFO - codeparrot_training - Step 13073: {'lr': 0.0004931258887139041, 'samples': 6693888, 'steps': 13073, 'loss/train': 2.08758282661438}
-03/04/2022 04:49:04 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/04/2022 04:49:09 - INFO - codeparrot_training - Step 13074: {'lr': 0.0004931246527818785, 'samples': 6694400, 'steps': 13074, 'loss/train': 2.3706142902374268}
-03/04/2022 04:49:12 - INFO - codeparrot_training - Step 13075: {'lr': 0.0004931234167403047, 'samples': 6694912, 'steps': 13075, 'loss/train': 2.0335452556610107}
-03/04/2022 04:49:12 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/04/2022 04:49:17 - INFO - codeparrot_training - Step 13076: {'lr': 0.0004931221805891833, 'samples': 6695424, 'steps': 13076, 'loss/train': 1.9239863157272339}
-03/04/2022 04:49:20 - INFO - codeparrot_training - Step 13077: {'lr': 0.0004931209443285147, 'samples': 6695936, 'steps': 13077, 'loss/train': 1.974662184715271}
-03/04/2022 04:49:20 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 04:49:26 - INFO - codeparrot_training - Step 13078: {'lr': 0.0004931197079582996, 'samples': 6696448, 'steps': 13078, 'loss/train': 2.2348737716674805}
-03/04/2022 04:49:29 - INFO - codeparrot_training - Step 13079: {'lr': 0.0004931184714785385, 'samples': 6696960, 'steps': 13079, 'loss/train': 2.0080044269561768}
-03/04/2022 04:49:29 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/04/2022 04:49:34 - INFO - codeparrot_training - Step 13080: {'lr': 0.000493117234889232, 'samples': 6697472, 'steps': 13080, 'loss/train': 2.1045174598693848}
-03/04/2022 04:49:37 - INFO - codeparrot_training - Step 13081: {'lr': 0.0004931159981903805, 'samples': 6697984, 'steps': 13081, 'loss/train': 2.232595205307007}
-03/04/2022 04:49:37 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 04:49:42 - INFO - codeparrot_training - Step 13082: {'lr': 0.0004931147613819848, 'samples': 6698496, 'steps': 13082, 'loss/train': 1.6593393087387085}
-03/04/2022 04:49:46 - INFO - codeparrot_training - Step 13083: {'lr': 0.0004931135244640453, 'samples': 6699008, 'steps': 13083, 'loss/train': 2.014519691467285}
-03/04/2022 04:49:46 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 04:49:51 - INFO - codeparrot_training - Step 13084: {'lr': 0.0004931122874365627, 'samples': 6699520, 'steps': 13084, 'loss/train': 1.5681724548339844}
-03/04/2022 04:49:54 - INFO - codeparrot_training - Step 13085: {'lr': 0.0004931110502995374, 'samples': 6700032, 'steps': 13085, 'loss/train': 1.9996986389160156}
-03/04/2022 04:49:54 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 04:49:59 - INFO - codeparrot_training - Step 13086: {'lr': 0.0004931098130529699, 'samples': 6700544, 'steps': 13086, 'loss/train': 2.6853280067443848}
-03/04/2022 04:50:02 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/04/2022 04:50:05 - INFO - codeparrot_training - Step 13087: {'lr': 0.000493108575696861, 'samples': 6701056, 'steps': 13087, 'loss/train': 1.7992584705352783}
-03/04/2022 04:50:08 - INFO - codeparrot_training - Step 13088: {'lr': 0.0004931073382312111, 'samples': 6701568, 'steps': 13088, 'loss/train': 0.7160924077033997}
-03/04/2022 04:50:11 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/04/2022 04:50:13 - INFO - codeparrot_training - Step 13089: {'lr': 0.0004931061006560207, 'samples': 6702080, 'steps': 13089, 'loss/train': 1.5267868041992188}
-03/04/2022 04:50:16 - INFO - codeparrot_training - Step 13090: {'lr': 0.0004931048629712905, 'samples': 6702592, 'steps': 13090, 'loss/train': 2.168081045150757}
-03/04/2022 04:50:19 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 04:50:22 - INFO - codeparrot_training - Step 13091: {'lr': 0.000493103625177021, 'samples': 6703104, 'steps': 13091, 'loss/train': 1.327993631362915}
-03/04/2022 04:50:25 - INFO - codeparrot_training - Step 13092: {'lr': 0.0004931023872732128, 'samples': 6703616, 'steps': 13092, 'loss/train': 0.6715813875198364}
-03/04/2022 04:50:28 - INFO - codeparrot_training - Step 13093: {'lr': 0.0004931011492598664, 'samples': 6704128, 'steps': 13093, 'loss/train': 2.0834357738494873}
-03/04/2022 04:50:28 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 04:50:33 - INFO - codeparrot_training - Step 13094: {'lr': 0.0004930999111369824, 'samples': 6704640, 'steps': 13094, 'loss/train': 2.040203809738159}
-03/04/2022 04:50:37 - INFO - codeparrot_training - Step 13095: {'lr': 0.0004930986729045613, 'samples': 6705152, 'steps': 13095, 'loss/train': 2.3114678859710693}
-03/04/2022 04:50:37 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 04:50:42 - INFO - codeparrot_training - Step 13096: {'lr': 0.0004930974345626036, 'samples': 6705664, 'steps': 13096, 'loss/train': 2.2261366844177246}
-03/04/2022 04:50:45 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 04:50:47 - INFO - codeparrot_training - Step 13097: {'lr': 0.00049309619611111, 'samples': 6706176, 'steps': 13097, 'loss/train': 1.8477181196212769}
-03/04/2022 04:50:50 - INFO - codeparrot_training - Step 13098: {'lr': 0.000493094957550081, 'samples': 6706688, 'steps': 13098, 'loss/train': 1.3578797578811646}
-03/04/2022 04:50:53 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/04/2022 04:50:55 - INFO - codeparrot_training - Step 13099: {'lr': 0.0004930937188795172, 'samples': 6707200, 'steps': 13099, 'loss/train': 0.15270721912384033}
-03/04/2022 04:50:59 - INFO - codeparrot_training - Step 13100: {'lr': 0.0004930924800994192, 'samples': 6707712, 'steps': 13100, 'loss/train': 0.8016639947891235}
-03/04/2022 04:51:01 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 04:51:04 - INFO - codeparrot_training - Step 13101: {'lr': 0.0004930912412097874, 'samples': 6708224, 'steps': 13101, 'loss/train': 1.7989773750305176}
-03/04/2022 04:51:07 - INFO - codeparrot_training - Step 13102: {'lr': 0.0004930900022106224, 'samples': 6708736, 'steps': 13102, 'loss/train': 1.3576291799545288}
-03/04/2022 04:51:09 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/04/2022 04:51:12 - INFO - codeparrot_training - Step 13103: {'lr': 0.0004930887631019248, 'samples': 6709248, 'steps': 13103, 'loss/train': 0.7848191261291504}
-03/04/2022 04:51:15 - INFO - codeparrot_training - Step 13104: {'lr': 0.0004930875238836951, 'samples': 6709760, 'steps': 13104, 'loss/train': 1.528442621231079}
-03/04/2022 04:51:18 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/04/2022 04:51:21 - INFO - codeparrot_training - Step 13105: {'lr': 0.000493086284555934, 'samples': 6710272, 'steps': 13105, 'loss/train': 1.8855589628219604}
-03/04/2022 04:51:24 - INFO - codeparrot_training - Step 13106: {'lr': 0.0004930850451186421, 'samples': 6710784, 'steps': 13106, 'loss/train': 2.2330942153930664}
-03/04/2022 04:51:26 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/04/2022 04:51:29 - INFO - codeparrot_training - Step 13107: {'lr': 0.0004930838055718196, 'samples': 6711296, 'steps': 13107, 'loss/train': 0.6903477311134338}
-03/04/2022 04:51:32 - INFO - codeparrot_training - Step 13108: {'lr': 0.0004930825659154674, 'samples': 6711808, 'steps': 13108, 'loss/train': 1.7454627752304077}
-03/04/2022 04:51:35 - INFO - codeparrot_training - Step 13109: {'lr': 0.000493081326149586, 'samples': 6712320, 'steps': 13109, 'loss/train': 1.7845584154129028}
-03/04/2022 04:51:36 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 04:51:41 - INFO - codeparrot_training - Step 13110: {'lr': 0.0004930800862741758, 'samples': 6712832, 'steps': 13110, 'loss/train': 1.4773979187011719}
-03/04/2022 04:51:44 - INFO - codeparrot_training - Step 13111: {'lr': 0.0004930788462892375, 'samples': 6713344, 'steps': 13111, 'loss/train': 2.4963226318359375}
-03/04/2022 04:51:44 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/04/2022 04:51:49 - INFO - codeparrot_training - Step 13112: {'lr': 0.0004930776061947716, 'samples': 6713856, 'steps': 13112, 'loss/train': 2.2531180381774902}
-03/04/2022 04:51:52 - INFO - codeparrot_training - Step 13113: {'lr': 0.0004930763659907788, 'samples': 6714368, 'steps': 13113, 'loss/train': 1.9713128805160522}
-03/04/2022 04:51:52 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/04/2022 04:51:58 - INFO - codeparrot_training - Step 13114: {'lr': 0.0004930751256772593, 'samples': 6714880, 'steps': 13114, 'loss/train': 1.3396497964859009}
-03/04/2022 04:52:01 - INFO - codeparrot_training - Step 13115: {'lr': 0.0004930738852542141, 'samples': 6715392, 'steps': 13115, 'loss/train': 2.249760627746582}
-03/04/2022 04:52:01 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 04:52:06 - INFO - codeparrot_training - Step 13116: {'lr': 0.0004930726447216435, 'samples': 6715904, 'steps': 13116, 'loss/train': 1.340121865272522}
-03/04/2022 04:52:09 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/04/2022 04:52:12 - INFO - codeparrot_training - Step 13117: {'lr': 0.0004930714040795481, 'samples': 6716416, 'steps': 13117, 'loss/train': 1.5547151565551758}
-03/04/2022 04:52:15 - INFO - codeparrot_training - Step 13118: {'lr': 0.0004930701633279285, 'samples': 6716928, 'steps': 13118, 'loss/train': 1.7666821479797363}
-03/04/2022 04:52:18 - INFO - codeparrot_training - Step 13119: {'lr': 0.0004930689224667853, 'samples': 6717440, 'steps': 13119, 'loss/train': 1.6436291933059692}
-03/04/2022 04:52:18 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/04/2022 04:52:23 - INFO - codeparrot_training - Step 13120: {'lr': 0.0004930676814961189, 'samples': 6717952, 'steps': 13120, 'loss/train': 2.2763187885284424}
-03/04/2022 04:52:26 - INFO - codeparrot_training - Step 13121: {'lr': 0.00049306644041593, 'samples': 6718464, 'steps': 13121, 'loss/train': 7.966343402862549}
-03/04/2022 04:52:27 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/04/2022 04:52:32 - INFO - codeparrot_training - Step 13122: {'lr': 0.0004930651992262191, 'samples': 6718976, 'steps': 13122, 'loss/train': 1.241257905960083}
-03/04/2022 04:52:35 - INFO - codeparrot_training - Step 13123: {'lr': 0.0004930639579269866, 'samples': 6719488, 'steps': 13123, 'loss/train': 1.332110047340393}
-03/04/2022 04:52:35 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/04/2022 04:52:40 - INFO - codeparrot_training - Step 13124: {'lr': 0.0004930627165182335, 'samples': 6720000, 'steps': 13124, 'loss/train': 1.765529990196228}
-03/04/2022 04:52:43 - INFO - codeparrot_training - Step 13125: {'lr': 0.00049306147499996, 'samples': 6720512, 'steps': 13125, 'loss/train': 1.4806770086288452}
-03/04/2022 04:52:44 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/04/2022 04:52:48 - INFO - codeparrot_training - Step 13126: {'lr': 0.0004930602333721667, 'samples': 6721024, 'steps': 13126, 'loss/train': 1.9269587993621826}
-03/04/2022 04:52:52 - INFO - codeparrot_training - Step 13127: {'lr': 0.0004930589916348542, 'samples': 6721536, 'steps': 13127, 'loss/train': 2.691502094268799}
-03/04/2022 04:52:52 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 04:52:57 - INFO - codeparrot_training - Step 13128: {'lr': 0.0004930577497880231, 'samples': 6722048, 'steps': 13128, 'loss/train': 2.1468210220336914}
-03/04/2022 04:53:00 - INFO - codeparrot_training - Step 13129: {'lr': 0.000493056507831674, 'samples': 6722560, 'steps': 13129, 'loss/train': 2.2745869159698486}
-03/04/2022 04:53:00 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 04:53:05 - INFO - codeparrot_training - Step 13130: {'lr': 0.0004930552657658073, 'samples': 6723072, 'steps': 13130, 'loss/train': 2.7480051517486572}
-03/04/2022 04:53:08 - INFO - codeparrot_training - Step 13131: {'lr': 0.0004930540235904237, 'samples': 6723584, 'steps': 13131, 'loss/train': 1.7749087810516357}
-03/04/2022 04:53:08 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/04/2022 04:53:14 - INFO - codeparrot_training - Step 13132: {'lr': 0.0004930527813055237, 'samples': 6724096, 'steps': 13132, 'loss/train': 2.6740431785583496}
-03/04/2022 04:53:16 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 04:53:19 - INFO - codeparrot_training - Step 13133: {'lr': 0.0004930515389111078, 'samples': 6724608, 'steps': 13133, 'loss/train': 1.7918955087661743}
-03/04/2022 04:53:22 - INFO - codeparrot_training - Step 13134: {'lr': 0.0004930502964071767, 'samples': 6725120, 'steps': 13134, 'loss/train': 2.820740222930908}
-03/04/2022 04:53:25 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 04:53:27 - INFO - codeparrot_training - Step 13135: {'lr': 0.0004930490537937309, 'samples': 6725632, 'steps': 13135, 'loss/train': 2.945972204208374}
-03/04/2022 04:53:30 - INFO - codeparrot_training - Step 13136: {'lr': 0.0004930478110707709, 'samples': 6726144, 'steps': 13136, 'loss/train': 2.489427328109741}
-03/04/2022 04:53:33 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/04/2022 04:53:36 - INFO - codeparrot_training - Step 13137: {'lr': 0.0004930465682382973, 'samples': 6726656, 'steps': 13137, 'loss/train': 2.226686954498291}
-03/04/2022 04:53:39 - INFO - codeparrot_training - Step 13138: {'lr': 0.0004930453252963107, 'samples': 6727168, 'steps': 13138, 'loss/train': 1.1934903860092163}
-03/04/2022 04:53:41 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 04:53:44 - INFO - codeparrot_training - Step 13139: {'lr': 0.0004930440822448115, 'samples': 6727680, 'steps': 13139, 'loss/train': 0.6670829057693481}
-03/04/2022 04:53:47 - INFO - codeparrot_training - Step 13140: {'lr': 0.0004930428390838006, 'samples': 6728192, 'steps': 13140, 'loss/train': 1.6291142702102661}
-03/04/2022 04:53:50 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/04/2022 04:53:52 - INFO - codeparrot_training - Step 13141: {'lr': 0.0004930415958132782, 'samples': 6728704, 'steps': 13141, 'loss/train': 2.8551955223083496}
-03/04/2022 04:53:56 - INFO - codeparrot_training - Step 13142: {'lr': 0.0004930403524332451, 'samples': 6729216, 'steps': 13142, 'loss/train': 2.057386875152588}
-03/04/2022 04:53:58 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/04/2022 04:54:01 - INFO - codeparrot_training - Step 13143: {'lr': 0.0004930391089437017, 'samples': 6729728, 'steps': 13143, 'loss/train': 1.8200455904006958}
-03/04/2022 04:54:04 - INFO - codeparrot_training - Step 13144: {'lr': 0.0004930378653446487, 'samples': 6730240, 'steps': 13144, 'loss/train': 1.43320631980896}
-03/04/2022 04:54:06 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 04:54:09 - INFO - codeparrot_training - Step 13145: {'lr': 0.0004930366216360865, 'samples': 6730752, 'steps': 13145, 'loss/train': 1.8586037158966064}
-03/04/2022 04:54:12 - INFO - codeparrot_training - Step 13146: {'lr': 0.0004930353778180158, 'samples': 6731264, 'steps': 13146, 'loss/train': 1.9915502071380615}
-03/04/2022 04:54:15 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/04/2022 04:54:18 - INFO - codeparrot_training - Step 13147: {'lr': 0.0004930341338904371, 'samples': 6731776, 'steps': 13147, 'loss/train': 1.7118264436721802}
-03/04/2022 04:54:21 - INFO - codeparrot_training - Step 13148: {'lr': 0.000493032889853351, 'samples': 6732288, 'steps': 13148, 'loss/train': 2.615612506866455}
-03/04/2022 04:54:25 - INFO - codeparrot_training - Step 13149: {'lr': 0.0004930316457067579, 'samples': 6732800, 'steps': 13149, 'loss/train': 3.477891206741333}
-03/04/2022 04:54:25 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/04/2022 04:54:30 - INFO - codeparrot_training - Step 13150: {'lr': 0.0004930304014506586, 'samples': 6733312, 'steps': 13150, 'loss/train': 1.6123292446136475}
-03/04/2022 04:54:33 - INFO - codeparrot_training - Step 13151: {'lr': 0.0004930291570850536, 'samples': 6733824, 'steps': 13151, 'loss/train': 1.9766733646392822}
-03/04/2022 04:54:33 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 04:54:38 - INFO - codeparrot_training - Step 13152: {'lr': 0.0004930279126099433, 'samples': 6734336, 'steps': 13152, 'loss/train': 1.7321412563323975}
-03/04/2022 04:54:41 - INFO - codeparrot_training - Step 13153: {'lr': 0.0004930266680253284, 'samples': 6734848, 'steps': 13153, 'loss/train': 1.9978100061416626}
-03/04/2022 04:54:41 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/04/2022 04:54:47 - INFO - codeparrot_training - Step 13154: {'lr': 0.0004930254233312095, 'samples': 6735360, 'steps': 13154, 'loss/train': 1.7233209609985352}
-03/04/2022 04:54:49 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/04/2022 04:54:52 - INFO - codeparrot_training - Step 13155: {'lr': 0.000493024178527587, 'samples': 6735872, 'steps': 13155, 'loss/train': 2.2131097316741943}
-03/04/2022 04:54:55 - INFO - codeparrot_training - Step 13156: {'lr': 0.0004930229336144616, 'samples': 6736384, 'steps': 13156, 'loss/train': 1.8466347455978394}
-03/04/2022 04:54:58 - INFO - codeparrot_training - Step 13157: {'lr': 0.0004930216885918339, 'samples': 6736896, 'steps': 13157, 'loss/train': 1.5629072189331055}
-03/04/2022 04:54:58 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/04/2022 04:55:04 - INFO - codeparrot_training - Step 13158: {'lr': 0.0004930204434597042, 'samples': 6737408, 'steps': 13158, 'loss/train': 2.001706838607788}
-03/04/2022 04:55:07 - INFO - codeparrot_training - Step 13159: {'lr': 0.0004930191982180734, 'samples': 6737920, 'steps': 13159, 'loss/train': 1.4211230278015137}
-03/04/2022 04:55:07 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/04/2022 04:55:12 - INFO - codeparrot_training - Step 13160: {'lr': 0.0004930179528669418, 'samples': 6738432, 'steps': 13160, 'loss/train': 2.254640579223633}
-03/04/2022 04:55:15 - INFO - codeparrot_training - Step 13161: {'lr': 0.0004930167074063101, 'samples': 6738944, 'steps': 13161, 'loss/train': 1.4558978080749512}
-03/04/2022 04:55:15 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 04:55:21 - INFO - codeparrot_training - Step 13162: {'lr': 0.0004930154618361789, 'samples': 6739456, 'steps': 13162, 'loss/train': 1.060451865196228}
-03/04/2022 04:55:24 - INFO - codeparrot_training - Step 13163: {'lr': 0.0004930142161565486, 'samples': 6739968, 'steps': 13163, 'loss/train': 2.160736560821533}
-03/04/2022 04:55:24 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/04/2022 04:55:29 - INFO - codeparrot_training - Step 13164: {'lr': 0.0004930129703674198, 'samples': 6740480, 'steps': 13164, 'loss/train': 1.7798265218734741}
-03/04/2022 04:55:32 - INFO - codeparrot_training - Step 13165: {'lr': 0.0004930117244687931, 'samples': 6740992, 'steps': 13165, 'loss/train': 1.6706347465515137}
-03/04/2022 04:55:32 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 04:55:38 - INFO - codeparrot_training - Step 13166: {'lr': 0.0004930104784606692, 'samples': 6741504, 'steps': 13166, 'loss/train': 1.6737663745880127}
-03/04/2022 04:55:41 - INFO - codeparrot_training - Step 13167: {'lr': 0.0004930092323430484, 'samples': 6742016, 'steps': 13167, 'loss/train': 1.349854826927185}
-03/04/2022 04:55:41 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 04:55:46 - INFO - codeparrot_training - Step 13168: {'lr': 0.0004930079861159315, 'samples': 6742528, 'steps': 13168, 'loss/train': 2.0092456340789795}
-03/04/2022 04:55:50 - INFO - codeparrot_training - Step 13169: {'lr': 0.0004930067397793188, 'samples': 6743040, 'steps': 13169, 'loss/train': 2.44942307472229}
-03/04/2022 04:55:50 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/04/2022 04:55:55 - INFO - codeparrot_training - Step 13170: {'lr': 0.0004930054933332111, 'samples': 6743552, 'steps': 13170, 'loss/train': 1.7770360708236694}
-03/04/2022 04:55:58 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/04/2022 04:56:00 - INFO - codeparrot_training - Step 13171: {'lr': 0.0004930042467776089, 'samples': 6744064, 'steps': 13171, 'loss/train': 1.9960795640945435}
-03/04/2022 04:56:04 - INFO - codeparrot_training - Step 13172: {'lr': 0.0004930030001125128, 'samples': 6744576, 'steps': 13172, 'loss/train': 1.8534011840820312}
-03/04/2022 04:56:07 - INFO - codeparrot_training - Step 13173: {'lr': 0.000493001753337923, 'samples': 6745088, 'steps': 13173, 'loss/train': 2.5233731269836426}
-03/04/2022 04:56:07 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/04/2022 04:56:12 - INFO - codeparrot_training - Step 13174: {'lr': 0.0004930005064538406, 'samples': 6745600, 'steps': 13174, 'loss/train': 1.1840883493423462}
-03/04/2022 04:56:15 - INFO - codeparrot_training - Step 13175: {'lr': 0.0004929992594602659, 'samples': 6746112, 'steps': 13175, 'loss/train': 2.0720021724700928}
-03/04/2022 04:56:17 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/04/2022 04:56:21 - INFO - codeparrot_training - Step 13176: {'lr': 0.0004929980123571995, 'samples': 6746624, 'steps': 13176, 'loss/train': 2.6416914463043213}
-03/04/2022 04:56:24 - INFO - codeparrot_training - Step 13177: {'lr': 0.000492996765144642, 'samples': 6747136, 'steps': 13177, 'loss/train': 1.3721624612808228}
-03/04/2022 04:56:25 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 04:56:29 - INFO - codeparrot_training - Step 13178: {'lr': 0.0004929955178225938, 'samples': 6747648, 'steps': 13178, 'loss/train': 2.3114938735961914}
-03/04/2022 04:56:32 - INFO - codeparrot_training - Step 13179: {'lr': 0.0004929942703910556, 'samples': 6748160, 'steps': 13179, 'loss/train': 0.7970108389854431}
-03/04/2022 04:56:35 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/04/2022 04:56:38 - INFO - codeparrot_training - Step 13180: {'lr': 0.0004929930228500279, 'samples': 6748672, 'steps': 13180, 'loss/train': 2.0473430156707764}
-03/04/2022 04:56:41 - INFO - codeparrot_training - Step 13181: {'lr': 0.0004929917751995114, 'samples': 6749184, 'steps': 13181, 'loss/train': 1.8346039056777954}
-03/04/2022 04:56:44 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 04:56:46 - INFO - codeparrot_training - Step 13182: {'lr': 0.0004929905274395064, 'samples': 6749696, 'steps': 13182, 'loss/train': 1.9943147897720337}
-03/04/2022 04:56:49 - INFO - codeparrot_training - Step 13183: {'lr': 0.0004929892795700137, 'samples': 6750208, 'steps': 13183, 'loss/train': 1.8089057207107544}
-03/04/2022 04:56:52 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 04:56:55 - INFO - codeparrot_training - Step 13184: {'lr': 0.0004929880315910338, 'samples': 6750720, 'steps': 13184, 'loss/train': 1.6732630729675293}
-03/04/2022 04:56:58 - INFO - codeparrot_training - Step 13185: {'lr': 0.0004929867835025672, 'samples': 6751232, 'steps': 13185, 'loss/train': 2.432166337966919}
-03/04/2022 04:57:00 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/04/2022 04:57:03 - INFO - codeparrot_training - Step 13186: {'lr': 0.0004929855353046145, 'samples': 6751744, 'steps': 13186, 'loss/train': 1.9487863779067993}
-03/04/2022 04:57:06 - INFO - codeparrot_training - Step 13187: {'lr': 0.0004929842869971763, 'samples': 6752256, 'steps': 13187, 'loss/train': 2.0110366344451904}
-03/04/2022 04:57:09 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 04:57:11 - INFO - codeparrot_training - Step 13188: {'lr': 0.000492983038580253, 'samples': 6752768, 'steps': 13188, 'loss/train': 2.3208813667297363}
-03/04/2022 04:57:15 - INFO - codeparrot_training - Step 13189: {'lr': 0.0004929817900538455, 'samples': 6753280, 'steps': 13189, 'loss/train': 1.8502918481826782}
-03/04/2022 04:57:17 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/04/2022 04:57:20 - INFO - codeparrot_training - Step 13190: {'lr': 0.000492980541417954, 'samples': 6753792, 'steps': 13190, 'loss/train': 1.1478374004364014}
-03/04/2022 04:57:23 - INFO - codeparrot_training - Step 13191: {'lr': 0.0004929792926725794, 'samples': 6754304, 'steps': 13191, 'loss/train': 1.371823787689209}
-03/04/2022 04:57:26 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 04:57:28 - INFO - codeparrot_training - Step 13192: {'lr': 0.000492978043817722, 'samples': 6754816, 'steps': 13192, 'loss/train': 2.5858101844787598}
-03/04/2022 04:57:31 - INFO - codeparrot_training - Step 13193: {'lr': 0.0004929767948533823, 'samples': 6755328, 'steps': 13193, 'loss/train': 2.253326654434204}
-03/04/2022 04:57:34 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 04:57:37 - INFO - codeparrot_training - Step 13194: {'lr': 0.0004929755457795612, 'samples': 6755840, 'steps': 13194, 'loss/train': 1.6029647588729858}
-03/04/2022 04:57:40 - INFO - codeparrot_training - Step 13195: {'lr': 0.0004929742965962589, 'samples': 6756352, 'steps': 13195, 'loss/train': 1.5241855382919312}
-03/04/2022 04:57:42 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/04/2022 04:57:45 - INFO - codeparrot_training - Step 13196: {'lr': 0.0004929730473034763, 'samples': 6756864, 'steps': 13196, 'loss/train': 1.7500392198562622}
-03/04/2022 04:57:48 - INFO - codeparrot_training - Step 13197: {'lr': 0.0004929717979012136, 'samples': 6757376, 'steps': 13197, 'loss/train': 2.2778196334838867}
-03/04/2022 04:57:51 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/04/2022 04:57:54 - INFO - codeparrot_training - Step 13198: {'lr': 0.0004929705483894717, 'samples': 6757888, 'steps': 13198, 'loss/train': 2.0819475650787354}
-03/04/2022 04:57:57 - INFO - codeparrot_training - Step 13199: {'lr': 0.000492969298768251, 'samples': 6758400, 'steps': 13199, 'loss/train': 1.6904313564300537}
-03/04/2022 04:57:59 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/04/2022 04:58:02 - INFO - codeparrot_training - Step 13200: {'lr': 0.000492968049037552, 'samples': 6758912, 'steps': 13200, 'loss/train': 2.0165891647338867}
-03/04/2022 04:58:05 - INFO - codeparrot_training - Step 13201: {'lr': 0.0004929667991973754, 'samples': 6759424, 'steps': 13201, 'loss/train': 2.4619107246398926}
-03/04/2022 04:58:09 - INFO - codeparrot_training - Step 13202: {'lr': 0.0004929655492477218, 'samples': 6759936, 'steps': 13202, 'loss/train': 1.4771134853363037}
-03/04/2022 04:58:09 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/04/2022 04:58:14 - INFO - codeparrot_training - Step 13203: {'lr': 0.0004929642991885916, 'samples': 6760448, 'steps': 13203, 'loss/train': 2.379103899002075}
-03/04/2022 04:58:17 - INFO - codeparrot_training - Step 13204: {'lr': 0.0004929630490199854, 'samples': 6760960, 'steps': 13204, 'loss/train': 2.2157578468322754}
-03/04/2022 04:58:18 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/04/2022 04:58:22 - INFO - codeparrot_training - Step 13205: {'lr': 0.0004929617987419039, 'samples': 6761472, 'steps': 13205, 'loss/train': 2.126471519470215}
-03/04/2022 04:58:25 - INFO - codeparrot_training - Step 13206: {'lr': 0.0004929605483543474, 'samples': 6761984, 'steps': 13206, 'loss/train': 1.6909995079040527}
-03/04/2022 04:58:26 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 04:58:31 - INFO - codeparrot_training - Step 13207: {'lr': 0.0004929592978573168, 'samples': 6762496, 'steps': 13207, 'loss/train': 2.614638328552246}
-03/04/2022 04:58:34 - INFO - codeparrot_training - Step 13208: {'lr': 0.0004929580472508124, 'samples': 6763008, 'steps': 13208, 'loss/train': 1.3411011695861816}
-03/04/2022 04:58:34 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/04/2022 04:58:39 - INFO - codeparrot_training - Step 13209: {'lr': 0.0004929567965348347, 'samples': 6763520, 'steps': 13209, 'loss/train': 1.8276851177215576}
-03/04/2022 04:58:42 - INFO - codeparrot_training - Step 13210: {'lr': 0.0004929555457093847, 'samples': 6764032, 'steps': 13210, 'loss/train': 1.3238048553466797}
-03/04/2022 04:58:43 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 04:58:48 - INFO - codeparrot_training - Step 13211: {'lr': 0.0004929542947744625, 'samples': 6764544, 'steps': 13211, 'loss/train': 1.957888126373291}
-03/04/2022 04:58:51 - INFO - codeparrot_training - Step 13212: {'lr': 0.0004929530437300689, 'samples': 6765056, 'steps': 13212, 'loss/train': 1.9819663763046265}
-03/04/2022 04:58:51 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/04/2022 04:58:56 - INFO - codeparrot_training - Step 13213: {'lr': 0.0004929517925762045, 'samples': 6765568, 'steps': 13213, 'loss/train': 2.2157325744628906}
-03/04/2022 04:58:59 - INFO - codeparrot_training - Step 13214: {'lr': 0.0004929505413128696, 'samples': 6766080, 'steps': 13214, 'loss/train': 2.316343069076538}
-03/04/2022 04:59:00 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 04:59:04 - INFO - codeparrot_training - Step 13215: {'lr': 0.000492949289940065, 'samples': 6766592, 'steps': 13215, 'loss/train': 1.8990188837051392}
-03/04/2022 04:59:08 - INFO - codeparrot_training - Step 13216: {'lr': 0.0004929480384577912, 'samples': 6767104, 'steps': 13216, 'loss/train': 1.8238246440887451}
-03/04/2022 04:59:08 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/04/2022 04:59:13 - INFO - codeparrot_training - Step 13217: {'lr': 0.0004929467868660487, 'samples': 6767616, 'steps': 13217, 'loss/train': 1.838107705116272}
-03/04/2022 04:59:16 - INFO - codeparrot_training - Step 13218: {'lr': 0.0004929455351648383, 'samples': 6768128, 'steps': 13218, 'loss/train': 2.3382387161254883}
-03/04/2022 04:59:17 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/04/2022 04:59:21 - INFO - codeparrot_training - Step 13219: {'lr': 0.0004929442833541603, 'samples': 6768640, 'steps': 13219, 'loss/train': 1.9942933320999146}
-03/04/2022 04:59:25 - INFO - codeparrot_training - Step 13220: {'lr': 0.0004929430314340154, 'samples': 6769152, 'steps': 13220, 'loss/train': 1.8104296922683716}
-03/04/2022 04:59:25 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 04:59:30 - INFO - codeparrot_training - Step 13221: {'lr': 0.000492941779404404, 'samples': 6769664, 'steps': 13221, 'loss/train': 1.942964792251587}
-03/04/2022 04:59:33 - INFO - codeparrot_training - Step 13222: {'lr': 0.0004929405272653269, 'samples': 6770176, 'steps': 13222, 'loss/train': 2.214965343475342}
-03/04/2022 04:59:33 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 04:59:38 - INFO - codeparrot_training - Step 13223: {'lr': 0.0004929392750167845, 'samples': 6770688, 'steps': 13223, 'loss/train': 0.8616025447845459}
-03/04/2022 04:59:41 - INFO - codeparrot_training - Step 13224: {'lr': 0.0004929380226587774, 'samples': 6771200, 'steps': 13224, 'loss/train': 2.1993730068206787}
-03/04/2022 04:59:42 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/04/2022 04:59:47 - INFO - codeparrot_training - Step 13225: {'lr': 0.0004929367701913062, 'samples': 6771712, 'steps': 13225, 'loss/train': 1.4711788892745972}
-03/04/2022 04:59:50 - INFO - codeparrot_training - Step 13226: {'lr': 0.0004929355176143714, 'samples': 6772224, 'steps': 13226, 'loss/train': 2.344313621520996}
-03/04/2022 04:59:50 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 04:59:55 - INFO - codeparrot_training - Step 13227: {'lr': 0.0004929342649279736, 'samples': 6772736, 'steps': 13227, 'loss/train': 2.3981878757476807}
-03/04/2022 04:59:58 - INFO - codeparrot_training - Step 13228: {'lr': 0.0004929330121321134, 'samples': 6773248, 'steps': 13228, 'loss/train': 1.5895262956619263}
-03/04/2022 04:59:59 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/04/2022 05:00:04 - INFO - codeparrot_training - Step 13229: {'lr': 0.0004929317592267913, 'samples': 6773760, 'steps': 13229, 'loss/train': 2.0848426818847656}
-03/04/2022 05:00:07 - INFO - codeparrot_training - Step 13230: {'lr': 0.000492930506212008, 'samples': 6774272, 'steps': 13230, 'loss/train': 1.9671871662139893}
-03/04/2022 05:00:07 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 05:00:12 - INFO - codeparrot_training - Step 13231: {'lr': 0.0004929292530877638, 'samples': 6774784, 'steps': 13231, 'loss/train': 1.267630934715271}
-03/04/2022 05:00:15 - INFO - codeparrot_training - Step 13232: {'lr': 0.0004929279998540596, 'samples': 6775296, 'steps': 13232, 'loss/train': 2.5629351139068604}
-03/04/2022 05:00:15 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/04/2022 05:00:20 - INFO - codeparrot_training - Step 13233: {'lr': 0.0004929267465108956, 'samples': 6775808, 'steps': 13233, 'loss/train': 2.2821044921875}
-03/04/2022 05:00:24 - INFO - codeparrot_training - Step 13234: {'lr': 0.0004929254930582728, 'samples': 6776320, 'steps': 13234, 'loss/train': 1.6690943241119385}
-03/04/2022 05:00:24 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/04/2022 05:00:29 - INFO - codeparrot_training - Step 13235: {'lr': 0.0004929242394961914, 'samples': 6776832, 'steps': 13235, 'loss/train': 1.9928261041641235}
-03/04/2022 05:00:32 - INFO - codeparrot_training - Step 13236: {'lr': 0.000492922985824652, 'samples': 6777344, 'steps': 13236, 'loss/train': 2.3126277923583984}
-03/04/2022 05:00:32 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/04/2022 05:00:38 - INFO - codeparrot_training - Step 13237: {'lr': 0.0004929217320436553, 'samples': 6777856, 'steps': 13237, 'loss/train': 1.8105863332748413}
-03/04/2022 05:00:40 - INFO - codeparrot_training - Skipping example with length 462 (seq_length=1024)
-03/04/2022 05:00:43 - INFO - codeparrot_training - Step 13238: {'lr': 0.0004929204781532018, 'samples': 6778368, 'steps': 13238, 'loss/train': 1.5574378967285156}
-03/04/2022 05:00:46 - INFO - codeparrot_training - Step 13239: {'lr': 0.0004929192241532921, 'samples': 6778880, 'steps': 13239, 'loss/train': 2.468404531478882}
-03/04/2022 05:00:49 - INFO - codeparrot_training - Step 13240: {'lr': 0.0004929179700439269, 'samples': 6779392, 'steps': 13240, 'loss/train': 1.7039964199066162}
-03/04/2022 05:00:49 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/04/2022 05:00:54 - INFO - codeparrot_training - Step 13241: {'lr': 0.0004929167158251065, 'samples': 6779904, 'steps': 13241, 'loss/train': 1.7813071012496948}
-03/04/2022 05:00:58 - INFO - codeparrot_training - Step 13242: {'lr': 0.0004929154614968315, 'samples': 6780416, 'steps': 13242, 'loss/train': 2.5394058227539062}
-03/04/2022 05:00:58 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/04/2022 05:01:03 - INFO - codeparrot_training - Step 13243: {'lr': 0.0004929142070591026, 'samples': 6780928, 'steps': 13243, 'loss/train': 1.2870250940322876}
-03/04/2022 05:01:06 - INFO - codeparrot_training - Step 13244: {'lr': 0.0004929129525119203, 'samples': 6781440, 'steps': 13244, 'loss/train': 1.6033523082733154}
-03/04/2022 05:01:06 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 05:01:12 - INFO - codeparrot_training - Step 13245: {'lr': 0.0004929116978552851, 'samples': 6781952, 'steps': 13245, 'loss/train': 1.455845832824707}
-03/04/2022 05:01:15 - INFO - codeparrot_training - Step 13246: {'lr': 0.0004929104430891978, 'samples': 6782464, 'steps': 13246, 'loss/train': 2.349780797958374}
-03/04/2022 05:01:15 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 05:01:20 - INFO - codeparrot_training - Step 13247: {'lr': 0.0004929091882136587, 'samples': 6782976, 'steps': 13247, 'loss/train': 2.8174376487731934}
-03/04/2022 05:01:23 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/04/2022 05:01:25 - INFO - codeparrot_training - Step 13248: {'lr': 0.0004929079332286685, 'samples': 6783488, 'steps': 13248, 'loss/train': 1.1387797594070435}
-03/04/2022 05:01:28 - INFO - codeparrot_training - Step 13249: {'lr': 0.0004929066781342277, 'samples': 6784000, 'steps': 13249, 'loss/train': 1.6028177738189697}
-03/04/2022 05:01:31 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/04/2022 05:01:34 - INFO - codeparrot_training - Step 13250: {'lr': 0.0004929054229303369, 'samples': 6784512, 'steps': 13250, 'loss/train': 2.270951747894287}
-03/04/2022 05:01:37 - INFO - codeparrot_training - Step 13251: {'lr': 0.0004929041676169967, 'samples': 6785024, 'steps': 13251, 'loss/train': 2.168370246887207}
-03/04/2022 05:01:39 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 05:01:42 - INFO - codeparrot_training - Step 13252: {'lr': 0.0004929029121942077, 'samples': 6785536, 'steps': 13252, 'loss/train': 1.1578481197357178}
-03/04/2022 05:01:45 - INFO - codeparrot_training - Step 13253: {'lr': 0.0004929016566619703, 'samples': 6786048, 'steps': 13253, 'loss/train': 1.628798484802246}
-03/04/2022 05:01:48 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/04/2022 05:01:50 - INFO - codeparrot_training - Step 13254: {'lr': 0.0004929004010202851, 'samples': 6786560, 'steps': 13254, 'loss/train': 1.9326046705245972}
-03/04/2022 05:01:54 - INFO - codeparrot_training - Step 13255: {'lr': 0.0004928991452691528, 'samples': 6787072, 'steps': 13255, 'loss/train': 1.9895201921463013}
-03/04/2022 05:01:56 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/04/2022 05:01:59 - INFO - codeparrot_training - Step 13256: {'lr': 0.0004928978894085739, 'samples': 6787584, 'steps': 13256, 'loss/train': 1.2684364318847656}
-03/04/2022 05:02:02 - INFO - codeparrot_training - Step 13257: {'lr': 0.000492896633438549, 'samples': 6788096, 'steps': 13257, 'loss/train': 2.304921865463257}
-03/04/2022 05:02:05 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/04/2022 05:02:07 - INFO - codeparrot_training - Step 13258: {'lr': 0.0004928953773590785, 'samples': 6788608, 'steps': 13258, 'loss/train': 2.5441384315490723}
-03/04/2022 05:02:11 - INFO - codeparrot_training - Step 13259: {'lr': 0.0004928941211701632, 'samples': 6789120, 'steps': 13259, 'loss/train': 1.8563812971115112}
-03/04/2022 05:02:13 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 05:02:16 - INFO - codeparrot_training - Step 13260: {'lr': 0.0004928928648718035, 'samples': 6789632, 'steps': 13260, 'loss/train': 2.4027483463287354}
-03/04/2022 05:02:19 - INFO - codeparrot_training - Step 13261: {'lr': 0.0004928916084640001, 'samples': 6790144, 'steps': 13261, 'loss/train': 1.9142744541168213}
-03/04/2022 05:02:22 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 05:02:24 - INFO - codeparrot_training - Step 13262: {'lr': 0.0004928903519467534, 'samples': 6790656, 'steps': 13262, 'loss/train': 1.6057987213134766}
-03/04/2022 05:02:27 - INFO - codeparrot_training - Step 13263: {'lr': 0.0004928890953200641, 'samples': 6791168, 'steps': 13263, 'loss/train': 2.019097089767456}
-03/04/2022 05:02:30 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 05:02:33 - INFO - codeparrot_training - Step 13264: {'lr': 0.0004928878385839327, 'samples': 6791680, 'steps': 13264, 'loss/train': 1.917822241783142}
-03/04/2022 05:02:36 - INFO - codeparrot_training - Step 13265: {'lr': 0.0004928865817383597, 'samples': 6792192, 'steps': 13265, 'loss/train': 1.4053516387939453}
-03/04/2022 05:02:39 - INFO - codeparrot_training - Step 13266: {'lr': 0.0004928853247833459, 'samples': 6792704, 'steps': 13266, 'loss/train': 1.6025692224502563}
-03/04/2022 05:02:40 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/04/2022 05:02:45 - INFO - codeparrot_training - Step 13267: {'lr': 0.0004928840677188918, 'samples': 6793216, 'steps': 13267, 'loss/train': 1.1411787271499634}
-03/04/2022 05:02:48 - INFO - codeparrot_training - Step 13268: {'lr': 0.0004928828105449977, 'samples': 6793728, 'steps': 13268, 'loss/train': 2.130810499191284}
-03/04/2022 05:02:48 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/04/2022 05:02:53 - INFO - codeparrot_training - Step 13269: {'lr': 0.0004928815532616644, 'samples': 6794240, 'steps': 13269, 'loss/train': 1.3839725255966187}
-03/04/2022 05:02:56 - INFO - codeparrot_training - Step 13270: {'lr': 0.0004928802958688924, 'samples': 6794752, 'steps': 13270, 'loss/train': 2.04555082321167}
-03/04/2022 05:02:57 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 05:03:02 - INFO - codeparrot_training - Step 13271: {'lr': 0.0004928790383666823, 'samples': 6795264, 'steps': 13271, 'loss/train': 1.391777515411377}
-03/04/2022 05:03:05 - INFO - codeparrot_training - Step 13272: {'lr': 0.0004928777807550348, 'samples': 6795776, 'steps': 13272, 'loss/train': 1.41947340965271}
-03/04/2022 05:03:05 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 05:03:10 - INFO - codeparrot_training - Step 13273: {'lr': 0.0004928765230339502, 'samples': 6796288, 'steps': 13273, 'loss/train': 1.9424504041671753}
-03/04/2022 05:03:13 - INFO - codeparrot_training - Step 13274: {'lr': 0.000492875265203429, 'samples': 6796800, 'steps': 13274, 'loss/train': 0.37050873041152954}
-03/04/2022 05:03:13 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/04/2022 05:03:18 - INFO - codeparrot_training - Step 13275: {'lr': 0.0004928740072634722, 'samples': 6797312, 'steps': 13275, 'loss/train': 1.2458142042160034}
-03/04/2022 05:03:22 - INFO - codeparrot_training - Step 13276: {'lr': 0.0004928727492140801, 'samples': 6797824, 'steps': 13276, 'loss/train': 2.0976779460906982}
-03/04/2022 05:03:22 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/04/2022 05:03:27 - INFO - codeparrot_training - Step 13277: {'lr': 0.0004928714910552533, 'samples': 6798336, 'steps': 13277, 'loss/train': 2.2356719970703125}
-03/04/2022 05:03:30 - INFO - codeparrot_training - Step 13278: {'lr': 0.0004928702327869922, 'samples': 6798848, 'steps': 13278, 'loss/train': 1.8515127897262573}
-03/04/2022 05:03:30 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 05:03:36 - INFO - codeparrot_training - Step 13279: {'lr': 0.0004928689744092976, 'samples': 6799360, 'steps': 13279, 'loss/train': 2.2815568447113037}
-03/04/2022 05:03:39 - INFO - codeparrot_training - Step 13280: {'lr': 0.0004928677159221701, 'samples': 6799872, 'steps': 13280, 'loss/train': 2.4587254524230957}
-03/04/2022 05:03:40 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/04/2022 05:03:44 - INFO - codeparrot_training - Step 13281: {'lr': 0.00049286645732561, 'samples': 6800384, 'steps': 13281, 'loss/train': 2.167850971221924}
-03/04/2022 05:03:47 - INFO - codeparrot_training - Step 13282: {'lr': 0.0004928651986196181, 'samples': 6800896, 'steps': 13282, 'loss/train': 0.8748239874839783}
-03/04/2022 05:03:48 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/04/2022 05:03:52 - INFO - codeparrot_training - Step 13283: {'lr': 0.0004928639398041948, 'samples': 6801408, 'steps': 13283, 'loss/train': 2.6929657459259033}
-03/04/2022 05:03:56 - INFO - codeparrot_training - Step 13284: {'lr': 0.0004928626808793409, 'samples': 6801920, 'steps': 13284, 'loss/train': 2.279388189315796}
-03/04/2022 05:03:57 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 05:04:01 - INFO - codeparrot_training - Step 13285: {'lr': 0.0004928614218450568, 'samples': 6802432, 'steps': 13285, 'loss/train': 1.8392786979675293}
-03/04/2022 05:04:04 - INFO - codeparrot_training - Step 13286: {'lr': 0.000492860162701343, 'samples': 6802944, 'steps': 13286, 'loss/train': 2.6370997428894043}
-03/04/2022 05:04:05 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/04/2022 05:04:09 - INFO - codeparrot_training - Step 13287: {'lr': 0.0004928589034482001, 'samples': 6803456, 'steps': 13287, 'loss/train': 1.487797498703003}
-03/04/2022 05:04:12 - INFO - codeparrot_training - Step 13288: {'lr': 0.000492857644085629, 'samples': 6803968, 'steps': 13288, 'loss/train': 2.2168056964874268}
-03/04/2022 05:04:14 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/04/2022 05:04:18 - INFO - codeparrot_training - Step 13289: {'lr': 0.0004928563846136296, 'samples': 6804480, 'steps': 13289, 'loss/train': 1.9492120742797852}
-03/04/2022 05:04:21 - INFO - codeparrot_training - Step 13290: {'lr': 0.0004928551250322032, 'samples': 6804992, 'steps': 13290, 'loss/train': 2.1066718101501465}
-03/04/2022 05:04:22 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/04/2022 05:04:26 - INFO - codeparrot_training - Step 13291: {'lr': 0.0004928538653413499, 'samples': 6805504, 'steps': 13291, 'loss/train': 2.0170438289642334}
-03/04/2022 05:04:29 - INFO - codeparrot_training - Step 13292: {'lr': 0.0004928526055410704, 'samples': 6806016, 'steps': 13292, 'loss/train': 1.9921526908874512}
-03/04/2022 05:04:31 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/04/2022 05:04:34 - INFO - codeparrot_training - Step 13293: {'lr': 0.0004928513456313653, 'samples': 6806528, 'steps': 13293, 'loss/train': 1.1400866508483887}
-03/04/2022 05:04:38 - INFO - codeparrot_training - Step 13294: {'lr': 0.000492850085612235, 'samples': 6807040, 'steps': 13294, 'loss/train': 2.204876661300659}
-03/04/2022 05:04:39 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/04/2022 05:04:43 - INFO - codeparrot_training - Step 13295: {'lr': 0.0004928488254836804, 'samples': 6807552, 'steps': 13295, 'loss/train': 1.581234097480774}
-03/04/2022 05:04:46 - INFO - codeparrot_training - Step 13296: {'lr': 0.0004928475652457017, 'samples': 6808064, 'steps': 13296, 'loss/train': 1.5424816608428955}
-03/04/2022 05:04:48 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/04/2022 05:04:51 - INFO - codeparrot_training - Step 13297: {'lr': 0.0004928463048982998, 'samples': 6808576, 'steps': 13297, 'loss/train': 2.8367176055908203}
-03/04/2022 05:04:55 - INFO - codeparrot_training - Step 13298: {'lr': 0.0004928450444414749, 'samples': 6809088, 'steps': 13298, 'loss/train': 1.1020877361297607}
-03/04/2022 05:04:56 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/04/2022 05:05:00 - INFO - codeparrot_training - Step 13299: {'lr': 0.0004928437838752278, 'samples': 6809600, 'steps': 13299, 'loss/train': 2.130694627761841}
-03/04/2022 05:05:03 - INFO - codeparrot_training - Step 13300: {'lr': 0.0004928425231995593, 'samples': 6810112, 'steps': 13300, 'loss/train': 2.7829599380493164}
-03/04/2022 05:05:04 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/04/2022 05:05:08 - INFO - codeparrot_training - Step 13301: {'lr': 0.0004928412624144694, 'samples': 6810624, 'steps': 13301, 'loss/train': 2.897446870803833}
-03/04/2022 05:05:11 - INFO - codeparrot_training - Step 13302: {'lr': 0.0004928400015199591, 'samples': 6811136, 'steps': 13302, 'loss/train': 1.7290700674057007}
-03/04/2022 05:05:13 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/04/2022 05:05:17 - INFO - codeparrot_training - Step 13303: {'lr': 0.0004928387405160288, 'samples': 6811648, 'steps': 13303, 'loss/train': 1.5698926448822021}
-03/04/2022 05:05:20 - INFO - codeparrot_training - Step 13304: {'lr': 0.0004928374794026792, 'samples': 6812160, 'steps': 13304, 'loss/train': 1.3532004356384277}
-03/04/2022 05:05:21 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 05:05:25 - INFO - codeparrot_training - Step 13305: {'lr': 0.0004928362181799107, 'samples': 6812672, 'steps': 13305, 'loss/train': 2.46488618850708}
-03/04/2022 05:05:28 - INFO - codeparrot_training - Step 13306: {'lr': 0.0004928349568477239, 'samples': 6813184, 'steps': 13306, 'loss/train': 1.7176592350006104}
-03/04/2022 05:05:30 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 05:05:33 - INFO - codeparrot_training - Step 13307: {'lr': 0.0004928336954061195, 'samples': 6813696, 'steps': 13307, 'loss/train': 2.3260908126831055}
-03/04/2022 05:05:37 - INFO - codeparrot_training - Step 13308: {'lr': 0.000492832433855098, 'samples': 6814208, 'steps': 13308, 'loss/train': 2.0624337196350098}
-03/04/2022 05:05:38 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/04/2022 05:05:42 - INFO - codeparrot_training - Step 13309: {'lr': 0.0004928311721946599, 'samples': 6814720, 'steps': 13309, 'loss/train': 2.2602617740631104}
-03/04/2022 05:05:45 - INFO - codeparrot_training - Step 13310: {'lr': 0.0004928299104248059, 'samples': 6815232, 'steps': 13310, 'loss/train': 2.7597057819366455}
-03/04/2022 05:05:46 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/04/2022 05:05:50 - INFO - codeparrot_training - Step 13311: {'lr': 0.0004928286485455365, 'samples': 6815744, 'steps': 13311, 'loss/train': 2.1784145832061768}
-03/04/2022 05:05:53 - INFO - codeparrot_training - Step 13312: {'lr': 0.0004928273865568521, 'samples': 6816256, 'steps': 13312, 'loss/train': 1.7779589891433716}
-03/04/2022 05:05:54 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 05:05:59 - INFO - codeparrot_training - Step 13313: {'lr': 0.0004928261244587536, 'samples': 6816768, 'steps': 13313, 'loss/train': 1.082588791847229}
-03/04/2022 05:06:02 - INFO - codeparrot_training - Step 13314: {'lr': 0.0004928248622512412, 'samples': 6817280, 'steps': 13314, 'loss/train': 0.6486206650733948}
-03/04/2022 05:06:03 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/04/2022 05:06:07 - INFO - codeparrot_training - Step 13315: {'lr': 0.0004928235999343159, 'samples': 6817792, 'steps': 13315, 'loss/train': 2.381211757659912}
-03/04/2022 05:06:10 - INFO - codeparrot_training - Step 13316: {'lr': 0.0004928223375079778, 'samples': 6818304, 'steps': 13316, 'loss/train': 1.814554214477539}
-03/04/2022 05:06:11 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/04/2022 05:06:15 - INFO - codeparrot_training - Step 13317: {'lr': 0.0004928210749722278, 'samples': 6818816, 'steps': 13317, 'loss/train': 2.247446298599243}
-03/04/2022 05:06:19 - INFO - codeparrot_training - Step 13318: {'lr': 0.0004928198123270664, 'samples': 6819328, 'steps': 13318, 'loss/train': 2.1695940494537354}
-03/04/2022 05:06:19 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/04/2022 05:06:24 - INFO - codeparrot_training - Step 13319: {'lr': 0.0004928185495724942, 'samples': 6819840, 'steps': 13319, 'loss/train': 2.2240867614746094}
-03/04/2022 05:06:27 - INFO - codeparrot_training - Step 13320: {'lr': 0.0004928172867085115, 'samples': 6820352, 'steps': 13320, 'loss/train': 1.8011338710784912}
-03/04/2022 05:06:28 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/04/2022 05:06:32 - INFO - codeparrot_training - Step 13321: {'lr': 0.0004928160237351192, 'samples': 6820864, 'steps': 13321, 'loss/train': 1.8857786655426025}
-03/04/2022 05:06:35 - INFO - codeparrot_training - Step 13322: {'lr': 0.0004928147606523179, 'samples': 6821376, 'steps': 13322, 'loss/train': 1.4106031656265259}
-03/04/2022 05:06:36 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/04/2022 05:06:41 - INFO - codeparrot_training - Step 13323: {'lr': 0.0004928134974601078, 'samples': 6821888, 'steps': 13323, 'loss/train': 1.332114577293396}
-03/04/2022 05:06:44 - INFO - codeparrot_training - Step 13324: {'lr': 0.0004928122341584897, 'samples': 6822400, 'steps': 13324, 'loss/train': 1.583372712135315}
-03/04/2022 05:06:45 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/04/2022 05:06:49 - INFO - codeparrot_training - Step 13325: {'lr': 0.0004928109707474643, 'samples': 6822912, 'steps': 13325, 'loss/train': 1.0640736818313599}
-03/04/2022 05:06:52 - INFO - codeparrot_training - Step 13326: {'lr': 0.0004928097072270319, 'samples': 6823424, 'steps': 13326, 'loss/train': 1.72687566280365}
-03/04/2022 05:06:53 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/04/2022 05:06:58 - INFO - codeparrot_training - Step 13327: {'lr': 0.0004928084435971932, 'samples': 6823936, 'steps': 13327, 'loss/train': 1.8843727111816406}
-03/04/2022 05:07:01 - INFO - codeparrot_training - Step 13328: {'lr': 0.0004928071798579488, 'samples': 6824448, 'steps': 13328, 'loss/train': 1.7000539302825928}
-03/04/2022 05:07:02 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 05:07:06 - INFO - codeparrot_training - Step 13329: {'lr': 0.0004928059160092993, 'samples': 6824960, 'steps': 13329, 'loss/train': 1.3381729125976562}
-03/04/2022 05:07:09 - INFO - codeparrot_training - Step 13330: {'lr': 0.000492804652051245, 'samples': 6825472, 'steps': 13330, 'loss/train': 1.8879109621047974}
-03/04/2022 05:07:10 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 05:07:15 - INFO - codeparrot_training - Step 13331: {'lr': 0.0004928033879837868, 'samples': 6825984, 'steps': 13331, 'loss/train': 2.3959531784057617}
-03/04/2022 05:07:18 - INFO - codeparrot_training - Step 13332: {'lr': 0.0004928021238069251, 'samples': 6826496, 'steps': 13332, 'loss/train': 2.3502390384674072}
-03/04/2022 05:07:19 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/04/2022 05:07:23 - INFO - codeparrot_training - Step 13333: {'lr': 0.0004928008595206605, 'samples': 6827008, 'steps': 13333, 'loss/train': 2.254474639892578}
-03/04/2022 05:07:26 - INFO - codeparrot_training - Step 13334: {'lr': 0.0004927995951249937, 'samples': 6827520, 'steps': 13334, 'loss/train': 2.4279630184173584}
-03/04/2022 05:07:27 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/04/2022 05:07:31 - INFO - codeparrot_training - Step 13335: {'lr': 0.0004927983306199251, 'samples': 6828032, 'steps': 13335, 'loss/train': 2.4693126678466797}
-03/04/2022 05:07:35 - INFO - codeparrot_training - Step 13336: {'lr': 0.0004927970660054552, 'samples': 6828544, 'steps': 13336, 'loss/train': 1.9251638650894165}
-03/04/2022 05:07:36 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/04/2022 05:07:40 - INFO - codeparrot_training - Step 13337: {'lr': 0.0004927958012815849, 'samples': 6829056, 'steps': 13337, 'loss/train': 1.6905845403671265}
-03/04/2022 05:07:43 - INFO - codeparrot_training - Step 13338: {'lr': 0.0004927945364483144, 'samples': 6829568, 'steps': 13338, 'loss/train': 1.2993814945220947}
-03/04/2022 05:07:44 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/04/2022 05:07:48 - INFO - codeparrot_training - Step 13339: {'lr': 0.0004927932715056444, 'samples': 6830080, 'steps': 13339, 'loss/train': 2.5805935859680176}
-03/04/2022 05:07:52 - INFO - codeparrot_training - Step 13340: {'lr': 0.0004927920064535756, 'samples': 6830592, 'steps': 13340, 'loss/train': 2.262587785720825}
-03/04/2022 05:07:53 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/04/2022 05:07:57 - INFO - codeparrot_training - Step 13341: {'lr': 0.0004927907412921084, 'samples': 6831104, 'steps': 13341, 'loss/train': 4.037944316864014}
-03/04/2022 05:08:00 - INFO - codeparrot_training - Step 13342: {'lr': 0.0004927894760212435, 'samples': 6831616, 'steps': 13342, 'loss/train': 2.536261796951294}
-03/04/2022 05:08:02 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/04/2022 05:08:06 - INFO - codeparrot_training - Step 13343: {'lr': 0.0004927882106409813, 'samples': 6832128, 'steps': 13343, 'loss/train': 2.093315839767456}
-03/04/2022 05:08:09 - INFO - codeparrot_training - Step 13344: {'lr': 0.0004927869451513226, 'samples': 6832640, 'steps': 13344, 'loss/train': 2.380563735961914}
-03/04/2022 05:08:13 - INFO - codeparrot_training - Step 13345: {'lr': 0.0004927856795522678, 'samples': 6833152, 'steps': 13345, 'loss/train': 1.0517983436584473}
-03/04/2022 05:08:14 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/04/2022 05:08:18 - INFO - codeparrot_training - Step 13346: {'lr': 0.0004927844138438175, 'samples': 6833664, 'steps': 13346, 'loss/train': 1.9538688659667969}
-03/04/2022 05:08:21 - INFO - codeparrot_training - Step 13347: {'lr': 0.0004927831480259723, 'samples': 6834176, 'steps': 13347, 'loss/train': 2.1036174297332764}
-03/04/2022 05:08:22 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 05:08:26 - INFO - codeparrot_training - Step 13348: {'lr': 0.0004927818820987328, 'samples': 6834688, 'steps': 13348, 'loss/train': 1.5035640001296997}
-03/04/2022 05:08:29 - INFO - codeparrot_training - Step 13349: {'lr': 0.0004927806160620995, 'samples': 6835200, 'steps': 13349, 'loss/train': 3.1861519813537598}
-03/04/2022 05:08:31 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/04/2022 05:08:35 - INFO - codeparrot_training - Step 13350: {'lr': 0.0004927793499160729, 'samples': 6835712, 'steps': 13350, 'loss/train': 1.1737160682678223}
-03/04/2022 05:08:38 - INFO - codeparrot_training - Step 13351: {'lr': 0.000492778083660654, 'samples': 6836224, 'steps': 13351, 'loss/train': 2.1187031269073486}
-03/04/2022 05:08:40 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 05:08:43 - INFO - codeparrot_training - Step 13352: {'lr': 0.0004927768172958427, 'samples': 6836736, 'steps': 13352, 'loss/train': 1.4748250246047974}
-03/04/2022 05:08:46 - INFO - codeparrot_training - Step 13353: {'lr': 0.00049277555082164, 'samples': 6837248, 'steps': 13353, 'loss/train': 1.8878852128982544}
-03/04/2022 05:08:48 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 05:08:52 - INFO - codeparrot_training - Step 13354: {'lr': 0.0004927742842380465, 'samples': 6837760, 'steps': 13354, 'loss/train': 1.8579548597335815}
-03/04/2022 05:08:55 - INFO - codeparrot_training - Step 13355: {'lr': 0.0004927730175450626, 'samples': 6838272, 'steps': 13355, 'loss/train': 2.665435791015625}
-03/04/2022 05:08:57 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/04/2022 05:09:00 - INFO - codeparrot_training - Step 13356: {'lr': 0.0004927717507426887, 'samples': 6838784, 'steps': 13356, 'loss/train': 2.168813705444336}
-03/04/2022 05:09:03 - INFO - codeparrot_training - Step 13357: {'lr': 0.0004927704838309259, 'samples': 6839296, 'steps': 13357, 'loss/train': 3.2030956745147705}
-03/04/2022 05:09:06 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/04/2022 05:09:09 - INFO - codeparrot_training - Step 13358: {'lr': 0.0004927692168097743, 'samples': 6839808, 'steps': 13358, 'loss/train': 2.2619035243988037}
-03/04/2022 05:09:12 - INFO - codeparrot_training - Step 13359: {'lr': 0.0004927679496792347, 'samples': 6840320, 'steps': 13359, 'loss/train': 2.3521862030029297}
-03/04/2022 05:09:15 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/04/2022 05:09:17 - INFO - codeparrot_training - Step 13360: {'lr': 0.0004927666824393076, 'samples': 6840832, 'steps': 13360, 'loss/train': 2.6010100841522217}
-03/04/2022 05:09:20 - INFO - codeparrot_training - Step 13361: {'lr': 0.0004927654150899937, 'samples': 6841344, 'steps': 13361, 'loss/train': 1.6832001209259033}
-03/04/2022 05:09:23 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/04/2022 05:09:25 - INFO - codeparrot_training - Step 13362: {'lr': 0.0004927641476312932, 'samples': 6841856, 'steps': 13362, 'loss/train': 1.9665132761001587}
-03/04/2022 05:09:29 - INFO - codeparrot_training - Step 13363: {'lr': 0.000492762880063207, 'samples': 6842368, 'steps': 13363, 'loss/train': 1.1055748462677002}
-03/04/2022 05:09:31 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/04/2022 05:09:34 - INFO - codeparrot_training - Step 13364: {'lr': 0.0004927616123857357, 'samples': 6842880, 'steps': 13364, 'loss/train': 2.3493905067443848}
-03/04/2022 05:09:37 - INFO - codeparrot_training - Step 13365: {'lr': 0.0004927603445988797, 'samples': 6843392, 'steps': 13365, 'loss/train': 2.5699288845062256}
-03/04/2022 05:09:40 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 05:09:42 - INFO - codeparrot_training - Step 13366: {'lr': 0.0004927590767026396, 'samples': 6843904, 'steps': 13366, 'loss/train': 1.9303780794143677}
-03/04/2022 05:09:46 - INFO - codeparrot_training - Step 13367: {'lr': 0.0004927578086970161, 'samples': 6844416, 'steps': 13367, 'loss/train': 2.465127468109131}
-03/04/2022 05:09:48 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/04/2022 05:09:51 - INFO - codeparrot_training - Step 13368: {'lr': 0.0004927565405820096, 'samples': 6844928, 'steps': 13368, 'loss/train': 2.4340717792510986}
-03/04/2022 05:09:54 - INFO - codeparrot_training - Step 13369: {'lr': 0.0004927552723576207, 'samples': 6845440, 'steps': 13369, 'loss/train': 1.581923246383667}
-03/04/2022 05:09:57 - INFO - codeparrot_training - Skipping example with length 233 (seq_length=1024)
-03/04/2022 05:09:59 - INFO - codeparrot_training - Step 13370: {'lr': 0.0004927540040238501, 'samples': 6845952, 'steps': 13370, 'loss/train': 1.9679538011550903}
-03/04/2022 05:10:02 - INFO - codeparrot_training - Step 13371: {'lr': 0.0004927527355806983, 'samples': 6846464, 'steps': 13371, 'loss/train': 2.357977867126465}
-03/04/2022 05:10:05 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/04/2022 05:10:08 - INFO - codeparrot_training - Step 13372: {'lr': 0.0004927514670281659, 'samples': 6846976, 'steps': 13372, 'loss/train': 2.0572352409362793}
-03/04/2022 05:10:11 - INFO - codeparrot_training - Step 13373: {'lr': 0.0004927501983662534, 'samples': 6847488, 'steps': 13373, 'loss/train': 1.9040250778198242}
-03/04/2022 05:10:13 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/04/2022 05:10:16 - INFO - codeparrot_training - Step 13374: {'lr': 0.0004927489295949613, 'samples': 6848000, 'steps': 13374, 'loss/train': 1.7871370315551758}
-03/04/2022 05:10:19 - INFO - codeparrot_training - Step 13375: {'lr': 0.0004927476607142904, 'samples': 6848512, 'steps': 13375, 'loss/train': 2.50321364402771}
-03/04/2022 05:10:21 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/04/2022 05:10:25 - INFO - codeparrot_training - Step 13376: {'lr': 0.0004927463917242411, 'samples': 6849024, 'steps': 13376, 'loss/train': 1.9689903259277344}
-03/04/2022 05:10:28 - INFO - codeparrot_training - Step 13377: {'lr': 0.0004927451226248141, 'samples': 6849536, 'steps': 13377, 'loss/train': 1.179306149482727}
-03/04/2022 05:10:30 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 05:10:33 - INFO - codeparrot_training - Step 13378: {'lr': 0.0004927438534160098, 'samples': 6850048, 'steps': 13378, 'loss/train': 1.7766168117523193}
-03/04/2022 05:10:36 - INFO - codeparrot_training - Step 13379: {'lr': 0.0004927425840978289, 'samples': 6850560, 'steps': 13379, 'loss/train': 2.685537099838257}
-03/04/2022 05:10:38 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/04/2022 05:10:41 - INFO - codeparrot_training - Step 13380: {'lr': 0.0004927413146702719, 'samples': 6851072, 'steps': 13380, 'loss/train': 2.3092610836029053}
-03/04/2022 05:10:45 - INFO - codeparrot_training - Step 13381: {'lr': 0.0004927400451333394, 'samples': 6851584, 'steps': 13381, 'loss/train': 2.3443355560302734}
-03/04/2022 05:10:47 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/04/2022 05:10:50 - INFO - codeparrot_training - Step 13382: {'lr': 0.0004927387754870321, 'samples': 6852096, 'steps': 13382, 'loss/train': 1.4301015138626099}
-03/04/2022 05:10:53 - INFO - codeparrot_training - Step 13383: {'lr': 0.0004927375057313504, 'samples': 6852608, 'steps': 13383, 'loss/train': 2.0485775470733643}
-03/04/2022 05:10:55 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/04/2022 05:10:58 - INFO - codeparrot_training - Step 13384: {'lr': 0.0004927362358662948, 'samples': 6853120, 'steps': 13384, 'loss/train': 1.6270455121994019}
-03/04/2022 05:11:01 - INFO - codeparrot_training - Step 13385: {'lr': 0.0004927349658918662, 'samples': 6853632, 'steps': 13385, 'loss/train': 1.8019218444824219}
-03/04/2022 05:11:03 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/04/2022 05:11:07 - INFO - codeparrot_training - Step 13386: {'lr': 0.0004927336958080648, 'samples': 6854144, 'steps': 13386, 'loss/train': 2.5564987659454346}
-03/04/2022 05:11:10 - INFO - codeparrot_training - Step 13387: {'lr': 0.0004927324256148914, 'samples': 6854656, 'steps': 13387, 'loss/train': 1.4747062921524048}
-03/04/2022 05:11:12 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/04/2022 05:11:15 - INFO - codeparrot_training - Step 13388: {'lr': 0.0004927311553123465, 'samples': 6855168, 'steps': 13388, 'loss/train': 2.970655918121338}
-03/04/2022 05:11:18 - INFO - codeparrot_training - Step 13389: {'lr': 0.0004927298849004307, 'samples': 6855680, 'steps': 13389, 'loss/train': 1.552445411682129}
-03/04/2022 05:11:20 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/04/2022 05:11:23 - INFO - codeparrot_training - Step 13390: {'lr': 0.0004927286143791447, 'samples': 6856192, 'steps': 13390, 'loss/train': 2.475818157196045}
-03/04/2022 05:11:27 - INFO - codeparrot_training - Step 13391: {'lr': 0.0004927273437484888, 'samples': 6856704, 'steps': 13391, 'loss/train': 2.042188882827759}
-03/04/2022 05:11:28 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/04/2022 05:11:32 - INFO - codeparrot_training - Step 13392: {'lr': 0.0004927260730084636, 'samples': 6857216, 'steps': 13392, 'loss/train': 1.3181431293487549}
-03/04/2022 05:11:35 - INFO - codeparrot_training - Step 13393: {'lr': 0.0004927248021590699, 'samples': 6857728, 'steps': 13393, 'loss/train': 2.2708096504211426}
-03/04/2022 05:11:37 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/04/2022 05:11:40 - INFO - codeparrot_training - Step 13394: {'lr': 0.0004927235312003082, 'samples': 6858240, 'steps': 13394, 'loss/train': 2.2695693969726562}
-03/04/2022 05:11:44 - INFO - codeparrot_training - Step 13395: {'lr': 0.0004927222601321789, 'samples': 6858752, 'steps': 13395, 'loss/train': 1.0179111957550049}
-03/04/2022 05:11:45 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/04/2022 05:11:49 - INFO - codeparrot_training - Step 13396: {'lr': 0.0004927209889546828, 'samples': 6859264, 'steps': 13396, 'loss/train': 2.919968843460083}
-03/04/2022 05:11:52 - INFO - codeparrot_training - Step 13397: {'lr': 0.0004927197176678203, 'samples': 6859776, 'steps': 13397, 'loss/train': 2.3022985458374023}
-03/04/2022 05:11:53 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/04/2022 05:11:57 - INFO - codeparrot_training - Step 13398: {'lr': 0.000492718446271592, 'samples': 6860288, 'steps': 13398, 'loss/train': 2.306781530380249}
-03/04/2022 05:12:00 - INFO - codeparrot_training - Step 13399: {'lr': 0.0004927171747659986, 'samples': 6860800, 'steps': 13399, 'loss/train': 2.111529588699341}
-03/04/2022 05:12:02 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/04/2022 05:12:06 - INFO - codeparrot_training - Step 13400: {'lr': 0.0004927159031510405, 'samples': 6861312, 'steps': 13400, 'loss/train': 1.5477195978164673}
-03/04/2022 05:12:09 - INFO - codeparrot_training - Step 13401: {'lr': 0.0004927146314267184, 'samples': 6861824, 'steps': 13401, 'loss/train': 1.9659844636917114}
-03/04/2022 05:12:10 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/04/2022 05:12:14 - INFO - codeparrot_training - Step 13402: {'lr': 0.000492713359593033, 'samples': 6862336, 'steps': 13402, 'loss/train': 1.3377810716629028}
-03/04/2022 05:12:17 - INFO - codeparrot_training - Step 13403: {'lr': 0.0004927120876499846, 'samples': 6862848, 'steps': 13403, 'loss/train': 0.22095853090286255}
-03/04/2022 05:12:19 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/04/2022 05:12:23 - INFO - codeparrot_training - Step 13404: {'lr': 0.0004927108155975738, 'samples': 6863360, 'steps': 13404, 'loss/train': 2.376896619796753}
-03/04/2022 05:12:26 - INFO - codeparrot_training - Step 13405: {'lr': 0.0004927095434358012, 'samples': 6863872, 'steps': 13405, 'loss/train': 0.3220463991165161}
-03/04/2022 05:12:27 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 05:12:31 - INFO - codeparrot_training - Step 13406: {'lr': 0.0004927082711646676, 'samples': 6864384, 'steps': 13406, 'loss/train': 2.33569073677063}
-03/04/2022 05:12:34 - INFO - codeparrot_training - Step 13407: {'lr': 0.0004927069987841733, 'samples': 6864896, 'steps': 13407, 'loss/train': 2.4126782417297363}
-03/04/2022 05:12:36 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/04/2022 05:12:39 - INFO - codeparrot_training - Step 13408: {'lr': 0.0004927057262943189, 'samples': 6865408, 'steps': 13408, 'loss/train': 2.0062289237976074}
-03/04/2022 05:12:43 - INFO - codeparrot_training - Step 13409: {'lr': 0.0004927044536951052, 'samples': 6865920, 'steps': 13409, 'loss/train': 1.6381884813308716}
-03/04/2022 05:12:44 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 05:12:48 - INFO - codeparrot_training - Step 13410: {'lr': 0.0004927031809865324, 'samples': 6866432, 'steps': 13410, 'loss/train': 0.11173456907272339}
-03/04/2022 05:12:51 - INFO - codeparrot_training - Step 13411: {'lr': 0.0004927019081686015, 'samples': 6866944, 'steps': 13411, 'loss/train': 1.4920639991760254}
-03/04/2022 05:12:53 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/04/2022 05:12:56 - INFO - codeparrot_training - Step 13412: {'lr': 0.0004927006352413128, 'samples': 6867456, 'steps': 13412, 'loss/train': 1.8619693517684937}
-03/04/2022 05:13:00 - INFO - codeparrot_training - Step 13413: {'lr': 0.000492699362204667, 'samples': 6867968, 'steps': 13413, 'loss/train': 1.5930536985397339}
-03/04/2022 05:13:01 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/04/2022 05:13:05 - INFO - codeparrot_training - Step 13414: {'lr': 0.0004926980890586645, 'samples': 6868480, 'steps': 13414, 'loss/train': 2.4329278469085693}
-03/04/2022 05:13:08 - INFO - codeparrot_training - Step 13415: {'lr': 0.000492696815803306, 'samples': 6868992, 'steps': 13415, 'loss/train': 2.0143964290618896}
-03/04/2022 05:13:09 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 05:13:13 - INFO - codeparrot_training - Step 13416: {'lr': 0.0004926955424385921, 'samples': 6869504, 'steps': 13416, 'loss/train': 1.8370026350021362}
-03/04/2022 05:13:16 - INFO - codeparrot_training - Step 13417: {'lr': 0.0004926942689645234, 'samples': 6870016, 'steps': 13417, 'loss/train': 1.066860556602478}
-03/04/2022 05:13:18 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/04/2022 05:13:22 - INFO - codeparrot_training - Step 13418: {'lr': 0.0004926929953811003, 'samples': 6870528, 'steps': 13418, 'loss/train': 3.075352191925049}
-03/04/2022 05:13:25 - INFO - codeparrot_training - Step 13419: {'lr': 0.0004926917216883235, 'samples': 6871040, 'steps': 13419, 'loss/train': 1.9877028465270996}
-03/04/2022 05:13:26 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/04/2022 05:13:30 - INFO - codeparrot_training - Step 13420: {'lr': 0.0004926904478861937, 'samples': 6871552, 'steps': 13420, 'loss/train': 1.7826645374298096}
-03/04/2022 05:13:33 - INFO - codeparrot_training - Step 13421: {'lr': 0.0004926891739747111, 'samples': 6872064, 'steps': 13421, 'loss/train': 2.210176706314087}
-03/04/2022 05:13:34 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/04/2022 05:13:38 - INFO - codeparrot_training - Step 13422: {'lr': 0.0004926878999538766, 'samples': 6872576, 'steps': 13422, 'loss/train': 1.7870256900787354}
-03/04/2022 05:13:42 - INFO - codeparrot_training - Step 13423: {'lr': 0.0004926866258236907, 'samples': 6873088, 'steps': 13423, 'loss/train': 1.5246186256408691}
-03/04/2022 05:13:43 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/04/2022 05:13:47 - INFO - codeparrot_training - Step 13424: {'lr': 0.000492685351584154, 'samples': 6873600, 'steps': 13424, 'loss/train': 2.5892648696899414}
-03/04/2022 05:13:50 - INFO - codeparrot_training - Step 13425: {'lr': 0.000492684077235267, 'samples': 6874112, 'steps': 13425, 'loss/train': 1.4511345624923706}
-03/04/2022 05:13:52 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/04/2022 05:13:55 - INFO - codeparrot_training - Step 13426: {'lr': 0.0004926828027770302, 'samples': 6874624, 'steps': 13426, 'loss/train': 2.0987086296081543}
-03/04/2022 05:13:59 - INFO - codeparrot_training - Step 13427: {'lr': 0.0004926815282094443, 'samples': 6875136, 'steps': 13427, 'loss/train': 1.6078892946243286}
-03/04/2022 05:14:00 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/04/2022 05:14:04 - INFO - codeparrot_training - Step 13428: {'lr': 0.00049268025353251, 'samples': 6875648, 'steps': 13428, 'loss/train': 2.2358031272888184}
-03/04/2022 05:14:07 - INFO - codeparrot_training - Step 13429: {'lr': 0.0004926789787462276, 'samples': 6876160, 'steps': 13429, 'loss/train': 2.0798423290252686}
-03/04/2022 05:14:09 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/04/2022 05:14:12 - INFO - codeparrot_training - Step 13430: {'lr': 0.0004926777038505978, 'samples': 6876672, 'steps': 13430, 'loss/train': 1.8680251836776733}
-03/04/2022 05:14:15 - INFO - codeparrot_training - Step 13431: {'lr': 0.0004926764288456212, 'samples': 6877184, 'steps': 13431, 'loss/train': 1.5333977937698364}
-03/04/2022 05:14:17 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/04/2022 05:14:21 - INFO - codeparrot_training - Step 13432: {'lr': 0.0004926751537312982, 'samples': 6877696, 'steps': 13432, 'loss/train': 1.780661940574646}
-03/04/2022 05:14:24 - INFO - codeparrot_training - Step 13433: {'lr': 0.0004926738785076297, 'samples': 6878208, 'steps': 13433, 'loss/train': 1.3333585262298584}
-03/04/2022 05:14:25 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 05:14:29 - INFO - codeparrot_training - Step 13434: {'lr': 0.000492672603174616, 'samples': 6878720, 'steps': 13434, 'loss/train': 2.61962890625}
-03/04/2022 05:14:32 - INFO - codeparrot_training - Step 13435: {'lr': 0.0004926713277322579, 'samples': 6879232, 'steps': 13435, 'loss/train': 1.797806739807129}
-03/04/2022 05:14:34 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/04/2022 05:14:38 - INFO - codeparrot_training - Step 13436: {'lr': 0.0004926700521805557, 'samples': 6879744, 'steps': 13436, 'loss/train': 1.7795894145965576}
-03/04/2022 05:14:41 - INFO - codeparrot_training - Step 13437: {'lr': 0.0004926687765195102, 'samples': 6880256, 'steps': 13437, 'loss/train': 2.0210657119750977}
-03/04/2022 05:14:43 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 05:14:46 - INFO - codeparrot_training - Step 13438: {'lr': 0.0004926675007491218, 'samples': 6880768, 'steps': 13438, 'loss/train': 2.03934383392334}
-03/04/2022 05:14:49 - INFO - codeparrot_training - Step 13439: {'lr': 0.0004926662248693912, 'samples': 6881280, 'steps': 13439, 'loss/train': 1.2984142303466797}
-03/04/2022 05:14:51 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/04/2022 05:14:54 - INFO - codeparrot_training - Step 13440: {'lr': 0.000492664948880319, 'samples': 6881792, 'steps': 13440, 'loss/train': 2.252088785171509}
-03/04/2022 05:14:58 - INFO - codeparrot_training - Step 13441: {'lr': 0.0004926636727819057, 'samples': 6882304, 'steps': 13441, 'loss/train': 1.8871530294418335}
-03/04/2022 05:14:59 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/04/2022 05:15:03 - INFO - codeparrot_training - Step 13442: {'lr': 0.0004926623965741519, 'samples': 6882816, 'steps': 13442, 'loss/train': 2.232340097427368}
-03/04/2022 05:15:06 - INFO - codeparrot_training - Step 13443: {'lr': 0.0004926611202570582, 'samples': 6883328, 'steps': 13443, 'loss/train': 2.0693295001983643}
-03/04/2022 05:15:07 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 05:15:11 - INFO - codeparrot_training - Step 13444: {'lr': 0.0004926598438306252, 'samples': 6883840, 'steps': 13444, 'loss/train': 1.3893249034881592}
-03/04/2022 05:15:15 - INFO - codeparrot_training - Step 13445: {'lr': 0.0004926585672948532, 'samples': 6884352, 'steps': 13445, 'loss/train': 1.23430335521698}
-03/04/2022 05:15:16 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/04/2022 05:15:20 - INFO - codeparrot_training - Step 13446: {'lr': 0.0004926572906497432, 'samples': 6884864, 'steps': 13446, 'loss/train': 1.953246831893921}
-03/04/2022 05:15:23 - INFO - codeparrot_training - Step 13447: {'lr': 0.0004926560138952955, 'samples': 6885376, 'steps': 13447, 'loss/train': 0.19027571380138397}
-03/04/2022 05:15:25 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/04/2022 05:15:28 - INFO - codeparrot_training - Step 13448: {'lr': 0.0004926547370315106, 'samples': 6885888, 'steps': 13448, 'loss/train': 0.5688481330871582}
-03/04/2022 05:15:31 - INFO - codeparrot_training - Step 13449: {'lr': 0.0004926534600583894, 'samples': 6886400, 'steps': 13449, 'loss/train': 1.2278218269348145}
-03/04/2022 05:15:33 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/04/2022 05:15:37 - INFO - codeparrot_training - Step 13450: {'lr': 0.0004926521829759323, 'samples': 6886912, 'steps': 13450, 'loss/train': 2.2948429584503174}
-03/04/2022 05:15:40 - INFO - codeparrot_training - Step 13451: {'lr': 0.0004926509057841397, 'samples': 6887424, 'steps': 13451, 'loss/train': 1.7474080324172974}
-03/04/2022 05:15:42 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/04/2022 05:15:45 - INFO - codeparrot_training - Step 13452: {'lr': 0.0004926496284830125, 'samples': 6887936, 'steps': 13452, 'loss/train': 2.330728769302368}
-03/04/2022 05:15:48 - INFO - codeparrot_training - Step 13453: {'lr': 0.0004926483510725511, 'samples': 6888448, 'steps': 13453, 'loss/train': 1.6540865898132324}
-03/04/2022 05:15:50 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/04/2022 05:15:54 - INFO - codeparrot_training - Step 13454: {'lr': 0.000492647073552756, 'samples': 6888960, 'steps': 13454, 'loss/train': 1.856745958328247}
-03/04/2022 05:15:57 - INFO - codeparrot_training - Step 13455: {'lr': 0.000492645795923628, 'samples': 6889472, 'steps': 13455, 'loss/train': 1.9347368478775024}
-03/04/2022 05:15:58 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/04/2022 05:16:02 - INFO - codeparrot_training - Step 13456: {'lr': 0.0004926445181851675, 'samples': 6889984, 'steps': 13456, 'loss/train': 1.89517343044281}
-03/04/2022 05:16:05 - INFO - codeparrot_training - Step 13457: {'lr': 0.0004926432403373752, 'samples': 6890496, 'steps': 13457, 'loss/train': 3.6312129497528076}
-03/04/2022 05:16:07 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/04/2022 05:16:10 - INFO - codeparrot_training - Step 13458: {'lr': 0.0004926419623802515, 'samples': 6891008, 'steps': 13458, 'loss/train': 2.9795172214508057}
-03/04/2022 05:16:14 - INFO - codeparrot_training - Step 13459: {'lr': 0.0004926406843137971, 'samples': 6891520, 'steps': 13459, 'loss/train': 2.1301276683807373}
-03/04/2022 05:16:15 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 05:16:19 - INFO - codeparrot_training - Step 13460: {'lr': 0.0004926394061380126, 'samples': 6892032, 'steps': 13460, 'loss/train': 1.6621326208114624}
-03/04/2022 05:16:22 - INFO - codeparrot_training - Step 13461: {'lr': 0.0004926381278528984, 'samples': 6892544, 'steps': 13461, 'loss/train': 2.3306474685668945}
-03/04/2022 05:16:25 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/04/2022 05:16:28 - INFO - codeparrot_training - Step 13462: {'lr': 0.0004926368494584553, 'samples': 6893056, 'steps': 13462, 'loss/train': 1.8882334232330322}
-03/04/2022 05:16:31 - INFO - codeparrot_training - Step 13463: {'lr': 0.0004926355709546838, 'samples': 6893568, 'steps': 13463, 'loss/train': 1.6502820253372192}
-03/04/2022 05:16:34 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/04/2022 05:16:36 - INFO - codeparrot_training - Step 13464: {'lr': 0.0004926342923415844, 'samples': 6894080, 'steps': 13464, 'loss/train': 1.818873643875122}
-03/04/2022 05:16:39 - INFO - codeparrot_training - Step 13465: {'lr': 0.0004926330136191577, 'samples': 6894592, 'steps': 13465, 'loss/train': 2.3190395832061768}
-03/04/2022 05:16:42 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/04/2022 05:16:44 - INFO - codeparrot_training - Step 13466: {'lr': 0.0004926317347874044, 'samples': 6895104, 'steps': 13466, 'loss/train': 1.901984453201294}
-03/04/2022 05:16:48 - INFO - codeparrot_training - Step 13467: {'lr': 0.000492630455846325, 'samples': 6895616, 'steps': 13467, 'loss/train': 1.85716712474823}
-03/04/2022 05:16:50 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/04/2022 05:16:53 - INFO - codeparrot_training - Step 13468: {'lr': 0.0004926291767959199, 'samples': 6896128, 'steps': 13468, 'loss/train': 2.3081700801849365}
-03/04/2022 05:16:56 - INFO - codeparrot_training - Step 13469: {'lr': 0.00049262789763619, 'samples': 6896640, 'steps': 13469, 'loss/train': 2.356903553009033}
-03/04/2022 05:16:59 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 05:17:02 - INFO - codeparrot_training - Step 13470: {'lr': 0.0004926266183671356, 'samples': 6897152, 'steps': 13470, 'loss/train': 1.526713490486145}
-03/04/2022 05:17:05 - INFO - codeparrot_training - Step 13471: {'lr': 0.0004926253389887575, 'samples': 6897664, 'steps': 13471, 'loss/train': 2.139163017272949}
-03/04/2022 05:17:08 - INFO - codeparrot_training - Step 13472: {'lr': 0.0004926240595010561, 'samples': 6898176, 'steps': 13472, 'loss/train': 2.045407772064209}
-03/04/2022 05:17:10 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 05:17:14 - INFO - codeparrot_training - Step 13473: {'lr': 0.000492622779904032, 'samples': 6898688, 'steps': 13473, 'loss/train': 2.124788761138916}
-03/04/2022 05:17:17 - INFO - codeparrot_training - Step 13474: {'lr': 0.000492621500197686, 'samples': 6899200, 'steps': 13474, 'loss/train': 1.6369333267211914}
-03/04/2022 05:17:19 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 05:17:22 - INFO - codeparrot_training - Step 13475: {'lr': 0.0004926202203820182, 'samples': 6899712, 'steps': 13475, 'loss/train': 1.9187955856323242}
-03/04/2022 05:17:25 - INFO - codeparrot_training - Step 13476: {'lr': 0.0004926189404570297, 'samples': 6900224, 'steps': 13476, 'loss/train': 2.213310718536377}
-03/04/2022 05:17:27 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/04/2022 05:17:31 - INFO - codeparrot_training - Step 13477: {'lr': 0.0004926176604227208, 'samples': 6900736, 'steps': 13477, 'loss/train': 2.3274128437042236}
-03/04/2022 05:17:34 - INFO - codeparrot_training - Step 13478: {'lr': 0.0004926163802790922, 'samples': 6901248, 'steps': 13478, 'loss/train': 2.6650452613830566}
-03/04/2022 05:17:36 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 05:17:39 - INFO - codeparrot_training - Step 13479: {'lr': 0.0004926151000261442, 'samples': 6901760, 'steps': 13479, 'loss/train': 2.1363463401794434}
-03/04/2022 05:17:42 - INFO - codeparrot_training - Step 13480: {'lr': 0.0004926138196638777, 'samples': 6902272, 'steps': 13480, 'loss/train': 1.9222080707550049}
-03/04/2022 05:17:44 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/04/2022 05:17:47 - INFO - codeparrot_training - Step 13481: {'lr': 0.0004926125391922932, 'samples': 6902784, 'steps': 13481, 'loss/train': 2.2532804012298584}
-03/04/2022 05:17:51 - INFO - codeparrot_training - Step 13482: {'lr': 0.0004926112586113912, 'samples': 6903296, 'steps': 13482, 'loss/train': 2.010538101196289}
-03/04/2022 05:17:53 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 05:17:56 - INFO - codeparrot_training - Step 13483: {'lr': 0.0004926099779211723, 'samples': 6903808, 'steps': 13483, 'loss/train': 2.648890733718872}
-03/04/2022 05:17:59 - INFO - codeparrot_training - Step 13484: {'lr': 0.0004926086971216371, 'samples': 6904320, 'steps': 13484, 'loss/train': 1.7678247690200806}
-03/04/2022 05:18:01 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/04/2022 05:18:05 - INFO - codeparrot_training - Step 13485: {'lr': 0.0004926074162127862, 'samples': 6904832, 'steps': 13485, 'loss/train': 1.4061825275421143}
-03/04/2022 05:18:08 - INFO - codeparrot_training - Step 13486: {'lr': 0.0004926061351946201, 'samples': 6905344, 'steps': 13486, 'loss/train': 1.705674409866333}
-03/04/2022 05:18:10 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/04/2022 05:18:13 - INFO - codeparrot_training - Step 13487: {'lr': 0.0004926048540671394, 'samples': 6905856, 'steps': 13487, 'loss/train': 2.181276559829712}
-03/04/2022 05:18:16 - INFO - codeparrot_training - Step 13488: {'lr': 0.0004926035728303447, 'samples': 6906368, 'steps': 13488, 'loss/train': 1.4857563972473145}
-03/04/2022 05:18:19 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/04/2022 05:18:21 - INFO - codeparrot_training - Step 13489: {'lr': 0.0004926022914842366, 'samples': 6906880, 'steps': 13489, 'loss/train': 2.1555094718933105}
-03/04/2022 05:18:25 - INFO - codeparrot_training - Step 13490: {'lr': 0.0004926010100288156, 'samples': 6907392, 'steps': 13490, 'loss/train': 2.1066508293151855}
-03/04/2022 05:18:27 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/04/2022 05:18:30 - INFO - codeparrot_training - Step 13491: {'lr': 0.0004925997284640823, 'samples': 6907904, 'steps': 13491, 'loss/train': 2.140728712081909}
-03/04/2022 05:18:33 - INFO - codeparrot_training - Step 13492: {'lr': 0.0004925984467900374, 'samples': 6908416, 'steps': 13492, 'loss/train': 2.2309622764587402}
-03/04/2022 05:18:36 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 05:18:38 - INFO - codeparrot_training - Step 13493: {'lr': 0.0004925971650066814, 'samples': 6908928, 'steps': 13493, 'loss/train': 1.6306496858596802}
-03/04/2022 05:18:41 - INFO - codeparrot_training - Step 13494: {'lr': 0.0004925958831140147, 'samples': 6909440, 'steps': 13494, 'loss/train': 1.8768305778503418}
-03/04/2022 05:18:44 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/04/2022 05:18:47 - INFO - codeparrot_training - Step 13495: {'lr': 0.0004925946011120382, 'samples': 6909952, 'steps': 13495, 'loss/train': 1.3399808406829834}
-03/04/2022 05:18:50 - INFO - codeparrot_training - Step 13496: {'lr': 0.0004925933190007523, 'samples': 6910464, 'steps': 13496, 'loss/train': 1.7801934480667114}
-03/04/2022 05:18:52 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 05:18:55 - INFO - codeparrot_training - Step 13497: {'lr': 0.0004925920367801575, 'samples': 6910976, 'steps': 13497, 'loss/train': 1.3534823656082153}
-03/04/2022 05:18:58 - INFO - codeparrot_training - Step 13498: {'lr': 0.0004925907544502545, 'samples': 6911488, 'steps': 13498, 'loss/train': 2.0174665451049805}
-03/04/2022 05:19:01 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/04/2022 05:19:04 - INFO - codeparrot_training - Step 13499: {'lr': 0.000492589472011044, 'samples': 6912000, 'steps': 13499, 'loss/train': 0.6362736225128174}
-03/04/2022 05:19:07 - INFO - codeparrot_training - Step 13500: {'lr': 0.0004925881894625263, 'samples': 6912512, 'steps': 13500, 'loss/train': 1.662095546722412}
-03/04/2022 05:19:09 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/04/2022 05:19:12 - INFO - codeparrot_training - Step 13501: {'lr': 0.0004925869068047021, 'samples': 6913024, 'steps': 13501, 'loss/train': 2.4770877361297607}
-03/04/2022 05:19:15 - INFO - codeparrot_training - Step 13502: {'lr': 0.000492585624037572, 'samples': 6913536, 'steps': 13502, 'loss/train': 1.7946038246154785}
-03/04/2022 05:19:17 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/04/2022 05:19:20 - INFO - codeparrot_training - Step 13503: {'lr': 0.0004925843411611366, 'samples': 6914048, 'steps': 13503, 'loss/train': 1.9703198671340942}
-03/04/2022 05:19:23 - INFO - codeparrot_training - Step 13504: {'lr': 0.0004925830581753964, 'samples': 6914560, 'steps': 13504, 'loss/train': 2.346294641494751}
-03/04/2022 05:19:26 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 05:19:29 - INFO - codeparrot_training - Step 13505: {'lr': 0.000492581775080352, 'samples': 6915072, 'steps': 13505, 'loss/train': 2.550539255142212}
-03/04/2022 05:19:32 - INFO - codeparrot_training - Step 13506: {'lr': 0.000492580491876004, 'samples': 6915584, 'steps': 13506, 'loss/train': 1.451461911201477}
-03/04/2022 05:19:34 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/04/2022 05:19:37 - INFO - codeparrot_training - Step 13507: {'lr': 0.000492579208562353, 'samples': 6916096, 'steps': 13507, 'loss/train': 1.5310044288635254}
-03/04/2022 05:19:40 - INFO - codeparrot_training - Step 13508: {'lr': 0.0004925779251393995, 'samples': 6916608, 'steps': 13508, 'loss/train': 2.2415313720703125}
-03/04/2022 05:19:43 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/04/2022 05:19:47 - INFO - codeparrot_training - Step 13509: {'lr': 0.0004925766416071441, 'samples': 6917120, 'steps': 13509, 'loss/train': 2.521507978439331}
-03/04/2022 05:19:50 - INFO - codeparrot_training - Step 13510: {'lr': 0.0004925753579655876, 'samples': 6917632, 'steps': 13510, 'loss/train': 3.3811023235321045}
-03/04/2022 05:19:53 - INFO - codeparrot_training - Step 13511: {'lr': 0.0004925740742147302, 'samples': 6918144, 'steps': 13511, 'loss/train': 2.5567383766174316}
-03/04/2022 05:19:55 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/04/2022 05:19:59 - INFO - codeparrot_training - Step 13512: {'lr': 0.0004925727903545727, 'samples': 6918656, 'steps': 13512, 'loss/train': 2.255796194076538}
-03/04/2022 05:20:02 - INFO - codeparrot_training - Step 13513: {'lr': 0.0004925715063851157, 'samples': 6919168, 'steps': 13513, 'loss/train': 2.0264289379119873}
-03/04/2022 05:20:05 - INFO - codeparrot_training - Step 13514: {'lr': 0.0004925702223063597, 'samples': 6919680, 'steps': 13514, 'loss/train': 0.08994235098361969}
-03/04/2022 05:20:06 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/04/2022 05:20:10 - INFO - codeparrot_training - Step 13515: {'lr': 0.0004925689381183052, 'samples': 6920192, 'steps': 13515, 'loss/train': 2.1495232582092285}
-03/04/2022 05:20:13 - INFO - codeparrot_training - Step 13516: {'lr': 0.0004925676538209531, 'samples': 6920704, 'steps': 13516, 'loss/train': 1.836436152458191}
-03/04/2022 05:20:14 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/04/2022 05:20:19 - INFO - codeparrot_training - Step 13517: {'lr': 0.0004925663694143036, 'samples': 6921216, 'steps': 13517, 'loss/train': 1.7946308851242065}
-03/04/2022 05:20:22 - INFO - codeparrot_training - Step 13518: {'lr': 0.0004925650848983575, 'samples': 6921728, 'steps': 13518, 'loss/train': 1.8348814249038696}
-03/04/2022 05:20:27 - INFO - codeparrot_training - Step 13519: {'lr': 0.0004925638002731153, 'samples': 6922240, 'steps': 13519, 'loss/train': 2.0067808628082275}
-03/04/2022 05:20:30 - INFO - codeparrot_training - Step 13520: {'lr': 0.0004925625155385775, 'samples': 6922752, 'steps': 13520, 'loss/train': 2.855752468109131}
-03/04/2022 05:20:31 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/04/2022 05:20:36 - INFO - codeparrot_training - Step 13521: {'lr': 0.0004925612306947449, 'samples': 6923264, 'steps': 13521, 'loss/train': 1.3104417324066162}
-03/04/2022 05:20:39 - INFO - codeparrot_training - Step 13522: {'lr': 0.0004925599457416179, 'samples': 6923776, 'steps': 13522, 'loss/train': 1.9305830001831055}
-03/04/2022 05:20:44 - INFO - codeparrot_training - Step 13523: {'lr': 0.0004925586606791972, 'samples': 6924288, 'steps': 13523, 'loss/train': 1.3736974000930786}
-03/04/2022 05:20:47 - INFO - codeparrot_training - Step 13524: {'lr': 0.0004925573755074832, 'samples': 6924800, 'steps': 13524, 'loss/train': 3.020737886428833}
-03/04/2022 05:20:48 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/04/2022 05:20:52 - INFO - codeparrot_training - Step 13525: {'lr': 0.0004925560902264766, 'samples': 6925312, 'steps': 13525, 'loss/train': 1.5558431148529053}
-03/04/2022 05:20:56 - INFO - codeparrot_training - Step 13526: {'lr': 0.000492554804836178, 'samples': 6925824, 'steps': 13526, 'loss/train': 1.2434511184692383}
-03/04/2022 05:20:56 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 05:21:01 - INFO - codeparrot_training - Step 13527: {'lr': 0.000492553519336588, 'samples': 6926336, 'steps': 13527, 'loss/train': 1.047995924949646}
-03/04/2022 05:21:04 - INFO - codeparrot_training - Step 13528: {'lr': 0.000492552233727707, 'samples': 6926848, 'steps': 13528, 'loss/train': 2.210149049758911}
-03/04/2022 05:21:04 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 05:21:09 - INFO - codeparrot_training - Step 13529: {'lr': 0.0004925509480095358, 'samples': 6927360, 'steps': 13529, 'loss/train': 0.39753738045692444}
-03/04/2022 05:21:12 - INFO - codeparrot_training - Step 13530: {'lr': 0.0004925496621820749, 'samples': 6927872, 'steps': 13530, 'loss/train': 2.476029634475708}
-03/04/2022 05:21:13 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/04/2022 05:21:18 - INFO - codeparrot_training - Step 13531: {'lr': 0.0004925483762453249, 'samples': 6928384, 'steps': 13531, 'loss/train': 1.3090766668319702}
-03/04/2022 05:21:21 - INFO - codeparrot_training - Step 13532: {'lr': 0.0004925470901992863, 'samples': 6928896, 'steps': 13532, 'loss/train': 0.3224385380744934}
-03/04/2022 05:21:22 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 05:21:26 - INFO - codeparrot_training - Step 13533: {'lr': 0.0004925458040439596, 'samples': 6929408, 'steps': 13533, 'loss/train': 1.1418240070343018}
-03/04/2022 05:21:29 - INFO - codeparrot_training - Step 13534: {'lr': 0.0004925445177793457, 'samples': 6929920, 'steps': 13534, 'loss/train': 2.3276007175445557}
-03/04/2022 05:21:30 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/04/2022 05:21:35 - INFO - codeparrot_training - Step 13535: {'lr': 0.0004925432314054448, 'samples': 6930432, 'steps': 13535, 'loss/train': 2.479883909225464}
-03/04/2022 05:21:38 - INFO - codeparrot_training - Step 13536: {'lr': 0.0004925419449222578, 'samples': 6930944, 'steps': 13536, 'loss/train': 1.3037700653076172}
-03/04/2022 05:21:39 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 05:21:43 - INFO - codeparrot_training - Step 13537: {'lr': 0.0004925406583297851, 'samples': 6931456, 'steps': 13537, 'loss/train': 0.7279533743858337}
-03/04/2022 05:21:46 - INFO - codeparrot_training - Step 13538: {'lr': 0.0004925393716280274, 'samples': 6931968, 'steps': 13538, 'loss/train': 2.6059703826904297}
-03/04/2022 05:21:47 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/04/2022 05:21:52 - INFO - codeparrot_training - Step 13539: {'lr': 0.0004925380848169851, 'samples': 6932480, 'steps': 13539, 'loss/train': 2.4498519897460938}
-03/04/2022 05:21:55 - INFO - codeparrot_training - Step 13540: {'lr': 0.0004925367978966588, 'samples': 6932992, 'steps': 13540, 'loss/train': 0.4040643572807312}
-03/04/2022 05:21:55 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 05:22:00 - INFO - codeparrot_training - Step 13541: {'lr': 0.0004925355108670493, 'samples': 6933504, 'steps': 13541, 'loss/train': 1.7866746187210083}
-03/04/2022 05:22:03 - INFO - codeparrot_training - Step 13542: {'lr': 0.0004925342237281571, 'samples': 6934016, 'steps': 13542, 'loss/train': 2.3927597999572754}
-03/04/2022 05:22:03 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/04/2022 05:22:08 - INFO - codeparrot_training - Step 13543: {'lr': 0.0004925329364799825, 'samples': 6934528, 'steps': 13543, 'loss/train': 2.1777451038360596}
-03/04/2022 05:22:12 - INFO - codeparrot_training - Step 13544: {'lr': 0.0004925316491225265, 'samples': 6935040, 'steps': 13544, 'loss/train': 1.9517524242401123}
-03/04/2022 05:22:12 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 05:22:17 - INFO - codeparrot_training - Step 13545: {'lr': 0.0004925303616557893, 'samples': 6935552, 'steps': 13545, 'loss/train': 1.5095123052597046}
-03/04/2022 05:22:20 - INFO - codeparrot_training - Step 13546: {'lr': 0.0004925290740797718, 'samples': 6936064, 'steps': 13546, 'loss/train': 1.2489185333251953}
-03/04/2022 05:22:20 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/04/2022 05:22:25 - INFO - codeparrot_training - Step 13547: {'lr': 0.0004925277863944745, 'samples': 6936576, 'steps': 13547, 'loss/train': 1.2392264604568481}
-03/04/2022 05:22:28 - INFO - codeparrot_training - Step 13548: {'lr': 0.0004925264985998978, 'samples': 6937088, 'steps': 13548, 'loss/train': 2.522761106491089}
-03/04/2022 05:22:30 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 05:22:34 - INFO - codeparrot_training - Step 13549: {'lr': 0.0004925252106960425, 'samples': 6937600, 'steps': 13549, 'loss/train': 1.559619665145874}
-03/04/2022 05:22:37 - INFO - codeparrot_training - Step 13550: {'lr': 0.000492523922682909, 'samples': 6938112, 'steps': 13550, 'loss/train': 1.5317686796188354}
-03/04/2022 05:22:38 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/04/2022 05:22:42 - INFO - codeparrot_training - Step 13551: {'lr': 0.0004925226345604979, 'samples': 6938624, 'steps': 13551, 'loss/train': 2.378748893737793}
-03/04/2022 05:22:46 - INFO - codeparrot_training - Step 13552: {'lr': 0.0004925213463288099, 'samples': 6939136, 'steps': 13552, 'loss/train': 2.16408109664917}
-03/04/2022 05:22:46 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/04/2022 05:22:51 - INFO - codeparrot_training - Step 13553: {'lr': 0.0004925200579878456, 'samples': 6939648, 'steps': 13553, 'loss/train': 2.1439409255981445}
-03/04/2022 05:22:54 - INFO - codeparrot_training - Step 13554: {'lr': 0.0004925187695376055, 'samples': 6940160, 'steps': 13554, 'loss/train': 2.1641719341278076}
-03/04/2022 05:22:55 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/04/2022 05:22:59 - INFO - codeparrot_training - Step 13555: {'lr': 0.0004925174809780901, 'samples': 6940672, 'steps': 13555, 'loss/train': 2.239227533340454}
-03/04/2022 05:23:03 - INFO - codeparrot_training - Step 13556: {'lr': 0.0004925161923093001, 'samples': 6941184, 'steps': 13556, 'loss/train': 1.1068352460861206}
-03/04/2022 05:23:03 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/04/2022 05:23:08 - INFO - codeparrot_training - Step 13557: {'lr': 0.000492514903531236, 'samples': 6941696, 'steps': 13557, 'loss/train': 1.2473351955413818}
-03/04/2022 05:23:11 - INFO - codeparrot_training - Step 13558: {'lr': 0.0004925136146438986, 'samples': 6942208, 'steps': 13558, 'loss/train': 1.990122675895691}
-03/04/2022 05:23:12 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/04/2022 05:23:16 - INFO - codeparrot_training - Step 13559: {'lr': 0.0004925123256472881, 'samples': 6942720, 'steps': 13559, 'loss/train': 1.3115978240966797}
-03/04/2022 05:23:19 - INFO - codeparrot_training - Step 13560: {'lr': 0.0004925110365414054, 'samples': 6943232, 'steps': 13560, 'loss/train': 1.770188808441162}
-03/04/2022 05:23:20 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/04/2022 05:23:25 - INFO - codeparrot_training - Step 13561: {'lr': 0.0004925097473262509, 'samples': 6943744, 'steps': 13561, 'loss/train': 1.9573014974594116}
-03/04/2022 05:23:28 - INFO - codeparrot_training - Step 13562: {'lr': 0.0004925084580018253, 'samples': 6944256, 'steps': 13562, 'loss/train': 2.0674917697906494}
-03/04/2022 05:23:28 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/04/2022 05:23:33 - INFO - codeparrot_training - Step 13563: {'lr': 0.0004925071685681292, 'samples': 6944768, 'steps': 13563, 'loss/train': 1.6297191381454468}
-03/04/2022 05:23:36 - INFO - codeparrot_training - Step 13564: {'lr': 0.000492505879025163, 'samples': 6945280, 'steps': 13564, 'loss/train': 2.488027811050415}
-03/04/2022 05:23:37 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/04/2022 05:23:41 - INFO - codeparrot_training - Step 13565: {'lr': 0.0004925045893729274, 'samples': 6945792, 'steps': 13565, 'loss/train': 1.8187692165374756}
-03/04/2022 05:23:45 - INFO - codeparrot_training - Step 13566: {'lr': 0.000492503299611423, 'samples': 6946304, 'steps': 13566, 'loss/train': 2.0925350189208984}
-03/04/2022 05:23:45 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/04/2022 05:23:50 - INFO - codeparrot_training - Step 13567: {'lr': 0.0004925020097406504, 'samples': 6946816, 'steps': 13567, 'loss/train': 1.6251267194747925}
-03/04/2022 05:23:53 - INFO - codeparrot_training - Step 13568: {'lr': 0.00049250071976061, 'samples': 6947328, 'steps': 13568, 'loss/train': 0.7762260437011719}
-03/04/2022 05:23:54 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 05:23:58 - INFO - codeparrot_training - Step 13569: {'lr': 0.0004924994296713026, 'samples': 6947840, 'steps': 13569, 'loss/train': 2.2228825092315674}
-03/04/2022 05:24:01 - INFO - codeparrot_training - Step 13570: {'lr': 0.0004924981394727288, 'samples': 6948352, 'steps': 13570, 'loss/train': 2.542447090148926}
-03/04/2022 05:24:03 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/04/2022 05:24:07 - INFO - codeparrot_training - Step 13571: {'lr': 0.0004924968491648889, 'samples': 6948864, 'steps': 13571, 'loss/train': 2.1445789337158203}
-03/04/2022 05:24:10 - INFO - codeparrot_training - Step 13572: {'lr': 0.0004924955587477837, 'samples': 6949376, 'steps': 13572, 'loss/train': 2.189575672149658}
-03/04/2022 05:24:11 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/04/2022 05:24:15 - INFO - codeparrot_training - Step 13573: {'lr': 0.0004924942682214138, 'samples': 6949888, 'steps': 13573, 'loss/train': 1.4546749591827393}
-03/04/2022 05:24:18 - INFO - codeparrot_training - Step 13574: {'lr': 0.0004924929775857798, 'samples': 6950400, 'steps': 13574, 'loss/train': 2.3234424591064453}
-03/04/2022 05:24:19 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 05:24:24 - INFO - codeparrot_training - Step 13575: {'lr': 0.0004924916868408821, 'samples': 6950912, 'steps': 13575, 'loss/train': 1.4348307847976685}
-03/04/2022 05:24:27 - INFO - codeparrot_training - Step 13576: {'lr': 0.0004924903959867214, 'samples': 6951424, 'steps': 13576, 'loss/train': 1.7732630968093872}
-03/04/2022 05:24:27 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/04/2022 05:24:32 - INFO - codeparrot_training - Step 13577: {'lr': 0.0004924891050232984, 'samples': 6951936, 'steps': 13577, 'loss/train': 2.0082669258117676}
-03/04/2022 05:24:35 - INFO - codeparrot_training - Step 13578: {'lr': 0.0004924878139506134, 'samples': 6952448, 'steps': 13578, 'loss/train': 2.157660484313965}
-03/04/2022 05:24:36 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/04/2022 05:24:40 - INFO - codeparrot_training - Step 13579: {'lr': 0.0004924865227686671, 'samples': 6952960, 'steps': 13579, 'loss/train': 2.332773447036743}
-03/04/2022 05:24:44 - INFO - codeparrot_training - Step 13580: {'lr': 0.0004924852314774602, 'samples': 6953472, 'steps': 13580, 'loss/train': 1.786578893661499}
-03/04/2022 05:24:44 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/04/2022 05:24:49 - INFO - codeparrot_training - Step 13581: {'lr': 0.0004924839400769932, 'samples': 6953984, 'steps': 13581, 'loss/train': 1.6177051067352295}
-03/04/2022 05:24:52 - INFO - codeparrot_training - Step 13582: {'lr': 0.0004924826485672667, 'samples': 6954496, 'steps': 13582, 'loss/train': 1.8337808847427368}
-03/04/2022 05:24:53 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/04/2022 05:24:57 - INFO - codeparrot_training - Step 13583: {'lr': 0.0004924813569482812, 'samples': 6955008, 'steps': 13583, 'loss/train': 1.8550056219100952}
-03/04/2022 05:25:00 - INFO - codeparrot_training - Step 13584: {'lr': 0.0004924800652200373, 'samples': 6955520, 'steps': 13584, 'loss/train': 2.1848936080932617}
-03/04/2022 05:25:01 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/04/2022 05:25:06 - INFO - codeparrot_training - Step 13585: {'lr': 0.0004924787733825357, 'samples': 6956032, 'steps': 13585, 'loss/train': 2.4904232025146484}
-03/04/2022 05:25:09 - INFO - codeparrot_training - Step 13586: {'lr': 0.0004924774814357768, 'samples': 6956544, 'steps': 13586, 'loss/train': 2.3049912452697754}
-03/04/2022 05:25:09 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 05:25:14 - INFO - codeparrot_training - Step 13587: {'lr': 0.0004924761893797615, 'samples': 6957056, 'steps': 13587, 'loss/train': 1.401726484298706}
-03/04/2022 05:25:17 - INFO - codeparrot_training - Step 13588: {'lr': 0.00049247489721449, 'samples': 6957568, 'steps': 13588, 'loss/train': 1.3148479461669922}
-03/04/2022 05:25:18 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/04/2022 05:25:23 - INFO - codeparrot_training - Step 13589: {'lr': 0.0004924736049399631, 'samples': 6958080, 'steps': 13589, 'loss/train': 1.3621245622634888}
-03/04/2022 05:25:26 - INFO - codeparrot_training - Step 13590: {'lr': 0.0004924723125561813, 'samples': 6958592, 'steps': 13590, 'loss/train': 1.4765440225601196}
-03/04/2022 05:25:26 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/04/2022 05:25:31 - INFO - codeparrot_training - Step 13591: {'lr': 0.0004924710200631453, 'samples': 6959104, 'steps': 13591, 'loss/train': 1.8108930587768555}
-03/04/2022 05:25:34 - INFO - codeparrot_training - Step 13592: {'lr': 0.0004924697274608556, 'samples': 6959616, 'steps': 13592, 'loss/train': 2.880939245223999}
-03/04/2022 05:25:36 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/04/2022 05:25:40 - INFO - codeparrot_training - Step 13593: {'lr': 0.0004924684347493126, 'samples': 6960128, 'steps': 13593, 'loss/train': 1.6047450304031372}
-03/04/2022 05:25:43 - INFO - codeparrot_training - Step 13594: {'lr': 0.0004924671419285172, 'samples': 6960640, 'steps': 13594, 'loss/train': 1.8335658311843872}
-03/04/2022 05:25:44 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/04/2022 05:25:48 - INFO - codeparrot_training - Step 13595: {'lr': 0.0004924658489984699, 'samples': 6961152, 'steps': 13595, 'loss/train': 1.3684356212615967}
-03/04/2022 05:25:51 - INFO - codeparrot_training - Step 13596: {'lr': 0.0004924645559591712, 'samples': 6961664, 'steps': 13596, 'loss/train': 2.3713643550872803}
-03/04/2022 05:25:52 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/04/2022 05:25:56 - INFO - codeparrot_training - Step 13597: {'lr': 0.0004924632628106217, 'samples': 6962176, 'steps': 13597, 'loss/train': 1.6199485063552856}
-03/04/2022 05:26:00 - INFO - codeparrot_training - Step 13598: {'lr': 0.000492461969552822, 'samples': 6962688, 'steps': 13598, 'loss/train': 2.30619740486145}
-03/04/2022 05:26:01 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 05:26:05 - INFO - codeparrot_training - Step 13599: {'lr': 0.0004924606761857726, 'samples': 6963200, 'steps': 13599, 'loss/train': 1.4329155683517456}
-03/04/2022 05:26:08 - INFO - codeparrot_training - Step 13600: {'lr': 0.0004924593827094744, 'samples': 6963712, 'steps': 13600, 'loss/train': 2.134326696395874}
-03/04/2022 05:26:09 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/04/2022 05:26:14 - INFO - codeparrot_training - Step 13601: {'lr': 0.0004924580891239274, 'samples': 6964224, 'steps': 13601, 'loss/train': 1.5783792734146118}
-03/04/2022 05:26:17 - INFO - codeparrot_training - Step 13602: {'lr': 0.0004924567954291328, 'samples': 6964736, 'steps': 13602, 'loss/train': 2.30511212348938}
-03/04/2022 05:26:19 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 05:26:22 - INFO - codeparrot_training - Step 13603: {'lr': 0.0004924555016250908, 'samples': 6965248, 'steps': 13603, 'loss/train': 1.3425709009170532}
-03/04/2022 05:26:25 - INFO - codeparrot_training - Step 13604: {'lr': 0.0004924542077118021, 'samples': 6965760, 'steps': 13604, 'loss/train': 1.9989111423492432}
-03/04/2022 05:26:28 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 05:26:31 - INFO - codeparrot_training - Step 13605: {'lr': 0.0004924529136892673, 'samples': 6966272, 'steps': 13605, 'loss/train': 2.1374306678771973}
-03/04/2022 05:26:34 - INFO - codeparrot_training - Step 13606: {'lr': 0.0004924516195574869, 'samples': 6966784, 'steps': 13606, 'loss/train': 2.869487762451172}
-03/04/2022 05:26:37 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/04/2022 05:26:39 - INFO - codeparrot_training - Step 13607: {'lr': 0.0004924503253164614, 'samples': 6967296, 'steps': 13607, 'loss/train': 2.038933038711548}
-03/04/2022 05:26:42 - INFO - codeparrot_training - Step 13608: {'lr': 0.0004924490309661918, 'samples': 6967808, 'steps': 13608, 'loss/train': 2.109379291534424}
-03/04/2022 05:26:45 - INFO - codeparrot_training - Step 13609: {'lr': 0.0004924477365066783, 'samples': 6968320, 'steps': 13609, 'loss/train': 1.8304818868637085}
-03/04/2022 05:26:45 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/04/2022 05:26:51 - INFO - codeparrot_training - Step 13610: {'lr': 0.0004924464419379217, 'samples': 6968832, 'steps': 13610, 'loss/train': 2.289030075073242}
-03/04/2022 05:26:54 - INFO - codeparrot_training - Step 13611: {'lr': 0.0004924451472599222, 'samples': 6969344, 'steps': 13611, 'loss/train': 2.35603404045105}
-03/04/2022 05:26:54 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/04/2022 05:26:59 - INFO - codeparrot_training - Step 13612: {'lr': 0.000492443852472681, 'samples': 6969856, 'steps': 13612, 'loss/train': 2.2680470943450928}
-03/04/2022 05:27:02 - INFO - codeparrot_training - Step 13613: {'lr': 0.000492442557576198, 'samples': 6970368, 'steps': 13613, 'loss/train': 2.816297769546509}
-03/04/2022 05:27:02 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 05:27:08 - INFO - codeparrot_training - Step 13614: {'lr': 0.0004924412625704744, 'samples': 6970880, 'steps': 13614, 'loss/train': 1.4156662225723267}
-03/04/2022 05:27:10 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/04/2022 05:27:13 - INFO - codeparrot_training - Step 13615: {'lr': 0.0004924399674555103, 'samples': 6971392, 'steps': 13615, 'loss/train': 3.3438618183135986}
-03/04/2022 05:27:16 - INFO - codeparrot_training - Step 13616: {'lr': 0.0004924386722313066, 'samples': 6971904, 'steps': 13616, 'loss/train': 1.7403500080108643}
-03/04/2022 05:27:19 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 05:27:21 - INFO - codeparrot_training - Step 13617: {'lr': 0.0004924373768978638, 'samples': 6972416, 'steps': 13617, 'loss/train': 4.93893575668335}
-03/04/2022 05:27:24 - INFO - codeparrot_training - Step 13618: {'lr': 0.0004924360814551825, 'samples': 6972928, 'steps': 13618, 'loss/train': 2.1774485111236572}
-03/04/2022 05:27:27 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/04/2022 05:27:30 - INFO - codeparrot_training - Step 13619: {'lr': 0.0004924347859032631, 'samples': 6973440, 'steps': 13619, 'loss/train': 2.4175825119018555}
-03/04/2022 05:27:33 - INFO - codeparrot_training - Step 13620: {'lr': 0.0004924334902421065, 'samples': 6973952, 'steps': 13620, 'loss/train': 2.313145875930786}
-03/04/2022 05:27:35 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 05:27:38 - INFO - codeparrot_training - Step 13621: {'lr': 0.0004924321944717129, 'samples': 6974464, 'steps': 13621, 'loss/train': 2.197544813156128}
-03/04/2022 05:27:41 - INFO - codeparrot_training - Step 13622: {'lr': 0.0004924308985920832, 'samples': 6974976, 'steps': 13622, 'loss/train': 1.8921781778335571}
-03/04/2022 05:27:43 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/04/2022 05:27:47 - INFO - codeparrot_training - Step 13623: {'lr': 0.0004924296026032179, 'samples': 6975488, 'steps': 13623, 'loss/train': 1.9220691919326782}
-03/04/2022 05:27:50 - INFO - codeparrot_training - Step 13624: {'lr': 0.0004924283065051176, 'samples': 6976000, 'steps': 13624, 'loss/train': 1.5789515972137451}
-03/04/2022 05:27:52 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 05:27:55 - INFO - codeparrot_training - Step 13625: {'lr': 0.0004924270102977827, 'samples': 6976512, 'steps': 13625, 'loss/train': 1.4915937185287476}
-03/04/2022 05:27:58 - INFO - codeparrot_training - Step 13626: {'lr': 0.0004924257139812141, 'samples': 6977024, 'steps': 13626, 'loss/train': 1.8407337665557861}
-03/04/2022 05:28:01 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/04/2022 05:28:04 - INFO - codeparrot_training - Step 13627: {'lr': 0.0004924244175554121, 'samples': 6977536, 'steps': 13627, 'loss/train': 2.125081777572632}
-03/04/2022 05:28:07 - INFO - codeparrot_training - Step 13628: {'lr': 0.0004924231210203775, 'samples': 6978048, 'steps': 13628, 'loss/train': 0.6267706155776978}
-03/04/2022 05:28:09 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 05:28:12 - INFO - codeparrot_training - Step 13629: {'lr': 0.0004924218243761106, 'samples': 6978560, 'steps': 13629, 'loss/train': 1.2793807983398438}
-03/04/2022 05:28:15 - INFO - codeparrot_training - Step 13630: {'lr': 0.0004924205276226123, 'samples': 6979072, 'steps': 13630, 'loss/train': 2.2741260528564453}
-03/04/2022 05:28:17 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/04/2022 05:28:20 - INFO - codeparrot_training - Step 13631: {'lr': 0.000492419230759883, 'samples': 6979584, 'steps': 13631, 'loss/train': 1.2786744832992554}
-03/04/2022 05:28:23 - INFO - codeparrot_training - Step 13632: {'lr': 0.0004924179337879234, 'samples': 6980096, 'steps': 13632, 'loss/train': 1.8926026821136475}
-03/04/2022 05:28:26 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 05:28:29 - INFO - codeparrot_training - Step 13633: {'lr': 0.000492416636706734, 'samples': 6980608, 'steps': 13633, 'loss/train': 2.418912172317505}
-03/04/2022 05:28:32 - INFO - codeparrot_training - Step 13634: {'lr': 0.0004924153395163153, 'samples': 6981120, 'steps': 13634, 'loss/train': 2.8478331565856934}
-03/04/2022 05:28:34 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/04/2022 05:28:37 - INFO - codeparrot_training - Step 13635: {'lr': 0.0004924140422166681, 'samples': 6981632, 'steps': 13635, 'loss/train': 2.1206393241882324}
-03/04/2022 05:28:40 - INFO - codeparrot_training - Step 13636: {'lr': 0.0004924127448077929, 'samples': 6982144, 'steps': 13636, 'loss/train': 1.1110291481018066}
-03/04/2022 05:28:42 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 05:28:45 - INFO - codeparrot_training - Step 13637: {'lr': 0.0004924114472896902, 'samples': 6982656, 'steps': 13637, 'loss/train': 0.977797269821167}
-03/04/2022 05:28:49 - INFO - codeparrot_training - Step 13638: {'lr': 0.0004924101496623606, 'samples': 6983168, 'steps': 13638, 'loss/train': 2.2239527702331543}
-03/04/2022 05:28:50 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/04/2022 05:28:54 - INFO - codeparrot_training - Step 13639: {'lr': 0.0004924088519258049, 'samples': 6983680, 'steps': 13639, 'loss/train': 0.21945294737815857}
-03/04/2022 05:28:57 - INFO - codeparrot_training - Step 13640: {'lr': 0.0004924075540800233, 'samples': 6984192, 'steps': 13640, 'loss/train': 2.228769063949585}
-03/04/2022 05:29:00 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/04/2022 05:29:03 - INFO - codeparrot_training - Step 13641: {'lr': 0.0004924062561250167, 'samples': 6984704, 'steps': 13641, 'loss/train': 1.9830541610717773}
-03/04/2022 05:29:06 - INFO - codeparrot_training - Step 13642: {'lr': 0.0004924049580607855, 'samples': 6985216, 'steps': 13642, 'loss/train': 1.2833359241485596}
-03/04/2022 05:29:09 - INFO - codeparrot_training - Step 13643: {'lr': 0.0004924036598873305, 'samples': 6985728, 'steps': 13643, 'loss/train': 2.361818313598633}
-03/04/2022 05:29:10 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/04/2022 05:29:14 - INFO - codeparrot_training - Step 13644: {'lr': 0.0004924023616046521, 'samples': 6986240, 'steps': 13644, 'loss/train': 1.8041396141052246}
-03/04/2022 05:29:18 - INFO - codeparrot_training - Step 13645: {'lr': 0.000492401063212751, 'samples': 6986752, 'steps': 13645, 'loss/train': 1.5789713859558105}
-03/04/2022 05:29:19 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/04/2022 05:29:23 - INFO - codeparrot_training - Step 13646: {'lr': 0.0004923997647116276, 'samples': 6987264, 'steps': 13646, 'loss/train': 1.858320951461792}
-03/04/2022 05:29:26 - INFO - codeparrot_training - Step 13647: {'lr': 0.0004923984661012827, 'samples': 6987776, 'steps': 13647, 'loss/train': 1.4062340259552002}
-03/04/2022 05:29:27 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/04/2022 05:29:31 - INFO - codeparrot_training - Step 13648: {'lr': 0.0004923971673817167, 'samples': 6988288, 'steps': 13648, 'loss/train': 1.9781841039657593}
-03/04/2022 05:29:34 - INFO - codeparrot_training - Step 13649: {'lr': 0.0004923958685529303, 'samples': 6988800, 'steps': 13649, 'loss/train': 2.2174887657165527}
-03/04/2022 05:29:35 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/04/2022 05:29:40 - INFO - codeparrot_training - Step 13650: {'lr': 0.0004923945696149241, 'samples': 6989312, 'steps': 13650, 'loss/train': 0.7192129492759705}
-03/04/2022 05:29:43 - INFO - codeparrot_training - Step 13651: {'lr': 0.0004923932705676986, 'samples': 6989824, 'steps': 13651, 'loss/train': 2.0144400596618652}
-03/04/2022 05:29:48 - INFO - codeparrot_training - Step 13652: {'lr': 0.0004923919714112545, 'samples': 6990336, 'steps': 13652, 'loss/train': 2.3147919178009033}
-03/04/2022 05:29:51 - INFO - codeparrot_training - Step 13653: {'lr': 0.0004923906721455922, 'samples': 6990848, 'steps': 13653, 'loss/train': 1.6381654739379883}
-03/04/2022 05:29:52 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 05:29:57 - INFO - codeparrot_training - Step 13654: {'lr': 0.0004923893727707125, 'samples': 6991360, 'steps': 13654, 'loss/train': 1.8692902326583862}
-03/04/2022 05:30:00 - INFO - codeparrot_training - Step 13655: {'lr': 0.0004923880732866159, 'samples': 6991872, 'steps': 13655, 'loss/train': 1.8588309288024902}
-03/04/2022 05:30:00 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/04/2022 05:30:05 - INFO - codeparrot_training - Step 13656: {'lr': 0.0004923867736933029, 'samples': 6992384, 'steps': 13656, 'loss/train': 0.5575523972511292}
-03/04/2022 05:30:08 - INFO - codeparrot_training - Step 13657: {'lr': 0.0004923854739907743, 'samples': 6992896, 'steps': 13657, 'loss/train': 1.463771939277649}
-03/04/2022 05:30:09 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/04/2022 05:30:13 - INFO - codeparrot_training - Step 13658: {'lr': 0.0004923841741790304, 'samples': 6993408, 'steps': 13658, 'loss/train': 1.952718734741211}
-03/04/2022 05:30:16 - INFO - codeparrot_training - Step 13659: {'lr': 0.0004923828742580719, 'samples': 6993920, 'steps': 13659, 'loss/train': 1.6298378705978394}
-03/04/2022 05:30:17 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/04/2022 05:30:22 - INFO - codeparrot_training - Step 13660: {'lr': 0.0004923815742278996, 'samples': 6994432, 'steps': 13660, 'loss/train': 2.0043890476226807}
-03/04/2022 05:30:25 - INFO - codeparrot_training - Step 13661: {'lr': 0.0004923802740885139, 'samples': 6994944, 'steps': 13661, 'loss/train': 1.4171550273895264}
-03/04/2022 05:30:25 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 05:30:30 - INFO - codeparrot_training - Step 13662: {'lr': 0.0004923789738399152, 'samples': 6995456, 'steps': 13662, 'loss/train': 2.4771206378936768}
-03/04/2022 05:30:33 - INFO - codeparrot_training - Step 13663: {'lr': 0.0004923776734821044, 'samples': 6995968, 'steps': 13663, 'loss/train': 2.5788869857788086}
-03/04/2022 05:30:33 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 05:30:39 - INFO - codeparrot_training - Step 13664: {'lr': 0.0004923763730150819, 'samples': 6996480, 'steps': 13664, 'loss/train': 1.8427051305770874}
-03/04/2022 05:30:42 - INFO - codeparrot_training - Step 13665: {'lr': 0.0004923750724388483, 'samples': 6996992, 'steps': 13665, 'loss/train': 1.6044913530349731}
-03/04/2022 05:30:42 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/04/2022 05:30:47 - INFO - codeparrot_training - Step 13666: {'lr': 0.0004923737717534044, 'samples': 6997504, 'steps': 13666, 'loss/train': 0.6680895686149597}
-03/04/2022 05:30:50 - INFO - codeparrot_training - Step 13667: {'lr': 0.0004923724709587504, 'samples': 6998016, 'steps': 13667, 'loss/train': 0.7211914658546448}
-03/04/2022 05:30:50 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 05:30:55 - INFO - codeparrot_training - Step 13668: {'lr': 0.0004923711700548873, 'samples': 6998528, 'steps': 13668, 'loss/train': 2.085970878601074}
-03/04/2022 05:30:59 - INFO - codeparrot_training - Step 13669: {'lr': 0.0004923698690418154, 'samples': 6999040, 'steps': 13669, 'loss/train': 1.7607659101486206}
-03/04/2022 05:30:59 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/04/2022 05:31:04 - INFO - codeparrot_training - Step 13670: {'lr': 0.0004923685679195355, 'samples': 6999552, 'steps': 13670, 'loss/train': 1.502682089805603}
-03/04/2022 05:31:07 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/04/2022 05:31:09 - INFO - codeparrot_training - Step 13671: {'lr': 0.0004923672666880479, 'samples': 7000064, 'steps': 13671, 'loss/train': 2.853696584701538}
-03/04/2022 05:31:12 - INFO - codeparrot_training - Step 13672: {'lr': 0.0004923659653473533, 'samples': 7000576, 'steps': 13672, 'loss/train': 2.4992403984069824}
-03/04/2022 05:31:15 - INFO - codeparrot_training - Step 13673: {'lr': 0.0004923646638974524, 'samples': 7001088, 'steps': 13673, 'loss/train': 1.5706171989440918}
-03/04/2022 05:31:15 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/04/2022 05:31:21 - INFO - codeparrot_training - Step 13674: {'lr': 0.0004923633623383459, 'samples': 7001600, 'steps': 13674, 'loss/train': 2.259997606277466}
-03/04/2022 05:31:23 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 05:31:26 - INFO - codeparrot_training - Step 13675: {'lr': 0.0004923620606700341, 'samples': 7002112, 'steps': 13675, 'loss/train': 1.2341901063919067}
-03/04/2022 05:31:29 - INFO - codeparrot_training - Step 13676: {'lr': 0.0004923607588925177, 'samples': 7002624, 'steps': 13676, 'loss/train': 2.164978504180908}
-03/04/2022 05:31:32 - INFO - codeparrot_training - Step 13677: {'lr': 0.0004923594570057972, 'samples': 7003136, 'steps': 13677, 'loss/train': 2.017721176147461}
-03/04/2022 05:31:32 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/04/2022 05:31:38 - INFO - codeparrot_training - Step 13678: {'lr': 0.0004923581550098733, 'samples': 7003648, 'steps': 13678, 'loss/train': 1.7709311246871948}
-03/04/2022 05:31:41 - INFO - codeparrot_training - Step 13679: {'lr': 0.0004923568529047466, 'samples': 7004160, 'steps': 13679, 'loss/train': 1.1077591180801392}
-03/04/2022 05:31:41 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/04/2022 05:31:46 - INFO - codeparrot_training - Step 13680: {'lr': 0.0004923555506904176, 'samples': 7004672, 'steps': 13680, 'loss/train': 2.9988324642181396}
-03/04/2022 05:31:49 - INFO - codeparrot_training - Step 13681: {'lr': 0.0004923542483668869, 'samples': 7005184, 'steps': 13681, 'loss/train': 1.6528286933898926}
-03/04/2022 05:31:50 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/04/2022 05:31:54 - INFO - codeparrot_training - Step 13682: {'lr': 0.0004923529459341553, 'samples': 7005696, 'steps': 13682, 'loss/train': 1.7451907396316528}
-03/04/2022 05:31:58 - INFO - codeparrot_training - Step 13683: {'lr': 0.000492351643392223, 'samples': 7006208, 'steps': 13683, 'loss/train': 1.6952463388442993}
-03/04/2022 05:32:03 - INFO - codeparrot_training - Step 13684: {'lr': 0.0004923503407410908, 'samples': 7006720, 'steps': 13684, 'loss/train': 2.4653160572052}
-03/04/2022 05:32:06 - INFO - codeparrot_training - Step 13685: {'lr': 0.0004923490379807594, 'samples': 7007232, 'steps': 13685, 'loss/train': 2.1022233963012695}
-03/04/2022 05:32:06 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/04/2022 05:32:11 - INFO - codeparrot_training - Step 13686: {'lr': 0.0004923477351112291, 'samples': 7007744, 'steps': 13686, 'loss/train': 1.238703727722168}
-03/04/2022 05:32:14 - INFO - codeparrot_training - Step 13687: {'lr': 0.0004923464321325008, 'samples': 7008256, 'steps': 13687, 'loss/train': 2.1372673511505127}
-03/04/2022 05:32:15 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 05:32:20 - INFO - codeparrot_training - Step 13688: {'lr': 0.0004923451290445749, 'samples': 7008768, 'steps': 13688, 'loss/train': 1.778368353843689}
-03/04/2022 05:32:23 - INFO - codeparrot_training - Step 13689: {'lr': 0.000492343825847452, 'samples': 7009280, 'steps': 13689, 'loss/train': 1.9421924352645874}
-03/04/2022 05:32:23 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/04/2022 05:32:28 - INFO - codeparrot_training - Step 13690: {'lr': 0.0004923425225411328, 'samples': 7009792, 'steps': 13690, 'loss/train': 2.077293634414673}
-03/04/2022 05:32:31 - INFO - codeparrot_training - Step 13691: {'lr': 0.0004923412191256176, 'samples': 7010304, 'steps': 13691, 'loss/train': 2.0436596870422363}
-03/04/2022 05:32:31 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/04/2022 05:32:36 - INFO - codeparrot_training - Step 13692: {'lr': 0.0004923399156009073, 'samples': 7010816, 'steps': 13692, 'loss/train': 1.2939774990081787}
-03/04/2022 05:32:39 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/04/2022 05:32:42 - INFO - codeparrot_training - Step 13693: {'lr': 0.0004923386119670024, 'samples': 7011328, 'steps': 13693, 'loss/train': 1.377705454826355}
-03/04/2022 05:32:45 - INFO - codeparrot_training - Step 13694: {'lr': 0.0004923373082239035, 'samples': 7011840, 'steps': 13694, 'loss/train': 1.606813907623291}
-03/04/2022 05:32:48 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/04/2022 05:32:51 - INFO - codeparrot_training - Step 13695: {'lr': 0.000492336004371611, 'samples': 7012352, 'steps': 13695, 'loss/train': 1.7375872135162354}
-03/04/2022 05:32:54 - INFO - codeparrot_training - Step 13696: {'lr': 0.0004923347004101257, 'samples': 7012864, 'steps': 13696, 'loss/train': 2.3808765411376953}
-03/04/2022 05:32:57 - INFO - codeparrot_training - Step 13697: {'lr': 0.0004923333963394482, 'samples': 7013376, 'steps': 13697, 'loss/train': 1.7773213386535645}
-03/04/2022 05:32:57 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/04/2022 05:33:02 - INFO - codeparrot_training - Step 13698: {'lr': 0.000492332092159579, 'samples': 7013888, 'steps': 13698, 'loss/train': 1.9305446147918701}
-03/04/2022 05:33:05 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 05:33:07 - INFO - codeparrot_training - Step 13699: {'lr': 0.0004923307878705186, 'samples': 7014400, 'steps': 13699, 'loss/train': 1.6196213960647583}
-03/04/2022 05:33:11 - INFO - codeparrot_training - Step 13700: {'lr': 0.0004923294834722678, 'samples': 7014912, 'steps': 13700, 'loss/train': 2.59881329536438}
-03/04/2022 05:33:13 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/04/2022 05:33:16 - INFO - codeparrot_training - Step 13701: {'lr': 0.000492328178964827, 'samples': 7015424, 'steps': 13701, 'loss/train': 1.955078363418579}
-03/04/2022 05:33:19 - INFO - codeparrot_training - Step 13702: {'lr': 0.0004923268743481969, 'samples': 7015936, 'steps': 13702, 'loss/train': 2.171308994293213}
-03/04/2022 05:33:22 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/04/2022 05:33:24 - INFO - codeparrot_training - Step 13703: {'lr': 0.000492325569622378, 'samples': 7016448, 'steps': 13703, 'loss/train': 1.1654374599456787}
-03/04/2022 05:33:28 - INFO - codeparrot_training - Step 13704: {'lr': 0.0004923242647873709, 'samples': 7016960, 'steps': 13704, 'loss/train': 1.3168948888778687}
-03/04/2022 05:33:31 - INFO - codeparrot_training - Step 13705: {'lr': 0.0004923229598431763, 'samples': 7017472, 'steps': 13705, 'loss/train': 1.5834335088729858}
-03/04/2022 05:33:31 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 05:33:36 - INFO - codeparrot_training - Step 13706: {'lr': 0.0004923216547897948, 'samples': 7017984, 'steps': 13706, 'loss/train': 2.6546428203582764}
-03/04/2022 05:33:39 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 05:33:41 - INFO - codeparrot_training - Step 13707: {'lr': 0.0004923203496272267, 'samples': 7018496, 'steps': 13707, 'loss/train': 2.1008973121643066}
-03/04/2022 05:33:45 - INFO - codeparrot_training - Step 13708: {'lr': 0.0004923190443554729, 'samples': 7019008, 'steps': 13708, 'loss/train': 0.7296139597892761}
-03/04/2022 05:33:47 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 05:33:50 - INFO - codeparrot_training - Step 13709: {'lr': 0.0004923177389745339, 'samples': 7019520, 'steps': 13709, 'loss/train': 1.771612524986267}
-03/04/2022 05:33:53 - INFO - codeparrot_training - Step 13710: {'lr': 0.0004923164334844103, 'samples': 7020032, 'steps': 13710, 'loss/train': 2.1677846908569336}
-03/04/2022 05:33:56 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 05:33:58 - INFO - codeparrot_training - Step 13711: {'lr': 0.0004923151278851025, 'samples': 7020544, 'steps': 13711, 'loss/train': 2.0312232971191406}
-03/04/2022 05:34:01 - INFO - codeparrot_training - Step 13712: {'lr': 0.0004923138221766114, 'samples': 7021056, 'steps': 13712, 'loss/train': 1.0519388914108276}
-03/04/2022 05:34:04 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/04/2022 05:34:07 - INFO - codeparrot_training - Step 13713: {'lr': 0.0004923125163589373, 'samples': 7021568, 'steps': 13713, 'loss/train': 1.8215103149414062}
-03/04/2022 05:34:10 - INFO - codeparrot_training - Step 13714: {'lr': 0.0004923112104320811, 'samples': 7022080, 'steps': 13714, 'loss/train': 2.89663028717041}
-03/04/2022 05:34:13 - INFO - codeparrot_training - Step 13715: {'lr': 0.000492309904396043, 'samples': 7022592, 'steps': 13715, 'loss/train': 1.7339508533477783}
-03/04/2022 05:34:13 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/04/2022 05:34:19 - INFO - codeparrot_training - Step 13716: {'lr': 0.0004923085982508239, 'samples': 7023104, 'steps': 13716, 'loss/train': 2.727125644683838}
-03/04/2022 05:34:21 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/04/2022 05:34:24 - INFO - codeparrot_training - Step 13717: {'lr': 0.0004923072919964243, 'samples': 7023616, 'steps': 13717, 'loss/train': 1.6222742795944214}
-03/04/2022 05:34:27 - INFO - codeparrot_training - Step 13718: {'lr': 0.0004923059856328447, 'samples': 7024128, 'steps': 13718, 'loss/train': 1.4606027603149414}
-03/04/2022 05:34:30 - INFO - codeparrot_training - Step 13719: {'lr': 0.0004923046791600859, 'samples': 7024640, 'steps': 13719, 'loss/train': 1.4888792037963867}
-03/04/2022 05:34:30 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 05:34:36 - INFO - codeparrot_training - Step 13720: {'lr': 0.0004923033725781482, 'samples': 7025152, 'steps': 13720, 'loss/train': 1.8522557020187378}
-03/04/2022 05:34:39 - INFO - codeparrot_training - Step 13721: {'lr': 0.0004923020658870324, 'samples': 7025664, 'steps': 13721, 'loss/train': 2.2643561363220215}
-03/04/2022 05:34:42 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/04/2022 05:34:45 - INFO - codeparrot_training - Step 13722: {'lr': 0.000492300759086739, 'samples': 7026176, 'steps': 13722, 'loss/train': 2.673191547393799}
-03/04/2022 05:34:48 - INFO - codeparrot_training - Step 13723: {'lr': 0.0004922994521772687, 'samples': 7026688, 'steps': 13723, 'loss/train': 2.460218667984009}
-03/04/2022 05:34:51 - INFO - codeparrot_training - Step 13724: {'lr': 0.000492298145158622, 'samples': 7027200, 'steps': 13724, 'loss/train': 1.7116565704345703}
-03/04/2022 05:34:51 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/04/2022 05:34:56 - INFO - codeparrot_training - Step 13725: {'lr': 0.0004922968380307994, 'samples': 7027712, 'steps': 13725, 'loss/train': 2.542766571044922}
-03/04/2022 05:35:00 - INFO - codeparrot_training - Step 13726: {'lr': 0.0004922955307938016, 'samples': 7028224, 'steps': 13726, 'loss/train': 2.123725652694702}
-03/04/2022 05:35:00 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 05:35:05 - INFO - codeparrot_training - Step 13727: {'lr': 0.0004922942234476292, 'samples': 7028736, 'steps': 13727, 'loss/train': 1.0970513820648193}
-03/04/2022 05:35:08 - INFO - codeparrot_training - Step 13728: {'lr': 0.0004922929159922828, 'samples': 7029248, 'steps': 13728, 'loss/train': 2.5990664958953857}
-03/04/2022 05:35:08 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/04/2022 05:35:13 - INFO - codeparrot_training - Step 13729: {'lr': 0.0004922916084277629, 'samples': 7029760, 'steps': 13729, 'loss/train': 1.987476110458374}
-03/04/2022 05:35:16 - INFO - codeparrot_training - Step 13730: {'lr': 0.0004922903007540701, 'samples': 7030272, 'steps': 13730, 'loss/train': 2.1737239360809326}
-03/04/2022 05:35:16 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/04/2022 05:35:22 - INFO - codeparrot_training - Step 13731: {'lr': 0.0004922889929712051, 'samples': 7030784, 'steps': 13731, 'loss/train': 2.4656002521514893}
-03/04/2022 05:35:25 - INFO - codeparrot_training - Step 13732: {'lr': 0.0004922876850791684, 'samples': 7031296, 'steps': 13732, 'loss/train': 1.991053819656372}
-03/04/2022 05:35:25 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/04/2022 05:35:30 - INFO - codeparrot_training - Step 13733: {'lr': 0.0004922863770779606, 'samples': 7031808, 'steps': 13733, 'loss/train': 1.910313606262207}
-03/04/2022 05:35:33 - INFO - codeparrot_training - Step 13734: {'lr': 0.0004922850689675823, 'samples': 7032320, 'steps': 13734, 'loss/train': 2.1331381797790527}
-03/04/2022 05:35:34 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/04/2022 05:35:39 - INFO - codeparrot_training - Step 13735: {'lr': 0.0004922837607480341, 'samples': 7032832, 'steps': 13735, 'loss/train': 2.2410054206848145}
-03/04/2022 05:35:42 - INFO - codeparrot_training - Step 13736: {'lr': 0.0004922824524193166, 'samples': 7033344, 'steps': 13736, 'loss/train': 1.8574775457382202}
-03/04/2022 05:35:42 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/04/2022 05:35:47 - INFO - codeparrot_training - Step 13737: {'lr': 0.0004922811439814303, 'samples': 7033856, 'steps': 13737, 'loss/train': 3.954754590988159}
-03/04/2022 05:35:51 - INFO - codeparrot_training - Step 13738: {'lr': 0.0004922798354343758, 'samples': 7034368, 'steps': 13738, 'loss/train': 2.4007251262664795}
-03/04/2022 05:35:52 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 05:35:56 - INFO - codeparrot_training - Step 13739: {'lr': 0.0004922785267781539, 'samples': 7034880, 'steps': 13739, 'loss/train': 1.5300596952438354}
-03/04/2022 05:35:59 - INFO - codeparrot_training - Step 13740: {'lr': 0.000492277218012765, 'samples': 7035392, 'steps': 13740, 'loss/train': 1.9363566637039185}
-03/04/2022 05:36:00 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/04/2022 05:36:04 - INFO - codeparrot_training - Step 13741: {'lr': 0.0004922759091382097, 'samples': 7035904, 'steps': 13741, 'loss/train': 2.433671712875366}
-03/04/2022 05:36:07 - INFO - codeparrot_training - Step 13742: {'lr': 0.0004922746001544885, 'samples': 7036416, 'steps': 13742, 'loss/train': 2.258741617202759}
-03/04/2022 05:36:09 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/04/2022 05:36:13 - INFO - codeparrot_training - Step 13743: {'lr': 0.0004922732910616023, 'samples': 7036928, 'steps': 13743, 'loss/train': 1.5411723852157593}
-03/04/2022 05:36:16 - INFO - codeparrot_training - Step 13744: {'lr': 0.0004922719818595514, 'samples': 7037440, 'steps': 13744, 'loss/train': 2.168130874633789}
-03/04/2022 05:36:17 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/04/2022 05:36:21 - INFO - codeparrot_training - Step 13745: {'lr': 0.0004922706725483364, 'samples': 7037952, 'steps': 13745, 'loss/train': 2.150653123855591}
-03/04/2022 05:36:24 - INFO - codeparrot_training - Step 13746: {'lr': 0.0004922693631279581, 'samples': 7038464, 'steps': 13746, 'loss/train': 1.846826434135437}
-03/04/2022 05:36:26 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 05:36:29 - INFO - codeparrot_training - Step 13747: {'lr': 0.000492268053598417, 'samples': 7038976, 'steps': 13747, 'loss/train': 1.8907181024551392}
-03/04/2022 05:36:33 - INFO - codeparrot_training - Step 13748: {'lr': 0.0004922667439597136, 'samples': 7039488, 'steps': 13748, 'loss/train': 1.8034273386001587}
-03/04/2022 05:36:34 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/04/2022 05:36:38 - INFO - codeparrot_training - Step 13749: {'lr': 0.0004922654342118484, 'samples': 7040000, 'steps': 13749, 'loss/train': 2.093733787536621}
-03/04/2022 05:36:41 - INFO - codeparrot_training - Step 13750: {'lr': 0.0004922641243548223, 'samples': 7040512, 'steps': 13750, 'loss/train': 1.3197438716888428}
-03/04/2022 05:36:42 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 05:36:46 - INFO - codeparrot_training - Step 13751: {'lr': 0.0004922628143886358, 'samples': 7041024, 'steps': 13751, 'loss/train': 1.5290896892547607}
-03/04/2022 05:36:50 - INFO - codeparrot_training - Step 13752: {'lr': 0.0004922615043132892, 'samples': 7041536, 'steps': 13752, 'loss/train': 2.090012788772583}
-03/04/2022 05:36:51 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 05:36:55 - INFO - codeparrot_training - Step 13753: {'lr': 0.0004922601941287835, 'samples': 7042048, 'steps': 13753, 'loss/train': 1.81102454662323}
-03/04/2022 05:36:58 - INFO - codeparrot_training - Step 13754: {'lr': 0.0004922588838351189, 'samples': 7042560, 'steps': 13754, 'loss/train': 1.8440344333648682}
-03/04/2022 05:36:59 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 05:37:03 - INFO - codeparrot_training - Step 13755: {'lr': 0.0004922575734322963, 'samples': 7043072, 'steps': 13755, 'loss/train': 2.32879376411438}
-03/04/2022 05:37:06 - INFO - codeparrot_training - Step 13756: {'lr': 0.0004922562629203161, 'samples': 7043584, 'steps': 13756, 'loss/train': 1.5566606521606445}
-03/04/2022 05:37:08 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 05:37:12 - INFO - codeparrot_training - Step 13757: {'lr': 0.0004922549522991791, 'samples': 7044096, 'steps': 13757, 'loss/train': 1.4942212104797363}
-03/04/2022 05:37:15 - INFO - codeparrot_training - Step 13758: {'lr': 0.0004922536415688856, 'samples': 7044608, 'steps': 13758, 'loss/train': 1.7564756870269775}
-03/04/2022 05:37:16 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/04/2022 05:37:20 - INFO - codeparrot_training - Step 13759: {'lr': 0.0004922523307294364, 'samples': 7045120, 'steps': 13759, 'loss/train': 1.3146753311157227}
-03/04/2022 05:37:23 - INFO - codeparrot_training - Step 13760: {'lr': 0.0004922510197808321, 'samples': 7045632, 'steps': 13760, 'loss/train': 3.1566147804260254}
-03/04/2022 05:37:24 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/04/2022 05:37:28 - INFO - codeparrot_training - Step 13761: {'lr': 0.0004922497087230732, 'samples': 7046144, 'steps': 13761, 'loss/train': 2.265101432800293}
-03/04/2022 05:37:32 - INFO - codeparrot_training - Step 13762: {'lr': 0.0004922483975561603, 'samples': 7046656, 'steps': 13762, 'loss/train': 2.1779379844665527}
-03/04/2022 05:37:33 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/04/2022 05:37:37 - INFO - codeparrot_training - Step 13763: {'lr': 0.000492247086280094, 'samples': 7047168, 'steps': 13763, 'loss/train': 2.024317979812622}
-03/04/2022 05:37:40 - INFO - codeparrot_training - Step 13764: {'lr': 0.0004922457748948749, 'samples': 7047680, 'steps': 13764, 'loss/train': 2.4135138988494873}
-03/04/2022 05:37:41 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/04/2022 05:37:45 - INFO - codeparrot_training - Step 13765: {'lr': 0.0004922444634005037, 'samples': 7048192, 'steps': 13765, 'loss/train': 1.85458505153656}
-03/04/2022 05:37:49 - INFO - codeparrot_training - Step 13766: {'lr': 0.0004922431517969808, 'samples': 7048704, 'steps': 13766, 'loss/train': 1.7893669605255127}
-03/04/2022 05:37:49 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 05:37:54 - INFO - codeparrot_training - Step 13767: {'lr': 0.0004922418400843068, 'samples': 7049216, 'steps': 13767, 'loss/train': 2.130017042160034}
-03/04/2022 05:37:57 - INFO - codeparrot_training - Step 13768: {'lr': 0.0004922405282624825, 'samples': 7049728, 'steps': 13768, 'loss/train': 1.5751020908355713}
-03/04/2022 05:37:57 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/04/2022 05:38:02 - INFO - codeparrot_training - Step 13769: {'lr': 0.0004922392163315083, 'samples': 7050240, 'steps': 13769, 'loss/train': 2.07431697845459}
-03/04/2022 05:38:05 - INFO - codeparrot_training - Step 13770: {'lr': 0.0004922379042913848, 'samples': 7050752, 'steps': 13770, 'loss/train': 1.6321134567260742}
-03/04/2022 05:38:06 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/04/2022 05:38:11 - INFO - codeparrot_training - Step 13771: {'lr': 0.0004922365921421126, 'samples': 7051264, 'steps': 13771, 'loss/train': 0.5383518934249878}
-03/04/2022 05:38:14 - INFO - codeparrot_training - Step 13772: {'lr': 0.0004922352798836924, 'samples': 7051776, 'steps': 13772, 'loss/train': 1.457706093788147}
-03/04/2022 05:38:14 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 05:38:19 - INFO - codeparrot_training - Step 13773: {'lr': 0.0004922339675161248, 'samples': 7052288, 'steps': 13773, 'loss/train': 2.0068092346191406}
-03/04/2022 05:38:22 - INFO - codeparrot_training - Step 13774: {'lr': 0.0004922326550394102, 'samples': 7052800, 'steps': 13774, 'loss/train': 1.682745099067688}
-03/04/2022 05:38:22 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/04/2022 05:38:27 - INFO - codeparrot_training - Step 13775: {'lr': 0.0004922313424535494, 'samples': 7053312, 'steps': 13775, 'loss/train': 1.9917305707931519}
-03/04/2022 05:38:30 - INFO - codeparrot_training - Step 13776: {'lr': 0.0004922300297585428, 'samples': 7053824, 'steps': 13776, 'loss/train': 1.5729330778121948}
-03/04/2022 05:38:31 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 05:38:36 - INFO - codeparrot_training - Step 13777: {'lr': 0.0004922287169543911, 'samples': 7054336, 'steps': 13777, 'loss/train': 1.9090073108673096}
-03/04/2022 05:38:39 - INFO - codeparrot_training - Step 13778: {'lr': 0.0004922274040410949, 'samples': 7054848, 'steps': 13778, 'loss/train': 1.760307788848877}
-03/04/2022 05:38:39 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/04/2022 05:38:44 - INFO - codeparrot_training - Step 13779: {'lr': 0.0004922260910186548, 'samples': 7055360, 'steps': 13779, 'loss/train': 1.6923671960830688}
-03/04/2022 05:38:47 - INFO - codeparrot_training - Step 13780: {'lr': 0.0004922247778870714, 'samples': 7055872, 'steps': 13780, 'loss/train': 2.840445041656494}
-03/04/2022 05:38:47 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/04/2022 05:38:53 - INFO - codeparrot_training - Step 13781: {'lr': 0.0004922234646463451, 'samples': 7056384, 'steps': 13781, 'loss/train': 2.051880121231079}
-03/04/2022 05:38:55 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 05:38:58 - INFO - codeparrot_training - Step 13782: {'lr': 0.0004922221512964767, 'samples': 7056896, 'steps': 13782, 'loss/train': 0.818953812122345}
-03/04/2022 05:39:01 - INFO - codeparrot_training - Step 13783: {'lr': 0.0004922208378374668, 'samples': 7057408, 'steps': 13783, 'loss/train': 1.0975111722946167}
-03/04/2022 05:39:04 - INFO - codeparrot_training - Step 13784: {'lr': 0.0004922195242693159, 'samples': 7057920, 'steps': 13784, 'loss/train': 2.4420621395111084}
-03/04/2022 05:39:04 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 05:39:09 - INFO - codeparrot_training - Step 13785: {'lr': 0.0004922182105920246, 'samples': 7058432, 'steps': 13785, 'loss/train': 0.6164647936820984}
-03/04/2022 05:39:12 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/04/2022 05:39:15 - INFO - codeparrot_training - Step 13786: {'lr': 0.0004922168968055935, 'samples': 7058944, 'steps': 13786, 'loss/train': 2.049877643585205}
-03/04/2022 05:39:18 - INFO - codeparrot_training - Step 13787: {'lr': 0.0004922155829100233, 'samples': 7059456, 'steps': 13787, 'loss/train': 1.1787705421447754}
-03/04/2022 05:39:20 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 05:39:23 - INFO - codeparrot_training - Step 13788: {'lr': 0.0004922142689053144, 'samples': 7059968, 'steps': 13788, 'loss/train': 2.3741793632507324}
-03/04/2022 05:39:26 - INFO - codeparrot_training - Step 13789: {'lr': 0.0004922129547914675, 'samples': 7060480, 'steps': 13789, 'loss/train': 2.3867530822753906}
-03/04/2022 05:39:29 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 05:39:32 - INFO - codeparrot_training - Step 13790: {'lr': 0.0004922116405684832, 'samples': 7060992, 'steps': 13790, 'loss/train': 1.4483634233474731}
-03/04/2022 05:39:35 - INFO - codeparrot_training - Step 13791: {'lr': 0.0004922103262363621, 'samples': 7061504, 'steps': 13791, 'loss/train': 2.3612256050109863}
-03/04/2022 05:39:38 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 05:39:40 - INFO - codeparrot_training - Step 13792: {'lr': 0.0004922090117951047, 'samples': 7062016, 'steps': 13792, 'loss/train': 1.6426775455474854}
-03/04/2022 05:39:43 - INFO - codeparrot_training - Step 13793: {'lr': 0.0004922076972447117, 'samples': 7062528, 'steps': 13793, 'loss/train': 2.3286550045013428}
-03/04/2022 05:39:46 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/04/2022 05:39:49 - INFO - codeparrot_training - Step 13794: {'lr': 0.0004922063825851836, 'samples': 7063040, 'steps': 13794, 'loss/train': 2.0031180381774902}
-03/04/2022 05:39:52 - INFO - codeparrot_training - Step 13795: {'lr': 0.0004922050678165211, 'samples': 7063552, 'steps': 13795, 'loss/train': 2.381171226501465}
-03/04/2022 05:39:55 - INFO - codeparrot_training - Step 13796: {'lr': 0.0004922037529387247, 'samples': 7064064, 'steps': 13796, 'loss/train': 1.4075833559036255}
-03/04/2022 05:39:55 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/04/2022 05:40:00 - INFO - codeparrot_training - Step 13797: {'lr': 0.000492202437951795, 'samples': 7064576, 'steps': 13797, 'loss/train': 1.9204422235488892}
-03/04/2022 05:40:03 - INFO - codeparrot_training - Step 13798: {'lr': 0.0004922011228557327, 'samples': 7065088, 'steps': 13798, 'loss/train': 2.531078577041626}
-03/04/2022 05:40:03 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/04/2022 05:40:08 - INFO - codeparrot_training - Step 13799: {'lr': 0.0004921998076505383, 'samples': 7065600, 'steps': 13799, 'loss/train': 2.274237632751465}
-03/04/2022 05:40:12 - INFO - codeparrot_training - Step 13800: {'lr': 0.0004921984923362124, 'samples': 7066112, 'steps': 13800, 'loss/train': 0.7893486618995667}
-03/04/2022 05:40:12 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/04/2022 05:40:17 - INFO - codeparrot_training - Step 13801: {'lr': 0.0004921971769127555, 'samples': 7066624, 'steps': 13801, 'loss/train': 1.5467408895492554}
-03/04/2022 05:40:20 - INFO - codeparrot_training - Step 13802: {'lr': 0.0004921958613801683, 'samples': 7067136, 'steps': 13802, 'loss/train': 1.5360370874404907}
-03/04/2022 05:40:20 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/04/2022 05:40:25 - INFO - codeparrot_training - Step 13803: {'lr': 0.0004921945457384516, 'samples': 7067648, 'steps': 13803, 'loss/train': 1.865400791168213}
-03/04/2022 05:40:28 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/04/2022 05:40:31 - INFO - codeparrot_training - Step 13804: {'lr': 0.0004921932299876055, 'samples': 7068160, 'steps': 13804, 'loss/train': 1.1733925342559814}
-03/04/2022 05:40:34 - INFO - codeparrot_training - Step 13805: {'lr': 0.000492191914127631, 'samples': 7068672, 'steps': 13805, 'loss/train': 1.4450894594192505}
-03/04/2022 05:40:36 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/04/2022 05:40:39 - INFO - codeparrot_training - Step 13806: {'lr': 0.0004921905981585286, 'samples': 7069184, 'steps': 13806, 'loss/train': 2.004146099090576}
-03/04/2022 05:40:42 - INFO - codeparrot_training - Step 13807: {'lr': 0.0004921892820802988, 'samples': 7069696, 'steps': 13807, 'loss/train': 1.9667387008666992}
-03/04/2022 05:40:47 - INFO - codeparrot_training - Step 13808: {'lr': 0.0004921879658929422, 'samples': 7070208, 'steps': 13808, 'loss/train': 1.6616489887237549}
-03/04/2022 05:40:50 - INFO - codeparrot_training - Step 13809: {'lr': 0.0004921866495964594, 'samples': 7070720, 'steps': 13809, 'loss/train': 1.2034920454025269}
-03/04/2022 05:40:53 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 05:40:56 - INFO - codeparrot_training - Step 13810: {'lr': 0.0004921853331908512, 'samples': 7071232, 'steps': 13810, 'loss/train': 1.245255708694458}
-03/04/2022 05:40:59 - INFO - codeparrot_training - Step 13811: {'lr': 0.000492184016676118, 'samples': 7071744, 'steps': 13811, 'loss/train': 1.7392985820770264}
-03/04/2022 05:41:01 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/04/2022 05:41:04 - INFO - codeparrot_training - Step 13812: {'lr': 0.0004921827000522603, 'samples': 7072256, 'steps': 13812, 'loss/train': 2.2761151790618896}
-03/04/2022 05:41:07 - INFO - codeparrot_training - Step 13813: {'lr': 0.0004921813833192788, 'samples': 7072768, 'steps': 13813, 'loss/train': 1.2025890350341797}
-03/04/2022 05:41:10 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/04/2022 05:41:13 - INFO - codeparrot_training - Step 13814: {'lr': 0.0004921800664771743, 'samples': 7073280, 'steps': 13814, 'loss/train': 2.002155303955078}
-03/04/2022 05:41:16 - INFO - codeparrot_training - Step 13815: {'lr': 0.0004921787495259471, 'samples': 7073792, 'steps': 13815, 'loss/train': 0.9399207234382629}
-03/04/2022 05:41:18 - INFO - codeparrot_training - Skipping example with length 996 (seq_length=1024)
-03/04/2022 05:41:21 - INFO - codeparrot_training - Step 13816: {'lr': 0.0004921774324655978, 'samples': 7074304, 'steps': 13816, 'loss/train': 1.6605106592178345}
-03/04/2022 05:41:24 - INFO - codeparrot_training - Step 13817: {'lr': 0.0004921761152961271, 'samples': 7074816, 'steps': 13817, 'loss/train': 2.375492811203003}
-03/04/2022 05:41:26 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 05:41:29 - INFO - codeparrot_training - Step 13818: {'lr': 0.0004921747980175357, 'samples': 7075328, 'steps': 13818, 'loss/train': 1.863887906074524}
-03/04/2022 05:41:32 - INFO - codeparrot_training - Step 13819: {'lr': 0.0004921734806298241, 'samples': 7075840, 'steps': 13819, 'loss/train': 2.3057823181152344}
-03/04/2022 05:41:34 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/04/2022 05:41:38 - INFO - codeparrot_training - Step 13820: {'lr': 0.0004921721631329927, 'samples': 7076352, 'steps': 13820, 'loss/train': 6.706635475158691}
-03/04/2022 05:41:41 - INFO - codeparrot_training - Step 13821: {'lr': 0.0004921708455270424, 'samples': 7076864, 'steps': 13821, 'loss/train': 2.3316869735717773}
-03/04/2022 05:41:44 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 05:41:46 - INFO - codeparrot_training - Step 13822: {'lr': 0.0004921695278119736, 'samples': 7077376, 'steps': 13822, 'loss/train': 2.328218698501587}
-03/04/2022 05:41:50 - INFO - codeparrot_training - Step 13823: {'lr': 0.0004921682099877869, 'samples': 7077888, 'steps': 13823, 'loss/train': 1.9240471124649048}
-03/04/2022 05:41:53 - INFO - codeparrot_training - Step 13824: {'lr': 0.000492166892054483, 'samples': 7078400, 'steps': 13824, 'loss/train': 1.588504433631897}
-03/04/2022 05:41:53 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 05:41:58 - INFO - codeparrot_training - Step 13825: {'lr': 0.0004921655740120623, 'samples': 7078912, 'steps': 13825, 'loss/train': 2.2063634395599365}
-03/04/2022 05:42:01 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/04/2022 05:42:03 - INFO - codeparrot_training - Step 13826: {'lr': 0.0004921642558605257, 'samples': 7079424, 'steps': 13826, 'loss/train': 2.506638526916504}
-03/04/2022 05:42:07 - INFO - codeparrot_training - Step 13827: {'lr': 0.0004921629375998736, 'samples': 7079936, 'steps': 13827, 'loss/train': 1.0995808839797974}
-03/04/2022 05:42:10 - INFO - codeparrot_training - Step 13828: {'lr': 0.0004921616192301065, 'samples': 7080448, 'steps': 13828, 'loss/train': 2.3207848072052}
-03/04/2022 05:42:10 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 05:42:15 - INFO - codeparrot_training - Step 13829: {'lr': 0.0004921603007512253, 'samples': 7080960, 'steps': 13829, 'loss/train': 2.0733141899108887}
-03/04/2022 05:42:18 - INFO - codeparrot_training - Step 13830: {'lr': 0.0004921589821632302, 'samples': 7081472, 'steps': 13830, 'loss/train': 1.927516222000122}
-03/04/2022 05:42:18 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/04/2022 05:42:24 - INFO - codeparrot_training - Step 13831: {'lr': 0.0004921576634661221, 'samples': 7081984, 'steps': 13831, 'loss/train': 2.0424108505249023}
-03/04/2022 05:42:26 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 05:42:29 - INFO - codeparrot_training - Step 13832: {'lr': 0.0004921563446599015, 'samples': 7082496, 'steps': 13832, 'loss/train': 1.653813362121582}
-03/04/2022 05:42:32 - INFO - codeparrot_training - Step 13833: {'lr': 0.000492155025744569, 'samples': 7083008, 'steps': 13833, 'loss/train': 2.27618408203125}
-03/04/2022 05:42:35 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 05:42:37 - INFO - codeparrot_training - Step 13834: {'lr': 0.0004921537067201252, 'samples': 7083520, 'steps': 13834, 'loss/train': 1.6876907348632812}
-03/04/2022 05:42:40 - INFO - codeparrot_training - Step 13835: {'lr': 0.0004921523875865706, 'samples': 7084032, 'steps': 13835, 'loss/train': 2.6345391273498535}
-03/04/2022 05:42:43 - INFO - codeparrot_training - Step 13836: {'lr': 0.000492151068343906, 'samples': 7084544, 'steps': 13836, 'loss/train': 1.9526569843292236}
-03/04/2022 05:42:43 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/04/2022 05:42:49 - INFO - codeparrot_training - Step 13837: {'lr': 0.0004921497489921318, 'samples': 7085056, 'steps': 13837, 'loss/train': 2.8377845287323}
-03/04/2022 05:42:52 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/04/2022 05:42:54 - INFO - codeparrot_training - Step 13838: {'lr': 0.0004921484295312485, 'samples': 7085568, 'steps': 13838, 'loss/train': 1.777223825454712}
-03/04/2022 05:42:57 - INFO - codeparrot_training - Step 13839: {'lr': 0.0004921471099612571, 'samples': 7086080, 'steps': 13839, 'loss/train': 0.38702282309532166}
-03/04/2022 05:43:00 - INFO - codeparrot_training - Step 13840: {'lr': 0.0004921457902821578, 'samples': 7086592, 'steps': 13840, 'loss/train': 1.706692099571228}
-03/04/2022 05:43:00 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/04/2022 05:43:06 - INFO - codeparrot_training - Step 13841: {'lr': 0.0004921444704939514, 'samples': 7087104, 'steps': 13841, 'loss/train': 1.4635167121887207}
-03/04/2022 05:43:09 - INFO - codeparrot_training - Step 13842: {'lr': 0.0004921431505966384, 'samples': 7087616, 'steps': 13842, 'loss/train': 1.0871002674102783}
-03/04/2022 05:43:09 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/04/2022 05:43:14 - INFO - codeparrot_training - Step 13843: {'lr': 0.0004921418305902194, 'samples': 7088128, 'steps': 13843, 'loss/train': 1.7205017805099487}
-03/04/2022 05:43:17 - INFO - codeparrot_training - Step 13844: {'lr': 0.0004921405104746951, 'samples': 7088640, 'steps': 13844, 'loss/train': 1.8003944158554077}
-03/04/2022 05:43:17 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/04/2022 05:43:23 - INFO - codeparrot_training - Step 13845: {'lr': 0.0004921391902500661, 'samples': 7089152, 'steps': 13845, 'loss/train': 1.3729408979415894}
-03/04/2022 05:43:25 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/04/2022 05:43:28 - INFO - codeparrot_training - Step 13846: {'lr': 0.0004921378699163328, 'samples': 7089664, 'steps': 13846, 'loss/train': 1.7800675630569458}
-03/04/2022 05:43:31 - INFO - codeparrot_training - Step 13847: {'lr': 0.0004921365494734959, 'samples': 7090176, 'steps': 13847, 'loss/train': 1.508734941482544}
-03/04/2022 05:43:34 - INFO - codeparrot_training - Step 13848: {'lr': 0.0004921352289215561, 'samples': 7090688, 'steps': 13848, 'loss/train': 2.0013065338134766}
-03/04/2022 05:43:34 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/04/2022 05:43:40 - INFO - codeparrot_training - Step 13849: {'lr': 0.0004921339082605137, 'samples': 7091200, 'steps': 13849, 'loss/train': 1.5000802278518677}
-03/04/2022 05:43:43 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 05:43:45 - INFO - codeparrot_training - Step 13850: {'lr': 0.0004921325874903697, 'samples': 7091712, 'steps': 13850, 'loss/train': 1.3020309209823608}
-03/04/2022 05:43:48 - INFO - codeparrot_training - Step 13851: {'lr': 0.0004921312666111245, 'samples': 7092224, 'steps': 13851, 'loss/train': 1.38003671169281}
-03/04/2022 05:43:51 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/04/2022 05:43:53 - INFO - codeparrot_training - Step 13852: {'lr': 0.0004921299456227785, 'samples': 7092736, 'steps': 13852, 'loss/train': 2.127854108810425}
-03/04/2022 05:43:57 - INFO - codeparrot_training - Step 13853: {'lr': 0.0004921286245253327, 'samples': 7093248, 'steps': 13853, 'loss/train': 2.3068461418151855}
-03/04/2022 05:43:59 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/04/2022 05:44:02 - INFO - codeparrot_training - Step 13854: {'lr': 0.0004921273033187874, 'samples': 7093760, 'steps': 13854, 'loss/train': 2.1664419174194336}
-03/04/2022 05:44:05 - INFO - codeparrot_training - Step 13855: {'lr': 0.0004921259820031431, 'samples': 7094272, 'steps': 13855, 'loss/train': 1.5732530355453491}
-03/04/2022 05:44:08 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 05:44:11 - INFO - codeparrot_training - Step 13856: {'lr': 0.0004921246605784008, 'samples': 7094784, 'steps': 13856, 'loss/train': 2.6420533657073975}
-03/04/2022 05:44:14 - INFO - codeparrot_training - Step 13857: {'lr': 0.0004921233390445608, 'samples': 7095296, 'steps': 13857, 'loss/train': 2.3059651851654053}
-03/04/2022 05:44:16 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/04/2022 05:44:19 - INFO - codeparrot_training - Step 13858: {'lr': 0.0004921220174016238, 'samples': 7095808, 'steps': 13858, 'loss/train': 1.173789620399475}
-03/04/2022 05:44:22 - INFO - codeparrot_training - Step 13859: {'lr': 0.0004921206956495903, 'samples': 7096320, 'steps': 13859, 'loss/train': 1.9339733123779297}
-03/04/2022 05:44:25 - INFO - codeparrot_training - Step 13860: {'lr': 0.000492119373788461, 'samples': 7096832, 'steps': 13860, 'loss/train': 1.5416935682296753}
-03/04/2022 05:44:25 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/04/2022 05:44:31 - INFO - codeparrot_training - Step 13861: {'lr': 0.0004921180518182363, 'samples': 7097344, 'steps': 13861, 'loss/train': 2.0088181495666504}
-03/04/2022 05:44:34 - INFO - codeparrot_training - Step 13862: {'lr': 0.0004921167297389171, 'samples': 7097856, 'steps': 13862, 'loss/train': 2.3566389083862305}
-03/04/2022 05:44:34 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/04/2022 05:44:39 - INFO - codeparrot_training - Step 13863: {'lr': 0.0004921154075505038, 'samples': 7098368, 'steps': 13863, 'loss/train': 1.5766892433166504}
-03/04/2022 05:44:42 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 05:44:44 - INFO - codeparrot_training - Step 13864: {'lr': 0.0004921140852529969, 'samples': 7098880, 'steps': 13864, 'loss/train': 2.3183646202087402}
-03/04/2022 05:44:48 - INFO - codeparrot_training - Step 13865: {'lr': 0.0004921127628463972, 'samples': 7099392, 'steps': 13865, 'loss/train': 1.6249338388442993}
-03/04/2022 05:44:50 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/04/2022 05:44:53 - INFO - codeparrot_training - Step 13866: {'lr': 0.0004921114403307053, 'samples': 7099904, 'steps': 13866, 'loss/train': 2.0201940536499023}
-03/04/2022 05:44:56 - INFO - codeparrot_training - Step 13867: {'lr': 0.0004921101177059218, 'samples': 7100416, 'steps': 13867, 'loss/train': 1.921600103378296}
-03/04/2022 05:44:59 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/04/2022 05:45:01 - INFO - codeparrot_training - Step 13868: {'lr': 0.0004921087949720471, 'samples': 7100928, 'steps': 13868, 'loss/train': 1.0248303413391113}
-03/04/2022 05:45:04 - INFO - codeparrot_training - Step 13869: {'lr': 0.0004921074721290819, 'samples': 7101440, 'steps': 13869, 'loss/train': 2.1942384243011475}
-03/04/2022 05:45:07 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/04/2022 05:45:10 - INFO - codeparrot_training - Step 13870: {'lr': 0.0004921061491770268, 'samples': 7101952, 'steps': 13870, 'loss/train': 2.237002372741699}
-03/04/2022 05:45:13 - INFO - codeparrot_training - Step 13871: {'lr': 0.0004921048261158825, 'samples': 7102464, 'steps': 13871, 'loss/train': 1.0420719385147095}
-03/04/2022 05:45:16 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/04/2022 05:45:18 - INFO - codeparrot_training - Step 13872: {'lr': 0.0004921035029456493, 'samples': 7102976, 'steps': 13872, 'loss/train': 2.193112373352051}
-03/04/2022 05:45:21 - INFO - codeparrot_training - Step 13873: {'lr': 0.0004921021796663282, 'samples': 7103488, 'steps': 13873, 'loss/train': 2.121328115463257}
-03/04/2022 05:45:25 - INFO - codeparrot_training - Step 13874: {'lr': 0.0004921008562779195, 'samples': 7104000, 'steps': 13874, 'loss/train': 6.635128021240234}
-03/04/2022 05:45:30 - INFO - codeparrot_training - Step 13875: {'lr': 0.0004920995327804239, 'samples': 7104512, 'steps': 13875, 'loss/train': 1.8228464126586914}
-03/04/2022 05:45:33 - INFO - codeparrot_training - Step 13876: {'lr': 0.000492098209173842, 'samples': 7105024, 'steps': 13876, 'loss/train': 1.2901074886322021}
-03/04/2022 05:45:34 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/04/2022 05:45:38 - INFO - codeparrot_training - Step 13877: {'lr': 0.0004920968854581745, 'samples': 7105536, 'steps': 13877, 'loss/train': 2.237931728363037}
-03/04/2022 05:45:42 - INFO - codeparrot_training - Step 13878: {'lr': 0.0004920955616334216, 'samples': 7106048, 'steps': 13878, 'loss/train': 2.097480297088623}
-03/04/2022 05:45:43 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/04/2022 05:45:47 - INFO - codeparrot_training - Step 13879: {'lr': 0.0004920942376995844, 'samples': 7106560, 'steps': 13879, 'loss/train': 2.555480718612671}
-03/04/2022 05:45:50 - INFO - codeparrot_training - Step 13880: {'lr': 0.0004920929136566632, 'samples': 7107072, 'steps': 13880, 'loss/train': 1.999619722366333}
-03/04/2022 05:45:52 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/04/2022 05:45:56 - INFO - codeparrot_training - Step 13881: {'lr': 0.0004920915895046587, 'samples': 7107584, 'steps': 13881, 'loss/train': 1.2324823141098022}
-03/04/2022 05:45:59 - INFO - codeparrot_training - Step 13882: {'lr': 0.0004920902652435715, 'samples': 7108096, 'steps': 13882, 'loss/train': 2.818128824234009}
-03/04/2022 05:46:01 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/04/2022 05:46:04 - INFO - codeparrot_training - Step 13883: {'lr': 0.0004920889408734021, 'samples': 7108608, 'steps': 13883, 'loss/train': 2.1015212535858154}
-03/04/2022 05:46:07 - INFO - codeparrot_training - Step 13884: {'lr': 0.0004920876163941511, 'samples': 7109120, 'steps': 13884, 'loss/train': 1.929923415184021}
-03/04/2022 05:46:09 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/04/2022 05:46:13 - INFO - codeparrot_training - Step 13885: {'lr': 0.0004920862918058192, 'samples': 7109632, 'steps': 13885, 'loss/train': 2.3912131786346436}
-03/04/2022 05:46:16 - INFO - codeparrot_training - Step 13886: {'lr': 0.000492084967108407, 'samples': 7110144, 'steps': 13886, 'loss/train': 0.812364399433136}
-03/04/2022 05:46:18 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/04/2022 05:46:21 - INFO - codeparrot_training - Step 13887: {'lr': 0.000492083642301915, 'samples': 7110656, 'steps': 13887, 'loss/train': 1.8444164991378784}
-03/04/2022 05:46:24 - INFO - codeparrot_training - Step 13888: {'lr': 0.0004920823173863439, 'samples': 7111168, 'steps': 13888, 'loss/train': 1.8949565887451172}
-03/04/2022 05:46:26 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 05:46:29 - INFO - codeparrot_training - Step 13889: {'lr': 0.0004920809923616942, 'samples': 7111680, 'steps': 13889, 'loss/train': 2.3655784130096436}
-03/04/2022 05:46:33 - INFO - codeparrot_training - Step 13890: {'lr': 0.0004920796672279666, 'samples': 7112192, 'steps': 13890, 'loss/train': 2.5036697387695312}
-03/04/2022 05:46:34 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/04/2022 05:46:38 - INFO - codeparrot_training - Step 13891: {'lr': 0.0004920783419851615, 'samples': 7112704, 'steps': 13891, 'loss/train': 2.140683650970459}
-03/04/2022 05:46:41 - INFO - codeparrot_training - Step 13892: {'lr': 0.0004920770166332798, 'samples': 7113216, 'steps': 13892, 'loss/train': 1.6183316707611084}
-03/04/2022 05:46:42 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/04/2022 05:46:46 - INFO - codeparrot_training - Step 13893: {'lr': 0.0004920756911723219, 'samples': 7113728, 'steps': 13893, 'loss/train': 1.0210148096084595}
-03/04/2022 05:46:49 - INFO - codeparrot_training - Step 13894: {'lr': 0.0004920743656022884, 'samples': 7114240, 'steps': 13894, 'loss/train': 2.059379816055298}
-03/04/2022 05:46:51 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/04/2022 05:46:55 - INFO - codeparrot_training - Step 13895: {'lr': 0.0004920730399231799, 'samples': 7114752, 'steps': 13895, 'loss/train': 1.9587607383728027}
-03/04/2022 05:46:58 - INFO - codeparrot_training - Step 13896: {'lr': 0.000492071714134997, 'samples': 7115264, 'steps': 13896, 'loss/train': 2.3177950382232666}
-03/04/2022 05:47:03 - INFO - codeparrot_training - Step 13897: {'lr': 0.0004920703882377403, 'samples': 7115776, 'steps': 13897, 'loss/train': 1.8285906314849854}
-03/04/2022 05:47:07 - INFO - codeparrot_training - Step 13898: {'lr': 0.0004920690622314105, 'samples': 7116288, 'steps': 13898, 'loss/train': 2.07369065284729}
-03/04/2022 05:47:10 - INFO - codeparrot_training - Step 13899: {'lr': 0.0004920677361160081, 'samples': 7116800, 'steps': 13899, 'loss/train': 1.4604885578155518}
-03/04/2022 05:47:10 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/04/2022 05:47:15 - INFO - codeparrot_training - Step 13900: {'lr': 0.0004920664098915337, 'samples': 7117312, 'steps': 13900, 'loss/train': 2.8327829837799072}
-03/04/2022 05:47:18 - INFO - codeparrot_training - Step 13901: {'lr': 0.000492065083557988, 'samples': 7117824, 'steps': 13901, 'loss/train': 1.2991677522659302}
-03/04/2022 05:47:18 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 05:47:24 - INFO - codeparrot_training - Step 13902: {'lr': 0.0004920637571153713, 'samples': 7118336, 'steps': 13902, 'loss/train': 1.3735127449035645}
-03/04/2022 05:47:27 - INFO - codeparrot_training - Step 13903: {'lr': 0.0004920624305636846, 'samples': 7118848, 'steps': 13903, 'loss/train': 2.475213050842285}
-03/04/2022 05:47:27 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/04/2022 05:47:32 - INFO - codeparrot_training - Step 13904: {'lr': 0.0004920611039029283, 'samples': 7119360, 'steps': 13904, 'loss/train': 3.0299201011657715}
-03/04/2022 05:47:35 - INFO - codeparrot_training - Step 13905: {'lr': 0.0004920597771331029, 'samples': 7119872, 'steps': 13905, 'loss/train': 1.606934905052185}
-03/04/2022 05:47:35 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 05:47:41 - INFO - codeparrot_training - Step 13906: {'lr': 0.0004920584502542091, 'samples': 7120384, 'steps': 13906, 'loss/train': 2.0838353633880615}
-03/04/2022 05:47:44 - INFO - codeparrot_training - Step 13907: {'lr': 0.0004920571232662475, 'samples': 7120896, 'steps': 13907, 'loss/train': 2.5342671871185303}
-03/04/2022 05:47:45 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/04/2022 05:47:49 - INFO - codeparrot_training - Step 13908: {'lr': 0.0004920557961692188, 'samples': 7121408, 'steps': 13908, 'loss/train': 0.9780105352401733}
-03/04/2022 05:47:52 - INFO - codeparrot_training - Step 13909: {'lr': 0.0004920544689631233, 'samples': 7121920, 'steps': 13909, 'loss/train': 2.1340739727020264}
-03/04/2022 05:47:53 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 05:47:58 - INFO - codeparrot_training - Step 13910: {'lr': 0.000492053141647962, 'samples': 7122432, 'steps': 13910, 'loss/train': 1.2010740041732788}
-03/04/2022 05:48:01 - INFO - codeparrot_training - Step 13911: {'lr': 0.0004920518142237352, 'samples': 7122944, 'steps': 13911, 'loss/train': 1.5362221002578735}
-03/04/2022 05:48:01 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 05:48:06 - INFO - codeparrot_training - Step 13912: {'lr': 0.0004920504866904436, 'samples': 7123456, 'steps': 13912, 'loss/train': 2.202838897705078}
-03/04/2022 05:48:09 - INFO - codeparrot_training - Step 13913: {'lr': 0.0004920491590480878, 'samples': 7123968, 'steps': 13913, 'loss/train': 2.5388736724853516}
-03/04/2022 05:48:10 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/04/2022 05:48:14 - INFO - codeparrot_training - Step 13914: {'lr': 0.0004920478312966683, 'samples': 7124480, 'steps': 13914, 'loss/train': 2.099266529083252}
-03/04/2022 05:48:17 - INFO - codeparrot_training - Step 13915: {'lr': 0.0004920465034361859, 'samples': 7124992, 'steps': 13915, 'loss/train': 1.7619258165359497}
-03/04/2022 05:48:18 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 05:48:23 - INFO - codeparrot_training - Step 13916: {'lr': 0.000492045175466641, 'samples': 7125504, 'steps': 13916, 'loss/train': 2.0869882106781006}
-03/04/2022 05:48:26 - INFO - codeparrot_training - Step 13917: {'lr': 0.0004920438473880344, 'samples': 7126016, 'steps': 13917, 'loss/train': 1.6799697875976562}
-03/04/2022 05:48:26 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 05:48:31 - INFO - codeparrot_training - Step 13918: {'lr': 0.0004920425192003663, 'samples': 7126528, 'steps': 13918, 'loss/train': 1.5521717071533203}
-03/04/2022 05:48:34 - INFO - codeparrot_training - Step 13919: {'lr': 0.0004920411909036379, 'samples': 7127040, 'steps': 13919, 'loss/train': 1.9308875799179077}
-03/04/2022 05:48:34 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 05:48:39 - INFO - codeparrot_training - Step 13920: {'lr': 0.0004920398624978493, 'samples': 7127552, 'steps': 13920, 'loss/train': 2.3379929065704346}
-03/04/2022 05:48:43 - INFO - codeparrot_training - Step 13921: {'lr': 0.0004920385339830012, 'samples': 7128064, 'steps': 13921, 'loss/train': 2.4879884719848633}
-03/04/2022 05:48:43 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/04/2022 05:48:48 - INFO - codeparrot_training - Step 13922: {'lr': 0.0004920372053590945, 'samples': 7128576, 'steps': 13922, 'loss/train': 3.004866361618042}
-03/04/2022 05:48:51 - INFO - codeparrot_training - Step 13923: {'lr': 0.0004920358766261294, 'samples': 7129088, 'steps': 13923, 'loss/train': 2.3878026008605957}
-03/04/2022 05:48:51 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/04/2022 05:48:57 - INFO - codeparrot_training - Step 13924: {'lr': 0.0004920345477841067, 'samples': 7129600, 'steps': 13924, 'loss/train': 1.8098949193954468}
-03/04/2022 05:49:00 - INFO - codeparrot_training - Step 13925: {'lr': 0.000492033218833027, 'samples': 7130112, 'steps': 13925, 'loss/train': 0.2654152512550354}
-03/04/2022 05:49:00 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/04/2022 05:49:05 - INFO - codeparrot_training - Step 13926: {'lr': 0.0004920318897728909, 'samples': 7130624, 'steps': 13926, 'loss/train': 5.15228271484375}
-03/04/2022 05:49:08 - INFO - codeparrot_training - Step 13927: {'lr': 0.0004920305606036988, 'samples': 7131136, 'steps': 13927, 'loss/train': 2.644486427307129}
-03/04/2022 05:49:08 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 05:49:13 - INFO - codeparrot_training - Step 13928: {'lr': 0.0004920292313254516, 'samples': 7131648, 'steps': 13928, 'loss/train': 2.088285446166992}
-03/04/2022 05:49:17 - INFO - codeparrot_training - Step 13929: {'lr': 0.0004920279019381497, 'samples': 7132160, 'steps': 13929, 'loss/train': 1.924926996231079}
-03/04/2022 05:49:17 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 05:49:22 - INFO - codeparrot_training - Step 13930: {'lr': 0.0004920265724417938, 'samples': 7132672, 'steps': 13930, 'loss/train': 1.2212401628494263}
-03/04/2022 05:49:25 - INFO - codeparrot_training - Step 13931: {'lr': 0.0004920252428363845, 'samples': 7133184, 'steps': 13931, 'loss/train': 2.1055896282196045}
-03/04/2022 05:49:25 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/04/2022 05:49:30 - INFO - codeparrot_training - Step 13932: {'lr': 0.0004920239131219223, 'samples': 7133696, 'steps': 13932, 'loss/train': 2.1152336597442627}
-03/04/2022 05:49:33 - INFO - codeparrot_training - Step 13933: {'lr': 0.0004920225832984079, 'samples': 7134208, 'steps': 13933, 'loss/train': 1.9696638584136963}
-03/04/2022 05:49:33 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 05:49:38 - INFO - codeparrot_training - Step 13934: {'lr': 0.0004920212533658419, 'samples': 7134720, 'steps': 13934, 'loss/train': 2.2886734008789062}
-03/04/2022 05:49:42 - INFO - codeparrot_training - Step 13935: {'lr': 0.0004920199233242247, 'samples': 7135232, 'steps': 13935, 'loss/train': 2.0676329135894775}
-03/04/2022 05:49:42 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/04/2022 05:49:47 - INFO - codeparrot_training - Step 13936: {'lr': 0.0004920185931735572, 'samples': 7135744, 'steps': 13936, 'loss/train': 2.0155959129333496}
-03/04/2022 05:49:50 - INFO - codeparrot_training - Step 13937: {'lr': 0.0004920172629138399, 'samples': 7136256, 'steps': 13937, 'loss/train': 2.1086642742156982}
-03/04/2022 05:49:50 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/04/2022 05:49:55 - INFO - codeparrot_training - Step 13938: {'lr': 0.0004920159325450731, 'samples': 7136768, 'steps': 13938, 'loss/train': 1.7148977518081665}
-03/04/2022 05:49:58 - INFO - codeparrot_training - Step 13939: {'lr': 0.0004920146020672578, 'samples': 7137280, 'steps': 13939, 'loss/train': 1.2497236728668213}
-03/04/2022 05:49:58 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 05:50:04 - INFO - codeparrot_training - Step 13940: {'lr': 0.0004920132714803946, 'samples': 7137792, 'steps': 13940, 'loss/train': 1.785296082496643}
-03/04/2022 05:50:06 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 05:50:09 - INFO - codeparrot_training - Step 13941: {'lr': 0.0004920119407844838, 'samples': 7138304, 'steps': 13941, 'loss/train': 2.3904848098754883}
-03/04/2022 05:50:12 - INFO - codeparrot_training - Step 13942: {'lr': 0.0004920106099795262, 'samples': 7138816, 'steps': 13942, 'loss/train': 2.0314736366271973}
-03/04/2022 05:50:15 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 05:50:17 - INFO - codeparrot_training - Step 13943: {'lr': 0.0004920092790655224, 'samples': 7139328, 'steps': 13943, 'loss/train': 1.3853546380996704}
-03/04/2022 05:50:20 - INFO - codeparrot_training - Step 13944: {'lr': 0.0004920079480424728, 'samples': 7139840, 'steps': 13944, 'loss/train': 2.978848934173584}
-03/04/2022 05:50:23 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/04/2022 05:50:26 - INFO - codeparrot_training - Step 13945: {'lr': 0.0004920066169103783, 'samples': 7140352, 'steps': 13945, 'loss/train': 2.2305729389190674}
-03/04/2022 05:50:29 - INFO - codeparrot_training - Step 13946: {'lr': 0.0004920052856692394, 'samples': 7140864, 'steps': 13946, 'loss/train': 1.7851394414901733}
-03/04/2022 05:50:32 - INFO - codeparrot_training - Step 13947: {'lr': 0.0004920039543190565, 'samples': 7141376, 'steps': 13947, 'loss/train': 1.7024136781692505}
-03/04/2022 05:50:32 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/04/2022 05:50:37 - INFO - codeparrot_training - Step 13948: {'lr': 0.0004920026228598303, 'samples': 7141888, 'steps': 13948, 'loss/train': 2.0784802436828613}
-03/04/2022 05:50:40 - INFO - codeparrot_training - Step 13949: {'lr': 0.0004920012912915616, 'samples': 7142400, 'steps': 13949, 'loss/train': 1.5339996814727783}
-03/04/2022 05:50:40 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/04/2022 05:50:45 - INFO - codeparrot_training - Step 13950: {'lr': 0.0004919999596142508, 'samples': 7142912, 'steps': 13950, 'loss/train': 1.9049612283706665}
-03/04/2022 05:50:49 - INFO - codeparrot_training - Step 13951: {'lr': 0.0004919986278278986, 'samples': 7143424, 'steps': 13951, 'loss/train': 1.7781169414520264}
-03/04/2022 05:50:49 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 05:50:54 - INFO - codeparrot_training - Step 13952: {'lr': 0.0004919972959325055, 'samples': 7143936, 'steps': 13952, 'loss/train': 1.2177876234054565}
-03/04/2022 05:50:57 - INFO - codeparrot_training - Step 13953: {'lr': 0.0004919959639280722, 'samples': 7144448, 'steps': 13953, 'loss/train': 2.4373157024383545}
-03/04/2022 05:50:57 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 05:51:02 - INFO - codeparrot_training - Step 13954: {'lr': 0.0004919946318145992, 'samples': 7144960, 'steps': 13954, 'loss/train': 1.9082763195037842}
-03/04/2022 05:51:06 - INFO - codeparrot_training - Step 13955: {'lr': 0.0004919932995920872, 'samples': 7145472, 'steps': 13955, 'loss/train': 2.6807849407196045}
-03/04/2022 05:51:06 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/04/2022 05:51:11 - INFO - codeparrot_training - Step 13956: {'lr': 0.0004919919672605366, 'samples': 7145984, 'steps': 13956, 'loss/train': 1.6824249029159546}
-03/04/2022 05:51:14 - INFO - codeparrot_training - Step 13957: {'lr': 0.0004919906348199483, 'samples': 7146496, 'steps': 13957, 'loss/train': 1.4683411121368408}
-03/04/2022 05:51:14 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/04/2022 05:51:20 - INFO - codeparrot_training - Step 13958: {'lr': 0.0004919893022703228, 'samples': 7147008, 'steps': 13958, 'loss/train': 2.334958553314209}
-03/04/2022 05:51:23 - INFO - codeparrot_training - Step 13959: {'lr': 0.0004919879696116605, 'samples': 7147520, 'steps': 13959, 'loss/train': 0.8585454225540161}
-03/04/2022 05:51:24 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 05:51:28 - INFO - codeparrot_training - Step 13960: {'lr': 0.0004919866368439624, 'samples': 7148032, 'steps': 13960, 'loss/train': 3.3964898586273193}
-03/04/2022 05:51:31 - INFO - codeparrot_training - Step 13961: {'lr': 0.0004919853039672287, 'samples': 7148544, 'steps': 13961, 'loss/train': 1.97477126121521}
-03/04/2022 05:51:32 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/04/2022 05:51:37 - INFO - codeparrot_training - Step 13962: {'lr': 0.00049198397098146, 'samples': 7149056, 'steps': 13962, 'loss/train': 2.0126211643218994}
-03/04/2022 05:51:40 - INFO - codeparrot_training - Step 13963: {'lr': 0.0004919826378866573, 'samples': 7149568, 'steps': 13963, 'loss/train': 2.1873202323913574}
-03/04/2022 05:51:41 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 05:51:45 - INFO - codeparrot_training - Step 13964: {'lr': 0.0004919813046828209, 'samples': 7150080, 'steps': 13964, 'loss/train': 2.0261824131011963}
-03/04/2022 05:51:48 - INFO - codeparrot_training - Step 13965: {'lr': 0.0004919799713699514, 'samples': 7150592, 'steps': 13965, 'loss/train': 4.201659202575684}
-03/04/2022 05:51:49 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/04/2022 05:51:54 - INFO - codeparrot_training - Step 13966: {'lr': 0.0004919786379480494, 'samples': 7151104, 'steps': 13966, 'loss/train': 1.6815226078033447}
-03/04/2022 05:51:57 - INFO - codeparrot_training - Step 13967: {'lr': 0.0004919773044171158, 'samples': 7151616, 'steps': 13967, 'loss/train': 2.084561586380005}
-03/04/2022 05:51:58 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/04/2022 05:52:02 - INFO - codeparrot_training - Step 13968: {'lr': 0.0004919759707771507, 'samples': 7152128, 'steps': 13968, 'loss/train': 1.970318078994751}
-03/04/2022 05:52:05 - INFO - codeparrot_training - Step 13969: {'lr': 0.0004919746370281551, 'samples': 7152640, 'steps': 13969, 'loss/train': 2.1815624237060547}
-03/04/2022 05:52:06 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 05:52:10 - INFO - codeparrot_training - Step 13970: {'lr': 0.0004919733031701295, 'samples': 7153152, 'steps': 13970, 'loss/train': 2.034651041030884}
-03/04/2022 05:52:14 - INFO - codeparrot_training - Step 13971: {'lr': 0.0004919719692030743, 'samples': 7153664, 'steps': 13971, 'loss/train': 1.5955557823181152}
-03/04/2022 05:52:15 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/04/2022 05:52:19 - INFO - codeparrot_training - Step 13972: {'lr': 0.0004919706351269904, 'samples': 7154176, 'steps': 13972, 'loss/train': 2.1782138347625732}
-03/04/2022 05:52:22 - INFO - codeparrot_training - Step 13973: {'lr': 0.0004919693009418782, 'samples': 7154688, 'steps': 13973, 'loss/train': 1.962145447731018}
-03/04/2022 05:52:24 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/04/2022 05:52:27 - INFO - codeparrot_training - Step 13974: {'lr': 0.0004919679666477384, 'samples': 7155200, 'steps': 13974, 'loss/train': 1.0628620386123657}
-03/04/2022 05:52:30 - INFO - codeparrot_training - Step 13975: {'lr': 0.0004919666322445715, 'samples': 7155712, 'steps': 13975, 'loss/train': 1.925017237663269}
-03/04/2022 05:52:32 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 05:52:36 - INFO - codeparrot_training - Step 13976: {'lr': 0.0004919652977323783, 'samples': 7156224, 'steps': 13976, 'loss/train': 2.38873028755188}
-03/04/2022 05:52:39 - INFO - codeparrot_training - Step 13977: {'lr': 0.0004919639631111592, 'samples': 7156736, 'steps': 13977, 'loss/train': 0.6375347375869751}
-03/04/2022 05:52:41 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 05:52:44 - INFO - codeparrot_training - Step 13978: {'lr': 0.0004919626283809149, 'samples': 7157248, 'steps': 13978, 'loss/train': 2.4640443325042725}
-03/04/2022 05:52:47 - INFO - codeparrot_training - Step 13979: {'lr': 0.0004919612935416459, 'samples': 7157760, 'steps': 13979, 'loss/train': 1.988576054573059}
-03/04/2022 05:52:49 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/04/2022 05:52:52 - INFO - codeparrot_training - Step 13980: {'lr': 0.000491959958593353, 'samples': 7158272, 'steps': 13980, 'loss/train': 2.6399481296539307}
-03/04/2022 05:52:56 - INFO - codeparrot_training - Step 13981: {'lr': 0.0004919586235360365, 'samples': 7158784, 'steps': 13981, 'loss/train': 1.8989062309265137}
-03/04/2022 05:52:58 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 05:53:01 - INFO - codeparrot_training - Step 13982: {'lr': 0.0004919572883696974, 'samples': 7159296, 'steps': 13982, 'loss/train': 2.23386549949646}
-03/04/2022 05:53:04 - INFO - codeparrot_training - Step 13983: {'lr': 0.0004919559530943359, 'samples': 7159808, 'steps': 13983, 'loss/train': 1.7406151294708252}
-03/04/2022 05:53:06 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/04/2022 05:53:09 - INFO - codeparrot_training - Step 13984: {'lr': 0.0004919546177099528, 'samples': 7160320, 'steps': 13984, 'loss/train': 2.3210766315460205}
-03/04/2022 05:53:12 - INFO - codeparrot_training - Step 13985: {'lr': 0.0004919532822165487, 'samples': 7160832, 'steps': 13985, 'loss/train': 1.9358881711959839}
-03/04/2022 05:53:14 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/04/2022 05:53:18 - INFO - codeparrot_training - Step 13986: {'lr': 0.0004919519466141242, 'samples': 7161344, 'steps': 13986, 'loss/train': 1.864014983177185}
-03/04/2022 05:53:21 - INFO - codeparrot_training - Step 13987: {'lr': 0.0004919506109026799, 'samples': 7161856, 'steps': 13987, 'loss/train': 2.087329149246216}
-03/04/2022 05:53:22 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 05:53:26 - INFO - codeparrot_training - Step 13988: {'lr': 0.0004919492750822163, 'samples': 7162368, 'steps': 13988, 'loss/train': 1.8173290491104126}
-03/04/2022 05:53:29 - INFO - codeparrot_training - Step 13989: {'lr': 0.0004919479391527343, 'samples': 7162880, 'steps': 13989, 'loss/train': 2.0140275955200195}
-03/04/2022 05:53:30 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/04/2022 05:53:34 - INFO - codeparrot_training - Step 13990: {'lr': 0.0004919466031142342, 'samples': 7163392, 'steps': 13990, 'loss/train': 0.9639871120452881}
-03/04/2022 05:53:37 - INFO - codeparrot_training - Step 13991: {'lr': 0.0004919452669667166, 'samples': 7163904, 'steps': 13991, 'loss/train': 2.548413038253784}
-03/04/2022 05:53:39 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/04/2022 05:53:43 - INFO - codeparrot_training - Step 13992: {'lr': 0.0004919439307101822, 'samples': 7164416, 'steps': 13992, 'loss/train': 2.0972495079040527}
-03/04/2022 05:53:46 - INFO - codeparrot_training - Step 13993: {'lr': 0.0004919425943446317, 'samples': 7164928, 'steps': 13993, 'loss/train': 1.8180569410324097}
-03/04/2022 05:53:47 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/04/2022 05:53:51 - INFO - codeparrot_training - Step 13994: {'lr': 0.0004919412578700654, 'samples': 7165440, 'steps': 13994, 'loss/train': 1.5299862623214722}
-03/04/2022 05:53:54 - INFO - codeparrot_training - Step 13995: {'lr': 0.0004919399212864843, 'samples': 7165952, 'steps': 13995, 'loss/train': 2.073214292526245}
-03/04/2022 05:53:56 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/04/2022 05:54:00 - INFO - codeparrot_training - Step 13996: {'lr': 0.0004919385845938888, 'samples': 7166464, 'steps': 13996, 'loss/train': 1.7051867246627808}
-03/04/2022 05:54:03 - INFO - codeparrot_training - Step 13997: {'lr': 0.0004919372477922794, 'samples': 7166976, 'steps': 13997, 'loss/train': 1.313161015510559}
-03/04/2022 05:54:04 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/04/2022 05:54:08 - INFO - codeparrot_training - Step 13998: {'lr': 0.0004919359108816569, 'samples': 7167488, 'steps': 13998, 'loss/train': 1.8579096794128418}
-03/04/2022 05:54:11 - INFO - codeparrot_training - Step 13999: {'lr': 0.0004919345738620218, 'samples': 7168000, 'steps': 13999, 'loss/train': 1.849039077758789}
-03/04/2022 05:54:13 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 05:54:16 - INFO - codeparrot_training - Step 14000: {'lr': 0.0004919332367333747, 'samples': 7168512, 'steps': 14000, 'loss/train': 1.3656651973724365}
-03/04/2022 05:54:20 - INFO - codeparrot_training - Step 14001: {'lr': 0.0004919318994957162, 'samples': 7169024, 'steps': 14001, 'loss/train': 2.0255234241485596}
-03/04/2022 05:54:21 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/04/2022 05:54:25 - INFO - codeparrot_training - Step 14002: {'lr': 0.0004919305621490469, 'samples': 7169536, 'steps': 14002, 'loss/train': 1.9137911796569824}
-03/04/2022 05:54:28 - INFO - codeparrot_training - Step 14003: {'lr': 0.0004919292246933675, 'samples': 7170048, 'steps': 14003, 'loss/train': 1.8781532049179077}
-03/04/2022 05:54:29 - INFO - codeparrot_training - Skipping example with length 524 (seq_length=1024)
-03/04/2022 05:54:33 - INFO - codeparrot_training - Step 14004: {'lr': 0.0004919278871286785, 'samples': 7170560, 'steps': 14004, 'loss/train': 2.49585223197937}
-03/04/2022 05:54:36 - INFO - codeparrot_training - Step 14005: {'lr': 0.0004919265494549805, 'samples': 7171072, 'steps': 14005, 'loss/train': 2.170870304107666}
-03/04/2022 05:54:38 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/04/2022 05:54:42 - INFO - codeparrot_training - Step 14006: {'lr': 0.0004919252116722742, 'samples': 7171584, 'steps': 14006, 'loss/train': 1.2844462394714355}
-03/04/2022 05:54:45 - INFO - codeparrot_training - Step 14007: {'lr': 0.0004919238737805601, 'samples': 7172096, 'steps': 14007, 'loss/train': 1.8963029384613037}
-03/04/2022 05:54:46 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/04/2022 05:54:50 - INFO - codeparrot_training - Step 14008: {'lr': 0.0004919225357798387, 'samples': 7172608, 'steps': 14008, 'loss/train': 1.9304652214050293}
-03/04/2022 05:54:53 - INFO - codeparrot_training - Step 14009: {'lr': 0.000491921197670111, 'samples': 7173120, 'steps': 14009, 'loss/train': 2.031053304672241}
-03/04/2022 05:54:55 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/04/2022 05:54:59 - INFO - codeparrot_training - Step 14010: {'lr': 0.0004919198594513771, 'samples': 7173632, 'steps': 14010, 'loss/train': 0.9281302690505981}
-03/04/2022 05:55:02 - INFO - codeparrot_training - Step 14011: {'lr': 0.0004919185211236379, 'samples': 7174144, 'steps': 14011, 'loss/train': 1.0891904830932617}
-03/04/2022 05:55:03 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 05:55:07 - INFO - codeparrot_training - Step 14012: {'lr': 0.000491917182686894, 'samples': 7174656, 'steps': 14012, 'loss/train': 2.1382899284362793}
-03/04/2022 05:55:10 - INFO - codeparrot_training - Step 14013: {'lr': 0.0004919158441411459, 'samples': 7175168, 'steps': 14013, 'loss/train': 2.1449997425079346}
-03/04/2022 05:55:12 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/04/2022 05:55:15 - INFO - codeparrot_training - Step 14014: {'lr': 0.0004919145054863943, 'samples': 7175680, 'steps': 14014, 'loss/train': 2.336923122406006}
-03/04/2022 05:55:19 - INFO - codeparrot_training - Step 14015: {'lr': 0.0004919131667226398, 'samples': 7176192, 'steps': 14015, 'loss/train': 1.6024322509765625}
-03/04/2022 05:55:20 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 05:55:24 - INFO - codeparrot_training - Step 14016: {'lr': 0.0004919118278498828, 'samples': 7176704, 'steps': 14016, 'loss/train': 1.9863035678863525}
-03/04/2022 05:55:27 - INFO - codeparrot_training - Step 14017: {'lr': 0.0004919104888681242, 'samples': 7177216, 'steps': 14017, 'loss/train': 1.9998358488082886}
-03/04/2022 05:55:30 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 05:55:33 - INFO - codeparrot_training - Step 14018: {'lr': 0.0004919091497773643, 'samples': 7177728, 'steps': 14018, 'loss/train': 1.789475917816162}
-03/04/2022 05:55:36 - INFO - codeparrot_training - Step 14019: {'lr': 0.0004919078105776041, 'samples': 7178240, 'steps': 14019, 'loss/train': 2.1098225116729736}
-03/04/2022 05:55:38 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 05:55:41 - INFO - codeparrot_training - Step 14020: {'lr': 0.0004919064712688439, 'samples': 7178752, 'steps': 14020, 'loss/train': 2.2897260189056396}
-03/04/2022 05:55:44 - INFO - codeparrot_training - Step 14021: {'lr': 0.0004919051318510844, 'samples': 7179264, 'steps': 14021, 'loss/train': 0.1453106850385666}
-03/04/2022 05:55:48 - INFO - codeparrot_training - Step 14022: {'lr': 0.0004919037923243261, 'samples': 7179776, 'steps': 14022, 'loss/train': 2.3614444732666016}
-03/04/2022 05:55:48 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 05:55:53 - INFO - codeparrot_training - Step 14023: {'lr': 0.0004919024526885697, 'samples': 7180288, 'steps': 14023, 'loss/train': 2.506523370742798}
-03/04/2022 05:55:56 - INFO - codeparrot_training - Step 14024: {'lr': 0.0004919011129438158, 'samples': 7180800, 'steps': 14024, 'loss/train': 2.176182270050049}
-03/04/2022 05:55:56 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/04/2022 05:56:01 - INFO - codeparrot_training - Step 14025: {'lr': 0.0004918997730900649, 'samples': 7181312, 'steps': 14025, 'loss/train': 2.152094841003418}
-03/04/2022 05:56:04 - INFO - codeparrot_training - Step 14026: {'lr': 0.0004918984331273178, 'samples': 7181824, 'steps': 14026, 'loss/train': 2.332519054412842}
-03/04/2022 05:56:05 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/04/2022 05:56:10 - INFO - codeparrot_training - Step 14027: {'lr': 0.0004918970930555751, 'samples': 7182336, 'steps': 14027, 'loss/train': 2.489626407623291}
-03/04/2022 05:56:13 - INFO - codeparrot_training - Step 14028: {'lr': 0.0004918957528748371, 'samples': 7182848, 'steps': 14028, 'loss/train': 2.0826807022094727}
-03/04/2022 05:56:13 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/04/2022 05:56:18 - INFO - codeparrot_training - Step 14029: {'lr': 0.0004918944125851047, 'samples': 7183360, 'steps': 14029, 'loss/train': 2.5289883613586426}
-03/04/2022 05:56:21 - INFO - codeparrot_training - Step 14030: {'lr': 0.0004918930721863784, 'samples': 7183872, 'steps': 14030, 'loss/train': 1.9666383266448975}
-03/04/2022 05:56:22 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/04/2022 05:56:27 - INFO - codeparrot_training - Step 14031: {'lr': 0.0004918917316786589, 'samples': 7184384, 'steps': 14031, 'loss/train': 2.3281028270721436}
-03/04/2022 05:56:30 - INFO - codeparrot_training - Step 14032: {'lr': 0.0004918903910619465, 'samples': 7184896, 'steps': 14032, 'loss/train': 2.4829254150390625}
-03/04/2022 05:56:30 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 05:56:35 - INFO - codeparrot_training - Step 14033: {'lr': 0.0004918890503362422, 'samples': 7185408, 'steps': 14033, 'loss/train': 2.108673334121704}
-03/04/2022 05:56:38 - INFO - codeparrot_training - Step 14034: {'lr': 0.0004918877095015465, 'samples': 7185920, 'steps': 14034, 'loss/train': 2.060053586959839}
-03/04/2022 05:56:38 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/04/2022 05:56:43 - INFO - codeparrot_training - Step 14035: {'lr': 0.0004918863685578598, 'samples': 7186432, 'steps': 14035, 'loss/train': 0.635498583316803}
-03/04/2022 05:56:47 - INFO - codeparrot_training - Step 14036: {'lr': 0.0004918850275051829, 'samples': 7186944, 'steps': 14036, 'loss/train': 1.4036310911178589}
-03/04/2022 05:56:47 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/04/2022 05:56:52 - INFO - codeparrot_training - Step 14037: {'lr': 0.0004918836863435162, 'samples': 7187456, 'steps': 14037, 'loss/train': 1.5927863121032715}
-03/04/2022 05:56:55 - INFO - codeparrot_training - Step 14038: {'lr': 0.0004918823450728606, 'samples': 7187968, 'steps': 14038, 'loss/train': 1.9537044763565063}
-03/04/2022 05:56:55 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/04/2022 05:57:00 - INFO - codeparrot_training - Step 14039: {'lr': 0.0004918810036932164, 'samples': 7188480, 'steps': 14039, 'loss/train': 2.1265370845794678}
-03/04/2022 05:57:03 - INFO - codeparrot_training - Step 14040: {'lr': 0.0004918796622045844, 'samples': 7188992, 'steps': 14040, 'loss/train': 2.207047462463379}
-03/04/2022 05:57:03 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/04/2022 05:57:09 - INFO - codeparrot_training - Step 14041: {'lr': 0.0004918783206069652, 'samples': 7189504, 'steps': 14041, 'loss/train': 1.7336440086364746}
-03/04/2022 05:57:12 - INFO - codeparrot_training - Step 14042: {'lr': 0.0004918769789003593, 'samples': 7190016, 'steps': 14042, 'loss/train': 1.6138806343078613}
-03/04/2022 05:57:12 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/04/2022 05:57:17 - INFO - codeparrot_training - Step 14043: {'lr': 0.0004918756370847674, 'samples': 7190528, 'steps': 14043, 'loss/train': 1.4313749074935913}
-03/04/2022 05:57:20 - INFO - codeparrot_training - Step 14044: {'lr': 0.0004918742951601902, 'samples': 7191040, 'steps': 14044, 'loss/train': 2.357377052307129}
-03/04/2022 05:57:21 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/04/2022 05:57:26 - INFO - codeparrot_training - Step 14045: {'lr': 0.000491872953126628, 'samples': 7191552, 'steps': 14045, 'loss/train': 1.1253046989440918}
-03/04/2022 05:57:29 - INFO - codeparrot_training - Step 14046: {'lr': 0.0004918716109840817, 'samples': 7192064, 'steps': 14046, 'loss/train': 2.136277198791504}
-03/04/2022 05:57:29 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 05:57:34 - INFO - codeparrot_training - Step 14047: {'lr': 0.0004918702687325517, 'samples': 7192576, 'steps': 14047, 'loss/train': 2.2617716789245605}
-03/04/2022 05:57:37 - INFO - codeparrot_training - Step 14048: {'lr': 0.0004918689263720388, 'samples': 7193088, 'steps': 14048, 'loss/train': 1.6275819540023804}
-03/04/2022 05:57:38 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/04/2022 05:57:43 - INFO - codeparrot_training - Step 14049: {'lr': 0.0004918675839025434, 'samples': 7193600, 'steps': 14049, 'loss/train': 2.029517650604248}
-03/04/2022 05:57:46 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 05:57:48 - INFO - codeparrot_training - Step 14050: {'lr': 0.0004918662413240662, 'samples': 7194112, 'steps': 14050, 'loss/train': 1.0937405824661255}
-03/04/2022 05:57:51 - INFO - codeparrot_training - Step 14051: {'lr': 0.0004918648986366078, 'samples': 7194624, 'steps': 14051, 'loss/train': 2.325713634490967}
-03/04/2022 05:57:54 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/04/2022 05:57:56 - INFO - codeparrot_training - Step 14052: {'lr': 0.0004918635558401687, 'samples': 7195136, 'steps': 14052, 'loss/train': 1.9886972904205322}
-03/04/2022 05:58:00 - INFO - codeparrot_training - Step 14053: {'lr': 0.0004918622129347498, 'samples': 7195648, 'steps': 14053, 'loss/train': 1.7364531755447388}
-03/04/2022 05:58:02 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 05:58:05 - INFO - codeparrot_training - Step 14054: {'lr': 0.0004918608699203515, 'samples': 7196160, 'steps': 14054, 'loss/train': 1.5989786386489868}
-03/04/2022 05:58:08 - INFO - codeparrot_training - Step 14055: {'lr': 0.0004918595267969744, 'samples': 7196672, 'steps': 14055, 'loss/train': 1.640325665473938}
-03/04/2022 05:58:10 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/04/2022 05:58:13 - INFO - codeparrot_training - Step 14056: {'lr': 0.0004918581835646191, 'samples': 7197184, 'steps': 14056, 'loss/train': 2.262174606323242}
-03/04/2022 05:58:16 - INFO - codeparrot_training - Step 14057: {'lr': 0.0004918568402232863, 'samples': 7197696, 'steps': 14057, 'loss/train': 1.4383906126022339}
-03/04/2022 05:58:19 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 05:58:22 - INFO - codeparrot_training - Step 14058: {'lr': 0.0004918554967729764, 'samples': 7198208, 'steps': 14058, 'loss/train': 1.932021975517273}
-03/04/2022 05:58:25 - INFO - codeparrot_training - Step 14059: {'lr': 0.0004918541532136902, 'samples': 7198720, 'steps': 14059, 'loss/train': 1.8150835037231445}
-03/04/2022 05:58:27 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/04/2022 05:58:30 - INFO - codeparrot_training - Step 14060: {'lr': 0.0004918528095454283, 'samples': 7199232, 'steps': 14060, 'loss/train': 1.4453004598617554}
-03/04/2022 05:58:33 - INFO - codeparrot_training - Step 14061: {'lr': 0.0004918514657681913, 'samples': 7199744, 'steps': 14061, 'loss/train': 2.9402449131011963}
-03/04/2022 05:58:36 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/04/2022 05:58:39 - INFO - codeparrot_training - Step 14062: {'lr': 0.0004918501218819796, 'samples': 7200256, 'steps': 14062, 'loss/train': 1.6087387800216675}
-03/04/2022 05:58:42 - INFO - codeparrot_training - Step 14063: {'lr': 0.0004918487778867941, 'samples': 7200768, 'steps': 14063, 'loss/train': 2.0506086349487305}
-03/04/2022 05:58:44 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/04/2022 05:58:47 - INFO - codeparrot_training - Step 14064: {'lr': 0.0004918474337826353, 'samples': 7201280, 'steps': 14064, 'loss/train': 1.619303822517395}
-03/04/2022 05:58:50 - INFO - codeparrot_training - Step 14065: {'lr': 0.0004918460895695037, 'samples': 7201792, 'steps': 14065, 'loss/train': 1.127860426902771}
-03/04/2022 05:58:53 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 05:58:55 - INFO - codeparrot_training - Step 14066: {'lr': 0.0004918447452474, 'samples': 7202304, 'steps': 14066, 'loss/train': 2.289330244064331}
-03/04/2022 05:58:58 - INFO - codeparrot_training - Step 14067: {'lr': 0.0004918434008163247, 'samples': 7202816, 'steps': 14067, 'loss/train': 1.1197565793991089}
-03/04/2022 05:59:01 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/04/2022 05:59:04 - INFO - codeparrot_training - Step 14068: {'lr': 0.0004918420562762786, 'samples': 7203328, 'steps': 14068, 'loss/train': 2.2395644187927246}
-03/04/2022 05:59:07 - INFO - codeparrot_training - Step 14069: {'lr': 0.0004918407116272622, 'samples': 7203840, 'steps': 14069, 'loss/train': 2.1948904991149902}
-03/04/2022 05:59:09 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/04/2022 05:59:12 - INFO - codeparrot_training - Step 14070: {'lr': 0.000491839366869276, 'samples': 7204352, 'steps': 14070, 'loss/train': 2.0624635219573975}
-03/04/2022 05:59:16 - INFO - codeparrot_training - Step 14071: {'lr': 0.000491838022002321, 'samples': 7204864, 'steps': 14071, 'loss/train': 1.5776728391647339}
-03/04/2022 05:59:18 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 05:59:21 - INFO - codeparrot_training - Step 14072: {'lr': 0.0004918366770263972, 'samples': 7205376, 'steps': 14072, 'loss/train': 2.1290087699890137}
-03/04/2022 05:59:24 - INFO - codeparrot_training - Step 14073: {'lr': 0.0004918353319415057, 'samples': 7205888, 'steps': 14073, 'loss/train': 2.388699769973755}
-03/04/2022 05:59:27 - INFO - codeparrot_training - Step 14074: {'lr': 0.0004918339867476469, 'samples': 7206400, 'steps': 14074, 'loss/train': 2.464887857437134}
-03/04/2022 05:59:28 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 05:59:33 - INFO - codeparrot_training - Step 14075: {'lr': 0.0004918326414448214, 'samples': 7206912, 'steps': 14075, 'loss/train': 2.3424885272979736}
-03/04/2022 05:59:36 - INFO - codeparrot_training - Step 14076: {'lr': 0.0004918312960330299, 'samples': 7207424, 'steps': 14076, 'loss/train': 0.8553295135498047}
-03/04/2022 05:59:36 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/04/2022 05:59:41 - INFO - codeparrot_training - Step 14077: {'lr': 0.0004918299505122729, 'samples': 7207936, 'steps': 14077, 'loss/train': 2.844550132751465}
-03/04/2022 05:59:44 - INFO - codeparrot_training - Step 14078: {'lr': 0.000491828604882551, 'samples': 7208448, 'steps': 14078, 'loss/train': 1.55009925365448}
-03/04/2022 05:59:45 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 05:59:50 - INFO - codeparrot_training - Step 14079: {'lr': 0.0004918272591438649, 'samples': 7208960, 'steps': 14079, 'loss/train': 1.9941363334655762}
-03/04/2022 05:59:53 - INFO - codeparrot_training - Step 14080: {'lr': 0.0004918259132962153, 'samples': 7209472, 'steps': 14080, 'loss/train': 2.313652276992798}
-03/04/2022 05:59:55 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/04/2022 05:59:58 - INFO - codeparrot_training - Step 14081: {'lr': 0.0004918245673396025, 'samples': 7209984, 'steps': 14081, 'loss/train': 1.7981575727462769}
-03/04/2022 06:00:01 - INFO - codeparrot_training - Step 14082: {'lr': 0.0004918232212740274, 'samples': 7210496, 'steps': 14082, 'loss/train': 2.260336399078369}
-03/04/2022 06:00:04 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 06:00:07 - INFO - codeparrot_training - Step 14083: {'lr': 0.0004918218750994904, 'samples': 7211008, 'steps': 14083, 'loss/train': 1.9509133100509644}
-03/04/2022 06:00:10 - INFO - codeparrot_training - Step 14084: {'lr': 0.0004918205288159923, 'samples': 7211520, 'steps': 14084, 'loss/train': 2.4949567317962646}
-03/04/2022 06:00:12 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/04/2022 06:00:15 - INFO - codeparrot_training - Step 14085: {'lr': 0.0004918191824235335, 'samples': 7212032, 'steps': 14085, 'loss/train': 2.0261800289154053}
-03/04/2022 06:00:18 - INFO - codeparrot_training - Step 14086: {'lr': 0.0004918178359221147, 'samples': 7212544, 'steps': 14086, 'loss/train': 1.5548934936523438}
-03/04/2022 06:00:20 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/04/2022 06:00:23 - INFO - codeparrot_training - Step 14087: {'lr': 0.0004918164893117366, 'samples': 7213056, 'steps': 14087, 'loss/train': 1.7176016569137573}
-03/04/2022 06:00:27 - INFO - codeparrot_training - Step 14088: {'lr': 0.0004918151425923996, 'samples': 7213568, 'steps': 14088, 'loss/train': 1.7271625995635986}
-03/04/2022 06:00:29 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 06:00:32 - INFO - codeparrot_training - Step 14089: {'lr': 0.0004918137957641046, 'samples': 7214080, 'steps': 14089, 'loss/train': 1.9582417011260986}
-03/04/2022 06:00:35 - INFO - codeparrot_training - Step 14090: {'lr': 0.000491812448826852, 'samples': 7214592, 'steps': 14090, 'loss/train': 1.6457774639129639}
-03/04/2022 06:00:37 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 06:00:40 - INFO - codeparrot_training - Step 14091: {'lr': 0.0004918111017806424, 'samples': 7215104, 'steps': 14091, 'loss/train': 1.9556223154067993}
-03/04/2022 06:00:43 - INFO - codeparrot_training - Step 14092: {'lr': 0.0004918097546254764, 'samples': 7215616, 'steps': 14092, 'loss/train': 1.1843924522399902}
-03/04/2022 06:00:45 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/04/2022 06:00:49 - INFO - codeparrot_training - Step 14093: {'lr': 0.0004918084073613547, 'samples': 7216128, 'steps': 14093, 'loss/train': 1.7675302028656006}
-03/04/2022 06:00:52 - INFO - codeparrot_training - Step 14094: {'lr': 0.0004918070599882778, 'samples': 7216640, 'steps': 14094, 'loss/train': 1.5487662553787231}
-03/04/2022 06:00:54 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/04/2022 06:00:57 - INFO - codeparrot_training - Step 14095: {'lr': 0.0004918057125062465, 'samples': 7217152, 'steps': 14095, 'loss/train': 2.8335893154144287}
-03/04/2022 06:01:00 - INFO - codeparrot_training - Step 14096: {'lr': 0.0004918043649152612, 'samples': 7217664, 'steps': 14096, 'loss/train': 2.0373036861419678}
-03/04/2022 06:01:02 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/04/2022 06:01:05 - INFO - codeparrot_training - Step 14097: {'lr': 0.0004918030172153225, 'samples': 7218176, 'steps': 14097, 'loss/train': 1.532878041267395}
-03/04/2022 06:01:09 - INFO - codeparrot_training - Step 14098: {'lr': 0.0004918016694064313, 'samples': 7218688, 'steps': 14098, 'loss/train': 1.9771639108657837}
-03/04/2022 06:01:11 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 06:01:14 - INFO - codeparrot_training - Step 14099: {'lr': 0.0004918003214885877, 'samples': 7219200, 'steps': 14099, 'loss/train': 2.1318392753601074}
-03/04/2022 06:01:17 - INFO - codeparrot_training - Step 14100: {'lr': 0.0004917989734617928, 'samples': 7219712, 'steps': 14100, 'loss/train': 1.7022360563278198}
-03/04/2022 06:01:19 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/04/2022 06:01:22 - INFO - codeparrot_training - Step 14101: {'lr': 0.0004917976253260471, 'samples': 7220224, 'steps': 14101, 'loss/train': 1.8486034870147705}
-03/04/2022 06:01:26 - INFO - codeparrot_training - Step 14102: {'lr': 0.000491796277081351, 'samples': 7220736, 'steps': 14102, 'loss/train': 1.4838587045669556}
-03/04/2022 06:01:29 - INFO - codeparrot_training - Step 14103: {'lr': 0.0004917949287277052, 'samples': 7221248, 'steps': 14103, 'loss/train': 1.9135456085205078}
-03/04/2022 06:01:29 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 06:01:35 - INFO - codeparrot_training - Step 14104: {'lr': 0.0004917935802651104, 'samples': 7221760, 'steps': 14104, 'loss/train': 1.3786108493804932}
-03/04/2022 06:01:38 - INFO - codeparrot_training - Step 14105: {'lr': 0.0004917922316935671, 'samples': 7222272, 'steps': 14105, 'loss/train': 2.3258466720581055}
-03/04/2022 06:01:40 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/04/2022 06:01:43 - INFO - codeparrot_training - Step 14106: {'lr': 0.000491790883013076, 'samples': 7222784, 'steps': 14106, 'loss/train': 1.7083362340927124}
-03/04/2022 06:01:46 - INFO - codeparrot_training - Step 14107: {'lr': 0.0004917895342236377, 'samples': 7223296, 'steps': 14107, 'loss/train': 2.8553473949432373}
-03/04/2022 06:01:48 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/04/2022 06:01:52 - INFO - codeparrot_training - Step 14108: {'lr': 0.0004917881853252527, 'samples': 7223808, 'steps': 14108, 'loss/train': 2.031553268432617}
-03/04/2022 06:01:55 - INFO - codeparrot_training - Step 14109: {'lr': 0.0004917868363179216, 'samples': 7224320, 'steps': 14109, 'loss/train': 1.5042833089828491}
-03/04/2022 06:01:57 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/04/2022 06:02:00 - INFO - codeparrot_training - Step 14110: {'lr': 0.0004917854872016451, 'samples': 7224832, 'steps': 14110, 'loss/train': 1.8604176044464111}
-03/04/2022 06:02:03 - INFO - codeparrot_training - Step 14111: {'lr': 0.000491784137976424, 'samples': 7225344, 'steps': 14111, 'loss/train': 1.4956369400024414}
-03/04/2022 06:02:06 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/04/2022 06:02:09 - INFO - codeparrot_training - Step 14112: {'lr': 0.0004917827886422586, 'samples': 7225856, 'steps': 14112, 'loss/train': 1.3805453777313232}
-03/04/2022 06:02:12 - INFO - codeparrot_training - Step 14113: {'lr': 0.0004917814391991494, 'samples': 7226368, 'steps': 14113, 'loss/train': 2.364252805709839}
-03/04/2022 06:02:14 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/04/2022 06:02:17 - INFO - codeparrot_training - Step 14114: {'lr': 0.0004917800896470974, 'samples': 7226880, 'steps': 14114, 'loss/train': 2.1706013679504395}
-03/04/2022 06:02:20 - INFO - codeparrot_training - Step 14115: {'lr': 0.000491778739986103, 'samples': 7227392, 'steps': 14115, 'loss/train': 2.177109718322754}
-03/04/2022 06:02:23 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 06:02:26 - INFO - codeparrot_training - Step 14116: {'lr': 0.0004917773902161669, 'samples': 7227904, 'steps': 14116, 'loss/train': 0.5813825726509094}
-03/04/2022 06:02:29 - INFO - codeparrot_training - Step 14117: {'lr': 0.0004917760403372895, 'samples': 7228416, 'steps': 14117, 'loss/train': 2.0776968002319336}
-03/04/2022 06:02:31 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/04/2022 06:02:34 - INFO - codeparrot_training - Step 14118: {'lr': 0.0004917746903494717, 'samples': 7228928, 'steps': 14118, 'loss/train': 1.767589807510376}
-03/04/2022 06:02:37 - INFO - codeparrot_training - Step 14119: {'lr': 0.0004917733402527138, 'samples': 7229440, 'steps': 14119, 'loss/train': 2.4280426502227783}
-03/04/2022 06:02:39 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 06:02:42 - INFO - codeparrot_training - Step 14120: {'lr': 0.0004917719900470167, 'samples': 7229952, 'steps': 14120, 'loss/train': 1.7785121202468872}
-03/04/2022 06:02:46 - INFO - codeparrot_training - Step 14121: {'lr': 0.0004917706397323808, 'samples': 7230464, 'steps': 14121, 'loss/train': 2.0207407474517822}
-03/04/2022 06:02:48 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/04/2022 06:02:51 - INFO - codeparrot_training - Step 14122: {'lr': 0.0004917692893088067, 'samples': 7230976, 'steps': 14122, 'loss/train': 1.822907567024231}
-03/04/2022 06:02:54 - INFO - codeparrot_training - Step 14123: {'lr': 0.0004917679387762952, 'samples': 7231488, 'steps': 14123, 'loss/train': 1.7399559020996094}
-03/04/2022 06:02:57 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/04/2022 06:02:59 - INFO - codeparrot_training - Step 14124: {'lr': 0.0004917665881348467, 'samples': 7232000, 'steps': 14124, 'loss/train': 1.255372166633606}
-03/04/2022 06:03:02 - INFO - codeparrot_training - Step 14125: {'lr': 0.000491765237384462, 'samples': 7232512, 'steps': 14125, 'loss/train': 2.0268311500549316}
-03/04/2022 06:03:05 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/04/2022 06:03:08 - INFO - codeparrot_training - Step 14126: {'lr': 0.0004917638865251416, 'samples': 7233024, 'steps': 14126, 'loss/train': 1.4348195791244507}
-03/04/2022 06:03:11 - INFO - codeparrot_training - Step 14127: {'lr': 0.0004917625355568861, 'samples': 7233536, 'steps': 14127, 'loss/train': 3.2066614627838135}
-03/04/2022 06:03:14 - INFO - codeparrot_training - Step 14128: {'lr': 0.0004917611844796962, 'samples': 7234048, 'steps': 14128, 'loss/train': 1.3921555280685425}
-03/04/2022 06:03:14 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/04/2022 06:03:19 - INFO - codeparrot_training - Step 14129: {'lr': 0.0004917598332935724, 'samples': 7234560, 'steps': 14129, 'loss/train': 2.052250623703003}
-03/04/2022 06:03:22 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 06:03:24 - INFO - codeparrot_training - Step 14130: {'lr': 0.0004917584819985153, 'samples': 7235072, 'steps': 14130, 'loss/train': 1.931939959526062}
-03/04/2022 06:03:28 - INFO - codeparrot_training - Step 14131: {'lr': 0.0004917571305945256, 'samples': 7235584, 'steps': 14131, 'loss/train': 2.0276830196380615}
-03/04/2022 06:03:30 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 06:03:33 - INFO - codeparrot_training - Step 14132: {'lr': 0.0004917557790816039, 'samples': 7236096, 'steps': 14132, 'loss/train': 1.152252435684204}
-03/04/2022 06:03:36 - INFO - codeparrot_training - Step 14133: {'lr': 0.0004917544274597507, 'samples': 7236608, 'steps': 14133, 'loss/train': 2.0702474117279053}
-03/04/2022 06:03:39 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/04/2022 06:03:41 - INFO - codeparrot_training - Step 14134: {'lr': 0.0004917530757289668, 'samples': 7237120, 'steps': 14134, 'loss/train': 1.851188063621521}
-03/04/2022 06:03:45 - INFO - codeparrot_training - Step 14135: {'lr': 0.0004917517238892526, 'samples': 7237632, 'steps': 14135, 'loss/train': 2.0769472122192383}
-03/04/2022 06:03:47 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 06:03:50 - INFO - codeparrot_training - Step 14136: {'lr': 0.0004917503719406087, 'samples': 7238144, 'steps': 14136, 'loss/train': 1.9030643701553345}
-03/04/2022 06:03:53 - INFO - codeparrot_training - Step 14137: {'lr': 0.000491749019883036, 'samples': 7238656, 'steps': 14137, 'loss/train': 1.427193522453308}
-03/04/2022 06:03:55 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/04/2022 06:03:58 - INFO - codeparrot_training - Step 14138: {'lr': 0.0004917476677165349, 'samples': 7239168, 'steps': 14138, 'loss/train': 1.97562837600708}
-03/04/2022 06:04:01 - INFO - codeparrot_training - Step 14139: {'lr': 0.0004917463154411059, 'samples': 7239680, 'steps': 14139, 'loss/train': 2.3944435119628906}
-03/04/2022 06:04:04 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 06:04:07 - INFO - codeparrot_training - Step 14140: {'lr': 0.0004917449630567499, 'samples': 7240192, 'steps': 14140, 'loss/train': 1.399261713027954}
-03/04/2022 06:04:10 - INFO - codeparrot_training - Step 14141: {'lr': 0.0004917436105634673, 'samples': 7240704, 'steps': 14141, 'loss/train': 1.736466407775879}
-03/04/2022 06:04:12 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 06:04:15 - INFO - codeparrot_training - Step 14142: {'lr': 0.0004917422579612587, 'samples': 7241216, 'steps': 14142, 'loss/train': 2.32731556892395}
-03/04/2022 06:04:18 - INFO - codeparrot_training - Step 14143: {'lr': 0.0004917409052501248, 'samples': 7241728, 'steps': 14143, 'loss/train': 1.035368800163269}
-03/04/2022 06:04:20 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 06:04:23 - INFO - codeparrot_training - Step 14144: {'lr': 0.0004917395524300661, 'samples': 7242240, 'steps': 14144, 'loss/train': 1.9322433471679688}
-03/04/2022 06:04:27 - INFO - codeparrot_training - Step 14145: {'lr': 0.0004917381995010834, 'samples': 7242752, 'steps': 14145, 'loss/train': 1.344626545906067}
-03/04/2022 06:04:29 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 06:04:32 - INFO - codeparrot_training - Step 14146: {'lr': 0.0004917368464631772, 'samples': 7243264, 'steps': 14146, 'loss/train': 2.4868645668029785}
-03/04/2022 06:04:35 - INFO - codeparrot_training - Step 14147: {'lr': 0.0004917354933163481, 'samples': 7243776, 'steps': 14147, 'loss/train': 1.8004776239395142}
-03/04/2022 06:04:38 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 06:04:40 - INFO - codeparrot_training - Step 14148: {'lr': 0.0004917341400605967, 'samples': 7244288, 'steps': 14148, 'loss/train': 1.790788173675537}
-03/04/2022 06:04:43 - INFO - codeparrot_training - Step 14149: {'lr': 0.0004917327866959236, 'samples': 7244800, 'steps': 14149, 'loss/train': 1.8403900861740112}
-03/04/2022 06:04:46 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 06:04:49 - INFO - codeparrot_training - Step 14150: {'lr': 0.0004917314332223295, 'samples': 7245312, 'steps': 14150, 'loss/train': 1.7214235067367554}
-03/04/2022 06:04:52 - INFO - codeparrot_training - Step 14151: {'lr': 0.0004917300796398148, 'samples': 7245824, 'steps': 14151, 'loss/train': 3.2851078510284424}
-03/04/2022 06:04:55 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 06:04:57 - INFO - codeparrot_training - Step 14152: {'lr': 0.0004917287259483805, 'samples': 7246336, 'steps': 14152, 'loss/train': 2.455721139907837}
-03/04/2022 06:05:00 - INFO - codeparrot_training - Step 14153: {'lr': 0.0004917273721480268, 'samples': 7246848, 'steps': 14153, 'loss/train': 2.1717467308044434}
-03/04/2022 06:05:03 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/04/2022 06:05:06 - INFO - codeparrot_training - Step 14154: {'lr': 0.0004917260182387545, 'samples': 7247360, 'steps': 14154, 'loss/train': 2.0319719314575195}
-03/04/2022 06:05:09 - INFO - codeparrot_training - Step 14155: {'lr': 0.0004917246642205642, 'samples': 7247872, 'steps': 14155, 'loss/train': 2.0803442001342773}
-03/04/2022 06:05:11 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/04/2022 06:05:14 - INFO - codeparrot_training - Step 14156: {'lr': 0.0004917233100934565, 'samples': 7248384, 'steps': 14156, 'loss/train': 2.020536184310913}
-03/04/2022 06:05:17 - INFO - codeparrot_training - Step 14157: {'lr': 0.0004917219558574319, 'samples': 7248896, 'steps': 14157, 'loss/train': 2.2461462020874023}
-03/04/2022 06:05:20 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/04/2022 06:05:22 - INFO - codeparrot_training - Step 14158: {'lr': 0.0004917206015124913, 'samples': 7249408, 'steps': 14158, 'loss/train': 2.004253625869751}
-03/04/2022 06:05:26 - INFO - codeparrot_training - Step 14159: {'lr': 0.000491719247058635, 'samples': 7249920, 'steps': 14159, 'loss/train': 1.481923222541809}
-03/04/2022 06:05:29 - INFO - codeparrot_training - Step 14160: {'lr': 0.0004917178924958638, 'samples': 7250432, 'steps': 14160, 'loss/train': 2.3976943492889404}
-03/04/2022 06:05:29 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/04/2022 06:05:34 - INFO - codeparrot_training - Step 14161: {'lr': 0.0004917165378241782, 'samples': 7250944, 'steps': 14161, 'loss/train': 2.197486400604248}
-03/04/2022 06:05:37 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/04/2022 06:05:40 - INFO - codeparrot_training - Step 14162: {'lr': 0.0004917151830435789, 'samples': 7251456, 'steps': 14162, 'loss/train': 0.21552236378192902}
-03/04/2022 06:05:43 - INFO - codeparrot_training - Step 14163: {'lr': 0.0004917138281540664, 'samples': 7251968, 'steps': 14163, 'loss/train': 3.6254513263702393}
-03/04/2022 06:05:46 - INFO - codeparrot_training - Step 14164: {'lr': 0.0004917124731556415, 'samples': 7252480, 'steps': 14164, 'loss/train': 2.2480087280273438}
-03/04/2022 06:05:46 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/04/2022 06:05:51 - INFO - codeparrot_training - Step 14165: {'lr': 0.0004917111180483046, 'samples': 7252992, 'steps': 14165, 'loss/train': 1.9839259386062622}
-03/04/2022 06:05:54 - INFO - codeparrot_training - Step 14166: {'lr': 0.0004917097628320564, 'samples': 7253504, 'steps': 14166, 'loss/train': 2.3352880477905273}
-03/04/2022 06:05:54 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/04/2022 06:06:00 - INFO - codeparrot_training - Step 14167: {'lr': 0.0004917084075068975, 'samples': 7254016, 'steps': 14167, 'loss/train': 4.436394214630127}
-03/04/2022 06:06:03 - INFO - codeparrot_training - Step 14168: {'lr': 0.0004917070520728286, 'samples': 7254528, 'steps': 14168, 'loss/train': 2.2190985679626465}
-03/04/2022 06:06:03 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 06:06:08 - INFO - codeparrot_training - Step 14169: {'lr': 0.0004917056965298501, 'samples': 7255040, 'steps': 14169, 'loss/train': 1.8285722732543945}
-03/04/2022 06:06:11 - INFO - codeparrot_training - Step 14170: {'lr': 0.0004917043408779629, 'samples': 7255552, 'steps': 14170, 'loss/train': 2.3963589668273926}
-03/04/2022 06:06:11 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/04/2022 06:06:17 - INFO - codeparrot_training - Step 14171: {'lr': 0.0004917029851171674, 'samples': 7256064, 'steps': 14171, 'loss/train': 1.4748644828796387}
-03/04/2022 06:06:20 - INFO - codeparrot_training - Step 14172: {'lr': 0.0004917016292474642, 'samples': 7256576, 'steps': 14172, 'loss/train': 2.2353291511535645}
-03/04/2022 06:06:20 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/04/2022 06:06:25 - INFO - codeparrot_training - Step 14173: {'lr': 0.000491700273268854, 'samples': 7257088, 'steps': 14173, 'loss/train': 1.1788721084594727}
-03/04/2022 06:06:28 - INFO - codeparrot_training - Step 14174: {'lr': 0.0004916989171813374, 'samples': 7257600, 'steps': 14174, 'loss/train': 1.5724031925201416}
-03/04/2022 06:06:30 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/04/2022 06:06:34 - INFO - codeparrot_training - Step 14175: {'lr': 0.000491697560984915, 'samples': 7258112, 'steps': 14175, 'loss/train': 2.4798543453216553}
-03/04/2022 06:06:37 - INFO - codeparrot_training - Step 14176: {'lr': 0.0004916962046795874, 'samples': 7258624, 'steps': 14176, 'loss/train': 1.9561808109283447}
-03/04/2022 06:06:39 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 06:06:42 - INFO - codeparrot_training - Step 14177: {'lr': 0.0004916948482653553, 'samples': 7259136, 'steps': 14177, 'loss/train': 1.3199094533920288}
-03/04/2022 06:06:46 - INFO - codeparrot_training - Step 14178: {'lr': 0.0004916934917422191, 'samples': 7259648, 'steps': 14178, 'loss/train': 1.6395163536071777}
-03/04/2022 06:06:47 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 06:06:51 - INFO - codeparrot_training - Step 14179: {'lr': 0.0004916921351101796, 'samples': 7260160, 'steps': 14179, 'loss/train': 2.5117416381835938}
-03/04/2022 06:06:54 - INFO - codeparrot_training - Step 14180: {'lr': 0.0004916907783692374, 'samples': 7260672, 'steps': 14180, 'loss/train': 1.5332996845245361}
-03/04/2022 06:06:56 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/04/2022 06:06:59 - INFO - codeparrot_training - Step 14181: {'lr': 0.000491689421519393, 'samples': 7261184, 'steps': 14181, 'loss/train': 1.9325716495513916}
-03/04/2022 06:07:03 - INFO - codeparrot_training - Step 14182: {'lr': 0.0004916880645606471, 'samples': 7261696, 'steps': 14182, 'loss/train': 1.5303658246994019}
-03/04/2022 06:07:04 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/04/2022 06:07:08 - INFO - codeparrot_training - Step 14183: {'lr': 0.0004916867074930002, 'samples': 7262208, 'steps': 14183, 'loss/train': 2.585043430328369}
-03/04/2022 06:07:11 - INFO - codeparrot_training - Step 14184: {'lr': 0.0004916853503164531, 'samples': 7262720, 'steps': 14184, 'loss/train': 1.9897273778915405}
-03/04/2022 06:07:13 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/04/2022 06:07:16 - INFO - codeparrot_training - Step 14185: {'lr': 0.0004916839930310063, 'samples': 7263232, 'steps': 14185, 'loss/train': 2.503770589828491}
-03/04/2022 06:07:20 - INFO - codeparrot_training - Step 14186: {'lr': 0.0004916826356366605, 'samples': 7263744, 'steps': 14186, 'loss/train': 2.0324082374572754}
-03/04/2022 06:07:22 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 06:07:25 - INFO - codeparrot_training - Step 14187: {'lr': 0.0004916812781334161, 'samples': 7264256, 'steps': 14187, 'loss/train': 1.7574560642242432}
-03/04/2022 06:07:28 - INFO - codeparrot_training - Step 14188: {'lr': 0.0004916799205212739, 'samples': 7264768, 'steps': 14188, 'loss/train': 1.8053512573242188}
-03/04/2022 06:07:30 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 06:07:33 - INFO - codeparrot_training - Step 14189: {'lr': 0.0004916785628002345, 'samples': 7265280, 'steps': 14189, 'loss/train': 1.1721782684326172}
-03/04/2022 06:07:36 - INFO - codeparrot_training - Step 14190: {'lr': 0.0004916772049702984, 'samples': 7265792, 'steps': 14190, 'loss/train': 2.601606845855713}
-03/04/2022 06:07:38 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/04/2022 06:07:42 - INFO - codeparrot_training - Step 14191: {'lr': 0.0004916758470314662, 'samples': 7266304, 'steps': 14191, 'loss/train': 2.3373591899871826}
-03/04/2022 06:07:45 - INFO - codeparrot_training - Step 14192: {'lr': 0.0004916744889837388, 'samples': 7266816, 'steps': 14192, 'loss/train': 1.7102779150009155}
-03/04/2022 06:07:47 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/04/2022 06:07:50 - INFO - codeparrot_training - Step 14193: {'lr': 0.0004916731308271165, 'samples': 7267328, 'steps': 14193, 'loss/train': 2.44355845451355}
-03/04/2022 06:07:53 - INFO - codeparrot_training - Step 14194: {'lr': 0.0004916717725616, 'samples': 7267840, 'steps': 14194, 'loss/train': 1.2849955558776855}
-03/04/2022 06:07:56 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/04/2022 06:07:59 - INFO - codeparrot_training - Step 14195: {'lr': 0.0004916704141871899, 'samples': 7268352, 'steps': 14195, 'loss/train': 2.715428113937378}
-03/04/2022 06:08:02 - INFO - codeparrot_training - Step 14196: {'lr': 0.000491669055703887, 'samples': 7268864, 'steps': 14196, 'loss/train': 1.9365639686584473}
-03/04/2022 06:08:04 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/04/2022 06:08:07 - INFO - codeparrot_training - Step 14197: {'lr': 0.0004916676971116916, 'samples': 7269376, 'steps': 14197, 'loss/train': 2.300436019897461}
-03/04/2022 06:08:10 - INFO - codeparrot_training - Step 14198: {'lr': 0.0004916663384106045, 'samples': 7269888, 'steps': 14198, 'loss/train': 0.9593050479888916}
-03/04/2022 06:08:12 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/04/2022 06:08:15 - INFO - codeparrot_training - Step 14199: {'lr': 0.0004916649796006263, 'samples': 7270400, 'steps': 14199, 'loss/train': 2.0727598667144775}
-03/04/2022 06:08:19 - INFO - codeparrot_training - Step 14200: {'lr': 0.0004916636206817575, 'samples': 7270912, 'steps': 14200, 'loss/train': 1.5179156064987183}
-03/04/2022 06:08:21 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/04/2022 06:08:24 - INFO - codeparrot_training - Step 14201: {'lr': 0.0004916622616539988, 'samples': 7271424, 'steps': 14201, 'loss/train': 1.7960783243179321}
-03/04/2022 06:08:27 - INFO - codeparrot_training - Step 14202: {'lr': 0.000491660902517351, 'samples': 7271936, 'steps': 14202, 'loss/train': 1.6204743385314941}
-03/04/2022 06:08:29 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 06:08:32 - INFO - codeparrot_training - Step 14203: {'lr': 0.0004916595432718143, 'samples': 7272448, 'steps': 14203, 'loss/train': 1.948642373085022}
-03/04/2022 06:08:35 - INFO - codeparrot_training - Step 14204: {'lr': 0.0004916581839173897, 'samples': 7272960, 'steps': 14204, 'loss/train': 2.0180249214172363}
-03/04/2022 06:08:38 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/04/2022 06:08:41 - INFO - codeparrot_training - Step 14205: {'lr': 0.0004916568244540776, 'samples': 7273472, 'steps': 14205, 'loss/train': 2.2430737018585205}
-03/04/2022 06:08:44 - INFO - codeparrot_training - Step 14206: {'lr': 0.0004916554648818787, 'samples': 7273984, 'steps': 14206, 'loss/train': 2.585120677947998}
-03/04/2022 06:08:47 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/04/2022 06:08:49 - INFO - codeparrot_training - Step 14207: {'lr': 0.0004916541052007936, 'samples': 7274496, 'steps': 14207, 'loss/train': 2.0552845001220703}
-03/04/2022 06:08:52 - INFO - codeparrot_training - Step 14208: {'lr': 0.0004916527454108227, 'samples': 7275008, 'steps': 14208, 'loss/train': 1.977124571800232}
-03/04/2022 06:08:55 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 06:08:58 - INFO - codeparrot_training - Step 14209: {'lr': 0.0004916513855119669, 'samples': 7275520, 'steps': 14209, 'loss/train': 1.8182508945465088}
-03/04/2022 06:09:01 - INFO - codeparrot_training - Step 14210: {'lr': 0.0004916500255042268, 'samples': 7276032, 'steps': 14210, 'loss/train': 1.9227043390274048}
-03/04/2022 06:09:03 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 06:09:06 - INFO - codeparrot_training - Step 14211: {'lr': 0.0004916486653876029, 'samples': 7276544, 'steps': 14211, 'loss/train': 1.5095062255859375}
-03/04/2022 06:09:09 - INFO - codeparrot_training - Step 14212: {'lr': 0.0004916473051620958, 'samples': 7277056, 'steps': 14212, 'loss/train': 1.3492730855941772}
-03/04/2022 06:09:12 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/04/2022 06:09:15 - INFO - codeparrot_training - Step 14213: {'lr': 0.0004916459448277062, 'samples': 7277568, 'steps': 14213, 'loss/train': 1.7559547424316406}
-03/04/2022 06:09:18 - INFO - codeparrot_training - Step 14214: {'lr': 0.0004916445843844346, 'samples': 7278080, 'steps': 14214, 'loss/train': 2.4339466094970703}
-03/04/2022 06:09:21 - INFO - codeparrot_training - Step 14215: {'lr': 0.0004916432238322818, 'samples': 7278592, 'steps': 14215, 'loss/train': 2.252617597579956}
-03/04/2022 06:09:21 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 06:09:26 - INFO - codeparrot_training - Step 14216: {'lr': 0.0004916418631712481, 'samples': 7279104, 'steps': 14216, 'loss/train': 1.367840051651001}
-03/04/2022 06:09:30 - INFO - codeparrot_training - Step 14217: {'lr': 0.0004916405024013344, 'samples': 7279616, 'steps': 14217, 'loss/train': 2.338386058807373}
-03/04/2022 06:09:30 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 06:09:35 - INFO - codeparrot_training - Step 14218: {'lr': 0.0004916391415225413, 'samples': 7280128, 'steps': 14218, 'loss/train': 0.27708151936531067}
-03/04/2022 06:09:38 - INFO - codeparrot_training - Step 14219: {'lr': 0.0004916377805348692, 'samples': 7280640, 'steps': 14219, 'loss/train': 1.680544376373291}
-03/04/2022 06:09:38 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/04/2022 06:09:44 - INFO - codeparrot_training - Step 14220: {'lr': 0.000491636419438319, 'samples': 7281152, 'steps': 14220, 'loss/train': 1.745717167854309}
-03/04/2022 06:09:47 - INFO - codeparrot_training - Step 14221: {'lr': 0.000491635058232891, 'samples': 7281664, 'steps': 14221, 'loss/train': 1.9172159433364868}
-03/04/2022 06:09:47 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 06:09:52 - INFO - codeparrot_training - Step 14222: {'lr': 0.0004916336969185861, 'samples': 7282176, 'steps': 14222, 'loss/train': 1.722316861152649}
-03/04/2022 06:09:55 - INFO - codeparrot_training - Step 14223: {'lr': 0.0004916323354954047, 'samples': 7282688, 'steps': 14223, 'loss/train': 2.5080134868621826}
-03/04/2022 06:09:55 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/04/2022 06:10:01 - INFO - codeparrot_training - Step 14224: {'lr': 0.0004916309739633475, 'samples': 7283200, 'steps': 14224, 'loss/train': 0.5345838069915771}
-03/04/2022 06:10:04 - INFO - codeparrot_training - Step 14225: {'lr': 0.0004916296123224151, 'samples': 7283712, 'steps': 14225, 'loss/train': 1.3750916719436646}
-03/04/2022 06:10:04 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/04/2022 06:10:09 - INFO - codeparrot_training - Step 14226: {'lr': 0.0004916282505726082, 'samples': 7284224, 'steps': 14226, 'loss/train': 2.5240821838378906}
-03/04/2022 06:10:12 - INFO - codeparrot_training - Step 14227: {'lr': 0.0004916268887139272, 'samples': 7284736, 'steps': 14227, 'loss/train': 2.396711826324463}
-03/04/2022 06:10:12 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 06:10:17 - INFO - codeparrot_training - Step 14228: {'lr': 0.000491625526746373, 'samples': 7285248, 'steps': 14228, 'loss/train': 1.888750672340393}
-03/04/2022 06:10:20 - INFO - codeparrot_training - Step 14229: {'lr': 0.000491624164669946, 'samples': 7285760, 'steps': 14229, 'loss/train': 0.5199436545372009}
-03/04/2022 06:10:20 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/04/2022 06:10:26 - INFO - codeparrot_training - Step 14230: {'lr': 0.0004916228024846469, 'samples': 7286272, 'steps': 14230, 'loss/train': 1.2509794235229492}
-03/04/2022 06:10:28 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/04/2022 06:10:31 - INFO - codeparrot_training - Step 14231: {'lr': 0.0004916214401904763, 'samples': 7286784, 'steps': 14231, 'loss/train': 1.9572216272354126}
-03/04/2022 06:10:34 - INFO - codeparrot_training - Step 14232: {'lr': 0.0004916200777874348, 'samples': 7287296, 'steps': 14232, 'loss/train': 1.566149353981018}
-03/04/2022 06:10:37 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/04/2022 06:10:40 - INFO - codeparrot_training - Step 14233: {'lr': 0.000491618715275523, 'samples': 7287808, 'steps': 14233, 'loss/train': 1.4629558324813843}
-03/04/2022 06:10:43 - INFO - codeparrot_training - Step 14234: {'lr': 0.0004916173526547415, 'samples': 7288320, 'steps': 14234, 'loss/train': 1.4451991319656372}
-03/04/2022 06:10:46 - INFO - codeparrot_training - Step 14235: {'lr': 0.000491615989925091, 'samples': 7288832, 'steps': 14235, 'loss/train': 4.627155303955078}
-03/04/2022 06:10:47 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/04/2022 06:10:51 - INFO - codeparrot_training - Step 14236: {'lr': 0.0004916146270865721, 'samples': 7289344, 'steps': 14236, 'loss/train': 2.0916194915771484}
-03/04/2022 06:10:54 - INFO - codeparrot_training - Step 14237: {'lr': 0.0004916132641391854, 'samples': 7289856, 'steps': 14237, 'loss/train': 1.862131953239441}
-03/04/2022 06:10:55 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 06:11:00 - INFO - codeparrot_training - Step 14238: {'lr': 0.0004916119010829314, 'samples': 7290368, 'steps': 14238, 'loss/train': 1.8892422914505005}
-03/04/2022 06:11:03 - INFO - codeparrot_training - Step 14239: {'lr': 0.0004916105379178108, 'samples': 7290880, 'steps': 14239, 'loss/train': 2.194267988204956}
-03/04/2022 06:11:04 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/04/2022 06:11:08 - INFO - codeparrot_training - Step 14240: {'lr': 0.0004916091746438243, 'samples': 7291392, 'steps': 14240, 'loss/train': 0.744387686252594}
-03/04/2022 06:11:11 - INFO - codeparrot_training - Step 14241: {'lr': 0.0004916078112609724, 'samples': 7291904, 'steps': 14241, 'loss/train': 2.1298577785491943}
-03/04/2022 06:11:12 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 06:11:17 - INFO - codeparrot_training - Step 14242: {'lr': 0.0004916064477692557, 'samples': 7292416, 'steps': 14242, 'loss/train': 2.0762457847595215}
-03/04/2022 06:11:20 - INFO - codeparrot_training - Step 14243: {'lr': 0.0004916050841686748, 'samples': 7292928, 'steps': 14243, 'loss/train': 1.1841678619384766}
-03/04/2022 06:11:21 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/04/2022 06:11:25 - INFO - codeparrot_training - Step 14244: {'lr': 0.0004916037204592306, 'samples': 7293440, 'steps': 14244, 'loss/train': 2.080345392227173}
-03/04/2022 06:11:28 - INFO - codeparrot_training - Step 14245: {'lr': 0.0004916023566409233, 'samples': 7293952, 'steps': 14245, 'loss/train': 1.7572335004806519}
-03/04/2022 06:11:29 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 06:11:34 - INFO - codeparrot_training - Step 14246: {'lr': 0.0004916009927137538, 'samples': 7294464, 'steps': 14246, 'loss/train': 2.3588881492614746}
-03/04/2022 06:11:37 - INFO - codeparrot_training - Step 14247: {'lr': 0.0004915996286777226, 'samples': 7294976, 'steps': 14247, 'loss/train': 1.1647560596466064}
-03/04/2022 06:11:38 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/04/2022 06:11:42 - INFO - codeparrot_training - Step 14248: {'lr': 0.0004915982645328304, 'samples': 7295488, 'steps': 14248, 'loss/train': 0.579420268535614}
-03/04/2022 06:11:45 - INFO - codeparrot_training - Step 14249: {'lr': 0.0004915969002790777, 'samples': 7296000, 'steps': 14249, 'loss/train': 1.8022586107254028}
-03/04/2022 06:11:46 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 06:11:50 - INFO - codeparrot_training - Step 14250: {'lr': 0.0004915955359164651, 'samples': 7296512, 'steps': 14250, 'loss/train': 0.6959905028343201}
-03/04/2022 06:11:54 - INFO - codeparrot_training - Step 14251: {'lr': 0.0004915941714449933, 'samples': 7297024, 'steps': 14251, 'loss/train': 1.3195152282714844}
-03/04/2022 06:11:54 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/04/2022 06:11:59 - INFO - codeparrot_training - Step 14252: {'lr': 0.000491592806864663, 'samples': 7297536, 'steps': 14252, 'loss/train': 1.6952584981918335}
-03/04/2022 06:12:02 - INFO - codeparrot_training - Step 14253: {'lr': 0.0004915914421754746, 'samples': 7298048, 'steps': 14253, 'loss/train': 1.9855080842971802}
-03/04/2022 06:12:03 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 06:12:07 - INFO - codeparrot_training - Step 14254: {'lr': 0.0004915900773774289, 'samples': 7298560, 'steps': 14254, 'loss/train': 0.6670559644699097}
-03/04/2022 06:12:11 - INFO - codeparrot_training - Step 14255: {'lr': 0.0004915887124705263, 'samples': 7299072, 'steps': 14255, 'loss/train': 2.2182819843292236}
-03/04/2022 06:12:11 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/04/2022 06:12:16 - INFO - codeparrot_training - Step 14256: {'lr': 0.0004915873474547677, 'samples': 7299584, 'steps': 14256, 'loss/train': 1.8272300958633423}
-03/04/2022 06:12:19 - INFO - codeparrot_training - Step 14257: {'lr': 0.0004915859823301535, 'samples': 7300096, 'steps': 14257, 'loss/train': 1.8698537349700928}
-03/04/2022 06:12:19 - INFO - codeparrot_training - Skipping example with length 1010 (seq_length=1024)
-03/04/2022 06:12:24 - INFO - codeparrot_training - Step 14258: {'lr': 0.0004915846170966845, 'samples': 7300608, 'steps': 14258, 'loss/train': 2.0088584423065186}
-03/04/2022 06:12:27 - INFO - codeparrot_training - Step 14259: {'lr': 0.000491583251754361, 'samples': 7301120, 'steps': 14259, 'loss/train': 1.4501758813858032}
-03/04/2022 06:12:28 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/04/2022 06:12:33 - INFO - codeparrot_training - Step 14260: {'lr': 0.0004915818863031839, 'samples': 7301632, 'steps': 14260, 'loss/train': 1.3482004404067993}
-03/04/2022 06:12:36 - INFO - codeparrot_training - Step 14261: {'lr': 0.0004915805207431537, 'samples': 7302144, 'steps': 14261, 'loss/train': 0.8652366995811462}
-03/04/2022 06:12:36 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/04/2022 06:12:41 - INFO - codeparrot_training - Step 14262: {'lr': 0.0004915791550742712, 'samples': 7302656, 'steps': 14262, 'loss/train': 1.5553480386734009}
-03/04/2022 06:12:44 - INFO - codeparrot_training - Step 14263: {'lr': 0.0004915777892965368, 'samples': 7303168, 'steps': 14263, 'loss/train': 1.4239702224731445}
-03/04/2022 06:12:44 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/04/2022 06:12:49 - INFO - codeparrot_training - Step 14264: {'lr': 0.0004915764234099511, 'samples': 7303680, 'steps': 14264, 'loss/train': 2.2353384494781494}
-03/04/2022 06:12:53 - INFO - codeparrot_training - Step 14265: {'lr': 0.0004915750574145148, 'samples': 7304192, 'steps': 14265, 'loss/train': 2.2278833389282227}
-03/04/2022 06:12:53 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 06:12:58 - INFO - codeparrot_training - Step 14266: {'lr': 0.0004915736913102285, 'samples': 7304704, 'steps': 14266, 'loss/train': 1.1661616563796997}
-03/04/2022 06:13:01 - INFO - codeparrot_training - Step 14267: {'lr': 0.0004915723250970928, 'samples': 7305216, 'steps': 14267, 'loss/train': 2.3178136348724365}
-03/04/2022 06:13:02 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/04/2022 06:13:06 - INFO - codeparrot_training - Step 14268: {'lr': 0.0004915709587751084, 'samples': 7305728, 'steps': 14268, 'loss/train': 2.063960552215576}
-03/04/2022 06:13:10 - INFO - codeparrot_training - Step 14269: {'lr': 0.0004915695923442759, 'samples': 7306240, 'steps': 14269, 'loss/train': 2.1381986141204834}
-03/04/2022 06:13:10 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/04/2022 06:13:15 - INFO - codeparrot_training - Step 14270: {'lr': 0.0004915682258045958, 'samples': 7306752, 'steps': 14270, 'loss/train': 4.605743408203125}
-03/04/2022 06:13:18 - INFO - codeparrot_training - Step 14271: {'lr': 0.0004915668591560688, 'samples': 7307264, 'steps': 14271, 'loss/train': 1.6811282634735107}
-03/04/2022 06:13:19 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/04/2022 06:13:24 - INFO - codeparrot_training - Step 14272: {'lr': 0.0004915654923986955, 'samples': 7307776, 'steps': 14272, 'loss/train': 0.7460503578186035}
-03/04/2022 06:13:27 - INFO - codeparrot_training - Step 14273: {'lr': 0.0004915641255324764, 'samples': 7308288, 'steps': 14273, 'loss/train': 2.21169376373291}
-03/04/2022 06:13:30 - INFO - codeparrot_training - Step 14274: {'lr': 0.0004915627585574124, 'samples': 7308800, 'steps': 14274, 'loss/train': 1.7855303287506104}
-03/04/2022 06:13:30 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/04/2022 06:13:35 - INFO - codeparrot_training - Step 14275: {'lr': 0.0004915613914735038, 'samples': 7309312, 'steps': 14275, 'loss/train': 1.5133812427520752}
-03/04/2022 06:13:39 - INFO - codeparrot_training - Step 14276: {'lr': 0.0004915600242807516, 'samples': 7309824, 'steps': 14276, 'loss/train': 1.6044930219650269}
-03/04/2022 06:13:39 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/04/2022 06:13:44 - INFO - codeparrot_training - Step 14277: {'lr': 0.000491558656979156, 'samples': 7310336, 'steps': 14277, 'loss/train': 1.647684931755066}
-03/04/2022 06:13:47 - INFO - codeparrot_training - Step 14278: {'lr': 0.0004915572895687179, 'samples': 7310848, 'steps': 14278, 'loss/train': 2.7551302909851074}
-03/04/2022 06:13:48 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/04/2022 06:13:52 - INFO - codeparrot_training - Step 14279: {'lr': 0.0004915559220494376, 'samples': 7311360, 'steps': 14279, 'loss/train': 1.898055911064148}
-03/04/2022 06:13:56 - INFO - codeparrot_training - Step 14280: {'lr': 0.0004915545544213161, 'samples': 7311872, 'steps': 14280, 'loss/train': 2.357741117477417}
-03/04/2022 06:13:56 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/04/2022 06:14:01 - INFO - codeparrot_training - Step 14281: {'lr': 0.0004915531866843539, 'samples': 7312384, 'steps': 14281, 'loss/train': 1.879067301750183}
-03/04/2022 06:14:04 - INFO - codeparrot_training - Step 14282: {'lr': 0.0004915518188385514, 'samples': 7312896, 'steps': 14282, 'loss/train': 2.2388193607330322}
-03/04/2022 06:14:04 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/04/2022 06:14:09 - INFO - codeparrot_training - Step 14283: {'lr': 0.0004915504508839095, 'samples': 7313408, 'steps': 14283, 'loss/train': 3.1415860652923584}
-03/04/2022 06:14:12 - INFO - codeparrot_training - Step 14284: {'lr': 0.0004915490828204287, 'samples': 7313920, 'steps': 14284, 'loss/train': 1.9163907766342163}
-03/04/2022 06:14:13 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/04/2022 06:14:18 - INFO - codeparrot_training - Step 14285: {'lr': 0.0004915477146481095, 'samples': 7314432, 'steps': 14285, 'loss/train': 1.63360595703125}
-03/04/2022 06:14:21 - INFO - codeparrot_training - Step 14286: {'lr': 0.0004915463463669527, 'samples': 7314944, 'steps': 14286, 'loss/train': 1.9109654426574707}
-03/04/2022 06:14:21 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/04/2022 06:14:26 - INFO - codeparrot_training - Step 14287: {'lr': 0.0004915449779769589, 'samples': 7315456, 'steps': 14287, 'loss/train': 2.6195859909057617}
-03/04/2022 06:14:29 - INFO - codeparrot_training - Step 14288: {'lr': 0.0004915436094781285, 'samples': 7315968, 'steps': 14288, 'loss/train': 2.620976209640503}
-03/04/2022 06:14:30 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 06:14:34 - INFO - codeparrot_training - Step 14289: {'lr': 0.0004915422408704624, 'samples': 7316480, 'steps': 14289, 'loss/train': 1.7827203273773193}
-03/04/2022 06:14:38 - INFO - codeparrot_training - Step 14290: {'lr': 0.0004915408721539612, 'samples': 7316992, 'steps': 14290, 'loss/train': 1.7861549854278564}
-03/04/2022 06:14:38 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/04/2022 06:14:43 - INFO - codeparrot_training - Step 14291: {'lr': 0.0004915395033286251, 'samples': 7317504, 'steps': 14291, 'loss/train': 2.223322868347168}
-03/04/2022 06:14:46 - INFO - codeparrot_training - Step 14292: {'lr': 0.0004915381343944552, 'samples': 7318016, 'steps': 14292, 'loss/train': 2.003300905227661}
-03/04/2022 06:14:46 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/04/2022 06:14:51 - INFO - codeparrot_training - Step 14293: {'lr': 0.0004915367653514521, 'samples': 7318528, 'steps': 14293, 'loss/train': 2.240624189376831}
-03/04/2022 06:14:54 - INFO - codeparrot_training - Step 14294: {'lr': 0.0004915353961996161, 'samples': 7319040, 'steps': 14294, 'loss/train': 1.0146031379699707}
-03/04/2022 06:14:55 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/04/2022 06:15:00 - INFO - codeparrot_training - Step 14295: {'lr': 0.000491534026938948, 'samples': 7319552, 'steps': 14295, 'loss/train': 2.0750718116760254}
-03/04/2022 06:15:03 - INFO - codeparrot_training - Step 14296: {'lr': 0.0004915326575694484, 'samples': 7320064, 'steps': 14296, 'loss/train': 1.5163726806640625}
-03/04/2022 06:15:03 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/04/2022 06:15:08 - INFO - codeparrot_training - Step 14297: {'lr': 0.0004915312880911178, 'samples': 7320576, 'steps': 14297, 'loss/train': 1.3846347332000732}
-03/04/2022 06:15:11 - INFO - codeparrot_training - Step 14298: {'lr': 0.000491529918503957, 'samples': 7321088, 'steps': 14298, 'loss/train': 1.816333293914795}
-03/04/2022 06:15:12 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 06:15:17 - INFO - codeparrot_training - Step 14299: {'lr': 0.0004915285488079666, 'samples': 7321600, 'steps': 14299, 'loss/train': 1.5736254453659058}
-03/04/2022 06:15:20 - INFO - codeparrot_training - Step 14300: {'lr': 0.0004915271790031471, 'samples': 7322112, 'steps': 14300, 'loss/train': 2.455777168273926}
-03/04/2022 06:15:20 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 06:15:25 - INFO - codeparrot_training - Step 14301: {'lr': 0.0004915258090894993, 'samples': 7322624, 'steps': 14301, 'loss/train': 2.395232915878296}
-03/04/2022 06:15:28 - INFO - codeparrot_training - Step 14302: {'lr': 0.0004915244390670236, 'samples': 7323136, 'steps': 14302, 'loss/train': 1.8394737243652344}
-03/04/2022 06:15:28 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/04/2022 06:15:33 - INFO - codeparrot_training - Step 14303: {'lr': 0.0004915230689357206, 'samples': 7323648, 'steps': 14303, 'loss/train': 1.1850640773773193}
-03/04/2022 06:15:37 - INFO - codeparrot_training - Step 14304: {'lr': 0.0004915216986955913, 'samples': 7324160, 'steps': 14304, 'loss/train': 2.038642168045044}
-03/04/2022 06:15:37 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 06:15:42 - INFO - codeparrot_training - Step 14305: {'lr': 0.0004915203283466359, 'samples': 7324672, 'steps': 14305, 'loss/train': 1.9360450506210327}
-03/04/2022 06:15:45 - INFO - codeparrot_training - Step 14306: {'lr': 0.0004915189578888552, 'samples': 7325184, 'steps': 14306, 'loss/train': 1.3032705783843994}
-03/04/2022 06:15:45 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/04/2022 06:15:50 - INFO - codeparrot_training - Step 14307: {'lr': 0.0004915175873222497, 'samples': 7325696, 'steps': 14307, 'loss/train': 1.4848895072937012}
-03/04/2022 06:15:54 - INFO - codeparrot_training - Step 14308: {'lr': 0.0004915162166468201, 'samples': 7326208, 'steps': 14308, 'loss/train': 1.6991854906082153}
-03/04/2022 06:15:55 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/04/2022 06:15:59 - INFO - codeparrot_training - Step 14309: {'lr': 0.0004915148458625671, 'samples': 7326720, 'steps': 14309, 'loss/train': 2.7459051609039307}
-03/04/2022 06:16:02 - INFO - codeparrot_training - Step 14310: {'lr': 0.0004915134749694912, 'samples': 7327232, 'steps': 14310, 'loss/train': 1.379279613494873}
-03/04/2022 06:16:03 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/04/2022 06:16:07 - INFO - codeparrot_training - Step 14311: {'lr': 0.000491512103967593, 'samples': 7327744, 'steps': 14311, 'loss/train': 2.0206189155578613}
-03/04/2022 06:16:10 - INFO - codeparrot_training - Step 14312: {'lr': 0.0004915107328568733, 'samples': 7328256, 'steps': 14312, 'loss/train': 1.9697151184082031}
-03/04/2022 06:16:11 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 06:16:16 - INFO - codeparrot_training - Step 14313: {'lr': 0.0004915093616373326, 'samples': 7328768, 'steps': 14313, 'loss/train': 0.49298498034477234}
-03/04/2022 06:16:19 - INFO - codeparrot_training - Step 14314: {'lr': 0.0004915079903089714, 'samples': 7329280, 'steps': 14314, 'loss/train': 1.997862696647644}
-03/04/2022 06:16:20 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/04/2022 06:16:24 - INFO - codeparrot_training - Step 14315: {'lr': 0.0004915066188717905, 'samples': 7329792, 'steps': 14315, 'loss/train': 2.2948365211486816}
-03/04/2022 06:16:27 - INFO - codeparrot_training - Step 14316: {'lr': 0.0004915052473257904, 'samples': 7330304, 'steps': 14316, 'loss/train': 2.6600778102874756}
-03/04/2022 06:16:28 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/04/2022 06:16:32 - INFO - codeparrot_training - Step 14317: {'lr': 0.0004915038756709717, 'samples': 7330816, 'steps': 14317, 'loss/train': 2.134594678878784}
-03/04/2022 06:16:35 - INFO - codeparrot_training - Step 14318: {'lr': 0.0004915025039073352, 'samples': 7331328, 'steps': 14318, 'loss/train': 2.041787624359131}
-03/04/2022 06:16:36 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 06:16:41 - INFO - codeparrot_training - Step 14319: {'lr': 0.0004915011320348814, 'samples': 7331840, 'steps': 14319, 'loss/train': 2.0761001110076904}
-03/04/2022 06:16:44 - INFO - codeparrot_training - Step 14320: {'lr': 0.0004914997600536108, 'samples': 7332352, 'steps': 14320, 'loss/train': 1.800355315208435}
-03/04/2022 06:16:45 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 06:16:49 - INFO - codeparrot_training - Step 14321: {'lr': 0.0004914983879635242, 'samples': 7332864, 'steps': 14321, 'loss/train': 2.8229751586914062}
-03/04/2022 06:16:52 - INFO - codeparrot_training - Step 14322: {'lr': 0.0004914970157646222, 'samples': 7333376, 'steps': 14322, 'loss/train': 2.1409029960632324}
-03/04/2022 06:16:53 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/04/2022 06:16:57 - INFO - codeparrot_training - Step 14323: {'lr': 0.0004914956434569054, 'samples': 7333888, 'steps': 14323, 'loss/train': 2.2634387016296387}
-03/04/2022 06:17:01 - INFO - codeparrot_training - Step 14324: {'lr': 0.0004914942710403743, 'samples': 7334400, 'steps': 14324, 'loss/train': 1.7075189352035522}
-03/04/2022 06:17:01 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/04/2022 06:17:06 - INFO - codeparrot_training - Step 14325: {'lr': 0.0004914928985150296, 'samples': 7334912, 'steps': 14325, 'loss/train': 1.6243937015533447}
-03/04/2022 06:17:09 - INFO - codeparrot_training - Step 14326: {'lr': 0.0004914915258808719, 'samples': 7335424, 'steps': 14326, 'loss/train': 1.5995562076568604}
-03/04/2022 06:17:10 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/04/2022 06:17:14 - INFO - codeparrot_training - Step 14327: {'lr': 0.0004914901531379019, 'samples': 7335936, 'steps': 14327, 'loss/train': 1.8039770126342773}
-03/04/2022 06:17:17 - INFO - codeparrot_training - Step 14328: {'lr': 0.0004914887802861201, 'samples': 7336448, 'steps': 14328, 'loss/train': 1.8638969659805298}
-03/04/2022 06:17:18 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/04/2022 06:17:23 - INFO - codeparrot_training - Step 14329: {'lr': 0.0004914874073255273, 'samples': 7336960, 'steps': 14329, 'loss/train': 2.4733259677886963}
-03/04/2022 06:17:26 - INFO - codeparrot_training - Step 14330: {'lr': 0.0004914860342561239, 'samples': 7337472, 'steps': 14330, 'loss/train': 2.0416102409362793}
-03/04/2022 06:17:26 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 06:17:31 - INFO - codeparrot_training - Step 14331: {'lr': 0.0004914846610779107, 'samples': 7337984, 'steps': 14331, 'loss/train': 2.267395257949829}
-03/04/2022 06:17:34 - INFO - codeparrot_training - Step 14332: {'lr': 0.0004914832877908881, 'samples': 7338496, 'steps': 14332, 'loss/train': 1.6219416856765747}
-03/04/2022 06:17:35 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 06:17:40 - INFO - codeparrot_training - Step 14333: {'lr': 0.0004914819143950571, 'samples': 7339008, 'steps': 14333, 'loss/train': 3.81795597076416}
-03/04/2022 06:17:43 - INFO - codeparrot_training - Step 14334: {'lr': 0.0004914805408904179, 'samples': 7339520, 'steps': 14334, 'loss/train': 1.8976693153381348}
-03/04/2022 06:17:44 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/04/2022 06:17:48 - INFO - codeparrot_training - Step 14335: {'lr': 0.0004914791672769713, 'samples': 7340032, 'steps': 14335, 'loss/train': 2.490804672241211}
-03/04/2022 06:17:52 - INFO - codeparrot_training - Step 14336: {'lr': 0.000491477793554718, 'samples': 7340544, 'steps': 14336, 'loss/train': 2.0633811950683594}
-03/04/2022 06:17:53 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 06:17:57 - INFO - codeparrot_training - Step 14337: {'lr': 0.0004914764197236584, 'samples': 7341056, 'steps': 14337, 'loss/train': 2.054426431655884}
-03/04/2022 06:18:00 - INFO - codeparrot_training - Step 14338: {'lr': 0.0004914750457837933, 'samples': 7341568, 'steps': 14338, 'loss/train': 1.7547253370285034}
-03/04/2022 06:18:01 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/04/2022 06:18:05 - INFO - codeparrot_training - Step 14339: {'lr': 0.0004914736717351233, 'samples': 7342080, 'steps': 14339, 'loss/train': 2.154184341430664}
-03/04/2022 06:18:08 - INFO - codeparrot_training - Step 14340: {'lr': 0.000491472297577649, 'samples': 7342592, 'steps': 14340, 'loss/train': 2.188509464263916}
-03/04/2022 06:18:10 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/04/2022 06:18:14 - INFO - codeparrot_training - Step 14341: {'lr': 0.000491470923311371, 'samples': 7343104, 'steps': 14341, 'loss/train': 3.1184048652648926}
-03/04/2022 06:18:17 - INFO - codeparrot_training - Step 14342: {'lr': 0.0004914695489362899, 'samples': 7343616, 'steps': 14342, 'loss/train': 2.1223978996276855}
-03/04/2022 06:18:18 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/04/2022 06:18:22 - INFO - codeparrot_training - Step 14343: {'lr': 0.0004914681744524064, 'samples': 7344128, 'steps': 14343, 'loss/train': 2.2126879692077637}
-03/04/2022 06:18:25 - INFO - codeparrot_training - Step 14344: {'lr': 0.0004914667998597211, 'samples': 7344640, 'steps': 14344, 'loss/train': 1.7135676145553589}
-03/04/2022 06:18:26 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 06:18:31 - INFO - codeparrot_training - Step 14345: {'lr': 0.0004914654251582344, 'samples': 7345152, 'steps': 14345, 'loss/train': 1.2409839630126953}
-03/04/2022 06:18:34 - INFO - codeparrot_training - Step 14346: {'lr': 0.0004914640503479473, 'samples': 7345664, 'steps': 14346, 'loss/train': 2.0488991737365723}
-03/04/2022 06:18:35 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 06:18:39 - INFO - codeparrot_training - Step 14347: {'lr': 0.0004914626754288601, 'samples': 7346176, 'steps': 14347, 'loss/train': 1.6215101480484009}
-03/04/2022 06:18:42 - INFO - codeparrot_training - Step 14348: {'lr': 0.0004914613004009736, 'samples': 7346688, 'steps': 14348, 'loss/train': 2.105660915374756}
-03/04/2022 06:18:43 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 06:18:48 - INFO - codeparrot_training - Step 14349: {'lr': 0.0004914599252642884, 'samples': 7347200, 'steps': 14349, 'loss/train': 1.9093232154846191}
-03/04/2022 06:18:51 - INFO - codeparrot_training - Step 14350: {'lr': 0.000491458550018805, 'samples': 7347712, 'steps': 14350, 'loss/train': 2.3278238773345947}
-03/04/2022 06:18:53 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/04/2022 06:18:56 - INFO - codeparrot_training - Step 14351: {'lr': 0.0004914571746645242, 'samples': 7348224, 'steps': 14351, 'loss/train': 1.9460830688476562}
-03/04/2022 06:18:59 - INFO - codeparrot_training - Step 14352: {'lr': 0.0004914557992014465, 'samples': 7348736, 'steps': 14352, 'loss/train': 1.0790350437164307}
-03/04/2022 06:19:01 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/04/2022 06:19:04 - INFO - codeparrot_training - Step 14353: {'lr': 0.0004914544236295725, 'samples': 7349248, 'steps': 14353, 'loss/train': 1.802169680595398}
-03/04/2022 06:19:08 - INFO - codeparrot_training - Step 14354: {'lr': 0.0004914530479489029, 'samples': 7349760, 'steps': 14354, 'loss/train': 1.9990493059158325}
-03/04/2022 06:19:10 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/04/2022 06:19:13 - INFO - codeparrot_training - Step 14355: {'lr': 0.0004914516721594382, 'samples': 7350272, 'steps': 14355, 'loss/train': 1.7308757305145264}
-03/04/2022 06:19:16 - INFO - codeparrot_training - Step 14356: {'lr': 0.0004914502962611792, 'samples': 7350784, 'steps': 14356, 'loss/train': 1.7645049095153809}
-03/04/2022 06:19:18 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 06:19:21 - INFO - codeparrot_training - Step 14357: {'lr': 0.0004914489202541264, 'samples': 7351296, 'steps': 14357, 'loss/train': 2.67923903465271}
-03/04/2022 06:19:24 - INFO - codeparrot_training - Step 14358: {'lr': 0.0004914475441382804, 'samples': 7351808, 'steps': 14358, 'loss/train': 2.2711639404296875}
-03/04/2022 06:19:26 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/04/2022 06:19:30 - INFO - codeparrot_training - Step 14359: {'lr': 0.0004914461679136419, 'samples': 7352320, 'steps': 14359, 'loss/train': 1.8810752630233765}
-03/04/2022 06:19:33 - INFO - codeparrot_training - Step 14360: {'lr': 0.0004914447915802115, 'samples': 7352832, 'steps': 14360, 'loss/train': 1.8955930471420288}
-03/04/2022 06:19:35 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 06:19:38 - INFO - codeparrot_training - Step 14361: {'lr': 0.0004914434151379898, 'samples': 7353344, 'steps': 14361, 'loss/train': 1.7055202722549438}
-03/04/2022 06:19:41 - INFO - codeparrot_training - Step 14362: {'lr': 0.0004914420385869773, 'samples': 7353856, 'steps': 14362, 'loss/train': 2.1090762615203857}
-03/04/2022 06:19:43 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/04/2022 06:19:47 - INFO - codeparrot_training - Step 14363: {'lr': 0.0004914406619271749, 'samples': 7354368, 'steps': 14363, 'loss/train': 0.24174199998378754}
-03/04/2022 06:19:50 - INFO - codeparrot_training - Step 14364: {'lr': 0.0004914392851585829, 'samples': 7354880, 'steps': 14364, 'loss/train': 2.1869916915893555}
-03/04/2022 06:19:51 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/04/2022 06:19:55 - INFO - codeparrot_training - Step 14365: {'lr': 0.0004914379082812023, 'samples': 7355392, 'steps': 14365, 'loss/train': 3.3959670066833496}
-03/04/2022 06:19:58 - INFO - codeparrot_training - Step 14366: {'lr': 0.0004914365312950333, 'samples': 7355904, 'steps': 14366, 'loss/train': 3.0393214225769043}
-03/04/2022 06:19:59 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 06:20:03 - INFO - codeparrot_training - Step 14367: {'lr': 0.0004914351542000768, 'samples': 7356416, 'steps': 14367, 'loss/train': 1.400913119316101}
-03/04/2022 06:20:07 - INFO - codeparrot_training - Step 14368: {'lr': 0.0004914337769963334, 'samples': 7356928, 'steps': 14368, 'loss/train': 1.390156626701355}
-03/04/2022 06:20:08 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 06:20:12 - INFO - codeparrot_training - Step 14369: {'lr': 0.0004914323996838036, 'samples': 7357440, 'steps': 14369, 'loss/train': 2.0969855785369873}
-03/04/2022 06:20:15 - INFO - codeparrot_training - Step 14370: {'lr': 0.0004914310222624881, 'samples': 7357952, 'steps': 14370, 'loss/train': 1.926300048828125}
-03/04/2022 06:20:17 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 06:20:20 - INFO - codeparrot_training - Step 14371: {'lr': 0.0004914296447323875, 'samples': 7358464, 'steps': 14371, 'loss/train': 1.7234209775924683}
-03/04/2022 06:20:23 - INFO - codeparrot_training - Step 14372: {'lr': 0.0004914282670935025, 'samples': 7358976, 'steps': 14372, 'loss/train': 1.935867428779602}
-03/04/2022 06:20:25 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/04/2022 06:20:29 - INFO - codeparrot_training - Step 14373: {'lr': 0.0004914268893458336, 'samples': 7359488, 'steps': 14373, 'loss/train': 1.7760341167449951}
-03/04/2022 06:20:32 - INFO - codeparrot_training - Step 14374: {'lr': 0.0004914255114893814, 'samples': 7360000, 'steps': 14374, 'loss/train': 1.8799419403076172}
-03/04/2022 06:20:34 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 06:20:37 - INFO - codeparrot_training - Step 14375: {'lr': 0.0004914241335241467, 'samples': 7360512, 'steps': 14375, 'loss/train': 0.5779846906661987}
-03/04/2022 06:20:40 - INFO - codeparrot_training - Step 14376: {'lr': 0.0004914227554501299, 'samples': 7361024, 'steps': 14376, 'loss/train': 1.251105546951294}
-03/04/2022 06:20:42 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/04/2022 06:20:45 - INFO - codeparrot_training - Step 14377: {'lr': 0.0004914213772673319, 'samples': 7361536, 'steps': 14377, 'loss/train': 2.1097686290740967}
-03/04/2022 06:20:49 - INFO - codeparrot_training - Step 14378: {'lr': 0.0004914199989757529, 'samples': 7362048, 'steps': 14378, 'loss/train': 1.9985071420669556}
-03/04/2022 06:20:50 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/04/2022 06:20:54 - INFO - codeparrot_training - Step 14379: {'lr': 0.000491418620575394, 'samples': 7362560, 'steps': 14379, 'loss/train': 2.482874631881714}
-03/04/2022 06:20:57 - INFO - codeparrot_training - Step 14380: {'lr': 0.0004914172420662556, 'samples': 7363072, 'steps': 14380, 'loss/train': 0.28944510221481323}
-03/04/2022 06:20:59 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 06:21:03 - INFO - codeparrot_training - Step 14381: {'lr': 0.0004914158634483381, 'samples': 7363584, 'steps': 14381, 'loss/train': 1.7732185125350952}
-03/04/2022 06:21:06 - INFO - codeparrot_training - Step 14382: {'lr': 0.0004914144847216425, 'samples': 7364096, 'steps': 14382, 'loss/train': 2.2940447330474854}
-03/04/2022 06:21:07 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/04/2022 06:21:11 - INFO - codeparrot_training - Step 14383: {'lr': 0.0004914131058861693, 'samples': 7364608, 'steps': 14383, 'loss/train': 1.4175775051116943}
-03/04/2022 06:21:14 - INFO - codeparrot_training - Step 14384: {'lr': 0.000491411726941919, 'samples': 7365120, 'steps': 14384, 'loss/train': 1.9683401584625244}
-03/04/2022 06:21:16 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 06:21:19 - INFO - codeparrot_training - Step 14385: {'lr': 0.0004914103478888922, 'samples': 7365632, 'steps': 14385, 'loss/train': 1.910413146018982}
-03/04/2022 06:21:22 - INFO - codeparrot_training - Step 14386: {'lr': 0.0004914089687270898, 'samples': 7366144, 'steps': 14386, 'loss/train': 1.3410594463348389}
-03/04/2022 06:21:24 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/04/2022 06:21:28 - INFO - codeparrot_training - Step 14387: {'lr': 0.0004914075894565122, 'samples': 7366656, 'steps': 14387, 'loss/train': 2.0387821197509766}
-03/04/2022 06:21:31 - INFO - codeparrot_training - Step 14388: {'lr': 0.00049140621007716, 'samples': 7367168, 'steps': 14388, 'loss/train': 1.1221325397491455}
-03/04/2022 06:21:32 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/04/2022 06:21:36 - INFO - codeparrot_training - Step 14389: {'lr': 0.0004914048305890339, 'samples': 7367680, 'steps': 14389, 'loss/train': 2.5614843368530273}
-03/04/2022 06:21:39 - INFO - codeparrot_training - Step 14390: {'lr': 0.0004914034509921345, 'samples': 7368192, 'steps': 14390, 'loss/train': 0.7834432721138}
-03/04/2022 06:21:41 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 06:21:45 - INFO - codeparrot_training - Step 14391: {'lr': 0.0004914020712864626, 'samples': 7368704, 'steps': 14391, 'loss/train': 2.189486265182495}
-03/04/2022 06:21:48 - INFO - codeparrot_training - Step 14392: {'lr': 0.0004914006914720184, 'samples': 7369216, 'steps': 14392, 'loss/train': 2.0616707801818848}
-03/04/2022 06:21:49 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 06:21:53 - INFO - codeparrot_training - Step 14393: {'lr': 0.0004913993115488029, 'samples': 7369728, 'steps': 14393, 'loss/train': 2.0021705627441406}
-03/04/2022 06:21:56 - INFO - codeparrot_training - Step 14394: {'lr': 0.0004913979315168167, 'samples': 7370240, 'steps': 14394, 'loss/train': 1.989573359489441}
-03/04/2022 06:21:57 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/04/2022 06:22:01 - INFO - codeparrot_training - Step 14395: {'lr': 0.0004913965513760601, 'samples': 7370752, 'steps': 14395, 'loss/train': 2.3525359630584717}
-03/04/2022 06:22:05 - INFO - codeparrot_training - Step 14396: {'lr': 0.0004913951711265341, 'samples': 7371264, 'steps': 14396, 'loss/train': 1.826217532157898}
-03/04/2022 06:22:06 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/04/2022 06:22:10 - INFO - codeparrot_training - Step 14397: {'lr': 0.0004913937907682391, 'samples': 7371776, 'steps': 14397, 'loss/train': 0.41573911905288696}
-03/04/2022 06:22:13 - INFO - codeparrot_training - Step 14398: {'lr': 0.0004913924103011757, 'samples': 7372288, 'steps': 14398, 'loss/train': 1.8899304866790771}
-03/04/2022 06:22:15 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/04/2022 06:22:18 - INFO - codeparrot_training - Step 14399: {'lr': 0.0004913910297253448, 'samples': 7372800, 'steps': 14399, 'loss/train': 1.4923806190490723}
-03/04/2022 06:22:21 - INFO - codeparrot_training - Step 14400: {'lr': 0.0004913896490407467, 'samples': 7373312, 'steps': 14400, 'loss/train': 1.9882166385650635}
-03/04/2022 06:22:23 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/04/2022 06:22:27 - INFO - codeparrot_training - Step 14401: {'lr': 0.0004913882682473821, 'samples': 7373824, 'steps': 14401, 'loss/train': 2.000774621963501}
-03/04/2022 06:22:30 - INFO - codeparrot_training - Step 14402: {'lr': 0.0004913868873452519, 'samples': 7374336, 'steps': 14402, 'loss/train': 1.0393277406692505}
-03/04/2022 06:22:31 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 06:22:35 - INFO - codeparrot_training - Step 14403: {'lr': 0.0004913855063343563, 'samples': 7374848, 'steps': 14403, 'loss/train': 0.7617495656013489}
-03/04/2022 06:22:38 - INFO - codeparrot_training - Step 14404: {'lr': 0.0004913841252146961, 'samples': 7375360, 'steps': 14404, 'loss/train': 1.8369593620300293}
-03/04/2022 06:22:40 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/04/2022 06:22:44 - INFO - codeparrot_training - Step 14405: {'lr': 0.000491382743986272, 'samples': 7375872, 'steps': 14405, 'loss/train': 1.962270736694336}
-03/04/2022 06:22:47 - INFO - codeparrot_training - Step 14406: {'lr': 0.0004913813626490845, 'samples': 7376384, 'steps': 14406, 'loss/train': 1.7333030700683594}
-03/04/2022 06:22:48 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 06:22:52 - INFO - codeparrot_training - Step 14407: {'lr': 0.0004913799812031343, 'samples': 7376896, 'steps': 14407, 'loss/train': 2.528257131576538}
-03/04/2022 06:22:55 - INFO - codeparrot_training - Step 14408: {'lr': 0.0004913785996484221, 'samples': 7377408, 'steps': 14408, 'loss/train': 1.6382982730865479}
-03/04/2022 06:22:57 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/04/2022 06:23:00 - INFO - codeparrot_training - Step 14409: {'lr': 0.0004913772179849483, 'samples': 7377920, 'steps': 14409, 'loss/train': 1.6913334131240845}
-03/04/2022 06:23:04 - INFO - codeparrot_training - Step 14410: {'lr': 0.0004913758362127137, 'samples': 7378432, 'steps': 14410, 'loss/train': 1.8752018213272095}
-03/04/2022 06:23:05 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/04/2022 06:23:09 - INFO - codeparrot_training - Step 14411: {'lr': 0.0004913744543317189, 'samples': 7378944, 'steps': 14411, 'loss/train': 1.66899573802948}
-03/04/2022 06:23:12 - INFO - codeparrot_training - Step 14412: {'lr': 0.0004913730723419645, 'samples': 7379456, 'steps': 14412, 'loss/train': 2.15905499458313}
-03/04/2022 06:23:13 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/04/2022 06:23:17 - INFO - codeparrot_training - Step 14413: {'lr': 0.000491371690243451, 'samples': 7379968, 'steps': 14413, 'loss/train': 1.746608018875122}
-03/04/2022 06:23:20 - INFO - codeparrot_training - Step 14414: {'lr': 0.0004913703080361793, 'samples': 7380480, 'steps': 14414, 'loss/train': 1.2203691005706787}
-03/04/2022 06:23:22 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/04/2022 06:23:26 - INFO - codeparrot_training - Step 14415: {'lr': 0.0004913689257201499, 'samples': 7380992, 'steps': 14415, 'loss/train': 1.8603719472885132}
-03/04/2022 06:23:29 - INFO - codeparrot_training - Step 14416: {'lr': 0.0004913675432953633, 'samples': 7381504, 'steps': 14416, 'loss/train': 6.800209045410156}
-03/04/2022 06:23:31 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/04/2022 06:23:34 - INFO - codeparrot_training - Step 14417: {'lr': 0.0004913661607618202, 'samples': 7382016, 'steps': 14417, 'loss/train': 1.5742721557617188}
-03/04/2022 06:23:37 - INFO - codeparrot_training - Step 14418: {'lr': 0.0004913647781195212, 'samples': 7382528, 'steps': 14418, 'loss/train': 1.5692485570907593}
-03/04/2022 06:23:39 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/04/2022 06:23:43 - INFO - codeparrot_training - Step 14419: {'lr': 0.000491363395368467, 'samples': 7383040, 'steps': 14419, 'loss/train': 2.5370593070983887}
-03/04/2022 06:23:46 - INFO - codeparrot_training - Step 14420: {'lr': 0.0004913620125086581, 'samples': 7383552, 'steps': 14420, 'loss/train': 2.0688862800598145}
-03/04/2022 06:23:48 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/04/2022 06:23:51 - INFO - codeparrot_training - Step 14421: {'lr': 0.0004913606295400953, 'samples': 7384064, 'steps': 14421, 'loss/train': 2.409972667694092}
-03/04/2022 06:23:54 - INFO - codeparrot_training - Step 14422: {'lr': 0.000491359246462779, 'samples': 7384576, 'steps': 14422, 'loss/train': 1.8495386838912964}
-03/04/2022 06:23:56 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/04/2022 06:23:59 - INFO - codeparrot_training - Step 14423: {'lr': 0.0004913578632767101, 'samples': 7385088, 'steps': 14423, 'loss/train': 2.1343462467193604}
-03/04/2022 06:24:03 - INFO - codeparrot_training - Step 14424: {'lr': 0.0004913564799818891, 'samples': 7385600, 'steps': 14424, 'loss/train': 1.7525283098220825}
-03/04/2022 06:24:05 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/04/2022 06:24:08 - INFO - codeparrot_training - Step 14425: {'lr': 0.0004913550965783165, 'samples': 7386112, 'steps': 14425, 'loss/train': 1.942346215248108}
-03/04/2022 06:24:11 - INFO - codeparrot_training - Step 14426: {'lr': 0.000491353713065993, 'samples': 7386624, 'steps': 14426, 'loss/train': 1.7242460250854492}
-03/04/2022 06:24:13 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/04/2022 06:24:16 - INFO - codeparrot_training - Step 14427: {'lr': 0.0004913523294449193, 'samples': 7387136, 'steps': 14427, 'loss/train': 1.68510103225708}
-03/04/2022 06:24:19 - INFO - codeparrot_training - Step 14428: {'lr': 0.0004913509457150959, 'samples': 7387648, 'steps': 14428, 'loss/train': 0.8327200412750244}
-03/04/2022 06:24:22 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/04/2022 06:24:25 - INFO - codeparrot_training - Step 14429: {'lr': 0.0004913495618765235, 'samples': 7388160, 'steps': 14429, 'loss/train': 2.531555414199829}
-03/04/2022 06:24:28 - INFO - codeparrot_training - Step 14430: {'lr': 0.0004913481779292027, 'samples': 7388672, 'steps': 14430, 'loss/train': 1.9820325374603271}
-03/04/2022 06:24:30 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/04/2022 06:24:33 - INFO - codeparrot_training - Step 14431: {'lr': 0.0004913467938731341, 'samples': 7389184, 'steps': 14431, 'loss/train': 0.340747594833374}
-03/04/2022 06:24:36 - INFO - codeparrot_training - Step 14432: {'lr': 0.0004913454097083185, 'samples': 7389696, 'steps': 14432, 'loss/train': 1.9931721687316895}
-03/04/2022 06:24:39 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 06:24:42 - INFO - codeparrot_training - Step 14433: {'lr': 0.0004913440254347563, 'samples': 7390208, 'steps': 14433, 'loss/train': 1.9757556915283203}
-03/04/2022 06:24:45 - INFO - codeparrot_training - Step 14434: {'lr': 0.0004913426410524482, 'samples': 7390720, 'steps': 14434, 'loss/train': 1.4333192110061646}
-03/04/2022 06:24:49 - INFO - codeparrot_training - Step 14435: {'lr': 0.0004913412565613948, 'samples': 7391232, 'steps': 14435, 'loss/train': 0.3389715552330017}
-03/04/2022 06:24:50 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/04/2022 06:24:54 - INFO - codeparrot_training - Step 14436: {'lr': 0.0004913398719615968, 'samples': 7391744, 'steps': 14436, 'loss/train': 2.714110851287842}
-03/04/2022 06:24:57 - INFO - codeparrot_training - Step 14437: {'lr': 0.0004913384872530548, 'samples': 7392256, 'steps': 14437, 'loss/train': 2.4186582565307617}
-03/04/2022 06:25:02 - INFO - codeparrot_training - Step 14438: {'lr': 0.0004913371024357694, 'samples': 7392768, 'steps': 14438, 'loss/train': 2.0867905616760254}
-03/04/2022 06:25:06 - INFO - codeparrot_training - Step 14439: {'lr': 0.0004913357175097412, 'samples': 7393280, 'steps': 14439, 'loss/train': 3.0046653747558594}
-03/04/2022 06:25:07 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 06:25:11 - INFO - codeparrot_training - Step 14440: {'lr': 0.0004913343324749708, 'samples': 7393792, 'steps': 14440, 'loss/train': 1.14833664894104}
-03/04/2022 06:25:14 - INFO - codeparrot_training - Step 14441: {'lr': 0.000491332947331459, 'samples': 7394304, 'steps': 14441, 'loss/train': 0.3480164110660553}
-03/04/2022 06:25:16 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/04/2022 06:25:19 - INFO - codeparrot_training - Step 14442: {'lr': 0.0004913315620792061, 'samples': 7394816, 'steps': 14442, 'loss/train': 2.157649517059326}
-03/04/2022 06:25:23 - INFO - codeparrot_training - Step 14443: {'lr': 0.0004913301767182131, 'samples': 7395328, 'steps': 14443, 'loss/train': 1.914414644241333}
-03/04/2022 06:25:24 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/04/2022 06:25:28 - INFO - codeparrot_training - Step 14444: {'lr': 0.0004913287912484804, 'samples': 7395840, 'steps': 14444, 'loss/train': 1.9475805759429932}
-03/04/2022 06:25:31 - INFO - codeparrot_training - Step 14445: {'lr': 0.0004913274056700087, 'samples': 7396352, 'steps': 14445, 'loss/train': 2.117434024810791}
-03/04/2022 06:25:33 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 06:25:36 - INFO - codeparrot_training - Step 14446: {'lr': 0.0004913260199827986, 'samples': 7396864, 'steps': 14446, 'loss/train': 1.5287809371948242}
-03/04/2022 06:25:39 - INFO - codeparrot_training - Step 14447: {'lr': 0.0004913246341868506, 'samples': 7397376, 'steps': 14447, 'loss/train': 1.8601295948028564}
-03/04/2022 06:25:41 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/04/2022 06:25:45 - INFO - codeparrot_training - Step 14448: {'lr': 0.0004913232482821656, 'samples': 7397888, 'steps': 14448, 'loss/train': 3.257267951965332}
-03/04/2022 06:25:48 - INFO - codeparrot_training - Step 14449: {'lr': 0.0004913218622687439, 'samples': 7398400, 'steps': 14449, 'loss/train': 2.6513214111328125}
-03/04/2022 06:25:49 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 06:25:53 - INFO - codeparrot_training - Step 14450: {'lr': 0.0004913204761465864, 'samples': 7398912, 'steps': 14450, 'loss/train': 2.2245357036590576}
-03/04/2022 06:25:56 - INFO - codeparrot_training - Step 14451: {'lr': 0.0004913190899156936, 'samples': 7399424, 'steps': 14451, 'loss/train': 2.2819674015045166}
-03/04/2022 06:25:58 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/04/2022 06:26:01 - INFO - codeparrot_training - Step 14452: {'lr': 0.0004913177035760661, 'samples': 7399936, 'steps': 14452, 'loss/train': 1.460228681564331}
-03/04/2022 06:26:05 - INFO - codeparrot_training - Step 14453: {'lr': 0.0004913163171277046, 'samples': 7400448, 'steps': 14453, 'loss/train': 2.1257636547088623}
-03/04/2022 06:26:06 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/04/2022 06:26:10 - INFO - codeparrot_training - Step 14454: {'lr': 0.0004913149305706097, 'samples': 7400960, 'steps': 14454, 'loss/train': 1.921343207359314}
-03/04/2022 06:26:13 - INFO - codeparrot_training - Step 14455: {'lr': 0.0004913135439047821, 'samples': 7401472, 'steps': 14455, 'loss/train': 2.285409927368164}
-03/04/2022 06:26:14 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/04/2022 06:26:19 - INFO - codeparrot_training - Step 14456: {'lr': 0.0004913121571302222, 'samples': 7401984, 'steps': 14456, 'loss/train': 1.9380728006362915}
-03/04/2022 06:26:22 - INFO - codeparrot_training - Step 14457: {'lr': 0.0004913107702469308, 'samples': 7402496, 'steps': 14457, 'loss/train': 1.7929013967514038}
-03/04/2022 06:26:24 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 06:26:27 - INFO - codeparrot_training - Step 14458: {'lr': 0.0004913093832549085, 'samples': 7403008, 'steps': 14458, 'loss/train': 1.5380946397781372}
-03/04/2022 06:26:30 - INFO - codeparrot_training - Step 14459: {'lr': 0.000491307996154156, 'samples': 7403520, 'steps': 14459, 'loss/train': 2.2656002044677734}
-03/04/2022 06:26:32 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/04/2022 06:26:35 - INFO - codeparrot_training - Step 14460: {'lr': 0.0004913066089446737, 'samples': 7404032, 'steps': 14460, 'loss/train': 1.7820347547531128}
-03/04/2022 06:26:39 - INFO - codeparrot_training - Step 14461: {'lr': 0.0004913052216264624, 'samples': 7404544, 'steps': 14461, 'loss/train': 2.418726682662964}
-03/04/2022 06:26:41 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/04/2022 06:26:44 - INFO - codeparrot_training - Step 14462: {'lr': 0.0004913038341995227, 'samples': 7405056, 'steps': 14462, 'loss/train': 2.1311638355255127}
-03/04/2022 06:26:47 - INFO - codeparrot_training - Step 14463: {'lr': 0.0004913024466638553, 'samples': 7405568, 'steps': 14463, 'loss/train': 2.6009774208068848}
-03/04/2022 06:26:49 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 06:26:52 - INFO - codeparrot_training - Step 14464: {'lr': 0.0004913010590194607, 'samples': 7406080, 'steps': 14464, 'loss/train': 2.5856761932373047}
-03/04/2022 06:26:55 - INFO - codeparrot_training - Step 14465: {'lr': 0.0004912996712663396, 'samples': 7406592, 'steps': 14465, 'loss/train': 1.8325659036636353}
-03/04/2022 06:26:57 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/04/2022 06:27:01 - INFO - codeparrot_training - Step 14466: {'lr': 0.0004912982834044924, 'samples': 7407104, 'steps': 14466, 'loss/train': 1.5171058177947998}
-03/04/2022 06:27:04 - INFO - codeparrot_training - Step 14467: {'lr': 0.0004912968954339202, 'samples': 7407616, 'steps': 14467, 'loss/train': 3.098964214324951}
-03/04/2022 06:27:06 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/04/2022 06:27:09 - INFO - codeparrot_training - Step 14468: {'lr': 0.0004912955073546231, 'samples': 7408128, 'steps': 14468, 'loss/train': 2.0326600074768066}
-03/04/2022 06:27:12 - INFO - codeparrot_training - Step 14469: {'lr': 0.0004912941191666021, 'samples': 7408640, 'steps': 14469, 'loss/train': 2.104299783706665}
-03/04/2022 06:27:14 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/04/2022 06:27:17 - INFO - codeparrot_training - Step 14470: {'lr': 0.0004912927308698576, 'samples': 7409152, 'steps': 14470, 'loss/train': 2.0014119148254395}
-03/04/2022 06:27:21 - INFO - codeparrot_training - Step 14471: {'lr': 0.0004912913424643904, 'samples': 7409664, 'steps': 14471, 'loss/train': 1.5135406255722046}
-03/04/2022 06:27:22 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/04/2022 06:27:26 - INFO - codeparrot_training - Step 14472: {'lr': 0.0004912899539502011, 'samples': 7410176, 'steps': 14472, 'loss/train': 1.8165996074676514}
-03/04/2022 06:27:29 - INFO - codeparrot_training - Step 14473: {'lr': 0.0004912885653272902, 'samples': 7410688, 'steps': 14473, 'loss/train': 2.773125410079956}
-03/04/2022 06:27:31 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/04/2022 06:27:34 - INFO - codeparrot_training - Step 14474: {'lr': 0.0004912871765956583, 'samples': 7411200, 'steps': 14474, 'loss/train': 2.297253370285034}
-03/04/2022 06:27:37 - INFO - codeparrot_training - Step 14475: {'lr': 0.0004912857877553062, 'samples': 7411712, 'steps': 14475, 'loss/train': 2.364647150039673}
-03/04/2022 06:27:39 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/04/2022 06:27:43 - INFO - codeparrot_training - Step 14476: {'lr': 0.0004912843988062345, 'samples': 7412224, 'steps': 14476, 'loss/train': 1.8616231679916382}
-03/04/2022 06:27:46 - INFO - codeparrot_training - Step 14477: {'lr': 0.0004912830097484437, 'samples': 7412736, 'steps': 14477, 'loss/train': 2.4723265171051025}
-03/04/2022 06:27:47 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/04/2022 06:27:51 - INFO - codeparrot_training - Step 14478: {'lr': 0.0004912816205819346, 'samples': 7413248, 'steps': 14478, 'loss/train': 2.984126329421997}
-03/04/2022 06:27:54 - INFO - codeparrot_training - Step 14479: {'lr': 0.0004912802313067076, 'samples': 7413760, 'steps': 14479, 'loss/train': 2.533031702041626}
-03/04/2022 06:27:56 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 06:28:00 - INFO - codeparrot_training - Step 14480: {'lr': 0.0004912788419227635, 'samples': 7414272, 'steps': 14480, 'loss/train': 1.643554449081421}
-03/04/2022 06:28:03 - INFO - codeparrot_training - Step 14481: {'lr': 0.000491277452430103, 'samples': 7414784, 'steps': 14481, 'loss/train': 1.7966300249099731}
-03/04/2022 06:28:04 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/04/2022 06:28:08 - INFO - codeparrot_training - Step 14482: {'lr': 0.0004912760628287264, 'samples': 7415296, 'steps': 14482, 'loss/train': 1.757705807685852}
-03/04/2022 06:28:11 - INFO - codeparrot_training - Step 14483: {'lr': 0.0004912746731186346, 'samples': 7415808, 'steps': 14483, 'loss/train': 2.4631762504577637}
-03/04/2022 06:28:13 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 06:28:17 - INFO - codeparrot_training - Step 14484: {'lr': 0.0004912732832998281, 'samples': 7416320, 'steps': 14484, 'loss/train': 2.13379168510437}
-03/04/2022 06:28:20 - INFO - codeparrot_training - Step 14485: {'lr': 0.0004912718933723077, 'samples': 7416832, 'steps': 14485, 'loss/train': 2.0991714000701904}
-03/04/2022 06:28:22 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/04/2022 06:28:25 - INFO - codeparrot_training - Step 14486: {'lr': 0.0004912705033360738, 'samples': 7417344, 'steps': 14486, 'loss/train': 1.7966372966766357}
-03/04/2022 06:28:28 - INFO - codeparrot_training - Step 14487: {'lr': 0.0004912691131911272, 'samples': 7417856, 'steps': 14487, 'loss/train': 2.5449700355529785}
-03/04/2022 06:28:30 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 06:28:34 - INFO - codeparrot_training - Step 14488: {'lr': 0.0004912677229374684, 'samples': 7418368, 'steps': 14488, 'loss/train': 2.716484546661377}
-03/04/2022 06:28:37 - INFO - codeparrot_training - Step 14489: {'lr': 0.0004912663325750982, 'samples': 7418880, 'steps': 14489, 'loss/train': 2.2420601844787598}
-03/04/2022 06:28:39 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/04/2022 06:28:42 - INFO - codeparrot_training - Step 14490: {'lr': 0.000491264942104017, 'samples': 7419392, 'steps': 14490, 'loss/train': 1.498968482017517}
-03/04/2022 06:28:45 - INFO - codeparrot_training - Step 14491: {'lr': 0.0004912635515242257, 'samples': 7419904, 'steps': 14491, 'loss/train': 1.995278000831604}
-03/04/2022 06:28:47 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/04/2022 06:28:51 - INFO - codeparrot_training - Step 14492: {'lr': 0.0004912621608357246, 'samples': 7420416, 'steps': 14492, 'loss/train': 2.262125015258789}
-03/04/2022 06:28:54 - INFO - codeparrot_training - Step 14493: {'lr': 0.0004912607700385146, 'samples': 7420928, 'steps': 14493, 'loss/train': 1.8236291408538818}
-03/04/2022 06:28:56 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 06:28:59 - INFO - codeparrot_training - Step 14494: {'lr': 0.0004912593791325962, 'samples': 7421440, 'steps': 14494, 'loss/train': 2.2424938678741455}
-03/04/2022 06:29:02 - INFO - codeparrot_training - Step 14495: {'lr': 0.00049125798811797, 'samples': 7421952, 'steps': 14495, 'loss/train': 1.5904203653335571}
-03/04/2022 06:29:04 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/04/2022 06:29:07 - INFO - codeparrot_training - Step 14496: {'lr': 0.0004912565969946367, 'samples': 7422464, 'steps': 14496, 'loss/train': 3.070687770843506}
-03/04/2022 06:29:11 - INFO - codeparrot_training - Step 14497: {'lr': 0.0004912552057625969, 'samples': 7422976, 'steps': 14497, 'loss/train': 1.498801827430725}
-03/04/2022 06:29:13 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 06:29:16 - INFO - codeparrot_training - Step 14498: {'lr': 0.0004912538144218512, 'samples': 7423488, 'steps': 14498, 'loss/train': 1.7878761291503906}
-03/04/2022 06:29:19 - INFO - codeparrot_training - Step 14499: {'lr': 0.0004912524229724002, 'samples': 7424000, 'steps': 14499, 'loss/train': 2.2555534839630127}
-03/04/2022 06:29:21 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/04/2022 06:29:24 - INFO - codeparrot_training - Step 14500: {'lr': 0.0004912510314142447, 'samples': 7424512, 'steps': 14500, 'loss/train': 2.003948926925659}
-03/04/2022 06:29:28 - INFO - codeparrot_training - Step 14501: {'lr': 0.0004912496397473852, 'samples': 7425024, 'steps': 14501, 'loss/train': 2.805720329284668}
-03/04/2022 06:29:29 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/04/2022 06:29:33 - INFO - codeparrot_training - Step 14502: {'lr': 0.0004912482479718223, 'samples': 7425536, 'steps': 14502, 'loss/train': 2.0828697681427}
-03/04/2022 06:29:36 - INFO - codeparrot_training - Step 14503: {'lr': 0.0004912468560875566, 'samples': 7426048, 'steps': 14503, 'loss/train': 2.0467758178710938}
-03/04/2022 06:29:38 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/04/2022 06:29:42 - INFO - codeparrot_training - Step 14504: {'lr': 0.0004912454640945889, 'samples': 7426560, 'steps': 14504, 'loss/train': 2.238650321960449}
-03/04/2022 06:29:45 - INFO - codeparrot_training - Step 14505: {'lr': 0.0004912440719929196, 'samples': 7427072, 'steps': 14505, 'loss/train': 1.838680624961853}
-03/04/2022 06:29:48 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 06:29:50 - INFO - codeparrot_training - Step 14506: {'lr': 0.0004912426797825495, 'samples': 7427584, 'steps': 14506, 'loss/train': 1.6315889358520508}
-03/04/2022 06:29:53 - INFO - codeparrot_training - Step 14507: {'lr': 0.0004912412874634792, 'samples': 7428096, 'steps': 14507, 'loss/train': 1.3664159774780273}
-03/04/2022 06:29:56 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/04/2022 06:29:59 - INFO - codeparrot_training - Step 14508: {'lr': 0.0004912398950357094, 'samples': 7428608, 'steps': 14508, 'loss/train': 1.8985521793365479}
-03/04/2022 06:30:02 - INFO - codeparrot_training - Step 14509: {'lr': 0.0004912385024992404, 'samples': 7429120, 'steps': 14509, 'loss/train': 2.4850635528564453}
-03/04/2022 06:30:04 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 06:30:07 - INFO - codeparrot_training - Step 14510: {'lr': 0.0004912371098540733, 'samples': 7429632, 'steps': 14510, 'loss/train': 1.6081393957138062}
-03/04/2022 06:30:10 - INFO - codeparrot_training - Step 14511: {'lr': 0.0004912357171002082, 'samples': 7430144, 'steps': 14511, 'loss/train': 1.694367527961731}
-03/04/2022 06:30:13 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/04/2022 06:30:16 - INFO - codeparrot_training - Step 14512: {'lr': 0.0004912343242376462, 'samples': 7430656, 'steps': 14512, 'loss/train': 1.676770806312561}
-03/04/2022 06:30:19 - INFO - codeparrot_training - Step 14513: {'lr': 0.0004912329312663877, 'samples': 7431168, 'steps': 14513, 'loss/train': 5.479614734649658}
-03/04/2022 06:30:22 - INFO - codeparrot_training - Step 14514: {'lr': 0.0004912315381864333, 'samples': 7431680, 'steps': 14514, 'loss/train': 2.211632490158081}
-03/04/2022 06:30:24 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 06:30:28 - INFO - codeparrot_training - Step 14515: {'lr': 0.0004912301449977837, 'samples': 7432192, 'steps': 14515, 'loss/train': 1.9117107391357422}
-03/04/2022 06:30:31 - INFO - codeparrot_training - Step 14516: {'lr': 0.0004912287517004397, 'samples': 7432704, 'steps': 14516, 'loss/train': 2.794334888458252}
-03/04/2022 06:30:32 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/04/2022 06:30:36 - INFO - codeparrot_training - Step 14517: {'lr': 0.0004912273582944015, 'samples': 7433216, 'steps': 14517, 'loss/train': 1.8504031896591187}
-03/04/2022 06:30:40 - INFO - codeparrot_training - Step 14518: {'lr': 0.0004912259647796701, 'samples': 7433728, 'steps': 14518, 'loss/train': 1.9625581502914429}
-03/04/2022 06:30:41 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/04/2022 06:30:45 - INFO - codeparrot_training - Step 14519: {'lr': 0.000491224571156246, 'samples': 7434240, 'steps': 14519, 'loss/train': 1.009057879447937}
-03/04/2022 06:30:48 - INFO - codeparrot_training - Step 14520: {'lr': 0.0004912231774241298, 'samples': 7434752, 'steps': 14520, 'loss/train': 1.715103030204773}
-03/04/2022 06:30:49 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/04/2022 06:30:53 - INFO - codeparrot_training - Step 14521: {'lr': 0.0004912217835833222, 'samples': 7435264, 'steps': 14521, 'loss/train': 2.075608968734741}
-03/04/2022 06:30:56 - INFO - codeparrot_training - Step 14522: {'lr': 0.0004912203896338238, 'samples': 7435776, 'steps': 14522, 'loss/train': 1.935987114906311}
-03/04/2022 06:30:58 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 06:31:02 - INFO - codeparrot_training - Step 14523: {'lr': 0.0004912189955756351, 'samples': 7436288, 'steps': 14523, 'loss/train': 1.8402944803237915}
-03/04/2022 06:31:05 - INFO - codeparrot_training - Step 14524: {'lr': 0.000491217601408757, 'samples': 7436800, 'steps': 14524, 'loss/train': 1.854288101196289}
-03/04/2022 06:31:06 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/04/2022 06:31:10 - INFO - codeparrot_training - Step 14525: {'lr': 0.0004912162071331898, 'samples': 7437312, 'steps': 14525, 'loss/train': 1.6029694080352783}
-03/04/2022 06:31:13 - INFO - codeparrot_training - Step 14526: {'lr': 0.0004912148127489345, 'samples': 7437824, 'steps': 14526, 'loss/train': 0.5844347476959229}
-03/04/2022 06:31:15 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 06:31:18 - INFO - codeparrot_training - Step 14527: {'lr': 0.0004912134182559913, 'samples': 7438336, 'steps': 14527, 'loss/train': 2.516000509262085}
-03/04/2022 06:31:21 - INFO - codeparrot_training - Step 14528: {'lr': 0.0004912120236543611, 'samples': 7438848, 'steps': 14528, 'loss/train': 1.7172017097473145}
-03/04/2022 06:31:23 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/04/2022 06:31:27 - INFO - codeparrot_training - Step 14529: {'lr': 0.0004912106289440446, 'samples': 7439360, 'steps': 14529, 'loss/train': 2.199767827987671}
-03/04/2022 06:31:30 - INFO - codeparrot_training - Step 14530: {'lr': 0.0004912092341250422, 'samples': 7439872, 'steps': 14530, 'loss/train': 2.219837188720703}
-03/04/2022 06:31:31 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/04/2022 06:31:35 - INFO - codeparrot_training - Step 14531: {'lr': 0.0004912078391973547, 'samples': 7440384, 'steps': 14531, 'loss/train': 2.0327115058898926}
-03/04/2022 06:31:38 - INFO - codeparrot_training - Step 14532: {'lr': 0.0004912064441609827, 'samples': 7440896, 'steps': 14532, 'loss/train': 2.1392030715942383}
-03/04/2022 06:31:40 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/04/2022 06:31:44 - INFO - codeparrot_training - Step 14533: {'lr': 0.0004912050490159268, 'samples': 7441408, 'steps': 14533, 'loss/train': 1.4625823497772217}
-03/04/2022 06:31:47 - INFO - codeparrot_training - Step 14534: {'lr': 0.0004912036537621877, 'samples': 7441920, 'steps': 14534, 'loss/train': 1.2951244115829468}
-03/04/2022 06:31:48 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 06:31:52 - INFO - codeparrot_training - Step 14535: {'lr': 0.0004912022583997658, 'samples': 7442432, 'steps': 14535, 'loss/train': 1.7372350692749023}
-03/04/2022 06:31:55 - INFO - codeparrot_training - Step 14536: {'lr': 0.0004912008629286619, 'samples': 7442944, 'steps': 14536, 'loss/train': 1.7023965120315552}
-03/04/2022 06:31:57 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/04/2022 06:32:00 - INFO - codeparrot_training - Step 14537: {'lr': 0.0004911994673488766, 'samples': 7443456, 'steps': 14537, 'loss/train': 1.6753547191619873}
-03/04/2022 06:32:04 - INFO - codeparrot_training - Step 14538: {'lr': 0.0004911980716604107, 'samples': 7443968, 'steps': 14538, 'loss/train': 2.0169801712036133}
-03/04/2022 06:32:05 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/04/2022 06:32:09 - INFO - codeparrot_training - Step 14539: {'lr': 0.0004911966758632645, 'samples': 7444480, 'steps': 14539, 'loss/train': 1.919997215270996}
-03/04/2022 06:32:12 - INFO - codeparrot_training - Step 14540: {'lr': 0.000491195279957439, 'samples': 7444992, 'steps': 14540, 'loss/train': 2.225802183151245}
-03/04/2022 06:32:13 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/04/2022 06:32:18 - INFO - codeparrot_training - Step 14541: {'lr': 0.0004911938839429344, 'samples': 7445504, 'steps': 14541, 'loss/train': 1.7405496835708618}
-03/04/2022 06:32:21 - INFO - codeparrot_training - Step 14542: {'lr': 0.0004911924878197517, 'samples': 7446016, 'steps': 14542, 'loss/train': 1.8485711812973022}
-03/04/2022 06:32:23 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 06:32:26 - INFO - codeparrot_training - Step 14543: {'lr': 0.0004911910915878913, 'samples': 7446528, 'steps': 14543, 'loss/train': 2.301920175552368}
-03/04/2022 06:32:29 - INFO - codeparrot_training - Step 14544: {'lr': 0.000491189695247354, 'samples': 7447040, 'steps': 14544, 'loss/train': 1.9799779653549194}
-03/04/2022 06:32:31 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/04/2022 06:32:34 - INFO - codeparrot_training - Step 14545: {'lr': 0.0004911882987981404, 'samples': 7447552, 'steps': 14545, 'loss/train': 2.5267088413238525}
-03/04/2022 06:32:38 - INFO - codeparrot_training - Step 14546: {'lr': 0.0004911869022402508, 'samples': 7448064, 'steps': 14546, 'loss/train': 2.5846734046936035}
-03/04/2022 06:32:39 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/04/2022 06:32:43 - INFO - codeparrot_training - Step 14547: {'lr': 0.0004911855055736863, 'samples': 7448576, 'steps': 14547, 'loss/train': 1.4648802280426025}
-03/04/2022 06:32:46 - INFO - codeparrot_training - Step 14548: {'lr': 0.0004911841087984473, 'samples': 7449088, 'steps': 14548, 'loss/train': 1.8752671480178833}
-03/04/2022 06:32:48 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/04/2022 06:32:51 - INFO - codeparrot_training - Step 14549: {'lr': 0.0004911827119145345, 'samples': 7449600, 'steps': 14549, 'loss/train': 0.353299081325531}
-03/04/2022 06:32:54 - INFO - codeparrot_training - Step 14550: {'lr': 0.0004911813149219485, 'samples': 7450112, 'steps': 14550, 'loss/train': 6.297086715698242}
-03/04/2022 06:32:57 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/04/2022 06:33:00 - INFO - codeparrot_training - Step 14551: {'lr': 0.0004911799178206899, 'samples': 7450624, 'steps': 14551, 'loss/train': 2.8947672843933105}
-03/04/2022 06:33:03 - INFO - codeparrot_training - Step 14552: {'lr': 0.0004911785206107592, 'samples': 7451136, 'steps': 14552, 'loss/train': 2.089668035507202}
-03/04/2022 06:33:06 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 06:33:08 - INFO - codeparrot_training - Step 14553: {'lr': 0.0004911771232921575, 'samples': 7451648, 'steps': 14553, 'loss/train': 0.6191847324371338}
-03/04/2022 06:33:11 - INFO - codeparrot_training - Step 14554: {'lr': 0.0004911757258648849, 'samples': 7452160, 'steps': 14554, 'loss/train': 2.3816077709198}
-03/04/2022 06:33:14 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 06:33:17 - INFO - codeparrot_training - Step 14555: {'lr': 0.0004911743283289423, 'samples': 7452672, 'steps': 14555, 'loss/train': 1.1510287523269653}
-03/04/2022 06:33:20 - INFO - codeparrot_training - Step 14556: {'lr': 0.0004911729306843302, 'samples': 7453184, 'steps': 14556, 'loss/train': 2.528628349304199}
-03/04/2022 06:33:22 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/04/2022 06:33:25 - INFO - codeparrot_training - Step 14557: {'lr': 0.0004911715329310493, 'samples': 7453696, 'steps': 14557, 'loss/train': 1.6334818601608276}
-03/04/2022 06:33:28 - INFO - codeparrot_training - Step 14558: {'lr': 0.0004911701350691002, 'samples': 7454208, 'steps': 14558, 'loss/train': 2.3500399589538574}
-03/04/2022 06:33:31 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 06:33:33 - INFO - codeparrot_training - Step 14559: {'lr': 0.0004911687370984836, 'samples': 7454720, 'steps': 14559, 'loss/train': 0.9696388840675354}
-03/04/2022 06:33:37 - INFO - codeparrot_training - Step 14560: {'lr': 0.0004911673390192002, 'samples': 7455232, 'steps': 14560, 'loss/train': 2.413771152496338}
-03/04/2022 06:33:39 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/04/2022 06:33:42 - INFO - codeparrot_training - Step 14561: {'lr': 0.0004911659408312505, 'samples': 7455744, 'steps': 14561, 'loss/train': 2.0632970333099365}
-03/04/2022 06:33:45 - INFO - codeparrot_training - Step 14562: {'lr': 0.000491164542534635, 'samples': 7456256, 'steps': 14562, 'loss/train': 1.930906891822815}
-03/04/2022 06:33:47 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 06:33:50 - INFO - codeparrot_training - Step 14563: {'lr': 0.0004911631441293546, 'samples': 7456768, 'steps': 14563, 'loss/train': 1.8056648969650269}
-03/04/2022 06:33:53 - INFO - codeparrot_training - Step 14564: {'lr': 0.0004911617456154097, 'samples': 7457280, 'steps': 14564, 'loss/train': 1.5647716522216797}
-03/04/2022 06:33:59 - INFO - codeparrot_training - Step 14565: {'lr': 0.0004911603469928012, 'samples': 7457792, 'steps': 14565, 'loss/train': 1.6819095611572266}
-03/04/2022 06:34:02 - INFO - codeparrot_training - Step 14566: {'lr': 0.0004911589482615294, 'samples': 7458304, 'steps': 14566, 'loss/train': 3.0265262126922607}
-03/04/2022 06:34:05 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/04/2022 06:34:07 - INFO - codeparrot_training - Step 14567: {'lr': 0.0004911575494215952, 'samples': 7458816, 'steps': 14567, 'loss/train': 1.4194704294204712}
-03/04/2022 06:34:10 - INFO - codeparrot_training - Step 14568: {'lr': 0.0004911561504729992, 'samples': 7459328, 'steps': 14568, 'loss/train': 1.4257439374923706}
-03/04/2022 06:34:13 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/04/2022 06:34:16 - INFO - codeparrot_training - Step 14569: {'lr': 0.0004911547514157417, 'samples': 7459840, 'steps': 14569, 'loss/train': 1.6735121011734009}
-03/04/2022 06:34:19 - INFO - codeparrot_training - Step 14570: {'lr': 0.0004911533522498239, 'samples': 7460352, 'steps': 14570, 'loss/train': 2.2158429622650146}
-03/04/2022 06:34:22 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/04/2022 06:34:24 - INFO - codeparrot_training - Step 14571: {'lr': 0.0004911519529752459, 'samples': 7460864, 'steps': 14571, 'loss/train': 2.3231990337371826}
-03/04/2022 06:34:27 - INFO - codeparrot_training - Step 14572: {'lr': 0.0004911505535920086, 'samples': 7461376, 'steps': 14572, 'loss/train': 0.6035769581794739}
-03/04/2022 06:34:30 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 06:34:33 - INFO - codeparrot_training - Step 14573: {'lr': 0.0004911491541001126, 'samples': 7461888, 'steps': 14573, 'loss/train': 2.384101629257202}
-03/04/2022 06:34:36 - INFO - codeparrot_training - Step 14574: {'lr': 0.0004911477544995585, 'samples': 7462400, 'steps': 14574, 'loss/train': 2.2773332595825195}
-03/04/2022 06:34:39 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/04/2022 06:34:41 - INFO - codeparrot_training - Step 14575: {'lr': 0.000491146354790347, 'samples': 7462912, 'steps': 14575, 'loss/train': 2.335326910018921}
-03/04/2022 06:34:44 - INFO - codeparrot_training - Step 14576: {'lr': 0.0004911449549724786, 'samples': 7463424, 'steps': 14576, 'loss/train': 1.9962650537490845}
-03/04/2022 06:34:47 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 06:34:49 - INFO - codeparrot_training - Step 14577: {'lr': 0.0004911435550459541, 'samples': 7463936, 'steps': 14577, 'loss/train': 1.4513343572616577}
-03/04/2022 06:34:53 - INFO - codeparrot_training - Step 14578: {'lr': 0.0004911421550107739, 'samples': 7464448, 'steps': 14578, 'loss/train': 2.121506690979004}
-03/04/2022 06:34:55 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/04/2022 06:34:58 - INFO - codeparrot_training - Step 14579: {'lr': 0.0004911407548669389, 'samples': 7464960, 'steps': 14579, 'loss/train': 0.8584125638008118}
-03/04/2022 06:35:01 - INFO - codeparrot_training - Step 14580: {'lr': 0.0004911393546144495, 'samples': 7465472, 'steps': 14580, 'loss/train': 2.848935842514038}
-03/04/2022 06:35:03 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 06:35:06 - INFO - codeparrot_training - Step 14581: {'lr': 0.0004911379542533065, 'samples': 7465984, 'steps': 14581, 'loss/train': 2.339160919189453}
-03/04/2022 06:35:09 - INFO - codeparrot_training - Step 14582: {'lr': 0.0004911365537835105, 'samples': 7466496, 'steps': 14582, 'loss/train': 1.238793134689331}
-03/04/2022 06:35:12 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/04/2022 06:35:14 - INFO - codeparrot_training - Step 14583: {'lr': 0.000491135153205062, 'samples': 7467008, 'steps': 14583, 'loss/train': 1.2921392917633057}
-03/04/2022 06:35:18 - INFO - codeparrot_training - Step 14584: {'lr': 0.0004911337525179616, 'samples': 7467520, 'steps': 14584, 'loss/train': 1.743784785270691}
-03/04/2022 06:35:20 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/04/2022 06:35:23 - INFO - codeparrot_training - Step 14585: {'lr': 0.0004911323517222103, 'samples': 7468032, 'steps': 14585, 'loss/train': 1.556057095527649}
-03/04/2022 06:35:26 - INFO - codeparrot_training - Step 14586: {'lr': 0.0004911309508178084, 'samples': 7468544, 'steps': 14586, 'loss/train': 2.493086814880371}
-03/04/2022 06:35:28 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/04/2022 06:35:31 - INFO - codeparrot_training - Step 14587: {'lr': 0.0004911295498047565, 'samples': 7469056, 'steps': 14587, 'loss/train': 1.7547245025634766}
-03/04/2022 06:35:35 - INFO - codeparrot_training - Step 14588: {'lr': 0.0004911281486830554, 'samples': 7469568, 'steps': 14588, 'loss/train': 1.5730189085006714}
-03/04/2022 06:35:36 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/04/2022 06:35:40 - INFO - codeparrot_training - Step 14589: {'lr': 0.0004911267474527058, 'samples': 7470080, 'steps': 14589, 'loss/train': 2.0088188648223877}
-03/04/2022 06:35:43 - INFO - codeparrot_training - Step 14590: {'lr': 0.000491125346113708, 'samples': 7470592, 'steps': 14590, 'loss/train': 2.0329227447509766}
-03/04/2022 06:35:45 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 06:35:48 - INFO - codeparrot_training - Step 14591: {'lr': 0.000491123944666063, 'samples': 7471104, 'steps': 14591, 'loss/train': 1.7886011600494385}
-03/04/2022 06:35:51 - INFO - codeparrot_training - Step 14592: {'lr': 0.0004911225431097712, 'samples': 7471616, 'steps': 14592, 'loss/train': 2.3092310428619385}
-03/04/2022 06:35:53 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/04/2022 06:35:57 - INFO - codeparrot_training - Step 14593: {'lr': 0.0004911211414448333, 'samples': 7472128, 'steps': 14593, 'loss/train': 2.4593002796173096}
-03/04/2022 06:36:00 - INFO - codeparrot_training - Step 14594: {'lr': 0.0004911197396712501, 'samples': 7472640, 'steps': 14594, 'loss/train': 2.6979477405548096}
-03/04/2022 06:36:01 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/04/2022 06:36:05 - INFO - codeparrot_training - Step 14595: {'lr': 0.0004911183377890218, 'samples': 7473152, 'steps': 14595, 'loss/train': 1.6064343452453613}
-03/04/2022 06:36:08 - INFO - codeparrot_training - Step 14596: {'lr': 0.0004911169357981496, 'samples': 7473664, 'steps': 14596, 'loss/train': 1.7913718223571777}
-03/04/2022 06:36:10 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 06:36:14 - INFO - codeparrot_training - Step 14597: {'lr': 0.0004911155336986335, 'samples': 7474176, 'steps': 14597, 'loss/train': 2.2539985179901123}
-03/04/2022 06:36:18 - INFO - codeparrot_training - Step 14598: {'lr': 0.0004911141314904747, 'samples': 7474688, 'steps': 14598, 'loss/train': 1.1991071701049805}
-03/04/2022 06:36:21 - INFO - codeparrot_training - Step 14599: {'lr': 0.0004911127291736735, 'samples': 7475200, 'steps': 14599, 'loss/train': 2.04853892326355}
-03/04/2022 06:36:23 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/04/2022 06:36:26 - INFO - codeparrot_training - Step 14600: {'lr': 0.0004911113267482307, 'samples': 7475712, 'steps': 14600, 'loss/train': 2.0307557582855225}
-03/04/2022 06:36:29 - INFO - codeparrot_training - Step 14601: {'lr': 0.0004911099242141467, 'samples': 7476224, 'steps': 14601, 'loss/train': 1.8280770778656006}
-03/04/2022 06:36:31 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 06:36:34 - INFO - codeparrot_training - Step 14602: {'lr': 0.0004911085215714224, 'samples': 7476736, 'steps': 14602, 'loss/train': 2.266578197479248}
-03/04/2022 06:36:38 - INFO - codeparrot_training - Step 14603: {'lr': 0.0004911071188200584, 'samples': 7477248, 'steps': 14603, 'loss/train': 1.5705084800720215}
-03/04/2022 06:36:40 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/04/2022 06:36:43 - INFO - codeparrot_training - Step 14604: {'lr': 0.0004911057159600551, 'samples': 7477760, 'steps': 14604, 'loss/train': 1.9830840826034546}
-03/04/2022 06:36:47 - INFO - codeparrot_training - Step 14605: {'lr': 0.0004911043129914133, 'samples': 7478272, 'steps': 14605, 'loss/train': 2.99961519241333}
-03/04/2022 06:36:49 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/04/2022 06:36:52 - INFO - codeparrot_training - Step 14606: {'lr': 0.0004911029099141336, 'samples': 7478784, 'steps': 14606, 'loss/train': 1.2199786901474}
-03/04/2022 06:36:55 - INFO - codeparrot_training - Step 14607: {'lr': 0.0004911015067282168, 'samples': 7479296, 'steps': 14607, 'loss/train': 1.725904107093811}
-03/04/2022 06:36:58 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 06:37:00 - INFO - codeparrot_training - Step 14608: {'lr': 0.0004911001034336633, 'samples': 7479808, 'steps': 14608, 'loss/train': 1.8643933534622192}
-03/04/2022 06:37:04 - INFO - codeparrot_training - Step 14609: {'lr': 0.0004910987000304737, 'samples': 7480320, 'steps': 14609, 'loss/train': 1.780038833618164}
-03/04/2022 06:37:07 - INFO - codeparrot_training - Step 14610: {'lr': 0.0004910972965186488, 'samples': 7480832, 'steps': 14610, 'loss/train': 1.5725963115692139}
-03/04/2022 06:37:07 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 06:37:12 - INFO - codeparrot_training - Step 14611: {'lr': 0.0004910958928981893, 'samples': 7481344, 'steps': 14611, 'loss/train': 2.021512269973755}
-03/04/2022 06:37:15 - INFO - codeparrot_training - Step 14612: {'lr': 0.0004910944891690956, 'samples': 7481856, 'steps': 14612, 'loss/train': 2.0517730712890625}
-03/04/2022 06:37:15 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 06:37:20 - INFO - codeparrot_training - Step 14613: {'lr': 0.0004910930853313686, 'samples': 7482368, 'steps': 14613, 'loss/train': 2.263488531112671}
-03/04/2022 06:37:24 - INFO - codeparrot_training - Step 14614: {'lr': 0.0004910916813850086, 'samples': 7482880, 'steps': 14614, 'loss/train': 1.823209285736084}
-03/04/2022 06:37:24 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/04/2022 06:37:29 - INFO - codeparrot_training - Step 14615: {'lr': 0.0004910902773300164, 'samples': 7483392, 'steps': 14615, 'loss/train': 2.210144281387329}
-03/04/2022 06:37:32 - INFO - codeparrot_training - Step 14616: {'lr': 0.0004910888731663928, 'samples': 7483904, 'steps': 14616, 'loss/train': 1.571336269378662}
-03/04/2022 06:37:32 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 06:37:37 - INFO - codeparrot_training - Step 14617: {'lr': 0.0004910874688941381, 'samples': 7484416, 'steps': 14617, 'loss/train': 2.0486555099487305}
-03/04/2022 06:37:40 - INFO - codeparrot_training - Step 14618: {'lr': 0.0004910860645132532, 'samples': 7484928, 'steps': 14618, 'loss/train': 3.554835081100464}
-03/04/2022 06:37:41 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/04/2022 06:37:46 - INFO - codeparrot_training - Step 14619: {'lr': 0.0004910846600237386, 'samples': 7485440, 'steps': 14619, 'loss/train': 2.208528518676758}
-03/04/2022 06:37:49 - INFO - codeparrot_training - Step 14620: {'lr': 0.0004910832554255951, 'samples': 7485952, 'steps': 14620, 'loss/train': 3.5059988498687744}
-03/04/2022 06:37:49 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/04/2022 06:37:54 - INFO - codeparrot_training - Step 14621: {'lr': 0.0004910818507188231, 'samples': 7486464, 'steps': 14621, 'loss/train': 1.7604866027832031}
-03/04/2022 06:37:57 - INFO - codeparrot_training - Step 14622: {'lr': 0.0004910804459034233, 'samples': 7486976, 'steps': 14622, 'loss/train': 1.89711332321167}
-03/04/2022 06:37:57 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/04/2022 06:38:03 - INFO - codeparrot_training - Step 14623: {'lr': 0.0004910790409793965, 'samples': 7487488, 'steps': 14623, 'loss/train': 2.2551050186157227}
-03/04/2022 06:38:05 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/04/2022 06:38:08 - INFO - codeparrot_training - Step 14624: {'lr': 0.000491077635946743, 'samples': 7488000, 'steps': 14624, 'loss/train': 1.3373290300369263}
-03/04/2022 06:38:11 - INFO - codeparrot_training - Step 14625: {'lr': 0.0004910762308054638, 'samples': 7488512, 'steps': 14625, 'loss/train': 1.4902293682098389}
-03/04/2022 06:38:14 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 06:38:16 - INFO - codeparrot_training - Step 14626: {'lr': 0.0004910748255555593, 'samples': 7489024, 'steps': 14626, 'loss/train': 1.4497263431549072}
-03/04/2022 06:38:20 - INFO - codeparrot_training - Step 14627: {'lr': 0.0004910734201970302, 'samples': 7489536, 'steps': 14627, 'loss/train': 1.9737129211425781}
-03/04/2022 06:38:22 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 06:38:25 - INFO - codeparrot_training - Step 14628: {'lr': 0.0004910720147298772, 'samples': 7490048, 'steps': 14628, 'loss/train': 2.359262228012085}
-03/04/2022 06:38:28 - INFO - codeparrot_training - Step 14629: {'lr': 0.0004910706091541009, 'samples': 7490560, 'steps': 14629, 'loss/train': 1.6546589136123657}
-03/04/2022 06:38:31 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/04/2022 06:38:33 - INFO - codeparrot_training - Step 14630: {'lr': 0.0004910692034697018, 'samples': 7491072, 'steps': 14630, 'loss/train': 1.9492182731628418}
-03/04/2022 06:38:36 - INFO - codeparrot_training - Step 14631: {'lr': 0.0004910677976766807, 'samples': 7491584, 'steps': 14631, 'loss/train': 2.0811994075775146}
-03/04/2022 06:38:39 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 06:38:42 - INFO - codeparrot_training - Step 14632: {'lr': 0.0004910663917750382, 'samples': 7492096, 'steps': 14632, 'loss/train': 2.102867841720581}
-03/04/2022 06:38:45 - INFO - codeparrot_training - Step 14633: {'lr': 0.0004910649857647748, 'samples': 7492608, 'steps': 14633, 'loss/train': 1.3692461252212524}
-03/04/2022 06:38:48 - INFO - codeparrot_training - Step 14634: {'lr': 0.0004910635796458913, 'samples': 7493120, 'steps': 14634, 'loss/train': 4.224267959594727}
-03/04/2022 06:38:50 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 06:38:54 - INFO - codeparrot_training - Step 14635: {'lr': 0.0004910621734183882, 'samples': 7493632, 'steps': 14635, 'loss/train': 2.570574998855591}
-03/04/2022 06:38:57 - INFO - codeparrot_training - Step 14636: {'lr': 0.0004910607670822663, 'samples': 7494144, 'steps': 14636, 'loss/train': 1.0257019996643066}
-03/04/2022 06:38:58 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 06:39:02 - INFO - codeparrot_training - Step 14637: {'lr': 0.0004910593606375261, 'samples': 7494656, 'steps': 14637, 'loss/train': 2.0437047481536865}
-03/04/2022 06:39:05 - INFO - codeparrot_training - Step 14638: {'lr': 0.0004910579540841683, 'samples': 7495168, 'steps': 14638, 'loss/train': 1.9655358791351318}
-03/04/2022 06:39:07 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 06:39:11 - INFO - codeparrot_training - Step 14639: {'lr': 0.0004910565474221934, 'samples': 7495680, 'steps': 14639, 'loss/train': 2.2278788089752197}
-03/04/2022 06:39:14 - INFO - codeparrot_training - Step 14640: {'lr': 0.0004910551406516022, 'samples': 7496192, 'steps': 14640, 'loss/train': 2.319030284881592}
-03/04/2022 06:39:15 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/04/2022 06:39:19 - INFO - codeparrot_training - Step 14641: {'lr': 0.0004910537337723954, 'samples': 7496704, 'steps': 14641, 'loss/train': 1.9509186744689941}
-03/04/2022 06:39:22 - INFO - codeparrot_training - Step 14642: {'lr': 0.0004910523267845733, 'samples': 7497216, 'steps': 14642, 'loss/train': 2.3421730995178223}
-03/04/2022 06:39:24 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/04/2022 06:39:27 - INFO - codeparrot_training - Step 14643: {'lr': 0.0004910509196881369, 'samples': 7497728, 'steps': 14643, 'loss/train': 0.9727531671524048}
-03/04/2022 06:39:31 - INFO - codeparrot_training - Step 14644: {'lr': 0.0004910495124830866, 'samples': 7498240, 'steps': 14644, 'loss/train': 1.9049800634384155}
-03/04/2022 06:39:32 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/04/2022 06:39:36 - INFO - codeparrot_training - Step 14645: {'lr': 0.0004910481051694231, 'samples': 7498752, 'steps': 14645, 'loss/train': 1.2123641967773438}
-03/04/2022 06:39:39 - INFO - codeparrot_training - Step 14646: {'lr': 0.0004910466977471471, 'samples': 7499264, 'steps': 14646, 'loss/train': 1.6685471534729004}
-03/04/2022 06:39:40 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/04/2022 06:39:44 - INFO - codeparrot_training - Step 14647: {'lr': 0.0004910452902162592, 'samples': 7499776, 'steps': 14647, 'loss/train': 2.649479389190674}
-03/04/2022 06:39:47 - INFO - codeparrot_training - Step 14648: {'lr': 0.0004910438825767599, 'samples': 7500288, 'steps': 14648, 'loss/train': 1.614532232284546}
-03/04/2022 06:39:49 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/04/2022 06:39:53 - INFO - codeparrot_training - Step 14649: {'lr': 0.00049104247482865, 'samples': 7500800, 'steps': 14649, 'loss/train': 2.0369694232940674}
-03/04/2022 06:39:56 - INFO - codeparrot_training - Step 14650: {'lr': 0.0004910410669719301, 'samples': 7501312, 'steps': 14650, 'loss/train': 2.3648855686187744}
-03/04/2022 06:39:57 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/04/2022 06:40:01 - INFO - codeparrot_training - Step 14651: {'lr': 0.0004910396590066008, 'samples': 7501824, 'steps': 14651, 'loss/train': 2.138284921646118}
-03/04/2022 06:40:04 - INFO - codeparrot_training - Step 14652: {'lr': 0.0004910382509326627, 'samples': 7502336, 'steps': 14652, 'loss/train': 1.6167713403701782}
-03/04/2022 06:40:06 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/04/2022 06:40:10 - INFO - codeparrot_training - Step 14653: {'lr': 0.0004910368427501166, 'samples': 7502848, 'steps': 14653, 'loss/train': 1.788743495941162}
-03/04/2022 06:40:13 - INFO - codeparrot_training - Step 14654: {'lr': 0.000491035434458963, 'samples': 7503360, 'steps': 14654, 'loss/train': 2.3953487873077393}
-03/04/2022 06:40:15 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/04/2022 06:40:18 - INFO - codeparrot_training - Step 14655: {'lr': 0.0004910340260592024, 'samples': 7503872, 'steps': 14655, 'loss/train': 2.199718952178955}
-03/04/2022 06:40:22 - INFO - codeparrot_training - Step 14656: {'lr': 0.0004910326175508357, 'samples': 7504384, 'steps': 14656, 'loss/train': 2.3690104484558105}
-03/04/2022 06:40:24 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/04/2022 06:40:28 - INFO - codeparrot_training - Step 14657: {'lr': 0.0004910312089338634, 'samples': 7504896, 'steps': 14657, 'loss/train': 1.3987480401992798}
-03/04/2022 06:40:31 - INFO - codeparrot_training - Step 14658: {'lr': 0.0004910298002082863, 'samples': 7505408, 'steps': 14658, 'loss/train': 1.9630708694458008}
-03/04/2022 06:40:34 - INFO - codeparrot_training - Step 14659: {'lr': 0.0004910283913741047, 'samples': 7505920, 'steps': 14659, 'loss/train': 2.4032437801361084}
-03/04/2022 06:40:37 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/04/2022 06:40:40 - INFO - codeparrot_training - Step 14660: {'lr': 0.0004910269824313194, 'samples': 7506432, 'steps': 14660, 'loss/train': 2.293853282928467}
-03/04/2022 06:40:43 - INFO - codeparrot_training - Step 14661: {'lr': 0.0004910255733799312, 'samples': 7506944, 'steps': 14661, 'loss/train': 1.4194084405899048}
-03/04/2022 06:40:46 - INFO - codeparrot_training - Step 14662: {'lr': 0.0004910241642199406, 'samples': 7507456, 'steps': 14662, 'loss/train': 1.725920557975769}
-03/04/2022 06:40:46 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/04/2022 06:40:51 - INFO - codeparrot_training - Step 14663: {'lr': 0.0004910227549513481, 'samples': 7507968, 'steps': 14663, 'loss/train': 1.6435123682022095}
-03/04/2022 06:40:55 - INFO - codeparrot_training - Step 14664: {'lr': 0.0004910213455741546, 'samples': 7508480, 'steps': 14664, 'loss/train': 1.7588903903961182}
-03/04/2022 06:40:55 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/04/2022 06:41:00 - INFO - codeparrot_training - Step 14665: {'lr': 0.0004910199360883605, 'samples': 7508992, 'steps': 14665, 'loss/train': 2.0121936798095703}
-03/04/2022 06:41:03 - INFO - codeparrot_training - Step 14666: {'lr': 0.0004910185264939667, 'samples': 7509504, 'steps': 14666, 'loss/train': 2.4503378868103027}
-03/04/2022 06:41:04 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 06:41:08 - INFO - codeparrot_training - Step 14667: {'lr': 0.0004910171167909734, 'samples': 7510016, 'steps': 14667, 'loss/train': 2.4290552139282227}
-03/04/2022 06:41:12 - INFO - codeparrot_training - Step 14668: {'lr': 0.0004910157069793816, 'samples': 7510528, 'steps': 14668, 'loss/train': 2.0673577785491943}
-03/04/2022 06:41:13 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 06:41:17 - INFO - codeparrot_training - Step 14669: {'lr': 0.000491014297059192, 'samples': 7511040, 'steps': 14669, 'loss/train': 1.433302640914917}
-03/04/2022 06:41:20 - INFO - codeparrot_training - Step 14670: {'lr': 0.000491012887030405, 'samples': 7511552, 'steps': 14670, 'loss/train': 3.188472032546997}
-03/04/2022 06:41:21 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 06:41:25 - INFO - codeparrot_training - Step 14671: {'lr': 0.0004910114768930212, 'samples': 7512064, 'steps': 14671, 'loss/train': 2.2035863399505615}
-03/04/2022 06:41:28 - INFO - codeparrot_training - Step 14672: {'lr': 0.0004910100666470415, 'samples': 7512576, 'steps': 14672, 'loss/train': 2.323603391647339}
-03/04/2022 06:41:29 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 06:41:34 - INFO - codeparrot_training - Step 14673: {'lr': 0.0004910086562924663, 'samples': 7513088, 'steps': 14673, 'loss/train': 2.518293857574463}
-03/04/2022 06:41:37 - INFO - codeparrot_training - Step 14674: {'lr': 0.0004910072458292963, 'samples': 7513600, 'steps': 14674, 'loss/train': 1.5799893140792847}
-03/04/2022 06:41:37 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 06:41:42 - INFO - codeparrot_training - Step 14675: {'lr': 0.0004910058352575322, 'samples': 7514112, 'steps': 14675, 'loss/train': 2.012984037399292}
-03/04/2022 06:41:45 - INFO - codeparrot_training - Step 14676: {'lr': 0.0004910044245771745, 'samples': 7514624, 'steps': 14676, 'loss/train': 1.5848982334136963}
-03/04/2022 06:41:46 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/04/2022 06:41:51 - INFO - codeparrot_training - Step 14677: {'lr': 0.0004910030137882241, 'samples': 7515136, 'steps': 14677, 'loss/train': 1.6715326309204102}
-03/04/2022 06:41:54 - INFO - codeparrot_training - Step 14678: {'lr': 0.0004910016028906813, 'samples': 7515648, 'steps': 14678, 'loss/train': 1.989601731300354}
-03/04/2022 06:41:55 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 06:41:59 - INFO - codeparrot_training - Step 14679: {'lr': 0.000491000191884547, 'samples': 7516160, 'steps': 14679, 'loss/train': 2.2734744548797607}
-03/04/2022 06:42:02 - INFO - codeparrot_training - Step 14680: {'lr': 0.0004909987807698217, 'samples': 7516672, 'steps': 14680, 'loss/train': 2.3192481994628906}
-03/04/2022 06:42:03 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/04/2022 06:42:07 - INFO - codeparrot_training - Step 14681: {'lr': 0.000490997369546506, 'samples': 7517184, 'steps': 14681, 'loss/train': 1.9882738590240479}
-03/04/2022 06:42:10 - INFO - codeparrot_training - Step 14682: {'lr': 0.0004909959582146007, 'samples': 7517696, 'steps': 14682, 'loss/train': 0.8383315801620483}
-03/04/2022 06:42:11 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 06:42:16 - INFO - codeparrot_training - Step 14683: {'lr': 0.0004909945467741063, 'samples': 7518208, 'steps': 14683, 'loss/train': 2.073594808578491}
-03/04/2022 06:42:19 - INFO - codeparrot_training - Step 14684: {'lr': 0.0004909931352250235, 'samples': 7518720, 'steps': 14684, 'loss/train': 1.5811772346496582}
-03/04/2022 06:42:19 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/04/2022 06:42:24 - INFO - codeparrot_training - Step 14685: {'lr': 0.0004909917235673529, 'samples': 7519232, 'steps': 14685, 'loss/train': 2.6342933177948}
-03/04/2022 06:42:27 - INFO - codeparrot_training - Step 14686: {'lr': 0.0004909903118010951, 'samples': 7519744, 'steps': 14686, 'loss/train': 2.7538511753082275}
-03/04/2022 06:42:28 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 06:42:33 - INFO - codeparrot_training - Step 14687: {'lr': 0.0004909888999262509, 'samples': 7520256, 'steps': 14687, 'loss/train': 2.253537654876709}
-03/04/2022 06:42:36 - INFO - codeparrot_training - Step 14688: {'lr': 0.0004909874879428207, 'samples': 7520768, 'steps': 14688, 'loss/train': 1.2533048391342163}
-03/04/2022 06:42:36 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 06:42:41 - INFO - codeparrot_training - Step 14689: {'lr': 0.0004909860758508052, 'samples': 7521280, 'steps': 14689, 'loss/train': 1.9635541439056396}
-03/04/2022 06:42:44 - INFO - codeparrot_training - Step 14690: {'lr': 0.0004909846636502053, 'samples': 7521792, 'steps': 14690, 'loss/train': 1.3718457221984863}
-03/04/2022 06:42:44 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/04/2022 06:42:49 - INFO - codeparrot_training - Step 14691: {'lr': 0.0004909832513410213, 'samples': 7522304, 'steps': 14691, 'loss/train': 2.1683828830718994}
-03/04/2022 06:42:53 - INFO - codeparrot_training - Step 14692: {'lr': 0.000490981838923254, 'samples': 7522816, 'steps': 14692, 'loss/train': 2.0924875736236572}
-03/04/2022 06:42:53 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/04/2022 06:42:58 - INFO - codeparrot_training - Step 14693: {'lr': 0.000490980426396904, 'samples': 7523328, 'steps': 14693, 'loss/train': 2.285388946533203}
-03/04/2022 06:43:01 - INFO - codeparrot_training - Step 14694: {'lr': 0.0004909790137619719, 'samples': 7523840, 'steps': 14694, 'loss/train': 2.0614092350006104}
-03/04/2022 06:43:01 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 06:43:06 - INFO - codeparrot_training - Step 14695: {'lr': 0.0004909776010184585, 'samples': 7524352, 'steps': 14695, 'loss/train': 1.6009719371795654}
-03/04/2022 06:43:09 - INFO - codeparrot_training - Step 14696: {'lr': 0.0004909761881663642, 'samples': 7524864, 'steps': 14696, 'loss/train': 1.9446743726730347}
-03/04/2022 06:43:09 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/04/2022 06:43:15 - INFO - codeparrot_training - Step 14697: {'lr': 0.0004909747752056897, 'samples': 7525376, 'steps': 14697, 'loss/train': 2.1978580951690674}
-03/04/2022 06:43:18 - INFO - codeparrot_training - Step 14698: {'lr': 0.0004909733621364358, 'samples': 7525888, 'steps': 14698, 'loss/train': 2.117098569869995}
-03/04/2022 06:43:18 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 06:43:23 - INFO - codeparrot_training - Step 14699: {'lr': 0.0004909719489586029, 'samples': 7526400, 'steps': 14699, 'loss/train': 1.2105036973953247}
-03/04/2022 06:43:26 - INFO - codeparrot_training - Step 14700: {'lr': 0.0004909705356721919, 'samples': 7526912, 'steps': 14700, 'loss/train': 2.2474896907806396}
-03/04/2022 06:43:26 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/04/2022 06:43:32 - INFO - codeparrot_training - Step 14701: {'lr': 0.0004909691222772032, 'samples': 7527424, 'steps': 14701, 'loss/train': 1.917746901512146}
-03/04/2022 06:43:35 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/04/2022 06:43:37 - INFO - codeparrot_training - Step 14702: {'lr': 0.0004909677087736375, 'samples': 7527936, 'steps': 14702, 'loss/train': 2.4915997982025146}
-03/04/2022 06:43:40 - INFO - codeparrot_training - Step 14703: {'lr': 0.0004909662951614955, 'samples': 7528448, 'steps': 14703, 'loss/train': 2.1721649169921875}
-03/04/2022 06:43:43 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/04/2022 06:43:45 - INFO - codeparrot_training - Step 14704: {'lr': 0.0004909648814407779, 'samples': 7528960, 'steps': 14704, 'loss/train': 1.4694454669952393}
-03/04/2022 06:43:49 - INFO - codeparrot_training - Step 14705: {'lr': 0.0004909634676114851, 'samples': 7529472, 'steps': 14705, 'loss/train': 2.041003942489624}
-03/04/2022 06:43:51 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 06:43:54 - INFO - codeparrot_training - Step 14706: {'lr': 0.000490962053673618, 'samples': 7529984, 'steps': 14706, 'loss/train': 1.6300005912780762}
-03/04/2022 06:43:57 - INFO - codeparrot_training - Step 14707: {'lr': 0.0004909606396271771, 'samples': 7530496, 'steps': 14707, 'loss/train': 0.8956642746925354}
-03/04/2022 06:44:00 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/04/2022 06:44:02 - INFO - codeparrot_training - Step 14708: {'lr': 0.000490959225472163, 'samples': 7531008, 'steps': 14708, 'loss/train': 2.7529919147491455}
-03/04/2022 06:44:06 - INFO - codeparrot_training - Step 14709: {'lr': 0.0004909578112085764, 'samples': 7531520, 'steps': 14709, 'loss/train': 2.400735855102539}
-03/04/2022 06:44:09 - INFO - codeparrot_training - Step 14710: {'lr': 0.0004909563968364179, 'samples': 7532032, 'steps': 14710, 'loss/train': 2.3151586055755615}
-03/04/2022 06:44:09 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 06:44:14 - INFO - codeparrot_training - Step 14711: {'lr': 0.0004909549823556883, 'samples': 7532544, 'steps': 14711, 'loss/train': 2.5324535369873047}
-03/04/2022 06:44:17 - INFO - codeparrot_training - Step 14712: {'lr': 0.000490953567766388, 'samples': 7533056, 'steps': 14712, 'loss/train': 1.6273378133773804}
-03/04/2022 06:44:17 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/04/2022 06:44:23 - INFO - codeparrot_training - Step 14713: {'lr': 0.0004909521530685177, 'samples': 7533568, 'steps': 14713, 'loss/train': 2.1107065677642822}
-03/04/2022 06:44:26 - INFO - codeparrot_training - Step 14714: {'lr': 0.0004909507382620782, 'samples': 7534080, 'steps': 14714, 'loss/train': 2.4669392108917236}
-03/04/2022 06:44:26 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/04/2022 06:44:31 - INFO - codeparrot_training - Step 14715: {'lr': 0.0004909493233470699, 'samples': 7534592, 'steps': 14715, 'loss/train': 1.101711392402649}
-03/04/2022 06:44:34 - INFO - codeparrot_training - Step 14716: {'lr': 0.0004909479083234936, 'samples': 7535104, 'steps': 14716, 'loss/train': 1.6404054164886475}
-03/04/2022 06:44:34 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/04/2022 06:44:39 - INFO - codeparrot_training - Step 14717: {'lr': 0.0004909464931913499, 'samples': 7535616, 'steps': 14717, 'loss/train': 1.8112688064575195}
-03/04/2022 06:44:42 - INFO - codeparrot_training - Step 14718: {'lr': 0.0004909450779506393, 'samples': 7536128, 'steps': 14718, 'loss/train': 2.130506992340088}
-03/04/2022 06:44:43 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 06:44:48 - INFO - codeparrot_training - Step 14719: {'lr': 0.0004909436626013628, 'samples': 7536640, 'steps': 14719, 'loss/train': 1.4773776531219482}
-03/04/2022 06:44:51 - INFO - codeparrot_training - Step 14720: {'lr': 0.0004909422471435207, 'samples': 7537152, 'steps': 14720, 'loss/train': 2.170724391937256}
-03/04/2022 06:44:51 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 06:44:56 - INFO - codeparrot_training - Step 14721: {'lr': 0.0004909408315771136, 'samples': 7537664, 'steps': 14721, 'loss/train': 2.3787031173706055}
-03/04/2022 06:44:59 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/04/2022 06:45:01 - INFO - codeparrot_training - Step 14722: {'lr': 0.0004909394159021425, 'samples': 7538176, 'steps': 14722, 'loss/train': 1.292271375656128}
-03/04/2022 06:45:05 - INFO - codeparrot_training - Step 14723: {'lr': 0.0004909380001186077, 'samples': 7538688, 'steps': 14723, 'loss/train': 2.110703229904175}
-03/04/2022 06:45:07 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/04/2022 06:45:10 - INFO - codeparrot_training - Step 14724: {'lr': 0.00049093658422651, 'samples': 7539200, 'steps': 14724, 'loss/train': 1.499112606048584}
-03/04/2022 06:45:13 - INFO - codeparrot_training - Step 14725: {'lr': 0.00049093516822585, 'samples': 7539712, 'steps': 14725, 'loss/train': 2.119870662689209}
-03/04/2022 06:45:16 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 06:45:18 - INFO - codeparrot_training - Step 14726: {'lr': 0.0004909337521166282, 'samples': 7540224, 'steps': 14726, 'loss/train': 1.8298006057739258}
-03/04/2022 06:45:22 - INFO - codeparrot_training - Step 14727: {'lr': 0.0004909323358988455, 'samples': 7540736, 'steps': 14727, 'loss/train': 1.5055103302001953}
-03/04/2022 06:45:24 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 06:45:27 - INFO - codeparrot_training - Step 14728: {'lr': 0.0004909309195725024, 'samples': 7541248, 'steps': 14728, 'loss/train': 2.972954273223877}
-03/04/2022 06:45:30 - INFO - codeparrot_training - Step 14729: {'lr': 0.0004909295031375996, 'samples': 7541760, 'steps': 14729, 'loss/train': 1.897033929824829}
-03/04/2022 06:45:33 - INFO - codeparrot_training - Step 14730: {'lr': 0.0004909280865941375, 'samples': 7542272, 'steps': 14730, 'loss/train': 1.6935392618179321}
-03/04/2022 06:45:34 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/04/2022 06:45:39 - INFO - codeparrot_training - Step 14731: {'lr': 0.0004909266699421171, 'samples': 7542784, 'steps': 14731, 'loss/train': 1.11825430393219}
-03/04/2022 06:45:42 - INFO - codeparrot_training - Step 14732: {'lr': 0.0004909252531815388, 'samples': 7543296, 'steps': 14732, 'loss/train': 1.7479898929595947}
-03/04/2022 06:45:42 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 06:45:47 - INFO - codeparrot_training - Step 14733: {'lr': 0.0004909238363124033, 'samples': 7543808, 'steps': 14733, 'loss/train': 2.2148473262786865}
-03/04/2022 06:45:51 - INFO - codeparrot_training - Step 14734: {'lr': 0.0004909224193347112, 'samples': 7544320, 'steps': 14734, 'loss/train': 2.3035871982574463}
-03/04/2022 06:45:51 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 06:45:56 - INFO - codeparrot_training - Step 14735: {'lr': 0.0004909210022484633, 'samples': 7544832, 'steps': 14735, 'loss/train': 2.125235080718994}
-03/04/2022 06:45:59 - INFO - codeparrot_training - Step 14736: {'lr': 0.00049091958505366, 'samples': 7545344, 'steps': 14736, 'loss/train': 1.5646641254425049}
-03/04/2022 06:45:59 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/04/2022 06:46:05 - INFO - codeparrot_training - Step 14737: {'lr': 0.000490918167750302, 'samples': 7545856, 'steps': 14737, 'loss/train': 1.6524014472961426}
-03/04/2022 06:46:07 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 06:46:10 - INFO - codeparrot_training - Step 14738: {'lr': 0.00049091675033839, 'samples': 7546368, 'steps': 14738, 'loss/train': 2.2973427772521973}
-03/04/2022 06:46:13 - INFO - codeparrot_training - Step 14739: {'lr': 0.0004909153328179248, 'samples': 7546880, 'steps': 14739, 'loss/train': 0.9242503046989441}
-03/04/2022 06:46:15 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/04/2022 06:46:18 - INFO - codeparrot_training - Step 14740: {'lr': 0.0004909139151889067, 'samples': 7547392, 'steps': 14740, 'loss/train': 2.1719131469726562}
-03/04/2022 06:46:21 - INFO - codeparrot_training - Step 14741: {'lr': 0.0004909124974513366, 'samples': 7547904, 'steps': 14741, 'loss/train': 2.1536879539489746}
-03/04/2022 06:46:24 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/04/2022 06:46:27 - INFO - codeparrot_training - Step 14742: {'lr': 0.000490911079605215, 'samples': 7548416, 'steps': 14742, 'loss/train': 2.5071182250976562}
-03/04/2022 06:46:30 - INFO - codeparrot_training - Step 14743: {'lr': 0.0004909096616505426, 'samples': 7548928, 'steps': 14743, 'loss/train': 1.7381165027618408}
-03/04/2022 06:46:32 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/04/2022 06:46:35 - INFO - codeparrot_training - Step 14744: {'lr': 0.00049090824358732, 'samples': 7549440, 'steps': 14744, 'loss/train': 2.0084168910980225}
-03/04/2022 06:46:38 - INFO - codeparrot_training - Step 14745: {'lr': 0.0004909068254155479, 'samples': 7549952, 'steps': 14745, 'loss/train': 1.2694228887557983}
-03/04/2022 06:46:41 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/04/2022 06:46:44 - INFO - codeparrot_training - Step 14746: {'lr': 0.0004909054071352269, 'samples': 7550464, 'steps': 14746, 'loss/train': 1.3982563018798828}
-03/04/2022 06:46:47 - INFO - codeparrot_training - Step 14747: {'lr': 0.0004909039887463576, 'samples': 7550976, 'steps': 14747, 'loss/train': 2.3374099731445312}
-03/04/2022 06:46:49 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 06:46:52 - INFO - codeparrot_training - Step 14748: {'lr': 0.0004909025702489407, 'samples': 7551488, 'steps': 14748, 'loss/train': 1.9864240884780884}
-03/04/2022 06:46:55 - INFO - codeparrot_training - Step 14749: {'lr': 0.0004909011516429768, 'samples': 7552000, 'steps': 14749, 'loss/train': 1.9765621423721313}
-03/04/2022 06:46:57 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/04/2022 06:47:00 - INFO - codeparrot_training - Step 14750: {'lr': 0.0004908997329284667, 'samples': 7552512, 'steps': 14750, 'loss/train': 2.1755943298339844}
-03/04/2022 06:47:04 - INFO - codeparrot_training - Step 14751: {'lr': 0.0004908983141054107, 'samples': 7553024, 'steps': 14751, 'loss/train': 2.1491146087646484}
-03/04/2022 06:47:06 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/04/2022 06:47:09 - INFO - codeparrot_training - Step 14752: {'lr': 0.0004908968951738098, 'samples': 7553536, 'steps': 14752, 'loss/train': 2.0037455558776855}
-03/04/2022 06:47:12 - INFO - codeparrot_training - Step 14753: {'lr': 0.0004908954761336643, 'samples': 7554048, 'steps': 14753, 'loss/train': 2.3902029991149902}
-03/04/2022 06:47:14 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 06:47:17 - INFO - codeparrot_training - Step 14754: {'lr': 0.0004908940569849751, 'samples': 7554560, 'steps': 14754, 'loss/train': 2.0751538276672363}
-03/04/2022 06:47:21 - INFO - codeparrot_training - Step 14755: {'lr': 0.0004908926377277428, 'samples': 7555072, 'steps': 14755, 'loss/train': 1.230668067932129}
-03/04/2022 06:47:23 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/04/2022 06:47:26 - INFO - codeparrot_training - Step 14756: {'lr': 0.000490891218361968, 'samples': 7555584, 'steps': 14756, 'loss/train': 2.204907178878784}
-03/04/2022 06:47:29 - INFO - codeparrot_training - Step 14757: {'lr': 0.0004908897988876512, 'samples': 7556096, 'steps': 14757, 'loss/train': 0.6431739330291748}
-03/04/2022 06:47:31 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/04/2022 06:47:35 - INFO - codeparrot_training - Step 14758: {'lr': 0.0004908883793047934, 'samples': 7556608, 'steps': 14758, 'loss/train': 2.2087621688842773}
-03/04/2022 06:47:38 - INFO - codeparrot_training - Step 14759: {'lr': 0.0004908869596133948, 'samples': 7557120, 'steps': 14759, 'loss/train': 1.9185585975646973}
-03/04/2022 06:47:41 - INFO - codeparrot_training - Step 14760: {'lr': 0.0004908855398134563, 'samples': 7557632, 'steps': 14760, 'loss/train': 2.2183895111083984}
-03/04/2022 06:47:43 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 06:47:46 - INFO - codeparrot_training - Step 14761: {'lr': 0.0004908841199049785, 'samples': 7558144, 'steps': 14761, 'loss/train': 2.723599672317505}
-03/04/2022 06:47:50 - INFO - codeparrot_training - Step 14762: {'lr': 0.0004908826998879621, 'samples': 7558656, 'steps': 14762, 'loss/train': 1.9236141443252563}
-03/04/2022 06:47:52 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 06:47:55 - INFO - codeparrot_training - Step 14763: {'lr': 0.0004908812797624077, 'samples': 7559168, 'steps': 14763, 'loss/train': 1.8582115173339844}
-03/04/2022 06:47:58 - INFO - codeparrot_training - Step 14764: {'lr': 0.0004908798595283159, 'samples': 7559680, 'steps': 14764, 'loss/train': 2.219526767730713}
-03/04/2022 06:48:01 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/04/2022 06:48:03 - INFO - codeparrot_training - Step 14765: {'lr': 0.0004908784391856872, 'samples': 7560192, 'steps': 14765, 'loss/train': 1.60055673122406}
-03/04/2022 06:48:06 - INFO - codeparrot_training - Step 14766: {'lr': 0.0004908770187345225, 'samples': 7560704, 'steps': 14766, 'loss/train': 1.7707672119140625}
-03/04/2022 06:48:09 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/04/2022 06:48:12 - INFO - codeparrot_training - Step 14767: {'lr': 0.0004908755981748223, 'samples': 7561216, 'steps': 14767, 'loss/train': 1.1856181621551514}
-03/04/2022 06:48:15 - INFO - codeparrot_training - Step 14768: {'lr': 0.0004908741775065873, 'samples': 7561728, 'steps': 14768, 'loss/train': 2.1365485191345215}
-03/04/2022 06:48:17 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/04/2022 06:48:20 - INFO - codeparrot_training - Step 14769: {'lr': 0.0004908727567298181, 'samples': 7562240, 'steps': 14769, 'loss/train': 1.617590308189392}
-03/04/2022 06:48:23 - INFO - codeparrot_training - Step 14770: {'lr': 0.0004908713358445154, 'samples': 7562752, 'steps': 14770, 'loss/train': 2.2341930866241455}
-03/04/2022 06:48:26 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 06:48:29 - INFO - codeparrot_training - Step 14771: {'lr': 0.0004908699148506797, 'samples': 7563264, 'steps': 14771, 'loss/train': 2.6435506343841553}
-03/04/2022 06:48:32 - INFO - codeparrot_training - Step 14772: {'lr': 0.0004908684937483119, 'samples': 7563776, 'steps': 14772, 'loss/train': 2.4005675315856934}
-03/04/2022 06:48:34 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/04/2022 06:48:37 - INFO - codeparrot_training - Step 14773: {'lr': 0.0004908670725374122, 'samples': 7564288, 'steps': 14773, 'loss/train': 2.1996238231658936}
-03/04/2022 06:48:40 - INFO - codeparrot_training - Step 14774: {'lr': 0.0004908656512179817, 'samples': 7564800, 'steps': 14774, 'loss/train': 1.5077009201049805}
-03/04/2022 06:48:43 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/04/2022 06:48:45 - INFO - codeparrot_training - Step 14775: {'lr': 0.0004908642297900209, 'samples': 7565312, 'steps': 14775, 'loss/train': 1.8075239658355713}
-03/04/2022 06:48:49 - INFO - codeparrot_training - Step 14776: {'lr': 0.0004908628082535303, 'samples': 7565824, 'steps': 14776, 'loss/train': 2.71407151222229}
-03/04/2022 06:48:51 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 06:48:54 - INFO - codeparrot_training - Step 14777: {'lr': 0.0004908613866085106, 'samples': 7566336, 'steps': 14777, 'loss/train': 2.263681650161743}
-03/04/2022 06:48:57 - INFO - codeparrot_training - Step 14778: {'lr': 0.0004908599648549626, 'samples': 7566848, 'steps': 14778, 'loss/train': 2.114062786102295}
-03/04/2022 06:49:00 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 06:49:02 - INFO - codeparrot_training - Step 14779: {'lr': 0.0004908585429928867, 'samples': 7567360, 'steps': 14779, 'loss/train': 1.8943430185317993}
-03/04/2022 06:49:05 - INFO - codeparrot_training - Step 14780: {'lr': 0.0004908571210222837, 'samples': 7567872, 'steps': 14780, 'loss/train': 2.3442790508270264}
-03/04/2022 06:49:08 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/04/2022 06:49:10 - INFO - codeparrot_training - Step 14781: {'lr': 0.0004908556989431543, 'samples': 7568384, 'steps': 14781, 'loss/train': 2.070960760116577}
-03/04/2022 06:49:14 - INFO - codeparrot_training - Step 14782: {'lr': 0.0004908542767554988, 'samples': 7568896, 'steps': 14782, 'loss/train': 0.7488842010498047}
-03/04/2022 06:49:16 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/04/2022 06:49:19 - INFO - codeparrot_training - Step 14783: {'lr': 0.0004908528544593184, 'samples': 7569408, 'steps': 14783, 'loss/train': 1.1876795291900635}
-03/04/2022 06:49:22 - INFO - codeparrot_training - Step 14784: {'lr': 0.0004908514320546132, 'samples': 7569920, 'steps': 14784, 'loss/train': 2.2304956912994385}
-03/04/2022 06:49:24 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/04/2022 06:49:27 - INFO - codeparrot_training - Step 14785: {'lr': 0.000490850009541384, 'samples': 7570432, 'steps': 14785, 'loss/train': 1.3856542110443115}
-03/04/2022 06:49:30 - INFO - codeparrot_training - Step 14786: {'lr': 0.0004908485869196317, 'samples': 7570944, 'steps': 14786, 'loss/train': 2.1042659282684326}
-03/04/2022 06:49:33 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/04/2022 06:49:36 - INFO - codeparrot_training - Step 14787: {'lr': 0.0004908471641893566, 'samples': 7571456, 'steps': 14787, 'loss/train': 1.8831329345703125}
-03/04/2022 06:49:39 - INFO - codeparrot_training - Step 14788: {'lr': 0.0004908457413505596, 'samples': 7571968, 'steps': 14788, 'loss/train': 2.126296043395996}
-03/04/2022 06:49:41 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 06:49:44 - INFO - codeparrot_training - Step 14789: {'lr': 0.0004908443184032411, 'samples': 7572480, 'steps': 14789, 'loss/train': 2.4326670169830322}
-03/04/2022 06:49:47 - INFO - codeparrot_training - Step 14790: {'lr': 0.0004908428953474019, 'samples': 7572992, 'steps': 14790, 'loss/train': 1.8303239345550537}
-03/04/2022 06:49:49 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 06:49:53 - INFO - codeparrot_training - Step 14791: {'lr': 0.0004908414721830427, 'samples': 7573504, 'steps': 14791, 'loss/train': 2.38638973236084}
-03/04/2022 06:49:56 - INFO - codeparrot_training - Step 14792: {'lr': 0.000490840048910164, 'samples': 7574016, 'steps': 14792, 'loss/train': 1.5329978466033936}
-03/04/2022 06:49:58 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/04/2022 06:50:01 - INFO - codeparrot_training - Step 14793: {'lr': 0.0004908386255287664, 'samples': 7574528, 'steps': 14793, 'loss/train': 2.197253704071045}
-03/04/2022 06:50:04 - INFO - codeparrot_training - Step 14794: {'lr': 0.0004908372020388508, 'samples': 7575040, 'steps': 14794, 'loss/train': 1.618466854095459}
-03/04/2022 06:50:07 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/04/2022 06:50:10 - INFO - codeparrot_training - Step 14795: {'lr': 0.0004908357784404175, 'samples': 7575552, 'steps': 14795, 'loss/train': 2.030888795852661}
-03/04/2022 06:50:13 - INFO - codeparrot_training - Step 14796: {'lr': 0.0004908343547334674, 'samples': 7576064, 'steps': 14796, 'loss/train': 1.6332695484161377}
-03/04/2022 06:50:15 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 06:50:18 - INFO - codeparrot_training - Step 14797: {'lr': 0.0004908329309180011, 'samples': 7576576, 'steps': 14797, 'loss/train': 1.1188822984695435}
-03/04/2022 06:50:21 - INFO - codeparrot_training - Step 14798: {'lr': 0.0004908315069940191, 'samples': 7577088, 'steps': 14798, 'loss/train': 2.0643434524536133}
-03/04/2022 06:50:23 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 06:50:26 - INFO - codeparrot_training - Step 14799: {'lr': 0.0004908300829615222, 'samples': 7577600, 'steps': 14799, 'loss/train': 1.1506123542785645}
-03/04/2022 06:50:30 - INFO - codeparrot_training - Step 14800: {'lr': 0.000490828658820511, 'samples': 7578112, 'steps': 14800, 'loss/train': 2.809218645095825}
-03/04/2022 06:50:31 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 06:50:35 - INFO - codeparrot_training - Step 14801: {'lr': 0.0004908272345709861, 'samples': 7578624, 'steps': 14801, 'loss/train': 2.1479434967041016}
-03/04/2022 06:50:38 - INFO - codeparrot_training - Step 14802: {'lr': 0.0004908258102129481, 'samples': 7579136, 'steps': 14802, 'loss/train': 2.6268274784088135}
-03/04/2022 06:50:40 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 06:50:43 - INFO - codeparrot_training - Step 14803: {'lr': 0.0004908243857463978, 'samples': 7579648, 'steps': 14803, 'loss/train': 1.0144504308700562}
-03/04/2022 06:50:46 - INFO - codeparrot_training - Step 14804: {'lr': 0.0004908229611713357, 'samples': 7580160, 'steps': 14804, 'loss/train': 1.5571867227554321}
-03/04/2022 06:50:48 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/04/2022 06:50:52 - INFO - codeparrot_training - Step 14805: {'lr': 0.0004908215364877625, 'samples': 7580672, 'steps': 14805, 'loss/train': 1.9515894651412964}
-03/04/2022 06:50:55 - INFO - codeparrot_training - Step 14806: {'lr': 0.0004908201116956788, 'samples': 7581184, 'steps': 14806, 'loss/train': 1.951917052268982}
-03/04/2022 06:50:57 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/04/2022 06:51:00 - INFO - codeparrot_training - Step 14807: {'lr': 0.0004908186867950854, 'samples': 7581696, 'steps': 14807, 'loss/train': 2.310009479522705}
-03/04/2022 06:51:03 - INFO - codeparrot_training - Step 14808: {'lr': 0.0004908172617859826, 'samples': 7582208, 'steps': 14808, 'loss/train': 2.3065805435180664}
-03/04/2022 06:51:05 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/04/2022 06:51:09 - INFO - codeparrot_training - Step 14809: {'lr': 0.0004908158366683714, 'samples': 7582720, 'steps': 14809, 'loss/train': 1.7898012399673462}
-03/04/2022 06:51:12 - INFO - codeparrot_training - Step 14810: {'lr': 0.0004908144114422523, 'samples': 7583232, 'steps': 14810, 'loss/train': 1.957484483718872}
-03/04/2022 06:51:13 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 06:51:17 - INFO - codeparrot_training - Step 14811: {'lr': 0.000490812986107626, 'samples': 7583744, 'steps': 14811, 'loss/train': 0.3570864498615265}
-03/04/2022 06:51:20 - INFO - codeparrot_training - Step 14812: {'lr': 0.000490811560664493, 'samples': 7584256, 'steps': 14812, 'loss/train': 0.472942978143692}
-03/04/2022 06:51:22 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/04/2022 06:51:25 - INFO - codeparrot_training - Step 14813: {'lr': 0.000490810135112854, 'samples': 7584768, 'steps': 14813, 'loss/train': 1.538577675819397}
-03/04/2022 06:51:29 - INFO - codeparrot_training - Step 14814: {'lr': 0.0004908087094527097, 'samples': 7585280, 'steps': 14814, 'loss/train': 1.5698546171188354}
-03/04/2022 06:51:30 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 06:51:34 - INFO - codeparrot_training - Step 14815: {'lr': 0.0004908072836840607, 'samples': 7585792, 'steps': 14815, 'loss/train': 2.5484986305236816}
-03/04/2022 06:51:37 - INFO - codeparrot_training - Step 14816: {'lr': 0.0004908058578069077, 'samples': 7586304, 'steps': 14816, 'loss/train': 4.311676502227783}
-03/04/2022 06:51:40 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/04/2022 06:51:42 - INFO - codeparrot_training - Step 14817: {'lr': 0.0004908044318212512, 'samples': 7586816, 'steps': 14817, 'loss/train': 1.7337148189544678}
-03/04/2022 06:51:46 - INFO - codeparrot_training - Step 14818: {'lr': 0.000490803005727092, 'samples': 7587328, 'steps': 14818, 'loss/train': 2.038957118988037}
-03/04/2022 06:51:48 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/04/2022 06:51:51 - INFO - codeparrot_training - Step 14819: {'lr': 0.0004908015795244307, 'samples': 7587840, 'steps': 14819, 'loss/train': 2.022719383239746}
-03/04/2022 06:51:54 - INFO - codeparrot_training - Step 14820: {'lr': 0.0004908001532132679, 'samples': 7588352, 'steps': 14820, 'loss/train': 1.4078097343444824}
-03/04/2022 06:51:56 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/04/2022 06:51:59 - INFO - codeparrot_training - Step 14821: {'lr': 0.0004907987267936042, 'samples': 7588864, 'steps': 14821, 'loss/train': 2.0463342666625977}
-03/04/2022 06:52:02 - INFO - codeparrot_training - Step 14822: {'lr': 0.0004907973002654404, 'samples': 7589376, 'steps': 14822, 'loss/train': 1.795935869216919}
-03/04/2022 06:52:05 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 06:52:08 - INFO - codeparrot_training - Step 14823: {'lr': 0.0004907958736287771, 'samples': 7589888, 'steps': 14823, 'loss/train': 2.0834760665893555}
-03/04/2022 06:52:11 - INFO - codeparrot_training - Step 14824: {'lr': 0.0004907944468836148, 'samples': 7590400, 'steps': 14824, 'loss/train': 2.5151803493499756}
-03/04/2022 06:52:13 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/04/2022 06:52:16 - INFO - codeparrot_training - Step 14825: {'lr': 0.0004907930200299543, 'samples': 7590912, 'steps': 14825, 'loss/train': 2.5355141162872314}
-03/04/2022 06:52:19 - INFO - codeparrot_training - Step 14826: {'lr': 0.0004907915930677961, 'samples': 7591424, 'steps': 14826, 'loss/train': 1.2377476692199707}
-03/04/2022 06:52:22 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 06:52:25 - INFO - codeparrot_training - Step 14827: {'lr': 0.000490790165997141, 'samples': 7591936, 'steps': 14827, 'loss/train': 2.1949877738952637}
-03/04/2022 06:52:28 - INFO - codeparrot_training - Step 14828: {'lr': 0.0004907887388179896, 'samples': 7592448, 'steps': 14828, 'loss/train': 2.7577333450317383}
-03/04/2022 06:52:30 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/04/2022 06:52:33 - INFO - codeparrot_training - Step 14829: {'lr': 0.0004907873115303424, 'samples': 7592960, 'steps': 14829, 'loss/train': 0.5537659525871277}
-03/04/2022 06:52:36 - INFO - codeparrot_training - Step 14830: {'lr': 0.0004907858841342002, 'samples': 7593472, 'steps': 14830, 'loss/train': 1.895676612854004}
-03/04/2022 06:52:38 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/04/2022 06:52:42 - INFO - codeparrot_training - Step 14831: {'lr': 0.0004907844566295637, 'samples': 7593984, 'steps': 14831, 'loss/train': 0.7850965261459351}
-03/04/2022 06:52:45 - INFO - codeparrot_training - Step 14832: {'lr': 0.0004907830290164332, 'samples': 7594496, 'steps': 14832, 'loss/train': 1.9194023609161377}
-03/04/2022 06:52:49 - INFO - codeparrot_training - Step 14833: {'lr': 0.0004907816012948098, 'samples': 7595008, 'steps': 14833, 'loss/train': 1.253013253211975}
-03/04/2022 06:52:51 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/04/2022 06:52:54 - INFO - codeparrot_training - Step 14834: {'lr': 0.0004907801734646938, 'samples': 7595520, 'steps': 14834, 'loss/train': 2.457982063293457}
-03/04/2022 06:52:57 - INFO - codeparrot_training - Step 14835: {'lr': 0.000490778745526086, 'samples': 7596032, 'steps': 14835, 'loss/train': 1.756037712097168}
-03/04/2022 06:52:59 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/04/2022 06:53:02 - INFO - codeparrot_training - Step 14836: {'lr': 0.000490777317478987, 'samples': 7596544, 'steps': 14836, 'loss/train': 2.1507925987243652}
-03/04/2022 06:53:05 - INFO - codeparrot_training - Step 14837: {'lr': 0.0004907758893233975, 'samples': 7597056, 'steps': 14837, 'loss/train': 2.0984346866607666}
-03/04/2022 06:53:07 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 06:53:11 - INFO - codeparrot_training - Step 14838: {'lr': 0.0004907744610593181, 'samples': 7597568, 'steps': 14838, 'loss/train': 0.6184648871421814}
-03/04/2022 06:53:14 - INFO - codeparrot_training - Step 14839: {'lr': 0.0004907730326867495, 'samples': 7598080, 'steps': 14839, 'loss/train': 1.4238630533218384}
-03/04/2022 06:53:16 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/04/2022 06:53:19 - INFO - codeparrot_training - Step 14840: {'lr': 0.0004907716042056921, 'samples': 7598592, 'steps': 14840, 'loss/train': 1.987376093864441}
-03/04/2022 06:53:22 - INFO - codeparrot_training - Step 14841: {'lr': 0.0004907701756161469, 'samples': 7599104, 'steps': 14841, 'loss/train': 2.0438320636749268}
-03/04/2022 06:53:24 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/04/2022 06:53:28 - INFO - codeparrot_training - Step 14842: {'lr': 0.0004907687469181143, 'samples': 7599616, 'steps': 14842, 'loss/train': 1.4644241333007812}
-03/04/2022 06:53:31 - INFO - codeparrot_training - Step 14843: {'lr': 0.000490767318111595, 'samples': 7600128, 'steps': 14843, 'loss/train': 1.9290045499801636}
-03/04/2022 06:53:33 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/04/2022 06:53:36 - INFO - codeparrot_training - Step 14844: {'lr': 0.0004907658891965897, 'samples': 7600640, 'steps': 14844, 'loss/train': 1.722917079925537}
-03/04/2022 06:53:39 - INFO - codeparrot_training - Step 14845: {'lr': 0.000490764460173099, 'samples': 7601152, 'steps': 14845, 'loss/train': 2.748063564300537}
-03/04/2022 06:53:41 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 06:53:44 - INFO - codeparrot_training - Step 14846: {'lr': 0.0004907630310411236, 'samples': 7601664, 'steps': 14846, 'loss/train': 1.333661675453186}
-03/04/2022 06:53:48 - INFO - codeparrot_training - Step 14847: {'lr': 0.000490761601800664, 'samples': 7602176, 'steps': 14847, 'loss/train': 1.8628424406051636}
-03/04/2022 06:53:49 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/04/2022 06:53:53 - INFO - codeparrot_training - Step 14848: {'lr': 0.000490760172451721, 'samples': 7602688, 'steps': 14848, 'loss/train': 2.586153745651245}
-03/04/2022 06:53:56 - INFO - codeparrot_training - Step 14849: {'lr': 0.0004907587429942952, 'samples': 7603200, 'steps': 14849, 'loss/train': 0.47511401772499084}
-03/04/2022 06:53:59 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/04/2022 06:54:02 - INFO - codeparrot_training - Step 14850: {'lr': 0.0004907573134283872, 'samples': 7603712, 'steps': 14850, 'loss/train': 1.8210901021957397}
-03/04/2022 06:54:05 - INFO - codeparrot_training - Step 14851: {'lr': 0.0004907558837539976, 'samples': 7604224, 'steps': 14851, 'loss/train': 2.25459361076355}
-03/04/2022 06:54:08 - INFO - codeparrot_training - Step 14852: {'lr': 0.0004907544539711272, 'samples': 7604736, 'steps': 14852, 'loss/train': 2.0861735343933105}
-03/04/2022 06:54:08 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/04/2022 06:54:13 - INFO - codeparrot_training - Step 14853: {'lr': 0.0004907530240797765, 'samples': 7605248, 'steps': 14853, 'loss/train': 2.2932205200195312}
-03/04/2022 06:54:16 - INFO - codeparrot_training - Step 14854: {'lr': 0.0004907515940799463, 'samples': 7605760, 'steps': 14854, 'loss/train': 2.1399428844451904}
-03/04/2022 06:54:17 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/04/2022 06:54:22 - INFO - codeparrot_training - Step 14855: {'lr': 0.000490750163971637, 'samples': 7606272, 'steps': 14855, 'loss/train': 1.9158586263656616}
-03/04/2022 06:54:25 - INFO - codeparrot_training - Step 14856: {'lr': 0.0004907487337548495, 'samples': 7606784, 'steps': 14856, 'loss/train': 0.3825668394565582}
-03/04/2022 06:54:25 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 06:54:30 - INFO - codeparrot_training - Step 14857: {'lr': 0.0004907473034295843, 'samples': 7607296, 'steps': 14857, 'loss/train': 1.1837295293807983}
-03/04/2022 06:54:33 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/04/2022 06:54:36 - INFO - codeparrot_training - Step 14858: {'lr': 0.0004907458729958422, 'samples': 7607808, 'steps': 14858, 'loss/train': 2.323683261871338}
-03/04/2022 06:54:39 - INFO - codeparrot_training - Step 14859: {'lr': 0.0004907444424536235, 'samples': 7608320, 'steps': 14859, 'loss/train': 2.2730228900909424}
-03/04/2022 06:54:41 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 06:54:44 - INFO - codeparrot_training - Step 14860: {'lr': 0.0004907430118029293, 'samples': 7608832, 'steps': 14860, 'loss/train': 2.102879762649536}
-03/04/2022 06:54:47 - INFO - codeparrot_training - Step 14861: {'lr': 0.0004907415810437598, 'samples': 7609344, 'steps': 14861, 'loss/train': 1.375104308128357}
-03/04/2022 06:54:50 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/04/2022 06:54:53 - INFO - codeparrot_training - Step 14862: {'lr': 0.0004907401501761159, 'samples': 7609856, 'steps': 14862, 'loss/train': 0.5515731573104858}
-03/04/2022 06:54:56 - INFO - codeparrot_training - Step 14863: {'lr': 0.0004907387191999984, 'samples': 7610368, 'steps': 14863, 'loss/train': 2.2391197681427}
-03/04/2022 06:54:58 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 06:55:01 - INFO - codeparrot_training - Step 14864: {'lr': 0.0004907372881154075, 'samples': 7610880, 'steps': 14864, 'loss/train': 1.1627790927886963}
-03/04/2022 06:55:04 - INFO - codeparrot_training - Step 14865: {'lr': 0.0004907358569223442, 'samples': 7611392, 'steps': 14865, 'loss/train': 0.9954293370246887}
-03/04/2022 06:55:07 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/04/2022 06:55:09 - INFO - codeparrot_training - Step 14866: {'lr': 0.000490734425620809, 'samples': 7611904, 'steps': 14866, 'loss/train': 1.747148036956787}
-03/04/2022 06:55:13 - INFO - codeparrot_training - Step 14867: {'lr': 0.0004907329942108027, 'samples': 7612416, 'steps': 14867, 'loss/train': 1.3641358613967896}
-03/04/2022 06:55:15 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/04/2022 06:55:18 - INFO - codeparrot_training - Step 14868: {'lr': 0.0004907315626923258, 'samples': 7612928, 'steps': 14868, 'loss/train': 0.8825204372406006}
-03/04/2022 06:55:21 - INFO - codeparrot_training - Step 14869: {'lr': 0.0004907301310653789, 'samples': 7613440, 'steps': 14869, 'loss/train': 1.9374521970748901}
-03/04/2022 06:55:23 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 06:55:26 - INFO - codeparrot_training - Step 14870: {'lr': 0.0004907286993299627, 'samples': 7613952, 'steps': 14870, 'loss/train': 2.520207643508911}
-03/04/2022 06:55:29 - INFO - codeparrot_training - Step 14871: {'lr': 0.0004907272674860779, 'samples': 7614464, 'steps': 14871, 'loss/train': 2.148125410079956}
-03/04/2022 06:55:31 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 06:55:35 - INFO - codeparrot_training - Step 14872: {'lr': 0.0004907258355337251, 'samples': 7614976, 'steps': 14872, 'loss/train': 1.9124828577041626}
-03/04/2022 06:55:38 - INFO - codeparrot_training - Step 14873: {'lr': 0.0004907244034729049, 'samples': 7615488, 'steps': 14873, 'loss/train': 1.3855915069580078}
-03/04/2022 06:55:40 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 06:55:43 - INFO - codeparrot_training - Step 14874: {'lr': 0.0004907229713036181, 'samples': 7616000, 'steps': 14874, 'loss/train': 2.184109926223755}
-03/04/2022 06:55:47 - INFO - codeparrot_training - Step 14875: {'lr': 0.0004907215390258652, 'samples': 7616512, 'steps': 14875, 'loss/train': 1.2043431997299194}
-03/04/2022 06:55:49 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/04/2022 06:55:52 - INFO - codeparrot_training - Step 14876: {'lr': 0.0004907201066396469, 'samples': 7617024, 'steps': 14876, 'loss/train': 1.9058420658111572}
-03/04/2022 06:55:55 - INFO - codeparrot_training - Step 14877: {'lr': 0.0004907186741449638, 'samples': 7617536, 'steps': 14877, 'loss/train': 1.8475852012634277}
-03/04/2022 06:55:57 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/04/2022 06:56:00 - INFO - codeparrot_training - Step 14878: {'lr': 0.0004907172415418166, 'samples': 7618048, 'steps': 14878, 'loss/train': 1.8471620082855225}
-03/04/2022 06:56:04 - INFO - codeparrot_training - Step 14879: {'lr': 0.0004907158088302059, 'samples': 7618560, 'steps': 14879, 'loss/train': 1.8655991554260254}
-03/04/2022 06:56:06 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/04/2022 06:56:09 - INFO - codeparrot_training - Step 14880: {'lr': 0.0004907143760101325, 'samples': 7619072, 'steps': 14880, 'loss/train': 1.5891087055206299}
-03/04/2022 06:56:12 - INFO - codeparrot_training - Step 14881: {'lr': 0.0004907129430815968, 'samples': 7619584, 'steps': 14881, 'loss/train': 1.7535555362701416}
-03/04/2022 06:56:14 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/04/2022 06:56:17 - INFO - codeparrot_training - Step 14882: {'lr': 0.0004907115100445996, 'samples': 7620096, 'steps': 14882, 'loss/train': 2.453596353530884}
-03/04/2022 06:56:20 - INFO - codeparrot_training - Step 14883: {'lr': 0.0004907100768991415, 'samples': 7620608, 'steps': 14883, 'loss/train': 2.5015950202941895}
-03/04/2022 06:56:23 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 06:56:26 - INFO - codeparrot_training - Step 14884: {'lr': 0.0004907086436452231, 'samples': 7621120, 'steps': 14884, 'loss/train': 2.205388069152832}
-03/04/2022 06:56:29 - INFO - codeparrot_training - Step 14885: {'lr': 0.0004907072102828451, 'samples': 7621632, 'steps': 14885, 'loss/train': 1.8657959699630737}
-03/04/2022 06:56:31 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/04/2022 06:56:34 - INFO - codeparrot_training - Step 14886: {'lr': 0.0004907057768120082, 'samples': 7622144, 'steps': 14886, 'loss/train': 1.9342138767242432}
-03/04/2022 06:56:37 - INFO - codeparrot_training - Step 14887: {'lr': 0.000490704343232713, 'samples': 7622656, 'steps': 14887, 'loss/train': 2.3188588619232178}
-03/04/2022 06:56:39 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 06:56:43 - INFO - codeparrot_training - Step 14888: {'lr': 0.0004907029095449602, 'samples': 7623168, 'steps': 14888, 'loss/train': 2.067739248275757}
-03/04/2022 06:56:46 - INFO - codeparrot_training - Step 14889: {'lr': 0.0004907014757487503, 'samples': 7623680, 'steps': 14889, 'loss/train': 2.173959255218506}
-03/04/2022 06:56:48 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/04/2022 06:56:51 - INFO - codeparrot_training - Step 14890: {'lr': 0.0004907000418440839, 'samples': 7624192, 'steps': 14890, 'loss/train': 2.1084046363830566}
-03/04/2022 06:56:54 - INFO - codeparrot_training - Step 14891: {'lr': 0.000490698607830962, 'samples': 7624704, 'steps': 14891, 'loss/train': 1.509670615196228}
-03/04/2022 06:56:56 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/04/2022 06:56:59 - INFO - codeparrot_training - Step 14892: {'lr': 0.0004906971737093849, 'samples': 7625216, 'steps': 14892, 'loss/train': 2.0196332931518555}
-03/04/2022 06:57:03 - INFO - codeparrot_training - Step 14893: {'lr': 0.0004906957394793534, 'samples': 7625728, 'steps': 14893, 'loss/train': 1.8569101095199585}
-03/04/2022 06:57:04 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/04/2022 06:57:08 - INFO - codeparrot_training - Step 14894: {'lr': 0.0004906943051408682, 'samples': 7626240, 'steps': 14894, 'loss/train': 1.747148036956787}
-03/04/2022 06:57:11 - INFO - codeparrot_training - Step 14895: {'lr': 0.0004906928706939296, 'samples': 7626752, 'steps': 14895, 'loss/train': 2.7112009525299072}
-03/04/2022 06:57:12 - INFO - codeparrot_training - Skipping example with length 524 (seq_length=1024)
-03/04/2022 06:57:16 - INFO - codeparrot_training - Step 14896: {'lr': 0.0004906914361385387, 'samples': 7627264, 'steps': 14896, 'loss/train': 2.2090160846710205}
-03/04/2022 06:57:20 - INFO - codeparrot_training - Step 14897: {'lr': 0.0004906900014746959, 'samples': 7627776, 'steps': 14897, 'loss/train': 2.2012648582458496}
-03/04/2022 06:57:22 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 06:57:25 - INFO - codeparrot_training - Step 14898: {'lr': 0.000490688566702402, 'samples': 7628288, 'steps': 14898, 'loss/train': 1.1052067279815674}
-03/04/2022 06:57:28 - INFO - codeparrot_training - Step 14899: {'lr': 0.0004906871318216575, 'samples': 7628800, 'steps': 14899, 'loss/train': 1.538980484008789}
-03/04/2022 06:57:30 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 06:57:33 - INFO - codeparrot_training - Step 14900: {'lr': 0.000490685696832463, 'samples': 7629312, 'steps': 14900, 'loss/train': 2.368417501449585}
-03/04/2022 06:57:37 - INFO - codeparrot_training - Step 14901: {'lr': 0.0004906842617348193, 'samples': 7629824, 'steps': 14901, 'loss/train': 2.719616651535034}
-03/04/2022 06:57:39 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/04/2022 06:57:42 - INFO - codeparrot_training - Step 14902: {'lr': 0.000490682826528727, 'samples': 7630336, 'steps': 14902, 'loss/train': 2.436473846435547}
-03/04/2022 06:57:45 - INFO - codeparrot_training - Step 14903: {'lr': 0.0004906813912141868, 'samples': 7630848, 'steps': 14903, 'loss/train': 1.8522274494171143}
-03/04/2022 06:57:47 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/04/2022 06:57:50 - INFO - codeparrot_training - Step 14904: {'lr': 0.0004906799557911992, 'samples': 7631360, 'steps': 14904, 'loss/train': 1.943617582321167}
-03/04/2022 06:57:53 - INFO - codeparrot_training - Step 14905: {'lr': 0.0004906785202597649, 'samples': 7631872, 'steps': 14905, 'loss/train': 2.2208662033081055}
-03/04/2022 06:57:56 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 06:57:59 - INFO - codeparrot_training - Step 14906: {'lr': 0.0004906770846198846, 'samples': 7632384, 'steps': 14906, 'loss/train': 1.9372612237930298}
-03/04/2022 06:58:02 - INFO - codeparrot_training - Step 14907: {'lr': 0.0004906756488715589, 'samples': 7632896, 'steps': 14907, 'loss/train': 2.0531349182128906}
-03/04/2022 06:58:04 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 06:58:07 - INFO - codeparrot_training - Step 14908: {'lr': 0.0004906742130147884, 'samples': 7633408, 'steps': 14908, 'loss/train': 1.6233035326004028}
-03/04/2022 06:58:10 - INFO - codeparrot_training - Step 14909: {'lr': 0.0004906727770495739, 'samples': 7633920, 'steps': 14909, 'loss/train': 1.8712456226348877}
-03/04/2022 06:58:13 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/04/2022 06:58:16 - INFO - codeparrot_training - Step 14910: {'lr': 0.000490671340975916, 'samples': 7634432, 'steps': 14910, 'loss/train': 3.089346408843994}
-03/04/2022 06:58:19 - INFO - codeparrot_training - Step 14911: {'lr': 0.0004906699047938153, 'samples': 7634944, 'steps': 14911, 'loss/train': 2.5405306816101074}
-03/04/2022 06:58:21 - INFO - codeparrot_training - Skipping example with length 996 (seq_length=1024)
-03/04/2022 06:58:24 - INFO - codeparrot_training - Step 14912: {'lr': 0.0004906684685032724, 'samples': 7635456, 'steps': 14912, 'loss/train': 1.4016519784927368}
-03/04/2022 06:58:27 - INFO - codeparrot_training - Step 14913: {'lr': 0.0004906670321042881, 'samples': 7635968, 'steps': 14913, 'loss/train': 2.0802087783813477}
-03/04/2022 06:58:30 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 06:58:33 - INFO - codeparrot_training - Step 14914: {'lr': 0.0004906655955968628, 'samples': 7636480, 'steps': 14914, 'loss/train': 1.4861576557159424}
-03/04/2022 06:58:36 - INFO - codeparrot_training - Step 14915: {'lr': 0.0004906641589809973, 'samples': 7636992, 'steps': 14915, 'loss/train': 2.187530994415283}
-03/04/2022 06:58:39 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 06:58:41 - INFO - codeparrot_training - Step 14916: {'lr': 0.0004906627222566924, 'samples': 7637504, 'steps': 14916, 'loss/train': 2.4307940006256104}
-03/04/2022 06:58:44 - INFO - codeparrot_training - Step 14917: {'lr': 0.0004906612854239485, 'samples': 7638016, 'steps': 14917, 'loss/train': 1.3820312023162842}
-03/04/2022 06:58:47 - INFO - codeparrot_training - Step 14918: {'lr': 0.0004906598484827663, 'samples': 7638528, 'steps': 14918, 'loss/train': 1.6620413064956665}
-03/04/2022 06:58:48 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 06:58:53 - INFO - codeparrot_training - Step 14919: {'lr': 0.0004906584114331465, 'samples': 7639040, 'steps': 14919, 'loss/train': 2.373547077178955}
-03/04/2022 06:58:56 - INFO - codeparrot_training - Step 14920: {'lr': 0.0004906569742750899, 'samples': 7639552, 'steps': 14920, 'loss/train': 2.427340269088745}
-03/04/2022 06:58:56 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/04/2022 06:59:01 - INFO - codeparrot_training - Step 14921: {'lr': 0.0004906555370085968, 'samples': 7640064, 'steps': 14921, 'loss/train': 1.9629123210906982}
-03/04/2022 06:59:05 - INFO - codeparrot_training - Step 14922: {'lr': 0.000490654099633668, 'samples': 7640576, 'steps': 14922, 'loss/train': 1.9595204591751099}
-03/04/2022 06:59:05 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/04/2022 06:59:10 - INFO - codeparrot_training - Step 14923: {'lr': 0.0004906526621503043, 'samples': 7641088, 'steps': 14923, 'loss/train': 1.7763832807540894}
-03/04/2022 06:59:13 - INFO - codeparrot_training - Step 14924: {'lr': 0.0004906512245585062, 'samples': 7641600, 'steps': 14924, 'loss/train': 0.3099691569805145}
-03/04/2022 06:59:13 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 06:59:19 - INFO - codeparrot_training - Step 14925: {'lr': 0.0004906497868582743, 'samples': 7642112, 'steps': 14925, 'loss/train': 1.1812852621078491}
-03/04/2022 06:59:22 - INFO - codeparrot_training - Step 14926: {'lr': 0.0004906483490496093, 'samples': 7642624, 'steps': 14926, 'loss/train': 2.0033152103424072}
-03/04/2022 06:59:22 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 06:59:27 - INFO - codeparrot_training - Step 14927: {'lr': 0.000490646911132512, 'samples': 7643136, 'steps': 14927, 'loss/train': 2.1338155269622803}
-03/04/2022 06:59:30 - INFO - codeparrot_training - Step 14928: {'lr': 0.0004906454731069828, 'samples': 7643648, 'steps': 14928, 'loss/train': 1.7533210515975952}
-03/04/2022 06:59:30 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/04/2022 06:59:36 - INFO - codeparrot_training - Step 14929: {'lr': 0.0004906440349730226, 'samples': 7644160, 'steps': 14929, 'loss/train': 1.7572906017303467}
-03/04/2022 06:59:39 - INFO - codeparrot_training - Step 14930: {'lr': 0.0004906425967306317, 'samples': 7644672, 'steps': 14930, 'loss/train': 1.225350260734558}
-03/04/2022 06:59:39 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/04/2022 06:59:44 - INFO - codeparrot_training - Step 14931: {'lr': 0.0004906411583798112, 'samples': 7645184, 'steps': 14931, 'loss/train': 2.207165002822876}
-03/04/2022 06:59:47 - INFO - codeparrot_training - Step 14932: {'lr': 0.0004906397199205614, 'samples': 7645696, 'steps': 14932, 'loss/train': 2.2762038707733154}
-03/04/2022 06:59:48 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/04/2022 06:59:53 - INFO - codeparrot_training - Step 14933: {'lr': 0.000490638281352883, 'samples': 7646208, 'steps': 14933, 'loss/train': 2.102884531021118}
-03/04/2022 06:59:56 - INFO - codeparrot_training - Step 14934: {'lr': 0.0004906368426767767, 'samples': 7646720, 'steps': 14934, 'loss/train': 1.58052396774292}
-03/04/2022 06:59:56 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/04/2022 07:00:01 - INFO - codeparrot_training - Step 14935: {'lr': 0.0004906354038922432, 'samples': 7647232, 'steps': 14935, 'loss/train': 1.4161901473999023}
-03/04/2022 07:00:04 - INFO - codeparrot_training - Step 14936: {'lr': 0.000490633964999283, 'samples': 7647744, 'steps': 14936, 'loss/train': 2.836017608642578}
-03/04/2022 07:00:05 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/04/2022 07:00:10 - INFO - codeparrot_training - Step 14937: {'lr': 0.000490632525997897, 'samples': 7648256, 'steps': 14937, 'loss/train': 2.168604850769043}
-03/04/2022 07:00:13 - INFO - codeparrot_training - Step 14938: {'lr': 0.0004906310868880856, 'samples': 7648768, 'steps': 14938, 'loss/train': 3.040954113006592}
-03/04/2022 07:00:13 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 07:00:18 - INFO - codeparrot_training - Step 14939: {'lr': 0.0004906296476698496, 'samples': 7649280, 'steps': 14939, 'loss/train': 2.9795429706573486}
-03/04/2022 07:00:21 - INFO - codeparrot_training - Step 14940: {'lr': 0.0004906282083431897, 'samples': 7649792, 'steps': 14940, 'loss/train': 2.3751585483551025}
-03/04/2022 07:00:22 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 07:00:27 - INFO - codeparrot_training - Step 14941: {'lr': 0.0004906267689081063, 'samples': 7650304, 'steps': 14941, 'loss/train': 1.2633403539657593}
-03/04/2022 07:00:30 - INFO - codeparrot_training - Step 14942: {'lr': 0.0004906253293646002, 'samples': 7650816, 'steps': 14942, 'loss/train': 1.737440586090088}
-03/04/2022 07:00:31 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/04/2022 07:00:35 - INFO - codeparrot_training - Step 14943: {'lr': 0.0004906238897126721, 'samples': 7651328, 'steps': 14943, 'loss/train': 2.3974080085754395}
-03/04/2022 07:00:38 - INFO - codeparrot_training - Step 14944: {'lr': 0.0004906224499523225, 'samples': 7651840, 'steps': 14944, 'loss/train': 2.2566750049591064}
-03/04/2022 07:00:39 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/04/2022 07:00:43 - INFO - codeparrot_training - Step 14945: {'lr': 0.0004906210100835522, 'samples': 7652352, 'steps': 14945, 'loss/train': 2.1617672443389893}
-03/04/2022 07:00:47 - INFO - codeparrot_training - Step 14946: {'lr': 0.0004906195701063617, 'samples': 7652864, 'steps': 14946, 'loss/train': 1.3634265661239624}
-03/04/2022 07:00:48 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/04/2022 07:00:52 - INFO - codeparrot_training - Step 14947: {'lr': 0.0004906181300207518, 'samples': 7653376, 'steps': 14947, 'loss/train': 1.7232900857925415}
-03/04/2022 07:00:55 - INFO - codeparrot_training - Step 14948: {'lr': 0.0004906166898267231, 'samples': 7653888, 'steps': 14948, 'loss/train': 1.9308077096939087}
-03/04/2022 07:00:56 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 07:01:01 - INFO - codeparrot_training - Step 14949: {'lr': 0.0004906152495242763, 'samples': 7654400, 'steps': 14949, 'loss/train': 2.3163673877716064}
-03/04/2022 07:01:04 - INFO - codeparrot_training - Step 14950: {'lr': 0.0004906138091134118, 'samples': 7654912, 'steps': 14950, 'loss/train': 2.4248881340026855}
-03/04/2022 07:01:07 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 07:01:09 - INFO - codeparrot_training - Step 14951: {'lr': 0.0004906123685941306, 'samples': 7655424, 'steps': 14951, 'loss/train': 0.3125258684158325}
-03/04/2022 07:01:12 - INFO - codeparrot_training - Step 14952: {'lr': 0.000490610927966433, 'samples': 7655936, 'steps': 14952, 'loss/train': 1.3769967555999756}
-03/04/2022 07:01:16 - INFO - codeparrot_training - Step 14953: {'lr': 0.00049060948723032, 'samples': 7656448, 'steps': 14953, 'loss/train': 2.551874876022339}
-03/04/2022 07:01:16 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 07:01:21 - INFO - codeparrot_training - Step 14954: {'lr': 0.000490608046385792, 'samples': 7656960, 'steps': 14954, 'loss/train': 1.9698054790496826}
-03/04/2022 07:01:24 - INFO - codeparrot_training - Step 14955: {'lr': 0.0004906066054328498, 'samples': 7657472, 'steps': 14955, 'loss/train': 1.6258517503738403}
-03/04/2022 07:01:24 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/04/2022 07:01:30 - INFO - codeparrot_training - Step 14956: {'lr': 0.0004906051643714939, 'samples': 7657984, 'steps': 14956, 'loss/train': 1.954817533493042}
-03/04/2022 07:01:33 - INFO - codeparrot_training - Step 14957: {'lr': 0.000490603723201725, 'samples': 7658496, 'steps': 14957, 'loss/train': 2.226294755935669}
-03/04/2022 07:01:33 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/04/2022 07:01:38 - INFO - codeparrot_training - Step 14958: {'lr': 0.0004906022819235438, 'samples': 7659008, 'steps': 14958, 'loss/train': 1.972947359085083}
-03/04/2022 07:01:41 - INFO - codeparrot_training - Step 14959: {'lr': 0.000490600840536951, 'samples': 7659520, 'steps': 14959, 'loss/train': 1.5450226068496704}
-03/04/2022 07:01:41 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/04/2022 07:01:46 - INFO - codeparrot_training - Step 14960: {'lr': 0.0004905993990419471, 'samples': 7660032, 'steps': 14960, 'loss/train': 1.164553165435791}
-03/04/2022 07:01:49 - INFO - codeparrot_training - Step 14961: {'lr': 0.0004905979574385328, 'samples': 7660544, 'steps': 14961, 'loss/train': 0.9571763873100281}
-03/04/2022 07:01:50 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 07:01:55 - INFO - codeparrot_training - Step 14962: {'lr': 0.0004905965157267088, 'samples': 7661056, 'steps': 14962, 'loss/train': 2.126681327819824}
-03/04/2022 07:01:58 - INFO - codeparrot_training - Step 14963: {'lr': 0.0004905950739064758, 'samples': 7661568, 'steps': 14963, 'loss/train': 1.879597783088684}
-03/04/2022 07:01:58 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/04/2022 07:02:03 - INFO - codeparrot_training - Step 14964: {'lr': 0.0004905936319778343, 'samples': 7662080, 'steps': 14964, 'loss/train': 1.7371450662612915}
-03/04/2022 07:02:06 - INFO - codeparrot_training - Step 14965: {'lr': 0.000490592189940785, 'samples': 7662592, 'steps': 14965, 'loss/train': 1.7903847694396973}
-03/04/2022 07:02:07 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/04/2022 07:02:12 - INFO - codeparrot_training - Step 14966: {'lr': 0.0004905907477953286, 'samples': 7663104, 'steps': 14966, 'loss/train': 2.259704828262329}
-03/04/2022 07:02:15 - INFO - codeparrot_training - Step 14967: {'lr': 0.0004905893055414658, 'samples': 7663616, 'steps': 14967, 'loss/train': 1.8130583763122559}
-03/04/2022 07:02:16 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 07:02:20 - INFO - codeparrot_training - Step 14968: {'lr': 0.0004905878631791971, 'samples': 7664128, 'steps': 14968, 'loss/train': 2.633150100708008}
-03/04/2022 07:02:23 - INFO - codeparrot_training - Step 14969: {'lr': 0.0004905864207085232, 'samples': 7664640, 'steps': 14969, 'loss/train': 2.120356798171997}
-03/04/2022 07:02:24 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/04/2022 07:02:29 - INFO - codeparrot_training - Step 14970: {'lr': 0.0004905849781294448, 'samples': 7665152, 'steps': 14970, 'loss/train': 1.996085286140442}
-03/04/2022 07:02:32 - INFO - codeparrot_training - Step 14971: {'lr': 0.0004905835354419625, 'samples': 7665664, 'steps': 14971, 'loss/train': 1.6456400156021118}
-03/04/2022 07:02:32 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/04/2022 07:02:37 - INFO - codeparrot_training - Step 14972: {'lr': 0.0004905820926460769, 'samples': 7666176, 'steps': 14972, 'loss/train': 1.9395033121109009}
-03/04/2022 07:02:40 - INFO - codeparrot_training - Step 14973: {'lr': 0.0004905806497417888, 'samples': 7666688, 'steps': 14973, 'loss/train': 1.740837574005127}
-03/04/2022 07:02:40 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 07:02:45 - INFO - codeparrot_training - Step 14974: {'lr': 0.0004905792067290988, 'samples': 7667200, 'steps': 14974, 'loss/train': 2.338318347930908}
-03/04/2022 07:02:49 - INFO - codeparrot_training - Step 14975: {'lr': 0.0004905777636080075, 'samples': 7667712, 'steps': 14975, 'loss/train': 0.23063331842422485}
-03/04/2022 07:02:49 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 07:02:54 - INFO - codeparrot_training - Step 14976: {'lr': 0.0004905763203785157, 'samples': 7668224, 'steps': 14976, 'loss/train': 1.9267724752426147}
-03/04/2022 07:02:57 - INFO - codeparrot_training - Step 14977: {'lr': 0.0004905748770406237, 'samples': 7668736, 'steps': 14977, 'loss/train': 2.6396360397338867}
-03/04/2022 07:02:57 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/04/2022 07:03:02 - INFO - codeparrot_training - Step 14978: {'lr': 0.0004905734335943325, 'samples': 7669248, 'steps': 14978, 'loss/train': 1.8374978303909302}
-03/04/2022 07:03:05 - INFO - codeparrot_training - Step 14979: {'lr': 0.0004905719900396426, 'samples': 7669760, 'steps': 14979, 'loss/train': 2.8721961975097656}
-03/04/2022 07:03:06 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 07:03:11 - INFO - codeparrot_training - Step 14980: {'lr': 0.0004905705463765546, 'samples': 7670272, 'steps': 14980, 'loss/train': 1.235705018043518}
-03/04/2022 07:03:14 - INFO - codeparrot_training - Step 14981: {'lr': 0.0004905691026050692, 'samples': 7670784, 'steps': 14981, 'loss/train': 1.6876442432403564}
-03/04/2022 07:03:14 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 07:03:19 - INFO - codeparrot_training - Step 14982: {'lr': 0.0004905676587251873, 'samples': 7671296, 'steps': 14982, 'loss/train': 1.2237870693206787}
-03/04/2022 07:03:22 - INFO - codeparrot_training - Step 14983: {'lr': 0.0004905662147369091, 'samples': 7671808, 'steps': 14983, 'loss/train': 2.40667462348938}
-03/04/2022 07:03:23 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/04/2022 07:03:28 - INFO - codeparrot_training - Step 14984: {'lr': 0.0004905647706402356, 'samples': 7672320, 'steps': 14984, 'loss/train': 1.3823845386505127}
-03/04/2022 07:03:31 - INFO - codeparrot_training - Step 14985: {'lr': 0.0004905633264351673, 'samples': 7672832, 'steps': 14985, 'loss/train': 1.6295167207717896}
-03/04/2022 07:03:31 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 07:03:36 - INFO - codeparrot_training - Step 14986: {'lr': 0.0004905618821217048, 'samples': 7673344, 'steps': 14986, 'loss/train': 1.969110131263733}
-03/04/2022 07:03:39 - INFO - codeparrot_training - Step 14987: {'lr': 0.0004905604376998489, 'samples': 7673856, 'steps': 14987, 'loss/train': 1.998218297958374}
-03/04/2022 07:03:39 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 07:03:44 - INFO - codeparrot_training - Step 14988: {'lr': 0.0004905589931696002, 'samples': 7674368, 'steps': 14988, 'loss/train': 1.626004934310913}
-03/04/2022 07:03:48 - INFO - codeparrot_training - Step 14989: {'lr': 0.0004905575485309593, 'samples': 7674880, 'steps': 14989, 'loss/train': 1.5093497037887573}
-03/04/2022 07:03:48 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 07:03:53 - INFO - codeparrot_training - Step 14990: {'lr': 0.0004905561037839269, 'samples': 7675392, 'steps': 14990, 'loss/train': 2.110227346420288}
-03/04/2022 07:03:56 - INFO - codeparrot_training - Step 14991: {'lr': 0.0004905546589285036, 'samples': 7675904, 'steps': 14991, 'loss/train': 1.7446317672729492}
-03/04/2022 07:03:56 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/04/2022 07:04:02 - INFO - codeparrot_training - Step 14992: {'lr': 0.0004905532139646901, 'samples': 7676416, 'steps': 14992, 'loss/train': 1.4323376417160034}
-03/04/2022 07:04:05 - INFO - codeparrot_training - Step 14993: {'lr': 0.000490551768892487, 'samples': 7676928, 'steps': 14993, 'loss/train': 2.5835154056549072}
-03/04/2022 07:04:05 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/04/2022 07:04:10 - INFO - codeparrot_training - Step 14994: {'lr': 0.000490550323711895, 'samples': 7677440, 'steps': 14994, 'loss/train': 1.9858660697937012}
-03/04/2022 07:04:13 - INFO - codeparrot_training - Step 14995: {'lr': 0.0004905488784229147, 'samples': 7677952, 'steps': 14995, 'loss/train': 1.6081502437591553}
-03/04/2022 07:04:14 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 07:04:19 - INFO - codeparrot_training - Step 14996: {'lr': 0.000490547433025547, 'samples': 7678464, 'steps': 14996, 'loss/train': 1.7831274271011353}
-03/04/2022 07:04:22 - INFO - codeparrot_training - Step 14997: {'lr': 0.0004905459875197921, 'samples': 7678976, 'steps': 14997, 'loss/train': 2.1401777267456055}
-03/04/2022 07:04:23 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 07:04:27 - INFO - codeparrot_training - Step 14998: {'lr': 0.000490544541905651, 'samples': 7679488, 'steps': 14998, 'loss/train': 2.165583372116089}
-03/04/2022 07:04:31 - INFO - codeparrot_training - Step 14999: {'lr': 0.0004905430961831242, 'samples': 7680000, 'steps': 14999, 'loss/train': 1.8511422872543335}
-03/04/2022 07:04:31 - INFO - codeparrot_training - Evaluating and saving model checkpoint
-03/04/2022 07:04:44 - WARNING - huggingface_hub.repository - Several commits (3) will be pushed upstream.
-03/04/2022 07:04:44 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
-03/04/2022 07:05:08 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/cm_code_clippy
-   ad512a7..7d4fba8  glowing-puddle-3 -> glowing-puddle-3
-
-03/04/2022 07:05:11 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/04/2022 07:05:15 - INFO - codeparrot_training - Step 15000: {'lr': 0.0004905416503522123, 'samples': 7680512, 'steps': 15000, 'loss/train': 1.124108910560608}
-03/04/2022 07:05:18 - INFO - codeparrot_training - Step 15001: {'lr': 0.0004905402044129162, 'samples': 7681024, 'steps': 15001, 'loss/train': 2.0032455921173096}
-03/04/2022 07:05:19 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/04/2022 07:05:23 - INFO - codeparrot_training - Step 15002: {'lr': 0.0004905387583652363, 'samples': 7681536, 'steps': 15002, 'loss/train': 2.7251927852630615}
-03/04/2022 07:05:26 - INFO - codeparrot_training - Step 15003: {'lr': 0.0004905373122091734, 'samples': 7682048, 'steps': 15003, 'loss/train': 1.965111255645752}
-03/04/2022 07:05:27 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 07:05:31 - INFO - codeparrot_training - Step 15004: {'lr': 0.0004905358659447281, 'samples': 7682560, 'steps': 15004, 'loss/train': 1.788163423538208}
-03/04/2022 07:05:34 - INFO - codeparrot_training - Step 15005: {'lr': 0.000490534419571901, 'samples': 7683072, 'steps': 15005, 'loss/train': 1.9516544342041016}
-03/04/2022 07:05:36 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/04/2022 07:05:40 - INFO - codeparrot_training - Step 15006: {'lr': 0.0004905329730906929, 'samples': 7683584, 'steps': 15006, 'loss/train': 2.2833268642425537}
-03/04/2022 07:05:43 - INFO - codeparrot_training - Step 15007: {'lr': 0.0004905315265011043, 'samples': 7684096, 'steps': 15007, 'loss/train': 2.0812675952911377}
-03/04/2022 07:05:45 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 07:05:48 - INFO - codeparrot_training - Step 15008: {'lr': 0.0004905300798031359, 'samples': 7684608, 'steps': 15008, 'loss/train': 1.2740222215652466}
-03/04/2022 07:05:52 - INFO - codeparrot_training - Step 15009: {'lr': 0.0004905286329967883, 'samples': 7685120, 'steps': 15009, 'loss/train': 2.039226531982422}
-03/04/2022 07:05:54 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 07:05:57 - INFO - codeparrot_training - Step 15010: {'lr': 0.0004905271860820622, 'samples': 7685632, 'steps': 15010, 'loss/train': 1.8363571166992188}
-03/04/2022 07:06:00 - INFO - codeparrot_training - Step 15011: {'lr': 0.0004905257390589585, 'samples': 7686144, 'steps': 15011, 'loss/train': 0.8878414034843445}
-03/04/2022 07:06:02 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 07:06:05 - INFO - codeparrot_training - Step 15012: {'lr': 0.0004905242919274774, 'samples': 7686656, 'steps': 15012, 'loss/train': 1.7550570964813232}
-03/04/2022 07:06:08 - INFO - codeparrot_training - Step 15013: {'lr': 0.0004905228446876197, 'samples': 7687168, 'steps': 15013, 'loss/train': 1.8136323690414429}
-03/04/2022 07:06:10 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 07:06:14 - INFO - codeparrot_training - Step 15014: {'lr': 0.0004905213973393863, 'samples': 7687680, 'steps': 15014, 'loss/train': 1.7531710863113403}
-03/04/2022 07:06:17 - INFO - codeparrot_training - Step 15015: {'lr': 0.0004905199498827776, 'samples': 7688192, 'steps': 15015, 'loss/train': 1.9604685306549072}
-03/04/2022 07:06:18 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/04/2022 07:06:22 - INFO - codeparrot_training - Step 15016: {'lr': 0.0004905185023177942, 'samples': 7688704, 'steps': 15016, 'loss/train': 2.5374135971069336}
-03/04/2022 07:06:25 - INFO - codeparrot_training - Step 15017: {'lr': 0.0004905170546444371, 'samples': 7689216, 'steps': 15017, 'loss/train': 1.3926631212234497}
-03/04/2022 07:06:27 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 07:06:31 - INFO - codeparrot_training - Step 15018: {'lr': 0.0004905156068627065, 'samples': 7689728, 'steps': 15018, 'loss/train': 1.8392575979232788}
-03/04/2022 07:06:34 - INFO - codeparrot_training - Step 15019: {'lr': 0.0004905141589726035, 'samples': 7690240, 'steps': 15019, 'loss/train': 1.5275486707687378}
-03/04/2022 07:06:36 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 07:06:39 - INFO - codeparrot_training - Step 15020: {'lr': 0.0004905127109741284, 'samples': 7690752, 'steps': 15020, 'loss/train': 2.386080026626587}
-03/04/2022 07:06:42 - INFO - codeparrot_training - Step 15021: {'lr': 0.000490511262867282, 'samples': 7691264, 'steps': 15021, 'loss/train': 1.7695971727371216}
-03/04/2022 07:06:44 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 07:06:47 - INFO - codeparrot_training - Step 15022: {'lr': 0.000490509814652065, 'samples': 7691776, 'steps': 15022, 'loss/train': 2.126218795776367}
-03/04/2022 07:06:51 - INFO - codeparrot_training - Step 15023: {'lr': 0.0004905083663284779, 'samples': 7692288, 'steps': 15023, 'loss/train': 2.6205484867095947}
-03/04/2022 07:06:52 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/04/2022 07:06:56 - INFO - codeparrot_training - Step 15024: {'lr': 0.0004905069178965214, 'samples': 7692800, 'steps': 15024, 'loss/train': 1.3500251770019531}
-03/04/2022 07:06:59 - INFO - codeparrot_training - Step 15025: {'lr': 0.0004905054693561963, 'samples': 7693312, 'steps': 15025, 'loss/train': 2.3454055786132812}
-03/04/2022 07:07:01 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/04/2022 07:07:04 - INFO - codeparrot_training - Step 15026: {'lr': 0.0004905040207075032, 'samples': 7693824, 'steps': 15026, 'loss/train': 1.996700644493103}
-03/04/2022 07:07:07 - INFO - codeparrot_training - Step 15027: {'lr': 0.0004905025719504426, 'samples': 7694336, 'steps': 15027, 'loss/train': 2.2744147777557373}
-03/04/2022 07:07:09 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/04/2022 07:07:13 - INFO - codeparrot_training - Step 15028: {'lr': 0.0004905011230850152, 'samples': 7694848, 'steps': 15028, 'loss/train': 0.8628334403038025}
-03/04/2022 07:07:16 - INFO - codeparrot_training - Step 15029: {'lr': 0.0004904996741112218, 'samples': 7695360, 'steps': 15029, 'loss/train': 1.7831729650497437}
-03/04/2022 07:07:18 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/04/2022 07:07:22 - INFO - codeparrot_training - Step 15030: {'lr': 0.0004904982250290629, 'samples': 7695872, 'steps': 15030, 'loss/train': 1.9099750518798828}
-03/04/2022 07:07:25 - INFO - codeparrot_training - Step 15031: {'lr': 0.0004904967758385393, 'samples': 7696384, 'steps': 15031, 'loss/train': 1.6613608598709106}
-03/04/2022 07:07:26 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 07:07:30 - INFO - codeparrot_training - Step 15032: {'lr': 0.0004904953265396515, 'samples': 7696896, 'steps': 15032, 'loss/train': 1.2869060039520264}
-03/04/2022 07:07:33 - INFO - codeparrot_training - Step 15033: {'lr': 0.0004904938771324002, 'samples': 7697408, 'steps': 15033, 'loss/train': 2.502641439437866}
-03/04/2022 07:07:35 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/04/2022 07:07:38 - INFO - codeparrot_training - Step 15034: {'lr': 0.0004904924276167861, 'samples': 7697920, 'steps': 15034, 'loss/train': 1.7009127140045166}
-03/04/2022 07:07:42 - INFO - codeparrot_training - Step 15035: {'lr': 0.0004904909779928099, 'samples': 7698432, 'steps': 15035, 'loss/train': 2.0681939125061035}
-03/04/2022 07:07:43 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/04/2022 07:07:47 - INFO - codeparrot_training - Step 15036: {'lr': 0.000490489528260472, 'samples': 7698944, 'steps': 15036, 'loss/train': 2.3724069595336914}
-03/04/2022 07:07:50 - INFO - codeparrot_training - Step 15037: {'lr': 0.0004904880784197734, 'samples': 7699456, 'steps': 15037, 'loss/train': 1.9611097574234009}
-03/04/2022 07:07:51 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 07:07:55 - INFO - codeparrot_training - Step 15038: {'lr': 0.0004904866284707144, 'samples': 7699968, 'steps': 15038, 'loss/train': 1.6469544172286987}
-03/04/2022 07:07:58 - INFO - codeparrot_training - Step 15039: {'lr': 0.000490485178413296, 'samples': 7700480, 'steps': 15039, 'loss/train': 1.4382404088974}
-03/04/2022 07:07:59 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/04/2022 07:08:04 - INFO - codeparrot_training - Step 15040: {'lr': 0.0004904837282475186, 'samples': 7700992, 'steps': 15040, 'loss/train': 2.009895086288452}
-03/04/2022 07:08:07 - INFO - codeparrot_training - Step 15041: {'lr': 0.000490482277973383, 'samples': 7701504, 'steps': 15041, 'loss/train': 2.740320920944214}
-03/04/2022 07:08:08 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/04/2022 07:08:12 - INFO - codeparrot_training - Step 15042: {'lr': 0.0004904808275908898, 'samples': 7702016, 'steps': 15042, 'loss/train': 1.9641858339309692}
-03/04/2022 07:08:15 - INFO - codeparrot_training - Step 15043: {'lr': 0.0004904793771000396, 'samples': 7702528, 'steps': 15043, 'loss/train': 1.9127044677734375}
-03/04/2022 07:08:17 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 07:08:21 - INFO - codeparrot_training - Step 15044: {'lr': 0.0004904779265008331, 'samples': 7703040, 'steps': 15044, 'loss/train': 1.3630226850509644}
-03/04/2022 07:08:24 - INFO - codeparrot_training - Step 15045: {'lr': 0.000490476475793271, 'samples': 7703552, 'steps': 15045, 'loss/train': 2.223031759262085}
-03/04/2022 07:08:26 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/04/2022 07:08:29 - INFO - codeparrot_training - Step 15046: {'lr': 0.0004904750249773538, 'samples': 7704064, 'steps': 15046, 'loss/train': 2.304105758666992}
-03/04/2022 07:08:32 - INFO - codeparrot_training - Step 15047: {'lr': 0.0004904735740530825, 'samples': 7704576, 'steps': 15047, 'loss/train': 1.2682045698165894}
-03/04/2022 07:08:34 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 07:08:37 - INFO - codeparrot_training - Step 15048: {'lr': 0.0004904721230204573, 'samples': 7705088, 'steps': 15048, 'loss/train': 1.1306997537612915}
-03/04/2022 07:08:41 - INFO - codeparrot_training - Step 15049: {'lr': 0.0004904706718794791, 'samples': 7705600, 'steps': 15049, 'loss/train': 2.649277925491333}
-03/04/2022 07:08:42 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/04/2022 07:08:46 - INFO - codeparrot_training - Step 15050: {'lr': 0.0004904692206301487, 'samples': 7706112, 'steps': 15050, 'loss/train': 2.3671743869781494}
-03/04/2022 07:08:49 - INFO - codeparrot_training - Step 15051: {'lr': 0.0004904677692724664, 'samples': 7706624, 'steps': 15051, 'loss/train': 1.6050739288330078}
-03/04/2022 07:08:51 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/04/2022 07:08:54 - INFO - codeparrot_training - Step 15052: {'lr': 0.000490466317806433, 'samples': 7707136, 'steps': 15052, 'loss/train': 2.0828144550323486}
-03/04/2022 07:08:57 - INFO - codeparrot_training - Step 15053: {'lr': 0.0004904648662320493, 'samples': 7707648, 'steps': 15053, 'loss/train': 1.9346091747283936}
-03/04/2022 07:08:59 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 07:09:03 - INFO - codeparrot_training - Step 15054: {'lr': 0.0004904634145493159, 'samples': 7708160, 'steps': 15054, 'loss/train': 1.2007808685302734}
-03/04/2022 07:09:06 - INFO - codeparrot_training - Step 15055: {'lr': 0.0004904619627582332, 'samples': 7708672, 'steps': 15055, 'loss/train': 1.6872395277023315}
-03/04/2022 07:09:09 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/04/2022 07:09:12 - INFO - codeparrot_training - Step 15056: {'lr': 0.0004904605108588023, 'samples': 7709184, 'steps': 15056, 'loss/train': 1.869847297668457}
-03/04/2022 07:09:15 - INFO - codeparrot_training - Step 15057: {'lr': 0.0004904590588510234, 'samples': 7709696, 'steps': 15057, 'loss/train': 2.2120299339294434}
-03/04/2022 07:09:17 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/04/2022 07:09:20 - INFO - codeparrot_training - Step 15058: {'lr': 0.0004904576067348975, 'samples': 7710208, 'steps': 15058, 'loss/train': 1.7059688568115234}
-03/04/2022 07:09:23 - INFO - codeparrot_training - Step 15059: {'lr': 0.000490456154510425, 'samples': 7710720, 'steps': 15059, 'loss/train': 2.4730095863342285}
-03/04/2022 07:09:26 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/04/2022 07:09:28 - INFO - codeparrot_training - Step 15060: {'lr': 0.0004904547021776067, 'samples': 7711232, 'steps': 15060, 'loss/train': 1.04810631275177}
-03/04/2022 07:09:32 - INFO - codeparrot_training - Step 15061: {'lr': 0.0004904532497364432, 'samples': 7711744, 'steps': 15061, 'loss/train': 2.8565568923950195}
-03/04/2022 07:09:34 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/04/2022 07:09:37 - INFO - codeparrot_training - Step 15062: {'lr': 0.0004904517971869352, 'samples': 7712256, 'steps': 15062, 'loss/train': 2.3585734367370605}
-03/04/2022 07:09:40 - INFO - codeparrot_training - Step 15063: {'lr': 0.0004904503445290833, 'samples': 7712768, 'steps': 15063, 'loss/train': 1.2566827535629272}
-03/04/2022 07:09:42 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 07:09:45 - INFO - codeparrot_training - Step 15064: {'lr': 0.0004904488917628882, 'samples': 7713280, 'steps': 15064, 'loss/train': 1.9569579362869263}
-03/04/2022 07:09:48 - INFO - codeparrot_training - Step 15065: {'lr': 0.0004904474388883507, 'samples': 7713792, 'steps': 15065, 'loss/train': 2.10269832611084}
-03/04/2022 07:09:51 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 07:09:54 - INFO - codeparrot_training - Step 15066: {'lr': 0.000490445985905471, 'samples': 7714304, 'steps': 15066, 'loss/train': 1.148998737335205}
-03/04/2022 07:09:57 - INFO - codeparrot_training - Step 15067: {'lr': 0.0004904445328142503, 'samples': 7714816, 'steps': 15067, 'loss/train': 2.0510916709899902}
-03/04/2022 07:09:59 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 07:10:02 - INFO - codeparrot_training - Step 15068: {'lr': 0.0004904430796146889, 'samples': 7715328, 'steps': 15068, 'loss/train': 1.3475439548492432}
-03/04/2022 07:10:05 - INFO - codeparrot_training - Step 15069: {'lr': 0.0004904416263067876, 'samples': 7715840, 'steps': 15069, 'loss/train': 2.5242676734924316}
-03/04/2022 07:10:08 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/04/2022 07:10:11 - INFO - codeparrot_training - Step 15070: {'lr': 0.0004904401728905469, 'samples': 7716352, 'steps': 15070, 'loss/train': 1.4060122966766357}
-03/04/2022 07:10:14 - INFO - codeparrot_training - Step 15071: {'lr': 0.0004904387193659677, 'samples': 7716864, 'steps': 15071, 'loss/train': 1.8636971712112427}
-03/04/2022 07:10:16 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/04/2022 07:10:19 - INFO - codeparrot_training - Step 15072: {'lr': 0.0004904372657330504, 'samples': 7717376, 'steps': 15072, 'loss/train': 1.5916359424591064}
-03/04/2022 07:10:23 - INFO - codeparrot_training - Step 15073: {'lr': 0.0004904358119917959, 'samples': 7717888, 'steps': 15073, 'loss/train': 1.9074276685714722}
-03/04/2022 07:10:26 - INFO - codeparrot_training - Step 15074: {'lr': 0.0004904343581422047, 'samples': 7718400, 'steps': 15074, 'loss/train': 3.2441749572753906}
-03/04/2022 07:10:26 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/04/2022 07:10:31 - INFO - codeparrot_training - Step 15075: {'lr': 0.0004904329041842774, 'samples': 7718912, 'steps': 15075, 'loss/train': 2.0777430534362793}
-03/04/2022 07:10:34 - INFO - codeparrot_training - Step 15076: {'lr': 0.0004904314501180148, 'samples': 7719424, 'steps': 15076, 'loss/train': 1.8914417028427124}
-03/04/2022 07:10:35 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/04/2022 07:10:39 - INFO - codeparrot_training - Step 15077: {'lr': 0.0004904299959434175, 'samples': 7719936, 'steps': 15077, 'loss/train': 2.005387783050537}
-03/04/2022 07:10:43 - INFO - codeparrot_training - Step 15078: {'lr': 0.0004904285416604862, 'samples': 7720448, 'steps': 15078, 'loss/train': 1.587920904159546}
-03/04/2022 07:10:43 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 07:10:48 - INFO - codeparrot_training - Step 15079: {'lr': 0.0004904270872692215, 'samples': 7720960, 'steps': 15079, 'loss/train': 2.0889852046966553}
-03/04/2022 07:10:51 - INFO - codeparrot_training - Step 15080: {'lr': 0.0004904256327696241, 'samples': 7721472, 'steps': 15080, 'loss/train': 1.4562541246414185}
-03/04/2022 07:10:51 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/04/2022 07:10:56 - INFO - codeparrot_training - Step 15081: {'lr': 0.0004904241781616945, 'samples': 7721984, 'steps': 15081, 'loss/train': 1.8364921808242798}
-03/04/2022 07:10:59 - INFO - codeparrot_training - Step 15082: {'lr': 0.0004904227234454335, 'samples': 7722496, 'steps': 15082, 'loss/train': 1.363698124885559}
-03/04/2022 07:11:00 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/04/2022 07:11:05 - INFO - codeparrot_training - Step 15083: {'lr': 0.0004904212686208418, 'samples': 7723008, 'steps': 15083, 'loss/train': 1.8146157264709473}
-03/04/2022 07:11:08 - INFO - codeparrot_training - Step 15084: {'lr': 0.00049041981368792, 'samples': 7723520, 'steps': 15084, 'loss/train': 2.31183123588562}
-03/04/2022 07:11:08 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/04/2022 07:11:13 - INFO - codeparrot_training - Step 15085: {'lr': 0.0004904183586466686, 'samples': 7724032, 'steps': 15085, 'loss/train': 2.5919792652130127}
-03/04/2022 07:11:16 - INFO - codeparrot_training - Step 15086: {'lr': 0.0004904169034970885, 'samples': 7724544, 'steps': 15086, 'loss/train': 1.306950569152832}
-03/04/2022 07:11:17 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/04/2022 07:11:22 - INFO - codeparrot_training - Step 15087: {'lr': 0.0004904154482391803, 'samples': 7725056, 'steps': 15087, 'loss/train': 1.560609221458435}
-03/04/2022 07:11:25 - INFO - codeparrot_training - Step 15088: {'lr': 0.0004904139928729445, 'samples': 7725568, 'steps': 15088, 'loss/train': 1.7392244338989258}
-03/04/2022 07:11:25 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/04/2022 07:11:30 - INFO - codeparrot_training - Step 15089: {'lr': 0.0004904125373983819, 'samples': 7726080, 'steps': 15089, 'loss/train': 2.120112419128418}
-03/04/2022 07:11:33 - INFO - codeparrot_training - Step 15090: {'lr': 0.0004904110818154931, 'samples': 7726592, 'steps': 15090, 'loss/train': 1.361201286315918}
-03/04/2022 07:11:33 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/04/2022 07:11:38 - INFO - codeparrot_training - Step 15091: {'lr': 0.0004904096261242789, 'samples': 7727104, 'steps': 15091, 'loss/train': 1.7765558958053589}
-03/04/2022 07:11:42 - INFO - codeparrot_training - Step 15092: {'lr': 0.0004904081703247397, 'samples': 7727616, 'steps': 15092, 'loss/train': 1.2364274263381958}
-03/04/2022 07:11:42 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 07:11:47 - INFO - codeparrot_training - Step 15093: {'lr': 0.0004904067144168763, 'samples': 7728128, 'steps': 15093, 'loss/train': 1.9350498914718628}
-03/04/2022 07:11:50 - INFO - codeparrot_training - Step 15094: {'lr': 0.0004904052584006895, 'samples': 7728640, 'steps': 15094, 'loss/train': 1.9972333908081055}
-03/04/2022 07:11:50 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 07:11:55 - INFO - codeparrot_training - Step 15095: {'lr': 0.0004904038022761797, 'samples': 7729152, 'steps': 15095, 'loss/train': 2.5483715534210205}
-03/04/2022 07:11:59 - INFO - codeparrot_training - Step 15096: {'lr': 0.0004904023460433475, 'samples': 7729664, 'steps': 15096, 'loss/train': 2.1004207134246826}
-03/04/2022 07:11:59 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/04/2022 07:12:04 - INFO - codeparrot_training - Step 15097: {'lr': 0.0004904008897021939, 'samples': 7730176, 'steps': 15097, 'loss/train': 2.2273781299591064}
-03/04/2022 07:12:07 - INFO - codeparrot_training - Step 15098: {'lr': 0.0004903994332527193, 'samples': 7730688, 'steps': 15098, 'loss/train': 2.102306365966797}
-03/04/2022 07:12:07 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/04/2022 07:12:12 - INFO - codeparrot_training - Step 15099: {'lr': 0.0004903979766949244, 'samples': 7731200, 'steps': 15099, 'loss/train': 1.6808604001998901}
-03/04/2022 07:12:16 - INFO - codeparrot_training - Step 15100: {'lr': 0.00049039652002881, 'samples': 7731712, 'steps': 15100, 'loss/train': 1.13270103931427}
-03/04/2022 07:12:16 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 07:12:21 - INFO - codeparrot_training - Step 15101: {'lr': 0.0004903950632543766, 'samples': 7732224, 'steps': 15101, 'loss/train': 1.835746169090271}
-03/04/2022 07:12:24 - INFO - codeparrot_training - Step 15102: {'lr': 0.0004903936063716248, 'samples': 7732736, 'steps': 15102, 'loss/train': 1.6485700607299805}
-03/04/2022 07:12:24 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/04/2022 07:12:29 - INFO - codeparrot_training - Step 15103: {'lr': 0.0004903921493805554, 'samples': 7733248, 'steps': 15103, 'loss/train': 2.1256768703460693}
-03/04/2022 07:12:32 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/04/2022 07:12:35 - INFO - codeparrot_training - Step 15104: {'lr': 0.000490390692281169, 'samples': 7733760, 'steps': 15104, 'loss/train': 0.5741967558860779}
-03/04/2022 07:12:38 - INFO - codeparrot_training - Step 15105: {'lr': 0.0004903892350734663, 'samples': 7734272, 'steps': 15105, 'loss/train': 2.141782522201538}
-03/04/2022 07:12:41 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/04/2022 07:12:43 - INFO - codeparrot_training - Step 15106: {'lr': 0.0004903877777574479, 'samples': 7734784, 'steps': 15106, 'loss/train': 1.3447749614715576}
-03/04/2022 07:12:46 - INFO - codeparrot_training - Step 15107: {'lr': 0.0004903863203331145, 'samples': 7735296, 'steps': 15107, 'loss/train': 2.221787929534912}
-03/04/2022 07:12:49 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 07:12:51 - INFO - codeparrot_training - Step 15108: {'lr': 0.0004903848628004667, 'samples': 7735808, 'steps': 15108, 'loss/train': 1.5001084804534912}
-03/04/2022 07:12:55 - INFO - codeparrot_training - Step 15109: {'lr': 0.0004903834051595052, 'samples': 7736320, 'steps': 15109, 'loss/train': 2.3787012100219727}
-03/04/2022 07:12:58 - INFO - codeparrot_training - Step 15110: {'lr': 0.0004903819474102306, 'samples': 7736832, 'steps': 15110, 'loss/train': 1.1772141456604004}
-03/04/2022 07:12:58 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/04/2022 07:13:03 - INFO - codeparrot_training - Step 15111: {'lr': 0.0004903804895526437, 'samples': 7737344, 'steps': 15111, 'loss/train': 1.8408877849578857}
-03/04/2022 07:13:06 - INFO - codeparrot_training - Step 15112: {'lr': 0.0004903790315867449, 'samples': 7737856, 'steps': 15112, 'loss/train': 1.5420091152191162}
-03/04/2022 07:13:06 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/04/2022 07:13:12 - INFO - codeparrot_training - Step 15113: {'lr': 0.0004903775735125352, 'samples': 7738368, 'steps': 15113, 'loss/train': 2.2399837970733643}
-03/04/2022 07:13:15 - INFO - codeparrot_training - Step 15114: {'lr': 0.0004903761153300149, 'samples': 7738880, 'steps': 15114, 'loss/train': 2.094606876373291}
-03/04/2022 07:13:17 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/04/2022 07:13:20 - INFO - codeparrot_training - Step 15115: {'lr': 0.000490374657039185, 'samples': 7739392, 'steps': 15115, 'loss/train': 1.7523351907730103}
-03/04/2022 07:13:23 - INFO - codeparrot_training - Step 15116: {'lr': 0.0004903731986400459, 'samples': 7739904, 'steps': 15116, 'loss/train': 0.9121655225753784}
-03/04/2022 07:13:25 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/04/2022 07:13:29 - INFO - codeparrot_training - Step 15117: {'lr': 0.0004903717401325983, 'samples': 7740416, 'steps': 15117, 'loss/train': 1.7191216945648193}
-03/04/2022 07:13:32 - INFO - codeparrot_training - Step 15118: {'lr': 0.000490370281516843, 'samples': 7740928, 'steps': 15118, 'loss/train': 1.6949079036712646}
-03/04/2022 07:13:34 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/04/2022 07:13:37 - INFO - codeparrot_training - Step 15119: {'lr': 0.0004903688227927806, 'samples': 7741440, 'steps': 15119, 'loss/train': 2.0688724517822266}
-03/04/2022 07:13:40 - INFO - codeparrot_training - Step 15120: {'lr': 0.0004903673639604116, 'samples': 7741952, 'steps': 15120, 'loss/train': 1.5784456729888916}
-03/04/2022 07:13:42 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/04/2022 07:13:46 - INFO - codeparrot_training - Step 15121: {'lr': 0.0004903659050197369, 'samples': 7742464, 'steps': 15121, 'loss/train': 1.3689708709716797}
-03/04/2022 07:13:49 - INFO - codeparrot_training - Step 15122: {'lr': 0.0004903644459707569, 'samples': 7742976, 'steps': 15122, 'loss/train': 2.1300764083862305}
-03/04/2022 07:13:51 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/04/2022 07:13:54 - INFO - codeparrot_training - Step 15123: {'lr': 0.0004903629868134725, 'samples': 7743488, 'steps': 15123, 'loss/train': 2.0668346881866455}
-03/04/2022 07:13:57 - INFO - codeparrot_training - Step 15124: {'lr': 0.0004903615275478841, 'samples': 7744000, 'steps': 15124, 'loss/train': 1.5456273555755615}
-03/04/2022 07:14:00 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 07:14:03 - INFO - codeparrot_training - Step 15125: {'lr': 0.0004903600681739926, 'samples': 7744512, 'steps': 15125, 'loss/train': 1.9291473627090454}
-03/04/2022 07:14:06 - INFO - codeparrot_training - Step 15126: {'lr': 0.0004903586086917986, 'samples': 7745024, 'steps': 15126, 'loss/train': 2.6652748584747314}
-03/04/2022 07:14:08 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/04/2022 07:14:11 - INFO - codeparrot_training - Step 15127: {'lr': 0.0004903571491013027, 'samples': 7745536, 'steps': 15127, 'loss/train': 1.7841682434082031}
-03/04/2022 07:14:14 - INFO - codeparrot_training - Step 15128: {'lr': 0.0004903556894025055, 'samples': 7746048, 'steps': 15128, 'loss/train': 1.5957554578781128}
-03/04/2022 07:14:16 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/04/2022 07:14:20 - INFO - codeparrot_training - Step 15129: {'lr': 0.0004903542295954077, 'samples': 7746560, 'steps': 15129, 'loss/train': 1.7252914905548096}
-03/04/2022 07:14:23 - INFO - codeparrot_training - Step 15130: {'lr': 0.0004903527696800102, 'samples': 7747072, 'steps': 15130, 'loss/train': 2.686516284942627}
-03/04/2022 07:14:24 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/04/2022 07:14:28 - INFO - codeparrot_training - Step 15131: {'lr': 0.0004903513096563133, 'samples': 7747584, 'steps': 15131, 'loss/train': 1.9319047927856445}
-03/04/2022 07:14:31 - INFO - codeparrot_training - Step 15132: {'lr': 0.0004903498495243178, 'samples': 7748096, 'steps': 15132, 'loss/train': 1.4640710353851318}
-03/04/2022 07:14:33 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 07:14:36 - INFO - codeparrot_training - Step 15133: {'lr': 0.0004903483892840244, 'samples': 7748608, 'steps': 15133, 'loss/train': 2.272279739379883}
-03/04/2022 07:14:40 - INFO - codeparrot_training - Step 15134: {'lr': 0.0004903469289354338, 'samples': 7749120, 'steps': 15134, 'loss/train': 3.2980268001556396}
-03/04/2022 07:14:42 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/04/2022 07:14:45 - INFO - codeparrot_training - Step 15135: {'lr': 0.0004903454684785465, 'samples': 7749632, 'steps': 15135, 'loss/train': 1.8776437044143677}
-03/04/2022 07:14:48 - INFO - codeparrot_training - Step 15136: {'lr': 0.0004903440079133633, 'samples': 7750144, 'steps': 15136, 'loss/train': 2.0369532108306885}
-03/04/2022 07:14:50 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 07:14:53 - INFO - codeparrot_training - Step 15137: {'lr': 0.0004903425472398846, 'samples': 7750656, 'steps': 15137, 'loss/train': 2.3640620708465576}
-03/04/2022 07:14:57 - INFO - codeparrot_training - Step 15138: {'lr': 0.0004903410864581115, 'samples': 7751168, 'steps': 15138, 'loss/train': 2.666942834854126}
-03/04/2022 07:14:58 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 07:15:02 - INFO - codeparrot_training - Step 15139: {'lr': 0.0004903396255680443, 'samples': 7751680, 'steps': 15139, 'loss/train': 2.244220018386841}
-03/04/2022 07:15:05 - INFO - codeparrot_training - Step 15140: {'lr': 0.0004903381645696838, 'samples': 7752192, 'steps': 15140, 'loss/train': 1.952545404434204}
-03/04/2022 07:15:07 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/04/2022 07:15:10 - INFO - codeparrot_training - Step 15141: {'lr': 0.0004903367034630307, 'samples': 7752704, 'steps': 15141, 'loss/train': 1.6053801774978638}
-03/04/2022 07:15:13 - INFO - codeparrot_training - Step 15142: {'lr': 0.0004903352422480855, 'samples': 7753216, 'steps': 15142, 'loss/train': 2.145606756210327}
-03/04/2022 07:15:15 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 07:15:19 - INFO - codeparrot_training - Step 15143: {'lr': 0.000490333780924849, 'samples': 7753728, 'steps': 15143, 'loss/train': 1.378994345664978}
-03/04/2022 07:15:22 - INFO - codeparrot_training - Step 15144: {'lr': 0.0004903323194933218, 'samples': 7754240, 'steps': 15144, 'loss/train': 1.8914250135421753}
-03/04/2022 07:15:23 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/04/2022 07:15:27 - INFO - codeparrot_training - Step 15145: {'lr': 0.0004903308579535045, 'samples': 7754752, 'steps': 15145, 'loss/train': 1.6645804643630981}
-03/04/2022 07:15:30 - INFO - codeparrot_training - Step 15146: {'lr': 0.0004903293963053979, 'samples': 7755264, 'steps': 15146, 'loss/train': 1.6760786771774292}
-03/04/2022 07:15:31 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/04/2022 07:15:36 - INFO - codeparrot_training - Step 15147: {'lr': 0.0004903279345490026, 'samples': 7755776, 'steps': 15147, 'loss/train': 0.5476749539375305}
-03/04/2022 07:15:39 - INFO - codeparrot_training - Step 15148: {'lr': 0.0004903264726843191, 'samples': 7756288, 'steps': 15148, 'loss/train': 2.1113502979278564}
-03/04/2022 07:15:40 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 07:15:44 - INFO - codeparrot_training - Step 15149: {'lr': 0.0004903250107113483, 'samples': 7756800, 'steps': 15149, 'loss/train': 0.5562407374382019}
-03/04/2022 07:15:47 - INFO - codeparrot_training - Step 15150: {'lr': 0.0004903235486300908, 'samples': 7757312, 'steps': 15150, 'loss/train': 2.553931713104248}
-03/04/2022 07:15:48 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 07:15:52 - INFO - codeparrot_training - Step 15151: {'lr': 0.0004903220864405471, 'samples': 7757824, 'steps': 15151, 'loss/train': 1.8831093311309814}
-03/04/2022 07:15:56 - INFO - codeparrot_training - Step 15152: {'lr': 0.000490320624142718, 'samples': 7758336, 'steps': 15152, 'loss/train': 2.189178466796875}
-03/04/2022 07:15:56 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 07:16:01 - INFO - codeparrot_training - Step 15153: {'lr': 0.0004903191617366043, 'samples': 7758848, 'steps': 15153, 'loss/train': 1.3438587188720703}
-03/04/2022 07:16:04 - INFO - codeparrot_training - Step 15154: {'lr': 0.0004903176992222063, 'samples': 7759360, 'steps': 15154, 'loss/train': 2.5476737022399902}
-03/04/2022 07:16:05 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/04/2022 07:16:09 - INFO - codeparrot_training - Step 15155: {'lr': 0.000490316236599525, 'samples': 7759872, 'steps': 15155, 'loss/train': 0.9849637746810913}
-03/04/2022 07:16:12 - INFO - codeparrot_training - Step 15156: {'lr': 0.0004903147738685609, 'samples': 7760384, 'steps': 15156, 'loss/train': 2.612017869949341}
-03/04/2022 07:16:13 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/04/2022 07:16:18 - INFO - codeparrot_training - Step 15157: {'lr': 0.0004903133110293145, 'samples': 7760896, 'steps': 15157, 'loss/train': 3.3260271549224854}
-03/04/2022 07:16:21 - INFO - codeparrot_training - Step 15158: {'lr': 0.0004903118480817868, 'samples': 7761408, 'steps': 15158, 'loss/train': 1.8378442525863647}
-03/04/2022 07:16:22 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/04/2022 07:16:26 - INFO - codeparrot_training - Step 15159: {'lr': 0.0004903103850259781, 'samples': 7761920, 'steps': 15159, 'loss/train': 1.5548557043075562}
-03/04/2022 07:16:29 - INFO - codeparrot_training - Step 15160: {'lr': 0.0004903089218618895, 'samples': 7762432, 'steps': 15160, 'loss/train': 1.8729041814804077}
-03/04/2022 07:16:30 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/04/2022 07:16:35 - INFO - codeparrot_training - Step 15161: {'lr': 0.0004903074585895212, 'samples': 7762944, 'steps': 15161, 'loss/train': 1.6403844356536865}
-03/04/2022 07:16:38 - INFO - codeparrot_training - Step 15162: {'lr': 0.0004903059952088742, 'samples': 7763456, 'steps': 15162, 'loss/train': 2.155118465423584}
-03/04/2022 07:16:38 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/04/2022 07:16:43 - INFO - codeparrot_training - Step 15163: {'lr': 0.0004903045317199489, 'samples': 7763968, 'steps': 15163, 'loss/train': 2.757357120513916}
-03/04/2022 07:16:46 - INFO - codeparrot_training - Step 15164: {'lr': 0.0004903030681227463, 'samples': 7764480, 'steps': 15164, 'loss/train': 0.7976189255714417}
-03/04/2022 07:16:47 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/04/2022 07:16:51 - INFO - codeparrot_training - Step 15165: {'lr': 0.0004903016044172666, 'samples': 7764992, 'steps': 15165, 'loss/train': 1.812813639640808}
-03/04/2022 07:16:55 - INFO - codeparrot_training - Step 15166: {'lr': 0.0004903001406035109, 'samples': 7765504, 'steps': 15166, 'loss/train': 1.7326570749282837}
-03/04/2022 07:16:55 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/04/2022 07:17:00 - INFO - codeparrot_training - Step 15167: {'lr': 0.0004902986766814795, 'samples': 7766016, 'steps': 15167, 'loss/train': 1.8663133382797241}
-03/04/2022 07:17:03 - INFO - codeparrot_training - Step 15168: {'lr': 0.0004902972126511734, 'samples': 7766528, 'steps': 15168, 'loss/train': 1.5511295795440674}
-03/04/2022 07:17:04 - INFO - codeparrot_training - Skipping example with length 920 (seq_length=1024)
-03/04/2022 07:17:08 - INFO - codeparrot_training - Step 15169: {'lr': 0.0004902957485125929, 'samples': 7767040, 'steps': 15169, 'loss/train': 1.2507461309432983}
-03/04/2022 07:17:12 - INFO - codeparrot_training - Step 15170: {'lr': 0.0004902942842657389, 'samples': 7767552, 'steps': 15170, 'loss/train': 1.5924980640411377}
-03/04/2022 07:17:13 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/04/2022 07:17:17 - INFO - codeparrot_training - Step 15171: {'lr': 0.0004902928199106121, 'samples': 7768064, 'steps': 15171, 'loss/train': 0.4915942847728729}
-03/04/2022 07:17:20 - INFO - codeparrot_training - Step 15172: {'lr': 0.000490291355447213, 'samples': 7768576, 'steps': 15172, 'loss/train': 3.7962846755981445}
-03/04/2022 07:17:21 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 07:17:25 - INFO - codeparrot_training - Step 15173: {'lr': 0.0004902898908755424, 'samples': 7769088, 'steps': 15173, 'loss/train': 1.7255077362060547}
-03/04/2022 07:17:29 - INFO - codeparrot_training - Step 15174: {'lr': 0.0004902884261956007, 'samples': 7769600, 'steps': 15174, 'loss/train': 1.0302788019180298}
-03/04/2022 07:17:30 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/04/2022 07:17:34 - INFO - codeparrot_training - Step 15175: {'lr': 0.0004902869614073889, 'samples': 7770112, 'steps': 15175, 'loss/train': 1.2291743755340576}
-03/04/2022 07:17:37 - INFO - codeparrot_training - Step 15176: {'lr': 0.0004902854965109074, 'samples': 7770624, 'steps': 15176, 'loss/train': 1.9349719285964966}
-03/04/2022 07:17:39 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/04/2022 07:17:42 - INFO - codeparrot_training - Step 15177: {'lr': 0.0004902840315061571, 'samples': 7771136, 'steps': 15177, 'loss/train': 0.698824942111969}
-03/04/2022 07:17:45 - INFO - codeparrot_training - Step 15178: {'lr': 0.0004902825663931384, 'samples': 7771648, 'steps': 15178, 'loss/train': 1.9414786100387573}
-03/04/2022 07:17:47 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 07:17:51 - INFO - codeparrot_training - Step 15179: {'lr': 0.0004902811011718521, 'samples': 7772160, 'steps': 15179, 'loss/train': 1.5617390871047974}
-03/04/2022 07:17:54 - INFO - codeparrot_training - Step 15180: {'lr': 0.0004902796358422989, 'samples': 7772672, 'steps': 15180, 'loss/train': 2.312124490737915}
-03/04/2022 07:17:56 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 07:17:59 - INFO - codeparrot_training - Step 15181: {'lr': 0.0004902781704044793, 'samples': 7773184, 'steps': 15181, 'loss/train': 1.7238904237747192}
-03/04/2022 07:18:02 - INFO - codeparrot_training - Step 15182: {'lr': 0.0004902767048583942, 'samples': 7773696, 'steps': 15182, 'loss/train': 2.102057695388794}
-03/04/2022 07:18:04 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 07:18:08 - INFO - codeparrot_training - Step 15183: {'lr': 0.000490275239204044, 'samples': 7774208, 'steps': 15183, 'loss/train': 1.9617153406143188}
-03/04/2022 07:18:11 - INFO - codeparrot_training - Step 15184: {'lr': 0.0004902737734414296, 'samples': 7774720, 'steps': 15184, 'loss/train': 1.735923171043396}
-03/04/2022 07:18:13 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/04/2022 07:18:16 - INFO - codeparrot_training - Step 15185: {'lr': 0.0004902723075705514, 'samples': 7775232, 'steps': 15185, 'loss/train': 1.4334698915481567}
-03/04/2022 07:18:19 - INFO - codeparrot_training - Step 15186: {'lr': 0.0004902708415914103, 'samples': 7775744, 'steps': 15186, 'loss/train': 2.086953639984131}
-03/04/2022 07:18:21 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 07:18:25 - INFO - codeparrot_training - Step 15187: {'lr': 0.0004902693755040069, 'samples': 7776256, 'steps': 15187, 'loss/train': 2.099219799041748}
-03/04/2022 07:18:28 - INFO - codeparrot_training - Step 15188: {'lr': 0.0004902679093083418, 'samples': 7776768, 'steps': 15188, 'loss/train': 1.505436897277832}
-03/04/2022 07:18:30 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 07:18:33 - INFO - codeparrot_training - Step 15189: {'lr': 0.0004902664430044156, 'samples': 7777280, 'steps': 15189, 'loss/train': 2.5259106159210205}
-03/04/2022 07:18:36 - INFO - codeparrot_training - Step 15190: {'lr': 0.0004902649765922292, 'samples': 7777792, 'steps': 15190, 'loss/train': 1.666769027709961}
-03/04/2022 07:18:38 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/04/2022 07:18:41 - INFO - codeparrot_training - Step 15191: {'lr': 0.0004902635100717831, 'samples': 7778304, 'steps': 15191, 'loss/train': 2.411850929260254}
-03/04/2022 07:18:45 - INFO - codeparrot_training - Step 15192: {'lr': 0.0004902620434430778, 'samples': 7778816, 'steps': 15192, 'loss/train': 1.8869235515594482}
-03/04/2022 07:18:47 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/04/2022 07:18:50 - INFO - codeparrot_training - Step 15193: {'lr': 0.0004902605767061142, 'samples': 7779328, 'steps': 15193, 'loss/train': 2.333179235458374}
-03/04/2022 07:18:53 - INFO - codeparrot_training - Step 15194: {'lr': 0.000490259109860893, 'samples': 7779840, 'steps': 15194, 'loss/train': 2.038902997970581}
-03/04/2022 07:18:55 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/04/2022 07:18:58 - INFO - codeparrot_training - Step 15195: {'lr': 0.0004902576429074146, 'samples': 7780352, 'steps': 15195, 'loss/train': 2.3260610103607178}
-03/04/2022 07:19:01 - INFO - codeparrot_training - Step 15196: {'lr': 0.0004902561758456799, 'samples': 7780864, 'steps': 15196, 'loss/train': 1.5010385513305664}
-03/04/2022 07:19:03 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/04/2022 07:19:07 - INFO - codeparrot_training - Step 15197: {'lr': 0.0004902547086756895, 'samples': 7781376, 'steps': 15197, 'loss/train': 1.5812582969665527}
-03/04/2022 07:19:10 - INFO - codeparrot_training - Step 15198: {'lr': 0.000490253241397444, 'samples': 7781888, 'steps': 15198, 'loss/train': 1.8837867975234985}
-03/04/2022 07:19:12 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/04/2022 07:19:15 - INFO - codeparrot_training - Step 15199: {'lr': 0.0004902517740109441, 'samples': 7782400, 'steps': 15199, 'loss/train': 0.7866479754447937}
-03/04/2022 07:19:18 - INFO - codeparrot_training - Step 15200: {'lr': 0.0004902503065161905, 'samples': 7782912, 'steps': 15200, 'loss/train': 1.841648817062378}
-03/04/2022 07:19:20 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/04/2022 07:19:24 - INFO - codeparrot_training - Step 15201: {'lr': 0.0004902488389131837, 'samples': 7783424, 'steps': 15201, 'loss/train': 2.3344342708587646}
-03/04/2022 07:19:27 - INFO - codeparrot_training - Step 15202: {'lr': 0.0004902473712019246, 'samples': 7783936, 'steps': 15202, 'loss/train': 2.5264275074005127}
-03/04/2022 07:19:29 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/04/2022 07:19:32 - INFO - codeparrot_training - Step 15203: {'lr': 0.0004902459033824137, 'samples': 7784448, 'steps': 15203, 'loss/train': 1.5581485033035278}
-03/04/2022 07:19:35 - INFO - codeparrot_training - Step 15204: {'lr': 0.0004902444354546516, 'samples': 7784960, 'steps': 15204, 'loss/train': 2.0676255226135254}
-03/04/2022 07:19:37 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/04/2022 07:19:40 - INFO - codeparrot_training - Step 15205: {'lr': 0.0004902429674186392, 'samples': 7785472, 'steps': 15205, 'loss/train': 1.9360315799713135}
-03/04/2022 07:19:43 - INFO - codeparrot_training - Step 15206: {'lr': 0.000490241499274377, 'samples': 7785984, 'steps': 15206, 'loss/train': 2.9299957752227783}
-03/04/2022 07:19:45 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/04/2022 07:19:49 - INFO - codeparrot_training - Step 15207: {'lr': 0.0004902400310218657, 'samples': 7786496, 'steps': 15207, 'loss/train': 1.4535551071166992}
-03/04/2022 07:19:52 - INFO - codeparrot_training - Step 15208: {'lr': 0.0004902385626611059, 'samples': 7787008, 'steps': 15208, 'loss/train': 2.0935304164886475}
-03/04/2022 07:19:54 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 07:19:57 - INFO - codeparrot_training - Step 15209: {'lr': 0.0004902370941920984, 'samples': 7787520, 'steps': 15209, 'loss/train': 1.5534124374389648}
-03/04/2022 07:20:00 - INFO - codeparrot_training - Step 15210: {'lr': 0.0004902356256148437, 'samples': 7788032, 'steps': 15210, 'loss/train': 1.4026484489440918}
-03/04/2022 07:20:02 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 07:20:06 - INFO - codeparrot_training - Step 15211: {'lr': 0.0004902341569293425, 'samples': 7788544, 'steps': 15211, 'loss/train': 1.85818350315094}
-03/04/2022 07:20:09 - INFO - codeparrot_training - Step 15212: {'lr': 0.0004902326881355955, 'samples': 7789056, 'steps': 15212, 'loss/train': 0.7760187387466431}
-03/04/2022 07:20:11 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 07:20:14 - INFO - codeparrot_training - Step 15213: {'lr': 0.0004902312192336034, 'samples': 7789568, 'steps': 15213, 'loss/train': 2.8424904346466064}
-03/04/2022 07:20:17 - INFO - codeparrot_training - Step 15214: {'lr': 0.000490229750223367, 'samples': 7790080, 'steps': 15214, 'loss/train': 2.1905300617218018}
-03/04/2022 07:20:19 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/04/2022 07:20:22 - INFO - codeparrot_training - Step 15215: {'lr': 0.0004902282811048864, 'samples': 7790592, 'steps': 15215, 'loss/train': 2.2173264026641846}
-03/04/2022 07:20:26 - INFO - codeparrot_training - Step 15216: {'lr': 0.000490226811878163, 'samples': 7791104, 'steps': 15216, 'loss/train': 2.5282797813415527}
-03/04/2022 07:20:28 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/04/2022 07:20:31 - INFO - codeparrot_training - Step 15217: {'lr': 0.0004902253425431969, 'samples': 7791616, 'steps': 15217, 'loss/train': 1.6504093408584595}
-03/04/2022 07:20:34 - INFO - codeparrot_training - Step 15218: {'lr': 0.000490223873099989, 'samples': 7792128, 'steps': 15218, 'loss/train': 2.87551212310791}
-03/04/2022 07:20:36 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/04/2022 07:20:40 - INFO - codeparrot_training - Step 15219: {'lr': 0.00049022240354854, 'samples': 7792640, 'steps': 15219, 'loss/train': 2.115551471710205}
-03/04/2022 07:20:43 - INFO - codeparrot_training - Step 15220: {'lr': 0.0004902209338888503, 'samples': 7793152, 'steps': 15220, 'loss/train': 2.09633207321167}
-03/04/2022 07:20:45 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/04/2022 07:20:48 - INFO - codeparrot_training - Step 15221: {'lr': 0.000490219464120921, 'samples': 7793664, 'steps': 15221, 'loss/train': 2.0706825256347656}
-03/04/2022 07:20:51 - INFO - codeparrot_training - Step 15222: {'lr': 0.0004902179942447524, 'samples': 7794176, 'steps': 15222, 'loss/train': 0.9063794612884521}
-03/04/2022 07:20:53 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/04/2022 07:20:56 - INFO - codeparrot_training - Step 15223: {'lr': 0.0004902165242603452, 'samples': 7794688, 'steps': 15223, 'loss/train': 2.0035009384155273}
-03/04/2022 07:21:00 - INFO - codeparrot_training - Step 15224: {'lr': 0.0004902150541677003, 'samples': 7795200, 'steps': 15224, 'loss/train': 1.4303995370864868}
-03/04/2022 07:21:01 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/04/2022 07:21:05 - INFO - codeparrot_training - Step 15225: {'lr': 0.0004902135839668181, 'samples': 7795712, 'steps': 15225, 'loss/train': 1.6400343179702759}
-03/04/2022 07:21:08 - INFO - codeparrot_training - Step 15226: {'lr': 0.0004902121136576994, 'samples': 7796224, 'steps': 15226, 'loss/train': 2.183572769165039}
-03/04/2022 07:21:10 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 07:21:13 - INFO - codeparrot_training - Step 15227: {'lr': 0.0004902106432403448, 'samples': 7796736, 'steps': 15227, 'loss/train': 1.891182541847229}
-03/04/2022 07:21:16 - INFO - codeparrot_training - Step 15228: {'lr': 0.0004902091727147551, 'samples': 7797248, 'steps': 15228, 'loss/train': 1.5757231712341309}
-03/04/2022 07:21:18 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/04/2022 07:21:22 - INFO - codeparrot_training - Step 15229: {'lr': 0.0004902077020809307, 'samples': 7797760, 'steps': 15229, 'loss/train': 1.731397032737732}
-03/04/2022 07:21:25 - INFO - codeparrot_training - Step 15230: {'lr': 0.0004902062313388725, 'samples': 7798272, 'steps': 15230, 'loss/train': 1.678324818611145}
-03/04/2022 07:21:27 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/04/2022 07:21:30 - INFO - codeparrot_training - Step 15231: {'lr': 0.0004902047604885811, 'samples': 7798784, 'steps': 15231, 'loss/train': 1.8555573225021362}
-03/04/2022 07:21:33 - INFO - codeparrot_training - Step 15232: {'lr': 0.0004902032895300571, 'samples': 7799296, 'steps': 15232, 'loss/train': 1.5739105939865112}
-03/04/2022 07:21:37 - INFO - codeparrot_training - Step 15233: {'lr': 0.0004902018184633012, 'samples': 7799808, 'steps': 15233, 'loss/train': 1.8048126697540283}
-03/04/2022 07:21:37 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/04/2022 07:21:42 - INFO - codeparrot_training - Step 15234: {'lr': 0.0004902003472883141, 'samples': 7800320, 'steps': 15234, 'loss/train': 1.7564748525619507}
-03/04/2022 07:21:45 - INFO - codeparrot_training - Step 15235: {'lr': 0.0004901988760050964, 'samples': 7800832, 'steps': 15235, 'loss/train': 3.1761510372161865}
-03/04/2022 07:21:45 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/04/2022 07:21:50 - INFO - codeparrot_training - Step 15236: {'lr': 0.0004901974046136488, 'samples': 7801344, 'steps': 15236, 'loss/train': 1.9835566282272339}
-03/04/2022 07:21:53 - INFO - codeparrot_training - Step 15237: {'lr': 0.000490195933113972, 'samples': 7801856, 'steps': 15237, 'loss/train': 2.1465821266174316}
-03/04/2022 07:21:53 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/04/2022 07:21:59 - INFO - codeparrot_training - Step 15238: {'lr': 0.0004901944615060665, 'samples': 7802368, 'steps': 15238, 'loss/train': 2.3163886070251465}
-03/04/2022 07:22:02 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 07:22:04 - INFO - codeparrot_training - Step 15239: {'lr': 0.0004901929897899331, 'samples': 7802880, 'steps': 15239, 'loss/train': 0.7243784666061401}
-03/04/2022 07:22:07 - INFO - codeparrot_training - Step 15240: {'lr': 0.0004901915179655726, 'samples': 7803392, 'steps': 15240, 'loss/train': 2.2140231132507324}
-03/04/2022 07:22:10 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/04/2022 07:22:12 - INFO - codeparrot_training - Step 15241: {'lr': 0.0004901900460329853, 'samples': 7803904, 'steps': 15241, 'loss/train': 1.2285170555114746}
-03/04/2022 07:22:16 - INFO - codeparrot_training - Step 15242: {'lr': 0.0004901885739921723, 'samples': 7804416, 'steps': 15242, 'loss/train': 2.7111494541168213}
-03/04/2022 07:22:18 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/04/2022 07:22:21 - INFO - codeparrot_training - Step 15243: {'lr': 0.0004901871018431339, 'samples': 7804928, 'steps': 15243, 'loss/train': 1.1326370239257812}
-03/04/2022 07:22:24 - INFO - codeparrot_training - Step 15244: {'lr': 0.0004901856295858708, 'samples': 7805440, 'steps': 15244, 'loss/train': 2.541508913040161}
-03/04/2022 07:22:27 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/04/2022 07:22:29 - INFO - codeparrot_training - Step 15245: {'lr': 0.0004901841572203839, 'samples': 7805952, 'steps': 15245, 'loss/train': 2.1089820861816406}
-03/04/2022 07:22:32 - INFO - codeparrot_training - Step 15246: {'lr': 0.0004901826847466738, 'samples': 7806464, 'steps': 15246, 'loss/train': 1.3867634534835815}
-03/04/2022 07:22:35 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/04/2022 07:22:38 - INFO - codeparrot_training - Step 15247: {'lr': 0.000490181212164741, 'samples': 7806976, 'steps': 15247, 'loss/train': 1.8241404294967651}
-03/04/2022 07:22:41 - INFO - codeparrot_training - Step 15248: {'lr': 0.0004901797394745861, 'samples': 7807488, 'steps': 15248, 'loss/train': 2.1299917697906494}
-03/04/2022 07:22:44 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/04/2022 07:22:46 - INFO - codeparrot_training - Step 15249: {'lr': 0.0004901782666762102, 'samples': 7808000, 'steps': 15249, 'loss/train': 1.1770910024642944}
-03/04/2022 07:22:49 - INFO - codeparrot_training - Step 15250: {'lr': 0.0004901767937696135, 'samples': 7808512, 'steps': 15250, 'loss/train': 1.8715301752090454}
-03/04/2022 07:22:52 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 07:22:55 - INFO - codeparrot_training - Step 15251: {'lr': 0.0004901753207547969, 'samples': 7809024, 'steps': 15251, 'loss/train': 0.9937017560005188}
-03/04/2022 07:22:58 - INFO - codeparrot_training - Step 15252: {'lr': 0.000490173847631761, 'samples': 7809536, 'steps': 15252, 'loss/train': 1.591740369796753}
-03/04/2022 07:23:01 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/04/2022 07:23:03 - INFO - codeparrot_training - Step 15253: {'lr': 0.0004901723744005065, 'samples': 7810048, 'steps': 15253, 'loss/train': 1.4574079513549805}
-03/04/2022 07:23:06 - INFO - codeparrot_training - Step 15254: {'lr': 0.0004901709010610339, 'samples': 7810560, 'steps': 15254, 'loss/train': 1.7175101041793823}
-03/04/2022 07:23:09 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/04/2022 07:23:12 - INFO - codeparrot_training - Step 15255: {'lr': 0.0004901694276133441, 'samples': 7811072, 'steps': 15255, 'loss/train': 1.7223721742630005}
-03/04/2022 07:23:15 - INFO - codeparrot_training - Step 15256: {'lr': 0.0004901679540574377, 'samples': 7811584, 'steps': 15256, 'loss/train': 1.258499026298523}
-03/04/2022 07:23:18 - INFO - codeparrot_training - Step 15257: {'lr': 0.0004901664803933153, 'samples': 7812096, 'steps': 15257, 'loss/train': 3.2945361137390137}
-03/04/2022 07:23:19 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/04/2022 07:23:23 - INFO - codeparrot_training - Step 15258: {'lr': 0.0004901650066209775, 'samples': 7812608, 'steps': 15258, 'loss/train': 1.926669716835022}
-03/04/2022 07:23:26 - INFO - codeparrot_training - Step 15259: {'lr': 0.0004901635327404252, 'samples': 7813120, 'steps': 15259, 'loss/train': 2.186293601989746}
-03/04/2022 07:23:27 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/04/2022 07:23:32 - INFO - codeparrot_training - Step 15260: {'lr': 0.0004901620587516587, 'samples': 7813632, 'steps': 15260, 'loss/train': 2.044063091278076}
-03/04/2022 07:23:35 - INFO - codeparrot_training - Step 15261: {'lr': 0.0004901605846546791, 'samples': 7814144, 'steps': 15261, 'loss/train': 1.447873830795288}
-03/04/2022 07:23:35 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/04/2022 07:23:40 - INFO - codeparrot_training - Step 15262: {'lr': 0.0004901591104494868, 'samples': 7814656, 'steps': 15262, 'loss/train': 1.7271538972854614}
-03/04/2022 07:23:43 - INFO - codeparrot_training - Step 15263: {'lr': 0.0004901576361360825, 'samples': 7815168, 'steps': 15263, 'loss/train': 1.806506872177124}
-03/04/2022 07:23:44 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 07:23:49 - INFO - codeparrot_training - Step 15264: {'lr': 0.0004901561617144667, 'samples': 7815680, 'steps': 15264, 'loss/train': 2.1292619705200195}
-03/04/2022 07:23:52 - INFO - codeparrot_training - Step 15265: {'lr': 0.0004901546871846405, 'samples': 7816192, 'steps': 15265, 'loss/train': 1.0907188653945923}
-03/04/2022 07:23:53 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/04/2022 07:23:57 - INFO - codeparrot_training - Step 15266: {'lr': 0.0004901532125466041, 'samples': 7816704, 'steps': 15266, 'loss/train': 1.791675090789795}
-03/04/2022 07:24:00 - INFO - codeparrot_training - Step 15267: {'lr': 0.0004901517378003584, 'samples': 7817216, 'steps': 15267, 'loss/train': 1.4815144538879395}
-03/04/2022 07:24:01 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/04/2022 07:24:06 - INFO - codeparrot_training - Step 15268: {'lr': 0.0004901502629459042, 'samples': 7817728, 'steps': 15268, 'loss/train': 1.456441879272461}
-03/04/2022 07:24:09 - INFO - codeparrot_training - Step 15269: {'lr': 0.000490148787983242, 'samples': 7818240, 'steps': 15269, 'loss/train': 1.6347016096115112}
-03/04/2022 07:24:09 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 07:24:14 - INFO - codeparrot_training - Step 15270: {'lr': 0.0004901473129123723, 'samples': 7818752, 'steps': 15270, 'loss/train': 2.2746646404266357}
-03/04/2022 07:24:17 - INFO - codeparrot_training - Step 15271: {'lr': 0.0004901458377332959, 'samples': 7819264, 'steps': 15271, 'loss/train': 1.4392486810684204}
-03/04/2022 07:24:18 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/04/2022 07:24:22 - INFO - codeparrot_training - Step 15272: {'lr': 0.0004901443624460136, 'samples': 7819776, 'steps': 15272, 'loss/train': 2.8615505695343018}
-03/04/2022 07:24:26 - INFO - codeparrot_training - Step 15273: {'lr': 0.000490142887050526, 'samples': 7820288, 'steps': 15273, 'loss/train': 1.342346429824829}
-03/04/2022 07:24:26 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 07:24:31 - INFO - codeparrot_training - Step 15274: {'lr': 0.0004901414115468335, 'samples': 7820800, 'steps': 15274, 'loss/train': 2.0299603939056396}
-03/04/2022 07:24:34 - INFO - codeparrot_training - Step 15275: {'lr': 0.0004901399359349372, 'samples': 7821312, 'steps': 15275, 'loss/train': 2.2227683067321777}
-03/04/2022 07:24:34 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 07:24:39 - INFO - codeparrot_training - Step 15276: {'lr': 0.0004901384602148376, 'samples': 7821824, 'steps': 15276, 'loss/train': 2.1070261001586914}
-03/04/2022 07:24:42 - INFO - codeparrot_training - Step 15277: {'lr': 0.0004901369843865351, 'samples': 7822336, 'steps': 15277, 'loss/train': 1.4880017042160034}
-03/04/2022 07:24:43 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/04/2022 07:24:48 - INFO - codeparrot_training - Step 15278: {'lr': 0.0004901355084500307, 'samples': 7822848, 'steps': 15278, 'loss/train': 3.137118339538574}
-03/04/2022 07:24:51 - INFO - codeparrot_training - Step 15279: {'lr': 0.000490134032405325, 'samples': 7823360, 'steps': 15279, 'loss/train': 2.436488628387451}
-03/04/2022 07:24:51 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 07:24:56 - INFO - codeparrot_training - Step 15280: {'lr': 0.0004901325562524185, 'samples': 7823872, 'steps': 15280, 'loss/train': 1.637918472290039}
-03/04/2022 07:24:59 - INFO - codeparrot_training - Step 15281: {'lr': 0.0004901310799913121, 'samples': 7824384, 'steps': 15281, 'loss/train': 2.729994535446167}
-03/04/2022 07:25:00 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 07:25:04 - INFO - codeparrot_training - Step 15282: {'lr': 0.0004901296036220062, 'samples': 7824896, 'steps': 15282, 'loss/train': 2.30092453956604}
-03/04/2022 07:25:08 - INFO - codeparrot_training - Step 15283: {'lr': 0.0004901281271445016, 'samples': 7825408, 'steps': 15283, 'loss/train': 2.0814621448516846}
-03/04/2022 07:25:08 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/04/2022 07:25:13 - INFO - codeparrot_training - Step 15284: {'lr': 0.000490126650558799, 'samples': 7825920, 'steps': 15284, 'loss/train': 1.6219745874404907}
-03/04/2022 07:25:16 - INFO - codeparrot_training - Step 15285: {'lr': 0.000490125173864899, 'samples': 7826432, 'steps': 15285, 'loss/train': 1.4268916845321655}
-03/04/2022 07:25:17 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/04/2022 07:25:21 - INFO - codeparrot_training - Step 15286: {'lr': 0.0004901236970628024, 'samples': 7826944, 'steps': 15286, 'loss/train': 1.961130976676941}
-03/04/2022 07:25:25 - INFO - codeparrot_training - Step 15287: {'lr': 0.0004901222201525099, 'samples': 7827456, 'steps': 15287, 'loss/train': 1.8257182836532593}
-03/04/2022 07:25:26 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/04/2022 07:25:30 - INFO - codeparrot_training - Step 15288: {'lr': 0.0004901207431340218, 'samples': 7827968, 'steps': 15288, 'loss/train': 2.2725532054901123}
-03/04/2022 07:25:33 - INFO - codeparrot_training - Step 15289: {'lr': 0.000490119266007339, 'samples': 7828480, 'steps': 15289, 'loss/train': 1.7536238431930542}
-03/04/2022 07:25:34 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/04/2022 07:25:38 - INFO - codeparrot_training - Step 15290: {'lr': 0.0004901177887724623, 'samples': 7828992, 'steps': 15290, 'loss/train': 2.088576555252075}
-03/04/2022 07:25:42 - INFO - codeparrot_training - Step 15291: {'lr': 0.0004901163114293921, 'samples': 7829504, 'steps': 15291, 'loss/train': 2.578240394592285}
-03/04/2022 07:25:43 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/04/2022 07:25:47 - INFO - codeparrot_training - Step 15292: {'lr': 0.0004901148339781293, 'samples': 7830016, 'steps': 15292, 'loss/train': 1.7349385023117065}
-03/04/2022 07:25:50 - INFO - codeparrot_training - Step 15293: {'lr': 0.0004901133564186744, 'samples': 7830528, 'steps': 15293, 'loss/train': 1.563867211341858}
-03/04/2022 07:25:51 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/04/2022 07:25:55 - INFO - codeparrot_training - Step 15294: {'lr': 0.0004901118787510281, 'samples': 7831040, 'steps': 15294, 'loss/train': 1.7346563339233398}
-03/04/2022 07:25:58 - INFO - codeparrot_training - Step 15295: {'lr': 0.0004901104009751912, 'samples': 7831552, 'steps': 15295, 'loss/train': 2.137028694152832}
-03/04/2022 07:25:59 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 07:26:04 - INFO - codeparrot_training - Step 15296: {'lr': 0.0004901089230911642, 'samples': 7832064, 'steps': 15296, 'loss/train': 2.3368046283721924}
-03/04/2022 07:26:07 - INFO - codeparrot_training - Step 15297: {'lr': 0.0004901074450989479, 'samples': 7832576, 'steps': 15297, 'loss/train': 1.988429069519043}
-03/04/2022 07:26:08 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/04/2022 07:26:12 - INFO - codeparrot_training - Step 15298: {'lr': 0.0004901059669985427, 'samples': 7833088, 'steps': 15298, 'loss/train': 2.413472890853882}
-03/04/2022 07:26:15 - INFO - codeparrot_training - Step 15299: {'lr': 0.0004901044887899496, 'samples': 7833600, 'steps': 15299, 'loss/train': 1.4780139923095703}
-03/04/2022 07:26:16 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/04/2022 07:26:20 - INFO - codeparrot_training - Step 15300: {'lr': 0.0004901030104731691, 'samples': 7834112, 'steps': 15300, 'loss/train': 1.8444883823394775}
-03/04/2022 07:26:24 - INFO - codeparrot_training - Step 15301: {'lr': 0.0004901015320482019, 'samples': 7834624, 'steps': 15301, 'loss/train': 1.8762239217758179}
-03/04/2022 07:26:25 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 07:26:29 - INFO - codeparrot_training - Step 15302: {'lr': 0.0004901000535150486, 'samples': 7835136, 'steps': 15302, 'loss/train': 2.056536912918091}
-03/04/2022 07:26:32 - INFO - codeparrot_training - Step 15303: {'lr': 0.0004900985748737101, 'samples': 7835648, 'steps': 15303, 'loss/train': 2.1779062747955322}
-03/04/2022 07:26:33 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/04/2022 07:26:38 - INFO - codeparrot_training - Step 15304: {'lr': 0.0004900970961241866, 'samples': 7836160, 'steps': 15304, 'loss/train': 2.4206621646881104}
-03/04/2022 07:26:41 - INFO - codeparrot_training - Step 15305: {'lr': 0.0004900956172664792, 'samples': 7836672, 'steps': 15305, 'loss/train': 0.9039513468742371}
-03/04/2022 07:26:43 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 07:26:46 - INFO - codeparrot_training - Step 15306: {'lr': 0.0004900941383005884, 'samples': 7837184, 'steps': 15306, 'loss/train': 1.9638017416000366}
-03/04/2022 07:26:49 - INFO - codeparrot_training - Step 15307: {'lr': 0.0004900926592265149, 'samples': 7837696, 'steps': 15307, 'loss/train': 1.99547278881073}
-03/04/2022 07:26:52 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/04/2022 07:26:54 - INFO - codeparrot_training - Step 15308: {'lr': 0.0004900911800442593, 'samples': 7838208, 'steps': 15308, 'loss/train': 2.008004903793335}
-03/04/2022 07:26:58 - INFO - codeparrot_training - Step 15309: {'lr': 0.0004900897007538225, 'samples': 7838720, 'steps': 15309, 'loss/train': 2.3296170234680176}
-03/04/2022 07:27:00 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/04/2022 07:27:03 - INFO - codeparrot_training - Step 15310: {'lr': 0.0004900882213552049, 'samples': 7839232, 'steps': 15310, 'loss/train': 1.9096734523773193}
-03/04/2022 07:27:06 - INFO - codeparrot_training - Step 15311: {'lr': 0.0004900867418484072, 'samples': 7839744, 'steps': 15311, 'loss/train': 0.9354264736175537}
-03/04/2022 07:27:08 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/04/2022 07:27:12 - INFO - codeparrot_training - Step 15312: {'lr': 0.0004900852622334301, 'samples': 7840256, 'steps': 15312, 'loss/train': 1.0957728624343872}
-03/04/2022 07:27:15 - INFO - codeparrot_training - Step 15313: {'lr': 0.0004900837825102743, 'samples': 7840768, 'steps': 15313, 'loss/train': 1.95063316822052}
-03/04/2022 07:27:17 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/04/2022 07:27:20 - INFO - codeparrot_training - Step 15314: {'lr': 0.0004900823026789405, 'samples': 7841280, 'steps': 15314, 'loss/train': 1.5769211053848267}
-03/04/2022 07:27:23 - INFO - codeparrot_training - Step 15315: {'lr': 0.0004900808227394293, 'samples': 7841792, 'steps': 15315, 'loss/train': 1.635298252105713}
-03/04/2022 07:27:25 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/04/2022 07:27:29 - INFO - codeparrot_training - Step 15316: {'lr': 0.0004900793426917412, 'samples': 7842304, 'steps': 15316, 'loss/train': 2.0013387203216553}
-03/04/2022 07:27:32 - INFO - codeparrot_training - Step 15317: {'lr': 0.0004900778625358774, 'samples': 7842816, 'steps': 15317, 'loss/train': 1.2605314254760742}
-03/04/2022 07:27:34 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/04/2022 07:27:37 - INFO - codeparrot_training - Step 15318: {'lr': 0.000490076382271838, 'samples': 7843328, 'steps': 15318, 'loss/train': 2.136317253112793}
-03/04/2022 07:27:40 - INFO - codeparrot_training - Step 15319: {'lr': 0.0004900749018996238, 'samples': 7843840, 'steps': 15319, 'loss/train': 2.025815725326538}
-03/04/2022 07:27:43 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/04/2022 07:27:45 - INFO - codeparrot_training - Step 15320: {'lr': 0.0004900734214192358, 'samples': 7844352, 'steps': 15320, 'loss/train': 2.649696111679077}
-03/04/2022 07:27:49 - INFO - codeparrot_training - Step 15321: {'lr': 0.0004900719408306743, 'samples': 7844864, 'steps': 15321, 'loss/train': 1.9660518169403076}
-03/04/2022 07:27:52 - INFO - codeparrot_training - Step 15322: {'lr': 0.0004900704601339401, 'samples': 7845376, 'steps': 15322, 'loss/train': 0.16374270617961884}
-03/04/2022 07:27:52 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 07:27:57 - INFO - codeparrot_training - Step 15323: {'lr': 0.0004900689793290339, 'samples': 7845888, 'steps': 15323, 'loss/train': 1.5246270895004272}
-03/04/2022 07:28:00 - INFO - codeparrot_training - Step 15324: {'lr': 0.0004900674984159562, 'samples': 7846400, 'steps': 15324, 'loss/train': 1.683797001838684}
-03/04/2022 07:28:00 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/04/2022 07:28:06 - INFO - codeparrot_training - Step 15325: {'lr': 0.0004900660173947079, 'samples': 7846912, 'steps': 15325, 'loss/train': 2.071974277496338}
-03/04/2022 07:28:08 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/04/2022 07:28:11 - INFO - codeparrot_training - Step 15326: {'lr': 0.0004900645362652895, 'samples': 7847424, 'steps': 15326, 'loss/train': 1.0616647005081177}
-03/04/2022 07:28:14 - INFO - codeparrot_training - Step 15327: {'lr': 0.0004900630550277018, 'samples': 7847936, 'steps': 15327, 'loss/train': 2.631700277328491}
-03/04/2022 07:28:17 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 07:28:19 - INFO - codeparrot_training - Step 15328: {'lr': 0.0004900615736819452, 'samples': 7848448, 'steps': 15328, 'loss/train': 2.0920910835266113}
-03/04/2022 07:28:23 - INFO - codeparrot_training - Step 15329: {'lr': 0.0004900600922280207, 'samples': 7848960, 'steps': 15329, 'loss/train': 2.014713764190674}
-03/04/2022 07:28:25 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/04/2022 07:28:28 - INFO - codeparrot_training - Step 15330: {'lr': 0.0004900586106659289, 'samples': 7849472, 'steps': 15330, 'loss/train': 2.2079737186431885}
-03/04/2022 07:28:31 - INFO - codeparrot_training - Step 15331: {'lr': 0.0004900571289956703, 'samples': 7849984, 'steps': 15331, 'loss/train': 2.026646375656128}
-03/04/2022 07:28:34 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 07:28:37 - INFO - codeparrot_training - Step 15332: {'lr': 0.0004900556472172457, 'samples': 7850496, 'steps': 15332, 'loss/train': 2.5494980812072754}
-03/04/2022 07:28:40 - INFO - codeparrot_training - Step 15333: {'lr': 0.0004900541653306557, 'samples': 7851008, 'steps': 15333, 'loss/train': 2.3377397060394287}
-03/04/2022 07:28:43 - INFO - codeparrot_training - Step 15334: {'lr': 0.0004900526833359009, 'samples': 7851520, 'steps': 15334, 'loss/train': 2.220517635345459}
-03/04/2022 07:28:43 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/04/2022 07:28:48 - INFO - codeparrot_training - Step 15335: {'lr': 0.0004900512012329822, 'samples': 7852032, 'steps': 15335, 'loss/train': 2.1473395824432373}
-03/04/2022 07:28:51 - INFO - codeparrot_training - Step 15336: {'lr': 0.0004900497190219002, 'samples': 7852544, 'steps': 15336, 'loss/train': 1.8074777126312256}
-03/04/2022 07:28:51 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/04/2022 07:28:57 - INFO - codeparrot_training - Step 15337: {'lr': 0.0004900482367026554, 'samples': 7853056, 'steps': 15337, 'loss/train': 2.5616025924682617}
-03/04/2022 07:29:00 - INFO - codeparrot_training - Step 15338: {'lr': 0.0004900467542752485, 'samples': 7853568, 'steps': 15338, 'loss/train': 0.3747663199901581}
-03/04/2022 07:29:00 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 07:29:05 - INFO - codeparrot_training - Step 15339: {'lr': 0.0004900452717396803, 'samples': 7854080, 'steps': 15339, 'loss/train': 0.3845232427120209}
-03/04/2022 07:29:08 - INFO - codeparrot_training - Step 15340: {'lr': 0.0004900437890959515, 'samples': 7854592, 'steps': 15340, 'loss/train': 2.1470634937286377}
-03/04/2022 07:29:08 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 07:29:13 - INFO - codeparrot_training - Step 15341: {'lr': 0.0004900423063440625, 'samples': 7855104, 'steps': 15341, 'loss/train': 3.0711188316345215}
-03/04/2022 07:29:17 - INFO - codeparrot_training - Step 15342: {'lr': 0.0004900408234840142, 'samples': 7855616, 'steps': 15342, 'loss/train': 2.0878663063049316}
-03/04/2022 07:29:17 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/04/2022 07:29:22 - INFO - codeparrot_training - Step 15343: {'lr': 0.0004900393405158073, 'samples': 7856128, 'steps': 15343, 'loss/train': 2.511601448059082}
-03/04/2022 07:29:25 - INFO - codeparrot_training - Step 15344: {'lr': 0.0004900378574394423, 'samples': 7856640, 'steps': 15344, 'loss/train': 2.314175844192505}
-03/04/2022 07:29:26 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/04/2022 07:29:30 - INFO - codeparrot_training - Step 15345: {'lr': 0.00049003637425492, 'samples': 7857152, 'steps': 15345, 'loss/train': 2.021688938140869}
-03/04/2022 07:29:34 - INFO - codeparrot_training - Step 15346: {'lr': 0.0004900348909622409, 'samples': 7857664, 'steps': 15346, 'loss/train': 1.5831284523010254}
-03/04/2022 07:29:34 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/04/2022 07:29:39 - INFO - codeparrot_training - Step 15347: {'lr': 0.0004900334075614059, 'samples': 7858176, 'steps': 15347, 'loss/train': 2.6837236881256104}
-03/04/2022 07:29:42 - INFO - codeparrot_training - Step 15348: {'lr': 0.0004900319240524155, 'samples': 7858688, 'steps': 15348, 'loss/train': 1.692237377166748}
-03/04/2022 07:29:42 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 07:29:47 - INFO - codeparrot_training - Step 15349: {'lr': 0.0004900304404352704, 'samples': 7859200, 'steps': 15349, 'loss/train': 2.2119593620300293}
-03/04/2022 07:29:50 - INFO - codeparrot_training - Step 15350: {'lr': 0.0004900289567099713, 'samples': 7859712, 'steps': 15350, 'loss/train': 1.4525253772735596}
-03/04/2022 07:29:51 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/04/2022 07:29:56 - INFO - codeparrot_training - Step 15351: {'lr': 0.000490027472876519, 'samples': 7860224, 'steps': 15351, 'loss/train': 0.9180548191070557}
-03/04/2022 07:29:59 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/04/2022 07:30:01 - INFO - codeparrot_training - Step 15352: {'lr': 0.0004900259889349138, 'samples': 7860736, 'steps': 15352, 'loss/train': 2.1855111122131348}
-03/04/2022 07:30:05 - INFO - codeparrot_training - Step 15353: {'lr': 0.0004900245048851567, 'samples': 7861248, 'steps': 15353, 'loss/train': 2.287900924682617}
-03/04/2022 07:30:08 - INFO - codeparrot_training - Step 15354: {'lr': 0.0004900230207272483, 'samples': 7861760, 'steps': 15354, 'loss/train': 0.17259082198143005}
-03/04/2022 07:30:08 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 07:30:13 - INFO - codeparrot_training - Step 15355: {'lr': 0.000490021536461189, 'samples': 7862272, 'steps': 15355, 'loss/train': 1.9748649597167969}
-03/04/2022 07:30:16 - INFO - codeparrot_training - Step 15356: {'lr': 0.00049002005208698, 'samples': 7862784, 'steps': 15356, 'loss/train': 0.2705856263637543}
-03/04/2022 07:30:17 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/04/2022 07:30:21 - INFO - codeparrot_training - Step 15357: {'lr': 0.0004900185676046214, 'samples': 7863296, 'steps': 15357, 'loss/train': 1.4590259790420532}
-03/04/2022 07:30:25 - INFO - codeparrot_training - Step 15358: {'lr': 0.0004900170830141144, 'samples': 7863808, 'steps': 15358, 'loss/train': 1.8637088537216187}
-03/04/2022 07:30:26 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/04/2022 07:30:30 - INFO - codeparrot_training - Step 15359: {'lr': 0.0004900155983154592, 'samples': 7864320, 'steps': 15359, 'loss/train': 2.0526022911071777}
-03/04/2022 07:30:33 - INFO - codeparrot_training - Step 15360: {'lr': 0.0004900141135086569, 'samples': 7864832, 'steps': 15360, 'loss/train': 1.3982640504837036}
-03/04/2022 07:30:34 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 07:30:38 - INFO - codeparrot_training - Step 15361: {'lr': 0.0004900126285937077, 'samples': 7865344, 'steps': 15361, 'loss/train': 1.1787586212158203}
-03/04/2022 07:30:41 - INFO - codeparrot_training - Step 15362: {'lr': 0.0004900111435706127, 'samples': 7865856, 'steps': 15362, 'loss/train': 1.76839017868042}
-03/04/2022 07:30:42 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 07:30:47 - INFO - codeparrot_training - Step 15363: {'lr': 0.0004900096584393723, 'samples': 7866368, 'steps': 15363, 'loss/train': 1.76022469997406}
-03/04/2022 07:30:50 - INFO - codeparrot_training - Step 15364: {'lr': 0.0004900081731999872, 'samples': 7866880, 'steps': 15364, 'loss/train': 1.8010162115097046}
-03/04/2022 07:30:50 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/04/2022 07:30:55 - INFO - codeparrot_training - Step 15365: {'lr': 0.0004900066878524582, 'samples': 7867392, 'steps': 15365, 'loss/train': 1.8669334650039673}
-03/04/2022 07:30:58 - INFO - codeparrot_training - Step 15366: {'lr': 0.0004900052023967859, 'samples': 7867904, 'steps': 15366, 'loss/train': 2.011361598968506}
-03/04/2022 07:30:59 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/04/2022 07:31:04 - INFO - codeparrot_training - Step 15367: {'lr': 0.0004900037168329709, 'samples': 7868416, 'steps': 15367, 'loss/train': 2.5831313133239746}
-03/04/2022 07:31:07 - INFO - codeparrot_training - Step 15368: {'lr': 0.000490002231161014, 'samples': 7868928, 'steps': 15368, 'loss/train': 1.6952158212661743}
-03/04/2022 07:31:07 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 07:31:12 - INFO - codeparrot_training - Step 15369: {'lr': 0.0004900007453809157, 'samples': 7869440, 'steps': 15369, 'loss/train': 2.6012558937072754}
-03/04/2022 07:31:15 - INFO - codeparrot_training - Step 15370: {'lr': 0.0004899992594926769, 'samples': 7869952, 'steps': 15370, 'loss/train': 2.082909107208252}
-03/04/2022 07:31:16 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 07:31:21 - INFO - codeparrot_training - Step 15371: {'lr': 0.000489997773496298, 'samples': 7870464, 'steps': 15371, 'loss/train': 1.5804387331008911}
-03/04/2022 07:31:24 - INFO - codeparrot_training - Step 15372: {'lr': 0.0004899962873917798, 'samples': 7870976, 'steps': 15372, 'loss/train': 1.3597859144210815}
-03/04/2022 07:31:25 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/04/2022 07:31:29 - INFO - codeparrot_training - Step 15373: {'lr': 0.000489994801179123, 'samples': 7871488, 'steps': 15373, 'loss/train': 0.5767632722854614}
-03/04/2022 07:31:32 - INFO - codeparrot_training - Step 15374: {'lr': 0.0004899933148583284, 'samples': 7872000, 'steps': 15374, 'loss/train': 0.2697375416755676}
-03/04/2022 07:31:33 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 07:31:37 - INFO - codeparrot_training - Step 15375: {'lr': 0.0004899918284293964, 'samples': 7872512, 'steps': 15375, 'loss/train': 1.9592632055282593}
-03/04/2022 07:31:41 - INFO - codeparrot_training - Step 15376: {'lr': 0.0004899903418923278, 'samples': 7873024, 'steps': 15376, 'loss/train': 1.408479928970337}
-03/04/2022 07:31:42 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 07:31:46 - INFO - codeparrot_training - Step 15377: {'lr': 0.0004899888552471232, 'samples': 7873536, 'steps': 15377, 'loss/train': 1.783188819885254}
-03/04/2022 07:31:49 - INFO - codeparrot_training - Step 15378: {'lr': 0.0004899873684937833, 'samples': 7874048, 'steps': 15378, 'loss/train': 1.876893162727356}
-03/04/2022 07:31:50 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/04/2022 07:31:54 - INFO - codeparrot_training - Step 15379: {'lr': 0.0004899858816323089, 'samples': 7874560, 'steps': 15379, 'loss/train': 1.3946398496627808}
-03/04/2022 07:31:57 - INFO - codeparrot_training - Step 15380: {'lr': 0.0004899843946627006, 'samples': 7875072, 'steps': 15380, 'loss/train': 1.9439603090286255}
-03/04/2022 07:31:58 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 07:32:03 - INFO - codeparrot_training - Step 15381: {'lr': 0.0004899829075849589, 'samples': 7875584, 'steps': 15381, 'loss/train': 1.363639235496521}
-03/04/2022 07:32:06 - INFO - codeparrot_training - Step 15382: {'lr': 0.0004899814203990847, 'samples': 7876096, 'steps': 15382, 'loss/train': 2.6532938480377197}
-03/04/2022 07:32:07 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 07:32:11 - INFO - codeparrot_training - Step 15383: {'lr': 0.0004899799331050785, 'samples': 7876608, 'steps': 15383, 'loss/train': 1.9514384269714355}
-03/04/2022 07:32:14 - INFO - codeparrot_training - Step 15384: {'lr': 0.0004899784457029411, 'samples': 7877120, 'steps': 15384, 'loss/train': 1.534258484840393}
-03/04/2022 07:32:15 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/04/2022 07:32:19 - INFO - codeparrot_training - Step 15385: {'lr': 0.000489976958192673, 'samples': 7877632, 'steps': 15385, 'loss/train': 2.0465333461761475}
-03/04/2022 07:32:23 - INFO - codeparrot_training - Step 15386: {'lr': 0.0004899754705742752, 'samples': 7878144, 'steps': 15386, 'loss/train': 1.786224126815796}
-03/04/2022 07:32:24 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/04/2022 07:32:28 - INFO - codeparrot_training - Step 15387: {'lr': 0.0004899739828477481, 'samples': 7878656, 'steps': 15387, 'loss/train': 1.5553171634674072}
-03/04/2022 07:32:31 - INFO - codeparrot_training - Step 15388: {'lr': 0.0004899724950130923, 'samples': 7879168, 'steps': 15388, 'loss/train': 2.878305435180664}
-03/04/2022 07:32:32 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/04/2022 07:32:36 - INFO - codeparrot_training - Step 15389: {'lr': 0.0004899710070703087, 'samples': 7879680, 'steps': 15389, 'loss/train': 1.093400001525879}
-03/04/2022 07:32:40 - INFO - codeparrot_training - Step 15390: {'lr': 0.0004899695190193978, 'samples': 7880192, 'steps': 15390, 'loss/train': 1.1266734600067139}
-03/04/2022 07:32:41 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 07:32:45 - INFO - codeparrot_training - Step 15391: {'lr': 0.0004899680308603604, 'samples': 7880704, 'steps': 15391, 'loss/train': 2.5061869621276855}
-03/04/2022 07:32:48 - INFO - codeparrot_training - Step 15392: {'lr': 0.000489966542593197, 'samples': 7881216, 'steps': 15392, 'loss/train': 0.8983432650566101}
-03/04/2022 07:32:49 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 07:32:53 - INFO - codeparrot_training - Step 15393: {'lr': 0.0004899650542179085, 'samples': 7881728, 'steps': 15393, 'loss/train': 1.6177502870559692}
-03/04/2022 07:32:56 - INFO - codeparrot_training - Step 15394: {'lr': 0.0004899635657344954, 'samples': 7882240, 'steps': 15394, 'loss/train': 1.330331563949585}
-03/04/2022 07:32:58 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/04/2022 07:33:02 - INFO - codeparrot_training - Step 15395: {'lr': 0.0004899620771429585, 'samples': 7882752, 'steps': 15395, 'loss/train': 3.236412763595581}
-03/04/2022 07:33:05 - INFO - codeparrot_training - Step 15396: {'lr': 0.0004899605884432983, 'samples': 7883264, 'steps': 15396, 'loss/train': 2.59488582611084}
-03/04/2022 07:33:06 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 07:33:10 - INFO - codeparrot_training - Step 15397: {'lr': 0.0004899590996355155, 'samples': 7883776, 'steps': 15397, 'loss/train': 1.7290860414505005}
-03/04/2022 07:33:13 - INFO - codeparrot_training - Step 15398: {'lr': 0.000489957610719611, 'samples': 7884288, 'steps': 15398, 'loss/train': 1.3584386110305786}
-03/04/2022 07:33:14 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/04/2022 07:33:19 - INFO - codeparrot_training - Step 15399: {'lr': 0.0004899561216955852, 'samples': 7884800, 'steps': 15399, 'loss/train': 1.5643391609191895}
-03/04/2022 07:33:22 - INFO - codeparrot_training - Step 15400: {'lr': 0.0004899546325634388, 'samples': 7885312, 'steps': 15400, 'loss/train': 2.9252898693084717}
-03/04/2022 07:33:24 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/04/2022 07:33:27 - INFO - codeparrot_training - Step 15401: {'lr': 0.0004899531433231728, 'samples': 7885824, 'steps': 15401, 'loss/train': 0.5506502389907837}
-03/04/2022 07:33:30 - INFO - codeparrot_training - Step 15402: {'lr': 0.0004899516539747874, 'samples': 7886336, 'steps': 15402, 'loss/train': 1.3804658651351929}
-03/04/2022 07:33:32 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/04/2022 07:33:36 - INFO - codeparrot_training - Step 15403: {'lr': 0.0004899501645182835, 'samples': 7886848, 'steps': 15403, 'loss/train': 1.5797665119171143}
-03/04/2022 07:33:39 - INFO - codeparrot_training - Step 15404: {'lr': 0.0004899486749536618, 'samples': 7887360, 'steps': 15404, 'loss/train': 1.5813759565353394}
-03/04/2022 07:33:41 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/04/2022 07:33:44 - INFO - codeparrot_training - Step 15405: {'lr': 0.000489947185280923, 'samples': 7887872, 'steps': 15405, 'loss/train': 1.7318525314331055}
-03/04/2022 07:33:47 - INFO - codeparrot_training - Step 15406: {'lr': 0.0004899456955000676, 'samples': 7888384, 'steps': 15406, 'loss/train': 1.0347015857696533}
-03/04/2022 07:33:49 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/04/2022 07:33:53 - INFO - codeparrot_training - Step 15407: {'lr': 0.0004899442056110964, 'samples': 7888896, 'steps': 15407, 'loss/train': 1.2970328330993652}
-03/04/2022 07:33:56 - INFO - codeparrot_training - Step 15408: {'lr': 0.00048994271561401, 'samples': 7889408, 'steps': 15408, 'loss/train': 1.0163860321044922}
-03/04/2022 07:33:58 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 07:34:01 - INFO - codeparrot_training - Step 15409: {'lr': 0.0004899412255088091, 'samples': 7889920, 'steps': 15409, 'loss/train': 1.7994736433029175}
-03/04/2022 07:34:04 - INFO - codeparrot_training - Step 15410: {'lr': 0.0004899397352954945, 'samples': 7890432, 'steps': 15410, 'loss/train': 2.405808210372925}
-03/04/2022 07:34:06 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 07:34:10 - INFO - codeparrot_training - Step 15411: {'lr': 0.0004899382449740667, 'samples': 7890944, 'steps': 15411, 'loss/train': 2.838749408721924}
-03/04/2022 07:34:13 - INFO - codeparrot_training - Step 15412: {'lr': 0.0004899367545445264, 'samples': 7891456, 'steps': 15412, 'loss/train': 2.049316883087158}
-03/04/2022 07:34:14 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 07:34:19 - INFO - codeparrot_training - Step 15413: {'lr': 0.0004899352640068743, 'samples': 7891968, 'steps': 15413, 'loss/train': 2.0771126747131348}
-03/04/2022 07:34:22 - INFO - codeparrot_training - Step 15414: {'lr': 0.0004899337733611113, 'samples': 7892480, 'steps': 15414, 'loss/train': 2.6827025413513184}
-03/04/2022 07:34:25 - INFO - codeparrot_training - Step 15415: {'lr': 0.0004899322826072375, 'samples': 7892992, 'steps': 15415, 'loss/train': 2.4132609367370605}
-03/04/2022 07:34:25 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/04/2022 07:34:30 - INFO - codeparrot_training - Step 15416: {'lr': 0.0004899307917452542, 'samples': 7893504, 'steps': 15416, 'loss/train': 2.190967082977295}
-03/04/2022 07:34:34 - INFO - codeparrot_training - Step 15417: {'lr': 0.0004899293007751616, 'samples': 7894016, 'steps': 15417, 'loss/train': 1.7037417888641357}
-03/04/2022 07:34:34 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 07:34:39 - INFO - codeparrot_training - Step 15418: {'lr': 0.0004899278096969605, 'samples': 7894528, 'steps': 15418, 'loss/train': 1.549236536026001}
-03/04/2022 07:34:42 - INFO - codeparrot_training - Step 15419: {'lr': 0.0004899263185106518, 'samples': 7895040, 'steps': 15419, 'loss/train': 2.7990338802337646}
-03/04/2022 07:34:43 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 07:34:47 - INFO - codeparrot_training - Step 15420: {'lr': 0.000489924827216236, 'samples': 7895552, 'steps': 15420, 'loss/train': 1.5396349430084229}
-03/04/2022 07:34:50 - INFO - codeparrot_training - Step 15421: {'lr': 0.0004899233358137137, 'samples': 7896064, 'steps': 15421, 'loss/train': 1.5125325918197632}
-03/04/2022 07:34:51 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 07:34:56 - INFO - codeparrot_training - Step 15422: {'lr': 0.0004899218443030857, 'samples': 7896576, 'steps': 15422, 'loss/train': 3.9291932582855225}
-03/04/2022 07:34:59 - INFO - codeparrot_training - Step 15423: {'lr': 0.0004899203526843526, 'samples': 7897088, 'steps': 15423, 'loss/train': 1.889095425605774}
-03/04/2022 07:35:00 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/04/2022 07:35:04 - INFO - codeparrot_training - Step 15424: {'lr': 0.000489918860957515, 'samples': 7897600, 'steps': 15424, 'loss/train': 1.970321774482727}
-03/04/2022 07:35:07 - INFO - codeparrot_training - Step 15425: {'lr': 0.0004899173691225737, 'samples': 7898112, 'steps': 15425, 'loss/train': 1.9425466060638428}
-03/04/2022 07:35:08 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 07:35:12 - INFO - codeparrot_training - Step 15426: {'lr': 0.0004899158771795295, 'samples': 7898624, 'steps': 15426, 'loss/train': 1.9016437530517578}
-03/04/2022 07:35:16 - INFO - codeparrot_training - Step 15427: {'lr': 0.0004899143851283827, 'samples': 7899136, 'steps': 15427, 'loss/train': 2.6441962718963623}
-03/04/2022 07:35:16 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 07:35:21 - INFO - codeparrot_training - Step 15428: {'lr': 0.0004899128929691343, 'samples': 7899648, 'steps': 15428, 'loss/train': 2.0410842895507812}
-03/04/2022 07:35:24 - INFO - codeparrot_training - Step 15429: {'lr': 0.0004899114007017849, 'samples': 7900160, 'steps': 15429, 'loss/train': 2.4312095642089844}
-03/04/2022 07:35:25 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 07:35:29 - INFO - codeparrot_training - Step 15430: {'lr': 0.000489909908326335, 'samples': 7900672, 'steps': 15430, 'loss/train': 2.036289930343628}
-03/04/2022 07:35:33 - INFO - codeparrot_training - Step 15431: {'lr': 0.0004899084158427855, 'samples': 7901184, 'steps': 15431, 'loss/train': 1.9077401161193848}
-03/04/2022 07:35:33 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 07:35:38 - INFO - codeparrot_training - Step 15432: {'lr': 0.0004899069232511368, 'samples': 7901696, 'steps': 15432, 'loss/train': 2.345599889755249}
-03/04/2022 07:35:41 - INFO - codeparrot_training - Step 15433: {'lr': 0.0004899054305513899, 'samples': 7902208, 'steps': 15433, 'loss/train': 1.9886152744293213}
-03/04/2022 07:35:42 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/04/2022 07:35:46 - INFO - codeparrot_training - Step 15434: {'lr': 0.0004899039377435452, 'samples': 7902720, 'steps': 15434, 'loss/train': 1.7461305856704712}
-03/04/2022 07:35:49 - INFO - codeparrot_training - Step 15435: {'lr': 0.0004899024448276036, 'samples': 7903232, 'steps': 15435, 'loss/train': 2.007394313812256}
-03/04/2022 07:35:50 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/04/2022 07:35:55 - INFO - codeparrot_training - Step 15436: {'lr': 0.0004899009518035657, 'samples': 7903744, 'steps': 15436, 'loss/train': 1.881616473197937}
-03/04/2022 07:35:58 - INFO - codeparrot_training - Step 15437: {'lr': 0.000489899458671432, 'samples': 7904256, 'steps': 15437, 'loss/train': 2.014139413833618}
-03/04/2022 07:35:59 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 07:36:03 - INFO - codeparrot_training - Step 15438: {'lr': 0.0004898979654312034, 'samples': 7904768, 'steps': 15438, 'loss/train': 2.6880035400390625}
-03/04/2022 07:36:06 - INFO - codeparrot_training - Step 15439: {'lr': 0.0004898964720828804, 'samples': 7905280, 'steps': 15439, 'loss/train': 1.6997483968734741}
-03/04/2022 07:36:08 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 07:36:12 - INFO - codeparrot_training - Step 15440: {'lr': 0.0004898949786264638, 'samples': 7905792, 'steps': 15440, 'loss/train': 0.6220483779907227}
-03/04/2022 07:36:15 - INFO - codeparrot_training - Step 15441: {'lr': 0.0004898934850619542, 'samples': 7906304, 'steps': 15441, 'loss/train': 2.204728603363037}
-03/04/2022 07:36:16 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/04/2022 07:36:20 - INFO - codeparrot_training - Step 15442: {'lr': 0.0004898919913893522, 'samples': 7906816, 'steps': 15442, 'loss/train': 1.9425610303878784}
-03/04/2022 07:36:23 - INFO - codeparrot_training - Step 15443: {'lr': 0.0004898904976086588, 'samples': 7907328, 'steps': 15443, 'loss/train': 1.3312140703201294}
-03/04/2022 07:36:24 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/04/2022 07:36:29 - INFO - codeparrot_training - Step 15444: {'lr': 0.0004898890037198743, 'samples': 7907840, 'steps': 15444, 'loss/train': 2.002432107925415}
-03/04/2022 07:36:32 - INFO - codeparrot_training - Step 15445: {'lr': 0.0004898875097229995, 'samples': 7908352, 'steps': 15445, 'loss/train': 2.4981448650360107}
-03/04/2022 07:36:33 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 07:36:37 - INFO - codeparrot_training - Step 15446: {'lr': 0.0004898860156180351, 'samples': 7908864, 'steps': 15446, 'loss/train': 2.014364004135132}
-03/04/2022 07:36:40 - INFO - codeparrot_training - Step 15447: {'lr': 0.0004898845214049818, 'samples': 7909376, 'steps': 15447, 'loss/train': 1.142008662223816}
-03/04/2022 07:36:41 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 07:36:45 - INFO - codeparrot_training - Step 15448: {'lr': 0.0004898830270838403, 'samples': 7909888, 'steps': 15448, 'loss/train': 1.0710009336471558}
-03/04/2022 07:36:49 - INFO - codeparrot_training - Step 15449: {'lr': 0.0004898815326546111, 'samples': 7910400, 'steps': 15449, 'loss/train': 2.6670305728912354}
-03/04/2022 07:36:50 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/04/2022 07:36:54 - INFO - codeparrot_training - Step 15450: {'lr': 0.0004898800381172951, 'samples': 7910912, 'steps': 15450, 'loss/train': 1.7864562273025513}
-03/04/2022 07:36:57 - INFO - codeparrot_training - Step 15451: {'lr': 0.0004898785434718927, 'samples': 7911424, 'steps': 15451, 'loss/train': 1.459734320640564}
-03/04/2022 07:36:58 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/04/2022 07:37:02 - INFO - codeparrot_training - Step 15452: {'lr': 0.0004898770487184047, 'samples': 7911936, 'steps': 15452, 'loss/train': 1.8777679204940796}
-03/04/2022 07:37:05 - INFO - codeparrot_training - Step 15453: {'lr': 0.000489875553856832, 'samples': 7912448, 'steps': 15453, 'loss/train': 2.6495299339294434}
-03/04/2022 07:37:07 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 07:37:11 - INFO - codeparrot_training - Step 15454: {'lr': 0.000489874058887175, 'samples': 7912960, 'steps': 15454, 'loss/train': 0.30565372109413147}
-03/04/2022 07:37:14 - INFO - codeparrot_training - Step 15455: {'lr': 0.0004898725638094345, 'samples': 7913472, 'steps': 15455, 'loss/train': 2.2005231380462646}
-03/04/2022 07:37:15 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 07:37:19 - INFO - codeparrot_training - Step 15456: {'lr': 0.0004898710686236109, 'samples': 7913984, 'steps': 15456, 'loss/train': 2.09761381149292}
-03/04/2022 07:37:22 - INFO - codeparrot_training - Step 15457: {'lr': 0.0004898695733297054, 'samples': 7914496, 'steps': 15457, 'loss/train': 1.9442355632781982}
-03/04/2022 07:37:23 - INFO - codeparrot_training - Skipping example with length 158 (seq_length=1024)
-03/04/2022 07:37:28 - INFO - codeparrot_training - Step 15458: {'lr': 0.0004898680779277182, 'samples': 7915008, 'steps': 15458, 'loss/train': 2.0893824100494385}
-03/04/2022 07:37:31 - INFO - codeparrot_training - Step 15459: {'lr': 0.0004898665824176502, 'samples': 7915520, 'steps': 15459, 'loss/train': 2.2771191596984863}
-03/04/2022 07:37:31 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/04/2022 07:37:36 - INFO - codeparrot_training - Step 15460: {'lr': 0.000489865086799502, 'samples': 7916032, 'steps': 15460, 'loss/train': 2.5538787841796875}
-03/04/2022 07:37:39 - INFO - codeparrot_training - Step 15461: {'lr': 0.0004898635910732743, 'samples': 7916544, 'steps': 15461, 'loss/train': 2.42826247215271}
-03/04/2022 07:37:40 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 07:37:44 - INFO - codeparrot_training - Step 15462: {'lr': 0.0004898620952389677, 'samples': 7917056, 'steps': 15462, 'loss/train': 1.670270562171936}
-03/04/2022 07:37:48 - INFO - codeparrot_training - Step 15463: {'lr': 0.000489860599296583, 'samples': 7917568, 'steps': 15463, 'loss/train': 2.1151483058929443}
-03/04/2022 07:37:49 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/04/2022 07:37:53 - INFO - codeparrot_training - Step 15464: {'lr': 0.0004898591032461208, 'samples': 7918080, 'steps': 15464, 'loss/train': 1.593345046043396}
-03/04/2022 07:37:56 - INFO - codeparrot_training - Step 15465: {'lr': 0.0004898576070875818, 'samples': 7918592, 'steps': 15465, 'loss/train': 2.0916292667388916}
-03/04/2022 07:37:57 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 07:38:01 - INFO - codeparrot_training - Step 15466: {'lr': 0.0004898561108209667, 'samples': 7919104, 'steps': 15466, 'loss/train': 1.96178138256073}
-03/04/2022 07:38:05 - INFO - codeparrot_training - Step 15467: {'lr': 0.0004898546144462762, 'samples': 7919616, 'steps': 15467, 'loss/train': 2.278851270675659}
-03/04/2022 07:38:06 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/04/2022 07:38:10 - INFO - codeparrot_training - Step 15468: {'lr': 0.0004898531179635108, 'samples': 7920128, 'steps': 15468, 'loss/train': 2.491122245788574}
-03/04/2022 07:38:13 - INFO - codeparrot_training - Step 15469: {'lr': 0.0004898516213726712, 'samples': 7920640, 'steps': 15469, 'loss/train': 1.9041359424591064}
-03/04/2022 07:38:15 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/04/2022 07:38:18 - INFO - codeparrot_training - Step 15470: {'lr': 0.0004898501246737583, 'samples': 7921152, 'steps': 15470, 'loss/train': 2.9109950065612793}
-03/04/2022 07:38:21 - INFO - codeparrot_training - Step 15471: {'lr': 0.0004898486278667725, 'samples': 7921664, 'steps': 15471, 'loss/train': 1.9082738161087036}
-03/04/2022 07:38:23 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 07:38:27 - INFO - codeparrot_training - Step 15472: {'lr': 0.0004898471309517148, 'samples': 7922176, 'steps': 15472, 'loss/train': 1.2683079242706299}
-03/04/2022 07:38:30 - INFO - codeparrot_training - Step 15473: {'lr': 0.0004898456339285857, 'samples': 7922688, 'steps': 15473, 'loss/train': 2.021400213241577}
-03/04/2022 07:38:31 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/04/2022 07:38:35 - INFO - codeparrot_training - Step 15474: {'lr': 0.0004898441367973856, 'samples': 7923200, 'steps': 15474, 'loss/train': 1.680795431137085}
-03/04/2022 07:38:38 - INFO - codeparrot_training - Step 15475: {'lr': 0.0004898426395581156, 'samples': 7923712, 'steps': 15475, 'loss/train': 1.2884926795959473}
-03/04/2022 07:38:39 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 07:38:44 - INFO - codeparrot_training - Step 15476: {'lr': 0.0004898411422107762, 'samples': 7924224, 'steps': 15476, 'loss/train': 1.8410600423812866}
-03/04/2022 07:38:47 - INFO - codeparrot_training - Step 15477: {'lr': 0.0004898396447553681, 'samples': 7924736, 'steps': 15477, 'loss/train': 2.328235626220703}
-03/04/2022 07:38:48 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/04/2022 07:38:52 - INFO - codeparrot_training - Step 15478: {'lr': 0.000489838147191892, 'samples': 7925248, 'steps': 15478, 'loss/train': 1.4466079473495483}
-03/04/2022 07:38:55 - INFO - codeparrot_training - Step 15479: {'lr': 0.0004898366495203483, 'samples': 7925760, 'steps': 15479, 'loss/train': 2.0889716148376465}
-03/04/2022 07:38:56 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/04/2022 07:39:00 - INFO - codeparrot_training - Step 15480: {'lr': 0.0004898351517407381, 'samples': 7926272, 'steps': 15480, 'loss/train': 2.57910418510437}
-03/04/2022 07:39:04 - INFO - codeparrot_training - Step 15481: {'lr': 0.0004898336538530619, 'samples': 7926784, 'steps': 15481, 'loss/train': 0.9258764386177063}
-03/04/2022 07:39:04 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 07:39:09 - INFO - codeparrot_training - Step 15482: {'lr': 0.0004898321558573203, 'samples': 7927296, 'steps': 15482, 'loss/train': 1.7317770719528198}
-03/04/2022 07:39:12 - INFO - codeparrot_training - Step 15483: {'lr': 0.000489830657753514, 'samples': 7927808, 'steps': 15483, 'loss/train': 2.154567003250122}
-03/04/2022 07:39:13 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 07:39:17 - INFO - codeparrot_training - Step 15484: {'lr': 0.0004898291595416438, 'samples': 7928320, 'steps': 15484, 'loss/train': 1.4654713869094849}
-03/04/2022 07:39:20 - INFO - codeparrot_training - Step 15485: {'lr': 0.0004898276612217102, 'samples': 7928832, 'steps': 15485, 'loss/train': 2.106961727142334}
-03/04/2022 07:39:21 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/04/2022 07:39:26 - INFO - codeparrot_training - Step 15486: {'lr': 0.0004898261627937139, 'samples': 7929344, 'steps': 15486, 'loss/train': 1.6929203271865845}
-03/04/2022 07:39:29 - INFO - codeparrot_training - Step 15487: {'lr': 0.0004898246642576559, 'samples': 7929856, 'steps': 15487, 'loss/train': 0.299540251493454}
-03/04/2022 07:39:30 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 07:39:35 - INFO - codeparrot_training - Step 15488: {'lr': 0.0004898231656135362, 'samples': 7930368, 'steps': 15488, 'loss/train': 2.2357938289642334}
-03/04/2022 07:39:38 - INFO - codeparrot_training - Step 15489: {'lr': 0.0004898216668613562, 'samples': 7930880, 'steps': 15489, 'loss/train': 1.817880630493164}
-03/04/2022 07:39:39 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 07:39:43 - INFO - codeparrot_training - Step 15490: {'lr': 0.0004898201680011161, 'samples': 7931392, 'steps': 15490, 'loss/train': 1.8166682720184326}
-03/04/2022 07:39:46 - INFO - codeparrot_training - Step 15491: {'lr': 0.0004898186690328168, 'samples': 7931904, 'steps': 15491, 'loss/train': 1.9559389352798462}
-03/04/2022 07:39:48 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 07:39:51 - INFO - codeparrot_training - Step 15492: {'lr': 0.000489817169956459, 'samples': 7932416, 'steps': 15492, 'loss/train': 2.202038526535034}
-03/04/2022 07:39:55 - INFO - codeparrot_training - Step 15493: {'lr': 0.0004898156707720432, 'samples': 7932928, 'steps': 15493, 'loss/train': 0.9259675741195679}
-03/04/2022 07:39:56 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/04/2022 07:40:00 - INFO - codeparrot_training - Step 15494: {'lr': 0.0004898141714795701, 'samples': 7933440, 'steps': 15494, 'loss/train': 2.0608153343200684}
-03/04/2022 07:40:03 - INFO - codeparrot_training - Step 15495: {'lr': 0.0004898126720790405, 'samples': 7933952, 'steps': 15495, 'loss/train': 1.8343485593795776}
-03/04/2022 07:40:05 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/04/2022 07:40:08 - INFO - codeparrot_training - Step 15496: {'lr': 0.0004898111725704549, 'samples': 7934464, 'steps': 15496, 'loss/train': 2.832853078842163}
-03/04/2022 07:40:11 - INFO - codeparrot_training - Step 15497: {'lr': 0.0004898096729538142, 'samples': 7934976, 'steps': 15497, 'loss/train': 1.620359182357788}
-03/04/2022 07:40:13 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 07:40:17 - INFO - codeparrot_training - Step 15498: {'lr': 0.000489808173229119, 'samples': 7935488, 'steps': 15498, 'loss/train': 1.658172369003296}
-03/04/2022 07:40:20 - INFO - codeparrot_training - Step 15499: {'lr': 0.0004898066733963699, 'samples': 7936000, 'steps': 15499, 'loss/train': 0.7932114005088806}
-03/04/2022 07:40:21 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/04/2022 07:40:25 - INFO - codeparrot_training - Step 15500: {'lr': 0.0004898051734555676, 'samples': 7936512, 'steps': 15500, 'loss/train': 1.9625887870788574}
-03/04/2022 07:40:28 - INFO - codeparrot_training - Step 15501: {'lr': 0.0004898036734067127, 'samples': 7937024, 'steps': 15501, 'loss/train': 1.7892743349075317}
-03/04/2022 07:40:30 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/04/2022 07:40:33 - INFO - codeparrot_training - Step 15502: {'lr': 0.000489802173249806, 'samples': 7937536, 'steps': 15502, 'loss/train': 1.9243348836898804}
-03/04/2022 07:40:37 - INFO - codeparrot_training - Step 15503: {'lr': 0.0004898006729848482, 'samples': 7938048, 'steps': 15503, 'loss/train': 1.8306759595870972}
-03/04/2022 07:40:38 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/04/2022 07:40:42 - INFO - codeparrot_training - Step 15504: {'lr': 0.0004897991726118399, 'samples': 7938560, 'steps': 15504, 'loss/train': 2.0525686740875244}
-03/04/2022 07:40:45 - INFO - codeparrot_training - Step 15505: {'lr': 0.0004897976721307818, 'samples': 7939072, 'steps': 15505, 'loss/train': 1.6747798919677734}
-03/04/2022 07:40:47 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 07:40:51 - INFO - codeparrot_training - Step 15506: {'lr': 0.0004897961715416746, 'samples': 7939584, 'steps': 15506, 'loss/train': 1.4539427757263184}
-03/04/2022 07:40:54 - INFO - codeparrot_training - Step 15507: {'lr': 0.0004897946708445189, 'samples': 7940096, 'steps': 15507, 'loss/train': 1.5788847208023071}
-03/04/2022 07:40:57 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/04/2022 07:41:00 - INFO - codeparrot_training - Step 15508: {'lr': 0.0004897931700393154, 'samples': 7940608, 'steps': 15508, 'loss/train': 2.2925736904144287}
-03/04/2022 07:41:03 - INFO - codeparrot_training - Step 15509: {'lr': 0.0004897916691260648, 'samples': 7941120, 'steps': 15509, 'loss/train': 1.3521226644515991}
-03/04/2022 07:41:06 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/04/2022 07:41:08 - INFO - codeparrot_training - Step 15510: {'lr': 0.0004897901681047679, 'samples': 7941632, 'steps': 15510, 'loss/train': 2.5287580490112305}
-03/04/2022 07:41:12 - INFO - codeparrot_training - Step 15511: {'lr': 0.0004897886669754251, 'samples': 7942144, 'steps': 15511, 'loss/train': 0.21695557236671448}
-03/04/2022 07:41:14 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 07:41:17 - INFO - codeparrot_training - Step 15512: {'lr': 0.0004897871657380373, 'samples': 7942656, 'steps': 15512, 'loss/train': 1.4420907497406006}
-03/04/2022 07:41:20 - INFO - codeparrot_training - Step 15513: {'lr': 0.0004897856643926051, 'samples': 7943168, 'steps': 15513, 'loss/train': 1.1334095001220703}
-03/04/2022 07:41:23 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 07:41:25 - INFO - codeparrot_training - Step 15514: {'lr': 0.0004897841629391291, 'samples': 7943680, 'steps': 15514, 'loss/train': 1.4499120712280273}
-03/04/2022 07:41:29 - INFO - codeparrot_training - Step 15515: {'lr': 0.0004897826613776101, 'samples': 7944192, 'steps': 15515, 'loss/train': 2.596832513809204}
-03/04/2022 07:41:31 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/04/2022 07:41:34 - INFO - codeparrot_training - Step 15516: {'lr': 0.0004897811597080488, 'samples': 7944704, 'steps': 15516, 'loss/train': 2.5342442989349365}
-03/04/2022 07:41:37 - INFO - codeparrot_training - Step 15517: {'lr': 0.0004897796579304458, 'samples': 7945216, 'steps': 15517, 'loss/train': 1.6077481508255005}
-03/04/2022 07:41:39 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 07:41:42 - INFO - codeparrot_training - Step 15518: {'lr': 0.0004897781560448017, 'samples': 7945728, 'steps': 15518, 'loss/train': 1.6803473234176636}
-03/04/2022 07:41:45 - INFO - codeparrot_training - Step 15519: {'lr': 0.0004897766540511173, 'samples': 7946240, 'steps': 15519, 'loss/train': 2.1792116165161133}
-03/04/2022 07:41:48 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 07:41:51 - INFO - codeparrot_training - Step 15520: {'lr': 0.0004897751519493933, 'samples': 7946752, 'steps': 15520, 'loss/train': 2.3816514015197754}
-03/04/2022 07:41:54 - INFO - codeparrot_training - Step 15521: {'lr': 0.0004897736497396303, 'samples': 7947264, 'steps': 15521, 'loss/train': 2.8611607551574707}
-03/04/2022 07:41:56 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/04/2022 07:41:59 - INFO - codeparrot_training - Step 15522: {'lr': 0.000489772147421829, 'samples': 7947776, 'steps': 15522, 'loss/train': 1.8840316534042358}
-03/04/2022 07:42:02 - INFO - codeparrot_training - Step 15523: {'lr': 0.0004897706449959899, 'samples': 7948288, 'steps': 15523, 'loss/train': 1.8905023336410522}
-03/04/2022 07:42:05 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/04/2022 07:42:08 - INFO - codeparrot_training - Step 15524: {'lr': 0.000489769142462114, 'samples': 7948800, 'steps': 15524, 'loss/train': 1.2950785160064697}
-03/04/2022 07:42:11 - INFO - codeparrot_training - Step 15525: {'lr': 0.0004897676398202018, 'samples': 7949312, 'steps': 15525, 'loss/train': 2.2493841648101807}
-03/04/2022 07:42:13 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/04/2022 07:42:16 - INFO - codeparrot_training - Step 15526: {'lr': 0.000489766137070254, 'samples': 7949824, 'steps': 15526, 'loss/train': 2.226500988006592}
-03/04/2022 07:42:19 - INFO - codeparrot_training - Step 15527: {'lr': 0.0004897646342122713, 'samples': 7950336, 'steps': 15527, 'loss/train': 1.69699227809906}
-03/04/2022 07:42:21 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/04/2022 07:42:25 - INFO - codeparrot_training - Step 15528: {'lr': 0.0004897631312462544, 'samples': 7950848, 'steps': 15528, 'loss/train': 1.94154953956604}
-03/04/2022 07:42:28 - INFO - codeparrot_training - Step 15529: {'lr': 0.0004897616281722038, 'samples': 7951360, 'steps': 15529, 'loss/train': 1.7297444343566895}
-03/04/2022 07:42:31 - INFO - codeparrot_training - Step 15530: {'lr': 0.0004897601249901204, 'samples': 7951872, 'steps': 15530, 'loss/train': 2.2708733081817627}
-03/04/2022 07:42:32 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 07:42:36 - INFO - codeparrot_training - Step 15531: {'lr': 0.0004897586217000047, 'samples': 7952384, 'steps': 15531, 'loss/train': 1.6525484323501587}
-03/04/2022 07:42:40 - INFO - codeparrot_training - Step 15532: {'lr': 0.0004897571183018576, 'samples': 7952896, 'steps': 15532, 'loss/train': 1.5343036651611328}
-03/04/2022 07:42:40 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/04/2022 07:42:45 - INFO - codeparrot_training - Step 15533: {'lr': 0.0004897556147956796, 'samples': 7953408, 'steps': 15533, 'loss/train': 2.1478469371795654}
-03/04/2022 07:42:48 - INFO - codeparrot_training - Step 15534: {'lr': 0.0004897541111814714, 'samples': 7953920, 'steps': 15534, 'loss/train': 1.7728590965270996}
-03/04/2022 07:42:49 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/04/2022 07:42:53 - INFO - codeparrot_training - Step 15535: {'lr': 0.0004897526074592337, 'samples': 7954432, 'steps': 15535, 'loss/train': 0.5322246551513672}
-03/04/2022 07:42:56 - INFO - codeparrot_training - Step 15536: {'lr': 0.0004897511036289671, 'samples': 7954944, 'steps': 15536, 'loss/train': 2.214263677597046}
-03/04/2022 07:42:57 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/04/2022 07:43:02 - INFO - codeparrot_training - Step 15537: {'lr': 0.0004897495996906725, 'samples': 7955456, 'steps': 15537, 'loss/train': 1.684836983680725}
-03/04/2022 07:43:05 - INFO - codeparrot_training - Step 15538: {'lr': 0.0004897480956443503, 'samples': 7955968, 'steps': 15538, 'loss/train': 2.200009822845459}
-03/04/2022 07:43:06 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 07:43:10 - INFO - codeparrot_training - Step 15539: {'lr': 0.0004897465914900013, 'samples': 7956480, 'steps': 15539, 'loss/train': 1.9549001455307007}
-03/04/2022 07:43:13 - INFO - codeparrot_training - Step 15540: {'lr': 0.0004897450872276263, 'samples': 7956992, 'steps': 15540, 'loss/train': 1.8357181549072266}
-03/04/2022 07:43:14 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/04/2022 07:43:18 - INFO - codeparrot_training - Step 15541: {'lr': 0.0004897435828572258, 'samples': 7957504, 'steps': 15541, 'loss/train': 2.2722294330596924}
-03/04/2022 07:43:22 - INFO - codeparrot_training - Step 15542: {'lr': 0.0004897420783788006, 'samples': 7958016, 'steps': 15542, 'loss/train': 1.7276039123535156}
-03/04/2022 07:43:22 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 07:43:27 - INFO - codeparrot_training - Step 15543: {'lr': 0.0004897405737923511, 'samples': 7958528, 'steps': 15543, 'loss/train': 1.77358078956604}
-03/04/2022 07:43:30 - INFO - codeparrot_training - Step 15544: {'lr': 0.0004897390690978785, 'samples': 7959040, 'steps': 15544, 'loss/train': 2.437380075454712}
-03/04/2022 07:43:31 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 07:43:35 - INFO - codeparrot_training - Step 15545: {'lr': 0.000489737564295383, 'samples': 7959552, 'steps': 15545, 'loss/train': 1.2213376760482788}
-03/04/2022 07:43:38 - INFO - codeparrot_training - Step 15546: {'lr': 0.0004897360593848655, 'samples': 7960064, 'steps': 15546, 'loss/train': 0.9281087517738342}
-03/04/2022 07:43:39 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 07:43:44 - INFO - codeparrot_training - Step 15547: {'lr': 0.0004897345543663266, 'samples': 7960576, 'steps': 15547, 'loss/train': 1.7189769744873047}
-03/04/2022 07:43:47 - INFO - codeparrot_training - Step 15548: {'lr': 0.000489733049239767, 'samples': 7961088, 'steps': 15548, 'loss/train': 2.868016004562378}
-03/04/2022 07:43:49 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 07:43:53 - INFO - codeparrot_training - Step 15549: {'lr': 0.0004897315440051874, 'samples': 7961600, 'steps': 15549, 'loss/train': 2.4554531574249268}
-03/04/2022 07:43:56 - INFO - codeparrot_training - Step 15550: {'lr': 0.0004897300386625885, 'samples': 7962112, 'steps': 15550, 'loss/train': 0.8456427454948425}
-03/04/2022 07:43:57 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 07:44:01 - INFO - codeparrot_training - Step 15551: {'lr': 0.0004897285332119709, 'samples': 7962624, 'steps': 15551, 'loss/train': 1.7276837825775146}
-03/04/2022 07:44:04 - INFO - codeparrot_training - Step 15552: {'lr': 0.0004897270276533355, 'samples': 7963136, 'steps': 15552, 'loss/train': 3.0288171768188477}
-03/04/2022 07:44:07 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/04/2022 07:44:10 - INFO - codeparrot_training - Step 15553: {'lr': 0.0004897255219866825, 'samples': 7963648, 'steps': 15553, 'loss/train': 1.9529637098312378}
-03/04/2022 07:44:13 - INFO - codeparrot_training - Step 15554: {'lr': 0.000489724016212013, 'samples': 7964160, 'steps': 15554, 'loss/train': 1.773878812789917}
-03/04/2022 07:44:15 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/04/2022 07:44:18 - INFO - codeparrot_training - Step 15555: {'lr': 0.0004897225103293277, 'samples': 7964672, 'steps': 15555, 'loss/train': 2.08489727973938}
-03/04/2022 07:44:21 - INFO - codeparrot_training - Step 15556: {'lr': 0.0004897210043386269, 'samples': 7965184, 'steps': 15556, 'loss/train': 2.656689405441284}
-03/04/2022 07:44:24 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/04/2022 07:44:27 - INFO - codeparrot_training - Step 15557: {'lr': 0.0004897194982399117, 'samples': 7965696, 'steps': 15557, 'loss/train': 2.133646011352539}
-03/04/2022 07:44:30 - INFO - codeparrot_training - Step 15558: {'lr': 0.0004897179920331826, 'samples': 7966208, 'steps': 15558, 'loss/train': 2.2503154277801514}
-03/04/2022 07:44:32 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/04/2022 07:44:35 - INFO - codeparrot_training - Step 15559: {'lr': 0.0004897164857184401, 'samples': 7966720, 'steps': 15559, 'loss/train': 3.2825610637664795}
-03/04/2022 07:44:38 - INFO - codeparrot_training - Step 15560: {'lr': 0.0004897149792956852, 'samples': 7967232, 'steps': 15560, 'loss/train': 1.1401220560073853}
-03/04/2022 07:44:41 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/04/2022 07:44:43 - INFO - codeparrot_training - Step 15561: {'lr': 0.0004897134727649184, 'samples': 7967744, 'steps': 15561, 'loss/train': 2.068169355392456}
-03/04/2022 07:44:47 - INFO - codeparrot_training - Step 15562: {'lr': 0.0004897119661261403, 'samples': 7968256, 'steps': 15562, 'loss/train': 2.204420328140259}
-03/04/2022 07:44:49 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 07:44:52 - INFO - codeparrot_training - Step 15563: {'lr': 0.0004897104593793518, 'samples': 7968768, 'steps': 15563, 'loss/train': 2.25547456741333}
-03/04/2022 07:44:55 - INFO - codeparrot_training - Step 15564: {'lr': 0.0004897089525245535, 'samples': 7969280, 'steps': 15564, 'loss/train': 1.3469637632369995}
-03/04/2022 07:44:58 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 07:45:00 - INFO - codeparrot_training - Step 15565: {'lr': 0.000489707445561746, 'samples': 7969792, 'steps': 15565, 'loss/train': 2.262488603591919}
-03/04/2022 07:45:04 - INFO - codeparrot_training - Step 15566: {'lr': 0.0004897059384909299, 'samples': 7970304, 'steps': 15566, 'loss/train': 2.519568920135498}
-03/04/2022 07:45:06 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/04/2022 07:45:09 - INFO - codeparrot_training - Step 15567: {'lr': 0.0004897044313121061, 'samples': 7970816, 'steps': 15567, 'loss/train': 2.0533998012542725}
-03/04/2022 07:45:12 - INFO - codeparrot_training - Step 15568: {'lr': 0.0004897029240252753, 'samples': 7971328, 'steps': 15568, 'loss/train': 2.0569255352020264}
-03/04/2022 07:45:14 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 07:45:17 - INFO - codeparrot_training - Step 15569: {'lr': 0.000489701416630438, 'samples': 7971840, 'steps': 15569, 'loss/train': 1.7303447723388672}
-03/04/2022 07:45:21 - INFO - codeparrot_training - Step 15570: {'lr': 0.0004896999091275948, 'samples': 7972352, 'steps': 15570, 'loss/train': 0.8770133256912231}
-03/04/2022 07:45:23 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/04/2022 07:45:26 - INFO - codeparrot_training - Step 15571: {'lr': 0.0004896984015167466, 'samples': 7972864, 'steps': 15571, 'loss/train': 0.6278535723686218}
-03/04/2022 07:45:29 - INFO - codeparrot_training - Step 15572: {'lr': 0.0004896968937978941, 'samples': 7973376, 'steps': 15572, 'loss/train': 1.5002636909484863}
-03/04/2022 07:45:32 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/04/2022 07:45:34 - INFO - codeparrot_training - Step 15573: {'lr': 0.0004896953859710379, 'samples': 7973888, 'steps': 15573, 'loss/train': 1.0698113441467285}
-03/04/2022 07:45:38 - INFO - codeparrot_training - Step 15574: {'lr': 0.0004896938780361784, 'samples': 7974400, 'steps': 15574, 'loss/train': 1.5110538005828857}
-03/04/2022 07:45:40 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 07:45:43 - INFO - codeparrot_training - Step 15575: {'lr': 0.0004896923699933167, 'samples': 7974912, 'steps': 15575, 'loss/train': 1.6775097846984863}
-03/04/2022 07:45:46 - INFO - codeparrot_training - Step 15576: {'lr': 0.0004896908618424533, 'samples': 7975424, 'steps': 15576, 'loss/train': 1.170007586479187}
-03/04/2022 07:45:48 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/04/2022 07:45:51 - INFO - codeparrot_training - Step 15577: {'lr': 0.0004896893535835889, 'samples': 7975936, 'steps': 15577, 'loss/train': 1.8936434984207153}
-03/04/2022 07:45:54 - INFO - codeparrot_training - Step 15578: {'lr': 0.0004896878452167241, 'samples': 7976448, 'steps': 15578, 'loss/train': 2.204287528991699}
-03/04/2022 07:45:57 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/04/2022 07:46:00 - INFO - codeparrot_training - Step 15579: {'lr': 0.0004896863367418598, 'samples': 7976960, 'steps': 15579, 'loss/train': 1.9621821641921997}
-03/04/2022 07:46:03 - INFO - codeparrot_training - Step 15580: {'lr': 0.0004896848281589966, 'samples': 7977472, 'steps': 15580, 'loss/train': 2.264508008956909}
-03/04/2022 07:46:06 - INFO - codeparrot_training - Step 15581: {'lr': 0.0004896833194681349, 'samples': 7977984, 'steps': 15581, 'loss/train': 2.0917906761169434}
-03/04/2022 07:46:07 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 07:46:11 - INFO - codeparrot_training - Step 15582: {'lr': 0.0004896818106692757, 'samples': 7978496, 'steps': 15582, 'loss/train': 1.7354539632797241}
-03/04/2022 07:46:15 - INFO - codeparrot_training - Step 15583: {'lr': 0.0004896803017624196, 'samples': 7979008, 'steps': 15583, 'loss/train': 1.9600088596343994}
-03/04/2022 07:46:15 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 07:46:20 - INFO - codeparrot_training - Step 15584: {'lr': 0.0004896787927475671, 'samples': 7979520, 'steps': 15584, 'loss/train': 1.9290682077407837}
-03/04/2022 07:46:23 - INFO - codeparrot_training - Step 15585: {'lr': 0.0004896772836247192, 'samples': 7980032, 'steps': 15585, 'loss/train': 2.10720157623291}
-03/04/2022 07:46:25 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 07:46:29 - INFO - codeparrot_training - Step 15586: {'lr': 0.0004896757743938764, 'samples': 7980544, 'steps': 15586, 'loss/train': 1.5047657489776611}
-03/04/2022 07:46:32 - INFO - codeparrot_training - Step 15587: {'lr': 0.0004896742650550393, 'samples': 7981056, 'steps': 15587, 'loss/train': 1.5336370468139648}
-03/04/2022 07:46:34 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 07:46:37 - INFO - codeparrot_training - Step 15588: {'lr': 0.0004896727556082086, 'samples': 7981568, 'steps': 15588, 'loss/train': 1.5767669677734375}
-03/04/2022 07:46:40 - INFO - codeparrot_training - Step 15589: {'lr': 0.0004896712460533854, 'samples': 7982080, 'steps': 15589, 'loss/train': 1.7325730323791504}
-03/04/2022 07:46:43 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 07:46:46 - INFO - codeparrot_training - Step 15590: {'lr': 0.0004896697363905697, 'samples': 7982592, 'steps': 15590, 'loss/train': 1.9023256301879883}
-03/04/2022 07:46:49 - INFO - codeparrot_training - Step 15591: {'lr': 0.0004896682266197626, 'samples': 7983104, 'steps': 15591, 'loss/train': 1.7700974941253662}
-03/04/2022 07:46:51 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/04/2022 07:46:54 - INFO - codeparrot_training - Step 15592: {'lr': 0.0004896667167409648, 'samples': 7983616, 'steps': 15592, 'loss/train': 1.6174067258834839}
-03/04/2022 07:46:57 - INFO - codeparrot_training - Step 15593: {'lr': 0.0004896652067541767, 'samples': 7984128, 'steps': 15593, 'loss/train': 1.9236781597137451}
-03/04/2022 07:47:03 - INFO - codeparrot_training - Step 15594: {'lr': 0.0004896636966593993, 'samples': 7984640, 'steps': 15594, 'loss/train': 1.7120556831359863}
-03/04/2022 07:47:06 - INFO - codeparrot_training - Step 15595: {'lr': 0.0004896621864566331, 'samples': 7985152, 'steps': 15595, 'loss/train': 2.080111265182495}
-03/04/2022 07:47:09 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 07:47:11 - INFO - codeparrot_training - Step 15596: {'lr': 0.0004896606761458788, 'samples': 7985664, 'steps': 15596, 'loss/train': 2.073698043823242}
-03/04/2022 07:47:14 - INFO - codeparrot_training - Step 15597: {'lr': 0.0004896591657271371, 'samples': 7986176, 'steps': 15597, 'loss/train': 2.1522998809814453}
-03/04/2022 07:47:17 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/04/2022 07:47:19 - INFO - codeparrot_training - Step 15598: {'lr': 0.0004896576552004087, 'samples': 7986688, 'steps': 15598, 'loss/train': 2.25711727142334}
-03/04/2022 07:47:23 - INFO - codeparrot_training - Step 15599: {'lr': 0.0004896561445656943, 'samples': 7987200, 'steps': 15599, 'loss/train': 1.7083323001861572}
-03/04/2022 07:47:25 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/04/2022 07:47:28 - INFO - codeparrot_training - Step 15600: {'lr': 0.0004896546338229945, 'samples': 7987712, 'steps': 15600, 'loss/train': 1.8336783647537231}
-03/04/2022 07:47:31 - INFO - codeparrot_training - Step 15601: {'lr': 0.00048965312297231, 'samples': 7988224, 'steps': 15601, 'loss/train': 2.040998697280884}
-03/04/2022 07:47:34 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 07:47:37 - INFO - codeparrot_training - Step 15602: {'lr': 0.0004896516120136415, 'samples': 7988736, 'steps': 15602, 'loss/train': 1.830528974533081}
-03/04/2022 07:47:40 - INFO - codeparrot_training - Step 15603: {'lr': 0.0004896501009469896, 'samples': 7989248, 'steps': 15603, 'loss/train': 3.5036025047302246}
-03/04/2022 07:47:43 - INFO - codeparrot_training - Step 15604: {'lr': 0.0004896485897723552, 'samples': 7989760, 'steps': 15604, 'loss/train': 1.9894554615020752}
-03/04/2022 07:47:44 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/04/2022 07:47:48 - INFO - codeparrot_training - Step 15605: {'lr': 0.0004896470784897388, 'samples': 7990272, 'steps': 15605, 'loss/train': 1.2023062705993652}
-03/04/2022 07:47:52 - INFO - codeparrot_training - Step 15606: {'lr': 0.0004896455670991411, 'samples': 7990784, 'steps': 15606, 'loss/train': 1.3464702367782593}
-03/04/2022 07:47:52 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/04/2022 07:47:57 - INFO - codeparrot_training - Step 15607: {'lr': 0.0004896440556005628, 'samples': 7991296, 'steps': 15607, 'loss/train': 6.8068528175354}
-03/04/2022 07:48:00 - INFO - codeparrot_training - Step 15608: {'lr': 0.0004896425439940047, 'samples': 7991808, 'steps': 15608, 'loss/train': 2.566437244415283}
-03/04/2022 07:48:02 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 07:48:05 - INFO - codeparrot_training - Step 15609: {'lr': 0.0004896410322794673, 'samples': 7992320, 'steps': 15609, 'loss/train': 1.656408667564392}
-03/04/2022 07:48:08 - INFO - codeparrot_training - Step 15610: {'lr': 0.0004896395204569512, 'samples': 7992832, 'steps': 15610, 'loss/train': 2.533376932144165}
-03/04/2022 07:48:10 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/04/2022 07:48:14 - INFO - codeparrot_training - Step 15611: {'lr': 0.0004896380085264573, 'samples': 7993344, 'steps': 15611, 'loss/train': 1.599376916885376}
-03/04/2022 07:48:17 - INFO - codeparrot_training - Step 15612: {'lr': 0.0004896364964879864, 'samples': 7993856, 'steps': 15612, 'loss/train': 1.5482906103134155}
-03/04/2022 07:48:18 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 07:48:22 - INFO - codeparrot_training - Step 15613: {'lr': 0.0004896349843415389, 'samples': 7994368, 'steps': 15613, 'loss/train': 1.8338699340820312}
-03/04/2022 07:48:25 - INFO - codeparrot_training - Step 15614: {'lr': 0.0004896334720871156, 'samples': 7994880, 'steps': 15614, 'loss/train': 2.9976632595062256}
-03/04/2022 07:48:27 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/04/2022 07:48:30 - INFO - codeparrot_training - Step 15615: {'lr': 0.0004896319597247169, 'samples': 7995392, 'steps': 15615, 'loss/train': 1.7623733282089233}
-03/04/2022 07:48:34 - INFO - codeparrot_training - Step 15616: {'lr': 0.0004896304472543439, 'samples': 7995904, 'steps': 15616, 'loss/train': 2.2343811988830566}
-03/04/2022 07:48:35 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 07:48:39 - INFO - codeparrot_training - Step 15617: {'lr': 0.0004896289346759973, 'samples': 7996416, 'steps': 15617, 'loss/train': 1.7282114028930664}
-03/04/2022 07:48:42 - INFO - codeparrot_training - Step 15618: {'lr': 0.0004896274219896773, 'samples': 7996928, 'steps': 15618, 'loss/train': 3.023613214492798}
-03/04/2022 07:48:44 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/04/2022 07:48:47 - INFO - codeparrot_training - Step 15619: {'lr': 0.000489625909195385, 'samples': 7997440, 'steps': 15619, 'loss/train': 2.0036978721618652}
-03/04/2022 07:48:51 - INFO - codeparrot_training - Step 15620: {'lr': 0.0004896243962931211, 'samples': 7997952, 'steps': 15620, 'loss/train': 2.3277180194854736}
-03/04/2022 07:48:52 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 07:48:56 - INFO - codeparrot_training - Step 15621: {'lr': 0.0004896228832828861, 'samples': 7998464, 'steps': 15621, 'loss/train': 2.0538904666900635}
-03/04/2022 07:48:59 - INFO - codeparrot_training - Step 15622: {'lr': 0.0004896213701646806, 'samples': 7998976, 'steps': 15622, 'loss/train': 1.7036488056182861}
-03/04/2022 07:49:00 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/04/2022 07:49:04 - INFO - codeparrot_training - Step 15623: {'lr': 0.0004896198569385055, 'samples': 7999488, 'steps': 15623, 'loss/train': 1.2380073070526123}
-03/04/2022 07:49:08 - INFO - codeparrot_training - Step 15624: {'lr': 0.0004896183436043613, 'samples': 8000000, 'steps': 15624, 'loss/train': 0.34877222776412964}
-03/04/2022 07:49:09 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 07:49:13 - INFO - codeparrot_training - Step 15625: {'lr': 0.0004896168301622488, 'samples': 8000512, 'steps': 15625, 'loss/train': 2.1807491779327393}
-03/04/2022 07:49:16 - INFO - codeparrot_training - Step 15626: {'lr': 0.0004896153166121688, 'samples': 8001024, 'steps': 15626, 'loss/train': 1.338117241859436}
-03/04/2022 07:49:17 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/04/2022 07:49:21 - INFO - codeparrot_training - Step 15627: {'lr': 0.0004896138029541217, 'samples': 8001536, 'steps': 15627, 'loss/train': 2.3398923873901367}
-03/04/2022 07:49:24 - INFO - codeparrot_training - Step 15628: {'lr': 0.0004896122891881083, 'samples': 8002048, 'steps': 15628, 'loss/train': 1.6659098863601685}
-03/04/2022 07:49:26 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/04/2022 07:49:29 - INFO - codeparrot_training - Step 15629: {'lr': 0.0004896107753141293, 'samples': 8002560, 'steps': 15629, 'loss/train': 0.8720934987068176}
-03/04/2022 07:49:33 - INFO - codeparrot_training - Step 15630: {'lr': 0.0004896092613321854, 'samples': 8003072, 'steps': 15630, 'loss/train': 1.6802074909210205}
-03/04/2022 07:49:34 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/04/2022 07:49:38 - INFO - codeparrot_training - Step 15631: {'lr': 0.0004896077472422773, 'samples': 8003584, 'steps': 15631, 'loss/train': 2.2948222160339355}
-03/04/2022 07:49:41 - INFO - codeparrot_training - Step 15632: {'lr': 0.0004896062330444057, 'samples': 8004096, 'steps': 15632, 'loss/train': 2.5763370990753174}
-03/04/2022 07:49:44 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 07:49:46 - INFO - codeparrot_training - Step 15633: {'lr': 0.0004896047187385711, 'samples': 8004608, 'steps': 15633, 'loss/train': 2.338783025741577}
-03/04/2022 07:49:50 - INFO - codeparrot_training - Step 15634: {'lr': 0.0004896032043247744, 'samples': 8005120, 'steps': 15634, 'loss/train': 2.18501877784729}
-03/04/2022 07:49:52 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/04/2022 07:49:55 - INFO - codeparrot_training - Step 15635: {'lr': 0.0004896016898030161, 'samples': 8005632, 'steps': 15635, 'loss/train': 1.0636016130447388}
-03/04/2022 07:49:58 - INFO - codeparrot_training - Step 15636: {'lr': 0.0004896001751732971, 'samples': 8006144, 'steps': 15636, 'loss/train': 1.1967425346374512}
-03/04/2022 07:50:01 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/04/2022 07:50:03 - INFO - codeparrot_training - Step 15637: {'lr': 0.0004895986604356178, 'samples': 8006656, 'steps': 15637, 'loss/train': 0.7863867878913879}
-03/04/2022 07:50:07 - INFO - codeparrot_training - Step 15638: {'lr': 0.0004895971455899792, 'samples': 8007168, 'steps': 15638, 'loss/train': 1.7963286638259888}
-03/04/2022 07:50:09 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 07:50:12 - INFO - codeparrot_training - Step 15639: {'lr': 0.0004895956306363818, 'samples': 8007680, 'steps': 15639, 'loss/train': 1.2012642621994019}
-03/04/2022 07:50:15 - INFO - codeparrot_training - Step 15640: {'lr': 0.0004895941155748263, 'samples': 8008192, 'steps': 15640, 'loss/train': 1.476168155670166}
-03/04/2022 07:50:17 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 07:50:20 - INFO - codeparrot_training - Step 15641: {'lr': 0.0004895926004053133, 'samples': 8008704, 'steps': 15641, 'loss/train': 1.5905035734176636}
-03/04/2022 07:50:23 - INFO - codeparrot_training - Step 15642: {'lr': 0.0004895910851278436, 'samples': 8009216, 'steps': 15642, 'loss/train': 1.6183972358703613}
-03/04/2022 07:50:25 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/04/2022 07:50:29 - INFO - codeparrot_training - Step 15643: {'lr': 0.0004895895697424179, 'samples': 8009728, 'steps': 15643, 'loss/train': 1.5347144603729248}
-03/04/2022 07:50:32 - INFO - codeparrot_training - Step 15644: {'lr': 0.0004895880542490369, 'samples': 8010240, 'steps': 15644, 'loss/train': 1.1086368560791016}
-03/04/2022 07:50:34 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/04/2022 07:50:37 - INFO - codeparrot_training - Step 15645: {'lr': 0.0004895865386477011, 'samples': 8010752, 'steps': 15645, 'loss/train': 0.9567164182662964}
-03/04/2022 07:50:40 - INFO - codeparrot_training - Step 15646: {'lr': 0.0004895850229384113, 'samples': 8011264, 'steps': 15646, 'loss/train': 2.146369457244873}
-03/04/2022 07:50:42 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/04/2022 07:50:46 - INFO - codeparrot_training - Step 15647: {'lr': 0.0004895835071211682, 'samples': 8011776, 'steps': 15647, 'loss/train': 1.4812657833099365}
-03/04/2022 07:50:49 - INFO - codeparrot_training - Step 15648: {'lr': 0.0004895819911959725, 'samples': 8012288, 'steps': 15648, 'loss/train': 2.689929246902466}
-03/04/2022 07:50:51 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/04/2022 07:50:54 - INFO - codeparrot_training - Step 15649: {'lr': 0.0004895804751628249, 'samples': 8012800, 'steps': 15649, 'loss/train': 2.492647409439087}
-03/04/2022 07:50:58 - INFO - codeparrot_training - Step 15650: {'lr': 0.0004895789590217259, 'samples': 8013312, 'steps': 15650, 'loss/train': 2.0614447593688965}
-03/04/2022 07:51:01 - INFO - codeparrot_training - Step 15651: {'lr': 0.0004895774427726764, 'samples': 8013824, 'steps': 15651, 'loss/train': 2.0234296321868896}
-03/04/2022 07:51:01 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/04/2022 07:51:06 - INFO - codeparrot_training - Step 15652: {'lr': 0.000489575926415677, 'samples': 8014336, 'steps': 15652, 'loss/train': 2.566713809967041}
-03/04/2022 07:51:09 - INFO - codeparrot_training - Step 15653: {'lr': 0.0004895744099507284, 'samples': 8014848, 'steps': 15653, 'loss/train': 1.3444267511367798}
-03/04/2022 07:51:10 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 07:51:14 - INFO - codeparrot_training - Step 15654: {'lr': 0.0004895728933778313, 'samples': 8015360, 'steps': 15654, 'loss/train': 1.556229591369629}
-03/04/2022 07:51:18 - INFO - codeparrot_training - Step 15655: {'lr': 0.0004895713766969863, 'samples': 8015872, 'steps': 15655, 'loss/train': 1.6726371049880981}
-03/04/2022 07:51:18 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 07:51:23 - INFO - codeparrot_training - Step 15656: {'lr': 0.0004895698599081942, 'samples': 8016384, 'steps': 15656, 'loss/train': 3.325284719467163}
-03/04/2022 07:51:26 - INFO - codeparrot_training - Step 15657: {'lr': 0.0004895683430114555, 'samples': 8016896, 'steps': 15657, 'loss/train': 2.0596282482147217}
-03/04/2022 07:51:26 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/04/2022 07:51:31 - INFO - codeparrot_training - Step 15658: {'lr': 0.0004895668260067711, 'samples': 8017408, 'steps': 15658, 'loss/train': 1.5727821588516235}
-03/04/2022 07:51:34 - INFO - codeparrot_training - Step 15659: {'lr': 0.0004895653088941416, 'samples': 8017920, 'steps': 15659, 'loss/train': 1.684291124343872}
-03/04/2022 07:51:35 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 07:51:40 - INFO - codeparrot_training - Step 15660: {'lr': 0.0004895637916735675, 'samples': 8018432, 'steps': 15660, 'loss/train': 1.999837875366211}
-03/04/2022 07:51:43 - INFO - codeparrot_training - Step 15661: {'lr': 0.0004895622743450497, 'samples': 8018944, 'steps': 15661, 'loss/train': 2.152054786682129}
-03/04/2022 07:51:43 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 07:51:48 - INFO - codeparrot_training - Step 15662: {'lr': 0.000489560756908589, 'samples': 8019456, 'steps': 15662, 'loss/train': 1.985174298286438}
-03/04/2022 07:51:51 - INFO - codeparrot_training - Step 15663: {'lr': 0.0004895592393641858, 'samples': 8019968, 'steps': 15663, 'loss/train': 2.06432843208313}
-03/04/2022 07:51:51 - INFO - codeparrot_training - Skipping example with length 86 (seq_length=1024)
-03/04/2022 07:51:57 - INFO - codeparrot_training - Step 15664: {'lr': 0.0004895577217118408, 'samples': 8020480, 'steps': 15664, 'loss/train': 1.4724737405776978}
-03/04/2022 07:52:00 - INFO - codeparrot_training - Step 15665: {'lr': 0.000489556203951555, 'samples': 8020992, 'steps': 15665, 'loss/train': 2.0836777687072754}
-03/04/2022 07:52:02 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/04/2022 07:52:05 - INFO - codeparrot_training - Step 15666: {'lr': 0.0004895546860833287, 'samples': 8021504, 'steps': 15666, 'loss/train': 1.4378376007080078}
-03/04/2022 07:52:09 - INFO - codeparrot_training - Step 15667: {'lr': 0.000489553168107163, 'samples': 8022016, 'steps': 15667, 'loss/train': 2.417998790740967}
-03/04/2022 07:52:11 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/04/2022 07:52:14 - INFO - codeparrot_training - Step 15668: {'lr': 0.0004895516500230581, 'samples': 8022528, 'steps': 15668, 'loss/train': 1.929077386856079}
-03/04/2022 07:52:17 - INFO - codeparrot_training - Step 15669: {'lr': 0.000489550131831015, 'samples': 8023040, 'steps': 15669, 'loss/train': 2.634594202041626}
-03/04/2022 07:52:20 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/04/2022 07:52:22 - INFO - codeparrot_training - Step 15670: {'lr': 0.0004895486135310343, 'samples': 8023552, 'steps': 15670, 'loss/train': 1.6383463144302368}
-03/04/2022 07:52:26 - INFO - codeparrot_training - Step 15671: {'lr': 0.0004895470951231166, 'samples': 8024064, 'steps': 15671, 'loss/train': 1.5963491201400757}
-03/04/2022 07:52:28 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/04/2022 07:52:31 - INFO - codeparrot_training - Step 15672: {'lr': 0.0004895455766072629, 'samples': 8024576, 'steps': 15672, 'loss/train': 2.2744712829589844}
-03/04/2022 07:52:34 - INFO - codeparrot_training - Step 15673: {'lr': 0.0004895440579834736, 'samples': 8025088, 'steps': 15673, 'loss/train': 1.329055905342102}
-03/04/2022 07:52:36 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/04/2022 07:52:39 - INFO - codeparrot_training - Step 15674: {'lr': 0.0004895425392517493, 'samples': 8025600, 'steps': 15674, 'loss/train': 2.1262319087982178}
-03/04/2022 07:52:42 - INFO - codeparrot_training - Step 15675: {'lr': 0.0004895410204120909, 'samples': 8026112, 'steps': 15675, 'loss/train': 0.7481274604797363}
-03/04/2022 07:52:45 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/04/2022 07:52:48 - INFO - codeparrot_training - Step 15676: {'lr': 0.000489539501464499, 'samples': 8026624, 'steps': 15676, 'loss/train': 1.6115937232971191}
-03/04/2022 07:52:51 - INFO - codeparrot_training - Step 15677: {'lr': 0.0004895379824089743, 'samples': 8027136, 'steps': 15677, 'loss/train': 0.3066820800304413}
-03/04/2022 07:52:53 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 07:52:56 - INFO - codeparrot_training - Step 15678: {'lr': 0.0004895364632455175, 'samples': 8027648, 'steps': 15678, 'loss/train': 1.414406418800354}
-03/04/2022 07:52:59 - INFO - codeparrot_training - Step 15679: {'lr': 0.0004895349439741292, 'samples': 8028160, 'steps': 15679, 'loss/train': 1.7060343027114868}
-03/04/2022 07:53:02 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/04/2022 07:53:05 - INFO - codeparrot_training - Step 15680: {'lr': 0.0004895334245948103, 'samples': 8028672, 'steps': 15680, 'loss/train': 1.9586430788040161}
-03/04/2022 07:53:08 - INFO - codeparrot_training - Step 15681: {'lr': 0.0004895319051075612, 'samples': 8029184, 'steps': 15681, 'loss/train': 2.3563432693481445}
-03/04/2022 07:53:10 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/04/2022 07:53:13 - INFO - codeparrot_training - Step 15682: {'lr': 0.0004895303855123828, 'samples': 8029696, 'steps': 15682, 'loss/train': 2.764169216156006}
-03/04/2022 07:53:16 - INFO - codeparrot_training - Step 15683: {'lr': 0.0004895288658092757, 'samples': 8030208, 'steps': 15683, 'loss/train': 1.7268319129943848}
-03/04/2022 07:53:19 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 07:53:22 - INFO - codeparrot_training - Step 15684: {'lr': 0.0004895273459982406, 'samples': 8030720, 'steps': 15684, 'loss/train': 2.6820268630981445}
-03/04/2022 07:53:25 - INFO - codeparrot_training - Step 15685: {'lr': 0.0004895258260792781, 'samples': 8031232, 'steps': 15685, 'loss/train': 1.7235958576202393}
-03/04/2022 07:53:27 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/04/2022 07:53:30 - INFO - codeparrot_training - Step 15686: {'lr': 0.0004895243060523889, 'samples': 8031744, 'steps': 15686, 'loss/train': 1.5525797605514526}
-03/04/2022 07:53:33 - INFO - codeparrot_training - Step 15687: {'lr': 0.0004895227859175739, 'samples': 8032256, 'steps': 15687, 'loss/train': 2.6901612281799316}
-03/04/2022 07:53:36 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 07:53:38 - INFO - codeparrot_training - Step 15688: {'lr': 0.0004895212656748336, 'samples': 8032768, 'steps': 15688, 'loss/train': 1.9821029901504517}
-03/04/2022 07:53:42 - INFO - codeparrot_training - Step 15689: {'lr': 0.0004895197453241687, 'samples': 8033280, 'steps': 15689, 'loss/train': 2.3617098331451416}
-03/04/2022 07:53:44 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/04/2022 07:53:47 - INFO - codeparrot_training - Step 15690: {'lr': 0.0004895182248655798, 'samples': 8033792, 'steps': 15690, 'loss/train': 1.5950372219085693}
-03/04/2022 07:53:50 - INFO - codeparrot_training - Step 15691: {'lr': 0.0004895167042990678, 'samples': 8034304, 'steps': 15691, 'loss/train': 2.5935111045837402}
-03/04/2022 07:53:52 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 07:53:55 - INFO - codeparrot_training - Step 15692: {'lr': 0.0004895151836246332, 'samples': 8034816, 'steps': 15692, 'loss/train': 1.9146080017089844}
-03/04/2022 07:53:59 - INFO - codeparrot_training - Step 15693: {'lr': 0.0004895136628422767, 'samples': 8035328, 'steps': 15693, 'loss/train': 1.6679564714431763}
-03/04/2022 07:54:01 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/04/2022 07:54:04 - INFO - codeparrot_training - Step 15694: {'lr': 0.0004895121419519992, 'samples': 8035840, 'steps': 15694, 'loss/train': 1.7771307229995728}
-03/04/2022 07:54:07 - INFO - codeparrot_training - Step 15695: {'lr': 0.0004895106209538011, 'samples': 8036352, 'steps': 15695, 'loss/train': 2.3171160221099854}
-03/04/2022 07:54:09 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 07:54:12 - INFO - codeparrot_training - Step 15696: {'lr': 0.0004895090998476833, 'samples': 8036864, 'steps': 15696, 'loss/train': 2.1088979244232178}
-03/04/2022 07:54:15 - INFO - codeparrot_training - Step 15697: {'lr': 0.0004895075786336463, 'samples': 8037376, 'steps': 15697, 'loss/train': 1.5757842063903809}
-03/04/2022 07:54:18 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 07:54:21 - INFO - codeparrot_training - Step 15698: {'lr': 0.000489506057311691, 'samples': 8037888, 'steps': 15698, 'loss/train': 2.090244770050049}
-03/04/2022 07:54:24 - INFO - codeparrot_training - Step 15699: {'lr': 0.0004895045358818179, 'samples': 8038400, 'steps': 15699, 'loss/train': 1.1505576372146606}
-03/04/2022 07:54:27 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/04/2022 07:54:29 - INFO - codeparrot_training - Step 15700: {'lr': 0.0004895030143440278, 'samples': 8038912, 'steps': 15700, 'loss/train': 2.5268542766571045}
-03/04/2022 07:54:32 - INFO - codeparrot_training - Step 15701: {'lr': 0.0004895014926983212, 'samples': 8039424, 'steps': 15701, 'loss/train': 0.5695185661315918}
-03/04/2022 07:54:35 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 07:54:38 - INFO - codeparrot_training - Step 15702: {'lr': 0.0004894999709446991, 'samples': 8039936, 'steps': 15702, 'loss/train': 1.5199710130691528}
-03/04/2022 07:54:41 - INFO - codeparrot_training - Step 15703: {'lr': 0.0004894984490831619, 'samples': 8040448, 'steps': 15703, 'loss/train': 0.9801062941551208}
-03/04/2022 07:54:43 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 07:54:46 - INFO - codeparrot_training - Step 15704: {'lr': 0.0004894969271137104, 'samples': 8040960, 'steps': 15704, 'loss/train': 1.1070969104766846}
-03/04/2022 07:54:49 - INFO - codeparrot_training - Step 15705: {'lr': 0.0004894954050363452, 'samples': 8041472, 'steps': 15705, 'loss/train': 1.569886565208435}
-03/04/2022 07:54:52 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/04/2022 07:54:55 - INFO - codeparrot_training - Step 15706: {'lr': 0.0004894938828510672, 'samples': 8041984, 'steps': 15706, 'loss/train': 2.23795747756958}
-03/04/2022 07:54:58 - INFO - codeparrot_training - Step 15707: {'lr': 0.000489492360557877, 'samples': 8042496, 'steps': 15707, 'loss/train': 2.299255132675171}
-03/04/2022 07:55:00 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/04/2022 07:55:03 - INFO - codeparrot_training - Step 15708: {'lr': 0.0004894908381567751, 'samples': 8043008, 'steps': 15708, 'loss/train': 2.358010768890381}
-03/04/2022 07:55:06 - INFO - codeparrot_training - Step 15709: {'lr': 0.0004894893156477623, 'samples': 8043520, 'steps': 15709, 'loss/train': 1.6785175800323486}
-03/04/2022 07:55:08 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/04/2022 07:55:11 - INFO - codeparrot_training - Step 15710: {'lr': 0.0004894877930308395, 'samples': 8044032, 'steps': 15710, 'loss/train': 0.8974571824073792}
-03/04/2022 07:55:15 - INFO - codeparrot_training - Step 15711: {'lr': 0.0004894862703060071, 'samples': 8044544, 'steps': 15711, 'loss/train': 1.5870919227600098}
-03/04/2022 07:55:17 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 07:55:20 - INFO - codeparrot_training - Step 15712: {'lr': 0.0004894847474732658, 'samples': 8045056, 'steps': 15712, 'loss/train': 1.1885066032409668}
-03/04/2022 07:55:23 - INFO - codeparrot_training - Step 15713: {'lr': 0.0004894832245326165, 'samples': 8045568, 'steps': 15713, 'loss/train': 2.2328274250030518}
-03/04/2022 07:55:25 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/04/2022 07:55:28 - INFO - codeparrot_training - Step 15714: {'lr': 0.0004894817014840597, 'samples': 8046080, 'steps': 15714, 'loss/train': 5.130954265594482}
-03/04/2022 07:55:32 - INFO - codeparrot_training - Step 15715: {'lr': 0.0004894801783275961, 'samples': 8046592, 'steps': 15715, 'loss/train': 2.535412311553955}
-03/04/2022 07:55:33 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 07:55:37 - INFO - codeparrot_training - Step 15716: {'lr': 0.0004894786550632264, 'samples': 8047104, 'steps': 15716, 'loss/train': 1.7470682859420776}
-03/04/2022 07:55:40 - INFO - codeparrot_training - Step 15717: {'lr': 0.0004894771316909514, 'samples': 8047616, 'steps': 15717, 'loss/train': 1.9062572717666626}
-03/04/2022 07:55:42 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/04/2022 07:55:45 - INFO - codeparrot_training - Step 15718: {'lr': 0.0004894756082107717, 'samples': 8048128, 'steps': 15718, 'loss/train': 1.096044898033142}
-03/04/2022 07:55:49 - INFO - codeparrot_training - Step 15719: {'lr': 0.0004894740846226879, 'samples': 8048640, 'steps': 15719, 'loss/train': 2.2670860290527344}
-03/04/2022 07:55:50 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 07:55:54 - INFO - codeparrot_training - Step 15720: {'lr': 0.0004894725609267009, 'samples': 8049152, 'steps': 15720, 'loss/train': 1.387764573097229}
-03/04/2022 07:55:57 - INFO - codeparrot_training - Step 15721: {'lr': 0.0004894710371228111, 'samples': 8049664, 'steps': 15721, 'loss/train': 1.4563462734222412}
-03/04/2022 07:55:59 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 07:56:02 - INFO - codeparrot_training - Step 15722: {'lr': 0.0004894695132110196, 'samples': 8050176, 'steps': 15722, 'loss/train': 2.169600009918213}
-03/04/2022 07:56:06 - INFO - codeparrot_training - Step 15723: {'lr': 0.0004894679891913266, 'samples': 8050688, 'steps': 15723, 'loss/train': 6.802032470703125}
-03/04/2022 07:56:08 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 07:56:11 - INFO - codeparrot_training - Step 15724: {'lr': 0.000489466465063733, 'samples': 8051200, 'steps': 15724, 'loss/train': 2.100257635116577}
-03/04/2022 07:56:14 - INFO - codeparrot_training - Step 15725: {'lr': 0.0004894649408282396, 'samples': 8051712, 'steps': 15725, 'loss/train': 1.6503151655197144}
-03/04/2022 07:56:17 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 07:56:19 - INFO - codeparrot_training - Step 15726: {'lr': 0.000489463416484847, 'samples': 8052224, 'steps': 15726, 'loss/train': 1.1871337890625}
-03/04/2022 07:56:22 - INFO - codeparrot_training - Step 15727: {'lr': 0.0004894618920335558, 'samples': 8052736, 'steps': 15727, 'loss/train': 2.119513511657715}
-03/04/2022 07:56:25 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/04/2022 07:56:28 - INFO - codeparrot_training - Step 15728: {'lr': 0.0004894603674743668, 'samples': 8053248, 'steps': 15728, 'loss/train': 1.731230616569519}
-03/04/2022 07:56:31 - INFO - codeparrot_training - Step 15729: {'lr': 0.0004894588428072808, 'samples': 8053760, 'steps': 15729, 'loss/train': 0.736242413520813}
-03/04/2022 07:56:34 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/04/2022 07:56:36 - INFO - codeparrot_training - Step 15730: {'lr': 0.0004894573180322982, 'samples': 8054272, 'steps': 15730, 'loss/train': 1.8481392860412598}
-03/04/2022 07:56:39 - INFO - codeparrot_training - Step 15731: {'lr': 0.0004894557931494199, 'samples': 8054784, 'steps': 15731, 'loss/train': 1.7223693132400513}
-03/04/2022 07:56:43 - INFO - codeparrot_training - Step 15732: {'lr': 0.0004894542681586465, 'samples': 8055296, 'steps': 15732, 'loss/train': 1.4309290647506714}
-03/04/2022 07:56:43 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 07:56:48 - INFO - codeparrot_training - Step 15733: {'lr': 0.0004894527430599786, 'samples': 8055808, 'steps': 15733, 'loss/train': 2.109006643295288}
-03/04/2022 07:56:51 - INFO - codeparrot_training - Step 15734: {'lr': 0.0004894512178534171, 'samples': 8056320, 'steps': 15734, 'loss/train': 1.0732314586639404}
-03/04/2022 07:56:51 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 07:56:56 - INFO - codeparrot_training - Step 15735: {'lr': 0.0004894496925389625, 'samples': 8056832, 'steps': 15735, 'loss/train': 0.8656599521636963}
-03/04/2022 07:57:00 - INFO - codeparrot_training - Step 15736: {'lr': 0.0004894481671166155, 'samples': 8057344, 'steps': 15736, 'loss/train': 0.9400997757911682}
-03/04/2022 07:57:00 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 07:57:05 - INFO - codeparrot_training - Step 15737: {'lr': 0.0004894466415863771, 'samples': 8057856, 'steps': 15737, 'loss/train': 2.0122127532958984}
-03/04/2022 07:57:08 - INFO - codeparrot_training - Step 15738: {'lr': 0.0004894451159482476, 'samples': 8058368, 'steps': 15738, 'loss/train': 2.140281915664673}
-03/04/2022 07:57:08 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/04/2022 07:57:13 - INFO - codeparrot_training - Step 15739: {'lr': 0.0004894435902022277, 'samples': 8058880, 'steps': 15739, 'loss/train': 2.9429759979248047}
-03/04/2022 07:57:17 - INFO - codeparrot_training - Step 15740: {'lr': 0.0004894420643483184, 'samples': 8059392, 'steps': 15740, 'loss/train': 1.9873096942901611}
-03/04/2022 07:57:17 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/04/2022 07:57:22 - INFO - codeparrot_training - Step 15741: {'lr': 0.0004894405383865201, 'samples': 8059904, 'steps': 15741, 'loss/train': 1.499707818031311}
-03/04/2022 07:57:25 - INFO - codeparrot_training - Step 15742: {'lr': 0.0004894390123168337, 'samples': 8060416, 'steps': 15742, 'loss/train': 1.6385310888290405}
-03/04/2022 07:57:25 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/04/2022 07:57:30 - INFO - codeparrot_training - Step 15743: {'lr': 0.0004894374861392596, 'samples': 8060928, 'steps': 15743, 'loss/train': 2.066291570663452}
-03/04/2022 07:57:33 - INFO - codeparrot_training - Step 15744: {'lr': 0.0004894359598537987, 'samples': 8061440, 'steps': 15744, 'loss/train': 0.9673469066619873}
-03/04/2022 07:57:33 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 07:57:39 - INFO - codeparrot_training - Step 15745: {'lr': 0.0004894344334604517, 'samples': 8061952, 'steps': 15745, 'loss/train': 2.314256191253662}
-03/04/2022 07:57:42 - INFO - codeparrot_training - Step 15746: {'lr': 0.0004894329069592192, 'samples': 8062464, 'steps': 15746, 'loss/train': 0.258719265460968}
-03/04/2022 07:57:42 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/04/2022 07:57:47 - INFO - codeparrot_training - Step 15747: {'lr': 0.000489431380350102, 'samples': 8062976, 'steps': 15747, 'loss/train': 1.5270055532455444}
-03/04/2022 07:57:51 - INFO - codeparrot_training - Step 15748: {'lr': 0.0004894298536331007, 'samples': 8063488, 'steps': 15748, 'loss/train': 2.2317898273468018}
-03/04/2022 07:57:52 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 07:57:56 - INFO - codeparrot_training - Step 15749: {'lr': 0.000489428326808216, 'samples': 8064000, 'steps': 15749, 'loss/train': 2.160482883453369}
-03/04/2022 07:57:59 - INFO - codeparrot_training - Step 15750: {'lr': 0.0004894267998754486, 'samples': 8064512, 'steps': 15750, 'loss/train': 1.7678260803222656}
-03/04/2022 07:58:00 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 07:58:04 - INFO - codeparrot_training - Step 15751: {'lr': 0.0004894252728347992, 'samples': 8065024, 'steps': 15751, 'loss/train': 2.3406460285186768}
-03/04/2022 07:58:08 - INFO - codeparrot_training - Step 15752: {'lr': 0.0004894237456862684, 'samples': 8065536, 'steps': 15752, 'loss/train': 1.9627060890197754}
-03/04/2022 07:58:08 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/04/2022 07:58:13 - INFO - codeparrot_training - Step 15753: {'lr': 0.000489422218429857, 'samples': 8066048, 'steps': 15753, 'loss/train': 1.8094896078109741}
-03/04/2022 07:58:16 - INFO - codeparrot_training - Step 15754: {'lr': 0.0004894206910655656, 'samples': 8066560, 'steps': 15754, 'loss/train': 0.9984133839607239}
-03/04/2022 07:58:16 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 07:58:21 - INFO - codeparrot_training - Step 15755: {'lr': 0.0004894191635933949, 'samples': 8067072, 'steps': 15755, 'loss/train': 1.1861696243286133}
-03/04/2022 07:58:24 - INFO - codeparrot_training - Step 15756: {'lr': 0.0004894176360133456, 'samples': 8067584, 'steps': 15756, 'loss/train': 1.8479070663452148}
-03/04/2022 07:58:24 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/04/2022 07:58:30 - INFO - codeparrot_training - Step 15757: {'lr': 0.0004894161083254186, 'samples': 8068096, 'steps': 15757, 'loss/train': 2.597443103790283}
-03/04/2022 07:58:33 - INFO - codeparrot_training - Step 15758: {'lr': 0.0004894145805296143, 'samples': 8068608, 'steps': 15758, 'loss/train': 1.9176812171936035}
-03/04/2022 07:58:33 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/04/2022 07:58:39 - INFO - codeparrot_training - Step 15759: {'lr': 0.0004894130526259334, 'samples': 8069120, 'steps': 15759, 'loss/train': 2.292680025100708}
-03/04/2022 07:58:42 - INFO - codeparrot_training - Step 15760: {'lr': 0.0004894115246143768, 'samples': 8069632, 'steps': 15760, 'loss/train': 1.7781001329421997}
-03/04/2022 07:58:45 - INFO - codeparrot_training - Step 15761: {'lr': 0.0004894099964949449, 'samples': 8070144, 'steps': 15761, 'loss/train': 2.007512092590332}
-03/04/2022 07:58:46 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 07:58:50 - INFO - codeparrot_training - Step 15762: {'lr': 0.0004894084682676387, 'samples': 8070656, 'steps': 15762, 'loss/train': 1.850338101387024}
-03/04/2022 07:58:54 - INFO - codeparrot_training - Step 15763: {'lr': 0.0004894069399324586, 'samples': 8071168, 'steps': 15763, 'loss/train': 1.583418607711792}
-03/04/2022 07:58:55 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/04/2022 07:58:59 - INFO - codeparrot_training - Step 15764: {'lr': 0.0004894054114894055, 'samples': 8071680, 'steps': 15764, 'loss/train': 2.399912118911743}
-03/04/2022 07:59:02 - INFO - codeparrot_training - Step 15765: {'lr': 0.00048940388293848, 'samples': 8072192, 'steps': 15765, 'loss/train': 1.6176056861877441}
-03/04/2022 07:59:04 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/04/2022 07:59:07 - INFO - codeparrot_training - Step 15766: {'lr': 0.000489402354279683, 'samples': 8072704, 'steps': 15766, 'loss/train': 2.1097328662872314}
-03/04/2022 07:59:11 - INFO - codeparrot_training - Step 15767: {'lr': 0.0004894008255130147, 'samples': 8073216, 'steps': 15767, 'loss/train': 1.6398531198501587}
-03/04/2022 07:59:12 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/04/2022 07:59:16 - INFO - codeparrot_training - Step 15768: {'lr': 0.0004893992966384762, 'samples': 8073728, 'steps': 15768, 'loss/train': 0.8948653936386108}
-03/04/2022 07:59:19 - INFO - codeparrot_training - Step 15769: {'lr': 0.0004893977676560682, 'samples': 8074240, 'steps': 15769, 'loss/train': 2.3008790016174316}
-03/04/2022 07:59:21 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 07:59:24 - INFO - codeparrot_training - Step 15770: {'lr': 0.000489396238565791, 'samples': 8074752, 'steps': 15770, 'loss/train': 1.6504114866256714}
-03/04/2022 07:59:27 - INFO - codeparrot_training - Step 15771: {'lr': 0.0004893947093676458, 'samples': 8075264, 'steps': 15771, 'loss/train': 1.8950122594833374}
-03/04/2022 07:59:29 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 07:59:33 - INFO - codeparrot_training - Step 15772: {'lr': 0.0004893931800616329, 'samples': 8075776, 'steps': 15772, 'loss/train': 1.6442188024520874}
-03/04/2022 07:59:36 - INFO - codeparrot_training - Step 15773: {'lr': 0.0004893916506477532, 'samples': 8076288, 'steps': 15773, 'loss/train': 1.806784749031067}
-03/04/2022 07:59:38 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 07:59:41 - INFO - codeparrot_training - Step 15774: {'lr': 0.0004893901211260073, 'samples': 8076800, 'steps': 15774, 'loss/train': 1.3734625577926636}
-03/04/2022 07:59:44 - INFO - codeparrot_training - Step 15775: {'lr': 0.0004893885914963958, 'samples': 8077312, 'steps': 15775, 'loss/train': 2.3755300045013428}
-03/04/2022 07:59:46 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 07:59:50 - INFO - codeparrot_training - Step 15776: {'lr': 0.0004893870617589196, 'samples': 8077824, 'steps': 15776, 'loss/train': 0.982387363910675}
-03/04/2022 07:59:53 - INFO - codeparrot_training - Step 15777: {'lr': 0.0004893855319135791, 'samples': 8078336, 'steps': 15777, 'loss/train': 2.390859365463257}
-03/04/2022 07:59:55 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/04/2022 07:59:58 - INFO - codeparrot_training - Step 15778: {'lr': 0.0004893840019603754, 'samples': 8078848, 'steps': 15778, 'loss/train': 2.067556142807007}
-03/04/2022 08:00:01 - INFO - codeparrot_training - Step 15779: {'lr': 0.0004893824718993088, 'samples': 8079360, 'steps': 15779, 'loss/train': 2.096879720687866}
-03/04/2022 08:00:03 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 08:00:06 - INFO - codeparrot_training - Step 15780: {'lr': 0.0004893809417303803, 'samples': 8079872, 'steps': 15780, 'loss/train': 1.7250200510025024}
-03/04/2022 08:00:10 - INFO - codeparrot_training - Step 15781: {'lr': 0.0004893794114535905, 'samples': 8080384, 'steps': 15781, 'loss/train': 1.2458003759384155}
-03/04/2022 08:00:11 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/04/2022 08:00:15 - INFO - codeparrot_training - Step 15782: {'lr': 0.0004893778810689399, 'samples': 8080896, 'steps': 15782, 'loss/train': 1.8468230962753296}
-03/04/2022 08:00:18 - INFO - codeparrot_training - Step 15783: {'lr': 0.0004893763505764292, 'samples': 8081408, 'steps': 15783, 'loss/train': 3.7919137477874756}
-03/04/2022 08:00:20 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/04/2022 08:00:23 - INFO - codeparrot_training - Step 15784: {'lr': 0.0004893748199760594, 'samples': 8081920, 'steps': 15784, 'loss/train': 1.166268229484558}
-03/04/2022 08:00:26 - INFO - codeparrot_training - Step 15785: {'lr': 0.0004893732892678309, 'samples': 8082432, 'steps': 15785, 'loss/train': 2.209667444229126}
-03/04/2022 08:00:28 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/04/2022 08:00:32 - INFO - codeparrot_training - Step 15786: {'lr': 0.0004893717584517445, 'samples': 8082944, 'steps': 15786, 'loss/train': 2.6296679973602295}
-03/04/2022 08:00:35 - INFO - codeparrot_training - Step 15787: {'lr': 0.000489370227527801, 'samples': 8083456, 'steps': 15787, 'loss/train': 1.7829806804656982}
-03/04/2022 08:00:38 - INFO - codeparrot_training - Step 15788: {'lr': 0.0004893686964960009, 'samples': 8083968, 'steps': 15788, 'loss/train': 2.3239595890045166}
-03/04/2022 08:00:38 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 08:00:44 - INFO - codeparrot_training - Step 15789: {'lr': 0.0004893671653563448, 'samples': 8084480, 'steps': 15789, 'loss/train': 1.8203243017196655}
-03/04/2022 08:00:47 - INFO - codeparrot_training - Step 15790: {'lr': 0.0004893656341088338, 'samples': 8084992, 'steps': 15790, 'loss/train': 2.1572787761688232}
-03/04/2022 08:00:48 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/04/2022 08:00:52 - INFO - codeparrot_training - Step 15791: {'lr': 0.0004893641027534682, 'samples': 8085504, 'steps': 15791, 'loss/train': 2.2781121730804443}
-03/04/2022 08:00:55 - INFO - codeparrot_training - Step 15792: {'lr': 0.0004893625712902489, 'samples': 8086016, 'steps': 15792, 'loss/train': 1.9550840854644775}
-03/04/2022 08:00:56 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 08:01:01 - INFO - codeparrot_training - Step 15793: {'lr': 0.0004893610397191764, 'samples': 8086528, 'steps': 15793, 'loss/train': 1.6182414293289185}
-03/04/2022 08:01:04 - INFO - codeparrot_training - Step 15794: {'lr': 0.0004893595080402517, 'samples': 8087040, 'steps': 15794, 'loss/train': 1.7665551900863647}
-03/04/2022 08:01:05 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 08:01:09 - INFO - codeparrot_training - Step 15795: {'lr': 0.0004893579762534751, 'samples': 8087552, 'steps': 15795, 'loss/train': 1.4938420057296753}
-03/04/2022 08:01:12 - INFO - codeparrot_training - Step 15796: {'lr': 0.0004893564443588476, 'samples': 8088064, 'steps': 15796, 'loss/train': 2.1501986980438232}
-03/04/2022 08:01:13 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/04/2022 08:01:17 - INFO - codeparrot_training - Step 15797: {'lr': 0.0004893549123563697, 'samples': 8088576, 'steps': 15797, 'loss/train': 0.7328019738197327}
-03/04/2022 08:01:21 - INFO - codeparrot_training - Step 15798: {'lr': 0.0004893533802460422, 'samples': 8089088, 'steps': 15798, 'loss/train': 2.7890186309814453}
-03/04/2022 08:01:21 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 08:01:26 - INFO - codeparrot_training - Step 15799: {'lr': 0.0004893518480278658, 'samples': 8089600, 'steps': 15799, 'loss/train': 1.7985717058181763}
-03/04/2022 08:01:29 - INFO - codeparrot_training - Step 15800: {'lr': 0.0004893503157018412, 'samples': 8090112, 'steps': 15800, 'loss/train': 2.0957748889923096}
-03/04/2022 08:01:30 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 08:01:34 - INFO - codeparrot_training - Step 15801: {'lr': 0.000489348783267969, 'samples': 8090624, 'steps': 15801, 'loss/train': 1.6135627031326294}
-03/04/2022 08:01:38 - INFO - codeparrot_training - Step 15802: {'lr': 0.0004893472507262499, 'samples': 8091136, 'steps': 15802, 'loss/train': 2.281519889831543}
-03/04/2022 08:01:38 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 08:01:43 - INFO - codeparrot_training - Step 15803: {'lr': 0.0004893457180766846, 'samples': 8091648, 'steps': 15803, 'loss/train': 0.18596215546131134}
-03/04/2022 08:01:46 - INFO - codeparrot_training - Step 15804: {'lr': 0.0004893441853192739, 'samples': 8092160, 'steps': 15804, 'loss/train': 1.4705119132995605}
-03/04/2022 08:01:46 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/04/2022 08:01:51 - INFO - codeparrot_training - Step 15805: {'lr': 0.0004893426524540183, 'samples': 8092672, 'steps': 15805, 'loss/train': 2.06527042388916}
-03/04/2022 08:01:54 - INFO - codeparrot_training - Step 15806: {'lr': 0.0004893411194809186, 'samples': 8093184, 'steps': 15806, 'loss/train': 2.124040365219116}
-03/04/2022 08:01:54 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 08:02:00 - INFO - codeparrot_training - Step 15807: {'lr': 0.0004893395863999755, 'samples': 8093696, 'steps': 15807, 'loss/train': 1.6741931438446045}
-03/04/2022 08:02:03 - INFO - codeparrot_training - Step 15808: {'lr': 0.0004893380532111898, 'samples': 8094208, 'steps': 15808, 'loss/train': 2.011415719985962}
-03/04/2022 08:02:03 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/04/2022 08:02:08 - INFO - codeparrot_training - Step 15809: {'lr': 0.0004893365199145619, 'samples': 8094720, 'steps': 15809, 'loss/train': 1.4917219877243042}
-03/04/2022 08:02:11 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/04/2022 08:02:13 - INFO - codeparrot_training - Step 15810: {'lr': 0.0004893349865100927, 'samples': 8095232, 'steps': 15810, 'loss/train': 1.5114916563034058}
-03/04/2022 08:02:17 - INFO - codeparrot_training - Step 15811: {'lr': 0.0004893334529977828, 'samples': 8095744, 'steps': 15811, 'loss/train': 1.9902334213256836}
-03/04/2022 08:02:20 - INFO - codeparrot_training - Step 15812: {'lr': 0.0004893319193776331, 'samples': 8096256, 'steps': 15812, 'loss/train': 1.152863621711731}
-03/04/2022 08:02:20 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/04/2022 08:02:25 - INFO - codeparrot_training - Step 15813: {'lr': 0.000489330385649644, 'samples': 8096768, 'steps': 15813, 'loss/train': 1.5612592697143555}
-03/04/2022 08:02:28 - INFO - codeparrot_training - Step 15814: {'lr': 0.0004893288518138163, 'samples': 8097280, 'steps': 15814, 'loss/train': 2.08412766456604}
-03/04/2022 08:02:28 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/04/2022 08:02:34 - INFO - codeparrot_training - Step 15815: {'lr': 0.0004893273178701508, 'samples': 8097792, 'steps': 15815, 'loss/train': 3.6469032764434814}
-03/04/2022 08:02:36 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 08:02:39 - INFO - codeparrot_training - Step 15816: {'lr': 0.0004893257838186481, 'samples': 8098304, 'steps': 15816, 'loss/train': 1.4669967889785767}
-03/04/2022 08:02:42 - INFO - codeparrot_training - Step 15817: {'lr': 0.0004893242496593089, 'samples': 8098816, 'steps': 15817, 'loss/train': 2.26248836517334}
-03/04/2022 08:02:45 - INFO - codeparrot_training - Step 15818: {'lr': 0.0004893227153921338, 'samples': 8099328, 'steps': 15818, 'loss/train': 6.722436428070068}
-03/04/2022 08:02:46 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/04/2022 08:02:51 - INFO - codeparrot_training - Step 15819: {'lr': 0.0004893211810171237, 'samples': 8099840, 'steps': 15819, 'loss/train': 2.182323455810547}
-03/04/2022 08:02:54 - INFO - codeparrot_training - Step 15820: {'lr': 0.0004893196465342791, 'samples': 8100352, 'steps': 15820, 'loss/train': 1.7550013065338135}
-03/04/2022 08:02:55 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/04/2022 08:02:59 - INFO - codeparrot_training - Step 15821: {'lr': 0.0004893181119436007, 'samples': 8100864, 'steps': 15821, 'loss/train': 2.352924346923828}
-03/04/2022 08:03:02 - INFO - codeparrot_training - Step 15822: {'lr': 0.0004893165772450893, 'samples': 8101376, 'steps': 15822, 'loss/train': 1.8123749494552612}
-03/04/2022 08:03:03 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/04/2022 08:03:08 - INFO - codeparrot_training - Step 15823: {'lr': 0.0004893150424387456, 'samples': 8101888, 'steps': 15823, 'loss/train': 1.9320213794708252}
-03/04/2022 08:03:11 - INFO - codeparrot_training - Step 15824: {'lr': 0.0004893135075245702, 'samples': 8102400, 'steps': 15824, 'loss/train': 0.6169528365135193}
-03/04/2022 08:03:11 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 08:03:16 - INFO - codeparrot_training - Step 15825: {'lr': 0.0004893119725025639, 'samples': 8102912, 'steps': 15825, 'loss/train': 1.7955065965652466}
-03/04/2022 08:03:19 - INFO - codeparrot_training - Step 15826: {'lr': 0.0004893104373727272, 'samples': 8103424, 'steps': 15826, 'loss/train': 1.3975342512130737}
-03/04/2022 08:03:20 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/04/2022 08:03:25 - INFO - codeparrot_training - Step 15827: {'lr': 0.0004893089021350609, 'samples': 8103936, 'steps': 15827, 'loss/train': 1.7311853170394897}
-03/04/2022 08:03:28 - INFO - codeparrot_training - Step 15828: {'lr': 0.0004893073667895658, 'samples': 8104448, 'steps': 15828, 'loss/train': 0.5723534822463989}
-03/04/2022 08:03:28 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/04/2022 08:03:33 - INFO - codeparrot_training - Step 15829: {'lr': 0.0004893058313362424, 'samples': 8104960, 'steps': 15829, 'loss/train': 2.4262561798095703}
-03/04/2022 08:03:36 - INFO - codeparrot_training - Step 15830: {'lr': 0.0004893042957750916, 'samples': 8105472, 'steps': 15830, 'loss/train': 1.6608119010925293}
-03/04/2022 08:03:37 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 08:03:42 - INFO - codeparrot_training - Step 15831: {'lr': 0.0004893027601061138, 'samples': 8105984, 'steps': 15831, 'loss/train': 2.279754161834717}
-03/04/2022 08:03:45 - INFO - codeparrot_training - Step 15832: {'lr': 0.00048930122432931, 'samples': 8106496, 'steps': 15832, 'loss/train': 2.34913969039917}
-03/04/2022 08:03:46 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/04/2022 08:03:50 - INFO - codeparrot_training - Step 15833: {'lr': 0.0004892996884446807, 'samples': 8107008, 'steps': 15833, 'loss/train': 1.6687400341033936}
-03/04/2022 08:03:54 - INFO - codeparrot_training - Step 15834: {'lr': 0.0004892981524522267, 'samples': 8107520, 'steps': 15834, 'loss/train': 1.4493680000305176}
-03/04/2022 08:03:55 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/04/2022 08:03:59 - INFO - codeparrot_training - Step 15835: {'lr': 0.0004892966163519487, 'samples': 8108032, 'steps': 15835, 'loss/train': 2.158994197845459}
-03/04/2022 08:04:02 - INFO - codeparrot_training - Step 15836: {'lr': 0.0004892950801438472, 'samples': 8108544, 'steps': 15836, 'loss/train': 2.445634603500366}
-03/04/2022 08:04:04 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/04/2022 08:04:08 - INFO - codeparrot_training - Step 15837: {'lr': 0.0004892935438279231, 'samples': 8109056, 'steps': 15837, 'loss/train': 2.107288360595703}
-03/04/2022 08:04:11 - INFO - codeparrot_training - Step 15838: {'lr': 0.0004892920074041771, 'samples': 8109568, 'steps': 15838, 'loss/train': 1.5856229066848755}
-03/04/2022 08:04:14 - INFO - codeparrot_training - Step 15839: {'lr': 0.0004892904708726096, 'samples': 8110080, 'steps': 15839, 'loss/train': 2.4564788341522217}
-03/04/2022 08:04:16 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/04/2022 08:04:20 - INFO - codeparrot_training - Step 15840: {'lr': 0.0004892889342332218, 'samples': 8110592, 'steps': 15840, 'loss/train': 2.463087797164917}
-03/04/2022 08:04:23 - INFO - codeparrot_training - Step 15841: {'lr': 0.000489287397486014, 'samples': 8111104, 'steps': 15841, 'loss/train': 2.2456350326538086}
-03/04/2022 08:04:24 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 08:04:28 - INFO - codeparrot_training - Step 15842: {'lr': 0.0004892858606309868, 'samples': 8111616, 'steps': 15842, 'loss/train': 2.015606164932251}
-03/04/2022 08:04:31 - INFO - codeparrot_training - Step 15843: {'lr': 0.0004892843236681412, 'samples': 8112128, 'steps': 15843, 'loss/train': 2.396704912185669}
-03/04/2022 08:04:33 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 08:04:37 - INFO - codeparrot_training - Step 15844: {'lr': 0.0004892827865974779, 'samples': 8112640, 'steps': 15844, 'loss/train': 2.3219165802001953}
-03/04/2022 08:04:40 - INFO - codeparrot_training - Step 15845: {'lr': 0.0004892812494189973, 'samples': 8113152, 'steps': 15845, 'loss/train': 2.236128330230713}
-03/04/2022 08:04:41 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/04/2022 08:04:45 - INFO - codeparrot_training - Step 15846: {'lr': 0.0004892797121327003, 'samples': 8113664, 'steps': 15846, 'loss/train': 1.9846620559692383}
-03/04/2022 08:04:48 - INFO - codeparrot_training - Step 15847: {'lr': 0.0004892781747385876, 'samples': 8114176, 'steps': 15847, 'loss/train': 1.8854482173919678}
-03/04/2022 08:04:49 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 08:04:53 - INFO - codeparrot_training - Step 15848: {'lr': 0.0004892766372366598, 'samples': 8114688, 'steps': 15848, 'loss/train': 2.14094877243042}
-03/04/2022 08:04:57 - INFO - codeparrot_training - Step 15849: {'lr': 0.0004892750996269177, 'samples': 8115200, 'steps': 15849, 'loss/train': 1.92839777469635}
-03/04/2022 08:04:58 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 08:05:02 - INFO - codeparrot_training - Step 15850: {'lr': 0.0004892735619093618, 'samples': 8115712, 'steps': 15850, 'loss/train': 1.8320256471633911}
-03/04/2022 08:05:05 - INFO - codeparrot_training - Step 15851: {'lr': 0.0004892720240839931, 'samples': 8116224, 'steps': 15851, 'loss/train': 1.133046269416809}
-03/04/2022 08:05:06 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/04/2022 08:05:10 - INFO - codeparrot_training - Step 15852: {'lr': 0.0004892704861508121, 'samples': 8116736, 'steps': 15852, 'loss/train': 1.5446724891662598}
-03/04/2022 08:05:14 - INFO - codeparrot_training - Step 15853: {'lr': 0.0004892689481098193, 'samples': 8117248, 'steps': 15853, 'loss/train': 0.6465367674827576}
-03/04/2022 08:05:15 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 08:05:19 - INFO - codeparrot_training - Step 15854: {'lr': 0.0004892674099610158, 'samples': 8117760, 'steps': 15854, 'loss/train': 2.0504391193389893}
-03/04/2022 08:05:22 - INFO - codeparrot_training - Step 15855: {'lr': 0.000489265871704402, 'samples': 8118272, 'steps': 15855, 'loss/train': 1.7675758600234985}
-03/04/2022 08:05:23 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/04/2022 08:05:27 - INFO - codeparrot_training - Step 15856: {'lr': 0.0004892643333399788, 'samples': 8118784, 'steps': 15856, 'loss/train': 1.8653327226638794}
-03/04/2022 08:05:31 - INFO - codeparrot_training - Step 15857: {'lr': 0.0004892627948677467, 'samples': 8119296, 'steps': 15857, 'loss/train': 1.6817375421524048}
-03/04/2022 08:05:32 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/04/2022 08:05:36 - INFO - codeparrot_training - Step 15858: {'lr': 0.0004892612562877066, 'samples': 8119808, 'steps': 15858, 'loss/train': 2.5121445655822754}
-03/04/2022 08:05:39 - INFO - codeparrot_training - Step 15859: {'lr': 0.0004892597175998589, 'samples': 8120320, 'steps': 15859, 'loss/train': 2.230720281600952}
-03/04/2022 08:05:40 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/04/2022 08:05:44 - INFO - codeparrot_training - Step 15860: {'lr': 0.0004892581788042045, 'samples': 8120832, 'steps': 15860, 'loss/train': 1.6992627382278442}
-03/04/2022 08:05:47 - INFO - codeparrot_training - Step 15861: {'lr': 0.0004892566399007441, 'samples': 8121344, 'steps': 15861, 'loss/train': 2.367680788040161}
-03/04/2022 08:05:48 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 08:05:53 - INFO - codeparrot_training - Step 15862: {'lr': 0.0004892551008894784, 'samples': 8121856, 'steps': 15862, 'loss/train': 1.3575867414474487}
-03/04/2022 08:05:56 - INFO - codeparrot_training - Step 15863: {'lr': 0.0004892535617704079, 'samples': 8122368, 'steps': 15863, 'loss/train': 1.7326768636703491}
-03/04/2022 08:05:57 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/04/2022 08:06:01 - INFO - codeparrot_training - Step 15864: {'lr': 0.0004892520225435336, 'samples': 8122880, 'steps': 15864, 'loss/train': 2.236912488937378}
-03/04/2022 08:06:04 - INFO - codeparrot_training - Step 15865: {'lr': 0.000489250483208856, 'samples': 8123392, 'steps': 15865, 'loss/train': 1.875346064567566}
-03/04/2022 08:06:05 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 08:06:10 - INFO - codeparrot_training - Step 15866: {'lr': 0.0004892489437663758, 'samples': 8123904, 'steps': 15866, 'loss/train': 1.5783551931381226}
-03/04/2022 08:06:13 - INFO - codeparrot_training - Step 15867: {'lr': 0.0004892474042160936, 'samples': 8124416, 'steps': 15867, 'loss/train': 0.7856854200363159}
-03/04/2022 08:06:16 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/04/2022 08:06:18 - INFO - codeparrot_training - Step 15868: {'lr': 0.0004892458645580103, 'samples': 8124928, 'steps': 15868, 'loss/train': 1.161672592163086}
-03/04/2022 08:06:21 - INFO - codeparrot_training - Step 15869: {'lr': 0.0004892443247921265, 'samples': 8125440, 'steps': 15869, 'loss/train': 2.6213581562042236}
-03/04/2022 08:06:24 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/04/2022 08:06:27 - INFO - codeparrot_training - Step 15870: {'lr': 0.0004892427849184428, 'samples': 8125952, 'steps': 15870, 'loss/train': 2.2652716636657715}
-03/04/2022 08:06:30 - INFO - codeparrot_training - Step 15871: {'lr': 0.0004892412449369602, 'samples': 8126464, 'steps': 15871, 'loss/train': 1.668884038925171}
-03/04/2022 08:06:32 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/04/2022 08:06:35 - INFO - codeparrot_training - Step 15872: {'lr': 0.0004892397048476791, 'samples': 8126976, 'steps': 15872, 'loss/train': 2.220470666885376}
-03/04/2022 08:06:38 - INFO - codeparrot_training - Step 15873: {'lr': 0.0004892381646506002, 'samples': 8127488, 'steps': 15873, 'loss/train': 1.9844043254852295}
-03/04/2022 08:06:42 - INFO - codeparrot_training - Step 15874: {'lr': 0.0004892366243457244, 'samples': 8128000, 'steps': 15874, 'loss/train': 1.0987316370010376}
-03/04/2022 08:06:42 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/04/2022 08:06:47 - INFO - codeparrot_training - Step 15875: {'lr': 0.0004892350839330522, 'samples': 8128512, 'steps': 15875, 'loss/train': 1.033462405204773}
-03/04/2022 08:06:50 - INFO - codeparrot_training - Step 15876: {'lr': 0.0004892335434125844, 'samples': 8129024, 'steps': 15876, 'loss/train': 1.4013376235961914}
-03/04/2022 08:06:50 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/04/2022 08:06:55 - INFO - codeparrot_training - Step 15877: {'lr': 0.0004892320027843216, 'samples': 8129536, 'steps': 15877, 'loss/train': 0.6777030229568481}
-03/04/2022 08:06:59 - INFO - codeparrot_training - Step 15878: {'lr': 0.0004892304620482646, 'samples': 8130048, 'steps': 15878, 'loss/train': 1.9155230522155762}
-03/04/2022 08:06:59 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/04/2022 08:07:04 - INFO - codeparrot_training - Step 15879: {'lr': 0.000489228921204414, 'samples': 8130560, 'steps': 15879, 'loss/train': 1.9339735507965088}
-03/04/2022 08:07:07 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/04/2022 08:07:09 - INFO - codeparrot_training - Step 15880: {'lr': 0.0004892273802527706, 'samples': 8131072, 'steps': 15880, 'loss/train': 2.108027219772339}
-03/04/2022 08:07:12 - INFO - codeparrot_training - Step 15881: {'lr': 0.000489225839193335, 'samples': 8131584, 'steps': 15881, 'loss/train': 1.762894630432129}
-03/04/2022 08:07:15 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 08:07:17 - INFO - codeparrot_training - Step 15882: {'lr': 0.0004892242980261079, 'samples': 8132096, 'steps': 15882, 'loss/train': 2.032097816467285}
-03/04/2022 08:07:21 - INFO - codeparrot_training - Step 15883: {'lr': 0.0004892227567510901, 'samples': 8132608, 'steps': 15883, 'loss/train': 1.822227120399475}
-03/04/2022 08:07:23 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 08:07:26 - INFO - codeparrot_training - Step 15884: {'lr': 0.0004892212153682822, 'samples': 8133120, 'steps': 15884, 'loss/train': 1.586495280265808}
-03/04/2022 08:07:30 - INFO - codeparrot_training - Step 15885: {'lr': 0.0004892196738776848, 'samples': 8133632, 'steps': 15885, 'loss/train': 1.091257929801941}
-03/04/2022 08:07:33 - INFO - codeparrot_training - Step 15886: {'lr': 0.0004892181322792989, 'samples': 8134144, 'steps': 15886, 'loss/train': 2.4290037155151367}
-03/04/2022 08:07:34 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 08:07:38 - INFO - codeparrot_training - Step 15887: {'lr': 0.0004892165905731248, 'samples': 8134656, 'steps': 15887, 'loss/train': 1.8909389972686768}
-03/04/2022 08:07:41 - INFO - codeparrot_training - Step 15888: {'lr': 0.0004892150487591635, 'samples': 8135168, 'steps': 15888, 'loss/train': 1.070261836051941}
-03/04/2022 08:07:43 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/04/2022 08:07:46 - INFO - codeparrot_training - Step 15889: {'lr': 0.0004892135068374156, 'samples': 8135680, 'steps': 15889, 'loss/train': 1.9358346462249756}
-03/04/2022 08:07:50 - INFO - codeparrot_training - Step 15890: {'lr': 0.0004892119648078817, 'samples': 8136192, 'steps': 15890, 'loss/train': 2.5113108158111572}
-03/04/2022 08:07:51 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 08:07:55 - INFO - codeparrot_training - Step 15891: {'lr': 0.0004892104226705627, 'samples': 8136704, 'steps': 15891, 'loss/train': 1.4813250303268433}
-03/04/2022 08:07:58 - INFO - codeparrot_training - Step 15892: {'lr': 0.0004892088804254591, 'samples': 8137216, 'steps': 15892, 'loss/train': 1.735444188117981}
-03/04/2022 08:08:00 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/04/2022 08:08:03 - INFO - codeparrot_training - Step 15893: {'lr': 0.0004892073380725716, 'samples': 8137728, 'steps': 15893, 'loss/train': 0.21478936076164246}
-03/04/2022 08:08:06 - INFO - codeparrot_training - Step 15894: {'lr': 0.0004892057956119012, 'samples': 8138240, 'steps': 15894, 'loss/train': 2.0290284156799316}
-03/04/2022 08:08:08 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 08:08:12 - INFO - codeparrot_training - Step 15895: {'lr': 0.0004892042530434482, 'samples': 8138752, 'steps': 15895, 'loss/train': 1.847808599472046}
-03/04/2022 08:08:15 - INFO - codeparrot_training - Step 15896: {'lr': 0.0004892027103672134, 'samples': 8139264, 'steps': 15896, 'loss/train': 2.3561031818389893}
-03/04/2022 08:08:17 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/04/2022 08:08:20 - INFO - codeparrot_training - Step 15897: {'lr': 0.0004892011675831976, 'samples': 8139776, 'steps': 15897, 'loss/train': 1.825137972831726}
-03/04/2022 08:08:23 - INFO - codeparrot_training - Step 15898: {'lr': 0.0004891996246914014, 'samples': 8140288, 'steps': 15898, 'loss/train': 2.7217257022857666}
-03/04/2022 08:08:25 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/04/2022 08:08:28 - INFO - codeparrot_training - Step 15899: {'lr': 0.0004891980816918257, 'samples': 8140800, 'steps': 15899, 'loss/train': 2.161484956741333}
-03/04/2022 08:08:32 - INFO - codeparrot_training - Step 15900: {'lr': 0.0004891965385844709, 'samples': 8141312, 'steps': 15900, 'loss/train': 1.3729290962219238}
-03/04/2022 08:08:33 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/04/2022 08:08:37 - INFO - codeparrot_training - Step 15901: {'lr': 0.0004891949953693378, 'samples': 8141824, 'steps': 15901, 'loss/train': 1.8371444940567017}
-03/04/2022 08:08:40 - INFO - codeparrot_training - Step 15902: {'lr': 0.0004891934520464273, 'samples': 8142336, 'steps': 15902, 'loss/train': 1.0400646924972534}
-03/04/2022 08:08:42 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/04/2022 08:08:45 - INFO - codeparrot_training - Step 15903: {'lr': 0.0004891919086157398, 'samples': 8142848, 'steps': 15903, 'loss/train': 1.1689378023147583}
-03/04/2022 08:08:49 - INFO - codeparrot_training - Step 15904: {'lr': 0.000489190365077276, 'samples': 8143360, 'steps': 15904, 'loss/train': 1.826979637145996}
-03/04/2022 08:08:50 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/04/2022 08:08:54 - INFO - codeparrot_training - Step 15905: {'lr': 0.0004891888214310369, 'samples': 8143872, 'steps': 15905, 'loss/train': 2.569539785385132}
-03/04/2022 08:08:57 - INFO - codeparrot_training - Step 15906: {'lr': 0.000489187277677023, 'samples': 8144384, 'steps': 15906, 'loss/train': 2.307072639465332}
-03/04/2022 08:08:58 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/04/2022 08:09:03 - INFO - codeparrot_training - Step 15907: {'lr': 0.000489185733815235, 'samples': 8144896, 'steps': 15907, 'loss/train': 1.8718996047973633}
-03/04/2022 08:09:06 - INFO - codeparrot_training - Step 15908: {'lr': 0.0004891841898456735, 'samples': 8145408, 'steps': 15908, 'loss/train': 2.5906143188476562}
-03/04/2022 08:09:08 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 08:09:11 - INFO - codeparrot_training - Step 15909: {'lr': 0.0004891826457683394, 'samples': 8145920, 'steps': 15909, 'loss/train': 2.35233473777771}
-03/04/2022 08:09:14 - INFO - codeparrot_training - Step 15910: {'lr': 0.0004891811015832332, 'samples': 8146432, 'steps': 15910, 'loss/train': 2.5454862117767334}
-03/04/2022 08:09:16 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/04/2022 08:09:19 - INFO - codeparrot_training - Step 15911: {'lr': 0.0004891795572903557, 'samples': 8146944, 'steps': 15911, 'loss/train': 2.1073851585388184}
-03/04/2022 08:09:22 - INFO - codeparrot_training - Step 15912: {'lr': 0.0004891780128897077, 'samples': 8147456, 'steps': 15912, 'loss/train': 1.6469091176986694}
-03/04/2022 08:09:24 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/04/2022 08:09:28 - INFO - codeparrot_training - Step 15913: {'lr': 0.0004891764683812896, 'samples': 8147968, 'steps': 15913, 'loss/train': 1.3148953914642334}
-03/04/2022 08:09:31 - INFO - codeparrot_training - Step 15914: {'lr': 0.0004891749237651024, 'samples': 8148480, 'steps': 15914, 'loss/train': 1.747546911239624}
-03/04/2022 08:09:33 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/04/2022 08:09:36 - INFO - codeparrot_training - Step 15915: {'lr': 0.0004891733790411466, 'samples': 8148992, 'steps': 15915, 'loss/train': 2.2069268226623535}
-03/04/2022 08:09:39 - INFO - codeparrot_training - Step 15916: {'lr': 0.000489171834209423, 'samples': 8149504, 'steps': 15916, 'loss/train': 1.907037615776062}
-03/04/2022 08:09:41 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 08:09:44 - INFO - codeparrot_training - Step 15917: {'lr': 0.0004891702892699323, 'samples': 8150016, 'steps': 15917, 'loss/train': 2.838202476501465}
-03/04/2022 08:09:48 - INFO - codeparrot_training - Step 15918: {'lr': 0.0004891687442226751, 'samples': 8150528, 'steps': 15918, 'loss/train': 1.1139270067214966}
-03/04/2022 08:09:49 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 08:09:53 - INFO - codeparrot_training - Step 15919: {'lr': 0.0004891671990676522, 'samples': 8151040, 'steps': 15919, 'loss/train': 1.6333458423614502}
-03/04/2022 08:09:56 - INFO - codeparrot_training - Step 15920: {'lr': 0.0004891656538048642, 'samples': 8151552, 'steps': 15920, 'loss/train': 0.8280512690544128}
-03/04/2022 08:09:58 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/04/2022 08:10:01 - INFO - codeparrot_training - Step 15921: {'lr': 0.0004891641084343118, 'samples': 8152064, 'steps': 15921, 'loss/train': 0.4806496798992157}
-03/04/2022 08:10:04 - INFO - codeparrot_training - Step 15922: {'lr': 0.0004891625629559959, 'samples': 8152576, 'steps': 15922, 'loss/train': 1.7383266687393188}
-03/04/2022 08:10:06 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 08:10:10 - INFO - codeparrot_training - Step 15923: {'lr': 0.0004891610173699169, 'samples': 8153088, 'steps': 15923, 'loss/train': 0.9154915809631348}
-03/04/2022 08:10:13 - INFO - codeparrot_training - Step 15924: {'lr': 0.0004891594716760757, 'samples': 8153600, 'steps': 15924, 'loss/train': 1.2812516689300537}
-03/04/2022 08:10:15 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 08:10:18 - INFO - codeparrot_training - Step 15925: {'lr': 0.0004891579258744728, 'samples': 8154112, 'steps': 15925, 'loss/train': 1.7019883394241333}
-03/04/2022 08:10:21 - INFO - codeparrot_training - Step 15926: {'lr': 0.0004891563799651092, 'samples': 8154624, 'steps': 15926, 'loss/train': 1.9730263948440552}
-03/04/2022 08:10:23 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 08:10:27 - INFO - codeparrot_training - Step 15927: {'lr': 0.0004891548339479854, 'samples': 8155136, 'steps': 15927, 'loss/train': 2.4476823806762695}
-03/04/2022 08:10:30 - INFO - codeparrot_training - Step 15928: {'lr': 0.0004891532878231021, 'samples': 8155648, 'steps': 15928, 'loss/train': 0.9744095802307129}
-03/04/2022 08:10:32 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/04/2022 08:10:35 - INFO - codeparrot_training - Step 15929: {'lr': 0.00048915174159046, 'samples': 8156160, 'steps': 15929, 'loss/train': 2.172797441482544}
-03/04/2022 08:10:38 - INFO - codeparrot_training - Step 15930: {'lr': 0.0004891501952500599, 'samples': 8156672, 'steps': 15930, 'loss/train': 1.408158302307129}
-03/04/2022 08:10:40 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/04/2022 08:10:43 - INFO - codeparrot_training - Step 15931: {'lr': 0.0004891486488019023, 'samples': 8157184, 'steps': 15931, 'loss/train': 2.1941165924072266}
-03/04/2022 08:10:47 - INFO - codeparrot_training - Step 15932: {'lr': 0.000489147102245988, 'samples': 8157696, 'steps': 15932, 'loss/train': 1.90802800655365}
-03/04/2022 08:10:48 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 08:10:52 - INFO - codeparrot_training - Step 15933: {'lr': 0.0004891455555823179, 'samples': 8158208, 'steps': 15933, 'loss/train': 1.3605841398239136}
-03/04/2022 08:10:55 - INFO - codeparrot_training - Step 15934: {'lr': 0.0004891440088108923, 'samples': 8158720, 'steps': 15934, 'loss/train': 2.020583391189575}
-03/04/2022 08:10:57 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 08:11:01 - INFO - codeparrot_training - Step 15935: {'lr': 0.0004891424619317121, 'samples': 8159232, 'steps': 15935, 'loss/train': 0.9181253910064697}
-03/04/2022 08:11:04 - INFO - codeparrot_training - Step 15936: {'lr': 0.000489140914944778, 'samples': 8159744, 'steps': 15936, 'loss/train': 1.0891193151474}
-03/04/2022 08:11:06 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/04/2022 08:11:09 - INFO - codeparrot_training - Step 15937: {'lr': 0.0004891393678500909, 'samples': 8160256, 'steps': 15937, 'loss/train': 1.5200639963150024}
-03/04/2022 08:11:12 - INFO - codeparrot_training - Step 15938: {'lr': 0.0004891378206476511, 'samples': 8160768, 'steps': 15938, 'loss/train': 1.6848254203796387}
-03/04/2022 08:11:14 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 08:11:17 - INFO - codeparrot_training - Step 15939: {'lr': 0.0004891362733374595, 'samples': 8161280, 'steps': 15939, 'loss/train': 1.5263921022415161}
-03/04/2022 08:11:21 - INFO - codeparrot_training - Step 15940: {'lr': 0.0004891347259195168, 'samples': 8161792, 'steps': 15940, 'loss/train': 1.1496570110321045}
-03/04/2022 08:11:23 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 08:11:26 - INFO - codeparrot_training - Step 15941: {'lr': 0.0004891331783938238, 'samples': 8162304, 'steps': 15941, 'loss/train': 1.8480569124221802}
-03/04/2022 08:11:29 - INFO - codeparrot_training - Step 15942: {'lr': 0.000489131630760381, 'samples': 8162816, 'steps': 15942, 'loss/train': 0.8411359190940857}
-03/04/2022 08:11:31 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/04/2022 08:11:34 - INFO - codeparrot_training - Step 15943: {'lr': 0.000489130083019189, 'samples': 8163328, 'steps': 15943, 'loss/train': 2.0692622661590576}
-03/04/2022 08:11:37 - INFO - codeparrot_training - Step 15944: {'lr': 0.000489128535170249, 'samples': 8163840, 'steps': 15944, 'loss/train': 2.2139692306518555}
-03/04/2022 08:11:40 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/04/2022 08:11:43 - INFO - codeparrot_training - Step 15945: {'lr': 0.0004891269872135611, 'samples': 8164352, 'steps': 15945, 'loss/train': 1.6871144771575928}
-03/04/2022 08:11:46 - INFO - codeparrot_training - Step 15946: {'lr': 0.0004891254391491264, 'samples': 8164864, 'steps': 15946, 'loss/train': 1.8881088495254517}
-03/04/2022 08:11:48 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 08:11:51 - INFO - codeparrot_training - Step 15947: {'lr': 0.0004891238909769454, 'samples': 8165376, 'steps': 15947, 'loss/train': 1.7407503128051758}
-03/04/2022 08:11:54 - INFO - codeparrot_training - Step 15948: {'lr': 0.0004891223426970189, 'samples': 8165888, 'steps': 15948, 'loss/train': 2.3193178176879883}
-03/04/2022 08:11:56 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/04/2022 08:12:00 - INFO - codeparrot_training - Step 15949: {'lr': 0.0004891207943093476, 'samples': 8166400, 'steps': 15949, 'loss/train': 1.7809083461761475}
-03/04/2022 08:12:03 - INFO - codeparrot_training - Step 15950: {'lr': 0.000489119245813932, 'samples': 8166912, 'steps': 15950, 'loss/train': 1.8434104919433594}
-03/04/2022 08:12:05 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 08:12:08 - INFO - codeparrot_training - Step 15951: {'lr': 0.0004891176972107731, 'samples': 8167424, 'steps': 15951, 'loss/train': 2.105038642883301}
-03/04/2022 08:12:11 - INFO - codeparrot_training - Step 15952: {'lr': 0.0004891161484998715, 'samples': 8167936, 'steps': 15952, 'loss/train': 1.9321300983428955}
-03/04/2022 08:12:13 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/04/2022 08:12:17 - INFO - codeparrot_training - Step 15953: {'lr': 0.0004891145996812279, 'samples': 8168448, 'steps': 15953, 'loss/train': 2.2044837474823}
-03/04/2022 08:12:20 - INFO - codeparrot_training - Step 15954: {'lr': 0.0004891130507548427, 'samples': 8168960, 'steps': 15954, 'loss/train': 1.4614242315292358}
-03/04/2022 08:12:22 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/04/2022 08:12:25 - INFO - codeparrot_training - Step 15955: {'lr': 0.000489111501720717, 'samples': 8169472, 'steps': 15955, 'loss/train': 1.4192380905151367}
-03/04/2022 08:12:28 - INFO - codeparrot_training - Step 15956: {'lr': 0.0004891099525788514, 'samples': 8169984, 'steps': 15956, 'loss/train': 2.2037250995635986}
-03/04/2022 08:12:30 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/04/2022 08:12:33 - INFO - codeparrot_training - Step 15957: {'lr': 0.0004891084033292464, 'samples': 8170496, 'steps': 15957, 'loss/train': 1.7308428287506104}
-03/04/2022 08:12:37 - INFO - codeparrot_training - Step 15958: {'lr': 0.0004891068539719031, 'samples': 8171008, 'steps': 15958, 'loss/train': 2.250924825668335}
-03/04/2022 08:12:39 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/04/2022 08:12:42 - INFO - codeparrot_training - Step 15959: {'lr': 0.0004891053045068217, 'samples': 8171520, 'steps': 15959, 'loss/train': 2.1372478008270264}
-03/04/2022 08:12:45 - INFO - codeparrot_training - Step 15960: {'lr': 0.0004891037549340032, 'samples': 8172032, 'steps': 15960, 'loss/train': 1.8430269956588745}
-03/04/2022 08:12:48 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 08:12:50 - INFO - codeparrot_training - Step 15961: {'lr': 0.0004891022052534482, 'samples': 8172544, 'steps': 15961, 'loss/train': 1.8960281610488892}
-03/04/2022 08:12:54 - INFO - codeparrot_training - Step 15962: {'lr': 0.0004891006554651574, 'samples': 8173056, 'steps': 15962, 'loss/train': 1.3815077543258667}
-03/04/2022 08:12:56 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/04/2022 08:12:59 - INFO - codeparrot_training - Step 15963: {'lr': 0.0004890991055691318, 'samples': 8173568, 'steps': 15963, 'loss/train': 1.8064050674438477}
-03/04/2022 08:13:02 - INFO - codeparrot_training - Step 15964: {'lr': 0.0004890975555653716, 'samples': 8174080, 'steps': 15964, 'loss/train': 1.4979465007781982}
-03/04/2022 08:13:04 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/04/2022 08:13:07 - INFO - codeparrot_training - Step 15965: {'lr': 0.0004890960054538778, 'samples': 8174592, 'steps': 15965, 'loss/train': 2.520284652709961}
-03/04/2022 08:13:11 - INFO - codeparrot_training - Step 15966: {'lr': 0.000489094455234651, 'samples': 8175104, 'steps': 15966, 'loss/train': 2.3158254623413086}
-03/04/2022 08:13:13 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/04/2022 08:13:16 - INFO - codeparrot_training - Step 15967: {'lr': 0.0004890929049076919, 'samples': 8175616, 'steps': 15967, 'loss/train': 1.9096425771713257}
-03/04/2022 08:13:19 - INFO - codeparrot_training - Step 15968: {'lr': 0.0004890913544730013, 'samples': 8176128, 'steps': 15968, 'loss/train': 1.879757046699524}
-03/04/2022 08:13:21 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/04/2022 08:13:24 - INFO - codeparrot_training - Step 15969: {'lr': 0.0004890898039305798, 'samples': 8176640, 'steps': 15969, 'loss/train': 1.1629698276519775}
-03/04/2022 08:13:27 - INFO - codeparrot_training - Step 15970: {'lr': 0.000489088253280428, 'samples': 8177152, 'steps': 15970, 'loss/train': 1.643641710281372}
-03/04/2022 08:13:30 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 08:13:33 - INFO - codeparrot_training - Step 15971: {'lr': 0.0004890867025225469, 'samples': 8177664, 'steps': 15971, 'loss/train': 1.6386851072311401}
-03/04/2022 08:13:36 - INFO - codeparrot_training - Step 15972: {'lr': 0.000489085151656937, 'samples': 8178176, 'steps': 15972, 'loss/train': 1.796078085899353}
-03/04/2022 08:13:38 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 08:13:41 - INFO - codeparrot_training - Step 15973: {'lr': 0.000489083600683599, 'samples': 8178688, 'steps': 15973, 'loss/train': 1.964971661567688}
-03/04/2022 08:13:44 - INFO - codeparrot_training - Step 15974: {'lr': 0.0004890820496025335, 'samples': 8179200, 'steps': 15974, 'loss/train': 2.150369167327881}
-03/04/2022 08:13:47 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 08:13:50 - INFO - codeparrot_training - Step 15975: {'lr': 0.0004890804984137415, 'samples': 8179712, 'steps': 15975, 'loss/train': 1.9185349941253662}
-03/04/2022 08:13:53 - INFO - codeparrot_training - Step 15976: {'lr': 0.0004890789471172233, 'samples': 8180224, 'steps': 15976, 'loss/train': 1.7790374755859375}
-03/04/2022 08:13:56 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 08:13:59 - INFO - codeparrot_training - Step 15977: {'lr': 0.00048907739571298, 'samples': 8180736, 'steps': 15977, 'loss/train': 1.7202320098876953}
-03/04/2022 08:14:02 - INFO - codeparrot_training - Step 15978: {'lr': 0.000489075844201012, 'samples': 8181248, 'steps': 15978, 'loss/train': 1.1985440254211426}
-03/04/2022 08:14:05 - INFO - codeparrot_training - Step 15979: {'lr': 0.0004890742925813202, 'samples': 8181760, 'steps': 15979, 'loss/train': 2.2064850330352783}
-03/04/2022 08:14:08 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 08:14:10 - INFO - codeparrot_training - Step 15980: {'lr': 0.0004890727408539051, 'samples': 8182272, 'steps': 15980, 'loss/train': 2.1215715408325195}
-03/04/2022 08:14:14 - INFO - codeparrot_training - Step 15981: {'lr': 0.0004890711890187676, 'samples': 8182784, 'steps': 15981, 'loss/train': 1.9274007081985474}
-03/04/2022 08:14:16 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/04/2022 08:14:19 - INFO - codeparrot_training - Step 15982: {'lr': 0.0004890696370759085, 'samples': 8183296, 'steps': 15982, 'loss/train': 2.704514503479004}
-03/04/2022 08:14:22 - INFO - codeparrot_training - Step 15983: {'lr': 0.0004890680850253281, 'samples': 8183808, 'steps': 15983, 'loss/train': 2.16925048828125}
-03/04/2022 08:14:24 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 08:14:27 - INFO - codeparrot_training - Step 15984: {'lr': 0.0004890665328670273, 'samples': 8184320, 'steps': 15984, 'loss/train': 2.0490660667419434}
-03/04/2022 08:14:30 - INFO - codeparrot_training - Step 15985: {'lr': 0.0004890649806010067, 'samples': 8184832, 'steps': 15985, 'loss/train': 1.6507622003555298}
-03/04/2022 08:14:32 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 08:14:36 - INFO - codeparrot_training - Step 15986: {'lr': 0.0004890634282272673, 'samples': 8185344, 'steps': 15986, 'loss/train': 1.192713975906372}
-03/04/2022 08:14:39 - INFO - codeparrot_training - Step 15987: {'lr': 0.0004890618757458096, 'samples': 8185856, 'steps': 15987, 'loss/train': 2.0257797241210938}
-03/04/2022 08:14:41 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 08:14:44 - INFO - codeparrot_training - Step 15988: {'lr': 0.0004890603231566343, 'samples': 8186368, 'steps': 15988, 'loss/train': 2.0535452365875244}
-03/04/2022 08:14:47 - INFO - codeparrot_training - Step 15989: {'lr': 0.000489058770459742, 'samples': 8186880, 'steps': 15989, 'loss/train': 1.711564302444458}
-03/04/2022 08:14:49 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/04/2022 08:14:53 - INFO - codeparrot_training - Step 15990: {'lr': 0.0004890572176551337, 'samples': 8187392, 'steps': 15990, 'loss/train': 1.0720800161361694}
-03/04/2022 08:14:56 - INFO - codeparrot_training - Step 15991: {'lr': 0.0004890556647428097, 'samples': 8187904, 'steps': 15991, 'loss/train': 2.0773980617523193}
-03/04/2022 08:14:57 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 08:15:01 - INFO - codeparrot_training - Step 15992: {'lr': 0.0004890541117227711, 'samples': 8188416, 'steps': 15992, 'loss/train': 2.21012282371521}
-03/04/2022 08:15:04 - INFO - codeparrot_training - Step 15993: {'lr': 0.0004890525585950181, 'samples': 8188928, 'steps': 15993, 'loss/train': 2.4045891761779785}
-03/04/2022 08:15:06 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/04/2022 08:15:09 - INFO - codeparrot_training - Step 15994: {'lr': 0.000489051005359552, 'samples': 8189440, 'steps': 15994, 'loss/train': 1.3287371397018433}
-03/04/2022 08:15:13 - INFO - codeparrot_training - Step 15995: {'lr': 0.0004890494520163731, 'samples': 8189952, 'steps': 15995, 'loss/train': 2.5904393196105957}
-03/04/2022 08:15:14 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/04/2022 08:15:18 - INFO - codeparrot_training - Step 15996: {'lr': 0.0004890478985654823, 'samples': 8190464, 'steps': 15996, 'loss/train': 2.031301736831665}
-03/04/2022 08:15:21 - INFO - codeparrot_training - Step 15997: {'lr': 0.0004890463450068801, 'samples': 8190976, 'steps': 15997, 'loss/train': 2.444502353668213}
-03/04/2022 08:15:22 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/04/2022 08:15:26 - INFO - codeparrot_training - Step 15998: {'lr': 0.0004890447913405673, 'samples': 8191488, 'steps': 15998, 'loss/train': 1.9029850959777832}
-03/04/2022 08:15:30 - INFO - codeparrot_training - Step 15999: {'lr': 0.0004890432375665447, 'samples': 8192000, 'steps': 15999, 'loss/train': 1.806227207183838}
-03/04/2022 08:15:31 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 08:15:35 - INFO - codeparrot_training - Step 16000: {'lr': 0.0004890416836848127, 'samples': 8192512, 'steps': 16000, 'loss/train': 2.837110996246338}
-03/04/2022 08:15:38 - INFO - codeparrot_training - Step 16001: {'lr': 0.0004890401296953723, 'samples': 8193024, 'steps': 16001, 'loss/train': 1.0709452629089355}
-03/04/2022 08:15:40 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 08:15:44 - INFO - codeparrot_training - Step 16002: {'lr': 0.0004890385755982243, 'samples': 8193536, 'steps': 16002, 'loss/train': 2.1455135345458984}
-03/04/2022 08:15:47 - INFO - codeparrot_training - Step 16003: {'lr': 0.0004890370213933691, 'samples': 8194048, 'steps': 16003, 'loss/train': 2.4262654781341553}
-03/04/2022 08:15:49 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 08:15:52 - INFO - codeparrot_training - Step 16004: {'lr': 0.0004890354670808074, 'samples': 8194560, 'steps': 16004, 'loss/train': 2.000058174133301}
-03/04/2022 08:15:55 - INFO - codeparrot_training - Step 16005: {'lr': 0.0004890339126605401, 'samples': 8195072, 'steps': 16005, 'loss/train': 2.374931573867798}
-03/04/2022 08:15:57 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 08:16:01 - INFO - codeparrot_training - Step 16006: {'lr': 0.0004890323581325677, 'samples': 8195584, 'steps': 16006, 'loss/train': 1.7162998914718628}
-03/04/2022 08:16:04 - INFO - codeparrot_training - Step 16007: {'lr': 0.0004890308034968911, 'samples': 8196096, 'steps': 16007, 'loss/train': 2.157804012298584}
-03/04/2022 08:16:06 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 08:16:09 - INFO - codeparrot_training - Step 16008: {'lr': 0.0004890292487535108, 'samples': 8196608, 'steps': 16008, 'loss/train': 1.023560643196106}
-03/04/2022 08:16:12 - INFO - codeparrot_training - Step 16009: {'lr': 0.0004890276939024278, 'samples': 8197120, 'steps': 16009, 'loss/train': 2.151146173477173}
-03/04/2022 08:16:14 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/04/2022 08:16:18 - INFO - codeparrot_training - Step 16010: {'lr': 0.0004890261389436424, 'samples': 8197632, 'steps': 16010, 'loss/train': 2.4966530799865723}
-03/04/2022 08:16:21 - INFO - codeparrot_training - Step 16011: {'lr': 0.0004890245838771557, 'samples': 8198144, 'steps': 16011, 'loss/train': 1.8235560655593872}
-03/04/2022 08:16:22 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/04/2022 08:16:26 - INFO - codeparrot_training - Step 16012: {'lr': 0.0004890230287029681, 'samples': 8198656, 'steps': 16012, 'loss/train': 2.27071475982666}
-03/04/2022 08:16:29 - INFO - codeparrot_training - Step 16013: {'lr': 0.0004890214734210805, 'samples': 8199168, 'steps': 16013, 'loss/train': 1.4055893421173096}
-03/04/2022 08:16:31 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/04/2022 08:16:35 - INFO - codeparrot_training - Step 16014: {'lr': 0.0004890199180314935, 'samples': 8199680, 'steps': 16014, 'loss/train': 1.869050145149231}
-03/04/2022 08:16:38 - INFO - codeparrot_training - Step 16015: {'lr': 0.0004890183625342078, 'samples': 8200192, 'steps': 16015, 'loss/train': 1.9164482355117798}
-03/04/2022 08:16:40 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/04/2022 08:16:43 - INFO - codeparrot_training - Step 16016: {'lr': 0.0004890168069292241, 'samples': 8200704, 'steps': 16016, 'loss/train': 1.8110665082931519}
-03/04/2022 08:16:46 - INFO - codeparrot_training - Step 16017: {'lr': 0.000489015251216543, 'samples': 8201216, 'steps': 16017, 'loss/train': 2.0182888507843018}
-03/04/2022 08:16:48 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 08:16:51 - INFO - codeparrot_training - Step 16018: {'lr': 0.0004890136953961654, 'samples': 8201728, 'steps': 16018, 'loss/train': 2.110051393508911}
-03/04/2022 08:16:55 - INFO - codeparrot_training - Step 16019: {'lr': 0.000489012139468092, 'samples': 8202240, 'steps': 16019, 'loss/train': 1.598767638206482}
-03/04/2022 08:16:56 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/04/2022 08:17:00 - INFO - codeparrot_training - Step 16020: {'lr': 0.0004890105834323233, 'samples': 8202752, 'steps': 16020, 'loss/train': 1.3805426359176636}
-03/04/2022 08:17:03 - INFO - codeparrot_training - Step 16021: {'lr': 0.0004890090272888602, 'samples': 8203264, 'steps': 16021, 'loss/train': 1.526781678199768}
-03/04/2022 08:17:04 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 08:17:08 - INFO - codeparrot_training - Step 16022: {'lr': 0.0004890074710377033, 'samples': 8203776, 'steps': 16022, 'loss/train': 1.666969656944275}
-03/04/2022 08:17:11 - INFO - codeparrot_training - Step 16023: {'lr': 0.0004890059146788532, 'samples': 8204288, 'steps': 16023, 'loss/train': 1.8739378452301025}
-03/04/2022 08:17:13 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/04/2022 08:17:17 - INFO - codeparrot_training - Step 16024: {'lr': 0.000489004358212311, 'samples': 8204800, 'steps': 16024, 'loss/train': 2.3105900287628174}
-03/04/2022 08:17:20 - INFO - codeparrot_training - Step 16025: {'lr': 0.0004890028016380769, 'samples': 8205312, 'steps': 16025, 'loss/train': 2.232114553451538}
-03/04/2022 08:17:21 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/04/2022 08:17:25 - INFO - codeparrot_training - Step 16026: {'lr': 0.0004890012449561518, 'samples': 8205824, 'steps': 16026, 'loss/train': 1.22097647190094}
-03/04/2022 08:17:28 - INFO - codeparrot_training - Step 16027: {'lr': 0.0004889996881665366, 'samples': 8206336, 'steps': 16027, 'loss/train': 2.9566426277160645}
-03/04/2022 08:17:29 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/04/2022 08:17:33 - INFO - codeparrot_training - Step 16028: {'lr': 0.0004889981312692317, 'samples': 8206848, 'steps': 16028, 'loss/train': 1.058837652206421}
-03/04/2022 08:17:37 - INFO - codeparrot_training - Step 16029: {'lr': 0.000488996574264238, 'samples': 8207360, 'steps': 16029, 'loss/train': 1.7570722103118896}
-03/04/2022 08:17:38 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/04/2022 08:17:42 - INFO - codeparrot_training - Step 16030: {'lr': 0.000488995017151556, 'samples': 8207872, 'steps': 16030, 'loss/train': 1.798453450202942}
-03/04/2022 08:17:45 - INFO - codeparrot_training - Step 16031: {'lr': 0.0004889934599311867, 'samples': 8208384, 'steps': 16031, 'loss/train': 1.3538175821304321}
-03/04/2022 08:17:46 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/04/2022 08:17:50 - INFO - codeparrot_training - Step 16032: {'lr': 0.0004889919026031306, 'samples': 8208896, 'steps': 16032, 'loss/train': 2.4699196815490723}
-03/04/2022 08:17:53 - INFO - codeparrot_training - Step 16033: {'lr': 0.0004889903451673884, 'samples': 8209408, 'steps': 16033, 'loss/train': 1.386980652809143}
-03/04/2022 08:17:54 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 08:17:59 - INFO - codeparrot_training - Step 16034: {'lr': 0.0004889887876239608, 'samples': 8209920, 'steps': 16034, 'loss/train': 1.71080482006073}
-03/04/2022 08:18:02 - INFO - codeparrot_training - Step 16035: {'lr': 0.0004889872299728486, 'samples': 8210432, 'steps': 16035, 'loss/train': 2.1239185333251953}
-03/04/2022 08:18:03 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 08:18:07 - INFO - codeparrot_training - Step 16036: {'lr': 0.0004889856722140525, 'samples': 8210944, 'steps': 16036, 'loss/train': 1.1463099718093872}
-03/04/2022 08:18:10 - INFO - codeparrot_training - Step 16037: {'lr': 0.000488984114347573, 'samples': 8211456, 'steps': 16037, 'loss/train': 2.139702796936035}
-03/04/2022 08:18:11 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/04/2022 08:18:16 - INFO - codeparrot_training - Step 16038: {'lr': 0.000488982556373411, 'samples': 8211968, 'steps': 16038, 'loss/train': 1.1784212589263916}
-03/04/2022 08:18:19 - INFO - codeparrot_training - Step 16039: {'lr': 0.0004889809982915672, 'samples': 8212480, 'steps': 16039, 'loss/train': 1.8799773454666138}
-03/04/2022 08:18:20 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/04/2022 08:18:24 - INFO - codeparrot_training - Step 16040: {'lr': 0.0004889794401020422, 'samples': 8212992, 'steps': 16040, 'loss/train': 1.89878249168396}
-03/04/2022 08:18:27 - INFO - codeparrot_training - Step 16041: {'lr': 0.0004889778818048368, 'samples': 8213504, 'steps': 16041, 'loss/train': 1.3498899936676025}
-03/04/2022 08:18:29 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 08:18:33 - INFO - codeparrot_training - Step 16042: {'lr': 0.0004889763233999516, 'samples': 8214016, 'steps': 16042, 'loss/train': 2.2422473430633545}
-03/04/2022 08:18:36 - INFO - codeparrot_training - Step 16043: {'lr': 0.0004889747648873874, 'samples': 8214528, 'steps': 16043, 'loss/train': 2.0304276943206787}
-03/04/2022 08:18:37 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/04/2022 08:18:41 - INFO - codeparrot_training - Step 16044: {'lr': 0.0004889732062671448, 'samples': 8215040, 'steps': 16044, 'loss/train': 1.253030776977539}
-03/04/2022 08:18:44 - INFO - codeparrot_training - Step 16045: {'lr': 0.0004889716475392247, 'samples': 8215552, 'steps': 16045, 'loss/train': 2.686518907546997}
-03/04/2022 08:18:46 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 08:18:50 - INFO - codeparrot_training - Step 16046: {'lr': 0.0004889700887036275, 'samples': 8216064, 'steps': 16046, 'loss/train': 2.4120290279388428}
-03/04/2022 08:18:53 - INFO - codeparrot_training - Step 16047: {'lr': 0.0004889685297603541, 'samples': 8216576, 'steps': 16047, 'loss/train': 1.7913895845413208}
-03/04/2022 08:18:54 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/04/2022 08:18:58 - INFO - codeparrot_training - Step 16048: {'lr': 0.0004889669707094052, 'samples': 8217088, 'steps': 16048, 'loss/train': 2.4196865558624268}
-03/04/2022 08:19:01 - INFO - codeparrot_training - Step 16049: {'lr': 0.0004889654115507815, 'samples': 8217600, 'steps': 16049, 'loss/train': 2.511270523071289}
-03/04/2022 08:19:03 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 08:19:06 - INFO - codeparrot_training - Step 16050: {'lr': 0.0004889638522844836, 'samples': 8218112, 'steps': 16050, 'loss/train': 2.014045000076294}
-03/04/2022 08:19:10 - INFO - codeparrot_training - Step 16051: {'lr': 0.0004889622929105123, 'samples': 8218624, 'steps': 16051, 'loss/train': 1.580773115158081}
-03/04/2022 08:19:11 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 08:19:15 - INFO - codeparrot_training - Step 16052: {'lr': 0.0004889607334288683, 'samples': 8219136, 'steps': 16052, 'loss/train': 1.9482122659683228}
-03/04/2022 08:19:18 - INFO - codeparrot_training - Step 16053: {'lr': 0.0004889591738395522, 'samples': 8219648, 'steps': 16053, 'loss/train': 1.421478509902954}
-03/04/2022 08:19:20 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 08:19:23 - INFO - codeparrot_training - Step 16054: {'lr': 0.0004889576141425649, 'samples': 8220160, 'steps': 16054, 'loss/train': 0.7449761033058167}
-03/04/2022 08:19:26 - INFO - codeparrot_training - Step 16055: {'lr': 0.0004889560543379069, 'samples': 8220672, 'steps': 16055, 'loss/train': 2.2041666507720947}
-03/04/2022 08:19:28 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/04/2022 08:19:32 - INFO - codeparrot_training - Step 16056: {'lr': 0.000488954494425579, 'samples': 8221184, 'steps': 16056, 'loss/train': 1.9152884483337402}
-03/04/2022 08:19:35 - INFO - codeparrot_training - Step 16057: {'lr': 0.000488952934405582, 'samples': 8221696, 'steps': 16057, 'loss/train': 2.0389585494995117}
-03/04/2022 08:19:36 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/04/2022 08:19:40 - INFO - codeparrot_training - Step 16058: {'lr': 0.0004889513742779164, 'samples': 8222208, 'steps': 16058, 'loss/train': 1.678281545639038}
-03/04/2022 08:19:43 - INFO - codeparrot_training - Step 16059: {'lr': 0.0004889498140425829, 'samples': 8222720, 'steps': 16059, 'loss/train': 0.624750018119812}
-03/04/2022 08:19:45 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 08:19:49 - INFO - codeparrot_training - Step 16060: {'lr': 0.0004889482536995825, 'samples': 8223232, 'steps': 16060, 'loss/train': 1.8798847198486328}
-03/04/2022 08:19:52 - INFO - codeparrot_training - Step 16061: {'lr': 0.0004889466932489157, 'samples': 8223744, 'steps': 16061, 'loss/train': 1.7294416427612305}
-03/04/2022 08:19:53 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 08:19:57 - INFO - codeparrot_training - Step 16062: {'lr': 0.0004889451326905831, 'samples': 8224256, 'steps': 16062, 'loss/train': 0.885642945766449}
-03/04/2022 08:20:00 - INFO - codeparrot_training - Step 16063: {'lr': 0.0004889435720245855, 'samples': 8224768, 'steps': 16063, 'loss/train': 1.6908111572265625}
-03/04/2022 08:20:01 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 08:20:05 - INFO - codeparrot_training - Step 16064: {'lr': 0.0004889420112509237, 'samples': 8225280, 'steps': 16064, 'loss/train': 2.0448262691497803}
-03/04/2022 08:20:09 - INFO - codeparrot_training - Step 16065: {'lr': 0.0004889404503695983, 'samples': 8225792, 'steps': 16065, 'loss/train': 1.0186573266983032}
-03/04/2022 08:20:10 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/04/2022 08:20:14 - INFO - codeparrot_training - Step 16066: {'lr': 0.0004889388893806099, 'samples': 8226304, 'steps': 16066, 'loss/train': 1.3194963932037354}
-03/04/2022 08:20:17 - INFO - codeparrot_training - Step 16067: {'lr': 0.0004889373282839594, 'samples': 8226816, 'steps': 16067, 'loss/train': 1.5543700456619263}
-03/04/2022 08:20:18 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/04/2022 08:20:23 - INFO - codeparrot_training - Step 16068: {'lr': 0.0004889357670796474, 'samples': 8227328, 'steps': 16068, 'loss/train': 2.5440874099731445}
-03/04/2022 08:20:26 - INFO - codeparrot_training - Step 16069: {'lr': 0.0004889342057676748, 'samples': 8227840, 'steps': 16069, 'loss/train': 1.768068552017212}
-03/04/2022 08:20:27 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 08:20:31 - INFO - codeparrot_training - Step 16070: {'lr': 0.000488932644348042, 'samples': 8228352, 'steps': 16070, 'loss/train': 0.25640177726745605}
-03/04/2022 08:20:34 - INFO - codeparrot_training - Step 16071: {'lr': 0.0004889310828207498, 'samples': 8228864, 'steps': 16071, 'loss/train': 1.7538979053497314}
-03/04/2022 08:20:35 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 08:20:39 - INFO - codeparrot_training - Step 16072: {'lr': 0.000488929521185799, 'samples': 8229376, 'steps': 16072, 'loss/train': 2.57619047164917}
-03/04/2022 08:20:43 - INFO - codeparrot_training - Step 16073: {'lr': 0.0004889279594431903, 'samples': 8229888, 'steps': 16073, 'loss/train': 2.501298427581787}
-03/04/2022 08:20:44 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 08:20:48 - INFO - codeparrot_training - Step 16074: {'lr': 0.0004889263975929242, 'samples': 8230400, 'steps': 16074, 'loss/train': 2.206531524658203}
-03/04/2022 08:20:51 - INFO - codeparrot_training - Step 16075: {'lr': 0.0004889248356350016, 'samples': 8230912, 'steps': 16075, 'loss/train': 0.863510012626648}
-03/04/2022 08:20:52 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/04/2022 08:20:56 - INFO - codeparrot_training - Step 16076: {'lr': 0.0004889232735694232, 'samples': 8231424, 'steps': 16076, 'loss/train': 2.0025265216827393}
-03/04/2022 08:20:59 - INFO - codeparrot_training - Step 16077: {'lr': 0.0004889217113961896, 'samples': 8231936, 'steps': 16077, 'loss/train': 1.8470087051391602}
-03/04/2022 08:21:00 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/04/2022 08:21:05 - INFO - codeparrot_training - Step 16078: {'lr': 0.0004889201491153016, 'samples': 8232448, 'steps': 16078, 'loss/train': 1.2813292741775513}
-03/04/2022 08:21:08 - INFO - codeparrot_training - Step 16079: {'lr': 0.0004889185867267599, 'samples': 8232960, 'steps': 16079, 'loss/train': 2.0163514614105225}
-03/04/2022 08:21:09 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/04/2022 08:21:13 - INFO - codeparrot_training - Step 16080: {'lr': 0.0004889170242305652, 'samples': 8233472, 'steps': 16080, 'loss/train': 1.738868236541748}
-03/04/2022 08:21:16 - INFO - codeparrot_training - Step 16081: {'lr': 0.0004889154616267181, 'samples': 8233984, 'steps': 16081, 'loss/train': 2.1362087726593018}
-03/04/2022 08:21:17 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/04/2022 08:21:21 - INFO - codeparrot_training - Step 16082: {'lr': 0.0004889138989152194, 'samples': 8234496, 'steps': 16082, 'loss/train': 2.1465413570404053}
-03/04/2022 08:21:25 - INFO - codeparrot_training - Step 16083: {'lr': 0.0004889123360960698, 'samples': 8235008, 'steps': 16083, 'loss/train': 2.540071487426758}
-03/04/2022 08:21:26 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/04/2022 08:21:30 - INFO - codeparrot_training - Step 16084: {'lr': 0.0004889107731692699, 'samples': 8235520, 'steps': 16084, 'loss/train': 2.0456109046936035}
-03/04/2022 08:21:33 - INFO - codeparrot_training - Step 16085: {'lr': 0.0004889092101348206, 'samples': 8236032, 'steps': 16085, 'loss/train': 1.906584620475769}
-03/04/2022 08:21:35 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/04/2022 08:21:38 - INFO - codeparrot_training - Step 16086: {'lr': 0.0004889076469927225, 'samples': 8236544, 'steps': 16086, 'loss/train': 1.867908239364624}
-03/04/2022 08:21:42 - INFO - codeparrot_training - Step 16087: {'lr': 0.0004889060837429762, 'samples': 8237056, 'steps': 16087, 'loss/train': 1.7816317081451416}
-03/04/2022 08:21:43 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/04/2022 08:21:47 - INFO - codeparrot_training - Step 16088: {'lr': 0.0004889045203855826, 'samples': 8237568, 'steps': 16088, 'loss/train': 1.3998560905456543}
-03/04/2022 08:21:50 - INFO - codeparrot_training - Step 16089: {'lr': 0.0004889029569205423, 'samples': 8238080, 'steps': 16089, 'loss/train': 1.6776505708694458}
-03/04/2022 08:21:52 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 08:21:55 - INFO - codeparrot_training - Step 16090: {'lr': 0.0004889013933478559, 'samples': 8238592, 'steps': 16090, 'loss/train': 2.1155169010162354}
-03/04/2022 08:21:59 - INFO - codeparrot_training - Step 16091: {'lr': 0.0004888998296675243, 'samples': 8239104, 'steps': 16091, 'loss/train': 1.6578240394592285}
-03/04/2022 08:22:00 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 08:22:04 - INFO - codeparrot_training - Step 16092: {'lr': 0.0004888982658795482, 'samples': 8239616, 'steps': 16092, 'loss/train': 1.7067776918411255}
-03/04/2022 08:22:07 - INFO - codeparrot_training - Step 16093: {'lr': 0.0004888967019839282, 'samples': 8240128, 'steps': 16093, 'loss/train': 1.858924388885498}
-03/04/2022 08:22:09 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 08:22:12 - INFO - codeparrot_training - Step 16094: {'lr': 0.000488895137980665, 'samples': 8240640, 'steps': 16094, 'loss/train': 2.258974313735962}
-03/04/2022 08:22:16 - INFO - codeparrot_training - Step 16095: {'lr': 0.0004888935738697593, 'samples': 8241152, 'steps': 16095, 'loss/train': 1.5699955224990845}
-03/04/2022 08:22:18 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 08:22:21 - INFO - codeparrot_training - Step 16096: {'lr': 0.0004888920096512118, 'samples': 8241664, 'steps': 16096, 'loss/train': 1.866520881652832}
-03/04/2022 08:22:24 - INFO - codeparrot_training - Step 16097: {'lr': 0.0004888904453250233, 'samples': 8242176, 'steps': 16097, 'loss/train': 2.166182279586792}
-03/04/2022 08:22:26 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 08:22:29 - INFO - codeparrot_training - Step 16098: {'lr': 0.0004888888808911946, 'samples': 8242688, 'steps': 16098, 'loss/train': 1.2927037477493286}
-03/04/2022 08:22:32 - INFO - codeparrot_training - Step 16099: {'lr': 0.0004888873163497261, 'samples': 8243200, 'steps': 16099, 'loss/train': 1.735762596130371}
-03/04/2022 08:22:35 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 08:22:38 - INFO - codeparrot_training - Step 16100: {'lr': 0.0004888857517006186, 'samples': 8243712, 'steps': 16100, 'loss/train': 2.1306138038635254}
-03/04/2022 08:22:41 - INFO - codeparrot_training - Step 16101: {'lr': 0.000488884186943873, 'samples': 8244224, 'steps': 16101, 'loss/train': 1.062048316001892}
-03/04/2022 08:22:43 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 08:22:46 - INFO - codeparrot_training - Step 16102: {'lr': 0.0004888826220794899, 'samples': 8244736, 'steps': 16102, 'loss/train': 1.2356011867523193}
-03/04/2022 08:22:49 - INFO - codeparrot_training - Step 16103: {'lr': 0.0004888810571074698, 'samples': 8245248, 'steps': 16103, 'loss/train': 0.996645450592041}
-03/04/2022 08:22:51 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/04/2022 08:22:54 - INFO - codeparrot_training - Step 16104: {'lr': 0.0004888794920278137, 'samples': 8245760, 'steps': 16104, 'loss/train': 1.9622377157211304}
-03/04/2022 08:22:58 - INFO - codeparrot_training - Step 16105: {'lr': 0.0004888779268405223, 'samples': 8246272, 'steps': 16105, 'loss/train': 1.7462842464447021}
-03/04/2022 08:22:59 - INFO - codeparrot_training - Skipping example with length 822 (seq_length=1024)
-03/04/2022 08:23:03 - INFO - codeparrot_training - Step 16106: {'lr': 0.0004888763615455959, 'samples': 8246784, 'steps': 16106, 'loss/train': 2.2172703742980957}
-03/04/2022 08:23:06 - INFO - codeparrot_training - Step 16107: {'lr': 0.0004888747961430358, 'samples': 8247296, 'steps': 16107, 'loss/train': 2.3934457302093506}
-03/04/2022 08:23:08 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/04/2022 08:23:12 - INFO - codeparrot_training - Step 16108: {'lr': 0.0004888732306328422, 'samples': 8247808, 'steps': 16108, 'loss/train': 2.0733537673950195}
-03/04/2022 08:23:15 - INFO - codeparrot_training - Step 16109: {'lr': 0.000488871665015016, 'samples': 8248320, 'steps': 16109, 'loss/train': 1.424755573272705}
-03/04/2022 08:23:16 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/04/2022 08:23:20 - INFO - codeparrot_training - Step 16110: {'lr': 0.0004888700992895581, 'samples': 8248832, 'steps': 16110, 'loss/train': 1.8470808267593384}
-03/04/2022 08:23:23 - INFO - codeparrot_training - Step 16111: {'lr': 0.0004888685334564688, 'samples': 8249344, 'steps': 16111, 'loss/train': 1.7087559700012207}
-03/04/2022 08:23:25 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/04/2022 08:23:28 - INFO - codeparrot_training - Step 16112: {'lr': 0.0004888669675157492, 'samples': 8249856, 'steps': 16112, 'loss/train': 1.4280099868774414}
-03/04/2022 08:23:32 - INFO - codeparrot_training - Step 16113: {'lr': 0.0004888654014673998, 'samples': 8250368, 'steps': 16113, 'loss/train': 1.9675606489181519}
-03/04/2022 08:23:33 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 08:23:37 - INFO - codeparrot_training - Step 16114: {'lr': 0.0004888638353114212, 'samples': 8250880, 'steps': 16114, 'loss/train': 1.131265640258789}
-03/04/2022 08:23:40 - INFO - codeparrot_training - Step 16115: {'lr': 0.0004888622690478144, 'samples': 8251392, 'steps': 16115, 'loss/train': 1.437040090560913}
-03/04/2022 08:23:42 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/04/2022 08:23:45 - INFO - codeparrot_training - Step 16116: {'lr': 0.0004888607026765799, 'samples': 8251904, 'steps': 16116, 'loss/train': 1.9726862907409668}
-03/04/2022 08:23:49 - INFO - codeparrot_training - Step 16117: {'lr': 0.0004888591361977184, 'samples': 8252416, 'steps': 16117, 'loss/train': 2.1556813716888428}
-03/04/2022 08:23:50 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/04/2022 08:23:54 - INFO - codeparrot_training - Step 16118: {'lr': 0.0004888575696112308, 'samples': 8252928, 'steps': 16118, 'loss/train': 1.6974804401397705}
-03/04/2022 08:23:57 - INFO - codeparrot_training - Step 16119: {'lr': 0.0004888560029171175, 'samples': 8253440, 'steps': 16119, 'loss/train': 2.380051612854004}
-03/04/2022 08:23:58 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/04/2022 08:24:02 - INFO - codeparrot_training - Step 16120: {'lr': 0.0004888544361153794, 'samples': 8253952, 'steps': 16120, 'loss/train': 1.5583192110061646}
-03/04/2022 08:24:05 - INFO - codeparrot_training - Step 16121: {'lr': 0.0004888528692060173, 'samples': 8254464, 'steps': 16121, 'loss/train': 2.51651668548584}
-03/04/2022 08:24:07 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 08:24:11 - INFO - codeparrot_training - Step 16122: {'lr': 0.0004888513021890316, 'samples': 8254976, 'steps': 16122, 'loss/train': 1.7720905542373657}
-03/04/2022 08:24:14 - INFO - codeparrot_training - Step 16123: {'lr': 0.0004888497350644234, 'samples': 8255488, 'steps': 16123, 'loss/train': 1.6488277912139893}
-03/04/2022 08:24:15 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/04/2022 08:24:19 - INFO - codeparrot_training - Step 16124: {'lr': 0.000488848167832193, 'samples': 8256000, 'steps': 16124, 'loss/train': 2.496272087097168}
-03/04/2022 08:24:22 - INFO - codeparrot_training - Step 16125: {'lr': 0.0004888466004923413, 'samples': 8256512, 'steps': 16125, 'loss/train': 3.7929582595825195}
-03/04/2022 08:24:24 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/04/2022 08:24:28 - INFO - codeparrot_training - Step 16126: {'lr': 0.0004888450330448692, 'samples': 8257024, 'steps': 16126, 'loss/train': 2.3383591175079346}
-03/04/2022 08:24:31 - INFO - codeparrot_training - Step 16127: {'lr': 0.000488843465489777, 'samples': 8257536, 'steps': 16127, 'loss/train': 1.2399309873580933}
-03/04/2022 08:24:32 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 08:24:36 - INFO - codeparrot_training - Step 16128: {'lr': 0.0004888418978270658, 'samples': 8258048, 'steps': 16128, 'loss/train': 2.023458957672119}
-03/04/2022 08:24:39 - INFO - codeparrot_training - Step 16129: {'lr': 0.000488840330056736, 'samples': 8258560, 'steps': 16129, 'loss/train': 0.867405116558075}
-03/04/2022 08:24:40 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 08:24:44 - INFO - codeparrot_training - Step 16130: {'lr': 0.0004888387621787885, 'samples': 8259072, 'steps': 16130, 'loss/train': 1.700221300125122}
-03/04/2022 08:24:47 - INFO - codeparrot_training - Step 16131: {'lr': 0.0004888371941932239, 'samples': 8259584, 'steps': 16131, 'loss/train': 2.6374945640563965}
-03/04/2022 08:24:49 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/04/2022 08:24:53 - INFO - codeparrot_training - Step 16132: {'lr': 0.000488835626100043, 'samples': 8260096, 'steps': 16132, 'loss/train': 1.8760226964950562}
-03/04/2022 08:24:56 - INFO - codeparrot_training - Step 16133: {'lr': 0.0004888340578992464, 'samples': 8260608, 'steps': 16133, 'loss/train': 2.160445213317871}
-03/04/2022 08:24:57 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 08:25:01 - INFO - codeparrot_training - Step 16134: {'lr': 0.0004888324895908349, 'samples': 8261120, 'steps': 16134, 'loss/train': 1.2084697484970093}
-03/04/2022 08:25:04 - INFO - codeparrot_training - Step 16135: {'lr': 0.0004888309211748091, 'samples': 8261632, 'steps': 16135, 'loss/train': 2.1752138137817383}
-03/04/2022 08:25:06 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/04/2022 08:25:09 - INFO - codeparrot_training - Step 16136: {'lr': 0.0004888293526511697, 'samples': 8262144, 'steps': 16136, 'loss/train': 1.3664453029632568}
-03/04/2022 08:25:13 - INFO - codeparrot_training - Step 16137: {'lr': 0.0004888277840199177, 'samples': 8262656, 'steps': 16137, 'loss/train': 1.881345510482788}
-03/04/2022 08:25:14 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 08:25:18 - INFO - codeparrot_training - Step 16138: {'lr': 0.0004888262152810534, 'samples': 8263168, 'steps': 16138, 'loss/train': 2.372832775115967}
-03/04/2022 08:25:21 - INFO - codeparrot_training - Step 16139: {'lr': 0.0004888246464345779, 'samples': 8263680, 'steps': 16139, 'loss/train': 1.2288739681243896}
-03/04/2022 08:25:23 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/04/2022 08:25:26 - INFO - codeparrot_training - Step 16140: {'lr': 0.0004888230774804915, 'samples': 8264192, 'steps': 16140, 'loss/train': 1.8634742498397827}
-03/04/2022 08:25:30 - INFO - codeparrot_training - Step 16141: {'lr': 0.0004888215084187952, 'samples': 8264704, 'steps': 16141, 'loss/train': 1.641205072402954}
-03/04/2022 08:25:31 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/04/2022 08:25:35 - INFO - codeparrot_training - Step 16142: {'lr': 0.0004888199392494896, 'samples': 8265216, 'steps': 16142, 'loss/train': 1.8594779968261719}
-03/04/2022 08:25:38 - INFO - codeparrot_training - Step 16143: {'lr': 0.0004888183699725755, 'samples': 8265728, 'steps': 16143, 'loss/train': 1.2768545150756836}
-03/04/2022 08:25:39 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 08:25:43 - INFO - codeparrot_training - Step 16144: {'lr': 0.0004888168005880533, 'samples': 8266240, 'steps': 16144, 'loss/train': 2.348010540008545}
-03/04/2022 08:25:46 - INFO - codeparrot_training - Step 16145: {'lr': 0.0004888152310959242, 'samples': 8266752, 'steps': 16145, 'loss/train': 2.1777427196502686}
-03/04/2022 08:25:48 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/04/2022 08:25:52 - INFO - codeparrot_training - Step 16146: {'lr': 0.0004888136614961885, 'samples': 8267264, 'steps': 16146, 'loss/train': 2.066293716430664}
-03/04/2022 08:25:55 - INFO - codeparrot_training - Step 16147: {'lr': 0.000488812091788847, 'samples': 8267776, 'steps': 16147, 'loss/train': 2.361811399459839}
-03/04/2022 08:25:56 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/04/2022 08:26:00 - INFO - codeparrot_training - Step 16148: {'lr': 0.0004888105219739005, 'samples': 8268288, 'steps': 16148, 'loss/train': 1.4620476961135864}
-03/04/2022 08:26:03 - INFO - codeparrot_training - Step 16149: {'lr': 0.0004888089520513497, 'samples': 8268800, 'steps': 16149, 'loss/train': 1.6388620138168335}
-03/04/2022 08:26:04 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/04/2022 08:26:09 - INFO - codeparrot_training - Step 16150: {'lr': 0.0004888073820211952, 'samples': 8269312, 'steps': 16150, 'loss/train': 1.579231858253479}
-03/04/2022 08:26:12 - INFO - codeparrot_training - Step 16151: {'lr': 0.0004888058118834379, 'samples': 8269824, 'steps': 16151, 'loss/train': 1.775742769241333}
-03/04/2022 08:26:13 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/04/2022 08:26:17 - INFO - codeparrot_training - Step 16152: {'lr': 0.0004888042416380784, 'samples': 8270336, 'steps': 16152, 'loss/train': 2.6505253314971924}
-03/04/2022 08:26:21 - INFO - codeparrot_training - Step 16153: {'lr': 0.0004888026712851172, 'samples': 8270848, 'steps': 16153, 'loss/train': 1.5418152809143066}
-03/04/2022 08:26:21 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/04/2022 08:26:26 - INFO - codeparrot_training - Step 16154: {'lr': 0.0004888011008245554, 'samples': 8271360, 'steps': 16154, 'loss/train': 2.11429500579834}
-03/04/2022 08:26:29 - INFO - codeparrot_training - Step 16155: {'lr': 0.0004887995302563934, 'samples': 8271872, 'steps': 16155, 'loss/train': 2.352250576019287}
-03/04/2022 08:26:30 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/04/2022 08:26:34 - INFO - codeparrot_training - Step 16156: {'lr': 0.000488797959580632, 'samples': 8272384, 'steps': 16156, 'loss/train': 1.414434552192688}
-03/04/2022 08:26:37 - INFO - codeparrot_training - Step 16157: {'lr': 0.000488796388797272, 'samples': 8272896, 'steps': 16157, 'loss/train': 0.6504292488098145}
-03/04/2022 08:26:39 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/04/2022 08:26:43 - INFO - codeparrot_training - Step 16158: {'lr': 0.0004887948179063139, 'samples': 8273408, 'steps': 16158, 'loss/train': 1.564260482788086}
-03/04/2022 08:26:46 - INFO - codeparrot_training - Step 16159: {'lr': 0.0004887932469077587, 'samples': 8273920, 'steps': 16159, 'loss/train': 1.779106855392456}
-03/04/2022 08:26:47 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/04/2022 08:26:51 - INFO - codeparrot_training - Step 16160: {'lr': 0.0004887916758016069, 'samples': 8274432, 'steps': 16160, 'loss/train': 1.971617579460144}
-03/04/2022 08:26:54 - INFO - codeparrot_training - Step 16161: {'lr': 0.0004887901045878592, 'samples': 8274944, 'steps': 16161, 'loss/train': 2.1870310306549072}
-03/04/2022 08:26:55 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 08:27:00 - INFO - codeparrot_training - Step 16162: {'lr': 0.0004887885332665165, 'samples': 8275456, 'steps': 16162, 'loss/train': 1.8949812650680542}
-03/04/2022 08:27:03 - INFO - codeparrot_training - Step 16163: {'lr': 0.0004887869618375793, 'samples': 8275968, 'steps': 16163, 'loss/train': 1.8161934614181519}
-03/04/2022 08:27:04 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/04/2022 08:27:08 - INFO - codeparrot_training - Step 16164: {'lr': 0.0004887853903010483, 'samples': 8276480, 'steps': 16164, 'loss/train': 2.1300110816955566}
-03/04/2022 08:27:11 - INFO - codeparrot_training - Step 16165: {'lr': 0.0004887838186569244, 'samples': 8276992, 'steps': 16165, 'loss/train': 1.3764344453811646}
-03/04/2022 08:27:12 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 08:27:17 - INFO - codeparrot_training - Step 16166: {'lr': 0.0004887822469052081, 'samples': 8277504, 'steps': 16166, 'loss/train': 1.259840488433838}
-03/04/2022 08:27:20 - INFO - codeparrot_training - Step 16167: {'lr': 0.0004887806750459002, 'samples': 8278016, 'steps': 16167, 'loss/train': 1.6597380638122559}
-03/04/2022 08:27:21 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/04/2022 08:27:25 - INFO - codeparrot_training - Step 16168: {'lr': 0.0004887791030790016, 'samples': 8278528, 'steps': 16168, 'loss/train': 1.7345441579818726}
-03/04/2022 08:27:28 - INFO - codeparrot_training - Step 16169: {'lr': 0.0004887775310045126, 'samples': 8279040, 'steps': 16169, 'loss/train': 2.454425096511841}
-03/04/2022 08:27:29 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 08:27:34 - INFO - codeparrot_training - Step 16170: {'lr': 0.0004887759588224342, 'samples': 8279552, 'steps': 16170, 'loss/train': 2.3924410343170166}
-03/04/2022 08:27:37 - INFO - codeparrot_training - Step 16171: {'lr': 0.000488774386532767, 'samples': 8280064, 'steps': 16171, 'loss/train': 1.7405668497085571}
-03/04/2022 08:27:38 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/04/2022 08:27:42 - INFO - codeparrot_training - Step 16172: {'lr': 0.0004887728141355118, 'samples': 8280576, 'steps': 16172, 'loss/train': 2.053586721420288}
-03/04/2022 08:27:45 - INFO - codeparrot_training - Step 16173: {'lr': 0.0004887712416306693, 'samples': 8281088, 'steps': 16173, 'loss/train': 1.695051670074463}
-03/04/2022 08:27:47 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/04/2022 08:27:50 - INFO - codeparrot_training - Step 16174: {'lr': 0.00048876966901824, 'samples': 8281600, 'steps': 16174, 'loss/train': 1.518394947052002}
-03/04/2022 08:27:54 - INFO - codeparrot_training - Step 16175: {'lr': 0.0004887680962982249, 'samples': 8282112, 'steps': 16175, 'loss/train': 2.001528739929199}
-03/04/2022 08:27:55 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 08:27:59 - INFO - codeparrot_training - Step 16176: {'lr': 0.0004887665234706247, 'samples': 8282624, 'steps': 16176, 'loss/train': 2.5772359371185303}
-03/04/2022 08:28:02 - INFO - codeparrot_training - Step 16177: {'lr': 0.0004887649505354398, 'samples': 8283136, 'steps': 16177, 'loss/train': 0.8842549324035645}
-03/04/2022 08:28:04 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 08:28:08 - INFO - codeparrot_training - Step 16178: {'lr': 0.000488763377492671, 'samples': 8283648, 'steps': 16178, 'loss/train': 1.412381649017334}
-03/04/2022 08:28:11 - INFO - codeparrot_training - Step 16179: {'lr': 0.0004887618043423194, 'samples': 8284160, 'steps': 16179, 'loss/train': 1.6233022212982178}
-03/04/2022 08:28:13 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 08:28:16 - INFO - codeparrot_training - Step 16180: {'lr': 0.0004887602310843852, 'samples': 8284672, 'steps': 16180, 'loss/train': 2.275810956954956}
-03/04/2022 08:28:19 - INFO - codeparrot_training - Step 16181: {'lr': 0.0004887586577188694, 'samples': 8285184, 'steps': 16181, 'loss/train': 2.532498836517334}
-03/04/2022 08:28:22 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 08:28:24 - INFO - codeparrot_training - Step 16182: {'lr': 0.0004887570842457726, 'samples': 8285696, 'steps': 16182, 'loss/train': 1.252089500427246}
-03/04/2022 08:28:28 - INFO - codeparrot_training - Step 16183: {'lr': 0.0004887555106650956, 'samples': 8286208, 'steps': 16183, 'loss/train': 1.5297998189926147}
-03/04/2022 08:28:30 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/04/2022 08:28:33 - INFO - codeparrot_training - Step 16184: {'lr': 0.000488753936976839, 'samples': 8286720, 'steps': 16184, 'loss/train': 1.6619635820388794}
-03/04/2022 08:28:36 - INFO - codeparrot_training - Step 16185: {'lr': 0.0004887523631810036, 'samples': 8287232, 'steps': 16185, 'loss/train': 1.5206786394119263}
-03/04/2022 08:28:39 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/04/2022 08:28:41 - INFO - codeparrot_training - Step 16186: {'lr': 0.00048875078927759, 'samples': 8287744, 'steps': 16186, 'loss/train': 2.6936628818511963}
-03/04/2022 08:28:45 - INFO - codeparrot_training - Step 16187: {'lr': 0.000488749215266599, 'samples': 8288256, 'steps': 16187, 'loss/train': 1.905018925666809}
-03/04/2022 08:28:47 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/04/2022 08:28:50 - INFO - codeparrot_training - Step 16188: {'lr': 0.0004887476411480314, 'samples': 8288768, 'steps': 16188, 'loss/train': 1.834274411201477}
-03/04/2022 08:28:53 - INFO - codeparrot_training - Step 16189: {'lr': 0.0004887460669218877, 'samples': 8289280, 'steps': 16189, 'loss/train': 1.703017234802246}
-03/04/2022 08:28:56 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/04/2022 08:28:58 - INFO - codeparrot_training - Step 16190: {'lr': 0.0004887444925881688, 'samples': 8289792, 'steps': 16190, 'loss/train': 2.132237195968628}
-03/04/2022 08:29:01 - INFO - codeparrot_training - Step 16191: {'lr': 0.0004887429181468752, 'samples': 8290304, 'steps': 16191, 'loss/train': 2.9703009128570557}
-03/04/2022 08:29:04 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/04/2022 08:29:07 - INFO - codeparrot_training - Step 16192: {'lr': 0.0004887413435980077, 'samples': 8290816, 'steps': 16192, 'loss/train': 1.3766413927078247}
-03/04/2022 08:29:11 - INFO - codeparrot_training - Step 16193: {'lr': 0.0004887397689415672, 'samples': 8291328, 'steps': 16193, 'loss/train': 0.9252809882164001}
-03/04/2022 08:29:14 - INFO - codeparrot_training - Step 16194: {'lr': 0.0004887381941775541, 'samples': 8291840, 'steps': 16194, 'loss/train': 2.2073724269866943}
-03/04/2022 08:29:16 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/04/2022 08:29:19 - INFO - codeparrot_training - Step 16195: {'lr': 0.0004887366193059693, 'samples': 8292352, 'steps': 16195, 'loss/train': 1.4966994524002075}
-03/04/2022 08:29:22 - INFO - codeparrot_training - Step 16196: {'lr': 0.0004887350443268134, 'samples': 8292864, 'steps': 16196, 'loss/train': 1.479994297027588}
-03/04/2022 08:29:24 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 08:29:27 - INFO - codeparrot_training - Step 16197: {'lr': 0.0004887334692400872, 'samples': 8293376, 'steps': 16197, 'loss/train': 2.2081053256988525}
-03/04/2022 08:29:30 - INFO - codeparrot_training - Step 16198: {'lr': 0.0004887318940457915, 'samples': 8293888, 'steps': 16198, 'loss/train': 1.5185822248458862}
-03/04/2022 08:29:32 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 08:29:36 - INFO - codeparrot_training - Step 16199: {'lr': 0.0004887303187439267, 'samples': 8294400, 'steps': 16199, 'loss/train': 1.6668519973754883}
-03/04/2022 08:29:39 - INFO - codeparrot_training - Step 16200: {'lr': 0.0004887287433344939, 'samples': 8294912, 'steps': 16200, 'loss/train': 1.736337661743164}
-03/04/2022 08:29:42 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 08:29:44 - INFO - codeparrot_training - Step 16201: {'lr': 0.0004887271678174935, 'samples': 8295424, 'steps': 16201, 'loss/train': 2.709927797317505}
-03/04/2022 08:29:48 - INFO - codeparrot_training - Step 16202: {'lr': 0.0004887255921929264, 'samples': 8295936, 'steps': 16202, 'loss/train': 2.1274397373199463}
-03/04/2022 08:29:50 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/04/2022 08:29:53 - INFO - codeparrot_training - Step 16203: {'lr': 0.0004887240164607931, 'samples': 8296448, 'steps': 16203, 'loss/train': 2.7359538078308105}
-03/04/2022 08:29:56 - INFO - codeparrot_training - Step 16204: {'lr': 0.0004887224406210945, 'samples': 8296960, 'steps': 16204, 'loss/train': 2.073945999145508}
-03/04/2022 08:29:59 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 08:30:01 - INFO - codeparrot_training - Step 16205: {'lr': 0.0004887208646738312, 'samples': 8297472, 'steps': 16205, 'loss/train': 1.4177926778793335}
-03/04/2022 08:30:05 - INFO - codeparrot_training - Step 16206: {'lr': 0.000488719288619004, 'samples': 8297984, 'steps': 16206, 'loss/train': 0.8719953894615173}
-03/04/2022 08:30:07 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/04/2022 08:30:10 - INFO - codeparrot_training - Step 16207: {'lr': 0.0004887177124566136, 'samples': 8298496, 'steps': 16207, 'loss/train': 1.8617607355117798}
-03/04/2022 08:30:13 - INFO - codeparrot_training - Step 16208: {'lr': 0.0004887161361866607, 'samples': 8299008, 'steps': 16208, 'loss/train': 6.998103141784668}
-03/04/2022 08:30:15 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 08:30:18 - INFO - codeparrot_training - Step 16209: {'lr': 0.000488714559809146, 'samples': 8299520, 'steps': 16209, 'loss/train': 1.85304594039917}
-03/04/2022 08:30:21 - INFO - codeparrot_training - Step 16210: {'lr': 0.0004887129833240703, 'samples': 8300032, 'steps': 16210, 'loss/train': 2.4427542686462402}
-03/04/2022 08:30:23 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 08:30:27 - INFO - codeparrot_training - Step 16211: {'lr': 0.000488711406731434, 'samples': 8300544, 'steps': 16211, 'loss/train': 1.6055783033370972}
-03/04/2022 08:30:30 - INFO - codeparrot_training - Step 16212: {'lr': 0.0004887098300312381, 'samples': 8301056, 'steps': 16212, 'loss/train': 1.6247010231018066}
-03/04/2022 08:30:32 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/04/2022 08:30:35 - INFO - codeparrot_training - Step 16213: {'lr': 0.0004887082532234832, 'samples': 8301568, 'steps': 16213, 'loss/train': 1.6986756324768066}
-03/04/2022 08:30:38 - INFO - codeparrot_training - Step 16214: {'lr': 0.0004887066763081702, 'samples': 8302080, 'steps': 16214, 'loss/train': 1.5028762817382812}
-03/04/2022 08:30:40 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/04/2022 08:30:44 - INFO - codeparrot_training - Step 16215: {'lr': 0.0004887050992852995, 'samples': 8302592, 'steps': 16215, 'loss/train': 2.176476240158081}
-03/04/2022 08:30:47 - INFO - codeparrot_training - Step 16216: {'lr': 0.000488703522154872, 'samples': 8303104, 'steps': 16216, 'loss/train': 1.727066159248352}
-03/04/2022 08:30:49 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 08:30:52 - INFO - codeparrot_training - Step 16217: {'lr': 0.0004887019449168884, 'samples': 8303616, 'steps': 16217, 'loss/train': 0.5155454874038696}
-03/04/2022 08:30:55 - INFO - codeparrot_training - Step 16218: {'lr': 0.0004887003675713493, 'samples': 8304128, 'steps': 16218, 'loss/train': 2.167361259460449}
-03/04/2022 08:30:57 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/04/2022 08:31:01 - INFO - codeparrot_training - Step 16219: {'lr': 0.0004886987901182556, 'samples': 8304640, 'steps': 16219, 'loss/train': 1.8261597156524658}
-03/04/2022 08:31:04 - INFO - codeparrot_training - Step 16220: {'lr': 0.0004886972125576079, 'samples': 8305152, 'steps': 16220, 'loss/train': 1.7096847295761108}
-03/04/2022 08:31:06 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/04/2022 08:31:09 - INFO - codeparrot_training - Step 16221: {'lr': 0.0004886956348894069, 'samples': 8305664, 'steps': 16221, 'loss/train': 2.0300941467285156}
-03/04/2022 08:31:12 - INFO - codeparrot_training - Step 16222: {'lr': 0.0004886940571136533, 'samples': 8306176, 'steps': 16222, 'loss/train': 2.0135064125061035}
-03/04/2022 08:31:14 - INFO - codeparrot_training - Skipping example with length 524 (seq_length=1024)
-03/04/2022 08:31:18 - INFO - codeparrot_training - Step 16223: {'lr': 0.0004886924792303479, 'samples': 8306688, 'steps': 16223, 'loss/train': 2.2782342433929443}
-03/04/2022 08:31:21 - INFO - codeparrot_training - Step 16224: {'lr': 0.0004886909012394913, 'samples': 8307200, 'steps': 16224, 'loss/train': 1.7928155660629272}
-03/04/2022 08:31:23 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/04/2022 08:31:26 - INFO - codeparrot_training - Step 16225: {'lr': 0.0004886893231410844, 'samples': 8307712, 'steps': 16225, 'loss/train': 1.1453008651733398}
-03/04/2022 08:31:29 - INFO - codeparrot_training - Step 16226: {'lr': 0.0004886877449351276, 'samples': 8308224, 'steps': 16226, 'loss/train': 1.9457550048828125}
-03/04/2022 08:31:32 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/04/2022 08:31:35 - INFO - codeparrot_training - Step 16227: {'lr': 0.0004886861666216219, 'samples': 8308736, 'steps': 16227, 'loss/train': 2.231879472732544}
-03/04/2022 08:31:38 - INFO - codeparrot_training - Step 16228: {'lr': 0.0004886845882005679, 'samples': 8309248, 'steps': 16228, 'loss/train': 2.0991926193237305}
-03/04/2022 08:31:40 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/04/2022 08:31:43 - INFO - codeparrot_training - Step 16229: {'lr': 0.0004886830096719662, 'samples': 8309760, 'steps': 16229, 'loss/train': 2.0748748779296875}
-03/04/2022 08:31:46 - INFO - codeparrot_training - Step 16230: {'lr': 0.0004886814310358176, 'samples': 8310272, 'steps': 16230, 'loss/train': 1.8112804889678955}
-03/04/2022 08:31:48 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/04/2022 08:31:51 - INFO - codeparrot_training - Step 16231: {'lr': 0.000488679852292123, 'samples': 8310784, 'steps': 16231, 'loss/train': 1.3747007846832275}
-03/04/2022 08:31:55 - INFO - codeparrot_training - Step 16232: {'lr': 0.0004886782734408828, 'samples': 8311296, 'steps': 16232, 'loss/train': 1.6902848482131958}
-03/04/2022 08:31:57 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 08:32:00 - INFO - codeparrot_training - Step 16233: {'lr': 0.0004886766944820979, 'samples': 8311808, 'steps': 16233, 'loss/train': 1.6983884572982788}
-03/04/2022 08:32:03 - INFO - codeparrot_training - Step 16234: {'lr': 0.0004886751154157689, 'samples': 8312320, 'steps': 16234, 'loss/train': 1.8751786947250366}
-03/04/2022 08:32:05 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/04/2022 08:32:08 - INFO - codeparrot_training - Step 16235: {'lr': 0.0004886735362418967, 'samples': 8312832, 'steps': 16235, 'loss/train': 0.4464772939682007}
-03/04/2022 08:32:11 - INFO - codeparrot_training - Step 16236: {'lr': 0.0004886719569604818, 'samples': 8313344, 'steps': 16236, 'loss/train': 1.763805627822876}
-03/04/2022 08:32:14 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/04/2022 08:32:17 - INFO - codeparrot_training - Step 16237: {'lr': 0.000488670377571525, 'samples': 8313856, 'steps': 16237, 'loss/train': 1.3114837408065796}
-03/04/2022 08:32:20 - INFO - codeparrot_training - Step 16238: {'lr': 0.0004886687980750271, 'samples': 8314368, 'steps': 16238, 'loss/train': 2.2473745346069336}
-03/04/2022 08:32:22 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 08:32:25 - INFO - codeparrot_training - Step 16239: {'lr': 0.0004886672184709886, 'samples': 8314880, 'steps': 16239, 'loss/train': 2.284607410430908}
-03/04/2022 08:32:28 - INFO - codeparrot_training - Step 16240: {'lr': 0.0004886656387594104, 'samples': 8315392, 'steps': 16240, 'loss/train': 2.138957977294922}
-03/04/2022 08:32:30 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 08:32:34 - INFO - codeparrot_training - Step 16241: {'lr': 0.0004886640589402932, 'samples': 8315904, 'steps': 16241, 'loss/train': 1.9323773384094238}
-03/04/2022 08:32:37 - INFO - codeparrot_training - Step 16242: {'lr': 0.0004886624790136375, 'samples': 8316416, 'steps': 16242, 'loss/train': 1.8334922790527344}
-03/04/2022 08:32:39 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/04/2022 08:32:42 - INFO - codeparrot_training - Step 16243: {'lr': 0.0004886608989794443, 'samples': 8316928, 'steps': 16243, 'loss/train': 2.8203155994415283}
-03/04/2022 08:32:45 - INFO - codeparrot_training - Step 16244: {'lr': 0.0004886593188377142, 'samples': 8317440, 'steps': 16244, 'loss/train': 1.8669228553771973}
-03/04/2022 08:32:47 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 08:32:51 - INFO - codeparrot_training - Step 16245: {'lr': 0.0004886577385884478, 'samples': 8317952, 'steps': 16245, 'loss/train': 2.733999013900757}
-03/04/2022 08:32:54 - INFO - codeparrot_training - Step 16246: {'lr': 0.0004886561582316458, 'samples': 8318464, 'steps': 16246, 'loss/train': 2.389343023300171}
-03/04/2022 08:32:57 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/04/2022 08:32:59 - INFO - codeparrot_training - Step 16247: {'lr': 0.0004886545777673093, 'samples': 8318976, 'steps': 16247, 'loss/train': 1.3846372365951538}
-03/04/2022 08:33:02 - INFO - codeparrot_training - Step 16248: {'lr': 0.0004886529971954385, 'samples': 8319488, 'steps': 16248, 'loss/train': 2.1152260303497314}
-03/04/2022 08:33:05 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 08:33:08 - INFO - codeparrot_training - Step 16249: {'lr': 0.0004886514165160345, 'samples': 8320000, 'steps': 16249, 'loss/train': 1.9478179216384888}
-03/04/2022 08:33:11 - INFO - codeparrot_training - Step 16250: {'lr': 0.0004886498357290979, 'samples': 8320512, 'steps': 16250, 'loss/train': 2.284682273864746}
-03/04/2022 08:33:13 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/04/2022 08:33:16 - INFO - codeparrot_training - Step 16251: {'lr': 0.0004886482548346291, 'samples': 8321024, 'steps': 16251, 'loss/train': 1.765131950378418}
-03/04/2022 08:33:19 - INFO - codeparrot_training - Step 16252: {'lr': 0.0004886466738326293, 'samples': 8321536, 'steps': 16252, 'loss/train': 2.0178256034851074}
-03/04/2022 08:33:22 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/04/2022 08:33:25 - INFO - codeparrot_training - Step 16253: {'lr': 0.000488645092723099, 'samples': 8322048, 'steps': 16253, 'loss/train': 2.428711414337158}
-03/04/2022 08:33:28 - INFO - codeparrot_training - Step 16254: {'lr': 0.0004886435115060388, 'samples': 8322560, 'steps': 16254, 'loss/train': 2.002218008041382}
-03/04/2022 08:33:30 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/04/2022 08:33:33 - INFO - codeparrot_training - Step 16255: {'lr': 0.0004886419301814495, 'samples': 8323072, 'steps': 16255, 'loss/train': 1.0418208837509155}
-03/04/2022 08:33:36 - INFO - codeparrot_training - Step 16256: {'lr': 0.0004886403487493319, 'samples': 8323584, 'steps': 16256, 'loss/train': 1.7002395391464233}
-03/04/2022 08:33:38 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/04/2022 08:33:41 - INFO - codeparrot_training - Step 16257: {'lr': 0.0004886387672096866, 'samples': 8324096, 'steps': 16257, 'loss/train': 2.1541051864624023}
-03/04/2022 08:33:45 - INFO - codeparrot_training - Step 16258: {'lr': 0.0004886371855625143, 'samples': 8324608, 'steps': 16258, 'loss/train': 1.1288487911224365}
-03/04/2022 08:33:47 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/04/2022 08:33:50 - INFO - codeparrot_training - Step 16259: {'lr': 0.0004886356038078159, 'samples': 8325120, 'steps': 16259, 'loss/train': 1.866613507270813}
-03/04/2022 08:33:53 - INFO - codeparrot_training - Step 16260: {'lr': 0.0004886340219455919, 'samples': 8325632, 'steps': 16260, 'loss/train': 2.0085225105285645}
-03/04/2022 08:33:55 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/04/2022 08:33:58 - INFO - codeparrot_training - Step 16261: {'lr': 0.0004886324399758431, 'samples': 8326144, 'steps': 16261, 'loss/train': 2.328104257583618}
-03/04/2022 08:34:01 - INFO - codeparrot_training - Step 16262: {'lr': 0.0004886308578985702, 'samples': 8326656, 'steps': 16262, 'loss/train': 0.9662577509880066}
-03/04/2022 08:34:03 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 08:34:07 - INFO - codeparrot_training - Step 16263: {'lr': 0.0004886292757137739, 'samples': 8327168, 'steps': 16263, 'loss/train': 1.5578356981277466}
-03/04/2022 08:34:10 - INFO - codeparrot_training - Step 16264: {'lr': 0.0004886276934214551, 'samples': 8327680, 'steps': 16264, 'loss/train': 1.5682373046875}
-03/04/2022 08:34:13 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 08:34:15 - INFO - codeparrot_training - Step 16265: {'lr': 0.0004886261110216141, 'samples': 8328192, 'steps': 16265, 'loss/train': 1.538379192352295}
-03/04/2022 08:34:18 - INFO - codeparrot_training - Step 16266: {'lr': 0.000488624528514252, 'samples': 8328704, 'steps': 16266, 'loss/train': 1.9214611053466797}
-03/04/2022 08:34:21 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/04/2022 08:34:24 - INFO - codeparrot_training - Step 16267: {'lr': 0.0004886229458993693, 'samples': 8329216, 'steps': 16267, 'loss/train': 1.781991720199585}
-03/04/2022 08:34:27 - INFO - codeparrot_training - Step 16268: {'lr': 0.0004886213631769669, 'samples': 8329728, 'steps': 16268, 'loss/train': 2.1212308406829834}
-03/04/2022 08:34:30 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/04/2022 08:34:32 - INFO - codeparrot_training - Step 16269: {'lr': 0.0004886197803470453, 'samples': 8330240, 'steps': 16269, 'loss/train': 1.99233078956604}
-03/04/2022 08:34:35 - INFO - codeparrot_training - Step 16270: {'lr': 0.0004886181974096052, 'samples': 8330752, 'steps': 16270, 'loss/train': 1.4627552032470703}
-03/04/2022 08:34:38 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/04/2022 08:34:41 - INFO - codeparrot_training - Step 16271: {'lr': 0.0004886166143646476, 'samples': 8331264, 'steps': 16271, 'loss/train': 1.8879719972610474}
-03/04/2022 08:34:44 - INFO - codeparrot_training - Step 16272: {'lr': 0.000488615031212173, 'samples': 8331776, 'steps': 16272, 'loss/train': 1.8473461866378784}
-03/04/2022 08:34:47 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/04/2022 08:34:49 - INFO - codeparrot_training - Step 16273: {'lr': 0.0004886134479521821, 'samples': 8332288, 'steps': 16273, 'loss/train': 1.276752233505249}
-03/04/2022 08:34:52 - INFO - codeparrot_training - Step 16274: {'lr': 0.0004886118645846757, 'samples': 8332800, 'steps': 16274, 'loss/train': 1.794073462486267}
-03/04/2022 08:34:55 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 08:34:57 - INFO - codeparrot_training - Step 16275: {'lr': 0.0004886102811096544, 'samples': 8333312, 'steps': 16275, 'loss/train': 1.6298946142196655}
-03/04/2022 08:35:01 - INFO - codeparrot_training - Step 16276: {'lr': 0.0004886086975271191, 'samples': 8333824, 'steps': 16276, 'loss/train': 2.318837881088257}
-03/04/2022 08:35:03 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/04/2022 08:35:06 - INFO - codeparrot_training - Step 16277: {'lr': 0.0004886071138370704, 'samples': 8334336, 'steps': 16277, 'loss/train': 2.6901960372924805}
-03/04/2022 08:35:09 - INFO - codeparrot_training - Step 16278: {'lr': 0.000488605530039509, 'samples': 8334848, 'steps': 16278, 'loss/train': 2.326103448867798}
-03/04/2022 08:35:11 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/04/2022 08:35:14 - INFO - codeparrot_training - Step 16279: {'lr': 0.0004886039461344356, 'samples': 8335360, 'steps': 16279, 'loss/train': 2.022749900817871}
-03/04/2022 08:35:17 - INFO - codeparrot_training - Step 16280: {'lr': 0.0004886023621218509, 'samples': 8335872, 'steps': 16280, 'loss/train': 1.428017497062683}
-03/04/2022 08:35:20 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 08:35:23 - INFO - codeparrot_training - Step 16281: {'lr': 0.0004886007780017557, 'samples': 8336384, 'steps': 16281, 'loss/train': 2.040410280227661}
-03/04/2022 08:35:26 - INFO - codeparrot_training - Step 16282: {'lr': 0.0004885991937741506, 'samples': 8336896, 'steps': 16282, 'loss/train': 2.6690139770507812}
-03/04/2022 08:35:28 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/04/2022 08:35:31 - INFO - codeparrot_training - Step 16283: {'lr': 0.0004885976094390366, 'samples': 8337408, 'steps': 16283, 'loss/train': 2.343161106109619}
-03/04/2022 08:35:34 - INFO - codeparrot_training - Step 16284: {'lr': 0.000488596024996414, 'samples': 8337920, 'steps': 16284, 'loss/train': 1.8221739530563354}
-03/04/2022 08:35:36 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/04/2022 08:35:40 - INFO - codeparrot_training - Step 16285: {'lr': 0.0004885944404462838, 'samples': 8338432, 'steps': 16285, 'loss/train': 2.3313353061676025}
-03/04/2022 08:35:43 - INFO - codeparrot_training - Step 16286: {'lr': 0.0004885928557886466, 'samples': 8338944, 'steps': 16286, 'loss/train': 1.553094506263733}
-03/04/2022 08:35:46 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/04/2022 08:35:48 - INFO - codeparrot_training - Step 16287: {'lr': 0.0004885912710235031, 'samples': 8339456, 'steps': 16287, 'loss/train': 1.7495057582855225}
-03/04/2022 08:35:51 - INFO - codeparrot_training - Step 16288: {'lr': 0.0004885896861508541, 'samples': 8339968, 'steps': 16288, 'loss/train': 1.5911059379577637}
-03/04/2022 08:35:54 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/04/2022 08:35:57 - INFO - codeparrot_training - Step 16289: {'lr': 0.0004885881011707003, 'samples': 8340480, 'steps': 16289, 'loss/train': 1.7349072694778442}
-03/04/2022 08:36:00 - INFO - codeparrot_training - Step 16290: {'lr': 0.0004885865160830422, 'samples': 8340992, 'steps': 16290, 'loss/train': 1.7129225730895996}
-03/04/2022 08:36:02 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/04/2022 08:36:05 - INFO - codeparrot_training - Step 16291: {'lr': 0.0004885849308878809, 'samples': 8341504, 'steps': 16291, 'loss/train': 1.9480869770050049}
-03/04/2022 08:36:09 - INFO - codeparrot_training - Step 16292: {'lr': 0.0004885833455852169, 'samples': 8342016, 'steps': 16292, 'loss/train': 1.8706939220428467}
-03/04/2022 08:36:12 - INFO - codeparrot_training - Step 16293: {'lr': 0.0004885817601750509, 'samples': 8342528, 'steps': 16293, 'loss/train': 0.9647485017776489}
-03/04/2022 08:36:12 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/04/2022 08:36:17 - INFO - codeparrot_training - Step 16294: {'lr': 0.0004885801746573836, 'samples': 8343040, 'steps': 16294, 'loss/train': 1.9916930198669434}
-03/04/2022 08:36:20 - INFO - codeparrot_training - Step 16295: {'lr': 0.0004885785890322158, 'samples': 8343552, 'steps': 16295, 'loss/train': 3.2068467140197754}
-03/04/2022 08:36:21 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/04/2022 08:36:25 - INFO - codeparrot_training - Step 16296: {'lr': 0.0004885770032995482, 'samples': 8344064, 'steps': 16296, 'loss/train': 0.7710683345794678}
-03/04/2022 08:36:29 - INFO - codeparrot_training - Step 16297: {'lr': 0.0004885754174593814, 'samples': 8344576, 'steps': 16297, 'loss/train': 1.5819766521453857}
-03/04/2022 08:36:29 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/04/2022 08:36:34 - INFO - codeparrot_training - Step 16298: {'lr': 0.0004885738315117162, 'samples': 8345088, 'steps': 16298, 'loss/train': 1.5976943969726562}
-03/04/2022 08:36:37 - INFO - codeparrot_training - Step 16299: {'lr': 0.0004885722454565534, 'samples': 8345600, 'steps': 16299, 'loss/train': 1.8697959184646606}
-03/04/2022 08:36:37 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 08:36:42 - INFO - codeparrot_training - Step 16300: {'lr': 0.0004885706592938936, 'samples': 8346112, 'steps': 16300, 'loss/train': 2.616769313812256}
-03/04/2022 08:36:45 - INFO - codeparrot_training - Step 16301: {'lr': 0.0004885690730237375, 'samples': 8346624, 'steps': 16301, 'loss/train': 1.8084639310836792}
-03/04/2022 08:36:46 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 08:36:51 - INFO - codeparrot_training - Step 16302: {'lr': 0.0004885674866460858, 'samples': 8347136, 'steps': 16302, 'loss/train': 2.3747527599334717}
-03/04/2022 08:36:54 - INFO - codeparrot_training - Step 16303: {'lr': 0.0004885659001609393, 'samples': 8347648, 'steps': 16303, 'loss/train': 1.0494694709777832}
-03/04/2022 08:36:54 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 08:36:59 - INFO - codeparrot_training - Step 16304: {'lr': 0.0004885643135682987, 'samples': 8348160, 'steps': 16304, 'loss/train': 1.2134062051773071}
-03/04/2022 08:37:02 - INFO - codeparrot_training - Step 16305: {'lr': 0.0004885627268681648, 'samples': 8348672, 'steps': 16305, 'loss/train': 1.5553817749023438}
-03/04/2022 08:37:02 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/04/2022 08:37:08 - INFO - codeparrot_training - Step 16306: {'lr': 0.0004885611400605381, 'samples': 8349184, 'steps': 16306, 'loss/train': 0.7348319888114929}
-03/04/2022 08:37:11 - INFO - codeparrot_training - Step 16307: {'lr': 0.0004885595531454195, 'samples': 8349696, 'steps': 16307, 'loss/train': 1.392432689666748}
-03/04/2022 08:37:11 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 08:37:16 - INFO - codeparrot_training - Step 16308: {'lr': 0.0004885579661228097, 'samples': 8350208, 'steps': 16308, 'loss/train': 1.9520777463912964}
-03/04/2022 08:37:19 - INFO - codeparrot_training - Step 16309: {'lr': 0.0004885563789927092, 'samples': 8350720, 'steps': 16309, 'loss/train': 2.1646621227264404}
-03/04/2022 08:37:20 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/04/2022 08:37:25 - INFO - codeparrot_training - Step 16310: {'lr': 0.0004885547917551189, 'samples': 8351232, 'steps': 16310, 'loss/train': 2.200105905532837}
-03/04/2022 08:37:28 - INFO - codeparrot_training - Step 16311: {'lr': 0.0004885532044100396, 'samples': 8351744, 'steps': 16311, 'loss/train': 2.1152734756469727}
-03/04/2022 08:37:31 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/04/2022 08:37:34 - INFO - codeparrot_training - Step 16312: {'lr': 0.0004885516169574719, 'samples': 8352256, 'steps': 16312, 'loss/train': 1.840437412261963}
-03/04/2022 08:37:37 - INFO - codeparrot_training - Step 16313: {'lr': 0.0004885500293974165, 'samples': 8352768, 'steps': 16313, 'loss/train': 0.478522390127182}
-03/04/2022 08:37:39 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/04/2022 08:37:42 - INFO - codeparrot_training - Step 16314: {'lr': 0.0004885484417298741, 'samples': 8353280, 'steps': 16314, 'loss/train': 2.347452163696289}
-03/04/2022 08:37:45 - INFO - codeparrot_training - Step 16315: {'lr': 0.0004885468539548455, 'samples': 8353792, 'steps': 16315, 'loss/train': 1.9225770235061646}
-03/04/2022 08:37:48 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 08:37:50 - INFO - codeparrot_training - Step 16316: {'lr': 0.0004885452660723313, 'samples': 8354304, 'steps': 16316, 'loss/train': 1.8872768878936768}
-03/04/2022 08:37:54 - INFO - codeparrot_training - Step 16317: {'lr': 0.0004885436780823324, 'samples': 8354816, 'steps': 16317, 'loss/train': 1.2461172342300415}
-03/04/2022 08:37:57 - INFO - codeparrot_training - Step 16318: {'lr': 0.0004885420899848492, 'samples': 8355328, 'steps': 16318, 'loss/train': 1.4898695945739746}
-03/04/2022 08:37:57 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/04/2022 08:38:02 - INFO - codeparrot_training - Step 16319: {'lr': 0.0004885405017798828, 'samples': 8355840, 'steps': 16319, 'loss/train': 2.015568733215332}
-03/04/2022 08:38:05 - INFO - codeparrot_training - Step 16320: {'lr': 0.0004885389134674337, 'samples': 8356352, 'steps': 16320, 'loss/train': 1.9870113134384155}
-03/04/2022 08:38:05 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/04/2022 08:38:11 - INFO - codeparrot_training - Step 16321: {'lr': 0.0004885373250475026, 'samples': 8356864, 'steps': 16321, 'loss/train': 0.9783211350440979}
-03/04/2022 08:38:14 - INFO - codeparrot_training - Step 16322: {'lr': 0.0004885357365200903, 'samples': 8357376, 'steps': 16322, 'loss/train': 2.743126392364502}
-03/04/2022 08:38:16 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 08:38:19 - INFO - codeparrot_training - Step 16323: {'lr': 0.0004885341478851975, 'samples': 8357888, 'steps': 16323, 'loss/train': 0.46866661310195923}
-03/04/2022 08:38:23 - INFO - codeparrot_training - Step 16324: {'lr': 0.0004885325591428248, 'samples': 8358400, 'steps': 16324, 'loss/train': 1.577775239944458}
-03/04/2022 08:38:24 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/04/2022 08:38:28 - INFO - codeparrot_training - Step 16325: {'lr': 0.0004885309702929731, 'samples': 8358912, 'steps': 16325, 'loss/train': 1.9194586277008057}
-03/04/2022 08:38:31 - INFO - codeparrot_training - Step 16326: {'lr': 0.000488529381335643, 'samples': 8359424, 'steps': 16326, 'loss/train': 1.9354419708251953}
-03/04/2022 08:38:33 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/04/2022 08:38:37 - INFO - codeparrot_training - Step 16327: {'lr': 0.0004885277922708352, 'samples': 8359936, 'steps': 16327, 'loss/train': 1.9065040349960327}
-03/04/2022 08:38:40 - INFO - codeparrot_training - Step 16328: {'lr': 0.0004885262030985504, 'samples': 8360448, 'steps': 16328, 'loss/train': 2.034669876098633}
-03/04/2022 08:38:42 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 08:38:45 - INFO - codeparrot_training - Step 16329: {'lr': 0.0004885246138187896, 'samples': 8360960, 'steps': 16329, 'loss/train': 2.1502139568328857}
-03/04/2022 08:38:48 - INFO - codeparrot_training - Step 16330: {'lr': 0.0004885230244315531, 'samples': 8361472, 'steps': 16330, 'loss/train': 1.6941417455673218}
-03/04/2022 08:38:51 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/04/2022 08:38:54 - INFO - codeparrot_training - Step 16331: {'lr': 0.0004885214349368419, 'samples': 8361984, 'steps': 16331, 'loss/train': 2.103154182434082}
-03/04/2022 08:38:57 - INFO - codeparrot_training - Step 16332: {'lr': 0.0004885198453346565, 'samples': 8362496, 'steps': 16332, 'loss/train': 2.4901154041290283}
-03/04/2022 08:39:00 - INFO - codeparrot_training - Step 16333: {'lr': 0.0004885182556249978, 'samples': 8363008, 'steps': 16333, 'loss/train': 2.248621702194214}
-03/04/2022 08:39:00 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 08:39:05 - INFO - codeparrot_training - Step 16334: {'lr': 0.0004885166658078666, 'samples': 8363520, 'steps': 16334, 'loss/train': 1.976453185081482}
-03/04/2022 08:39:08 - INFO - codeparrot_training - Step 16335: {'lr': 0.0004885150758832632, 'samples': 8364032, 'steps': 16335, 'loss/train': 0.9693822264671326}
-03/04/2022 08:39:08 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 08:39:14 - INFO - codeparrot_training - Step 16336: {'lr': 0.0004885134858511888, 'samples': 8364544, 'steps': 16336, 'loss/train': 2.021921157836914}
-03/04/2022 08:39:17 - INFO - codeparrot_training - Step 16337: {'lr': 0.0004885118957116438, 'samples': 8365056, 'steps': 16337, 'loss/train': 2.153299570083618}
-03/04/2022 08:39:17 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/04/2022 08:39:22 - INFO - codeparrot_training - Step 16338: {'lr': 0.000488510305464629, 'samples': 8365568, 'steps': 16338, 'loss/train': 0.4131595194339752}
-03/04/2022 08:39:25 - INFO - codeparrot_training - Step 16339: {'lr': 0.0004885087151101453, 'samples': 8366080, 'steps': 16339, 'loss/train': 2.1611082553863525}
-03/04/2022 08:39:25 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/04/2022 08:39:30 - INFO - codeparrot_training - Step 16340: {'lr': 0.0004885071246481931, 'samples': 8366592, 'steps': 16340, 'loss/train': 1.5361522436141968}
-03/04/2022 08:39:34 - INFO - codeparrot_training - Step 16341: {'lr': 0.0004885055340787733, 'samples': 8367104, 'steps': 16341, 'loss/train': 2.841336488723755}
-03/04/2022 08:39:34 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/04/2022 08:39:39 - INFO - codeparrot_training - Step 16342: {'lr': 0.0004885039434018866, 'samples': 8367616, 'steps': 16342, 'loss/train': 2.0472989082336426}
-03/04/2022 08:39:42 - INFO - codeparrot_training - Step 16343: {'lr': 0.0004885023526175337, 'samples': 8368128, 'steps': 16343, 'loss/train': 2.8409836292266846}
-03/04/2022 08:39:42 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/04/2022 08:39:47 - INFO - codeparrot_training - Step 16344: {'lr': 0.0004885007617257154, 'samples': 8368640, 'steps': 16344, 'loss/train': 2.11627197265625}
-03/04/2022 08:39:51 - INFO - codeparrot_training - Step 16345: {'lr': 0.0004884991707264322, 'samples': 8369152, 'steps': 16345, 'loss/train': 1.9433125257492065}
-03/04/2022 08:39:51 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 08:39:56 - INFO - codeparrot_training - Step 16346: {'lr': 0.000488497579619685, 'samples': 8369664, 'steps': 16346, 'loss/train': 1.5647889375686646}
-03/04/2022 08:39:59 - INFO - codeparrot_training - Step 16347: {'lr': 0.0004884959884054745, 'samples': 8370176, 'steps': 16347, 'loss/train': 1.5386345386505127}
-03/04/2022 08:39:59 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/04/2022 08:40:05 - INFO - codeparrot_training - Step 16348: {'lr': 0.0004884943970838014, 'samples': 8370688, 'steps': 16348, 'loss/train': 2.0312376022338867}
-03/04/2022 08:40:08 - INFO - codeparrot_training - Step 16349: {'lr': 0.0004884928056546663, 'samples': 8371200, 'steps': 16349, 'loss/train': 1.971061110496521}
-03/04/2022 08:40:08 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 08:40:13 - INFO - codeparrot_training - Step 16350: {'lr': 0.0004884912141180701, 'samples': 8371712, 'steps': 16350, 'loss/train': 2.3363723754882812}
-03/04/2022 08:40:16 - INFO - codeparrot_training - Step 16351: {'lr': 0.0004884896224740136, 'samples': 8372224, 'steps': 16351, 'loss/train': 1.6670196056365967}
-03/04/2022 08:40:16 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/04/2022 08:40:22 - INFO - codeparrot_training - Step 16352: {'lr': 0.0004884880307224972, 'samples': 8372736, 'steps': 16352, 'loss/train': 1.4225924015045166}
-03/04/2022 08:40:25 - INFO - codeparrot_training - Step 16353: {'lr': 0.0004884864388635217, 'samples': 8373248, 'steps': 16353, 'loss/train': 0.1494947224855423}
-03/04/2022 08:40:25 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/04/2022 08:40:30 - INFO - codeparrot_training - Step 16354: {'lr': 0.0004884848468970879, 'samples': 8373760, 'steps': 16354, 'loss/train': 1.8595839738845825}
-03/04/2022 08:40:33 - INFO - codeparrot_training - Step 16355: {'lr': 0.0004884832548231966, 'samples': 8374272, 'steps': 16355, 'loss/train': 1.6779239177703857}
-03/04/2022 08:40:33 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/04/2022 08:40:39 - INFO - codeparrot_training - Step 16356: {'lr': 0.0004884816626418484, 'samples': 8374784, 'steps': 16356, 'loss/train': 1.8837916851043701}
-03/04/2022 08:40:42 - INFO - codeparrot_training - Step 16357: {'lr': 0.000488480070353044, 'samples': 8375296, 'steps': 16357, 'loss/train': 1.214759111404419}
-03/04/2022 08:40:42 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/04/2022 08:40:47 - INFO - codeparrot_training - Step 16358: {'lr': 0.0004884784779567843, 'samples': 8375808, 'steps': 16358, 'loss/train': 2.0302274227142334}
-03/04/2022 08:40:50 - INFO - codeparrot_training - Step 16359: {'lr': 0.0004884768854530696, 'samples': 8376320, 'steps': 16359, 'loss/train': 2.6051042079925537}
-03/04/2022 08:40:51 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/04/2022 08:40:56 - INFO - codeparrot_training - Step 16360: {'lr': 0.0004884752928419012, 'samples': 8376832, 'steps': 16360, 'loss/train': 2.216580867767334}
-03/04/2022 08:40:59 - INFO - codeparrot_training - Step 16361: {'lr': 0.0004884737001232793, 'samples': 8377344, 'steps': 16361, 'loss/train': 2.3614847660064697}
-03/04/2022 08:41:00 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 08:41:04 - INFO - codeparrot_training - Step 16362: {'lr': 0.000488472107297205, 'samples': 8377856, 'steps': 16362, 'loss/train': 1.8771743774414062}
-03/04/2022 08:41:07 - INFO - codeparrot_training - Step 16363: {'lr': 0.0004884705143636788, 'samples': 8378368, 'steps': 16363, 'loss/train': 1.6833462715148926}
-03/04/2022 08:41:08 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 08:41:12 - INFO - codeparrot_training - Step 16364: {'lr': 0.0004884689213227013, 'samples': 8378880, 'steps': 16364, 'loss/train': 1.9249987602233887}
-03/04/2022 08:41:16 - INFO - codeparrot_training - Step 16365: {'lr': 0.0004884673281742736, 'samples': 8379392, 'steps': 16365, 'loss/train': 1.058294653892517}
-03/04/2022 08:41:16 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 08:41:21 - INFO - codeparrot_training - Step 16366: {'lr': 0.0004884657349183961, 'samples': 8379904, 'steps': 16366, 'loss/train': 1.865576148033142}
-03/04/2022 08:41:24 - INFO - codeparrot_training - Step 16367: {'lr': 0.0004884641415550696, 'samples': 8380416, 'steps': 16367, 'loss/train': 1.5700007677078247}
-03/04/2022 08:41:25 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/04/2022 08:41:29 - INFO - codeparrot_training - Step 16368: {'lr': 0.0004884625480842949, 'samples': 8380928, 'steps': 16368, 'loss/train': 2.2438154220581055}
-03/04/2022 08:41:32 - INFO - codeparrot_training - Step 16369: {'lr': 0.0004884609545060726, 'samples': 8381440, 'steps': 16369, 'loss/train': 2.161803960800171}
-03/04/2022 08:41:34 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 08:41:38 - INFO - codeparrot_training - Step 16370: {'lr': 0.0004884593608204035, 'samples': 8381952, 'steps': 16370, 'loss/train': 3.4671592712402344}
-03/04/2022 08:41:41 - INFO - codeparrot_training - Step 16371: {'lr': 0.0004884577670272882, 'samples': 8382464, 'steps': 16371, 'loss/train': 2.4168713092803955}
-03/04/2022 08:41:43 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 08:41:46 - INFO - codeparrot_training - Step 16372: {'lr': 0.0004884561731267278, 'samples': 8382976, 'steps': 16372, 'loss/train': 1.680180549621582}
-03/04/2022 08:41:49 - INFO - codeparrot_training - Step 16373: {'lr': 0.0004884545791187224, 'samples': 8383488, 'steps': 16373, 'loss/train': 2.24761700630188}
-03/04/2022 08:41:51 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/04/2022 08:41:55 - INFO - codeparrot_training - Step 16374: {'lr': 0.0004884529850032732, 'samples': 8384000, 'steps': 16374, 'loss/train': 1.6884914636611938}
-03/04/2022 08:41:58 - INFO - codeparrot_training - Step 16375: {'lr': 0.0004884513907803808, 'samples': 8384512, 'steps': 16375, 'loss/train': 2.682286024093628}
-03/04/2022 08:41:59 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/04/2022 08:42:03 - INFO - codeparrot_training - Step 16376: {'lr': 0.0004884497964500457, 'samples': 8385024, 'steps': 16376, 'loss/train': 1.6001795530319214}
-03/04/2022 08:42:07 - INFO - codeparrot_training - Step 16377: {'lr': 0.000488448202012269, 'samples': 8385536, 'steps': 16377, 'loss/train': 2.0706160068511963}
-03/04/2022 08:42:08 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 08:42:12 - INFO - codeparrot_training - Step 16378: {'lr': 0.0004884466074670512, 'samples': 8386048, 'steps': 16378, 'loss/train': 1.4148619174957275}
-03/04/2022 08:42:15 - INFO - codeparrot_training - Step 16379: {'lr': 0.0004884450128143929, 'samples': 8386560, 'steps': 16379, 'loss/train': 1.5309103727340698}
-03/04/2022 08:42:16 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/04/2022 08:42:20 - INFO - codeparrot_training - Step 16380: {'lr': 0.000488443418054295, 'samples': 8387072, 'steps': 16380, 'loss/train': 1.9036521911621094}
-03/04/2022 08:42:23 - INFO - codeparrot_training - Step 16381: {'lr': 0.0004884418231867583, 'samples': 8387584, 'steps': 16381, 'loss/train': 1.7319591045379639}
-03/04/2022 08:42:25 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/04/2022 08:42:29 - INFO - codeparrot_training - Step 16382: {'lr': 0.0004884402282117833, 'samples': 8388096, 'steps': 16382, 'loss/train': 1.9059211015701294}
-03/04/2022 08:42:32 - INFO - codeparrot_training - Step 16383: {'lr': 0.0004884386331293708, 'samples': 8388608, 'steps': 16383, 'loss/train': 2.3407557010650635}
-03/04/2022 08:42:33 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 08:42:37 - INFO - codeparrot_training - Step 16384: {'lr': 0.0004884370379395215, 'samples': 8389120, 'steps': 16384, 'loss/train': 1.7239257097244263}
-03/04/2022 08:42:40 - INFO - codeparrot_training - Step 16385: {'lr': 0.0004884354426422363, 'samples': 8389632, 'steps': 16385, 'loss/train': 2.0407824516296387}
-03/04/2022 08:42:42 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 08:42:45 - INFO - codeparrot_training - Step 16386: {'lr': 0.0004884338472375156, 'samples': 8390144, 'steps': 16386, 'loss/train': 2.4947617053985596}
-03/04/2022 08:42:49 - INFO - codeparrot_training - Step 16387: {'lr': 0.0004884322517253604, 'samples': 8390656, 'steps': 16387, 'loss/train': 2.1813197135925293}
-03/04/2022 08:42:50 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 08:42:54 - INFO - codeparrot_training - Step 16388: {'lr': 0.0004884306561057713, 'samples': 8391168, 'steps': 16388, 'loss/train': 6.550569534301758}
-03/04/2022 08:42:57 - INFO - codeparrot_training - Step 16389: {'lr': 0.000488429060378749, 'samples': 8391680, 'steps': 16389, 'loss/train': 1.762549877166748}
-03/04/2022 08:43:00 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/04/2022 08:43:03 - INFO - codeparrot_training - Step 16390: {'lr': 0.0004884274645442942, 'samples': 8392192, 'steps': 16390, 'loss/train': 2.424325466156006}
-03/04/2022 08:43:06 - INFO - codeparrot_training - Step 16391: {'lr': 0.0004884258686024077, 'samples': 8392704, 'steps': 16391, 'loss/train': 0.29353129863739014}
-03/04/2022 08:43:08 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 08:43:11 - INFO - codeparrot_training - Step 16392: {'lr': 0.0004884242725530902, 'samples': 8393216, 'steps': 16392, 'loss/train': 1.0659098625183105}
-03/04/2022 08:43:14 - INFO - codeparrot_training - Step 16393: {'lr': 0.0004884226763963423, 'samples': 8393728, 'steps': 16393, 'loss/train': 1.8349199295043945}
-03/04/2022 08:43:17 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/04/2022 08:43:20 - INFO - codeparrot_training - Step 16394: {'lr': 0.000488421080132165, 'samples': 8394240, 'steps': 16394, 'loss/train': 2.378765106201172}
-03/04/2022 08:43:23 - INFO - codeparrot_training - Step 16395: {'lr': 0.0004884194837605587, 'samples': 8394752, 'steps': 16395, 'loss/train': 1.544532060623169}
-03/04/2022 08:43:25 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/04/2022 08:43:28 - INFO - codeparrot_training - Step 16396: {'lr': 0.0004884178872815243, 'samples': 8395264, 'steps': 16396, 'loss/train': 2.2379274368286133}
-03/04/2022 08:43:31 - INFO - codeparrot_training - Step 16397: {'lr': 0.0004884162906950624, 'samples': 8395776, 'steps': 16397, 'loss/train': 2.1827073097229004}
-03/04/2022 08:43:33 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/04/2022 08:43:36 - INFO - codeparrot_training - Step 16398: {'lr': 0.000488414694001174, 'samples': 8396288, 'steps': 16398, 'loss/train': 1.7113568782806396}
-03/04/2022 08:43:40 - INFO - codeparrot_training - Step 16399: {'lr': 0.0004884130971998595, 'samples': 8396800, 'steps': 16399, 'loss/train': 0.541576087474823}
-03/04/2022 08:43:42 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/04/2022 08:43:45 - INFO - codeparrot_training - Step 16400: {'lr': 0.0004884115002911197, 'samples': 8397312, 'steps': 16400, 'loss/train': 2.4893033504486084}
-03/04/2022 08:43:48 - INFO - codeparrot_training - Step 16401: {'lr': 0.0004884099032749554, 'samples': 8397824, 'steps': 16401, 'loss/train': 2.2197635173797607}
-03/04/2022 08:43:50 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 08:43:53 - INFO - codeparrot_training - Step 16402: {'lr': 0.0004884083061513672, 'samples': 8398336, 'steps': 16402, 'loss/train': 1.6724162101745605}
-03/04/2022 08:43:57 - INFO - codeparrot_training - Step 16403: {'lr': 0.0004884067089203559, 'samples': 8398848, 'steps': 16403, 'loss/train': 0.9342283606529236}
-03/04/2022 08:43:59 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/04/2022 08:44:02 - INFO - codeparrot_training - Step 16404: {'lr': 0.0004884051115819224, 'samples': 8399360, 'steps': 16404, 'loss/train': 1.2800562381744385}
-03/04/2022 08:44:05 - INFO - codeparrot_training - Step 16405: {'lr': 0.000488403514136067, 'samples': 8399872, 'steps': 16405, 'loss/train': 2.3662519454956055}
-03/04/2022 08:44:08 - INFO - codeparrot_training - Step 16406: {'lr': 0.0004884019165827909, 'samples': 8400384, 'steps': 16406, 'loss/train': 1.8137977123260498}
-03/04/2022 08:44:08 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/04/2022 08:44:13 - INFO - codeparrot_training - Step 16407: {'lr': 0.0004884003189220945, 'samples': 8400896, 'steps': 16407, 'loss/train': 1.5275542736053467}
-03/04/2022 08:44:16 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 08:44:19 - INFO - codeparrot_training - Step 16408: {'lr': 0.0004883987211539785, 'samples': 8401408, 'steps': 16408, 'loss/train': 2.0113325119018555}
-03/04/2022 08:44:22 - INFO - codeparrot_training - Step 16409: {'lr': 0.0004883971232784438, 'samples': 8401920, 'steps': 16409, 'loss/train': 1.3769861459732056}
-03/04/2022 08:44:24 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/04/2022 08:44:27 - INFO - codeparrot_training - Step 16410: {'lr': 0.0004883955252954909, 'samples': 8402432, 'steps': 16410, 'loss/train': 2.0431456565856934}
-03/04/2022 08:44:30 - INFO - codeparrot_training - Step 16411: {'lr': 0.0004883939272051208, 'samples': 8402944, 'steps': 16411, 'loss/train': 1.7873300313949585}
-03/04/2022 08:44:32 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/04/2022 08:44:35 - INFO - codeparrot_training - Step 16412: {'lr': 0.000488392329007334, 'samples': 8403456, 'steps': 16412, 'loss/train': 2.0017151832580566}
-03/04/2022 08:44:39 - INFO - codeparrot_training - Step 16413: {'lr': 0.0004883907307021314, 'samples': 8403968, 'steps': 16413, 'loss/train': 1.756945013999939}
-03/04/2022 08:44:41 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 08:44:44 - INFO - codeparrot_training - Step 16414: {'lr': 0.0004883891322895134, 'samples': 8404480, 'steps': 16414, 'loss/train': 1.899993896484375}
-03/04/2022 08:44:47 - INFO - codeparrot_training - Step 16415: {'lr': 0.000488387533769481, 'samples': 8404992, 'steps': 16415, 'loss/train': 1.3593714237213135}
-03/04/2022 08:44:50 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 08:44:53 - INFO - codeparrot_training - Step 16416: {'lr': 0.000488385935142035, 'samples': 8405504, 'steps': 16416, 'loss/train': 2.884122133255005}
-03/04/2022 08:44:56 - INFO - codeparrot_training - Step 16417: {'lr': 0.0004883843364071759, 'samples': 8406016, 'steps': 16417, 'loss/train': 1.846139907836914}
-03/04/2022 08:44:58 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 08:45:01 - INFO - codeparrot_training - Step 16418: {'lr': 0.0004883827375649045, 'samples': 8406528, 'steps': 16418, 'loss/train': 1.3730463981628418}
-03/04/2022 08:45:05 - INFO - codeparrot_training - Step 16419: {'lr': 0.0004883811386152216, 'samples': 8407040, 'steps': 16419, 'loss/train': 1.8221787214279175}
-03/04/2022 08:45:07 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 08:45:10 - INFO - codeparrot_training - Step 16420: {'lr': 0.0004883795395581277, 'samples': 8407552, 'steps': 16420, 'loss/train': 1.4449278116226196}
-03/04/2022 08:45:13 - INFO - codeparrot_training - Step 16421: {'lr': 0.0004883779403936237, 'samples': 8408064, 'steps': 16421, 'loss/train': 1.92012357711792}
-03/04/2022 08:45:15 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/04/2022 08:45:18 - INFO - codeparrot_training - Step 16422: {'lr': 0.0004883763411217103, 'samples': 8408576, 'steps': 16422, 'loss/train': 2.222801446914673}
-03/04/2022 08:45:21 - INFO - codeparrot_training - Step 16423: {'lr': 0.0004883747417423882, 'samples': 8409088, 'steps': 16423, 'loss/train': 0.47974029183387756}
-03/04/2022 08:45:23 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/04/2022 08:45:27 - INFO - codeparrot_training - Step 16424: {'lr': 0.000488373142255658, 'samples': 8409600, 'steps': 16424, 'loss/train': 3.604419708251953}
-03/04/2022 08:45:30 - INFO - codeparrot_training - Step 16425: {'lr': 0.0004883715426615207, 'samples': 8410112, 'steps': 16425, 'loss/train': 1.943888545036316}
-03/04/2022 08:45:32 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/04/2022 08:45:35 - INFO - codeparrot_training - Step 16426: {'lr': 0.0004883699429599768, 'samples': 8410624, 'steps': 16426, 'loss/train': 1.618390440940857}
-03/04/2022 08:45:39 - INFO - codeparrot_training - Step 16427: {'lr': 0.0004883683431510272, 'samples': 8411136, 'steps': 16427, 'loss/train': 2.245054006576538}
-03/04/2022 08:45:41 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/04/2022 08:45:44 - INFO - codeparrot_training - Step 16428: {'lr': 0.0004883667432346723, 'samples': 8411648, 'steps': 16428, 'loss/train': 1.7984651327133179}
-03/04/2022 08:45:47 - INFO - codeparrot_training - Step 16429: {'lr': 0.0004883651432109132, 'samples': 8412160, 'steps': 16429, 'loss/train': 1.4769923686981201}
-03/04/2022 08:45:49 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/04/2022 08:45:52 - INFO - codeparrot_training - Step 16430: {'lr': 0.0004883635430797502, 'samples': 8412672, 'steps': 16430, 'loss/train': 1.7652015686035156}
-03/04/2022 08:45:55 - INFO - codeparrot_training - Step 16431: {'lr': 0.0004883619428411846, 'samples': 8413184, 'steps': 16431, 'loss/train': 1.9275730848312378}
-03/04/2022 08:45:57 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/04/2022 08:46:01 - INFO - codeparrot_training - Step 16432: {'lr': 0.0004883603424952165, 'samples': 8413696, 'steps': 16432, 'loss/train': 1.6035029888153076}
-03/04/2022 08:46:04 - INFO - codeparrot_training - Step 16433: {'lr': 0.0004883587420418471, 'samples': 8414208, 'steps': 16433, 'loss/train': 1.8572572469711304}
-03/04/2022 08:46:05 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/04/2022 08:46:09 - INFO - codeparrot_training - Step 16434: {'lr': 0.0004883571414810769, 'samples': 8414720, 'steps': 16434, 'loss/train': 0.7688239216804504}
-03/04/2022 08:46:12 - INFO - codeparrot_training - Step 16435: {'lr': 0.0004883555408129066, 'samples': 8415232, 'steps': 16435, 'loss/train': 1.0418535470962524}
-03/04/2022 08:46:14 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 08:46:18 - INFO - codeparrot_training - Step 16436: {'lr': 0.0004883539400373369, 'samples': 8415744, 'steps': 16436, 'loss/train': 2.462855577468872}
-03/04/2022 08:46:21 - INFO - codeparrot_training - Step 16437: {'lr': 0.0004883523391543687, 'samples': 8416256, 'steps': 16437, 'loss/train': 2.115964651107788}
-03/04/2022 08:46:23 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/04/2022 08:46:26 - INFO - codeparrot_training - Step 16438: {'lr': 0.0004883507381640026, 'samples': 8416768, 'steps': 16438, 'loss/train': 1.6613762378692627}
-03/04/2022 08:46:29 - INFO - codeparrot_training - Step 16439: {'lr': 0.0004883491370662393, 'samples': 8417280, 'steps': 16439, 'loss/train': 1.7432026863098145}
-03/04/2022 08:46:31 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 08:46:35 - INFO - codeparrot_training - Step 16440: {'lr': 0.0004883475358610794, 'samples': 8417792, 'steps': 16440, 'loss/train': 2.375701904296875}
-03/04/2022 08:46:38 - INFO - codeparrot_training - Step 16441: {'lr': 0.000488345934548524, 'samples': 8418304, 'steps': 16441, 'loss/train': 2.737980365753174}
-03/04/2022 08:46:41 - INFO - codeparrot_training - Step 16442: {'lr': 0.0004883443331285736, 'samples': 8418816, 'steps': 16442, 'loss/train': 0.6280149817466736}
-03/04/2022 08:46:42 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 08:46:46 - INFO - codeparrot_training - Step 16443: {'lr': 0.0004883427316012289, 'samples': 8419328, 'steps': 16443, 'loss/train': 1.4167916774749756}
-03/04/2022 08:46:49 - INFO - codeparrot_training - Step 16444: {'lr': 0.0004883411299664906, 'samples': 8419840, 'steps': 16444, 'loss/train': 1.8453447818756104}
-03/04/2022 08:46:50 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/04/2022 08:46:55 - INFO - codeparrot_training - Step 16445: {'lr': 0.0004883395282243595, 'samples': 8420352, 'steps': 16445, 'loss/train': 2.0180883407592773}
-03/04/2022 08:46:58 - INFO - codeparrot_training - Step 16446: {'lr': 0.0004883379263748363, 'samples': 8420864, 'steps': 16446, 'loss/train': 1.4337706565856934}
-03/04/2022 08:46:58 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/04/2022 08:47:03 - INFO - codeparrot_training - Step 16447: {'lr': 0.0004883363244179217, 'samples': 8421376, 'steps': 16447, 'loss/train': 2.104165554046631}
-03/04/2022 08:47:06 - INFO - codeparrot_training - Step 16448: {'lr': 0.0004883347223536164, 'samples': 8421888, 'steps': 16448, 'loss/train': 2.71697998046875}
-03/04/2022 08:47:06 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 08:47:12 - INFO - codeparrot_training - Step 16449: {'lr': 0.0004883331201819211, 'samples': 8422400, 'steps': 16449, 'loss/train': 1.981850028038025}
-03/04/2022 08:47:15 - INFO - codeparrot_training - Step 16450: {'lr': 0.0004883315179028366, 'samples': 8422912, 'steps': 16450, 'loss/train': 1.8353919982910156}
-03/04/2022 08:47:15 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 08:47:20 - INFO - codeparrot_training - Step 16451: {'lr': 0.0004883299155163636, 'samples': 8423424, 'steps': 16451, 'loss/train': 2.083240032196045}
-03/04/2022 08:47:23 - INFO - codeparrot_training - Step 16452: {'lr': 0.0004883283130225029, 'samples': 8423936, 'steps': 16452, 'loss/train': 1.5761168003082275}
-03/04/2022 08:47:23 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 08:47:28 - INFO - codeparrot_training - Step 16453: {'lr': 0.0004883267104212551, 'samples': 8424448, 'steps': 16453, 'loss/train': 2.1332712173461914}
-03/04/2022 08:47:32 - INFO - codeparrot_training - Step 16454: {'lr': 0.0004883251077126209, 'samples': 8424960, 'steps': 16454, 'loss/train': 2.032949924468994}
-03/04/2022 08:47:32 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/04/2022 08:47:37 - INFO - codeparrot_training - Step 16455: {'lr': 0.0004883235048966011, 'samples': 8425472, 'steps': 16455, 'loss/train': 0.4261553883552551}
-03/04/2022 08:47:40 - INFO - codeparrot_training - Step 16456: {'lr': 0.0004883219019731964, 'samples': 8425984, 'steps': 16456, 'loss/train': 1.5995630025863647}
-03/04/2022 08:47:41 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/04/2022 08:47:45 - INFO - codeparrot_training - Step 16457: {'lr': 0.0004883202989424076, 'samples': 8426496, 'steps': 16457, 'loss/train': 1.059237003326416}
-03/04/2022 08:47:49 - INFO - codeparrot_training - Step 16458: {'lr': 0.0004883186958042354, 'samples': 8427008, 'steps': 16458, 'loss/train': 0.44589293003082275}
-03/04/2022 08:47:49 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 08:47:54 - INFO - codeparrot_training - Step 16459: {'lr': 0.0004883170925586804, 'samples': 8427520, 'steps': 16459, 'loss/train': 1.8939913511276245}
-03/04/2022 08:47:57 - INFO - codeparrot_training - Step 16460: {'lr': 0.0004883154892057433, 'samples': 8428032, 'steps': 16460, 'loss/train': 2.273163080215454}
-03/04/2022 08:47:57 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/04/2022 08:48:02 - INFO - codeparrot_training - Step 16461: {'lr': 0.000488313885745425, 'samples': 8428544, 'steps': 16461, 'loss/train': 1.6056065559387207}
-03/04/2022 08:48:05 - INFO - codeparrot_training - Step 16462: {'lr': 0.0004883122821777261, 'samples': 8429056, 'steps': 16462, 'loss/train': 2.0975940227508545}
-03/04/2022 08:48:06 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/04/2022 08:48:11 - INFO - codeparrot_training - Step 16463: {'lr': 0.0004883106785026475, 'samples': 8429568, 'steps': 16463, 'loss/train': 1.7993580102920532}
-03/04/2022 08:48:14 - INFO - codeparrot_training - Step 16464: {'lr': 0.0004883090747201897, 'samples': 8430080, 'steps': 16464, 'loss/train': 1.6430062055587769}
-03/04/2022 08:48:14 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/04/2022 08:48:19 - INFO - codeparrot_training - Step 16465: {'lr': 0.0004883074708303534, 'samples': 8430592, 'steps': 16465, 'loss/train': 1.3656504154205322}
-03/04/2022 08:48:22 - INFO - codeparrot_training - Step 16466: {'lr': 0.0004883058668331396, 'samples': 8431104, 'steps': 16466, 'loss/train': 1.9298224449157715}
-03/04/2022 08:48:22 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/04/2022 08:48:27 - INFO - codeparrot_training - Step 16467: {'lr': 0.0004883042627285488, 'samples': 8431616, 'steps': 16467, 'loss/train': 1.0262864828109741}
-03/04/2022 08:48:30 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/04/2022 08:48:33 - INFO - codeparrot_training - Step 16468: {'lr': 0.0004883026585165817, 'samples': 8432128, 'steps': 16468, 'loss/train': 1.9309629201889038}
-03/04/2022 08:48:36 - INFO - codeparrot_training - Step 16469: {'lr': 0.0004883010541972392, 'samples': 8432640, 'steps': 16469, 'loss/train': 1.3404954671859741}
-03/04/2022 08:48:39 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/04/2022 08:48:41 - INFO - codeparrot_training - Step 16470: {'lr': 0.0004882994497705219, 'samples': 8433152, 'steps': 16470, 'loss/train': 1.471269965171814}
-03/04/2022 08:48:44 - INFO - codeparrot_training - Step 16471: {'lr': 0.0004882978452364305, 'samples': 8433664, 'steps': 16471, 'loss/train': 1.9538277387619019}
-03/04/2022 08:48:47 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/04/2022 08:48:50 - INFO - codeparrot_training - Step 16472: {'lr': 0.0004882962405949658, 'samples': 8434176, 'steps': 16472, 'loss/train': 0.9498873949050903}
-03/04/2022 08:48:53 - INFO - codeparrot_training - Step 16473: {'lr': 0.0004882946358461285, 'samples': 8434688, 'steps': 16473, 'loss/train': 1.5891410112380981}
-03/04/2022 08:48:56 - INFO - codeparrot_training - Step 16474: {'lr': 0.0004882930309899192, 'samples': 8435200, 'steps': 16474, 'loss/train': 4.115705966949463}
-03/04/2022 08:48:56 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 08:49:01 - INFO - codeparrot_training - Step 16475: {'lr': 0.000488291426026339, 'samples': 8435712, 'steps': 16475, 'loss/train': 2.1988816261291504}
-03/04/2022 08:49:04 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 08:49:07 - INFO - codeparrot_training - Step 16476: {'lr': 0.0004882898209553881, 'samples': 8436224, 'steps': 16476, 'loss/train': 2.47982120513916}
-03/04/2022 08:49:10 - INFO - codeparrot_training - Step 16477: {'lr': 0.0004882882157770676, 'samples': 8436736, 'steps': 16477, 'loss/train': 1.7204853296279907}
-03/04/2022 08:49:13 - INFO - codeparrot_training - Step 16478: {'lr': 0.000488286610491378, 'samples': 8437248, 'steps': 16478, 'loss/train': 1.2006235122680664}
-03/04/2022 08:49:14 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 08:49:19 - INFO - codeparrot_training - Step 16479: {'lr': 0.0004882850050983203, 'samples': 8437760, 'steps': 16479, 'loss/train': 2.713766098022461}
-03/04/2022 08:49:22 - INFO - codeparrot_training - Step 16480: {'lr': 0.0004882833995978949, 'samples': 8438272, 'steps': 16480, 'loss/train': 1.9634824991226196}
-03/04/2022 08:49:22 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/04/2022 08:49:27 - INFO - codeparrot_training - Step 16481: {'lr': 0.0004882817939901027, 'samples': 8438784, 'steps': 16481, 'loss/train': 1.8109197616577148}
-03/04/2022 08:49:30 - INFO - codeparrot_training - Step 16482: {'lr': 0.0004882801882749445, 'samples': 8439296, 'steps': 16482, 'loss/train': 2.3125808238983154}
-03/04/2022 08:49:31 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 08:49:36 - INFO - codeparrot_training - Step 16483: {'lr': 0.0004882785824524209, 'samples': 8439808, 'steps': 16483, 'loss/train': 2.422185182571411}
-03/04/2022 08:49:39 - INFO - codeparrot_training - Step 16484: {'lr': 0.0004882769765225326, 'samples': 8440320, 'steps': 16484, 'loss/train': 1.7352460622787476}
-03/04/2022 08:49:40 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/04/2022 08:49:44 - INFO - codeparrot_training - Step 16485: {'lr': 0.00048827537048528035, 'samples': 8440832, 'steps': 16485, 'loss/train': 2.7356927394866943}
-03/04/2022 08:49:47 - INFO - codeparrot_training - Step 16486: {'lr': 0.00048827376434066493, 'samples': 8441344, 'steps': 16486, 'loss/train': 1.5061273574829102}
-03/04/2022 08:49:48 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/04/2022 08:49:53 - INFO - codeparrot_training - Step 16487: {'lr': 0.0004882721580886871, 'samples': 8441856, 'steps': 16487, 'loss/train': 1.4718307256698608}
-03/04/2022 08:49:56 - INFO - codeparrot_training - Step 16488: {'lr': 0.00048827055172934744, 'samples': 8442368, 'steps': 16488, 'loss/train': 2.4316797256469727}
-03/04/2022 08:49:57 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 08:50:01 - INFO - codeparrot_training - Step 16489: {'lr': 0.0004882689452626468, 'samples': 8442880, 'steps': 16489, 'loss/train': 1.7944515943527222}
-03/04/2022 08:50:04 - INFO - codeparrot_training - Step 16490: {'lr': 0.00048826733868858577, 'samples': 8443392, 'steps': 16490, 'loss/train': 1.5502034425735474}
-03/04/2022 08:50:05 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/04/2022 08:50:10 - INFO - codeparrot_training - Step 16491: {'lr': 0.00048826573200716516, 'samples': 8443904, 'steps': 16491, 'loss/train': 1.7131142616271973}
-03/04/2022 08:50:13 - INFO - codeparrot_training - Step 16492: {'lr': 0.0004882641252183857, 'samples': 8444416, 'steps': 16492, 'loss/train': 1.7050395011901855}
-03/04/2022 08:50:18 - INFO - codeparrot_training - Step 16493: {'lr': 0.0004882625183222481, 'samples': 8444928, 'steps': 16493, 'loss/train': 2.1461682319641113}
-03/04/2022 08:50:21 - INFO - codeparrot_training - Step 16494: {'lr': 0.00048826091131875317, 'samples': 8445440, 'steps': 16494, 'loss/train': 2.159764289855957}
-03/04/2022 08:50:22 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/04/2022 08:50:26 - INFO - codeparrot_training - Step 16495: {'lr': 0.00048825930420790144, 'samples': 8445952, 'steps': 16495, 'loss/train': 1.6271209716796875}
-03/04/2022 08:50:29 - INFO - codeparrot_training - Step 16496: {'lr': 0.0004882576969896938, 'samples': 8446464, 'steps': 16496, 'loss/train': 1.6771215200424194}
-03/04/2022 08:50:30 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 08:50:35 - INFO - codeparrot_training - Step 16497: {'lr': 0.00048825608966413095, 'samples': 8446976, 'steps': 16497, 'loss/train': 2.129197120666504}
-03/04/2022 08:50:38 - INFO - codeparrot_training - Step 16498: {'lr': 0.0004882544822312135, 'samples': 8447488, 'steps': 16498, 'loss/train': 0.7159848809242249}
-03/04/2022 08:50:38 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/04/2022 08:50:43 - INFO - codeparrot_training - Step 16499: {'lr': 0.00048825287469094224, 'samples': 8448000, 'steps': 16499, 'loss/train': 0.7264172434806824}
-03/04/2022 08:50:46 - INFO - codeparrot_training - Step 16500: {'lr': 0.000488251267043318, 'samples': 8448512, 'steps': 16500, 'loss/train': 1.967427372932434}
-03/04/2022 08:50:47 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/04/2022 08:50:52 - INFO - codeparrot_training - Step 16501: {'lr': 0.00048824965928834143, 'samples': 8449024, 'steps': 16501, 'loss/train': 1.1117445230484009}
-03/04/2022 08:50:55 - INFO - codeparrot_training - Step 16502: {'lr': 0.0004882480514260131, 'samples': 8449536, 'steps': 16502, 'loss/train': 1.6806604862213135}
-03/04/2022 08:50:55 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 08:51:00 - INFO - codeparrot_training - Step 16503: {'lr': 0.000488246443456334, 'samples': 8450048, 'steps': 16503, 'loss/train': 2.1147561073303223}
-03/04/2022 08:51:03 - INFO - codeparrot_training - Step 16504: {'lr': 0.0004882448353793048, 'samples': 8450560, 'steps': 16504, 'loss/train': 2.4821555614471436}
-03/04/2022 08:51:03 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/04/2022 08:51:08 - INFO - codeparrot_training - Step 16505: {'lr': 0.000488243227194926, 'samples': 8451072, 'steps': 16505, 'loss/train': 1.6439998149871826}
-03/04/2022 08:51:11 - INFO - codeparrot_training - Step 16506: {'lr': 0.00048824161890319854, 'samples': 8451584, 'steps': 16506, 'loss/train': 1.218070149421692}
-03/04/2022 08:51:12 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 08:51:17 - INFO - codeparrot_training - Step 16507: {'lr': 0.00048824001050412304, 'samples': 8452096, 'steps': 16507, 'loss/train': 2.236164093017578}
-03/04/2022 08:51:20 - INFO - codeparrot_training - Step 16508: {'lr': 0.0004882384019977003, 'samples': 8452608, 'steps': 16508, 'loss/train': 1.8140965700149536}
-03/04/2022 08:51:21 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 08:51:25 - INFO - codeparrot_training - Step 16509: {'lr': 0.000488236793383931, 'samples': 8453120, 'steps': 16509, 'loss/train': 1.58786940574646}
-03/04/2022 08:51:28 - INFO - codeparrot_training - Step 16510: {'lr': 0.00048823518466281586, 'samples': 8453632, 'steps': 16510, 'loss/train': 2.582559823989868}
-03/04/2022 08:51:29 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 08:51:34 - INFO - codeparrot_training - Step 16511: {'lr': 0.0004882335758343557, 'samples': 8454144, 'steps': 16511, 'loss/train': 1.897495985031128}
-03/04/2022 08:51:37 - INFO - codeparrot_training - Step 16512: {'lr': 0.0004882319668985511, 'samples': 8454656, 'steps': 16512, 'loss/train': 1.8930240869522095}
-03/04/2022 08:51:42 - INFO - codeparrot_training - Step 16513: {'lr': 0.00048823035785540284, 'samples': 8455168, 'steps': 16513, 'loss/train': 2.1198575496673584}
-03/04/2022 08:51:45 - INFO - codeparrot_training - Step 16514: {'lr': 0.0004882287487049117, 'samples': 8455680, 'steps': 16514, 'loss/train': 1.6999025344848633}
-03/04/2022 08:51:46 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/04/2022 08:51:51 - INFO - codeparrot_training - Step 16515: {'lr': 0.00048822713944707833, 'samples': 8456192, 'steps': 16515, 'loss/train': 1.9500010013580322}
-03/04/2022 08:51:54 - INFO - codeparrot_training - Step 16516: {'lr': 0.0004882255300819035, 'samples': 8456704, 'steps': 16516, 'loss/train': 1.5312080383300781}
-03/04/2022 08:51:55 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/04/2022 08:51:59 - INFO - codeparrot_training - Step 16517: {'lr': 0.0004882239206093879, 'samples': 8457216, 'steps': 16517, 'loss/train': 0.8108397126197815}
-03/04/2022 08:52:02 - INFO - codeparrot_training - Step 16518: {'lr': 0.0004882223110295323, 'samples': 8457728, 'steps': 16518, 'loss/train': 1.5769646167755127}
-03/04/2022 08:52:03 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/04/2022 08:52:08 - INFO - codeparrot_training - Step 16519: {'lr': 0.00048822070134233743, 'samples': 8458240, 'steps': 16519, 'loss/train': 1.5263577699661255}
-03/04/2022 08:52:11 - INFO - codeparrot_training - Step 16520: {'lr': 0.000488219091547804, 'samples': 8458752, 'steps': 16520, 'loss/train': 2.1808791160583496}
-03/04/2022 08:52:13 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/04/2022 08:52:16 - INFO - codeparrot_training - Step 16521: {'lr': 0.0004882174816459326, 'samples': 8459264, 'steps': 16521, 'loss/train': 1.4515050649642944}
-03/04/2022 08:52:19 - INFO - codeparrot_training - Step 16522: {'lr': 0.0004882158716367242, 'samples': 8459776, 'steps': 16522, 'loss/train': 1.5568034648895264}
-03/04/2022 08:52:21 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 08:52:25 - INFO - codeparrot_training - Step 16523: {'lr': 0.0004882142615201793, 'samples': 8460288, 'steps': 16523, 'loss/train': 1.9983128309249878}
-03/04/2022 08:52:28 - INFO - codeparrot_training - Step 16524: {'lr': 0.00048821265129629887, 'samples': 8460800, 'steps': 16524, 'loss/train': 1.3830703496932983}
-03/04/2022 08:52:30 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 08:52:33 - INFO - codeparrot_training - Step 16525: {'lr': 0.0004882110409650834, 'samples': 8461312, 'steps': 16525, 'loss/train': 2.3797736167907715}
-03/04/2022 08:52:36 - INFO - codeparrot_training - Step 16526: {'lr': 0.0004882094305265338, 'samples': 8461824, 'steps': 16526, 'loss/train': 1.6942509412765503}
-03/04/2022 08:52:39 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 08:52:42 - INFO - codeparrot_training - Step 16527: {'lr': 0.00048820781998065054, 'samples': 8462336, 'steps': 16527, 'loss/train': 1.725527048110962}
-03/04/2022 08:52:45 - INFO - codeparrot_training - Step 16528: {'lr': 0.00048820620932743465, 'samples': 8462848, 'steps': 16528, 'loss/train': 1.5236940383911133}
-03/04/2022 08:52:47 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/04/2022 08:52:50 - INFO - codeparrot_training - Step 16529: {'lr': 0.0004882045985668867, 'samples': 8463360, 'steps': 16529, 'loss/train': 1.4523777961730957}
-03/04/2022 08:52:53 - INFO - codeparrot_training - Step 16530: {'lr': 0.0004882029876990074, 'samples': 8463872, 'steps': 16530, 'loss/train': 1.6205475330352783}
-03/04/2022 08:52:56 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/04/2022 08:52:58 - INFO - codeparrot_training - Step 16531: {'lr': 0.0004882013767237975, 'samples': 8464384, 'steps': 16531, 'loss/train': 2.1257123947143555}
-03/04/2022 08:53:02 - INFO - codeparrot_training - Step 16532: {'lr': 0.0004881997656412578, 'samples': 8464896, 'steps': 16532, 'loss/train': 1.6770117282867432}
-03/04/2022 08:53:04 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/04/2022 08:53:07 - INFO - codeparrot_training - Step 16533: {'lr': 0.0004881981544513889, 'samples': 8465408, 'steps': 16533, 'loss/train': 1.9519438743591309}
-03/04/2022 08:53:10 - INFO - codeparrot_training - Step 16534: {'lr': 0.0004881965431541916, 'samples': 8465920, 'steps': 16534, 'loss/train': 1.8548449277877808}
-03/04/2022 08:53:13 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/04/2022 08:53:16 - INFO - codeparrot_training - Step 16535: {'lr': 0.0004881949317496667, 'samples': 8466432, 'steps': 16535, 'loss/train': 1.4767296314239502}
-03/04/2022 08:53:19 - INFO - codeparrot_training - Step 16536: {'lr': 0.0004881933202378147, 'samples': 8466944, 'steps': 16536, 'loss/train': 1.932114601135254}
-03/04/2022 08:53:21 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/04/2022 08:53:24 - INFO - codeparrot_training - Step 16537: {'lr': 0.0004881917086186365, 'samples': 8467456, 'steps': 16537, 'loss/train': 2.5938267707824707}
-03/04/2022 08:53:27 - INFO - codeparrot_training - Step 16538: {'lr': 0.0004881900968921328, 'samples': 8467968, 'steps': 16538, 'loss/train': 1.5332279205322266}
-03/04/2022 08:53:30 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/04/2022 08:53:32 - INFO - codeparrot_training - Step 16539: {'lr': 0.00048818848505830436, 'samples': 8468480, 'steps': 16539, 'loss/train': 1.6837527751922607}
-03/04/2022 08:53:36 - INFO - codeparrot_training - Step 16540: {'lr': 0.0004881868731171518, 'samples': 8468992, 'steps': 16540, 'loss/train': 3.549009323120117}
-03/04/2022 08:53:38 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/04/2022 08:53:41 - INFO - codeparrot_training - Step 16541: {'lr': 0.000488185261068676, 'samples': 8469504, 'steps': 16541, 'loss/train': 1.4544156789779663}
-03/04/2022 08:53:44 - INFO - codeparrot_training - Step 16542: {'lr': 0.0004881836489128776, 'samples': 8470016, 'steps': 16542, 'loss/train': 1.245230793952942}
-03/04/2022 08:53:46 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/04/2022 08:53:49 - INFO - codeparrot_training - Step 16543: {'lr': 0.00048818203664975727, 'samples': 8470528, 'steps': 16543, 'loss/train': 2.0431759357452393}
-03/04/2022 08:53:52 - INFO - codeparrot_training - Step 16544: {'lr': 0.00048818042427931573, 'samples': 8471040, 'steps': 16544, 'loss/train': 1.1005769968032837}
-03/04/2022 08:53:55 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 08:53:58 - INFO - codeparrot_training - Step 16545: {'lr': 0.00048817881180155385, 'samples': 8471552, 'steps': 16545, 'loss/train': 2.6497230529785156}
-03/04/2022 08:54:01 - INFO - codeparrot_training - Step 16546: {'lr': 0.0004881771992164722, 'samples': 8472064, 'steps': 16546, 'loss/train': 2.312631845474243}
-03/04/2022 08:54:03 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 08:54:06 - INFO - codeparrot_training - Step 16547: {'lr': 0.0004881755865240717, 'samples': 8472576, 'steps': 16547, 'loss/train': 1.629122018814087}
-03/04/2022 08:54:09 - INFO - codeparrot_training - Step 16548: {'lr': 0.0004881739737243528, 'samples': 8473088, 'steps': 16548, 'loss/train': 4.586852073669434}
-03/04/2022 08:54:11 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/04/2022 08:54:14 - INFO - codeparrot_training - Step 16549: {'lr': 0.00048817236081731655, 'samples': 8473600, 'steps': 16549, 'loss/train': 2.1240968704223633}
-03/04/2022 08:54:18 - INFO - codeparrot_training - Step 16550: {'lr': 0.0004881707478029634, 'samples': 8474112, 'steps': 16550, 'loss/train': 1.92020583152771}
-03/04/2022 08:54:20 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/04/2022 08:54:23 - INFO - codeparrot_training - Step 16551: {'lr': 0.0004881691346812942, 'samples': 8474624, 'steps': 16551, 'loss/train': 1.2693634033203125}
-03/04/2022 08:54:26 - INFO - codeparrot_training - Step 16552: {'lr': 0.0004881675214523097, 'samples': 8475136, 'steps': 16552, 'loss/train': 0.9423460960388184}
-03/04/2022 08:54:28 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/04/2022 08:54:31 - INFO - codeparrot_training - Step 16553: {'lr': 0.00048816590811601054, 'samples': 8475648, 'steps': 16553, 'loss/train': 1.7125828266143799}
-03/04/2022 08:54:35 - INFO - codeparrot_training - Step 16554: {'lr': 0.0004881642946723975, 'samples': 8476160, 'steps': 16554, 'loss/train': 1.2231742143630981}
-03/04/2022 08:54:36 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/04/2022 08:54:40 - INFO - codeparrot_training - Step 16555: {'lr': 0.00048816268112147134, 'samples': 8476672, 'steps': 16555, 'loss/train': 2.664358139038086}
-03/04/2022 08:54:43 - INFO - codeparrot_training - Step 16556: {'lr': 0.00048816106746323273, 'samples': 8477184, 'steps': 16556, 'loss/train': 0.9690961837768555}
-03/04/2022 08:54:45 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/04/2022 08:54:48 - INFO - codeparrot_training - Step 16557: {'lr': 0.00048815945369768245, 'samples': 8477696, 'steps': 16557, 'loss/train': 1.73697829246521}
-03/04/2022 08:54:51 - INFO - codeparrot_training - Step 16558: {'lr': 0.00048815783982482115, 'samples': 8478208, 'steps': 16558, 'loss/train': 1.9005706310272217}
-03/04/2022 08:54:54 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/04/2022 08:54:57 - INFO - codeparrot_training - Step 16559: {'lr': 0.0004881562258446496, 'samples': 8478720, 'steps': 16559, 'loss/train': 2.010918140411377}
-03/04/2022 08:55:00 - INFO - codeparrot_training - Step 16560: {'lr': 0.00048815461175716855, 'samples': 8479232, 'steps': 16560, 'loss/train': 1.6496511697769165}
-03/04/2022 08:55:02 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/04/2022 08:55:05 - INFO - codeparrot_training - Step 16561: {'lr': 0.00048815299756237873, 'samples': 8479744, 'steps': 16561, 'loss/train': 1.4427142143249512}
-03/04/2022 08:55:08 - INFO - codeparrot_training - Step 16562: {'lr': 0.0004881513832602808, 'samples': 8480256, 'steps': 16562, 'loss/train': 2.1401188373565674}
-03/04/2022 08:55:12 - INFO - codeparrot_training - Step 16563: {'lr': 0.0004881497688508756, 'samples': 8480768, 'steps': 16563, 'loss/train': 1.9297064542770386}
-03/04/2022 08:55:12 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 08:55:17 - INFO - codeparrot_training - Step 16564: {'lr': 0.0004881481543341637, 'samples': 8481280, 'steps': 16564, 'loss/train': 2.005859851837158}
-03/04/2022 08:55:20 - INFO - codeparrot_training - Step 16565: {'lr': 0.000488146539710146, 'samples': 8481792, 'steps': 16565, 'loss/train': 2.1767263412475586}
-03/04/2022 08:55:22 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 08:55:26 - INFO - codeparrot_training - Step 16566: {'lr': 0.00048814492497882306, 'samples': 8482304, 'steps': 16566, 'loss/train': 1.6742664575576782}
-03/04/2022 08:55:29 - INFO - codeparrot_training - Step 16567: {'lr': 0.00048814331014019577, 'samples': 8482816, 'steps': 16567, 'loss/train': 2.8731586933135986}
-03/04/2022 08:55:30 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/04/2022 08:55:34 - INFO - codeparrot_training - Step 16568: {'lr': 0.0004881416951942647, 'samples': 8483328, 'steps': 16568, 'loss/train': 5.4098005294799805}
-03/04/2022 08:55:37 - INFO - codeparrot_training - Step 16569: {'lr': 0.0004881400801410307, 'samples': 8483840, 'steps': 16569, 'loss/train': 1.516476035118103}
-03/04/2022 08:55:40 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 08:55:43 - INFO - codeparrot_training - Step 16570: {'lr': 0.0004881384649804945, 'samples': 8484352, 'steps': 16570, 'loss/train': 1.746759295463562}
-03/04/2022 08:55:46 - INFO - codeparrot_training - Step 16571: {'lr': 0.0004881368497126567, 'samples': 8484864, 'steps': 16571, 'loss/train': 1.6414941549301147}
-03/04/2022 08:55:48 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/04/2022 08:55:51 - INFO - codeparrot_training - Step 16572: {'lr': 0.00048813523433751814, 'samples': 8485376, 'steps': 16572, 'loss/train': 1.994202733039856}
-03/04/2022 08:55:54 - INFO - codeparrot_training - Step 16573: {'lr': 0.00048813361885507956, 'samples': 8485888, 'steps': 16573, 'loss/train': 1.460244059562683}
-03/04/2022 08:55:56 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 08:56:00 - INFO - codeparrot_training - Step 16574: {'lr': 0.00048813200326534156, 'samples': 8486400, 'steps': 16574, 'loss/train': 2.621657133102417}
-03/04/2022 08:56:03 - INFO - codeparrot_training - Step 16575: {'lr': 0.00048813038756830506, 'samples': 8486912, 'steps': 16575, 'loss/train': 1.9320424795150757}
-03/04/2022 08:56:06 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/04/2022 08:56:08 - INFO - codeparrot_training - Step 16576: {'lr': 0.00048812877176397066, 'samples': 8487424, 'steps': 16576, 'loss/train': 1.4567440748214722}
-03/04/2022 08:56:12 - INFO - codeparrot_training - Step 16577: {'lr': 0.00048812715585233905, 'samples': 8487936, 'steps': 16577, 'loss/train': 1.8638925552368164}
-03/04/2022 08:56:14 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/04/2022 08:56:17 - INFO - codeparrot_training - Step 16578: {'lr': 0.000488125539833411, 'samples': 8488448, 'steps': 16578, 'loss/train': 1.1370714902877808}
-03/04/2022 08:56:20 - INFO - codeparrot_training - Step 16579: {'lr': 0.0004881239237071873, 'samples': 8488960, 'steps': 16579, 'loss/train': 1.7270461320877075}
-03/04/2022 08:56:23 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/04/2022 08:56:25 - INFO - codeparrot_training - Step 16580: {'lr': 0.0004881223074736687, 'samples': 8489472, 'steps': 16580, 'loss/train': 2.0917625427246094}
-03/04/2022 08:56:28 - INFO - codeparrot_training - Step 16581: {'lr': 0.00048812069113285573, 'samples': 8489984, 'steps': 16581, 'loss/train': 1.518120527267456}
-03/04/2022 08:56:31 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/04/2022 08:56:34 - INFO - codeparrot_training - Step 16582: {'lr': 0.00048811907468474934, 'samples': 8490496, 'steps': 16582, 'loss/train': 0.1303931623697281}
-03/04/2022 08:56:37 - INFO - codeparrot_training - Step 16583: {'lr': 0.00048811745812935015, 'samples': 8491008, 'steps': 16583, 'loss/train': 2.194061756134033}
-03/04/2022 08:56:39 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/04/2022 08:56:42 - INFO - codeparrot_training - Step 16584: {'lr': 0.00048811584146665895, 'samples': 8491520, 'steps': 16584, 'loss/train': 1.5363976955413818}
-03/04/2022 08:56:45 - INFO - codeparrot_training - Step 16585: {'lr': 0.0004881142246966763, 'samples': 8492032, 'steps': 16585, 'loss/train': 2.0598225593566895}
-03/04/2022 08:56:48 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 08:56:50 - INFO - codeparrot_training - Step 16586: {'lr': 0.00048811260781940317, 'samples': 8492544, 'steps': 16586, 'loss/train': 0.2607193887233734}
-03/04/2022 08:56:54 - INFO - codeparrot_training - Step 16587: {'lr': 0.00048811099083484016, 'samples': 8493056, 'steps': 16587, 'loss/train': 1.5231043100357056}
-03/04/2022 08:56:56 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 08:56:59 - INFO - codeparrot_training - Step 16588: {'lr': 0.000488109373742988, 'samples': 8493568, 'steps': 16588, 'loss/train': 2.4526803493499756}
-03/04/2022 08:57:02 - INFO - codeparrot_training - Step 16589: {'lr': 0.0004881077565438474, 'samples': 8494080, 'steps': 16589, 'loss/train': 2.3064687252044678}
-03/04/2022 08:57:04 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/04/2022 08:57:07 - INFO - codeparrot_training - Step 16590: {'lr': 0.0004881061392374192, 'samples': 8494592, 'steps': 16590, 'loss/train': 1.3833872079849243}
-03/04/2022 08:57:10 - INFO - codeparrot_training - Step 16591: {'lr': 0.000488104521823704, 'samples': 8495104, 'steps': 16591, 'loss/train': 1.6452972888946533}
-03/04/2022 08:57:13 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/04/2022 08:57:16 - INFO - codeparrot_training - Step 16592: {'lr': 0.00048810290430270257, 'samples': 8495616, 'steps': 16592, 'loss/train': 2.212461233139038}
-03/04/2022 08:57:19 - INFO - codeparrot_training - Step 16593: {'lr': 0.0004881012866744156, 'samples': 8496128, 'steps': 16593, 'loss/train': 2.3824303150177}
-03/04/2022 08:57:21 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 08:57:24 - INFO - codeparrot_training - Step 16594: {'lr': 0.00048809966893884396, 'samples': 8496640, 'steps': 16594, 'loss/train': 1.6391851902008057}
-03/04/2022 08:57:27 - INFO - codeparrot_training - Step 16595: {'lr': 0.00048809805109598813, 'samples': 8497152, 'steps': 16595, 'loss/train': 1.965467929840088}
-03/04/2022 08:57:29 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/04/2022 08:57:32 - INFO - codeparrot_training - Step 16596: {'lr': 0.0004880964331458492, 'samples': 8497664, 'steps': 16596, 'loss/train': 2.131965398788452}
-03/04/2022 08:57:36 - INFO - codeparrot_training - Step 16597: {'lr': 0.0004880948150884276, 'samples': 8498176, 'steps': 16597, 'loss/train': 1.191604495048523}
-03/04/2022 08:57:38 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 08:57:41 - INFO - codeparrot_training - Step 16598: {'lr': 0.00048809319692372406, 'samples': 8498688, 'steps': 16598, 'loss/train': 1.635105013847351}
-03/04/2022 08:57:44 - INFO - codeparrot_training - Step 16599: {'lr': 0.0004880915786517395, 'samples': 8499200, 'steps': 16599, 'loss/train': 1.7494173049926758}
-03/04/2022 08:57:46 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/04/2022 08:57:49 - INFO - codeparrot_training - Step 16600: {'lr': 0.00048808996027247453, 'samples': 8499712, 'steps': 16600, 'loss/train': 1.7936832904815674}
-03/04/2022 08:57:52 - INFO - codeparrot_training - Step 16601: {'lr': 0.0004880883417859299, 'samples': 8500224, 'steps': 16601, 'loss/train': 1.9150307178497314}
-03/04/2022 08:57:54 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/04/2022 08:57:58 - INFO - codeparrot_training - Step 16602: {'lr': 0.0004880867231921063, 'samples': 8500736, 'steps': 16602, 'loss/train': 2.179809093475342}
-03/04/2022 08:58:01 - INFO - codeparrot_training - Step 16603: {'lr': 0.0004880851044910045, 'samples': 8501248, 'steps': 16603, 'loss/train': 1.3965831995010376}
-03/04/2022 08:58:03 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 08:58:06 - INFO - codeparrot_training - Step 16604: {'lr': 0.0004880834856826253, 'samples': 8501760, 'steps': 16604, 'loss/train': 1.848528504371643}
-03/04/2022 08:58:09 - INFO - codeparrot_training - Step 16605: {'lr': 0.0004880818667669693, 'samples': 8502272, 'steps': 16605, 'loss/train': 0.983249306678772}
-03/04/2022 08:58:11 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 08:58:14 - INFO - codeparrot_training - Step 16606: {'lr': 0.00048808024774403726, 'samples': 8502784, 'steps': 16606, 'loss/train': 2.7971549034118652}
-03/04/2022 08:58:18 - INFO - codeparrot_training - Step 16607: {'lr': 0.00048807862861382996, 'samples': 8503296, 'steps': 16607, 'loss/train': 2.3572897911071777}
-03/04/2022 08:58:19 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/04/2022 08:58:23 - INFO - codeparrot_training - Step 16608: {'lr': 0.0004880770093763481, 'samples': 8503808, 'steps': 16608, 'loss/train': 1.2899162769317627}
-03/04/2022 08:58:26 - INFO - codeparrot_training - Step 16609: {'lr': 0.0004880753900315924, 'samples': 8504320, 'steps': 16609, 'loss/train': 1.4081403017044067}
-03/04/2022 08:58:28 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/04/2022 08:58:31 - INFO - codeparrot_training - Step 16610: {'lr': 0.00048807377057956365, 'samples': 8504832, 'steps': 16610, 'loss/train': 2.1993486881256104}
-03/04/2022 08:58:35 - INFO - codeparrot_training - Step 16611: {'lr': 0.00048807215102026247, 'samples': 8505344, 'steps': 16611, 'loss/train': 1.9136772155761719}
-03/04/2022 08:58:36 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/04/2022 08:58:40 - INFO - codeparrot_training - Step 16612: {'lr': 0.00048807053135368973, 'samples': 8505856, 'steps': 16612, 'loss/train': 1.2492166757583618}
-03/04/2022 08:58:43 - INFO - codeparrot_training - Step 16613: {'lr': 0.00048806891157984604, 'samples': 8506368, 'steps': 16613, 'loss/train': 1.9695073366165161}
-03/04/2022 08:58:45 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 08:58:48 - INFO - codeparrot_training - Step 16614: {'lr': 0.0004880672916987322, 'samples': 8506880, 'steps': 16614, 'loss/train': 2.2194902896881104}
-03/04/2022 08:58:51 - INFO - codeparrot_training - Step 16615: {'lr': 0.0004880656717103489, 'samples': 8507392, 'steps': 16615, 'loss/train': 1.6845721006393433}
-03/04/2022 08:58:57 - INFO - codeparrot_training - Step 16616: {'lr': 0.0004880640516146968, 'samples': 8507904, 'steps': 16616, 'loss/train': 2.425220012664795}
-03/04/2022 08:59:00 - INFO - codeparrot_training - Step 16617: {'lr': 0.0004880624314117768, 'samples': 8508416, 'steps': 16617, 'loss/train': 2.359647274017334}
-03/04/2022 08:59:02 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 08:59:05 - INFO - codeparrot_training - Step 16618: {'lr': 0.0004880608111015895, 'samples': 8508928, 'steps': 16618, 'loss/train': 1.6987509727478027}
-03/04/2022 08:59:08 - INFO - codeparrot_training - Step 16619: {'lr': 0.00048805919068413574, 'samples': 8509440, 'steps': 16619, 'loss/train': 2.0077006816864014}
-03/04/2022 08:59:10 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/04/2022 08:59:13 - INFO - codeparrot_training - Step 16620: {'lr': 0.0004880575701594161, 'samples': 8509952, 'steps': 16620, 'loss/train': 2.5801820755004883}
-03/04/2022 08:59:17 - INFO - codeparrot_training - Step 16621: {'lr': 0.0004880559495274315, 'samples': 8510464, 'steps': 16621, 'loss/train': 2.3096323013305664}
-03/04/2022 08:59:19 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 08:59:22 - INFO - codeparrot_training - Step 16622: {'lr': 0.00048805432878818247, 'samples': 8510976, 'steps': 16622, 'loss/train': 1.8001234531402588}
-03/04/2022 08:59:25 - INFO - codeparrot_training - Step 16623: {'lr': 0.0004880527079416698, 'samples': 8511488, 'steps': 16623, 'loss/train': 1.8345078229904175}
-03/04/2022 08:59:27 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/04/2022 08:59:30 - INFO - codeparrot_training - Step 16624: {'lr': 0.00048805108698789435, 'samples': 8512000, 'steps': 16624, 'loss/train': 1.1190029382705688}
-03/04/2022 08:59:34 - INFO - codeparrot_training - Step 16625: {'lr': 0.00048804946592685667, 'samples': 8512512, 'steps': 16625, 'loss/train': 1.680300235748291}
-03/04/2022 08:59:36 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/04/2022 08:59:39 - INFO - codeparrot_training - Step 16626: {'lr': 0.0004880478447585576, 'samples': 8513024, 'steps': 16626, 'loss/train': 2.4135780334472656}
-03/04/2022 08:59:42 - INFO - codeparrot_training - Step 16627: {'lr': 0.00048804622348299785, 'samples': 8513536, 'steps': 16627, 'loss/train': 1.5653162002563477}
-03/04/2022 08:59:45 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/04/2022 08:59:48 - INFO - codeparrot_training - Step 16628: {'lr': 0.0004880446021001782, 'samples': 8514048, 'steps': 16628, 'loss/train': 0.38516438007354736}
-03/04/2022 08:59:51 - INFO - codeparrot_training - Step 16629: {'lr': 0.00048804298061009925, 'samples': 8514560, 'steps': 16629, 'loss/train': 2.3354785442352295}
-03/04/2022 08:59:54 - INFO - codeparrot_training - Step 16630: {'lr': 0.0004880413590127619, 'samples': 8515072, 'steps': 16630, 'loss/train': 1.5391613245010376}
-03/04/2022 08:59:54 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/04/2022 08:59:59 - INFO - codeparrot_training - Step 16631: {'lr': 0.0004880397373081666, 'samples': 8515584, 'steps': 16631, 'loss/train': 2.2083847522735596}
-03/04/2022 09:00:02 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 09:00:05 - INFO - codeparrot_training - Step 16632: {'lr': 0.0004880381154963145, 'samples': 8516096, 'steps': 16632, 'loss/train': 1.8506433963775635}
-03/04/2022 09:00:08 - INFO - codeparrot_training - Step 16633: {'lr': 0.0004880364935772059, 'samples': 8516608, 'steps': 16633, 'loss/train': 1.2671072483062744}
-03/04/2022 09:00:10 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/04/2022 09:00:13 - INFO - codeparrot_training - Step 16634: {'lr': 0.00048803487155084184, 'samples': 8517120, 'steps': 16634, 'loss/train': 1.402799367904663}
-03/04/2022 09:00:16 - INFO - codeparrot_training - Step 16635: {'lr': 0.00048803324941722295, 'samples': 8517632, 'steps': 16635, 'loss/train': 1.8695707321166992}
-03/04/2022 09:00:18 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 09:00:21 - INFO - codeparrot_training - Step 16636: {'lr': 0.0004880316271763499, 'samples': 8518144, 'steps': 16636, 'loss/train': 1.6234724521636963}
-03/04/2022 09:00:24 - INFO - codeparrot_training - Step 16637: {'lr': 0.0004880300048282235, 'samples': 8518656, 'steps': 16637, 'loss/train': 1.39134681224823}
-03/04/2022 09:00:27 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/04/2022 09:00:30 - INFO - codeparrot_training - Step 16638: {'lr': 0.00048802838237284443, 'samples': 8519168, 'steps': 16638, 'loss/train': 2.4961256980895996}
-03/04/2022 09:00:33 - INFO - codeparrot_training - Step 16639: {'lr': 0.0004880267598102135, 'samples': 8519680, 'steps': 16639, 'loss/train': 2.0822393894195557}
-03/04/2022 09:00:35 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 09:00:38 - INFO - codeparrot_training - Step 16640: {'lr': 0.0004880251371403313, 'samples': 8520192, 'steps': 16640, 'loss/train': 1.7616218328475952}
-03/04/2022 09:00:41 - INFO - codeparrot_training - Step 16641: {'lr': 0.0004880235143631987, 'samples': 8520704, 'steps': 16641, 'loss/train': 2.0404610633850098}
-03/04/2022 09:00:43 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/04/2022 09:00:47 - INFO - codeparrot_training - Step 16642: {'lr': 0.0004880218914788164, 'samples': 8521216, 'steps': 16642, 'loss/train': 1.8404872417449951}
-03/04/2022 09:00:50 - INFO - codeparrot_training - Step 16643: {'lr': 0.00048802026848718505, 'samples': 8521728, 'steps': 16643, 'loss/train': 2.1120808124542236}
-03/04/2022 09:00:52 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/04/2022 09:00:55 - INFO - codeparrot_training - Step 16644: {'lr': 0.0004880186453883054, 'samples': 8522240, 'steps': 16644, 'loss/train': 1.665408730506897}
-03/04/2022 09:00:58 - INFO - codeparrot_training - Step 16645: {'lr': 0.00048801702218217834, 'samples': 8522752, 'steps': 16645, 'loss/train': 1.1136960983276367}
-03/04/2022 09:01:00 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/04/2022 09:01:03 - INFO - codeparrot_training - Step 16646: {'lr': 0.0004880153988688044, 'samples': 8523264, 'steps': 16646, 'loss/train': 2.0179731845855713}
-03/04/2022 09:01:07 - INFO - codeparrot_training - Step 16647: {'lr': 0.0004880137754481845, 'samples': 8523776, 'steps': 16647, 'loss/train': 1.9022858142852783}
-03/04/2022 09:01:09 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/04/2022 09:01:12 - INFO - codeparrot_training - Step 16648: {'lr': 0.0004880121519203191, 'samples': 8524288, 'steps': 16648, 'loss/train': 2.039890766143799}
-03/04/2022 09:01:15 - INFO - codeparrot_training - Step 16649: {'lr': 0.0004880105282852092, 'samples': 8524800, 'steps': 16649, 'loss/train': 1.739603877067566}
-03/04/2022 09:01:17 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 09:01:20 - INFO - codeparrot_training - Step 16650: {'lr': 0.0004880089045428554, 'samples': 8525312, 'steps': 16650, 'loss/train': 2.0189335346221924}
-03/04/2022 09:01:23 - INFO - codeparrot_training - Step 16651: {'lr': 0.0004880072806932585, 'samples': 8525824, 'steps': 16651, 'loss/train': 2.2903056144714355}
-03/04/2022 09:01:26 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/04/2022 09:01:29 - INFO - codeparrot_training - Step 16652: {'lr': 0.00048800565673641917, 'samples': 8526336, 'steps': 16652, 'loss/train': 1.9041879177093506}
-03/04/2022 09:01:32 - INFO - codeparrot_training - Step 16653: {'lr': 0.0004880040326723382, 'samples': 8526848, 'steps': 16653, 'loss/train': 1.887171983718872}
-03/04/2022 09:01:35 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/04/2022 09:01:37 - INFO - codeparrot_training - Step 16654: {'lr': 0.0004880024085010162, 'samples': 8527360, 'steps': 16654, 'loss/train': 2.095214605331421}
-03/04/2022 09:01:40 - INFO - codeparrot_training - Step 16655: {'lr': 0.00048800078422245406, 'samples': 8527872, 'steps': 16655, 'loss/train': 1.6468513011932373}
-03/04/2022 09:01:44 - INFO - codeparrot_training - Step 16656: {'lr': 0.0004879991598366524, 'samples': 8528384, 'steps': 16656, 'loss/train': 1.9055964946746826}
-03/04/2022 09:01:44 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 09:01:49 - INFO - codeparrot_training - Step 16657: {'lr': 0.000487997535343612, 'samples': 8528896, 'steps': 16657, 'loss/train': 0.5104544758796692}
-03/04/2022 09:01:52 - INFO - codeparrot_training - Step 16658: {'lr': 0.0004879959107433336, 'samples': 8529408, 'steps': 16658, 'loss/train': 1.3045573234558105}
-03/04/2022 09:01:52 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/04/2022 09:01:57 - INFO - codeparrot_training - Step 16659: {'lr': 0.00048799428603581786, 'samples': 8529920, 'steps': 16659, 'loss/train': 1.5870933532714844}
-03/04/2022 09:02:00 - INFO - codeparrot_training - Step 16660: {'lr': 0.0004879926612210656, 'samples': 8530432, 'steps': 16660, 'loss/train': 2.5221951007843018}
-03/04/2022 09:02:01 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/04/2022 09:02:06 - INFO - codeparrot_training - Step 16661: {'lr': 0.0004879910362990775, 'samples': 8530944, 'steps': 16661, 'loss/train': 2.5674779415130615}
-03/04/2022 09:02:09 - INFO - codeparrot_training - Step 16662: {'lr': 0.0004879894112698544, 'samples': 8531456, 'steps': 16662, 'loss/train': 1.7332818508148193}
-03/04/2022 09:02:09 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 09:02:14 - INFO - codeparrot_training - Step 16663: {'lr': 0.0004879877861333969, 'samples': 8531968, 'steps': 16663, 'loss/train': 1.498223066329956}
-03/04/2022 09:02:17 - INFO - codeparrot_training - Step 16664: {'lr': 0.00048798616088970573, 'samples': 8532480, 'steps': 16664, 'loss/train': 0.8574267029762268}
-03/04/2022 09:02:17 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 09:02:23 - INFO - codeparrot_training - Step 16665: {'lr': 0.0004879845355387817, 'samples': 8532992, 'steps': 16665, 'loss/train': 2.1271824836730957}
-03/04/2022 09:02:26 - INFO - codeparrot_training - Step 16666: {'lr': 0.00048798291008062553, 'samples': 8533504, 'steps': 16666, 'loss/train': 1.761151909828186}
-03/04/2022 09:02:26 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/04/2022 09:02:31 - INFO - codeparrot_training - Step 16667: {'lr': 0.0004879812845152379, 'samples': 8534016, 'steps': 16667, 'loss/train': 1.2976549863815308}
-03/04/2022 09:02:34 - INFO - codeparrot_training - Step 16668: {'lr': 0.0004879796588426195, 'samples': 8534528, 'steps': 16668, 'loss/train': 2.0821914672851562}
-03/04/2022 09:02:35 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/04/2022 09:02:40 - INFO - codeparrot_training - Step 16669: {'lr': 0.0004879780330627713, 'samples': 8535040, 'steps': 16669, 'loss/train': 1.6671078205108643}
-03/04/2022 09:02:43 - INFO - codeparrot_training - Step 16670: {'lr': 0.0004879764071756938, 'samples': 8535552, 'steps': 16670, 'loss/train': 1.6932450532913208}
-03/04/2022 09:02:43 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/04/2022 09:02:48 - INFO - codeparrot_training - Step 16671: {'lr': 0.00048797478118138777, 'samples': 8536064, 'steps': 16671, 'loss/train': 1.9135266542434692}
-03/04/2022 09:02:51 - INFO - codeparrot_training - Step 16672: {'lr': 0.000487973155079854, 'samples': 8536576, 'steps': 16672, 'loss/train': 2.252218723297119}
-03/04/2022 09:02:52 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 09:02:56 - INFO - codeparrot_training - Step 16673: {'lr': 0.0004879715288710932, 'samples': 8537088, 'steps': 16673, 'loss/train': 0.8685274720191956}
-03/04/2022 09:03:00 - INFO - codeparrot_training - Step 16674: {'lr': 0.0004879699025551061, 'samples': 8537600, 'steps': 16674, 'loss/train': 1.9682334661483765}
-03/04/2022 09:03:00 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 09:03:05 - INFO - codeparrot_training - Step 16675: {'lr': 0.0004879682761318934, 'samples': 8538112, 'steps': 16675, 'loss/train': 2.4010026454925537}
-03/04/2022 09:03:08 - INFO - codeparrot_training - Step 16676: {'lr': 0.00048796664960145596, 'samples': 8538624, 'steps': 16676, 'loss/train': 1.5005769729614258}
-03/04/2022 09:03:08 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/04/2022 09:03:14 - INFO - codeparrot_training - Step 16677: {'lr': 0.00048796502296379437, 'samples': 8539136, 'steps': 16677, 'loss/train': 1.351193904876709}
-03/04/2022 09:03:17 - INFO - codeparrot_training - Step 16678: {'lr': 0.0004879633962189094, 'samples': 8539648, 'steps': 16678, 'loss/train': 2.5455265045166016}
-03/04/2022 09:03:17 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 09:03:22 - INFO - codeparrot_training - Step 16679: {'lr': 0.0004879617693668018, 'samples': 8540160, 'steps': 16679, 'loss/train': 1.5512962341308594}
-03/04/2022 09:03:25 - INFO - codeparrot_training - Step 16680: {'lr': 0.00048796014240747227, 'samples': 8540672, 'steps': 16680, 'loss/train': 1.5147302150726318}
-03/04/2022 09:03:27 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 09:03:31 - INFO - codeparrot_training - Step 16681: {'lr': 0.0004879585153409216, 'samples': 8541184, 'steps': 16681, 'loss/train': 1.8735524415969849}
-03/04/2022 09:03:34 - INFO - codeparrot_training - Step 16682: {'lr': 0.0004879568881671505, 'samples': 8541696, 'steps': 16682, 'loss/train': 2.0253565311431885}
-03/04/2022 09:03:35 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/04/2022 09:03:39 - INFO - codeparrot_training - Step 16683: {'lr': 0.0004879552608861597, 'samples': 8542208, 'steps': 16683, 'loss/train': 2.9551174640655518}
-03/04/2022 09:03:42 - INFO - codeparrot_training - Step 16684: {'lr': 0.00048795363349794996, 'samples': 8542720, 'steps': 16684, 'loss/train': 1.4628971815109253}
-03/04/2022 09:03:44 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/04/2022 09:03:48 - INFO - codeparrot_training - Step 16685: {'lr': 0.00048795200600252193, 'samples': 8543232, 'steps': 16685, 'loss/train': 1.9313147068023682}
-03/04/2022 09:03:51 - INFO - codeparrot_training - Step 16686: {'lr': 0.00048795037839987644, 'samples': 8543744, 'steps': 16686, 'loss/train': 1.8491053581237793}
-03/04/2022 09:03:52 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/04/2022 09:03:56 - INFO - codeparrot_training - Step 16687: {'lr': 0.0004879487506900141, 'samples': 8544256, 'steps': 16687, 'loss/train': 4.9222917556762695}
-03/04/2022 09:03:59 - INFO - codeparrot_training - Step 16688: {'lr': 0.0004879471228729358, 'samples': 8544768, 'steps': 16688, 'loss/train': 1.630972146987915}
-03/04/2022 09:04:01 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/04/2022 09:04:04 - INFO - codeparrot_training - Step 16689: {'lr': 0.0004879454949486422, 'samples': 8545280, 'steps': 16689, 'loss/train': 1.4569423198699951}
-03/04/2022 09:04:08 - INFO - codeparrot_training - Step 16690: {'lr': 0.000487943866917134, 'samples': 8545792, 'steps': 16690, 'loss/train': 2.64225697517395}
-03/04/2022 09:04:09 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 09:04:13 - INFO - codeparrot_training - Step 16691: {'lr': 0.00048794223877841197, 'samples': 8546304, 'steps': 16691, 'loss/train': 1.6660428047180176}
-03/04/2022 09:04:16 - INFO - codeparrot_training - Step 16692: {'lr': 0.00048794061053247686, 'samples': 8546816, 'steps': 16692, 'loss/train': 1.0559406280517578}
-03/04/2022 09:04:19 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/04/2022 09:04:22 - INFO - codeparrot_training - Step 16693: {'lr': 0.0004879389821793294, 'samples': 8547328, 'steps': 16693, 'loss/train': 2.074751377105713}
-03/04/2022 09:04:25 - INFO - codeparrot_training - Step 16694: {'lr': 0.00048793735371897027, 'samples': 8547840, 'steps': 16694, 'loss/train': 2.5704195499420166}
-03/04/2022 09:04:27 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/04/2022 09:04:30 - INFO - codeparrot_training - Step 16695: {'lr': 0.00048793572515140024, 'samples': 8548352, 'steps': 16695, 'loss/train': 1.7796664237976074}
-03/04/2022 09:04:33 - INFO - codeparrot_training - Step 16696: {'lr': 0.00048793409647662, 'samples': 8548864, 'steps': 16696, 'loss/train': 2.454838275909424}
-03/04/2022 09:04:36 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/04/2022 09:04:39 - INFO - codeparrot_training - Step 16697: {'lr': 0.0004879324676946304, 'samples': 8549376, 'steps': 16697, 'loss/train': 2.831484079360962}
-03/04/2022 09:04:42 - INFO - codeparrot_training - Step 16698: {'lr': 0.0004879308388054321, 'samples': 8549888, 'steps': 16698, 'loss/train': 1.5918872356414795}
-03/04/2022 09:04:44 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/04/2022 09:04:47 - INFO - codeparrot_training - Step 16699: {'lr': 0.0004879292098090258, 'samples': 8550400, 'steps': 16699, 'loss/train': 2.4023540019989014}
-03/04/2022 09:04:50 - INFO - codeparrot_training - Step 16700: {'lr': 0.00048792758070541234, 'samples': 8550912, 'steps': 16700, 'loss/train': 1.765406608581543}
-03/04/2022 09:04:53 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 09:04:56 - INFO - codeparrot_training - Step 16701: {'lr': 0.00048792595149459226, 'samples': 8551424, 'steps': 16701, 'loss/train': 0.5077486634254456}
-03/04/2022 09:04:59 - INFO - codeparrot_training - Step 16702: {'lr': 0.0004879243221765665, 'samples': 8551936, 'steps': 16702, 'loss/train': 1.7503204345703125}
-03/04/2022 09:05:02 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/04/2022 09:05:04 - INFO - codeparrot_training - Step 16703: {'lr': 0.00048792269275133574, 'samples': 8552448, 'steps': 16703, 'loss/train': 2.37258243560791}
-03/04/2022 09:05:07 - INFO - codeparrot_training - Step 16704: {'lr': 0.0004879210632189006, 'samples': 8552960, 'steps': 16704, 'loss/train': 2.250486135482788}
-03/04/2022 09:05:11 - INFO - codeparrot_training - Step 16705: {'lr': 0.0004879194335792619, 'samples': 8553472, 'steps': 16705, 'loss/train': 0.5273582935333252}
-03/04/2022 09:05:11 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/04/2022 09:05:16 - INFO - codeparrot_training - Step 16706: {'lr': 0.0004879178038324205, 'samples': 8553984, 'steps': 16706, 'loss/train': 2.17018723487854}
-03/04/2022 09:05:19 - INFO - codeparrot_training - Step 16707: {'lr': 0.0004879161739783769, 'samples': 8554496, 'steps': 16707, 'loss/train': 2.2166433334350586}
-03/04/2022 09:05:20 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/04/2022 09:05:24 - INFO - codeparrot_training - Step 16708: {'lr': 0.00048791454401713195, 'samples': 8555008, 'steps': 16708, 'loss/train': 2.136784553527832}
-03/04/2022 09:05:28 - INFO - codeparrot_training - Step 16709: {'lr': 0.00048791291394868644, 'samples': 8555520, 'steps': 16709, 'loss/train': 2.529398202896118}
-03/04/2022 09:05:28 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/04/2022 09:05:33 - INFO - codeparrot_training - Step 16710: {'lr': 0.000487911283773041, 'samples': 8556032, 'steps': 16710, 'loss/train': 2.0423038005828857}
-03/04/2022 09:05:36 - INFO - codeparrot_training - Step 16711: {'lr': 0.0004879096534901964, 'samples': 8556544, 'steps': 16711, 'loss/train': 3.4875011444091797}
-03/04/2022 09:05:37 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 09:05:41 - INFO - codeparrot_training - Step 16712: {'lr': 0.00048790802310015336, 'samples': 8557056, 'steps': 16712, 'loss/train': 1.6342641115188599}
-03/04/2022 09:05:44 - INFO - codeparrot_training - Step 16713: {'lr': 0.0004879063926029127, 'samples': 8557568, 'steps': 16713, 'loss/train': 1.3797892332077026}
-03/04/2022 09:05:45 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 09:05:50 - INFO - codeparrot_training - Step 16714: {'lr': 0.00048790476199847506, 'samples': 8558080, 'steps': 16714, 'loss/train': 2.3978869915008545}
-03/04/2022 09:05:53 - INFO - codeparrot_training - Step 16715: {'lr': 0.0004879031312868412, 'samples': 8558592, 'steps': 16715, 'loss/train': 1.9270598888397217}
-03/04/2022 09:05:53 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/04/2022 09:05:58 - INFO - codeparrot_training - Step 16716: {'lr': 0.00048790150046801187, 'samples': 8559104, 'steps': 16716, 'loss/train': 2.549328327178955}
-03/04/2022 09:06:01 - INFO - codeparrot_training - Step 16717: {'lr': 0.0004878998695419877, 'samples': 8559616, 'steps': 16717, 'loss/train': 1.8845922946929932}
-03/04/2022 09:06:02 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 09:06:06 - INFO - codeparrot_training - Step 16718: {'lr': 0.0004878982385087697, 'samples': 8560128, 'steps': 16718, 'loss/train': 2.2903623580932617}
-03/04/2022 09:06:10 - INFO - codeparrot_training - Step 16719: {'lr': 0.0004878966073683583, 'samples': 8560640, 'steps': 16719, 'loss/train': 0.9374154210090637}
-03/04/2022 09:06:10 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/04/2022 09:06:15 - INFO - codeparrot_training - Step 16720: {'lr': 0.0004878949761207544, 'samples': 8561152, 'steps': 16720, 'loss/train': 1.3983957767486572}
-03/04/2022 09:06:18 - INFO - codeparrot_training - Step 16721: {'lr': 0.0004878933447659587, 'samples': 8561664, 'steps': 16721, 'loss/train': 2.1902999877929688}
-03/04/2022 09:06:19 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/04/2022 09:06:23 - INFO - codeparrot_training - Step 16722: {'lr': 0.0004878917133039719, 'samples': 8562176, 'steps': 16722, 'loss/train': 2.1337084770202637}
-03/04/2022 09:06:26 - INFO - codeparrot_training - Step 16723: {'lr': 0.00048789008173479476, 'samples': 8562688, 'steps': 16723, 'loss/train': 1.9695619344711304}
-03/04/2022 09:06:27 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/04/2022 09:06:32 - INFO - codeparrot_training - Step 16724: {'lr': 0.0004878884500584281, 'samples': 8563200, 'steps': 16724, 'loss/train': 1.370527744293213}
-03/04/2022 09:06:35 - INFO - codeparrot_training - Step 16725: {'lr': 0.0004878868182748725, 'samples': 8563712, 'steps': 16725, 'loss/train': 0.3641508221626282}
-03/04/2022 09:06:36 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 09:06:40 - INFO - codeparrot_training - Step 16726: {'lr': 0.0004878851863841287, 'samples': 8564224, 'steps': 16726, 'loss/train': 1.5229601860046387}
-03/04/2022 09:06:43 - INFO - codeparrot_training - Step 16727: {'lr': 0.00048788355438619764, 'samples': 8564736, 'steps': 16727, 'loss/train': 1.4827646017074585}
-03/04/2022 09:06:44 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/04/2022 09:06:49 - INFO - codeparrot_training - Step 16728: {'lr': 0.00048788192228107986, 'samples': 8565248, 'steps': 16728, 'loss/train': 2.850599765777588}
-03/04/2022 09:06:52 - INFO - codeparrot_training - Step 16729: {'lr': 0.00048788029006877623, 'samples': 8565760, 'steps': 16729, 'loss/train': 2.25079607963562}
-03/04/2022 09:06:52 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/04/2022 09:06:57 - INFO - codeparrot_training - Step 16730: {'lr': 0.0004878786577492873, 'samples': 8566272, 'steps': 16730, 'loss/train': 1.6387897729873657}
-03/04/2022 09:07:00 - INFO - codeparrot_training - Step 16731: {'lr': 0.00048787702532261396, 'samples': 8566784, 'steps': 16731, 'loss/train': 2.0271520614624023}
-03/04/2022 09:07:01 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 09:07:05 - INFO - codeparrot_training - Step 16732: {'lr': 0.0004878753927887569, 'samples': 8567296, 'steps': 16732, 'loss/train': 2.5411384105682373}
-03/04/2022 09:07:09 - INFO - codeparrot_training - Step 16733: {'lr': 0.0004878737601477169, 'samples': 8567808, 'steps': 16733, 'loss/train': 2.135249376296997}
-03/04/2022 09:07:09 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 09:07:14 - INFO - codeparrot_training - Step 16734: {'lr': 0.0004878721273994946, 'samples': 8568320, 'steps': 16734, 'loss/train': 1.8367668390274048}
-03/04/2022 09:07:17 - INFO - codeparrot_training - Step 16735: {'lr': 0.00048787049454409085, 'samples': 8568832, 'steps': 16735, 'loss/train': 1.0575274229049683}
-03/04/2022 09:07:18 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/04/2022 09:07:22 - INFO - codeparrot_training - Step 16736: {'lr': 0.0004878688615815063, 'samples': 8569344, 'steps': 16736, 'loss/train': 1.688331127166748}
-03/04/2022 09:07:25 - INFO - codeparrot_training - Step 16737: {'lr': 0.0004878672285117417, 'samples': 8569856, 'steps': 16737, 'loss/train': 2.2730164527893066}
-03/04/2022 09:07:26 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/04/2022 09:07:31 - INFO - codeparrot_training - Step 16738: {'lr': 0.0004878655953347978, 'samples': 8570368, 'steps': 16738, 'loss/train': 1.7579344511032104}
-03/04/2022 09:07:34 - INFO - codeparrot_training - Step 16739: {'lr': 0.0004878639620506753, 'samples': 8570880, 'steps': 16739, 'loss/train': 2.4228334426879883}
-03/04/2022 09:07:34 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 09:07:39 - INFO - codeparrot_training - Step 16740: {'lr': 0.00048786232865937504, 'samples': 8571392, 'steps': 16740, 'loss/train': 1.3742014169692993}
-03/04/2022 09:07:42 - INFO - codeparrot_training - Step 16741: {'lr': 0.0004878606951608976, 'samples': 8571904, 'steps': 16741, 'loss/train': 1.9895243644714355}
-03/04/2022 09:07:43 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/04/2022 09:07:48 - INFO - codeparrot_training - Step 16742: {'lr': 0.00048785906155524386, 'samples': 8572416, 'steps': 16742, 'loss/train': 1.8570005893707275}
-03/04/2022 09:07:51 - INFO - codeparrot_training - Step 16743: {'lr': 0.0004878574278424145, 'samples': 8572928, 'steps': 16743, 'loss/train': 2.195761203765869}
-03/04/2022 09:07:51 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 09:07:56 - INFO - codeparrot_training - Step 16744: {'lr': 0.0004878557940224102, 'samples': 8573440, 'steps': 16744, 'loss/train': 1.3034437894821167}
-03/04/2022 09:07:59 - INFO - codeparrot_training - Step 16745: {'lr': 0.0004878541600952318, 'samples': 8573952, 'steps': 16745, 'loss/train': 2.34202241897583}
-03/04/2022 09:08:00 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 09:08:05 - INFO - codeparrot_training - Step 16746: {'lr': 0.00048785252606087996, 'samples': 8574464, 'steps': 16746, 'loss/train': 1.6847962141036987}
-03/04/2022 09:08:08 - INFO - codeparrot_training - Step 16747: {'lr': 0.0004878508919193555, 'samples': 8574976, 'steps': 16747, 'loss/train': 1.8350378274917603}
-03/04/2022 09:08:09 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/04/2022 09:08:13 - INFO - codeparrot_training - Step 16748: {'lr': 0.000487849257670659, 'samples': 8575488, 'steps': 16748, 'loss/train': 1.8376457691192627}
-03/04/2022 09:08:16 - INFO - codeparrot_training - Step 16749: {'lr': 0.0004878476233147914, 'samples': 8576000, 'steps': 16749, 'loss/train': 2.877941370010376}
-03/04/2022 09:08:17 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 09:08:22 - INFO - codeparrot_training - Step 16750: {'lr': 0.00048784598885175324, 'samples': 8576512, 'steps': 16750, 'loss/train': 1.2408077716827393}
-03/04/2022 09:08:25 - INFO - codeparrot_training - Step 16751: {'lr': 0.00048784435428154537, 'samples': 8577024, 'steps': 16751, 'loss/train': 1.8337435722351074}
-03/04/2022 09:08:26 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 09:08:30 - INFO - codeparrot_training - Step 16752: {'lr': 0.0004878427196041686, 'samples': 8577536, 'steps': 16752, 'loss/train': 2.547670841217041}
-03/04/2022 09:08:33 - INFO - codeparrot_training - Step 16753: {'lr': 0.00048784108481962347, 'samples': 8578048, 'steps': 16753, 'loss/train': 6.489173412322998}
-03/04/2022 09:08:36 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 09:08:39 - INFO - codeparrot_training - Step 16754: {'lr': 0.00048783944992791085, 'samples': 8578560, 'steps': 16754, 'loss/train': 1.5650520324707031}
-03/04/2022 09:08:42 - INFO - codeparrot_training - Step 16755: {'lr': 0.00048783781492903145, 'samples': 8579072, 'steps': 16755, 'loss/train': 2.4490368366241455}
-03/04/2022 09:08:44 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/04/2022 09:08:47 - INFO - codeparrot_training - Step 16756: {'lr': 0.00048783617982298594, 'samples': 8579584, 'steps': 16756, 'loss/train': 2.366964340209961}
-03/04/2022 09:08:50 - INFO - codeparrot_training - Step 16757: {'lr': 0.00048783454460977517, 'samples': 8580096, 'steps': 16757, 'loss/train': 1.4457862377166748}
-03/04/2022 09:08:54 - INFO - codeparrot_training - Step 16758: {'lr': 0.00048783290928939985, 'samples': 8580608, 'steps': 16758, 'loss/train': 0.7980867624282837}
-03/04/2022 09:08:54 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/04/2022 09:08:59 - INFO - codeparrot_training - Step 16759: {'lr': 0.00048783127386186064, 'samples': 8581120, 'steps': 16759, 'loss/train': 1.9489564895629883}
-03/04/2022 09:09:02 - INFO - codeparrot_training - Step 16760: {'lr': 0.00048782963832715834, 'samples': 8581632, 'steps': 16760, 'loss/train': 1.7456711530685425}
-03/04/2022 09:09:02 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/04/2022 09:09:07 - INFO - codeparrot_training - Step 16761: {'lr': 0.0004878280026852937, 'samples': 8582144, 'steps': 16761, 'loss/train': 1.222352385520935}
-03/04/2022 09:09:10 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 09:09:12 - INFO - codeparrot_training - Step 16762: {'lr': 0.00048782636693626736, 'samples': 8582656, 'steps': 16762, 'loss/train': 2.1475255489349365}
-03/04/2022 09:09:16 - INFO - codeparrot_training - Step 16763: {'lr': 0.0004878247310800802, 'samples': 8583168, 'steps': 16763, 'loss/train': 1.7000850439071655}
-03/04/2022 09:09:18 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/04/2022 09:09:21 - INFO - codeparrot_training - Step 16764: {'lr': 0.0004878230951167328, 'samples': 8583680, 'steps': 16764, 'loss/train': 1.8506168127059937}
-03/04/2022 09:09:24 - INFO - codeparrot_training - Step 16765: {'lr': 0.0004878214590462261, 'samples': 8584192, 'steps': 16765, 'loss/train': 2.3854928016662598}
-03/04/2022 09:09:26 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 09:09:29 - INFO - codeparrot_training - Step 16766: {'lr': 0.0004878198228685607, 'samples': 8584704, 'steps': 16766, 'loss/train': 2.3422558307647705}
-03/04/2022 09:09:32 - INFO - codeparrot_training - Step 16767: {'lr': 0.00048781818658373734, 'samples': 8585216, 'steps': 16767, 'loss/train': 1.6928225755691528}
-03/04/2022 09:09:35 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/04/2022 09:09:38 - INFO - codeparrot_training - Step 16768: {'lr': 0.00048781655019175676, 'samples': 8585728, 'steps': 16768, 'loss/train': 1.8302969932556152}
-03/04/2022 09:09:41 - INFO - codeparrot_training - Step 16769: {'lr': 0.00048781491369261965, 'samples': 8586240, 'steps': 16769, 'loss/train': 1.6847326755523682}
-03/04/2022 09:09:43 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 09:09:46 - INFO - codeparrot_training - Step 16770: {'lr': 0.00048781327708632695, 'samples': 8586752, 'steps': 16770, 'loss/train': 1.6954201459884644}
-03/04/2022 09:09:49 - INFO - codeparrot_training - Step 16771: {'lr': 0.0004878116403728792, 'samples': 8587264, 'steps': 16771, 'loss/train': 2.2453973293304443}
-03/04/2022 09:09:52 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 09:09:55 - INFO - codeparrot_training - Step 16772: {'lr': 0.0004878100035522771, 'samples': 8587776, 'steps': 16772, 'loss/train': 1.6055817604064941}
-03/04/2022 09:09:58 - INFO - codeparrot_training - Step 16773: {'lr': 0.00048780836662452154, 'samples': 8588288, 'steps': 16773, 'loss/train': 1.3732736110687256}
-03/04/2022 09:10:00 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 09:10:03 - INFO - codeparrot_training - Step 16774: {'lr': 0.00048780672958961325, 'samples': 8588800, 'steps': 16774, 'loss/train': 1.4095689058303833}
-03/04/2022 09:10:06 - INFO - codeparrot_training - Step 16775: {'lr': 0.0004878050924475529, 'samples': 8589312, 'steps': 16775, 'loss/train': 1.9039345979690552}
-03/04/2022 09:10:09 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/04/2022 09:10:11 - INFO - codeparrot_training - Step 16776: {'lr': 0.00048780345519834124, 'samples': 8589824, 'steps': 16776, 'loss/train': 1.191585659980774}
-03/04/2022 09:10:15 - INFO - codeparrot_training - Step 16777: {'lr': 0.000487801817841979, 'samples': 8590336, 'steps': 16777, 'loss/train': 0.9453536868095398}
-03/04/2022 09:10:17 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/04/2022 09:10:21 - INFO - codeparrot_training - Step 16778: {'lr': 0.0004878001803784669, 'samples': 8590848, 'steps': 16778, 'loss/train': 1.7707719802856445}
-03/04/2022 09:10:24 - INFO - codeparrot_training - Step 16779: {'lr': 0.00048779854280780576, 'samples': 8591360, 'steps': 16779, 'loss/train': 1.0595307350158691}
-03/04/2022 09:10:27 - INFO - codeparrot_training - Step 16780: {'lr': 0.00048779690512999627, 'samples': 8591872, 'steps': 16780, 'loss/train': 0.5918049812316895}
-03/04/2022 09:10:28 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/04/2022 09:10:32 - INFO - codeparrot_training - Step 16781: {'lr': 0.0004877952673450391, 'samples': 8592384, 'steps': 16781, 'loss/train': 1.9472204446792603}
-03/04/2022 09:10:35 - INFO - codeparrot_training - Step 16782: {'lr': 0.0004877936294529351, 'samples': 8592896, 'steps': 16782, 'loss/train': 2.1891071796417236}
-03/04/2022 09:10:36 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/04/2022 09:10:41 - INFO - codeparrot_training - Step 16783: {'lr': 0.00048779199145368494, 'samples': 8593408, 'steps': 16783, 'loss/train': 1.0650302171707153}
-03/04/2022 09:10:44 - INFO - codeparrot_training - Step 16784: {'lr': 0.0004877903533472894, 'samples': 8593920, 'steps': 16784, 'loss/train': 2.2744765281677246}
-03/04/2022 09:10:45 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/04/2022 09:10:49 - INFO - codeparrot_training - Step 16785: {'lr': 0.0004877887151337492, 'samples': 8594432, 'steps': 16785, 'loss/train': 1.9492017030715942}
-03/04/2022 09:10:52 - INFO - codeparrot_training - Step 16786: {'lr': 0.0004877870768130651, 'samples': 8594944, 'steps': 16786, 'loss/train': 2.0014824867248535}
-03/04/2022 09:10:53 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/04/2022 09:10:57 - INFO - codeparrot_training - Step 16787: {'lr': 0.0004877854383852377, 'samples': 8595456, 'steps': 16787, 'loss/train': 2.024102210998535}
-03/04/2022 09:11:01 - INFO - codeparrot_training - Step 16788: {'lr': 0.000487783799850268, 'samples': 8595968, 'steps': 16788, 'loss/train': 1.4918347597122192}
-03/04/2022 09:11:01 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/04/2022 09:11:06 - INFO - codeparrot_training - Step 16789: {'lr': 0.00048778216120815644, 'samples': 8596480, 'steps': 16789, 'loss/train': 2.108762741088867}
-03/04/2022 09:11:09 - INFO - codeparrot_training - Step 16790: {'lr': 0.00048778052245890404, 'samples': 8596992, 'steps': 16790, 'loss/train': 2.3487672805786133}
-03/04/2022 09:11:10 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 09:11:14 - INFO - codeparrot_training - Step 16791: {'lr': 0.0004877788836025113, 'samples': 8597504, 'steps': 16791, 'loss/train': 1.0121835470199585}
-03/04/2022 09:11:17 - INFO - codeparrot_training - Step 16792: {'lr': 0.0004877772446389791, 'samples': 8598016, 'steps': 16792, 'loss/train': 2.469670295715332}
-03/04/2022 09:11:18 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/04/2022 09:11:23 - INFO - codeparrot_training - Step 16793: {'lr': 0.0004877756055683082, 'samples': 8598528, 'steps': 16793, 'loss/train': 0.41385364532470703}
-03/04/2022 09:11:26 - INFO - codeparrot_training - Step 16794: {'lr': 0.0004877739663904992, 'samples': 8599040, 'steps': 16794, 'loss/train': 2.033597707748413}
-03/04/2022 09:11:26 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/04/2022 09:11:31 - INFO - codeparrot_training - Step 16795: {'lr': 0.00048777232710555296, 'samples': 8599552, 'steps': 16795, 'loss/train': 1.7967733144760132}
-03/04/2022 09:11:34 - INFO - codeparrot_training - Step 16796: {'lr': 0.0004877706877134702, 'samples': 8600064, 'steps': 16796, 'loss/train': 1.6678260564804077}
-03/04/2022 09:11:35 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 09:11:40 - INFO - codeparrot_training - Step 16797: {'lr': 0.0004877690482142516, 'samples': 8600576, 'steps': 16797, 'loss/train': 1.972100019454956}
-03/04/2022 09:11:43 - INFO - codeparrot_training - Step 16798: {'lr': 0.0004877674086078979, 'samples': 8601088, 'steps': 16798, 'loss/train': 2.4862613677978516}
-03/04/2022 09:11:44 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 09:11:48 - INFO - codeparrot_training - Step 16799: {'lr': 0.0004877657688944099, 'samples': 8601600, 'steps': 16799, 'loss/train': 1.739594578742981}
-03/04/2022 09:11:51 - INFO - codeparrot_training - Step 16800: {'lr': 0.0004877641290737884, 'samples': 8602112, 'steps': 16800, 'loss/train': 1.928982138633728}
-03/04/2022 09:11:53 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 09:11:56 - INFO - codeparrot_training - Step 16801: {'lr': 0.000487762489146034, 'samples': 8602624, 'steps': 16801, 'loss/train': 1.5922176837921143}
-03/04/2022 09:12:00 - INFO - codeparrot_training - Step 16802: {'lr': 0.0004877608491111475, 'samples': 8603136, 'steps': 16802, 'loss/train': 2.1041958332061768}
-03/04/2022 09:12:01 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 09:12:05 - INFO - codeparrot_training - Step 16803: {'lr': 0.0004877592089691296, 'samples': 8603648, 'steps': 16803, 'loss/train': 6.40061616897583}
-03/04/2022 09:12:08 - INFO - codeparrot_training - Step 16804: {'lr': 0.00048775756871998106, 'samples': 8604160, 'steps': 16804, 'loss/train': 1.7058134078979492}
-03/04/2022 09:12:10 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/04/2022 09:12:13 - INFO - codeparrot_training - Step 16805: {'lr': 0.0004877559283637026, 'samples': 8604672, 'steps': 16805, 'loss/train': 1.8942151069641113}
-03/04/2022 09:12:17 - INFO - codeparrot_training - Step 16806: {'lr': 0.0004877542879002951, 'samples': 8605184, 'steps': 16806, 'loss/train': 1.3459999561309814}
-03/04/2022 09:12:18 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/04/2022 09:12:22 - INFO - codeparrot_training - Step 16807: {'lr': 0.0004877526473297591, 'samples': 8605696, 'steps': 16807, 'loss/train': 2.0614078044891357}
-03/04/2022 09:12:25 - INFO - codeparrot_training - Step 16808: {'lr': 0.0004877510066520954, 'samples': 8606208, 'steps': 16808, 'loss/train': 1.862703561782837}
-03/04/2022 09:12:26 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 09:12:30 - INFO - codeparrot_training - Step 16809: {'lr': 0.0004877493658673048, 'samples': 8606720, 'steps': 16809, 'loss/train': 2.9184420108795166}
-03/04/2022 09:12:33 - INFO - codeparrot_training - Step 16810: {'lr': 0.00048774772497538806, 'samples': 8607232, 'steps': 16810, 'loss/train': 1.9242480993270874}
-03/04/2022 09:12:35 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/04/2022 09:12:39 - INFO - codeparrot_training - Step 16811: {'lr': 0.0004877460839763458, 'samples': 8607744, 'steps': 16811, 'loss/train': 2.3118088245391846}
-03/04/2022 09:12:42 - INFO - codeparrot_training - Step 16812: {'lr': 0.0004877444428701788, 'samples': 8608256, 'steps': 16812, 'loss/train': 2.727816343307495}
-03/04/2022 09:12:43 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/04/2022 09:12:47 - INFO - codeparrot_training - Step 16813: {'lr': 0.0004877428016568879, 'samples': 8608768, 'steps': 16813, 'loss/train': 1.2772276401519775}
-03/04/2022 09:12:50 - INFO - codeparrot_training - Step 16814: {'lr': 0.00048774116033647373, 'samples': 8609280, 'steps': 16814, 'loss/train': 2.22672700881958}
-03/04/2022 09:12:51 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 09:12:56 - INFO - codeparrot_training - Step 16815: {'lr': 0.0004877395189089371, 'samples': 8609792, 'steps': 16815, 'loss/train': 1.1322365999221802}
-03/04/2022 09:12:59 - INFO - codeparrot_training - Step 16816: {'lr': 0.00048773787737427867, 'samples': 8610304, 'steps': 16816, 'loss/train': 1.9681241512298584}
-03/04/2022 09:13:00 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 09:13:04 - INFO - codeparrot_training - Step 16817: {'lr': 0.0004877362357324992, 'samples': 8610816, 'steps': 16817, 'loss/train': 2.3060851097106934}
-03/04/2022 09:13:07 - INFO - codeparrot_training - Step 16818: {'lr': 0.0004877345939835995, 'samples': 8611328, 'steps': 16818, 'loss/train': 1.7466137409210205}
-03/04/2022 09:13:08 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/04/2022 09:13:12 - INFO - codeparrot_training - Step 16819: {'lr': 0.0004877329521275802, 'samples': 8611840, 'steps': 16819, 'loss/train': 1.6963021755218506}
-03/04/2022 09:13:16 - INFO - codeparrot_training - Step 16820: {'lr': 0.0004877313101644422, 'samples': 8612352, 'steps': 16820, 'loss/train': 1.8235007524490356}
-03/04/2022 09:13:17 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 09:13:21 - INFO - codeparrot_training - Step 16821: {'lr': 0.000487729668094186, 'samples': 8612864, 'steps': 16821, 'loss/train': 1.168093204498291}
-03/04/2022 09:13:24 - INFO - codeparrot_training - Step 16822: {'lr': 0.0004877280259168125, 'samples': 8613376, 'steps': 16822, 'loss/train': 1.7980440855026245}
-03/04/2022 09:13:25 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 09:13:30 - INFO - codeparrot_training - Step 16823: {'lr': 0.0004877263836323226, 'samples': 8613888, 'steps': 16823, 'loss/train': 2.24636173248291}
-03/04/2022 09:13:33 - INFO - codeparrot_training - Step 16824: {'lr': 0.00048772474124071663, 'samples': 8614400, 'steps': 16824, 'loss/train': 1.5120302438735962}
-03/04/2022 09:13:36 - INFO - codeparrot_training - Step 16825: {'lr': 0.0004877230987419957, 'samples': 8614912, 'steps': 16825, 'loss/train': 2.156494617462158}
-03/04/2022 09:13:37 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/04/2022 09:13:42 - INFO - codeparrot_training - Step 16826: {'lr': 0.00048772145613616035, 'samples': 8615424, 'steps': 16826, 'loss/train': 1.7621532678604126}
-03/04/2022 09:13:45 - INFO - codeparrot_training - Step 16827: {'lr': 0.00048771981342321145, 'samples': 8615936, 'steps': 16827, 'loss/train': 2.2267062664031982}
-03/04/2022 09:13:46 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/04/2022 09:13:50 - INFO - codeparrot_training - Step 16828: {'lr': 0.0004877181706031496, 'samples': 8616448, 'steps': 16828, 'loss/train': 2.7509829998016357}
-03/04/2022 09:13:53 - INFO - codeparrot_training - Step 16829: {'lr': 0.00048771652767597563, 'samples': 8616960, 'steps': 16829, 'loss/train': 1.7442864179611206}
-03/04/2022 09:13:55 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/04/2022 09:13:59 - INFO - codeparrot_training - Step 16830: {'lr': 0.0004877148846416903, 'samples': 8617472, 'steps': 16830, 'loss/train': 2.0920181274414062}
-03/04/2022 09:14:02 - INFO - codeparrot_training - Step 16831: {'lr': 0.0004877132415002943, 'samples': 8617984, 'steps': 16831, 'loss/train': 2.050269603729248}
-03/04/2022 09:14:03 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 09:14:07 - INFO - codeparrot_training - Step 16832: {'lr': 0.00048771159825178827, 'samples': 8618496, 'steps': 16832, 'loss/train': 1.4495407342910767}
-03/04/2022 09:14:10 - INFO - codeparrot_training - Step 16833: {'lr': 0.0004877099548961732, 'samples': 8619008, 'steps': 16833, 'loss/train': 1.9929603338241577}
-03/04/2022 09:14:12 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 09:14:16 - INFO - codeparrot_training - Step 16834: {'lr': 0.0004877083114334496, 'samples': 8619520, 'steps': 16834, 'loss/train': 1.6012290716171265}
-03/04/2022 09:14:19 - INFO - codeparrot_training - Step 16835: {'lr': 0.0004877066678636184, 'samples': 8620032, 'steps': 16835, 'loss/train': 2.109827756881714}
-03/04/2022 09:14:20 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 09:14:24 - INFO - codeparrot_training - Step 16836: {'lr': 0.00048770502418668017, 'samples': 8620544, 'steps': 16836, 'loss/train': 0.9779191017150879}
-03/04/2022 09:14:27 - INFO - codeparrot_training - Step 16837: {'lr': 0.00048770338040263574, 'samples': 8621056, 'steps': 16837, 'loss/train': 1.9277397394180298}
-03/04/2022 09:14:29 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/04/2022 09:14:33 - INFO - codeparrot_training - Step 16838: {'lr': 0.00048770173651148586, 'samples': 8621568, 'steps': 16838, 'loss/train': 1.742400050163269}
-03/04/2022 09:14:36 - INFO - codeparrot_training - Step 16839: {'lr': 0.0004877000925132312, 'samples': 8622080, 'steps': 16839, 'loss/train': 2.306121587753296}
-03/04/2022 09:14:38 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 09:14:41 - INFO - codeparrot_training - Step 16840: {'lr': 0.0004876984484078726, 'samples': 8622592, 'steps': 16840, 'loss/train': 1.6649868488311768}
-03/04/2022 09:14:44 - INFO - codeparrot_training - Step 16841: {'lr': 0.0004876968041954107, 'samples': 8623104, 'steps': 16841, 'loss/train': 1.966260552406311}
-03/04/2022 09:14:46 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/04/2022 09:14:49 - INFO - codeparrot_training - Step 16842: {'lr': 0.00048769515987584624, 'samples': 8623616, 'steps': 16842, 'loss/train': 1.2436267137527466}
-03/04/2022 09:14:53 - INFO - codeparrot_training - Step 16843: {'lr': 0.0004876935154491801, 'samples': 8624128, 'steps': 16843, 'loss/train': 1.6472392082214355}
-03/04/2022 09:14:54 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/04/2022 09:14:58 - INFO - codeparrot_training - Step 16844: {'lr': 0.00048769187091541287, 'samples': 8624640, 'steps': 16844, 'loss/train': 2.2080459594726562}
-03/04/2022 09:15:01 - INFO - codeparrot_training - Step 16845: {'lr': 0.0004876902262745454, 'samples': 8625152, 'steps': 16845, 'loss/train': 2.3519277572631836}
-03/04/2022 09:15:03 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 09:15:06 - INFO - codeparrot_training - Step 16846: {'lr': 0.00048768858152657837, 'samples': 8625664, 'steps': 16846, 'loss/train': 1.8650680780410767}
-03/04/2022 09:15:09 - INFO - codeparrot_training - Step 16847: {'lr': 0.0004876869366715125, 'samples': 8626176, 'steps': 16847, 'loss/train': 2.2649085521698}
-03/04/2022 09:15:11 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 09:15:15 - INFO - codeparrot_training - Step 16848: {'lr': 0.0004876852917093486, 'samples': 8626688, 'steps': 16848, 'loss/train': 1.7680608034133911}
-03/04/2022 09:15:18 - INFO - codeparrot_training - Step 16849: {'lr': 0.0004876836466400874, 'samples': 8627200, 'steps': 16849, 'loss/train': 2.2456302642822266}
-03/04/2022 09:15:20 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/04/2022 09:15:23 - INFO - codeparrot_training - Step 16850: {'lr': 0.00048768200146372955, 'samples': 8627712, 'steps': 16850, 'loss/train': 2.1874747276306152}
-03/04/2022 09:15:26 - INFO - codeparrot_training - Step 16851: {'lr': 0.00048768035618027597, 'samples': 8628224, 'steps': 16851, 'loss/train': 1.171908974647522}
-03/04/2022 09:15:28 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/04/2022 09:15:32 - INFO - codeparrot_training - Step 16852: {'lr': 0.00048767871078972717, 'samples': 8628736, 'steps': 16852, 'loss/train': 2.3781909942626953}
-03/04/2022 09:15:35 - INFO - codeparrot_training - Step 16853: {'lr': 0.000487677065292084, 'samples': 8629248, 'steps': 16853, 'loss/train': 2.421755075454712}
-03/04/2022 09:15:37 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/04/2022 09:15:40 - INFO - codeparrot_training - Step 16854: {'lr': 0.0004876754196873473, 'samples': 8629760, 'steps': 16854, 'loss/train': 2.2711586952209473}
-03/04/2022 09:15:43 - INFO - codeparrot_training - Step 16855: {'lr': 0.00048767377397551773, 'samples': 8630272, 'steps': 16855, 'loss/train': 2.336109161376953}
-03/04/2022 09:15:45 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 09:15:49 - INFO - codeparrot_training - Step 16856: {'lr': 0.00048767212815659593, 'samples': 8630784, 'steps': 16856, 'loss/train': 7.030905723571777}
-03/04/2022 09:15:52 - INFO - codeparrot_training - Step 16857: {'lr': 0.0004876704822305828, 'samples': 8631296, 'steps': 16857, 'loss/train': 2.7630112171173096}
-03/04/2022 09:15:54 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/04/2022 09:15:57 - INFO - codeparrot_training - Step 16858: {'lr': 0.00048766883619747906, 'samples': 8631808, 'steps': 16858, 'loss/train': 1.823747158050537}
-03/04/2022 09:16:00 - INFO - codeparrot_training - Step 16859: {'lr': 0.00048766719005728534, 'samples': 8632320, 'steps': 16859, 'loss/train': 1.8633544445037842}
-03/04/2022 09:16:03 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/04/2022 09:16:05 - INFO - codeparrot_training - Step 16860: {'lr': 0.0004876655438100024, 'samples': 8632832, 'steps': 16860, 'loss/train': 2.5746958255767822}
-03/04/2022 09:16:09 - INFO - codeparrot_training - Step 16861: {'lr': 0.00048766389745563113, 'samples': 8633344, 'steps': 16861, 'loss/train': 1.5694084167480469}
-03/04/2022 09:16:11 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 09:16:14 - INFO - codeparrot_training - Step 16862: {'lr': 0.00048766225099417215, 'samples': 8633856, 'steps': 16862, 'loss/train': 1.3526335954666138}
-03/04/2022 09:16:17 - INFO - codeparrot_training - Step 16863: {'lr': 0.0004876606044256262, 'samples': 8634368, 'steps': 16863, 'loss/train': 2.037963390350342}
-03/04/2022 09:16:20 - INFO - codeparrot_training - Step 16864: {'lr': 0.0004876589577499941, 'samples': 8634880, 'steps': 16864, 'loss/train': 1.548314094543457}
-03/04/2022 09:16:20 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/04/2022 09:16:26 - INFO - codeparrot_training - Step 16865: {'lr': 0.0004876573109672765, 'samples': 8635392, 'steps': 16865, 'loss/train': 1.710619568824768}
-03/04/2022 09:16:28 - INFO - codeparrot_training - Skipping example with length 920 (seq_length=1024)
-03/04/2022 09:16:31 - INFO - codeparrot_training - Step 16866: {'lr': 0.0004876556640774742, 'samples': 8635904, 'steps': 16866, 'loss/train': 2.2892911434173584}
-03/04/2022 09:16:34 - INFO - codeparrot_training - Step 16867: {'lr': 0.0004876540170805879, 'samples': 8636416, 'steps': 16867, 'loss/train': 2.0580506324768066}
-03/04/2022 09:16:37 - INFO - codeparrot_training - Step 16868: {'lr': 0.00048765236997661845, 'samples': 8636928, 'steps': 16868, 'loss/train': 1.7206205129623413}
-03/04/2022 09:16:38 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/04/2022 09:16:43 - INFO - codeparrot_training - Step 16869: {'lr': 0.0004876507227655664, 'samples': 8637440, 'steps': 16869, 'loss/train': 1.4987205266952515}
-03/04/2022 09:16:46 - INFO - codeparrot_training - Step 16870: {'lr': 0.00048764907544743264, 'samples': 8637952, 'steps': 16870, 'loss/train': 2.0848255157470703}
-03/04/2022 09:16:47 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/04/2022 09:16:51 - INFO - codeparrot_training - Step 16871: {'lr': 0.0004876474280222179, 'samples': 8638464, 'steps': 16871, 'loss/train': 1.2447184324264526}
-03/04/2022 09:16:55 - INFO - codeparrot_training - Step 16872: {'lr': 0.00048764578048992284, 'samples': 8638976, 'steps': 16872, 'loss/train': 1.8943469524383545}
-03/04/2022 09:16:55 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/04/2022 09:17:00 - INFO - codeparrot_training - Step 16873: {'lr': 0.0004876441328505483, 'samples': 8639488, 'steps': 16873, 'loss/train': 2.31379771232605}
-03/04/2022 09:17:03 - INFO - codeparrot_training - Step 16874: {'lr': 0.000487642485104095, 'samples': 8640000, 'steps': 16874, 'loss/train': 1.1681108474731445}
-03/04/2022 09:17:04 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 09:17:08 - INFO - codeparrot_training - Step 16875: {'lr': 0.00048764083725056365, 'samples': 8640512, 'steps': 16875, 'loss/train': 0.10291320830583572}
-03/04/2022 09:17:12 - INFO - codeparrot_training - Step 16876: {'lr': 0.00048763918928995496, 'samples': 8641024, 'steps': 16876, 'loss/train': 1.9710620641708374}
-03/04/2022 09:17:14 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/04/2022 09:17:17 - INFO - codeparrot_training - Step 16877: {'lr': 0.00048763754122226977, 'samples': 8641536, 'steps': 16877, 'loss/train': 1.6267890930175781}
-03/04/2022 09:17:20 - INFO - codeparrot_training - Step 16878: {'lr': 0.00048763589304750876, 'samples': 8642048, 'steps': 16878, 'loss/train': 2.508193016052246}
-03/04/2022 09:17:22 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/04/2022 09:17:25 - INFO - codeparrot_training - Step 16879: {'lr': 0.0004876342447656727, 'samples': 8642560, 'steps': 16879, 'loss/train': 2.3881168365478516}
-03/04/2022 09:17:29 - INFO - codeparrot_training - Step 16880: {'lr': 0.00048763259637676226, 'samples': 8643072, 'steps': 16880, 'loss/train': 1.9023140668869019}
-03/04/2022 09:17:31 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/04/2022 09:17:34 - INFO - codeparrot_training - Step 16881: {'lr': 0.00048763094788077834, 'samples': 8643584, 'steps': 16881, 'loss/train': 1.6261519193649292}
-03/04/2022 09:17:37 - INFO - codeparrot_training - Step 16882: {'lr': 0.0004876292992777215, 'samples': 8644096, 'steps': 16882, 'loss/train': 0.24607695639133453}
-03/04/2022 09:17:39 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/04/2022 09:17:42 - INFO - codeparrot_training - Step 16883: {'lr': 0.00048762765056759255, 'samples': 8644608, 'steps': 16883, 'loss/train': 2.590109348297119}
-03/04/2022 09:17:45 - INFO - codeparrot_training - Step 16884: {'lr': 0.00048762600175039227, 'samples': 8645120, 'steps': 16884, 'loss/train': 2.155954360961914}
-03/04/2022 09:17:47 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 09:17:51 - INFO - codeparrot_training - Step 16885: {'lr': 0.0004876243528261214, 'samples': 8645632, 'steps': 16885, 'loss/train': 1.25299870967865}
-03/04/2022 09:17:54 - INFO - codeparrot_training - Step 16886: {'lr': 0.0004876227037947807, 'samples': 8646144, 'steps': 16886, 'loss/train': 0.6563835144042969}
-03/04/2022 09:17:55 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/04/2022 09:17:59 - INFO - codeparrot_training - Step 16887: {'lr': 0.0004876210546563707, 'samples': 8646656, 'steps': 16887, 'loss/train': 0.5206893086433411}
-03/04/2022 09:18:02 - INFO - codeparrot_training - Step 16888: {'lr': 0.0004876194054108926, 'samples': 8647168, 'steps': 16888, 'loss/train': 1.8378583192825317}
-03/04/2022 09:18:04 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 09:18:07 - INFO - codeparrot_training - Step 16889: {'lr': 0.0004876177560583466, 'samples': 8647680, 'steps': 16889, 'loss/train': 1.7045217752456665}
-03/04/2022 09:18:11 - INFO - codeparrot_training - Step 16890: {'lr': 0.00048761610659873387, 'samples': 8648192, 'steps': 16890, 'loss/train': 2.1792893409729004}
-03/04/2022 09:18:12 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 09:18:16 - INFO - codeparrot_training - Step 16891: {'lr': 0.0004876144570320549, 'samples': 8648704, 'steps': 16891, 'loss/train': 2.275803804397583}
-03/04/2022 09:18:19 - INFO - codeparrot_training - Step 16892: {'lr': 0.0004876128073583106, 'samples': 8649216, 'steps': 16892, 'loss/train': 1.317810297012329}
-03/04/2022 09:18:20 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/04/2022 09:18:24 - INFO - codeparrot_training - Step 16893: {'lr': 0.00048761115757750155, 'samples': 8649728, 'steps': 16893, 'loss/train': 1.1555465459823608}
-03/04/2022 09:18:28 - INFO - codeparrot_training - Step 16894: {'lr': 0.00048760950768962863, 'samples': 8650240, 'steps': 16894, 'loss/train': 1.5093331336975098}
-03/04/2022 09:18:29 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 09:18:33 - INFO - codeparrot_training - Step 16895: {'lr': 0.00048760785769469254, 'samples': 8650752, 'steps': 16895, 'loss/train': 1.4779750108718872}
-03/04/2022 09:18:36 - INFO - codeparrot_training - Step 16896: {'lr': 0.00048760620759269403, 'samples': 8651264, 'steps': 16896, 'loss/train': 1.955522894859314}
-03/04/2022 09:18:38 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 09:18:41 - INFO - codeparrot_training - Step 16897: {'lr': 0.00048760455738363376, 'samples': 8651776, 'steps': 16897, 'loss/train': 2.022625684738159}
-03/04/2022 09:18:44 - INFO - codeparrot_training - Step 16898: {'lr': 0.0004876029070675126, 'samples': 8652288, 'steps': 16898, 'loss/train': 1.8878549337387085}
-03/04/2022 09:18:46 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 09:18:50 - INFO - codeparrot_training - Step 16899: {'lr': 0.0004876012566443312, 'samples': 8652800, 'steps': 16899, 'loss/train': 2.2100322246551514}
-03/04/2022 09:18:53 - INFO - codeparrot_training - Step 16900: {'lr': 0.00048759960611409036, 'samples': 8653312, 'steps': 16900, 'loss/train': 2.43709659576416}
-03/04/2022 09:18:54 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 09:18:58 - INFO - codeparrot_training - Step 16901: {'lr': 0.00048759795547679083, 'samples': 8653824, 'steps': 16901, 'loss/train': 2.4187655448913574}
-03/04/2022 09:19:01 - INFO - codeparrot_training - Step 16902: {'lr': 0.00048759630473243327, 'samples': 8654336, 'steps': 16902, 'loss/train': 1.537337064743042}
-03/04/2022 09:19:03 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 09:19:06 - INFO - codeparrot_training - Step 16903: {'lr': 0.00048759465388101855, 'samples': 8654848, 'steps': 16903, 'loss/train': 1.8529452085494995}
-03/04/2022 09:19:10 - INFO - codeparrot_training - Step 16904: {'lr': 0.0004875930029225473, 'samples': 8655360, 'steps': 16904, 'loss/train': 2.9206037521362305}
-03/04/2022 09:19:11 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 09:19:15 - INFO - codeparrot_training - Step 16905: {'lr': 0.0004875913518570203, 'samples': 8655872, 'steps': 16905, 'loss/train': 3.0768840312957764}
-03/04/2022 09:19:18 - INFO - codeparrot_training - Step 16906: {'lr': 0.0004875897006844383, 'samples': 8656384, 'steps': 16906, 'loss/train': 1.8729430437088013}
-03/04/2022 09:19:20 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/04/2022 09:19:24 - INFO - codeparrot_training - Step 16907: {'lr': 0.00048758804940480203, 'samples': 8656896, 'steps': 16907, 'loss/train': 2.024226665496826}
-03/04/2022 09:19:27 - INFO - codeparrot_training - Step 16908: {'lr': 0.0004875863980181123, 'samples': 8657408, 'steps': 16908, 'loss/train': 0.9614630937576294}
-03/04/2022 09:19:29 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/04/2022 09:19:32 - INFO - codeparrot_training - Step 16909: {'lr': 0.0004875847465243698, 'samples': 8657920, 'steps': 16909, 'loss/train': 2.0694754123687744}
-03/04/2022 09:19:35 - INFO - codeparrot_training - Step 16910: {'lr': 0.00048758309492357533, 'samples': 8658432, 'steps': 16910, 'loss/train': 2.0329232215881348}
-03/04/2022 09:19:38 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/04/2022 09:19:40 - INFO - codeparrot_training - Step 16911: {'lr': 0.0004875814432157295, 'samples': 8658944, 'steps': 16911, 'loss/train': 2.2260448932647705}
-03/04/2022 09:19:44 - INFO - codeparrot_training - Step 16912: {'lr': 0.0004875797914008332, 'samples': 8659456, 'steps': 16912, 'loss/train': 1.645774245262146}
-03/04/2022 09:19:46 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/04/2022 09:19:49 - INFO - codeparrot_training - Step 16913: {'lr': 0.00048757813947888706, 'samples': 8659968, 'steps': 16913, 'loss/train': 1.9161906242370605}
-03/04/2022 09:19:52 - INFO - codeparrot_training - Step 16914: {'lr': 0.0004875764874498919, 'samples': 8660480, 'steps': 16914, 'loss/train': 2.214254140853882}
-03/04/2022 09:19:55 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/04/2022 09:19:57 - INFO - codeparrot_training - Step 16915: {'lr': 0.00048757483531384837, 'samples': 8660992, 'steps': 16915, 'loss/train': 1.419070839881897}
-03/04/2022 09:20:00 - INFO - codeparrot_training - Step 16916: {'lr': 0.0004875731830707574, 'samples': 8661504, 'steps': 16916, 'loss/train': 1.6740669012069702}
-03/04/2022 09:20:03 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/04/2022 09:20:06 - INFO - codeparrot_training - Step 16917: {'lr': 0.00048757153072061954, 'samples': 8662016, 'steps': 16917, 'loss/train': 1.8722896575927734}
-03/04/2022 09:20:09 - INFO - codeparrot_training - Step 16918: {'lr': 0.0004875698782634357, 'samples': 8662528, 'steps': 16918, 'loss/train': 1.0943175554275513}
-03/04/2022 09:20:11 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 09:20:14 - INFO - codeparrot_training - Step 16919: {'lr': 0.00048756822569920647, 'samples': 8663040, 'steps': 16919, 'loss/train': 1.3030593395233154}
-03/04/2022 09:20:18 - INFO - codeparrot_training - Step 16920: {'lr': 0.0004875665730279326, 'samples': 8663552, 'steps': 16920, 'loss/train': 1.9468982219696045}
-03/04/2022 09:20:21 - INFO - codeparrot_training - Step 16921: {'lr': 0.000487564920249615, 'samples': 8664064, 'steps': 16921, 'loss/train': 0.286955863237381}
-03/04/2022 09:20:21 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 09:20:26 - INFO - codeparrot_training - Step 16922: {'lr': 0.00048756326736425427, 'samples': 8664576, 'steps': 16922, 'loss/train': 1.8562086820602417}
-03/04/2022 09:20:29 - INFO - codeparrot_training - Step 16923: {'lr': 0.00048756161437185126, 'samples': 8665088, 'steps': 16923, 'loss/train': 1.963325023651123}
-03/04/2022 09:20:30 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/04/2022 09:20:35 - INFO - codeparrot_training - Step 16924: {'lr': 0.0004875599612724066, 'samples': 8665600, 'steps': 16924, 'loss/train': 2.058159351348877}
-03/04/2022 09:20:38 - INFO - codeparrot_training - Step 16925: {'lr': 0.00048755830806592105, 'samples': 8666112, 'steps': 16925, 'loss/train': 2.0522348880767822}
-03/04/2022 09:20:39 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/04/2022 09:20:43 - INFO - codeparrot_training - Step 16926: {'lr': 0.00048755665475239547, 'samples': 8666624, 'steps': 16926, 'loss/train': 1.7096834182739258}
-03/04/2022 09:20:46 - INFO - codeparrot_training - Step 16927: {'lr': 0.0004875550013318305, 'samples': 8667136, 'steps': 16927, 'loss/train': 2.08017635345459}
-03/04/2022 09:20:47 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 09:20:51 - INFO - codeparrot_training - Step 16928: {'lr': 0.0004875533478042269, 'samples': 8667648, 'steps': 16928, 'loss/train': 1.6763980388641357}
-03/04/2022 09:20:55 - INFO - codeparrot_training - Step 16929: {'lr': 0.00048755169416958544, 'samples': 8668160, 'steps': 16929, 'loss/train': 2.043870210647583}
-03/04/2022 09:20:56 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 09:21:00 - INFO - codeparrot_training - Step 16930: {'lr': 0.00048755004042790685, 'samples': 8668672, 'steps': 16930, 'loss/train': 2.068103551864624}
-03/04/2022 09:21:03 - INFO - codeparrot_training - Step 16931: {'lr': 0.00048754838657919186, 'samples': 8669184, 'steps': 16931, 'loss/train': 2.09295654296875}
-03/04/2022 09:21:04 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/04/2022 09:21:08 - INFO - codeparrot_training - Step 16932: {'lr': 0.00048754673262344124, 'samples': 8669696, 'steps': 16932, 'loss/train': 2.4502410888671875}
-03/04/2022 09:21:12 - INFO - codeparrot_training - Step 16933: {'lr': 0.00048754507856065574, 'samples': 8670208, 'steps': 16933, 'loss/train': 2.406803607940674}
-03/04/2022 09:21:13 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 09:21:17 - INFO - codeparrot_training - Step 16934: {'lr': 0.0004875434243908361, 'samples': 8670720, 'steps': 16934, 'loss/train': 2.2319862842559814}
-03/04/2022 09:21:20 - INFO - codeparrot_training - Step 16935: {'lr': 0.00048754177011398303, 'samples': 8671232, 'steps': 16935, 'loss/train': 1.6219836473464966}
-03/04/2022 09:21:21 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 09:21:25 - INFO - codeparrot_training - Step 16936: {'lr': 0.0004875401157300973, 'samples': 8671744, 'steps': 16936, 'loss/train': 1.7857357263565063}
-03/04/2022 09:21:28 - INFO - codeparrot_training - Step 16937: {'lr': 0.00048753846123917964, 'samples': 8672256, 'steps': 16937, 'loss/train': 1.4194968938827515}
-03/04/2022 09:21:30 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/04/2022 09:21:34 - INFO - codeparrot_training - Step 16938: {'lr': 0.0004875368066412309, 'samples': 8672768, 'steps': 16938, 'loss/train': 1.8956108093261719}
-03/04/2022 09:21:37 - INFO - codeparrot_training - Step 16939: {'lr': 0.00048753515193625165, 'samples': 8673280, 'steps': 16939, 'loss/train': 0.9386816620826721}
-03/04/2022 09:21:38 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/04/2022 09:21:42 - INFO - codeparrot_training - Step 16940: {'lr': 0.00048753349712424277, 'samples': 8673792, 'steps': 16940, 'loss/train': 1.05565345287323}
-03/04/2022 09:21:45 - INFO - codeparrot_training - Step 16941: {'lr': 0.00048753184220520497, 'samples': 8674304, 'steps': 16941, 'loss/train': 1.794123888015747}
-03/04/2022 09:21:46 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/04/2022 09:21:51 - INFO - codeparrot_training - Step 16942: {'lr': 0.000487530187179139, 'samples': 8674816, 'steps': 16942, 'loss/train': 1.8177355527877808}
-03/04/2022 09:21:54 - INFO - codeparrot_training - Step 16943: {'lr': 0.00048752853204604555, 'samples': 8675328, 'steps': 16943, 'loss/train': 2.7921884059906006}
-03/04/2022 09:21:55 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 09:21:59 - INFO - codeparrot_training - Step 16944: {'lr': 0.00048752687680592545, 'samples': 8675840, 'steps': 16944, 'loss/train': 2.029855251312256}
-03/04/2022 09:22:02 - INFO - codeparrot_training - Step 16945: {'lr': 0.00048752522145877937, 'samples': 8676352, 'steps': 16945, 'loss/train': 1.8961869478225708}
-03/04/2022 09:22:03 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 09:22:07 - INFO - codeparrot_training - Step 16946: {'lr': 0.0004875235660046081, 'samples': 8676864, 'steps': 16946, 'loss/train': 1.404382586479187}
-03/04/2022 09:22:11 - INFO - codeparrot_training - Step 16947: {'lr': 0.0004875219104434124, 'samples': 8677376, 'steps': 16947, 'loss/train': 2.0380818843841553}
-03/04/2022 09:22:12 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/04/2022 09:22:16 - INFO - codeparrot_training - Step 16948: {'lr': 0.0004875202547751929, 'samples': 8677888, 'steps': 16948, 'loss/train': 2.6288721561431885}
-03/04/2022 09:22:19 - INFO - codeparrot_training - Step 16949: {'lr': 0.00048751859899995054, 'samples': 8678400, 'steps': 16949, 'loss/train': 1.5813437700271606}
-03/04/2022 09:22:20 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/04/2022 09:22:24 - INFO - codeparrot_training - Step 16950: {'lr': 0.0004875169431176859, 'samples': 8678912, 'steps': 16950, 'loss/train': 1.0193238258361816}
-03/04/2022 09:22:27 - INFO - codeparrot_training - Step 16951: {'lr': 0.0004875152871283999, 'samples': 8679424, 'steps': 16951, 'loss/train': 1.7038531303405762}
-03/04/2022 09:22:29 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/04/2022 09:22:33 - INFO - codeparrot_training - Step 16952: {'lr': 0.0004875136310320931, 'samples': 8679936, 'steps': 16952, 'loss/train': 1.9126293659210205}
-03/04/2022 09:22:36 - INFO - codeparrot_training - Step 16953: {'lr': 0.0004875119748287663, 'samples': 8680448, 'steps': 16953, 'loss/train': 2.454759359359741}
-03/04/2022 09:22:37 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/04/2022 09:22:41 - INFO - codeparrot_training - Step 16954: {'lr': 0.0004875103185184203, 'samples': 8680960, 'steps': 16954, 'loss/train': 1.74368417263031}
-03/04/2022 09:22:44 - INFO - codeparrot_training - Step 16955: {'lr': 0.00048750866210105583, 'samples': 8681472, 'steps': 16955, 'loss/train': 0.1641991138458252}
-03/04/2022 09:22:46 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/04/2022 09:22:50 - INFO - codeparrot_training - Step 16956: {'lr': 0.0004875070055766736, 'samples': 8681984, 'steps': 16956, 'loss/train': 1.929293155670166}
-03/04/2022 09:22:53 - INFO - codeparrot_training - Step 16957: {'lr': 0.0004875053489452743, 'samples': 8682496, 'steps': 16957, 'loss/train': 1.4869800806045532}
-03/04/2022 09:22:54 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/04/2022 09:22:58 - INFO - codeparrot_training - Step 16958: {'lr': 0.00048750369220685886, 'samples': 8683008, 'steps': 16958, 'loss/train': 1.9670077562332153}
-03/04/2022 09:23:01 - INFO - codeparrot_training - Step 16959: {'lr': 0.0004875020353614279, 'samples': 8683520, 'steps': 16959, 'loss/train': 2.647514581680298}
-03/04/2022 09:23:03 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/04/2022 09:23:06 - INFO - codeparrot_training - Step 16960: {'lr': 0.0004875003784089822, 'samples': 8684032, 'steps': 16960, 'loss/train': 2.0391526222229004}
-03/04/2022 09:23:10 - INFO - codeparrot_training - Step 16961: {'lr': 0.00048749872134952243, 'samples': 8684544, 'steps': 16961, 'loss/train': 1.7749903202056885}
-03/04/2022 09:23:11 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 09:23:15 - INFO - codeparrot_training - Step 16962: {'lr': 0.0004874970641830495, 'samples': 8685056, 'steps': 16962, 'loss/train': 1.1836737394332886}
-03/04/2022 09:23:18 - INFO - codeparrot_training - Step 16963: {'lr': 0.000487495406909564, 'samples': 8685568, 'steps': 16963, 'loss/train': 1.72423255443573}
-03/04/2022 09:23:20 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/04/2022 09:23:24 - INFO - codeparrot_training - Step 16964: {'lr': 0.00048749374952906677, 'samples': 8686080, 'steps': 16964, 'loss/train': 2.1110990047454834}
-03/04/2022 09:23:27 - INFO - codeparrot_training - Step 16965: {'lr': 0.0004874920920415584, 'samples': 8686592, 'steps': 16965, 'loss/train': 1.8694078922271729}
-03/04/2022 09:23:28 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 09:23:32 - INFO - codeparrot_training - Step 16966: {'lr': 0.0004874904344470399, 'samples': 8687104, 'steps': 16966, 'loss/train': 2.0700762271881104}
-03/04/2022 09:23:36 - INFO - codeparrot_training - Step 16967: {'lr': 0.00048748877674551183, 'samples': 8687616, 'steps': 16967, 'loss/train': 3.6208784580230713}
-03/04/2022 09:23:38 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/04/2022 09:23:41 - INFO - codeparrot_training - Step 16968: {'lr': 0.00048748711893697495, 'samples': 8688128, 'steps': 16968, 'loss/train': 1.273001790046692}
-03/04/2022 09:23:44 - INFO - codeparrot_training - Step 16969: {'lr': 0.0004874854610214301, 'samples': 8688640, 'steps': 16969, 'loss/train': 1.6043765544891357}
-03/04/2022 09:23:46 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 09:23:49 - INFO - codeparrot_training - Step 16970: {'lr': 0.00048748380299887793, 'samples': 8689152, 'steps': 16970, 'loss/train': 2.1030914783477783}
-03/04/2022 09:23:53 - INFO - codeparrot_training - Step 16971: {'lr': 0.0004874821448693192, 'samples': 8689664, 'steps': 16971, 'loss/train': 1.783687710762024}
-03/04/2022 09:23:55 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/04/2022 09:23:58 - INFO - codeparrot_training - Step 16972: {'lr': 0.00048748048663275475, 'samples': 8690176, 'steps': 16972, 'loss/train': 2.1835052967071533}
-03/04/2022 09:24:01 - INFO - codeparrot_training - Step 16973: {'lr': 0.00048747882828918524, 'samples': 8690688, 'steps': 16973, 'loss/train': 2.5105714797973633}
-03/04/2022 09:24:04 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/04/2022 09:24:06 - INFO - codeparrot_training - Step 16974: {'lr': 0.0004874771698386113, 'samples': 8691200, 'steps': 16974, 'loss/train': 1.6340335607528687}
-03/04/2022 09:24:10 - INFO - codeparrot_training - Step 16975: {'lr': 0.00048747551128103397, 'samples': 8691712, 'steps': 16975, 'loss/train': 2.034607410430908}
-03/04/2022 09:24:13 - INFO - codeparrot_training - Step 16976: {'lr': 0.00048747385261645377, 'samples': 8692224, 'steps': 16976, 'loss/train': 1.6640053987503052}
-03/04/2022 09:24:13 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/04/2022 09:24:18 - INFO - codeparrot_training - Step 16977: {'lr': 0.0004874721938448715, 'samples': 8692736, 'steps': 16977, 'loss/train': 2.047442674636841}
-03/04/2022 09:24:21 - INFO - codeparrot_training - Step 16978: {'lr': 0.000487470534966288, 'samples': 8693248, 'steps': 16978, 'loss/train': 2.3193156719207764}
-03/04/2022 09:24:22 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/04/2022 09:24:27 - INFO - codeparrot_training - Step 16979: {'lr': 0.0004874688759807039, 'samples': 8693760, 'steps': 16979, 'loss/train': 1.3341710567474365}
-03/04/2022 09:24:30 - INFO - codeparrot_training - Step 16980: {'lr': 0.00048746721688812004, 'samples': 8694272, 'steps': 16980, 'loss/train': 1.8903558254241943}
-03/04/2022 09:24:30 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/04/2022 09:24:35 - INFO - codeparrot_training - Step 16981: {'lr': 0.00048746555768853703, 'samples': 8694784, 'steps': 16981, 'loss/train': 1.7109447717666626}
-03/04/2022 09:24:38 - INFO - codeparrot_training - Step 16982: {'lr': 0.00048746389838195573, 'samples': 8695296, 'steps': 16982, 'loss/train': 2.277663230895996}
-03/04/2022 09:24:38 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/04/2022 09:24:44 - INFO - codeparrot_training - Step 16983: {'lr': 0.0004874622389683768, 'samples': 8695808, 'steps': 16983, 'loss/train': 2.342374801635742}
-03/04/2022 09:24:47 - INFO - codeparrot_training - Step 16984: {'lr': 0.0004874605794478012, 'samples': 8696320, 'steps': 16984, 'loss/train': 2.1430656909942627}
-03/04/2022 09:24:47 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/04/2022 09:24:52 - INFO - codeparrot_training - Step 16985: {'lr': 0.0004874589198202294, 'samples': 8696832, 'steps': 16985, 'loss/train': 2.5442886352539062}
-03/04/2022 09:24:55 - INFO - codeparrot_training - Step 16986: {'lr': 0.0004874572600856624, 'samples': 8697344, 'steps': 16986, 'loss/train': 1.8319238424301147}
-03/04/2022 09:24:56 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 09:25:01 - INFO - codeparrot_training - Step 16987: {'lr': 0.0004874556002441007, 'samples': 8697856, 'steps': 16987, 'loss/train': 1.7899049520492554}
-03/04/2022 09:25:04 - INFO - codeparrot_training - Step 16988: {'lr': 0.0004874539402955452, 'samples': 8698368, 'steps': 16988, 'loss/train': 1.7940919399261475}
-03/04/2022 09:25:04 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 09:25:09 - INFO - codeparrot_training - Step 16989: {'lr': 0.00048745228023999666, 'samples': 8698880, 'steps': 16989, 'loss/train': 1.297383427619934}
-03/04/2022 09:25:12 - INFO - codeparrot_training - Step 16990: {'lr': 0.0004874506200774557, 'samples': 8699392, 'steps': 16990, 'loss/train': 2.2932510375976562}
-03/04/2022 09:25:13 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/04/2022 09:25:17 - INFO - codeparrot_training - Step 16991: {'lr': 0.00048744895980792327, 'samples': 8699904, 'steps': 16991, 'loss/train': 1.3940424919128418}
-03/04/2022 09:25:21 - INFO - codeparrot_training - Step 16992: {'lr': 0.00048744729943139993, 'samples': 8700416, 'steps': 16992, 'loss/train': 2.2109503746032715}
-03/04/2022 09:25:22 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/04/2022 09:25:26 - INFO - codeparrot_training - Step 16993: {'lr': 0.0004874456389478865, 'samples': 8700928, 'steps': 16993, 'loss/train': 1.9773454666137695}
-03/04/2022 09:25:29 - INFO - codeparrot_training - Step 16994: {'lr': 0.00048744397835738377, 'samples': 8701440, 'steps': 16994, 'loss/train': 2.3317158222198486}
-03/04/2022 09:25:30 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/04/2022 09:25:34 - INFO - codeparrot_training - Step 16995: {'lr': 0.00048744231765989246, 'samples': 8701952, 'steps': 16995, 'loss/train': 2.1656618118286133}
-03/04/2022 09:25:38 - INFO - codeparrot_training - Step 16996: {'lr': 0.0004874406568554132, 'samples': 8702464, 'steps': 16996, 'loss/train': 2.202397108078003}
-03/04/2022 09:25:39 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/04/2022 09:25:43 - INFO - codeparrot_training - Step 16997: {'lr': 0.0004874389959439469, 'samples': 8702976, 'steps': 16997, 'loss/train': 2.656357765197754}
-03/04/2022 09:25:46 - INFO - codeparrot_training - Step 16998: {'lr': 0.0004874373349254943, 'samples': 8703488, 'steps': 16998, 'loss/train': 1.1595306396484375}
-03/04/2022 09:25:49 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/04/2022 09:25:52 - INFO - codeparrot_training - Step 16999: {'lr': 0.00048743567380005604, 'samples': 8704000, 'steps': 16999, 'loss/train': 2.014744281768799}
-03/04/2022 09:25:55 - INFO - codeparrot_training - Step 17000: {'lr': 0.000487434012567633, 'samples': 8704512, 'steps': 17000, 'loss/train': 2.2198593616485596}
-03/04/2022 09:25:57 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 09:26:00 - INFO - codeparrot_training - Step 17001: {'lr': 0.0004874323512282258, 'samples': 8705024, 'steps': 17001, 'loss/train': 1.7270327806472778}
-03/04/2022 09:26:03 - INFO - codeparrot_training - Step 17002: {'lr': 0.00048743068978183523, 'samples': 8705536, 'steps': 17002, 'loss/train': 1.6361719369888306}
-03/04/2022 09:26:05 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/04/2022 09:26:08 - INFO - codeparrot_training - Step 17003: {'lr': 0.00048742902822846215, 'samples': 8706048, 'steps': 17003, 'loss/train': 1.610042929649353}
-03/04/2022 09:26:12 - INFO - codeparrot_training - Step 17004: {'lr': 0.0004874273665681071, 'samples': 8706560, 'steps': 17004, 'loss/train': 2.1730690002441406}
-03/04/2022 09:26:14 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/04/2022 09:26:17 - INFO - codeparrot_training - Step 17005: {'lr': 0.00048742570480077096, 'samples': 8707072, 'steps': 17005, 'loss/train': 1.8673317432403564}
-03/04/2022 09:26:20 - INFO - codeparrot_training - Step 17006: {'lr': 0.0004874240429264545, 'samples': 8707584, 'steps': 17006, 'loss/train': 1.839585304260254}
-03/04/2022 09:26:23 - INFO - codeparrot_training - Step 17007: {'lr': 0.00048742238094515844, 'samples': 8708096, 'steps': 17007, 'loss/train': 4.15144157409668}
-03/04/2022 09:26:24 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 09:26:29 - INFO - codeparrot_training - Step 17008: {'lr': 0.00048742071885688354, 'samples': 8708608, 'steps': 17008, 'loss/train': 2.374964475631714}
-03/04/2022 09:26:32 - INFO - codeparrot_training - Step 17009: {'lr': 0.00048741905666163047, 'samples': 8709120, 'steps': 17009, 'loss/train': 6.283572196960449}
-03/04/2022 09:26:34 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/04/2022 09:26:37 - INFO - codeparrot_training - Step 17010: {'lr': 0.00048741739435940003, 'samples': 8709632, 'steps': 17010, 'loss/train': 1.635693073272705}
-03/04/2022 09:26:41 - INFO - codeparrot_training - Step 17011: {'lr': 0.000487415731950193, 'samples': 8710144, 'steps': 17011, 'loss/train': 2.453800678253174}
-03/04/2022 09:26:43 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 09:26:46 - INFO - codeparrot_training - Step 17012: {'lr': 0.0004874140694340101, 'samples': 8710656, 'steps': 17012, 'loss/train': 0.5076583027839661}
-03/04/2022 09:26:49 - INFO - codeparrot_training - Step 17013: {'lr': 0.0004874124068108521, 'samples': 8711168, 'steps': 17013, 'loss/train': 2.672123432159424}
-03/04/2022 09:26:51 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 09:26:54 - INFO - codeparrot_training - Step 17014: {'lr': 0.00048741074408071975, 'samples': 8711680, 'steps': 17014, 'loss/train': 2.1428098678588867}
-03/04/2022 09:26:58 - INFO - codeparrot_training - Step 17015: {'lr': 0.00048740908124361373, 'samples': 8712192, 'steps': 17015, 'loss/train': 1.359662413597107}
-03/04/2022 09:27:00 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/04/2022 09:27:03 - INFO - codeparrot_training - Step 17016: {'lr': 0.0004874074182995349, 'samples': 8712704, 'steps': 17016, 'loss/train': 6.8417510986328125}
-03/04/2022 09:27:06 - INFO - codeparrot_training - Step 17017: {'lr': 0.0004874057552484839, 'samples': 8713216, 'steps': 17017, 'loss/train': 2.714891195297241}
-03/04/2022 09:27:08 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/04/2022 09:27:11 - INFO - codeparrot_training - Step 17018: {'lr': 0.00048740409209046154, 'samples': 8713728, 'steps': 17018, 'loss/train': 1.4954580068588257}
-03/04/2022 09:27:14 - INFO - codeparrot_training - Step 17019: {'lr': 0.0004874024288254686, 'samples': 8714240, 'steps': 17019, 'loss/train': 1.4837478399276733}
-03/04/2022 09:27:17 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 09:27:20 - INFO - codeparrot_training - Step 17020: {'lr': 0.00048740076545350573, 'samples': 8714752, 'steps': 17020, 'loss/train': 1.0343765020370483}
-03/04/2022 09:27:23 - INFO - codeparrot_training - Step 17021: {'lr': 0.00048739910197457376, 'samples': 8715264, 'steps': 17021, 'loss/train': 1.7516624927520752}
-03/04/2022 09:27:25 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/04/2022 09:27:28 - INFO - codeparrot_training - Step 17022: {'lr': 0.00048739743838867344, 'samples': 8715776, 'steps': 17022, 'loss/train': 2.433748245239258}
-03/04/2022 09:27:31 - INFO - codeparrot_training - Step 17023: {'lr': 0.00048739577469580545, 'samples': 8716288, 'steps': 17023, 'loss/train': 2.1277201175689697}
-03/04/2022 09:27:33 - INFO - codeparrot_training - Skipping example with length 822 (seq_length=1024)
-03/04/2022 09:27:36 - INFO - codeparrot_training - Step 17024: {'lr': 0.0004873941108959706, 'samples': 8716800, 'steps': 17024, 'loss/train': 1.1943570375442505}
-03/04/2022 09:27:40 - INFO - codeparrot_training - Step 17025: {'lr': 0.0004873924469891697, 'samples': 8717312, 'steps': 17025, 'loss/train': 1.1365171670913696}
-03/04/2022 09:27:41 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 09:27:45 - INFO - codeparrot_training - Step 17026: {'lr': 0.00048739078297540335, 'samples': 8717824, 'steps': 17026, 'loss/train': 1.7916502952575684}
-03/04/2022 09:27:48 - INFO - codeparrot_training - Step 17027: {'lr': 0.00048738911885467243, 'samples': 8718336, 'steps': 17027, 'loss/train': 2.611462354660034}
-03/04/2022 09:27:50 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 09:27:53 - INFO - codeparrot_training - Step 17028: {'lr': 0.00048738745462697754, 'samples': 8718848, 'steps': 17028, 'loss/train': 2.2122631072998047}
-03/04/2022 09:27:56 - INFO - codeparrot_training - Step 17029: {'lr': 0.0004873857902923196, 'samples': 8719360, 'steps': 17029, 'loss/train': 1.6640962362289429}
-03/04/2022 09:27:58 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/04/2022 09:28:02 - INFO - codeparrot_training - Step 17030: {'lr': 0.00048738412585069927, 'samples': 8719872, 'steps': 17030, 'loss/train': 1.687991976737976}
-03/04/2022 09:28:05 - INFO - codeparrot_training - Step 17031: {'lr': 0.00048738246130211734, 'samples': 8720384, 'steps': 17031, 'loss/train': 2.4635486602783203}
-03/04/2022 09:28:07 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/04/2022 09:28:10 - INFO - codeparrot_training - Step 17032: {'lr': 0.00048738079664657454, 'samples': 8720896, 'steps': 17032, 'loss/train': 6.62474250793457}
-03/04/2022 09:28:13 - INFO - codeparrot_training - Step 17033: {'lr': 0.00048737913188407156, 'samples': 8721408, 'steps': 17033, 'loss/train': 2.0110085010528564}
-03/04/2022 09:28:16 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/04/2022 09:28:19 - INFO - codeparrot_training - Step 17034: {'lr': 0.00048737746701460927, 'samples': 8721920, 'steps': 17034, 'loss/train': 1.663604497909546}
-03/04/2022 09:28:22 - INFO - codeparrot_training - Step 17035: {'lr': 0.0004873758020381883, 'samples': 8722432, 'steps': 17035, 'loss/train': 2.368196964263916}
-03/04/2022 09:28:24 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/04/2022 09:28:27 - INFO - codeparrot_training - Step 17036: {'lr': 0.00048737413695480947, 'samples': 8722944, 'steps': 17036, 'loss/train': 3.2607014179229736}
-03/04/2022 09:28:30 - INFO - codeparrot_training - Step 17037: {'lr': 0.00048737247176447354, 'samples': 8723456, 'steps': 17037, 'loss/train': 2.2232487201690674}
-03/04/2022 09:28:33 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/04/2022 09:28:36 - INFO - codeparrot_training - Step 17038: {'lr': 0.0004873708064671812, 'samples': 8723968, 'steps': 17038, 'loss/train': 2.1876864433288574}
-03/04/2022 09:28:39 - INFO - codeparrot_training - Step 17039: {'lr': 0.0004873691410629333, 'samples': 8724480, 'steps': 17039, 'loss/train': 2.320192575454712}
-03/04/2022 09:28:41 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/04/2022 09:28:44 - INFO - codeparrot_training - Step 17040: {'lr': 0.0004873674755517304, 'samples': 8724992, 'steps': 17040, 'loss/train': 2.677354097366333}
-03/04/2022 09:28:47 - INFO - codeparrot_training - Step 17041: {'lr': 0.00048736580993357357, 'samples': 8725504, 'steps': 17041, 'loss/train': 1.1840838193893433}
-03/04/2022 09:28:49 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 09:28:53 - INFO - codeparrot_training - Step 17042: {'lr': 0.0004873641442084632, 'samples': 8726016, 'steps': 17042, 'loss/train': 1.269323468208313}
-03/04/2022 09:28:56 - INFO - codeparrot_training - Step 17043: {'lr': 0.00048736247837640037, 'samples': 8726528, 'steps': 17043, 'loss/train': 1.7999725341796875}
-03/04/2022 09:28:58 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/04/2022 09:29:01 - INFO - codeparrot_training - Step 17044: {'lr': 0.0004873608124373855, 'samples': 8727040, 'steps': 17044, 'loss/train': 2.438044309616089}
-03/04/2022 09:29:04 - INFO - codeparrot_training - Step 17045: {'lr': 0.00048735914639141964, 'samples': 8727552, 'steps': 17045, 'loss/train': 1.3694199323654175}
-03/04/2022 09:29:07 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/04/2022 09:29:09 - INFO - codeparrot_training - Step 17046: {'lr': 0.00048735748023850337, 'samples': 8728064, 'steps': 17046, 'loss/train': 2.089823007583618}
-03/04/2022 09:29:13 - INFO - codeparrot_training - Step 17047: {'lr': 0.00048735581397863745, 'samples': 8728576, 'steps': 17047, 'loss/train': 1.908474326133728}
-03/04/2022 09:29:15 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 09:29:18 - INFO - codeparrot_training - Step 17048: {'lr': 0.0004873541476118227, 'samples': 8729088, 'steps': 17048, 'loss/train': 1.8098095655441284}
-03/04/2022 09:29:21 - INFO - codeparrot_training - Step 17049: {'lr': 0.00048735248113805976, 'samples': 8729600, 'steps': 17049, 'loss/train': 1.1103909015655518}
-03/04/2022 09:29:24 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/04/2022 09:29:26 - INFO - codeparrot_training - Step 17050: {'lr': 0.0004873508145573495, 'samples': 8730112, 'steps': 17050, 'loss/train': 0.9631534218788147}
-03/04/2022 09:29:30 - INFO - codeparrot_training - Step 17051: {'lr': 0.00048734914786969266, 'samples': 8730624, 'steps': 17051, 'loss/train': 2.084745168685913}
-03/04/2022 09:29:32 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/04/2022 09:29:35 - INFO - codeparrot_training - Step 17052: {'lr': 0.00048734748107509, 'samples': 8731136, 'steps': 17052, 'loss/train': 1.2581549882888794}
-03/04/2022 09:29:38 - INFO - codeparrot_training - Step 17053: {'lr': 0.0004873458141735421, 'samples': 8731648, 'steps': 17053, 'loss/train': 1.807431936264038}
-03/04/2022 09:29:41 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/04/2022 09:29:43 - INFO - codeparrot_training - Step 17054: {'lr': 0.0004873441471650499, 'samples': 8732160, 'steps': 17054, 'loss/train': 2.3514840602874756}
-03/04/2022 09:29:46 - INFO - codeparrot_training - Step 17055: {'lr': 0.00048734248004961414, 'samples': 8732672, 'steps': 17055, 'loss/train': 2.524091958999634}
-03/04/2022 09:29:49 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/04/2022 09:29:52 - INFO - codeparrot_training - Step 17056: {'lr': 0.00048734081282723543, 'samples': 8733184, 'steps': 17056, 'loss/train': 1.3448936939239502}
-03/04/2022 09:29:55 - INFO - codeparrot_training - Step 17057: {'lr': 0.00048733914549791465, 'samples': 8733696, 'steps': 17057, 'loss/train': 1.5965874195098877}
-03/04/2022 09:29:57 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/04/2022 09:30:00 - INFO - codeparrot_training - Step 17058: {'lr': 0.0004873374780616525, 'samples': 8734208, 'steps': 17058, 'loss/train': 1.9870991706848145}
-03/04/2022 09:30:03 - INFO - codeparrot_training - Step 17059: {'lr': 0.00048733581051844976, 'samples': 8734720, 'steps': 17059, 'loss/train': 1.9849728345870972}
-03/04/2022 09:30:06 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/04/2022 09:30:09 - INFO - codeparrot_training - Step 17060: {'lr': 0.00048733414286830716, 'samples': 8735232, 'steps': 17060, 'loss/train': 1.3484708070755005}
-03/04/2022 09:30:12 - INFO - codeparrot_training - Step 17061: {'lr': 0.00048733247511122547, 'samples': 8735744, 'steps': 17061, 'loss/train': 2.432173490524292}
-03/04/2022 09:30:14 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 09:30:17 - INFO - codeparrot_training - Step 17062: {'lr': 0.00048733080724720545, 'samples': 8736256, 'steps': 17062, 'loss/train': 5.5679826736450195}
-03/04/2022 09:30:21 - INFO - codeparrot_training - Step 17063: {'lr': 0.00048732913927624776, 'samples': 8736768, 'steps': 17063, 'loss/train': 1.5371040105819702}
-03/04/2022 09:30:24 - INFO - codeparrot_training - Step 17064: {'lr': 0.0004873274711983533, 'samples': 8737280, 'steps': 17064, 'loss/train': 2.051386833190918}
-03/04/2022 09:30:24 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/04/2022 09:30:29 - INFO - codeparrot_training - Step 17065: {'lr': 0.0004873258030135227, 'samples': 8737792, 'steps': 17065, 'loss/train': 1.4739885330200195}
-03/04/2022 09:30:33 - INFO - codeparrot_training - Step 17066: {'lr': 0.0004873241347217567, 'samples': 8738304, 'steps': 17066, 'loss/train': 2.2407567501068115}
-03/04/2022 09:30:34 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 09:30:38 - INFO - codeparrot_training - Step 17067: {'lr': 0.0004873224663230562, 'samples': 8738816, 'steps': 17067, 'loss/train': 2.238762140274048}
-03/04/2022 09:30:41 - INFO - codeparrot_training - Step 17068: {'lr': 0.0004873207978174219, 'samples': 8739328, 'steps': 17068, 'loss/train': 2.1703383922576904}
-03/04/2022 09:30:42 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/04/2022 09:30:46 - INFO - codeparrot_training - Step 17069: {'lr': 0.00048731912920485444, 'samples': 8739840, 'steps': 17069, 'loss/train': 1.6807875633239746}
-03/04/2022 09:30:49 - INFO - codeparrot_training - Step 17070: {'lr': 0.0004873174604853546, 'samples': 8740352, 'steps': 17070, 'loss/train': 1.9073567390441895}
-03/04/2022 09:30:51 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/04/2022 09:30:55 - INFO - codeparrot_training - Step 17071: {'lr': 0.00048731579165892325, 'samples': 8740864, 'steps': 17071, 'loss/train': 0.8900700211524963}
-03/04/2022 09:30:58 - INFO - codeparrot_training - Step 17072: {'lr': 0.000487314122725561, 'samples': 8741376, 'steps': 17072, 'loss/train': 1.9029769897460938}
-03/04/2022 09:30:59 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/04/2022 09:31:04 - INFO - codeparrot_training - Step 17073: {'lr': 0.00048731245368526877, 'samples': 8741888, 'steps': 17073, 'loss/train': 1.752681016921997}
-03/04/2022 09:31:07 - INFO - codeparrot_training - Step 17074: {'lr': 0.0004873107845380471, 'samples': 8742400, 'steps': 17074, 'loss/train': 3.722543239593506}
-03/04/2022 09:31:10 - INFO - codeparrot_training - Step 17075: {'lr': 0.00048730911528389686, 'samples': 8742912, 'steps': 17075, 'loss/train': 1.7301571369171143}
-03/04/2022 09:31:10 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/04/2022 09:31:15 - INFO - codeparrot_training - Step 17076: {'lr': 0.0004873074459228188, 'samples': 8743424, 'steps': 17076, 'loss/train': 1.7591311931610107}
-03/04/2022 09:31:18 - INFO - codeparrot_training - Step 17077: {'lr': 0.0004873057764548138, 'samples': 8743936, 'steps': 17077, 'loss/train': 2.2447030544281006}
-03/04/2022 09:31:18 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 09:31:24 - INFO - codeparrot_training - Step 17078: {'lr': 0.00048730410687988237, 'samples': 8744448, 'steps': 17078, 'loss/train': 1.5612919330596924}
-03/04/2022 09:31:27 - INFO - codeparrot_training - Step 17079: {'lr': 0.00048730243719802535, 'samples': 8744960, 'steps': 17079, 'loss/train': 2.052609920501709}
-03/04/2022 09:31:30 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/04/2022 09:31:33 - INFO - codeparrot_training - Step 17080: {'lr': 0.00048730076740924355, 'samples': 8745472, 'steps': 17080, 'loss/train': 2.001112461090088}
-03/04/2022 09:31:36 - INFO - codeparrot_training - Step 17081: {'lr': 0.0004872990975135377, 'samples': 8745984, 'steps': 17081, 'loss/train': 0.40842610597610474}
-03/04/2022 09:31:38 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 09:31:41 - INFO - codeparrot_training - Step 17082: {'lr': 0.0004872974275109085, 'samples': 8746496, 'steps': 17082, 'loss/train': 1.1621137857437134}
-03/04/2022 09:31:44 - INFO - codeparrot_training - Step 17083: {'lr': 0.00048729575740135675, 'samples': 8747008, 'steps': 17083, 'loss/train': 2.1182966232299805}
-03/04/2022 09:31:47 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 09:31:50 - INFO - codeparrot_training - Step 17084: {'lr': 0.0004872940871848832, 'samples': 8747520, 'steps': 17084, 'loss/train': 1.7584813833236694}
-03/04/2022 09:31:53 - INFO - codeparrot_training - Step 17085: {'lr': 0.00048729241686148864, 'samples': 8748032, 'steps': 17085, 'loss/train': 1.2249332666397095}
-03/04/2022 09:31:55 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 09:31:58 - INFO - codeparrot_training - Step 17086: {'lr': 0.0004872907464311737, 'samples': 8748544, 'steps': 17086, 'loss/train': 2.3586435317993164}
-03/04/2022 09:32:01 - INFO - codeparrot_training - Step 17087: {'lr': 0.0004872890758939392, 'samples': 8749056, 'steps': 17087, 'loss/train': 2.992093563079834}
-03/04/2022 09:32:04 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 09:32:07 - INFO - codeparrot_training - Step 17088: {'lr': 0.00048728740524978597, 'samples': 8749568, 'steps': 17088, 'loss/train': 2.095993995666504}
-03/04/2022 09:32:10 - INFO - codeparrot_training - Step 17089: {'lr': 0.00048728573449871473, 'samples': 8750080, 'steps': 17089, 'loss/train': 2.9900293350219727}
-03/04/2022 09:32:13 - INFO - codeparrot_training - Step 17090: {'lr': 0.0004872840636407261, 'samples': 8750592, 'steps': 17090, 'loss/train': 2.517744541168213}
-03/04/2022 09:32:13 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/04/2022 09:32:18 - INFO - codeparrot_training - Step 17091: {'lr': 0.00048728239267582096, 'samples': 8751104, 'steps': 17091, 'loss/train': 1.5301023721694946}
-03/04/2022 09:32:21 - INFO - codeparrot_training - Step 17092: {'lr': 0.00048728072160400006, 'samples': 8751616, 'steps': 17092, 'loss/train': 1.8416099548339844}
-03/04/2022 09:32:21 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/04/2022 09:32:27 - INFO - codeparrot_training - Step 17093: {'lr': 0.0004872790504252641, 'samples': 8752128, 'steps': 17093, 'loss/train': 0.8109533786773682}
-03/04/2022 09:32:30 - INFO - codeparrot_training - Step 17094: {'lr': 0.0004872773791396139, 'samples': 8752640, 'steps': 17094, 'loss/train': 1.6323556900024414}
-03/04/2022 09:32:30 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/04/2022 09:32:35 - INFO - codeparrot_training - Step 17095: {'lr': 0.0004872757077470502, 'samples': 8753152, 'steps': 17095, 'loss/train': 2.3780570030212402}
-03/04/2022 09:32:38 - INFO - codeparrot_training - Step 17096: {'lr': 0.0004872740362475737, 'samples': 8753664, 'steps': 17096, 'loss/train': 1.4135091304779053}
-03/04/2022 09:32:38 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/04/2022 09:32:44 - INFO - codeparrot_training - Step 17097: {'lr': 0.0004872723646411851, 'samples': 8754176, 'steps': 17097, 'loss/train': 1.5938845872879028}
-03/04/2022 09:32:47 - INFO - codeparrot_training - Step 17098: {'lr': 0.0004872706929278853, 'samples': 8754688, 'steps': 17098, 'loss/train': 1.1584092378616333}
-03/04/2022 09:32:47 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/04/2022 09:32:52 - INFO - codeparrot_training - Step 17099: {'lr': 0.000487269021107675, 'samples': 8755200, 'steps': 17099, 'loss/train': 1.1859915256500244}
-03/04/2022 09:32:55 - INFO - codeparrot_training - Step 17100: {'lr': 0.0004872673491805549, 'samples': 8755712, 'steps': 17100, 'loss/train': 2.2391159534454346}
-03/04/2022 09:32:55 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/04/2022 09:33:01 - INFO - codeparrot_training - Step 17101: {'lr': 0.0004872656771465259, 'samples': 8756224, 'steps': 17101, 'loss/train': 0.9763694405555725}
-03/04/2022 09:33:04 - INFO - codeparrot_training - Step 17102: {'lr': 0.00048726400500558856, 'samples': 8756736, 'steps': 17102, 'loss/train': 1.8844467401504517}
-03/04/2022 09:33:04 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/04/2022 09:33:09 - INFO - codeparrot_training - Step 17103: {'lr': 0.0004872623327577437, 'samples': 8757248, 'steps': 17103, 'loss/train': 2.577543020248413}
-03/04/2022 09:33:12 - INFO - codeparrot_training - Step 17104: {'lr': 0.0004872606604029921, 'samples': 8757760, 'steps': 17104, 'loss/train': 1.1057757139205933}
-03/04/2022 09:33:12 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/04/2022 09:33:18 - INFO - codeparrot_training - Step 17105: {'lr': 0.00048725898794133455, 'samples': 8758272, 'steps': 17105, 'loss/train': 1.9573076963424683}
-03/04/2022 09:33:21 - INFO - codeparrot_training - Step 17106: {'lr': 0.00048725731537277173, 'samples': 8758784, 'steps': 17106, 'loss/train': 2.4027652740478516}
-03/04/2022 09:33:21 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/04/2022 09:33:26 - INFO - codeparrot_training - Step 17107: {'lr': 0.0004872556426973044, 'samples': 8759296, 'steps': 17107, 'loss/train': 2.096590280532837}
-03/04/2022 09:33:29 - INFO - codeparrot_training - Step 17108: {'lr': 0.0004872539699149334, 'samples': 8759808, 'steps': 17108, 'loss/train': 3.0715389251708984}
-03/04/2022 09:33:29 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 09:33:35 - INFO - codeparrot_training - Step 17109: {'lr': 0.0004872522970256594, 'samples': 8760320, 'steps': 17109, 'loss/train': 1.5525943040847778}
-03/04/2022 09:33:38 - INFO - codeparrot_training - Step 17110: {'lr': 0.00048725062402948314, 'samples': 8760832, 'steps': 17110, 'loss/train': 2.497875213623047}
-03/04/2022 09:33:38 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 09:33:43 - INFO - codeparrot_training - Step 17111: {'lr': 0.00048724895092640546, 'samples': 8761344, 'steps': 17111, 'loss/train': 2.5655417442321777}
-03/04/2022 09:33:46 - INFO - codeparrot_training - Step 17112: {'lr': 0.00048724727771642706, 'samples': 8761856, 'steps': 17112, 'loss/train': 2.0300776958465576}
-03/04/2022 09:33:46 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/04/2022 09:33:52 - INFO - codeparrot_training - Step 17113: {'lr': 0.00048724560439954867, 'samples': 8762368, 'steps': 17113, 'loss/train': 1.3643265962600708}
-03/04/2022 09:33:55 - INFO - codeparrot_training - Step 17114: {'lr': 0.00048724393097577113, 'samples': 8762880, 'steps': 17114, 'loss/train': 3.0808236598968506}
-03/04/2022 09:33:55 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/04/2022 09:34:00 - INFO - codeparrot_training - Step 17115: {'lr': 0.0004872422574450951, 'samples': 8763392, 'steps': 17115, 'loss/train': 2.3056414127349854}
-03/04/2022 09:34:03 - INFO - codeparrot_training - Step 17116: {'lr': 0.0004872405838075213, 'samples': 8763904, 'steps': 17116, 'loss/train': 1.0287232398986816}
-03/04/2022 09:34:03 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 09:34:09 - INFO - codeparrot_training - Step 17117: {'lr': 0.00048723891006305066, 'samples': 8764416, 'steps': 17117, 'loss/train': 1.6343083381652832}
-03/04/2022 09:34:11 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 09:34:14 - INFO - codeparrot_training - Step 17118: {'lr': 0.0004872372362116838, 'samples': 8764928, 'steps': 17118, 'loss/train': 1.8367695808410645}
-03/04/2022 09:34:17 - INFO - codeparrot_training - Step 17119: {'lr': 0.0004872355622534215, 'samples': 8765440, 'steps': 17119, 'loss/train': 1.476016640663147}
-03/04/2022 09:34:20 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 09:34:22 - INFO - codeparrot_training - Step 17120: {'lr': 0.0004872338881882644, 'samples': 8765952, 'steps': 17120, 'loss/train': 3.5359251499176025}
-03/04/2022 09:34:25 - INFO - codeparrot_training - Step 17121: {'lr': 0.00048723221401621354, 'samples': 8766464, 'steps': 17121, 'loss/train': 1.3585875034332275}
-03/04/2022 09:34:28 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 09:34:31 - INFO - codeparrot_training - Step 17122: {'lr': 0.0004872305397372694, 'samples': 8766976, 'steps': 17122, 'loss/train': 1.6164674758911133}
-03/04/2022 09:34:34 - INFO - codeparrot_training - Step 17123: {'lr': 0.0004872288653514329, 'samples': 8767488, 'steps': 17123, 'loss/train': 1.6768649816513062}
-03/04/2022 09:34:36 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/04/2022 09:34:39 - INFO - codeparrot_training - Step 17124: {'lr': 0.0004872271908587047, 'samples': 8768000, 'steps': 17124, 'loss/train': 6.6288299560546875}
-03/04/2022 09:34:42 - INFO - codeparrot_training - Step 17125: {'lr': 0.0004872255162590856, 'samples': 8768512, 'steps': 17125, 'loss/train': 1.3283218145370483}
-03/04/2022 09:34:46 - INFO - codeparrot_training - Step 17126: {'lr': 0.0004872238415525764, 'samples': 8769024, 'steps': 17126, 'loss/train': 1.7718658447265625}
-03/04/2022 09:34:46 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/04/2022 09:34:51 - INFO - codeparrot_training - Step 17127: {'lr': 0.0004872221667391777, 'samples': 8769536, 'steps': 17127, 'loss/train': 1.925257682800293}
-03/04/2022 09:34:54 - INFO - codeparrot_training - Step 17128: {'lr': 0.00048722049181889037, 'samples': 8770048, 'steps': 17128, 'loss/train': 2.0928568840026855}
-03/04/2022 09:34:54 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/04/2022 09:34:59 - INFO - codeparrot_training - Step 17129: {'lr': 0.0004872188167917152, 'samples': 8770560, 'steps': 17129, 'loss/train': 2.0784177780151367}
-03/04/2022 09:35:03 - INFO - codeparrot_training - Step 17130: {'lr': 0.00048721714165765286, 'samples': 8771072, 'steps': 17130, 'loss/train': 1.6427758932113647}
-03/04/2022 09:35:03 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/04/2022 09:35:08 - INFO - codeparrot_training - Step 17131: {'lr': 0.00048721546641670413, 'samples': 8771584, 'steps': 17131, 'loss/train': 1.6314719915390015}
-03/04/2022 09:35:11 - INFO - codeparrot_training - Step 17132: {'lr': 0.00048721379106886976, 'samples': 8772096, 'steps': 17132, 'loss/train': 2.1309096813201904}
-03/04/2022 09:35:11 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/04/2022 09:35:16 - INFO - codeparrot_training - Step 17133: {'lr': 0.0004872121156141506, 'samples': 8772608, 'steps': 17133, 'loss/train': 2.6584198474884033}
-03/04/2022 09:35:19 - INFO - codeparrot_training - Step 17134: {'lr': 0.0004872104400525472, 'samples': 8773120, 'steps': 17134, 'loss/train': 2.2348036766052246}
-03/04/2022 09:35:19 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 09:35:25 - INFO - codeparrot_training - Step 17135: {'lr': 0.0004872087643840605, 'samples': 8773632, 'steps': 17135, 'loss/train': 1.9893642663955688}
-03/04/2022 09:35:28 - INFO - codeparrot_training - Step 17136: {'lr': 0.00048720708860869116, 'samples': 8774144, 'steps': 17136, 'loss/train': 2.3746910095214844}
-03/04/2022 09:35:28 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 09:35:33 - INFO - codeparrot_training - Step 17137: {'lr': 0.00048720541272644004, 'samples': 8774656, 'steps': 17137, 'loss/train': 2.1710352897644043}
-03/04/2022 09:35:36 - INFO - codeparrot_training - Step 17138: {'lr': 0.00048720373673730773, 'samples': 8775168, 'steps': 17138, 'loss/train': 2.093069553375244}
-03/04/2022 09:35:36 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/04/2022 09:35:42 - INFO - codeparrot_training - Step 17139: {'lr': 0.00048720206064129516, 'samples': 8775680, 'steps': 17139, 'loss/train': 1.600235104560852}
-03/04/2022 09:35:44 - INFO - codeparrot_training - Skipping example with length 920 (seq_length=1024)
-03/04/2022 09:35:47 - INFO - codeparrot_training - Step 17140: {'lr': 0.0004872003844384029, 'samples': 8776192, 'steps': 17140, 'loss/train': 1.9445676803588867}
-03/04/2022 09:35:50 - INFO - codeparrot_training - Step 17141: {'lr': 0.0004871987081286319, 'samples': 8776704, 'steps': 17141, 'loss/train': 2.0022990703582764}
-03/04/2022 09:35:53 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/04/2022 09:35:55 - INFO - codeparrot_training - Step 17142: {'lr': 0.0004871970317119828, 'samples': 8777216, 'steps': 17142, 'loss/train': 2.2677621841430664}
-03/04/2022 09:35:58 - INFO - codeparrot_training - Step 17143: {'lr': 0.00048719535518845634, 'samples': 8777728, 'steps': 17143, 'loss/train': 1.8111815452575684}
-03/04/2022 09:36:01 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 09:36:04 - INFO - codeparrot_training - Step 17144: {'lr': 0.0004871936785580533, 'samples': 8778240, 'steps': 17144, 'loss/train': 1.5211622714996338}
-03/04/2022 09:36:07 - INFO - codeparrot_training - Step 17145: {'lr': 0.0004871920018207745, 'samples': 8778752, 'steps': 17145, 'loss/train': 2.3356804847717285}
-03/04/2022 09:36:09 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 09:36:12 - INFO - codeparrot_training - Step 17146: {'lr': 0.0004871903249766206, 'samples': 8779264, 'steps': 17146, 'loss/train': 0.3230781555175781}
-03/04/2022 09:36:15 - INFO - codeparrot_training - Step 17147: {'lr': 0.0004871886480255925, 'samples': 8779776, 'steps': 17147, 'loss/train': 3.221109390258789}
-03/04/2022 09:36:19 - INFO - codeparrot_training - Step 17148: {'lr': 0.0004871869709676907, 'samples': 8780288, 'steps': 17148, 'loss/train': 2.2650420665740967}
-03/04/2022 09:36:19 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 09:36:24 - INFO - codeparrot_training - Step 17149: {'lr': 0.0004871852938029162, 'samples': 8780800, 'steps': 17149, 'loss/train': 2.366748571395874}
-03/04/2022 09:36:27 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 09:36:29 - INFO - codeparrot_training - Step 17150: {'lr': 0.00048718361653126975, 'samples': 8781312, 'steps': 17150, 'loss/train': 2.064260959625244}
-03/04/2022 09:36:33 - INFO - codeparrot_training - Step 17151: {'lr': 0.0004871819391527519, 'samples': 8781824, 'steps': 17151, 'loss/train': 1.5360852479934692}
-03/04/2022 09:36:35 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/04/2022 09:36:38 - INFO - codeparrot_training - Step 17152: {'lr': 0.0004871802616673636, 'samples': 8782336, 'steps': 17152, 'loss/train': 1.4840549230575562}
-03/04/2022 09:36:41 - INFO - codeparrot_training - Step 17153: {'lr': 0.00048717858407510545, 'samples': 8782848, 'steps': 17153, 'loss/train': 1.605756402015686}
-03/04/2022 09:36:44 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 09:36:46 - INFO - codeparrot_training - Step 17154: {'lr': 0.0004871769063759783, 'samples': 8783360, 'steps': 17154, 'loss/train': 2.627948522567749}
-03/04/2022 09:36:49 - INFO - codeparrot_training - Step 17155: {'lr': 0.000487175228569983, 'samples': 8783872, 'steps': 17155, 'loss/train': 0.9743406176567078}
-03/04/2022 09:36:52 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/04/2022 09:36:55 - INFO - codeparrot_training - Step 17156: {'lr': 0.0004871735506571201, 'samples': 8784384, 'steps': 17156, 'loss/train': 1.6425554752349854}
-03/04/2022 09:36:58 - INFO - codeparrot_training - Step 17157: {'lr': 0.00048717187263739046, 'samples': 8784896, 'steps': 17157, 'loss/train': 1.7979509830474854}
-03/04/2022 09:37:01 - INFO - codeparrot_training - Step 17158: {'lr': 0.00048717019451079493, 'samples': 8785408, 'steps': 17158, 'loss/train': 1.873268723487854}
-03/04/2022 09:37:01 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/04/2022 09:37:06 - INFO - codeparrot_training - Step 17159: {'lr': 0.00048716851627733404, 'samples': 8785920, 'steps': 17159, 'loss/train': 1.8272831439971924}
-03/04/2022 09:37:09 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 09:37:12 - INFO - codeparrot_training - Step 17160: {'lr': 0.00048716683793700876, 'samples': 8786432, 'steps': 17160, 'loss/train': 2.3660850524902344}
-03/04/2022 09:37:15 - INFO - codeparrot_training - Step 17161: {'lr': 0.00048716515948981975, 'samples': 8786944, 'steps': 17161, 'loss/train': 2.6776652336120605}
-03/04/2022 09:37:17 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 09:37:20 - INFO - codeparrot_training - Step 17162: {'lr': 0.0004871634809357678, 'samples': 8787456, 'steps': 17162, 'loss/train': 2.009446620941162}
-03/04/2022 09:37:23 - INFO - codeparrot_training - Step 17163: {'lr': 0.00048716180227485365, 'samples': 8787968, 'steps': 17163, 'loss/train': 1.2721511125564575}
-03/04/2022 09:37:26 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 09:37:28 - INFO - codeparrot_training - Step 17164: {'lr': 0.000487160123507078, 'samples': 8788480, 'steps': 17164, 'loss/train': 1.7694755792617798}
-03/04/2022 09:37:32 - INFO - codeparrot_training - Step 17165: {'lr': 0.00048715844463244166, 'samples': 8788992, 'steps': 17165, 'loss/train': 2.118525981903076}
-03/04/2022 09:37:34 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/04/2022 09:37:37 - INFO - codeparrot_training - Step 17166: {'lr': 0.0004871567656509454, 'samples': 8789504, 'steps': 17166, 'loss/train': 0.41063520312309265}
-03/04/2022 09:37:40 - INFO - codeparrot_training - Step 17167: {'lr': 0.00048715508656259, 'samples': 8790016, 'steps': 17167, 'loss/train': 1.2649964094161987}
-03/04/2022 09:37:43 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/04/2022 09:37:45 - INFO - codeparrot_training - Step 17168: {'lr': 0.00048715340736737615, 'samples': 8790528, 'steps': 17168, 'loss/train': 2.618745803833008}
-03/04/2022 09:37:48 - INFO - codeparrot_training - Step 17169: {'lr': 0.0004871517280653046, 'samples': 8791040, 'steps': 17169, 'loss/train': 2.0385875701904297}
-03/04/2022 09:37:51 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 09:37:54 - INFO - codeparrot_training - Step 17170: {'lr': 0.0004871500486563761, 'samples': 8791552, 'steps': 17170, 'loss/train': 2.3049304485321045}
-03/04/2022 09:37:57 - INFO - codeparrot_training - Step 17171: {'lr': 0.0004871483691405916, 'samples': 8792064, 'steps': 17171, 'loss/train': 2.17268705368042}
-03/04/2022 09:37:59 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/04/2022 09:38:02 - INFO - codeparrot_training - Step 17172: {'lr': 0.0004871466895179516, 'samples': 8792576, 'steps': 17172, 'loss/train': 2.057309150695801}
-03/04/2022 09:38:05 - INFO - codeparrot_training - Step 17173: {'lr': 0.000487145009788457, 'samples': 8793088, 'steps': 17173, 'loss/train': 4.4460344314575195}
-03/04/2022 09:38:08 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/04/2022 09:38:11 - INFO - codeparrot_training - Step 17174: {'lr': 0.0004871433299521085, 'samples': 8793600, 'steps': 17174, 'loss/train': 2.193152904510498}
-03/04/2022 09:38:14 - INFO - codeparrot_training - Step 17175: {'lr': 0.00048714165000890685, 'samples': 8794112, 'steps': 17175, 'loss/train': 1.9647339582443237}
-03/04/2022 09:38:16 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/04/2022 09:38:19 - INFO - codeparrot_training - Step 17176: {'lr': 0.00048713996995885286, 'samples': 8794624, 'steps': 17176, 'loss/train': 1.7832444906234741}
-03/04/2022 09:38:22 - INFO - codeparrot_training - Step 17177: {'lr': 0.0004871382898019472, 'samples': 8795136, 'steps': 17177, 'loss/train': 1.4419245719909668}
-03/04/2022 09:38:25 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/04/2022 09:38:27 - INFO - codeparrot_training - Step 17178: {'lr': 0.0004871366095381908, 'samples': 8795648, 'steps': 17178, 'loss/train': 1.6321632862091064}
-03/04/2022 09:38:31 - INFO - codeparrot_training - Step 17179: {'lr': 0.00048713492916758425, 'samples': 8796160, 'steps': 17179, 'loss/train': 1.8229118585586548}
-03/04/2022 09:38:33 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/04/2022 09:38:36 - INFO - codeparrot_training - Step 17180: {'lr': 0.00048713324869012833, 'samples': 8796672, 'steps': 17180, 'loss/train': 1.8744003772735596}
-03/04/2022 09:38:39 - INFO - codeparrot_training - Step 17181: {'lr': 0.0004871315681058238, 'samples': 8797184, 'steps': 17181, 'loss/train': 0.44500213861465454}
-03/04/2022 09:38:42 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/04/2022 09:38:44 - INFO - codeparrot_training - Step 17182: {'lr': 0.0004871298874146716, 'samples': 8797696, 'steps': 17182, 'loss/train': 1.674233078956604}
-03/04/2022 09:38:48 - INFO - codeparrot_training - Step 17183: {'lr': 0.00048712820661667215, 'samples': 8798208, 'steps': 17183, 'loss/train': 0.7629336714744568}
-03/04/2022 09:38:50 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/04/2022 09:38:53 - INFO - codeparrot_training - Step 17184: {'lr': 0.0004871265257118265, 'samples': 8798720, 'steps': 17184, 'loss/train': 1.3591198921203613}
-03/04/2022 09:38:56 - INFO - codeparrot_training - Step 17185: {'lr': 0.0004871248447001352, 'samples': 8799232, 'steps': 17185, 'loss/train': 1.744114637374878}
-03/04/2022 09:38:59 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 09:39:01 - INFO - codeparrot_training - Step 17186: {'lr': 0.0004871231635815992, 'samples': 8799744, 'steps': 17186, 'loss/train': 2.3362245559692383}
-03/04/2022 09:39:04 - INFO - codeparrot_training - Step 17187: {'lr': 0.0004871214823562191, 'samples': 8800256, 'steps': 17187, 'loss/train': 2.155303955078125}
-03/04/2022 09:39:07 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/04/2022 09:39:10 - INFO - codeparrot_training - Step 17188: {'lr': 0.0004871198010239958, 'samples': 8800768, 'steps': 17188, 'loss/train': 2.2956764698028564}
-03/04/2022 09:39:13 - INFO - codeparrot_training - Step 17189: {'lr': 0.0004871181195849299, 'samples': 8801280, 'steps': 17189, 'loss/train': 1.8212308883666992}
-03/04/2022 09:39:16 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 09:39:18 - INFO - codeparrot_training - Step 17190: {'lr': 0.00048711643803902227, 'samples': 8801792, 'steps': 17190, 'loss/train': 1.9037054777145386}
-03/04/2022 09:39:21 - INFO - codeparrot_training - Step 17191: {'lr': 0.00048711475638627363, 'samples': 8802304, 'steps': 17191, 'loss/train': 2.2839877605438232}
-03/04/2022 09:39:24 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 09:39:27 - INFO - codeparrot_training - Step 17192: {'lr': 0.0004871130746266847, 'samples': 8802816, 'steps': 17192, 'loss/train': 2.323458194732666}
-03/04/2022 09:39:30 - INFO - codeparrot_training - Step 17193: {'lr': 0.00048711139276025626, 'samples': 8803328, 'steps': 17193, 'loss/train': 1.6542283296585083}
-03/04/2022 09:39:32 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 09:39:35 - INFO - codeparrot_training - Step 17194: {'lr': 0.00048710971078698916, 'samples': 8803840, 'steps': 17194, 'loss/train': 1.9304890632629395}
-03/04/2022 09:39:38 - INFO - codeparrot_training - Step 17195: {'lr': 0.0004871080287068841, 'samples': 8804352, 'steps': 17195, 'loss/train': 1.6915414333343506}
-03/04/2022 09:39:40 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/04/2022 09:39:43 - INFO - codeparrot_training - Step 17196: {'lr': 0.00048710634651994176, 'samples': 8804864, 'steps': 17196, 'loss/train': 1.9733059406280518}
-03/04/2022 09:39:47 - INFO - codeparrot_training - Step 17197: {'lr': 0.0004871046642261629, 'samples': 8805376, 'steps': 17197, 'loss/train': 1.8302311897277832}
-03/04/2022 09:39:49 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 09:39:52 - INFO - codeparrot_training - Step 17198: {'lr': 0.0004871029818255485, 'samples': 8805888, 'steps': 17198, 'loss/train': 1.5511212348937988}
-03/04/2022 09:39:55 - INFO - codeparrot_training - Step 17199: {'lr': 0.0004871012993180991, 'samples': 8806400, 'steps': 17199, 'loss/train': 2.3325717449188232}
-03/04/2022 09:39:57 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/04/2022 09:40:00 - INFO - codeparrot_training - Step 17200: {'lr': 0.0004870996167038154, 'samples': 8806912, 'steps': 17200, 'loss/train': 2.51958966255188}
-03/04/2022 09:40:03 - INFO - codeparrot_training - Step 17201: {'lr': 0.0004870979339826984, 'samples': 8807424, 'steps': 17201, 'loss/train': 2.025771141052246}
-03/04/2022 09:40:06 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 09:40:09 - INFO - codeparrot_training - Step 17202: {'lr': 0.00048709625115474865, 'samples': 8807936, 'steps': 17202, 'loss/train': 1.9421520233154297}
-03/04/2022 09:40:12 - INFO - codeparrot_training - Step 17203: {'lr': 0.00048709456821996705, 'samples': 8808448, 'steps': 17203, 'loss/train': 1.8844058513641357}
-03/04/2022 09:40:14 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 09:40:17 - INFO - codeparrot_training - Step 17204: {'lr': 0.0004870928851783543, 'samples': 8808960, 'steps': 17204, 'loss/train': 1.8601571321487427}
-03/04/2022 09:40:20 - INFO - codeparrot_training - Step 17205: {'lr': 0.00048709120202991107, 'samples': 8809472, 'steps': 17205, 'loss/train': 1.4029299020767212}
-03/04/2022 09:40:23 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/04/2022 09:40:26 - INFO - codeparrot_training - Step 17206: {'lr': 0.0004870895187746383, 'samples': 8809984, 'steps': 17206, 'loss/train': 1.2994829416275024}
-03/04/2022 09:40:29 - INFO - codeparrot_training - Step 17207: {'lr': 0.00048708783541253655, 'samples': 8810496, 'steps': 17207, 'loss/train': 1.9149757623672485}
-03/04/2022 09:40:32 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 09:40:34 - INFO - codeparrot_training - Step 17208: {'lr': 0.00048708615194360675, 'samples': 8811008, 'steps': 17208, 'loss/train': 1.8116834163665771}
-03/04/2022 09:40:37 - INFO - codeparrot_training - Step 17209: {'lr': 0.0004870844683678496, 'samples': 8811520, 'steps': 17209, 'loss/train': 1.893630027770996}
-03/04/2022 09:40:41 - INFO - codeparrot_training - Step 17210: {'lr': 0.0004870827846852658, 'samples': 8812032, 'steps': 17210, 'loss/train': 2.1882166862487793}
-03/04/2022 09:40:41 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 09:40:46 - INFO - codeparrot_training - Step 17211: {'lr': 0.00048708110089585617, 'samples': 8812544, 'steps': 17211, 'loss/train': 0.36348676681518555}
-03/04/2022 09:40:49 - INFO - codeparrot_training - Step 17212: {'lr': 0.00048707941699962143, 'samples': 8813056, 'steps': 17212, 'loss/train': 1.9120007753372192}
-03/04/2022 09:40:49 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 09:40:54 - INFO - codeparrot_training - Step 17213: {'lr': 0.0004870777329965624, 'samples': 8813568, 'steps': 17213, 'loss/train': 1.587878704071045}
-03/04/2022 09:40:57 - INFO - codeparrot_training - Step 17214: {'lr': 0.00048707604888667983, 'samples': 8814080, 'steps': 17214, 'loss/train': 1.5667716264724731}
-03/04/2022 09:40:57 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 09:41:03 - INFO - codeparrot_training - Step 17215: {'lr': 0.0004870743646699744, 'samples': 8814592, 'steps': 17215, 'loss/train': 2.01271653175354}
-03/04/2022 09:41:06 - INFO - codeparrot_training - Step 17216: {'lr': 0.0004870726803464469, 'samples': 8815104, 'steps': 17216, 'loss/train': 1.2849370241165161}
-03/04/2022 09:41:07 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/04/2022 09:41:11 - INFO - codeparrot_training - Step 17217: {'lr': 0.00048707099591609816, 'samples': 8815616, 'steps': 17217, 'loss/train': 1.995800256729126}
-03/04/2022 09:41:14 - INFO - codeparrot_training - Step 17218: {'lr': 0.0004870693113789289, 'samples': 8816128, 'steps': 17218, 'loss/train': 2.1396496295928955}
-03/04/2022 09:41:15 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/04/2022 09:41:20 - INFO - codeparrot_training - Step 17219: {'lr': 0.00048706762673493987, 'samples': 8816640, 'steps': 17219, 'loss/train': 1.4164272546768188}
-03/04/2022 09:41:23 - INFO - codeparrot_training - Step 17220: {'lr': 0.00048706594198413177, 'samples': 8817152, 'steps': 17220, 'loss/train': 1.4853577613830566}
-03/04/2022 09:41:23 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 09:41:28 - INFO - codeparrot_training - Step 17221: {'lr': 0.0004870642571265054, 'samples': 8817664, 'steps': 17221, 'loss/train': 0.30922991037368774}
-03/04/2022 09:41:31 - INFO - codeparrot_training - Step 17222: {'lr': 0.0004870625721620616, 'samples': 8818176, 'steps': 17222, 'loss/train': 2.199002981185913}
-03/04/2022 09:41:32 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/04/2022 09:41:36 - INFO - codeparrot_training - Step 17223: {'lr': 0.00048706088709080103, 'samples': 8818688, 'steps': 17223, 'loss/train': 3.0391952991485596}
-03/04/2022 09:41:40 - INFO - codeparrot_training - Step 17224: {'lr': 0.00048705920191272447, 'samples': 8819200, 'steps': 17224, 'loss/train': 1.3640570640563965}
-03/04/2022 09:41:40 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 09:41:45 - INFO - codeparrot_training - Step 17225: {'lr': 0.0004870575166278327, 'samples': 8819712, 'steps': 17225, 'loss/train': 1.945119857788086}
-03/04/2022 09:41:48 - INFO - codeparrot_training - Step 17226: {'lr': 0.0004870558312361265, 'samples': 8820224, 'steps': 17226, 'loss/train': 0.1389172524213791}
-03/04/2022 09:41:48 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 09:41:53 - INFO - codeparrot_training - Step 17227: {'lr': 0.0004870541457376066, 'samples': 8820736, 'steps': 17227, 'loss/train': 1.1025177240371704}
-03/04/2022 09:41:56 - INFO - codeparrot_training - Step 17228: {'lr': 0.0004870524601322737, 'samples': 8821248, 'steps': 17228, 'loss/train': 1.5354255437850952}
-03/04/2022 09:41:56 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/04/2022 09:42:02 - INFO - codeparrot_training - Step 17229: {'lr': 0.00048705077442012866, 'samples': 8821760, 'steps': 17229, 'loss/train': 3.416273593902588}
-03/04/2022 09:42:05 - INFO - codeparrot_training - Step 17230: {'lr': 0.0004870490886011723, 'samples': 8822272, 'steps': 17230, 'loss/train': 2.3873677253723145}
-03/04/2022 09:42:05 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/04/2022 09:42:10 - INFO - codeparrot_training - Step 17231: {'lr': 0.0004870474026754051, 'samples': 8822784, 'steps': 17231, 'loss/train': 1.6248579025268555}
-03/04/2022 09:42:13 - INFO - codeparrot_training - Step 17232: {'lr': 0.00048704571664282806, 'samples': 8823296, 'steps': 17232, 'loss/train': 1.8388217687606812}
-03/04/2022 09:42:13 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/04/2022 09:42:19 - INFO - codeparrot_training - Step 17233: {'lr': 0.0004870440305034419, 'samples': 8823808, 'steps': 17233, 'loss/train': 1.719441294670105}
-03/04/2022 09:42:22 - INFO - codeparrot_training - Step 17234: {'lr': 0.00048704234425724736, 'samples': 8824320, 'steps': 17234, 'loss/train': 2.2794764041900635}
-03/04/2022 09:42:22 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 09:42:27 - INFO - codeparrot_training - Step 17235: {'lr': 0.0004870406579042452, 'samples': 8824832, 'steps': 17235, 'loss/train': 2.451948881149292}
-03/04/2022 09:42:30 - INFO - codeparrot_training - Step 17236: {'lr': 0.00048703897144443615, 'samples': 8825344, 'steps': 17236, 'loss/train': 2.450913906097412}
-03/04/2022 09:42:30 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/04/2022 09:42:35 - INFO - codeparrot_training - Step 17237: {'lr': 0.000487037284877821, 'samples': 8825856, 'steps': 17237, 'loss/train': 1.8403140306472778}
-03/04/2022 09:42:38 - INFO - codeparrot_training - Step 17238: {'lr': 0.00048703559820440054, 'samples': 8826368, 'steps': 17238, 'loss/train': 1.515211582183838}
-03/04/2022 09:42:39 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 09:42:44 - INFO - codeparrot_training - Step 17239: {'lr': 0.0004870339114241755, 'samples': 8826880, 'steps': 17239, 'loss/train': 1.9624067544937134}
-03/04/2022 09:42:47 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 09:42:49 - INFO - codeparrot_training - Step 17240: {'lr': 0.00048703222453714656, 'samples': 8827392, 'steps': 17240, 'loss/train': 1.813470721244812}
-03/04/2022 09:42:52 - INFO - codeparrot_training - Step 17241: {'lr': 0.0004870305375433146, 'samples': 8827904, 'steps': 17241, 'loss/train': 1.9446817636489868}
-03/04/2022 09:42:55 - INFO - codeparrot_training - Step 17242: {'lr': 0.0004870288504426804, 'samples': 8828416, 'steps': 17242, 'loss/train': 1.0914981365203857}
-03/04/2022 09:42:55 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 09:43:01 - INFO - codeparrot_training - Step 17243: {'lr': 0.0004870271632352446, 'samples': 8828928, 'steps': 17243, 'loss/train': 1.5446547269821167}
-03/04/2022 09:43:04 - INFO - codeparrot_training - Step 17244: {'lr': 0.000487025475921008, 'samples': 8829440, 'steps': 17244, 'loss/train': 1.75636625289917}
-03/04/2022 09:43:04 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 09:43:09 - INFO - codeparrot_training - Step 17245: {'lr': 0.00048702378849997143, 'samples': 8829952, 'steps': 17245, 'loss/train': 2.251702070236206}
-03/04/2022 09:43:12 - INFO - codeparrot_training - Step 17246: {'lr': 0.0004870221009721356, 'samples': 8830464, 'steps': 17246, 'loss/train': 2.2966339588165283}
-03/04/2022 09:43:13 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/04/2022 09:43:18 - INFO - codeparrot_training - Step 17247: {'lr': 0.00048702041333750117, 'samples': 8830976, 'steps': 17247, 'loss/train': 1.9002872705459595}
-03/04/2022 09:43:21 - INFO - codeparrot_training - Step 17248: {'lr': 0.0004870187255960691, 'samples': 8831488, 'steps': 17248, 'loss/train': 1.1937402486801147}
-03/04/2022 09:43:21 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 09:43:26 - INFO - codeparrot_training - Step 17249: {'lr': 0.00048701703774784, 'samples': 8832000, 'steps': 17249, 'loss/train': 1.2602213621139526}
-03/04/2022 09:43:29 - INFO - codeparrot_training - Step 17250: {'lr': 0.0004870153497928147, 'samples': 8832512, 'steps': 17250, 'loss/train': 1.9372429847717285}
-03/04/2022 09:43:29 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 09:43:34 - INFO - codeparrot_training - Step 17251: {'lr': 0.00048701366173099396, 'samples': 8833024, 'steps': 17251, 'loss/train': 1.6361618041992188}
-03/04/2022 09:43:38 - INFO - codeparrot_training - Step 17252: {'lr': 0.0004870119735623785, 'samples': 8833536, 'steps': 17252, 'loss/train': 1.045925259590149}
-03/04/2022 09:43:38 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/04/2022 09:43:43 - INFO - codeparrot_training - Step 17253: {'lr': 0.00048701028528696914, 'samples': 8834048, 'steps': 17253, 'loss/train': 0.7971089482307434}
-03/04/2022 09:43:46 - INFO - codeparrot_training - Step 17254: {'lr': 0.0004870085969047665, 'samples': 8834560, 'steps': 17254, 'loss/train': 1.316550374031067}
-03/04/2022 09:43:46 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/04/2022 09:43:51 - INFO - codeparrot_training - Step 17255: {'lr': 0.00048700690841577154, 'samples': 8835072, 'steps': 17255, 'loss/train': 0.9032773375511169}
-03/04/2022 09:43:54 - INFO - codeparrot_training - Step 17256: {'lr': 0.0004870052198199849, 'samples': 8835584, 'steps': 17256, 'loss/train': 1.1718623638153076}
-03/04/2022 09:43:54 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/04/2022 09:44:00 - INFO - codeparrot_training - Step 17257: {'lr': 0.00048700353111740734, 'samples': 8836096, 'steps': 17257, 'loss/train': 1.1684075593948364}
-03/04/2022 09:44:03 - INFO - codeparrot_training - Step 17258: {'lr': 0.0004870018423080397, 'samples': 8836608, 'steps': 17258, 'loss/train': 2.087352752685547}
-03/04/2022 09:44:03 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/04/2022 09:44:08 - INFO - codeparrot_training - Step 17259: {'lr': 0.00048700015339188266, 'samples': 8837120, 'steps': 17259, 'loss/train': 1.2166283130645752}
-03/04/2022 09:44:11 - INFO - codeparrot_training - Step 17260: {'lr': 0.0004869984643689369, 'samples': 8837632, 'steps': 17260, 'loss/train': 1.9575586318969727}
-03/04/2022 09:44:11 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/04/2022 09:44:17 - INFO - codeparrot_training - Step 17261: {'lr': 0.00048699677523920346, 'samples': 8838144, 'steps': 17261, 'loss/train': 1.5496422052383423}
-03/04/2022 09:44:20 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/04/2022 09:44:22 - INFO - codeparrot_training - Step 17262: {'lr': 0.00048699508600268284, 'samples': 8838656, 'steps': 17262, 'loss/train': 2.54762864112854}
-03/04/2022 09:44:25 - INFO - codeparrot_training - Step 17263: {'lr': 0.00048699339665937594, 'samples': 8839168, 'steps': 17263, 'loss/train': 2.1158645153045654}
-03/04/2022 09:44:28 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/04/2022 09:44:30 - INFO - codeparrot_training - Step 17264: {'lr': 0.0004869917072092834, 'samples': 8839680, 'steps': 17264, 'loss/train': 1.9821112155914307}
-03/04/2022 09:44:33 - INFO - codeparrot_training - Step 17265: {'lr': 0.00048699001765240615, 'samples': 8840192, 'steps': 17265, 'loss/train': 2.285323143005371}
-03/04/2022 09:44:36 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/04/2022 09:44:39 - INFO - codeparrot_training - Step 17266: {'lr': 0.00048698832798874477, 'samples': 8840704, 'steps': 17266, 'loss/train': 2.0845487117767334}
-03/04/2022 09:44:42 - INFO - codeparrot_training - Step 17267: {'lr': 0.0004869866382183001, 'samples': 8841216, 'steps': 17267, 'loss/train': 1.7546137571334839}
-03/04/2022 09:44:45 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/04/2022 09:44:47 - INFO - codeparrot_training - Step 17268: {'lr': 0.00048698494834107297, 'samples': 8841728, 'steps': 17268, 'loss/train': 2.6543989181518555}
-03/04/2022 09:44:50 - INFO - codeparrot_training - Step 17269: {'lr': 0.000486983258357064, 'samples': 8842240, 'steps': 17269, 'loss/train': 2.1987643241882324}
-03/04/2022 09:44:54 - INFO - codeparrot_training - Step 17270: {'lr': 0.00048698156826627414, 'samples': 8842752, 'steps': 17270, 'loss/train': 1.4019421339035034}
-03/04/2022 09:44:54 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/04/2022 09:44:59 - INFO - codeparrot_training - Step 17271: {'lr': 0.00048697987806870397, 'samples': 8843264, 'steps': 17271, 'loss/train': 2.231374502182007}
-03/04/2022 09:45:02 - INFO - codeparrot_training - Step 17272: {'lr': 0.0004869781877643543, 'samples': 8843776, 'steps': 17272, 'loss/train': 2.0675179958343506}
-03/04/2022 09:45:02 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/04/2022 09:45:07 - INFO - codeparrot_training - Step 17273: {'lr': 0.000486976497353226, 'samples': 8844288, 'steps': 17273, 'loss/train': 1.9011173248291016}
-03/04/2022 09:45:10 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 09:45:13 - INFO - codeparrot_training - Step 17274: {'lr': 0.0004869748068353197, 'samples': 8844800, 'steps': 17274, 'loss/train': 1.6328771114349365}
-03/04/2022 09:45:16 - INFO - codeparrot_training - Step 17275: {'lr': 0.00048697311621063625, 'samples': 8845312, 'steps': 17275, 'loss/train': 2.1835434436798096}
-03/04/2022 09:45:19 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/04/2022 09:45:21 - INFO - codeparrot_training - Step 17276: {'lr': 0.0004869714254791763, 'samples': 8845824, 'steps': 17276, 'loss/train': 2.477288246154785}
-03/04/2022 09:45:24 - INFO - codeparrot_training - Step 17277: {'lr': 0.00048696973464094076, 'samples': 8846336, 'steps': 17277, 'loss/train': 1.7769064903259277}
-03/04/2022 09:45:27 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 09:45:30 - INFO - codeparrot_training - Step 17278: {'lr': 0.00048696804369593023, 'samples': 8846848, 'steps': 17278, 'loss/train': 2.077842950820923}
-03/04/2022 09:45:33 - INFO - codeparrot_training - Step 17279: {'lr': 0.0004869663526441456, 'samples': 8847360, 'steps': 17279, 'loss/train': 2.525975465774536}
-03/04/2022 09:45:35 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/04/2022 09:45:38 - INFO - codeparrot_training - Step 17280: {'lr': 0.0004869646614855876, 'samples': 8847872, 'steps': 17280, 'loss/train': 1.6253045797348022}
-03/04/2022 09:45:41 - INFO - codeparrot_training - Step 17281: {'lr': 0.0004869629702202569, 'samples': 8848384, 'steps': 17281, 'loss/train': 2.010293960571289}
-03/04/2022 09:45:43 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/04/2022 09:45:47 - INFO - codeparrot_training - Step 17282: {'lr': 0.0004869612788481544, 'samples': 8848896, 'steps': 17282, 'loss/train': 0.5218611359596252}
-03/04/2022 09:45:50 - INFO - codeparrot_training - Step 17283: {'lr': 0.00048695958736928084, 'samples': 8849408, 'steps': 17283, 'loss/train': 2.7404403686523438}
-03/04/2022 09:45:52 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/04/2022 09:45:55 - INFO - codeparrot_training - Step 17284: {'lr': 0.00048695789578363693, 'samples': 8849920, 'steps': 17284, 'loss/train': 2.1637532711029053}
-03/04/2022 09:45:58 - INFO - codeparrot_training - Step 17285: {'lr': 0.00048695620409122345, 'samples': 8850432, 'steps': 17285, 'loss/train': 0.47995975613594055}
-03/04/2022 09:46:01 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 09:46:03 - INFO - codeparrot_training - Step 17286: {'lr': 0.00048695451229204115, 'samples': 8850944, 'steps': 17286, 'loss/train': 2.5006909370422363}
-03/04/2022 09:46:07 - INFO - codeparrot_training - Step 17287: {'lr': 0.0004869528203860908, 'samples': 8851456, 'steps': 17287, 'loss/train': 2.719730854034424}
-03/04/2022 09:46:09 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/04/2022 09:46:12 - INFO - codeparrot_training - Step 17288: {'lr': 0.0004869511283733732, 'samples': 8851968, 'steps': 17288, 'loss/train': 1.7425758838653564}
-03/04/2022 09:46:15 - INFO - codeparrot_training - Step 17289: {'lr': 0.000486949436253889, 'samples': 8852480, 'steps': 17289, 'loss/train': 1.031009316444397}
-03/04/2022 09:46:17 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 09:46:20 - INFO - codeparrot_training - Step 17290: {'lr': 0.0004869477440276391, 'samples': 8852992, 'steps': 17290, 'loss/train': 2.2604832649230957}
-03/04/2022 09:46:23 - INFO - codeparrot_training - Step 17291: {'lr': 0.00048694605169462415, 'samples': 8853504, 'steps': 17291, 'loss/train': 3.219592332839966}
-03/04/2022 09:46:25 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/04/2022 09:46:29 - INFO - codeparrot_training - Step 17292: {'lr': 0.00048694435925484506, 'samples': 8854016, 'steps': 17292, 'loss/train': 2.4387688636779785}
-03/04/2022 09:46:32 - INFO - codeparrot_training - Step 17293: {'lr': 0.0004869426667083024, 'samples': 8854528, 'steps': 17293, 'loss/train': 1.6752530336380005}
-03/04/2022 09:46:34 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 09:46:37 - INFO - codeparrot_training - Step 17294: {'lr': 0.00048694097405499703, 'samples': 8855040, 'steps': 17294, 'loss/train': 2.059356451034546}
-03/04/2022 09:46:40 - INFO - codeparrot_training - Step 17295: {'lr': 0.0004869392812949298, 'samples': 8855552, 'steps': 17295, 'loss/train': 2.0992352962493896}
-03/04/2022 09:46:43 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 09:46:46 - INFO - codeparrot_training - Step 17296: {'lr': 0.00048693758842810133, 'samples': 8856064, 'steps': 17296, 'loss/train': 2.2586476802825928}
-03/04/2022 09:46:49 - INFO - codeparrot_training - Step 17297: {'lr': 0.00048693589545451243, 'samples': 8856576, 'steps': 17297, 'loss/train': 1.8282818794250488}
-03/04/2022 09:46:51 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/04/2022 09:46:54 - INFO - codeparrot_training - Step 17298: {'lr': 0.00048693420237416393, 'samples': 8857088, 'steps': 17298, 'loss/train': 1.5754973888397217}
-03/04/2022 09:46:57 - INFO - codeparrot_training - Step 17299: {'lr': 0.00048693250918705643, 'samples': 8857600, 'steps': 17299, 'loss/train': 1.4311652183532715}
-03/04/2022 09:47:00 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/04/2022 09:47:02 - INFO - codeparrot_training - Step 17300: {'lr': 0.0004869308158931909, 'samples': 8858112, 'steps': 17300, 'loss/train': 2.1784815788269043}
-03/04/2022 09:47:05 - INFO - codeparrot_training - Step 17301: {'lr': 0.00048692912249256794, 'samples': 8858624, 'steps': 17301, 'loss/train': 1.1745154857635498}
-03/04/2022 09:47:08 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/04/2022 09:47:11 - INFO - codeparrot_training - Step 17302: {'lr': 0.00048692742898518836, 'samples': 8859136, 'steps': 17302, 'loss/train': 2.6955294609069824}
-03/04/2022 09:47:14 - INFO - codeparrot_training - Step 17303: {'lr': 0.000486925735371053, 'samples': 8859648, 'steps': 17303, 'loss/train': 2.307054281234741}
-03/04/2022 09:47:16 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/04/2022 09:47:19 - INFO - codeparrot_training - Step 17304: {'lr': 0.00048692404165016256, 'samples': 8860160, 'steps': 17304, 'loss/train': 1.6755462884902954}
-03/04/2022 09:47:22 - INFO - codeparrot_training - Step 17305: {'lr': 0.0004869223478225178, 'samples': 8860672, 'steps': 17305, 'loss/train': 1.9983936548233032}
-03/04/2022 09:47:25 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/04/2022 09:47:28 - INFO - codeparrot_training - Step 17306: {'lr': 0.00048692065388811944, 'samples': 8861184, 'steps': 17306, 'loss/train': 1.57350492477417}
-03/04/2022 09:47:31 - INFO - codeparrot_training - Step 17307: {'lr': 0.0004869189598469683, 'samples': 8861696, 'steps': 17307, 'loss/train': 1.6303462982177734}
-03/04/2022 09:47:33 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/04/2022 09:47:36 - INFO - codeparrot_training - Step 17308: {'lr': 0.00048691726569906514, 'samples': 8862208, 'steps': 17308, 'loss/train': 2.31445050239563}
-03/04/2022 09:47:39 - INFO - codeparrot_training - Step 17309: {'lr': 0.0004869155714444107, 'samples': 8862720, 'steps': 17309, 'loss/train': 2.349963665008545}
-03/04/2022 09:47:41 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/04/2022 09:47:44 - INFO - codeparrot_training - Step 17310: {'lr': 0.00048691387708300584, 'samples': 8863232, 'steps': 17310, 'loss/train': 2.0869531631469727}
-03/04/2022 09:47:48 - INFO - codeparrot_training - Step 17311: {'lr': 0.00048691218261485113, 'samples': 8863744, 'steps': 17311, 'loss/train': 1.0911774635314941}
-03/04/2022 09:47:50 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/04/2022 09:47:53 - INFO - codeparrot_training - Step 17312: {'lr': 0.00048691048803994755, 'samples': 8864256, 'steps': 17312, 'loss/train': 2.1496052742004395}
-03/04/2022 09:47:56 - INFO - codeparrot_training - Step 17313: {'lr': 0.00048690879335829565, 'samples': 8864768, 'steps': 17313, 'loss/train': 2.471639394760132}
-03/04/2022 09:47:58 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/04/2022 09:48:01 - INFO - codeparrot_training - Step 17314: {'lr': 0.00048690709856989635, 'samples': 8865280, 'steps': 17314, 'loss/train': 2.02889084815979}
-03/04/2022 09:48:05 - INFO - codeparrot_training - Step 17315: {'lr': 0.00048690540367475046, 'samples': 8865792, 'steps': 17315, 'loss/train': 2.2712082862854004}
-03/04/2022 09:48:06 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 09:48:10 - INFO - codeparrot_training - Step 17316: {'lr': 0.00048690370867285847, 'samples': 8866304, 'steps': 17316, 'loss/train': 2.235522747039795}
-03/04/2022 09:48:13 - INFO - codeparrot_training - Step 17317: {'lr': 0.00048690201356422146, 'samples': 8866816, 'steps': 17317, 'loss/train': 1.9494624137878418}
-03/04/2022 09:48:15 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/04/2022 09:48:19 - INFO - codeparrot_training - Step 17318: {'lr': 0.00048690031834884004, 'samples': 8867328, 'steps': 17318, 'loss/train': 1.9272725582122803}
-03/04/2022 09:48:22 - INFO - codeparrot_training - Step 17319: {'lr': 0.00048689862302671495, 'samples': 8867840, 'steps': 17319, 'loss/train': 1.976380705833435}
-03/04/2022 09:48:25 - INFO - codeparrot_training - Step 17320: {'lr': 0.000486896927597847, 'samples': 8868352, 'steps': 17320, 'loss/train': 4.037226676940918}
-03/04/2022 09:48:25 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/04/2022 09:48:30 - INFO - codeparrot_training - Step 17321: {'lr': 0.00048689523206223693, 'samples': 8868864, 'steps': 17321, 'loss/train': 2.167853832244873}
-03/04/2022 09:48:33 - INFO - codeparrot_training - Step 17322: {'lr': 0.00048689353641988563, 'samples': 8869376, 'steps': 17322, 'loss/train': 2.148064374923706}
-03/04/2022 09:48:34 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/04/2022 09:48:39 - INFO - codeparrot_training - Step 17323: {'lr': 0.0004868918406707937, 'samples': 8869888, 'steps': 17323, 'loss/train': 1.8597944974899292}
-03/04/2022 09:48:42 - INFO - codeparrot_training - Step 17324: {'lr': 0.00048689014481496197, 'samples': 8870400, 'steps': 17324, 'loss/train': 2.038318157196045}
-03/04/2022 09:48:43 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/04/2022 09:48:47 - INFO - codeparrot_training - Step 17325: {'lr': 0.0004868884488523911, 'samples': 8870912, 'steps': 17325, 'loss/train': 1.7909826040267944}
-03/04/2022 09:48:51 - INFO - codeparrot_training - Step 17326: {'lr': 0.0004868867527830821, 'samples': 8871424, 'steps': 17326, 'loss/train': 2.2037529945373535}
-03/04/2022 09:48:51 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/04/2022 09:48:56 - INFO - codeparrot_training - Step 17327: {'lr': 0.0004868850566070355, 'samples': 8871936, 'steps': 17327, 'loss/train': 1.774157166481018}
-03/04/2022 09:48:59 - INFO - codeparrot_training - Step 17328: {'lr': 0.00048688336032425217, 'samples': 8872448, 'steps': 17328, 'loss/train': 1.6554423570632935}
-03/04/2022 09:49:01 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/04/2022 09:49:05 - INFO - codeparrot_training - Step 17329: {'lr': 0.0004868816639347328, 'samples': 8872960, 'steps': 17329, 'loss/train': 1.4885557889938354}
-03/04/2022 09:49:08 - INFO - codeparrot_training - Step 17330: {'lr': 0.0004868799674384783, 'samples': 8873472, 'steps': 17330, 'loss/train': 1.5337415933609009}
-03/04/2022 09:49:10 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/04/2022 09:49:13 - INFO - codeparrot_training - Step 17331: {'lr': 0.0004868782708354893, 'samples': 8873984, 'steps': 17331, 'loss/train': 2.437392473220825}
-03/04/2022 09:49:16 - INFO - codeparrot_training - Step 17332: {'lr': 0.0004868765741257666, 'samples': 8874496, 'steps': 17332, 'loss/train': 2.2315688133239746}
-03/04/2022 09:49:18 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 09:49:21 - INFO - codeparrot_training - Step 17333: {'lr': 0.00048687487730931096, 'samples': 8875008, 'steps': 17333, 'loss/train': 2.9484143257141113}
-03/04/2022 09:49:25 - INFO - codeparrot_training - Step 17334: {'lr': 0.00048687318038612317, 'samples': 8875520, 'steps': 17334, 'loss/train': 2.6707797050476074}
-03/04/2022 09:49:27 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/04/2022 09:49:30 - INFO - codeparrot_training - Step 17335: {'lr': 0.000486871483356204, 'samples': 8876032, 'steps': 17335, 'loss/train': 1.4475077390670776}
-03/04/2022 09:49:33 - INFO - codeparrot_training - Step 17336: {'lr': 0.00048686978621955416, 'samples': 8876544, 'steps': 17336, 'loss/train': 2.0893421173095703}
-03/04/2022 09:49:35 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/04/2022 09:49:38 - INFO - codeparrot_training - Step 17337: {'lr': 0.00048686808897617447, 'samples': 8877056, 'steps': 17337, 'loss/train': 2.1351988315582275}
-03/04/2022 09:49:41 - INFO - codeparrot_training - Step 17338: {'lr': 0.00048686639162606564, 'samples': 8877568, 'steps': 17338, 'loss/train': 1.9153072834014893}
-03/04/2022 09:49:43 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/04/2022 09:49:47 - INFO - codeparrot_training - Step 17339: {'lr': 0.0004868646941692285, 'samples': 8878080, 'steps': 17339, 'loss/train': 2.2189078330993652}
-03/04/2022 09:49:50 - INFO - codeparrot_training - Step 17340: {'lr': 0.0004868629966056638, 'samples': 8878592, 'steps': 17340, 'loss/train': 1.9150062799453735}
-03/04/2022 09:49:52 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 09:49:55 - INFO - codeparrot_training - Step 17341: {'lr': 0.0004868612989353722, 'samples': 8879104, 'steps': 17341, 'loss/train': 1.5314157009124756}
-03/04/2022 09:49:58 - INFO - codeparrot_training - Step 17342: {'lr': 0.0004868596011583547, 'samples': 8879616, 'steps': 17342, 'loss/train': 2.3834354877471924}
-03/04/2022 09:50:00 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/04/2022 09:50:04 - INFO - codeparrot_training - Step 17343: {'lr': 0.00048685790327461184, 'samples': 8880128, 'steps': 17343, 'loss/train': 2.534484386444092}
-03/04/2022 09:50:07 - INFO - codeparrot_training - Step 17344: {'lr': 0.0004868562052841444, 'samples': 8880640, 'steps': 17344, 'loss/train': 1.5348937511444092}
-03/04/2022 09:50:08 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 09:50:12 - INFO - codeparrot_training - Step 17345: {'lr': 0.00048685450718695335, 'samples': 8881152, 'steps': 17345, 'loss/train': 2.5259578227996826}
-03/04/2022 09:50:15 - INFO - codeparrot_training - Step 17346: {'lr': 0.00048685280898303916, 'samples': 8881664, 'steps': 17346, 'loss/train': 1.5742652416229248}
-03/04/2022 09:50:17 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 09:50:20 - INFO - codeparrot_training - Step 17347: {'lr': 0.00048685111067240283, 'samples': 8882176, 'steps': 17347, 'loss/train': 1.5508952140808105}
-03/04/2022 09:50:24 - INFO - codeparrot_training - Step 17348: {'lr': 0.00048684941225504507, 'samples': 8882688, 'steps': 17348, 'loss/train': 2.2930684089660645}
-03/04/2022 09:50:25 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/04/2022 09:50:29 - INFO - codeparrot_training - Step 17349: {'lr': 0.0004868477137309666, 'samples': 8883200, 'steps': 17349, 'loss/train': 1.9486385583877563}
-03/04/2022 09:50:32 - INFO - codeparrot_training - Step 17350: {'lr': 0.00048684601510016817, 'samples': 8883712, 'steps': 17350, 'loss/train': 1.42340886592865}
-03/04/2022 09:50:33 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 09:50:37 - INFO - codeparrot_training - Step 17351: {'lr': 0.00048684431636265065, 'samples': 8884224, 'steps': 17351, 'loss/train': 3.863535165786743}
-03/04/2022 09:50:41 - INFO - codeparrot_training - Step 17352: {'lr': 0.00048684261751841463, 'samples': 8884736, 'steps': 17352, 'loss/train': 2.362060308456421}
-03/04/2022 09:50:42 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/04/2022 09:50:46 - INFO - codeparrot_training - Step 17353: {'lr': 0.000486840918567461, 'samples': 8885248, 'steps': 17353, 'loss/train': 2.6487672328948975}
-03/04/2022 09:50:49 - INFO - codeparrot_training - Step 17354: {'lr': 0.0004868392195097906, 'samples': 8885760, 'steps': 17354, 'loss/train': 2.5347976684570312}
-03/04/2022 09:50:51 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/04/2022 09:50:54 - INFO - codeparrot_training - Step 17355: {'lr': 0.0004868375203454041, 'samples': 8886272, 'steps': 17355, 'loss/train': 1.7541838884353638}
-03/04/2022 09:50:58 - INFO - codeparrot_training - Step 17356: {'lr': 0.00048683582107430227, 'samples': 8886784, 'steps': 17356, 'loss/train': 2.014817714691162}
-03/04/2022 09:50:59 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 09:51:03 - INFO - codeparrot_training - Step 17357: {'lr': 0.0004868341216964858, 'samples': 8887296, 'steps': 17357, 'loss/train': 1.5625805854797363}
-03/04/2022 09:51:06 - INFO - codeparrot_training - Step 17358: {'lr': 0.00048683242221195553, 'samples': 8887808, 'steps': 17358, 'loss/train': 1.4986333847045898}
-03/04/2022 09:51:08 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 09:51:11 - INFO - codeparrot_training - Step 17359: {'lr': 0.00048683072262071224, 'samples': 8888320, 'steps': 17359, 'loss/train': 4.085904598236084}
-03/04/2022 09:51:14 - INFO - codeparrot_training - Step 17360: {'lr': 0.00048682902292275667, 'samples': 8888832, 'steps': 17360, 'loss/train': 2.0843968391418457}
-03/04/2022 09:51:16 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/04/2022 09:51:20 - INFO - codeparrot_training - Step 17361: {'lr': 0.00048682732311808964, 'samples': 8889344, 'steps': 17361, 'loss/train': 1.0921473503112793}
-03/04/2022 09:51:23 - INFO - codeparrot_training - Step 17362: {'lr': 0.00048682562320671185, 'samples': 8889856, 'steps': 17362, 'loss/train': 1.8331644535064697}
-03/04/2022 09:51:25 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/04/2022 09:51:28 - INFO - codeparrot_training - Step 17363: {'lr': 0.00048682392318862407, 'samples': 8890368, 'steps': 17363, 'loss/train': 2.178312301635742}
-03/04/2022 09:51:31 - INFO - codeparrot_training - Step 17364: {'lr': 0.00048682222306382705, 'samples': 8890880, 'steps': 17364, 'loss/train': 1.2663837671279907}
-03/04/2022 09:51:33 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 09:51:37 - INFO - codeparrot_training - Step 17365: {'lr': 0.0004868205228323217, 'samples': 8891392, 'steps': 17365, 'loss/train': 1.4743783473968506}
-03/04/2022 09:51:40 - INFO - codeparrot_training - Step 17366: {'lr': 0.0004868188224941086, 'samples': 8891904, 'steps': 17366, 'loss/train': 1.944361925125122}
-03/04/2022 09:51:42 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/04/2022 09:51:45 - INFO - codeparrot_training - Step 17367: {'lr': 0.0004868171220491886, 'samples': 8892416, 'steps': 17367, 'loss/train': 1.1691508293151855}
-03/04/2022 09:51:48 - INFO - codeparrot_training - Step 17368: {'lr': 0.00048681542149756253, 'samples': 8892928, 'steps': 17368, 'loss/train': 4.596549034118652}
-03/04/2022 09:51:50 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/04/2022 09:51:54 - INFO - codeparrot_training - Step 17369: {'lr': 0.00048681372083923103, 'samples': 8893440, 'steps': 17369, 'loss/train': 2.343165159225464}
-03/04/2022 09:51:57 - INFO - codeparrot_training - Step 17370: {'lr': 0.0004868120200741949, 'samples': 8893952, 'steps': 17370, 'loss/train': 1.1830004453659058}
-03/04/2022 09:51:59 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/04/2022 09:52:02 - INFO - codeparrot_training - Step 17371: {'lr': 0.0004868103192024549, 'samples': 8894464, 'steps': 17371, 'loss/train': 1.66206693649292}
-03/04/2022 09:52:06 - INFO - codeparrot_training - Step 17372: {'lr': 0.0004868086182240119, 'samples': 8894976, 'steps': 17372, 'loss/train': 3.5952112674713135}
-03/04/2022 09:52:08 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 09:52:11 - INFO - codeparrot_training - Step 17373: {'lr': 0.00048680691713886653, 'samples': 8895488, 'steps': 17373, 'loss/train': 2.071876049041748}
-03/04/2022 09:52:14 - INFO - codeparrot_training - Step 17374: {'lr': 0.00048680521594701964, 'samples': 8896000, 'steps': 17374, 'loss/train': 1.9146305322647095}
-03/04/2022 09:52:17 - INFO - codeparrot_training - Step 17375: {'lr': 0.00048680351464847207, 'samples': 8896512, 'steps': 17375, 'loss/train': 2.272498607635498}
-03/04/2022 09:52:18 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 09:52:22 - INFO - codeparrot_training - Step 17376: {'lr': 0.00048680181324322437, 'samples': 8897024, 'steps': 17376, 'loss/train': 1.9188755750656128}
-03/04/2022 09:52:26 - INFO - codeparrot_training - Step 17377: {'lr': 0.00048680011173127746, 'samples': 8897536, 'steps': 17377, 'loss/train': 1.5273181200027466}
-03/04/2022 09:52:26 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 09:52:31 - INFO - codeparrot_training - Step 17378: {'lr': 0.00048679841011263204, 'samples': 8898048, 'steps': 17378, 'loss/train': 2.3655288219451904}
-03/04/2022 09:52:34 - INFO - codeparrot_training - Step 17379: {'lr': 0.00048679670838728894, 'samples': 8898560, 'steps': 17379, 'loss/train': 2.498816728591919}
-03/04/2022 09:52:34 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/04/2022 09:52:39 - INFO - codeparrot_training - Step 17380: {'lr': 0.0004867950065552489, 'samples': 8899072, 'steps': 17380, 'loss/train': 2.1316235065460205}
-03/04/2022 09:52:43 - INFO - codeparrot_training - Step 17381: {'lr': 0.00048679330461651275, 'samples': 8899584, 'steps': 17381, 'loss/train': 2.5681545734405518}
-03/04/2022 09:52:43 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 09:52:48 - INFO - codeparrot_training - Step 17382: {'lr': 0.00048679160257108107, 'samples': 8900096, 'steps': 17382, 'loss/train': 1.466504693031311}
-03/04/2022 09:52:51 - INFO - codeparrot_training - Step 17383: {'lr': 0.00048678990041895484, 'samples': 8900608, 'steps': 17383, 'loss/train': 1.8894259929656982}
-03/04/2022 09:52:51 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/04/2022 09:52:56 - INFO - codeparrot_training - Step 17384: {'lr': 0.00048678819816013467, 'samples': 8901120, 'steps': 17384, 'loss/train': 1.6218822002410889}
-03/04/2022 09:52:59 - INFO - codeparrot_training - Step 17385: {'lr': 0.0004867864957946214, 'samples': 8901632, 'steps': 17385, 'loss/train': 1.5856868028640747}
-03/04/2022 09:52:59 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/04/2022 09:53:05 - INFO - codeparrot_training - Step 17386: {'lr': 0.0004867847933224158, 'samples': 8902144, 'steps': 17386, 'loss/train': 1.6890685558319092}
-03/04/2022 09:53:08 - INFO - codeparrot_training - Step 17387: {'lr': 0.0004867830907435187, 'samples': 8902656, 'steps': 17387, 'loss/train': 1.729661226272583}
-03/04/2022 09:53:08 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/04/2022 09:53:13 - INFO - codeparrot_training - Step 17388: {'lr': 0.0004867813880579307, 'samples': 8903168, 'steps': 17388, 'loss/train': 0.9801804423332214}
-03/04/2022 09:53:17 - INFO - codeparrot_training - Step 17389: {'lr': 0.0004867796852656527, 'samples': 8903680, 'steps': 17389, 'loss/train': 1.689299464225769}
-03/04/2022 09:53:17 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 09:53:22 - INFO - codeparrot_training - Step 17390: {'lr': 0.00048677798236668537, 'samples': 8904192, 'steps': 17390, 'loss/train': 1.9638237953186035}
-03/04/2022 09:53:25 - INFO - codeparrot_training - Step 17391: {'lr': 0.00048677627936102966, 'samples': 8904704, 'steps': 17391, 'loss/train': 0.7934051156044006}
-03/04/2022 09:53:26 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 09:53:30 - INFO - codeparrot_training - Step 17392: {'lr': 0.0004867745762486861, 'samples': 8905216, 'steps': 17392, 'loss/train': 2.198030471801758}
-03/04/2022 09:53:33 - INFO - codeparrot_training - Step 17393: {'lr': 0.0004867728730296556, 'samples': 8905728, 'steps': 17393, 'loss/train': 2.381946086883545}
-03/04/2022 09:53:34 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/04/2022 09:53:39 - INFO - codeparrot_training - Step 17394: {'lr': 0.0004867711697039389, 'samples': 8906240, 'steps': 17394, 'loss/train': 1.8666225671768188}
-03/04/2022 09:53:42 - INFO - codeparrot_training - Step 17395: {'lr': 0.00048676946627153675, 'samples': 8906752, 'steps': 17395, 'loss/train': 1.9783819913864136}
-03/04/2022 09:53:43 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/04/2022 09:53:47 - INFO - codeparrot_training - Step 17396: {'lr': 0.00048676776273244994, 'samples': 8907264, 'steps': 17396, 'loss/train': 1.210360050201416}
-03/04/2022 09:53:51 - INFO - codeparrot_training - Step 17397: {'lr': 0.00048676605908667926, 'samples': 8907776, 'steps': 17397, 'loss/train': 2.0759546756744385}
-03/04/2022 09:53:52 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/04/2022 09:53:56 - INFO - codeparrot_training - Step 17398: {'lr': 0.00048676435533422536, 'samples': 8908288, 'steps': 17398, 'loss/train': 1.6193052530288696}
-03/04/2022 09:53:59 - INFO - codeparrot_training - Step 17399: {'lr': 0.00048676265147508917, 'samples': 8908800, 'steps': 17399, 'loss/train': 0.7337481379508972}
-03/04/2022 09:54:00 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/04/2022 09:54:04 - INFO - codeparrot_training - Step 17400: {'lr': 0.00048676094750927144, 'samples': 8909312, 'steps': 17400, 'loss/train': 0.6842808127403259}
-03/04/2022 09:54:07 - INFO - codeparrot_training - Step 17401: {'lr': 0.0004867592434367728, 'samples': 8909824, 'steps': 17401, 'loss/train': 2.0560038089752197}
-03/04/2022 09:54:08 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/04/2022 09:54:13 - INFO - codeparrot_training - Step 17402: {'lr': 0.0004867575392575941, 'samples': 8910336, 'steps': 17402, 'loss/train': 2.546003818511963}
-03/04/2022 09:54:16 - INFO - codeparrot_training - Step 17403: {'lr': 0.0004867558349717361, 'samples': 8910848, 'steps': 17403, 'loss/train': 1.4340087175369263}
-03/04/2022 09:54:17 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/04/2022 09:54:21 - INFO - codeparrot_training - Step 17404: {'lr': 0.0004867541305791996, 'samples': 8911360, 'steps': 17404, 'loss/train': 2.2930328845977783}
-03/04/2022 09:54:24 - INFO - codeparrot_training - Step 17405: {'lr': 0.00048675242607998533, 'samples': 8911872, 'steps': 17405, 'loss/train': 1.115888237953186}
-03/04/2022 09:54:25 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 09:54:29 - INFO - codeparrot_training - Step 17406: {'lr': 0.00048675072147409405, 'samples': 8912384, 'steps': 17406, 'loss/train': 1.584164023399353}
-03/04/2022 09:54:33 - INFO - codeparrot_training - Step 17407: {'lr': 0.0004867490167615266, 'samples': 8912896, 'steps': 17407, 'loss/train': 1.4932974576950073}
-03/04/2022 09:54:33 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/04/2022 09:54:38 - INFO - codeparrot_training - Step 17408: {'lr': 0.0004867473119422837, 'samples': 8913408, 'steps': 17408, 'loss/train': 2.0521583557128906}
-03/04/2022 09:54:41 - INFO - codeparrot_training - Step 17409: {'lr': 0.00048674560701636606, 'samples': 8913920, 'steps': 17409, 'loss/train': 2.3083689212799072}
-03/04/2022 09:54:42 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/04/2022 09:54:46 - INFO - codeparrot_training - Step 17410: {'lr': 0.0004867439019837745, 'samples': 8914432, 'steps': 17410, 'loss/train': 1.5680906772613525}
-03/04/2022 09:54:50 - INFO - codeparrot_training - Step 17411: {'lr': 0.00048674219684450985, 'samples': 8914944, 'steps': 17411, 'loss/train': 2.1664350032806396}
-03/04/2022 09:54:50 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/04/2022 09:54:55 - INFO - codeparrot_training - Step 17412: {'lr': 0.00048674049159857277, 'samples': 8915456, 'steps': 17412, 'loss/train': 0.27272841334342957}
-03/04/2022 09:54:58 - INFO - codeparrot_training - Step 17413: {'lr': 0.0004867387862459641, 'samples': 8915968, 'steps': 17413, 'loss/train': 0.3583604097366333}
-03/04/2022 09:55:00 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/04/2022 09:55:04 - INFO - codeparrot_training - Step 17414: {'lr': 0.0004867370807866845, 'samples': 8916480, 'steps': 17414, 'loss/train': 2.5279293060302734}
-03/04/2022 09:55:07 - INFO - codeparrot_training - Step 17415: {'lr': 0.000486735375220735, 'samples': 8916992, 'steps': 17415, 'loss/train': 1.5873537063598633}
-03/04/2022 09:55:08 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/04/2022 09:55:12 - INFO - codeparrot_training - Step 17416: {'lr': 0.00048673366954811605, 'samples': 8917504, 'steps': 17416, 'loss/train': 1.963753581047058}
-03/04/2022 09:55:15 - INFO - codeparrot_training - Step 17417: {'lr': 0.0004867319637688286, 'samples': 8918016, 'steps': 17417, 'loss/train': 2.0981223583221436}
-03/04/2022 09:55:16 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/04/2022 09:55:20 - INFO - codeparrot_training - Step 17418: {'lr': 0.0004867302578828734, 'samples': 8918528, 'steps': 17418, 'loss/train': 1.9392707347869873}
-03/04/2022 09:55:23 - INFO - codeparrot_training - Step 17419: {'lr': 0.0004867285518902512, 'samples': 8919040, 'steps': 17419, 'loss/train': 1.7900147438049316}
-03/04/2022 09:55:25 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/04/2022 09:55:29 - INFO - codeparrot_training - Step 17420: {'lr': 0.0004867268457909627, 'samples': 8919552, 'steps': 17420, 'loss/train': 2.244166612625122}
-03/04/2022 09:55:32 - INFO - codeparrot_training - Step 17421: {'lr': 0.0004867251395850088, 'samples': 8920064, 'steps': 17421, 'loss/train': 2.1061275005340576}
-03/04/2022 09:55:34 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/04/2022 09:55:37 - INFO - codeparrot_training - Step 17422: {'lr': 0.00048672343327239024, 'samples': 8920576, 'steps': 17422, 'loss/train': 2.272671699523926}
-03/04/2022 09:55:40 - INFO - codeparrot_training - Step 17423: {'lr': 0.00048672172685310767, 'samples': 8921088, 'steps': 17423, 'loss/train': 2.0651159286499023}
-03/04/2022 09:55:42 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 09:55:46 - INFO - codeparrot_training - Step 17424: {'lr': 0.000486720020327162, 'samples': 8921600, 'steps': 17424, 'loss/train': 2.221189260482788}
-03/04/2022 09:55:49 - INFO - codeparrot_training - Step 17425: {'lr': 0.00048671831369455386, 'samples': 8922112, 'steps': 17425, 'loss/train': 2.040565013885498}
-03/04/2022 09:55:50 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 09:55:54 - INFO - codeparrot_training - Step 17426: {'lr': 0.0004867166069552842, 'samples': 8922624, 'steps': 17426, 'loss/train': 2.3854594230651855}
-03/04/2022 09:55:57 - INFO - codeparrot_training - Step 17427: {'lr': 0.00048671490010935366, 'samples': 8923136, 'steps': 17427, 'loss/train': 1.0068728923797607}
-03/04/2022 09:55:59 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 09:56:03 - INFO - codeparrot_training - Step 17428: {'lr': 0.00048671319315676305, 'samples': 8923648, 'steps': 17428, 'loss/train': 0.772129237651825}
-03/04/2022 09:56:06 - INFO - codeparrot_training - Step 17429: {'lr': 0.00048671148609751307, 'samples': 8924160, 'steps': 17429, 'loss/train': 1.6925119161605835}
-03/04/2022 09:56:07 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 09:56:11 - INFO - codeparrot_training - Step 17430: {'lr': 0.0004867097789316046, 'samples': 8924672, 'steps': 17430, 'loss/train': 0.9923723936080933}
-03/04/2022 09:56:14 - INFO - codeparrot_training - Step 17431: {'lr': 0.0004867080716590384, 'samples': 8925184, 'steps': 17431, 'loss/train': 2.7427384853363037}
-03/04/2022 09:56:16 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/04/2022 09:56:20 - INFO - codeparrot_training - Step 17432: {'lr': 0.0004867063642798151, 'samples': 8925696, 'steps': 17432, 'loss/train': 1.735987663269043}
-03/04/2022 09:56:23 - INFO - codeparrot_training - Step 17433: {'lr': 0.0004867046567939356, 'samples': 8926208, 'steps': 17433, 'loss/train': 1.1434357166290283}
-03/04/2022 09:56:24 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 09:56:28 - INFO - codeparrot_training - Step 17434: {'lr': 0.00048670294920140063, 'samples': 8926720, 'steps': 17434, 'loss/train': 2.0311763286590576}
-03/04/2022 09:56:31 - INFO - codeparrot_training - Step 17435: {'lr': 0.00048670124150221094, 'samples': 8927232, 'steps': 17435, 'loss/train': 1.5631150007247925}
-03/04/2022 09:56:33 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/04/2022 09:56:36 - INFO - codeparrot_training - Step 17436: {'lr': 0.00048669953369636737, 'samples': 8927744, 'steps': 17436, 'loss/train': 3.770456075668335}
-03/04/2022 09:56:39 - INFO - codeparrot_training - Step 17437: {'lr': 0.00048669782578387067, 'samples': 8928256, 'steps': 17437, 'loss/train': 1.7463977336883545}
-03/04/2022 09:56:41 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 09:56:45 - INFO - codeparrot_training - Step 17438: {'lr': 0.00048669611776472153, 'samples': 8928768, 'steps': 17438, 'loss/train': 1.8469116687774658}
-03/04/2022 09:56:48 - INFO - codeparrot_training - Step 17439: {'lr': 0.00048669440963892074, 'samples': 8929280, 'steps': 17439, 'loss/train': 0.9974958300590515}
-03/04/2022 09:56:50 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/04/2022 09:56:53 - INFO - codeparrot_training - Step 17440: {'lr': 0.00048669270140646914, 'samples': 8929792, 'steps': 17440, 'loss/train': 1.4441546201705933}
-03/04/2022 09:56:56 - INFO - codeparrot_training - Step 17441: {'lr': 0.0004866909930673675, 'samples': 8930304, 'steps': 17441, 'loss/train': 4.304600238800049}
-03/04/2022 09:56:58 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 09:57:02 - INFO - codeparrot_training - Step 17442: {'lr': 0.00048668928462161653, 'samples': 8930816, 'steps': 17442, 'loss/train': 1.6706762313842773}
-03/04/2022 09:57:05 - INFO - codeparrot_training - Step 17443: {'lr': 0.000486687576069217, 'samples': 8931328, 'steps': 17443, 'loss/train': 2.1230764389038086}
-03/04/2022 09:57:07 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/04/2022 09:57:10 - INFO - codeparrot_training - Step 17444: {'lr': 0.00048668586741016967, 'samples': 8931840, 'steps': 17444, 'loss/train': 2.54822039604187}
-03/04/2022 09:57:13 - INFO - codeparrot_training - Step 17445: {'lr': 0.0004866841586444754, 'samples': 8932352, 'steps': 17445, 'loss/train': 1.943244457244873}
-03/04/2022 09:57:15 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/04/2022 09:57:18 - INFO - codeparrot_training - Step 17446: {'lr': 0.0004866824497721349, 'samples': 8932864, 'steps': 17446, 'loss/train': 1.5995303392410278}
-03/04/2022 09:57:22 - INFO - codeparrot_training - Step 17447: {'lr': 0.0004866807407931489, 'samples': 8933376, 'steps': 17447, 'loss/train': 1.1105982065200806}
-03/04/2022 09:57:24 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/04/2022 09:57:27 - INFO - codeparrot_training - Step 17448: {'lr': 0.0004866790317075182, 'samples': 8933888, 'steps': 17448, 'loss/train': 2.2593681812286377}
-03/04/2022 09:57:30 - INFO - codeparrot_training - Step 17449: {'lr': 0.00048667732251524365, 'samples': 8934400, 'steps': 17449, 'loss/train': 1.4902570247650146}
-03/04/2022 09:57:32 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/04/2022 09:57:35 - INFO - codeparrot_training - Step 17450: {'lr': 0.0004866756132163259, 'samples': 8934912, 'steps': 17450, 'loss/train': 1.6365641355514526}
-03/04/2022 09:57:39 - INFO - codeparrot_training - Step 17451: {'lr': 0.0004866739038107658, 'samples': 8935424, 'steps': 17451, 'loss/train': 1.4022942781448364}
-03/04/2022 09:57:41 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/04/2022 09:57:44 - INFO - codeparrot_training - Step 17452: {'lr': 0.000486672194298564, 'samples': 8935936, 'steps': 17452, 'loss/train': 1.8087025880813599}
-03/04/2022 09:57:47 - INFO - codeparrot_training - Step 17453: {'lr': 0.00048667048467972146, 'samples': 8936448, 'steps': 17453, 'loss/train': 1.5490342378616333}
-03/04/2022 09:57:49 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 09:57:52 - INFO - codeparrot_training - Step 17454: {'lr': 0.00048666877495423885, 'samples': 8936960, 'steps': 17454, 'loss/train': 1.5633742809295654}
-03/04/2022 09:57:56 - INFO - codeparrot_training - Step 17455: {'lr': 0.0004866670651221169, 'samples': 8937472, 'steps': 17455, 'loss/train': 1.9414530992507935}
-03/04/2022 09:57:58 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/04/2022 09:58:01 - INFO - codeparrot_training - Step 17456: {'lr': 0.0004866653551833564, 'samples': 8937984, 'steps': 17456, 'loss/train': 1.933963656425476}
-03/04/2022 09:58:04 - INFO - codeparrot_training - Step 17457: {'lr': 0.00048666364513795816, 'samples': 8938496, 'steps': 17457, 'loss/train': 2.837127447128296}
-03/04/2022 09:58:06 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/04/2022 09:58:09 - INFO - codeparrot_training - Step 17458: {'lr': 0.00048666193498592304, 'samples': 8939008, 'steps': 17458, 'loss/train': 2.07375431060791}
-03/04/2022 09:58:13 - INFO - codeparrot_training - Step 17459: {'lr': 0.0004866602247272516, 'samples': 8939520, 'steps': 17459, 'loss/train': 1.8138986825942993}
-03/04/2022 09:58:15 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/04/2022 09:58:18 - INFO - codeparrot_training - Step 17460: {'lr': 0.0004866585143619447, 'samples': 8940032, 'steps': 17460, 'loss/train': 2.1539480686187744}
-03/04/2022 09:58:21 - INFO - codeparrot_training - Step 17461: {'lr': 0.00048665680389000315, 'samples': 8940544, 'steps': 17461, 'loss/train': 2.3927083015441895}
-03/04/2022 09:58:23 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 09:58:26 - INFO - codeparrot_training - Step 17462: {'lr': 0.0004866550933114277, 'samples': 8941056, 'steps': 17462, 'loss/train': 1.6544108390808105}
-03/04/2022 09:58:29 - INFO - codeparrot_training - Step 17463: {'lr': 0.00048665338262621915, 'samples': 8941568, 'steps': 17463, 'loss/train': 1.9657609462738037}
-03/04/2022 09:58:31 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 09:58:35 - INFO - codeparrot_training - Step 17464: {'lr': 0.00048665167183437817, 'samples': 8942080, 'steps': 17464, 'loss/train': 1.7576611042022705}
-03/04/2022 09:58:38 - INFO - codeparrot_training - Step 17465: {'lr': 0.00048664996093590563, 'samples': 8942592, 'steps': 17465, 'loss/train': 1.4785993099212646}
-03/04/2022 09:58:40 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 09:58:43 - INFO - codeparrot_training - Step 17466: {'lr': 0.0004866482499308023, 'samples': 8943104, 'steps': 17466, 'loss/train': 2.5017590522766113}
-03/04/2022 09:58:46 - INFO - codeparrot_training - Step 17467: {'lr': 0.0004866465388190689, 'samples': 8943616, 'steps': 17467, 'loss/train': 2.458921194076538}
-03/04/2022 09:58:48 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 09:58:51 - INFO - codeparrot_training - Step 17468: {'lr': 0.0004866448276007062, 'samples': 8944128, 'steps': 17468, 'loss/train': 1.8777260780334473}
-03/04/2022 09:58:55 - INFO - codeparrot_training - Step 17469: {'lr': 0.000486643116275715, 'samples': 8944640, 'steps': 17469, 'loss/train': 0.9366203546524048}
-03/04/2022 09:58:57 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 09:59:00 - INFO - codeparrot_training - Step 17470: {'lr': 0.00048664140484409613, 'samples': 8945152, 'steps': 17470, 'loss/train': 2.4246394634246826}
-03/04/2022 09:59:03 - INFO - codeparrot_training - Step 17471: {'lr': 0.0004866396933058502, 'samples': 8945664, 'steps': 17471, 'loss/train': 1.7949024438858032}
-03/04/2022 09:59:05 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 09:59:08 - INFO - codeparrot_training - Step 17472: {'lr': 0.00048663798166097814, 'samples': 8946176, 'steps': 17472, 'loss/train': 2.146641254425049}
-03/04/2022 09:59:12 - INFO - codeparrot_training - Step 17473: {'lr': 0.0004866362699094806, 'samples': 8946688, 'steps': 17473, 'loss/train': 1.968339443206787}
-03/04/2022 09:59:13 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/04/2022 09:59:17 - INFO - codeparrot_training - Step 17474: {'lr': 0.0004866345580513585, 'samples': 8947200, 'steps': 17474, 'loss/train': 1.3272043466567993}
-03/04/2022 09:59:20 - INFO - codeparrot_training - Step 17475: {'lr': 0.0004866328460866124, 'samples': 8947712, 'steps': 17475, 'loss/train': 2.153667688369751}
-03/04/2022 09:59:22 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/04/2022 09:59:25 - INFO - codeparrot_training - Step 17476: {'lr': 0.0004866311340152433, 'samples': 8948224, 'steps': 17476, 'loss/train': 1.8605622053146362}
-03/04/2022 09:59:28 - INFO - codeparrot_training - Step 17477: {'lr': 0.0004866294218372518, 'samples': 8948736, 'steps': 17477, 'loss/train': 2.1031110286712646}
-03/04/2022 09:59:30 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/04/2022 09:59:34 - INFO - codeparrot_training - Step 17478: {'lr': 0.0004866277095526387, 'samples': 8949248, 'steps': 17478, 'loss/train': 2.0577657222747803}
-03/04/2022 09:59:37 - INFO - codeparrot_training - Step 17479: {'lr': 0.00048662599716140485, 'samples': 8949760, 'steps': 17479, 'loss/train': 1.7718837261199951}
-03/04/2022 09:59:40 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/04/2022 09:59:43 - INFO - codeparrot_training - Step 17480: {'lr': 0.00048662428466355104, 'samples': 8950272, 'steps': 17480, 'loss/train': 0.2787880003452301}
-03/04/2022 09:59:46 - INFO - codeparrot_training - Step 17481: {'lr': 0.0004866225720590779, 'samples': 8950784, 'steps': 17481, 'loss/train': 1.958360195159912}
-03/04/2022 09:59:49 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 09:59:51 - INFO - codeparrot_training - Step 17482: {'lr': 0.00048662085934798627, 'samples': 8951296, 'steps': 17482, 'loss/train': 2.183255195617676}
-03/04/2022 09:59:54 - INFO - codeparrot_training - Step 17483: {'lr': 0.00048661914653027694, 'samples': 8951808, 'steps': 17483, 'loss/train': 1.2469645738601685}
-03/04/2022 09:59:57 - INFO - codeparrot_training - Step 17484: {'lr': 0.0004866174336059507, 'samples': 8952320, 'steps': 17484, 'loss/train': 1.2980523109436035}
-03/04/2022 09:59:57 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/04/2022 10:00:03 - INFO - codeparrot_training - Step 17485: {'lr': 0.00048661572057500833, 'samples': 8952832, 'steps': 17485, 'loss/train': 1.6882472038269043}
-03/04/2022 10:00:05 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/04/2022 10:00:08 - INFO - codeparrot_training - Step 17486: {'lr': 0.00048661400743745057, 'samples': 8953344, 'steps': 17486, 'loss/train': 2.026535987854004}
-03/04/2022 10:00:11 - INFO - codeparrot_training - Step 17487: {'lr': 0.00048661229419327806, 'samples': 8953856, 'steps': 17487, 'loss/train': 1.7439520359039307}
-03/04/2022 10:00:14 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 10:00:16 - INFO - codeparrot_training - Step 17488: {'lr': 0.0004866105808424918, 'samples': 8954368, 'steps': 17488, 'loss/train': 1.232743740081787}
-03/04/2022 10:00:20 - INFO - codeparrot_training - Step 17489: {'lr': 0.0004866088673850925, 'samples': 8954880, 'steps': 17489, 'loss/train': 0.8887256383895874}
-03/04/2022 10:00:22 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 10:00:25 - INFO - codeparrot_training - Step 17490: {'lr': 0.0004866071538210808, 'samples': 8955392, 'steps': 17490, 'loss/train': 2.049025058746338}
-03/04/2022 10:00:28 - INFO - codeparrot_training - Step 17491: {'lr': 0.0004866054401504576, 'samples': 8955904, 'steps': 17491, 'loss/train': 2.1216042041778564}
-03/04/2022 10:00:30 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 10:00:33 - INFO - codeparrot_training - Step 17492: {'lr': 0.0004866037263732237, 'samples': 8956416, 'steps': 17492, 'loss/train': 1.8742773532867432}
-03/04/2022 10:00:36 - INFO - codeparrot_training - Step 17493: {'lr': 0.00048660201248937974, 'samples': 8956928, 'steps': 17493, 'loss/train': 2.2393858432769775}
-03/04/2022 10:00:39 - INFO - codeparrot_training - Skipping example with length 385 (seq_length=1024)
-03/04/2022 10:00:42 - INFO - codeparrot_training - Step 17494: {'lr': 0.0004866002984989266, 'samples': 8957440, 'steps': 17494, 'loss/train': 2.285616159439087}
-03/04/2022 10:00:45 - INFO - codeparrot_training - Step 17495: {'lr': 0.000486598584401865, 'samples': 8957952, 'steps': 17495, 'loss/train': 1.475893259048462}
-03/04/2022 10:00:47 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/04/2022 10:00:50 - INFO - codeparrot_training - Step 17496: {'lr': 0.0004865968701981958, 'samples': 8958464, 'steps': 17496, 'loss/train': 1.0781662464141846}
-03/04/2022 10:00:53 - INFO - codeparrot_training - Step 17497: {'lr': 0.0004865951558879196, 'samples': 8958976, 'steps': 17497, 'loss/train': 1.1213489770889282}
-03/04/2022 10:00:55 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 10:00:59 - INFO - codeparrot_training - Step 17498: {'lr': 0.00048659344147103725, 'samples': 8959488, 'steps': 17498, 'loss/train': 1.6617635488510132}
-03/04/2022 10:01:02 - INFO - codeparrot_training - Step 17499: {'lr': 0.0004865917269475496, 'samples': 8960000, 'steps': 17499, 'loss/train': 1.0772353410720825}
-03/04/2022 10:01:06 - INFO - codeparrot_training - Step 17500: {'lr': 0.00048659001231745734, 'samples': 8960512, 'steps': 17500, 'loss/train': 2.22719669342041}
-03/04/2022 10:01:07 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/04/2022 10:01:11 - INFO - codeparrot_training - Step 17501: {'lr': 0.0004865882975807614, 'samples': 8961024, 'steps': 17501, 'loss/train': 1.9549181461334229}
-03/04/2022 10:01:14 - INFO - codeparrot_training - Step 17502: {'lr': 0.00048658658273746224, 'samples': 8961536, 'steps': 17502, 'loss/train': 0.5291174650192261}
-03/04/2022 10:01:15 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 10:01:19 - INFO - codeparrot_training - Step 17503: {'lr': 0.00048658486778756097, 'samples': 8962048, 'steps': 17503, 'loss/train': 0.6541529297828674}
-03/04/2022 10:01:22 - INFO - codeparrot_training - Step 17504: {'lr': 0.0004865831527310581, 'samples': 8962560, 'steps': 17504, 'loss/train': 2.266359329223633}
-03/04/2022 10:01:24 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/04/2022 10:01:28 - INFO - codeparrot_training - Step 17505: {'lr': 0.00048658143756795456, 'samples': 8963072, 'steps': 17505, 'loss/train': 2.1067585945129395}
-03/04/2022 10:01:31 - INFO - codeparrot_training - Step 17506: {'lr': 0.0004865797222982511, 'samples': 8963584, 'steps': 17506, 'loss/train': 1.5077117681503296}
-03/04/2022 10:01:32 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/04/2022 10:01:36 - INFO - codeparrot_training - Step 17507: {'lr': 0.0004865780069219484, 'samples': 8964096, 'steps': 17507, 'loss/train': 2.258826494216919}
-03/04/2022 10:01:39 - INFO - codeparrot_training - Step 17508: {'lr': 0.00048657629143904733, 'samples': 8964608, 'steps': 17508, 'loss/train': 1.718372106552124}
-03/04/2022 10:01:41 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/04/2022 10:01:45 - INFO - codeparrot_training - Step 17509: {'lr': 0.0004865745758495487, 'samples': 8965120, 'steps': 17509, 'loss/train': 1.9021540880203247}
-03/04/2022 10:01:48 - INFO - codeparrot_training - Step 17510: {'lr': 0.00048657286015345313, 'samples': 8965632, 'steps': 17510, 'loss/train': 1.8333172798156738}
-03/04/2022 10:01:49 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 10:01:53 - INFO - codeparrot_training - Step 17511: {'lr': 0.00048657114435076153, 'samples': 8966144, 'steps': 17511, 'loss/train': 1.5887185335159302}
-03/04/2022 10:01:56 - INFO - codeparrot_training - Step 17512: {'lr': 0.00048656942844147464, 'samples': 8966656, 'steps': 17512, 'loss/train': 1.8052523136138916}
-03/04/2022 10:01:57 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/04/2022 10:02:01 - INFO - codeparrot_training - Step 17513: {'lr': 0.00048656771242559316, 'samples': 8967168, 'steps': 17513, 'loss/train': 1.012425422668457}
-03/04/2022 10:02:04 - INFO - codeparrot_training - Step 17514: {'lr': 0.0004865659963031179, 'samples': 8967680, 'steps': 17514, 'loss/train': 1.6891604661941528}
-03/04/2022 10:02:06 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/04/2022 10:02:10 - INFO - codeparrot_training - Step 17515: {'lr': 0.0004865642800740497, 'samples': 8968192, 'steps': 17515, 'loss/train': 0.5532246232032776}
-03/04/2022 10:02:13 - INFO - codeparrot_training - Step 17516: {'lr': 0.0004865625637383893, 'samples': 8968704, 'steps': 17516, 'loss/train': 1.4154000282287598}
-03/04/2022 10:02:14 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/04/2022 10:02:18 - INFO - codeparrot_training - Step 17517: {'lr': 0.00048656084729613747, 'samples': 8969216, 'steps': 17517, 'loss/train': 1.7067205905914307}
-03/04/2022 10:02:21 - INFO - codeparrot_training - Step 17518: {'lr': 0.0004865591307472949, 'samples': 8969728, 'steps': 17518, 'loss/train': 1.6207877397537231}
-03/04/2022 10:02:22 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/04/2022 10:02:27 - INFO - codeparrot_training - Step 17519: {'lr': 0.0004865574140918625, 'samples': 8970240, 'steps': 17519, 'loss/train': 1.9701826572418213}
-03/04/2022 10:02:30 - INFO - codeparrot_training - Step 17520: {'lr': 0.00048655569732984096, 'samples': 8970752, 'steps': 17520, 'loss/train': 2.5090763568878174}
-03/04/2022 10:02:31 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 10:02:35 - INFO - codeparrot_training - Step 17521: {'lr': 0.000486553980461231, 'samples': 8971264, 'steps': 17521, 'loss/train': 1.961938738822937}
-03/04/2022 10:02:38 - INFO - codeparrot_training - Step 17522: {'lr': 0.0004865522634860335, 'samples': 8971776, 'steps': 17522, 'loss/train': 1.928957223892212}
-03/04/2022 10:02:39 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/04/2022 10:02:43 - INFO - codeparrot_training - Step 17523: {'lr': 0.00048655054640424936, 'samples': 8972288, 'steps': 17523, 'loss/train': 0.6531922817230225}
-03/04/2022 10:02:47 - INFO - codeparrot_training - Step 17524: {'lr': 0.00048654882921587907, 'samples': 8972800, 'steps': 17524, 'loss/train': 1.671759843826294}
-03/04/2022 10:02:47 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 10:02:52 - INFO - codeparrot_training - Step 17525: {'lr': 0.00048654711192092347, 'samples': 8973312, 'steps': 17525, 'loss/train': 2.2500996589660645}
-03/04/2022 10:02:55 - INFO - codeparrot_training - Step 17526: {'lr': 0.0004865453945193835, 'samples': 8973824, 'steps': 17526, 'loss/train': 1.526464819908142}
-03/04/2022 10:02:56 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/04/2022 10:03:00 - INFO - codeparrot_training - Step 17527: {'lr': 0.00048654367701125975, 'samples': 8974336, 'steps': 17527, 'loss/train': 1.4553059339523315}
-03/04/2022 10:03:03 - INFO - codeparrot_training - Step 17528: {'lr': 0.0004865419593965531, 'samples': 8974848, 'steps': 17528, 'loss/train': 1.3860597610473633}
-03/04/2022 10:03:04 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/04/2022 10:03:09 - INFO - codeparrot_training - Step 17529: {'lr': 0.0004865402416752642, 'samples': 8975360, 'steps': 17529, 'loss/train': 1.6394612789154053}
-03/04/2022 10:03:12 - INFO - codeparrot_training - Step 17530: {'lr': 0.0004865385238473941, 'samples': 8975872, 'steps': 17530, 'loss/train': 1.9682866334915161}
-03/04/2022 10:03:12 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 10:03:17 - INFO - codeparrot_training - Step 17531: {'lr': 0.00048653680591294324, 'samples': 8976384, 'steps': 17531, 'loss/train': 1.5194083452224731}
-03/04/2022 10:03:20 - INFO - codeparrot_training - Step 17532: {'lr': 0.00048653508787191256, 'samples': 8976896, 'steps': 17532, 'loss/train': 0.8864246606826782}
-03/04/2022 10:03:22 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 10:03:26 - INFO - codeparrot_training - Step 17533: {'lr': 0.00048653336972430297, 'samples': 8977408, 'steps': 17533, 'loss/train': 1.4005341529846191}
-03/04/2022 10:03:29 - INFO - codeparrot_training - Step 17534: {'lr': 0.0004865316514701149, 'samples': 8977920, 'steps': 17534, 'loss/train': 2.2071056365966797}
-03/04/2022 10:03:30 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/04/2022 10:03:34 - INFO - codeparrot_training - Step 17535: {'lr': 0.0004865299331093495, 'samples': 8978432, 'steps': 17535, 'loss/train': 2.486935615539551}
-03/04/2022 10:03:37 - INFO - codeparrot_training - Step 17536: {'lr': 0.0004865282146420072, 'samples': 8978944, 'steps': 17536, 'loss/train': 1.3634134531021118}
-03/04/2022 10:03:38 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 10:03:42 - INFO - codeparrot_training - Step 17537: {'lr': 0.000486526496068089, 'samples': 8979456, 'steps': 17537, 'loss/train': 1.4799875020980835}
-03/04/2022 10:03:46 - INFO - codeparrot_training - Step 17538: {'lr': 0.0004865247773875956, 'samples': 8979968, 'steps': 17538, 'loss/train': 1.841787576675415}
-03/04/2022 10:03:47 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/04/2022 10:03:51 - INFO - codeparrot_training - Step 17539: {'lr': 0.0004865230586005278, 'samples': 8980480, 'steps': 17539, 'loss/train': 1.7419323921203613}
-03/04/2022 10:03:54 - INFO - codeparrot_training - Step 17540: {'lr': 0.00048652133970688633, 'samples': 8980992, 'steps': 17540, 'loss/train': 2.4380974769592285}
-03/04/2022 10:03:55 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/04/2022 10:03:59 - INFO - codeparrot_training - Step 17541: {'lr': 0.00048651962070667197, 'samples': 8981504, 'steps': 17541, 'loss/train': 2.268869638442993}
-03/04/2022 10:04:02 - INFO - codeparrot_training - Step 17542: {'lr': 0.00048651790159988563, 'samples': 8982016, 'steps': 17542, 'loss/train': 1.991766333580017}
-03/04/2022 10:04:03 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/04/2022 10:04:08 - INFO - codeparrot_training - Step 17543: {'lr': 0.0004865161823865279, 'samples': 8982528, 'steps': 17543, 'loss/train': 1.8155313730239868}
-03/04/2022 10:04:11 - INFO - codeparrot_training - Step 17544: {'lr': 0.0004865144630665996, 'samples': 8983040, 'steps': 17544, 'loss/train': 2.5009231567382812}
-03/04/2022 10:04:12 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 10:04:16 - INFO - codeparrot_training - Step 17545: {'lr': 0.0004865127436401016, 'samples': 8983552, 'steps': 17545, 'loss/train': 1.4555943012237549}
-03/04/2022 10:04:20 - INFO - codeparrot_training - Step 17546: {'lr': 0.00048651102410703464, 'samples': 8984064, 'steps': 17546, 'loss/train': 1.0512042045593262}
-03/04/2022 10:04:20 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/04/2022 10:04:25 - INFO - codeparrot_training - Step 17547: {'lr': 0.00048650930446739936, 'samples': 8984576, 'steps': 17547, 'loss/train': 1.6190294027328491}
-03/04/2022 10:04:28 - INFO - codeparrot_training - Step 17548: {'lr': 0.00048650758472119666, 'samples': 8985088, 'steps': 17548, 'loss/train': 2.3988797664642334}
-03/04/2022 10:04:29 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/04/2022 10:04:33 - INFO - codeparrot_training - Step 17549: {'lr': 0.0004865058648684273, 'samples': 8985600, 'steps': 17549, 'loss/train': 2.135314702987671}
-03/04/2022 10:04:37 - INFO - codeparrot_training - Step 17550: {'lr': 0.00048650414490909207, 'samples': 8986112, 'steps': 17550, 'loss/train': 2.772081136703491}
-03/04/2022 10:04:37 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/04/2022 10:04:42 - INFO - codeparrot_training - Step 17551: {'lr': 0.00048650242484319175, 'samples': 8986624, 'steps': 17551, 'loss/train': 1.734859585762024}
-03/04/2022 10:04:45 - INFO - codeparrot_training - Step 17552: {'lr': 0.000486500704670727, 'samples': 8987136, 'steps': 17552, 'loss/train': 1.4752333164215088}
-03/04/2022 10:04:46 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/04/2022 10:04:50 - INFO - codeparrot_training - Step 17553: {'lr': 0.0004864989843916987, 'samples': 8987648, 'steps': 17553, 'loss/train': 2.2745983600616455}
-03/04/2022 10:04:53 - INFO - codeparrot_training - Step 17554: {'lr': 0.0004864972640061077, 'samples': 8988160, 'steps': 17554, 'loss/train': 1.5310611724853516}
-03/04/2022 10:04:54 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 10:04:59 - INFO - codeparrot_training - Step 17555: {'lr': 0.00048649554351395453, 'samples': 8988672, 'steps': 17555, 'loss/train': 1.629929780960083}
-03/04/2022 10:05:02 - INFO - codeparrot_training - Step 17556: {'lr': 0.00048649382291524024, 'samples': 8989184, 'steps': 17556, 'loss/train': 2.7335784435272217}
-03/04/2022 10:05:03 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/04/2022 10:05:07 - INFO - codeparrot_training - Step 17557: {'lr': 0.0004864921022099654, 'samples': 8989696, 'steps': 17557, 'loss/train': 1.7072685956954956}
-03/04/2022 10:05:10 - INFO - codeparrot_training - Step 17558: {'lr': 0.00048649038139813097, 'samples': 8990208, 'steps': 17558, 'loss/train': 1.6765410900115967}
-03/04/2022 10:05:12 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/04/2022 10:05:16 - INFO - codeparrot_training - Step 17559: {'lr': 0.00048648866047973756, 'samples': 8990720, 'steps': 17559, 'loss/train': 2.1487529277801514}
-03/04/2022 10:05:19 - INFO - codeparrot_training - Step 17560: {'lr': 0.000486486939454786, 'samples': 8991232, 'steps': 17560, 'loss/train': 1.8863013982772827}
-03/04/2022 10:05:21 - INFO - codeparrot_training - Skipping example with length 983 (seq_length=1024)
-03/04/2022 10:05:24 - INFO - codeparrot_training - Step 17561: {'lr': 0.0004864852183232771, 'samples': 8991744, 'steps': 17561, 'loss/train': 2.576676368713379}
-03/04/2022 10:05:28 - INFO - codeparrot_training - Step 17562: {'lr': 0.0004864834970852116, 'samples': 8992256, 'steps': 17562, 'loss/train': 0.7206814885139465}
-03/04/2022 10:05:30 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 10:05:33 - INFO - codeparrot_training - Step 17563: {'lr': 0.0004864817757405903, 'samples': 8992768, 'steps': 17563, 'loss/train': 3.5090718269348145}
-03/04/2022 10:05:36 - INFO - codeparrot_training - Step 17564: {'lr': 0.0004864800542894139, 'samples': 8993280, 'steps': 17564, 'loss/train': 2.3452277183532715}
-03/04/2022 10:05:38 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/04/2022 10:05:41 - INFO - codeparrot_training - Step 17565: {'lr': 0.0004864783327316833, 'samples': 8993792, 'steps': 17565, 'loss/train': 2.127779960632324}
-03/04/2022 10:05:45 - INFO - codeparrot_training - Step 17566: {'lr': 0.0004864766110673992, 'samples': 8994304, 'steps': 17566, 'loss/train': 2.0877671241760254}
-03/04/2022 10:05:47 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/04/2022 10:05:50 - INFO - codeparrot_training - Step 17567: {'lr': 0.00048647488929656237, 'samples': 8994816, 'steps': 17567, 'loss/train': 2.0738120079040527}
-03/04/2022 10:05:53 - INFO - codeparrot_training - Step 17568: {'lr': 0.00048647316741917365, 'samples': 8995328, 'steps': 17568, 'loss/train': 2.059305429458618}
-03/04/2022 10:05:55 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 10:05:58 - INFO - codeparrot_training - Step 17569: {'lr': 0.0004864714454352337, 'samples': 8995840, 'steps': 17569, 'loss/train': 0.8107307553291321}
-03/04/2022 10:06:01 - INFO - codeparrot_training - Step 17570: {'lr': 0.00048646972334474343, 'samples': 8996352, 'steps': 17570, 'loss/train': 2.313713788986206}
-03/04/2022 10:06:03 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 10:06:07 - INFO - codeparrot_training - Step 17571: {'lr': 0.0004864680011477035, 'samples': 8996864, 'steps': 17571, 'loss/train': 2.336162567138672}
-03/04/2022 10:06:10 - INFO - codeparrot_training - Step 17572: {'lr': 0.00048646627884411475, 'samples': 8997376, 'steps': 17572, 'loss/train': 1.567208170890808}
-03/04/2022 10:06:11 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 10:06:15 - INFO - codeparrot_training - Step 17573: {'lr': 0.00048646455643397803, 'samples': 8997888, 'steps': 17573, 'loss/train': 2.1745076179504395}
-03/04/2022 10:06:18 - INFO - codeparrot_training - Step 17574: {'lr': 0.0004864628339172939, 'samples': 8998400, 'steps': 17574, 'loss/train': 1.6507943868637085}
-03/04/2022 10:06:20 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/04/2022 10:06:24 - INFO - codeparrot_training - Step 17575: {'lr': 0.00048646111129406336, 'samples': 8998912, 'steps': 17575, 'loss/train': 1.9911279678344727}
-03/04/2022 10:06:27 - INFO - codeparrot_training - Step 17576: {'lr': 0.00048645938856428704, 'samples': 8999424, 'steps': 17576, 'loss/train': 2.317091941833496}
-03/04/2022 10:06:31 - INFO - codeparrot_training - Step 17577: {'lr': 0.0004864576657279658, 'samples': 8999936, 'steps': 17577, 'loss/train': 1.3761736154556274}
-03/04/2022 10:06:32 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 10:06:36 - INFO - codeparrot_training - Step 17578: {'lr': 0.0004864559427851003, 'samples': 9000448, 'steps': 17578, 'loss/train': 2.0744898319244385}
-03/04/2022 10:06:39 - INFO - codeparrot_training - Step 17579: {'lr': 0.0004864542197356915, 'samples': 9000960, 'steps': 17579, 'loss/train': 1.7768676280975342}
-03/04/2022 10:06:40 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 10:06:44 - INFO - codeparrot_training - Step 17580: {'lr': 0.00048645249657974007, 'samples': 9001472, 'steps': 17580, 'loss/train': 2.198215961456299}
-03/04/2022 10:06:47 - INFO - codeparrot_training - Step 17581: {'lr': 0.00048645077331724675, 'samples': 9001984, 'steps': 17581, 'loss/train': 2.1666393280029297}
-03/04/2022 10:06:49 - INFO - codeparrot_training - Skipping example with length 996 (seq_length=1024)
-03/04/2022 10:06:53 - INFO - codeparrot_training - Step 17582: {'lr': 0.00048644904994821236, 'samples': 9002496, 'steps': 17582, 'loss/train': 1.941099762916565}
-03/04/2022 10:06:56 - INFO - codeparrot_training - Step 17583: {'lr': 0.0004864473264726377, 'samples': 9003008, 'steps': 17583, 'loss/train': 1.1259727478027344}
-03/04/2022 10:06:57 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/04/2022 10:07:01 - INFO - codeparrot_training - Step 17584: {'lr': 0.00048644560289052354, 'samples': 9003520, 'steps': 17584, 'loss/train': 1.7475858926773071}
-03/04/2022 10:07:04 - INFO - codeparrot_training - Step 17585: {'lr': 0.0004864438792018706, 'samples': 9004032, 'steps': 17585, 'loss/train': 2.318572521209717}
-03/04/2022 10:07:06 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 10:07:10 - INFO - codeparrot_training - Step 17586: {'lr': 0.0004864421554066797, 'samples': 9004544, 'steps': 17586, 'loss/train': 2.3089892864227295}
-03/04/2022 10:07:13 - INFO - codeparrot_training - Step 17587: {'lr': 0.00048644043150495165, 'samples': 9005056, 'steps': 17587, 'loss/train': 0.2032512128353119}
-03/04/2022 10:07:15 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/04/2022 10:07:18 - INFO - codeparrot_training - Step 17588: {'lr': 0.00048643870749668717, 'samples': 9005568, 'steps': 17588, 'loss/train': 1.7974562644958496}
-03/04/2022 10:07:21 - INFO - codeparrot_training - Step 17589: {'lr': 0.000486436983381887, 'samples': 9006080, 'steps': 17589, 'loss/train': 2.8676092624664307}
-03/04/2022 10:07:23 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/04/2022 10:07:26 - INFO - codeparrot_training - Step 17590: {'lr': 0.0004864352591605521, 'samples': 9006592, 'steps': 17590, 'loss/train': 0.5876865386962891}
-03/04/2022 10:07:30 - INFO - codeparrot_training - Step 17591: {'lr': 0.00048643353483268306, 'samples': 9007104, 'steps': 17591, 'loss/train': 1.7547401189804077}
-03/04/2022 10:07:32 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/04/2022 10:07:35 - INFO - codeparrot_training - Step 17592: {'lr': 0.00048643181039828066, 'samples': 9007616, 'steps': 17592, 'loss/train': 2.2119452953338623}
-03/04/2022 10:07:38 - INFO - codeparrot_training - Step 17593: {'lr': 0.00048643008585734575, 'samples': 9008128, 'steps': 17593, 'loss/train': 1.88961660861969}
-03/04/2022 10:07:40 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 10:07:43 - INFO - codeparrot_training - Step 17594: {'lr': 0.00048642836120987913, 'samples': 9008640, 'steps': 17594, 'loss/train': 1.90827214717865}
-03/04/2022 10:07:46 - INFO - codeparrot_training - Step 17595: {'lr': 0.0004864266364558816, 'samples': 9009152, 'steps': 17595, 'loss/train': 2.2824532985687256}
-03/04/2022 10:07:49 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/04/2022 10:07:52 - INFO - codeparrot_training - Step 17596: {'lr': 0.00048642491159535373, 'samples': 9009664, 'steps': 17596, 'loss/train': 1.8547747135162354}
-03/04/2022 10:07:55 - INFO - codeparrot_training - Step 17597: {'lr': 0.0004864231866282965, 'samples': 9010176, 'steps': 17597, 'loss/train': 1.8802217245101929}
-03/04/2022 10:07:57 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/04/2022 10:08:00 - INFO - codeparrot_training - Step 17598: {'lr': 0.0004864214615547107, 'samples': 9010688, 'steps': 17598, 'loss/train': 2.2182347774505615}
-03/04/2022 10:08:04 - INFO - codeparrot_training - Step 17599: {'lr': 0.000486419736374597, 'samples': 9011200, 'steps': 17599, 'loss/train': 0.8598599433898926}
-03/04/2022 10:08:06 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/04/2022 10:08:09 - INFO - codeparrot_training - Step 17600: {'lr': 0.0004864180110879562, 'samples': 9011712, 'steps': 17600, 'loss/train': 1.7239487171173096}
-03/04/2022 10:08:12 - INFO - codeparrot_training - Step 17601: {'lr': 0.00048641628569478916, 'samples': 9012224, 'steps': 17601, 'loss/train': 1.9089040756225586}
-03/04/2022 10:08:14 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 10:08:17 - INFO - codeparrot_training - Step 17602: {'lr': 0.00048641456019509643, 'samples': 9012736, 'steps': 17602, 'loss/train': 1.6981314420700073}
-03/04/2022 10:08:20 - INFO - codeparrot_training - Step 17603: {'lr': 0.0004864128345888791, 'samples': 9013248, 'steps': 17603, 'loss/train': 1.4950491189956665}
-03/04/2022 10:08:22 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/04/2022 10:08:26 - INFO - codeparrot_training - Step 17604: {'lr': 0.0004864111088761377, 'samples': 9013760, 'steps': 17604, 'loss/train': 1.935075044631958}
-03/04/2022 10:08:29 - INFO - codeparrot_training - Step 17605: {'lr': 0.00048640938305687315, 'samples': 9014272, 'steps': 17605, 'loss/train': 1.6077208518981934}
-03/04/2022 10:08:31 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/04/2022 10:08:34 - INFO - codeparrot_training - Step 17606: {'lr': 0.00048640765713108615, 'samples': 9014784, 'steps': 17606, 'loss/train': 1.9503464698791504}
-03/04/2022 10:08:37 - INFO - codeparrot_training - Step 17607: {'lr': 0.00048640593109877754, 'samples': 9015296, 'steps': 17607, 'loss/train': 1.9272223711013794}
-03/04/2022 10:08:39 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 10:08:42 - INFO - codeparrot_training - Step 17608: {'lr': 0.00048640420495994806, 'samples': 9015808, 'steps': 17608, 'loss/train': 1.0286378860473633}
-03/04/2022 10:08:46 - INFO - codeparrot_training - Step 17609: {'lr': 0.0004864024787145985, 'samples': 9016320, 'steps': 17609, 'loss/train': 1.7398898601531982}
-03/04/2022 10:08:47 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/04/2022 10:08:51 - INFO - codeparrot_training - Step 17610: {'lr': 0.00048640075236272963, 'samples': 9016832, 'steps': 17610, 'loss/train': 1.24214506149292}
-03/04/2022 10:08:54 - INFO - codeparrot_training - Step 17611: {'lr': 0.00048639902590434214, 'samples': 9017344, 'steps': 17611, 'loss/train': 1.920548677444458}
-03/04/2022 10:08:56 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 10:08:59 - INFO - codeparrot_training - Step 17612: {'lr': 0.000486397299339437, 'samples': 9017856, 'steps': 17612, 'loss/train': 2.1269848346710205}
-03/04/2022 10:09:02 - INFO - codeparrot_training - Step 17613: {'lr': 0.0004863955726680149, 'samples': 9018368, 'steps': 17613, 'loss/train': 1.3759475946426392}
-03/04/2022 10:09:04 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 10:09:08 - INFO - codeparrot_training - Step 17614: {'lr': 0.0004863938458900765, 'samples': 9018880, 'steps': 17614, 'loss/train': 2.0317418575286865}
-03/04/2022 10:09:11 - INFO - codeparrot_training - Step 17615: {'lr': 0.0004863921190056227, 'samples': 9019392, 'steps': 17615, 'loss/train': 2.0633790493011475}
-03/04/2022 10:09:12 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 10:09:16 - INFO - codeparrot_training - Step 17616: {'lr': 0.0004863903920146544, 'samples': 9019904, 'steps': 17616, 'loss/train': 1.8916194438934326}
-03/04/2022 10:09:19 - INFO - codeparrot_training - Step 17617: {'lr': 0.00048638866491717214, 'samples': 9020416, 'steps': 17617, 'loss/train': 1.8547922372817993}
-03/04/2022 10:09:20 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 10:09:25 - INFO - codeparrot_training - Step 17618: {'lr': 0.00048638693771317675, 'samples': 9020928, 'steps': 17618, 'loss/train': 1.225846290588379}
-03/04/2022 10:09:28 - INFO - codeparrot_training - Step 17619: {'lr': 0.0004863852104026691, 'samples': 9021440, 'steps': 17619, 'loss/train': 1.4563539028167725}
-03/04/2022 10:09:29 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/04/2022 10:09:33 - INFO - codeparrot_training - Step 17620: {'lr': 0.00048638348298564996, 'samples': 9021952, 'steps': 17620, 'loss/train': 1.7040396928787231}
-03/04/2022 10:09:36 - INFO - codeparrot_training - Step 17621: {'lr': 0.00048638175546212, 'samples': 9022464, 'steps': 17621, 'loss/train': 1.949562668800354}
-03/04/2022 10:09:37 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/04/2022 10:09:41 - INFO - codeparrot_training - Step 17622: {'lr': 0.00048638002783208013, 'samples': 9022976, 'steps': 17622, 'loss/train': 2.0607011318206787}
-03/04/2022 10:09:45 - INFO - codeparrot_training - Step 17623: {'lr': 0.000486378300095531, 'samples': 9023488, 'steps': 17623, 'loss/train': 1.7003434896469116}
-03/04/2022 10:09:46 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 10:09:50 - INFO - codeparrot_training - Step 17624: {'lr': 0.0004863765722524735, 'samples': 9024000, 'steps': 17624, 'loss/train': 1.6860395669937134}
-03/04/2022 10:09:53 - INFO - codeparrot_training - Step 17625: {'lr': 0.0004863748443029083, 'samples': 9024512, 'steps': 17625, 'loss/train': 0.8460400700569153}
-03/04/2022 10:09:54 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 10:09:58 - INFO - codeparrot_training - Step 17626: {'lr': 0.00048637311624683634, 'samples': 9025024, 'steps': 17626, 'loss/train': 1.7587765455245972}
-03/04/2022 10:10:02 - INFO - codeparrot_training - Step 17627: {'lr': 0.0004863713880842583, 'samples': 9025536, 'steps': 17627, 'loss/train': 1.8418492078781128}
-03/04/2022 10:10:03 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 10:10:07 - INFO - codeparrot_training - Step 17628: {'lr': 0.0004863696598151749, 'samples': 9026048, 'steps': 17628, 'loss/train': 1.4723191261291504}
-03/04/2022 10:10:10 - INFO - codeparrot_training - Step 17629: {'lr': 0.00048636793143958695, 'samples': 9026560, 'steps': 17629, 'loss/train': 1.772235631942749}
-03/04/2022 10:10:11 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 10:10:15 - INFO - codeparrot_training - Step 17630: {'lr': 0.00048636620295749533, 'samples': 9027072, 'steps': 17630, 'loss/train': 1.7997725009918213}
-03/04/2022 10:10:18 - INFO - codeparrot_training - Step 17631: {'lr': 0.00048636447436890075, 'samples': 9027584, 'steps': 17631, 'loss/train': 0.6357917785644531}
-03/04/2022 10:10:19 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/04/2022 10:10:24 - INFO - codeparrot_training - Step 17632: {'lr': 0.0004863627456738039, 'samples': 9028096, 'steps': 17632, 'loss/train': 2.239332437515259}
-03/04/2022 10:10:27 - INFO - codeparrot_training - Step 17633: {'lr': 0.00048636101687220566, 'samples': 9028608, 'steps': 17633, 'loss/train': 2.904937744140625}
-03/04/2022 10:10:28 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 10:10:32 - INFO - codeparrot_training - Step 17634: {'lr': 0.0004863592879641069, 'samples': 9029120, 'steps': 17634, 'loss/train': 3.5956308841705322}
-03/04/2022 10:10:35 - INFO - codeparrot_training - Step 17635: {'lr': 0.0004863575589495082, 'samples': 9029632, 'steps': 17635, 'loss/train': 2.3567843437194824}
-03/04/2022 10:10:36 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/04/2022 10:10:41 - INFO - codeparrot_training - Step 17636: {'lr': 0.00048635582982841047, 'samples': 9030144, 'steps': 17636, 'loss/train': 0.4492986798286438}
-03/04/2022 10:10:44 - INFO - codeparrot_training - Step 17637: {'lr': 0.0004863541006008144, 'samples': 9030656, 'steps': 17637, 'loss/train': 2.123424768447876}
-03/04/2022 10:10:45 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/04/2022 10:10:49 - INFO - codeparrot_training - Step 17638: {'lr': 0.0004863523712667209, 'samples': 9031168, 'steps': 17638, 'loss/train': 2.20582914352417}
-03/04/2022 10:10:52 - INFO - codeparrot_training - Step 17639: {'lr': 0.00048635064182613063, 'samples': 9031680, 'steps': 17639, 'loss/train': 1.7743374109268188}
-03/04/2022 10:10:53 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 10:10:58 - INFO - codeparrot_training - Step 17640: {'lr': 0.00048634891227904435, 'samples': 9032192, 'steps': 17640, 'loss/train': 0.7972428202629089}
-03/04/2022 10:11:01 - INFO - codeparrot_training - Step 17641: {'lr': 0.00048634718262546297, 'samples': 9032704, 'steps': 17641, 'loss/train': 2.2068734169006348}
-03/04/2022 10:11:02 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 10:11:06 - INFO - codeparrot_training - Step 17642: {'lr': 0.0004863454528653872, 'samples': 9033216, 'steps': 17642, 'loss/train': 2.4259376525878906}
-03/04/2022 10:11:09 - INFO - codeparrot_training - Step 17643: {'lr': 0.0004863437229988178, 'samples': 9033728, 'steps': 17643, 'loss/train': 2.207216739654541}
-03/04/2022 10:11:10 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/04/2022 10:11:15 - INFO - codeparrot_training - Step 17644: {'lr': 0.00048634199302575554, 'samples': 9034240, 'steps': 17644, 'loss/train': 1.207603931427002}
-03/04/2022 10:11:18 - INFO - codeparrot_training - Step 17645: {'lr': 0.00048634026294620125, 'samples': 9034752, 'steps': 17645, 'loss/train': 2.7826144695281982}
-03/04/2022 10:11:18 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/04/2022 10:11:23 - INFO - codeparrot_training - Step 17646: {'lr': 0.00048633853276015566, 'samples': 9035264, 'steps': 17646, 'loss/train': 1.972805380821228}
-03/04/2022 10:11:26 - INFO - codeparrot_training - Step 17647: {'lr': 0.00048633680246761956, 'samples': 9035776, 'steps': 17647, 'loss/train': 1.7668378353118896}
-03/04/2022 10:11:27 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 10:11:32 - INFO - codeparrot_training - Step 17648: {'lr': 0.00048633507206859383, 'samples': 9036288, 'steps': 17648, 'loss/train': 2.037001609802246}
-03/04/2022 10:11:35 - INFO - codeparrot_training - Step 17649: {'lr': 0.00048633334156307907, 'samples': 9036800, 'steps': 17649, 'loss/train': 2.074406623840332}
-03/04/2022 10:11:35 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/04/2022 10:11:40 - INFO - codeparrot_training - Step 17650: {'lr': 0.0004863316109510762, 'samples': 9037312, 'steps': 17650, 'loss/train': 2.3729002475738525}
-03/04/2022 10:11:43 - INFO - codeparrot_training - Step 17651: {'lr': 0.00048632988023258596, 'samples': 9037824, 'steps': 17651, 'loss/train': 1.5393352508544922}
-03/04/2022 10:11:44 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/04/2022 10:11:48 - INFO - codeparrot_training - Step 17652: {'lr': 0.00048632814940760907, 'samples': 9038336, 'steps': 17652, 'loss/train': 1.5689913034439087}
-03/04/2022 10:11:52 - INFO - codeparrot_training - Step 17653: {'lr': 0.00048632641847614645, 'samples': 9038848, 'steps': 17653, 'loss/train': 1.1076264381408691}
-03/04/2022 10:11:52 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 10:11:57 - INFO - codeparrot_training - Step 17654: {'lr': 0.0004863246874381987, 'samples': 9039360, 'steps': 17654, 'loss/train': 1.8635759353637695}
-03/04/2022 10:12:00 - INFO - codeparrot_training - Step 17655: {'lr': 0.00048632295629376675, 'samples': 9039872, 'steps': 17655, 'loss/train': 6.607613563537598}
-03/04/2022 10:12:01 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/04/2022 10:12:05 - INFO - codeparrot_training - Step 17656: {'lr': 0.00048632122504285133, 'samples': 9040384, 'steps': 17656, 'loss/train': 1.8852834701538086}
-03/04/2022 10:12:08 - INFO - codeparrot_training - Step 17657: {'lr': 0.0004863194936854531, 'samples': 9040896, 'steps': 17657, 'loss/train': 0.7700000405311584}
-03/04/2022 10:12:09 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/04/2022 10:12:14 - INFO - codeparrot_training - Step 17658: {'lr': 0.0004863177622215731, 'samples': 9041408, 'steps': 17658, 'loss/train': 1.6644924879074097}
-03/04/2022 10:12:17 - INFO - codeparrot_training - Step 17659: {'lr': 0.00048631603065121186, 'samples': 9041920, 'steps': 17659, 'loss/train': 1.8249307870864868}
-03/04/2022 10:12:18 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/04/2022 10:12:22 - INFO - codeparrot_training - Step 17660: {'lr': 0.00048631429897437033, 'samples': 9042432, 'steps': 17660, 'loss/train': 2.348249673843384}
-03/04/2022 10:12:25 - INFO - codeparrot_training - Step 17661: {'lr': 0.0004863125671910492, 'samples': 9042944, 'steps': 17661, 'loss/train': 1.6972764730453491}
-03/04/2022 10:12:26 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 10:12:31 - INFO - codeparrot_training - Step 17662: {'lr': 0.00048631083530124934, 'samples': 9043456, 'steps': 17662, 'loss/train': 3.2287490367889404}
-03/04/2022 10:12:34 - INFO - codeparrot_training - Step 17663: {'lr': 0.00048630910330497133, 'samples': 9043968, 'steps': 17663, 'loss/train': 1.681514024734497}
-03/04/2022 10:12:34 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 10:12:39 - INFO - codeparrot_training - Step 17664: {'lr': 0.0004863073712022162, 'samples': 9044480, 'steps': 17664, 'loss/train': 1.3225152492523193}
-03/04/2022 10:12:42 - INFO - codeparrot_training - Step 17665: {'lr': 0.00048630563899298453, 'samples': 9044992, 'steps': 17665, 'loss/train': 1.9729799032211304}
-03/04/2022 10:12:43 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/04/2022 10:12:47 - INFO - codeparrot_training - Step 17666: {'lr': 0.00048630390667727725, 'samples': 9045504, 'steps': 17666, 'loss/train': 1.533424973487854}
-03/04/2022 10:12:51 - INFO - codeparrot_training - Step 17667: {'lr': 0.00048630217425509503, 'samples': 9046016, 'steps': 17667, 'loss/train': 1.9706906080245972}
-03/04/2022 10:12:51 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 10:12:56 - INFO - codeparrot_training - Step 17668: {'lr': 0.00048630044172643874, 'samples': 9046528, 'steps': 17668, 'loss/train': 1.8294565677642822}
-03/04/2022 10:12:59 - INFO - codeparrot_training - Step 17669: {'lr': 0.0004862987090913091, 'samples': 9047040, 'steps': 17669, 'loss/train': 1.4363197088241577}
-03/04/2022 10:13:00 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/04/2022 10:13:04 - INFO - codeparrot_training - Step 17670: {'lr': 0.0004862969763497069, 'samples': 9047552, 'steps': 17670, 'loss/train': 1.3284187316894531}
-03/04/2022 10:13:08 - INFO - codeparrot_training - Step 17671: {'lr': 0.0004862952435016329, 'samples': 9048064, 'steps': 17671, 'loss/train': 2.295074462890625}
-03/04/2022 10:13:08 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 10:13:13 - INFO - codeparrot_training - Step 17672: {'lr': 0.00048629351054708795, 'samples': 9048576, 'steps': 17672, 'loss/train': 2.168184518814087}
-03/04/2022 10:13:16 - INFO - codeparrot_training - Step 17673: {'lr': 0.0004862917774860728, 'samples': 9049088, 'steps': 17673, 'loss/train': 0.5962517857551575}
-03/04/2022 10:13:17 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/04/2022 10:13:21 - INFO - codeparrot_training - Step 17674: {'lr': 0.0004862900443185882, 'samples': 9049600, 'steps': 17674, 'loss/train': 1.9558539390563965}
-03/04/2022 10:13:25 - INFO - codeparrot_training - Step 17675: {'lr': 0.00048628831104463496, 'samples': 9050112, 'steps': 17675, 'loss/train': 1.6678858995437622}
-03/04/2022 10:13:25 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 10:13:30 - INFO - codeparrot_training - Step 17676: {'lr': 0.0004862865776642138, 'samples': 9050624, 'steps': 17676, 'loss/train': 1.8748124837875366}
-03/04/2022 10:13:33 - INFO - codeparrot_training - Step 17677: {'lr': 0.00048628484417732567, 'samples': 9051136, 'steps': 17677, 'loss/train': 2.0056073665618896}
-03/04/2022 10:13:34 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/04/2022 10:13:38 - INFO - codeparrot_training - Step 17678: {'lr': 0.00048628311058397113, 'samples': 9051648, 'steps': 17678, 'loss/train': 0.38666510581970215}
-03/04/2022 10:13:41 - INFO - codeparrot_training - Step 17679: {'lr': 0.0004862813768841511, 'samples': 9052160, 'steps': 17679, 'loss/train': 2.337892532348633}
-03/04/2022 10:13:42 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/04/2022 10:13:47 - INFO - codeparrot_training - Step 17680: {'lr': 0.0004862796430778663, 'samples': 9052672, 'steps': 17680, 'loss/train': 1.7537779808044434}
-03/04/2022 10:13:50 - INFO - codeparrot_training - Step 17681: {'lr': 0.0004862779091651176, 'samples': 9053184, 'steps': 17681, 'loss/train': 1.5733609199523926}
-03/04/2022 10:13:51 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/04/2022 10:13:55 - INFO - codeparrot_training - Step 17682: {'lr': 0.0004862761751459057, 'samples': 9053696, 'steps': 17682, 'loss/train': 1.7090234756469727}
-03/04/2022 10:13:58 - INFO - codeparrot_training - Step 17683: {'lr': 0.0004862744410202314, 'samples': 9054208, 'steps': 17683, 'loss/train': 2.0518720149993896}
-03/04/2022 10:13:59 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/04/2022 10:14:04 - INFO - codeparrot_training - Step 17684: {'lr': 0.00048627270678809544, 'samples': 9054720, 'steps': 17684, 'loss/train': 1.5172041654586792}
-03/04/2022 10:14:07 - INFO - codeparrot_training - Step 17685: {'lr': 0.0004862709724494987, 'samples': 9055232, 'steps': 17685, 'loss/train': 3.033221960067749}
-03/04/2022 10:14:09 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 10:14:12 - INFO - codeparrot_training - Step 17686: {'lr': 0.0004862692380044419, 'samples': 9055744, 'steps': 17686, 'loss/train': 1.462652564048767}
-03/04/2022 10:14:16 - INFO - codeparrot_training - Step 17687: {'lr': 0.0004862675034529258, 'samples': 9056256, 'steps': 17687, 'loss/train': 1.5332857370376587}
-03/04/2022 10:14:17 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/04/2022 10:14:21 - INFO - codeparrot_training - Step 17688: {'lr': 0.0004862657687949512, 'samples': 9056768, 'steps': 17688, 'loss/train': 2.1807737350463867}
-03/04/2022 10:14:24 - INFO - codeparrot_training - Step 17689: {'lr': 0.00048626403403051894, 'samples': 9057280, 'steps': 17689, 'loss/train': 2.2318689823150635}
-03/04/2022 10:14:26 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/04/2022 10:14:29 - INFO - codeparrot_training - Step 17690: {'lr': 0.00048626229915962974, 'samples': 9057792, 'steps': 17690, 'loss/train': 2.1156489849090576}
-03/04/2022 10:14:32 - INFO - codeparrot_training - Step 17691: {'lr': 0.00048626056418228436, 'samples': 9058304, 'steps': 17691, 'loss/train': 2.3834731578826904}
-03/04/2022 10:14:34 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 10:14:38 - INFO - codeparrot_training - Step 17692: {'lr': 0.0004862588290984836, 'samples': 9058816, 'steps': 17692, 'loss/train': 1.3038816452026367}
-03/04/2022 10:14:41 - INFO - codeparrot_training - Step 17693: {'lr': 0.0004862570939082283, 'samples': 9059328, 'steps': 17693, 'loss/train': 1.7594530582427979}
-03/04/2022 10:14:43 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/04/2022 10:14:46 - INFO - codeparrot_training - Step 17694: {'lr': 0.0004862553586115192, 'samples': 9059840, 'steps': 17694, 'loss/train': 1.9955484867095947}
-03/04/2022 10:14:49 - INFO - codeparrot_training - Step 17695: {'lr': 0.00048625362320835707, 'samples': 9060352, 'steps': 17695, 'loss/train': 1.9345263242721558}
-03/04/2022 10:14:51 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 10:14:54 - INFO - codeparrot_training - Step 17696: {'lr': 0.00048625188769874274, 'samples': 9060864, 'steps': 17696, 'loss/train': 1.8068077564239502}
-03/04/2022 10:14:58 - INFO - codeparrot_training - Step 17697: {'lr': 0.0004862501520826769, 'samples': 9061376, 'steps': 17697, 'loss/train': 2.245685577392578}
-03/04/2022 10:14:59 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/04/2022 10:15:03 - INFO - codeparrot_training - Step 17698: {'lr': 0.0004862484163601604, 'samples': 9061888, 'steps': 17698, 'loss/train': 0.6369031071662903}
-03/04/2022 10:15:06 - INFO - codeparrot_training - Step 17699: {'lr': 0.000486246680531194, 'samples': 9062400, 'steps': 17699, 'loss/train': 1.768449068069458}
-03/04/2022 10:15:08 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 10:15:11 - INFO - codeparrot_training - Step 17700: {'lr': 0.0004862449445957785, 'samples': 9062912, 'steps': 17700, 'loss/train': 2.1338040828704834}
-03/04/2022 10:15:14 - INFO - codeparrot_training - Step 17701: {'lr': 0.00048624320855391467, 'samples': 9063424, 'steps': 17701, 'loss/train': 2.0154802799224854}
-03/04/2022 10:15:16 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/04/2022 10:15:20 - INFO - codeparrot_training - Step 17702: {'lr': 0.00048624147240560335, 'samples': 9063936, 'steps': 17702, 'loss/train': 1.2814348936080933}
-03/04/2022 10:15:23 - INFO - codeparrot_training - Step 17703: {'lr': 0.00048623973615084516, 'samples': 9064448, 'steps': 17703, 'loss/train': 1.9243766069412231}
-03/04/2022 10:15:25 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 10:15:28 - INFO - codeparrot_training - Step 17704: {'lr': 0.0004862379997896411, 'samples': 9064960, 'steps': 17704, 'loss/train': 2.4178271293640137}
-03/04/2022 10:15:31 - INFO - codeparrot_training - Step 17705: {'lr': 0.0004862362633219918, 'samples': 9065472, 'steps': 17705, 'loss/train': 1.716621994972229}
-03/04/2022 10:15:33 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/04/2022 10:15:37 - INFO - codeparrot_training - Step 17706: {'lr': 0.000486234526747898, 'samples': 9065984, 'steps': 17706, 'loss/train': 1.9617663621902466}
-03/04/2022 10:15:40 - INFO - codeparrot_training - Step 17707: {'lr': 0.0004862327900673607, 'samples': 9066496, 'steps': 17707, 'loss/train': 1.2907534837722778}
-03/04/2022 10:15:42 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 10:15:45 - INFO - codeparrot_training - Step 17708: {'lr': 0.00048623105328038054, 'samples': 9067008, 'steps': 17708, 'loss/train': 2.301517963409424}
-03/04/2022 10:15:48 - INFO - codeparrot_training - Step 17709: {'lr': 0.0004862293163869582, 'samples': 9067520, 'steps': 17709, 'loss/train': 6.103832721710205}
-03/04/2022 10:15:50 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/04/2022 10:15:54 - INFO - codeparrot_training - Step 17710: {'lr': 0.00048622757938709466, 'samples': 9068032, 'steps': 17710, 'loss/train': 1.9855128526687622}
-03/04/2022 10:15:57 - INFO - codeparrot_training - Step 17711: {'lr': 0.0004862258422807906, 'samples': 9068544, 'steps': 17711, 'loss/train': 2.271008014678955}
-03/04/2022 10:15:59 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/04/2022 10:16:02 - INFO - codeparrot_training - Step 17712: {'lr': 0.0004862241050680468, 'samples': 9069056, 'steps': 17712, 'loss/train': 1.8510534763336182}
-03/04/2022 10:16:05 - INFO - codeparrot_training - Step 17713: {'lr': 0.00048622236774886415, 'samples': 9069568, 'steps': 17713, 'loss/train': 1.4446097612380981}
-03/04/2022 10:16:07 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/04/2022 10:16:10 - INFO - codeparrot_training - Step 17714: {'lr': 0.00048622063032324324, 'samples': 9070080, 'steps': 17714, 'loss/train': 1.821443796157837}
-03/04/2022 10:16:14 - INFO - codeparrot_training - Step 17715: {'lr': 0.000486218892791185, 'samples': 9070592, 'steps': 17715, 'loss/train': 2.290062427520752}
-03/04/2022 10:16:16 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/04/2022 10:16:19 - INFO - codeparrot_training - Step 17716: {'lr': 0.00048621715515269017, 'samples': 9071104, 'steps': 17716, 'loss/train': 1.4744815826416016}
-03/04/2022 10:16:22 - INFO - codeparrot_training - Step 17717: {'lr': 0.0004862154174077595, 'samples': 9071616, 'steps': 17717, 'loss/train': 1.8535871505737305}
-03/04/2022 10:16:24 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/04/2022 10:16:27 - INFO - codeparrot_training - Step 17718: {'lr': 0.00048621367955639395, 'samples': 9072128, 'steps': 17718, 'loss/train': 1.9828473329544067}
-03/04/2022 10:16:31 - INFO - codeparrot_training - Step 17719: {'lr': 0.00048621194159859403, 'samples': 9072640, 'steps': 17719, 'loss/train': 2.549678087234497}
-03/04/2022 10:16:34 - INFO - codeparrot_training - Step 17720: {'lr': 0.0004862102035343607, 'samples': 9073152, 'steps': 17720, 'loss/train': 1.8110220432281494}
-03/04/2022 10:16:34 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 10:16:39 - INFO - codeparrot_training - Step 17721: {'lr': 0.0004862084653636947, 'samples': 9073664, 'steps': 17721, 'loss/train': 2.418520927429199}
-03/04/2022 10:16:42 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 10:16:44 - INFO - codeparrot_training - Step 17722: {'lr': 0.00048620672708659675, 'samples': 9074176, 'steps': 17722, 'loss/train': 2.3744192123413086}
-03/04/2022 10:16:48 - INFO - codeparrot_training - Step 17723: {'lr': 0.0004862049887030677, 'samples': 9074688, 'steps': 17723, 'loss/train': 2.035863161087036}
-03/04/2022 10:16:50 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/04/2022 10:16:53 - INFO - codeparrot_training - Step 17724: {'lr': 0.0004862032502131084, 'samples': 9075200, 'steps': 17724, 'loss/train': 1.3808050155639648}
-03/04/2022 10:16:56 - INFO - codeparrot_training - Step 17725: {'lr': 0.00048620151161671955, 'samples': 9075712, 'steps': 17725, 'loss/train': 2.359888792037964}
-03/04/2022 10:16:59 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 10:17:01 - INFO - codeparrot_training - Step 17726: {'lr': 0.00048619977291390186, 'samples': 9076224, 'steps': 17726, 'loss/train': 2.1780660152435303}
-03/04/2022 10:17:04 - INFO - codeparrot_training - Step 17727: {'lr': 0.00048619803410465624, 'samples': 9076736, 'steps': 17727, 'loss/train': 2.087703227996826}
-03/04/2022 10:17:07 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/04/2022 10:17:10 - INFO - codeparrot_training - Step 17728: {'lr': 0.00048619629518898344, 'samples': 9077248, 'steps': 17728, 'loss/train': 2.3904354572296143}
-03/04/2022 10:17:13 - INFO - codeparrot_training - Step 17729: {'lr': 0.00048619455616688426, 'samples': 9077760, 'steps': 17729, 'loss/train': 1.4124566316604614}
-03/04/2022 10:17:15 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 10:17:18 - INFO - codeparrot_training - Step 17730: {'lr': 0.0004861928170383594, 'samples': 9078272, 'steps': 17730, 'loss/train': 2.0840649604797363}
-03/04/2022 10:17:21 - INFO - codeparrot_training - Step 17731: {'lr': 0.0004861910778034098, 'samples': 9078784, 'steps': 17731, 'loss/train': 2.2153894901275635}
-03/04/2022 10:17:24 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/04/2022 10:17:26 - INFO - codeparrot_training - Step 17732: {'lr': 0.00048618933846203606, 'samples': 9079296, 'steps': 17732, 'loss/train': 2.1978988647460938}
-03/04/2022 10:17:30 - INFO - codeparrot_training - Step 17733: {'lr': 0.00048618759901423905, 'samples': 9079808, 'steps': 17733, 'loss/train': 2.311605215072632}
-03/04/2022 10:17:32 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 10:17:35 - INFO - codeparrot_training - Step 17734: {'lr': 0.0004861858594600196, 'samples': 9080320, 'steps': 17734, 'loss/train': 2.317366600036621}
-03/04/2022 10:17:38 - INFO - codeparrot_training - Step 17735: {'lr': 0.0004861841197993784, 'samples': 9080832, 'steps': 17735, 'loss/train': 1.759225845336914}
-03/04/2022 10:17:40 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 10:17:43 - INFO - codeparrot_training - Step 17736: {'lr': 0.0004861823800323163, 'samples': 9081344, 'steps': 17736, 'loss/train': 2.191605806350708}
-03/04/2022 10:17:46 - INFO - codeparrot_training - Step 17737: {'lr': 0.00048618064015883405, 'samples': 9081856, 'steps': 17737, 'loss/train': 1.8051154613494873}
-03/04/2022 10:17:49 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 10:17:52 - INFO - codeparrot_training - Step 17738: {'lr': 0.0004861789001789325, 'samples': 9082368, 'steps': 17738, 'loss/train': 1.6233527660369873}
-03/04/2022 10:17:55 - INFO - codeparrot_training - Step 17739: {'lr': 0.00048617716009261236, 'samples': 9082880, 'steps': 17739, 'loss/train': 0.7418481707572937}
-03/04/2022 10:17:58 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/04/2022 10:18:00 - INFO - codeparrot_training - Step 17740: {'lr': 0.00048617541989987435, 'samples': 9083392, 'steps': 17740, 'loss/train': 0.9539466500282288}
-03/04/2022 10:18:03 - INFO - codeparrot_training - Step 17741: {'lr': 0.00048617367960071946, 'samples': 9083904, 'steps': 17741, 'loss/train': 2.478332042694092}
-03/04/2022 10:18:06 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/04/2022 10:18:09 - INFO - codeparrot_training - Step 17742: {'lr': 0.0004861719391951483, 'samples': 9084416, 'steps': 17742, 'loss/train': 2.326171636581421}
-03/04/2022 10:18:12 - INFO - codeparrot_training - Step 17743: {'lr': 0.0004861701986831617, 'samples': 9084928, 'steps': 17743, 'loss/train': 0.6232874989509583}
-03/04/2022 10:18:15 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/04/2022 10:18:17 - INFO - codeparrot_training - Step 17744: {'lr': 0.0004861684580647605, 'samples': 9085440, 'steps': 17744, 'loss/train': 2.100576162338257}
-03/04/2022 10:18:20 - INFO - codeparrot_training - Step 17745: {'lr': 0.0004861667173399453, 'samples': 9085952, 'steps': 17745, 'loss/train': 1.5485637187957764}
-03/04/2022 10:18:23 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/04/2022 10:18:26 - INFO - codeparrot_training - Step 17746: {'lr': 0.0004861649765087172, 'samples': 9086464, 'steps': 17746, 'loss/train': 2.3322460651397705}
-03/04/2022 10:18:29 - INFO - codeparrot_training - Step 17747: {'lr': 0.0004861632355710767, 'samples': 9086976, 'steps': 17747, 'loss/train': 1.530109167098999}
-03/04/2022 10:18:31 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 10:18:34 - INFO - codeparrot_training - Step 17748: {'lr': 0.00048616149452702473, 'samples': 9087488, 'steps': 17748, 'loss/train': 1.5493450164794922}
-03/04/2022 10:18:37 - INFO - codeparrot_training - Step 17749: {'lr': 0.00048615975337656204, 'samples': 9088000, 'steps': 17749, 'loss/train': 1.6963845491409302}
-03/04/2022 10:18:40 - INFO - codeparrot_training - Step 17750: {'lr': 0.00048615801211968936, 'samples': 9088512, 'steps': 17750, 'loss/train': 1.4918327331542969}
-03/04/2022 10:18:40 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 10:18:46 - INFO - codeparrot_training - Step 17751: {'lr': 0.00048615627075640754, 'samples': 9089024, 'steps': 17751, 'loss/train': 1.7240005731582642}
-03/04/2022 10:18:49 - INFO - codeparrot_training - Step 17752: {'lr': 0.00048615452928671746, 'samples': 9089536, 'steps': 17752, 'loss/train': 1.6236759424209595}
-03/04/2022 10:18:49 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 10:18:54 - INFO - codeparrot_training - Step 17753: {'lr': 0.00048615278771061966, 'samples': 9090048, 'steps': 17753, 'loss/train': 1.8908346891403198}
-03/04/2022 10:18:57 - INFO - codeparrot_training - Step 17754: {'lr': 0.0004861510460281151, 'samples': 9090560, 'steps': 17754, 'loss/train': 2.601339340209961}
-03/04/2022 10:18:58 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 10:19:03 - INFO - codeparrot_training - Step 17755: {'lr': 0.0004861493042392045, 'samples': 9091072, 'steps': 17755, 'loss/train': 2.139415740966797}
-03/04/2022 10:19:06 - INFO - codeparrot_training - Step 17756: {'lr': 0.00048614756234388866, 'samples': 9091584, 'steps': 17756, 'loss/train': 1.5492589473724365}
-03/04/2022 10:19:06 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/04/2022 10:19:12 - INFO - codeparrot_training - Step 17757: {'lr': 0.00048614582034216844, 'samples': 9092096, 'steps': 17757, 'loss/train': 1.579012155532837}
-03/04/2022 10:19:15 - INFO - codeparrot_training - Step 17758: {'lr': 0.0004861440782340445, 'samples': 9092608, 'steps': 17758, 'loss/train': 1.7648820877075195}
-03/04/2022 10:19:16 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 10:19:20 - INFO - codeparrot_training - Step 17759: {'lr': 0.0004861423360195177, 'samples': 9093120, 'steps': 17759, 'loss/train': 1.7838704586029053}
-03/04/2022 10:19:23 - INFO - codeparrot_training - Step 17760: {'lr': 0.0004861405936985888, 'samples': 9093632, 'steps': 17760, 'loss/train': 2.6226906776428223}
-03/04/2022 10:19:24 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 10:19:28 - INFO - codeparrot_training - Step 17761: {'lr': 0.0004861388512712586, 'samples': 9094144, 'steps': 17761, 'loss/train': 1.6749874353408813}
-03/04/2022 10:19:31 - INFO - codeparrot_training - Step 17762: {'lr': 0.0004861371087375279, 'samples': 9094656, 'steps': 17762, 'loss/train': 1.7222553491592407}
-03/04/2022 10:19:32 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/04/2022 10:19:37 - INFO - codeparrot_training - Step 17763: {'lr': 0.0004861353660973974, 'samples': 9095168, 'steps': 17763, 'loss/train': 1.785827398300171}
-03/04/2022 10:19:40 - INFO - codeparrot_training - Step 17764: {'lr': 0.00048613362335086797, 'samples': 9095680, 'steps': 17764, 'loss/train': 1.5541337728500366}
-03/04/2022 10:19:41 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 10:19:45 - INFO - codeparrot_training - Step 17765: {'lr': 0.00048613188049794045, 'samples': 9096192, 'steps': 17765, 'loss/train': 1.2781540155410767}
-03/04/2022 10:19:48 - INFO - codeparrot_training - Step 17766: {'lr': 0.00048613013753861546, 'samples': 9096704, 'steps': 17766, 'loss/train': 2.3325955867767334}
-03/04/2022 10:19:50 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/04/2022 10:19:54 - INFO - codeparrot_training - Step 17767: {'lr': 0.0004861283944728939, 'samples': 9097216, 'steps': 17767, 'loss/train': 0.5109339356422424}
-03/04/2022 10:19:57 - INFO - codeparrot_training - Step 17768: {'lr': 0.0004861266513007765, 'samples': 9097728, 'steps': 17768, 'loss/train': 1.574790596961975}
-03/04/2022 10:19:58 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 10:20:02 - INFO - codeparrot_training - Step 17769: {'lr': 0.00048612490802226415, 'samples': 9098240, 'steps': 17769, 'loss/train': 2.0797767639160156}
-03/04/2022 10:20:05 - INFO - codeparrot_training - Step 17770: {'lr': 0.0004861231646373575, 'samples': 9098752, 'steps': 17770, 'loss/train': 1.0968800783157349}
-03/04/2022 10:20:06 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 10:20:10 - INFO - codeparrot_training - Step 17771: {'lr': 0.0004861214211460574, 'samples': 9099264, 'steps': 17771, 'loss/train': 2.443734884262085}
-03/04/2022 10:20:13 - INFO - codeparrot_training - Step 17772: {'lr': 0.00048611967754836466, 'samples': 9099776, 'steps': 17772, 'loss/train': 1.7949525117874146}
-03/04/2022 10:20:15 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 10:20:19 - INFO - codeparrot_training - Step 17773: {'lr': 0.00048611793384428006, 'samples': 9100288, 'steps': 17773, 'loss/train': 1.2950407266616821}
-03/04/2022 10:20:22 - INFO - codeparrot_training - Step 17774: {'lr': 0.00048611619003380426, 'samples': 9100800, 'steps': 17774, 'loss/train': 1.9074108600616455}
-03/04/2022 10:20:23 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/04/2022 10:20:27 - INFO - codeparrot_training - Step 17775: {'lr': 0.0004861144461169382, 'samples': 9101312, 'steps': 17775, 'loss/train': 1.7672216892242432}
-03/04/2022 10:20:30 - INFO - codeparrot_training - Step 17776: {'lr': 0.00048611270209368264, 'samples': 9101824, 'steps': 17776, 'loss/train': 2.340533971786499}
-03/04/2022 10:20:31 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/04/2022 10:20:36 - INFO - codeparrot_training - Step 17777: {'lr': 0.0004861109579640384, 'samples': 9102336, 'steps': 17777, 'loss/train': 2.144207239151001}
-03/04/2022 10:20:39 - INFO - codeparrot_training - Step 17778: {'lr': 0.0004861092137280061, 'samples': 9102848, 'steps': 17778, 'loss/train': 2.109093427658081}
-03/04/2022 10:20:40 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 10:20:44 - INFO - codeparrot_training - Step 17779: {'lr': 0.00048610746938558666, 'samples': 9103360, 'steps': 17779, 'loss/train': 2.0275611877441406}
-03/04/2022 10:20:47 - INFO - codeparrot_training - Step 17780: {'lr': 0.0004861057249367808, 'samples': 9103872, 'steps': 17780, 'loss/train': 1.4868932962417603}
-03/04/2022 10:20:48 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/04/2022 10:20:52 - INFO - codeparrot_training - Step 17781: {'lr': 0.00048610398038158943, 'samples': 9104384, 'steps': 17781, 'loss/train': 2.6400856971740723}
-03/04/2022 10:20:56 - INFO - codeparrot_training - Step 17782: {'lr': 0.00048610223572001315, 'samples': 9104896, 'steps': 17782, 'loss/train': 1.562225103378296}
-03/04/2022 10:20:57 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/04/2022 10:21:01 - INFO - codeparrot_training - Step 17783: {'lr': 0.0004861004909520529, 'samples': 9105408, 'steps': 17783, 'loss/train': 2.1309163570404053}
-03/04/2022 10:21:04 - INFO - codeparrot_training - Step 17784: {'lr': 0.00048609874607770945, 'samples': 9105920, 'steps': 17784, 'loss/train': 2.0285756587982178}
-03/04/2022 10:21:05 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/04/2022 10:21:09 - INFO - codeparrot_training - Step 17785: {'lr': 0.0004860970010969835, 'samples': 9106432, 'steps': 17785, 'loss/train': 2.120077133178711}
-03/04/2022 10:21:13 - INFO - codeparrot_training - Step 17786: {'lr': 0.0004860952560098759, 'samples': 9106944, 'steps': 17786, 'loss/train': 6.571303367614746}
-03/04/2022 10:21:14 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 10:21:18 - INFO - codeparrot_training - Step 17787: {'lr': 0.0004860935108163874, 'samples': 9107456, 'steps': 17787, 'loss/train': 2.4582624435424805}
-03/04/2022 10:21:21 - INFO - codeparrot_training - Step 17788: {'lr': 0.0004860917655165188, 'samples': 9107968, 'steps': 17788, 'loss/train': 1.878982663154602}
-03/04/2022 10:21:23 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 10:21:26 - INFO - codeparrot_training - Step 17789: {'lr': 0.00048609002011027093, 'samples': 9108480, 'steps': 17789, 'loss/train': 2.6355230808258057}
-03/04/2022 10:21:30 - INFO - codeparrot_training - Step 17790: {'lr': 0.0004860882745976445, 'samples': 9108992, 'steps': 17790, 'loss/train': 1.7478280067443848}
-03/04/2022 10:21:31 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/04/2022 10:21:35 - INFO - codeparrot_training - Step 17791: {'lr': 0.00048608652897864034, 'samples': 9109504, 'steps': 17791, 'loss/train': 1.9377306699752808}
-03/04/2022 10:21:38 - INFO - codeparrot_training - Step 17792: {'lr': 0.0004860847832532593, 'samples': 9110016, 'steps': 17792, 'loss/train': 6.481588840484619}
-03/04/2022 10:21:40 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 10:21:43 - INFO - codeparrot_training - Step 17793: {'lr': 0.00048608303742150204, 'samples': 9110528, 'steps': 17793, 'loss/train': 1.701877474784851}
-03/04/2022 10:21:46 - INFO - codeparrot_training - Step 17794: {'lr': 0.0004860812914833694, 'samples': 9111040, 'steps': 17794, 'loss/train': 1.6577447652816772}
-03/04/2022 10:21:48 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/04/2022 10:21:52 - INFO - codeparrot_training - Step 17795: {'lr': 0.00048607954543886225, 'samples': 9111552, 'steps': 17795, 'loss/train': 2.0152506828308105}
-03/04/2022 10:21:55 - INFO - codeparrot_training - Step 17796: {'lr': 0.00048607779928798125, 'samples': 9112064, 'steps': 17796, 'loss/train': 2.206902027130127}
-03/04/2022 10:21:58 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 10:22:00 - INFO - codeparrot_training - Step 17797: {'lr': 0.0004860760530307272, 'samples': 9112576, 'steps': 17797, 'loss/train': 2.1188292503356934}
-03/04/2022 10:22:04 - INFO - codeparrot_training - Step 17798: {'lr': 0.00048607430666710097, 'samples': 9113088, 'steps': 17798, 'loss/train': 1.6576124429702759}
-03/04/2022 10:22:07 - INFO - codeparrot_training - Step 17799: {'lr': 0.00048607256019710327, 'samples': 9113600, 'steps': 17799, 'loss/train': 0.6621900796890259}
-03/04/2022 10:22:07 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/04/2022 10:22:12 - INFO - codeparrot_training - Step 17800: {'lr': 0.0004860708136207349, 'samples': 9114112, 'steps': 17800, 'loss/train': 1.7865641117095947}
-03/04/2022 10:22:15 - INFO - codeparrot_training - Step 17801: {'lr': 0.0004860690669379967, 'samples': 9114624, 'steps': 17801, 'loss/train': 2.306563377380371}
-03/04/2022 10:22:15 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/04/2022 10:22:21 - INFO - codeparrot_training - Step 17802: {'lr': 0.00048606732014888946, 'samples': 9115136, 'steps': 17802, 'loss/train': 1.876184344291687}
-03/04/2022 10:22:24 - INFO - codeparrot_training - Step 17803: {'lr': 0.0004860655732534138, 'samples': 9115648, 'steps': 17803, 'loss/train': 2.920649766921997}
-03/04/2022 10:22:24 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/04/2022 10:22:29 - INFO - codeparrot_training - Step 17804: {'lr': 0.00048606382625157075, 'samples': 9116160, 'steps': 17804, 'loss/train': 1.4683581590652466}
-03/04/2022 10:22:32 - INFO - codeparrot_training - Step 17805: {'lr': 0.00048606207914336097, 'samples': 9116672, 'steps': 17805, 'loss/train': 1.7028052806854248}
-03/04/2022 10:22:34 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/04/2022 10:22:38 - INFO - codeparrot_training - Step 17806: {'lr': 0.0004860603319287853, 'samples': 9117184, 'steps': 17806, 'loss/train': 1.2631663084030151}
-03/04/2022 10:22:41 - INFO - codeparrot_training - Step 17807: {'lr': 0.0004860585846078444, 'samples': 9117696, 'steps': 17807, 'loss/train': 2.9094741344451904}
-03/04/2022 10:22:42 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/04/2022 10:22:46 - INFO - codeparrot_training - Step 17808: {'lr': 0.00048605683718053915, 'samples': 9118208, 'steps': 17808, 'loss/train': 1.3682935237884521}
-03/04/2022 10:22:50 - INFO - codeparrot_training - Step 17809: {'lr': 0.0004860550896468704, 'samples': 9118720, 'steps': 17809, 'loss/train': 2.239513397216797}
-03/04/2022 10:22:53 - INFO - codeparrot_training - Step 17810: {'lr': 0.00048605334200683883, 'samples': 9119232, 'steps': 17810, 'loss/train': 1.5332149267196655}
-03/04/2022 10:22:53 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 10:22:58 - INFO - codeparrot_training - Step 17811: {'lr': 0.0004860515942604452, 'samples': 9119744, 'steps': 17811, 'loss/train': 0.28796666860580444}
-03/04/2022 10:23:01 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/04/2022 10:23:03 - INFO - codeparrot_training - Step 17812: {'lr': 0.00048604984640769047, 'samples': 9120256, 'steps': 17812, 'loss/train': 1.5087194442749023}
-03/04/2022 10:23:06 - INFO - codeparrot_training - Step 17813: {'lr': 0.00048604809844857524, 'samples': 9120768, 'steps': 17813, 'loss/train': 1.7067015171051025}
-03/04/2022 10:23:09 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/04/2022 10:23:12 - INFO - codeparrot_training - Step 17814: {'lr': 0.0004860463503831004, 'samples': 9121280, 'steps': 17814, 'loss/train': 2.264066219329834}
-03/04/2022 10:23:15 - INFO - codeparrot_training - Step 17815: {'lr': 0.0004860446022112668, 'samples': 9121792, 'steps': 17815, 'loss/train': 1.8676426410675049}
-03/04/2022 10:23:17 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/04/2022 10:23:20 - INFO - codeparrot_training - Step 17816: {'lr': 0.00048604285393307503, 'samples': 9122304, 'steps': 17816, 'loss/train': 1.574478268623352}
-03/04/2022 10:23:23 - INFO - codeparrot_training - Step 17817: {'lr': 0.000486041105548526, 'samples': 9122816, 'steps': 17817, 'loss/train': 1.9657503366470337}
-03/04/2022 10:23:26 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/04/2022 10:23:28 - INFO - codeparrot_training - Step 17818: {'lr': 0.00048603935705762057, 'samples': 9123328, 'steps': 17818, 'loss/train': 1.4719229936599731}
-03/04/2022 10:23:32 - INFO - codeparrot_training - Step 17819: {'lr': 0.0004860376084603594, 'samples': 9123840, 'steps': 17819, 'loss/train': 1.640405535697937}
-03/04/2022 10:23:34 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/04/2022 10:23:37 - INFO - codeparrot_training - Step 17820: {'lr': 0.00048603585975674334, 'samples': 9124352, 'steps': 17820, 'loss/train': 2.375603675842285}
-03/04/2022 10:23:40 - INFO - codeparrot_training - Step 17821: {'lr': 0.0004860341109467732, 'samples': 9124864, 'steps': 17821, 'loss/train': 1.5005080699920654}
-03/04/2022 10:23:42 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/04/2022 10:23:45 - INFO - codeparrot_training - Step 17822: {'lr': 0.00048603236203044963, 'samples': 9125376, 'steps': 17822, 'loss/train': 2.234281539916992}
-03/04/2022 10:23:48 - INFO - codeparrot_training - Step 17823: {'lr': 0.00048603061300777365, 'samples': 9125888, 'steps': 17823, 'loss/train': 1.6722205877304077}
-03/04/2022 10:23:51 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/04/2022 10:23:54 - INFO - codeparrot_training - Step 17824: {'lr': 0.0004860288638787458, 'samples': 9126400, 'steps': 17824, 'loss/train': 2.1265439987182617}
-03/04/2022 10:23:57 - INFO - codeparrot_training - Step 17825: {'lr': 0.000486027114643367, 'samples': 9126912, 'steps': 17825, 'loss/train': 1.9362610578536987}
-03/04/2022 10:23:59 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/04/2022 10:24:02 - INFO - codeparrot_training - Step 17826: {'lr': 0.0004860253653016381, 'samples': 9127424, 'steps': 17826, 'loss/train': 1.7321217060089111}
-03/04/2022 10:24:06 - INFO - codeparrot_training - Step 17827: {'lr': 0.00048602361585355975, 'samples': 9127936, 'steps': 17827, 'loss/train': 1.7324565649032593}
-03/04/2022 10:24:09 - INFO - codeparrot_training - Step 17828: {'lr': 0.0004860218662991328, 'samples': 9128448, 'steps': 17828, 'loss/train': 3.582538604736328}
-03/04/2022 10:24:09 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/04/2022 10:24:14 - INFO - codeparrot_training - Step 17829: {'lr': 0.0004860201166383581, 'samples': 9128960, 'steps': 17829, 'loss/train': 1.9982986450195312}
-03/04/2022 10:24:18 - INFO - codeparrot_training - Step 17830: {'lr': 0.00048601836687123636, 'samples': 9129472, 'steps': 17830, 'loss/train': 2.0823776721954346}
-03/04/2022 10:24:19 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/04/2022 10:24:23 - INFO - codeparrot_training - Step 17831: {'lr': 0.00048601661699776834, 'samples': 9129984, 'steps': 17831, 'loss/train': 2.225951671600342}
-03/04/2022 10:24:26 - INFO - codeparrot_training - Step 17832: {'lr': 0.0004860148670179549, 'samples': 9130496, 'steps': 17832, 'loss/train': 1.7576751708984375}
-03/04/2022 10:24:28 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/04/2022 10:24:31 - INFO - codeparrot_training - Step 17833: {'lr': 0.0004860131169317968, 'samples': 9131008, 'steps': 17833, 'loss/train': 1.6903122663497925}
-03/04/2022 10:24:35 - INFO - codeparrot_training - Step 17834: {'lr': 0.0004860113667392948, 'samples': 9131520, 'steps': 17834, 'loss/train': 1.425572156906128}
-03/04/2022 10:24:36 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 10:24:40 - INFO - codeparrot_training - Step 17835: {'lr': 0.00048600961644044977, 'samples': 9132032, 'steps': 17835, 'loss/train': 1.1547815799713135}
-03/04/2022 10:24:43 - INFO - codeparrot_training - Step 17836: {'lr': 0.0004860078660352625, 'samples': 9132544, 'steps': 17836, 'loss/train': 1.5370306968688965}
-03/04/2022 10:24:44 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/04/2022 10:24:48 - INFO - codeparrot_training - Step 17837: {'lr': 0.0004860061155237336, 'samples': 9133056, 'steps': 17837, 'loss/train': 2.139240264892578}
-03/04/2022 10:24:52 - INFO - codeparrot_training - Step 17838: {'lr': 0.0004860043649058641, 'samples': 9133568, 'steps': 17838, 'loss/train': 2.436844825744629}
-03/04/2022 10:24:53 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 10:24:57 - INFO - codeparrot_training - Step 17839: {'lr': 0.00048600261418165456, 'samples': 9134080, 'steps': 17839, 'loss/train': 1.9371930360794067}
-03/04/2022 10:25:00 - INFO - codeparrot_training - Step 17840: {'lr': 0.00048600086335110593, 'samples': 9134592, 'steps': 17840, 'loss/train': 2.185899257659912}
-03/04/2022 10:25:01 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/04/2022 10:25:05 - INFO - codeparrot_training - Step 17841: {'lr': 0.000485999112414219, 'samples': 9135104, 'steps': 17841, 'loss/train': 1.8543041944503784}
-03/04/2022 10:25:09 - INFO - codeparrot_training - Step 17842: {'lr': 0.0004859973613709945, 'samples': 9135616, 'steps': 17842, 'loss/train': 2.198478937149048}
-03/04/2022 10:25:10 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/04/2022 10:25:14 - INFO - codeparrot_training - Step 17843: {'lr': 0.0004859956102214332, 'samples': 9136128, 'steps': 17843, 'loss/train': 0.8056599497795105}
-03/04/2022 10:25:17 - INFO - codeparrot_training - Step 17844: {'lr': 0.00048599385896553595, 'samples': 9136640, 'steps': 17844, 'loss/train': 2.4066812992095947}
-03/04/2022 10:25:19 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/04/2022 10:25:22 - INFO - codeparrot_training - Step 17845: {'lr': 0.0004859921076033034, 'samples': 9137152, 'steps': 17845, 'loss/train': 1.611732840538025}
-03/04/2022 10:25:25 - INFO - codeparrot_training - Step 17846: {'lr': 0.00048599035613473656, 'samples': 9137664, 'steps': 17846, 'loss/train': 0.21718797087669373}
-03/04/2022 10:25:27 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 10:25:31 - INFO - codeparrot_training - Step 17847: {'lr': 0.0004859886045598361, 'samples': 9138176, 'steps': 17847, 'loss/train': 2.153369903564453}
-03/04/2022 10:25:34 - INFO - codeparrot_training - Step 17848: {'lr': 0.0004859868528786028, 'samples': 9138688, 'steps': 17848, 'loss/train': 2.4223315715789795}
-03/04/2022 10:25:36 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/04/2022 10:25:39 - INFO - codeparrot_training - Step 17849: {'lr': 0.0004859851010910374, 'samples': 9139200, 'steps': 17849, 'loss/train': 2.064225673675537}
-03/04/2022 10:25:42 - INFO - codeparrot_training - Step 17850: {'lr': 0.0004859833491971409, 'samples': 9139712, 'steps': 17850, 'loss/train': 2.4244697093963623}
-03/04/2022 10:25:44 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 10:25:48 - INFO - codeparrot_training - Step 17851: {'lr': 0.0004859815971969138, 'samples': 9140224, 'steps': 17851, 'loss/train': 1.4374090433120728}
-03/04/2022 10:25:51 - INFO - codeparrot_training - Step 17852: {'lr': 0.0004859798450903571, 'samples': 9140736, 'steps': 17852, 'loss/train': 1.2511670589447021}
-03/04/2022 10:25:53 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/04/2022 10:25:56 - INFO - codeparrot_training - Step 17853: {'lr': 0.00048597809287747153, 'samples': 9141248, 'steps': 17853, 'loss/train': 2.2726194858551025}
-03/04/2022 10:25:59 - INFO - codeparrot_training - Step 17854: {'lr': 0.0004859763405582579, 'samples': 9141760, 'steps': 17854, 'loss/train': 2.140408515930176}
-03/04/2022 10:26:01 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 10:26:05 - INFO - codeparrot_training - Step 17855: {'lr': 0.00048597458813271686, 'samples': 9142272, 'steps': 17855, 'loss/train': 1.5727490186691284}
-03/04/2022 10:26:08 - INFO - codeparrot_training - Step 17856: {'lr': 0.0004859728356008494, 'samples': 9142784, 'steps': 17856, 'loss/train': 1.2421655654907227}
-03/04/2022 10:26:10 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 10:26:13 - INFO - codeparrot_training - Step 17857: {'lr': 0.00048597108296265625, 'samples': 9143296, 'steps': 17857, 'loss/train': 2.2662882804870605}
-03/04/2022 10:26:16 - INFO - codeparrot_training - Step 17858: {'lr': 0.00048596933021813815, 'samples': 9143808, 'steps': 17858, 'loss/train': 3.875774621963501}
-03/04/2022 10:26:18 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 10:26:21 - INFO - codeparrot_training - Step 17859: {'lr': 0.0004859675773672959, 'samples': 9144320, 'steps': 17859, 'loss/train': 2.0801782608032227}
-03/04/2022 10:26:24 - INFO - codeparrot_training - Step 17860: {'lr': 0.00048596582441013026, 'samples': 9144832, 'steps': 17860, 'loss/train': 1.5048261880874634}
-03/04/2022 10:26:26 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/04/2022 10:26:30 - INFO - codeparrot_training - Step 17861: {'lr': 0.0004859640713466421, 'samples': 9145344, 'steps': 17861, 'loss/train': 1.3153377771377563}
-03/04/2022 10:26:33 - INFO - codeparrot_training - Step 17862: {'lr': 0.0004859623181768321, 'samples': 9145856, 'steps': 17862, 'loss/train': 2.3679609298706055}
-03/04/2022 10:26:35 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 10:26:38 - INFO - codeparrot_training - Step 17863: {'lr': 0.0004859605649007012, 'samples': 9146368, 'steps': 17863, 'loss/train': 1.0770646333694458}
-03/04/2022 10:26:42 - INFO - codeparrot_training - Step 17864: {'lr': 0.00048595881151825015, 'samples': 9146880, 'steps': 17864, 'loss/train': 1.9120949506759644}
-03/04/2022 10:26:44 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 10:26:47 - INFO - codeparrot_training - Step 17865: {'lr': 0.00048595705802947963, 'samples': 9147392, 'steps': 17865, 'loss/train': 2.716195583343506}
-03/04/2022 10:26:50 - INFO - codeparrot_training - Step 17866: {'lr': 0.0004859553044343905, 'samples': 9147904, 'steps': 17866, 'loss/train': 1.989767074584961}
-03/04/2022 10:26:53 - INFO - codeparrot_training - Step 17867: {'lr': 0.0004859535507329836, 'samples': 9148416, 'steps': 17867, 'loss/train': 2.102576971054077}
-03/04/2022 10:26:53 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/04/2022 10:26:59 - INFO - codeparrot_training - Step 17868: {'lr': 0.0004859517969252596, 'samples': 9148928, 'steps': 17868, 'loss/train': 2.435636281967163}
-03/04/2022 10:27:02 - INFO - codeparrot_training - Step 17869: {'lr': 0.0004859500430112194, 'samples': 9149440, 'steps': 17869, 'loss/train': 2.0064215660095215}
-03/04/2022 10:27:02 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 10:27:07 - INFO - codeparrot_training - Step 17870: {'lr': 0.0004859482889908637, 'samples': 9149952, 'steps': 17870, 'loss/train': 2.305504322052002}
-03/04/2022 10:27:10 - INFO - codeparrot_training - Step 17871: {'lr': 0.0004859465348641934, 'samples': 9150464, 'steps': 17871, 'loss/train': 2.0494394302368164}
-03/04/2022 10:27:10 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 10:27:16 - INFO - codeparrot_training - Step 17872: {'lr': 0.0004859447806312093, 'samples': 9150976, 'steps': 17872, 'loss/train': 1.590112328529358}
-03/04/2022 10:27:19 - INFO - codeparrot_training - Step 17873: {'lr': 0.000485943026291912, 'samples': 9151488, 'steps': 17873, 'loss/train': 2.2903757095336914}
-03/04/2022 10:27:19 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/04/2022 10:27:24 - INFO - codeparrot_training - Step 17874: {'lr': 0.0004859412718463025, 'samples': 9152000, 'steps': 17874, 'loss/train': 1.7905049324035645}
-03/04/2022 10:27:27 - INFO - codeparrot_training - Step 17875: {'lr': 0.00048593951729438144, 'samples': 9152512, 'steps': 17875, 'loss/train': 2.9008686542510986}
-03/04/2022 10:27:27 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/04/2022 10:27:33 - INFO - codeparrot_training - Step 17876: {'lr': 0.0004859377626361497, 'samples': 9153024, 'steps': 17876, 'loss/train': 2.267151117324829}
-03/04/2022 10:27:36 - INFO - codeparrot_training - Step 17877: {'lr': 0.00048593600787160806, 'samples': 9153536, 'steps': 17877, 'loss/train': 2.1864523887634277}
-03/04/2022 10:27:36 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/04/2022 10:27:41 - INFO - codeparrot_training - Step 17878: {'lr': 0.0004859342530007572, 'samples': 9154048, 'steps': 17878, 'loss/train': 2.10567045211792}
-03/04/2022 10:27:44 - INFO - codeparrot_training - Step 17879: {'lr': 0.0004859324980235982, 'samples': 9154560, 'steps': 17879, 'loss/train': 1.776522159576416}
-03/04/2022 10:27:44 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 10:27:50 - INFO - codeparrot_training - Step 17880: {'lr': 0.0004859307429401315, 'samples': 9155072, 'steps': 17880, 'loss/train': 0.3131960332393646}
-03/04/2022 10:27:53 - INFO - codeparrot_training - Step 17881: {'lr': 0.0004859289877503581, 'samples': 9155584, 'steps': 17881, 'loss/train': 1.7575178146362305}
-03/04/2022 10:27:53 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 10:27:58 - INFO - codeparrot_training - Step 17882: {'lr': 0.00048592723245427874, 'samples': 9156096, 'steps': 17882, 'loss/train': 1.8007426261901855}
-03/04/2022 10:28:01 - INFO - codeparrot_training - Step 17883: {'lr': 0.00048592547705189414, 'samples': 9156608, 'steps': 17883, 'loss/train': 1.7338191270828247}
-03/04/2022 10:28:01 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 10:28:07 - INFO - codeparrot_training - Step 17884: {'lr': 0.00048592372154320526, 'samples': 9157120, 'steps': 17884, 'loss/train': 1.6480505466461182}
-03/04/2022 10:28:10 - INFO - codeparrot_training - Step 17885: {'lr': 0.0004859219659282127, 'samples': 9157632, 'steps': 17885, 'loss/train': 1.8349205255508423}
-03/04/2022 10:28:10 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 10:28:15 - INFO - codeparrot_training - Step 17886: {'lr': 0.00048592021020691745, 'samples': 9158144, 'steps': 17886, 'loss/train': 1.9793702363967896}
-03/04/2022 10:28:18 - INFO - codeparrot_training - Step 17887: {'lr': 0.00048591845437932014, 'samples': 9158656, 'steps': 17887, 'loss/train': 2.4264745712280273}
-03/04/2022 10:28:18 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/04/2022 10:28:23 - INFO - codeparrot_training - Step 17888: {'lr': 0.0004859166984454216, 'samples': 9159168, 'steps': 17888, 'loss/train': 1.9110783338546753}
-03/04/2022 10:28:27 - INFO - codeparrot_training - Step 17889: {'lr': 0.0004859149424052226, 'samples': 9159680, 'steps': 17889, 'loss/train': 1.779573917388916}
-03/04/2022 10:28:27 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/04/2022 10:28:32 - INFO - codeparrot_training - Step 17890: {'lr': 0.00048591318625872403, 'samples': 9160192, 'steps': 17890, 'loss/train': 2.6852073669433594}
-03/04/2022 10:28:35 - INFO - codeparrot_training - Step 17891: {'lr': 0.00048591143000592665, 'samples': 9160704, 'steps': 17891, 'loss/train': 2.311511278152466}
-03/04/2022 10:28:35 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 10:28:40 - INFO - codeparrot_training - Step 17892: {'lr': 0.00048590967364683116, 'samples': 9161216, 'steps': 17892, 'loss/train': 1.5691888332366943}
-03/04/2022 10:28:43 - INFO - codeparrot_training - Step 17893: {'lr': 0.0004859079171814384, 'samples': 9161728, 'steps': 17893, 'loss/train': 1.765015721321106}
-03/04/2022 10:28:44 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 10:28:49 - INFO - codeparrot_training - Step 17894: {'lr': 0.00048590616060974917, 'samples': 9162240, 'steps': 17894, 'loss/train': 2.658764362335205}
-03/04/2022 10:28:52 - INFO - codeparrot_training - Step 17895: {'lr': 0.00048590440393176434, 'samples': 9162752, 'steps': 17895, 'loss/train': 1.4545196294784546}
-03/04/2022 10:28:52 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/04/2022 10:28:58 - INFO - codeparrot_training - Step 17896: {'lr': 0.00048590264714748455, 'samples': 9163264, 'steps': 17896, 'loss/train': 1.000144362449646}
-03/04/2022 10:29:01 - INFO - codeparrot_training - Step 17897: {'lr': 0.0004859008902569107, 'samples': 9163776, 'steps': 17897, 'loss/train': 2.6297059059143066}
-03/04/2022 10:29:04 - INFO - codeparrot_training - Step 17898: {'lr': 0.00048589913326004355, 'samples': 9164288, 'steps': 17898, 'loss/train': 3.405886173248291}
-03/04/2022 10:29:04 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/04/2022 10:29:10 - INFO - codeparrot_training - Step 17899: {'lr': 0.0004858973761568839, 'samples': 9164800, 'steps': 17899, 'loss/train': 2.0175230503082275}
-03/04/2022 10:29:13 - INFO - codeparrot_training - Step 17900: {'lr': 0.0004858956189474325, 'samples': 9165312, 'steps': 17900, 'loss/train': 1.7527515888214111}
-03/04/2022 10:29:14 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/04/2022 10:29:18 - INFO - codeparrot_training - Step 17901: {'lr': 0.0004858938616316902, 'samples': 9165824, 'steps': 17901, 'loss/train': 1.518686294555664}
-03/04/2022 10:29:21 - INFO - codeparrot_training - Step 17902: {'lr': 0.00048589210420965775, 'samples': 9166336, 'steps': 17902, 'loss/train': 1.7290287017822266}
-03/04/2022 10:29:22 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/04/2022 10:29:27 - INFO - codeparrot_training - Step 17903: {'lr': 0.0004858903466813359, 'samples': 9166848, 'steps': 17903, 'loss/train': 1.7932206392288208}
-03/04/2022 10:29:30 - INFO - codeparrot_training - Step 17904: {'lr': 0.0004858885890467256, 'samples': 9167360, 'steps': 17904, 'loss/train': 2.01130747795105}
-03/04/2022 10:29:30 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 10:29:35 - INFO - codeparrot_training - Step 17905: {'lr': 0.00048588683130582755, 'samples': 9167872, 'steps': 17905, 'loss/train': 2.3892242908477783}
-03/04/2022 10:29:38 - INFO - codeparrot_training - Step 17906: {'lr': 0.00048588507345864246, 'samples': 9168384, 'steps': 17906, 'loss/train': 1.3342276811599731}
-03/04/2022 10:29:39 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 10:29:43 - INFO - codeparrot_training - Step 17907: {'lr': 0.00048588331550517125, 'samples': 9168896, 'steps': 17907, 'loss/train': 1.867754578590393}
-03/04/2022 10:29:47 - INFO - codeparrot_training - Step 17908: {'lr': 0.0004858815574454146, 'samples': 9169408, 'steps': 17908, 'loss/train': 2.381133556365967}
-03/04/2022 10:29:47 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/04/2022 10:29:52 - INFO - codeparrot_training - Step 17909: {'lr': 0.0004858797992793734, 'samples': 9169920, 'steps': 17909, 'loss/train': 1.1802715063095093}
-03/04/2022 10:29:55 - INFO - codeparrot_training - Step 17910: {'lr': 0.0004858780410070484, 'samples': 9170432, 'steps': 17910, 'loss/train': 1.8835339546203613}
-03/04/2022 10:29:56 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/04/2022 10:30:00 - INFO - codeparrot_training - Step 17911: {'lr': 0.0004858762826284404, 'samples': 9170944, 'steps': 17911, 'loss/train': 1.9693881273269653}
-03/04/2022 10:30:03 - INFO - codeparrot_training - Step 17912: {'lr': 0.00048587452414355014, 'samples': 9171456, 'steps': 17912, 'loss/train': 1.8358622789382935}
-03/04/2022 10:30:04 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/04/2022 10:30:09 - INFO - codeparrot_training - Step 17913: {'lr': 0.00048587276555237853, 'samples': 9171968, 'steps': 17913, 'loss/train': 1.396765947341919}
-03/04/2022 10:30:12 - INFO - codeparrot_training - Step 17914: {'lr': 0.00048587100685492626, 'samples': 9172480, 'steps': 17914, 'loss/train': 1.5540350675582886}
-03/04/2022 10:30:13 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 10:30:17 - INFO - codeparrot_training - Step 17915: {'lr': 0.00048586924805119416, 'samples': 9172992, 'steps': 17915, 'loss/train': 1.8883739709854126}
-03/04/2022 10:30:20 - INFO - codeparrot_training - Step 17916: {'lr': 0.00048586748914118303, 'samples': 9173504, 'steps': 17916, 'loss/train': 1.954619288444519}
-03/04/2022 10:30:21 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/04/2022 10:30:26 - INFO - codeparrot_training - Step 17917: {'lr': 0.0004858657301248936, 'samples': 9174016, 'steps': 17917, 'loss/train': 1.6975774765014648}
-03/04/2022 10:30:29 - INFO - codeparrot_training - Step 17918: {'lr': 0.00048586397100232673, 'samples': 9174528, 'steps': 17918, 'loss/train': 1.643062949180603}
-03/04/2022 10:30:29 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 10:30:34 - INFO - codeparrot_training - Step 17919: {'lr': 0.00048586221177348323, 'samples': 9175040, 'steps': 17919, 'loss/train': 1.676998496055603}
-03/04/2022 10:30:37 - INFO - codeparrot_training - Step 17920: {'lr': 0.00048586045243836386, 'samples': 9175552, 'steps': 17920, 'loss/train': 0.6074520945549011}
-03/04/2022 10:30:38 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 10:30:42 - INFO - codeparrot_training - Step 17921: {'lr': 0.0004858586929969693, 'samples': 9176064, 'steps': 17921, 'loss/train': 1.6989924907684326}
-03/04/2022 10:30:46 - INFO - codeparrot_training - Step 17922: {'lr': 0.0004858569334493006, 'samples': 9176576, 'steps': 17922, 'loss/train': 1.5533548593521118}
-03/04/2022 10:30:46 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 10:30:51 - INFO - codeparrot_training - Step 17923: {'lr': 0.0004858551737953583, 'samples': 9177088, 'steps': 17923, 'loss/train': 1.2561545372009277}
-03/04/2022 10:30:54 - INFO - codeparrot_training - Step 17924: {'lr': 0.00048585341403514337, 'samples': 9177600, 'steps': 17924, 'loss/train': 1.9216408729553223}
-03/04/2022 10:30:54 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 10:30:59 - INFO - codeparrot_training - Step 17925: {'lr': 0.0004858516541686565, 'samples': 9178112, 'steps': 17925, 'loss/train': 1.966538667678833}
-03/04/2022 10:31:03 - INFO - codeparrot_training - Step 17926: {'lr': 0.0004858498941958985, 'samples': 9178624, 'steps': 17926, 'loss/train': 1.8347549438476562}
-03/04/2022 10:31:03 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 10:31:08 - INFO - codeparrot_training - Step 17927: {'lr': 0.00048584813411687016, 'samples': 9179136, 'steps': 17927, 'loss/train': 2.569918394088745}
-03/04/2022 10:31:11 - INFO - codeparrot_training - Step 17928: {'lr': 0.00048584637393157235, 'samples': 9179648, 'steps': 17928, 'loss/train': 2.0229415893554688}
-03/04/2022 10:31:12 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/04/2022 10:31:16 - INFO - codeparrot_training - Step 17929: {'lr': 0.00048584461364000576, 'samples': 9180160, 'steps': 17929, 'loss/train': 1.9846856594085693}
-03/04/2022 10:31:20 - INFO - codeparrot_training - Step 17930: {'lr': 0.00048584285324217125, 'samples': 9180672, 'steps': 17930, 'loss/train': 1.317876935005188}
-03/04/2022 10:31:20 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/04/2022 10:31:25 - INFO - codeparrot_training - Step 17931: {'lr': 0.00048584109273806954, 'samples': 9181184, 'steps': 17931, 'loss/train': 0.9953736662864685}
-03/04/2022 10:31:28 - INFO - codeparrot_training - Step 17932: {'lr': 0.00048583933212770154, 'samples': 9181696, 'steps': 17932, 'loss/train': 1.6938326358795166}
-03/04/2022 10:31:29 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/04/2022 10:31:33 - INFO - codeparrot_training - Step 17933: {'lr': 0.00048583757141106796, 'samples': 9182208, 'steps': 17933, 'loss/train': 1.0503252744674683}
-03/04/2022 10:31:37 - INFO - codeparrot_training - Step 17934: {'lr': 0.00048583581058816956, 'samples': 9182720, 'steps': 17934, 'loss/train': 2.849365234375}
-03/04/2022 10:31:37 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 10:31:42 - INFO - codeparrot_training - Step 17935: {'lr': 0.00048583404965900725, 'samples': 9183232, 'steps': 17935, 'loss/train': 2.1897635459899902}
-03/04/2022 10:31:45 - INFO - codeparrot_training - Step 17936: {'lr': 0.0004858322886235817, 'samples': 9183744, 'steps': 17936, 'loss/train': 1.4693580865859985}
-03/04/2022 10:31:46 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 10:31:50 - INFO - codeparrot_training - Step 17937: {'lr': 0.0004858305274818938, 'samples': 9184256, 'steps': 17937, 'loss/train': 2.256385326385498}
-03/04/2022 10:31:54 - INFO - codeparrot_training - Step 17938: {'lr': 0.0004858287662339443, 'samples': 9184768, 'steps': 17938, 'loss/train': 2.1504509449005127}
-03/04/2022 10:31:55 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/04/2022 10:31:59 - INFO - codeparrot_training - Step 17939: {'lr': 0.00048582700487973397, 'samples': 9185280, 'steps': 17939, 'loss/train': 0.9490213394165039}
-03/04/2022 10:32:02 - INFO - codeparrot_training - Step 17940: {'lr': 0.00048582524341926365, 'samples': 9185792, 'steps': 17940, 'loss/train': 2.726505994796753}
-03/04/2022 10:32:05 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/04/2022 10:32:07 - INFO - codeparrot_training - Step 17941: {'lr': 0.0004858234818525341, 'samples': 9186304, 'steps': 17941, 'loss/train': 2.010714530944824}
-03/04/2022 10:32:11 - INFO - codeparrot_training - Step 17942: {'lr': 0.0004858217201795462, 'samples': 9186816, 'steps': 17942, 'loss/train': 1.4964302778244019}
-03/04/2022 10:32:13 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/04/2022 10:32:16 - INFO - codeparrot_training - Step 17943: {'lr': 0.0004858199584003006, 'samples': 9187328, 'steps': 17943, 'loss/train': 2.02614426612854}
-03/04/2022 10:32:19 - INFO - codeparrot_training - Step 17944: {'lr': 0.00048581819651479814, 'samples': 9187840, 'steps': 17944, 'loss/train': 2.0124404430389404}
-03/04/2022 10:32:21 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 10:32:25 - INFO - codeparrot_training - Step 17945: {'lr': 0.0004858164345230397, 'samples': 9188352, 'steps': 17945, 'loss/train': 2.463244676589966}
-03/04/2022 10:32:28 - INFO - codeparrot_training - Step 17946: {'lr': 0.000485814672425026, 'samples': 9188864, 'steps': 17946, 'loss/train': 2.408086061477661}
-03/04/2022 10:32:31 - INFO - codeparrot_training - Step 17947: {'lr': 0.0004858129102207578, 'samples': 9189376, 'steps': 17947, 'loss/train': 2.2369468212127686}
-03/04/2022 10:32:31 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/04/2022 10:32:36 - INFO - codeparrot_training - Step 17948: {'lr': 0.0004858111479102359, 'samples': 9189888, 'steps': 17948, 'loss/train': 2.375378370285034}
-03/04/2022 10:32:39 - INFO - codeparrot_training - Step 17949: {'lr': 0.00048580938549346134, 'samples': 9190400, 'steps': 17949, 'loss/train': 2.475522994995117}
-03/04/2022 10:32:40 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/04/2022 10:32:45 - INFO - codeparrot_training - Step 17950: {'lr': 0.00048580762297043456, 'samples': 9190912, 'steps': 17950, 'loss/train': 2.236032009124756}
-03/04/2022 10:32:48 - INFO - codeparrot_training - Step 17951: {'lr': 0.00048580586034115646, 'samples': 9191424, 'steps': 17951, 'loss/train': 2.2231626510620117}
-03/04/2022 10:32:48 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/04/2022 10:32:53 - INFO - codeparrot_training - Step 17952: {'lr': 0.000485804097605628, 'samples': 9191936, 'steps': 17952, 'loss/train': 1.9672455787658691}
-03/04/2022 10:32:56 - INFO - codeparrot_training - Step 17953: {'lr': 0.00048580233476384975, 'samples': 9192448, 'steps': 17953, 'loss/train': 2.1051361560821533}
-03/04/2022 10:32:56 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/04/2022 10:33:02 - INFO - codeparrot_training - Step 17954: {'lr': 0.0004858005718158227, 'samples': 9192960, 'steps': 17954, 'loss/train': 2.143631935119629}
-03/04/2022 10:33:05 - INFO - codeparrot_training - Step 17955: {'lr': 0.0004857988087615475, 'samples': 9193472, 'steps': 17955, 'loss/train': 1.2157316207885742}
-03/04/2022 10:33:06 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 10:33:10 - INFO - codeparrot_training - Step 17956: {'lr': 0.000485797045601025, 'samples': 9193984, 'steps': 17956, 'loss/train': 2.2033121585845947}
-03/04/2022 10:33:13 - INFO - codeparrot_training - Step 17957: {'lr': 0.000485795282334256, 'samples': 9194496, 'steps': 17957, 'loss/train': 2.0269510746002197}
-03/04/2022 10:33:14 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/04/2022 10:33:19 - INFO - codeparrot_training - Step 17958: {'lr': 0.00048579351896124127, 'samples': 9195008, 'steps': 17958, 'loss/train': 1.4344686269760132}
-03/04/2022 10:33:22 - INFO - codeparrot_training - Step 17959: {'lr': 0.0004857917554819816, 'samples': 9195520, 'steps': 17959, 'loss/train': 1.6970462799072266}
-03/04/2022 10:33:23 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 10:33:27 - INFO - codeparrot_training - Step 17960: {'lr': 0.00048578999189647786, 'samples': 9196032, 'steps': 17960, 'loss/train': 2.0903196334838867}
-03/04/2022 10:33:30 - INFO - codeparrot_training - Step 17961: {'lr': 0.00048578822820473074, 'samples': 9196544, 'steps': 17961, 'loss/train': 2.6818742752075195}
-03/04/2022 10:33:32 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 10:33:36 - INFO - codeparrot_training - Step 17962: {'lr': 0.00048578646440674113, 'samples': 9197056, 'steps': 17962, 'loss/train': 2.7154769897460938}
-03/04/2022 10:33:39 - INFO - codeparrot_training - Step 17963: {'lr': 0.0004857847005025097, 'samples': 9197568, 'steps': 17963, 'loss/train': 0.820645272731781}
-03/04/2022 10:33:40 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/04/2022 10:33:44 - INFO - codeparrot_training - Step 17964: {'lr': 0.0004857829364920374, 'samples': 9198080, 'steps': 17964, 'loss/train': 1.5918126106262207}
-03/04/2022 10:33:47 - INFO - codeparrot_training - Step 17965: {'lr': 0.0004857811723753249, 'samples': 9198592, 'steps': 17965, 'loss/train': 2.334970235824585}
-03/04/2022 10:33:49 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 10:33:52 - INFO - codeparrot_training - Step 17966: {'lr': 0.00048577940815237305, 'samples': 9199104, 'steps': 17966, 'loss/train': 2.3832833766937256}
-03/04/2022 10:33:55 - INFO - codeparrot_training - Step 17967: {'lr': 0.00048577764382318265, 'samples': 9199616, 'steps': 17967, 'loss/train': 2.2226688861846924}
-03/04/2022 10:33:57 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 10:34:01 - INFO - codeparrot_training - Step 17968: {'lr': 0.0004857758793877545, 'samples': 9200128, 'steps': 17968, 'loss/train': 1.931725025177002}
-03/04/2022 10:34:04 - INFO - codeparrot_training - Step 17969: {'lr': 0.00048577411484608936, 'samples': 9200640, 'steps': 17969, 'loss/train': 1.3119089603424072}
-03/04/2022 10:34:05 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 10:34:09 - INFO - codeparrot_training - Step 17970: {'lr': 0.000485772350198188, 'samples': 9201152, 'steps': 17970, 'loss/train': 2.582390069961548}
-03/04/2022 10:34:12 - INFO - codeparrot_training - Step 17971: {'lr': 0.00048577058544405126, 'samples': 9201664, 'steps': 17971, 'loss/train': 3.350034236907959}
-03/04/2022 10:34:14 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/04/2022 10:34:18 - INFO - codeparrot_training - Step 17972: {'lr': 0.00048576882058368, 'samples': 9202176, 'steps': 17972, 'loss/train': 1.2379509210586548}
-03/04/2022 10:34:21 - INFO - codeparrot_training - Step 17973: {'lr': 0.0004857670556170749, 'samples': 9202688, 'steps': 17973, 'loss/train': 1.0760782957077026}
-03/04/2022 10:34:22 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/04/2022 10:34:26 - INFO - codeparrot_training - Step 17974: {'lr': 0.0004857652905442368, 'samples': 9203200, 'steps': 17974, 'loss/train': 2.2804627418518066}
-03/04/2022 10:34:29 - INFO - codeparrot_training - Step 17975: {'lr': 0.0004857635253651665, 'samples': 9203712, 'steps': 17975, 'loss/train': 2.1901297569274902}
-03/04/2022 10:34:31 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/04/2022 10:34:34 - INFO - codeparrot_training - Step 17976: {'lr': 0.00048576176007986485, 'samples': 9204224, 'steps': 17976, 'loss/train': 1.8554326295852661}
-03/04/2022 10:34:38 - INFO - codeparrot_training - Step 17977: {'lr': 0.00048575999468833256, 'samples': 9204736, 'steps': 17977, 'loss/train': 2.3351311683654785}
-03/04/2022 10:34:39 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/04/2022 10:34:43 - INFO - codeparrot_training - Step 17978: {'lr': 0.0004857582291905704, 'samples': 9205248, 'steps': 17978, 'loss/train': 0.15328112244606018}
-03/04/2022 10:34:46 - INFO - codeparrot_training - Step 17979: {'lr': 0.00048575646358657934, 'samples': 9205760, 'steps': 17979, 'loss/train': 2.0097973346710205}
-03/04/2022 10:34:48 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 10:34:51 - INFO - codeparrot_training - Step 17980: {'lr': 0.00048575469787635997, 'samples': 9206272, 'steps': 17980, 'loss/train': 1.606844186782837}
-03/04/2022 10:34:55 - INFO - codeparrot_training - Step 17981: {'lr': 0.00048575293205991313, 'samples': 9206784, 'steps': 17981, 'loss/train': 1.4724386930465698}
-03/04/2022 10:34:56 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/04/2022 10:35:00 - INFO - codeparrot_training - Step 17982: {'lr': 0.0004857511661372397, 'samples': 9207296, 'steps': 17982, 'loss/train': 1.8826807737350464}
-03/04/2022 10:35:03 - INFO - codeparrot_training - Step 17983: {'lr': 0.00048574940010834045, 'samples': 9207808, 'steps': 17983, 'loss/train': 1.4941933155059814}
-03/04/2022 10:35:04 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/04/2022 10:35:08 - INFO - codeparrot_training - Step 17984: {'lr': 0.0004857476339732161, 'samples': 9208320, 'steps': 17984, 'loss/train': 1.4574716091156006}
-03/04/2022 10:35:11 - INFO - codeparrot_training - Step 17985: {'lr': 0.0004857458677318676, 'samples': 9208832, 'steps': 17985, 'loss/train': 0.6438436508178711}
-03/04/2022 10:35:13 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/04/2022 10:35:16 - INFO - codeparrot_training - Step 17986: {'lr': 0.0004857441013842956, 'samples': 9209344, 'steps': 17986, 'loss/train': 1.3890058994293213}
-03/04/2022 10:35:20 - INFO - codeparrot_training - Step 17987: {'lr': 0.0004857423349305009, 'samples': 9209856, 'steps': 17987, 'loss/train': 1.3494640588760376}
-03/04/2022 10:35:21 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/04/2022 10:35:25 - INFO - codeparrot_training - Step 17988: {'lr': 0.00048574056837048443, 'samples': 9210368, 'steps': 17988, 'loss/train': 1.2988080978393555}
-03/04/2022 10:35:28 - INFO - codeparrot_training - Step 17989: {'lr': 0.0004857388017042468, 'samples': 9210880, 'steps': 17989, 'loss/train': 2.346762180328369}
-03/04/2022 10:35:29 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/04/2022 10:35:34 - INFO - codeparrot_training - Step 17990: {'lr': 0.000485737034931789, 'samples': 9211392, 'steps': 17990, 'loss/train': 0.5437436103820801}
-03/04/2022 10:35:37 - INFO - codeparrot_training - Step 17991: {'lr': 0.00048573526805311166, 'samples': 9211904, 'steps': 17991, 'loss/train': 1.441810131072998}
-03/04/2022 10:35:39 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/04/2022 10:35:42 - INFO - codeparrot_training - Step 17992: {'lr': 0.0004857335010682157, 'samples': 9212416, 'steps': 17992, 'loss/train': 1.4207707643508911}
-03/04/2022 10:35:45 - INFO - codeparrot_training - Step 17993: {'lr': 0.0004857317339771018, 'samples': 9212928, 'steps': 17993, 'loss/train': 2.026493549346924}
-03/04/2022 10:35:47 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/04/2022 10:35:50 - INFO - codeparrot_training - Step 17994: {'lr': 0.0004857299667797709, 'samples': 9213440, 'steps': 17994, 'loss/train': 1.2757443189620972}
-03/04/2022 10:35:54 - INFO - codeparrot_training - Step 17995: {'lr': 0.0004857281994762236, 'samples': 9213952, 'steps': 17995, 'loss/train': 2.365861415863037}
-03/04/2022 10:35:55 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 10:35:59 - INFO - codeparrot_training - Step 17996: {'lr': 0.00048572643206646097, 'samples': 9214464, 'steps': 17996, 'loss/train': 2.232513189315796}
-03/04/2022 10:36:02 - INFO - codeparrot_training - Step 17997: {'lr': 0.0004857246645504835, 'samples': 9214976, 'steps': 17997, 'loss/train': 1.9699103832244873}
-03/04/2022 10:36:04 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/04/2022 10:36:07 - INFO - codeparrot_training - Step 17998: {'lr': 0.00048572289692829217, 'samples': 9215488, 'steps': 17998, 'loss/train': 0.9075934290885925}
-03/04/2022 10:36:10 - INFO - codeparrot_training - Step 17999: {'lr': 0.00048572112919988776, 'samples': 9216000, 'steps': 17999, 'loss/train': 1.6704392433166504}
-03/04/2022 10:36:12 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/04/2022 10:36:16 - INFO - codeparrot_training - Step 18000: {'lr': 0.00048571936136527106, 'samples': 9216512, 'steps': 18000, 'loss/train': 1.5186116695404053}
-03/04/2022 10:36:19 - INFO - codeparrot_training - Step 18001: {'lr': 0.0004857175934244428, 'samples': 9217024, 'steps': 18001, 'loss/train': 1.5295902490615845}
-03/04/2022 10:36:21 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/04/2022 10:36:24 - INFO - codeparrot_training - Step 18002: {'lr': 0.0004857158253774039, 'samples': 9217536, 'steps': 18002, 'loss/train': 2.2725470066070557}
-03/04/2022 10:36:27 - INFO - codeparrot_training - Step 18003: {'lr': 0.0004857140572241551, 'samples': 9218048, 'steps': 18003, 'loss/train': 2.6969449520111084}
-03/04/2022 10:36:29 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/04/2022 10:36:33 - INFO - codeparrot_training - Step 18004: {'lr': 0.00048571228896469713, 'samples': 9218560, 'steps': 18004, 'loss/train': 3.7287542819976807}
-03/04/2022 10:36:36 - INFO - codeparrot_training - Step 18005: {'lr': 0.0004857105205990308, 'samples': 9219072, 'steps': 18005, 'loss/train': 2.7973008155822754}
-03/04/2022 10:36:38 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 10:36:41 - INFO - codeparrot_training - Step 18006: {'lr': 0.00048570875212715706, 'samples': 9219584, 'steps': 18006, 'loss/train': 1.6999956369400024}
-03/04/2022 10:36:44 - INFO - codeparrot_training - Step 18007: {'lr': 0.0004857069835490765, 'samples': 9220096, 'steps': 18007, 'loss/train': 1.8991800546646118}
-03/04/2022 10:36:47 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/04/2022 10:36:50 - INFO - codeparrot_training - Step 18008: {'lr': 0.00048570521486479004, 'samples': 9220608, 'steps': 18008, 'loss/train': 2.0468904972076416}
-03/04/2022 10:36:53 - INFO - codeparrot_training - Step 18009: {'lr': 0.0004857034460742984, 'samples': 9221120, 'steps': 18009, 'loss/train': 1.946960210800171}
-03/04/2022 10:36:55 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/04/2022 10:36:58 - INFO - codeparrot_training - Step 18010: {'lr': 0.0004857016771776025, 'samples': 9221632, 'steps': 18010, 'loss/train': 1.429425597190857}
-03/04/2022 10:37:01 - INFO - codeparrot_training - Step 18011: {'lr': 0.000485699908174703, 'samples': 9222144, 'steps': 18011, 'loss/train': 1.0200977325439453}
-03/04/2022 10:37:04 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/04/2022 10:37:07 - INFO - codeparrot_training - Step 18012: {'lr': 0.0004856981390656008, 'samples': 9222656, 'steps': 18012, 'loss/train': 1.9465402364730835}
-03/04/2022 10:37:10 - INFO - codeparrot_training - Step 18013: {'lr': 0.00048569636985029664, 'samples': 9223168, 'steps': 18013, 'loss/train': 1.9815924167633057}
-03/04/2022 10:37:13 - INFO - codeparrot_training - Step 18014: {'lr': 0.00048569460052879136, 'samples': 9223680, 'steps': 18014, 'loss/train': 1.3275963068008423}
-03/04/2022 10:37:13 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 10:37:18 - INFO - codeparrot_training - Step 18015: {'lr': 0.0004856928311010857, 'samples': 9224192, 'steps': 18015, 'loss/train': 0.8757449984550476}
-03/04/2022 10:37:21 - INFO - codeparrot_training - Step 18016: {'lr': 0.00048569106156718045, 'samples': 9224704, 'steps': 18016, 'loss/train': 1.8529599905014038}
-03/04/2022 10:37:22 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/04/2022 10:37:27 - INFO - codeparrot_training - Step 18017: {'lr': 0.00048568929192707657, 'samples': 9225216, 'steps': 18017, 'loss/train': 1.8402068614959717}
-03/04/2022 10:37:30 - INFO - codeparrot_training - Step 18018: {'lr': 0.0004856875221807746, 'samples': 9225728, 'steps': 18018, 'loss/train': 1.3871861696243286}
-03/04/2022 10:37:30 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 10:37:35 - INFO - codeparrot_training - Step 18019: {'lr': 0.0004856857523282755, 'samples': 9226240, 'steps': 18019, 'loss/train': 1.9113489389419556}
-03/04/2022 10:37:38 - INFO - codeparrot_training - Step 18020: {'lr': 0.0004856839823695801, 'samples': 9226752, 'steps': 18020, 'loss/train': 1.095318078994751}
-03/04/2022 10:37:39 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/04/2022 10:37:44 - INFO - codeparrot_training - Step 18021: {'lr': 0.00048568221230468905, 'samples': 9227264, 'steps': 18021, 'loss/train': 2.558804988861084}
-03/04/2022 10:37:47 - INFO - codeparrot_training - Step 18022: {'lr': 0.0004856804421336033, 'samples': 9227776, 'steps': 18022, 'loss/train': 2.1312220096588135}
-03/04/2022 10:37:48 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 10:37:52 - INFO - codeparrot_training - Step 18023: {'lr': 0.0004856786718563235, 'samples': 9228288, 'steps': 18023, 'loss/train': 2.475565195083618}
-03/04/2022 10:37:55 - INFO - codeparrot_training - Step 18024: {'lr': 0.0004856769014728506, 'samples': 9228800, 'steps': 18024, 'loss/train': 1.9089443683624268}
-03/04/2022 10:37:56 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/04/2022 10:38:01 - INFO - codeparrot_training - Step 18025: {'lr': 0.0004856751309831853, 'samples': 9229312, 'steps': 18025, 'loss/train': 1.5559073686599731}
-03/04/2022 10:38:04 - INFO - codeparrot_training - Step 18026: {'lr': 0.00048567336038732843, 'samples': 9229824, 'steps': 18026, 'loss/train': 1.7330362796783447}
-03/04/2022 10:38:04 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/04/2022 10:38:09 - INFO - codeparrot_training - Step 18027: {'lr': 0.0004856715896852808, 'samples': 9230336, 'steps': 18027, 'loss/train': 1.6141101121902466}
-03/04/2022 10:38:12 - INFO - codeparrot_training - Step 18028: {'lr': 0.0004856698188770432, 'samples': 9230848, 'steps': 18028, 'loss/train': 1.4546313285827637}
-03/04/2022 10:38:13 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/04/2022 10:38:18 - INFO - codeparrot_training - Step 18029: {'lr': 0.0004856680479626163, 'samples': 9231360, 'steps': 18029, 'loss/train': 2.1798646450042725}
-03/04/2022 10:38:21 - INFO - codeparrot_training - Step 18030: {'lr': 0.0004856662769420012, 'samples': 9231872, 'steps': 18030, 'loss/train': 1.4729083776474}
-03/04/2022 10:38:21 - INFO - codeparrot_training - Skipping example with length 285 (seq_length=1024)
-03/04/2022 10:38:26 - INFO - codeparrot_training - Step 18031: {'lr': 0.0004856645058151984, 'samples': 9232384, 'steps': 18031, 'loss/train': 2.651660442352295}
-03/04/2022 10:38:29 - INFO - codeparrot_training - Step 18032: {'lr': 0.0004856627345822088, 'samples': 9232896, 'steps': 18032, 'loss/train': 1.392628788948059}
-03/04/2022 10:38:30 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/04/2022 10:38:34 - INFO - codeparrot_training - Step 18033: {'lr': 0.0004856609632430332, 'samples': 9233408, 'steps': 18033, 'loss/train': 1.0114233493804932}
-03/04/2022 10:38:38 - INFO - codeparrot_training - Step 18034: {'lr': 0.00048565919179767246, 'samples': 9233920, 'steps': 18034, 'loss/train': 1.9368866682052612}
-03/04/2022 10:38:38 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 10:38:43 - INFO - codeparrot_training - Step 18035: {'lr': 0.0004856574202461273, 'samples': 9234432, 'steps': 18035, 'loss/train': 2.0502843856811523}
-03/04/2022 10:38:46 - INFO - codeparrot_training - Step 18036: {'lr': 0.0004856556485883985, 'samples': 9234944, 'steps': 18036, 'loss/train': 2.0591673851013184}
-03/04/2022 10:38:47 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/04/2022 10:38:51 - INFO - codeparrot_training - Step 18037: {'lr': 0.000485653876824487, 'samples': 9235456, 'steps': 18037, 'loss/train': 2.247814178466797}
-03/04/2022 10:38:55 - INFO - codeparrot_training - Step 18038: {'lr': 0.00048565210495439337, 'samples': 9235968, 'steps': 18038, 'loss/train': 1.8806456327438354}
-03/04/2022 10:38:55 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/04/2022 10:39:00 - INFO - codeparrot_training - Step 18039: {'lr': 0.00048565033297811867, 'samples': 9236480, 'steps': 18039, 'loss/train': 1.737932801246643}
-03/04/2022 10:39:03 - INFO - codeparrot_training - Step 18040: {'lr': 0.0004856485608956635, 'samples': 9236992, 'steps': 18040, 'loss/train': 2.3661177158355713}
-03/04/2022 10:39:04 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 10:39:08 - INFO - codeparrot_training - Step 18041: {'lr': 0.00048564678870702873, 'samples': 9237504, 'steps': 18041, 'loss/train': 1.7484675645828247}
-03/04/2022 10:39:12 - INFO - codeparrot_training - Step 18042: {'lr': 0.00048564501641221516, 'samples': 9238016, 'steps': 18042, 'loss/train': 3.8200252056121826}
-03/04/2022 10:39:13 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/04/2022 10:39:17 - INFO - codeparrot_training - Step 18043: {'lr': 0.00048564324401122357, 'samples': 9238528, 'steps': 18043, 'loss/train': 1.715099811553955}
-03/04/2022 10:39:20 - INFO - codeparrot_training - Step 18044: {'lr': 0.0004856414715040548, 'samples': 9239040, 'steps': 18044, 'loss/train': 2.0503923892974854}
-03/04/2022 10:39:21 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/04/2022 10:39:25 - INFO - codeparrot_training - Step 18045: {'lr': 0.0004856396988907096, 'samples': 9239552, 'steps': 18045, 'loss/train': 2.0969982147216797}
-03/04/2022 10:39:28 - INFO - codeparrot_training - Step 18046: {'lr': 0.00048563792617118876, 'samples': 9240064, 'steps': 18046, 'loss/train': 2.093975782394409}
-03/04/2022 10:39:29 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/04/2022 10:39:34 - INFO - codeparrot_training - Step 18047: {'lr': 0.00048563615334549316, 'samples': 9240576, 'steps': 18047, 'loss/train': 1.804709792137146}
-03/04/2022 10:39:37 - INFO - codeparrot_training - Step 18048: {'lr': 0.0004856343804136235, 'samples': 9241088, 'steps': 18048, 'loss/train': 1.3839179277420044}
-03/04/2022 10:39:37 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/04/2022 10:39:42 - INFO - codeparrot_training - Step 18049: {'lr': 0.0004856326073755806, 'samples': 9241600, 'steps': 18049, 'loss/train': 1.8178420066833496}
-03/04/2022 10:39:45 - INFO - codeparrot_training - Step 18050: {'lr': 0.0004856308342313653, 'samples': 9242112, 'steps': 18050, 'loss/train': 1.7415199279785156}
-03/04/2022 10:39:46 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 10:39:51 - INFO - codeparrot_training - Step 18051: {'lr': 0.00048562906098097847, 'samples': 9242624, 'steps': 18051, 'loss/train': 1.1081905364990234}
-03/04/2022 10:39:54 - INFO - codeparrot_training - Step 18052: {'lr': 0.0004856272876244208, 'samples': 9243136, 'steps': 18052, 'loss/train': 1.2996468544006348}
-03/04/2022 10:39:55 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/04/2022 10:39:59 - INFO - codeparrot_training - Step 18053: {'lr': 0.000485625514161693, 'samples': 9243648, 'steps': 18053, 'loss/train': 1.8077263832092285}
-03/04/2022 10:40:02 - INFO - codeparrot_training - Step 18054: {'lr': 0.00048562374059279604, 'samples': 9244160, 'steps': 18054, 'loss/train': 1.6736817359924316}
-03/04/2022 10:40:03 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/04/2022 10:40:07 - INFO - codeparrot_training - Step 18055: {'lr': 0.00048562196691773066, 'samples': 9244672, 'steps': 18055, 'loss/train': 2.287008762359619}
-03/04/2022 10:40:11 - INFO - codeparrot_training - Step 18056: {'lr': 0.00048562019313649766, 'samples': 9245184, 'steps': 18056, 'loss/train': 1.9728847742080688}
-03/04/2022 10:40:12 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 10:40:16 - INFO - codeparrot_training - Step 18057: {'lr': 0.0004856184192490979, 'samples': 9245696, 'steps': 18057, 'loss/train': 2.219099998474121}
-03/04/2022 10:40:19 - INFO - codeparrot_training - Step 18058: {'lr': 0.000485616645255532, 'samples': 9246208, 'steps': 18058, 'loss/train': 1.670425295829773}
-03/04/2022 10:40:21 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/04/2022 10:40:24 - INFO - codeparrot_training - Step 18059: {'lr': 0.0004856148711558009, 'samples': 9246720, 'steps': 18059, 'loss/train': 1.6569184064865112}
-03/04/2022 10:40:27 - INFO - codeparrot_training - Step 18060: {'lr': 0.00048561309694990543, 'samples': 9247232, 'steps': 18060, 'loss/train': 2.1069703102111816}
-03/04/2022 10:40:29 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 10:40:33 - INFO - codeparrot_training - Step 18061: {'lr': 0.00048561132263784634, 'samples': 9247744, 'steps': 18061, 'loss/train': 2.3802969455718994}
-03/04/2022 10:40:36 - INFO - codeparrot_training - Step 18062: {'lr': 0.00048560954821962434, 'samples': 9248256, 'steps': 18062, 'loss/train': 1.9015684127807617}
-03/04/2022 10:40:37 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/04/2022 10:40:41 - INFO - codeparrot_training - Step 18063: {'lr': 0.0004856077736952404, 'samples': 9248768, 'steps': 18063, 'loss/train': 1.143176794052124}
-03/04/2022 10:40:44 - INFO - codeparrot_training - Step 18064: {'lr': 0.00048560599906469513, 'samples': 9249280, 'steps': 18064, 'loss/train': 1.6036642789840698}
-03/04/2022 10:40:45 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/04/2022 10:40:50 - INFO - codeparrot_training - Step 18065: {'lr': 0.00048560422432798956, 'samples': 9249792, 'steps': 18065, 'loss/train': 1.9430943727493286}
-03/04/2022 10:40:53 - INFO - codeparrot_training - Step 18066: {'lr': 0.0004856024494851243, 'samples': 9250304, 'steps': 18066, 'loss/train': 2.0861451625823975}
-03/04/2022 10:40:54 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 10:40:58 - INFO - codeparrot_training - Step 18067: {'lr': 0.00048560067453610025, 'samples': 9250816, 'steps': 18067, 'loss/train': 2.1829288005828857}
-03/04/2022 10:41:01 - INFO - codeparrot_training - Step 18068: {'lr': 0.00048559889948091814, 'samples': 9251328, 'steps': 18068, 'loss/train': 2.066016674041748}
-03/04/2022 10:41:02 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 10:41:06 - INFO - codeparrot_training - Step 18069: {'lr': 0.0004855971243195788, 'samples': 9251840, 'steps': 18069, 'loss/train': 2.2173357009887695}
-03/04/2022 10:41:10 - INFO - codeparrot_training - Step 18070: {'lr': 0.00048559534905208304, 'samples': 9252352, 'steps': 18070, 'loss/train': 1.6213802099227905}
-03/04/2022 10:41:11 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 10:41:15 - INFO - codeparrot_training - Step 18071: {'lr': 0.0004855935736784316, 'samples': 9252864, 'steps': 18071, 'loss/train': 1.671156883239746}
-03/04/2022 10:41:18 - INFO - codeparrot_training - Step 18072: {'lr': 0.00048559179819862537, 'samples': 9253376, 'steps': 18072, 'loss/train': 1.8741987943649292}
-03/04/2022 10:41:19 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 10:41:23 - INFO - codeparrot_training - Step 18073: {'lr': 0.0004855900226126651, 'samples': 9253888, 'steps': 18073, 'loss/train': 2.0565757751464844}
-03/04/2022 10:41:26 - INFO - codeparrot_training - Step 18074: {'lr': 0.00048558824692055156, 'samples': 9254400, 'steps': 18074, 'loss/train': 1.8783035278320312}
-03/04/2022 10:41:27 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/04/2022 10:41:32 - INFO - codeparrot_training - Step 18075: {'lr': 0.0004855864711222857, 'samples': 9254912, 'steps': 18075, 'loss/train': 1.6303091049194336}
-03/04/2022 10:41:35 - INFO - codeparrot_training - Step 18076: {'lr': 0.0004855846952178682, 'samples': 9255424, 'steps': 18076, 'loss/train': 2.446316719055176}
-03/04/2022 10:41:36 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/04/2022 10:41:40 - INFO - codeparrot_training - Step 18077: {'lr': 0.0004855829192072998, 'samples': 9255936, 'steps': 18077, 'loss/train': 2.20450496673584}
-03/04/2022 10:41:43 - INFO - codeparrot_training - Step 18078: {'lr': 0.00048558114309058144, 'samples': 9256448, 'steps': 18078, 'loss/train': 2.0531225204467773}
-03/04/2022 10:41:44 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/04/2022 10:41:49 - INFO - codeparrot_training - Step 18079: {'lr': 0.00048557936686771376, 'samples': 9256960, 'steps': 18079, 'loss/train': 1.5814470052719116}
-03/04/2022 10:41:52 - INFO - codeparrot_training - Step 18080: {'lr': 0.0004855775905386977, 'samples': 9257472, 'steps': 18080, 'loss/train': 1.6231176853179932}
-03/04/2022 10:41:53 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 10:41:57 - INFO - codeparrot_training - Step 18081: {'lr': 0.000485575814103534, 'samples': 9257984, 'steps': 18081, 'loss/train': 2.071795701980591}
-03/04/2022 10:42:00 - INFO - codeparrot_training - Step 18082: {'lr': 0.0004855740375622235, 'samples': 9258496, 'steps': 18082, 'loss/train': 1.9343911409378052}
-03/04/2022 10:42:02 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/04/2022 10:42:06 - INFO - codeparrot_training - Step 18083: {'lr': 0.00048557226091476704, 'samples': 9259008, 'steps': 18083, 'loss/train': 2.3774161338806152}
-03/04/2022 10:42:09 - INFO - codeparrot_training - Step 18084: {'lr': 0.0004855704841611652, 'samples': 9259520, 'steps': 18084, 'loss/train': 2.3986387252807617}
-03/04/2022 10:42:10 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/04/2022 10:42:14 - INFO - codeparrot_training - Step 18085: {'lr': 0.00048556870730141906, 'samples': 9260032, 'steps': 18085, 'loss/train': 2.759908676147461}
-03/04/2022 10:42:17 - INFO - codeparrot_training - Step 18086: {'lr': 0.00048556693033552926, 'samples': 9260544, 'steps': 18086, 'loss/train': 1.035249948501587}
-03/04/2022 10:42:19 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 10:42:23 - INFO - codeparrot_training - Step 18087: {'lr': 0.0004855651532634966, 'samples': 9261056, 'steps': 18087, 'loss/train': 0.7822667956352234}
-03/04/2022 10:42:26 - INFO - codeparrot_training - Step 18088: {'lr': 0.00048556337608532196, 'samples': 9261568, 'steps': 18088, 'loss/train': 1.3302208185195923}
-03/04/2022 10:42:27 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 10:42:31 - INFO - codeparrot_training - Step 18089: {'lr': 0.00048556159880100604, 'samples': 9262080, 'steps': 18089, 'loss/train': 2.014796018600464}
-03/04/2022 10:42:34 - INFO - codeparrot_training - Step 18090: {'lr': 0.00048555982141054976, 'samples': 9262592, 'steps': 18090, 'loss/train': 2.652547836303711}
-03/04/2022 10:42:36 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 10:42:39 - INFO - codeparrot_training - Step 18091: {'lr': 0.0004855580439139539, 'samples': 9263104, 'steps': 18091, 'loss/train': 2.0466766357421875}
-03/04/2022 10:42:43 - INFO - codeparrot_training - Step 18092: {'lr': 0.00048555626631121906, 'samples': 9263616, 'steps': 18092, 'loss/train': 2.089583396911621}
-03/04/2022 10:42:44 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/04/2022 10:42:48 - INFO - codeparrot_training - Step 18093: {'lr': 0.0004855544886023463, 'samples': 9264128, 'steps': 18093, 'loss/train': 0.16876201331615448}
-03/04/2022 10:42:51 - INFO - codeparrot_training - Step 18094: {'lr': 0.00048555271078733637, 'samples': 9264640, 'steps': 18094, 'loss/train': 1.6249490976333618}
-03/04/2022 10:42:53 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 10:42:56 - INFO - codeparrot_training - Step 18095: {'lr': 0.00048555093286618996, 'samples': 9265152, 'steps': 18095, 'loss/train': 2.4962408542633057}
-03/04/2022 10:42:59 - INFO - codeparrot_training - Step 18096: {'lr': 0.0004855491548389079, 'samples': 9265664, 'steps': 18096, 'loss/train': 2.375613212585449}
-03/04/2022 10:43:01 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 10:43:05 - INFO - codeparrot_training - Step 18097: {'lr': 0.0004855473767054911, 'samples': 9266176, 'steps': 18097, 'loss/train': 2.2110486030578613}
-03/04/2022 10:43:08 - INFO - codeparrot_training - Step 18098: {'lr': 0.00048554559846594026, 'samples': 9266688, 'steps': 18098, 'loss/train': 2.25071120262146}
-03/04/2022 10:43:09 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 10:43:13 - INFO - codeparrot_training - Step 18099: {'lr': 0.0004855438201202562, 'samples': 9267200, 'steps': 18099, 'loss/train': 1.436682939529419}
-03/04/2022 10:43:16 - INFO - codeparrot_training - Step 18100: {'lr': 0.0004855420416684398, 'samples': 9267712, 'steps': 18100, 'loss/train': 1.9390878677368164}
-03/04/2022 10:43:18 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 10:43:22 - INFO - codeparrot_training - Step 18101: {'lr': 0.0004855402631104917, 'samples': 9268224, 'steps': 18101, 'loss/train': 1.920385479927063}
-03/04/2022 10:43:25 - INFO - codeparrot_training - Step 18102: {'lr': 0.0004855384844464128, 'samples': 9268736, 'steps': 18102, 'loss/train': 2.405860662460327}
-03/04/2022 10:43:26 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/04/2022 10:43:30 - INFO - codeparrot_training - Step 18103: {'lr': 0.00048553670567620395, 'samples': 9269248, 'steps': 18103, 'loss/train': 0.23816826939582825}
-03/04/2022 10:43:33 - INFO - codeparrot_training - Step 18104: {'lr': 0.0004855349267998659, 'samples': 9269760, 'steps': 18104, 'loss/train': 1.858398675918579}
-03/04/2022 10:43:34 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/04/2022 10:43:39 - INFO - codeparrot_training - Step 18105: {'lr': 0.0004855331478173994, 'samples': 9270272, 'steps': 18105, 'loss/train': 1.6501152515411377}
-03/04/2022 10:43:42 - INFO - codeparrot_training - Step 18106: {'lr': 0.0004855313687288053, 'samples': 9270784, 'steps': 18106, 'loss/train': 1.6377369165420532}
-03/04/2022 10:43:44 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/04/2022 10:43:47 - INFO - codeparrot_training - Step 18107: {'lr': 0.00048552958953408437, 'samples': 9271296, 'steps': 18107, 'loss/train': 2.0241332054138184}
-03/04/2022 10:43:50 - INFO - codeparrot_training - Step 18108: {'lr': 0.0004855278102332375, 'samples': 9271808, 'steps': 18108, 'loss/train': 1.9219976663589478}
-03/04/2022 10:43:52 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 10:43:56 - INFO - codeparrot_training - Step 18109: {'lr': 0.0004855260308262654, 'samples': 9272320, 'steps': 18109, 'loss/train': 1.2442052364349365}
-03/04/2022 10:43:59 - INFO - codeparrot_training - Step 18110: {'lr': 0.00048552425131316893, 'samples': 9272832, 'steps': 18110, 'loss/train': 1.189245581626892}
-03/04/2022 10:44:01 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 10:44:04 - INFO - codeparrot_training - Step 18111: {'lr': 0.0004855224716939488, 'samples': 9273344, 'steps': 18111, 'loss/train': 0.2728780210018158}
-03/04/2022 10:44:07 - INFO - codeparrot_training - Step 18112: {'lr': 0.0004855206919686059, 'samples': 9273856, 'steps': 18112, 'loss/train': 1.5287086963653564}
-03/04/2022 10:44:10 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/04/2022 10:44:13 - INFO - codeparrot_training - Step 18113: {'lr': 0.0004855189121371411, 'samples': 9274368, 'steps': 18113, 'loss/train': 1.8683959245681763}
-03/04/2022 10:44:16 - INFO - codeparrot_training - Step 18114: {'lr': 0.00048551713219955505, 'samples': 9274880, 'steps': 18114, 'loss/train': 2.177990436553955}
-03/04/2022 10:44:18 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 10:44:21 - INFO - codeparrot_training - Step 18115: {'lr': 0.00048551535215584865, 'samples': 9275392, 'steps': 18115, 'loss/train': 1.667421817779541}
-03/04/2022 10:44:24 - INFO - codeparrot_training - Step 18116: {'lr': 0.00048551357200602265, 'samples': 9275904, 'steps': 18116, 'loss/train': 1.9115840196609497}
-03/04/2022 10:44:27 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/04/2022 10:44:30 - INFO - codeparrot_training - Step 18117: {'lr': 0.0004855117917500778, 'samples': 9276416, 'steps': 18117, 'loss/train': 4.902676582336426}
-03/04/2022 10:44:33 - INFO - codeparrot_training - Step 18118: {'lr': 0.000485510011388015, 'samples': 9276928, 'steps': 18118, 'loss/train': 1.980588674545288}
-03/04/2022 10:44:35 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/04/2022 10:44:38 - INFO - codeparrot_training - Step 18119: {'lr': 0.00048550823091983507, 'samples': 9277440, 'steps': 18119, 'loss/train': 1.7924127578735352}
-03/04/2022 10:44:41 - INFO - codeparrot_training - Step 18120: {'lr': 0.00048550645034553877, 'samples': 9277952, 'steps': 18120, 'loss/train': 2.468632936477661}
-03/04/2022 10:44:43 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/04/2022 10:44:47 - INFO - codeparrot_training - Step 18121: {'lr': 0.00048550466966512684, 'samples': 9278464, 'steps': 18121, 'loss/train': 2.55251145362854}
-03/04/2022 10:44:50 - INFO - codeparrot_training - Step 18122: {'lr': 0.0004855028888786002, 'samples': 9278976, 'steps': 18122, 'loss/train': 2.2567946910858154}
-03/04/2022 10:44:53 - INFO - codeparrot_training - Step 18123: {'lr': 0.00048550110798595953, 'samples': 9279488, 'steps': 18123, 'loss/train': 2.068143367767334}
-03/04/2022 10:44:53 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/04/2022 10:44:59 - INFO - codeparrot_training - Step 18124: {'lr': 0.0004854993269872057, 'samples': 9280000, 'steps': 18124, 'loss/train': 1.589461088180542}
-03/04/2022 10:45:02 - INFO - codeparrot_training - Step 18125: {'lr': 0.0004854975458823396, 'samples': 9280512, 'steps': 18125, 'loss/train': 1.9462170600891113}
-03/04/2022 10:45:02 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/04/2022 10:45:07 - INFO - codeparrot_training - Step 18126: {'lr': 0.0004854957646713618, 'samples': 9281024, 'steps': 18126, 'loss/train': 2.1950531005859375}
-03/04/2022 10:45:10 - INFO - codeparrot_training - Step 18127: {'lr': 0.00048549398335427337, 'samples': 9281536, 'steps': 18127, 'loss/train': 1.8298622369766235}
-03/04/2022 10:45:10 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 10:45:16 - INFO - codeparrot_training - Step 18128: {'lr': 0.0004854922019310749, 'samples': 9282048, 'steps': 18128, 'loss/train': 1.6145155429840088}
-03/04/2022 10:45:19 - INFO - codeparrot_training - Step 18129: {'lr': 0.0004854904204017673, 'samples': 9282560, 'steps': 18129, 'loss/train': 3.039752244949341}
-03/04/2022 10:45:19 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 10:45:24 - INFO - codeparrot_training - Step 18130: {'lr': 0.0004854886387663514, 'samples': 9283072, 'steps': 18130, 'loss/train': 2.218212366104126}
-03/04/2022 10:45:27 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/04/2022 10:45:29 - INFO - codeparrot_training - Step 18131: {'lr': 0.0004854868570248279, 'samples': 9283584, 'steps': 18131, 'loss/train': 2.1105751991271973}
-03/04/2022 10:45:32 - INFO - codeparrot_training - Step 18132: {'lr': 0.00048548507517719766, 'samples': 9284096, 'steps': 18132, 'loss/train': 2.0062012672424316}
-03/04/2022 10:45:35 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/04/2022 10:45:38 - INFO - codeparrot_training - Step 18133: {'lr': 0.0004854832932234615, 'samples': 9284608, 'steps': 18133, 'loss/train': 2.2786216735839844}
-03/04/2022 10:45:41 - INFO - codeparrot_training - Step 18134: {'lr': 0.0004854815111636202, 'samples': 9285120, 'steps': 18134, 'loss/train': 1.3398759365081787}
-03/04/2022 10:45:44 - INFO - codeparrot_training - Step 18135: {'lr': 0.00048547972899767454, 'samples': 9285632, 'steps': 18135, 'loss/train': 1.7908903360366821}
-03/04/2022 10:45:44 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 10:45:50 - INFO - codeparrot_training - Step 18136: {'lr': 0.0004854779467256254, 'samples': 9286144, 'steps': 18136, 'loss/train': 2.049302101135254}
-03/04/2022 10:45:53 - INFO - codeparrot_training - Step 18137: {'lr': 0.00048547616434747344, 'samples': 9286656, 'steps': 18137, 'loss/train': 1.7474358081817627}
-03/04/2022 10:45:57 - INFO - codeparrot_training - Step 18138: {'lr': 0.0004854743818632196, 'samples': 9287168, 'steps': 18138, 'loss/train': 2.1214473247528076}
-03/04/2022 10:45:57 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 10:46:02 - INFO - codeparrot_training - Step 18139: {'lr': 0.0004854725992728647, 'samples': 9287680, 'steps': 18139, 'loss/train': 1.5066131353378296}
-03/04/2022 10:46:05 - INFO - codeparrot_training - Step 18140: {'lr': 0.00048547081657640935, 'samples': 9288192, 'steps': 18140, 'loss/train': 1.8441829681396484}
-03/04/2022 10:46:05 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/04/2022 10:46:10 - INFO - codeparrot_training - Step 18141: {'lr': 0.00048546903377385457, 'samples': 9288704, 'steps': 18141, 'loss/train': 2.590217113494873}
-03/04/2022 10:46:14 - INFO - codeparrot_training - Step 18142: {'lr': 0.00048546725086520107, 'samples': 9289216, 'steps': 18142, 'loss/train': 1.0912885665893555}
-03/04/2022 10:46:14 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 10:46:19 - INFO - codeparrot_training - Step 18143: {'lr': 0.00048546546785044965, 'samples': 9289728, 'steps': 18143, 'loss/train': 1.736397385597229}
-03/04/2022 10:46:22 - INFO - codeparrot_training - Step 18144: {'lr': 0.00048546368472960114, 'samples': 9290240, 'steps': 18144, 'loss/train': 2.0963330268859863}
-03/04/2022 10:46:22 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/04/2022 10:46:27 - INFO - codeparrot_training - Step 18145: {'lr': 0.00048546190150265634, 'samples': 9290752, 'steps': 18145, 'loss/train': 1.2742969989776611}
-03/04/2022 10:46:30 - INFO - codeparrot_training - Step 18146: {'lr': 0.00048546011816961597, 'samples': 9291264, 'steps': 18146, 'loss/train': 1.5042163133621216}
-03/04/2022 10:46:31 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 10:46:36 - INFO - codeparrot_training - Step 18147: {'lr': 0.00048545833473048094, 'samples': 9291776, 'steps': 18147, 'loss/train': 1.5104914903640747}
-03/04/2022 10:46:39 - INFO - codeparrot_training - Step 18148: {'lr': 0.00048545655118525206, 'samples': 9292288, 'steps': 18148, 'loss/train': 1.9205474853515625}
-03/04/2022 10:46:39 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/04/2022 10:46:44 - INFO - codeparrot_training - Step 18149: {'lr': 0.00048545476753393004, 'samples': 9292800, 'steps': 18149, 'loss/train': 2.573028564453125}
-03/04/2022 10:46:47 - INFO - codeparrot_training - Step 18150: {'lr': 0.0004854529837765158, 'samples': 9293312, 'steps': 18150, 'loss/train': 2.023547887802124}
-03/04/2022 10:46:48 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 10:46:53 - INFO - codeparrot_training - Step 18151: {'lr': 0.00048545119991301, 'samples': 9293824, 'steps': 18151, 'loss/train': 2.0021164417266846}
-03/04/2022 10:46:56 - INFO - codeparrot_training - Step 18152: {'lr': 0.0004854494159434135, 'samples': 9294336, 'steps': 18152, 'loss/train': 0.919468879699707}
-03/04/2022 10:46:57 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/04/2022 10:47:02 - INFO - codeparrot_training - Step 18153: {'lr': 0.0004854476318677272, 'samples': 9294848, 'steps': 18153, 'loss/train': 1.643168330192566}
-03/04/2022 10:47:05 - INFO - codeparrot_training - Step 18154: {'lr': 0.00048544584768595185, 'samples': 9295360, 'steps': 18154, 'loss/train': 1.4010717868804932}
-03/04/2022 10:47:06 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/04/2022 10:47:10 - INFO - codeparrot_training - Step 18155: {'lr': 0.00048544406339808823, 'samples': 9295872, 'steps': 18155, 'loss/train': 1.7568873167037964}
-03/04/2022 10:47:13 - INFO - codeparrot_training - Step 18156: {'lr': 0.00048544227900413706, 'samples': 9296384, 'steps': 18156, 'loss/train': 2.4814627170562744}
-03/04/2022 10:47:15 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/04/2022 10:47:18 - INFO - codeparrot_training - Step 18157: {'lr': 0.0004854404945040993, 'samples': 9296896, 'steps': 18157, 'loss/train': 2.220127582550049}
-03/04/2022 10:47:21 - INFO - codeparrot_training - Step 18158: {'lr': 0.0004854387098979757, 'samples': 9297408, 'steps': 18158, 'loss/train': 2.0150656700134277}
-03/04/2022 10:47:23 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 10:47:27 - INFO - codeparrot_training - Step 18159: {'lr': 0.000485436925185767, 'samples': 9297920, 'steps': 18159, 'loss/train': 2.4550116062164307}
-03/04/2022 10:47:30 - INFO - codeparrot_training - Step 18160: {'lr': 0.00048543514036747404, 'samples': 9298432, 'steps': 18160, 'loss/train': 1.6928722858428955}
-03/04/2022 10:47:32 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 10:47:35 - INFO - codeparrot_training - Step 18161: {'lr': 0.00048543335544309776, 'samples': 9298944, 'steps': 18161, 'loss/train': 1.3122540712356567}
-03/04/2022 10:47:38 - INFO - codeparrot_training - Step 18162: {'lr': 0.00048543157041263876, 'samples': 9299456, 'steps': 18162, 'loss/train': 2.782217264175415}
-03/04/2022 10:47:40 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/04/2022 10:47:44 - INFO - codeparrot_training - Step 18163: {'lr': 0.0004854297852760979, 'samples': 9299968, 'steps': 18163, 'loss/train': 1.5713459253311157}
-03/04/2022 10:47:47 - INFO - codeparrot_training - Step 18164: {'lr': 0.000485428000033476, 'samples': 9300480, 'steps': 18164, 'loss/train': 1.82054603099823}
-03/04/2022 10:47:48 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 10:47:52 - INFO - codeparrot_training - Step 18165: {'lr': 0.00048542621468477393, 'samples': 9300992, 'steps': 18165, 'loss/train': 2.9185140132904053}
-03/04/2022 10:47:55 - INFO - codeparrot_training - Step 18166: {'lr': 0.0004854244292299924, 'samples': 9301504, 'steps': 18166, 'loss/train': 1.570572853088379}
-03/04/2022 10:47:57 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 10:48:01 - INFO - codeparrot_training - Step 18167: {'lr': 0.0004854226436691323, 'samples': 9302016, 'steps': 18167, 'loss/train': 2.3989386558532715}
-03/04/2022 10:48:04 - INFO - codeparrot_training - Step 18168: {'lr': 0.0004854208580021944, 'samples': 9302528, 'steps': 18168, 'loss/train': 2.2819504737854004}
-03/04/2022 10:48:05 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 10:48:09 - INFO - codeparrot_training - Step 18169: {'lr': 0.00048541907222917946, 'samples': 9303040, 'steps': 18169, 'loss/train': 2.2821881771087646}
-03/04/2022 10:48:12 - INFO - codeparrot_training - Step 18170: {'lr': 0.0004854172863500883, 'samples': 9303552, 'steps': 18170, 'loss/train': 1.4971988201141357}
-03/04/2022 10:48:14 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/04/2022 10:48:17 - INFO - codeparrot_training - Step 18171: {'lr': 0.00048541550036492175, 'samples': 9304064, 'steps': 18171, 'loss/train': 1.3860183954238892}
-03/04/2022 10:48:21 - INFO - codeparrot_training - Step 18172: {'lr': 0.00048541371427368064, 'samples': 9304576, 'steps': 18172, 'loss/train': 2.343593120574951}
-03/04/2022 10:48:22 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 10:48:26 - INFO - codeparrot_training - Step 18173: {'lr': 0.0004854119280763657, 'samples': 9305088, 'steps': 18173, 'loss/train': 1.435987114906311}
-03/04/2022 10:48:29 - INFO - codeparrot_training - Step 18174: {'lr': 0.00048541014177297783, 'samples': 9305600, 'steps': 18174, 'loss/train': 2.1377627849578857}
-03/04/2022 10:48:30 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/04/2022 10:48:34 - INFO - codeparrot_training - Step 18175: {'lr': 0.0004854083553635178, 'samples': 9306112, 'steps': 18175, 'loss/train': 0.17470578849315643}
-03/04/2022 10:48:37 - INFO - codeparrot_training - Step 18176: {'lr': 0.00048540656884798626, 'samples': 9306624, 'steps': 18176, 'loss/train': 1.5009955167770386}
-03/04/2022 10:48:39 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/04/2022 10:48:43 - INFO - codeparrot_training - Step 18177: {'lr': 0.0004854047822263843, 'samples': 9307136, 'steps': 18177, 'loss/train': 2.6751229763031006}
-03/04/2022 10:48:46 - INFO - codeparrot_training - Step 18178: {'lr': 0.00048540299549871256, 'samples': 9307648, 'steps': 18178, 'loss/train': 1.7673426866531372}
-03/04/2022 10:48:47 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 10:48:51 - INFO - codeparrot_training - Step 18179: {'lr': 0.0004854012086649718, 'samples': 9308160, 'steps': 18179, 'loss/train': 1.6755092144012451}
-03/04/2022 10:48:54 - INFO - codeparrot_training - Step 18180: {'lr': 0.00048539942172516295, 'samples': 9308672, 'steps': 18180, 'loss/train': 1.1478462219238281}
-03/04/2022 10:48:55 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/04/2022 10:48:59 - INFO - codeparrot_training - Step 18181: {'lr': 0.00048539763467928665, 'samples': 9309184, 'steps': 18181, 'loss/train': 1.398455023765564}
-03/04/2022 10:49:03 - INFO - codeparrot_training - Step 18182: {'lr': 0.0004853958475273439, 'samples': 9309696, 'steps': 18182, 'loss/train': 2.507258176803589}
-03/04/2022 10:49:04 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/04/2022 10:49:08 - INFO - codeparrot_training - Step 18183: {'lr': 0.0004853940602693354, 'samples': 9310208, 'steps': 18183, 'loss/train': 2.286450147628784}
-03/04/2022 10:49:11 - INFO - codeparrot_training - Step 18184: {'lr': 0.00048539227290526194, 'samples': 9310720, 'steps': 18184, 'loss/train': 2.0574443340301514}
-03/04/2022 10:49:12 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/04/2022 10:49:16 - INFO - codeparrot_training - Step 18185: {'lr': 0.00048539048543512443, 'samples': 9311232, 'steps': 18185, 'loss/train': 2.2459826469421387}
-03/04/2022 10:49:19 - INFO - codeparrot_training - Step 18186: {'lr': 0.0004853886978589235, 'samples': 9311744, 'steps': 18186, 'loss/train': 2.054753065109253}
-03/04/2022 10:49:20 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/04/2022 10:49:25 - INFO - codeparrot_training - Step 18187: {'lr': 0.0004853869101766601, 'samples': 9312256, 'steps': 18187, 'loss/train': 2.14632248878479}
-03/04/2022 10:49:28 - INFO - codeparrot_training - Step 18188: {'lr': 0.000485385122388335, 'samples': 9312768, 'steps': 18188, 'loss/train': 1.4769386053085327}
-03/04/2022 10:49:29 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 10:49:33 - INFO - codeparrot_training - Step 18189: {'lr': 0.000485383334493949, 'samples': 9313280, 'steps': 18189, 'loss/train': 2.614997625350952}
-03/04/2022 10:49:36 - INFO - codeparrot_training - Step 18190: {'lr': 0.00048538154649350286, 'samples': 9313792, 'steps': 18190, 'loss/train': 2.3883473873138428}
-03/04/2022 10:49:37 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/04/2022 10:49:42 - INFO - codeparrot_training - Step 18191: {'lr': 0.00048537975838699744, 'samples': 9314304, 'steps': 18191, 'loss/train': 1.9786314964294434}
-03/04/2022 10:49:45 - INFO - codeparrot_training - Step 18192: {'lr': 0.0004853779701744335, 'samples': 9314816, 'steps': 18192, 'loss/train': 3.294447660446167}
-03/04/2022 10:49:46 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/04/2022 10:49:50 - INFO - codeparrot_training - Step 18193: {'lr': 0.000485376181855812, 'samples': 9315328, 'steps': 18193, 'loss/train': 1.499484896659851}
-03/04/2022 10:49:53 - INFO - codeparrot_training - Step 18194: {'lr': 0.00048537439343113354, 'samples': 9315840, 'steps': 18194, 'loss/train': 1.5188711881637573}
-03/04/2022 10:49:54 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 10:49:58 - INFO - codeparrot_training - Step 18195: {'lr': 0.000485372604900399, 'samples': 9316352, 'steps': 18195, 'loss/train': 1.8748955726623535}
-03/04/2022 10:50:01 - INFO - codeparrot_training - Step 18196: {'lr': 0.0004853708162636092, 'samples': 9316864, 'steps': 18196, 'loss/train': 1.8775769472122192}
-03/04/2022 10:50:02 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/04/2022 10:50:07 - INFO - codeparrot_training - Step 18197: {'lr': 0.00048536902752076494, 'samples': 9317376, 'steps': 18197, 'loss/train': 1.6920803785324097}
-03/04/2022 10:50:10 - INFO - codeparrot_training - Step 18198: {'lr': 0.00048536723867186705, 'samples': 9317888, 'steps': 18198, 'loss/train': 1.82218337059021}
-03/04/2022 10:50:11 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/04/2022 10:50:15 - INFO - codeparrot_training - Step 18199: {'lr': 0.0004853654497169163, 'samples': 9318400, 'steps': 18199, 'loss/train': 1.3713641166687012}
-03/04/2022 10:50:18 - INFO - codeparrot_training - Step 18200: {'lr': 0.00048536366065591354, 'samples': 9318912, 'steps': 18200, 'loss/train': 2.632209062576294}
-03/04/2022 10:50:19 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 10:50:24 - INFO - codeparrot_training - Step 18201: {'lr': 0.00048536187148885956, 'samples': 9319424, 'steps': 18201, 'loss/train': 1.1285573244094849}
-03/04/2022 10:50:27 - INFO - codeparrot_training - Step 18202: {'lr': 0.0004853600822157551, 'samples': 9319936, 'steps': 18202, 'loss/train': 1.556025743484497}
-03/04/2022 10:50:28 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 10:50:32 - INFO - codeparrot_training - Step 18203: {'lr': 0.000485358292836601, 'samples': 9320448, 'steps': 18203, 'loss/train': 1.3551188707351685}
-03/04/2022 10:50:35 - INFO - codeparrot_training - Step 18204: {'lr': 0.0004853565033513982, 'samples': 9320960, 'steps': 18204, 'loss/train': 1.5533242225646973}
-03/04/2022 10:50:36 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/04/2022 10:50:40 - INFO - codeparrot_training - Step 18205: {'lr': 0.0004853547137601473, 'samples': 9321472, 'steps': 18205, 'loss/train': 2.388479709625244}
-03/04/2022 10:50:44 - INFO - codeparrot_training - Step 18206: {'lr': 0.0004853529240628493, 'samples': 9321984, 'steps': 18206, 'loss/train': 0.753523051738739}
-03/04/2022 10:50:44 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/04/2022 10:50:49 - INFO - codeparrot_training - Step 18207: {'lr': 0.00048535113425950474, 'samples': 9322496, 'steps': 18207, 'loss/train': 2.4384591579437256}
-03/04/2022 10:50:52 - INFO - codeparrot_training - Step 18208: {'lr': 0.0004853493443501147, 'samples': 9323008, 'steps': 18208, 'loss/train': 1.854074478149414}
-03/04/2022 10:50:52 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/04/2022 10:50:57 - INFO - codeparrot_training - Step 18209: {'lr': 0.0004853475543346798, 'samples': 9323520, 'steps': 18209, 'loss/train': 2.5852653980255127}
-03/04/2022 10:51:00 - INFO - codeparrot_training - Step 18210: {'lr': 0.000485345764213201, 'samples': 9324032, 'steps': 18210, 'loss/train': 1.6585125923156738}
-03/04/2022 10:51:01 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/04/2022 10:51:06 - INFO - codeparrot_training - Step 18211: {'lr': 0.00048534397398567895, 'samples': 9324544, 'steps': 18211, 'loss/train': 1.8183873891830444}
-03/04/2022 10:51:09 - INFO - codeparrot_training - Step 18212: {'lr': 0.00048534218365211456, 'samples': 9325056, 'steps': 18212, 'loss/train': 1.7596406936645508}
-03/04/2022 10:51:09 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/04/2022 10:51:14 - INFO - codeparrot_training - Step 18213: {'lr': 0.0004853403932125087, 'samples': 9325568, 'steps': 18213, 'loss/train': 1.411900281906128}
-03/04/2022 10:51:17 - INFO - codeparrot_training - Step 18214: {'lr': 0.00048533860266686203, 'samples': 9326080, 'steps': 18214, 'loss/train': 1.0179402828216553}
-03/04/2022 10:51:18 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/04/2022 10:51:23 - INFO - codeparrot_training - Step 18215: {'lr': 0.0004853368120151754, 'samples': 9326592, 'steps': 18215, 'loss/train': 2.0289433002471924}
-03/04/2022 10:51:26 - INFO - codeparrot_training - Step 18216: {'lr': 0.00048533502125744967, 'samples': 9327104, 'steps': 18216, 'loss/train': 1.7340096235275269}
-03/04/2022 10:51:27 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/04/2022 10:51:31 - INFO - codeparrot_training - Step 18217: {'lr': 0.0004853332303936856, 'samples': 9327616, 'steps': 18217, 'loss/train': 1.9724284410476685}
-03/04/2022 10:51:34 - INFO - codeparrot_training - Step 18218: {'lr': 0.000485331439423884, 'samples': 9328128, 'steps': 18218, 'loss/train': 0.6834306120872498}
-03/04/2022 10:51:34 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/04/2022 10:51:39 - INFO - codeparrot_training - Step 18219: {'lr': 0.00048532964834804566, 'samples': 9328640, 'steps': 18219, 'loss/train': 1.5619028806686401}
-03/04/2022 10:51:43 - INFO - codeparrot_training - Step 18220: {'lr': 0.00048532785716617145, 'samples': 9329152, 'steps': 18220, 'loss/train': 2.102036714553833}
-03/04/2022 10:51:43 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 10:51:48 - INFO - codeparrot_training - Step 18221: {'lr': 0.0004853260658782621, 'samples': 9329664, 'steps': 18221, 'loss/train': 1.6399744749069214}
-03/04/2022 10:51:51 - INFO - codeparrot_training - Step 18222: {'lr': 0.0004853242744843185, 'samples': 9330176, 'steps': 18222, 'loss/train': 1.8537662029266357}
-03/04/2022 10:51:51 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/04/2022 10:51:56 - INFO - codeparrot_training - Step 18223: {'lr': 0.0004853224829843414, 'samples': 9330688, 'steps': 18223, 'loss/train': 1.5931265354156494}
-03/04/2022 10:52:00 - INFO - codeparrot_training - Step 18224: {'lr': 0.00048532069137833156, 'samples': 9331200, 'steps': 18224, 'loss/train': 2.2442336082458496}
-03/04/2022 10:52:00 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/04/2022 10:52:05 - INFO - codeparrot_training - Step 18225: {'lr': 0.00048531889966628997, 'samples': 9331712, 'steps': 18225, 'loss/train': 1.6392074823379517}
-03/04/2022 10:52:08 - INFO - codeparrot_training - Step 18226: {'lr': 0.00048531710784821726, 'samples': 9332224, 'steps': 18226, 'loss/train': 1.8301458358764648}
-03/04/2022 10:52:09 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/04/2022 10:52:14 - INFO - codeparrot_training - Step 18227: {'lr': 0.0004853153159241143, 'samples': 9332736, 'steps': 18227, 'loss/train': 2.495155096054077}
-03/04/2022 10:52:17 - INFO - codeparrot_training - Step 18228: {'lr': 0.0004853135238939818, 'samples': 9333248, 'steps': 18228, 'loss/train': 2.1819264888763428}
-03/04/2022 10:52:18 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/04/2022 10:52:23 - INFO - codeparrot_training - Step 18229: {'lr': 0.0004853117317578207, 'samples': 9333760, 'steps': 18229, 'loss/train': 1.3795888423919678}
-03/04/2022 10:52:26 - INFO - codeparrot_training - Step 18230: {'lr': 0.00048530993951563186, 'samples': 9334272, 'steps': 18230, 'loss/train': 2.9523425102233887}
-03/04/2022 10:52:27 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/04/2022 10:52:31 - INFO - codeparrot_training - Step 18231: {'lr': 0.0004853081471674159, 'samples': 9334784, 'steps': 18231, 'loss/train': 2.0674586296081543}
-03/04/2022 10:52:34 - INFO - codeparrot_training - Step 18232: {'lr': 0.00048530635471317373, 'samples': 9335296, 'steps': 18232, 'loss/train': 2.2321128845214844}
-03/04/2022 10:52:35 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/04/2022 10:52:39 - INFO - codeparrot_training - Step 18233: {'lr': 0.0004853045621529062, 'samples': 9335808, 'steps': 18233, 'loss/train': 2.2057061195373535}
-03/04/2022 10:52:42 - INFO - codeparrot_training - Step 18234: {'lr': 0.000485302769486614, 'samples': 9336320, 'steps': 18234, 'loss/train': 1.205553412437439}
-03/04/2022 10:52:43 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/04/2022 10:52:48 - INFO - codeparrot_training - Step 18235: {'lr': 0.000485300976714298, 'samples': 9336832, 'steps': 18235, 'loss/train': 2.614043951034546}
-03/04/2022 10:52:51 - INFO - codeparrot_training - Step 18236: {'lr': 0.00048529918383595906, 'samples': 9337344, 'steps': 18236, 'loss/train': 2.301786422729492}
-03/04/2022 10:52:52 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/04/2022 10:52:56 - INFO - codeparrot_training - Step 18237: {'lr': 0.0004852973908515979, 'samples': 9337856, 'steps': 18237, 'loss/train': 2.196226119995117}
-03/04/2022 10:52:59 - INFO - codeparrot_training - Step 18238: {'lr': 0.0004852955977612154, 'samples': 9338368, 'steps': 18238, 'loss/train': 1.836904525756836}
-03/04/2022 10:53:00 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/04/2022 10:53:05 - INFO - codeparrot_training - Step 18239: {'lr': 0.0004852938045648123, 'samples': 9338880, 'steps': 18239, 'loss/train': 2.1827328205108643}
-03/04/2022 10:53:08 - INFO - codeparrot_training - Step 18240: {'lr': 0.0004852920112623895, 'samples': 9339392, 'steps': 18240, 'loss/train': 1.7151637077331543}
-03/04/2022 10:53:09 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/04/2022 10:53:13 - INFO - codeparrot_training - Step 18241: {'lr': 0.00048529021785394765, 'samples': 9339904, 'steps': 18241, 'loss/train': 2.133742570877075}
-03/04/2022 10:53:16 - INFO - codeparrot_training - Step 18242: {'lr': 0.00048528842433948776, 'samples': 9340416, 'steps': 18242, 'loss/train': 2.045778512954712}
-03/04/2022 10:53:17 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/04/2022 10:53:21 - INFO - codeparrot_training - Step 18243: {'lr': 0.00048528663071901047, 'samples': 9340928, 'steps': 18243, 'loss/train': 1.5479552745819092}
-03/04/2022 10:53:24 - INFO - codeparrot_training - Step 18244: {'lr': 0.0004852848369925167, 'samples': 9341440, 'steps': 18244, 'loss/train': 2.0801334381103516}
-03/04/2022 10:53:25 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/04/2022 10:53:30 - INFO - codeparrot_training - Step 18245: {'lr': 0.00048528304316000723, 'samples': 9341952, 'steps': 18245, 'loss/train': 2.0605545043945312}
-03/04/2022 10:53:33 - INFO - codeparrot_training - Step 18246: {'lr': 0.0004852812492214828, 'samples': 9342464, 'steps': 18246, 'loss/train': 2.2233240604400635}
-03/04/2022 10:53:34 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/04/2022 10:53:38 - INFO - codeparrot_training - Step 18247: {'lr': 0.0004852794551769443, 'samples': 9342976, 'steps': 18247, 'loss/train': 1.9782811403274536}
-03/04/2022 10:53:41 - INFO - codeparrot_training - Step 18248: {'lr': 0.0004852776610263925, 'samples': 9343488, 'steps': 18248, 'loss/train': 2.9322197437286377}
-03/04/2022 10:53:42 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/04/2022 10:53:47 - INFO - codeparrot_training - Step 18249: {'lr': 0.0004852758667698282, 'samples': 9344000, 'steps': 18249, 'loss/train': 2.0607337951660156}
-03/04/2022 10:53:50 - INFO - codeparrot_training - Step 18250: {'lr': 0.00048527407240725223, 'samples': 9344512, 'steps': 18250, 'loss/train': 1.9452424049377441}
-03/04/2022 10:53:50 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/04/2022 10:53:55 - INFO - codeparrot_training - Step 18251: {'lr': 0.0004852722779386654, 'samples': 9345024, 'steps': 18251, 'loss/train': 1.723856806755066}
-03/04/2022 10:53:58 - INFO - codeparrot_training - Step 18252: {'lr': 0.00048527048336406855, 'samples': 9345536, 'steps': 18252, 'loss/train': 2.221266984939575}
-03/04/2022 10:53:59 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/04/2022 10:54:03 - INFO - codeparrot_training - Step 18253: {'lr': 0.00048526868868346243, 'samples': 9346048, 'steps': 18253, 'loss/train': 1.8505656719207764}
-03/04/2022 10:54:07 - INFO - codeparrot_training - Step 18254: {'lr': 0.0004852668938968478, 'samples': 9346560, 'steps': 18254, 'loss/train': 1.4746960401535034}
-03/04/2022 10:54:07 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/04/2022 10:54:12 - INFO - codeparrot_training - Step 18255: {'lr': 0.0004852650990042256, 'samples': 9347072, 'steps': 18255, 'loss/train': 1.4613163471221924}
-03/04/2022 10:54:15 - INFO - codeparrot_training - Step 18256: {'lr': 0.0004852633040055966, 'samples': 9347584, 'steps': 18256, 'loss/train': 0.9769079089164734}
-03/04/2022 10:54:15 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/04/2022 10:54:20 - INFO - codeparrot_training - Step 18257: {'lr': 0.00048526150890096153, 'samples': 9348096, 'steps': 18257, 'loss/train': 1.9854415655136108}
-03/04/2022 10:54:23 - INFO - codeparrot_training - Step 18258: {'lr': 0.0004852597136903213, 'samples': 9348608, 'steps': 18258, 'loss/train': 1.7607790231704712}
-03/04/2022 10:54:24 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 10:54:29 - INFO - codeparrot_training - Step 18259: {'lr': 0.0004852579183736766, 'samples': 9349120, 'steps': 18259, 'loss/train': 2.0394575595855713}
-03/04/2022 10:54:32 - INFO - codeparrot_training - Step 18260: {'lr': 0.00048525612295102836, 'samples': 9349632, 'steps': 18260, 'loss/train': 2.3096461296081543}
-03/04/2022 10:54:32 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/04/2022 10:54:37 - INFO - codeparrot_training - Step 18261: {'lr': 0.00048525432742237736, 'samples': 9350144, 'steps': 18261, 'loss/train': 2.093048334121704}
-03/04/2022 10:54:41 - INFO - codeparrot_training - Step 18262: {'lr': 0.00048525253178772435, 'samples': 9350656, 'steps': 18262, 'loss/train': 1.3561371564865112}
-03/04/2022 10:54:41 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/04/2022 10:54:46 - INFO - codeparrot_training - Step 18263: {'lr': 0.0004852507360470702, 'samples': 9351168, 'steps': 18263, 'loss/train': 2.1919522285461426}
-03/04/2022 10:54:49 - INFO - codeparrot_training - Step 18264: {'lr': 0.0004852489402004157, 'samples': 9351680, 'steps': 18264, 'loss/train': 2.740966796875}
-03/04/2022 10:54:49 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 10:54:55 - INFO - codeparrot_training - Step 18265: {'lr': 0.0004852471442477617, 'samples': 9352192, 'steps': 18265, 'loss/train': 2.069730758666992}
-03/04/2022 10:54:58 - INFO - codeparrot_training - Step 18266: {'lr': 0.0004852453481891089, 'samples': 9352704, 'steps': 18266, 'loss/train': 2.016751527786255}
-03/04/2022 10:54:58 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/04/2022 10:55:03 - INFO - codeparrot_training - Step 18267: {'lr': 0.00048524355202445827, 'samples': 9353216, 'steps': 18267, 'loss/train': 1.914576530456543}
-03/04/2022 10:55:06 - INFO - codeparrot_training - Step 18268: {'lr': 0.0004852417557538104, 'samples': 9353728, 'steps': 18268, 'loss/train': 1.8839232921600342}
-03/04/2022 10:55:07 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 10:55:12 - INFO - codeparrot_training - Step 18269: {'lr': 0.00048523995937716625, 'samples': 9354240, 'steps': 18269, 'loss/train': 1.947262167930603}
-03/04/2022 10:55:15 - INFO - codeparrot_training - Step 18270: {'lr': 0.0004852381628945267, 'samples': 9354752, 'steps': 18270, 'loss/train': 1.3263734579086304}
-03/04/2022 10:55:15 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/04/2022 10:55:20 - INFO - codeparrot_training - Step 18271: {'lr': 0.0004852363663058924, 'samples': 9355264, 'steps': 18271, 'loss/train': 1.7802315950393677}
-03/04/2022 10:55:23 - INFO - codeparrot_training - Step 18272: {'lr': 0.0004852345696112642, 'samples': 9355776, 'steps': 18272, 'loss/train': 2.2371175289154053}
-03/04/2022 10:55:23 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 10:55:28 - INFO - codeparrot_training - Step 18273: {'lr': 0.00048523277281064295, 'samples': 9356288, 'steps': 18273, 'loss/train': 1.3925259113311768}
-03/04/2022 10:55:32 - INFO - codeparrot_training - Step 18274: {'lr': 0.0004852309759040294, 'samples': 9356800, 'steps': 18274, 'loss/train': 2.0915920734405518}
-03/04/2022 10:55:32 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/04/2022 10:55:37 - INFO - codeparrot_training - Step 18275: {'lr': 0.00048522917889142446, 'samples': 9357312, 'steps': 18275, 'loss/train': 0.8720462918281555}
-03/04/2022 10:55:40 - INFO - codeparrot_training - Step 18276: {'lr': 0.00048522738177282887, 'samples': 9357824, 'steps': 18276, 'loss/train': 1.1411646604537964}
-03/04/2022 10:55:40 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/04/2022 10:55:45 - INFO - codeparrot_training - Step 18277: {'lr': 0.0004852255845482435, 'samples': 9358336, 'steps': 18277, 'loss/train': 1.9095391035079956}
-03/04/2022 10:55:48 - INFO - codeparrot_training - Step 18278: {'lr': 0.0004852237872176691, 'samples': 9358848, 'steps': 18278, 'loss/train': 2.213942766189575}
-03/04/2022 10:55:48 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/04/2022 10:55:54 - INFO - codeparrot_training - Step 18279: {'lr': 0.00048522198978110645, 'samples': 9359360, 'steps': 18279, 'loss/train': 1.8118561506271362}
-03/04/2022 10:55:57 - INFO - codeparrot_training - Step 18280: {'lr': 0.0004852201922385564, 'samples': 9359872, 'steps': 18280, 'loss/train': 1.664801836013794}
-03/04/2022 10:55:57 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 10:56:02 - INFO - codeparrot_training - Step 18281: {'lr': 0.00048521839459001977, 'samples': 9360384, 'steps': 18281, 'loss/train': 1.5844284296035767}
-03/04/2022 10:56:06 - INFO - codeparrot_training - Step 18282: {'lr': 0.0004852165968354973, 'samples': 9360896, 'steps': 18282, 'loss/train': 1.729973316192627}
-03/04/2022 10:56:06 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 10:56:11 - INFO - codeparrot_training - Step 18283: {'lr': 0.00048521479897499, 'samples': 9361408, 'steps': 18283, 'loss/train': 1.558517575263977}
-03/04/2022 10:56:14 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 10:56:16 - INFO - codeparrot_training - Step 18284: {'lr': 0.0004852130010084984, 'samples': 9361920, 'steps': 18284, 'loss/train': 1.6576042175292969}
-03/04/2022 10:56:19 - INFO - codeparrot_training - Step 18285: {'lr': 0.0004852112029360235, 'samples': 9362432, 'steps': 18285, 'loss/train': 1.002662181854248}
-03/04/2022 10:56:22 - INFO - codeparrot_training - Step 18286: {'lr': 0.0004852094047575661, 'samples': 9362944, 'steps': 18286, 'loss/train': 1.1213048696517944}
-03/04/2022 10:56:22 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/04/2022 10:56:28 - INFO - codeparrot_training - Step 18287: {'lr': 0.00048520760647312696, 'samples': 9363456, 'steps': 18287, 'loss/train': 2.043750524520874}
-03/04/2022 10:56:31 - INFO - codeparrot_training - Step 18288: {'lr': 0.00048520580808270687, 'samples': 9363968, 'steps': 18288, 'loss/train': 1.9394551515579224}
-03/04/2022 10:56:31 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/04/2022 10:56:36 - INFO - codeparrot_training - Step 18289: {'lr': 0.0004852040095863067, 'samples': 9364480, 'steps': 18289, 'loss/train': 1.3327577114105225}
-03/04/2022 10:56:39 - INFO - codeparrot_training - Step 18290: {'lr': 0.0004852022109839273, 'samples': 9364992, 'steps': 18290, 'loss/train': 0.5110849142074585}
-03/04/2022 10:56:39 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 10:56:45 - INFO - codeparrot_training - Step 18291: {'lr': 0.0004852004122755693, 'samples': 9365504, 'steps': 18291, 'loss/train': 1.9804211854934692}
-03/04/2022 10:56:48 - INFO - codeparrot_training - Step 18292: {'lr': 0.00048519861346123363, 'samples': 9366016, 'steps': 18292, 'loss/train': 2.014268398284912}
-03/04/2022 10:56:48 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 10:56:53 - INFO - codeparrot_training - Step 18293: {'lr': 0.0004851968145409211, 'samples': 9366528, 'steps': 18293, 'loss/train': 1.0858033895492554}
-03/04/2022 10:56:56 - INFO - codeparrot_training - Step 18294: {'lr': 0.00048519501551463255, 'samples': 9367040, 'steps': 18294, 'loss/train': 1.7102940082550049}
-03/04/2022 10:56:57 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/04/2022 10:57:02 - INFO - codeparrot_training - Step 18295: {'lr': 0.0004851932163823688, 'samples': 9367552, 'steps': 18295, 'loss/train': 1.9881410598754883}
-03/04/2022 10:57:05 - INFO - codeparrot_training - Step 18296: {'lr': 0.0004851914171441305, 'samples': 9368064, 'steps': 18296, 'loss/train': 2.1276955604553223}
-03/04/2022 10:57:05 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/04/2022 10:57:10 - INFO - codeparrot_training - Step 18297: {'lr': 0.00048518961779991866, 'samples': 9368576, 'steps': 18297, 'loss/train': 1.192862868309021}
-03/04/2022 10:57:13 - INFO - codeparrot_training - Step 18298: {'lr': 0.00048518781834973405, 'samples': 9369088, 'steps': 18298, 'loss/train': 2.3407680988311768}
-03/04/2022 10:57:14 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/04/2022 10:57:18 - INFO - codeparrot_training - Step 18299: {'lr': 0.0004851860187935773, 'samples': 9369600, 'steps': 18299, 'loss/train': 1.3622851371765137}
-03/04/2022 10:57:22 - INFO - codeparrot_training - Step 18300: {'lr': 0.0004851842191314494, 'samples': 9370112, 'steps': 18300, 'loss/train': 2.1296513080596924}
-03/04/2022 10:57:22 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/04/2022 10:57:27 - INFO - codeparrot_training - Step 18301: {'lr': 0.0004851824193633512, 'samples': 9370624, 'steps': 18301, 'loss/train': 3.5405852794647217}
-03/04/2022 10:57:30 - INFO - codeparrot_training - Step 18302: {'lr': 0.00048518061948928337, 'samples': 9371136, 'steps': 18302, 'loss/train': 1.771193027496338}
-03/04/2022 10:57:30 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/04/2022 10:57:35 - INFO - codeparrot_training - Step 18303: {'lr': 0.0004851788195092468, 'samples': 9371648, 'steps': 18303, 'loss/train': 1.4726768732070923}
-03/04/2022 10:57:38 - INFO - codeparrot_training - Step 18304: {'lr': 0.00048517701942324225, 'samples': 9372160, 'steps': 18304, 'loss/train': 1.878865122795105}
-03/04/2022 10:57:39 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/04/2022 10:57:44 - INFO - codeparrot_training - Step 18305: {'lr': 0.00048517521923127063, 'samples': 9372672, 'steps': 18305, 'loss/train': 1.5493512153625488}
-03/04/2022 10:57:47 - INFO - codeparrot_training - Step 18306: {'lr': 0.00048517341893333267, 'samples': 9373184, 'steps': 18306, 'loss/train': 2.729825496673584}
-03/04/2022 10:57:47 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 10:57:52 - INFO - codeparrot_training - Step 18307: {'lr': 0.0004851716185294291, 'samples': 9373696, 'steps': 18307, 'loss/train': 1.8430007696151733}
-03/04/2022 10:57:55 - INFO - codeparrot_training - Step 18308: {'lr': 0.00048516981801956097, 'samples': 9374208, 'steps': 18308, 'loss/train': 2.2501707077026367}
-03/04/2022 10:57:56 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/04/2022 10:58:00 - INFO - codeparrot_training - Step 18309: {'lr': 0.00048516801740372886, 'samples': 9374720, 'steps': 18309, 'loss/train': 2.4119529724121094}
-03/04/2022 10:58:04 - INFO - codeparrot_training - Step 18310: {'lr': 0.0004851662166819337, 'samples': 9375232, 'steps': 18310, 'loss/train': 1.8136041164398193}
-03/04/2022 10:58:04 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/04/2022 10:58:09 - INFO - codeparrot_training - Step 18311: {'lr': 0.00048516441585417624, 'samples': 9375744, 'steps': 18311, 'loss/train': 1.4453084468841553}
-03/04/2022 10:58:12 - INFO - codeparrot_training - Step 18312: {'lr': 0.0004851626149204573, 'samples': 9376256, 'steps': 18312, 'loss/train': 2.648723840713501}
-03/04/2022 10:58:13 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/04/2022 10:58:17 - INFO - codeparrot_training - Step 18313: {'lr': 0.0004851608138807778, 'samples': 9376768, 'steps': 18313, 'loss/train': 1.7889841794967651}
-03/04/2022 10:58:21 - INFO - codeparrot_training - Step 18314: {'lr': 0.0004851590127351384, 'samples': 9377280, 'steps': 18314, 'loss/train': 2.186408281326294}
-03/04/2022 10:58:21 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/04/2022 10:58:26 - INFO - codeparrot_training - Step 18315: {'lr': 0.0004851572114835401, 'samples': 9377792, 'steps': 18315, 'loss/train': 1.7851719856262207}
-03/04/2022 10:58:29 - INFO - codeparrot_training - Step 18316: {'lr': 0.0004851554101259834, 'samples': 9378304, 'steps': 18316, 'loss/train': 1.9697951078414917}
-03/04/2022 10:58:30 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/04/2022 10:58:34 - INFO - codeparrot_training - Step 18317: {'lr': 0.00048515360866246943, 'samples': 9378816, 'steps': 18317, 'loss/train': 1.8904918432235718}
-03/04/2022 10:58:37 - INFO - codeparrot_training - Step 18318: {'lr': 0.00048515180709299884, 'samples': 9379328, 'steps': 18318, 'loss/train': 1.726677656173706}
-03/04/2022 10:58:38 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 10:58:43 - INFO - codeparrot_training - Step 18319: {'lr': 0.0004851500054175725, 'samples': 9379840, 'steps': 18319, 'loss/train': 1.6175761222839355}
-03/04/2022 10:58:46 - INFO - codeparrot_training - Step 18320: {'lr': 0.00048514820363619116, 'samples': 9380352, 'steps': 18320, 'loss/train': 1.8298180103302002}
-03/04/2022 10:58:46 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 10:58:51 - INFO - codeparrot_training - Step 18321: {'lr': 0.0004851464017488556, 'samples': 9380864, 'steps': 18321, 'loss/train': 1.946031093597412}
-03/04/2022 10:58:55 - INFO - codeparrot_training - Step 18322: {'lr': 0.0004851445997555668, 'samples': 9381376, 'steps': 18322, 'loss/train': 1.415920615196228}
-03/04/2022 10:58:55 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 10:59:00 - INFO - codeparrot_training - Step 18323: {'lr': 0.00048514279765632547, 'samples': 9381888, 'steps': 18323, 'loss/train': 1.362214207649231}
-03/04/2022 10:59:03 - INFO - codeparrot_training - Step 18324: {'lr': 0.0004851409954511324, 'samples': 9382400, 'steps': 18324, 'loss/train': 1.3780734539031982}
-03/04/2022 10:59:03 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/04/2022 10:59:08 - INFO - codeparrot_training - Step 18325: {'lr': 0.0004851391931399884, 'samples': 9382912, 'steps': 18325, 'loss/train': 2.1429405212402344}
-03/04/2022 10:59:11 - INFO - codeparrot_training - Step 18326: {'lr': 0.0004851373907228943, 'samples': 9383424, 'steps': 18326, 'loss/train': 0.9744027853012085}
-03/04/2022 10:59:12 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/04/2022 10:59:17 - INFO - codeparrot_training - Step 18327: {'lr': 0.00048513558819985106, 'samples': 9383936, 'steps': 18327, 'loss/train': 2.1866867542266846}
-03/04/2022 10:59:20 - INFO - codeparrot_training - Step 18328: {'lr': 0.0004851337855708592, 'samples': 9384448, 'steps': 18328, 'loss/train': 1.52213716506958}
-03/04/2022 10:59:21 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 10:59:25 - INFO - codeparrot_training - Step 18329: {'lr': 0.0004851319828359198, 'samples': 9384960, 'steps': 18329, 'loss/train': 2.0765464305877686}
-03/04/2022 10:59:29 - INFO - codeparrot_training - Step 18330: {'lr': 0.0004851301799950334, 'samples': 9385472, 'steps': 18330, 'loss/train': 1.6254172325134277}
-03/04/2022 10:59:30 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/04/2022 10:59:34 - INFO - codeparrot_training - Step 18331: {'lr': 0.00048512837704820107, 'samples': 9385984, 'steps': 18331, 'loss/train': 0.7720240354537964}
-03/04/2022 10:59:37 - INFO - codeparrot_training - Step 18332: {'lr': 0.00048512657399542346, 'samples': 9386496, 'steps': 18332, 'loss/train': 1.239613652229309}
-03/04/2022 10:59:38 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 10:59:42 - INFO - codeparrot_training - Step 18333: {'lr': 0.0004851247708367015, 'samples': 9387008, 'steps': 18333, 'loss/train': 1.4806938171386719}
-03/04/2022 10:59:46 - INFO - codeparrot_training - Step 18334: {'lr': 0.000485122967572036, 'samples': 9387520, 'steps': 18334, 'loss/train': 2.7859201431274414}
-03/04/2022 10:59:46 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 10:59:51 - INFO - codeparrot_training - Step 18335: {'lr': 0.0004851211642014276, 'samples': 9388032, 'steps': 18335, 'loss/train': 1.7991938591003418}
-03/04/2022 10:59:54 - INFO - codeparrot_training - Step 18336: {'lr': 0.0004851193607248773, 'samples': 9388544, 'steps': 18336, 'loss/train': 1.8204762935638428}
-03/04/2022 10:59:54 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/04/2022 10:59:59 - INFO - codeparrot_training - Step 18337: {'lr': 0.00048511755714238585, 'samples': 9389056, 'steps': 18337, 'loss/train': 1.6833757162094116}
-03/04/2022 11:00:02 - INFO - codeparrot_training - Step 18338: {'lr': 0.0004851157534539541, 'samples': 9389568, 'steps': 18338, 'loss/train': 0.8949117660522461}
-03/04/2022 11:00:03 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 11:00:08 - INFO - codeparrot_training - Step 18339: {'lr': 0.0004851139496595827, 'samples': 9390080, 'steps': 18339, 'loss/train': 2.561525344848633}
-03/04/2022 11:00:11 - INFO - codeparrot_training - Step 18340: {'lr': 0.00048511214575927265, 'samples': 9390592, 'steps': 18340, 'loss/train': 1.8069894313812256}
-03/04/2022 11:00:11 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/04/2022 11:00:16 - INFO - codeparrot_training - Step 18341: {'lr': 0.0004851103417530247, 'samples': 9391104, 'steps': 18341, 'loss/train': 1.712579607963562}
-03/04/2022 11:00:19 - INFO - codeparrot_training - Step 18342: {'lr': 0.0004851085376408396, 'samples': 9391616, 'steps': 18342, 'loss/train': 2.138662576675415}
-03/04/2022 11:00:20 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 11:00:24 - INFO - codeparrot_training - Step 18343: {'lr': 0.0004851067334227183, 'samples': 9392128, 'steps': 18343, 'loss/train': 1.3638745546340942}
-03/04/2022 11:00:27 - INFO - codeparrot_training - Step 18344: {'lr': 0.0004851049290986615, 'samples': 9392640, 'steps': 18344, 'loss/train': 1.8900386095046997}
-03/04/2022 11:00:28 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/04/2022 11:00:33 - INFO - codeparrot_training - Step 18345: {'lr': 0.00048510312466867, 'samples': 9393152, 'steps': 18345, 'loss/train': 2.219289541244507}
-03/04/2022 11:00:36 - INFO - codeparrot_training - Step 18346: {'lr': 0.0004851013201327448, 'samples': 9393664, 'steps': 18346, 'loss/train': 0.6594041585922241}
-03/04/2022 11:00:36 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 11:00:41 - INFO - codeparrot_training - Step 18347: {'lr': 0.0004850995154908864, 'samples': 9394176, 'steps': 18347, 'loss/train': 1.8689993619918823}
-03/04/2022 11:00:44 - INFO - codeparrot_training - Step 18348: {'lr': 0.0004850977107430959, 'samples': 9394688, 'steps': 18348, 'loss/train': 2.0344364643096924}
-03/04/2022 11:00:45 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/04/2022 11:00:50 - INFO - codeparrot_training - Step 18349: {'lr': 0.000485095905889374, 'samples': 9395200, 'steps': 18349, 'loss/train': 2.2893478870391846}
-03/04/2022 11:00:53 - INFO - codeparrot_training - Step 18350: {'lr': 0.00048509410092972144, 'samples': 9395712, 'steps': 18350, 'loss/train': 2.0365936756134033}
-03/04/2022 11:00:53 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/04/2022 11:00:58 - INFO - codeparrot_training - Step 18351: {'lr': 0.0004850922958641392, 'samples': 9396224, 'steps': 18351, 'loss/train': 1.7240798473358154}
-03/04/2022 11:01:01 - INFO - codeparrot_training - Step 18352: {'lr': 0.0004850904906926279, 'samples': 9396736, 'steps': 18352, 'loss/train': 2.2109782695770264}
-03/04/2022 11:01:01 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/04/2022 11:01:06 - INFO - codeparrot_training - Step 18353: {'lr': 0.0004850886854151885, 'samples': 9397248, 'steps': 18353, 'loss/train': 1.5442615747451782}
-03/04/2022 11:01:10 - INFO - codeparrot_training - Step 18354: {'lr': 0.0004850868800318218, 'samples': 9397760, 'steps': 18354, 'loss/train': 1.3746986389160156}
-03/04/2022 11:01:10 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/04/2022 11:01:15 - INFO - codeparrot_training - Step 18355: {'lr': 0.00048508507454252846, 'samples': 9398272, 'steps': 18355, 'loss/train': 1.8537578582763672}
-03/04/2022 11:01:18 - INFO - codeparrot_training - Step 18356: {'lr': 0.00048508326894730955, 'samples': 9398784, 'steps': 18356, 'loss/train': 1.3993995189666748}
-03/04/2022 11:01:19 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/04/2022 11:01:23 - INFO - codeparrot_training - Step 18357: {'lr': 0.00048508146324616566, 'samples': 9399296, 'steps': 18357, 'loss/train': 2.464998483657837}
-03/04/2022 11:01:27 - INFO - codeparrot_training - Step 18358: {'lr': 0.0004850796574390977, 'samples': 9399808, 'steps': 18358, 'loss/train': 1.473577857017517}
-03/04/2022 11:01:27 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/04/2022 11:01:32 - INFO - codeparrot_training - Step 18359: {'lr': 0.0004850778515261065, 'samples': 9400320, 'steps': 18359, 'loss/train': 1.4236046075820923}
-03/04/2022 11:01:35 - INFO - codeparrot_training - Step 18360: {'lr': 0.0004850760455071929, 'samples': 9400832, 'steps': 18360, 'loss/train': 1.2305594682693481}
-03/04/2022 11:01:36 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 11:01:40 - INFO - codeparrot_training - Step 18361: {'lr': 0.0004850742393823576, 'samples': 9401344, 'steps': 18361, 'loss/train': 2.2984797954559326}
-03/04/2022 11:01:43 - INFO - codeparrot_training - Step 18362: {'lr': 0.0004850724331516014, 'samples': 9401856, 'steps': 18362, 'loss/train': 0.4427529573440552}
-03/04/2022 11:01:44 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 11:01:49 - INFO - codeparrot_training - Step 18363: {'lr': 0.0004850706268149253, 'samples': 9402368, 'steps': 18363, 'loss/train': 2.2801313400268555}
-03/04/2022 11:01:52 - INFO - codeparrot_training - Step 18364: {'lr': 0.00048506882037233, 'samples': 9402880, 'steps': 18364, 'loss/train': 1.8894996643066406}
-03/04/2022 11:01:57 - INFO - codeparrot_training - Step 18365: {'lr': 0.0004850670138238162, 'samples': 9403392, 'steps': 18365, 'loss/train': 2.2794344425201416}
-03/04/2022 11:02:00 - INFO - codeparrot_training - Step 18366: {'lr': 0.00048506520716938496, 'samples': 9403904, 'steps': 18366, 'loss/train': 1.8961193561553955}
-03/04/2022 11:02:01 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/04/2022 11:02:06 - INFO - codeparrot_training - Step 18367: {'lr': 0.00048506340040903697, 'samples': 9404416, 'steps': 18367, 'loss/train': 0.9867935180664062}
-03/04/2022 11:02:09 - INFO - codeparrot_training - Step 18368: {'lr': 0.00048506159354277294, 'samples': 9404928, 'steps': 18368, 'loss/train': 1.255003809928894}
-03/04/2022 11:02:10 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/04/2022 11:02:14 - INFO - codeparrot_training - Step 18369: {'lr': 0.00048505978657059385, 'samples': 9405440, 'steps': 18369, 'loss/train': 1.041564702987671}
-03/04/2022 11:02:17 - INFO - codeparrot_training - Step 18370: {'lr': 0.0004850579794925004, 'samples': 9405952, 'steps': 18370, 'loss/train': 0.7095953822135925}
-03/04/2022 11:02:18 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/04/2022 11:02:23 - INFO - codeparrot_training - Step 18371: {'lr': 0.0004850561723084935, 'samples': 9406464, 'steps': 18371, 'loss/train': 2.619865894317627}
-03/04/2022 11:02:26 - INFO - codeparrot_training - Step 18372: {'lr': 0.0004850543650185739, 'samples': 9406976, 'steps': 18372, 'loss/train': 2.142362117767334}
-03/04/2022 11:02:27 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/04/2022 11:02:31 - INFO - codeparrot_training - Step 18373: {'lr': 0.0004850525576227425, 'samples': 9407488, 'steps': 18373, 'loss/train': 3.424837589263916}
-03/04/2022 11:02:34 - INFO - codeparrot_training - Step 18374: {'lr': 0.000485050750121, 'samples': 9408000, 'steps': 18374, 'loss/train': 1.4887712001800537}
-03/04/2022 11:02:35 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/04/2022 11:02:39 - INFO - codeparrot_training - Step 18375: {'lr': 0.0004850489425133472, 'samples': 9408512, 'steps': 18375, 'loss/train': 1.8042188882827759}
-03/04/2022 11:02:43 - INFO - codeparrot_training - Step 18376: {'lr': 0.000485047134799785, 'samples': 9409024, 'steps': 18376, 'loss/train': 1.0195910930633545}
-03/04/2022 11:02:44 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/04/2022 11:02:48 - INFO - codeparrot_training - Step 18377: {'lr': 0.00048504532698031416, 'samples': 9409536, 'steps': 18377, 'loss/train': 2.890273094177246}
-03/04/2022 11:02:51 - INFO - codeparrot_training - Step 18378: {'lr': 0.0004850435190549356, 'samples': 9410048, 'steps': 18378, 'loss/train': 1.7224996089935303}
-03/04/2022 11:02:52 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 11:02:56 - INFO - codeparrot_training - Step 18379: {'lr': 0.00048504171102365, 'samples': 9410560, 'steps': 18379, 'loss/train': 2.611513376235962}
-03/04/2022 11:02:59 - INFO - codeparrot_training - Step 18380: {'lr': 0.0004850399028864583, 'samples': 9411072, 'steps': 18380, 'loss/train': 2.106030225753784}
-03/04/2022 11:03:01 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/04/2022 11:03:05 - INFO - codeparrot_training - Step 18381: {'lr': 0.0004850380946433611, 'samples': 9411584, 'steps': 18381, 'loss/train': 2.270951986312866}
-03/04/2022 11:03:08 - INFO - codeparrot_training - Step 18382: {'lr': 0.00048503628629435947, 'samples': 9412096, 'steps': 18382, 'loss/train': 1.838679313659668}
-03/04/2022 11:03:09 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/04/2022 11:03:13 - INFO - codeparrot_training - Step 18383: {'lr': 0.0004850344778394541, 'samples': 9412608, 'steps': 18383, 'loss/train': 1.0550923347473145}
-03/04/2022 11:03:16 - INFO - codeparrot_training - Step 18384: {'lr': 0.0004850326692786459, 'samples': 9413120, 'steps': 18384, 'loss/train': 1.6507469415664673}
-03/04/2022 11:03:18 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/04/2022 11:03:22 - INFO - codeparrot_training - Step 18385: {'lr': 0.00048503086061193546, 'samples': 9413632, 'steps': 18385, 'loss/train': 1.7794790267944336}
-03/04/2022 11:03:25 - INFO - codeparrot_training - Step 18386: {'lr': 0.0004850290518393238, 'samples': 9414144, 'steps': 18386, 'loss/train': 1.6199897527694702}
-03/04/2022 11:03:26 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 11:03:30 - INFO - codeparrot_training - Step 18387: {'lr': 0.0004850272429608117, 'samples': 9414656, 'steps': 18387, 'loss/train': 2.7739269733428955}
-03/04/2022 11:03:33 - INFO - codeparrot_training - Step 18388: {'lr': 0.0004850254339764, 'samples': 9415168, 'steps': 18388, 'loss/train': 2.6320977210998535}
-03/04/2022 11:03:34 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 11:03:38 - INFO - codeparrot_training - Step 18389: {'lr': 0.00048502362488608933, 'samples': 9415680, 'steps': 18389, 'loss/train': 1.6955331563949585}
-03/04/2022 11:03:42 - INFO - codeparrot_training - Step 18390: {'lr': 0.0004850218156898807, 'samples': 9416192, 'steps': 18390, 'loss/train': 2.1118922233581543}
-03/04/2022 11:03:42 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 11:03:47 - INFO - codeparrot_training - Step 18391: {'lr': 0.00048502000638777487, 'samples': 9416704, 'steps': 18391, 'loss/train': 2.3155555725097656}
-03/04/2022 11:03:50 - INFO - codeparrot_training - Step 18392: {'lr': 0.0004850181969797727, 'samples': 9417216, 'steps': 18392, 'loss/train': 2.1229631900787354}
-03/04/2022 11:03:51 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 11:03:55 - INFO - codeparrot_training - Step 18393: {'lr': 0.00048501638746587493, 'samples': 9417728, 'steps': 18393, 'loss/train': 0.9226692914962769}
-03/04/2022 11:03:58 - INFO - codeparrot_training - Step 18394: {'lr': 0.0004850145778460824, 'samples': 9418240, 'steps': 18394, 'loss/train': 2.2738592624664307}
-03/04/2022 11:04:00 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/04/2022 11:04:04 - INFO - codeparrot_training - Step 18395: {'lr': 0.00048501276812039585, 'samples': 9418752, 'steps': 18395, 'loss/train': 2.171638250350952}
-03/04/2022 11:04:07 - INFO - codeparrot_training - Step 18396: {'lr': 0.00048501095828881627, 'samples': 9419264, 'steps': 18396, 'loss/train': 2.60176157951355}
-03/04/2022 11:04:08 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/04/2022 11:04:12 - INFO - codeparrot_training - Step 18397: {'lr': 0.00048500914835134434, 'samples': 9419776, 'steps': 18397, 'loss/train': 2.1515607833862305}
-03/04/2022 11:04:15 - INFO - codeparrot_training - Step 18398: {'lr': 0.00048500733830798094, 'samples': 9420288, 'steps': 18398, 'loss/train': 2.244356870651245}
-03/04/2022 11:04:17 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/04/2022 11:04:21 - INFO - codeparrot_training - Step 18399: {'lr': 0.00048500552815872687, 'samples': 9420800, 'steps': 18399, 'loss/train': 1.870226263999939}
-03/04/2022 11:04:24 - INFO - codeparrot_training - Step 18400: {'lr': 0.0004850037179035829, 'samples': 9421312, 'steps': 18400, 'loss/train': 0.8520978689193726}
-03/04/2022 11:04:26 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/04/2022 11:04:29 - INFO - codeparrot_training - Step 18401: {'lr': 0.00048500190754254994, 'samples': 9421824, 'steps': 18401, 'loss/train': 2.917323350906372}
-03/04/2022 11:04:32 - INFO - codeparrot_training - Step 18402: {'lr': 0.00048500009707562865, 'samples': 9422336, 'steps': 18402, 'loss/train': 2.520568370819092}
-03/04/2022 11:04:34 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/04/2022 11:04:38 - INFO - codeparrot_training - Step 18403: {'lr': 0.00048499828650281994, 'samples': 9422848, 'steps': 18403, 'loss/train': 1.4298882484436035}
-03/04/2022 11:04:41 - INFO - codeparrot_training - Step 18404: {'lr': 0.00048499647582412475, 'samples': 9423360, 'steps': 18404, 'loss/train': 1.807638168334961}
-03/04/2022 11:04:43 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 11:04:46 - INFO - codeparrot_training - Step 18405: {'lr': 0.0004849946650395437, 'samples': 9423872, 'steps': 18405, 'loss/train': 2.1311452388763428}
-03/04/2022 11:04:49 - INFO - codeparrot_training - Step 18406: {'lr': 0.0004849928541490777, 'samples': 9424384, 'steps': 18406, 'loss/train': 2.3526368141174316}
-03/04/2022 11:04:51 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/04/2022 11:04:54 - INFO - codeparrot_training - Step 18407: {'lr': 0.0004849910431527275, 'samples': 9424896, 'steps': 18407, 'loss/train': 4.080538749694824}
-03/04/2022 11:04:58 - INFO - codeparrot_training - Step 18408: {'lr': 0.000484989232050494, 'samples': 9425408, 'steps': 18408, 'loss/train': 2.182673454284668}
-03/04/2022 11:04:59 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/04/2022 11:05:03 - INFO - codeparrot_training - Step 18409: {'lr': 0.00048498742084237796, 'samples': 9425920, 'steps': 18409, 'loss/train': 1.7661281824111938}
-03/04/2022 11:05:06 - INFO - codeparrot_training - Step 18410: {'lr': 0.00048498560952838025, 'samples': 9426432, 'steps': 18410, 'loss/train': 1.5193949937820435}
-03/04/2022 11:05:08 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/04/2022 11:05:11 - INFO - codeparrot_training - Step 18411: {'lr': 0.00048498379810850157, 'samples': 9426944, 'steps': 18411, 'loss/train': 1.077130675315857}
-03/04/2022 11:05:14 - INFO - codeparrot_training - Step 18412: {'lr': 0.0004849819865827429, 'samples': 9427456, 'steps': 18412, 'loss/train': 1.9507781267166138}
-03/04/2022 11:05:16 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/04/2022 11:05:20 - INFO - codeparrot_training - Step 18413: {'lr': 0.0004849801749511049, 'samples': 9427968, 'steps': 18413, 'loss/train': 1.5407238006591797}
-03/04/2022 11:05:23 - INFO - codeparrot_training - Step 18414: {'lr': 0.00048497836321358855, 'samples': 9428480, 'steps': 18414, 'loss/train': 1.251877784729004}
-03/04/2022 11:05:24 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/04/2022 11:05:28 - INFO - codeparrot_training - Step 18415: {'lr': 0.00048497655137019454, 'samples': 9428992, 'steps': 18415, 'loss/train': 2.5805718898773193}
-03/04/2022 11:05:31 - INFO - codeparrot_training - Step 18416: {'lr': 0.0004849747394209237, 'samples': 9429504, 'steps': 18416, 'loss/train': 1.6916395425796509}
-03/04/2022 11:05:33 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/04/2022 11:05:37 - INFO - codeparrot_training - Step 18417: {'lr': 0.00048497292736577685, 'samples': 9430016, 'steps': 18417, 'loss/train': 1.8639475107192993}
-03/04/2022 11:05:40 - INFO - codeparrot_training - Step 18418: {'lr': 0.0004849711152047549, 'samples': 9430528, 'steps': 18418, 'loss/train': 1.8788647651672363}
-03/04/2022 11:05:41 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/04/2022 11:05:45 - INFO - codeparrot_training - Step 18419: {'lr': 0.0004849693029378585, 'samples': 9431040, 'steps': 18419, 'loss/train': 1.8164551258087158}
-03/04/2022 11:05:48 - INFO - codeparrot_training - Step 18420: {'lr': 0.0004849674905650886, 'samples': 9431552, 'steps': 18420, 'loss/train': 2.2755930423736572}
-03/04/2022 11:05:50 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/04/2022 11:05:54 - INFO - codeparrot_training - Step 18421: {'lr': 0.000484965678086446, 'samples': 9432064, 'steps': 18421, 'loss/train': 2.435889959335327}
-03/04/2022 11:05:57 - INFO - codeparrot_training - Step 18422: {'lr': 0.0004849638655019315, 'samples': 9432576, 'steps': 18422, 'loss/train': 2.2917630672454834}
-03/04/2022 11:05:58 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/04/2022 11:06:02 - INFO - codeparrot_training - Step 18423: {'lr': 0.0004849620528115458, 'samples': 9433088, 'steps': 18423, 'loss/train': 1.7281819581985474}
-03/04/2022 11:06:05 - INFO - codeparrot_training - Step 18424: {'lr': 0.0004849602400152899, 'samples': 9433600, 'steps': 18424, 'loss/train': 1.268783450126648}
-03/04/2022 11:06:07 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/04/2022 11:06:11 - INFO - codeparrot_training - Step 18425: {'lr': 0.0004849584271131646, 'samples': 9434112, 'steps': 18425, 'loss/train': 1.215120792388916}
-03/04/2022 11:06:14 - INFO - codeparrot_training - Step 18426: {'lr': 0.00048495661410517056, 'samples': 9434624, 'steps': 18426, 'loss/train': 1.0621538162231445}
-03/04/2022 11:06:15 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/04/2022 11:06:19 - INFO - codeparrot_training - Step 18427: {'lr': 0.0004849548009913087, 'samples': 9435136, 'steps': 18427, 'loss/train': 1.845723032951355}
-03/04/2022 11:06:22 - INFO - codeparrot_training - Step 18428: {'lr': 0.00048495298777157994, 'samples': 9435648, 'steps': 18428, 'loss/train': 1.743212103843689}
-03/04/2022 11:06:24 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/04/2022 11:06:28 - INFO - codeparrot_training - Step 18429: {'lr': 0.0004849511744459849, 'samples': 9436160, 'steps': 18429, 'loss/train': 1.881903886795044}
-03/04/2022 11:06:31 - INFO - codeparrot_training - Step 18430: {'lr': 0.00048494936101452446, 'samples': 9436672, 'steps': 18430, 'loss/train': 2.280258893966675}
-03/04/2022 11:06:33 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 11:06:36 - INFO - codeparrot_training - Step 18431: {'lr': 0.00048494754747719954, 'samples': 9437184, 'steps': 18431, 'loss/train': 2.0006377696990967}
-03/04/2022 11:06:39 - INFO - codeparrot_training - Step 18432: {'lr': 0.00048494573383401084, 'samples': 9437696, 'steps': 18432, 'loss/train': 2.024935007095337}
-03/04/2022 11:06:42 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/04/2022 11:06:45 - INFO - codeparrot_training - Step 18433: {'lr': 0.0004849439200849592, 'samples': 9438208, 'steps': 18433, 'loss/train': 1.4845633506774902}
-03/04/2022 11:06:48 - INFO - codeparrot_training - Step 18434: {'lr': 0.0004849421062300455, 'samples': 9438720, 'steps': 18434, 'loss/train': 2.6267776489257812}
-03/04/2022 11:06:50 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/04/2022 11:06:53 - INFO - codeparrot_training - Step 18435: {'lr': 0.0004849402922692705, 'samples': 9439232, 'steps': 18435, 'loss/train': 1.8070685863494873}
-03/04/2022 11:06:56 - INFO - codeparrot_training - Step 18436: {'lr': 0.000484938478202635, 'samples': 9439744, 'steps': 18436, 'loss/train': 1.5213689804077148}
-03/04/2022 11:06:58 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/04/2022 11:07:02 - INFO - codeparrot_training - Step 18437: {'lr': 0.0004849366640301399, 'samples': 9440256, 'steps': 18437, 'loss/train': 1.969919204711914}
-03/04/2022 11:07:05 - INFO - codeparrot_training - Step 18438: {'lr': 0.00048493484975178593, 'samples': 9440768, 'steps': 18438, 'loss/train': 1.0668004751205444}
-03/04/2022 11:07:07 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/04/2022 11:07:10 - INFO - codeparrot_training - Step 18439: {'lr': 0.00048493303536757394, 'samples': 9441280, 'steps': 18439, 'loss/train': 2.2972185611724854}
-03/04/2022 11:07:13 - INFO - codeparrot_training - Step 18440: {'lr': 0.00048493122087750473, 'samples': 9441792, 'steps': 18440, 'loss/train': 0.6279820799827576}
-03/04/2022 11:07:15 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 11:07:19 - INFO - codeparrot_training - Step 18441: {'lr': 0.0004849294062815792, 'samples': 9442304, 'steps': 18441, 'loss/train': 1.1119056940078735}
-03/04/2022 11:07:22 - INFO - codeparrot_training - Step 18442: {'lr': 0.000484927591579798, 'samples': 9442816, 'steps': 18442, 'loss/train': 1.4312788248062134}
-03/04/2022 11:07:24 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/04/2022 11:07:27 - INFO - codeparrot_training - Step 18443: {'lr': 0.0004849257767721622, 'samples': 9443328, 'steps': 18443, 'loss/train': 1.7428877353668213}
-03/04/2022 11:07:30 - INFO - codeparrot_training - Step 18444: {'lr': 0.00048492396185867236, 'samples': 9443840, 'steps': 18444, 'loss/train': 1.4280723333358765}
-03/04/2022 11:07:32 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/04/2022 11:07:35 - INFO - codeparrot_training - Step 18445: {'lr': 0.0004849221468393294, 'samples': 9444352, 'steps': 18445, 'loss/train': 1.5985113382339478}
-03/04/2022 11:07:39 - INFO - codeparrot_training - Step 18446: {'lr': 0.00048492033171413425, 'samples': 9444864, 'steps': 18446, 'loss/train': 1.890008807182312}
-03/04/2022 11:07:40 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/04/2022 11:07:44 - INFO - codeparrot_training - Step 18447: {'lr': 0.00048491851648308756, 'samples': 9445376, 'steps': 18447, 'loss/train': 1.81052827835083}
-03/04/2022 11:07:47 - INFO - codeparrot_training - Step 18448: {'lr': 0.00048491670114619026, 'samples': 9445888, 'steps': 18448, 'loss/train': 0.9550400376319885}
-03/04/2022 11:07:49 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/04/2022 11:07:52 - INFO - codeparrot_training - Step 18449: {'lr': 0.000484914885703443, 'samples': 9446400, 'steps': 18449, 'loss/train': 2.0922329425811768}
-03/04/2022 11:07:56 - INFO - codeparrot_training - Step 18450: {'lr': 0.00048491307015484684, 'samples': 9446912, 'steps': 18450, 'loss/train': 2.092632532119751}
-03/04/2022 11:07:58 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 11:08:01 - INFO - codeparrot_training - Step 18451: {'lr': 0.0004849112545004024, 'samples': 9447424, 'steps': 18451, 'loss/train': 1.9754749536514282}
-03/04/2022 11:08:04 - INFO - codeparrot_training - Step 18452: {'lr': 0.00048490943874011054, 'samples': 9447936, 'steps': 18452, 'loss/train': 2.3035242557525635}
-03/04/2022 11:08:06 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 11:08:09 - INFO - codeparrot_training - Step 18453: {'lr': 0.00048490762287397215, 'samples': 9448448, 'steps': 18453, 'loss/train': 2.4951043128967285}
-03/04/2022 11:08:13 - INFO - codeparrot_training - Step 18454: {'lr': 0.00048490580690198804, 'samples': 9448960, 'steps': 18454, 'loss/train': 2.146663188934326}
-03/04/2022 11:08:15 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/04/2022 11:08:18 - INFO - codeparrot_training - Step 18455: {'lr': 0.000484903990824159, 'samples': 9449472, 'steps': 18455, 'loss/train': 2.28841233253479}
-03/04/2022 11:08:21 - INFO - codeparrot_training - Step 18456: {'lr': 0.0004849021746404859, 'samples': 9449984, 'steps': 18456, 'loss/train': 2.623843193054199}
-03/04/2022 11:08:23 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/04/2022 11:08:26 - INFO - codeparrot_training - Step 18457: {'lr': 0.00048490035835096936, 'samples': 9450496, 'steps': 18457, 'loss/train': 1.6935759782791138}
-03/04/2022 11:08:30 - INFO - codeparrot_training - Step 18458: {'lr': 0.0004848985419556104, 'samples': 9451008, 'steps': 18458, 'loss/train': 1.5955548286437988}
-03/04/2022 11:08:32 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 11:08:35 - INFO - codeparrot_training - Step 18459: {'lr': 0.0004848967254544099, 'samples': 9451520, 'steps': 18459, 'loss/train': 1.4711685180664062}
-03/04/2022 11:08:38 - INFO - codeparrot_training - Step 18460: {'lr': 0.00048489490884736844, 'samples': 9452032, 'steps': 18460, 'loss/train': 2.0197815895080566}
-03/04/2022 11:08:40 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/04/2022 11:08:43 - INFO - codeparrot_training - Step 18461: {'lr': 0.00048489309213448696, 'samples': 9452544, 'steps': 18461, 'loss/train': 2.737483501434326}
-03/04/2022 11:08:46 - INFO - codeparrot_training - Step 18462: {'lr': 0.00048489127531576627, 'samples': 9453056, 'steps': 18462, 'loss/train': 2.3246302604675293}
-03/04/2022 11:08:49 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 11:08:52 - INFO - codeparrot_training - Step 18463: {'lr': 0.0004848894583912072, 'samples': 9453568, 'steps': 18463, 'loss/train': 2.0120387077331543}
-03/04/2022 11:08:55 - INFO - codeparrot_training - Step 18464: {'lr': 0.00048488764136081063, 'samples': 9454080, 'steps': 18464, 'loss/train': 2.274989128112793}
-03/04/2022 11:08:57 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 11:09:00 - INFO - codeparrot_training - Step 18465: {'lr': 0.00048488582422457726, 'samples': 9454592, 'steps': 18465, 'loss/train': 1.391667366027832}
-03/04/2022 11:09:03 - INFO - codeparrot_training - Step 18466: {'lr': 0.000484884006982508, 'samples': 9455104, 'steps': 18466, 'loss/train': 2.4340569972991943}
-03/04/2022 11:09:05 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/04/2022 11:09:09 - INFO - codeparrot_training - Step 18467: {'lr': 0.0004848821896346036, 'samples': 9455616, 'steps': 18467, 'loss/train': 1.4563145637512207}
-03/04/2022 11:09:12 - INFO - codeparrot_training - Step 18468: {'lr': 0.0004848803721808649, 'samples': 9456128, 'steps': 18468, 'loss/train': 2.0214438438415527}
-03/04/2022 11:09:14 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/04/2022 11:09:17 - INFO - codeparrot_training - Step 18469: {'lr': 0.0004848785546212927, 'samples': 9456640, 'steps': 18469, 'loss/train': 1.5536054372787476}
-03/04/2022 11:09:20 - INFO - codeparrot_training - Step 18470: {'lr': 0.00048487673695588794, 'samples': 9457152, 'steps': 18470, 'loss/train': 1.899634838104248}
-03/04/2022 11:09:22 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 11:09:26 - INFO - codeparrot_training - Step 18471: {'lr': 0.00048487491918465135, 'samples': 9457664, 'steps': 18471, 'loss/train': 1.238110899925232}
-03/04/2022 11:09:29 - INFO - codeparrot_training - Step 18472: {'lr': 0.00048487310130758366, 'samples': 9458176, 'steps': 18472, 'loss/train': 0.931202232837677}
-03/04/2022 11:09:30 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/04/2022 11:09:34 - INFO - codeparrot_training - Step 18473: {'lr': 0.00048487128332468576, 'samples': 9458688, 'steps': 18473, 'loss/train': 2.0761559009552}
-03/04/2022 11:09:37 - INFO - codeparrot_training - Step 18474: {'lr': 0.00048486946523595856, 'samples': 9459200, 'steps': 18474, 'loss/train': 1.456026315689087}
-03/04/2022 11:09:39 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/04/2022 11:09:43 - INFO - codeparrot_training - Step 18475: {'lr': 0.00048486764704140276, 'samples': 9459712, 'steps': 18475, 'loss/train': 1.9242653846740723}
-03/04/2022 11:09:46 - INFO - codeparrot_training - Step 18476: {'lr': 0.00048486582874101924, 'samples': 9460224, 'steps': 18476, 'loss/train': 2.184377670288086}
-03/04/2022 11:09:47 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/04/2022 11:09:51 - INFO - codeparrot_training - Step 18477: {'lr': 0.0004848640103348088, 'samples': 9460736, 'steps': 18477, 'loss/train': 1.8564081192016602}
-03/04/2022 11:09:54 - INFO - codeparrot_training - Step 18478: {'lr': 0.00048486219182277226, 'samples': 9461248, 'steps': 18478, 'loss/train': 2.330422878265381}
-03/04/2022 11:09:56 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 11:09:59 - INFO - codeparrot_training - Step 18479: {'lr': 0.00048486037320491043, 'samples': 9461760, 'steps': 18479, 'loss/train': 1.584395170211792}
-03/04/2022 11:10:03 - INFO - codeparrot_training - Step 18480: {'lr': 0.0004848585544812242, 'samples': 9462272, 'steps': 18480, 'loss/train': 1.6666456460952759}
-03/04/2022 11:10:04 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 11:10:08 - INFO - codeparrot_training - Step 18481: {'lr': 0.0004848567356517143, 'samples': 9462784, 'steps': 18481, 'loss/train': 1.4618659019470215}
-03/04/2022 11:10:11 - INFO - codeparrot_training - Step 18482: {'lr': 0.00048485491671638146, 'samples': 9463296, 'steps': 18482, 'loss/train': 2.1894304752349854}
-03/04/2022 11:10:13 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/04/2022 11:10:16 - INFO - codeparrot_training - Step 18483: {'lr': 0.0004848530976752268, 'samples': 9463808, 'steps': 18483, 'loss/train': 2.0315933227539062}
-03/04/2022 11:10:19 - INFO - codeparrot_training - Step 18484: {'lr': 0.0004848512785282508, 'samples': 9464320, 'steps': 18484, 'loss/train': 1.6910381317138672}
-03/04/2022 11:10:21 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/04/2022 11:10:25 - INFO - codeparrot_training - Step 18485: {'lr': 0.00048484945927545456, 'samples': 9464832, 'steps': 18485, 'loss/train': 0.8209490776062012}
-03/04/2022 11:10:28 - INFO - codeparrot_training - Step 18486: {'lr': 0.0004848476399168387, 'samples': 9465344, 'steps': 18486, 'loss/train': 1.7438864707946777}
-03/04/2022 11:10:30 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 11:10:34 - INFO - codeparrot_training - Step 18487: {'lr': 0.0004848458204524042, 'samples': 9465856, 'steps': 18487, 'loss/train': 1.479312539100647}
-03/04/2022 11:10:37 - INFO - codeparrot_training - Step 18488: {'lr': 0.00048484400088215173, 'samples': 9466368, 'steps': 18488, 'loss/train': 1.8798394203186035}
-03/04/2022 11:10:40 - INFO - codeparrot_training - Step 18489: {'lr': 0.0004848421812060821, 'samples': 9466880, 'steps': 18489, 'loss/train': 1.4872218370437622}
-03/04/2022 11:10:42 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/04/2022 11:10:45 - INFO - codeparrot_training - Step 18490: {'lr': 0.0004848403614241964, 'samples': 9467392, 'steps': 18490, 'loss/train': 1.8513764142990112}
-03/04/2022 11:10:49 - INFO - codeparrot_training - Step 18491: {'lr': 0.00048483854153649514, 'samples': 9467904, 'steps': 18491, 'loss/train': 0.6446804404258728}
-03/04/2022 11:10:51 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/04/2022 11:10:54 - INFO - codeparrot_training - Step 18492: {'lr': 0.0004848367215429793, 'samples': 9468416, 'steps': 18492, 'loss/train': 1.9910953044891357}
-03/04/2022 11:10:57 - INFO - codeparrot_training - Step 18493: {'lr': 0.0004848349014436496, 'samples': 9468928, 'steps': 18493, 'loss/train': 1.5275315046310425}
-03/04/2022 11:10:59 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/04/2022 11:11:02 - INFO - codeparrot_training - Step 18494: {'lr': 0.00048483308123850697, 'samples': 9469440, 'steps': 18494, 'loss/train': 1.7263447046279907}
-03/04/2022 11:11:06 - INFO - codeparrot_training - Step 18495: {'lr': 0.00048483126092755215, 'samples': 9469952, 'steps': 18495, 'loss/train': 2.0994651317596436}
-03/04/2022 11:11:08 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/04/2022 11:11:11 - INFO - codeparrot_training - Step 18496: {'lr': 0.000484829440510786, 'samples': 9470464, 'steps': 18496, 'loss/train': 2.1174917221069336}
-03/04/2022 11:11:14 - INFO - codeparrot_training - Step 18497: {'lr': 0.0004848276199882093, 'samples': 9470976, 'steps': 18497, 'loss/train': 2.03486704826355}
-03/04/2022 11:11:16 - INFO - codeparrot_training - Skipping example with length 385 (seq_length=1024)
-03/04/2022 11:11:19 - INFO - codeparrot_training - Step 18498: {'lr': 0.0004848257993598229, 'samples': 9471488, 'steps': 18498, 'loss/train': 2.219670295715332}
-03/04/2022 11:11:22 - INFO - codeparrot_training - Step 18499: {'lr': 0.00048482397862562764, 'samples': 9472000, 'steps': 18499, 'loss/train': 2.98835825920105}
-03/04/2022 11:11:25 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/04/2022 11:11:28 - INFO - codeparrot_training - Step 18500: {'lr': 0.00048482215778562434, 'samples': 9472512, 'steps': 18500, 'loss/train': 2.662452220916748}
-03/04/2022 11:11:31 - INFO - codeparrot_training - Step 18501: {'lr': 0.00048482033683981376, 'samples': 9473024, 'steps': 18501, 'loss/train': 2.0756499767303467}
-03/04/2022 11:11:33 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 11:11:36 - INFO - codeparrot_training - Step 18502: {'lr': 0.0004848185157881968, 'samples': 9473536, 'steps': 18502, 'loss/train': 2.126345634460449}
-03/04/2022 11:11:39 - INFO - codeparrot_training - Step 18503: {'lr': 0.0004848166946307742, 'samples': 9474048, 'steps': 18503, 'loss/train': 1.6209193468093872}
-03/04/2022 11:11:41 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/04/2022 11:11:44 - INFO - codeparrot_training - Step 18504: {'lr': 0.0004848148733675468, 'samples': 9474560, 'steps': 18504, 'loss/train': 2.2926669120788574}
-03/04/2022 11:11:48 - INFO - codeparrot_training - Step 18505: {'lr': 0.0004848130519985155, 'samples': 9475072, 'steps': 18505, 'loss/train': 2.561042308807373}
-03/04/2022 11:11:49 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/04/2022 11:11:53 - INFO - codeparrot_training - Step 18506: {'lr': 0.000484811230523681, 'samples': 9475584, 'steps': 18506, 'loss/train': 1.04912269115448}
-03/04/2022 11:11:56 - INFO - codeparrot_training - Step 18507: {'lr': 0.00048480940894304425, 'samples': 9476096, 'steps': 18507, 'loss/train': 1.7873740196228027}
-03/04/2022 11:11:59 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/04/2022 11:12:01 - INFO - codeparrot_training - Step 18508: {'lr': 0.000484807587256606, 'samples': 9476608, 'steps': 18508, 'loss/train': 2.349071741104126}
-03/04/2022 11:12:05 - INFO - codeparrot_training - Step 18509: {'lr': 0.00048480576546436707, 'samples': 9477120, 'steps': 18509, 'loss/train': 1.917291522026062}
-03/04/2022 11:12:07 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 11:12:10 - INFO - codeparrot_training - Step 18510: {'lr': 0.0004848039435663282, 'samples': 9477632, 'steps': 18510, 'loss/train': 2.1191718578338623}
-03/04/2022 11:12:13 - INFO - codeparrot_training - Step 18511: {'lr': 0.0004848021215624904, 'samples': 9478144, 'steps': 18511, 'loss/train': 2.095357656478882}
-03/04/2022 11:12:15 - INFO - codeparrot_training - Skipping example with length 385 (seq_length=1024)
-03/04/2022 11:12:18 - INFO - codeparrot_training - Step 18512: {'lr': 0.0004848002994528543, 'samples': 9478656, 'steps': 18512, 'loss/train': 2.636151075363159}
-03/04/2022 11:12:21 - INFO - codeparrot_training - Step 18513: {'lr': 0.0004847984772374209, 'samples': 9479168, 'steps': 18513, 'loss/train': 1.6719088554382324}
-03/04/2022 11:12:24 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/04/2022 11:12:27 - INFO - codeparrot_training - Step 18514: {'lr': 0.0004847966549161909, 'samples': 9479680, 'steps': 18514, 'loss/train': 2.065788984298706}
-03/04/2022 11:12:30 - INFO - codeparrot_training - Step 18515: {'lr': 0.0004847948324891651, 'samples': 9480192, 'steps': 18515, 'loss/train': 2.217582941055298}
-03/04/2022 11:12:32 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 11:12:35 - INFO - codeparrot_training - Step 18516: {'lr': 0.00048479300995634447, 'samples': 9480704, 'steps': 18516, 'loss/train': 2.1215009689331055}
-03/04/2022 11:12:38 - INFO - codeparrot_training - Step 18517: {'lr': 0.0004847911873177296, 'samples': 9481216, 'steps': 18517, 'loss/train': 1.1368504762649536}
-03/04/2022 11:12:40 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/04/2022 11:12:44 - INFO - codeparrot_training - Step 18518: {'lr': 0.0004847893645733216, 'samples': 9481728, 'steps': 18518, 'loss/train': 2.0612235069274902}
-03/04/2022 11:12:47 - INFO - codeparrot_training - Step 18519: {'lr': 0.000484787541723121, 'samples': 9482240, 'steps': 18519, 'loss/train': 1.5083931684494019}
-03/04/2022 11:12:48 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 11:12:52 - INFO - codeparrot_training - Step 18520: {'lr': 0.0004847857187671288, 'samples': 9482752, 'steps': 18520, 'loss/train': 2.049680471420288}
-03/04/2022 11:12:55 - INFO - codeparrot_training - Step 18521: {'lr': 0.00048478389570534575, 'samples': 9483264, 'steps': 18521, 'loss/train': 0.8156064748764038}
-03/04/2022 11:12:57 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/04/2022 11:13:01 - INFO - codeparrot_training - Step 18522: {'lr': 0.0004847820725377728, 'samples': 9483776, 'steps': 18522, 'loss/train': 1.9106088876724243}
-03/04/2022 11:13:04 - INFO - codeparrot_training - Step 18523: {'lr': 0.0004847802492644106, 'samples': 9484288, 'steps': 18523, 'loss/train': 1.9337154626846313}
-03/04/2022 11:13:06 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 11:13:09 - INFO - codeparrot_training - Step 18524: {'lr': 0.00048477842588526, 'samples': 9484800, 'steps': 18524, 'loss/train': 2.2174770832061768}
-03/04/2022 11:13:12 - INFO - codeparrot_training - Step 18525: {'lr': 0.000484776602400322, 'samples': 9485312, 'steps': 18525, 'loss/train': 2.1930646896362305}
-03/04/2022 11:13:14 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/04/2022 11:13:18 - INFO - codeparrot_training - Step 18526: {'lr': 0.00048477477880959715, 'samples': 9485824, 'steps': 18526, 'loss/train': 1.790900707244873}
-03/04/2022 11:13:21 - INFO - codeparrot_training - Step 18527: {'lr': 0.00048477295511308645, 'samples': 9486336, 'steps': 18527, 'loss/train': 1.7812747955322266}
-03/04/2022 11:13:23 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 11:13:26 - INFO - codeparrot_training - Step 18528: {'lr': 0.0004847711313107907, 'samples': 9486848, 'steps': 18528, 'loss/train': 1.9633147716522217}
-03/04/2022 11:13:29 - INFO - codeparrot_training - Step 18529: {'lr': 0.0004847693074027106, 'samples': 9487360, 'steps': 18529, 'loss/train': 2.104095220565796}
-03/04/2022 11:13:31 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 11:13:34 - INFO - codeparrot_training - Step 18530: {'lr': 0.0004847674833888472, 'samples': 9487872, 'steps': 18530, 'loss/train': 1.7089003324508667}
-03/04/2022 11:13:38 - INFO - codeparrot_training - Step 18531: {'lr': 0.0004847656592692012, 'samples': 9488384, 'steps': 18531, 'loss/train': 1.050249457359314}
-03/04/2022 11:13:39 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/04/2022 11:13:43 - INFO - codeparrot_training - Step 18532: {'lr': 0.00048476383504377337, 'samples': 9488896, 'steps': 18532, 'loss/train': 2.0180017948150635}
-03/04/2022 11:13:46 - INFO - codeparrot_training - Step 18533: {'lr': 0.00048476201071256453, 'samples': 9489408, 'steps': 18533, 'loss/train': 1.8865082263946533}
-03/04/2022 11:13:48 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 11:13:51 - INFO - codeparrot_training - Step 18534: {'lr': 0.0004847601862755756, 'samples': 9489920, 'steps': 18534, 'loss/train': 0.2787712812423706}
-03/04/2022 11:13:54 - INFO - codeparrot_training - Step 18535: {'lr': 0.0004847583617328074, 'samples': 9490432, 'steps': 18535, 'loss/train': 2.752586603164673}
-03/04/2022 11:13:57 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/04/2022 11:14:00 - INFO - codeparrot_training - Step 18536: {'lr': 0.00048475653708426067, 'samples': 9490944, 'steps': 18536, 'loss/train': 1.963914394378662}
-03/04/2022 11:14:03 - INFO - codeparrot_training - Step 18537: {'lr': 0.00048475471232993625, 'samples': 9491456, 'steps': 18537, 'loss/train': 1.4105111360549927}
-03/04/2022 11:14:05 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 11:14:08 - INFO - codeparrot_training - Step 18538: {'lr': 0.000484752887469835, 'samples': 9491968, 'steps': 18538, 'loss/train': 1.9283291101455688}
-03/04/2022 11:14:11 - INFO - codeparrot_training - Step 18539: {'lr': 0.0004847510625039577, 'samples': 9492480, 'steps': 18539, 'loss/train': 0.3878302276134491}
-03/04/2022 11:14:14 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/04/2022 11:14:17 - INFO - codeparrot_training - Step 18540: {'lr': 0.00048474923743230513, 'samples': 9492992, 'steps': 18540, 'loss/train': 2.338212490081787}
-03/04/2022 11:14:20 - INFO - codeparrot_training - Step 18541: {'lr': 0.0004847474122548783, 'samples': 9493504, 'steps': 18541, 'loss/train': 2.1132614612579346}
-03/04/2022 11:14:22 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/04/2022 11:14:25 - INFO - codeparrot_training - Step 18542: {'lr': 0.00048474558697167783, 'samples': 9494016, 'steps': 18542, 'loss/train': 1.8636130094528198}
-03/04/2022 11:14:28 - INFO - codeparrot_training - Step 18543: {'lr': 0.0004847437615827046, 'samples': 9494528, 'steps': 18543, 'loss/train': 2.4386281967163086}
-03/04/2022 11:14:31 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 11:14:33 - INFO - codeparrot_training - Step 18544: {'lr': 0.0004847419360879596, 'samples': 9495040, 'steps': 18544, 'loss/train': 1.816033959388733}
-03/04/2022 11:14:37 - INFO - codeparrot_training - Step 18545: {'lr': 0.00048474011048744336, 'samples': 9495552, 'steps': 18545, 'loss/train': 2.0651051998138428}
-03/04/2022 11:14:39 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/04/2022 11:14:42 - INFO - codeparrot_training - Step 18546: {'lr': 0.0004847382847811569, 'samples': 9496064, 'steps': 18546, 'loss/train': 1.6472558975219727}
-03/04/2022 11:14:45 - INFO - codeparrot_training - Step 18547: {'lr': 0.00048473645896910094, 'samples': 9496576, 'steps': 18547, 'loss/train': 1.049011468887329}
-03/04/2022 11:14:47 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/04/2022 11:14:50 - INFO - codeparrot_training - Step 18548: {'lr': 0.0004847346330512764, 'samples': 9497088, 'steps': 18548, 'loss/train': 2.3326668739318848}
-03/04/2022 11:14:53 - INFO - codeparrot_training - Step 18549: {'lr': 0.0004847328070276841, 'samples': 9497600, 'steps': 18549, 'loss/train': 1.5755760669708252}
-03/04/2022 11:14:55 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 11:14:59 - INFO - codeparrot_training - Step 18550: {'lr': 0.00048473098089832475, 'samples': 9498112, 'steps': 18550, 'loss/train': 1.3139079809188843}
-03/04/2022 11:15:02 - INFO - codeparrot_training - Step 18551: {'lr': 0.0004847291546631992, 'samples': 9498624, 'steps': 18551, 'loss/train': 1.1636090278625488}
-03/04/2022 11:15:04 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 11:15:07 - INFO - codeparrot_training - Step 18552: {'lr': 0.0004847273283223084, 'samples': 9499136, 'steps': 18552, 'loss/train': 1.8903982639312744}
-03/04/2022 11:15:10 - INFO - codeparrot_training - Step 18553: {'lr': 0.0004847255018756531, 'samples': 9499648, 'steps': 18553, 'loss/train': 2.1605091094970703}
-03/04/2022 11:15:13 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/04/2022 11:15:16 - INFO - codeparrot_training - Step 18554: {'lr': 0.0004847236753232341, 'samples': 9500160, 'steps': 18554, 'loss/train': 1.2117749452590942}
-03/04/2022 11:15:19 - INFO - codeparrot_training - Step 18555: {'lr': 0.0004847218486650522, 'samples': 9500672, 'steps': 18555, 'loss/train': 2.3666164875030518}
-03/04/2022 11:15:22 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/04/2022 11:15:24 - INFO - codeparrot_training - Step 18556: {'lr': 0.00048472002190110827, 'samples': 9501184, 'steps': 18556, 'loss/train': 1.8320696353912354}
-03/04/2022 11:15:27 - INFO - codeparrot_training - Step 18557: {'lr': 0.0004847181950314031, 'samples': 9501696, 'steps': 18557, 'loss/train': 1.1412675380706787}
-03/04/2022 11:15:30 - INFO - codeparrot_training - Step 18558: {'lr': 0.00048471636805593756, 'samples': 9502208, 'steps': 18558, 'loss/train': 2.4363162517547607}
-03/04/2022 11:15:31 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/04/2022 11:15:36 - INFO - codeparrot_training - Step 18559: {'lr': 0.0004847145409747125, 'samples': 9502720, 'steps': 18559, 'loss/train': 1.9373393058776855}
-03/04/2022 11:15:39 - INFO - codeparrot_training - Step 18560: {'lr': 0.00048471271378772857, 'samples': 9503232, 'steps': 18560, 'loss/train': 1.5204576253890991}
-03/04/2022 11:15:39 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/04/2022 11:15:44 - INFO - codeparrot_training - Step 18561: {'lr': 0.00048471088649498675, 'samples': 9503744, 'steps': 18561, 'loss/train': 2.788674831390381}
-03/04/2022 11:15:47 - INFO - codeparrot_training - Step 18562: {'lr': 0.0004847090590964879, 'samples': 9504256, 'steps': 18562, 'loss/train': 1.7964012622833252}
-03/04/2022 11:15:48 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 11:15:53 - INFO - codeparrot_training - Step 18563: {'lr': 0.00048470723159223266, 'samples': 9504768, 'steps': 18563, 'loss/train': 2.6237716674804688}
-03/04/2022 11:15:56 - INFO - codeparrot_training - Step 18564: {'lr': 0.00048470540398222207, 'samples': 9505280, 'steps': 18564, 'loss/train': 1.6793261766433716}
-03/04/2022 11:15:56 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 11:16:01 - INFO - codeparrot_training - Step 18565: {'lr': 0.00048470357626645676, 'samples': 9505792, 'steps': 18565, 'loss/train': 1.6865196228027344}
-03/04/2022 11:16:04 - INFO - codeparrot_training - Step 18566: {'lr': 0.0004847017484449377, 'samples': 9506304, 'steps': 18566, 'loss/train': 2.3380489349365234}
-03/04/2022 11:16:04 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 11:16:10 - INFO - codeparrot_training - Step 18567: {'lr': 0.0004846999205176657, 'samples': 9506816, 'steps': 18567, 'loss/train': 2.257566213607788}
-03/04/2022 11:16:13 - INFO - codeparrot_training - Step 18568: {'lr': 0.00048469809248464135, 'samples': 9507328, 'steps': 18568, 'loss/train': 1.1617008447647095}
-03/04/2022 11:16:13 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 11:16:18 - INFO - codeparrot_training - Step 18569: {'lr': 0.0004846962643458658, 'samples': 9507840, 'steps': 18569, 'loss/train': 1.7205252647399902}
-03/04/2022 11:16:21 - INFO - codeparrot_training - Step 18570: {'lr': 0.00048469443610133975, 'samples': 9508352, 'steps': 18570, 'loss/train': 2.593264102935791}
-03/04/2022 11:16:21 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/04/2022 11:16:26 - INFO - codeparrot_training - Step 18571: {'lr': 0.00048469260775106394, 'samples': 9508864, 'steps': 18571, 'loss/train': 2.1549558639526367}
-03/04/2022 11:16:30 - INFO - codeparrot_training - Step 18572: {'lr': 0.0004846907792950393, 'samples': 9509376, 'steps': 18572, 'loss/train': 1.3617210388183594}
-03/04/2022 11:16:30 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 11:16:35 - INFO - codeparrot_training - Step 18573: {'lr': 0.00048468895073326663, 'samples': 9509888, 'steps': 18573, 'loss/train': 1.536342978477478}
-03/04/2022 11:16:38 - INFO - codeparrot_training - Step 18574: {'lr': 0.0004846871220657467, 'samples': 9510400, 'steps': 18574, 'loss/train': 1.5257291793823242}
-03/04/2022 11:16:38 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/04/2022 11:16:43 - INFO - codeparrot_training - Step 18575: {'lr': 0.0004846852932924804, 'samples': 9510912, 'steps': 18575, 'loss/train': 2.4912612438201904}
-03/04/2022 11:16:46 - INFO - codeparrot_training - Step 18576: {'lr': 0.00048468346441346853, 'samples': 9511424, 'steps': 18576, 'loss/train': 1.8597791194915771}
-03/04/2022 11:16:46 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/04/2022 11:16:52 - INFO - codeparrot_training - Step 18577: {'lr': 0.0004846816354287119, 'samples': 9511936, 'steps': 18577, 'loss/train': 1.4713172912597656}
-03/04/2022 11:16:55 - INFO - codeparrot_training - Step 18578: {'lr': 0.0004846798063382114, 'samples': 9512448, 'steps': 18578, 'loss/train': 1.8098719120025635}
-03/04/2022 11:16:55 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 11:17:00 - INFO - codeparrot_training - Step 18579: {'lr': 0.0004846779771419677, 'samples': 9512960, 'steps': 18579, 'loss/train': 1.3425004482269287}
-03/04/2022 11:17:04 - INFO - codeparrot_training - Step 18580: {'lr': 0.0004846761478399818, 'samples': 9513472, 'steps': 18580, 'loss/train': 1.9333806037902832}
-03/04/2022 11:17:04 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/04/2022 11:17:09 - INFO - codeparrot_training - Step 18581: {'lr': 0.0004846743184322544, 'samples': 9513984, 'steps': 18581, 'loss/train': 2.009906768798828}
-03/04/2022 11:17:12 - INFO - codeparrot_training - Step 18582: {'lr': 0.00048467248891878644, 'samples': 9514496, 'steps': 18582, 'loss/train': 2.2230184078216553}
-03/04/2022 11:17:12 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/04/2022 11:17:17 - INFO - codeparrot_training - Step 18583: {'lr': 0.00048467065929957867, 'samples': 9515008, 'steps': 18583, 'loss/train': 2.2730114459991455}
-03/04/2022 11:17:21 - INFO - codeparrot_training - Step 18584: {'lr': 0.00048466882957463186, 'samples': 9515520, 'steps': 18584, 'loss/train': 0.6144452691078186}
-03/04/2022 11:17:21 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/04/2022 11:17:26 - INFO - codeparrot_training - Step 18585: {'lr': 0.0004846669997439469, 'samples': 9516032, 'steps': 18585, 'loss/train': 1.515714406967163}
-03/04/2022 11:17:29 - INFO - codeparrot_training - Step 18586: {'lr': 0.0004846651698075246, 'samples': 9516544, 'steps': 18586, 'loss/train': 1.4900751113891602}
-03/04/2022 11:17:29 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/04/2022 11:17:34 - INFO - codeparrot_training - Step 18587: {'lr': 0.00048466333976536594, 'samples': 9517056, 'steps': 18587, 'loss/train': 1.795306921005249}
-03/04/2022 11:17:37 - INFO - codeparrot_training - Step 18588: {'lr': 0.0004846615096174715, 'samples': 9517568, 'steps': 18588, 'loss/train': 2.108651638031006}
-03/04/2022 11:17:38 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 11:17:43 - INFO - codeparrot_training - Step 18589: {'lr': 0.00048465967936384217, 'samples': 9518080, 'steps': 18589, 'loss/train': 1.6753283739089966}
-03/04/2022 11:17:46 - INFO - codeparrot_training - Step 18590: {'lr': 0.00048465784900447885, 'samples': 9518592, 'steps': 18590, 'loss/train': 1.7715721130371094}
-03/04/2022 11:17:46 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/04/2022 11:17:51 - INFO - codeparrot_training - Step 18591: {'lr': 0.00048465601853938224, 'samples': 9519104, 'steps': 18591, 'loss/train': 2.307238817214966}
-03/04/2022 11:17:54 - INFO - codeparrot_training - Step 18592: {'lr': 0.0004846541879685533, 'samples': 9519616, 'steps': 18592, 'loss/train': 2.603482246398926}
-03/04/2022 11:17:54 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 11:18:00 - INFO - codeparrot_training - Step 18593: {'lr': 0.0004846523572919929, 'samples': 9520128, 'steps': 18593, 'loss/train': 2.4395039081573486}
-03/04/2022 11:18:03 - INFO - codeparrot_training - Step 18594: {'lr': 0.00048465052650970166, 'samples': 9520640, 'steps': 18594, 'loss/train': 2.085561513900757}
-03/04/2022 11:18:03 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/04/2022 11:18:08 - INFO - codeparrot_training - Step 18595: {'lr': 0.00048464869562168055, 'samples': 9521152, 'steps': 18595, 'loss/train': 1.9810832738876343}
-03/04/2022 11:18:11 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 11:18:13 - INFO - codeparrot_training - Step 18596: {'lr': 0.0004846468646279304, 'samples': 9521664, 'steps': 18596, 'loss/train': 1.617682695388794}
-03/04/2022 11:18:17 - INFO - codeparrot_training - Step 18597: {'lr': 0.0004846450335284519, 'samples': 9522176, 'steps': 18597, 'loss/train': 2.1768369674682617}
-03/04/2022 11:18:19 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/04/2022 11:18:22 - INFO - codeparrot_training - Step 18598: {'lr': 0.00048464320232324604, 'samples': 9522688, 'steps': 18598, 'loss/train': 2.210847854614258}
-03/04/2022 11:18:25 - INFO - codeparrot_training - Step 18599: {'lr': 0.00048464137101231355, 'samples': 9523200, 'steps': 18599, 'loss/train': 1.6373380422592163}
-03/04/2022 11:18:28 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/04/2022 11:18:30 - INFO - codeparrot_training - Step 18600: {'lr': 0.0004846395395956553, 'samples': 9523712, 'steps': 18600, 'loss/train': 1.5658397674560547}
-03/04/2022 11:18:33 - INFO - codeparrot_training - Step 18601: {'lr': 0.00048463770807327206, 'samples': 9524224, 'steps': 18601, 'loss/train': 1.9267481565475464}
-03/04/2022 11:18:36 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 11:18:39 - INFO - codeparrot_training - Step 18602: {'lr': 0.00048463587644516473, 'samples': 9524736, 'steps': 18602, 'loss/train': 1.4138847589492798}
-03/04/2022 11:18:42 - INFO - codeparrot_training - Step 18603: {'lr': 0.00048463404471133404, 'samples': 9525248, 'steps': 18603, 'loss/train': 2.1727564334869385}
-03/04/2022 11:18:45 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 11:18:47 - INFO - codeparrot_training - Step 18604: {'lr': 0.00048463221287178094, 'samples': 9525760, 'steps': 18604, 'loss/train': 2.15557861328125}
-03/04/2022 11:18:50 - INFO - codeparrot_training - Step 18605: {'lr': 0.0004846303809265061, 'samples': 9526272, 'steps': 18605, 'loss/train': 2.978668451309204}
-03/04/2022 11:18:53 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/04/2022 11:18:56 - INFO - codeparrot_training - Step 18606: {'lr': 0.00048462854887551044, 'samples': 9526784, 'steps': 18606, 'loss/train': 1.835233211517334}
-03/04/2022 11:18:59 - INFO - codeparrot_training - Step 18607: {'lr': 0.0004846267167187949, 'samples': 9527296, 'steps': 18607, 'loss/train': 0.6333346962928772}
-03/04/2022 11:19:02 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 11:19:04 - INFO - codeparrot_training - Step 18608: {'lr': 0.00048462488445636005, 'samples': 9527808, 'steps': 18608, 'loss/train': 2.327176570892334}
-03/04/2022 11:19:07 - INFO - codeparrot_training - Step 18609: {'lr': 0.0004846230520882069, 'samples': 9528320, 'steps': 18609, 'loss/train': 2.1208627223968506}
-03/04/2022 11:19:10 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 11:19:12 - INFO - codeparrot_training - Step 18610: {'lr': 0.00048462121961433623, 'samples': 9528832, 'steps': 18610, 'loss/train': 1.677850604057312}
-03/04/2022 11:19:16 - INFO - codeparrot_training - Step 18611: {'lr': 0.00048461938703474886, 'samples': 9529344, 'steps': 18611, 'loss/train': 1.2169485092163086}
-03/04/2022 11:19:18 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/04/2022 11:19:21 - INFO - codeparrot_training - Step 18612: {'lr': 0.00048461755434944554, 'samples': 9529856, 'steps': 18612, 'loss/train': 1.8525623083114624}
-03/04/2022 11:19:24 - INFO - codeparrot_training - Step 18613: {'lr': 0.00048461572155842725, 'samples': 9530368, 'steps': 18613, 'loss/train': 2.153980255126953}
-03/04/2022 11:19:27 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/04/2022 11:19:30 - INFO - codeparrot_training - Step 18614: {'lr': 0.00048461388866169474, 'samples': 9530880, 'steps': 18614, 'loss/train': 0.7949098944664001}
-03/04/2022 11:19:33 - INFO - codeparrot_training - Step 18615: {'lr': 0.00048461205565924884, 'samples': 9531392, 'steps': 18615, 'loss/train': 2.060805082321167}
-03/04/2022 11:19:35 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 11:19:38 - INFO - codeparrot_training - Step 18616: {'lr': 0.0004846102225510903, 'samples': 9531904, 'steps': 18616, 'loss/train': 0.91429203748703}
-03/04/2022 11:19:41 - INFO - codeparrot_training - Step 18617: {'lr': 0.00048460838933722005, 'samples': 9532416, 'steps': 18617, 'loss/train': 2.4738800525665283}
-03/04/2022 11:19:44 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/04/2022 11:19:47 - INFO - codeparrot_training - Step 18618: {'lr': 0.0004846065560176389, 'samples': 9532928, 'steps': 18618, 'loss/train': 1.794521689414978}
-03/04/2022 11:19:50 - INFO - codeparrot_training - Step 18619: {'lr': 0.00048460472259234764, 'samples': 9533440, 'steps': 18619, 'loss/train': 3.534989595413208}
-03/04/2022 11:19:52 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/04/2022 11:19:55 - INFO - codeparrot_training - Step 18620: {'lr': 0.0004846028890613471, 'samples': 9533952, 'steps': 18620, 'loss/train': 1.9484655857086182}
-03/04/2022 11:19:58 - INFO - codeparrot_training - Step 18621: {'lr': 0.00048460105542463805, 'samples': 9534464, 'steps': 18621, 'loss/train': 1.5850346088409424}
-03/04/2022 11:20:01 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 11:20:04 - INFO - codeparrot_training - Step 18622: {'lr': 0.00048459922168222146, 'samples': 9534976, 'steps': 18622, 'loss/train': 2.3599042892456055}
-03/04/2022 11:20:07 - INFO - codeparrot_training - Step 18623: {'lr': 0.00048459738783409814, 'samples': 9535488, 'steps': 18623, 'loss/train': 2.1653757095336914}
-03/04/2022 11:20:10 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 11:20:12 - INFO - codeparrot_training - Step 18624: {'lr': 0.0004845955538802688, 'samples': 9536000, 'steps': 18624, 'loss/train': 0.38898828625679016}
-03/04/2022 11:20:15 - INFO - codeparrot_training - Step 18625: {'lr': 0.0004845937198207343, 'samples': 9536512, 'steps': 18625, 'loss/train': 1.0213191509246826}
-03/04/2022 11:20:18 - INFO - codeparrot_training - Step 18626: {'lr': 0.0004845918856554955, 'samples': 9537024, 'steps': 18626, 'loss/train': 1.5238466262817383}
-03/04/2022 11:20:19 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/04/2022 11:20:24 - INFO - codeparrot_training - Step 18627: {'lr': 0.00048459005138455326, 'samples': 9537536, 'steps': 18627, 'loss/train': 1.6991515159606934}
-03/04/2022 11:20:27 - INFO - codeparrot_training - Step 18628: {'lr': 0.0004845882170079083, 'samples': 9538048, 'steps': 18628, 'loss/train': 2.7840237617492676}
-03/04/2022 11:20:28 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/04/2022 11:20:33 - INFO - codeparrot_training - Step 18629: {'lr': 0.00048458638252556153, 'samples': 9538560, 'steps': 18629, 'loss/train': 1.6910163164138794}
-03/04/2022 11:20:36 - INFO - codeparrot_training - Step 18630: {'lr': 0.0004845845479375138, 'samples': 9539072, 'steps': 18630, 'loss/train': 1.8570753335952759}
-03/04/2022 11:20:36 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 11:20:41 - INFO - codeparrot_training - Step 18631: {'lr': 0.00048458271324376586, 'samples': 9539584, 'steps': 18631, 'loss/train': 1.959281086921692}
-03/04/2022 11:20:44 - INFO - codeparrot_training - Step 18632: {'lr': 0.0004845808784443185, 'samples': 9540096, 'steps': 18632, 'loss/train': 1.8797138929367065}
-03/04/2022 11:20:46 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/04/2022 11:20:50 - INFO - codeparrot_training - Step 18633: {'lr': 0.00048457904353917277, 'samples': 9540608, 'steps': 18633, 'loss/train': 2.426520347595215}
-03/04/2022 11:20:53 - INFO - codeparrot_training - Step 18634: {'lr': 0.0004845772085283292, 'samples': 9541120, 'steps': 18634, 'loss/train': 2.1023919582366943}
-03/04/2022 11:20:54 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/04/2022 11:20:58 - INFO - codeparrot_training - Step 18635: {'lr': 0.00048457537341178885, 'samples': 9541632, 'steps': 18635, 'loss/train': 0.7451614141464233}
-03/04/2022 11:21:01 - INFO - codeparrot_training - Step 18636: {'lr': 0.0004845735381895524, 'samples': 9542144, 'steps': 18636, 'loss/train': 1.9899470806121826}
-03/04/2022 11:21:03 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/04/2022 11:21:07 - INFO - codeparrot_training - Step 18637: {'lr': 0.0004845717028616208, 'samples': 9542656, 'steps': 18637, 'loss/train': 1.253427267074585}
-03/04/2022 11:21:10 - INFO - codeparrot_training - Step 18638: {'lr': 0.00048456986742799474, 'samples': 9543168, 'steps': 18638, 'loss/train': 1.4142787456512451}
-03/04/2022 11:21:12 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/04/2022 11:21:15 - INFO - codeparrot_training - Step 18639: {'lr': 0.00048456803188867513, 'samples': 9543680, 'steps': 18639, 'loss/train': 0.3258473575115204}
-03/04/2022 11:21:18 - INFO - codeparrot_training - Step 18640: {'lr': 0.00048456619624366284, 'samples': 9544192, 'steps': 18640, 'loss/train': 1.8020405769348145}
-03/04/2022 11:21:20 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 11:21:23 - INFO - codeparrot_training - Step 18641: {'lr': 0.0004845643604929586, 'samples': 9544704, 'steps': 18641, 'loss/train': 1.9824633598327637}
-03/04/2022 11:21:26 - INFO - codeparrot_training - Step 18642: {'lr': 0.00048456252463656326, 'samples': 9545216, 'steps': 18642, 'loss/train': 1.7848169803619385}
-03/04/2022 11:21:28 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/04/2022 11:21:32 - INFO - codeparrot_training - Step 18643: {'lr': 0.00048456068867447767, 'samples': 9545728, 'steps': 18643, 'loss/train': 2.3442366123199463}
-03/04/2022 11:21:35 - INFO - codeparrot_training - Step 18644: {'lr': 0.0004845588526067027, 'samples': 9546240, 'steps': 18644, 'loss/train': 1.2293621301651}
-03/04/2022 11:21:37 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/04/2022 11:21:40 - INFO - codeparrot_training - Step 18645: {'lr': 0.00048455701643323914, 'samples': 9546752, 'steps': 18645, 'loss/train': 0.39537808299064636}
-03/04/2022 11:21:43 - INFO - codeparrot_training - Step 18646: {'lr': 0.00048455518015408773, 'samples': 9547264, 'steps': 18646, 'loss/train': 1.3319121599197388}
-03/04/2022 11:21:45 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/04/2022 11:21:49 - INFO - codeparrot_training - Step 18647: {'lr': 0.00048455334376924943, 'samples': 9547776, 'steps': 18647, 'loss/train': 2.346625328063965}
-03/04/2022 11:21:52 - INFO - codeparrot_training - Step 18648: {'lr': 0.000484551507278725, 'samples': 9548288, 'steps': 18648, 'loss/train': 1.897567629814148}
-03/04/2022 11:21:53 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/04/2022 11:21:57 - INFO - codeparrot_training - Step 18649: {'lr': 0.0004845496706825152, 'samples': 9548800, 'steps': 18649, 'loss/train': 0.4966985881328583}
-03/04/2022 11:22:00 - INFO - codeparrot_training - Step 18650: {'lr': 0.0004845478339806211, 'samples': 9549312, 'steps': 18650, 'loss/train': 2.2122271060943604}
-03/04/2022 11:22:02 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 11:22:05 - INFO - codeparrot_training - Step 18651: {'lr': 0.00048454599717304327, 'samples': 9549824, 'steps': 18651, 'loss/train': 1.926338791847229}
-03/04/2022 11:22:09 - INFO - codeparrot_training - Step 18652: {'lr': 0.0004845441602597826, 'samples': 9550336, 'steps': 18652, 'loss/train': 1.9956798553466797}
-03/04/2022 11:22:11 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 11:22:14 - INFO - codeparrot_training - Step 18653: {'lr': 0.00048454232324084004, 'samples': 9550848, 'steps': 18653, 'loss/train': 2.1422927379608154}
-03/04/2022 11:22:17 - INFO - codeparrot_training - Step 18654: {'lr': 0.0004845404861162163, 'samples': 9551360, 'steps': 18654, 'loss/train': 1.9878453016281128}
-03/04/2022 11:22:19 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/04/2022 11:22:22 - INFO - codeparrot_training - Step 18655: {'lr': 0.00048453864888591214, 'samples': 9551872, 'steps': 18655, 'loss/train': 1.5010088682174683}
-03/04/2022 11:22:26 - INFO - codeparrot_training - Step 18656: {'lr': 0.0004845368115499286, 'samples': 9552384, 'steps': 18656, 'loss/train': 1.9379220008850098}
-03/04/2022 11:22:27 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/04/2022 11:22:31 - INFO - codeparrot_training - Step 18657: {'lr': 0.0004845349741082663, 'samples': 9552896, 'steps': 18657, 'loss/train': 1.701704502105713}
-03/04/2022 11:22:34 - INFO - codeparrot_training - Step 18658: {'lr': 0.00048453313656092624, 'samples': 9553408, 'steps': 18658, 'loss/train': 1.5231951475143433}
-03/04/2022 11:22:36 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 11:22:39 - INFO - codeparrot_training - Step 18659: {'lr': 0.0004845312989079091, 'samples': 9553920, 'steps': 18659, 'loss/train': 1.9109621047973633}
-03/04/2022 11:22:43 - INFO - codeparrot_training - Step 18660: {'lr': 0.0004845294611492158, 'samples': 9554432, 'steps': 18660, 'loss/train': 2.275043487548828}
-03/04/2022 11:22:44 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/04/2022 11:22:48 - INFO - codeparrot_training - Step 18661: {'lr': 0.00048452762328484724, 'samples': 9554944, 'steps': 18661, 'loss/train': 1.6225910186767578}
-03/04/2022 11:22:51 - INFO - codeparrot_training - Step 18662: {'lr': 0.000484525785314804, 'samples': 9555456, 'steps': 18662, 'loss/train': 1.8858624696731567}
-03/04/2022 11:22:53 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/04/2022 11:22:56 - INFO - codeparrot_training - Step 18663: {'lr': 0.0004845239472390872, 'samples': 9555968, 'steps': 18663, 'loss/train': 1.585341453552246}
-03/04/2022 11:22:59 - INFO - codeparrot_training - Step 18664: {'lr': 0.0004845221090576974, 'samples': 9556480, 'steps': 18664, 'loss/train': 1.6354918479919434}
-03/04/2022 11:23:01 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 11:23:05 - INFO - codeparrot_training - Step 18665: {'lr': 0.0004845202707706356, 'samples': 9556992, 'steps': 18665, 'loss/train': 2.3232977390289307}
-03/04/2022 11:23:08 - INFO - codeparrot_training - Step 18666: {'lr': 0.0004845184323779026, 'samples': 9557504, 'steps': 18666, 'loss/train': 1.7097289562225342}
-03/04/2022 11:23:09 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 11:23:13 - INFO - codeparrot_training - Step 18667: {'lr': 0.0004845165938794992, 'samples': 9558016, 'steps': 18667, 'loss/train': 2.210744857788086}
-03/04/2022 11:23:16 - INFO - codeparrot_training - Step 18668: {'lr': 0.0004845147552754263, 'samples': 9558528, 'steps': 18668, 'loss/train': 1.9959138631820679}
-03/04/2022 11:23:17 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/04/2022 11:23:21 - INFO - codeparrot_training - Step 18669: {'lr': 0.0004845129165656846, 'samples': 9559040, 'steps': 18669, 'loss/train': 2.067938804626465}
-03/04/2022 11:23:25 - INFO - codeparrot_training - Step 18670: {'lr': 0.00048451107775027505, 'samples': 9559552, 'steps': 18670, 'loss/train': 1.9366010427474976}
-03/04/2022 11:23:26 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/04/2022 11:23:30 - INFO - codeparrot_training - Step 18671: {'lr': 0.0004845092388291984, 'samples': 9560064, 'steps': 18671, 'loss/train': 1.8821918964385986}
-03/04/2022 11:23:33 - INFO - codeparrot_training - Step 18672: {'lr': 0.0004845073998024555, 'samples': 9560576, 'steps': 18672, 'loss/train': 1.7919342517852783}
-03/04/2022 11:23:34 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/04/2022 11:23:38 - INFO - codeparrot_training - Step 18673: {'lr': 0.0004845055606700472, 'samples': 9561088, 'steps': 18673, 'loss/train': 1.4468282461166382}
-03/04/2022 11:23:41 - INFO - codeparrot_training - Step 18674: {'lr': 0.0004845037214319743, 'samples': 9561600, 'steps': 18674, 'loss/train': 1.2045326232910156}
-03/04/2022 11:23:42 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 11:23:47 - INFO - codeparrot_training - Step 18675: {'lr': 0.00048450188208823766, 'samples': 9562112, 'steps': 18675, 'loss/train': 0.3356643617153168}
-03/04/2022 11:23:50 - INFO - codeparrot_training - Step 18676: {'lr': 0.00048450004263883806, 'samples': 9562624, 'steps': 18676, 'loss/train': 1.7247512340545654}
-03/04/2022 11:23:51 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/04/2022 11:23:55 - INFO - codeparrot_training - Step 18677: {'lr': 0.00048449820308377634, 'samples': 9563136, 'steps': 18677, 'loss/train': 1.617692232131958}
-03/04/2022 11:23:58 - INFO - codeparrot_training - Step 18678: {'lr': 0.00048449636342305343, 'samples': 9563648, 'steps': 18678, 'loss/train': 1.7291593551635742}
-03/04/2022 11:24:00 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/04/2022 11:24:04 - INFO - codeparrot_training - Step 18679: {'lr': 0.00048449452365667003, 'samples': 9564160, 'steps': 18679, 'loss/train': 2.717499017715454}
-03/04/2022 11:24:07 - INFO - codeparrot_training - Step 18680: {'lr': 0.00048449268378462695, 'samples': 9564672, 'steps': 18680, 'loss/train': 1.1360418796539307}
-03/04/2022 11:24:08 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 11:24:12 - INFO - codeparrot_training - Step 18681: {'lr': 0.00048449084380692523, 'samples': 9565184, 'steps': 18681, 'loss/train': 1.5038435459136963}
-03/04/2022 11:24:15 - INFO - codeparrot_training - Step 18682: {'lr': 0.0004844890037235654, 'samples': 9565696, 'steps': 18682, 'loss/train': 1.6827296018600464}
-03/04/2022 11:24:16 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 11:24:20 - INFO - codeparrot_training - Step 18683: {'lr': 0.00048448716353454856, 'samples': 9566208, 'steps': 18683, 'loss/train': 2.609442949295044}
-03/04/2022 11:24:24 - INFO - codeparrot_training - Step 18684: {'lr': 0.0004844853232398754, 'samples': 9566720, 'steps': 18684, 'loss/train': 1.8652749061584473}
-03/04/2022 11:24:25 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/04/2022 11:24:29 - INFO - codeparrot_training - Step 18685: {'lr': 0.00048448348283954674, 'samples': 9567232, 'steps': 18685, 'loss/train': 3.186627149581909}
-03/04/2022 11:24:32 - INFO - codeparrot_training - Step 18686: {'lr': 0.00048448164233356344, 'samples': 9567744, 'steps': 18686, 'loss/train': 1.9955461025238037}
-03/04/2022 11:24:33 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/04/2022 11:24:37 - INFO - codeparrot_training - Step 18687: {'lr': 0.0004844798017219264, 'samples': 9568256, 'steps': 18687, 'loss/train': 1.6639479398727417}
-03/04/2022 11:24:40 - INFO - codeparrot_training - Step 18688: {'lr': 0.00048447796100463625, 'samples': 9568768, 'steps': 18688, 'loss/train': 2.1941463947296143}
-03/04/2022 11:24:42 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 11:24:46 - INFO - codeparrot_training - Step 18689: {'lr': 0.0004844761201816941, 'samples': 9569280, 'steps': 18689, 'loss/train': 1.9166429042816162}
-03/04/2022 11:24:49 - INFO - codeparrot_training - Step 18690: {'lr': 0.0004844742792531005, 'samples': 9569792, 'steps': 18690, 'loss/train': 0.9608784317970276}
-03/04/2022 11:24:50 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/04/2022 11:24:54 - INFO - codeparrot_training - Step 18691: {'lr': 0.00048447243821885644, 'samples': 9570304, 'steps': 18691, 'loss/train': 2.1382737159729004}
-03/04/2022 11:24:57 - INFO - codeparrot_training - Step 18692: {'lr': 0.0004844705970789628, 'samples': 9570816, 'steps': 18692, 'loss/train': 2.12459659576416}
-03/04/2022 11:24:59 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 11:25:03 - INFO - codeparrot_training - Step 18693: {'lr': 0.0004844687558334202, 'samples': 9571328, 'steps': 18693, 'loss/train': 1.4535390138626099}
-03/04/2022 11:25:06 - INFO - codeparrot_training - Step 18694: {'lr': 0.0004844669144822297, 'samples': 9571840, 'steps': 18694, 'loss/train': 1.6481950283050537}
-03/04/2022 11:25:07 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/04/2022 11:25:11 - INFO - codeparrot_training - Step 18695: {'lr': 0.000484465073025392, 'samples': 9572352, 'steps': 18695, 'loss/train': 2.197214365005493}
-03/04/2022 11:25:14 - INFO - codeparrot_training - Step 18696: {'lr': 0.00048446323146290795, 'samples': 9572864, 'steps': 18696, 'loss/train': 2.472566843032837}
-03/04/2022 11:25:15 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/04/2022 11:25:20 - INFO - codeparrot_training - Step 18697: {'lr': 0.0004844613897947784, 'samples': 9573376, 'steps': 18697, 'loss/train': 2.1920671463012695}
-03/04/2022 11:25:23 - INFO - codeparrot_training - Step 18698: {'lr': 0.00048445954802100414, 'samples': 9573888, 'steps': 18698, 'loss/train': 1.8001036643981934}
-03/04/2022 11:25:24 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 11:25:28 - INFO - codeparrot_training - Step 18699: {'lr': 0.000484457706141586, 'samples': 9574400, 'steps': 18699, 'loss/train': 3.9755606651306152}
-03/04/2022 11:25:31 - INFO - codeparrot_training - Step 18700: {'lr': 0.0004844558641565249, 'samples': 9574912, 'steps': 18700, 'loss/train': 2.1277782917022705}
-03/04/2022 11:25:33 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 11:25:37 - INFO - codeparrot_training - Step 18701: {'lr': 0.00048445402206582155, 'samples': 9575424, 'steps': 18701, 'loss/train': 2.263615608215332}
-03/04/2022 11:25:40 - INFO - codeparrot_training - Step 18702: {'lr': 0.0004844521798694768, 'samples': 9575936, 'steps': 18702, 'loss/train': 2.168971538543701}
-03/04/2022 11:25:41 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 11:25:45 - INFO - codeparrot_training - Step 18703: {'lr': 0.0004844503375674916, 'samples': 9576448, 'steps': 18703, 'loss/train': 2.249758243560791}
-03/04/2022 11:25:48 - INFO - codeparrot_training - Step 18704: {'lr': 0.0004844484951598667, 'samples': 9576960, 'steps': 18704, 'loss/train': 2.043807029724121}
-03/04/2022 11:25:49 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/04/2022 11:25:54 - INFO - codeparrot_training - Step 18705: {'lr': 0.00048444665264660286, 'samples': 9577472, 'steps': 18705, 'loss/train': 1.8751020431518555}
-03/04/2022 11:25:57 - INFO - codeparrot_training - Step 18706: {'lr': 0.000484444810027701, 'samples': 9577984, 'steps': 18706, 'loss/train': 1.8361985683441162}
-03/04/2022 11:25:58 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 11:26:02 - INFO - codeparrot_training - Step 18707: {'lr': 0.00048444296730316196, 'samples': 9578496, 'steps': 18707, 'loss/train': 2.200230836868286}
-03/04/2022 11:26:05 - INFO - codeparrot_training - Step 18708: {'lr': 0.0004844411244729865, 'samples': 9579008, 'steps': 18708, 'loss/train': 2.188616991043091}
-03/04/2022 11:26:06 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/04/2022 11:26:11 - INFO - codeparrot_training - Step 18709: {'lr': 0.00048443928153717555, 'samples': 9579520, 'steps': 18709, 'loss/train': 1.953428864479065}
-03/04/2022 11:26:14 - INFO - codeparrot_training - Step 18710: {'lr': 0.00048443743849572974, 'samples': 9580032, 'steps': 18710, 'loss/train': 2.486377239227295}
-03/04/2022 11:26:14 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/04/2022 11:26:19 - INFO - codeparrot_training - Step 18711: {'lr': 0.00048443559534865017, 'samples': 9580544, 'steps': 18711, 'loss/train': 1.770187497138977}
-03/04/2022 11:26:22 - INFO - codeparrot_training - Step 18712: {'lr': 0.0004844337520959375, 'samples': 9581056, 'steps': 18712, 'loss/train': 2.476099967956543}
-03/04/2022 11:26:23 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/04/2022 11:26:28 - INFO - codeparrot_training - Step 18713: {'lr': 0.00048443190873759256, 'samples': 9581568, 'steps': 18713, 'loss/train': 0.15470083057880402}
-03/04/2022 11:26:31 - INFO - codeparrot_training - Step 18714: {'lr': 0.00048443006527361626, 'samples': 9582080, 'steps': 18714, 'loss/train': 1.3089662790298462}
-03/04/2022 11:26:32 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 11:26:36 - INFO - codeparrot_training - Step 18715: {'lr': 0.0004844282217040094, 'samples': 9582592, 'steps': 18715, 'loss/train': 1.8125014305114746}
-03/04/2022 11:26:39 - INFO - codeparrot_training - Step 18716: {'lr': 0.00048442637802877277, 'samples': 9583104, 'steps': 18716, 'loss/train': 1.7381807565689087}
-03/04/2022 11:26:40 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/04/2022 11:26:44 - INFO - codeparrot_training - Step 18717: {'lr': 0.0004844245342479072, 'samples': 9583616, 'steps': 18717, 'loss/train': 2.0978126525878906}
-03/04/2022 11:26:48 - INFO - codeparrot_training - Step 18718: {'lr': 0.00048442269036141363, 'samples': 9584128, 'steps': 18718, 'loss/train': 2.6747753620147705}
-03/04/2022 11:26:49 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/04/2022 11:26:53 - INFO - codeparrot_training - Step 18719: {'lr': 0.0004844208463692928, 'samples': 9584640, 'steps': 18719, 'loss/train': 2.0001118183135986}
-03/04/2022 11:26:56 - INFO - codeparrot_training - Step 18720: {'lr': 0.00048441900227154557, 'samples': 9585152, 'steps': 18720, 'loss/train': 2.0925276279449463}
-03/04/2022 11:26:57 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 11:27:01 - INFO - codeparrot_training - Step 18721: {'lr': 0.00048441715806817265, 'samples': 9585664, 'steps': 18721, 'loss/train': 1.874349594116211}
-03/04/2022 11:27:04 - INFO - codeparrot_training - Step 18722: {'lr': 0.0004844153137591751, 'samples': 9586176, 'steps': 18722, 'loss/train': 1.665478229522705}
-03/04/2022 11:27:06 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/04/2022 11:27:10 - INFO - codeparrot_training - Step 18723: {'lr': 0.00048441346934455356, 'samples': 9586688, 'steps': 18723, 'loss/train': 2.8001251220703125}
-03/04/2022 11:27:13 - INFO - codeparrot_training - Step 18724: {'lr': 0.0004844116248243089, 'samples': 9587200, 'steps': 18724, 'loss/train': 6.581409454345703}
-03/04/2022 11:27:15 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 11:27:18 - INFO - codeparrot_training - Step 18725: {'lr': 0.0004844097801984421, 'samples': 9587712, 'steps': 18725, 'loss/train': 0.9101142883300781}
-03/04/2022 11:27:21 - INFO - codeparrot_training - Step 18726: {'lr': 0.0004844079354669537, 'samples': 9588224, 'steps': 18726, 'loss/train': 2.154237985610962}
-03/04/2022 11:27:23 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 11:27:27 - INFO - codeparrot_training - Step 18727: {'lr': 0.0004844060906298448, 'samples': 9588736, 'steps': 18727, 'loss/train': 2.1521406173706055}
-03/04/2022 11:27:30 - INFO - codeparrot_training - Step 18728: {'lr': 0.0004844042456871162, 'samples': 9589248, 'steps': 18728, 'loss/train': 2.6673505306243896}
-03/04/2022 11:27:32 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/04/2022 11:27:35 - INFO - codeparrot_training - Step 18729: {'lr': 0.0004844024006387685, 'samples': 9589760, 'steps': 18729, 'loss/train': 1.8051283359527588}
-03/04/2022 11:27:38 - INFO - codeparrot_training - Step 18730: {'lr': 0.00048440055548480275, 'samples': 9590272, 'steps': 18730, 'loss/train': 1.8653290271759033}
-03/04/2022 11:27:40 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 11:27:43 - INFO - codeparrot_training - Step 18731: {'lr': 0.0004843987102252198, 'samples': 9590784, 'steps': 18731, 'loss/train': 2.2406249046325684}
-03/04/2022 11:27:47 - INFO - codeparrot_training - Step 18732: {'lr': 0.0004843968648600204, 'samples': 9591296, 'steps': 18732, 'loss/train': 2.10929536819458}
-03/04/2022 11:27:48 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/04/2022 11:27:52 - INFO - codeparrot_training - Step 18733: {'lr': 0.00048439501938920534, 'samples': 9591808, 'steps': 18733, 'loss/train': 2.762437343597412}
-03/04/2022 11:27:55 - INFO - codeparrot_training - Step 18734: {'lr': 0.0004843931738127755, 'samples': 9592320, 'steps': 18734, 'loss/train': 1.3573552370071411}
-03/04/2022 11:27:57 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/04/2022 11:28:00 - INFO - codeparrot_training - Step 18735: {'lr': 0.0004843913281307317, 'samples': 9592832, 'steps': 18735, 'loss/train': 2.4097611904144287}
-03/04/2022 11:28:03 - INFO - codeparrot_training - Step 18736: {'lr': 0.0004843894823430749, 'samples': 9593344, 'steps': 18736, 'loss/train': 2.028916358947754}
-03/04/2022 11:28:05 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/04/2022 11:28:09 - INFO - codeparrot_training - Step 18737: {'lr': 0.00048438763644980564, 'samples': 9593856, 'steps': 18737, 'loss/train': 1.843319058418274}
-03/04/2022 11:28:12 - INFO - codeparrot_training - Step 18738: {'lr': 0.0004843857904509251, 'samples': 9594368, 'steps': 18738, 'loss/train': 1.6730185747146606}
-03/04/2022 11:28:13 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 11:28:17 - INFO - codeparrot_training - Step 18739: {'lr': 0.00048438394434643386, 'samples': 9594880, 'steps': 18739, 'loss/train': 1.9768719673156738}
-03/04/2022 11:28:20 - INFO - codeparrot_training - Step 18740: {'lr': 0.0004843820981363328, 'samples': 9595392, 'steps': 18740, 'loss/train': 1.3856767416000366}
-03/04/2022 11:28:22 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/04/2022 11:28:26 - INFO - codeparrot_training - Step 18741: {'lr': 0.00048438025182062286, 'samples': 9595904, 'steps': 18741, 'loss/train': 1.7631081342697144}
-03/04/2022 11:28:29 - INFO - codeparrot_training - Step 18742: {'lr': 0.00048437840539930466, 'samples': 9596416, 'steps': 18742, 'loss/train': 1.2301301956176758}
-03/04/2022 11:28:30 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/04/2022 11:28:34 - INFO - codeparrot_training - Step 18743: {'lr': 0.0004843765588723793, 'samples': 9596928, 'steps': 18743, 'loss/train': 1.481696605682373}
-03/04/2022 11:28:37 - INFO - codeparrot_training - Step 18744: {'lr': 0.00048437471223984743, 'samples': 9597440, 'steps': 18744, 'loss/train': 0.9930187463760376}
-03/04/2022 11:28:38 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/04/2022 11:28:42 - INFO - codeparrot_training - Step 18745: {'lr': 0.00048437286550170996, 'samples': 9597952, 'steps': 18745, 'loss/train': 2.121004819869995}
-03/04/2022 11:28:45 - INFO - codeparrot_training - Step 18746: {'lr': 0.00048437101865796763, 'samples': 9598464, 'steps': 18746, 'loss/train': 1.6093497276306152}
-03/04/2022 11:28:46 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/04/2022 11:28:51 - INFO - codeparrot_training - Step 18747: {'lr': 0.0004843691717086214, 'samples': 9598976, 'steps': 18747, 'loss/train': 1.3541057109832764}
-03/04/2022 11:28:54 - INFO - codeparrot_training - Step 18748: {'lr': 0.000484367324653672, 'samples': 9599488, 'steps': 18748, 'loss/train': 3.338500499725342}
-03/04/2022 11:28:55 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 11:28:59 - INFO - codeparrot_training - Step 18749: {'lr': 0.0004843654774931203, 'samples': 9600000, 'steps': 18749, 'loss/train': 2.453988552093506}
-03/04/2022 11:29:02 - INFO - codeparrot_training - Step 18750: {'lr': 0.00048436363022696715, 'samples': 9600512, 'steps': 18750, 'loss/train': 1.7140696048736572}
-03/04/2022 11:29:03 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/04/2022 11:29:08 - INFO - codeparrot_training - Step 18751: {'lr': 0.0004843617828552134, 'samples': 9601024, 'steps': 18751, 'loss/train': 2.0701112747192383}
-03/04/2022 11:29:11 - INFO - codeparrot_training - Step 18752: {'lr': 0.00048435993537785976, 'samples': 9601536, 'steps': 18752, 'loss/train': 1.9245834350585938}
-03/04/2022 11:29:11 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/04/2022 11:29:16 - INFO - codeparrot_training - Step 18753: {'lr': 0.0004843580877949072, 'samples': 9602048, 'steps': 18753, 'loss/train': 1.781040072441101}
-03/04/2022 11:29:19 - INFO - codeparrot_training - Step 18754: {'lr': 0.0004843562401063565, 'samples': 9602560, 'steps': 18754, 'loss/train': 0.4453231990337372}
-03/04/2022 11:29:20 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/04/2022 11:29:24 - INFO - codeparrot_training - Step 18755: {'lr': 0.0004843543923122085, 'samples': 9603072, 'steps': 18755, 'loss/train': 1.7451831102371216}
-03/04/2022 11:29:27 - INFO - codeparrot_training - Step 18756: {'lr': 0.000484352544412464, 'samples': 9603584, 'steps': 18756, 'loss/train': 2.2969822883605957}
-03/04/2022 11:29:28 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 11:29:33 - INFO - codeparrot_training - Step 18757: {'lr': 0.0004843506964071239, 'samples': 9604096, 'steps': 18757, 'loss/train': 1.0719404220581055}
-03/04/2022 11:29:36 - INFO - codeparrot_training - Step 18758: {'lr': 0.000484348848296189, 'samples': 9604608, 'steps': 18758, 'loss/train': 2.1931777000427246}
-03/04/2022 11:29:36 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 11:29:41 - INFO - codeparrot_training - Step 18759: {'lr': 0.00048434700007966006, 'samples': 9605120, 'steps': 18759, 'loss/train': 1.4994028806686401}
-03/04/2022 11:29:44 - INFO - codeparrot_training - Step 18760: {'lr': 0.000484345151757538, 'samples': 9605632, 'steps': 18760, 'loss/train': 1.6078579425811768}
-03/04/2022 11:29:44 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/04/2022 11:29:50 - INFO - codeparrot_training - Step 18761: {'lr': 0.0004843433033298237, 'samples': 9606144, 'steps': 18761, 'loss/train': 2.0058186054229736}
-03/04/2022 11:29:53 - INFO - codeparrot_training - Step 18762: {'lr': 0.00048434145479651783, 'samples': 9606656, 'steps': 18762, 'loss/train': 0.9449602961540222}
-03/04/2022 11:29:53 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/04/2022 11:29:58 - INFO - codeparrot_training - Step 18763: {'lr': 0.00048433960615762136, 'samples': 9607168, 'steps': 18763, 'loss/train': 1.5731689929962158}
-03/04/2022 11:30:01 - INFO - codeparrot_training - Step 18764: {'lr': 0.0004843377574131351, 'samples': 9607680, 'steps': 18764, 'loss/train': 2.0683114528656006}
-03/04/2022 11:30:01 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/04/2022 11:30:06 - INFO - codeparrot_training - Step 18765: {'lr': 0.0004843359085630598, 'samples': 9608192, 'steps': 18765, 'loss/train': 1.8814387321472168}
-03/04/2022 11:30:10 - INFO - codeparrot_training - Step 18766: {'lr': 0.0004843340596073964, 'samples': 9608704, 'steps': 18766, 'loss/train': 2.196035623550415}
-03/04/2022 11:30:10 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 11:30:15 - INFO - codeparrot_training - Step 18767: {'lr': 0.0004843322105461457, 'samples': 9609216, 'steps': 18767, 'loss/train': 1.5553410053253174}
-03/04/2022 11:30:18 - INFO - codeparrot_training - Step 18768: {'lr': 0.0004843303613793085, 'samples': 9609728, 'steps': 18768, 'loss/train': 1.979210615158081}
-03/04/2022 11:30:18 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/04/2022 11:30:23 - INFO - codeparrot_training - Step 18769: {'lr': 0.00048432851210688567, 'samples': 9610240, 'steps': 18769, 'loss/train': 1.5078314542770386}
-03/04/2022 11:30:27 - INFO - codeparrot_training - Step 18770: {'lr': 0.00048432666272887805, 'samples': 9610752, 'steps': 18770, 'loss/train': 0.7725059390068054}
-03/04/2022 11:30:27 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/04/2022 11:30:32 - INFO - codeparrot_training - Step 18771: {'lr': 0.0004843248132452864, 'samples': 9611264, 'steps': 18771, 'loss/train': 2.1700289249420166}
-03/04/2022 11:30:35 - INFO - codeparrot_training - Step 18772: {'lr': 0.0004843229636561116, 'samples': 9611776, 'steps': 18772, 'loss/train': 2.0334813594818115}
-03/04/2022 11:30:36 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/04/2022 11:30:40 - INFO - codeparrot_training - Step 18773: {'lr': 0.00048432111396135447, 'samples': 9612288, 'steps': 18773, 'loss/train': 0.9832890629768372}
-03/04/2022 11:30:43 - INFO - codeparrot_training - Step 18774: {'lr': 0.0004843192641610159, 'samples': 9612800, 'steps': 18774, 'loss/train': 1.4118719100952148}
-03/04/2022 11:30:44 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/04/2022 11:30:49 - INFO - codeparrot_training - Step 18775: {'lr': 0.00048431741425509676, 'samples': 9613312, 'steps': 18775, 'loss/train': 1.9816854000091553}
-03/04/2022 11:30:52 - INFO - codeparrot_training - Step 18776: {'lr': 0.0004843155642435977, 'samples': 9613824, 'steps': 18776, 'loss/train': 2.5705301761627197}
-03/04/2022 11:30:53 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 11:30:57 - INFO - codeparrot_training - Step 18777: {'lr': 0.0004843137141265197, 'samples': 9614336, 'steps': 18777, 'loss/train': 2.2404863834381104}
-03/04/2022 11:31:00 - INFO - codeparrot_training - Step 18778: {'lr': 0.00048431186390386356, 'samples': 9614848, 'steps': 18778, 'loss/train': 2.130772113800049}
-03/04/2022 11:31:02 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 11:31:06 - INFO - codeparrot_training - Step 18779: {'lr': 0.0004843100135756301, 'samples': 9615360, 'steps': 18779, 'loss/train': 1.9024523496627808}
-03/04/2022 11:31:09 - INFO - codeparrot_training - Step 18780: {'lr': 0.0004843081631418202, 'samples': 9615872, 'steps': 18780, 'loss/train': 1.7291662693023682}
-03/04/2022 11:31:10 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/04/2022 11:31:14 - INFO - codeparrot_training - Step 18781: {'lr': 0.00048430631260243465, 'samples': 9616384, 'steps': 18781, 'loss/train': 0.40338289737701416}
-03/04/2022 11:31:17 - INFO - codeparrot_training - Step 18782: {'lr': 0.00048430446195747424, 'samples': 9616896, 'steps': 18782, 'loss/train': 1.7083451747894287}
-03/04/2022 11:31:19 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 11:31:23 - INFO - codeparrot_training - Step 18783: {'lr': 0.00048430261120693986, 'samples': 9617408, 'steps': 18783, 'loss/train': 1.6826075315475464}
-03/04/2022 11:31:26 - INFO - codeparrot_training - Step 18784: {'lr': 0.0004843007603508324, 'samples': 9617920, 'steps': 18784, 'loss/train': 1.7044516801834106}
-03/04/2022 11:31:27 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 11:31:31 - INFO - codeparrot_training - Step 18785: {'lr': 0.00048429890938915255, 'samples': 9618432, 'steps': 18785, 'loss/train': 2.071485996246338}
-03/04/2022 11:31:35 - INFO - codeparrot_training - Step 18786: {'lr': 0.0004842970583219013, 'samples': 9618944, 'steps': 18786, 'loss/train': 1.734368085861206}
-03/04/2022 11:31:37 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 11:31:40 - INFO - codeparrot_training - Step 18787: {'lr': 0.0004842952071490794, 'samples': 9619456, 'steps': 18787, 'loss/train': 1.2761015892028809}
-03/04/2022 11:31:43 - INFO - codeparrot_training - Step 18788: {'lr': 0.0004842933558706877, 'samples': 9619968, 'steps': 18788, 'loss/train': 2.4544172286987305}
-03/04/2022 11:31:45 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/04/2022 11:31:48 - INFO - codeparrot_training - Step 18789: {'lr': 0.000484291504486727, 'samples': 9620480, 'steps': 18789, 'loss/train': 1.68110990524292}
-03/04/2022 11:31:51 - INFO - codeparrot_training - Step 18790: {'lr': 0.0004842896529971982, 'samples': 9620992, 'steps': 18790, 'loss/train': 1.950022578239441}
-03/04/2022 11:31:54 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/04/2022 11:31:57 - INFO - codeparrot_training - Step 18791: {'lr': 0.00048428780140210204, 'samples': 9621504, 'steps': 18791, 'loss/train': 1.8345999717712402}
-03/04/2022 11:32:00 - INFO - codeparrot_training - Step 18792: {'lr': 0.0004842859497014394, 'samples': 9622016, 'steps': 18792, 'loss/train': 2.5877773761749268}
-03/04/2022 11:32:02 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/04/2022 11:32:05 - INFO - codeparrot_training - Step 18793: {'lr': 0.0004842840978952112, 'samples': 9622528, 'steps': 18793, 'loss/train': 1.6293140649795532}
-03/04/2022 11:32:09 - INFO - codeparrot_training - Step 18794: {'lr': 0.00048428224598341815, 'samples': 9623040, 'steps': 18794, 'loss/train': 2.328880548477173}
-03/04/2022 11:32:12 - INFO - codeparrot_training - Step 18795: {'lr': 0.0004842803939660612, 'samples': 9623552, 'steps': 18795, 'loss/train': 2.7087950706481934}
-03/04/2022 11:32:12 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 11:32:17 - INFO - codeparrot_training - Step 18796: {'lr': 0.00048427854184314103, 'samples': 9624064, 'steps': 18796, 'loss/train': 1.5651978254318237}
-03/04/2022 11:32:20 - INFO - codeparrot_training - Step 18797: {'lr': 0.0004842766896146586, 'samples': 9624576, 'steps': 18797, 'loss/train': 1.7399743795394897}
-03/04/2022 11:32:20 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 11:32:25 - INFO - codeparrot_training - Step 18798: {'lr': 0.0004842748372806147, 'samples': 9625088, 'steps': 18798, 'loss/train': 1.9911308288574219}
-03/04/2022 11:32:29 - INFO - codeparrot_training - Step 18799: {'lr': 0.00048427298484101023, 'samples': 9625600, 'steps': 18799, 'loss/train': 1.6232185363769531}
-03/04/2022 11:32:29 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 11:32:34 - INFO - codeparrot_training - Step 18800: {'lr': 0.0004842711322958459, 'samples': 9626112, 'steps': 18800, 'loss/train': 1.7984949350357056}
-03/04/2022 11:32:37 - INFO - codeparrot_training - Step 18801: {'lr': 0.0004842692796451226, 'samples': 9626624, 'steps': 18801, 'loss/train': 2.115788459777832}
-03/04/2022 11:32:37 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/04/2022 11:32:42 - INFO - codeparrot_training - Step 18802: {'lr': 0.0004842674268888413, 'samples': 9627136, 'steps': 18802, 'loss/train': 2.425422191619873}
-03/04/2022 11:32:46 - INFO - codeparrot_training - Step 18803: {'lr': 0.0004842655740270026, 'samples': 9627648, 'steps': 18803, 'loss/train': 2.3153176307678223}
-03/04/2022 11:32:46 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/04/2022 11:32:51 - INFO - codeparrot_training - Step 18804: {'lr': 0.0004842637210596075, 'samples': 9628160, 'steps': 18804, 'loss/train': 2.315945863723755}
-03/04/2022 11:32:54 - INFO - codeparrot_training - Step 18805: {'lr': 0.0004842618679866567, 'samples': 9628672, 'steps': 18805, 'loss/train': 2.0727834701538086}
-03/04/2022 11:32:54 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 11:32:59 - INFO - codeparrot_training - Step 18806: {'lr': 0.0004842600148081512, 'samples': 9629184, 'steps': 18806, 'loss/train': 1.867490291595459}
-03/04/2022 11:33:03 - INFO - codeparrot_training - Step 18807: {'lr': 0.00048425816152409173, 'samples': 9629696, 'steps': 18807, 'loss/train': 1.857409954071045}
-03/04/2022 11:33:03 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/04/2022 11:33:08 - INFO - codeparrot_training - Step 18808: {'lr': 0.00048425630813447916, 'samples': 9630208, 'steps': 18808, 'loss/train': 1.7350701093673706}
-03/04/2022 11:33:11 - INFO - codeparrot_training - Step 18809: {'lr': 0.0004842544546393143, 'samples': 9630720, 'steps': 18809, 'loss/train': 2.1851868629455566}
-03/04/2022 11:33:11 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/04/2022 11:33:16 - INFO - codeparrot_training - Step 18810: {'lr': 0.00048425260103859797, 'samples': 9631232, 'steps': 18810, 'loss/train': 1.3644074201583862}
-03/04/2022 11:33:19 - INFO - codeparrot_training - Step 18811: {'lr': 0.0004842507473323311, 'samples': 9631744, 'steps': 18811, 'loss/train': 1.9206910133361816}
-03/04/2022 11:33:20 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/04/2022 11:33:25 - INFO - codeparrot_training - Step 18812: {'lr': 0.00048424889352051436, 'samples': 9632256, 'steps': 18812, 'loss/train': 2.1552112102508545}
-03/04/2022 11:33:28 - INFO - codeparrot_training - Step 18813: {'lr': 0.00048424703960314876, 'samples': 9632768, 'steps': 18813, 'loss/train': 1.8455636501312256}
-03/04/2022 11:33:29 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/04/2022 11:33:33 - INFO - codeparrot_training - Step 18814: {'lr': 0.00048424518558023505, 'samples': 9633280, 'steps': 18814, 'loss/train': 1.9680267572402954}
-03/04/2022 11:33:36 - INFO - codeparrot_training - Step 18815: {'lr': 0.00048424333145177405, 'samples': 9633792, 'steps': 18815, 'loss/train': 1.1750985383987427}
-03/04/2022 11:33:37 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 11:33:42 - INFO - codeparrot_training - Step 18816: {'lr': 0.00048424147721776666, 'samples': 9634304, 'steps': 18816, 'loss/train': 1.6044591665267944}
-03/04/2022 11:33:45 - INFO - codeparrot_training - Step 18817: {'lr': 0.00048423962287821366, 'samples': 9634816, 'steps': 18817, 'loss/train': 1.5276528596878052}
-03/04/2022 11:33:46 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/04/2022 11:33:50 - INFO - codeparrot_training - Step 18818: {'lr': 0.00048423776843311585, 'samples': 9635328, 'steps': 18818, 'loss/train': 1.3185639381408691}
-03/04/2022 11:33:53 - INFO - codeparrot_training - Step 18819: {'lr': 0.00048423591388247416, 'samples': 9635840, 'steps': 18819, 'loss/train': 2.2984344959259033}
-03/04/2022 11:33:54 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/04/2022 11:33:59 - INFO - codeparrot_training - Step 18820: {'lr': 0.0004842340592262894, 'samples': 9636352, 'steps': 18820, 'loss/train': 1.6472363471984863}
-03/04/2022 11:34:02 - INFO - codeparrot_training - Step 18821: {'lr': 0.00048423220446456233, 'samples': 9636864, 'steps': 18821, 'loss/train': 1.7826682329177856}
-03/04/2022 11:34:02 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 11:34:07 - INFO - codeparrot_training - Step 18822: {'lr': 0.0004842303495972939, 'samples': 9637376, 'steps': 18822, 'loss/train': 1.6552066802978516}
-03/04/2022 11:34:10 - INFO - codeparrot_training - Step 18823: {'lr': 0.00048422849462448483, 'samples': 9637888, 'steps': 18823, 'loss/train': 1.492329716682434}
-03/04/2022 11:34:11 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 11:34:16 - INFO - codeparrot_training - Step 18824: {'lr': 0.0004842266395461361, 'samples': 9638400, 'steps': 18824, 'loss/train': 0.8477040529251099}
-03/04/2022 11:34:19 - INFO - codeparrot_training - Step 18825: {'lr': 0.0004842247843622484, 'samples': 9638912, 'steps': 18825, 'loss/train': 2.4148192405700684}
-03/04/2022 11:34:19 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/04/2022 11:34:24 - INFO - codeparrot_training - Step 18826: {'lr': 0.0004842229290728226, 'samples': 9639424, 'steps': 18826, 'loss/train': 2.385000228881836}
-03/04/2022 11:34:28 - INFO - codeparrot_training - Step 18827: {'lr': 0.0004842210736778596, 'samples': 9639936, 'steps': 18827, 'loss/train': 2.152012825012207}
-03/04/2022 11:34:29 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/04/2022 11:34:33 - INFO - codeparrot_training - Step 18828: {'lr': 0.0004842192181773602, 'samples': 9640448, 'steps': 18828, 'loss/train': 1.4903982877731323}
-03/04/2022 11:34:36 - INFO - codeparrot_training - Step 18829: {'lr': 0.0004842173625713252, 'samples': 9640960, 'steps': 18829, 'loss/train': 2.1151227951049805}
-03/04/2022 11:34:38 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 11:34:41 - INFO - codeparrot_training - Step 18830: {'lr': 0.0004842155068597556, 'samples': 9641472, 'steps': 18830, 'loss/train': 2.022162675857544}
-03/04/2022 11:34:44 - INFO - codeparrot_training - Step 18831: {'lr': 0.0004842136510426519, 'samples': 9641984, 'steps': 18831, 'loss/train': 1.7516696453094482}
-03/04/2022 11:34:46 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 11:34:50 - INFO - codeparrot_training - Step 18832: {'lr': 0.00048421179512001536, 'samples': 9642496, 'steps': 18832, 'loss/train': 2.323667287826538}
-03/04/2022 11:34:53 - INFO - codeparrot_training - Step 18833: {'lr': 0.0004842099390918464, 'samples': 9643008, 'steps': 18833, 'loss/train': 1.1472338438034058}
-03/04/2022 11:34:55 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/04/2022 11:34:58 - INFO - codeparrot_training - Step 18834: {'lr': 0.00048420808295814624, 'samples': 9643520, 'steps': 18834, 'loss/train': 1.6151005029678345}
-03/04/2022 11:35:01 - INFO - codeparrot_training - Step 18835: {'lr': 0.00048420622671891533, 'samples': 9644032, 'steps': 18835, 'loss/train': 1.7424150705337524}
-03/04/2022 11:35:03 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/04/2022 11:35:06 - INFO - codeparrot_training - Step 18836: {'lr': 0.00048420437037415486, 'samples': 9644544, 'steps': 18836, 'loss/train': 2.0469555854797363}
-03/04/2022 11:35:10 - INFO - codeparrot_training - Step 18837: {'lr': 0.00048420251392386547, 'samples': 9645056, 'steps': 18837, 'loss/train': 2.0514585971832275}
-03/04/2022 11:35:12 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/04/2022 11:35:15 - INFO - codeparrot_training - Step 18838: {'lr': 0.0004842006573680481, 'samples': 9645568, 'steps': 18838, 'loss/train': 1.6851743459701538}
-03/04/2022 11:35:18 - INFO - codeparrot_training - Step 18839: {'lr': 0.0004841988007067034, 'samples': 9646080, 'steps': 18839, 'loss/train': 2.150240182876587}
-03/04/2022 11:35:20 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/04/2022 11:35:23 - INFO - codeparrot_training - Step 18840: {'lr': 0.00048419694393983244, 'samples': 9646592, 'steps': 18840, 'loss/train': 1.399125099182129}
-03/04/2022 11:35:26 - INFO - codeparrot_training - Step 18841: {'lr': 0.00048419508706743587, 'samples': 9647104, 'steps': 18841, 'loss/train': 1.7481093406677246}
-03/04/2022 11:35:28 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 11:35:32 - INFO - codeparrot_training - Step 18842: {'lr': 0.00048419323008951467, 'samples': 9647616, 'steps': 18842, 'loss/train': 0.8703935146331787}
-03/04/2022 11:35:35 - INFO - codeparrot_training - Step 18843: {'lr': 0.00048419137300606963, 'samples': 9648128, 'steps': 18843, 'loss/train': 2.217064142227173}
-03/04/2022 11:35:37 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 11:35:40 - INFO - codeparrot_training - Step 18844: {'lr': 0.00048418951581710154, 'samples': 9648640, 'steps': 18844, 'loss/train': 1.8804919719696045}
-03/04/2022 11:35:43 - INFO - codeparrot_training - Step 18845: {'lr': 0.00048418765852261124, 'samples': 9649152, 'steps': 18845, 'loss/train': 1.0722016096115112}
-03/04/2022 11:35:45 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/04/2022 11:35:49 - INFO - codeparrot_training - Step 18846: {'lr': 0.0004841858011225996, 'samples': 9649664, 'steps': 18846, 'loss/train': 2.064152956008911}
-03/04/2022 11:35:52 - INFO - codeparrot_training - Step 18847: {'lr': 0.0004841839436170675, 'samples': 9650176, 'steps': 18847, 'loss/train': 2.1688082218170166}
-03/04/2022 11:35:54 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/04/2022 11:35:57 - INFO - codeparrot_training - Step 18848: {'lr': 0.0004841820860060157, 'samples': 9650688, 'steps': 18848, 'loss/train': 2.0846259593963623}
-03/04/2022 11:36:00 - INFO - codeparrot_training - Step 18849: {'lr': 0.0004841802282894451, 'samples': 9651200, 'steps': 18849, 'loss/train': 2.3165507316589355}
-03/04/2022 11:36:02 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/04/2022 11:36:06 - INFO - codeparrot_training - Step 18850: {'lr': 0.0004841783704673565, 'samples': 9651712, 'steps': 18850, 'loss/train': 2.692078113555908}
-03/04/2022 11:36:09 - INFO - codeparrot_training - Step 18851: {'lr': 0.00048417651253975067, 'samples': 9652224, 'steps': 18851, 'loss/train': 1.9232019186019897}
-03/04/2022 11:36:11 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/04/2022 11:36:14 - INFO - codeparrot_training - Step 18852: {'lr': 0.00048417465450662856, 'samples': 9652736, 'steps': 18852, 'loss/train': 1.7609304189682007}
-03/04/2022 11:36:17 - INFO - codeparrot_training - Step 18853: {'lr': 0.0004841727963679909, 'samples': 9653248, 'steps': 18853, 'loss/train': 2.05295729637146}
-03/04/2022 11:36:19 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 11:36:22 - INFO - codeparrot_training - Step 18854: {'lr': 0.0004841709381238387, 'samples': 9653760, 'steps': 18854, 'loss/train': 1.6966197490692139}
-03/04/2022 11:36:26 - INFO - codeparrot_training - Step 18855: {'lr': 0.0004841690797741726, 'samples': 9654272, 'steps': 18855, 'loss/train': 1.5814461708068848}
-03/04/2022 11:36:28 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/04/2022 11:36:31 - INFO - codeparrot_training - Step 18856: {'lr': 0.0004841672213189936, 'samples': 9654784, 'steps': 18856, 'loss/train': 2.0249903202056885}
-03/04/2022 11:36:34 - INFO - codeparrot_training - Step 18857: {'lr': 0.00048416536275830245, 'samples': 9655296, 'steps': 18857, 'loss/train': 1.6269772052764893}
-03/04/2022 11:36:36 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/04/2022 11:36:39 - INFO - codeparrot_training - Step 18858: {'lr': 0.00048416350409209995, 'samples': 9655808, 'steps': 18858, 'loss/train': 1.9774409532546997}
-03/04/2022 11:36:42 - INFO - codeparrot_training - Step 18859: {'lr': 0.000484161645320387, 'samples': 9656320, 'steps': 18859, 'loss/train': 0.8609490990638733}
-03/04/2022 11:36:45 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/04/2022 11:36:48 - INFO - codeparrot_training - Step 18860: {'lr': 0.0004841597864431645, 'samples': 9656832, 'steps': 18860, 'loss/train': 1.1048015356063843}
-03/04/2022 11:36:51 - INFO - codeparrot_training - Step 18861: {'lr': 0.00048415792746043314, 'samples': 9657344, 'steps': 18861, 'loss/train': 1.8426761627197266}
-03/04/2022 11:36:53 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/04/2022 11:36:56 - INFO - codeparrot_training - Step 18862: {'lr': 0.00048415606837219383, 'samples': 9657856, 'steps': 18862, 'loss/train': 1.9556596279144287}
-03/04/2022 11:36:59 - INFO - codeparrot_training - Step 18863: {'lr': 0.00048415420917844744, 'samples': 9658368, 'steps': 18863, 'loss/train': 2.4026763439178467}
-03/04/2022 11:37:01 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/04/2022 11:37:04 - INFO - codeparrot_training - Step 18864: {'lr': 0.00048415234987919474, 'samples': 9658880, 'steps': 18864, 'loss/train': 2.398061990737915}
-03/04/2022 11:37:08 - INFO - codeparrot_training - Step 18865: {'lr': 0.0004841504904744367, 'samples': 9659392, 'steps': 18865, 'loss/train': 1.456453561782837}
-03/04/2022 11:37:10 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/04/2022 11:37:13 - INFO - codeparrot_training - Step 18866: {'lr': 0.0004841486309641739, 'samples': 9659904, 'steps': 18866, 'loss/train': 2.2722597122192383}
-03/04/2022 11:37:16 - INFO - codeparrot_training - Step 18867: {'lr': 0.00048414677134840753, 'samples': 9660416, 'steps': 18867, 'loss/train': 1.5971976518630981}
-03/04/2022 11:37:18 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/04/2022 11:37:21 - INFO - codeparrot_training - Step 18868: {'lr': 0.00048414491162713814, 'samples': 9660928, 'steps': 18868, 'loss/train': 1.6686257123947144}
-03/04/2022 11:37:24 - INFO - codeparrot_training - Step 18869: {'lr': 0.00048414305180036665, 'samples': 9661440, 'steps': 18869, 'loss/train': 1.4527621269226074}
-03/04/2022 11:37:27 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/04/2022 11:37:30 - INFO - codeparrot_training - Step 18870: {'lr': 0.0004841411918680939, 'samples': 9661952, 'steps': 18870, 'loss/train': 2.0201773643493652}
-03/04/2022 11:37:33 - INFO - codeparrot_training - Step 18871: {'lr': 0.0004841393318303208, 'samples': 9662464, 'steps': 18871, 'loss/train': 2.09139347076416}
-03/04/2022 11:37:35 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/04/2022 11:37:38 - INFO - codeparrot_training - Step 18872: {'lr': 0.0004841374716870481, 'samples': 9662976, 'steps': 18872, 'loss/train': 1.3751871585845947}
-03/04/2022 11:37:41 - INFO - codeparrot_training - Step 18873: {'lr': 0.00048413561143827665, 'samples': 9663488, 'steps': 18873, 'loss/train': 1.838456392288208}
-03/04/2022 11:37:43 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/04/2022 11:37:47 - INFO - codeparrot_training - Step 18874: {'lr': 0.00048413375108400736, 'samples': 9664000, 'steps': 18874, 'loss/train': 1.8765060901641846}
-03/04/2022 11:37:50 - INFO - codeparrot_training - Step 18875: {'lr': 0.000484131890624241, 'samples': 9664512, 'steps': 18875, 'loss/train': 2.359983205795288}
-03/04/2022 11:37:52 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 11:37:55 - INFO - codeparrot_training - Step 18876: {'lr': 0.00048413003005897835, 'samples': 9665024, 'steps': 18876, 'loss/train': 0.865959644317627}
-03/04/2022 11:37:58 - INFO - codeparrot_training - Step 18877: {'lr': 0.0004841281693882204, 'samples': 9665536, 'steps': 18877, 'loss/train': 2.9329640865325928}
-03/04/2022 11:38:00 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/04/2022 11:38:03 - INFO - codeparrot_training - Step 18878: {'lr': 0.0004841263086119679, 'samples': 9666048, 'steps': 18878, 'loss/train': 1.5220533609390259}
-03/04/2022 11:38:06 - INFO - codeparrot_training - Step 18879: {'lr': 0.00048412444773022166, 'samples': 9666560, 'steps': 18879, 'loss/train': 2.1814446449279785}
-03/04/2022 11:38:08 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/04/2022 11:38:12 - INFO - codeparrot_training - Step 18880: {'lr': 0.0004841225867429826, 'samples': 9667072, 'steps': 18880, 'loss/train': 1.748016119003296}
-03/04/2022 11:38:15 - INFO - codeparrot_training - Step 18881: {'lr': 0.0004841207256502515, 'samples': 9667584, 'steps': 18881, 'loss/train': 1.4086146354675293}
-03/04/2022 11:38:17 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 11:38:20 - INFO - codeparrot_training - Step 18882: {'lr': 0.0004841188644520292, 'samples': 9668096, 'steps': 18882, 'loss/train': 0.8337785601615906}
-03/04/2022 11:38:23 - INFO - codeparrot_training - Step 18883: {'lr': 0.0004841170031483165, 'samples': 9668608, 'steps': 18883, 'loss/train': 1.4421498775482178}
-03/04/2022 11:38:25 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/04/2022 11:38:29 - INFO - codeparrot_training - Step 18884: {'lr': 0.0004841151417391144, 'samples': 9669120, 'steps': 18884, 'loss/train': 2.093618631362915}
-03/04/2022 11:38:32 - INFO - codeparrot_training - Step 18885: {'lr': 0.00048411328022442357, 'samples': 9669632, 'steps': 18885, 'loss/train': 0.3024679720401764}
-03/04/2022 11:38:33 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/04/2022 11:38:37 - INFO - codeparrot_training - Step 18886: {'lr': 0.000484111418604245, 'samples': 9670144, 'steps': 18886, 'loss/train': 0.9253832697868347}
-03/04/2022 11:38:40 - INFO - codeparrot_training - Step 18887: {'lr': 0.00048410955687857926, 'samples': 9670656, 'steps': 18887, 'loss/train': 1.9889194965362549}
-03/04/2022 11:38:42 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/04/2022 11:38:45 - INFO - codeparrot_training - Step 18888: {'lr': 0.0004841076950474275, 'samples': 9671168, 'steps': 18888, 'loss/train': 2.1439049243927}
-03/04/2022 11:38:49 - INFO - codeparrot_training - Step 18889: {'lr': 0.0004841058331107904, 'samples': 9671680, 'steps': 18889, 'loss/train': 1.5098984241485596}
-03/04/2022 11:38:50 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 11:38:54 - INFO - codeparrot_training - Step 18890: {'lr': 0.00048410397106866883, 'samples': 9672192, 'steps': 18890, 'loss/train': 2.2515597343444824}
-03/04/2022 11:38:57 - INFO - codeparrot_training - Step 18891: {'lr': 0.0004841021089210636, 'samples': 9672704, 'steps': 18891, 'loss/train': 1.8628891706466675}
-03/04/2022 11:38:59 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/04/2022 11:39:03 - INFO - codeparrot_training - Step 18892: {'lr': 0.0004841002466679756, 'samples': 9673216, 'steps': 18892, 'loss/train': 1.9686559438705444}
-03/04/2022 11:39:06 - INFO - codeparrot_training - Step 18893: {'lr': 0.00048409838430940556, 'samples': 9673728, 'steps': 18893, 'loss/train': 2.1620476245880127}
-03/04/2022 11:39:09 - INFO - codeparrot_training - Step 18894: {'lr': 0.00048409652184535447, 'samples': 9674240, 'steps': 18894, 'loss/train': 2.1118781566619873}
-03/04/2022 11:39:10 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/04/2022 11:39:15 - INFO - codeparrot_training - Step 18895: {'lr': 0.0004840946592758231, 'samples': 9674752, 'steps': 18895, 'loss/train': 1.2853448390960693}
-03/04/2022 11:39:18 - INFO - codeparrot_training - Step 18896: {'lr': 0.00048409279660081226, 'samples': 9675264, 'steps': 18896, 'loss/train': 1.9561264514923096}
-03/04/2022 11:39:18 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 11:39:23 - INFO - codeparrot_training - Step 18897: {'lr': 0.0004840909338203229, 'samples': 9675776, 'steps': 18897, 'loss/train': 1.5552215576171875}
-03/04/2022 11:39:26 - INFO - codeparrot_training - Step 18898: {'lr': 0.0004840890709343557, 'samples': 9676288, 'steps': 18898, 'loss/train': 1.9831048250198364}
-03/04/2022 11:39:27 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/04/2022 11:39:32 - INFO - codeparrot_training - Step 18899: {'lr': 0.0004840872079429116, 'samples': 9676800, 'steps': 18899, 'loss/train': 2.1790332794189453}
-03/04/2022 11:39:35 - INFO - codeparrot_training - Step 18900: {'lr': 0.00048408534484599143, 'samples': 9677312, 'steps': 18900, 'loss/train': 0.7052431702613831}
-03/04/2022 11:39:35 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/04/2022 11:39:40 - INFO - codeparrot_training - Step 18901: {'lr': 0.00048408348164359594, 'samples': 9677824, 'steps': 18901, 'loss/train': 2.4601945877075195}
-03/04/2022 11:39:43 - INFO - codeparrot_training - Step 18902: {'lr': 0.00048408161833572613, 'samples': 9678336, 'steps': 18902, 'loss/train': 0.45307451486587524}
-03/04/2022 11:39:44 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/04/2022 11:39:48 - INFO - codeparrot_training - Step 18903: {'lr': 0.0004840797549223827, 'samples': 9678848, 'steps': 18903, 'loss/train': 1.3949933052062988}
-03/04/2022 11:39:52 - INFO - codeparrot_training - Step 18904: {'lr': 0.00048407789140356654, 'samples': 9679360, 'steps': 18904, 'loss/train': 2.1120448112487793}
-03/04/2022 11:39:52 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/04/2022 11:39:57 - INFO - codeparrot_training - Step 18905: {'lr': 0.00048407602777927856, 'samples': 9679872, 'steps': 18905, 'loss/train': 1.866988182067871}
-03/04/2022 11:40:00 - INFO - codeparrot_training - Step 18906: {'lr': 0.0004840741640495195, 'samples': 9680384, 'steps': 18906, 'loss/train': 1.9366118907928467}
-03/04/2022 11:40:01 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/04/2022 11:40:05 - INFO - codeparrot_training - Step 18907: {'lr': 0.0004840723002142902, 'samples': 9680896, 'steps': 18907, 'loss/train': 1.7483357191085815}
-03/04/2022 11:40:09 - INFO - codeparrot_training - Step 18908: {'lr': 0.0004840704362735916, 'samples': 9681408, 'steps': 18908, 'loss/train': 1.833714485168457}
-03/04/2022 11:40:09 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/04/2022 11:40:14 - INFO - codeparrot_training - Step 18909: {'lr': 0.0004840685722274244, 'samples': 9681920, 'steps': 18909, 'loss/train': 2.896550178527832}
-03/04/2022 11:40:17 - INFO - codeparrot_training - Step 18910: {'lr': 0.0004840667080757896, 'samples': 9682432, 'steps': 18910, 'loss/train': 0.30527424812316895}
-03/04/2022 11:40:20 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/04/2022 11:40:23 - INFO - codeparrot_training - Step 18911: {'lr': 0.00048406484381868786, 'samples': 9682944, 'steps': 18911, 'loss/train': 2.285104274749756}
-03/04/2022 11:40:26 - INFO - codeparrot_training - Step 18912: {'lr': 0.0004840629794561202, 'samples': 9683456, 'steps': 18912, 'loss/train': 2.1645188331604004}
-03/04/2022 11:40:28 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/04/2022 11:40:31 - INFO - codeparrot_training - Step 18913: {'lr': 0.0004840611149880873, 'samples': 9683968, 'steps': 18913, 'loss/train': 2.071486473083496}
-03/04/2022 11:40:34 - INFO - codeparrot_training - Step 18914: {'lr': 0.0004840592504145901, 'samples': 9684480, 'steps': 18914, 'loss/train': 2.4001708030700684}
-03/04/2022 11:40:36 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 11:40:40 - INFO - codeparrot_training - Step 18915: {'lr': 0.0004840573857356294, 'samples': 9684992, 'steps': 18915, 'loss/train': 1.8180575370788574}
-03/04/2022 11:40:43 - INFO - codeparrot_training - Step 18916: {'lr': 0.0004840555209512061, 'samples': 9685504, 'steps': 18916, 'loss/train': 1.3874621391296387}
-03/04/2022 11:40:45 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/04/2022 11:40:48 - INFO - codeparrot_training - Step 18917: {'lr': 0.00048405365606132096, 'samples': 9686016, 'steps': 18917, 'loss/train': 2.131986379623413}
-03/04/2022 11:40:51 - INFO - codeparrot_training - Step 18918: {'lr': 0.00048405179106597487, 'samples': 9686528, 'steps': 18918, 'loss/train': 2.083812713623047}
-03/04/2022 11:40:53 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/04/2022 11:40:56 - INFO - codeparrot_training - Step 18919: {'lr': 0.0004840499259651686, 'samples': 9687040, 'steps': 18919, 'loss/train': 1.722593069076538}
-03/04/2022 11:41:00 - INFO - codeparrot_training - Step 18920: {'lr': 0.0004840480607589031, 'samples': 9687552, 'steps': 18920, 'loss/train': 1.0751938819885254}
-03/04/2022 11:41:01 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/04/2022 11:41:05 - INFO - codeparrot_training - Step 18921: {'lr': 0.0004840461954471792, 'samples': 9688064, 'steps': 18921, 'loss/train': 1.32506263256073}
-03/04/2022 11:41:08 - INFO - codeparrot_training - Step 18922: {'lr': 0.00048404433002999757, 'samples': 9688576, 'steps': 18922, 'loss/train': 1.8463013172149658}
-03/04/2022 11:41:10 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/04/2022 11:41:13 - INFO - codeparrot_training - Step 18923: {'lr': 0.0004840424645073593, 'samples': 9689088, 'steps': 18923, 'loss/train': 1.4452793598175049}
-03/04/2022 11:41:17 - INFO - codeparrot_training - Step 18924: {'lr': 0.000484040598879265, 'samples': 9689600, 'steps': 18924, 'loss/train': 1.8344627618789673}
-03/04/2022 11:41:18 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/04/2022 11:41:22 - INFO - codeparrot_training - Step 18925: {'lr': 0.0004840387331457157, 'samples': 9690112, 'steps': 18925, 'loss/train': 1.174454689025879}
-03/04/2022 11:41:25 - INFO - codeparrot_training - Step 18926: {'lr': 0.00048403686730671215, 'samples': 9690624, 'steps': 18926, 'loss/train': 2.839798927307129}
-03/04/2022 11:41:27 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/04/2022 11:41:30 - INFO - codeparrot_training - Step 18927: {'lr': 0.0004840350013622552, 'samples': 9691136, 'steps': 18927, 'loss/train': 2.109863042831421}
-03/04/2022 11:41:34 - INFO - codeparrot_training - Step 18928: {'lr': 0.0004840331353123456, 'samples': 9691648, 'steps': 18928, 'loss/train': 1.0836116075515747}
-03/04/2022 11:41:35 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 11:41:39 - INFO - codeparrot_training - Step 18929: {'lr': 0.00048403126915698435, 'samples': 9692160, 'steps': 18929, 'loss/train': 1.998971700668335}
-03/04/2022 11:41:42 - INFO - codeparrot_training - Step 18930: {'lr': 0.00048402940289617223, 'samples': 9692672, 'steps': 18930, 'loss/train': 2.094602346420288}
-03/04/2022 11:41:44 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 11:41:47 - INFO - codeparrot_training - Step 18931: {'lr': 0.00048402753652991007, 'samples': 9693184, 'steps': 18931, 'loss/train': 2.234116315841675}
-03/04/2022 11:41:51 - INFO - codeparrot_training - Step 18932: {'lr': 0.0004840256700581988, 'samples': 9693696, 'steps': 18932, 'loss/train': 1.6848856210708618}
-03/04/2022 11:41:53 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 11:41:56 - INFO - codeparrot_training - Step 18933: {'lr': 0.000484023803481039, 'samples': 9694208, 'steps': 18933, 'loss/train': 1.5142589807510376}
-03/04/2022 11:41:59 - INFO - codeparrot_training - Step 18934: {'lr': 0.00048402193679843175, 'samples': 9694720, 'steps': 18934, 'loss/train': 1.6145626306533813}
-03/04/2022 11:42:01 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/04/2022 11:42:04 - INFO - codeparrot_training - Step 18935: {'lr': 0.00048402007001037786, 'samples': 9695232, 'steps': 18935, 'loss/train': 2.3712897300720215}
-03/04/2022 11:42:07 - INFO - codeparrot_training - Step 18936: {'lr': 0.0004840182031168781, 'samples': 9695744, 'steps': 18936, 'loss/train': 2.1619105339050293}
-03/04/2022 11:42:10 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/04/2022 11:42:13 - INFO - codeparrot_training - Step 18937: {'lr': 0.0004840163361179334, 'samples': 9696256, 'steps': 18937, 'loss/train': 1.4338833093643188}
-03/04/2022 11:42:16 - INFO - codeparrot_training - Step 18938: {'lr': 0.00048401446901354453, 'samples': 9696768, 'steps': 18938, 'loss/train': 1.5021555423736572}
-03/04/2022 11:42:18 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 11:42:21 - INFO - codeparrot_training - Step 18939: {'lr': 0.0004840126018037123, 'samples': 9697280, 'steps': 18939, 'loss/train': 2.1810550689697266}
-03/04/2022 11:42:24 - INFO - codeparrot_training - Step 18940: {'lr': 0.0004840107344884377, 'samples': 9697792, 'steps': 18940, 'loss/train': 2.2943902015686035}
-03/04/2022 11:42:26 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/04/2022 11:42:29 - INFO - codeparrot_training - Step 18941: {'lr': 0.0004840088670677214, 'samples': 9698304, 'steps': 18941, 'loss/train': 1.8216155767440796}
-03/04/2022 11:42:33 - INFO - codeparrot_training - Step 18942: {'lr': 0.0004840069995415643, 'samples': 9698816, 'steps': 18942, 'loss/train': 1.0184500217437744}
-03/04/2022 11:42:35 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/04/2022 11:42:38 - INFO - codeparrot_training - Step 18943: {'lr': 0.0004840051319099673, 'samples': 9699328, 'steps': 18943, 'loss/train': 0.5910075902938843}
-03/04/2022 11:42:41 - INFO - codeparrot_training - Step 18944: {'lr': 0.0004840032641729312, 'samples': 9699840, 'steps': 18944, 'loss/train': 2.010183811187744}
-03/04/2022 11:42:43 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 11:42:46 - INFO - codeparrot_training - Step 18945: {'lr': 0.0004840013963304568, 'samples': 9700352, 'steps': 18945, 'loss/train': 1.8688609600067139}
-03/04/2022 11:42:50 - INFO - codeparrot_training - Step 18946: {'lr': 0.000483999528382545, 'samples': 9700864, 'steps': 18946, 'loss/train': 1.3555198907852173}
-03/04/2022 11:42:52 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 11:42:55 - INFO - codeparrot_training - Step 18947: {'lr': 0.00048399766032919666, 'samples': 9701376, 'steps': 18947, 'loss/train': 2.201612949371338}
-03/04/2022 11:42:58 - INFO - codeparrot_training - Step 18948: {'lr': 0.0004839957921704126, 'samples': 9701888, 'steps': 18948, 'loss/train': 1.6157660484313965}
-03/04/2022 11:43:00 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/04/2022 11:43:03 - INFO - codeparrot_training - Step 18949: {'lr': 0.0004839939239061936, 'samples': 9702400, 'steps': 18949, 'loss/train': 1.6845982074737549}
-03/04/2022 11:43:06 - INFO - codeparrot_training - Step 18950: {'lr': 0.00048399205553654046, 'samples': 9702912, 'steps': 18950, 'loss/train': 1.034011721611023}
-03/04/2022 11:43:09 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 11:43:12 - INFO - codeparrot_training - Step 18951: {'lr': 0.0004839901870614543, 'samples': 9703424, 'steps': 18951, 'loss/train': 1.8456207513809204}
-03/04/2022 11:43:15 - INFO - codeparrot_training - Step 18952: {'lr': 0.0004839883184809356, 'samples': 9703936, 'steps': 18952, 'loss/train': 2.756098985671997}
-03/04/2022 11:43:18 - INFO - codeparrot_training - Step 18953: {'lr': 0.00048398644979498543, 'samples': 9704448, 'steps': 18953, 'loss/train': 2.1422269344329834}
-03/04/2022 11:43:19 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 11:43:24 - INFO - codeparrot_training - Step 18954: {'lr': 0.0004839845810036047, 'samples': 9704960, 'steps': 18954, 'loss/train': 2.0475411415100098}
-03/04/2022 11:43:27 - INFO - codeparrot_training - Step 18955: {'lr': 0.00048398271210679393, 'samples': 9705472, 'steps': 18955, 'loss/train': 1.032584547996521}
-03/04/2022 11:43:27 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/04/2022 11:43:33 - INFO - codeparrot_training - Step 18956: {'lr': 0.0004839808431045543, 'samples': 9705984, 'steps': 18956, 'loss/train': 1.9920839071273804}
-03/04/2022 11:43:36 - INFO - codeparrot_training - Step 18957: {'lr': 0.00048397897399688643, 'samples': 9706496, 'steps': 18957, 'loss/train': 2.384577989578247}
-03/04/2022 11:43:37 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/04/2022 11:43:41 - INFO - codeparrot_training - Step 18958: {'lr': 0.0004839771047837913, 'samples': 9707008, 'steps': 18958, 'loss/train': 1.454741358757019}
-03/04/2022 11:43:44 - INFO - codeparrot_training - Step 18959: {'lr': 0.00048397523546526966, 'samples': 9707520, 'steps': 18959, 'loss/train': 1.9132548570632935}
-03/04/2022 11:43:46 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 11:43:50 - INFO - codeparrot_training - Step 18960: {'lr': 0.0004839733660413224, 'samples': 9708032, 'steps': 18960, 'loss/train': 1.326029658317566}
-03/04/2022 11:43:53 - INFO - codeparrot_training - Step 18961: {'lr': 0.0004839714965119504, 'samples': 9708544, 'steps': 18961, 'loss/train': 2.167956829071045}
-03/04/2022 11:43:55 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/04/2022 11:43:58 - INFO - codeparrot_training - Step 18962: {'lr': 0.0004839696268771544, 'samples': 9709056, 'steps': 18962, 'loss/train': 1.6004564762115479}
-03/04/2022 11:44:01 - INFO - codeparrot_training - Step 18963: {'lr': 0.0004839677571369353, 'samples': 9709568, 'steps': 18963, 'loss/train': 1.5438333749771118}
-03/04/2022 11:44:03 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/04/2022 11:44:06 - INFO - codeparrot_training - Step 18964: {'lr': 0.000483965887291294, 'samples': 9710080, 'steps': 18964, 'loss/train': 2.3998265266418457}
-03/04/2022 11:44:10 - INFO - codeparrot_training - Step 18965: {'lr': 0.0004839640173402312, 'samples': 9710592, 'steps': 18965, 'loss/train': 1.964352011680603}
-03/04/2022 11:44:12 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/04/2022 11:44:15 - INFO - codeparrot_training - Step 18966: {'lr': 0.00048396214728374786, 'samples': 9711104, 'steps': 18966, 'loss/train': 2.3243701457977295}
-03/04/2022 11:44:18 - INFO - codeparrot_training - Step 18967: {'lr': 0.00048396027712184475, 'samples': 9711616, 'steps': 18967, 'loss/train': 0.46013572812080383}
-03/04/2022 11:44:21 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 11:44:23 - INFO - codeparrot_training - Step 18968: {'lr': 0.0004839584068545228, 'samples': 9712128, 'steps': 18968, 'loss/train': 1.8779137134552002}
-03/04/2022 11:44:27 - INFO - codeparrot_training - Step 18969: {'lr': 0.0004839565364817828, 'samples': 9712640, 'steps': 18969, 'loss/train': 1.3133918046951294}
-03/04/2022 11:44:29 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/04/2022 11:44:32 - INFO - codeparrot_training - Step 18970: {'lr': 0.0004839546660036256, 'samples': 9713152, 'steps': 18970, 'loss/train': 1.8428951501846313}
-03/04/2022 11:44:35 - INFO - codeparrot_training - Step 18971: {'lr': 0.000483952795420052, 'samples': 9713664, 'steps': 18971, 'loss/train': 2.036573886871338}
-03/04/2022 11:44:38 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 11:44:40 - INFO - codeparrot_training - Step 18972: {'lr': 0.0004839509247310629, 'samples': 9714176, 'steps': 18972, 'loss/train': 1.877515196800232}
-03/04/2022 11:44:43 - INFO - codeparrot_training - Step 18973: {'lr': 0.00048394905393665913, 'samples': 9714688, 'steps': 18973, 'loss/train': 2.503880500793457}
-03/04/2022 11:44:46 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/04/2022 11:44:49 - INFO - codeparrot_training - Step 18974: {'lr': 0.00048394718303684147, 'samples': 9715200, 'steps': 18974, 'loss/train': 1.5977927446365356}
-03/04/2022 11:44:52 - INFO - codeparrot_training - Step 18975: {'lr': 0.00048394531203161084, 'samples': 9715712, 'steps': 18975, 'loss/train': 1.4963845014572144}
-03/04/2022 11:44:55 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/04/2022 11:44:57 - INFO - codeparrot_training - Step 18976: {'lr': 0.00048394344092096816, 'samples': 9716224, 'steps': 18976, 'loss/train': 0.832568883895874}
-03/04/2022 11:45:00 - INFO - codeparrot_training - Step 18977: {'lr': 0.0004839415697049141, 'samples': 9716736, 'steps': 18977, 'loss/train': 1.440832495689392}
-03/04/2022 11:45:03 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/04/2022 11:45:06 - INFO - codeparrot_training - Step 18978: {'lr': 0.00048393969838344956, 'samples': 9717248, 'steps': 18978, 'loss/train': 1.5311620235443115}
-03/04/2022 11:45:09 - INFO - codeparrot_training - Step 18979: {'lr': 0.0004839378269565754, 'samples': 9717760, 'steps': 18979, 'loss/train': 1.526186227798462}
-03/04/2022 11:45:12 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 11:45:14 - INFO - codeparrot_training - Step 18980: {'lr': 0.00048393595542429253, 'samples': 9718272, 'steps': 18980, 'loss/train': 1.9008655548095703}
-03/04/2022 11:45:17 - INFO - codeparrot_training - Step 18981: {'lr': 0.0004839340837866016, 'samples': 9718784, 'steps': 18981, 'loss/train': 1.1398667097091675}
-03/04/2022 11:45:20 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/04/2022 11:45:23 - INFO - codeparrot_training - Step 18982: {'lr': 0.00048393221204350376, 'samples': 9719296, 'steps': 18982, 'loss/train': 1.7926596403121948}
-03/04/2022 11:45:26 - INFO - codeparrot_training - Step 18983: {'lr': 0.0004839303401949996, 'samples': 9719808, 'steps': 18983, 'loss/train': 1.5848299264907837}
-03/04/2022 11:45:28 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 11:45:31 - INFO - codeparrot_training - Step 18984: {'lr': 0.00048392846824109, 'samples': 9720320, 'steps': 18984, 'loss/train': 2.1856110095977783}
-03/04/2022 11:45:34 - INFO - codeparrot_training - Step 18985: {'lr': 0.00048392659618177585, 'samples': 9720832, 'steps': 18985, 'loss/train': 1.6672126054763794}
-03/04/2022 11:45:37 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/04/2022 11:45:39 - INFO - codeparrot_training - Step 18986: {'lr': 0.000483924724017058, 'samples': 9721344, 'steps': 18986, 'loss/train': 2.425717830657959}
-03/04/2022 11:45:43 - INFO - codeparrot_training - Step 18987: {'lr': 0.00048392285174693727, 'samples': 9721856, 'steps': 18987, 'loss/train': 1.7312487363815308}
-03/04/2022 11:45:45 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 11:45:48 - INFO - codeparrot_training - Step 18988: {'lr': 0.0004839209793714146, 'samples': 9722368, 'steps': 18988, 'loss/train': 1.3286852836608887}
-03/04/2022 11:45:51 - INFO - codeparrot_training - Step 18989: {'lr': 0.00048391910689049057, 'samples': 9722880, 'steps': 18989, 'loss/train': 1.4873157739639282}
-03/04/2022 11:45:53 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/04/2022 11:45:56 - INFO - codeparrot_training - Step 18990: {'lr': 0.00048391723430416634, 'samples': 9723392, 'steps': 18990, 'loss/train': 2.465550422668457}
-03/04/2022 11:45:59 - INFO - codeparrot_training - Step 18991: {'lr': 0.00048391536161244254, 'samples': 9723904, 'steps': 18991, 'loss/train': 1.602460503578186}
-03/04/2022 11:46:02 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/04/2022 11:46:05 - INFO - codeparrot_training - Step 18992: {'lr': 0.0004839134888153202, 'samples': 9724416, 'steps': 18992, 'loss/train': 2.133727788925171}
-03/04/2022 11:46:08 - INFO - codeparrot_training - Step 18993: {'lr': 0.00048391161591279994, 'samples': 9724928, 'steps': 18993, 'loss/train': 1.759141445159912}
-03/04/2022 11:46:10 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/04/2022 11:46:13 - INFO - codeparrot_training - Step 18994: {'lr': 0.0004839097429048827, 'samples': 9725440, 'steps': 18994, 'loss/train': 1.1383148431777954}
-03/04/2022 11:46:16 - INFO - codeparrot_training - Step 18995: {'lr': 0.00048390786979156944, 'samples': 9725952, 'steps': 18995, 'loss/train': 1.5835357904434204}
-03/04/2022 11:46:18 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/04/2022 11:46:21 - INFO - codeparrot_training - Step 18996: {'lr': 0.0004839059965728608, 'samples': 9726464, 'steps': 18996, 'loss/train': 2.011943817138672}
-03/04/2022 11:46:25 - INFO - codeparrot_training - Step 18997: {'lr': 0.0004839041232487578, 'samples': 9726976, 'steps': 18997, 'loss/train': 2.0797183513641357}
-03/04/2022 11:46:27 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 11:46:30 - INFO - codeparrot_training - Step 18998: {'lr': 0.0004839022498192612, 'samples': 9727488, 'steps': 18998, 'loss/train': 1.960619330406189}
-03/04/2022 11:46:33 - INFO - codeparrot_training - Step 18999: {'lr': 0.0004839003762843718, 'samples': 9728000, 'steps': 18999, 'loss/train': 2.089538812637329}
-03/04/2022 11:46:35 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/04/2022 11:46:38 - INFO - codeparrot_training - Step 19000: {'lr': 0.00048389850264409054, 'samples': 9728512, 'steps': 19000, 'loss/train': 3.279268980026245}
-03/04/2022 11:46:41 - INFO - codeparrot_training - Step 19001: {'lr': 0.00048389662889841825, 'samples': 9729024, 'steps': 19001, 'loss/train': 1.7961187362670898}
-03/04/2022 11:46:43 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 11:46:47 - INFO - codeparrot_training - Step 19002: {'lr': 0.0004838947550473557, 'samples': 9729536, 'steps': 19002, 'loss/train': 1.7270654439926147}
-03/04/2022 11:46:50 - INFO - codeparrot_training - Step 19003: {'lr': 0.00048389288109090383, 'samples': 9730048, 'steps': 19003, 'loss/train': 1.5645725727081299}
-03/04/2022 11:46:52 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 11:46:55 - INFO - codeparrot_training - Step 19004: {'lr': 0.0004838910070290634, 'samples': 9730560, 'steps': 19004, 'loss/train': 2.003458261489868}
-03/04/2022 11:46:58 - INFO - codeparrot_training - Step 19005: {'lr': 0.00048388913286183535, 'samples': 9731072, 'steps': 19005, 'loss/train': 2.1503946781158447}
-03/04/2022 11:47:00 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/04/2022 11:47:04 - INFO - codeparrot_training - Step 19006: {'lr': 0.0004838872585892204, 'samples': 9731584, 'steps': 19006, 'loss/train': 1.5831043720245361}
-03/04/2022 11:47:07 - INFO - codeparrot_training - Step 19007: {'lr': 0.00048388538421121946, 'samples': 9732096, 'steps': 19007, 'loss/train': 1.6411235332489014}
-03/04/2022 11:47:09 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/04/2022 11:47:12 - INFO - codeparrot_training - Step 19008: {'lr': 0.00048388350972783346, 'samples': 9732608, 'steps': 19008, 'loss/train': 1.3564029932022095}
-03/04/2022 11:47:15 - INFO - codeparrot_training - Step 19009: {'lr': 0.000483881635139063, 'samples': 9733120, 'steps': 19009, 'loss/train': 1.3944162130355835}
-03/04/2022 11:47:17 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 11:47:21 - INFO - codeparrot_training - Step 19010: {'lr': 0.00048387976044490924, 'samples': 9733632, 'steps': 19010, 'loss/train': 2.2904255390167236}
-03/04/2022 11:47:24 - INFO - codeparrot_training - Step 19011: {'lr': 0.0004838778856453728, 'samples': 9734144, 'steps': 19011, 'loss/train': 0.15952759981155396}
-03/04/2022 11:47:26 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/04/2022 11:47:29 - INFO - codeparrot_training - Step 19012: {'lr': 0.00048387601074045464, 'samples': 9734656, 'steps': 19012, 'loss/train': 1.0988926887512207}
-03/04/2022 11:47:32 - INFO - codeparrot_training - Step 19013: {'lr': 0.0004838741357301555, 'samples': 9735168, 'steps': 19013, 'loss/train': 2.176988124847412}
-03/04/2022 11:47:35 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 11:47:37 - INFO - codeparrot_training - Step 19014: {'lr': 0.00048387226061447633, 'samples': 9735680, 'steps': 19014, 'loss/train': 1.3985174894332886}
-03/04/2022 11:47:41 - INFO - codeparrot_training - Step 19015: {'lr': 0.0004838703853934179, 'samples': 9736192, 'steps': 19015, 'loss/train': 1.3478243350982666}
-03/04/2022 11:47:44 - INFO - codeparrot_training - Step 19016: {'lr': 0.0004838685100669811, 'samples': 9736704, 'steps': 19016, 'loss/train': 2.4625613689422607}
-03/04/2022 11:47:44 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/04/2022 11:47:49 - INFO - codeparrot_training - Step 19017: {'lr': 0.0004838666346351667, 'samples': 9737216, 'steps': 19017, 'loss/train': 1.6678452491760254}
-03/04/2022 11:47:52 - INFO - codeparrot_training - Step 19018: {'lr': 0.0004838647590979757, 'samples': 9737728, 'steps': 19018, 'loss/train': 1.9159846305847168}
-03/04/2022 11:47:52 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/04/2022 11:47:58 - INFO - codeparrot_training - Step 19019: {'lr': 0.00048386288345540876, 'samples': 9738240, 'steps': 19019, 'loss/train': 2.9255483150482178}
-03/04/2022 11:48:01 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/04/2022 11:48:03 - INFO - codeparrot_training - Step 19020: {'lr': 0.00048386100770746686, 'samples': 9738752, 'steps': 19020, 'loss/train': 1.499014973640442}
-03/04/2022 11:48:06 - INFO - codeparrot_training - Step 19021: {'lr': 0.00048385913185415076, 'samples': 9739264, 'steps': 19021, 'loss/train': 1.595326542854309}
-03/04/2022 11:48:10 - INFO - codeparrot_training - Step 19022: {'lr': 0.00048385725589546137, 'samples': 9739776, 'steps': 19022, 'loss/train': 2.221832513809204}
-03/04/2022 11:48:10 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/04/2022 11:48:15 - INFO - codeparrot_training - Step 19023: {'lr': 0.0004838553798313995, 'samples': 9740288, 'steps': 19023, 'loss/train': 1.2831733226776123}
-03/04/2022 11:48:18 - INFO - codeparrot_training - Step 19024: {'lr': 0.000483853503661966, 'samples': 9740800, 'steps': 19024, 'loss/train': 1.8742140531539917}
-03/04/2022 11:48:19 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 11:48:23 - INFO - codeparrot_training - Step 19025: {'lr': 0.00048385162738716174, 'samples': 9741312, 'steps': 19025, 'loss/train': 2.7154455184936523}
-03/04/2022 11:48:26 - INFO - codeparrot_training - Step 19026: {'lr': 0.00048384975100698756, 'samples': 9741824, 'steps': 19026, 'loss/train': 2.0792431831359863}
-03/04/2022 11:48:27 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/04/2022 11:48:32 - INFO - codeparrot_training - Step 19027: {'lr': 0.0004838478745214443, 'samples': 9742336, 'steps': 19027, 'loss/train': 1.7366892099380493}
-03/04/2022 11:48:35 - INFO - codeparrot_training - Step 19028: {'lr': 0.00048384599793053275, 'samples': 9742848, 'steps': 19028, 'loss/train': 2.5608417987823486}
-03/04/2022 11:48:35 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/04/2022 11:48:40 - INFO - codeparrot_training - Step 19029: {'lr': 0.0004838441212342538, 'samples': 9743360, 'steps': 19029, 'loss/train': 1.9441933631896973}
-03/04/2022 11:48:43 - INFO - codeparrot_training - Step 19030: {'lr': 0.0004838422444326084, 'samples': 9743872, 'steps': 19030, 'loss/train': 2.444429874420166}
-03/04/2022 11:48:43 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/04/2022 11:48:48 - INFO - codeparrot_training - Step 19031: {'lr': 0.0004838403675255971, 'samples': 9744384, 'steps': 19031, 'loss/train': 1.1212583780288696}
-03/04/2022 11:48:52 - INFO - codeparrot_training - Step 19032: {'lr': 0.0004838384905132211, 'samples': 9744896, 'steps': 19032, 'loss/train': 1.5249422788619995}
-03/04/2022 11:48:52 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 11:48:57 - INFO - codeparrot_training - Step 19033: {'lr': 0.000483836613395481, 'samples': 9745408, 'steps': 19033, 'loss/train': 1.9500643014907837}
-03/04/2022 11:49:00 - INFO - codeparrot_training - Step 19034: {'lr': 0.0004838347361723778, 'samples': 9745920, 'steps': 19034, 'loss/train': 3.127875328063965}
-03/04/2022 11:49:00 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/04/2022 11:49:05 - INFO - codeparrot_training - Step 19035: {'lr': 0.0004838328588439123, 'samples': 9746432, 'steps': 19035, 'loss/train': 1.4075943231582642}
-03/04/2022 11:49:09 - INFO - codeparrot_training - Step 19036: {'lr': 0.0004838309814100852, 'samples': 9746944, 'steps': 19036, 'loss/train': 1.29261314868927}
-03/04/2022 11:49:09 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/04/2022 11:49:14 - INFO - codeparrot_training - Step 19037: {'lr': 0.0004838291038708975, 'samples': 9747456, 'steps': 19037, 'loss/train': 2.0055441856384277}
-03/04/2022 11:49:17 - INFO - codeparrot_training - Step 19038: {'lr': 0.00048382722622635014, 'samples': 9747968, 'steps': 19038, 'loss/train': 2.0530107021331787}
-03/04/2022 11:49:17 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/04/2022 11:49:22 - INFO - codeparrot_training - Step 19039: {'lr': 0.0004838253484764437, 'samples': 9748480, 'steps': 19039, 'loss/train': 2.0924108028411865}
-03/04/2022 11:49:25 - INFO - codeparrot_training - Step 19040: {'lr': 0.0004838234706211792, 'samples': 9748992, 'steps': 19040, 'loss/train': 1.9779973030090332}
-03/04/2022 11:49:26 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/04/2022 11:49:31 - INFO - codeparrot_training - Step 19041: {'lr': 0.00048382159266055746, 'samples': 9749504, 'steps': 19041, 'loss/train': 2.190882921218872}
-03/04/2022 11:49:34 - INFO - codeparrot_training - Step 19042: {'lr': 0.0004838197145945793, 'samples': 9750016, 'steps': 19042, 'loss/train': 1.2907377481460571}
-03/04/2022 11:49:34 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/04/2022 11:49:39 - INFO - codeparrot_training - Step 19043: {'lr': 0.0004838178364232456, 'samples': 9750528, 'steps': 19043, 'loss/train': 1.638651967048645}
-03/04/2022 11:49:42 - INFO - codeparrot_training - Step 19044: {'lr': 0.00048381595814655723, 'samples': 9751040, 'steps': 19044, 'loss/train': 1.438443660736084}
-03/04/2022 11:49:43 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/04/2022 11:49:48 - INFO - codeparrot_training - Step 19045: {'lr': 0.000483814079764515, 'samples': 9751552, 'steps': 19045, 'loss/train': 2.238020658493042}
-03/04/2022 11:49:51 - INFO - codeparrot_training - Step 19046: {'lr': 0.00048381220127711967, 'samples': 9752064, 'steps': 19046, 'loss/train': 2.3671090602874756}
-03/04/2022 11:49:52 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 11:49:56 - INFO - codeparrot_training - Step 19047: {'lr': 0.0004838103226843722, 'samples': 9752576, 'steps': 19047, 'loss/train': 2.1221764087677}
-03/04/2022 11:49:59 - INFO - codeparrot_training - Step 19048: {'lr': 0.00048380844398627343, 'samples': 9753088, 'steps': 19048, 'loss/train': 2.0431272983551025}
-03/04/2022 11:50:00 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 11:50:05 - INFO - codeparrot_training - Step 19049: {'lr': 0.0004838065651828242, 'samples': 9753600, 'steps': 19049, 'loss/train': 2.2768983840942383}
-03/04/2022 11:50:08 - INFO - codeparrot_training - Step 19050: {'lr': 0.0004838046862740253, 'samples': 9754112, 'steps': 19050, 'loss/train': 1.7647593021392822}
-03/04/2022 11:50:09 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/04/2022 11:50:13 - INFO - codeparrot_training - Step 19051: {'lr': 0.0004838028072598777, 'samples': 9754624, 'steps': 19051, 'loss/train': 1.7352306842803955}
-03/04/2022 11:50:16 - INFO - codeparrot_training - Step 19052: {'lr': 0.00048380092814038204, 'samples': 9755136, 'steps': 19052, 'loss/train': 1.452945590019226}
-03/04/2022 11:50:17 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 11:50:21 - INFO - codeparrot_training - Step 19053: {'lr': 0.0004837990489155394, 'samples': 9755648, 'steps': 19053, 'loss/train': 2.563706874847412}
-03/04/2022 11:50:25 - INFO - codeparrot_training - Step 19054: {'lr': 0.00048379716958535043, 'samples': 9756160, 'steps': 19054, 'loss/train': 2.543973922729492}
-03/04/2022 11:50:25 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 11:50:30 - INFO - codeparrot_training - Step 19055: {'lr': 0.00048379529014981604, 'samples': 9756672, 'steps': 19055, 'loss/train': 2.4402763843536377}
-03/04/2022 11:50:33 - INFO - codeparrot_training - Step 19056: {'lr': 0.0004837934106089372, 'samples': 9757184, 'steps': 19056, 'loss/train': 1.7875601053237915}
-03/04/2022 11:50:34 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/04/2022 11:50:38 - INFO - codeparrot_training - Step 19057: {'lr': 0.0004837915309627146, 'samples': 9757696, 'steps': 19057, 'loss/train': 1.4509854316711426}
-03/04/2022 11:50:41 - INFO - codeparrot_training - Step 19058: {'lr': 0.00048378965121114917, 'samples': 9758208, 'steps': 19058, 'loss/train': 1.6792768239974976}
-03/04/2022 11:50:42 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/04/2022 11:50:47 - INFO - codeparrot_training - Step 19059: {'lr': 0.00048378777135424166, 'samples': 9758720, 'steps': 19059, 'loss/train': 2.413252353668213}
-03/04/2022 11:50:50 - INFO - codeparrot_training - Step 19060: {'lr': 0.0004837858913919931, 'samples': 9759232, 'steps': 19060, 'loss/train': 1.2645363807678223}
-03/04/2022 11:50:51 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/04/2022 11:50:55 - INFO - codeparrot_training - Step 19061: {'lr': 0.0004837840113244042, 'samples': 9759744, 'steps': 19061, 'loss/train': 1.630685806274414}
-03/04/2022 11:50:58 - INFO - codeparrot_training - Step 19062: {'lr': 0.00048378213115147573, 'samples': 9760256, 'steps': 19062, 'loss/train': 1.057685136795044}
-03/04/2022 11:50:59 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 11:51:04 - INFO - codeparrot_training - Step 19063: {'lr': 0.00048378025087320877, 'samples': 9760768, 'steps': 19063, 'loss/train': 1.7737960815429688}
-03/04/2022 11:51:07 - INFO - codeparrot_training - Step 19064: {'lr': 0.0004837783704896039, 'samples': 9761280, 'steps': 19064, 'loss/train': 1.5925313234329224}
-03/04/2022 11:51:08 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 11:51:12 - INFO - codeparrot_training - Step 19065: {'lr': 0.0004837764900006623, 'samples': 9761792, 'steps': 19065, 'loss/train': 2.1146035194396973}
-03/04/2022 11:51:15 - INFO - codeparrot_training - Step 19066: {'lr': 0.0004837746094063844, 'samples': 9762304, 'steps': 19066, 'loss/train': 2.251293420791626}
-03/04/2022 11:51:16 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/04/2022 11:51:20 - INFO - codeparrot_training - Step 19067: {'lr': 0.00048377272870677135, 'samples': 9762816, 'steps': 19067, 'loss/train': 1.7928745746612549}
-03/04/2022 11:51:23 - INFO - codeparrot_training - Step 19068: {'lr': 0.000483770847901824, 'samples': 9763328, 'steps': 19068, 'loss/train': 1.2164032459259033}
-03/04/2022 11:51:24 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 11:51:29 - INFO - codeparrot_training - Step 19069: {'lr': 0.000483768966991543, 'samples': 9763840, 'steps': 19069, 'loss/train': 1.2205106019973755}
-03/04/2022 11:51:32 - INFO - codeparrot_training - Step 19070: {'lr': 0.0004837670859759294, 'samples': 9764352, 'steps': 19070, 'loss/train': 1.5738540887832642}
-03/04/2022 11:51:32 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/04/2022 11:51:37 - INFO - codeparrot_training - Step 19071: {'lr': 0.0004837652048549839, 'samples': 9764864, 'steps': 19071, 'loss/train': 1.7990918159484863}
-03/04/2022 11:51:40 - INFO - codeparrot_training - Step 19072: {'lr': 0.00048376332362870745, 'samples': 9765376, 'steps': 19072, 'loss/train': 0.4122887849807739}
-03/04/2022 11:51:41 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/04/2022 11:51:46 - INFO - codeparrot_training - Step 19073: {'lr': 0.00048376144229710083, 'samples': 9765888, 'steps': 19073, 'loss/train': 1.8524566888809204}
-03/04/2022 11:51:49 - INFO - codeparrot_training - Step 19074: {'lr': 0.00048375956086016495, 'samples': 9766400, 'steps': 19074, 'loss/train': 0.6110670566558838}
-03/04/2022 11:51:50 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/04/2022 11:51:54 - INFO - codeparrot_training - Step 19075: {'lr': 0.0004837576793179005, 'samples': 9766912, 'steps': 19075, 'loss/train': 1.9604233503341675}
-03/04/2022 11:51:57 - INFO - codeparrot_training - Step 19076: {'lr': 0.00048375579767030854, 'samples': 9767424, 'steps': 19076, 'loss/train': 2.643186330795288}
-03/04/2022 11:51:58 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/04/2022 11:52:02 - INFO - codeparrot_training - Step 19077: {'lr': 0.0004837539159173898, 'samples': 9767936, 'steps': 19077, 'loss/train': 1.9121967554092407}
-03/04/2022 11:52:06 - INFO - codeparrot_training - Step 19078: {'lr': 0.00048375203405914515, 'samples': 9768448, 'steps': 19078, 'loss/train': 1.8233567476272583}
-03/04/2022 11:52:06 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/04/2022 11:52:11 - INFO - codeparrot_training - Step 19079: {'lr': 0.00048375015209557547, 'samples': 9768960, 'steps': 19079, 'loss/train': 1.0104713439941406}
-03/04/2022 11:52:14 - INFO - codeparrot_training - Step 19080: {'lr': 0.00048374827002668156, 'samples': 9769472, 'steps': 19080, 'loss/train': 2.27640438079834}
-03/04/2022 11:52:15 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/04/2022 11:52:19 - INFO - codeparrot_training - Step 19081: {'lr': 0.0004837463878524643, 'samples': 9769984, 'steps': 19081, 'loss/train': 1.6136780977249146}
-03/04/2022 11:52:22 - INFO - codeparrot_training - Step 19082: {'lr': 0.0004837445055729245, 'samples': 9770496, 'steps': 19082, 'loss/train': 1.794377088546753}
-03/04/2022 11:52:23 - INFO - codeparrot_training - Skipping example with length 524 (seq_length=1024)
-03/04/2022 11:52:28 - INFO - codeparrot_training - Step 19083: {'lr': 0.00048374262318806306, 'samples': 9771008, 'steps': 19083, 'loss/train': 2.699237585067749}
-03/04/2022 11:52:31 - INFO - codeparrot_training - Step 19084: {'lr': 0.00048374074069788077, 'samples': 9771520, 'steps': 19084, 'loss/train': 1.7152440547943115}
-03/04/2022 11:52:32 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/04/2022 11:52:36 - INFO - codeparrot_training - Step 19085: {'lr': 0.0004837388581023785, 'samples': 9772032, 'steps': 19085, 'loss/train': 2.246276617050171}
-03/04/2022 11:52:39 - INFO - codeparrot_training - Step 19086: {'lr': 0.0004837369754015571, 'samples': 9772544, 'steps': 19086, 'loss/train': 2.317816734313965}
-03/04/2022 11:52:40 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 11:52:44 - INFO - codeparrot_training - Step 19087: {'lr': 0.0004837350925954175, 'samples': 9773056, 'steps': 19087, 'loss/train': 2.17105770111084}
-03/04/2022 11:52:47 - INFO - codeparrot_training - Step 19088: {'lr': 0.00048373320968396043, 'samples': 9773568, 'steps': 19088, 'loss/train': 1.25314199924469}
-03/04/2022 11:52:48 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/04/2022 11:52:53 - INFO - codeparrot_training - Step 19089: {'lr': 0.0004837313266671868, 'samples': 9774080, 'steps': 19089, 'loss/train': 2.478390693664551}
-03/04/2022 11:52:56 - INFO - codeparrot_training - Step 19090: {'lr': 0.0004837294435450974, 'samples': 9774592, 'steps': 19090, 'loss/train': 2.1400089263916016}
-03/04/2022 11:52:57 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/04/2022 11:53:01 - INFO - codeparrot_training - Step 19091: {'lr': 0.00048372756031769316, 'samples': 9775104, 'steps': 19091, 'loss/train': 1.4048184156417847}
-03/04/2022 11:53:04 - INFO - codeparrot_training - Step 19092: {'lr': 0.00048372567698497487, 'samples': 9775616, 'steps': 19092, 'loss/train': 1.4838258028030396}
-03/04/2022 11:53:05 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 11:53:10 - INFO - codeparrot_training - Step 19093: {'lr': 0.0004837237935469434, 'samples': 9776128, 'steps': 19093, 'loss/train': 2.8436176776885986}
-03/04/2022 11:53:13 - INFO - codeparrot_training - Step 19094: {'lr': 0.00048372191000359955, 'samples': 9776640, 'steps': 19094, 'loss/train': 1.7321768999099731}
-03/04/2022 11:53:14 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/04/2022 11:53:18 - INFO - codeparrot_training - Step 19095: {'lr': 0.00048372002635494425, 'samples': 9777152, 'steps': 19095, 'loss/train': 1.1744433641433716}
-03/04/2022 11:53:21 - INFO - codeparrot_training - Step 19096: {'lr': 0.00048371814260097834, 'samples': 9777664, 'steps': 19096, 'loss/train': 2.2022459506988525}
-03/04/2022 11:53:23 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/04/2022 11:53:27 - INFO - codeparrot_training - Step 19097: {'lr': 0.0004837162587417027, 'samples': 9778176, 'steps': 19097, 'loss/train': 2.0238356590270996}
-03/04/2022 11:53:30 - INFO - codeparrot_training - Step 19098: {'lr': 0.000483714374777118, 'samples': 9778688, 'steps': 19098, 'loss/train': 1.7563862800598145}
-03/04/2022 11:53:31 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 11:53:35 - INFO - codeparrot_training - Step 19099: {'lr': 0.00048371249070722525, 'samples': 9779200, 'steps': 19099, 'loss/train': 2.233898401260376}
-03/04/2022 11:53:38 - INFO - codeparrot_training - Step 19100: {'lr': 0.0004837106065320253, 'samples': 9779712, 'steps': 19100, 'loss/train': 1.9447814226150513}
-03/04/2022 11:53:39 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/04/2022 11:53:44 - INFO - codeparrot_training - Step 19101: {'lr': 0.00048370872225151886, 'samples': 9780224, 'steps': 19101, 'loss/train': 1.9835928678512573}
-03/04/2022 11:53:47 - INFO - codeparrot_training - Step 19102: {'lr': 0.0004837068378657069, 'samples': 9780736, 'steps': 19102, 'loss/train': 3.504672050476074}
-03/04/2022 11:53:48 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 11:53:52 - INFO - codeparrot_training - Step 19103: {'lr': 0.0004837049533745903, 'samples': 9781248, 'steps': 19103, 'loss/train': 1.6461220979690552}
-03/04/2022 11:53:55 - INFO - codeparrot_training - Step 19104: {'lr': 0.00048370306877816983, 'samples': 9781760, 'steps': 19104, 'loss/train': 1.7725573778152466}
-03/04/2022 11:53:56 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/04/2022 11:54:00 - INFO - codeparrot_training - Step 19105: {'lr': 0.00048370118407644637, 'samples': 9782272, 'steps': 19105, 'loss/train': 2.170769691467285}
-03/04/2022 11:54:04 - INFO - codeparrot_training - Step 19106: {'lr': 0.0004836992992694208, 'samples': 9782784, 'steps': 19106, 'loss/train': 1.5784662961959839}
-03/04/2022 11:54:04 - INFO - codeparrot_training - Skipping example with length 86 (seq_length=1024)
-03/04/2022 11:54:09 - INFO - codeparrot_training - Step 19107: {'lr': 0.00048369741435709383, 'samples': 9783296, 'steps': 19107, 'loss/train': 1.3038992881774902}
-03/04/2022 11:54:12 - INFO - codeparrot_training - Step 19108: {'lr': 0.0004836955293394665, 'samples': 9783808, 'steps': 19108, 'loss/train': 0.14452621340751648}
-03/04/2022 11:54:13 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 11:54:17 - INFO - codeparrot_training - Step 19109: {'lr': 0.00048369364421653953, 'samples': 9784320, 'steps': 19109, 'loss/train': 1.9905946254730225}
-03/04/2022 11:54:20 - INFO - codeparrot_training - Step 19110: {'lr': 0.00048369175898831384, 'samples': 9784832, 'steps': 19110, 'loss/train': 1.8986555337905884}
-03/04/2022 11:54:21 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 11:54:26 - INFO - codeparrot_training - Step 19111: {'lr': 0.0004836898736547902, 'samples': 9785344, 'steps': 19111, 'loss/train': 1.5801424980163574}
-03/04/2022 11:54:29 - INFO - codeparrot_training - Step 19112: {'lr': 0.0004836879882159696, 'samples': 9785856, 'steps': 19112, 'loss/train': 1.1774191856384277}
-03/04/2022 11:54:30 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/04/2022 11:54:34 - INFO - codeparrot_training - Step 19113: {'lr': 0.0004836861026718527, 'samples': 9786368, 'steps': 19113, 'loss/train': 1.3509186506271362}
-03/04/2022 11:54:37 - INFO - codeparrot_training - Step 19114: {'lr': 0.00048368421702244045, 'samples': 9786880, 'steps': 19114, 'loss/train': 1.0715093612670898}
-03/04/2022 11:54:39 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 11:54:43 - INFO - codeparrot_training - Step 19115: {'lr': 0.00048368233126773377, 'samples': 9787392, 'steps': 19115, 'loss/train': 2.2267539501190186}
-03/04/2022 11:54:46 - INFO - codeparrot_training - Step 19116: {'lr': 0.0004836804454077334, 'samples': 9787904, 'steps': 19116, 'loss/train': 0.31432002782821655}
-03/04/2022 11:54:48 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 11:54:51 - INFO - codeparrot_training - Step 19117: {'lr': 0.0004836785594424402, 'samples': 9788416, 'steps': 19117, 'loss/train': 1.4672951698303223}
-03/04/2022 11:54:54 - INFO - codeparrot_training - Step 19118: {'lr': 0.0004836766733718551, 'samples': 9788928, 'steps': 19118, 'loss/train': 1.642343282699585}
-03/04/2022 11:54:57 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 11:55:00 - INFO - codeparrot_training - Step 19119: {'lr': 0.0004836747871959789, 'samples': 9789440, 'steps': 19119, 'loss/train': 2.110652446746826}
-03/04/2022 11:55:03 - INFO - codeparrot_training - Step 19120: {'lr': 0.0004836729009148124, 'samples': 9789952, 'steps': 19120, 'loss/train': 1.5951192378997803}
-03/04/2022 11:55:05 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/04/2022 11:55:08 - INFO - codeparrot_training - Step 19121: {'lr': 0.0004836710145283565, 'samples': 9790464, 'steps': 19121, 'loss/train': 1.269866704940796}
-03/04/2022 11:55:11 - INFO - codeparrot_training - Step 19122: {'lr': 0.0004836691280366121, 'samples': 9790976, 'steps': 19122, 'loss/train': 1.9087607860565186}
-03/04/2022 11:55:14 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/04/2022 11:55:16 - INFO - codeparrot_training - Step 19123: {'lr': 0.00048366724143958, 'samples': 9791488, 'steps': 19123, 'loss/train': 1.862273097038269}
-03/04/2022 11:55:20 - INFO - codeparrot_training - Step 19124: {'lr': 0.0004836653547372609, 'samples': 9792000, 'steps': 19124, 'loss/train': 2.057279109954834}
-03/04/2022 11:55:22 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/04/2022 11:55:25 - INFO - codeparrot_training - Step 19125: {'lr': 0.00048366346792965597, 'samples': 9792512, 'steps': 19125, 'loss/train': 1.9222984313964844}
-03/04/2022 11:55:28 - INFO - codeparrot_training - Step 19126: {'lr': 0.0004836615810167658, 'samples': 9793024, 'steps': 19126, 'loss/train': 2.2686641216278076}
-03/04/2022 11:55:32 - INFO - codeparrot_training - Step 19127: {'lr': 0.00048365969399859134, 'samples': 9793536, 'steps': 19127, 'loss/train': 0.8202565312385559}
-03/04/2022 11:55:32 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/04/2022 11:55:37 - INFO - codeparrot_training - Step 19128: {'lr': 0.00048365780687513346, 'samples': 9794048, 'steps': 19128, 'loss/train': 2.5410282611846924}
-03/04/2022 11:55:40 - INFO - codeparrot_training - Step 19129: {'lr': 0.00048365591964639294, 'samples': 9794560, 'steps': 19129, 'loss/train': 2.3165457248687744}
-03/04/2022 11:55:40 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/04/2022 11:55:45 - INFO - codeparrot_training - Step 19130: {'lr': 0.0004836540323123707, 'samples': 9795072, 'steps': 19130, 'loss/train': 1.4240673780441284}
-03/04/2022 11:55:49 - INFO - codeparrot_training - Step 19131: {'lr': 0.00048365214487306753, 'samples': 9795584, 'steps': 19131, 'loss/train': 1.878705382347107}
-03/04/2022 11:55:49 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/04/2022 11:55:54 - INFO - codeparrot_training - Step 19132: {'lr': 0.00048365025732848433, 'samples': 9796096, 'steps': 19132, 'loss/train': 1.3484946489334106}
-03/04/2022 11:55:57 - INFO - codeparrot_training - Step 19133: {'lr': 0.0004836483696786219, 'samples': 9796608, 'steps': 19133, 'loss/train': 0.6353148818016052}
-03/04/2022 11:55:57 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 11:56:03 - INFO - codeparrot_training - Step 19134: {'lr': 0.00048364648192348117, 'samples': 9797120, 'steps': 19134, 'loss/train': 1.8673421144485474}
-03/04/2022 11:56:06 - INFO - codeparrot_training - Step 19135: {'lr': 0.0004836445940630629, 'samples': 9797632, 'steps': 19135, 'loss/train': 7.163940906524658}
-03/04/2022 11:56:06 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/04/2022 11:56:12 - INFO - codeparrot_training - Step 19136: {'lr': 0.0004836427060973679, 'samples': 9798144, 'steps': 19136, 'loss/train': 1.746547818183899}
-03/04/2022 11:56:15 - INFO - codeparrot_training - Step 19137: {'lr': 0.00048364081802639724, 'samples': 9798656, 'steps': 19137, 'loss/train': 1.1063121557235718}
-03/04/2022 11:56:15 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 11:56:20 - INFO - codeparrot_training - Step 19138: {'lr': 0.00048363892985015157, 'samples': 9799168, 'steps': 19138, 'loss/train': 2.475808620452881}
-03/04/2022 11:56:24 - INFO - codeparrot_training - Step 19139: {'lr': 0.00048363704156863187, 'samples': 9799680, 'steps': 19139, 'loss/train': 1.6867518424987793}
-03/04/2022 11:56:24 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/04/2022 11:56:29 - INFO - codeparrot_training - Step 19140: {'lr': 0.0004836351531818388, 'samples': 9800192, 'steps': 19140, 'loss/train': 1.982181429862976}
-03/04/2022 11:56:32 - INFO - codeparrot_training - Step 19141: {'lr': 0.00048363326468977343, 'samples': 9800704, 'steps': 19141, 'loss/train': 1.9938501119613647}
-03/04/2022 11:56:34 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/04/2022 11:56:38 - INFO - codeparrot_training - Step 19142: {'lr': 0.00048363137609243654, 'samples': 9801216, 'steps': 19142, 'loss/train': 2.0216190814971924}
-03/04/2022 11:56:41 - INFO - codeparrot_training - Step 19143: {'lr': 0.0004836294873898289, 'samples': 9801728, 'steps': 19143, 'loss/train': 1.3790148496627808}
-03/04/2022 11:56:42 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/04/2022 11:56:46 - INFO - codeparrot_training - Step 19144: {'lr': 0.00048362759858195146, 'samples': 9802240, 'steps': 19144, 'loss/train': 2.297219753265381}
-03/04/2022 11:56:49 - INFO - codeparrot_training - Step 19145: {'lr': 0.0004836257096688049, 'samples': 9802752, 'steps': 19145, 'loss/train': 2.281494379043579}
-03/04/2022 11:56:51 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/04/2022 11:56:54 - INFO - codeparrot_training - Step 19146: {'lr': 0.00048362382065039034, 'samples': 9803264, 'steps': 19146, 'loss/train': 1.4901124238967896}
-03/04/2022 11:56:58 - INFO - codeparrot_training - Step 19147: {'lr': 0.00048362193152670847, 'samples': 9803776, 'steps': 19147, 'loss/train': 2.378389596939087}
-03/04/2022 11:56:59 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 11:57:03 - INFO - codeparrot_training - Step 19148: {'lr': 0.0004836200422977601, 'samples': 9804288, 'steps': 19148, 'loss/train': 2.3423774242401123}
-03/04/2022 11:57:06 - INFO - codeparrot_training - Step 19149: {'lr': 0.00048361815296354624, 'samples': 9804800, 'steps': 19149, 'loss/train': 1.0031681060791016}
-03/04/2022 11:57:07 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/04/2022 11:57:11 - INFO - codeparrot_training - Step 19150: {'lr': 0.00048361626352406756, 'samples': 9805312, 'steps': 19150, 'loss/train': 1.2146589756011963}
-03/04/2022 11:57:14 - INFO - codeparrot_training - Step 19151: {'lr': 0.00048361437397932504, 'samples': 9805824, 'steps': 19151, 'loss/train': 1.7427363395690918}
-03/04/2022 11:57:16 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/04/2022 11:57:20 - INFO - codeparrot_training - Step 19152: {'lr': 0.0004836124843293195, 'samples': 9806336, 'steps': 19152, 'loss/train': 1.4175242185592651}
-03/04/2022 11:57:23 - INFO - codeparrot_training - Step 19153: {'lr': 0.00048361059457405176, 'samples': 9806848, 'steps': 19153, 'loss/train': 1.8482346534729004}
-03/04/2022 11:57:24 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 11:57:28 - INFO - codeparrot_training - Step 19154: {'lr': 0.0004836087047135227, 'samples': 9807360, 'steps': 19154, 'loss/train': 1.7978466749191284}
-03/04/2022 11:57:31 - INFO - codeparrot_training - Step 19155: {'lr': 0.0004836068147477331, 'samples': 9807872, 'steps': 19155, 'loss/train': 0.8323595523834229}
-03/04/2022 11:57:33 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/04/2022 11:57:37 - INFO - codeparrot_training - Step 19156: {'lr': 0.0004836049246766839, 'samples': 9808384, 'steps': 19156, 'loss/train': 1.709352731704712}
-03/04/2022 11:57:40 - INFO - codeparrot_training - Step 19157: {'lr': 0.000483603034500376, 'samples': 9808896, 'steps': 19157, 'loss/train': 2.8450510501861572}
-03/04/2022 11:57:41 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 11:57:45 - INFO - codeparrot_training - Step 19158: {'lr': 0.0004836011442188101, 'samples': 9809408, 'steps': 19158, 'loss/train': 2.048278331756592}
-03/04/2022 11:57:48 - INFO - codeparrot_training - Step 19159: {'lr': 0.00048359925383198714, 'samples': 9809920, 'steps': 19159, 'loss/train': 2.202749729156494}
-03/04/2022 11:57:50 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/04/2022 11:57:54 - INFO - codeparrot_training - Step 19160: {'lr': 0.000483597363339908, 'samples': 9810432, 'steps': 19160, 'loss/train': 3.1279592514038086}
-03/04/2022 11:57:57 - INFO - codeparrot_training - Step 19161: {'lr': 0.0004835954727425734, 'samples': 9810944, 'steps': 19161, 'loss/train': 1.1556938886642456}
-03/04/2022 11:57:58 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/04/2022 11:58:02 - INFO - codeparrot_training - Step 19162: {'lr': 0.0004835935820399844, 'samples': 9811456, 'steps': 19162, 'loss/train': 1.2859561443328857}
-03/04/2022 11:58:05 - INFO - codeparrot_training - Step 19163: {'lr': 0.0004835916912321417, 'samples': 9811968, 'steps': 19163, 'loss/train': 1.7841856479644775}
-03/04/2022 11:58:07 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 11:58:11 - INFO - codeparrot_training - Step 19164: {'lr': 0.0004835898003190462, 'samples': 9812480, 'steps': 19164, 'loss/train': 1.51145339012146}
-03/04/2022 11:58:14 - INFO - codeparrot_training - Step 19165: {'lr': 0.00048358790930069876, 'samples': 9812992, 'steps': 19165, 'loss/train': 2.3694372177124023}
-03/04/2022 11:58:16 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/04/2022 11:58:19 - INFO - codeparrot_training - Step 19166: {'lr': 0.0004835860181771001, 'samples': 9813504, 'steps': 19166, 'loss/train': 1.9863017797470093}
-03/04/2022 11:58:22 - INFO - codeparrot_training - Step 19167: {'lr': 0.0004835841269482513, 'samples': 9814016, 'steps': 19167, 'loss/train': 1.4639633893966675}
-03/04/2022 11:58:25 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/04/2022 11:58:27 - INFO - codeparrot_training - Step 19168: {'lr': 0.00048358223561415306, 'samples': 9814528, 'steps': 19168, 'loss/train': 1.8229817152023315}
-03/04/2022 11:58:31 - INFO - codeparrot_training - Step 19169: {'lr': 0.0004835803441748062, 'samples': 9815040, 'steps': 19169, 'loss/train': 2.03450083732605}
-03/04/2022 11:58:33 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/04/2022 11:58:36 - INFO - codeparrot_training - Step 19170: {'lr': 0.0004835784526302117, 'samples': 9815552, 'steps': 19170, 'loss/train': 2.0309102535247803}
-03/04/2022 11:58:39 - INFO - codeparrot_training - Step 19171: {'lr': 0.0004835765609803704, 'samples': 9816064, 'steps': 19171, 'loss/train': 2.1762948036193848}
-03/04/2022 11:58:42 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 11:58:44 - INFO - codeparrot_training - Step 19172: {'lr': 0.00048357466922528306, 'samples': 9816576, 'steps': 19172, 'loss/train': 1.680019497871399}
-03/04/2022 11:58:48 - INFO - codeparrot_training - Step 19173: {'lr': 0.00048357277736495055, 'samples': 9817088, 'steps': 19173, 'loss/train': 2.8795645236968994}
-03/04/2022 11:58:50 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/04/2022 11:58:53 - INFO - codeparrot_training - Step 19174: {'lr': 0.0004835708853993738, 'samples': 9817600, 'steps': 19174, 'loss/train': 2.565791368484497}
-03/04/2022 11:58:56 - INFO - codeparrot_training - Step 19175: {'lr': 0.0004835689933285536, 'samples': 9818112, 'steps': 19175, 'loss/train': 1.8138941526412964}
-03/04/2022 11:58:58 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 11:59:01 - INFO - codeparrot_training - Step 19176: {'lr': 0.0004835671011524908, 'samples': 9818624, 'steps': 19176, 'loss/train': 2.5753040313720703}
-03/04/2022 11:59:04 - INFO - codeparrot_training - Step 19177: {'lr': 0.0004835652088711863, 'samples': 9819136, 'steps': 19177, 'loss/train': 1.8757364749908447}
-03/04/2022 11:59:07 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/04/2022 11:59:10 - INFO - codeparrot_training - Step 19178: {'lr': 0.0004835633164846409, 'samples': 9819648, 'steps': 19178, 'loss/train': 1.2767757177352905}
-03/04/2022 11:59:13 - INFO - codeparrot_training - Step 19179: {'lr': 0.00048356142399285545, 'samples': 9820160, 'steps': 19179, 'loss/train': 2.2289605140686035}
-03/04/2022 11:59:15 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/04/2022 11:59:18 - INFO - codeparrot_training - Step 19180: {'lr': 0.00048355953139583087, 'samples': 9820672, 'steps': 19180, 'loss/train': 2.0466277599334717}
-03/04/2022 11:59:21 - INFO - codeparrot_training - Step 19181: {'lr': 0.00048355763869356794, 'samples': 9821184, 'steps': 19181, 'loss/train': 1.4102799892425537}
-03/04/2022 11:59:24 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/04/2022 11:59:27 - INFO - codeparrot_training - Step 19182: {'lr': 0.0004835557458860675, 'samples': 9821696, 'steps': 19182, 'loss/train': 1.8225607872009277}
-03/04/2022 11:59:30 - INFO - codeparrot_training - Step 19183: {'lr': 0.00048355385297333054, 'samples': 9822208, 'steps': 19183, 'loss/train': 1.7419897317886353}
-03/04/2022 11:59:33 - INFO - codeparrot_training - Step 19184: {'lr': 0.0004835519599553578, 'samples': 9822720, 'steps': 19184, 'loss/train': 0.32982850074768066}
-03/04/2022 11:59:33 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/04/2022 11:59:38 - INFO - codeparrot_training - Step 19185: {'lr': 0.0004835500668321501, 'samples': 9823232, 'steps': 19185, 'loss/train': 1.4835785627365112}
-03/04/2022 11:59:41 - INFO - codeparrot_training - Step 19186: {'lr': 0.0004835481736037084, 'samples': 9823744, 'steps': 19186, 'loss/train': 1.8163987398147583}
-03/04/2022 11:59:42 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/04/2022 11:59:47 - INFO - codeparrot_training - Step 19187: {'lr': 0.0004835462802700334, 'samples': 9824256, 'steps': 19187, 'loss/train': 1.8382768630981445}
-03/04/2022 11:59:50 - INFO - codeparrot_training - Step 19188: {'lr': 0.00048354438683112614, 'samples': 9824768, 'steps': 19188, 'loss/train': 2.3431332111358643}
-03/04/2022 11:59:50 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/04/2022 11:59:55 - INFO - codeparrot_training - Step 19189: {'lr': 0.00048354249328698743, 'samples': 9825280, 'steps': 19189, 'loss/train': 1.530107855796814}
-03/04/2022 11:59:58 - INFO - codeparrot_training - Step 19190: {'lr': 0.000483540599637618, 'samples': 9825792, 'steps': 19190, 'loss/train': 1.6673619747161865}
-03/04/2022 11:59:59 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/04/2022 12:00:04 - INFO - codeparrot_training - Step 19191: {'lr': 0.00048353870588301875, 'samples': 9826304, 'steps': 19191, 'loss/train': 2.306063413619995}
-03/04/2022 12:00:07 - INFO - codeparrot_training - Step 19192: {'lr': 0.00048353681202319056, 'samples': 9826816, 'steps': 19192, 'loss/train': 1.1075419187545776}
-03/04/2022 12:00:07 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/04/2022 12:00:12 - INFO - codeparrot_training - Step 19193: {'lr': 0.0004835349180581343, 'samples': 9827328, 'steps': 19193, 'loss/train': 2.191236734390259}
-03/04/2022 12:00:15 - INFO - codeparrot_training - Step 19194: {'lr': 0.0004835330239878509, 'samples': 9827840, 'steps': 19194, 'loss/train': 1.6895511150360107}
-03/04/2022 12:00:16 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/04/2022 12:00:21 - INFO - codeparrot_training - Step 19195: {'lr': 0.00048353112981234104, 'samples': 9828352, 'steps': 19195, 'loss/train': 1.9214640855789185}
-03/04/2022 12:00:24 - INFO - codeparrot_training - Step 19196: {'lr': 0.0004835292355316057, 'samples': 9828864, 'steps': 19196, 'loss/train': 2.1213974952697754}
-03/04/2022 12:00:24 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 12:00:29 - INFO - codeparrot_training - Step 19197: {'lr': 0.0004835273411456456, 'samples': 9829376, 'steps': 19197, 'loss/train': 1.8801548480987549}
-03/04/2022 12:00:32 - INFO - codeparrot_training - Step 19198: {'lr': 0.00048352544665446174, 'samples': 9829888, 'steps': 19198, 'loss/train': 1.9582149982452393}
-03/04/2022 12:00:33 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/04/2022 12:00:38 - INFO - codeparrot_training - Step 19199: {'lr': 0.000483523552058055, 'samples': 9830400, 'steps': 19199, 'loss/train': 1.9739776849746704}
-03/04/2022 12:00:41 - INFO - codeparrot_training - Step 19200: {'lr': 0.00048352165735642607, 'samples': 9830912, 'steps': 19200, 'loss/train': 2.1278481483459473}
-03/04/2022 12:00:41 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 12:00:46 - INFO - codeparrot_training - Step 19201: {'lr': 0.00048351976254957585, 'samples': 9831424, 'steps': 19201, 'loss/train': 0.1349494755268097}
-03/04/2022 12:00:49 - INFO - codeparrot_training - Step 19202: {'lr': 0.0004835178676375053, 'samples': 9831936, 'steps': 19202, 'loss/train': 2.1137335300445557}
-03/04/2022 12:00:50 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/04/2022 12:00:55 - INFO - codeparrot_training - Step 19203: {'lr': 0.0004835159726202151, 'samples': 9832448, 'steps': 19203, 'loss/train': 2.3948311805725098}
-03/04/2022 12:00:58 - INFO - codeparrot_training - Step 19204: {'lr': 0.0004835140774977063, 'samples': 9832960, 'steps': 19204, 'loss/train': 1.5204931497573853}
-03/04/2022 12:00:58 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/04/2022 12:01:03 - INFO - codeparrot_training - Step 19205: {'lr': 0.0004835121822699796, 'samples': 9833472, 'steps': 19205, 'loss/train': 0.251239150762558}
-03/04/2022 12:01:06 - INFO - codeparrot_training - Step 19206: {'lr': 0.000483510286937036, 'samples': 9833984, 'steps': 19206, 'loss/train': 2.0902206897735596}
-03/04/2022 12:01:07 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/04/2022 12:01:12 - INFO - codeparrot_training - Step 19207: {'lr': 0.0004835083914988762, 'samples': 9834496, 'steps': 19207, 'loss/train': 2.0913524627685547}
-03/04/2022 12:01:15 - INFO - codeparrot_training - Step 19208: {'lr': 0.0004835064959555011, 'samples': 9835008, 'steps': 19208, 'loss/train': 2.2383651733398438}
-03/04/2022 12:01:16 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/04/2022 12:01:20 - INFO - codeparrot_training - Step 19209: {'lr': 0.00048350460030691165, 'samples': 9835520, 'steps': 19209, 'loss/train': 0.13571296632289886}
-03/04/2022 12:01:23 - INFO - codeparrot_training - Step 19210: {'lr': 0.00048350270455310864, 'samples': 9836032, 'steps': 19210, 'loss/train': 2.2258427143096924}
-03/04/2022 12:01:24 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 12:01:29 - INFO - codeparrot_training - Step 19211: {'lr': 0.00048350080869409285, 'samples': 9836544, 'steps': 19211, 'loss/train': 2.1521544456481934}
-03/04/2022 12:01:32 - INFO - codeparrot_training - Step 19212: {'lr': 0.0004834989127298652, 'samples': 9837056, 'steps': 19212, 'loss/train': 1.8312052488327026}
-03/04/2022 12:01:33 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/04/2022 12:01:37 - INFO - codeparrot_training - Step 19213: {'lr': 0.00048349701666042656, 'samples': 9837568, 'steps': 19213, 'loss/train': 1.7185653448104858}
-03/04/2022 12:01:40 - INFO - codeparrot_training - Step 19214: {'lr': 0.00048349512048577784, 'samples': 9838080, 'steps': 19214, 'loss/train': 1.8280302286148071}
-03/04/2022 12:01:41 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/04/2022 12:01:46 - INFO - codeparrot_training - Step 19215: {'lr': 0.00048349322420591966, 'samples': 9838592, 'steps': 19215, 'loss/train': 1.0927460193634033}
-03/04/2022 12:01:49 - INFO - codeparrot_training - Step 19216: {'lr': 0.00048349132782085316, 'samples': 9839104, 'steps': 19216, 'loss/train': 2.105433940887451}
-03/04/2022 12:01:50 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 12:01:54 - INFO - codeparrot_training - Step 19217: {'lr': 0.00048348943133057903, 'samples': 9839616, 'steps': 19217, 'loss/train': 2.235795736312866}
-03/04/2022 12:01:57 - INFO - codeparrot_training - Step 19218: {'lr': 0.0004834875347350982, 'samples': 9840128, 'steps': 19218, 'loss/train': 1.8776991367340088}
-03/04/2022 12:01:58 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/04/2022 12:02:03 - INFO - codeparrot_training - Step 19219: {'lr': 0.00048348563803441146, 'samples': 9840640, 'steps': 19219, 'loss/train': 1.2585382461547852}
-03/04/2022 12:02:06 - INFO - codeparrot_training - Step 19220: {'lr': 0.0004834837412285197, 'samples': 9841152, 'steps': 19220, 'loss/train': 2.2572309970855713}
-03/04/2022 12:02:07 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/04/2022 12:02:11 - INFO - codeparrot_training - Step 19221: {'lr': 0.00048348184431742377, 'samples': 9841664, 'steps': 19221, 'loss/train': 2.3496923446655273}
-03/04/2022 12:02:14 - INFO - codeparrot_training - Step 19222: {'lr': 0.00048347994730112457, 'samples': 9842176, 'steps': 19222, 'loss/train': 1.4268132448196411}
-03/04/2022 12:02:15 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/04/2022 12:02:19 - INFO - codeparrot_training - Step 19223: {'lr': 0.00048347805017962274, 'samples': 9842688, 'steps': 19223, 'loss/train': 1.7214634418487549}
-03/04/2022 12:02:23 - INFO - codeparrot_training - Step 19224: {'lr': 0.00048347615295291947, 'samples': 9843200, 'steps': 19224, 'loss/train': 2.3575832843780518}
-03/04/2022 12:02:24 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/04/2022 12:02:28 - INFO - codeparrot_training - Step 19225: {'lr': 0.0004834742556210154, 'samples': 9843712, 'steps': 19225, 'loss/train': 1.6836076974868774}
-03/04/2022 12:02:31 - INFO - codeparrot_training - Step 19226: {'lr': 0.00048347235818391144, 'samples': 9844224, 'steps': 19226, 'loss/train': 1.7872214317321777}
-03/04/2022 12:02:32 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 12:02:36 - INFO - codeparrot_training - Step 19227: {'lr': 0.0004834704606416084, 'samples': 9844736, 'steps': 19227, 'loss/train': 1.583264946937561}
-03/04/2022 12:02:39 - INFO - codeparrot_training - Step 19228: {'lr': 0.00048346856299410725, 'samples': 9845248, 'steps': 19228, 'loss/train': 1.917128324508667}
-03/04/2022 12:02:40 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/04/2022 12:02:45 - INFO - codeparrot_training - Step 19229: {'lr': 0.0004834666652414087, 'samples': 9845760, 'steps': 19229, 'loss/train': 1.6872631311416626}
-03/04/2022 12:02:48 - INFO - codeparrot_training - Step 19230: {'lr': 0.0004834647673835137, 'samples': 9846272, 'steps': 19230, 'loss/train': 1.928819179534912}
-03/04/2022 12:02:49 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 12:02:53 - INFO - codeparrot_training - Step 19231: {'lr': 0.00048346286942042307, 'samples': 9846784, 'steps': 19231, 'loss/train': 1.5109403133392334}
-03/04/2022 12:02:57 - INFO - codeparrot_training - Step 19232: {'lr': 0.0004834609713521377, 'samples': 9847296, 'steps': 19232, 'loss/train': 2.046553134918213}
-03/04/2022 12:02:58 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 12:03:02 - INFO - codeparrot_training - Step 19233: {'lr': 0.0004834590731786584, 'samples': 9847808, 'steps': 19233, 'loss/train': 2.262617349624634}
-03/04/2022 12:03:05 - INFO - codeparrot_training - Step 19234: {'lr': 0.000483457174899986, 'samples': 9848320, 'steps': 19234, 'loss/train': 1.626882791519165}
-03/04/2022 12:03:06 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/04/2022 12:03:10 - INFO - codeparrot_training - Step 19235: {'lr': 0.00048345527651612145, 'samples': 9848832, 'steps': 19235, 'loss/train': 2.079869031906128}
-03/04/2022 12:03:13 - INFO - codeparrot_training - Step 19236: {'lr': 0.00048345337802706555, 'samples': 9849344, 'steps': 19236, 'loss/train': 1.315872311592102}
-03/04/2022 12:03:15 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/04/2022 12:03:19 - INFO - codeparrot_training - Step 19237: {'lr': 0.0004834514794328192, 'samples': 9849856, 'steps': 19237, 'loss/train': 2.0964419841766357}
-03/04/2022 12:03:22 - INFO - codeparrot_training - Step 19238: {'lr': 0.00048344958073338315, 'samples': 9850368, 'steps': 19238, 'loss/train': 2.6559531688690186}
-03/04/2022 12:03:24 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 12:03:27 - INFO - codeparrot_training - Step 19239: {'lr': 0.00048344768192875833, 'samples': 9850880, 'steps': 19239, 'loss/train': 1.4975786209106445}
-03/04/2022 12:03:30 - INFO - codeparrot_training - Step 19240: {'lr': 0.00048344578301894557, 'samples': 9851392, 'steps': 19240, 'loss/train': 2.0107827186584473}
-03/04/2022 12:03:32 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/04/2022 12:03:36 - INFO - codeparrot_training - Step 19241: {'lr': 0.0004834438840039458, 'samples': 9851904, 'steps': 19241, 'loss/train': 1.8459316492080688}
-03/04/2022 12:03:39 - INFO - codeparrot_training - Step 19242: {'lr': 0.0004834419848837598, 'samples': 9852416, 'steps': 19242, 'loss/train': 1.7205618619918823}
-03/04/2022 12:03:40 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 12:03:44 - INFO - codeparrot_training - Step 19243: {'lr': 0.00048344008565838844, 'samples': 9852928, 'steps': 19243, 'loss/train': 1.420960545539856}
-03/04/2022 12:03:47 - INFO - codeparrot_training - Step 19244: {'lr': 0.00048343818632783255, 'samples': 9853440, 'steps': 19244, 'loss/train': 1.973958969116211}
-03/04/2022 12:03:48 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 12:03:52 - INFO - codeparrot_training - Step 19245: {'lr': 0.00048343628689209305, 'samples': 9853952, 'steps': 19245, 'loss/train': 1.7565151453018188}
-03/04/2022 12:03:56 - INFO - codeparrot_training - Step 19246: {'lr': 0.00048343438735117076, 'samples': 9854464, 'steps': 19246, 'loss/train': 2.030247449874878}
-03/04/2022 12:03:57 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 12:04:01 - INFO - codeparrot_training - Step 19247: {'lr': 0.00048343248770506655, 'samples': 9854976, 'steps': 19247, 'loss/train': 1.8498939275741577}
-03/04/2022 12:04:04 - INFO - codeparrot_training - Step 19248: {'lr': 0.0004834305879537812, 'samples': 9855488, 'steps': 19248, 'loss/train': 1.9585132598876953}
-03/04/2022 12:04:05 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 12:04:09 - INFO - codeparrot_training - Step 19249: {'lr': 0.00048342868809731567, 'samples': 9856000, 'steps': 19249, 'loss/train': 1.5519633293151855}
-03/04/2022 12:04:12 - INFO - codeparrot_training - Step 19250: {'lr': 0.0004834267881356708, 'samples': 9856512, 'steps': 19250, 'loss/train': 1.732340693473816}
-03/04/2022 12:04:13 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 12:04:18 - INFO - codeparrot_training - Step 19251: {'lr': 0.0004834248880688474, 'samples': 9857024, 'steps': 19251, 'loss/train': 2.159620523452759}
-03/04/2022 12:04:21 - INFO - codeparrot_training - Step 19252: {'lr': 0.00048342298789684637, 'samples': 9857536, 'steps': 19252, 'loss/train': 1.828635573387146}
-03/04/2022 12:04:23 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/04/2022 12:04:26 - INFO - codeparrot_training - Step 19253: {'lr': 0.0004834210876196685, 'samples': 9858048, 'steps': 19253, 'loss/train': 1.9632184505462646}
-03/04/2022 12:04:29 - INFO - codeparrot_training - Step 19254: {'lr': 0.0004834191872373147, 'samples': 9858560, 'steps': 19254, 'loss/train': 1.521689534187317}
-03/04/2022 12:04:31 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/04/2022 12:04:35 - INFO - codeparrot_training - Step 19255: {'lr': 0.0004834172867497858, 'samples': 9859072, 'steps': 19255, 'loss/train': 1.9479116201400757}
-03/04/2022 12:04:38 - INFO - codeparrot_training - Step 19256: {'lr': 0.0004834153861570827, 'samples': 9859584, 'steps': 19256, 'loss/train': 1.847349762916565}
-03/04/2022 12:04:40 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 12:04:43 - INFO - codeparrot_training - Step 19257: {'lr': 0.00048341348545920623, 'samples': 9860096, 'steps': 19257, 'loss/train': 2.014557361602783}
-03/04/2022 12:04:46 - INFO - codeparrot_training - Step 19258: {'lr': 0.0004834115846561572, 'samples': 9860608, 'steps': 19258, 'loss/train': 1.702178955078125}
-03/04/2022 12:04:49 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/04/2022 12:04:52 - INFO - codeparrot_training - Step 19259: {'lr': 0.0004834096837479366, 'samples': 9861120, 'steps': 19259, 'loss/train': 1.6481796503067017}
-03/04/2022 12:04:55 - INFO - codeparrot_training - Step 19260: {'lr': 0.00048340778273454514, 'samples': 9861632, 'steps': 19260, 'loss/train': 1.8168548345565796}
-03/04/2022 12:04:57 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/04/2022 12:05:00 - INFO - codeparrot_training - Step 19261: {'lr': 0.00048340588161598373, 'samples': 9862144, 'steps': 19261, 'loss/train': 2.3058178424835205}
-03/04/2022 12:05:03 - INFO - codeparrot_training - Step 19262: {'lr': 0.00048340398039225325, 'samples': 9862656, 'steps': 19262, 'loss/train': 1.9409716129302979}
-03/04/2022 12:05:05 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 12:05:09 - INFO - codeparrot_training - Step 19263: {'lr': 0.0004834020790633545, 'samples': 9863168, 'steps': 19263, 'loss/train': 0.9839010238647461}
-03/04/2022 12:05:12 - INFO - codeparrot_training - Step 19264: {'lr': 0.00048340017762928843, 'samples': 9863680, 'steps': 19264, 'loss/train': 2.3588013648986816}
-03/04/2022 12:05:14 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/04/2022 12:05:17 - INFO - codeparrot_training - Step 19265: {'lr': 0.00048339827609005583, 'samples': 9864192, 'steps': 19265, 'loss/train': 1.7827677726745605}
-03/04/2022 12:05:20 - INFO - codeparrot_training - Step 19266: {'lr': 0.00048339637444565756, 'samples': 9864704, 'steps': 19266, 'loss/train': 1.8599581718444824}
-03/04/2022 12:05:23 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 12:05:26 - INFO - codeparrot_training - Step 19267: {'lr': 0.0004833944726960945, 'samples': 9865216, 'steps': 19267, 'loss/train': 2.3508286476135254}
-03/04/2022 12:05:29 - INFO - codeparrot_training - Step 19268: {'lr': 0.00048339257084136747, 'samples': 9865728, 'steps': 19268, 'loss/train': 2.3346028327941895}
-03/04/2022 12:05:31 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/04/2022 12:05:34 - INFO - codeparrot_training - Step 19269: {'lr': 0.0004833906688814774, 'samples': 9866240, 'steps': 19269, 'loss/train': 2.1749258041381836}
-03/04/2022 12:05:37 - INFO - codeparrot_training - Step 19270: {'lr': 0.00048338876681642504, 'samples': 9866752, 'steps': 19270, 'loss/train': 1.7811172008514404}
-03/04/2022 12:05:39 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/04/2022 12:05:42 - INFO - codeparrot_training - Step 19271: {'lr': 0.0004833868646462113, 'samples': 9867264, 'steps': 19271, 'loss/train': 1.9683254957199097}
-03/04/2022 12:05:46 - INFO - codeparrot_training - Step 19272: {'lr': 0.00048338496237083705, 'samples': 9867776, 'steps': 19272, 'loss/train': 2.141453981399536}
-03/04/2022 12:05:48 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 12:05:51 - INFO - codeparrot_training - Step 19273: {'lr': 0.00048338305999030313, 'samples': 9868288, 'steps': 19273, 'loss/train': 2.4394173622131348}
-03/04/2022 12:05:54 - INFO - codeparrot_training - Step 19274: {'lr': 0.00048338115750461044, 'samples': 9868800, 'steps': 19274, 'loss/train': 1.9317326545715332}
-03/04/2022 12:05:56 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 12:06:00 - INFO - codeparrot_training - Step 19275: {'lr': 0.0004833792549137598, 'samples': 9869312, 'steps': 19275, 'loss/train': 1.9801526069641113}
-03/04/2022 12:06:03 - INFO - codeparrot_training - Step 19276: {'lr': 0.00048337735221775204, 'samples': 9869824, 'steps': 19276, 'loss/train': 1.58380126953125}
-03/04/2022 12:06:05 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 12:06:08 - INFO - codeparrot_training - Step 19277: {'lr': 0.000483375449416588, 'samples': 9870336, 'steps': 19277, 'loss/train': 1.0538156032562256}
-03/04/2022 12:06:11 - INFO - codeparrot_training - Step 19278: {'lr': 0.0004833735465102687, 'samples': 9870848, 'steps': 19278, 'loss/train': 2.0572452545166016}
-03/04/2022 12:06:14 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/04/2022 12:06:16 - INFO - codeparrot_training - Step 19279: {'lr': 0.0004833716434987948, 'samples': 9871360, 'steps': 19279, 'loss/train': 2.492720127105713}
-03/04/2022 12:06:20 - INFO - codeparrot_training - Step 19280: {'lr': 0.0004833697403821672, 'samples': 9871872, 'steps': 19280, 'loss/train': 1.0325214862823486}
-03/04/2022 12:06:22 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 12:06:25 - INFO - codeparrot_training - Step 19281: {'lr': 0.0004833678371603869, 'samples': 9872384, 'steps': 19281, 'loss/train': 2.03554630279541}
-03/04/2022 12:06:28 - INFO - codeparrot_training - Step 19282: {'lr': 0.0004833659338334546, 'samples': 9872896, 'steps': 19282, 'loss/train': 1.0189350843429565}
-03/04/2022 12:06:30 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/04/2022 12:06:33 - INFO - codeparrot_training - Step 19283: {'lr': 0.0004833640304013712, 'samples': 9873408, 'steps': 19283, 'loss/train': 1.4337482452392578}
-03/04/2022 12:06:36 - INFO - codeparrot_training - Step 19284: {'lr': 0.0004833621268641376, 'samples': 9873920, 'steps': 19284, 'loss/train': 1.8620758056640625}
-03/04/2022 12:06:38 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 12:06:42 - INFO - codeparrot_training - Step 19285: {'lr': 0.0004833602232217546, 'samples': 9874432, 'steps': 19285, 'loss/train': 2.062908887863159}
-03/04/2022 12:06:45 - INFO - codeparrot_training - Step 19286: {'lr': 0.0004833583194742231, 'samples': 9874944, 'steps': 19286, 'loss/train': 2.3928706645965576}
-03/04/2022 12:06:47 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 12:06:50 - INFO - codeparrot_training - Step 19287: {'lr': 0.00048335641562154396, 'samples': 9875456, 'steps': 19287, 'loss/train': 2.010359764099121}
-03/04/2022 12:06:53 - INFO - codeparrot_training - Step 19288: {'lr': 0.00048335451166371803, 'samples': 9875968, 'steps': 19288, 'loss/train': 1.8696197271347046}
-03/04/2022 12:06:55 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 12:06:59 - INFO - codeparrot_training - Step 19289: {'lr': 0.0004833526076007461, 'samples': 9876480, 'steps': 19289, 'loss/train': 2.1333889961242676}
-03/04/2022 12:07:02 - INFO - codeparrot_training - Step 19290: {'lr': 0.0004833507034326291, 'samples': 9876992, 'steps': 19290, 'loss/train': 1.6926838159561157}
-03/04/2022 12:07:04 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 12:07:07 - INFO - codeparrot_training - Step 19291: {'lr': 0.0004833487991593679, 'samples': 9877504, 'steps': 19291, 'loss/train': 1.4763946533203125}
-03/04/2022 12:07:10 - INFO - codeparrot_training - Step 19292: {'lr': 0.0004833468947809633, 'samples': 9878016, 'steps': 19292, 'loss/train': 1.8973913192749023}
-03/04/2022 12:07:12 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/04/2022 12:07:15 - INFO - codeparrot_training - Step 19293: {'lr': 0.0004833449902974162, 'samples': 9878528, 'steps': 19293, 'loss/train': 2.0443220138549805}
-03/04/2022 12:07:19 - INFO - codeparrot_training - Step 19294: {'lr': 0.00048334308570872745, 'samples': 9879040, 'steps': 19294, 'loss/train': 1.4786533117294312}
-03/04/2022 12:07:21 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/04/2022 12:07:24 - INFO - codeparrot_training - Step 19295: {'lr': 0.00048334118101489793, 'samples': 9879552, 'steps': 19295, 'loss/train': 1.7237526178359985}
-03/04/2022 12:07:27 - INFO - codeparrot_training - Step 19296: {'lr': 0.00048333927621592844, 'samples': 9880064, 'steps': 19296, 'loss/train': 2.043454170227051}
-03/04/2022 12:07:29 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/04/2022 12:07:32 - INFO - codeparrot_training - Step 19297: {'lr': 0.00048333737131181986, 'samples': 9880576, 'steps': 19297, 'loss/train': 2.1414129734039307}
-03/04/2022 12:07:36 - INFO - codeparrot_training - Step 19298: {'lr': 0.00048333546630257315, 'samples': 9881088, 'steps': 19298, 'loss/train': 1.6831251382827759}
-03/04/2022 12:07:38 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/04/2022 12:07:41 - INFO - codeparrot_training - Step 19299: {'lr': 0.000483333561188189, 'samples': 9881600, 'steps': 19299, 'loss/train': 1.9294929504394531}
-03/04/2022 12:07:44 - INFO - codeparrot_training - Step 19300: {'lr': 0.00048333165596866837, 'samples': 9882112, 'steps': 19300, 'loss/train': 1.6280734539031982}
-03/04/2022 12:07:46 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 12:07:49 - INFO - codeparrot_training - Step 19301: {'lr': 0.00048332975064401207, 'samples': 9882624, 'steps': 19301, 'loss/train': 1.9647443294525146}
-03/04/2022 12:07:52 - INFO - codeparrot_training - Step 19302: {'lr': 0.000483327845214221, 'samples': 9883136, 'steps': 19302, 'loss/train': 2.116105318069458}
-03/04/2022 12:07:54 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 12:07:58 - INFO - codeparrot_training - Step 19303: {'lr': 0.00048332593967929607, 'samples': 9883648, 'steps': 19303, 'loss/train': 1.831972599029541}
-03/04/2022 12:08:01 - INFO - codeparrot_training - Step 19304: {'lr': 0.000483324034039238, 'samples': 9884160, 'steps': 19304, 'loss/train': 2.275942802429199}
-03/04/2022 12:08:03 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/04/2022 12:08:06 - INFO - codeparrot_training - Step 19305: {'lr': 0.00048332212829404775, 'samples': 9884672, 'steps': 19305, 'loss/train': 1.900220274925232}
-03/04/2022 12:08:09 - INFO - codeparrot_training - Step 19306: {'lr': 0.0004833202224437261, 'samples': 9885184, 'steps': 19306, 'loss/train': 1.8362157344818115}
-03/04/2022 12:08:11 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/04/2022 12:08:14 - INFO - codeparrot_training - Step 19307: {'lr': 0.000483318316488274, 'samples': 9885696, 'steps': 19307, 'loss/train': 1.8705945014953613}
-03/04/2022 12:08:18 - INFO - codeparrot_training - Step 19308: {'lr': 0.00048331641042769223, 'samples': 9886208, 'steps': 19308, 'loss/train': 2.4039907455444336}
-03/04/2022 12:08:20 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/04/2022 12:08:23 - INFO - codeparrot_training - Step 19309: {'lr': 0.00048331450426198177, 'samples': 9886720, 'steps': 19309, 'loss/train': 1.7002663612365723}
-03/04/2022 12:08:26 - INFO - codeparrot_training - Step 19310: {'lr': 0.0004833125979911434, 'samples': 9887232, 'steps': 19310, 'loss/train': 1.6479078531265259}
-03/04/2022 12:08:28 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 12:08:31 - INFO - codeparrot_training - Step 19311: {'lr': 0.0004833106916151778, 'samples': 9887744, 'steps': 19311, 'loss/train': 2.1744163036346436}
-03/04/2022 12:08:34 - INFO - codeparrot_training - Step 19312: {'lr': 0.00048330878513408616, 'samples': 9888256, 'steps': 19312, 'loss/train': 1.5220141410827637}
-03/04/2022 12:08:36 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/04/2022 12:08:40 - INFO - codeparrot_training - Step 19313: {'lr': 0.00048330687854786914, 'samples': 9888768, 'steps': 19313, 'loss/train': 1.9622236490249634}
-03/04/2022 12:08:43 - INFO - codeparrot_training - Step 19314: {'lr': 0.00048330497185652765, 'samples': 9889280, 'steps': 19314, 'loss/train': 1.5901180505752563}
-03/04/2022 12:08:45 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 12:08:48 - INFO - codeparrot_training - Step 19315: {'lr': 0.00048330306506006257, 'samples': 9889792, 'steps': 19315, 'loss/train': 0.7435954213142395}
-03/04/2022 12:08:51 - INFO - codeparrot_training - Step 19316: {'lr': 0.00048330115815847465, 'samples': 9890304, 'steps': 19316, 'loss/train': 1.8161375522613525}
-03/04/2022 12:08:53 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/04/2022 12:08:56 - INFO - codeparrot_training - Step 19317: {'lr': 0.0004832992511517649, 'samples': 9890816, 'steps': 19317, 'loss/train': 2.188796281814575}
-03/04/2022 12:09:00 - INFO - codeparrot_training - Step 19318: {'lr': 0.00048329734403993406, 'samples': 9891328, 'steps': 19318, 'loss/train': 2.335855484008789}
-03/04/2022 12:09:01 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/04/2022 12:09:05 - INFO - codeparrot_training - Step 19319: {'lr': 0.00048329543682298307, 'samples': 9891840, 'steps': 19319, 'loss/train': 1.6678653955459595}
-03/04/2022 12:09:08 - INFO - codeparrot_training - Step 19320: {'lr': 0.0004832935295009127, 'samples': 9892352, 'steps': 19320, 'loss/train': 2.1617918014526367}
-03/04/2022 12:09:10 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 12:09:13 - INFO - codeparrot_training - Step 19321: {'lr': 0.0004832916220737239, 'samples': 9892864, 'steps': 19321, 'loss/train': 2.206672430038452}
-03/04/2022 12:09:16 - INFO - codeparrot_training - Step 19322: {'lr': 0.0004832897145414175, 'samples': 9893376, 'steps': 19322, 'loss/train': 1.6992571353912354}
-03/04/2022 12:09:18 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 12:09:22 - INFO - codeparrot_training - Step 19323: {'lr': 0.0004832878069039943, 'samples': 9893888, 'steps': 19323, 'loss/train': 1.1923803091049194}
-03/04/2022 12:09:25 - INFO - codeparrot_training - Step 19324: {'lr': 0.0004832858991614553, 'samples': 9894400, 'steps': 19324, 'loss/train': 1.9934492111206055}
-03/04/2022 12:09:27 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 12:09:30 - INFO - codeparrot_training - Step 19325: {'lr': 0.00048328399131380127, 'samples': 9894912, 'steps': 19325, 'loss/train': 1.8674728870391846}
-03/04/2022 12:09:34 - INFO - codeparrot_training - Step 19326: {'lr': 0.00048328208336103305, 'samples': 9895424, 'steps': 19326, 'loss/train': 1.5498058795928955}
-03/04/2022 12:09:36 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 12:09:39 - INFO - codeparrot_training - Step 19327: {'lr': 0.0004832801753031515, 'samples': 9895936, 'steps': 19327, 'loss/train': 2.139103889465332}
-03/04/2022 12:09:42 - INFO - codeparrot_training - Step 19328: {'lr': 0.00048327826714015756, 'samples': 9896448, 'steps': 19328, 'loss/train': 2.107386350631714}
-03/04/2022 12:09:45 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/04/2022 12:09:47 - INFO - codeparrot_training - Step 19329: {'lr': 0.00048327635887205196, 'samples': 9896960, 'steps': 19329, 'loss/train': 2.255783796310425}
-03/04/2022 12:09:51 - INFO - codeparrot_training - Step 19330: {'lr': 0.00048327445049883567, 'samples': 9897472, 'steps': 19330, 'loss/train': 2.0729496479034424}
-03/04/2022 12:09:53 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 12:09:56 - INFO - codeparrot_training - Step 19331: {'lr': 0.0004832725420205095, 'samples': 9897984, 'steps': 19331, 'loss/train': 2.3872690200805664}
-03/04/2022 12:09:59 - INFO - codeparrot_training - Step 19332: {'lr': 0.00048327063343707433, 'samples': 9898496, 'steps': 19332, 'loss/train': 0.9744631052017212}
-03/04/2022 12:10:02 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/04/2022 12:10:04 - INFO - codeparrot_training - Step 19333: {'lr': 0.000483268724748531, 'samples': 9899008, 'steps': 19333, 'loss/train': 1.9922106266021729}
-03/04/2022 12:10:07 - INFO - codeparrot_training - Step 19334: {'lr': 0.0004832668159548804, 'samples': 9899520, 'steps': 19334, 'loss/train': 1.9680490493774414}
-03/04/2022 12:10:10 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/04/2022 12:10:13 - INFO - codeparrot_training - Step 19335: {'lr': 0.00048326490705612337, 'samples': 9900032, 'steps': 19335, 'loss/train': 1.9399536848068237}
-03/04/2022 12:10:16 - INFO - codeparrot_training - Step 19336: {'lr': 0.0004832629980522608, 'samples': 9900544, 'steps': 19336, 'loss/train': 2.3833587169647217}
-03/04/2022 12:10:18 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 12:10:21 - INFO - codeparrot_training - Step 19337: {'lr': 0.00048326108894329345, 'samples': 9901056, 'steps': 19337, 'loss/train': 2.703951358795166}
-03/04/2022 12:10:24 - INFO - codeparrot_training - Step 19338: {'lr': 0.00048325917972922227, 'samples': 9901568, 'steps': 19338, 'loss/train': 1.470207929611206}
-03/04/2022 12:10:27 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 12:10:30 - INFO - codeparrot_training - Step 19339: {'lr': 0.00048325727041004815, 'samples': 9902080, 'steps': 19339, 'loss/train': 3.110485076904297}
-03/04/2022 12:10:33 - INFO - codeparrot_training - Step 19340: {'lr': 0.0004832553609857719, 'samples': 9902592, 'steps': 19340, 'loss/train': 2.1446051597595215}
-03/04/2022 12:10:35 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 12:10:38 - INFO - codeparrot_training - Step 19341: {'lr': 0.0004832534514563943, 'samples': 9903104, 'steps': 19341, 'loss/train': 2.3085782527923584}
-03/04/2022 12:10:41 - INFO - codeparrot_training - Step 19342: {'lr': 0.0004832515418219164, 'samples': 9903616, 'steps': 19342, 'loss/train': 1.6689728498458862}
-03/04/2022 12:10:44 - INFO - codeparrot_training - Step 19343: {'lr': 0.0004832496320823389, 'samples': 9904128, 'steps': 19343, 'loss/train': 2.0844027996063232}
-03/04/2022 12:10:44 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 12:10:50 - INFO - codeparrot_training - Step 19344: {'lr': 0.0004832477222376627, 'samples': 9904640, 'steps': 19344, 'loss/train': 2.620640993118286}
-03/04/2022 12:10:53 - INFO - codeparrot_training - Step 19345: {'lr': 0.0004832458122878888, 'samples': 9905152, 'steps': 19345, 'loss/train': 2.244377851486206}
-03/04/2022 12:10:53 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/04/2022 12:10:58 - INFO - codeparrot_training - Step 19346: {'lr': 0.0004832439022330178, 'samples': 9905664, 'steps': 19346, 'loss/train': 1.867787480354309}
-03/04/2022 12:11:01 - INFO - codeparrot_training - Step 19347: {'lr': 0.00048324199207305075, 'samples': 9906176, 'steps': 19347, 'loss/train': 2.215949535369873}
-03/04/2022 12:11:01 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/04/2022 12:11:06 - INFO - codeparrot_training - Step 19348: {'lr': 0.0004832400818079884, 'samples': 9906688, 'steps': 19348, 'loss/train': 0.7336384654045105}
-03/04/2022 12:11:09 - INFO - codeparrot_training - Step 19349: {'lr': 0.00048323817143783174, 'samples': 9907200, 'steps': 19349, 'loss/train': 1.5405983924865723}
-03/04/2022 12:11:10 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/04/2022 12:11:15 - INFO - codeparrot_training - Step 19350: {'lr': 0.0004832362609625815, 'samples': 9907712, 'steps': 19350, 'loss/train': 2.5343809127807617}
-03/04/2022 12:11:18 - INFO - codeparrot_training - Step 19351: {'lr': 0.0004832343503822386, 'samples': 9908224, 'steps': 19351, 'loss/train': 1.4504948854446411}
-03/04/2022 12:11:18 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/04/2022 12:11:23 - INFO - codeparrot_training - Step 19352: {'lr': 0.000483232439696804, 'samples': 9908736, 'steps': 19352, 'loss/train': 0.884429395198822}
-03/04/2022 12:11:26 - INFO - codeparrot_training - Step 19353: {'lr': 0.0004832305289062784, 'samples': 9909248, 'steps': 19353, 'loss/train': 1.5595014095306396}
-03/04/2022 12:11:27 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 12:11:32 - INFO - codeparrot_training - Step 19354: {'lr': 0.00048322861801066265, 'samples': 9909760, 'steps': 19354, 'loss/train': 2.072275161743164}
-03/04/2022 12:11:35 - INFO - codeparrot_training - Step 19355: {'lr': 0.00048322670700995775, 'samples': 9910272, 'steps': 19355, 'loss/train': 1.8293801546096802}
-03/04/2022 12:11:35 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/04/2022 12:11:40 - INFO - codeparrot_training - Step 19356: {'lr': 0.0004832247959041645, 'samples': 9910784, 'steps': 19356, 'loss/train': 2.4597456455230713}
-03/04/2022 12:11:43 - INFO - codeparrot_training - Step 19357: {'lr': 0.0004832228846932838, 'samples': 9911296, 'steps': 19357, 'loss/train': 1.856176495552063}
-03/04/2022 12:11:43 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/04/2022 12:11:49 - INFO - codeparrot_training - Step 19358: {'lr': 0.0004832209733773164, 'samples': 9911808, 'steps': 19358, 'loss/train': 2.220309019088745}
-03/04/2022 12:11:52 - INFO - codeparrot_training - Step 19359: {'lr': 0.0004832190619562632, 'samples': 9912320, 'steps': 19359, 'loss/train': 2.279001474380493}
-03/04/2022 12:11:53 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/04/2022 12:11:57 - INFO - codeparrot_training - Step 19360: {'lr': 0.00048321715043012515, 'samples': 9912832, 'steps': 19360, 'loss/train': 1.7336853742599487}
-03/04/2022 12:12:00 - INFO - codeparrot_training - Step 19361: {'lr': 0.00048321523879890307, 'samples': 9913344, 'steps': 19361, 'loss/train': 1.6324422359466553}
-03/04/2022 12:12:01 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/04/2022 12:12:06 - INFO - codeparrot_training - Step 19362: {'lr': 0.00048321332706259773, 'samples': 9913856, 'steps': 19362, 'loss/train': 2.036705255508423}
-03/04/2022 12:12:09 - INFO - codeparrot_training - Step 19363: {'lr': 0.0004832114152212101, 'samples': 9914368, 'steps': 19363, 'loss/train': 2.0809576511383057}
-03/04/2022 12:12:09 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 12:12:14 - INFO - codeparrot_training - Step 19364: {'lr': 0.000483209503274741, 'samples': 9914880, 'steps': 19364, 'loss/train': 1.6379246711730957}
-03/04/2022 12:12:17 - INFO - codeparrot_training - Step 19365: {'lr': 0.0004832075912231913, 'samples': 9915392, 'steps': 19365, 'loss/train': 1.777904987335205}
-03/04/2022 12:12:18 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/04/2022 12:12:23 - INFO - codeparrot_training - Step 19366: {'lr': 0.0004832056790665619, 'samples': 9915904, 'steps': 19366, 'loss/train': 0.5791195631027222}
-03/04/2022 12:12:26 - INFO - codeparrot_training - Step 19367: {'lr': 0.0004832037668048536, 'samples': 9916416, 'steps': 19367, 'loss/train': 1.7071946859359741}
-03/04/2022 12:12:26 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/04/2022 12:12:31 - INFO - codeparrot_training - Step 19368: {'lr': 0.00048320185443806717, 'samples': 9916928, 'steps': 19368, 'loss/train': 2.0559747219085693}
-03/04/2022 12:12:34 - INFO - codeparrot_training - Step 19369: {'lr': 0.0004831999419662037, 'samples': 9917440, 'steps': 19369, 'loss/train': 1.5099694728851318}
-03/04/2022 12:12:35 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/04/2022 12:12:40 - INFO - codeparrot_training - Step 19370: {'lr': 0.0004831980293892639, 'samples': 9917952, 'steps': 19370, 'loss/train': 1.4393583536148071}
-03/04/2022 12:12:43 - INFO - codeparrot_training - Step 19371: {'lr': 0.0004831961167072487, 'samples': 9918464, 'steps': 19371, 'loss/train': 2.0649352073669434}
-03/04/2022 12:12:44 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/04/2022 12:12:48 - INFO - codeparrot_training - Step 19372: {'lr': 0.0004831942039201589, 'samples': 9918976, 'steps': 19372, 'loss/train': 1.838057279586792}
-03/04/2022 12:12:51 - INFO - codeparrot_training - Step 19373: {'lr': 0.0004831922910279954, 'samples': 9919488, 'steps': 19373, 'loss/train': 2.1100895404815674}
-03/04/2022 12:12:53 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 12:12:57 - INFO - codeparrot_training - Step 19374: {'lr': 0.000483190378030759, 'samples': 9920000, 'steps': 19374, 'loss/train': 2.1403770446777344}
-03/04/2022 12:13:00 - INFO - codeparrot_training - Step 19375: {'lr': 0.0004831884649284507, 'samples': 9920512, 'steps': 19375, 'loss/train': 1.5291773080825806}
-03/04/2022 12:13:01 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 12:13:05 - INFO - codeparrot_training - Step 19376: {'lr': 0.00048318655172107126, 'samples': 9921024, 'steps': 19376, 'loss/train': 1.7640737295150757}
-03/04/2022 12:13:08 - INFO - codeparrot_training - Step 19377: {'lr': 0.0004831846384086215, 'samples': 9921536, 'steps': 19377, 'loss/train': 1.6455087661743164}
-03/04/2022 12:13:10 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/04/2022 12:13:14 - INFO - codeparrot_training - Step 19378: {'lr': 0.0004831827249911024, 'samples': 9922048, 'steps': 19378, 'loss/train': 1.585808277130127}
-03/04/2022 12:13:17 - INFO - codeparrot_training - Step 19379: {'lr': 0.0004831808114685147, 'samples': 9922560, 'steps': 19379, 'loss/train': 2.1369926929473877}
-03/04/2022 12:13:18 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/04/2022 12:13:22 - INFO - codeparrot_training - Step 19380: {'lr': 0.00048317889784085935, 'samples': 9923072, 'steps': 19380, 'loss/train': 2.4225330352783203}
-03/04/2022 12:13:25 - INFO - codeparrot_training - Step 19381: {'lr': 0.0004831769841081372, 'samples': 9923584, 'steps': 19381, 'loss/train': 4.066267490386963}
-03/04/2022 12:13:27 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 12:13:30 - INFO - codeparrot_training - Step 19382: {'lr': 0.00048317507027034913, 'samples': 9924096, 'steps': 19382, 'loss/train': 1.6341750621795654}
-03/04/2022 12:13:34 - INFO - codeparrot_training - Step 19383: {'lr': 0.0004831731563274959, 'samples': 9924608, 'steps': 19383, 'loss/train': 1.903091311454773}
-03/04/2022 12:13:35 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 12:13:39 - INFO - codeparrot_training - Step 19384: {'lr': 0.0004831712422795785, 'samples': 9925120, 'steps': 19384, 'loss/train': 2.115166187286377}
-03/04/2022 12:13:42 - INFO - codeparrot_training - Step 19385: {'lr': 0.00048316932812659776, 'samples': 9925632, 'steps': 19385, 'loss/train': 1.5342516899108887}
-03/04/2022 12:13:44 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/04/2022 12:13:47 - INFO - codeparrot_training - Step 19386: {'lr': 0.00048316741386855445, 'samples': 9926144, 'steps': 19386, 'loss/train': 1.8595731258392334}
-03/04/2022 12:13:51 - INFO - codeparrot_training - Step 19387: {'lr': 0.0004831654995054495, 'samples': 9926656, 'steps': 19387, 'loss/train': 1.5135680437088013}
-03/04/2022 12:13:53 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/04/2022 12:13:56 - INFO - codeparrot_training - Step 19388: {'lr': 0.0004831635850372838, 'samples': 9927168, 'steps': 19388, 'loss/train': 2.286105155944824}
-03/04/2022 12:13:59 - INFO - codeparrot_training - Step 19389: {'lr': 0.00048316167046405826, 'samples': 9927680, 'steps': 19389, 'loss/train': 1.7907754182815552}
-03/04/2022 12:14:01 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 12:14:04 - INFO - codeparrot_training - Step 19390: {'lr': 0.0004831597557857735, 'samples': 9928192, 'steps': 19390, 'loss/train': 2.052823543548584}
-03/04/2022 12:14:08 - INFO - codeparrot_training - Step 19391: {'lr': 0.00048315784100243063, 'samples': 9928704, 'steps': 19391, 'loss/train': 2.0606441497802734}
-03/04/2022 12:14:10 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/04/2022 12:14:13 - INFO - codeparrot_training - Step 19392: {'lr': 0.0004831559261140305, 'samples': 9929216, 'steps': 19392, 'loss/train': 2.084334373474121}
-03/04/2022 12:14:16 - INFO - codeparrot_training - Step 19393: {'lr': 0.0004831540111205739, 'samples': 9929728, 'steps': 19393, 'loss/train': 2.010958194732666}
-03/04/2022 12:14:18 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/04/2022 12:14:21 - INFO - codeparrot_training - Step 19394: {'lr': 0.00048315209602206165, 'samples': 9930240, 'steps': 19394, 'loss/train': 2.6461446285247803}
-03/04/2022 12:14:25 - INFO - codeparrot_training - Step 19395: {'lr': 0.0004831501808184947, 'samples': 9930752, 'steps': 19395, 'loss/train': 1.9386167526245117}
-03/04/2022 12:14:27 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 12:14:30 - INFO - codeparrot_training - Step 19396: {'lr': 0.0004831482655098738, 'samples': 9931264, 'steps': 19396, 'loss/train': 1.460323691368103}
-03/04/2022 12:14:33 - INFO - codeparrot_training - Step 19397: {'lr': 0.00048314635009619997, 'samples': 9931776, 'steps': 19397, 'loss/train': 1.9102013111114502}
-03/04/2022 12:14:35 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/04/2022 12:14:38 - INFO - codeparrot_training - Step 19398: {'lr': 0.0004831444345774739, 'samples': 9932288, 'steps': 19398, 'loss/train': 2.3662991523742676}
-03/04/2022 12:14:41 - INFO - codeparrot_training - Step 19399: {'lr': 0.00048314251895369663, 'samples': 9932800, 'steps': 19399, 'loss/train': 1.2344551086425781}
-03/04/2022 12:14:44 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 12:14:47 - INFO - codeparrot_training - Step 19400: {'lr': 0.000483140603224869, 'samples': 9933312, 'steps': 19400, 'loss/train': 2.3091928958892822}
-03/04/2022 12:14:50 - INFO - codeparrot_training - Step 19401: {'lr': 0.00048313868739099166, 'samples': 9933824, 'steps': 19401, 'loss/train': 1.1534194946289062}
-03/04/2022 12:14:52 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 12:14:55 - INFO - codeparrot_training - Step 19402: {'lr': 0.0004831367714520657, 'samples': 9934336, 'steps': 19402, 'loss/train': 1.9784660339355469}
-03/04/2022 12:14:58 - INFO - codeparrot_training - Step 19403: {'lr': 0.0004831348554080919, 'samples': 9934848, 'steps': 19403, 'loss/train': 1.7035642862319946}
-03/04/2022 12:15:01 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/04/2022 12:15:04 - INFO - codeparrot_training - Step 19404: {'lr': 0.0004831329392590711, 'samples': 9935360, 'steps': 19404, 'loss/train': 2.002788782119751}
-03/04/2022 12:15:07 - INFO - codeparrot_training - Step 19405: {'lr': 0.00048313102300500424, 'samples': 9935872, 'steps': 19405, 'loss/train': 2.222447395324707}
-03/04/2022 12:15:10 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 12:15:12 - INFO - codeparrot_training - Step 19406: {'lr': 0.00048312910664589215, 'samples': 9936384, 'steps': 19406, 'loss/train': 1.5017746686935425}
-03/04/2022 12:15:15 - INFO - codeparrot_training - Step 19407: {'lr': 0.0004831271901817357, 'samples': 9936896, 'steps': 19407, 'loss/train': 1.5154513120651245}
-03/04/2022 12:15:18 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 12:15:21 - INFO - codeparrot_training - Step 19408: {'lr': 0.00048312527361253567, 'samples': 9937408, 'steps': 19408, 'loss/train': 1.360522985458374}
-03/04/2022 12:15:24 - INFO - codeparrot_training - Step 19409: {'lr': 0.000483123356938293, 'samples': 9937920, 'steps': 19409, 'loss/train': 1.5016167163848877}
-03/04/2022 12:15:26 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 12:15:29 - INFO - codeparrot_training - Step 19410: {'lr': 0.00048312144015900856, 'samples': 9938432, 'steps': 19410, 'loss/train': 2.0484724044799805}
-03/04/2022 12:15:32 - INFO - codeparrot_training - Step 19411: {'lr': 0.00048311952327468325, 'samples': 9938944, 'steps': 19411, 'loss/train': 1.936078667640686}
-03/04/2022 12:15:35 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/04/2022 12:15:37 - INFO - codeparrot_training - Step 19412: {'lr': 0.00048311760628531777, 'samples': 9939456, 'steps': 19412, 'loss/train': 1.872390627861023}
-03/04/2022 12:15:41 - INFO - codeparrot_training - Step 19413: {'lr': 0.00048311568919091316, 'samples': 9939968, 'steps': 19413, 'loss/train': 1.6997140645980835}
-03/04/2022 12:15:43 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/04/2022 12:15:46 - INFO - codeparrot_training - Step 19414: {'lr': 0.00048311377199147023, 'samples': 9940480, 'steps': 19414, 'loss/train': 2.1552505493164062}
-03/04/2022 12:15:49 - INFO - codeparrot_training - Step 19415: {'lr': 0.00048311185468698974, 'samples': 9940992, 'steps': 19415, 'loss/train': 1.7392278909683228}
-03/04/2022 12:15:52 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 12:15:55 - INFO - codeparrot_training - Step 19416: {'lr': 0.00048310993727747277, 'samples': 9941504, 'steps': 19416, 'loss/train': 1.571963906288147}
-03/04/2022 12:15:58 - INFO - codeparrot_training - Step 19417: {'lr': 0.00048310801976292, 'samples': 9942016, 'steps': 19417, 'loss/train': 2.1123247146606445}
-03/04/2022 12:16:01 - INFO - codeparrot_training - Step 19418: {'lr': 0.0004831061021433323, 'samples': 9942528, 'steps': 19418, 'loss/train': 0.5974637866020203}
-03/04/2022 12:16:01 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/04/2022 12:16:06 - INFO - codeparrot_training - Step 19419: {'lr': 0.00048310418441871065, 'samples': 9943040, 'steps': 19419, 'loss/train': 2.9887120723724365}
-03/04/2022 12:16:09 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/04/2022 12:16:11 - INFO - codeparrot_training - Step 19420: {'lr': 0.00048310226658905585, 'samples': 9943552, 'steps': 19420, 'loss/train': 1.8934903144836426}
-03/04/2022 12:16:15 - INFO - codeparrot_training - Step 19421: {'lr': 0.00048310034865436876, 'samples': 9944064, 'steps': 19421, 'loss/train': 2.0137338638305664}
-03/04/2022 12:16:17 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 12:16:20 - INFO - codeparrot_training - Step 19422: {'lr': 0.0004830984306146503, 'samples': 9944576, 'steps': 19422, 'loss/train': 1.6406397819519043}
-03/04/2022 12:16:23 - INFO - codeparrot_training - Step 19423: {'lr': 0.0004830965124699012, 'samples': 9945088, 'steps': 19423, 'loss/train': 1.6938649415969849}
-03/04/2022 12:16:26 - INFO - codeparrot_training - Step 19424: {'lr': 0.00048309459422012243, 'samples': 9945600, 'steps': 19424, 'loss/train': 0.2350090742111206}
-03/04/2022 12:16:27 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 12:16:32 - INFO - codeparrot_training - Step 19425: {'lr': 0.0004830926758653148, 'samples': 9946112, 'steps': 19425, 'loss/train': 1.2396119832992554}
-03/04/2022 12:16:35 - INFO - codeparrot_training - Step 19426: {'lr': 0.00048309075740547925, 'samples': 9946624, 'steps': 19426, 'loss/train': 2.0918478965759277}
-03/04/2022 12:16:35 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/04/2022 12:16:40 - INFO - codeparrot_training - Step 19427: {'lr': 0.0004830888388406166, 'samples': 9947136, 'steps': 19427, 'loss/train': 2.319352149963379}
-03/04/2022 12:16:43 - INFO - codeparrot_training - Step 19428: {'lr': 0.00048308692017072773, 'samples': 9947648, 'steps': 19428, 'loss/train': 1.8921654224395752}
-03/04/2022 12:16:44 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/04/2022 12:16:48 - INFO - codeparrot_training - Step 19429: {'lr': 0.00048308500139581344, 'samples': 9948160, 'steps': 19429, 'loss/train': 2.432421922683716}
-03/04/2022 12:16:52 - INFO - codeparrot_training - Step 19430: {'lr': 0.00048308308251587476, 'samples': 9948672, 'steps': 19430, 'loss/train': 2.0783071517944336}
-03/04/2022 12:16:52 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 12:16:57 - INFO - codeparrot_training - Step 19431: {'lr': 0.00048308116353091234, 'samples': 9949184, 'steps': 19431, 'loss/train': 0.9391849637031555}
-03/04/2022 12:17:00 - INFO - codeparrot_training - Step 19432: {'lr': 0.00048307924444092716, 'samples': 9949696, 'steps': 19432, 'loss/train': 2.500607967376709}
-03/04/2022 12:17:01 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 12:17:05 - INFO - codeparrot_training - Step 19433: {'lr': 0.0004830773252459201, 'samples': 9950208, 'steps': 19433, 'loss/train': 2.1477081775665283}
-03/04/2022 12:17:09 - INFO - codeparrot_training - Step 19434: {'lr': 0.00048307540594589194, 'samples': 9950720, 'steps': 19434, 'loss/train': 1.7711230516433716}
-03/04/2022 12:17:09 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 12:17:14 - INFO - codeparrot_training - Step 19435: {'lr': 0.0004830734865408437, 'samples': 9951232, 'steps': 19435, 'loss/train': 1.4419500827789307}
-03/04/2022 12:17:17 - INFO - codeparrot_training - Step 19436: {'lr': 0.000483071567030776, 'samples': 9951744, 'steps': 19436, 'loss/train': 1.2735028266906738}
-03/04/2022 12:17:18 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/04/2022 12:17:23 - INFO - codeparrot_training - Step 19437: {'lr': 0.00048306964741568994, 'samples': 9952256, 'steps': 19437, 'loss/train': 1.419663667678833}
-03/04/2022 12:17:26 - INFO - codeparrot_training - Step 19438: {'lr': 0.00048306772769558624, 'samples': 9952768, 'steps': 19438, 'loss/train': 2.163883686065674}
-03/04/2022 12:17:27 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 12:17:31 - INFO - codeparrot_training - Step 19439: {'lr': 0.0004830658078704659, 'samples': 9953280, 'steps': 19439, 'loss/train': 1.9183329343795776}
-03/04/2022 12:17:34 - INFO - codeparrot_training - Step 19440: {'lr': 0.0004830638879403296, 'samples': 9953792, 'steps': 19440, 'loss/train': 1.5530331134796143}
-03/04/2022 12:17:36 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 12:17:40 - INFO - codeparrot_training - Step 19441: {'lr': 0.00048306196790517844, 'samples': 9954304, 'steps': 19441, 'loss/train': 0.17361800372600555}
-03/04/2022 12:17:43 - INFO - codeparrot_training - Step 19442: {'lr': 0.0004830600477650131, 'samples': 9954816, 'steps': 19442, 'loss/train': 1.9050164222717285}
-03/04/2022 12:17:44 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/04/2022 12:17:48 - INFO - codeparrot_training - Step 19443: {'lr': 0.0004830581275198344, 'samples': 9955328, 'steps': 19443, 'loss/train': 2.2285735607147217}
-03/04/2022 12:17:51 - INFO - codeparrot_training - Step 19444: {'lr': 0.00048305620716964336, 'samples': 9955840, 'steps': 19444, 'loss/train': 1.9254708290100098}
-03/04/2022 12:17:53 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 12:17:57 - INFO - codeparrot_training - Step 19445: {'lr': 0.00048305428671444083, 'samples': 9956352, 'steps': 19445, 'loss/train': 2.113628625869751}
-03/04/2022 12:18:00 - INFO - codeparrot_training - Step 19446: {'lr': 0.00048305236615422763, 'samples': 9956864, 'steps': 19446, 'loss/train': 6.591501712799072}
-03/04/2022 12:18:02 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 12:18:05 - INFO - codeparrot_training - Step 19447: {'lr': 0.00048305044548900463, 'samples': 9957376, 'steps': 19447, 'loss/train': 1.8314212560653687}
-03/04/2022 12:18:08 - INFO - codeparrot_training - Step 19448: {'lr': 0.0004830485247187727, 'samples': 9957888, 'steps': 19448, 'loss/train': 1.7388160228729248}
-03/04/2022 12:18:11 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/04/2022 12:18:14 - INFO - codeparrot_training - Step 19449: {'lr': 0.0004830466038435327, 'samples': 9958400, 'steps': 19449, 'loss/train': 2.6245033740997314}
-03/04/2022 12:18:17 - INFO - codeparrot_training - Step 19450: {'lr': 0.0004830446828632854, 'samples': 9958912, 'steps': 19450, 'loss/train': 1.7751208543777466}
-03/04/2022 12:18:20 - INFO - codeparrot_training - Step 19451: {'lr': 0.00048304276177803186, 'samples': 9959424, 'steps': 19451, 'loss/train': 1.7307716608047485}
-03/04/2022 12:18:20 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/04/2022 12:18:25 - INFO - codeparrot_training - Step 19452: {'lr': 0.00048304084058777285, 'samples': 9959936, 'steps': 19452, 'loss/train': 1.3346421718597412}
-03/04/2022 12:18:29 - INFO - codeparrot_training - Step 19453: {'lr': 0.00048303891929250923, 'samples': 9960448, 'steps': 19453, 'loss/train': 1.4874038696289062}
-03/04/2022 12:18:29 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 12:18:34 - INFO - codeparrot_training - Step 19454: {'lr': 0.0004830369978922418, 'samples': 9960960, 'steps': 19454, 'loss/train': 2.417426586151123}
-03/04/2022 12:18:37 - INFO - codeparrot_training - Step 19455: {'lr': 0.00048303507638697155, 'samples': 9961472, 'steps': 19455, 'loss/train': 1.5272533893585205}
-03/04/2022 12:18:37 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/04/2022 12:18:42 - INFO - codeparrot_training - Step 19456: {'lr': 0.0004830331547766993, 'samples': 9961984, 'steps': 19456, 'loss/train': 2.231531858444214}
-03/04/2022 12:18:45 - INFO - codeparrot_training - Step 19457: {'lr': 0.0004830312330614259, 'samples': 9962496, 'steps': 19457, 'loss/train': 1.2478259801864624}
-03/04/2022 12:18:45 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 12:18:51 - INFO - codeparrot_training - Step 19458: {'lr': 0.00048302931124115226, 'samples': 9963008, 'steps': 19458, 'loss/train': 2.0705831050872803}
-03/04/2022 12:18:54 - INFO - codeparrot_training - Step 19459: {'lr': 0.0004830273893158791, 'samples': 9963520, 'steps': 19459, 'loss/train': 1.7067620754241943}
-03/04/2022 12:18:54 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/04/2022 12:18:59 - INFO - codeparrot_training - Step 19460: {'lr': 0.0004830254672856075, 'samples': 9964032, 'steps': 19460, 'loss/train': 1.600019097328186}
-03/04/2022 12:19:02 - INFO - codeparrot_training - Step 19461: {'lr': 0.00048302354515033813, 'samples': 9964544, 'steps': 19461, 'loss/train': 0.7247123122215271}
-03/04/2022 12:19:02 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/04/2022 12:19:08 - INFO - codeparrot_training - Step 19462: {'lr': 0.00048302162291007203, 'samples': 9965056, 'steps': 19462, 'loss/train': 0.20816490054130554}
-03/04/2022 12:19:11 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 12:19:13 - INFO - codeparrot_training - Step 19463: {'lr': 0.00048301970056480994, 'samples': 9965568, 'steps': 19463, 'loss/train': 2.3204257488250732}
-03/04/2022 12:19:16 - INFO - codeparrot_training - Step 19464: {'lr': 0.00048301777811455274, 'samples': 9966080, 'steps': 19464, 'loss/train': 2.091796398162842}
-03/04/2022 12:19:19 - INFO - codeparrot_training - Step 19465: {'lr': 0.0004830158555593014, 'samples': 9966592, 'steps': 19465, 'loss/train': 1.9790256023406982}
-03/04/2022 12:19:19 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 12:19:25 - INFO - codeparrot_training - Step 19466: {'lr': 0.00048301393289905663, 'samples': 9967104, 'steps': 19466, 'loss/train': 1.699397087097168}
-03/04/2022 12:19:28 - INFO - codeparrot_training - Step 19467: {'lr': 0.00048301201013381946, 'samples': 9967616, 'steps': 19467, 'loss/train': 2.4085586071014404}
-03/04/2022 12:19:28 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 12:19:33 - INFO - codeparrot_training - Step 19468: {'lr': 0.00048301008726359064, 'samples': 9968128, 'steps': 19468, 'loss/train': 1.531436800956726}
-03/04/2022 12:19:37 - INFO - codeparrot_training - Step 19469: {'lr': 0.00048300816428837104, 'samples': 9968640, 'steps': 19469, 'loss/train': 2.052704095840454}
-03/04/2022 12:19:37 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/04/2022 12:19:42 - INFO - codeparrot_training - Step 19470: {'lr': 0.00048300624120816153, 'samples': 9969152, 'steps': 19470, 'loss/train': 1.5572563409805298}
-03/04/2022 12:19:45 - INFO - codeparrot_training - Step 19471: {'lr': 0.0004830043180229631, 'samples': 9969664, 'steps': 19471, 'loss/train': 1.6688894033432007}
-03/04/2022 12:19:45 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/04/2022 12:19:50 - INFO - codeparrot_training - Step 19472: {'lr': 0.0004830023947327764, 'samples': 9970176, 'steps': 19472, 'loss/train': 1.6920973062515259}
-03/04/2022 12:19:53 - INFO - codeparrot_training - Step 19473: {'lr': 0.0004830004713376025, 'samples': 9970688, 'steps': 19473, 'loss/train': 2.8595988750457764}
-03/04/2022 12:19:53 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 12:19:58 - INFO - codeparrot_training - Step 19474: {'lr': 0.00048299854783744224, 'samples': 9971200, 'steps': 19474, 'loss/train': 1.881035566329956}
-03/04/2022 12:20:01 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/04/2022 12:20:04 - INFO - codeparrot_training - Step 19475: {'lr': 0.0004829966242322963, 'samples': 9971712, 'steps': 19475, 'loss/train': 2.28920316696167}
-03/04/2022 12:20:07 - INFO - codeparrot_training - Step 19476: {'lr': 0.00048299470052216576, 'samples': 9972224, 'steps': 19476, 'loss/train': 1.7556978464126587}
-03/04/2022 12:20:10 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/04/2022 12:20:12 - INFO - codeparrot_training - Step 19477: {'lr': 0.0004829927767070514, 'samples': 9972736, 'steps': 19477, 'loss/train': 2.22821307182312}
-03/04/2022 12:20:15 - INFO - codeparrot_training - Step 19478: {'lr': 0.0004829908527869541, 'samples': 9973248, 'steps': 19478, 'loss/train': 1.9674879312515259}
-03/04/2022 12:20:18 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/04/2022 12:20:21 - INFO - codeparrot_training - Step 19479: {'lr': 0.0004829889287618746, 'samples': 9973760, 'steps': 19479, 'loss/train': 1.6904776096343994}
-03/04/2022 12:20:24 - INFO - codeparrot_training - Step 19480: {'lr': 0.000482987004631814, 'samples': 9974272, 'steps': 19480, 'loss/train': 1.566239356994629}
-03/04/2022 12:20:27 - INFO - codeparrot_training - Step 19481: {'lr': 0.000482985080396773, 'samples': 9974784, 'steps': 19481, 'loss/train': 4.24210786819458}
-03/04/2022 12:20:27 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 12:20:32 - INFO - codeparrot_training - Step 19482: {'lr': 0.00048298315605675257, 'samples': 9975296, 'steps': 19482, 'loss/train': 2.1614882946014404}
-03/04/2022 12:20:35 - INFO - codeparrot_training - Step 19483: {'lr': 0.0004829812316117535, 'samples': 9975808, 'steps': 19483, 'loss/train': 1.0340620279312134}
-03/04/2022 12:20:35 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/04/2022 12:20:41 - INFO - codeparrot_training - Step 19484: {'lr': 0.0004829793070617767, 'samples': 9976320, 'steps': 19484, 'loss/train': 1.7095084190368652}
-03/04/2022 12:20:43 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 12:20:46 - INFO - codeparrot_training - Step 19485: {'lr': 0.000482977382406823, 'samples': 9976832, 'steps': 19485, 'loss/train': 1.198760747909546}
-03/04/2022 12:20:50 - INFO - codeparrot_training - Step 19486: {'lr': 0.00048297545764689327, 'samples': 9977344, 'steps': 19486, 'loss/train': 1.2047996520996094}
-03/04/2022 12:20:53 - INFO - codeparrot_training - Step 19487: {'lr': 0.00048297353278198843, 'samples': 9977856, 'steps': 19487, 'loss/train': 0.14014442265033722}
-03/04/2022 12:20:55 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/04/2022 12:20:58 - INFO - codeparrot_training - Step 19488: {'lr': 0.00048297160781210925, 'samples': 9978368, 'steps': 19488, 'loss/train': 1.6574344635009766}
-03/04/2022 12:21:01 - INFO - codeparrot_training - Step 19489: {'lr': 0.00048296968273725673, 'samples': 9978880, 'steps': 19489, 'loss/train': 1.616039514541626}
-03/04/2022 12:21:03 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 12:21:07 - INFO - codeparrot_training - Step 19490: {'lr': 0.0004829677575574316, 'samples': 9979392, 'steps': 19490, 'loss/train': 2.202183961868286}
-03/04/2022 12:21:10 - INFO - codeparrot_training - Step 19491: {'lr': 0.0004829658322726348, 'samples': 9979904, 'steps': 19491, 'loss/train': 1.9947285652160645}
-03/04/2022 12:21:12 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 12:21:15 - INFO - codeparrot_training - Step 19492: {'lr': 0.00048296390688286724, 'samples': 9980416, 'steps': 19492, 'loss/train': 2.507314682006836}
-03/04/2022 12:21:18 - INFO - codeparrot_training - Step 19493: {'lr': 0.00048296198138812974, 'samples': 9980928, 'steps': 19493, 'loss/train': 2.001742124557495}
-03/04/2022 12:21:21 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 12:21:23 - INFO - codeparrot_training - Step 19494: {'lr': 0.00048296005578842314, 'samples': 9981440, 'steps': 19494, 'loss/train': 1.9592903852462769}
-03/04/2022 12:21:27 - INFO - codeparrot_training - Step 19495: {'lr': 0.0004829581300837483, 'samples': 9981952, 'steps': 19495, 'loss/train': 2.031825304031372}
-03/04/2022 12:21:29 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/04/2022 12:21:32 - INFO - codeparrot_training - Step 19496: {'lr': 0.00048295620427410614, 'samples': 9982464, 'steps': 19496, 'loss/train': 1.0448518991470337}
-03/04/2022 12:21:35 - INFO - codeparrot_training - Step 19497: {'lr': 0.00048295427835949757, 'samples': 9982976, 'steps': 19497, 'loss/train': 2.4872782230377197}
-03/04/2022 12:21:37 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/04/2022 12:21:40 - INFO - codeparrot_training - Step 19498: {'lr': 0.0004829523523399233, 'samples': 9983488, 'steps': 19498, 'loss/train': 1.2650761604309082}
-03/04/2022 12:21:43 - INFO - codeparrot_training - Step 19499: {'lr': 0.0004829504262153844, 'samples': 9984000, 'steps': 19499, 'loss/train': 2.1082210540771484}
-03/04/2022 12:21:46 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 12:21:49 - INFO - codeparrot_training - Step 19500: {'lr': 0.00048294849998588155, 'samples': 9984512, 'steps': 19500, 'loss/train': 1.3178647756576538}
-03/04/2022 12:21:52 - INFO - codeparrot_training - Step 19501: {'lr': 0.0004829465736514157, 'samples': 9985024, 'steps': 19501, 'loss/train': 1.2574142217636108}
-03/04/2022 12:21:54 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 12:21:57 - INFO - codeparrot_training - Step 19502: {'lr': 0.0004829446472119878, 'samples': 9985536, 'steps': 19502, 'loss/train': 1.8499481678009033}
-03/04/2022 12:22:00 - INFO - codeparrot_training - Step 19503: {'lr': 0.0004829427206675986, 'samples': 9986048, 'steps': 19503, 'loss/train': 1.6837809085845947}
-03/04/2022 12:22:02 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 12:22:06 - INFO - codeparrot_training - Step 19504: {'lr': 0.000482940794018249, 'samples': 9986560, 'steps': 19504, 'loss/train': 1.8355480432510376}
-03/04/2022 12:22:09 - INFO - codeparrot_training - Step 19505: {'lr': 0.00048293886726393984, 'samples': 9987072, 'steps': 19505, 'loss/train': 2.2327864170074463}
-03/04/2022 12:22:11 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/04/2022 12:22:14 - INFO - codeparrot_training - Step 19506: {'lr': 0.00048293694040467205, 'samples': 9987584, 'steps': 19506, 'loss/train': 1.8651883602142334}
-03/04/2022 12:22:17 - INFO - codeparrot_training - Step 19507: {'lr': 0.00048293501344044644, 'samples': 9988096, 'steps': 19507, 'loss/train': 2.1500892639160156}
-03/04/2022 12:22:20 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/04/2022 12:22:23 - INFO - codeparrot_training - Step 19508: {'lr': 0.00048293308637126393, 'samples': 9988608, 'steps': 19508, 'loss/train': 1.6436740159988403}
-03/04/2022 12:22:26 - INFO - codeparrot_training - Step 19509: {'lr': 0.0004829311591971254, 'samples': 9989120, 'steps': 19509, 'loss/train': 1.94767427444458}
-03/04/2022 12:22:28 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/04/2022 12:22:31 - INFO - codeparrot_training - Step 19510: {'lr': 0.0004829292319180316, 'samples': 9989632, 'steps': 19510, 'loss/train': 2.696727752685547}
-03/04/2022 12:22:34 - INFO - codeparrot_training - Step 19511: {'lr': 0.00048292730453398355, 'samples': 9990144, 'steps': 19511, 'loss/train': 1.6681278944015503}
-03/04/2022 12:22:37 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/04/2022 12:22:39 - INFO - codeparrot_training - Step 19512: {'lr': 0.00048292537704498203, 'samples': 9990656, 'steps': 19512, 'loss/train': 1.2130415439605713}
-03/04/2022 12:22:43 - INFO - codeparrot_training - Step 19513: {'lr': 0.00048292344945102795, 'samples': 9991168, 'steps': 19513, 'loss/train': 1.0961002111434937}
-03/04/2022 12:22:45 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/04/2022 12:22:48 - INFO - codeparrot_training - Step 19514: {'lr': 0.0004829215217521221, 'samples': 9991680, 'steps': 19514, 'loss/train': 2.175157308578491}
-03/04/2022 12:22:51 - INFO - codeparrot_training - Step 19515: {'lr': 0.00048291959394826546, 'samples': 9992192, 'steps': 19515, 'loss/train': 1.7235057353973389}
-03/04/2022 12:22:54 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 12:22:56 - INFO - codeparrot_training - Step 19516: {'lr': 0.00048291766603945885, 'samples': 9992704, 'steps': 19516, 'loss/train': 2.1452224254608154}
-03/04/2022 12:22:59 - INFO - codeparrot_training - Step 19517: {'lr': 0.0004829157380257031, 'samples': 9993216, 'steps': 19517, 'loss/train': 1.732651948928833}
-03/04/2022 12:23:02 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/04/2022 12:23:05 - INFO - codeparrot_training - Step 19518: {'lr': 0.0004829138099069991, 'samples': 9993728, 'steps': 19518, 'loss/train': 2.2896955013275146}
-03/04/2022 12:23:08 - INFO - codeparrot_training - Step 19519: {'lr': 0.0004829118816833478, 'samples': 9994240, 'steps': 19519, 'loss/train': 1.7804704904556274}
-03/04/2022 12:23:10 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/04/2022 12:23:13 - INFO - codeparrot_training - Step 19520: {'lr': 0.00048290995335474997, 'samples': 9994752, 'steps': 19520, 'loss/train': 1.975152611732483}
-03/04/2022 12:23:16 - INFO - codeparrot_training - Step 19521: {'lr': 0.0004829080249212064, 'samples': 9995264, 'steps': 19521, 'loss/train': 1.7336583137512207}
-03/04/2022 12:23:19 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/04/2022 12:23:21 - INFO - codeparrot_training - Step 19522: {'lr': 0.00048290609638271823, 'samples': 9995776, 'steps': 19522, 'loss/train': 1.6004469394683838}
-03/04/2022 12:23:25 - INFO - codeparrot_training - Step 19523: {'lr': 0.00048290416773928615, 'samples': 9996288, 'steps': 19523, 'loss/train': 1.9194672107696533}
-03/04/2022 12:23:27 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/04/2022 12:23:30 - INFO - codeparrot_training - Step 19524: {'lr': 0.00048290223899091094, 'samples': 9996800, 'steps': 19524, 'loss/train': 1.548783302307129}
-03/04/2022 12:23:33 - INFO - codeparrot_training - Step 19525: {'lr': 0.0004829003101375937, 'samples': 9997312, 'steps': 19525, 'loss/train': 1.8592116832733154}
-03/04/2022 12:23:35 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/04/2022 12:23:38 - INFO - codeparrot_training - Step 19526: {'lr': 0.00048289838117933505, 'samples': 9997824, 'steps': 19526, 'loss/train': 2.3796582221984863}
-03/04/2022 12:23:42 - INFO - codeparrot_training - Step 19527: {'lr': 0.0004828964521161361, 'samples': 9998336, 'steps': 19527, 'loss/train': 1.2461003065109253}
-03/04/2022 12:23:44 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/04/2022 12:23:47 - INFO - codeparrot_training - Step 19528: {'lr': 0.0004828945229479975, 'samples': 9998848, 'steps': 19528, 'loss/train': 2.2604713439941406}
-03/04/2022 12:23:50 - INFO - codeparrot_training - Step 19529: {'lr': 0.0004828925936749202, 'samples': 9999360, 'steps': 19529, 'loss/train': 1.5753413438796997}
-03/04/2022 12:23:53 - INFO - codeparrot_training - Step 19530: {'lr': 0.0004828906642969052, 'samples': 9999872, 'steps': 19530, 'loss/train': 1.0638411045074463}
-03/04/2022 12:23:53 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 12:23:59 - INFO - codeparrot_training - Step 19531: {'lr': 0.00048288873481395323, 'samples': 10000384, 'steps': 19531, 'loss/train': 2.356968402862549}
-03/04/2022 12:24:02 - INFO - codeparrot_training - Step 19532: {'lr': 0.0004828868052260652, 'samples': 10000896, 'steps': 19532, 'loss/train': 0.748901903629303}
-03/04/2022 12:24:02 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 12:24:07 - INFO - codeparrot_training - Step 19533: {'lr': 0.0004828848755332419, 'samples': 10001408, 'steps': 19533, 'loss/train': 1.8329068422317505}
-03/04/2022 12:24:10 - INFO - codeparrot_training - Step 19534: {'lr': 0.0004828829457354843, 'samples': 10001920, 'steps': 19534, 'loss/train': 1.0727920532226562}
-03/04/2022 12:24:11 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 12:24:16 - INFO - codeparrot_training - Step 19535: {'lr': 0.0004828810158327933, 'samples': 10002432, 'steps': 19535, 'loss/train': 1.2543997764587402}
-03/04/2022 12:24:19 - INFO - codeparrot_training - Step 19536: {'lr': 0.00048287908582516964, 'samples': 10002944, 'steps': 19536, 'loss/train': 0.34468138217926025}
-03/04/2022 12:24:19 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 12:24:24 - INFO - codeparrot_training - Step 19537: {'lr': 0.00048287715571261424, 'samples': 10003456, 'steps': 19537, 'loss/train': 1.2039214372634888}
-03/04/2022 12:24:28 - INFO - codeparrot_training - Step 19538: {'lr': 0.00048287522549512806, 'samples': 10003968, 'steps': 19538, 'loss/train': 0.6806887984275818}
-03/04/2022 12:24:28 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/04/2022 12:24:33 - INFO - codeparrot_training - Step 19539: {'lr': 0.0004828732951727119, 'samples': 10004480, 'steps': 19539, 'loss/train': 1.8837666511535645}
-03/04/2022 12:24:36 - INFO - codeparrot_training - Step 19540: {'lr': 0.00048287136474536657, 'samples': 10004992, 'steps': 19540, 'loss/train': 1.9773361682891846}
-03/04/2022 12:24:37 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/04/2022 12:24:41 - INFO - codeparrot_training - Step 19541: {'lr': 0.000482869434213093, 'samples': 10005504, 'steps': 19541, 'loss/train': 2.079502582550049}
-03/04/2022 12:24:44 - INFO - codeparrot_training - Step 19542: {'lr': 0.0004828675035758921, 'samples': 10006016, 'steps': 19542, 'loss/train': 1.6656849384307861}
-03/04/2022 12:24:45 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 12:24:50 - INFO - codeparrot_training - Step 19543: {'lr': 0.00048286557283376465, 'samples': 10006528, 'steps': 19543, 'loss/train': 1.924633502960205}
-03/04/2022 12:24:53 - INFO - codeparrot_training - Step 19544: {'lr': 0.0004828636419867116, 'samples': 10007040, 'steps': 19544, 'loss/train': 1.9084010124206543}
-03/04/2022 12:24:53 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/04/2022 12:24:58 - INFO - codeparrot_training - Step 19545: {'lr': 0.00048286171103473376, 'samples': 10007552, 'steps': 19545, 'loss/train': 2.430124521255493}
-03/04/2022 12:25:01 - INFO - codeparrot_training - Step 19546: {'lr': 0.00048285977997783203, 'samples': 10008064, 'steps': 19546, 'loss/train': 2.267749547958374}
-03/04/2022 12:25:01 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 12:25:06 - INFO - codeparrot_training - Step 19547: {'lr': 0.0004828578488160073, 'samples': 10008576, 'steps': 19547, 'loss/train': 1.7599269151687622}
-03/04/2022 12:25:10 - INFO - codeparrot_training - Step 19548: {'lr': 0.0004828559175492604, 'samples': 10009088, 'steps': 19548, 'loss/train': 2.2090535163879395}
-03/04/2022 12:25:10 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/04/2022 12:25:15 - INFO - codeparrot_training - Step 19549: {'lr': 0.0004828539861775922, 'samples': 10009600, 'steps': 19549, 'loss/train': 2.474966049194336}
-03/04/2022 12:25:18 - INFO - codeparrot_training - Step 19550: {'lr': 0.0004828520547010036, 'samples': 10010112, 'steps': 19550, 'loss/train': 2.012188196182251}
-03/04/2022 12:25:18 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 12:25:23 - INFO - codeparrot_training - Step 19551: {'lr': 0.0004828501231194955, 'samples': 10010624, 'steps': 19551, 'loss/train': 2.024797201156616}
-03/04/2022 12:25:26 - INFO - codeparrot_training - Step 19552: {'lr': 0.0004828481914330687, 'samples': 10011136, 'steps': 19552, 'loss/train': 2.010770797729492}
-03/04/2022 12:25:26 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 12:25:32 - INFO - codeparrot_training - Step 19553: {'lr': 0.000482846259641724, 'samples': 10011648, 'steps': 19553, 'loss/train': 1.7437877655029297}
-03/04/2022 12:25:35 - INFO - codeparrot_training - Step 19554: {'lr': 0.0004828443277454625, 'samples': 10012160, 'steps': 19554, 'loss/train': 1.518804669380188}
-03/04/2022 12:25:35 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/04/2022 12:25:40 - INFO - codeparrot_training - Step 19555: {'lr': 0.0004828423957442849, 'samples': 10012672, 'steps': 19555, 'loss/train': 2.184455633163452}
-03/04/2022 12:25:43 - INFO - codeparrot_training - Step 19556: {'lr': 0.00048284046363819213, 'samples': 10013184, 'steps': 19556, 'loss/train': 1.7571711540222168}
-03/04/2022 12:25:43 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/04/2022 12:25:49 - INFO - codeparrot_training - Step 19557: {'lr': 0.000482838531427185, 'samples': 10013696, 'steps': 19557, 'loss/train': 1.6274282932281494}
-03/04/2022 12:25:52 - INFO - codeparrot_training - Step 19558: {'lr': 0.00048283659911126445, 'samples': 10014208, 'steps': 19558, 'loss/train': 1.438607931137085}
-03/04/2022 12:25:52 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/04/2022 12:25:57 - INFO - codeparrot_training - Step 19559: {'lr': 0.0004828346666904313, 'samples': 10014720, 'steps': 19559, 'loss/train': 1.5621559619903564}
-03/04/2022 12:26:02 - INFO - codeparrot_training - Step 19560: {'lr': 0.00048283273416468644, 'samples': 10015232, 'steps': 19560, 'loss/train': 0.47866740822792053}
-03/04/2022 12:26:06 - INFO - codeparrot_training - Step 19561: {'lr': 0.0004828308015340307, 'samples': 10015744, 'steps': 19561, 'loss/train': 2.464336633682251}
-03/04/2022 12:26:08 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/04/2022 12:26:11 - INFO - codeparrot_training - Step 19562: {'lr': 0.0004828288687984651, 'samples': 10016256, 'steps': 19562, 'loss/train': 2.2050108909606934}
-03/04/2022 12:26:14 - INFO - codeparrot_training - Step 19563: {'lr': 0.0004828269359579903, 'samples': 10016768, 'steps': 19563, 'loss/train': 2.899597644805908}
-03/04/2022 12:26:17 - INFO - codeparrot_training - Step 19564: {'lr': 0.00048282500301260735, 'samples': 10017280, 'steps': 19564, 'loss/train': 1.4282641410827637}
-03/04/2022 12:26:17 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/04/2022 12:26:23 - INFO - codeparrot_training - Step 19565: {'lr': 0.000482823069962317, 'samples': 10017792, 'steps': 19565, 'loss/train': 1.9808768033981323}
-03/04/2022 12:26:26 - INFO - codeparrot_training - Step 19566: {'lr': 0.0004828211368071202, 'samples': 10018304, 'steps': 19566, 'loss/train': 1.8418406248092651}
-03/04/2022 12:26:26 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/04/2022 12:26:31 - INFO - codeparrot_training - Step 19567: {'lr': 0.0004828192035470178, 'samples': 10018816, 'steps': 19567, 'loss/train': 2.2723824977874756}
-03/04/2022 12:26:34 - INFO - codeparrot_training - Step 19568: {'lr': 0.00048281727018201063, 'samples': 10019328, 'steps': 19568, 'loss/train': 1.1990255117416382}
-03/04/2022 12:26:34 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/04/2022 12:26:40 - INFO - codeparrot_training - Step 19569: {'lr': 0.00048281533671209955, 'samples': 10019840, 'steps': 19569, 'loss/train': 0.9779643416404724}
-03/04/2022 12:26:43 - INFO - codeparrot_training - Step 19570: {'lr': 0.0004828134031372855, 'samples': 10020352, 'steps': 19570, 'loss/train': 2.1884806156158447}
-03/04/2022 12:26:44 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/04/2022 12:26:48 - INFO - codeparrot_training - Step 19571: {'lr': 0.00048281146945756937, 'samples': 10020864, 'steps': 19571, 'loss/train': 1.5977798700332642}
-03/04/2022 12:26:51 - INFO - codeparrot_training - Step 19572: {'lr': 0.00048280953567295196, 'samples': 10021376, 'steps': 19572, 'loss/train': 1.5649935007095337}
-03/04/2022 12:26:52 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/04/2022 12:26:57 - INFO - codeparrot_training - Step 19573: {'lr': 0.0004828076017834342, 'samples': 10021888, 'steps': 19573, 'loss/train': 1.7698712348937988}
-03/04/2022 12:27:00 - INFO - codeparrot_training - Step 19574: {'lr': 0.00048280566778901684, 'samples': 10022400, 'steps': 19574, 'loss/train': 1.3151737451553345}
-03/04/2022 12:27:01 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 12:27:05 - INFO - codeparrot_training - Step 19575: {'lr': 0.00048280373368970086, 'samples': 10022912, 'steps': 19575, 'loss/train': 2.602470874786377}
-03/04/2022 12:27:08 - INFO - codeparrot_training - Step 19576: {'lr': 0.0004828017994854872, 'samples': 10023424, 'steps': 19576, 'loss/train': 1.8715189695358276}
-03/04/2022 12:27:09 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/04/2022 12:27:14 - INFO - codeparrot_training - Step 19577: {'lr': 0.0004827998651763765, 'samples': 10023936, 'steps': 19577, 'loss/train': 1.833382248878479}
-03/04/2022 12:27:17 - INFO - codeparrot_training - Step 19578: {'lr': 0.0004827979307623699, 'samples': 10024448, 'steps': 19578, 'loss/train': 2.0861172676086426}
-03/04/2022 12:27:18 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 12:27:22 - INFO - codeparrot_training - Step 19579: {'lr': 0.0004827959962434681, 'samples': 10024960, 'steps': 19579, 'loss/train': 1.2611104249954224}
-03/04/2022 12:27:25 - INFO - codeparrot_training - Step 19580: {'lr': 0.00048279406161967197, 'samples': 10025472, 'steps': 19580, 'loss/train': 2.140249490737915}
-03/04/2022 12:27:26 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/04/2022 12:27:30 - INFO - codeparrot_training - Step 19581: {'lr': 0.0004827921268909825, 'samples': 10025984, 'steps': 19581, 'loss/train': 2.5501272678375244}
-03/04/2022 12:27:34 - INFO - codeparrot_training - Step 19582: {'lr': 0.0004827901920574005, 'samples': 10026496, 'steps': 19582, 'loss/train': 2.8026888370513916}
-03/04/2022 12:27:35 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/04/2022 12:27:39 - INFO - codeparrot_training - Step 19583: {'lr': 0.0004827882571189268, 'samples': 10027008, 'steps': 19583, 'loss/train': 1.7835613489151}
-03/04/2022 12:27:42 - INFO - codeparrot_training - Step 19584: {'lr': 0.00048278632207556226, 'samples': 10027520, 'steps': 19584, 'loss/train': 1.8873343467712402}
-03/04/2022 12:27:43 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/04/2022 12:27:47 - INFO - codeparrot_training - Step 19585: {'lr': 0.00048278438692730784, 'samples': 10028032, 'steps': 19585, 'loss/train': 1.5582023859024048}
-03/04/2022 12:27:50 - INFO - codeparrot_training - Step 19586: {'lr': 0.00048278245167416434, 'samples': 10028544, 'steps': 19586, 'loss/train': 2.1747469902038574}
-03/04/2022 12:27:56 - INFO - codeparrot_training - Step 19587: {'lr': 0.0004827805163161327, 'samples': 10029056, 'steps': 19587, 'loss/train': 1.4605070352554321}
-03/04/2022 12:27:59 - INFO - codeparrot_training - Step 19588: {'lr': 0.0004827785808532137, 'samples': 10029568, 'steps': 19588, 'loss/train': 2.5666894912719727}
-03/04/2022 12:28:00 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/04/2022 12:28:04 - INFO - codeparrot_training - Step 19589: {'lr': 0.0004827766452854083, 'samples': 10030080, 'steps': 19589, 'loss/train': 2.7876060009002686}
-03/04/2022 12:28:07 - INFO - codeparrot_training - Step 19590: {'lr': 0.0004827747096127173, 'samples': 10030592, 'steps': 19590, 'loss/train': 1.920558214187622}
-03/04/2022 12:28:08 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 12:28:13 - INFO - codeparrot_training - Step 19591: {'lr': 0.00048277277383514165, 'samples': 10031104, 'steps': 19591, 'loss/train': 2.2619717121124268}
-03/04/2022 12:28:16 - INFO - codeparrot_training - Step 19592: {'lr': 0.00048277083795268216, 'samples': 10031616, 'steps': 19592, 'loss/train': 1.9289435148239136}
-03/04/2022 12:28:17 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/04/2022 12:28:21 - INFO - codeparrot_training - Step 19593: {'lr': 0.0004827689019653397, 'samples': 10032128, 'steps': 19593, 'loss/train': 1.250562310218811}
-03/04/2022 12:28:24 - INFO - codeparrot_training - Step 19594: {'lr': 0.00048276696587311525, 'samples': 10032640, 'steps': 19594, 'loss/train': 1.7592219114303589}
-03/04/2022 12:28:25 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 12:28:29 - INFO - codeparrot_training - Step 19595: {'lr': 0.00048276502967600955, 'samples': 10033152, 'steps': 19595, 'loss/train': 3.874727249145508}
-03/04/2022 12:28:32 - INFO - codeparrot_training - Step 19596: {'lr': 0.00048276309337402345, 'samples': 10033664, 'steps': 19596, 'loss/train': 1.7101479768753052}
-03/04/2022 12:28:34 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 12:28:38 - INFO - codeparrot_training - Step 19597: {'lr': 0.000482761156967158, 'samples': 10034176, 'steps': 19597, 'loss/train': 1.588287591934204}
-03/04/2022 12:28:41 - INFO - codeparrot_training - Step 19598: {'lr': 0.0004827592204554139, 'samples': 10034688, 'steps': 19598, 'loss/train': 2.2950551509857178}
-03/04/2022 12:28:42 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/04/2022 12:28:46 - INFO - codeparrot_training - Step 19599: {'lr': 0.00048275728383879215, 'samples': 10035200, 'steps': 19599, 'loss/train': 1.7765518426895142}
-03/04/2022 12:28:49 - INFO - codeparrot_training - Step 19600: {'lr': 0.0004827553471172935, 'samples': 10035712, 'steps': 19600, 'loss/train': 2.505875587463379}
-03/04/2022 12:28:50 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/04/2022 12:28:55 - INFO - codeparrot_training - Step 19601: {'lr': 0.00048275341029091885, 'samples': 10036224, 'steps': 19601, 'loss/train': 2.125891923904419}
-03/04/2022 12:28:58 - INFO - codeparrot_training - Step 19602: {'lr': 0.0004827514733596692, 'samples': 10036736, 'steps': 19602, 'loss/train': 1.9785504341125488}
-03/04/2022 12:28:58 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/04/2022 12:29:03 - INFO - codeparrot_training - Step 19603: {'lr': 0.00048274953632354524, 'samples': 10037248, 'steps': 19603, 'loss/train': 2.523259401321411}
-03/04/2022 12:29:06 - INFO - codeparrot_training - Step 19604: {'lr': 0.000482747599182548, 'samples': 10037760, 'steps': 19604, 'loss/train': 1.796750783920288}
-03/04/2022 12:29:07 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 12:29:11 - INFO - codeparrot_training - Step 19605: {'lr': 0.00048274566193667824, 'samples': 10038272, 'steps': 19605, 'loss/train': 2.0548095703125}
-03/04/2022 12:29:15 - INFO - codeparrot_training - Step 19606: {'lr': 0.0004827437245859369, 'samples': 10038784, 'steps': 19606, 'loss/train': 2.111943244934082}
-03/04/2022 12:29:15 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/04/2022 12:29:20 - INFO - codeparrot_training - Step 19607: {'lr': 0.0004827417871303248, 'samples': 10039296, 'steps': 19607, 'loss/train': 2.286667585372925}
-03/04/2022 12:29:23 - INFO - codeparrot_training - Step 19608: {'lr': 0.00048273984956984285, 'samples': 10039808, 'steps': 19608, 'loss/train': 1.4727572202682495}
-03/04/2022 12:29:24 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/04/2022 12:29:28 - INFO - codeparrot_training - Step 19609: {'lr': 0.0004827379119044919, 'samples': 10040320, 'steps': 19609, 'loss/train': 1.7012600898742676}
-03/04/2022 12:29:32 - INFO - codeparrot_training - Step 19610: {'lr': 0.00048273597413427284, 'samples': 10040832, 'steps': 19610, 'loss/train': 1.28578519821167}
-03/04/2022 12:29:33 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/04/2022 12:29:37 - INFO - codeparrot_training - Step 19611: {'lr': 0.00048273403625918653, 'samples': 10041344, 'steps': 19611, 'loss/train': 1.6905452013015747}
-03/04/2022 12:29:40 - INFO - codeparrot_training - Step 19612: {'lr': 0.0004827320982792339, 'samples': 10041856, 'steps': 19612, 'loss/train': 2.045376777648926}
-03/04/2022 12:29:41 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/04/2022 12:29:45 - INFO - codeparrot_training - Step 19613: {'lr': 0.00048273016019441585, 'samples': 10042368, 'steps': 19613, 'loss/train': 1.9756158590316772}
-03/04/2022 12:29:48 - INFO - codeparrot_training - Step 19614: {'lr': 0.00048272822200473304, 'samples': 10042880, 'steps': 19614, 'loss/train': 0.9551622867584229}
-03/04/2022 12:29:50 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/04/2022 12:29:54 - INFO - codeparrot_training - Step 19615: {'lr': 0.0004827262837101866, 'samples': 10043392, 'steps': 19615, 'loss/train': 1.9031625986099243}
-03/04/2022 12:29:57 - INFO - codeparrot_training - Step 19616: {'lr': 0.0004827243453107772, 'samples': 10043904, 'steps': 19616, 'loss/train': 2.0338525772094727}
-03/04/2022 12:29:58 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/04/2022 12:30:02 - INFO - codeparrot_training - Step 19617: {'lr': 0.0004827224068065058, 'samples': 10044416, 'steps': 19617, 'loss/train': 2.066007375717163}
-03/04/2022 12:30:05 - INFO - codeparrot_training - Step 19618: {'lr': 0.0004827204681973733, 'samples': 10044928, 'steps': 19618, 'loss/train': 2.1195881366729736}
-03/04/2022 12:30:06 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/04/2022 12:30:11 - INFO - codeparrot_training - Step 19619: {'lr': 0.00048271852948338057, 'samples': 10045440, 'steps': 19619, 'loss/train': 1.7249844074249268}
-03/04/2022 12:30:14 - INFO - codeparrot_training - Step 19620: {'lr': 0.00048271659066452847, 'samples': 10045952, 'steps': 19620, 'loss/train': 1.456711769104004}
-03/04/2022 12:30:15 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/04/2022 12:30:19 - INFO - codeparrot_training - Step 19621: {'lr': 0.0004827146517408178, 'samples': 10046464, 'steps': 19621, 'loss/train': 1.2809100151062012}
-03/04/2022 12:30:22 - INFO - codeparrot_training - Step 19622: {'lr': 0.0004827127127122495, 'samples': 10046976, 'steps': 19622, 'loss/train': 2.207751750946045}
-03/04/2022 12:30:23 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/04/2022 12:30:28 - INFO - codeparrot_training - Step 19623: {'lr': 0.00048271077357882455, 'samples': 10047488, 'steps': 19623, 'loss/train': 2.057893753051758}
-03/04/2022 12:30:31 - INFO - codeparrot_training - Step 19624: {'lr': 0.00048270883434054364, 'samples': 10048000, 'steps': 19624, 'loss/train': 2.098374605178833}
-03/04/2022 12:30:32 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/04/2022 12:30:36 - INFO - codeparrot_training - Step 19625: {'lr': 0.00048270689499740774, 'samples': 10048512, 'steps': 19625, 'loss/train': 2.298408269882202}
-03/04/2022 12:30:39 - INFO - codeparrot_training - Step 19626: {'lr': 0.0004827049555494176, 'samples': 10049024, 'steps': 19626, 'loss/train': 2.519592761993408}
-03/04/2022 12:30:40 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/04/2022 12:30:45 - INFO - codeparrot_training - Step 19627: {'lr': 0.00048270301599657436, 'samples': 10049536, 'steps': 19627, 'loss/train': 1.2468628883361816}
-03/04/2022 12:30:48 - INFO - codeparrot_training - Step 19628: {'lr': 0.0004827010763388786, 'samples': 10050048, 'steps': 19628, 'loss/train': 1.2400918006896973}
-03/04/2022 12:30:49 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/04/2022 12:30:53 - INFO - codeparrot_training - Step 19629: {'lr': 0.00048269913657633147, 'samples': 10050560, 'steps': 19629, 'loss/train': 0.7863187789916992}
-03/04/2022 12:30:56 - INFO - codeparrot_training - Step 19630: {'lr': 0.00048269719670893357, 'samples': 10051072, 'steps': 19630, 'loss/train': 2.37595272064209}
-03/04/2022 12:30:58 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 12:31:01 - INFO - codeparrot_training - Step 19631: {'lr': 0.00048269525673668595, 'samples': 10051584, 'steps': 19631, 'loss/train': 1.8215774297714233}
-03/04/2022 12:31:05 - INFO - codeparrot_training - Step 19632: {'lr': 0.00048269331665958947, 'samples': 10052096, 'steps': 19632, 'loss/train': 1.652806043624878}
-03/04/2022 12:31:06 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/04/2022 12:31:10 - INFO - codeparrot_training - Step 19633: {'lr': 0.00048269137647764495, 'samples': 10052608, 'steps': 19633, 'loss/train': 1.957367181777954}
-03/04/2022 12:31:13 - INFO - codeparrot_training - Step 19634: {'lr': 0.00048268943619085325, 'samples': 10053120, 'steps': 19634, 'loss/train': 2.0553481578826904}
-03/04/2022 12:31:15 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/04/2022 12:31:19 - INFO - codeparrot_training - Step 19635: {'lr': 0.00048268749579921536, 'samples': 10053632, 'steps': 19635, 'loss/train': 1.7191535234451294}
-03/04/2022 12:31:22 - INFO - codeparrot_training - Step 19636: {'lr': 0.00048268555530273197, 'samples': 10054144, 'steps': 19636, 'loss/train': 2.286865234375}
-03/04/2022 12:31:23 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 12:31:27 - INFO - codeparrot_training - Step 19637: {'lr': 0.0004826836147014041, 'samples': 10054656, 'steps': 19637, 'loss/train': 3.7865476608276367}
-03/04/2022 12:31:30 - INFO - codeparrot_training - Step 19638: {'lr': 0.0004826816739952326, 'samples': 10055168, 'steps': 19638, 'loss/train': 0.860769510269165}
-03/04/2022 12:31:32 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/04/2022 12:31:35 - INFO - codeparrot_training - Step 19639: {'lr': 0.0004826797331842183, 'samples': 10055680, 'steps': 19639, 'loss/train': 1.4444221258163452}
-03/04/2022 12:31:39 - INFO - codeparrot_training - Step 19640: {'lr': 0.0004826777922683622, 'samples': 10056192, 'steps': 19640, 'loss/train': 1.126543641090393}
-03/04/2022 12:31:41 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/04/2022 12:31:44 - INFO - codeparrot_training - Step 19641: {'lr': 0.0004826758512476649, 'samples': 10056704, 'steps': 19641, 'loss/train': 1.6133081912994385}
-03/04/2022 12:31:47 - INFO - codeparrot_training - Step 19642: {'lr': 0.0004826739101221276, 'samples': 10057216, 'steps': 19642, 'loss/train': 1.738745927810669}
-03/04/2022 12:31:49 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/04/2022 12:31:53 - INFO - codeparrot_training - Step 19643: {'lr': 0.000482671968891751, 'samples': 10057728, 'steps': 19643, 'loss/train': 2.2655255794525146}
-03/04/2022 12:31:56 - INFO - codeparrot_training - Step 19644: {'lr': 0.000482670027556536, 'samples': 10058240, 'steps': 19644, 'loss/train': 1.685506820678711}
-03/04/2022 12:31:58 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/04/2022 12:32:01 - INFO - codeparrot_training - Step 19645: {'lr': 0.0004826680861164834, 'samples': 10058752, 'steps': 19645, 'loss/train': 1.8673630952835083}
-03/04/2022 12:32:04 - INFO - codeparrot_training - Step 19646: {'lr': 0.00048266614457159426, 'samples': 10059264, 'steps': 19646, 'loss/train': 2.01196026802063}
-03/04/2022 12:32:06 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/04/2022 12:32:09 - INFO - codeparrot_training - Step 19647: {'lr': 0.0004826642029218693, 'samples': 10059776, 'steps': 19647, 'loss/train': 2.2941343784332275}
-03/04/2022 12:32:13 - INFO - codeparrot_training - Step 19648: {'lr': 0.00048266226116730937, 'samples': 10060288, 'steps': 19648, 'loss/train': 1.9964947700500488}
-03/04/2022 12:32:15 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/04/2022 12:32:18 - INFO - codeparrot_training - Step 19649: {'lr': 0.00048266031930791555, 'samples': 10060800, 'steps': 19649, 'loss/train': 1.5013586282730103}
-03/04/2022 12:32:21 - INFO - codeparrot_training - Step 19650: {'lr': 0.0004826583773436884, 'samples': 10061312, 'steps': 19650, 'loss/train': 1.6277484893798828}
-03/04/2022 12:32:23 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/04/2022 12:32:26 - INFO - codeparrot_training - Step 19651: {'lr': 0.00048265643527462915, 'samples': 10061824, 'steps': 19651, 'loss/train': 1.5069152116775513}
-03/04/2022 12:32:30 - INFO - codeparrot_training - Step 19652: {'lr': 0.00048265449310073847, 'samples': 10062336, 'steps': 19652, 'loss/train': 1.9873210191726685}
-03/04/2022 12:32:32 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 12:32:35 - INFO - codeparrot_training - Step 19653: {'lr': 0.0004826525508220172, 'samples': 10062848, 'steps': 19653, 'loss/train': 1.6652189493179321}
-03/04/2022 12:32:38 - INFO - codeparrot_training - Step 19654: {'lr': 0.0004826506084384663, 'samples': 10063360, 'steps': 19654, 'loss/train': 1.3454701900482178}
-03/04/2022 12:32:40 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/04/2022 12:32:43 - INFO - codeparrot_training - Step 19655: {'lr': 0.00048264866595008665, 'samples': 10063872, 'steps': 19655, 'loss/train': 2.0290963649749756}
-03/04/2022 12:32:46 - INFO - codeparrot_training - Step 19656: {'lr': 0.0004826467233568791, 'samples': 10064384, 'steps': 19656, 'loss/train': 2.2111222743988037}
-03/04/2022 12:32:48 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/04/2022 12:32:52 - INFO - codeparrot_training - Step 19657: {'lr': 0.00048264478065884454, 'samples': 10064896, 'steps': 19657, 'loss/train': 1.249247431755066}
-03/04/2022 12:32:55 - INFO - codeparrot_training - Step 19658: {'lr': 0.0004826428378559838, 'samples': 10065408, 'steps': 19658, 'loss/train': 1.8117727041244507}
-03/04/2022 12:32:57 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/04/2022 12:33:00 - INFO - codeparrot_training - Step 19659: {'lr': 0.00048264089494829776, 'samples': 10065920, 'steps': 19659, 'loss/train': 2.988041877746582}
-03/04/2022 12:33:03 - INFO - codeparrot_training - Step 19660: {'lr': 0.0004826389519357874, 'samples': 10066432, 'steps': 19660, 'loss/train': 2.1863536834716797}
-03/04/2022 12:33:06 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/04/2022 12:33:09 - INFO - codeparrot_training - Step 19661: {'lr': 0.00048263700881845346, 'samples': 10066944, 'steps': 19661, 'loss/train': 1.9041731357574463}
-03/04/2022 12:33:12 - INFO - codeparrot_training - Step 19662: {'lr': 0.00048263506559629687, 'samples': 10067456, 'steps': 19662, 'loss/train': 1.8874706029891968}
-03/04/2022 12:33:14 - INFO - codeparrot_training - Skipping example with length 7 (seq_length=1024)
-03/04/2022 12:33:17 - INFO - codeparrot_training - Step 19663: {'lr': 0.00048263312226931853, 'samples': 10067968, 'steps': 19663, 'loss/train': 1.748679757118225}
-03/04/2022 12:33:20 - INFO - codeparrot_training - Step 19664: {'lr': 0.0004826311788375193, 'samples': 10068480, 'steps': 19664, 'loss/train': 1.4524743556976318}
-03/04/2022 12:33:22 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/04/2022 12:33:26 - INFO - codeparrot_training - Step 19665: {'lr': 0.00048262923530090007, 'samples': 10068992, 'steps': 19665, 'loss/train': 1.778059482574463}
-03/04/2022 12:33:29 - INFO - codeparrot_training - Step 19666: {'lr': 0.0004826272916594616, 'samples': 10069504, 'steps': 19666, 'loss/train': 1.4261882305145264}
-03/04/2022 12:33:31 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/04/2022 12:33:34 - INFO - codeparrot_training - Step 19667: {'lr': 0.000482625347913205, 'samples': 10070016, 'steps': 19667, 'loss/train': 2.420652151107788}
-03/04/2022 12:33:37 - INFO - codeparrot_training - Step 19668: {'lr': 0.0004826234040621309, 'samples': 10070528, 'steps': 19668, 'loss/train': 1.6412914991378784}
-03/04/2022 12:33:39 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/04/2022 12:33:42 - INFO - codeparrot_training - Step 19669: {'lr': 0.00048262146010624035, 'samples': 10071040, 'steps': 19669, 'loss/train': 1.15757155418396}
-03/04/2022 12:33:46 - INFO - codeparrot_training - Step 19670: {'lr': 0.0004826195160455341, 'samples': 10071552, 'steps': 19670, 'loss/train': 0.6988943815231323}
-03/04/2022 12:33:48 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/04/2022 12:33:51 - INFO - codeparrot_training - Step 19671: {'lr': 0.00048261757188001314, 'samples': 10072064, 'steps': 19671, 'loss/train': 2.032111883163452}
-03/04/2022 12:33:54 - INFO - codeparrot_training - Step 19672: {'lr': 0.00048261562760967824, 'samples': 10072576, 'steps': 19672, 'loss/train': 1.2864502668380737}
-03/04/2022 12:33:56 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 12:33:59 - INFO - codeparrot_training - Step 19673: {'lr': 0.0004826136832345304, 'samples': 10073088, 'steps': 19673, 'loss/train': 1.955210566520691}
-03/04/2022 12:34:02 - INFO - codeparrot_training - Step 19674: {'lr': 0.00048261173875457035, 'samples': 10073600, 'steps': 19674, 'loss/train': 2.087470769882202}
-03/04/2022 12:34:04 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 12:34:08 - INFO - codeparrot_training - Step 19675: {'lr': 0.0004826097941697991, 'samples': 10074112, 'steps': 19675, 'loss/train': 2.261869192123413}
-03/04/2022 12:34:11 - INFO - codeparrot_training - Step 19676: {'lr': 0.0004826078494802174, 'samples': 10074624, 'steps': 19676, 'loss/train': 2.022291421890259}
-03/04/2022 12:34:13 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/04/2022 12:34:16 - INFO - codeparrot_training - Step 19677: {'lr': 0.00048260590468582624, 'samples': 10075136, 'steps': 19677, 'loss/train': 2.183664083480835}
-03/04/2022 12:34:19 - INFO - codeparrot_training - Step 19678: {'lr': 0.0004826039597866265, 'samples': 10075648, 'steps': 19678, 'loss/train': 0.8393725156784058}
-03/04/2022 12:34:21 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 12:34:24 - INFO - codeparrot_training - Step 19679: {'lr': 0.00048260201478261887, 'samples': 10076160, 'steps': 19679, 'loss/train': 2.456508159637451}
-03/04/2022 12:34:28 - INFO - codeparrot_training - Step 19680: {'lr': 0.0004826000696738045, 'samples': 10076672, 'steps': 19680, 'loss/train': 1.8994140625}
-03/04/2022 12:34:29 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/04/2022 12:34:33 - INFO - codeparrot_training - Step 19681: {'lr': 0.000482598124460184, 'samples': 10077184, 'steps': 19681, 'loss/train': 2.5178744792938232}
-03/04/2022 12:34:36 - INFO - codeparrot_training - Step 19682: {'lr': 0.00048259617914175846, 'samples': 10077696, 'steps': 19682, 'loss/train': 1.3134336471557617}
-03/04/2022 12:34:38 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/04/2022 12:34:41 - INFO - codeparrot_training - Step 19683: {'lr': 0.00048259423371852867, 'samples': 10078208, 'steps': 19683, 'loss/train': 1.6205726861953735}
-03/04/2022 12:34:45 - INFO - codeparrot_training - Step 19684: {'lr': 0.0004825922881904955, 'samples': 10078720, 'steps': 19684, 'loss/train': 1.6164289712905884}
-03/04/2022 12:34:46 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 12:34:50 - INFO - codeparrot_training - Step 19685: {'lr': 0.00048259034255765984, 'samples': 10079232, 'steps': 19685, 'loss/train': 2.225207805633545}
-03/04/2022 12:34:53 - INFO - codeparrot_training - Step 19686: {'lr': 0.00048258839682002253, 'samples': 10079744, 'steps': 19686, 'loss/train': 0.9545813798904419}
-03/04/2022 12:34:55 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 12:34:58 - INFO - codeparrot_training - Step 19687: {'lr': 0.00048258645097758445, 'samples': 10080256, 'steps': 19687, 'loss/train': 1.949307918548584}
-03/04/2022 12:35:01 - INFO - codeparrot_training - Step 19688: {'lr': 0.0004825845050303466, 'samples': 10080768, 'steps': 19688, 'loss/train': 1.3289258480072021}
-03/04/2022 12:35:03 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/04/2022 12:35:07 - INFO - codeparrot_training - Step 19689: {'lr': 0.00048258255897830967, 'samples': 10081280, 'steps': 19689, 'loss/train': 1.8775722980499268}
-03/04/2022 12:35:10 - INFO - codeparrot_training - Step 19690: {'lr': 0.0004825806128214747, 'samples': 10081792, 'steps': 19690, 'loss/train': 1.3639203310012817}
-03/04/2022 12:35:12 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 12:35:15 - INFO - codeparrot_training - Step 19691: {'lr': 0.00048257866655984237, 'samples': 10082304, 'steps': 19691, 'loss/train': 1.2828947305679321}
-03/04/2022 12:35:18 - INFO - codeparrot_training - Step 19692: {'lr': 0.0004825767201934138, 'samples': 10082816, 'steps': 19692, 'loss/train': 1.3774327039718628}
-03/04/2022 12:35:20 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/04/2022 12:35:24 - INFO - codeparrot_training - Step 19693: {'lr': 0.0004825747737221897, 'samples': 10083328, 'steps': 19693, 'loss/train': 2.1454508304595947}
-03/04/2022 12:35:27 - INFO - codeparrot_training - Step 19694: {'lr': 0.000482572827146171, 'samples': 10083840, 'steps': 19694, 'loss/train': 1.3843377828598022}
-03/04/2022 12:35:29 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 12:35:32 - INFO - codeparrot_training - Step 19695: {'lr': 0.00048257088046535864, 'samples': 10084352, 'steps': 19695, 'loss/train': 1.3183873891830444}
-03/04/2022 12:35:36 - INFO - codeparrot_training - Step 19696: {'lr': 0.0004825689336797534, 'samples': 10084864, 'steps': 19696, 'loss/train': 5.601188659667969}
-03/04/2022 12:35:38 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/04/2022 12:35:41 - INFO - codeparrot_training - Step 19697: {'lr': 0.00048256698678935615, 'samples': 10085376, 'steps': 19697, 'loss/train': 1.476180076599121}
-03/04/2022 12:35:44 - INFO - codeparrot_training - Step 19698: {'lr': 0.00048256503979416776, 'samples': 10085888, 'steps': 19698, 'loss/train': 2.46618914604187}
-03/04/2022 12:35:47 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/04/2022 12:35:49 - INFO - codeparrot_training - Step 19699: {'lr': 0.0004825630926941892, 'samples': 10086400, 'steps': 19699, 'loss/train': 2.1515254974365234}
-03/04/2022 12:35:52 - INFO - codeparrot_training - Step 19700: {'lr': 0.0004825611454894213, 'samples': 10086912, 'steps': 19700, 'loss/train': 2.8739025592803955}
-03/04/2022 12:35:56 - INFO - codeparrot_training - Step 19701: {'lr': 0.000482559198179865, 'samples': 10087424, 'steps': 19701, 'loss/train': 1.6649550199508667}
-03/04/2022 12:35:56 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/04/2022 12:36:01 - INFO - codeparrot_training - Step 19702: {'lr': 0.00048255725076552103, 'samples': 10087936, 'steps': 19702, 'loss/train': 1.1353758573532104}
-03/04/2022 12:36:04 - INFO - codeparrot_training - Step 19703: {'lr': 0.0004825553032463904, 'samples': 10088448, 'steps': 19703, 'loss/train': 1.9337323904037476}
-03/04/2022 12:36:04 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 12:36:10 - INFO - codeparrot_training - Step 19704: {'lr': 0.00048255335562247395, 'samples': 10088960, 'steps': 19704, 'loss/train': 1.4765249490737915}
-03/04/2022 12:36:13 - INFO - codeparrot_training - Step 19705: {'lr': 0.0004825514078937725, 'samples': 10089472, 'steps': 19705, 'loss/train': 2.290787935256958}
-03/04/2022 12:36:13 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/04/2022 12:36:18 - INFO - codeparrot_training - Step 19706: {'lr': 0.000482549460060287, 'samples': 10089984, 'steps': 19706, 'loss/train': 1.4927024841308594}
-03/04/2022 12:36:21 - INFO - codeparrot_training - Step 19707: {'lr': 0.0004825475121220183, 'samples': 10090496, 'steps': 19707, 'loss/train': 0.7977847456932068}
-03/04/2022 12:36:21 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/04/2022 12:36:27 - INFO - codeparrot_training - Step 19708: {'lr': 0.0004825455640789672, 'samples': 10091008, 'steps': 19708, 'loss/train': 2.2151689529418945}
-03/04/2022 12:36:30 - INFO - codeparrot_training - Step 19709: {'lr': 0.00048254361593113475, 'samples': 10091520, 'steps': 19709, 'loss/train': 1.4912447929382324}
-03/04/2022 12:36:30 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 12:36:35 - INFO - codeparrot_training - Step 19710: {'lr': 0.0004825416676785217, 'samples': 10092032, 'steps': 19710, 'loss/train': 1.931646466255188}
-03/04/2022 12:36:38 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/04/2022 12:36:40 - INFO - codeparrot_training - Step 19711: {'lr': 0.000482539719321129, 'samples': 10092544, 'steps': 19711, 'loss/train': 1.190773367881775}
-03/04/2022 12:36:43 - INFO - codeparrot_training - Step 19712: {'lr': 0.00048253777085895745, 'samples': 10093056, 'steps': 19712, 'loss/train': 1.0326586961746216}
-03/04/2022 12:36:46 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/04/2022 12:36:49 - INFO - codeparrot_training - Step 19713: {'lr': 0.000482535822292008, 'samples': 10093568, 'steps': 19713, 'loss/train': 1.6159954071044922}
-03/04/2022 12:36:52 - INFO - codeparrot_training - Step 19714: {'lr': 0.0004825338736202815, 'samples': 10094080, 'steps': 19714, 'loss/train': 2.495863676071167}
-03/04/2022 12:36:55 - INFO - codeparrot_training - Step 19715: {'lr': 0.00048253192484377884, 'samples': 10094592, 'steps': 19715, 'loss/train': 1.8896089792251587}
-03/04/2022 12:36:55 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/04/2022 12:37:00 - INFO - codeparrot_training - Step 19716: {'lr': 0.0004825299759625008, 'samples': 10095104, 'steps': 19716, 'loss/train': 1.5112648010253906}
-03/04/2022 12:37:04 - INFO - codeparrot_training - Step 19717: {'lr': 0.0004825280269764484, 'samples': 10095616, 'steps': 19717, 'loss/train': 2.1475510597229004}
-03/04/2022 12:37:04 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 12:37:09 - INFO - codeparrot_training - Step 19718: {'lr': 0.0004825260778856224, 'samples': 10096128, 'steps': 19718, 'loss/train': 2.2658729553222656}
-03/04/2022 12:37:12 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/04/2022 12:37:14 - INFO - codeparrot_training - Step 19719: {'lr': 0.0004825241286900238, 'samples': 10096640, 'steps': 19719, 'loss/train': 2.0432329177856445}
-03/04/2022 12:37:17 - INFO - codeparrot_training - Step 19720: {'lr': 0.0004825221793896535, 'samples': 10097152, 'steps': 19720, 'loss/train': 1.6331830024719238}
-03/04/2022 12:37:21 - INFO - codeparrot_training - Step 19721: {'lr': 0.0004825202299845122, 'samples': 10097664, 'steps': 19721, 'loss/train': 2.598694324493408}
-03/04/2022 12:37:21 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/04/2022 12:37:26 - INFO - codeparrot_training - Step 19722: {'lr': 0.00048251828047460077, 'samples': 10098176, 'steps': 19722, 'loss/train': 1.9113349914550781}
-03/04/2022 12:37:29 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 12:37:31 - INFO - codeparrot_training - Step 19723: {'lr': 0.0004825163308599203, 'samples': 10098688, 'steps': 19723, 'loss/train': 1.3988053798675537}
-03/04/2022 12:37:34 - INFO - codeparrot_training - Step 19724: {'lr': 0.0004825143811404716, 'samples': 10099200, 'steps': 19724, 'loss/train': 1.6237815618515015}
-03/04/2022 12:37:37 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/04/2022 12:37:40 - INFO - codeparrot_training - Step 19725: {'lr': 0.00048251243131625543, 'samples': 10099712, 'steps': 19725, 'loss/train': 2.0333735942840576}
-03/04/2022 12:37:43 - INFO - codeparrot_training - Step 19726: {'lr': 0.0004825104813872728, 'samples': 10100224, 'steps': 19726, 'loss/train': 2.4387876987457275}
-03/04/2022 12:37:46 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 12:37:48 - INFO - codeparrot_training - Step 19727: {'lr': 0.0004825085313535245, 'samples': 10100736, 'steps': 19727, 'loss/train': 2.0156004428863525}
-03/04/2022 12:37:51 - INFO - codeparrot_training - Step 19728: {'lr': 0.00048250658121501145, 'samples': 10101248, 'steps': 19728, 'loss/train': 1.7837638854980469}
-03/04/2022 12:37:55 - INFO - codeparrot_training - Step 19729: {'lr': 0.00048250463097173447, 'samples': 10101760, 'steps': 19729, 'loss/train': 1.5581458806991577}
-03/04/2022 12:37:55 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/04/2022 12:38:00 - INFO - codeparrot_training - Step 19730: {'lr': 0.0004825026806236946, 'samples': 10102272, 'steps': 19730, 'loss/train': 2.0141704082489014}
-03/04/2022 12:38:03 - INFO - codeparrot_training - Step 19731: {'lr': 0.00048250073017089257, 'samples': 10102784, 'steps': 19731, 'loss/train': 0.9369689226150513}
-03/04/2022 12:38:04 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/04/2022 12:38:08 - INFO - codeparrot_training - Step 19732: {'lr': 0.00048249877961332923, 'samples': 10103296, 'steps': 19732, 'loss/train': 2.0229740142822266}
-03/04/2022 12:38:12 - INFO - codeparrot_training - Step 19733: {'lr': 0.0004824968289510056, 'samples': 10103808, 'steps': 19733, 'loss/train': 2.5996181964874268}
-03/04/2022 12:38:13 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/04/2022 12:38:17 - INFO - codeparrot_training - Step 19734: {'lr': 0.0004824948781839225, 'samples': 10104320, 'steps': 19734, 'loss/train': 1.764369010925293}
-03/04/2022 12:38:20 - INFO - codeparrot_training - Step 19735: {'lr': 0.0004824929273120807, 'samples': 10104832, 'steps': 19735, 'loss/train': 2.1641292572021484}
-03/04/2022 12:38:21 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 12:38:25 - INFO - codeparrot_training - Step 19736: {'lr': 0.0004824909763354813, 'samples': 10105344, 'steps': 19736, 'loss/train': 1.8608489036560059}
-03/04/2022 12:38:28 - INFO - codeparrot_training - Step 19737: {'lr': 0.00048248902525412497, 'samples': 10105856, 'steps': 19737, 'loss/train': 2.047818183898926}
-03/04/2022 12:38:30 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/04/2022 12:38:34 - INFO - codeparrot_training - Step 19738: {'lr': 0.0004824870740680127, 'samples': 10106368, 'steps': 19738, 'loss/train': 2.260714054107666}
-03/04/2022 12:38:37 - INFO - codeparrot_training - Step 19739: {'lr': 0.0004824851227771453, 'samples': 10106880, 'steps': 19739, 'loss/train': 2.3353888988494873}
-03/04/2022 12:38:42 - INFO - codeparrot_training - Step 19740: {'lr': 0.00048248317138152374, 'samples': 10107392, 'steps': 19740, 'loss/train': 1.7353488206863403}
-03/04/2022 12:38:45 - INFO - codeparrot_training - Step 19741: {'lr': 0.00048248121988114887, 'samples': 10107904, 'steps': 19741, 'loss/train': 2.275988817214966}
-03/04/2022 12:38:46 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/04/2022 12:38:50 - INFO - codeparrot_training - Step 19742: {'lr': 0.00048247926827602153, 'samples': 10108416, 'steps': 19742, 'loss/train': 1.7174770832061768}
-03/04/2022 12:38:54 - INFO - codeparrot_training - Step 19743: {'lr': 0.0004824773165661426, 'samples': 10108928, 'steps': 19743, 'loss/train': 2.736206531524658}
-03/04/2022 12:38:54 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 12:38:59 - INFO - codeparrot_training - Step 19744: {'lr': 0.000482475364751513, 'samples': 10109440, 'steps': 19744, 'loss/train': 2.2439889907836914}
-03/04/2022 12:39:02 - INFO - codeparrot_training - Step 19745: {'lr': 0.0004824734128321335, 'samples': 10109952, 'steps': 19745, 'loss/train': 1.8169364929199219}
-03/04/2022 12:39:03 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 12:39:07 - INFO - codeparrot_training - Step 19746: {'lr': 0.0004824714608080052, 'samples': 10110464, 'steps': 19746, 'loss/train': 1.9187331199645996}
-03/04/2022 12:39:10 - INFO - codeparrot_training - Step 19747: {'lr': 0.00048246950867912873, 'samples': 10110976, 'steps': 19747, 'loss/train': 2.1378655433654785}
-03/04/2022 12:39:11 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/04/2022 12:39:16 - INFO - codeparrot_training - Step 19748: {'lr': 0.0004824675564455052, 'samples': 10111488, 'steps': 19748, 'loss/train': 2.3286235332489014}
-03/04/2022 12:39:19 - INFO - codeparrot_training - Step 19749: {'lr': 0.0004824656041071353, 'samples': 10112000, 'steps': 19749, 'loss/train': 1.7786535024642944}
-03/04/2022 12:39:19 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/04/2022 12:39:24 - INFO - codeparrot_training - Step 19750: {'lr': 0.00048246365166402003, 'samples': 10112512, 'steps': 19750, 'loss/train': 2.05889892578125}
-03/04/2022 12:39:27 - INFO - codeparrot_training - Step 19751: {'lr': 0.00048246169911616015, 'samples': 10113024, 'steps': 19751, 'loss/train': 2.0969083309173584}
-03/04/2022 12:39:28 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 12:39:33 - INFO - codeparrot_training - Step 19752: {'lr': 0.00048245974646355673, 'samples': 10113536, 'steps': 19752, 'loss/train': 2.4036197662353516}
-03/04/2022 12:39:36 - INFO - codeparrot_training - Step 19753: {'lr': 0.00048245779370621045, 'samples': 10114048, 'steps': 19753, 'loss/train': 1.8346132040023804}
-03/04/2022 12:39:36 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/04/2022 12:39:41 - INFO - codeparrot_training - Step 19754: {'lr': 0.0004824558408441223, 'samples': 10114560, 'steps': 19754, 'loss/train': 1.2586987018585205}
-03/04/2022 12:39:44 - INFO - codeparrot_training - Step 19755: {'lr': 0.00048245388787729316, 'samples': 10115072, 'steps': 19755, 'loss/train': 2.221259117126465}
-03/04/2022 12:39:44 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/04/2022 12:39:50 - INFO - codeparrot_training - Step 19756: {'lr': 0.00048245193480572383, 'samples': 10115584, 'steps': 19756, 'loss/train': 1.2530372142791748}
-03/04/2022 12:39:53 - INFO - codeparrot_training - Step 19757: {'lr': 0.0004824499816294152, 'samples': 10116096, 'steps': 19757, 'loss/train': 1.8443191051483154}
-03/04/2022 12:39:53 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 12:39:59 - INFO - codeparrot_training - Step 19758: {'lr': 0.0004824480283483683, 'samples': 10116608, 'steps': 19758, 'loss/train': 0.9319930076599121}
-03/04/2022 12:40:02 - INFO - codeparrot_training - Step 19759: {'lr': 0.0004824460749625839, 'samples': 10117120, 'steps': 19759, 'loss/train': 3.4166860580444336}
-03/04/2022 12:40:05 - INFO - codeparrot_training - Step 19760: {'lr': 0.00048244412147206283, 'samples': 10117632, 'steps': 19760, 'loss/train': 3.465986728668213}
-03/04/2022 12:40:05 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 12:40:11 - INFO - codeparrot_training - Step 19761: {'lr': 0.00048244216787680607, 'samples': 10118144, 'steps': 19761, 'loss/train': 2.099868059158325}
-03/04/2022 12:40:14 - INFO - codeparrot_training - Step 19762: {'lr': 0.0004824402141768145, 'samples': 10118656, 'steps': 19762, 'loss/train': 1.2014586925506592}
-03/04/2022 12:40:14 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/04/2022 12:40:19 - INFO - codeparrot_training - Step 19763: {'lr': 0.0004824382603720888, 'samples': 10119168, 'steps': 19763, 'loss/train': 2.4093170166015625}
-03/04/2022 12:40:22 - INFO - codeparrot_training - Step 19764: {'lr': 0.00048243630646263016, 'samples': 10119680, 'steps': 19764, 'loss/train': 1.0819671154022217}
-03/04/2022 12:40:22 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 12:40:28 - INFO - codeparrot_training - Step 19765: {'lr': 0.00048243435244843926, 'samples': 10120192, 'steps': 19765, 'loss/train': 1.0348646640777588}
-03/04/2022 12:40:30 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 12:40:33 - INFO - codeparrot_training - Step 19766: {'lr': 0.000482432398329517, 'samples': 10120704, 'steps': 19766, 'loss/train': 1.5714190006256104}
-03/04/2022 12:40:36 - INFO - codeparrot_training - Step 19767: {'lr': 0.00048243044410586433, 'samples': 10121216, 'steps': 19767, 'loss/train': 1.9391505718231201}
-03/04/2022 12:40:38 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 12:40:41 - INFO - codeparrot_training - Step 19768: {'lr': 0.00048242848977748205, 'samples': 10121728, 'steps': 19768, 'loss/train': 2.2395808696746826}
-03/04/2022 12:40:44 - INFO - codeparrot_training - Step 19769: {'lr': 0.0004824265353443711, 'samples': 10122240, 'steps': 19769, 'loss/train': 1.5851178169250488}
-03/04/2022 12:40:47 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/04/2022 12:40:50 - INFO - codeparrot_training - Step 19770: {'lr': 0.00048242458080653233, 'samples': 10122752, 'steps': 19770, 'loss/train': 1.7473492622375488}
-03/04/2022 12:40:53 - INFO - codeparrot_training - Step 19771: {'lr': 0.0004824226261639666, 'samples': 10123264, 'steps': 19771, 'loss/train': 2.1804256439208984}
-03/04/2022 12:40:55 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 12:40:58 - INFO - codeparrot_training - Step 19772: {'lr': 0.00048242067141667487, 'samples': 10123776, 'steps': 19772, 'loss/train': 1.622178554534912}
-03/04/2022 12:41:01 - INFO - codeparrot_training - Step 19773: {'lr': 0.00048241871656465795, 'samples': 10124288, 'steps': 19773, 'loss/train': 2.159731864929199}
-03/04/2022 12:41:03 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 12:41:07 - INFO - codeparrot_training - Step 19774: {'lr': 0.0004824167616079168, 'samples': 10124800, 'steps': 19774, 'loss/train': 1.8339184522628784}
-03/04/2022 12:41:10 - INFO - codeparrot_training - Step 19775: {'lr': 0.0004824148065464522, 'samples': 10125312, 'steps': 19775, 'loss/train': 1.6273595094680786}
-03/04/2022 12:41:11 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/04/2022 12:41:15 - INFO - codeparrot_training - Step 19776: {'lr': 0.00048241285138026505, 'samples': 10125824, 'steps': 19776, 'loss/train': 1.8645442724227905}
-03/04/2022 12:41:18 - INFO - codeparrot_training - Step 19777: {'lr': 0.00048241089610935627, 'samples': 10126336, 'steps': 19777, 'loss/train': 2.2174816131591797}
-03/04/2022 12:41:20 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/04/2022 12:41:23 - INFO - codeparrot_training - Step 19778: {'lr': 0.0004824089407337267, 'samples': 10126848, 'steps': 19778, 'loss/train': 2.3656773567199707}
-03/04/2022 12:41:27 - INFO - codeparrot_training - Step 19779: {'lr': 0.00048240698525337726, 'samples': 10127360, 'steps': 19779, 'loss/train': 2.0957984924316406}
-03/04/2022 12:41:28 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 12:41:32 - INFO - codeparrot_training - Step 19780: {'lr': 0.0004824050296683089, 'samples': 10127872, 'steps': 19780, 'loss/train': 1.813086748123169}
-03/04/2022 12:41:35 - INFO - codeparrot_training - Step 19781: {'lr': 0.0004824030739785223, 'samples': 10128384, 'steps': 19781, 'loss/train': 1.1297773122787476}
-03/04/2022 12:41:37 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/04/2022 12:41:40 - INFO - codeparrot_training - Step 19782: {'lr': 0.00048240111818401854, 'samples': 10128896, 'steps': 19782, 'loss/train': 1.286503791809082}
-03/04/2022 12:41:43 - INFO - codeparrot_training - Step 19783: {'lr': 0.0004823991622847984, 'samples': 10129408, 'steps': 19783, 'loss/train': 2.514251232147217}
-03/04/2022 12:41:45 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/04/2022 12:41:49 - INFO - codeparrot_training - Step 19784: {'lr': 0.0004823972062808628, 'samples': 10129920, 'steps': 19784, 'loss/train': 0.543460488319397}
-03/04/2022 12:41:52 - INFO - codeparrot_training - Step 19785: {'lr': 0.0004823952501722126, 'samples': 10130432, 'steps': 19785, 'loss/train': 2.372936248779297}
-03/04/2022 12:41:53 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/04/2022 12:41:57 - INFO - codeparrot_training - Step 19786: {'lr': 0.00048239329395884865, 'samples': 10130944, 'steps': 19786, 'loss/train': 2.0636587142944336}
-03/04/2022 12:42:00 - INFO - codeparrot_training - Step 19787: {'lr': 0.00048239133764077193, 'samples': 10131456, 'steps': 19787, 'loss/train': 1.55360746383667}
-03/04/2022 12:42:01 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 12:42:05 - INFO - codeparrot_training - Step 19788: {'lr': 0.00048238938121798313, 'samples': 10131968, 'steps': 19788, 'loss/train': 1.9706697463989258}
-03/04/2022 12:42:09 - INFO - codeparrot_training - Step 19789: {'lr': 0.00048238742469048344, 'samples': 10132480, 'steps': 19789, 'loss/train': 1.5519390106201172}
-03/04/2022 12:42:10 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/04/2022 12:42:14 - INFO - codeparrot_training - Step 19790: {'lr': 0.00048238546805827345, 'samples': 10132992, 'steps': 19790, 'loss/train': 1.9163192510604858}
-03/04/2022 12:42:17 - INFO - codeparrot_training - Step 19791: {'lr': 0.00048238351132135415, 'samples': 10133504, 'steps': 19791, 'loss/train': 0.7453199028968811}
-03/04/2022 12:42:18 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/04/2022 12:42:23 - INFO - codeparrot_training - Step 19792: {'lr': 0.0004823815544797265, 'samples': 10134016, 'steps': 19792, 'loss/train': 2.4835805892944336}
-03/04/2022 12:42:26 - INFO - codeparrot_training - Step 19793: {'lr': 0.0004823795975333912, 'samples': 10134528, 'steps': 19793, 'loss/train': 1.1235730648040771}
-03/04/2022 12:42:27 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 12:42:31 - INFO - codeparrot_training - Step 19794: {'lr': 0.0004823776404823493, 'samples': 10135040, 'steps': 19794, 'loss/train': 1.400590419769287}
-03/04/2022 12:42:34 - INFO - codeparrot_training - Step 19795: {'lr': 0.00048237568332660163, 'samples': 10135552, 'steps': 19795, 'loss/train': 1.948028802871704}
-03/04/2022 12:42:36 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 12:42:40 - INFO - codeparrot_training - Step 19796: {'lr': 0.0004823737260661491, 'samples': 10136064, 'steps': 19796, 'loss/train': 1.8016453981399536}
-03/04/2022 12:42:43 - INFO - codeparrot_training - Step 19797: {'lr': 0.00048237176870099256, 'samples': 10136576, 'steps': 19797, 'loss/train': 2.1367990970611572}
-03/04/2022 12:42:46 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/04/2022 12:42:48 - INFO - codeparrot_training - Step 19798: {'lr': 0.0004823698112311328, 'samples': 10137088, 'steps': 19798, 'loss/train': 1.521304965019226}
-03/04/2022 12:42:51 - INFO - codeparrot_training - Step 19799: {'lr': 0.00048236785365657076, 'samples': 10137600, 'steps': 19799, 'loss/train': 1.541629672050476}
-03/04/2022 12:42:54 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/04/2022 12:42:56 - INFO - codeparrot_training - Step 19800: {'lr': 0.00048236589597730744, 'samples': 10138112, 'steps': 19800, 'loss/train': 1.769490122795105}
-03/04/2022 12:43:00 - INFO - codeparrot_training - Step 19801: {'lr': 0.00048236393819334363, 'samples': 10138624, 'steps': 19801, 'loss/train': 2.436988115310669}
-03/04/2022 12:43:02 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 12:43:05 - INFO - codeparrot_training - Step 19802: {'lr': 0.0004823619803046802, 'samples': 10139136, 'steps': 19802, 'loss/train': 0.8740523457527161}
-03/04/2022 12:43:08 - INFO - codeparrot_training - Step 19803: {'lr': 0.00048236002231131803, 'samples': 10139648, 'steps': 19803, 'loss/train': 1.0888659954071045}
-03/04/2022 12:43:10 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/04/2022 12:43:13 - INFO - codeparrot_training - Step 19804: {'lr': 0.00048235806421325803, 'samples': 10140160, 'steps': 19804, 'loss/train': 3.4079155921936035}
-03/04/2022 12:43:17 - INFO - codeparrot_training - Step 19805: {'lr': 0.0004823561060105011, 'samples': 10140672, 'steps': 19805, 'loss/train': 2.1065566539764404}
-03/04/2022 12:43:19 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 12:43:22 - INFO - codeparrot_training - Step 19806: {'lr': 0.00048235414770304803, 'samples': 10141184, 'steps': 19806, 'loss/train': 1.8995722532272339}
-03/04/2022 12:43:25 - INFO - codeparrot_training - Step 19807: {'lr': 0.00048235218929089987, 'samples': 10141696, 'steps': 19807, 'loss/train': 2.222193956375122}
-03/04/2022 12:43:27 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 12:43:30 - INFO - codeparrot_training - Step 19808: {'lr': 0.00048235023077405724, 'samples': 10142208, 'steps': 19808, 'loss/train': 0.7014352083206177}
-03/04/2022 12:43:33 - INFO - codeparrot_training - Step 19809: {'lr': 0.0004823482721525213, 'samples': 10142720, 'steps': 19809, 'loss/train': 2.1093897819519043}
-03/04/2022 12:43:36 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/04/2022 12:43:39 - INFO - codeparrot_training - Step 19810: {'lr': 0.0004823463134262928, 'samples': 10143232, 'steps': 19810, 'loss/train': 0.7520968317985535}
-03/04/2022 12:43:42 - INFO - codeparrot_training - Step 19811: {'lr': 0.00048234435459537265, 'samples': 10143744, 'steps': 19811, 'loss/train': 1.8982757329940796}
-03/04/2022 12:43:45 - INFO - codeparrot_training - Step 19812: {'lr': 0.0004823423956597617, 'samples': 10144256, 'steps': 19812, 'loss/train': 1.940994381904602}
-03/04/2022 12:43:45 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/04/2022 12:43:50 - INFO - codeparrot_training - Step 19813: {'lr': 0.0004823404366194608, 'samples': 10144768, 'steps': 19813, 'loss/train': 0.9113917946815491}
-03/04/2022 12:43:54 - INFO - codeparrot_training - Step 19814: {'lr': 0.0004823384774744709, 'samples': 10145280, 'steps': 19814, 'loss/train': 0.8768632411956787}
-03/04/2022 12:43:54 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 12:43:59 - INFO - codeparrot_training - Step 19815: {'lr': 0.000482336518224793, 'samples': 10145792, 'steps': 19815, 'loss/train': 1.825161337852478}
-03/04/2022 12:44:02 - INFO - codeparrot_training - Step 19816: {'lr': 0.00048233455887042764, 'samples': 10146304, 'steps': 19816, 'loss/train': 2.094974994659424}
-03/04/2022 12:44:02 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/04/2022 12:44:07 - INFO - codeparrot_training - Step 19817: {'lr': 0.0004823325994113761, 'samples': 10146816, 'steps': 19817, 'loss/train': 1.8246568441390991}
-03/04/2022 12:44:10 - INFO - codeparrot_training - Step 19818: {'lr': 0.00048233063984763895, 'samples': 10147328, 'steps': 19818, 'loss/train': 2.088975191116333}
-03/04/2022 12:44:11 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/04/2022 12:44:16 - INFO - codeparrot_training - Step 19819: {'lr': 0.0004823286801792173, 'samples': 10147840, 'steps': 19819, 'loss/train': 1.2220865488052368}
-03/04/2022 12:44:19 - INFO - codeparrot_training - Step 19820: {'lr': 0.0004823267204061118, 'samples': 10148352, 'steps': 19820, 'loss/train': 1.873769760131836}
-03/04/2022 12:44:19 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/04/2022 12:44:24 - INFO - codeparrot_training - Step 19821: {'lr': 0.0004823247605283236, 'samples': 10148864, 'steps': 19821, 'loss/train': 1.4555636644363403}
-03/04/2022 12:44:27 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/04/2022 12:44:29 - INFO - codeparrot_training - Step 19822: {'lr': 0.0004823228005458534, 'samples': 10149376, 'steps': 19822, 'loss/train': 1.1933542490005493}
-03/04/2022 12:44:32 - INFO - codeparrot_training - Step 19823: {'lr': 0.00048232084045870204, 'samples': 10149888, 'steps': 19823, 'loss/train': 1.7981982231140137}
-03/04/2022 12:44:35 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/04/2022 12:44:38 - INFO - codeparrot_training - Step 19824: {'lr': 0.00048231888026687065, 'samples': 10150400, 'steps': 19824, 'loss/train': 1.1931565999984741}
-03/04/2022 12:44:41 - INFO - codeparrot_training - Step 19825: {'lr': 0.00048231691997035987, 'samples': 10150912, 'steps': 19825, 'loss/train': 2.326483726501465}
-03/04/2022 12:44:43 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/04/2022 12:44:46 - INFO - codeparrot_training - Step 19826: {'lr': 0.00048231495956917067, 'samples': 10151424, 'steps': 19826, 'loss/train': 2.116652727127075}
-03/04/2022 12:44:49 - INFO - codeparrot_training - Step 19827: {'lr': 0.00048231299906330397, 'samples': 10151936, 'steps': 19827, 'loss/train': 2.197244644165039}
-03/04/2022 12:44:52 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/04/2022 12:44:55 - INFO - codeparrot_training - Step 19828: {'lr': 0.0004823110384527606, 'samples': 10152448, 'steps': 19828, 'loss/train': 1.7668880224227905}
-03/04/2022 12:44:58 - INFO - codeparrot_training - Step 19829: {'lr': 0.0004823090777375414, 'samples': 10152960, 'steps': 19829, 'loss/train': 0.8269534111022949}
-03/04/2022 12:45:00 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/04/2022 12:45:03 - INFO - codeparrot_training - Step 19830: {'lr': 0.0004823071169176474, 'samples': 10153472, 'steps': 19830, 'loss/train': 2.3575305938720703}
-03/04/2022 12:45:06 - INFO - codeparrot_training - Step 19831: {'lr': 0.00048230515599307933, 'samples': 10153984, 'steps': 19831, 'loss/train': 1.777549386024475}
-03/04/2022 12:45:08 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/04/2022 12:45:11 - INFO - codeparrot_training - Step 19832: {'lr': 0.0004823031949638382, 'samples': 10154496, 'steps': 19832, 'loss/train': 2.2322680950164795}
-03/04/2022 12:45:15 - INFO - codeparrot_training - Step 19833: {'lr': 0.0004823012338299248, 'samples': 10155008, 'steps': 19833, 'loss/train': 1.8456605672836304}
-03/04/2022 12:45:17 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/04/2022 12:45:20 - INFO - codeparrot_training - Step 19834: {'lr': 0.0004822992725913401, 'samples': 10155520, 'steps': 19834, 'loss/train': 2.3469038009643555}
-03/04/2022 12:45:23 - INFO - codeparrot_training - Step 19835: {'lr': 0.00048229731124808484, 'samples': 10156032, 'steps': 19835, 'loss/train': 2.3397114276885986}
-03/04/2022 12:45:25 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/04/2022 12:45:28 - INFO - codeparrot_training - Step 19836: {'lr': 0.00048229534980016007, 'samples': 10156544, 'steps': 19836, 'loss/train': 1.7590001821517944}
-03/04/2022 12:45:31 - INFO - codeparrot_training - Step 19837: {'lr': 0.0004822933882475666, 'samples': 10157056, 'steps': 19837, 'loss/train': 1.294845461845398}
-03/04/2022 12:45:33 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 12:45:37 - INFO - codeparrot_training - Step 19838: {'lr': 0.00048229142659030527, 'samples': 10157568, 'steps': 19838, 'loss/train': 2.8006882667541504}
-03/04/2022 12:45:40 - INFO - codeparrot_training - Step 19839: {'lr': 0.000482289464828377, 'samples': 10158080, 'steps': 19839, 'loss/train': 2.0161168575286865}
-03/04/2022 12:45:42 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/04/2022 12:45:45 - INFO - codeparrot_training - Step 19840: {'lr': 0.00048228750296178276, 'samples': 10158592, 'steps': 19840, 'loss/train': 2.1369569301605225}
-03/04/2022 12:45:48 - INFO - codeparrot_training - Step 19841: {'lr': 0.0004822855409905233, 'samples': 10159104, 'steps': 19841, 'loss/train': 1.606272578239441}
-03/04/2022 12:45:50 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 12:45:53 - INFO - codeparrot_training - Step 19842: {'lr': 0.00048228357891459954, 'samples': 10159616, 'steps': 19842, 'loss/train': 2.259392499923706}
-03/04/2022 12:45:57 - INFO - codeparrot_training - Step 19843: {'lr': 0.0004822816167340124, 'samples': 10160128, 'steps': 19843, 'loss/train': 1.9413256645202637}
-03/04/2022 12:45:58 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/04/2022 12:46:02 - INFO - codeparrot_training - Step 19844: {'lr': 0.00048227965444876277, 'samples': 10160640, 'steps': 19844, 'loss/train': 2.229551076889038}
-03/04/2022 12:46:05 - INFO - codeparrot_training - Step 19845: {'lr': 0.0004822776920588515, 'samples': 10161152, 'steps': 19845, 'loss/train': 1.5100980997085571}
-03/04/2022 12:46:07 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/04/2022 12:46:10 - INFO - codeparrot_training - Step 19846: {'lr': 0.0004822757295642795, 'samples': 10161664, 'steps': 19846, 'loss/train': 1.8339672088623047}
-03/04/2022 12:46:13 - INFO - codeparrot_training - Step 19847: {'lr': 0.00048227376696504765, 'samples': 10162176, 'steps': 19847, 'loss/train': 1.4135137796401978}
-03/04/2022 12:46:15 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 12:46:19 - INFO - codeparrot_training - Step 19848: {'lr': 0.0004822718042611568, 'samples': 10162688, 'steps': 19848, 'loss/train': 1.491626262664795}
-03/04/2022 12:46:22 - INFO - codeparrot_training - Step 19849: {'lr': 0.0004822698414526079, 'samples': 10163200, 'steps': 19849, 'loss/train': 1.3416436910629272}
-03/04/2022 12:46:23 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 12:46:27 - INFO - codeparrot_training - Step 19850: {'lr': 0.0004822678785394017, 'samples': 10163712, 'steps': 19850, 'loss/train': 2.096189022064209}
-03/04/2022 12:46:30 - INFO - codeparrot_training - Step 19851: {'lr': 0.0004822659155215393, 'samples': 10164224, 'steps': 19851, 'loss/train': 1.9066327810287476}
-03/04/2022 12:46:32 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/04/2022 12:46:36 - INFO - codeparrot_training - Step 19852: {'lr': 0.00048226395239902133, 'samples': 10164736, 'steps': 19852, 'loss/train': 1.7607125043869019}
-03/04/2022 12:46:39 - INFO - codeparrot_training - Step 19853: {'lr': 0.00048226198917184886, 'samples': 10165248, 'steps': 19853, 'loss/train': 2.250265121459961}
-03/04/2022 12:46:41 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 12:46:44 - INFO - codeparrot_training - Step 19854: {'lr': 0.00048226002584002276, 'samples': 10165760, 'steps': 19854, 'loss/train': 1.1960186958312988}
-03/04/2022 12:46:47 - INFO - codeparrot_training - Step 19855: {'lr': 0.00048225806240354387, 'samples': 10166272, 'steps': 19855, 'loss/train': 2.1483571529388428}
-03/04/2022 12:46:49 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/04/2022 12:46:53 - INFO - codeparrot_training - Step 19856: {'lr': 0.0004822560988624131, 'samples': 10166784, 'steps': 19856, 'loss/train': 1.7365542650222778}
-03/04/2022 12:46:56 - INFO - codeparrot_training - Step 19857: {'lr': 0.0004822541352166312, 'samples': 10167296, 'steps': 19857, 'loss/train': 2.011840343475342}
-03/04/2022 12:46:58 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/04/2022 12:47:01 - INFO - codeparrot_training - Step 19858: {'lr': 0.0004822521714661993, 'samples': 10167808, 'steps': 19858, 'loss/train': 1.406099796295166}
-03/04/2022 12:47:04 - INFO - codeparrot_training - Step 19859: {'lr': 0.0004822502076111181, 'samples': 10168320, 'steps': 19859, 'loss/train': 1.5457159280776978}
-03/04/2022 12:47:06 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/04/2022 12:47:10 - INFO - codeparrot_training - Step 19860: {'lr': 0.0004822482436513885, 'samples': 10168832, 'steps': 19860, 'loss/train': 2.1389973163604736}
-03/04/2022 12:47:13 - INFO - codeparrot_training - Step 19861: {'lr': 0.0004822462795870115, 'samples': 10169344, 'steps': 19861, 'loss/train': 2.313721179962158}
-03/04/2022 12:47:14 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 12:47:18 - INFO - codeparrot_training - Step 19862: {'lr': 0.00048224431541798784, 'samples': 10169856, 'steps': 19862, 'loss/train': 1.9697843790054321}
-03/04/2022 12:47:21 - INFO - codeparrot_training - Step 19863: {'lr': 0.00048224235114431856, 'samples': 10170368, 'steps': 19863, 'loss/train': 1.612579345703125}
-03/04/2022 12:47:23 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 12:47:26 - INFO - codeparrot_training - Step 19864: {'lr': 0.0004822403867660044, 'samples': 10170880, 'steps': 19864, 'loss/train': 1.8613646030426025}
-03/04/2022 12:47:30 - INFO - codeparrot_training - Step 19865: {'lr': 0.0004822384222830463, 'samples': 10171392, 'steps': 19865, 'loss/train': 1.5513694286346436}
-03/04/2022 12:47:32 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/04/2022 12:47:35 - INFO - codeparrot_training - Step 19866: {'lr': 0.0004822364576954452, 'samples': 10171904, 'steps': 19866, 'loss/train': 2.2861578464508057}
-03/04/2022 12:47:38 - INFO - codeparrot_training - Step 19867: {'lr': 0.0004822344930032019, 'samples': 10172416, 'steps': 19867, 'loss/train': 2.0221612453460693}
-03/04/2022 12:47:40 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/04/2022 12:47:43 - INFO - codeparrot_training - Step 19868: {'lr': 0.00048223252820631736, 'samples': 10172928, 'steps': 19868, 'loss/train': 1.6351757049560547}
-03/04/2022 12:47:47 - INFO - codeparrot_training - Step 19869: {'lr': 0.00048223056330479235, 'samples': 10173440, 'steps': 19869, 'loss/train': 1.9015299081802368}
-03/04/2022 12:47:49 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 12:47:52 - INFO - codeparrot_training - Step 19870: {'lr': 0.00048222859829862784, 'samples': 10173952, 'steps': 19870, 'loss/train': 2.0677883625030518}
-03/04/2022 12:47:55 - INFO - codeparrot_training - Step 19871: {'lr': 0.0004822266331878248, 'samples': 10174464, 'steps': 19871, 'loss/train': 5.846251964569092}
-03/04/2022 12:47:59 - INFO - codeparrot_training - Step 19872: {'lr': 0.00048222466797238396, 'samples': 10174976, 'steps': 19872, 'loss/train': 2.1159582138061523}
-03/04/2022 12:48:00 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/04/2022 12:48:04 - INFO - codeparrot_training - Step 19873: {'lr': 0.00048222270265230627, 'samples': 10175488, 'steps': 19873, 'loss/train': 2.1772701740264893}
-03/04/2022 12:48:07 - INFO - codeparrot_training - Step 19874: {'lr': 0.0004822207372275926, 'samples': 10176000, 'steps': 19874, 'loss/train': 2.099034070968628}
-03/04/2022 12:48:09 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/04/2022 12:48:12 - INFO - codeparrot_training - Step 19875: {'lr': 0.0004822187716982439, 'samples': 10176512, 'steps': 19875, 'loss/train': 1.6294924020767212}
-03/04/2022 12:48:16 - INFO - codeparrot_training - Step 19876: {'lr': 0.000482216806064261, 'samples': 10177024, 'steps': 19876, 'loss/train': 0.6671847701072693}
-03/04/2022 12:48:18 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/04/2022 12:48:22 - INFO - codeparrot_training - Step 19877: {'lr': 0.0004822148403256447, 'samples': 10177536, 'steps': 19877, 'loss/train': 1.3587850332260132}
-03/04/2022 12:48:25 - INFO - codeparrot_training - Step 19878: {'lr': 0.00048221287448239604, 'samples': 10178048, 'steps': 19878, 'loss/train': 1.6287637948989868}
-03/04/2022 12:48:28 - INFO - codeparrot_training - Step 19879: {'lr': 0.00048221090853451586, 'samples': 10178560, 'steps': 19879, 'loss/train': 4.206445217132568}
-03/04/2022 12:48:29 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 12:48:33 - INFO - codeparrot_training - Step 19880: {'lr': 0.000482208942482005, 'samples': 10179072, 'steps': 19880, 'loss/train': 2.585996627807617}
-03/04/2022 12:48:37 - INFO - codeparrot_training - Step 19881: {'lr': 0.00048220697632486443, 'samples': 10179584, 'steps': 19881, 'loss/train': 1.856677770614624}
-03/04/2022 12:48:38 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/04/2022 12:48:42 - INFO - codeparrot_training - Step 19882: {'lr': 0.0004822050100630949, 'samples': 10180096, 'steps': 19882, 'loss/train': 2.6133460998535156}
-03/04/2022 12:48:45 - INFO - codeparrot_training - Step 19883: {'lr': 0.0004822030436966974, 'samples': 10180608, 'steps': 19883, 'loss/train': 1.9130083322525024}
-03/04/2022 12:48:47 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 12:48:50 - INFO - codeparrot_training - Step 19884: {'lr': 0.0004822010772256728, 'samples': 10181120, 'steps': 19884, 'loss/train': 1.904091238975525}
-03/04/2022 12:48:54 - INFO - codeparrot_training - Step 19885: {'lr': 0.00048219911065002196, 'samples': 10181632, 'steps': 19885, 'loss/train': 0.36119067668914795}
-03/04/2022 12:48:56 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/04/2022 12:48:59 - INFO - codeparrot_training - Step 19886: {'lr': 0.00048219714396974587, 'samples': 10182144, 'steps': 19886, 'loss/train': 2.3573157787323}
-03/04/2022 12:49:02 - INFO - codeparrot_training - Step 19887: {'lr': 0.0004821951771848452, 'samples': 10182656, 'steps': 19887, 'loss/train': 1.3326640129089355}
-03/04/2022 12:49:04 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 12:49:07 - INFO - codeparrot_training - Step 19888: {'lr': 0.00048219321029532104, 'samples': 10183168, 'steps': 19888, 'loss/train': 2.4931702613830566}
-03/04/2022 12:49:10 - INFO - codeparrot_training - Step 19889: {'lr': 0.0004821912433011742, 'samples': 10183680, 'steps': 19889, 'loss/train': 2.361409902572632}
-03/04/2022 12:49:12 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/04/2022 12:49:16 - INFO - codeparrot_training - Step 19890: {'lr': 0.00048218927620240557, 'samples': 10184192, 'steps': 19890, 'loss/train': 2.5654208660125732}
-03/04/2022 12:49:19 - INFO - codeparrot_training - Step 19891: {'lr': 0.00048218730899901596, 'samples': 10184704, 'steps': 19891, 'loss/train': 1.270777940750122}
-03/04/2022 12:49:21 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 12:49:24 - INFO - codeparrot_training - Step 19892: {'lr': 0.0004821853416910065, 'samples': 10185216, 'steps': 19892, 'loss/train': 1.8993537425994873}
-03/04/2022 12:49:27 - INFO - codeparrot_training - Step 19893: {'lr': 0.0004821833742783778, 'samples': 10185728, 'steps': 19893, 'loss/train': 2.244206666946411}
-03/04/2022 12:49:29 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/04/2022 12:49:32 - INFO - codeparrot_training - Step 19894: {'lr': 0.0004821814067611308, 'samples': 10186240, 'steps': 19894, 'loss/train': 2.8118410110473633}
-03/04/2022 12:49:36 - INFO - codeparrot_training - Step 19895: {'lr': 0.00048217943913926646, 'samples': 10186752, 'steps': 19895, 'loss/train': 2.512181043624878}
-03/04/2022 12:49:37 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/04/2022 12:49:41 - INFO - codeparrot_training - Step 19896: {'lr': 0.00048217747141278574, 'samples': 10187264, 'steps': 19896, 'loss/train': 1.631456971168518}
-03/04/2022 12:49:44 - INFO - codeparrot_training - Step 19897: {'lr': 0.00048217550358168937, 'samples': 10187776, 'steps': 19897, 'loss/train': 2.365751266479492}
-03/04/2022 12:49:46 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 12:49:49 - INFO - codeparrot_training - Step 19898: {'lr': 0.00048217353564597833, 'samples': 10188288, 'steps': 19898, 'loss/train': 1.9473241567611694}
-03/04/2022 12:49:52 - INFO - codeparrot_training - Step 19899: {'lr': 0.0004821715676056534, 'samples': 10188800, 'steps': 19899, 'loss/train': 1.387442708015442}
-03/04/2022 12:49:54 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 12:49:58 - INFO - codeparrot_training - Step 19900: {'lr': 0.0004821695994607156, 'samples': 10189312, 'steps': 19900, 'loss/train': 2.386030673980713}
-03/04/2022 12:50:01 - INFO - codeparrot_training - Step 19901: {'lr': 0.0004821676312111658, 'samples': 10189824, 'steps': 19901, 'loss/train': 2.32594633102417}
-03/04/2022 12:50:03 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 12:50:06 - INFO - codeparrot_training - Step 19902: {'lr': 0.0004821656628570048, 'samples': 10190336, 'steps': 19902, 'loss/train': 1.980303406715393}
-03/04/2022 12:50:09 - INFO - codeparrot_training - Step 19903: {'lr': 0.00048216369439823355, 'samples': 10190848, 'steps': 19903, 'loss/train': 0.3905542492866516}
-03/04/2022 12:50:11 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/04/2022 12:50:14 - INFO - codeparrot_training - Step 19904: {'lr': 0.0004821617258348529, 'samples': 10191360, 'steps': 19904, 'loss/train': 2.0039732456207275}
-03/04/2022 12:50:18 - INFO - codeparrot_training - Step 19905: {'lr': 0.0004821597571668638, 'samples': 10191872, 'steps': 19905, 'loss/train': 2.573153018951416}
-03/04/2022 12:50:19 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/04/2022 12:50:23 - INFO - codeparrot_training - Step 19906: {'lr': 0.00048215778839426706, 'samples': 10192384, 'steps': 19906, 'loss/train': 1.1939237117767334}
-03/04/2022 12:50:26 - INFO - codeparrot_training - Step 19907: {'lr': 0.0004821558195170636, 'samples': 10192896, 'steps': 19907, 'loss/train': 4.5415873527526855}
-03/04/2022 12:50:28 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/04/2022 12:50:31 - INFO - codeparrot_training - Step 19908: {'lr': 0.00048215385053525434, 'samples': 10193408, 'steps': 19908, 'loss/train': 1.3344182968139648}
-03/04/2022 12:50:35 - INFO - codeparrot_training - Step 19909: {'lr': 0.00048215188144884013, 'samples': 10193920, 'steps': 19909, 'loss/train': 2.006150722503662}
-03/04/2022 12:50:36 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 12:50:40 - INFO - codeparrot_training - Step 19910: {'lr': 0.0004821499122578218, 'samples': 10194432, 'steps': 19910, 'loss/train': 0.7829998135566711}
-03/04/2022 12:50:43 - INFO - codeparrot_training - Step 19911: {'lr': 0.00048214794296220045, 'samples': 10194944, 'steps': 19911, 'loss/train': 1.2131595611572266}
-03/04/2022 12:50:44 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 12:50:48 - INFO - codeparrot_training - Step 19912: {'lr': 0.00048214597356197665, 'samples': 10195456, 'steps': 19912, 'loss/train': 1.990240454673767}
-03/04/2022 12:50:51 - INFO - codeparrot_training - Step 19913: {'lr': 0.00048214400405715153, 'samples': 10195968, 'steps': 19913, 'loss/train': 2.4458274841308594}
-03/04/2022 12:50:53 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/04/2022 12:50:57 - INFO - codeparrot_training - Step 19914: {'lr': 0.000482142034447726, 'samples': 10196480, 'steps': 19914, 'loss/train': 0.8386738300323486}
-03/04/2022 12:51:00 - INFO - codeparrot_training - Step 19915: {'lr': 0.0004821400647337007, 'samples': 10196992, 'steps': 19915, 'loss/train': 2.039153814315796}
-03/04/2022 12:51:01 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/04/2022 12:51:05 - INFO - codeparrot_training - Step 19916: {'lr': 0.0004821380949150768, 'samples': 10197504, 'steps': 19916, 'loss/train': 2.3632099628448486}
-03/04/2022 12:51:08 - INFO - codeparrot_training - Step 19917: {'lr': 0.0004821361249918549, 'samples': 10198016, 'steps': 19917, 'loss/train': 0.9795604348182678}
-03/04/2022 12:51:09 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 12:51:13 - INFO - codeparrot_training - Step 19918: {'lr': 0.0004821341549640361, 'samples': 10198528, 'steps': 19918, 'loss/train': 0.4375520348548889}
-03/04/2022 12:51:17 - INFO - codeparrot_training - Step 19919: {'lr': 0.00048213218483162133, 'samples': 10199040, 'steps': 19919, 'loss/train': 2.4106063842773438}
-03/04/2022 12:51:18 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 12:51:22 - INFO - codeparrot_training - Step 19920: {'lr': 0.0004821302145946113, 'samples': 10199552, 'steps': 19920, 'loss/train': 2.4637293815612793}
-03/04/2022 12:51:25 - INFO - codeparrot_training - Step 19921: {'lr': 0.00048212824425300694, 'samples': 10200064, 'steps': 19921, 'loss/train': 1.8230139017105103}
-03/04/2022 12:51:26 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/04/2022 12:51:30 - INFO - codeparrot_training - Step 19922: {'lr': 0.0004821262738068093, 'samples': 10200576, 'steps': 19922, 'loss/train': 0.28044453263282776}
-03/04/2022 12:51:33 - INFO - codeparrot_training - Step 19923: {'lr': 0.00048212430325601905, 'samples': 10201088, 'steps': 19923, 'loss/train': 2.140770673751831}
-03/04/2022 12:51:35 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/04/2022 12:51:39 - INFO - codeparrot_training - Step 19924: {'lr': 0.0004821223326006372, 'samples': 10201600, 'steps': 19924, 'loss/train': 2.0337555408477783}
-03/04/2022 12:51:42 - INFO - codeparrot_training - Step 19925: {'lr': 0.0004821203618406645, 'samples': 10202112, 'steps': 19925, 'loss/train': 2.077075481414795}
-03/04/2022 12:51:43 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/04/2022 12:51:47 - INFO - codeparrot_training - Step 19926: {'lr': 0.0004821183909761021, 'samples': 10202624, 'steps': 19926, 'loss/train': 1.4259023666381836}
-03/04/2022 12:51:50 - INFO - codeparrot_training - Step 19927: {'lr': 0.00048211642000695065, 'samples': 10203136, 'steps': 19927, 'loss/train': 2.1770501136779785}
-03/04/2022 12:51:52 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/04/2022 12:51:56 - INFO - codeparrot_training - Step 19928: {'lr': 0.0004821144489332112, 'samples': 10203648, 'steps': 19928, 'loss/train': 1.353190302848816}
-03/04/2022 12:51:59 - INFO - codeparrot_training - Step 19929: {'lr': 0.0004821124777548845, 'samples': 10204160, 'steps': 19929, 'loss/train': 2.052112102508545}
-03/04/2022 12:52:00 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/04/2022 12:52:04 - INFO - codeparrot_training - Step 19930: {'lr': 0.0004821105064719715, 'samples': 10204672, 'steps': 19930, 'loss/train': 1.6590656042099}
-03/04/2022 12:52:07 - INFO - codeparrot_training - Step 19931: {'lr': 0.0004821085350844731, 'samples': 10205184, 'steps': 19931, 'loss/train': 1.5206894874572754}
-03/04/2022 12:52:08 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 12:52:12 - INFO - codeparrot_training - Step 19932: {'lr': 0.0004821065635923902, 'samples': 10205696, 'steps': 19932, 'loss/train': 1.9014419317245483}
-03/04/2022 12:52:16 - INFO - codeparrot_training - Step 19933: {'lr': 0.0004821045919957237, 'samples': 10206208, 'steps': 19933, 'loss/train': 2.737725019454956}
-03/04/2022 12:52:17 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/04/2022 12:52:21 - INFO - codeparrot_training - Step 19934: {'lr': 0.00048210262029447425, 'samples': 10206720, 'steps': 19934, 'loss/train': 1.7995728254318237}
-03/04/2022 12:52:24 - INFO - codeparrot_training - Step 19935: {'lr': 0.0004821006484886431, 'samples': 10207232, 'steps': 19935, 'loss/train': 2.1414871215820312}
-03/04/2022 12:52:25 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/04/2022 12:52:29 - INFO - codeparrot_training - Step 19936: {'lr': 0.000482098676578231, 'samples': 10207744, 'steps': 19936, 'loss/train': 1.7058907747268677}
-03/04/2022 12:52:32 - INFO - codeparrot_training - Step 19937: {'lr': 0.0004820967045632388, 'samples': 10208256, 'steps': 19937, 'loss/train': 1.9326146841049194}
-03/04/2022 12:52:33 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 12:52:38 - INFO - codeparrot_training - Step 19938: {'lr': 0.00048209473244366737, 'samples': 10208768, 'steps': 19938, 'loss/train': 2.094433546066284}
-03/04/2022 12:52:41 - INFO - codeparrot_training - Step 19939: {'lr': 0.00048209276021951765, 'samples': 10209280, 'steps': 19939, 'loss/train': 1.6312905550003052}
-03/04/2022 12:52:42 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/04/2022 12:52:46 - INFO - codeparrot_training - Step 19940: {'lr': 0.00048209078789079055, 'samples': 10209792, 'steps': 19940, 'loss/train': 1.726961612701416}
-03/04/2022 12:52:49 - INFO - codeparrot_training - Step 19941: {'lr': 0.00048208881545748684, 'samples': 10210304, 'steps': 19941, 'loss/train': 2.3568150997161865}
-03/04/2022 12:52:50 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/04/2022 12:52:55 - INFO - codeparrot_training - Step 19942: {'lr': 0.00048208684291960755, 'samples': 10210816, 'steps': 19942, 'loss/train': 1.687651515007019}
-03/04/2022 12:52:58 - INFO - codeparrot_training - Step 19943: {'lr': 0.0004820848702771535, 'samples': 10211328, 'steps': 19943, 'loss/train': 1.6996532678604126}
-03/04/2022 12:52:58 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 12:53:03 - INFO - codeparrot_training - Step 19944: {'lr': 0.0004820828975301256, 'samples': 10211840, 'steps': 19944, 'loss/train': 2.243648052215576}
-03/04/2022 12:53:06 - INFO - codeparrot_training - Step 19945: {'lr': 0.0004820809246785247, 'samples': 10212352, 'steps': 19945, 'loss/train': 1.5898510217666626}
-03/04/2022 12:53:07 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 12:53:12 - INFO - codeparrot_training - Step 19946: {'lr': 0.00048207895172235174, 'samples': 10212864, 'steps': 19946, 'loss/train': 1.6597234010696411}
-03/04/2022 12:53:15 - INFO - codeparrot_training - Step 19947: {'lr': 0.00048207697866160755, 'samples': 10213376, 'steps': 19947, 'loss/train': 2.011300563812256}
-03/04/2022 12:53:17 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/04/2022 12:53:21 - INFO - codeparrot_training - Step 19948: {'lr': 0.0004820750054962931, 'samples': 10213888, 'steps': 19948, 'loss/train': 1.3744240999221802}
-03/04/2022 12:53:24 - INFO - codeparrot_training - Step 19949: {'lr': 0.00048207303222640917, 'samples': 10214400, 'steps': 19949, 'loss/train': 1.8370249271392822}
-03/04/2022 12:53:26 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 12:53:29 - INFO - codeparrot_training - Step 19950: {'lr': 0.00048207105885195677, 'samples': 10214912, 'steps': 19950, 'loss/train': 2.258617401123047}
-03/04/2022 12:53:32 - INFO - codeparrot_training - Step 19951: {'lr': 0.0004820690853729367, 'samples': 10215424, 'steps': 19951, 'loss/train': 1.6942468881607056}
-03/04/2022 12:53:34 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/04/2022 12:53:37 - INFO - codeparrot_training - Step 19952: {'lr': 0.00048206711178934994, 'samples': 10215936, 'steps': 19952, 'loss/train': 1.6091153621673584}
-03/04/2022 12:53:40 - INFO - codeparrot_training - Step 19953: {'lr': 0.00048206513810119725, 'samples': 10216448, 'steps': 19953, 'loss/train': 2.026717185974121}
-03/04/2022 12:53:42 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/04/2022 12:53:46 - INFO - codeparrot_training - Step 19954: {'lr': 0.0004820631643084796, 'samples': 10216960, 'steps': 19954, 'loss/train': 1.5112526416778564}
-03/04/2022 12:53:49 - INFO - codeparrot_training - Step 19955: {'lr': 0.00048206119041119787, 'samples': 10217472, 'steps': 19955, 'loss/train': 1.1783504486083984}
-03/04/2022 12:53:51 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 12:53:54 - INFO - codeparrot_training - Step 19956: {'lr': 0.000482059216409353, 'samples': 10217984, 'steps': 19956, 'loss/train': 2.051764726638794}
-03/04/2022 12:53:57 - INFO - codeparrot_training - Step 19957: {'lr': 0.0004820572423029458, 'samples': 10218496, 'steps': 19957, 'loss/train': 2.219106435775757}
-03/04/2022 12:53:59 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 12:54:03 - INFO - codeparrot_training - Step 19958: {'lr': 0.00048205526809197717, 'samples': 10219008, 'steps': 19958, 'loss/train': 1.5578713417053223}
-03/04/2022 12:54:06 - INFO - codeparrot_training - Step 19959: {'lr': 0.000482053293776448, 'samples': 10219520, 'steps': 19959, 'loss/train': 2.391291856765747}
-03/04/2022 12:54:07 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/04/2022 12:54:11 - INFO - codeparrot_training - Step 19960: {'lr': 0.0004820513193563593, 'samples': 10220032, 'steps': 19960, 'loss/train': 1.622519612312317}
-03/04/2022 12:54:14 - INFO - codeparrot_training - Step 19961: {'lr': 0.00048204934483171176, 'samples': 10220544, 'steps': 19961, 'loss/train': 1.7340925931930542}
-03/04/2022 12:54:16 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/04/2022 12:54:19 - INFO - codeparrot_training - Step 19962: {'lr': 0.0004820473702025064, 'samples': 10221056, 'steps': 19962, 'loss/train': 2.8198986053466797}
-03/04/2022 12:54:23 - INFO - codeparrot_training - Step 19963: {'lr': 0.000482045395468744, 'samples': 10221568, 'steps': 19963, 'loss/train': 0.433694988489151}
-03/04/2022 12:54:24 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 12:54:28 - INFO - codeparrot_training - Step 19964: {'lr': 0.0004820434206304256, 'samples': 10222080, 'steps': 19964, 'loss/train': 0.6892015337944031}
-03/04/2022 12:54:31 - INFO - codeparrot_training - Step 19965: {'lr': 0.000482041445687552, 'samples': 10222592, 'steps': 19965, 'loss/train': 0.16242405772209167}
-03/04/2022 12:54:33 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/04/2022 12:54:37 - INFO - codeparrot_training - Step 19966: {'lr': 0.0004820394706401242, 'samples': 10223104, 'steps': 19966, 'loss/train': 1.3020055294036865}
-03/04/2022 12:54:40 - INFO - codeparrot_training - Step 19967: {'lr': 0.0004820374954881429, 'samples': 10223616, 'steps': 19967, 'loss/train': 2.1176605224609375}
-03/04/2022 12:54:43 - INFO - codeparrot_training - Step 19968: {'lr': 0.000482035520231609, 'samples': 10224128, 'steps': 19968, 'loss/train': 2.1836509704589844}
-03/04/2022 12:54:44 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 12:54:48 - INFO - codeparrot_training - Step 19969: {'lr': 0.00048203354487052363, 'samples': 10224640, 'steps': 19969, 'loss/train': 1.9374854564666748}
-03/04/2022 12:54:52 - INFO - codeparrot_training - Step 19970: {'lr': 0.00048203156940488745, 'samples': 10225152, 'steps': 19970, 'loss/train': 1.6065590381622314}
-03/04/2022 12:54:52 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 12:54:57 - INFO - codeparrot_training - Step 19971: {'lr': 0.00048202959383470144, 'samples': 10225664, 'steps': 19971, 'loss/train': 2.0499842166900635}
-03/04/2022 12:55:00 - INFO - codeparrot_training - Step 19972: {'lr': 0.00048202761815996646, 'samples': 10226176, 'steps': 19972, 'loss/train': 1.7869300842285156}
-03/04/2022 12:55:00 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 12:55:05 - INFO - codeparrot_training - Step 19973: {'lr': 0.0004820256423806835, 'samples': 10226688, 'steps': 19973, 'loss/train': 2.4714343547821045}
-03/04/2022 12:55:08 - INFO - codeparrot_training - Step 19974: {'lr': 0.00048202366649685325, 'samples': 10227200, 'steps': 19974, 'loss/train': 1.6435937881469727}
-03/04/2022 12:55:08 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/04/2022 12:55:14 - INFO - codeparrot_training - Step 19975: {'lr': 0.0004820216905084768, 'samples': 10227712, 'steps': 19975, 'loss/train': 1.4493975639343262}
-03/04/2022 12:55:17 - INFO - codeparrot_training - Step 19976: {'lr': 0.00048201971441555485, 'samples': 10228224, 'steps': 19976, 'loss/train': 1.781044363975525}
-03/04/2022 12:55:17 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/04/2022 12:55:22 - INFO - codeparrot_training - Step 19977: {'lr': 0.0004820177382180885, 'samples': 10228736, 'steps': 19977, 'loss/train': 1.7119731903076172}
-03/04/2022 12:55:25 - INFO - codeparrot_training - Step 19978: {'lr': 0.00048201576191607843, 'samples': 10229248, 'steps': 19978, 'loss/train': 1.9400750398635864}
-03/04/2022 12:55:25 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/04/2022 12:55:31 - INFO - codeparrot_training - Step 19979: {'lr': 0.00048201378550952575, 'samples': 10229760, 'steps': 19979, 'loss/train': 2.0348732471466064}
-03/04/2022 12:55:33 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/04/2022 12:55:36 - INFO - codeparrot_training - Step 19980: {'lr': 0.0004820118089984312, 'samples': 10230272, 'steps': 19980, 'loss/train': 1.7032426595687866}
-03/04/2022 12:55:39 - INFO - codeparrot_training - Step 19981: {'lr': 0.0004820098323827957, 'samples': 10230784, 'steps': 19981, 'loss/train': 1.5216456651687622}
-03/04/2022 12:55:42 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/04/2022 12:55:44 - INFO - codeparrot_training - Step 19982: {'lr': 0.0004820078556626202, 'samples': 10231296, 'steps': 19982, 'loss/train': 1.7924262285232544}
-03/04/2022 12:55:47 - INFO - codeparrot_training - Step 19983: {'lr': 0.0004820058788379055, 'samples': 10231808, 'steps': 19983, 'loss/train': 2.1892576217651367}
-03/04/2022 12:55:50 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/04/2022 12:55:53 - INFO - codeparrot_training - Step 19984: {'lr': 0.0004820039019086525, 'samples': 10232320, 'steps': 19984, 'loss/train': 1.3113913536071777}
-03/04/2022 12:55:56 - INFO - codeparrot_training - Step 19985: {'lr': 0.00048200192487486216, 'samples': 10232832, 'steps': 19985, 'loss/train': 2.098022699356079}
-03/04/2022 12:55:59 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/04/2022 12:56:01 - INFO - codeparrot_training - Step 19986: {'lr': 0.00048199994773653535, 'samples': 10233344, 'steps': 19986, 'loss/train': 2.157574415206909}
-03/04/2022 12:56:04 - INFO - codeparrot_training - Step 19987: {'lr': 0.0004819979704936729, 'samples': 10233856, 'steps': 19987, 'loss/train': 1.7193831205368042}
-03/04/2022 12:56:07 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/04/2022 12:56:09 - INFO - codeparrot_training - Step 19988: {'lr': 0.00048199599314627576, 'samples': 10234368, 'steps': 19988, 'loss/train': 1.6702628135681152}
-03/04/2022 12:56:13 - INFO - codeparrot_training - Step 19989: {'lr': 0.00048199401569434477, 'samples': 10234880, 'steps': 19989, 'loss/train': 1.913305640220642}
-03/04/2022 12:56:15 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/04/2022 12:56:18 - INFO - codeparrot_training - Step 19990: {'lr': 0.00048199203813788086, 'samples': 10235392, 'steps': 19990, 'loss/train': 2.1595559120178223}
-03/04/2022 12:56:21 - INFO - codeparrot_training - Step 19991: {'lr': 0.00048199006047688496, 'samples': 10235904, 'steps': 19991, 'loss/train': 1.6218160390853882}
-03/04/2022 12:56:24 - INFO - codeparrot_training - Step 19992: {'lr': 0.0004819880827113579, 'samples': 10236416, 'steps': 19992, 'loss/train': 1.8791284561157227}
-03/04/2022 12:56:24 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/04/2022 12:56:30 - INFO - codeparrot_training - Step 19993: {'lr': 0.0004819861048413006, 'samples': 10236928, 'steps': 19993, 'loss/train': 2.498661518096924}
-03/04/2022 12:56:33 - INFO - codeparrot_training - Step 19994: {'lr': 0.00048198412686671394, 'samples': 10237440, 'steps': 19994, 'loss/train': 0.9555248618125916}
-03/04/2022 12:56:33 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/04/2022 12:56:38 - INFO - codeparrot_training - Step 19995: {'lr': 0.0004819821487875988, 'samples': 10237952, 'steps': 19995, 'loss/train': 2.326756238937378}
-03/04/2022 12:56:41 - INFO - codeparrot_training - Step 19996: {'lr': 0.0004819801706039561, 'samples': 10238464, 'steps': 19996, 'loss/train': 1.367641806602478}
-03/04/2022 12:56:41 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/04/2022 12:56:46 - INFO - codeparrot_training - Step 19997: {'lr': 0.0004819781923157867, 'samples': 10238976, 'steps': 19997, 'loss/train': 2.3526673316955566}
-03/04/2022 12:56:50 - INFO - codeparrot_training - Step 19998: {'lr': 0.00048197621392309154, 'samples': 10239488, 'steps': 19998, 'loss/train': 1.8712676763534546}
-03/04/2022 12:56:50 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 12:56:55 - INFO - codeparrot_training - Step 19999: {'lr': 0.00048197423542587143, 'samples': 10240000, 'steps': 19999, 'loss/train': 1.2787634134292603}
-03/04/2022 12:56:55 - INFO - codeparrot_training - Evaluating and saving model checkpoint
-03/04/2022 12:57:09 - WARNING - huggingface_hub.repository - Several commits (4) will be pushed upstream.
-03/04/2022 12:57:09 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
-03/04/2022 12:57:32 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/cm_code_clippy
-   7d4fba8..3033721  glowing-puddle-3 -> glowing-puddle-3
-
-03/04/2022 12:57:36 - INFO - codeparrot_training - Step 20000: {'lr': 0.0004819722568241274, 'samples': 10240512, 'steps': 20000, 'loss/train': 1.6575286388397217}
-03/04/2022 12:57:36 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/04/2022 12:57:41 - INFO - codeparrot_training - Step 20001: {'lr': 0.0004819702781178601, 'samples': 10241024, 'steps': 20001, 'loss/train': 2.603853702545166}
-03/04/2022 12:57:44 - INFO - codeparrot_training - Step 20002: {'lr': 0.00048196829930707066, 'samples': 10241536, 'steps': 20002, 'loss/train': 1.8656319379806519}
-03/04/2022 12:57:45 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/04/2022 12:57:50 - INFO - codeparrot_training - Step 20003: {'lr': 0.0004819663203917599, 'samples': 10242048, 'steps': 20003, 'loss/train': 1.3059179782867432}
-03/04/2022 12:57:53 - INFO - codeparrot_training - Step 20004: {'lr': 0.0004819643413719287, 'samples': 10242560, 'steps': 20004, 'loss/train': 1.2890772819519043}
-03/04/2022 12:57:55 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/04/2022 12:57:59 - INFO - codeparrot_training - Step 20005: {'lr': 0.0004819623622475779, 'samples': 10243072, 'steps': 20005, 'loss/train': 2.073068380355835}
-03/04/2022 12:58:02 - INFO - codeparrot_training - Step 20006: {'lr': 0.00048196038301870847, 'samples': 10243584, 'steps': 20006, 'loss/train': 2.0313401222229004}
-03/04/2022 12:58:04 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 12:58:07 - INFO - codeparrot_training - Step 20007: {'lr': 0.0004819584036853212, 'samples': 10244096, 'steps': 20007, 'loss/train': 2.538348913192749}
-03/04/2022 12:58:10 - INFO - codeparrot_training - Step 20008: {'lr': 0.00048195642424741716, 'samples': 10244608, 'steps': 20008, 'loss/train': 2.657820224761963}
-03/04/2022 12:58:13 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 12:58:16 - INFO - codeparrot_training - Step 20009: {'lr': 0.00048195444470499704, 'samples': 10245120, 'steps': 20009, 'loss/train': 2.204522132873535}
-03/04/2022 12:58:19 - INFO - codeparrot_training - Step 20010: {'lr': 0.0004819524650580619, 'samples': 10245632, 'steps': 20010, 'loss/train': 2.578894853591919}
-03/04/2022 12:58:21 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 12:58:24 - INFO - codeparrot_training - Step 20011: {'lr': 0.0004819504853066126, 'samples': 10246144, 'steps': 20011, 'loss/train': 1.9453705549240112}
-03/04/2022 12:58:27 - INFO - codeparrot_training - Step 20012: {'lr': 0.0004819485054506498, 'samples': 10246656, 'steps': 20012, 'loss/train': 2.286206007003784}
-03/04/2022 12:58:30 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 12:58:33 - INFO - codeparrot_training - Step 20013: {'lr': 0.00048194652549017484, 'samples': 10247168, 'steps': 20013, 'loss/train': 2.0102620124816895}
-03/04/2022 12:58:36 - INFO - codeparrot_training - Step 20014: {'lr': 0.0004819445454251882, 'samples': 10247680, 'steps': 20014, 'loss/train': 2.317781925201416}
-03/04/2022 12:58:39 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/04/2022 12:58:41 - INFO - codeparrot_training - Step 20015: {'lr': 0.0004819425652556909, 'samples': 10248192, 'steps': 20015, 'loss/train': 1.2648102045059204}
-03/04/2022 12:58:44 - INFO - codeparrot_training - Step 20016: {'lr': 0.0004819405849816839, 'samples': 10248704, 'steps': 20016, 'loss/train': 1.5415961742401123}
-03/04/2022 12:58:47 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 12:58:50 - INFO - codeparrot_training - Step 20017: {'lr': 0.00048193860460316805, 'samples': 10249216, 'steps': 20017, 'loss/train': 2.311629295349121}
-03/04/2022 12:58:53 - INFO - codeparrot_training - Step 20018: {'lr': 0.00048193662412014427, 'samples': 10249728, 'steps': 20018, 'loss/train': 1.4635286331176758}
-03/04/2022 12:58:56 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/04/2022 12:58:58 - INFO - codeparrot_training - Step 20019: {'lr': 0.0004819346435326134, 'samples': 10250240, 'steps': 20019, 'loss/train': 0.2795967161655426}
-03/04/2022 12:59:01 - INFO - codeparrot_training - Step 20020: {'lr': 0.00048193266284057634, 'samples': 10250752, 'steps': 20020, 'loss/train': 1.7154669761657715}
-03/04/2022 12:59:05 - INFO - codeparrot_training - Step 20021: {'lr': 0.0004819306820440341, 'samples': 10251264, 'steps': 20021, 'loss/train': 1.126009464263916}
-03/04/2022 12:59:05 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/04/2022 12:59:10 - INFO - codeparrot_training - Step 20022: {'lr': 0.0004819287011429874, 'samples': 10251776, 'steps': 20022, 'loss/train': 0.5634230375289917}
-03/04/2022 12:59:13 - INFO - codeparrot_training - Step 20023: {'lr': 0.0004819267201374372, 'samples': 10252288, 'steps': 20023, 'loss/train': 2.269754648208618}
-03/04/2022 12:59:14 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/04/2022 12:59:18 - INFO - codeparrot_training - Step 20024: {'lr': 0.0004819247390273844, 'samples': 10252800, 'steps': 20024, 'loss/train': 2.016040086746216}
-03/04/2022 12:59:21 - INFO - codeparrot_training - Step 20025: {'lr': 0.00048192275781282993, 'samples': 10253312, 'steps': 20025, 'loss/train': 1.7799144983291626}
-03/04/2022 12:59:22 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 12:59:27 - INFO - codeparrot_training - Step 20026: {'lr': 0.00048192077649377455, 'samples': 10253824, 'steps': 20026, 'loss/train': 1.4315651655197144}
-03/04/2022 12:59:30 - INFO - codeparrot_training - Step 20027: {'lr': 0.0004819187950702193, 'samples': 10254336, 'steps': 20027, 'loss/train': 1.9015066623687744}
-03/04/2022 12:59:31 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 12:59:35 - INFO - codeparrot_training - Step 20028: {'lr': 0.00048191681354216504, 'samples': 10254848, 'steps': 20028, 'loss/train': 1.982316255569458}
-03/04/2022 12:59:38 - INFO - codeparrot_training - Step 20029: {'lr': 0.0004819148319096126, 'samples': 10255360, 'steps': 20029, 'loss/train': 1.954868197441101}
-03/04/2022 12:59:39 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 12:59:44 - INFO - codeparrot_training - Step 20030: {'lr': 0.00048191285017256297, 'samples': 10255872, 'steps': 20030, 'loss/train': 1.918177604675293}
-03/04/2022 12:59:47 - INFO - codeparrot_training - Step 20031: {'lr': 0.00048191086833101695, 'samples': 10256384, 'steps': 20031, 'loss/train': 2.029825448989868}
-03/04/2022 12:59:48 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 12:59:52 - INFO - codeparrot_training - Step 20032: {'lr': 0.00048190888638497553, 'samples': 10256896, 'steps': 20032, 'loss/train': 2.1189045906066895}
-03/04/2022 12:59:55 - INFO - codeparrot_training - Step 20033: {'lr': 0.00048190690433443946, 'samples': 10257408, 'steps': 20033, 'loss/train': 2.132322311401367}
-03/04/2022 12:59:56 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/04/2022 13:00:01 - INFO - codeparrot_training - Step 20034: {'lr': 0.0004819049221794097, 'samples': 10257920, 'steps': 20034, 'loss/train': 1.5557727813720703}
-03/04/2022 13:00:04 - INFO - codeparrot_training - Step 20035: {'lr': 0.0004819029399198873, 'samples': 10258432, 'steps': 20035, 'loss/train': 2.551872968673706}
-03/04/2022 13:00:05 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 13:00:09 - INFO - codeparrot_training - Step 20036: {'lr': 0.0004819009575558729, 'samples': 10258944, 'steps': 20036, 'loss/train': 1.3711940050125122}
-03/04/2022 13:00:12 - INFO - codeparrot_training - Step 20037: {'lr': 0.0004818989750873676, 'samples': 10259456, 'steps': 20037, 'loss/train': 0.147262305021286}
-03/04/2022 13:00:13 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/04/2022 13:00:17 - INFO - codeparrot_training - Step 20038: {'lr': 0.00048189699251437206, 'samples': 10259968, 'steps': 20038, 'loss/train': 1.6891417503356934}
-03/04/2022 13:00:21 - INFO - codeparrot_training - Step 20039: {'lr': 0.0004818950098368874, 'samples': 10260480, 'steps': 20039, 'loss/train': 2.598771095275879}
-03/04/2022 13:00:22 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/04/2022 13:00:26 - INFO - codeparrot_training - Step 20040: {'lr': 0.00048189302705491446, 'samples': 10260992, 'steps': 20040, 'loss/train': 2.1570889949798584}
-03/04/2022 13:00:29 - INFO - codeparrot_training - Step 20041: {'lr': 0.000481891044168454, 'samples': 10261504, 'steps': 20041, 'loss/train': 3.5457839965820312}
-03/04/2022 13:00:30 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 13:00:35 - INFO - codeparrot_training - Step 20042: {'lr': 0.00048188906117750706, 'samples': 10262016, 'steps': 20042, 'loss/train': 1.9421305656433105}
-03/04/2022 13:00:38 - INFO - codeparrot_training - Step 20043: {'lr': 0.00048188707808207457, 'samples': 10262528, 'steps': 20043, 'loss/train': 1.1323516368865967}
-03/04/2022 13:00:39 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/04/2022 13:00:43 - INFO - codeparrot_training - Step 20044: {'lr': 0.00048188509488215724, 'samples': 10263040, 'steps': 20044, 'loss/train': 1.6568485498428345}
-03/04/2022 13:00:46 - INFO - codeparrot_training - Step 20045: {'lr': 0.0004818831115777561, 'samples': 10263552, 'steps': 20045, 'loss/train': 2.068376302719116}
-03/04/2022 13:00:47 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 13:00:52 - INFO - codeparrot_training - Step 20046: {'lr': 0.00048188112816887203, 'samples': 10264064, 'steps': 20046, 'loss/train': 2.6807892322540283}
-03/04/2022 13:00:55 - INFO - codeparrot_training - Step 20047: {'lr': 0.0004818791446555059, 'samples': 10264576, 'steps': 20047, 'loss/train': 2.1022512912750244}
-03/04/2022 13:00:56 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/04/2022 13:01:00 - INFO - codeparrot_training - Step 20048: {'lr': 0.00048187716103765854, 'samples': 10265088, 'steps': 20048, 'loss/train': 1.0668904781341553}
-03/04/2022 13:01:04 - INFO - codeparrot_training - Step 20049: {'lr': 0.0004818751773153309, 'samples': 10265600, 'steps': 20049, 'loss/train': 1.9260876178741455}
-03/04/2022 13:01:06 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/04/2022 13:01:09 - INFO - codeparrot_training - Step 20050: {'lr': 0.000481873193488524, 'samples': 10266112, 'steps': 20050, 'loss/train': 1.8349353075027466}
-03/04/2022 13:01:12 - INFO - codeparrot_training - Step 20051: {'lr': 0.0004818712095572385, 'samples': 10266624, 'steps': 20051, 'loss/train': 1.828360915184021}
-03/04/2022 13:01:14 - INFO - codeparrot_training - Skipping example with length 7 (seq_length=1024)
-03/04/2022 13:01:17 - INFO - codeparrot_training - Step 20052: {'lr': 0.0004818692255214755, 'samples': 10267136, 'steps': 20052, 'loss/train': 0.5336731672286987}
-03/04/2022 13:01:21 - INFO - codeparrot_training - Step 20053: {'lr': 0.00048186724138123577, 'samples': 10267648, 'steps': 20053, 'loss/train': 3.193540334701538}
-03/04/2022 13:01:22 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 13:01:26 - INFO - codeparrot_training - Step 20054: {'lr': 0.00048186525713652024, 'samples': 10268160, 'steps': 20054, 'loss/train': 2.0249836444854736}
-03/04/2022 13:01:29 - INFO - codeparrot_training - Step 20055: {'lr': 0.0004818632727873298, 'samples': 10268672, 'steps': 20055, 'loss/train': 0.8536461591720581}
-03/04/2022 13:01:30 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/04/2022 13:01:34 - INFO - codeparrot_training - Step 20056: {'lr': 0.00048186128833366536, 'samples': 10269184, 'steps': 20056, 'loss/train': 1.551547646522522}
-03/04/2022 13:01:37 - INFO - codeparrot_training - Step 20057: {'lr': 0.0004818593037755278, 'samples': 10269696, 'steps': 20057, 'loss/train': 1.8232673406600952}
-03/04/2022 13:01:39 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/04/2022 13:01:43 - INFO - codeparrot_training - Step 20058: {'lr': 0.000481857319112918, 'samples': 10270208, 'steps': 20058, 'loss/train': 1.820905089378357}
-03/04/2022 13:01:46 - INFO - codeparrot_training - Step 20059: {'lr': 0.0004818553343458368, 'samples': 10270720, 'steps': 20059, 'loss/train': 2.261099338531494}
-03/04/2022 13:01:47 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/04/2022 13:01:51 - INFO - codeparrot_training - Step 20060: {'lr': 0.00048185334947428525, 'samples': 10271232, 'steps': 20060, 'loss/train': 1.95997154712677}
-03/04/2022 13:01:54 - INFO - codeparrot_training - Step 20061: {'lr': 0.0004818513644982642, 'samples': 10271744, 'steps': 20061, 'loss/train': 1.8718122243881226}
-03/04/2022 13:01:56 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/04/2022 13:02:00 - INFO - codeparrot_training - Step 20062: {'lr': 0.0004818493794177744, 'samples': 10272256, 'steps': 20062, 'loss/train': 1.9540126323699951}
-03/04/2022 13:02:03 - INFO - codeparrot_training - Step 20063: {'lr': 0.00048184739423281695, 'samples': 10272768, 'steps': 20063, 'loss/train': 1.9549976587295532}
-03/04/2022 13:02:04 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 13:02:08 - INFO - codeparrot_training - Step 20064: {'lr': 0.00048184540894339256, 'samples': 10273280, 'steps': 20064, 'loss/train': 2.454415798187256}
-03/04/2022 13:02:11 - INFO - codeparrot_training - Step 20065: {'lr': 0.00048184342354950225, 'samples': 10273792, 'steps': 20065, 'loss/train': 1.5750740766525269}
-03/04/2022 13:02:13 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 13:02:17 - INFO - codeparrot_training - Step 20066: {'lr': 0.00048184143805114684, 'samples': 10274304, 'steps': 20066, 'loss/train': 1.4278597831726074}
-03/04/2022 13:02:20 - INFO - codeparrot_training - Step 20067: {'lr': 0.00048183945244832725, 'samples': 10274816, 'steps': 20067, 'loss/train': 1.3187370300292969}
-03/04/2022 13:02:22 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 13:02:25 - INFO - codeparrot_training - Step 20068: {'lr': 0.00048183746674104446, 'samples': 10275328, 'steps': 20068, 'loss/train': 2.2554614543914795}
-03/04/2022 13:02:28 - INFO - codeparrot_training - Step 20069: {'lr': 0.00048183548092929916, 'samples': 10275840, 'steps': 20069, 'loss/train': 1.1259300708770752}
-03/04/2022 13:02:30 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/04/2022 13:02:34 - INFO - codeparrot_training - Step 20070: {'lr': 0.0004818334950130925, 'samples': 10276352, 'steps': 20070, 'loss/train': 1.6540038585662842}
-03/04/2022 13:02:37 - INFO - codeparrot_training - Step 20071: {'lr': 0.00048183150899242514, 'samples': 10276864, 'steps': 20071, 'loss/train': 1.6608667373657227}
-03/04/2022 13:02:39 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 13:02:42 - INFO - codeparrot_training - Step 20072: {'lr': 0.0004818295228672981, 'samples': 10277376, 'steps': 20072, 'loss/train': 0.9173825979232788}
-03/04/2022 13:02:45 - INFO - codeparrot_training - Step 20073: {'lr': 0.0004818275366377123, 'samples': 10277888, 'steps': 20073, 'loss/train': 2.0447678565979004}
-03/04/2022 13:02:47 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/04/2022 13:02:51 - INFO - codeparrot_training - Step 20074: {'lr': 0.00048182555030366854, 'samples': 10278400, 'steps': 20074, 'loss/train': 1.6849154233932495}
-03/04/2022 13:02:54 - INFO - codeparrot_training - Step 20075: {'lr': 0.0004818235638651678, 'samples': 10278912, 'steps': 20075, 'loss/train': 0.7425598502159119}
-03/04/2022 13:02:56 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/04/2022 13:02:59 - INFO - codeparrot_training - Step 20076: {'lr': 0.0004818215773222109, 'samples': 10279424, 'steps': 20076, 'loss/train': 1.851235032081604}
-03/04/2022 13:03:02 - INFO - codeparrot_training - Step 20077: {'lr': 0.0004818195906747988, 'samples': 10279936, 'steps': 20077, 'loss/train': 2.7639236450195312}
-03/04/2022 13:03:04 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/04/2022 13:03:08 - INFO - codeparrot_training - Step 20078: {'lr': 0.0004818176039229324, 'samples': 10280448, 'steps': 20078, 'loss/train': 1.697530746459961}
-03/04/2022 13:03:11 - INFO - codeparrot_training - Step 20079: {'lr': 0.0004818156170666125, 'samples': 10280960, 'steps': 20079, 'loss/train': 2.0468196868896484}
-03/04/2022 13:03:13 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 13:03:16 - INFO - codeparrot_training - Step 20080: {'lr': 0.0004818136301058401, 'samples': 10281472, 'steps': 20080, 'loss/train': 1.2681143283843994}
-03/04/2022 13:03:19 - INFO - codeparrot_training - Step 20081: {'lr': 0.0004818116430406161, 'samples': 10281984, 'steps': 20081, 'loss/train': 2.1994969844818115}
-03/04/2022 13:03:21 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 13:03:25 - INFO - codeparrot_training - Step 20082: {'lr': 0.00048180965587094125, 'samples': 10282496, 'steps': 20082, 'loss/train': 1.341614007949829}
-03/04/2022 13:03:28 - INFO - codeparrot_training - Step 20083: {'lr': 0.00048180766859681664, 'samples': 10283008, 'steps': 20083, 'loss/train': 1.024436354637146}
-03/04/2022 13:03:31 - INFO - codeparrot_training - Step 20084: {'lr': 0.000481805681218243, 'samples': 10283520, 'steps': 20084, 'loss/train': 1.46431565284729}
-03/04/2022 13:03:31 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/04/2022 13:03:36 - INFO - codeparrot_training - Step 20085: {'lr': 0.0004818036937352214, 'samples': 10284032, 'steps': 20085, 'loss/train': 1.140002965927124}
-03/04/2022 13:03:40 - INFO - codeparrot_training - Step 20086: {'lr': 0.0004818017061477525, 'samples': 10284544, 'steps': 20086, 'loss/train': 2.3306374549865723}
-03/04/2022 13:03:40 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/04/2022 13:03:45 - INFO - codeparrot_training - Step 20087: {'lr': 0.00048179971845583734, 'samples': 10285056, 'steps': 20087, 'loss/train': 1.966194987297058}
-03/04/2022 13:03:48 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 13:03:50 - INFO - codeparrot_training - Step 20088: {'lr': 0.00048179773065947683, 'samples': 10285568, 'steps': 20088, 'loss/train': 2.0812532901763916}
-03/04/2022 13:03:53 - INFO - codeparrot_training - Step 20089: {'lr': 0.0004817957427586719, 'samples': 10286080, 'steps': 20089, 'loss/train': 2.00014591217041}
-03/04/2022 13:03:56 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/04/2022 13:03:58 - INFO - codeparrot_training - Step 20090: {'lr': 0.00048179375475342333, 'samples': 10286592, 'steps': 20090, 'loss/train': 1.510907769203186}
-03/04/2022 13:04:02 - INFO - codeparrot_training - Step 20091: {'lr': 0.00048179176664373214, 'samples': 10287104, 'steps': 20091, 'loss/train': 2.672574758529663}
-03/04/2022 13:04:04 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 13:04:07 - INFO - codeparrot_training - Step 20092: {'lr': 0.0004817897784295991, 'samples': 10287616, 'steps': 20092, 'loss/train': 1.299666404724121}
-03/04/2022 13:04:10 - INFO - codeparrot_training - Step 20093: {'lr': 0.0004817877901110251, 'samples': 10288128, 'steps': 20093, 'loss/train': 1.459531545639038}
-03/04/2022 13:04:13 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/04/2022 13:04:15 - INFO - codeparrot_training - Step 20094: {'lr': 0.0004817858016880112, 'samples': 10288640, 'steps': 20094, 'loss/train': 2.0033960342407227}
-03/04/2022 13:04:18 - INFO - codeparrot_training - Step 20095: {'lr': 0.0004817838131605582, 'samples': 10289152, 'steps': 20095, 'loss/train': 1.1471773386001587}
-03/04/2022 13:04:21 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/04/2022 13:04:24 - INFO - codeparrot_training - Step 20096: {'lr': 0.00048178182452866694, 'samples': 10289664, 'steps': 20096, 'loss/train': 1.3958827257156372}
-03/04/2022 13:04:27 - INFO - codeparrot_training - Step 20097: {'lr': 0.0004817798357923384, 'samples': 10290176, 'steps': 20097, 'loss/train': 1.8693748712539673}
-03/04/2022 13:04:30 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/04/2022 13:04:32 - INFO - codeparrot_training - Step 20098: {'lr': 0.00048177784695157335, 'samples': 10290688, 'steps': 20098, 'loss/train': 1.9797894954681396}
-03/04/2022 13:04:35 - INFO - codeparrot_training - Step 20099: {'lr': 0.00048177585800637286, 'samples': 10291200, 'steps': 20099, 'loss/train': 1.9770817756652832}
-03/04/2022 13:04:38 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 13:04:40 - INFO - codeparrot_training - Step 20100: {'lr': 0.00048177386895673774, 'samples': 10291712, 'steps': 20100, 'loss/train': 1.1254260540008545}
-03/04/2022 13:04:44 - INFO - codeparrot_training - Step 20101: {'lr': 0.0004817718798026689, 'samples': 10292224, 'steps': 20101, 'loss/train': 2.1793744564056396}
-03/04/2022 13:04:46 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/04/2022 13:04:49 - INFO - codeparrot_training - Step 20102: {'lr': 0.0004817698905441672, 'samples': 10292736, 'steps': 20102, 'loss/train': 2.199984550476074}
-03/04/2022 13:04:52 - INFO - codeparrot_training - Step 20103: {'lr': 0.0004817679011812336, 'samples': 10293248, 'steps': 20103, 'loss/train': 1.8419699668884277}
-03/04/2022 13:04:55 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/04/2022 13:04:57 - INFO - codeparrot_training - Step 20104: {'lr': 0.00048176591171386884, 'samples': 10293760, 'steps': 20104, 'loss/train': 1.6900770664215088}
-03/04/2022 13:05:00 - INFO - codeparrot_training - Step 20105: {'lr': 0.0004817639221420741, 'samples': 10294272, 'steps': 20105, 'loss/train': 1.9167472124099731}
-03/04/2022 13:05:03 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 13:05:06 - INFO - codeparrot_training - Step 20106: {'lr': 0.00048176193246585, 'samples': 10294784, 'steps': 20106, 'loss/train': 2.16170072555542}
-03/04/2022 13:05:09 - INFO - codeparrot_training - Step 20107: {'lr': 0.00048175994268519765, 'samples': 10295296, 'steps': 20107, 'loss/train': 1.8333518505096436}
-03/04/2022 13:05:12 - INFO - codeparrot_training - Step 20108: {'lr': 0.00048175795280011775, 'samples': 10295808, 'steps': 20108, 'loss/train': 1.4512406587600708}
-03/04/2022 13:05:12 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/04/2022 13:05:18 - INFO - codeparrot_training - Step 20109: {'lr': 0.00048175596281061135, 'samples': 10296320, 'steps': 20109, 'loss/train': 2.8230700492858887}
-03/04/2022 13:05:21 - INFO - codeparrot_training - Step 20110: {'lr': 0.00048175397271667925, 'samples': 10296832, 'steps': 20110, 'loss/train': 1.7583922147750854}
-03/04/2022 13:05:21 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/04/2022 13:05:26 - INFO - codeparrot_training - Step 20111: {'lr': 0.00048175198251832244, 'samples': 10297344, 'steps': 20111, 'loss/train': 1.7755942344665527}
-03/04/2022 13:05:29 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/04/2022 13:05:31 - INFO - codeparrot_training - Step 20112: {'lr': 0.00048174999221554173, 'samples': 10297856, 'steps': 20112, 'loss/train': 2.415696859359741}
-03/04/2022 13:05:35 - INFO - codeparrot_training - Step 20113: {'lr': 0.000481748001808338, 'samples': 10298368, 'steps': 20113, 'loss/train': 2.4323534965515137}
-03/04/2022 13:05:37 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 13:05:40 - INFO - codeparrot_training - Step 20114: {'lr': 0.00048174601129671223, 'samples': 10298880, 'steps': 20114, 'loss/train': 1.8854634761810303}
-03/04/2022 13:05:43 - INFO - codeparrot_training - Step 20115: {'lr': 0.00048174402068066534, 'samples': 10299392, 'steps': 20115, 'loss/train': 0.9546204209327698}
-03/04/2022 13:05:46 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/04/2022 13:05:48 - INFO - codeparrot_training - Step 20116: {'lr': 0.0004817420299601981, 'samples': 10299904, 'steps': 20116, 'loss/train': 0.9483279585838318}
-03/04/2022 13:05:51 - INFO - codeparrot_training - Step 20117: {'lr': 0.0004817400391353115, 'samples': 10300416, 'steps': 20117, 'loss/train': 0.5516338348388672}
-03/04/2022 13:05:54 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/04/2022 13:05:57 - INFO - codeparrot_training - Step 20118: {'lr': 0.00048173804820600646, 'samples': 10300928, 'steps': 20118, 'loss/train': 1.8890305757522583}
-03/04/2022 13:06:00 - INFO - codeparrot_training - Step 20119: {'lr': 0.0004817360571722838, 'samples': 10301440, 'steps': 20119, 'loss/train': 2.0130345821380615}
-03/04/2022 13:06:02 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/04/2022 13:06:05 - INFO - codeparrot_training - Step 20120: {'lr': 0.00048173406603414445, 'samples': 10301952, 'steps': 20120, 'loss/train': 1.9464830160140991}
-03/04/2022 13:06:08 - INFO - codeparrot_training - Step 20121: {'lr': 0.00048173207479158933, 'samples': 10302464, 'steps': 20121, 'loss/train': 1.805264949798584}
-03/04/2022 13:06:11 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 13:06:13 - INFO - codeparrot_training - Step 20122: {'lr': 0.0004817300834446192, 'samples': 10302976, 'steps': 20122, 'loss/train': 2.198972225189209}
-03/04/2022 13:06:17 - INFO - codeparrot_training - Step 20123: {'lr': 0.0004817280919932352, 'samples': 10303488, 'steps': 20123, 'loss/train': 2.301971197128296}
-03/04/2022 13:06:19 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/04/2022 13:06:22 - INFO - codeparrot_training - Step 20124: {'lr': 0.000481726100437438, 'samples': 10304000, 'steps': 20124, 'loss/train': 1.30559241771698}
-03/04/2022 13:06:25 - INFO - codeparrot_training - Step 20125: {'lr': 0.00048172410877722865, 'samples': 10304512, 'steps': 20125, 'loss/train': 1.7633129358291626}
-03/04/2022 13:06:27 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 13:06:30 - INFO - codeparrot_training - Step 20126: {'lr': 0.00048172211701260807, 'samples': 10305024, 'steps': 20126, 'loss/train': 1.035833716392517}
-03/04/2022 13:06:33 - INFO - codeparrot_training - Step 20127: {'lr': 0.0004817201251435769, 'samples': 10305536, 'steps': 20127, 'loss/train': 1.7589365243911743}
-03/04/2022 13:06:36 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 13:06:39 - INFO - codeparrot_training - Step 20128: {'lr': 0.00048171813317013633, 'samples': 10306048, 'steps': 20128, 'loss/train': 1.0727430582046509}
-03/04/2022 13:06:42 - INFO - codeparrot_training - Step 20129: {'lr': 0.00048171614109228714, 'samples': 10306560, 'steps': 20129, 'loss/train': 2.10495662689209}
-03/04/2022 13:06:45 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 13:06:47 - INFO - codeparrot_training - Step 20130: {'lr': 0.0004817141489100302, 'samples': 10307072, 'steps': 20130, 'loss/train': 2.4750287532806396}
-03/04/2022 13:06:50 - INFO - codeparrot_training - Step 20131: {'lr': 0.0004817121566233665, 'samples': 10307584, 'steps': 20131, 'loss/train': 1.5406067371368408}
-03/04/2022 13:06:53 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/04/2022 13:06:56 - INFO - codeparrot_training - Step 20132: {'lr': 0.0004817101642322968, 'samples': 10308096, 'steps': 20132, 'loss/train': 1.4651095867156982}
-03/04/2022 13:06:59 - INFO - codeparrot_training - Step 20133: {'lr': 0.00048170817173682215, 'samples': 10308608, 'steps': 20133, 'loss/train': 1.4553554058074951}
-03/04/2022 13:07:02 - INFO - codeparrot_training - Step 20134: {'lr': 0.00048170617913694333, 'samples': 10309120, 'steps': 20134, 'loss/train': 2.036808490753174}
-03/04/2022 13:07:03 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 13:07:07 - INFO - codeparrot_training - Step 20135: {'lr': 0.00048170418643266125, 'samples': 10309632, 'steps': 20135, 'loss/train': 2.0080301761627197}
-03/04/2022 13:07:10 - INFO - codeparrot_training - Step 20136: {'lr': 0.00048170219362397685, 'samples': 10310144, 'steps': 20136, 'loss/train': 1.347101092338562}
-03/04/2022 13:07:11 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/04/2022 13:07:16 - INFO - codeparrot_training - Step 20137: {'lr': 0.00048170020071089105, 'samples': 10310656, 'steps': 20137, 'loss/train': 4.991723537445068}
-03/04/2022 13:07:19 - INFO - codeparrot_training - Step 20138: {'lr': 0.00048169820769340476, 'samples': 10311168, 'steps': 20138, 'loss/train': 1.162432312965393}
-03/04/2022 13:07:20 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/04/2022 13:07:24 - INFO - codeparrot_training - Step 20139: {'lr': 0.0004816962145715188, 'samples': 10311680, 'steps': 20139, 'loss/train': 1.8139748573303223}
-03/04/2022 13:07:28 - INFO - codeparrot_training - Step 20140: {'lr': 0.00048169422134523404, 'samples': 10312192, 'steps': 20140, 'loss/train': 2.475980520248413}
-03/04/2022 13:07:28 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/04/2022 13:07:33 - INFO - codeparrot_training - Step 20141: {'lr': 0.0004816922280145515, 'samples': 10312704, 'steps': 20141, 'loss/train': 1.9039881229400635}
-03/04/2022 13:07:36 - INFO - codeparrot_training - Step 20142: {'lr': 0.00048169023457947195, 'samples': 10313216, 'steps': 20142, 'loss/train': 1.8672627210617065}
-03/04/2022 13:07:37 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 13:07:41 - INFO - codeparrot_training - Step 20143: {'lr': 0.0004816882410399964, 'samples': 10313728, 'steps': 20143, 'loss/train': 2.564636707305908}
-03/04/2022 13:07:44 - INFO - codeparrot_training - Step 20144: {'lr': 0.00048168624739612577, 'samples': 10314240, 'steps': 20144, 'loss/train': 1.9907383918762207}
-03/04/2022 13:07:45 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/04/2022 13:07:50 - INFO - codeparrot_training - Step 20145: {'lr': 0.0004816842536478608, 'samples': 10314752, 'steps': 20145, 'loss/train': 1.6476013660430908}
-03/04/2022 13:07:53 - INFO - codeparrot_training - Step 20146: {'lr': 0.00048168225979520254, 'samples': 10315264, 'steps': 20146, 'loss/train': 1.472593069076538}
-03/04/2022 13:07:54 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 13:07:58 - INFO - codeparrot_training - Step 20147: {'lr': 0.0004816802658381518, 'samples': 10315776, 'steps': 20147, 'loss/train': 1.2078913450241089}
-03/04/2022 13:08:01 - INFO - codeparrot_training - Step 20148: {'lr': 0.00048167827177670946, 'samples': 10316288, 'steps': 20148, 'loss/train': 1.2442843914031982}
-03/04/2022 13:08:02 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/04/2022 13:08:07 - INFO - codeparrot_training - Step 20149: {'lr': 0.0004816762776108765, 'samples': 10316800, 'steps': 20149, 'loss/train': 2.3771984577178955}
-03/04/2022 13:08:10 - INFO - codeparrot_training - Step 20150: {'lr': 0.0004816742833406538, 'samples': 10317312, 'steps': 20150, 'loss/train': 1.1970820426940918}
-03/04/2022 13:08:11 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/04/2022 13:08:15 - INFO - codeparrot_training - Step 20151: {'lr': 0.0004816722889660423, 'samples': 10317824, 'steps': 20151, 'loss/train': 2.3721420764923096}
-03/04/2022 13:08:18 - INFO - codeparrot_training - Step 20152: {'lr': 0.00048167029448704273, 'samples': 10318336, 'steps': 20152, 'loss/train': 1.976988434791565}
-03/04/2022 13:08:19 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 13:08:24 - INFO - codeparrot_training - Step 20153: {'lr': 0.00048166829990365615, 'samples': 10318848, 'steps': 20153, 'loss/train': 2.734611988067627}
-03/04/2022 13:08:27 - INFO - codeparrot_training - Step 20154: {'lr': 0.0004816663052158834, 'samples': 10319360, 'steps': 20154, 'loss/train': 1.5984156131744385}
-03/04/2022 13:08:27 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 13:08:32 - INFO - codeparrot_training - Step 20155: {'lr': 0.0004816643104237254, 'samples': 10319872, 'steps': 20155, 'loss/train': 1.739317774772644}
-03/04/2022 13:08:35 - INFO - codeparrot_training - Step 20156: {'lr': 0.00048166231552718305, 'samples': 10320384, 'steps': 20156, 'loss/train': 3.2433419227600098}
-03/04/2022 13:08:36 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 13:08:40 - INFO - codeparrot_training - Step 20157: {'lr': 0.0004816603205262572, 'samples': 10320896, 'steps': 20157, 'loss/train': 2.416246175765991}
-03/04/2022 13:08:44 - INFO - codeparrot_training - Step 20158: {'lr': 0.0004816583254209488, 'samples': 10321408, 'steps': 20158, 'loss/train': 2.883939266204834}
-03/04/2022 13:08:45 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/04/2022 13:08:49 - INFO - codeparrot_training - Step 20159: {'lr': 0.00048165633021125874, 'samples': 10321920, 'steps': 20159, 'loss/train': 1.9856821298599243}
-03/04/2022 13:08:52 - INFO - codeparrot_training - Step 20160: {'lr': 0.0004816543348971879, 'samples': 10322432, 'steps': 20160, 'loss/train': 0.317841500043869}
-03/04/2022 13:08:54 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/04/2022 13:08:58 - INFO - codeparrot_training - Step 20161: {'lr': 0.0004816523394787372, 'samples': 10322944, 'steps': 20161, 'loss/train': 1.9499415159225464}
-03/04/2022 13:09:01 - INFO - codeparrot_training - Step 20162: {'lr': 0.00048165034395590756, 'samples': 10323456, 'steps': 20162, 'loss/train': 1.7060134410858154}
-03/04/2022 13:09:02 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 13:09:06 - INFO - codeparrot_training - Step 20163: {'lr': 0.0004816483483286998, 'samples': 10323968, 'steps': 20163, 'loss/train': 2.481736421585083}
-03/04/2022 13:09:09 - INFO - codeparrot_training - Step 20164: {'lr': 0.0004816463525971149, 'samples': 10324480, 'steps': 20164, 'loss/train': 1.8282256126403809}
-03/04/2022 13:09:11 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 13:09:15 - INFO - codeparrot_training - Step 20165: {'lr': 0.0004816443567611537, 'samples': 10324992, 'steps': 20165, 'loss/train': 2.4921884536743164}
-03/04/2022 13:09:18 - INFO - codeparrot_training - Step 20166: {'lr': 0.00048164236082081713, 'samples': 10325504, 'steps': 20166, 'loss/train': 1.69943368434906}
-03/04/2022 13:09:19 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 13:09:23 - INFO - codeparrot_training - Step 20167: {'lr': 0.00048164036477610616, 'samples': 10326016, 'steps': 20167, 'loss/train': 1.9492504596710205}
-03/04/2022 13:09:26 - INFO - codeparrot_training - Step 20168: {'lr': 0.00048163836862702154, 'samples': 10326528, 'steps': 20168, 'loss/train': 0.9991345405578613}
-03/04/2022 13:09:28 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 13:09:32 - INFO - codeparrot_training - Step 20169: {'lr': 0.0004816363723735643, 'samples': 10327040, 'steps': 20169, 'loss/train': 2.475334405899048}
-03/04/2022 13:09:35 - INFO - codeparrot_training - Step 20170: {'lr': 0.00048163437601573525, 'samples': 10327552, 'steps': 20170, 'loss/train': 1.964302897453308}
-03/04/2022 13:09:36 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/04/2022 13:09:40 - INFO - codeparrot_training - Step 20171: {'lr': 0.00048163237955353526, 'samples': 10328064, 'steps': 20171, 'loss/train': 1.1419132947921753}
-03/04/2022 13:09:43 - INFO - codeparrot_training - Step 20172: {'lr': 0.00048163038298696537, 'samples': 10328576, 'steps': 20172, 'loss/train': 2.510044813156128}
-03/04/2022 13:09:44 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 13:09:48 - INFO - codeparrot_training - Step 20173: {'lr': 0.00048162838631602643, 'samples': 10329088, 'steps': 20173, 'loss/train': 1.101884365081787}
-03/04/2022 13:09:52 - INFO - codeparrot_training - Step 20174: {'lr': 0.00048162638954071926, 'samples': 10329600, 'steps': 20174, 'loss/train': 1.9567729234695435}
-03/04/2022 13:09:53 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/04/2022 13:09:57 - INFO - codeparrot_training - Step 20175: {'lr': 0.0004816243926610448, 'samples': 10330112, 'steps': 20175, 'loss/train': 1.6369774341583252}
-03/04/2022 13:10:00 - INFO - codeparrot_training - Step 20176: {'lr': 0.000481622395677004, 'samples': 10330624, 'steps': 20176, 'loss/train': 1.3960374593734741}
-03/04/2022 13:10:01 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/04/2022 13:10:05 - INFO - codeparrot_training - Step 20177: {'lr': 0.0004816203985885977, 'samples': 10331136, 'steps': 20177, 'loss/train': 1.8416271209716797}
-03/04/2022 13:10:08 - INFO - codeparrot_training - Step 20178: {'lr': 0.0004816184013958268, 'samples': 10331648, 'steps': 20178, 'loss/train': 2.1183910369873047}
-03/04/2022 13:10:09 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 13:10:14 - INFO - codeparrot_training - Step 20179: {'lr': 0.0004816164040986923, 'samples': 10332160, 'steps': 20179, 'loss/train': 2.0789103507995605}
-03/04/2022 13:10:17 - INFO - codeparrot_training - Step 20180: {'lr': 0.00048161440669719496, 'samples': 10332672, 'steps': 20180, 'loss/train': 1.6821813583374023}
-03/04/2022 13:10:17 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 13:10:22 - INFO - codeparrot_training - Step 20181: {'lr': 0.00048161240919133573, 'samples': 10333184, 'steps': 20181, 'loss/train': 2.166088819503784}
-03/04/2022 13:10:25 - INFO - codeparrot_training - Step 20182: {'lr': 0.00048161041158111564, 'samples': 10333696, 'steps': 20182, 'loss/train': 1.8097742795944214}
-03/04/2022 13:10:26 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/04/2022 13:10:30 - INFO - codeparrot_training - Step 20183: {'lr': 0.0004816084138665353, 'samples': 10334208, 'steps': 20183, 'loss/train': 1.6145159006118774}
-03/04/2022 13:10:34 - INFO - codeparrot_training - Step 20184: {'lr': 0.00048160641604759593, 'samples': 10334720, 'steps': 20184, 'loss/train': 2.049403190612793}
-03/04/2022 13:10:34 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/04/2022 13:10:39 - INFO - codeparrot_training - Step 20185: {'lr': 0.0004816044181242982, 'samples': 10335232, 'steps': 20185, 'loss/train': 1.927978754043579}
-03/04/2022 13:10:42 - INFO - codeparrot_training - Step 20186: {'lr': 0.0004816024200966431, 'samples': 10335744, 'steps': 20186, 'loss/train': 1.9577816724777222}
-03/04/2022 13:10:43 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/04/2022 13:10:47 - INFO - codeparrot_training - Step 20187: {'lr': 0.00048160042196463153, 'samples': 10336256, 'steps': 20187, 'loss/train': 1.8856642246246338}
-03/04/2022 13:10:50 - INFO - codeparrot_training - Step 20188: {'lr': 0.00048159842372826446, 'samples': 10336768, 'steps': 20188, 'loss/train': 1.9664798974990845}
-03/04/2022 13:10:51 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/04/2022 13:10:56 - INFO - codeparrot_training - Step 20189: {'lr': 0.0004815964253875426, 'samples': 10337280, 'steps': 20189, 'loss/train': 2.6603853702545166}
-03/04/2022 13:10:59 - INFO - codeparrot_training - Step 20190: {'lr': 0.000481594426942467, 'samples': 10337792, 'steps': 20190, 'loss/train': 2.2537975311279297}
-03/04/2022 13:11:00 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 13:11:04 - INFO - codeparrot_training - Step 20191: {'lr': 0.0004815924283930385, 'samples': 10338304, 'steps': 20191, 'loss/train': 2.1698126792907715}
-03/04/2022 13:11:07 - INFO - codeparrot_training - Step 20192: {'lr': 0.0004815904297392582, 'samples': 10338816, 'steps': 20192, 'loss/train': 1.97845458984375}
-03/04/2022 13:11:08 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 13:11:13 - INFO - codeparrot_training - Step 20193: {'lr': 0.00048158843098112657, 'samples': 10339328, 'steps': 20193, 'loss/train': 1.9734463691711426}
-03/04/2022 13:11:16 - INFO - codeparrot_training - Step 20194: {'lr': 0.00048158643211864495, 'samples': 10339840, 'steps': 20194, 'loss/train': 2.654714822769165}
-03/04/2022 13:11:18 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 13:11:21 - INFO - codeparrot_training - Step 20195: {'lr': 0.000481584433151814, 'samples': 10340352, 'steps': 20195, 'loss/train': 1.906168818473816}
-03/04/2022 13:11:25 - INFO - codeparrot_training - Step 20196: {'lr': 0.00048158243408063465, 'samples': 10340864, 'steps': 20196, 'loss/train': 2.7094783782958984}
-03/04/2022 13:11:26 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 13:11:30 - INFO - codeparrot_training - Step 20197: {'lr': 0.0004815804349051078, 'samples': 10341376, 'steps': 20197, 'loss/train': 0.5238750576972961}
-03/04/2022 13:11:33 - INFO - codeparrot_training - Step 20198: {'lr': 0.0004815784356252344, 'samples': 10341888, 'steps': 20198, 'loss/train': 1.9689972400665283}
-03/04/2022 13:11:35 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 13:11:38 - INFO - codeparrot_training - Step 20199: {'lr': 0.0004815764362410154, 'samples': 10342400, 'steps': 20199, 'loss/train': 0.46228301525115967}
-03/04/2022 13:11:41 - INFO - codeparrot_training - Step 20200: {'lr': 0.0004815744367524516, 'samples': 10342912, 'steps': 20200, 'loss/train': 2.4215142726898193}
-03/04/2022 13:11:43 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/04/2022 13:11:47 - INFO - codeparrot_training - Step 20201: {'lr': 0.0004815724371595439, 'samples': 10343424, 'steps': 20201, 'loss/train': 1.6345268487930298}
-03/04/2022 13:11:50 - INFO - codeparrot_training - Step 20202: {'lr': 0.00048157043746229324, 'samples': 10343936, 'steps': 20202, 'loss/train': 1.781322956085205}
-03/04/2022 13:11:51 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/04/2022 13:11:55 - INFO - codeparrot_training - Step 20203: {'lr': 0.0004815684376607006, 'samples': 10344448, 'steps': 20203, 'loss/train': 2.2415480613708496}
-03/04/2022 13:11:58 - INFO - codeparrot_training - Step 20204: {'lr': 0.0004815664377547667, 'samples': 10344960, 'steps': 20204, 'loss/train': 1.5976799726486206}
-03/04/2022 13:12:00 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/04/2022 13:12:04 - INFO - codeparrot_training - Step 20205: {'lr': 0.00048156443774449254, 'samples': 10345472, 'steps': 20205, 'loss/train': 1.0402053594589233}
-03/04/2022 13:12:07 - INFO - codeparrot_training - Step 20206: {'lr': 0.00048156243762987905, 'samples': 10345984, 'steps': 20206, 'loss/train': 0.26645708084106445}
-03/04/2022 13:12:08 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 13:12:12 - INFO - codeparrot_training - Step 20207: {'lr': 0.00048156043741092705, 'samples': 10346496, 'steps': 20207, 'loss/train': 0.5832125544548035}
-03/04/2022 13:12:15 - INFO - codeparrot_training - Step 20208: {'lr': 0.00048155843708763755, 'samples': 10347008, 'steps': 20208, 'loss/train': 1.3667802810668945}
-03/04/2022 13:12:17 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/04/2022 13:12:20 - INFO - codeparrot_training - Step 20209: {'lr': 0.0004815564366600114, 'samples': 10347520, 'steps': 20209, 'loss/train': 1.5324790477752686}
-03/04/2022 13:12:24 - INFO - codeparrot_training - Step 20210: {'lr': 0.0004815544361280494, 'samples': 10348032, 'steps': 20210, 'loss/train': 1.0052947998046875}
-03/04/2022 13:12:26 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 13:12:29 - INFO - codeparrot_training - Step 20211: {'lr': 0.00048155243549175263, 'samples': 10348544, 'steps': 20211, 'loss/train': 1.9849969148635864}
-03/04/2022 13:12:32 - INFO - codeparrot_training - Step 20212: {'lr': 0.00048155043475112184, 'samples': 10349056, 'steps': 20212, 'loss/train': 2.4145913124084473}
-03/04/2022 13:12:34 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 13:12:37 - INFO - codeparrot_training - Step 20213: {'lr': 0.0004815484339061581, 'samples': 10349568, 'steps': 20213, 'loss/train': 1.6418592929840088}
-03/04/2022 13:12:40 - INFO - codeparrot_training - Step 20214: {'lr': 0.0004815464329568621, 'samples': 10350080, 'steps': 20214, 'loss/train': 2.285188913345337}
-03/04/2022 13:12:43 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/04/2022 13:12:46 - INFO - codeparrot_training - Step 20215: {'lr': 0.00048154443190323495, 'samples': 10350592, 'steps': 20215, 'loss/train': 1.8057971000671387}
-03/04/2022 13:12:49 - INFO - codeparrot_training - Step 20216: {'lr': 0.0004815424307452774, 'samples': 10351104, 'steps': 20216, 'loss/train': 2.2119946479797363}
-03/04/2022 13:12:51 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/04/2022 13:12:54 - INFO - codeparrot_training - Step 20217: {'lr': 0.0004815404294829904, 'samples': 10351616, 'steps': 20217, 'loss/train': 1.617721676826477}
-03/04/2022 13:12:57 - INFO - codeparrot_training - Step 20218: {'lr': 0.0004815384281163748, 'samples': 10352128, 'steps': 20218, 'loss/train': 1.3031798601150513}
-03/04/2022 13:13:00 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/04/2022 13:13:03 - INFO - codeparrot_training - Step 20219: {'lr': 0.0004815364266454316, 'samples': 10352640, 'steps': 20219, 'loss/train': 1.5227128267288208}
-03/04/2022 13:13:06 - INFO - codeparrot_training - Step 20220: {'lr': 0.00048153442507016173, 'samples': 10353152, 'steps': 20220, 'loss/train': 1.3807380199432373}
-03/04/2022 13:13:08 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/04/2022 13:13:11 - INFO - codeparrot_training - Step 20221: {'lr': 0.00048153242339056594, 'samples': 10353664, 'steps': 20221, 'loss/train': 2.0320663452148438}
-03/04/2022 13:13:14 - INFO - codeparrot_training - Step 20222: {'lr': 0.0004815304216066453, 'samples': 10354176, 'steps': 20222, 'loss/train': 1.5758334398269653}
-03/04/2022 13:13:16 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 13:13:19 - INFO - codeparrot_training - Step 20223: {'lr': 0.0004815284197184005, 'samples': 10354688, 'steps': 20223, 'loss/train': 2.03945255279541}
-03/04/2022 13:13:23 - INFO - codeparrot_training - Step 20224: {'lr': 0.0004815264177258326, 'samples': 10355200, 'steps': 20224, 'loss/train': 1.8572531938552856}
-03/04/2022 13:13:25 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/04/2022 13:13:28 - INFO - codeparrot_training - Step 20225: {'lr': 0.00048152441562894255, 'samples': 10355712, 'steps': 20225, 'loss/train': 2.2414445877075195}
-03/04/2022 13:13:31 - INFO - codeparrot_training - Step 20226: {'lr': 0.0004815224134277311, 'samples': 10356224, 'steps': 20226, 'loss/train': 1.9176788330078125}
-03/04/2022 13:13:33 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/04/2022 13:13:36 - INFO - codeparrot_training - Step 20227: {'lr': 0.00048152041112219926, 'samples': 10356736, 'steps': 20227, 'loss/train': 2.175896406173706}
-03/04/2022 13:13:39 - INFO - codeparrot_training - Step 20228: {'lr': 0.0004815184087123479, 'samples': 10357248, 'steps': 20228, 'loss/train': 2.489959716796875}
-03/04/2022 13:13:41 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/04/2022 13:13:45 - INFO - codeparrot_training - Step 20229: {'lr': 0.0004815164061981778, 'samples': 10357760, 'steps': 20229, 'loss/train': 2.494072675704956}
-03/04/2022 13:13:48 - INFO - codeparrot_training - Step 20230: {'lr': 0.0004815144035796901, 'samples': 10358272, 'steps': 20230, 'loss/train': 1.5134727954864502}
-03/04/2022 13:13:50 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 13:13:53 - INFO - codeparrot_training - Step 20231: {'lr': 0.0004815124008568856, 'samples': 10358784, 'steps': 20231, 'loss/train': 1.9387024641036987}
-03/04/2022 13:13:56 - INFO - codeparrot_training - Step 20232: {'lr': 0.00048151039802976517, 'samples': 10359296, 'steps': 20232, 'loss/train': 3.3582944869995117}
-03/04/2022 13:13:59 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/04/2022 13:14:02 - INFO - codeparrot_training - Step 20233: {'lr': 0.00048150839509832966, 'samples': 10359808, 'steps': 20233, 'loss/train': 1.329757809638977}
-03/04/2022 13:14:05 - INFO - codeparrot_training - Step 20234: {'lr': 0.0004815063920625801, 'samples': 10360320, 'steps': 20234, 'loss/train': 1.709287405014038}
-03/04/2022 13:14:07 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/04/2022 13:14:10 - INFO - codeparrot_training - Step 20235: {'lr': 0.00048150438892251724, 'samples': 10360832, 'steps': 20235, 'loss/train': 1.7714455127716064}
-03/04/2022 13:14:13 - INFO - codeparrot_training - Step 20236: {'lr': 0.00048150238567814217, 'samples': 10361344, 'steps': 20236, 'loss/train': 1.9611821174621582}
-03/04/2022 13:14:16 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/04/2022 13:14:19 - INFO - codeparrot_training - Step 20237: {'lr': 0.0004815003823294557, 'samples': 10361856, 'steps': 20237, 'loss/train': 2.4422056674957275}
-03/04/2022 13:14:22 - INFO - codeparrot_training - Step 20238: {'lr': 0.0004814983788764587, 'samples': 10362368, 'steps': 20238, 'loss/train': 2.015700578689575}
-03/04/2022 13:14:24 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/04/2022 13:14:27 - INFO - codeparrot_training - Step 20239: {'lr': 0.00048149637531915215, 'samples': 10362880, 'steps': 20239, 'loss/train': 2.3615810871124268}
-03/04/2022 13:14:30 - INFO - codeparrot_training - Step 20240: {'lr': 0.00048149437165753684, 'samples': 10363392, 'steps': 20240, 'loss/train': 0.887686550617218}
-03/04/2022 13:14:33 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 13:14:36 - INFO - codeparrot_training - Step 20241: {'lr': 0.00048149236789161374, 'samples': 10363904, 'steps': 20241, 'loss/train': 2.2266316413879395}
-03/04/2022 13:14:39 - INFO - codeparrot_training - Step 20242: {'lr': 0.0004814903640213838, 'samples': 10364416, 'steps': 20242, 'loss/train': 2.1513102054595947}
-03/04/2022 13:14:41 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 13:14:44 - INFO - codeparrot_training - Step 20243: {'lr': 0.0004814883600468478, 'samples': 10364928, 'steps': 20243, 'loss/train': 1.7661263942718506}
-03/04/2022 13:14:47 - INFO - codeparrot_training - Step 20244: {'lr': 0.0004814863559680068, 'samples': 10365440, 'steps': 20244, 'loss/train': 2.161482095718384}
-03/04/2022 13:14:52 - INFO - codeparrot_training - Step 20245: {'lr': 0.00048148435178486156, 'samples': 10365952, 'steps': 20245, 'loss/train': 2.3683910369873047}
-03/04/2022 13:14:56 - INFO - codeparrot_training - Step 20246: {'lr': 0.00048148234749741304, 'samples': 10366464, 'steps': 20246, 'loss/train': 1.5506311655044556}
-03/04/2022 13:14:57 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/04/2022 13:15:01 - INFO - codeparrot_training - Step 20247: {'lr': 0.0004814803431056622, 'samples': 10366976, 'steps': 20247, 'loss/train': 1.8024710416793823}
-03/04/2022 13:15:04 - INFO - codeparrot_training - Step 20248: {'lr': 0.0004814783386096099, 'samples': 10367488, 'steps': 20248, 'loss/train': 1.8314342498779297}
-03/04/2022 13:15:06 - INFO - codeparrot_training - Skipping example with length 462 (seq_length=1024)
-03/04/2022 13:15:09 - INFO - codeparrot_training - Step 20249: {'lr': 0.00048147633400925693, 'samples': 10368000, 'steps': 20249, 'loss/train': 1.8675981760025024}
-03/04/2022 13:15:12 - INFO - codeparrot_training - Step 20250: {'lr': 0.00048147432930460433, 'samples': 10368512, 'steps': 20250, 'loss/train': 2.258758068084717}
-03/04/2022 13:15:14 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/04/2022 13:15:18 - INFO - codeparrot_training - Step 20251: {'lr': 0.00048147232449565305, 'samples': 10369024, 'steps': 20251, 'loss/train': 1.3598523139953613}
-03/04/2022 13:15:21 - INFO - codeparrot_training - Step 20252: {'lr': 0.00048147031958240384, 'samples': 10369536, 'steps': 20252, 'loss/train': 1.931631326675415}
-03/04/2022 13:15:23 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/04/2022 13:15:26 - INFO - codeparrot_training - Step 20253: {'lr': 0.00048146831456485776, 'samples': 10370048, 'steps': 20253, 'loss/train': 1.5764318704605103}
-03/04/2022 13:15:29 - INFO - codeparrot_training - Step 20254: {'lr': 0.0004814663094430155, 'samples': 10370560, 'steps': 20254, 'loss/train': 1.3625842332839966}
-03/04/2022 13:15:31 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/04/2022 13:15:34 - INFO - codeparrot_training - Step 20255: {'lr': 0.00048146430421687817, 'samples': 10371072, 'steps': 20255, 'loss/train': 1.9887365102767944}
-03/04/2022 13:15:38 - INFO - codeparrot_training - Step 20256: {'lr': 0.00048146229888644656, 'samples': 10371584, 'steps': 20256, 'loss/train': 0.7683753371238708}
-03/04/2022 13:15:40 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/04/2022 13:15:43 - INFO - codeparrot_training - Step 20257: {'lr': 0.00048146029345172165, 'samples': 10372096, 'steps': 20257, 'loss/train': 2.2820956707000732}
-03/04/2022 13:15:46 - INFO - codeparrot_training - Step 20258: {'lr': 0.0004814582879127043, 'samples': 10372608, 'steps': 20258, 'loss/train': 1.757788896560669}
-03/04/2022 13:15:48 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/04/2022 13:15:51 - INFO - codeparrot_training - Step 20259: {'lr': 0.0004814562822693954, 'samples': 10373120, 'steps': 20259, 'loss/train': 1.8060390949249268}
-03/04/2022 13:15:54 - INFO - codeparrot_training - Step 20260: {'lr': 0.00048145427652179583, 'samples': 10373632, 'steps': 20260, 'loss/train': 1.931718349456787}
-03/04/2022 13:15:56 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 13:16:00 - INFO - codeparrot_training - Step 20261: {'lr': 0.0004814522706699066, 'samples': 10374144, 'steps': 20261, 'loss/train': 1.9194152355194092}
-03/04/2022 13:16:03 - INFO - codeparrot_training - Step 20262: {'lr': 0.00048145026471372855, 'samples': 10374656, 'steps': 20262, 'loss/train': 1.2826192378997803}
-03/04/2022 13:16:04 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 13:16:08 - INFO - codeparrot_training - Step 20263: {'lr': 0.0004814482586532626, 'samples': 10375168, 'steps': 20263, 'loss/train': 1.9188547134399414}
-03/04/2022 13:16:11 - INFO - codeparrot_training - Step 20264: {'lr': 0.00048144625248850955, 'samples': 10375680, 'steps': 20264, 'loss/train': 2.2196075916290283}
-03/04/2022 13:16:13 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 13:16:17 - INFO - codeparrot_training - Step 20265: {'lr': 0.0004814442462194704, 'samples': 10376192, 'steps': 20265, 'loss/train': 1.2020035982131958}
-03/04/2022 13:16:20 - INFO - codeparrot_training - Step 20266: {'lr': 0.0004814422398461461, 'samples': 10376704, 'steps': 20266, 'loss/train': 2.0894978046417236}
-03/04/2022 13:16:21 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/04/2022 13:16:25 - INFO - codeparrot_training - Step 20267: {'lr': 0.00048144023336853746, 'samples': 10377216, 'steps': 20267, 'loss/train': 2.225355625152588}
-03/04/2022 13:16:28 - INFO - codeparrot_training - Step 20268: {'lr': 0.00048143822678664545, 'samples': 10377728, 'steps': 20268, 'loss/train': 1.3462374210357666}
-03/04/2022 13:16:30 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 13:16:33 - INFO - codeparrot_training - Step 20269: {'lr': 0.00048143622010047096, 'samples': 10378240, 'steps': 20269, 'loss/train': 2.0127334594726562}
-03/04/2022 13:16:37 - INFO - codeparrot_training - Step 20270: {'lr': 0.0004814342133100149, 'samples': 10378752, 'steps': 20270, 'loss/train': 1.4516279697418213}
-03/04/2022 13:16:38 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 13:16:42 - INFO - codeparrot_training - Step 20271: {'lr': 0.00048143220641527805, 'samples': 10379264, 'steps': 20271, 'loss/train': 1.6147431135177612}
-03/04/2022 13:16:45 - INFO - codeparrot_training - Step 20272: {'lr': 0.0004814301994162615, 'samples': 10379776, 'steps': 20272, 'loss/train': 1.3817028999328613}
-03/04/2022 13:16:47 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/04/2022 13:16:50 - INFO - codeparrot_training - Step 20273: {'lr': 0.000481428192312966, 'samples': 10380288, 'steps': 20273, 'loss/train': 2.0180304050445557}
-03/04/2022 13:16:53 - INFO - codeparrot_training - Step 20274: {'lr': 0.0004814261851053926, 'samples': 10380800, 'steps': 20274, 'loss/train': 1.9820739030838013}
-03/04/2022 13:16:55 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/04/2022 13:16:59 - INFO - codeparrot_training - Step 20275: {'lr': 0.00048142417779354214, 'samples': 10381312, 'steps': 20275, 'loss/train': 1.9524707794189453}
-03/04/2022 13:17:02 - INFO - codeparrot_training - Step 20276: {'lr': 0.0004814221703774155, 'samples': 10381824, 'steps': 20276, 'loss/train': 1.286349892616272}
-03/04/2022 13:17:04 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 13:17:07 - INFO - codeparrot_training - Step 20277: {'lr': 0.00048142016285701356, 'samples': 10382336, 'steps': 20277, 'loss/train': 1.608291745185852}
-03/04/2022 13:17:10 - INFO - codeparrot_training - Step 20278: {'lr': 0.00048141815523233735, 'samples': 10382848, 'steps': 20278, 'loss/train': 2.0682904720306396}
-03/04/2022 13:17:12 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/04/2022 13:17:16 - INFO - codeparrot_training - Step 20279: {'lr': 0.00048141614750338757, 'samples': 10383360, 'steps': 20279, 'loss/train': 1.3807785511016846}
-03/04/2022 13:17:19 - INFO - codeparrot_training - Step 20280: {'lr': 0.00048141413967016535, 'samples': 10383872, 'steps': 20280, 'loss/train': 1.4437352418899536}
-03/04/2022 13:17:20 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 13:17:24 - INFO - codeparrot_training - Step 20281: {'lr': 0.00048141213173267145, 'samples': 10384384, 'steps': 20281, 'loss/train': 0.9472389221191406}
-03/04/2022 13:17:27 - INFO - codeparrot_training - Step 20282: {'lr': 0.0004814101236909068, 'samples': 10384896, 'steps': 20282, 'loss/train': 2.4436330795288086}
-03/04/2022 13:17:29 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 13:17:33 - INFO - codeparrot_training - Step 20283: {'lr': 0.00048140811554487234, 'samples': 10385408, 'steps': 20283, 'loss/train': 1.425564169883728}
-03/04/2022 13:17:36 - INFO - codeparrot_training - Step 20284: {'lr': 0.000481406107294569, 'samples': 10385920, 'steps': 20284, 'loss/train': 1.5306607484817505}
-03/04/2022 13:17:37 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/04/2022 13:17:41 - INFO - codeparrot_training - Step 20285: {'lr': 0.0004814040989399975, 'samples': 10386432, 'steps': 20285, 'loss/train': 1.5772647857666016}
-03/04/2022 13:17:44 - INFO - codeparrot_training - Step 20286: {'lr': 0.000481402090481159, 'samples': 10386944, 'steps': 20286, 'loss/train': 1.8681546449661255}
-03/04/2022 13:17:46 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/04/2022 13:17:50 - INFO - codeparrot_training - Step 20287: {'lr': 0.0004814000819180543, 'samples': 10387456, 'steps': 20287, 'loss/train': 2.0079705715179443}
-03/04/2022 13:17:53 - INFO - codeparrot_training - Step 20288: {'lr': 0.00048139807325068423, 'samples': 10387968, 'steps': 20288, 'loss/train': 1.4021387100219727}
-03/04/2022 13:17:55 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/04/2022 13:17:58 - INFO - codeparrot_training - Step 20289: {'lr': 0.0004813960644790498, 'samples': 10388480, 'steps': 20289, 'loss/train': 2.0971012115478516}
-03/04/2022 13:18:01 - INFO - codeparrot_training - Step 20290: {'lr': 0.00048139405560315186, 'samples': 10388992, 'steps': 20290, 'loss/train': 1.857638955116272}
-03/04/2022 13:18:03 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/04/2022 13:18:07 - INFO - codeparrot_training - Step 20291: {'lr': 0.0004813920466229913, 'samples': 10389504, 'steps': 20291, 'loss/train': 2.142422676086426}
-03/04/2022 13:18:10 - INFO - codeparrot_training - Step 20292: {'lr': 0.0004813900375385691, 'samples': 10390016, 'steps': 20292, 'loss/train': 2.0671212673187256}
-03/04/2022 13:18:12 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/04/2022 13:18:15 - INFO - codeparrot_training - Step 20293: {'lr': 0.0004813880283498861, 'samples': 10390528, 'steps': 20293, 'loss/train': 1.4597253799438477}
-03/04/2022 13:18:18 - INFO - codeparrot_training - Step 20294: {'lr': 0.00048138601905694324, 'samples': 10391040, 'steps': 20294, 'loss/train': 1.7426204681396484}
-03/04/2022 13:18:20 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 13:18:23 - INFO - codeparrot_training - Step 20295: {'lr': 0.0004813840096597414, 'samples': 10391552, 'steps': 20295, 'loss/train': 1.7160520553588867}
-03/04/2022 13:18:27 - INFO - codeparrot_training - Step 20296: {'lr': 0.00048138200015828146, 'samples': 10392064, 'steps': 20296, 'loss/train': 1.929692268371582}
-03/04/2022 13:18:28 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/04/2022 13:18:32 - INFO - codeparrot_training - Step 20297: {'lr': 0.00048137999055256444, 'samples': 10392576, 'steps': 20297, 'loss/train': 1.9815778732299805}
-03/04/2022 13:18:35 - INFO - codeparrot_training - Step 20298: {'lr': 0.0004813779808425911, 'samples': 10393088, 'steps': 20298, 'loss/train': 1.6334166526794434}
-03/04/2022 13:18:37 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 13:18:40 - INFO - codeparrot_training - Step 20299: {'lr': 0.0004813759710283624, 'samples': 10393600, 'steps': 20299, 'loss/train': 2.034120798110962}
-03/04/2022 13:18:43 - INFO - codeparrot_training - Step 20300: {'lr': 0.0004813739611098793, 'samples': 10394112, 'steps': 20300, 'loss/train': 1.7253496646881104}
-03/04/2022 13:18:45 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/04/2022 13:18:49 - INFO - codeparrot_training - Step 20301: {'lr': 0.00048137195108714266, 'samples': 10394624, 'steps': 20301, 'loss/train': 1.3769193887710571}
-03/04/2022 13:18:52 - INFO - codeparrot_training - Step 20302: {'lr': 0.00048136994096015343, 'samples': 10395136, 'steps': 20302, 'loss/train': 1.826712965965271}
-03/04/2022 13:18:53 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 13:18:57 - INFO - codeparrot_training - Step 20303: {'lr': 0.00048136793072891236, 'samples': 10395648, 'steps': 20303, 'loss/train': 2.2832858562469482}
-03/04/2022 13:19:00 - INFO - codeparrot_training - Step 20304: {'lr': 0.00048136592039342053, 'samples': 10396160, 'steps': 20304, 'loss/train': 2.2106282711029053}
-03/04/2022 13:19:01 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 13:19:05 - INFO - codeparrot_training - Step 20305: {'lr': 0.0004813639099536789, 'samples': 10396672, 'steps': 20305, 'loss/train': 1.3505048751831055}
-03/04/2022 13:19:09 - INFO - codeparrot_training - Step 20306: {'lr': 0.0004813618994096881, 'samples': 10397184, 'steps': 20306, 'loss/train': 2.0112452507019043}
-03/04/2022 13:19:09 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/04/2022 13:19:14 - INFO - codeparrot_training - Step 20307: {'lr': 0.0004813598887614492, 'samples': 10397696, 'steps': 20307, 'loss/train': 1.1415553092956543}
-03/04/2022 13:19:17 - INFO - codeparrot_training - Step 20308: {'lr': 0.0004813578780089632, 'samples': 10398208, 'steps': 20308, 'loss/train': 2.2053706645965576}
-03/04/2022 13:19:18 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/04/2022 13:19:22 - INFO - codeparrot_training - Step 20309: {'lr': 0.00048135586715223087, 'samples': 10398720, 'steps': 20309, 'loss/train': 1.2573555707931519}
-03/04/2022 13:19:26 - INFO - codeparrot_training - Step 20310: {'lr': 0.00048135385619125316, 'samples': 10399232, 'steps': 20310, 'loss/train': 1.9854685068130493}
-03/04/2022 13:19:27 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 13:19:31 - INFO - codeparrot_training - Step 20311: {'lr': 0.00048135184512603093, 'samples': 10399744, 'steps': 20311, 'loss/train': 2.006193161010742}
-03/04/2022 13:19:34 - INFO - codeparrot_training - Step 20312: {'lr': 0.00048134983395656516, 'samples': 10400256, 'steps': 20312, 'loss/train': 1.9392521381378174}
-03/04/2022 13:19:35 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 13:19:40 - INFO - codeparrot_training - Step 20313: {'lr': 0.00048134782268285676, 'samples': 10400768, 'steps': 20313, 'loss/train': 0.6946647763252258}
-03/04/2022 13:19:43 - INFO - codeparrot_training - Step 20314: {'lr': 0.00048134581130490655, 'samples': 10401280, 'steps': 20314, 'loss/train': 0.8104281425476074}
-03/04/2022 13:19:45 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/04/2022 13:19:48 - INFO - codeparrot_training - Step 20315: {'lr': 0.0004813437998227155, 'samples': 10401792, 'steps': 20315, 'loss/train': 1.896400809288025}
-03/04/2022 13:19:51 - INFO - codeparrot_training - Step 20316: {'lr': 0.00048134178823628455, 'samples': 10402304, 'steps': 20316, 'loss/train': 1.3297690153121948}
-03/04/2022 13:19:54 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/04/2022 13:19:57 - INFO - codeparrot_training - Step 20317: {'lr': 0.0004813397765456145, 'samples': 10402816, 'steps': 20317, 'loss/train': 1.544603943824768}
-03/04/2022 13:20:00 - INFO - codeparrot_training - Step 20318: {'lr': 0.00048133776475070637, 'samples': 10403328, 'steps': 20318, 'loss/train': 1.4077571630477905}
-03/04/2022 13:20:02 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 13:20:05 - INFO - codeparrot_training - Step 20319: {'lr': 0.00048133575285156093, 'samples': 10403840, 'steps': 20319, 'loss/train': 1.7472107410430908}
-03/04/2022 13:20:08 - INFO - codeparrot_training - Step 20320: {'lr': 0.00048133374084817927, 'samples': 10404352, 'steps': 20320, 'loss/train': 1.233176589012146}
-03/04/2022 13:20:13 - INFO - codeparrot_training - Step 20321: {'lr': 0.00048133172874056213, 'samples': 10404864, 'steps': 20321, 'loss/train': 2.1606802940368652}
-03/04/2022 13:20:17 - INFO - codeparrot_training - Step 20322: {'lr': 0.0004813297165287105, 'samples': 10405376, 'steps': 20322, 'loss/train': 0.23842552304267883}
-03/04/2022 13:20:19 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 13:20:22 - INFO - codeparrot_training - Step 20323: {'lr': 0.00048132770421262526, 'samples': 10405888, 'steps': 20323, 'loss/train': 2.1917285919189453}
-03/04/2022 13:20:25 - INFO - codeparrot_training - Step 20324: {'lr': 0.00048132569179230736, 'samples': 10406400, 'steps': 20324, 'loss/train': 2.2419137954711914}
-03/04/2022 13:20:27 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 13:20:30 - INFO - codeparrot_training - Step 20325: {'lr': 0.0004813236792677577, 'samples': 10406912, 'steps': 20325, 'loss/train': 1.8667510747909546}
-03/04/2022 13:20:33 - INFO - codeparrot_training - Step 20326: {'lr': 0.00048132166663897703, 'samples': 10407424, 'steps': 20326, 'loss/train': 1.754474401473999}
-03/04/2022 13:20:35 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 13:20:39 - INFO - codeparrot_training - Step 20327: {'lr': 0.0004813196539059665, 'samples': 10407936, 'steps': 20327, 'loss/train': 2.130167007446289}
-03/04/2022 13:20:42 - INFO - codeparrot_training - Step 20328: {'lr': 0.0004813176410687269, 'samples': 10408448, 'steps': 20328, 'loss/train': 1.6143391132354736}
-03/04/2022 13:20:43 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 13:20:47 - INFO - codeparrot_training - Step 20329: {'lr': 0.00048131562812725904, 'samples': 10408960, 'steps': 20329, 'loss/train': 1.4584846496582031}
-03/04/2022 13:20:50 - INFO - codeparrot_training - Step 20330: {'lr': 0.000481313615081564, 'samples': 10409472, 'steps': 20330, 'loss/train': 0.5400277376174927}
-03/04/2022 13:20:52 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/04/2022 13:20:56 - INFO - codeparrot_training - Step 20331: {'lr': 0.00048131160193164266, 'samples': 10409984, 'steps': 20331, 'loss/train': 1.5004860162734985}
-03/04/2022 13:20:59 - INFO - codeparrot_training - Step 20332: {'lr': 0.0004813095886774958, 'samples': 10410496, 'steps': 20332, 'loss/train': 1.6282845735549927}
-03/04/2022 13:21:00 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/04/2022 13:21:04 - INFO - codeparrot_training - Step 20333: {'lr': 0.00048130757531912447, 'samples': 10411008, 'steps': 20333, 'loss/train': 1.8343230485916138}
-03/04/2022 13:21:07 - INFO - codeparrot_training - Step 20334: {'lr': 0.00048130556185652947, 'samples': 10411520, 'steps': 20334, 'loss/train': 1.8938406705856323}
-03/04/2022 13:21:09 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 13:21:13 - INFO - codeparrot_training - Step 20335: {'lr': 0.0004813035482897118, 'samples': 10412032, 'steps': 20335, 'loss/train': 1.6977053880691528}
-03/04/2022 13:21:16 - INFO - codeparrot_training - Step 20336: {'lr': 0.00048130153461867225, 'samples': 10412544, 'steps': 20336, 'loss/train': 1.8562641143798828}
-03/04/2022 13:21:17 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/04/2022 13:21:21 - INFO - codeparrot_training - Step 20337: {'lr': 0.0004812995208434119, 'samples': 10413056, 'steps': 20337, 'loss/train': 2.538099765777588}
-03/04/2022 13:21:24 - INFO - codeparrot_training - Step 20338: {'lr': 0.00048129750696393144, 'samples': 10413568, 'steps': 20338, 'loss/train': 1.3659586906433105}
-03/04/2022 13:21:25 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 13:21:29 - INFO - codeparrot_training - Step 20339: {'lr': 0.00048129549298023196, 'samples': 10414080, 'steps': 20339, 'loss/train': 2.215716600418091}
-03/04/2022 13:21:33 - INFO - codeparrot_training - Step 20340: {'lr': 0.0004812934788923143, 'samples': 10414592, 'steps': 20340, 'loss/train': 1.971356749534607}
-03/04/2022 13:21:34 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/04/2022 13:21:38 - INFO - codeparrot_training - Step 20341: {'lr': 0.00048129146470017933, 'samples': 10415104, 'steps': 20341, 'loss/train': 1.595149040222168}
-03/04/2022 13:21:41 - INFO - codeparrot_training - Step 20342: {'lr': 0.000481289450403828, 'samples': 10415616, 'steps': 20342, 'loss/train': 1.8534880876541138}
-03/04/2022 13:21:42 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/04/2022 13:21:46 - INFO - codeparrot_training - Step 20343: {'lr': 0.0004812874360032613, 'samples': 10416128, 'steps': 20343, 'loss/train': 2.1731081008911133}
-03/04/2022 13:21:50 - INFO - codeparrot_training - Step 20344: {'lr': 0.0004812854214984799, 'samples': 10416640, 'steps': 20344, 'loss/train': 1.5320478677749634}
-03/04/2022 13:21:50 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/04/2022 13:21:55 - INFO - codeparrot_training - Step 20345: {'lr': 0.000481283406889485, 'samples': 10417152, 'steps': 20345, 'loss/train': 2.062438488006592}
-03/04/2022 13:21:58 - INFO - codeparrot_training - Step 20346: {'lr': 0.00048128139217627725, 'samples': 10417664, 'steps': 20346, 'loss/train': 2.098503351211548}
-03/04/2022 13:21:59 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/04/2022 13:22:03 - INFO - codeparrot_training - Step 20347: {'lr': 0.00048127937735885774, 'samples': 10418176, 'steps': 20347, 'loss/train': 2.301358222961426}
-03/04/2022 13:22:06 - INFO - codeparrot_training - Step 20348: {'lr': 0.0004812773624372273, 'samples': 10418688, 'steps': 20348, 'loss/train': 1.6554186344146729}
-03/04/2022 13:22:07 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/04/2022 13:22:12 - INFO - codeparrot_training - Step 20349: {'lr': 0.0004812753474113869, 'samples': 10419200, 'steps': 20349, 'loss/train': 1.3251705169677734}
-03/04/2022 13:22:15 - INFO - codeparrot_training - Step 20350: {'lr': 0.0004812733322813373, 'samples': 10419712, 'steps': 20350, 'loss/train': 1.3182694911956787}
-03/04/2022 13:22:18 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 13:22:21 - INFO - codeparrot_training - Step 20351: {'lr': 0.00048127131704707953, 'samples': 10420224, 'steps': 20351, 'loss/train': 1.0903029441833496}
-03/04/2022 13:22:24 - INFO - codeparrot_training - Step 20352: {'lr': 0.0004812693017086145, 'samples': 10420736, 'steps': 20352, 'loss/train': 1.7895545959472656}
-03/04/2022 13:22:26 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 13:22:29 - INFO - codeparrot_training - Step 20353: {'lr': 0.00048126728626594315, 'samples': 10421248, 'steps': 20353, 'loss/train': 1.431334137916565}
-03/04/2022 13:22:32 - INFO - codeparrot_training - Step 20354: {'lr': 0.00048126527071906623, 'samples': 10421760, 'steps': 20354, 'loss/train': 1.5782909393310547}
-03/04/2022 13:22:35 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/04/2022 13:22:37 - INFO - codeparrot_training - Step 20355: {'lr': 0.0004812632550679848, 'samples': 10422272, 'steps': 20355, 'loss/train': 2.2521138191223145}
-03/04/2022 13:22:41 - INFO - codeparrot_training - Step 20356: {'lr': 0.00048126123931269973, 'samples': 10422784, 'steps': 20356, 'loss/train': 1.773417353630066}
-03/04/2022 13:22:43 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/04/2022 13:22:46 - INFO - codeparrot_training - Step 20357: {'lr': 0.0004812592234532118, 'samples': 10423296, 'steps': 20357, 'loss/train': 1.5069940090179443}
-03/04/2022 13:22:49 - INFO - codeparrot_training - Step 20358: {'lr': 0.00048125720748952216, 'samples': 10423808, 'steps': 20358, 'loss/train': 1.9643890857696533}
-03/04/2022 13:22:52 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 13:22:54 - INFO - codeparrot_training - Step 20359: {'lr': 0.00048125519142163157, 'samples': 10424320, 'steps': 20359, 'loss/train': 2.557032823562622}
-03/04/2022 13:22:58 - INFO - codeparrot_training - Step 20360: {'lr': 0.0004812531752495409, 'samples': 10424832, 'steps': 20360, 'loss/train': 2.056480646133423}
-03/04/2022 13:23:00 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 13:23:03 - INFO - codeparrot_training - Step 20361: {'lr': 0.00048125115897325115, 'samples': 10425344, 'steps': 20361, 'loss/train': 1.844163179397583}
-03/04/2022 13:23:06 - INFO - codeparrot_training - Step 20362: {'lr': 0.0004812491425927632, 'samples': 10425856, 'steps': 20362, 'loss/train': 1.5912896394729614}
-03/04/2022 13:23:10 - INFO - codeparrot_training - Step 20363: {'lr': 0.000481247126108078, 'samples': 10426368, 'steps': 20363, 'loss/train': 1.7340617179870605}
-03/04/2022 13:23:10 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/04/2022 13:23:15 - INFO - codeparrot_training - Step 20364: {'lr': 0.00048124510951919633, 'samples': 10426880, 'steps': 20364, 'loss/train': 1.1696362495422363}
-03/04/2022 13:23:18 - INFO - codeparrot_training - Step 20365: {'lr': 0.0004812430928261192, 'samples': 10427392, 'steps': 20365, 'loss/train': 0.907446563243866}
-03/04/2022 13:23:19 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 13:23:23 - INFO - codeparrot_training - Step 20366: {'lr': 0.00048124107602884753, 'samples': 10427904, 'steps': 20366, 'loss/train': 2.48476243019104}
-03/04/2022 13:23:26 - INFO - codeparrot_training - Step 20367: {'lr': 0.0004812390591273822, 'samples': 10428416, 'steps': 20367, 'loss/train': 1.7469379901885986}
-03/04/2022 13:23:28 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 13:23:32 - INFO - codeparrot_training - Step 20368: {'lr': 0.00048123704212172416, 'samples': 10428928, 'steps': 20368, 'loss/train': 1.1882168054580688}
-03/04/2022 13:23:35 - INFO - codeparrot_training - Step 20369: {'lr': 0.0004812350250118742, 'samples': 10429440, 'steps': 20369, 'loss/train': 1.5872604846954346}
-03/04/2022 13:23:36 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 13:23:40 - INFO - codeparrot_training - Step 20370: {'lr': 0.0004812330077978333, 'samples': 10429952, 'steps': 20370, 'loss/train': 2.2186641693115234}
-03/04/2022 13:23:43 - INFO - codeparrot_training - Step 20371: {'lr': 0.0004812309904796024, 'samples': 10430464, 'steps': 20371, 'loss/train': 2.340975284576416}
-03/04/2022 13:23:45 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/04/2022 13:23:49 - INFO - codeparrot_training - Step 20372: {'lr': 0.0004812289730571824, 'samples': 10430976, 'steps': 20372, 'loss/train': 2.283179759979248}
-03/04/2022 13:23:52 - INFO - codeparrot_training - Step 20373: {'lr': 0.00048122695553057417, 'samples': 10431488, 'steps': 20373, 'loss/train': 1.290582299232483}
-03/04/2022 13:23:54 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 13:23:57 - INFO - codeparrot_training - Step 20374: {'lr': 0.00048122493789977866, 'samples': 10432000, 'steps': 20374, 'loss/train': 1.8281712532043457}
-03/04/2022 13:24:00 - INFO - codeparrot_training - Step 20375: {'lr': 0.00048122292016479674, 'samples': 10432512, 'steps': 20375, 'loss/train': 1.3553353548049927}
-03/04/2022 13:24:02 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/04/2022 13:24:05 - INFO - codeparrot_training - Step 20376: {'lr': 0.0004812209023256294, 'samples': 10433024, 'steps': 20376, 'loss/train': 1.724345326423645}
-03/04/2022 13:24:09 - INFO - codeparrot_training - Step 20377: {'lr': 0.0004812188843822775, 'samples': 10433536, 'steps': 20377, 'loss/train': 2.3454768657684326}
-03/04/2022 13:24:11 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 13:24:14 - INFO - codeparrot_training - Step 20378: {'lr': 0.0004812168663347418, 'samples': 10434048, 'steps': 20378, 'loss/train': 2.4093613624572754}
-03/04/2022 13:24:17 - INFO - codeparrot_training - Step 20379: {'lr': 0.00048121484818302343, 'samples': 10434560, 'steps': 20379, 'loss/train': 1.271134376525879}
-03/04/2022 13:24:19 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 13:24:22 - INFO - codeparrot_training - Step 20380: {'lr': 0.00048121282992712324, 'samples': 10435072, 'steps': 20380, 'loss/train': 1.9415888786315918}
-03/04/2022 13:24:25 - INFO - codeparrot_training - Step 20381: {'lr': 0.00048121081156704207, 'samples': 10435584, 'steps': 20381, 'loss/train': 2.448842763900757}
-03/04/2022 13:24:27 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 13:24:31 - INFO - codeparrot_training - Step 20382: {'lr': 0.00048120879310278094, 'samples': 10436096, 'steps': 20382, 'loss/train': 2.6376023292541504}
-03/04/2022 13:24:34 - INFO - codeparrot_training - Step 20383: {'lr': 0.00048120677453434066, 'samples': 10436608, 'steps': 20383, 'loss/train': 0.865773618221283}
-03/04/2022 13:24:36 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/04/2022 13:24:39 - INFO - codeparrot_training - Step 20384: {'lr': 0.00048120475586172217, 'samples': 10437120, 'steps': 20384, 'loss/train': 2.056737184524536}
-03/04/2022 13:24:42 - INFO - codeparrot_training - Step 20385: {'lr': 0.00048120273708492637, 'samples': 10437632, 'steps': 20385, 'loss/train': 1.8882478475570679}
-03/04/2022 13:24:44 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/04/2022 13:24:48 - INFO - codeparrot_training - Step 20386: {'lr': 0.0004812007182039542, 'samples': 10438144, 'steps': 20386, 'loss/train': 1.3399277925491333}
-03/04/2022 13:24:51 - INFO - codeparrot_training - Step 20387: {'lr': 0.00048119869921880656, 'samples': 10438656, 'steps': 20387, 'loss/train': 1.551895022392273}
-03/04/2022 13:24:53 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 13:24:56 - INFO - codeparrot_training - Step 20388: {'lr': 0.00048119668012948434, 'samples': 10439168, 'steps': 20388, 'loss/train': 2.479062557220459}
-03/04/2022 13:24:59 - INFO - codeparrot_training - Step 20389: {'lr': 0.0004811946609359885, 'samples': 10439680, 'steps': 20389, 'loss/train': 1.934212327003479}
-03/04/2022 13:25:01 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 13:25:05 - INFO - codeparrot_training - Step 20390: {'lr': 0.00048119264163831987, 'samples': 10440192, 'steps': 20390, 'loss/train': 2.335300922393799}
-03/04/2022 13:25:08 - INFO - codeparrot_training - Step 20391: {'lr': 0.0004811906222364794, 'samples': 10440704, 'steps': 20391, 'loss/train': 2.26424241065979}
-03/04/2022 13:25:10 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/04/2022 13:25:13 - INFO - codeparrot_training - Step 20392: {'lr': 0.00048118860273046804, 'samples': 10441216, 'steps': 20392, 'loss/train': 1.7915430068969727}
-03/04/2022 13:25:16 - INFO - codeparrot_training - Step 20393: {'lr': 0.00048118658312028663, 'samples': 10441728, 'steps': 20393, 'loss/train': 0.38916534185409546}
-03/04/2022 13:25:18 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 13:25:21 - INFO - codeparrot_training - Step 20394: {'lr': 0.0004811845634059361, 'samples': 10442240, 'steps': 20394, 'loss/train': 2.617605447769165}
-03/04/2022 13:25:25 - INFO - codeparrot_training - Step 20395: {'lr': 0.0004811825435874174, 'samples': 10442752, 'steps': 20395, 'loss/train': 1.5396442413330078}
-03/04/2022 13:25:26 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 13:25:30 - INFO - codeparrot_training - Step 20396: {'lr': 0.0004811805236647314, 'samples': 10443264, 'steps': 20396, 'loss/train': 1.2303355932235718}
-03/04/2022 13:25:33 - INFO - codeparrot_training - Step 20397: {'lr': 0.0004811785036378791, 'samples': 10443776, 'steps': 20397, 'loss/train': 1.3081837892532349}
-03/04/2022 13:25:35 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/04/2022 13:25:38 - INFO - codeparrot_training - Step 20398: {'lr': 0.0004811764835068613, 'samples': 10444288, 'steps': 20398, 'loss/train': 1.8741294145584106}
-03/04/2022 13:25:41 - INFO - codeparrot_training - Step 20399: {'lr': 0.0004811744632716789, 'samples': 10444800, 'steps': 20399, 'loss/train': 2.0554354190826416}
-03/04/2022 13:25:43 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/04/2022 13:25:47 - INFO - codeparrot_training - Step 20400: {'lr': 0.0004811724429323329, 'samples': 10445312, 'steps': 20400, 'loss/train': 1.965099811553955}
-03/04/2022 13:25:50 - INFO - codeparrot_training - Step 20401: {'lr': 0.0004811704224888241, 'samples': 10445824, 'steps': 20401, 'loss/train': 2.2221293449401855}
-03/04/2022 13:25:52 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 13:25:55 - INFO - codeparrot_training - Step 20402: {'lr': 0.0004811684019411535, 'samples': 10446336, 'steps': 20402, 'loss/train': 2.4441635608673096}
-03/04/2022 13:25:59 - INFO - codeparrot_training - Step 20403: {'lr': 0.000481166381289322, 'samples': 10446848, 'steps': 20403, 'loss/train': 1.9303005933761597}
-03/04/2022 13:26:01 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/04/2022 13:26:04 - INFO - codeparrot_training - Step 20404: {'lr': 0.0004811643605333305, 'samples': 10447360, 'steps': 20404, 'loss/train': 2.419502019882202}
-03/04/2022 13:26:07 - INFO - codeparrot_training - Step 20405: {'lr': 0.0004811623396731799, 'samples': 10447872, 'steps': 20405, 'loss/train': 0.5135295391082764}
-03/04/2022 13:26:09 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/04/2022 13:26:12 - INFO - codeparrot_training - Step 20406: {'lr': 0.0004811603187088711, 'samples': 10448384, 'steps': 20406, 'loss/train': 2.0092034339904785}
-03/04/2022 13:26:15 - INFO - codeparrot_training - Step 20407: {'lr': 0.00048115829764040503, 'samples': 10448896, 'steps': 20407, 'loss/train': 1.9149476289749146}
-03/04/2022 13:26:18 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/04/2022 13:26:21 - INFO - codeparrot_training - Step 20408: {'lr': 0.0004811562764677826, 'samples': 10449408, 'steps': 20408, 'loss/train': 1.9891232252120972}
-03/04/2022 13:26:24 - INFO - codeparrot_training - Step 20409: {'lr': 0.00048115425519100474, 'samples': 10449920, 'steps': 20409, 'loss/train': 1.968295693397522}
-03/04/2022 13:26:26 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 13:26:29 - INFO - codeparrot_training - Step 20410: {'lr': 0.0004811522338100723, 'samples': 10450432, 'steps': 20410, 'loss/train': 1.7027602195739746}
-03/04/2022 13:26:32 - INFO - codeparrot_training - Step 20411: {'lr': 0.0004811502123249862, 'samples': 10450944, 'steps': 20411, 'loss/train': 2.7670481204986572}
-03/04/2022 13:26:34 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/04/2022 13:26:38 - INFO - codeparrot_training - Step 20412: {'lr': 0.0004811481907357475, 'samples': 10451456, 'steps': 20412, 'loss/train': 2.065373420715332}
-03/04/2022 13:26:41 - INFO - codeparrot_training - Step 20413: {'lr': 0.000481146169042357, 'samples': 10451968, 'steps': 20413, 'loss/train': 2.3624441623687744}
-03/04/2022 13:26:45 - INFO - codeparrot_training - Step 20414: {'lr': 0.0004811441472448155, 'samples': 10452480, 'steps': 20414, 'loss/train': 1.972161889076233}
-03/04/2022 13:26:47 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/04/2022 13:26:50 - INFO - codeparrot_training - Step 20415: {'lr': 0.000481142125343124, 'samples': 10452992, 'steps': 20415, 'loss/train': 1.8398648500442505}
-03/04/2022 13:26:53 - INFO - codeparrot_training - Step 20416: {'lr': 0.0004811401033372835, 'samples': 10453504, 'steps': 20416, 'loss/train': 1.709134817123413}
-03/04/2022 13:26:55 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/04/2022 13:26:58 - INFO - codeparrot_training - Step 20417: {'lr': 0.0004811380812272948, 'samples': 10454016, 'steps': 20417, 'loss/train': 2.085507392883301}
-03/04/2022 13:27:02 - INFO - codeparrot_training - Step 20418: {'lr': 0.0004811360590131589, 'samples': 10454528, 'steps': 20418, 'loss/train': 1.4669723510742188}
-03/04/2022 13:27:03 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/04/2022 13:27:07 - INFO - codeparrot_training - Step 20419: {'lr': 0.00048113403669487655, 'samples': 10455040, 'steps': 20419, 'loss/train': 1.52060067653656}
-03/04/2022 13:27:10 - INFO - codeparrot_training - Step 20420: {'lr': 0.0004811320142724489, 'samples': 10455552, 'steps': 20420, 'loss/train': 2.3218374252319336}
-03/04/2022 13:27:12 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/04/2022 13:27:15 - INFO - codeparrot_training - Step 20421: {'lr': 0.0004811299917458766, 'samples': 10456064, 'steps': 20421, 'loss/train': 2.3772382736206055}
-03/04/2022 13:27:18 - INFO - codeparrot_training - Step 20422: {'lr': 0.00048112796911516076, 'samples': 10456576, 'steps': 20422, 'loss/train': 1.7651783227920532}
-03/04/2022 13:27:20 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 13:27:24 - INFO - codeparrot_training - Step 20423: {'lr': 0.00048112594638030225, 'samples': 10457088, 'steps': 20423, 'loss/train': 2.3160226345062256}
-03/04/2022 13:27:27 - INFO - codeparrot_training - Step 20424: {'lr': 0.00048112392354130194, 'samples': 10457600, 'steps': 20424, 'loss/train': 1.6645604372024536}
-03/04/2022 13:27:28 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/04/2022 13:27:32 - INFO - codeparrot_training - Step 20425: {'lr': 0.00048112190059816076, 'samples': 10458112, 'steps': 20425, 'loss/train': 1.8664242029190063}
-03/04/2022 13:27:35 - INFO - codeparrot_training - Step 20426: {'lr': 0.0004811198775508796, 'samples': 10458624, 'steps': 20426, 'loss/train': 1.6594371795654297}
-03/04/2022 13:27:37 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 13:27:40 - INFO - codeparrot_training - Step 20427: {'lr': 0.0004811178543994593, 'samples': 10459136, 'steps': 20427, 'loss/train': 0.7872492074966431}
-03/04/2022 13:27:44 - INFO - codeparrot_training - Step 20428: {'lr': 0.000481115831143901, 'samples': 10459648, 'steps': 20428, 'loss/train': 1.242393970489502}
-03/04/2022 13:27:45 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 13:27:49 - INFO - codeparrot_training - Step 20429: {'lr': 0.00048111380778420544, 'samples': 10460160, 'steps': 20429, 'loss/train': 1.8225417137145996}
-03/04/2022 13:27:52 - INFO - codeparrot_training - Step 20430: {'lr': 0.0004811117843203735, 'samples': 10460672, 'steps': 20430, 'loss/train': 1.223367691040039}
-03/04/2022 13:27:53 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/04/2022 13:27:57 - INFO - codeparrot_training - Step 20431: {'lr': 0.00048110976075240624, 'samples': 10461184, 'steps': 20431, 'loss/train': 3.027543067932129}
-03/04/2022 13:28:00 - INFO - codeparrot_training - Step 20432: {'lr': 0.00048110773708030444, 'samples': 10461696, 'steps': 20432, 'loss/train': 1.7364612817764282}
-03/04/2022 13:28:02 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 13:28:06 - INFO - codeparrot_training - Step 20433: {'lr': 0.00048110571330406903, 'samples': 10462208, 'steps': 20433, 'loss/train': 2.1509816646575928}
-03/04/2022 13:28:09 - INFO - codeparrot_training - Step 20434: {'lr': 0.0004811036894237011, 'samples': 10462720, 'steps': 20434, 'loss/train': 1.8670737743377686}
-03/04/2022 13:28:10 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/04/2022 13:28:14 - INFO - codeparrot_training - Step 20435: {'lr': 0.00048110166543920125, 'samples': 10463232, 'steps': 20435, 'loss/train': 0.5064175128936768}
-03/04/2022 13:28:17 - INFO - codeparrot_training - Step 20436: {'lr': 0.0004810996413505706, 'samples': 10463744, 'steps': 20436, 'loss/train': 2.10916805267334}
-03/04/2022 13:28:18 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/04/2022 13:28:23 - INFO - codeparrot_training - Step 20437: {'lr': 0.0004810976171578101, 'samples': 10464256, 'steps': 20437, 'loss/train': 2.328972101211548}
-03/04/2022 13:28:26 - INFO - codeparrot_training - Step 20438: {'lr': 0.00048109559286092047, 'samples': 10464768, 'steps': 20438, 'loss/train': 2.05403208732605}
-03/04/2022 13:28:27 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 13:28:31 - INFO - codeparrot_training - Step 20439: {'lr': 0.0004810935684599028, 'samples': 10465280, 'steps': 20439, 'loss/train': 1.608642339706421}
-03/04/2022 13:28:34 - INFO - codeparrot_training - Step 20440: {'lr': 0.00048109154395475787, 'samples': 10465792, 'steps': 20440, 'loss/train': 2.510542631149292}
-03/04/2022 13:28:35 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 13:28:40 - INFO - codeparrot_training - Step 20441: {'lr': 0.00048108951934548673, 'samples': 10466304, 'steps': 20441, 'loss/train': 1.219976782798767}
-03/04/2022 13:28:43 - INFO - codeparrot_training - Step 20442: {'lr': 0.0004810874946320901, 'samples': 10466816, 'steps': 20442, 'loss/train': 2.348198175430298}
-03/04/2022 13:28:44 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/04/2022 13:28:48 - INFO - codeparrot_training - Step 20443: {'lr': 0.00048108546981456916, 'samples': 10467328, 'steps': 20443, 'loss/train': 1.7358585596084595}
-03/04/2022 13:28:51 - INFO - codeparrot_training - Step 20444: {'lr': 0.0004810834448929246, 'samples': 10467840, 'steps': 20444, 'loss/train': 2.3606083393096924}
-03/04/2022 13:28:52 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/04/2022 13:28:57 - INFO - codeparrot_training - Step 20445: {'lr': 0.0004810814198671574, 'samples': 10468352, 'steps': 20445, 'loss/train': 1.7099816799163818}
-03/04/2022 13:29:00 - INFO - codeparrot_training - Step 20446: {'lr': 0.00048107939473726846, 'samples': 10468864, 'steps': 20446, 'loss/train': 2.0231876373291016}
-03/04/2022 13:29:01 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/04/2022 13:29:05 - INFO - codeparrot_training - Step 20447: {'lr': 0.0004810773695032588, 'samples': 10469376, 'steps': 20447, 'loss/train': 1.808205246925354}
-03/04/2022 13:29:08 - INFO - codeparrot_training - Step 20448: {'lr': 0.00048107534416512915, 'samples': 10469888, 'steps': 20448, 'loss/train': 2.2882440090179443}
-03/04/2022 13:29:09 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/04/2022 13:29:13 - INFO - codeparrot_training - Step 20449: {'lr': 0.00048107331872288055, 'samples': 10470400, 'steps': 20449, 'loss/train': 1.2700802087783813}
-03/04/2022 13:29:17 - INFO - codeparrot_training - Step 20450: {'lr': 0.0004810712931765139, 'samples': 10470912, 'steps': 20450, 'loss/train': 2.8365399837493896}
-03/04/2022 13:29:18 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/04/2022 13:29:22 - INFO - codeparrot_training - Step 20451: {'lr': 0.00048106926752603007, 'samples': 10471424, 'steps': 20451, 'loss/train': 1.5664759874343872}
-03/04/2022 13:29:25 - INFO - codeparrot_training - Step 20452: {'lr': 0.00048106724177143, 'samples': 10471936, 'steps': 20452, 'loss/train': 2.0549042224884033}
-03/04/2022 13:29:26 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/04/2022 13:29:30 - INFO - codeparrot_training - Step 20453: {'lr': 0.00048106521591271455, 'samples': 10472448, 'steps': 20453, 'loss/train': 2.18337345123291}
-03/04/2022 13:29:33 - INFO - codeparrot_training - Step 20454: {'lr': 0.00048106318994988476, 'samples': 10472960, 'steps': 20454, 'loss/train': 1.731911540031433}
-03/04/2022 13:29:35 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/04/2022 13:29:39 - INFO - codeparrot_training - Step 20455: {'lr': 0.0004810611638829414, 'samples': 10473472, 'steps': 20455, 'loss/train': 1.9947426319122314}
-03/04/2022 13:29:42 - INFO - codeparrot_training - Step 20456: {'lr': 0.00048105913771188545, 'samples': 10473984, 'steps': 20456, 'loss/train': 2.0211124420166016}
-03/04/2022 13:29:43 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 13:29:48 - INFO - codeparrot_training - Step 20457: {'lr': 0.00048105711143671783, 'samples': 10474496, 'steps': 20457, 'loss/train': 2.29929518699646}
-03/04/2022 13:29:51 - INFO - codeparrot_training - Step 20458: {'lr': 0.0004810550850574394, 'samples': 10475008, 'steps': 20458, 'loss/train': 0.413383424282074}
-03/04/2022 13:29:53 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 13:29:56 - INFO - codeparrot_training - Step 20459: {'lr': 0.0004810530585740512, 'samples': 10475520, 'steps': 20459, 'loss/train': 1.200756311416626}
-03/04/2022 13:29:59 - INFO - codeparrot_training - Step 20460: {'lr': 0.00048105103198655406, 'samples': 10476032, 'steps': 20460, 'loss/train': 1.3011879920959473}
-03/04/2022 13:30:02 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/04/2022 13:30:04 - INFO - codeparrot_training - Step 20461: {'lr': 0.0004810490052949488, 'samples': 10476544, 'steps': 20461, 'loss/train': 1.2738149166107178}
-03/04/2022 13:30:08 - INFO - codeparrot_training - Step 20462: {'lr': 0.0004810469784992365, 'samples': 10477056, 'steps': 20462, 'loss/train': 2.066554546356201}
-03/04/2022 13:30:10 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/04/2022 13:30:13 - INFO - codeparrot_training - Step 20463: {'lr': 0.00048104495159941794, 'samples': 10477568, 'steps': 20463, 'loss/train': 2.2703185081481934}
-03/04/2022 13:30:16 - INFO - codeparrot_training - Step 20464: {'lr': 0.00048104292459549413, 'samples': 10478080, 'steps': 20464, 'loss/train': 0.5864220261573792}
-03/04/2022 13:30:19 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/04/2022 13:30:21 - INFO - codeparrot_training - Step 20465: {'lr': 0.0004810408974874659, 'samples': 10478592, 'steps': 20465, 'loss/train': 1.6697965860366821}
-03/04/2022 13:30:24 - INFO - codeparrot_training - Step 20466: {'lr': 0.0004810388702753342, 'samples': 10479104, 'steps': 20466, 'loss/train': 2.1550307273864746}
-03/04/2022 13:30:27 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/04/2022 13:30:30 - INFO - codeparrot_training - Step 20467: {'lr': 0.0004810368429591, 'samples': 10479616, 'steps': 20467, 'loss/train': 0.8951159715652466}
-03/04/2022 13:30:33 - INFO - codeparrot_training - Step 20468: {'lr': 0.00048103481553876415, 'samples': 10480128, 'steps': 20468, 'loss/train': 2.172673225402832}
-03/04/2022 13:30:35 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/04/2022 13:30:38 - INFO - codeparrot_training - Step 20469: {'lr': 0.0004810327880143276, 'samples': 10480640, 'steps': 20469, 'loss/train': 0.3059053122997284}
-03/04/2022 13:30:41 - INFO - codeparrot_training - Step 20470: {'lr': 0.00048103076038579125, 'samples': 10481152, 'steps': 20470, 'loss/train': 1.6274641752243042}
-03/04/2022 13:30:44 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/04/2022 13:30:46 - INFO - codeparrot_training - Step 20471: {'lr': 0.00048102873265315596, 'samples': 10481664, 'steps': 20471, 'loss/train': 1.9880660772323608}
-03/04/2022 13:30:50 - INFO - codeparrot_training - Step 20472: {'lr': 0.0004810267048164227, 'samples': 10482176, 'steps': 20472, 'loss/train': 1.835856318473816}
-03/04/2022 13:30:52 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/04/2022 13:30:55 - INFO - codeparrot_training - Step 20473: {'lr': 0.0004810246768755924, 'samples': 10482688, 'steps': 20473, 'loss/train': 1.7808772325515747}
-03/04/2022 13:30:58 - INFO - codeparrot_training - Step 20474: {'lr': 0.0004810226488306659, 'samples': 10483200, 'steps': 20474, 'loss/train': 1.7930465936660767}
-03/04/2022 13:31:01 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 13:31:03 - INFO - codeparrot_training - Step 20475: {'lr': 0.00048102062068164413, 'samples': 10483712, 'steps': 20475, 'loss/train': 1.8961561918258667}
-03/04/2022 13:31:07 - INFO - codeparrot_training - Step 20476: {'lr': 0.0004810185924285281, 'samples': 10484224, 'steps': 20476, 'loss/train': 1.7032997608184814}
-03/04/2022 13:31:09 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/04/2022 13:31:12 - INFO - codeparrot_training - Step 20477: {'lr': 0.00048101656407131864, 'samples': 10484736, 'steps': 20477, 'loss/train': 1.1949142217636108}
-03/04/2022 13:31:15 - INFO - codeparrot_training - Step 20478: {'lr': 0.00048101453561001667, 'samples': 10485248, 'steps': 20478, 'loss/train': 1.038216471672058}
-03/04/2022 13:31:17 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/04/2022 13:31:20 - INFO - codeparrot_training - Step 20479: {'lr': 0.00048101250704462315, 'samples': 10485760, 'steps': 20479, 'loss/train': 2.075403928756714}
-03/04/2022 13:31:24 - INFO - codeparrot_training - Step 20480: {'lr': 0.0004810104783751389, 'samples': 10486272, 'steps': 20480, 'loss/train': 1.7467021942138672}
-03/04/2022 13:31:26 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/04/2022 13:31:29 - INFO - codeparrot_training - Step 20481: {'lr': 0.00048100844960156496, 'samples': 10486784, 'steps': 20481, 'loss/train': 1.327009677886963}
-03/04/2022 13:31:32 - INFO - codeparrot_training - Step 20482: {'lr': 0.0004810064207239021, 'samples': 10487296, 'steps': 20482, 'loss/train': 1.840355396270752}
-03/04/2022 13:31:35 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 13:31:37 - INFO - codeparrot_training - Step 20483: {'lr': 0.0004810043917421514, 'samples': 10487808, 'steps': 20483, 'loss/train': 1.8505570888519287}
-03/04/2022 13:31:41 - INFO - codeparrot_training - Step 20484: {'lr': 0.0004810023626563136, 'samples': 10488320, 'steps': 20484, 'loss/train': 3.536642074584961}
-03/04/2022 13:31:43 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/04/2022 13:31:46 - INFO - codeparrot_training - Step 20485: {'lr': 0.0004810003334663898, 'samples': 10488832, 'steps': 20485, 'loss/train': 2.4519662857055664}
-03/04/2022 13:31:49 - INFO - codeparrot_training - Step 20486: {'lr': 0.0004809983041723807, 'samples': 10489344, 'steps': 20486, 'loss/train': 2.0070531368255615}
-03/04/2022 13:31:52 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/04/2022 13:31:54 - INFO - codeparrot_training - Step 20487: {'lr': 0.00048099627477428744, 'samples': 10489856, 'steps': 20487, 'loss/train': 2.567838430404663}
-03/04/2022 13:31:57 - INFO - codeparrot_training - Step 20488: {'lr': 0.0004809942452721107, 'samples': 10490368, 'steps': 20488, 'loss/train': 1.092480182647705}
-03/04/2022 13:32:00 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/04/2022 13:32:03 - INFO - codeparrot_training - Step 20489: {'lr': 0.0004809922156658516, 'samples': 10490880, 'steps': 20489, 'loss/train': 1.9522677659988403}
-03/04/2022 13:32:06 - INFO - codeparrot_training - Step 20490: {'lr': 0.00048099018595551096, 'samples': 10491392, 'steps': 20490, 'loss/train': 1.6156349182128906}
-03/04/2022 13:32:08 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 13:32:11 - INFO - codeparrot_training - Step 20491: {'lr': 0.0004809881561410897, 'samples': 10491904, 'steps': 20491, 'loss/train': 1.7115347385406494}
-03/04/2022 13:32:14 - INFO - codeparrot_training - Step 20492: {'lr': 0.00048098612622258873, 'samples': 10492416, 'steps': 20492, 'loss/train': 2.4155454635620117}
-03/04/2022 13:32:16 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 13:32:19 - INFO - codeparrot_training - Step 20493: {'lr': 0.00048098409620000906, 'samples': 10492928, 'steps': 20493, 'loss/train': 2.2255070209503174}
-03/04/2022 13:32:23 - INFO - codeparrot_training - Step 20494: {'lr': 0.00048098206607335135, 'samples': 10493440, 'steps': 20494, 'loss/train': 2.27629017829895}
-03/04/2022 13:32:25 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/04/2022 13:32:28 - INFO - codeparrot_training - Step 20495: {'lr': 0.00048098003584261684, 'samples': 10493952, 'steps': 20495, 'loss/train': 2.08027982711792}
-03/04/2022 13:32:31 - INFO - codeparrot_training - Step 20496: {'lr': 0.00048097800550780625, 'samples': 10494464, 'steps': 20496, 'loss/train': 2.0890092849731445}
-03/04/2022 13:32:34 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/04/2022 13:32:36 - INFO - codeparrot_training - Step 20497: {'lr': 0.0004809759750689205, 'samples': 10494976, 'steps': 20497, 'loss/train': 0.8619827628135681}
-03/04/2022 13:32:39 - INFO - codeparrot_training - Step 20498: {'lr': 0.00048097394452596053, 'samples': 10495488, 'steps': 20498, 'loss/train': 1.5897575616836548}
-03/04/2022 13:32:42 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 13:32:45 - INFO - codeparrot_training - Step 20499: {'lr': 0.0004809719138789273, 'samples': 10496000, 'steps': 20499, 'loss/train': 0.8328710794448853}
-03/04/2022 13:32:48 - INFO - codeparrot_training - Step 20500: {'lr': 0.0004809698831278217, 'samples': 10496512, 'steps': 20500, 'loss/train': 2.0871291160583496}
-03/04/2022 13:32:50 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/04/2022 13:32:53 - INFO - codeparrot_training - Step 20501: {'lr': 0.0004809678522726446, 'samples': 10497024, 'steps': 20501, 'loss/train': 1.9859899282455444}
-03/04/2022 13:32:56 - INFO - codeparrot_training - Step 20502: {'lr': 0.000480965821313397, 'samples': 10497536, 'steps': 20502, 'loss/train': 2.541849136352539}
-03/04/2022 13:32:59 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 13:33:01 - INFO - codeparrot_training - Step 20503: {'lr': 0.0004809637902500797, 'samples': 10498048, 'steps': 20503, 'loss/train': 1.9376754760742188}
-03/04/2022 13:33:05 - INFO - codeparrot_training - Step 20504: {'lr': 0.00048096175908269375, 'samples': 10498560, 'steps': 20504, 'loss/train': 2.102771043777466}
-03/04/2022 13:33:07 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 13:33:10 - INFO - codeparrot_training - Step 20505: {'lr': 0.00048095972781124, 'samples': 10499072, 'steps': 20505, 'loss/train': 0.9444851279258728}
-03/04/2022 13:33:13 - INFO - codeparrot_training - Step 20506: {'lr': 0.00048095769643571927, 'samples': 10499584, 'steps': 20506, 'loss/train': 2.1419150829315186}
-03/04/2022 13:33:15 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/04/2022 13:33:18 - INFO - codeparrot_training - Step 20507: {'lr': 0.0004809556649561326, 'samples': 10500096, 'steps': 20507, 'loss/train': 1.7455748319625854}
-03/04/2022 13:33:21 - INFO - codeparrot_training - Step 20508: {'lr': 0.0004809536333724809, 'samples': 10500608, 'steps': 20508, 'loss/train': 2.4186573028564453}
-03/04/2022 13:33:24 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/04/2022 13:33:27 - INFO - codeparrot_training - Step 20509: {'lr': 0.000480951601684765, 'samples': 10501120, 'steps': 20509, 'loss/train': 1.6323879957199097}
-03/04/2022 13:33:30 - INFO - codeparrot_training - Step 20510: {'lr': 0.00048094956989298593, 'samples': 10501632, 'steps': 20510, 'loss/train': 1.8355625867843628}
-03/04/2022 13:33:33 - INFO - codeparrot_training - Step 20511: {'lr': 0.0004809475379971445, 'samples': 10502144, 'steps': 20511, 'loss/train': 0.627000093460083}
-03/04/2022 13:33:33 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/04/2022 13:33:39 - INFO - codeparrot_training - Step 20512: {'lr': 0.00048094550599724176, 'samples': 10502656, 'steps': 20512, 'loss/train': 1.5604933500289917}
-03/04/2022 13:33:42 - INFO - codeparrot_training - Step 20513: {'lr': 0.0004809434738932785, 'samples': 10503168, 'steps': 20513, 'loss/train': 1.6675570011138916}
-03/04/2022 13:33:42 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 13:33:47 - INFO - codeparrot_training - Step 20514: {'lr': 0.0004809414416852557, 'samples': 10503680, 'steps': 20514, 'loss/train': 0.2800006568431854}
-03/04/2022 13:33:50 - INFO - codeparrot_training - Step 20515: {'lr': 0.00048093940937317414, 'samples': 10504192, 'steps': 20515, 'loss/train': 2.060588836669922}
-03/04/2022 13:33:50 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/04/2022 13:33:56 - INFO - codeparrot_training - Step 20516: {'lr': 0.00048093737695703494, 'samples': 10504704, 'steps': 20516, 'loss/train': 1.6464698314666748}
-03/04/2022 13:33:59 - INFO - codeparrot_training - Step 20517: {'lr': 0.0004809353444368389, 'samples': 10505216, 'steps': 20517, 'loss/train': 2.219045400619507}
-03/04/2022 13:33:59 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/04/2022 13:34:05 - INFO - codeparrot_training - Step 20518: {'lr': 0.00048093331181258694, 'samples': 10505728, 'steps': 20518, 'loss/train': 2.6132962703704834}
-03/04/2022 13:34:08 - INFO - codeparrot_training - Step 20519: {'lr': 0.00048093127908428, 'samples': 10506240, 'steps': 20519, 'loss/train': 2.3432576656341553}
-03/04/2022 13:34:10 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 13:34:13 - INFO - codeparrot_training - Step 20520: {'lr': 0.00048092924625191903, 'samples': 10506752, 'steps': 20520, 'loss/train': 2.1681833267211914}
-03/04/2022 13:34:16 - INFO - codeparrot_training - Step 20521: {'lr': 0.0004809272133155048, 'samples': 10507264, 'steps': 20521, 'loss/train': 2.10150408744812}
-03/04/2022 13:34:19 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/04/2022 13:34:22 - INFO - codeparrot_training - Step 20522: {'lr': 0.00048092518027503844, 'samples': 10507776, 'steps': 20522, 'loss/train': 1.8934534788131714}
-03/04/2022 13:34:25 - INFO - codeparrot_training - Step 20523: {'lr': 0.0004809231471305208, 'samples': 10508288, 'steps': 20523, 'loss/train': 1.7568614482879639}
-03/04/2022 13:34:27 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 13:34:30 - INFO - codeparrot_training - Step 20524: {'lr': 0.0004809211138819526, 'samples': 10508800, 'steps': 20524, 'loss/train': 2.171069383621216}
-03/04/2022 13:34:33 - INFO - codeparrot_training - Step 20525: {'lr': 0.000480919080529335, 'samples': 10509312, 'steps': 20525, 'loss/train': 1.9185090065002441}
-03/04/2022 13:34:35 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 13:34:38 - INFO - codeparrot_training - Step 20526: {'lr': 0.0004809170470726688, 'samples': 10509824, 'steps': 20526, 'loss/train': 1.6862729787826538}
-03/04/2022 13:34:42 - INFO - codeparrot_training - Step 20527: {'lr': 0.00048091501351195495, 'samples': 10510336, 'steps': 20527, 'loss/train': 2.5053324699401855}
-03/04/2022 13:34:44 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 13:34:47 - INFO - codeparrot_training - Step 20528: {'lr': 0.00048091297984719433, 'samples': 10510848, 'steps': 20528, 'loss/train': 1.1084288358688354}
-03/04/2022 13:34:50 - INFO - codeparrot_training - Step 20529: {'lr': 0.0004809109460783879, 'samples': 10511360, 'steps': 20529, 'loss/train': 2.0203561782836914}
-03/04/2022 13:34:52 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/04/2022 13:34:55 - INFO - codeparrot_training - Step 20530: {'lr': 0.0004809089122055366, 'samples': 10511872, 'steps': 20530, 'loss/train': 2.093722105026245}
-03/04/2022 13:34:58 - INFO - codeparrot_training - Step 20531: {'lr': 0.00048090687822864125, 'samples': 10512384, 'steps': 20531, 'loss/train': 1.423715353012085}
-03/04/2022 13:35:00 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/04/2022 13:35:04 - INFO - codeparrot_training - Step 20532: {'lr': 0.00048090484414770284, 'samples': 10512896, 'steps': 20532, 'loss/train': 1.8944523334503174}
-03/04/2022 13:35:07 - INFO - codeparrot_training - Step 20533: {'lr': 0.00048090280996272234, 'samples': 10513408, 'steps': 20533, 'loss/train': 1.0160870552062988}
-03/04/2022 13:35:09 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 13:35:12 - INFO - codeparrot_training - Step 20534: {'lr': 0.0004809007756737005, 'samples': 10513920, 'steps': 20534, 'loss/train': 1.5946910381317139}
-03/04/2022 13:35:15 - INFO - codeparrot_training - Step 20535: {'lr': 0.0004808987412806384, 'samples': 10514432, 'steps': 20535, 'loss/train': 1.1321042776107788}
-03/04/2022 13:35:17 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 13:35:21 - INFO - codeparrot_training - Step 20536: {'lr': 0.0004808967067835369, 'samples': 10514944, 'steps': 20536, 'loss/train': 1.8620120286941528}
-03/04/2022 13:35:24 - INFO - codeparrot_training - Step 20537: {'lr': 0.00048089467218239687, 'samples': 10515456, 'steps': 20537, 'loss/train': 2.162780284881592}
-03/04/2022 13:35:25 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/04/2022 13:35:29 - INFO - codeparrot_training - Step 20538: {'lr': 0.00048089263747721925, 'samples': 10515968, 'steps': 20538, 'loss/train': 1.5353078842163086}
-03/04/2022 13:35:32 - INFO - codeparrot_training - Step 20539: {'lr': 0.000480890602668005, 'samples': 10516480, 'steps': 20539, 'loss/train': 1.1610027551651}
-03/04/2022 13:35:37 - INFO - codeparrot_training - Step 20540: {'lr': 0.000480888567754755, 'samples': 10516992, 'steps': 20540, 'loss/train': 4.48935604095459}
-03/04/2022 13:35:41 - INFO - codeparrot_training - Step 20541: {'lr': 0.0004808865327374701, 'samples': 10517504, 'steps': 20541, 'loss/train': 2.20967960357666}
-03/04/2022 13:35:42 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/04/2022 13:35:46 - INFO - codeparrot_training - Step 20542: {'lr': 0.0004808844976161514, 'samples': 10518016, 'steps': 20542, 'loss/train': 2.2568769454956055}
-03/04/2022 13:35:49 - INFO - codeparrot_training - Step 20543: {'lr': 0.0004808824623907997, 'samples': 10518528, 'steps': 20543, 'loss/train': 1.5520856380462646}
-03/04/2022 13:35:51 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/04/2022 13:35:54 - INFO - codeparrot_training - Step 20544: {'lr': 0.0004808804270614159, 'samples': 10519040, 'steps': 20544, 'loss/train': 2.4500033855438232}
-03/04/2022 13:35:58 - INFO - codeparrot_training - Step 20545: {'lr': 0.0004808783916280008, 'samples': 10519552, 'steps': 20545, 'loss/train': 1.1142815351486206}
-03/04/2022 13:35:59 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/04/2022 13:36:03 - INFO - codeparrot_training - Step 20546: {'lr': 0.0004808763560905557, 'samples': 10520064, 'steps': 20546, 'loss/train': 1.5092437267303467}
-03/04/2022 13:36:06 - INFO - codeparrot_training - Step 20547: {'lr': 0.0004808743204490811, 'samples': 10520576, 'steps': 20547, 'loss/train': 1.8915859460830688}
-03/04/2022 13:36:08 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/04/2022 13:36:11 - INFO - codeparrot_training - Step 20548: {'lr': 0.00048087228470357823, 'samples': 10521088, 'steps': 20548, 'loss/train': 1.743141770362854}
-03/04/2022 13:36:14 - INFO - codeparrot_training - Step 20549: {'lr': 0.00048087024885404777, 'samples': 10521600, 'steps': 20549, 'loss/train': 1.4230200052261353}
-03/04/2022 13:36:16 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/04/2022 13:36:20 - INFO - codeparrot_training - Step 20550: {'lr': 0.00048086821290049077, 'samples': 10522112, 'steps': 20550, 'loss/train': 2.04496431350708}
-03/04/2022 13:36:23 - INFO - codeparrot_training - Step 20551: {'lr': 0.00048086617684290814, 'samples': 10522624, 'steps': 20551, 'loss/train': 2.203918933868408}
-03/04/2022 13:36:24 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/04/2022 13:36:28 - INFO - codeparrot_training - Step 20552: {'lr': 0.00048086414068130077, 'samples': 10523136, 'steps': 20552, 'loss/train': 0.7275916934013367}
-03/04/2022 13:36:31 - INFO - codeparrot_training - Step 20553: {'lr': 0.00048086210441566956, 'samples': 10523648, 'steps': 20553, 'loss/train': 1.4173226356506348}
-03/04/2022 13:36:33 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/04/2022 13:36:37 - INFO - codeparrot_training - Step 20554: {'lr': 0.00048086006804601544, 'samples': 10524160, 'steps': 20554, 'loss/train': 2.5101277828216553}
-03/04/2022 13:36:40 - INFO - codeparrot_training - Step 20555: {'lr': 0.00048085803157233933, 'samples': 10524672, 'steps': 20555, 'loss/train': 1.5636099576950073}
-03/04/2022 13:36:41 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 13:36:45 - INFO - codeparrot_training - Step 20556: {'lr': 0.00048085599499464216, 'samples': 10525184, 'steps': 20556, 'loss/train': 2.111664295196533}
-03/04/2022 13:36:48 - INFO - codeparrot_training - Step 20557: {'lr': 0.0004808539583129249, 'samples': 10525696, 'steps': 20557, 'loss/train': 2.3063805103302}
-03/04/2022 13:36:50 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/04/2022 13:36:53 - INFO - codeparrot_training - Step 20558: {'lr': 0.0004808519215271884, 'samples': 10526208, 'steps': 20558, 'loss/train': 2.0706403255462646}
-03/04/2022 13:36:57 - INFO - codeparrot_training - Step 20559: {'lr': 0.0004808498846374335, 'samples': 10526720, 'steps': 20559, 'loss/train': 2.0973684787750244}
-03/04/2022 13:36:58 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 13:37:02 - INFO - codeparrot_training - Step 20560: {'lr': 0.0004808478476436612, 'samples': 10527232, 'steps': 20560, 'loss/train': 1.6198869943618774}
-03/04/2022 13:37:05 - INFO - codeparrot_training - Step 20561: {'lr': 0.00048084581054587253, 'samples': 10527744, 'steps': 20561, 'loss/train': 1.901327133178711}
-03/04/2022 13:37:08 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 13:37:10 - INFO - codeparrot_training - Step 20562: {'lr': 0.0004808437733440682, 'samples': 10528256, 'steps': 20562, 'loss/train': 1.534468412399292}
-03/04/2022 13:37:14 - INFO - codeparrot_training - Step 20563: {'lr': 0.0004808417360382493, 'samples': 10528768, 'steps': 20563, 'loss/train': 1.8267016410827637}
-03/04/2022 13:37:16 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/04/2022 13:37:19 - INFO - codeparrot_training - Step 20564: {'lr': 0.00048083969862841667, 'samples': 10529280, 'steps': 20564, 'loss/train': 1.7290340662002563}
-03/04/2022 13:37:22 - INFO - codeparrot_training - Step 20565: {'lr': 0.00048083766111457115, 'samples': 10529792, 'steps': 20565, 'loss/train': 2.2309768199920654}
-03/04/2022 13:37:26 - INFO - codeparrot_training - Step 20566: {'lr': 0.0004808356234967138, 'samples': 10530304, 'steps': 20566, 'loss/train': 1.1230095624923706}
-03/04/2022 13:37:26 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/04/2022 13:37:31 - INFO - codeparrot_training - Step 20567: {'lr': 0.00048083358577484547, 'samples': 10530816, 'steps': 20567, 'loss/train': 2.190361976623535}
-03/04/2022 13:37:34 - INFO - codeparrot_training - Step 20568: {'lr': 0.0004808315479489671, 'samples': 10531328, 'steps': 20568, 'loss/train': 0.7066911458969116}
-03/04/2022 13:37:34 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/04/2022 13:37:39 - INFO - codeparrot_training - Step 20569: {'lr': 0.00048082951001907965, 'samples': 10531840, 'steps': 20569, 'loss/train': 2.0183420181274414}
-03/04/2022 13:37:43 - INFO - codeparrot_training - Step 20570: {'lr': 0.0004808274719851839, 'samples': 10532352, 'steps': 20570, 'loss/train': 1.7740540504455566}
-03/04/2022 13:37:43 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/04/2022 13:37:48 - INFO - codeparrot_training - Step 20571: {'lr': 0.0004808254338472809, 'samples': 10532864, 'steps': 20571, 'loss/train': 2.0523171424865723}
-03/04/2022 13:37:51 - INFO - codeparrot_training - Step 20572: {'lr': 0.00048082339560537145, 'samples': 10533376, 'steps': 20572, 'loss/train': 2.1971435546875}
-03/04/2022 13:37:51 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/04/2022 13:37:56 - INFO - codeparrot_training - Step 20573: {'lr': 0.00048082135725945665, 'samples': 10533888, 'steps': 20573, 'loss/train': 1.814721941947937}
-03/04/2022 13:37:59 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 13:38:02 - INFO - codeparrot_training - Step 20574: {'lr': 0.0004808193188095372, 'samples': 10534400, 'steps': 20574, 'loss/train': 0.9366166591644287}
-03/04/2022 13:38:05 - INFO - codeparrot_training - Step 20575: {'lr': 0.0004808172802556142, 'samples': 10534912, 'steps': 20575, 'loss/train': 0.9939374923706055}
-03/04/2022 13:38:08 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/04/2022 13:38:10 - INFO - codeparrot_training - Step 20576: {'lr': 0.0004808152415976885, 'samples': 10535424, 'steps': 20576, 'loss/train': 1.3819323778152466}
-03/04/2022 13:38:13 - INFO - codeparrot_training - Step 20577: {'lr': 0.000480813202835761, 'samples': 10535936, 'steps': 20577, 'loss/train': 1.6481845378875732}
-03/04/2022 13:38:16 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 13:38:18 - INFO - codeparrot_training - Step 20578: {'lr': 0.0004808111639698326, 'samples': 10536448, 'steps': 20578, 'loss/train': 2.095339059829712}
-03/04/2022 13:38:22 - INFO - codeparrot_training - Step 20579: {'lr': 0.0004808091249999043, 'samples': 10536960, 'steps': 20579, 'loss/train': 2.475553035736084}
-03/04/2022 13:38:24 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 13:38:27 - INFO - codeparrot_training - Step 20580: {'lr': 0.0004808070859259769, 'samples': 10537472, 'steps': 20580, 'loss/train': 1.9107547998428345}
-03/04/2022 13:38:30 - INFO - codeparrot_training - Step 20581: {'lr': 0.0004808050467480515, 'samples': 10537984, 'steps': 20581, 'loss/train': 0.558265209197998}
-03/04/2022 13:38:33 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/04/2022 13:38:35 - INFO - codeparrot_training - Step 20582: {'lr': 0.0004808030074661288, 'samples': 10538496, 'steps': 20582, 'loss/train': 2.1978917121887207}
-03/04/2022 13:38:38 - INFO - codeparrot_training - Step 20583: {'lr': 0.0004808009680802099, 'samples': 10539008, 'steps': 20583, 'loss/train': 2.066957473754883}
-03/04/2022 13:38:41 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/04/2022 13:38:44 - INFO - codeparrot_training - Step 20584: {'lr': 0.00048079892859029564, 'samples': 10539520, 'steps': 20584, 'loss/train': 1.6681959629058838}
-03/04/2022 13:38:47 - INFO - codeparrot_training - Step 20585: {'lr': 0.00048079688899638684, 'samples': 10540032, 'steps': 20585, 'loss/train': 1.9815449714660645}
-03/04/2022 13:38:49 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 13:38:52 - INFO - codeparrot_training - Step 20586: {'lr': 0.0004807948492984846, 'samples': 10540544, 'steps': 20586, 'loss/train': 1.190662145614624}
-03/04/2022 13:38:55 - INFO - codeparrot_training - Step 20587: {'lr': 0.0004807928094965898, 'samples': 10541056, 'steps': 20587, 'loss/train': 2.0260086059570312}
-03/04/2022 13:38:58 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/04/2022 13:39:01 - INFO - codeparrot_training - Step 20588: {'lr': 0.0004807907695907032, 'samples': 10541568, 'steps': 20588, 'loss/train': 1.2616569995880127}
-03/04/2022 13:39:04 - INFO - codeparrot_training - Step 20589: {'lr': 0.000480788729580826, 'samples': 10542080, 'steps': 20589, 'loss/train': 2.016632318496704}
-03/04/2022 13:39:07 - INFO - codeparrot_training - Step 20590: {'lr': 0.00048078668946695887, 'samples': 10542592, 'steps': 20590, 'loss/train': 1.2489697933197021}
-03/04/2022 13:39:07 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/04/2022 13:39:12 - INFO - codeparrot_training - Step 20591: {'lr': 0.0004807846492491028, 'samples': 10543104, 'steps': 20591, 'loss/train': 2.332156181335449}
-03/04/2022 13:39:15 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 13:39:18 - INFO - codeparrot_training - Step 20592: {'lr': 0.0004807826089272588, 'samples': 10543616, 'steps': 20592, 'loss/train': 1.9255601167678833}
-03/04/2022 13:39:21 - INFO - codeparrot_training - Step 20593: {'lr': 0.0004807805685014277, 'samples': 10544128, 'steps': 20593, 'loss/train': 2.1923904418945312}
-03/04/2022 13:39:24 - INFO - codeparrot_training - Step 20594: {'lr': 0.00048077852797161034, 'samples': 10544640, 'steps': 20594, 'loss/train': 0.2019602209329605}
-03/04/2022 13:39:24 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/04/2022 13:39:29 - INFO - codeparrot_training - Step 20595: {'lr': 0.0004807764873378079, 'samples': 10545152, 'steps': 20595, 'loss/train': 0.9719663262367249}
-03/04/2022 13:39:32 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 13:39:35 - INFO - codeparrot_training - Step 20596: {'lr': 0.000480774446600021, 'samples': 10545664, 'steps': 20596, 'loss/train': 2.263751983642578}
-03/04/2022 13:39:38 - INFO - codeparrot_training - Step 20597: {'lr': 0.00048077240575825075, 'samples': 10546176, 'steps': 20597, 'loss/train': 1.2643367052078247}
-03/04/2022 13:39:41 - INFO - codeparrot_training - Step 20598: {'lr': 0.000480770364812498, 'samples': 10546688, 'steps': 20598, 'loss/train': 2.0041215419769287}
-03/04/2022 13:39:41 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/04/2022 13:39:46 - INFO - codeparrot_training - Step 20599: {'lr': 0.0004807683237627637, 'samples': 10547200, 'steps': 20599, 'loss/train': 1.9147244691848755}
-03/04/2022 13:39:49 - INFO - codeparrot_training - Step 20600: {'lr': 0.0004807662826090488, 'samples': 10547712, 'steps': 20600, 'loss/train': 1.4070805311203003}
-03/04/2022 13:39:50 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 13:39:55 - INFO - codeparrot_training - Step 20601: {'lr': 0.00048076424135135406, 'samples': 10548224, 'steps': 20601, 'loss/train': 1.6716095209121704}
-03/04/2022 13:39:58 - INFO - codeparrot_training - Step 20602: {'lr': 0.00048076219998968055, 'samples': 10548736, 'steps': 20602, 'loss/train': 0.5408016443252563}
-03/04/2022 13:39:58 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 13:40:03 - INFO - codeparrot_training - Step 20603: {'lr': 0.0004807601585240292, 'samples': 10549248, 'steps': 20603, 'loss/train': 1.7388633489608765}
-03/04/2022 13:40:06 - INFO - codeparrot_training - Step 20604: {'lr': 0.0004807581169544009, 'samples': 10549760, 'steps': 20604, 'loss/train': 2.4022042751312256}
-03/04/2022 13:40:06 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 13:40:12 - INFO - codeparrot_training - Step 20605: {'lr': 0.00048075607528079645, 'samples': 10550272, 'steps': 20605, 'loss/train': 1.3515058755874634}
-03/04/2022 13:40:15 - INFO - codeparrot_training - Step 20606: {'lr': 0.0004807540335032169, 'samples': 10550784, 'steps': 20606, 'loss/train': 1.7544512748718262}
-03/04/2022 13:40:15 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 13:40:20 - INFO - codeparrot_training - Step 20607: {'lr': 0.0004807519916216633, 'samples': 10551296, 'steps': 20607, 'loss/train': 2.1516003608703613}
-03/04/2022 13:40:23 - INFO - codeparrot_training - Step 20608: {'lr': 0.0004807499496361362, 'samples': 10551808, 'steps': 20608, 'loss/train': 2.469893455505371}
-03/04/2022 13:40:23 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/04/2022 13:40:29 - INFO - codeparrot_training - Step 20609: {'lr': 0.00048074790754663686, 'samples': 10552320, 'steps': 20609, 'loss/train': 2.3112213611602783}
-03/04/2022 13:40:31 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/04/2022 13:40:34 - INFO - codeparrot_training - Step 20610: {'lr': 0.000480745865353166, 'samples': 10552832, 'steps': 20610, 'loss/train': 1.4391309022903442}
-03/04/2022 13:40:37 - INFO - codeparrot_training - Step 20611: {'lr': 0.0004807438230557247, 'samples': 10553344, 'steps': 20611, 'loss/train': 0.9567596316337585}
-03/04/2022 13:40:40 - INFO - codeparrot_training - Step 20612: {'lr': 0.00048074178065431373, 'samples': 10553856, 'steps': 20612, 'loss/train': 2.9121127128601074}
-03/04/2022 13:40:40 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/04/2022 13:40:46 - INFO - codeparrot_training - Step 20613: {'lr': 0.0004807397381489341, 'samples': 10554368, 'steps': 20613, 'loss/train': 1.4604493379592896}
-03/04/2022 13:40:49 - INFO - codeparrot_training - Step 20614: {'lr': 0.00048073769553958666, 'samples': 10554880, 'steps': 20614, 'loss/train': 2.5874922275543213}
-03/04/2022 13:40:49 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/04/2022 13:40:54 - INFO - codeparrot_training - Step 20615: {'lr': 0.00048073565282627246, 'samples': 10555392, 'steps': 20615, 'loss/train': 2.803088903427124}
-03/04/2022 13:40:57 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/04/2022 13:40:59 - INFO - codeparrot_training - Step 20616: {'lr': 0.0004807336100089923, 'samples': 10555904, 'steps': 20616, 'loss/train': 2.074979543685913}
-03/04/2022 13:41:03 - INFO - codeparrot_training - Step 20617: {'lr': 0.0004807315670877471, 'samples': 10556416, 'steps': 20617, 'loss/train': 1.9806272983551025}
-03/04/2022 13:41:05 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/04/2022 13:41:08 - INFO - codeparrot_training - Step 20618: {'lr': 0.00048072952406253783, 'samples': 10556928, 'steps': 20618, 'loss/train': 0.21339386701583862}
-03/04/2022 13:41:11 - INFO - codeparrot_training - Step 20619: {'lr': 0.00048072748093336536, 'samples': 10557440, 'steps': 20619, 'loss/train': 1.7451608180999756}
-03/04/2022 13:41:14 - INFO - codeparrot_training - Step 20620: {'lr': 0.00048072543770023076, 'samples': 10557952, 'steps': 20620, 'loss/train': 1.8885148763656616}
-03/04/2022 13:41:14 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/04/2022 13:41:20 - INFO - codeparrot_training - Step 20621: {'lr': 0.0004807233943631347, 'samples': 10558464, 'steps': 20621, 'loss/train': 2.109591007232666}
-03/04/2022 13:41:23 - INFO - codeparrot_training - Step 20622: {'lr': 0.0004807213509220784, 'samples': 10558976, 'steps': 20622, 'loss/train': 1.2343413829803467}
-03/04/2022 13:41:23 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/04/2022 13:41:28 - INFO - codeparrot_training - Step 20623: {'lr': 0.0004807193073770625, 'samples': 10559488, 'steps': 20623, 'loss/train': 2.5142805576324463}
-03/04/2022 13:41:31 - INFO - codeparrot_training - Step 20624: {'lr': 0.0004807172637280881, 'samples': 10560000, 'steps': 20624, 'loss/train': 2.1950204372406006}
-03/04/2022 13:41:32 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/04/2022 13:41:37 - INFO - codeparrot_training - Step 20625: {'lr': 0.000480715219975156, 'samples': 10560512, 'steps': 20625, 'loss/train': 2.2035341262817383}
-03/04/2022 13:41:40 - INFO - codeparrot_training - Step 20626: {'lr': 0.0004807131761182672, 'samples': 10561024, 'steps': 20626, 'loss/train': 2.5084140300750732}
-03/04/2022 13:41:40 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/04/2022 13:41:45 - INFO - codeparrot_training - Step 20627: {'lr': 0.00048071113215742263, 'samples': 10561536, 'steps': 20627, 'loss/train': 1.960379958152771}
-03/04/2022 13:41:48 - INFO - codeparrot_training - Step 20628: {'lr': 0.00048070908809262316, 'samples': 10562048, 'steps': 20628, 'loss/train': 2.1590895652770996}
-03/04/2022 13:41:48 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/04/2022 13:41:53 - INFO - codeparrot_training - Step 20629: {'lr': 0.0004807070439238698, 'samples': 10562560, 'steps': 20629, 'loss/train': 2.1765875816345215}
-03/04/2022 13:41:57 - INFO - codeparrot_training - Step 20630: {'lr': 0.0004807049996511633, 'samples': 10563072, 'steps': 20630, 'loss/train': 1.2814838886260986}
-03/04/2022 13:41:57 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 13:42:02 - INFO - codeparrot_training - Step 20631: {'lr': 0.00048070295527450474, 'samples': 10563584, 'steps': 20631, 'loss/train': 2.005636692047119}
-03/04/2022 13:42:05 - INFO - codeparrot_training - Step 20632: {'lr': 0.000480700910793895, 'samples': 10564096, 'steps': 20632, 'loss/train': 2.1985225677490234}
-03/04/2022 13:42:05 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/04/2022 13:42:10 - INFO - codeparrot_training - Step 20633: {'lr': 0.000480698866209335, 'samples': 10564608, 'steps': 20633, 'loss/train': 1.8133372068405151}
-03/04/2022 13:42:13 - INFO - codeparrot_training - Step 20634: {'lr': 0.0004806968215208256, 'samples': 10565120, 'steps': 20634, 'loss/train': 1.233330488204956}
-03/04/2022 13:42:14 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 13:42:19 - INFO - codeparrot_training - Step 20635: {'lr': 0.0004806947767283678, 'samples': 10565632, 'steps': 20635, 'loss/train': 1.4435844421386719}
-03/04/2022 13:42:22 - INFO - codeparrot_training - Step 20636: {'lr': 0.0004806927318319625, 'samples': 10566144, 'steps': 20636, 'loss/train': 2.1718313694000244}
-03/04/2022 13:42:22 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/04/2022 13:42:27 - INFO - codeparrot_training - Step 20637: {'lr': 0.0004806906868316106, 'samples': 10566656, 'steps': 20637, 'loss/train': 2.0529532432556152}
-03/04/2022 13:42:30 - INFO - codeparrot_training - Step 20638: {'lr': 0.000480688641727313, 'samples': 10567168, 'steps': 20638, 'loss/train': 2.0600876808166504}
-03/04/2022 13:42:30 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/04/2022 13:42:36 - INFO - codeparrot_training - Step 20639: {'lr': 0.00048068659651907076, 'samples': 10567680, 'steps': 20639, 'loss/train': 2.0734565258026123}
-03/04/2022 13:42:39 - INFO - codeparrot_training - Step 20640: {'lr': 0.0004806845512068846, 'samples': 10568192, 'steps': 20640, 'loss/train': 2.5211849212646484}
-03/04/2022 13:42:39 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/04/2022 13:42:44 - INFO - codeparrot_training - Step 20641: {'lr': 0.00048068250579075554, 'samples': 10568704, 'steps': 20641, 'loss/train': 2.2971339225769043}
-03/04/2022 13:42:47 - INFO - codeparrot_training - Step 20642: {'lr': 0.00048068046027068456, 'samples': 10569216, 'steps': 20642, 'loss/train': 2.349273443222046}
-03/04/2022 13:42:47 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/04/2022 13:42:53 - INFO - codeparrot_training - Step 20643: {'lr': 0.0004806784146466726, 'samples': 10569728, 'steps': 20643, 'loss/train': 2.259838819503784}
-03/04/2022 13:42:56 - INFO - codeparrot_training - Step 20644: {'lr': 0.00048067636891872036, 'samples': 10570240, 'steps': 20644, 'loss/train': 1.8413264751434326}
-03/04/2022 13:42:56 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/04/2022 13:43:01 - INFO - codeparrot_training - Step 20645: {'lr': 0.00048067432308682894, 'samples': 10570752, 'steps': 20645, 'loss/train': 2.1669483184814453}
-03/04/2022 13:43:04 - INFO - codeparrot_training - Step 20646: {'lr': 0.0004806722771509993, 'samples': 10571264, 'steps': 20646, 'loss/train': 1.2995960712432861}
-03/04/2022 13:43:04 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/04/2022 13:43:10 - INFO - codeparrot_training - Step 20647: {'lr': 0.0004806702311112322, 'samples': 10571776, 'steps': 20647, 'loss/train': 1.0408862829208374}
-03/04/2022 13:43:13 - INFO - codeparrot_training - Step 20648: {'lr': 0.0004806681849675287, 'samples': 10572288, 'steps': 20648, 'loss/train': 2.52351713180542}
-03/04/2022 13:43:13 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/04/2022 13:43:18 - INFO - codeparrot_training - Step 20649: {'lr': 0.00048066613871988967, 'samples': 10572800, 'steps': 20649, 'loss/train': 2.007094383239746}
-03/04/2022 13:43:21 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 13:43:23 - INFO - codeparrot_training - Step 20650: {'lr': 0.00048066409236831607, 'samples': 10573312, 'steps': 20650, 'loss/train': 1.3885326385498047}
-03/04/2022 13:43:27 - INFO - codeparrot_training - Step 20651: {'lr': 0.0004806620459128087, 'samples': 10573824, 'steps': 20651, 'loss/train': 1.963650107383728}
-03/04/2022 13:43:29 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 13:43:32 - INFO - codeparrot_training - Step 20652: {'lr': 0.0004806599993533687, 'samples': 10574336, 'steps': 20652, 'loss/train': 2.060060977935791}
-03/04/2022 13:43:35 - INFO - codeparrot_training - Step 20653: {'lr': 0.00048065795268999677, 'samples': 10574848, 'steps': 20653, 'loss/train': 2.368366241455078}
-03/04/2022 13:43:38 - INFO - codeparrot_training - Step 20654: {'lr': 0.00048065590592269393, 'samples': 10575360, 'steps': 20654, 'loss/train': 1.8393296003341675}
-03/04/2022 13:43:38 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/04/2022 13:43:43 - INFO - codeparrot_training - Step 20655: {'lr': 0.00048065385905146114, 'samples': 10575872, 'steps': 20655, 'loss/train': 1.888199806213379}
-03/04/2022 13:43:47 - INFO - codeparrot_training - Step 20656: {'lr': 0.0004806518120762993, 'samples': 10576384, 'steps': 20656, 'loss/train': 2.014191150665283}
-03/04/2022 13:43:47 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/04/2022 13:43:52 - INFO - codeparrot_training - Step 20657: {'lr': 0.00048064976499720923, 'samples': 10576896, 'steps': 20657, 'loss/train': 1.9318780899047852}
-03/04/2022 13:43:55 - INFO - codeparrot_training - Step 20658: {'lr': 0.000480647717814192, 'samples': 10577408, 'steps': 20658, 'loss/train': 2.656240463256836}
-03/04/2022 13:43:55 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/04/2022 13:44:00 - INFO - codeparrot_training - Step 20659: {'lr': 0.0004806456705272484, 'samples': 10577920, 'steps': 20659, 'loss/train': 2.0877795219421387}
-03/04/2022 13:44:04 - INFO - codeparrot_training - Step 20660: {'lr': 0.0004806436231363795, 'samples': 10578432, 'steps': 20660, 'loss/train': 1.1328251361846924}
-03/04/2022 13:44:04 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/04/2022 13:44:09 - INFO - codeparrot_training - Step 20661: {'lr': 0.00048064157564158607, 'samples': 10578944, 'steps': 20661, 'loss/train': 1.7436243295669556}
-03/04/2022 13:44:12 - INFO - codeparrot_training - Step 20662: {'lr': 0.00048063952804286913, 'samples': 10579456, 'steps': 20662, 'loss/train': 1.046575903892517}
-03/04/2022 13:44:12 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 13:44:17 - INFO - codeparrot_training - Step 20663: {'lr': 0.0004806374803402296, 'samples': 10579968, 'steps': 20663, 'loss/train': 1.5387860536575317}
-03/04/2022 13:44:21 - INFO - codeparrot_training - Step 20664: {'lr': 0.00048063543253366837, 'samples': 10580480, 'steps': 20664, 'loss/train': 1.6794464588165283}
-03/04/2022 13:44:21 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/04/2022 13:44:26 - INFO - codeparrot_training - Step 20665: {'lr': 0.0004806333846231864, 'samples': 10580992, 'steps': 20665, 'loss/train': 1.3881405591964722}
-03/04/2022 13:44:29 - INFO - codeparrot_training - Step 20666: {'lr': 0.00048063133660878455, 'samples': 10581504, 'steps': 20666, 'loss/train': 2.3521902561187744}
-03/04/2022 13:44:29 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/04/2022 13:44:34 - INFO - codeparrot_training - Step 20667: {'lr': 0.00048062928849046377, 'samples': 10582016, 'steps': 20667, 'loss/train': 2.146852970123291}
-03/04/2022 13:44:37 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 13:44:40 - INFO - codeparrot_training - Step 20668: {'lr': 0.00048062724026822504, 'samples': 10582528, 'steps': 20668, 'loss/train': 1.692043662071228}
-03/04/2022 13:44:43 - INFO - codeparrot_training - Step 20669: {'lr': 0.00048062519194206916, 'samples': 10583040, 'steps': 20669, 'loss/train': 1.7595391273498535}
-03/04/2022 13:44:46 - INFO - codeparrot_training - Step 20670: {'lr': 0.0004806231435119972, 'samples': 10583552, 'steps': 20670, 'loss/train': 1.5545532703399658}
-03/04/2022 13:44:46 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 13:44:51 - INFO - codeparrot_training - Step 20671: {'lr': 0.00048062109497800997, 'samples': 10584064, 'steps': 20671, 'loss/train': 2.72775936126709}
-03/04/2022 13:44:55 - INFO - codeparrot_training - Step 20672: {'lr': 0.00048061904634010845, 'samples': 10584576, 'steps': 20672, 'loss/train': 0.38718119263648987}
-03/04/2022 13:44:55 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/04/2022 13:45:00 - INFO - codeparrot_training - Step 20673: {'lr': 0.0004806169975982935, 'samples': 10585088, 'steps': 20673, 'loss/train': 1.6511955261230469}
-03/04/2022 13:45:03 - INFO - codeparrot_training - Step 20674: {'lr': 0.0004806149487525662, 'samples': 10585600, 'steps': 20674, 'loss/train': 0.8807926177978516}
-03/04/2022 13:45:03 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/04/2022 13:45:08 - INFO - codeparrot_training - Step 20675: {'lr': 0.0004806128998029272, 'samples': 10586112, 'steps': 20675, 'loss/train': 1.7558990716934204}
-03/04/2022 13:45:11 - INFO - codeparrot_training - Step 20676: {'lr': 0.0004806108507493777, 'samples': 10586624, 'steps': 20676, 'loss/train': 1.5095884799957275}
-03/04/2022 13:45:11 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 13:45:17 - INFO - codeparrot_training - Step 20677: {'lr': 0.0004806088015919185, 'samples': 10587136, 'steps': 20677, 'loss/train': 2.048875093460083}
-03/04/2022 13:45:20 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/04/2022 13:45:22 - INFO - codeparrot_training - Step 20678: {'lr': 0.0004806067523305505, 'samples': 10587648, 'steps': 20678, 'loss/train': 0.9130741357803345}
-03/04/2022 13:45:25 - INFO - codeparrot_training - Step 20679: {'lr': 0.0004806047029652747, 'samples': 10588160, 'steps': 20679, 'loss/train': 1.9362869262695312}
-03/04/2022 13:45:28 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/04/2022 13:45:30 - INFO - codeparrot_training - Step 20680: {'lr': 0.00048060265349609193, 'samples': 10588672, 'steps': 20680, 'loss/train': 2.0841214656829834}
-03/04/2022 13:45:34 - INFO - codeparrot_training - Step 20681: {'lr': 0.0004806006039230032, 'samples': 10589184, 'steps': 20681, 'loss/train': 2.533137321472168}
-03/04/2022 13:45:37 - INFO - codeparrot_training - Step 20682: {'lr': 0.0004805985542460094, 'samples': 10589696, 'steps': 20682, 'loss/train': 5.91558313369751}
-03/04/2022 13:45:37 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 13:45:42 - INFO - codeparrot_training - Step 20683: {'lr': 0.00048059650446511136, 'samples': 10590208, 'steps': 20683, 'loss/train': 2.247016191482544}
-03/04/2022 13:45:45 - INFO - codeparrot_training - Step 20684: {'lr': 0.00048059445458031023, 'samples': 10590720, 'steps': 20684, 'loss/train': 1.9033803939819336}
-03/04/2022 13:45:45 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/04/2022 13:45:50 - INFO - codeparrot_training - Step 20685: {'lr': 0.0004805924045916067, 'samples': 10591232, 'steps': 20685, 'loss/train': 2.1728031635284424}
-03/04/2022 13:45:53 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/04/2022 13:45:56 - INFO - codeparrot_training - Step 20686: {'lr': 0.00048059035449900185, 'samples': 10591744, 'steps': 20686, 'loss/train': 1.8516231775283813}
-03/04/2022 13:45:59 - INFO - codeparrot_training - Step 20687: {'lr': 0.0004805883043024965, 'samples': 10592256, 'steps': 20687, 'loss/train': 1.5646461248397827}
-03/04/2022 13:46:02 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 13:46:04 - INFO - codeparrot_training - Step 20688: {'lr': 0.0004805862540020917, 'samples': 10592768, 'steps': 20688, 'loss/train': 1.2542964220046997}
-03/04/2022 13:46:07 - INFO - codeparrot_training - Step 20689: {'lr': 0.0004805842035977882, 'samples': 10593280, 'steps': 20689, 'loss/train': 2.107980966567993}
-03/04/2022 13:46:10 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/04/2022 13:46:13 - INFO - codeparrot_training - Step 20690: {'lr': 0.00048058215308958703, 'samples': 10593792, 'steps': 20690, 'loss/train': 1.6637312173843384}
-03/04/2022 13:46:16 - INFO - codeparrot_training - Step 20691: {'lr': 0.00048058010247748904, 'samples': 10594304, 'steps': 20691, 'loss/train': 1.996462345123291}
-03/04/2022 13:46:19 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/04/2022 13:46:21 - INFO - codeparrot_training - Step 20692: {'lr': 0.0004805780517614954, 'samples': 10594816, 'steps': 20692, 'loss/train': 1.6531703472137451}
-03/04/2022 13:46:24 - INFO - codeparrot_training - Step 20693: {'lr': 0.0004805760009416067, 'samples': 10595328, 'steps': 20693, 'loss/train': 1.759236454963684}
-03/04/2022 13:46:27 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/04/2022 13:46:29 - INFO - codeparrot_training - Step 20694: {'lr': 0.000480573950017824, 'samples': 10595840, 'steps': 20694, 'loss/train': 1.5111132860183716}
-03/04/2022 13:46:33 - INFO - codeparrot_training - Step 20695: {'lr': 0.0004805718989901483, 'samples': 10596352, 'steps': 20695, 'loss/train': 0.814595103263855}
-03/04/2022 13:46:35 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/04/2022 13:46:38 - INFO - codeparrot_training - Step 20696: {'lr': 0.00048056984785858046, 'samples': 10596864, 'steps': 20696, 'loss/train': 1.1707097291946411}
-03/04/2022 13:46:41 - INFO - codeparrot_training - Step 20697: {'lr': 0.0004805677966231214, 'samples': 10597376, 'steps': 20697, 'loss/train': 1.855120062828064}
-03/04/2022 13:46:43 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 13:46:46 - INFO - codeparrot_training - Step 20698: {'lr': 0.00048056574528377205, 'samples': 10597888, 'steps': 20698, 'loss/train': 1.75473952293396}
-03/04/2022 13:46:49 - INFO - codeparrot_training - Step 20699: {'lr': 0.00048056369384053335, 'samples': 10598400, 'steps': 20699, 'loss/train': 1.9385000467300415}
-03/04/2022 13:46:52 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/04/2022 13:46:55 - INFO - codeparrot_training - Step 20700: {'lr': 0.00048056164229340613, 'samples': 10598912, 'steps': 20700, 'loss/train': 1.8183764219284058}
-03/04/2022 13:46:58 - INFO - codeparrot_training - Step 20701: {'lr': 0.0004805595906423914, 'samples': 10599424, 'steps': 20701, 'loss/train': 2.7235965728759766}
-03/04/2022 13:47:00 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/04/2022 13:47:03 - INFO - codeparrot_training - Step 20702: {'lr': 0.00048055753888749013, 'samples': 10599936, 'steps': 20702, 'loss/train': 2.039680004119873}
-03/04/2022 13:47:06 - INFO - codeparrot_training - Step 20703: {'lr': 0.0004805554870287032, 'samples': 10600448, 'steps': 20703, 'loss/train': 1.6946420669555664}
-03/04/2022 13:47:09 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 13:47:11 - INFO - codeparrot_training - Step 20704: {'lr': 0.0004805534350660315, 'samples': 10600960, 'steps': 20704, 'loss/train': 2.3469293117523193}
-03/04/2022 13:47:15 - INFO - codeparrot_training - Step 20705: {'lr': 0.000480551382999476, 'samples': 10601472, 'steps': 20705, 'loss/train': 1.5779931545257568}
-03/04/2022 13:47:17 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/04/2022 13:47:20 - INFO - codeparrot_training - Step 20706: {'lr': 0.00048054933082903754, 'samples': 10601984, 'steps': 20706, 'loss/train': 2.0609006881713867}
-03/04/2022 13:47:23 - INFO - codeparrot_training - Step 20707: {'lr': 0.00048054727855471717, 'samples': 10602496, 'steps': 20707, 'loss/train': 1.4554849863052368}
-03/04/2022 13:47:26 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/04/2022 13:47:29 - INFO - codeparrot_training - Step 20708: {'lr': 0.00048054522617651575, 'samples': 10603008, 'steps': 20708, 'loss/train': 1.3971600532531738}
-03/04/2022 13:47:32 - INFO - codeparrot_training - Step 20709: {'lr': 0.0004805431736944342, 'samples': 10603520, 'steps': 20709, 'loss/train': 0.2454409897327423}
-03/04/2022 13:47:34 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/04/2022 13:47:37 - INFO - codeparrot_training - Step 20710: {'lr': 0.0004805411211084735, 'samples': 10604032, 'steps': 20710, 'loss/train': 1.6719807386398315}
-03/04/2022 13:47:40 - INFO - codeparrot_training - Step 20711: {'lr': 0.0004805390684186344, 'samples': 10604544, 'steps': 20711, 'loss/train': 1.3089810609817505}
-03/04/2022 13:47:44 - INFO - codeparrot_training - Step 20712: {'lr': 0.00048053701562491804, 'samples': 10605056, 'steps': 20712, 'loss/train': 1.367372751235962}
-03/04/2022 13:47:44 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 13:47:49 - INFO - codeparrot_training - Step 20713: {'lr': 0.0004805349627273253, 'samples': 10605568, 'steps': 20713, 'loss/train': 2.0853347778320312}
-03/04/2022 13:47:52 - INFO - codeparrot_training - Step 20714: {'lr': 0.00048053290972585697, 'samples': 10606080, 'steps': 20714, 'loss/train': 1.9316208362579346}
-03/04/2022 13:47:52 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 13:47:58 - INFO - codeparrot_training - Step 20715: {'lr': 0.0004805308566205141, 'samples': 10606592, 'steps': 20715, 'loss/train': 1.5982234477996826}
-03/04/2022 13:48:01 - INFO - codeparrot_training - Step 20716: {'lr': 0.00048052880341129764, 'samples': 10607104, 'steps': 20716, 'loss/train': 6.703266620635986}
-03/04/2022 13:48:02 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/04/2022 13:48:06 - INFO - codeparrot_training - Step 20717: {'lr': 0.00048052675009820837, 'samples': 10607616, 'steps': 20717, 'loss/train': 0.8411498069763184}
-03/04/2022 13:48:09 - INFO - codeparrot_training - Step 20718: {'lr': 0.0004805246966812474, 'samples': 10608128, 'steps': 20718, 'loss/train': 1.5483967065811157}
-03/04/2022 13:48:11 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 13:48:15 - INFO - codeparrot_training - Step 20719: {'lr': 0.0004805226431604155, 'samples': 10608640, 'steps': 20719, 'loss/train': 1.997488260269165}
-03/04/2022 13:48:18 - INFO - codeparrot_training - Step 20720: {'lr': 0.00048052058953571366, 'samples': 10609152, 'steps': 20720, 'loss/train': 2.891796588897705}
-03/04/2022 13:48:19 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 13:48:23 - INFO - codeparrot_training - Step 20721: {'lr': 0.0004805185358071428, 'samples': 10609664, 'steps': 20721, 'loss/train': 1.9587011337280273}
-03/04/2022 13:48:26 - INFO - codeparrot_training - Step 20722: {'lr': 0.0004805164819747038, 'samples': 10610176, 'steps': 20722, 'loss/train': 1.9166762828826904}
-03/04/2022 13:48:27 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/04/2022 13:48:31 - INFO - codeparrot_training - Step 20723: {'lr': 0.0004805144280383977, 'samples': 10610688, 'steps': 20723, 'loss/train': 2.055347204208374}
-03/04/2022 13:48:35 - INFO - codeparrot_training - Step 20724: {'lr': 0.00048051237399822534, 'samples': 10611200, 'steps': 20724, 'loss/train': 2.1195297241210938}
-03/04/2022 13:48:35 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 13:48:40 - INFO - codeparrot_training - Step 20725: {'lr': 0.00048051031985418764, 'samples': 10611712, 'steps': 20725, 'loss/train': 2.290299654006958}
-03/04/2022 13:48:43 - INFO - codeparrot_training - Step 20726: {'lr': 0.0004805082656062856, 'samples': 10612224, 'steps': 20726, 'loss/train': 1.9501078128814697}
-03/04/2022 13:48:44 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/04/2022 13:48:48 - INFO - codeparrot_training - Step 20727: {'lr': 0.00048050621125451996, 'samples': 10612736, 'steps': 20727, 'loss/train': 0.9164448976516724}
-03/04/2022 13:48:52 - INFO - codeparrot_training - Step 20728: {'lr': 0.00048050415679889194, 'samples': 10613248, 'steps': 20728, 'loss/train': 1.0623432397842407}
-03/04/2022 13:48:53 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/04/2022 13:48:57 - INFO - codeparrot_training - Step 20729: {'lr': 0.0004805021022394022, 'samples': 10613760, 'steps': 20729, 'loss/train': 1.7323359251022339}
-03/04/2022 13:49:00 - INFO - codeparrot_training - Step 20730: {'lr': 0.0004805000475760518, 'samples': 10614272, 'steps': 20730, 'loss/train': 1.662230372428894}
-03/04/2022 13:49:01 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 13:49:05 - INFO - codeparrot_training - Step 20731: {'lr': 0.0004804979928088417, 'samples': 10614784, 'steps': 20731, 'loss/train': 0.5864414572715759}
-03/04/2022 13:49:08 - INFO - codeparrot_training - Step 20732: {'lr': 0.0004804959379377727, 'samples': 10615296, 'steps': 20732, 'loss/train': 2.540903091430664}
-03/04/2022 13:49:10 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/04/2022 13:49:14 - INFO - codeparrot_training - Step 20733: {'lr': 0.00048049388296284576, 'samples': 10615808, 'steps': 20733, 'loss/train': 1.2453272342681885}
-03/04/2022 13:49:17 - INFO - codeparrot_training - Step 20734: {'lr': 0.00048049182788406186, 'samples': 10616320, 'steps': 20734, 'loss/train': 1.6099131107330322}
-03/04/2022 13:49:18 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/04/2022 13:49:22 - INFO - codeparrot_training - Step 20735: {'lr': 0.0004804897727014219, 'samples': 10616832, 'steps': 20735, 'loss/train': 1.4992687702178955}
-03/04/2022 13:49:25 - INFO - codeparrot_training - Step 20736: {'lr': 0.0004804877174149268, 'samples': 10617344, 'steps': 20736, 'loss/train': 1.464448094367981}
-03/04/2022 13:49:27 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/04/2022 13:49:31 - INFO - codeparrot_training - Step 20737: {'lr': 0.00048048566202457747, 'samples': 10617856, 'steps': 20737, 'loss/train': 1.8131709098815918}
-03/04/2022 13:49:34 - INFO - codeparrot_training - Step 20738: {'lr': 0.00048048360653037494, 'samples': 10618368, 'steps': 20738, 'loss/train': 0.7531116008758545}
-03/04/2022 13:49:35 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/04/2022 13:49:39 - INFO - codeparrot_training - Step 20739: {'lr': 0.00048048155093231994, 'samples': 10618880, 'steps': 20739, 'loss/train': 1.7284878492355347}
-03/04/2022 13:49:42 - INFO - codeparrot_training - Step 20740: {'lr': 0.00048047949523041355, 'samples': 10619392, 'steps': 20740, 'loss/train': 1.8991143703460693}
-03/04/2022 13:49:44 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/04/2022 13:49:48 - INFO - codeparrot_training - Step 20741: {'lr': 0.0004804774394246567, 'samples': 10619904, 'steps': 20741, 'loss/train': 1.7342756986618042}
-03/04/2022 13:49:51 - INFO - codeparrot_training - Step 20742: {'lr': 0.0004804753835150503, 'samples': 10620416, 'steps': 20742, 'loss/train': 1.453991174697876}
-03/04/2022 13:49:52 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/04/2022 13:49:56 - INFO - codeparrot_training - Step 20743: {'lr': 0.0004804733275015951, 'samples': 10620928, 'steps': 20743, 'loss/train': 1.5944546461105347}
-03/04/2022 13:49:59 - INFO - codeparrot_training - Step 20744: {'lr': 0.0004804712713842923, 'samples': 10621440, 'steps': 20744, 'loss/train': 1.490140438079834}
-03/04/2022 13:50:01 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/04/2022 13:50:04 - INFO - codeparrot_training - Step 20745: {'lr': 0.0004804692151631427, 'samples': 10621952, 'steps': 20745, 'loss/train': 1.663615107536316}
-03/04/2022 13:50:08 - INFO - codeparrot_training - Step 20746: {'lr': 0.00048046715883814716, 'samples': 10622464, 'steps': 20746, 'loss/train': 2.4552431106567383}
-03/04/2022 13:50:09 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 13:50:13 - INFO - codeparrot_training - Step 20747: {'lr': 0.00048046510240930674, 'samples': 10622976, 'steps': 20747, 'loss/train': 2.5529441833496094}
-03/04/2022 13:50:16 - INFO - codeparrot_training - Step 20748: {'lr': 0.00048046304587662225, 'samples': 10623488, 'steps': 20748, 'loss/train': 1.8041871786117554}
-03/04/2022 13:50:18 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/04/2022 13:50:21 - INFO - codeparrot_training - Step 20749: {'lr': 0.00048046098924009467, 'samples': 10624000, 'steps': 20749, 'loss/train': 1.9448494911193848}
-03/04/2022 13:50:25 - INFO - codeparrot_training - Step 20750: {'lr': 0.00048045893249972497, 'samples': 10624512, 'steps': 20750, 'loss/train': 1.6445696353912354}
-03/04/2022 13:50:26 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 13:50:30 - INFO - codeparrot_training - Step 20751: {'lr': 0.000480456875655514, 'samples': 10625024, 'steps': 20751, 'loss/train': 1.8324373960494995}
-03/04/2022 13:50:33 - INFO - codeparrot_training - Step 20752: {'lr': 0.0004804548187074628, 'samples': 10625536, 'steps': 20752, 'loss/train': 0.8228806257247925}
-03/04/2022 13:50:35 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/04/2022 13:50:38 - INFO - codeparrot_training - Step 20753: {'lr': 0.0004804527616555721, 'samples': 10626048, 'steps': 20753, 'loss/train': 1.895346999168396}
-03/04/2022 13:50:41 - INFO - codeparrot_training - Step 20754: {'lr': 0.00048045070449984295, 'samples': 10626560, 'steps': 20754, 'loss/train': 3.001166582107544}
-03/04/2022 13:50:43 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/04/2022 13:50:47 - INFO - codeparrot_training - Step 20755: {'lr': 0.0004804486472402763, 'samples': 10627072, 'steps': 20755, 'loss/train': 2.32140851020813}
-03/04/2022 13:50:50 - INFO - codeparrot_training - Step 20756: {'lr': 0.0004804465898768731, 'samples': 10627584, 'steps': 20756, 'loss/train': 2.0942177772521973}
-03/04/2022 13:50:52 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/04/2022 13:50:56 - INFO - codeparrot_training - Step 20757: {'lr': 0.00048044453240963413, 'samples': 10628096, 'steps': 20757, 'loss/train': 1.6772987842559814}
-03/04/2022 13:50:59 - INFO - codeparrot_training - Step 20758: {'lr': 0.00048044247483856043, 'samples': 10628608, 'steps': 20758, 'loss/train': 1.9403187036514282}
-03/04/2022 13:51:02 - INFO - codeparrot_training - Step 20759: {'lr': 0.00048044041716365296, 'samples': 10629120, 'steps': 20759, 'loss/train': 1.6408607959747314}
-03/04/2022 13:51:03 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/04/2022 13:51:07 - INFO - codeparrot_training - Step 20760: {'lr': 0.00048043835938491253, 'samples': 10629632, 'steps': 20760, 'loss/train': 1.9574334621429443}
-03/04/2022 13:51:10 - INFO - codeparrot_training - Step 20761: {'lr': 0.0004804363015023402, 'samples': 10630144, 'steps': 20761, 'loss/train': 1.4089950323104858}
-03/04/2022 13:51:11 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/04/2022 13:51:16 - INFO - codeparrot_training - Step 20762: {'lr': 0.00048043424351593676, 'samples': 10630656, 'steps': 20762, 'loss/train': 1.580742359161377}
-03/04/2022 13:51:19 - INFO - codeparrot_training - Step 20763: {'lr': 0.0004804321854257032, 'samples': 10631168, 'steps': 20763, 'loss/train': 1.594428300857544}
-03/04/2022 13:51:19 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/04/2022 13:51:24 - INFO - codeparrot_training - Step 20764: {'lr': 0.0004804301272316405, 'samples': 10631680, 'steps': 20764, 'loss/train': 1.2975013256072998}
-03/04/2022 13:51:27 - INFO - codeparrot_training - Step 20765: {'lr': 0.0004804280689337496, 'samples': 10632192, 'steps': 20765, 'loss/train': 1.986747145652771}
-03/04/2022 13:51:28 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 13:51:33 - INFO - codeparrot_training - Step 20766: {'lr': 0.00048042601053203125, 'samples': 10632704, 'steps': 20766, 'loss/train': 2.9567766189575195}
-03/04/2022 13:51:36 - INFO - codeparrot_training - Step 20767: {'lr': 0.00048042395202648646, 'samples': 10633216, 'steps': 20767, 'loss/train': 2.460460662841797}
-03/04/2022 13:51:37 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 13:51:41 - INFO - codeparrot_training - Step 20768: {'lr': 0.00048042189341711636, 'samples': 10633728, 'steps': 20768, 'loss/train': 1.9340392351150513}
-03/04/2022 13:51:44 - INFO - codeparrot_training - Step 20769: {'lr': 0.0004804198347039216, 'samples': 10634240, 'steps': 20769, 'loss/train': 1.8332546949386597}
-03/04/2022 13:51:45 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 13:51:49 - INFO - codeparrot_training - Step 20770: {'lr': 0.0004804177758869032, 'samples': 10634752, 'steps': 20770, 'loss/train': 2.072420835494995}
-03/04/2022 13:51:53 - INFO - codeparrot_training - Step 20771: {'lr': 0.0004804157169660622, 'samples': 10635264, 'steps': 20771, 'loss/train': 0.5164312124252319}
-03/04/2022 13:51:54 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/04/2022 13:51:58 - INFO - codeparrot_training - Step 20772: {'lr': 0.00048041365794139934, 'samples': 10635776, 'steps': 20772, 'loss/train': 1.6460829973220825}
-03/04/2022 13:52:01 - INFO - codeparrot_training - Step 20773: {'lr': 0.00048041159881291574, 'samples': 10636288, 'steps': 20773, 'loss/train': 0.6652989387512207}
-03/04/2022 13:52:03 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/04/2022 13:52:06 - INFO - codeparrot_training - Step 20774: {'lr': 0.0004804095395806122, 'samples': 10636800, 'steps': 20774, 'loss/train': 1.890141487121582}
-03/04/2022 13:52:09 - INFO - codeparrot_training - Step 20775: {'lr': 0.00048040748024448954, 'samples': 10637312, 'steps': 20775, 'loss/train': 2.6718902587890625}
-03/04/2022 13:52:11 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/04/2022 13:52:15 - INFO - codeparrot_training - Step 20776: {'lr': 0.00048040542080454897, 'samples': 10637824, 'steps': 20776, 'loss/train': 2.159229278564453}
-03/04/2022 13:52:18 - INFO - codeparrot_training - Step 20777: {'lr': 0.0004804033612607912, 'samples': 10638336, 'steps': 20777, 'loss/train': 1.537187099456787}
-03/04/2022 13:52:19 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/04/2022 13:52:23 - INFO - codeparrot_training - Step 20778: {'lr': 0.00048040130161321724, 'samples': 10638848, 'steps': 20778, 'loss/train': 1.7471376657485962}
-03/04/2022 13:52:26 - INFO - codeparrot_training - Step 20779: {'lr': 0.0004803992418618281, 'samples': 10639360, 'steps': 20779, 'loss/train': 2.4992740154266357}
-03/04/2022 13:52:27 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/04/2022 13:52:32 - INFO - codeparrot_training - Step 20780: {'lr': 0.00048039718200662454, 'samples': 10639872, 'steps': 20780, 'loss/train': 1.9102097749710083}
-03/04/2022 13:52:35 - INFO - codeparrot_training - Step 20781: {'lr': 0.0004803951220476076, 'samples': 10640384, 'steps': 20781, 'loss/train': 1.8250401020050049}
-03/04/2022 13:52:36 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/04/2022 13:52:40 - INFO - codeparrot_training - Step 20782: {'lr': 0.00048039306198477817, 'samples': 10640896, 'steps': 20782, 'loss/train': 2.0065274238586426}
-03/04/2022 13:52:43 - INFO - codeparrot_training - Step 20783: {'lr': 0.0004803910018181371, 'samples': 10641408, 'steps': 20783, 'loss/train': 1.005293369293213}
-03/04/2022 13:52:44 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 13:52:48 - INFO - codeparrot_training - Step 20784: {'lr': 0.0004803889415476855, 'samples': 10641920, 'steps': 20784, 'loss/train': 2.4946234226226807}
-03/04/2022 13:52:52 - INFO - codeparrot_training - Step 20785: {'lr': 0.0004803868811734242, 'samples': 10642432, 'steps': 20785, 'loss/train': 1.9197194576263428}
-03/04/2022 13:52:52 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 13:52:57 - INFO - codeparrot_training - Step 20786: {'lr': 0.00048038482069535406, 'samples': 10642944, 'steps': 20786, 'loss/train': 2.383737802505493}
-03/04/2022 13:53:00 - INFO - codeparrot_training - Step 20787: {'lr': 0.000480382760113476, 'samples': 10643456, 'steps': 20787, 'loss/train': 2.4900193214416504}
-03/04/2022 13:53:01 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/04/2022 13:53:05 - INFO - codeparrot_training - Step 20788: {'lr': 0.00048038069942779116, 'samples': 10643968, 'steps': 20788, 'loss/train': 2.7334108352661133}
-03/04/2022 13:53:09 - INFO - codeparrot_training - Step 20789: {'lr': 0.00048037863863830034, 'samples': 10644480, 'steps': 20789, 'loss/train': 1.751271367073059}
-03/04/2022 13:53:09 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/04/2022 13:53:14 - INFO - codeparrot_training - Step 20790: {'lr': 0.0004803765777450044, 'samples': 10644992, 'steps': 20790, 'loss/train': 2.4003334045410156}
-03/04/2022 13:53:17 - INFO - codeparrot_training - Step 20791: {'lr': 0.00048037451674790433, 'samples': 10645504, 'steps': 20791, 'loss/train': 1.570690393447876}
-03/04/2022 13:53:17 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/04/2022 13:53:22 - INFO - codeparrot_training - Step 20792: {'lr': 0.0004803724556470011, 'samples': 10646016, 'steps': 20792, 'loss/train': 2.028837203979492}
-03/04/2022 13:53:25 - INFO - codeparrot_training - Step 20793: {'lr': 0.0004803703944422956, 'samples': 10646528, 'steps': 20793, 'loss/train': 2.036442279815674}
-03/04/2022 13:53:26 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/04/2022 13:53:31 - INFO - codeparrot_training - Step 20794: {'lr': 0.0004803683331337887, 'samples': 10647040, 'steps': 20794, 'loss/train': 1.6753735542297363}
-03/04/2022 13:53:34 - INFO - codeparrot_training - Step 20795: {'lr': 0.0004803662717214814, 'samples': 10647552, 'steps': 20795, 'loss/train': 1.06248939037323}
-03/04/2022 13:53:34 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/04/2022 13:53:39 - INFO - codeparrot_training - Step 20796: {'lr': 0.00048036421020537464, 'samples': 10648064, 'steps': 20796, 'loss/train': 1.664320707321167}
-03/04/2022 13:53:42 - INFO - codeparrot_training - Step 20797: {'lr': 0.0004803621485854693, 'samples': 10648576, 'steps': 20797, 'loss/train': 1.7644977569580078}
-03/04/2022 13:53:43 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/04/2022 13:53:48 - INFO - codeparrot_training - Step 20798: {'lr': 0.00048036008686176636, 'samples': 10649088, 'steps': 20798, 'loss/train': 1.125112771987915}
-03/04/2022 13:53:51 - INFO - codeparrot_training - Step 20799: {'lr': 0.0004803580250342666, 'samples': 10649600, 'steps': 20799, 'loss/train': 1.0924681425094604}
-03/04/2022 13:53:51 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/04/2022 13:53:56 - INFO - codeparrot_training - Step 20800: {'lr': 0.00048035596310297125, 'samples': 10650112, 'steps': 20800, 'loss/train': 1.4679067134857178}
-03/04/2022 13:53:59 - INFO - codeparrot_training - Step 20801: {'lr': 0.0004803539010678809, 'samples': 10650624, 'steps': 20801, 'loss/train': 2.2058913707733154}
-03/04/2022 13:53:59 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 13:54:04 - INFO - codeparrot_training - Step 20802: {'lr': 0.00048035183892899676, 'samples': 10651136, 'steps': 20802, 'loss/train': 2.0208399295806885}
-03/04/2022 13:54:08 - INFO - codeparrot_training - Step 20803: {'lr': 0.0004803497766863195, 'samples': 10651648, 'steps': 20803, 'loss/train': 2.344757318496704}
-03/04/2022 13:54:08 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/04/2022 13:54:13 - INFO - codeparrot_training - Step 20804: {'lr': 0.00048034771433985035, 'samples': 10652160, 'steps': 20804, 'loss/train': 1.1309911012649536}
-03/04/2022 13:54:16 - INFO - codeparrot_training - Step 20805: {'lr': 0.00048034565188959, 'samples': 10652672, 'steps': 20805, 'loss/train': 1.8621139526367188}
-03/04/2022 13:54:17 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/04/2022 13:54:22 - INFO - codeparrot_training - Step 20806: {'lr': 0.0004803435893355394, 'samples': 10653184, 'steps': 20806, 'loss/train': 2.0247139930725098}
-03/04/2022 13:54:25 - INFO - codeparrot_training - Step 20807: {'lr': 0.00048034152667769957, 'samples': 10653696, 'steps': 20807, 'loss/train': 1.5568569898605347}
-03/04/2022 13:54:26 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 13:54:30 - INFO - codeparrot_training - Step 20808: {'lr': 0.0004803394639160714, 'samples': 10654208, 'steps': 20808, 'loss/train': 1.249288558959961}
-03/04/2022 13:54:33 - INFO - codeparrot_training - Step 20809: {'lr': 0.00048033740105065585, 'samples': 10654720, 'steps': 20809, 'loss/train': 2.435887098312378}
-03/04/2022 13:54:35 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 13:54:39 - INFO - codeparrot_training - Step 20810: {'lr': 0.0004803353380814538, 'samples': 10655232, 'steps': 20810, 'loss/train': 1.5099842548370361}
-03/04/2022 13:54:42 - INFO - codeparrot_training - Step 20811: {'lr': 0.00048033327500846625, 'samples': 10655744, 'steps': 20811, 'loss/train': 1.4758402109146118}
-03/04/2022 13:54:43 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/04/2022 13:54:47 - INFO - codeparrot_training - Step 20812: {'lr': 0.000480331211831694, 'samples': 10656256, 'steps': 20812, 'loss/train': 2.047667980194092}
-03/04/2022 13:54:50 - INFO - codeparrot_training - Step 20813: {'lr': 0.00048032914855113807, 'samples': 10656768, 'steps': 20813, 'loss/train': 2.0801894664764404}
-03/04/2022 13:54:52 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 13:54:56 - INFO - codeparrot_training - Step 20814: {'lr': 0.00048032708516679946, 'samples': 10657280, 'steps': 20814, 'loss/train': 2.168907642364502}
-03/04/2022 13:54:59 - INFO - codeparrot_training - Step 20815: {'lr': 0.00048032502167867896, 'samples': 10657792, 'steps': 20815, 'loss/train': 2.041142225265503}
-03/04/2022 13:55:00 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 13:55:04 - INFO - codeparrot_training - Step 20816: {'lr': 0.0004803229580867775, 'samples': 10658304, 'steps': 20816, 'loss/train': 1.5593611001968384}
-03/04/2022 13:55:07 - INFO - codeparrot_training - Step 20817: {'lr': 0.0004803208943910962, 'samples': 10658816, 'steps': 20817, 'loss/train': 1.5333776473999023}
-03/04/2022 13:55:08 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/04/2022 13:55:13 - INFO - codeparrot_training - Step 20818: {'lr': 0.00048031883059163576, 'samples': 10659328, 'steps': 20818, 'loss/train': 1.8670252561569214}
-03/04/2022 13:55:16 - INFO - codeparrot_training - Step 20819: {'lr': 0.00048031676668839723, 'samples': 10659840, 'steps': 20819, 'loss/train': 1.8951810598373413}
-03/04/2022 13:55:17 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 13:55:21 - INFO - codeparrot_training - Step 20820: {'lr': 0.00048031470268138153, 'samples': 10660352, 'steps': 20820, 'loss/train': 0.6324357390403748}
-03/04/2022 13:55:24 - INFO - codeparrot_training - Step 20821: {'lr': 0.00048031263857058957, 'samples': 10660864, 'steps': 20821, 'loss/train': 1.783376693725586}
-03/04/2022 13:55:26 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 13:55:30 - INFO - codeparrot_training - Step 20822: {'lr': 0.00048031057435602234, 'samples': 10661376, 'steps': 20822, 'loss/train': 2.5321507453918457}
-03/04/2022 13:55:33 - INFO - codeparrot_training - Step 20823: {'lr': 0.0004803085100376807, 'samples': 10661888, 'steps': 20823, 'loss/train': 1.523669719696045}
-03/04/2022 13:55:35 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 13:55:38 - INFO - codeparrot_training - Step 20824: {'lr': 0.00048030644561556556, 'samples': 10662400, 'steps': 20824, 'loss/train': 2.407277822494507}
-03/04/2022 13:55:42 - INFO - codeparrot_training - Step 20825: {'lr': 0.0004803043810896779, 'samples': 10662912, 'steps': 20825, 'loss/train': 1.562023401260376}
-03/04/2022 13:55:44 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/04/2022 13:55:47 - INFO - codeparrot_training - Step 20826: {'lr': 0.00048030231646001867, 'samples': 10663424, 'steps': 20826, 'loss/train': 2.7319130897521973}
-03/04/2022 13:55:50 - INFO - codeparrot_training - Step 20827: {'lr': 0.0004803002517265887, 'samples': 10663936, 'steps': 20827, 'loss/train': 1.715059757232666}
-03/04/2022 13:55:53 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/04/2022 13:55:55 - INFO - codeparrot_training - Step 20828: {'lr': 0.0004802981868893891, 'samples': 10664448, 'steps': 20828, 'loss/train': 2.1793973445892334}
-03/04/2022 13:55:59 - INFO - codeparrot_training - Step 20829: {'lr': 0.00048029612194842056, 'samples': 10664960, 'steps': 20829, 'loss/train': 1.8685741424560547}
-03/04/2022 13:56:01 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 13:56:04 - INFO - codeparrot_training - Step 20830: {'lr': 0.0004802940569036842, 'samples': 10665472, 'steps': 20830, 'loss/train': 1.1490752696990967}
-03/04/2022 13:56:07 - INFO - codeparrot_training - Step 20831: {'lr': 0.0004802919917551809, 'samples': 10665984, 'steps': 20831, 'loss/train': 1.8238575458526611}
-03/04/2022 13:56:09 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/04/2022 13:56:12 - INFO - codeparrot_training - Step 20832: {'lr': 0.00048028992650291156, 'samples': 10666496, 'steps': 20832, 'loss/train': 1.3150571584701538}
-03/04/2022 13:56:15 - INFO - codeparrot_training - Step 20833: {'lr': 0.00048028786114687715, 'samples': 10667008, 'steps': 20833, 'loss/train': 1.9175732135772705}
-03/04/2022 13:56:18 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/04/2022 13:56:21 - INFO - codeparrot_training - Step 20834: {'lr': 0.0004802857956870786, 'samples': 10667520, 'steps': 20834, 'loss/train': 2.3021647930145264}
-03/04/2022 13:56:24 - INFO - codeparrot_training - Step 20835: {'lr': 0.00048028373012351684, 'samples': 10668032, 'steps': 20835, 'loss/train': 2.487605333328247}
-03/04/2022 13:56:26 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/04/2022 13:56:29 - INFO - codeparrot_training - Step 20836: {'lr': 0.00048028166445619275, 'samples': 10668544, 'steps': 20836, 'loss/train': 0.32284048199653625}
-03/04/2022 13:56:33 - INFO - codeparrot_training - Step 20837: {'lr': 0.0004802795986851073, 'samples': 10669056, 'steps': 20837, 'loss/train': 1.2048430442810059}
-03/04/2022 13:56:35 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 13:56:38 - INFO - codeparrot_training - Step 20838: {'lr': 0.00048027753281026144, 'samples': 10669568, 'steps': 20838, 'loss/train': 2.0701801776885986}
-03/04/2022 13:56:41 - INFO - codeparrot_training - Step 20839: {'lr': 0.000480275466831656, 'samples': 10670080, 'steps': 20839, 'loss/train': 1.565854787826538}
-03/04/2022 13:56:44 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/04/2022 13:56:46 - INFO - codeparrot_training - Step 20840: {'lr': 0.00048027340074929207, 'samples': 10670592, 'steps': 20840, 'loss/train': 1.6101205348968506}
-03/04/2022 13:56:50 - INFO - codeparrot_training - Step 20841: {'lr': 0.0004802713345631705, 'samples': 10671104, 'steps': 20841, 'loss/train': 1.9119445085525513}
-03/04/2022 13:56:52 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/04/2022 13:56:55 - INFO - codeparrot_training - Step 20842: {'lr': 0.0004802692682732922, 'samples': 10671616, 'steps': 20842, 'loss/train': 2.7444100379943848}
-03/04/2022 13:56:58 - INFO - codeparrot_training - Step 20843: {'lr': 0.0004802672018796581, 'samples': 10672128, 'steps': 20843, 'loss/train': 1.5290002822875977}
-03/04/2022 13:57:01 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 13:57:03 - INFO - codeparrot_training - Step 20844: {'lr': 0.0004802651353822691, 'samples': 10672640, 'steps': 20844, 'loss/train': 1.1908310651779175}
-03/04/2022 13:57:06 - INFO - codeparrot_training - Step 20845: {'lr': 0.0004802630687811263, 'samples': 10673152, 'steps': 20845, 'loss/train': 1.260087251663208}
-03/04/2022 13:57:09 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 13:57:12 - INFO - codeparrot_training - Step 20846: {'lr': 0.00048026100207623047, 'samples': 10673664, 'steps': 20846, 'loss/train': 1.8149884939193726}
-03/04/2022 13:57:15 - INFO - codeparrot_training - Step 20847: {'lr': 0.0004802589352675826, 'samples': 10674176, 'steps': 20847, 'loss/train': 1.40677011013031}
-03/04/2022 13:57:17 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/04/2022 13:57:20 - INFO - codeparrot_training - Step 20848: {'lr': 0.0004802568683551836, 'samples': 10674688, 'steps': 20848, 'loss/train': 1.8028876781463623}
-03/04/2022 13:57:23 - INFO - codeparrot_training - Step 20849: {'lr': 0.0004802548013390343, 'samples': 10675200, 'steps': 20849, 'loss/train': 2.1015944480895996}
-03/04/2022 13:57:26 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 13:57:29 - INFO - codeparrot_training - Step 20850: {'lr': 0.00048025273421913587, 'samples': 10675712, 'steps': 20850, 'loss/train': 1.793839693069458}
-03/04/2022 13:57:32 - INFO - codeparrot_training - Step 20851: {'lr': 0.0004802506669954891, 'samples': 10676224, 'steps': 20851, 'loss/train': 1.029511570930481}
-03/04/2022 13:57:34 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/04/2022 13:57:37 - INFO - codeparrot_training - Step 20852: {'lr': 0.00048024859966809487, 'samples': 10676736, 'steps': 20852, 'loss/train': 1.8482638597488403}
-03/04/2022 13:57:40 - INFO - codeparrot_training - Step 20853: {'lr': 0.00048024653223695425, 'samples': 10677248, 'steps': 20853, 'loss/train': 2.040074348449707}
-03/04/2022 13:57:43 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/04/2022 13:57:45 - INFO - codeparrot_training - Step 20854: {'lr': 0.00048024446470206806, 'samples': 10677760, 'steps': 20854, 'loss/train': 2.1193761825561523}
-03/04/2022 13:57:49 - INFO - codeparrot_training - Step 20855: {'lr': 0.0004802423970634373, 'samples': 10678272, 'steps': 20855, 'loss/train': 1.9989287853240967}
-03/04/2022 13:57:51 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/04/2022 13:57:54 - INFO - codeparrot_training - Step 20856: {'lr': 0.00048024032932106277, 'samples': 10678784, 'steps': 20856, 'loss/train': 2.5009138584136963}
-03/04/2022 13:57:57 - INFO - codeparrot_training - Step 20857: {'lr': 0.00048023826147494556, 'samples': 10679296, 'steps': 20857, 'loss/train': 1.629153847694397}
-03/04/2022 13:58:00 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/04/2022 13:58:02 - INFO - codeparrot_training - Step 20858: {'lr': 0.0004802361935250865, 'samples': 10679808, 'steps': 20858, 'loss/train': 1.8697221279144287}
-03/04/2022 13:58:06 - INFO - codeparrot_training - Step 20859: {'lr': 0.0004802341254714867, 'samples': 10680320, 'steps': 20859, 'loss/train': 1.629812240600586}
-03/04/2022 13:58:08 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 13:58:11 - INFO - codeparrot_training - Step 20860: {'lr': 0.00048023205731414684, 'samples': 10680832, 'steps': 20860, 'loss/train': 2.1021032333374023}
-03/04/2022 13:58:14 - INFO - codeparrot_training - Step 20861: {'lr': 0.00048022998905306795, 'samples': 10681344, 'steps': 20861, 'loss/train': 1.8104851245880127}
-03/04/2022 13:58:17 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 13:58:19 - INFO - codeparrot_training - Step 20862: {'lr': 0.00048022792068825107, 'samples': 10681856, 'steps': 20862, 'loss/train': 1.7847647666931152}
-03/04/2022 13:58:23 - INFO - codeparrot_training - Step 20863: {'lr': 0.00048022585221969697, 'samples': 10682368, 'steps': 20863, 'loss/train': 2.2858006954193115}
-03/04/2022 13:58:25 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/04/2022 13:58:28 - INFO - codeparrot_training - Step 20864: {'lr': 0.00048022378364740673, 'samples': 10682880, 'steps': 20864, 'loss/train': 1.3208547830581665}
-03/04/2022 13:58:31 - INFO - codeparrot_training - Step 20865: {'lr': 0.0004802217149713811, 'samples': 10683392, 'steps': 20865, 'loss/train': 1.2520369291305542}
-03/04/2022 13:58:33 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 13:58:36 - INFO - codeparrot_training - Step 20866: {'lr': 0.0004802196461916212, 'samples': 10683904, 'steps': 20866, 'loss/train': 2.5959959030151367}
-03/04/2022 13:58:40 - INFO - codeparrot_training - Step 20867: {'lr': 0.0004802175773081278, 'samples': 10684416, 'steps': 20867, 'loss/train': 1.8089581727981567}
-03/04/2022 13:58:42 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/04/2022 13:58:45 - INFO - codeparrot_training - Step 20868: {'lr': 0.000480215508320902, 'samples': 10684928, 'steps': 20868, 'loss/train': 2.142228603363037}
-03/04/2022 13:58:48 - INFO - codeparrot_training - Step 20869: {'lr': 0.0004802134392299446, 'samples': 10685440, 'steps': 20869, 'loss/train': 2.1460585594177246}
-03/04/2022 13:58:50 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/04/2022 13:58:53 - INFO - codeparrot_training - Step 20870: {'lr': 0.0004802113700352566, 'samples': 10685952, 'steps': 20870, 'loss/train': 1.9857639074325562}
-03/04/2022 13:58:57 - INFO - codeparrot_training - Step 20871: {'lr': 0.00048020930073683886, 'samples': 10686464, 'steps': 20871, 'loss/train': 2.2877047061920166}
-03/04/2022 13:58:59 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 13:59:02 - INFO - codeparrot_training - Step 20872: {'lr': 0.0004802072313346924, 'samples': 10686976, 'steps': 20872, 'loss/train': 1.6700838804244995}
-03/04/2022 13:59:05 - INFO - codeparrot_training - Step 20873: {'lr': 0.00048020516182881813, 'samples': 10687488, 'steps': 20873, 'loss/train': 2.167400598526001}
-03/04/2022 13:59:07 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/04/2022 13:59:10 - INFO - codeparrot_training - Step 20874: {'lr': 0.00048020309221921686, 'samples': 10688000, 'steps': 20874, 'loss/train': 2.214726686477661}
-03/04/2022 13:59:13 - INFO - codeparrot_training - Step 20875: {'lr': 0.00048020102250588976, 'samples': 10688512, 'steps': 20875, 'loss/train': 1.4992328882217407}
-03/04/2022 13:59:15 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/04/2022 13:59:19 - INFO - codeparrot_training - Step 20876: {'lr': 0.00048019895268883764, 'samples': 10689024, 'steps': 20876, 'loss/train': 1.7187817096710205}
-03/04/2022 13:59:22 - INFO - codeparrot_training - Step 20877: {'lr': 0.0004801968827680613, 'samples': 10689536, 'steps': 20877, 'loss/train': 2.057805061340332}
-03/04/2022 13:59:24 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/04/2022 13:59:27 - INFO - codeparrot_training - Step 20878: {'lr': 0.00048019481274356194, 'samples': 10690048, 'steps': 20878, 'loss/train': 1.156369686126709}
-03/04/2022 13:59:30 - INFO - codeparrot_training - Step 20879: {'lr': 0.0004801927426153402, 'samples': 10690560, 'steps': 20879, 'loss/train': 2.293339490890503}
-03/04/2022 13:59:32 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/04/2022 13:59:36 - INFO - codeparrot_training - Step 20880: {'lr': 0.00048019067238339725, 'samples': 10691072, 'steps': 20880, 'loss/train': 2.0923233032226562}
-03/04/2022 13:59:39 - INFO - codeparrot_training - Step 20881: {'lr': 0.000480188602047734, 'samples': 10691584, 'steps': 20881, 'loss/train': 1.6031556129455566}
-03/04/2022 13:59:44 - INFO - codeparrot_training - Step 20882: {'lr': 0.0004801865316083512, 'samples': 10692096, 'steps': 20882, 'loss/train': 2.1488945484161377}
-03/04/2022 13:59:47 - INFO - codeparrot_training - Step 20883: {'lr': 0.0004801844610652499, 'samples': 10692608, 'steps': 20883, 'loss/train': 1.5937058925628662}
-03/04/2022 13:59:49 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/04/2022 13:59:53 - INFO - codeparrot_training - Step 20884: {'lr': 0.0004801823904184311, 'samples': 10693120, 'steps': 20884, 'loss/train': 2.144099235534668}
-03/04/2022 13:59:56 - INFO - codeparrot_training - Step 20885: {'lr': 0.00048018031966789564, 'samples': 10693632, 'steps': 20885, 'loss/train': 2.1497116088867188}
-03/04/2022 13:59:58 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/04/2022 14:00:02 - INFO - codeparrot_training - Step 20886: {'lr': 0.0004801782488136445, 'samples': 10694144, 'steps': 20886, 'loss/train': 1.049652099609375}
-03/04/2022 14:00:05 - INFO - codeparrot_training - Step 20887: {'lr': 0.00048017617785567855, 'samples': 10694656, 'steps': 20887, 'loss/train': 1.0194826126098633}
-03/04/2022 14:00:08 - INFO - codeparrot_training - Step 20888: {'lr': 0.00048017410679399876, 'samples': 10695168, 'steps': 20888, 'loss/train': 0.33174365758895874}
-03/04/2022 14:00:08 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/04/2022 14:00:13 - INFO - codeparrot_training - Step 20889: {'lr': 0.00048017203562860614, 'samples': 10695680, 'steps': 20889, 'loss/train': 0.7849172949790955}
-03/04/2022 14:00:16 - INFO - codeparrot_training - Step 20890: {'lr': 0.0004801699643595015, 'samples': 10696192, 'steps': 20890, 'loss/train': 2.1856367588043213}
-03/04/2022 14:00:17 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/04/2022 14:00:22 - INFO - codeparrot_training - Step 20891: {'lr': 0.00048016789298668583, 'samples': 10696704, 'steps': 20891, 'loss/train': 0.7068802714347839}
-03/04/2022 14:00:25 - INFO - codeparrot_training - Step 20892: {'lr': 0.0004801658215101601, 'samples': 10697216, 'steps': 20892, 'loss/train': 2.197996139526367}
-03/04/2022 14:00:25 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/04/2022 14:00:30 - INFO - codeparrot_training - Step 20893: {'lr': 0.00048016374992992516, 'samples': 10697728, 'steps': 20893, 'loss/train': 1.6651238203048706}
-03/04/2022 14:00:33 - INFO - codeparrot_training - Step 20894: {'lr': 0.000480161678245982, 'samples': 10698240, 'steps': 20894, 'loss/train': 1.8614627122879028}
-03/04/2022 14:00:34 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/04/2022 14:00:39 - INFO - codeparrot_training - Step 20895: {'lr': 0.0004801596064583315, 'samples': 10698752, 'steps': 20895, 'loss/train': 1.5763322114944458}
-03/04/2022 14:00:42 - INFO - codeparrot_training - Step 20896: {'lr': 0.00048015753456697466, 'samples': 10699264, 'steps': 20896, 'loss/train': 1.7777482271194458}
-03/04/2022 14:00:42 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 14:00:47 - INFO - codeparrot_training - Step 20897: {'lr': 0.00048015546257191243, 'samples': 10699776, 'steps': 20897, 'loss/train': 2.374885320663452}
-03/04/2022 14:00:50 - INFO - codeparrot_training - Step 20898: {'lr': 0.00048015339047314566, 'samples': 10700288, 'steps': 20898, 'loss/train': 0.5673134326934814}
-03/04/2022 14:00:51 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/04/2022 14:00:56 - INFO - codeparrot_training - Step 20899: {'lr': 0.00048015131827067534, 'samples': 10700800, 'steps': 20899, 'loss/train': 2.348464012145996}
-03/04/2022 14:00:59 - INFO - codeparrot_training - Step 20900: {'lr': 0.0004801492459645024, 'samples': 10701312, 'steps': 20900, 'loss/train': 1.106835961341858}
-03/04/2022 14:01:00 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 14:01:04 - INFO - codeparrot_training - Step 20901: {'lr': 0.0004801471735546277, 'samples': 10701824, 'steps': 20901, 'loss/train': 1.5124635696411133}
-03/04/2022 14:01:07 - INFO - codeparrot_training - Step 20902: {'lr': 0.0004801451010410522, 'samples': 10702336, 'steps': 20902, 'loss/train': 1.7611114978790283}
-03/04/2022 14:01:08 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 14:01:13 - INFO - codeparrot_training - Step 20903: {'lr': 0.000480143028423777, 'samples': 10702848, 'steps': 20903, 'loss/train': 1.1506478786468506}
-03/04/2022 14:01:16 - INFO - codeparrot_training - Step 20904: {'lr': 0.0004801409557028028, 'samples': 10703360, 'steps': 20904, 'loss/train': 1.01083242893219}
-03/04/2022 14:01:17 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 14:01:21 - INFO - codeparrot_training - Step 20905: {'lr': 0.0004801388828781307, 'samples': 10703872, 'steps': 20905, 'loss/train': 2.435297727584839}
-03/04/2022 14:01:24 - INFO - codeparrot_training - Step 20906: {'lr': 0.00048013680994976154, 'samples': 10704384, 'steps': 20906, 'loss/train': 1.0091973543167114}
-03/04/2022 14:01:25 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/04/2022 14:01:30 - INFO - codeparrot_training - Step 20907: {'lr': 0.0004801347369176963, 'samples': 10704896, 'steps': 20907, 'loss/train': 0.6503301858901978}
-03/04/2022 14:01:33 - INFO - codeparrot_training - Step 20908: {'lr': 0.00048013266378193586, 'samples': 10705408, 'steps': 20908, 'loss/train': 2.2979490756988525}
-03/04/2022 14:01:34 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/04/2022 14:01:38 - INFO - codeparrot_training - Step 20909: {'lr': 0.00048013059054248134, 'samples': 10705920, 'steps': 20909, 'loss/train': 1.460168719291687}
-03/04/2022 14:01:41 - INFO - codeparrot_training - Step 20910: {'lr': 0.00048012851719933335, 'samples': 10706432, 'steps': 20910, 'loss/train': 2.3421051502227783}
-03/04/2022 14:01:42 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/04/2022 14:01:47 - INFO - codeparrot_training - Step 20911: {'lr': 0.000480126443752493, 'samples': 10706944, 'steps': 20911, 'loss/train': 2.89636492729187}
-03/04/2022 14:01:50 - INFO - codeparrot_training - Step 20912: {'lr': 0.0004801243702019614, 'samples': 10707456, 'steps': 20912, 'loss/train': 1.5734823942184448}
-03/04/2022 14:01:50 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 14:01:55 - INFO - codeparrot_training - Step 20913: {'lr': 0.00048012229654773915, 'samples': 10707968, 'steps': 20913, 'loss/train': 1.6774368286132812}
-03/04/2022 14:01:58 - INFO - codeparrot_training - Step 20914: {'lr': 0.0004801202227898274, 'samples': 10708480, 'steps': 20914, 'loss/train': 2.2911112308502197}
-03/04/2022 14:01:59 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/04/2022 14:02:04 - INFO - codeparrot_training - Step 20915: {'lr': 0.00048011814892822704, 'samples': 10708992, 'steps': 20915, 'loss/train': 1.8135896921157837}
-03/04/2022 14:02:07 - INFO - codeparrot_training - Step 20916: {'lr': 0.00048011607496293896, 'samples': 10709504, 'steps': 20916, 'loss/train': 6.612919330596924}
-03/04/2022 14:02:08 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/04/2022 14:02:12 - INFO - codeparrot_training - Step 20917: {'lr': 0.0004801140008939642, 'samples': 10710016, 'steps': 20917, 'loss/train': 2.074500560760498}
-03/04/2022 14:02:15 - INFO - codeparrot_training - Step 20918: {'lr': 0.00048011192672130356, 'samples': 10710528, 'steps': 20918, 'loss/train': 2.1148486137390137}
-03/04/2022 14:02:18 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 14:02:21 - INFO - codeparrot_training - Step 20919: {'lr': 0.000480109852444958, 'samples': 10711040, 'steps': 20919, 'loss/train': 2.084437370300293}
-03/04/2022 14:02:24 - INFO - codeparrot_training - Step 20920: {'lr': 0.0004801077780649286, 'samples': 10711552, 'steps': 20920, 'loss/train': 1.447923183441162}
-03/04/2022 14:02:26 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 14:02:29 - INFO - codeparrot_training - Step 20921: {'lr': 0.00048010570358121606, 'samples': 10712064, 'steps': 20921, 'loss/train': 0.7491136789321899}
-03/04/2022 14:02:32 - INFO - codeparrot_training - Step 20922: {'lr': 0.0004801036289938215, 'samples': 10712576, 'steps': 20922, 'loss/train': 2.1448090076446533}
-03/04/2022 14:02:35 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/04/2022 14:02:38 - INFO - codeparrot_training - Step 20923: {'lr': 0.0004801015543027458, 'samples': 10713088, 'steps': 20923, 'loss/train': 1.3634004592895508}
-03/04/2022 14:02:41 - INFO - codeparrot_training - Step 20924: {'lr': 0.0004800994795079899, 'samples': 10713600, 'steps': 20924, 'loss/train': 1.8497120141983032}
-03/04/2022 14:02:44 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/04/2022 14:02:46 - INFO - codeparrot_training - Step 20925: {'lr': 0.00048009740460955465, 'samples': 10714112, 'steps': 20925, 'loss/train': 4.047117710113525}
-03/04/2022 14:02:49 - INFO - codeparrot_training - Step 20926: {'lr': 0.00048009532960744116, 'samples': 10714624, 'steps': 20926, 'loss/train': 1.832513689994812}
-03/04/2022 14:02:52 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/04/2022 14:02:55 - INFO - codeparrot_training - Step 20927: {'lr': 0.0004800932545016502, 'samples': 10715136, 'steps': 20927, 'loss/train': 1.8530898094177246}
-03/04/2022 14:02:58 - INFO - codeparrot_training - Step 20928: {'lr': 0.0004800911792921828, 'samples': 10715648, 'steps': 20928, 'loss/train': 1.5409419536590576}
-03/04/2022 14:03:00 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/04/2022 14:03:03 - INFO - codeparrot_training - Step 20929: {'lr': 0.0004800891039790399, 'samples': 10716160, 'steps': 20929, 'loss/train': 1.2101333141326904}
-03/04/2022 14:03:06 - INFO - codeparrot_training - Step 20930: {'lr': 0.00048008702856222233, 'samples': 10716672, 'steps': 20930, 'loss/train': 1.9573794603347778}
-03/04/2022 14:03:09 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/04/2022 14:03:12 - INFO - codeparrot_training - Step 20931: {'lr': 0.0004800849530417312, 'samples': 10717184, 'steps': 20931, 'loss/train': 2.1005876064300537}
-03/04/2022 14:03:15 - INFO - codeparrot_training - Step 20932: {'lr': 0.00048008287741756715, 'samples': 10717696, 'steps': 20932, 'loss/train': 2.5953757762908936}
-03/04/2022 14:03:18 - INFO - codeparrot_training - Step 20933: {'lr': 0.00048008080168973144, 'samples': 10718208, 'steps': 20933, 'loss/train': 1.108125925064087}
-03/04/2022 14:03:18 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/04/2022 14:03:23 - INFO - codeparrot_training - Step 20934: {'lr': 0.00048007872585822486, 'samples': 10718720, 'steps': 20934, 'loss/train': 6.591165065765381}
-03/04/2022 14:03:27 - INFO - codeparrot_training - Step 20935: {'lr': 0.00048007664992304834, 'samples': 10719232, 'steps': 20935, 'loss/train': 2.307241678237915}
-03/04/2022 14:03:27 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 14:03:32 - INFO - codeparrot_training - Step 20936: {'lr': 0.0004800745738842029, 'samples': 10719744, 'steps': 20936, 'loss/train': 2.2226650714874268}
-03/04/2022 14:03:35 - INFO - codeparrot_training - Step 20937: {'lr': 0.0004800724977416894, 'samples': 10720256, 'steps': 20937, 'loss/train': 1.2777947187423706}
-03/04/2022 14:03:35 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/04/2022 14:03:40 - INFO - codeparrot_training - Step 20938: {'lr': 0.00048007042149550866, 'samples': 10720768, 'steps': 20938, 'loss/train': 1.9590764045715332}
-03/04/2022 14:03:44 - INFO - codeparrot_training - Step 20939: {'lr': 0.00048006834514566183, 'samples': 10721280, 'steps': 20939, 'loss/train': 2.402327299118042}
-03/04/2022 14:03:44 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/04/2022 14:03:49 - INFO - codeparrot_training - Step 20940: {'lr': 0.00048006626869214977, 'samples': 10721792, 'steps': 20940, 'loss/train': 2.055049419403076}
-03/04/2022 14:03:52 - INFO - codeparrot_training - Step 20941: {'lr': 0.00048006419213497334, 'samples': 10722304, 'steps': 20941, 'loss/train': 1.448603868484497}
-03/04/2022 14:03:52 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/04/2022 14:03:57 - INFO - codeparrot_training - Step 20942: {'lr': 0.0004800621154741335, 'samples': 10722816, 'steps': 20942, 'loss/train': 2.7676401138305664}
-03/04/2022 14:04:00 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/04/2022 14:04:03 - INFO - codeparrot_training - Step 20943: {'lr': 0.00048006003870963135, 'samples': 10723328, 'steps': 20943, 'loss/train': 2.422480344772339}
-03/04/2022 14:04:06 - INFO - codeparrot_training - Step 20944: {'lr': 0.0004800579618414676, 'samples': 10723840, 'steps': 20944, 'loss/train': 2.5437510013580322}
-03/04/2022 14:04:09 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 14:04:11 - INFO - codeparrot_training - Step 20945: {'lr': 0.0004800558848696433, 'samples': 10724352, 'steps': 20945, 'loss/train': 1.9272394180297852}
-03/04/2022 14:04:14 - INFO - codeparrot_training - Step 20946: {'lr': 0.0004800538077941594, 'samples': 10724864, 'steps': 20946, 'loss/train': 3.2978649139404297}
-03/04/2022 14:04:17 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 14:04:20 - INFO - codeparrot_training - Step 20947: {'lr': 0.00048005173061501673, 'samples': 10725376, 'steps': 20947, 'loss/train': 2.176875352859497}
-03/04/2022 14:04:23 - INFO - codeparrot_training - Step 20948: {'lr': 0.0004800496533322164, 'samples': 10725888, 'steps': 20948, 'loss/train': 1.7226618528366089}
-03/04/2022 14:04:26 - INFO - codeparrot_training - Step 20949: {'lr': 0.00048004757594575923, 'samples': 10726400, 'steps': 20949, 'loss/train': 2.182947874069214}
-03/04/2022 14:04:26 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/04/2022 14:04:32 - INFO - codeparrot_training - Step 20950: {'lr': 0.0004800454984556461, 'samples': 10726912, 'steps': 20950, 'loss/train': 2.4146082401275635}
-03/04/2022 14:04:35 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/04/2022 14:04:37 - INFO - codeparrot_training - Step 20951: {'lr': 0.00048004342086187805, 'samples': 10727424, 'steps': 20951, 'loss/train': 0.6538257598876953}
-03/04/2022 14:04:41 - INFO - codeparrot_training - Step 20952: {'lr': 0.000480041343164456, 'samples': 10727936, 'steps': 20952, 'loss/train': 1.0694661140441895}
-03/04/2022 14:04:43 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/04/2022 14:04:46 - INFO - codeparrot_training - Step 20953: {'lr': 0.0004800392653633808, 'samples': 10728448, 'steps': 20953, 'loss/train': 1.3556169271469116}
-03/04/2022 14:04:50 - INFO - codeparrot_training - Step 20954: {'lr': 0.0004800371874586535, 'samples': 10728960, 'steps': 20954, 'loss/train': 1.6540600061416626}
-03/04/2022 14:04:52 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/04/2022 14:04:55 - INFO - codeparrot_training - Step 20955: {'lr': 0.0004800351094502751, 'samples': 10729472, 'steps': 20955, 'loss/train': 0.1891086995601654}
-03/04/2022 14:04:58 - INFO - codeparrot_training - Step 20956: {'lr': 0.00048003303133824633, 'samples': 10729984, 'steps': 20956, 'loss/train': 2.4375791549682617}
-03/04/2022 14:05:01 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 14:05:03 - INFO - codeparrot_training - Step 20957: {'lr': 0.0004800309531225683, 'samples': 10730496, 'steps': 20957, 'loss/train': 2.1612603664398193}
-03/04/2022 14:05:06 - INFO - codeparrot_training - Step 20958: {'lr': 0.00048002887480324175, 'samples': 10731008, 'steps': 20958, 'loss/train': 1.142179012298584}
-03/04/2022 14:05:09 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/04/2022 14:05:12 - INFO - codeparrot_training - Step 20959: {'lr': 0.0004800267963802678, 'samples': 10731520, 'steps': 20959, 'loss/train': 2.0623273849487305}
-03/04/2022 14:05:15 - INFO - codeparrot_training - Step 20960: {'lr': 0.0004800247178536473, 'samples': 10732032, 'steps': 20960, 'loss/train': 1.951095700263977}
-03/04/2022 14:05:17 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/04/2022 14:05:20 - INFO - codeparrot_training - Step 20961: {'lr': 0.0004800226392233813, 'samples': 10732544, 'steps': 20961, 'loss/train': 1.7979859113693237}
-03/04/2022 14:05:23 - INFO - codeparrot_training - Step 20962: {'lr': 0.00048002056048947054, 'samples': 10733056, 'steps': 20962, 'loss/train': 2.0531952381134033}
-03/04/2022 14:05:26 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 14:05:29 - INFO - codeparrot_training - Step 20963: {'lr': 0.0004800184816519161, 'samples': 10733568, 'steps': 20963, 'loss/train': 1.2084144353866577}
-03/04/2022 14:05:32 - INFO - codeparrot_training - Step 20964: {'lr': 0.0004800164027107189, 'samples': 10734080, 'steps': 20964, 'loss/train': 0.9265140891075134}
-03/04/2022 14:05:34 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/04/2022 14:05:37 - INFO - codeparrot_training - Step 20965: {'lr': 0.0004800143236658798, 'samples': 10734592, 'steps': 20965, 'loss/train': 2.211191177368164}
-03/04/2022 14:05:40 - INFO - codeparrot_training - Step 20966: {'lr': 0.0004800122445173999, 'samples': 10735104, 'steps': 20966, 'loss/train': 1.792712688446045}
-03/04/2022 14:05:42 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 14:05:45 - INFO - codeparrot_training - Step 20967: {'lr': 0.00048001016526528, 'samples': 10735616, 'steps': 20967, 'loss/train': 0.8221688270568848}
-03/04/2022 14:05:49 - INFO - codeparrot_training - Step 20968: {'lr': 0.00048000808590952106, 'samples': 10736128, 'steps': 20968, 'loss/train': 2.807900905609131}
-03/04/2022 14:05:50 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 14:05:54 - INFO - codeparrot_training - Step 20969: {'lr': 0.0004800060064501239, 'samples': 10736640, 'steps': 20969, 'loss/train': 1.5611026287078857}
-03/04/2022 14:05:57 - INFO - codeparrot_training - Step 20970: {'lr': 0.00048000392688708976, 'samples': 10737152, 'steps': 20970, 'loss/train': 1.8889790773391724}
-03/04/2022 14:05:59 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/04/2022 14:06:02 - INFO - codeparrot_training - Step 20971: {'lr': 0.00048000184722041934, 'samples': 10737664, 'steps': 20971, 'loss/train': 2.887594699859619}
-03/04/2022 14:06:06 - INFO - codeparrot_training - Step 20972: {'lr': 0.00047999976745011366, 'samples': 10738176, 'steps': 20972, 'loss/train': 1.2868293523788452}
-03/04/2022 14:06:08 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/04/2022 14:06:11 - INFO - codeparrot_training - Step 20973: {'lr': 0.0004799976875761736, 'samples': 10738688, 'steps': 20973, 'loss/train': 2.1198692321777344}
-03/04/2022 14:06:14 - INFO - codeparrot_training - Step 20974: {'lr': 0.00047999560759860006, 'samples': 10739200, 'steps': 20974, 'loss/train': 1.9696040153503418}
-03/04/2022 14:06:17 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/04/2022 14:06:19 - INFO - codeparrot_training - Step 20975: {'lr': 0.00047999352751739414, 'samples': 10739712, 'steps': 20975, 'loss/train': 6.751706123352051}
-03/04/2022 14:06:23 - INFO - codeparrot_training - Step 20976: {'lr': 0.0004799914473325567, 'samples': 10740224, 'steps': 20976, 'loss/train': 2.803312063217163}
-03/04/2022 14:06:25 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 14:06:28 - INFO - codeparrot_training - Step 20977: {'lr': 0.00047998936704408865, 'samples': 10740736, 'steps': 20977, 'loss/train': 1.6607009172439575}
-03/04/2022 14:06:31 - INFO - codeparrot_training - Step 20978: {'lr': 0.00047998728665199085, 'samples': 10741248, 'steps': 20978, 'loss/train': 1.9760867357254028}
-03/04/2022 14:06:35 - INFO - codeparrot_training - Step 20979: {'lr': 0.00047998520615626447, 'samples': 10741760, 'steps': 20979, 'loss/train': 2.697526454925537}
-03/04/2022 14:06:35 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/04/2022 14:06:40 - INFO - codeparrot_training - Step 20980: {'lr': 0.0004799831255569102, 'samples': 10742272, 'steps': 20980, 'loss/train': 2.7061853408813477}
-03/04/2022 14:06:43 - INFO - codeparrot_training - Step 20981: {'lr': 0.00047998104485392915, 'samples': 10742784, 'steps': 20981, 'loss/train': 1.7697581052780151}
-03/04/2022 14:06:43 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/04/2022 14:06:48 - INFO - codeparrot_training - Step 20982: {'lr': 0.0004799789640473221, 'samples': 10743296, 'steps': 20982, 'loss/train': 2.2667737007141113}
-03/04/2022 14:06:51 - INFO - codeparrot_training - Step 20983: {'lr': 0.0004799768831370902, 'samples': 10743808, 'steps': 20983, 'loss/train': 2.551400661468506}
-03/04/2022 14:06:52 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/04/2022 14:06:57 - INFO - codeparrot_training - Step 20984: {'lr': 0.0004799748021232342, 'samples': 10744320, 'steps': 20984, 'loss/train': 2.3130695819854736}
-03/04/2022 14:07:00 - INFO - codeparrot_training - Step 20985: {'lr': 0.00047997272100575505, 'samples': 10744832, 'steps': 20985, 'loss/train': 2.0080254077911377}
-03/04/2022 14:07:00 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/04/2022 14:07:05 - INFO - codeparrot_training - Step 20986: {'lr': 0.00047997063978465383, 'samples': 10745344, 'steps': 20986, 'loss/train': 2.0402441024780273}
-03/04/2022 14:07:08 - INFO - codeparrot_training - Step 20987: {'lr': 0.0004799685584599313, 'samples': 10745856, 'steps': 20987, 'loss/train': 1.6427807807922363}
-03/04/2022 14:07:09 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/04/2022 14:07:14 - INFO - codeparrot_training - Step 20988: {'lr': 0.00047996647703158857, 'samples': 10746368, 'steps': 20988, 'loss/train': 2.0794150829315186}
-03/04/2022 14:07:17 - INFO - codeparrot_training - Step 20989: {'lr': 0.00047996439549962647, 'samples': 10746880, 'steps': 20989, 'loss/train': 2.5017802715301514}
-03/04/2022 14:07:18 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 14:07:22 - INFO - codeparrot_training - Step 20990: {'lr': 0.00047996231386404593, 'samples': 10747392, 'steps': 20990, 'loss/train': 1.7806341648101807}
-03/04/2022 14:07:25 - INFO - codeparrot_training - Step 20991: {'lr': 0.00047996023212484797, 'samples': 10747904, 'steps': 20991, 'loss/train': 1.590509295463562}
-03/04/2022 14:07:26 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 14:07:31 - INFO - codeparrot_training - Step 20992: {'lr': 0.00047995815028203346, 'samples': 10748416, 'steps': 20992, 'loss/train': 2.24640154838562}
-03/04/2022 14:07:34 - INFO - codeparrot_training - Step 20993: {'lr': 0.00047995606833560337, 'samples': 10748928, 'steps': 20993, 'loss/train': 1.8359594345092773}
-03/04/2022 14:07:35 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/04/2022 14:07:39 - INFO - codeparrot_training - Step 20994: {'lr': 0.0004799539862855585, 'samples': 10749440, 'steps': 20994, 'loss/train': 1.5833895206451416}
-03/04/2022 14:07:42 - INFO - codeparrot_training - Step 20995: {'lr': 0.00047995190413190004, 'samples': 10749952, 'steps': 20995, 'loss/train': 2.503422737121582}
-03/04/2022 14:07:43 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/04/2022 14:07:48 - INFO - codeparrot_training - Step 20996: {'lr': 0.00047994982187462876, 'samples': 10750464, 'steps': 20996, 'loss/train': 2.1112051010131836}
-03/04/2022 14:07:51 - INFO - codeparrot_training - Step 20997: {'lr': 0.0004799477395137457, 'samples': 10750976, 'steps': 20997, 'loss/train': 1.7586954832077026}
-03/04/2022 14:07:52 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/04/2022 14:07:56 - INFO - codeparrot_training - Step 20998: {'lr': 0.00047994565704925166, 'samples': 10751488, 'steps': 20998, 'loss/train': 1.296667218208313}
-03/04/2022 14:07:59 - INFO - codeparrot_training - Step 20999: {'lr': 0.0004799435744811477, 'samples': 10752000, 'steps': 20999, 'loss/train': 1.3900771141052246}
-03/04/2022 14:08:00 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/04/2022 14:08:05 - INFO - codeparrot_training - Step 21000: {'lr': 0.0004799414918094347, 'samples': 10752512, 'steps': 21000, 'loss/train': 1.9416128396987915}
-03/04/2022 14:08:08 - INFO - codeparrot_training - Step 21001: {'lr': 0.0004799394090341136, 'samples': 10753024, 'steps': 21001, 'loss/train': 1.7562849521636963}
-03/04/2022 14:08:09 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 14:08:13 - INFO - codeparrot_training - Step 21002: {'lr': 0.0004799373261551854, 'samples': 10753536, 'steps': 21002, 'loss/train': 1.7214233875274658}
-03/04/2022 14:08:17 - INFO - codeparrot_training - Step 21003: {'lr': 0.0004799352431726509, 'samples': 10754048, 'steps': 21003, 'loss/train': 1.6033939123153687}
-03/04/2022 14:08:17 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/04/2022 14:08:22 - INFO - codeparrot_training - Step 21004: {'lr': 0.0004799331600865112, 'samples': 10754560, 'steps': 21004, 'loss/train': 1.4792697429656982}
-03/04/2022 14:08:25 - INFO - codeparrot_training - Step 21005: {'lr': 0.0004799310768967671, 'samples': 10755072, 'steps': 21005, 'loss/train': 1.6898143291473389}
-03/04/2022 14:08:26 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/04/2022 14:08:30 - INFO - codeparrot_training - Step 21006: {'lr': 0.00047992899360341966, 'samples': 10755584, 'steps': 21006, 'loss/train': 1.9339125156402588}
-03/04/2022 14:08:34 - INFO - codeparrot_training - Step 21007: {'lr': 0.0004799269102064698, 'samples': 10756096, 'steps': 21007, 'loss/train': 1.8577698469161987}
-03/04/2022 14:08:35 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/04/2022 14:08:39 - INFO - codeparrot_training - Step 21008: {'lr': 0.0004799248267059183, 'samples': 10756608, 'steps': 21008, 'loss/train': 3.099095106124878}
-03/04/2022 14:08:42 - INFO - codeparrot_training - Step 21009: {'lr': 0.0004799227431017663, 'samples': 10757120, 'steps': 21009, 'loss/train': 1.3929773569107056}
-03/04/2022 14:08:43 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 14:08:47 - INFO - codeparrot_training - Step 21010: {'lr': 0.0004799206593940147, 'samples': 10757632, 'steps': 21010, 'loss/train': 1.6412585973739624}
-03/04/2022 14:08:51 - INFO - codeparrot_training - Step 21011: {'lr': 0.0004799185755826644, 'samples': 10758144, 'steps': 21011, 'loss/train': 2.2008609771728516}
-03/04/2022 14:08:52 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/04/2022 14:08:56 - INFO - codeparrot_training - Step 21012: {'lr': 0.00047991649166771624, 'samples': 10758656, 'steps': 21012, 'loss/train': 1.2843642234802246}
-03/04/2022 14:08:59 - INFO - codeparrot_training - Step 21013: {'lr': 0.00047991440764917127, 'samples': 10759168, 'steps': 21013, 'loss/train': 2.390031099319458}
-03/04/2022 14:09:00 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 14:09:04 - INFO - codeparrot_training - Step 21014: {'lr': 0.0004799123235270305, 'samples': 10759680, 'steps': 21014, 'loss/train': 1.5562835931777954}
-03/04/2022 14:09:07 - INFO - codeparrot_training - Step 21015: {'lr': 0.0004799102393012947, 'samples': 10760192, 'steps': 21015, 'loss/train': 2.2148594856262207}
-03/04/2022 14:09:09 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 14:09:13 - INFO - codeparrot_training - Step 21016: {'lr': 0.0004799081549719649, 'samples': 10760704, 'steps': 21016, 'loss/train': 2.123008966445923}
-03/04/2022 14:09:17 - INFO - codeparrot_training - Step 21017: {'lr': 0.0004799060705390421, 'samples': 10761216, 'steps': 21017, 'loss/train': 1.887379765510559}
-03/04/2022 14:09:20 - INFO - codeparrot_training - Step 21018: {'lr': 0.00047990398600252713, 'samples': 10761728, 'steps': 21018, 'loss/train': 2.049764633178711}
-03/04/2022 14:09:21 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/04/2022 14:09:25 - INFO - codeparrot_training - Step 21019: {'lr': 0.00047990190136242103, 'samples': 10762240, 'steps': 21019, 'loss/train': 2.232881546020508}
-03/04/2022 14:09:28 - INFO - codeparrot_training - Step 21020: {'lr': 0.0004798998166187246, 'samples': 10762752, 'steps': 21020, 'loss/train': 2.300814151763916}
-03/04/2022 14:09:29 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 14:09:33 - INFO - codeparrot_training - Step 21021: {'lr': 0.0004798977317714389, 'samples': 10763264, 'steps': 21021, 'loss/train': 2.5423784255981445}
-03/04/2022 14:09:37 - INFO - codeparrot_training - Step 21022: {'lr': 0.00047989564682056487, 'samples': 10763776, 'steps': 21022, 'loss/train': 2.376940965652466}
-03/04/2022 14:09:38 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 14:09:42 - INFO - codeparrot_training - Step 21023: {'lr': 0.0004798935617661033, 'samples': 10764288, 'steps': 21023, 'loss/train': 1.8303455114364624}
-03/04/2022 14:09:45 - INFO - codeparrot_training - Step 21024: {'lr': 0.0004798914766080553, 'samples': 10764800, 'steps': 21024, 'loss/train': 1.8974179029464722}
-03/04/2022 14:09:46 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/04/2022 14:09:50 - INFO - codeparrot_training - Step 21025: {'lr': 0.00047988939134642174, 'samples': 10765312, 'steps': 21025, 'loss/train': 3.2753186225891113}
-03/04/2022 14:09:54 - INFO - codeparrot_training - Step 21026: {'lr': 0.00047988730598120356, 'samples': 10765824, 'steps': 21026, 'loss/train': 1.611180305480957}
-03/04/2022 14:09:55 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/04/2022 14:09:59 - INFO - codeparrot_training - Step 21027: {'lr': 0.00047988522051240173, 'samples': 10766336, 'steps': 21027, 'loss/train': 1.8409048318862915}
-03/04/2022 14:10:02 - INFO - codeparrot_training - Step 21028: {'lr': 0.0004798831349400172, 'samples': 10766848, 'steps': 21028, 'loss/train': 2.9157004356384277}
-03/04/2022 14:10:03 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/04/2022 14:10:07 - INFO - codeparrot_training - Step 21029: {'lr': 0.0004798810492640508, 'samples': 10767360, 'steps': 21029, 'loss/train': 0.5771483182907104}
-03/04/2022 14:10:10 - INFO - codeparrot_training - Step 21030: {'lr': 0.00047987896348450354, 'samples': 10767872, 'steps': 21030, 'loss/train': 1.7507086992263794}
-03/04/2022 14:10:12 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/04/2022 14:10:16 - INFO - codeparrot_training - Step 21031: {'lr': 0.00047987687760137646, 'samples': 10768384, 'steps': 21031, 'loss/train': 2.245497465133667}
-03/04/2022 14:10:19 - INFO - codeparrot_training - Step 21032: {'lr': 0.00047987479161467033, 'samples': 10768896, 'steps': 21032, 'loss/train': 2.177969217300415}
-03/04/2022 14:10:20 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 14:10:24 - INFO - codeparrot_training - Step 21033: {'lr': 0.0004798727055243862, 'samples': 10769408, 'steps': 21033, 'loss/train': 1.567217469215393}
-03/04/2022 14:10:27 - INFO - codeparrot_training - Step 21034: {'lr': 0.000479870619330525, 'samples': 10769920, 'steps': 21034, 'loss/train': 2.0709125995635986}
-03/04/2022 14:10:29 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 14:10:33 - INFO - codeparrot_training - Step 21035: {'lr': 0.0004798685330330876, 'samples': 10770432, 'steps': 21035, 'loss/train': 1.8080439567565918}
-03/04/2022 14:10:36 - INFO - codeparrot_training - Step 21036: {'lr': 0.000479866446632075, 'samples': 10770944, 'steps': 21036, 'loss/train': 2.0826783180236816}
-03/04/2022 14:10:37 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 14:10:41 - INFO - codeparrot_training - Step 21037: {'lr': 0.00047986436012748815, 'samples': 10771456, 'steps': 21037, 'loss/train': 1.887762188911438}
-03/04/2022 14:10:44 - INFO - codeparrot_training - Step 21038: {'lr': 0.00047986227351932785, 'samples': 10771968, 'steps': 21038, 'loss/train': 1.950585126876831}
-03/04/2022 14:10:45 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 14:10:50 - INFO - codeparrot_training - Step 21039: {'lr': 0.00047986018680759525, 'samples': 10772480, 'steps': 21039, 'loss/train': 1.5664708614349365}
-03/04/2022 14:10:53 - INFO - codeparrot_training - Step 21040: {'lr': 0.00047985809999229125, 'samples': 10772992, 'steps': 21040, 'loss/train': 2.358828544616699}
-03/04/2022 14:10:55 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/04/2022 14:10:58 - INFO - codeparrot_training - Step 21041: {'lr': 0.00047985601307341667, 'samples': 10773504, 'steps': 21041, 'loss/train': 2.6842236518859863}
-03/04/2022 14:11:01 - INFO - codeparrot_training - Step 21042: {'lr': 0.0004798539260509725, 'samples': 10774016, 'steps': 21042, 'loss/train': 1.2840571403503418}
-03/04/2022 14:11:04 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 14:11:07 - INFO - codeparrot_training - Step 21043: {'lr': 0.00047985183892495977, 'samples': 10774528, 'steps': 21043, 'loss/train': 2.5035223960876465}
-03/04/2022 14:11:10 - INFO - codeparrot_training - Step 21044: {'lr': 0.00047984975169537925, 'samples': 10775040, 'steps': 21044, 'loss/train': 2.1038990020751953}
-03/04/2022 14:11:12 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/04/2022 14:11:15 - INFO - codeparrot_training - Step 21045: {'lr': 0.00047984766436223205, 'samples': 10775552, 'steps': 21045, 'loss/train': 1.960594654083252}
-03/04/2022 14:11:18 - INFO - codeparrot_training - Step 21046: {'lr': 0.000479845576925519, 'samples': 10776064, 'steps': 21046, 'loss/train': 1.6092848777770996}
-03/04/2022 14:11:21 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/04/2022 14:11:24 - INFO - codeparrot_training - Step 21047: {'lr': 0.00047984348938524113, 'samples': 10776576, 'steps': 21047, 'loss/train': 1.8981611728668213}
-03/04/2022 14:11:27 - INFO - codeparrot_training - Step 21048: {'lr': 0.00047984140174139926, 'samples': 10777088, 'steps': 21048, 'loss/train': 1.8008337020874023}
-03/04/2022 14:11:29 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/04/2022 14:11:32 - INFO - codeparrot_training - Step 21049: {'lr': 0.0004798393139939945, 'samples': 10777600, 'steps': 21049, 'loss/train': 1.901609182357788}
-03/04/2022 14:11:35 - INFO - codeparrot_training - Step 21050: {'lr': 0.0004798372261430276, 'samples': 10778112, 'steps': 21050, 'loss/train': 1.91522216796875}
-03/04/2022 14:11:37 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 14:11:41 - INFO - codeparrot_training - Step 21051: {'lr': 0.00047983513818849967, 'samples': 10778624, 'steps': 21051, 'loss/train': 2.1081037521362305}
-03/04/2022 14:11:44 - INFO - codeparrot_training - Step 21052: {'lr': 0.0004798330501304115, 'samples': 10779136, 'steps': 21052, 'loss/train': 1.9694583415985107}
-03/04/2022 14:11:46 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/04/2022 14:11:49 - INFO - codeparrot_training - Step 21053: {'lr': 0.00047983096196876413, 'samples': 10779648, 'steps': 21053, 'loss/train': 1.954062581062317}
-03/04/2022 14:11:52 - INFO - codeparrot_training - Step 21054: {'lr': 0.00047982887370355846, 'samples': 10780160, 'steps': 21054, 'loss/train': 2.002750873565674}
-03/04/2022 14:11:55 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 14:11:58 - INFO - codeparrot_training - Step 21055: {'lr': 0.0004798267853347955, 'samples': 10780672, 'steps': 21055, 'loss/train': 1.5530085563659668}
-03/04/2022 14:12:01 - INFO - codeparrot_training - Step 21056: {'lr': 0.0004798246968624761, 'samples': 10781184, 'steps': 21056, 'loss/train': 1.9373832941055298}
-03/04/2022 14:12:03 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 14:12:06 - INFO - codeparrot_training - Step 21057: {'lr': 0.00047982260828660124, 'samples': 10781696, 'steps': 21057, 'loss/train': 1.8972980976104736}
-03/04/2022 14:12:09 - INFO - codeparrot_training - Step 21058: {'lr': 0.0004798205196071719, 'samples': 10782208, 'steps': 21058, 'loss/train': 2.7910962104797363}
-03/04/2022 14:12:12 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/04/2022 14:12:15 - INFO - codeparrot_training - Step 21059: {'lr': 0.00047981843082418884, 'samples': 10782720, 'steps': 21059, 'loss/train': 2.2382314205169678}
-03/04/2022 14:12:18 - INFO - codeparrot_training - Step 21060: {'lr': 0.0004798163419376533, 'samples': 10783232, 'steps': 21060, 'loss/train': 2.063704490661621}
-03/04/2022 14:12:20 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/04/2022 14:12:23 - INFO - codeparrot_training - Step 21061: {'lr': 0.00047981425294756595, 'samples': 10783744, 'steps': 21061, 'loss/train': 1.33449387550354}
-03/04/2022 14:12:26 - INFO - codeparrot_training - Step 21062: {'lr': 0.00047981216385392796, 'samples': 10784256, 'steps': 21062, 'loss/train': 2.142117500305176}
-03/04/2022 14:12:28 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/04/2022 14:12:32 - INFO - codeparrot_training - Step 21063: {'lr': 0.0004798100746567401, 'samples': 10784768, 'steps': 21063, 'loss/train': 2.1613659858703613}
-03/04/2022 14:12:35 - INFO - codeparrot_training - Step 21064: {'lr': 0.00047980798535600334, 'samples': 10785280, 'steps': 21064, 'loss/train': 2.1160268783569336}
-03/04/2022 14:12:37 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/04/2022 14:12:40 - INFO - codeparrot_training - Step 21065: {'lr': 0.00047980589595171866, 'samples': 10785792, 'steps': 21065, 'loss/train': 1.4669512510299683}
-03/04/2022 14:12:43 - INFO - codeparrot_training - Step 21066: {'lr': 0.000479803806443887, 'samples': 10786304, 'steps': 21066, 'loss/train': 2.2270255088806152}
-03/04/2022 14:12:45 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 14:12:48 - INFO - codeparrot_training - Step 21067: {'lr': 0.0004798017168325093, 'samples': 10786816, 'steps': 21067, 'loss/train': 2.0607972145080566}
-03/04/2022 14:12:51 - INFO - codeparrot_training - Step 21068: {'lr': 0.0004797996271175865, 'samples': 10787328, 'steps': 21068, 'loss/train': 1.4589486122131348}
-03/04/2022 14:12:53 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/04/2022 14:12:57 - INFO - codeparrot_training - Step 21069: {'lr': 0.00047979753729911944, 'samples': 10787840, 'steps': 21069, 'loss/train': 2.265150785446167}
-03/04/2022 14:13:00 - INFO - codeparrot_training - Step 21070: {'lr': 0.00047979544737710925, 'samples': 10788352, 'steps': 21070, 'loss/train': 1.6598445177078247}
-03/04/2022 14:13:01 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/04/2022 14:13:05 - INFO - codeparrot_training - Step 21071: {'lr': 0.00047979335735155677, 'samples': 10788864, 'steps': 21071, 'loss/train': 1.4378305673599243}
-03/04/2022 14:13:09 - INFO - codeparrot_training - Step 21072: {'lr': 0.00047979126722246294, 'samples': 10789376, 'steps': 21072, 'loss/train': 2.14701771736145}
-03/04/2022 14:13:11 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 14:13:14 - INFO - codeparrot_training - Step 21073: {'lr': 0.0004797891769898287, 'samples': 10789888, 'steps': 21073, 'loss/train': 2.206808567047119}
-03/04/2022 14:13:17 - INFO - codeparrot_training - Step 21074: {'lr': 0.00047978708665365503, 'samples': 10790400, 'steps': 21074, 'loss/train': 1.7821307182312012}
-03/04/2022 14:13:20 - INFO - codeparrot_training - Step 21075: {'lr': 0.0004797849962139428, 'samples': 10790912, 'steps': 21075, 'loss/train': 2.60322642326355}
-03/04/2022 14:13:20 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 14:13:26 - INFO - codeparrot_training - Step 21076: {'lr': 0.00047978290567069306, 'samples': 10791424, 'steps': 21076, 'loss/train': 1.3353028297424316}
-03/04/2022 14:13:29 - INFO - codeparrot_training - Step 21077: {'lr': 0.00047978081502390656, 'samples': 10791936, 'steps': 21077, 'loss/train': 2.302077531814575}
-03/04/2022 14:13:29 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 14:13:34 - INFO - codeparrot_training - Step 21078: {'lr': 0.0004797787242735845, 'samples': 10792448, 'steps': 21078, 'loss/train': 1.8832178115844727}
-03/04/2022 14:13:37 - INFO - codeparrot_training - Step 21079: {'lr': 0.00047977663341972765, 'samples': 10792960, 'steps': 21079, 'loss/train': 1.789940595626831}
-03/04/2022 14:13:37 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/04/2022 14:13:43 - INFO - codeparrot_training - Step 21080: {'lr': 0.00047977454246233696, 'samples': 10793472, 'steps': 21080, 'loss/train': 1.8167808055877686}
-03/04/2022 14:13:46 - INFO - codeparrot_training - Step 21081: {'lr': 0.00047977245140141354, 'samples': 10793984, 'steps': 21081, 'loss/train': 2.1022427082061768}
-03/04/2022 14:13:46 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 14:13:51 - INFO - codeparrot_training - Step 21082: {'lr': 0.00047977036023695807, 'samples': 10794496, 'steps': 21082, 'loss/train': 2.226292848587036}
-03/04/2022 14:13:54 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/04/2022 14:13:56 - INFO - codeparrot_training - Step 21083: {'lr': 0.00047976826896897165, 'samples': 10795008, 'steps': 21083, 'loss/train': 1.9705091714859009}
-03/04/2022 14:13:59 - INFO - codeparrot_training - Step 21084: {'lr': 0.0004797661775974552, 'samples': 10795520, 'steps': 21084, 'loss/train': 2.0154731273651123}
-03/04/2022 14:14:02 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/04/2022 14:14:05 - INFO - codeparrot_training - Step 21085: {'lr': 0.00047976408612240964, 'samples': 10796032, 'steps': 21085, 'loss/train': 1.8506687879562378}
-03/04/2022 14:14:08 - INFO - codeparrot_training - Step 21086: {'lr': 0.00047976199454383595, 'samples': 10796544, 'steps': 21086, 'loss/train': 1.7181332111358643}
-03/04/2022 14:14:11 - INFO - codeparrot_training - Step 21087: {'lr': 0.00047975990286173504, 'samples': 10797056, 'steps': 21087, 'loss/train': 0.6872444748878479}
-03/04/2022 14:14:11 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/04/2022 14:14:17 - INFO - codeparrot_training - Step 21088: {'lr': 0.00047975781107610784, 'samples': 10797568, 'steps': 21088, 'loss/train': 1.6296441555023193}
-03/04/2022 14:14:20 - INFO - codeparrot_training - Step 21089: {'lr': 0.0004797557191869554, 'samples': 10798080, 'steps': 21089, 'loss/train': 2.564734697341919}
-03/04/2022 14:14:20 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/04/2022 14:14:25 - INFO - codeparrot_training - Step 21090: {'lr': 0.0004797536271942785, 'samples': 10798592, 'steps': 21090, 'loss/train': 2.3377904891967773}
-03/04/2022 14:14:28 - INFO - codeparrot_training - Step 21091: {'lr': 0.00047975153509807815, 'samples': 10799104, 'steps': 21091, 'loss/train': 1.4904173612594604}
-03/04/2022 14:14:29 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 14:14:33 - INFO - codeparrot_training - Step 21092: {'lr': 0.0004797494428983553, 'samples': 10799616, 'steps': 21092, 'loss/train': 1.7046700716018677}
-03/04/2022 14:14:37 - INFO - codeparrot_training - Step 21093: {'lr': 0.000479747350595111, 'samples': 10800128, 'steps': 21093, 'loss/train': 1.6265757083892822}
-03/04/2022 14:14:37 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/04/2022 14:14:42 - INFO - codeparrot_training - Step 21094: {'lr': 0.00047974525818834604, 'samples': 10800640, 'steps': 21094, 'loss/train': 1.2710318565368652}
-03/04/2022 14:14:45 - INFO - codeparrot_training - Step 21095: {'lr': 0.0004797431656780613, 'samples': 10801152, 'steps': 21095, 'loss/train': 0.3854876756668091}
-03/04/2022 14:14:45 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/04/2022 14:14:50 - INFO - codeparrot_training - Step 21096: {'lr': 0.000479741073064258, 'samples': 10801664, 'steps': 21096, 'loss/train': 2.340409517288208}
-03/04/2022 14:14:54 - INFO - codeparrot_training - Step 21097: {'lr': 0.0004797389803469369, 'samples': 10802176, 'steps': 21097, 'loss/train': 2.3350300788879395}
-03/04/2022 14:14:54 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/04/2022 14:14:59 - INFO - codeparrot_training - Step 21098: {'lr': 0.0004797368875260988, 'samples': 10802688, 'steps': 21098, 'loss/train': 0.8781698942184448}
-03/04/2022 14:15:02 - INFO - codeparrot_training - Step 21099: {'lr': 0.00047973479460174497, 'samples': 10803200, 'steps': 21099, 'loss/train': 1.9037513732910156}
-03/04/2022 14:15:02 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/04/2022 14:15:07 - INFO - codeparrot_training - Step 21100: {'lr': 0.00047973270157387605, 'samples': 10803712, 'steps': 21100, 'loss/train': 1.9518972635269165}
-03/04/2022 14:15:10 - INFO - codeparrot_training - Step 21101: {'lr': 0.0004797306084424932, 'samples': 10804224, 'steps': 21101, 'loss/train': 1.909010887145996}
-03/04/2022 14:15:11 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 14:15:16 - INFO - codeparrot_training - Step 21102: {'lr': 0.0004797285152075973, 'samples': 10804736, 'steps': 21102, 'loss/train': 2.565692663192749}
-03/04/2022 14:15:19 - INFO - codeparrot_training - Step 21103: {'lr': 0.00047972642186918925, 'samples': 10805248, 'steps': 21103, 'loss/train': 1.776336669921875}
-03/04/2022 14:15:19 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 14:15:24 - INFO - codeparrot_training - Step 21104: {'lr': 0.00047972432842727003, 'samples': 10805760, 'steps': 21104, 'loss/train': 1.6379461288452148}
-03/04/2022 14:15:28 - INFO - codeparrot_training - Step 21105: {'lr': 0.0004797222348818405, 'samples': 10806272, 'steps': 21105, 'loss/train': 1.8836085796356201}
-03/04/2022 14:15:28 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 14:15:33 - INFO - codeparrot_training - Step 21106: {'lr': 0.00047972014123290183, 'samples': 10806784, 'steps': 21106, 'loss/train': 1.0955758094787598}
-03/04/2022 14:15:36 - INFO - codeparrot_training - Step 21107: {'lr': 0.00047971804748045464, 'samples': 10807296, 'steps': 21107, 'loss/train': 2.4363014698028564}
-03/04/2022 14:15:36 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/04/2022 14:15:41 - INFO - codeparrot_training - Step 21108: {'lr': 0.00047971595362450014, 'samples': 10807808, 'steps': 21108, 'loss/train': 1.5124515295028687}
-03/04/2022 14:15:44 - INFO - codeparrot_training - Step 21109: {'lr': 0.00047971385966503923, 'samples': 10808320, 'steps': 21109, 'loss/train': 1.6728283166885376}
-03/04/2022 14:15:44 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/04/2022 14:15:50 - INFO - codeparrot_training - Step 21110: {'lr': 0.0004797117656020727, 'samples': 10808832, 'steps': 21110, 'loss/train': 2.0742056369781494}
-03/04/2022 14:15:53 - INFO - codeparrot_training - Step 21111: {'lr': 0.0004797096714356016, 'samples': 10809344, 'steps': 21111, 'loss/train': 0.3206772804260254}
-03/04/2022 14:15:53 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 14:15:59 - INFO - codeparrot_training - Step 21112: {'lr': 0.0004797075771656269, 'samples': 10809856, 'steps': 21112, 'loss/train': 0.6569735407829285}
-03/04/2022 14:16:02 - INFO - codeparrot_training - Step 21113: {'lr': 0.0004797054827921495, 'samples': 10810368, 'steps': 21113, 'loss/train': 2.222818613052368}
-03/04/2022 14:16:06 - INFO - codeparrot_training - Step 21114: {'lr': 0.0004797033883151703, 'samples': 10810880, 'steps': 21114, 'loss/train': 1.4898802042007446}
-03/04/2022 14:16:07 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 14:16:11 - INFO - codeparrot_training - Step 21115: {'lr': 0.0004797012937346904, 'samples': 10811392, 'steps': 21115, 'loss/train': 2.8644816875457764}
-03/04/2022 14:16:14 - INFO - codeparrot_training - Step 21116: {'lr': 0.0004796991990507106, 'samples': 10811904, 'steps': 21116, 'loss/train': 2.0687501430511475}
-03/04/2022 14:16:16 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/04/2022 14:16:19 - INFO - codeparrot_training - Step 21117: {'lr': 0.00047969710426323185, 'samples': 10812416, 'steps': 21117, 'loss/train': 1.5901048183441162}
-03/04/2022 14:16:22 - INFO - codeparrot_training - Step 21118: {'lr': 0.0004796950093722552, 'samples': 10812928, 'steps': 21118, 'loss/train': 1.8892055749893188}
-03/04/2022 14:16:24 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/04/2022 14:16:28 - INFO - codeparrot_training - Step 21119: {'lr': 0.00047969291437778143, 'samples': 10813440, 'steps': 21119, 'loss/train': 1.3112480640411377}
-03/04/2022 14:16:31 - INFO - codeparrot_training - Step 21120: {'lr': 0.00047969081927981165, 'samples': 10813952, 'steps': 21120, 'loss/train': 1.636164903640747}
-03/04/2022 14:16:33 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/04/2022 14:16:36 - INFO - codeparrot_training - Step 21121: {'lr': 0.0004796887240783467, 'samples': 10814464, 'steps': 21121, 'loss/train': 1.861754059791565}
-03/04/2022 14:16:39 - INFO - codeparrot_training - Step 21122: {'lr': 0.0004796866287733875, 'samples': 10814976, 'steps': 21122, 'loss/train': 1.8809359073638916}
-03/04/2022 14:16:41 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/04/2022 14:16:45 - INFO - codeparrot_training - Step 21123: {'lr': 0.0004796845333649352, 'samples': 10815488, 'steps': 21123, 'loss/train': 1.9858554601669312}
-03/04/2022 14:16:48 - INFO - codeparrot_training - Step 21124: {'lr': 0.00047968243785299046, 'samples': 10816000, 'steps': 21124, 'loss/train': 2.4395761489868164}
-03/04/2022 14:16:50 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/04/2022 14:16:53 - INFO - codeparrot_training - Step 21125: {'lr': 0.0004796803422375544, 'samples': 10816512, 'steps': 21125, 'loss/train': 2.148000717163086}
-03/04/2022 14:16:56 - INFO - codeparrot_training - Step 21126: {'lr': 0.0004796782465186279, 'samples': 10817024, 'steps': 21126, 'loss/train': 2.086805582046509}
-03/04/2022 14:16:58 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/04/2022 14:17:02 - INFO - codeparrot_training - Step 21127: {'lr': 0.00047967615069621197, 'samples': 10817536, 'steps': 21127, 'loss/train': 2.1219265460968018}
-03/04/2022 14:17:05 - INFO - codeparrot_training - Step 21128: {'lr': 0.0004796740547703075, 'samples': 10818048, 'steps': 21128, 'loss/train': 1.184230923652649}
-03/04/2022 14:17:06 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/04/2022 14:17:10 - INFO - codeparrot_training - Step 21129: {'lr': 0.00047967195874091547, 'samples': 10818560, 'steps': 21129, 'loss/train': 3.0659241676330566}
-03/04/2022 14:17:13 - INFO - codeparrot_training - Step 21130: {'lr': 0.00047966986260803676, 'samples': 10819072, 'steps': 21130, 'loss/train': 0.58502596616745}
-03/04/2022 14:17:15 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/04/2022 14:17:18 - INFO - codeparrot_training - Step 21131: {'lr': 0.0004796677663716723, 'samples': 10819584, 'steps': 21131, 'loss/train': 1.8203253746032715}
-03/04/2022 14:17:21 - INFO - codeparrot_training - Step 21132: {'lr': 0.00047966567003182315, 'samples': 10820096, 'steps': 21132, 'loss/train': 1.6295959949493408}
-03/04/2022 14:17:23 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/04/2022 14:17:27 - INFO - codeparrot_training - Step 21133: {'lr': 0.0004796635735884902, 'samples': 10820608, 'steps': 21133, 'loss/train': 1.7200300693511963}
-03/04/2022 14:17:30 - INFO - codeparrot_training - Step 21134: {'lr': 0.0004796614770416744, 'samples': 10821120, 'steps': 21134, 'loss/train': 2.2141950130462646}
-03/04/2022 14:17:31 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 14:17:35 - INFO - codeparrot_training - Step 21135: {'lr': 0.00047965938039137666, 'samples': 10821632, 'steps': 21135, 'loss/train': 1.9960881471633911}
-03/04/2022 14:17:39 - INFO - codeparrot_training - Step 21136: {'lr': 0.000479657283637598, 'samples': 10822144, 'steps': 21136, 'loss/train': 1.7144848108291626}
-03/04/2022 14:17:40 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/04/2022 14:17:44 - INFO - codeparrot_training - Step 21137: {'lr': 0.00047965518678033924, 'samples': 10822656, 'steps': 21137, 'loss/train': 1.7283679246902466}
-03/04/2022 14:17:47 - INFO - codeparrot_training - Step 21138: {'lr': 0.00047965308981960143, 'samples': 10823168, 'steps': 21138, 'loss/train': 0.9877696633338928}
-03/04/2022 14:17:48 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/04/2022 14:17:52 - INFO - codeparrot_training - Step 21139: {'lr': 0.0004796509927553854, 'samples': 10823680, 'steps': 21139, 'loss/train': 1.753754734992981}
-03/04/2022 14:17:55 - INFO - codeparrot_training - Step 21140: {'lr': 0.00047964889558769233, 'samples': 10824192, 'steps': 21140, 'loss/train': 1.286018967628479}
-03/04/2022 14:17:57 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/04/2022 14:18:01 - INFO - codeparrot_training - Step 21141: {'lr': 0.00047964679831652294, 'samples': 10824704, 'steps': 21141, 'loss/train': 1.8315149545669556}
-03/04/2022 14:18:04 - INFO - codeparrot_training - Step 21142: {'lr': 0.00047964470094187815, 'samples': 10825216, 'steps': 21142, 'loss/train': 2.1816277503967285}
-03/04/2022 14:18:05 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 14:18:09 - INFO - codeparrot_training - Step 21143: {'lr': 0.0004796426034637591, 'samples': 10825728, 'steps': 21143, 'loss/train': 2.2653775215148926}
-03/04/2022 14:18:12 - INFO - codeparrot_training - Step 21144: {'lr': 0.0004796405058821666, 'samples': 10826240, 'steps': 21144, 'loss/train': 1.5483577251434326}
-03/04/2022 14:18:14 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/04/2022 14:18:17 - INFO - codeparrot_training - Step 21145: {'lr': 0.0004796384081971017, 'samples': 10826752, 'steps': 21145, 'loss/train': 2.0517871379852295}
-03/04/2022 14:18:21 - INFO - codeparrot_training - Step 21146: {'lr': 0.0004796363104085652, 'samples': 10827264, 'steps': 21146, 'loss/train': 0.9529291391372681}
-03/04/2022 14:18:22 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 14:18:26 - INFO - codeparrot_training - Step 21147: {'lr': 0.00047963421251655817, 'samples': 10827776, 'steps': 21147, 'loss/train': 1.492002248764038}
-03/04/2022 14:18:29 - INFO - codeparrot_training - Step 21148: {'lr': 0.00047963211452108144, 'samples': 10828288, 'steps': 21148, 'loss/train': 2.3942465782165527}
-03/04/2022 14:18:31 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/04/2022 14:18:34 - INFO - codeparrot_training - Step 21149: {'lr': 0.0004796300164221361, 'samples': 10828800, 'steps': 21149, 'loss/train': 2.0873513221740723}
-03/04/2022 14:18:38 - INFO - codeparrot_training - Step 21150: {'lr': 0.00047962791821972296, 'samples': 10829312, 'steps': 21150, 'loss/train': 1.69476318359375}
-03/04/2022 14:18:40 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/04/2022 14:18:43 - INFO - codeparrot_training - Step 21151: {'lr': 0.00047962581991384305, 'samples': 10829824, 'steps': 21151, 'loss/train': 1.4095745086669922}
-03/04/2022 14:18:46 - INFO - codeparrot_training - Step 21152: {'lr': 0.0004796237215044973, 'samples': 10830336, 'steps': 21152, 'loss/train': 2.3897125720977783}
-03/04/2022 14:18:50 - INFO - codeparrot_training - Step 21153: {'lr': 0.0004796216229916867, 'samples': 10830848, 'steps': 21153, 'loss/train': 1.0487030744552612}
-03/04/2022 14:18:50 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 14:18:55 - INFO - codeparrot_training - Step 21154: {'lr': 0.000479619524375412, 'samples': 10831360, 'steps': 21154, 'loss/train': 2.096177101135254}
-03/04/2022 14:18:58 - INFO - codeparrot_training - Step 21155: {'lr': 0.0004796174256556744, 'samples': 10831872, 'steps': 21155, 'loss/train': 1.7782570123672485}
-03/04/2022 14:18:58 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 14:19:03 - INFO - codeparrot_training - Step 21156: {'lr': 0.0004796153268324747, 'samples': 10832384, 'steps': 21156, 'loss/train': 2.2128190994262695}
-03/04/2022 14:19:07 - INFO - codeparrot_training - Step 21157: {'lr': 0.00047961322790581384, 'samples': 10832896, 'steps': 21157, 'loss/train': 1.3381930589675903}
-03/04/2022 14:19:07 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/04/2022 14:19:12 - INFO - codeparrot_training - Step 21158: {'lr': 0.00047961112887569285, 'samples': 10833408, 'steps': 21158, 'loss/train': 2.3194620609283447}
-03/04/2022 14:19:15 - INFO - codeparrot_training - Step 21159: {'lr': 0.0004796090297421126, 'samples': 10833920, 'steps': 21159, 'loss/train': 1.6068179607391357}
-03/04/2022 14:19:15 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 14:19:20 - INFO - codeparrot_training - Step 21160: {'lr': 0.0004796069305050741, 'samples': 10834432, 'steps': 21160, 'loss/train': 2.635826826095581}
-03/04/2022 14:19:24 - INFO - codeparrot_training - Step 21161: {'lr': 0.0004796048311645782, 'samples': 10834944, 'steps': 21161, 'loss/train': 1.6798481941223145}
-03/04/2022 14:19:25 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/04/2022 14:19:29 - INFO - codeparrot_training - Step 21162: {'lr': 0.00047960273172062596, 'samples': 10835456, 'steps': 21162, 'loss/train': 2.228679895401001}
-03/04/2022 14:19:32 - INFO - codeparrot_training - Step 21163: {'lr': 0.00047960063217321824, 'samples': 10835968, 'steps': 21163, 'loss/train': 1.3766992092132568}
-03/04/2022 14:19:33 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/04/2022 14:19:37 - INFO - codeparrot_training - Step 21164: {'lr': 0.0004795985325223561, 'samples': 10836480, 'steps': 21164, 'loss/train': 1.5830128192901611}
-03/04/2022 14:19:40 - INFO - codeparrot_training - Step 21165: {'lr': 0.00047959643276804026, 'samples': 10836992, 'steps': 21165, 'loss/train': 0.8572365641593933}
-03/04/2022 14:19:41 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/04/2022 14:19:46 - INFO - codeparrot_training - Step 21166: {'lr': 0.0004795943329102719, 'samples': 10837504, 'steps': 21166, 'loss/train': 1.6668130159378052}
-03/04/2022 14:19:49 - INFO - codeparrot_training - Step 21167: {'lr': 0.00047959223294905185, 'samples': 10838016, 'steps': 21167, 'loss/train': 2.3324332237243652}
-03/04/2022 14:19:50 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/04/2022 14:19:54 - INFO - codeparrot_training - Step 21168: {'lr': 0.00047959013288438113, 'samples': 10838528, 'steps': 21168, 'loss/train': 1.7264528274536133}
-03/04/2022 14:19:57 - INFO - codeparrot_training - Step 21169: {'lr': 0.0004795880327162606, 'samples': 10839040, 'steps': 21169, 'loss/train': 2.182647466659546}
-03/04/2022 14:19:58 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/04/2022 14:20:03 - INFO - codeparrot_training - Step 21170: {'lr': 0.0004795859324446912, 'samples': 10839552, 'steps': 21170, 'loss/train': 1.8980892896652222}
-03/04/2022 14:20:06 - INFO - codeparrot_training - Step 21171: {'lr': 0.000479583832069674, 'samples': 10840064, 'steps': 21171, 'loss/train': 0.9141941070556641}
-03/04/2022 14:20:07 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/04/2022 14:20:11 - INFO - codeparrot_training - Step 21172: {'lr': 0.00047958173159120984, 'samples': 10840576, 'steps': 21172, 'loss/train': 2.176936626434326}
-03/04/2022 14:20:14 - INFO - codeparrot_training - Step 21173: {'lr': 0.0004795796310092997, 'samples': 10841088, 'steps': 21173, 'loss/train': 0.3896430432796478}
-03/04/2022 14:20:16 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/04/2022 14:20:19 - INFO - codeparrot_training - Step 21174: {'lr': 0.00047957753032394445, 'samples': 10841600, 'steps': 21174, 'loss/train': 1.7506471872329712}
-03/04/2022 14:20:23 - INFO - codeparrot_training - Step 21175: {'lr': 0.00047957542953514523, 'samples': 10842112, 'steps': 21175, 'loss/train': 1.6608985662460327}
-03/04/2022 14:20:24 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 14:20:28 - INFO - codeparrot_training - Step 21176: {'lr': 0.00047957332864290283, 'samples': 10842624, 'steps': 21176, 'loss/train': 1.8469350337982178}
-03/04/2022 14:20:31 - INFO - codeparrot_training - Step 21177: {'lr': 0.00047957122764721817, 'samples': 10843136, 'steps': 21177, 'loss/train': 2.1154544353485107}
-03/04/2022 14:20:32 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/04/2022 14:20:36 - INFO - codeparrot_training - Step 21178: {'lr': 0.00047956912654809227, 'samples': 10843648, 'steps': 21178, 'loss/train': 1.2120853662490845}
-03/04/2022 14:20:40 - INFO - codeparrot_training - Step 21179: {'lr': 0.0004795670253455261, 'samples': 10844160, 'steps': 21179, 'loss/train': 1.3024139404296875}
-03/04/2022 14:20:41 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 14:20:45 - INFO - codeparrot_training - Step 21180: {'lr': 0.00047956492403952055, 'samples': 10844672, 'steps': 21180, 'loss/train': 1.7748509645462036}
-03/04/2022 14:20:48 - INFO - codeparrot_training - Step 21181: {'lr': 0.00047956282263007663, 'samples': 10845184, 'steps': 21181, 'loss/train': 1.1602504253387451}
-03/04/2022 14:20:49 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/04/2022 14:20:53 - INFO - codeparrot_training - Step 21182: {'lr': 0.00047956072111719517, 'samples': 10845696, 'steps': 21182, 'loss/train': 1.948672890663147}
-03/04/2022 14:20:57 - INFO - codeparrot_training - Step 21183: {'lr': 0.00047955861950087724, 'samples': 10846208, 'steps': 21183, 'loss/train': 1.7772477865219116}
-03/04/2022 14:20:57 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/04/2022 14:21:02 - INFO - codeparrot_training - Step 21184: {'lr': 0.00047955651778112376, 'samples': 10846720, 'steps': 21184, 'loss/train': 2.0294008255004883}
-03/04/2022 14:21:05 - INFO - codeparrot_training - Step 21185: {'lr': 0.00047955441595793556, 'samples': 10847232, 'steps': 21185, 'loss/train': 2.0014960765838623}
-03/04/2022 14:21:06 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/04/2022 14:21:10 - INFO - codeparrot_training - Step 21186: {'lr': 0.0004795523140313138, 'samples': 10847744, 'steps': 21186, 'loss/train': 2.378399610519409}
-03/04/2022 14:21:13 - INFO - codeparrot_training - Step 21187: {'lr': 0.00047955021200125924, 'samples': 10848256, 'steps': 21187, 'loss/train': 1.92316472530365}
-03/04/2022 14:21:14 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 14:21:19 - INFO - codeparrot_training - Step 21188: {'lr': 0.0004795481098677729, 'samples': 10848768, 'steps': 21188, 'loss/train': 1.6132185459136963}
-03/04/2022 14:21:22 - INFO - codeparrot_training - Step 21189: {'lr': 0.00047954600763085577, 'samples': 10849280, 'steps': 21189, 'loss/train': 1.5404436588287354}
-03/04/2022 14:21:23 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/04/2022 14:21:28 - INFO - codeparrot_training - Step 21190: {'lr': 0.0004795439052905087, 'samples': 10849792, 'steps': 21190, 'loss/train': 2.15837025642395}
-03/04/2022 14:21:31 - INFO - codeparrot_training - Step 21191: {'lr': 0.0004795418028467327, 'samples': 10850304, 'steps': 21191, 'loss/train': 1.824462890625}
-03/04/2022 14:21:32 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 14:21:36 - INFO - codeparrot_training - Step 21192: {'lr': 0.0004795397002995288, 'samples': 10850816, 'steps': 21192, 'loss/train': 1.597153663635254}
-03/04/2022 14:21:39 - INFO - codeparrot_training - Step 21193: {'lr': 0.0004795375976488977, 'samples': 10851328, 'steps': 21193, 'loss/train': 0.21810907125473022}
-03/04/2022 14:21:41 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 14:21:44 - INFO - codeparrot_training - Step 21194: {'lr': 0.00047953549489484056, 'samples': 10851840, 'steps': 21194, 'loss/train': 1.9583873748779297}
-03/04/2022 14:21:47 - INFO - codeparrot_training - Step 21195: {'lr': 0.0004795333920373583, 'samples': 10852352, 'steps': 21195, 'loss/train': 1.7765870094299316}
-03/04/2022 14:21:49 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/04/2022 14:21:53 - INFO - codeparrot_training - Step 21196: {'lr': 0.00047953128907645185, 'samples': 10852864, 'steps': 21196, 'loss/train': 1.6495625972747803}
-03/04/2022 14:21:56 - INFO - codeparrot_training - Step 21197: {'lr': 0.000479529186012122, 'samples': 10853376, 'steps': 21197, 'loss/train': 2.202082395553589}
-03/04/2022 14:21:57 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/04/2022 14:22:01 - INFO - codeparrot_training - Step 21198: {'lr': 0.00047952708284437, 'samples': 10853888, 'steps': 21198, 'loss/train': 1.6591230630874634}
-03/04/2022 14:22:04 - INFO - codeparrot_training - Step 21199: {'lr': 0.0004795249795731966, 'samples': 10854400, 'steps': 21199, 'loss/train': 2.1426596641540527}
-03/04/2022 14:22:06 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 14:22:10 - INFO - codeparrot_training - Step 21200: {'lr': 0.00047952287619860273, 'samples': 10854912, 'steps': 21200, 'loss/train': 2.395808219909668}
-03/04/2022 14:22:13 - INFO - codeparrot_training - Step 21201: {'lr': 0.0004795207727205895, 'samples': 10855424, 'steps': 21201, 'loss/train': 1.162631869316101}
-03/04/2022 14:22:14 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/04/2022 14:22:18 - INFO - codeparrot_training - Step 21202: {'lr': 0.00047951866913915767, 'samples': 10855936, 'steps': 21202, 'loss/train': 2.3184118270874023}
-03/04/2022 14:22:21 - INFO - codeparrot_training - Step 21203: {'lr': 0.0004795165654543082, 'samples': 10856448, 'steps': 21203, 'loss/train': 1.7647569179534912}
-03/04/2022 14:22:23 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 14:22:26 - INFO - codeparrot_training - Step 21204: {'lr': 0.0004795144616660422, 'samples': 10856960, 'steps': 21204, 'loss/train': 1.7691354751586914}
-03/04/2022 14:22:30 - INFO - codeparrot_training - Step 21205: {'lr': 0.0004795123577743605, 'samples': 10857472, 'steps': 21205, 'loss/train': 1.7189066410064697}
-03/04/2022 14:22:31 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/04/2022 14:22:35 - INFO - codeparrot_training - Step 21206: {'lr': 0.0004795102537792641, 'samples': 10857984, 'steps': 21206, 'loss/train': 2.5308282375335693}
-03/04/2022 14:22:38 - INFO - codeparrot_training - Step 21207: {'lr': 0.000479508149680754, 'samples': 10858496, 'steps': 21207, 'loss/train': 1.822077989578247}
-03/04/2022 14:22:40 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/04/2022 14:22:43 - INFO - codeparrot_training - Step 21208: {'lr': 0.0004795060454788309, 'samples': 10859008, 'steps': 21208, 'loss/train': 1.976842999458313}
-03/04/2022 14:22:47 - INFO - codeparrot_training - Step 21209: {'lr': 0.000479503941173496, 'samples': 10859520, 'steps': 21209, 'loss/train': 1.593087077140808}
-03/04/2022 14:22:48 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/04/2022 14:22:52 - INFO - codeparrot_training - Step 21210: {'lr': 0.0004795018367647501, 'samples': 10860032, 'steps': 21210, 'loss/train': 1.2500641345977783}
-03/04/2022 14:22:55 - INFO - codeparrot_training - Step 21211: {'lr': 0.0004794997322525944, 'samples': 10860544, 'steps': 21211, 'loss/train': 0.2709581255912781}
-03/04/2022 14:22:57 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/04/2022 14:23:00 - INFO - codeparrot_training - Step 21212: {'lr': 0.0004794976276370295, 'samples': 10861056, 'steps': 21212, 'loss/train': 1.6405266523361206}
-03/04/2022 14:23:04 - INFO - codeparrot_training - Step 21213: {'lr': 0.00047949552291805654, 'samples': 10861568, 'steps': 21213, 'loss/train': 2.248438596725464}
-03/04/2022 14:23:05 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/04/2022 14:23:09 - INFO - codeparrot_training - Step 21214: {'lr': 0.0004794934180956764, 'samples': 10862080, 'steps': 21214, 'loss/train': 2.4185264110565186}
-03/04/2022 14:23:12 - INFO - codeparrot_training - Step 21215: {'lr': 0.00047949131316989016, 'samples': 10862592, 'steps': 21215, 'loss/train': 2.5255978107452393}
-03/04/2022 14:23:13 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/04/2022 14:23:17 - INFO - codeparrot_training - Step 21216: {'lr': 0.0004794892081406986, 'samples': 10863104, 'steps': 21216, 'loss/train': 0.6957576274871826}
-03/04/2022 14:23:20 - INFO - codeparrot_training - Step 21217: {'lr': 0.00047948710300810276, 'samples': 10863616, 'steps': 21217, 'loss/train': 2.071634531021118}
-03/04/2022 14:23:22 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/04/2022 14:23:26 - INFO - codeparrot_training - Step 21218: {'lr': 0.0004794849977721036, 'samples': 10864128, 'steps': 21218, 'loss/train': 2.4744577407836914}
-03/04/2022 14:23:29 - INFO - codeparrot_training - Step 21219: {'lr': 0.00047948289243270205, 'samples': 10864640, 'steps': 21219, 'loss/train': 2.1670923233032227}
-03/04/2022 14:23:30 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/04/2022 14:23:34 - INFO - codeparrot_training - Step 21220: {'lr': 0.000479480786989899, 'samples': 10865152, 'steps': 21220, 'loss/train': 1.4368562698364258}
-03/04/2022 14:23:38 - INFO - codeparrot_training - Step 21221: {'lr': 0.0004794786814436955, 'samples': 10865664, 'steps': 21221, 'loss/train': 2.2024271488189697}
-03/04/2022 14:23:40 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/04/2022 14:23:43 - INFO - codeparrot_training - Step 21222: {'lr': 0.0004794765757940924, 'samples': 10866176, 'steps': 21222, 'loss/train': 1.7404894828796387}
-03/04/2022 14:23:46 - INFO - codeparrot_training - Step 21223: {'lr': 0.00047947447004109066, 'samples': 10866688, 'steps': 21223, 'loss/train': 1.8579998016357422}
-03/04/2022 14:23:48 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 14:23:51 - INFO - codeparrot_training - Step 21224: {'lr': 0.0004794723641846914, 'samples': 10867200, 'steps': 21224, 'loss/train': 1.075830101966858}
-03/04/2022 14:23:54 - INFO - codeparrot_training - Step 21225: {'lr': 0.0004794702582248953, 'samples': 10867712, 'steps': 21225, 'loss/train': 2.50860333442688}
-03/04/2022 14:23:57 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/04/2022 14:24:00 - INFO - codeparrot_training - Step 21226: {'lr': 0.0004794681521617035, 'samples': 10868224, 'steps': 21226, 'loss/train': 0.9017037153244019}
-03/04/2022 14:24:03 - INFO - codeparrot_training - Step 21227: {'lr': 0.0004794660459951169, 'samples': 10868736, 'steps': 21227, 'loss/train': 1.7271755933761597}
-03/04/2022 14:24:05 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/04/2022 14:24:08 - INFO - codeparrot_training - Step 21228: {'lr': 0.0004794639397251365, 'samples': 10869248, 'steps': 21228, 'loss/train': 2.3620362281799316}
-03/04/2022 14:24:11 - INFO - codeparrot_training - Step 21229: {'lr': 0.00047946183335176307, 'samples': 10869760, 'steps': 21229, 'loss/train': 1.7966151237487793}
-03/04/2022 14:24:13 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/04/2022 14:24:16 - INFO - codeparrot_training - Step 21230: {'lr': 0.00047945972687499775, 'samples': 10870272, 'steps': 21230, 'loss/train': 2.0047144889831543}
-03/04/2022 14:24:19 - INFO - codeparrot_training - Step 21231: {'lr': 0.0004794576202948414, 'samples': 10870784, 'steps': 21231, 'loss/train': 2.7041053771972656}
-03/04/2022 14:24:22 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/04/2022 14:24:25 - INFO - codeparrot_training - Step 21232: {'lr': 0.000479455513611295, 'samples': 10871296, 'steps': 21232, 'loss/train': 1.4387954473495483}
-03/04/2022 14:24:28 - INFO - codeparrot_training - Step 21233: {'lr': 0.00047945340682435943, 'samples': 10871808, 'steps': 21233, 'loss/train': 0.8335886001586914}
-03/04/2022 14:24:30 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 14:24:33 - INFO - codeparrot_training - Step 21234: {'lr': 0.00047945129993403577, 'samples': 10872320, 'steps': 21234, 'loss/train': 1.9933964014053345}
-03/04/2022 14:24:36 - INFO - codeparrot_training - Step 21235: {'lr': 0.00047944919294032486, 'samples': 10872832, 'steps': 21235, 'loss/train': 1.8389767408370972}
-03/04/2022 14:24:38 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 14:24:42 - INFO - codeparrot_training - Step 21236: {'lr': 0.00047944708584322763, 'samples': 10873344, 'steps': 21236, 'loss/train': 1.8486281633377075}
-03/04/2022 14:24:45 - INFO - codeparrot_training - Step 21237: {'lr': 0.00047944497864274517, 'samples': 10873856, 'steps': 21237, 'loss/train': 4.02432107925415}
-03/04/2022 14:24:47 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 14:24:50 - INFO - codeparrot_training - Step 21238: {'lr': 0.00047944287133887834, 'samples': 10874368, 'steps': 21238, 'loss/train': 1.546904444694519}
-03/04/2022 14:24:53 - INFO - codeparrot_training - Step 21239: {'lr': 0.00047944076393162806, 'samples': 10874880, 'steps': 21239, 'loss/train': 1.6473089456558228}
-03/04/2022 14:24:55 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/04/2022 14:24:59 - INFO - codeparrot_training - Step 21240: {'lr': 0.00047943865642099525, 'samples': 10875392, 'steps': 21240, 'loss/train': 1.1174792051315308}
-03/04/2022 14:25:02 - INFO - codeparrot_training - Step 21241: {'lr': 0.00047943654880698106, 'samples': 10875904, 'steps': 21241, 'loss/train': 1.893358588218689}
-03/04/2022 14:25:04 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/04/2022 14:25:07 - INFO - codeparrot_training - Step 21242: {'lr': 0.00047943444108958623, 'samples': 10876416, 'steps': 21242, 'loss/train': 2.127570390701294}
-03/04/2022 14:25:10 - INFO - codeparrot_training - Step 21243: {'lr': 0.00047943233326881176, 'samples': 10876928, 'steps': 21243, 'loss/train': 1.6648515462875366}
-03/04/2022 14:25:13 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 14:25:16 - INFO - codeparrot_training - Step 21244: {'lr': 0.00047943022534465866, 'samples': 10877440, 'steps': 21244, 'loss/train': 2.2198119163513184}
-03/04/2022 14:25:19 - INFO - codeparrot_training - Step 21245: {'lr': 0.00047942811731712775, 'samples': 10877952, 'steps': 21245, 'loss/train': 1.7648465633392334}
-03/04/2022 14:25:21 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 14:25:24 - INFO - codeparrot_training - Step 21246: {'lr': 0.0004794260091862202, 'samples': 10878464, 'steps': 21246, 'loss/train': 1.7027069330215454}
-03/04/2022 14:25:27 - INFO - codeparrot_training - Step 21247: {'lr': 0.0004794239009519368, 'samples': 10878976, 'steps': 21247, 'loss/train': 1.7320854663848877}
-03/04/2022 14:25:30 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 14:25:33 - INFO - codeparrot_training - Step 21248: {'lr': 0.00047942179261427847, 'samples': 10879488, 'steps': 21248, 'loss/train': 1.9551740884780884}
-03/04/2022 14:25:36 - INFO - codeparrot_training - Step 21249: {'lr': 0.0004794196841732463, 'samples': 10880000, 'steps': 21249, 'loss/train': 1.5515176057815552}
-03/04/2022 14:25:39 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/04/2022 14:25:41 - INFO - codeparrot_training - Step 21250: {'lr': 0.0004794175756288411, 'samples': 10880512, 'steps': 21250, 'loss/train': 1.80269193649292}
-03/04/2022 14:25:44 - INFO - codeparrot_training - Step 21251: {'lr': 0.00047941546698106386, 'samples': 10881024, 'steps': 21251, 'loss/train': 1.7902920246124268}
-03/04/2022 14:25:47 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 14:25:50 - INFO - codeparrot_training - Step 21252: {'lr': 0.0004794133582299156, 'samples': 10881536, 'steps': 21252, 'loss/train': 1.7715116739273071}
-03/04/2022 14:25:53 - INFO - codeparrot_training - Step 21253: {'lr': 0.0004794112493753972, 'samples': 10882048, 'steps': 21253, 'loss/train': 1.9789659976959229}
-03/04/2022 14:25:55 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/04/2022 14:25:58 - INFO - codeparrot_training - Step 21254: {'lr': 0.0004794091404175097, 'samples': 10882560, 'steps': 21254, 'loss/train': 1.9713318347930908}
-03/04/2022 14:26:01 - INFO - codeparrot_training - Step 21255: {'lr': 0.00047940703135625386, 'samples': 10883072, 'steps': 21255, 'loss/train': 2.0809836387634277}
-03/04/2022 14:26:04 - INFO - codeparrot_training - Step 21256: {'lr': 0.0004794049221916308, 'samples': 10883584, 'steps': 21256, 'loss/train': 2.098627805709839}
-03/04/2022 14:26:04 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/04/2022 14:26:10 - INFO - codeparrot_training - Step 21257: {'lr': 0.00047940281292364146, 'samples': 10884096, 'steps': 21257, 'loss/train': 3.2147161960601807}
-03/04/2022 14:26:13 - INFO - codeparrot_training - Step 21258: {'lr': 0.0004794007035522867, 'samples': 10884608, 'steps': 21258, 'loss/train': 2.747690200805664}
-03/04/2022 14:26:13 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/04/2022 14:26:18 - INFO - codeparrot_training - Step 21259: {'lr': 0.0004793985940775676, 'samples': 10885120, 'steps': 21259, 'loss/train': 2.3952293395996094}
-03/04/2022 14:26:21 - INFO - codeparrot_training - Step 21260: {'lr': 0.0004793964844994849, 'samples': 10885632, 'steps': 21260, 'loss/train': 2.247006416320801}
-03/04/2022 14:26:21 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 14:26:27 - INFO - codeparrot_training - Step 21261: {'lr': 0.00047939437481803984, 'samples': 10886144, 'steps': 21261, 'loss/train': 2.2030515670776367}
-03/04/2022 14:26:30 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 14:26:32 - INFO - codeparrot_training - Step 21262: {'lr': 0.00047939226503323313, 'samples': 10886656, 'steps': 21262, 'loss/train': 1.8542122840881348}
-03/04/2022 14:26:35 - INFO - codeparrot_training - Step 21263: {'lr': 0.0004793901551450658, 'samples': 10887168, 'steps': 21263, 'loss/train': 0.8855220079421997}
-03/04/2022 14:26:38 - INFO - codeparrot_training - Step 21264: {'lr': 0.00047938804515353887, 'samples': 10887680, 'steps': 21264, 'loss/train': 2.002821207046509}
-03/04/2022 14:26:38 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/04/2022 14:26:44 - INFO - codeparrot_training - Step 21265: {'lr': 0.00047938593505865315, 'samples': 10888192, 'steps': 21265, 'loss/train': 2.742032527923584}
-03/04/2022 14:26:47 - INFO - codeparrot_training - Step 21266: {'lr': 0.00047938382486040963, 'samples': 10888704, 'steps': 21266, 'loss/train': 1.1937470436096191}
-03/04/2022 14:26:47 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 14:26:52 - INFO - codeparrot_training - Step 21267: {'lr': 0.0004793817145588094, 'samples': 10889216, 'steps': 21267, 'loss/train': 1.0652046203613281}
-03/04/2022 14:26:55 - INFO - codeparrot_training - Step 21268: {'lr': 0.0004793796041538533, 'samples': 10889728, 'steps': 21268, 'loss/train': 1.5225547552108765}
-03/04/2022 14:26:56 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 14:27:00 - INFO - codeparrot_training - Step 21269: {'lr': 0.00047937749364554226, 'samples': 10890240, 'steps': 21269, 'loss/train': 1.6688915491104126}
-03/04/2022 14:27:04 - INFO - codeparrot_training - Step 21270: {'lr': 0.0004793753830338773, 'samples': 10890752, 'steps': 21270, 'loss/train': 2.0986592769622803}
-03/04/2022 14:27:04 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/04/2022 14:27:09 - INFO - codeparrot_training - Step 21271: {'lr': 0.00047937327231885925, 'samples': 10891264, 'steps': 21271, 'loss/train': 1.4415392875671387}
-03/04/2022 14:27:12 - INFO - codeparrot_training - Step 21272: {'lr': 0.0004793711615004892, 'samples': 10891776, 'steps': 21272, 'loss/train': 2.268324375152588}
-03/04/2022 14:27:13 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/04/2022 14:27:17 - INFO - codeparrot_training - Step 21273: {'lr': 0.000479369050578768, 'samples': 10892288, 'steps': 21273, 'loss/train': 1.6223810911178589}
-03/04/2022 14:27:21 - INFO - codeparrot_training - Step 21274: {'lr': 0.0004793669395536967, 'samples': 10892800, 'steps': 21274, 'loss/train': 2.4806551933288574}
-03/04/2022 14:27:21 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/04/2022 14:27:26 - INFO - codeparrot_training - Step 21275: {'lr': 0.00047936482842527616, 'samples': 10893312, 'steps': 21275, 'loss/train': 1.9370464086532593}
-03/04/2022 14:27:29 - INFO - codeparrot_training - Step 21276: {'lr': 0.00047936271719350743, 'samples': 10893824, 'steps': 21276, 'loss/train': 0.3720245361328125}
-03/04/2022 14:27:30 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/04/2022 14:27:34 - INFO - codeparrot_training - Step 21277: {'lr': 0.0004793606058583913, 'samples': 10894336, 'steps': 21277, 'loss/train': 1.8277949094772339}
-03/04/2022 14:27:37 - INFO - codeparrot_training - Step 21278: {'lr': 0.00047935849441992887, 'samples': 10894848, 'steps': 21278, 'loss/train': 2.3039402961730957}
-03/04/2022 14:27:38 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/04/2022 14:27:43 - INFO - codeparrot_training - Step 21279: {'lr': 0.00047935638287812104, 'samples': 10895360, 'steps': 21279, 'loss/train': 2.679325580596924}
-03/04/2022 14:27:46 - INFO - codeparrot_training - Step 21280: {'lr': 0.00047935427123296884, 'samples': 10895872, 'steps': 21280, 'loss/train': 2.481029987335205}
-03/04/2022 14:27:46 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/04/2022 14:27:51 - INFO - codeparrot_training - Step 21281: {'lr': 0.000479352159484473, 'samples': 10896384, 'steps': 21281, 'loss/train': 1.6225268840789795}
-03/04/2022 14:27:54 - INFO - codeparrot_training - Step 21282: {'lr': 0.0004793500476326347, 'samples': 10896896, 'steps': 21282, 'loss/train': 1.9672857522964478}
-03/04/2022 14:27:54 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/04/2022 14:28:00 - INFO - codeparrot_training - Step 21283: {'lr': 0.0004793479356774548, 'samples': 10897408, 'steps': 21283, 'loss/train': 1.6339694261550903}
-03/04/2022 14:28:03 - INFO - codeparrot_training - Step 21284: {'lr': 0.00047934582361893423, 'samples': 10897920, 'steps': 21284, 'loss/train': 1.7789896726608276}
-03/04/2022 14:28:03 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/04/2022 14:28:08 - INFO - codeparrot_training - Step 21285: {'lr': 0.000479343711457074, 'samples': 10898432, 'steps': 21285, 'loss/train': 2.081801414489746}
-03/04/2022 14:28:11 - INFO - codeparrot_training - Step 21286: {'lr': 0.00047934159919187504, 'samples': 10898944, 'steps': 21286, 'loss/train': 1.4552674293518066}
-03/04/2022 14:28:11 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/04/2022 14:28:16 - INFO - codeparrot_training - Step 21287: {'lr': 0.0004793394868233383, 'samples': 10899456, 'steps': 21287, 'loss/train': 0.5746604800224304}
-03/04/2022 14:28:20 - INFO - codeparrot_training - Step 21288: {'lr': 0.0004793373743514647, 'samples': 10899968, 'steps': 21288, 'loss/train': 3.265566110610962}
-03/04/2022 14:28:20 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/04/2022 14:28:25 - INFO - codeparrot_training - Step 21289: {'lr': 0.0004793352617762552, 'samples': 10900480, 'steps': 21289, 'loss/train': 1.5769035816192627}
-03/04/2022 14:28:28 - INFO - codeparrot_training - Step 21290: {'lr': 0.0004793331490977108, 'samples': 10900992, 'steps': 21290, 'loss/train': 1.8881736993789673}
-03/04/2022 14:28:28 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 14:28:34 - INFO - codeparrot_training - Step 21291: {'lr': 0.0004793310363158324, 'samples': 10901504, 'steps': 21291, 'loss/train': 2.6699297428131104}
-03/04/2022 14:28:37 - INFO - codeparrot_training - Step 21292: {'lr': 0.00047932892343062103, 'samples': 10902016, 'steps': 21292, 'loss/train': 1.404732584953308}
-03/04/2022 14:28:37 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/04/2022 14:28:42 - INFO - codeparrot_training - Step 21293: {'lr': 0.00047932681044207757, 'samples': 10902528, 'steps': 21293, 'loss/train': 1.9775080680847168}
-03/04/2022 14:28:45 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/04/2022 14:28:48 - INFO - codeparrot_training - Step 21294: {'lr': 0.0004793246973502029, 'samples': 10903040, 'steps': 21294, 'loss/train': 1.6194936037063599}
-03/04/2022 14:28:51 - INFO - codeparrot_training - Step 21295: {'lr': 0.0004793225841549982, 'samples': 10903552, 'steps': 21295, 'loss/train': 0.8015040755271912}
-03/04/2022 14:28:53 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 14:28:56 - INFO - codeparrot_training - Step 21296: {'lr': 0.00047932047085646416, 'samples': 10904064, 'steps': 21296, 'loss/train': 1.8374627828598022}
-03/04/2022 14:28:59 - INFO - codeparrot_training - Step 21297: {'lr': 0.0004793183574546019, 'samples': 10904576, 'steps': 21297, 'loss/train': 0.8128302097320557}
-03/04/2022 14:29:02 - INFO - codeparrot_training - Step 21298: {'lr': 0.0004793162439494123, 'samples': 10905088, 'steps': 21298, 'loss/train': 0.6968725919723511}
-03/04/2022 14:29:03 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/04/2022 14:29:08 - INFO - codeparrot_training - Step 21299: {'lr': 0.00047931413034089644, 'samples': 10905600, 'steps': 21299, 'loss/train': 1.9320310354232788}
-03/04/2022 14:29:11 - INFO - codeparrot_training - Step 21300: {'lr': 0.00047931201662905503, 'samples': 10906112, 'steps': 21300, 'loss/train': 1.0564392805099487}
-03/04/2022 14:29:11 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 14:29:16 - INFO - codeparrot_training - Step 21301: {'lr': 0.00047930990281388927, 'samples': 10906624, 'steps': 21301, 'loss/train': 1.7168023586273193}
-03/04/2022 14:29:19 - INFO - codeparrot_training - Step 21302: {'lr': 0.00047930778889539996, 'samples': 10907136, 'steps': 21302, 'loss/train': 2.5230023860931396}
-03/04/2022 14:29:19 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/04/2022 14:29:25 - INFO - codeparrot_training - Step 21303: {'lr': 0.00047930567487358813, 'samples': 10907648, 'steps': 21303, 'loss/train': 2.559621572494507}
-03/04/2022 14:29:28 - INFO - codeparrot_training - Step 21304: {'lr': 0.00047930356074845466, 'samples': 10908160, 'steps': 21304, 'loss/train': 1.103300929069519}
-03/04/2022 14:29:29 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/04/2022 14:29:33 - INFO - codeparrot_training - Step 21305: {'lr': 0.0004793014465200005, 'samples': 10908672, 'steps': 21305, 'loss/train': 1.5795378684997559}
-03/04/2022 14:29:36 - INFO - codeparrot_training - Step 21306: {'lr': 0.0004792993321882267, 'samples': 10909184, 'steps': 21306, 'loss/train': 0.7476072311401367}
-03/04/2022 14:29:37 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 14:29:42 - INFO - codeparrot_training - Step 21307: {'lr': 0.0004792972177531342, 'samples': 10909696, 'steps': 21307, 'loss/train': 3.5414369106292725}
-03/04/2022 14:29:45 - INFO - codeparrot_training - Step 21308: {'lr': 0.0004792951032147239, 'samples': 10910208, 'steps': 21308, 'loss/train': 2.594623327255249}
-03/04/2022 14:29:45 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 14:29:50 - INFO - codeparrot_training - Step 21309: {'lr': 0.00047929298857299677, 'samples': 10910720, 'steps': 21309, 'loss/train': 2.068553924560547}
-03/04/2022 14:29:53 - INFO - codeparrot_training - Step 21310: {'lr': 0.00047929087382795374, 'samples': 10911232, 'steps': 21310, 'loss/train': 1.318542242050171}
-03/04/2022 14:29:54 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/04/2022 14:29:59 - INFO - codeparrot_training - Step 21311: {'lr': 0.0004792887589795957, 'samples': 10911744, 'steps': 21311, 'loss/train': 1.2751250267028809}
-03/04/2022 14:30:02 - INFO - codeparrot_training - Step 21312: {'lr': 0.00047928664402792376, 'samples': 10912256, 'steps': 21312, 'loss/train': 1.4075323343276978}
-03/04/2022 14:30:02 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 14:30:07 - INFO - codeparrot_training - Step 21313: {'lr': 0.0004792845289729388, 'samples': 10912768, 'steps': 21313, 'loss/train': 2.446117877960205}
-03/04/2022 14:30:10 - INFO - codeparrot_training - Step 21314: {'lr': 0.00047928241381464177, 'samples': 10913280, 'steps': 21314, 'loss/train': 2.0164198875427246}
-03/04/2022 14:30:11 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 14:30:16 - INFO - codeparrot_training - Step 21315: {'lr': 0.0004792802985530337, 'samples': 10913792, 'steps': 21315, 'loss/train': 1.168752670288086}
-03/04/2022 14:30:19 - INFO - codeparrot_training - Step 21316: {'lr': 0.0004792781831881153, 'samples': 10914304, 'steps': 21316, 'loss/train': 1.9491513967514038}
-03/04/2022 14:30:19 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/04/2022 14:30:24 - INFO - codeparrot_training - Step 21317: {'lr': 0.0004792760677198878, 'samples': 10914816, 'steps': 21317, 'loss/train': 0.6838359236717224}
-03/04/2022 14:30:27 - INFO - codeparrot_training - Step 21318: {'lr': 0.00047927395214835203, 'samples': 10915328, 'steps': 21318, 'loss/train': 1.6185662746429443}
-03/04/2022 14:30:27 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/04/2022 14:30:33 - INFO - codeparrot_training - Step 21319: {'lr': 0.0004792718364735089, 'samples': 10915840, 'steps': 21319, 'loss/train': 1.8563828468322754}
-03/04/2022 14:30:36 - INFO - codeparrot_training - Step 21320: {'lr': 0.00047926972069535945, 'samples': 10916352, 'steps': 21320, 'loss/train': 2.3466405868530273}
-03/04/2022 14:30:37 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/04/2022 14:30:41 - INFO - codeparrot_training - Step 21321: {'lr': 0.00047926760481390465, 'samples': 10916864, 'steps': 21321, 'loss/train': 2.049877882003784}
-03/04/2022 14:30:44 - INFO - codeparrot_training - Step 21322: {'lr': 0.00047926548882914533, 'samples': 10917376, 'steps': 21322, 'loss/train': 2.4038209915161133}
-03/04/2022 14:30:45 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 14:30:49 - INFO - codeparrot_training - Step 21323: {'lr': 0.0004792633727410826, 'samples': 10917888, 'steps': 21323, 'loss/train': 1.2239258289337158}
-03/04/2022 14:30:53 - INFO - codeparrot_training - Step 21324: {'lr': 0.0004792612565497172, 'samples': 10918400, 'steps': 21324, 'loss/train': 1.2301756143569946}
-03/04/2022 14:30:53 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/04/2022 14:30:58 - INFO - codeparrot_training - Step 21325: {'lr': 0.00047925914025505036, 'samples': 10918912, 'steps': 21325, 'loss/train': 2.311999797821045}
-03/04/2022 14:31:01 - INFO - codeparrot_training - Step 21326: {'lr': 0.0004792570238570828, 'samples': 10919424, 'steps': 21326, 'loss/train': 2.101301431655884}
-03/04/2022 14:31:02 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/04/2022 14:31:06 - INFO - codeparrot_training - Step 21327: {'lr': 0.00047925490735581557, 'samples': 10919936, 'steps': 21327, 'loss/train': 2.495593309402466}
-03/04/2022 14:31:10 - INFO - codeparrot_training - Step 21328: {'lr': 0.00047925279075124963, 'samples': 10920448, 'steps': 21328, 'loss/train': 1.4839733839035034}
-03/04/2022 14:31:10 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/04/2022 14:31:15 - INFO - codeparrot_training - Step 21329: {'lr': 0.00047925067404338596, 'samples': 10920960, 'steps': 21329, 'loss/train': 1.6059410572052002}
-03/04/2022 14:31:18 - INFO - codeparrot_training - Step 21330: {'lr': 0.00047924855723222536, 'samples': 10921472, 'steps': 21330, 'loss/train': 1.5514646768569946}
-03/04/2022 14:31:19 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/04/2022 14:31:23 - INFO - codeparrot_training - Step 21331: {'lr': 0.000479246440317769, 'samples': 10921984, 'steps': 21331, 'loss/train': 1.4081480503082275}
-03/04/2022 14:31:26 - INFO - codeparrot_training - Step 21332: {'lr': 0.00047924432330001776, 'samples': 10922496, 'steps': 21332, 'loss/train': 1.3725852966308594}
-03/04/2022 14:31:27 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/04/2022 14:31:32 - INFO - codeparrot_training - Step 21333: {'lr': 0.0004792422061789725, 'samples': 10923008, 'steps': 21333, 'loss/train': 1.1545569896697998}
-03/04/2022 14:31:35 - INFO - codeparrot_training - Step 21334: {'lr': 0.0004792400889546342, 'samples': 10923520, 'steps': 21334, 'loss/train': 2.1848702430725098}
-03/04/2022 14:31:35 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/04/2022 14:31:40 - INFO - codeparrot_training - Step 21335: {'lr': 0.00047923797162700393, 'samples': 10924032, 'steps': 21335, 'loss/train': 2.1090304851531982}
-03/04/2022 14:31:43 - INFO - codeparrot_training - Step 21336: {'lr': 0.0004792358541960826, 'samples': 10924544, 'steps': 21336, 'loss/train': 1.8369355201721191}
-03/04/2022 14:31:44 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 14:31:49 - INFO - codeparrot_training - Step 21337: {'lr': 0.000479233736661871, 'samples': 10925056, 'steps': 21337, 'loss/train': 1.6815305948257446}
-03/04/2022 14:31:52 - INFO - codeparrot_training - Step 21338: {'lr': 0.0004792316190243703, 'samples': 10925568, 'steps': 21338, 'loss/train': 1.9934661388397217}
-03/04/2022 14:31:52 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 14:31:57 - INFO - codeparrot_training - Step 21339: {'lr': 0.0004792295012835814, 'samples': 10926080, 'steps': 21339, 'loss/train': 2.0236146450042725}
-03/04/2022 14:32:00 - INFO - codeparrot_training - Step 21340: {'lr': 0.0004792273834395052, 'samples': 10926592, 'steps': 21340, 'loss/train': 2.7067954540252686}
-03/04/2022 14:32:01 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 14:32:05 - INFO - codeparrot_training - Step 21341: {'lr': 0.0004792252654921426, 'samples': 10927104, 'steps': 21341, 'loss/train': 2.5637238025665283}
-03/04/2022 14:32:08 - INFO - codeparrot_training - Step 21342: {'lr': 0.00047922314744149475, 'samples': 10927616, 'steps': 21342, 'loss/train': 0.33674442768096924}
-03/04/2022 14:32:09 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 14:32:14 - INFO - codeparrot_training - Step 21343: {'lr': 0.0004792210292875624, 'samples': 10928128, 'steps': 21343, 'loss/train': 2.657834529876709}
-03/04/2022 14:32:17 - INFO - codeparrot_training - Step 21344: {'lr': 0.00047921891103034665, 'samples': 10928640, 'steps': 21344, 'loss/train': 1.8752540349960327}
-03/04/2022 14:32:17 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/04/2022 14:32:22 - INFO - codeparrot_training - Step 21345: {'lr': 0.0004792167926698483, 'samples': 10929152, 'steps': 21345, 'loss/train': 2.227583885192871}
-03/04/2022 14:32:25 - INFO - codeparrot_training - Step 21346: {'lr': 0.0004792146742060685, 'samples': 10929664, 'steps': 21346, 'loss/train': 2.0447771549224854}
-03/04/2022 14:32:26 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/04/2022 14:32:31 - INFO - codeparrot_training - Step 21347: {'lr': 0.00047921255563900813, 'samples': 10930176, 'steps': 21347, 'loss/train': 1.8645390272140503}
-03/04/2022 14:32:34 - INFO - codeparrot_training - Step 21348: {'lr': 0.000479210436968668, 'samples': 10930688, 'steps': 21348, 'loss/train': 2.2230801582336426}
-03/04/2022 14:32:34 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/04/2022 14:32:39 - INFO - codeparrot_training - Step 21349: {'lr': 0.0004792083181950493, 'samples': 10931200, 'steps': 21349, 'loss/train': 2.3117294311523438}
-03/04/2022 14:32:42 - INFO - codeparrot_training - Step 21350: {'lr': 0.0004792061993181528, 'samples': 10931712, 'steps': 21350, 'loss/train': 1.3179750442504883}
-03/04/2022 14:32:43 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/04/2022 14:32:47 - INFO - codeparrot_training - Step 21351: {'lr': 0.00047920408033797954, 'samples': 10932224, 'steps': 21351, 'loss/train': 1.6069706678390503}
-03/04/2022 14:32:50 - INFO - codeparrot_training - Step 21352: {'lr': 0.0004792019612545304, 'samples': 10932736, 'steps': 21352, 'loss/train': 1.1786447763442993}
-03/04/2022 14:32:51 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 14:32:56 - INFO - codeparrot_training - Step 21353: {'lr': 0.00047919984206780647, 'samples': 10933248, 'steps': 21353, 'loss/train': 2.8706212043762207}
-03/04/2022 14:32:59 - INFO - codeparrot_training - Step 21354: {'lr': 0.0004791977227778086, 'samples': 10933760, 'steps': 21354, 'loss/train': 1.6270660161972046}
-03/04/2022 14:33:00 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 14:33:04 - INFO - codeparrot_training - Step 21355: {'lr': 0.00047919560338453783, 'samples': 10934272, 'steps': 21355, 'loss/train': 1.8051972389221191}
-03/04/2022 14:33:07 - INFO - codeparrot_training - Step 21356: {'lr': 0.000479193483887995, 'samples': 10934784, 'steps': 21356, 'loss/train': 1.9108983278274536}
-03/04/2022 14:33:08 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 14:33:13 - INFO - codeparrot_training - Step 21357: {'lr': 0.0004791913642881811, 'samples': 10935296, 'steps': 21357, 'loss/train': 1.7846661806106567}
-03/04/2022 14:33:16 - INFO - codeparrot_training - Step 21358: {'lr': 0.00047918924458509717, 'samples': 10935808, 'steps': 21358, 'loss/train': 1.5067073106765747}
-03/04/2022 14:33:16 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 14:33:21 - INFO - codeparrot_training - Step 21359: {'lr': 0.00047918712477874404, 'samples': 10936320, 'steps': 21359, 'loss/train': 1.8304567337036133}
-03/04/2022 14:33:24 - INFO - codeparrot_training - Step 21360: {'lr': 0.00047918500486912276, 'samples': 10936832, 'steps': 21360, 'loss/train': 1.9056445360183716}
-03/04/2022 14:33:25 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 14:33:29 - INFO - codeparrot_training - Step 21361: {'lr': 0.00047918288485623427, 'samples': 10937344, 'steps': 21361, 'loss/train': 1.833178162574768}
-03/04/2022 14:33:33 - INFO - codeparrot_training - Step 21362: {'lr': 0.0004791807647400795, 'samples': 10937856, 'steps': 21362, 'loss/train': 1.2298716306686401}
-03/04/2022 14:33:33 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/04/2022 14:33:38 - INFO - codeparrot_training - Step 21363: {'lr': 0.0004791786445206594, 'samples': 10938368, 'steps': 21363, 'loss/train': 1.4132949113845825}
-03/04/2022 14:33:41 - INFO - codeparrot_training - Step 21364: {'lr': 0.00047917652419797495, 'samples': 10938880, 'steps': 21364, 'loss/train': 1.4455417394638062}
-03/04/2022 14:33:41 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 14:33:46 - INFO - codeparrot_training - Step 21365: {'lr': 0.0004791744037720271, 'samples': 10939392, 'steps': 21365, 'loss/train': 6.877840518951416}
-03/04/2022 14:33:50 - INFO - codeparrot_training - Step 21366: {'lr': 0.00047917228324281683, 'samples': 10939904, 'steps': 21366, 'loss/train': 2.338094711303711}
-03/04/2022 14:33:50 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/04/2022 14:33:55 - INFO - codeparrot_training - Step 21367: {'lr': 0.00047917016261034496, 'samples': 10940416, 'steps': 21367, 'loss/train': 0.27147966623306274}
-03/04/2022 14:33:58 - INFO - codeparrot_training - Step 21368: {'lr': 0.0004791680418746126, 'samples': 10940928, 'steps': 21368, 'loss/train': 1.8768056631088257}
-03/04/2022 14:33:59 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/04/2022 14:34:03 - INFO - codeparrot_training - Step 21369: {'lr': 0.00047916592103562075, 'samples': 10941440, 'steps': 21369, 'loss/train': 1.8415457010269165}
-03/04/2022 14:34:06 - INFO - codeparrot_training - Step 21370: {'lr': 0.00047916380009337014, 'samples': 10941952, 'steps': 21370, 'loss/train': 1.7826203107833862}
-03/04/2022 14:34:07 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/04/2022 14:34:12 - INFO - codeparrot_training - Step 21371: {'lr': 0.0004791616790478619, 'samples': 10942464, 'steps': 21371, 'loss/train': 1.73987877368927}
-03/04/2022 14:34:15 - INFO - codeparrot_training - Step 21372: {'lr': 0.000479159557899097, 'samples': 10942976, 'steps': 21372, 'loss/train': 2.4192821979522705}
-03/04/2022 14:34:17 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/04/2022 14:34:21 - INFO - codeparrot_training - Step 21373: {'lr': 0.00047915743664707626, 'samples': 10943488, 'steps': 21373, 'loss/train': 6.676584243774414}
-03/04/2022 14:34:24 - INFO - codeparrot_training - Step 21374: {'lr': 0.0004791553152918008, 'samples': 10944000, 'steps': 21374, 'loss/train': 2.3663370609283447}
-03/04/2022 14:34:26 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 14:34:29 - INFO - codeparrot_training - Step 21375: {'lr': 0.0004791531938332714, 'samples': 10944512, 'steps': 21375, 'loss/train': 2.0791358947753906}
-03/04/2022 14:34:32 - INFO - codeparrot_training - Step 21376: {'lr': 0.0004791510722714891, 'samples': 10945024, 'steps': 21376, 'loss/train': 1.7046338319778442}
-03/04/2022 14:34:35 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/04/2022 14:34:38 - INFO - codeparrot_training - Step 21377: {'lr': 0.000479148950606455, 'samples': 10945536, 'steps': 21377, 'loss/train': 1.1815587282180786}
-03/04/2022 14:34:41 - INFO - codeparrot_training - Step 21378: {'lr': 0.00047914682883816977, 'samples': 10946048, 'steps': 21378, 'loss/train': 2.4111080169677734}
-03/04/2022 14:34:43 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/04/2022 14:34:46 - INFO - codeparrot_training - Step 21379: {'lr': 0.00047914470696663457, 'samples': 10946560, 'steps': 21379, 'loss/train': 1.0533455610275269}
-03/04/2022 14:34:49 - INFO - codeparrot_training - Step 21380: {'lr': 0.00047914258499185037, 'samples': 10947072, 'steps': 21380, 'loss/train': 1.893118143081665}
-03/04/2022 14:34:52 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/04/2022 14:34:54 - INFO - codeparrot_training - Step 21381: {'lr': 0.000479140462913818, 'samples': 10947584, 'steps': 21381, 'loss/train': 1.881816029548645}
-03/04/2022 14:34:57 - INFO - codeparrot_training - Step 21382: {'lr': 0.0004791383407325384, 'samples': 10948096, 'steps': 21382, 'loss/train': 1.0542922019958496}
-03/04/2022 14:35:00 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/04/2022 14:35:03 - INFO - codeparrot_training - Step 21383: {'lr': 0.0004791362184480127, 'samples': 10948608, 'steps': 21383, 'loss/train': 2.705415964126587}
-03/04/2022 14:35:06 - INFO - codeparrot_training - Step 21384: {'lr': 0.0004791340960602417, 'samples': 10949120, 'steps': 21384, 'loss/train': 1.5238046646118164}
-03/04/2022 14:35:09 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/04/2022 14:35:12 - INFO - codeparrot_training - Step 21385: {'lr': 0.0004791319735692264, 'samples': 10949632, 'steps': 21385, 'loss/train': 1.2581837177276611}
-03/04/2022 14:35:15 - INFO - codeparrot_training - Step 21386: {'lr': 0.00047912985097496786, 'samples': 10950144, 'steps': 21386, 'loss/train': 1.4499257802963257}
-03/04/2022 14:35:18 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/04/2022 14:35:20 - INFO - codeparrot_training - Step 21387: {'lr': 0.00047912772827746685, 'samples': 10950656, 'steps': 21387, 'loss/train': 0.7538501024246216}
-03/04/2022 14:35:23 - INFO - codeparrot_training - Step 21388: {'lr': 0.00047912560547672453, 'samples': 10951168, 'steps': 21388, 'loss/train': 2.9867985248565674}
-03/04/2022 14:35:26 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 14:35:28 - INFO - codeparrot_training - Step 21389: {'lr': 0.0004791234825727416, 'samples': 10951680, 'steps': 21389, 'loss/train': 1.7869586944580078}
-03/04/2022 14:35:32 - INFO - codeparrot_training - Step 21390: {'lr': 0.0004791213595655193, 'samples': 10952192, 'steps': 21390, 'loss/train': 1.676133155822754}
-03/04/2022 14:35:34 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/04/2022 14:35:37 - INFO - codeparrot_training - Step 21391: {'lr': 0.0004791192364550584, 'samples': 10952704, 'steps': 21391, 'loss/train': 2.747164726257324}
-03/04/2022 14:35:40 - INFO - codeparrot_training - Step 21392: {'lr': 0.00047911711324135985, 'samples': 10953216, 'steps': 21392, 'loss/train': 2.1707706451416016}
-03/04/2022 14:35:43 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/04/2022 14:35:45 - INFO - codeparrot_training - Step 21393: {'lr': 0.00047911498992442476, 'samples': 10953728, 'steps': 21393, 'loss/train': 2.0733323097229004}
-03/04/2022 14:35:49 - INFO - codeparrot_training - Step 21394: {'lr': 0.0004791128665042539, 'samples': 10954240, 'steps': 21394, 'loss/train': 1.882938265800476}
-03/04/2022 14:35:51 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/04/2022 14:35:54 - INFO - codeparrot_training - Step 21395: {'lr': 0.0004791107429808484, 'samples': 10954752, 'steps': 21395, 'loss/train': 1.7375019788742065}
-03/04/2022 14:35:57 - INFO - codeparrot_training - Step 21396: {'lr': 0.00047910861935420915, 'samples': 10955264, 'steps': 21396, 'loss/train': 2.0429680347442627}
-03/04/2022 14:36:00 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/04/2022 14:36:02 - INFO - codeparrot_training - Step 21397: {'lr': 0.00047910649562433696, 'samples': 10955776, 'steps': 21397, 'loss/train': 1.4532302618026733}
-03/04/2022 14:36:05 - INFO - codeparrot_training - Step 21398: {'lr': 0.000479104371791233, 'samples': 10956288, 'steps': 21398, 'loss/train': 2.2226054668426514}
-03/04/2022 14:36:08 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/04/2022 14:36:11 - INFO - codeparrot_training - Step 21399: {'lr': 0.0004791022478548982, 'samples': 10956800, 'steps': 21399, 'loss/train': 1.7070503234863281}
-03/04/2022 14:36:14 - INFO - codeparrot_training - Step 21400: {'lr': 0.0004791001238153334, 'samples': 10957312, 'steps': 21400, 'loss/train': 1.6513333320617676}
-03/04/2022 14:36:17 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 14:36:19 - INFO - codeparrot_training - Step 21401: {'lr': 0.00047909799967253957, 'samples': 10957824, 'steps': 21401, 'loss/train': 1.1307201385498047}
-03/04/2022 14:36:22 - INFO - codeparrot_training - Step 21402: {'lr': 0.00047909587542651776, 'samples': 10958336, 'steps': 21402, 'loss/train': 0.2515629231929779}
-03/04/2022 14:36:25 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/04/2022 14:36:28 - INFO - codeparrot_training - Step 21403: {'lr': 0.00047909375107726894, 'samples': 10958848, 'steps': 21403, 'loss/train': 1.240584135055542}
-03/04/2022 14:36:31 - INFO - codeparrot_training - Step 21404: {'lr': 0.000479091626624794, 'samples': 10959360, 'steps': 21404, 'loss/train': 2.0698139667510986}
-03/04/2022 14:36:33 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/04/2022 14:36:36 - INFO - codeparrot_training - Step 21405: {'lr': 0.00047908950206909385, 'samples': 10959872, 'steps': 21405, 'loss/train': 2.3667664527893066}
-03/04/2022 14:36:39 - INFO - codeparrot_training - Step 21406: {'lr': 0.0004790873774101695, 'samples': 10960384, 'steps': 21406, 'loss/train': 0.7792904376983643}
-03/04/2022 14:36:42 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/04/2022 14:36:44 - INFO - codeparrot_training - Step 21407: {'lr': 0.00047908525264802194, 'samples': 10960896, 'steps': 21407, 'loss/train': 1.5116703510284424}
-03/04/2022 14:36:48 - INFO - codeparrot_training - Step 21408: {'lr': 0.00047908312778265213, 'samples': 10961408, 'steps': 21408, 'loss/train': 1.9496053457260132}
-03/04/2022 14:36:50 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/04/2022 14:36:53 - INFO - codeparrot_training - Step 21409: {'lr': 0.00047908100281406096, 'samples': 10961920, 'steps': 21409, 'loss/train': 1.6290923357009888}
-03/04/2022 14:36:56 - INFO - codeparrot_training - Step 21410: {'lr': 0.00047907887774224946, 'samples': 10962432, 'steps': 21410, 'loss/train': 1.5754854679107666}
-03/04/2022 14:36:59 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/04/2022 14:37:01 - INFO - codeparrot_training - Step 21411: {'lr': 0.0004790767525672185, 'samples': 10962944, 'steps': 21411, 'loss/train': 1.5278072357177734}
-03/04/2022 14:37:05 - INFO - codeparrot_training - Step 21412: {'lr': 0.0004790746272889691, 'samples': 10963456, 'steps': 21412, 'loss/train': 1.3580609560012817}
-03/04/2022 14:37:07 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/04/2022 14:37:10 - INFO - codeparrot_training - Step 21413: {'lr': 0.00047907250190750225, 'samples': 10963968, 'steps': 21413, 'loss/train': 0.5422234535217285}
-03/04/2022 14:37:13 - INFO - codeparrot_training - Step 21414: {'lr': 0.0004790703764228188, 'samples': 10964480, 'steps': 21414, 'loss/train': 1.479291558265686}
-03/04/2022 14:37:15 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/04/2022 14:37:18 - INFO - codeparrot_training - Step 21415: {'lr': 0.0004790682508349198, 'samples': 10964992, 'steps': 21415, 'loss/train': 1.4466280937194824}
-03/04/2022 14:37:21 - INFO - codeparrot_training - Step 21416: {'lr': 0.00047906612514380623, 'samples': 10965504, 'steps': 21416, 'loss/train': 1.9544333219528198}
-03/04/2022 14:37:24 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/04/2022 14:37:27 - INFO - codeparrot_training - Step 21417: {'lr': 0.000479063999349479, 'samples': 10966016, 'steps': 21417, 'loss/train': 1.6393282413482666}
-03/04/2022 14:37:30 - INFO - codeparrot_training - Step 21418: {'lr': 0.00047906187345193895, 'samples': 10966528, 'steps': 21418, 'loss/train': 2.806004047393799}
-03/04/2022 14:37:33 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/04/2022 14:37:35 - INFO - codeparrot_training - Step 21419: {'lr': 0.0004790597474511873, 'samples': 10967040, 'steps': 21419, 'loss/train': 1.5740598440170288}
-03/04/2022 14:37:38 - INFO - codeparrot_training - Step 21420: {'lr': 0.0004790576213472248, 'samples': 10967552, 'steps': 21420, 'loss/train': 1.1114505529403687}
-03/04/2022 14:37:42 - INFO - codeparrot_training - Step 21421: {'lr': 0.0004790554951400524, 'samples': 10968064, 'steps': 21421, 'loss/train': 2.140463352203369}
-03/04/2022 14:37:42 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 14:37:47 - INFO - codeparrot_training - Step 21422: {'lr': 0.0004790533688296712, 'samples': 10968576, 'steps': 21422, 'loss/train': 1.3225126266479492}
-03/04/2022 14:37:50 - INFO - codeparrot_training - Step 21423: {'lr': 0.0004790512424160821, 'samples': 10969088, 'steps': 21423, 'loss/train': 1.3168799877166748}
-03/04/2022 14:37:50 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 14:37:55 - INFO - codeparrot_training - Step 21424: {'lr': 0.00047904911589928605, 'samples': 10969600, 'steps': 21424, 'loss/train': 1.9538557529449463}
-03/04/2022 14:37:58 - INFO - codeparrot_training - Step 21425: {'lr': 0.00047904698927928404, 'samples': 10970112, 'steps': 21425, 'loss/train': 2.121349334716797}
-03/04/2022 14:37:58 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 14:38:04 - INFO - codeparrot_training - Step 21426: {'lr': 0.0004790448625560769, 'samples': 10970624, 'steps': 21426, 'loss/train': 1.1823254823684692}
-03/04/2022 14:38:07 - INFO - codeparrot_training - Step 21427: {'lr': 0.0004790427357296657, 'samples': 10971136, 'steps': 21427, 'loss/train': 1.8716572523117065}
-03/04/2022 14:38:07 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/04/2022 14:38:12 - INFO - codeparrot_training - Step 21428: {'lr': 0.0004790406088000514, 'samples': 10971648, 'steps': 21428, 'loss/train': 2.1148195266723633}
-03/04/2022 14:38:15 - INFO - codeparrot_training - Step 21429: {'lr': 0.00047903848176723493, 'samples': 10972160, 'steps': 21429, 'loss/train': 3.000239372253418}
-03/04/2022 14:38:15 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 14:38:21 - INFO - codeparrot_training - Step 21430: {'lr': 0.0004790363546312172, 'samples': 10972672, 'steps': 21430, 'loss/train': 1.7237545251846313}
-03/04/2022 14:38:24 - INFO - codeparrot_training - Step 21431: {'lr': 0.0004790342273919993, 'samples': 10973184, 'steps': 21431, 'loss/train': 2.141228675842285}
-03/04/2022 14:38:24 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 14:38:29 - INFO - codeparrot_training - Step 21432: {'lr': 0.00047903210004958207, 'samples': 10973696, 'steps': 21432, 'loss/train': 2.4902491569519043}
-03/04/2022 14:38:32 - INFO - codeparrot_training - Step 21433: {'lr': 0.0004790299726039665, 'samples': 10974208, 'steps': 21433, 'loss/train': 2.3511226177215576}
-03/04/2022 14:38:32 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 14:38:37 - INFO - codeparrot_training - Step 21434: {'lr': 0.0004790278450551536, 'samples': 10974720, 'steps': 21434, 'loss/train': 1.6275179386138916}
-03/04/2022 14:38:40 - INFO - codeparrot_training - Step 21435: {'lr': 0.00047902571740314427, 'samples': 10975232, 'steps': 21435, 'loss/train': 1.6710506677627563}
-03/04/2022 14:38:41 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/04/2022 14:38:46 - INFO - codeparrot_training - Step 21436: {'lr': 0.00047902358964793944, 'samples': 10975744, 'steps': 21436, 'loss/train': 2.1068241596221924}
-03/04/2022 14:38:49 - INFO - codeparrot_training - Step 21437: {'lr': 0.0004790214617895402, 'samples': 10976256, 'steps': 21437, 'loss/train': 2.9839892387390137}
-03/04/2022 14:38:49 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/04/2022 14:38:54 - INFO - codeparrot_training - Step 21438: {'lr': 0.0004790193338279474, 'samples': 10976768, 'steps': 21438, 'loss/train': 1.7487232685089111}
-03/04/2022 14:38:58 - INFO - codeparrot_training - Step 21439: {'lr': 0.000479017205763162, 'samples': 10977280, 'steps': 21439, 'loss/train': 1.7582899332046509}
-03/04/2022 14:38:58 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/04/2022 14:39:03 - INFO - codeparrot_training - Step 21440: {'lr': 0.000479015077595185, 'samples': 10977792, 'steps': 21440, 'loss/train': 1.2180627584457397}
-03/04/2022 14:39:06 - INFO - codeparrot_training - Step 21441: {'lr': 0.0004790129493240173, 'samples': 10978304, 'steps': 21441, 'loss/train': 2.4189274311065674}
-03/04/2022 14:39:06 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/04/2022 14:39:11 - INFO - codeparrot_training - Step 21442: {'lr': 0.0004790108209496599, 'samples': 10978816, 'steps': 21442, 'loss/train': 1.5742186307907104}
-03/04/2022 14:39:14 - INFO - codeparrot_training - Step 21443: {'lr': 0.00047900869247211384, 'samples': 10979328, 'steps': 21443, 'loss/train': 1.613582730293274}
-03/04/2022 14:39:15 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/04/2022 14:39:20 - INFO - codeparrot_training - Step 21444: {'lr': 0.0004790065638913799, 'samples': 10979840, 'steps': 21444, 'loss/train': 2.002614974975586}
-03/04/2022 14:39:23 - INFO - codeparrot_training - Step 21445: {'lr': 0.00047900443520745915, 'samples': 10980352, 'steps': 21445, 'loss/train': 1.3103599548339844}
-03/04/2022 14:39:23 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/04/2022 14:39:28 - INFO - codeparrot_training - Step 21446: {'lr': 0.0004790023064203526, 'samples': 10980864, 'steps': 21446, 'loss/train': 1.1245958805084229}
-03/04/2022 14:39:31 - INFO - codeparrot_training - Step 21447: {'lr': 0.00047900017753006106, 'samples': 10981376, 'steps': 21447, 'loss/train': 1.8358019590377808}
-03/04/2022 14:39:32 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/04/2022 14:39:37 - INFO - codeparrot_training - Step 21448: {'lr': 0.0004789980485365857, 'samples': 10981888, 'steps': 21448, 'loss/train': 1.849956750869751}
-03/04/2022 14:39:40 - INFO - codeparrot_training - Step 21449: {'lr': 0.00047899591943992726, 'samples': 10982400, 'steps': 21449, 'loss/train': 1.408422827720642}
-03/04/2022 14:39:40 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 14:39:45 - INFO - codeparrot_training - Step 21450: {'lr': 0.0004789937902400868, 'samples': 10982912, 'steps': 21450, 'loss/train': 1.7223128080368042}
-03/04/2022 14:39:48 - INFO - codeparrot_training - Step 21451: {'lr': 0.00047899166093706523, 'samples': 10983424, 'steps': 21451, 'loss/train': 2.3465030193328857}
-03/04/2022 14:39:48 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 14:39:53 - INFO - codeparrot_training - Step 21452: {'lr': 0.0004789895315308636, 'samples': 10983936, 'steps': 21452, 'loss/train': 0.9675999283790588}
-03/04/2022 14:39:56 - INFO - codeparrot_training - Step 21453: {'lr': 0.00047898740202148284, 'samples': 10984448, 'steps': 21453, 'loss/train': 2.007962942123413}
-03/04/2022 14:39:56 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 14:40:02 - INFO - codeparrot_training - Step 21454: {'lr': 0.0004789852724089239, 'samples': 10984960, 'steps': 21454, 'loss/train': 1.3526530265808105}
-03/04/2022 14:40:05 - INFO - codeparrot_training - Step 21455: {'lr': 0.00047898314269318766, 'samples': 10985472, 'steps': 21455, 'loss/train': 1.8304344415664673}
-03/04/2022 14:40:05 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/04/2022 14:40:10 - INFO - codeparrot_training - Step 21456: {'lr': 0.00047898101287427523, 'samples': 10985984, 'steps': 21456, 'loss/train': 2.2407093048095703}
-03/04/2022 14:40:13 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/04/2022 14:40:15 - INFO - codeparrot_training - Step 21457: {'lr': 0.0004789788829521874, 'samples': 10986496, 'steps': 21457, 'loss/train': 1.9300391674041748}
-03/04/2022 14:40:19 - INFO - codeparrot_training - Step 21458: {'lr': 0.0004789767529269253, 'samples': 10987008, 'steps': 21458, 'loss/train': 1.9247490167617798}
-03/04/2022 14:40:21 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/04/2022 14:40:24 - INFO - codeparrot_training - Step 21459: {'lr': 0.0004789746227984897, 'samples': 10987520, 'steps': 21459, 'loss/train': 2.1624252796173096}
-03/04/2022 14:40:27 - INFO - codeparrot_training - Step 21460: {'lr': 0.0004789724925668818, 'samples': 10988032, 'steps': 21460, 'loss/train': 2.142587184906006}
-03/04/2022 14:40:30 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/04/2022 14:40:32 - INFO - codeparrot_training - Step 21461: {'lr': 0.00047897036223210234, 'samples': 10988544, 'steps': 21461, 'loss/train': 2.19892954826355}
-03/04/2022 14:40:36 - INFO - codeparrot_training - Step 21462: {'lr': 0.00047896823179415237, 'samples': 10989056, 'steps': 21462, 'loss/train': 2.5395398139953613}
-03/04/2022 14:40:38 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/04/2022 14:40:41 - INFO - codeparrot_training - Step 21463: {'lr': 0.0004789661012530329, 'samples': 10989568, 'steps': 21463, 'loss/train': 1.254885196685791}
-03/04/2022 14:40:44 - INFO - codeparrot_training - Step 21464: {'lr': 0.00047896397060874485, 'samples': 10990080, 'steps': 21464, 'loss/train': 1.7813750505447388}
-03/04/2022 14:40:47 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/04/2022 14:40:49 - INFO - codeparrot_training - Step 21465: {'lr': 0.0004789618398612891, 'samples': 10990592, 'steps': 21465, 'loss/train': 1.9561644792556763}
-03/04/2022 14:40:52 - INFO - codeparrot_training - Step 21466: {'lr': 0.0004789597090106667, 'samples': 10991104, 'steps': 21466, 'loss/train': 2.4381911754608154}
-03/04/2022 14:40:55 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 14:40:58 - INFO - codeparrot_training - Step 21467: {'lr': 0.00047895757805687864, 'samples': 10991616, 'steps': 21467, 'loss/train': 1.7176200151443481}
-03/04/2022 14:41:01 - INFO - codeparrot_training - Step 21468: {'lr': 0.0004789554469999258, 'samples': 10992128, 'steps': 21468, 'loss/train': 1.1600180864334106}
-03/04/2022 14:41:03 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/04/2022 14:41:06 - INFO - codeparrot_training - Step 21469: {'lr': 0.0004789533158398091, 'samples': 10992640, 'steps': 21469, 'loss/train': 1.734182357788086}
-03/04/2022 14:41:09 - INFO - codeparrot_training - Step 21470: {'lr': 0.00047895118457652965, 'samples': 10993152, 'steps': 21470, 'loss/train': 2.157457113265991}
-03/04/2022 14:41:11 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/04/2022 14:41:15 - INFO - codeparrot_training - Step 21471: {'lr': 0.0004789490532100883, 'samples': 10993664, 'steps': 21471, 'loss/train': 1.8903000354766846}
-03/04/2022 14:41:18 - INFO - codeparrot_training - Step 21472: {'lr': 0.000478946921740486, 'samples': 10994176, 'steps': 21472, 'loss/train': 1.1657543182373047}
-03/04/2022 14:41:20 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 14:41:23 - INFO - codeparrot_training - Step 21473: {'lr': 0.0004789447901677238, 'samples': 10994688, 'steps': 21473, 'loss/train': 2.1841516494750977}
-03/04/2022 14:41:26 - INFO - codeparrot_training - Step 21474: {'lr': 0.00047894265849180264, 'samples': 10995200, 'steps': 21474, 'loss/train': 1.8514823913574219}
-03/04/2022 14:41:28 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 14:41:31 - INFO - codeparrot_training - Step 21475: {'lr': 0.00047894052671272337, 'samples': 10995712, 'steps': 21475, 'loss/train': 1.860870599746704}
-03/04/2022 14:41:35 - INFO - codeparrot_training - Step 21476: {'lr': 0.0004789383948304871, 'samples': 10996224, 'steps': 21476, 'loss/train': 2.0299603939056396}
-03/04/2022 14:41:37 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/04/2022 14:41:40 - INFO - codeparrot_training - Step 21477: {'lr': 0.00047893626284509466, 'samples': 10996736, 'steps': 21477, 'loss/train': 2.009037971496582}
-03/04/2022 14:41:43 - INFO - codeparrot_training - Step 21478: {'lr': 0.0004789341307565471, 'samples': 10997248, 'steps': 21478, 'loss/train': 2.1882731914520264}
-03/04/2022 14:41:45 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 14:41:48 - INFO - codeparrot_training - Step 21479: {'lr': 0.0004789319985648454, 'samples': 10997760, 'steps': 21479, 'loss/train': 1.9371702671051025}
-03/04/2022 14:41:51 - INFO - codeparrot_training - Step 21480: {'lr': 0.0004789298662699905, 'samples': 10998272, 'steps': 21480, 'loss/train': 1.4941586256027222}
-03/04/2022 14:41:54 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/04/2022 14:41:57 - INFO - codeparrot_training - Step 21481: {'lr': 0.0004789277338719832, 'samples': 10998784, 'steps': 21481, 'loss/train': 0.9644403457641602}
-03/04/2022 14:42:00 - INFO - codeparrot_training - Step 21482: {'lr': 0.0004789256013708246, 'samples': 10999296, 'steps': 21482, 'loss/train': 1.8315128087997437}
-03/04/2022 14:42:03 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/04/2022 14:42:05 - INFO - codeparrot_training - Step 21483: {'lr': 0.0004789234687665158, 'samples': 10999808, 'steps': 21483, 'loss/train': 1.4685949087142944}
-03/04/2022 14:42:08 - INFO - codeparrot_training - Step 21484: {'lr': 0.0004789213360590575, 'samples': 11000320, 'steps': 21484, 'loss/train': 2.1373486518859863}
-03/04/2022 14:42:11 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 14:42:14 - INFO - codeparrot_training - Step 21485: {'lr': 0.00047891920324845085, 'samples': 11000832, 'steps': 21485, 'loss/train': 1.3258105516433716}
-03/04/2022 14:42:17 - INFO - codeparrot_training - Step 21486: {'lr': 0.00047891707033469665, 'samples': 11001344, 'steps': 21486, 'loss/train': 2.312465190887451}
-03/04/2022 14:42:20 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/04/2022 14:42:22 - INFO - codeparrot_training - Step 21487: {'lr': 0.00047891493731779607, 'samples': 11001856, 'steps': 21487, 'loss/train': 1.0944656133651733}
-03/04/2022 14:42:25 - INFO - codeparrot_training - Step 21488: {'lr': 0.00047891280419774985, 'samples': 11002368, 'steps': 21488, 'loss/train': 2.453826427459717}
-03/04/2022 14:42:28 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/04/2022 14:42:31 - INFO - codeparrot_training - Step 21489: {'lr': 0.0004789106709745591, 'samples': 11002880, 'steps': 21489, 'loss/train': 1.8672728538513184}
-03/04/2022 14:42:34 - INFO - codeparrot_training - Step 21490: {'lr': 0.0004789085376482247, 'samples': 11003392, 'steps': 21490, 'loss/train': 1.3548579216003418}
-03/04/2022 14:42:36 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/04/2022 14:42:39 - INFO - codeparrot_training - Step 21491: {'lr': 0.00047890640421874775, 'samples': 11003904, 'steps': 21491, 'loss/train': 1.7006772756576538}
-03/04/2022 14:42:42 - INFO - codeparrot_training - Step 21492: {'lr': 0.000478904270686129, 'samples': 11004416, 'steps': 21492, 'loss/train': 1.7065300941467285}
-03/04/2022 14:42:45 - INFO - codeparrot_training - Step 21493: {'lr': 0.00047890213705036955, 'samples': 11004928, 'steps': 21493, 'loss/train': 2.139211893081665}
-03/04/2022 14:42:45 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 14:42:51 - INFO - codeparrot_training - Step 21494: {'lr': 0.00047890000331147033, 'samples': 11005440, 'steps': 21494, 'loss/train': 2.007594347000122}
-03/04/2022 14:42:54 - INFO - codeparrot_training - Step 21495: {'lr': 0.0004788978694694323, 'samples': 11005952, 'steps': 21495, 'loss/train': 1.5440399646759033}
-03/04/2022 14:42:54 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/04/2022 14:42:59 - INFO - codeparrot_training - Step 21496: {'lr': 0.0004788957355242564, 'samples': 11006464, 'steps': 21496, 'loss/train': 2.0802841186523438}
-03/04/2022 14:43:02 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/04/2022 14:43:04 - INFO - codeparrot_training - Step 21497: {'lr': 0.00047889360147594363, 'samples': 11006976, 'steps': 21497, 'loss/train': 1.7139008045196533}
-03/04/2022 14:43:08 - INFO - codeparrot_training - Step 21498: {'lr': 0.00047889146732449497, 'samples': 11007488, 'steps': 21498, 'loss/train': 1.6637988090515137}
-03/04/2022 14:43:10 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/04/2022 14:43:13 - INFO - codeparrot_training - Step 21499: {'lr': 0.00047888933306991136, 'samples': 11008000, 'steps': 21499, 'loss/train': 2.4190354347229004}
-03/04/2022 14:43:16 - INFO - codeparrot_training - Step 21500: {'lr': 0.00047888719871219367, 'samples': 11008512, 'steps': 21500, 'loss/train': 1.8156580924987793}
-03/04/2022 14:43:19 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/04/2022 14:43:21 - INFO - codeparrot_training - Step 21501: {'lr': 0.00047888506425134293, 'samples': 11009024, 'steps': 21501, 'loss/train': 1.4511713981628418}
-03/04/2022 14:43:25 - INFO - codeparrot_training - Step 21502: {'lr': 0.0004788829296873601, 'samples': 11009536, 'steps': 21502, 'loss/train': 1.841587781906128}
-03/04/2022 14:43:27 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 14:43:30 - INFO - codeparrot_training - Step 21503: {'lr': 0.0004788807950202463, 'samples': 11010048, 'steps': 21503, 'loss/train': 1.9730677604675293}
-03/04/2022 14:43:33 - INFO - codeparrot_training - Step 21504: {'lr': 0.00047887866025000226, 'samples': 11010560, 'steps': 21504, 'loss/train': 1.7167561054229736}
-03/04/2022 14:43:38 - INFO - codeparrot_training - Step 21505: {'lr': 0.000478876525376629, 'samples': 11011072, 'steps': 21505, 'loss/train': 2.352836847305298}
-03/04/2022 14:43:41 - INFO - codeparrot_training - Step 21506: {'lr': 0.00047887439040012755, 'samples': 11011584, 'steps': 21506, 'loss/train': 1.7617042064666748}
-03/04/2022 14:43:44 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/04/2022 14:43:47 - INFO - codeparrot_training - Step 21507: {'lr': 0.0004788722553204988, 'samples': 11012096, 'steps': 21507, 'loss/train': 2.0973446369171143}
-03/04/2022 14:43:50 - INFO - codeparrot_training - Step 21508: {'lr': 0.0004788701201377438, 'samples': 11012608, 'steps': 21508, 'loss/train': 2.298877000808716}
-03/04/2022 14:43:52 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/04/2022 14:43:55 - INFO - codeparrot_training - Step 21509: {'lr': 0.0004788679848518633, 'samples': 11013120, 'steps': 21509, 'loss/train': 1.7931782007217407}
-03/04/2022 14:43:58 - INFO - codeparrot_training - Step 21510: {'lr': 0.0004788658494628586, 'samples': 11013632, 'steps': 21510, 'loss/train': 1.6538856029510498}
-03/04/2022 14:44:01 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/04/2022 14:44:04 - INFO - codeparrot_training - Step 21511: {'lr': 0.0004788637139707304, 'samples': 11014144, 'steps': 21511, 'loss/train': 1.9512265920639038}
-03/04/2022 14:44:07 - INFO - codeparrot_training - Step 21512: {'lr': 0.00047886157837547975, 'samples': 11014656, 'steps': 21512, 'loss/train': 4.8209381103515625}
-03/04/2022 14:44:09 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 14:44:12 - INFO - codeparrot_training - Step 21513: {'lr': 0.0004788594426771076, 'samples': 11015168, 'steps': 21513, 'loss/train': 2.5708723068237305}
-03/04/2022 14:44:15 - INFO - codeparrot_training - Step 21514: {'lr': 0.0004788573068756149, 'samples': 11015680, 'steps': 21514, 'loss/train': 2.220301628112793}
-03/04/2022 14:44:18 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 14:44:20 - INFO - codeparrot_training - Step 21515: {'lr': 0.0004788551709710027, 'samples': 11016192, 'steps': 21515, 'loss/train': 1.7218488454818726}
-03/04/2022 14:44:24 - INFO - codeparrot_training - Step 21516: {'lr': 0.0004788530349632718, 'samples': 11016704, 'steps': 21516, 'loss/train': 1.4557878971099854}
-03/04/2022 14:44:26 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/04/2022 14:44:29 - INFO - codeparrot_training - Step 21517: {'lr': 0.00047885089885242333, 'samples': 11017216, 'steps': 21517, 'loss/train': 1.94817316532135}
-03/04/2022 14:44:32 - INFO - codeparrot_training - Step 21518: {'lr': 0.0004788487626384581, 'samples': 11017728, 'steps': 21518, 'loss/train': 1.7355237007141113}
-03/04/2022 14:44:34 - INFO - codeparrot_training - Skipping example with length 1010 (seq_length=1024)
-03/04/2022 14:44:37 - INFO - codeparrot_training - Step 21519: {'lr': 0.0004788466263213772, 'samples': 11018240, 'steps': 21519, 'loss/train': 2.206615447998047}
-03/04/2022 14:44:41 - INFO - codeparrot_training - Step 21520: {'lr': 0.00047884448990118155, 'samples': 11018752, 'steps': 21520, 'loss/train': 1.5198429822921753}
-03/04/2022 14:44:43 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 14:44:46 - INFO - codeparrot_training - Step 21521: {'lr': 0.0004788423533778721, 'samples': 11019264, 'steps': 21521, 'loss/train': 1.537156581878662}
-03/04/2022 14:44:49 - INFO - codeparrot_training - Step 21522: {'lr': 0.00047884021675144987, 'samples': 11019776, 'steps': 21522, 'loss/train': 2.3668158054351807}
-03/04/2022 14:44:52 - INFO - codeparrot_training - Step 21523: {'lr': 0.0004788380800219156, 'samples': 11020288, 'steps': 21523, 'loss/train': 2.0248425006866455}
-03/04/2022 14:44:52 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/04/2022 14:44:58 - INFO - codeparrot_training - Step 21524: {'lr': 0.0004788359431892706, 'samples': 11020800, 'steps': 21524, 'loss/train': 1.0499323606491089}
-03/04/2022 14:45:01 - INFO - codeparrot_training - Step 21525: {'lr': 0.00047883380625351557, 'samples': 11021312, 'steps': 21525, 'loss/train': 1.4792402982711792}
-03/04/2022 14:45:01 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/04/2022 14:45:06 - INFO - codeparrot_training - Step 21526: {'lr': 0.00047883166921465156, 'samples': 11021824, 'steps': 21526, 'loss/train': 0.5955403447151184}
-03/04/2022 14:45:09 - INFO - codeparrot_training - Step 21527: {'lr': 0.00047882953207267954, 'samples': 11022336, 'steps': 21527, 'loss/train': 2.020458221435547}
-03/04/2022 14:45:10 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/04/2022 14:45:15 - INFO - codeparrot_training - Step 21528: {'lr': 0.00047882739482760044, 'samples': 11022848, 'steps': 21528, 'loss/train': 3.0137877464294434}
-03/04/2022 14:45:18 - INFO - codeparrot_training - Step 21529: {'lr': 0.0004788252574794153, 'samples': 11023360, 'steps': 21529, 'loss/train': 2.3676369190216064}
-03/04/2022 14:45:18 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 14:45:23 - INFO - codeparrot_training - Step 21530: {'lr': 0.000478823120028125, 'samples': 11023872, 'steps': 21530, 'loss/train': 1.057709813117981}
-03/04/2022 14:45:26 - INFO - codeparrot_training - Step 21531: {'lr': 0.0004788209824737305, 'samples': 11024384, 'steps': 21531, 'loss/train': 2.3037679195404053}
-03/04/2022 14:45:27 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/04/2022 14:45:32 - INFO - codeparrot_training - Step 21532: {'lr': 0.00047881884481623286, 'samples': 11024896, 'steps': 21532, 'loss/train': 2.2995364665985107}
-03/04/2022 14:45:35 - INFO - codeparrot_training - Step 21533: {'lr': 0.000478816707055633, 'samples': 11025408, 'steps': 21533, 'loss/train': 1.383269190788269}
-03/04/2022 14:45:35 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/04/2022 14:45:40 - INFO - codeparrot_training - Step 21534: {'lr': 0.0004788145691919318, 'samples': 11025920, 'steps': 21534, 'loss/train': 2.041614294052124}
-03/04/2022 14:45:43 - INFO - codeparrot_training - Step 21535: {'lr': 0.0004788124312251303, 'samples': 11026432, 'steps': 21535, 'loss/train': 1.1838492155075073}
-03/04/2022 14:45:45 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/04/2022 14:45:49 - INFO - codeparrot_training - Step 21536: {'lr': 0.0004788102931552294, 'samples': 11026944, 'steps': 21536, 'loss/train': 1.5915859937667847}
-03/04/2022 14:45:52 - INFO - codeparrot_training - Step 21537: {'lr': 0.0004788081549822302, 'samples': 11027456, 'steps': 21537, 'loss/train': 1.9229464530944824}
-03/04/2022 14:45:54 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 14:45:57 - INFO - codeparrot_training - Step 21538: {'lr': 0.0004788060167061335, 'samples': 11027968, 'steps': 21538, 'loss/train': 2.2973062992095947}
-03/04/2022 14:46:00 - INFO - codeparrot_training - Step 21539: {'lr': 0.0004788038783269404, 'samples': 11028480, 'steps': 21539, 'loss/train': 2.0456817150115967}
-03/04/2022 14:46:03 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/04/2022 14:46:06 - INFO - codeparrot_training - Step 21540: {'lr': 0.00047880173984465174, 'samples': 11028992, 'steps': 21540, 'loss/train': 1.6001238822937012}
-03/04/2022 14:46:09 - INFO - codeparrot_training - Step 21541: {'lr': 0.0004787996012592686, 'samples': 11029504, 'steps': 21541, 'loss/train': 1.678215503692627}
-03/04/2022 14:46:11 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/04/2022 14:46:14 - INFO - codeparrot_training - Step 21542: {'lr': 0.0004787974625707919, 'samples': 11030016, 'steps': 21542, 'loss/train': 1.3499032258987427}
-03/04/2022 14:46:17 - INFO - codeparrot_training - Step 21543: {'lr': 0.0004787953237792225, 'samples': 11030528, 'steps': 21543, 'loss/train': 1.7572563886642456}
-03/04/2022 14:46:20 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/04/2022 14:46:23 - INFO - codeparrot_training - Step 21544: {'lr': 0.0004787931848845616, 'samples': 11031040, 'steps': 21544, 'loss/train': 2.4015235900878906}
-03/04/2022 14:46:26 - INFO - codeparrot_training - Step 21545: {'lr': 0.00047879104588680987, 'samples': 11031552, 'steps': 21545, 'loss/train': 1.8358739614486694}
-03/04/2022 14:46:28 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/04/2022 14:46:31 - INFO - codeparrot_training - Step 21546: {'lr': 0.00047878890678596854, 'samples': 11032064, 'steps': 21546, 'loss/train': 1.4450644254684448}
-03/04/2022 14:46:34 - INFO - codeparrot_training - Step 21547: {'lr': 0.00047878676758203844, 'samples': 11032576, 'steps': 21547, 'loss/train': 1.9784510135650635}
-03/04/2022 14:46:36 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/04/2022 14:46:40 - INFO - codeparrot_training - Step 21548: {'lr': 0.00047878462827502055, 'samples': 11033088, 'steps': 21548, 'loss/train': 2.089634895324707}
-03/04/2022 14:46:43 - INFO - codeparrot_training - Step 21549: {'lr': 0.0004787824888649158, 'samples': 11033600, 'steps': 21549, 'loss/train': 2.3916525840759277}
-03/04/2022 14:46:45 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 14:46:48 - INFO - codeparrot_training - Step 21550: {'lr': 0.0004787803493517252, 'samples': 11034112, 'steps': 21550, 'loss/train': 2.3134846687316895}
-03/04/2022 14:46:51 - INFO - codeparrot_training - Step 21551: {'lr': 0.0004787782097354497, 'samples': 11034624, 'steps': 21551, 'loss/train': 1.5790374279022217}
-03/04/2022 14:46:53 - INFO - codeparrot_training - Skipping example with length 822 (seq_length=1024)
-03/04/2022 14:46:57 - INFO - codeparrot_training - Step 21552: {'lr': 0.00047877607001609035, 'samples': 11035136, 'steps': 21552, 'loss/train': 1.7583547830581665}
-03/04/2022 14:47:00 - INFO - codeparrot_training - Step 21553: {'lr': 0.00047877393019364796, 'samples': 11035648, 'steps': 21553, 'loss/train': 1.8453491926193237}
-03/04/2022 14:47:02 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/04/2022 14:47:05 - INFO - codeparrot_training - Step 21554: {'lr': 0.0004787717902681236, 'samples': 11036160, 'steps': 21554, 'loss/train': 5.243675231933594}
-03/04/2022 14:47:08 - INFO - codeparrot_training - Step 21555: {'lr': 0.00047876965023951814, 'samples': 11036672, 'steps': 21555, 'loss/train': 1.7240666151046753}
-03/04/2022 14:47:10 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/04/2022 14:47:13 - INFO - codeparrot_training - Step 21556: {'lr': 0.00047876751010783266, 'samples': 11037184, 'steps': 21556, 'loss/train': 3.3290889263153076}
-03/04/2022 14:47:17 - INFO - codeparrot_training - Step 21557: {'lr': 0.0004787653698730681, 'samples': 11037696, 'steps': 21557, 'loss/train': 1.8469316959381104}
-03/04/2022 14:47:19 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/04/2022 14:47:22 - INFO - codeparrot_training - Step 21558: {'lr': 0.00047876322953522535, 'samples': 11038208, 'steps': 21558, 'loss/train': 2.0145440101623535}
-03/04/2022 14:47:25 - INFO - codeparrot_training - Step 21559: {'lr': 0.00047876108909430536, 'samples': 11038720, 'steps': 21559, 'loss/train': 0.9881811738014221}
-03/04/2022 14:47:27 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/04/2022 14:47:30 - INFO - codeparrot_training - Step 21560: {'lr': 0.00047875894855030923, 'samples': 11039232, 'steps': 21560, 'loss/train': 1.459581971168518}
-03/04/2022 14:47:33 - INFO - codeparrot_training - Step 21561: {'lr': 0.00047875680790323785, 'samples': 11039744, 'steps': 21561, 'loss/train': 1.5403809547424316}
-03/04/2022 14:47:35 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 14:47:39 - INFO - codeparrot_training - Step 21562: {'lr': 0.0004787546671530921, 'samples': 11040256, 'steps': 21562, 'loss/train': 1.7764769792556763}
-03/04/2022 14:47:42 - INFO - codeparrot_training - Step 21563: {'lr': 0.0004787525262998731, 'samples': 11040768, 'steps': 21563, 'loss/train': 2.0692877769470215}
-03/04/2022 14:47:44 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 14:47:47 - INFO - codeparrot_training - Step 21564: {'lr': 0.0004787503853435817, 'samples': 11041280, 'steps': 21564, 'loss/train': 2.2987916469573975}
-03/04/2022 14:47:50 - INFO - codeparrot_training - Step 21565: {'lr': 0.00047874824428421897, 'samples': 11041792, 'steps': 21565, 'loss/train': 1.960558295249939}
-03/04/2022 14:47:52 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/04/2022 14:47:55 - INFO - codeparrot_training - Step 21566: {'lr': 0.0004787461031217858, 'samples': 11042304, 'steps': 21566, 'loss/train': 1.108335018157959}
-03/04/2022 14:47:59 - INFO - codeparrot_training - Step 21567: {'lr': 0.0004787439618562831, 'samples': 11042816, 'steps': 21567, 'loss/train': 1.7978209257125854}
-03/04/2022 14:48:00 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/04/2022 14:48:04 - INFO - codeparrot_training - Step 21568: {'lr': 0.000478741820487712, 'samples': 11043328, 'steps': 21568, 'loss/train': 1.945860505104065}
-03/04/2022 14:48:07 - INFO - codeparrot_training - Step 21569: {'lr': 0.0004787396790160733, 'samples': 11043840, 'steps': 21569, 'loss/train': 1.7507333755493164}
-03/04/2022 14:48:09 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 14:48:12 - INFO - codeparrot_training - Step 21570: {'lr': 0.00047873753744136807, 'samples': 11044352, 'steps': 21570, 'loss/train': 1.6642969846725464}
-03/04/2022 14:48:16 - INFO - codeparrot_training - Step 21571: {'lr': 0.0004787353957635971, 'samples': 11044864, 'steps': 21571, 'loss/train': 1.5343148708343506}
-03/04/2022 14:48:17 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 14:48:21 - INFO - codeparrot_training - Step 21572: {'lr': 0.0004787332539827617, 'samples': 11045376, 'steps': 21572, 'loss/train': 1.265346646308899}
-03/04/2022 14:48:24 - INFO - codeparrot_training - Step 21573: {'lr': 0.00047873111209886245, 'samples': 11045888, 'steps': 21573, 'loss/train': 1.1103456020355225}
-03/04/2022 14:48:25 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 14:48:29 - INFO - codeparrot_training - Step 21574: {'lr': 0.00047872897011190063, 'samples': 11046400, 'steps': 21574, 'loss/train': 1.6689702272415161}
-03/04/2022 14:48:33 - INFO - codeparrot_training - Step 21575: {'lr': 0.00047872682802187693, 'samples': 11046912, 'steps': 21575, 'loss/train': 1.1269067525863647}
-03/04/2022 14:48:34 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 14:48:38 - INFO - codeparrot_training - Step 21576: {'lr': 0.0004787246858287926, 'samples': 11047424, 'steps': 21576, 'loss/train': 1.9633636474609375}
-03/04/2022 14:48:41 - INFO - codeparrot_training - Step 21577: {'lr': 0.0004787225435326483, 'samples': 11047936, 'steps': 21577, 'loss/train': 2.339289903640747}
-03/04/2022 14:48:42 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/04/2022 14:48:46 - INFO - codeparrot_training - Step 21578: {'lr': 0.0004787204011334453, 'samples': 11048448, 'steps': 21578, 'loss/train': 0.6621271967887878}
-03/04/2022 14:48:49 - INFO - codeparrot_training - Step 21579: {'lr': 0.0004787182586311843, 'samples': 11048960, 'steps': 21579, 'loss/train': 2.0520291328430176}
-03/04/2022 14:48:51 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 14:48:55 - INFO - codeparrot_training - Step 21580: {'lr': 0.0004787161160258664, 'samples': 11049472, 'steps': 21580, 'loss/train': 1.9009538888931274}
-03/04/2022 14:48:58 - INFO - codeparrot_training - Step 21581: {'lr': 0.00047871397331749254, 'samples': 11049984, 'steps': 21581, 'loss/train': 1.6777318716049194}
-03/04/2022 14:48:59 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 14:49:03 - INFO - codeparrot_training - Step 21582: {'lr': 0.00047871183050606376, 'samples': 11050496, 'steps': 21582, 'loss/train': 1.5293546915054321}
-03/04/2022 14:49:06 - INFO - codeparrot_training - Step 21583: {'lr': 0.00047870968759158096, 'samples': 11051008, 'steps': 21583, 'loss/train': 2.180189609527588}
-03/04/2022 14:49:08 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/04/2022 14:49:12 - INFO - codeparrot_training - Step 21584: {'lr': 0.000478707544574045, 'samples': 11051520, 'steps': 21584, 'loss/train': 2.138096809387207}
-03/04/2022 14:49:15 - INFO - codeparrot_training - Step 21585: {'lr': 0.000478705401453457, 'samples': 11052032, 'steps': 21585, 'loss/train': 2.0357449054718018}
-03/04/2022 14:49:16 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 14:49:20 - INFO - codeparrot_training - Step 21586: {'lr': 0.000478703258229818, 'samples': 11052544, 'steps': 21586, 'loss/train': 2.038154363632202}
-03/04/2022 14:49:23 - INFO - codeparrot_training - Step 21587: {'lr': 0.0004787011149031287, 'samples': 11053056, 'steps': 21587, 'loss/train': 1.6752598285675049}
-03/04/2022 14:49:24 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 14:49:29 - INFO - codeparrot_training - Step 21588: {'lr': 0.0004786989714733902, 'samples': 11053568, 'steps': 21588, 'loss/train': 1.709121584892273}
-03/04/2022 14:49:32 - INFO - codeparrot_training - Step 21589: {'lr': 0.0004786968279406035, 'samples': 11054080, 'steps': 21589, 'loss/train': 1.585824966430664}
-03/04/2022 14:49:33 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 14:49:37 - INFO - codeparrot_training - Step 21590: {'lr': 0.0004786946843047696, 'samples': 11054592, 'steps': 21590, 'loss/train': 1.5783535242080688}
-03/04/2022 14:49:40 - INFO - codeparrot_training - Step 21591: {'lr': 0.00047869254056588927, 'samples': 11055104, 'steps': 21591, 'loss/train': 1.7673418521881104}
-03/04/2022 14:49:41 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/04/2022 14:49:46 - INFO - codeparrot_training - Step 21592: {'lr': 0.0004786903967239637, 'samples': 11055616, 'steps': 21592, 'loss/train': 2.1486194133758545}
-03/04/2022 14:49:49 - INFO - codeparrot_training - Step 21593: {'lr': 0.0004786882527789938, 'samples': 11056128, 'steps': 21593, 'loss/train': 1.8065016269683838}
-03/04/2022 14:49:53 - INFO - codeparrot_training - Step 21594: {'lr': 0.00047868610873098047, 'samples': 11056640, 'steps': 21594, 'loss/train': 1.7069061994552612}
-03/04/2022 14:49:54 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 14:49:58 - INFO - codeparrot_training - Step 21595: {'lr': 0.0004786839645799247, 'samples': 11057152, 'steps': 21595, 'loss/train': 2.43520188331604}
-03/04/2022 14:50:01 - INFO - codeparrot_training - Step 21596: {'lr': 0.00047868182032582746, 'samples': 11057664, 'steps': 21596, 'loss/train': 1.8797132968902588}
-03/04/2022 14:50:02 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 14:50:06 - INFO - codeparrot_training - Step 21597: {'lr': 0.00047867967596868974, 'samples': 11058176, 'steps': 21597, 'loss/train': 2.293253183364868}
-03/04/2022 14:50:09 - INFO - codeparrot_training - Step 21598: {'lr': 0.00047867753150851244, 'samples': 11058688, 'steps': 21598, 'loss/train': 1.947310209274292}
-03/04/2022 14:50:10 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 14:50:15 - INFO - codeparrot_training - Step 21599: {'lr': 0.0004786753869452966, 'samples': 11059200, 'steps': 21599, 'loss/train': 1.0892637968063354}
-03/04/2022 14:50:18 - INFO - codeparrot_training - Step 21600: {'lr': 0.00047867324227904317, 'samples': 11059712, 'steps': 21600, 'loss/train': 1.5483022928237915}
-03/04/2022 14:50:19 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 14:50:23 - INFO - codeparrot_training - Step 21601: {'lr': 0.0004786710975097531, 'samples': 11060224, 'steps': 21601, 'loss/train': 1.3634780645370483}
-03/04/2022 14:50:26 - INFO - codeparrot_training - Step 21602: {'lr': 0.0004786689526374274, 'samples': 11060736, 'steps': 21602, 'loss/train': 1.9115177392959595}
-03/04/2022 14:50:27 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/04/2022 14:50:31 - INFO - codeparrot_training - Step 21603: {'lr': 0.00047866680766206693, 'samples': 11061248, 'steps': 21603, 'loss/train': 1.928360939025879}
-03/04/2022 14:50:35 - INFO - codeparrot_training - Step 21604: {'lr': 0.0004786646625836727, 'samples': 11061760, 'steps': 21604, 'loss/train': 1.3518400192260742}
-03/04/2022 14:50:36 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/04/2022 14:50:40 - INFO - codeparrot_training - Step 21605: {'lr': 0.0004786625174022458, 'samples': 11062272, 'steps': 21605, 'loss/train': 1.6078460216522217}
-03/04/2022 14:50:43 - INFO - codeparrot_training - Step 21606: {'lr': 0.00047866037211778705, 'samples': 11062784, 'steps': 21606, 'loss/train': 1.8137054443359375}
-03/04/2022 14:50:44 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/04/2022 14:50:48 - INFO - codeparrot_training - Step 21607: {'lr': 0.0004786582267302975, 'samples': 11063296, 'steps': 21607, 'loss/train': 1.192622423171997}
-03/04/2022 14:50:51 - INFO - codeparrot_training - Step 21608: {'lr': 0.000478656081239778, 'samples': 11063808, 'steps': 21608, 'loss/train': 1.2776453495025635}
-03/04/2022 14:50:52 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 14:50:57 - INFO - codeparrot_training - Step 21609: {'lr': 0.0004786539356462297, 'samples': 11064320, 'steps': 21609, 'loss/train': 2.407715320587158}
-03/04/2022 14:51:00 - INFO - codeparrot_training - Step 21610: {'lr': 0.0004786517899496534, 'samples': 11064832, 'steps': 21610, 'loss/train': 2.002889633178711}
-03/04/2022 14:51:00 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/04/2022 14:51:05 - INFO - codeparrot_training - Step 21611: {'lr': 0.0004786496441500502, 'samples': 11065344, 'steps': 21611, 'loss/train': 1.9632091522216797}
-03/04/2022 14:51:08 - INFO - codeparrot_training - Step 21612: {'lr': 0.00047864749824742093, 'samples': 11065856, 'steps': 21612, 'loss/train': 1.731671690940857}
-03/04/2022 14:51:09 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 14:51:13 - INFO - codeparrot_training - Step 21613: {'lr': 0.00047864535224176666, 'samples': 11066368, 'steps': 21613, 'loss/train': 1.9077495336532593}
-03/04/2022 14:51:17 - INFO - codeparrot_training - Step 21614: {'lr': 0.0004786432061330882, 'samples': 11066880, 'steps': 21614, 'loss/train': 2.1098737716674805}
-03/04/2022 14:51:18 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 14:51:22 - INFO - codeparrot_training - Step 21615: {'lr': 0.0004786410599213868, 'samples': 11067392, 'steps': 21615, 'loss/train': 1.7675665616989136}
-03/04/2022 14:51:25 - INFO - codeparrot_training - Step 21616: {'lr': 0.00047863891360666323, 'samples': 11067904, 'steps': 21616, 'loss/train': 1.6805068254470825}
-03/04/2022 14:51:26 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/04/2022 14:51:31 - INFO - codeparrot_training - Step 21617: {'lr': 0.00047863676718891846, 'samples': 11068416, 'steps': 21617, 'loss/train': 1.790153980255127}
-03/04/2022 14:51:34 - INFO - codeparrot_training - Step 21618: {'lr': 0.0004786346206681535, 'samples': 11068928, 'steps': 21618, 'loss/train': 1.2833428382873535}
-03/04/2022 14:51:37 - INFO - codeparrot_training - Step 21619: {'lr': 0.0004786324740443693, 'samples': 11069440, 'steps': 21619, 'loss/train': 2.032071352005005}
-03/04/2022 14:51:37 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/04/2022 14:51:42 - INFO - codeparrot_training - Step 21620: {'lr': 0.00047863032731756684, 'samples': 11069952, 'steps': 21620, 'loss/train': 1.3048440217971802}
-03/04/2022 14:51:45 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 14:51:48 - INFO - codeparrot_training - Step 21621: {'lr': 0.0004786281804877471, 'samples': 11070464, 'steps': 21621, 'loss/train': 2.5797715187072754}
-03/04/2022 14:51:51 - INFO - codeparrot_training - Step 21622: {'lr': 0.00047862603355491103, 'samples': 11070976, 'steps': 21622, 'loss/train': 2.66520619392395}
-03/04/2022 14:51:54 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/04/2022 14:51:56 - INFO - codeparrot_training - Step 21623: {'lr': 0.0004786238865190595, 'samples': 11071488, 'steps': 21623, 'loss/train': 1.3190083503723145}
-03/04/2022 14:51:59 - INFO - codeparrot_training - Step 21624: {'lr': 0.0004786217393801937, 'samples': 11072000, 'steps': 21624, 'loss/train': 1.344419002532959}
-03/04/2022 14:52:02 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/04/2022 14:52:04 - INFO - codeparrot_training - Step 21625: {'lr': 0.00047861959213831446, 'samples': 11072512, 'steps': 21625, 'loss/train': 1.826554775238037}
-03/04/2022 14:52:08 - INFO - codeparrot_training - Step 21626: {'lr': 0.0004786174447934227, 'samples': 11073024, 'steps': 21626, 'loss/train': 1.7219583988189697}
-03/04/2022 14:52:10 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 14:52:13 - INFO - codeparrot_training - Step 21627: {'lr': 0.0004786152973455195, 'samples': 11073536, 'steps': 21627, 'loss/train': 1.9456664323806763}
-03/04/2022 14:52:16 - INFO - codeparrot_training - Step 21628: {'lr': 0.0004786131497946058, 'samples': 11074048, 'steps': 21628, 'loss/train': 1.9369336366653442}
-03/04/2022 14:52:19 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/04/2022 14:52:21 - INFO - codeparrot_training - Step 21629: {'lr': 0.0004786110021406824, 'samples': 11074560, 'steps': 21629, 'loss/train': 2.341231346130371}
-03/04/2022 14:52:25 - INFO - codeparrot_training - Step 21630: {'lr': 0.0004786088543837506, 'samples': 11075072, 'steps': 21630, 'loss/train': 1.1697386503219604}
-03/04/2022 14:52:27 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 14:52:30 - INFO - codeparrot_training - Step 21631: {'lr': 0.00047860670652381105, 'samples': 11075584, 'steps': 21631, 'loss/train': 2.088310956954956}
-03/04/2022 14:52:33 - INFO - codeparrot_training - Step 21632: {'lr': 0.00047860455856086487, 'samples': 11076096, 'steps': 21632, 'loss/train': 1.918359637260437}
-03/04/2022 14:52:36 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/04/2022 14:52:38 - INFO - codeparrot_training - Step 21633: {'lr': 0.00047860241049491303, 'samples': 11076608, 'steps': 21633, 'loss/train': 1.7962597608566284}
-03/04/2022 14:52:41 - INFO - codeparrot_training - Step 21634: {'lr': 0.00047860026232595645, 'samples': 11077120, 'steps': 21634, 'loss/train': 1.3057301044464111}
-03/04/2022 14:52:45 - INFO - codeparrot_training - Step 21635: {'lr': 0.0004785981140539961, 'samples': 11077632, 'steps': 21635, 'loss/train': 1.847962498664856}
-03/04/2022 14:52:45 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/04/2022 14:52:50 - INFO - codeparrot_training - Step 21636: {'lr': 0.000478595965679033, 'samples': 11078144, 'steps': 21636, 'loss/train': 0.7102426290512085}
-03/04/2022 14:52:53 - INFO - codeparrot_training - Step 21637: {'lr': 0.0004785938172010681, 'samples': 11078656, 'steps': 21637, 'loss/train': 1.4587161540985107}
-03/04/2022 14:52:53 - INFO - codeparrot_training - Skipping example with length 233 (seq_length=1024)
-03/04/2022 14:52:58 - INFO - codeparrot_training - Step 21638: {'lr': 0.0004785916686201023, 'samples': 11079168, 'steps': 21638, 'loss/train': 1.1614410877227783}
-03/04/2022 14:53:02 - INFO - codeparrot_training - Step 21639: {'lr': 0.00047858951993613665, 'samples': 11079680, 'steps': 21639, 'loss/train': 1.8197566270828247}
-03/04/2022 14:53:02 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/04/2022 14:53:07 - INFO - codeparrot_training - Step 21640: {'lr': 0.0004785873711491721, 'samples': 11080192, 'steps': 21640, 'loss/train': 1.907324194908142}
-03/04/2022 14:53:10 - INFO - codeparrot_training - Step 21641: {'lr': 0.00047858522225920964, 'samples': 11080704, 'steps': 21641, 'loss/train': 1.4754407405853271}
-03/04/2022 14:53:10 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/04/2022 14:53:15 - INFO - codeparrot_training - Step 21642: {'lr': 0.00047858307326625014, 'samples': 11081216, 'steps': 21642, 'loss/train': 1.5278581380844116}
-03/04/2022 14:53:18 - INFO - codeparrot_training - Step 21643: {'lr': 0.00047858092417029464, 'samples': 11081728, 'steps': 21643, 'loss/train': 1.350403070449829}
-03/04/2022 14:53:18 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/04/2022 14:53:24 - INFO - codeparrot_training - Step 21644: {'lr': 0.00047857877497134416, 'samples': 11082240, 'steps': 21644, 'loss/train': 1.7687522172927856}
-03/04/2022 14:53:27 - INFO - codeparrot_training - Step 21645: {'lr': 0.0004785766256693995, 'samples': 11082752, 'steps': 21645, 'loss/train': 1.978022813796997}
-03/04/2022 14:53:27 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/04/2022 14:53:32 - INFO - codeparrot_training - Step 21646: {'lr': 0.0004785744762644619, 'samples': 11083264, 'steps': 21646, 'loss/train': 2.0448451042175293}
-03/04/2022 14:53:36 - INFO - codeparrot_training - Step 21647: {'lr': 0.00047857232675653207, 'samples': 11083776, 'steps': 21647, 'loss/train': 2.01790714263916}
-03/04/2022 14:53:36 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 14:53:41 - INFO - codeparrot_training - Step 21648: {'lr': 0.00047857017714561105, 'samples': 11084288, 'steps': 21648, 'loss/train': 1.658448576927185}
-03/04/2022 14:53:44 - INFO - codeparrot_training - Step 21649: {'lr': 0.00047856802743169994, 'samples': 11084800, 'steps': 21649, 'loss/train': 0.9894323348999023}
-03/04/2022 14:53:44 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/04/2022 14:53:49 - INFO - codeparrot_training - Step 21650: {'lr': 0.00047856587761479954, 'samples': 11085312, 'steps': 21650, 'loss/train': 0.8269980549812317}
-03/04/2022 14:53:52 - INFO - codeparrot_training - Step 21651: {'lr': 0.00047856372769491083, 'samples': 11085824, 'steps': 21651, 'loss/train': 1.817694902420044}
-03/04/2022 14:53:52 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/04/2022 14:53:58 - INFO - codeparrot_training - Step 21652: {'lr': 0.0004785615776720349, 'samples': 11086336, 'steps': 21652, 'loss/train': 0.826675295829773}
-03/04/2022 14:54:01 - INFO - codeparrot_training - Step 21653: {'lr': 0.0004785594275461726, 'samples': 11086848, 'steps': 21653, 'loss/train': 2.391334056854248}
-03/04/2022 14:54:01 - INFO - codeparrot_training - Skipping example with length 158 (seq_length=1024)
-03/04/2022 14:54:06 - INFO - codeparrot_training - Step 21654: {'lr': 0.00047855727731732503, 'samples': 11087360, 'steps': 21654, 'loss/train': 1.5006520748138428}
-03/04/2022 14:54:09 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/04/2022 14:54:12 - INFO - codeparrot_training - Step 21655: {'lr': 0.00047855512698549295, 'samples': 11087872, 'steps': 21655, 'loss/train': 2.0863168239593506}
-03/04/2022 14:54:15 - INFO - codeparrot_training - Step 21656: {'lr': 0.00047855297655067754, 'samples': 11088384, 'steps': 21656, 'loss/train': 1.3177684545516968}
-03/04/2022 14:54:18 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/04/2022 14:54:20 - INFO - codeparrot_training - Step 21657: {'lr': 0.0004785508260128797, 'samples': 11088896, 'steps': 21657, 'loss/train': 2.400218963623047}
-03/04/2022 14:54:23 - INFO - codeparrot_training - Step 21658: {'lr': 0.00047854867537210034, 'samples': 11089408, 'steps': 21658, 'loss/train': 1.112760066986084}
-03/04/2022 14:54:26 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/04/2022 14:54:28 - INFO - codeparrot_training - Step 21659: {'lr': 0.00047854652462834055, 'samples': 11089920, 'steps': 21659, 'loss/train': 1.8920199871063232}
-03/04/2022 14:54:32 - INFO - codeparrot_training - Step 21660: {'lr': 0.0004785443737816012, 'samples': 11090432, 'steps': 21660, 'loss/train': 1.0126533508300781}
-03/04/2022 14:54:34 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 14:54:37 - INFO - codeparrot_training - Step 21661: {'lr': 0.0004785422228318832, 'samples': 11090944, 'steps': 21661, 'loss/train': 2.1009271144866943}
-03/04/2022 14:54:40 - INFO - codeparrot_training - Step 21662: {'lr': 0.0004785400717791877, 'samples': 11091456, 'steps': 21662, 'loss/train': 2.6071882247924805}
-03/04/2022 14:54:43 - INFO - codeparrot_training - Step 21663: {'lr': 0.0004785379206235155, 'samples': 11091968, 'steps': 21663, 'loss/train': 2.219818592071533}
-03/04/2022 14:54:43 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 14:54:49 - INFO - codeparrot_training - Step 21664: {'lr': 0.00047853576936486764, 'samples': 11092480, 'steps': 21664, 'loss/train': 1.9400922060012817}
-03/04/2022 14:54:52 - INFO - codeparrot_training - Step 21665: {'lr': 0.00047853361800324516, 'samples': 11092992, 'steps': 21665, 'loss/train': 2.5393707752227783}
-03/04/2022 14:54:52 - INFO - codeparrot_training - Skipping example with length 1010 (seq_length=1024)
-03/04/2022 14:54:57 - INFO - codeparrot_training - Step 21666: {'lr': 0.0004785314665386489, 'samples': 11093504, 'steps': 21666, 'loss/train': 1.2286263704299927}
-03/04/2022 14:55:00 - INFO - codeparrot_training - Step 21667: {'lr': 0.00047852931497107987, 'samples': 11094016, 'steps': 21667, 'loss/train': 1.368502140045166}
-03/04/2022 14:55:00 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 14:55:06 - INFO - codeparrot_training - Step 21668: {'lr': 0.0004785271633005391, 'samples': 11094528, 'steps': 21668, 'loss/train': 2.007194757461548}
-03/04/2022 14:55:09 - INFO - codeparrot_training - Step 21669: {'lr': 0.0004785250115270275, 'samples': 11095040, 'steps': 21669, 'loss/train': 2.440783739089966}
-03/04/2022 14:55:10 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/04/2022 14:55:14 - INFO - codeparrot_training - Step 21670: {'lr': 0.00047852285965054606, 'samples': 11095552, 'steps': 21670, 'loss/train': 2.2348263263702393}
-03/04/2022 14:55:18 - INFO - codeparrot_training - Step 21671: {'lr': 0.00047852070767109573, 'samples': 11096064, 'steps': 21671, 'loss/train': 2.220184087753296}
-03/04/2022 14:55:19 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/04/2022 14:55:23 - INFO - codeparrot_training - Step 21672: {'lr': 0.00047851855558867754, 'samples': 11096576, 'steps': 21672, 'loss/train': 1.1613482236862183}
-03/04/2022 14:55:26 - INFO - codeparrot_training - Step 21673: {'lr': 0.0004785164034032924, 'samples': 11097088, 'steps': 21673, 'loss/train': 1.9185817241668701}
-03/04/2022 14:55:28 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/04/2022 14:55:32 - INFO - codeparrot_training - Step 21674: {'lr': 0.0004785142511149412, 'samples': 11097600, 'steps': 21674, 'loss/train': 1.819951057434082}
-03/04/2022 14:55:35 - INFO - codeparrot_training - Step 21675: {'lr': 0.0004785120987236251, 'samples': 11098112, 'steps': 21675, 'loss/train': 0.316189706325531}
-03/04/2022 14:55:36 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/04/2022 14:55:40 - INFO - codeparrot_training - Step 21676: {'lr': 0.00047850994622934494, 'samples': 11098624, 'steps': 21676, 'loss/train': 2.013767957687378}
-03/04/2022 14:55:43 - INFO - codeparrot_training - Step 21677: {'lr': 0.0004785077936321018, 'samples': 11099136, 'steps': 21677, 'loss/train': 2.2385544776916504}
-03/04/2022 14:55:45 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/04/2022 14:55:48 - INFO - codeparrot_training - Step 21678: {'lr': 0.00047850564093189653, 'samples': 11099648, 'steps': 21678, 'loss/train': 3.0174810886383057}
-03/04/2022 14:55:52 - INFO - codeparrot_training - Step 21679: {'lr': 0.0004785034881287301, 'samples': 11100160, 'steps': 21679, 'loss/train': 1.6125528812408447}
-03/04/2022 14:55:53 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 14:55:57 - INFO - codeparrot_training - Step 21680: {'lr': 0.0004785013352226035, 'samples': 11100672, 'steps': 21680, 'loss/train': 3.0373880863189697}
-03/04/2022 14:56:00 - INFO - codeparrot_training - Step 21681: {'lr': 0.00047849918221351783, 'samples': 11101184, 'steps': 21681, 'loss/train': 1.4415744543075562}
-03/04/2022 14:56:01 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 14:56:05 - INFO - codeparrot_training - Step 21682: {'lr': 0.0004784970291014739, 'samples': 11101696, 'steps': 21682, 'loss/train': 1.8824474811553955}
-03/04/2022 14:56:08 - INFO - codeparrot_training - Step 21683: {'lr': 0.0004784948758864727, 'samples': 11102208, 'steps': 21683, 'loss/train': 1.5492140054702759}
-03/04/2022 14:56:09 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/04/2022 14:56:14 - INFO - codeparrot_training - Step 21684: {'lr': 0.0004784927225685153, 'samples': 11102720, 'steps': 21684, 'loss/train': 1.8457438945770264}
-03/04/2022 14:56:17 - INFO - codeparrot_training - Step 21685: {'lr': 0.00047849056914760256, 'samples': 11103232, 'steps': 21685, 'loss/train': 1.9551037549972534}
-03/04/2022 14:56:18 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/04/2022 14:56:22 - INFO - codeparrot_training - Step 21686: {'lr': 0.00047848841562373557, 'samples': 11103744, 'steps': 21686, 'loss/train': 1.2601282596588135}
-03/04/2022 14:56:25 - INFO - codeparrot_training - Step 21687: {'lr': 0.00047848626199691513, 'samples': 11104256, 'steps': 21687, 'loss/train': 1.7526013851165771}
-03/04/2022 14:56:26 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/04/2022 14:56:30 - INFO - codeparrot_training - Step 21688: {'lr': 0.00047848410826714237, 'samples': 11104768, 'steps': 21688, 'loss/train': 2.0657994747161865}
-03/04/2022 14:56:34 - INFO - codeparrot_training - Step 21689: {'lr': 0.00047848195443441817, 'samples': 11105280, 'steps': 21689, 'loss/train': 1.0728436708450317}
-03/04/2022 14:56:35 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/04/2022 14:56:39 - INFO - codeparrot_training - Step 21690: {'lr': 0.0004784798004987435, 'samples': 11105792, 'steps': 21690, 'loss/train': 2.465104818344116}
-03/04/2022 14:56:42 - INFO - codeparrot_training - Step 21691: {'lr': 0.00047847764646011937, 'samples': 11106304, 'steps': 21691, 'loss/train': 2.1175787448883057}
-03/04/2022 14:56:43 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/04/2022 14:56:47 - INFO - codeparrot_training - Step 21692: {'lr': 0.0004784754923185468, 'samples': 11106816, 'steps': 21692, 'loss/train': 1.729608178138733}
-03/04/2022 14:56:50 - INFO - codeparrot_training - Step 21693: {'lr': 0.00047847333807402666, 'samples': 11107328, 'steps': 21693, 'loss/train': 0.4215858578681946}
-03/04/2022 14:56:51 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/04/2022 14:56:56 - INFO - codeparrot_training - Step 21694: {'lr': 0.00047847118372655996, 'samples': 11107840, 'steps': 21694, 'loss/train': 2.21457576751709}
-03/04/2022 14:56:59 - INFO - codeparrot_training - Step 21695: {'lr': 0.00047846902927614767, 'samples': 11108352, 'steps': 21695, 'loss/train': 1.8113813400268555}
-03/04/2022 14:57:00 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/04/2022 14:57:04 - INFO - codeparrot_training - Step 21696: {'lr': 0.0004784668747227907, 'samples': 11108864, 'steps': 21696, 'loss/train': 1.9821256399154663}
-03/04/2022 14:57:08 - INFO - codeparrot_training - Step 21697: {'lr': 0.00047846472006649016, 'samples': 11109376, 'steps': 21697, 'loss/train': 2.344200372695923}
-03/04/2022 14:57:09 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 14:57:13 - INFO - codeparrot_training - Step 21698: {'lr': 0.0004784625653072469, 'samples': 11109888, 'steps': 21698, 'loss/train': 1.6732059717178345}
-03/04/2022 14:57:16 - INFO - codeparrot_training - Step 21699: {'lr': 0.00047846041044506194, 'samples': 11110400, 'steps': 21699, 'loss/train': 1.6493163108825684}
-03/04/2022 14:57:17 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 14:57:21 - INFO - codeparrot_training - Step 21700: {'lr': 0.00047845825547993627, 'samples': 11110912, 'steps': 21700, 'loss/train': 2.19193696975708}
-03/04/2022 14:57:24 - INFO - codeparrot_training - Step 21701: {'lr': 0.0004784561004118708, 'samples': 11111424, 'steps': 21701, 'loss/train': 1.7970657348632812}
-03/04/2022 14:57:26 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/04/2022 14:57:30 - INFO - codeparrot_training - Step 21702: {'lr': 0.0004784539452408666, 'samples': 11111936, 'steps': 21702, 'loss/train': 2.316287040710449}
-03/04/2022 14:57:33 - INFO - codeparrot_training - Step 21703: {'lr': 0.0004784517899669245, 'samples': 11112448, 'steps': 21703, 'loss/train': 1.5626832246780396}
-03/04/2022 14:57:34 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/04/2022 14:57:38 - INFO - codeparrot_training - Step 21704: {'lr': 0.00047844963459004565, 'samples': 11112960, 'steps': 21704, 'loss/train': 1.337782621383667}
-03/04/2022 14:57:41 - INFO - codeparrot_training - Step 21705: {'lr': 0.00047844747911023077, 'samples': 11113472, 'steps': 21705, 'loss/train': 2.074763536453247}
-03/04/2022 14:57:42 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/04/2022 14:57:46 - INFO - codeparrot_training - Step 21706: {'lr': 0.00047844532352748115, 'samples': 11113984, 'steps': 21706, 'loss/train': 2.3312253952026367}
-03/04/2022 14:57:50 - INFO - codeparrot_training - Step 21707: {'lr': 0.0004784431678417975, 'samples': 11114496, 'steps': 21707, 'loss/train': 1.8276689052581787}
-03/04/2022 14:57:51 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 14:57:55 - INFO - codeparrot_training - Step 21708: {'lr': 0.00047844101205318085, 'samples': 11115008, 'steps': 21708, 'loss/train': 1.8994722366333008}
-03/04/2022 14:57:58 - INFO - codeparrot_training - Step 21709: {'lr': 0.0004784388561616323, 'samples': 11115520, 'steps': 21709, 'loss/train': 1.519018292427063}
-03/04/2022 14:57:59 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/04/2022 14:58:03 - INFO - codeparrot_training - Step 21710: {'lr': 0.0004784367001671526, 'samples': 11116032, 'steps': 21710, 'loss/train': 1.8370649814605713}
-03/04/2022 14:58:06 - INFO - codeparrot_training - Step 21711: {'lr': 0.00047843454406974295, 'samples': 11116544, 'steps': 21711, 'loss/train': 2.0374484062194824}
-03/04/2022 14:58:07 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/04/2022 14:58:12 - INFO - codeparrot_training - Step 21712: {'lr': 0.00047843238786940423, 'samples': 11117056, 'steps': 21712, 'loss/train': 2.071685552597046}
-03/04/2022 14:58:15 - INFO - codeparrot_training - Step 21713: {'lr': 0.0004784302315661373, 'samples': 11117568, 'steps': 21713, 'loss/train': 1.0735783576965332}
-03/04/2022 14:58:16 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/04/2022 14:58:20 - INFO - codeparrot_training - Step 21714: {'lr': 0.00047842807515994335, 'samples': 11118080, 'steps': 21714, 'loss/train': 1.7324104309082031}
-03/04/2022 14:58:23 - INFO - codeparrot_training - Step 21715: {'lr': 0.00047842591865082315, 'samples': 11118592, 'steps': 21715, 'loss/train': 1.5595492124557495}
-03/04/2022 14:58:24 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/04/2022 14:58:29 - INFO - codeparrot_training - Step 21716: {'lr': 0.0004784237620387778, 'samples': 11119104, 'steps': 21716, 'loss/train': 1.6675643920898438}
-03/04/2022 14:58:32 - INFO - codeparrot_training - Step 21717: {'lr': 0.0004784216053238082, 'samples': 11119616, 'steps': 21717, 'loss/train': 1.787959337234497}
-03/04/2022 14:58:32 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/04/2022 14:58:37 - INFO - codeparrot_training - Step 21718: {'lr': 0.00047841944850591535, 'samples': 11120128, 'steps': 21718, 'loss/train': 1.1109071969985962}
-03/04/2022 14:58:40 - INFO - codeparrot_training - Step 21719: {'lr': 0.0004784172915851003, 'samples': 11120640, 'steps': 21719, 'loss/train': 1.6595643758773804}
-03/04/2022 14:58:41 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 14:58:45 - INFO - codeparrot_training - Step 21720: {'lr': 0.00047841513456136383, 'samples': 11121152, 'steps': 21720, 'loss/train': 2.393651247024536}
-03/04/2022 14:58:49 - INFO - codeparrot_training - Step 21721: {'lr': 0.000478412977434707, 'samples': 11121664, 'steps': 21721, 'loss/train': 2.4198668003082275}
-03/04/2022 14:58:49 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/04/2022 14:58:54 - INFO - codeparrot_training - Step 21722: {'lr': 0.00047841082020513094, 'samples': 11122176, 'steps': 21722, 'loss/train': 1.7189557552337646}
-03/04/2022 14:58:57 - INFO - codeparrot_training - Step 21723: {'lr': 0.0004784086628726364, 'samples': 11122688, 'steps': 21723, 'loss/train': 2.244342088699341}
-03/04/2022 14:58:58 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 14:59:02 - INFO - codeparrot_training - Step 21724: {'lr': 0.0004784065054372245, 'samples': 11123200, 'steps': 21724, 'loss/train': 1.615106463432312}
-03/04/2022 14:59:05 - INFO - codeparrot_training - Step 21725: {'lr': 0.0004784043478988961, 'samples': 11123712, 'steps': 21725, 'loss/train': 1.6999868154525757}
-03/04/2022 14:59:06 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/04/2022 14:59:11 - INFO - codeparrot_training - Step 21726: {'lr': 0.00047840219025765225, 'samples': 11124224, 'steps': 21726, 'loss/train': 1.6159816980361938}
-03/04/2022 14:59:14 - INFO - codeparrot_training - Step 21727: {'lr': 0.0004784000325134939, 'samples': 11124736, 'steps': 21727, 'loss/train': 1.9638736248016357}
-03/04/2022 14:59:14 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/04/2022 14:59:19 - INFO - codeparrot_training - Step 21728: {'lr': 0.00047839787466642206, 'samples': 11125248, 'steps': 21728, 'loss/train': 2.0567774772644043}
-03/04/2022 14:59:22 - INFO - codeparrot_training - Step 21729: {'lr': 0.00047839571671643756, 'samples': 11125760, 'steps': 21729, 'loss/train': 1.733555793762207}
-03/04/2022 14:59:23 - INFO - codeparrot_training - Skipping example with length 86 (seq_length=1024)
-03/04/2022 14:59:28 - INFO - codeparrot_training - Step 21730: {'lr': 0.0004783935586635415, 'samples': 11126272, 'steps': 21730, 'loss/train': 1.6846046447753906}
-03/04/2022 14:59:31 - INFO - codeparrot_training - Step 21731: {'lr': 0.0004783914005077349, 'samples': 11126784, 'steps': 21731, 'loss/train': 1.7137106657028198}
-03/04/2022 14:59:32 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/04/2022 14:59:36 - INFO - codeparrot_training - Step 21732: {'lr': 0.0004783892422490186, 'samples': 11127296, 'steps': 21732, 'loss/train': 1.7345740795135498}
-03/04/2022 14:59:39 - INFO - codeparrot_training - Step 21733: {'lr': 0.00047838708388739365, 'samples': 11127808, 'steps': 21733, 'loss/train': 0.2502008378505707}
-03/04/2022 14:59:41 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 14:59:45 - INFO - codeparrot_training - Step 21734: {'lr': 0.000478384925422861, 'samples': 11128320, 'steps': 21734, 'loss/train': 2.210984945297241}
-03/04/2022 14:59:48 - INFO - codeparrot_training - Step 21735: {'lr': 0.00047838276685542157, 'samples': 11128832, 'steps': 21735, 'loss/train': 1.765194058418274}
-03/04/2022 14:59:50 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/04/2022 14:59:53 - INFO - codeparrot_training - Step 21736: {'lr': 0.0004783806081850765, 'samples': 11129344, 'steps': 21736, 'loss/train': 2.104729652404785}
-03/04/2022 14:59:56 - INFO - codeparrot_training - Step 21737: {'lr': 0.0004783784494118266, 'samples': 11129856, 'steps': 21737, 'loss/train': 2.6189260482788086}
-03/04/2022 14:59:59 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 15:00:02 - INFO - codeparrot_training - Step 21738: {'lr': 0.00047837629053567286, 'samples': 11130368, 'steps': 21738, 'loss/train': 2.0532193183898926}
-03/04/2022 15:00:05 - INFO - codeparrot_training - Step 21739: {'lr': 0.00047837413155661635, 'samples': 11130880, 'steps': 21739, 'loss/train': 2.3693361282348633}
-03/04/2022 15:00:08 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/04/2022 15:00:10 - INFO - codeparrot_training - Step 21740: {'lr': 0.000478371972474658, 'samples': 11131392, 'steps': 21740, 'loss/train': 1.2502208948135376}
-03/04/2022 15:00:13 - INFO - codeparrot_training - Step 21741: {'lr': 0.00047836981328979865, 'samples': 11131904, 'steps': 21741, 'loss/train': 0.970448911190033}
-03/04/2022 15:00:16 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 15:00:19 - INFO - codeparrot_training - Step 21742: {'lr': 0.00047836765400203953, 'samples': 11132416, 'steps': 21742, 'loss/train': 1.3334587812423706}
-03/04/2022 15:00:22 - INFO - codeparrot_training - Step 21743: {'lr': 0.00047836549461138133, 'samples': 11132928, 'steps': 21743, 'loss/train': 2.1743268966674805}
-03/04/2022 15:00:24 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/04/2022 15:00:27 - INFO - codeparrot_training - Step 21744: {'lr': 0.00047836333511782524, 'samples': 11133440, 'steps': 21744, 'loss/train': 1.9751198291778564}
-03/04/2022 15:00:30 - INFO - codeparrot_training - Step 21745: {'lr': 0.00047836117552137213, 'samples': 11133952, 'steps': 21745, 'loss/train': 2.1148226261138916}
-03/04/2022 15:00:33 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 15:00:36 - INFO - codeparrot_training - Step 21746: {'lr': 0.00047835901582202303, 'samples': 11134464, 'steps': 21746, 'loss/train': 1.7244793176651}
-03/04/2022 15:00:39 - INFO - codeparrot_training - Step 21747: {'lr': 0.00047835685601977886, 'samples': 11134976, 'steps': 21747, 'loss/train': 2.2816364765167236}
-03/04/2022 15:00:41 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 15:00:44 - INFO - codeparrot_training - Step 21748: {'lr': 0.00047835469611464055, 'samples': 11135488, 'steps': 21748, 'loss/train': 1.4153542518615723}
-03/04/2022 15:00:47 - INFO - codeparrot_training - Step 21749: {'lr': 0.0004783525361066092, 'samples': 11136000, 'steps': 21749, 'loss/train': 2.523851156234741}
-03/04/2022 15:00:50 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/04/2022 15:00:53 - INFO - codeparrot_training - Step 21750: {'lr': 0.00047835037599568576, 'samples': 11136512, 'steps': 21750, 'loss/train': 1.9915122985839844}
-03/04/2022 15:00:56 - INFO - codeparrot_training - Step 21751: {'lr': 0.0004783482157818711, 'samples': 11137024, 'steps': 21751, 'loss/train': 1.9623181819915771}
-03/04/2022 15:00:58 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 15:01:01 - INFO - codeparrot_training - Step 21752: {'lr': 0.0004783460554651663, 'samples': 11137536, 'steps': 21752, 'loss/train': 1.7801955938339233}
-03/04/2022 15:01:04 - INFO - codeparrot_training - Step 21753: {'lr': 0.0004783438950455723, 'samples': 11138048, 'steps': 21753, 'loss/train': 1.9983958005905151}
-03/04/2022 15:01:06 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/04/2022 15:01:09 - INFO - codeparrot_training - Step 21754: {'lr': 0.00047834173452309005, 'samples': 11138560, 'steps': 21754, 'loss/train': 2.329423427581787}
-03/04/2022 15:01:13 - INFO - codeparrot_training - Step 21755: {'lr': 0.00047833957389772046, 'samples': 11139072, 'steps': 21755, 'loss/train': 0.6731268167495728}
-03/04/2022 15:01:14 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/04/2022 15:01:18 - INFO - codeparrot_training - Step 21756: {'lr': 0.0004783374131694647, 'samples': 11139584, 'steps': 21756, 'loss/train': 2.144912004470825}
-03/04/2022 15:01:21 - INFO - codeparrot_training - Step 21757: {'lr': 0.00047833525233832356, 'samples': 11140096, 'steps': 21757, 'loss/train': 1.8825634717941284}
-03/04/2022 15:01:24 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 15:01:26 - INFO - codeparrot_training - Step 21758: {'lr': 0.00047833309140429803, 'samples': 11140608, 'steps': 21758, 'loss/train': 1.7558887004852295}
-03/04/2022 15:01:30 - INFO - codeparrot_training - Step 21759: {'lr': 0.0004783309303673892, 'samples': 11141120, 'steps': 21759, 'loss/train': 1.4758727550506592}
-03/04/2022 15:01:32 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 15:01:35 - INFO - codeparrot_training - Step 21760: {'lr': 0.00047832876922759805, 'samples': 11141632, 'steps': 21760, 'loss/train': 1.8323588371276855}
-03/04/2022 15:01:38 - INFO - codeparrot_training - Step 21761: {'lr': 0.0004783266079849253, 'samples': 11142144, 'steps': 21761, 'loss/train': 1.8024146556854248}
-03/04/2022 15:01:41 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 15:01:44 - INFO - codeparrot_training - Step 21762: {'lr': 0.00047832444663937227, 'samples': 11142656, 'steps': 21762, 'loss/train': 1.5333456993103027}
-03/04/2022 15:01:47 - INFO - codeparrot_training - Step 21763: {'lr': 0.0004783222851909397, 'samples': 11143168, 'steps': 21763, 'loss/train': 3.0703651905059814}
-03/04/2022 15:01:50 - INFO - codeparrot_training - Step 21764: {'lr': 0.0004783201236396286, 'samples': 11143680, 'steps': 21764, 'loss/train': 6.750307083129883}
-03/04/2022 15:01:50 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 15:01:55 - INFO - codeparrot_training - Step 21765: {'lr': 0.00047831796198544, 'samples': 11144192, 'steps': 21765, 'loss/train': 1.9327011108398438}
-03/04/2022 15:01:58 - INFO - codeparrot_training - Step 21766: {'lr': 0.0004783158002283749, 'samples': 11144704, 'steps': 21766, 'loss/train': 2.030412197113037}
-03/04/2022 15:01:59 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/04/2022 15:02:04 - INFO - codeparrot_training - Step 21767: {'lr': 0.0004783136383684342, 'samples': 11145216, 'steps': 21767, 'loss/train': 2.0477700233459473}
-03/04/2022 15:02:07 - INFO - codeparrot_training - Step 21768: {'lr': 0.0004783114764056188, 'samples': 11145728, 'steps': 21768, 'loss/train': 2.0731847286224365}
-03/04/2022 15:02:08 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/04/2022 15:02:12 - INFO - codeparrot_training - Step 21769: {'lr': 0.00047830931433992985, 'samples': 11146240, 'steps': 21769, 'loss/train': 0.8285195231437683}
-03/04/2022 15:02:16 - INFO - codeparrot_training - Step 21770: {'lr': 0.00047830715217136825, 'samples': 11146752, 'steps': 21770, 'loss/train': 1.6179840564727783}
-03/04/2022 15:02:16 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/04/2022 15:02:22 - INFO - codeparrot_training - Step 21771: {'lr': 0.000478304989899935, 'samples': 11147264, 'steps': 21771, 'loss/train': 2.338785409927368}
-03/04/2022 15:02:25 - INFO - codeparrot_training - Step 21772: {'lr': 0.00047830282752563103, 'samples': 11147776, 'steps': 21772, 'loss/train': 2.212019920349121}
-03/04/2022 15:02:28 - INFO - codeparrot_training - Step 21773: {'lr': 0.00047830066504845725, 'samples': 11148288, 'steps': 21773, 'loss/train': 1.7606385946273804}
-03/04/2022 15:02:28 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/04/2022 15:02:33 - INFO - codeparrot_training - Step 21774: {'lr': 0.0004782985024684148, 'samples': 11148800, 'steps': 21774, 'loss/train': 1.7152084112167358}
-03/04/2022 15:02:37 - INFO - codeparrot_training - Step 21775: {'lr': 0.0004782963397855046, 'samples': 11149312, 'steps': 21775, 'loss/train': 2.0207455158233643}
-03/04/2022 15:02:37 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/04/2022 15:02:42 - INFO - codeparrot_training - Step 21776: {'lr': 0.00047829417699972747, 'samples': 11149824, 'steps': 21776, 'loss/train': 1.9341248273849487}
-03/04/2022 15:02:45 - INFO - codeparrot_training - Step 21777: {'lr': 0.0004782920141110846, 'samples': 11150336, 'steps': 21777, 'loss/train': 1.9932191371917725}
-03/04/2022 15:02:45 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/04/2022 15:02:50 - INFO - codeparrot_training - Step 21778: {'lr': 0.0004782898511195768, 'samples': 11150848, 'steps': 21778, 'loss/train': 1.6232519149780273}
-03/04/2022 15:02:53 - INFO - codeparrot_training - Step 21779: {'lr': 0.00047828768802520515, 'samples': 11151360, 'steps': 21779, 'loss/train': 1.546098232269287}
-03/04/2022 15:02:54 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 15:02:59 - INFO - codeparrot_training - Step 21780: {'lr': 0.0004782855248279706, 'samples': 11151872, 'steps': 21780, 'loss/train': 1.3727585077285767}
-03/04/2022 15:03:02 - INFO - codeparrot_training - Step 21781: {'lr': 0.0004782833615278741, 'samples': 11152384, 'steps': 21781, 'loss/train': 0.88832688331604}
-03/04/2022 15:03:02 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 15:03:07 - INFO - codeparrot_training - Step 21782: {'lr': 0.00047828119812491664, 'samples': 11152896, 'steps': 21782, 'loss/train': 1.9670883417129517}
-03/04/2022 15:03:10 - INFO - codeparrot_training - Step 21783: {'lr': 0.0004782790346190993, 'samples': 11153408, 'steps': 21783, 'loss/train': 1.6801140308380127}
-03/04/2022 15:03:11 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/04/2022 15:03:16 - INFO - codeparrot_training - Step 21784: {'lr': 0.00047827687101042283, 'samples': 11153920, 'steps': 21784, 'loss/train': 1.8986095190048218}
-03/04/2022 15:03:19 - INFO - codeparrot_training - Step 21785: {'lr': 0.00047827470729888834, 'samples': 11154432, 'steps': 21785, 'loss/train': 1.5478370189666748}
-03/04/2022 15:03:19 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/04/2022 15:03:24 - INFO - codeparrot_training - Step 21786: {'lr': 0.0004782725434844968, 'samples': 11154944, 'steps': 21786, 'loss/train': 1.7326003313064575}
-03/04/2022 15:03:27 - INFO - codeparrot_training - Step 21787: {'lr': 0.00047827037956724915, 'samples': 11155456, 'steps': 21787, 'loss/train': 1.4197208881378174}
-03/04/2022 15:03:28 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/04/2022 15:03:32 - INFO - codeparrot_training - Step 21788: {'lr': 0.00047826821554714644, 'samples': 11155968, 'steps': 21788, 'loss/train': 1.9779229164123535}
-03/04/2022 15:03:36 - INFO - codeparrot_training - Step 21789: {'lr': 0.00047826605142418954, 'samples': 11156480, 'steps': 21789, 'loss/train': 1.8464950323104858}
-03/04/2022 15:03:36 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 15:03:41 - INFO - codeparrot_training - Step 21790: {'lr': 0.0004782638871983795, 'samples': 11156992, 'steps': 21790, 'loss/train': 2.5263938903808594}
-03/04/2022 15:03:44 - INFO - codeparrot_training - Step 21791: {'lr': 0.0004782617228697173, 'samples': 11157504, 'steps': 21791, 'loss/train': 1.3994050025939941}
-03/04/2022 15:03:44 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/04/2022 15:03:49 - INFO - codeparrot_training - Step 21792: {'lr': 0.0004782595584382039, 'samples': 11158016, 'steps': 21792, 'loss/train': 2.4515292644500732}
-03/04/2022 15:03:52 - INFO - codeparrot_training - Step 21793: {'lr': 0.0004782573939038402, 'samples': 11158528, 'steps': 21793, 'loss/train': 1.7702375650405884}
-03/04/2022 15:03:52 - INFO - codeparrot_training - Skipping example with length 5 (seq_length=1024)
-03/04/2022 15:03:58 - INFO - codeparrot_training - Step 21794: {'lr': 0.0004782552292666273, 'samples': 11159040, 'steps': 21794, 'loss/train': 2.139216661453247}
-03/04/2022 15:04:01 - INFO - codeparrot_training - Step 21795: {'lr': 0.0004782530645265661, 'samples': 11159552, 'steps': 21795, 'loss/train': 1.4114508628845215}
-03/04/2022 15:04:01 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/04/2022 15:04:06 - INFO - codeparrot_training - Step 21796: {'lr': 0.0004782508996836576, 'samples': 11160064, 'steps': 21796, 'loss/train': 0.22169779241085052}
-03/04/2022 15:04:09 - INFO - codeparrot_training - Step 21797: {'lr': 0.00047824873473790275, 'samples': 11160576, 'steps': 21797, 'loss/train': 1.795056700706482}
-03/04/2022 15:04:09 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/04/2022 15:04:14 - INFO - codeparrot_training - Step 21798: {'lr': 0.0004782465696893025, 'samples': 11161088, 'steps': 21798, 'loss/train': 2.2166190147399902}
-03/04/2022 15:04:18 - INFO - codeparrot_training - Step 21799: {'lr': 0.0004782444045378579, 'samples': 11161600, 'steps': 21799, 'loss/train': 2.013003349304199}
-03/04/2022 15:04:18 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/04/2022 15:04:23 - INFO - codeparrot_training - Step 21800: {'lr': 0.00047824223928356993, 'samples': 11162112, 'steps': 21800, 'loss/train': 1.4470890760421753}
-03/04/2022 15:04:26 - INFO - codeparrot_training - Step 21801: {'lr': 0.0004782400739264395, 'samples': 11162624, 'steps': 21801, 'loss/train': 1.2553268671035767}
-03/04/2022 15:04:26 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/04/2022 15:04:32 - INFO - codeparrot_training - Step 21802: {'lr': 0.00047823790846646764, 'samples': 11163136, 'steps': 21802, 'loss/train': 2.2673146724700928}
-03/04/2022 15:04:35 - INFO - codeparrot_training - Step 21803: {'lr': 0.0004782357429036553, 'samples': 11163648, 'steps': 21803, 'loss/train': 1.3851523399353027}
-03/04/2022 15:04:35 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/04/2022 15:04:40 - INFO - codeparrot_training - Step 21804: {'lr': 0.00047823357723800344, 'samples': 11164160, 'steps': 21804, 'loss/train': 1.148398518562317}
-03/04/2022 15:04:43 - INFO - codeparrot_training - Step 21805: {'lr': 0.000478231411469513, 'samples': 11164672, 'steps': 21805, 'loss/train': 2.158350944519043}
-03/04/2022 15:04:43 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/04/2022 15:04:48 - INFO - codeparrot_training - Step 21806: {'lr': 0.000478229245598185, 'samples': 11165184, 'steps': 21806, 'loss/train': 1.5747545957565308}
-03/04/2022 15:04:51 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/04/2022 15:04:54 - INFO - codeparrot_training - Step 21807: {'lr': 0.00047822707962402055, 'samples': 11165696, 'steps': 21807, 'loss/train': 2.123668909072876}
-03/04/2022 15:04:57 - INFO - codeparrot_training - Step 21808: {'lr': 0.00047822491354702044, 'samples': 11166208, 'steps': 21808, 'loss/train': 2.398266077041626}
-03/04/2022 15:05:00 - INFO - codeparrot_training - Step 21809: {'lr': 0.0004782227473671857, 'samples': 11166720, 'steps': 21809, 'loss/train': 2.150418519973755}
-03/04/2022 15:05:00 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/04/2022 15:05:05 - INFO - codeparrot_training - Step 21810: {'lr': 0.00047822058108451727, 'samples': 11167232, 'steps': 21810, 'loss/train': 1.6845968961715698}
-03/04/2022 15:05:09 - INFO - codeparrot_training - Step 21811: {'lr': 0.0004782184146990162, 'samples': 11167744, 'steps': 21811, 'loss/train': 1.9970160722732544}
-03/04/2022 15:05:09 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/04/2022 15:05:14 - INFO - codeparrot_training - Step 21812: {'lr': 0.00047821624821068346, 'samples': 11168256, 'steps': 21812, 'loss/train': 1.906862497329712}
-03/04/2022 15:05:17 - INFO - codeparrot_training - Step 21813: {'lr': 0.00047821408161952, 'samples': 11168768, 'steps': 21813, 'loss/train': 0.9338131546974182}
-03/04/2022 15:05:17 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 15:05:22 - INFO - codeparrot_training - Step 21814: {'lr': 0.00047821191492552676, 'samples': 11169280, 'steps': 21814, 'loss/train': 2.402505397796631}
-03/04/2022 15:05:26 - INFO - codeparrot_training - Step 21815: {'lr': 0.00047820974812870477, 'samples': 11169792, 'steps': 21815, 'loss/train': 1.173385739326477}
-03/04/2022 15:05:26 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/04/2022 15:05:31 - INFO - codeparrot_training - Step 21816: {'lr': 0.00047820758122905493, 'samples': 11170304, 'steps': 21816, 'loss/train': 2.1541244983673096}
-03/04/2022 15:05:34 - INFO - codeparrot_training - Step 21817: {'lr': 0.0004782054142265784, 'samples': 11170816, 'steps': 21817, 'loss/train': 2.2916057109832764}
-03/04/2022 15:05:40 - INFO - codeparrot_training - Step 21818: {'lr': 0.00047820324712127593, 'samples': 11171328, 'steps': 21818, 'loss/train': 2.580711841583252}
-03/04/2022 15:05:43 - INFO - codeparrot_training - Step 21819: {'lr': 0.0004782010799131487, 'samples': 11171840, 'steps': 21819, 'loss/train': 2.334886074066162}
-03/04/2022 15:05:45 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/04/2022 15:05:48 - INFO - codeparrot_training - Step 21820: {'lr': 0.0004781989126021975, 'samples': 11172352, 'steps': 21820, 'loss/train': 1.8340622186660767}
-03/04/2022 15:05:51 - INFO - codeparrot_training - Step 21821: {'lr': 0.00047819674518842335, 'samples': 11172864, 'steps': 21821, 'loss/train': 1.7518725395202637}
-03/04/2022 15:05:53 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 15:05:56 - INFO - codeparrot_training - Step 21822: {'lr': 0.00047819457767182735, 'samples': 11173376, 'steps': 21822, 'loss/train': 2.2857983112335205}
-03/04/2022 15:06:00 - INFO - codeparrot_training - Step 21823: {'lr': 0.0004781924100524104, 'samples': 11173888, 'steps': 21823, 'loss/train': 2.1611151695251465}
-03/04/2022 15:06:01 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 15:06:05 - INFO - codeparrot_training - Step 21824: {'lr': 0.00047819024233017337, 'samples': 11174400, 'steps': 21824, 'loss/train': 2.8073413372039795}
-03/04/2022 15:06:08 - INFO - codeparrot_training - Step 21825: {'lr': 0.00047818807450511746, 'samples': 11174912, 'steps': 21825, 'loss/train': 1.690420389175415}
-03/04/2022 15:06:11 - INFO - codeparrot_training - Step 21826: {'lr': 0.00047818590657724345, 'samples': 11175424, 'steps': 21826, 'loss/train': 2.0372583866119385}
-03/04/2022 15:06:11 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/04/2022 15:06:17 - INFO - codeparrot_training - Step 21827: {'lr': 0.0004781837385465524, 'samples': 11175936, 'steps': 21827, 'loss/train': 0.8191588521003723}
-03/04/2022 15:06:20 - INFO - codeparrot_training - Step 21828: {'lr': 0.00047818157041304535, 'samples': 11176448, 'steps': 21828, 'loss/train': 2.6526706218719482}
-03/04/2022 15:06:20 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/04/2022 15:06:25 - INFO - codeparrot_training - Step 21829: {'lr': 0.00047817940217672315, 'samples': 11176960, 'steps': 21829, 'loss/train': 2.260767698287964}
-03/04/2022 15:06:28 - INFO - codeparrot_training - Step 21830: {'lr': 0.0004781772338375868, 'samples': 11177472, 'steps': 21830, 'loss/train': 1.464534878730774}
-03/04/2022 15:06:28 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/04/2022 15:06:34 - INFO - codeparrot_training - Step 21831: {'lr': 0.0004781750653956374, 'samples': 11177984, 'steps': 21831, 'loss/train': 1.628416657447815}
-03/04/2022 15:06:37 - INFO - codeparrot_training - Step 21832: {'lr': 0.00047817289685087575, 'samples': 11178496, 'steps': 21832, 'loss/train': 2.012073040008545}
-03/04/2022 15:06:37 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 15:06:42 - INFO - codeparrot_training - Step 21833: {'lr': 0.00047817072820330287, 'samples': 11179008, 'steps': 21833, 'loss/train': 1.7664902210235596}
-03/04/2022 15:06:45 - INFO - codeparrot_training - Step 21834: {'lr': 0.0004781685594529199, 'samples': 11179520, 'steps': 21834, 'loss/train': 1.1208529472351074}
-03/04/2022 15:06:46 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/04/2022 15:06:51 - INFO - codeparrot_training - Step 21835: {'lr': 0.00047816639059972767, 'samples': 11180032, 'steps': 21835, 'loss/train': 1.084551215171814}
-03/04/2022 15:06:54 - INFO - codeparrot_training - Step 21836: {'lr': 0.00047816422164372713, 'samples': 11180544, 'steps': 21836, 'loss/train': 1.924899935722351}
-03/04/2022 15:06:55 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/04/2022 15:06:59 - INFO - codeparrot_training - Step 21837: {'lr': 0.00047816205258491935, 'samples': 11181056, 'steps': 21837, 'loss/train': 1.776485562324524}
-03/04/2022 15:07:02 - INFO - codeparrot_training - Step 21838: {'lr': 0.0004781598834233053, 'samples': 11181568, 'steps': 21838, 'loss/train': 1.2393256425857544}
-03/04/2022 15:07:03 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/04/2022 15:07:08 - INFO - codeparrot_training - Step 21839: {'lr': 0.0004781577141588859, 'samples': 11182080, 'steps': 21839, 'loss/train': 1.3320717811584473}
-03/04/2022 15:07:11 - INFO - codeparrot_training - Step 21840: {'lr': 0.0004781555447916621, 'samples': 11182592, 'steps': 21840, 'loss/train': 2.4278759956359863}
-03/04/2022 15:07:11 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/04/2022 15:07:16 - INFO - codeparrot_training - Step 21841: {'lr': 0.000478153375321635, 'samples': 11183104, 'steps': 21841, 'loss/train': 0.885839581489563}
-03/04/2022 15:07:19 - INFO - codeparrot_training - Step 21842: {'lr': 0.0004781512057488055, 'samples': 11183616, 'steps': 21842, 'loss/train': 2.154135227203369}
-03/04/2022 15:07:20 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/04/2022 15:07:25 - INFO - codeparrot_training - Step 21843: {'lr': 0.00047814903607317454, 'samples': 11184128, 'steps': 21843, 'loss/train': 2.189629554748535}
-03/04/2022 15:07:28 - INFO - codeparrot_training - Step 21844: {'lr': 0.00047814686629474323, 'samples': 11184640, 'steps': 21844, 'loss/train': 1.5701254606246948}
-03/04/2022 15:07:30 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/04/2022 15:07:33 - INFO - codeparrot_training - Step 21845: {'lr': 0.00047814469641351237, 'samples': 11185152, 'steps': 21845, 'loss/train': 1.7391749620437622}
-03/04/2022 15:07:37 - INFO - codeparrot_training - Step 21846: {'lr': 0.0004781425264294831, 'samples': 11185664, 'steps': 21846, 'loss/train': 1.8192226886749268}
-03/04/2022 15:07:38 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 15:07:42 - INFO - codeparrot_training - Step 21847: {'lr': 0.0004781403563426563, 'samples': 11186176, 'steps': 21847, 'loss/train': 2.321241855621338}
-03/04/2022 15:07:45 - INFO - codeparrot_training - Step 21848: {'lr': 0.00047813818615303295, 'samples': 11186688, 'steps': 21848, 'loss/train': 1.6791707277297974}
-03/04/2022 15:07:47 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 15:07:50 - INFO - codeparrot_training - Step 21849: {'lr': 0.00047813601586061414, 'samples': 11187200, 'steps': 21849, 'loss/train': 1.761741042137146}
-03/04/2022 15:07:53 - INFO - codeparrot_training - Step 21850: {'lr': 0.0004781338454654007, 'samples': 11187712, 'steps': 21850, 'loss/train': 2.7285876274108887}
-03/04/2022 15:07:55 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/04/2022 15:07:59 - INFO - codeparrot_training - Step 21851: {'lr': 0.00047813167496739363, 'samples': 11188224, 'steps': 21851, 'loss/train': 2.0957930088043213}
-03/04/2022 15:08:02 - INFO - codeparrot_training - Step 21852: {'lr': 0.00047812950436659405, 'samples': 11188736, 'steps': 21852, 'loss/train': 1.8517420291900635}
-03/04/2022 15:08:03 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/04/2022 15:08:07 - INFO - codeparrot_training - Step 21853: {'lr': 0.0004781273336630028, 'samples': 11189248, 'steps': 21853, 'loss/train': 2.5016672611236572}
-03/04/2022 15:08:10 - INFO - codeparrot_training - Step 21854: {'lr': 0.00047812516285662086, 'samples': 11189760, 'steps': 21854, 'loss/train': 0.9420574307441711}
-03/04/2022 15:08:12 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 15:08:16 - INFO - codeparrot_training - Step 21855: {'lr': 0.00047812299194744924, 'samples': 11190272, 'steps': 21855, 'loss/train': 2.1337785720825195}
-03/04/2022 15:08:19 - INFO - codeparrot_training - Step 21856: {'lr': 0.0004781208209354889, 'samples': 11190784, 'steps': 21856, 'loss/train': 2.581223726272583}
-03/04/2022 15:08:20 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 15:08:24 - INFO - codeparrot_training - Step 21857: {'lr': 0.00047811864982074087, 'samples': 11191296, 'steps': 21857, 'loss/train': 2.2595906257629395}
-03/04/2022 15:08:28 - INFO - codeparrot_training - Step 21858: {'lr': 0.0004781164786032061, 'samples': 11191808, 'steps': 21858, 'loss/train': 1.933264970779419}
-03/04/2022 15:08:29 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 15:08:33 - INFO - codeparrot_training - Step 21859: {'lr': 0.0004781143072828856, 'samples': 11192320, 'steps': 21859, 'loss/train': 2.4519965648651123}
-03/04/2022 15:08:36 - INFO - codeparrot_training - Step 21860: {'lr': 0.00047811213585978023, 'samples': 11192832, 'steps': 21860, 'loss/train': 1.7040185928344727}
-03/04/2022 15:08:37 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 15:08:42 - INFO - codeparrot_training - Step 21861: {'lr': 0.0004781099643338911, 'samples': 11193344, 'steps': 21861, 'loss/train': 2.434128761291504}
-03/04/2022 15:08:45 - INFO - codeparrot_training - Step 21862: {'lr': 0.00047810779270521914, 'samples': 11193856, 'steps': 21862, 'loss/train': 2.8304762840270996}
-03/04/2022 15:08:46 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/04/2022 15:08:50 - INFO - codeparrot_training - Step 21863: {'lr': 0.0004781056209737653, 'samples': 11194368, 'steps': 21863, 'loss/train': 2.906376600265503}
-03/04/2022 15:08:53 - INFO - codeparrot_training - Step 21864: {'lr': 0.00047810344913953065, 'samples': 11194880, 'steps': 21864, 'loss/train': 1.102380633354187}
-03/04/2022 15:08:54 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/04/2022 15:08:59 - INFO - codeparrot_training - Step 21865: {'lr': 0.0004781012772025161, 'samples': 11195392, 'steps': 21865, 'loss/train': 1.9105682373046875}
-03/04/2022 15:09:02 - INFO - codeparrot_training - Step 21866: {'lr': 0.0004780991051627226, 'samples': 11195904, 'steps': 21866, 'loss/train': 2.0018744468688965}
-03/04/2022 15:09:03 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 15:09:07 - INFO - codeparrot_training - Step 21867: {'lr': 0.0004780969330201511, 'samples': 11196416, 'steps': 21867, 'loss/train': 2.1055076122283936}
-03/04/2022 15:09:10 - INFO - codeparrot_training - Step 21868: {'lr': 0.0004780947607748027, 'samples': 11196928, 'steps': 21868, 'loss/train': 1.8085702657699585}
-03/04/2022 15:09:12 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/04/2022 15:09:15 - INFO - codeparrot_training - Step 21869: {'lr': 0.00047809258842667837, 'samples': 11197440, 'steps': 21869, 'loss/train': 1.9983018636703491}
-03/04/2022 15:09:19 - INFO - codeparrot_training - Step 21870: {'lr': 0.000478090415975779, 'samples': 11197952, 'steps': 21870, 'loss/train': 1.7375638484954834}
-03/04/2022 15:09:20 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 15:09:24 - INFO - codeparrot_training - Step 21871: {'lr': 0.00047808824342210565, 'samples': 11198464, 'steps': 21871, 'loss/train': 2.9153366088867188}
-03/04/2022 15:09:28 - INFO - codeparrot_training - Step 21872: {'lr': 0.0004780860707656592, 'samples': 11198976, 'steps': 21872, 'loss/train': 2.194629669189453}
-03/04/2022 15:09:31 - INFO - codeparrot_training - Step 21873: {'lr': 0.0004780838980064407, 'samples': 11199488, 'steps': 21873, 'loss/train': 1.9374475479125977}
-03/04/2022 15:09:31 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 15:09:36 - INFO - codeparrot_training - Step 21874: {'lr': 0.00047808172514445115, 'samples': 11200000, 'steps': 21874, 'loss/train': 2.315654754638672}
-03/04/2022 15:09:39 - INFO - codeparrot_training - Step 21875: {'lr': 0.0004780795521796914, 'samples': 11200512, 'steps': 21875, 'loss/train': 2.5133540630340576}
-03/04/2022 15:09:40 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/04/2022 15:09:45 - INFO - codeparrot_training - Step 21876: {'lr': 0.0004780773791121626, 'samples': 11201024, 'steps': 21876, 'loss/train': 1.17023503780365}
-03/04/2022 15:09:48 - INFO - codeparrot_training - Step 21877: {'lr': 0.0004780752059418656, 'samples': 11201536, 'steps': 21877, 'loss/train': 2.0274531841278076}
-03/04/2022 15:09:49 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 15:09:53 - INFO - codeparrot_training - Step 21878: {'lr': 0.0004780730326688015, 'samples': 11202048, 'steps': 21878, 'loss/train': 2.395108699798584}
-03/04/2022 15:09:56 - INFO - codeparrot_training - Step 21879: {'lr': 0.0004780708592929712, 'samples': 11202560, 'steps': 21879, 'loss/train': 0.8744766116142273}
-03/04/2022 15:09:58 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/04/2022 15:10:02 - INFO - codeparrot_training - Step 21880: {'lr': 0.0004780686858143756, 'samples': 11203072, 'steps': 21880, 'loss/train': 2.3479812145233154}
-03/04/2022 15:10:05 - INFO - codeparrot_training - Step 21881: {'lr': 0.0004780665122330159, 'samples': 11203584, 'steps': 21881, 'loss/train': 2.292370319366455}
-03/04/2022 15:10:06 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/04/2022 15:10:10 - INFO - codeparrot_training - Step 21882: {'lr': 0.00047806433854889285, 'samples': 11204096, 'steps': 21882, 'loss/train': 2.1839635372161865}
-03/04/2022 15:10:13 - INFO - codeparrot_training - Step 21883: {'lr': 0.0004780621647620076, 'samples': 11204608, 'steps': 21883, 'loss/train': 1.233628511428833}
-03/04/2022 15:10:14 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/04/2022 15:10:18 - INFO - codeparrot_training - Step 21884: {'lr': 0.00047805999087236097, 'samples': 11205120, 'steps': 21884, 'loss/train': 1.3520617485046387}
-03/04/2022 15:10:22 - INFO - codeparrot_training - Step 21885: {'lr': 0.0004780578168799541, 'samples': 11205632, 'steps': 21885, 'loss/train': 1.4650671482086182}
-03/04/2022 15:10:23 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 15:10:27 - INFO - codeparrot_training - Step 21886: {'lr': 0.00047805564278478787, 'samples': 11206144, 'steps': 21886, 'loss/train': 1.2267347574234009}
-03/04/2022 15:10:30 - INFO - codeparrot_training - Step 21887: {'lr': 0.00047805346858686325, 'samples': 11206656, 'steps': 21887, 'loss/train': 1.8517637252807617}
-03/04/2022 15:10:31 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 15:10:35 - INFO - codeparrot_training - Step 21888: {'lr': 0.0004780512942861813, 'samples': 11207168, 'steps': 21888, 'loss/train': 1.3061579465866089}
-03/04/2022 15:10:38 - INFO - codeparrot_training - Step 21889: {'lr': 0.00047804911988274303, 'samples': 11207680, 'steps': 21889, 'loss/train': 0.7447634935379028}
-03/04/2022 15:10:40 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/04/2022 15:10:44 - INFO - codeparrot_training - Step 21890: {'lr': 0.00047804694537654927, 'samples': 11208192, 'steps': 21890, 'loss/train': 2.9917595386505127}
-03/04/2022 15:10:47 - INFO - codeparrot_training - Step 21891: {'lr': 0.00047804477076760106, 'samples': 11208704, 'steps': 21891, 'loss/train': 1.2507126331329346}
-03/04/2022 15:10:48 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 15:10:52 - INFO - codeparrot_training - Step 21892: {'lr': 0.0004780425960558994, 'samples': 11209216, 'steps': 21892, 'loss/train': 2.321552276611328}
-03/04/2022 15:10:56 - INFO - codeparrot_training - Step 21893: {'lr': 0.00047804042124144526, 'samples': 11209728, 'steps': 21893, 'loss/train': 2.0158417224884033}
-03/04/2022 15:10:57 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/04/2022 15:11:01 - INFO - codeparrot_training - Step 21894: {'lr': 0.00047803824632423967, 'samples': 11210240, 'steps': 21894, 'loss/train': 1.6909152269363403}
-03/04/2022 15:11:04 - INFO - codeparrot_training - Step 21895: {'lr': 0.0004780360713042835, 'samples': 11210752, 'steps': 21895, 'loss/train': 1.3176530599594116}
-03/04/2022 15:11:06 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/04/2022 15:11:09 - INFO - codeparrot_training - Step 21896: {'lr': 0.0004780338961815779, 'samples': 11211264, 'steps': 21896, 'loss/train': 1.0510034561157227}
-03/04/2022 15:11:12 - INFO - codeparrot_training - Step 21897: {'lr': 0.00047803172095612365, 'samples': 11211776, 'steps': 21897, 'loss/train': 2.5747287273406982}
-03/04/2022 15:11:15 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/04/2022 15:11:18 - INFO - codeparrot_training - Step 21898: {'lr': 0.00047802954562792185, 'samples': 11212288, 'steps': 21898, 'loss/train': 1.6837868690490723}
-03/04/2022 15:11:21 - INFO - codeparrot_training - Step 21899: {'lr': 0.0004780273701969734, 'samples': 11212800, 'steps': 21899, 'loss/train': 1.8674604892730713}
-03/04/2022 15:11:23 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/04/2022 15:11:26 - INFO - codeparrot_training - Step 21900: {'lr': 0.00047802519466327945, 'samples': 11213312, 'steps': 21900, 'loss/train': 2.1394357681274414}
-03/04/2022 15:11:29 - INFO - codeparrot_training - Step 21901: {'lr': 0.00047802301902684076, 'samples': 11213824, 'steps': 21901, 'loss/train': 1.7948881387710571}
-03/04/2022 15:11:31 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/04/2022 15:11:35 - INFO - codeparrot_training - Step 21902: {'lr': 0.0004780208432876585, 'samples': 11214336, 'steps': 21902, 'loss/train': 1.7493559122085571}
-03/04/2022 15:11:38 - INFO - codeparrot_training - Step 21903: {'lr': 0.00047801866744573353, 'samples': 11214848, 'steps': 21903, 'loss/train': 1.5645321607589722}
-03/04/2022 15:11:40 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/04/2022 15:11:43 - INFO - codeparrot_training - Step 21904: {'lr': 0.00047801649150106684, 'samples': 11215360, 'steps': 21904, 'loss/train': 1.8310548067092896}
-03/04/2022 15:11:46 - INFO - codeparrot_training - Step 21905: {'lr': 0.00047801431545365947, 'samples': 11215872, 'steps': 21905, 'loss/train': 1.6645469665527344}
-03/04/2022 15:11:48 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 15:11:51 - INFO - codeparrot_training - Step 21906: {'lr': 0.0004780121393035124, 'samples': 11216384, 'steps': 21906, 'loss/train': 2.0497524738311768}
-03/04/2022 15:11:55 - INFO - codeparrot_training - Step 21907: {'lr': 0.0004780099630506265, 'samples': 11216896, 'steps': 21907, 'loss/train': 1.5563349723815918}
-03/04/2022 15:11:56 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 15:12:00 - INFO - codeparrot_training - Step 21908: {'lr': 0.0004780077866950029, 'samples': 11217408, 'steps': 21908, 'loss/train': 1.4954856634140015}
-03/04/2022 15:12:03 - INFO - codeparrot_training - Step 21909: {'lr': 0.00047800561023664246, 'samples': 11217920, 'steps': 21909, 'loss/train': 1.5529009103775024}
-03/04/2022 15:12:07 - INFO - codeparrot_training - Step 21910: {'lr': 0.0004780034336755462, 'samples': 11218432, 'steps': 21910, 'loss/train': 0.8435540199279785}
-03/04/2022 15:12:07 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/04/2022 15:12:12 - INFO - codeparrot_training - Step 21911: {'lr': 0.00047800125701171517, 'samples': 11218944, 'steps': 21911, 'loss/train': 1.6277611255645752}
-03/04/2022 15:12:15 - INFO - codeparrot_training - Step 21912: {'lr': 0.00047799908024515026, 'samples': 11219456, 'steps': 21912, 'loss/train': 2.128458023071289}
-03/04/2022 15:12:15 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 15:12:20 - INFO - codeparrot_training - Step 21913: {'lr': 0.0004779969033758525, 'samples': 11219968, 'steps': 21913, 'loss/train': 1.6970218420028687}
-03/04/2022 15:12:23 - INFO - codeparrot_training - Step 21914: {'lr': 0.00047799472640382287, 'samples': 11220480, 'steps': 21914, 'loss/train': 1.6252541542053223}
-03/04/2022 15:12:23 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 15:12:28 - INFO - codeparrot_training - Step 21915: {'lr': 0.0004779925493290623, 'samples': 11220992, 'steps': 21915, 'loss/train': 1.781416893005371}
-03/04/2022 15:12:32 - INFO - codeparrot_training - Step 21916: {'lr': 0.00047799037215157184, 'samples': 11221504, 'steps': 21916, 'loss/train': 1.6600096225738525}
-03/04/2022 15:12:32 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 15:12:37 - INFO - codeparrot_training - Step 21917: {'lr': 0.0004779881948713524, 'samples': 11222016, 'steps': 21917, 'loss/train': 0.763556957244873}
-03/04/2022 15:12:40 - INFO - codeparrot_training - Step 21918: {'lr': 0.000477986017488405, 'samples': 11222528, 'steps': 21918, 'loss/train': 1.7606571912765503}
-03/04/2022 15:12:40 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/04/2022 15:12:45 - INFO - codeparrot_training - Step 21919: {'lr': 0.00047798384000273053, 'samples': 11223040, 'steps': 21919, 'loss/train': 1.799996256828308}
-03/04/2022 15:12:49 - INFO - codeparrot_training - Step 21920: {'lr': 0.0004779816624143302, 'samples': 11223552, 'steps': 21920, 'loss/train': 1.1845853328704834}
-03/04/2022 15:12:49 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 15:12:54 - INFO - codeparrot_training - Step 21921: {'lr': 0.0004779794847232048, 'samples': 11224064, 'steps': 21921, 'loss/train': 0.5976961255073547}
-03/04/2022 15:12:57 - INFO - codeparrot_training - Step 21922: {'lr': 0.0004779773069293554, 'samples': 11224576, 'steps': 21922, 'loss/train': 1.7079509496688843}
-03/04/2022 15:12:57 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 15:13:02 - INFO - codeparrot_training - Step 21923: {'lr': 0.00047797512903278283, 'samples': 11225088, 'steps': 21923, 'loss/train': 1.7016901969909668}
-03/04/2022 15:13:05 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/04/2022 15:13:08 - INFO - codeparrot_training - Step 21924: {'lr': 0.0004779729510334883, 'samples': 11225600, 'steps': 21924, 'loss/train': 1.265492558479309}
-03/04/2022 15:13:11 - INFO - codeparrot_training - Step 21925: {'lr': 0.0004779707729314726, 'samples': 11226112, 'steps': 21925, 'loss/train': 2.2427430152893066}
-03/04/2022 15:13:14 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/04/2022 15:13:16 - INFO - codeparrot_training - Step 21926: {'lr': 0.0004779685947267369, 'samples': 11226624, 'steps': 21926, 'loss/train': 1.3757342100143433}
-03/04/2022 15:13:19 - INFO - codeparrot_training - Step 21927: {'lr': 0.00047796641641928195, 'samples': 11227136, 'steps': 21927, 'loss/train': 2.5644285678863525}
-03/04/2022 15:13:22 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/04/2022 15:13:25 - INFO - codeparrot_training - Step 21928: {'lr': 0.00047796423800910894, 'samples': 11227648, 'steps': 21928, 'loss/train': 2.0892622470855713}
-03/04/2022 15:13:28 - INFO - codeparrot_training - Step 21929: {'lr': 0.00047796205949621873, 'samples': 11228160, 'steps': 21929, 'loss/train': 1.2484568357467651}
-03/04/2022 15:13:31 - INFO - codeparrot_training - Step 21930: {'lr': 0.00047795988088061224, 'samples': 11228672, 'steps': 21930, 'loss/train': 2.413625955581665}
-03/04/2022 15:13:31 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/04/2022 15:13:36 - INFO - codeparrot_training - Step 21931: {'lr': 0.00047795770216229065, 'samples': 11229184, 'steps': 21931, 'loss/train': 2.2180533409118652}
-03/04/2022 15:13:39 - INFO - codeparrot_training - Step 21932: {'lr': 0.0004779555233412548, 'samples': 11229696, 'steps': 21932, 'loss/train': 0.7903336882591248}
-03/04/2022 15:13:40 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/04/2022 15:13:45 - INFO - codeparrot_training - Step 21933: {'lr': 0.0004779533444175058, 'samples': 11230208, 'steps': 21933, 'loss/train': 1.8956271409988403}
-03/04/2022 15:13:48 - INFO - codeparrot_training - Step 21934: {'lr': 0.00047795116539104445, 'samples': 11230720, 'steps': 21934, 'loss/train': 1.2361618280410767}
-03/04/2022 15:13:48 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 15:13:53 - INFO - codeparrot_training - Step 21935: {'lr': 0.0004779489862618718, 'samples': 11231232, 'steps': 21935, 'loss/train': 1.2130106687545776}
-03/04/2022 15:13:57 - INFO - codeparrot_training - Step 21936: {'lr': 0.00047794680702998893, 'samples': 11231744, 'steps': 21936, 'loss/train': 1.6484390497207642}
-03/04/2022 15:13:57 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/04/2022 15:14:02 - INFO - codeparrot_training - Step 21937: {'lr': 0.0004779446276953967, 'samples': 11232256, 'steps': 21937, 'loss/train': 2.1189677715301514}
-03/04/2022 15:14:05 - INFO - codeparrot_training - Step 21938: {'lr': 0.00047794244825809614, 'samples': 11232768, 'steps': 21938, 'loss/train': 2.193443536758423}
-03/04/2022 15:14:05 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/04/2022 15:14:10 - INFO - codeparrot_training - Step 21939: {'lr': 0.0004779402687180882, 'samples': 11233280, 'steps': 21939, 'loss/train': 1.525948405265808}
-03/04/2022 15:14:13 - INFO - codeparrot_training - Step 21940: {'lr': 0.00047793808907537394, 'samples': 11233792, 'steps': 21940, 'loss/train': 1.7107340097427368}
-03/04/2022 15:14:14 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 15:14:19 - INFO - codeparrot_training - Step 21941: {'lr': 0.0004779359093299543, 'samples': 11234304, 'steps': 21941, 'loss/train': 1.7578213214874268}
-03/04/2022 15:14:22 - INFO - codeparrot_training - Step 21942: {'lr': 0.00047793372948183024, 'samples': 11234816, 'steps': 21942, 'loss/train': 1.7391029596328735}
-03/04/2022 15:14:23 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 15:14:27 - INFO - codeparrot_training - Step 21943: {'lr': 0.0004779315495310027, 'samples': 11235328, 'steps': 21943, 'loss/train': 1.7528722286224365}
-03/04/2022 15:14:30 - INFO - codeparrot_training - Step 21944: {'lr': 0.00047792936947747285, 'samples': 11235840, 'steps': 21944, 'loss/train': 2.034247636795044}
-03/04/2022 15:14:31 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/04/2022 15:14:35 - INFO - codeparrot_training - Step 21945: {'lr': 0.00047792718932124147, 'samples': 11236352, 'steps': 21945, 'loss/train': 1.9893953800201416}
-03/04/2022 15:14:39 - INFO - codeparrot_training - Step 21946: {'lr': 0.00047792500906230963, 'samples': 11236864, 'steps': 21946, 'loss/train': 1.4049264192581177}
-03/04/2022 15:14:39 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/04/2022 15:14:44 - INFO - codeparrot_training - Step 21947: {'lr': 0.00047792282870067827, 'samples': 11237376, 'steps': 21947, 'loss/train': 2.1591737270355225}
-03/04/2022 15:14:47 - INFO - codeparrot_training - Step 21948: {'lr': 0.0004779206482363484, 'samples': 11237888, 'steps': 21948, 'loss/train': 2.408374071121216}
-03/04/2022 15:14:47 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 15:14:52 - INFO - codeparrot_training - Step 21949: {'lr': 0.000477918467669321, 'samples': 11238400, 'steps': 21949, 'loss/train': 3.3060591220855713}
-03/04/2022 15:14:55 - INFO - codeparrot_training - Step 21950: {'lr': 0.0004779162869995971, 'samples': 11238912, 'steps': 21950, 'loss/train': 2.0688822269439697}
-03/04/2022 15:14:56 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/04/2022 15:15:01 - INFO - codeparrot_training - Step 21951: {'lr': 0.00047791410622717757, 'samples': 11239424, 'steps': 21951, 'loss/train': 2.2057876586914062}
-03/04/2022 15:15:04 - INFO - codeparrot_training - Step 21952: {'lr': 0.0004779119253520635, 'samples': 11239936, 'steps': 21952, 'loss/train': 0.6143112182617188}
-03/04/2022 15:15:04 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 15:15:09 - INFO - codeparrot_training - Step 21953: {'lr': 0.0004779097443742558, 'samples': 11240448, 'steps': 21953, 'loss/train': 1.707655668258667}
-03/04/2022 15:15:12 - INFO - codeparrot_training - Step 21954: {'lr': 0.0004779075632937556, 'samples': 11240960, 'steps': 21954, 'loss/train': 1.8211047649383545}
-03/04/2022 15:15:13 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/04/2022 15:15:18 - INFO - codeparrot_training - Step 21955: {'lr': 0.00047790538211056366, 'samples': 11241472, 'steps': 21955, 'loss/train': 1.1796493530273438}
-03/04/2022 15:15:21 - INFO - codeparrot_training - Step 21956: {'lr': 0.00047790320082468106, 'samples': 11241984, 'steps': 21956, 'loss/train': 1.7350280284881592}
-03/04/2022 15:15:21 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/04/2022 15:15:27 - INFO - codeparrot_training - Step 21957: {'lr': 0.00047790101943610884, 'samples': 11242496, 'steps': 21957, 'loss/train': 1.922612190246582}
-03/04/2022 15:15:30 - INFO - codeparrot_training - Step 21958: {'lr': 0.000477898837944848, 'samples': 11243008, 'steps': 21958, 'loss/train': 2.4324440956115723}
-03/04/2022 15:15:32 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/04/2022 15:15:35 - INFO - codeparrot_training - Step 21959: {'lr': 0.0004778966563508994, 'samples': 11243520, 'steps': 21959, 'loss/train': 1.0910776853561401}
-03/04/2022 15:15:38 - INFO - codeparrot_training - Step 21960: {'lr': 0.00047789447465426406, 'samples': 11244032, 'steps': 21960, 'loss/train': 1.9292227029800415}
-03/04/2022 15:15:41 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/04/2022 15:15:44 - INFO - codeparrot_training - Step 21961: {'lr': 0.000477892292854943, 'samples': 11244544, 'steps': 21961, 'loss/train': 2.1197433471679688}
-03/04/2022 15:15:47 - INFO - codeparrot_training - Step 21962: {'lr': 0.00047789011095293723, 'samples': 11245056, 'steps': 21962, 'loss/train': 2.1343019008636475}
-03/04/2022 15:15:49 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/04/2022 15:15:52 - INFO - codeparrot_training - Step 21963: {'lr': 0.0004778879289482476, 'samples': 11245568, 'steps': 21963, 'loss/train': 1.8667480945587158}
-03/04/2022 15:15:55 - INFO - codeparrot_training - Step 21964: {'lr': 0.00047788574684087527, 'samples': 11246080, 'steps': 21964, 'loss/train': 2.2299346923828125}
-03/04/2022 15:15:59 - INFO - codeparrot_training - Step 21965: {'lr': 0.0004778835646308211, 'samples': 11246592, 'steps': 21965, 'loss/train': 0.9373946785926819}
-03/04/2022 15:15:59 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/04/2022 15:16:04 - INFO - codeparrot_training - Step 21966: {'lr': 0.0004778813823180861, 'samples': 11247104, 'steps': 21966, 'loss/train': 1.511555552482605}
-03/04/2022 15:16:07 - INFO - codeparrot_training - Step 21967: {'lr': 0.0004778791999026713, 'samples': 11247616, 'steps': 21967, 'loss/train': 1.9830635786056519}
-03/04/2022 15:16:07 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/04/2022 15:16:12 - INFO - codeparrot_training - Step 21968: {'lr': 0.0004778770173845777, 'samples': 11248128, 'steps': 21968, 'loss/train': 2.013211727142334}
-03/04/2022 15:16:16 - INFO - codeparrot_training - Step 21969: {'lr': 0.00047787483476380613, 'samples': 11248640, 'steps': 21969, 'loss/train': 2.1828744411468506}
-03/04/2022 15:16:16 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/04/2022 15:16:21 - INFO - codeparrot_training - Step 21970: {'lr': 0.0004778726520403577, 'samples': 11249152, 'steps': 21970, 'loss/train': 1.5246416330337524}
-03/04/2022 15:16:24 - INFO - codeparrot_training - Step 21971: {'lr': 0.00047787046921423336, 'samples': 11249664, 'steps': 21971, 'loss/train': 1.9714858531951904}
-03/04/2022 15:16:24 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/04/2022 15:16:29 - INFO - codeparrot_training - Step 21972: {'lr': 0.00047786828628543416, 'samples': 11250176, 'steps': 21972, 'loss/train': 1.3408609628677368}
-03/04/2022 15:16:32 - INFO - codeparrot_training - Step 21973: {'lr': 0.00047786610325396096, 'samples': 11250688, 'steps': 21973, 'loss/train': 1.411632776260376}
-03/04/2022 15:16:33 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/04/2022 15:16:38 - INFO - codeparrot_training - Step 21974: {'lr': 0.0004778639201198149, 'samples': 11251200, 'steps': 21974, 'loss/train': 1.6963574886322021}
-03/04/2022 15:16:41 - INFO - codeparrot_training - Step 21975: {'lr': 0.00047786173688299684, 'samples': 11251712, 'steps': 21975, 'loss/train': 1.9533493518829346}
-03/04/2022 15:16:41 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/04/2022 15:16:46 - INFO - codeparrot_training - Step 21976: {'lr': 0.00047785955354350776, 'samples': 11252224, 'steps': 21976, 'loss/train': 1.78054678440094}
-03/04/2022 15:16:49 - INFO - codeparrot_training - Step 21977: {'lr': 0.00047785737010134865, 'samples': 11252736, 'steps': 21977, 'loss/train': 1.3489006757736206}
-03/04/2022 15:16:49 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/04/2022 15:16:54 - INFO - codeparrot_training - Step 21978: {'lr': 0.0004778551865565206, 'samples': 11253248, 'steps': 21978, 'loss/train': 1.6467453241348267}
-03/04/2022 15:16:58 - INFO - codeparrot_training - Step 21979: {'lr': 0.00047785300290902446, 'samples': 11253760, 'steps': 21979, 'loss/train': 2.0208308696746826}
-03/04/2022 15:16:58 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/04/2022 15:17:03 - INFO - codeparrot_training - Step 21980: {'lr': 0.0004778508191588613, 'samples': 11254272, 'steps': 21980, 'loss/train': 2.4197616577148438}
-03/04/2022 15:17:06 - INFO - codeparrot_training - Step 21981: {'lr': 0.00047784863530603213, 'samples': 11254784, 'steps': 21981, 'loss/train': 1.2553106546401978}
-03/04/2022 15:17:06 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 15:17:11 - INFO - codeparrot_training - Step 21982: {'lr': 0.0004778464513505378, 'samples': 11255296, 'steps': 21982, 'loss/train': 2.1986725330352783}
-03/04/2022 15:17:14 - INFO - codeparrot_training - Step 21983: {'lr': 0.0004778442672923794, 'samples': 11255808, 'steps': 21983, 'loss/train': 1.7437392473220825}
-03/04/2022 15:17:15 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 15:17:20 - INFO - codeparrot_training - Step 21984: {'lr': 0.0004778420831315579, 'samples': 11256320, 'steps': 21984, 'loss/train': 2.50854229927063}
-03/04/2022 15:17:23 - INFO - codeparrot_training - Step 21985: {'lr': 0.0004778398988680743, 'samples': 11256832, 'steps': 21985, 'loss/train': 1.6756504774093628}
-03/04/2022 15:17:23 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 15:17:28 - INFO - codeparrot_training - Step 21986: {'lr': 0.00047783771450192946, 'samples': 11257344, 'steps': 21986, 'loss/train': 2.267674684524536}
-03/04/2022 15:17:31 - INFO - codeparrot_training - Step 21987: {'lr': 0.00047783553003312456, 'samples': 11257856, 'steps': 21987, 'loss/train': 2.1100542545318604}
-03/04/2022 15:17:31 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 15:17:37 - INFO - codeparrot_training - Step 21988: {'lr': 0.00047783334546166046, 'samples': 11258368, 'steps': 21988, 'loss/train': 2.270996332168579}
-03/04/2022 15:17:40 - INFO - codeparrot_training - Step 21989: {'lr': 0.0004778311607875382, 'samples': 11258880, 'steps': 21989, 'loss/train': 2.2060697078704834}
-03/04/2022 15:17:40 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/04/2022 15:17:45 - INFO - codeparrot_training - Step 21990: {'lr': 0.0004778289760107587, 'samples': 11259392, 'steps': 21990, 'loss/train': 1.3154963254928589}
-03/04/2022 15:17:48 - INFO - codeparrot_training - Step 21991: {'lr': 0.00047782679113132293, 'samples': 11259904, 'steps': 21991, 'loss/train': 1.5757817029953003}
-03/04/2022 15:17:49 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 15:17:54 - INFO - codeparrot_training - Step 21992: {'lr': 0.00047782460614923195, 'samples': 11260416, 'steps': 21992, 'loss/train': 2.063816547393799}
-03/04/2022 15:17:57 - INFO - codeparrot_training - Step 21993: {'lr': 0.00047782242106448675, 'samples': 11260928, 'steps': 21993, 'loss/train': 1.6355797052383423}
-03/04/2022 15:18:00 - INFO - codeparrot_training - Step 21994: {'lr': 0.00047782023587708826, 'samples': 11261440, 'steps': 21994, 'loss/train': 2.315589666366577}
-03/04/2022 15:18:00 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 15:18:06 - INFO - codeparrot_training - Step 21995: {'lr': 0.0004778180505870375, 'samples': 11261952, 'steps': 21995, 'loss/train': 1.960210919380188}
-03/04/2022 15:18:09 - INFO - codeparrot_training - Step 21996: {'lr': 0.0004778158651943355, 'samples': 11262464, 'steps': 21996, 'loss/train': 2.1770856380462646}
-03/04/2022 15:18:09 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/04/2022 15:18:14 - INFO - codeparrot_training - Step 21997: {'lr': 0.0004778136796989831, 'samples': 11262976, 'steps': 21997, 'loss/train': 1.9209784269332886}
-03/04/2022 15:18:17 - INFO - codeparrot_training - Step 21998: {'lr': 0.0004778114941009814, 'samples': 11263488, 'steps': 21998, 'loss/train': 1.9639023542404175}
-03/04/2022 15:18:17 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/04/2022 15:18:22 - INFO - codeparrot_training - Step 21999: {'lr': 0.0004778093084003313, 'samples': 11264000, 'steps': 21999, 'loss/train': 1.5556331872940063}
-03/04/2022 15:18:26 - INFO - codeparrot_training - Step 22000: {'lr': 0.00047780712259703394, 'samples': 11264512, 'steps': 22000, 'loss/train': 1.489432454109192}
-03/04/2022 15:18:26 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 15:18:31 - INFO - codeparrot_training - Step 22001: {'lr': 0.00047780493669109017, 'samples': 11265024, 'steps': 22001, 'loss/train': 2.092963933944702}
-03/04/2022 15:18:34 - INFO - codeparrot_training - Step 22002: {'lr': 0.000477802750682501, 'samples': 11265536, 'steps': 22002, 'loss/train': 1.696277379989624}
-03/04/2022 15:18:34 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 15:18:40 - INFO - codeparrot_training - Step 22003: {'lr': 0.0004778005645712674, 'samples': 11266048, 'steps': 22003, 'loss/train': 2.6606054306030273}
-03/04/2022 15:18:43 - INFO - codeparrot_training - Step 22004: {'lr': 0.00047779837835739043, 'samples': 11266560, 'steps': 22004, 'loss/train': 0.653022050857544}
-03/04/2022 15:18:43 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 15:18:48 - INFO - codeparrot_training - Step 22005: {'lr': 0.000477796192040871, 'samples': 11267072, 'steps': 22005, 'loss/train': 1.668879747390747}
-03/04/2022 15:18:51 - INFO - codeparrot_training - Step 22006: {'lr': 0.00047779400562171016, 'samples': 11267584, 'steps': 22006, 'loss/train': 1.1293333768844604}
-03/04/2022 15:18:51 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/04/2022 15:18:57 - INFO - codeparrot_training - Step 22007: {'lr': 0.00047779181909990876, 'samples': 11268096, 'steps': 22007, 'loss/train': 2.0693626403808594}
-03/04/2022 15:19:00 - INFO - codeparrot_training - Step 22008: {'lr': 0.000477789632475468, 'samples': 11268608, 'steps': 22008, 'loss/train': 1.37947416305542}
-03/04/2022 15:19:00 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 15:19:05 - INFO - codeparrot_training - Step 22009: {'lr': 0.00047778744574838864, 'samples': 11269120, 'steps': 22009, 'loss/train': 1.8734935522079468}
-03/04/2022 15:19:08 - INFO - codeparrot_training - Step 22010: {'lr': 0.00047778525891867187, 'samples': 11269632, 'steps': 22010, 'loss/train': 1.6540238857269287}
-03/04/2022 15:19:08 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/04/2022 15:19:13 - INFO - codeparrot_training - Step 22011: {'lr': 0.00047778307198631856, 'samples': 11270144, 'steps': 22011, 'loss/train': 1.8097188472747803}
-03/04/2022 15:19:16 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/04/2022 15:19:19 - INFO - codeparrot_training - Step 22012: {'lr': 0.00047778088495132963, 'samples': 11270656, 'steps': 22012, 'loss/train': 1.5720757246017456}
-03/04/2022 15:19:22 - INFO - codeparrot_training - Step 22013: {'lr': 0.0004777786978137062, 'samples': 11271168, 'steps': 22013, 'loss/train': 1.8225023746490479}
-03/04/2022 15:19:25 - INFO - codeparrot_training - Step 22014: {'lr': 0.00047777651057344915, 'samples': 11271680, 'steps': 22014, 'loss/train': 1.7627143859863281}
-03/04/2022 15:19:27 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/04/2022 15:19:31 - INFO - codeparrot_training - Step 22015: {'lr': 0.0004777743232305596, 'samples': 11272192, 'steps': 22015, 'loss/train': 1.4306069612503052}
-03/04/2022 15:19:34 - INFO - codeparrot_training - Step 22016: {'lr': 0.00047777213578503844, 'samples': 11272704, 'steps': 22016, 'loss/train': 1.5909779071807861}
-03/04/2022 15:19:36 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/04/2022 15:19:39 - INFO - codeparrot_training - Step 22017: {'lr': 0.0004777699482368867, 'samples': 11273216, 'steps': 22017, 'loss/train': 0.946075439453125}
-03/04/2022 15:19:42 - INFO - codeparrot_training - Step 22018: {'lr': 0.00047776776058610525, 'samples': 11273728, 'steps': 22018, 'loss/train': 1.881159782409668}
-03/04/2022 15:19:44 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/04/2022 15:19:48 - INFO - codeparrot_training - Step 22019: {'lr': 0.0004777655728326952, 'samples': 11274240, 'steps': 22019, 'loss/train': 1.3619402647018433}
-03/04/2022 15:19:51 - INFO - codeparrot_training - Step 22020: {'lr': 0.0004777633849766575, 'samples': 11274752, 'steps': 22020, 'loss/train': 1.4718782901763916}
-03/04/2022 15:19:52 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/04/2022 15:19:56 - INFO - codeparrot_training - Step 22021: {'lr': 0.00047776119701799317, 'samples': 11275264, 'steps': 22021, 'loss/train': 1.8714056015014648}
-03/04/2022 15:19:59 - INFO - codeparrot_training - Step 22022: {'lr': 0.0004777590089567031, 'samples': 11275776, 'steps': 22022, 'loss/train': 1.5571768283843994}
-03/04/2022 15:20:01 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/04/2022 15:20:05 - INFO - codeparrot_training - Step 22023: {'lr': 0.00047775682079278836, 'samples': 11276288, 'steps': 22023, 'loss/train': 1.7106083631515503}
-03/04/2022 15:20:08 - INFO - codeparrot_training - Step 22024: {'lr': 0.0004777546325262499, 'samples': 11276800, 'steps': 22024, 'loss/train': 2.4517662525177}
-03/04/2022 15:20:09 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 15:20:13 - INFO - codeparrot_training - Step 22025: {'lr': 0.00047775244415708873, 'samples': 11277312, 'steps': 22025, 'loss/train': 1.987546443939209}
-03/04/2022 15:20:16 - INFO - codeparrot_training - Step 22026: {'lr': 0.0004777502556853058, 'samples': 11277824, 'steps': 22026, 'loss/train': 2.0129141807556152}
-03/04/2022 15:20:18 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/04/2022 15:20:22 - INFO - codeparrot_training - Step 22027: {'lr': 0.00047774806711090213, 'samples': 11278336, 'steps': 22027, 'loss/train': 2.078073024749756}
-03/04/2022 15:20:25 - INFO - codeparrot_training - Step 22028: {'lr': 0.0004777458784338787, 'samples': 11278848, 'steps': 22028, 'loss/train': 1.2995330095291138}
-03/04/2022 15:20:27 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 15:20:30 - INFO - codeparrot_training - Step 22029: {'lr': 0.00047774368965423653, 'samples': 11279360, 'steps': 22029, 'loss/train': 2.0523064136505127}
-03/04/2022 15:20:33 - INFO - codeparrot_training - Step 22030: {'lr': 0.0004777415007719765, 'samples': 11279872, 'steps': 22030, 'loss/train': 1.2059636116027832}
-03/04/2022 15:20:35 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/04/2022 15:20:38 - INFO - codeparrot_training - Step 22031: {'lr': 0.00047773931178709975, 'samples': 11280384, 'steps': 22031, 'loss/train': 2.255063533782959}
-03/04/2022 15:20:42 - INFO - codeparrot_training - Step 22032: {'lr': 0.00047773712269960714, 'samples': 11280896, 'steps': 22032, 'loss/train': 0.68230140209198}
-03/04/2022 15:20:43 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 15:20:47 - INFO - codeparrot_training - Step 22033: {'lr': 0.00047773493350949963, 'samples': 11281408, 'steps': 22033, 'loss/train': 1.1164714097976685}
-03/04/2022 15:20:50 - INFO - codeparrot_training - Step 22034: {'lr': 0.00047773274421677834, 'samples': 11281920, 'steps': 22034, 'loss/train': 2.594212532043457}
-03/04/2022 15:20:51 - INFO - codeparrot_training - Skipping example with length 996 (seq_length=1024)
-03/04/2022 15:20:55 - INFO - codeparrot_training - Step 22035: {'lr': 0.0004777305548214442, 'samples': 11282432, 'steps': 22035, 'loss/train': 1.8005529642105103}
-03/04/2022 15:20:58 - INFO - codeparrot_training - Step 22036: {'lr': 0.0004777283653234982, 'samples': 11282944, 'steps': 22036, 'loss/train': 1.9482887983322144}
-03/04/2022 15:21:00 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/04/2022 15:21:04 - INFO - codeparrot_training - Step 22037: {'lr': 0.00047772617572294123, 'samples': 11283456, 'steps': 22037, 'loss/train': 2.0005550384521484}
-03/04/2022 15:21:07 - INFO - codeparrot_training - Step 22038: {'lr': 0.0004777239860197744, 'samples': 11283968, 'steps': 22038, 'loss/train': 1.4353426694869995}
-03/04/2022 15:21:08 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 15:21:12 - INFO - codeparrot_training - Step 22039: {'lr': 0.0004777217962139987, 'samples': 11284480, 'steps': 22039, 'loss/train': 2.328906297683716}
-03/04/2022 15:21:15 - INFO - codeparrot_training - Step 22040: {'lr': 0.000477719606305615, 'samples': 11284992, 'steps': 22040, 'loss/train': 1.821467638015747}
-03/04/2022 15:21:16 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/04/2022 15:21:21 - INFO - codeparrot_training - Step 22041: {'lr': 0.0004777174162946244, 'samples': 11285504, 'steps': 22041, 'loss/train': 2.6764228343963623}
-03/04/2022 15:21:24 - INFO - codeparrot_training - Step 22042: {'lr': 0.0004777152261810279, 'samples': 11286016, 'steps': 22042, 'loss/train': 2.2285783290863037}
-03/04/2022 15:21:27 - INFO - codeparrot_training - Step 22043: {'lr': 0.0004777130359648263, 'samples': 11286528, 'steps': 22043, 'loss/train': 2.2540347576141357}
-03/04/2022 15:21:27 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 15:21:33 - INFO - codeparrot_training - Step 22044: {'lr': 0.0004777108456460208, 'samples': 11287040, 'steps': 22044, 'loss/train': 1.9135873317718506}
-03/04/2022 15:21:36 - INFO - codeparrot_training - Step 22045: {'lr': 0.00047770865522461233, 'samples': 11287552, 'steps': 22045, 'loss/train': 1.4600987434387207}
-03/04/2022 15:21:36 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/04/2022 15:21:41 - INFO - codeparrot_training - Step 22046: {'lr': 0.0004777064647006018, 'samples': 11288064, 'steps': 22046, 'loss/train': 2.368587017059326}
-03/04/2022 15:21:44 - INFO - codeparrot_training - Step 22047: {'lr': 0.0004777042740739903, 'samples': 11288576, 'steps': 22047, 'loss/train': 1.941925048828125}
-03/04/2022 15:21:44 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/04/2022 15:21:49 - INFO - codeparrot_training - Step 22048: {'lr': 0.0004777020833447787, 'samples': 11289088, 'steps': 22048, 'loss/train': 1.3183236122131348}
-03/04/2022 15:21:53 - INFO - codeparrot_training - Step 22049: {'lr': 0.0004776998925129681, 'samples': 11289600, 'steps': 22049, 'loss/train': 1.8844407796859741}
-03/04/2022 15:21:53 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 15:21:58 - INFO - codeparrot_training - Step 22050: {'lr': 0.0004776977015785595, 'samples': 11290112, 'steps': 22050, 'loss/train': 0.652808427810669}
-03/04/2022 15:22:01 - INFO - codeparrot_training - Step 22051: {'lr': 0.0004776955105415537, 'samples': 11290624, 'steps': 22051, 'loss/train': 2.3172860145568848}
-03/04/2022 15:22:01 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 15:22:06 - INFO - codeparrot_training - Step 22052: {'lr': 0.00047769331940195194, 'samples': 11291136, 'steps': 22052, 'loss/train': 2.280590057373047}
-03/04/2022 15:22:09 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/04/2022 15:22:12 - INFO - codeparrot_training - Step 22053: {'lr': 0.00047769112815975503, 'samples': 11291648, 'steps': 22053, 'loss/train': 2.7132418155670166}
-03/04/2022 15:22:15 - INFO - codeparrot_training - Step 22054: {'lr': 0.00047768893681496397, 'samples': 11292160, 'steps': 22054, 'loss/train': 1.6149077415466309}
-03/04/2022 15:22:18 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/04/2022 15:22:20 - INFO - codeparrot_training - Step 22055: {'lr': 0.00047768674536757984, 'samples': 11292672, 'steps': 22055, 'loss/train': 1.3395129442214966}
-03/04/2022 15:22:23 - INFO - codeparrot_training - Step 22056: {'lr': 0.00047768455381760357, 'samples': 11293184, 'steps': 22056, 'loss/train': 1.3069261312484741}
-03/04/2022 15:22:26 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/04/2022 15:22:28 - INFO - codeparrot_training - Step 22057: {'lr': 0.00047768236216503613, 'samples': 11293696, 'steps': 22057, 'loss/train': 1.9505176544189453}
-03/04/2022 15:22:32 - INFO - codeparrot_training - Step 22058: {'lr': 0.00047768017040987856, 'samples': 11294208, 'steps': 22058, 'loss/train': 3.4990997314453125}
-03/04/2022 15:22:34 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/04/2022 15:22:37 - INFO - codeparrot_training - Step 22059: {'lr': 0.0004776779785521318, 'samples': 11294720, 'steps': 22059, 'loss/train': 1.1544699668884277}
-03/04/2022 15:22:40 - INFO - codeparrot_training - Step 22060: {'lr': 0.0004776757865917969, 'samples': 11295232, 'steps': 22060, 'loss/train': 0.9072554111480713}
-03/04/2022 15:22:42 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 15:22:45 - INFO - codeparrot_training - Step 22061: {'lr': 0.0004776735945288747, 'samples': 11295744, 'steps': 22061, 'loss/train': 2.2614681720733643}
-03/04/2022 15:22:49 - INFO - codeparrot_training - Step 22062: {'lr': 0.00047767140236336635, 'samples': 11296256, 'steps': 22062, 'loss/train': 2.565476179122925}
-03/04/2022 15:22:51 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/04/2022 15:22:54 - INFO - codeparrot_training - Step 22063: {'lr': 0.00047766921009527284, 'samples': 11296768, 'steps': 22063, 'loss/train': 2.4209182262420654}
-03/04/2022 15:22:57 - INFO - codeparrot_training - Step 22064: {'lr': 0.00047766701772459505, 'samples': 11297280, 'steps': 22064, 'loss/train': 1.689549207687378}
-03/04/2022 15:22:59 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 15:23:02 - INFO - codeparrot_training - Step 22065: {'lr': 0.00047766482525133405, 'samples': 11297792, 'steps': 22065, 'loss/train': 1.6977654695510864}
-03/04/2022 15:23:06 - INFO - codeparrot_training - Step 22066: {'lr': 0.00047766263267549073, 'samples': 11298304, 'steps': 22066, 'loss/train': 2.003960609436035}
-03/04/2022 15:23:08 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 15:23:11 - INFO - codeparrot_training - Step 22067: {'lr': 0.0004776604399970661, 'samples': 11298816, 'steps': 22067, 'loss/train': 2.128910779953003}
-03/04/2022 15:23:14 - INFO - codeparrot_training - Step 22068: {'lr': 0.0004776582472160613, 'samples': 11299328, 'steps': 22068, 'loss/train': 1.5377613306045532}
-03/04/2022 15:23:16 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 15:23:19 - INFO - codeparrot_training - Step 22069: {'lr': 0.0004776560543324772, 'samples': 11299840, 'steps': 22069, 'loss/train': 3.7584848403930664}
-03/04/2022 15:23:22 - INFO - codeparrot_training - Step 22070: {'lr': 0.0004776538613463147, 'samples': 11300352, 'steps': 22070, 'loss/train': 0.5112701058387756}
-03/04/2022 15:23:24 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 15:23:28 - INFO - codeparrot_training - Step 22071: {'lr': 0.00047765166825757487, 'samples': 11300864, 'steps': 22071, 'loss/train': 1.6936335563659668}
-03/04/2022 15:23:31 - INFO - codeparrot_training - Step 22072: {'lr': 0.00047764947506625887, 'samples': 11301376, 'steps': 22072, 'loss/train': 1.8575464487075806}
-03/04/2022 15:23:33 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 15:23:36 - INFO - codeparrot_training - Step 22073: {'lr': 0.00047764728177236736, 'samples': 11301888, 'steps': 22073, 'loss/train': 2.0432019233703613}
-03/04/2022 15:23:39 - INFO - codeparrot_training - Step 22074: {'lr': 0.0004776450883759016, 'samples': 11302400, 'steps': 22074, 'loss/train': 1.9877384901046753}
-03/04/2022 15:23:41 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/04/2022 15:23:45 - INFO - codeparrot_training - Step 22075: {'lr': 0.0004776428948768625, 'samples': 11302912, 'steps': 22075, 'loss/train': 2.1814913749694824}
-03/04/2022 15:23:48 - INFO - codeparrot_training - Step 22076: {'lr': 0.00047764070127525096, 'samples': 11303424, 'steps': 22076, 'loss/train': 1.649192214012146}
-03/04/2022 15:23:50 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/04/2022 15:23:53 - INFO - codeparrot_training - Step 22077: {'lr': 0.00047763850757106803, 'samples': 11303936, 'steps': 22077, 'loss/train': 1.643643856048584}
-03/04/2022 15:23:56 - INFO - codeparrot_training - Step 22078: {'lr': 0.0004776363137643147, 'samples': 11304448, 'steps': 22078, 'loss/train': 1.4457054138183594}
-03/04/2022 15:23:59 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/04/2022 15:24:02 - INFO - codeparrot_training - Step 22079: {'lr': 0.000477634119854992, 'samples': 11304960, 'steps': 22079, 'loss/train': 0.4887719750404358}
-03/04/2022 15:24:05 - INFO - codeparrot_training - Step 22080: {'lr': 0.00047763192584310087, 'samples': 11305472, 'steps': 22080, 'loss/train': 2.061272144317627}
-03/04/2022 15:24:09 - INFO - codeparrot_training - Step 22081: {'lr': 0.0004776297317286423, 'samples': 11305984, 'steps': 22081, 'loss/train': 2.3910043239593506}
-03/04/2022 15:24:10 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/04/2022 15:24:14 - INFO - codeparrot_training - Step 22082: {'lr': 0.00047762753751161725, 'samples': 11306496, 'steps': 22082, 'loss/train': 2.178981065750122}
-03/04/2022 15:24:17 - INFO - codeparrot_training - Step 22083: {'lr': 0.0004776253431920268, 'samples': 11307008, 'steps': 22083, 'loss/train': 2.106750249862671}
-03/04/2022 15:24:21 - INFO - codeparrot_training - Step 22084: {'lr': 0.00047762314876987185, 'samples': 11307520, 'steps': 22084, 'loss/train': 1.6975114345550537}
-03/04/2022 15:24:21 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/04/2022 15:24:26 - INFO - codeparrot_training - Step 22085: {'lr': 0.0004776209542451534, 'samples': 11308032, 'steps': 22085, 'loss/train': 1.9828957319259644}
-03/04/2022 15:24:29 - INFO - codeparrot_training - Step 22086: {'lr': 0.0004776187596178725, 'samples': 11308544, 'steps': 22086, 'loss/train': 2.6098997592926025}
-03/04/2022 15:24:29 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/04/2022 15:24:34 - INFO - codeparrot_training - Step 22087: {'lr': 0.00047761656488803006, 'samples': 11309056, 'steps': 22087, 'loss/train': 1.83033287525177}
-03/04/2022 15:24:38 - INFO - codeparrot_training - Step 22088: {'lr': 0.00047761437005562716, 'samples': 11309568, 'steps': 22088, 'loss/train': 1.8869757652282715}
-03/04/2022 15:24:38 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/04/2022 15:24:43 - INFO - codeparrot_training - Step 22089: {'lr': 0.00047761217512066475, 'samples': 11310080, 'steps': 22089, 'loss/train': 1.8974472284317017}
-03/04/2022 15:24:46 - INFO - codeparrot_training - Step 22090: {'lr': 0.0004776099800831437, 'samples': 11310592, 'steps': 22090, 'loss/train': 1.6315171718597412}
-03/04/2022 15:24:46 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/04/2022 15:24:51 - INFO - codeparrot_training - Step 22091: {'lr': 0.0004776077849430652, 'samples': 11311104, 'steps': 22091, 'loss/train': 2.0767128467559814}
-03/04/2022 15:24:54 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 15:24:56 - INFO - codeparrot_training - Step 22092: {'lr': 0.0004776055897004301, 'samples': 11311616, 'steps': 22092, 'loss/train': 1.8744815587997437}
-03/04/2022 15:25:00 - INFO - codeparrot_training - Step 22093: {'lr': 0.0004776033943552395, 'samples': 11312128, 'steps': 22093, 'loss/train': 0.7583313584327698}
-03/04/2022 15:25:02 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/04/2022 15:25:05 - INFO - codeparrot_training - Step 22094: {'lr': 0.0004776011989074943, 'samples': 11312640, 'steps': 22094, 'loss/train': 1.9622167348861694}
-03/04/2022 15:25:08 - INFO - codeparrot_training - Step 22095: {'lr': 0.00047759900335719543, 'samples': 11313152, 'steps': 22095, 'loss/train': 2.2771923542022705}
-03/04/2022 15:25:11 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/04/2022 15:25:13 - INFO - codeparrot_training - Step 22096: {'lr': 0.00047759680770434405, 'samples': 11313664, 'steps': 22096, 'loss/train': 2.0840837955474854}
-03/04/2022 15:25:16 - INFO - codeparrot_training - Step 22097: {'lr': 0.00047759461194894103, 'samples': 11314176, 'steps': 22097, 'loss/train': 1.9387022256851196}
-03/04/2022 15:25:19 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 15:25:22 - INFO - codeparrot_training - Step 22098: {'lr': 0.00047759241609098734, 'samples': 11314688, 'steps': 22098, 'loss/train': 1.8203294277191162}
-03/04/2022 15:25:25 - INFO - codeparrot_training - Step 22099: {'lr': 0.00047759022013048417, 'samples': 11315200, 'steps': 22099, 'loss/train': 1.6407618522644043}
-03/04/2022 15:25:28 - INFO - codeparrot_training - Step 22100: {'lr': 0.00047758802406743217, 'samples': 11315712, 'steps': 22100, 'loss/train': 1.1392550468444824}
-03/04/2022 15:25:28 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 15:25:33 - INFO - codeparrot_training - Step 22101: {'lr': 0.0004775858279018326, 'samples': 11316224, 'steps': 22101, 'loss/train': 1.2836378812789917}
-03/04/2022 15:25:37 - INFO - codeparrot_training - Step 22102: {'lr': 0.0004775836316336864, 'samples': 11316736, 'steps': 22102, 'loss/train': 1.9055947065353394}
-03/04/2022 15:25:37 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 15:25:42 - INFO - codeparrot_training - Step 22103: {'lr': 0.00047758143526299446, 'samples': 11317248, 'steps': 22103, 'loss/train': 1.8054033517837524}
-03/04/2022 15:25:45 - INFO - codeparrot_training - Step 22104: {'lr': 0.0004775792387897579, 'samples': 11317760, 'steps': 22104, 'loss/train': 2.1396689414978027}
-03/04/2022 15:25:45 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 15:25:50 - INFO - codeparrot_training - Step 22105: {'lr': 0.0004775770422139776, 'samples': 11318272, 'steps': 22105, 'loss/train': 2.4275412559509277}
-03/04/2022 15:25:54 - INFO - codeparrot_training - Step 22106: {'lr': 0.00047757484553565465, 'samples': 11318784, 'steps': 22106, 'loss/train': 1.9097182750701904}
-03/04/2022 15:25:54 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/04/2022 15:25:59 - INFO - codeparrot_training - Step 22107: {'lr': 0.00047757264875478996, 'samples': 11319296, 'steps': 22107, 'loss/train': 2.1254944801330566}
-03/04/2022 15:26:02 - INFO - codeparrot_training - Step 22108: {'lr': 0.0004775704518713845, 'samples': 11319808, 'steps': 22108, 'loss/train': 1.6625523567199707}
-03/04/2022 15:26:02 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/04/2022 15:26:07 - INFO - codeparrot_training - Step 22109: {'lr': 0.0004775682548854394, 'samples': 11320320, 'steps': 22109, 'loss/train': 1.638593316078186}
-03/04/2022 15:26:10 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/04/2022 15:26:12 - INFO - codeparrot_training - Step 22110: {'lr': 0.0004775660577969555, 'samples': 11320832, 'steps': 22110, 'loss/train': 1.3889845609664917}
-03/04/2022 15:26:16 - INFO - codeparrot_training - Step 22111: {'lr': 0.0004775638606059338, 'samples': 11321344, 'steps': 22111, 'loss/train': 1.2430495023727417}
-03/04/2022 15:26:18 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/04/2022 15:26:21 - INFO - codeparrot_training - Step 22112: {'lr': 0.00047756166331237545, 'samples': 11321856, 'steps': 22112, 'loss/train': 2.8328857421875}
-03/04/2022 15:26:24 - INFO - codeparrot_training - Step 22113: {'lr': 0.00047755946591628126, 'samples': 11322368, 'steps': 22113, 'loss/train': 1.9316152334213257}
-03/04/2022 15:26:27 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/04/2022 15:26:29 - INFO - codeparrot_training - Step 22114: {'lr': 0.00047755726841765224, 'samples': 11322880, 'steps': 22114, 'loss/train': 3.223008155822754}
-03/04/2022 15:26:33 - INFO - codeparrot_training - Step 22115: {'lr': 0.0004775550708164895, 'samples': 11323392, 'steps': 22115, 'loss/train': 1.8795032501220703}
-03/04/2022 15:26:36 - INFO - codeparrot_training - Step 22116: {'lr': 0.00047755287311279394, 'samples': 11323904, 'steps': 22116, 'loss/train': 1.7812528610229492}
-03/04/2022 15:26:36 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/04/2022 15:26:41 - INFO - codeparrot_training - Step 22117: {'lr': 0.00047755067530656656, 'samples': 11324416, 'steps': 22117, 'loss/train': 1.8688631057739258}
-03/04/2022 15:26:44 - INFO - codeparrot_training - Step 22118: {'lr': 0.00047754847739780835, 'samples': 11324928, 'steps': 22118, 'loss/train': 1.6323686838150024}
-03/04/2022 15:26:44 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 15:26:49 - INFO - codeparrot_training - Step 22119: {'lr': 0.0004775462793865203, 'samples': 11325440, 'steps': 22119, 'loss/train': 1.9232386350631714}
-03/04/2022 15:26:53 - INFO - codeparrot_training - Step 22120: {'lr': 0.00047754408127270346, 'samples': 11325952, 'steps': 22120, 'loss/train': 2.177112102508545}
-03/04/2022 15:26:53 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/04/2022 15:26:58 - INFO - codeparrot_training - Step 22121: {'lr': 0.0004775418830563587, 'samples': 11326464, 'steps': 22121, 'loss/train': 1.774481177330017}
-03/04/2022 15:27:01 - INFO - codeparrot_training - Step 22122: {'lr': 0.0004775396847374871, 'samples': 11326976, 'steps': 22122, 'loss/train': 2.301882743835449}
-03/04/2022 15:27:02 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/04/2022 15:27:07 - INFO - codeparrot_training - Step 22123: {'lr': 0.0004775374863160896, 'samples': 11327488, 'steps': 22123, 'loss/train': 2.515514612197876}
-03/04/2022 15:27:10 - INFO - codeparrot_training - Step 22124: {'lr': 0.0004775352877921673, 'samples': 11328000, 'steps': 22124, 'loss/train': 2.440469264984131}
-03/04/2022 15:27:11 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/04/2022 15:27:15 - INFO - codeparrot_training - Step 22125: {'lr': 0.000477533089165721, 'samples': 11328512, 'steps': 22125, 'loss/train': 1.8881285190582275}
-03/04/2022 15:27:19 - INFO - codeparrot_training - Step 22126: {'lr': 0.0004775308904367519, 'samples': 11329024, 'steps': 22126, 'loss/train': 1.1306160688400269}
-03/04/2022 15:27:21 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/04/2022 15:27:24 - INFO - codeparrot_training - Step 22127: {'lr': 0.0004775286916052609, 'samples': 11329536, 'steps': 22127, 'loss/train': 1.890255331993103}
-03/04/2022 15:27:27 - INFO - codeparrot_training - Step 22128: {'lr': 0.00047752649267124894, 'samples': 11330048, 'steps': 22128, 'loss/train': 0.8676541447639465}
-03/04/2022 15:27:30 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/04/2022 15:27:32 - INFO - codeparrot_training - Step 22129: {'lr': 0.0004775242936347171, 'samples': 11330560, 'steps': 22129, 'loss/train': 2.0903730392456055}
-03/04/2022 15:27:36 - INFO - codeparrot_training - Step 22130: {'lr': 0.0004775220944956662, 'samples': 11331072, 'steps': 22130, 'loss/train': 1.5051261186599731}
-03/04/2022 15:27:38 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 15:27:41 - INFO - codeparrot_training - Step 22131: {'lr': 0.00047751989525409745, 'samples': 11331584, 'steps': 22131, 'loss/train': 1.2066582441329956}
-03/04/2022 15:27:44 - INFO - codeparrot_training - Step 22132: {'lr': 0.0004775176959100117, 'samples': 11332096, 'steps': 22132, 'loss/train': 1.9609605073928833}
-03/04/2022 15:27:47 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 15:27:49 - INFO - codeparrot_training - Step 22133: {'lr': 0.00047751549646341007, 'samples': 11332608, 'steps': 22133, 'loss/train': 1.881510853767395}
-03/04/2022 15:27:53 - INFO - codeparrot_training - Step 22134: {'lr': 0.0004775132969142934, 'samples': 11333120, 'steps': 22134, 'loss/train': 1.3929623365402222}
-03/04/2022 15:27:55 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/04/2022 15:27:58 - INFO - codeparrot_training - Step 22135: {'lr': 0.00047751109726266273, 'samples': 11333632, 'steps': 22135, 'loss/train': 1.5073732137680054}
-03/04/2022 15:28:01 - INFO - codeparrot_training - Step 22136: {'lr': 0.00047750889750851913, 'samples': 11334144, 'steps': 22136, 'loss/train': 2.3854384422302246}
-03/04/2022 15:28:04 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/04/2022 15:28:06 - INFO - codeparrot_training - Step 22137: {'lr': 0.0004775066976518635, 'samples': 11334656, 'steps': 22137, 'loss/train': 1.7985275983810425}
-03/04/2022 15:28:09 - INFO - codeparrot_training - Step 22138: {'lr': 0.00047750449769269686, 'samples': 11335168, 'steps': 22138, 'loss/train': 2.312749147415161}
-03/04/2022 15:28:12 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/04/2022 15:28:15 - INFO - codeparrot_training - Step 22139: {'lr': 0.0004775022976310203, 'samples': 11335680, 'steps': 22139, 'loss/train': 1.6366263628005981}
-03/04/2022 15:28:18 - INFO - codeparrot_training - Step 22140: {'lr': 0.0004775000974668345, 'samples': 11336192, 'steps': 22140, 'loss/train': 2.004296064376831}
-03/04/2022 15:28:21 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 15:28:23 - INFO - codeparrot_training - Step 22141: {'lr': 0.00047749789720014085, 'samples': 11336704, 'steps': 22141, 'loss/train': 1.2976937294006348}
-03/04/2022 15:28:27 - INFO - codeparrot_training - Step 22142: {'lr': 0.00047749569683094015, 'samples': 11337216, 'steps': 22142, 'loss/train': 1.2908931970596313}
-03/04/2022 15:28:30 - INFO - codeparrot_training - Step 22143: {'lr': 0.00047749349635923334, 'samples': 11337728, 'steps': 22143, 'loss/train': 2.150090217590332}
-03/04/2022 15:28:30 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/04/2022 15:28:35 - INFO - codeparrot_training - Step 22144: {'lr': 0.0004774912957850215, 'samples': 11338240, 'steps': 22144, 'loss/train': 2.138568878173828}
-03/04/2022 15:28:38 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 15:28:40 - INFO - codeparrot_training - Step 22145: {'lr': 0.0004774890951083055, 'samples': 11338752, 'steps': 22145, 'loss/train': 2.0056004524230957}
-03/04/2022 15:28:43 - INFO - codeparrot_training - Step 22146: {'lr': 0.00047748689432908654, 'samples': 11339264, 'steps': 22146, 'loss/train': 2.105956792831421}
-03/04/2022 15:28:46 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 15:28:49 - INFO - codeparrot_training - Step 22147: {'lr': 0.00047748469344736547, 'samples': 11339776, 'steps': 22147, 'loss/train': 1.8261003494262695}
-03/04/2022 15:28:52 - INFO - codeparrot_training - Step 22148: {'lr': 0.00047748249246314323, 'samples': 11340288, 'steps': 22148, 'loss/train': 1.7923105955123901}
-03/04/2022 15:28:55 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 15:28:57 - INFO - codeparrot_training - Step 22149: {'lr': 0.000477480291376421, 'samples': 11340800, 'steps': 22149, 'loss/train': 1.5919932126998901}
-03/04/2022 15:29:00 - INFO - codeparrot_training - Step 22150: {'lr': 0.0004774780901871996, 'samples': 11341312, 'steps': 22150, 'loss/train': 1.6192091703414917}
-03/04/2022 15:29:03 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/04/2022 15:29:06 - INFO - codeparrot_training - Step 22151: {'lr': 0.0004774758888954801, 'samples': 11341824, 'steps': 22151, 'loss/train': 2.214567184448242}
-03/04/2022 15:29:09 - INFO - codeparrot_training - Step 22152: {'lr': 0.00047747368750126345, 'samples': 11342336, 'steps': 22152, 'loss/train': 1.5895987749099731}
-03/04/2022 15:29:12 - INFO - codeparrot_training - Step 22153: {'lr': 0.0004774714860045507, 'samples': 11342848, 'steps': 22153, 'loss/train': 0.42950475215911865}
-03/04/2022 15:29:12 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 15:29:17 - INFO - codeparrot_training - Step 22154: {'lr': 0.0004774692844053428, 'samples': 11343360, 'steps': 22154, 'loss/train': 2.304457187652588}
-03/04/2022 15:29:20 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/04/2022 15:29:23 - INFO - codeparrot_training - Step 22155: {'lr': 0.00047746708270364073, 'samples': 11343872, 'steps': 22155, 'loss/train': 2.3379828929901123}
-03/04/2022 15:29:26 - INFO - codeparrot_training - Step 22156: {'lr': 0.0004774648808994455, 'samples': 11344384, 'steps': 22156, 'loss/train': 0.9081267714500427}
-03/04/2022 15:29:28 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/04/2022 15:29:31 - INFO - codeparrot_training - Step 22157: {'lr': 0.0004774626789927582, 'samples': 11344896, 'steps': 22157, 'loss/train': 1.761013388633728}
-03/04/2022 15:29:34 - INFO - codeparrot_training - Step 22158: {'lr': 0.0004774604769835796, 'samples': 11345408, 'steps': 22158, 'loss/train': 2.0900137424468994}
-03/04/2022 15:29:37 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 15:29:40 - INFO - codeparrot_training - Step 22159: {'lr': 0.00047745827487191087, 'samples': 11345920, 'steps': 22159, 'loss/train': 2.0795984268188477}
-03/04/2022 15:29:43 - INFO - codeparrot_training - Step 22160: {'lr': 0.00047745607265775293, 'samples': 11346432, 'steps': 22160, 'loss/train': 1.7852567434310913}
-03/04/2022 15:29:45 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 15:29:48 - INFO - codeparrot_training - Step 22161: {'lr': 0.0004774538703411069, 'samples': 11346944, 'steps': 22161, 'loss/train': 1.7994163036346436}
-03/04/2022 15:29:51 - INFO - codeparrot_training - Step 22162: {'lr': 0.00047745166792197353, 'samples': 11347456, 'steps': 22162, 'loss/train': 1.9477393627166748}
-03/04/2022 15:29:54 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/04/2022 15:29:56 - INFO - codeparrot_training - Step 22163: {'lr': 0.000477449465400354, 'samples': 11347968, 'steps': 22163, 'loss/train': 2.093964099884033}
-03/04/2022 15:30:00 - INFO - codeparrot_training - Step 22164: {'lr': 0.00047744726277624926, 'samples': 11348480, 'steps': 22164, 'loss/train': 1.5399622917175293}
-03/04/2022 15:30:02 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/04/2022 15:30:05 - INFO - codeparrot_training - Step 22165: {'lr': 0.00047744506004966024, 'samples': 11348992, 'steps': 22165, 'loss/train': 1.3139619827270508}
-03/04/2022 15:30:08 - INFO - codeparrot_training - Step 22166: {'lr': 0.00047744285722058804, 'samples': 11349504, 'steps': 22166, 'loss/train': 2.1864373683929443}
-03/04/2022 15:30:11 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/04/2022 15:30:13 - INFO - codeparrot_training - Step 22167: {'lr': 0.0004774406542890336, 'samples': 11350016, 'steps': 22167, 'loss/train': 1.7841740846633911}
-03/04/2022 15:30:16 - INFO - codeparrot_training - Step 22168: {'lr': 0.0004774384512549979, 'samples': 11350528, 'steps': 22168, 'loss/train': 0.10313055664300919}
-03/04/2022 15:30:19 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/04/2022 15:30:22 - INFO - codeparrot_training - Step 22169: {'lr': 0.00047743624811848195, 'samples': 11351040, 'steps': 22169, 'loss/train': 2.0613551139831543}
-03/04/2022 15:30:25 - INFO - codeparrot_training - Step 22170: {'lr': 0.00047743404487948673, 'samples': 11351552, 'steps': 22170, 'loss/train': 1.4357821941375732}
-03/04/2022 15:30:28 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/04/2022 15:30:30 - INFO - codeparrot_training - Step 22171: {'lr': 0.0004774318415380132, 'samples': 11352064, 'steps': 22171, 'loss/train': 1.162430763244629}
-03/04/2022 15:30:33 - INFO - codeparrot_training - Step 22172: {'lr': 0.0004774296380940625, 'samples': 11352576, 'steps': 22172, 'loss/train': 1.048547625541687}
-03/04/2022 15:30:36 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/04/2022 15:30:39 - INFO - codeparrot_training - Step 22173: {'lr': 0.0004774274345476354, 'samples': 11353088, 'steps': 22173, 'loss/train': 1.8127728700637817}
-03/04/2022 15:30:42 - INFO - codeparrot_training - Step 22174: {'lr': 0.00047742523089873304, 'samples': 11353600, 'steps': 22174, 'loss/train': 1.5749802589416504}
-03/04/2022 15:30:45 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 15:30:47 - INFO - codeparrot_training - Step 22175: {'lr': 0.0004774230271473564, 'samples': 11354112, 'steps': 22175, 'loss/train': 2.324392318725586}
-03/04/2022 15:30:50 - INFO - codeparrot_training - Step 22176: {'lr': 0.00047742082329350644, 'samples': 11354624, 'steps': 22176, 'loss/train': 1.9879522323608398}
-03/04/2022 15:30:53 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 15:30:55 - INFO - codeparrot_training - Step 22177: {'lr': 0.0004774186193371841, 'samples': 11355136, 'steps': 22177, 'loss/train': 0.48985105752944946}
-03/04/2022 15:30:59 - INFO - codeparrot_training - Step 22178: {'lr': 0.00047741641527839054, 'samples': 11355648, 'steps': 22178, 'loss/train': 1.7213879823684692}
-03/04/2022 15:31:01 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 15:31:04 - INFO - codeparrot_training - Step 22179: {'lr': 0.00047741421111712666, 'samples': 11356160, 'steps': 22179, 'loss/train': 1.4045706987380981}
-03/04/2022 15:31:07 - INFO - codeparrot_training - Step 22180: {'lr': 0.00047741200685339337, 'samples': 11356672, 'steps': 22180, 'loss/train': 1.4715582132339478}
-03/04/2022 15:31:10 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 15:31:12 - INFO - codeparrot_training - Step 22181: {'lr': 0.0004774098024871918, 'samples': 11357184, 'steps': 22181, 'loss/train': 1.4860867261886597}
-03/04/2022 15:31:16 - INFO - codeparrot_training - Step 22182: {'lr': 0.00047740759801852284, 'samples': 11357696, 'steps': 22182, 'loss/train': 2.0933032035827637}
-03/04/2022 15:31:19 - INFO - codeparrot_training - Step 22183: {'lr': 0.00047740539344738754, 'samples': 11358208, 'steps': 22183, 'loss/train': 2.062950849533081}
-03/04/2022 15:31:19 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/04/2022 15:31:24 - INFO - codeparrot_training - Step 22184: {'lr': 0.00047740318877378685, 'samples': 11358720, 'steps': 22184, 'loss/train': 1.3282326459884644}
-03/04/2022 15:31:27 - INFO - codeparrot_training - Step 22185: {'lr': 0.00047740098399772185, 'samples': 11359232, 'steps': 22185, 'loss/train': 1.544287085533142}
-03/04/2022 15:31:28 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/04/2022 15:31:33 - INFO - codeparrot_training - Step 22186: {'lr': 0.0004773987791191935, 'samples': 11359744, 'steps': 22186, 'loss/train': 1.0829787254333496}
-03/04/2022 15:31:36 - INFO - codeparrot_training - Step 22187: {'lr': 0.0004773965741382027, 'samples': 11360256, 'steps': 22187, 'loss/train': 1.729000210762024}
-03/04/2022 15:31:36 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/04/2022 15:31:41 - INFO - codeparrot_training - Step 22188: {'lr': 0.00047739436905475054, 'samples': 11360768, 'steps': 22188, 'loss/train': 2.700211763381958}
-03/04/2022 15:31:44 - INFO - codeparrot_training - Step 22189: {'lr': 0.00047739216386883797, 'samples': 11361280, 'steps': 22189, 'loss/train': 1.390215277671814}
-03/04/2022 15:31:44 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/04/2022 15:31:49 - INFO - codeparrot_training - Step 22190: {'lr': 0.000477389958580466, 'samples': 11361792, 'steps': 22190, 'loss/train': 1.6053754091262817}
-03/04/2022 15:31:53 - INFO - codeparrot_training - Step 22191: {'lr': 0.0004773877531896356, 'samples': 11362304, 'steps': 22191, 'loss/train': 1.0694011449813843}
-03/04/2022 15:31:53 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 15:31:58 - INFO - codeparrot_training - Step 22192: {'lr': 0.00047738554769634784, 'samples': 11362816, 'steps': 22192, 'loss/train': 2.3320562839508057}
-03/04/2022 15:32:01 - INFO - codeparrot_training - Step 22193: {'lr': 0.00047738334210060366, 'samples': 11363328, 'steps': 22193, 'loss/train': 2.533250331878662}
-03/04/2022 15:32:01 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/04/2022 15:32:07 - INFO - codeparrot_training - Step 22194: {'lr': 0.000477381136402404, 'samples': 11363840, 'steps': 22194, 'loss/train': 1.622113585472107}
-03/04/2022 15:32:10 - INFO - codeparrot_training - Step 22195: {'lr': 0.00047737893060175, 'samples': 11364352, 'steps': 22195, 'loss/train': 1.4974398612976074}
-03/04/2022 15:32:10 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/04/2022 15:32:15 - INFO - codeparrot_training - Step 22196: {'lr': 0.00047737672469864246, 'samples': 11364864, 'steps': 22196, 'loss/train': 1.3227462768554688}
-03/04/2022 15:32:18 - INFO - codeparrot_training - Step 22197: {'lr': 0.0004773745186930825, 'samples': 11365376, 'steps': 22197, 'loss/train': 1.5945134162902832}
-03/04/2022 15:32:19 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 15:32:24 - INFO - codeparrot_training - Step 22198: {'lr': 0.00047737231258507116, 'samples': 11365888, 'steps': 22198, 'loss/train': 1.3415532112121582}
-03/04/2022 15:32:27 - INFO - codeparrot_training - Step 22199: {'lr': 0.00047737010637460934, 'samples': 11366400, 'steps': 22199, 'loss/train': 2.521217107772827}
-03/04/2022 15:32:27 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 15:32:32 - INFO - codeparrot_training - Step 22200: {'lr': 0.00047736790006169794, 'samples': 11366912, 'steps': 22200, 'loss/train': 0.458636611700058}
-03/04/2022 15:32:35 - INFO - codeparrot_training - Step 22201: {'lr': 0.00047736569364633817, 'samples': 11367424, 'steps': 22201, 'loss/train': 1.4262664318084717}
-03/04/2022 15:32:36 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 15:32:41 - INFO - codeparrot_training - Step 22202: {'lr': 0.00047736348712853094, 'samples': 11367936, 'steps': 22202, 'loss/train': 2.044226884841919}
-03/04/2022 15:32:44 - INFO - codeparrot_training - Step 22203: {'lr': 0.0004773612805082772, 'samples': 11368448, 'steps': 22203, 'loss/train': 0.9254205226898193}
-03/04/2022 15:32:44 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/04/2022 15:32:49 - INFO - codeparrot_training - Step 22204: {'lr': 0.000477359073785578, 'samples': 11368960, 'steps': 22204, 'loss/train': 2.8265929222106934}
-03/04/2022 15:32:52 - INFO - codeparrot_training - Step 22205: {'lr': 0.00047735686696043434, 'samples': 11369472, 'steps': 22205, 'loss/train': 1.9036263227462769}
-03/04/2022 15:32:52 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/04/2022 15:32:57 - INFO - codeparrot_training - Step 22206: {'lr': 0.0004773546600328471, 'samples': 11369984, 'steps': 22206, 'loss/train': 2.488102436065674}
-03/04/2022 15:33:01 - INFO - codeparrot_training - Step 22207: {'lr': 0.00047735245300281745, 'samples': 11370496, 'steps': 22207, 'loss/train': 6.530094623565674}
-03/04/2022 15:33:01 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 15:33:06 - INFO - codeparrot_training - Step 22208: {'lr': 0.00047735024587034625, 'samples': 11371008, 'steps': 22208, 'loss/train': 1.543666958808899}
-03/04/2022 15:33:09 - INFO - codeparrot_training - Step 22209: {'lr': 0.00047734803863543453, 'samples': 11371520, 'steps': 22209, 'loss/train': 1.9861810207366943}
-03/04/2022 15:33:10 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/04/2022 15:33:15 - INFO - codeparrot_training - Step 22210: {'lr': 0.00047734583129808327, 'samples': 11372032, 'steps': 22210, 'loss/train': 2.106640338897705}
-03/04/2022 15:33:18 - INFO - codeparrot_training - Step 22211: {'lr': 0.00047734362385829356, 'samples': 11372544, 'steps': 22211, 'loss/train': 1.6649212837219238}
-03/04/2022 15:33:18 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/04/2022 15:33:23 - INFO - codeparrot_training - Step 22212: {'lr': 0.0004773414163160662, 'samples': 11373056, 'steps': 22212, 'loss/train': 1.8969519138336182}
-03/04/2022 15:33:26 - INFO - codeparrot_training - Step 22213: {'lr': 0.00047733920867140244, 'samples': 11373568, 'steps': 22213, 'loss/train': 2.3982975482940674}
-03/04/2022 15:33:28 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 15:33:32 - INFO - codeparrot_training - Step 22214: {'lr': 0.00047733700092430305, 'samples': 11374080, 'steps': 22214, 'loss/train': 1.5661745071411133}
-03/04/2022 15:33:35 - INFO - codeparrot_training - Step 22215: {'lr': 0.0004773347930747691, 'samples': 11374592, 'steps': 22215, 'loss/train': 2.312277317047119}
-03/04/2022 15:33:36 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 15:33:40 - INFO - codeparrot_training - Step 22216: {'lr': 0.0004773325851228017, 'samples': 11375104, 'steps': 22216, 'loss/train': 1.1213816404342651}
-03/04/2022 15:33:43 - INFO - codeparrot_training - Step 22217: {'lr': 0.00047733037706840166, 'samples': 11375616, 'steps': 22217, 'loss/train': 1.9684717655181885}
-03/04/2022 15:33:45 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/04/2022 15:33:49 - INFO - codeparrot_training - Step 22218: {'lr': 0.0004773281689115701, 'samples': 11376128, 'steps': 22218, 'loss/train': 1.942457914352417}
-03/04/2022 15:33:52 - INFO - codeparrot_training - Step 22219: {'lr': 0.000477325960652308, 'samples': 11376640, 'steps': 22219, 'loss/train': 2.034529447555542}
-03/04/2022 15:33:53 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/04/2022 15:33:57 - INFO - codeparrot_training - Step 22220: {'lr': 0.0004773237522906163, 'samples': 11377152, 'steps': 22220, 'loss/train': 2.3409042358398438}
-03/04/2022 15:34:00 - INFO - codeparrot_training - Step 22221: {'lr': 0.000477321543826496, 'samples': 11377664, 'steps': 22221, 'loss/train': 2.5458621978759766}
-03/04/2022 15:34:02 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/04/2022 15:34:06 - INFO - codeparrot_training - Step 22222: {'lr': 0.00047731933525994814, 'samples': 11378176, 'steps': 22222, 'loss/train': 1.4944298267364502}
-03/04/2022 15:34:09 - INFO - codeparrot_training - Step 22223: {'lr': 0.0004773171265909737, 'samples': 11378688, 'steps': 22223, 'loss/train': 2.341916799545288}
-03/04/2022 15:34:10 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 15:34:14 - INFO - codeparrot_training - Step 22224: {'lr': 0.00047731491781957366, 'samples': 11379200, 'steps': 22224, 'loss/train': 1.1500470638275146}
-03/04/2022 15:34:17 - INFO - codeparrot_training - Step 22225: {'lr': 0.0004773127089457491, 'samples': 11379712, 'steps': 22225, 'loss/train': 2.523146152496338}
-03/04/2022 15:34:19 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 15:34:22 - INFO - codeparrot_training - Step 22226: {'lr': 0.0004773104999695008, 'samples': 11380224, 'steps': 22226, 'loss/train': 1.7590314149856567}
-03/04/2022 15:34:26 - INFO - codeparrot_training - Step 22227: {'lr': 0.00047730829089082994, 'samples': 11380736, 'steps': 22227, 'loss/train': 2.0174756050109863}
-03/04/2022 15:34:27 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/04/2022 15:34:31 - INFO - codeparrot_training - Step 22228: {'lr': 0.00047730608170973754, 'samples': 11381248, 'steps': 22228, 'loss/train': 1.6932587623596191}
-03/04/2022 15:34:34 - INFO - codeparrot_training - Step 22229: {'lr': 0.00047730387242622446, 'samples': 11381760, 'steps': 22229, 'loss/train': 0.9918410778045654}
-03/04/2022 15:34:37 - INFO - codeparrot_training - Step 22230: {'lr': 0.00047730166304029185, 'samples': 11382272, 'steps': 22230, 'loss/train': 2.60172700881958}
-03/04/2022 15:34:37 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/04/2022 15:34:43 - INFO - codeparrot_training - Step 22231: {'lr': 0.0004772994535519405, 'samples': 11382784, 'steps': 22231, 'loss/train': 1.4549503326416016}
-03/04/2022 15:34:46 - INFO - codeparrot_training - Step 22232: {'lr': 0.0004772972439611716, 'samples': 11383296, 'steps': 22232, 'loss/train': 1.8812918663024902}
-03/04/2022 15:34:46 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 15:34:52 - INFO - codeparrot_training - Step 22233: {'lr': 0.00047729503426798605, 'samples': 11383808, 'steps': 22233, 'loss/train': 2.0896060466766357}
-03/04/2022 15:34:55 - INFO - codeparrot_training - Step 22234: {'lr': 0.0004772928244723849, 'samples': 11384320, 'steps': 22234, 'loss/train': 6.667899131774902}
-03/04/2022 15:34:56 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/04/2022 15:35:00 - INFO - codeparrot_training - Step 22235: {'lr': 0.00047729061457436905, 'samples': 11384832, 'steps': 22235, 'loss/train': 1.5816584825515747}
-03/04/2022 15:35:03 - INFO - codeparrot_training - Step 22236: {'lr': 0.0004772884045739396, 'samples': 11385344, 'steps': 22236, 'loss/train': 2.3815054893493652}
-03/04/2022 15:35:04 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/04/2022 15:35:09 - INFO - codeparrot_training - Step 22237: {'lr': 0.0004772861944710974, 'samples': 11385856, 'steps': 22237, 'loss/train': 2.0315628051757812}
-03/04/2022 15:35:12 - INFO - codeparrot_training - Step 22238: {'lr': 0.00047728398426584375, 'samples': 11386368, 'steps': 22238, 'loss/train': 0.9229505658149719}
-03/04/2022 15:35:13 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/04/2022 15:35:17 - INFO - codeparrot_training - Step 22239: {'lr': 0.0004772817739581793, 'samples': 11386880, 'steps': 22239, 'loss/train': 2.113133430480957}
-03/04/2022 15:35:20 - INFO - codeparrot_training - Step 22240: {'lr': 0.0004772795635481052, 'samples': 11387392, 'steps': 22240, 'loss/train': 2.7265355587005615}
-03/04/2022 15:35:21 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 15:35:25 - INFO - codeparrot_training - Step 22241: {'lr': 0.00047727735303562246, 'samples': 11387904, 'steps': 22241, 'loss/train': 0.9764037728309631}
-03/04/2022 15:35:28 - INFO - codeparrot_training - Step 22242: {'lr': 0.000477275142420732, 'samples': 11388416, 'steps': 22242, 'loss/train': 1.3164842128753662}
-03/04/2022 15:35:30 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/04/2022 15:35:34 - INFO - codeparrot_training - Step 22243: {'lr': 0.000477272931703435, 'samples': 11388928, 'steps': 22243, 'loss/train': 1.9129084348678589}
-03/04/2022 15:35:37 - INFO - codeparrot_training - Step 22244: {'lr': 0.0004772707208837322, 'samples': 11389440, 'steps': 22244, 'loss/train': 1.6567832231521606}
-03/04/2022 15:35:39 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 15:35:42 - INFO - codeparrot_training - Step 22245: {'lr': 0.0004772685099616247, 'samples': 11389952, 'steps': 22245, 'loss/train': 1.7662593126296997}
-03/04/2022 15:35:45 - INFO - codeparrot_training - Step 22246: {'lr': 0.0004772662989371136, 'samples': 11390464, 'steps': 22246, 'loss/train': 1.3090407848358154}
-03/04/2022 15:35:47 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/04/2022 15:35:51 - INFO - codeparrot_training - Step 22247: {'lr': 0.0004772640878101998, 'samples': 11390976, 'steps': 22247, 'loss/train': 1.368567705154419}
-03/04/2022 15:35:54 - INFO - codeparrot_training - Step 22248: {'lr': 0.00047726187658088425, 'samples': 11391488, 'steps': 22248, 'loss/train': 1.6496580839157104}
-03/04/2022 15:35:56 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/04/2022 15:35:59 - INFO - codeparrot_training - Step 22249: {'lr': 0.0004772596652491681, 'samples': 11392000, 'steps': 22249, 'loss/train': 1.45890212059021}
-03/04/2022 15:36:02 - INFO - codeparrot_training - Step 22250: {'lr': 0.0004772574538150522, 'samples': 11392512, 'steps': 22250, 'loss/train': 1.843206763267517}
-03/04/2022 15:36:05 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/04/2022 15:36:08 - INFO - codeparrot_training - Step 22251: {'lr': 0.0004772552422785376, 'samples': 11393024, 'steps': 22251, 'loss/train': 1.441948652267456}
-03/04/2022 15:36:11 - INFO - codeparrot_training - Step 22252: {'lr': 0.00047725303063962535, 'samples': 11393536, 'steps': 22252, 'loss/train': 2.45949649810791}
-03/04/2022 15:36:13 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/04/2022 15:36:16 - INFO - codeparrot_training - Step 22253: {'lr': 0.00047725081889831626, 'samples': 11394048, 'steps': 22253, 'loss/train': 1.977330207824707}
-03/04/2022 15:36:19 - INFO - codeparrot_training - Step 22254: {'lr': 0.0004772486070546116, 'samples': 11394560, 'steps': 22254, 'loss/train': 1.642802357673645}
-03/04/2022 15:36:22 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/04/2022 15:36:25 - INFO - codeparrot_training - Step 22255: {'lr': 0.0004772463951085121, 'samples': 11395072, 'steps': 22255, 'loss/train': 1.6976144313812256}
-03/04/2022 15:36:28 - INFO - codeparrot_training - Step 22256: {'lr': 0.00047724418306001895, 'samples': 11395584, 'steps': 22256, 'loss/train': 2.4152402877807617}
-03/04/2022 15:36:30 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/04/2022 15:36:33 - INFO - codeparrot_training - Step 22257: {'lr': 0.0004772419709091331, 'samples': 11396096, 'steps': 22257, 'loss/train': 1.7744184732437134}
-03/04/2022 15:36:36 - INFO - codeparrot_training - Step 22258: {'lr': 0.00047723975865585544, 'samples': 11396608, 'steps': 22258, 'loss/train': 1.1372560262680054}
-03/04/2022 15:36:38 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/04/2022 15:36:41 - INFO - codeparrot_training - Step 22259: {'lr': 0.00047723754630018715, 'samples': 11397120, 'steps': 22259, 'loss/train': 1.1425553560256958}
-03/04/2022 15:36:44 - INFO - codeparrot_training - Step 22260: {'lr': 0.000477235333842129, 'samples': 11397632, 'steps': 22260, 'loss/train': 1.6570017337799072}
-03/04/2022 15:36:47 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/04/2022 15:36:50 - INFO - codeparrot_training - Step 22261: {'lr': 0.00047723312128168226, 'samples': 11398144, 'steps': 22261, 'loss/train': 1.2306241989135742}
-03/04/2022 15:36:53 - INFO - codeparrot_training - Step 22262: {'lr': 0.00047723090861884773, 'samples': 11398656, 'steps': 22262, 'loss/train': 2.264705181121826}
-03/04/2022 15:36:55 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 15:36:58 - INFO - codeparrot_training - Step 22263: {'lr': 0.00047722869585362646, 'samples': 11399168, 'steps': 22263, 'loss/train': 1.8475779294967651}
-03/04/2022 15:37:01 - INFO - codeparrot_training - Step 22264: {'lr': 0.0004772264829860194, 'samples': 11399680, 'steps': 22264, 'loss/train': 1.7155795097351074}
-03/04/2022 15:37:07 - INFO - codeparrot_training - Step 22265: {'lr': 0.00047722427001602765, 'samples': 11400192, 'steps': 22265, 'loss/train': 2.118985891342163}
-03/04/2022 15:37:10 - INFO - codeparrot_training - Step 22266: {'lr': 0.0004772220569436521, 'samples': 11400704, 'steps': 22266, 'loss/train': 1.783207654953003}
-03/04/2022 15:37:12 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 15:37:15 - INFO - codeparrot_training - Step 22267: {'lr': 0.0004772198437688938, 'samples': 11401216, 'steps': 22267, 'loss/train': 1.7310057878494263}
-03/04/2022 15:37:18 - INFO - codeparrot_training - Step 22268: {'lr': 0.0004772176304917538, 'samples': 11401728, 'steps': 22268, 'loss/train': 1.3361843824386597}
-03/04/2022 15:37:20 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 15:37:24 - INFO - codeparrot_training - Step 22269: {'lr': 0.00047721541711223306, 'samples': 11402240, 'steps': 22269, 'loss/train': 1.8218023777008057}
-03/04/2022 15:37:27 - INFO - codeparrot_training - Step 22270: {'lr': 0.00047721320363033247, 'samples': 11402752, 'steps': 22270, 'loss/train': 2.75347900390625}
-03/04/2022 15:37:30 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/04/2022 15:37:32 - INFO - codeparrot_training - Step 22271: {'lr': 0.00047721099004605316, 'samples': 11403264, 'steps': 22271, 'loss/train': 2.8340041637420654}
-03/04/2022 15:37:36 - INFO - codeparrot_training - Step 22272: {'lr': 0.00047720877635939606, 'samples': 11403776, 'steps': 22272, 'loss/train': 0.6918489933013916}
-03/04/2022 15:37:38 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 15:37:41 - INFO - codeparrot_training - Step 22273: {'lr': 0.0004772065625703622, 'samples': 11404288, 'steps': 22273, 'loss/train': 0.9932120442390442}
-03/04/2022 15:37:44 - INFO - codeparrot_training - Step 22274: {'lr': 0.0004772043486789526, 'samples': 11404800, 'steps': 22274, 'loss/train': 2.4619579315185547}
-03/04/2022 15:37:46 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 15:37:49 - INFO - codeparrot_training - Step 22275: {'lr': 0.0004772021346851682, 'samples': 11405312, 'steps': 22275, 'loss/train': 2.0812244415283203}
-03/04/2022 15:37:52 - INFO - codeparrot_training - Step 22276: {'lr': 0.00047719992058901006, 'samples': 11405824, 'steps': 22276, 'loss/train': 1.539668321609497}
-03/04/2022 15:37:55 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/04/2022 15:37:58 - INFO - codeparrot_training - Step 22277: {'lr': 0.0004771977063904791, 'samples': 11406336, 'steps': 22277, 'loss/train': 2.096402406692505}
-03/04/2022 15:38:01 - INFO - codeparrot_training - Step 22278: {'lr': 0.00047719549208957636, 'samples': 11406848, 'steps': 22278, 'loss/train': 2.2655439376831055}
-03/04/2022 15:38:04 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 15:38:06 - INFO - codeparrot_training - Step 22279: {'lr': 0.0004771932776863028, 'samples': 11407360, 'steps': 22279, 'loss/train': 2.152956247329712}
-03/04/2022 15:38:09 - INFO - codeparrot_training - Step 22280: {'lr': 0.0004771910631806595, 'samples': 11407872, 'steps': 22280, 'loss/train': 2.6602895259857178}
-03/04/2022 15:38:13 - INFO - codeparrot_training - Step 22281: {'lr': 0.00047718884857264745, 'samples': 11408384, 'steps': 22281, 'loss/train': 1.6638280153274536}
-03/04/2022 15:38:13 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 15:38:18 - INFO - codeparrot_training - Step 22282: {'lr': 0.0004771866338622676, 'samples': 11408896, 'steps': 22282, 'loss/train': 3.609278440475464}
-03/04/2022 15:38:21 - INFO - codeparrot_training - Step 22283: {'lr': 0.0004771844190495209, 'samples': 11409408, 'steps': 22283, 'loss/train': 2.2452914714813232}
-03/04/2022 15:38:22 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/04/2022 15:38:27 - INFO - codeparrot_training - Step 22284: {'lr': 0.0004771822041344085, 'samples': 11409920, 'steps': 22284, 'loss/train': 1.7666600942611694}
-03/04/2022 15:38:30 - INFO - codeparrot_training - Step 22285: {'lr': 0.0004771799891169312, 'samples': 11410432, 'steps': 22285, 'loss/train': 2.1622772216796875}
-03/04/2022 15:38:30 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/04/2022 15:38:35 - INFO - codeparrot_training - Step 22286: {'lr': 0.0004771777739970902, 'samples': 11410944, 'steps': 22286, 'loss/train': 1.982214093208313}
-03/04/2022 15:38:38 - INFO - codeparrot_training - Step 22287: {'lr': 0.0004771755587748863, 'samples': 11411456, 'steps': 22287, 'loss/train': 1.998295545578003}
-03/04/2022 15:38:39 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 15:38:44 - INFO - codeparrot_training - Step 22288: {'lr': 0.00047717334345032065, 'samples': 11411968, 'steps': 22288, 'loss/train': 1.9068212509155273}
-03/04/2022 15:38:47 - INFO - codeparrot_training - Step 22289: {'lr': 0.0004771711280233942, 'samples': 11412480, 'steps': 22289, 'loss/train': 1.9397213459014893}
-03/04/2022 15:38:48 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/04/2022 15:38:52 - INFO - codeparrot_training - Step 22290: {'lr': 0.000477168912494108, 'samples': 11412992, 'steps': 22290, 'loss/train': 2.200573682785034}
-03/04/2022 15:38:55 - INFO - codeparrot_training - Step 22291: {'lr': 0.00047716669686246287, 'samples': 11413504, 'steps': 22291, 'loss/train': 0.6923785209655762}
-03/04/2022 15:38:56 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 15:39:00 - INFO - codeparrot_training - Step 22292: {'lr': 0.00047716448112846, 'samples': 11414016, 'steps': 22292, 'loss/train': 1.8292288780212402}
-03/04/2022 15:39:04 - INFO - codeparrot_training - Step 22293: {'lr': 0.00047716226529210035, 'samples': 11414528, 'steps': 22293, 'loss/train': 1.7958790063858032}
-03/04/2022 15:39:05 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/04/2022 15:39:09 - INFO - codeparrot_training - Step 22294: {'lr': 0.00047716004935338484, 'samples': 11415040, 'steps': 22294, 'loss/train': 1.7815150022506714}
-03/04/2022 15:39:12 - INFO - codeparrot_training - Step 22295: {'lr': 0.0004771578333123145, 'samples': 11415552, 'steps': 22295, 'loss/train': 1.5924257040023804}
-03/04/2022 15:39:13 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 15:39:17 - INFO - codeparrot_training - Step 22296: {'lr': 0.00047715561716889037, 'samples': 11416064, 'steps': 22296, 'loss/train': 0.35261061787605286}
-03/04/2022 15:39:20 - INFO - codeparrot_training - Step 22297: {'lr': 0.0004771534009231134, 'samples': 11416576, 'steps': 22297, 'loss/train': 1.3618861436843872}
-03/04/2022 15:39:22 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/04/2022 15:39:26 - INFO - codeparrot_training - Step 22298: {'lr': 0.00047715118457498473, 'samples': 11417088, 'steps': 22298, 'loss/train': 1.5753991603851318}
-03/04/2022 15:39:29 - INFO - codeparrot_training - Step 22299: {'lr': 0.00047714896812450514, 'samples': 11417600, 'steps': 22299, 'loss/train': 2.196711540222168}
-03/04/2022 15:39:31 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 15:39:35 - INFO - codeparrot_training - Step 22300: {'lr': 0.00047714675157167573, 'samples': 11418112, 'steps': 22300, 'loss/train': 2.676680564880371}
-03/04/2022 15:39:38 - INFO - codeparrot_training - Step 22301: {'lr': 0.00047714453491649753, 'samples': 11418624, 'steps': 22301, 'loss/train': 1.1340454816818237}
-03/04/2022 15:39:39 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/04/2022 15:39:43 - INFO - codeparrot_training - Step 22302: {'lr': 0.00047714231815897145, 'samples': 11419136, 'steps': 22302, 'loss/train': 1.1262229681015015}
-03/04/2022 15:39:46 - INFO - codeparrot_training - Step 22303: {'lr': 0.0004771401012990986, 'samples': 11419648, 'steps': 22303, 'loss/train': 1.9904206991195679}
-03/04/2022 15:39:48 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 15:39:52 - INFO - codeparrot_training - Step 22304: {'lr': 0.0004771378843368799, 'samples': 11420160, 'steps': 22304, 'loss/train': 2.1478192806243896}
-03/04/2022 15:39:55 - INFO - codeparrot_training - Step 22305: {'lr': 0.0004771356672723164, 'samples': 11420672, 'steps': 22305, 'loss/train': 1.4392684698104858}
-03/04/2022 15:39:58 - INFO - codeparrot_training - Step 22306: {'lr': 0.0004771334501054091, 'samples': 11421184, 'steps': 22306, 'loss/train': 2.2167985439300537}
-03/04/2022 15:39:59 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/04/2022 15:40:04 - INFO - codeparrot_training - Step 22307: {'lr': 0.0004771312328361589, 'samples': 11421696, 'steps': 22307, 'loss/train': 1.5921905040740967}
-03/04/2022 15:40:07 - INFO - codeparrot_training - Step 22308: {'lr': 0.0004771290154645669, 'samples': 11422208, 'steps': 22308, 'loss/train': 1.3252410888671875}
-03/04/2022 15:40:08 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 15:40:12 - INFO - codeparrot_training - Step 22309: {'lr': 0.0004771267979906341, 'samples': 11422720, 'steps': 22309, 'loss/train': 1.9257309436798096}
-03/04/2022 15:40:15 - INFO - codeparrot_training - Step 22310: {'lr': 0.0004771245804143615, 'samples': 11423232, 'steps': 22310, 'loss/train': 2.038508892059326}
-03/04/2022 15:40:17 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/04/2022 15:40:21 - INFO - codeparrot_training - Step 22311: {'lr': 0.00047712236273574993, 'samples': 11423744, 'steps': 22311, 'loss/train': 1.9827864170074463}
-03/04/2022 15:40:24 - INFO - codeparrot_training - Step 22312: {'lr': 0.0004771201449548006, 'samples': 11424256, 'steps': 22312, 'loss/train': 2.0457041263580322}
-03/04/2022 15:40:25 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 15:40:29 - INFO - codeparrot_training - Step 22313: {'lr': 0.0004771179270715145, 'samples': 11424768, 'steps': 22313, 'loss/train': 1.5745621919631958}
-03/04/2022 15:40:32 - INFO - codeparrot_training - Step 22314: {'lr': 0.0004771157090858925, 'samples': 11425280, 'steps': 22314, 'loss/train': 2.0680339336395264}
-03/04/2022 15:40:34 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 15:40:38 - INFO - codeparrot_training - Step 22315: {'lr': 0.00047711349099793565, 'samples': 11425792, 'steps': 22315, 'loss/train': 1.7564970254898071}
-03/04/2022 15:40:41 - INFO - codeparrot_training - Step 22316: {'lr': 0.00047711127280764497, 'samples': 11426304, 'steps': 22316, 'loss/train': 2.1914710998535156}
-03/04/2022 15:40:43 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 15:40:46 - INFO - codeparrot_training - Step 22317: {'lr': 0.0004771090545150215, 'samples': 11426816, 'steps': 22317, 'loss/train': 1.8899551630020142}
-03/04/2022 15:40:49 - INFO - codeparrot_training - Step 22318: {'lr': 0.00047710683612006623, 'samples': 11427328, 'steps': 22318, 'loss/train': 1.6784968376159668}
-03/04/2022 15:40:52 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 15:40:55 - INFO - codeparrot_training - Step 22319: {'lr': 0.00047710461762278, 'samples': 11427840, 'steps': 22319, 'loss/train': 1.9902827739715576}
-03/04/2022 15:40:58 - INFO - codeparrot_training - Step 22320: {'lr': 0.00047710239902316404, 'samples': 11428352, 'steps': 22320, 'loss/train': 0.675197422504425}
-03/04/2022 15:41:01 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/04/2022 15:41:03 - INFO - codeparrot_training - Step 22321: {'lr': 0.0004771001803212192, 'samples': 11428864, 'steps': 22321, 'loss/train': 1.7486975193023682}
-03/04/2022 15:41:06 - INFO - codeparrot_training - Step 22322: {'lr': 0.0004770979615169466, 'samples': 11429376, 'steps': 22322, 'loss/train': 1.6954245567321777}
-03/04/2022 15:41:09 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/04/2022 15:41:11 - INFO - codeparrot_training - Step 22323: {'lr': 0.00047709574261034705, 'samples': 11429888, 'steps': 22323, 'loss/train': 1.8200124502182007}
-03/04/2022 15:41:15 - INFO - codeparrot_training - Step 22324: {'lr': 0.0004770935236014217, 'samples': 11430400, 'steps': 22324, 'loss/train': 2.0899829864501953}
-03/04/2022 15:41:17 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/04/2022 15:41:20 - INFO - codeparrot_training - Step 22325: {'lr': 0.00047709130449017154, 'samples': 11430912, 'steps': 22325, 'loss/train': 1.521140456199646}
-03/04/2022 15:41:23 - INFO - codeparrot_training - Step 22326: {'lr': 0.0004770890852765975, 'samples': 11431424, 'steps': 22326, 'loss/train': 1.193521499633789}
-03/04/2022 15:41:26 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/04/2022 15:41:29 - INFO - codeparrot_training - Step 22327: {'lr': 0.00047708686596070065, 'samples': 11431936, 'steps': 22327, 'loss/train': 1.7612429857254028}
-03/04/2022 15:41:32 - INFO - codeparrot_training - Step 22328: {'lr': 0.00047708464654248195, 'samples': 11432448, 'steps': 22328, 'loss/train': 2.2048349380493164}
-03/04/2022 15:41:35 - INFO - codeparrot_training - Step 22329: {'lr': 0.0004770824270219424, 'samples': 11432960, 'steps': 22329, 'loss/train': 2.541520595550537}
-03/04/2022 15:41:36 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/04/2022 15:41:41 - INFO - codeparrot_training - Step 22330: {'lr': 0.0004770802073990831, 'samples': 11433472, 'steps': 22330, 'loss/train': 1.1763559579849243}
-03/04/2022 15:41:44 - INFO - codeparrot_training - Step 22331: {'lr': 0.00047707798767390486, 'samples': 11433984, 'steps': 22331, 'loss/train': 1.6634845733642578}
-03/04/2022 15:41:47 - INFO - codeparrot_training - Step 22332: {'lr': 0.00047707576784640883, 'samples': 11434496, 'steps': 22332, 'loss/train': 1.0085744857788086}
-03/04/2022 15:41:49 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/04/2022 15:41:53 - INFO - codeparrot_training - Step 22333: {'lr': 0.00047707354791659594, 'samples': 11435008, 'steps': 22333, 'loss/train': 1.9908726215362549}
-03/04/2022 15:41:56 - INFO - codeparrot_training - Step 22334: {'lr': 0.0004770713278844672, 'samples': 11435520, 'steps': 22334, 'loss/train': 2.233520984649658}
-03/04/2022 15:41:58 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/04/2022 15:42:01 - INFO - codeparrot_training - Step 22335: {'lr': 0.00047706910775002363, 'samples': 11436032, 'steps': 22335, 'loss/train': 2.00911808013916}
-03/04/2022 15:42:04 - INFO - codeparrot_training - Step 22336: {'lr': 0.0004770668875132663, 'samples': 11436544, 'steps': 22336, 'loss/train': 1.6298381090164185}
-03/04/2022 15:42:07 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 15:42:10 - INFO - codeparrot_training - Step 22337: {'lr': 0.00047706466717419607, 'samples': 11437056, 'steps': 22337, 'loss/train': 1.8705356121063232}
-03/04/2022 15:42:13 - INFO - codeparrot_training - Step 22338: {'lr': 0.000477062446732814, 'samples': 11437568, 'steps': 22338, 'loss/train': 0.38395625352859497}
-03/04/2022 15:42:15 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/04/2022 15:42:18 - INFO - codeparrot_training - Step 22339: {'lr': 0.0004770602261891211, 'samples': 11438080, 'steps': 22339, 'loss/train': 2.2905497550964355}
-03/04/2022 15:42:21 - INFO - codeparrot_training - Step 22340: {'lr': 0.00047705800554311836, 'samples': 11438592, 'steps': 22340, 'loss/train': 1.857138991355896}
-03/04/2022 15:42:25 - INFO - codeparrot_training - Step 22341: {'lr': 0.0004770557847948068, 'samples': 11439104, 'steps': 22341, 'loss/train': 1.9479671716690063}
-03/04/2022 15:42:25 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/04/2022 15:42:30 - INFO - codeparrot_training - Step 22342: {'lr': 0.0004770535639441874, 'samples': 11439616, 'steps': 22342, 'loss/train': 2.412079095840454}
-03/04/2022 15:42:33 - INFO - codeparrot_training - Step 22343: {'lr': 0.0004770513429912612, 'samples': 11440128, 'steps': 22343, 'loss/train': 1.9400339126586914}
-03/04/2022 15:42:33 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/04/2022 15:42:38 - INFO - codeparrot_training - Step 22344: {'lr': 0.0004770491219360291, 'samples': 11440640, 'steps': 22344, 'loss/train': 1.485713005065918}
-03/04/2022 15:42:42 - INFO - codeparrot_training - Step 22345: {'lr': 0.00047704690077849223, 'samples': 11441152, 'steps': 22345, 'loss/train': 0.8323150277137756}
-03/04/2022 15:42:42 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/04/2022 15:42:47 - INFO - codeparrot_training - Step 22346: {'lr': 0.0004770446795186515, 'samples': 11441664, 'steps': 22346, 'loss/train': 0.8790633082389832}
-03/04/2022 15:42:50 - INFO - codeparrot_training - Step 22347: {'lr': 0.0004770424581565079, 'samples': 11442176, 'steps': 22347, 'loss/train': 2.1988582611083984}
-03/04/2022 15:42:50 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/04/2022 15:42:55 - INFO - codeparrot_training - Step 22348: {'lr': 0.0004770402366920625, 'samples': 11442688, 'steps': 22348, 'loss/train': 1.530765175819397}
-03/04/2022 15:42:58 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 15:43:00 - INFO - codeparrot_training - Step 22349: {'lr': 0.00047703801512531636, 'samples': 11443200, 'steps': 22349, 'loss/train': 2.006002187728882}
-03/04/2022 15:43:04 - INFO - codeparrot_training - Step 22350: {'lr': 0.00047703579345627036, 'samples': 11443712, 'steps': 22350, 'loss/train': 2.183684825897217}
-03/04/2022 15:43:06 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/04/2022 15:43:09 - INFO - codeparrot_training - Step 22351: {'lr': 0.00047703357168492544, 'samples': 11444224, 'steps': 22351, 'loss/train': 2.0730032920837402}
-03/04/2022 15:43:12 - INFO - codeparrot_training - Step 22352: {'lr': 0.0004770313498112828, 'samples': 11444736, 'steps': 22352, 'loss/train': 2.0986359119415283}
-03/04/2022 15:43:15 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/04/2022 15:43:17 - INFO - codeparrot_training - Step 22353: {'lr': 0.0004770291278353433, 'samples': 11445248, 'steps': 22353, 'loss/train': 3.2045609951019287}
-03/04/2022 15:43:20 - INFO - codeparrot_training - Step 22354: {'lr': 0.00047702690575710796, 'samples': 11445760, 'steps': 22354, 'loss/train': 2.330094814300537}
-03/04/2022 15:43:23 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 15:43:26 - INFO - codeparrot_training - Step 22355: {'lr': 0.0004770246835765778, 'samples': 11446272, 'steps': 22355, 'loss/train': 2.08205509185791}
-03/04/2022 15:43:29 - INFO - codeparrot_training - Step 22356: {'lr': 0.0004770224612937538, 'samples': 11446784, 'steps': 22356, 'loss/train': 2.1141655445098877}
-03/04/2022 15:43:32 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 15:43:34 - INFO - codeparrot_training - Step 22357: {'lr': 0.0004770202389086371, 'samples': 11447296, 'steps': 22357, 'loss/train': 1.9168789386749268}
-03/04/2022 15:43:37 - INFO - codeparrot_training - Step 22358: {'lr': 0.0004770180164212284, 'samples': 11447808, 'steps': 22358, 'loss/train': 2.5445199012756348}
-03/04/2022 15:43:40 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/04/2022 15:43:43 - INFO - codeparrot_training - Step 22359: {'lr': 0.00047701579383152906, 'samples': 11448320, 'steps': 22359, 'loss/train': 1.7233607769012451}
-03/04/2022 15:43:46 - INFO - codeparrot_training - Step 22360: {'lr': 0.0004770135711395398, 'samples': 11448832, 'steps': 22360, 'loss/train': 1.9921740293502808}
-03/04/2022 15:43:48 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 15:43:51 - INFO - codeparrot_training - Step 22361: {'lr': 0.0004770113483452618, 'samples': 11449344, 'steps': 22361, 'loss/train': 2.339416742324829}
-03/04/2022 15:43:54 - INFO - codeparrot_training - Step 22362: {'lr': 0.00047700912544869595, 'samples': 11449856, 'steps': 22362, 'loss/train': 1.277938961982727}
-03/04/2022 15:43:57 - INFO - codeparrot_training - Step 22363: {'lr': 0.0004770069024498433, 'samples': 11450368, 'steps': 22363, 'loss/train': 1.9749418497085571}
-03/04/2022 15:43:58 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/04/2022 15:44:03 - INFO - codeparrot_training - Step 22364: {'lr': 0.00047700467934870484, 'samples': 11450880, 'steps': 22364, 'loss/train': 2.426556348800659}
-03/04/2022 15:44:06 - INFO - codeparrot_training - Step 22365: {'lr': 0.0004770024561452816, 'samples': 11451392, 'steps': 22365, 'loss/train': 2.0053937435150146}
-03/04/2022 15:44:07 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 15:44:11 - INFO - codeparrot_training - Step 22366: {'lr': 0.0004770002328395745, 'samples': 11451904, 'steps': 22366, 'loss/train': 2.1311402320861816}
-03/04/2022 15:44:14 - INFO - codeparrot_training - Step 22367: {'lr': 0.00047699800943158454, 'samples': 11452416, 'steps': 22367, 'loss/train': 1.9790606498718262}
-03/04/2022 15:44:15 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/04/2022 15:44:20 - INFO - codeparrot_training - Step 22368: {'lr': 0.0004769957859213129, 'samples': 11452928, 'steps': 22368, 'loss/train': 2.0900065898895264}
-03/04/2022 15:44:23 - INFO - codeparrot_training - Step 22369: {'lr': 0.00047699356230876047, 'samples': 11453440, 'steps': 22369, 'loss/train': 1.4526458978652954}
-03/04/2022 15:44:24 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/04/2022 15:44:28 - INFO - codeparrot_training - Step 22370: {'lr': 0.0004769913385939282, 'samples': 11453952, 'steps': 22370, 'loss/train': 2.0202369689941406}
-03/04/2022 15:44:31 - INFO - codeparrot_training - Step 22371: {'lr': 0.0004769891147768171, 'samples': 11454464, 'steps': 22371, 'loss/train': 2.375291347503662}
-03/04/2022 15:44:32 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/04/2022 15:44:37 - INFO - codeparrot_training - Step 22372: {'lr': 0.00047698689085742823, 'samples': 11454976, 'steps': 22372, 'loss/train': 1.9892005920410156}
-03/04/2022 15:44:40 - INFO - codeparrot_training - Step 22373: {'lr': 0.00047698466683576256, 'samples': 11455488, 'steps': 22373, 'loss/train': 1.0614806413650513}
-03/04/2022 15:44:41 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/04/2022 15:44:45 - INFO - codeparrot_training - Step 22374: {'lr': 0.0004769824427118211, 'samples': 11456000, 'steps': 22374, 'loss/train': 1.7671689987182617}
-03/04/2022 15:44:48 - INFO - codeparrot_training - Step 22375: {'lr': 0.00047698021848560494, 'samples': 11456512, 'steps': 22375, 'loss/train': 1.735493779182434}
-03/04/2022 15:44:50 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 15:44:54 - INFO - codeparrot_training - Step 22376: {'lr': 0.0004769779941571149, 'samples': 11457024, 'steps': 22376, 'loss/train': 2.0558762550354004}
-03/04/2022 15:44:57 - INFO - codeparrot_training - Step 22377: {'lr': 0.00047697576972635213, 'samples': 11457536, 'steps': 22377, 'loss/train': 1.4781200885772705}
-03/04/2022 15:44:59 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 15:45:02 - INFO - codeparrot_training - Step 22378: {'lr': 0.0004769735451933176, 'samples': 11458048, 'steps': 22378, 'loss/train': 2.319829225540161}
-03/04/2022 15:45:05 - INFO - codeparrot_training - Step 22379: {'lr': 0.0004769713205580122, 'samples': 11458560, 'steps': 22379, 'loss/train': 2.630206346511841}
-03/04/2022 15:45:07 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 15:45:11 - INFO - codeparrot_training - Step 22380: {'lr': 0.0004769690958204371, 'samples': 11459072, 'steps': 22380, 'loss/train': 1.7876747846603394}
-03/04/2022 15:45:14 - INFO - codeparrot_training - Step 22381: {'lr': 0.0004769668709805932, 'samples': 11459584, 'steps': 22381, 'loss/train': 1.9131865501403809}
-03/04/2022 15:45:16 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/04/2022 15:45:19 - INFO - codeparrot_training - Step 22382: {'lr': 0.0004769646460384816, 'samples': 11460096, 'steps': 22382, 'loss/train': 1.5190072059631348}
-03/04/2022 15:45:22 - INFO - codeparrot_training - Step 22383: {'lr': 0.00047696242099410307, 'samples': 11460608, 'steps': 22383, 'loss/train': 1.8266668319702148}
-03/04/2022 15:45:25 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/04/2022 15:45:28 - INFO - codeparrot_training - Step 22384: {'lr': 0.00047696019584745887, 'samples': 11461120, 'steps': 22384, 'loss/train': 1.5854839086532593}
-03/04/2022 15:45:31 - INFO - codeparrot_training - Step 22385: {'lr': 0.00047695797059854996, 'samples': 11461632, 'steps': 22385, 'loss/train': 1.596534013748169}
-03/04/2022 15:45:33 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/04/2022 15:45:36 - INFO - codeparrot_training - Step 22386: {'lr': 0.0004769557452473772, 'samples': 11462144, 'steps': 22386, 'loss/train': 1.2219512462615967}
-03/04/2022 15:45:39 - INFO - codeparrot_training - Step 22387: {'lr': 0.00047695351979394173, 'samples': 11462656, 'steps': 22387, 'loss/train': 2.179931879043579}
-03/04/2022 15:45:42 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/04/2022 15:45:44 - INFO - codeparrot_training - Step 22388: {'lr': 0.00047695129423824454, 'samples': 11463168, 'steps': 22388, 'loss/train': 1.9552170038223267}
-03/04/2022 15:45:48 - INFO - codeparrot_training - Step 22389: {'lr': 0.0004769490685802865, 'samples': 11463680, 'steps': 22389, 'loss/train': 0.9540486335754395}
-03/04/2022 15:45:50 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/04/2022 15:45:53 - INFO - codeparrot_training - Step 22390: {'lr': 0.00047694684282006885, 'samples': 11464192, 'steps': 22390, 'loss/train': 2.1730754375457764}
-03/04/2022 15:45:56 - INFO - codeparrot_training - Step 22391: {'lr': 0.00047694461695759236, 'samples': 11464704, 'steps': 22391, 'loss/train': 1.9229793548583984}
-03/04/2022 15:45:58 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 15:46:01 - INFO - codeparrot_training - Step 22392: {'lr': 0.00047694239099285815, 'samples': 11465216, 'steps': 22392, 'loss/train': 1.3976644277572632}
-03/04/2022 15:46:05 - INFO - codeparrot_training - Step 22393: {'lr': 0.00047694016492586715, 'samples': 11465728, 'steps': 22393, 'loss/train': 2.3815677165985107}
-03/04/2022 15:46:07 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 15:46:10 - INFO - codeparrot_training - Step 22394: {'lr': 0.0004769379387566205, 'samples': 11466240, 'steps': 22394, 'loss/train': 2.52591872215271}
-03/04/2022 15:46:13 - INFO - codeparrot_training - Step 22395: {'lr': 0.000476935712485119, 'samples': 11466752, 'steps': 22395, 'loss/train': 1.505041241645813}
-03/04/2022 15:46:15 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 15:46:18 - INFO - codeparrot_training - Step 22396: {'lr': 0.0004769334861113639, 'samples': 11467264, 'steps': 22396, 'loss/train': 0.9479007124900818}
-03/04/2022 15:46:21 - INFO - codeparrot_training - Step 22397: {'lr': 0.000476931259635356, 'samples': 11467776, 'steps': 22397, 'loss/train': 1.8733607530593872}
-03/04/2022 15:46:24 - INFO - codeparrot_training - Skipping example with length 983 (seq_length=1024)
-03/04/2022 15:46:27 - INFO - codeparrot_training - Step 22398: {'lr': 0.00047692903305709646, 'samples': 11468288, 'steps': 22398, 'loss/train': 1.9552898406982422}
-03/04/2022 15:46:30 - INFO - codeparrot_training - Step 22399: {'lr': 0.0004769268063765861, 'samples': 11468800, 'steps': 22399, 'loss/train': 2.0450286865234375}
-03/04/2022 15:46:32 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/04/2022 15:46:35 - INFO - codeparrot_training - Step 22400: {'lr': 0.00047692457959382605, 'samples': 11469312, 'steps': 22400, 'loss/train': 3.4000706672668457}
-03/04/2022 15:46:38 - INFO - codeparrot_training - Step 22401: {'lr': 0.0004769223527088173, 'samples': 11469824, 'steps': 22401, 'loss/train': 1.5526716709136963}
-03/04/2022 15:46:41 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 15:46:44 - INFO - codeparrot_training - Step 22402: {'lr': 0.00047692012572156086, 'samples': 11470336, 'steps': 22402, 'loss/train': 2.104238986968994}
-03/04/2022 15:46:47 - INFO - codeparrot_training - Step 22403: {'lr': 0.00047691789863205764, 'samples': 11470848, 'steps': 22403, 'loss/train': 1.1048665046691895}
-03/04/2022 15:46:49 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/04/2022 15:46:52 - INFO - codeparrot_training - Step 22404: {'lr': 0.0004769156714403088, 'samples': 11471360, 'steps': 22404, 'loss/train': 1.678782343864441}
-03/04/2022 15:46:55 - INFO - codeparrot_training - Step 22405: {'lr': 0.0004769134441463152, 'samples': 11471872, 'steps': 22405, 'loss/train': 2.4589037895202637}
-03/04/2022 15:46:57 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/04/2022 15:47:01 - INFO - codeparrot_training - Step 22406: {'lr': 0.0004769112167500779, 'samples': 11472384, 'steps': 22406, 'loss/train': 2.0313570499420166}
-03/04/2022 15:47:04 - INFO - codeparrot_training - Step 22407: {'lr': 0.00047690898925159796, 'samples': 11472896, 'steps': 22407, 'loss/train': 1.5635850429534912}
-03/04/2022 15:47:07 - INFO - codeparrot_training - Step 22408: {'lr': 0.0004769067616508763, 'samples': 11473408, 'steps': 22408, 'loss/train': 2.1659297943115234}
-03/04/2022 15:47:07 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 15:47:12 - INFO - codeparrot_training - Step 22409: {'lr': 0.00047690453394791393, 'samples': 11473920, 'steps': 22409, 'loss/train': 2.2377867698669434}
-03/04/2022 15:47:15 - INFO - codeparrot_training - Step 22410: {'lr': 0.0004769023061427119, 'samples': 11474432, 'steps': 22410, 'loss/train': 2.085585594177246}
-03/04/2022 15:47:15 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 15:47:21 - INFO - codeparrot_training - Step 22411: {'lr': 0.0004769000782352713, 'samples': 11474944, 'steps': 22411, 'loss/train': 1.5014328956604004}
-03/04/2022 15:47:24 - INFO - codeparrot_training - Step 22412: {'lr': 0.00047689785022559284, 'samples': 11475456, 'steps': 22412, 'loss/train': 1.8411418199539185}
-03/04/2022 15:47:24 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/04/2022 15:47:29 - INFO - codeparrot_training - Step 22413: {'lr': 0.0004768956221136778, 'samples': 11475968, 'steps': 22413, 'loss/train': 1.9553931951522827}
-03/04/2022 15:47:32 - INFO - codeparrot_training - Step 22414: {'lr': 0.00047689339389952713, 'samples': 11476480, 'steps': 22414, 'loss/train': 1.9445511102676392}
-03/04/2022 15:47:32 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 15:47:38 - INFO - codeparrot_training - Step 22415: {'lr': 0.0004768911655831417, 'samples': 11476992, 'steps': 22415, 'loss/train': 2.0988261699676514}
-03/04/2022 15:47:41 - INFO - codeparrot_training - Step 22416: {'lr': 0.0004768889371645227, 'samples': 11477504, 'steps': 22416, 'loss/train': 1.9009219408035278}
-03/04/2022 15:47:42 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/04/2022 15:47:46 - INFO - codeparrot_training - Step 22417: {'lr': 0.000476886708643671, 'samples': 11478016, 'steps': 22417, 'loss/train': 2.716937303543091}
-03/04/2022 15:47:49 - INFO - codeparrot_training - Step 22418: {'lr': 0.0004768844800205877, 'samples': 11478528, 'steps': 22418, 'loss/train': 1.7089838981628418}
-03/04/2022 15:47:51 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 15:47:55 - INFO - codeparrot_training - Step 22419: {'lr': 0.0004768822512952737, 'samples': 11479040, 'steps': 22419, 'loss/train': 1.8988728523254395}
-03/04/2022 15:47:58 - INFO - codeparrot_training - Step 22420: {'lr': 0.0004768800224677301, 'samples': 11479552, 'steps': 22420, 'loss/train': 2.19171404838562}
-03/04/2022 15:47:59 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/04/2022 15:48:03 - INFO - codeparrot_training - Step 22421: {'lr': 0.0004768777935379578, 'samples': 11480064, 'steps': 22421, 'loss/train': 2.3457744121551514}
-03/04/2022 15:48:07 - INFO - codeparrot_training - Step 22422: {'lr': 0.0004768755645059579, 'samples': 11480576, 'steps': 22422, 'loss/train': 1.5806716680526733}
-03/04/2022 15:48:08 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/04/2022 15:48:12 - INFO - codeparrot_training - Step 22423: {'lr': 0.00047687333537173136, 'samples': 11481088, 'steps': 22423, 'loss/train': 2.1720352172851562}
-03/04/2022 15:48:15 - INFO - codeparrot_training - Step 22424: {'lr': 0.00047687110613527924, 'samples': 11481600, 'steps': 22424, 'loss/train': 2.2620861530303955}
-03/04/2022 15:48:16 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 15:48:20 - INFO - codeparrot_training - Step 22425: {'lr': 0.00047686887679660253, 'samples': 11482112, 'steps': 22425, 'loss/train': 3.5006890296936035}
-03/04/2022 15:48:23 - INFO - codeparrot_training - Step 22426: {'lr': 0.0004768666473557021, 'samples': 11482624, 'steps': 22426, 'loss/train': 2.3809986114501953}
-03/04/2022 15:48:25 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/04/2022 15:48:29 - INFO - codeparrot_training - Step 22427: {'lr': 0.0004768644178125791, 'samples': 11483136, 'steps': 22427, 'loss/train': 2.2899534702301025}
-03/04/2022 15:48:32 - INFO - codeparrot_training - Step 22428: {'lr': 0.0004768621881672345, 'samples': 11483648, 'steps': 22428, 'loss/train': 1.4964479207992554}
-03/04/2022 15:48:33 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/04/2022 15:48:37 - INFO - codeparrot_training - Step 22429: {'lr': 0.00047685995841966936, 'samples': 11484160, 'steps': 22429, 'loss/train': 1.91129732131958}
-03/04/2022 15:48:40 - INFO - codeparrot_training - Step 22430: {'lr': 0.0004768577285698845, 'samples': 11484672, 'steps': 22430, 'loss/train': 4.377689361572266}
-03/04/2022 15:48:42 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 15:48:45 - INFO - codeparrot_training - Step 22431: {'lr': 0.00047685549861788113, 'samples': 11485184, 'steps': 22431, 'loss/train': 2.3613810539245605}
-03/04/2022 15:48:49 - INFO - codeparrot_training - Step 22432: {'lr': 0.0004768532685636602, 'samples': 11485696, 'steps': 22432, 'loss/train': 1.6671661138534546}
-03/04/2022 15:48:50 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 15:48:54 - INFO - codeparrot_training - Step 22433: {'lr': 0.0004768510384072226, 'samples': 11486208, 'steps': 22433, 'loss/train': 1.9080430269241333}
-03/04/2022 15:48:57 - INFO - codeparrot_training - Step 22434: {'lr': 0.0004768488081485695, 'samples': 11486720, 'steps': 22434, 'loss/train': 0.7797421813011169}
-03/04/2022 15:48:58 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/04/2022 15:49:02 - INFO - codeparrot_training - Step 22435: {'lr': 0.0004768465777877018, 'samples': 11487232, 'steps': 22435, 'loss/train': 1.5904635190963745}
-03/04/2022 15:49:05 - INFO - codeparrot_training - Step 22436: {'lr': 0.0004768443473246205, 'samples': 11487744, 'steps': 22436, 'loss/train': 1.3765811920166016}
-03/04/2022 15:49:07 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 15:49:11 - INFO - codeparrot_training - Step 22437: {'lr': 0.00047684211675932665, 'samples': 11488256, 'steps': 22437, 'loss/train': 2.326796770095825}
-03/04/2022 15:49:14 - INFO - codeparrot_training - Step 22438: {'lr': 0.0004768398860918213, 'samples': 11488768, 'steps': 22438, 'loss/train': 1.441772222518921}
-03/04/2022 15:49:15 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 15:49:19 - INFO - codeparrot_training - Step 22439: {'lr': 0.0004768376553221053, 'samples': 11489280, 'steps': 22439, 'loss/train': 2.22330379486084}
-03/04/2022 15:49:22 - INFO - codeparrot_training - Step 22440: {'lr': 0.0004768354244501798, 'samples': 11489792, 'steps': 22440, 'loss/train': 1.7069092988967896}
-03/04/2022 15:49:24 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/04/2022 15:49:28 - INFO - codeparrot_training - Step 22441: {'lr': 0.0004768331934760458, 'samples': 11490304, 'steps': 22441, 'loss/train': 2.24930477142334}
-03/04/2022 15:49:31 - INFO - codeparrot_training - Step 22442: {'lr': 0.00047683096239970423, 'samples': 11490816, 'steps': 22442, 'loss/train': 2.0926597118377686}
-03/04/2022 15:49:32 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/04/2022 15:49:36 - INFO - codeparrot_training - Step 22443: {'lr': 0.0004768287312211561, 'samples': 11491328, 'steps': 22443, 'loss/train': 1.8300825357437134}
-03/04/2022 15:49:39 - INFO - codeparrot_training - Step 22444: {'lr': 0.0004768264999404025, 'samples': 11491840, 'steps': 22444, 'loss/train': 1.6856225728988647}
-03/04/2022 15:49:40 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 15:49:44 - INFO - codeparrot_training - Step 22445: {'lr': 0.00047682426855744434, 'samples': 11492352, 'steps': 22445, 'loss/train': 2.133347272872925}
-03/04/2022 15:49:48 - INFO - codeparrot_training - Step 22446: {'lr': 0.00047682203707228264, 'samples': 11492864, 'steps': 22446, 'loss/train': 1.9194990396499634}
-03/04/2022 15:49:48 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 15:49:53 - INFO - codeparrot_training - Step 22447: {'lr': 0.00047681980548491853, 'samples': 11493376, 'steps': 22447, 'loss/train': 1.4561387300491333}
-03/04/2022 15:49:56 - INFO - codeparrot_training - Step 22448: {'lr': 0.00047681757379535285, 'samples': 11493888, 'steps': 22448, 'loss/train': 1.2268905639648438}
-03/04/2022 15:49:57 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/04/2022 15:50:01 - INFO - codeparrot_training - Step 22449: {'lr': 0.00047681534200358665, 'samples': 11494400, 'steps': 22449, 'loss/train': 1.752184510231018}
-03/04/2022 15:50:04 - INFO - codeparrot_training - Step 22450: {'lr': 0.000476813110109621, 'samples': 11494912, 'steps': 22450, 'loss/train': 0.9723352789878845}
-03/04/2022 15:50:06 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/04/2022 15:50:10 - INFO - codeparrot_training - Step 22451: {'lr': 0.0004768108781134568, 'samples': 11495424, 'steps': 22451, 'loss/train': 1.312381625175476}
-03/04/2022 15:50:13 - INFO - codeparrot_training - Step 22452: {'lr': 0.0004768086460150952, 'samples': 11495936, 'steps': 22452, 'loss/train': 1.2121964693069458}
-03/04/2022 15:50:14 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 15:50:18 - INFO - codeparrot_training - Step 22453: {'lr': 0.00047680641381453703, 'samples': 11496448, 'steps': 22453, 'loss/train': 2.477135181427002}
-03/04/2022 15:50:21 - INFO - codeparrot_training - Step 22454: {'lr': 0.0004768041815117835, 'samples': 11496960, 'steps': 22454, 'loss/train': 2.1526434421539307}
-03/04/2022 15:50:22 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 15:50:27 - INFO - codeparrot_training - Step 22455: {'lr': 0.00047680194910683545, 'samples': 11497472, 'steps': 22455, 'loss/train': 1.3500245809555054}
-03/04/2022 15:50:30 - INFO - codeparrot_training - Step 22456: {'lr': 0.0004767997165996939, 'samples': 11497984, 'steps': 22456, 'loss/train': 1.5976893901824951}
-03/04/2022 15:50:31 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/04/2022 15:50:35 - INFO - codeparrot_training - Step 22457: {'lr': 0.00047679748399035994, 'samples': 11498496, 'steps': 22457, 'loss/train': 2.302093982696533}
-03/04/2022 15:50:38 - INFO - codeparrot_training - Step 22458: {'lr': 0.00047679525127883456, 'samples': 11499008, 'steps': 22458, 'loss/train': 1.4814116954803467}
-03/04/2022 15:50:39 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 15:50:43 - INFO - codeparrot_training - Step 22459: {'lr': 0.0004767930184651187, 'samples': 11499520, 'steps': 22459, 'loss/train': 1.1676796674728394}
-03/04/2022 15:50:47 - INFO - codeparrot_training - Step 22460: {'lr': 0.0004767907855492134, 'samples': 11500032, 'steps': 22460, 'loss/train': 1.2024859189987183}
-03/04/2022 15:50:47 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/04/2022 15:50:52 - INFO - codeparrot_training - Step 22461: {'lr': 0.0004767885525311197, 'samples': 11500544, 'steps': 22461, 'loss/train': 1.7455363273620605}
-03/04/2022 15:50:55 - INFO - codeparrot_training - Step 22462: {'lr': 0.0004767863194108386, 'samples': 11501056, 'steps': 22462, 'loss/train': 1.544686198234558}
-03/04/2022 15:50:56 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/04/2022 15:51:01 - INFO - codeparrot_training - Step 22463: {'lr': 0.000476784086188371, 'samples': 11501568, 'steps': 22463, 'loss/train': 3.3219072818756104}
-03/04/2022 15:51:04 - INFO - codeparrot_training - Step 22464: {'lr': 0.00047678185286371803, 'samples': 11502080, 'steps': 22464, 'loss/train': 1.7140549421310425}
-03/04/2022 15:51:06 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/04/2022 15:51:09 - INFO - codeparrot_training - Step 22465: {'lr': 0.0004767796194368807, 'samples': 11502592, 'steps': 22465, 'loss/train': 1.0810924768447876}
-03/04/2022 15:51:12 - INFO - codeparrot_training - Step 22466: {'lr': 0.00047677738590786, 'samples': 11503104, 'steps': 22466, 'loss/train': 1.381034255027771}
-03/04/2022 15:51:15 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/04/2022 15:51:18 - INFO - codeparrot_training - Step 22467: {'lr': 0.0004767751522766568, 'samples': 11503616, 'steps': 22467, 'loss/train': 2.795308828353882}
-03/04/2022 15:51:21 - INFO - codeparrot_training - Step 22468: {'lr': 0.00047677291854327224, 'samples': 11504128, 'steps': 22468, 'loss/train': 2.104806423187256}
-03/04/2022 15:51:23 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/04/2022 15:51:26 - INFO - codeparrot_training - Step 22469: {'lr': 0.00047677068470770737, 'samples': 11504640, 'steps': 22469, 'loss/train': 1.9409903287887573}
-03/04/2022 15:51:29 - INFO - codeparrot_training - Step 22470: {'lr': 0.00047676845076996305, 'samples': 11505152, 'steps': 22470, 'loss/train': 1.545997142791748}
-03/04/2022 15:51:32 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/04/2022 15:51:34 - INFO - codeparrot_training - Step 22471: {'lr': 0.0004767662167300404, 'samples': 11505664, 'steps': 22471, 'loss/train': 2.5562846660614014}
-03/04/2022 15:51:38 - INFO - codeparrot_training - Step 22472: {'lr': 0.0004767639825879404, 'samples': 11506176, 'steps': 22472, 'loss/train': 3.3168678283691406}
-03/04/2022 15:51:40 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 15:51:43 - INFO - codeparrot_training - Step 22473: {'lr': 0.000476761748343664, 'samples': 11506688, 'steps': 22473, 'loss/train': 4.830148696899414}
-03/04/2022 15:51:46 - INFO - codeparrot_training - Step 22474: {'lr': 0.00047675951399721235, 'samples': 11507200, 'steps': 22474, 'loss/train': 1.583141803741455}
-03/04/2022 15:51:49 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 15:51:51 - INFO - codeparrot_training - Step 22475: {'lr': 0.0004767572795485863, 'samples': 11507712, 'steps': 22475, 'loss/train': 1.974922776222229}
-03/04/2022 15:51:55 - INFO - codeparrot_training - Step 22476: {'lr': 0.00047675504499778695, 'samples': 11508224, 'steps': 22476, 'loss/train': 2.2848598957061768}
-03/04/2022 15:51:57 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/04/2022 15:52:00 - INFO - codeparrot_training - Step 22477: {'lr': 0.0004767528103448152, 'samples': 11508736, 'steps': 22477, 'loss/train': 2.3041112422943115}
-03/04/2022 15:52:03 - INFO - codeparrot_training - Step 22478: {'lr': 0.00047675057558967224, 'samples': 11509248, 'steps': 22478, 'loss/train': 1.721275806427002}
-03/04/2022 15:52:06 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 15:52:08 - INFO - codeparrot_training - Step 22479: {'lr': 0.0004767483407323589, 'samples': 11509760, 'steps': 22479, 'loss/train': 0.6822611093521118}
-03/04/2022 15:52:12 - INFO - codeparrot_training - Step 22480: {'lr': 0.00047674610577287625, 'samples': 11510272, 'steps': 22480, 'loss/train': 1.825452446937561}
-03/04/2022 15:52:14 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/04/2022 15:52:17 - INFO - codeparrot_training - Step 22481: {'lr': 0.00047674387071122536, 'samples': 11510784, 'steps': 22481, 'loss/train': 1.6028469800949097}
-03/04/2022 15:52:20 - INFO - codeparrot_training - Step 22482: {'lr': 0.0004767416355474071, 'samples': 11511296, 'steps': 22482, 'loss/train': 2.698817253112793}
-03/04/2022 15:52:23 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/04/2022 15:52:25 - INFO - codeparrot_training - Step 22483: {'lr': 0.00047673940028142265, 'samples': 11511808, 'steps': 22483, 'loss/train': 1.3137794733047485}
-03/04/2022 15:52:28 - INFO - codeparrot_training - Step 22484: {'lr': 0.0004767371649132729, 'samples': 11512320, 'steps': 22484, 'loss/train': 2.040895700454712}
-03/04/2022 15:52:32 - INFO - codeparrot_training - Step 22485: {'lr': 0.00047673492944295883, 'samples': 11512832, 'steps': 22485, 'loss/train': 6.617819309234619}
-03/04/2022 15:52:32 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 15:52:37 - INFO - codeparrot_training - Step 22486: {'lr': 0.0004767326938704816, 'samples': 11513344, 'steps': 22486, 'loss/train': 1.1397531032562256}
-03/04/2022 15:52:40 - INFO - codeparrot_training - Step 22487: {'lr': 0.00047673045819584197, 'samples': 11513856, 'steps': 22487, 'loss/train': 2.2056562900543213}
-03/04/2022 15:52:40 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 15:52:45 - INFO - codeparrot_training - Step 22488: {'lr': 0.0004767282224190412, 'samples': 11514368, 'steps': 22488, 'loss/train': 2.1432173252105713}
-03/04/2022 15:52:48 - INFO - codeparrot_training - Step 22489: {'lr': 0.00047672598654008015, 'samples': 11514880, 'steps': 22489, 'loss/train': 2.137909412384033}
-03/04/2022 15:52:49 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/04/2022 15:52:54 - INFO - codeparrot_training - Step 22490: {'lr': 0.0004767237505589599, 'samples': 11515392, 'steps': 22490, 'loss/train': 1.5522429943084717}
-03/04/2022 15:52:57 - INFO - codeparrot_training - Step 22491: {'lr': 0.0004767215144756814, 'samples': 11515904, 'steps': 22491, 'loss/train': 1.896788239479065}
-03/04/2022 15:52:57 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 15:53:02 - INFO - codeparrot_training - Step 22492: {'lr': 0.0004767192782902457, 'samples': 11516416, 'steps': 22492, 'loss/train': 2.0163357257843018}
-03/04/2022 15:53:05 - INFO - codeparrot_training - Step 22493: {'lr': 0.0004767170420026538, 'samples': 11516928, 'steps': 22493, 'loss/train': 1.80930495262146}
-03/04/2022 15:53:05 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 15:53:11 - INFO - codeparrot_training - Step 22494: {'lr': 0.0004767148056129067, 'samples': 11517440, 'steps': 22494, 'loss/train': 2.143876552581787}
-03/04/2022 15:53:14 - INFO - codeparrot_training - Step 22495: {'lr': 0.0004767125691210054, 'samples': 11517952, 'steps': 22495, 'loss/train': 2.2034823894500732}
-03/04/2022 15:53:14 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/04/2022 15:53:19 - INFO - codeparrot_training - Step 22496: {'lr': 0.00047671033252695083, 'samples': 11518464, 'steps': 22496, 'loss/train': 1.6189838647842407}
-03/04/2022 15:53:22 - INFO - codeparrot_training - Step 22497: {'lr': 0.0004767080958307442, 'samples': 11518976, 'steps': 22497, 'loss/train': 0.9233405590057373}
-03/04/2022 15:53:23 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 15:53:27 - INFO - codeparrot_training - Step 22498: {'lr': 0.0004767058590323864, 'samples': 11519488, 'steps': 22498, 'loss/train': 2.3180761337280273}
-03/04/2022 15:53:31 - INFO - codeparrot_training - Step 22499: {'lr': 0.00047670362213187833, 'samples': 11520000, 'steps': 22499, 'loss/train': 1.8340678215026855}
-03/04/2022 15:53:31 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/04/2022 15:53:36 - INFO - codeparrot_training - Step 22500: {'lr': 0.0004767013851292212, 'samples': 11520512, 'steps': 22500, 'loss/train': 1.3954896926879883}
-03/04/2022 15:53:39 - INFO - codeparrot_training - Step 22501: {'lr': 0.0004766991480244159, 'samples': 11521024, 'steps': 22501, 'loss/train': 1.6389615535736084}
-03/04/2022 15:53:40 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/04/2022 15:53:44 - INFO - codeparrot_training - Step 22502: {'lr': 0.0004766969108174635, 'samples': 11521536, 'steps': 22502, 'loss/train': 1.53696608543396}
-03/04/2022 15:53:48 - INFO - codeparrot_training - Step 22503: {'lr': 0.0004766946735083649, 'samples': 11522048, 'steps': 22503, 'loss/train': 5.497185230255127}
-03/04/2022 15:53:48 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/04/2022 15:53:53 - INFO - codeparrot_training - Step 22504: {'lr': 0.0004766924360971212, 'samples': 11522560, 'steps': 22504, 'loss/train': 2.12186598777771}
-03/04/2022 15:53:56 - INFO - codeparrot_training - Step 22505: {'lr': 0.00047669019858373343, 'samples': 11523072, 'steps': 22505, 'loss/train': 2.363293409347534}
-03/04/2022 15:53:58 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 15:54:01 - INFO - codeparrot_training - Step 22506: {'lr': 0.00047668796096820247, 'samples': 11523584, 'steps': 22506, 'loss/train': 0.5293604731559753}
-03/04/2022 15:54:05 - INFO - codeparrot_training - Step 22507: {'lr': 0.00047668572325052953, 'samples': 11524096, 'steps': 22507, 'loss/train': 1.743024230003357}
-03/04/2022 15:54:06 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/04/2022 15:54:10 - INFO - codeparrot_training - Step 22508: {'lr': 0.00047668348543071536, 'samples': 11524608, 'steps': 22508, 'loss/train': 1.6122633218765259}
-03/04/2022 15:54:13 - INFO - codeparrot_training - Step 22509: {'lr': 0.00047668124750876117, 'samples': 11525120, 'steps': 22509, 'loss/train': 2.0255401134490967}
-03/04/2022 15:54:14 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/04/2022 15:54:18 - INFO - codeparrot_training - Step 22510: {'lr': 0.0004766790094846679, 'samples': 11525632, 'steps': 22510, 'loss/train': 2.4109208583831787}
-03/04/2022 15:54:21 - INFO - codeparrot_training - Step 22511: {'lr': 0.0004766767713584367, 'samples': 11526144, 'steps': 22511, 'loss/train': 2.465013265609741}
-03/04/2022 15:54:23 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/04/2022 15:54:27 - INFO - codeparrot_training - Step 22512: {'lr': 0.00047667453313006826, 'samples': 11526656, 'steps': 22512, 'loss/train': 1.4937057495117188}
-03/04/2022 15:54:30 - INFO - codeparrot_training - Step 22513: {'lr': 0.00047667229479956386, 'samples': 11527168, 'steps': 22513, 'loss/train': 1.3148878812789917}
-03/04/2022 15:54:31 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/04/2022 15:54:35 - INFO - codeparrot_training - Step 22514: {'lr': 0.0004766700563669244, 'samples': 11527680, 'steps': 22514, 'loss/train': 1.7674264907836914}
-03/04/2022 15:54:38 - INFO - codeparrot_training - Step 22515: {'lr': 0.0004766678178321509, 'samples': 11528192, 'steps': 22515, 'loss/train': 1.6861134767532349}
-03/04/2022 15:54:40 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 15:54:44 - INFO - codeparrot_training - Step 22516: {'lr': 0.0004766655791952444, 'samples': 11528704, 'steps': 22516, 'loss/train': 2.0013840198516846}
-03/04/2022 15:54:47 - INFO - codeparrot_training - Step 22517: {'lr': 0.0004766633404562059, 'samples': 11529216, 'steps': 22517, 'loss/train': 1.7278904914855957}
-03/04/2022 15:54:48 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/04/2022 15:54:52 - INFO - codeparrot_training - Step 22518: {'lr': 0.0004766611016150364, 'samples': 11529728, 'steps': 22518, 'loss/train': 1.906418800354004}
-03/04/2022 15:54:55 - INFO - codeparrot_training - Step 22519: {'lr': 0.00047665886267173686, 'samples': 11530240, 'steps': 22519, 'loss/train': 2.3232064247131348}
-03/04/2022 15:54:57 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 15:55:01 - INFO - codeparrot_training - Step 22520: {'lr': 0.00047665662362630836, 'samples': 11530752, 'steps': 22520, 'loss/train': 1.5617451667785645}
-03/04/2022 15:55:04 - INFO - codeparrot_training - Step 22521: {'lr': 0.00047665438447875186, 'samples': 11531264, 'steps': 22521, 'loss/train': 1.9652162790298462}
-03/04/2022 15:55:06 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 15:55:09 - INFO - codeparrot_training - Step 22522: {'lr': 0.0004766521452290684, 'samples': 11531776, 'steps': 22522, 'loss/train': 2.05790376663208}
-03/04/2022 15:55:12 - INFO - codeparrot_training - Step 22523: {'lr': 0.00047664990587725905, 'samples': 11532288, 'steps': 22523, 'loss/train': 2.624528169631958}
-03/04/2022 15:55:14 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/04/2022 15:55:17 - INFO - codeparrot_training - Step 22524: {'lr': 0.0004766476664233247, 'samples': 11532800, 'steps': 22524, 'loss/train': 1.4314969778060913}
-03/04/2022 15:55:21 - INFO - codeparrot_training - Step 22525: {'lr': 0.0004766454268672664, 'samples': 11533312, 'steps': 22525, 'loss/train': 1.3567208051681519}
-03/04/2022 15:55:22 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 15:55:26 - INFO - codeparrot_training - Step 22526: {'lr': 0.00047664318720908516, 'samples': 11533824, 'steps': 22526, 'loss/train': 1.8593688011169434}
-03/04/2022 15:55:29 - INFO - codeparrot_training - Step 22527: {'lr': 0.000476640947448782, 'samples': 11534336, 'steps': 22527, 'loss/train': 1.9574041366577148}
-03/04/2022 15:55:32 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 15:55:34 - INFO - codeparrot_training - Step 22528: {'lr': 0.000476638707586358, 'samples': 11534848, 'steps': 22528, 'loss/train': 2.1821541786193848}
-03/04/2022 15:55:38 - INFO - codeparrot_training - Step 22529: {'lr': 0.000476636467621814, 'samples': 11535360, 'steps': 22529, 'loss/train': 2.1727144718170166}
-03/04/2022 15:55:40 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 15:55:43 - INFO - codeparrot_training - Step 22530: {'lr': 0.00047663422755515113, 'samples': 11535872, 'steps': 22530, 'loss/train': 1.0078575611114502}
-03/04/2022 15:55:46 - INFO - codeparrot_training - Step 22531: {'lr': 0.00047663198738637035, 'samples': 11536384, 'steps': 22531, 'loss/train': 2.5753650665283203}
-03/04/2022 15:55:49 - INFO - codeparrot_training - Step 22532: {'lr': 0.00047662974711547274, 'samples': 11536896, 'steps': 22532, 'loss/train': 1.5151337385177612}
-03/04/2022 15:55:50 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/04/2022 15:55:55 - INFO - codeparrot_training - Step 22533: {'lr': 0.0004766275067424593, 'samples': 11537408, 'steps': 22533, 'loss/train': 1.4739265441894531}
-03/04/2022 15:55:58 - INFO - codeparrot_training - Step 22534: {'lr': 0.0004766252662673309, 'samples': 11537920, 'steps': 22534, 'loss/train': 0.5902225971221924}
-03/04/2022 15:55:58 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 15:56:03 - INFO - codeparrot_training - Step 22535: {'lr': 0.0004766230256900887, 'samples': 11538432, 'steps': 22535, 'loss/train': 1.6894992589950562}
-03/04/2022 15:56:06 - INFO - codeparrot_training - Step 22536: {'lr': 0.0004766207850107337, 'samples': 11538944, 'steps': 22536, 'loss/train': 1.088456153869629}
-03/04/2022 15:56:07 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 15:56:12 - INFO - codeparrot_training - Step 22537: {'lr': 0.00047661854422926674, 'samples': 11539456, 'steps': 22537, 'loss/train': 1.5934957265853882}
-03/04/2022 15:56:15 - INFO - codeparrot_training - Step 22538: {'lr': 0.0004766163033456891, 'samples': 11539968, 'steps': 22538, 'loss/train': 2.377973794937134}
-03/04/2022 15:56:15 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/04/2022 15:56:20 - INFO - codeparrot_training - Step 22539: {'lr': 0.0004766140623600016, 'samples': 11540480, 'steps': 22539, 'loss/train': 1.418641448020935}
-03/04/2022 15:56:24 - INFO - codeparrot_training - Step 22540: {'lr': 0.0004766118212722053, 'samples': 11540992, 'steps': 22540, 'loss/train': 2.613971710205078}
-03/04/2022 15:56:24 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 15:56:29 - INFO - codeparrot_training - Step 22541: {'lr': 0.0004766095800823013, 'samples': 11541504, 'steps': 22541, 'loss/train': 1.6881815195083618}
-03/04/2022 15:56:32 - INFO - codeparrot_training - Step 22542: {'lr': 0.0004766073387902904, 'samples': 11542016, 'steps': 22542, 'loss/train': 2.552833080291748}
-03/04/2022 15:56:32 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/04/2022 15:56:37 - INFO - codeparrot_training - Step 22543: {'lr': 0.00047660509739617376, 'samples': 11542528, 'steps': 22543, 'loss/train': 1.949157953262329}
-03/04/2022 15:56:40 - INFO - codeparrot_training - Step 22544: {'lr': 0.00047660285589995233, 'samples': 11543040, 'steps': 22544, 'loss/train': 3.074531078338623}
-03/04/2022 15:56:40 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/04/2022 15:56:46 - INFO - codeparrot_training - Step 22545: {'lr': 0.0004766006143016272, 'samples': 11543552, 'steps': 22545, 'loss/train': 0.4609377980232239}
-03/04/2022 15:56:49 - INFO - codeparrot_training - Step 22546: {'lr': 0.0004765983726011993, 'samples': 11544064, 'steps': 22546, 'loss/train': 1.9356595277786255}
-03/04/2022 15:56:49 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/04/2022 15:56:54 - INFO - codeparrot_training - Step 22547: {'lr': 0.0004765961307986697, 'samples': 11544576, 'steps': 22547, 'loss/train': 1.354476809501648}
-03/04/2022 15:56:57 - INFO - codeparrot_training - Step 22548: {'lr': 0.0004765938888940393, 'samples': 11545088, 'steps': 22548, 'loss/train': 2.055955171585083}
-03/04/2022 15:56:58 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 15:57:03 - INFO - codeparrot_training - Step 22549: {'lr': 0.00047659164688730935, 'samples': 11545600, 'steps': 22549, 'loss/train': 0.9884545207023621}
-03/04/2022 15:57:06 - INFO - codeparrot_training - Step 22550: {'lr': 0.00047658940477848056, 'samples': 11546112, 'steps': 22550, 'loss/train': 1.931716799736023}
-03/04/2022 15:57:07 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/04/2022 15:57:11 - INFO - codeparrot_training - Step 22551: {'lr': 0.00047658716256755414, 'samples': 11546624, 'steps': 22551, 'loss/train': 1.811279296875}
-03/04/2022 15:57:14 - INFO - codeparrot_training - Step 22552: {'lr': 0.00047658492025453106, 'samples': 11547136, 'steps': 22552, 'loss/train': 1.874588966369629}
-03/04/2022 15:57:16 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 15:57:20 - INFO - codeparrot_training - Step 22553: {'lr': 0.00047658267783941223, 'samples': 11547648, 'steps': 22553, 'loss/train': 1.7483720779418945}
-03/04/2022 15:57:23 - INFO - codeparrot_training - Step 22554: {'lr': 0.0004765804353221988, 'samples': 11548160, 'steps': 22554, 'loss/train': 2.398430585861206}
-03/04/2022 15:57:24 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 15:57:28 - INFO - codeparrot_training - Step 22555: {'lr': 0.0004765781927028917, 'samples': 11548672, 'steps': 22555, 'loss/train': 1.5815105438232422}
-03/04/2022 15:57:31 - INFO - codeparrot_training - Step 22556: {'lr': 0.000476575949981492, 'samples': 11549184, 'steps': 22556, 'loss/train': 1.9444653987884521}
-03/04/2022 15:57:33 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/04/2022 15:57:36 - INFO - codeparrot_training - Step 22557: {'lr': 0.00047657370715800066, 'samples': 11549696, 'steps': 22557, 'loss/train': 2.27104115486145}
-03/04/2022 15:57:40 - INFO - codeparrot_training - Step 22558: {'lr': 0.0004765714642324187, 'samples': 11550208, 'steps': 22558, 'loss/train': 2.0951380729675293}
-03/04/2022 15:57:41 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/04/2022 15:57:45 - INFO - codeparrot_training - Step 22559: {'lr': 0.0004765692212047471, 'samples': 11550720, 'steps': 22559, 'loss/train': 0.9666503071784973}
-03/04/2022 15:57:48 - INFO - codeparrot_training - Step 22560: {'lr': 0.00047656697807498693, 'samples': 11551232, 'steps': 22560, 'loss/train': 1.8167030811309814}
-03/04/2022 15:57:50 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/04/2022 15:57:54 - INFO - codeparrot_training - Step 22561: {'lr': 0.0004765647348431392, 'samples': 11551744, 'steps': 22561, 'loss/train': 1.4436991214752197}
-03/04/2022 15:57:57 - INFO - codeparrot_training - Step 22562: {'lr': 0.00047656249150920485, 'samples': 11552256, 'steps': 22562, 'loss/train': 2.581723213195801}
-03/04/2022 15:57:58 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/04/2022 15:58:02 - INFO - codeparrot_training - Step 22563: {'lr': 0.000476560248073185, 'samples': 11552768, 'steps': 22563, 'loss/train': 2.346001386642456}
-03/04/2022 15:58:05 - INFO - codeparrot_training - Step 22564: {'lr': 0.0004765580045350805, 'samples': 11553280, 'steps': 22564, 'loss/train': 1.369173526763916}
-03/04/2022 15:58:07 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 15:58:10 - INFO - codeparrot_training - Step 22565: {'lr': 0.00047655576089489254, 'samples': 11553792, 'steps': 22565, 'loss/train': 1.4972577095031738}
-03/04/2022 15:58:14 - INFO - codeparrot_training - Step 22566: {'lr': 0.00047655351715262205, 'samples': 11554304, 'steps': 22566, 'loss/train': 1.991624116897583}
-03/04/2022 15:58:15 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/04/2022 15:58:19 - INFO - codeparrot_training - Step 22567: {'lr': 0.00047655127330827, 'samples': 11554816, 'steps': 22567, 'loss/train': 1.6280491352081299}
-03/04/2022 15:58:22 - INFO - codeparrot_training - Step 22568: {'lr': 0.00047654902936183745, 'samples': 11555328, 'steps': 22568, 'loss/train': 1.8660573959350586}
-03/04/2022 15:58:24 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/04/2022 15:58:27 - INFO - codeparrot_training - Step 22569: {'lr': 0.00047654678531332544, 'samples': 11555840, 'steps': 22569, 'loss/train': 1.9200700521469116}
-03/04/2022 15:58:30 - INFO - codeparrot_training - Step 22570: {'lr': 0.00047654454116273493, 'samples': 11556352, 'steps': 22570, 'loss/train': 2.5916576385498047}
-03/04/2022 15:58:32 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/04/2022 15:58:36 - INFO - codeparrot_training - Step 22571: {'lr': 0.0004765422969100669, 'samples': 11556864, 'steps': 22571, 'loss/train': 1.3937246799468994}
-03/04/2022 15:58:39 - INFO - codeparrot_training - Step 22572: {'lr': 0.00047654005255532247, 'samples': 11557376, 'steps': 22572, 'loss/train': 2.65877628326416}
-03/04/2022 15:58:41 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/04/2022 15:58:44 - INFO - codeparrot_training - Step 22573: {'lr': 0.0004765378080985026, 'samples': 11557888, 'steps': 22573, 'loss/train': 1.0780423879623413}
-03/04/2022 15:58:47 - INFO - codeparrot_training - Step 22574: {'lr': 0.00047653556353960825, 'samples': 11558400, 'steps': 22574, 'loss/train': 1.8875901699066162}
-03/04/2022 15:58:49 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/04/2022 15:58:53 - INFO - codeparrot_training - Step 22575: {'lr': 0.0004765333188786404, 'samples': 11558912, 'steps': 22575, 'loss/train': 2.4469127655029297}
-03/04/2022 15:58:56 - INFO - codeparrot_training - Step 22576: {'lr': 0.00047653107411560025, 'samples': 11559424, 'steps': 22576, 'loss/train': 1.5975571870803833}
-03/04/2022 15:58:57 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 15:59:01 - INFO - codeparrot_training - Step 22577: {'lr': 0.00047652882925048863, 'samples': 11559936, 'steps': 22577, 'loss/train': 2.0104424953460693}
-03/04/2022 15:59:04 - INFO - codeparrot_training - Step 22578: {'lr': 0.00047652658428330664, 'samples': 11560448, 'steps': 22578, 'loss/train': 1.6819692850112915}
-03/04/2022 15:59:06 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 15:59:10 - INFO - codeparrot_training - Step 22579: {'lr': 0.00047652433921405526, 'samples': 11560960, 'steps': 22579, 'loss/train': 2.1550815105438232}
-03/04/2022 15:59:13 - INFO - codeparrot_training - Step 22580: {'lr': 0.0004765220940427355, 'samples': 11561472, 'steps': 22580, 'loss/train': 1.942596197128296}
-03/04/2022 15:59:15 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 15:59:18 - INFO - codeparrot_training - Step 22581: {'lr': 0.0004765198487693484, 'samples': 11561984, 'steps': 22581, 'loss/train': 2.454638719558716}
-03/04/2022 15:59:21 - INFO - codeparrot_training - Step 22582: {'lr': 0.00047651760339389494, 'samples': 11562496, 'steps': 22582, 'loss/train': 1.1270755529403687}
-03/04/2022 15:59:23 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/04/2022 15:59:27 - INFO - codeparrot_training - Step 22583: {'lr': 0.0004765153579163761, 'samples': 11563008, 'steps': 22583, 'loss/train': 1.6555266380310059}
-03/04/2022 15:59:30 - INFO - codeparrot_training - Step 22584: {'lr': 0.000476513112336793, 'samples': 11563520, 'steps': 22584, 'loss/train': 1.6461373567581177}
-03/04/2022 15:59:32 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/04/2022 15:59:35 - INFO - codeparrot_training - Step 22585: {'lr': 0.00047651086665514655, 'samples': 11564032, 'steps': 22585, 'loss/train': 1.7901215553283691}
-03/04/2022 15:59:38 - INFO - codeparrot_training - Step 22586: {'lr': 0.00047650862087143787, 'samples': 11564544, 'steps': 22586, 'loss/train': 1.8084999322891235}
-03/04/2022 15:59:40 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 15:59:44 - INFO - codeparrot_training - Step 22587: {'lr': 0.0004765063749856678, 'samples': 11565056, 'steps': 22587, 'loss/train': 1.0192201137542725}
-03/04/2022 15:59:47 - INFO - codeparrot_training - Step 22588: {'lr': 0.00047650412899783747, 'samples': 11565568, 'steps': 22588, 'loss/train': 2.1669023036956787}
-03/04/2022 15:59:49 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/04/2022 15:59:52 - INFO - codeparrot_training - Step 22589: {'lr': 0.0004765018829079479, 'samples': 11566080, 'steps': 22589, 'loss/train': 2.085214376449585}
-03/04/2022 15:59:55 - INFO - codeparrot_training - Step 22590: {'lr': 0.0004764996367160001, 'samples': 11566592, 'steps': 22590, 'loss/train': 2.2782580852508545}
-03/04/2022 15:59:58 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/04/2022 16:00:00 - INFO - codeparrot_training - Step 22591: {'lr': 0.000476497390421995, 'samples': 11567104, 'steps': 22591, 'loss/train': 1.7893284559249878}
-03/04/2022 16:00:04 - INFO - codeparrot_training - Step 22592: {'lr': 0.00047649514402593377, 'samples': 11567616, 'steps': 22592, 'loss/train': 1.5248842239379883}
-03/04/2022 16:00:06 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/04/2022 16:00:09 - INFO - codeparrot_training - Step 22593: {'lr': 0.0004764928975278172, 'samples': 11568128, 'steps': 22593, 'loss/train': 0.3378801941871643}
-03/04/2022 16:00:12 - INFO - codeparrot_training - Step 22594: {'lr': 0.0004764906509276465, 'samples': 11568640, 'steps': 22594, 'loss/train': 2.554926872253418}
-03/04/2022 16:00:14 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/04/2022 16:00:17 - INFO - codeparrot_training - Step 22595: {'lr': 0.0004764884042254226, 'samples': 11569152, 'steps': 22595, 'loss/train': 1.769107699394226}
-03/04/2022 16:00:21 - INFO - codeparrot_training - Step 22596: {'lr': 0.0004764861574211465, 'samples': 11569664, 'steps': 22596, 'loss/train': 1.8507225513458252}
-03/04/2022 16:00:23 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/04/2022 16:00:26 - INFO - codeparrot_training - Step 22597: {'lr': 0.0004764839105148193, 'samples': 11570176, 'steps': 22597, 'loss/train': 1.958627462387085}
-03/04/2022 16:00:29 - INFO - codeparrot_training - Step 22598: {'lr': 0.00047648166350644185, 'samples': 11570688, 'steps': 22598, 'loss/train': 2.347872257232666}
-03/04/2022 16:00:32 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 16:00:34 - INFO - codeparrot_training - Step 22599: {'lr': 0.00047647941639601535, 'samples': 11571200, 'steps': 22599, 'loss/train': 1.5985592603683472}
-03/04/2022 16:00:37 - INFO - codeparrot_training - Step 22600: {'lr': 0.00047647716918354066, 'samples': 11571712, 'steps': 22600, 'loss/train': 1.9171409606933594}
-03/04/2022 16:00:40 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/04/2022 16:00:43 - INFO - codeparrot_training - Step 22601: {'lr': 0.00047647492186901884, 'samples': 11572224, 'steps': 22601, 'loss/train': 1.7307279109954834}
-03/04/2022 16:00:46 - INFO - codeparrot_training - Step 22602: {'lr': 0.0004764726744524509, 'samples': 11572736, 'steps': 22602, 'loss/train': 2.0675957202911377}
-03/04/2022 16:00:49 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/04/2022 16:00:51 - INFO - codeparrot_training - Step 22603: {'lr': 0.0004764704269338379, 'samples': 11573248, 'steps': 22603, 'loss/train': 2.919102907180786}
-03/04/2022 16:00:54 - INFO - codeparrot_training - Step 22604: {'lr': 0.00047646817931318086, 'samples': 11573760, 'steps': 22604, 'loss/train': 1.592376947402954}
-03/04/2022 16:00:57 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/04/2022 16:01:00 - INFO - codeparrot_training - Step 22605: {'lr': 0.0004764659315904807, 'samples': 11574272, 'steps': 22605, 'loss/train': 1.4732460975646973}
-03/04/2022 16:01:03 - INFO - codeparrot_training - Step 22606: {'lr': 0.0004764636837657385, 'samples': 11574784, 'steps': 22606, 'loss/train': 0.3842104971408844}
-03/04/2022 16:01:05 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/04/2022 16:01:08 - INFO - codeparrot_training - Step 22607: {'lr': 0.0004764614358389553, 'samples': 11575296, 'steps': 22607, 'loss/train': 2.1826395988464355}
-03/04/2022 16:01:11 - INFO - codeparrot_training - Step 22608: {'lr': 0.00047645918781013196, 'samples': 11575808, 'steps': 22608, 'loss/train': 2.3344006538391113}
-03/04/2022 16:01:14 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/04/2022 16:01:17 - INFO - codeparrot_training - Step 22609: {'lr': 0.0004764569396792697, 'samples': 11576320, 'steps': 22609, 'loss/train': 2.26448392868042}
-03/04/2022 16:01:20 - INFO - codeparrot_training - Step 22610: {'lr': 0.0004764546914463694, 'samples': 11576832, 'steps': 22610, 'loss/train': 1.5200139284133911}
-03/04/2022 16:01:23 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/04/2022 16:01:25 - INFO - codeparrot_training - Step 22611: {'lr': 0.0004764524431114321, 'samples': 11577344, 'steps': 22611, 'loss/train': 1.6231499910354614}
-03/04/2022 16:01:28 - INFO - codeparrot_training - Step 22612: {'lr': 0.0004764501946744589, 'samples': 11577856, 'steps': 22612, 'loss/train': 1.6300301551818848}
-03/04/2022 16:01:31 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 16:01:34 - INFO - codeparrot_training - Step 22613: {'lr': 0.00047644794613545065, 'samples': 11578368, 'steps': 22613, 'loss/train': 2.000049591064453}
-03/04/2022 16:01:37 - INFO - codeparrot_training - Step 22614: {'lr': 0.00047644569749440846, 'samples': 11578880, 'steps': 22614, 'loss/train': 2.1220104694366455}
-03/04/2022 16:01:39 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 16:01:42 - INFO - codeparrot_training - Step 22615: {'lr': 0.0004764434487513334, 'samples': 11579392, 'steps': 22615, 'loss/train': 2.661520004272461}
-03/04/2022 16:01:45 - INFO - codeparrot_training - Step 22616: {'lr': 0.00047644119990622637, 'samples': 11579904, 'steps': 22616, 'loss/train': 1.886074185371399}
-03/04/2022 16:01:48 - INFO - codeparrot_training - Step 22617: {'lr': 0.0004764389509590884, 'samples': 11580416, 'steps': 22617, 'loss/train': 1.822066307067871}
-03/04/2022 16:01:49 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/04/2022 16:01:54 - INFO - codeparrot_training - Step 22618: {'lr': 0.0004764367019099206, 'samples': 11580928, 'steps': 22618, 'loss/train': 1.6211234331130981}
-03/04/2022 16:01:57 - INFO - codeparrot_training - Step 22619: {'lr': 0.0004764344527587239, 'samples': 11581440, 'steps': 22619, 'loss/train': 1.3695306777954102}
-03/04/2022 16:01:57 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/04/2022 16:02:02 - INFO - codeparrot_training - Step 22620: {'lr': 0.00047643220350549934, 'samples': 11581952, 'steps': 22620, 'loss/train': 2.206536293029785}
-03/04/2022 16:02:05 - INFO - codeparrot_training - Step 22621: {'lr': 0.0004764299541502478, 'samples': 11582464, 'steps': 22621, 'loss/train': 1.4475903511047363}
-03/04/2022 16:02:05 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/04/2022 16:02:10 - INFO - codeparrot_training - Step 22622: {'lr': 0.0004764277046929706, 'samples': 11582976, 'steps': 22622, 'loss/train': 0.5897603631019592}
-03/04/2022 16:02:13 - INFO - codeparrot_training - Step 22623: {'lr': 0.00047642545513366843, 'samples': 11583488, 'steps': 22623, 'loss/train': 1.7979912757873535}
-03/04/2022 16:02:14 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/04/2022 16:02:19 - INFO - codeparrot_training - Step 22624: {'lr': 0.0004764232054723425, 'samples': 11584000, 'steps': 22624, 'loss/train': 3.314054489135742}
-03/04/2022 16:02:22 - INFO - codeparrot_training - Step 22625: {'lr': 0.0004764209557089938, 'samples': 11584512, 'steps': 22625, 'loss/train': 1.6141459941864014}
-03/04/2022 16:02:24 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/04/2022 16:02:28 - INFO - codeparrot_training - Step 22626: {'lr': 0.00047641870584362323, 'samples': 11585024, 'steps': 22626, 'loss/train': 2.0690886974334717}
-03/04/2022 16:02:31 - INFO - codeparrot_training - Step 22627: {'lr': 0.00047641645587623196, 'samples': 11585536, 'steps': 22627, 'loss/train': 1.6066988706588745}
-03/04/2022 16:02:35 - INFO - codeparrot_training - Step 22628: {'lr': 0.0004764142058068209, 'samples': 11586048, 'steps': 22628, 'loss/train': 2.2944929599761963}
-03/04/2022 16:02:36 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 16:02:40 - INFO - codeparrot_training - Step 22629: {'lr': 0.00047641195563539107, 'samples': 11586560, 'steps': 22629, 'loss/train': 1.8909772634506226}
-03/04/2022 16:02:43 - INFO - codeparrot_training - Step 22630: {'lr': 0.0004764097053619435, 'samples': 11587072, 'steps': 22630, 'loss/train': 2.3390133380889893}
-03/04/2022 16:02:44 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/04/2022 16:02:48 - INFO - codeparrot_training - Step 22631: {'lr': 0.00047640745498647925, 'samples': 11587584, 'steps': 22631, 'loss/train': 1.6426366567611694}
-03/04/2022 16:02:52 - INFO - codeparrot_training - Step 22632: {'lr': 0.00047640520450899926, 'samples': 11588096, 'steps': 22632, 'loss/train': 2.283498525619507}
-03/04/2022 16:02:54 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 16:02:57 - INFO - codeparrot_training - Step 22633: {'lr': 0.0004764029539295046, 'samples': 11588608, 'steps': 22633, 'loss/train': 1.8708990812301636}
-03/04/2022 16:03:00 - INFO - codeparrot_training - Step 22634: {'lr': 0.0004764007032479963, 'samples': 11589120, 'steps': 22634, 'loss/train': 2.1835198402404785}
-03/04/2022 16:03:02 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 16:03:05 - INFO - codeparrot_training - Step 22635: {'lr': 0.00047639845246447534, 'samples': 11589632, 'steps': 22635, 'loss/train': 1.0752500295639038}
-03/04/2022 16:03:09 - INFO - codeparrot_training - Step 22636: {'lr': 0.00047639620157894264, 'samples': 11590144, 'steps': 22636, 'loss/train': 0.21507570147514343}
-03/04/2022 16:03:11 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/04/2022 16:03:14 - INFO - codeparrot_training - Step 22637: {'lr': 0.00047639395059139936, 'samples': 11590656, 'steps': 22637, 'loss/train': 2.565269947052002}
-03/04/2022 16:03:17 - INFO - codeparrot_training - Step 22638: {'lr': 0.0004763916995018465, 'samples': 11591168, 'steps': 22638, 'loss/train': 1.5301684141159058}
-03/04/2022 16:03:19 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/04/2022 16:03:22 - INFO - codeparrot_training - Step 22639: {'lr': 0.00047638944831028497, 'samples': 11591680, 'steps': 22639, 'loss/train': 2.566046953201294}
-03/04/2022 16:03:25 - INFO - codeparrot_training - Step 22640: {'lr': 0.00047638719701671587, 'samples': 11592192, 'steps': 22640, 'loss/train': 1.4349173307418823}
-03/04/2022 16:03:28 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/04/2022 16:03:31 - INFO - codeparrot_training - Step 22641: {'lr': 0.00047638494562114015, 'samples': 11592704, 'steps': 22641, 'loss/train': 0.7630588412284851}
-03/04/2022 16:03:34 - INFO - codeparrot_training - Step 22642: {'lr': 0.0004763826941235589, 'samples': 11593216, 'steps': 22642, 'loss/train': 1.948015570640564}
-03/04/2022 16:03:36 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/04/2022 16:03:40 - INFO - codeparrot_training - Step 22643: {'lr': 0.00047638044252397313, 'samples': 11593728, 'steps': 22643, 'loss/train': 1.6665282249450684}
-03/04/2022 16:03:43 - INFO - codeparrot_training - Step 22644: {'lr': 0.0004763781908223838, 'samples': 11594240, 'steps': 22644, 'loss/train': 1.452444076538086}
-03/04/2022 16:03:46 - INFO - codeparrot_training - Step 22645: {'lr': 0.00047637593901879194, 'samples': 11594752, 'steps': 22645, 'loss/train': 3.2267260551452637}
-03/04/2022 16:03:49 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/04/2022 16:03:52 - INFO - codeparrot_training - Step 22646: {'lr': 0.00047637368711319863, 'samples': 11595264, 'steps': 22646, 'loss/train': 1.648328185081482}
-03/04/2022 16:03:55 - INFO - codeparrot_training - Step 22647: {'lr': 0.00047637143510560477, 'samples': 11595776, 'steps': 22647, 'loss/train': 2.0546798706054688}
-03/04/2022 16:03:58 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/04/2022 16:04:00 - INFO - codeparrot_training - Step 22648: {'lr': 0.0004763691829960114, 'samples': 11596288, 'steps': 22648, 'loss/train': 1.8836004734039307}
-03/04/2022 16:04:03 - INFO - codeparrot_training - Step 22649: {'lr': 0.00047636693078441963, 'samples': 11596800, 'steps': 22649, 'loss/train': 2.3728530406951904}
-03/04/2022 16:04:06 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 16:04:09 - INFO - codeparrot_training - Step 22650: {'lr': 0.0004763646784708304, 'samples': 11597312, 'steps': 22650, 'loss/train': 1.896786093711853}
-03/04/2022 16:04:12 - INFO - codeparrot_training - Step 22651: {'lr': 0.00047636242605524477, 'samples': 11597824, 'steps': 22651, 'loss/train': 1.9026237726211548}
-03/04/2022 16:04:15 - INFO - codeparrot_training - Step 22652: {'lr': 0.0004763601735376637, 'samples': 11598336, 'steps': 22652, 'loss/train': 0.977907121181488}
-03/04/2022 16:04:15 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 16:04:20 - INFO - codeparrot_training - Step 22653: {'lr': 0.0004763579209180882, 'samples': 11598848, 'steps': 22653, 'loss/train': 2.013745069503784}
-03/04/2022 16:04:23 - INFO - codeparrot_training - Step 22654: {'lr': 0.00047635566819651936, 'samples': 11599360, 'steps': 22654, 'loss/train': 1.9207147359848022}
-03/04/2022 16:04:29 - INFO - codeparrot_training - Step 22655: {'lr': 0.00047635341537295814, 'samples': 11599872, 'steps': 22655, 'loss/train': 1.819262981414795}
-03/04/2022 16:04:32 - INFO - codeparrot_training - Step 22656: {'lr': 0.0004763511624474055, 'samples': 11600384, 'steps': 22656, 'loss/train': 2.0213611125946045}
-03/04/2022 16:04:32 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/04/2022 16:04:37 - INFO - codeparrot_training - Step 22657: {'lr': 0.00047634890941986263, 'samples': 11600896, 'steps': 22657, 'loss/train': 2.116319179534912}
-03/04/2022 16:04:40 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/04/2022 16:04:43 - INFO - codeparrot_training - Step 22658: {'lr': 0.00047634665629033035, 'samples': 11601408, 'steps': 22658, 'loss/train': 1.5030882358551025}
-03/04/2022 16:04:46 - INFO - codeparrot_training - Step 22659: {'lr': 0.00047634440305880976, 'samples': 11601920, 'steps': 22659, 'loss/train': 1.4850702285766602}
-03/04/2022 16:04:48 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 16:04:51 - INFO - codeparrot_training - Step 22660: {'lr': 0.0004763421497253019, 'samples': 11602432, 'steps': 22660, 'loss/train': 1.2798643112182617}
-03/04/2022 16:04:54 - INFO - codeparrot_training - Step 22661: {'lr': 0.0004763398962898078, 'samples': 11602944, 'steps': 22661, 'loss/train': 2.254098415374756}
-03/04/2022 16:04:57 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 16:04:59 - INFO - codeparrot_training - Step 22662: {'lr': 0.0004763376427523284, 'samples': 11603456, 'steps': 22662, 'loss/train': 3.083556890487671}
-03/04/2022 16:05:02 - INFO - codeparrot_training - Step 22663: {'lr': 0.0004763353891128648, 'samples': 11603968, 'steps': 22663, 'loss/train': 0.16208121180534363}
-03/04/2022 16:05:05 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/04/2022 16:05:08 - INFO - codeparrot_training - Step 22664: {'lr': 0.00047633313537141786, 'samples': 11604480, 'steps': 22664, 'loss/train': 1.9340626001358032}
-03/04/2022 16:05:11 - INFO - codeparrot_training - Step 22665: {'lr': 0.00047633088152798875, 'samples': 11604992, 'steps': 22665, 'loss/train': 2.0426924228668213}
-03/04/2022 16:05:14 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 16:05:16 - INFO - codeparrot_training - Step 22666: {'lr': 0.00047632862758257845, 'samples': 11605504, 'steps': 22666, 'loss/train': 1.7117700576782227}
-03/04/2022 16:05:19 - INFO - codeparrot_training - Step 22667: {'lr': 0.0004763263735351879, 'samples': 11606016, 'steps': 22667, 'loss/train': 1.7728177309036255}
-03/04/2022 16:05:22 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/04/2022 16:05:25 - INFO - codeparrot_training - Step 22668: {'lr': 0.0004763241193858183, 'samples': 11606528, 'steps': 22668, 'loss/train': 1.4793943166732788}
-03/04/2022 16:05:28 - INFO - codeparrot_training - Step 22669: {'lr': 0.00047632186513447045, 'samples': 11607040, 'steps': 22669, 'loss/train': 2.451044797897339}
-03/04/2022 16:05:30 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 16:05:33 - INFO - codeparrot_training - Step 22670: {'lr': 0.0004763196107811455, 'samples': 11607552, 'steps': 22670, 'loss/train': 1.0946629047393799}
-03/04/2022 16:05:36 - INFO - codeparrot_training - Step 22671: {'lr': 0.0004763173563258444, 'samples': 11608064, 'steps': 22671, 'loss/train': 1.7203924655914307}
-03/04/2022 16:05:38 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 16:05:42 - INFO - codeparrot_training - Step 22672: {'lr': 0.0004763151017685682, 'samples': 11608576, 'steps': 22672, 'loss/train': 1.4023966789245605}
-03/04/2022 16:05:45 - INFO - codeparrot_training - Step 22673: {'lr': 0.0004763128471093179, 'samples': 11609088, 'steps': 22673, 'loss/train': 1.921789526939392}
-03/04/2022 16:05:47 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/04/2022 16:05:50 - INFO - codeparrot_training - Step 22674: {'lr': 0.0004763105923480946, 'samples': 11609600, 'steps': 22674, 'loss/train': 0.5169785618782043}
-03/04/2022 16:05:53 - INFO - codeparrot_training - Step 22675: {'lr': 0.0004763083374848991, 'samples': 11610112, 'steps': 22675, 'loss/train': 1.7987031936645508}
-03/04/2022 16:05:55 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/04/2022 16:05:59 - INFO - codeparrot_training - Step 22676: {'lr': 0.00047630608251973265, 'samples': 11610624, 'steps': 22676, 'loss/train': 1.7626670598983765}
-03/04/2022 16:06:02 - INFO - codeparrot_training - Step 22677: {'lr': 0.00047630382745259616, 'samples': 11611136, 'steps': 22677, 'loss/train': 1.9836996793746948}
-03/04/2022 16:06:05 - INFO - codeparrot_training - Step 22678: {'lr': 0.0004763015722834907, 'samples': 11611648, 'steps': 22678, 'loss/train': 2.206925392150879}
-03/04/2022 16:06:07 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/04/2022 16:06:10 - INFO - codeparrot_training - Step 22679: {'lr': 0.00047629931701241715, 'samples': 11612160, 'steps': 22679, 'loss/train': 1.5580421686172485}
-03/04/2022 16:06:14 - INFO - codeparrot_training - Step 22680: {'lr': 0.0004762970616393767, 'samples': 11612672, 'steps': 22680, 'loss/train': 2.068885087966919}
-03/04/2022 16:06:15 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/04/2022 16:06:19 - INFO - codeparrot_training - Step 22681: {'lr': 0.0004762948061643702, 'samples': 11613184, 'steps': 22681, 'loss/train': 2.1621265411376953}
-03/04/2022 16:06:22 - INFO - codeparrot_training - Step 22682: {'lr': 0.0004762925505873988, 'samples': 11613696, 'steps': 22682, 'loss/train': 1.8693995475769043}
-03/04/2022 16:06:24 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/04/2022 16:06:27 - INFO - codeparrot_training - Step 22683: {'lr': 0.00047629029490846346, 'samples': 11614208, 'steps': 22683, 'loss/train': 2.0313539505004883}
-03/04/2022 16:06:31 - INFO - codeparrot_training - Step 22684: {'lr': 0.00047628803912756523, 'samples': 11614720, 'steps': 22684, 'loss/train': 1.6997673511505127}
-03/04/2022 16:06:32 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/04/2022 16:06:36 - INFO - codeparrot_training - Step 22685: {'lr': 0.00047628578324470505, 'samples': 11615232, 'steps': 22685, 'loss/train': 1.9626903533935547}
-03/04/2022 16:06:39 - INFO - codeparrot_training - Step 22686: {'lr': 0.00047628352725988406, 'samples': 11615744, 'steps': 22686, 'loss/train': 1.327711820602417}
-03/04/2022 16:06:41 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/04/2022 16:06:44 - INFO - codeparrot_training - Step 22687: {'lr': 0.0004762812711731032, 'samples': 11616256, 'steps': 22687, 'loss/train': 2.008180618286133}
-03/04/2022 16:06:47 - INFO - codeparrot_training - Step 22688: {'lr': 0.00047627901498436344, 'samples': 11616768, 'steps': 22688, 'loss/train': 1.9528369903564453}
-03/04/2022 16:06:50 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 16:06:53 - INFO - codeparrot_training - Step 22689: {'lr': 0.0004762767586936658, 'samples': 11617280, 'steps': 22689, 'loss/train': 1.912990927696228}
-03/04/2022 16:06:56 - INFO - codeparrot_training - Step 22690: {'lr': 0.00047627450230101144, 'samples': 11617792, 'steps': 22690, 'loss/train': 2.3304872512817383}
-03/04/2022 16:06:58 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/04/2022 16:07:01 - INFO - codeparrot_training - Step 22691: {'lr': 0.0004762722458064013, 'samples': 11618304, 'steps': 22691, 'loss/train': 1.426804780960083}
-03/04/2022 16:07:04 - INFO - codeparrot_training - Step 22692: {'lr': 0.0004762699892098363, 'samples': 11618816, 'steps': 22692, 'loss/train': 1.1183570623397827}
-03/04/2022 16:07:06 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 16:07:10 - INFO - codeparrot_training - Step 22693: {'lr': 0.0004762677325113176, 'samples': 11619328, 'steps': 22693, 'loss/train': 1.8661285638809204}
-03/04/2022 16:07:13 - INFO - codeparrot_training - Step 22694: {'lr': 0.0004762654757108461, 'samples': 11619840, 'steps': 22694, 'loss/train': 1.5826612710952759}
-03/04/2022 16:07:15 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/04/2022 16:07:18 - INFO - codeparrot_training - Step 22695: {'lr': 0.00047626321880842287, 'samples': 11620352, 'steps': 22695, 'loss/train': 2.739610433578491}
-03/04/2022 16:07:21 - INFO - codeparrot_training - Step 22696: {'lr': 0.00047626096180404895, 'samples': 11620864, 'steps': 22696, 'loss/train': 2.1063945293426514}
-03/04/2022 16:07:23 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/04/2022 16:07:26 - INFO - codeparrot_training - Step 22697: {'lr': 0.0004762587046977253, 'samples': 11621376, 'steps': 22697, 'loss/train': 1.4844012260437012}
-03/04/2022 16:07:30 - INFO - codeparrot_training - Step 22698: {'lr': 0.000476256447489453, 'samples': 11621888, 'steps': 22698, 'loss/train': 2.2075445652008057}
-03/04/2022 16:07:31 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 16:07:35 - INFO - codeparrot_training - Step 22699: {'lr': 0.000476254190179233, 'samples': 11622400, 'steps': 22699, 'loss/train': 2.445279121398926}
-03/04/2022 16:07:38 - INFO - codeparrot_training - Step 22700: {'lr': 0.0004762519327670664, 'samples': 11622912, 'steps': 22700, 'loss/train': 0.778886079788208}
-03/04/2022 16:07:40 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/04/2022 16:07:44 - INFO - codeparrot_training - Step 22701: {'lr': 0.0004762496752529541, 'samples': 11623424, 'steps': 22701, 'loss/train': 1.7996127605438232}
-03/04/2022 16:07:47 - INFO - codeparrot_training - Step 22702: {'lr': 0.0004762474176368973, 'samples': 11623936, 'steps': 22702, 'loss/train': 1.610295295715332}
-03/04/2022 16:07:49 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/04/2022 16:07:52 - INFO - codeparrot_training - Step 22703: {'lr': 0.00047624515991889684, 'samples': 11624448, 'steps': 22703, 'loss/train': 1.8571619987487793}
-03/04/2022 16:07:55 - INFO - codeparrot_training - Step 22704: {'lr': 0.00047624290209895384, 'samples': 11624960, 'steps': 22704, 'loss/train': 1.5894479751586914}
-03/04/2022 16:07:58 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 16:08:00 - INFO - codeparrot_training - Step 22705: {'lr': 0.00047624064417706917, 'samples': 11625472, 'steps': 22705, 'loss/train': 2.102832555770874}
-03/04/2022 16:08:04 - INFO - codeparrot_training - Step 22706: {'lr': 0.00047623838615324407, 'samples': 11625984, 'steps': 22706, 'loss/train': 1.170867919921875}
-03/04/2022 16:08:06 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/04/2022 16:08:09 - INFO - codeparrot_training - Step 22707: {'lr': 0.0004762361280274794, 'samples': 11626496, 'steps': 22707, 'loss/train': 1.5442910194396973}
-03/04/2022 16:08:12 - INFO - codeparrot_training - Step 22708: {'lr': 0.0004762338697997762, 'samples': 11627008, 'steps': 22708, 'loss/train': 2.1116220951080322}
-03/04/2022 16:08:14 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/04/2022 16:08:17 - INFO - codeparrot_training - Step 22709: {'lr': 0.00047623161147013557, 'samples': 11627520, 'steps': 22709, 'loss/train': 1.5288029909133911}
-03/04/2022 16:08:20 - INFO - codeparrot_training - Step 22710: {'lr': 0.0004762293530385584, 'samples': 11628032, 'steps': 22710, 'loss/train': 1.672132134437561}
-03/04/2022 16:08:23 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/04/2022 16:08:26 - INFO - codeparrot_training - Step 22711: {'lr': 0.0004762270945050458, 'samples': 11628544, 'steps': 22711, 'loss/train': 1.8892134428024292}
-03/04/2022 16:08:29 - INFO - codeparrot_training - Step 22712: {'lr': 0.00047622483586959877, 'samples': 11629056, 'steps': 22712, 'loss/train': 1.66095769405365}
-03/04/2022 16:08:32 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 16:08:34 - INFO - codeparrot_training - Step 22713: {'lr': 0.00047622257713221826, 'samples': 11629568, 'steps': 22713, 'loss/train': 1.8577181100845337}
-03/04/2022 16:08:37 - INFO - codeparrot_training - Step 22714: {'lr': 0.00047622031829290545, 'samples': 11630080, 'steps': 22714, 'loss/train': 1.7829153537750244}
-03/04/2022 16:08:40 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 16:08:42 - INFO - codeparrot_training - Step 22715: {'lr': 0.0004762180593516612, 'samples': 11630592, 'steps': 22715, 'loss/train': 1.548112392425537}
-03/04/2022 16:08:46 - INFO - codeparrot_training - Step 22716: {'lr': 0.0004762158003084867, 'samples': 11631104, 'steps': 22716, 'loss/train': 1.9854425191879272}
-03/04/2022 16:08:48 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/04/2022 16:08:51 - INFO - codeparrot_training - Step 22717: {'lr': 0.0004762135411633827, 'samples': 11631616, 'steps': 22717, 'loss/train': 1.712017297744751}
-03/04/2022 16:08:54 - INFO - codeparrot_training - Step 22718: {'lr': 0.0004762112819163504, 'samples': 11632128, 'steps': 22718, 'loss/train': 2.221590518951416}
-03/04/2022 16:08:57 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/04/2022 16:08:59 - INFO - codeparrot_training - Step 22719: {'lr': 0.0004762090225673908, 'samples': 11632640, 'steps': 22719, 'loss/train': 2.351417303085327}
-03/04/2022 16:09:02 - INFO - codeparrot_training - Step 22720: {'lr': 0.0004762067631165049, 'samples': 11633152, 'steps': 22720, 'loss/train': 1.9199585914611816}
-03/04/2022 16:09:05 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/04/2022 16:09:08 - INFO - codeparrot_training - Step 22721: {'lr': 0.0004762045035636937, 'samples': 11633664, 'steps': 22721, 'loss/train': 1.9231112003326416}
-03/04/2022 16:09:11 - INFO - codeparrot_training - Step 22722: {'lr': 0.0004762022439089583, 'samples': 11634176, 'steps': 22722, 'loss/train': 2.0572171211242676}
-03/04/2022 16:09:13 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/04/2022 16:09:16 - INFO - codeparrot_training - Step 22723: {'lr': 0.0004761999841522996, 'samples': 11634688, 'steps': 22723, 'loss/train': 1.6132575273513794}
-03/04/2022 16:09:19 - INFO - codeparrot_training - Step 22724: {'lr': 0.0004761977242937188, 'samples': 11635200, 'steps': 22724, 'loss/train': 2.027494192123413}
-03/04/2022 16:09:22 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 16:09:25 - INFO - codeparrot_training - Step 22725: {'lr': 0.00047619546433321663, 'samples': 11635712, 'steps': 22725, 'loss/train': 1.6223715543746948}
-03/04/2022 16:09:28 - INFO - codeparrot_training - Step 22726: {'lr': 0.00047619320427079437, 'samples': 11636224, 'steps': 22726, 'loss/train': 1.6766353845596313}
-03/04/2022 16:09:30 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 16:09:33 - INFO - codeparrot_training - Step 22727: {'lr': 0.00047619094410645293, 'samples': 11636736, 'steps': 22727, 'loss/train': 1.3781834840774536}
-03/04/2022 16:09:36 - INFO - codeparrot_training - Step 22728: {'lr': 0.0004761886838401933, 'samples': 11637248, 'steps': 22728, 'loss/train': 1.0411885976791382}
-03/04/2022 16:09:39 - INFO - codeparrot_training - Step 22729: {'lr': 0.0004761864234720166, 'samples': 11637760, 'steps': 22729, 'loss/train': 2.4113283157348633}
-03/04/2022 16:09:40 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/04/2022 16:09:45 - INFO - codeparrot_training - Step 22730: {'lr': 0.00047618416300192375, 'samples': 11638272, 'steps': 22730, 'loss/train': 1.104407787322998}
-03/04/2022 16:09:48 - INFO - codeparrot_training - Step 22731: {'lr': 0.0004761819024299158, 'samples': 11638784, 'steps': 22731, 'loss/train': 2.0100302696228027}
-03/04/2022 16:09:48 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 16:09:53 - INFO - codeparrot_training - Step 22732: {'lr': 0.0004761796417559938, 'samples': 11639296, 'steps': 22732, 'loss/train': 2.6371166706085205}
-03/04/2022 16:09:56 - INFO - codeparrot_training - Step 22733: {'lr': 0.0004761773809801587, 'samples': 11639808, 'steps': 22733, 'loss/train': 2.1136434078216553}
-03/04/2022 16:09:57 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/04/2022 16:10:02 - INFO - codeparrot_training - Step 22734: {'lr': 0.0004761751201024116, 'samples': 11640320, 'steps': 22734, 'loss/train': 0.630546510219574}
-03/04/2022 16:10:05 - INFO - codeparrot_training - Step 22735: {'lr': 0.0004761728591227535, 'samples': 11640832, 'steps': 22735, 'loss/train': 0.5983878374099731}
-03/04/2022 16:10:05 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/04/2022 16:10:10 - INFO - codeparrot_training - Step 22736: {'lr': 0.00047617059804118536, 'samples': 11641344, 'steps': 22736, 'loss/train': 1.5056216716766357}
-03/04/2022 16:10:13 - INFO - codeparrot_training - Step 22737: {'lr': 0.0004761683368577083, 'samples': 11641856, 'steps': 22737, 'loss/train': 0.25127357244491577}
-03/04/2022 16:10:13 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 16:10:19 - INFO - codeparrot_training - Step 22738: {'lr': 0.0004761660755723232, 'samples': 11642368, 'steps': 22738, 'loss/train': 0.20365694165229797}
-03/04/2022 16:10:22 - INFO - codeparrot_training - Step 22739: {'lr': 0.0004761638141850312, 'samples': 11642880, 'steps': 22739, 'loss/train': 1.0232809782028198}
-03/04/2022 16:10:23 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 16:10:27 - INFO - codeparrot_training - Step 22740: {'lr': 0.0004761615526958333, 'samples': 11643392, 'steps': 22740, 'loss/train': 2.081066370010376}
-03/04/2022 16:10:30 - INFO - codeparrot_training - Step 22741: {'lr': 0.0004761592911047304, 'samples': 11643904, 'steps': 22741, 'loss/train': 2.209012031555176}
-03/04/2022 16:10:31 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/04/2022 16:10:36 - INFO - codeparrot_training - Step 22742: {'lr': 0.00047615702941172366, 'samples': 11644416, 'steps': 22742, 'loss/train': 2.0221681594848633}
-03/04/2022 16:10:39 - INFO - codeparrot_training - Step 22743: {'lr': 0.0004761547676168141, 'samples': 11644928, 'steps': 22743, 'loss/train': 1.688999056816101}
-03/04/2022 16:10:39 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 16:10:44 - INFO - codeparrot_training - Step 22744: {'lr': 0.0004761525057200027, 'samples': 11645440, 'steps': 22744, 'loss/train': 1.1519862413406372}
-03/04/2022 16:10:47 - INFO - codeparrot_training - Step 22745: {'lr': 0.00047615024372129033, 'samples': 11645952, 'steps': 22745, 'loss/train': 1.599500060081482}
-03/04/2022 16:10:48 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/04/2022 16:10:53 - INFO - codeparrot_training - Step 22746: {'lr': 0.0004761479816206783, 'samples': 11646464, 'steps': 22746, 'loss/train': 2.074352264404297}
-03/04/2022 16:10:56 - INFO - codeparrot_training - Step 22747: {'lr': 0.00047614571941816743, 'samples': 11646976, 'steps': 22747, 'loss/train': 1.9758764505386353}
-03/04/2022 16:10:57 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 16:11:01 - INFO - codeparrot_training - Step 22748: {'lr': 0.00047614345711375874, 'samples': 11647488, 'steps': 22748, 'loss/train': 2.2397775650024414}
-03/04/2022 16:11:04 - INFO - codeparrot_training - Step 22749: {'lr': 0.0004761411947074533, 'samples': 11648000, 'steps': 22749, 'loss/train': 1.8849570751190186}
-03/04/2022 16:11:06 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 16:11:09 - INFO - codeparrot_training - Step 22750: {'lr': 0.00047613893219925217, 'samples': 11648512, 'steps': 22750, 'loss/train': 1.5778478384017944}
-03/04/2022 16:11:13 - INFO - codeparrot_training - Step 22751: {'lr': 0.00047613666958915636, 'samples': 11649024, 'steps': 22751, 'loss/train': 1.908392071723938}
-03/04/2022 16:11:14 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 16:11:18 - INFO - codeparrot_training - Step 22752: {'lr': 0.0004761344068771668, 'samples': 11649536, 'steps': 22752, 'loss/train': 2.2471325397491455}
-03/04/2022 16:11:21 - INFO - codeparrot_training - Step 22753: {'lr': 0.0004761321440632846, 'samples': 11650048, 'steps': 22753, 'loss/train': 2.328744649887085}
-03/04/2022 16:11:23 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/04/2022 16:11:26 - INFO - codeparrot_training - Step 22754: {'lr': 0.00047612988114751074, 'samples': 11650560, 'steps': 22754, 'loss/train': 1.4198843240737915}
-03/04/2022 16:11:30 - INFO - codeparrot_training - Step 22755: {'lr': 0.00047612761812984626, 'samples': 11651072, 'steps': 22755, 'loss/train': 1.788591980934143}
-03/04/2022 16:11:31 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 16:11:35 - INFO - codeparrot_training - Step 22756: {'lr': 0.00047612535501029215, 'samples': 11651584, 'steps': 22756, 'loss/train': 2.0703320503234863}
-03/04/2022 16:11:38 - INFO - codeparrot_training - Step 22757: {'lr': 0.0004761230917888494, 'samples': 11652096, 'steps': 22757, 'loss/train': 2.3961472511291504}
-03/04/2022 16:11:39 - INFO - codeparrot_training - Skipping example with length 920 (seq_length=1024)
-03/04/2022 16:11:43 - INFO - codeparrot_training - Step 22758: {'lr': 0.00047612082846551913, 'samples': 11652608, 'steps': 22758, 'loss/train': 2.0931332111358643}
-03/04/2022 16:11:46 - INFO - codeparrot_training - Step 22759: {'lr': 0.0004761185650403023, 'samples': 11653120, 'steps': 22759, 'loss/train': 1.7007685899734497}
-03/04/2022 16:11:52 - INFO - codeparrot_training - Step 22760: {'lr': 0.0004761163015131999, 'samples': 11653632, 'steps': 22760, 'loss/train': 1.5417068004608154}
-03/04/2022 16:11:55 - INFO - codeparrot_training - Step 22761: {'lr': 0.00047611403788421305, 'samples': 11654144, 'steps': 22761, 'loss/train': 1.684132695198059}
-03/04/2022 16:11:56 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/04/2022 16:12:00 - INFO - codeparrot_training - Step 22762: {'lr': 0.0004761117741533426, 'samples': 11654656, 'steps': 22762, 'loss/train': 2.491093397140503}
-03/04/2022 16:12:04 - INFO - codeparrot_training - Step 22763: {'lr': 0.0004761095103205897, 'samples': 11655168, 'steps': 22763, 'loss/train': 1.538343071937561}
-03/04/2022 16:12:05 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 16:12:09 - INFO - codeparrot_training - Step 22764: {'lr': 0.00047610724638595545, 'samples': 11655680, 'steps': 22764, 'loss/train': 1.8998663425445557}
-03/04/2022 16:12:12 - INFO - codeparrot_training - Step 22765: {'lr': 0.00047610498234944065, 'samples': 11656192, 'steps': 22765, 'loss/train': 2.556018829345703}
-03/04/2022 16:12:14 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/04/2022 16:12:18 - INFO - codeparrot_training - Step 22766: {'lr': 0.00047610271821104647, 'samples': 11656704, 'steps': 22766, 'loss/train': 2.347198486328125}
-03/04/2022 16:12:21 - INFO - codeparrot_training - Step 22767: {'lr': 0.0004761004539707739, 'samples': 11657216, 'steps': 22767, 'loss/train': 1.8554072380065918}
-03/04/2022 16:12:22 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/04/2022 16:12:26 - INFO - codeparrot_training - Step 22768: {'lr': 0.00047609818962862394, 'samples': 11657728, 'steps': 22768, 'loss/train': 1.814836859703064}
-03/04/2022 16:12:29 - INFO - codeparrot_training - Step 22769: {'lr': 0.00047609592518459766, 'samples': 11658240, 'steps': 22769, 'loss/train': 1.9793697595596313}
-03/04/2022 16:12:31 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/04/2022 16:12:34 - INFO - codeparrot_training - Step 22770: {'lr': 0.00047609366063869595, 'samples': 11658752, 'steps': 22770, 'loss/train': 1.9207111597061157}
-03/04/2022 16:12:38 - INFO - codeparrot_training - Step 22771: {'lr': 0.00047609139599092006, 'samples': 11659264, 'steps': 22771, 'loss/train': 0.24691298604011536}
-03/04/2022 16:12:39 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 16:12:43 - INFO - codeparrot_training - Step 22772: {'lr': 0.0004760891312412708, 'samples': 11659776, 'steps': 22772, 'loss/train': 2.069065570831299}
-03/04/2022 16:12:46 - INFO - codeparrot_training - Step 22773: {'lr': 0.0004760868663897493, 'samples': 11660288, 'steps': 22773, 'loss/train': 2.096614122390747}
-03/04/2022 16:12:47 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/04/2022 16:12:51 - INFO - codeparrot_training - Step 22774: {'lr': 0.0004760846014363565, 'samples': 11660800, 'steps': 22774, 'loss/train': 2.151154041290283}
-03/04/2022 16:12:55 - INFO - codeparrot_training - Step 22775: {'lr': 0.0004760823363810935, 'samples': 11661312, 'steps': 22775, 'loss/train': 2.274588108062744}
-03/04/2022 16:12:56 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/04/2022 16:13:00 - INFO - codeparrot_training - Step 22776: {'lr': 0.0004760800712239612, 'samples': 11661824, 'steps': 22776, 'loss/train': 1.9499043226242065}
-03/04/2022 16:13:03 - INFO - codeparrot_training - Step 22777: {'lr': 0.0004760778059649609, 'samples': 11662336, 'steps': 22777, 'loss/train': 2.3628435134887695}
-03/04/2022 16:13:04 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/04/2022 16:13:08 - INFO - codeparrot_training - Step 22778: {'lr': 0.0004760755406040933, 'samples': 11662848, 'steps': 22778, 'loss/train': 1.9469445943832397}
-03/04/2022 16:13:11 - INFO - codeparrot_training - Step 22779: {'lr': 0.00047607327514135955, 'samples': 11663360, 'steps': 22779, 'loss/train': 1.6754398345947266}
-03/04/2022 16:13:12 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/04/2022 16:13:17 - INFO - codeparrot_training - Step 22780: {'lr': 0.00047607100957676067, 'samples': 11663872, 'steps': 22780, 'loss/train': 0.7512257695198059}
-03/04/2022 16:13:20 - INFO - codeparrot_training - Step 22781: {'lr': 0.0004760687439102977, 'samples': 11664384, 'steps': 22781, 'loss/train': 1.9664580821990967}
-03/04/2022 16:13:21 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 16:13:25 - INFO - codeparrot_training - Step 22782: {'lr': 0.0004760664781419717, 'samples': 11664896, 'steps': 22782, 'loss/train': 1.4796637296676636}
-03/04/2022 16:13:28 - INFO - codeparrot_training - Step 22783: {'lr': 0.00047606421227178354, 'samples': 11665408, 'steps': 22783, 'loss/train': 1.8408528566360474}
-03/04/2022 16:13:29 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/04/2022 16:13:34 - INFO - codeparrot_training - Step 22784: {'lr': 0.0004760619462997343, 'samples': 11665920, 'steps': 22784, 'loss/train': 1.5811431407928467}
-03/04/2022 16:13:37 - INFO - codeparrot_training - Step 22785: {'lr': 0.00047605968022582513, 'samples': 11666432, 'steps': 22785, 'loss/train': 1.2370188236236572}
-03/04/2022 16:13:37 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 16:13:42 - INFO - codeparrot_training - Step 22786: {'lr': 0.000476057414050057, 'samples': 11666944, 'steps': 22786, 'loss/train': 2.135481119155884}
-03/04/2022 16:13:45 - INFO - codeparrot_training - Step 22787: {'lr': 0.00047605514777243076, 'samples': 11667456, 'steps': 22787, 'loss/train': 1.6781362295150757}
-03/04/2022 16:13:46 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/04/2022 16:13:50 - INFO - codeparrot_training - Step 22788: {'lr': 0.0004760528813929476, 'samples': 11667968, 'steps': 22788, 'loss/train': 1.9624316692352295}
-03/04/2022 16:13:54 - INFO - codeparrot_training - Step 22789: {'lr': 0.0004760506149116085, 'samples': 11668480, 'steps': 22789, 'loss/train': 1.8866328001022339}
-03/04/2022 16:13:55 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 16:13:59 - INFO - codeparrot_training - Step 22790: {'lr': 0.0004760483483284145, 'samples': 11668992, 'steps': 22790, 'loss/train': 1.7144771814346313}
-03/04/2022 16:14:02 - INFO - codeparrot_training - Step 22791: {'lr': 0.0004760460816433666, 'samples': 11669504, 'steps': 22791, 'loss/train': 1.3186818361282349}
-03/04/2022 16:14:04 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 16:14:08 - INFO - codeparrot_training - Step 22792: {'lr': 0.0004760438148564659, 'samples': 11670016, 'steps': 22792, 'loss/train': 2.6404786109924316}
-03/04/2022 16:14:11 - INFO - codeparrot_training - Step 22793: {'lr': 0.00047604154796771327, 'samples': 11670528, 'steps': 22793, 'loss/train': 2.4536826610565186}
-03/04/2022 16:14:12 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 16:14:16 - INFO - codeparrot_training - Step 22794: {'lr': 0.0004760392809771098, 'samples': 11671040, 'steps': 22794, 'loss/train': 1.5103991031646729}
-03/04/2022 16:14:19 - INFO - codeparrot_training - Step 22795: {'lr': 0.00047603701388465646, 'samples': 11671552, 'steps': 22795, 'loss/train': 2.3070404529571533}
-03/04/2022 16:14:21 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 16:14:24 - INFO - codeparrot_training - Step 22796: {'lr': 0.0004760347466903544, 'samples': 11672064, 'steps': 22796, 'loss/train': 1.8583471775054932}
-03/04/2022 16:14:28 - INFO - codeparrot_training - Step 22797: {'lr': 0.0004760324793942046, 'samples': 11672576, 'steps': 22797, 'loss/train': 1.5414626598358154}
-03/04/2022 16:14:29 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 16:14:33 - INFO - codeparrot_training - Step 22798: {'lr': 0.000476030211996208, 'samples': 11673088, 'steps': 22798, 'loss/train': 2.4006781578063965}
-03/04/2022 16:14:36 - INFO - codeparrot_training - Step 22799: {'lr': 0.0004760279444963657, 'samples': 11673600, 'steps': 22799, 'loss/train': 0.9450362324714661}
-03/04/2022 16:14:38 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/04/2022 16:14:41 - INFO - codeparrot_training - Step 22800: {'lr': 0.0004760256768946787, 'samples': 11674112, 'steps': 22800, 'loss/train': 1.8798339366912842}
-03/04/2022 16:14:45 - INFO - codeparrot_training - Step 22801: {'lr': 0.00047602340919114793, 'samples': 11674624, 'steps': 22801, 'loss/train': 2.0531322956085205}
-03/04/2022 16:14:46 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 16:14:50 - INFO - codeparrot_training - Step 22802: {'lr': 0.00047602114138577464, 'samples': 11675136, 'steps': 22802, 'loss/train': 1.7071006298065186}
-03/04/2022 16:14:53 - INFO - codeparrot_training - Step 22803: {'lr': 0.00047601887347855965, 'samples': 11675648, 'steps': 22803, 'loss/train': 1.580344319343567}
-03/04/2022 16:14:54 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/04/2022 16:14:58 - INFO - codeparrot_training - Step 22804: {'lr': 0.00047601660546950396, 'samples': 11676160, 'steps': 22804, 'loss/train': 1.777332067489624}
-03/04/2022 16:15:02 - INFO - codeparrot_training - Step 22805: {'lr': 0.00047601433735860885, 'samples': 11676672, 'steps': 22805, 'loss/train': 3.8403055667877197}
-03/04/2022 16:15:03 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/04/2022 16:15:07 - INFO - codeparrot_training - Step 22806: {'lr': 0.000476012069145875, 'samples': 11677184, 'steps': 22806, 'loss/train': 1.9083597660064697}
-03/04/2022 16:15:10 - INFO - codeparrot_training - Step 22807: {'lr': 0.00047600980083130367, 'samples': 11677696, 'steps': 22807, 'loss/train': 1.925580382347107}
-03/04/2022 16:15:12 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 16:15:15 - INFO - codeparrot_training - Step 22808: {'lr': 0.0004760075324148959, 'samples': 11678208, 'steps': 22808, 'loss/train': 1.7848302125930786}
-03/04/2022 16:15:18 - INFO - codeparrot_training - Step 22809: {'lr': 0.00047600526389665246, 'samples': 11678720, 'steps': 22809, 'loss/train': 0.8680102229118347}
-03/04/2022 16:15:20 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 16:15:24 - INFO - codeparrot_training - Step 22810: {'lr': 0.00047600299527657464, 'samples': 11679232, 'steps': 22810, 'loss/train': 1.278043508529663}
-03/04/2022 16:15:27 - INFO - codeparrot_training - Step 22811: {'lr': 0.0004760007265546633, 'samples': 11679744, 'steps': 22811, 'loss/train': 0.26948729157447815}
-03/04/2022 16:15:29 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/04/2022 16:15:32 - INFO - codeparrot_training - Step 22812: {'lr': 0.00047599845773091957, 'samples': 11680256, 'steps': 22812, 'loss/train': 1.9197040796279907}
-03/04/2022 16:15:35 - INFO - codeparrot_training - Step 22813: {'lr': 0.0004759961888053444, 'samples': 11680768, 'steps': 22813, 'loss/train': 1.6887156963348389}
-03/04/2022 16:15:38 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 16:15:41 - INFO - codeparrot_training - Step 22814: {'lr': 0.00047599391977793884, 'samples': 11681280, 'steps': 22814, 'loss/train': 1.5206798315048218}
-03/04/2022 16:15:44 - INFO - codeparrot_training - Step 22815: {'lr': 0.00047599165064870385, 'samples': 11681792, 'steps': 22815, 'loss/train': 1.7349610328674316}
-03/04/2022 16:15:46 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/04/2022 16:15:49 - INFO - codeparrot_training - Step 22816: {'lr': 0.0004759893814176406, 'samples': 11682304, 'steps': 22816, 'loss/train': 1.872040867805481}
-03/04/2022 16:15:52 - INFO - codeparrot_training - Step 22817: {'lr': 0.00047598711208475, 'samples': 11682816, 'steps': 22817, 'loss/train': 1.8899965286254883}
-03/04/2022 16:15:54 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/04/2022 16:15:58 - INFO - codeparrot_training - Step 22818: {'lr': 0.00047598484265003307, 'samples': 11683328, 'steps': 22818, 'loss/train': 2.4383301734924316}
-03/04/2022 16:16:01 - INFO - codeparrot_training - Step 22819: {'lr': 0.00047598257311349087, 'samples': 11683840, 'steps': 22819, 'loss/train': 1.9012706279754639}
-03/04/2022 16:16:03 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/04/2022 16:16:06 - INFO - codeparrot_training - Step 22820: {'lr': 0.0004759803034751244, 'samples': 11684352, 'steps': 22820, 'loss/train': 2.6568329334259033}
-03/04/2022 16:16:09 - INFO - codeparrot_training - Step 22821: {'lr': 0.0004759780337349347, 'samples': 11684864, 'steps': 22821, 'loss/train': 2.0336782932281494}
-03/04/2022 16:16:11 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/04/2022 16:16:14 - INFO - codeparrot_training - Step 22822: {'lr': 0.0004759757638929227, 'samples': 11685376, 'steps': 22822, 'loss/train': 2.2956860065460205}
-03/04/2022 16:16:18 - INFO - codeparrot_training - Step 22823: {'lr': 0.00047597349394908967, 'samples': 11685888, 'steps': 22823, 'loss/train': 1.692417860031128}
-03/04/2022 16:16:20 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 16:16:23 - INFO - codeparrot_training - Step 22824: {'lr': 0.0004759712239034364, 'samples': 11686400, 'steps': 22824, 'loss/train': 1.8119562864303589}
-03/04/2022 16:16:26 - INFO - codeparrot_training - Step 22825: {'lr': 0.0004759689537559639, 'samples': 11686912, 'steps': 22825, 'loss/train': 1.2337623834609985}
-03/04/2022 16:16:28 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/04/2022 16:16:31 - INFO - codeparrot_training - Step 22826: {'lr': 0.0004759666835066734, 'samples': 11687424, 'steps': 22826, 'loss/train': 1.7540007829666138}
-03/04/2022 16:16:34 - INFO - codeparrot_training - Step 22827: {'lr': 0.00047596441315556575, 'samples': 11687936, 'steps': 22827, 'loss/train': 1.8777952194213867}
-03/04/2022 16:16:36 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/04/2022 16:16:40 - INFO - codeparrot_training - Step 22828: {'lr': 0.00047596214270264204, 'samples': 11688448, 'steps': 22828, 'loss/train': 0.8626569509506226}
-03/04/2022 16:16:43 - INFO - codeparrot_training - Step 22829: {'lr': 0.00047595987214790324, 'samples': 11688960, 'steps': 22829, 'loss/train': 2.044384002685547}
-03/04/2022 16:16:45 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 16:16:48 - INFO - codeparrot_training - Step 22830: {'lr': 0.0004759576014913505, 'samples': 11689472, 'steps': 22830, 'loss/train': 2.301889657974243}
-03/04/2022 16:16:51 - INFO - codeparrot_training - Step 22831: {'lr': 0.0004759553307329846, 'samples': 11689984, 'steps': 22831, 'loss/train': 2.602731943130493}
-03/04/2022 16:16:53 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/04/2022 16:16:56 - INFO - codeparrot_training - Step 22832: {'lr': 0.0004759530598728068, 'samples': 11690496, 'steps': 22832, 'loss/train': 0.7168457508087158}
-03/04/2022 16:17:00 - INFO - codeparrot_training - Step 22833: {'lr': 0.000475950788910818, 'samples': 11691008, 'steps': 22833, 'loss/train': 5.3758344650268555}
-03/04/2022 16:17:02 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/04/2022 16:17:05 - INFO - codeparrot_training - Step 22834: {'lr': 0.0004759485178470193, 'samples': 11691520, 'steps': 22834, 'loss/train': 2.7386538982391357}
-03/04/2022 16:17:08 - INFO - codeparrot_training - Step 22835: {'lr': 0.0004759462466814117, 'samples': 11692032, 'steps': 22835, 'loss/train': 1.9544155597686768}
-03/04/2022 16:17:10 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 16:17:13 - INFO - codeparrot_training - Step 22836: {'lr': 0.0004759439754139962, 'samples': 11692544, 'steps': 22836, 'loss/train': 1.9805902242660522}
-03/04/2022 16:17:16 - INFO - codeparrot_training - Step 22837: {'lr': 0.0004759417040447738, 'samples': 11693056, 'steps': 22837, 'loss/train': 1.2868802547454834}
-03/04/2022 16:17:18 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 16:17:22 - INFO - codeparrot_training - Step 22838: {'lr': 0.00047593943257374563, 'samples': 11693568, 'steps': 22838, 'loss/train': 2.5074782371520996}
-03/04/2022 16:17:25 - INFO - codeparrot_training - Step 22839: {'lr': 0.00047593716100091253, 'samples': 11694080, 'steps': 22839, 'loss/train': 2.6331851482391357}
-03/04/2022 16:17:27 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/04/2022 16:17:30 - INFO - codeparrot_training - Step 22840: {'lr': 0.00047593488932627567, 'samples': 11694592, 'steps': 22840, 'loss/train': 1.8131109476089478}
-03/04/2022 16:17:33 - INFO - codeparrot_training - Step 22841: {'lr': 0.00047593261754983607, 'samples': 11695104, 'steps': 22841, 'loss/train': 1.6030670404434204}
-03/04/2022 16:17:35 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/04/2022 16:17:39 - INFO - codeparrot_training - Step 22842: {'lr': 0.00047593034567159465, 'samples': 11695616, 'steps': 22842, 'loss/train': 1.712217092514038}
-03/04/2022 16:17:42 - INFO - codeparrot_training - Step 22843: {'lr': 0.00047592807369155256, 'samples': 11696128, 'steps': 22843, 'loss/train': 1.966463327407837}
-03/04/2022 16:17:46 - INFO - codeparrot_training - Step 22844: {'lr': 0.0004759258016097108, 'samples': 11696640, 'steps': 22844, 'loss/train': 1.0743975639343262}
-03/04/2022 16:17:47 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/04/2022 16:17:51 - INFO - codeparrot_training - Step 22845: {'lr': 0.0004759235294260703, 'samples': 11697152, 'steps': 22845, 'loss/train': 1.9415068626403809}
-03/04/2022 16:17:54 - INFO - codeparrot_training - Step 22846: {'lr': 0.0004759212571406321, 'samples': 11697664, 'steps': 22846, 'loss/train': 2.2889270782470703}
-03/04/2022 16:17:56 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 16:17:59 - INFO - codeparrot_training - Step 22847: {'lr': 0.00047591898475339735, 'samples': 11698176, 'steps': 22847, 'loss/train': 2.18639874458313}
-03/04/2022 16:18:03 - INFO - codeparrot_training - Step 22848: {'lr': 0.00047591671226436695, 'samples': 11698688, 'steps': 22848, 'loss/train': 1.4723293781280518}
-03/04/2022 16:18:05 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/04/2022 16:18:08 - INFO - codeparrot_training - Step 22849: {'lr': 0.00047591443967354196, 'samples': 11699200, 'steps': 22849, 'loss/train': 0.8739657402038574}
-03/04/2022 16:18:11 - INFO - codeparrot_training - Step 22850: {'lr': 0.00047591216698092344, 'samples': 11699712, 'steps': 22850, 'loss/train': 1.4261035919189453}
-03/04/2022 16:18:13 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 16:18:16 - INFO - codeparrot_training - Step 22851: {'lr': 0.00047590989418651243, 'samples': 11700224, 'steps': 22851, 'loss/train': 0.09826712310314178}
-03/04/2022 16:18:19 - INFO - codeparrot_training - Step 22852: {'lr': 0.00047590762129030986, 'samples': 11700736, 'steps': 22852, 'loss/train': 1.2697683572769165}
-03/04/2022 16:18:22 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/04/2022 16:18:25 - INFO - codeparrot_training - Step 22853: {'lr': 0.00047590534829231675, 'samples': 11701248, 'steps': 22853, 'loss/train': 1.8740471601486206}
-03/04/2022 16:18:28 - INFO - codeparrot_training - Step 22854: {'lr': 0.00047590307519253423, 'samples': 11701760, 'steps': 22854, 'loss/train': 1.0300347805023193}
-03/04/2022 16:18:31 - INFO - codeparrot_training - Step 22855: {'lr': 0.00047590080199096324, 'samples': 11702272, 'steps': 22855, 'loss/train': 1.5674493312835693}
-03/04/2022 16:18:31 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 16:18:36 - INFO - codeparrot_training - Step 22856: {'lr': 0.00047589852868760486, 'samples': 11702784, 'steps': 22856, 'loss/train': 1.3125629425048828}
-03/04/2022 16:18:39 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/04/2022 16:18:42 - INFO - codeparrot_training - Step 22857: {'lr': 0.00047589625528246006, 'samples': 11703296, 'steps': 22857, 'loss/train': 2.0716586112976074}
-03/04/2022 16:18:45 - INFO - codeparrot_training - Step 22858: {'lr': 0.0004758939817755299, 'samples': 11703808, 'steps': 22858, 'loss/train': 2.5346128940582275}
-03/04/2022 16:18:48 - INFO - codeparrot_training - Step 22859: {'lr': 0.0004758917081668155, 'samples': 11704320, 'steps': 22859, 'loss/train': 2.07692551612854}
-03/04/2022 16:18:48 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/04/2022 16:18:53 - INFO - codeparrot_training - Step 22860: {'lr': 0.00047588943445631767, 'samples': 11704832, 'steps': 22860, 'loss/train': 2.0187056064605713}
-03/04/2022 16:18:56 - INFO - codeparrot_training - Step 22861: {'lr': 0.0004758871606440376, 'samples': 11705344, 'steps': 22861, 'loss/train': 2.0269904136657715}
-03/04/2022 16:18:57 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/04/2022 16:19:02 - INFO - codeparrot_training - Step 22862: {'lr': 0.0004758848867299762, 'samples': 11705856, 'steps': 22862, 'loss/train': 1.879315733909607}
-03/04/2022 16:19:05 - INFO - codeparrot_training - Step 22863: {'lr': 0.0004758826127141346, 'samples': 11706368, 'steps': 22863, 'loss/train': 1.1295838356018066}
-03/04/2022 16:19:05 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 16:19:11 - INFO - codeparrot_training - Step 22864: {'lr': 0.00047588033859651376, 'samples': 11706880, 'steps': 22864, 'loss/train': 1.194993495941162}
-03/04/2022 16:19:14 - INFO - codeparrot_training - Step 22865: {'lr': 0.00047587806437711475, 'samples': 11707392, 'steps': 22865, 'loss/train': 1.7857860326766968}
-03/04/2022 16:19:15 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/04/2022 16:19:19 - INFO - codeparrot_training - Step 22866: {'lr': 0.0004758757900559385, 'samples': 11707904, 'steps': 22866, 'loss/train': 1.4991466999053955}
-03/04/2022 16:19:22 - INFO - codeparrot_training - Step 22867: {'lr': 0.0004758735156329862, 'samples': 11708416, 'steps': 22867, 'loss/train': 1.9092925786972046}
-03/04/2022 16:19:24 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/04/2022 16:19:28 - INFO - codeparrot_training - Step 22868: {'lr': 0.00047587124110825874, 'samples': 11708928, 'steps': 22868, 'loss/train': 2.8576369285583496}
-03/04/2022 16:19:31 - INFO - codeparrot_training - Step 22869: {'lr': 0.00047586896648175715, 'samples': 11709440, 'steps': 22869, 'loss/train': 2.0213112831115723}
-03/04/2022 16:19:32 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/04/2022 16:19:36 - INFO - codeparrot_training - Step 22870: {'lr': 0.00047586669175348254, 'samples': 11709952, 'steps': 22870, 'loss/train': 2.01139760017395}
-03/04/2022 16:19:39 - INFO - codeparrot_training - Step 22871: {'lr': 0.0004758644169234359, 'samples': 11710464, 'steps': 22871, 'loss/train': 1.6415945291519165}
-03/04/2022 16:19:41 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 16:19:44 - INFO - codeparrot_training - Step 22872: {'lr': 0.00047586214199161814, 'samples': 11710976, 'steps': 22872, 'loss/train': 2.0412938594818115}
-03/04/2022 16:19:48 - INFO - codeparrot_training - Step 22873: {'lr': 0.00047585986695803046, 'samples': 11711488, 'steps': 22873, 'loss/train': 1.9360533952713013}
-03/04/2022 16:19:49 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/04/2022 16:19:53 - INFO - codeparrot_training - Step 22874: {'lr': 0.0004758575918226738, 'samples': 11712000, 'steps': 22874, 'loss/train': 1.5150266885757446}
-03/04/2022 16:19:56 - INFO - codeparrot_training - Step 22875: {'lr': 0.0004758553165855492, 'samples': 11712512, 'steps': 22875, 'loss/train': 4.4166259765625}
-03/04/2022 16:19:58 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/04/2022 16:20:01 - INFO - codeparrot_training - Step 22876: {'lr': 0.00047585304124665766, 'samples': 11713024, 'steps': 22876, 'loss/train': 2.2174160480499268}
-03/04/2022 16:20:05 - INFO - codeparrot_training - Step 22877: {'lr': 0.0004758507658060003, 'samples': 11713536, 'steps': 22877, 'loss/train': 2.52005934715271}
-03/04/2022 16:20:06 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 16:20:10 - INFO - codeparrot_training - Step 22878: {'lr': 0.00047584849026357796, 'samples': 11714048, 'steps': 22878, 'loss/train': 1.2430938482284546}
-03/04/2022 16:20:13 - INFO - codeparrot_training - Step 22879: {'lr': 0.0004758462146193918, 'samples': 11714560, 'steps': 22879, 'loss/train': 2.15004825592041}
-03/04/2022 16:20:14 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/04/2022 16:20:18 - INFO - codeparrot_training - Step 22880: {'lr': 0.00047584393887344285, 'samples': 11715072, 'steps': 22880, 'loss/train': 1.5511045455932617}
-03/04/2022 16:20:21 - INFO - codeparrot_training - Step 22881: {'lr': 0.00047584166302573204, 'samples': 11715584, 'steps': 22881, 'loss/train': 1.7538604736328125}
-03/04/2022 16:20:23 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 16:20:27 - INFO - codeparrot_training - Step 22882: {'lr': 0.0004758393870762606, 'samples': 11716096, 'steps': 22882, 'loss/train': 1.5002350807189941}
-03/04/2022 16:20:30 - INFO - codeparrot_training - Step 22883: {'lr': 0.00047583711102502934, 'samples': 11716608, 'steps': 22883, 'loss/train': 1.954115867614746}
-03/04/2022 16:20:31 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 16:20:35 - INFO - codeparrot_training - Step 22884: {'lr': 0.0004758348348720393, 'samples': 11717120, 'steps': 22884, 'loss/train': 0.8601232767105103}
-03/04/2022 16:20:38 - INFO - codeparrot_training - Step 22885: {'lr': 0.00047583255861729167, 'samples': 11717632, 'steps': 22885, 'loss/train': 0.36167776584625244}
-03/04/2022 16:20:40 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 16:20:44 - INFO - codeparrot_training - Step 22886: {'lr': 0.00047583028226078734, 'samples': 11718144, 'steps': 22886, 'loss/train': 2.0548055171966553}
-03/04/2022 16:20:47 - INFO - codeparrot_training - Step 22887: {'lr': 0.0004758280058025274, 'samples': 11718656, 'steps': 22887, 'loss/train': 2.02970027923584}
-03/04/2022 16:20:48 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/04/2022 16:20:52 - INFO - codeparrot_training - Step 22888: {'lr': 0.00047582572924251276, 'samples': 11719168, 'steps': 22888, 'loss/train': 1.9080907106399536}
-03/04/2022 16:20:55 - INFO - codeparrot_training - Step 22889: {'lr': 0.00047582345258074453, 'samples': 11719680, 'steps': 22889, 'loss/train': 1.0518872737884521}
-03/04/2022 16:20:56 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 16:21:00 - INFO - codeparrot_training - Step 22890: {'lr': 0.0004758211758172238, 'samples': 11720192, 'steps': 22890, 'loss/train': 0.95332270860672}
-03/04/2022 16:21:03 - INFO - codeparrot_training - Step 22891: {'lr': 0.00047581889895195154, 'samples': 11720704, 'steps': 22891, 'loss/train': 1.528998613357544}
-03/04/2022 16:21:05 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/04/2022 16:21:09 - INFO - codeparrot_training - Step 22892: {'lr': 0.00047581662198492873, 'samples': 11721216, 'steps': 22892, 'loss/train': 1.4116953611373901}
-03/04/2022 16:21:12 - INFO - codeparrot_training - Step 22893: {'lr': 0.0004758143449161565, 'samples': 11721728, 'steps': 22893, 'loss/train': 0.6959846615791321}
-03/04/2022 16:21:13 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 16:21:17 - INFO - codeparrot_training - Step 22894: {'lr': 0.00047581206774563575, 'samples': 11722240, 'steps': 22894, 'loss/train': 2.263852596282959}
-03/04/2022 16:21:20 - INFO - codeparrot_training - Step 22895: {'lr': 0.0004758097904733676, 'samples': 11722752, 'steps': 22895, 'loss/train': 1.755010962486267}
-03/04/2022 16:21:22 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/04/2022 16:21:26 - INFO - codeparrot_training - Step 22896: {'lr': 0.000475807513099353, 'samples': 11723264, 'steps': 22896, 'loss/train': 2.370687961578369}
-03/04/2022 16:21:29 - INFO - codeparrot_training - Step 22897: {'lr': 0.000475805235623593, 'samples': 11723776, 'steps': 22897, 'loss/train': 1.2427406311035156}
-03/04/2022 16:21:30 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/04/2022 16:21:34 - INFO - codeparrot_training - Step 22898: {'lr': 0.0004758029580460887, 'samples': 11724288, 'steps': 22898, 'loss/train': 2.382619619369507}
-03/04/2022 16:21:37 - INFO - codeparrot_training - Step 22899: {'lr': 0.0004758006803668411, 'samples': 11724800, 'steps': 22899, 'loss/train': 0.23487669229507446}
-03/04/2022 16:21:38 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 16:21:42 - INFO - codeparrot_training - Step 22900: {'lr': 0.0004757984025858511, 'samples': 11725312, 'steps': 22900, 'loss/train': 1.7162998914718628}
-03/04/2022 16:21:46 - INFO - codeparrot_training - Step 22901: {'lr': 0.0004757961247031199, 'samples': 11725824, 'steps': 22901, 'loss/train': 1.060091257095337}
-03/04/2022 16:21:46 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 16:21:51 - INFO - codeparrot_training - Step 22902: {'lr': 0.00047579384671864845, 'samples': 11726336, 'steps': 22902, 'loss/train': 1.9821926355361938}
-03/04/2022 16:21:54 - INFO - codeparrot_training - Step 22903: {'lr': 0.0004757915686324377, 'samples': 11726848, 'steps': 22903, 'loss/train': 0.19560517370700836}
-03/04/2022 16:21:55 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/04/2022 16:21:59 - INFO - codeparrot_training - Step 22904: {'lr': 0.00047578929044448883, 'samples': 11727360, 'steps': 22904, 'loss/train': 1.213908314704895}
-03/04/2022 16:22:03 - INFO - codeparrot_training - Step 22905: {'lr': 0.0004757870121548028, 'samples': 11727872, 'steps': 22905, 'loss/train': 2.1588170528411865}
-03/04/2022 16:22:03 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/04/2022 16:22:08 - INFO - codeparrot_training - Step 22906: {'lr': 0.0004757847337633806, 'samples': 11728384, 'steps': 22906, 'loss/train': 2.1488897800445557}
-03/04/2022 16:22:11 - INFO - codeparrot_training - Step 22907: {'lr': 0.0004757824552702232, 'samples': 11728896, 'steps': 22907, 'loss/train': 2.1493983268737793}
-03/04/2022 16:22:12 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 16:22:16 - INFO - codeparrot_training - Step 22908: {'lr': 0.0004757801766753318, 'samples': 11729408, 'steps': 22908, 'loss/train': 1.3219431638717651}
-03/04/2022 16:22:20 - INFO - codeparrot_training - Step 22909: {'lr': 0.00047577789797870743, 'samples': 11729920, 'steps': 22909, 'loss/train': 1.6207704544067383}
-03/04/2022 16:22:21 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/04/2022 16:22:25 - INFO - codeparrot_training - Step 22910: {'lr': 0.0004757756191803508, 'samples': 11730432, 'steps': 22910, 'loss/train': 1.7265653610229492}
-03/04/2022 16:22:28 - INFO - codeparrot_training - Step 22911: {'lr': 0.0004757733402802633, 'samples': 11730944, 'steps': 22911, 'loss/train': 2.2151176929473877}
-03/04/2022 16:22:29 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 16:22:33 - INFO - codeparrot_training - Step 22912: {'lr': 0.0004757710612784458, 'samples': 11731456, 'steps': 22912, 'loss/train': 1.8647834062576294}
-03/04/2022 16:22:37 - INFO - codeparrot_training - Step 22913: {'lr': 0.0004757687821748994, 'samples': 11731968, 'steps': 22913, 'loss/train': 1.0429507493972778}
-03/04/2022 16:22:38 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 16:22:42 - INFO - codeparrot_training - Step 22914: {'lr': 0.00047576650296962496, 'samples': 11732480, 'steps': 22914, 'loss/train': 1.3514175415039062}
-03/04/2022 16:22:45 - INFO - codeparrot_training - Step 22915: {'lr': 0.0004757642236626237, 'samples': 11732992, 'steps': 22915, 'loss/train': 2.3628201484680176}
-03/04/2022 16:22:47 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/04/2022 16:22:50 - INFO - codeparrot_training - Step 22916: {'lr': 0.00047576194425389654, 'samples': 11733504, 'steps': 22916, 'loss/train': 0.7548831105232239}
-03/04/2022 16:22:53 - INFO - codeparrot_training - Step 22917: {'lr': 0.00047575966474344445, 'samples': 11734016, 'steps': 22917, 'loss/train': 1.9331450462341309}
-03/04/2022 16:22:56 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/04/2022 16:22:59 - INFO - codeparrot_training - Step 22918: {'lr': 0.00047575738513126867, 'samples': 11734528, 'steps': 22918, 'loss/train': 1.871644139289856}
-03/04/2022 16:23:02 - INFO - codeparrot_training - Step 22919: {'lr': 0.00047575510541737, 'samples': 11735040, 'steps': 22919, 'loss/train': 1.9274777173995972}
-03/04/2022 16:23:04 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/04/2022 16:23:07 - INFO - codeparrot_training - Step 22920: {'lr': 0.0004757528256017496, 'samples': 11735552, 'steps': 22920, 'loss/train': 1.7512754201889038}
-03/04/2022 16:23:10 - INFO - codeparrot_training - Step 22921: {'lr': 0.00047575054568440846, 'samples': 11736064, 'steps': 22921, 'loss/train': 0.29790833592414856}
-03/04/2022 16:23:12 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/04/2022 16:23:16 - INFO - codeparrot_training - Step 22922: {'lr': 0.00047574826566534764, 'samples': 11736576, 'steps': 22922, 'loss/train': 1.6377239227294922}
-03/04/2022 16:23:19 - INFO - codeparrot_training - Step 22923: {'lr': 0.0004757459855445681, 'samples': 11737088, 'steps': 22923, 'loss/train': 1.2359236478805542}
-03/04/2022 16:23:21 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 16:23:24 - INFO - codeparrot_training - Step 22924: {'lr': 0.0004757437053220709, 'samples': 11737600, 'steps': 22924, 'loss/train': 2.1611945629119873}
-03/04/2022 16:23:28 - INFO - codeparrot_training - Step 22925: {'lr': 0.0004757414249978571, 'samples': 11738112, 'steps': 22925, 'loss/train': 0.8202895522117615}
-03/04/2022 16:23:30 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/04/2022 16:23:33 - INFO - codeparrot_training - Step 22926: {'lr': 0.0004757391445719277, 'samples': 11738624, 'steps': 22926, 'loss/train': 2.0811893939971924}
-03/04/2022 16:23:36 - INFO - codeparrot_training - Step 22927: {'lr': 0.00047573686404428365, 'samples': 11739136, 'steps': 22927, 'loss/train': 2.065178632736206}
-03/04/2022 16:23:38 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/04/2022 16:23:41 - INFO - codeparrot_training - Step 22928: {'lr': 0.0004757345834149261, 'samples': 11739648, 'steps': 22928, 'loss/train': 1.4111851453781128}
-03/04/2022 16:23:44 - INFO - codeparrot_training - Step 22929: {'lr': 0.00047573230268385604, 'samples': 11740160, 'steps': 22929, 'loss/train': 1.8747248649597168}
-03/04/2022 16:23:46 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/04/2022 16:23:50 - INFO - codeparrot_training - Step 22930: {'lr': 0.0004757300218510745, 'samples': 11740672, 'steps': 22930, 'loss/train': 2.2454559803009033}
-03/04/2022 16:23:53 - INFO - codeparrot_training - Step 22931: {'lr': 0.00047572774091658243, 'samples': 11741184, 'steps': 22931, 'loss/train': 2.5826971530914307}
-03/04/2022 16:23:55 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/04/2022 16:23:58 - INFO - codeparrot_training - Step 22932: {'lr': 0.000475725459880381, 'samples': 11741696, 'steps': 22932, 'loss/train': 1.6706597805023193}
-03/04/2022 16:24:01 - INFO - codeparrot_training - Step 22933: {'lr': 0.00047572317874247107, 'samples': 11742208, 'steps': 22933, 'loss/train': 2.3651859760284424}
-03/04/2022 16:24:03 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/04/2022 16:24:07 - INFO - codeparrot_training - Step 22934: {'lr': 0.00047572089750285383, 'samples': 11742720, 'steps': 22934, 'loss/train': 1.698809027671814}
-03/04/2022 16:24:10 - INFO - codeparrot_training - Step 22935: {'lr': 0.00047571861616153025, 'samples': 11743232, 'steps': 22935, 'loss/train': 2.33353328704834}
-03/04/2022 16:24:12 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 16:24:15 - INFO - codeparrot_training - Step 22936: {'lr': 0.0004757163347185013, 'samples': 11743744, 'steps': 22936, 'loss/train': 0.9967316389083862}
-03/04/2022 16:24:18 - INFO - codeparrot_training - Step 22937: {'lr': 0.00047571405317376803, 'samples': 11744256, 'steps': 22937, 'loss/train': 1.9393481016159058}
-03/04/2022 16:24:21 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/04/2022 16:24:24 - INFO - codeparrot_training - Step 22938: {'lr': 0.0004757117715273316, 'samples': 11744768, 'steps': 22938, 'loss/train': 1.32143235206604}
-03/04/2022 16:24:27 - INFO - codeparrot_training - Step 22939: {'lr': 0.00047570948977919284, 'samples': 11745280, 'steps': 22939, 'loss/train': 1.8810559511184692}
-03/04/2022 16:24:30 - INFO - codeparrot_training - Step 22940: {'lr': 0.00047570720792935284, 'samples': 11745792, 'steps': 22940, 'loss/train': 2.8084115982055664}
-03/04/2022 16:24:30 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 16:24:35 - INFO - codeparrot_training - Step 22941: {'lr': 0.00047570492597781274, 'samples': 11746304, 'steps': 22941, 'loss/train': 2.0575263500213623}
-03/04/2022 16:24:39 - INFO - codeparrot_training - Step 22942: {'lr': 0.0004757026439245735, 'samples': 11746816, 'steps': 22942, 'loss/train': 1.5483179092407227}
-03/04/2022 16:24:39 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 16:24:44 - INFO - codeparrot_training - Step 22943: {'lr': 0.0004757003617696361, 'samples': 11747328, 'steps': 22943, 'loss/train': 2.5535199642181396}
-03/04/2022 16:24:47 - INFO - codeparrot_training - Step 22944: {'lr': 0.0004756980795130015, 'samples': 11747840, 'steps': 22944, 'loss/train': 1.9382071495056152}
-03/04/2022 16:24:47 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/04/2022 16:24:52 - INFO - codeparrot_training - Step 22945: {'lr': 0.00047569579715467093, 'samples': 11748352, 'steps': 22945, 'loss/train': 1.9776567220687866}
-03/04/2022 16:24:55 - INFO - codeparrot_training - Step 22946: {'lr': 0.00047569351469464526, 'samples': 11748864, 'steps': 22946, 'loss/train': 1.6974549293518066}
-03/04/2022 16:24:55 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/04/2022 16:25:01 - INFO - codeparrot_training - Step 22947: {'lr': 0.0004756912321329256, 'samples': 11749376, 'steps': 22947, 'loss/train': 1.902990460395813}
-03/04/2022 16:25:04 - INFO - codeparrot_training - Step 22948: {'lr': 0.000475688949469513, 'samples': 11749888, 'steps': 22948, 'loss/train': 1.766126036643982}
-03/04/2022 16:25:04 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/04/2022 16:25:09 - INFO - codeparrot_training - Step 22949: {'lr': 0.0004756866667044084, 'samples': 11750400, 'steps': 22949, 'loss/train': 1.1813002824783325}
-03/04/2022 16:25:12 - INFO - codeparrot_training - Step 22950: {'lr': 0.0004756843838376128, 'samples': 11750912, 'steps': 22950, 'loss/train': 2.3913285732269287}
-03/04/2022 16:25:12 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/04/2022 16:25:18 - INFO - codeparrot_training - Step 22951: {'lr': 0.0004756821008691274, 'samples': 11751424, 'steps': 22951, 'loss/train': 2.086440324783325}
-03/04/2022 16:25:21 - INFO - codeparrot_training - Step 22952: {'lr': 0.0004756798177989531, 'samples': 11751936, 'steps': 22952, 'loss/train': 1.5182918310165405}
-03/04/2022 16:25:21 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 16:25:26 - INFO - codeparrot_training - Step 22953: {'lr': 0.00047567753462709095, 'samples': 11752448, 'steps': 22953, 'loss/train': 2.460782766342163}
-03/04/2022 16:25:29 - INFO - codeparrot_training - Step 22954: {'lr': 0.00047567525135354193, 'samples': 11752960, 'steps': 22954, 'loss/train': 1.339983344078064}
-03/04/2022 16:25:29 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 16:25:35 - INFO - codeparrot_training - Step 22955: {'lr': 0.00047567296797830727, 'samples': 11753472, 'steps': 22955, 'loss/train': 2.493532180786133}
-03/04/2022 16:25:38 - INFO - codeparrot_training - Step 22956: {'lr': 0.00047567068450138773, 'samples': 11753984, 'steps': 22956, 'loss/train': 1.7990163564682007}
-03/04/2022 16:25:38 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/04/2022 16:25:43 - INFO - codeparrot_training - Step 22957: {'lr': 0.0004756684009227845, 'samples': 11754496, 'steps': 22957, 'loss/train': 2.379865884780884}
-03/04/2022 16:25:46 - INFO - codeparrot_training - Step 22958: {'lr': 0.0004756661172424986, 'samples': 11755008, 'steps': 22958, 'loss/train': 1.4592702388763428}
-03/04/2022 16:25:46 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/04/2022 16:25:51 - INFO - codeparrot_training - Step 22959: {'lr': 0.000475663833460531, 'samples': 11755520, 'steps': 22959, 'loss/train': 1.8321703672409058}
-03/04/2022 16:25:55 - INFO - codeparrot_training - Step 22960: {'lr': 0.00047566154957688275, 'samples': 11756032, 'steps': 22960, 'loss/train': 1.7337323427200317}
-03/04/2022 16:25:55 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/04/2022 16:26:00 - INFO - codeparrot_training - Step 22961: {'lr': 0.0004756592655915549, 'samples': 11756544, 'steps': 22961, 'loss/train': 1.3006869554519653}
-03/04/2022 16:26:03 - INFO - codeparrot_training - Step 22962: {'lr': 0.00047565698150454845, 'samples': 11757056, 'steps': 22962, 'loss/train': 2.3456032276153564}
-03/04/2022 16:26:03 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/04/2022 16:26:09 - INFO - codeparrot_training - Step 22963: {'lr': 0.0004756546973158644, 'samples': 11757568, 'steps': 22963, 'loss/train': 1.941611886024475}
-03/04/2022 16:26:12 - INFO - codeparrot_training - Step 22964: {'lr': 0.00047565241302550395, 'samples': 11758080, 'steps': 22964, 'loss/train': 2.023801565170288}
-03/04/2022 16:26:12 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 16:26:17 - INFO - codeparrot_training - Step 22965: {'lr': 0.0004756501286334679, 'samples': 11758592, 'steps': 22965, 'loss/train': 2.3101296424865723}
-03/04/2022 16:26:20 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/04/2022 16:26:22 - INFO - codeparrot_training - Step 22966: {'lr': 0.0004756478441397575, 'samples': 11759104, 'steps': 22966, 'loss/train': 1.7900031805038452}
-03/04/2022 16:26:26 - INFO - codeparrot_training - Step 22967: {'lr': 0.0004756455595443735, 'samples': 11759616, 'steps': 22967, 'loss/train': 2.0853164196014404}
-03/04/2022 16:26:29 - INFO - codeparrot_training - Step 22968: {'lr': 0.00047564327484731725, 'samples': 11760128, 'steps': 22968, 'loss/train': 1.4200279712677002}
-03/04/2022 16:26:29 - INFO - codeparrot_training - Skipping example with length 5 (seq_length=1024)
-03/04/2022 16:26:34 - INFO - codeparrot_training - Step 22969: {'lr': 0.0004756409900485895, 'samples': 11760640, 'steps': 22969, 'loss/train': 1.9931896924972534}
-03/04/2022 16:26:37 - INFO - codeparrot_training - Step 22970: {'lr': 0.00047563870514819154, 'samples': 11761152, 'steps': 22970, 'loss/train': 1.9345331192016602}
-03/04/2022 16:26:37 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/04/2022 16:26:43 - INFO - codeparrot_training - Step 22971: {'lr': 0.0004756364201461241, 'samples': 11761664, 'steps': 22971, 'loss/train': 1.6411733627319336}
-03/04/2022 16:26:45 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 16:26:48 - INFO - codeparrot_training - Step 22972: {'lr': 0.00047563413504238847, 'samples': 11762176, 'steps': 22972, 'loss/train': 1.4019917249679565}
-03/04/2022 16:26:51 - INFO - codeparrot_training - Step 22973: {'lr': 0.0004756318498369855, 'samples': 11762688, 'steps': 22973, 'loss/train': 1.0531474351882935}
-03/04/2022 16:26:54 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/04/2022 16:26:56 - INFO - codeparrot_training - Step 22974: {'lr': 0.0004756295645299164, 'samples': 11763200, 'steps': 22974, 'loss/train': 1.4114187955856323}
-03/04/2022 16:26:59 - INFO - codeparrot_training - Step 22975: {'lr': 0.00047562727912118206, 'samples': 11763712, 'steps': 22975, 'loss/train': 1.5655065774917603}
-03/04/2022 16:27:02 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/04/2022 16:27:05 - INFO - codeparrot_training - Step 22976: {'lr': 0.00047562499361078356, 'samples': 11764224, 'steps': 22976, 'loss/train': 1.260461449623108}
-03/04/2022 16:27:08 - INFO - codeparrot_training - Step 22977: {'lr': 0.00047562270799872186, 'samples': 11764736, 'steps': 22977, 'loss/train': 2.3474597930908203}
-03/04/2022 16:27:11 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 16:27:13 - INFO - codeparrot_training - Step 22978: {'lr': 0.00047562042228499815, 'samples': 11765248, 'steps': 22978, 'loss/train': 1.6275286674499512}
-03/04/2022 16:27:16 - INFO - codeparrot_training - Step 22979: {'lr': 0.00047561813646961325, 'samples': 11765760, 'steps': 22979, 'loss/train': 2.516315221786499}
-03/04/2022 16:27:19 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/04/2022 16:27:21 - INFO - codeparrot_training - Step 22980: {'lr': 0.0004756158505525684, 'samples': 11766272, 'steps': 22980, 'loss/train': 2.3076066970825195}
-03/04/2022 16:27:25 - INFO - codeparrot_training - Step 22981: {'lr': 0.0004756135645338644, 'samples': 11766784, 'steps': 22981, 'loss/train': 1.6677684783935547}
-03/04/2022 16:27:27 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/04/2022 16:27:30 - INFO - codeparrot_training - Step 22982: {'lr': 0.00047561127841350256, 'samples': 11767296, 'steps': 22982, 'loss/train': 1.734668493270874}
-03/04/2022 16:27:33 - INFO - codeparrot_training - Step 22983: {'lr': 0.0004756089921914837, 'samples': 11767808, 'steps': 22983, 'loss/train': 2.0724599361419678}
-03/04/2022 16:27:36 - INFO - codeparrot_training - Step 22984: {'lr': 0.00047560670586780886, 'samples': 11768320, 'steps': 22984, 'loss/train': 2.037463665008545}
-03/04/2022 16:27:36 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/04/2022 16:27:41 - INFO - codeparrot_training - Step 22985: {'lr': 0.0004756044194424792, 'samples': 11768832, 'steps': 22985, 'loss/train': 3.4214882850646973}
-03/04/2022 16:27:44 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 16:27:47 - INFO - codeparrot_training - Step 22986: {'lr': 0.0004756021329154956, 'samples': 11769344, 'steps': 22986, 'loss/train': 2.0647096633911133}
-03/04/2022 16:27:50 - INFO - codeparrot_training - Step 22987: {'lr': 0.0004755998462868592, 'samples': 11769856, 'steps': 22987, 'loss/train': 2.0848288536071777}
-03/04/2022 16:27:53 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/04/2022 16:27:55 - INFO - codeparrot_training - Step 22988: {'lr': 0.00047559755955657097, 'samples': 11770368, 'steps': 22988, 'loss/train': 1.0303720235824585}
-03/04/2022 16:27:58 - INFO - codeparrot_training - Step 22989: {'lr': 0.000475595272724632, 'samples': 11770880, 'steps': 22989, 'loss/train': 1.9435657262802124}
-03/04/2022 16:28:01 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 16:28:04 - INFO - codeparrot_training - Step 22990: {'lr': 0.00047559298579104325, 'samples': 11771392, 'steps': 22990, 'loss/train': 2.1524455547332764}
-03/04/2022 16:28:07 - INFO - codeparrot_training - Step 22991: {'lr': 0.00047559069875580573, 'samples': 11771904, 'steps': 22991, 'loss/train': 1.128570795059204}
-03/04/2022 16:28:09 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/04/2022 16:28:12 - INFO - codeparrot_training - Step 22992: {'lr': 0.00047558841161892063, 'samples': 11772416, 'steps': 22992, 'loss/train': 2.0047812461853027}
-03/04/2022 16:28:15 - INFO - codeparrot_training - Step 22993: {'lr': 0.00047558612438038887, 'samples': 11772928, 'steps': 22993, 'loss/train': 1.740499496459961}
-03/04/2022 16:28:17 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/04/2022 16:28:20 - INFO - codeparrot_training - Step 22994: {'lr': 0.00047558383704021136, 'samples': 11773440, 'steps': 22994, 'loss/train': 1.771320104598999}
-03/04/2022 16:28:23 - INFO - codeparrot_training - Step 22995: {'lr': 0.00047558154959838935, 'samples': 11773952, 'steps': 22995, 'loss/train': 2.0950584411621094}
-03/04/2022 16:28:26 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/04/2022 16:28:29 - INFO - codeparrot_training - Step 22996: {'lr': 0.0004755792620549237, 'samples': 11774464, 'steps': 22996, 'loss/train': 1.9343205690383911}
-03/04/2022 16:28:32 - INFO - codeparrot_training - Step 22997: {'lr': 0.0004755769744098156, 'samples': 11774976, 'steps': 22997, 'loss/train': 2.8106653690338135}
-03/04/2022 16:28:34 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/04/2022 16:28:37 - INFO - codeparrot_training - Step 22998: {'lr': 0.00047557468666306596, 'samples': 11775488, 'steps': 22998, 'loss/train': 1.1588821411132812}
-03/04/2022 16:28:40 - INFO - codeparrot_training - Step 22999: {'lr': 0.00047557239881467584, 'samples': 11776000, 'steps': 22999, 'loss/train': 2.5552332401275635}
-03/04/2022 16:28:43 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/04/2022 16:28:46 - INFO - codeparrot_training - Step 23000: {'lr': 0.0004755701108646463, 'samples': 11776512, 'steps': 23000, 'loss/train': 1.994852900505066}
-03/04/2022 16:28:49 - INFO - codeparrot_training - Step 23001: {'lr': 0.0004755678228129784, 'samples': 11777024, 'steps': 23001, 'loss/train': 1.7953674793243408}
-03/04/2022 16:28:51 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 16:28:55 - INFO - codeparrot_training - Step 23002: {'lr': 0.000475565534659673, 'samples': 11777536, 'steps': 23002, 'loss/train': 2.0082006454467773}
-03/04/2022 16:28:58 - INFO - codeparrot_training - Step 23003: {'lr': 0.00047556324640473134, 'samples': 11778048, 'steps': 23003, 'loss/train': 2.4463489055633545}
-03/04/2022 16:29:01 - INFO - codeparrot_training - Step 23004: {'lr': 0.0004755609580481543, 'samples': 11778560, 'steps': 23004, 'loss/train': 0.4766114056110382}
-03/04/2022 16:29:01 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/04/2022 16:29:06 - INFO - codeparrot_training - Step 23005: {'lr': 0.00047555866958994296, 'samples': 11779072, 'steps': 23005, 'loss/train': 2.430408000946045}
-03/04/2022 16:29:09 - INFO - codeparrot_training - Step 23006: {'lr': 0.00047555638103009845, 'samples': 11779584, 'steps': 23006, 'loss/train': 2.374987840652466}
-03/04/2022 16:29:10 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 16:29:15 - INFO - codeparrot_training - Step 23007: {'lr': 0.0004755540923686217, 'samples': 11780096, 'steps': 23007, 'loss/train': 1.8597408533096313}
-03/04/2022 16:29:18 - INFO - codeparrot_training - Step 23008: {'lr': 0.0004755518036055137, 'samples': 11780608, 'steps': 23008, 'loss/train': 2.040605306625366}
-03/04/2022 16:29:18 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 16:29:23 - INFO - codeparrot_training - Step 23009: {'lr': 0.0004755495147407756, 'samples': 11781120, 'steps': 23009, 'loss/train': 2.5775997638702393}
-03/04/2022 16:29:26 - INFO - codeparrot_training - Step 23010: {'lr': 0.00047554722577440833, 'samples': 11781632, 'steps': 23010, 'loss/train': 1.8656977415084839}
-03/04/2022 16:29:26 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/04/2022 16:29:32 - INFO - codeparrot_training - Step 23011: {'lr': 0.00047554493670641296, 'samples': 11782144, 'steps': 23011, 'loss/train': 1.6410373449325562}
-03/04/2022 16:29:35 - INFO - codeparrot_training - Step 23012: {'lr': 0.0004755426475367905, 'samples': 11782656, 'steps': 23012, 'loss/train': 1.3066271543502808}
-03/04/2022 16:29:35 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/04/2022 16:29:40 - INFO - codeparrot_training - Step 23013: {'lr': 0.00047554035826554206, 'samples': 11783168, 'steps': 23013, 'loss/train': 1.8616985082626343}
-03/04/2022 16:29:43 - INFO - codeparrot_training - Step 23014: {'lr': 0.0004755380688926686, 'samples': 11783680, 'steps': 23014, 'loss/train': 1.6147518157958984}
-03/04/2022 16:29:43 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/04/2022 16:29:48 - INFO - codeparrot_training - Step 23015: {'lr': 0.00047553577941817114, 'samples': 11784192, 'steps': 23015, 'loss/train': 1.8571584224700928}
-03/04/2022 16:29:51 - INFO - codeparrot_training - Step 23016: {'lr': 0.0004755334898420507, 'samples': 11784704, 'steps': 23016, 'loss/train': 2.8200230598449707}
-03/04/2022 16:29:52 - INFO - codeparrot_training - Skipping example with length 158 (seq_length=1024)
-03/04/2022 16:29:57 - INFO - codeparrot_training - Step 23017: {'lr': 0.00047553120016430837, 'samples': 11785216, 'steps': 23017, 'loss/train': 1.8625218868255615}
-03/04/2022 16:30:00 - INFO - codeparrot_training - Step 23018: {'lr': 0.0004755289103849453, 'samples': 11785728, 'steps': 23018, 'loss/train': 1.34120774269104}
-03/04/2022 16:30:00 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/04/2022 16:30:05 - INFO - codeparrot_training - Step 23019: {'lr': 0.0004755266205039622, 'samples': 11786240, 'steps': 23019, 'loss/train': 1.4224921464920044}
-03/04/2022 16:30:09 - INFO - codeparrot_training - Step 23020: {'lr': 0.00047552433052136034, 'samples': 11786752, 'steps': 23020, 'loss/train': 1.2657737731933594}
-03/04/2022 16:30:09 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/04/2022 16:30:14 - INFO - codeparrot_training - Step 23021: {'lr': 0.00047552204043714076, 'samples': 11787264, 'steps': 23021, 'loss/train': 2.0489630699157715}
-03/04/2022 16:30:17 - INFO - codeparrot_training - Step 23022: {'lr': 0.0004755197502513043, 'samples': 11787776, 'steps': 23022, 'loss/train': 3.2108404636383057}
-03/04/2022 16:30:17 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/04/2022 16:30:22 - INFO - codeparrot_training - Step 23023: {'lr': 0.00047551745996385233, 'samples': 11788288, 'steps': 23023, 'loss/train': 2.0837550163269043}
-03/04/2022 16:30:25 - INFO - codeparrot_training - Step 23024: {'lr': 0.00047551516957478545, 'samples': 11788800, 'steps': 23024, 'loss/train': 1.6003386974334717}
-03/04/2022 16:30:26 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/04/2022 16:30:31 - INFO - codeparrot_training - Step 23025: {'lr': 0.0004755128790841051, 'samples': 11789312, 'steps': 23025, 'loss/train': 6.2289018630981445}
-03/04/2022 16:30:34 - INFO - codeparrot_training - Step 23026: {'lr': 0.000475510588491812, 'samples': 11789824, 'steps': 23026, 'loss/train': 1.8534855842590332}
-03/04/2022 16:30:36 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/04/2022 16:30:39 - INFO - codeparrot_training - Step 23027: {'lr': 0.00047550829779790735, 'samples': 11790336, 'steps': 23027, 'loss/train': 2.139492988586426}
-03/04/2022 16:30:43 - INFO - codeparrot_training - Step 23028: {'lr': 0.0004755060070023921, 'samples': 11790848, 'steps': 23028, 'loss/train': 2.332176685333252}
-03/04/2022 16:30:45 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/04/2022 16:30:48 - INFO - codeparrot_training - Step 23029: {'lr': 0.0004755037161052674, 'samples': 11791360, 'steps': 23029, 'loss/train': 1.9241465330123901}
-03/04/2022 16:30:51 - INFO - codeparrot_training - Step 23030: {'lr': 0.00047550142510653415, 'samples': 11791872, 'steps': 23030, 'loss/train': 1.7896934747695923}
-03/04/2022 16:30:53 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/04/2022 16:30:56 - INFO - codeparrot_training - Step 23031: {'lr': 0.0004754991340061935, 'samples': 11792384, 'steps': 23031, 'loss/train': 1.6287156343460083}
-03/04/2022 16:30:59 - INFO - codeparrot_training - Step 23032: {'lr': 0.0004754968428042463, 'samples': 11792896, 'steps': 23032, 'loss/train': 1.6246886253356934}
-03/04/2022 16:31:02 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/04/2022 16:31:05 - INFO - codeparrot_training - Step 23033: {'lr': 0.0004754945515006938, 'samples': 11793408, 'steps': 23033, 'loss/train': 2.1187543869018555}
-03/04/2022 16:31:08 - INFO - codeparrot_training - Step 23034: {'lr': 0.0004754922600955369, 'samples': 11793920, 'steps': 23034, 'loss/train': 1.6580743789672852}
-03/04/2022 16:31:10 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 16:31:13 - INFO - codeparrot_training - Step 23035: {'lr': 0.0004754899685887767, 'samples': 11794432, 'steps': 23035, 'loss/train': 1.9432101249694824}
-03/04/2022 16:31:16 - INFO - codeparrot_training - Step 23036: {'lr': 0.0004754876769804142, 'samples': 11794944, 'steps': 23036, 'loss/train': 2.1283154487609863}
-03/04/2022 16:31:19 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/04/2022 16:31:22 - INFO - codeparrot_training - Step 23037: {'lr': 0.00047548538527045035, 'samples': 11795456, 'steps': 23037, 'loss/train': 1.5924506187438965}
-03/04/2022 16:31:25 - INFO - codeparrot_training - Step 23038: {'lr': 0.00047548309345888637, 'samples': 11795968, 'steps': 23038, 'loss/train': 1.8154445886611938}
-03/04/2022 16:31:29 - INFO - codeparrot_training - Step 23039: {'lr': 0.00047548080154572315, 'samples': 11796480, 'steps': 23039, 'loss/train': 2.1351099014282227}
-03/04/2022 16:31:30 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/04/2022 16:31:34 - INFO - codeparrot_training - Step 23040: {'lr': 0.00047547850953096174, 'samples': 11796992, 'steps': 23040, 'loss/train': 1.688396692276001}
-03/04/2022 16:31:37 - INFO - codeparrot_training - Step 23041: {'lr': 0.0004754762174146032, 'samples': 11797504, 'steps': 23041, 'loss/train': 2.04152512550354}
-03/04/2022 16:31:39 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/04/2022 16:31:42 - INFO - codeparrot_training - Step 23042: {'lr': 0.00047547392519664853, 'samples': 11798016, 'steps': 23042, 'loss/train': 2.2936015129089355}
-03/04/2022 16:31:45 - INFO - codeparrot_training - Step 23043: {'lr': 0.0004754716328770988, 'samples': 11798528, 'steps': 23043, 'loss/train': 1.445263147354126}
-03/04/2022 16:31:47 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/04/2022 16:31:51 - INFO - codeparrot_training - Step 23044: {'lr': 0.00047546934045595516, 'samples': 11799040, 'steps': 23044, 'loss/train': 2.192905902862549}
-03/04/2022 16:31:54 - INFO - codeparrot_training - Step 23045: {'lr': 0.00047546704793321835, 'samples': 11799552, 'steps': 23045, 'loss/train': 1.726205825805664}
-03/04/2022 16:31:55 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 16:31:59 - INFO - codeparrot_training - Step 23046: {'lr': 0.0004754647553088896, 'samples': 11800064, 'steps': 23046, 'loss/train': 1.5424405336380005}
-03/04/2022 16:32:02 - INFO - codeparrot_training - Step 23047: {'lr': 0.00047546246258297, 'samples': 11800576, 'steps': 23047, 'loss/train': 1.509690761566162}
-03/04/2022 16:32:04 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/04/2022 16:32:07 - INFO - codeparrot_training - Step 23048: {'lr': 0.00047546016975546037, 'samples': 11801088, 'steps': 23048, 'loss/train': 1.2615535259246826}
-03/04/2022 16:32:11 - INFO - codeparrot_training - Step 23049: {'lr': 0.00047545787682636194, 'samples': 11801600, 'steps': 23049, 'loss/train': 2.250267267227173}
-03/04/2022 16:32:12 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 16:32:16 - INFO - codeparrot_training - Step 23050: {'lr': 0.00047545558379567565, 'samples': 11802112, 'steps': 23050, 'loss/train': 1.4646823406219482}
-03/04/2022 16:32:19 - INFO - codeparrot_training - Step 23051: {'lr': 0.00047545329066340256, 'samples': 11802624, 'steps': 23051, 'loss/train': 1.7581777572631836}
-03/04/2022 16:32:20 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/04/2022 16:32:24 - INFO - codeparrot_training - Step 23052: {'lr': 0.00047545099742954367, 'samples': 11803136, 'steps': 23052, 'loss/train': 1.7429590225219727}
-03/04/2022 16:32:27 - INFO - codeparrot_training - Step 23053: {'lr': 0.0004754487040941001, 'samples': 11803648, 'steps': 23053, 'loss/train': 1.5483179092407227}
-03/04/2022 16:32:30 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 16:32:33 - INFO - codeparrot_training - Step 23054: {'lr': 0.0004754464106570727, 'samples': 11804160, 'steps': 23054, 'loss/train': 1.3968583345413208}
-03/04/2022 16:32:36 - INFO - codeparrot_training - Step 23055: {'lr': 0.00047544411711846277, 'samples': 11804672, 'steps': 23055, 'loss/train': 2.6310253143310547}
-03/04/2022 16:32:38 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 16:32:41 - INFO - codeparrot_training - Step 23056: {'lr': 0.00047544182347827114, 'samples': 11805184, 'steps': 23056, 'loss/train': 1.6130162477493286}
-03/04/2022 16:32:44 - INFO - codeparrot_training - Step 23057: {'lr': 0.0004754395297364989, 'samples': 11805696, 'steps': 23057, 'loss/train': 0.7534849047660828}
-03/04/2022 16:32:50 - INFO - codeparrot_training - Step 23058: {'lr': 0.0004754372358931471, 'samples': 11806208, 'steps': 23058, 'loss/train': 2.144620418548584}
-03/04/2022 16:32:53 - INFO - codeparrot_training - Step 23059: {'lr': 0.00047543494194821675, 'samples': 11806720, 'steps': 23059, 'loss/train': 1.540574312210083}
-03/04/2022 16:32:55 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/04/2022 16:32:59 - INFO - codeparrot_training - Step 23060: {'lr': 0.00047543264790170887, 'samples': 11807232, 'steps': 23060, 'loss/train': 1.6122313737869263}
-03/04/2022 16:33:02 - INFO - codeparrot_training - Step 23061: {'lr': 0.00047543035375362453, 'samples': 11807744, 'steps': 23061, 'loss/train': 2.5422613620758057}
-03/04/2022 16:33:05 - INFO - codeparrot_training - Step 23062: {'lr': 0.00047542805950396476, 'samples': 11808256, 'steps': 23062, 'loss/train': 2.2535688877105713}
-03/04/2022 16:33:06 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/04/2022 16:33:10 - INFO - codeparrot_training - Step 23063: {'lr': 0.00047542576515273064, 'samples': 11808768, 'steps': 23063, 'loss/train': 2.1243669986724854}
-03/04/2022 16:33:14 - INFO - codeparrot_training - Step 23064: {'lr': 0.0004754234706999231, 'samples': 11809280, 'steps': 23064, 'loss/train': 1.436521291732788}
-03/04/2022 16:33:14 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/04/2022 16:33:19 - INFO - codeparrot_training - Step 23065: {'lr': 0.0004754211761455432, 'samples': 11809792, 'steps': 23065, 'loss/train': 2.0821533203125}
-03/04/2022 16:33:22 - INFO - codeparrot_training - Step 23066: {'lr': 0.000475418881489592, 'samples': 11810304, 'steps': 23066, 'loss/train': 0.8612276315689087}
-03/04/2022 16:33:23 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/04/2022 16:33:27 - INFO - codeparrot_training - Step 23067: {'lr': 0.0004754165867320706, 'samples': 11810816, 'steps': 23067, 'loss/train': 2.5535988807678223}
-03/04/2022 16:33:31 - INFO - codeparrot_training - Step 23068: {'lr': 0.00047541429187297984, 'samples': 11811328, 'steps': 23068, 'loss/train': 1.878833532333374}
-03/04/2022 16:33:32 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 16:33:36 - INFO - codeparrot_training - Step 23069: {'lr': 0.00047541199691232094, 'samples': 11811840, 'steps': 23069, 'loss/train': 1.6413850784301758}
-03/04/2022 16:33:39 - INFO - codeparrot_training - Step 23070: {'lr': 0.0004754097018500949, 'samples': 11812352, 'steps': 23070, 'loss/train': 1.790895700454712}
-03/04/2022 16:33:40 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/04/2022 16:33:44 - INFO - codeparrot_training - Step 23071: {'lr': 0.0004754074066863027, 'samples': 11812864, 'steps': 23071, 'loss/train': 2.0991432666778564}
-03/04/2022 16:33:48 - INFO - codeparrot_training - Step 23072: {'lr': 0.0004754051114209454, 'samples': 11813376, 'steps': 23072, 'loss/train': 1.0667691230773926}
-03/04/2022 16:33:49 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/04/2022 16:33:53 - INFO - codeparrot_training - Step 23073: {'lr': 0.0004754028160540241, 'samples': 11813888, 'steps': 23073, 'loss/train': 1.6967476606369019}
-03/04/2022 16:33:56 - INFO - codeparrot_training - Step 23074: {'lr': 0.0004754005205855397, 'samples': 11814400, 'steps': 23074, 'loss/train': 1.9562907218933105}
-03/04/2022 16:33:57 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/04/2022 16:34:01 - INFO - codeparrot_training - Step 23075: {'lr': 0.0004753982250154933, 'samples': 11814912, 'steps': 23075, 'loss/train': 1.7984105348587036}
-03/04/2022 16:34:04 - INFO - codeparrot_training - Step 23076: {'lr': 0.00047539592934388596, 'samples': 11815424, 'steps': 23076, 'loss/train': 1.6219463348388672}
-03/04/2022 16:34:06 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 16:34:10 - INFO - codeparrot_training - Step 23077: {'lr': 0.0004753936335707187, 'samples': 11815936, 'steps': 23077, 'loss/train': 2.232764720916748}
-03/04/2022 16:34:13 - INFO - codeparrot_training - Step 23078: {'lr': 0.0004753913376959925, 'samples': 11816448, 'steps': 23078, 'loss/train': 2.0959174633026123}
-03/04/2022 16:34:14 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 16:34:18 - INFO - codeparrot_training - Step 23079: {'lr': 0.00047538904171970847, 'samples': 11816960, 'steps': 23079, 'loss/train': 2.0631630420684814}
-03/04/2022 16:34:22 - INFO - codeparrot_training - Step 23080: {'lr': 0.0004753867456418677, 'samples': 11817472, 'steps': 23080, 'loss/train': 0.5025739669799805}
-03/04/2022 16:34:23 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 16:34:27 - INFO - codeparrot_training - Step 23081: {'lr': 0.000475384449462471, 'samples': 11817984, 'steps': 23081, 'loss/train': 2.032984733581543}
-03/04/2022 16:34:30 - INFO - codeparrot_training - Step 23082: {'lr': 0.00047538215318151955, 'samples': 11818496, 'steps': 23082, 'loss/train': 1.2163959741592407}
-03/04/2022 16:34:32 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/04/2022 16:34:35 - INFO - codeparrot_training - Step 23083: {'lr': 0.0004753798567990145, 'samples': 11819008, 'steps': 23083, 'loss/train': 2.0322654247283936}
-03/04/2022 16:34:39 - INFO - codeparrot_training - Step 23084: {'lr': 0.00047537756031495673, 'samples': 11819520, 'steps': 23084, 'loss/train': 3.804889440536499}
-03/04/2022 16:34:41 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 16:34:44 - INFO - codeparrot_training - Step 23085: {'lr': 0.0004753752637293473, 'samples': 11820032, 'steps': 23085, 'loss/train': 1.8004741668701172}
-03/04/2022 16:34:47 - INFO - codeparrot_training - Step 23086: {'lr': 0.0004753729670421871, 'samples': 11820544, 'steps': 23086, 'loss/train': 1.7894450426101685}
-03/04/2022 16:34:49 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/04/2022 16:34:52 - INFO - codeparrot_training - Step 23087: {'lr': 0.0004753706702534775, 'samples': 11821056, 'steps': 23087, 'loss/train': 3.3105361461639404}
-03/04/2022 16:34:55 - INFO - codeparrot_training - Step 23088: {'lr': 0.0004753683733632193, 'samples': 11821568, 'steps': 23088, 'loss/train': 2.203911542892456}
-03/04/2022 16:34:58 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/04/2022 16:35:01 - INFO - codeparrot_training - Step 23089: {'lr': 0.0004753660763714136, 'samples': 11822080, 'steps': 23089, 'loss/train': 0.8561584949493408}
-03/04/2022 16:35:04 - INFO - codeparrot_training - Step 23090: {'lr': 0.00047536377927806143, 'samples': 11822592, 'steps': 23090, 'loss/train': 2.3126933574676514}
-03/04/2022 16:35:07 - INFO - codeparrot_training - Step 23091: {'lr': 0.0004753614820831638, 'samples': 11823104, 'steps': 23091, 'loss/train': 2.8475263118743896}
-03/04/2022 16:35:08 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 16:35:13 - INFO - codeparrot_training - Step 23092: {'lr': 0.0004753591847867218, 'samples': 11823616, 'steps': 23092, 'loss/train': 1.6417335271835327}
-03/04/2022 16:35:16 - INFO - codeparrot_training - Step 23093: {'lr': 0.0004753568873887364, 'samples': 11824128, 'steps': 23093, 'loss/train': 2.3573687076568604}
-03/04/2022 16:35:16 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/04/2022 16:35:22 - INFO - codeparrot_training - Step 23094: {'lr': 0.00047535458988920865, 'samples': 11824640, 'steps': 23094, 'loss/train': 2.2507686614990234}
-03/04/2022 16:35:25 - INFO - codeparrot_training - Step 23095: {'lr': 0.0004753522922881396, 'samples': 11825152, 'steps': 23095, 'loss/train': 1.3484667539596558}
-03/04/2022 16:35:28 - INFO - codeparrot_training - Step 23096: {'lr': 0.00047534999458553027, 'samples': 11825664, 'steps': 23096, 'loss/train': 1.5285576581954956}
-03/04/2022 16:35:28 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/04/2022 16:35:33 - INFO - codeparrot_training - Step 23097: {'lr': 0.00047534769678138177, 'samples': 11826176, 'steps': 23097, 'loss/train': 1.8699986934661865}
-03/04/2022 16:35:36 - INFO - codeparrot_training - Step 23098: {'lr': 0.00047534539887569507, 'samples': 11826688, 'steps': 23098, 'loss/train': 2.5110912322998047}
-03/04/2022 16:35:37 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 16:35:42 - INFO - codeparrot_training - Step 23099: {'lr': 0.00047534310086847116, 'samples': 11827200, 'steps': 23099, 'loss/train': 1.549009084701538}
-03/04/2022 16:35:45 - INFO - codeparrot_training - Step 23100: {'lr': 0.0004753408027597111, 'samples': 11827712, 'steps': 23100, 'loss/train': 2.0238702297210693}
-03/04/2022 16:35:45 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/04/2022 16:35:50 - INFO - codeparrot_training - Step 23101: {'lr': 0.0004753385045494161, 'samples': 11828224, 'steps': 23101, 'loss/train': 1.4151208400726318}
-03/04/2022 16:35:53 - INFO - codeparrot_training - Step 23102: {'lr': 0.0004753362062375869, 'samples': 11828736, 'steps': 23102, 'loss/train': 2.0502240657806396}
-03/04/2022 16:35:54 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/04/2022 16:35:59 - INFO - codeparrot_training - Step 23103: {'lr': 0.0004753339078242247, 'samples': 11829248, 'steps': 23103, 'loss/train': 1.7592886686325073}
-03/04/2022 16:36:02 - INFO - codeparrot_training - Step 23104: {'lr': 0.00047533160930933054, 'samples': 11829760, 'steps': 23104, 'loss/train': 2.433387279510498}
-03/04/2022 16:36:02 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/04/2022 16:36:07 - INFO - codeparrot_training - Step 23105: {'lr': 0.00047532931069290546, 'samples': 11830272, 'steps': 23105, 'loss/train': 2.179884433746338}
-03/04/2022 16:36:10 - INFO - codeparrot_training - Step 23106: {'lr': 0.00047532701197495043, 'samples': 11830784, 'steps': 23106, 'loss/train': 4.407009601593018}
-03/04/2022 16:36:11 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 16:36:16 - INFO - codeparrot_training - Step 23107: {'lr': 0.00047532471315546654, 'samples': 11831296, 'steps': 23107, 'loss/train': 1.6212294101715088}
-03/04/2022 16:36:19 - INFO - codeparrot_training - Step 23108: {'lr': 0.00047532241423445487, 'samples': 11831808, 'steps': 23108, 'loss/train': 1.8825764656066895}
-03/04/2022 16:36:19 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 16:36:24 - INFO - codeparrot_training - Step 23109: {'lr': 0.00047532011521191634, 'samples': 11832320, 'steps': 23109, 'loss/train': 2.4214417934417725}
-03/04/2022 16:36:27 - INFO - codeparrot_training - Step 23110: {'lr': 0.00047531781608785203, 'samples': 11832832, 'steps': 23110, 'loss/train': 1.827053189277649}
-03/04/2022 16:36:27 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/04/2022 16:36:33 - INFO - codeparrot_training - Step 23111: {'lr': 0.00047531551686226303, 'samples': 11833344, 'steps': 23111, 'loss/train': 0.8318002820014954}
-03/04/2022 16:36:36 - INFO - codeparrot_training - Step 23112: {'lr': 0.00047531321753515026, 'samples': 11833856, 'steps': 23112, 'loss/train': 1.63663911819458}
-03/04/2022 16:36:36 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/04/2022 16:36:41 - INFO - codeparrot_training - Step 23113: {'lr': 0.0004753109181065149, 'samples': 11834368, 'steps': 23113, 'loss/train': 2.08450984954834}
-03/04/2022 16:36:44 - INFO - codeparrot_training - Step 23114: {'lr': 0.00047530861857635786, 'samples': 11834880, 'steps': 23114, 'loss/train': 2.0302882194519043}
-03/04/2022 16:36:45 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 16:36:50 - INFO - codeparrot_training - Step 23115: {'lr': 0.00047530631894468034, 'samples': 11835392, 'steps': 23115, 'loss/train': 1.8528622388839722}
-03/04/2022 16:36:53 - INFO - codeparrot_training - Step 23116: {'lr': 0.0004753040192114831, 'samples': 11835904, 'steps': 23116, 'loss/train': 1.9577503204345703}
-03/04/2022 16:36:53 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 16:36:58 - INFO - codeparrot_training - Step 23117: {'lr': 0.00047530171937676754, 'samples': 11836416, 'steps': 23117, 'loss/train': 1.5306718349456787}
-03/04/2022 16:37:01 - INFO - codeparrot_training - Step 23118: {'lr': 0.0004752994194405344, 'samples': 11836928, 'steps': 23118, 'loss/train': 2.3487672805786133}
-03/04/2022 16:37:02 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/04/2022 16:37:07 - INFO - codeparrot_training - Step 23119: {'lr': 0.0004752971194027848, 'samples': 11837440, 'steps': 23119, 'loss/train': 1.8173080682754517}
-03/04/2022 16:37:10 - INFO - codeparrot_training - Step 23120: {'lr': 0.0004752948192635198, 'samples': 11837952, 'steps': 23120, 'loss/train': 1.9992766380310059}
-03/04/2022 16:37:10 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 16:37:15 - INFO - codeparrot_training - Step 23121: {'lr': 0.0004752925190227405, 'samples': 11838464, 'steps': 23121, 'loss/train': 0.9863783121109009}
-03/04/2022 16:37:18 - INFO - codeparrot_training - Step 23122: {'lr': 0.0004752902186804478, 'samples': 11838976, 'steps': 23122, 'loss/train': 2.241175413131714}
-03/04/2022 16:37:19 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/04/2022 16:37:23 - INFO - codeparrot_training - Step 23123: {'lr': 0.0004752879182366429, 'samples': 11839488, 'steps': 23123, 'loss/train': 2.085106134414673}
-03/04/2022 16:37:26 - INFO - codeparrot_training - Step 23124: {'lr': 0.0004752856176913266, 'samples': 11840000, 'steps': 23124, 'loss/train': 1.8239665031433105}
-03/04/2022 16:37:27 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/04/2022 16:37:32 - INFO - codeparrot_training - Step 23125: {'lr': 0.0004752833170445001, 'samples': 11840512, 'steps': 23125, 'loss/train': 1.6510252952575684}
-03/04/2022 16:37:35 - INFO - codeparrot_training - Step 23126: {'lr': 0.0004752810162961645, 'samples': 11841024, 'steps': 23126, 'loss/train': 2.223454713821411}
-03/04/2022 16:37:36 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/04/2022 16:37:40 - INFO - codeparrot_training - Step 23127: {'lr': 0.0004752787154463207, 'samples': 11841536, 'steps': 23127, 'loss/train': 1.3779000043869019}
-03/04/2022 16:37:43 - INFO - codeparrot_training - Step 23128: {'lr': 0.0004752764144949698, 'samples': 11842048, 'steps': 23128, 'loss/train': 2.237727403640747}
-03/04/2022 16:37:45 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/04/2022 16:37:49 - INFO - codeparrot_training - Step 23129: {'lr': 0.0004752741134421128, 'samples': 11842560, 'steps': 23129, 'loss/train': 1.6545382738113403}
-03/04/2022 16:37:52 - INFO - codeparrot_training - Step 23130: {'lr': 0.00047527181228775077, 'samples': 11843072, 'steps': 23130, 'loss/train': 1.7035603523254395}
-03/04/2022 16:37:53 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/04/2022 16:37:57 - INFO - codeparrot_training - Step 23131: {'lr': 0.0004752695110318848, 'samples': 11843584, 'steps': 23131, 'loss/train': 1.5229278802871704}
-03/04/2022 16:38:00 - INFO - codeparrot_training - Step 23132: {'lr': 0.00047526720967451573, 'samples': 11844096, 'steps': 23132, 'loss/train': 1.8826240301132202}
-03/04/2022 16:38:02 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/04/2022 16:38:06 - INFO - codeparrot_training - Step 23133: {'lr': 0.0004752649082156448, 'samples': 11844608, 'steps': 23133, 'loss/train': 1.5709871053695679}
-03/04/2022 16:38:09 - INFO - codeparrot_training - Step 23134: {'lr': 0.00047526260665527306, 'samples': 11845120, 'steps': 23134, 'loss/train': 4.263085842132568}
-03/04/2022 16:38:10 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/04/2022 16:38:14 - INFO - codeparrot_training - Step 23135: {'lr': 0.0004752603049934014, 'samples': 11845632, 'steps': 23135, 'loss/train': 0.931387186050415}
-03/04/2022 16:38:17 - INFO - codeparrot_training - Step 23136: {'lr': 0.0004752580032300309, 'samples': 11846144, 'steps': 23136, 'loss/train': 0.9280657172203064}
-03/04/2022 16:38:19 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/04/2022 16:38:22 - INFO - codeparrot_training - Step 23137: {'lr': 0.0004752557013651626, 'samples': 11846656, 'steps': 23137, 'loss/train': 1.8201422691345215}
-03/04/2022 16:38:26 - INFO - codeparrot_training - Step 23138: {'lr': 0.00047525339939879764, 'samples': 11847168, 'steps': 23138, 'loss/train': 1.7588602304458618}
-03/04/2022 16:38:27 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/04/2022 16:38:31 - INFO - codeparrot_training - Step 23139: {'lr': 0.0004752510973309369, 'samples': 11847680, 'steps': 23139, 'loss/train': 1.0945727825164795}
-03/04/2022 16:38:34 - INFO - codeparrot_training - Step 23140: {'lr': 0.00047524879516158155, 'samples': 11848192, 'steps': 23140, 'loss/train': 2.300016403198242}
-03/04/2022 16:38:36 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 16:38:39 - INFO - codeparrot_training - Step 23141: {'lr': 0.00047524649289073254, 'samples': 11848704, 'steps': 23141, 'loss/train': 1.8613742589950562}
-03/04/2022 16:38:43 - INFO - codeparrot_training - Step 23142: {'lr': 0.00047524419051839093, 'samples': 11849216, 'steps': 23142, 'loss/train': 1.7196059226989746}
-03/04/2022 16:38:45 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 16:38:48 - INFO - codeparrot_training - Step 23143: {'lr': 0.00047524188804455776, 'samples': 11849728, 'steps': 23143, 'loss/train': 2.2095608711242676}
-03/04/2022 16:38:51 - INFO - codeparrot_training - Step 23144: {'lr': 0.0004752395854692341, 'samples': 11850240, 'steps': 23144, 'loss/train': 2.335162878036499}
-03/04/2022 16:38:53 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 16:38:56 - INFO - codeparrot_training - Step 23145: {'lr': 0.0004752372827924209, 'samples': 11850752, 'steps': 23145, 'loss/train': 1.929175853729248}
-03/04/2022 16:38:59 - INFO - codeparrot_training - Step 23146: {'lr': 0.0004752349800141193, 'samples': 11851264, 'steps': 23146, 'loss/train': 2.6965572834014893}
-03/04/2022 16:39:02 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 16:39:05 - INFO - codeparrot_training - Step 23147: {'lr': 0.0004752326771343303, 'samples': 11851776, 'steps': 23147, 'loss/train': 1.53349769115448}
-03/04/2022 16:39:08 - INFO - codeparrot_training - Step 23148: {'lr': 0.00047523037415305494, 'samples': 11852288, 'steps': 23148, 'loss/train': 0.49059218168258667}
-03/04/2022 16:39:10 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/04/2022 16:39:13 - INFO - codeparrot_training - Step 23149: {'lr': 0.0004752280710702942, 'samples': 11852800, 'steps': 23149, 'loss/train': 2.1101698875427246}
-03/04/2022 16:39:16 - INFO - codeparrot_training - Step 23150: {'lr': 0.0004752257678860492, 'samples': 11853312, 'steps': 23150, 'loss/train': 2.3917670249938965}
-03/04/2022 16:39:20 - INFO - codeparrot_training - Step 23151: {'lr': 0.00047522346460032093, 'samples': 11853824, 'steps': 23151, 'loss/train': 1.9076279401779175}
-03/04/2022 16:39:20 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/04/2022 16:39:25 - INFO - codeparrot_training - Step 23152: {'lr': 0.0004752211612131104, 'samples': 11854336, 'steps': 23152, 'loss/train': 1.5884345769882202}
-03/04/2022 16:39:28 - INFO - codeparrot_training - Step 23153: {'lr': 0.00047521885772441874, 'samples': 11854848, 'steps': 23153, 'loss/train': 1.9376013278961182}
-03/04/2022 16:39:28 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/04/2022 16:39:34 - INFO - codeparrot_training - Step 23154: {'lr': 0.00047521655413424705, 'samples': 11855360, 'steps': 23154, 'loss/train': 1.9507161378860474}
-03/04/2022 16:39:37 - INFO - codeparrot_training - Step 23155: {'lr': 0.0004752142504425961, 'samples': 11855872, 'steps': 23155, 'loss/train': 1.5065698623657227}
-03/04/2022 16:39:37 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 16:39:42 - INFO - codeparrot_training - Step 23156: {'lr': 0.0004752119466494671, 'samples': 11856384, 'steps': 23156, 'loss/train': 2.0272810459136963}
-03/04/2022 16:39:45 - INFO - codeparrot_training - Step 23157: {'lr': 0.0004752096427548611, 'samples': 11856896, 'steps': 23157, 'loss/train': 1.5631744861602783}
-03/04/2022 16:39:46 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 16:39:51 - INFO - codeparrot_training - Step 23158: {'lr': 0.00047520733875877906, 'samples': 11857408, 'steps': 23158, 'loss/train': 0.9624627232551575}
-03/04/2022 16:39:54 - INFO - codeparrot_training - Step 23159: {'lr': 0.00047520503466122216, 'samples': 11857920, 'steps': 23159, 'loss/train': 2.444775342941284}
-03/04/2022 16:39:55 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/04/2022 16:39:59 - INFO - codeparrot_training - Step 23160: {'lr': 0.0004752027304621913, 'samples': 11858432, 'steps': 23160, 'loss/train': 1.7572758197784424}
-03/04/2022 16:40:02 - INFO - codeparrot_training - Step 23161: {'lr': 0.0004752004261616876, 'samples': 11858944, 'steps': 23161, 'loss/train': 1.698852777481079}
-03/04/2022 16:40:03 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 16:40:08 - INFO - codeparrot_training - Step 23162: {'lr': 0.000475198121759712, 'samples': 11859456, 'steps': 23162, 'loss/train': 1.5456608533859253}
-03/04/2022 16:40:11 - INFO - codeparrot_training - Step 23163: {'lr': 0.0004751958172562656, 'samples': 11859968, 'steps': 23163, 'loss/train': 1.4350578784942627}
-03/04/2022 16:40:11 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 16:40:16 - INFO - codeparrot_training - Step 23164: {'lr': 0.00047519351265134954, 'samples': 11860480, 'steps': 23164, 'loss/train': 1.976426601409912}
-03/04/2022 16:40:19 - INFO - codeparrot_training - Step 23165: {'lr': 0.00047519120794496466, 'samples': 11860992, 'steps': 23165, 'loss/train': 0.5072129368782043}
-03/04/2022 16:40:20 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 16:40:25 - INFO - codeparrot_training - Step 23166: {'lr': 0.00047518890313711217, 'samples': 11861504, 'steps': 23166, 'loss/train': 2.3028182983398438}
-03/04/2022 16:40:28 - INFO - codeparrot_training - Step 23167: {'lr': 0.000475186598227793, 'samples': 11862016, 'steps': 23167, 'loss/train': 3.029904365539551}
-03/04/2022 16:40:30 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/04/2022 16:40:33 - INFO - codeparrot_training - Step 23168: {'lr': 0.0004751842932170082, 'samples': 11862528, 'steps': 23168, 'loss/train': 2.0368826389312744}
-03/04/2022 16:40:36 - INFO - codeparrot_training - Step 23169: {'lr': 0.00047518198810475885, 'samples': 11863040, 'steps': 23169, 'loss/train': 2.1336557865142822}
-03/04/2022 16:40:38 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/04/2022 16:40:42 - INFO - codeparrot_training - Step 23170: {'lr': 0.00047517968289104596, 'samples': 11863552, 'steps': 23170, 'loss/train': 0.4163428246974945}
-03/04/2022 16:40:45 - INFO - codeparrot_training - Step 23171: {'lr': 0.0004751773775758706, 'samples': 11864064, 'steps': 23171, 'loss/train': 2.602907657623291}
-03/04/2022 16:40:47 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/04/2022 16:40:50 - INFO - codeparrot_training - Step 23172: {'lr': 0.00047517507215923376, 'samples': 11864576, 'steps': 23172, 'loss/train': 1.5484733581542969}
-03/04/2022 16:40:53 - INFO - codeparrot_training - Step 23173: {'lr': 0.00047517276664113653, 'samples': 11865088, 'steps': 23173, 'loss/train': 2.38571834564209}
-03/04/2022 16:40:55 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 16:40:59 - INFO - codeparrot_training - Step 23174: {'lr': 0.0004751704610215799, 'samples': 11865600, 'steps': 23174, 'loss/train': 1.8911632299423218}
-03/04/2022 16:41:02 - INFO - codeparrot_training - Step 23175: {'lr': 0.000475168155300565, 'samples': 11866112, 'steps': 23175, 'loss/train': 1.920558214187622}
-03/04/2022 16:41:04 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/04/2022 16:41:07 - INFO - codeparrot_training - Step 23176: {'lr': 0.00047516584947809274, 'samples': 11866624, 'steps': 23176, 'loss/train': 2.195065498352051}
-03/04/2022 16:41:10 - INFO - codeparrot_training - Step 23177: {'lr': 0.00047516354355416426, 'samples': 11867136, 'steps': 23177, 'loss/train': 1.7592113018035889}
-03/04/2022 16:41:12 - INFO - codeparrot_training - Skipping example with length 524 (seq_length=1024)
-03/04/2022 16:41:16 - INFO - codeparrot_training - Step 23178: {'lr': 0.00047516123752878054, 'samples': 11867648, 'steps': 23178, 'loss/train': 0.650576651096344}
-03/04/2022 16:41:19 - INFO - codeparrot_training - Step 23179: {'lr': 0.00047515893140194265, 'samples': 11868160, 'steps': 23179, 'loss/train': 2.4016125202178955}
-03/04/2022 16:41:21 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/04/2022 16:41:24 - INFO - codeparrot_training - Step 23180: {'lr': 0.0004751566251736516, 'samples': 11868672, 'steps': 23180, 'loss/train': 1.367958664894104}
-03/04/2022 16:41:27 - INFO - codeparrot_training - Step 23181: {'lr': 0.00047515431884390845, 'samples': 11869184, 'steps': 23181, 'loss/train': 0.4842330515384674}
-03/04/2022 16:41:29 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/04/2022 16:41:32 - INFO - codeparrot_training - Step 23182: {'lr': 0.00047515201241271426, 'samples': 11869696, 'steps': 23182, 'loss/train': 2.0785350799560547}
-03/04/2022 16:41:36 - INFO - codeparrot_training - Step 23183: {'lr': 0.00047514970588007007, 'samples': 11870208, 'steps': 23183, 'loss/train': 2.246145725250244}
-03/04/2022 16:41:37 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 16:41:41 - INFO - codeparrot_training - Step 23184: {'lr': 0.0004751473992459768, 'samples': 11870720, 'steps': 23184, 'loss/train': 0.2184327393770218}
-03/04/2022 16:41:44 - INFO - codeparrot_training - Step 23185: {'lr': 0.0004751450925104357, 'samples': 11871232, 'steps': 23185, 'loss/train': 2.077575206756592}
-03/04/2022 16:41:46 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/04/2022 16:41:49 - INFO - codeparrot_training - Step 23186: {'lr': 0.00047514278567344765, 'samples': 11871744, 'steps': 23186, 'loss/train': 2.5997774600982666}
-03/04/2022 16:41:52 - INFO - codeparrot_training - Step 23187: {'lr': 0.00047514047873501374, 'samples': 11872256, 'steps': 23187, 'loss/train': 1.9030721187591553}
-03/04/2022 16:41:54 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 16:41:58 - INFO - codeparrot_training - Step 23188: {'lr': 0.000475138171695135, 'samples': 11872768, 'steps': 23188, 'loss/train': 1.8333888053894043}
-03/04/2022 16:42:01 - INFO - codeparrot_training - Step 23189: {'lr': 0.00047513586455381245, 'samples': 11873280, 'steps': 23189, 'loss/train': 3.1604721546173096}
-03/04/2022 16:42:02 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 16:42:06 - INFO - codeparrot_training - Step 23190: {'lr': 0.00047513355731104717, 'samples': 11873792, 'steps': 23190, 'loss/train': 1.048467993736267}
-03/04/2022 16:42:09 - INFO - codeparrot_training - Step 23191: {'lr': 0.0004751312499668402, 'samples': 11874304, 'steps': 23191, 'loss/train': 1.2705897092819214}
-03/04/2022 16:42:11 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/04/2022 16:42:15 - INFO - codeparrot_training - Step 23192: {'lr': 0.00047512894252119256, 'samples': 11874816, 'steps': 23192, 'loss/train': 1.7074545621871948}
-03/04/2022 16:42:18 - INFO - codeparrot_training - Step 23193: {'lr': 0.0004751266349741053, 'samples': 11875328, 'steps': 23193, 'loss/train': 1.554880142211914}
-03/04/2022 16:42:20 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/04/2022 16:42:23 - INFO - codeparrot_training - Step 23194: {'lr': 0.0004751243273255794, 'samples': 11875840, 'steps': 23194, 'loss/train': 1.5918833017349243}
-03/04/2022 16:42:26 - INFO - codeparrot_training - Step 23195: {'lr': 0.000475122019575616, 'samples': 11876352, 'steps': 23195, 'loss/train': 2.129276990890503}
-03/04/2022 16:42:28 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/04/2022 16:42:32 - INFO - codeparrot_training - Step 23196: {'lr': 0.0004751197117242161, 'samples': 11876864, 'steps': 23196, 'loss/train': 1.8442822694778442}
-03/04/2022 16:42:35 - INFO - codeparrot_training - Step 23197: {'lr': 0.0004751174037713807, 'samples': 11877376, 'steps': 23197, 'loss/train': 2.510540008544922}
-03/04/2022 16:42:37 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/04/2022 16:42:40 - INFO - codeparrot_training - Step 23198: {'lr': 0.00047511509571711085, 'samples': 11877888, 'steps': 23198, 'loss/train': 2.797114372253418}
-03/04/2022 16:42:43 - INFO - codeparrot_training - Step 23199: {'lr': 0.00047511278756140766, 'samples': 11878400, 'steps': 23199, 'loss/train': 1.7481770515441895}
-03/04/2022 16:42:45 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/04/2022 16:42:48 - INFO - codeparrot_training - Step 23200: {'lr': 0.00047511047930427216, 'samples': 11878912, 'steps': 23200, 'loss/train': 2.042721748352051}
-03/04/2022 16:42:52 - INFO - codeparrot_training - Step 23201: {'lr': 0.00047510817094570526, 'samples': 11879424, 'steps': 23201, 'loss/train': 2.2307982444763184}
-03/04/2022 16:42:53 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 16:42:57 - INFO - codeparrot_training - Step 23202: {'lr': 0.00047510586248570815, 'samples': 11879936, 'steps': 23202, 'loss/train': 2.3846328258514404}
-03/04/2022 16:43:00 - INFO - codeparrot_training - Step 23203: {'lr': 0.00047510355392428176, 'samples': 11880448, 'steps': 23203, 'loss/train': 2.149144411087036}
-03/04/2022 16:43:02 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 16:43:05 - INFO - codeparrot_training - Step 23204: {'lr': 0.00047510124526142723, 'samples': 11880960, 'steps': 23204, 'loss/train': 2.113197088241577}
-03/04/2022 16:43:09 - INFO - codeparrot_training - Step 23205: {'lr': 0.00047509893649714554, 'samples': 11881472, 'steps': 23205, 'loss/train': 1.2601821422576904}
-03/04/2022 16:43:11 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 16:43:14 - INFO - codeparrot_training - Step 23206: {'lr': 0.00047509662763143775, 'samples': 11881984, 'steps': 23206, 'loss/train': 1.681097388267517}
-03/04/2022 16:43:17 - INFO - codeparrot_training - Step 23207: {'lr': 0.00047509431866430487, 'samples': 11882496, 'steps': 23207, 'loss/train': 0.9996436834335327}
-03/04/2022 16:43:19 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 16:43:22 - INFO - codeparrot_training - Step 23208: {'lr': 0.000475092009595748, 'samples': 11883008, 'steps': 23208, 'loss/train': 2.12515926361084}
-03/04/2022 16:43:26 - INFO - codeparrot_training - Step 23209: {'lr': 0.0004750897004257681, 'samples': 11883520, 'steps': 23209, 'loss/train': 1.9865151643753052}
-03/04/2022 16:43:31 - INFO - codeparrot_training - Step 23210: {'lr': 0.0004750873911543663, 'samples': 11884032, 'steps': 23210, 'loss/train': 1.2823290824890137}
-03/04/2022 16:43:34 - INFO - codeparrot_training - Step 23211: {'lr': 0.00047508508178154354, 'samples': 11884544, 'steps': 23211, 'loss/train': 1.5993494987487793}
-03/04/2022 16:43:37 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/04/2022 16:43:39 - INFO - codeparrot_training - Step 23212: {'lr': 0.00047508277230730095, 'samples': 11885056, 'steps': 23212, 'loss/train': 2.489546537399292}
-03/04/2022 16:43:43 - INFO - codeparrot_training - Step 23213: {'lr': 0.00047508046273163953, 'samples': 11885568, 'steps': 23213, 'loss/train': 1.9989416599273682}
-03/04/2022 16:43:45 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/04/2022 16:43:48 - INFO - codeparrot_training - Step 23214: {'lr': 0.0004750781530545603, 'samples': 11886080, 'steps': 23214, 'loss/train': 0.9731683135032654}
-03/04/2022 16:43:51 - INFO - codeparrot_training - Step 23215: {'lr': 0.0004750758432760644, 'samples': 11886592, 'steps': 23215, 'loss/train': 2.5060012340545654}
-03/04/2022 16:43:54 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 16:43:56 - INFO - codeparrot_training - Step 23216: {'lr': 0.0004750735333961527, 'samples': 11887104, 'steps': 23216, 'loss/train': 1.6150681972503662}
-03/04/2022 16:43:59 - INFO - codeparrot_training - Step 23217: {'lr': 0.00047507122341482644, 'samples': 11887616, 'steps': 23217, 'loss/train': 1.8424334526062012}
-03/04/2022 16:44:02 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/04/2022 16:44:05 - INFO - codeparrot_training - Step 23218: {'lr': 0.00047506891333208654, 'samples': 11888128, 'steps': 23218, 'loss/train': 1.9041028022766113}
-03/04/2022 16:44:08 - INFO - codeparrot_training - Step 23219: {'lr': 0.000475066603147934, 'samples': 11888640, 'steps': 23219, 'loss/train': 1.6045600175857544}
-03/04/2022 16:44:11 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 16:44:13 - INFO - codeparrot_training - Step 23220: {'lr': 0.00047506429286236997, 'samples': 11889152, 'steps': 23220, 'loss/train': 1.3972278833389282}
-03/04/2022 16:44:16 - INFO - codeparrot_training - Step 23221: {'lr': 0.00047506198247539546, 'samples': 11889664, 'steps': 23221, 'loss/train': 2.0493619441986084}
-03/04/2022 16:44:20 - INFO - codeparrot_training - Step 23222: {'lr': 0.0004750596719870114, 'samples': 11890176, 'steps': 23222, 'loss/train': 1.0680570602416992}
-03/04/2022 16:44:20 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 16:44:25 - INFO - codeparrot_training - Step 23223: {'lr': 0.000475057361397219, 'samples': 11890688, 'steps': 23223, 'loss/train': 2.067452907562256}
-03/04/2022 16:44:28 - INFO - codeparrot_training - Step 23224: {'lr': 0.0004750550507060192, 'samples': 11891200, 'steps': 23224, 'loss/train': 2.375077962875366}
-03/04/2022 16:44:30 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 16:44:34 - INFO - codeparrot_training - Step 23225: {'lr': 0.0004750527399134131, 'samples': 11891712, 'steps': 23225, 'loss/train': 2.5771713256835938}
-03/04/2022 16:44:37 - INFO - codeparrot_training - Step 23226: {'lr': 0.00047505042901940163, 'samples': 11892224, 'steps': 23226, 'loss/train': 4.00886869430542}
-03/04/2022 16:44:39 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/04/2022 16:44:42 - INFO - codeparrot_training - Step 23227: {'lr': 0.00047504811802398603, 'samples': 11892736, 'steps': 23227, 'loss/train': 2.4122233390808105}
-03/04/2022 16:44:45 - INFO - codeparrot_training - Step 23228: {'lr': 0.0004750458069271671, 'samples': 11893248, 'steps': 23228, 'loss/train': 1.5195339918136597}
-03/04/2022 16:44:47 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/04/2022 16:44:51 - INFO - codeparrot_training - Step 23229: {'lr': 0.0004750434957289461, 'samples': 11893760, 'steps': 23229, 'loss/train': 2.001708984375}
-03/04/2022 16:44:54 - INFO - codeparrot_training - Step 23230: {'lr': 0.0004750411844293239, 'samples': 11894272, 'steps': 23230, 'loss/train': 1.887816309928894}
-03/04/2022 16:44:56 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 16:44:59 - INFO - codeparrot_training - Step 23231: {'lr': 0.0004750388730283016, 'samples': 11894784, 'steps': 23231, 'loss/train': 1.5888465642929077}
-03/04/2022 16:45:02 - INFO - codeparrot_training - Step 23232: {'lr': 0.0004750365615258804, 'samples': 11895296, 'steps': 23232, 'loss/train': 2.467845916748047}
-03/04/2022 16:45:04 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/04/2022 16:45:08 - INFO - codeparrot_training - Step 23233: {'lr': 0.00047503424992206107, 'samples': 11895808, 'steps': 23233, 'loss/train': 1.9950379133224487}
-03/04/2022 16:45:11 - INFO - codeparrot_training - Step 23234: {'lr': 0.00047503193821684476, 'samples': 11896320, 'steps': 23234, 'loss/train': 2.179570436477661}
-03/04/2022 16:45:12 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/04/2022 16:45:16 - INFO - codeparrot_training - Step 23235: {'lr': 0.0004750296264102326, 'samples': 11896832, 'steps': 23235, 'loss/train': 2.0285236835479736}
-03/04/2022 16:45:19 - INFO - codeparrot_training - Step 23236: {'lr': 0.0004750273145022256, 'samples': 11897344, 'steps': 23236, 'loss/train': 1.436415433883667}
-03/04/2022 16:45:20 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 16:45:24 - INFO - codeparrot_training - Step 23237: {'lr': 0.00047502500249282464, 'samples': 11897856, 'steps': 23237, 'loss/train': 2.2570817470550537}
-03/04/2022 16:45:28 - INFO - codeparrot_training - Step 23238: {'lr': 0.000475022690382031, 'samples': 11898368, 'steps': 23238, 'loss/train': 1.4422721862792969}
-03/04/2022 16:45:29 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 16:45:33 - INFO - codeparrot_training - Step 23239: {'lr': 0.0004750203781698456, 'samples': 11898880, 'steps': 23239, 'loss/train': 0.9484816193580627}
-03/04/2022 16:45:36 - INFO - codeparrot_training - Step 23240: {'lr': 0.0004750180658562694, 'samples': 11899392, 'steps': 23240, 'loss/train': 1.9728771448135376}
-03/04/2022 16:45:37 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 16:45:41 - INFO - codeparrot_training - Step 23241: {'lr': 0.00047501575344130356, 'samples': 11899904, 'steps': 23241, 'loss/train': 1.2998861074447632}
-03/04/2022 16:45:44 - INFO - codeparrot_training - Step 23242: {'lr': 0.00047501344092494915, 'samples': 11900416, 'steps': 23242, 'loss/train': 1.3667830228805542}
-03/04/2022 16:45:46 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/04/2022 16:45:50 - INFO - codeparrot_training - Step 23243: {'lr': 0.0004750111283072071, 'samples': 11900928, 'steps': 23243, 'loss/train': 2.3024253845214844}
-03/04/2022 16:45:53 - INFO - codeparrot_training - Step 23244: {'lr': 0.00047500881558807854, 'samples': 11901440, 'steps': 23244, 'loss/train': 1.5687717199325562}
-03/04/2022 16:45:54 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/04/2022 16:45:58 - INFO - codeparrot_training - Step 23245: {'lr': 0.00047500650276756455, 'samples': 11901952, 'steps': 23245, 'loss/train': 2.361098527908325}
-03/04/2022 16:46:01 - INFO - codeparrot_training - Step 23246: {'lr': 0.00047500418984566594, 'samples': 11902464, 'steps': 23246, 'loss/train': 1.5479620695114136}
-03/04/2022 16:46:03 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/04/2022 16:46:06 - INFO - codeparrot_training - Step 23247: {'lr': 0.000475001876822384, 'samples': 11902976, 'steps': 23247, 'loss/train': 1.529552936553955}
-03/04/2022 16:46:10 - INFO - codeparrot_training - Step 23248: {'lr': 0.00047499956369771967, 'samples': 11903488, 'steps': 23248, 'loss/train': 2.109652280807495}
-03/04/2022 16:46:11 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 16:46:15 - INFO - codeparrot_training - Step 23249: {'lr': 0.00047499725047167406, 'samples': 11904000, 'steps': 23249, 'loss/train': 2.3392512798309326}
-03/04/2022 16:46:18 - INFO - codeparrot_training - Step 23250: {'lr': 0.0004749949371442481, 'samples': 11904512, 'steps': 23250, 'loss/train': 1.2236404418945312}
-03/04/2022 16:46:23 - INFO - codeparrot_training - Step 23251: {'lr': 0.00047499262371544294, 'samples': 11905024, 'steps': 23251, 'loss/train': 1.9393457174301147}
-03/04/2022 16:46:26 - INFO - codeparrot_training - Step 23252: {'lr': 0.00047499031018525953, 'samples': 11905536, 'steps': 23252, 'loss/train': 1.4881577491760254}
-03/04/2022 16:46:28 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/04/2022 16:46:32 - INFO - codeparrot_training - Step 23253: {'lr': 0.00047498799655369895, 'samples': 11906048, 'steps': 23253, 'loss/train': 1.5180965662002563}
-03/04/2022 16:46:35 - INFO - codeparrot_training - Step 23254: {'lr': 0.0004749856828207623, 'samples': 11906560, 'steps': 23254, 'loss/train': 2.0907058715820312}
-03/04/2022 16:46:36 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/04/2022 16:46:40 - INFO - codeparrot_training - Step 23255: {'lr': 0.00047498336898645055, 'samples': 11907072, 'steps': 23255, 'loss/train': 6.035892486572266}
-03/04/2022 16:46:44 - INFO - codeparrot_training - Step 23256: {'lr': 0.00047498105505076475, 'samples': 11907584, 'steps': 23256, 'loss/train': 1.687117338180542}
-03/04/2022 16:46:45 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 16:46:49 - INFO - codeparrot_training - Step 23257: {'lr': 0.000474978741013706, 'samples': 11908096, 'steps': 23257, 'loss/train': 1.9847980737686157}
-03/04/2022 16:46:52 - INFO - codeparrot_training - Step 23258: {'lr': 0.0004749764268752753, 'samples': 11908608, 'steps': 23258, 'loss/train': 0.7909811735153198}
-03/04/2022 16:46:54 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/04/2022 16:46:57 - INFO - codeparrot_training - Step 23259: {'lr': 0.0004749741126354736, 'samples': 11909120, 'steps': 23259, 'loss/train': 2.4033703804016113}
-03/04/2022 16:47:01 - INFO - codeparrot_training - Step 23260: {'lr': 0.00047497179829430217, 'samples': 11909632, 'steps': 23260, 'loss/train': 1.2061327695846558}
-03/04/2022 16:47:02 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 16:47:06 - INFO - codeparrot_training - Step 23261: {'lr': 0.0004749694838517619, 'samples': 11910144, 'steps': 23261, 'loss/train': 1.9675450325012207}
-03/04/2022 16:47:09 - INFO - codeparrot_training - Step 23262: {'lr': 0.0004749671693078538, 'samples': 11910656, 'steps': 23262, 'loss/train': 0.8200609683990479}
-03/04/2022 16:47:11 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 16:47:14 - INFO - codeparrot_training - Step 23263: {'lr': 0.00047496485466257896, 'samples': 11911168, 'steps': 23263, 'loss/train': 1.0342795848846436}
-03/04/2022 16:47:17 - INFO - codeparrot_training - Step 23264: {'lr': 0.0004749625399159384, 'samples': 11911680, 'steps': 23264, 'loss/train': 1.7826805114746094}
-03/04/2022 16:47:20 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/04/2022 16:47:23 - INFO - codeparrot_training - Step 23265: {'lr': 0.0004749602250679332, 'samples': 11912192, 'steps': 23265, 'loss/train': 2.282989263534546}
-03/04/2022 16:47:26 - INFO - codeparrot_training - Step 23266: {'lr': 0.00047495791011856447, 'samples': 11912704, 'steps': 23266, 'loss/train': 1.7917360067367554}
-03/04/2022 16:47:29 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 16:47:31 - INFO - codeparrot_training - Step 23267: {'lr': 0.00047495559506783317, 'samples': 11913216, 'steps': 23267, 'loss/train': 2.00886869430542}
-03/04/2022 16:47:34 - INFO - codeparrot_training - Step 23268: {'lr': 0.00047495327991574034, 'samples': 11913728, 'steps': 23268, 'loss/train': 1.374742031097412}
-03/04/2022 16:47:37 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/04/2022 16:47:40 - INFO - codeparrot_training - Step 23269: {'lr': 0.0004749509646622869, 'samples': 11914240, 'steps': 23269, 'loss/train': 1.2179855108261108}
-03/04/2022 16:47:43 - INFO - codeparrot_training - Step 23270: {'lr': 0.00047494864930747415, 'samples': 11914752, 'steps': 23270, 'loss/train': 1.9321541786193848}
-03/04/2022 16:47:45 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/04/2022 16:47:48 - INFO - codeparrot_training - Step 23271: {'lr': 0.000474946333851303, 'samples': 11915264, 'steps': 23271, 'loss/train': 0.9668684005737305}
-03/04/2022 16:47:51 - INFO - codeparrot_training - Step 23272: {'lr': 0.0004749440182937745, 'samples': 11915776, 'steps': 23272, 'loss/train': 1.0239180326461792}
-03/04/2022 16:47:54 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 16:47:56 - INFO - codeparrot_training - Step 23273: {'lr': 0.0004749417026348897, 'samples': 11916288, 'steps': 23273, 'loss/train': 1.9658229351043701}
-03/04/2022 16:48:00 - INFO - codeparrot_training - Step 23274: {'lr': 0.0004749393868746497, 'samples': 11916800, 'steps': 23274, 'loss/train': 1.0590659379959106}
-03/04/2022 16:48:02 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/04/2022 16:48:05 - INFO - codeparrot_training - Step 23275: {'lr': 0.0004749370710130554, 'samples': 11917312, 'steps': 23275, 'loss/train': 1.9139764308929443}
-03/04/2022 16:48:09 - INFO - codeparrot_training - Step 23276: {'lr': 0.00047493475505010793, 'samples': 11917824, 'steps': 23276, 'loss/train': 1.865933895111084}
-03/04/2022 16:48:12 - INFO - codeparrot_training - Step 23277: {'lr': 0.0004749324389858083, 'samples': 11918336, 'steps': 23277, 'loss/train': 2.1843745708465576}
-03/04/2022 16:48:13 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/04/2022 16:48:17 - INFO - codeparrot_training - Step 23278: {'lr': 0.00047493012282015767, 'samples': 11918848, 'steps': 23278, 'loss/train': 2.208540916442871}
-03/04/2022 16:48:20 - INFO - codeparrot_training - Step 23279: {'lr': 0.00047492780655315693, 'samples': 11919360, 'steps': 23279, 'loss/train': 1.549017071723938}
-03/04/2022 16:48:22 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/04/2022 16:48:26 - INFO - codeparrot_training - Step 23280: {'lr': 0.00047492549018480725, 'samples': 11919872, 'steps': 23280, 'loss/train': 1.855757236480713}
-03/04/2022 16:48:29 - INFO - codeparrot_training - Step 23281: {'lr': 0.00047492317371510955, 'samples': 11920384, 'steps': 23281, 'loss/train': 1.514805793762207}
-03/04/2022 16:48:31 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 16:48:34 - INFO - codeparrot_training - Step 23282: {'lr': 0.00047492085714406497, 'samples': 11920896, 'steps': 23282, 'loss/train': 2.5938451290130615}
-03/04/2022 16:48:37 - INFO - codeparrot_training - Step 23283: {'lr': 0.00047491854047167453, 'samples': 11921408, 'steps': 23283, 'loss/train': 1.7550021409988403}
-03/04/2022 16:48:39 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 16:48:42 - INFO - codeparrot_training - Step 23284: {'lr': 0.0004749162236979393, 'samples': 11921920, 'steps': 23284, 'loss/train': 1.1320462226867676}
-03/04/2022 16:48:46 - INFO - codeparrot_training - Step 23285: {'lr': 0.0004749139068228602, 'samples': 11922432, 'steps': 23285, 'loss/train': 2.1778528690338135}
-03/04/2022 16:48:47 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 16:48:51 - INFO - codeparrot_training - Step 23286: {'lr': 0.00047491158984643846, 'samples': 11922944, 'steps': 23286, 'loss/train': 2.530402421951294}
-03/04/2022 16:48:54 - INFO - codeparrot_training - Step 23287: {'lr': 0.0004749092727686749, 'samples': 11923456, 'steps': 23287, 'loss/train': 2.2478601932525635}
-03/04/2022 16:48:56 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 16:48:59 - INFO - codeparrot_training - Step 23288: {'lr': 0.00047490695558957083, 'samples': 11923968, 'steps': 23288, 'loss/train': 1.8344285488128662}
-03/04/2022 16:49:02 - INFO - codeparrot_training - Step 23289: {'lr': 0.00047490463830912713, 'samples': 11924480, 'steps': 23289, 'loss/train': 2.0236165523529053}
-03/04/2022 16:49:04 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/04/2022 16:49:08 - INFO - codeparrot_training - Step 23290: {'lr': 0.0004749023209273448, 'samples': 11924992, 'steps': 23290, 'loss/train': 1.8343675136566162}
-03/04/2022 16:49:11 - INFO - codeparrot_training - Step 23291: {'lr': 0.000474900003444225, 'samples': 11925504, 'steps': 23291, 'loss/train': 1.7070770263671875}
-03/04/2022 16:49:13 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/04/2022 16:49:16 - INFO - codeparrot_training - Step 23292: {'lr': 0.0004748976858597687, 'samples': 11926016, 'steps': 23292, 'loss/train': 2.586672782897949}
-03/04/2022 16:49:19 - INFO - codeparrot_training - Step 23293: {'lr': 0.00047489536817397706, 'samples': 11926528, 'steps': 23293, 'loss/train': 1.5994175672531128}
-03/04/2022 16:49:21 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 16:49:25 - INFO - codeparrot_training - Step 23294: {'lr': 0.00047489305038685094, 'samples': 11927040, 'steps': 23294, 'loss/train': 0.3096446990966797}
-03/04/2022 16:49:28 - INFO - codeparrot_training - Step 23295: {'lr': 0.00047489073249839153, 'samples': 11927552, 'steps': 23295, 'loss/train': 2.141629934310913}
-03/04/2022 16:49:30 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/04/2022 16:49:33 - INFO - codeparrot_training - Step 23296: {'lr': 0.0004748884145085998, 'samples': 11928064, 'steps': 23296, 'loss/train': 1.8182371854782104}
-03/04/2022 16:49:36 - INFO - codeparrot_training - Step 23297: {'lr': 0.0004748860964174768, 'samples': 11928576, 'steps': 23297, 'loss/train': 6.501819610595703}
-03/04/2022 16:49:38 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/04/2022 16:49:41 - INFO - codeparrot_training - Step 23298: {'lr': 0.00047488377822502365, 'samples': 11929088, 'steps': 23298, 'loss/train': 1.8701205253601074}
-03/04/2022 16:49:45 - INFO - codeparrot_training - Step 23299: {'lr': 0.00047488145993124134, 'samples': 11929600, 'steps': 23299, 'loss/train': 2.367201566696167}
-03/04/2022 16:49:47 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/04/2022 16:49:50 - INFO - codeparrot_training - Step 23300: {'lr': 0.0004748791415361309, 'samples': 11930112, 'steps': 23300, 'loss/train': 3.082859754562378}
-03/04/2022 16:49:53 - INFO - codeparrot_training - Step 23301: {'lr': 0.00047487682303969336, 'samples': 11930624, 'steps': 23301, 'loss/train': 2.5544567108154297}
-03/04/2022 16:49:56 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 16:49:59 - INFO - codeparrot_training - Step 23302: {'lr': 0.0004748745044419298, 'samples': 11931136, 'steps': 23302, 'loss/train': 2.31608510017395}
-03/04/2022 16:50:02 - INFO - codeparrot_training - Step 23303: {'lr': 0.0004748721857428413, 'samples': 11931648, 'steps': 23303, 'loss/train': 1.6009459495544434}
-03/04/2022 16:50:04 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 16:50:07 - INFO - codeparrot_training - Step 23304: {'lr': 0.00047486986694242887, 'samples': 11932160, 'steps': 23304, 'loss/train': 2.2071337699890137}
-03/04/2022 16:50:10 - INFO - codeparrot_training - Step 23305: {'lr': 0.0004748675480406934, 'samples': 11932672, 'steps': 23305, 'loss/train': 2.213888168334961}
-03/04/2022 16:50:13 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/04/2022 16:50:16 - INFO - codeparrot_training - Step 23306: {'lr': 0.0004748652290376363, 'samples': 11933184, 'steps': 23306, 'loss/train': 2.6588938236236572}
-03/04/2022 16:50:19 - INFO - codeparrot_training - Step 23307: {'lr': 0.00047486290993325824, 'samples': 11933696, 'steps': 23307, 'loss/train': 2.8442652225494385}
-03/04/2022 16:50:22 - INFO - codeparrot_training - Step 23308: {'lr': 0.00047486059072756047, 'samples': 11934208, 'steps': 23308, 'loss/train': 2.2317230701446533}
-03/04/2022 16:50:22 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/04/2022 16:50:27 - INFO - codeparrot_training - Step 23309: {'lr': 0.00047485827142054407, 'samples': 11934720, 'steps': 23309, 'loss/train': 1.5069676637649536}
-03/04/2022 16:50:30 - INFO - codeparrot_training - Step 23310: {'lr': 0.0004748559520122099, 'samples': 11935232, 'steps': 23310, 'loss/train': 0.9620670080184937}
-03/04/2022 16:50:31 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/04/2022 16:50:36 - INFO - codeparrot_training - Step 23311: {'lr': 0.0004748536325025591, 'samples': 11935744, 'steps': 23311, 'loss/train': 0.6787362694740295}
-03/04/2022 16:50:39 - INFO - codeparrot_training - Step 23312: {'lr': 0.0004748513128915928, 'samples': 11936256, 'steps': 23312, 'loss/train': 1.9569050073623657}
-03/04/2022 16:50:40 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/04/2022 16:50:44 - INFO - codeparrot_training - Step 23313: {'lr': 0.0004748489931793119, 'samples': 11936768, 'steps': 23313, 'loss/train': 1.692866563796997}
-03/04/2022 16:50:47 - INFO - codeparrot_training - Step 23314: {'lr': 0.00047484667336571753, 'samples': 11937280, 'steps': 23314, 'loss/train': 1.9662597179412842}
-03/04/2022 16:50:48 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/04/2022 16:50:53 - INFO - codeparrot_training - Step 23315: {'lr': 0.0004748443534508107, 'samples': 11937792, 'steps': 23315, 'loss/train': 2.0747299194335938}
-03/04/2022 16:50:56 - INFO - codeparrot_training - Step 23316: {'lr': 0.00047484203343459256, 'samples': 11938304, 'steps': 23316, 'loss/train': 2.2545511722564697}
-03/04/2022 16:50:57 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/04/2022 16:51:01 - INFO - codeparrot_training - Step 23317: {'lr': 0.000474839713317064, 'samples': 11938816, 'steps': 23317, 'loss/train': 2.180447578430176}
-03/04/2022 16:51:04 - INFO - codeparrot_training - Step 23318: {'lr': 0.00047483739309822615, 'samples': 11939328, 'steps': 23318, 'loss/train': 1.6996933221817017}
-03/04/2022 16:51:05 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/04/2022 16:51:10 - INFO - codeparrot_training - Step 23319: {'lr': 0.00047483507277808, 'samples': 11939840, 'steps': 23319, 'loss/train': 2.0626962184906006}
-03/04/2022 16:51:13 - INFO - codeparrot_training - Step 23320: {'lr': 0.0004748327523566267, 'samples': 11940352, 'steps': 23320, 'loss/train': 1.7217775583267212}
-03/04/2022 16:51:14 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 16:51:18 - INFO - codeparrot_training - Step 23321: {'lr': 0.0004748304318338672, 'samples': 11940864, 'steps': 23321, 'loss/train': 1.1312798261642456}
-03/04/2022 16:51:21 - INFO - codeparrot_training - Step 23322: {'lr': 0.00047482811120980254, 'samples': 11941376, 'steps': 23322, 'loss/train': 2.1096572875976562}
-03/04/2022 16:51:22 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 16:51:27 - INFO - codeparrot_training - Step 23323: {'lr': 0.0004748257904844339, 'samples': 11941888, 'steps': 23323, 'loss/train': 2.714707851409912}
-03/04/2022 16:51:30 - INFO - codeparrot_training - Step 23324: {'lr': 0.00047482346965776215, 'samples': 11942400, 'steps': 23324, 'loss/train': 0.7907835841178894}
-03/04/2022 16:51:30 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/04/2022 16:51:35 - INFO - codeparrot_training - Step 23325: {'lr': 0.0004748211487297884, 'samples': 11942912, 'steps': 23325, 'loss/train': 2.409842014312744}
-03/04/2022 16:51:38 - INFO - codeparrot_training - Step 23326: {'lr': 0.00047481882770051377, 'samples': 11943424, 'steps': 23326, 'loss/train': 1.2467879056930542}
-03/04/2022 16:51:39 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/04/2022 16:51:44 - INFO - codeparrot_training - Step 23327: {'lr': 0.00047481650656993924, 'samples': 11943936, 'steps': 23327, 'loss/train': 2.0101513862609863}
-03/04/2022 16:51:47 - INFO - codeparrot_training - Step 23328: {'lr': 0.00047481418533806586, 'samples': 11944448, 'steps': 23328, 'loss/train': 1.5548689365386963}
-03/04/2022 16:51:48 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 16:51:52 - INFO - codeparrot_training - Step 23329: {'lr': 0.0004748118640048946, 'samples': 11944960, 'steps': 23329, 'loss/train': 1.6938414573669434}
-03/04/2022 16:51:55 - INFO - codeparrot_training - Step 23330: {'lr': 0.00047480954257042666, 'samples': 11945472, 'steps': 23330, 'loss/train': 2.250408887863159}
-03/04/2022 16:51:56 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/04/2022 16:52:01 - INFO - codeparrot_training - Step 23331: {'lr': 0.000474807221034663, 'samples': 11945984, 'steps': 23331, 'loss/train': 1.1894129514694214}
-03/04/2022 16:52:04 - INFO - codeparrot_training - Step 23332: {'lr': 0.0004748048993976046, 'samples': 11946496, 'steps': 23332, 'loss/train': 1.5454301834106445}
-03/04/2022 16:52:05 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 16:52:09 - INFO - codeparrot_training - Step 23333: {'lr': 0.0004748025776592527, 'samples': 11947008, 'steps': 23333, 'loss/train': 1.8648681640625}
-03/04/2022 16:52:12 - INFO - codeparrot_training - Step 23334: {'lr': 0.00047480025581960817, 'samples': 11947520, 'steps': 23334, 'loss/train': 1.5155541896820068}
-03/04/2022 16:52:14 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/04/2022 16:52:18 - INFO - codeparrot_training - Step 23335: {'lr': 0.0004747979338786721, 'samples': 11948032, 'steps': 23335, 'loss/train': 2.2037553787231445}
-03/04/2022 16:52:21 - INFO - codeparrot_training - Step 23336: {'lr': 0.00047479561183644557, 'samples': 11948544, 'steps': 23336, 'loss/train': 2.0614449977874756}
-03/04/2022 16:52:23 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 16:52:26 - INFO - codeparrot_training - Step 23337: {'lr': 0.00047479328969292963, 'samples': 11949056, 'steps': 23337, 'loss/train': 1.6581941843032837}
-03/04/2022 16:52:29 - INFO - codeparrot_training - Step 23338: {'lr': 0.0004747909674481253, 'samples': 11949568, 'steps': 23338, 'loss/train': 2.0797245502471924}
-03/04/2022 16:52:32 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 16:52:35 - INFO - codeparrot_training - Step 23339: {'lr': 0.00047478864510203355, 'samples': 11950080, 'steps': 23339, 'loss/train': 1.4287866353988647}
-03/04/2022 16:52:38 - INFO - codeparrot_training - Step 23340: {'lr': 0.0004747863226546556, 'samples': 11950592, 'steps': 23340, 'loss/train': 2.6435933113098145}
-03/04/2022 16:52:40 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/04/2022 16:52:43 - INFO - codeparrot_training - Step 23341: {'lr': 0.0004747840001059923, 'samples': 11951104, 'steps': 23341, 'loss/train': 1.4793064594268799}
-03/04/2022 16:52:46 - INFO - codeparrot_training - Step 23342: {'lr': 0.00047478167745604495, 'samples': 11951616, 'steps': 23342, 'loss/train': 1.3045340776443481}
-03/04/2022 16:52:49 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/04/2022 16:52:52 - INFO - codeparrot_training - Step 23343: {'lr': 0.00047477935470481434, 'samples': 11952128, 'steps': 23343, 'loss/train': 2.1830544471740723}
-03/04/2022 16:52:55 - INFO - codeparrot_training - Step 23344: {'lr': 0.00047477703185230157, 'samples': 11952640, 'steps': 23344, 'loss/train': 1.7340668439865112}
-03/04/2022 16:52:57 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 16:53:00 - INFO - codeparrot_training - Step 23345: {'lr': 0.00047477470889850784, 'samples': 11953152, 'steps': 23345, 'loss/train': 1.2518830299377441}
-03/04/2022 16:53:03 - INFO - codeparrot_training - Step 23346: {'lr': 0.00047477238584343407, 'samples': 11953664, 'steps': 23346, 'loss/train': 1.9134511947631836}
-03/04/2022 16:53:06 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 16:53:09 - INFO - codeparrot_training - Step 23347: {'lr': 0.00047477006268708134, 'samples': 11954176, 'steps': 23347, 'loss/train': 4.755134105682373}
-03/04/2022 16:53:12 - INFO - codeparrot_training - Step 23348: {'lr': 0.00047476773942945063, 'samples': 11954688, 'steps': 23348, 'loss/train': 1.439097285270691}
-03/04/2022 16:53:15 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 16:53:17 - INFO - codeparrot_training - Step 23349: {'lr': 0.00047476541607054313, 'samples': 11955200, 'steps': 23349, 'loss/train': 1.1304434537887573}
-03/04/2022 16:53:20 - INFO - codeparrot_training - Step 23350: {'lr': 0.0004747630926103597, 'samples': 11955712, 'steps': 23350, 'loss/train': 0.5623083114624023}
-03/04/2022 16:53:23 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/04/2022 16:53:26 - INFO - codeparrot_training - Step 23351: {'lr': 0.0004747607690489015, 'samples': 11956224, 'steps': 23351, 'loss/train': 1.5679458379745483}
-03/04/2022 16:53:29 - INFO - codeparrot_training - Step 23352: {'lr': 0.00047475844538616966, 'samples': 11956736, 'steps': 23352, 'loss/train': 1.2520536184310913}
-03/04/2022 16:53:32 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 16:53:34 - INFO - codeparrot_training - Step 23353: {'lr': 0.0004747561216221651, 'samples': 11957248, 'steps': 23353, 'loss/train': 1.7548965215682983}
-03/04/2022 16:53:37 - INFO - codeparrot_training - Step 23354: {'lr': 0.0004747537977568889, 'samples': 11957760, 'steps': 23354, 'loss/train': 2.0397846698760986}
-03/04/2022 16:53:40 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/04/2022 16:53:43 - INFO - codeparrot_training - Step 23355: {'lr': 0.00047475147379034206, 'samples': 11958272, 'steps': 23355, 'loss/train': 1.9109156131744385}
-03/04/2022 16:53:46 - INFO - codeparrot_training - Step 23356: {'lr': 0.0004747491497225257, 'samples': 11958784, 'steps': 23356, 'loss/train': 1.8210498094558716}
-03/04/2022 16:53:49 - INFO - codeparrot_training - Step 23357: {'lr': 0.00047474682555344083, 'samples': 11959296, 'steps': 23357, 'loss/train': 2.2388362884521484}
-03/04/2022 16:53:49 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/04/2022 16:53:54 - INFO - codeparrot_training - Step 23358: {'lr': 0.00047474450128308853, 'samples': 11959808, 'steps': 23358, 'loss/train': 1.6404907703399658}
-03/04/2022 16:53:58 - INFO - codeparrot_training - Step 23359: {'lr': 0.0004747421769114698, 'samples': 11960320, 'steps': 23359, 'loss/train': 1.749161958694458}
-03/04/2022 16:53:58 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 16:54:03 - INFO - codeparrot_training - Step 23360: {'lr': 0.00047473985243858577, 'samples': 11960832, 'steps': 23360, 'loss/train': 2.251490592956543}
-03/04/2022 16:54:06 - INFO - codeparrot_training - Step 23361: {'lr': 0.00047473752786443736, 'samples': 11961344, 'steps': 23361, 'loss/train': 1.8118185997009277}
-03/04/2022 16:54:06 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/04/2022 16:54:11 - INFO - codeparrot_training - Step 23362: {'lr': 0.0004747352031890257, 'samples': 11961856, 'steps': 23362, 'loss/train': 2.0672035217285156}
-03/04/2022 16:54:15 - INFO - codeparrot_training - Step 23363: {'lr': 0.0004747328784123519, 'samples': 11962368, 'steps': 23363, 'loss/train': 1.6104357242584229}
-03/04/2022 16:54:15 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/04/2022 16:54:20 - INFO - codeparrot_training - Step 23364: {'lr': 0.00047473055353441685, 'samples': 11962880, 'steps': 23364, 'loss/train': 2.3544888496398926}
-03/04/2022 16:54:23 - INFO - codeparrot_training - Step 23365: {'lr': 0.0004747282285552217, 'samples': 11963392, 'steps': 23365, 'loss/train': 1.8929945230484009}
-03/04/2022 16:54:24 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/04/2022 16:54:28 - INFO - codeparrot_training - Step 23366: {'lr': 0.0004747259034747675, 'samples': 11963904, 'steps': 23366, 'loss/train': 2.221660614013672}
-03/04/2022 16:54:32 - INFO - codeparrot_training - Step 23367: {'lr': 0.00047472357829305524, 'samples': 11964416, 'steps': 23367, 'loss/train': 2.539306640625}
-03/04/2022 16:54:33 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/04/2022 16:54:37 - INFO - codeparrot_training - Step 23368: {'lr': 0.0004747212530100861, 'samples': 11964928, 'steps': 23368, 'loss/train': 1.8161391019821167}
-03/04/2022 16:54:40 - INFO - codeparrot_training - Step 23369: {'lr': 0.0004747189276258609, 'samples': 11965440, 'steps': 23369, 'loss/train': 2.1547319889068604}
-03/04/2022 16:54:41 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/04/2022 16:54:45 - INFO - codeparrot_training - Step 23370: {'lr': 0.0004747166021403809, 'samples': 11965952, 'steps': 23370, 'loss/train': 1.621546745300293}
-03/04/2022 16:54:49 - INFO - codeparrot_training - Step 23371: {'lr': 0.000474714276553647, 'samples': 11966464, 'steps': 23371, 'loss/train': 1.6483749151229858}
-03/04/2022 16:54:50 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 16:54:54 - INFO - codeparrot_training - Step 23372: {'lr': 0.00047471195086566035, 'samples': 11966976, 'steps': 23372, 'loss/train': 1.6799837350845337}
-03/04/2022 16:54:57 - INFO - codeparrot_training - Step 23373: {'lr': 0.000474709625076422, 'samples': 11967488, 'steps': 23373, 'loss/train': 2.281834125518799}
-03/04/2022 16:55:00 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 16:55:03 - INFO - codeparrot_training - Step 23374: {'lr': 0.0004747072991859329, 'samples': 11968000, 'steps': 23374, 'loss/train': 1.6455888748168945}
-03/04/2022 16:55:06 - INFO - codeparrot_training - Step 23375: {'lr': 0.0004747049731941942, 'samples': 11968512, 'steps': 23375, 'loss/train': 2.113337516784668}
-03/04/2022 16:55:08 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/04/2022 16:55:11 - INFO - codeparrot_training - Step 23376: {'lr': 0.0004747026471012069, 'samples': 11969024, 'steps': 23376, 'loss/train': 0.46364861726760864}
-03/04/2022 16:55:14 - INFO - codeparrot_training - Step 23377: {'lr': 0.000474700320906972, 'samples': 11969536, 'steps': 23377, 'loss/train': 0.826941728591919}
-03/04/2022 16:55:17 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/04/2022 16:55:20 - INFO - codeparrot_training - Step 23378: {'lr': 0.0004746979946114907, 'samples': 11970048, 'steps': 23378, 'loss/train': 2.1099185943603516}
-03/04/2022 16:55:23 - INFO - codeparrot_training - Step 23379: {'lr': 0.000474695668214764, 'samples': 11970560, 'steps': 23379, 'loss/train': 2.617692232131958}
-03/04/2022 16:55:25 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/04/2022 16:55:28 - INFO - codeparrot_training - Step 23380: {'lr': 0.00047469334171679266, 'samples': 11971072, 'steps': 23380, 'loss/train': 1.7464921474456787}
-03/04/2022 16:55:31 - INFO - codeparrot_training - Step 23381: {'lr': 0.00047469101511757815, 'samples': 11971584, 'steps': 23381, 'loss/train': 2.2422678470611572}
-03/04/2022 16:55:33 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 16:55:37 - INFO - codeparrot_training - Step 23382: {'lr': 0.00047468868841712134, 'samples': 11972096, 'steps': 23382, 'loss/train': 0.4601757526397705}
-03/04/2022 16:55:40 - INFO - codeparrot_training - Step 23383: {'lr': 0.00047468636161542325, 'samples': 11972608, 'steps': 23383, 'loss/train': 2.0826609134674072}
-03/04/2022 16:55:42 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/04/2022 16:55:45 - INFO - codeparrot_training - Step 23384: {'lr': 0.0004746840347124849, 'samples': 11973120, 'steps': 23384, 'loss/train': 1.9405590295791626}
-03/04/2022 16:55:48 - INFO - codeparrot_training - Step 23385: {'lr': 0.0004746817077083074, 'samples': 11973632, 'steps': 23385, 'loss/train': 1.1801667213439941}
-03/04/2022 16:55:50 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/04/2022 16:55:53 - INFO - codeparrot_training - Step 23386: {'lr': 0.00047467938060289185, 'samples': 11974144, 'steps': 23386, 'loss/train': 1.4176239967346191}
-03/04/2022 16:55:57 - INFO - codeparrot_training - Step 23387: {'lr': 0.0004746770533962391, 'samples': 11974656, 'steps': 23387, 'loss/train': 1.4661380052566528}
-03/04/2022 16:55:59 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/04/2022 16:56:02 - INFO - codeparrot_training - Step 23388: {'lr': 0.0004746747260883505, 'samples': 11975168, 'steps': 23388, 'loss/train': 2.1951780319213867}
-03/04/2022 16:56:05 - INFO - codeparrot_training - Step 23389: {'lr': 0.0004746723986792268, 'samples': 11975680, 'steps': 23389, 'loss/train': 1.2097113132476807}
-03/04/2022 16:56:07 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/04/2022 16:56:10 - INFO - codeparrot_training - Step 23390: {'lr': 0.0004746700711688693, 'samples': 11976192, 'steps': 23390, 'loss/train': 0.19772501289844513}
-03/04/2022 16:56:13 - INFO - codeparrot_training - Step 23391: {'lr': 0.0004746677435572789, 'samples': 11976704, 'steps': 23391, 'loss/train': 0.9094952344894409}
-03/04/2022 16:56:16 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/04/2022 16:56:19 - INFO - codeparrot_training - Step 23392: {'lr': 0.00047466541584445667, 'samples': 11977216, 'steps': 23392, 'loss/train': 2.0294089317321777}
-03/04/2022 16:56:22 - INFO - codeparrot_training - Step 23393: {'lr': 0.0004746630880304037, 'samples': 11977728, 'steps': 23393, 'loss/train': 1.804544448852539}
-03/04/2022 16:56:24 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 16:56:27 - INFO - codeparrot_training - Step 23394: {'lr': 0.0004746607601151209, 'samples': 11978240, 'steps': 23394, 'loss/train': 1.5381548404693604}
-03/04/2022 16:56:31 - INFO - codeparrot_training - Step 23395: {'lr': 0.0004746584320986096, 'samples': 11978752, 'steps': 23395, 'loss/train': 2.3071064949035645}
-03/04/2022 16:56:33 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/04/2022 16:56:36 - INFO - codeparrot_training - Step 23396: {'lr': 0.0004746561039808706, 'samples': 11979264, 'steps': 23396, 'loss/train': 1.8148623704910278}
-03/04/2022 16:56:39 - INFO - codeparrot_training - Step 23397: {'lr': 0.0004746537757619049, 'samples': 11979776, 'steps': 23397, 'loss/train': 1.9050732851028442}
-03/04/2022 16:56:41 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/04/2022 16:56:44 - INFO - codeparrot_training - Step 23398: {'lr': 0.00047465144744171387, 'samples': 11980288, 'steps': 23398, 'loss/train': 0.9550286531448364}
-03/04/2022 16:56:47 - INFO - codeparrot_training - Step 23399: {'lr': 0.0004746491190202983, 'samples': 11980800, 'steps': 23399, 'loss/train': 1.219398856163025}
-03/04/2022 16:56:50 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 16:56:53 - INFO - codeparrot_training - Step 23400: {'lr': 0.00047464679049765926, 'samples': 11981312, 'steps': 23400, 'loss/train': 1.648595929145813}
-03/04/2022 16:56:56 - INFO - codeparrot_training - Step 23401: {'lr': 0.00047464446187379787, 'samples': 11981824, 'steps': 23401, 'loss/train': 2.1689915657043457}
-03/04/2022 16:56:59 - INFO - codeparrot_training - Step 23402: {'lr': 0.00047464213314871514, 'samples': 11982336, 'steps': 23402, 'loss/train': 0.6996098160743713}
-03/04/2022 16:56:59 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/04/2022 16:57:05 - INFO - codeparrot_training - Step 23403: {'lr': 0.0004746398043224122, 'samples': 11982848, 'steps': 23403, 'loss/train': 1.2064995765686035}
-03/04/2022 16:57:08 - INFO - codeparrot_training - Step 23404: {'lr': 0.0004746374753948899, 'samples': 11983360, 'steps': 23404, 'loss/train': 0.9354748129844666}
-03/04/2022 16:57:08 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/04/2022 16:57:13 - INFO - codeparrot_training - Step 23405: {'lr': 0.00047463514636614945, 'samples': 11983872, 'steps': 23405, 'loss/train': 2.2265141010284424}
-03/04/2022 16:57:16 - INFO - codeparrot_training - Step 23406: {'lr': 0.00047463281723619203, 'samples': 11984384, 'steps': 23406, 'loss/train': 2.0179860591888428}
-03/04/2022 16:57:18 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/04/2022 16:57:22 - INFO - codeparrot_training - Step 23407: {'lr': 0.00047463048800501837, 'samples': 11984896, 'steps': 23407, 'loss/train': 1.6085623502731323}
-03/04/2022 16:57:25 - INFO - codeparrot_training - Step 23408: {'lr': 0.00047462815867262967, 'samples': 11985408, 'steps': 23408, 'loss/train': 0.5775954127311707}
-03/04/2022 16:57:26 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/04/2022 16:57:30 - INFO - codeparrot_training - Step 23409: {'lr': 0.0004746258292390271, 'samples': 11985920, 'steps': 23409, 'loss/train': 2.027233123779297}
-03/04/2022 16:57:33 - INFO - codeparrot_training - Step 23410: {'lr': 0.00047462349970421147, 'samples': 11986432, 'steps': 23410, 'loss/train': 1.7761943340301514}
-03/04/2022 16:57:35 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/04/2022 16:57:39 - INFO - codeparrot_training - Step 23411: {'lr': 0.0004746211700681841, 'samples': 11986944, 'steps': 23411, 'loss/train': 2.169621706008911}
-03/04/2022 16:57:42 - INFO - codeparrot_training - Step 23412: {'lr': 0.0004746188403309457, 'samples': 11987456, 'steps': 23412, 'loss/train': 2.430370807647705}
-03/04/2022 16:57:43 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 16:57:47 - INFO - codeparrot_training - Step 23413: {'lr': 0.00047461651049249764, 'samples': 11987968, 'steps': 23413, 'loss/train': 2.0490705966949463}
-03/04/2022 16:57:50 - INFO - codeparrot_training - Step 23414: {'lr': 0.0004746141805528409, 'samples': 11988480, 'steps': 23414, 'loss/train': 2.2713117599487305}
-03/04/2022 16:57:51 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 16:57:55 - INFO - codeparrot_training - Step 23415: {'lr': 0.00047461185051197644, 'samples': 11988992, 'steps': 23415, 'loss/train': 3.4521114826202393}
-03/04/2022 16:57:59 - INFO - codeparrot_training - Step 23416: {'lr': 0.0004746095203699053, 'samples': 11989504, 'steps': 23416, 'loss/train': 0.10956083238124847}
-03/04/2022 16:58:00 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/04/2022 16:58:04 - INFO - codeparrot_training - Step 23417: {'lr': 0.00047460719012662857, 'samples': 11990016, 'steps': 23417, 'loss/train': 1.0276734828948975}
-03/04/2022 16:58:07 - INFO - codeparrot_training - Step 23418: {'lr': 0.00047460485978214733, 'samples': 11990528, 'steps': 23418, 'loss/train': 2.5082268714904785}
-03/04/2022 16:58:09 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/04/2022 16:58:12 - INFO - codeparrot_training - Step 23419: {'lr': 0.00047460252933646265, 'samples': 11991040, 'steps': 23419, 'loss/train': 1.8034281730651855}
-03/04/2022 16:58:16 - INFO - codeparrot_training - Step 23420: {'lr': 0.0004746001987895755, 'samples': 11991552, 'steps': 23420, 'loss/train': 2.1163768768310547}
-03/04/2022 16:58:18 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 16:58:21 - INFO - codeparrot_training - Step 23421: {'lr': 0.00047459786814148697, 'samples': 11992064, 'steps': 23421, 'loss/train': 1.9776972532272339}
-03/04/2022 16:58:24 - INFO - codeparrot_training - Step 23422: {'lr': 0.0004745955373921981, 'samples': 11992576, 'steps': 23422, 'loss/train': 1.6589242219924927}
-03/04/2022 16:58:27 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 16:58:29 - INFO - codeparrot_training - Step 23423: {'lr': 0.0004745932065417099, 'samples': 11993088, 'steps': 23423, 'loss/train': 1.3764723539352417}
-03/04/2022 16:58:32 - INFO - codeparrot_training - Step 23424: {'lr': 0.00047459087559002355, 'samples': 11993600, 'steps': 23424, 'loss/train': 2.5065011978149414}
-03/04/2022 16:58:35 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/04/2022 16:58:38 - INFO - codeparrot_training - Step 23425: {'lr': 0.00047458854453713995, 'samples': 11994112, 'steps': 23425, 'loss/train': 1.5518229007720947}
-03/04/2022 16:58:41 - INFO - codeparrot_training - Step 23426: {'lr': 0.0004745862133830603, 'samples': 11994624, 'steps': 23426, 'loss/train': 2.317072868347168}
-03/04/2022 16:58:44 - INFO - codeparrot_training - Step 23427: {'lr': 0.00047458388212778547, 'samples': 11995136, 'steps': 23427, 'loss/train': 2.2092509269714355}
-03/04/2022 16:58:44 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/04/2022 16:58:50 - INFO - codeparrot_training - Step 23428: {'lr': 0.00047458155077131664, 'samples': 11995648, 'steps': 23428, 'loss/train': 1.8494211435317993}
-03/04/2022 16:58:52 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 16:58:55 - INFO - codeparrot_training - Step 23429: {'lr': 0.0004745792193136549, 'samples': 11996160, 'steps': 23429, 'loss/train': 2.2434237003326416}
-03/04/2022 16:58:58 - INFO - codeparrot_training - Step 23430: {'lr': 0.00047457688775480114, 'samples': 11996672, 'steps': 23430, 'loss/train': 0.8261879086494446}
-03/04/2022 16:59:01 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 16:59:03 - INFO - codeparrot_training - Step 23431: {'lr': 0.0004745745560947565, 'samples': 11997184, 'steps': 23431, 'loss/train': 1.5480263233184814}
-03/04/2022 16:59:06 - INFO - codeparrot_training - Step 23432: {'lr': 0.0004745722243335221, 'samples': 11997696, 'steps': 23432, 'loss/train': 1.6461553573608398}
-03/04/2022 16:59:09 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/04/2022 16:59:12 - INFO - codeparrot_training - Step 23433: {'lr': 0.0004745698924710988, 'samples': 11998208, 'steps': 23433, 'loss/train': 2.0817010402679443}
-03/04/2022 16:59:15 - INFO - codeparrot_training - Step 23434: {'lr': 0.00047456756050748793, 'samples': 11998720, 'steps': 23434, 'loss/train': 1.2123945951461792}
-03/04/2022 16:59:18 - INFO - codeparrot_training - Step 23435: {'lr': 0.0004745652284426903, 'samples': 11999232, 'steps': 23435, 'loss/train': 0.5027723908424377}
-03/04/2022 16:59:19 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/04/2022 16:59:24 - INFO - codeparrot_training - Step 23436: {'lr': 0.00047456289627670703, 'samples': 11999744, 'steps': 23436, 'loss/train': 1.8438464403152466}
-03/04/2022 16:59:27 - INFO - codeparrot_training - Step 23437: {'lr': 0.0004745605640095392, 'samples': 12000256, 'steps': 23437, 'loss/train': 1.4618467092514038}
-03/04/2022 16:59:27 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/04/2022 16:59:32 - INFO - codeparrot_training - Step 23438: {'lr': 0.00047455823164118787, 'samples': 12000768, 'steps': 23438, 'loss/train': 2.0180745124816895}
-03/04/2022 16:59:35 - INFO - codeparrot_training - Step 23439: {'lr': 0.00047455589917165406, 'samples': 12001280, 'steps': 23439, 'loss/train': 2.3782050609588623}
-03/04/2022 16:59:35 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/04/2022 16:59:40 - INFO - codeparrot_training - Step 23440: {'lr': 0.00047455356660093886, 'samples': 12001792, 'steps': 23440, 'loss/train': 1.8602378368377686}
-03/04/2022 16:59:44 - INFO - codeparrot_training - Step 23441: {'lr': 0.0004745512339290432, 'samples': 12002304, 'steps': 23441, 'loss/train': 1.1343469619750977}
-03/04/2022 16:59:44 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/04/2022 16:59:49 - INFO - codeparrot_training - Step 23442: {'lr': 0.00047454890115596824, 'samples': 12002816, 'steps': 23442, 'loss/train': 1.3163840770721436}
-03/04/2022 16:59:52 - INFO - codeparrot_training - Step 23443: {'lr': 0.00047454656828171504, 'samples': 12003328, 'steps': 23443, 'loss/train': 1.6837388277053833}
-03/04/2022 16:59:52 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/04/2022 16:59:57 - INFO - codeparrot_training - Step 23444: {'lr': 0.0004745442353062846, 'samples': 12003840, 'steps': 23444, 'loss/train': 1.6450188159942627}
-03/04/2022 17:00:00 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/04/2022 17:00:03 - INFO - codeparrot_training - Step 23445: {'lr': 0.000474541902229678, 'samples': 12004352, 'steps': 23445, 'loss/train': 1.9965230226516724}
-03/04/2022 17:00:06 - INFO - codeparrot_training - Step 23446: {'lr': 0.0004745395690518963, 'samples': 12004864, 'steps': 23446, 'loss/train': 2.395139217376709}
-03/04/2022 17:00:09 - INFO - codeparrot_training - Step 23447: {'lr': 0.0004745372357729405, 'samples': 12005376, 'steps': 23447, 'loss/train': 1.1257965564727783}
-03/04/2022 17:00:10 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 17:00:14 - INFO - codeparrot_training - Step 23448: {'lr': 0.0004745349023928117, 'samples': 12005888, 'steps': 23448, 'loss/train': 1.3181939125061035}
-03/04/2022 17:00:18 - INFO - codeparrot_training - Step 23449: {'lr': 0.000474532568911511, 'samples': 12006400, 'steps': 23449, 'loss/train': 1.7687578201293945}
-03/04/2022 17:00:18 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/04/2022 17:00:23 - INFO - codeparrot_training - Step 23450: {'lr': 0.00047453023532903927, 'samples': 12006912, 'steps': 23450, 'loss/train': 0.8469099402427673}
-03/04/2022 17:00:26 - INFO - codeparrot_training - Step 23451: {'lr': 0.00047452790164539775, 'samples': 12007424, 'steps': 23451, 'loss/train': 1.7994046211242676}
-03/04/2022 17:00:27 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 17:00:31 - INFO - codeparrot_training - Step 23452: {'lr': 0.00047452556786058744, 'samples': 12007936, 'steps': 23452, 'loss/train': 3.012195348739624}
-03/04/2022 17:00:35 - INFO - codeparrot_training - Step 23453: {'lr': 0.0004745232339746094, 'samples': 12008448, 'steps': 23453, 'loss/train': 1.2046812772750854}
-03/04/2022 17:00:35 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 17:00:40 - INFO - codeparrot_training - Step 23454: {'lr': 0.00047452089998746463, 'samples': 12008960, 'steps': 23454, 'loss/train': 1.482425570487976}
-03/04/2022 17:00:43 - INFO - codeparrot_training - Step 23455: {'lr': 0.0004745185658991541, 'samples': 12009472, 'steps': 23455, 'loss/train': 1.8183541297912598}
-03/04/2022 17:00:44 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 17:00:49 - INFO - codeparrot_training - Step 23456: {'lr': 0.0004745162317096791, 'samples': 12009984, 'steps': 23456, 'loss/train': 2.0668609142303467}
-03/04/2022 17:00:52 - INFO - codeparrot_training - Step 23457: {'lr': 0.0004745138974190405, 'samples': 12010496, 'steps': 23457, 'loss/train': 1.8630073070526123}
-03/04/2022 17:00:53 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/04/2022 17:00:57 - INFO - codeparrot_training - Step 23458: {'lr': 0.0004745115630272394, 'samples': 12011008, 'steps': 23458, 'loss/train': 2.25524640083313}
-03/04/2022 17:01:00 - INFO - codeparrot_training - Step 23459: {'lr': 0.00047450922853427686, 'samples': 12011520, 'steps': 23459, 'loss/train': 2.0050432682037354}
-03/04/2022 17:01:01 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/04/2022 17:01:06 - INFO - codeparrot_training - Step 23460: {'lr': 0.0004745068939401539, 'samples': 12012032, 'steps': 23460, 'loss/train': 1.227063536643982}
-03/04/2022 17:01:09 - INFO - codeparrot_training - Step 23461: {'lr': 0.0004745045592448717, 'samples': 12012544, 'steps': 23461, 'loss/train': 1.941652536392212}
-03/04/2022 17:01:10 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 17:01:14 - INFO - codeparrot_training - Step 23462: {'lr': 0.00047450222444843105, 'samples': 12013056, 'steps': 23462, 'loss/train': 1.8349345922470093}
-03/04/2022 17:01:17 - INFO - codeparrot_training - Step 23463: {'lr': 0.0004744998895508333, 'samples': 12013568, 'steps': 23463, 'loss/train': 2.3058278560638428}
-03/04/2022 17:01:18 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/04/2022 17:01:22 - INFO - codeparrot_training - Step 23464: {'lr': 0.0004744975545520793, 'samples': 12014080, 'steps': 23464, 'loss/train': 1.762920618057251}
-03/04/2022 17:01:25 - INFO - codeparrot_training - Step 23465: {'lr': 0.00047449521945217016, 'samples': 12014592, 'steps': 23465, 'loss/train': 2.111161708831787}
-03/04/2022 17:01:26 - INFO - codeparrot_training - Skipping example with length 158 (seq_length=1024)
-03/04/2022 17:01:31 - INFO - codeparrot_training - Step 23466: {'lr': 0.00047449288425110693, 'samples': 12015104, 'steps': 23466, 'loss/train': 1.8523049354553223}
-03/04/2022 17:01:34 - INFO - codeparrot_training - Step 23467: {'lr': 0.00047449054894889073, 'samples': 12015616, 'steps': 23467, 'loss/train': 2.217637062072754}
-03/04/2022 17:01:35 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/04/2022 17:01:39 - INFO - codeparrot_training - Step 23468: {'lr': 0.00047448821354552253, 'samples': 12016128, 'steps': 23468, 'loss/train': 1.8780640363693237}
-03/04/2022 17:01:42 - INFO - codeparrot_training - Step 23469: {'lr': 0.0004744858780410034, 'samples': 12016640, 'steps': 23469, 'loss/train': 1.4454163312911987}
-03/04/2022 17:01:43 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/04/2022 17:01:48 - INFO - codeparrot_training - Step 23470: {'lr': 0.0004744835424353344, 'samples': 12017152, 'steps': 23470, 'loss/train': 1.566304087638855}
-03/04/2022 17:01:51 - INFO - codeparrot_training - Step 23471: {'lr': 0.00047448120672851653, 'samples': 12017664, 'steps': 23471, 'loss/train': 1.8868640661239624}
-03/04/2022 17:01:51 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 17:01:56 - INFO - codeparrot_training - Step 23472: {'lr': 0.0004744788709205509, 'samples': 12018176, 'steps': 23472, 'loss/train': 2.040874481201172}
-03/04/2022 17:01:59 - INFO - codeparrot_training - Step 23473: {'lr': 0.0004744765350114386, 'samples': 12018688, 'steps': 23473, 'loss/train': 1.7099310159683228}
-03/04/2022 17:01:59 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/04/2022 17:02:04 - INFO - codeparrot_training - Step 23474: {'lr': 0.00047447419900118067, 'samples': 12019200, 'steps': 23474, 'loss/train': 1.608444094657898}
-03/04/2022 17:02:07 - INFO - codeparrot_training - Step 23475: {'lr': 0.00047447186288977804, 'samples': 12019712, 'steps': 23475, 'loss/train': 2.0884017944335938}
-03/04/2022 17:02:08 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/04/2022 17:02:13 - INFO - codeparrot_training - Step 23476: {'lr': 0.0004744695266772319, 'samples': 12020224, 'steps': 23476, 'loss/train': 1.5034143924713135}
-03/04/2022 17:02:16 - INFO - codeparrot_training - Step 23477: {'lr': 0.00047446719036354324, 'samples': 12020736, 'steps': 23477, 'loss/train': 1.3621755838394165}
-03/04/2022 17:02:16 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 17:02:21 - INFO - codeparrot_training - Step 23478: {'lr': 0.0004744648539487132, 'samples': 12021248, 'steps': 23478, 'loss/train': 1.4267070293426514}
-03/04/2022 17:02:24 - INFO - codeparrot_training - Step 23479: {'lr': 0.00047446251743274263, 'samples': 12021760, 'steps': 23479, 'loss/train': 1.8810547590255737}
-03/04/2022 17:02:24 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/04/2022 17:02:30 - INFO - codeparrot_training - Step 23480: {'lr': 0.0004744601808156328, 'samples': 12022272, 'steps': 23480, 'loss/train': 0.9832499027252197}
-03/04/2022 17:02:33 - INFO - codeparrot_training - Step 23481: {'lr': 0.00047445784409738467, 'samples': 12022784, 'steps': 23481, 'loss/train': 1.813855767250061}
-03/04/2022 17:02:33 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/04/2022 17:02:38 - INFO - codeparrot_training - Step 23482: {'lr': 0.0004744555072779993, 'samples': 12023296, 'steps': 23482, 'loss/train': 1.9193674325942993}
-03/04/2022 17:02:41 - INFO - codeparrot_training - Step 23483: {'lr': 0.0004744531703574777, 'samples': 12023808, 'steps': 23483, 'loss/train': 1.9211030006408691}
-03/04/2022 17:02:41 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/04/2022 17:02:46 - INFO - codeparrot_training - Step 23484: {'lr': 0.00047445083333582104, 'samples': 12024320, 'steps': 23484, 'loss/train': 1.236321210861206}
-03/04/2022 17:02:49 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 17:02:52 - INFO - codeparrot_training - Step 23485: {'lr': 0.00047444849621303023, 'samples': 12024832, 'steps': 23485, 'loss/train': 2.413282632827759}
-03/04/2022 17:02:55 - INFO - codeparrot_training - Step 23486: {'lr': 0.00047444615898910644, 'samples': 12025344, 'steps': 23486, 'loss/train': 1.1261612176895142}
-03/04/2022 17:02:58 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/04/2022 17:03:00 - INFO - codeparrot_training - Step 23487: {'lr': 0.00047444382166405067, 'samples': 12025856, 'steps': 23487, 'loss/train': 1.9765197038650513}
-03/04/2022 17:03:03 - INFO - codeparrot_training - Step 23488: {'lr': 0.0004744414842378639, 'samples': 12026368, 'steps': 23488, 'loss/train': 1.2254644632339478}
-03/04/2022 17:03:06 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/04/2022 17:03:09 - INFO - codeparrot_training - Step 23489: {'lr': 0.0004744391467105473, 'samples': 12026880, 'steps': 23489, 'loss/train': 1.5679121017456055}
-03/04/2022 17:03:12 - INFO - codeparrot_training - Step 23490: {'lr': 0.00047443680908210194, 'samples': 12027392, 'steps': 23490, 'loss/train': 2.325765371322632}
-03/04/2022 17:03:15 - INFO - codeparrot_training - Step 23491: {'lr': 0.00047443447135252876, 'samples': 12027904, 'steps': 23491, 'loss/train': 1.0986268520355225}
-03/04/2022 17:03:15 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/04/2022 17:03:20 - INFO - codeparrot_training - Step 23492: {'lr': 0.0004744321335218289, 'samples': 12028416, 'steps': 23492, 'loss/train': 2.4800143241882324}
-03/04/2022 17:03:23 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/04/2022 17:03:26 - INFO - codeparrot_training - Step 23493: {'lr': 0.0004744297955900034, 'samples': 12028928, 'steps': 23493, 'loss/train': 1.912929892539978}
-03/04/2022 17:03:29 - INFO - codeparrot_training - Step 23494: {'lr': 0.00047442745755705326, 'samples': 12029440, 'steps': 23494, 'loss/train': 1.6387978792190552}
-03/04/2022 17:03:32 - INFO - codeparrot_training - Step 23495: {'lr': 0.00047442511942297953, 'samples': 12029952, 'steps': 23495, 'loss/train': 2.175175189971924}
-03/04/2022 17:03:32 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/04/2022 17:03:37 - INFO - codeparrot_training - Step 23496: {'lr': 0.00047442278118778336, 'samples': 12030464, 'steps': 23496, 'loss/train': 1.7177956104278564}
-03/04/2022 17:03:40 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 17:03:42 - INFO - codeparrot_training - Step 23497: {'lr': 0.0004744204428514658, 'samples': 12030976, 'steps': 23497, 'loss/train': 1.0397047996520996}
-03/04/2022 17:03:46 - INFO - codeparrot_training - Step 23498: {'lr': 0.00047441810441402777, 'samples': 12031488, 'steps': 23498, 'loss/train': 1.153900146484375}
-03/04/2022 17:03:48 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/04/2022 17:03:51 - INFO - codeparrot_training - Step 23499: {'lr': 0.0004744157658754704, 'samples': 12032000, 'steps': 23499, 'loss/train': 1.704856038093567}
-03/04/2022 17:03:54 - INFO - codeparrot_training - Step 23500: {'lr': 0.0004744134272357948, 'samples': 12032512, 'steps': 23500, 'loss/train': 1.55928635597229}
-03/04/2022 17:03:56 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 17:03:59 - INFO - codeparrot_training - Step 23501: {'lr': 0.0004744110884950019, 'samples': 12033024, 'steps': 23501, 'loss/train': 2.0780394077301025}
-03/04/2022 17:04:02 - INFO - codeparrot_training - Step 23502: {'lr': 0.00047440874965309286, 'samples': 12033536, 'steps': 23502, 'loss/train': 1.1428110599517822}
-03/04/2022 17:04:05 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 17:04:08 - INFO - codeparrot_training - Step 23503: {'lr': 0.00047440641071006874, 'samples': 12034048, 'steps': 23503, 'loss/train': 1.0073317289352417}
-03/04/2022 17:04:11 - INFO - codeparrot_training - Step 23504: {'lr': 0.00047440407166593056, 'samples': 12034560, 'steps': 23504, 'loss/train': 1.7784956693649292}
-03/04/2022 17:04:13 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/04/2022 17:04:16 - INFO - codeparrot_training - Step 23505: {'lr': 0.0004744017325206793, 'samples': 12035072, 'steps': 23505, 'loss/train': 2.369910478591919}
-03/04/2022 17:04:19 - INFO - codeparrot_training - Step 23506: {'lr': 0.00047439939327431613, 'samples': 12035584, 'steps': 23506, 'loss/train': 2.3670477867126465}
-03/04/2022 17:04:23 - INFO - codeparrot_training - Step 23507: {'lr': 0.0004743970539268421, 'samples': 12036096, 'steps': 23507, 'loss/train': 0.7686943411827087}
-03/04/2022 17:04:23 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 17:04:28 - INFO - codeparrot_training - Step 23508: {'lr': 0.00047439471447825813, 'samples': 12036608, 'steps': 23508, 'loss/train': 2.1253182888031006}
-03/04/2022 17:04:31 - INFO - codeparrot_training - Step 23509: {'lr': 0.00047439237492856543, 'samples': 12037120, 'steps': 23509, 'loss/train': 2.4260661602020264}
-03/04/2022 17:04:31 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/04/2022 17:04:36 - INFO - codeparrot_training - Step 23510: {'lr': 0.0004743900352777649, 'samples': 12037632, 'steps': 23510, 'loss/train': 2.1083579063415527}
-03/04/2022 17:04:39 - INFO - codeparrot_training - Step 23511: {'lr': 0.0004743876955258578, 'samples': 12038144, 'steps': 23511, 'loss/train': 0.2786150872707367}
-03/04/2022 17:04:40 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/04/2022 17:04:45 - INFO - codeparrot_training - Step 23512: {'lr': 0.00047438535567284504, 'samples': 12038656, 'steps': 23512, 'loss/train': 2.179335355758667}
-03/04/2022 17:04:48 - INFO - codeparrot_training - Step 23513: {'lr': 0.00047438301571872763, 'samples': 12039168, 'steps': 23513, 'loss/train': 2.132192611694336}
-03/04/2022 17:04:48 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 17:04:53 - INFO - codeparrot_training - Step 23514: {'lr': 0.00047438067566350675, 'samples': 12039680, 'steps': 23514, 'loss/train': 1.8619375228881836}
-03/04/2022 17:04:56 - INFO - codeparrot_training - Step 23515: {'lr': 0.00047437833550718336, 'samples': 12040192, 'steps': 23515, 'loss/train': 2.378436803817749}
-03/04/2022 17:04:57 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/04/2022 17:05:02 - INFO - codeparrot_training - Step 23516: {'lr': 0.0004743759952497586, 'samples': 12040704, 'steps': 23516, 'loss/train': 0.8898215889930725}
-03/04/2022 17:05:05 - INFO - codeparrot_training - Step 23517: {'lr': 0.0004743736548912334, 'samples': 12041216, 'steps': 23517, 'loss/train': 1.524056315422058}
-03/04/2022 17:05:05 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 17:05:10 - INFO - codeparrot_training - Step 23518: {'lr': 0.00047437131443160897, 'samples': 12041728, 'steps': 23518, 'loss/train': 1.9366751909255981}
-03/04/2022 17:05:13 - INFO - codeparrot_training - Step 23519: {'lr': 0.0004743689738708863, 'samples': 12042240, 'steps': 23519, 'loss/train': 1.8843666315078735}
-03/04/2022 17:05:14 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/04/2022 17:05:18 - INFO - codeparrot_training - Step 23520: {'lr': 0.0004743666332090664, 'samples': 12042752, 'steps': 23520, 'loss/train': 2.3018317222595215}
-03/04/2022 17:05:22 - INFO - codeparrot_training - Step 23521: {'lr': 0.00047436429244615037, 'samples': 12043264, 'steps': 23521, 'loss/train': 2.0193848609924316}
-03/04/2022 17:05:22 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 17:05:27 - INFO - codeparrot_training - Step 23522: {'lr': 0.0004743619515821392, 'samples': 12043776, 'steps': 23522, 'loss/train': 2.4107556343078613}
-03/04/2022 17:05:30 - INFO - codeparrot_training - Step 23523: {'lr': 0.00047435961061703403, 'samples': 12044288, 'steps': 23523, 'loss/train': 1.341386079788208}
-03/04/2022 17:05:30 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/04/2022 17:05:35 - INFO - codeparrot_training - Step 23524: {'lr': 0.00047435726955083593, 'samples': 12044800, 'steps': 23524, 'loss/train': 2.6173596382141113}
-03/04/2022 17:05:39 - INFO - codeparrot_training - Step 23525: {'lr': 0.0004743549283835459, 'samples': 12045312, 'steps': 23525, 'loss/train': 1.7510402202606201}
-03/04/2022 17:05:39 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/04/2022 17:05:44 - INFO - codeparrot_training - Step 23526: {'lr': 0.00047435258711516496, 'samples': 12045824, 'steps': 23526, 'loss/train': 1.5542188882827759}
-03/04/2022 17:05:47 - INFO - codeparrot_training - Step 23527: {'lr': 0.0004743502457456942, 'samples': 12046336, 'steps': 23527, 'loss/train': 2.670391798019409}
-03/04/2022 17:05:47 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 17:05:52 - INFO - codeparrot_training - Step 23528: {'lr': 0.0004743479042751347, 'samples': 12046848, 'steps': 23528, 'loss/train': 1.172585368156433}
-03/04/2022 17:05:55 - INFO - codeparrot_training - Step 23529: {'lr': 0.0004743455627034875, 'samples': 12047360, 'steps': 23529, 'loss/train': 2.2008514404296875}
-03/04/2022 17:05:55 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/04/2022 17:06:01 - INFO - codeparrot_training - Step 23530: {'lr': 0.0004743432210307536, 'samples': 12047872, 'steps': 23530, 'loss/train': 1.9725878238677979}
-03/04/2022 17:06:04 - INFO - codeparrot_training - Step 23531: {'lr': 0.00047434087925693415, 'samples': 12048384, 'steps': 23531, 'loss/train': 1.465010166168213}
-03/04/2022 17:06:04 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 17:06:09 - INFO - codeparrot_training - Step 23532: {'lr': 0.00047433853738203013, 'samples': 12048896, 'steps': 23532, 'loss/train': 1.5991606712341309}
-03/04/2022 17:06:12 - INFO - codeparrot_training - Step 23533: {'lr': 0.00047433619540604264, 'samples': 12049408, 'steps': 23533, 'loss/train': 1.849231481552124}
-03/04/2022 17:06:12 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 17:06:18 - INFO - codeparrot_training - Step 23534: {'lr': 0.0004743338533289728, 'samples': 12049920, 'steps': 23534, 'loss/train': 0.566605269908905}
-03/04/2022 17:06:21 - INFO - codeparrot_training - Step 23535: {'lr': 0.0004743315111508215, 'samples': 12050432, 'steps': 23535, 'loss/train': 1.4799652099609375}
-03/04/2022 17:06:21 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/04/2022 17:06:26 - INFO - codeparrot_training - Step 23536: {'lr': 0.00047432916887158995, 'samples': 12050944, 'steps': 23536, 'loss/train': 2.2299134731292725}
-03/04/2022 17:06:30 - INFO - codeparrot_training - Step 23537: {'lr': 0.00047432682649127913, 'samples': 12051456, 'steps': 23537, 'loss/train': 1.3016821146011353}
-03/04/2022 17:06:30 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/04/2022 17:06:35 - INFO - codeparrot_training - Step 23538: {'lr': 0.00047432448400989004, 'samples': 12051968, 'steps': 23538, 'loss/train': 1.8141227960586548}
-03/04/2022 17:06:38 - INFO - codeparrot_training - Step 23539: {'lr': 0.0004743221414274238, 'samples': 12052480, 'steps': 23539, 'loss/train': 2.004836320877075}
-03/04/2022 17:06:38 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/04/2022 17:06:43 - INFO - codeparrot_training - Step 23540: {'lr': 0.00047431979874388154, 'samples': 12052992, 'steps': 23540, 'loss/train': 2.150920867919922}
-03/04/2022 17:06:46 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/04/2022 17:06:49 - INFO - codeparrot_training - Step 23541: {'lr': 0.0004743174559592642, 'samples': 12053504, 'steps': 23541, 'loss/train': 2.4125759601593018}
-03/04/2022 17:06:52 - INFO - codeparrot_training - Step 23542: {'lr': 0.0004743151130735729, 'samples': 12054016, 'steps': 23542, 'loss/train': 1.8427445888519287}
-03/04/2022 17:06:55 - INFO - codeparrot_training - Step 23543: {'lr': 0.0004743127700868086, 'samples': 12054528, 'steps': 23543, 'loss/train': 2.0841121673583984}
-03/04/2022 17:06:55 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 17:07:00 - INFO - codeparrot_training - Step 23544: {'lr': 0.00047431042699897245, 'samples': 12055040, 'steps': 23544, 'loss/train': 2.097198963165283}
-03/04/2022 17:07:04 - INFO - codeparrot_training - Step 23545: {'lr': 0.0004743080838100655, 'samples': 12055552, 'steps': 23545, 'loss/train': 1.3232982158660889}
-03/04/2022 17:07:04 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 17:07:09 - INFO - codeparrot_training - Step 23546: {'lr': 0.0004743057405200888, 'samples': 12056064, 'steps': 23546, 'loss/train': 1.6844393014907837}
-03/04/2022 17:07:12 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/04/2022 17:07:14 - INFO - codeparrot_training - Step 23547: {'lr': 0.0004743033971290434, 'samples': 12056576, 'steps': 23547, 'loss/train': 2.1217081546783447}
-03/04/2022 17:07:18 - INFO - codeparrot_training - Step 23548: {'lr': 0.00047430105363693034, 'samples': 12057088, 'steps': 23548, 'loss/train': 1.9872835874557495}
-03/04/2022 17:07:20 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 17:07:23 - INFO - codeparrot_training - Step 23549: {'lr': 0.0004742987100437507, 'samples': 12057600, 'steps': 23549, 'loss/train': 2.7428267002105713}
-03/04/2022 17:07:26 - INFO - codeparrot_training - Step 23550: {'lr': 0.00047429636634950545, 'samples': 12058112, 'steps': 23550, 'loss/train': 1.4733387231826782}
-03/04/2022 17:07:29 - INFO - codeparrot_training - Step 23551: {'lr': 0.0004742940225541958, 'samples': 12058624, 'steps': 23551, 'loss/train': 2.3202245235443115}
-03/04/2022 17:07:29 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/04/2022 17:07:35 - INFO - codeparrot_training - Step 23552: {'lr': 0.0004742916786578227, 'samples': 12059136, 'steps': 23552, 'loss/train': 2.0435256958007812}
-03/04/2022 17:07:38 - INFO - codeparrot_training - Step 23553: {'lr': 0.00047428933466038726, 'samples': 12059648, 'steps': 23553, 'loss/train': 1.517012119293213}
-03/04/2022 17:07:38 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/04/2022 17:07:43 - INFO - codeparrot_training - Step 23554: {'lr': 0.00047428699056189047, 'samples': 12060160, 'steps': 23554, 'loss/train': 0.7259073853492737}
-03/04/2022 17:07:46 - INFO - codeparrot_training - Step 23555: {'lr': 0.0004742846463623334, 'samples': 12060672, 'steps': 23555, 'loss/train': 1.9352827072143555}
-03/04/2022 17:07:46 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/04/2022 17:07:52 - INFO - codeparrot_training - Step 23556: {'lr': 0.0004742823020617172, 'samples': 12061184, 'steps': 23556, 'loss/train': 1.9622342586517334}
-03/04/2022 17:07:55 - INFO - codeparrot_training - Step 23557: {'lr': 0.0004742799576600427, 'samples': 12061696, 'steps': 23557, 'loss/train': 0.8845088481903076}
-03/04/2022 17:07:55 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 17:08:00 - INFO - codeparrot_training - Step 23558: {'lr': 0.00047427761315731133, 'samples': 12062208, 'steps': 23558, 'loss/train': 1.967919111251831}
-03/04/2022 17:08:03 - INFO - codeparrot_training - Step 23559: {'lr': 0.0004742752685535238, 'samples': 12062720, 'steps': 23559, 'loss/train': 2.3167214393615723}
-03/04/2022 17:08:04 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/04/2022 17:08:09 - INFO - codeparrot_training - Step 23560: {'lr': 0.00047427292384868134, 'samples': 12063232, 'steps': 23560, 'loss/train': 1.4588333368301392}
-03/04/2022 17:08:12 - INFO - codeparrot_training - Step 23561: {'lr': 0.0004742705790427849, 'samples': 12063744, 'steps': 23561, 'loss/train': 1.6884890794754028}
-03/04/2022 17:08:12 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 17:08:17 - INFO - codeparrot_training - Step 23562: {'lr': 0.00047426823413583563, 'samples': 12064256, 'steps': 23562, 'loss/train': 2.415215253829956}
-03/04/2022 17:08:20 - INFO - codeparrot_training - Step 23563: {'lr': 0.0004742658891278346, 'samples': 12064768, 'steps': 23563, 'loss/train': 1.3076276779174805}
-03/04/2022 17:08:21 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 17:08:25 - INFO - codeparrot_training - Step 23564: {'lr': 0.0004742635440187828, 'samples': 12065280, 'steps': 23564, 'loss/train': 2.0545005798339844}
-03/04/2022 17:08:29 - INFO - codeparrot_training - Step 23565: {'lr': 0.00047426119880868123, 'samples': 12065792, 'steps': 23565, 'loss/train': 1.8653738498687744}
-03/04/2022 17:08:29 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 17:08:34 - INFO - codeparrot_training - Step 23566: {'lr': 0.00047425885349753114, 'samples': 12066304, 'steps': 23566, 'loss/train': 1.3180036544799805}
-03/04/2022 17:08:37 - INFO - codeparrot_training - Step 23567: {'lr': 0.0004742565080853334, 'samples': 12066816, 'steps': 23567, 'loss/train': 1.856196403503418}
-03/04/2022 17:08:37 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/04/2022 17:08:42 - INFO - codeparrot_training - Step 23568: {'lr': 0.00047425416257208916, 'samples': 12067328, 'steps': 23568, 'loss/train': 1.5974044799804688}
-03/04/2022 17:08:45 - INFO - codeparrot_training - Step 23569: {'lr': 0.0004742518169577994, 'samples': 12067840, 'steps': 23569, 'loss/train': 2.042630910873413}
-03/04/2022 17:08:46 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/04/2022 17:08:51 - INFO - codeparrot_training - Step 23570: {'lr': 0.0004742494712424653, 'samples': 12068352, 'steps': 23570, 'loss/train': 1.7507457733154297}
-03/04/2022 17:08:54 - INFO - codeparrot_training - Step 23571: {'lr': 0.0004742471254260878, 'samples': 12068864, 'steps': 23571, 'loss/train': 2.1467745304107666}
-03/04/2022 17:08:54 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 17:08:59 - INFO - codeparrot_training - Step 23572: {'lr': 0.0004742447795086681, 'samples': 12069376, 'steps': 23572, 'loss/train': 1.8383021354675293}
-03/04/2022 17:09:02 - INFO - codeparrot_training - Step 23573: {'lr': 0.00047424243349020705, 'samples': 12069888, 'steps': 23573, 'loss/train': 1.8616427183151245}
-03/04/2022 17:09:03 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 17:09:08 - INFO - codeparrot_training - Step 23574: {'lr': 0.0004742400873707059, 'samples': 12070400, 'steps': 23574, 'loss/train': 1.8526434898376465}
-03/04/2022 17:09:11 - INFO - codeparrot_training - Step 23575: {'lr': 0.0004742377411501656, 'samples': 12070912, 'steps': 23575, 'loss/train': 1.5271366834640503}
-03/04/2022 17:09:11 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/04/2022 17:09:16 - INFO - codeparrot_training - Step 23576: {'lr': 0.00047423539482858724, 'samples': 12071424, 'steps': 23576, 'loss/train': 0.7044313549995422}
-03/04/2022 17:09:19 - INFO - codeparrot_training - Step 23577: {'lr': 0.0004742330484059718, 'samples': 12071936, 'steps': 23577, 'loss/train': 2.0854175090789795}
-03/04/2022 17:09:20 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/04/2022 17:09:25 - INFO - codeparrot_training - Step 23578: {'lr': 0.0004742307018823205, 'samples': 12072448, 'steps': 23578, 'loss/train': 2.156951904296875}
-03/04/2022 17:09:28 - INFO - codeparrot_training - Step 23579: {'lr': 0.0004742283552576343, 'samples': 12072960, 'steps': 23579, 'loss/train': 0.9826322793960571}
-03/04/2022 17:09:28 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 17:09:33 - INFO - codeparrot_training - Step 23580: {'lr': 0.0004742260085319142, 'samples': 12073472, 'steps': 23580, 'loss/train': 1.7294145822525024}
-03/04/2022 17:09:36 - INFO - codeparrot_training - Step 23581: {'lr': 0.0004742236617051614, 'samples': 12073984, 'steps': 23581, 'loss/train': 2.805243968963623}
-03/04/2022 17:09:37 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 17:09:41 - INFO - codeparrot_training - Step 23582: {'lr': 0.00047422131477737684, 'samples': 12074496, 'steps': 23582, 'loss/train': 1.8112674951553345}
-03/04/2022 17:09:45 - INFO - codeparrot_training - Step 23583: {'lr': 0.00047421896774856156, 'samples': 12075008, 'steps': 23583, 'loss/train': 1.5441052913665771}
-03/04/2022 17:09:45 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/04/2022 17:09:50 - INFO - codeparrot_training - Step 23584: {'lr': 0.00047421662061871675, 'samples': 12075520, 'steps': 23584, 'loss/train': 1.4458791017532349}
-03/04/2022 17:09:53 - INFO - codeparrot_training - Step 23585: {'lr': 0.0004742142733878433, 'samples': 12076032, 'steps': 23585, 'loss/train': 1.349284291267395}
-03/04/2022 17:09:54 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/04/2022 17:09:58 - INFO - codeparrot_training - Step 23586: {'lr': 0.0004742119260559424, 'samples': 12076544, 'steps': 23586, 'loss/train': 1.6640053987503052}
-03/04/2022 17:10:01 - INFO - codeparrot_training - Step 23587: {'lr': 0.0004742095786230152, 'samples': 12077056, 'steps': 23587, 'loss/train': 1.9211853742599487}
-03/04/2022 17:10:02 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/04/2022 17:10:07 - INFO - codeparrot_training - Step 23588: {'lr': 0.00047420723108906247, 'samples': 12077568, 'steps': 23588, 'loss/train': 1.4528789520263672}
-03/04/2022 17:10:10 - INFO - codeparrot_training - Step 23589: {'lr': 0.0004742048834540855, 'samples': 12078080, 'steps': 23589, 'loss/train': 0.8327783346176147}
-03/04/2022 17:10:10 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 17:10:15 - INFO - codeparrot_training - Step 23590: {'lr': 0.0004742025357180852, 'samples': 12078592, 'steps': 23590, 'loss/train': 1.0128346681594849}
-03/04/2022 17:10:18 - INFO - codeparrot_training - Step 23591: {'lr': 0.00047420018788106274, 'samples': 12079104, 'steps': 23591, 'loss/train': 1.473543643951416}
-03/04/2022 17:10:19 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 17:10:24 - INFO - codeparrot_training - Step 23592: {'lr': 0.00047419783994301915, 'samples': 12079616, 'steps': 23592, 'loss/train': 2.0908610820770264}
-03/04/2022 17:10:27 - INFO - codeparrot_training - Step 23593: {'lr': 0.0004741954919039554, 'samples': 12080128, 'steps': 23593, 'loss/train': 1.4416587352752686}
-03/04/2022 17:10:27 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 17:10:32 - INFO - codeparrot_training - Step 23594: {'lr': 0.0004741931437638727, 'samples': 12080640, 'steps': 23594, 'loss/train': 2.2837343215942383}
-03/04/2022 17:10:35 - INFO - codeparrot_training - Step 23595: {'lr': 0.000474190795522772, 'samples': 12081152, 'steps': 23595, 'loss/train': 1.3336920738220215}
-03/04/2022 17:10:36 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/04/2022 17:10:41 - INFO - codeparrot_training - Step 23596: {'lr': 0.00047418844718065433, 'samples': 12081664, 'steps': 23596, 'loss/train': 1.7545489072799683}
-03/04/2022 17:10:44 - INFO - codeparrot_training - Step 23597: {'lr': 0.0004741860987375209, 'samples': 12082176, 'steps': 23597, 'loss/train': 2.0765738487243652}
-03/04/2022 17:10:44 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 17:10:49 - INFO - codeparrot_training - Step 23598: {'lr': 0.00047418375019337263, 'samples': 12082688, 'steps': 23598, 'loss/train': 1.6435551643371582}
-03/04/2022 17:10:52 - INFO - codeparrot_training - Step 23599: {'lr': 0.00047418140154821065, 'samples': 12083200, 'steps': 23599, 'loss/train': 1.867525339126587}
-03/04/2022 17:10:53 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/04/2022 17:10:57 - INFO - codeparrot_training - Step 23600: {'lr': 0.00047417905280203594, 'samples': 12083712, 'steps': 23600, 'loss/train': 1.9708377122879028}
-03/04/2022 17:11:00 - INFO - codeparrot_training - Step 23601: {'lr': 0.00047417670395484963, 'samples': 12084224, 'steps': 23601, 'loss/train': 1.2928062677383423}
-03/04/2022 17:11:01 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 17:11:06 - INFO - codeparrot_training - Step 23602: {'lr': 0.0004741743550066527, 'samples': 12084736, 'steps': 23602, 'loss/train': 2.3730242252349854}
-03/04/2022 17:11:09 - INFO - codeparrot_training - Step 23603: {'lr': 0.00047417200595744637, 'samples': 12085248, 'steps': 23603, 'loss/train': 1.125169038772583}
-03/04/2022 17:11:09 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/04/2022 17:11:14 - INFO - codeparrot_training - Step 23604: {'lr': 0.0004741696568072316, 'samples': 12085760, 'steps': 23604, 'loss/train': 1.5960971117019653}
-03/04/2022 17:11:17 - INFO - codeparrot_training - Step 23605: {'lr': 0.00047416730755600936, 'samples': 12086272, 'steps': 23605, 'loss/train': 2.3962724208831787}
-03/04/2022 17:11:18 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/04/2022 17:11:23 - INFO - codeparrot_training - Step 23606: {'lr': 0.0004741649582037808, 'samples': 12086784, 'steps': 23606, 'loss/train': 0.5510353446006775}
-03/04/2022 17:11:26 - INFO - codeparrot_training - Step 23607: {'lr': 0.000474162608750547, 'samples': 12087296, 'steps': 23607, 'loss/train': 2.0942811965942383}
-03/04/2022 17:11:26 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 17:11:31 - INFO - codeparrot_training - Step 23608: {'lr': 0.000474160259196309, 'samples': 12087808, 'steps': 23608, 'loss/train': 1.9427745342254639}
-03/04/2022 17:11:34 - INFO - codeparrot_training - Step 23609: {'lr': 0.0004741579095410678, 'samples': 12088320, 'steps': 23609, 'loss/train': 2.088855266571045}
-03/04/2022 17:11:34 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/04/2022 17:11:39 - INFO - codeparrot_training - Step 23610: {'lr': 0.0004741555597848245, 'samples': 12088832, 'steps': 23610, 'loss/train': 2.0565576553344727}
-03/04/2022 17:11:43 - INFO - codeparrot_training - Step 23611: {'lr': 0.00047415320992758025, 'samples': 12089344, 'steps': 23611, 'loss/train': 2.374455451965332}
-03/04/2022 17:11:43 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 17:11:48 - INFO - codeparrot_training - Step 23612: {'lr': 0.00047415085996933593, 'samples': 12089856, 'steps': 23612, 'loss/train': 1.7058137655258179}
-03/04/2022 17:11:51 - INFO - codeparrot_training - Step 23613: {'lr': 0.00047414850991009275, 'samples': 12090368, 'steps': 23613, 'loss/train': 1.9095895290374756}
-03/04/2022 17:11:51 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 17:11:56 - INFO - codeparrot_training - Step 23614: {'lr': 0.00047414615974985164, 'samples': 12090880, 'steps': 23614, 'loss/train': 1.8851245641708374}
-03/04/2022 17:12:00 - INFO - codeparrot_training - Step 23615: {'lr': 0.0004741438094886138, 'samples': 12091392, 'steps': 23615, 'loss/train': 2.1114790439605713}
-03/04/2022 17:12:00 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/04/2022 17:12:06 - INFO - codeparrot_training - Step 23616: {'lr': 0.00047414145912638017, 'samples': 12091904, 'steps': 23616, 'loss/train': 1.9975779056549072}
-03/04/2022 17:12:09 - INFO - codeparrot_training - Step 23617: {'lr': 0.00047413910866315193, 'samples': 12092416, 'steps': 23617, 'loss/train': 1.2613639831542969}
-03/04/2022 17:12:12 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/04/2022 17:12:14 - INFO - codeparrot_training - Step 23618: {'lr': 0.00047413675809893, 'samples': 12092928, 'steps': 23618, 'loss/train': 2.2748653888702393}
-03/04/2022 17:12:17 - INFO - codeparrot_training - Step 23619: {'lr': 0.0004741344074337155, 'samples': 12093440, 'steps': 23619, 'loss/train': 1.9464027881622314}
-03/04/2022 17:12:20 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/04/2022 17:12:22 - INFO - codeparrot_training - Step 23620: {'lr': 0.00047413205666750955, 'samples': 12093952, 'steps': 23620, 'loss/train': 2.141181468963623}
-03/04/2022 17:12:26 - INFO - codeparrot_training - Step 23621: {'lr': 0.0004741297058003131, 'samples': 12094464, 'steps': 23621, 'loss/train': 1.5295274257659912}
-03/04/2022 17:12:28 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 17:12:31 - INFO - codeparrot_training - Step 23622: {'lr': 0.00047412735483212725, 'samples': 12094976, 'steps': 23622, 'loss/train': 1.7531987428665161}
-03/04/2022 17:12:34 - INFO - codeparrot_training - Step 23623: {'lr': 0.0004741250037629531, 'samples': 12095488, 'steps': 23623, 'loss/train': 2.047591209411621}
-03/04/2022 17:12:37 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/04/2022 17:12:39 - INFO - codeparrot_training - Step 23624: {'lr': 0.00047412265259279176, 'samples': 12096000, 'steps': 23624, 'loss/train': 2.372868299484253}
-03/04/2022 17:12:42 - INFO - codeparrot_training - Step 23625: {'lr': 0.0004741203013216441, 'samples': 12096512, 'steps': 23625, 'loss/train': 2.2884137630462646}
-03/04/2022 17:12:45 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/04/2022 17:12:48 - INFO - codeparrot_training - Step 23626: {'lr': 0.0004741179499495113, 'samples': 12097024, 'steps': 23626, 'loss/train': 0.9960039258003235}
-03/04/2022 17:12:51 - INFO - codeparrot_training - Step 23627: {'lr': 0.00047411559847639447, 'samples': 12097536, 'steps': 23627, 'loss/train': 1.1575157642364502}
-03/04/2022 17:12:54 - INFO - codeparrot_training - Step 23628: {'lr': 0.0004741132469022946, 'samples': 12098048, 'steps': 23628, 'loss/train': 0.948320209980011}
-03/04/2022 17:12:54 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 17:12:59 - INFO - codeparrot_training - Step 23629: {'lr': 0.00047411089522721275, 'samples': 12098560, 'steps': 23629, 'loss/train': 2.1054747104644775}
-03/04/2022 17:13:02 - INFO - codeparrot_training - Step 23630: {'lr': 0.00047410854345114996, 'samples': 12099072, 'steps': 23630, 'loss/train': 2.1440908908843994}
-03/04/2022 17:13:03 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 17:13:08 - INFO - codeparrot_training - Step 23631: {'lr': 0.0004741061915741073, 'samples': 12099584, 'steps': 23631, 'loss/train': 2.049994707107544}
-03/04/2022 17:13:11 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 17:13:13 - INFO - codeparrot_training - Step 23632: {'lr': 0.0004741038395960859, 'samples': 12100096, 'steps': 23632, 'loss/train': 1.2414079904556274}
-03/04/2022 17:13:16 - INFO - codeparrot_training - Step 23633: {'lr': 0.0004741014875170867, 'samples': 12100608, 'steps': 23633, 'loss/train': 1.8847893476486206}
-03/04/2022 17:13:19 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 17:13:21 - INFO - codeparrot_training - Step 23634: {'lr': 0.0004740991353371109, 'samples': 12101120, 'steps': 23634, 'loss/train': 2.2249531745910645}
-03/04/2022 17:13:25 - INFO - codeparrot_training - Step 23635: {'lr': 0.0004740967830561595, 'samples': 12101632, 'steps': 23635, 'loss/train': 1.290770411491394}
-03/04/2022 17:13:27 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/04/2022 17:13:30 - INFO - codeparrot_training - Step 23636: {'lr': 0.0004740944306742335, 'samples': 12102144, 'steps': 23636, 'loss/train': 2.369663715362549}
-03/04/2022 17:13:33 - INFO - codeparrot_training - Step 23637: {'lr': 0.00047409207819133406, 'samples': 12102656, 'steps': 23637, 'loss/train': 2.040771007537842}
-03/04/2022 17:13:36 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 17:13:38 - INFO - codeparrot_training - Step 23638: {'lr': 0.0004740897256074621, 'samples': 12103168, 'steps': 23638, 'loss/train': 2.007297992706299}
-03/04/2022 17:13:42 - INFO - codeparrot_training - Step 23639: {'lr': 0.00047408737292261883, 'samples': 12103680, 'steps': 23639, 'loss/train': 3.635899305343628}
-03/04/2022 17:13:44 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 17:13:47 - INFO - codeparrot_training - Step 23640: {'lr': 0.0004740850201368052, 'samples': 12104192, 'steps': 23640, 'loss/train': 2.0706632137298584}
-03/04/2022 17:13:50 - INFO - codeparrot_training - Step 23641: {'lr': 0.00047408266725002234, 'samples': 12104704, 'steps': 23641, 'loss/train': 1.956384539604187}
-03/04/2022 17:13:53 - INFO - codeparrot_training - Step 23642: {'lr': 0.00047408031426227136, 'samples': 12105216, 'steps': 23642, 'loss/train': 1.8224693536758423}
-03/04/2022 17:13:54 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 17:13:59 - INFO - codeparrot_training - Step 23643: {'lr': 0.0004740779611735532, 'samples': 12105728, 'steps': 23643, 'loss/train': 1.6501497030258179}
-03/04/2022 17:14:02 - INFO - codeparrot_training - Step 23644: {'lr': 0.00047407560798386894, 'samples': 12106240, 'steps': 23644, 'loss/train': 2.0401883125305176}
-03/04/2022 17:14:02 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/04/2022 17:14:07 - INFO - codeparrot_training - Step 23645: {'lr': 0.00047407325469321973, 'samples': 12106752, 'steps': 23645, 'loss/train': 1.2853413820266724}
-03/04/2022 17:14:10 - INFO - codeparrot_training - Step 23646: {'lr': 0.0004740709013016065, 'samples': 12107264, 'steps': 23646, 'loss/train': 2.1101059913635254}
-03/04/2022 17:14:11 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 17:14:16 - INFO - codeparrot_training - Step 23647: {'lr': 0.0004740685478090304, 'samples': 12107776, 'steps': 23647, 'loss/train': 2.25382924079895}
-03/04/2022 17:14:19 - INFO - codeparrot_training - Step 23648: {'lr': 0.00047406619421549247, 'samples': 12108288, 'steps': 23648, 'loss/train': 1.7696454524993896}
-03/04/2022 17:14:19 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/04/2022 17:14:24 - INFO - codeparrot_training - Step 23649: {'lr': 0.0004740638405209938, 'samples': 12108800, 'steps': 23649, 'loss/train': 1.336594820022583}
-03/04/2022 17:14:27 - INFO - codeparrot_training - Step 23650: {'lr': 0.0004740614867255353, 'samples': 12109312, 'steps': 23650, 'loss/train': 1.204626441001892}
-03/04/2022 17:14:28 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/04/2022 17:14:33 - INFO - codeparrot_training - Step 23651: {'lr': 0.0004740591328291183, 'samples': 12109824, 'steps': 23651, 'loss/train': 1.911062479019165}
-03/04/2022 17:14:36 - INFO - codeparrot_training - Step 23652: {'lr': 0.0004740567788317437, 'samples': 12110336, 'steps': 23652, 'loss/train': 1.620890736579895}
-03/04/2022 17:14:37 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/04/2022 17:14:41 - INFO - codeparrot_training - Step 23653: {'lr': 0.00047405442473341246, 'samples': 12110848, 'steps': 23653, 'loss/train': 1.7959572076797485}
-03/04/2022 17:14:44 - INFO - codeparrot_training - Step 23654: {'lr': 0.0004740520705341259, 'samples': 12111360, 'steps': 23654, 'loss/train': 2.5285186767578125}
-03/04/2022 17:14:45 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/04/2022 17:14:50 - INFO - codeparrot_training - Step 23655: {'lr': 0.0004740497162338848, 'samples': 12111872, 'steps': 23655, 'loss/train': 1.4534214735031128}
-03/04/2022 17:14:53 - INFO - codeparrot_training - Step 23656: {'lr': 0.00047404736183269045, 'samples': 12112384, 'steps': 23656, 'loss/train': 1.4537698030471802}
-03/04/2022 17:14:54 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/04/2022 17:14:58 - INFO - codeparrot_training - Step 23657: {'lr': 0.0004740450073305438, 'samples': 12112896, 'steps': 23657, 'loss/train': 1.4667598009109497}
-03/04/2022 17:15:01 - INFO - codeparrot_training - Step 23658: {'lr': 0.00047404265272744586, 'samples': 12113408, 'steps': 23658, 'loss/train': 1.3832734823226929}
-03/04/2022 17:15:02 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/04/2022 17:15:06 - INFO - codeparrot_training - Step 23659: {'lr': 0.0004740402980233978, 'samples': 12113920, 'steps': 23659, 'loss/train': 2.09853196144104}
-03/04/2022 17:15:10 - INFO - codeparrot_training - Step 23660: {'lr': 0.00047403794321840064, 'samples': 12114432, 'steps': 23660, 'loss/train': 1.8587846755981445}
-03/04/2022 17:15:11 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/04/2022 17:15:15 - INFO - codeparrot_training - Step 23661: {'lr': 0.0004740355883124555, 'samples': 12114944, 'steps': 23661, 'loss/train': 1.103425145149231}
-03/04/2022 17:15:18 - INFO - codeparrot_training - Step 23662: {'lr': 0.0004740332333055633, 'samples': 12115456, 'steps': 23662, 'loss/train': 2.531468629837036}
-03/04/2022 17:15:19 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/04/2022 17:15:23 - INFO - codeparrot_training - Step 23663: {'lr': 0.00047403087819772517, 'samples': 12115968, 'steps': 23663, 'loss/train': 2.1275932788848877}
-03/04/2022 17:15:26 - INFO - codeparrot_training - Step 23664: {'lr': 0.0004740285229889423, 'samples': 12116480, 'steps': 23664, 'loss/train': 1.7240160703659058}
-03/04/2022 17:15:28 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/04/2022 17:15:32 - INFO - codeparrot_training - Step 23665: {'lr': 0.0004740261676792155, 'samples': 12116992, 'steps': 23665, 'loss/train': 2.259674310684204}
-03/04/2022 17:15:35 - INFO - codeparrot_training - Step 23666: {'lr': 0.00047402381226854606, 'samples': 12117504, 'steps': 23666, 'loss/train': 1.846083164215088}
-03/04/2022 17:15:36 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/04/2022 17:15:40 - INFO - codeparrot_training - Step 23667: {'lr': 0.0004740214567569349, 'samples': 12118016, 'steps': 23667, 'loss/train': 2.290923595428467}
-03/04/2022 17:15:44 - INFO - codeparrot_training - Step 23668: {'lr': 0.00047401910114438313, 'samples': 12118528, 'steps': 23668, 'loss/train': 2.701794147491455}
-03/04/2022 17:15:45 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/04/2022 17:15:49 - INFO - codeparrot_training - Step 23669: {'lr': 0.0004740167454308918, 'samples': 12119040, 'steps': 23669, 'loss/train': 1.6841286420822144}
-03/04/2022 17:15:52 - INFO - codeparrot_training - Step 23670: {'lr': 0.00047401438961646206, 'samples': 12119552, 'steps': 23670, 'loss/train': 2.0812065601348877}
-03/04/2022 17:15:53 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/04/2022 17:15:57 - INFO - codeparrot_training - Step 23671: {'lr': 0.0004740120337010948, 'samples': 12120064, 'steps': 23671, 'loss/train': 2.4943108558654785}
-03/04/2022 17:16:01 - INFO - codeparrot_training - Step 23672: {'lr': 0.0004740096776847912, 'samples': 12120576, 'steps': 23672, 'loss/train': 1.3477282524108887}
-03/04/2022 17:16:02 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/04/2022 17:16:06 - INFO - codeparrot_training - Step 23673: {'lr': 0.0004740073215675523, 'samples': 12121088, 'steps': 23673, 'loss/train': 2.1261520385742188}
-03/04/2022 17:16:09 - INFO - codeparrot_training - Step 23674: {'lr': 0.00047400496534937914, 'samples': 12121600, 'steps': 23674, 'loss/train': 1.7481192350387573}
-03/04/2022 17:16:10 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/04/2022 17:16:14 - INFO - codeparrot_training - Step 23675: {'lr': 0.00047400260903027283, 'samples': 12122112, 'steps': 23675, 'loss/train': 1.3841853141784668}
-03/04/2022 17:16:18 - INFO - codeparrot_training - Step 23676: {'lr': 0.0004740002526102344, 'samples': 12122624, 'steps': 23676, 'loss/train': 1.9130616188049316}
-03/04/2022 17:16:19 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/04/2022 17:16:23 - INFO - codeparrot_training - Step 23677: {'lr': 0.0004739978960892649, 'samples': 12123136, 'steps': 23677, 'loss/train': 1.8244049549102783}
-03/04/2022 17:16:26 - INFO - codeparrot_training - Step 23678: {'lr': 0.0004739955394673654, 'samples': 12123648, 'steps': 23678, 'loss/train': 2.190603256225586}
-03/04/2022 17:16:27 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/04/2022 17:16:31 - INFO - codeparrot_training - Step 23679: {'lr': 0.000473993182744537, 'samples': 12124160, 'steps': 23679, 'loss/train': 1.7991740703582764}
-03/04/2022 17:16:35 - INFO - codeparrot_training - Step 23680: {'lr': 0.0004739908259207807, 'samples': 12124672, 'steps': 23680, 'loss/train': 2.238150119781494}
-03/04/2022 17:16:36 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 17:16:40 - INFO - codeparrot_training - Step 23681: {'lr': 0.00047398846899609755, 'samples': 12125184, 'steps': 23681, 'loss/train': 2.4663662910461426}
-03/04/2022 17:16:43 - INFO - codeparrot_training - Step 23682: {'lr': 0.0004739861119704887, 'samples': 12125696, 'steps': 23682, 'loss/train': 1.0735864639282227}
-03/04/2022 17:16:45 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/04/2022 17:16:48 - INFO - codeparrot_training - Step 23683: {'lr': 0.00047398375484395517, 'samples': 12126208, 'steps': 23683, 'loss/train': 1.6151368618011475}
-03/04/2022 17:16:52 - INFO - codeparrot_training - Step 23684: {'lr': 0.00047398139761649794, 'samples': 12126720, 'steps': 23684, 'loss/train': 1.4145499467849731}
-03/04/2022 17:16:53 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/04/2022 17:16:57 - INFO - codeparrot_training - Step 23685: {'lr': 0.00047397904028811824, 'samples': 12127232, 'steps': 23685, 'loss/train': 2.20929217338562}
-03/04/2022 17:17:00 - INFO - codeparrot_training - Step 23686: {'lr': 0.000473976682858817, 'samples': 12127744, 'steps': 23686, 'loss/train': 2.404446601867676}
-03/04/2022 17:17:04 - INFO - codeparrot_training - Step 23687: {'lr': 0.00047397432532859533, 'samples': 12128256, 'steps': 23687, 'loss/train': 1.5859482288360596}
-03/04/2022 17:17:04 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/04/2022 17:17:09 - INFO - codeparrot_training - Step 23688: {'lr': 0.00047397196769745435, 'samples': 12128768, 'steps': 23688, 'loss/train': 2.225498676300049}
-03/04/2022 17:17:12 - INFO - codeparrot_training - Step 23689: {'lr': 0.00047396960996539495, 'samples': 12129280, 'steps': 23689, 'loss/train': 1.8858722448349}
-03/04/2022 17:17:12 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 17:17:17 - INFO - codeparrot_training - Step 23690: {'lr': 0.00047396725213241835, 'samples': 12129792, 'steps': 23690, 'loss/train': 0.3528008460998535}
-03/04/2022 17:17:21 - INFO - codeparrot_training - Step 23691: {'lr': 0.0004739648941985256, 'samples': 12130304, 'steps': 23691, 'loss/train': 2.063058614730835}
-03/04/2022 17:17:21 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 17:17:26 - INFO - codeparrot_training - Step 23692: {'lr': 0.00047396253616371767, 'samples': 12130816, 'steps': 23692, 'loss/train': 2.606527090072632}
-03/04/2022 17:17:29 - INFO - codeparrot_training - Step 23693: {'lr': 0.00047396017802799566, 'samples': 12131328, 'steps': 23693, 'loss/train': 2.0827784538269043}
-03/04/2022 17:17:29 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/04/2022 17:17:34 - INFO - codeparrot_training - Step 23694: {'lr': 0.0004739578197913607, 'samples': 12131840, 'steps': 23694, 'loss/train': 1.569892406463623}
-03/04/2022 17:17:37 - INFO - codeparrot_training - Step 23695: {'lr': 0.00047395546145381377, 'samples': 12132352, 'steps': 23695, 'loss/train': 1.2835166454315186}
-03/04/2022 17:17:37 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 17:17:43 - INFO - codeparrot_training - Step 23696: {'lr': 0.000473953103015356, 'samples': 12132864, 'steps': 23696, 'loss/train': 2.1140060424804688}
-03/04/2022 17:17:46 - INFO - codeparrot_training - Step 23697: {'lr': 0.0004739507444759884, 'samples': 12133376, 'steps': 23697, 'loss/train': 2.259042263031006}
-03/04/2022 17:17:46 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 17:17:51 - INFO - codeparrot_training - Step 23698: {'lr': 0.0004739483858357121, 'samples': 12133888, 'steps': 23698, 'loss/train': 1.558167815208435}
-03/04/2022 17:17:54 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/04/2022 17:17:56 - INFO - codeparrot_training - Step 23699: {'lr': 0.00047394602709452806, 'samples': 12134400, 'steps': 23699, 'loss/train': 2.066560745239258}
-03/04/2022 17:17:59 - INFO - codeparrot_training - Step 23700: {'lr': 0.0004739436682524373, 'samples': 12134912, 'steps': 23700, 'loss/train': 1.818149209022522}
-03/04/2022 17:18:02 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 17:18:05 - INFO - codeparrot_training - Step 23701: {'lr': 0.00047394130930944115, 'samples': 12135424, 'steps': 23701, 'loss/train': 1.6560214757919312}
-03/04/2022 17:18:08 - INFO - codeparrot_training - Step 23702: {'lr': 0.0004739389502655404, 'samples': 12135936, 'steps': 23702, 'loss/train': 1.8994088172912598}
-03/04/2022 17:18:11 - INFO - codeparrot_training - Step 23703: {'lr': 0.0004739365911207363, 'samples': 12136448, 'steps': 23703, 'loss/train': 2.0355587005615234}
-03/04/2022 17:18:11 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/04/2022 17:18:16 - INFO - codeparrot_training - Step 23704: {'lr': 0.0004739342318750297, 'samples': 12136960, 'steps': 23704, 'loss/train': 1.6351745128631592}
-03/04/2022 17:18:19 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 17:18:22 - INFO - codeparrot_training - Step 23705: {'lr': 0.00047393187252842183, 'samples': 12137472, 'steps': 23705, 'loss/train': 1.9731441736221313}
-03/04/2022 17:18:25 - INFO - codeparrot_training - Step 23706: {'lr': 0.0004739295130809138, 'samples': 12137984, 'steps': 23706, 'loss/train': 2.0211598873138428}
-03/04/2022 17:18:28 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/04/2022 17:18:30 - INFO - codeparrot_training - Step 23707: {'lr': 0.0004739271535325065, 'samples': 12138496, 'steps': 23707, 'loss/train': 2.0636277198791504}
-03/04/2022 17:18:33 - INFO - codeparrot_training - Step 23708: {'lr': 0.00047392479388320106, 'samples': 12139008, 'steps': 23708, 'loss/train': 2.6288678646087646}
-03/04/2022 17:18:36 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/04/2022 17:18:39 - INFO - codeparrot_training - Step 23709: {'lr': 0.0004739224341329987, 'samples': 12139520, 'steps': 23709, 'loss/train': 1.1857538223266602}
-03/04/2022 17:18:42 - INFO - codeparrot_training - Step 23710: {'lr': 0.0004739200742819002, 'samples': 12140032, 'steps': 23710, 'loss/train': 1.7754943370819092}
-03/04/2022 17:18:45 - INFO - codeparrot_training - Step 23711: {'lr': 0.0004739177143299068, 'samples': 12140544, 'steps': 23711, 'loss/train': 2.097775936126709}
-03/04/2022 17:18:45 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/04/2022 17:18:50 - INFO - codeparrot_training - Step 23712: {'lr': 0.00047391535427701966, 'samples': 12141056, 'steps': 23712, 'loss/train': 2.475356340408325}
-03/04/2022 17:18:53 - INFO - codeparrot_training - Step 23713: {'lr': 0.0004739129941232396, 'samples': 12141568, 'steps': 23713, 'loss/train': 1.3106184005737305}
-03/04/2022 17:18:54 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 17:18:59 - INFO - codeparrot_training - Step 23714: {'lr': 0.0004739106338685678, 'samples': 12142080, 'steps': 23714, 'loss/train': 1.8121132850646973}
-03/04/2022 17:19:02 - INFO - codeparrot_training - Step 23715: {'lr': 0.00047390827351300537, 'samples': 12142592, 'steps': 23715, 'loss/train': 1.4897972345352173}
-03/04/2022 17:19:02 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/04/2022 17:19:07 - INFO - codeparrot_training - Step 23716: {'lr': 0.00047390591305655327, 'samples': 12143104, 'steps': 23716, 'loss/train': 1.3802684545516968}
-03/04/2022 17:19:10 - INFO - codeparrot_training - Step 23717: {'lr': 0.0004739035524992127, 'samples': 12143616, 'steps': 23717, 'loss/train': 2.931997299194336}
-03/04/2022 17:19:11 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/04/2022 17:19:15 - INFO - codeparrot_training - Step 23718: {'lr': 0.00047390119184098455, 'samples': 12144128, 'steps': 23718, 'loss/train': 2.1765103340148926}
-03/04/2022 17:19:19 - INFO - codeparrot_training - Step 23719: {'lr': 0.00047389883108187004, 'samples': 12144640, 'steps': 23719, 'loss/train': 2.733281373977661}
-03/04/2022 17:19:19 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 17:19:24 - INFO - codeparrot_training - Step 23720: {'lr': 0.00047389647022187014, 'samples': 12145152, 'steps': 23720, 'loss/train': 1.1348062753677368}
-03/04/2022 17:19:27 - INFO - codeparrot_training - Step 23721: {'lr': 0.000473894109260986, 'samples': 12145664, 'steps': 23721, 'loss/train': 1.650702953338623}
-03/04/2022 17:19:28 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/04/2022 17:19:32 - INFO - codeparrot_training - Step 23722: {'lr': 0.00047389174819921856, 'samples': 12146176, 'steps': 23722, 'loss/train': 2.044210195541382}
-03/04/2022 17:19:35 - INFO - codeparrot_training - Step 23723: {'lr': 0.000473889387036569, 'samples': 12146688, 'steps': 23723, 'loss/train': 2.248384714126587}
-03/04/2022 17:19:36 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 17:19:41 - INFO - codeparrot_training - Step 23724: {'lr': 0.0004738870257730383, 'samples': 12147200, 'steps': 23724, 'loss/train': 0.9605239033699036}
-03/04/2022 17:19:44 - INFO - codeparrot_training - Step 23725: {'lr': 0.00047388466440862755, 'samples': 12147712, 'steps': 23725, 'loss/train': 1.6707936525344849}
-03/04/2022 17:19:45 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/04/2022 17:19:49 - INFO - codeparrot_training - Step 23726: {'lr': 0.0004738823029433379, 'samples': 12148224, 'steps': 23726, 'loss/train': 2.073342800140381}
-03/04/2022 17:19:52 - INFO - codeparrot_training - Step 23727: {'lr': 0.0004738799413771703, 'samples': 12148736, 'steps': 23727, 'loss/train': 1.8634250164031982}
-03/04/2022 17:19:53 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/04/2022 17:19:58 - INFO - codeparrot_training - Step 23728: {'lr': 0.0004738775797101258, 'samples': 12149248, 'steps': 23728, 'loss/train': 1.5589054822921753}
-03/04/2022 17:20:01 - INFO - codeparrot_training - Step 23729: {'lr': 0.0004738752179422056, 'samples': 12149760, 'steps': 23729, 'loss/train': 2.0648515224456787}
-03/04/2022 17:20:01 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 17:20:06 - INFO - codeparrot_training - Step 23730: {'lr': 0.00047387285607341064, 'samples': 12150272, 'steps': 23730, 'loss/train': 1.9939045906066895}
-03/04/2022 17:20:09 - INFO - codeparrot_training - Step 23731: {'lr': 0.00047387049410374207, 'samples': 12150784, 'steps': 23731, 'loss/train': 2.070875883102417}
-03/04/2022 17:20:10 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 17:20:14 - INFO - codeparrot_training - Step 23732: {'lr': 0.00047386813203320084, 'samples': 12151296, 'steps': 23732, 'loss/train': 1.861603856086731}
-03/04/2022 17:20:18 - INFO - codeparrot_training - Step 23733: {'lr': 0.0004738657698617881, 'samples': 12151808, 'steps': 23733, 'loss/train': 1.8075370788574219}
-03/04/2022 17:20:18 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/04/2022 17:20:23 - INFO - codeparrot_training - Step 23734: {'lr': 0.00047386340758950494, 'samples': 12152320, 'steps': 23734, 'loss/train': 2.202697992324829}
-03/04/2022 17:20:26 - INFO - codeparrot_training - Step 23735: {'lr': 0.0004738610452163523, 'samples': 12152832, 'steps': 23735, 'loss/train': 2.1121022701263428}
-03/04/2022 17:20:26 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/04/2022 17:20:31 - INFO - codeparrot_training - Step 23736: {'lr': 0.00047385868274233144, 'samples': 12153344, 'steps': 23736, 'loss/train': 2.2542190551757812}
-03/04/2022 17:20:34 - INFO - codeparrot_training - Step 23737: {'lr': 0.0004738563201674432, 'samples': 12153856, 'steps': 23737, 'loss/train': 2.7913613319396973}
-03/04/2022 17:20:35 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 17:20:40 - INFO - codeparrot_training - Step 23738: {'lr': 0.00047385395749168885, 'samples': 12154368, 'steps': 23738, 'loss/train': 2.452979326248169}
-03/04/2022 17:20:43 - INFO - codeparrot_training - Step 23739: {'lr': 0.00047385159471506936, 'samples': 12154880, 'steps': 23739, 'loss/train': 1.2685240507125854}
-03/04/2022 17:20:44 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 17:20:48 - INFO - codeparrot_training - Step 23740: {'lr': 0.00047384923183758573, 'samples': 12155392, 'steps': 23740, 'loss/train': 1.3219494819641113}
-03/04/2022 17:20:52 - INFO - codeparrot_training - Step 23741: {'lr': 0.0004738468688592391, 'samples': 12155904, 'steps': 23741, 'loss/train': 3.1401445865631104}
-03/04/2022 17:20:52 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/04/2022 17:20:57 - INFO - codeparrot_training - Step 23742: {'lr': 0.00047384450578003055, 'samples': 12156416, 'steps': 23742, 'loss/train': 1.402923583984375}
-03/04/2022 17:21:00 - INFO - codeparrot_training - Step 23743: {'lr': 0.00047384214259996117, 'samples': 12156928, 'steps': 23743, 'loss/train': 0.37630972266197205}
-03/04/2022 17:21:00 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/04/2022 17:21:05 - INFO - codeparrot_training - Step 23744: {'lr': 0.0004738397793190319, 'samples': 12157440, 'steps': 23744, 'loss/train': 1.6994844675064087}
-03/04/2022 17:21:08 - INFO - codeparrot_training - Step 23745: {'lr': 0.00047383741593724386, 'samples': 12157952, 'steps': 23745, 'loss/train': 1.9833449125289917}
-03/04/2022 17:21:09 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 17:21:14 - INFO - codeparrot_training - Step 23746: {'lr': 0.0004738350524545982, 'samples': 12158464, 'steps': 23746, 'loss/train': 1.8134338855743408}
-03/04/2022 17:21:17 - INFO - codeparrot_training - Step 23747: {'lr': 0.0004738326888710959, 'samples': 12158976, 'steps': 23747, 'loss/train': 2.431206464767456}
-03/04/2022 17:21:17 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 17:21:22 - INFO - codeparrot_training - Step 23748: {'lr': 0.000473830325186738, 'samples': 12159488, 'steps': 23748, 'loss/train': 1.065942645072937}
-03/04/2022 17:21:25 - INFO - codeparrot_training - Step 23749: {'lr': 0.0004738279614015257, 'samples': 12160000, 'steps': 23749, 'loss/train': 1.8762257099151611}
-03/04/2022 17:21:26 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/04/2022 17:21:30 - INFO - codeparrot_training - Step 23750: {'lr': 0.0004738255975154599, 'samples': 12160512, 'steps': 23750, 'loss/train': 1.9966421127319336}
-03/04/2022 17:21:34 - INFO - codeparrot_training - Step 23751: {'lr': 0.0004738232335285417, 'samples': 12161024, 'steps': 23751, 'loss/train': 1.7481709718704224}
-03/04/2022 17:21:34 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 17:21:39 - INFO - codeparrot_training - Step 23752: {'lr': 0.0004738208694407723, 'samples': 12161536, 'steps': 23752, 'loss/train': 1.4975959062576294}
-03/04/2022 17:21:42 - INFO - codeparrot_training - Step 23753: {'lr': 0.00047381850525215265, 'samples': 12162048, 'steps': 23753, 'loss/train': 2.1139724254608154}
-03/04/2022 17:21:43 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/04/2022 17:21:47 - INFO - codeparrot_training - Step 23754: {'lr': 0.0004738161409626838, 'samples': 12162560, 'steps': 23754, 'loss/train': 1.6707584857940674}
-03/04/2022 17:21:50 - INFO - codeparrot_training - Step 23755: {'lr': 0.0004738137765723669, 'samples': 12163072, 'steps': 23755, 'loss/train': 1.4585719108581543}
-03/04/2022 17:21:51 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 17:21:56 - INFO - codeparrot_training - Step 23756: {'lr': 0.0004738114120812029, 'samples': 12163584, 'steps': 23756, 'loss/train': 1.399327278137207}
-03/04/2022 17:21:59 - INFO - codeparrot_training - Step 23757: {'lr': 0.000473809047489193, 'samples': 12164096, 'steps': 23757, 'loss/train': 1.1605526208877563}
-03/04/2022 17:22:00 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 17:22:04 - INFO - codeparrot_training - Step 23758: {'lr': 0.00047380668279633814, 'samples': 12164608, 'steps': 23758, 'loss/train': 1.6233943700790405}
-03/04/2022 17:22:07 - INFO - codeparrot_training - Step 23759: {'lr': 0.00047380431800263945, 'samples': 12165120, 'steps': 23759, 'loss/train': 0.8393142819404602}
-03/04/2022 17:22:08 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/04/2022 17:22:13 - INFO - codeparrot_training - Step 23760: {'lr': 0.000473801953108098, 'samples': 12165632, 'steps': 23760, 'loss/train': 1.7899975776672363}
-03/04/2022 17:22:16 - INFO - codeparrot_training - Step 23761: {'lr': 0.0004737995881127149, 'samples': 12166144, 'steps': 23761, 'loss/train': 1.5440043210983276}
-03/04/2022 17:22:17 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 17:22:21 - INFO - codeparrot_training - Step 23762: {'lr': 0.0004737972230164911, 'samples': 12166656, 'steps': 23762, 'loss/train': 2.426323413848877}
-03/04/2022 17:22:24 - INFO - codeparrot_training - Step 23763: {'lr': 0.0004737948578194278, 'samples': 12167168, 'steps': 23763, 'loss/train': 0.5034106969833374}
-03/04/2022 17:22:25 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 17:22:30 - INFO - codeparrot_training - Step 23764: {'lr': 0.00047379249252152585, 'samples': 12167680, 'steps': 23764, 'loss/train': 2.5461409091949463}
-03/04/2022 17:22:33 - INFO - codeparrot_training - Step 23765: {'lr': 0.00047379012712278656, 'samples': 12168192, 'steps': 23765, 'loss/train': 1.6752080917358398}
-03/04/2022 17:22:33 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 17:22:38 - INFO - codeparrot_training - Step 23766: {'lr': 0.0004737877616232108, 'samples': 12168704, 'steps': 23766, 'loss/train': 1.714516520500183}
-03/04/2022 17:22:41 - INFO - codeparrot_training - Step 23767: {'lr': 0.0004737853960227998, 'samples': 12169216, 'steps': 23767, 'loss/train': 1.1917070150375366}
-03/04/2022 17:22:42 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/04/2022 17:22:46 - INFO - codeparrot_training - Step 23768: {'lr': 0.00047378303032155454, 'samples': 12169728, 'steps': 23768, 'loss/train': 2.0745646953582764}
-03/04/2022 17:22:50 - INFO - codeparrot_training - Step 23769: {'lr': 0.0004737806645194761, 'samples': 12170240, 'steps': 23769, 'loss/train': 2.1327240467071533}
-03/04/2022 17:22:51 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 17:22:55 - INFO - codeparrot_training - Step 23770: {'lr': 0.00047377829861656556, 'samples': 12170752, 'steps': 23770, 'loss/train': 1.5674903392791748}
-03/04/2022 17:22:58 - INFO - codeparrot_training - Step 23771: {'lr': 0.000473775932612824, 'samples': 12171264, 'steps': 23771, 'loss/train': 0.6945176720619202}
-03/04/2022 17:22:59 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 17:23:03 - INFO - codeparrot_training - Step 23772: {'lr': 0.00047377356650825245, 'samples': 12171776, 'steps': 23772, 'loss/train': 1.8209755420684814}
-03/04/2022 17:23:06 - INFO - codeparrot_training - Step 23773: {'lr': 0.00047377120030285194, 'samples': 12172288, 'steps': 23773, 'loss/train': 2.033637285232544}
-03/04/2022 17:23:07 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 17:23:12 - INFO - codeparrot_training - Step 23774: {'lr': 0.0004737688339966235, 'samples': 12172800, 'steps': 23774, 'loss/train': 1.318041443824768}
-03/04/2022 17:23:15 - INFO - codeparrot_training - Step 23775: {'lr': 0.00047376646758956844, 'samples': 12173312, 'steps': 23775, 'loss/train': 1.529974341392517}
-03/04/2022 17:23:16 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/04/2022 17:23:20 - INFO - codeparrot_training - Step 23776: {'lr': 0.00047376410108168756, 'samples': 12173824, 'steps': 23776, 'loss/train': 1.8632819652557373}
-03/04/2022 17:23:23 - INFO - codeparrot_training - Step 23777: {'lr': 0.0004737617344729821, 'samples': 12174336, 'steps': 23777, 'loss/train': 1.1773691177368164}
-03/04/2022 17:23:24 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/04/2022 17:23:29 - INFO - codeparrot_training - Step 23778: {'lr': 0.00047375936776345297, 'samples': 12174848, 'steps': 23778, 'loss/train': 2.519303798675537}
-03/04/2022 17:23:32 - INFO - codeparrot_training - Step 23779: {'lr': 0.00047375700095310136, 'samples': 12175360, 'steps': 23779, 'loss/train': 2.1506848335266113}
-03/04/2022 17:23:33 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/04/2022 17:23:37 - INFO - codeparrot_training - Step 23780: {'lr': 0.0004737546340419283, 'samples': 12175872, 'steps': 23780, 'loss/train': 1.461902379989624}
-03/04/2022 17:23:40 - INFO - codeparrot_training - Step 23781: {'lr': 0.0004737522670299349, 'samples': 12176384, 'steps': 23781, 'loss/train': 1.752360224723816}
-03/04/2022 17:23:41 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/04/2022 17:23:46 - INFO - codeparrot_training - Step 23782: {'lr': 0.00047374989991712214, 'samples': 12176896, 'steps': 23782, 'loss/train': 2.0341153144836426}
-03/04/2022 17:23:49 - INFO - codeparrot_training - Step 23783: {'lr': 0.00047374753270349113, 'samples': 12177408, 'steps': 23783, 'loss/train': 1.2026571035385132}
-03/04/2022 17:23:50 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/04/2022 17:23:54 - INFO - codeparrot_training - Step 23784: {'lr': 0.00047374516538904287, 'samples': 12177920, 'steps': 23784, 'loss/train': 2.0054843425750732}
-03/04/2022 17:23:57 - INFO - codeparrot_training - Step 23785: {'lr': 0.0004737427979737786, 'samples': 12178432, 'steps': 23785, 'loss/train': 1.8798655271530151}
-03/04/2022 17:23:58 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/04/2022 17:24:02 - INFO - codeparrot_training - Step 23786: {'lr': 0.0004737404304576992, 'samples': 12178944, 'steps': 23786, 'loss/train': 1.8634406328201294}
-03/04/2022 17:24:06 - INFO - codeparrot_training - Step 23787: {'lr': 0.0004737380628408059, 'samples': 12179456, 'steps': 23787, 'loss/train': 2.1125690937042236}
-03/04/2022 17:24:06 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/04/2022 17:24:11 - INFO - codeparrot_training - Step 23788: {'lr': 0.00047373569512309963, 'samples': 12179968, 'steps': 23788, 'loss/train': 1.8610633611679077}
-03/04/2022 17:24:14 - INFO - codeparrot_training - Step 23789: {'lr': 0.0004737333273045815, 'samples': 12180480, 'steps': 23789, 'loss/train': 1.2013576030731201}
-03/04/2022 17:24:15 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/04/2022 17:24:19 - INFO - codeparrot_training - Step 23790: {'lr': 0.00047373095938525256, 'samples': 12180992, 'steps': 23790, 'loss/train': 2.0161452293395996}
-03/04/2022 17:24:22 - INFO - codeparrot_training - Step 23791: {'lr': 0.0004737285913651139, 'samples': 12181504, 'steps': 23791, 'loss/train': 1.1773390769958496}
-03/04/2022 17:24:23 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/04/2022 17:24:28 - INFO - codeparrot_training - Step 23792: {'lr': 0.0004737262232441667, 'samples': 12182016, 'steps': 23792, 'loss/train': 1.6415743827819824}
-03/04/2022 17:24:31 - INFO - codeparrot_training - Step 23793: {'lr': 0.00047372385502241176, 'samples': 12182528, 'steps': 23793, 'loss/train': 1.8930208683013916}
-03/04/2022 17:24:31 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 17:24:36 - INFO - codeparrot_training - Step 23794: {'lr': 0.0004737214866998504, 'samples': 12183040, 'steps': 23794, 'loss/train': 1.823832392692566}
-03/04/2022 17:24:39 - INFO - codeparrot_training - Step 23795: {'lr': 0.0004737191182764836, 'samples': 12183552, 'steps': 23795, 'loss/train': 2.3182008266448975}
-03/04/2022 17:24:40 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/04/2022 17:24:44 - INFO - codeparrot_training - Step 23796: {'lr': 0.0004737167497523124, 'samples': 12184064, 'steps': 23796, 'loss/train': 1.6382757425308228}
-03/04/2022 17:24:48 - INFO - codeparrot_training - Step 23797: {'lr': 0.0004737143811273379, 'samples': 12184576, 'steps': 23797, 'loss/train': 1.9215400218963623}
-03/04/2022 17:24:48 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 17:24:53 - INFO - codeparrot_training - Step 23798: {'lr': 0.0004737120124015611, 'samples': 12185088, 'steps': 23798, 'loss/train': 1.6340798139572144}
-03/04/2022 17:24:56 - INFO - codeparrot_training - Step 23799: {'lr': 0.00047370964357498313, 'samples': 12185600, 'steps': 23799, 'loss/train': 2.1025044918060303}
-03/04/2022 17:24:56 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/04/2022 17:25:01 - INFO - codeparrot_training - Step 23800: {'lr': 0.0004737072746476051, 'samples': 12186112, 'steps': 23800, 'loss/train': 1.9751176834106445}
-03/04/2022 17:25:04 - INFO - codeparrot_training - Step 23801: {'lr': 0.00047370490561942795, 'samples': 12186624, 'steps': 23801, 'loss/train': 2.1546971797943115}
-03/04/2022 17:25:05 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/04/2022 17:25:10 - INFO - codeparrot_training - Step 23802: {'lr': 0.00047370253649045286, 'samples': 12187136, 'steps': 23802, 'loss/train': 0.9956389665603638}
-03/04/2022 17:25:13 - INFO - codeparrot_training - Step 23803: {'lr': 0.00047370016726068086, 'samples': 12187648, 'steps': 23803, 'loss/train': 1.6071703433990479}
-03/04/2022 17:25:13 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 17:25:18 - INFO - codeparrot_training - Step 23804: {'lr': 0.000473697797930113, 'samples': 12188160, 'steps': 23804, 'loss/train': 1.7049932479858398}
-03/04/2022 17:25:21 - INFO - codeparrot_training - Step 23805: {'lr': 0.00047369542849875037, 'samples': 12188672, 'steps': 23805, 'loss/train': 2.2715654373168945}
-03/04/2022 17:25:21 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 17:25:26 - INFO - codeparrot_training - Step 23806: {'lr': 0.0004736930589665941, 'samples': 12189184, 'steps': 23806, 'loss/train': 1.4308083057403564}
-03/04/2022 17:25:30 - INFO - codeparrot_training - Step 23807: {'lr': 0.0004736906893336451, 'samples': 12189696, 'steps': 23807, 'loss/train': 2.0052084922790527}
-03/04/2022 17:25:30 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/04/2022 17:25:35 - INFO - codeparrot_training - Step 23808: {'lr': 0.00047368831959990453, 'samples': 12190208, 'steps': 23808, 'loss/train': 1.7973670959472656}
-03/04/2022 17:25:38 - INFO - codeparrot_training - Step 23809: {'lr': 0.0004736859497653735, 'samples': 12190720, 'steps': 23809, 'loss/train': 0.4463362991809845}
-03/04/2022 17:25:39 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/04/2022 17:25:44 - INFO - codeparrot_training - Step 23810: {'lr': 0.0004736835798300531, 'samples': 12191232, 'steps': 23810, 'loss/train': 1.3963499069213867}
-03/04/2022 17:25:47 - INFO - codeparrot_training - Step 23811: {'lr': 0.00047368120979394415, 'samples': 12191744, 'steps': 23811, 'loss/train': 1.2847224473953247}
-03/04/2022 17:25:48 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 17:25:52 - INFO - codeparrot_training - Step 23812: {'lr': 0.000473678839657048, 'samples': 12192256, 'steps': 23812, 'loss/train': 1.5554486513137817}
-03/04/2022 17:25:56 - INFO - codeparrot_training - Step 23813: {'lr': 0.0004736764694193656, 'samples': 12192768, 'steps': 23813, 'loss/train': 2.592989921569824}
-03/04/2022 17:25:57 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/04/2022 17:26:01 - INFO - codeparrot_training - Step 23814: {'lr': 0.0004736740990808981, 'samples': 12193280, 'steps': 23814, 'loss/train': 1.992108702659607}
-03/04/2022 17:26:04 - INFO - codeparrot_training - Step 23815: {'lr': 0.0004736717286416464, 'samples': 12193792, 'steps': 23815, 'loss/train': 0.7423959374427795}
-03/04/2022 17:26:06 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/04/2022 17:26:09 - INFO - codeparrot_training - Step 23816: {'lr': 0.0004736693581016117, 'samples': 12194304, 'steps': 23816, 'loss/train': 0.14589422941207886}
-03/04/2022 17:26:13 - INFO - codeparrot_training - Step 23817: {'lr': 0.00047366698746079507, 'samples': 12194816, 'steps': 23817, 'loss/train': 1.6043869256973267}
-03/04/2022 17:26:14 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/04/2022 17:26:18 - INFO - codeparrot_training - Step 23818: {'lr': 0.0004736646167191975, 'samples': 12195328, 'steps': 23818, 'loss/train': 1.9798797369003296}
-03/04/2022 17:26:21 - INFO - codeparrot_training - Step 23819: {'lr': 0.00047366224587682017, 'samples': 12195840, 'steps': 23819, 'loss/train': 2.308527708053589}
-03/04/2022 17:26:23 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/04/2022 17:26:26 - INFO - codeparrot_training - Step 23820: {'lr': 0.000473659874933664, 'samples': 12196352, 'steps': 23820, 'loss/train': 1.7681331634521484}
-03/04/2022 17:26:30 - INFO - codeparrot_training - Step 23821: {'lr': 0.0004736575038897303, 'samples': 12196864, 'steps': 23821, 'loss/train': 1.3930654525756836}
-03/04/2022 17:26:31 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/04/2022 17:26:35 - INFO - codeparrot_training - Step 23822: {'lr': 0.0004736551327450198, 'samples': 12197376, 'steps': 23822, 'loss/train': 1.3321549892425537}
-03/04/2022 17:26:38 - INFO - codeparrot_training - Step 23823: {'lr': 0.00047365276149953387, 'samples': 12197888, 'steps': 23823, 'loss/train': 1.489685297012329}
-03/04/2022 17:26:39 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/04/2022 17:26:43 - INFO - codeparrot_training - Step 23824: {'lr': 0.0004736503901532734, 'samples': 12198400, 'steps': 23824, 'loss/train': 1.849236249923706}
-03/04/2022 17:26:46 - INFO - codeparrot_training - Step 23825: {'lr': 0.00047364801870623954, 'samples': 12198912, 'steps': 23825, 'loss/train': 1.9351019859313965}
-03/04/2022 17:26:48 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/04/2022 17:26:52 - INFO - codeparrot_training - Step 23826: {'lr': 0.00047364564715843326, 'samples': 12199424, 'steps': 23826, 'loss/train': 2.2503044605255127}
-03/04/2022 17:26:55 - INFO - codeparrot_training - Step 23827: {'lr': 0.00047364327550985575, 'samples': 12199936, 'steps': 23827, 'loss/train': 1.9199212789535522}
-03/04/2022 17:26:56 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/04/2022 17:27:01 - INFO - codeparrot_training - Step 23828: {'lr': 0.00047364090376050805, 'samples': 12200448, 'steps': 23828, 'loss/train': 2.0211966037750244}
-03/04/2022 17:27:04 - INFO - codeparrot_training - Step 23829: {'lr': 0.0004736385319103912, 'samples': 12200960, 'steps': 23829, 'loss/train': 1.7986865043640137}
-03/04/2022 17:27:06 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 17:27:09 - INFO - codeparrot_training - Step 23830: {'lr': 0.00047363615995950624, 'samples': 12201472, 'steps': 23830, 'loss/train': 1.3328986167907715}
-03/04/2022 17:27:12 - INFO - codeparrot_training - Step 23831: {'lr': 0.0004736337879078544, 'samples': 12201984, 'steps': 23831, 'loss/train': 1.6971014738082886}
-03/04/2022 17:27:14 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 17:27:18 - INFO - codeparrot_training - Step 23832: {'lr': 0.0004736314157554365, 'samples': 12202496, 'steps': 23832, 'loss/train': 1.5707414150238037}
-03/04/2022 17:27:21 - INFO - codeparrot_training - Step 23833: {'lr': 0.00047362904350225376, 'samples': 12203008, 'steps': 23833, 'loss/train': 0.6342618465423584}
-03/04/2022 17:27:23 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 17:27:26 - INFO - codeparrot_training - Step 23834: {'lr': 0.0004736266711483073, 'samples': 12203520, 'steps': 23834, 'loss/train': 1.6019678115844727}
-03/04/2022 17:27:29 - INFO - codeparrot_training - Step 23835: {'lr': 0.00047362429869359803, 'samples': 12204032, 'steps': 23835, 'loss/train': 2.322605609893799}
-03/04/2022 17:27:31 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/04/2022 17:27:34 - INFO - codeparrot_training - Step 23836: {'lr': 0.0004736219261381271, 'samples': 12204544, 'steps': 23836, 'loss/train': 0.500464141368866}
-03/04/2022 17:27:38 - INFO - codeparrot_training - Step 23837: {'lr': 0.0004736195534818956, 'samples': 12205056, 'steps': 23837, 'loss/train': 1.456661343574524}
-03/04/2022 17:27:40 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/04/2022 17:27:43 - INFO - codeparrot_training - Step 23838: {'lr': 0.00047361718072490457, 'samples': 12205568, 'steps': 23838, 'loss/train': 1.9324203729629517}
-03/04/2022 17:27:46 - INFO - codeparrot_training - Step 23839: {'lr': 0.00047361480786715514, 'samples': 12206080, 'steps': 23839, 'loss/train': 1.3988748788833618}
-03/04/2022 17:27:48 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/04/2022 17:27:51 - INFO - codeparrot_training - Step 23840: {'lr': 0.00047361243490864826, 'samples': 12206592, 'steps': 23840, 'loss/train': 1.4323186874389648}
-03/04/2022 17:27:54 - INFO - codeparrot_training - Step 23841: {'lr': 0.00047361006184938517, 'samples': 12207104, 'steps': 23841, 'loss/train': 1.8228693008422852}
-03/04/2022 17:27:56 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/04/2022 17:28:00 - INFO - codeparrot_training - Step 23842: {'lr': 0.00047360768868936673, 'samples': 12207616, 'steps': 23842, 'loss/train': 1.984322190284729}
-03/04/2022 17:28:03 - INFO - codeparrot_training - Step 23843: {'lr': 0.00047360531542859415, 'samples': 12208128, 'steps': 23843, 'loss/train': 1.494211196899414}
-03/04/2022 17:28:05 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/04/2022 17:28:08 - INFO - codeparrot_training - Step 23844: {'lr': 0.00047360294206706845, 'samples': 12208640, 'steps': 23844, 'loss/train': 1.333129644393921}
-03/04/2022 17:28:11 - INFO - codeparrot_training - Step 23845: {'lr': 0.0004736005686047907, 'samples': 12209152, 'steps': 23845, 'loss/train': 0.9041134715080261}
-03/04/2022 17:28:13 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/04/2022 17:28:17 - INFO - codeparrot_training - Step 23846: {'lr': 0.000473598195041762, 'samples': 12209664, 'steps': 23846, 'loss/train': 1.2231093645095825}
-03/04/2022 17:28:20 - INFO - codeparrot_training - Step 23847: {'lr': 0.0004735958213779835, 'samples': 12210176, 'steps': 23847, 'loss/train': 0.9231230020523071}
-03/04/2022 17:28:22 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 17:28:25 - INFO - codeparrot_training - Step 23848: {'lr': 0.0004735934476134561, 'samples': 12210688, 'steps': 23848, 'loss/train': 0.6269928812980652}
-03/04/2022 17:28:28 - INFO - codeparrot_training - Step 23849: {'lr': 0.0004735910737481809, 'samples': 12211200, 'steps': 23849, 'loss/train': 2.0149922370910645}
-03/04/2022 17:28:30 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/04/2022 17:28:34 - INFO - codeparrot_training - Step 23850: {'lr': 0.0004735886997821591, 'samples': 12211712, 'steps': 23850, 'loss/train': 1.9665768146514893}
-03/04/2022 17:28:37 - INFO - codeparrot_training - Step 23851: {'lr': 0.00047358632571539163, 'samples': 12212224, 'steps': 23851, 'loss/train': 1.7910634279251099}
-03/04/2022 17:28:39 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/04/2022 17:28:42 - INFO - codeparrot_training - Step 23852: {'lr': 0.0004735839515478796, 'samples': 12212736, 'steps': 23852, 'loss/train': 1.2872527837753296}
-03/04/2022 17:28:45 - INFO - codeparrot_training - Step 23853: {'lr': 0.0004735815772796241, 'samples': 12213248, 'steps': 23853, 'loss/train': 2.1632232666015625}
-03/04/2022 17:28:47 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/04/2022 17:28:50 - INFO - codeparrot_training - Step 23854: {'lr': 0.0004735792029106262, 'samples': 12213760, 'steps': 23854, 'loss/train': 1.5957587957382202}
-03/04/2022 17:28:54 - INFO - codeparrot_training - Step 23855: {'lr': 0.0004735768284408869, 'samples': 12214272, 'steps': 23855, 'loss/train': 2.112071990966797}
-03/04/2022 17:28:59 - INFO - codeparrot_training - Step 23856: {'lr': 0.00047357445387040745, 'samples': 12214784, 'steps': 23856, 'loss/train': 1.7045769691467285}
-03/04/2022 17:29:02 - INFO - codeparrot_training - Step 23857: {'lr': 0.0004735720791991887, 'samples': 12215296, 'steps': 23857, 'loss/train': 1.773215651512146}
-03/04/2022 17:29:03 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/04/2022 17:29:07 - INFO - codeparrot_training - Step 23858: {'lr': 0.00047356970442723184, 'samples': 12215808, 'steps': 23858, 'loss/train': 1.8741148710250854}
-03/04/2022 17:29:10 - INFO - codeparrot_training - Step 23859: {'lr': 0.00047356732955453794, 'samples': 12216320, 'steps': 23859, 'loss/train': 0.4049205780029297}
-03/04/2022 17:29:12 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 17:29:16 - INFO - codeparrot_training - Step 23860: {'lr': 0.00047356495458110806, 'samples': 12216832, 'steps': 23860, 'loss/train': 1.4999581575393677}
-03/04/2022 17:29:19 - INFO - codeparrot_training - Step 23861: {'lr': 0.00047356257950694326, 'samples': 12217344, 'steps': 23861, 'loss/train': 1.5400173664093018}
-03/04/2022 17:29:21 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/04/2022 17:29:24 - INFO - codeparrot_training - Step 23862: {'lr': 0.0004735602043320446, 'samples': 12217856, 'steps': 23862, 'loss/train': 3.077800750732422}
-03/04/2022 17:29:27 - INFO - codeparrot_training - Step 23863: {'lr': 0.0004735578290564132, 'samples': 12218368, 'steps': 23863, 'loss/train': 1.6511355638504028}
-03/04/2022 17:29:29 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 17:29:33 - INFO - codeparrot_training - Step 23864: {'lr': 0.00047355545368005003, 'samples': 12218880, 'steps': 23864, 'loss/train': 1.6906017065048218}
-03/04/2022 17:29:36 - INFO - codeparrot_training - Step 23865: {'lr': 0.00047355307820295625, 'samples': 12219392, 'steps': 23865, 'loss/train': 2.152430772781372}
-03/04/2022 17:29:38 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 17:29:41 - INFO - codeparrot_training - Step 23866: {'lr': 0.00047355070262513287, 'samples': 12219904, 'steps': 23866, 'loss/train': 1.952852725982666}
-03/04/2022 17:29:44 - INFO - codeparrot_training - Step 23867: {'lr': 0.00047354832694658104, 'samples': 12220416, 'steps': 23867, 'loss/train': 1.8325508832931519}
-03/04/2022 17:29:46 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/04/2022 17:29:49 - INFO - codeparrot_training - Step 23868: {'lr': 0.0004735459511673018, 'samples': 12220928, 'steps': 23868, 'loss/train': 2.407017946243286}
-03/04/2022 17:29:53 - INFO - codeparrot_training - Step 23869: {'lr': 0.0004735435752872962, 'samples': 12221440, 'steps': 23869, 'loss/train': 1.8293453454971313}
-03/04/2022 17:29:55 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 17:29:58 - INFO - codeparrot_training - Step 23870: {'lr': 0.00047354119930656524, 'samples': 12221952, 'steps': 23870, 'loss/train': 1.750207781791687}
-03/04/2022 17:30:01 - INFO - codeparrot_training - Step 23871: {'lr': 0.0004735388232251101, 'samples': 12222464, 'steps': 23871, 'loss/train': 2.172213077545166}
-03/04/2022 17:30:03 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 17:30:06 - INFO - codeparrot_training - Step 23872: {'lr': 0.00047353644704293185, 'samples': 12222976, 'steps': 23872, 'loss/train': 3.1647231578826904}
-03/04/2022 17:30:09 - INFO - codeparrot_training - Step 23873: {'lr': 0.0004735340707600315, 'samples': 12223488, 'steps': 23873, 'loss/train': 1.7137821912765503}
-03/04/2022 17:30:11 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/04/2022 17:30:15 - INFO - codeparrot_training - Step 23874: {'lr': 0.0004735316943764102, 'samples': 12224000, 'steps': 23874, 'loss/train': 0.6968318819999695}
-03/04/2022 17:30:18 - INFO - codeparrot_training - Step 23875: {'lr': 0.0004735293178920689, 'samples': 12224512, 'steps': 23875, 'loss/train': 1.5216295719146729}
-03/04/2022 17:30:20 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/04/2022 17:30:23 - INFO - codeparrot_training - Step 23876: {'lr': 0.00047352694130700873, 'samples': 12225024, 'steps': 23876, 'loss/train': 2.2832508087158203}
-03/04/2022 17:30:26 - INFO - codeparrot_training - Step 23877: {'lr': 0.00047352456462123086, 'samples': 12225536, 'steps': 23877, 'loss/train': 1.9380419254302979}
-03/04/2022 17:30:28 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/04/2022 17:30:32 - INFO - codeparrot_training - Step 23878: {'lr': 0.00047352218783473614, 'samples': 12226048, 'steps': 23878, 'loss/train': 1.7024190425872803}
-03/04/2022 17:30:35 - INFO - codeparrot_training - Step 23879: {'lr': 0.0004735198109475258, 'samples': 12226560, 'steps': 23879, 'loss/train': 0.7260159850120544}
-03/04/2022 17:30:37 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/04/2022 17:30:40 - INFO - codeparrot_training - Step 23880: {'lr': 0.000473517433959601, 'samples': 12227072, 'steps': 23880, 'loss/train': 1.4091675281524658}
-03/04/2022 17:30:43 - INFO - codeparrot_training - Step 23881: {'lr': 0.00047351505687096257, 'samples': 12227584, 'steps': 23881, 'loss/train': 0.33322060108184814}
-03/04/2022 17:30:45 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/04/2022 17:30:48 - INFO - codeparrot_training - Step 23882: {'lr': 0.00047351267968161176, 'samples': 12228096, 'steps': 23882, 'loss/train': 2.1897242069244385}
-03/04/2022 17:30:51 - INFO - codeparrot_training - Step 23883: {'lr': 0.0004735103023915496, 'samples': 12228608, 'steps': 23883, 'loss/train': 2.036616325378418}
-03/04/2022 17:30:53 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 17:30:57 - INFO - codeparrot_training - Step 23884: {'lr': 0.0004735079250007771, 'samples': 12229120, 'steps': 23884, 'loss/train': 1.09048593044281}
-03/04/2022 17:31:00 - INFO - codeparrot_training - Step 23885: {'lr': 0.00047350554750929543, 'samples': 12229632, 'steps': 23885, 'loss/train': 1.5406955480575562}
-03/04/2022 17:31:02 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/04/2022 17:31:05 - INFO - codeparrot_training - Step 23886: {'lr': 0.0004735031699171055, 'samples': 12230144, 'steps': 23886, 'loss/train': 1.7726279497146606}
-03/04/2022 17:31:08 - INFO - codeparrot_training - Step 23887: {'lr': 0.0004735007922242086, 'samples': 12230656, 'steps': 23887, 'loss/train': 2.173550844192505}
-03/04/2022 17:31:11 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 17:31:14 - INFO - codeparrot_training - Step 23888: {'lr': 0.0004734984144306057, 'samples': 12231168, 'steps': 23888, 'loss/train': 0.677206814289093}
-03/04/2022 17:31:17 - INFO - codeparrot_training - Step 23889: {'lr': 0.0004734960365362978, 'samples': 12231680, 'steps': 23889, 'loss/train': 2.071901559829712}
-03/04/2022 17:31:19 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 17:31:22 - INFO - codeparrot_training - Step 23890: {'lr': 0.0004734936585412861, 'samples': 12232192, 'steps': 23890, 'loss/train': 2.3489248752593994}
-03/04/2022 17:31:25 - INFO - codeparrot_training - Step 23891: {'lr': 0.00047349128044557153, 'samples': 12232704, 'steps': 23891, 'loss/train': 1.4023581743240356}
-03/04/2022 17:31:27 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/04/2022 17:31:31 - INFO - codeparrot_training - Step 23892: {'lr': 0.0004734889022491553, 'samples': 12233216, 'steps': 23892, 'loss/train': 1.9757378101348877}
-03/04/2022 17:31:34 - INFO - codeparrot_training - Step 23893: {'lr': 0.0004734865239520384, 'samples': 12233728, 'steps': 23893, 'loss/train': 1.0370274782180786}
-03/04/2022 17:31:36 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 17:31:39 - INFO - codeparrot_training - Step 23894: {'lr': 0.0004734841455542219, 'samples': 12234240, 'steps': 23894, 'loss/train': 0.3951893150806427}
-03/04/2022 17:31:42 - INFO - codeparrot_training - Step 23895: {'lr': 0.0004734817670557069, 'samples': 12234752, 'steps': 23895, 'loss/train': 2.115211248397827}
-03/04/2022 17:31:44 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/04/2022 17:31:48 - INFO - codeparrot_training - Step 23896: {'lr': 0.00047347938845649447, 'samples': 12235264, 'steps': 23896, 'loss/train': 1.919592261314392}
-03/04/2022 17:31:51 - INFO - codeparrot_training - Step 23897: {'lr': 0.0004734770097565857, 'samples': 12235776, 'steps': 23897, 'loss/train': 2.262985944747925}
-03/04/2022 17:31:53 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 17:31:56 - INFO - codeparrot_training - Step 23898: {'lr': 0.00047347463095598157, 'samples': 12236288, 'steps': 23898, 'loss/train': 1.5039560794830322}
-03/04/2022 17:31:59 - INFO - codeparrot_training - Step 23899: {'lr': 0.00047347225205468323, 'samples': 12236800, 'steps': 23899, 'loss/train': 2.096666097640991}
-03/04/2022 17:32:01 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/04/2022 17:32:05 - INFO - codeparrot_training - Step 23900: {'lr': 0.00047346987305269184, 'samples': 12237312, 'steps': 23900, 'loss/train': 2.646045207977295}
-03/04/2022 17:32:08 - INFO - codeparrot_training - Step 23901: {'lr': 0.0004734674939500083, 'samples': 12237824, 'steps': 23901, 'loss/train': 1.7790571451187134}
-03/04/2022 17:32:09 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 17:32:13 - INFO - codeparrot_training - Step 23902: {'lr': 0.0004734651147466338, 'samples': 12238336, 'steps': 23902, 'loss/train': 1.5829920768737793}
-03/04/2022 17:32:16 - INFO - codeparrot_training - Step 23903: {'lr': 0.00047346273544256927, 'samples': 12238848, 'steps': 23903, 'loss/train': 1.910275936126709}
-03/04/2022 17:32:18 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/04/2022 17:32:21 - INFO - codeparrot_training - Step 23904: {'lr': 0.00047346035603781597, 'samples': 12239360, 'steps': 23904, 'loss/train': 1.4436780214309692}
-03/04/2022 17:32:25 - INFO - codeparrot_training - Step 23905: {'lr': 0.00047345797653237486, 'samples': 12239872, 'steps': 23905, 'loss/train': 1.614989995956421}
-03/04/2022 17:32:26 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/04/2022 17:32:30 - INFO - codeparrot_training - Step 23906: {'lr': 0.000473455596926247, 'samples': 12240384, 'steps': 23906, 'loss/train': 0.2401173859834671}
-03/04/2022 17:32:33 - INFO - codeparrot_training - Step 23907: {'lr': 0.0004734532172194335, 'samples': 12240896, 'steps': 23907, 'loss/train': 1.7380670309066772}
-03/04/2022 17:32:35 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/04/2022 17:32:38 - INFO - codeparrot_training - Step 23908: {'lr': 0.0004734508374119355, 'samples': 12241408, 'steps': 23908, 'loss/train': 1.709637999534607}
-03/04/2022 17:32:42 - INFO - codeparrot_training - Step 23909: {'lr': 0.0004734484575037539, 'samples': 12241920, 'steps': 23909, 'loss/train': 1.2764054536819458}
-03/04/2022 17:32:44 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/04/2022 17:32:47 - INFO - codeparrot_training - Step 23910: {'lr': 0.00047344607749489, 'samples': 12242432, 'steps': 23910, 'loss/train': 2.9722962379455566}
-03/04/2022 17:32:50 - INFO - codeparrot_training - Step 23911: {'lr': 0.00047344369738534466, 'samples': 12242944, 'steps': 23911, 'loss/train': 2.166679620742798}
-03/04/2022 17:32:53 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 17:32:55 - INFO - codeparrot_training - Step 23912: {'lr': 0.000473441317175119, 'samples': 12243456, 'steps': 23912, 'loss/train': 1.763956069946289}
-03/04/2022 17:32:59 - INFO - codeparrot_training - Step 23913: {'lr': 0.0004734389368642142, 'samples': 12243968, 'steps': 23913, 'loss/train': 1.8178014755249023}
-03/04/2022 17:33:01 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 17:33:04 - INFO - codeparrot_training - Step 23914: {'lr': 0.0004734365564526313, 'samples': 12244480, 'steps': 23914, 'loss/train': 1.9510051012039185}
-03/04/2022 17:33:07 - INFO - codeparrot_training - Step 23915: {'lr': 0.00047343417594037117, 'samples': 12244992, 'steps': 23915, 'loss/train': 1.7640701532363892}
-03/04/2022 17:33:10 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 17:33:12 - INFO - codeparrot_training - Step 23916: {'lr': 0.00047343179532743516, 'samples': 12245504, 'steps': 23916, 'loss/train': 1.808117389678955}
-03/04/2022 17:33:16 - INFO - codeparrot_training - Step 23917: {'lr': 0.00047342941461382427, 'samples': 12246016, 'steps': 23917, 'loss/train': 1.5267900228500366}
-03/04/2022 17:33:18 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/04/2022 17:33:21 - INFO - codeparrot_training - Step 23918: {'lr': 0.0004734270337995395, 'samples': 12246528, 'steps': 23918, 'loss/train': 1.9189980030059814}
-03/04/2022 17:33:24 - INFO - codeparrot_training - Step 23919: {'lr': 0.0004734246528845819, 'samples': 12247040, 'steps': 23919, 'loss/train': 1.418204665184021}
-03/04/2022 17:33:27 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 17:33:29 - INFO - codeparrot_training - Step 23920: {'lr': 0.0004734222718689527, 'samples': 12247552, 'steps': 23920, 'loss/train': 1.419854998588562}
-03/04/2022 17:33:32 - INFO - codeparrot_training - Step 23921: {'lr': 0.0004734198907526528, 'samples': 12248064, 'steps': 23921, 'loss/train': 1.628233551979065}
-03/04/2022 17:33:36 - INFO - codeparrot_training - Step 23922: {'lr': 0.00047341750953568335, 'samples': 12248576, 'steps': 23922, 'loss/train': 2.187562942504883}
-03/04/2022 17:33:36 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 17:33:41 - INFO - codeparrot_training - Step 23923: {'lr': 0.0004734151282180454, 'samples': 12249088, 'steps': 23923, 'loss/train': 1.1269090175628662}
-03/04/2022 17:33:44 - INFO - codeparrot_training - Step 23924: {'lr': 0.0004734127467997401, 'samples': 12249600, 'steps': 23924, 'loss/train': 1.4481438398361206}
-03/04/2022 17:33:44 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 17:33:50 - INFO - codeparrot_training - Step 23925: {'lr': 0.0004734103652807684, 'samples': 12250112, 'steps': 23925, 'loss/train': 2.157829761505127}
-03/04/2022 17:33:53 - INFO - codeparrot_training - Step 23926: {'lr': 0.0004734079836611315, 'samples': 12250624, 'steps': 23926, 'loss/train': 2.034489393234253}
-03/04/2022 17:33:53 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/04/2022 17:33:58 - INFO - codeparrot_training - Step 23927: {'lr': 0.0004734056019408304, 'samples': 12251136, 'steps': 23927, 'loss/train': 1.8642380237579346}
-03/04/2022 17:34:01 - INFO - codeparrot_training - Step 23928: {'lr': 0.00047340322011986614, 'samples': 12251648, 'steps': 23928, 'loss/train': 2.344905376434326}
-03/04/2022 17:34:01 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 17:34:07 - INFO - codeparrot_training - Step 23929: {'lr': 0.0004734008381982399, 'samples': 12252160, 'steps': 23929, 'loss/train': 1.4171013832092285}
-03/04/2022 17:34:10 - INFO - codeparrot_training - Step 23930: {'lr': 0.0004733984561759527, 'samples': 12252672, 'steps': 23930, 'loss/train': 1.8908283710479736}
-03/04/2022 17:34:10 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 17:34:15 - INFO - codeparrot_training - Step 23931: {'lr': 0.0004733960740530055, 'samples': 12253184, 'steps': 23931, 'loss/train': 1.677435040473938}
-03/04/2022 17:34:18 - INFO - codeparrot_training - Step 23932: {'lr': 0.0004733936918293995, 'samples': 12253696, 'steps': 23932, 'loss/train': 0.3762935698032379}
-03/04/2022 17:34:18 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/04/2022 17:34:24 - INFO - codeparrot_training - Step 23933: {'lr': 0.0004733913095051358, 'samples': 12254208, 'steps': 23933, 'loss/train': 2.461766004562378}
-03/04/2022 17:34:27 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/04/2022 17:34:29 - INFO - codeparrot_training - Step 23934: {'lr': 0.0004733889270802154, 'samples': 12254720, 'steps': 23934, 'loss/train': 1.6262305974960327}
-03/04/2022 17:34:32 - INFO - codeparrot_training - Step 23935: {'lr': 0.00047338654455463935, 'samples': 12255232, 'steps': 23935, 'loss/train': 1.2580357789993286}
-03/04/2022 17:34:36 - INFO - codeparrot_training - Step 23936: {'lr': 0.00047338416192840887, 'samples': 12255744, 'steps': 23936, 'loss/train': 0.8711478114128113}
-03/04/2022 17:34:36 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/04/2022 17:34:41 - INFO - codeparrot_training - Step 23937: {'lr': 0.0004733817792015249, 'samples': 12256256, 'steps': 23937, 'loss/train': 2.540367364883423}
-03/04/2022 17:34:44 - INFO - codeparrot_training - Step 23938: {'lr': 0.00047337939637398855, 'samples': 12256768, 'steps': 23938, 'loss/train': 2.43109393119812}
-03/04/2022 17:34:44 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 17:34:49 - INFO - codeparrot_training - Step 23939: {'lr': 0.0004733770134458009, 'samples': 12257280, 'steps': 23939, 'loss/train': 1.8598753213882446}
-03/04/2022 17:34:52 - INFO - codeparrot_training - Step 23940: {'lr': 0.0004733746304169629, 'samples': 12257792, 'steps': 23940, 'loss/train': 1.7228165864944458}
-03/04/2022 17:34:53 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/04/2022 17:34:58 - INFO - codeparrot_training - Step 23941: {'lr': 0.0004733722472874759, 'samples': 12258304, 'steps': 23941, 'loss/train': 1.557556390762329}
-03/04/2022 17:35:01 - INFO - codeparrot_training - Step 23942: {'lr': 0.0004733698640573407, 'samples': 12258816, 'steps': 23942, 'loss/train': 0.5993305444717407}
-03/04/2022 17:35:01 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/04/2022 17:35:06 - INFO - codeparrot_training - Step 23943: {'lr': 0.0004733674807265585, 'samples': 12259328, 'steps': 23943, 'loss/train': 1.4512182474136353}
-03/04/2022 17:35:09 - INFO - codeparrot_training - Step 23944: {'lr': 0.0004733650972951304, 'samples': 12259840, 'steps': 23944, 'loss/train': 2.135054349899292}
-03/04/2022 17:35:10 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/04/2022 17:35:15 - INFO - codeparrot_training - Step 23945: {'lr': 0.0004733627137630574, 'samples': 12260352, 'steps': 23945, 'loss/train': 2.1388466358184814}
-03/04/2022 17:35:18 - INFO - codeparrot_training - Step 23946: {'lr': 0.00047336033013034063, 'samples': 12260864, 'steps': 23946, 'loss/train': 1.8357486724853516}
-03/04/2022 17:35:18 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/04/2022 17:35:23 - INFO - codeparrot_training - Step 23947: {'lr': 0.00047335794639698117, 'samples': 12261376, 'steps': 23947, 'loss/train': 1.9736883640289307}
-03/04/2022 17:35:26 - INFO - codeparrot_training - Step 23948: {'lr': 0.00047335556256298, 'samples': 12261888, 'steps': 23948, 'loss/train': 1.2310667037963867}
-03/04/2022 17:35:26 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 17:35:32 - INFO - codeparrot_training - Step 23949: {'lr': 0.0004733531786283383, 'samples': 12262400, 'steps': 23949, 'loss/train': 1.3384042978286743}
-03/04/2022 17:35:35 - INFO - codeparrot_training - Step 23950: {'lr': 0.0004733507945930571, 'samples': 12262912, 'steps': 23950, 'loss/train': 1.9888116121292114}
-03/04/2022 17:35:35 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/04/2022 17:35:40 - INFO - codeparrot_training - Step 23951: {'lr': 0.0004733484104571375, 'samples': 12263424, 'steps': 23951, 'loss/train': 1.578676700592041}
-03/04/2022 17:35:43 - INFO - codeparrot_training - Step 23952: {'lr': 0.0004733460262205805, 'samples': 12263936, 'steps': 23952, 'loss/train': 1.6494693756103516}
-03/04/2022 17:35:43 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/04/2022 17:35:49 - INFO - codeparrot_training - Step 23953: {'lr': 0.00047334364188338725, 'samples': 12264448, 'steps': 23953, 'loss/train': 2.2031571865081787}
-03/04/2022 17:35:51 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/04/2022 17:35:54 - INFO - codeparrot_training - Step 23954: {'lr': 0.0004733412574455588, 'samples': 12264960, 'steps': 23954, 'loss/train': 1.836792230606079}
-03/04/2022 17:35:57 - INFO - codeparrot_training - Step 23955: {'lr': 0.00047333887290709623, 'samples': 12265472, 'steps': 23955, 'loss/train': 1.553954839706421}
-03/04/2022 17:36:00 - INFO - codeparrot_training - Step 23956: {'lr': 0.00047333648826800056, 'samples': 12265984, 'steps': 23956, 'loss/train': 4.7044501304626465}
-03/04/2022 17:36:01 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 17:36:06 - INFO - codeparrot_training - Step 23957: {'lr': 0.000473334103528273, 'samples': 12266496, 'steps': 23957, 'loss/train': 1.8536087274551392}
-03/04/2022 17:36:09 - INFO - codeparrot_training - Step 23958: {'lr': 0.00047333171868791453, 'samples': 12267008, 'steps': 23958, 'loss/train': 1.9488499164581299}
-03/04/2022 17:36:10 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/04/2022 17:36:14 - INFO - codeparrot_training - Step 23959: {'lr': 0.00047332933374692623, 'samples': 12267520, 'steps': 23959, 'loss/train': 2.128302812576294}
-03/04/2022 17:36:17 - INFO - codeparrot_training - Step 23960: {'lr': 0.0004733269487053091, 'samples': 12268032, 'steps': 23960, 'loss/train': 2.0150668621063232}
-03/04/2022 17:36:18 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/04/2022 17:36:23 - INFO - codeparrot_training - Step 23961: {'lr': 0.0004733245635630644, 'samples': 12268544, 'steps': 23961, 'loss/train': 0.8445484042167664}
-03/04/2022 17:36:26 - INFO - codeparrot_training - Step 23962: {'lr': 0.000473322178320193, 'samples': 12269056, 'steps': 23962, 'loss/train': 2.204127550125122}
-03/04/2022 17:36:27 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/04/2022 17:36:31 - INFO - codeparrot_training - Step 23963: {'lr': 0.0004733197929766961, 'samples': 12269568, 'steps': 23963, 'loss/train': 1.1881022453308105}
-03/04/2022 17:36:35 - INFO - codeparrot_training - Step 23964: {'lr': 0.0004733174075325748, 'samples': 12270080, 'steps': 23964, 'loss/train': 1.2383887767791748}
-03/04/2022 17:36:37 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/04/2022 17:36:40 - INFO - codeparrot_training - Step 23965: {'lr': 0.0004733150219878301, 'samples': 12270592, 'steps': 23965, 'loss/train': 1.5078856945037842}
-03/04/2022 17:36:43 - INFO - codeparrot_training - Step 23966: {'lr': 0.00047331263634246314, 'samples': 12271104, 'steps': 23966, 'loss/train': 1.5834245681762695}
-03/04/2022 17:36:45 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 17:36:48 - INFO - codeparrot_training - Step 23967: {'lr': 0.0004733102505964749, 'samples': 12271616, 'steps': 23967, 'loss/train': 1.9126179218292236}
-03/04/2022 17:36:51 - INFO - codeparrot_training - Step 23968: {'lr': 0.00047330786474986645, 'samples': 12272128, 'steps': 23968, 'loss/train': 1.7528331279754639}
-03/04/2022 17:36:53 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/04/2022 17:36:57 - INFO - codeparrot_training - Step 23969: {'lr': 0.00047330547880263896, 'samples': 12272640, 'steps': 23969, 'loss/train': 1.6887513399124146}
-03/04/2022 17:37:00 - INFO - codeparrot_training - Step 23970: {'lr': 0.00047330309275479354, 'samples': 12273152, 'steps': 23970, 'loss/train': 2.1356794834136963}
-03/04/2022 17:37:05 - INFO - codeparrot_training - Step 23971: {'lr': 0.00047330070660633113, 'samples': 12273664, 'steps': 23971, 'loss/train': 2.0459330081939697}
-03/04/2022 17:37:08 - INFO - codeparrot_training - Step 23972: {'lr': 0.00047329832035725286, 'samples': 12274176, 'steps': 23972, 'loss/train': 1.8139877319335938}
-03/04/2022 17:37:10 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 17:37:13 - INFO - codeparrot_training - Step 23973: {'lr': 0.0004732959340075598, 'samples': 12274688, 'steps': 23973, 'loss/train': 2.2142395973205566}
-03/04/2022 17:37:17 - INFO - codeparrot_training - Step 23974: {'lr': 0.0004732935475572531, 'samples': 12275200, 'steps': 23974, 'loss/train': 1.9302705526351929}
-03/04/2022 17:37:18 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 17:37:22 - INFO - codeparrot_training - Step 23975: {'lr': 0.00047329116100633373, 'samples': 12275712, 'steps': 23975, 'loss/train': 1.5582859516143799}
-03/04/2022 17:37:25 - INFO - codeparrot_training - Step 23976: {'lr': 0.0004732887743548028, 'samples': 12276224, 'steps': 23976, 'loss/train': 1.7522284984588623}
-03/04/2022 17:37:28 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 17:37:30 - INFO - codeparrot_training - Step 23977: {'lr': 0.0004732863876026614, 'samples': 12276736, 'steps': 23977, 'loss/train': 2.160885810852051}
-03/04/2022 17:37:34 - INFO - codeparrot_training - Step 23978: {'lr': 0.00047328400074991064, 'samples': 12277248, 'steps': 23978, 'loss/train': 0.8982470631599426}
-03/04/2022 17:37:36 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 17:37:39 - INFO - codeparrot_training - Step 23979: {'lr': 0.00047328161379655155, 'samples': 12277760, 'steps': 23979, 'loss/train': 2.4329946041107178}
-03/04/2022 17:37:42 - INFO - codeparrot_training - Step 23980: {'lr': 0.00047327922674258516, 'samples': 12278272, 'steps': 23980, 'loss/train': 2.042363166809082}
-03/04/2022 17:37:44 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/04/2022 17:37:47 - INFO - codeparrot_training - Step 23981: {'lr': 0.00047327683958801257, 'samples': 12278784, 'steps': 23981, 'loss/train': 2.079195737838745}
-03/04/2022 17:37:51 - INFO - codeparrot_training - Step 23982: {'lr': 0.00047327445233283496, 'samples': 12279296, 'steps': 23982, 'loss/train': 1.0602015256881714}
-03/04/2022 17:37:53 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 17:37:56 - INFO - codeparrot_training - Step 23983: {'lr': 0.0004732720649770533, 'samples': 12279808, 'steps': 23983, 'loss/train': 1.8659113645553589}
-03/04/2022 17:37:59 - INFO - codeparrot_training - Step 23984: {'lr': 0.00047326967752066876, 'samples': 12280320, 'steps': 23984, 'loss/train': 2.1499650478363037}
-03/04/2022 17:38:02 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 17:38:05 - INFO - codeparrot_training - Step 23985: {'lr': 0.0004732672899636822, 'samples': 12280832, 'steps': 23985, 'loss/train': 1.7113415002822876}
-03/04/2022 17:38:08 - INFO - codeparrot_training - Step 23986: {'lr': 0.00047326490230609495, 'samples': 12281344, 'steps': 23986, 'loss/train': 1.9768426418304443}
-03/04/2022 17:38:10 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/04/2022 17:38:13 - INFO - codeparrot_training - Step 23987: {'lr': 0.000473262514547908, 'samples': 12281856, 'steps': 23987, 'loss/train': 1.4057209491729736}
-03/04/2022 17:38:16 - INFO - codeparrot_training - Step 23988: {'lr': 0.00047326012668912233, 'samples': 12282368, 'steps': 23988, 'loss/train': 1.2061398029327393}
-03/04/2022 17:38:19 - INFO - codeparrot_training - Step 23989: {'lr': 0.0004732577387297391, 'samples': 12282880, 'steps': 23989, 'loss/train': 1.1489900350570679}
-03/04/2022 17:38:19 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 17:38:25 - INFO - codeparrot_training - Step 23990: {'lr': 0.00047325535066975946, 'samples': 12283392, 'steps': 23990, 'loss/train': 1.8282450437545776}
-03/04/2022 17:38:28 - INFO - codeparrot_training - Step 23991: {'lr': 0.0004732529625091843, 'samples': 12283904, 'steps': 23991, 'loss/train': 1.712887167930603}
-03/04/2022 17:38:28 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/04/2022 17:38:33 - INFO - codeparrot_training - Step 23992: {'lr': 0.0004732505742480149, 'samples': 12284416, 'steps': 23992, 'loss/train': 1.0021024942398071}
-03/04/2022 17:38:36 - INFO - codeparrot_training - Step 23993: {'lr': 0.00047324818588625214, 'samples': 12284928, 'steps': 23993, 'loss/train': 1.4539430141448975}
-03/04/2022 17:38:37 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/04/2022 17:38:42 - INFO - codeparrot_training - Step 23994: {'lr': 0.0004732457974238972, 'samples': 12285440, 'steps': 23994, 'loss/train': 0.9547393918037415}
-03/04/2022 17:38:45 - INFO - codeparrot_training - Step 23995: {'lr': 0.0004732434088609512, 'samples': 12285952, 'steps': 23995, 'loss/train': 1.734820008277893}
-03/04/2022 17:38:45 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/04/2022 17:38:50 - INFO - codeparrot_training - Step 23996: {'lr': 0.00047324102019741514, 'samples': 12286464, 'steps': 23996, 'loss/train': 1.3970927000045776}
-03/04/2022 17:38:53 - INFO - codeparrot_training - Step 23997: {'lr': 0.00047323863143329016, 'samples': 12286976, 'steps': 23997, 'loss/train': 2.0924859046936035}
-03/04/2022 17:38:54 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/04/2022 17:38:59 - INFO - codeparrot_training - Step 23998: {'lr': 0.00047323624256857724, 'samples': 12287488, 'steps': 23998, 'loss/train': 1.594757080078125}
-03/04/2022 17:39:02 - INFO - codeparrot_training - Step 23999: {'lr': 0.0004732338536032775, 'samples': 12288000, 'steps': 23999, 'loss/train': 1.2504795789718628}
-03/04/2022 17:39:03 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/04/2022 17:39:07 - INFO - codeparrot_training - Step 24000: {'lr': 0.0004732314645373921, 'samples': 12288512, 'steps': 24000, 'loss/train': 2.314279079437256}
-03/04/2022 17:39:11 - INFO - codeparrot_training - Step 24001: {'lr': 0.0004732290753709221, 'samples': 12289024, 'steps': 24001, 'loss/train': 2.141962766647339}
-03/04/2022 17:39:13 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/04/2022 17:39:16 - INFO - codeparrot_training - Step 24002: {'lr': 0.0004732266861038684, 'samples': 12289536, 'steps': 24002, 'loss/train': 2.798734188079834}
-03/04/2022 17:39:19 - INFO - codeparrot_training - Step 24003: {'lr': 0.0004732242967362322, 'samples': 12290048, 'steps': 24003, 'loss/train': 1.7036367654800415}
-03/04/2022 17:39:22 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/04/2022 17:39:24 - INFO - codeparrot_training - Step 24004: {'lr': 0.00047322190726801464, 'samples': 12290560, 'steps': 24004, 'loss/train': 1.954026460647583}
-03/04/2022 17:39:27 - INFO - codeparrot_training - Step 24005: {'lr': 0.0004732195176992167, 'samples': 12291072, 'steps': 24005, 'loss/train': 1.6941807270050049}
-03/04/2022 17:39:30 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/04/2022 17:39:33 - INFO - codeparrot_training - Step 24006: {'lr': 0.0004732171280298395, 'samples': 12291584, 'steps': 24006, 'loss/train': 1.7170467376708984}
-03/04/2022 17:39:36 - INFO - codeparrot_training - Step 24007: {'lr': 0.0004732147382598842, 'samples': 12292096, 'steps': 24007, 'loss/train': 2.024646520614624}
-03/04/2022 17:39:38 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/04/2022 17:39:41 - INFO - codeparrot_training - Step 24008: {'lr': 0.00047321234838935164, 'samples': 12292608, 'steps': 24008, 'loss/train': 2.142948627471924}
-03/04/2022 17:39:44 - INFO - codeparrot_training - Step 24009: {'lr': 0.0004732099584182431, 'samples': 12293120, 'steps': 24009, 'loss/train': 2.047590970993042}
-03/04/2022 17:39:47 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/04/2022 17:39:49 - INFO - codeparrot_training - Step 24010: {'lr': 0.00047320756834655955, 'samples': 12293632, 'steps': 24010, 'loss/train': 1.8889671564102173}
-03/04/2022 17:39:53 - INFO - codeparrot_training - Step 24011: {'lr': 0.0004732051781743022, 'samples': 12294144, 'steps': 24011, 'loss/train': 2.0373222827911377}
-03/04/2022 17:39:55 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/04/2022 17:39:58 - INFO - codeparrot_training - Step 24012: {'lr': 0.00047320278790147197, 'samples': 12294656, 'steps': 24012, 'loss/train': 1.8597666025161743}
-03/04/2022 17:40:01 - INFO - codeparrot_training - Step 24013: {'lr': 0.00047320039752807, 'samples': 12295168, 'steps': 24013, 'loss/train': 1.8789314031600952}
-03/04/2022 17:40:04 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 17:40:07 - INFO - codeparrot_training - Step 24014: {'lr': 0.0004731980070540974, 'samples': 12295680, 'steps': 24014, 'loss/train': 1.380476713180542}
-03/04/2022 17:40:10 - INFO - codeparrot_training - Step 24015: {'lr': 0.0004731956164795552, 'samples': 12296192, 'steps': 24015, 'loss/train': 2.4772913455963135}
-03/04/2022 17:40:13 - INFO - codeparrot_training - Step 24016: {'lr': 0.0004731932258044446, 'samples': 12296704, 'steps': 24016, 'loss/train': 2.029371976852417}
-03/04/2022 17:40:15 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/04/2022 17:40:18 - INFO - codeparrot_training - Step 24017: {'lr': 0.00047319083502876647, 'samples': 12297216, 'steps': 24017, 'loss/train': 2.1769299507141113}
-03/04/2022 17:40:22 - INFO - codeparrot_training - Step 24018: {'lr': 0.00047318844415252204, 'samples': 12297728, 'steps': 24018, 'loss/train': 2.0114574432373047}
-03/04/2022 17:40:23 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/04/2022 17:40:27 - INFO - codeparrot_training - Step 24019: {'lr': 0.00047318605317571227, 'samples': 12298240, 'steps': 24019, 'loss/train': 1.3914356231689453}
-03/04/2022 17:40:30 - INFO - codeparrot_training - Step 24020: {'lr': 0.0004731836620983384, 'samples': 12298752, 'steps': 24020, 'loss/train': 2.696396589279175}
-03/04/2022 17:40:32 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 17:40:36 - INFO - codeparrot_training - Step 24021: {'lr': 0.00047318127092040144, 'samples': 12299264, 'steps': 24021, 'loss/train': 0.6576046943664551}
-03/04/2022 17:40:39 - INFO - codeparrot_training - Step 24022: {'lr': 0.00047317887964190233, 'samples': 12299776, 'steps': 24022, 'loss/train': 2.228574514389038}
-03/04/2022 17:40:42 - INFO - codeparrot_training - Step 24023: {'lr': 0.00047317648826284233, 'samples': 12300288, 'steps': 24023, 'loss/train': 2.692107677459717}
-03/04/2022 17:40:43 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 17:40:47 - INFO - codeparrot_training - Step 24024: {'lr': 0.0004731740967832224, 'samples': 12300800, 'steps': 24024, 'loss/train': 1.8153022527694702}
-03/04/2022 17:40:51 - INFO - codeparrot_training - Step 24025: {'lr': 0.00047317170520304373, 'samples': 12301312, 'steps': 24025, 'loss/train': 2.3017916679382324}
-03/04/2022 17:40:52 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/04/2022 17:40:56 - INFO - codeparrot_training - Step 24026: {'lr': 0.0004731693135223073, 'samples': 12301824, 'steps': 24026, 'loss/train': 1.8597946166992188}
-03/04/2022 17:40:59 - INFO - codeparrot_training - Step 24027: {'lr': 0.0004731669217410142, 'samples': 12302336, 'steps': 24027, 'loss/train': 2.1309926509857178}
-03/04/2022 17:41:00 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/04/2022 17:41:04 - INFO - codeparrot_training - Step 24028: {'lr': 0.0004731645298591656, 'samples': 12302848, 'steps': 24028, 'loss/train': 1.2750903367996216}
-03/04/2022 17:41:07 - INFO - codeparrot_training - Step 24029: {'lr': 0.0004731621378767624, 'samples': 12303360, 'steps': 24029, 'loss/train': 2.113081932067871}
-03/04/2022 17:41:09 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/04/2022 17:41:13 - INFO - codeparrot_training - Step 24030: {'lr': 0.0004731597457938059, 'samples': 12303872, 'steps': 24030, 'loss/train': 2.7036962509155273}
-03/04/2022 17:41:16 - INFO - codeparrot_training - Step 24031: {'lr': 0.000473157353610297, 'samples': 12304384, 'steps': 24031, 'loss/train': 1.3331118822097778}
-03/04/2022 17:41:18 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/04/2022 17:41:21 - INFO - codeparrot_training - Step 24032: {'lr': 0.0004731549613262368, 'samples': 12304896, 'steps': 24032, 'loss/train': 1.1536608934402466}
-03/04/2022 17:41:25 - INFO - codeparrot_training - Step 24033: {'lr': 0.0004731525689416265, 'samples': 12305408, 'steps': 24033, 'loss/train': 1.8285322189331055}
-03/04/2022 17:41:26 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/04/2022 17:41:30 - INFO - codeparrot_training - Step 24034: {'lr': 0.0004731501764564671, 'samples': 12305920, 'steps': 24034, 'loss/train': 2.0663998126983643}
-03/04/2022 17:41:33 - INFO - codeparrot_training - Step 24035: {'lr': 0.00047314778387075963, 'samples': 12306432, 'steps': 24035, 'loss/train': 2.880819320678711}
-03/04/2022 17:41:35 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 17:41:38 - INFO - codeparrot_training - Step 24036: {'lr': 0.00047314539118450516, 'samples': 12306944, 'steps': 24036, 'loss/train': 1.9792269468307495}
-03/04/2022 17:41:41 - INFO - codeparrot_training - Step 24037: {'lr': 0.0004731429983977049, 'samples': 12307456, 'steps': 24037, 'loss/train': 1.946357250213623}
-03/04/2022 17:41:43 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/04/2022 17:41:47 - INFO - codeparrot_training - Step 24038: {'lr': 0.00047314060551035983, 'samples': 12307968, 'steps': 24038, 'loss/train': 0.681414783000946}
-03/04/2022 17:41:50 - INFO - codeparrot_training - Step 24039: {'lr': 0.00047313821252247104, 'samples': 12308480, 'steps': 24039, 'loss/train': 1.6910324096679688}
-03/04/2022 17:41:51 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 17:41:55 - INFO - codeparrot_training - Step 24040: {'lr': 0.00047313581943403963, 'samples': 12308992, 'steps': 24040, 'loss/train': 1.865984320640564}
-03/04/2022 17:41:58 - INFO - codeparrot_training - Step 24041: {'lr': 0.0004731334262450666, 'samples': 12309504, 'steps': 24041, 'loss/train': 1.7499123811721802}
-03/04/2022 17:41:59 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/04/2022 17:42:04 - INFO - codeparrot_training - Step 24042: {'lr': 0.00047313103295555317, 'samples': 12310016, 'steps': 24042, 'loss/train': 1.863382339477539}
-03/04/2022 17:42:07 - INFO - codeparrot_training - Step 24043: {'lr': 0.0004731286395655003, 'samples': 12310528, 'steps': 24043, 'loss/train': 2.0376853942871094}
-03/04/2022 17:42:08 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 17:42:12 - INFO - codeparrot_training - Step 24044: {'lr': 0.00047312624607490913, 'samples': 12311040, 'steps': 24044, 'loss/train': 2.291694164276123}
-03/04/2022 17:42:16 - INFO - codeparrot_training - Step 24045: {'lr': 0.0004731238524837807, 'samples': 12311552, 'steps': 24045, 'loss/train': 1.5295854806900024}
-03/04/2022 17:42:19 - INFO - codeparrot_training - Step 24046: {'lr': 0.00047312145879211607, 'samples': 12312064, 'steps': 24046, 'loss/train': 1.867437720298767}
-03/04/2022 17:42:19 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/04/2022 17:42:24 - INFO - codeparrot_training - Step 24047: {'lr': 0.0004731190649999164, 'samples': 12312576, 'steps': 24047, 'loss/train': 1.4578790664672852}
-03/04/2022 17:42:27 - INFO - codeparrot_training - Step 24048: {'lr': 0.0004731166711071827, 'samples': 12313088, 'steps': 24048, 'loss/train': 2.1888656616210938}
-03/04/2022 17:42:27 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 17:42:33 - INFO - codeparrot_training - Step 24049: {'lr': 0.0004731142771139161, 'samples': 12313600, 'steps': 24049, 'loss/train': 1.564119577407837}
-03/04/2022 17:42:36 - INFO - codeparrot_training - Step 24050: {'lr': 0.00047311188302011766, 'samples': 12314112, 'steps': 24050, 'loss/train': 1.344059944152832}
-03/04/2022 17:42:36 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/04/2022 17:42:41 - INFO - codeparrot_training - Step 24051: {'lr': 0.00047310948882578843, 'samples': 12314624, 'steps': 24051, 'loss/train': 2.639352560043335}
-03/04/2022 17:42:44 - INFO - codeparrot_training - Step 24052: {'lr': 0.0004731070945309295, 'samples': 12315136, 'steps': 24052, 'loss/train': 0.25408416986465454}
-03/04/2022 17:42:44 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/04/2022 17:42:50 - INFO - codeparrot_training - Step 24053: {'lr': 0.00047310470013554195, 'samples': 12315648, 'steps': 24053, 'loss/train': 1.477995753288269}
-03/04/2022 17:42:53 - INFO - codeparrot_training - Step 24054: {'lr': 0.0004731023056396269, 'samples': 12316160, 'steps': 24054, 'loss/train': 2.3762307167053223}
-03/04/2022 17:42:53 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/04/2022 17:42:58 - INFO - codeparrot_training - Step 24055: {'lr': 0.00047309991104318533, 'samples': 12316672, 'steps': 24055, 'loss/train': 1.9683674573898315}
-03/04/2022 17:43:01 - INFO - codeparrot_training - Step 24056: {'lr': 0.00047309751634621845, 'samples': 12317184, 'steps': 24056, 'loss/train': 0.9495123028755188}
-03/04/2022 17:43:01 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 17:43:06 - INFO - codeparrot_training - Step 24057: {'lr': 0.0004730951215487272, 'samples': 12317696, 'steps': 24057, 'loss/train': 0.9281378984451294}
-03/04/2022 17:43:10 - INFO - codeparrot_training - Step 24058: {'lr': 0.0004730927266507128, 'samples': 12318208, 'steps': 24058, 'loss/train': 1.6143735647201538}
-03/04/2022 17:43:10 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 17:43:15 - INFO - codeparrot_training - Step 24059: {'lr': 0.00047309033165217617, 'samples': 12318720, 'steps': 24059, 'loss/train': 2.534825086593628}
-03/04/2022 17:43:18 - INFO - codeparrot_training - Step 24060: {'lr': 0.00047308793655311855, 'samples': 12319232, 'steps': 24060, 'loss/train': 1.866559624671936}
-03/04/2022 17:43:18 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/04/2022 17:43:23 - INFO - codeparrot_training - Step 24061: {'lr': 0.000473085541353541, 'samples': 12319744, 'steps': 24061, 'loss/train': 2.032223701477051}
-03/04/2022 17:43:26 - INFO - codeparrot_training - Step 24062: {'lr': 0.00047308314605344447, 'samples': 12320256, 'steps': 24062, 'loss/train': 2.103241205215454}
-03/04/2022 17:43:27 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/04/2022 17:43:32 - INFO - codeparrot_training - Step 24063: {'lr': 0.00047308075065283006, 'samples': 12320768, 'steps': 24063, 'loss/train': 2.1359989643096924}
-03/04/2022 17:43:35 - INFO - codeparrot_training - Step 24064: {'lr': 0.00047307835515169905, 'samples': 12321280, 'steps': 24064, 'loss/train': 0.9582512378692627}
-03/04/2022 17:43:35 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 17:43:40 - INFO - codeparrot_training - Step 24065: {'lr': 0.00047307595955005226, 'samples': 12321792, 'steps': 24065, 'loss/train': 1.7214199304580688}
-03/04/2022 17:43:43 - INFO - codeparrot_training - Step 24066: {'lr': 0.000473073563847891, 'samples': 12322304, 'steps': 24066, 'loss/train': 2.2545158863067627}
-03/04/2022 17:43:44 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/04/2022 17:43:49 - INFO - codeparrot_training - Step 24067: {'lr': 0.0004730711680452161, 'samples': 12322816, 'steps': 24067, 'loss/train': 1.2077125310897827}
-03/04/2022 17:43:52 - INFO - codeparrot_training - Step 24068: {'lr': 0.00047306877214202885, 'samples': 12323328, 'steps': 24068, 'loss/train': 1.7463852167129517}
-03/04/2022 17:43:52 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 17:43:57 - INFO - codeparrot_training - Step 24069: {'lr': 0.00047306637613833024, 'samples': 12323840, 'steps': 24069, 'loss/train': 1.29376220703125}
-03/04/2022 17:44:00 - INFO - codeparrot_training - Step 24070: {'lr': 0.00047306398003412137, 'samples': 12324352, 'steps': 24070, 'loss/train': 1.8340561389923096}
-03/04/2022 17:44:00 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/04/2022 17:44:06 - INFO - codeparrot_training - Step 24071: {'lr': 0.00047306158382940327, 'samples': 12324864, 'steps': 24071, 'loss/train': 1.7877377271652222}
-03/04/2022 17:44:09 - INFO - codeparrot_training - Step 24072: {'lr': 0.0004730591875241771, 'samples': 12325376, 'steps': 24072, 'loss/train': 2.0209290981292725}
-03/04/2022 17:44:09 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/04/2022 17:44:14 - INFO - codeparrot_training - Step 24073: {'lr': 0.0004730567911184439, 'samples': 12325888, 'steps': 24073, 'loss/train': 1.5094003677368164}
-03/04/2022 17:44:17 - INFO - codeparrot_training - Step 24074: {'lr': 0.00047305439461220477, 'samples': 12326400, 'steps': 24074, 'loss/train': 2.001117706298828}
-03/04/2022 17:44:18 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/04/2022 17:44:22 - INFO - codeparrot_training - Step 24075: {'lr': 0.00047305199800546077, 'samples': 12326912, 'steps': 24075, 'loss/train': 2.267198085784912}
-03/04/2022 17:44:26 - INFO - codeparrot_training - Step 24076: {'lr': 0.00047304960129821295, 'samples': 12327424, 'steps': 24076, 'loss/train': 1.993097186088562}
-03/04/2022 17:44:26 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/04/2022 17:44:31 - INFO - codeparrot_training - Step 24077: {'lr': 0.00047304720449046247, 'samples': 12327936, 'steps': 24077, 'loss/train': 1.6710890531539917}
-03/04/2022 17:44:34 - INFO - codeparrot_training - Step 24078: {'lr': 0.0004730448075822103, 'samples': 12328448, 'steps': 24078, 'loss/train': 2.0695934295654297}
-03/04/2022 17:44:35 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/04/2022 17:44:39 - INFO - codeparrot_training - Step 24079: {'lr': 0.0004730424105734576, 'samples': 12328960, 'steps': 24079, 'loss/train': 1.1796817779541016}
-03/04/2022 17:44:43 - INFO - codeparrot_training - Step 24080: {'lr': 0.00047304001346420543, 'samples': 12329472, 'steps': 24080, 'loss/train': 1.0936622619628906}
-03/04/2022 17:44:44 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 17:44:48 - INFO - codeparrot_training - Step 24081: {'lr': 0.0004730376162544549, 'samples': 12329984, 'steps': 24081, 'loss/train': 1.9510287046432495}
-03/04/2022 17:44:51 - INFO - codeparrot_training - Step 24082: {'lr': 0.00047303521894420707, 'samples': 12330496, 'steps': 24082, 'loss/train': 1.5031731128692627}
-03/04/2022 17:44:53 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 17:44:56 - INFO - codeparrot_training - Step 24083: {'lr': 0.00047303282153346297, 'samples': 12331008, 'steps': 24083, 'loss/train': 2.164016008377075}
-03/04/2022 17:45:00 - INFO - codeparrot_training - Step 24084: {'lr': 0.00047303042402222373, 'samples': 12331520, 'steps': 24084, 'loss/train': 1.9378501176834106}
-03/04/2022 17:45:01 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/04/2022 17:45:05 - INFO - codeparrot_training - Step 24085: {'lr': 0.00047302802641049045, 'samples': 12332032, 'steps': 24085, 'loss/train': 1.3063926696777344}
-03/04/2022 17:45:08 - INFO - codeparrot_training - Step 24086: {'lr': 0.00047302562869826415, 'samples': 12332544, 'steps': 24086, 'loss/train': 2.0311295986175537}
-03/04/2022 17:45:10 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/04/2022 17:45:13 - INFO - codeparrot_training - Step 24087: {'lr': 0.000473023230885546, 'samples': 12333056, 'steps': 24087, 'loss/train': 1.6284961700439453}
-03/04/2022 17:45:16 - INFO - codeparrot_training - Step 24088: {'lr': 0.00047302083297233693, 'samples': 12333568, 'steps': 24088, 'loss/train': 2.2828192710876465}
-03/04/2022 17:45:18 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 17:45:22 - INFO - codeparrot_training - Step 24089: {'lr': 0.0004730184349586382, 'samples': 12334080, 'steps': 24089, 'loss/train': 1.3438918590545654}
-03/04/2022 17:45:25 - INFO - codeparrot_training - Step 24090: {'lr': 0.0004730160368444507, 'samples': 12334592, 'steps': 24090, 'loss/train': 1.990256428718567}
-03/04/2022 17:45:26 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 17:45:30 - INFO - codeparrot_training - Step 24091: {'lr': 0.00047301363862977574, 'samples': 12335104, 'steps': 24091, 'loss/train': 1.713231086730957}
-03/04/2022 17:45:33 - INFO - codeparrot_training - Step 24092: {'lr': 0.00047301124031461425, 'samples': 12335616, 'steps': 24092, 'loss/train': 2.353463888168335}
-03/04/2022 17:45:35 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/04/2022 17:45:39 - INFO - codeparrot_training - Step 24093: {'lr': 0.00047300884189896734, 'samples': 12336128, 'steps': 24093, 'loss/train': 1.4828822612762451}
-03/04/2022 17:45:42 - INFO - codeparrot_training - Step 24094: {'lr': 0.00047300644338283597, 'samples': 12336640, 'steps': 24094, 'loss/train': 1.365534782409668}
-03/04/2022 17:45:43 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/04/2022 17:45:47 - INFO - codeparrot_training - Step 24095: {'lr': 0.00047300404476622145, 'samples': 12337152, 'steps': 24095, 'loss/train': 1.539475917816162}
-03/04/2022 17:45:50 - INFO - codeparrot_training - Step 24096: {'lr': 0.0004730016460491247, 'samples': 12337664, 'steps': 24096, 'loss/train': 1.6724570989608765}
-03/04/2022 17:45:52 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 17:45:55 - INFO - codeparrot_training - Step 24097: {'lr': 0.00047299924723154686, 'samples': 12338176, 'steps': 24097, 'loss/train': 1.4161325693130493}
-03/04/2022 17:45:59 - INFO - codeparrot_training - Step 24098: {'lr': 0.000472996848313489, 'samples': 12338688, 'steps': 24098, 'loss/train': 1.1850368976593018}
-03/04/2022 17:46:00 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 17:46:04 - INFO - codeparrot_training - Step 24099: {'lr': 0.0004729944492949523, 'samples': 12339200, 'steps': 24099, 'loss/train': 2.1958770751953125}
-03/04/2022 17:46:07 - INFO - codeparrot_training - Step 24100: {'lr': 0.0004729920501759376, 'samples': 12339712, 'steps': 24100, 'loss/train': 2.2872612476348877}
-03/04/2022 17:46:09 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/04/2022 17:46:12 - INFO - codeparrot_training - Step 24101: {'lr': 0.0004729896509564462, 'samples': 12340224, 'steps': 24101, 'loss/train': 1.0160070657730103}
-03/04/2022 17:46:16 - INFO - codeparrot_training - Step 24102: {'lr': 0.00047298725163647903, 'samples': 12340736, 'steps': 24102, 'loss/train': 1.6186915636062622}
-03/04/2022 17:46:17 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/04/2022 17:46:21 - INFO - codeparrot_training - Step 24103: {'lr': 0.00047298485221603735, 'samples': 12341248, 'steps': 24103, 'loss/train': 2.277391195297241}
-03/04/2022 17:46:24 - INFO - codeparrot_training - Step 24104: {'lr': 0.0004729824526951221, 'samples': 12341760, 'steps': 24104, 'loss/train': 1.1548101902008057}
-03/04/2022 17:46:25 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/04/2022 17:46:29 - INFO - codeparrot_training - Step 24105: {'lr': 0.0004729800530737344, 'samples': 12342272, 'steps': 24105, 'loss/train': 1.977251410484314}
-03/04/2022 17:46:32 - INFO - codeparrot_training - Step 24106: {'lr': 0.0004729776533518753, 'samples': 12342784, 'steps': 24106, 'loss/train': 1.1591229438781738}
-03/04/2022 17:46:34 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/04/2022 17:46:38 - INFO - codeparrot_training - Step 24107: {'lr': 0.00047297525352954587, 'samples': 12343296, 'steps': 24107, 'loss/train': 1.3035218715667725}
-03/04/2022 17:46:41 - INFO - codeparrot_training - Step 24108: {'lr': 0.00047297285360674724, 'samples': 12343808, 'steps': 24108, 'loss/train': 1.6273456811904907}
-03/04/2022 17:46:42 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 17:46:46 - INFO - codeparrot_training - Step 24109: {'lr': 0.0004729704535834806, 'samples': 12344320, 'steps': 24109, 'loss/train': 2.817026138305664}
-03/04/2022 17:46:49 - INFO - codeparrot_training - Step 24110: {'lr': 0.0004729680534597468, 'samples': 12344832, 'steps': 24110, 'loss/train': 1.8457839488983154}
-03/04/2022 17:46:51 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 17:46:55 - INFO - codeparrot_training - Step 24111: {'lr': 0.0004729656532355471, 'samples': 12345344, 'steps': 24111, 'loss/train': 2.2977142333984375}
-03/04/2022 17:46:58 - INFO - codeparrot_training - Step 24112: {'lr': 0.00047296325291088247, 'samples': 12345856, 'steps': 24112, 'loss/train': 0.9623086452484131}
-03/04/2022 17:46:59 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/04/2022 17:47:03 - INFO - codeparrot_training - Step 24113: {'lr': 0.00047296085248575405, 'samples': 12346368, 'steps': 24113, 'loss/train': 1.8958494663238525}
-03/04/2022 17:47:06 - INFO - codeparrot_training - Step 24114: {'lr': 0.000472958451960163, 'samples': 12346880, 'steps': 24114, 'loss/train': 1.454222559928894}
-03/04/2022 17:47:08 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/04/2022 17:47:11 - INFO - codeparrot_training - Step 24115: {'lr': 0.0004729560513341101, 'samples': 12347392, 'steps': 24115, 'loss/train': 1.0426387786865234}
-03/04/2022 17:47:15 - INFO - codeparrot_training - Step 24116: {'lr': 0.0004729536506075969, 'samples': 12347904, 'steps': 24116, 'loss/train': 2.1908011436462402}
-03/04/2022 17:47:16 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/04/2022 17:47:20 - INFO - codeparrot_training - Step 24117: {'lr': 0.000472951249780624, 'samples': 12348416, 'steps': 24117, 'loss/train': 1.8156861066818237}
-03/04/2022 17:47:23 - INFO - codeparrot_training - Step 24118: {'lr': 0.0004729488488531928, 'samples': 12348928, 'steps': 24118, 'loss/train': 1.1649701595306396}
-03/04/2022 17:47:25 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 17:47:28 - INFO - codeparrot_training - Step 24119: {'lr': 0.00047294644782530437, 'samples': 12349440, 'steps': 24119, 'loss/train': 1.635706901550293}
-03/04/2022 17:47:31 - INFO - codeparrot_training - Step 24120: {'lr': 0.0004729440466969596, 'samples': 12349952, 'steps': 24120, 'loss/train': 2.102741003036499}
-03/04/2022 17:47:33 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/04/2022 17:47:37 - INFO - codeparrot_training - Step 24121: {'lr': 0.00047294164546815977, 'samples': 12350464, 'steps': 24121, 'loss/train': 1.5973258018493652}
-03/04/2022 17:47:40 - INFO - codeparrot_training - Step 24122: {'lr': 0.0004729392441389058, 'samples': 12350976, 'steps': 24122, 'loss/train': 1.2368218898773193}
-03/04/2022 17:47:41 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/04/2022 17:47:45 - INFO - codeparrot_training - Step 24123: {'lr': 0.0004729368427091989, 'samples': 12351488, 'steps': 24123, 'loss/train': 1.6933103799819946}
-03/04/2022 17:47:48 - INFO - codeparrot_training - Step 24124: {'lr': 0.0004729344411790401, 'samples': 12352000, 'steps': 24124, 'loss/train': 1.779477596282959}
-03/04/2022 17:47:49 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/04/2022 17:47:53 - INFO - codeparrot_training - Step 24125: {'lr': 0.00047293203954843036, 'samples': 12352512, 'steps': 24125, 'loss/train': 2.0349197387695312}
-03/04/2022 17:47:57 - INFO - codeparrot_training - Step 24126: {'lr': 0.000472929637817371, 'samples': 12353024, 'steps': 24126, 'loss/train': 1.9012538194656372}
-03/04/2022 17:47:58 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/04/2022 17:48:02 - INFO - codeparrot_training - Step 24127: {'lr': 0.00047292723598586295, 'samples': 12353536, 'steps': 24127, 'loss/train': 1.712430477142334}
-03/04/2022 17:48:05 - INFO - codeparrot_training - Step 24128: {'lr': 0.0004729248340539074, 'samples': 12354048, 'steps': 24128, 'loss/train': 1.263621211051941}
-03/04/2022 17:48:07 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/04/2022 17:48:11 - INFO - codeparrot_training - Step 24129: {'lr': 0.00047292243202150524, 'samples': 12354560, 'steps': 24129, 'loss/train': 2.3800225257873535}
-03/04/2022 17:48:14 - INFO - codeparrot_training - Step 24130: {'lr': 0.00047292002988865773, 'samples': 12355072, 'steps': 24130, 'loss/train': 1.3819352388381958}
-03/04/2022 17:48:17 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 17:48:19 - INFO - codeparrot_training - Step 24131: {'lr': 0.0004729176276553659, 'samples': 12355584, 'steps': 24131, 'loss/train': 1.6979447603225708}
-03/04/2022 17:48:23 - INFO - codeparrot_training - Step 24132: {'lr': 0.00047291522532163084, 'samples': 12356096, 'steps': 24132, 'loss/train': 2.4203293323516846}
-03/04/2022 17:48:26 - INFO - codeparrot_training - Step 24133: {'lr': 0.0004729128228874536, 'samples': 12356608, 'steps': 24133, 'loss/train': 1.396500587463379}
-03/04/2022 17:48:26 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 17:48:31 - INFO - codeparrot_training - Step 24134: {'lr': 0.0004729104203528353, 'samples': 12357120, 'steps': 24134, 'loss/train': 1.724676489830017}
-03/04/2022 17:48:34 - INFO - codeparrot_training - Step 24135: {'lr': 0.0004729080177177769, 'samples': 12357632, 'steps': 24135, 'loss/train': 1.9641534090042114}
-03/04/2022 17:48:35 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 17:48:40 - INFO - codeparrot_training - Step 24136: {'lr': 0.0004729056149822797, 'samples': 12358144, 'steps': 24136, 'loss/train': 2.251063585281372}
-03/04/2022 17:48:43 - INFO - codeparrot_training - Step 24137: {'lr': 0.0004729032121463447, 'samples': 12358656, 'steps': 24137, 'loss/train': 1.8379000425338745}
-03/04/2022 17:48:43 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/04/2022 17:48:48 - INFO - codeparrot_training - Step 24138: {'lr': 0.00047290080920997285, 'samples': 12359168, 'steps': 24138, 'loss/train': 1.8562967777252197}
-03/04/2022 17:48:51 - INFO - codeparrot_training - Step 24139: {'lr': 0.0004728984061731654, 'samples': 12359680, 'steps': 24139, 'loss/train': 1.772022008895874}
-03/04/2022 17:48:52 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/04/2022 17:48:57 - INFO - codeparrot_training - Step 24140: {'lr': 0.00047289600303592334, 'samples': 12360192, 'steps': 24140, 'loss/train': 2.4628498554229736}
-03/04/2022 17:49:00 - INFO - codeparrot_training - Step 24141: {'lr': 0.00047289359979824774, 'samples': 12360704, 'steps': 24141, 'loss/train': 1.763590693473816}
-03/04/2022 17:49:01 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/04/2022 17:49:05 - INFO - codeparrot_training - Step 24142: {'lr': 0.0004728911964601398, 'samples': 12361216, 'steps': 24142, 'loss/train': 0.7303640842437744}
-03/04/2022 17:49:08 - INFO - codeparrot_training - Step 24143: {'lr': 0.00047288879302160046, 'samples': 12361728, 'steps': 24143, 'loss/train': 2.0565216541290283}
-03/04/2022 17:49:09 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/04/2022 17:49:14 - INFO - codeparrot_training - Step 24144: {'lr': 0.000472886389482631, 'samples': 12362240, 'steps': 24144, 'loss/train': 2.1034488677978516}
-03/04/2022 17:49:17 - INFO - codeparrot_training - Step 24145: {'lr': 0.00047288398584323225, 'samples': 12362752, 'steps': 24145, 'loss/train': 1.5689754486083984}
-03/04/2022 17:49:18 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/04/2022 17:49:22 - INFO - codeparrot_training - Step 24146: {'lr': 0.0004728815821034055, 'samples': 12363264, 'steps': 24146, 'loss/train': 1.4876484870910645}
-03/04/2022 17:49:25 - INFO - codeparrot_training - Step 24147: {'lr': 0.00047287917826315163, 'samples': 12363776, 'steps': 24147, 'loss/train': 2.3330321311950684}
-03/04/2022 17:49:26 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/04/2022 17:49:30 - INFO - codeparrot_training - Step 24148: {'lr': 0.00047287677432247187, 'samples': 12364288, 'steps': 24148, 'loss/train': 1.0961991548538208}
-03/04/2022 17:49:34 - INFO - codeparrot_training - Step 24149: {'lr': 0.0004728743702813674, 'samples': 12364800, 'steps': 24149, 'loss/train': 2.125617504119873}
-03/04/2022 17:49:35 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 17:49:39 - INFO - codeparrot_training - Step 24150: {'lr': 0.00047287196613983906, 'samples': 12365312, 'steps': 24150, 'loss/train': 1.4978234767913818}
-03/04/2022 17:49:42 - INFO - codeparrot_training - Step 24151: {'lr': 0.00047286956189788803, 'samples': 12365824, 'steps': 24151, 'loss/train': 2.1263692378997803}
-03/04/2022 17:49:43 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 17:49:47 - INFO - codeparrot_training - Step 24152: {'lr': 0.0004728671575555155, 'samples': 12366336, 'steps': 24152, 'loss/train': 2.7224557399749756}
-03/04/2022 17:49:51 - INFO - codeparrot_training - Step 24153: {'lr': 0.00047286475311272244, 'samples': 12366848, 'steps': 24153, 'loss/train': 1.6270722150802612}
-03/04/2022 17:49:52 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/04/2022 17:49:56 - INFO - codeparrot_training - Step 24154: {'lr': 0.00047286234856950995, 'samples': 12367360, 'steps': 24154, 'loss/train': 0.6083402633666992}
-03/04/2022 17:49:59 - INFO - codeparrot_training - Step 24155: {'lr': 0.0004728599439258791, 'samples': 12367872, 'steps': 24155, 'loss/train': 1.332889437675476}
-03/04/2022 17:50:01 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 17:50:04 - INFO - codeparrot_training - Step 24156: {'lr': 0.00047285753918183105, 'samples': 12368384, 'steps': 24156, 'loss/train': 2.27038311958313}
-03/04/2022 17:50:07 - INFO - codeparrot_training - Step 24157: {'lr': 0.0004728551343373668, 'samples': 12368896, 'steps': 24157, 'loss/train': 0.8916676044464111}
-03/04/2022 17:50:09 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/04/2022 17:50:13 - INFO - codeparrot_training - Step 24158: {'lr': 0.0004728527293924875, 'samples': 12369408, 'steps': 24158, 'loss/train': 2.1318705081939697}
-03/04/2022 17:50:16 - INFO - codeparrot_training - Step 24159: {'lr': 0.0004728503243471941, 'samples': 12369920, 'steps': 24159, 'loss/train': 1.942136287689209}
-03/04/2022 17:50:18 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/04/2022 17:50:21 - INFO - codeparrot_training - Step 24160: {'lr': 0.00047284791920148786, 'samples': 12370432, 'steps': 24160, 'loss/train': 1.8322309255599976}
-03/04/2022 17:50:24 - INFO - codeparrot_training - Step 24161: {'lr': 0.0004728455139553698, 'samples': 12370944, 'steps': 24161, 'loss/train': 2.179103136062622}
-03/04/2022 17:50:27 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/04/2022 17:50:30 - INFO - codeparrot_training - Step 24162: {'lr': 0.00047284310860884097, 'samples': 12371456, 'steps': 24162, 'loss/train': 2.1942903995513916}
-03/04/2022 17:50:33 - INFO - codeparrot_training - Step 24163: {'lr': 0.0004728407031619025, 'samples': 12371968, 'steps': 24163, 'loss/train': 1.5318578481674194}
-03/04/2022 17:50:35 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/04/2022 17:50:38 - INFO - codeparrot_training - Step 24164: {'lr': 0.00047283829761455545, 'samples': 12372480, 'steps': 24164, 'loss/train': 1.6229345798492432}
-03/04/2022 17:50:41 - INFO - codeparrot_training - Step 24165: {'lr': 0.00047283589196680083, 'samples': 12372992, 'steps': 24165, 'loss/train': 1.9523741006851196}
-03/04/2022 17:50:44 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/04/2022 17:50:47 - INFO - codeparrot_training - Step 24166: {'lr': 0.00047283348621863987, 'samples': 12373504, 'steps': 24166, 'loss/train': 2.51261043548584}
-03/04/2022 17:50:50 - INFO - codeparrot_training - Step 24167: {'lr': 0.0004728310803700735, 'samples': 12374016, 'steps': 24167, 'loss/train': 1.9374743700027466}
-03/04/2022 17:50:52 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 17:50:55 - INFO - codeparrot_training - Step 24168: {'lr': 0.00047282867442110296, 'samples': 12374528, 'steps': 24168, 'loss/train': 2.0913774967193604}
-03/04/2022 17:50:58 - INFO - codeparrot_training - Step 24169: {'lr': 0.0004728262683717292, 'samples': 12375040, 'steps': 24169, 'loss/train': 1.3591228723526}
-03/04/2022 17:51:01 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/04/2022 17:51:03 - INFO - codeparrot_training - Step 24170: {'lr': 0.0004728238622219534, 'samples': 12375552, 'steps': 24170, 'loss/train': 1.3195126056671143}
-03/04/2022 17:51:07 - INFO - codeparrot_training - Step 24171: {'lr': 0.0004728214559717766, 'samples': 12376064, 'steps': 24171, 'loss/train': 1.9557253122329712}
-03/04/2022 17:51:09 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 17:51:12 - INFO - codeparrot_training - Step 24172: {'lr': 0.0004728190496211999, 'samples': 12376576, 'steps': 24172, 'loss/train': 2.031425952911377}
-03/04/2022 17:51:15 - INFO - codeparrot_training - Step 24173: {'lr': 0.0004728166431702243, 'samples': 12377088, 'steps': 24173, 'loss/train': 2.1004862785339355}
-03/04/2022 17:51:18 - INFO - codeparrot_training - Step 24174: {'lr': 0.0004728142366188511, 'samples': 12377600, 'steps': 24174, 'loss/train': 1.667949914932251}
-03/04/2022 17:51:19 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 17:51:24 - INFO - codeparrot_training - Step 24175: {'lr': 0.0004728118299670812, 'samples': 12378112, 'steps': 24175, 'loss/train': 1.277051329612732}
-03/04/2022 17:51:27 - INFO - codeparrot_training - Step 24176: {'lr': 0.0004728094232149156, 'samples': 12378624, 'steps': 24176, 'loss/train': 1.111968755722046}
-03/04/2022 17:51:27 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 17:51:32 - INFO - codeparrot_training - Step 24177: {'lr': 0.0004728070163623557, 'samples': 12379136, 'steps': 24177, 'loss/train': 2.2291765213012695}
-03/04/2022 17:51:35 - INFO - codeparrot_training - Step 24178: {'lr': 0.00047280460940940224, 'samples': 12379648, 'steps': 24178, 'loss/train': 1.8652911186218262}
-03/04/2022 17:51:35 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 17:51:40 - INFO - codeparrot_training - Step 24179: {'lr': 0.00047280220235605653, 'samples': 12380160, 'steps': 24179, 'loss/train': 1.82382071018219}
-03/04/2022 17:51:44 - INFO - codeparrot_training - Step 24180: {'lr': 0.00047279979520231956, 'samples': 12380672, 'steps': 24180, 'loss/train': 0.9858987331390381}
-03/04/2022 17:51:44 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 17:51:49 - INFO - codeparrot_training - Step 24181: {'lr': 0.0004727973879481925, 'samples': 12381184, 'steps': 24181, 'loss/train': 6.967962265014648}
-03/04/2022 17:51:52 - INFO - codeparrot_training - Step 24182: {'lr': 0.0004727949805936763, 'samples': 12381696, 'steps': 24182, 'loss/train': 1.5779021978378296}
-03/04/2022 17:51:53 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/04/2022 17:51:57 - INFO - codeparrot_training - Step 24183: {'lr': 0.00047279257313877216, 'samples': 12382208, 'steps': 24183, 'loss/train': 1.7934304475784302}
-03/04/2022 17:52:00 - INFO - codeparrot_training - Step 24184: {'lr': 0.00047279016558348107, 'samples': 12382720, 'steps': 24184, 'loss/train': 2.243180513381958}
-03/04/2022 17:52:02 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/04/2022 17:52:06 - INFO - codeparrot_training - Step 24185: {'lr': 0.00047278775792780424, 'samples': 12383232, 'steps': 24185, 'loss/train': 1.7482424974441528}
-03/04/2022 17:52:09 - INFO - codeparrot_training - Step 24186: {'lr': 0.00047278535017174266, 'samples': 12383744, 'steps': 24186, 'loss/train': 1.3965650796890259}
-03/04/2022 17:52:10 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/04/2022 17:52:14 - INFO - codeparrot_training - Step 24187: {'lr': 0.00047278294231529745, 'samples': 12384256, 'steps': 24187, 'loss/train': 1.8189219236373901}
-03/04/2022 17:52:17 - INFO - codeparrot_training - Step 24188: {'lr': 0.0004727805343584697, 'samples': 12384768, 'steps': 24188, 'loss/train': 2.2225255966186523}
-03/04/2022 17:52:19 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 17:52:23 - INFO - codeparrot_training - Step 24189: {'lr': 0.00047277812630126044, 'samples': 12385280, 'steps': 24189, 'loss/train': 0.787157416343689}
-03/04/2022 17:52:26 - INFO - codeparrot_training - Step 24190: {'lr': 0.0004727757181436708, 'samples': 12385792, 'steps': 24190, 'loss/train': 1.96137273311615}
-03/04/2022 17:52:27 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/04/2022 17:52:31 - INFO - codeparrot_training - Step 24191: {'lr': 0.0004727733098857019, 'samples': 12386304, 'steps': 24191, 'loss/train': 1.1898096799850464}
-03/04/2022 17:52:34 - INFO - codeparrot_training - Step 24192: {'lr': 0.0004727709015273547, 'samples': 12386816, 'steps': 24192, 'loss/train': 1.6955680847167969}
-03/04/2022 17:52:36 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/04/2022 17:52:40 - INFO - codeparrot_training - Step 24193: {'lr': 0.00047276849306863045, 'samples': 12387328, 'steps': 24193, 'loss/train': 1.356069564819336}
-03/04/2022 17:52:43 - INFO - codeparrot_training - Step 24194: {'lr': 0.0004727660845095301, 'samples': 12387840, 'steps': 24194, 'loss/train': 0.5605583190917969}
-03/04/2022 17:52:46 - INFO - codeparrot_training - Step 24195: {'lr': 0.0004727636758500548, 'samples': 12388352, 'steps': 24195, 'loss/train': 1.6826062202453613}
-03/04/2022 17:52:48 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/04/2022 17:52:52 - INFO - codeparrot_training - Step 24196: {'lr': 0.0004727612670902057, 'samples': 12388864, 'steps': 24196, 'loss/train': 2.06768536567688}
-03/04/2022 17:52:55 - INFO - codeparrot_training - Step 24197: {'lr': 0.0004727588582299837, 'samples': 12389376, 'steps': 24197, 'loss/train': 1.405544400215149}
-03/04/2022 17:52:57 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/04/2022 17:53:00 - INFO - codeparrot_training - Step 24198: {'lr': 0.00047275644926939004, 'samples': 12389888, 'steps': 24198, 'loss/train': 2.158219575881958}
-03/04/2022 17:53:04 - INFO - codeparrot_training - Step 24199: {'lr': 0.0004727540402084258, 'samples': 12390400, 'steps': 24199, 'loss/train': 1.8030403852462769}
-03/04/2022 17:53:06 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 17:53:09 - INFO - codeparrot_training - Step 24200: {'lr': 0.00047275163104709196, 'samples': 12390912, 'steps': 24200, 'loss/train': 2.058849334716797}
-03/04/2022 17:53:12 - INFO - codeparrot_training - Step 24201: {'lr': 0.0004727492217853897, 'samples': 12391424, 'steps': 24201, 'loss/train': 1.6077334880828857}
-03/04/2022 17:53:14 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/04/2022 17:53:17 - INFO - codeparrot_training - Step 24202: {'lr': 0.0004727468124233201, 'samples': 12391936, 'steps': 24202, 'loss/train': 1.2564737796783447}
-03/04/2022 17:53:21 - INFO - codeparrot_training - Step 24203: {'lr': 0.0004727444029608842, 'samples': 12392448, 'steps': 24203, 'loss/train': 1.886802077293396}
-03/04/2022 17:53:23 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/04/2022 17:53:26 - INFO - codeparrot_training - Step 24204: {'lr': 0.0004727419933980831, 'samples': 12392960, 'steps': 24204, 'loss/train': 0.9463183283805847}
-03/04/2022 17:53:29 - INFO - codeparrot_training - Step 24205: {'lr': 0.00047273958373491795, 'samples': 12393472, 'steps': 24205, 'loss/train': 2.2054271697998047}
-03/04/2022 17:53:31 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/04/2022 17:53:34 - INFO - codeparrot_training - Step 24206: {'lr': 0.0004727371739713897, 'samples': 12393984, 'steps': 24206, 'loss/train': 1.0134239196777344}
-03/04/2022 17:53:38 - INFO - codeparrot_training - Step 24207: {'lr': 0.0004727347641074996, 'samples': 12394496, 'steps': 24207, 'loss/train': 1.611152172088623}
-03/04/2022 17:53:40 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/04/2022 17:53:43 - INFO - codeparrot_training - Step 24208: {'lr': 0.0004727323541432486, 'samples': 12395008, 'steps': 24208, 'loss/train': 1.29292893409729}
-03/04/2022 17:53:46 - INFO - codeparrot_training - Step 24209: {'lr': 0.0004727299440786378, 'samples': 12395520, 'steps': 24209, 'loss/train': 1.5374947786331177}
-03/04/2022 17:53:48 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/04/2022 17:53:51 - INFO - codeparrot_training - Step 24210: {'lr': 0.0004727275339136684, 'samples': 12396032, 'steps': 24210, 'loss/train': 0.5444936752319336}
-03/04/2022 17:53:54 - INFO - codeparrot_training - Step 24211: {'lr': 0.0004727251236483414, 'samples': 12396544, 'steps': 24211, 'loss/train': 2.217684268951416}
-03/04/2022 17:53:57 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/04/2022 17:54:00 - INFO - codeparrot_training - Step 24212: {'lr': 0.0004727227132826579, 'samples': 12397056, 'steps': 24212, 'loss/train': 2.098790407180786}
-03/04/2022 17:54:03 - INFO - codeparrot_training - Step 24213: {'lr': 0.00047272030281661894, 'samples': 12397568, 'steps': 24213, 'loss/train': 1.6188281774520874}
-03/04/2022 17:54:05 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 17:54:08 - INFO - codeparrot_training - Step 24214: {'lr': 0.0004727178922502257, 'samples': 12398080, 'steps': 24214, 'loss/train': 1.2367664575576782}
-03/04/2022 17:54:11 - INFO - codeparrot_training - Step 24215: {'lr': 0.00047271548158347917, 'samples': 12398592, 'steps': 24215, 'loss/train': 1.5913017988204956}
-03/04/2022 17:54:14 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/04/2022 17:54:17 - INFO - codeparrot_training - Step 24216: {'lr': 0.00047271307081638047, 'samples': 12399104, 'steps': 24216, 'loss/train': 1.8503285646438599}
-03/04/2022 17:54:20 - INFO - codeparrot_training - Step 24217: {'lr': 0.0004727106599489307, 'samples': 12399616, 'steps': 24217, 'loss/train': 2.405428886413574}
-03/04/2022 17:54:22 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 17:54:25 - INFO - codeparrot_training - Step 24218: {'lr': 0.000472708248981131, 'samples': 12400128, 'steps': 24218, 'loss/train': 1.2816799879074097}
-03/04/2022 17:54:28 - INFO - codeparrot_training - Step 24219: {'lr': 0.0004727058379129824, 'samples': 12400640, 'steps': 24219, 'loss/train': 0.7940981388092041}
-03/04/2022 17:54:34 - INFO - codeparrot_training - Step 24220: {'lr': 0.00047270342674448593, 'samples': 12401152, 'steps': 24220, 'loss/train': 1.9487758874893188}
-03/04/2022 17:54:37 - INFO - codeparrot_training - Step 24221: {'lr': 0.0004727010154756427, 'samples': 12401664, 'steps': 24221, 'loss/train': 2.4605300426483154}
-03/04/2022 17:54:39 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/04/2022 17:54:42 - INFO - codeparrot_training - Step 24222: {'lr': 0.00047269860410645395, 'samples': 12402176, 'steps': 24222, 'loss/train': 1.4327507019042969}
-03/04/2022 17:54:45 - INFO - codeparrot_training - Step 24223: {'lr': 0.00047269619263692056, 'samples': 12402688, 'steps': 24223, 'loss/train': 1.8794963359832764}
-03/04/2022 17:54:47 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/04/2022 17:54:51 - INFO - codeparrot_training - Step 24224: {'lr': 0.0004726937810670437, 'samples': 12403200, 'steps': 24224, 'loss/train': 2.1202423572540283}
-03/04/2022 17:54:54 - INFO - codeparrot_training - Step 24225: {'lr': 0.00047269136939682445, 'samples': 12403712, 'steps': 24225, 'loss/train': 1.8469197750091553}
-03/04/2022 17:54:56 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/04/2022 17:54:59 - INFO - codeparrot_training - Step 24226: {'lr': 0.00047268895762626396, 'samples': 12404224, 'steps': 24226, 'loss/train': 2.1769583225250244}
-03/04/2022 17:55:02 - INFO - codeparrot_training - Step 24227: {'lr': 0.00047268654575536326, 'samples': 12404736, 'steps': 24227, 'loss/train': 1.6712318658828735}
-03/04/2022 17:55:04 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/04/2022 17:55:08 - INFO - codeparrot_training - Step 24228: {'lr': 0.0004726841337841234, 'samples': 12405248, 'steps': 24228, 'loss/train': 1.8083689212799072}
-03/04/2022 17:55:11 - INFO - codeparrot_training - Step 24229: {'lr': 0.00047268172171254554, 'samples': 12405760, 'steps': 24229, 'loss/train': 1.786656379699707}
-03/04/2022 17:55:14 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 17:55:16 - INFO - codeparrot_training - Step 24230: {'lr': 0.00047267930954063064, 'samples': 12406272, 'steps': 24230, 'loss/train': 1.7426141500473022}
-03/04/2022 17:55:19 - INFO - codeparrot_training - Step 24231: {'lr': 0.00047267689726838004, 'samples': 12406784, 'steps': 24231, 'loss/train': 2.165428400039673}
-03/04/2022 17:55:23 - INFO - codeparrot_training - Step 24232: {'lr': 0.00047267448489579455, 'samples': 12407296, 'steps': 24232, 'loss/train': 1.243091106414795}
-03/04/2022 17:55:23 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/04/2022 17:55:28 - INFO - codeparrot_training - Step 24233: {'lr': 0.00047267207242287536, 'samples': 12407808, 'steps': 24233, 'loss/train': 1.6409904956817627}
-03/04/2022 17:55:31 - INFO - codeparrot_training - Step 24234: {'lr': 0.0004726696598496236, 'samples': 12408320, 'steps': 24234, 'loss/train': 3.0037033557891846}
-03/04/2022 17:55:32 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 17:55:36 - INFO - codeparrot_training - Step 24235: {'lr': 0.0004726672471760404, 'samples': 12408832, 'steps': 24235, 'loss/train': 1.533087968826294}
-03/04/2022 17:55:40 - INFO - codeparrot_training - Step 24236: {'lr': 0.0004726648344021267, 'samples': 12409344, 'steps': 24236, 'loss/train': 1.656006932258606}
-03/04/2022 17:55:40 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 17:55:45 - INFO - codeparrot_training - Step 24237: {'lr': 0.0004726624215278836, 'samples': 12409856, 'steps': 24237, 'loss/train': 2.3111319541931152}
-03/04/2022 17:55:48 - INFO - codeparrot_training - Step 24238: {'lr': 0.0004726600085533124, 'samples': 12410368, 'steps': 24238, 'loss/train': 2.4196877479553223}
-03/04/2022 17:55:49 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 17:55:53 - INFO - codeparrot_training - Step 24239: {'lr': 0.0004726575954784139, 'samples': 12410880, 'steps': 24239, 'loss/train': 1.694189190864563}
-03/04/2022 17:55:56 - INFO - codeparrot_training - Step 24240: {'lr': 0.0004726551823031894, 'samples': 12411392, 'steps': 24240, 'loss/train': 2.8977043628692627}
-03/04/2022 17:55:57 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/04/2022 17:56:02 - INFO - codeparrot_training - Step 24241: {'lr': 0.0004726527690276399, 'samples': 12411904, 'steps': 24241, 'loss/train': 1.1131377220153809}
-03/04/2022 17:56:05 - INFO - codeparrot_training - Step 24242: {'lr': 0.0004726503556517665, 'samples': 12412416, 'steps': 24242, 'loss/train': 1.5966359376907349}
-03/04/2022 17:56:05 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 17:56:10 - INFO - codeparrot_training - Step 24243: {'lr': 0.0004726479421755703, 'samples': 12412928, 'steps': 24243, 'loss/train': 1.7151087522506714}
-03/04/2022 17:56:13 - INFO - codeparrot_training - Step 24244: {'lr': 0.0004726455285990523, 'samples': 12413440, 'steps': 24244, 'loss/train': 1.148912787437439}
-03/04/2022 17:56:14 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 17:56:18 - INFO - codeparrot_training - Step 24245: {'lr': 0.00047264311492221375, 'samples': 12413952, 'steps': 24245, 'loss/train': 1.2204225063323975}
-03/04/2022 17:56:22 - INFO - codeparrot_training - Step 24246: {'lr': 0.00047264070114505556, 'samples': 12414464, 'steps': 24246, 'loss/train': 1.3114022016525269}
-03/04/2022 17:56:22 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/04/2022 17:56:27 - INFO - codeparrot_training - Step 24247: {'lr': 0.00047263828726757897, 'samples': 12414976, 'steps': 24247, 'loss/train': 1.5454684495925903}
-03/04/2022 17:56:30 - INFO - codeparrot_training - Step 24248: {'lr': 0.00047263587328978495, 'samples': 12415488, 'steps': 24248, 'loss/train': 1.6634445190429688}
-03/04/2022 17:56:30 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 17:56:35 - INFO - codeparrot_training - Step 24249: {'lr': 0.00047263345921167473, 'samples': 12416000, 'steps': 24249, 'loss/train': 3.235689640045166}
-03/04/2022 17:56:39 - INFO - codeparrot_training - Step 24250: {'lr': 0.00047263104503324926, 'samples': 12416512, 'steps': 24250, 'loss/train': 1.3774714469909668}
-03/04/2022 17:56:39 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 17:56:44 - INFO - codeparrot_training - Step 24251: {'lr': 0.00047262863075450966, 'samples': 12417024, 'steps': 24251, 'loss/train': 2.329606533050537}
-03/04/2022 17:56:47 - INFO - codeparrot_training - Step 24252: {'lr': 0.0004726262163754571, 'samples': 12417536, 'steps': 24252, 'loss/train': 0.966454803943634}
-03/04/2022 17:56:48 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/04/2022 17:56:52 - INFO - codeparrot_training - Step 24253: {'lr': 0.00047262380189609253, 'samples': 12418048, 'steps': 24253, 'loss/train': 1.990532636642456}
-03/04/2022 17:56:55 - INFO - codeparrot_training - Step 24254: {'lr': 0.0004726213873164171, 'samples': 12418560, 'steps': 24254, 'loss/train': 1.827122449874878}
-03/04/2022 17:56:56 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 17:57:01 - INFO - codeparrot_training - Step 24255: {'lr': 0.00047261897263643196, 'samples': 12419072, 'steps': 24255, 'loss/train': 2.008157968521118}
-03/04/2022 17:57:04 - INFO - codeparrot_training - Step 24256: {'lr': 0.0004726165578561381, 'samples': 12419584, 'steps': 24256, 'loss/train': 1.4422613382339478}
-03/04/2022 17:57:05 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/04/2022 17:57:09 - INFO - codeparrot_training - Step 24257: {'lr': 0.0004726141429755367, 'samples': 12420096, 'steps': 24257, 'loss/train': 2.193883180618286}
-03/04/2022 17:57:12 - INFO - codeparrot_training - Step 24258: {'lr': 0.0004726117279946288, 'samples': 12420608, 'steps': 24258, 'loss/train': 1.925605058670044}
-03/04/2022 17:57:13 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/04/2022 17:57:18 - INFO - codeparrot_training - Step 24259: {'lr': 0.0004726093129134155, 'samples': 12421120, 'steps': 24259, 'loss/train': 1.809482455253601}
-03/04/2022 17:57:21 - INFO - codeparrot_training - Step 24260: {'lr': 0.0004726068977318978, 'samples': 12421632, 'steps': 24260, 'loss/train': 2.085036516189575}
-03/04/2022 17:57:22 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/04/2022 17:57:26 - INFO - codeparrot_training - Step 24261: {'lr': 0.0004726044824500769, 'samples': 12422144, 'steps': 24261, 'loss/train': 1.197949767112732}
-03/04/2022 17:57:29 - INFO - codeparrot_training - Step 24262: {'lr': 0.0004726020670679538, 'samples': 12422656, 'steps': 24262, 'loss/train': 1.528116226196289}
-03/04/2022 17:57:30 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/04/2022 17:57:35 - INFO - codeparrot_training - Step 24263: {'lr': 0.00047259965158552976, 'samples': 12423168, 'steps': 24263, 'loss/train': 2.322021722793579}
-03/04/2022 17:57:38 - INFO - codeparrot_training - Step 24264: {'lr': 0.00047259723600280573, 'samples': 12423680, 'steps': 24264, 'loss/train': 2.0564043521881104}
-03/04/2022 17:57:38 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 17:57:43 - INFO - codeparrot_training - Step 24265: {'lr': 0.0004725948203197828, 'samples': 12424192, 'steps': 24265, 'loss/train': 2.2129111289978027}
-03/04/2022 17:57:46 - INFO - codeparrot_training - Step 24266: {'lr': 0.0004725924045364621, 'samples': 12424704, 'steps': 24266, 'loss/train': 2.3588967323303223}
-03/04/2022 17:57:47 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/04/2022 17:57:51 - INFO - codeparrot_training - Step 24267: {'lr': 0.00047258998865284463, 'samples': 12425216, 'steps': 24267, 'loss/train': 2.0209569931030273}
-03/04/2022 17:57:55 - INFO - codeparrot_training - Step 24268: {'lr': 0.0004725875726689316, 'samples': 12425728, 'steps': 24268, 'loss/train': 1.6326833963394165}
-03/04/2022 17:57:55 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 17:58:00 - INFO - codeparrot_training - Step 24269: {'lr': 0.000472585156584724, 'samples': 12426240, 'steps': 24269, 'loss/train': 1.5918077230453491}
-03/04/2022 17:58:03 - INFO - codeparrot_training - Step 24270: {'lr': 0.00047258274040022305, 'samples': 12426752, 'steps': 24270, 'loss/train': 2.1289052963256836}
-03/04/2022 17:58:04 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 17:58:08 - INFO - codeparrot_training - Step 24271: {'lr': 0.0004725803241154297, 'samples': 12427264, 'steps': 24271, 'loss/train': 1.4785586595535278}
-03/04/2022 17:58:12 - INFO - codeparrot_training - Step 24272: {'lr': 0.0004725779077303451, 'samples': 12427776, 'steps': 24272, 'loss/train': 2.4786362648010254}
-03/04/2022 17:58:13 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 17:58:17 - INFO - codeparrot_training - Step 24273: {'lr': 0.0004725754912449703, 'samples': 12428288, 'steps': 24273, 'loss/train': 1.2445313930511475}
-03/04/2022 17:58:20 - INFO - codeparrot_training - Step 24274: {'lr': 0.0004725730746593064, 'samples': 12428800, 'steps': 24274, 'loss/train': 1.2462815046310425}
-03/04/2022 17:58:21 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 17:58:25 - INFO - codeparrot_training - Step 24275: {'lr': 0.0004725706579733546, 'samples': 12429312, 'steps': 24275, 'loss/train': 1.4222785234451294}
-03/04/2022 17:58:29 - INFO - codeparrot_training - Step 24276: {'lr': 0.00047256824118711583, 'samples': 12429824, 'steps': 24276, 'loss/train': 3.2636332511901855}
-03/04/2022 17:58:30 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 17:58:34 - INFO - codeparrot_training - Step 24277: {'lr': 0.00047256582430059126, 'samples': 12430336, 'steps': 24277, 'loss/train': 1.9199249744415283}
-03/04/2022 17:58:37 - INFO - codeparrot_training - Step 24278: {'lr': 0.00047256340731378194, 'samples': 12430848, 'steps': 24278, 'loss/train': 1.3929206132888794}
-03/04/2022 17:58:38 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/04/2022 17:58:42 - INFO - codeparrot_training - Step 24279: {'lr': 0.00047256099022668896, 'samples': 12431360, 'steps': 24279, 'loss/train': 1.118316411972046}
-03/04/2022 17:58:46 - INFO - codeparrot_training - Step 24280: {'lr': 0.00047255857303931347, 'samples': 12431872, 'steps': 24280, 'loss/train': 1.2074640989303589}
-03/04/2022 17:58:47 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/04/2022 17:58:51 - INFO - codeparrot_training - Step 24281: {'lr': 0.00047255615575165653, 'samples': 12432384, 'steps': 24281, 'loss/train': 2.0333824157714844}
-03/04/2022 17:58:54 - INFO - codeparrot_training - Step 24282: {'lr': 0.0004725537383637193, 'samples': 12432896, 'steps': 24282, 'loss/train': 1.473068118095398}
-03/04/2022 17:58:55 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/04/2022 17:58:59 - INFO - codeparrot_training - Step 24283: {'lr': 0.0004725513208755027, 'samples': 12433408, 'steps': 24283, 'loss/train': 1.9178364276885986}
-03/04/2022 17:59:02 - INFO - codeparrot_training - Step 24284: {'lr': 0.0004725489032870079, 'samples': 12433920, 'steps': 24284, 'loss/train': 1.0104693174362183}
-03/04/2022 17:59:04 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/04/2022 17:59:08 - INFO - codeparrot_training - Step 24285: {'lr': 0.000472546485598236, 'samples': 12434432, 'steps': 24285, 'loss/train': 1.3684591054916382}
-03/04/2022 17:59:11 - INFO - codeparrot_training - Step 24286: {'lr': 0.0004725440678091881, 'samples': 12434944, 'steps': 24286, 'loss/train': 1.81865394115448}
-03/04/2022 17:59:12 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 17:59:16 - INFO - codeparrot_training - Step 24287: {'lr': 0.00047254164991986525, 'samples': 12435456, 'steps': 24287, 'loss/train': 1.9759001731872559}
-03/04/2022 17:59:19 - INFO - codeparrot_training - Step 24288: {'lr': 0.0004725392319302686, 'samples': 12435968, 'steps': 24288, 'loss/train': 0.8127661943435669}
-03/04/2022 17:59:21 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 17:59:25 - INFO - codeparrot_training - Step 24289: {'lr': 0.0004725368138403992, 'samples': 12436480, 'steps': 24289, 'loss/train': 1.5502636432647705}
-03/04/2022 17:59:28 - INFO - codeparrot_training - Step 24290: {'lr': 0.00047253439565025815, 'samples': 12436992, 'steps': 24290, 'loss/train': 2.0844812393188477}
-03/04/2022 17:59:29 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 17:59:33 - INFO - codeparrot_training - Step 24291: {'lr': 0.00047253197735984653, 'samples': 12437504, 'steps': 24291, 'loss/train': 1.2805588245391846}
-03/04/2022 17:59:36 - INFO - codeparrot_training - Step 24292: {'lr': 0.00047252955896916546, 'samples': 12438016, 'steps': 24292, 'loss/train': 2.0271823406219482}
-03/04/2022 17:59:38 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/04/2022 17:59:41 - INFO - codeparrot_training - Step 24293: {'lr': 0.000472527140478216, 'samples': 12438528, 'steps': 24293, 'loss/train': 1.4711685180664062}
-03/04/2022 17:59:45 - INFO - codeparrot_training - Step 24294: {'lr': 0.00047252472188699917, 'samples': 12439040, 'steps': 24294, 'loss/train': 1.8819751739501953}
-03/04/2022 17:59:46 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 17:59:50 - INFO - codeparrot_training - Step 24295: {'lr': 0.0004725223031955162, 'samples': 12439552, 'steps': 24295, 'loss/train': 1.436058521270752}
-03/04/2022 17:59:53 - INFO - codeparrot_training - Step 24296: {'lr': 0.0004725198844037681, 'samples': 12440064, 'steps': 24296, 'loss/train': 1.1211553812026978}
-03/04/2022 17:59:55 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 17:59:58 - INFO - codeparrot_training - Step 24297: {'lr': 0.00047251746551175603, 'samples': 12440576, 'steps': 24297, 'loss/train': 2.218895673751831}
-03/04/2022 18:00:02 - INFO - codeparrot_training - Step 24298: {'lr': 0.000472515046519481, 'samples': 12441088, 'steps': 24298, 'loss/train': 2.248339891433716}
-03/04/2022 18:00:03 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/04/2022 18:00:07 - INFO - codeparrot_training - Step 24299: {'lr': 0.000472512627426944, 'samples': 12441600, 'steps': 24299, 'loss/train': 2.126749038696289}
-03/04/2022 18:00:10 - INFO - codeparrot_training - Step 24300: {'lr': 0.0004725102082341464, 'samples': 12442112, 'steps': 24300, 'loss/train': 2.5303127765655518}
-03/04/2022 18:00:11 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/04/2022 18:00:15 - INFO - codeparrot_training - Step 24301: {'lr': 0.00047250778894108905, 'samples': 12442624, 'steps': 24301, 'loss/train': 0.06717956811189651}
-03/04/2022 18:00:18 - INFO - codeparrot_training - Step 24302: {'lr': 0.0004725053695477731, 'samples': 12443136, 'steps': 24302, 'loss/train': 1.585740089416504}
-03/04/2022 18:00:20 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/04/2022 18:00:24 - INFO - codeparrot_training - Step 24303: {'lr': 0.0004725029500541997, 'samples': 12443648, 'steps': 24303, 'loss/train': 1.6549819707870483}
-03/04/2022 18:00:27 - INFO - codeparrot_training - Step 24304: {'lr': 0.00047250053046036996, 'samples': 12444160, 'steps': 24304, 'loss/train': 1.9009531736373901}
-03/04/2022 18:00:29 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/04/2022 18:00:32 - INFO - codeparrot_training - Step 24305: {'lr': 0.00047249811076628483, 'samples': 12444672, 'steps': 24305, 'loss/train': 1.6141051054000854}
-03/04/2022 18:00:35 - INFO - codeparrot_training - Step 24306: {'lr': 0.00047249569097194554, 'samples': 12445184, 'steps': 24306, 'loss/train': 1.180796504020691}
-03/04/2022 18:00:37 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/04/2022 18:00:41 - INFO - codeparrot_training - Step 24307: {'lr': 0.0004724932710773531, 'samples': 12445696, 'steps': 24307, 'loss/train': 2.142131805419922}
-03/04/2022 18:00:44 - INFO - codeparrot_training - Step 24308: {'lr': 0.00047249085108250867, 'samples': 12446208, 'steps': 24308, 'loss/train': 1.8203576803207397}
-03/04/2022 18:00:45 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/04/2022 18:00:49 - INFO - codeparrot_training - Step 24309: {'lr': 0.0004724884309874132, 'samples': 12446720, 'steps': 24309, 'loss/train': 2.0513458251953125}
-03/04/2022 18:00:52 - INFO - codeparrot_training - Step 24310: {'lr': 0.00047248601079206797, 'samples': 12447232, 'steps': 24310, 'loss/train': 1.5736480951309204}
-03/04/2022 18:00:54 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/04/2022 18:00:57 - INFO - codeparrot_training - Step 24311: {'lr': 0.0004724835904964739, 'samples': 12447744, 'steps': 24311, 'loss/train': 1.607282280921936}
-03/04/2022 18:01:01 - INFO - codeparrot_training - Step 24312: {'lr': 0.0004724811701006322, 'samples': 12448256, 'steps': 24312, 'loss/train': 1.243443250656128}
-03/04/2022 18:01:02 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/04/2022 18:01:06 - INFO - codeparrot_training - Step 24313: {'lr': 0.00047247874960454394, 'samples': 12448768, 'steps': 24313, 'loss/train': 1.4909756183624268}
-03/04/2022 18:01:09 - INFO - codeparrot_training - Step 24314: {'lr': 0.0004724763290082102, 'samples': 12449280, 'steps': 24314, 'loss/train': 1.3621405363082886}
-03/04/2022 18:01:11 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 18:01:14 - INFO - codeparrot_training - Step 24315: {'lr': 0.000472473908311632, 'samples': 12449792, 'steps': 24315, 'loss/train': 1.7611249685287476}
-03/04/2022 18:01:17 - INFO - codeparrot_training - Step 24316: {'lr': 0.0004724714875148105, 'samples': 12450304, 'steps': 24316, 'loss/train': 1.7962604761123657}
-03/04/2022 18:01:19 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/04/2022 18:01:23 - INFO - codeparrot_training - Step 24317: {'lr': 0.0004724690666177468, 'samples': 12450816, 'steps': 24317, 'loss/train': 2.24535870552063}
-03/04/2022 18:01:26 - INFO - codeparrot_training - Step 24318: {'lr': 0.00047246664562044193, 'samples': 12451328, 'steps': 24318, 'loss/train': 1.973689317703247}
-03/04/2022 18:01:28 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/04/2022 18:01:31 - INFO - codeparrot_training - Step 24319: {'lr': 0.0004724642245228971, 'samples': 12451840, 'steps': 24319, 'loss/train': 1.793555736541748}
-03/04/2022 18:01:34 - INFO - codeparrot_training - Step 24320: {'lr': 0.0004724618033251133, 'samples': 12452352, 'steps': 24320, 'loss/train': 1.4529109001159668}
-03/04/2022 18:01:37 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/04/2022 18:01:40 - INFO - codeparrot_training - Step 24321: {'lr': 0.0004724593820270916, 'samples': 12452864, 'steps': 24321, 'loss/train': 1.4393378496170044}
-03/04/2022 18:01:43 - INFO - codeparrot_training - Step 24322: {'lr': 0.00047245696062883316, 'samples': 12453376, 'steps': 24322, 'loss/train': 2.1024208068847656}
-03/04/2022 18:01:45 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 18:01:48 - INFO - codeparrot_training - Step 24323: {'lr': 0.0004724545391303391, 'samples': 12453888, 'steps': 24323, 'loss/train': 2.196434497833252}
-03/04/2022 18:01:51 - INFO - codeparrot_training - Step 24324: {'lr': 0.0004724521175316103, 'samples': 12454400, 'steps': 24324, 'loss/train': 1.4231659173965454}
-03/04/2022 18:01:54 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 18:01:57 - INFO - codeparrot_training - Step 24325: {'lr': 0.0004724496958326482, 'samples': 12454912, 'steps': 24325, 'loss/train': 1.9584357738494873}
-03/04/2022 18:02:00 - INFO - codeparrot_training - Step 24326: {'lr': 0.00047244727403345356, 'samples': 12455424, 'steps': 24326, 'loss/train': 0.1598268300294876}
-03/04/2022 18:02:03 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/04/2022 18:02:05 - INFO - codeparrot_training - Step 24327: {'lr': 0.00047244485213402765, 'samples': 12455936, 'steps': 24327, 'loss/train': 1.1262717247009277}
-03/04/2022 18:02:09 - INFO - codeparrot_training - Step 24328: {'lr': 0.0004724424301343716, 'samples': 12456448, 'steps': 24328, 'loss/train': 1.877912998199463}
-03/04/2022 18:02:12 - INFO - codeparrot_training - Step 24329: {'lr': 0.00047244000803448635, 'samples': 12456960, 'steps': 24329, 'loss/train': 1.9288427829742432}
-03/04/2022 18:02:12 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/04/2022 18:02:17 - INFO - codeparrot_training - Step 24330: {'lr': 0.000472437585834373, 'samples': 12457472, 'steps': 24330, 'loss/train': 1.4592257738113403}
-03/04/2022 18:02:20 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/04/2022 18:02:23 - INFO - codeparrot_training - Step 24331: {'lr': 0.00047243516353403283, 'samples': 12457984, 'steps': 24331, 'loss/train': 0.9039060473442078}
-03/04/2022 18:02:26 - INFO - codeparrot_training - Step 24332: {'lr': 0.0004724327411334668, 'samples': 12458496, 'steps': 24332, 'loss/train': 1.7935844659805298}
-03/04/2022 18:02:29 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 18:02:31 - INFO - codeparrot_training - Step 24333: {'lr': 0.00047243031863267594, 'samples': 12459008, 'steps': 24333, 'loss/train': 2.445127010345459}
-03/04/2022 18:02:34 - INFO - codeparrot_training - Step 24334: {'lr': 0.0004724278960316615, 'samples': 12459520, 'steps': 24334, 'loss/train': 2.669174909591675}
-03/04/2022 18:02:37 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/04/2022 18:02:39 - INFO - codeparrot_training - Step 24335: {'lr': 0.00047242547333042434, 'samples': 12460032, 'steps': 24335, 'loss/train': 1.7123916149139404}
-03/04/2022 18:02:43 - INFO - codeparrot_training - Step 24336: {'lr': 0.0004724230505289658, 'samples': 12460544, 'steps': 24336, 'loss/train': 1.8329994678497314}
-03/04/2022 18:02:45 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/04/2022 18:02:48 - INFO - codeparrot_training - Step 24337: {'lr': 0.0004724206276272868, 'samples': 12461056, 'steps': 24337, 'loss/train': 1.385656714439392}
-03/04/2022 18:02:51 - INFO - codeparrot_training - Step 24338: {'lr': 0.0004724182046253885, 'samples': 12461568, 'steps': 24338, 'loss/train': 1.7086632251739502}
-03/04/2022 18:02:54 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/04/2022 18:02:56 - INFO - codeparrot_training - Step 24339: {'lr': 0.0004724157815232721, 'samples': 12462080, 'steps': 24339, 'loss/train': 2.2320055961608887}
-03/04/2022 18:03:00 - INFO - codeparrot_training - Step 24340: {'lr': 0.00047241335832093844, 'samples': 12462592, 'steps': 24340, 'loss/train': 0.9382586479187012}
-03/04/2022 18:03:02 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/04/2022 18:03:05 - INFO - codeparrot_training - Step 24341: {'lr': 0.00047241093501838887, 'samples': 12463104, 'steps': 24341, 'loss/train': 2.093116283416748}
-03/04/2022 18:03:08 - INFO - codeparrot_training - Step 24342: {'lr': 0.00047240851161562433, 'samples': 12463616, 'steps': 24342, 'loss/train': 2.223428964614868}
-03/04/2022 18:03:12 - INFO - codeparrot_training - Step 24343: {'lr': 0.00047240608811264595, 'samples': 12464128, 'steps': 24343, 'loss/train': 0.7209265828132629}
-03/04/2022 18:03:14 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/04/2022 18:03:17 - INFO - codeparrot_training - Step 24344: {'lr': 0.0004724036645094548, 'samples': 12464640, 'steps': 24344, 'loss/train': 1.713396430015564}
-03/04/2022 18:03:20 - INFO - codeparrot_training - Step 24345: {'lr': 0.00047240124080605197, 'samples': 12465152, 'steps': 24345, 'loss/train': 1.6939464807510376}
-03/04/2022 18:03:22 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/04/2022 18:03:25 - INFO - codeparrot_training - Step 24346: {'lr': 0.0004723988170024386, 'samples': 12465664, 'steps': 24346, 'loss/train': 1.4689526557922363}
-03/04/2022 18:03:28 - INFO - codeparrot_training - Step 24347: {'lr': 0.0004723963930986157, 'samples': 12466176, 'steps': 24347, 'loss/train': 2.147712230682373}
-03/04/2022 18:03:31 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 18:03:34 - INFO - codeparrot_training - Step 24348: {'lr': 0.0004723939690945845, 'samples': 12466688, 'steps': 24348, 'loss/train': 2.07883882522583}
-03/04/2022 18:03:37 - INFO - codeparrot_training - Step 24349: {'lr': 0.000472391544990346, 'samples': 12467200, 'steps': 24349, 'loss/train': 1.3336700201034546}
-03/04/2022 18:03:39 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/04/2022 18:03:42 - INFO - codeparrot_training - Step 24350: {'lr': 0.0004723891207859012, 'samples': 12467712, 'steps': 24350, 'loss/train': 2.1112406253814697}
-03/04/2022 18:03:45 - INFO - codeparrot_training - Step 24351: {'lr': 0.00047238669648125146, 'samples': 12468224, 'steps': 24351, 'loss/train': 1.4390971660614014}
-03/04/2022 18:03:48 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/04/2022 18:03:51 - INFO - codeparrot_training - Step 24352: {'lr': 0.00047238427207639755, 'samples': 12468736, 'steps': 24352, 'loss/train': 0.2923624515533447}
-03/04/2022 18:03:54 - INFO - codeparrot_training - Step 24353: {'lr': 0.0004723818475713408, 'samples': 12469248, 'steps': 24353, 'loss/train': 0.1767493337392807}
-03/04/2022 18:03:56 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 18:03:59 - INFO - codeparrot_training - Step 24354: {'lr': 0.00047237942296608223, 'samples': 12469760, 'steps': 24354, 'loss/train': 1.5050644874572754}
-03/04/2022 18:04:02 - INFO - codeparrot_training - Step 24355: {'lr': 0.00047237699826062286, 'samples': 12470272, 'steps': 24355, 'loss/train': 2.0005292892456055}
-03/04/2022 18:04:04 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/04/2022 18:04:08 - INFO - codeparrot_training - Step 24356: {'lr': 0.0004723745734549639, 'samples': 12470784, 'steps': 24356, 'loss/train': 1.1322113275527954}
-03/04/2022 18:04:11 - INFO - codeparrot_training - Step 24357: {'lr': 0.0004723721485491064, 'samples': 12471296, 'steps': 24357, 'loss/train': 1.1600359678268433}
-03/04/2022 18:04:13 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/04/2022 18:04:16 - INFO - codeparrot_training - Step 24358: {'lr': 0.0004723697235430514, 'samples': 12471808, 'steps': 24358, 'loss/train': 2.173736333847046}
-03/04/2022 18:04:19 - INFO - codeparrot_training - Step 24359: {'lr': 0.0004723672984368, 'samples': 12472320, 'steps': 24359, 'loss/train': 2.0850322246551514}
-03/04/2022 18:04:21 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/04/2022 18:04:25 - INFO - codeparrot_training - Step 24360: {'lr': 0.00047236487323035344, 'samples': 12472832, 'steps': 24360, 'loss/train': 1.83031165599823}
-03/04/2022 18:04:28 - INFO - codeparrot_training - Step 24361: {'lr': 0.00047236244792371265, 'samples': 12473344, 'steps': 24361, 'loss/train': 1.1164134740829468}
-03/04/2022 18:04:30 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 18:04:33 - INFO - codeparrot_training - Step 24362: {'lr': 0.0004723600225168787, 'samples': 12473856, 'steps': 24362, 'loss/train': 2.0817224979400635}
-03/04/2022 18:04:37 - INFO - codeparrot_training - Step 24363: {'lr': 0.0004723575970098528, 'samples': 12474368, 'steps': 24363, 'loss/train': 1.3799952268600464}
-03/04/2022 18:04:40 - INFO - codeparrot_training - Step 24364: {'lr': 0.00047235517140263605, 'samples': 12474880, 'steps': 24364, 'loss/train': 2.1925430297851562}
-03/04/2022 18:04:41 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 18:04:45 - INFO - codeparrot_training - Step 24365: {'lr': 0.00047235274569522946, 'samples': 12475392, 'steps': 24365, 'loss/train': 2.468376874923706}
-03/04/2022 18:04:48 - INFO - codeparrot_training - Step 24366: {'lr': 0.0004723503198876341, 'samples': 12475904, 'steps': 24366, 'loss/train': 0.807769775390625}
-03/04/2022 18:04:50 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 18:04:54 - INFO - codeparrot_training - Step 24367: {'lr': 0.0004723478939798512, 'samples': 12476416, 'steps': 24367, 'loss/train': 2.205425262451172}
-03/04/2022 18:04:57 - INFO - codeparrot_training - Step 24368: {'lr': 0.0004723454679718817, 'samples': 12476928, 'steps': 24368, 'loss/train': 1.4210705757141113}
-03/04/2022 18:04:58 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/04/2022 18:05:02 - INFO - codeparrot_training - Step 24369: {'lr': 0.00047234304186372685, 'samples': 12477440, 'steps': 24369, 'loss/train': 1.8271970748901367}
-03/04/2022 18:05:05 - INFO - codeparrot_training - Step 24370: {'lr': 0.00047234061565538753, 'samples': 12477952, 'steps': 24370, 'loss/train': 1.784451961517334}
-03/04/2022 18:05:07 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/04/2022 18:05:11 - INFO - codeparrot_training - Step 24371: {'lr': 0.0004723381893468651, 'samples': 12478464, 'steps': 24371, 'loss/train': 1.1715573072433472}
-03/04/2022 18:05:14 - INFO - codeparrot_training - Step 24372: {'lr': 0.00047233576293816045, 'samples': 12478976, 'steps': 24372, 'loss/train': 4.757570266723633}
-03/04/2022 18:05:16 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/04/2022 18:05:19 - INFO - codeparrot_training - Step 24373: {'lr': 0.00047233333642927465, 'samples': 12479488, 'steps': 24373, 'loss/train': 2.2656476497650146}
-03/04/2022 18:05:22 - INFO - codeparrot_training - Step 24374: {'lr': 0.000472330909820209, 'samples': 12480000, 'steps': 24374, 'loss/train': 1.0471769571304321}
-03/04/2022 18:05:24 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 18:05:28 - INFO - codeparrot_training - Step 24375: {'lr': 0.0004723284831109644, 'samples': 12480512, 'steps': 24375, 'loss/train': 2.597299814224243}
-03/04/2022 18:05:31 - INFO - codeparrot_training - Step 24376: {'lr': 0.0004723260563015421, 'samples': 12481024, 'steps': 24376, 'loss/train': 1.5757673978805542}
-03/04/2022 18:05:32 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/04/2022 18:05:36 - INFO - codeparrot_training - Step 24377: {'lr': 0.00047232362939194305, 'samples': 12481536, 'steps': 24377, 'loss/train': 1.9884790182113647}
-03/04/2022 18:05:39 - INFO - codeparrot_training - Step 24378: {'lr': 0.0004723212023821684, 'samples': 12482048, 'steps': 24378, 'loss/train': 2.1321568489074707}
-03/04/2022 18:05:41 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/04/2022 18:05:45 - INFO - codeparrot_training - Step 24379: {'lr': 0.0004723187752722193, 'samples': 12482560, 'steps': 24379, 'loss/train': 0.2590729594230652}
-03/04/2022 18:05:48 - INFO - codeparrot_training - Step 24380: {'lr': 0.00047231634806209675, 'samples': 12483072, 'steps': 24380, 'loss/train': 2.262324571609497}
-03/04/2022 18:05:49 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/04/2022 18:05:53 - INFO - codeparrot_training - Step 24381: {'lr': 0.0004723139207518019, 'samples': 12483584, 'steps': 24381, 'loss/train': 2.645519256591797}
-03/04/2022 18:05:56 - INFO - codeparrot_training - Step 24382: {'lr': 0.00047231149334133577, 'samples': 12484096, 'steps': 24382, 'loss/train': 1.8642394542694092}
-03/04/2022 18:05:58 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/04/2022 18:06:02 - INFO - codeparrot_training - Step 24383: {'lr': 0.00047230906583069953, 'samples': 12484608, 'steps': 24383, 'loss/train': 2.182098627090454}
-03/04/2022 18:06:05 - INFO - codeparrot_training - Step 24384: {'lr': 0.0004723066382198943, 'samples': 12485120, 'steps': 24384, 'loss/train': 1.527432918548584}
-03/04/2022 18:06:07 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/04/2022 18:06:10 - INFO - codeparrot_training - Step 24385: {'lr': 0.00047230421050892116, 'samples': 12485632, 'steps': 24385, 'loss/train': 1.624372959136963}
-03/04/2022 18:06:13 - INFO - codeparrot_training - Step 24386: {'lr': 0.00047230178269778105, 'samples': 12486144, 'steps': 24386, 'loss/train': 1.0148608684539795}
-03/04/2022 18:06:15 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/04/2022 18:06:19 - INFO - codeparrot_training - Step 24387: {'lr': 0.00047229935478647524, 'samples': 12486656, 'steps': 24387, 'loss/train': 1.683343768119812}
-03/04/2022 18:06:22 - INFO - codeparrot_training - Step 24388: {'lr': 0.0004722969267750048, 'samples': 12487168, 'steps': 24388, 'loss/train': 1.9828135967254639}
-03/04/2022 18:06:25 - INFO - codeparrot_training - Step 24389: {'lr': 0.0004722944986633708, 'samples': 12487680, 'steps': 24389, 'loss/train': 2.1722311973571777}
-03/04/2022 18:06:25 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/04/2022 18:06:30 - INFO - codeparrot_training - Step 24390: {'lr': 0.0004722920704515743, 'samples': 12488192, 'steps': 24390, 'loss/train': 2.1045186519622803}
-03/04/2022 18:06:33 - INFO - codeparrot_training - Step 24391: {'lr': 0.00047228964213961647, 'samples': 12488704, 'steps': 24391, 'loss/train': 1.7001378536224365}
-03/04/2022 18:06:33 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/04/2022 18:06:39 - INFO - codeparrot_training - Step 24392: {'lr': 0.00047228721372749826, 'samples': 12489216, 'steps': 24392, 'loss/train': 1.915138840675354}
-03/04/2022 18:06:42 - INFO - codeparrot_training - Step 24393: {'lr': 0.000472284785215221, 'samples': 12489728, 'steps': 24393, 'loss/train': 2.13015079498291}
-03/04/2022 18:06:42 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/04/2022 18:06:47 - INFO - codeparrot_training - Step 24394: {'lr': 0.0004722823566027855, 'samples': 12490240, 'steps': 24394, 'loss/train': 2.219012498855591}
-03/04/2022 18:06:50 - INFO - codeparrot_training - Step 24395: {'lr': 0.00047227992789019316, 'samples': 12490752, 'steps': 24395, 'loss/train': 1.7858574390411377}
-03/04/2022 18:06:50 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 18:06:56 - INFO - codeparrot_training - Step 24396: {'lr': 0.0004722774990774448, 'samples': 12491264, 'steps': 24396, 'loss/train': 1.7749426364898682}
-03/04/2022 18:06:59 - INFO - codeparrot_training - Step 24397: {'lr': 0.00047227507016454163, 'samples': 12491776, 'steps': 24397, 'loss/train': 0.8248541355133057}
-03/04/2022 18:06:59 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/04/2022 18:07:04 - INFO - codeparrot_training - Step 24398: {'lr': 0.00047227264115148475, 'samples': 12492288, 'steps': 24398, 'loss/train': 2.2411694526672363}
-03/04/2022 18:07:07 - INFO - codeparrot_training - Step 24399: {'lr': 0.00047227021203827523, 'samples': 12492800, 'steps': 24399, 'loss/train': 1.6435426473617554}
-03/04/2022 18:07:07 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 18:07:13 - INFO - codeparrot_training - Step 24400: {'lr': 0.0004722677828249142, 'samples': 12493312, 'steps': 24400, 'loss/train': 1.185342788696289}
-03/04/2022 18:07:16 - INFO - codeparrot_training - Step 24401: {'lr': 0.0004722653535114028, 'samples': 12493824, 'steps': 24401, 'loss/train': 2.6949777603149414}
-03/04/2022 18:07:17 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 18:07:21 - INFO - codeparrot_training - Step 24402: {'lr': 0.00047226292409774205, 'samples': 12494336, 'steps': 24402, 'loss/train': 2.3745765686035156}
-03/04/2022 18:07:25 - INFO - codeparrot_training - Step 24403: {'lr': 0.00047226049458393306, 'samples': 12494848, 'steps': 24403, 'loss/train': 1.638043999671936}
-03/04/2022 18:07:25 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 18:07:30 - INFO - codeparrot_training - Step 24404: {'lr': 0.0004722580649699768, 'samples': 12495360, 'steps': 24404, 'loss/train': 1.4944322109222412}
-03/04/2022 18:07:33 - INFO - codeparrot_training - Step 24405: {'lr': 0.00047225563525587463, 'samples': 12495872, 'steps': 24405, 'loss/train': 0.6046652793884277}
-03/04/2022 18:07:34 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/04/2022 18:07:38 - INFO - codeparrot_training - Step 24406: {'lr': 0.0004722532054416274, 'samples': 12496384, 'steps': 24406, 'loss/train': 2.2182908058166504}
-03/04/2022 18:07:41 - INFO - codeparrot_training - Step 24407: {'lr': 0.0004722507755272364, 'samples': 12496896, 'steps': 24407, 'loss/train': 2.009392261505127}
-03/04/2022 18:07:42 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 18:07:47 - INFO - codeparrot_training - Step 24408: {'lr': 0.0004722483455127026, 'samples': 12497408, 'steps': 24408, 'loss/train': 1.5220409631729126}
-03/04/2022 18:07:50 - INFO - codeparrot_training - Step 24409: {'lr': 0.000472245915398027, 'samples': 12497920, 'steps': 24409, 'loss/train': 1.907294750213623}
-03/04/2022 18:07:51 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/04/2022 18:07:55 - INFO - codeparrot_training - Step 24410: {'lr': 0.0004722434851832109, 'samples': 12498432, 'steps': 24410, 'loss/train': 1.4560720920562744}
-03/04/2022 18:07:58 - INFO - codeparrot_training - Step 24411: {'lr': 0.00047224105486825543, 'samples': 12498944, 'steps': 24411, 'loss/train': 0.20736485719680786}
-03/04/2022 18:07:59 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 18:08:04 - INFO - codeparrot_training - Step 24412: {'lr': 0.0004722386244531615, 'samples': 12499456, 'steps': 24412, 'loss/train': 2.3332815170288086}
-03/04/2022 18:08:07 - INFO - codeparrot_training - Step 24413: {'lr': 0.0004722361939379302, 'samples': 12499968, 'steps': 24413, 'loss/train': 0.7977463603019714}
-03/04/2022 18:08:08 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/04/2022 18:08:12 - INFO - codeparrot_training - Step 24414: {'lr': 0.0004722337633225627, 'samples': 12500480, 'steps': 24414, 'loss/train': 2.2121291160583496}
-03/04/2022 18:08:15 - INFO - codeparrot_training - Step 24415: {'lr': 0.0004722313326070602, 'samples': 12500992, 'steps': 24415, 'loss/train': 1.4571318626403809}
-03/04/2022 18:08:16 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 18:08:21 - INFO - codeparrot_training - Step 24416: {'lr': 0.00047222890179142365, 'samples': 12501504, 'steps': 24416, 'loss/train': 1.727952241897583}
-03/04/2022 18:08:24 - INFO - codeparrot_training - Step 24417: {'lr': 0.00047222647087565413, 'samples': 12502016, 'steps': 24417, 'loss/train': 2.189281463623047}
-03/04/2022 18:08:25 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/04/2022 18:08:29 - INFO - codeparrot_training - Step 24418: {'lr': 0.0004722240398597528, 'samples': 12502528, 'steps': 24418, 'loss/train': 1.3159852027893066}
-03/04/2022 18:08:32 - INFO - codeparrot_training - Step 24419: {'lr': 0.0004722216087437208, 'samples': 12503040, 'steps': 24419, 'loss/train': 1.853790283203125}
-03/04/2022 18:08:33 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/04/2022 18:08:38 - INFO - codeparrot_training - Step 24420: {'lr': 0.0004722191775275592, 'samples': 12503552, 'steps': 24420, 'loss/train': 2.5647730827331543}
-03/04/2022 18:08:41 - INFO - codeparrot_training - Step 24421: {'lr': 0.00047221674621126896, 'samples': 12504064, 'steps': 24421, 'loss/train': 1.9466300010681152}
-03/04/2022 18:08:42 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 18:08:46 - INFO - codeparrot_training - Step 24422: {'lr': 0.0004722143147948513, 'samples': 12504576, 'steps': 24422, 'loss/train': 2.532318592071533}
-03/04/2022 18:08:49 - INFO - codeparrot_training - Step 24423: {'lr': 0.0004722118832783074, 'samples': 12505088, 'steps': 24423, 'loss/train': 1.0570956468582153}
-03/04/2022 18:08:51 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 18:08:55 - INFO - codeparrot_training - Step 24424: {'lr': 0.0004722094516616382, 'samples': 12505600, 'steps': 24424, 'loss/train': 2.0713443756103516}
-03/04/2022 18:08:58 - INFO - codeparrot_training - Step 24425: {'lr': 0.0004722070199448448, 'samples': 12506112, 'steps': 24425, 'loss/train': 2.467946767807007}
-03/04/2022 18:09:00 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/04/2022 18:09:03 - INFO - codeparrot_training - Step 24426: {'lr': 0.00047220458812792846, 'samples': 12506624, 'steps': 24426, 'loss/train': 1.4189249277114868}
-03/04/2022 18:09:06 - INFO - codeparrot_training - Step 24427: {'lr': 0.00047220215621089005, 'samples': 12507136, 'steps': 24427, 'loss/train': 1.767484188079834}
-03/04/2022 18:09:08 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/04/2022 18:09:12 - INFO - codeparrot_training - Step 24428: {'lr': 0.00047219972419373083, 'samples': 12507648, 'steps': 24428, 'loss/train': 1.7900302410125732}
-03/04/2022 18:09:15 - INFO - codeparrot_training - Step 24429: {'lr': 0.00047219729207645183, 'samples': 12508160, 'steps': 24429, 'loss/train': 1.5192335844039917}
-03/04/2022 18:09:17 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/04/2022 18:09:20 - INFO - codeparrot_training - Step 24430: {'lr': 0.0004721948598590542, 'samples': 12508672, 'steps': 24430, 'loss/train': 2.370107412338257}
-03/04/2022 18:09:23 - INFO - codeparrot_training - Step 24431: {'lr': 0.0004721924275415389, 'samples': 12509184, 'steps': 24431, 'loss/train': 1.8538939952850342}
-03/04/2022 18:09:25 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/04/2022 18:09:29 - INFO - codeparrot_training - Step 24432: {'lr': 0.0004721899951239072, 'samples': 12509696, 'steps': 24432, 'loss/train': 2.228358745574951}
-03/04/2022 18:09:32 - INFO - codeparrot_training - Step 24433: {'lr': 0.0004721875626061601, 'samples': 12510208, 'steps': 24433, 'loss/train': 1.3693757057189941}
-03/04/2022 18:09:35 - INFO - codeparrot_training - Step 24434: {'lr': 0.00047218512998829874, 'samples': 12510720, 'steps': 24434, 'loss/train': 0.5329472422599792}
-03/04/2022 18:09:35 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/04/2022 18:09:41 - INFO - codeparrot_training - Step 24435: {'lr': 0.00047218269727032413, 'samples': 12511232, 'steps': 24435, 'loss/train': 1.679201364517212}
-03/04/2022 18:09:44 - INFO - codeparrot_training - Step 24436: {'lr': 0.00047218026445223745, 'samples': 12511744, 'steps': 24436, 'loss/train': 1.9591596126556396}
-03/04/2022 18:09:44 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/04/2022 18:09:49 - INFO - codeparrot_training - Step 24437: {'lr': 0.0004721778315340398, 'samples': 12512256, 'steps': 24437, 'loss/train': 1.9117988348007202}
-03/04/2022 18:09:52 - INFO - codeparrot_training - Step 24438: {'lr': 0.0004721753985157322, 'samples': 12512768, 'steps': 24438, 'loss/train': 2.1197919845581055}
-03/04/2022 18:09:52 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/04/2022 18:09:57 - INFO - codeparrot_training - Step 24439: {'lr': 0.0004721729653973158, 'samples': 12513280, 'steps': 24439, 'loss/train': 1.2452572584152222}
-03/04/2022 18:10:01 - INFO - codeparrot_training - Step 24440: {'lr': 0.0004721705321787917, 'samples': 12513792, 'steps': 24440, 'loss/train': 1.5007168054580688}
-03/04/2022 18:10:01 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/04/2022 18:10:06 - INFO - codeparrot_training - Step 24441: {'lr': 0.00047216809886016097, 'samples': 12514304, 'steps': 24441, 'loss/train': 1.8779655694961548}
-03/04/2022 18:10:09 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 18:10:11 - INFO - codeparrot_training - Step 24442: {'lr': 0.0004721656654414248, 'samples': 12514816, 'steps': 24442, 'loss/train': 1.6226814985275269}
-03/04/2022 18:10:14 - INFO - codeparrot_training - Step 24443: {'lr': 0.00047216323192258416, 'samples': 12515328, 'steps': 24443, 'loss/train': 0.7962010502815247}
-03/04/2022 18:10:18 - INFO - codeparrot_training - Step 24444: {'lr': 0.0004721607983036401, 'samples': 12515840, 'steps': 24444, 'loss/train': 1.578208565711975}
-03/04/2022 18:10:18 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/04/2022 18:10:23 - INFO - codeparrot_training - Step 24445: {'lr': 0.00047215836458459393, 'samples': 12516352, 'steps': 24445, 'loss/train': 1.2195442914962769}
-03/04/2022 18:10:26 - INFO - codeparrot_training - Step 24446: {'lr': 0.00047215593076544663, 'samples': 12516864, 'steps': 24446, 'loss/train': 0.40893515944480896}
-03/04/2022 18:10:26 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 18:10:31 - INFO - codeparrot_training - Step 24447: {'lr': 0.0004721534968461992, 'samples': 12517376, 'steps': 24447, 'loss/train': 0.2289259433746338}
-03/04/2022 18:10:34 - INFO - codeparrot_training - Step 24448: {'lr': 0.00047215106282685296, 'samples': 12517888, 'steps': 24448, 'loss/train': 1.391273021697998}
-03/04/2022 18:10:35 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/04/2022 18:10:40 - INFO - codeparrot_training - Step 24449: {'lr': 0.0004721486287074088, 'samples': 12518400, 'steps': 24449, 'loss/train': 1.8093549013137817}
-03/04/2022 18:10:43 - INFO - codeparrot_training - Step 24450: {'lr': 0.0004721461944878679, 'samples': 12518912, 'steps': 24450, 'loss/train': 2.0668952465057373}
-03/04/2022 18:10:43 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/04/2022 18:10:48 - INFO - codeparrot_training - Step 24451: {'lr': 0.00047214376016823143, 'samples': 12519424, 'steps': 24451, 'loss/train': 6.699965953826904}
-03/04/2022 18:10:51 - INFO - codeparrot_training - Step 24452: {'lr': 0.0004721413257485003, 'samples': 12519936, 'steps': 24452, 'loss/train': 1.061889886856079}
-03/04/2022 18:10:53 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 18:10:57 - INFO - codeparrot_training - Step 24453: {'lr': 0.0004721388912286758, 'samples': 12520448, 'steps': 24453, 'loss/train': 1.724984049797058}
-03/04/2022 18:11:00 - INFO - codeparrot_training - Step 24454: {'lr': 0.0004721364566087589, 'samples': 12520960, 'steps': 24454, 'loss/train': 1.633524775505066}
-03/04/2022 18:11:01 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 18:11:05 - INFO - codeparrot_training - Step 24455: {'lr': 0.00047213402188875077, 'samples': 12521472, 'steps': 24455, 'loss/train': 1.8652018308639526}
-03/04/2022 18:11:08 - INFO - codeparrot_training - Step 24456: {'lr': 0.00047213158706865246, 'samples': 12521984, 'steps': 24456, 'loss/train': 1.1079046726226807}
-03/04/2022 18:11:10 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/04/2022 18:11:14 - INFO - codeparrot_training - Step 24457: {'lr': 0.000472129152148465, 'samples': 12522496, 'steps': 24457, 'loss/train': 2.1000828742980957}
-03/04/2022 18:11:17 - INFO - codeparrot_training - Step 24458: {'lr': 0.0004721267171281897, 'samples': 12523008, 'steps': 24458, 'loss/train': 1.0880120992660522}
-03/04/2022 18:11:19 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 18:11:22 - INFO - codeparrot_training - Step 24459: {'lr': 0.00047212428200782744, 'samples': 12523520, 'steps': 24459, 'loss/train': 2.7211813926696777}
-03/04/2022 18:11:25 - INFO - codeparrot_training - Step 24460: {'lr': 0.00047212184678737946, 'samples': 12524032, 'steps': 24460, 'loss/train': 0.42921656370162964}
-03/04/2022 18:11:28 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 18:11:31 - INFO - codeparrot_training - Step 24461: {'lr': 0.00047211941146684677, 'samples': 12524544, 'steps': 24461, 'loss/train': 1.3911974430084229}
-03/04/2022 18:11:34 - INFO - codeparrot_training - Step 24462: {'lr': 0.00047211697604623056, 'samples': 12525056, 'steps': 24462, 'loss/train': 1.533073902130127}
-03/04/2022 18:11:37 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 18:11:39 - INFO - codeparrot_training - Step 24463: {'lr': 0.0004721145405255318, 'samples': 12525568, 'steps': 24463, 'loss/train': 1.7363744974136353}
-03/04/2022 18:11:42 - INFO - codeparrot_training - Step 24464: {'lr': 0.00047211210490475167, 'samples': 12526080, 'steps': 24464, 'loss/train': 2.428699493408203}
-03/04/2022 18:11:45 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/04/2022 18:11:48 - INFO - codeparrot_training - Step 24465: {'lr': 0.0004721096691838913, 'samples': 12526592, 'steps': 24465, 'loss/train': 2.038604736328125}
-03/04/2022 18:11:51 - INFO - codeparrot_training - Step 24466: {'lr': 0.00047210723336295167, 'samples': 12527104, 'steps': 24466, 'loss/train': 1.4739770889282227}
-03/04/2022 18:11:54 - INFO - codeparrot_training - Step 24467: {'lr': 0.00047210479744193404, 'samples': 12527616, 'steps': 24467, 'loss/train': 1.4840128421783447}
-03/04/2022 18:11:55 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 18:12:00 - INFO - codeparrot_training - Step 24468: {'lr': 0.0004721023614208393, 'samples': 12528128, 'steps': 24468, 'loss/train': 2.714526891708374}
-03/04/2022 18:12:03 - INFO - codeparrot_training - Step 24469: {'lr': 0.0004720999252996687, 'samples': 12528640, 'steps': 24469, 'loss/train': 2.1996963024139404}
-03/04/2022 18:12:04 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 18:12:08 - INFO - codeparrot_training - Step 24470: {'lr': 0.00047209748907842337, 'samples': 12529152, 'steps': 24470, 'loss/train': 1.0092376470565796}
-03/04/2022 18:12:11 - INFO - codeparrot_training - Step 24471: {'lr': 0.0004720950527571043, 'samples': 12529664, 'steps': 24471, 'loss/train': 0.25098586082458496}
-03/04/2022 18:12:12 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/04/2022 18:12:16 - INFO - codeparrot_training - Step 24472: {'lr': 0.0004720926163357126, 'samples': 12530176, 'steps': 24472, 'loss/train': 1.353118896484375}
-03/04/2022 18:12:20 - INFO - codeparrot_training - Step 24473: {'lr': 0.0004720901798142494, 'samples': 12530688, 'steps': 24473, 'loss/train': 0.6609816551208496}
-03/04/2022 18:12:20 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 18:12:25 - INFO - codeparrot_training - Step 24474: {'lr': 0.00047208774319271586, 'samples': 12531200, 'steps': 24474, 'loss/train': 1.1361074447631836}
-03/04/2022 18:12:28 - INFO - codeparrot_training - Step 24475: {'lr': 0.00047208530647111294, 'samples': 12531712, 'steps': 24475, 'loss/train': 1.7579642534255981}
-03/04/2022 18:12:29 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/04/2022 18:12:33 - INFO - codeparrot_training - Step 24476: {'lr': 0.0004720828696494418, 'samples': 12532224, 'steps': 24476, 'loss/train': 2.0598790645599365}
-03/04/2022 18:12:37 - INFO - codeparrot_training - Step 24477: {'lr': 0.00047208043272770354, 'samples': 12532736, 'steps': 24477, 'loss/train': 1.8200620412826538}
-03/04/2022 18:12:37 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 18:12:42 - INFO - codeparrot_training - Step 24478: {'lr': 0.0004720779957058993, 'samples': 12533248, 'steps': 24478, 'loss/train': 1.9939210414886475}
-03/04/2022 18:12:45 - INFO - codeparrot_training - Step 24479: {'lr': 0.0004720755585840302, 'samples': 12533760, 'steps': 24479, 'loss/train': 2.6640143394470215}
-03/04/2022 18:12:46 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/04/2022 18:12:50 - INFO - codeparrot_training - Step 24480: {'lr': 0.0004720731213620972, 'samples': 12534272, 'steps': 24480, 'loss/train': 2.259087562561035}
-03/04/2022 18:12:53 - INFO - codeparrot_training - Step 24481: {'lr': 0.00047207068404010147, 'samples': 12534784, 'steps': 24481, 'loss/train': 2.4170734882354736}
-03/04/2022 18:12:54 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 18:12:59 - INFO - codeparrot_training - Step 24482: {'lr': 0.00047206824661804415, 'samples': 12535296, 'steps': 24482, 'loss/train': 1.2653634548187256}
-03/04/2022 18:13:02 - INFO - codeparrot_training - Step 24483: {'lr': 0.0004720658090959263, 'samples': 12535808, 'steps': 24483, 'loss/train': 1.7588878870010376}
-03/04/2022 18:13:03 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/04/2022 18:13:07 - INFO - codeparrot_training - Step 24484: {'lr': 0.000472063371473749, 'samples': 12536320, 'steps': 24484, 'loss/train': 1.985325574874878}
-03/04/2022 18:13:10 - INFO - codeparrot_training - Step 24485: {'lr': 0.0004720609337515134, 'samples': 12536832, 'steps': 24485, 'loss/train': 1.5193121433258057}
-03/04/2022 18:13:12 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 18:13:16 - INFO - codeparrot_training - Step 24486: {'lr': 0.00047205849592922057, 'samples': 12537344, 'steps': 24486, 'loss/train': 1.4992685317993164}
-03/04/2022 18:13:19 - INFO - codeparrot_training - Step 24487: {'lr': 0.00047205605800687154, 'samples': 12537856, 'steps': 24487, 'loss/train': 1.8267135620117188}
-03/04/2022 18:13:20 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 18:13:24 - INFO - codeparrot_training - Step 24488: {'lr': 0.0004720536199844676, 'samples': 12538368, 'steps': 24488, 'loss/train': 1.7764939069747925}
-03/04/2022 18:13:27 - INFO - codeparrot_training - Step 24489: {'lr': 0.00047205118186200963, 'samples': 12538880, 'steps': 24489, 'loss/train': 1.4721856117248535}
-03/04/2022 18:13:28 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/04/2022 18:13:32 - INFO - codeparrot_training - Step 24490: {'lr': 0.00047204874363949886, 'samples': 12539392, 'steps': 24490, 'loss/train': 1.372139573097229}
-03/04/2022 18:13:36 - INFO - codeparrot_training - Step 24491: {'lr': 0.00047204630531693634, 'samples': 12539904, 'steps': 24491, 'loss/train': 2.137242555618286}
-03/04/2022 18:13:37 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/04/2022 18:13:41 - INFO - codeparrot_training - Step 24492: {'lr': 0.0004720438668943232, 'samples': 12540416, 'steps': 24492, 'loss/train': 2.2619221210479736}
-03/04/2022 18:13:44 - INFO - codeparrot_training - Step 24493: {'lr': 0.0004720414283716605, 'samples': 12540928, 'steps': 24493, 'loss/train': 2.112708330154419}
-03/04/2022 18:13:45 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/04/2022 18:13:49 - INFO - codeparrot_training - Step 24494: {'lr': 0.00047203898974894934, 'samples': 12541440, 'steps': 24494, 'loss/train': 2.1385791301727295}
-03/04/2022 18:13:52 - INFO - codeparrot_training - Step 24495: {'lr': 0.0004720365510261909, 'samples': 12541952, 'steps': 24495, 'loss/train': 1.9912108182907104}
-03/04/2022 18:13:53 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/04/2022 18:13:58 - INFO - codeparrot_training - Step 24496: {'lr': 0.00047203411220338615, 'samples': 12542464, 'steps': 24496, 'loss/train': 1.3300347328186035}
-03/04/2022 18:14:01 - INFO - codeparrot_training - Step 24497: {'lr': 0.00047203167328053634, 'samples': 12542976, 'steps': 24497, 'loss/train': 2.0370845794677734}
-03/04/2022 18:14:01 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 18:14:06 - INFO - codeparrot_training - Step 24498: {'lr': 0.0004720292342576423, 'samples': 12543488, 'steps': 24498, 'loss/train': 1.6814428567886353}
-03/04/2022 18:14:09 - INFO - codeparrot_training - Step 24499: {'lr': 0.0004720267951347055, 'samples': 12544000, 'steps': 24499, 'loss/train': 2.4289727210998535}
-03/04/2022 18:14:10 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/04/2022 18:14:14 - INFO - codeparrot_training - Step 24500: {'lr': 0.00047202435591172677, 'samples': 12544512, 'steps': 24500, 'loss/train': 2.6393795013427734}
-03/04/2022 18:14:18 - INFO - codeparrot_training - Step 24501: {'lr': 0.00047202191658870737, 'samples': 12545024, 'steps': 24501, 'loss/train': 1.8278721570968628}
-03/04/2022 18:14:18 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/04/2022 18:14:23 - INFO - codeparrot_training - Step 24502: {'lr': 0.00047201947716564826, 'samples': 12545536, 'steps': 24502, 'loss/train': 1.6945443153381348}
-03/04/2022 18:14:26 - INFO - codeparrot_training - Step 24503: {'lr': 0.00047201703764255057, 'samples': 12546048, 'steps': 24503, 'loss/train': 1.7766820192337036}
-03/04/2022 18:14:27 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 18:14:31 - INFO - codeparrot_training - Step 24504: {'lr': 0.0004720145980194155, 'samples': 12546560, 'steps': 24504, 'loss/train': 2.3230977058410645}
-03/04/2022 18:14:35 - INFO - codeparrot_training - Step 24505: {'lr': 0.000472012158296244, 'samples': 12547072, 'steps': 24505, 'loss/train': 1.488804817199707}
-03/04/2022 18:14:35 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 18:14:40 - INFO - codeparrot_training - Step 24506: {'lr': 0.0004720097184730373, 'samples': 12547584, 'steps': 24506, 'loss/train': 1.3458027839660645}
-03/04/2022 18:14:43 - INFO - codeparrot_training - Step 24507: {'lr': 0.00047200727854979644, 'samples': 12548096, 'steps': 24507, 'loss/train': 2.2157466411590576}
-03/04/2022 18:14:44 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 18:14:48 - INFO - codeparrot_training - Step 24508: {'lr': 0.00047200483852652257, 'samples': 12548608, 'steps': 24508, 'loss/train': 1.5014764070510864}
-03/04/2022 18:14:52 - INFO - codeparrot_training - Step 24509: {'lr': 0.0004720023984032167, 'samples': 12549120, 'steps': 24509, 'loss/train': 2.3097431659698486}
-03/04/2022 18:14:52 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/04/2022 18:14:57 - INFO - codeparrot_training - Step 24510: {'lr': 0.00047199995817987997, 'samples': 12549632, 'steps': 24510, 'loss/train': 2.1296088695526123}
-03/04/2022 18:15:00 - INFO - codeparrot_training - Step 24511: {'lr': 0.00047199751785651346, 'samples': 12550144, 'steps': 24511, 'loss/train': 1.9083112478256226}
-03/04/2022 18:15:00 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/04/2022 18:15:05 - INFO - codeparrot_training - Step 24512: {'lr': 0.0004719950774331183, 'samples': 12550656, 'steps': 24512, 'loss/train': 1.4810632467269897}
-03/04/2022 18:15:08 - INFO - codeparrot_training - Step 24513: {'lr': 0.00047199263690969563, 'samples': 12551168, 'steps': 24513, 'loss/train': 2.143918752670288}
-03/04/2022 18:15:09 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/04/2022 18:15:14 - INFO - codeparrot_training - Step 24514: {'lr': 0.00047199019628624647, 'samples': 12551680, 'steps': 24514, 'loss/train': 1.8891240358352661}
-03/04/2022 18:15:17 - INFO - codeparrot_training - Step 24515: {'lr': 0.00047198775556277195, 'samples': 12552192, 'steps': 24515, 'loss/train': 1.6359902620315552}
-03/04/2022 18:15:19 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/04/2022 18:15:22 - INFO - codeparrot_training - Step 24516: {'lr': 0.0004719853147392732, 'samples': 12552704, 'steps': 24516, 'loss/train': 0.7026808857917786}
-03/04/2022 18:15:26 - INFO - codeparrot_training - Step 24517: {'lr': 0.0004719828738157512, 'samples': 12553216, 'steps': 24517, 'loss/train': 2.0743086338043213}
-03/04/2022 18:15:27 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 18:15:31 - INFO - codeparrot_training - Step 24518: {'lr': 0.0004719804327922073, 'samples': 12553728, 'steps': 24518, 'loss/train': 1.3966413736343384}
-03/04/2022 18:15:34 - INFO - codeparrot_training - Step 24519: {'lr': 0.00047197799166864233, 'samples': 12554240, 'steps': 24519, 'loss/train': 2.173198699951172}
-03/04/2022 18:15:36 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 18:15:39 - INFO - codeparrot_training - Step 24520: {'lr': 0.00047197555044505756, 'samples': 12554752, 'steps': 24520, 'loss/train': 1.8667889833450317}
-03/04/2022 18:15:43 - INFO - codeparrot_training - Step 24521: {'lr': 0.000471973109121454, 'samples': 12555264, 'steps': 24521, 'loss/train': 3.210848569869995}
-03/04/2022 18:15:44 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 18:15:48 - INFO - codeparrot_training - Step 24522: {'lr': 0.00047197066769783284, 'samples': 12555776, 'steps': 24522, 'loss/train': 1.9343254566192627}
-03/04/2022 18:15:51 - INFO - codeparrot_training - Step 24523: {'lr': 0.000471968226174195, 'samples': 12556288, 'steps': 24523, 'loss/train': 0.7525582909584045}
-03/04/2022 18:15:52 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 18:15:56 - INFO - codeparrot_training - Step 24524: {'lr': 0.00047196578455054175, 'samples': 12556800, 'steps': 24524, 'loss/train': 1.727347731590271}
-03/04/2022 18:15:59 - INFO - codeparrot_training - Step 24525: {'lr': 0.00047196334282687414, 'samples': 12557312, 'steps': 24525, 'loss/train': 1.3574981689453125}
-03/04/2022 18:16:05 - INFO - codeparrot_training - Step 24526: {'lr': 0.00047196090100319333, 'samples': 12557824, 'steps': 24526, 'loss/train': 1.7813762426376343}
-03/04/2022 18:16:08 - INFO - codeparrot_training - Step 24527: {'lr': 0.00047195845907950035, 'samples': 12558336, 'steps': 24527, 'loss/train': 1.7903351783752441}
-03/04/2022 18:16:09 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/04/2022 18:16:13 - INFO - codeparrot_training - Step 24528: {'lr': 0.0004719560170557963, 'samples': 12558848, 'steps': 24528, 'loss/train': 1.6665645837783813}
-03/04/2022 18:16:16 - INFO - codeparrot_training - Step 24529: {'lr': 0.0004719535749320823, 'samples': 12559360, 'steps': 24529, 'loss/train': 2.075484275817871}
-03/04/2022 18:16:17 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 18:16:21 - INFO - codeparrot_training - Step 24530: {'lr': 0.0004719511327083594, 'samples': 12559872, 'steps': 24530, 'loss/train': 1.9032742977142334}
-03/04/2022 18:16:25 - INFO - codeparrot_training - Step 24531: {'lr': 0.0004719486903846288, 'samples': 12560384, 'steps': 24531, 'loss/train': 2.14788818359375}
-03/04/2022 18:16:26 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/04/2022 18:16:30 - INFO - codeparrot_training - Step 24532: {'lr': 0.0004719462479608915, 'samples': 12560896, 'steps': 24532, 'loss/train': 2.316221237182617}
-03/04/2022 18:16:33 - INFO - codeparrot_training - Step 24533: {'lr': 0.0004719438054371487, 'samples': 12561408, 'steps': 24533, 'loss/train': 1.7690099477767944}
-03/04/2022 18:16:34 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 18:16:38 - INFO - codeparrot_training - Step 24534: {'lr': 0.00047194136281340137, 'samples': 12561920, 'steps': 24534, 'loss/train': 2.424327850341797}
-03/04/2022 18:16:41 - INFO - codeparrot_training - Step 24535: {'lr': 0.00047193892008965077, 'samples': 12562432, 'steps': 24535, 'loss/train': 1.5116389989852905}
-03/04/2022 18:16:43 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/04/2022 18:16:47 - INFO - codeparrot_training - Step 24536: {'lr': 0.0004719364772658978, 'samples': 12562944, 'steps': 24536, 'loss/train': 2.1700985431671143}
-03/04/2022 18:16:50 - INFO - codeparrot_training - Step 24537: {'lr': 0.00047193403434214385, 'samples': 12563456, 'steps': 24537, 'loss/train': 1.4450080394744873}
-03/04/2022 18:16:51 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 18:16:55 - INFO - codeparrot_training - Step 24538: {'lr': 0.0004719315913183897, 'samples': 12563968, 'steps': 24538, 'loss/train': 2.150500774383545}
-03/04/2022 18:16:58 - INFO - codeparrot_training - Step 24539: {'lr': 0.0004719291481946367, 'samples': 12564480, 'steps': 24539, 'loss/train': 2.2522151470184326}
-03/04/2022 18:16:59 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/04/2022 18:17:04 - INFO - codeparrot_training - Step 24540: {'lr': 0.00047192670497088577, 'samples': 12564992, 'steps': 24540, 'loss/train': 2.0248465538024902}
-03/04/2022 18:17:07 - INFO - codeparrot_training - Step 24541: {'lr': 0.0004719242616471381, 'samples': 12565504, 'steps': 24541, 'loss/train': 1.4819066524505615}
-03/04/2022 18:17:08 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/04/2022 18:17:12 - INFO - codeparrot_training - Step 24542: {'lr': 0.00047192181822339484, 'samples': 12566016, 'steps': 24542, 'loss/train': 2.0245165824890137}
-03/04/2022 18:17:15 - INFO - codeparrot_training - Step 24543: {'lr': 0.000471919374699657, 'samples': 12566528, 'steps': 24543, 'loss/train': 1.413270115852356}
-03/04/2022 18:17:16 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 18:17:20 - INFO - codeparrot_training - Step 24544: {'lr': 0.0004719169310759257, 'samples': 12567040, 'steps': 24544, 'loss/train': 1.6650365591049194}
-03/04/2022 18:17:24 - INFO - codeparrot_training - Step 24545: {'lr': 0.0004719144873522021, 'samples': 12567552, 'steps': 24545, 'loss/train': 1.930375576019287}
-03/04/2022 18:17:24 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/04/2022 18:17:29 - INFO - codeparrot_training - Step 24546: {'lr': 0.0004719120435284872, 'samples': 12568064, 'steps': 24546, 'loss/train': 1.8358403444290161}
-03/04/2022 18:17:32 - INFO - codeparrot_training - Step 24547: {'lr': 0.0004719095996047822, 'samples': 12568576, 'steps': 24547, 'loss/train': 1.933958888053894}
-03/04/2022 18:17:33 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/04/2022 18:17:37 - INFO - codeparrot_training - Step 24548: {'lr': 0.0004719071555810881, 'samples': 12569088, 'steps': 24548, 'loss/train': 1.9388989210128784}
-03/04/2022 18:17:41 - INFO - codeparrot_training - Step 24549: {'lr': 0.00047190471145740616, 'samples': 12569600, 'steps': 24549, 'loss/train': 1.7561167478561401}
-03/04/2022 18:17:41 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/04/2022 18:17:46 - INFO - codeparrot_training - Step 24550: {'lr': 0.0004719022672337373, 'samples': 12570112, 'steps': 24550, 'loss/train': 1.8279350996017456}
-03/04/2022 18:17:49 - INFO - codeparrot_training - Step 24551: {'lr': 0.0004718998229100827, 'samples': 12570624, 'steps': 24551, 'loss/train': 2.385383367538452}
-03/04/2022 18:17:50 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/04/2022 18:17:54 - INFO - codeparrot_training - Step 24552: {'lr': 0.00047189737848644356, 'samples': 12571136, 'steps': 24552, 'loss/train': 1.4607124328613281}
-03/04/2022 18:17:58 - INFO - codeparrot_training - Step 24553: {'lr': 0.0004718949339628208, 'samples': 12571648, 'steps': 24553, 'loss/train': 0.7268022894859314}
-03/04/2022 18:17:59 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/04/2022 18:18:03 - INFO - codeparrot_training - Step 24554: {'lr': 0.0004718924893392156, 'samples': 12572160, 'steps': 24554, 'loss/train': 2.2649381160736084}
-03/04/2022 18:18:06 - INFO - codeparrot_training - Step 24555: {'lr': 0.0004718900446156291, 'samples': 12572672, 'steps': 24555, 'loss/train': 2.1796867847442627}
-03/04/2022 18:18:07 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/04/2022 18:18:11 - INFO - codeparrot_training - Step 24556: {'lr': 0.00047188759979206236, 'samples': 12573184, 'steps': 24556, 'loss/train': 6.590080261230469}
-03/04/2022 18:18:15 - INFO - codeparrot_training - Step 24557: {'lr': 0.00047188515486851646, 'samples': 12573696, 'steps': 24557, 'loss/train': 2.23767352104187}
-03/04/2022 18:18:16 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 18:18:20 - INFO - codeparrot_training - Step 24558: {'lr': 0.0004718827098449926, 'samples': 12574208, 'steps': 24558, 'loss/train': 1.1052218675613403}
-03/04/2022 18:18:23 - INFO - codeparrot_training - Step 24559: {'lr': 0.00047188026472149184, 'samples': 12574720, 'steps': 24559, 'loss/train': 2.023693084716797}
-03/04/2022 18:18:25 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 18:18:28 - INFO - codeparrot_training - Step 24560: {'lr': 0.0004718778194980151, 'samples': 12575232, 'steps': 24560, 'loss/train': 2.0866916179656982}
-03/04/2022 18:18:32 - INFO - codeparrot_training - Step 24561: {'lr': 0.00047187537417456375, 'samples': 12575744, 'steps': 24561, 'loss/train': 1.3673527240753174}
-03/04/2022 18:18:34 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/04/2022 18:18:37 - INFO - codeparrot_training - Step 24562: {'lr': 0.00047187292875113874, 'samples': 12576256, 'steps': 24562, 'loss/train': 1.8108468055725098}
-03/04/2022 18:18:40 - INFO - codeparrot_training - Step 24563: {'lr': 0.0004718704832277413, 'samples': 12576768, 'steps': 24563, 'loss/train': 1.9500696659088135}
-03/04/2022 18:18:42 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 18:18:45 - INFO - codeparrot_training - Step 24564: {'lr': 0.0004718680376043724, 'samples': 12577280, 'steps': 24564, 'loss/train': 1.730804443359375}
-03/04/2022 18:18:48 - INFO - codeparrot_training - Step 24565: {'lr': 0.00047186559188103314, 'samples': 12577792, 'steps': 24565, 'loss/train': 1.918236494064331}
-03/04/2022 18:18:50 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/04/2022 18:18:54 - INFO - codeparrot_training - Step 24566: {'lr': 0.00047186314605772466, 'samples': 12578304, 'steps': 24566, 'loss/train': 2.5635764598846436}
-03/04/2022 18:18:57 - INFO - codeparrot_training - Step 24567: {'lr': 0.00047186070013444814, 'samples': 12578816, 'steps': 24567, 'loss/train': 1.6767905950546265}
-03/04/2022 18:18:59 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 18:19:03 - INFO - codeparrot_training - Step 24568: {'lr': 0.00047185825411120454, 'samples': 12579328, 'steps': 24568, 'loss/train': 2.050144672393799}
-03/04/2022 18:19:06 - INFO - codeparrot_training - Step 24569: {'lr': 0.0004718558079879951, 'samples': 12579840, 'steps': 24569, 'loss/train': 1.763521432876587}
-03/04/2022 18:19:09 - INFO - codeparrot_training - Step 24570: {'lr': 0.00047185336176482084, 'samples': 12580352, 'steps': 24570, 'loss/train': 2.0117151737213135}
-03/04/2022 18:19:10 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/04/2022 18:19:14 - INFO - codeparrot_training - Step 24571: {'lr': 0.00047185091544168286, 'samples': 12580864, 'steps': 24571, 'loss/train': 1.7698872089385986}
-03/04/2022 18:19:17 - INFO - codeparrot_training - Step 24572: {'lr': 0.00047184846901858225, 'samples': 12581376, 'steps': 24572, 'loss/train': 1.6262294054031372}
-03/04/2022 18:19:18 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/04/2022 18:19:23 - INFO - codeparrot_training - Step 24573: {'lr': 0.0004718460224955202, 'samples': 12581888, 'steps': 24573, 'loss/train': 1.5951533317565918}
-03/04/2022 18:19:26 - INFO - codeparrot_training - Step 24574: {'lr': 0.0004718435758724977, 'samples': 12582400, 'steps': 24574, 'loss/train': 2.9642019271850586}
-03/04/2022 18:19:27 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/04/2022 18:19:31 - INFO - codeparrot_training - Step 24575: {'lr': 0.000471841129149516, 'samples': 12582912, 'steps': 24575, 'loss/train': 2.0319533348083496}
-03/04/2022 18:19:35 - INFO - codeparrot_training - Step 24576: {'lr': 0.000471838682326576, 'samples': 12583424, 'steps': 24576, 'loss/train': 2.546630859375}
-03/04/2022 18:19:36 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 18:19:40 - INFO - codeparrot_training - Step 24577: {'lr': 0.000471836235403679, 'samples': 12583936, 'steps': 24577, 'loss/train': 1.4531915187835693}
-03/04/2022 18:19:43 - INFO - codeparrot_training - Step 24578: {'lr': 0.000471833788380826, 'samples': 12584448, 'steps': 24578, 'loss/train': 0.9757839441299438}
-03/04/2022 18:19:44 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/04/2022 18:19:48 - INFO - codeparrot_training - Step 24579: {'lr': 0.0004718313412580181, 'samples': 12584960, 'steps': 24579, 'loss/train': 1.4331064224243164}
-03/04/2022 18:19:52 - INFO - codeparrot_training - Step 24580: {'lr': 0.0004718288940352564, 'samples': 12585472, 'steps': 24580, 'loss/train': 2.2657902240753174}
-03/04/2022 18:19:53 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/04/2022 18:19:57 - INFO - codeparrot_training - Step 24581: {'lr': 0.00047182644671254207, 'samples': 12585984, 'steps': 24581, 'loss/train': 1.5244977474212646}
-03/04/2022 18:20:00 - INFO - codeparrot_training - Step 24582: {'lr': 0.0004718239992898761, 'samples': 12586496, 'steps': 24582, 'loss/train': 1.7095324993133545}
-03/04/2022 18:20:01 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/04/2022 18:20:05 - INFO - codeparrot_training - Step 24583: {'lr': 0.00047182155176725974, 'samples': 12587008, 'steps': 24583, 'loss/train': 0.6961734890937805}
-03/04/2022 18:20:09 - INFO - codeparrot_training - Step 24584: {'lr': 0.00047181910414469396, 'samples': 12587520, 'steps': 24584, 'loss/train': 2.1303796768188477}
-03/04/2022 18:20:10 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 18:20:14 - INFO - codeparrot_training - Step 24585: {'lr': 0.0004718166564221799, 'samples': 12588032, 'steps': 24585, 'loss/train': 1.4709196090698242}
-03/04/2022 18:20:17 - INFO - codeparrot_training - Step 24586: {'lr': 0.0004718142085997187, 'samples': 12588544, 'steps': 24586, 'loss/train': 1.9656394720077515}
-03/04/2022 18:20:18 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/04/2022 18:20:22 - INFO - codeparrot_training - Step 24587: {'lr': 0.0004718117606773115, 'samples': 12589056, 'steps': 24587, 'loss/train': 1.9627468585968018}
-03/04/2022 18:20:26 - INFO - codeparrot_training - Step 24588: {'lr': 0.0004718093126549592, 'samples': 12589568, 'steps': 24588, 'loss/train': 1.5840452909469604}
-03/04/2022 18:20:27 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/04/2022 18:20:31 - INFO - codeparrot_training - Step 24589: {'lr': 0.0004718068645326632, 'samples': 12590080, 'steps': 24589, 'loss/train': 1.8670438528060913}
-03/04/2022 18:20:34 - INFO - codeparrot_training - Step 24590: {'lr': 0.0004718044163104244, 'samples': 12590592, 'steps': 24590, 'loss/train': 2.1948065757751465}
-03/04/2022 18:20:35 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 18:20:39 - INFO - codeparrot_training - Step 24591: {'lr': 0.0004718019679882439, 'samples': 12591104, 'steps': 24591, 'loss/train': 1.3284690380096436}
-03/04/2022 18:20:42 - INFO - codeparrot_training - Step 24592: {'lr': 0.0004717995195661229, 'samples': 12591616, 'steps': 24592, 'loss/train': 2.0250327587127686}
-03/04/2022 18:20:44 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/04/2022 18:20:48 - INFO - codeparrot_training - Step 24593: {'lr': 0.00047179707104406243, 'samples': 12592128, 'steps': 24593, 'loss/train': 0.7504532933235168}
-03/04/2022 18:20:51 - INFO - codeparrot_training - Step 24594: {'lr': 0.0004717946224220637, 'samples': 12592640, 'steps': 24594, 'loss/train': 2.6074228286743164}
-03/04/2022 18:20:52 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/04/2022 18:20:56 - INFO - codeparrot_training - Step 24595: {'lr': 0.0004717921737001276, 'samples': 12593152, 'steps': 24595, 'loss/train': 2.201826572418213}
-03/04/2022 18:20:59 - INFO - codeparrot_training - Step 24596: {'lr': 0.0004717897248782555, 'samples': 12593664, 'steps': 24596, 'loss/train': 3.2422537803649902}
-03/04/2022 18:21:01 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/04/2022 18:21:05 - INFO - codeparrot_training - Step 24597: {'lr': 0.0004717872759564483, 'samples': 12594176, 'steps': 24597, 'loss/train': 1.6248276233673096}
-03/04/2022 18:21:08 - INFO - codeparrot_training - Step 24598: {'lr': 0.00047178482693470723, 'samples': 12594688, 'steps': 24598, 'loss/train': 1.4413553476333618}
-03/04/2022 18:21:09 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 18:21:13 - INFO - codeparrot_training - Step 24599: {'lr': 0.0004717823778130333, 'samples': 12595200, 'steps': 24599, 'loss/train': 1.9830931425094604}
-03/04/2022 18:21:16 - INFO - codeparrot_training - Step 24600: {'lr': 0.0004717799285914276, 'samples': 12595712, 'steps': 24600, 'loss/train': 1.6674185991287231}
-03/04/2022 18:21:18 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/04/2022 18:21:22 - INFO - codeparrot_training - Step 24601: {'lr': 0.00047177747926989134, 'samples': 12596224, 'steps': 24601, 'loss/train': 1.9463204145431519}
-03/04/2022 18:21:25 - INFO - codeparrot_training - Step 24602: {'lr': 0.00047177502984842556, 'samples': 12596736, 'steps': 24602, 'loss/train': 2.432020664215088}
-03/04/2022 18:21:26 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/04/2022 18:21:30 - INFO - codeparrot_training - Step 24603: {'lr': 0.0004717725803270314, 'samples': 12597248, 'steps': 24603, 'loss/train': 1.981979489326477}
-03/04/2022 18:21:33 - INFO - codeparrot_training - Step 24604: {'lr': 0.00047177013070570997, 'samples': 12597760, 'steps': 24604, 'loss/train': 1.765755295753479}
-03/04/2022 18:21:35 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/04/2022 18:21:38 - INFO - codeparrot_training - Step 24605: {'lr': 0.00047176768098446234, 'samples': 12598272, 'steps': 24605, 'loss/train': 1.9796833992004395}
-03/04/2022 18:21:42 - INFO - codeparrot_training - Step 24606: {'lr': 0.0004717652311632895, 'samples': 12598784, 'steps': 24606, 'loss/train': 1.2564719915390015}
-03/04/2022 18:21:43 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/04/2022 18:21:47 - INFO - codeparrot_training - Step 24607: {'lr': 0.00047176278124219276, 'samples': 12599296, 'steps': 24607, 'loss/train': 1.5903581380844116}
-03/04/2022 18:21:50 - INFO - codeparrot_training - Step 24608: {'lr': 0.0004717603312211731, 'samples': 12599808, 'steps': 24608, 'loss/train': 1.499257206916809}
-03/04/2022 18:21:51 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/04/2022 18:21:55 - INFO - codeparrot_training - Step 24609: {'lr': 0.0004717578811002317, 'samples': 12600320, 'steps': 24609, 'loss/train': 2.3004422187805176}
-03/04/2022 18:21:58 - INFO - codeparrot_training - Step 24610: {'lr': 0.00047175543087936954, 'samples': 12600832, 'steps': 24610, 'loss/train': 2.0687336921691895}
-03/04/2022 18:22:00 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/04/2022 18:22:04 - INFO - codeparrot_training - Step 24611: {'lr': 0.0004717529805585879, 'samples': 12601344, 'steps': 24611, 'loss/train': 2.2662270069122314}
-03/04/2022 18:22:07 - INFO - codeparrot_training - Step 24612: {'lr': 0.0004717505301378877, 'samples': 12601856, 'steps': 24612, 'loss/train': 1.3154491186141968}
-03/04/2022 18:22:08 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/04/2022 18:22:12 - INFO - codeparrot_training - Step 24613: {'lr': 0.0004717480796172702, 'samples': 12602368, 'steps': 24613, 'loss/train': 2.4597747325897217}
-03/04/2022 18:22:16 - INFO - codeparrot_training - Step 24614: {'lr': 0.00047174562899673645, 'samples': 12602880, 'steps': 24614, 'loss/train': 1.6482360363006592}
-03/04/2022 18:22:17 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/04/2022 18:22:21 - INFO - codeparrot_training - Step 24615: {'lr': 0.0004717431782762875, 'samples': 12603392, 'steps': 24615, 'loss/train': 2.3247969150543213}
-03/04/2022 18:22:24 - INFO - codeparrot_training - Step 24616: {'lr': 0.0004717407274559245, 'samples': 12603904, 'steps': 24616, 'loss/train': 2.0946590900421143}
-03/04/2022 18:22:25 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/04/2022 18:22:29 - INFO - codeparrot_training - Step 24617: {'lr': 0.0004717382765356485, 'samples': 12604416, 'steps': 24617, 'loss/train': 2.04229736328125}
-03/04/2022 18:22:33 - INFO - codeparrot_training - Step 24618: {'lr': 0.0004717358255154607, 'samples': 12604928, 'steps': 24618, 'loss/train': 1.5731310844421387}
-03/04/2022 18:22:33 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 18:22:38 - INFO - codeparrot_training - Step 24619: {'lr': 0.0004717333743953622, 'samples': 12605440, 'steps': 24619, 'loss/train': 1.8345510959625244}
-03/04/2022 18:22:41 - INFO - codeparrot_training - Step 24620: {'lr': 0.00047173092317535404, 'samples': 12605952, 'steps': 24620, 'loss/train': 2.272402763366699}
-03/04/2022 18:22:44 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/04/2022 18:22:47 - INFO - codeparrot_training - Step 24621: {'lr': 0.0004717284718554373, 'samples': 12606464, 'steps': 24621, 'loss/train': 1.4395856857299805}
-03/04/2022 18:22:50 - INFO - codeparrot_training - Step 24622: {'lr': 0.00047172602043561317, 'samples': 12606976, 'steps': 24622, 'loss/train': 2.451172351837158}
-03/04/2022 18:22:52 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 18:22:55 - INFO - codeparrot_training - Step 24623: {'lr': 0.00047172356891588273, 'samples': 12607488, 'steps': 24623, 'loss/train': 1.952971339225769}
-03/04/2022 18:22:58 - INFO - codeparrot_training - Step 24624: {'lr': 0.0004717211172962471, 'samples': 12608000, 'steps': 24624, 'loss/train': 2.029336452484131}
-03/04/2022 18:23:01 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/04/2022 18:23:04 - INFO - codeparrot_training - Step 24625: {'lr': 0.0004717186655767073, 'samples': 12608512, 'steps': 24625, 'loss/train': 2.1454498767852783}
-03/04/2022 18:23:07 - INFO - codeparrot_training - Step 24626: {'lr': 0.0004717162137572645, 'samples': 12609024, 'steps': 24626, 'loss/train': 2.2643885612487793}
-03/04/2022 18:23:09 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 18:23:12 - INFO - codeparrot_training - Step 24627: {'lr': 0.0004717137618379198, 'samples': 12609536, 'steps': 24627, 'loss/train': 1.9836783409118652}
-03/04/2022 18:23:15 - INFO - codeparrot_training - Step 24628: {'lr': 0.0004717113098186743, 'samples': 12610048, 'steps': 24628, 'loss/train': 3.6853578090667725}
-03/04/2022 18:23:18 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 18:23:20 - INFO - codeparrot_training - Step 24629: {'lr': 0.00047170885769952907, 'samples': 12610560, 'steps': 24629, 'loss/train': 1.6440081596374512}
-03/04/2022 18:23:24 - INFO - codeparrot_training - Step 24630: {'lr': 0.00047170640548048525, 'samples': 12611072, 'steps': 24630, 'loss/train': 2.314687490463257}
-03/04/2022 18:23:26 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 18:23:29 - INFO - codeparrot_training - Step 24631: {'lr': 0.000471703953161544, 'samples': 12611584, 'steps': 24631, 'loss/train': 1.898622989654541}
-03/04/2022 18:23:32 - INFO - codeparrot_training - Step 24632: {'lr': 0.00047170150074270635, 'samples': 12612096, 'steps': 24632, 'loss/train': 1.4048856496810913}
-03/04/2022 18:23:34 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 18:23:38 - INFO - codeparrot_training - Step 24633: {'lr': 0.0004716990482239735, 'samples': 12612608, 'steps': 24633, 'loss/train': 1.1435734033584595}
-03/04/2022 18:23:41 - INFO - codeparrot_training - Step 24634: {'lr': 0.0004716965956053463, 'samples': 12613120, 'steps': 24634, 'loss/train': 2.3474020957946777}
-03/04/2022 18:23:44 - INFO - codeparrot_training - Step 24635: {'lr': 0.00047169414288682616, 'samples': 12613632, 'steps': 24635, 'loss/train': 1.4966769218444824}
-03/04/2022 18:23:45 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/04/2022 18:23:49 - INFO - codeparrot_training - Step 24636: {'lr': 0.0004716916900684141, 'samples': 12614144, 'steps': 24636, 'loss/train': 2.193981170654297}
-03/04/2022 18:23:52 - INFO - codeparrot_training - Step 24637: {'lr': 0.00047168923715011103, 'samples': 12614656, 'steps': 24637, 'loss/train': 1.9065353870391846}
-03/04/2022 18:23:53 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/04/2022 18:23:58 - INFO - codeparrot_training - Step 24638: {'lr': 0.00047168678413191833, 'samples': 12615168, 'steps': 24638, 'loss/train': 3.219130754470825}
-03/04/2022 18:24:01 - INFO - codeparrot_training - Step 24639: {'lr': 0.00047168433101383694, 'samples': 12615680, 'steps': 24639, 'loss/train': 1.8705313205718994}
-03/04/2022 18:24:02 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 18:24:06 - INFO - codeparrot_training - Step 24640: {'lr': 0.000471681877795868, 'samples': 12616192, 'steps': 24640, 'loss/train': 1.8961694240570068}
-03/04/2022 18:24:09 - INFO - codeparrot_training - Step 24641: {'lr': 0.0004716794244780127, 'samples': 12616704, 'steps': 24641, 'loss/train': 1.523282766342163}
-03/04/2022 18:24:10 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 18:24:15 - INFO - codeparrot_training - Step 24642: {'lr': 0.0004716769710602721, 'samples': 12617216, 'steps': 24642, 'loss/train': 2.1076977252960205}
-03/04/2022 18:24:18 - INFO - codeparrot_training - Step 24643: {'lr': 0.00047167451754264714, 'samples': 12617728, 'steps': 24643, 'loss/train': 2.709289073944092}
-03/04/2022 18:24:19 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/04/2022 18:24:23 - INFO - codeparrot_training - Step 24644: {'lr': 0.0004716720639251392, 'samples': 12618240, 'steps': 24644, 'loss/train': 1.3856135606765747}
-03/04/2022 18:24:26 - INFO - codeparrot_training - Step 24645: {'lr': 0.0004716696102077491, 'samples': 12618752, 'steps': 24645, 'loss/train': 1.8420995473861694}
-03/04/2022 18:24:28 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 18:24:32 - INFO - codeparrot_training - Step 24646: {'lr': 0.0004716671563904782, 'samples': 12619264, 'steps': 24646, 'loss/train': 1.2377257347106934}
-03/04/2022 18:24:35 - INFO - codeparrot_training - Step 24647: {'lr': 0.0004716647024733275, 'samples': 12619776, 'steps': 24647, 'loss/train': 2.076728343963623}
-03/04/2022 18:24:36 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 18:24:40 - INFO - codeparrot_training - Step 24648: {'lr': 0.00047166224845629804, 'samples': 12620288, 'steps': 24648, 'loss/train': 1.1040862798690796}
-03/04/2022 18:24:43 - INFO - codeparrot_training - Step 24649: {'lr': 0.000471659794339391, 'samples': 12620800, 'steps': 24649, 'loss/train': 1.9048970937728882}
-03/04/2022 18:24:45 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/04/2022 18:24:49 - INFO - codeparrot_training - Step 24650: {'lr': 0.00047165734012260754, 'samples': 12621312, 'steps': 24650, 'loss/train': 1.1207002401351929}
-03/04/2022 18:24:52 - INFO - codeparrot_training - Step 24651: {'lr': 0.0004716548858059486, 'samples': 12621824, 'steps': 24651, 'loss/train': 1.5597668886184692}
-03/04/2022 18:24:53 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 18:24:57 - INFO - codeparrot_training - Step 24652: {'lr': 0.0004716524313894155, 'samples': 12622336, 'steps': 24652, 'loss/train': 2.1996593475341797}
-03/04/2022 18:25:00 - INFO - codeparrot_training - Step 24653: {'lr': 0.0004716499768730092, 'samples': 12622848, 'steps': 24653, 'loss/train': 1.3493784666061401}
-03/04/2022 18:25:02 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/04/2022 18:25:05 - INFO - codeparrot_training - Step 24654: {'lr': 0.0004716475222567308, 'samples': 12623360, 'steps': 24654, 'loss/train': 2.2032954692840576}
-03/04/2022 18:25:09 - INFO - codeparrot_training - Step 24655: {'lr': 0.0004716450675405815, 'samples': 12623872, 'steps': 24655, 'loss/train': 1.7622028589248657}
-03/04/2022 18:25:10 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 18:25:14 - INFO - codeparrot_training - Step 24656: {'lr': 0.0004716426127245623, 'samples': 12624384, 'steps': 24656, 'loss/train': 1.983569860458374}
-03/04/2022 18:25:17 - INFO - codeparrot_training - Step 24657: {'lr': 0.00047164015780867444, 'samples': 12624896, 'steps': 24657, 'loss/train': 2.214242696762085}
-03/04/2022 18:25:18 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/04/2022 18:25:22 - INFO - codeparrot_training - Step 24658: {'lr': 0.0004716377027929189, 'samples': 12625408, 'steps': 24658, 'loss/train': 1.776280164718628}
-03/04/2022 18:25:25 - INFO - codeparrot_training - Step 24659: {'lr': 0.00047163524767729684, 'samples': 12625920, 'steps': 24659, 'loss/train': 1.9588526487350464}
-03/04/2022 18:25:27 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/04/2022 18:25:31 - INFO - codeparrot_training - Step 24660: {'lr': 0.0004716327924618093, 'samples': 12626432, 'steps': 24660, 'loss/train': 1.6434866189956665}
-03/04/2022 18:25:34 - INFO - codeparrot_training - Step 24661: {'lr': 0.0004716303371464575, 'samples': 12626944, 'steps': 24661, 'loss/train': 1.8649039268493652}
-03/04/2022 18:25:35 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/04/2022 18:25:39 - INFO - codeparrot_training - Step 24662: {'lr': 0.0004716278817312425, 'samples': 12627456, 'steps': 24662, 'loss/train': 1.211341381072998}
-03/04/2022 18:25:42 - INFO - codeparrot_training - Step 24663: {'lr': 0.0004716254262161653, 'samples': 12627968, 'steps': 24663, 'loss/train': 1.6941208839416504}
-03/04/2022 18:25:44 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/04/2022 18:25:48 - INFO - codeparrot_training - Step 24664: {'lr': 0.00047162297060122726, 'samples': 12628480, 'steps': 24664, 'loss/train': 1.5189270973205566}
-03/04/2022 18:25:51 - INFO - codeparrot_training - Step 24665: {'lr': 0.0004716205148864292, 'samples': 12628992, 'steps': 24665, 'loss/train': 1.6657893657684326}
-03/04/2022 18:25:52 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/04/2022 18:25:56 - INFO - codeparrot_training - Step 24666: {'lr': 0.0004716180590717724, 'samples': 12629504, 'steps': 24666, 'loss/train': 1.8152621984481812}
-03/04/2022 18:25:59 - INFO - codeparrot_training - Step 24667: {'lr': 0.0004716156031572579, 'samples': 12630016, 'steps': 24667, 'loss/train': 2.112004041671753}
-03/04/2022 18:26:00 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/04/2022 18:26:05 - INFO - codeparrot_training - Step 24668: {'lr': 0.00047161314714288697, 'samples': 12630528, 'steps': 24668, 'loss/train': 1.8357746601104736}
-03/04/2022 18:26:08 - INFO - codeparrot_training - Step 24669: {'lr': 0.00047161069102866037, 'samples': 12631040, 'steps': 24669, 'loss/train': 2.348203420639038}
-03/04/2022 18:26:09 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 18:26:13 - INFO - codeparrot_training - Step 24670: {'lr': 0.00047160823481457955, 'samples': 12631552, 'steps': 24670, 'loss/train': 1.9957668781280518}
-03/04/2022 18:26:16 - INFO - codeparrot_training - Step 24671: {'lr': 0.0004716057785006454, 'samples': 12632064, 'steps': 24671, 'loss/train': 1.6927039623260498}
-03/04/2022 18:26:17 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 18:26:21 - INFO - codeparrot_training - Step 24672: {'lr': 0.00047160332208685915, 'samples': 12632576, 'steps': 24672, 'loss/train': 2.0702621936798096}
-03/04/2022 18:26:25 - INFO - codeparrot_training - Step 24673: {'lr': 0.00047160086557322185, 'samples': 12633088, 'steps': 24673, 'loss/train': 1.5426883697509766}
-03/04/2022 18:26:26 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/04/2022 18:26:30 - INFO - codeparrot_training - Step 24674: {'lr': 0.0004715984089597346, 'samples': 12633600, 'steps': 24674, 'loss/train': 2.240640640258789}
-03/04/2022 18:26:33 - INFO - codeparrot_training - Step 24675: {'lr': 0.00047159595224639854, 'samples': 12634112, 'steps': 24675, 'loss/train': 0.9570732116699219}
-03/04/2022 18:26:34 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/04/2022 18:26:38 - INFO - codeparrot_training - Step 24676: {'lr': 0.00047159349543321477, 'samples': 12634624, 'steps': 24676, 'loss/train': 1.171364665031433}
-03/04/2022 18:26:42 - INFO - codeparrot_training - Step 24677: {'lr': 0.00047159103852018443, 'samples': 12635136, 'steps': 24677, 'loss/train': 1.5713319778442383}
-03/04/2022 18:26:43 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 18:26:47 - INFO - codeparrot_training - Step 24678: {'lr': 0.00047158858150730856, 'samples': 12635648, 'steps': 24678, 'loss/train': 1.747634768486023}
-03/04/2022 18:26:50 - INFO - codeparrot_training - Step 24679: {'lr': 0.00047158612439458824, 'samples': 12636160, 'steps': 24679, 'loss/train': 2.0623903274536133}
-03/04/2022 18:26:52 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/04/2022 18:26:55 - INFO - codeparrot_training - Step 24680: {'lr': 0.00047158366718202466, 'samples': 12636672, 'steps': 24680, 'loss/train': 2.718082904815674}
-03/04/2022 18:26:59 - INFO - codeparrot_training - Step 24681: {'lr': 0.00047158120986961897, 'samples': 12637184, 'steps': 24681, 'loss/train': 2.000596523284912}
-03/04/2022 18:27:00 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/04/2022 18:27:04 - INFO - codeparrot_training - Step 24682: {'lr': 0.00047157875245737213, 'samples': 12637696, 'steps': 24682, 'loss/train': 1.8995782136917114}
-03/04/2022 18:27:07 - INFO - codeparrot_training - Step 24683: {'lr': 0.0004715762949452853, 'samples': 12638208, 'steps': 24683, 'loss/train': 2.354377031326294}
-03/04/2022 18:27:09 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 18:27:12 - INFO - codeparrot_training - Step 24684: {'lr': 0.0004715738373333597, 'samples': 12638720, 'steps': 24684, 'loss/train': 1.7715439796447754}
-03/04/2022 18:27:16 - INFO - codeparrot_training - Step 24685: {'lr': 0.00047157137962159626, 'samples': 12639232, 'steps': 24685, 'loss/train': 1.3711684942245483}
-03/04/2022 18:27:17 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/04/2022 18:27:21 - INFO - codeparrot_training - Step 24686: {'lr': 0.00047156892180999624, 'samples': 12639744, 'steps': 24686, 'loss/train': 1.1598052978515625}
-03/04/2022 18:27:24 - INFO - codeparrot_training - Step 24687: {'lr': 0.0004715664638985606, 'samples': 12640256, 'steps': 24687, 'loss/train': 1.291690707206726}
-03/04/2022 18:27:26 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/04/2022 18:27:29 - INFO - codeparrot_training - Step 24688: {'lr': 0.00047156400588729066, 'samples': 12640768, 'steps': 24688, 'loss/train': 1.5799421072006226}
-03/04/2022 18:27:32 - INFO - codeparrot_training - Step 24689: {'lr': 0.0004715615477761873, 'samples': 12641280, 'steps': 24689, 'loss/train': 2.627638101577759}
-03/04/2022 18:27:34 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/04/2022 18:27:38 - INFO - codeparrot_training - Step 24690: {'lr': 0.00047155908956525173, 'samples': 12641792, 'steps': 24690, 'loss/train': 2.178576946258545}
-03/04/2022 18:27:41 - INFO - codeparrot_training - Step 24691: {'lr': 0.00047155663125448514, 'samples': 12642304, 'steps': 24691, 'loss/train': 1.528391718864441}
-03/04/2022 18:27:43 - INFO - codeparrot_training - Skipping example with length 822 (seq_length=1024)
-03/04/2022 18:27:46 - INFO - codeparrot_training - Step 24692: {'lr': 0.00047155417284388846, 'samples': 12642816, 'steps': 24692, 'loss/train': 1.4242124557495117}
-03/04/2022 18:27:49 - INFO - codeparrot_training - Step 24693: {'lr': 0.0004715517143334629, 'samples': 12643328, 'steps': 24693, 'loss/train': 1.6316503286361694}
-03/04/2022 18:27:51 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/04/2022 18:27:54 - INFO - codeparrot_training - Step 24694: {'lr': 0.00047154925572320957, 'samples': 12643840, 'steps': 24694, 'loss/train': 1.9165469408035278}
-03/04/2022 18:27:58 - INFO - codeparrot_training - Step 24695: {'lr': 0.00047154679701312953, 'samples': 12644352, 'steps': 24695, 'loss/train': 1.4554461240768433}
-03/04/2022 18:28:00 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 18:28:03 - INFO - codeparrot_training - Step 24696: {'lr': 0.00047154433820322395, 'samples': 12644864, 'steps': 24696, 'loss/train': 2.001314878463745}
-03/04/2022 18:28:06 - INFO - codeparrot_training - Step 24697: {'lr': 0.0004715418792934939, 'samples': 12645376, 'steps': 24697, 'loss/train': 1.549970269203186}
-03/04/2022 18:28:08 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 18:28:11 - INFO - codeparrot_training - Step 24698: {'lr': 0.00047153942028394056, 'samples': 12645888, 'steps': 24698, 'loss/train': 1.726121425628662}
-03/04/2022 18:28:15 - INFO - codeparrot_training - Step 24699: {'lr': 0.0004715369611745649, 'samples': 12646400, 'steps': 24699, 'loss/train': 1.913517713546753}
-03/04/2022 18:28:17 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/04/2022 18:28:20 - INFO - codeparrot_training - Step 24700: {'lr': 0.00047153450196536816, 'samples': 12646912, 'steps': 24700, 'loss/train': 1.3226584196090698}
-03/04/2022 18:28:23 - INFO - codeparrot_training - Step 24701: {'lr': 0.00047153204265635136, 'samples': 12647424, 'steps': 24701, 'loss/train': 1.125030279159546}
-03/04/2022 18:28:26 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/04/2022 18:28:28 - INFO - codeparrot_training - Step 24702: {'lr': 0.0004715295832475156, 'samples': 12647936, 'steps': 24702, 'loss/train': 1.5114527940750122}
-03/04/2022 18:28:32 - INFO - codeparrot_training - Step 24703: {'lr': 0.0004715271237388621, 'samples': 12648448, 'steps': 24703, 'loss/train': 1.9711768627166748}
-03/04/2022 18:28:34 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/04/2022 18:28:37 - INFO - codeparrot_training - Step 24704: {'lr': 0.00047152466413039187, 'samples': 12648960, 'steps': 24704, 'loss/train': 2.4147050380706787}
-03/04/2022 18:28:40 - INFO - codeparrot_training - Step 24705: {'lr': 0.000471522204422106, 'samples': 12649472, 'steps': 24705, 'loss/train': 1.3595484495162964}
-03/04/2022 18:28:43 - INFO - codeparrot_training - Step 24706: {'lr': 0.0004715197446140057, 'samples': 12649984, 'steps': 24706, 'loss/train': 1.8579267263412476}
-03/04/2022 18:28:44 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 18:28:49 - INFO - codeparrot_training - Step 24707: {'lr': 0.000471517284706092, 'samples': 12650496, 'steps': 24707, 'loss/train': 2.4519073963165283}
-03/04/2022 18:28:52 - INFO - codeparrot_training - Step 24708: {'lr': 0.0004715148246983661, 'samples': 12651008, 'steps': 24708, 'loss/train': 2.1708130836486816}
-03/04/2022 18:28:53 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/04/2022 18:28:57 - INFO - codeparrot_training - Step 24709: {'lr': 0.000471512364590829, 'samples': 12651520, 'steps': 24709, 'loss/train': 1.411179542541504}
-03/04/2022 18:29:00 - INFO - codeparrot_training - Step 24710: {'lr': 0.0004715099043834818, 'samples': 12652032, 'steps': 24710, 'loss/train': 2.5634896755218506}
-03/04/2022 18:29:01 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 18:29:06 - INFO - codeparrot_training - Step 24711: {'lr': 0.00047150744407632565, 'samples': 12652544, 'steps': 24711, 'loss/train': 3.6621053218841553}
-03/04/2022 18:29:09 - INFO - codeparrot_training - Step 24712: {'lr': 0.00047150498366936165, 'samples': 12653056, 'steps': 24712, 'loss/train': 1.6211223602294922}
-03/04/2022 18:29:09 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 18:29:14 - INFO - codeparrot_training - Step 24713: {'lr': 0.000471502523162591, 'samples': 12653568, 'steps': 24713, 'loss/train': 0.3041895031929016}
-03/04/2022 18:29:17 - INFO - codeparrot_training - Step 24714: {'lr': 0.00047150006255601475, 'samples': 12654080, 'steps': 24714, 'loss/train': 1.7482783794403076}
-03/04/2022 18:29:18 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 18:29:23 - INFO - codeparrot_training - Step 24715: {'lr': 0.00047149760184963385, 'samples': 12654592, 'steps': 24715, 'loss/train': 1.5121724605560303}
-03/04/2022 18:29:26 - INFO - codeparrot_training - Step 24716: {'lr': 0.0004714951410434497, 'samples': 12655104, 'steps': 24716, 'loss/train': 1.9706952571868896}
-03/04/2022 18:29:26 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/04/2022 18:29:31 - INFO - codeparrot_training - Step 24717: {'lr': 0.00047149268013746317, 'samples': 12655616, 'steps': 24717, 'loss/train': 2.383165121078491}
-03/04/2022 18:29:34 - INFO - codeparrot_training - Step 24718: {'lr': 0.00047149021913167545, 'samples': 12656128, 'steps': 24718, 'loss/train': 2.336829900741577}
-03/04/2022 18:29:34 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 18:29:39 - INFO - codeparrot_training - Step 24719: {'lr': 0.0004714877580260877, 'samples': 12656640, 'steps': 24719, 'loss/train': 1.8537455797195435}
-03/04/2022 18:29:43 - INFO - codeparrot_training - Step 24720: {'lr': 0.00047148529682070094, 'samples': 12657152, 'steps': 24720, 'loss/train': 0.9557305574417114}
-03/04/2022 18:29:43 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/04/2022 18:29:48 - INFO - codeparrot_training - Step 24721: {'lr': 0.00047148283551551643, 'samples': 12657664, 'steps': 24721, 'loss/train': 1.1513121128082275}
-03/04/2022 18:29:51 - INFO - codeparrot_training - Step 24722: {'lr': 0.000471480374110535, 'samples': 12658176, 'steps': 24722, 'loss/train': 1.4778661727905273}
-03/04/2022 18:29:51 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/04/2022 18:29:56 - INFO - codeparrot_training - Step 24723: {'lr': 0.00047147791260575804, 'samples': 12658688, 'steps': 24723, 'loss/train': 1.6362143754959106}
-03/04/2022 18:30:00 - INFO - codeparrot_training - Step 24724: {'lr': 0.0004714754510011866, 'samples': 12659200, 'steps': 24724, 'loss/train': 1.64474356174469}
-03/04/2022 18:30:00 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 18:30:05 - INFO - codeparrot_training - Step 24725: {'lr': 0.0004714729892968216, 'samples': 12659712, 'steps': 24725, 'loss/train': 0.701042115688324}
-03/04/2022 18:30:08 - INFO - codeparrot_training - Step 24726: {'lr': 0.0004714705274926644, 'samples': 12660224, 'steps': 24726, 'loss/train': 1.1750068664550781}
-03/04/2022 18:30:08 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 18:30:13 - INFO - codeparrot_training - Step 24727: {'lr': 0.00047146806558871594, 'samples': 12660736, 'steps': 24727, 'loss/train': 2.2862913608551025}
-03/04/2022 18:30:17 - INFO - codeparrot_training - Step 24728: {'lr': 0.0004714656035849774, 'samples': 12661248, 'steps': 24728, 'loss/train': 2.1631500720977783}
-03/04/2022 18:30:17 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/04/2022 18:30:22 - INFO - codeparrot_training - Step 24729: {'lr': 0.00047146314148144986, 'samples': 12661760, 'steps': 24729, 'loss/train': 2.0542526245117188}
-03/04/2022 18:30:25 - INFO - codeparrot_training - Step 24730: {'lr': 0.00047146067927813454, 'samples': 12662272, 'steps': 24730, 'loss/train': 2.438232421875}
-03/04/2022 18:30:25 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/04/2022 18:30:30 - INFO - codeparrot_training - Step 24731: {'lr': 0.00047145821697503235, 'samples': 12662784, 'steps': 24731, 'loss/train': 2.171314239501953}
-03/04/2022 18:30:33 - INFO - codeparrot_training - Step 24732: {'lr': 0.00047145575457214453, 'samples': 12663296, 'steps': 24732, 'loss/train': 1.537041187286377}
-03/04/2022 18:30:34 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/04/2022 18:30:39 - INFO - codeparrot_training - Step 24733: {'lr': 0.00047145329206947216, 'samples': 12663808, 'steps': 24733, 'loss/train': 2.600062131881714}
-03/04/2022 18:30:42 - INFO - codeparrot_training - Step 24734: {'lr': 0.0004714508294670164, 'samples': 12664320, 'steps': 24734, 'loss/train': 1.532106876373291}
-03/04/2022 18:30:42 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 18:30:47 - INFO - codeparrot_training - Step 24735: {'lr': 0.00047144836676477823, 'samples': 12664832, 'steps': 24735, 'loss/train': 2.280266284942627}
-03/04/2022 18:30:50 - INFO - codeparrot_training - Step 24736: {'lr': 0.00047144590396275895, 'samples': 12665344, 'steps': 24736, 'loss/train': 1.6883699893951416}
-03/04/2022 18:30:51 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/04/2022 18:30:56 - INFO - codeparrot_training - Step 24737: {'lr': 0.0004714434410609595, 'samples': 12665856, 'steps': 24737, 'loss/train': 2.0127952098846436}
-03/04/2022 18:30:59 - INFO - codeparrot_training - Step 24738: {'lr': 0.00047144097805938104, 'samples': 12666368, 'steps': 24738, 'loss/train': 1.7633246183395386}
-03/04/2022 18:30:59 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/04/2022 18:31:04 - INFO - codeparrot_training - Step 24739: {'lr': 0.0004714385149580247, 'samples': 12666880, 'steps': 24739, 'loss/train': 2.41957426071167}
-03/04/2022 18:31:07 - INFO - codeparrot_training - Step 24740: {'lr': 0.0004714360517568916, 'samples': 12667392, 'steps': 24740, 'loss/train': 2.0245862007141113}
-03/04/2022 18:31:08 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/04/2022 18:31:13 - INFO - codeparrot_training - Step 24741: {'lr': 0.00047143358845598283, 'samples': 12667904, 'steps': 24741, 'loss/train': 2.1678361892700195}
-03/04/2022 18:31:16 - INFO - codeparrot_training - Step 24742: {'lr': 0.0004714311250552995, 'samples': 12668416, 'steps': 24742, 'loss/train': 2.006564140319824}
-03/04/2022 18:31:17 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/04/2022 18:31:21 - INFO - codeparrot_training - Step 24743: {'lr': 0.0004714286615548427, 'samples': 12668928, 'steps': 24743, 'loss/train': 1.7313655614852905}
-03/04/2022 18:31:24 - INFO - codeparrot_training - Step 24744: {'lr': 0.00047142619795461363, 'samples': 12669440, 'steps': 24744, 'loss/train': 1.4713009595870972}
-03/04/2022 18:31:25 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/04/2022 18:31:29 - INFO - codeparrot_training - Step 24745: {'lr': 0.0004714237342546133, 'samples': 12669952, 'steps': 24745, 'loss/train': 1.4249142408370972}
-03/04/2022 18:31:33 - INFO - codeparrot_training - Step 24746: {'lr': 0.0004714212704548428, 'samples': 12670464, 'steps': 24746, 'loss/train': 1.8464289903640747}
-03/04/2022 18:31:33 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 18:31:38 - INFO - codeparrot_training - Step 24747: {'lr': 0.0004714188065553033, 'samples': 12670976, 'steps': 24747, 'loss/train': 1.1678587198257446}
-03/04/2022 18:31:41 - INFO - codeparrot_training - Step 24748: {'lr': 0.000471416342555996, 'samples': 12671488, 'steps': 24748, 'loss/train': 1.7508043050765991}
-03/04/2022 18:31:42 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/04/2022 18:31:46 - INFO - codeparrot_training - Step 24749: {'lr': 0.00047141387845692174, 'samples': 12672000, 'steps': 24749, 'loss/train': 1.5101207494735718}
-03/04/2022 18:31:50 - INFO - codeparrot_training - Step 24750: {'lr': 0.0004714114142580819, 'samples': 12672512, 'steps': 24750, 'loss/train': 2.2803940773010254}
-03/04/2022 18:31:50 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/04/2022 18:31:55 - INFO - codeparrot_training - Step 24751: {'lr': 0.00047140894995947755, 'samples': 12673024, 'steps': 24751, 'loss/train': 1.4348726272583008}
-03/04/2022 18:31:58 - INFO - codeparrot_training - Step 24752: {'lr': 0.00047140648556110966, 'samples': 12673536, 'steps': 24752, 'loss/train': 1.384469985961914}
-03/04/2022 18:31:58 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/04/2022 18:32:03 - INFO - codeparrot_training - Step 24753: {'lr': 0.00047140402106297946, 'samples': 12674048, 'steps': 24753, 'loss/train': 1.2430760860443115}
-03/04/2022 18:32:06 - INFO - codeparrot_training - Step 24754: {'lr': 0.000471401556465088, 'samples': 12674560, 'steps': 24754, 'loss/train': 1.639783263206482}
-03/04/2022 18:32:07 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/04/2022 18:32:12 - INFO - codeparrot_training - Step 24755: {'lr': 0.00047139909176743643, 'samples': 12675072, 'steps': 24755, 'loss/train': 2.177448272705078}
-03/04/2022 18:32:15 - INFO - codeparrot_training - Step 24756: {'lr': 0.0004713966269700259, 'samples': 12675584, 'steps': 24756, 'loss/train': 1.2752490043640137}
-03/04/2022 18:32:15 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/04/2022 18:32:20 - INFO - codeparrot_training - Step 24757: {'lr': 0.0004713941620728574, 'samples': 12676096, 'steps': 24757, 'loss/train': 2.029435873031616}
-03/04/2022 18:32:23 - INFO - codeparrot_training - Step 24758: {'lr': 0.0004713916970759321, 'samples': 12676608, 'steps': 24758, 'loss/train': 1.7979013919830322}
-03/04/2022 18:32:24 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/04/2022 18:32:29 - INFO - codeparrot_training - Step 24759: {'lr': 0.00047138923197925114, 'samples': 12677120, 'steps': 24759, 'loss/train': 1.868674397468567}
-03/04/2022 18:32:32 - INFO - codeparrot_training - Step 24760: {'lr': 0.00047138676678281564, 'samples': 12677632, 'steps': 24760, 'loss/train': 3.1697590351104736}
-03/04/2022 18:32:32 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/04/2022 18:32:37 - INFO - codeparrot_training - Step 24761: {'lr': 0.00047138430148662666, 'samples': 12678144, 'steps': 24761, 'loss/train': 0.5748162865638733}
-03/04/2022 18:32:40 - INFO - codeparrot_training - Step 24762: {'lr': 0.0004713818360906853, 'samples': 12678656, 'steps': 24762, 'loss/train': 2.116304874420166}
-03/04/2022 18:32:41 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 18:32:45 - INFO - codeparrot_training - Step 24763: {'lr': 0.0004713793705949927, 'samples': 12679168, 'steps': 24763, 'loss/train': 1.9361690282821655}
-03/04/2022 18:32:49 - INFO - codeparrot_training - Step 24764: {'lr': 0.00047137690499955, 'samples': 12679680, 'steps': 24764, 'loss/train': 1.661600112915039}
-03/04/2022 18:32:49 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/04/2022 18:32:54 - INFO - codeparrot_training - Step 24765: {'lr': 0.0004713744393043583, 'samples': 12680192, 'steps': 24765, 'loss/train': 1.9061942100524902}
-03/04/2022 18:32:57 - INFO - codeparrot_training - Step 24766: {'lr': 0.00047137197350941864, 'samples': 12680704, 'steps': 24766, 'loss/train': 2.067296266555786}
-03/04/2022 18:32:58 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/04/2022 18:33:02 - INFO - codeparrot_training - Step 24767: {'lr': 0.0004713695076147322, 'samples': 12681216, 'steps': 24767, 'loss/train': 1.8959370851516724}
-03/04/2022 18:33:06 - INFO - codeparrot_training - Step 24768: {'lr': 0.0004713670416203001, 'samples': 12681728, 'steps': 24768, 'loss/train': 1.6699947118759155}
-03/04/2022 18:33:06 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/04/2022 18:33:11 - INFO - codeparrot_training - Step 24769: {'lr': 0.00047136457552612344, 'samples': 12682240, 'steps': 24769, 'loss/train': 1.8406429290771484}
-03/04/2022 18:33:14 - INFO - codeparrot_training - Step 24770: {'lr': 0.00047136210933220325, 'samples': 12682752, 'steps': 24770, 'loss/train': 1.5311241149902344}
-03/04/2022 18:33:14 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/04/2022 18:33:19 - INFO - codeparrot_training - Step 24771: {'lr': 0.0004713596430385408, 'samples': 12683264, 'steps': 24771, 'loss/train': 1.4714120626449585}
-03/04/2022 18:33:22 - INFO - codeparrot_training - Step 24772: {'lr': 0.00047135717664513704, 'samples': 12683776, 'steps': 24772, 'loss/train': 2.10063099861145}
-03/04/2022 18:33:23 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/04/2022 18:33:28 - INFO - codeparrot_training - Step 24773: {'lr': 0.00047135471015199315, 'samples': 12684288, 'steps': 24773, 'loss/train': 1.682602882385254}
-03/04/2022 18:33:31 - INFO - codeparrot_training - Step 24774: {'lr': 0.00047135224355911035, 'samples': 12684800, 'steps': 24774, 'loss/train': 1.9194884300231934}
-03/04/2022 18:33:32 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/04/2022 18:33:36 - INFO - codeparrot_training - Step 24775: {'lr': 0.0004713497768664895, 'samples': 12685312, 'steps': 24775, 'loss/train': 1.8973873853683472}
-03/04/2022 18:33:39 - INFO - codeparrot_training - Step 24776: {'lr': 0.00047134731007413195, 'samples': 12685824, 'steps': 24776, 'loss/train': 1.981945276260376}
-03/04/2022 18:33:40 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 18:33:45 - INFO - codeparrot_training - Step 24777: {'lr': 0.0004713448431820387, 'samples': 12686336, 'steps': 24777, 'loss/train': 2.4914448261260986}
-03/04/2022 18:33:48 - INFO - codeparrot_training - Step 24778: {'lr': 0.00047134237619021085, 'samples': 12686848, 'steps': 24778, 'loss/train': 0.3672856092453003}
-03/04/2022 18:33:49 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/04/2022 18:33:53 - INFO - codeparrot_training - Step 24779: {'lr': 0.00047133990909864953, 'samples': 12687360, 'steps': 24779, 'loss/train': 1.419208288192749}
-03/04/2022 18:33:56 - INFO - codeparrot_training - Step 24780: {'lr': 0.0004713374419073559, 'samples': 12687872, 'steps': 24780, 'loss/train': 2.0719738006591797}
-03/04/2022 18:33:57 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/04/2022 18:34:01 - INFO - codeparrot_training - Step 24781: {'lr': 0.000471334974616331, 'samples': 12688384, 'steps': 24781, 'loss/train': 1.7094753980636597}
-03/04/2022 18:34:05 - INFO - codeparrot_training - Step 24782: {'lr': 0.0004713325072255761, 'samples': 12688896, 'steps': 24782, 'loss/train': 2.5775630474090576}
-03/04/2022 18:34:05 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 18:34:10 - INFO - codeparrot_training - Step 24783: {'lr': 0.000471330039735092, 'samples': 12689408, 'steps': 24783, 'loss/train': 1.6372050046920776}
-03/04/2022 18:34:13 - INFO - codeparrot_training - Step 24784: {'lr': 0.0004713275721448801, 'samples': 12689920, 'steps': 24784, 'loss/train': 2.311481475830078}
-03/04/2022 18:34:14 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/04/2022 18:34:19 - INFO - codeparrot_training - Step 24785: {'lr': 0.0004713251044549414, 'samples': 12690432, 'steps': 24785, 'loss/train': 1.3840956687927246}
-03/04/2022 18:34:22 - INFO - codeparrot_training - Step 24786: {'lr': 0.000471322636665277, 'samples': 12690944, 'steps': 24786, 'loss/train': 1.8654656410217285}
-03/04/2022 18:34:23 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 18:34:27 - INFO - codeparrot_training - Step 24787: {'lr': 0.0004713201687758881, 'samples': 12691456, 'steps': 24787, 'loss/train': 3.042464017868042}
-03/04/2022 18:34:30 - INFO - codeparrot_training - Step 24788: {'lr': 0.00047131770078677574, 'samples': 12691968, 'steps': 24788, 'loss/train': 1.2435691356658936}
-03/04/2022 18:34:31 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/04/2022 18:34:35 - INFO - codeparrot_training - Step 24789: {'lr': 0.000471315232697941, 'samples': 12692480, 'steps': 24789, 'loss/train': 1.8597811460494995}
-03/04/2022 18:34:38 - INFO - codeparrot_training - Step 24790: {'lr': 0.000471312764509385, 'samples': 12692992, 'steps': 24790, 'loss/train': 1.4346798658370972}
-03/04/2022 18:34:39 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/04/2022 18:34:44 - INFO - codeparrot_training - Step 24791: {'lr': 0.0004713102962211089, 'samples': 12693504, 'steps': 24791, 'loss/train': 2.1289052963256836}
-03/04/2022 18:34:47 - INFO - codeparrot_training - Step 24792: {'lr': 0.0004713078278331138, 'samples': 12694016, 'steps': 24792, 'loss/train': 1.555801510810852}
-03/04/2022 18:34:47 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/04/2022 18:34:52 - INFO - codeparrot_training - Step 24793: {'lr': 0.00047130535934540086, 'samples': 12694528, 'steps': 24793, 'loss/train': 2.58398175239563}
-03/04/2022 18:34:55 - INFO - codeparrot_training - Step 24794: {'lr': 0.00047130289075797107, 'samples': 12695040, 'steps': 24794, 'loss/train': 1.2993934154510498}
-03/04/2022 18:34:56 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 18:35:01 - INFO - codeparrot_training - Step 24795: {'lr': 0.0004713004220708257, 'samples': 12695552, 'steps': 24795, 'loss/train': 1.974942922592163}
-03/04/2022 18:35:04 - INFO - codeparrot_training - Step 24796: {'lr': 0.0004712979532839656, 'samples': 12696064, 'steps': 24796, 'loss/train': 1.9970390796661377}
-03/04/2022 18:35:06 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/04/2022 18:35:09 - INFO - codeparrot_training - Step 24797: {'lr': 0.00047129548439739225, 'samples': 12696576, 'steps': 24797, 'loss/train': 1.8911539316177368}
-03/04/2022 18:35:12 - INFO - codeparrot_training - Step 24798: {'lr': 0.0004712930154111065, 'samples': 12697088, 'steps': 24798, 'loss/train': 1.6669784784317017}
-03/04/2022 18:35:14 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/04/2022 18:35:18 - INFO - codeparrot_training - Step 24799: {'lr': 0.00047129054632510947, 'samples': 12697600, 'steps': 24799, 'loss/train': 1.5699328184127808}
-03/04/2022 18:35:21 - INFO - codeparrot_training - Step 24800: {'lr': 0.00047128807713940244, 'samples': 12698112, 'steps': 24800, 'loss/train': 2.102475166320801}
-03/04/2022 18:35:22 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/04/2022 18:35:26 - INFO - codeparrot_training - Step 24801: {'lr': 0.00047128560785398633, 'samples': 12698624, 'steps': 24801, 'loss/train': 3.260636568069458}
-03/04/2022 18:35:29 - INFO - codeparrot_training - Step 24802: {'lr': 0.0004712831384688624, 'samples': 12699136, 'steps': 24802, 'loss/train': 0.6887727975845337}
-03/04/2022 18:35:31 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 18:35:34 - INFO - codeparrot_training - Step 24803: {'lr': 0.00047128066898403166, 'samples': 12699648, 'steps': 24803, 'loss/train': 0.8184208273887634}
-03/04/2022 18:35:38 - INFO - codeparrot_training - Step 24804: {'lr': 0.00047127819939949534, 'samples': 12700160, 'steps': 24804, 'loss/train': 1.3844348192214966}
-03/04/2022 18:35:39 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/04/2022 18:35:43 - INFO - codeparrot_training - Step 24805: {'lr': 0.00047127572971525437, 'samples': 12700672, 'steps': 24805, 'loss/train': 1.5843253135681152}
-03/04/2022 18:35:46 - INFO - codeparrot_training - Step 24806: {'lr': 0.00047127325993131006, 'samples': 12701184, 'steps': 24806, 'loss/train': 0.9158748984336853}
-03/04/2022 18:35:48 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/04/2022 18:35:51 - INFO - codeparrot_training - Step 24807: {'lr': 0.0004712707900476634, 'samples': 12701696, 'steps': 24807, 'loss/train': 1.7368192672729492}
-03/04/2022 18:35:54 - INFO - codeparrot_training - Step 24808: {'lr': 0.00047126832006431555, 'samples': 12702208, 'steps': 24808, 'loss/train': 1.935489296913147}
-03/04/2022 18:35:56 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/04/2022 18:36:00 - INFO - codeparrot_training - Step 24809: {'lr': 0.00047126584998126756, 'samples': 12702720, 'steps': 24809, 'loss/train': 1.3985446691513062}
-03/04/2022 18:36:03 - INFO - codeparrot_training - Step 24810: {'lr': 0.0004712633797985206, 'samples': 12703232, 'steps': 24810, 'loss/train': 1.9078701734542847}
-03/04/2022 18:36:04 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 18:36:08 - INFO - codeparrot_training - Step 24811: {'lr': 0.0004712609095160758, 'samples': 12703744, 'steps': 24811, 'loss/train': 1.8915894031524658}
-03/04/2022 18:36:11 - INFO - codeparrot_training - Step 24812: {'lr': 0.0004712584391339343, 'samples': 12704256, 'steps': 24812, 'loss/train': 1.4928852319717407}
-03/04/2022 18:36:12 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/04/2022 18:36:17 - INFO - codeparrot_training - Step 24813: {'lr': 0.0004712559686520971, 'samples': 12704768, 'steps': 24813, 'loss/train': 1.1476874351501465}
-03/04/2022 18:36:20 - INFO - codeparrot_training - Step 24814: {'lr': 0.0004712534980705654, 'samples': 12705280, 'steps': 24814, 'loss/train': 2.1341991424560547}
-03/04/2022 18:36:21 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 18:36:25 - INFO - codeparrot_training - Step 24815: {'lr': 0.0004712510273893402, 'samples': 12705792, 'steps': 24815, 'loss/train': 1.3223248720169067}
-03/04/2022 18:36:28 - INFO - codeparrot_training - Step 24816: {'lr': 0.00047124855660842283, 'samples': 12706304, 'steps': 24816, 'loss/train': 2.0045816898345947}
-03/04/2022 18:36:29 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 18:36:33 - INFO - codeparrot_training - Step 24817: {'lr': 0.00047124608572781426, 'samples': 12706816, 'steps': 24817, 'loss/train': 1.4444947242736816}
-03/04/2022 18:36:36 - INFO - codeparrot_training - Step 24818: {'lr': 0.0004712436147475155, 'samples': 12707328, 'steps': 24818, 'loss/train': 1.4498720169067383}
-03/04/2022 18:36:37 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 18:36:42 - INFO - codeparrot_training - Step 24819: {'lr': 0.0004712411436675279, 'samples': 12707840, 'steps': 24819, 'loss/train': 1.1109795570373535}
-03/04/2022 18:36:45 - INFO - codeparrot_training - Step 24820: {'lr': 0.0004712386724878524, 'samples': 12708352, 'steps': 24820, 'loss/train': 2.0805931091308594}
-03/04/2022 18:36:46 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 18:36:50 - INFO - codeparrot_training - Step 24821: {'lr': 0.0004712362012084902, 'samples': 12708864, 'steps': 24821, 'loss/train': 1.9600995779037476}
-03/04/2022 18:36:53 - INFO - codeparrot_training - Step 24822: {'lr': 0.00047123372982944237, 'samples': 12709376, 'steps': 24822, 'loss/train': 2.2254559993743896}
-03/04/2022 18:36:54 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/04/2022 18:36:59 - INFO - codeparrot_training - Step 24823: {'lr': 0.00047123125835071004, 'samples': 12709888, 'steps': 24823, 'loss/train': 1.095399022102356}
-03/04/2022 18:37:02 - INFO - codeparrot_training - Step 24824: {'lr': 0.00047122878677229426, 'samples': 12710400, 'steps': 24824, 'loss/train': 2.186128616333008}
-03/04/2022 18:37:02 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 18:37:07 - INFO - codeparrot_training - Step 24825: {'lr': 0.0004712263150941962, 'samples': 12710912, 'steps': 24825, 'loss/train': 2.0428526401519775}
-03/04/2022 18:37:10 - INFO - codeparrot_training - Step 24826: {'lr': 0.0004712238433164171, 'samples': 12711424, 'steps': 24826, 'loss/train': 1.5557576417922974}
-03/04/2022 18:37:11 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 18:37:15 - INFO - codeparrot_training - Step 24827: {'lr': 0.00047122137143895785, 'samples': 12711936, 'steps': 24827, 'loss/train': 1.5509964227676392}
-03/04/2022 18:37:19 - INFO - codeparrot_training - Step 24828: {'lr': 0.0004712188994618197, 'samples': 12712448, 'steps': 24828, 'loss/train': 1.858122706413269}
-03/04/2022 18:37:19 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/04/2022 18:37:24 - INFO - codeparrot_training - Step 24829: {'lr': 0.0004712164273850037, 'samples': 12712960, 'steps': 24829, 'loss/train': 1.96244478225708}
-03/04/2022 18:37:27 - INFO - codeparrot_training - Step 24830: {'lr': 0.00047121395520851103, 'samples': 12713472, 'steps': 24830, 'loss/train': 2.172309398651123}
-03/04/2022 18:37:28 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/04/2022 18:37:32 - INFO - codeparrot_training - Step 24831: {'lr': 0.00047121148293234274, 'samples': 12713984, 'steps': 24831, 'loss/train': 2.1327712535858154}
-03/04/2022 18:37:36 - INFO - codeparrot_training - Step 24832: {'lr': 0.00047120901055649995, 'samples': 12714496, 'steps': 24832, 'loss/train': 2.144022226333618}
-03/04/2022 18:37:36 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/04/2022 18:37:41 - INFO - codeparrot_training - Step 24833: {'lr': 0.0004712065380809838, 'samples': 12715008, 'steps': 24833, 'loss/train': 1.895795226097107}
-03/04/2022 18:37:44 - INFO - codeparrot_training - Step 24834: {'lr': 0.0004712040655057954, 'samples': 12715520, 'steps': 24834, 'loss/train': 1.3786791563034058}
-03/04/2022 18:37:45 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 18:37:49 - INFO - codeparrot_training - Step 24835: {'lr': 0.0004712015928309359, 'samples': 12716032, 'steps': 24835, 'loss/train': 2.516359329223633}
-03/04/2022 18:37:52 - INFO - codeparrot_training - Step 24836: {'lr': 0.0004711991200564064, 'samples': 12716544, 'steps': 24836, 'loss/train': 0.6548260450363159}
-03/04/2022 18:37:53 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 18:37:58 - INFO - codeparrot_training - Step 24837: {'lr': 0.0004711966471822079, 'samples': 12717056, 'steps': 24837, 'loss/train': 1.8074663877487183}
-03/04/2022 18:38:01 - INFO - codeparrot_training - Step 24838: {'lr': 0.00047119417420834163, 'samples': 12717568, 'steps': 24838, 'loss/train': 1.9456706047058105}
-03/04/2022 18:38:02 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/04/2022 18:38:06 - INFO - codeparrot_training - Step 24839: {'lr': 0.00047119170113480867, 'samples': 12718080, 'steps': 24839, 'loss/train': 1.8541808128356934}
-03/04/2022 18:38:09 - INFO - codeparrot_training - Step 24840: {'lr': 0.00047118922796161026, 'samples': 12718592, 'steps': 24840, 'loss/train': 1.629652738571167}
-03/04/2022 18:38:10 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/04/2022 18:38:15 - INFO - codeparrot_training - Step 24841: {'lr': 0.00047118675468874727, 'samples': 12719104, 'steps': 24841, 'loss/train': 0.9782308340072632}
-03/04/2022 18:38:18 - INFO - codeparrot_training - Step 24842: {'lr': 0.00047118428131622095, 'samples': 12719616, 'steps': 24842, 'loss/train': 6.431194305419922}
-03/04/2022 18:38:20 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/04/2022 18:38:23 - INFO - codeparrot_training - Step 24843: {'lr': 0.00047118180784403243, 'samples': 12720128, 'steps': 24843, 'loss/train': 0.2310839593410492}
-03/04/2022 18:38:26 - INFO - codeparrot_training - Step 24844: {'lr': 0.0004711793342721828, 'samples': 12720640, 'steps': 24844, 'loss/train': 1.244694709777832}
-03/04/2022 18:38:28 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/04/2022 18:38:32 - INFO - codeparrot_training - Step 24845: {'lr': 0.00047117686060067315, 'samples': 12721152, 'steps': 24845, 'loss/train': 1.4048770666122437}
-03/04/2022 18:38:35 - INFO - codeparrot_training - Step 24846: {'lr': 0.00047117438682950467, 'samples': 12721664, 'steps': 24846, 'loss/train': 2.539346218109131}
-03/04/2022 18:38:36 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/04/2022 18:38:40 - INFO - codeparrot_training - Step 24847: {'lr': 0.0004711719129586784, 'samples': 12722176, 'steps': 24847, 'loss/train': 1.7890695333480835}
-03/04/2022 18:38:43 - INFO - codeparrot_training - Step 24848: {'lr': 0.0004711694389881955, 'samples': 12722688, 'steps': 24848, 'loss/train': 1.1161158084869385}
-03/04/2022 18:38:46 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/04/2022 18:38:49 - INFO - codeparrot_training - Step 24849: {'lr': 0.000471166964918057, 'samples': 12723200, 'steps': 24849, 'loss/train': 1.636245608329773}
-03/04/2022 18:38:52 - INFO - codeparrot_training - Step 24850: {'lr': 0.0004711644907482641, 'samples': 12723712, 'steps': 24850, 'loss/train': 2.0334742069244385}
-03/04/2022 18:38:54 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/04/2022 18:38:57 - INFO - codeparrot_training - Step 24851: {'lr': 0.00047116201647881794, 'samples': 12724224, 'steps': 24851, 'loss/train': 1.5915987491607666}
-03/04/2022 18:39:00 - INFO - codeparrot_training - Step 24852: {'lr': 0.00047115954210971955, 'samples': 12724736, 'steps': 24852, 'loss/train': 1.8039389848709106}
-03/04/2022 18:39:03 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/04/2022 18:39:06 - INFO - codeparrot_training - Step 24853: {'lr': 0.0004711570676409701, 'samples': 12725248, 'steps': 24853, 'loss/train': 2.2020270824432373}
-03/04/2022 18:39:09 - INFO - codeparrot_training - Step 24854: {'lr': 0.0004711545930725707, 'samples': 12725760, 'steps': 24854, 'loss/train': 2.2233572006225586}
-03/04/2022 18:39:12 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 18:39:14 - INFO - codeparrot_training - Step 24855: {'lr': 0.0004711521184045224, 'samples': 12726272, 'steps': 24855, 'loss/train': 2.358600378036499}
-03/04/2022 18:39:17 - INFO - codeparrot_training - Step 24856: {'lr': 0.0004711496436368264, 'samples': 12726784, 'steps': 24856, 'loss/train': 2.116020679473877}
-03/04/2022 18:39:20 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/04/2022 18:39:23 - INFO - codeparrot_training - Step 24857: {'lr': 0.00047114716876948384, 'samples': 12727296, 'steps': 24857, 'loss/train': 1.5870885848999023}
-03/04/2022 18:39:26 - INFO - codeparrot_training - Step 24858: {'lr': 0.0004711446938024957, 'samples': 12727808, 'steps': 24858, 'loss/train': 1.6376358270645142}
-03/04/2022 18:39:29 - INFO - codeparrot_training - Step 24859: {'lr': 0.00047114221873586316, 'samples': 12728320, 'steps': 24859, 'loss/train': 1.9628387689590454}
-03/04/2022 18:39:30 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 18:39:34 - INFO - codeparrot_training - Step 24860: {'lr': 0.00047113974356958744, 'samples': 12728832, 'steps': 24860, 'loss/train': 1.893445611000061}
-03/04/2022 18:39:38 - INFO - codeparrot_training - Step 24861: {'lr': 0.0004711372683036695, 'samples': 12729344, 'steps': 24861, 'loss/train': 2.0230894088745117}
-03/04/2022 18:39:38 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/04/2022 18:39:43 - INFO - codeparrot_training - Step 24862: {'lr': 0.0004711347929381105, 'samples': 12729856, 'steps': 24862, 'loss/train': 1.976881742477417}
-03/04/2022 18:39:46 - INFO - codeparrot_training - Step 24863: {'lr': 0.00047113231747291165, 'samples': 12730368, 'steps': 24863, 'loss/train': 2.106827974319458}
-03/04/2022 18:39:47 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/04/2022 18:39:51 - INFO - codeparrot_training - Step 24864: {'lr': 0.0004711298419080739, 'samples': 12730880, 'steps': 24864, 'loss/train': 1.6346181631088257}
-03/04/2022 18:39:54 - INFO - codeparrot_training - Step 24865: {'lr': 0.00047112736624359855, 'samples': 12731392, 'steps': 24865, 'loss/train': 1.6802377700805664}
-03/04/2022 18:39:55 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/04/2022 18:40:00 - INFO - codeparrot_training - Step 24866: {'lr': 0.00047112489047948655, 'samples': 12731904, 'steps': 24866, 'loss/train': 1.6255707740783691}
-03/04/2022 18:40:03 - INFO - codeparrot_training - Step 24867: {'lr': 0.00047112241461573913, 'samples': 12732416, 'steps': 24867, 'loss/train': 1.9285180568695068}
-03/04/2022 18:40:03 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 18:40:08 - INFO - codeparrot_training - Step 24868: {'lr': 0.0004711199386523573, 'samples': 12732928, 'steps': 24868, 'loss/train': 1.7694237232208252}
-03/04/2022 18:40:11 - INFO - codeparrot_training - Step 24869: {'lr': 0.0004711174625893423, 'samples': 12733440, 'steps': 24869, 'loss/train': 1.6412372589111328}
-03/04/2022 18:40:12 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/04/2022 18:40:17 - INFO - codeparrot_training - Step 24870: {'lr': 0.00047111498642669517, 'samples': 12733952, 'steps': 24870, 'loss/train': 2.040531635284424}
-03/04/2022 18:40:20 - INFO - codeparrot_training - Step 24871: {'lr': 0.00047111251016441704, 'samples': 12734464, 'steps': 24871, 'loss/train': 1.301876187324524}
-03/04/2022 18:40:20 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 18:40:25 - INFO - codeparrot_training - Step 24872: {'lr': 0.0004711100338025089, 'samples': 12734976, 'steps': 24872, 'loss/train': 3.1480305194854736}
-03/04/2022 18:40:28 - INFO - codeparrot_training - Step 24873: {'lr': 0.00047110755734097216, 'samples': 12735488, 'steps': 24873, 'loss/train': 1.8286571502685547}
-03/04/2022 18:40:29 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 18:40:34 - INFO - codeparrot_training - Step 24874: {'lr': 0.00047110508077980774, 'samples': 12736000, 'steps': 24874, 'loss/train': 2.0031323432922363}
-03/04/2022 18:40:37 - INFO - codeparrot_training - Step 24875: {'lr': 0.00047110260411901674, 'samples': 12736512, 'steps': 24875, 'loss/train': 1.9324493408203125}
-03/04/2022 18:40:37 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/04/2022 18:40:42 - INFO - codeparrot_training - Step 24876: {'lr': 0.0004711001273586003, 'samples': 12737024, 'steps': 24876, 'loss/train': 2.104465961456299}
-03/04/2022 18:40:45 - INFO - codeparrot_training - Step 24877: {'lr': 0.0004710976504985596, 'samples': 12737536, 'steps': 24877, 'loss/train': 1.1745017766952515}
-03/04/2022 18:40:46 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/04/2022 18:40:50 - INFO - codeparrot_training - Step 24878: {'lr': 0.00047109517353889575, 'samples': 12738048, 'steps': 24878, 'loss/train': 2.057974100112915}
-03/04/2022 18:40:54 - INFO - codeparrot_training - Step 24879: {'lr': 0.0004710926964796097, 'samples': 12738560, 'steps': 24879, 'loss/train': 1.3076591491699219}
-03/04/2022 18:40:55 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 18:40:59 - INFO - codeparrot_training - Step 24880: {'lr': 0.00047109021932070284, 'samples': 12739072, 'steps': 24880, 'loss/train': 0.7329766154289246}
-03/04/2022 18:41:02 - INFO - codeparrot_training - Step 24881: {'lr': 0.00047108774206217605, 'samples': 12739584, 'steps': 24881, 'loss/train': 1.622717022895813}
-03/04/2022 18:41:03 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/04/2022 18:41:07 - INFO - codeparrot_training - Step 24882: {'lr': 0.00047108526470403055, 'samples': 12740096, 'steps': 24882, 'loss/train': 1.7440543174743652}
-03/04/2022 18:41:11 - INFO - codeparrot_training - Step 24883: {'lr': 0.0004710827872462674, 'samples': 12740608, 'steps': 24883, 'loss/train': 1.5303852558135986}
-03/04/2022 18:41:12 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/04/2022 18:41:16 - INFO - codeparrot_training - Step 24884: {'lr': 0.00047108030968888784, 'samples': 12741120, 'steps': 24884, 'loss/train': 1.5286173820495605}
-03/04/2022 18:41:19 - INFO - codeparrot_training - Step 24885: {'lr': 0.00047107783203189285, 'samples': 12741632, 'steps': 24885, 'loss/train': 1.8543621301651}
-03/04/2022 18:41:20 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/04/2022 18:41:24 - INFO - codeparrot_training - Step 24886: {'lr': 0.0004710753542752836, 'samples': 12742144, 'steps': 24886, 'loss/train': 1.5102683305740356}
-03/04/2022 18:41:27 - INFO - codeparrot_training - Step 24887: {'lr': 0.0004710728764190612, 'samples': 12742656, 'steps': 24887, 'loss/train': 1.116586446762085}
-03/04/2022 18:41:28 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/04/2022 18:41:33 - INFO - codeparrot_training - Step 24888: {'lr': 0.0004710703984632268, 'samples': 12743168, 'steps': 24888, 'loss/train': 1.1865496635437012}
-03/04/2022 18:41:36 - INFO - codeparrot_training - Step 24889: {'lr': 0.0004710679204077815, 'samples': 12743680, 'steps': 24889, 'loss/train': 2.4639081954956055}
-03/04/2022 18:41:37 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 18:41:41 - INFO - codeparrot_training - Step 24890: {'lr': 0.0004710654422527264, 'samples': 12744192, 'steps': 24890, 'loss/train': 2.2100818157196045}
-03/04/2022 18:41:44 - INFO - codeparrot_training - Step 24891: {'lr': 0.0004710629639980626, 'samples': 12744704, 'steps': 24891, 'loss/train': 0.8656883835792542}
-03/04/2022 18:41:45 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/04/2022 18:41:49 - INFO - codeparrot_training - Step 24892: {'lr': 0.0004710604856437912, 'samples': 12745216, 'steps': 24892, 'loss/train': 2.1469385623931885}
-03/04/2022 18:41:53 - INFO - codeparrot_training - Step 24893: {'lr': 0.00047105800718991343, 'samples': 12745728, 'steps': 24893, 'loss/train': 1.8515512943267822}
-03/04/2022 18:41:54 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 18:41:58 - INFO - codeparrot_training - Step 24894: {'lr': 0.0004710555286364303, 'samples': 12746240, 'steps': 24894, 'loss/train': 2.153735876083374}
-03/04/2022 18:42:01 - INFO - codeparrot_training - Step 24895: {'lr': 0.000471053049983343, 'samples': 12746752, 'steps': 24895, 'loss/train': 2.042614459991455}
-03/04/2022 18:42:02 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 18:42:06 - INFO - codeparrot_training - Step 24896: {'lr': 0.0004710505712306526, 'samples': 12747264, 'steps': 24896, 'loss/train': 2.0345306396484375}
-03/04/2022 18:42:09 - INFO - codeparrot_training - Step 24897: {'lr': 0.00047104809237836023, 'samples': 12747776, 'steps': 24897, 'loss/train': 1.5434627532958984}
-03/04/2022 18:42:11 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/04/2022 18:42:15 - INFO - codeparrot_training - Step 24898: {'lr': 0.0004710456134264669, 'samples': 12748288, 'steps': 24898, 'loss/train': 2.387312412261963}
-03/04/2022 18:42:18 - INFO - codeparrot_training - Step 24899: {'lr': 0.0004710431343749739, 'samples': 12748800, 'steps': 24899, 'loss/train': 1.9605172872543335}
-03/04/2022 18:42:19 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/04/2022 18:42:24 - INFO - codeparrot_training - Step 24900: {'lr': 0.0004710406552238823, 'samples': 12749312, 'steps': 24900, 'loss/train': 0.6529803276062012}
-03/04/2022 18:42:27 - INFO - codeparrot_training - Step 24901: {'lr': 0.0004710381759731932, 'samples': 12749824, 'steps': 24901, 'loss/train': 0.7979986071586609}
-03/04/2022 18:42:29 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/04/2022 18:42:32 - INFO - codeparrot_training - Step 24902: {'lr': 0.0004710356966229077, 'samples': 12750336, 'steps': 24902, 'loss/train': 2.3305885791778564}
-03/04/2022 18:42:35 - INFO - codeparrot_training - Step 24903: {'lr': 0.00047103321717302684, 'samples': 12750848, 'steps': 24903, 'loss/train': 2.0249645709991455}
-03/04/2022 18:42:37 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/04/2022 18:42:40 - INFO - codeparrot_training - Step 24904: {'lr': 0.00047103073762355186, 'samples': 12751360, 'steps': 24904, 'loss/train': 2.050994634628296}
-03/04/2022 18:42:44 - INFO - codeparrot_training - Step 24905: {'lr': 0.0004710282579744839, 'samples': 12751872, 'steps': 24905, 'loss/train': 1.5681874752044678}
-03/04/2022 18:42:45 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/04/2022 18:42:49 - INFO - codeparrot_training - Step 24906: {'lr': 0.000471025778225824, 'samples': 12752384, 'steps': 24906, 'loss/train': 1.983225703239441}
-03/04/2022 18:42:52 - INFO - codeparrot_training - Step 24907: {'lr': 0.0004710232983775733, 'samples': 12752896, 'steps': 24907, 'loss/train': 2.021562099456787}
-03/04/2022 18:42:54 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/04/2022 18:42:57 - INFO - codeparrot_training - Step 24908: {'lr': 0.0004710208184297329, 'samples': 12753408, 'steps': 24908, 'loss/train': 1.7951819896697998}
-03/04/2022 18:43:01 - INFO - codeparrot_training - Step 24909: {'lr': 0.0004710183383823039, 'samples': 12753920, 'steps': 24909, 'loss/train': 1.7496154308319092}
-03/04/2022 18:43:03 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/04/2022 18:43:06 - INFO - codeparrot_training - Step 24910: {'lr': 0.00047101585823528745, 'samples': 12754432, 'steps': 24910, 'loss/train': 2.1086714267730713}
-03/04/2022 18:43:09 - INFO - codeparrot_training - Step 24911: {'lr': 0.0004710133779886847, 'samples': 12754944, 'steps': 24911, 'loss/train': 1.8396482467651367}
-03/04/2022 18:43:12 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 18:43:14 - INFO - codeparrot_training - Step 24912: {'lr': 0.00047101089764249674, 'samples': 12755456, 'steps': 24912, 'loss/train': 1.2248332500457764}
-03/04/2022 18:43:18 - INFO - codeparrot_training - Step 24913: {'lr': 0.0004710084171967246, 'samples': 12755968, 'steps': 24913, 'loss/train': 2.089012384414673}
-03/04/2022 18:43:20 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 18:43:23 - INFO - codeparrot_training - Step 24914: {'lr': 0.00047100593665136946, 'samples': 12756480, 'steps': 24914, 'loss/train': 1.5919601917266846}
-03/04/2022 18:43:26 - INFO - codeparrot_training - Step 24915: {'lr': 0.0004710034560064326, 'samples': 12756992, 'steps': 24915, 'loss/train': 2.4778003692626953}
-03/04/2022 18:43:28 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/04/2022 18:43:31 - INFO - codeparrot_training - Step 24916: {'lr': 0.00047100097526191486, 'samples': 12757504, 'steps': 24916, 'loss/train': 0.6893563866615295}
-03/04/2022 18:43:35 - INFO - codeparrot_training - Step 24917: {'lr': 0.0004709984944178176, 'samples': 12758016, 'steps': 24917, 'loss/train': 2.0988693237304688}
-03/04/2022 18:43:37 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/04/2022 18:43:40 - INFO - codeparrot_training - Step 24918: {'lr': 0.0004709960134741418, 'samples': 12758528, 'steps': 24918, 'loss/train': 1.8802374601364136}
-03/04/2022 18:43:43 - INFO - codeparrot_training - Step 24919: {'lr': 0.00047099353243088856, 'samples': 12759040, 'steps': 24919, 'loss/train': 2.2433252334594727}
-03/04/2022 18:43:46 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 18:43:48 - INFO - codeparrot_training - Step 24920: {'lr': 0.00047099105128805906, 'samples': 12759552, 'steps': 24920, 'loss/train': 2.100476026535034}
-03/04/2022 18:43:52 - INFO - codeparrot_training - Step 24921: {'lr': 0.00047098857004565444, 'samples': 12760064, 'steps': 24921, 'loss/train': 2.0219154357910156}
-03/04/2022 18:43:54 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/04/2022 18:43:57 - INFO - codeparrot_training - Step 24922: {'lr': 0.00047098608870367576, 'samples': 12760576, 'steps': 24922, 'loss/train': 3.877866744995117}
-03/04/2022 18:44:00 - INFO - codeparrot_training - Step 24923: {'lr': 0.00047098360726212406, 'samples': 12761088, 'steps': 24923, 'loss/train': 1.6774747371673584}
-03/04/2022 18:44:03 - INFO - codeparrot_training - Step 24924: {'lr': 0.0004709811257210007, 'samples': 12761600, 'steps': 24924, 'loss/train': 1.8757973909378052}
-03/04/2022 18:44:03 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 18:44:09 - INFO - codeparrot_training - Step 24925: {'lr': 0.0004709786440803066, 'samples': 12762112, 'steps': 24925, 'loss/train': 2.5808777809143066}
-03/04/2022 18:44:12 - INFO - codeparrot_training - Step 24926: {'lr': 0.00047097616234004295, 'samples': 12762624, 'steps': 24926, 'loss/train': 1.5634788274765015}
-03/04/2022 18:44:12 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 18:44:17 - INFO - codeparrot_training - Step 24927: {'lr': 0.00047097368050021083, 'samples': 12763136, 'steps': 24927, 'loss/train': 1.775482416152954}
-03/04/2022 18:44:20 - INFO - codeparrot_training - Step 24928: {'lr': 0.0004709711985608114, 'samples': 12763648, 'steps': 24928, 'loss/train': 1.88935387134552}
-03/04/2022 18:44:20 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/04/2022 18:44:26 - INFO - codeparrot_training - Step 24929: {'lr': 0.0004709687165218457, 'samples': 12764160, 'steps': 24929, 'loss/train': 2.3144657611846924}
-03/04/2022 18:44:29 - INFO - codeparrot_training - Step 24930: {'lr': 0.00047096623438331497, 'samples': 12764672, 'steps': 24930, 'loss/train': 1.6460819244384766}
-03/04/2022 18:44:29 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 18:44:34 - INFO - codeparrot_training - Step 24931: {'lr': 0.00047096375214522026, 'samples': 12765184, 'steps': 24931, 'loss/train': 2.142514705657959}
-03/04/2022 18:44:37 - INFO - codeparrot_training - Step 24932: {'lr': 0.0004709612698075627, 'samples': 12765696, 'steps': 24932, 'loss/train': 2.4411206245422363}
-03/04/2022 18:44:38 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/04/2022 18:44:43 - INFO - codeparrot_training - Step 24933: {'lr': 0.00047095878737034335, 'samples': 12766208, 'steps': 24933, 'loss/train': 1.6176233291625977}
-03/04/2022 18:44:46 - INFO - codeparrot_training - Step 24934: {'lr': 0.00047095630483356336, 'samples': 12766720, 'steps': 24934, 'loss/train': 1.9376760721206665}
-03/04/2022 18:44:46 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/04/2022 18:44:51 - INFO - codeparrot_training - Step 24935: {'lr': 0.00047095382219722396, 'samples': 12767232, 'steps': 24935, 'loss/train': 2.4250974655151367}
-03/04/2022 18:44:54 - INFO - codeparrot_training - Step 24936: {'lr': 0.0004709513394613261, 'samples': 12767744, 'steps': 24936, 'loss/train': 1.857292652130127}
-03/04/2022 18:44:55 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/04/2022 18:45:00 - INFO - codeparrot_training - Step 24937: {'lr': 0.00047094885662587104, 'samples': 12768256, 'steps': 24937, 'loss/train': 2.092085599899292}
-03/04/2022 18:45:03 - INFO - codeparrot_training - Step 24938: {'lr': 0.0004709463736908598, 'samples': 12768768, 'steps': 24938, 'loss/train': 1.8080271482467651}
-03/04/2022 18:45:03 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/04/2022 18:45:08 - INFO - codeparrot_training - Step 24939: {'lr': 0.0004709438906562935, 'samples': 12769280, 'steps': 24939, 'loss/train': 1.7955389022827148}
-03/04/2022 18:45:11 - INFO - codeparrot_training - Step 24940: {'lr': 0.0004709414075221734, 'samples': 12769792, 'steps': 24940, 'loss/train': 1.6947675943374634}
-03/04/2022 18:45:12 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/04/2022 18:45:17 - INFO - codeparrot_training - Step 24941: {'lr': 0.0004709389242885004, 'samples': 12770304, 'steps': 24941, 'loss/train': 2.4031200408935547}
-03/04/2022 18:45:20 - INFO - codeparrot_training - Step 24942: {'lr': 0.00047093644095527574, 'samples': 12770816, 'steps': 24942, 'loss/train': 1.7674018144607544}
-03/04/2022 18:45:20 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 18:45:25 - INFO - codeparrot_training - Step 24943: {'lr': 0.00047093395752250056, 'samples': 12771328, 'steps': 24943, 'loss/train': 2.4696271419525146}
-03/04/2022 18:45:28 - INFO - codeparrot_training - Step 24944: {'lr': 0.000470931473990176, 'samples': 12771840, 'steps': 24944, 'loss/train': 0.6401808261871338}
-03/04/2022 18:45:33 - INFO - codeparrot_training - Step 24945: {'lr': 0.00047092899035830303, 'samples': 12772352, 'steps': 24945, 'loss/train': 2.658026933670044}
-03/04/2022 18:45:37 - INFO - codeparrot_training - Step 24946: {'lr': 0.00047092650662688295, 'samples': 12772864, 'steps': 24946, 'loss/train': 2.1546244621276855}
-03/04/2022 18:45:37 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/04/2022 18:45:42 - INFO - codeparrot_training - Step 24947: {'lr': 0.00047092402279591674, 'samples': 12773376, 'steps': 24947, 'loss/train': 2.378253698348999}
-03/04/2022 18:45:45 - INFO - codeparrot_training - Step 24948: {'lr': 0.00047092153886540554, 'samples': 12773888, 'steps': 24948, 'loss/train': 3.363250970840454}
-03/04/2022 18:45:46 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/04/2022 18:45:50 - INFO - codeparrot_training - Step 24949: {'lr': 0.0004709190548353506, 'samples': 12774400, 'steps': 24949, 'loss/train': 1.3287534713745117}
-03/04/2022 18:45:53 - INFO - codeparrot_training - Step 24950: {'lr': 0.0004709165707057529, 'samples': 12774912, 'steps': 24950, 'loss/train': 2.2605483531951904}
-03/04/2022 18:45:54 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/04/2022 18:45:59 - INFO - codeparrot_training - Step 24951: {'lr': 0.0004709140864766136, 'samples': 12775424, 'steps': 24951, 'loss/train': 1.9181729555130005}
-03/04/2022 18:46:02 - INFO - codeparrot_training - Step 24952: {'lr': 0.0004709116021479338, 'samples': 12775936, 'steps': 24952, 'loss/train': 1.3643338680267334}
-03/04/2022 18:46:02 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/04/2022 18:46:07 - INFO - codeparrot_training - Step 24953: {'lr': 0.00047090911771971466, 'samples': 12776448, 'steps': 24953, 'loss/train': 2.471200466156006}
-03/04/2022 18:46:10 - INFO - codeparrot_training - Step 24954: {'lr': 0.0004709066331919573, 'samples': 12776960, 'steps': 24954, 'loss/train': 1.9177130460739136}
-03/04/2022 18:46:10 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/04/2022 18:46:16 - INFO - codeparrot_training - Step 24955: {'lr': 0.0004709041485646628, 'samples': 12777472, 'steps': 24955, 'loss/train': 1.465484619140625}
-03/04/2022 18:46:19 - INFO - codeparrot_training - Step 24956: {'lr': 0.0004709016638378323, 'samples': 12777984, 'steps': 24956, 'loss/train': 1.728784203529358}
-03/04/2022 18:46:19 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/04/2022 18:46:24 - INFO - codeparrot_training - Step 24957: {'lr': 0.00047089917901146694, 'samples': 12778496, 'steps': 24957, 'loss/train': 1.9586820602416992}
-03/04/2022 18:46:27 - INFO - codeparrot_training - Step 24958: {'lr': 0.0004708966940855678, 'samples': 12779008, 'steps': 24958, 'loss/train': 1.8313367366790771}
-03/04/2022 18:46:27 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 18:46:32 - INFO - codeparrot_training - Step 24959: {'lr': 0.00047089420906013603, 'samples': 12779520, 'steps': 24959, 'loss/train': 1.7662988901138306}
-03/04/2022 18:46:36 - INFO - codeparrot_training - Step 24960: {'lr': 0.0004708917239351727, 'samples': 12780032, 'steps': 24960, 'loss/train': 2.4338669776916504}
-03/04/2022 18:46:36 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/04/2022 18:46:41 - INFO - codeparrot_training - Step 24961: {'lr': 0.000470889238710679, 'samples': 12780544, 'steps': 24961, 'loss/train': 1.1666676998138428}
-03/04/2022 18:46:44 - INFO - codeparrot_training - Step 24962: {'lr': 0.00047088675338665596, 'samples': 12781056, 'steps': 24962, 'loss/train': 1.6253352165222168}
-03/04/2022 18:46:45 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/04/2022 18:46:49 - INFO - codeparrot_training - Step 24963: {'lr': 0.00047088426796310486, 'samples': 12781568, 'steps': 24963, 'loss/train': 2.147866725921631}
-03/04/2022 18:46:53 - INFO - codeparrot_training - Step 24964: {'lr': 0.00047088178244002665, 'samples': 12782080, 'steps': 24964, 'loss/train': 2.0557682514190674}
-03/04/2022 18:46:53 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/04/2022 18:46:58 - INFO - codeparrot_training - Step 24965: {'lr': 0.00047087929681742253, 'samples': 12782592, 'steps': 24965, 'loss/train': 2.175708532333374}
-03/04/2022 18:47:01 - INFO - codeparrot_training - Step 24966: {'lr': 0.00047087681109529364, 'samples': 12783104, 'steps': 24966, 'loss/train': 2.0590152740478516}
-03/04/2022 18:47:01 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/04/2022 18:47:06 - INFO - codeparrot_training - Step 24967: {'lr': 0.00047087432527364106, 'samples': 12783616, 'steps': 24967, 'loss/train': 1.9796541929244995}
-03/04/2022 18:47:10 - INFO - codeparrot_training - Step 24968: {'lr': 0.0004708718393524659, 'samples': 12784128, 'steps': 24968, 'loss/train': 2.414903402328491}
-03/04/2022 18:47:10 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/04/2022 18:47:15 - INFO - codeparrot_training - Step 24969: {'lr': 0.0004708693533317693, 'samples': 12784640, 'steps': 24969, 'loss/train': 2.6535918712615967}
-03/04/2022 18:47:18 - INFO - codeparrot_training - Step 24970: {'lr': 0.00047086686721155237, 'samples': 12785152, 'steps': 24970, 'loss/train': 1.1157567501068115}
-03/04/2022 18:47:18 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/04/2022 18:47:23 - INFO - codeparrot_training - Step 24971: {'lr': 0.00047086438099181615, 'samples': 12785664, 'steps': 24971, 'loss/train': 2.202526807785034}
-03/04/2022 18:47:26 - INFO - codeparrot_training - Step 24972: {'lr': 0.00047086189467256194, 'samples': 12786176, 'steps': 24972, 'loss/train': 0.7043659687042236}
-03/04/2022 18:47:27 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/04/2022 18:47:32 - INFO - codeparrot_training - Step 24973: {'lr': 0.0004708594082537908, 'samples': 12786688, 'steps': 24973, 'loss/train': 1.529456615447998}
-03/04/2022 18:47:35 - INFO - codeparrot_training - Step 24974: {'lr': 0.00047085692173550375, 'samples': 12787200, 'steps': 24974, 'loss/train': 2.5783801078796387}
-03/04/2022 18:47:35 - INFO - codeparrot_training - Skipping example with length 553 (seq_length=1024)
-03/04/2022 18:47:40 - INFO - codeparrot_training - Step 24975: {'lr': 0.00047085443511770206, 'samples': 12787712, 'steps': 24975, 'loss/train': 2.3002161979675293}
-03/04/2022 18:47:43 - INFO - codeparrot_training - Step 24976: {'lr': 0.0004708519484003867, 'samples': 12788224, 'steps': 24976, 'loss/train': 1.3256142139434814}
-03/04/2022 18:47:44 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 18:47:48 - INFO - codeparrot_training - Step 24977: {'lr': 0.0004708494615835589, 'samples': 12788736, 'steps': 24977, 'loss/train': 0.8662199378013611}
-03/04/2022 18:47:52 - INFO - codeparrot_training - Step 24978: {'lr': 0.00047084697466721973, 'samples': 12789248, 'steps': 24978, 'loss/train': 1.232911229133606}
-03/04/2022 18:47:52 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/04/2022 18:47:57 - INFO - codeparrot_training - Step 24979: {'lr': 0.0004708444876513703, 'samples': 12789760, 'steps': 24979, 'loss/train': 1.8080540895462036}
-03/04/2022 18:48:00 - INFO - codeparrot_training - Step 24980: {'lr': 0.0004708420005360118, 'samples': 12790272, 'steps': 24980, 'loss/train': 1.7607859373092651}
-03/04/2022 18:48:01 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/04/2022 18:48:05 - INFO - codeparrot_training - Step 24981: {'lr': 0.0004708395133211452, 'samples': 12790784, 'steps': 24981, 'loss/train': 2.2153525352478027}
-03/04/2022 18:48:09 - INFO - codeparrot_training - Step 24982: {'lr': 0.0004708370260067718, 'samples': 12791296, 'steps': 24982, 'loss/train': 1.7659032344818115}
-03/04/2022 18:48:09 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 18:48:14 - INFO - codeparrot_training - Step 24983: {'lr': 0.00047083453859289267, 'samples': 12791808, 'steps': 24983, 'loss/train': 2.293233633041382}
-03/04/2022 18:48:17 - INFO - codeparrot_training - Step 24984: {'lr': 0.00047083205107950886, 'samples': 12792320, 'steps': 24984, 'loss/train': 2.0944364070892334}
-03/04/2022 18:48:17 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/04/2022 18:48:22 - INFO - codeparrot_training - Step 24985: {'lr': 0.00047082956346662153, 'samples': 12792832, 'steps': 24985, 'loss/train': 2.52630615234375}
-03/04/2022 18:48:25 - INFO - codeparrot_training - Step 24986: {'lr': 0.00047082707575423177, 'samples': 12793344, 'steps': 24986, 'loss/train': 1.5145107507705688}
-03/04/2022 18:48:26 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 18:48:31 - INFO - codeparrot_training - Step 24987: {'lr': 0.00047082458794234087, 'samples': 12793856, 'steps': 24987, 'loss/train': 1.5130829811096191}
-03/04/2022 18:48:34 - INFO - codeparrot_training - Step 24988: {'lr': 0.0004708221000309497, 'samples': 12794368, 'steps': 24988, 'loss/train': 0.8722270131111145}
-03/04/2022 18:48:34 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/04/2022 18:48:39 - INFO - codeparrot_training - Step 24989: {'lr': 0.0004708196120200595, 'samples': 12794880, 'steps': 24989, 'loss/train': 1.739190936088562}
-03/04/2022 18:48:42 - INFO - codeparrot_training - Step 24990: {'lr': 0.0004708171239096715, 'samples': 12795392, 'steps': 24990, 'loss/train': 2.555328845977783}
-03/04/2022 18:48:48 - INFO - codeparrot_training - Step 24991: {'lr': 0.00047081463569978655, 'samples': 12795904, 'steps': 24991, 'loss/train': 1.9925888776779175}
-03/04/2022 18:48:51 - INFO - codeparrot_training - Step 24992: {'lr': 0.00047081214739040606, 'samples': 12796416, 'steps': 24992, 'loss/train': 2.0597944259643555}
-03/04/2022 18:48:51 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 18:48:57 - INFO - codeparrot_training - Step 24993: {'lr': 0.000470809658981531, 'samples': 12796928, 'steps': 24993, 'loss/train': 2.0660297870635986}
-03/04/2022 18:49:00 - INFO - codeparrot_training - Step 24994: {'lr': 0.00047080717047316245, 'samples': 12797440, 'steps': 24994, 'loss/train': 1.3143672943115234}
-03/04/2022 18:49:03 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/04/2022 18:49:05 - INFO - codeparrot_training - Step 24995: {'lr': 0.0004708046818653017, 'samples': 12797952, 'steps': 24995, 'loss/train': 1.9656524658203125}
-03/04/2022 18:49:08 - INFO - codeparrot_training - Step 24996: {'lr': 0.0004708021931579497, 'samples': 12798464, 'steps': 24996, 'loss/train': 2.3586835861206055}
-03/04/2022 18:49:11 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/04/2022 18:49:14 - INFO - codeparrot_training - Step 24997: {'lr': 0.00047079970435110765, 'samples': 12798976, 'steps': 24997, 'loss/train': 1.260233998298645}
-03/04/2022 18:49:17 - INFO - codeparrot_training - Step 24998: {'lr': 0.0004707972154447766, 'samples': 12799488, 'steps': 24998, 'loss/train': 1.7081503868103027}
-03/04/2022 18:49:20 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 18:49:22 - INFO - codeparrot_training - Step 24999: {'lr': 0.00047079472643895784, 'samples': 12800000, 'steps': 24999, 'loss/train': 1.3369230031967163}
-03/04/2022 18:49:22 - INFO - codeparrot_training - Evaluating and saving model checkpoint
-03/04/2022 18:49:37 - WARNING - huggingface_hub.repository - Several commits (5) will be pushed upstream.
-03/04/2022 18:49:37 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
-03/04/2022 18:50:21 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/cm_code_clippy
-   3033721..20b2be6  glowing-puddle-3 -> glowing-puddle-3
-
-03/04/2022 18:50:26 - INFO - codeparrot_training - Step 25000: {'lr': 0.00047079223733365234, 'samples': 12800512, 'steps': 25000, 'loss/train': 2.2720863819122314}
-03/04/2022 18:50:29 - INFO - codeparrot_training - Step 25001: {'lr': 0.0004707897481288612, 'samples': 12801024, 'steps': 25001, 'loss/train': 2.1621482372283936}
-03/04/2022 18:50:29 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/04/2022 18:50:34 - INFO - codeparrot_training - Step 25002: {'lr': 0.00047078725882458575, 'samples': 12801536, 'steps': 25002, 'loss/train': 1.4488753080368042}
-03/04/2022 18:50:38 - INFO - codeparrot_training - Step 25003: {'lr': 0.0004707847694208269, 'samples': 12802048, 'steps': 25003, 'loss/train': 0.9972745180130005}
-03/04/2022 18:50:38 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/04/2022 18:50:43 - INFO - codeparrot_training - Step 25004: {'lr': 0.0004707822799175858, 'samples': 12802560, 'steps': 25004, 'loss/train': 2.1641221046447754}
-03/04/2022 18:50:46 - INFO - codeparrot_training - Step 25005: {'lr': 0.00047077979031486363, 'samples': 12803072, 'steps': 25005, 'loss/train': 1.856127142906189}
-03/04/2022 18:50:46 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 18:50:51 - INFO - codeparrot_training - Step 25006: {'lr': 0.0004707773006126615, 'samples': 12803584, 'steps': 25006, 'loss/train': 1.4223352670669556}
-03/04/2022 18:50:54 - INFO - codeparrot_training - Step 25007: {'lr': 0.0004707748108109805, 'samples': 12804096, 'steps': 25007, 'loss/train': 0.637409508228302}
-03/04/2022 18:50:55 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/04/2022 18:51:00 - INFO - codeparrot_training - Step 25008: {'lr': 0.0004707723209098218, 'samples': 12804608, 'steps': 25008, 'loss/train': 2.6404271125793457}
-03/04/2022 18:51:03 - INFO - codeparrot_training - Step 25009: {'lr': 0.0004707698309091865, 'samples': 12805120, 'steps': 25009, 'loss/train': 1.7266995906829834}
-03/04/2022 18:51:04 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/04/2022 18:51:08 - INFO - codeparrot_training - Step 25010: {'lr': 0.00047076734080907576, 'samples': 12805632, 'steps': 25010, 'loss/train': 1.8949495553970337}
-03/04/2022 18:51:12 - INFO - codeparrot_training - Step 25011: {'lr': 0.0004707648506094906, 'samples': 12806144, 'steps': 25011, 'loss/train': 1.8175896406173706}
-03/04/2022 18:51:12 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 18:51:17 - INFO - codeparrot_training - Step 25012: {'lr': 0.0004707623603104322, 'samples': 12806656, 'steps': 25012, 'loss/train': 1.9081592559814453}
-03/04/2022 18:51:20 - INFO - codeparrot_training - Step 25013: {'lr': 0.0004707598699119018, 'samples': 12807168, 'steps': 25013, 'loss/train': 2.038910388946533}
-03/04/2022 18:51:21 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/04/2022 18:51:25 - INFO - codeparrot_training - Step 25014: {'lr': 0.0004707573794139003, 'samples': 12807680, 'steps': 25014, 'loss/train': 2.047226905822754}
-03/04/2022 18:51:28 - INFO - codeparrot_training - Step 25015: {'lr': 0.0004707548888164289, 'samples': 12808192, 'steps': 25015, 'loss/train': 1.7910176515579224}
-03/04/2022 18:51:29 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/04/2022 18:51:34 - INFO - codeparrot_training - Step 25016: {'lr': 0.0004707523981194889, 'samples': 12808704, 'steps': 25016, 'loss/train': 3.326096296310425}
-03/04/2022 18:51:37 - INFO - codeparrot_training - Step 25017: {'lr': 0.00047074990732308116, 'samples': 12809216, 'steps': 25017, 'loss/train': 1.117077112197876}
-03/04/2022 18:51:37 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/04/2022 18:51:42 - INFO - codeparrot_training - Step 25018: {'lr': 0.00047074741642720694, 'samples': 12809728, 'steps': 25018, 'loss/train': 0.4787640869617462}
-03/04/2022 18:51:45 - INFO - codeparrot_training - Step 25019: {'lr': 0.0004707449254318673, 'samples': 12810240, 'steps': 25019, 'loss/train': 2.1188161373138428}
-03/04/2022 18:51:46 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/04/2022 18:51:51 - INFO - codeparrot_training - Step 25020: {'lr': 0.0004707424343370635, 'samples': 12810752, 'steps': 25020, 'loss/train': 1.9546939134597778}
-03/04/2022 18:51:54 - INFO - codeparrot_training - Step 25021: {'lr': 0.00047073994314279647, 'samples': 12811264, 'steps': 25021, 'loss/train': 1.2242841720581055}
-03/04/2022 18:51:55 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/04/2022 18:51:59 - INFO - codeparrot_training - Step 25022: {'lr': 0.0004707374518490675, 'samples': 12811776, 'steps': 25022, 'loss/train': 1.6900838613510132}
-03/04/2022 18:52:02 - INFO - codeparrot_training - Step 25023: {'lr': 0.0004707349604558776, 'samples': 12812288, 'steps': 25023, 'loss/train': 1.8855787515640259}
-03/04/2022 18:52:03 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/04/2022 18:52:07 - INFO - codeparrot_training - Step 25024: {'lr': 0.00047073246896322797, 'samples': 12812800, 'steps': 25024, 'loss/train': 1.83464515209198}
-03/04/2022 18:52:11 - INFO - codeparrot_training - Step 25025: {'lr': 0.00047072997737111966, 'samples': 12813312, 'steps': 25025, 'loss/train': 0.9294046759605408}
-03/04/2022 18:52:12 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/04/2022 18:52:16 - INFO - codeparrot_training - Step 25026: {'lr': 0.0004707274856795538, 'samples': 12813824, 'steps': 25026, 'loss/train': 1.5606272220611572}
-03/04/2022 18:52:19 - INFO - codeparrot_training - Step 25027: {'lr': 0.00047072499388853164, 'samples': 12814336, 'steps': 25027, 'loss/train': 1.9171658754348755}
-03/04/2022 18:52:20 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/04/2022 18:52:24 - INFO - codeparrot_training - Step 25028: {'lr': 0.0004707225019980541, 'samples': 12814848, 'steps': 25028, 'loss/train': 1.8090293407440186}
-03/04/2022 18:52:28 - INFO - codeparrot_training - Step 25029: {'lr': 0.00047072001000812247, 'samples': 12815360, 'steps': 25029, 'loss/train': 2.993135929107666}
-03/04/2022 18:52:29 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/04/2022 18:52:33 - INFO - codeparrot_training - Step 25030: {'lr': 0.00047071751791873774, 'samples': 12815872, 'steps': 25030, 'loss/train': 1.5688202381134033}
-03/04/2022 18:52:36 - INFO - codeparrot_training - Step 25031: {'lr': 0.0004707150257299012, 'samples': 12816384, 'steps': 25031, 'loss/train': 1.249319076538086}
-03/04/2022 18:52:37 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/04/2022 18:52:41 - INFO - codeparrot_training - Step 25032: {'lr': 0.0004707125334416138, 'samples': 12816896, 'steps': 25032, 'loss/train': 1.584047794342041}
-03/04/2022 18:52:45 - INFO - codeparrot_training - Step 25033: {'lr': 0.00047071004105387677, 'samples': 12817408, 'steps': 25033, 'loss/train': 2.4073853492736816}
-03/04/2022 18:52:46 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/04/2022 18:52:50 - INFO - codeparrot_training - Step 25034: {'lr': 0.00047070754856669115, 'samples': 12817920, 'steps': 25034, 'loss/train': 0.6741406321525574}
-03/04/2022 18:52:53 - INFO - codeparrot_training - Step 25035: {'lr': 0.0004707050559800582, 'samples': 12818432, 'steps': 25035, 'loss/train': 1.9144023656845093}
-03/04/2022 18:52:54 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/04/2022 18:52:58 - INFO - codeparrot_training - Step 25036: {'lr': 0.00047070256329397893, 'samples': 12818944, 'steps': 25036, 'loss/train': 1.4518067836761475}
-03/04/2022 18:53:02 - INFO - codeparrot_training - Step 25037: {'lr': 0.0004707000705084545, 'samples': 12819456, 'steps': 25037, 'loss/train': 1.837268590927124}
-03/04/2022 18:53:03 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/04/2022 18:53:07 - INFO - codeparrot_training - Step 25038: {'lr': 0.000470697577623486, 'samples': 12819968, 'steps': 25038, 'loss/train': 2.016571283340454}
-03/04/2022 18:53:10 - INFO - codeparrot_training - Step 25039: {'lr': 0.0004706950846390746, 'samples': 12820480, 'steps': 25039, 'loss/train': 2.1503210067749023}
-03/04/2022 18:53:13 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 18:53:16 - INFO - codeparrot_training - Step 25040: {'lr': 0.00047069259155522135, 'samples': 12820992, 'steps': 25040, 'loss/train': 2.202559471130371}
-03/04/2022 18:53:19 - INFO - codeparrot_training - Step 25041: {'lr': 0.0004706900983719274, 'samples': 12821504, 'steps': 25041, 'loss/train': 2.034719467163086}
-03/04/2022 18:53:22 - INFO - codeparrot_training - Step 25042: {'lr': 0.000470687605089194, 'samples': 12822016, 'steps': 25042, 'loss/train': 1.992671251296997}
-03/04/2022 18:53:22 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/04/2022 18:53:27 - INFO - codeparrot_training - Step 25043: {'lr': 0.0004706851117070221, 'samples': 12822528, 'steps': 25043, 'loss/train': 0.6675636768341064}
-03/04/2022 18:53:30 - INFO - codeparrot_training - Step 25044: {'lr': 0.0004706826182254129, 'samples': 12823040, 'steps': 25044, 'loss/train': 2.1059088706970215}
-03/04/2022 18:53:30 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/04/2022 18:53:36 - INFO - codeparrot_training - Step 25045: {'lr': 0.0004706801246443676, 'samples': 12823552, 'steps': 25045, 'loss/train': 1.8442326784133911}
-03/04/2022 18:53:39 - INFO - codeparrot_training - Step 25046: {'lr': 0.00047067763096388717, 'samples': 12824064, 'steps': 25046, 'loss/train': 2.0886495113372803}
-03/04/2022 18:53:39 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/04/2022 18:53:44 - INFO - codeparrot_training - Step 25047: {'lr': 0.00047067513718397283, 'samples': 12824576, 'steps': 25047, 'loss/train': 2.031420946121216}
-03/04/2022 18:53:48 - INFO - codeparrot_training - Step 25048: {'lr': 0.0004706726433046256, 'samples': 12825088, 'steps': 25048, 'loss/train': 1.1181421279907227}
-03/04/2022 18:53:48 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/04/2022 18:53:53 - INFO - codeparrot_training - Step 25049: {'lr': 0.00047067014932584674, 'samples': 12825600, 'steps': 25049, 'loss/train': 1.6002109050750732}
-03/04/2022 18:53:56 - INFO - codeparrot_training - Step 25050: {'lr': 0.0004706676552476373, 'samples': 12826112, 'steps': 25050, 'loss/train': 2.216784715652466}
-03/04/2022 18:53:56 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 18:54:01 - INFO - codeparrot_training - Step 25051: {'lr': 0.0004706651610699985, 'samples': 12826624, 'steps': 25051, 'loss/train': 2.6303858757019043}
-03/04/2022 18:54:04 - INFO - codeparrot_training - Step 25052: {'lr': 0.00047066266679293125, 'samples': 12827136, 'steps': 25052, 'loss/train': 1.6276215314865112}
-03/04/2022 18:54:04 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/04/2022 18:54:10 - INFO - codeparrot_training - Step 25053: {'lr': 0.0004706601724164369, 'samples': 12827648, 'steps': 25053, 'loss/train': 2.3101158142089844}
-03/04/2022 18:54:13 - INFO - codeparrot_training - Step 25054: {'lr': 0.0004706576779405165, 'samples': 12828160, 'steps': 25054, 'loss/train': 1.8676996231079102}
-03/04/2022 18:54:13 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/04/2022 18:54:18 - INFO - codeparrot_training - Step 25055: {'lr': 0.0004706551833651711, 'samples': 12828672, 'steps': 25055, 'loss/train': 2.157733678817749}
-03/04/2022 18:54:22 - INFO - codeparrot_training - Step 25056: {'lr': 0.0004706526886904019, 'samples': 12829184, 'steps': 25056, 'loss/train': 1.7926851511001587}
-03/04/2022 18:54:22 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 18:54:27 - INFO - codeparrot_training - Step 25057: {'lr': 0.00047065019391621, 'samples': 12829696, 'steps': 25057, 'loss/train': 2.1089589595794678}
-03/04/2022 18:54:30 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 18:54:32 - INFO - codeparrot_training - Step 25058: {'lr': 0.0004706476990425965, 'samples': 12830208, 'steps': 25058, 'loss/train': 1.7082737684249878}
-03/04/2022 18:54:35 - INFO - codeparrot_training - Step 25059: {'lr': 0.0004706452040695626, 'samples': 12830720, 'steps': 25059, 'loss/train': 1.017737627029419}
-03/04/2022 18:54:38 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/04/2022 18:54:41 - INFO - codeparrot_training - Step 25060: {'lr': 0.0004706427089971093, 'samples': 12831232, 'steps': 25060, 'loss/train': 1.5445334911346436}
-03/04/2022 18:54:44 - INFO - codeparrot_training - Step 25061: {'lr': 0.0004706402138252379, 'samples': 12831744, 'steps': 25061, 'loss/train': 1.8106290102005005}
-03/04/2022 18:54:46 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 18:54:49 - INFO - codeparrot_training - Step 25062: {'lr': 0.00047063771855394935, 'samples': 12832256, 'steps': 25062, 'loss/train': 1.4975013732910156}
-03/04/2022 18:54:52 - INFO - codeparrot_training - Step 25063: {'lr': 0.00047063522318324484, 'samples': 12832768, 'steps': 25063, 'loss/train': 1.8618700504302979}
-03/04/2022 18:54:55 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/04/2022 18:54:58 - INFO - codeparrot_training - Step 25064: {'lr': 0.00047063272771312556, 'samples': 12833280, 'steps': 25064, 'loss/train': 1.593176245689392}
-03/04/2022 18:55:01 - INFO - codeparrot_training - Step 25065: {'lr': 0.0004706302321435926, 'samples': 12833792, 'steps': 25065, 'loss/train': 1.29747474193573}
-03/04/2022 18:55:03 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/04/2022 18:55:06 - INFO - codeparrot_training - Step 25066: {'lr': 0.00047062773647464694, 'samples': 12834304, 'steps': 25066, 'loss/train': 1.6648106575012207}
-03/04/2022 18:55:09 - INFO - codeparrot_training - Step 25067: {'lr': 0.00047062524070628993, 'samples': 12834816, 'steps': 25067, 'loss/train': 1.6909915208816528}
-03/04/2022 18:55:11 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 18:55:14 - INFO - codeparrot_training - Step 25068: {'lr': 0.00047062274483852253, 'samples': 12835328, 'steps': 25068, 'loss/train': 1.6439026594161987}
-03/04/2022 18:55:17 - INFO - codeparrot_training - Step 25069: {'lr': 0.000470620248871346, 'samples': 12835840, 'steps': 25069, 'loss/train': 2.0186049938201904}
-03/04/2022 18:55:20 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/04/2022 18:55:23 - INFO - codeparrot_training - Step 25070: {'lr': 0.00047061775280476134, 'samples': 12836352, 'steps': 25070, 'loss/train': 1.5581883192062378}
-03/04/2022 18:55:26 - INFO - codeparrot_training - Step 25071: {'lr': 0.0004706152566387697, 'samples': 12836864, 'steps': 25071, 'loss/train': 2.0358872413635254}
-03/04/2022 18:55:28 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 18:55:31 - INFO - codeparrot_training - Step 25072: {'lr': 0.0004706127603733723, 'samples': 12837376, 'steps': 25072, 'loss/train': 2.5719916820526123}
-03/04/2022 18:55:35 - INFO - codeparrot_training - Step 25073: {'lr': 0.00047061026400857015, 'samples': 12837888, 'steps': 25073, 'loss/train': 2.193042755126953}
-03/04/2022 18:55:37 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/04/2022 18:55:40 - INFO - codeparrot_training - Step 25074: {'lr': 0.0004706077675443644, 'samples': 12838400, 'steps': 25074, 'loss/train': 1.1790868043899536}
-03/04/2022 18:55:43 - INFO - codeparrot_training - Step 25075: {'lr': 0.00047060527098075625, 'samples': 12838912, 'steps': 25075, 'loss/train': 0.6706814169883728}
-03/04/2022 18:55:45 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/04/2022 18:55:48 - INFO - codeparrot_training - Step 25076: {'lr': 0.0004706027743177467, 'samples': 12839424, 'steps': 25076, 'loss/train': 1.542373776435852}
-03/04/2022 18:55:51 - INFO - codeparrot_training - Step 25077: {'lr': 0.000470600277555337, 'samples': 12839936, 'steps': 25077, 'loss/train': 1.8712016344070435}
-03/04/2022 18:55:54 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 18:55:57 - INFO - codeparrot_training - Step 25078: {'lr': 0.0004705977806935282, 'samples': 12840448, 'steps': 25078, 'loss/train': 2.2446393966674805}
-03/04/2022 18:56:00 - INFO - codeparrot_training - Step 25079: {'lr': 0.00047059528373232147, 'samples': 12840960, 'steps': 25079, 'loss/train': 0.7199758291244507}
-03/04/2022 18:56:02 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/04/2022 18:56:05 - INFO - codeparrot_training - Step 25080: {'lr': 0.0004705927866717179, 'samples': 12841472, 'steps': 25080, 'loss/train': 2.435274124145508}
-03/04/2022 18:56:08 - INFO - codeparrot_training - Step 25081: {'lr': 0.0004705902895117186, 'samples': 12841984, 'steps': 25081, 'loss/train': 2.277270555496216}
-03/04/2022 18:56:11 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/04/2022 18:56:14 - INFO - codeparrot_training - Step 25082: {'lr': 0.00047058779225232474, 'samples': 12842496, 'steps': 25082, 'loss/train': 2.2829880714416504}
-03/04/2022 18:56:17 - INFO - codeparrot_training - Step 25083: {'lr': 0.0004705852948935374, 'samples': 12843008, 'steps': 25083, 'loss/train': 2.3227596282958984}
-03/04/2022 18:56:19 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/04/2022 18:56:22 - INFO - codeparrot_training - Step 25084: {'lr': 0.00047058279743535775, 'samples': 12843520, 'steps': 25084, 'loss/train': 2.129922389984131}
-03/04/2022 18:56:25 - INFO - codeparrot_training - Step 25085: {'lr': 0.0004705802998777869, 'samples': 12844032, 'steps': 25085, 'loss/train': 1.6463955640792847}
-03/04/2022 18:56:27 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 18:56:30 - INFO - codeparrot_training - Step 25086: {'lr': 0.0004705778022208259, 'samples': 12844544, 'steps': 25086, 'loss/train': 0.408038467168808}
-03/04/2022 18:56:34 - INFO - codeparrot_training - Step 25087: {'lr': 0.000470575304464476, 'samples': 12845056, 'steps': 25087, 'loss/train': 1.2450834512710571}
-03/04/2022 18:56:35 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 18:56:39 - INFO - codeparrot_training - Step 25088: {'lr': 0.00047057280660873835, 'samples': 12845568, 'steps': 25088, 'loss/train': 1.9729628562927246}
-03/04/2022 18:56:42 - INFO - codeparrot_training - Step 25089: {'lr': 0.00047057030865361397, 'samples': 12846080, 'steps': 25089, 'loss/train': 2.626375198364258}
-03/04/2022 18:56:44 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 18:56:47 - INFO - codeparrot_training - Step 25090: {'lr': 0.0004705678105991039, 'samples': 12846592, 'steps': 25090, 'loss/train': 1.944675087928772}
-03/04/2022 18:56:50 - INFO - codeparrot_training - Step 25091: {'lr': 0.00047056531244520945, 'samples': 12847104, 'steps': 25091, 'loss/train': 1.8182783126831055}
-03/04/2022 18:56:52 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/04/2022 18:56:56 - INFO - codeparrot_training - Step 25092: {'lr': 0.0004705628141919317, 'samples': 12847616, 'steps': 25092, 'loss/train': 1.8274507522583008}
-03/04/2022 18:56:59 - INFO - codeparrot_training - Step 25093: {'lr': 0.00047056031583927175, 'samples': 12848128, 'steps': 25093, 'loss/train': 1.9040497541427612}
-03/04/2022 18:57:01 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 18:57:04 - INFO - codeparrot_training - Step 25094: {'lr': 0.00047055781738723063, 'samples': 12848640, 'steps': 25094, 'loss/train': 1.5787038803100586}
-03/04/2022 18:57:07 - INFO - codeparrot_training - Step 25095: {'lr': 0.0004705553188358096, 'samples': 12849152, 'steps': 25095, 'loss/train': 1.8234866857528687}
-03/04/2022 18:57:09 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 18:57:13 - INFO - codeparrot_training - Step 25096: {'lr': 0.00047055282018500976, 'samples': 12849664, 'steps': 25096, 'loss/train': 0.7234331369400024}
-03/04/2022 18:57:16 - INFO - codeparrot_training - Step 25097: {'lr': 0.0004705503214348323, 'samples': 12850176, 'steps': 25097, 'loss/train': 2.4037978649139404}
-03/04/2022 18:57:18 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/04/2022 18:57:21 - INFO - codeparrot_training - Step 25098: {'lr': 0.0004705478225852782, 'samples': 12850688, 'steps': 25098, 'loss/train': 0.9351075291633606}
-03/04/2022 18:57:24 - INFO - codeparrot_training - Step 25099: {'lr': 0.0004705453236363486, 'samples': 12851200, 'steps': 25099, 'loss/train': 1.5597867965698242}
-03/04/2022 18:57:26 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 18:57:30 - INFO - codeparrot_training - Step 25100: {'lr': 0.00047054282458804477, 'samples': 12851712, 'steps': 25100, 'loss/train': 1.3071184158325195}
-03/04/2022 18:57:33 - INFO - codeparrot_training - Step 25101: {'lr': 0.0004705403254403677, 'samples': 12852224, 'steps': 25101, 'loss/train': 0.7174893021583557}
-03/04/2022 18:57:35 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/04/2022 18:57:38 - INFO - codeparrot_training - Step 25102: {'lr': 0.0004705378261933186, 'samples': 12852736, 'steps': 25102, 'loss/train': 1.067669153213501}
-03/04/2022 18:57:41 - INFO - codeparrot_training - Step 25103: {'lr': 0.0004705353268468985, 'samples': 12853248, 'steps': 25103, 'loss/train': 1.7714552879333496}
-03/04/2022 18:57:44 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/04/2022 18:57:47 - INFO - codeparrot_training - Step 25104: {'lr': 0.00047053282740110863, 'samples': 12853760, 'steps': 25104, 'loss/train': 2.1500978469848633}
-03/04/2022 18:57:50 - INFO - codeparrot_training - Step 25105: {'lr': 0.00047053032785595005, 'samples': 12854272, 'steps': 25105, 'loss/train': 1.275953769683838}
-03/04/2022 18:57:52 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 18:57:55 - INFO - codeparrot_training - Step 25106: {'lr': 0.0004705278282114239, 'samples': 12854784, 'steps': 25106, 'loss/train': 1.6331745386123657}
-03/04/2022 18:57:58 - INFO - codeparrot_training - Step 25107: {'lr': 0.0004705253284675314, 'samples': 12855296, 'steps': 25107, 'loss/train': 1.9976993799209595}
-03/04/2022 18:58:01 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 18:58:04 - INFO - codeparrot_training - Step 25108: {'lr': 0.00047052282862427355, 'samples': 12855808, 'steps': 25108, 'loss/train': 1.6986401081085205}
-03/04/2022 18:58:07 - INFO - codeparrot_training - Step 25109: {'lr': 0.0004705203286816514, 'samples': 12856320, 'steps': 25109, 'loss/train': 2.0565803050994873}
-03/04/2022 18:58:09 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 18:58:12 - INFO - codeparrot_training - Step 25110: {'lr': 0.0004705178286396663, 'samples': 12856832, 'steps': 25110, 'loss/train': 2.383732795715332}
-03/04/2022 18:58:15 - INFO - codeparrot_training - Step 25111: {'lr': 0.0004705153284983192, 'samples': 12857344, 'steps': 25111, 'loss/train': 2.3178975582122803}
-03/04/2022 18:58:19 - INFO - codeparrot_training - Step 25112: {'lr': 0.00047051282825761145, 'samples': 12857856, 'steps': 25112, 'loss/train': 6.633519172668457}
-03/04/2022 18:58:19 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/04/2022 18:58:24 - INFO - codeparrot_training - Step 25113: {'lr': 0.0004705103279175439, 'samples': 12858368, 'steps': 25113, 'loss/train': 1.6179064512252808}
-03/04/2022 18:58:27 - INFO - codeparrot_training - Step 25114: {'lr': 0.0004705078274781178, 'samples': 12858880, 'steps': 25114, 'loss/train': 2.0531108379364014}
-03/04/2022 18:58:27 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/04/2022 18:58:32 - INFO - codeparrot_training - Step 25115: {'lr': 0.0004705053269393343, 'samples': 12859392, 'steps': 25115, 'loss/train': 1.9238201379776}
-03/04/2022 18:58:35 - INFO - codeparrot_training - Step 25116: {'lr': 0.00047050282630119444, 'samples': 12859904, 'steps': 25116, 'loss/train': 1.5421780347824097}
-03/04/2022 18:58:36 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 18:58:41 - INFO - codeparrot_training - Step 25117: {'lr': 0.0004705003255636995, 'samples': 12860416, 'steps': 25117, 'loss/train': 0.8592211008071899}
-03/04/2022 18:58:44 - INFO - codeparrot_training - Step 25118: {'lr': 0.0004704978247268505, 'samples': 12860928, 'steps': 25118, 'loss/train': 0.7966042757034302}
-03/04/2022 18:58:44 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/04/2022 18:58:49 - INFO - codeparrot_training - Step 25119: {'lr': 0.0004704953237906485, 'samples': 12861440, 'steps': 25119, 'loss/train': 0.9785674214363098}
-03/04/2022 18:58:52 - INFO - codeparrot_training - Step 25120: {'lr': 0.0004704928227550949, 'samples': 12861952, 'steps': 25120, 'loss/train': 2.816507577896118}
-03/04/2022 18:58:52 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/04/2022 18:58:58 - INFO - codeparrot_training - Step 25121: {'lr': 0.00047049032162019044, 'samples': 12862464, 'steps': 25121, 'loss/train': 0.7571011185646057}
-03/04/2022 18:59:01 - INFO - codeparrot_training - Step 25122: {'lr': 0.0004704878203859365, 'samples': 12862976, 'steps': 25122, 'loss/train': 2.089536666870117}
-03/04/2022 18:59:01 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 18:59:06 - INFO - codeparrot_training - Step 25123: {'lr': 0.0004704853190523342, 'samples': 12863488, 'steps': 25123, 'loss/train': 1.6418256759643555}
-03/04/2022 18:59:09 - INFO - codeparrot_training - Step 25124: {'lr': 0.00047048281761938456, 'samples': 12864000, 'steps': 25124, 'loss/train': 2.2529735565185547}
-03/04/2022 18:59:09 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/04/2022 18:59:15 - INFO - codeparrot_training - Step 25125: {'lr': 0.00047048031608708875, 'samples': 12864512, 'steps': 25125, 'loss/train': 1.518971562385559}
-03/04/2022 18:59:18 - INFO - codeparrot_training - Step 25126: {'lr': 0.000470477814455448, 'samples': 12865024, 'steps': 25126, 'loss/train': 0.5627090930938721}
-03/04/2022 18:59:18 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/04/2022 18:59:23 - INFO - codeparrot_training - Step 25127: {'lr': 0.0004704753127244633, 'samples': 12865536, 'steps': 25127, 'loss/train': 1.6445062160491943}
-03/04/2022 18:59:26 - INFO - codeparrot_training - Step 25128: {'lr': 0.0004704728108941358, 'samples': 12866048, 'steps': 25128, 'loss/train': 1.6332228183746338}
-03/04/2022 18:59:26 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/04/2022 18:59:32 - INFO - codeparrot_training - Step 25129: {'lr': 0.00047047030896446665, 'samples': 12866560, 'steps': 25129, 'loss/train': 1.6114519834518433}
-03/04/2022 18:59:35 - INFO - codeparrot_training - Step 25130: {'lr': 0.000470467806935457, 'samples': 12867072, 'steps': 25130, 'loss/train': 1.2869783639907837}
-03/04/2022 18:59:35 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/04/2022 18:59:40 - INFO - codeparrot_training - Step 25131: {'lr': 0.000470465304807108, 'samples': 12867584, 'steps': 25131, 'loss/train': 2.123750925064087}
-03/04/2022 18:59:43 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/04/2022 18:59:45 - INFO - codeparrot_training - Step 25132: {'lr': 0.00047046280257942067, 'samples': 12868096, 'steps': 25132, 'loss/train': 1.4471428394317627}
-03/04/2022 18:59:49 - INFO - codeparrot_training - Step 25133: {'lr': 0.0004704603002523962, 'samples': 12868608, 'steps': 25133, 'loss/train': 2.197831153869629}
-03/04/2022 18:59:52 - INFO - codeparrot_training - Step 25134: {'lr': 0.00047045779782603584, 'samples': 12869120, 'steps': 25134, 'loss/train': 2.5113508701324463}
-03/04/2022 18:59:52 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/04/2022 18:59:57 - INFO - codeparrot_training - Step 25135: {'lr': 0.0004704552953003405, 'samples': 12869632, 'steps': 25135, 'loss/train': 1.752384066581726}
-03/04/2022 19:00:00 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/04/2022 19:00:03 - INFO - codeparrot_training - Step 25136: {'lr': 0.0004704527926753114, 'samples': 12870144, 'steps': 25136, 'loss/train': 1.596863865852356}
-03/04/2022 19:00:06 - INFO - codeparrot_training - Step 25137: {'lr': 0.00047045028995094967, 'samples': 12870656, 'steps': 25137, 'loss/train': 1.8330895900726318}
-03/04/2022 19:00:09 - INFO - codeparrot_training - Step 25138: {'lr': 0.0004704477871272564, 'samples': 12871168, 'steps': 25138, 'loss/train': 0.15386617183685303}
-03/04/2022 19:00:09 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/04/2022 19:00:14 - INFO - codeparrot_training - Step 25139: {'lr': 0.0004704452842042329, 'samples': 12871680, 'steps': 25139, 'loss/train': 1.7043108940124512}
-03/04/2022 19:00:17 - INFO - codeparrot_training - Step 25140: {'lr': 0.00047044278118188004, 'samples': 12872192, 'steps': 25140, 'loss/train': 2.0515506267547607}
-03/04/2022 19:00:17 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 19:00:23 - INFO - codeparrot_training - Step 25141: {'lr': 0.00047044027806019914, 'samples': 12872704, 'steps': 25141, 'loss/train': 1.908578634262085}
-03/04/2022 19:00:26 - INFO - codeparrot_training - Step 25142: {'lr': 0.0004704377748391912, 'samples': 12873216, 'steps': 25142, 'loss/train': 1.8420010805130005}
-03/04/2022 19:00:26 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/04/2022 19:00:31 - INFO - codeparrot_training - Step 25143: {'lr': 0.0004704352715188574, 'samples': 12873728, 'steps': 25143, 'loss/train': 1.9331549406051636}
-03/04/2022 19:00:34 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/04/2022 19:00:37 - INFO - codeparrot_training - Step 25144: {'lr': 0.0004704327680991989, 'samples': 12874240, 'steps': 25144, 'loss/train': 1.4206304550170898}
-03/04/2022 19:00:40 - INFO - codeparrot_training - Step 25145: {'lr': 0.00047043026458021677, 'samples': 12874752, 'steps': 25145, 'loss/train': 1.3277177810668945}
-03/04/2022 19:00:43 - INFO - codeparrot_training - Step 25146: {'lr': 0.0004704277609619122, 'samples': 12875264, 'steps': 25146, 'loss/train': 1.930651307106018}
-03/04/2022 19:00:43 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/04/2022 19:00:48 - INFO - codeparrot_training - Step 25147: {'lr': 0.0004704252572442862, 'samples': 12875776, 'steps': 25147, 'loss/train': 1.958849310874939}
-03/04/2022 19:00:51 - INFO - codeparrot_training - Step 25148: {'lr': 0.00047042275342734006, 'samples': 12876288, 'steps': 25148, 'loss/train': 1.7760303020477295}
-03/04/2022 19:00:51 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 19:00:57 - INFO - codeparrot_training - Step 25149: {'lr': 0.0004704202495110748, 'samples': 12876800, 'steps': 25149, 'loss/train': 1.5492703914642334}
-03/04/2022 19:01:00 - INFO - codeparrot_training - Step 25150: {'lr': 0.00047041774549549156, 'samples': 12877312, 'steps': 25150, 'loss/train': 1.0460854768753052}
-03/04/2022 19:01:00 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/04/2022 19:01:05 - INFO - codeparrot_training - Step 25151: {'lr': 0.00047041524138059153, 'samples': 12877824, 'steps': 25151, 'loss/train': 1.840155005455017}
-03/04/2022 19:01:08 - INFO - codeparrot_training - Step 25152: {'lr': 0.00047041273716637576, 'samples': 12878336, 'steps': 25152, 'loss/train': 1.597869634628296}
-03/04/2022 19:01:08 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/04/2022 19:01:14 - INFO - codeparrot_training - Step 25153: {'lr': 0.00047041023285284545, 'samples': 12878848, 'steps': 25153, 'loss/train': 2.067610740661621}
-03/04/2022 19:01:17 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/04/2022 19:01:19 - INFO - codeparrot_training - Step 25154: {'lr': 0.0004704077284400017, 'samples': 12879360, 'steps': 25154, 'loss/train': 2.047703981399536}
-03/04/2022 19:01:22 - INFO - codeparrot_training - Step 25155: {'lr': 0.0004704052239278456, 'samples': 12879872, 'steps': 25155, 'loss/train': 0.6569011807441711}
-03/04/2022 19:01:25 - INFO - codeparrot_training - Step 25156: {'lr': 0.00047040271931637824, 'samples': 12880384, 'steps': 25156, 'loss/train': 1.9719747304916382}
-03/04/2022 19:01:26 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/04/2022 19:01:31 - INFO - codeparrot_training - Step 25157: {'lr': 0.0004704002146056009, 'samples': 12880896, 'steps': 25157, 'loss/train': 1.5556350946426392}
-03/04/2022 19:01:34 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/04/2022 19:01:36 - INFO - codeparrot_training - Step 25158: {'lr': 0.0004703977097955146, 'samples': 12881408, 'steps': 25158, 'loss/train': 1.2840830087661743}
-03/04/2022 19:01:39 - INFO - codeparrot_training - Step 25159: {'lr': 0.0004703952048861204, 'samples': 12881920, 'steps': 25159, 'loss/train': 1.9405949115753174}
-03/04/2022 19:01:42 - INFO - codeparrot_training - Step 25160: {'lr': 0.00047039269987741967, 'samples': 12882432, 'steps': 25160, 'loss/train': 1.6845134496688843}
-03/04/2022 19:01:42 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 19:01:48 - INFO - codeparrot_training - Step 25161: {'lr': 0.0004703901947694134, 'samples': 12882944, 'steps': 25161, 'loss/train': 1.17493736743927}
-03/04/2022 19:01:51 - INFO - codeparrot_training - Step 25162: {'lr': 0.0004703876895621025, 'samples': 12883456, 'steps': 25162, 'loss/train': 1.9157634973526}
-03/04/2022 19:01:51 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/04/2022 19:01:56 - INFO - codeparrot_training - Step 25163: {'lr': 0.0004703851842554885, 'samples': 12883968, 'steps': 25163, 'loss/train': 1.5450847148895264}
-03/04/2022 19:01:59 - INFO - codeparrot_training - Step 25164: {'lr': 0.0004703826788495723, 'samples': 12884480, 'steps': 25164, 'loss/train': 1.941747784614563}
-03/04/2022 19:01:59 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 19:02:05 - INFO - codeparrot_training - Step 25165: {'lr': 0.00047038017334435504, 'samples': 12884992, 'steps': 25165, 'loss/train': 1.9387246370315552}
-03/04/2022 19:02:08 - INFO - codeparrot_training - Step 25166: {'lr': 0.00047037766773983794, 'samples': 12885504, 'steps': 25166, 'loss/train': 1.6091663837432861}
-03/04/2022 19:02:08 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/04/2022 19:02:13 - INFO - codeparrot_training - Step 25167: {'lr': 0.00047037516203602195, 'samples': 12886016, 'steps': 25167, 'loss/train': 1.8177059888839722}
-03/04/2022 19:02:16 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/04/2022 19:02:18 - INFO - codeparrot_training - Step 25168: {'lr': 0.0004703726562329084, 'samples': 12886528, 'steps': 25168, 'loss/train': 2.1129581928253174}
-03/04/2022 19:02:22 - INFO - codeparrot_training - Step 25169: {'lr': 0.0004703701503304983, 'samples': 12887040, 'steps': 25169, 'loss/train': 1.8308436870574951}
-03/04/2022 19:02:24 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 19:02:27 - INFO - codeparrot_training - Step 25170: {'lr': 0.0004703676443287928, 'samples': 12887552, 'steps': 25170, 'loss/train': 2.165034294128418}
-03/04/2022 19:02:30 - INFO - codeparrot_training - Step 25171: {'lr': 0.000470365138227793, 'samples': 12888064, 'steps': 25171, 'loss/train': 2.0599124431610107}
-03/04/2022 19:02:33 - INFO - codeparrot_training - Step 25172: {'lr': 0.0004703626320275002, 'samples': 12888576, 'steps': 25172, 'loss/train': 1.6414638757705688}
-03/04/2022 19:02:33 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/04/2022 19:02:39 - INFO - codeparrot_training - Step 25173: {'lr': 0.0004703601257279153, 'samples': 12889088, 'steps': 25173, 'loss/train': 2.1862542629241943}
-03/04/2022 19:02:42 - INFO - codeparrot_training - Step 25174: {'lr': 0.0004703576193290395, 'samples': 12889600, 'steps': 25174, 'loss/train': 1.4821419715881348}
-03/04/2022 19:02:42 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 19:02:47 - INFO - codeparrot_training - Step 25175: {'lr': 0.0004703551128308741, 'samples': 12890112, 'steps': 25175, 'loss/train': 1.5592763423919678}
-03/04/2022 19:02:50 - INFO - codeparrot_training - Step 25176: {'lr': 0.00047035260623341996, 'samples': 12890624, 'steps': 25176, 'loss/train': 1.7259502410888672}
-03/04/2022 19:02:50 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/04/2022 19:02:56 - INFO - codeparrot_training - Step 25177: {'lr': 0.0004703500995366784, 'samples': 12891136, 'steps': 25177, 'loss/train': 3.2288177013397217}
-03/04/2022 19:02:59 - INFO - codeparrot_training - Step 25178: {'lr': 0.00047034759274065043, 'samples': 12891648, 'steps': 25178, 'loss/train': 1.9151241779327393}
-03/04/2022 19:02:59 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/04/2022 19:03:05 - INFO - codeparrot_training - Step 25179: {'lr': 0.00047034508584533724, 'samples': 12892160, 'steps': 25179, 'loss/train': 1.3826673030853271}
-03/04/2022 19:03:08 - INFO - codeparrot_training - Step 25180: {'lr': 0.00047034257885074, 'samples': 12892672, 'steps': 25180, 'loss/train': 1.7321468591690063}
-03/04/2022 19:03:09 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/04/2022 19:03:13 - INFO - codeparrot_training - Step 25181: {'lr': 0.00047034007175685976, 'samples': 12893184, 'steps': 25181, 'loss/train': 1.6443660259246826}
-03/04/2022 19:03:16 - INFO - codeparrot_training - Step 25182: {'lr': 0.0004703375645636977, 'samples': 12893696, 'steps': 25182, 'loss/train': 1.483567237854004}
-03/04/2022 19:03:17 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 19:03:22 - INFO - codeparrot_training - Step 25183: {'lr': 0.0004703350572712549, 'samples': 12894208, 'steps': 25183, 'loss/train': 1.6034239530563354}
-03/04/2022 19:03:25 - INFO - codeparrot_training - Step 25184: {'lr': 0.00047033254987953254, 'samples': 12894720, 'steps': 25184, 'loss/train': 1.7478406429290771}
-03/04/2022 19:03:27 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 19:03:30 - INFO - codeparrot_training - Step 25185: {'lr': 0.0004703300423885318, 'samples': 12895232, 'steps': 25185, 'loss/train': 1.6723581552505493}
-03/04/2022 19:03:33 - INFO - codeparrot_training - Step 25186: {'lr': 0.0004703275347982536, 'samples': 12895744, 'steps': 25186, 'loss/train': 1.8128533363342285}
-03/04/2022 19:03:36 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/04/2022 19:03:39 - INFO - codeparrot_training - Step 25187: {'lr': 0.00047032502710869935, 'samples': 12896256, 'steps': 25187, 'loss/train': 0.7747647166252136}
-03/04/2022 19:03:42 - INFO - codeparrot_training - Step 25188: {'lr': 0.00047032251931987, 'samples': 12896768, 'steps': 25188, 'loss/train': 1.749839425086975}
-03/04/2022 19:03:44 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 19:03:47 - INFO - codeparrot_training - Step 25189: {'lr': 0.0004703200114317667, 'samples': 12897280, 'steps': 25189, 'loss/train': 2.5225415229797363}
-03/04/2022 19:03:50 - INFO - codeparrot_training - Step 25190: {'lr': 0.0004703175034443906, 'samples': 12897792, 'steps': 25190, 'loss/train': 1.805006980895996}
-03/04/2022 19:03:52 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 19:03:55 - INFO - codeparrot_training - Step 25191: {'lr': 0.00047031499535774284, 'samples': 12898304, 'steps': 25191, 'loss/train': 2.043449878692627}
-03/04/2022 19:03:59 - INFO - codeparrot_training - Step 25192: {'lr': 0.00047031248717182455, 'samples': 12898816, 'steps': 25192, 'loss/train': 1.819394588470459}
-03/04/2022 19:04:01 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/04/2022 19:04:04 - INFO - codeparrot_training - Step 25193: {'lr': 0.00047030997888663687, 'samples': 12899328, 'steps': 25193, 'loss/train': 1.368503451347351}
-03/04/2022 19:04:07 - INFO - codeparrot_training - Step 25194: {'lr': 0.00047030747050218094, 'samples': 12899840, 'steps': 25194, 'loss/train': 1.6617664098739624}
-03/04/2022 19:04:09 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 19:04:13 - INFO - codeparrot_training - Step 25195: {'lr': 0.0004703049620184578, 'samples': 12900352, 'steps': 25195, 'loss/train': 2.135477066040039}
-03/04/2022 19:04:16 - INFO - codeparrot_training - Step 25196: {'lr': 0.0004703024534354686, 'samples': 12900864, 'steps': 25196, 'loss/train': 1.9510955810546875}
-03/04/2022 19:04:18 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/04/2022 19:04:21 - INFO - codeparrot_training - Step 25197: {'lr': 0.0004702999447532146, 'samples': 12901376, 'steps': 25197, 'loss/train': 2.524611234664917}
-03/04/2022 19:04:24 - INFO - codeparrot_training - Step 25198: {'lr': 0.00047029743597169684, 'samples': 12901888, 'steps': 25198, 'loss/train': 2.1209006309509277}
-03/04/2022 19:04:26 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/04/2022 19:04:30 - INFO - codeparrot_training - Step 25199: {'lr': 0.0004702949270909164, 'samples': 12902400, 'steps': 25199, 'loss/train': 1.1638249158859253}
-03/04/2022 19:04:33 - INFO - codeparrot_training - Step 25200: {'lr': 0.0004702924181108745, 'samples': 12902912, 'steps': 25200, 'loss/train': 0.9145562052726746}
-03/04/2022 19:04:35 - INFO - codeparrot_training - Skipping example with length 7 (seq_length=1024)
-03/04/2022 19:04:38 - INFO - codeparrot_training - Step 25201: {'lr': 0.00047028990903157233, 'samples': 12903424, 'steps': 25201, 'loss/train': 2.6583075523376465}
-03/04/2022 19:04:41 - INFO - codeparrot_training - Step 25202: {'lr': 0.0004702873998530108, 'samples': 12903936, 'steps': 25202, 'loss/train': 2.027649402618408}
-03/04/2022 19:04:43 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/04/2022 19:04:46 - INFO - codeparrot_training - Step 25203: {'lr': 0.0004702848905751912, 'samples': 12904448, 'steps': 25203, 'loss/train': 2.4998562335968018}
-03/04/2022 19:04:50 - INFO - codeparrot_training - Step 25204: {'lr': 0.0004702823811981146, 'samples': 12904960, 'steps': 25204, 'loss/train': 1.6686561107635498}
-03/04/2022 19:04:52 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/04/2022 19:04:55 - INFO - codeparrot_training - Step 25205: {'lr': 0.0004702798717217822, 'samples': 12905472, 'steps': 25205, 'loss/train': 2.0256083011627197}
-03/04/2022 19:04:58 - INFO - codeparrot_training - Step 25206: {'lr': 0.0004702773621461951, 'samples': 12905984, 'steps': 25206, 'loss/train': 2.2310848236083984}
-03/04/2022 19:05:00 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 19:05:04 - INFO - codeparrot_training - Step 25207: {'lr': 0.0004702748524713544, 'samples': 12906496, 'steps': 25207, 'loss/train': 2.092449188232422}
-03/04/2022 19:05:07 - INFO - codeparrot_training - Step 25208: {'lr': 0.00047027234269726123, 'samples': 12907008, 'steps': 25208, 'loss/train': 1.7238491773605347}
-03/04/2022 19:05:10 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 19:05:13 - INFO - codeparrot_training - Step 25209: {'lr': 0.0004702698328239167, 'samples': 12907520, 'steps': 25209, 'loss/train': 0.3580975830554962}
-03/04/2022 19:05:16 - INFO - codeparrot_training - Step 25210: {'lr': 0.0004702673228513221, 'samples': 12908032, 'steps': 25210, 'loss/train': 1.4008368253707886}
-03/04/2022 19:05:19 - INFO - codeparrot_training - Step 25211: {'lr': 0.00047026481277947835, 'samples': 12908544, 'steps': 25211, 'loss/train': 2.0943400859832764}
-03/04/2022 19:05:21 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 19:05:24 - INFO - codeparrot_training - Step 25212: {'lr': 0.0004702623026083867, 'samples': 12909056, 'steps': 25212, 'loss/train': 2.0550129413604736}
-03/04/2022 19:05:28 - INFO - codeparrot_training - Step 25213: {'lr': 0.00047025979233804825, 'samples': 12909568, 'steps': 25213, 'loss/train': 1.938783049583435}
-03/04/2022 19:05:29 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/04/2022 19:05:33 - INFO - codeparrot_training - Step 25214: {'lr': 0.00047025728196846417, 'samples': 12910080, 'steps': 25214, 'loss/train': 1.9267405271530151}
-03/04/2022 19:05:36 - INFO - codeparrot_training - Step 25215: {'lr': 0.0004702547714996355, 'samples': 12910592, 'steps': 25215, 'loss/train': 2.0269620418548584}
-03/04/2022 19:05:38 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/04/2022 19:05:41 - INFO - codeparrot_training - Step 25216: {'lr': 0.00047025226093156346, 'samples': 12911104, 'steps': 25216, 'loss/train': 1.0818992853164673}
-03/04/2022 19:05:44 - INFO - codeparrot_training - Step 25217: {'lr': 0.0004702497502642492, 'samples': 12911616, 'steps': 25217, 'loss/train': 1.3142998218536377}
-03/04/2022 19:05:46 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/04/2022 19:05:50 - INFO - codeparrot_training - Step 25218: {'lr': 0.0004702472394976938, 'samples': 12912128, 'steps': 25218, 'loss/train': 1.9675078392028809}
-03/04/2022 19:05:53 - INFO - codeparrot_training - Step 25219: {'lr': 0.0004702447286318983, 'samples': 12912640, 'steps': 25219, 'loss/train': 1.5353033542633057}
-03/04/2022 19:05:55 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/04/2022 19:05:58 - INFO - codeparrot_training - Step 25220: {'lr': 0.0004702422176668639, 'samples': 12913152, 'steps': 25220, 'loss/train': 1.6003278493881226}
-03/04/2022 19:06:01 - INFO - codeparrot_training - Step 25221: {'lr': 0.00047023970660259193, 'samples': 12913664, 'steps': 25221, 'loss/train': 2.666259527206421}
-03/04/2022 19:06:03 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/04/2022 19:06:07 - INFO - codeparrot_training - Step 25222: {'lr': 0.0004702371954390832, 'samples': 12914176, 'steps': 25222, 'loss/train': 1.8576408624649048}
-03/04/2022 19:06:10 - INFO - codeparrot_training - Step 25223: {'lr': 0.00047023468417633905, 'samples': 12914688, 'steps': 25223, 'loss/train': 1.40735924243927}
-03/04/2022 19:06:12 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/04/2022 19:06:15 - INFO - codeparrot_training - Step 25224: {'lr': 0.0004702321728143605, 'samples': 12915200, 'steps': 25224, 'loss/train': 2.7171647548675537}
-03/04/2022 19:06:18 - INFO - codeparrot_training - Step 25225: {'lr': 0.0004702296613531488, 'samples': 12915712, 'steps': 25225, 'loss/train': 1.6771979331970215}
-03/04/2022 19:06:20 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/04/2022 19:06:24 - INFO - codeparrot_training - Step 25226: {'lr': 0.00047022714979270497, 'samples': 12916224, 'steps': 25226, 'loss/train': 2.799003839492798}
-03/04/2022 19:06:27 - INFO - codeparrot_training - Step 25227: {'lr': 0.0004702246381330302, 'samples': 12916736, 'steps': 25227, 'loss/train': 1.7640670537948608}
-03/04/2022 19:06:29 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 19:06:32 - INFO - codeparrot_training - Step 25228: {'lr': 0.00047022212637412553, 'samples': 12917248, 'steps': 25228, 'loss/train': 1.6470550298690796}
-03/04/2022 19:06:35 - INFO - codeparrot_training - Step 25229: {'lr': 0.00047021961451599226, 'samples': 12917760, 'steps': 25229, 'loss/train': 1.139792799949646}
-03/04/2022 19:06:38 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 19:06:41 - INFO - codeparrot_training - Step 25230: {'lr': 0.00047021710255863144, 'samples': 12918272, 'steps': 25230, 'loss/train': 2.0125138759613037}
-03/04/2022 19:06:44 - INFO - codeparrot_training - Step 25231: {'lr': 0.0004702145905020442, 'samples': 12918784, 'steps': 25231, 'loss/train': 1.4043655395507812}
-03/04/2022 19:06:46 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/04/2022 19:06:49 - INFO - codeparrot_training - Step 25232: {'lr': 0.0004702120783462316, 'samples': 12919296, 'steps': 25232, 'loss/train': 2.2226333618164062}
-03/04/2022 19:06:53 - INFO - codeparrot_training - Step 25233: {'lr': 0.00047020956609119483, 'samples': 12919808, 'steps': 25233, 'loss/train': 1.7125468254089355}
-03/04/2022 19:06:56 - INFO - codeparrot_training - Step 25234: {'lr': 0.0004702070537369351, 'samples': 12920320, 'steps': 25234, 'loss/train': 2.105487585067749}
-03/04/2022 19:06:56 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/04/2022 19:07:01 - INFO - codeparrot_training - Step 25235: {'lr': 0.00047020454128345333, 'samples': 12920832, 'steps': 25235, 'loss/train': 1.6363765001296997}
-03/04/2022 19:07:04 - INFO - codeparrot_training - Step 25236: {'lr': 0.00047020202873075093, 'samples': 12921344, 'steps': 25236, 'loss/train': 1.5417019128799438}
-03/04/2022 19:07:04 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 19:07:10 - INFO - codeparrot_training - Step 25237: {'lr': 0.00047019951607882884, 'samples': 12921856, 'steps': 25237, 'loss/train': 0.3437754511833191}
-03/04/2022 19:07:13 - INFO - codeparrot_training - Step 25238: {'lr': 0.0004701970033276882, 'samples': 12922368, 'steps': 25238, 'loss/train': 2.44795560836792}
-03/04/2022 19:07:13 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/04/2022 19:07:18 - INFO - codeparrot_training - Step 25239: {'lr': 0.0004701944904773303, 'samples': 12922880, 'steps': 25239, 'loss/train': 2.28684401512146}
-03/04/2022 19:07:21 - INFO - codeparrot_training - Step 25240: {'lr': 0.0004701919775277561, 'samples': 12923392, 'steps': 25240, 'loss/train': 2.272980213165283}
-03/04/2022 19:07:21 - INFO - codeparrot_training - Skipping example with length 1010 (seq_length=1024)
-03/04/2022 19:07:26 - INFO - codeparrot_training - Step 25241: {'lr': 0.0004701894644789668, 'samples': 12923904, 'steps': 25241, 'loss/train': 2.385653257369995}
-03/04/2022 19:07:30 - INFO - codeparrot_training - Step 25242: {'lr': 0.0004701869513309635, 'samples': 12924416, 'steps': 25242, 'loss/train': 1.9426751136779785}
-03/04/2022 19:07:30 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/04/2022 19:07:35 - INFO - codeparrot_training - Step 25243: {'lr': 0.0004701844380837474, 'samples': 12924928, 'steps': 25243, 'loss/train': 1.654362440109253}
-03/04/2022 19:07:38 - INFO - codeparrot_training - Step 25244: {'lr': 0.00047018192473731956, 'samples': 12925440, 'steps': 25244, 'loss/train': 1.473850965499878}
-03/04/2022 19:07:38 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 19:07:44 - INFO - codeparrot_training - Step 25245: {'lr': 0.0004701794112916812, 'samples': 12925952, 'steps': 25245, 'loss/train': 2.4931082725524902}
-03/04/2022 19:07:47 - INFO - codeparrot_training - Step 25246: {'lr': 0.00047017689774683325, 'samples': 12926464, 'steps': 25246, 'loss/train': 1.8041152954101562}
-03/04/2022 19:07:47 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/04/2022 19:07:52 - INFO - codeparrot_training - Step 25247: {'lr': 0.0004701743841027771, 'samples': 12926976, 'steps': 25247, 'loss/train': 1.866872787475586}
-03/04/2022 19:07:55 - INFO - codeparrot_training - Step 25248: {'lr': 0.0004701718703595138, 'samples': 12927488, 'steps': 25248, 'loss/train': 1.9223510026931763}
-03/04/2022 19:07:56 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/04/2022 19:08:01 - INFO - codeparrot_training - Step 25249: {'lr': 0.0004701693565170444, 'samples': 12928000, 'steps': 25249, 'loss/train': 1.2357670068740845}
-03/04/2022 19:08:04 - INFO - codeparrot_training - Step 25250: {'lr': 0.0004701668425753701, 'samples': 12928512, 'steps': 25250, 'loss/train': 2.2135913372039795}
-03/04/2022 19:08:04 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/04/2022 19:08:09 - INFO - codeparrot_training - Step 25251: {'lr': 0.000470164328534492, 'samples': 12929024, 'steps': 25251, 'loss/train': 1.73197603225708}
-03/04/2022 19:08:12 - INFO - codeparrot_training - Step 25252: {'lr': 0.00047016181439441126, 'samples': 12929536, 'steps': 25252, 'loss/train': 2.3281567096710205}
-03/04/2022 19:08:12 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/04/2022 19:08:17 - INFO - codeparrot_training - Step 25253: {'lr': 0.000470159300155129, 'samples': 12930048, 'steps': 25253, 'loss/train': 2.4120144844055176}
-03/04/2022 19:08:21 - INFO - codeparrot_training - Step 25254: {'lr': 0.00047015678581664635, 'samples': 12930560, 'steps': 25254, 'loss/train': 1.4932515621185303}
-03/04/2022 19:08:21 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 19:08:26 - INFO - codeparrot_training - Step 25255: {'lr': 0.00047015427137896446, 'samples': 12931072, 'steps': 25255, 'loss/train': 1.0346206426620483}
-03/04/2022 19:08:29 - INFO - codeparrot_training - Step 25256: {'lr': 0.0004701517568420844, 'samples': 12931584, 'steps': 25256, 'loss/train': 2.016472816467285}
-03/04/2022 19:08:29 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/04/2022 19:08:34 - INFO - codeparrot_training - Step 25257: {'lr': 0.0004701492422060074, 'samples': 12932096, 'steps': 25257, 'loss/train': 3.011521577835083}
-03/04/2022 19:08:37 - INFO - codeparrot_training - Step 25258: {'lr': 0.0004701467274707346, 'samples': 12932608, 'steps': 25258, 'loss/train': 1.5322874784469604}
-03/04/2022 19:08:38 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/04/2022 19:08:43 - INFO - codeparrot_training - Step 25259: {'lr': 0.0004701442126362671, 'samples': 12933120, 'steps': 25259, 'loss/train': 1.9460442066192627}
-03/04/2022 19:08:46 - INFO - codeparrot_training - Step 25260: {'lr': 0.0004701416977026059, 'samples': 12933632, 'steps': 25260, 'loss/train': 1.175583839416504}
-03/04/2022 19:08:46 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/04/2022 19:08:51 - INFO - codeparrot_training - Step 25261: {'lr': 0.0004701391826697523, 'samples': 12934144, 'steps': 25261, 'loss/train': 1.6859688758850098}
-03/04/2022 19:08:54 - INFO - codeparrot_training - Step 25262: {'lr': 0.00047013666753770736, 'samples': 12934656, 'steps': 25262, 'loss/train': 1.7589534521102905}
-03/04/2022 19:08:55 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/04/2022 19:09:00 - INFO - codeparrot_training - Step 25263: {'lr': 0.00047013415230647227, 'samples': 12935168, 'steps': 25263, 'loss/train': 2.5282318592071533}
-03/04/2022 19:09:03 - INFO - codeparrot_training - Step 25264: {'lr': 0.0004701316369760481, 'samples': 12935680, 'steps': 25264, 'loss/train': 2.1080193519592285}
-03/04/2022 19:09:03 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 19:09:08 - INFO - codeparrot_training - Step 25265: {'lr': 0.00047012912154643607, 'samples': 12936192, 'steps': 25265, 'loss/train': 2.1533796787261963}
-03/04/2022 19:09:11 - INFO - codeparrot_training - Step 25266: {'lr': 0.0004701266060176372, 'samples': 12936704, 'steps': 25266, 'loss/train': 1.4148755073547363}
-03/04/2022 19:09:12 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 19:09:17 - INFO - codeparrot_training - Step 25267: {'lr': 0.00047012409038965267, 'samples': 12937216, 'steps': 25267, 'loss/train': 1.7201858758926392}
-03/04/2022 19:09:20 - INFO - codeparrot_training - Step 25268: {'lr': 0.0004701215746624836, 'samples': 12937728, 'steps': 25268, 'loss/train': 1.5146760940551758}
-03/04/2022 19:09:20 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/04/2022 19:09:25 - INFO - codeparrot_training - Step 25269: {'lr': 0.0004701190588361312, 'samples': 12938240, 'steps': 25269, 'loss/train': 1.3812400102615356}
-03/04/2022 19:09:28 - INFO - codeparrot_training - Step 25270: {'lr': 0.0004701165429105966, 'samples': 12938752, 'steps': 25270, 'loss/train': 1.2600101232528687}
-03/04/2022 19:09:29 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/04/2022 19:09:33 - INFO - codeparrot_training - Step 25271: {'lr': 0.0004701140268858808, 'samples': 12939264, 'steps': 25271, 'loss/train': 1.79182767868042}
-03/04/2022 19:09:37 - INFO - codeparrot_training - Step 25272: {'lr': 0.000470111510761985, 'samples': 12939776, 'steps': 25272, 'loss/train': 1.163543939590454}
-03/04/2022 19:09:37 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/04/2022 19:09:42 - INFO - codeparrot_training - Step 25273: {'lr': 0.0004701089945389104, 'samples': 12940288, 'steps': 25273, 'loss/train': 2.542271137237549}
-03/04/2022 19:09:45 - INFO - codeparrot_training - Step 25274: {'lr': 0.00047010647821665803, 'samples': 12940800, 'steps': 25274, 'loss/train': 1.8514363765716553}
-03/04/2022 19:09:45 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 19:09:50 - INFO - codeparrot_training - Step 25275: {'lr': 0.0004701039617952291, 'samples': 12941312, 'steps': 25275, 'loss/train': 1.8375102281570435}
-03/04/2022 19:09:53 - INFO - codeparrot_training - Step 25276: {'lr': 0.00047010144527462474, 'samples': 12941824, 'steps': 25276, 'loss/train': 2.6323704719543457}
-03/04/2022 19:09:54 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/04/2022 19:09:59 - INFO - codeparrot_training - Step 25277: {'lr': 0.00047009892865484607, 'samples': 12942336, 'steps': 25277, 'loss/train': 1.118599772453308}
-03/04/2022 19:10:02 - INFO - codeparrot_training - Step 25278: {'lr': 0.00047009641193589423, 'samples': 12942848, 'steps': 25278, 'loss/train': 1.6042462587356567}
-03/04/2022 19:10:02 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/04/2022 19:10:07 - INFO - codeparrot_training - Step 25279: {'lr': 0.00047009389511777036, 'samples': 12943360, 'steps': 25279, 'loss/train': 2.020631790161133}
-03/04/2022 19:10:11 - INFO - codeparrot_training - Step 25280: {'lr': 0.0004700913782004755, 'samples': 12943872, 'steps': 25280, 'loss/train': 2.071779727935791}
-03/04/2022 19:10:11 - INFO - codeparrot_training - Skipping example with length 285 (seq_length=1024)
-03/04/2022 19:10:16 - INFO - codeparrot_training - Step 25281: {'lr': 0.00047008886118401084, 'samples': 12944384, 'steps': 25281, 'loss/train': 1.9672846794128418}
-03/04/2022 19:10:20 - INFO - codeparrot_training - Step 25282: {'lr': 0.0004700863440683776, 'samples': 12944896, 'steps': 25282, 'loss/train': 0.8893557190895081}
-03/04/2022 19:10:21 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/04/2022 19:10:25 - INFO - codeparrot_training - Step 25283: {'lr': 0.00047008382685357686, 'samples': 12945408, 'steps': 25283, 'loss/train': 1.433991551399231}
-03/04/2022 19:10:28 - INFO - codeparrot_training - Step 25284: {'lr': 0.0004700813095396098, 'samples': 12945920, 'steps': 25284, 'loss/train': 1.5477524995803833}
-03/04/2022 19:10:30 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 19:10:33 - INFO - codeparrot_training - Step 25285: {'lr': 0.00047007879212647744, 'samples': 12946432, 'steps': 25285, 'loss/train': 2.614014148712158}
-03/04/2022 19:10:37 - INFO - codeparrot_training - Step 25286: {'lr': 0.0004700762746141809, 'samples': 12946944, 'steps': 25286, 'loss/train': 2.3048131465911865}
-03/04/2022 19:10:38 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/04/2022 19:10:42 - INFO - codeparrot_training - Step 25287: {'lr': 0.0004700737570027214, 'samples': 12947456, 'steps': 25287, 'loss/train': 1.5815726518630981}
-03/04/2022 19:10:45 - INFO - codeparrot_training - Step 25288: {'lr': 0.00047007123929210015, 'samples': 12947968, 'steps': 25288, 'loss/train': 1.3431769609451294}
-03/04/2022 19:10:47 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/04/2022 19:10:50 - INFO - codeparrot_training - Step 25289: {'lr': 0.00047006872148231814, 'samples': 12948480, 'steps': 25289, 'loss/train': 2.1170506477355957}
-03/04/2022 19:10:53 - INFO - codeparrot_training - Step 25290: {'lr': 0.0004700662035733766, 'samples': 12948992, 'steps': 25290, 'loss/train': 1.7611955404281616}
-03/04/2022 19:10:55 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/04/2022 19:10:59 - INFO - codeparrot_training - Step 25291: {'lr': 0.0004700636855652766, 'samples': 12949504, 'steps': 25291, 'loss/train': 1.6154122352600098}
-03/04/2022 19:11:02 - INFO - codeparrot_training - Step 25292: {'lr': 0.0004700611674580193, 'samples': 12950016, 'steps': 25292, 'loss/train': 2.052398443222046}
-03/04/2022 19:11:03 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/04/2022 19:11:07 - INFO - codeparrot_training - Step 25293: {'lr': 0.0004700586492516058, 'samples': 12950528, 'steps': 25293, 'loss/train': 0.8360694050788879}
-03/04/2022 19:11:10 - INFO - codeparrot_training - Step 25294: {'lr': 0.00047005613094603727, 'samples': 12951040, 'steps': 25294, 'loss/train': 1.6595330238342285}
-03/04/2022 19:11:12 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 19:11:16 - INFO - codeparrot_training - Step 25295: {'lr': 0.0004700536125413149, 'samples': 12951552, 'steps': 25295, 'loss/train': 1.4597535133361816}
-03/04/2022 19:11:19 - INFO - codeparrot_training - Step 25296: {'lr': 0.00047005109403743976, 'samples': 12952064, 'steps': 25296, 'loss/train': 1.4352736473083496}
-03/04/2022 19:11:20 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 19:11:24 - INFO - codeparrot_training - Step 25297: {'lr': 0.00047004857543441294, 'samples': 12952576, 'steps': 25297, 'loss/train': 2.0718212127685547}
-03/04/2022 19:11:27 - INFO - codeparrot_training - Step 25298: {'lr': 0.00047004605673223567, 'samples': 12953088, 'steps': 25298, 'loss/train': 1.810469388961792}
-03/04/2022 19:11:28 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 19:11:32 - INFO - codeparrot_training - Step 25299: {'lr': 0.00047004353793090903, 'samples': 12953600, 'steps': 25299, 'loss/train': 1.957377552986145}
-03/04/2022 19:11:36 - INFO - codeparrot_training - Step 25300: {'lr': 0.00047004101903043416, 'samples': 12954112, 'steps': 25300, 'loss/train': 1.8267908096313477}
-03/04/2022 19:11:37 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 19:11:41 - INFO - codeparrot_training - Step 25301: {'lr': 0.00047003850003081215, 'samples': 12954624, 'steps': 25301, 'loss/train': 2.164577007293701}
-03/04/2022 19:11:44 - INFO - codeparrot_training - Step 25302: {'lr': 0.0004700359809320443, 'samples': 12955136, 'steps': 25302, 'loss/train': 1.6552242040634155}
-03/04/2022 19:11:46 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/04/2022 19:11:49 - INFO - codeparrot_training - Step 25303: {'lr': 0.0004700334617341316, 'samples': 12955648, 'steps': 25303, 'loss/train': 1.6860713958740234}
-03/04/2022 19:11:52 - INFO - codeparrot_training - Step 25304: {'lr': 0.0004700309424370752, 'samples': 12956160, 'steps': 25304, 'loss/train': 2.3178820610046387}
-03/04/2022 19:11:54 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 19:11:58 - INFO - codeparrot_training - Step 25305: {'lr': 0.00047002842304087625, 'samples': 12956672, 'steps': 25305, 'loss/train': 1.5979934930801392}
-03/04/2022 19:12:01 - INFO - codeparrot_training - Step 25306: {'lr': 0.00047002590354553586, 'samples': 12957184, 'steps': 25306, 'loss/train': 2.5537147521972656}
-03/04/2022 19:12:03 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/04/2022 19:12:06 - INFO - codeparrot_training - Step 25307: {'lr': 0.0004700233839510552, 'samples': 12957696, 'steps': 25307, 'loss/train': 2.104651927947998}
-03/04/2022 19:12:09 - INFO - codeparrot_training - Step 25308: {'lr': 0.00047002086425743545, 'samples': 12958208, 'steps': 25308, 'loss/train': 1.7871196269989014}
-03/04/2022 19:12:11 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/04/2022 19:12:15 - INFO - codeparrot_training - Step 25309: {'lr': 0.0004700183444646776, 'samples': 12958720, 'steps': 25309, 'loss/train': 2.587916612625122}
-03/04/2022 19:12:18 - INFO - codeparrot_training - Step 25310: {'lr': 0.000470015824572783, 'samples': 12959232, 'steps': 25310, 'loss/train': 0.13098278641700745}
-03/04/2022 19:12:19 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/04/2022 19:12:24 - INFO - codeparrot_training - Step 25311: {'lr': 0.00047001330458175264, 'samples': 12959744, 'steps': 25311, 'loss/train': 6.453415870666504}
-03/04/2022 19:12:27 - INFO - codeparrot_training - Step 25312: {'lr': 0.0004700107844915876, 'samples': 12960256, 'steps': 25312, 'loss/train': 1.5737439393997192}
-03/04/2022 19:12:30 - INFO - codeparrot_training - Step 25313: {'lr': 0.00047000826430228915, 'samples': 12960768, 'steps': 25313, 'loss/train': 2.7380714416503906}
-03/04/2022 19:12:30 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/04/2022 19:12:35 - INFO - codeparrot_training - Step 25314: {'lr': 0.00047000574401385835, 'samples': 12961280, 'steps': 25314, 'loss/train': 1.9988138675689697}
-03/04/2022 19:12:38 - INFO - codeparrot_training - Step 25315: {'lr': 0.0004700032236262964, 'samples': 12961792, 'steps': 25315, 'loss/train': 1.5793505907058716}
-03/04/2022 19:12:39 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/04/2022 19:12:44 - INFO - codeparrot_training - Step 25316: {'lr': 0.00047000070313960436, 'samples': 12962304, 'steps': 25316, 'loss/train': 1.8534351587295532}
-03/04/2022 19:12:47 - INFO - codeparrot_training - Step 25317: {'lr': 0.00046999818255378335, 'samples': 12962816, 'steps': 25317, 'loss/train': 1.8523732423782349}
-03/04/2022 19:12:47 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/04/2022 19:12:52 - INFO - codeparrot_training - Step 25318: {'lr': 0.00046999566186883466, 'samples': 12963328, 'steps': 25318, 'loss/train': 1.1400641202926636}
-03/04/2022 19:12:55 - INFO - codeparrot_training - Step 25319: {'lr': 0.0004699931410847592, 'samples': 12963840, 'steps': 25319, 'loss/train': 1.8348878622055054}
-03/04/2022 19:12:55 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/04/2022 19:13:01 - INFO - codeparrot_training - Step 25320: {'lr': 0.00046999062020155834, 'samples': 12964352, 'steps': 25320, 'loss/train': 0.44005560874938965}
-03/04/2022 19:13:04 - INFO - codeparrot_training - Step 25321: {'lr': 0.00046998809921923305, 'samples': 12964864, 'steps': 25321, 'loss/train': 1.711197853088379}
-03/04/2022 19:13:04 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/04/2022 19:13:09 - INFO - codeparrot_training - Step 25322: {'lr': 0.0004699855781377845, 'samples': 12965376, 'steps': 25322, 'loss/train': 1.533366322517395}
-03/04/2022 19:13:12 - INFO - codeparrot_training - Step 25323: {'lr': 0.0004699830569572139, 'samples': 12965888, 'steps': 25323, 'loss/train': 2.9759814739227295}
-03/04/2022 19:13:12 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/04/2022 19:13:17 - INFO - codeparrot_training - Step 25324: {'lr': 0.00046998053567752225, 'samples': 12966400, 'steps': 25324, 'loss/train': 0.6103813052177429}
-03/04/2022 19:13:21 - INFO - codeparrot_training - Step 25325: {'lr': 0.0004699780142987108, 'samples': 12966912, 'steps': 25325, 'loss/train': 1.7392432689666748}
-03/04/2022 19:13:21 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 19:13:26 - INFO - codeparrot_training - Step 25326: {'lr': 0.0004699754928207807, 'samples': 12967424, 'steps': 25326, 'loss/train': 1.7384638786315918}
-03/04/2022 19:13:29 - INFO - codeparrot_training - Step 25327: {'lr': 0.00046997297124373293, 'samples': 12967936, 'steps': 25327, 'loss/train': 1.2617100477218628}
-03/04/2022 19:13:29 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/04/2022 19:13:34 - INFO - codeparrot_training - Step 25328: {'lr': 0.00046997044956756883, 'samples': 12968448, 'steps': 25328, 'loss/train': 1.7598261833190918}
-03/04/2022 19:13:37 - INFO - codeparrot_training - Step 25329: {'lr': 0.00046996792779228935, 'samples': 12968960, 'steps': 25329, 'loss/train': 1.651097297668457}
-03/04/2022 19:13:38 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 19:13:43 - INFO - codeparrot_training - Step 25330: {'lr': 0.00046996540591789584, 'samples': 12969472, 'steps': 25330, 'loss/train': 1.7799313068389893}
-03/04/2022 19:13:46 - INFO - codeparrot_training - Step 25331: {'lr': 0.00046996288394438924, 'samples': 12969984, 'steps': 25331, 'loss/train': 1.2760562896728516}
-03/04/2022 19:13:46 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/04/2022 19:13:51 - INFO - codeparrot_training - Step 25332: {'lr': 0.00046996036187177073, 'samples': 12970496, 'steps': 25332, 'loss/train': 1.7225462198257446}
-03/04/2022 19:13:54 - INFO - codeparrot_training - Step 25333: {'lr': 0.0004699578397000415, 'samples': 12971008, 'steps': 25333, 'loss/train': 1.6820789575576782}
-03/04/2022 19:13:55 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/04/2022 19:14:00 - INFO - codeparrot_training - Step 25334: {'lr': 0.00046995531742920264, 'samples': 12971520, 'steps': 25334, 'loss/train': 1.9915714263916016}
-03/04/2022 19:14:03 - INFO - codeparrot_training - Step 25335: {'lr': 0.00046995279505925535, 'samples': 12972032, 'steps': 25335, 'loss/train': 2.4880597591400146}
-03/04/2022 19:14:03 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 19:14:08 - INFO - codeparrot_training - Step 25336: {'lr': 0.00046995027259020075, 'samples': 12972544, 'steps': 25336, 'loss/train': 2.4904191493988037}
-03/04/2022 19:14:11 - INFO - codeparrot_training - Step 25337: {'lr': 0.00046994775002203994, 'samples': 12973056, 'steps': 25337, 'loss/train': 1.7000421285629272}
-03/04/2022 19:14:12 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 19:14:17 - INFO - codeparrot_training - Step 25338: {'lr': 0.000469945227354774, 'samples': 12973568, 'steps': 25338, 'loss/train': 1.7487350702285767}
-03/04/2022 19:14:20 - INFO - codeparrot_training - Step 25339: {'lr': 0.00046994270458840416, 'samples': 12974080, 'steps': 25339, 'loss/train': 1.43644380569458}
-03/04/2022 19:14:20 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/04/2022 19:14:25 - INFO - codeparrot_training - Step 25340: {'lr': 0.0004699401817229316, 'samples': 12974592, 'steps': 25340, 'loss/train': 0.9968238472938538}
-03/04/2022 19:14:28 - INFO - codeparrot_training - Step 25341: {'lr': 0.0004699376587583573, 'samples': 12975104, 'steps': 25341, 'loss/train': 1.6751258373260498}
-03/04/2022 19:14:29 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 19:14:33 - INFO - codeparrot_training - Step 25342: {'lr': 0.0004699351356946825, 'samples': 12975616, 'steps': 25342, 'loss/train': 2.0064308643341064}
-03/04/2022 19:14:37 - INFO - codeparrot_training - Step 25343: {'lr': 0.00046993261253190833, 'samples': 12976128, 'steps': 25343, 'loss/train': 1.7874807119369507}
-03/04/2022 19:14:37 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/04/2022 19:14:42 - INFO - codeparrot_training - Step 25344: {'lr': 0.000469930089270036, 'samples': 12976640, 'steps': 25344, 'loss/train': 1.7672526836395264}
-03/04/2022 19:14:45 - INFO - codeparrot_training - Step 25345: {'lr': 0.0004699275659090665, 'samples': 12977152, 'steps': 25345, 'loss/train': 1.9256064891815186}
-03/04/2022 19:14:45 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/04/2022 19:14:50 - INFO - codeparrot_training - Step 25346: {'lr': 0.000469925042449001, 'samples': 12977664, 'steps': 25346, 'loss/train': 1.6666514873504639}
-03/04/2022 19:14:53 - INFO - codeparrot_training - Step 25347: {'lr': 0.0004699225188898407, 'samples': 12978176, 'steps': 25347, 'loss/train': 2.028059482574463}
-03/04/2022 19:14:54 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/04/2022 19:14:59 - INFO - codeparrot_training - Step 25348: {'lr': 0.00046991999523158666, 'samples': 12978688, 'steps': 25348, 'loss/train': 1.7633355855941772}
-03/04/2022 19:15:02 - INFO - codeparrot_training - Step 25349: {'lr': 0.0004699174714742401, 'samples': 12979200, 'steps': 25349, 'loss/train': 1.8247781991958618}
-03/04/2022 19:15:02 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/04/2022 19:15:07 - INFO - codeparrot_training - Step 25350: {'lr': 0.0004699149476178022, 'samples': 12979712, 'steps': 25350, 'loss/train': 2.3249549865722656}
-03/04/2022 19:15:10 - INFO - codeparrot_training - Step 25351: {'lr': 0.00046991242366227395, 'samples': 12980224, 'steps': 25351, 'loss/train': 2.033646821975708}
-03/04/2022 19:15:10 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 19:15:15 - INFO - codeparrot_training - Step 25352: {'lr': 0.0004699098996076565, 'samples': 12980736, 'steps': 25352, 'loss/train': 2.1840810775756836}
-03/04/2022 19:15:19 - INFO - codeparrot_training - Step 25353: {'lr': 0.0004699073754539511, 'samples': 12981248, 'steps': 25353, 'loss/train': 0.9812184572219849}
-03/04/2022 19:15:19 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/04/2022 19:15:24 - INFO - codeparrot_training - Step 25354: {'lr': 0.0004699048512011588, 'samples': 12981760, 'steps': 25354, 'loss/train': 2.208390474319458}
-03/04/2022 19:15:27 - INFO - codeparrot_training - Step 25355: {'lr': 0.0004699023268492808, 'samples': 12982272, 'steps': 25355, 'loss/train': 1.762279748916626}
-03/04/2022 19:15:27 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 19:15:33 - INFO - codeparrot_training - Step 25356: {'lr': 0.0004698998023983182, 'samples': 12982784, 'steps': 25356, 'loss/train': 1.1417272090911865}
-03/04/2022 19:15:36 - INFO - codeparrot_training - Step 25357: {'lr': 0.0004698972778482722, 'samples': 12983296, 'steps': 25357, 'loss/train': 1.4787989854812622}
-03/04/2022 19:15:36 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/04/2022 19:15:41 - INFO - codeparrot_training - Step 25358: {'lr': 0.0004698947531991438, 'samples': 12983808, 'steps': 25358, 'loss/train': 1.863358736038208}
-03/04/2022 19:15:44 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/04/2022 19:15:47 - INFO - codeparrot_training - Step 25359: {'lr': 0.0004698922284509342, 'samples': 12984320, 'steps': 25359, 'loss/train': 1.9527350664138794}
-03/04/2022 19:15:50 - INFO - codeparrot_training - Step 25360: {'lr': 0.00046988970360364456, 'samples': 12984832, 'steps': 25360, 'loss/train': 1.7599468231201172}
-03/04/2022 19:15:53 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 19:15:55 - INFO - codeparrot_training - Step 25361: {'lr': 0.0004698871786572761, 'samples': 12985344, 'steps': 25361, 'loss/train': 1.5590951442718506}
-03/04/2022 19:15:58 - INFO - codeparrot_training - Step 25362: {'lr': 0.0004698846536118298, 'samples': 12985856, 'steps': 25362, 'loss/train': 1.8527084589004517}
-03/04/2022 19:16:01 - INFO - codeparrot_training - Step 25363: {'lr': 0.00046988212846730686, 'samples': 12986368, 'steps': 25363, 'loss/train': 1.8146284818649292}
-03/04/2022 19:16:02 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 19:16:07 - INFO - codeparrot_training - Step 25364: {'lr': 0.0004698796032237085, 'samples': 12986880, 'steps': 25364, 'loss/train': 1.93575918674469}
-03/04/2022 19:16:10 - INFO - codeparrot_training - Step 25365: {'lr': 0.0004698770778810357, 'samples': 12987392, 'steps': 25365, 'loss/train': 1.7189249992370605}
-03/04/2022 19:16:10 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 19:16:15 - INFO - codeparrot_training - Step 25366: {'lr': 0.00046987455243928974, 'samples': 12987904, 'steps': 25366, 'loss/train': 1.3808679580688477}
-03/04/2022 19:16:19 - INFO - codeparrot_training - Step 25367: {'lr': 0.00046987202689847165, 'samples': 12988416, 'steps': 25367, 'loss/train': 3.013519763946533}
-03/04/2022 19:16:19 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/04/2022 19:16:24 - INFO - codeparrot_training - Step 25368: {'lr': 0.00046986950125858264, 'samples': 12988928, 'steps': 25368, 'loss/train': 1.7318766117095947}
-03/04/2022 19:16:27 - INFO - codeparrot_training - Step 25369: {'lr': 0.0004698669755196239, 'samples': 12989440, 'steps': 25369, 'loss/train': 2.2340152263641357}
-03/04/2022 19:16:28 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/04/2022 19:16:33 - INFO - codeparrot_training - Step 25370: {'lr': 0.0004698644496815964, 'samples': 12989952, 'steps': 25370, 'loss/train': 3.018932342529297}
-03/04/2022 19:16:36 - INFO - codeparrot_training - Step 25371: {'lr': 0.0004698619237445013, 'samples': 12990464, 'steps': 25371, 'loss/train': 2.163050413131714}
-03/04/2022 19:16:37 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 19:16:41 - INFO - codeparrot_training - Step 25372: {'lr': 0.00046985939770834, 'samples': 12990976, 'steps': 25372, 'loss/train': 1.3070533275604248}
-03/04/2022 19:16:45 - INFO - codeparrot_training - Step 25373: {'lr': 0.0004698568715731133, 'samples': 12991488, 'steps': 25373, 'loss/train': 2.114276885986328}
-03/04/2022 19:16:45 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/04/2022 19:16:50 - INFO - codeparrot_training - Step 25374: {'lr': 0.00046985434533882255, 'samples': 12992000, 'steps': 25374, 'loss/train': 1.9455182552337646}
-03/04/2022 19:16:53 - INFO - codeparrot_training - Step 25375: {'lr': 0.00046985181900546883, 'samples': 12992512, 'steps': 25375, 'loss/train': 1.8896756172180176}
-03/04/2022 19:16:54 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 19:16:58 - INFO - codeparrot_training - Step 25376: {'lr': 0.0004698492925730532, 'samples': 12993024, 'steps': 25376, 'loss/train': 2.2577056884765625}
-03/04/2022 19:17:01 - INFO - codeparrot_training - Step 25377: {'lr': 0.00046984676604157696, 'samples': 12993536, 'steps': 25377, 'loss/train': 1.6013085842132568}
-03/04/2022 19:17:02 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/04/2022 19:17:07 - INFO - codeparrot_training - Step 25378: {'lr': 0.0004698442394110411, 'samples': 12994048, 'steps': 25378, 'loss/train': 1.1733742952346802}
-03/04/2022 19:17:10 - INFO - codeparrot_training - Step 25379: {'lr': 0.0004698417126814468, 'samples': 12994560, 'steps': 25379, 'loss/train': 1.5479508638381958}
-03/04/2022 19:17:11 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 19:17:15 - INFO - codeparrot_training - Step 25380: {'lr': 0.0004698391858527953, 'samples': 12995072, 'steps': 25380, 'loss/train': 1.0326913595199585}
-03/04/2022 19:17:18 - INFO - codeparrot_training - Step 25381: {'lr': 0.0004698366589250876, 'samples': 12995584, 'steps': 25381, 'loss/train': 1.8304898738861084}
-03/04/2022 19:17:19 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 19:17:24 - INFO - codeparrot_training - Step 25382: {'lr': 0.0004698341318983249, 'samples': 12996096, 'steps': 25382, 'loss/train': 2.170163154602051}
-03/04/2022 19:17:27 - INFO - codeparrot_training - Step 25383: {'lr': 0.00046983160477250837, 'samples': 12996608, 'steps': 25383, 'loss/train': 1.8382006883621216}
-03/04/2022 19:17:30 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/04/2022 19:17:33 - INFO - codeparrot_training - Step 25384: {'lr': 0.00046982907754763905, 'samples': 12997120, 'steps': 25384, 'loss/train': 2.0447144508361816}
-03/04/2022 19:17:36 - INFO - codeparrot_training - Step 25385: {'lr': 0.0004698265502237182, 'samples': 12997632, 'steps': 25385, 'loss/train': 2.876307249069214}
-03/04/2022 19:17:38 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/04/2022 19:17:41 - INFO - codeparrot_training - Step 25386: {'lr': 0.0004698240228007469, 'samples': 12998144, 'steps': 25386, 'loss/train': 1.3803784847259521}
-03/04/2022 19:17:44 - INFO - codeparrot_training - Step 25387: {'lr': 0.0004698214952787262, 'samples': 12998656, 'steps': 25387, 'loss/train': 2.783010959625244}
-03/04/2022 19:17:47 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 19:17:50 - INFO - codeparrot_training - Step 25388: {'lr': 0.0004698189676576574, 'samples': 12999168, 'steps': 25388, 'loss/train': 1.868465542793274}
-03/04/2022 19:17:53 - INFO - codeparrot_training - Step 25389: {'lr': 0.00046981643993754155, 'samples': 12999680, 'steps': 25389, 'loss/train': 1.3487191200256348}
-03/04/2022 19:17:55 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 19:17:59 - INFO - codeparrot_training - Step 25390: {'lr': 0.0004698139121183798, 'samples': 13000192, 'steps': 25390, 'loss/train': 1.7889069318771362}
-03/04/2022 19:18:02 - INFO - codeparrot_training - Step 25391: {'lr': 0.00046981138420017335, 'samples': 13000704, 'steps': 25391, 'loss/train': 1.2679407596588135}
-03/04/2022 19:18:05 - INFO - codeparrot_training - Step 25392: {'lr': 0.00046980885618292317, 'samples': 13001216, 'steps': 25392, 'loss/train': 0.7383412718772888}
-03/04/2022 19:18:07 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/04/2022 19:18:10 - INFO - codeparrot_training - Step 25393: {'lr': 0.0004698063280666306, 'samples': 13001728, 'steps': 25393, 'loss/train': 0.6906705498695374}
-03/04/2022 19:18:13 - INFO - codeparrot_training - Step 25394: {'lr': 0.0004698037998512966, 'samples': 13002240, 'steps': 25394, 'loss/train': 1.7247951030731201}
-03/04/2022 19:18:16 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/04/2022 19:18:19 - INFO - codeparrot_training - Step 25395: {'lr': 0.00046980127153692256, 'samples': 13002752, 'steps': 25395, 'loss/train': 2.4694480895996094}
-03/04/2022 19:18:22 - INFO - codeparrot_training - Step 25396: {'lr': 0.00046979874312350935, 'samples': 13003264, 'steps': 25396, 'loss/train': 2.3787992000579834}
-03/04/2022 19:18:25 - INFO - codeparrot_training - Step 25397: {'lr': 0.00046979621461105817, 'samples': 13003776, 'steps': 25397, 'loss/train': 1.1216151714324951}
-03/04/2022 19:18:26 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/04/2022 19:18:32 - INFO - codeparrot_training - Step 25398: {'lr': 0.0004697936859995703, 'samples': 13004288, 'steps': 25398, 'loss/train': 1.9707132577896118}
-03/04/2022 19:18:35 - INFO - codeparrot_training - Step 25399: {'lr': 0.00046979115728904675, 'samples': 13004800, 'steps': 25399, 'loss/train': 1.8095448017120361}
-03/04/2022 19:18:38 - INFO - codeparrot_training - Step 25400: {'lr': 0.0004697886284794887, 'samples': 13005312, 'steps': 25400, 'loss/train': 1.9364482164382935}
-03/04/2022 19:18:39 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/04/2022 19:18:43 - INFO - codeparrot_training - Step 25401: {'lr': 0.00046978609957089724, 'samples': 13005824, 'steps': 25401, 'loss/train': 2.0713348388671875}
-03/04/2022 19:18:46 - INFO - codeparrot_training - Step 25402: {'lr': 0.0004697835705632736, 'samples': 13006336, 'steps': 25402, 'loss/train': 2.3738913536071777}
-03/04/2022 19:18:47 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 19:18:52 - INFO - codeparrot_training - Step 25403: {'lr': 0.00046978104145661885, 'samples': 13006848, 'steps': 25403, 'loss/train': 6.628108501434326}
-03/04/2022 19:18:55 - INFO - codeparrot_training - Step 25404: {'lr': 0.00046977851225093423, 'samples': 13007360, 'steps': 25404, 'loss/train': 1.9153882265090942}
-03/04/2022 19:18:56 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 19:19:00 - INFO - codeparrot_training - Step 25405: {'lr': 0.0004697759829462207, 'samples': 13007872, 'steps': 25405, 'loss/train': 2.217949151992798}
-03/04/2022 19:19:03 - INFO - codeparrot_training - Step 25406: {'lr': 0.0004697734535424796, 'samples': 13008384, 'steps': 25406, 'loss/train': 1.9899888038635254}
-03/04/2022 19:19:04 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 19:19:09 - INFO - codeparrot_training - Step 25407: {'lr': 0.0004697709240397119, 'samples': 13008896, 'steps': 25407, 'loss/train': 1.1458783149719238}
-03/04/2022 19:19:12 - INFO - codeparrot_training - Step 25408: {'lr': 0.00046976839443791887, 'samples': 13009408, 'steps': 25408, 'loss/train': 2.013826847076416}
-03/04/2022 19:19:13 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 19:19:17 - INFO - codeparrot_training - Step 25409: {'lr': 0.00046976586473710156, 'samples': 13009920, 'steps': 25409, 'loss/train': 1.3955961465835571}
-03/04/2022 19:19:20 - INFO - codeparrot_training - Step 25410: {'lr': 0.0004697633349372611, 'samples': 13010432, 'steps': 25410, 'loss/train': 1.5838645696640015}
-03/04/2022 19:19:22 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/04/2022 19:19:26 - INFO - codeparrot_training - Step 25411: {'lr': 0.00046976080503839874, 'samples': 13010944, 'steps': 25411, 'loss/train': 2.2237675189971924}
-03/04/2022 19:19:29 - INFO - codeparrot_training - Step 25412: {'lr': 0.0004697582750405155, 'samples': 13011456, 'steps': 25412, 'loss/train': 0.7739744186401367}
-03/04/2022 19:19:31 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/04/2022 19:19:34 - INFO - codeparrot_training - Step 25413: {'lr': 0.00046975574494361263, 'samples': 13011968, 'steps': 25413, 'loss/train': 2.140094757080078}
-03/04/2022 19:19:37 - INFO - codeparrot_training - Step 25414: {'lr': 0.00046975321474769115, 'samples': 13012480, 'steps': 25414, 'loss/train': 1.7429466247558594}
-03/04/2022 19:19:39 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 19:19:43 - INFO - codeparrot_training - Step 25415: {'lr': 0.0004697506844527523, 'samples': 13012992, 'steps': 25415, 'loss/train': 2.6152782440185547}
-03/04/2022 19:19:46 - INFO - codeparrot_training - Step 25416: {'lr': 0.0004697481540587972, 'samples': 13013504, 'steps': 25416, 'loss/train': 1.7161967754364014}
-03/04/2022 19:19:48 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 19:19:51 - INFO - codeparrot_training - Step 25417: {'lr': 0.00046974562356582694, 'samples': 13014016, 'steps': 25417, 'loss/train': 2.0265867710113525}
-03/04/2022 19:19:54 - INFO - codeparrot_training - Step 25418: {'lr': 0.0004697430929738427, 'samples': 13014528, 'steps': 25418, 'loss/train': 1.7055197954177856}
-03/04/2022 19:19:56 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 19:20:00 - INFO - codeparrot_training - Step 25419: {'lr': 0.0004697405622828456, 'samples': 13015040, 'steps': 25419, 'loss/train': 0.8557844758033752}
-03/04/2022 19:20:03 - INFO - codeparrot_training - Step 25420: {'lr': 0.00046973803149283686, 'samples': 13015552, 'steps': 25420, 'loss/train': 2.39294695854187}
-03/04/2022 19:20:05 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/04/2022 19:20:08 - INFO - codeparrot_training - Step 25421: {'lr': 0.0004697355006038175, 'samples': 13016064, 'steps': 25421, 'loss/train': 1.6991658210754395}
-03/04/2022 19:20:11 - INFO - codeparrot_training - Step 25422: {'lr': 0.0004697329696157887, 'samples': 13016576, 'steps': 25422, 'loss/train': 1.942380666732788}
-03/04/2022 19:20:14 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/04/2022 19:20:17 - INFO - codeparrot_training - Step 25423: {'lr': 0.00046973043852875163, 'samples': 13017088, 'steps': 25423, 'loss/train': 1.4704680442810059}
-03/04/2022 19:20:20 - INFO - codeparrot_training - Step 25424: {'lr': 0.00046972790734270745, 'samples': 13017600, 'steps': 25424, 'loss/train': 1.440824270248413}
-03/04/2022 19:20:22 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/04/2022 19:20:25 - INFO - codeparrot_training - Step 25425: {'lr': 0.0004697253760576572, 'samples': 13018112, 'steps': 25425, 'loss/train': 1.66150963306427}
-03/04/2022 19:20:28 - INFO - codeparrot_training - Step 25426: {'lr': 0.00046972284467360217, 'samples': 13018624, 'steps': 25426, 'loss/train': 1.2757622003555298}
-03/04/2022 19:20:31 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/04/2022 19:20:34 - INFO - codeparrot_training - Step 25427: {'lr': 0.0004697203131905433, 'samples': 13019136, 'steps': 25427, 'loss/train': 2.876934766769409}
-03/04/2022 19:20:37 - INFO - codeparrot_training - Step 25428: {'lr': 0.00046971778160848196, 'samples': 13019648, 'steps': 25428, 'loss/train': 1.770692229270935}
-03/04/2022 19:20:39 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/04/2022 19:20:42 - INFO - codeparrot_training - Step 25429: {'lr': 0.0004697152499274191, 'samples': 13020160, 'steps': 25429, 'loss/train': 0.806185781955719}
-03/04/2022 19:20:45 - INFO - codeparrot_training - Step 25430: {'lr': 0.00046971271814735593, 'samples': 13020672, 'steps': 25430, 'loss/train': 1.650345802307129}
-03/04/2022 19:20:48 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/04/2022 19:20:51 - INFO - codeparrot_training - Step 25431: {'lr': 0.0004697101862682936, 'samples': 13021184, 'steps': 25431, 'loss/train': 1.8754361867904663}
-03/04/2022 19:20:54 - INFO - codeparrot_training - Step 25432: {'lr': 0.00046970765429023336, 'samples': 13021696, 'steps': 25432, 'loss/train': 2.203113555908203}
-03/04/2022 19:20:56 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/04/2022 19:20:59 - INFO - codeparrot_training - Step 25433: {'lr': 0.00046970512221317616, 'samples': 13022208, 'steps': 25433, 'loss/train': 1.2450807094573975}
-03/04/2022 19:21:02 - INFO - codeparrot_training - Step 25434: {'lr': 0.00046970259003712323, 'samples': 13022720, 'steps': 25434, 'loss/train': 1.3730324506759644}
-03/04/2022 19:21:05 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/04/2022 19:21:07 - INFO - codeparrot_training - Step 25435: {'lr': 0.00046970005776207575, 'samples': 13023232, 'steps': 25435, 'loss/train': 2.3566360473632812}
-03/04/2022 19:21:11 - INFO - codeparrot_training - Step 25436: {'lr': 0.00046969752538803477, 'samples': 13023744, 'steps': 25436, 'loss/train': 0.9843683242797852}
-03/04/2022 19:21:13 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/04/2022 19:21:16 - INFO - codeparrot_training - Step 25437: {'lr': 0.0004696949929150015, 'samples': 13024256, 'steps': 25437, 'loss/train': 1.8300721645355225}
-03/04/2022 19:21:19 - INFO - codeparrot_training - Step 25438: {'lr': 0.00046969246034297697, 'samples': 13024768, 'steps': 25438, 'loss/train': 2.2559244632720947}
-03/04/2022 19:21:22 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/04/2022 19:21:24 - INFO - codeparrot_training - Step 25439: {'lr': 0.0004696899276719625, 'samples': 13025280, 'steps': 25439, 'loss/train': 2.0386831760406494}
-03/04/2022 19:21:28 - INFO - codeparrot_training - Step 25440: {'lr': 0.0004696873949019591, 'samples': 13025792, 'steps': 25440, 'loss/train': 1.8705074787139893}
-03/04/2022 19:21:30 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 19:21:33 - INFO - codeparrot_training - Step 25441: {'lr': 0.000469684862032968, 'samples': 13026304, 'steps': 25441, 'loss/train': 1.8020484447479248}
-03/04/2022 19:21:36 - INFO - codeparrot_training - Step 25442: {'lr': 0.0004696823290649902, 'samples': 13026816, 'steps': 25442, 'loss/train': 1.6336922645568848}
-03/04/2022 19:21:38 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 19:21:41 - INFO - codeparrot_training - Step 25443: {'lr': 0.000469679795998027, 'samples': 13027328, 'steps': 25443, 'loss/train': 2.300718307495117}
-03/04/2022 19:21:44 - INFO - codeparrot_training - Step 25444: {'lr': 0.00046967726283207945, 'samples': 13027840, 'steps': 25444, 'loss/train': 2.009284496307373}
-03/04/2022 19:21:47 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/04/2022 19:21:50 - INFO - codeparrot_training - Step 25445: {'lr': 0.0004696747295671487, 'samples': 13028352, 'steps': 25445, 'loss/train': 2.7127432823181152}
-03/04/2022 19:21:53 - INFO - codeparrot_training - Step 25446: {'lr': 0.000469672196203236, 'samples': 13028864, 'steps': 25446, 'loss/train': 2.504605531692505}
-03/04/2022 19:21:55 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 19:21:58 - INFO - codeparrot_training - Step 25447: {'lr': 0.0004696696627403423, 'samples': 13029376, 'steps': 25447, 'loss/train': 0.8868412375450134}
-03/04/2022 19:22:01 - INFO - codeparrot_training - Step 25448: {'lr': 0.00046966712917846887, 'samples': 13029888, 'steps': 25448, 'loss/train': 2.0862550735473633}
-03/04/2022 19:22:04 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 19:22:07 - INFO - codeparrot_training - Step 25449: {'lr': 0.00046966459551761684, 'samples': 13030400, 'steps': 25449, 'loss/train': 0.8388962149620056}
-03/04/2022 19:22:10 - INFO - codeparrot_training - Step 25450: {'lr': 0.00046966206175778723, 'samples': 13030912, 'steps': 25450, 'loss/train': 1.3482890129089355}
-03/04/2022 19:22:12 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/04/2022 19:22:15 - INFO - codeparrot_training - Step 25451: {'lr': 0.0004696595278989814, 'samples': 13031424, 'steps': 25451, 'loss/train': 1.2773497104644775}
-03/04/2022 19:22:18 - INFO - codeparrot_training - Step 25452: {'lr': 0.00046965699394120033, 'samples': 13031936, 'steps': 25452, 'loss/train': 1.2560234069824219}
-03/04/2022 19:22:20 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 19:22:24 - INFO - codeparrot_training - Step 25453: {'lr': 0.0004696544598844452, 'samples': 13032448, 'steps': 25453, 'loss/train': 0.8781254887580872}
-03/04/2022 19:22:27 - INFO - codeparrot_training - Step 25454: {'lr': 0.00046965192572871723, 'samples': 13032960, 'steps': 25454, 'loss/train': 2.633864164352417}
-03/04/2022 19:22:29 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/04/2022 19:22:32 - INFO - codeparrot_training - Step 25455: {'lr': 0.0004696493914740174, 'samples': 13033472, 'steps': 25455, 'loss/train': 0.208157017827034}
-03/04/2022 19:22:35 - INFO - codeparrot_training - Step 25456: {'lr': 0.00046964685712034697, 'samples': 13033984, 'steps': 25456, 'loss/train': 2.106882333755493}
-03/04/2022 19:22:38 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/04/2022 19:22:41 - INFO - codeparrot_training - Step 25457: {'lr': 0.00046964432266770713, 'samples': 13034496, 'steps': 25457, 'loss/train': 1.3349844217300415}
-03/04/2022 19:22:44 - INFO - codeparrot_training - Step 25458: {'lr': 0.0004696417881160989, 'samples': 13035008, 'steps': 25458, 'loss/train': 1.5720466375350952}
-03/04/2022 19:22:46 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/04/2022 19:22:49 - INFO - codeparrot_training - Step 25459: {'lr': 0.0004696392534655234, 'samples': 13035520, 'steps': 25459, 'loss/train': 1.8213374614715576}
-03/04/2022 19:22:52 - INFO - codeparrot_training - Step 25460: {'lr': 0.0004696367187159819, 'samples': 13036032, 'steps': 25460, 'loss/train': 1.1172958612442017}
-03/04/2022 19:22:55 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 19:22:58 - INFO - codeparrot_training - Step 25461: {'lr': 0.00046963418386747547, 'samples': 13036544, 'steps': 25461, 'loss/train': 1.5118916034698486}
-03/04/2022 19:23:01 - INFO - codeparrot_training - Step 25462: {'lr': 0.0004696316489200053, 'samples': 13037056, 'steps': 25462, 'loss/train': 2.1516897678375244}
-03/04/2022 19:23:06 - INFO - codeparrot_training - Step 25463: {'lr': 0.00046962911387357246, 'samples': 13037568, 'steps': 25463, 'loss/train': 1.5250990390777588}
-03/04/2022 19:23:09 - INFO - codeparrot_training - Step 25464: {'lr': 0.0004696265787281782, 'samples': 13038080, 'steps': 25464, 'loss/train': 1.4249238967895508}
-03/04/2022 19:23:12 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 19:23:15 - INFO - codeparrot_training - Step 25465: {'lr': 0.0004696240434838235, 'samples': 13038592, 'steps': 25465, 'loss/train': 1.3011730909347534}
-03/04/2022 19:23:18 - INFO - codeparrot_training - Step 25466: {'lr': 0.00046962150814050963, 'samples': 13039104, 'steps': 25466, 'loss/train': 1.488167643547058}
-03/04/2022 19:23:21 - INFO - codeparrot_training - Step 25467: {'lr': 0.0004696189726982377, 'samples': 13039616, 'steps': 25467, 'loss/train': 2.148378610610962}
-03/04/2022 19:23:22 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/04/2022 19:23:26 - INFO - codeparrot_training - Step 25468: {'lr': 0.00046961643715700885, 'samples': 13040128, 'steps': 25468, 'loss/train': 2.2054636478424072}
-03/04/2022 19:23:30 - INFO - codeparrot_training - Step 25469: {'lr': 0.00046961390151682426, 'samples': 13040640, 'steps': 25469, 'loss/train': 2.311095952987671}
-03/04/2022 19:23:30 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/04/2022 19:23:35 - INFO - codeparrot_training - Step 25470: {'lr': 0.000469611365777685, 'samples': 13041152, 'steps': 25470, 'loss/train': 1.5300289392471313}
-03/04/2022 19:23:38 - INFO - codeparrot_training - Step 25471: {'lr': 0.0004696088299395922, 'samples': 13041664, 'steps': 25471, 'loss/train': 2.0319151878356934}
-03/04/2022 19:23:38 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/04/2022 19:23:43 - INFO - codeparrot_training - Step 25472: {'lr': 0.0004696062940025471, 'samples': 13042176, 'steps': 25472, 'loss/train': 1.9446732997894287}
-03/04/2022 19:23:46 - INFO - codeparrot_training - Step 25473: {'lr': 0.0004696037579665509, 'samples': 13042688, 'steps': 25473, 'loss/train': 2.5790936946868896}
-03/04/2022 19:23:47 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/04/2022 19:23:52 - INFO - codeparrot_training - Step 25474: {'lr': 0.00046960122183160446, 'samples': 13043200, 'steps': 25474, 'loss/train': 1.8887279033660889}
-03/04/2022 19:23:55 - INFO - codeparrot_training - Step 25475: {'lr': 0.00046959868559770914, 'samples': 13043712, 'steps': 25475, 'loss/train': 1.4355084896087646}
-03/04/2022 19:23:55 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/04/2022 19:24:00 - INFO - codeparrot_training - Step 25476: {'lr': 0.00046959614926486606, 'samples': 13044224, 'steps': 25476, 'loss/train': 1.659017562866211}
-03/04/2022 19:24:03 - INFO - codeparrot_training - Step 25477: {'lr': 0.00046959361283307636, 'samples': 13044736, 'steps': 25477, 'loss/train': 1.377712607383728}
-03/04/2022 19:24:04 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/04/2022 19:24:09 - INFO - codeparrot_training - Step 25478: {'lr': 0.0004695910763023412, 'samples': 13045248, 'steps': 25478, 'loss/train': 2.275122880935669}
-03/04/2022 19:24:12 - INFO - codeparrot_training - Step 25479: {'lr': 0.0004695885396726616, 'samples': 13045760, 'steps': 25479, 'loss/train': 0.8331573605537415}
-03/04/2022 19:24:12 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/04/2022 19:24:17 - INFO - codeparrot_training - Step 25480: {'lr': 0.00046958600294403887, 'samples': 13046272, 'steps': 25480, 'loss/train': 0.5317729711532593}
-03/04/2022 19:24:20 - INFO - codeparrot_training - Step 25481: {'lr': 0.000469583466116474, 'samples': 13046784, 'steps': 25481, 'loss/train': 1.9140645265579224}
-03/04/2022 19:24:21 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/04/2022 19:24:25 - INFO - codeparrot_training - Step 25482: {'lr': 0.00046958092918996823, 'samples': 13047296, 'steps': 25482, 'loss/train': 1.4599580764770508}
-03/04/2022 19:24:28 - INFO - codeparrot_training - Step 25483: {'lr': 0.0004695783921645227, 'samples': 13047808, 'steps': 25483, 'loss/train': 1.858157992362976}
-03/04/2022 19:24:29 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/04/2022 19:24:34 - INFO - codeparrot_training - Step 25484: {'lr': 0.00046957585504013853, 'samples': 13048320, 'steps': 25484, 'loss/train': 1.5703688859939575}
-03/04/2022 19:24:37 - INFO - codeparrot_training - Step 25485: {'lr': 0.0004695733178168169, 'samples': 13048832, 'steps': 25485, 'loss/train': 1.8283672332763672}
-03/04/2022 19:24:37 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 19:24:42 - INFO - codeparrot_training - Step 25486: {'lr': 0.00046957078049455895, 'samples': 13049344, 'steps': 25486, 'loss/train': 1.4905426502227783}
-03/04/2022 19:24:46 - INFO - codeparrot_training - Step 25487: {'lr': 0.00046956824307336565, 'samples': 13049856, 'steps': 25487, 'loss/train': 2.2556517124176025}
-03/04/2022 19:24:46 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 19:24:51 - INFO - codeparrot_training - Step 25488: {'lr': 0.0004695657055532384, 'samples': 13050368, 'steps': 25488, 'loss/train': 2.299039125442505}
-03/04/2022 19:24:54 - INFO - codeparrot_training - Step 25489: {'lr': 0.0004695631679341782, 'samples': 13050880, 'steps': 25489, 'loss/train': 1.6763784885406494}
-03/04/2022 19:24:54 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/04/2022 19:24:59 - INFO - codeparrot_training - Step 25490: {'lr': 0.0004695606302161862, 'samples': 13051392, 'steps': 25490, 'loss/train': 1.3162503242492676}
-03/04/2022 19:25:03 - INFO - codeparrot_training - Step 25491: {'lr': 0.0004695580923992636, 'samples': 13051904, 'steps': 25491, 'loss/train': 1.248085856437683}
-03/04/2022 19:25:03 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/04/2022 19:25:08 - INFO - codeparrot_training - Step 25492: {'lr': 0.0004695555544834116, 'samples': 13052416, 'steps': 25492, 'loss/train': 3.236177921295166}
-03/04/2022 19:25:11 - INFO - codeparrot_training - Step 25493: {'lr': 0.00046955301646863114, 'samples': 13052928, 'steps': 25493, 'loss/train': 2.4744601249694824}
-03/04/2022 19:25:11 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/04/2022 19:25:16 - INFO - codeparrot_training - Step 25494: {'lr': 0.0004695504783549235, 'samples': 13053440, 'steps': 25494, 'loss/train': 2.267122268676758}
-03/04/2022 19:25:20 - INFO - codeparrot_training - Step 25495: {'lr': 0.0004695479401422898, 'samples': 13053952, 'steps': 25495, 'loss/train': 1.790039300918579}
-03/04/2022 19:25:20 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/04/2022 19:25:25 - INFO - codeparrot_training - Step 25496: {'lr': 0.0004695454018307312, 'samples': 13054464, 'steps': 25496, 'loss/train': 1.5867931842803955}
-03/04/2022 19:25:28 - INFO - codeparrot_training - Step 25497: {'lr': 0.0004695428634202488, 'samples': 13054976, 'steps': 25497, 'loss/train': 1.3060795068740845}
-03/04/2022 19:25:30 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/04/2022 19:25:34 - INFO - codeparrot_training - Step 25498: {'lr': 0.0004695403249108438, 'samples': 13055488, 'steps': 25498, 'loss/train': 1.9687601327896118}
-03/04/2022 19:25:37 - INFO - codeparrot_training - Step 25499: {'lr': 0.0004695377863025173, 'samples': 13056000, 'steps': 25499, 'loss/train': 2.364687919616699}
-03/04/2022 19:25:38 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/04/2022 19:25:42 - INFO - codeparrot_training - Step 25500: {'lr': 0.00046953524759527055, 'samples': 13056512, 'steps': 25500, 'loss/train': 1.4824386835098267}
-03/04/2022 19:25:45 - INFO - codeparrot_training - Step 25501: {'lr': 0.0004695327087891045, 'samples': 13057024, 'steps': 25501, 'loss/train': 1.6287752389907837}
-03/04/2022 19:25:46 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/04/2022 19:25:50 - INFO - codeparrot_training - Step 25502: {'lr': 0.00046953016988402044, 'samples': 13057536, 'steps': 25502, 'loss/train': 2.4598002433776855}
-03/04/2022 19:25:53 - INFO - codeparrot_training - Step 25503: {'lr': 0.0004695276308800194, 'samples': 13058048, 'steps': 25503, 'loss/train': 2.146589517593384}
-03/04/2022 19:25:54 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/04/2022 19:25:59 - INFO - codeparrot_training - Step 25504: {'lr': 0.00046952509177710267, 'samples': 13058560, 'steps': 25504, 'loss/train': 2.2702624797821045}
-03/04/2022 19:26:02 - INFO - codeparrot_training - Step 25505: {'lr': 0.00046952255257527134, 'samples': 13059072, 'steps': 25505, 'loss/train': 2.3818323612213135}
-03/04/2022 19:26:03 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 19:26:08 - INFO - codeparrot_training - Step 25506: {'lr': 0.0004695200132745265, 'samples': 13059584, 'steps': 25506, 'loss/train': 1.735205054283142}
-03/04/2022 19:26:11 - INFO - codeparrot_training - Step 25507: {'lr': 0.00046951747387486933, 'samples': 13060096, 'steps': 25507, 'loss/train': 0.24268989264965057}
-03/04/2022 19:26:14 - INFO - codeparrot_training - Step 25508: {'lr': 0.00046951493437630097, 'samples': 13060608, 'steps': 25508, 'loss/train': 1.9178614616394043}
-03/04/2022 19:26:14 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/04/2022 19:26:19 - INFO - codeparrot_training - Step 25509: {'lr': 0.0004695123947788226, 'samples': 13061120, 'steps': 25509, 'loss/train': 2.8096487522125244}
-03/04/2022 19:26:22 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/04/2022 19:26:25 - INFO - codeparrot_training - Step 25510: {'lr': 0.0004695098550824353, 'samples': 13061632, 'steps': 25510, 'loss/train': 1.8710687160491943}
-03/04/2022 19:26:28 - INFO - codeparrot_training - Step 25511: {'lr': 0.0004695073152871403, 'samples': 13062144, 'steps': 25511, 'loss/train': 1.6735628843307495}
-03/04/2022 19:26:31 - INFO - codeparrot_training - Step 25512: {'lr': 0.00046950477539293864, 'samples': 13062656, 'steps': 25512, 'loss/train': 1.9222924709320068}
-03/04/2022 19:26:31 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/04/2022 19:26:36 - INFO - codeparrot_training - Step 25513: {'lr': 0.0004695022353998315, 'samples': 13063168, 'steps': 25513, 'loss/train': 1.86252760887146}
-03/04/2022 19:26:40 - INFO - codeparrot_training - Step 25514: {'lr': 0.0004694996953078201, 'samples': 13063680, 'steps': 25514, 'loss/train': 2.654667615890503}
-03/04/2022 19:26:40 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/04/2022 19:26:45 - INFO - codeparrot_training - Step 25515: {'lr': 0.0004694971551169055, 'samples': 13064192, 'steps': 25515, 'loss/train': 1.5680612325668335}
-03/04/2022 19:26:48 - INFO - codeparrot_training - Step 25516: {'lr': 0.00046949461482708875, 'samples': 13064704, 'steps': 25516, 'loss/train': 2.2980082035064697}
-03/04/2022 19:26:48 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 19:26:53 - INFO - codeparrot_training - Step 25517: {'lr': 0.0004694920744383713, 'samples': 13065216, 'steps': 25517, 'loss/train': 1.0531436204910278}
-03/04/2022 19:26:57 - INFO - codeparrot_training - Step 25518: {'lr': 0.000469489533950754, 'samples': 13065728, 'steps': 25518, 'loss/train': 2.043027639389038}
-03/04/2022 19:26:57 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/04/2022 19:27:02 - INFO - codeparrot_training - Step 25519: {'lr': 0.00046948699336423817, 'samples': 13066240, 'steps': 25519, 'loss/train': 2.1827847957611084}
-03/04/2022 19:27:05 - INFO - codeparrot_training - Step 25520: {'lr': 0.0004694844526788248, 'samples': 13066752, 'steps': 25520, 'loss/train': 0.9641440510749817}
-03/04/2022 19:27:05 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/04/2022 19:27:10 - INFO - codeparrot_training - Step 25521: {'lr': 0.0004694819118945152, 'samples': 13067264, 'steps': 25521, 'loss/train': 1.4785652160644531}
-03/04/2022 19:27:13 - INFO - codeparrot_training - Step 25522: {'lr': 0.00046947937101131046, 'samples': 13067776, 'steps': 25522, 'loss/train': 1.9741688966751099}
-03/04/2022 19:27:14 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/04/2022 19:27:19 - INFO - codeparrot_training - Step 25523: {'lr': 0.0004694768300292116, 'samples': 13068288, 'steps': 25523, 'loss/train': 1.9820784330368042}
-03/04/2022 19:27:22 - INFO - codeparrot_training - Step 25524: {'lr': 0.0004694742889482199, 'samples': 13068800, 'steps': 25524, 'loss/train': 1.8756790161132812}
-03/04/2022 19:27:22 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/04/2022 19:27:27 - INFO - codeparrot_training - Step 25525: {'lr': 0.0004694717477683365, 'samples': 13069312, 'steps': 25525, 'loss/train': 2.252000331878662}
-03/04/2022 19:27:30 - INFO - codeparrot_training - Step 25526: {'lr': 0.0004694692064895625, 'samples': 13069824, 'steps': 25526, 'loss/train': 1.2726101875305176}
-03/04/2022 19:27:30 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 19:27:36 - INFO - codeparrot_training - Step 25527: {'lr': 0.0004694666651118991, 'samples': 13070336, 'steps': 25527, 'loss/train': 1.942238211631775}
-03/04/2022 19:27:39 - INFO - codeparrot_training - Step 25528: {'lr': 0.00046946412363534735, 'samples': 13070848, 'steps': 25528, 'loss/train': 1.694091558456421}
-03/04/2022 19:27:39 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/04/2022 19:27:44 - INFO - codeparrot_training - Step 25529: {'lr': 0.0004694615820599085, 'samples': 13071360, 'steps': 25529, 'loss/train': 1.6104822158813477}
-03/04/2022 19:27:47 - INFO - codeparrot_training - Step 25530: {'lr': 0.00046945904038558364, 'samples': 13071872, 'steps': 25530, 'loss/train': 2.3564205169677734}
-03/04/2022 19:27:47 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/04/2022 19:27:53 - INFO - codeparrot_training - Step 25531: {'lr': 0.00046945649861237387, 'samples': 13072384, 'steps': 25531, 'loss/train': 2.644564628601074}
-03/04/2022 19:27:56 - INFO - codeparrot_training - Step 25532: {'lr': 0.00046945395674028047, 'samples': 13072896, 'steps': 25532, 'loss/train': 1.0451500415802002}
-03/04/2022 19:27:57 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/04/2022 19:28:01 - INFO - codeparrot_training - Step 25533: {'lr': 0.0004694514147693044, 'samples': 13073408, 'steps': 25533, 'loss/train': 6.538641929626465}
-03/04/2022 19:28:04 - INFO - codeparrot_training - Step 25534: {'lr': 0.000469448872699447, 'samples': 13073920, 'steps': 25534, 'loss/train': 1.4924501180648804}
-03/04/2022 19:28:06 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/04/2022 19:28:09 - INFO - codeparrot_training - Step 25535: {'lr': 0.0004694463305307093, 'samples': 13074432, 'steps': 25535, 'loss/train': 1.0473151206970215}
-03/04/2022 19:28:13 - INFO - codeparrot_training - Step 25536: {'lr': 0.00046944378826309244, 'samples': 13074944, 'steps': 25536, 'loss/train': 1.9682713747024536}
-03/04/2022 19:28:14 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/04/2022 19:28:18 - INFO - codeparrot_training - Step 25537: {'lr': 0.00046944124589659765, 'samples': 13075456, 'steps': 25537, 'loss/train': 2.4293124675750732}
-03/04/2022 19:28:21 - INFO - codeparrot_training - Step 25538: {'lr': 0.00046943870343122595, 'samples': 13075968, 'steps': 25538, 'loss/train': 2.119398832321167}
-03/04/2022 19:28:22 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/04/2022 19:28:27 - INFO - codeparrot_training - Step 25539: {'lr': 0.0004694361608669786, 'samples': 13076480, 'steps': 25539, 'loss/train': 2.2235565185546875}
-03/04/2022 19:28:30 - INFO - codeparrot_training - Step 25540: {'lr': 0.0004694336182038567, 'samples': 13076992, 'steps': 25540, 'loss/train': 1.9418087005615234}
-03/04/2022 19:28:33 - INFO - codeparrot_training - Step 25541: {'lr': 0.00046943107544186144, 'samples': 13077504, 'steps': 25541, 'loss/train': 2.049295663833618}
-03/04/2022 19:28:33 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 19:28:38 - INFO - codeparrot_training - Step 25542: {'lr': 0.0004694285325809938, 'samples': 13078016, 'steps': 25542, 'loss/train': 2.1261496543884277}
-03/04/2022 19:28:41 - INFO - codeparrot_training - Step 25543: {'lr': 0.00046942598962125515, 'samples': 13078528, 'steps': 25543, 'loss/train': 1.9301607608795166}
-03/04/2022 19:28:42 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 19:28:47 - INFO - codeparrot_training - Step 25544: {'lr': 0.00046942344656264657, 'samples': 13079040, 'steps': 25544, 'loss/train': 2.0735669136047363}
-03/04/2022 19:28:50 - INFO - codeparrot_training - Step 25545: {'lr': 0.0004694209034051691, 'samples': 13079552, 'steps': 25545, 'loss/train': 1.5645065307617188}
-03/04/2022 19:28:50 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 19:28:55 - INFO - codeparrot_training - Step 25546: {'lr': 0.00046941836014882394, 'samples': 13080064, 'steps': 25546, 'loss/train': 2.1198136806488037}
-03/04/2022 19:28:58 - INFO - codeparrot_training - Step 25547: {'lr': 0.00046941581679361234, 'samples': 13080576, 'steps': 25547, 'loss/train': 1.9883184432983398}
-03/04/2022 19:28:59 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 19:29:04 - INFO - codeparrot_training - Step 25548: {'lr': 0.00046941327333953526, 'samples': 13081088, 'steps': 25548, 'loss/train': 1.9838398694992065}
-03/04/2022 19:29:07 - INFO - codeparrot_training - Step 25549: {'lr': 0.00046941072978659397, 'samples': 13081600, 'steps': 25549, 'loss/train': 2.0995378494262695}
-03/04/2022 19:29:07 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/04/2022 19:29:12 - INFO - codeparrot_training - Step 25550: {'lr': 0.00046940818613478964, 'samples': 13082112, 'steps': 25550, 'loss/train': 1.506577968597412}
-03/04/2022 19:29:15 - INFO - codeparrot_training - Step 25551: {'lr': 0.0004694056423841233, 'samples': 13082624, 'steps': 25551, 'loss/train': 2.5039942264556885}
-03/04/2022 19:29:16 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 19:29:20 - INFO - codeparrot_training - Step 25552: {'lr': 0.00046940309853459625, 'samples': 13083136, 'steps': 25552, 'loss/train': 2.0975401401519775}
-03/04/2022 19:29:24 - INFO - codeparrot_training - Step 25553: {'lr': 0.00046940055458620945, 'samples': 13083648, 'steps': 25553, 'loss/train': 2.0207152366638184}
-03/04/2022 19:29:24 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/04/2022 19:29:29 - INFO - codeparrot_training - Step 25554: {'lr': 0.0004693980105389642, 'samples': 13084160, 'steps': 25554, 'loss/train': 2.4204697608947754}
-03/04/2022 19:29:32 - INFO - codeparrot_training - Step 25555: {'lr': 0.00046939546639286156, 'samples': 13084672, 'steps': 25555, 'loss/train': 2.580156087875366}
-03/04/2022 19:29:32 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/04/2022 19:29:37 - INFO - codeparrot_training - Step 25556: {'lr': 0.00046939292214790275, 'samples': 13085184, 'steps': 25556, 'loss/train': 2.19118595123291}
-03/04/2022 19:29:41 - INFO - codeparrot_training - Step 25557: {'lr': 0.0004693903778040889, 'samples': 13085696, 'steps': 25557, 'loss/train': 1.671200156211853}
-03/04/2022 19:29:41 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/04/2022 19:29:46 - INFO - codeparrot_training - Step 25558: {'lr': 0.0004693878333614211, 'samples': 13086208, 'steps': 25558, 'loss/train': 1.713773250579834}
-03/04/2022 19:29:49 - INFO - codeparrot_training - Step 25559: {'lr': 0.0004693852888199005, 'samples': 13086720, 'steps': 25559, 'loss/train': 1.9031437635421753}
-03/04/2022 19:29:49 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 19:29:54 - INFO - codeparrot_training - Step 25560: {'lr': 0.0004693827441795283, 'samples': 13087232, 'steps': 25560, 'loss/train': 1.929993748664856}
-03/04/2022 19:29:58 - INFO - codeparrot_training - Step 25561: {'lr': 0.00046938019944030556, 'samples': 13087744, 'steps': 25561, 'loss/train': 1.4844731092453003}
-03/04/2022 19:29:59 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 19:30:03 - INFO - codeparrot_training - Step 25562: {'lr': 0.00046937765460223357, 'samples': 13088256, 'steps': 25562, 'loss/train': 2.0093929767608643}
-03/04/2022 19:30:06 - INFO - codeparrot_training - Step 25563: {'lr': 0.0004693751096653134, 'samples': 13088768, 'steps': 25563, 'loss/train': 1.611359715461731}
-03/04/2022 19:30:07 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/04/2022 19:30:11 - INFO - codeparrot_training - Step 25564: {'lr': 0.00046937256462954615, 'samples': 13089280, 'steps': 25564, 'loss/train': 1.8652870655059814}
-03/04/2022 19:30:15 - INFO - codeparrot_training - Step 25565: {'lr': 0.00046937001949493294, 'samples': 13089792, 'steps': 25565, 'loss/train': 2.514896869659424}
-03/04/2022 19:30:15 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 19:30:20 - INFO - codeparrot_training - Step 25566: {'lr': 0.0004693674742614751, 'samples': 13090304, 'steps': 25566, 'loss/train': 2.0481574535369873}
-03/04/2022 19:30:23 - INFO - codeparrot_training - Step 25567: {'lr': 0.0004693649289291736, 'samples': 13090816, 'steps': 25567, 'loss/train': 1.851012110710144}
-03/04/2022 19:30:24 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 19:30:28 - INFO - codeparrot_training - Step 25568: {'lr': 0.0004693623834980297, 'samples': 13091328, 'steps': 25568, 'loss/train': 6.5985307693481445}
-03/04/2022 19:30:32 - INFO - codeparrot_training - Step 25569: {'lr': 0.00046935983796804443, 'samples': 13091840, 'steps': 25569, 'loss/train': 1.994016170501709}
-03/04/2022 19:30:33 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 19:30:37 - INFO - codeparrot_training - Step 25570: {'lr': 0.000469357292339219, 'samples': 13092352, 'steps': 25570, 'loss/train': 2.1103549003601074}
-03/04/2022 19:30:40 - INFO - codeparrot_training - Step 25571: {'lr': 0.00046935474661155465, 'samples': 13092864, 'steps': 25571, 'loss/train': 2.151684045791626}
-03/04/2022 19:30:41 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/04/2022 19:30:45 - INFO - codeparrot_training - Step 25572: {'lr': 0.00046935220078505235, 'samples': 13093376, 'steps': 25572, 'loss/train': 1.9302334785461426}
-03/04/2022 19:30:48 - INFO - codeparrot_training - Step 25573: {'lr': 0.00046934965485971337, 'samples': 13093888, 'steps': 25573, 'loss/train': 1.9277316331863403}
-03/04/2022 19:30:50 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/04/2022 19:30:54 - INFO - codeparrot_training - Step 25574: {'lr': 0.00046934710883553884, 'samples': 13094400, 'steps': 25574, 'loss/train': 1.8211218118667603}
-03/04/2022 19:30:57 - INFO - codeparrot_training - Step 25575: {'lr': 0.00046934456271252985, 'samples': 13094912, 'steps': 25575, 'loss/train': 2.893122911453247}
-03/04/2022 19:30:58 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 19:31:02 - INFO - codeparrot_training - Step 25576: {'lr': 0.0004693420164906876, 'samples': 13095424, 'steps': 25576, 'loss/train': 2.557299852371216}
-03/04/2022 19:31:06 - INFO - codeparrot_training - Step 25577: {'lr': 0.0004693394701700132, 'samples': 13095936, 'steps': 25577, 'loss/train': 2.520155906677246}
-03/04/2022 19:31:07 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/04/2022 19:31:11 - INFO - codeparrot_training - Step 25578: {'lr': 0.00046933692375050783, 'samples': 13096448, 'steps': 25578, 'loss/train': 1.8020070791244507}
-03/04/2022 19:31:14 - INFO - codeparrot_training - Step 25579: {'lr': 0.00046933437723217265, 'samples': 13096960, 'steps': 25579, 'loss/train': 2.3446097373962402}
-03/04/2022 19:31:15 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/04/2022 19:31:19 - INFO - codeparrot_training - Step 25580: {'lr': 0.0004693318306150087, 'samples': 13097472, 'steps': 25580, 'loss/train': 1.7016338109970093}
-03/04/2022 19:31:22 - INFO - codeparrot_training - Step 25581: {'lr': 0.0004693292838990173, 'samples': 13097984, 'steps': 25581, 'loss/train': 1.2174557447433472}
-03/04/2022 19:31:23 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/04/2022 19:31:28 - INFO - codeparrot_training - Step 25582: {'lr': 0.0004693267370841995, 'samples': 13098496, 'steps': 25582, 'loss/train': 0.9873405694961548}
-03/04/2022 19:31:31 - INFO - codeparrot_training - Step 25583: {'lr': 0.00046932419017055646, 'samples': 13099008, 'steps': 25583, 'loss/train': 1.4384894371032715}
-03/04/2022 19:31:31 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 19:31:36 - INFO - codeparrot_training - Step 25584: {'lr': 0.0004693216431580893, 'samples': 13099520, 'steps': 25584, 'loss/train': 1.1552149057388306}
-03/04/2022 19:31:39 - INFO - codeparrot_training - Step 25585: {'lr': 0.00046931909604679925, 'samples': 13100032, 'steps': 25585, 'loss/train': 2.5182080268859863}
-03/04/2022 19:31:40 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 19:31:44 - INFO - codeparrot_training - Step 25586: {'lr': 0.0004693165488366873, 'samples': 13100544, 'steps': 25586, 'loss/train': 2.044692039489746}
-03/04/2022 19:31:48 - INFO - codeparrot_training - Step 25587: {'lr': 0.00046931400152775473, 'samples': 13101056, 'steps': 25587, 'loss/train': 1.7909234762191772}
-03/04/2022 19:31:48 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/04/2022 19:31:53 - INFO - codeparrot_training - Step 25588: {'lr': 0.00046931145412000265, 'samples': 13101568, 'steps': 25588, 'loss/train': 1.7947889566421509}
-03/04/2022 19:31:56 - INFO - codeparrot_training - Step 25589: {'lr': 0.00046930890661343226, 'samples': 13102080, 'steps': 25589, 'loss/train': 1.3816215991973877}
-03/04/2022 19:31:56 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 19:32:01 - INFO - codeparrot_training - Step 25590: {'lr': 0.00046930635900804466, 'samples': 13102592, 'steps': 25590, 'loss/train': 2.793059825897217}
-03/04/2022 19:32:05 - INFO - codeparrot_training - Step 25591: {'lr': 0.0004693038113038409, 'samples': 13103104, 'steps': 25591, 'loss/train': 1.6341270208358765}
-03/04/2022 19:32:05 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/04/2022 19:32:10 - INFO - codeparrot_training - Step 25592: {'lr': 0.0004693012635008224, 'samples': 13103616, 'steps': 25592, 'loss/train': 2.15512752532959}
-03/04/2022 19:32:13 - INFO - codeparrot_training - Step 25593: {'lr': 0.00046929871559898994, 'samples': 13104128, 'steps': 25593, 'loss/train': 1.784670352935791}
-03/04/2022 19:32:13 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/04/2022 19:32:18 - INFO - codeparrot_training - Step 25594: {'lr': 0.00046929616759834505, 'samples': 13104640, 'steps': 25594, 'loss/train': 2.7549431324005127}
-03/04/2022 19:32:21 - INFO - codeparrot_training - Step 25595: {'lr': 0.00046929361949888857, 'samples': 13105152, 'steps': 25595, 'loss/train': 2.017996311187744}
-03/04/2022 19:32:22 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/04/2022 19:32:27 - INFO - codeparrot_training - Step 25596: {'lr': 0.00046929107130062176, 'samples': 13105664, 'steps': 25596, 'loss/train': 2.2522010803222656}
-03/04/2022 19:32:30 - INFO - codeparrot_training - Step 25597: {'lr': 0.00046928852300354585, 'samples': 13106176, 'steps': 25597, 'loss/train': 2.138850688934326}
-03/04/2022 19:32:30 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/04/2022 19:32:35 - INFO - codeparrot_training - Step 25598: {'lr': 0.0004692859746076619, 'samples': 13106688, 'steps': 25598, 'loss/train': 1.3575628995895386}
-03/04/2022 19:32:38 - INFO - codeparrot_training - Step 25599: {'lr': 0.00046928342611297105, 'samples': 13107200, 'steps': 25599, 'loss/train': 1.8996742963790894}
-03/04/2022 19:32:39 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/04/2022 19:32:44 - INFO - codeparrot_training - Step 25600: {'lr': 0.00046928087751947444, 'samples': 13107712, 'steps': 25600, 'loss/train': 1.523504614830017}
-03/04/2022 19:32:47 - INFO - codeparrot_training - Step 25601: {'lr': 0.00046927832882717323, 'samples': 13108224, 'steps': 25601, 'loss/train': 1.3956414461135864}
-03/04/2022 19:32:47 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 19:32:52 - INFO - codeparrot_training - Step 25602: {'lr': 0.0004692757800360687, 'samples': 13108736, 'steps': 25602, 'loss/train': 2.287830352783203}
-03/04/2022 19:32:55 - INFO - codeparrot_training - Step 25603: {'lr': 0.0004692732311461618, 'samples': 13109248, 'steps': 25603, 'loss/train': 2.1512067317962646}
-03/04/2022 19:32:56 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/04/2022 19:33:00 - INFO - codeparrot_training - Step 25604: {'lr': 0.0004692706821574538, 'samples': 13109760, 'steps': 25604, 'loss/train': 1.6540371179580688}
-03/04/2022 19:33:04 - INFO - codeparrot_training - Step 25605: {'lr': 0.00046926813306994586, 'samples': 13110272, 'steps': 25605, 'loss/train': 1.6433981657028198}
-03/04/2022 19:33:04 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/04/2022 19:33:09 - INFO - codeparrot_training - Step 25606: {'lr': 0.00046926558388363904, 'samples': 13110784, 'steps': 25606, 'loss/train': 1.4688023328781128}
-03/04/2022 19:33:12 - INFO - codeparrot_training - Step 25607: {'lr': 0.00046926303459853447, 'samples': 13111296, 'steps': 25607, 'loss/train': 0.9257676601409912}
-03/04/2022 19:33:12 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/04/2022 19:33:17 - INFO - codeparrot_training - Step 25608: {'lr': 0.00046926048521463344, 'samples': 13111808, 'steps': 25608, 'loss/train': 1.3039506673812866}
-03/04/2022 19:33:20 - INFO - codeparrot_training - Step 25609: {'lr': 0.000469257935731937, 'samples': 13112320, 'steps': 25609, 'loss/train': 1.5367895364761353}
-03/04/2022 19:33:21 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/04/2022 19:33:26 - INFO - codeparrot_training - Step 25610: {'lr': 0.0004692553861504463, 'samples': 13112832, 'steps': 25610, 'loss/train': 2.0313289165496826}
-03/04/2022 19:33:29 - INFO - codeparrot_training - Step 25611: {'lr': 0.00046925283647016253, 'samples': 13113344, 'steps': 25611, 'loss/train': 1.483324408531189}
-03/04/2022 19:33:29 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 19:33:34 - INFO - codeparrot_training - Step 25612: {'lr': 0.0004692502866910868, 'samples': 13113856, 'steps': 25612, 'loss/train': 1.3099238872528076}
-03/04/2022 19:33:37 - INFO - codeparrot_training - Step 25613: {'lr': 0.0004692477368132203, 'samples': 13114368, 'steps': 25613, 'loss/train': 2.0489625930786133}
-03/04/2022 19:33:38 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 19:33:43 - INFO - codeparrot_training - Step 25614: {'lr': 0.0004692451868365641, 'samples': 13114880, 'steps': 25614, 'loss/train': 2.0967164039611816}
-03/04/2022 19:33:46 - INFO - codeparrot_training - Step 25615: {'lr': 0.00046924263676111945, 'samples': 13115392, 'steps': 25615, 'loss/train': 1.089672565460205}
-03/04/2022 19:33:46 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/04/2022 19:33:51 - INFO - codeparrot_training - Step 25616: {'lr': 0.00046924008658688745, 'samples': 13115904, 'steps': 25616, 'loss/train': 1.4431177377700806}
-03/04/2022 19:33:54 - INFO - codeparrot_training - Step 25617: {'lr': 0.00046923753631386924, 'samples': 13116416, 'steps': 25617, 'loss/train': 1.235486626625061}
-03/04/2022 19:33:54 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/04/2022 19:33:59 - INFO - codeparrot_training - Step 25618: {'lr': 0.0004692349859420659, 'samples': 13116928, 'steps': 25618, 'loss/train': 1.563315987586975}
-03/04/2022 19:34:03 - INFO - codeparrot_training - Step 25619: {'lr': 0.00046923243547147874, 'samples': 13117440, 'steps': 25619, 'loss/train': 2.0744869709014893}
-03/04/2022 19:34:03 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/04/2022 19:34:08 - INFO - codeparrot_training - Step 25620: {'lr': 0.0004692298849021088, 'samples': 13117952, 'steps': 25620, 'loss/train': 1.7623610496520996}
-03/04/2022 19:34:11 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/04/2022 19:34:13 - INFO - codeparrot_training - Step 25621: {'lr': 0.00046922733423395736, 'samples': 13118464, 'steps': 25621, 'loss/train': 1.1628296375274658}
-03/04/2022 19:34:16 - INFO - codeparrot_training - Step 25622: {'lr': 0.0004692247834670253, 'samples': 13118976, 'steps': 25622, 'loss/train': 1.7978562116622925}
-03/04/2022 19:34:20 - INFO - codeparrot_training - Step 25623: {'lr': 0.000469222232601314, 'samples': 13119488, 'steps': 25623, 'loss/train': 1.954198956489563}
-03/04/2022 19:34:20 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 19:34:25 - INFO - codeparrot_training - Step 25624: {'lr': 0.0004692196816368246, 'samples': 13120000, 'steps': 25624, 'loss/train': 1.76058030128479}
-03/04/2022 19:34:28 - INFO - codeparrot_training - Step 25625: {'lr': 0.00046921713057355817, 'samples': 13120512, 'steps': 25625, 'loss/train': 0.46784284710884094}
-03/04/2022 19:34:28 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/04/2022 19:34:34 - INFO - codeparrot_training - Step 25626: {'lr': 0.0004692145794115159, 'samples': 13121024, 'steps': 25626, 'loss/train': 1.738781452178955}
-03/04/2022 19:34:37 - INFO - codeparrot_training - Step 25627: {'lr': 0.00046921202815069883, 'samples': 13121536, 'steps': 25627, 'loss/train': 2.209368944168091}
-03/04/2022 19:34:37 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/04/2022 19:34:42 - INFO - codeparrot_training - Step 25628: {'lr': 0.00046920947679110833, 'samples': 13122048, 'steps': 25628, 'loss/train': 1.9466670751571655}
-03/04/2022 19:34:45 - INFO - codeparrot_training - Step 25629: {'lr': 0.00046920692533274533, 'samples': 13122560, 'steps': 25629, 'loss/train': 1.9629749059677124}
-03/04/2022 19:34:45 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 19:34:50 - INFO - codeparrot_training - Step 25630: {'lr': 0.0004692043737756111, 'samples': 13123072, 'steps': 25630, 'loss/train': 1.9756267070770264}
-03/04/2022 19:34:54 - INFO - codeparrot_training - Step 25631: {'lr': 0.00046920182211970677, 'samples': 13123584, 'steps': 25631, 'loss/train': 0.9821460247039795}
-03/04/2022 19:34:54 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 19:34:59 - INFO - codeparrot_training - Step 25632: {'lr': 0.00046919927036503353, 'samples': 13124096, 'steps': 25632, 'loss/train': 2.324683904647827}
-03/04/2022 19:35:02 - INFO - codeparrot_training - Step 25633: {'lr': 0.0004691967185115924, 'samples': 13124608, 'steps': 25633, 'loss/train': 1.4814739227294922}
-03/04/2022 19:35:02 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/04/2022 19:35:07 - INFO - codeparrot_training - Step 25634: {'lr': 0.00046919416655938465, 'samples': 13125120, 'steps': 25634, 'loss/train': 1.478456974029541}
-03/04/2022 19:35:11 - INFO - codeparrot_training - Step 25635: {'lr': 0.0004691916145084113, 'samples': 13125632, 'steps': 25635, 'loss/train': 2.4840168952941895}
-03/04/2022 19:35:11 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/04/2022 19:35:16 - INFO - codeparrot_training - Step 25636: {'lr': 0.0004691890623586737, 'samples': 13126144, 'steps': 25636, 'loss/train': 2.018822193145752}
-03/04/2022 19:35:19 - INFO - codeparrot_training - Step 25637: {'lr': 0.00046918651011017287, 'samples': 13126656, 'steps': 25637, 'loss/train': 2.5675034523010254}
-03/04/2022 19:35:19 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 19:35:24 - INFO - codeparrot_training - Step 25638: {'lr': 0.00046918395776290997, 'samples': 13127168, 'steps': 25638, 'loss/train': 1.7031505107879639}
-03/04/2022 19:35:27 - INFO - codeparrot_training - Step 25639: {'lr': 0.0004691814053168861, 'samples': 13127680, 'steps': 25639, 'loss/train': 1.558652400970459}
-03/04/2022 19:35:28 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 19:35:33 - INFO - codeparrot_training - Step 25640: {'lr': 0.0004691788527721026, 'samples': 13128192, 'steps': 25640, 'loss/train': 1.2536239624023438}
-03/04/2022 19:35:36 - INFO - codeparrot_training - Step 25641: {'lr': 0.0004691763001285604, 'samples': 13128704, 'steps': 25641, 'loss/train': 1.5706579685211182}
-03/04/2022 19:35:36 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/04/2022 19:35:41 - INFO - codeparrot_training - Step 25642: {'lr': 0.0004691737473862607, 'samples': 13129216, 'steps': 25642, 'loss/train': 1.7827893495559692}
-03/04/2022 19:35:44 - INFO - codeparrot_training - Step 25643: {'lr': 0.00046917119454520487, 'samples': 13129728, 'steps': 25643, 'loss/train': 1.0207802057266235}
-03/04/2022 19:35:45 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/04/2022 19:35:50 - INFO - codeparrot_training - Step 25644: {'lr': 0.00046916864160539376, 'samples': 13130240, 'steps': 25644, 'loss/train': 2.112990140914917}
-03/04/2022 19:35:53 - INFO - codeparrot_training - Step 25645: {'lr': 0.00046916608856682865, 'samples': 13130752, 'steps': 25645, 'loss/train': 1.4446650743484497}
-03/04/2022 19:35:53 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/04/2022 19:35:58 - INFO - codeparrot_training - Step 25646: {'lr': 0.0004691635354295106, 'samples': 13131264, 'steps': 25646, 'loss/train': 1.5009338855743408}
-03/04/2022 19:36:01 - INFO - codeparrot_training - Step 25647: {'lr': 0.00046916098219344093, 'samples': 13131776, 'steps': 25647, 'loss/train': 1.0889884233474731}
-03/04/2022 19:36:01 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 19:36:06 - INFO - codeparrot_training - Step 25648: {'lr': 0.0004691584288586207, 'samples': 13132288, 'steps': 25648, 'loss/train': 1.8314423561096191}
-03/04/2022 19:36:09 - INFO - codeparrot_training - Step 25649: {'lr': 0.0004691558754250511, 'samples': 13132800, 'steps': 25649, 'loss/train': 1.8279274702072144}
-03/04/2022 19:36:10 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/04/2022 19:36:15 - INFO - codeparrot_training - Step 25650: {'lr': 0.0004691533218927332, 'samples': 13133312, 'steps': 25650, 'loss/train': 1.9700393676757812}
-03/04/2022 19:36:18 - INFO - codeparrot_training - Step 25651: {'lr': 0.00046915076826166814, 'samples': 13133824, 'steps': 25651, 'loss/train': 2.469473123550415}
-03/04/2022 19:36:18 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/04/2022 19:36:24 - INFO - codeparrot_training - Step 25652: {'lr': 0.0004691482145318572, 'samples': 13134336, 'steps': 25652, 'loss/train': 1.3389499187469482}
-03/04/2022 19:36:27 - INFO - codeparrot_training - Step 25653: {'lr': 0.00046914566070330144, 'samples': 13134848, 'steps': 25653, 'loss/train': 2.1133339405059814}
-03/04/2022 19:36:28 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/04/2022 19:36:32 - INFO - codeparrot_training - Step 25654: {'lr': 0.00046914310677600204, 'samples': 13135360, 'steps': 25654, 'loss/train': 1.6804629564285278}
-03/04/2022 19:36:35 - INFO - codeparrot_training - Step 25655: {'lr': 0.00046914055274996017, 'samples': 13135872, 'steps': 25655, 'loss/train': 2.234924077987671}
-03/04/2022 19:36:37 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/04/2022 19:36:40 - INFO - codeparrot_training - Step 25656: {'lr': 0.00046913799862517686, 'samples': 13136384, 'steps': 25656, 'loss/train': 0.47969186305999756}
-03/04/2022 19:36:43 - INFO - codeparrot_training - Step 25657: {'lr': 0.0004691354444016534, 'samples': 13136896, 'steps': 25657, 'loss/train': 1.9764001369476318}
-03/04/2022 19:36:45 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/04/2022 19:36:49 - INFO - codeparrot_training - Step 25658: {'lr': 0.00046913289007939087, 'samples': 13137408, 'steps': 25658, 'loss/train': 1.7756062746047974}
-03/04/2022 19:36:52 - INFO - codeparrot_training - Step 25659: {'lr': 0.00046913033565839046, 'samples': 13137920, 'steps': 25659, 'loss/train': 1.8282790184020996}
-03/04/2022 19:36:53 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/04/2022 19:36:57 - INFO - codeparrot_training - Step 25660: {'lr': 0.0004691277811386533, 'samples': 13138432, 'steps': 25660, 'loss/train': 2.614138126373291}
-03/04/2022 19:37:00 - INFO - codeparrot_training - Step 25661: {'lr': 0.0004691252265201805, 'samples': 13138944, 'steps': 25661, 'loss/train': 1.8260549306869507}
-03/04/2022 19:37:02 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/04/2022 19:37:06 - INFO - codeparrot_training - Step 25662: {'lr': 0.00046912267180297337, 'samples': 13139456, 'steps': 25662, 'loss/train': 1.4136120080947876}
-03/04/2022 19:37:09 - INFO - codeparrot_training - Step 25663: {'lr': 0.0004691201169870328, 'samples': 13139968, 'steps': 25663, 'loss/train': 1.2220109701156616}
-03/04/2022 19:37:10 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/04/2022 19:37:14 - INFO - codeparrot_training - Step 25664: {'lr': 0.00046911756207236024, 'samples': 13140480, 'steps': 25664, 'loss/train': 2.043792724609375}
-03/04/2022 19:37:17 - INFO - codeparrot_training - Step 25665: {'lr': 0.0004691150070589566, 'samples': 13140992, 'steps': 25665, 'loss/train': 1.6563245058059692}
-03/04/2022 19:37:19 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/04/2022 19:37:23 - INFO - codeparrot_training - Step 25666: {'lr': 0.00046911245194682306, 'samples': 13141504, 'steps': 25666, 'loss/train': 2.127086877822876}
-03/04/2022 19:37:26 - INFO - codeparrot_training - Step 25667: {'lr': 0.00046910989673596093, 'samples': 13142016, 'steps': 25667, 'loss/train': 1.2142102718353271}
-03/04/2022 19:37:27 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/04/2022 19:37:31 - INFO - codeparrot_training - Step 25668: {'lr': 0.00046910734142637124, 'samples': 13142528, 'steps': 25668, 'loss/train': 1.6071752309799194}
-03/04/2022 19:37:34 - INFO - codeparrot_training - Step 25669: {'lr': 0.00046910478601805514, 'samples': 13143040, 'steps': 25669, 'loss/train': 1.6032277345657349}
-03/04/2022 19:37:35 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 19:37:39 - INFO - codeparrot_training - Step 25670: {'lr': 0.0004691022305110138, 'samples': 13143552, 'steps': 25670, 'loss/train': 1.4956276416778564}
-03/04/2022 19:37:43 - INFO - codeparrot_training - Step 25671: {'lr': 0.0004690996749052484, 'samples': 13144064, 'steps': 25671, 'loss/train': 1.9554494619369507}
-03/04/2022 19:37:44 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/04/2022 19:37:48 - INFO - codeparrot_training - Step 25672: {'lr': 0.00046909711920076, 'samples': 13144576, 'steps': 25672, 'loss/train': 2.5203769207000732}
-03/04/2022 19:37:51 - INFO - codeparrot_training - Step 25673: {'lr': 0.0004690945633975499, 'samples': 13145088, 'steps': 25673, 'loss/train': 2.047031879425049}
-03/04/2022 19:37:53 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/04/2022 19:37:56 - INFO - codeparrot_training - Step 25674: {'lr': 0.00046909200749561914, 'samples': 13145600, 'steps': 25674, 'loss/train': 1.3079192638397217}
-03/04/2022 19:38:00 - INFO - codeparrot_training - Step 25675: {'lr': 0.00046908945149496897, 'samples': 13146112, 'steps': 25675, 'loss/train': 2.713205099105835}
-03/04/2022 19:38:01 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/04/2022 19:38:05 - INFO - codeparrot_training - Step 25676: {'lr': 0.00046908689539560034, 'samples': 13146624, 'steps': 25676, 'loss/train': 0.8642597198486328}
-03/04/2022 19:38:08 - INFO - codeparrot_training - Step 25677: {'lr': 0.0004690843391975146, 'samples': 13147136, 'steps': 25677, 'loss/train': 2.11598801612854}
-03/04/2022 19:38:09 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/04/2022 19:38:13 - INFO - codeparrot_training - Step 25678: {'lr': 0.0004690817829007129, 'samples': 13147648, 'steps': 25678, 'loss/train': 1.6526800394058228}
-03/04/2022 19:38:17 - INFO - codeparrot_training - Step 25679: {'lr': 0.00046907922650519623, 'samples': 13148160, 'steps': 25679, 'loss/train': 2.2532341480255127}
-03/04/2022 19:38:18 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 19:38:22 - INFO - codeparrot_training - Step 25680: {'lr': 0.0004690766700109659, 'samples': 13148672, 'steps': 25680, 'loss/train': 2.280402421951294}
-03/04/2022 19:38:25 - INFO - codeparrot_training - Step 25681: {'lr': 0.00046907411341802295, 'samples': 13149184, 'steps': 25681, 'loss/train': 0.8179460763931274}
-03/04/2022 19:38:26 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/04/2022 19:38:30 - INFO - codeparrot_training - Step 25682: {'lr': 0.0004690715567263687, 'samples': 13149696, 'steps': 25682, 'loss/train': 2.325756549835205}
-03/04/2022 19:38:34 - INFO - codeparrot_training - Step 25683: {'lr': 0.00046906899993600406, 'samples': 13150208, 'steps': 25683, 'loss/train': 1.8430765867233276}
-03/04/2022 19:38:35 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/04/2022 19:38:39 - INFO - codeparrot_training - Step 25684: {'lr': 0.00046906644304693033, 'samples': 13150720, 'steps': 25684, 'loss/train': 1.4834637641906738}
-03/04/2022 19:38:42 - INFO - codeparrot_training - Step 25685: {'lr': 0.0004690638860591487, 'samples': 13151232, 'steps': 25685, 'loss/train': 2.361208200454712}
-03/04/2022 19:38:43 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 19:38:47 - INFO - codeparrot_training - Step 25686: {'lr': 0.00046906132897266026, 'samples': 13151744, 'steps': 25686, 'loss/train': 1.2955799102783203}
-03/04/2022 19:38:51 - INFO - codeparrot_training - Step 25687: {'lr': 0.00046905877178746614, 'samples': 13152256, 'steps': 25687, 'loss/train': 2.484726667404175}
-03/04/2022 19:38:52 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/04/2022 19:38:56 - INFO - codeparrot_training - Step 25688: {'lr': 0.0004690562145035675, 'samples': 13152768, 'steps': 25688, 'loss/train': 1.6255322694778442}
-03/04/2022 19:38:59 - INFO - codeparrot_training - Step 25689: {'lr': 0.00046905365712096553, 'samples': 13153280, 'steps': 25689, 'loss/train': 2.10624098777771}
-03/04/2022 19:39:00 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 19:39:04 - INFO - codeparrot_training - Step 25690: {'lr': 0.0004690510996396614, 'samples': 13153792, 'steps': 25690, 'loss/train': 1.2157890796661377}
-03/04/2022 19:39:07 - INFO - codeparrot_training - Step 25691: {'lr': 0.0004690485420596561, 'samples': 13154304, 'steps': 25691, 'loss/train': 2.579500913619995}
-03/04/2022 19:39:09 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/04/2022 19:39:13 - INFO - codeparrot_training - Step 25692: {'lr': 0.000469045984380951, 'samples': 13154816, 'steps': 25692, 'loss/train': 1.5140951871871948}
-03/04/2022 19:39:16 - INFO - codeparrot_training - Step 25693: {'lr': 0.0004690434266035471, 'samples': 13155328, 'steps': 25693, 'loss/train': 1.475740909576416}
-03/04/2022 19:39:17 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/04/2022 19:39:21 - INFO - codeparrot_training - Step 25694: {'lr': 0.00046904086872744577, 'samples': 13155840, 'steps': 25694, 'loss/train': 2.270071029663086}
-03/04/2022 19:39:24 - INFO - codeparrot_training - Step 25695: {'lr': 0.0004690383107526479, 'samples': 13156352, 'steps': 25695, 'loss/train': 1.8595331907272339}
-03/04/2022 19:39:26 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/04/2022 19:39:30 - INFO - codeparrot_training - Step 25696: {'lr': 0.0004690357526791547, 'samples': 13156864, 'steps': 25696, 'loss/train': 1.9620486497879028}
-03/04/2022 19:39:33 - INFO - codeparrot_training - Step 25697: {'lr': 0.00046903319450696744, 'samples': 13157376, 'steps': 25697, 'loss/train': 2.904324769973755}
-03/04/2022 19:39:35 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/04/2022 19:39:38 - INFO - codeparrot_training - Step 25698: {'lr': 0.00046903063623608714, 'samples': 13157888, 'steps': 25698, 'loss/train': 1.9329532384872437}
-03/04/2022 19:39:41 - INFO - codeparrot_training - Step 25699: {'lr': 0.00046902807786651507, 'samples': 13158400, 'steps': 25699, 'loss/train': 3.061762571334839}
-03/04/2022 19:39:43 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/04/2022 19:39:47 - INFO - codeparrot_training - Step 25700: {'lr': 0.00046902551939825236, 'samples': 13158912, 'steps': 25700, 'loss/train': 2.0464911460876465}
-03/04/2022 19:39:50 - INFO - codeparrot_training - Step 25701: {'lr': 0.00046902296083130003, 'samples': 13159424, 'steps': 25701, 'loss/train': 1.8379894495010376}
-03/04/2022 19:39:52 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 19:39:55 - INFO - codeparrot_training - Step 25702: {'lr': 0.00046902040216565945, 'samples': 13159936, 'steps': 25702, 'loss/train': 1.6784310340881348}
-03/04/2022 19:39:58 - INFO - codeparrot_training - Step 25703: {'lr': 0.0004690178434013316, 'samples': 13160448, 'steps': 25703, 'loss/train': 1.1337891817092896}
-03/04/2022 19:40:00 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 19:40:03 - INFO - codeparrot_training - Step 25704: {'lr': 0.00046901528453831764, 'samples': 13160960, 'steps': 25704, 'loss/train': 2.459540843963623}
-03/04/2022 19:40:07 - INFO - codeparrot_training - Step 25705: {'lr': 0.0004690127255766188, 'samples': 13161472, 'steps': 25705, 'loss/train': 1.7593038082122803}
-03/04/2022 19:40:09 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 19:40:12 - INFO - codeparrot_training - Step 25706: {'lr': 0.0004690101665162362, 'samples': 13161984, 'steps': 25706, 'loss/train': 1.7941027879714966}
-03/04/2022 19:40:15 - INFO - codeparrot_training - Step 25707: {'lr': 0.00046900760735717103, 'samples': 13162496, 'steps': 25707, 'loss/train': 2.2718758583068848}
-03/04/2022 19:40:17 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/04/2022 19:40:20 - INFO - codeparrot_training - Step 25708: {'lr': 0.00046900504809942433, 'samples': 13163008, 'steps': 25708, 'loss/train': 0.9856160879135132}
-03/04/2022 19:40:23 - INFO - codeparrot_training - Step 25709: {'lr': 0.00046900248874299746, 'samples': 13163520, 'steps': 25709, 'loss/train': 2.0409157276153564}
-03/04/2022 19:40:26 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 19:40:29 - INFO - codeparrot_training - Step 25710: {'lr': 0.0004689999292878914, 'samples': 13164032, 'steps': 25710, 'loss/train': 2.0801544189453125}
-03/04/2022 19:40:32 - INFO - codeparrot_training - Step 25711: {'lr': 0.00046899736973410734, 'samples': 13164544, 'steps': 25711, 'loss/train': 1.0832571983337402}
-03/04/2022 19:40:34 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 19:40:37 - INFO - codeparrot_training - Step 25712: {'lr': 0.0004689948100816465, 'samples': 13165056, 'steps': 25712, 'loss/train': 1.4017027616500854}
-03/04/2022 19:40:40 - INFO - codeparrot_training - Step 25713: {'lr': 0.00046899225033050985, 'samples': 13165568, 'steps': 25713, 'loss/train': 2.0863749980926514}
-03/04/2022 19:40:43 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/04/2022 19:40:46 - INFO - codeparrot_training - Step 25714: {'lr': 0.0004689896904806987, 'samples': 13166080, 'steps': 25714, 'loss/train': 1.7175102233886719}
-03/04/2022 19:40:49 - INFO - codeparrot_training - Step 25715: {'lr': 0.0004689871305322143, 'samples': 13166592, 'steps': 25715, 'loss/train': 2.223897695541382}
-03/04/2022 19:40:51 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 19:40:54 - INFO - codeparrot_training - Step 25716: {'lr': 0.0004689845704850576, 'samples': 13167104, 'steps': 25716, 'loss/train': 1.4767804145812988}
-03/04/2022 19:40:57 - INFO - codeparrot_training - Step 25717: {'lr': 0.0004689820103392298, 'samples': 13167616, 'steps': 25717, 'loss/train': 2.8384833335876465}
-03/04/2022 19:41:00 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/04/2022 19:41:03 - INFO - codeparrot_training - Step 25718: {'lr': 0.0004689794500947321, 'samples': 13168128, 'steps': 25718, 'loss/train': 1.5797239542007446}
-03/04/2022 19:41:06 - INFO - codeparrot_training - Step 25719: {'lr': 0.0004689768897515657, 'samples': 13168640, 'steps': 25719, 'loss/train': 1.79481041431427}
-03/04/2022 19:41:08 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 19:41:11 - INFO - codeparrot_training - Step 25720: {'lr': 0.0004689743293097316, 'samples': 13169152, 'steps': 25720, 'loss/train': 1.9758723974227905}
-03/04/2022 19:41:14 - INFO - codeparrot_training - Step 25721: {'lr': 0.0004689717687692311, 'samples': 13169664, 'steps': 25721, 'loss/train': 2.1605889797210693}
-03/04/2022 19:41:17 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/04/2022 19:41:20 - INFO - codeparrot_training - Step 25722: {'lr': 0.0004689692081300653, 'samples': 13170176, 'steps': 25722, 'loss/train': 1.4824808835983276}
-03/04/2022 19:41:23 - INFO - codeparrot_training - Step 25723: {'lr': 0.0004689666473922354, 'samples': 13170688, 'steps': 25723, 'loss/train': 1.045037031173706}
-03/04/2022 19:41:25 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/04/2022 19:41:28 - INFO - codeparrot_training - Step 25724: {'lr': 0.0004689640865557424, 'samples': 13171200, 'steps': 25724, 'loss/train': 2.0227856636047363}
-03/04/2022 19:41:31 - INFO - codeparrot_training - Step 25725: {'lr': 0.0004689615256205876, 'samples': 13171712, 'steps': 25725, 'loss/train': 2.1369924545288086}
-03/04/2022 19:41:33 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 19:41:37 - INFO - codeparrot_training - Step 25726: {'lr': 0.0004689589645867721, 'samples': 13172224, 'steps': 25726, 'loss/train': 2.2324066162109375}
-03/04/2022 19:41:40 - INFO - codeparrot_training - Step 25727: {'lr': 0.0004689564034542971, 'samples': 13172736, 'steps': 25727, 'loss/train': 1.7525347471237183}
-03/04/2022 19:41:42 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 19:41:45 - INFO - codeparrot_training - Step 25728: {'lr': 0.00046895384222316375, 'samples': 13173248, 'steps': 25728, 'loss/train': 1.9723695516586304}
-03/04/2022 19:41:48 - INFO - codeparrot_training - Step 25729: {'lr': 0.0004689512808933731, 'samples': 13173760, 'steps': 25729, 'loss/train': 2.0829074382781982}
-03/04/2022 19:41:50 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 19:41:54 - INFO - codeparrot_training - Step 25730: {'lr': 0.0004689487194649265, 'samples': 13174272, 'steps': 25730, 'loss/train': 1.7009503841400146}
-03/04/2022 19:41:57 - INFO - codeparrot_training - Step 25731: {'lr': 0.0004689461579378249, 'samples': 13174784, 'steps': 25731, 'loss/train': 1.3001179695129395}
-03/04/2022 19:41:59 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/04/2022 19:42:02 - INFO - codeparrot_training - Step 25732: {'lr': 0.0004689435963120696, 'samples': 13175296, 'steps': 25732, 'loss/train': 1.304050087928772}
-03/04/2022 19:42:05 - INFO - codeparrot_training - Step 25733: {'lr': 0.00046894103458766163, 'samples': 13175808, 'steps': 25733, 'loss/train': 0.9679852724075317}
-03/04/2022 19:42:08 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/04/2022 19:42:11 - INFO - codeparrot_training - Step 25734: {'lr': 0.0004689384727646022, 'samples': 13176320, 'steps': 25734, 'loss/train': 1.7003874778747559}
-03/04/2022 19:42:14 - INFO - codeparrot_training - Step 25735: {'lr': 0.00046893591084289256, 'samples': 13176832, 'steps': 25735, 'loss/train': 1.4563628435134888}
-03/04/2022 19:42:16 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/04/2022 19:42:19 - INFO - codeparrot_training - Step 25736: {'lr': 0.0004689333488225337, 'samples': 13177344, 'steps': 25736, 'loss/train': 2.0191643238067627}
-03/04/2022 19:42:22 - INFO - codeparrot_training - Step 25737: {'lr': 0.00046893078670352686, 'samples': 13177856, 'steps': 25737, 'loss/train': 1.7665600776672363}
-03/04/2022 19:42:24 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/04/2022 19:42:27 - INFO - codeparrot_training - Step 25738: {'lr': 0.0004689282244858732, 'samples': 13178368, 'steps': 25738, 'loss/train': 2.5812454223632812}
-03/04/2022 19:42:31 - INFO - codeparrot_training - Step 25739: {'lr': 0.00046892566216957387, 'samples': 13178880, 'steps': 25739, 'loss/train': 1.050881028175354}
-03/04/2022 19:42:33 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/04/2022 19:42:36 - INFO - codeparrot_training - Step 25740: {'lr': 0.00046892309975463, 'samples': 13179392, 'steps': 25740, 'loss/train': 2.2541086673736572}
-03/04/2022 19:42:39 - INFO - codeparrot_training - Step 25741: {'lr': 0.0004689205372410427, 'samples': 13179904, 'steps': 25741, 'loss/train': 1.3961035013198853}
-03/04/2022 19:42:42 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/04/2022 19:42:44 - INFO - codeparrot_training - Step 25742: {'lr': 0.00046891797462881327, 'samples': 13180416, 'steps': 25742, 'loss/train': 2.1329171657562256}
-03/04/2022 19:42:48 - INFO - codeparrot_training - Step 25743: {'lr': 0.0004689154119179427, 'samples': 13180928, 'steps': 25743, 'loss/train': 2.0172040462493896}
-03/04/2022 19:42:50 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/04/2022 19:42:53 - INFO - codeparrot_training - Step 25744: {'lr': 0.00046891284910843237, 'samples': 13181440, 'steps': 25744, 'loss/train': 1.993381381034851}
-03/04/2022 19:42:56 - INFO - codeparrot_training - Step 25745: {'lr': 0.0004689102862002832, 'samples': 13181952, 'steps': 25745, 'loss/train': 2.4731855392456055}
-03/04/2022 19:42:58 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/04/2022 19:43:01 - INFO - codeparrot_training - Step 25746: {'lr': 0.00046890772319349637, 'samples': 13182464, 'steps': 25746, 'loss/train': 2.4853122234344482}
-03/04/2022 19:43:05 - INFO - codeparrot_training - Step 25747: {'lr': 0.00046890516008807315, 'samples': 13182976, 'steps': 25747, 'loss/train': 1.6481667757034302}
-03/04/2022 19:43:08 - INFO - codeparrot_training - Step 25748: {'lr': 0.0004689025968840147, 'samples': 13183488, 'steps': 25748, 'loss/train': 2.0766830444335938}
-03/04/2022 19:43:08 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/04/2022 19:43:13 - INFO - codeparrot_training - Step 25749: {'lr': 0.00046890003358132204, 'samples': 13184000, 'steps': 25749, 'loss/train': 1.4666603803634644}
-03/04/2022 19:43:16 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/04/2022 19:43:18 - INFO - codeparrot_training - Step 25750: {'lr': 0.0004688974701799964, 'samples': 13184512, 'steps': 25750, 'loss/train': 1.6807059049606323}
-03/04/2022 19:43:22 - INFO - codeparrot_training - Step 25751: {'lr': 0.00046889490668003896, 'samples': 13185024, 'steps': 25751, 'loss/train': 1.9575626850128174}
-03/04/2022 19:43:25 - INFO - codeparrot_training - Step 25752: {'lr': 0.0004688923430814509, 'samples': 13185536, 'steps': 25752, 'loss/train': 6.606766700744629}
-03/04/2022 19:43:25 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/04/2022 19:43:30 - INFO - codeparrot_training - Step 25753: {'lr': 0.00046888977938423326, 'samples': 13186048, 'steps': 25753, 'loss/train': 1.017731785774231}
-03/04/2022 19:43:33 - INFO - codeparrot_training - Step 25754: {'lr': 0.00046888721558838734, 'samples': 13186560, 'steps': 25754, 'loss/train': 1.6070107221603394}
-03/04/2022 19:43:34 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/04/2022 19:43:38 - INFO - codeparrot_training - Step 25755: {'lr': 0.00046888465169391414, 'samples': 13187072, 'steps': 25755, 'loss/train': 1.8441321849822998}
-03/04/2022 19:43:42 - INFO - codeparrot_training - Step 25756: {'lr': 0.00046888208770081493, 'samples': 13187584, 'steps': 25756, 'loss/train': 1.8144243955612183}
-03/04/2022 19:43:42 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/04/2022 19:43:47 - INFO - codeparrot_training - Step 25757: {'lr': 0.0004688795236090908, 'samples': 13188096, 'steps': 25757, 'loss/train': 1.4829559326171875}
-03/04/2022 19:43:50 - INFO - codeparrot_training - Step 25758: {'lr': 0.000468876959418743, 'samples': 13188608, 'steps': 25758, 'loss/train': 1.6481634378433228}
-03/04/2022 19:43:50 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/04/2022 19:43:56 - INFO - codeparrot_training - Step 25759: {'lr': 0.0004688743951297726, 'samples': 13189120, 'steps': 25759, 'loss/train': 1.9870381355285645}
-03/04/2022 19:43:59 - INFO - codeparrot_training - Step 25760: {'lr': 0.0004688718307421807, 'samples': 13189632, 'steps': 25760, 'loss/train': 2.1658453941345215}
-03/04/2022 19:43:59 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 19:44:04 - INFO - codeparrot_training - Step 25761: {'lr': 0.0004688692662559686, 'samples': 13190144, 'steps': 25761, 'loss/train': 2.271631956100464}
-03/04/2022 19:44:07 - INFO - codeparrot_training - Step 25762: {'lr': 0.00046886670167113734, 'samples': 13190656, 'steps': 25762, 'loss/train': 1.7112658023834229}
-03/04/2022 19:44:08 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/04/2022 19:44:13 - INFO - codeparrot_training - Step 25763: {'lr': 0.00046886413698768816, 'samples': 13191168, 'steps': 25763, 'loss/train': 2.1874313354492188}
-03/04/2022 19:44:16 - INFO - codeparrot_training - Step 25764: {'lr': 0.0004688615722056222, 'samples': 13191680, 'steps': 25764, 'loss/train': 1.6382384300231934}
-03/04/2022 19:44:19 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 19:44:21 - INFO - codeparrot_training - Step 25765: {'lr': 0.00046885900732494053, 'samples': 13192192, 'steps': 25765, 'loss/train': 1.7944228649139404}
-03/04/2022 19:44:25 - INFO - codeparrot_training - Step 25766: {'lr': 0.0004688564423456444, 'samples': 13192704, 'steps': 25766, 'loss/train': 2.163855791091919}
-03/04/2022 19:44:27 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 19:44:30 - INFO - codeparrot_training - Step 25767: {'lr': 0.00046885387726773494, 'samples': 13193216, 'steps': 25767, 'loss/train': 2.276728391647339}
-03/04/2022 19:44:33 - INFO - codeparrot_training - Step 25768: {'lr': 0.0004688513120912133, 'samples': 13193728, 'steps': 25768, 'loss/train': 1.882814884185791}
-03/04/2022 19:44:36 - INFO - codeparrot_training - Step 25769: {'lr': 0.0004688487468160806, 'samples': 13194240, 'steps': 25769, 'loss/train': 2.0701003074645996}
-03/04/2022 19:44:36 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/04/2022 19:44:42 - INFO - codeparrot_training - Step 25770: {'lr': 0.000468846181442338, 'samples': 13194752, 'steps': 25770, 'loss/train': 2.5071463584899902}
-03/04/2022 19:44:45 - INFO - codeparrot_training - Step 25771: {'lr': 0.0004688436159699868, 'samples': 13195264, 'steps': 25771, 'loss/train': 2.086479663848877}
-03/04/2022 19:44:46 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/04/2022 19:44:50 - INFO - codeparrot_training - Step 25772: {'lr': 0.000468841050399028, 'samples': 13195776, 'steps': 25772, 'loss/train': 1.8353196382522583}
-03/04/2022 19:44:53 - INFO - codeparrot_training - Step 25773: {'lr': 0.0004688384847294628, 'samples': 13196288, 'steps': 25773, 'loss/train': 1.824231743812561}
-03/04/2022 19:44:54 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/04/2022 19:44:59 - INFO - codeparrot_training - Step 25774: {'lr': 0.0004688359189612923, 'samples': 13196800, 'steps': 25774, 'loss/train': 2.586979389190674}
-03/04/2022 19:45:02 - INFO - codeparrot_training - Step 25775: {'lr': 0.0004688333530945178, 'samples': 13197312, 'steps': 25775, 'loss/train': 2.59271502494812}
-03/04/2022 19:45:03 - INFO - codeparrot_training - Skipping example with length 385 (seq_length=1024)
-03/04/2022 19:45:07 - INFO - codeparrot_training - Step 25776: {'lr': 0.0004688307871291403, 'samples': 13197824, 'steps': 25776, 'loss/train': 1.7258427143096924}
-03/04/2022 19:45:10 - INFO - codeparrot_training - Step 25777: {'lr': 0.0004688282210651611, 'samples': 13198336, 'steps': 25777, 'loss/train': 1.5032305717468262}
-03/04/2022 19:45:11 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 19:45:16 - INFO - codeparrot_training - Step 25778: {'lr': 0.00046882565490258125, 'samples': 13198848, 'steps': 25778, 'loss/train': 1.2018293142318726}
-03/04/2022 19:45:19 - INFO - codeparrot_training - Step 25779: {'lr': 0.0004688230886414019, 'samples': 13199360, 'steps': 25779, 'loss/train': 1.6057734489440918}
-03/04/2022 19:45:20 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/04/2022 19:45:24 - INFO - codeparrot_training - Step 25780: {'lr': 0.0004688205222816242, 'samples': 13199872, 'steps': 25780, 'loss/train': 0.26883500814437866}
-03/04/2022 19:45:27 - INFO - codeparrot_training - Step 25781: {'lr': 0.00046881795582324944, 'samples': 13200384, 'steps': 25781, 'loss/train': 2.0397567749023438}
-03/04/2022 19:45:29 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/04/2022 19:45:33 - INFO - codeparrot_training - Step 25782: {'lr': 0.00046881538926627864, 'samples': 13200896, 'steps': 25782, 'loss/train': 0.980804443359375}
-03/04/2022 19:45:36 - INFO - codeparrot_training - Step 25783: {'lr': 0.000468812822610713, 'samples': 13201408, 'steps': 25783, 'loss/train': 1.9646778106689453}
-03/04/2022 19:45:37 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/04/2022 19:45:41 - INFO - codeparrot_training - Step 25784: {'lr': 0.00046881025585655367, 'samples': 13201920, 'steps': 25784, 'loss/train': 0.8479981422424316}
-03/04/2022 19:45:44 - INFO - codeparrot_training - Step 25785: {'lr': 0.0004688076890038019, 'samples': 13202432, 'steps': 25785, 'loss/train': 1.5140366554260254}
-03/04/2022 19:45:46 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 19:45:50 - INFO - codeparrot_training - Step 25786: {'lr': 0.00046880512205245867, 'samples': 13202944, 'steps': 25786, 'loss/train': 1.815520167350769}
-03/04/2022 19:45:53 - INFO - codeparrot_training - Step 25787: {'lr': 0.00046880255500252526, 'samples': 13203456, 'steps': 25787, 'loss/train': 1.4638351202011108}
-03/04/2022 19:45:54 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/04/2022 19:45:58 - INFO - codeparrot_training - Step 25788: {'lr': 0.0004687999878540028, 'samples': 13203968, 'steps': 25788, 'loss/train': 2.747626304626465}
-03/04/2022 19:46:01 - INFO - codeparrot_training - Step 25789: {'lr': 0.00046879742060689243, 'samples': 13204480, 'steps': 25789, 'loss/train': 0.11578322947025299}
-03/04/2022 19:46:02 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/04/2022 19:46:07 - INFO - codeparrot_training - Step 25790: {'lr': 0.0004687948532611953, 'samples': 13204992, 'steps': 25790, 'loss/train': 2.3247017860412598}
-03/04/2022 19:46:10 - INFO - codeparrot_training - Step 25791: {'lr': 0.0004687922858169126, 'samples': 13205504, 'steps': 25791, 'loss/train': 0.9731686115264893}
-03/04/2022 19:46:11 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/04/2022 19:46:15 - INFO - codeparrot_training - Step 25792: {'lr': 0.0004687897182740455, 'samples': 13206016, 'steps': 25792, 'loss/train': 1.597493290901184}
-03/04/2022 19:46:18 - INFO - codeparrot_training - Step 25793: {'lr': 0.0004687871506325951, 'samples': 13206528, 'steps': 25793, 'loss/train': 1.8939908742904663}
-03/04/2022 19:46:20 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 19:46:24 - INFO - codeparrot_training - Step 25794: {'lr': 0.00046878458289256264, 'samples': 13207040, 'steps': 25794, 'loss/train': 1.6569936275482178}
-03/04/2022 19:46:27 - INFO - codeparrot_training - Step 25795: {'lr': 0.00046878201505394913, 'samples': 13207552, 'steps': 25795, 'loss/train': 1.6879701614379883}
-03/04/2022 19:46:28 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 19:46:32 - INFO - codeparrot_training - Step 25796: {'lr': 0.0004687794471167559, 'samples': 13208064, 'steps': 25796, 'loss/train': 2.192411422729492}
-03/04/2022 19:46:35 - INFO - codeparrot_training - Step 25797: {'lr': 0.00046877687908098396, 'samples': 13208576, 'steps': 25797, 'loss/train': 1.340955376625061}
-03/04/2022 19:46:36 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/04/2022 19:46:40 - INFO - codeparrot_training - Step 25798: {'lr': 0.0004687743109466346, 'samples': 13209088, 'steps': 25798, 'loss/train': 2.3971335887908936}
-03/04/2022 19:46:44 - INFO - codeparrot_training - Step 25799: {'lr': 0.00046877174271370894, 'samples': 13209600, 'steps': 25799, 'loss/train': 1.605688452720642}
-03/04/2022 19:46:45 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/04/2022 19:46:49 - INFO - codeparrot_training - Step 25800: {'lr': 0.000468769174382208, 'samples': 13210112, 'steps': 25800, 'loss/train': 1.1746312379837036}
-03/04/2022 19:46:52 - INFO - codeparrot_training - Step 25801: {'lr': 0.0004687666059521331, 'samples': 13210624, 'steps': 25801, 'loss/train': 2.1345129013061523}
-03/04/2022 19:46:53 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 19:46:57 - INFO - codeparrot_training - Step 25802: {'lr': 0.0004687640374234854, 'samples': 13211136, 'steps': 25802, 'loss/train': 1.4977260828018188}
-03/04/2022 19:47:00 - INFO - codeparrot_training - Step 25803: {'lr': 0.0004687614687962659, 'samples': 13211648, 'steps': 25803, 'loss/train': 1.2754597663879395}
-03/04/2022 19:47:01 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 19:47:06 - INFO - codeparrot_training - Step 25804: {'lr': 0.0004687589000704759, 'samples': 13212160, 'steps': 25804, 'loss/train': 2.2735788822174072}
-03/04/2022 19:47:09 - INFO - codeparrot_training - Step 25805: {'lr': 0.0004687563312461165, 'samples': 13212672, 'steps': 25805, 'loss/train': 2.396667242050171}
-03/04/2022 19:47:10 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/04/2022 19:47:14 - INFO - codeparrot_training - Step 25806: {'lr': 0.00046875376232318887, 'samples': 13213184, 'steps': 25806, 'loss/train': 1.6642447710037231}
-03/04/2022 19:47:17 - INFO - codeparrot_training - Step 25807: {'lr': 0.00046875119330169426, 'samples': 13213696, 'steps': 25807, 'loss/train': 1.6901277303695679}
-03/04/2022 19:47:19 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/04/2022 19:47:23 - INFO - codeparrot_training - Step 25808: {'lr': 0.00046874862418163363, 'samples': 13214208, 'steps': 25808, 'loss/train': 1.4000072479248047}
-03/04/2022 19:47:26 - INFO - codeparrot_training - Step 25809: {'lr': 0.00046874605496300824, 'samples': 13214720, 'steps': 25809, 'loss/train': 1.4770371913909912}
-03/04/2022 19:47:27 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 19:47:31 - INFO - codeparrot_training - Step 25810: {'lr': 0.00046874348564581933, 'samples': 13215232, 'steps': 25810, 'loss/train': 1.1583110094070435}
-03/04/2022 19:47:34 - INFO - codeparrot_training - Step 25811: {'lr': 0.00046874091623006793, 'samples': 13215744, 'steps': 25811, 'loss/train': 1.7334119081497192}
-03/04/2022 19:47:36 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 19:47:39 - INFO - codeparrot_training - Step 25812: {'lr': 0.0004687383467157553, 'samples': 13216256, 'steps': 25812, 'loss/train': 2.045461416244507}
-03/04/2022 19:47:43 - INFO - codeparrot_training - Step 25813: {'lr': 0.0004687357771028825, 'samples': 13216768, 'steps': 25813, 'loss/train': 1.922663927078247}
-03/04/2022 19:47:44 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/04/2022 19:47:48 - INFO - codeparrot_training - Step 25814: {'lr': 0.00046873320739145073, 'samples': 13217280, 'steps': 25814, 'loss/train': 0.6600019335746765}
-03/04/2022 19:47:51 - INFO - codeparrot_training - Step 25815: {'lr': 0.0004687306375814612, 'samples': 13217792, 'steps': 25815, 'loss/train': 1.7463972568511963}
-03/04/2022 19:47:52 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/04/2022 19:47:56 - INFO - codeparrot_training - Step 25816: {'lr': 0.000468728067672915, 'samples': 13218304, 'steps': 25816, 'loss/train': 1.9042831659317017}
-03/04/2022 19:48:00 - INFO - codeparrot_training - Step 25817: {'lr': 0.00046872549766581326, 'samples': 13218816, 'steps': 25817, 'loss/train': 2.002692937850952}
-03/04/2022 19:48:01 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/04/2022 19:48:05 - INFO - codeparrot_training - Step 25818: {'lr': 0.00046872292756015724, 'samples': 13219328, 'steps': 25818, 'loss/train': 2.0099923610687256}
-03/04/2022 19:48:08 - INFO - codeparrot_training - Step 25819: {'lr': 0.000468720357355948, 'samples': 13219840, 'steps': 25819, 'loss/train': 0.819439709186554}
-03/04/2022 19:48:09 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/04/2022 19:48:13 - INFO - codeparrot_training - Step 25820: {'lr': 0.00046871778705318673, 'samples': 13220352, 'steps': 25820, 'loss/train': 1.730955719947815}
-03/04/2022 19:48:16 - INFO - codeparrot_training - Step 25821: {'lr': 0.0004687152166518747, 'samples': 13220864, 'steps': 25821, 'loss/train': 1.5430030822753906}
-03/04/2022 19:48:18 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/04/2022 19:48:22 - INFO - codeparrot_training - Step 25822: {'lr': 0.0004687126461520128, 'samples': 13221376, 'steps': 25822, 'loss/train': 1.933743953704834}
-03/04/2022 19:48:25 - INFO - codeparrot_training - Step 25823: {'lr': 0.0004687100755536025, 'samples': 13221888, 'steps': 25823, 'loss/train': 1.3258787393569946}
-03/04/2022 19:48:26 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/04/2022 19:48:30 - INFO - codeparrot_training - Step 25824: {'lr': 0.00046870750485664484, 'samples': 13222400, 'steps': 25824, 'loss/train': 1.5260109901428223}
-03/04/2022 19:48:34 - INFO - codeparrot_training - Step 25825: {'lr': 0.00046870493406114084, 'samples': 13222912, 'steps': 25825, 'loss/train': 2.4076874256134033}
-03/04/2022 19:48:34 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/04/2022 19:48:39 - INFO - codeparrot_training - Step 25826: {'lr': 0.0004687023631670918, 'samples': 13223424, 'steps': 25826, 'loss/train': 1.7408114671707153}
-03/04/2022 19:48:42 - INFO - codeparrot_training - Step 25827: {'lr': 0.0004686997921744989, 'samples': 13223936, 'steps': 25827, 'loss/train': 1.4906857013702393}
-03/04/2022 19:48:43 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 19:48:47 - INFO - codeparrot_training - Step 25828: {'lr': 0.0004686972210833632, 'samples': 13224448, 'steps': 25828, 'loss/train': 1.7101078033447266}
-03/04/2022 19:48:50 - INFO - codeparrot_training - Step 25829: {'lr': 0.0004686946498936859, 'samples': 13224960, 'steps': 25829, 'loss/train': 1.2496514320373535}
-03/04/2022 19:48:51 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 19:48:56 - INFO - codeparrot_training - Step 25830: {'lr': 0.00046869207860546826, 'samples': 13225472, 'steps': 25830, 'loss/train': 1.8885293006896973}
-03/04/2022 19:48:59 - INFO - codeparrot_training - Step 25831: {'lr': 0.00046868950721871126, 'samples': 13225984, 'steps': 25831, 'loss/train': 1.4806569814682007}
-03/04/2022 19:48:59 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/04/2022 19:49:04 - INFO - codeparrot_training - Step 25832: {'lr': 0.00046868693573341616, 'samples': 13226496, 'steps': 25832, 'loss/train': 1.8638274669647217}
-03/04/2022 19:49:07 - INFO - codeparrot_training - Step 25833: {'lr': 0.00046868436414958405, 'samples': 13227008, 'steps': 25833, 'loss/train': 2.0784008502960205}
-03/04/2022 19:49:08 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/04/2022 19:49:12 - INFO - codeparrot_training - Step 25834: {'lr': 0.00046868179246721623, 'samples': 13227520, 'steps': 25834, 'loss/train': 1.7019493579864502}
-03/04/2022 19:49:15 - INFO - codeparrot_training - Step 25835: {'lr': 0.00046867922068631374, 'samples': 13228032, 'steps': 25835, 'loss/train': 2.199866533279419}
-03/04/2022 19:49:16 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 19:49:21 - INFO - codeparrot_training - Step 25836: {'lr': 0.00046867664880687775, 'samples': 13228544, 'steps': 25836, 'loss/train': 2.098139762878418}
-03/04/2022 19:49:24 - INFO - codeparrot_training - Step 25837: {'lr': 0.00046867407682890937, 'samples': 13229056, 'steps': 25837, 'loss/train': 1.9209764003753662}
-03/04/2022 19:49:25 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/04/2022 19:49:29 - INFO - codeparrot_training - Step 25838: {'lr': 0.00046867150475240994, 'samples': 13229568, 'steps': 25838, 'loss/train': 1.697674036026001}
-03/04/2022 19:49:32 - INFO - codeparrot_training - Step 25839: {'lr': 0.0004686689325773805, 'samples': 13230080, 'steps': 25839, 'loss/train': 1.5586429834365845}
-03/04/2022 19:49:33 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 19:49:38 - INFO - codeparrot_training - Step 25840: {'lr': 0.00046866636030382217, 'samples': 13230592, 'steps': 25840, 'loss/train': 1.5807653665542603}
-03/04/2022 19:49:41 - INFO - codeparrot_training - Step 25841: {'lr': 0.00046866378793173616, 'samples': 13231104, 'steps': 25841, 'loss/train': 1.206275224685669}
-03/04/2022 19:49:42 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 19:49:46 - INFO - codeparrot_training - Step 25842: {'lr': 0.0004686612154611236, 'samples': 13231616, 'steps': 25842, 'loss/train': 1.5061042308807373}
-03/04/2022 19:49:49 - INFO - codeparrot_training - Step 25843: {'lr': 0.0004686586428919857, 'samples': 13232128, 'steps': 25843, 'loss/train': 1.8210333585739136}
-03/04/2022 19:49:51 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/04/2022 19:49:55 - INFO - codeparrot_training - Step 25844: {'lr': 0.00046865607022432356, 'samples': 13232640, 'steps': 25844, 'loss/train': 2.423743724822998}
-03/04/2022 19:49:58 - INFO - codeparrot_training - Step 25845: {'lr': 0.00046865349745813835, 'samples': 13233152, 'steps': 25845, 'loss/train': 1.5761553049087524}
-03/04/2022 19:49:59 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/04/2022 19:50:03 - INFO - codeparrot_training - Step 25846: {'lr': 0.00046865092459343126, 'samples': 13233664, 'steps': 25846, 'loss/train': 1.4360899925231934}
-03/04/2022 19:50:06 - INFO - codeparrot_training - Step 25847: {'lr': 0.00046864835163020353, 'samples': 13234176, 'steps': 25847, 'loss/train': 1.5536714792251587}
-03/04/2022 19:50:08 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/04/2022 19:50:12 - INFO - codeparrot_training - Step 25848: {'lr': 0.00046864577856845613, 'samples': 13234688, 'steps': 25848, 'loss/train': 1.4378796815872192}
-03/04/2022 19:50:15 - INFO - codeparrot_training - Step 25849: {'lr': 0.0004686432054081904, 'samples': 13235200, 'steps': 25849, 'loss/train': 1.5790094137191772}
-03/04/2022 19:50:16 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/04/2022 19:50:20 - INFO - codeparrot_training - Step 25850: {'lr': 0.00046864063214940735, 'samples': 13235712, 'steps': 25850, 'loss/train': 1.5388582944869995}
-03/04/2022 19:50:23 - INFO - codeparrot_training - Step 25851: {'lr': 0.0004686380587921082, 'samples': 13236224, 'steps': 25851, 'loss/train': 1.8229191303253174}
-03/04/2022 19:50:24 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/04/2022 19:50:28 - INFO - codeparrot_training - Step 25852: {'lr': 0.00046863548533629406, 'samples': 13236736, 'steps': 25852, 'loss/train': 1.728854775428772}
-03/04/2022 19:50:32 - INFO - codeparrot_training - Step 25853: {'lr': 0.00046863291178196625, 'samples': 13237248, 'steps': 25853, 'loss/train': 1.4876281023025513}
-03/04/2022 19:50:32 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/04/2022 19:50:37 - INFO - codeparrot_training - Step 25854: {'lr': 0.0004686303381291258, 'samples': 13237760, 'steps': 25854, 'loss/train': 1.4468914270401}
-03/04/2022 19:50:40 - INFO - codeparrot_training - Step 25855: {'lr': 0.00046862776437777386, 'samples': 13238272, 'steps': 25855, 'loss/train': 1.7548192739486694}
-03/04/2022 19:50:41 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 19:50:45 - INFO - codeparrot_training - Step 25856: {'lr': 0.00046862519052791166, 'samples': 13238784, 'steps': 25856, 'loss/train': 1.580428957939148}
-03/04/2022 19:50:49 - INFO - codeparrot_training - Step 25857: {'lr': 0.00046862261657954033, 'samples': 13239296, 'steps': 25857, 'loss/train': 0.580955982208252}
-03/04/2022 19:50:50 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/04/2022 19:50:54 - INFO - codeparrot_training - Step 25858: {'lr': 0.000468620042532661, 'samples': 13239808, 'steps': 25858, 'loss/train': 2.3391287326812744}
-03/04/2022 19:50:57 - INFO - codeparrot_training - Step 25859: {'lr': 0.0004686174683872748, 'samples': 13240320, 'steps': 25859, 'loss/train': 1.8355076313018799}
-03/04/2022 19:50:58 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/04/2022 19:51:02 - INFO - codeparrot_training - Step 25860: {'lr': 0.00046861489414338304, 'samples': 13240832, 'steps': 25860, 'loss/train': 1.988729476928711}
-03/04/2022 19:51:06 - INFO - codeparrot_training - Step 25861: {'lr': 0.0004686123198009867, 'samples': 13241344, 'steps': 25861, 'loss/train': 2.1283059120178223}
-03/04/2022 19:51:06 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/04/2022 19:51:11 - INFO - codeparrot_training - Step 25862: {'lr': 0.00046860974536008706, 'samples': 13241856, 'steps': 25862, 'loss/train': 1.9020934104919434}
-03/04/2022 19:51:14 - INFO - codeparrot_training - Step 25863: {'lr': 0.0004686071708206853, 'samples': 13242368, 'steps': 25863, 'loss/train': 2.4686341285705566}
-03/04/2022 19:51:15 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/04/2022 19:51:19 - INFO - codeparrot_training - Step 25864: {'lr': 0.0004686045961827824, 'samples': 13242880, 'steps': 25864, 'loss/train': 1.9187458753585815}
-03/04/2022 19:51:22 - INFO - codeparrot_training - Step 25865: {'lr': 0.00046860202144637976, 'samples': 13243392, 'steps': 25865, 'loss/train': 1.670817494392395}
-03/04/2022 19:51:23 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/04/2022 19:51:28 - INFO - codeparrot_training - Step 25866: {'lr': 0.00046859944661147837, 'samples': 13243904, 'steps': 25866, 'loss/train': 2.1109752655029297}
-03/04/2022 19:51:31 - INFO - codeparrot_training - Step 25867: {'lr': 0.00046859687167807943, 'samples': 13244416, 'steps': 25867, 'loss/train': 1.5801206827163696}
-03/04/2022 19:51:34 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 19:51:37 - INFO - codeparrot_training - Step 25868: {'lr': 0.0004685942966461841, 'samples': 13244928, 'steps': 25868, 'loss/train': 1.6933605670928955}
-03/04/2022 19:51:40 - INFO - codeparrot_training - Step 25869: {'lr': 0.00046859172151579354, 'samples': 13245440, 'steps': 25869, 'loss/train': 2.3044238090515137}
-03/04/2022 19:51:43 - INFO - codeparrot_training - Step 25870: {'lr': 0.00046858914628690896, 'samples': 13245952, 'steps': 25870, 'loss/train': 0.3217429220676422}
-03/04/2022 19:51:43 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 19:51:48 - INFO - codeparrot_training - Step 25871: {'lr': 0.0004685865709595315, 'samples': 13246464, 'steps': 25871, 'loss/train': 1.3033314943313599}
-03/04/2022 19:51:52 - INFO - codeparrot_training - Step 25872: {'lr': 0.00046858399553366224, 'samples': 13246976, 'steps': 25872, 'loss/train': 1.4432501792907715}
-03/04/2022 19:51:52 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/04/2022 19:51:57 - INFO - codeparrot_training - Step 25873: {'lr': 0.0004685814200093025, 'samples': 13247488, 'steps': 25873, 'loss/train': 1.7649273872375488}
-03/04/2022 19:52:00 - INFO - codeparrot_training - Step 25874: {'lr': 0.00046857884438645327, 'samples': 13248000, 'steps': 25874, 'loss/train': 1.8365867137908936}
-03/04/2022 19:52:00 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 19:52:05 - INFO - codeparrot_training - Step 25875: {'lr': 0.0004685762686651158, 'samples': 13248512, 'steps': 25875, 'loss/train': 0.6330443024635315}
-03/04/2022 19:52:08 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/04/2022 19:52:11 - INFO - codeparrot_training - Step 25876: {'lr': 0.0004685736928452913, 'samples': 13249024, 'steps': 25876, 'loss/train': 1.733134150505066}
-03/04/2022 19:52:14 - INFO - codeparrot_training - Step 25877: {'lr': 0.00046857111692698083, 'samples': 13249536, 'steps': 25877, 'loss/train': 1.5421223640441895}
-03/04/2022 19:52:17 - INFO - codeparrot_training - Step 25878: {'lr': 0.0004685685409101855, 'samples': 13250048, 'steps': 25878, 'loss/train': 1.3682268857955933}
-03/04/2022 19:52:17 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/04/2022 19:52:22 - INFO - codeparrot_training - Step 25879: {'lr': 0.00046856596479490667, 'samples': 13250560, 'steps': 25879, 'loss/train': 1.7628313302993774}
-03/04/2022 19:52:26 - INFO - codeparrot_training - Step 25880: {'lr': 0.0004685633885811453, 'samples': 13251072, 'steps': 25880, 'loss/train': 1.2176059484481812}
-03/04/2022 19:52:26 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/04/2022 19:52:31 - INFO - codeparrot_training - Step 25881: {'lr': 0.0004685608122689027, 'samples': 13251584, 'steps': 25881, 'loss/train': 1.5149364471435547}
-03/04/2022 19:52:34 - INFO - codeparrot_training - Step 25882: {'lr': 0.00046855823585818004, 'samples': 13252096, 'steps': 25882, 'loss/train': 0.4379826486110687}
-03/04/2022 19:52:34 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 19:52:39 - INFO - codeparrot_training - Step 25883: {'lr': 0.0004685556593489783, 'samples': 13252608, 'steps': 25883, 'loss/train': 1.1206492185592651}
-03/04/2022 19:52:42 - INFO - codeparrot_training - Step 25884: {'lr': 0.0004685530827412988, 'samples': 13253120, 'steps': 25884, 'loss/train': 1.8788888454437256}
-03/04/2022 19:52:43 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/04/2022 19:52:48 - INFO - codeparrot_training - Step 25885: {'lr': 0.0004685505060351426, 'samples': 13253632, 'steps': 25885, 'loss/train': 1.9359797239303589}
-03/04/2022 19:52:51 - INFO - codeparrot_training - Step 25886: {'lr': 0.00046854792923051094, 'samples': 13254144, 'steps': 25886, 'loss/train': 1.5377318859100342}
-03/04/2022 19:52:51 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/04/2022 19:52:56 - INFO - codeparrot_training - Step 25887: {'lr': 0.00046854535232740505, 'samples': 13254656, 'steps': 25887, 'loss/train': 1.8176591396331787}
-03/04/2022 19:52:59 - INFO - codeparrot_training - Step 25888: {'lr': 0.00046854277532582585, 'samples': 13255168, 'steps': 25888, 'loss/train': 1.9865645170211792}
-03/04/2022 19:52:59 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/04/2022 19:53:05 - INFO - codeparrot_training - Step 25889: {'lr': 0.0004685401982257747, 'samples': 13255680, 'steps': 25889, 'loss/train': 1.9261173009872437}
-03/04/2022 19:53:08 - INFO - codeparrot_training - Step 25890: {'lr': 0.0004685376210272527, 'samples': 13256192, 'steps': 25890, 'loss/train': 1.6129933595657349}
-03/04/2022 19:53:08 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/04/2022 19:53:14 - INFO - codeparrot_training - Step 25891: {'lr': 0.00046853504373026107, 'samples': 13256704, 'steps': 25891, 'loss/train': 2.1686131954193115}
-03/04/2022 19:53:17 - INFO - codeparrot_training - Step 25892: {'lr': 0.00046853246633480087, 'samples': 13257216, 'steps': 25892, 'loss/train': 2.083625078201294}
-03/04/2022 19:53:19 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 19:53:22 - INFO - codeparrot_training - Step 25893: {'lr': 0.0004685298888408733, 'samples': 13257728, 'steps': 25893, 'loss/train': 2.0017762184143066}
-03/04/2022 19:53:25 - INFO - codeparrot_training - Step 25894: {'lr': 0.0004685273112484796, 'samples': 13258240, 'steps': 25894, 'loss/train': 1.5308396816253662}
-03/04/2022 19:53:27 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/04/2022 19:53:31 - INFO - codeparrot_training - Step 25895: {'lr': 0.0004685247335576209, 'samples': 13258752, 'steps': 25895, 'loss/train': 2.1260509490966797}
-03/04/2022 19:53:34 - INFO - codeparrot_training - Step 25896: {'lr': 0.00046852215576829824, 'samples': 13259264, 'steps': 25896, 'loss/train': 1.7930532693862915}
-03/04/2022 19:53:36 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 19:53:39 - INFO - codeparrot_training - Step 25897: {'lr': 0.0004685195778805129, 'samples': 13259776, 'steps': 25897, 'loss/train': 1.9097622632980347}
-03/04/2022 19:53:42 - INFO - codeparrot_training - Step 25898: {'lr': 0.000468516999894266, 'samples': 13260288, 'steps': 25898, 'loss/train': 2.222501754760742}
-03/04/2022 19:53:44 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/04/2022 19:53:48 - INFO - codeparrot_training - Step 25899: {'lr': 0.0004685144218095587, 'samples': 13260800, 'steps': 25899, 'loss/train': 1.7289777994155884}
-03/04/2022 19:53:51 - INFO - codeparrot_training - Step 25900: {'lr': 0.00046851184362639223, 'samples': 13261312, 'steps': 25900, 'loss/train': 1.6573745012283325}
-03/04/2022 19:53:53 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 19:53:56 - INFO - codeparrot_training - Step 25901: {'lr': 0.0004685092653447676, 'samples': 13261824, 'steps': 25901, 'loss/train': 1.396908164024353}
-03/04/2022 19:53:59 - INFO - codeparrot_training - Step 25902: {'lr': 0.00046850668696468614, 'samples': 13262336, 'steps': 25902, 'loss/train': 1.5410982370376587}
-03/04/2022 19:54:01 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/04/2022 19:54:05 - INFO - codeparrot_training - Step 25903: {'lr': 0.0004685041084861489, 'samples': 13262848, 'steps': 25903, 'loss/train': 1.790032148361206}
-03/04/2022 19:54:08 - INFO - codeparrot_training - Step 25904: {'lr': 0.00046850152990915705, 'samples': 13263360, 'steps': 25904, 'loss/train': 2.288675308227539}
-03/04/2022 19:54:09 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 19:54:13 - INFO - codeparrot_training - Step 25905: {'lr': 0.0004684989512337119, 'samples': 13263872, 'steps': 25905, 'loss/train': 1.39580500125885}
-03/04/2022 19:54:16 - INFO - codeparrot_training - Step 25906: {'lr': 0.00046849637245981434, 'samples': 13264384, 'steps': 25906, 'loss/train': 1.4886870384216309}
-03/04/2022 19:54:18 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 19:54:21 - INFO - codeparrot_training - Step 25907: {'lr': 0.0004684937935874658, 'samples': 13264896, 'steps': 25907, 'loss/train': 2.217146396636963}
-03/04/2022 19:54:25 - INFO - codeparrot_training - Step 25908: {'lr': 0.00046849121461666734, 'samples': 13265408, 'steps': 25908, 'loss/train': 1.1402108669281006}
-03/04/2022 19:54:26 - INFO - codeparrot_training - Skipping example with length 822 (seq_length=1024)
-03/04/2022 19:54:30 - INFO - codeparrot_training - Step 25909: {'lr': 0.00046848863554742006, 'samples': 13265920, 'steps': 25909, 'loss/train': 2.503039836883545}
-03/04/2022 19:54:33 - INFO - codeparrot_training - Step 25910: {'lr': 0.0004684860563797252, 'samples': 13266432, 'steps': 25910, 'loss/train': 2.386862277984619}
-03/04/2022 19:54:34 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 19:54:38 - INFO - codeparrot_training - Step 25911: {'lr': 0.00046848347711358384, 'samples': 13266944, 'steps': 25911, 'loss/train': 1.451749324798584}
-03/04/2022 19:54:41 - INFO - codeparrot_training - Step 25912: {'lr': 0.0004684808977489973, 'samples': 13267456, 'steps': 25912, 'loss/train': 2.6808433532714844}
-03/04/2022 19:54:43 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/04/2022 19:54:47 - INFO - codeparrot_training - Step 25913: {'lr': 0.00046847831828596647, 'samples': 13267968, 'steps': 25913, 'loss/train': 1.3301246166229248}
-03/04/2022 19:54:50 - INFO - codeparrot_training - Step 25914: {'lr': 0.0004684757387244928, 'samples': 13268480, 'steps': 25914, 'loss/train': 1.0148881673812866}
-03/04/2022 19:54:51 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 19:54:55 - INFO - codeparrot_training - Step 25915: {'lr': 0.00046847315906457733, 'samples': 13268992, 'steps': 25915, 'loss/train': 2.179424524307251}
-03/04/2022 19:54:58 - INFO - codeparrot_training - Step 25916: {'lr': 0.0004684705793062212, 'samples': 13269504, 'steps': 25916, 'loss/train': 1.5378541946411133}
-03/04/2022 19:55:00 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/04/2022 19:55:04 - INFO - codeparrot_training - Step 25917: {'lr': 0.00046846799944942564, 'samples': 13270016, 'steps': 25917, 'loss/train': 1.903385043144226}
-03/04/2022 19:55:07 - INFO - codeparrot_training - Step 25918: {'lr': 0.00046846541949419177, 'samples': 13270528, 'steps': 25918, 'loss/train': 2.0768959522247314}
-03/04/2022 19:55:08 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 19:55:12 - INFO - codeparrot_training - Step 25919: {'lr': 0.00046846283944052073, 'samples': 13271040, 'steps': 25919, 'loss/train': 2.4806063175201416}
-03/04/2022 19:55:15 - INFO - codeparrot_training - Step 25920: {'lr': 0.0004684602592884136, 'samples': 13271552, 'steps': 25920, 'loss/train': 2.472268581390381}
-03/04/2022 19:55:17 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 19:55:21 - INFO - codeparrot_training - Step 25921: {'lr': 0.0004684576790378718, 'samples': 13272064, 'steps': 25921, 'loss/train': 2.091535806655884}
-03/04/2022 19:55:24 - INFO - codeparrot_training - Step 25922: {'lr': 0.00046845509868889625, 'samples': 13272576, 'steps': 25922, 'loss/train': 0.7834211587905884}
-03/04/2022 19:55:25 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 19:55:29 - INFO - codeparrot_training - Step 25923: {'lr': 0.00046845251824148825, 'samples': 13273088, 'steps': 25923, 'loss/train': 1.7245408296585083}
-03/04/2022 19:55:32 - INFO - codeparrot_training - Step 25924: {'lr': 0.0004684499376956489, 'samples': 13273600, 'steps': 25924, 'loss/train': 1.3210349082946777}
-03/04/2022 19:55:34 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/04/2022 19:55:38 - INFO - codeparrot_training - Step 25925: {'lr': 0.00046844735705137944, 'samples': 13274112, 'steps': 25925, 'loss/train': 1.2078791856765747}
-03/04/2022 19:55:41 - INFO - codeparrot_training - Step 25926: {'lr': 0.0004684447763086809, 'samples': 13274624, 'steps': 25926, 'loss/train': 1.9099268913269043}
-03/04/2022 19:55:42 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 19:55:46 - INFO - codeparrot_training - Step 25927: {'lr': 0.00046844219546755454, 'samples': 13275136, 'steps': 25927, 'loss/train': 1.9665889739990234}
-03/04/2022 19:55:49 - INFO - codeparrot_training - Step 25928: {'lr': 0.0004684396145280014, 'samples': 13275648, 'steps': 25928, 'loss/train': 1.132936716079712}
-03/04/2022 19:55:51 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/04/2022 19:55:55 - INFO - codeparrot_training - Step 25929: {'lr': 0.00046843703349002286, 'samples': 13276160, 'steps': 25929, 'loss/train': 1.3434978723526}
-03/04/2022 19:55:58 - INFO - codeparrot_training - Step 25930: {'lr': 0.00046843445235361994, 'samples': 13276672, 'steps': 25930, 'loss/train': 1.3434816598892212}
-03/04/2022 19:55:59 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 19:56:03 - INFO - codeparrot_training - Step 25931: {'lr': 0.0004684318711187938, 'samples': 13277184, 'steps': 25931, 'loss/train': 1.2936205863952637}
-03/04/2022 19:56:06 - INFO - codeparrot_training - Step 25932: {'lr': 0.0004684292897855457, 'samples': 13277696, 'steps': 25932, 'loss/train': 0.7396809458732605}
-03/04/2022 19:56:07 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 19:56:12 - INFO - codeparrot_training - Step 25933: {'lr': 0.00046842670835387667, 'samples': 13278208, 'steps': 25933, 'loss/train': 2.231295585632324}
-03/04/2022 19:56:15 - INFO - codeparrot_training - Step 25934: {'lr': 0.00046842412682378796, 'samples': 13278720, 'steps': 25934, 'loss/train': 2.269412040710449}
-03/04/2022 19:56:16 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/04/2022 19:56:20 - INFO - codeparrot_training - Step 25935: {'lr': 0.0004684215451952807, 'samples': 13279232, 'steps': 25935, 'loss/train': 2.0541248321533203}
-03/04/2022 19:56:23 - INFO - codeparrot_training - Step 25936: {'lr': 0.000468418963468356, 'samples': 13279744, 'steps': 25936, 'loss/train': 2.3254141807556152}
-03/04/2022 19:56:25 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/04/2022 19:56:29 - INFO - codeparrot_training - Step 25937: {'lr': 0.0004684163816430152, 'samples': 13280256, 'steps': 25937, 'loss/train': 1.1571645736694336}
-03/04/2022 19:56:32 - INFO - codeparrot_training - Step 25938: {'lr': 0.00046841379971925923, 'samples': 13280768, 'steps': 25938, 'loss/train': 1.0219831466674805}
-03/04/2022 19:56:33 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/04/2022 19:56:37 - INFO - codeparrot_training - Step 25939: {'lr': 0.0004684112176970895, 'samples': 13281280, 'steps': 25939, 'loss/train': 1.697920560836792}
-03/04/2022 19:56:40 - INFO - codeparrot_training - Step 25940: {'lr': 0.0004684086355765069, 'samples': 13281792, 'steps': 25940, 'loss/train': 1.6999151706695557}
-03/04/2022 19:56:42 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/04/2022 19:56:45 - INFO - codeparrot_training - Step 25941: {'lr': 0.00046840605335751284, 'samples': 13282304, 'steps': 25941, 'loss/train': 1.7646182775497437}
-03/04/2022 19:56:49 - INFO - codeparrot_training - Step 25942: {'lr': 0.0004684034710401084, 'samples': 13282816, 'steps': 25942, 'loss/train': 1.4748141765594482}
-03/04/2022 19:56:50 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 19:56:54 - INFO - codeparrot_training - Step 25943: {'lr': 0.00046840088862429465, 'samples': 13283328, 'steps': 25943, 'loss/train': 2.6214559078216553}
-03/04/2022 19:56:57 - INFO - codeparrot_training - Step 25944: {'lr': 0.00046839830611007297, 'samples': 13283840, 'steps': 25944, 'loss/train': 1.9332501888275146}
-03/04/2022 19:57:00 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/04/2022 19:57:03 - INFO - codeparrot_training - Step 25945: {'lr': 0.00046839572349744417, 'samples': 13284352, 'steps': 25945, 'loss/train': 1.9477851390838623}
-03/04/2022 19:57:06 - INFO - codeparrot_training - Step 25946: {'lr': 0.0004683931407864098, 'samples': 13284864, 'steps': 25946, 'loss/train': 1.5146911144256592}
-03/04/2022 19:57:08 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 19:57:11 - INFO - codeparrot_training - Step 25947: {'lr': 0.0004683905579769708, 'samples': 13285376, 'steps': 25947, 'loss/train': 1.7338972091674805}
-03/04/2022 19:57:14 - INFO - codeparrot_training - Step 25948: {'lr': 0.0004683879750691283, 'samples': 13285888, 'steps': 25948, 'loss/train': 1.0507495403289795}
-03/04/2022 19:57:16 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/04/2022 19:57:19 - INFO - codeparrot_training - Step 25949: {'lr': 0.00046838539206288366, 'samples': 13286400, 'steps': 25949, 'loss/train': 1.6068230867385864}
-03/04/2022 19:57:23 - INFO - codeparrot_training - Step 25950: {'lr': 0.00046838280895823795, 'samples': 13286912, 'steps': 25950, 'loss/train': 1.342026710510254}
-03/04/2022 19:57:25 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/04/2022 19:57:28 - INFO - codeparrot_training - Step 25951: {'lr': 0.0004683802257551922, 'samples': 13287424, 'steps': 25951, 'loss/train': 1.280750036239624}
-03/04/2022 19:57:31 - INFO - codeparrot_training - Step 25952: {'lr': 0.00046837764245374777, 'samples': 13287936, 'steps': 25952, 'loss/train': 1.242254376411438}
-03/04/2022 19:57:34 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/04/2022 19:57:37 - INFO - codeparrot_training - Step 25953: {'lr': 0.0004683750590539057, 'samples': 13288448, 'steps': 25953, 'loss/train': 2.5195491313934326}
-03/04/2022 19:57:40 - INFO - codeparrot_training - Step 25954: {'lr': 0.00046837247555566727, 'samples': 13288960, 'steps': 25954, 'loss/train': 0.6278606653213501}
-03/04/2022 19:57:43 - INFO - codeparrot_training - Step 25955: {'lr': 0.00046836989195903344, 'samples': 13289472, 'steps': 25955, 'loss/train': 1.9989103078842163}
-03/04/2022 19:57:45 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/04/2022 19:57:49 - INFO - codeparrot_training - Step 25956: {'lr': 0.00046836730826400565, 'samples': 13289984, 'steps': 25956, 'loss/train': 2.1316897869110107}
-03/04/2022 19:57:52 - INFO - codeparrot_training - Step 25957: {'lr': 0.00046836472447058485, 'samples': 13290496, 'steps': 25957, 'loss/train': 1.4017983675003052}
-03/04/2022 19:57:54 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 19:57:57 - INFO - codeparrot_training - Step 25958: {'lr': 0.0004683621405787723, 'samples': 13291008, 'steps': 25958, 'loss/train': 1.9236096143722534}
-03/04/2022 19:58:00 - INFO - codeparrot_training - Step 25959: {'lr': 0.0004683595565885691, 'samples': 13291520, 'steps': 25959, 'loss/train': 1.9333937168121338}
-03/04/2022 19:58:02 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 19:58:06 - INFO - codeparrot_training - Step 25960: {'lr': 0.0004683569724999765, 'samples': 13292032, 'steps': 25960, 'loss/train': 1.951561689376831}
-03/04/2022 19:58:09 - INFO - codeparrot_training - Step 25961: {'lr': 0.0004683543883129956, 'samples': 13292544, 'steps': 25961, 'loss/train': 1.8304283618927002}
-03/04/2022 19:58:12 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 19:58:14 - INFO - codeparrot_training - Step 25962: {'lr': 0.00046835180402762756, 'samples': 13293056, 'steps': 25962, 'loss/train': 1.6901862621307373}
-03/04/2022 19:58:17 - INFO - codeparrot_training - Step 25963: {'lr': 0.00046834921964387363, 'samples': 13293568, 'steps': 25963, 'loss/train': 5.451969623565674}
-03/04/2022 19:58:20 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 19:58:23 - INFO - codeparrot_training - Step 25964: {'lr': 0.0004683466351617348, 'samples': 13294080, 'steps': 25964, 'loss/train': 1.5150420665740967}
-03/04/2022 19:58:26 - INFO - codeparrot_training - Step 25965: {'lr': 0.00046834405058121244, 'samples': 13294592, 'steps': 25965, 'loss/train': 1.571437954902649}
-03/04/2022 19:58:28 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/04/2022 19:58:31 - INFO - codeparrot_training - Step 25966: {'lr': 0.0004683414659023076, 'samples': 13295104, 'steps': 25966, 'loss/train': 1.7864043712615967}
-03/04/2022 19:58:34 - INFO - codeparrot_training - Step 25967: {'lr': 0.0004683388811250214, 'samples': 13295616, 'steps': 25967, 'loss/train': 1.7730915546417236}
-03/04/2022 19:58:37 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 19:58:40 - INFO - codeparrot_training - Step 25968: {'lr': 0.0004683362962493552, 'samples': 13296128, 'steps': 25968, 'loss/train': 1.475606083869934}
-03/04/2022 19:58:43 - INFO - codeparrot_training - Step 25969: {'lr': 0.00046833371127530995, 'samples': 13296640, 'steps': 25969, 'loss/train': 2.481719732284546}
-03/04/2022 19:58:45 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/04/2022 19:58:48 - INFO - codeparrot_training - Step 25970: {'lr': 0.00046833112620288684, 'samples': 13297152, 'steps': 25970, 'loss/train': 1.379334807395935}
-03/04/2022 19:58:51 - INFO - codeparrot_training - Step 25971: {'lr': 0.0004683285410320872, 'samples': 13297664, 'steps': 25971, 'loss/train': 1.6995652914047241}
-03/04/2022 19:58:54 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/04/2022 19:58:57 - INFO - codeparrot_training - Step 25972: {'lr': 0.000468325955762912, 'samples': 13298176, 'steps': 25972, 'loss/train': 1.784519076347351}
-03/04/2022 19:59:00 - INFO - codeparrot_training - Step 25973: {'lr': 0.0004683233703953626, 'samples': 13298688, 'steps': 25973, 'loss/train': 2.130711793899536}
-03/04/2022 19:59:02 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/04/2022 19:59:05 - INFO - codeparrot_training - Step 25974: {'lr': 0.00046832078492944, 'samples': 13299200, 'steps': 25974, 'loss/train': 1.400537133216858}
-03/04/2022 19:59:08 - INFO - codeparrot_training - Step 25975: {'lr': 0.0004683181993651454, 'samples': 13299712, 'steps': 25975, 'loss/train': 1.9857072830200195}
-03/04/2022 19:59:11 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/04/2022 19:59:14 - INFO - codeparrot_training - Step 25976: {'lr': 0.0004683156137024801, 'samples': 13300224, 'steps': 25976, 'loss/train': 3.087407112121582}
-03/04/2022 19:59:17 - INFO - codeparrot_training - Step 25977: {'lr': 0.00046831302794144504, 'samples': 13300736, 'steps': 25977, 'loss/train': 2.095113515853882}
-03/04/2022 19:59:19 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 19:59:22 - INFO - codeparrot_training - Step 25978: {'lr': 0.00046831044208204154, 'samples': 13301248, 'steps': 25978, 'loss/train': 2.3248891830444336}
-03/04/2022 19:59:25 - INFO - codeparrot_training - Step 25979: {'lr': 0.0004683078561242707, 'samples': 13301760, 'steps': 25979, 'loss/train': 2.0172057151794434}
-03/04/2022 19:59:28 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/04/2022 19:59:30 - INFO - codeparrot_training - Step 25980: {'lr': 0.00046830527006813373, 'samples': 13302272, 'steps': 25980, 'loss/train': 1.6450740098953247}
-03/04/2022 19:59:34 - INFO - codeparrot_training - Step 25981: {'lr': 0.00046830268391363176, 'samples': 13302784, 'steps': 25981, 'loss/train': 2.0067148208618164}
-03/04/2022 19:59:36 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 19:59:39 - INFO - codeparrot_training - Step 25982: {'lr': 0.0004683000976607659, 'samples': 13303296, 'steps': 25982, 'loss/train': 0.389595627784729}
-03/04/2022 19:59:42 - INFO - codeparrot_training - Step 25983: {'lr': 0.00046829751130953747, 'samples': 13303808, 'steps': 25983, 'loss/train': 1.8984497785568237}
-03/04/2022 19:59:45 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/04/2022 19:59:47 - INFO - codeparrot_training - Step 25984: {'lr': 0.0004682949248599476, 'samples': 13304320, 'steps': 25984, 'loss/train': 0.3006818890571594}
-03/04/2022 19:59:51 - INFO - codeparrot_training - Step 25985: {'lr': 0.0004682923383119973, 'samples': 13304832, 'steps': 25985, 'loss/train': 1.7708948850631714}
-03/04/2022 19:59:54 - INFO - codeparrot_training - Step 25986: {'lr': 0.0004682897516656879, 'samples': 13305344, 'steps': 25986, 'loss/train': 1.1965590715408325}
-03/04/2022 19:59:54 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/04/2022 19:59:59 - INFO - codeparrot_training - Step 25987: {'lr': 0.00046828716492102043, 'samples': 13305856, 'steps': 25987, 'loss/train': 1.3682154417037964}
-03/04/2022 20:00:02 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 20:00:04 - INFO - codeparrot_training - Step 25988: {'lr': 0.0004682845780779962, 'samples': 13306368, 'steps': 25988, 'loss/train': 2.382455825805664}
-03/04/2022 20:00:08 - INFO - codeparrot_training - Step 25989: {'lr': 0.00046828199113661627, 'samples': 13306880, 'steps': 25989, 'loss/train': 1.4804397821426392}
-03/04/2022 20:00:10 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/04/2022 20:00:13 - INFO - codeparrot_training - Step 25990: {'lr': 0.0004682794040968819, 'samples': 13307392, 'steps': 25990, 'loss/train': 2.6654675006866455}
-03/04/2022 20:00:16 - INFO - codeparrot_training - Step 25991: {'lr': 0.0004682768169587942, 'samples': 13307904, 'steps': 25991, 'loss/train': 0.4490848779678345}
-03/04/2022 20:00:19 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/04/2022 20:00:21 - INFO - codeparrot_training - Step 25992: {'lr': 0.0004682742297223543, 'samples': 13308416, 'steps': 25992, 'loss/train': 1.8544172048568726}
-03/04/2022 20:00:24 - INFO - codeparrot_training - Step 25993: {'lr': 0.00046827164238756337, 'samples': 13308928, 'steps': 25993, 'loss/train': 2.208698034286499}
-03/04/2022 20:00:27 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/04/2022 20:00:30 - INFO - codeparrot_training - Step 25994: {'lr': 0.00046826905495442263, 'samples': 13309440, 'steps': 25994, 'loss/train': 1.708541750907898}
-03/04/2022 20:00:33 - INFO - codeparrot_training - Step 25995: {'lr': 0.00046826646742293326, 'samples': 13309952, 'steps': 25995, 'loss/train': 1.9661489725112915}
-03/04/2022 20:00:36 - INFO - codeparrot_training - Step 25996: {'lr': 0.00046826387979309635, 'samples': 13310464, 'steps': 25996, 'loss/train': 1.159864068031311}
-03/04/2022 20:00:38 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/04/2022 20:00:42 - INFO - codeparrot_training - Step 25997: {'lr': 0.0004682612920649131, 'samples': 13310976, 'steps': 25997, 'loss/train': 1.7186181545257568}
-03/04/2022 20:00:45 - INFO - codeparrot_training - Step 25998: {'lr': 0.00046825870423838466, 'samples': 13311488, 'steps': 25998, 'loss/train': 2.6319777965545654}
-03/04/2022 20:00:46 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/04/2022 20:00:50 - INFO - codeparrot_training - Step 25999: {'lr': 0.00046825611631351227, 'samples': 13312000, 'steps': 25999, 'loss/train': 1.9062258005142212}
-03/04/2022 20:00:53 - INFO - codeparrot_training - Step 26000: {'lr': 0.00046825352829029705, 'samples': 13312512, 'steps': 26000, 'loss/train': 1.642259120941162}
-03/04/2022 20:00:54 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 20:00:58 - INFO - codeparrot_training - Step 26001: {'lr': 0.00046825094016874014, 'samples': 13313024, 'steps': 26001, 'loss/train': 1.9957187175750732}
-03/04/2022 20:01:02 - INFO - codeparrot_training - Step 26002: {'lr': 0.00046824835194884273, 'samples': 13313536, 'steps': 26002, 'loss/train': 2.7465879917144775}
-03/04/2022 20:01:03 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 20:01:07 - INFO - codeparrot_training - Step 26003: {'lr': 0.0004682457636306059, 'samples': 13314048, 'steps': 26003, 'loss/train': 2.3993852138519287}
-03/04/2022 20:01:10 - INFO - codeparrot_training - Step 26004: {'lr': 0.000468243175214031, 'samples': 13314560, 'steps': 26004, 'loss/train': 1.9481501579284668}
-03/04/2022 20:01:11 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/04/2022 20:01:15 - INFO - codeparrot_training - Step 26005: {'lr': 0.00046824058669911906, 'samples': 13315072, 'steps': 26005, 'loss/train': 1.878860354423523}
-03/04/2022 20:01:18 - INFO - codeparrot_training - Step 26006: {'lr': 0.00046823799808587126, 'samples': 13315584, 'steps': 26006, 'loss/train': 2.114102840423584}
-03/04/2022 20:01:19 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/04/2022 20:01:24 - INFO - codeparrot_training - Step 26007: {'lr': 0.00046823540937428876, 'samples': 13316096, 'steps': 26007, 'loss/train': 1.279818058013916}
-03/04/2022 20:01:27 - INFO - codeparrot_training - Step 26008: {'lr': 0.0004682328205643728, 'samples': 13316608, 'steps': 26008, 'loss/train': 1.2121267318725586}
-03/04/2022 20:01:27 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/04/2022 20:01:32 - INFO - codeparrot_training - Step 26009: {'lr': 0.00046823023165612455, 'samples': 13317120, 'steps': 26009, 'loss/train': 1.4796291589736938}
-03/04/2022 20:01:35 - INFO - codeparrot_training - Step 26010: {'lr': 0.000468227642649545, 'samples': 13317632, 'steps': 26010, 'loss/train': 1.2600312232971191}
-03/04/2022 20:01:36 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/04/2022 20:01:41 - INFO - codeparrot_training - Step 26011: {'lr': 0.00046822505354463553, 'samples': 13318144, 'steps': 26011, 'loss/train': 1.5071678161621094}
-03/04/2022 20:01:44 - INFO - codeparrot_training - Step 26012: {'lr': 0.0004682224643413972, 'samples': 13318656, 'steps': 26012, 'loss/train': 1.6324503421783447}
-03/04/2022 20:01:44 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 20:01:49 - INFO - codeparrot_training - Step 26013: {'lr': 0.0004682198750398312, 'samples': 13319168, 'steps': 26013, 'loss/train': 1.8580371141433716}
-03/04/2022 20:01:52 - INFO - codeparrot_training - Step 26014: {'lr': 0.00046821728563993867, 'samples': 13319680, 'steps': 26014, 'loss/train': 1.4944595098495483}
-03/04/2022 20:01:53 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/04/2022 20:01:58 - INFO - codeparrot_training - Step 26015: {'lr': 0.0004682146961417208, 'samples': 13320192, 'steps': 26015, 'loss/train': 2.1687328815460205}
-03/04/2022 20:02:01 - INFO - codeparrot_training - Step 26016: {'lr': 0.00046821210654517874, 'samples': 13320704, 'steps': 26016, 'loss/train': 1.8499046564102173}
-03/04/2022 20:02:01 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/04/2022 20:02:06 - INFO - codeparrot_training - Step 26017: {'lr': 0.0004682095168503137, 'samples': 13321216, 'steps': 26017, 'loss/train': 1.6416001319885254}
-03/04/2022 20:02:09 - INFO - codeparrot_training - Step 26018: {'lr': 0.00046820692705712685, 'samples': 13321728, 'steps': 26018, 'loss/train': 1.6696640253067017}
-03/04/2022 20:02:10 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/04/2022 20:02:15 - INFO - codeparrot_training - Step 26019: {'lr': 0.00046820433716561927, 'samples': 13322240, 'steps': 26019, 'loss/train': 2.091885805130005}
-03/04/2022 20:02:18 - INFO - codeparrot_training - Step 26020: {'lr': 0.0004682017471757922, 'samples': 13322752, 'steps': 26020, 'loss/train': 1.6339701414108276}
-03/04/2022 20:02:18 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/04/2022 20:02:23 - INFO - codeparrot_training - Step 26021: {'lr': 0.0004681991570876468, 'samples': 13323264, 'steps': 26021, 'loss/train': 1.8215528726577759}
-03/04/2022 20:02:26 - INFO - codeparrot_training - Step 26022: {'lr': 0.00046819656690118424, 'samples': 13323776, 'steps': 26022, 'loss/train': 3.4259986877441406}
-03/04/2022 20:02:27 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 20:02:31 - INFO - codeparrot_training - Step 26023: {'lr': 0.00046819397661640563, 'samples': 13324288, 'steps': 26023, 'loss/train': 2.394054651260376}
-03/04/2022 20:02:35 - INFO - codeparrot_training - Step 26024: {'lr': 0.0004681913862333122, 'samples': 13324800, 'steps': 26024, 'loss/train': 1.49062180519104}
-03/04/2022 20:02:35 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 20:02:40 - INFO - codeparrot_training - Step 26025: {'lr': 0.0004681887957519051, 'samples': 13325312, 'steps': 26025, 'loss/train': 2.31349778175354}
-03/04/2022 20:02:43 - INFO - codeparrot_training - Step 26026: {'lr': 0.00046818620517218544, 'samples': 13325824, 'steps': 26026, 'loss/train': 0.6781665086746216}
-03/04/2022 20:02:43 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 20:02:48 - INFO - codeparrot_training - Step 26027: {'lr': 0.00046818361449415456, 'samples': 13326336, 'steps': 26027, 'loss/train': 2.374075412750244}
-03/04/2022 20:02:52 - INFO - codeparrot_training - Step 26028: {'lr': 0.00046818102371781343, 'samples': 13326848, 'steps': 26028, 'loss/train': 2.1996102333068848}
-03/04/2022 20:02:52 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/04/2022 20:02:57 - INFO - codeparrot_training - Step 26029: {'lr': 0.0004681784328431633, 'samples': 13327360, 'steps': 26029, 'loss/train': 1.759771704673767}
-03/04/2022 20:03:00 - INFO - codeparrot_training - Step 26030: {'lr': 0.0004681758418702054, 'samples': 13327872, 'steps': 26030, 'loss/train': 1.7152024507522583}
-03/04/2022 20:03:00 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 20:03:05 - INFO - codeparrot_training - Step 26031: {'lr': 0.0004681732507989408, 'samples': 13328384, 'steps': 26031, 'loss/train': 2.422318458557129}
-03/04/2022 20:03:09 - INFO - codeparrot_training - Step 26032: {'lr': 0.00046817065962937067, 'samples': 13328896, 'steps': 26032, 'loss/train': 1.7547481060028076}
-03/04/2022 20:03:09 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 20:03:14 - INFO - codeparrot_training - Step 26033: {'lr': 0.00046816806836149624, 'samples': 13329408, 'steps': 26033, 'loss/train': 1.7028642892837524}
-03/04/2022 20:03:17 - INFO - codeparrot_training - Step 26034: {'lr': 0.00046816547699531866, 'samples': 13329920, 'steps': 26034, 'loss/train': 1.9825752973556519}
-03/04/2022 20:03:17 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 20:03:24 - INFO - codeparrot_training - Step 26035: {'lr': 0.000468162885530839, 'samples': 13330432, 'steps': 26035, 'loss/train': 1.625740647315979}
-03/04/2022 20:03:27 - INFO - codeparrot_training - Step 26036: {'lr': 0.00046816029396805857, 'samples': 13330944, 'steps': 26036, 'loss/train': 1.21263587474823}
-03/04/2022 20:03:30 - INFO - codeparrot_training - Step 26037: {'lr': 0.00046815770230697844, 'samples': 13331456, 'steps': 26037, 'loss/train': 1.2467689514160156}
-03/04/2022 20:03:30 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/04/2022 20:03:35 - INFO - codeparrot_training - Step 26038: {'lr': 0.0004681551105475999, 'samples': 13331968, 'steps': 26038, 'loss/train': 1.9564452171325684}
-03/04/2022 20:03:39 - INFO - codeparrot_training - Step 26039: {'lr': 0.0004681525186899239, 'samples': 13332480, 'steps': 26039, 'loss/train': 0.5865878462791443}
-03/04/2022 20:03:39 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/04/2022 20:03:44 - INFO - codeparrot_training - Step 26040: {'lr': 0.00046814992673395185, 'samples': 13332992, 'steps': 26040, 'loss/train': 1.656312346458435}
-03/04/2022 20:03:47 - INFO - codeparrot_training - Step 26041: {'lr': 0.0004681473346796848, 'samples': 13333504, 'steps': 26041, 'loss/train': 1.2797900438308716}
-03/04/2022 20:03:48 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 20:03:52 - INFO - codeparrot_training - Step 26042: {'lr': 0.0004681447425271239, 'samples': 13334016, 'steps': 26042, 'loss/train': 1.9386578798294067}
-03/04/2022 20:03:56 - INFO - codeparrot_training - Step 26043: {'lr': 0.0004681421502762704, 'samples': 13334528, 'steps': 26043, 'loss/train': 1.8510576486587524}
-03/04/2022 20:03:56 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/04/2022 20:04:01 - INFO - codeparrot_training - Step 26044: {'lr': 0.0004681395579271253, 'samples': 13335040, 'steps': 26044, 'loss/train': 1.896577000617981}
-03/04/2022 20:04:04 - INFO - codeparrot_training - Step 26045: {'lr': 0.00046813696547969, 'samples': 13335552, 'steps': 26045, 'loss/train': 1.9619214534759521}
-03/04/2022 20:04:06 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/04/2022 20:04:10 - INFO - codeparrot_training - Step 26046: {'lr': 0.00046813437293396543, 'samples': 13336064, 'steps': 26046, 'loss/train': 1.7232069969177246}
-03/04/2022 20:04:13 - INFO - codeparrot_training - Step 26047: {'lr': 0.000468131780289953, 'samples': 13336576, 'steps': 26047, 'loss/train': 2.3391799926757812}
-03/04/2022 20:04:15 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/04/2022 20:04:18 - INFO - codeparrot_training - Step 26048: {'lr': 0.00046812918754765364, 'samples': 13337088, 'steps': 26048, 'loss/train': 1.3230880498886108}
-03/04/2022 20:04:21 - INFO - codeparrot_training - Step 26049: {'lr': 0.00046812659470706877, 'samples': 13337600, 'steps': 26049, 'loss/train': 2.23012638092041}
-03/04/2022 20:04:23 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/04/2022 20:04:27 - INFO - codeparrot_training - Step 26050: {'lr': 0.0004681240017681993, 'samples': 13338112, 'steps': 26050, 'loss/train': 1.5336859226226807}
-03/04/2022 20:04:30 - INFO - codeparrot_training - Step 26051: {'lr': 0.00046812140873104657, 'samples': 13338624, 'steps': 26051, 'loss/train': 1.8654184341430664}
-03/04/2022 20:04:31 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 20:04:35 - INFO - codeparrot_training - Step 26052: {'lr': 0.00046811881559561167, 'samples': 13339136, 'steps': 26052, 'loss/train': 1.5603783130645752}
-03/04/2022 20:04:38 - INFO - codeparrot_training - Step 26053: {'lr': 0.00046811622236189585, 'samples': 13339648, 'steps': 26053, 'loss/train': 1.9893840551376343}
-03/04/2022 20:04:40 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/04/2022 20:04:43 - INFO - codeparrot_training - Step 26054: {'lr': 0.0004681136290299002, 'samples': 13340160, 'steps': 26054, 'loss/train': 1.6339237689971924}
-03/04/2022 20:04:47 - INFO - codeparrot_training - Step 26055: {'lr': 0.00046811103559962585, 'samples': 13340672, 'steps': 26055, 'loss/train': 1.1602602005004883}
-03/04/2022 20:04:49 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/04/2022 20:04:52 - INFO - codeparrot_training - Step 26056: {'lr': 0.00046810844207107415, 'samples': 13341184, 'steps': 26056, 'loss/train': 1.939034104347229}
-03/04/2022 20:04:55 - INFO - codeparrot_training - Step 26057: {'lr': 0.0004681058484442461, 'samples': 13341696, 'steps': 26057, 'loss/train': 2.1607604026794434}
-03/04/2022 20:04:57 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/04/2022 20:05:01 - INFO - codeparrot_training - Step 26058: {'lr': 0.00046810325471914295, 'samples': 13342208, 'steps': 26058, 'loss/train': 1.9978156089782715}
-03/04/2022 20:05:04 - INFO - codeparrot_training - Step 26059: {'lr': 0.00046810066089576573, 'samples': 13342720, 'steps': 26059, 'loss/train': 2.2285096645355225}
-03/04/2022 20:05:06 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 20:05:09 - INFO - codeparrot_training - Step 26060: {'lr': 0.00046809806697411583, 'samples': 13343232, 'steps': 26060, 'loss/train': 1.9420771598815918}
-03/04/2022 20:05:12 - INFO - codeparrot_training - Step 26061: {'lr': 0.0004680954729541942, 'samples': 13343744, 'steps': 26061, 'loss/train': 1.859422206878662}
-03/04/2022 20:05:15 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/04/2022 20:05:18 - INFO - codeparrot_training - Step 26062: {'lr': 0.00046809287883600227, 'samples': 13344256, 'steps': 26062, 'loss/train': 2.1467933654785156}
-03/04/2022 20:05:21 - INFO - codeparrot_training - Step 26063: {'lr': 0.00046809028461954093, 'samples': 13344768, 'steps': 26063, 'loss/train': 1.8985170125961304}
-03/04/2022 20:05:24 - INFO - codeparrot_training - Step 26064: {'lr': 0.00046808769030481153, 'samples': 13345280, 'steps': 26064, 'loss/train': 2.155360221862793}
-03/04/2022 20:05:24 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/04/2022 20:05:29 - INFO - codeparrot_training - Step 26065: {'lr': 0.00046808509589181513, 'samples': 13345792, 'steps': 26065, 'loss/train': 2.5804591178894043}
-03/04/2022 20:05:33 - INFO - codeparrot_training - Step 26066: {'lr': 0.00046808250138055305, 'samples': 13346304, 'steps': 26066, 'loss/train': 1.4153510332107544}
-03/04/2022 20:05:33 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 20:05:38 - INFO - codeparrot_training - Step 26067: {'lr': 0.0004680799067710263, 'samples': 13346816, 'steps': 26067, 'loss/train': 1.696730136871338}
-03/04/2022 20:05:41 - INFO - codeparrot_training - Step 26068: {'lr': 0.00046807731206323605, 'samples': 13347328, 'steps': 26068, 'loss/train': 1.9909054040908813}
-03/04/2022 20:05:41 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 20:05:47 - INFO - codeparrot_training - Step 26069: {'lr': 0.00046807471725718357, 'samples': 13347840, 'steps': 26069, 'loss/train': 2.2206437587738037}
-03/04/2022 20:05:50 - INFO - codeparrot_training - Step 26070: {'lr': 0.00046807212235287, 'samples': 13348352, 'steps': 26070, 'loss/train': 1.504632592201233}
-03/04/2022 20:05:51 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 20:05:55 - INFO - codeparrot_training - Step 26071: {'lr': 0.0004680695273502965, 'samples': 13348864, 'steps': 26071, 'loss/train': 1.7281231880187988}
-03/04/2022 20:05:58 - INFO - codeparrot_training - Step 26072: {'lr': 0.00046806693224946426, 'samples': 13349376, 'steps': 26072, 'loss/train': 1.9475656747817993}
-03/04/2022 20:05:59 - INFO - codeparrot_training - Skipping example with length 233 (seq_length=1024)
-03/04/2022 20:06:04 - INFO - codeparrot_training - Step 26073: {'lr': 0.00046806433705037445, 'samples': 13349888, 'steps': 26073, 'loss/train': 1.2138975858688354}
-03/04/2022 20:06:07 - INFO - codeparrot_training - Step 26074: {'lr': 0.00046806174175302806, 'samples': 13350400, 'steps': 26074, 'loss/train': 1.6533374786376953}
-03/04/2022 20:06:07 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 20:06:12 - INFO - codeparrot_training - Step 26075: {'lr': 0.00046805914635742656, 'samples': 13350912, 'steps': 26075, 'loss/train': 1.3776440620422363}
-03/04/2022 20:06:15 - INFO - codeparrot_training - Step 26076: {'lr': 0.0004680565508635709, 'samples': 13351424, 'steps': 26076, 'loss/train': 1.4836182594299316}
-03/04/2022 20:06:16 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 20:06:21 - INFO - codeparrot_training - Step 26077: {'lr': 0.00046805395527146237, 'samples': 13351936, 'steps': 26077, 'loss/train': 0.08600012958049774}
-03/04/2022 20:06:24 - INFO - codeparrot_training - Step 26078: {'lr': 0.0004680513595811021, 'samples': 13352448, 'steps': 26078, 'loss/train': 2.2343058586120605}
-03/04/2022 20:06:24 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/04/2022 20:06:29 - INFO - codeparrot_training - Step 26079: {'lr': 0.0004680487637924912, 'samples': 13352960, 'steps': 26079, 'loss/train': 1.3945581912994385}
-03/04/2022 20:06:32 - INFO - codeparrot_training - Step 26080: {'lr': 0.0004680461679056309, 'samples': 13353472, 'steps': 26080, 'loss/train': 1.9323657751083374}
-03/04/2022 20:06:32 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/04/2022 20:06:37 - INFO - codeparrot_training - Step 26081: {'lr': 0.00046804357192052246, 'samples': 13353984, 'steps': 26081, 'loss/train': 1.6812783479690552}
-03/04/2022 20:06:40 - INFO - codeparrot_training - Step 26082: {'lr': 0.00046804097583716685, 'samples': 13354496, 'steps': 26082, 'loss/train': 1.9438518285751343}
-03/04/2022 20:06:41 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 20:06:46 - INFO - codeparrot_training - Step 26083: {'lr': 0.0004680383796555654, 'samples': 13355008, 'steps': 26083, 'loss/train': 1.2943382263183594}
-03/04/2022 20:06:49 - INFO - codeparrot_training - Step 26084: {'lr': 0.00046803578337571917, 'samples': 13355520, 'steps': 26084, 'loss/train': 1.0002782344818115}
-03/04/2022 20:06:49 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/04/2022 20:06:54 - INFO - codeparrot_training - Step 26085: {'lr': 0.00046803318699762937, 'samples': 13356032, 'steps': 26085, 'loss/train': 1.9299094676971436}
-03/04/2022 20:06:57 - INFO - codeparrot_training - Step 26086: {'lr': 0.0004680305905212972, 'samples': 13356544, 'steps': 26086, 'loss/train': 0.6169664859771729}
-03/04/2022 20:06:58 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/04/2022 20:07:03 - INFO - codeparrot_training - Step 26087: {'lr': 0.0004680279939467238, 'samples': 13357056, 'steps': 26087, 'loss/train': 1.0394940376281738}
-03/04/2022 20:07:06 - INFO - codeparrot_training - Step 26088: {'lr': 0.00046802539727391033, 'samples': 13357568, 'steps': 26088, 'loss/train': 0.7880287170410156}
-03/04/2022 20:07:06 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 20:07:11 - INFO - codeparrot_training - Step 26089: {'lr': 0.0004680228005028581, 'samples': 13358080, 'steps': 26089, 'loss/train': 2.655686378479004}
-03/04/2022 20:07:14 - INFO - codeparrot_training - Step 26090: {'lr': 0.000468020203633568, 'samples': 13358592, 'steps': 26090, 'loss/train': 2.0334312915802}
-03/04/2022 20:07:15 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/04/2022 20:07:20 - INFO - codeparrot_training - Step 26091: {'lr': 0.0004680176066660415, 'samples': 13359104, 'steps': 26091, 'loss/train': 1.6737325191497803}
-03/04/2022 20:07:23 - INFO - codeparrot_training - Step 26092: {'lr': 0.00046801500960027957, 'samples': 13359616, 'steps': 26092, 'loss/train': 0.2667890787124634}
-03/04/2022 20:07:23 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 20:07:28 - INFO - codeparrot_training - Step 26093: {'lr': 0.00046801241243628344, 'samples': 13360128, 'steps': 26093, 'loss/train': 1.9876550436019897}
-03/04/2022 20:07:32 - INFO - codeparrot_training - Step 26094: {'lr': 0.00046800981517405426, 'samples': 13360640, 'steps': 26094, 'loss/train': 1.8479565382003784}
-03/04/2022 20:07:32 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 20:07:37 - INFO - codeparrot_training - Step 26095: {'lr': 0.0004680072178135932, 'samples': 13361152, 'steps': 26095, 'loss/train': 2.7933173179626465}
-03/04/2022 20:07:40 - INFO - codeparrot_training - Step 26096: {'lr': 0.00046800462035490156, 'samples': 13361664, 'steps': 26096, 'loss/train': 1.850113034248352}
-03/04/2022 20:07:40 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/04/2022 20:07:45 - INFO - codeparrot_training - Step 26097: {'lr': 0.0004680020227979803, 'samples': 13362176, 'steps': 26097, 'loss/train': 2.1076200008392334}
-03/04/2022 20:07:48 - INFO - codeparrot_training - Step 26098: {'lr': 0.0004679994251428308, 'samples': 13362688, 'steps': 26098, 'loss/train': 1.461331844329834}
-03/04/2022 20:07:49 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/04/2022 20:07:54 - INFO - codeparrot_training - Step 26099: {'lr': 0.00046799682738945397, 'samples': 13363200, 'steps': 26099, 'loss/train': 2.1057004928588867}
-03/04/2022 20:07:57 - INFO - codeparrot_training - Step 26100: {'lr': 0.00046799422953785124, 'samples': 13363712, 'steps': 26100, 'loss/train': 1.9739357233047485}
-03/04/2022 20:07:57 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/04/2022 20:08:02 - INFO - codeparrot_training - Step 26101: {'lr': 0.00046799163158802365, 'samples': 13364224, 'steps': 26101, 'loss/train': 2.557032346725464}
-03/04/2022 20:08:05 - INFO - codeparrot_training - Step 26102: {'lr': 0.00046798903353997243, 'samples': 13364736, 'steps': 26102, 'loss/train': 1.5120562314987183}
-03/04/2022 20:08:06 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 20:08:11 - INFO - codeparrot_training - Step 26103: {'lr': 0.0004679864353936987, 'samples': 13365248, 'steps': 26103, 'loss/train': 1.576947569847107}
-03/04/2022 20:08:14 - INFO - codeparrot_training - Step 26104: {'lr': 0.0004679838371492036, 'samples': 13365760, 'steps': 26104, 'loss/train': 0.8888798356056213}
-03/04/2022 20:08:14 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/04/2022 20:08:19 - INFO - codeparrot_training - Step 26105: {'lr': 0.00046798123880648833, 'samples': 13366272, 'steps': 26105, 'loss/train': 1.4169363975524902}
-03/04/2022 20:08:22 - INFO - codeparrot_training - Step 26106: {'lr': 0.0004679786403655542, 'samples': 13366784, 'steps': 26106, 'loss/train': 1.9095174074172974}
-03/04/2022 20:08:23 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/04/2022 20:08:27 - INFO - codeparrot_training - Step 26107: {'lr': 0.0004679760418264021, 'samples': 13367296, 'steps': 26107, 'loss/train': 1.3199622631072998}
-03/04/2022 20:08:31 - INFO - codeparrot_training - Step 26108: {'lr': 0.00046797344318903343, 'samples': 13367808, 'steps': 26108, 'loss/train': 1.3211076259613037}
-03/04/2022 20:08:31 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/04/2022 20:08:36 - INFO - codeparrot_training - Step 26109: {'lr': 0.0004679708444534493, 'samples': 13368320, 'steps': 26109, 'loss/train': 1.430361032485962}
-03/04/2022 20:08:39 - INFO - codeparrot_training - Step 26110: {'lr': 0.0004679682456196509, 'samples': 13368832, 'steps': 26110, 'loss/train': 1.5073020458221436}
-03/04/2022 20:08:40 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 20:08:44 - INFO - codeparrot_training - Step 26111: {'lr': 0.0004679656466876393, 'samples': 13369344, 'steps': 26111, 'loss/train': 1.5049188137054443}
-03/04/2022 20:08:47 - INFO - codeparrot_training - Step 26112: {'lr': 0.00046796304765741583, 'samples': 13369856, 'steps': 26112, 'loss/train': 2.1840643882751465}
-03/04/2022 20:08:48 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/04/2022 20:08:53 - INFO - codeparrot_training - Step 26113: {'lr': 0.00046796044852898144, 'samples': 13370368, 'steps': 26113, 'loss/train': 1.8755805492401123}
-03/04/2022 20:08:56 - INFO - codeparrot_training - Step 26114: {'lr': 0.0004679578493023375, 'samples': 13370880, 'steps': 26114, 'loss/train': 2.1485798358917236}
-03/04/2022 20:08:56 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 20:09:01 - INFO - codeparrot_training - Step 26115: {'lr': 0.00046795524997748515, 'samples': 13371392, 'steps': 26115, 'loss/train': 1.7973297834396362}
-03/04/2022 20:09:05 - INFO - codeparrot_training - Step 26116: {'lr': 0.0004679526505544256, 'samples': 13371904, 'steps': 26116, 'loss/train': 1.2531079053878784}
-03/04/2022 20:09:06 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/04/2022 20:09:10 - INFO - codeparrot_training - Step 26117: {'lr': 0.0004679500510331598, 'samples': 13372416, 'steps': 26117, 'loss/train': 3.1542937755584717}
-03/04/2022 20:09:13 - INFO - codeparrot_training - Step 26118: {'lr': 0.00046794745141368917, 'samples': 13372928, 'steps': 26118, 'loss/train': 2.1721999645233154}
-03/04/2022 20:09:15 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/04/2022 20:09:18 - INFO - codeparrot_training - Step 26119: {'lr': 0.00046794485169601474, 'samples': 13373440, 'steps': 26119, 'loss/train': 1.8792463541030884}
-03/04/2022 20:09:22 - INFO - codeparrot_training - Step 26120: {'lr': 0.00046794225188013773, 'samples': 13373952, 'steps': 26120, 'loss/train': 1.7419171333312988}
-03/04/2022 20:09:23 - INFO - codeparrot_training - Skipping example with length 5 (seq_length=1024)
-03/04/2022 20:09:27 - INFO - codeparrot_training - Step 26121: {'lr': 0.00046793965196605927, 'samples': 13374464, 'steps': 26121, 'loss/train': 1.6223589181900024}
-03/04/2022 20:09:30 - INFO - codeparrot_training - Step 26122: {'lr': 0.00046793705195378066, 'samples': 13374976, 'steps': 26122, 'loss/train': 2.656970500946045}
-03/04/2022 20:09:32 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 20:09:35 - INFO - codeparrot_training - Step 26123: {'lr': 0.0004679344518433029, 'samples': 13375488, 'steps': 26123, 'loss/train': 0.9795936942100525}
-03/04/2022 20:09:39 - INFO - codeparrot_training - Step 26124: {'lr': 0.0004679318516346273, 'samples': 13376000, 'steps': 26124, 'loss/train': 1.3444304466247559}
-03/04/2022 20:09:41 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 20:09:44 - INFO - codeparrot_training - Step 26125: {'lr': 0.0004679292513277549, 'samples': 13376512, 'steps': 26125, 'loss/train': 1.149139404296875}
-03/04/2022 20:09:47 - INFO - codeparrot_training - Step 26126: {'lr': 0.0004679266509226869, 'samples': 13377024, 'steps': 26126, 'loss/train': 1.4356820583343506}
-03/04/2022 20:09:49 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 20:09:52 - INFO - codeparrot_training - Step 26127: {'lr': 0.0004679240504194246, 'samples': 13377536, 'steps': 26127, 'loss/train': 1.981621265411377}
-03/04/2022 20:09:56 - INFO - codeparrot_training - Step 26128: {'lr': 0.00046792144981796905, 'samples': 13378048, 'steps': 26128, 'loss/train': 1.70073664188385}
-03/04/2022 20:09:58 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/04/2022 20:10:01 - INFO - codeparrot_training - Step 26129: {'lr': 0.0004679188491183215, 'samples': 13378560, 'steps': 26129, 'loss/train': 2.0027880668640137}
-03/04/2022 20:10:04 - INFO - codeparrot_training - Step 26130: {'lr': 0.00046791624832048307, 'samples': 13379072, 'steps': 26130, 'loss/train': 2.084019422531128}
-03/04/2022 20:10:06 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/04/2022 20:10:09 - INFO - codeparrot_training - Step 26131: {'lr': 0.0004679136474244549, 'samples': 13379584, 'steps': 26131, 'loss/train': 2.7600772380828857}
-03/04/2022 20:10:13 - INFO - codeparrot_training - Step 26132: {'lr': 0.00046791104643023823, 'samples': 13380096, 'steps': 26132, 'loss/train': 0.683334231376648}
-03/04/2022 20:10:15 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/04/2022 20:10:18 - INFO - codeparrot_training - Step 26133: {'lr': 0.0004679084453378342, 'samples': 13380608, 'steps': 26133, 'loss/train': 1.2610054016113281}
-03/04/2022 20:10:21 - INFO - codeparrot_training - Step 26134: {'lr': 0.00046790584414724404, 'samples': 13381120, 'steps': 26134, 'loss/train': 2.120995044708252}
-03/04/2022 20:10:24 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 20:10:27 - INFO - codeparrot_training - Step 26135: {'lr': 0.0004679032428584687, 'samples': 13381632, 'steps': 26135, 'loss/train': 0.5777688026428223}
-03/04/2022 20:10:30 - INFO - codeparrot_training - Step 26136: {'lr': 0.0004679006414715097, 'samples': 13382144, 'steps': 26136, 'loss/train': 1.680233120918274}
-03/04/2022 20:10:32 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/04/2022 20:10:35 - INFO - codeparrot_training - Step 26137: {'lr': 0.00046789803998636796, 'samples': 13382656, 'steps': 26137, 'loss/train': 1.557360053062439}
-03/04/2022 20:10:38 - INFO - codeparrot_training - Step 26138: {'lr': 0.0004678954384030448, 'samples': 13383168, 'steps': 26138, 'loss/train': 2.390317440032959}
-03/04/2022 20:10:41 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/04/2022 20:10:44 - INFO - codeparrot_training - Step 26139: {'lr': 0.00046789283672154125, 'samples': 13383680, 'steps': 26139, 'loss/train': 3.7934465408325195}
-03/04/2022 20:10:47 - INFO - codeparrot_training - Step 26140: {'lr': 0.00046789023494185855, 'samples': 13384192, 'steps': 26140, 'loss/train': 1.860734462738037}
-03/04/2022 20:10:49 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 20:10:52 - INFO - codeparrot_training - Step 26141: {'lr': 0.0004678876330639978, 'samples': 13384704, 'steps': 26141, 'loss/train': 1.0154024362564087}
-03/04/2022 20:10:55 - INFO - codeparrot_training - Step 26142: {'lr': 0.0004678850310879604, 'samples': 13385216, 'steps': 26142, 'loss/train': 1.0069926977157593}
-03/04/2022 20:10:58 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/04/2022 20:11:01 - INFO - codeparrot_training - Step 26143: {'lr': 0.0004678824290137473, 'samples': 13385728, 'steps': 26143, 'loss/train': 2.7796263694763184}
-03/04/2022 20:11:04 - INFO - codeparrot_training - Step 26144: {'lr': 0.0004678798268413597, 'samples': 13386240, 'steps': 26144, 'loss/train': 1.9897270202636719}
-03/04/2022 20:11:06 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 20:11:09 - INFO - codeparrot_training - Step 26145: {'lr': 0.00046787722457079887, 'samples': 13386752, 'steps': 26145, 'loss/train': 1.4299817085266113}
-03/04/2022 20:11:12 - INFO - codeparrot_training - Step 26146: {'lr': 0.00046787462220206587, 'samples': 13387264, 'steps': 26146, 'loss/train': 2.2799880504608154}
-03/04/2022 20:11:15 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/04/2022 20:11:18 - INFO - codeparrot_training - Step 26147: {'lr': 0.00046787201973516195, 'samples': 13387776, 'steps': 26147, 'loss/train': 3.047572612762451}
-03/04/2022 20:11:21 - INFO - codeparrot_training - Step 26148: {'lr': 0.00046786941717008823, 'samples': 13388288, 'steps': 26148, 'loss/train': 1.9131559133529663}
-03/04/2022 20:11:24 - INFO - codeparrot_training - Step 26149: {'lr': 0.00046786681450684597, 'samples': 13388800, 'steps': 26149, 'loss/train': 2.2449686527252197}
-03/04/2022 20:11:24 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/04/2022 20:11:29 - INFO - codeparrot_training - Step 26150: {'lr': 0.00046786421174543625, 'samples': 13389312, 'steps': 26150, 'loss/train': 2.2072336673736572}
-03/04/2022 20:11:32 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/04/2022 20:11:35 - INFO - codeparrot_training - Step 26151: {'lr': 0.0004678616088858603, 'samples': 13389824, 'steps': 26151, 'loss/train': 1.7114315032958984}
-03/04/2022 20:11:38 - INFO - codeparrot_training - Step 26152: {'lr': 0.0004678590059281193, 'samples': 13390336, 'steps': 26152, 'loss/train': 1.3850131034851074}
-03/04/2022 20:11:41 - INFO - codeparrot_training - Step 26153: {'lr': 0.0004678564028722143, 'samples': 13390848, 'steps': 26153, 'loss/train': 1.811577320098877}
-03/04/2022 20:11:41 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 20:11:46 - INFO - codeparrot_training - Step 26154: {'lr': 0.0004678537997181467, 'samples': 13391360, 'steps': 26154, 'loss/train': 2.5950026512145996}
-03/04/2022 20:11:50 - INFO - codeparrot_training - Step 26155: {'lr': 0.00046785119646591746, 'samples': 13391872, 'steps': 26155, 'loss/train': 1.8332507610321045}
-03/04/2022 20:11:51 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/04/2022 20:11:55 - INFO - codeparrot_training - Step 26156: {'lr': 0.0004678485931155278, 'samples': 13392384, 'steps': 26156, 'loss/train': 1.0187549591064453}
-03/04/2022 20:11:58 - INFO - codeparrot_training - Step 26157: {'lr': 0.000467845989666979, 'samples': 13392896, 'steps': 26157, 'loss/train': 1.6289196014404297}
-03/04/2022 20:11:59 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/04/2022 20:12:03 - INFO - codeparrot_training - Step 26158: {'lr': 0.0004678433861202721, 'samples': 13393408, 'steps': 26158, 'loss/train': 2.2954211235046387}
-03/04/2022 20:12:06 - INFO - codeparrot_training - Step 26159: {'lr': 0.0004678407824754083, 'samples': 13393920, 'steps': 26159, 'loss/train': 1.9970982074737549}
-03/04/2022 20:12:07 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 20:12:12 - INFO - codeparrot_training - Step 26160: {'lr': 0.00046783817873238885, 'samples': 13394432, 'steps': 26160, 'loss/train': 1.2233350276947021}
-03/04/2022 20:12:15 - INFO - codeparrot_training - Step 26161: {'lr': 0.0004678355748912149, 'samples': 13394944, 'steps': 26161, 'loss/train': 2.286184787750244}
-03/04/2022 20:12:16 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/04/2022 20:12:20 - INFO - codeparrot_training - Step 26162: {'lr': 0.0004678329709518876, 'samples': 13395456, 'steps': 26162, 'loss/train': 1.8020402193069458}
-03/04/2022 20:12:23 - INFO - codeparrot_training - Step 26163: {'lr': 0.0004678303669144081, 'samples': 13395968, 'steps': 26163, 'loss/train': 2.1140902042388916}
-03/04/2022 20:12:24 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 20:12:29 - INFO - codeparrot_training - Step 26164: {'lr': 0.0004678277627787776, 'samples': 13396480, 'steps': 26164, 'loss/train': 2.2568657398223877}
-03/04/2022 20:12:32 - INFO - codeparrot_training - Step 26165: {'lr': 0.0004678251585449973, 'samples': 13396992, 'steps': 26165, 'loss/train': 1.4765487909317017}
-03/04/2022 20:12:33 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 20:12:37 - INFO - codeparrot_training - Step 26166: {'lr': 0.0004678225542130683, 'samples': 13397504, 'steps': 26166, 'loss/train': 1.8485795259475708}
-03/04/2022 20:12:40 - INFO - codeparrot_training - Step 26167: {'lr': 0.0004678199497829919, 'samples': 13398016, 'steps': 26167, 'loss/train': 1.8126024007797241}
-03/04/2022 20:12:41 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/04/2022 20:12:45 - INFO - codeparrot_training - Step 26168: {'lr': 0.0004678173452547691, 'samples': 13398528, 'steps': 26168, 'loss/train': 2.309438467025757}
-03/04/2022 20:12:49 - INFO - codeparrot_training - Step 26169: {'lr': 0.00046781474062840126, 'samples': 13399040, 'steps': 26169, 'loss/train': 2.106666326522827}
-03/04/2022 20:12:50 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/04/2022 20:12:54 - INFO - codeparrot_training - Step 26170: {'lr': 0.0004678121359038894, 'samples': 13399552, 'steps': 26170, 'loss/train': 1.9035935401916504}
-03/04/2022 20:12:57 - INFO - codeparrot_training - Step 26171: {'lr': 0.0004678095310812347, 'samples': 13400064, 'steps': 26171, 'loss/train': 2.0352907180786133}
-03/04/2022 20:12:58 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/04/2022 20:13:02 - INFO - codeparrot_training - Step 26172: {'lr': 0.0004678069261604384, 'samples': 13400576, 'steps': 26172, 'loss/train': 1.241420030593872}
-03/04/2022 20:13:06 - INFO - codeparrot_training - Step 26173: {'lr': 0.00046780432114150173, 'samples': 13401088, 'steps': 26173, 'loss/train': 2.4093480110168457}
-03/04/2022 20:13:07 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 20:13:11 - INFO - codeparrot_training - Step 26174: {'lr': 0.0004678017160244258, 'samples': 13401600, 'steps': 26174, 'loss/train': 1.6024255752563477}
-03/04/2022 20:13:14 - INFO - codeparrot_training - Step 26175: {'lr': 0.00046779911080921166, 'samples': 13402112, 'steps': 26175, 'loss/train': 1.385125756263733}
-03/04/2022 20:13:15 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/04/2022 20:13:19 - INFO - codeparrot_training - Step 26176: {'lr': 0.00046779650549586075, 'samples': 13402624, 'steps': 26176, 'loss/train': 2.995293140411377}
-03/04/2022 20:13:23 - INFO - codeparrot_training - Step 26177: {'lr': 0.000467793900084374, 'samples': 13403136, 'steps': 26177, 'loss/train': 1.6859033107757568}
-03/04/2022 20:13:24 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/04/2022 20:13:28 - INFO - codeparrot_training - Step 26178: {'lr': 0.0004677912945747527, 'samples': 13403648, 'steps': 26178, 'loss/train': 1.175668478012085}
-03/04/2022 20:13:31 - INFO - codeparrot_training - Step 26179: {'lr': 0.000467788688966998, 'samples': 13404160, 'steps': 26179, 'loss/train': 0.9898331165313721}
-03/04/2022 20:13:32 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 20:13:36 - INFO - codeparrot_training - Step 26180: {'lr': 0.00046778608326111104, 'samples': 13404672, 'steps': 26180, 'loss/train': 0.23517422378063202}
-03/04/2022 20:13:40 - INFO - codeparrot_training - Step 26181: {'lr': 0.00046778347745709317, 'samples': 13405184, 'steps': 26181, 'loss/train': 2.474379062652588}
-03/04/2022 20:13:41 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/04/2022 20:13:45 - INFO - codeparrot_training - Step 26182: {'lr': 0.0004677808715549453, 'samples': 13405696, 'steps': 26182, 'loss/train': 2.048320770263672}
-03/04/2022 20:13:48 - INFO - codeparrot_training - Step 26183: {'lr': 0.0004677782655546687, 'samples': 13406208, 'steps': 26183, 'loss/train': 2.0141658782958984}
-03/04/2022 20:13:49 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 20:13:53 - INFO - codeparrot_training - Step 26184: {'lr': 0.00046777565945626463, 'samples': 13406720, 'steps': 26184, 'loss/train': 2.0025410652160645}
-03/04/2022 20:13:57 - INFO - codeparrot_training - Step 26185: {'lr': 0.0004677730532597343, 'samples': 13407232, 'steps': 26185, 'loss/train': 1.4090379476547241}
-03/04/2022 20:13:57 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/04/2022 20:14:02 - INFO - codeparrot_training - Step 26186: {'lr': 0.00046777044696507867, 'samples': 13407744, 'steps': 26186, 'loss/train': 2.3672497272491455}
-03/04/2022 20:14:05 - INFO - codeparrot_training - Step 26187: {'lr': 0.00046776784057229906, 'samples': 13408256, 'steps': 26187, 'loss/train': 2.6451077461242676}
-03/04/2022 20:14:07 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/04/2022 20:14:11 - INFO - codeparrot_training - Step 26188: {'lr': 0.00046776523408139666, 'samples': 13408768, 'steps': 26188, 'loss/train': 2.16650128364563}
-03/04/2022 20:14:14 - INFO - codeparrot_training - Step 26189: {'lr': 0.0004677626274923726, 'samples': 13409280, 'steps': 26189, 'loss/train': 1.4568591117858887}
-03/04/2022 20:14:15 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/04/2022 20:14:19 - INFO - codeparrot_training - Step 26190: {'lr': 0.000467760020805228, 'samples': 13409792, 'steps': 26190, 'loss/train': 3.015784502029419}
-03/04/2022 20:14:22 - INFO - codeparrot_training - Step 26191: {'lr': 0.0004677574140199642, 'samples': 13410304, 'steps': 26191, 'loss/train': 2.0492053031921387}
-03/04/2022 20:14:24 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/04/2022 20:14:27 - INFO - codeparrot_training - Step 26192: {'lr': 0.00046775480713658215, 'samples': 13410816, 'steps': 26192, 'loss/train': 1.7014299631118774}
-03/04/2022 20:14:31 - INFO - codeparrot_training - Step 26193: {'lr': 0.00046775220015508325, 'samples': 13411328, 'steps': 26193, 'loss/train': 1.665052890777588}
-03/04/2022 20:14:32 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/04/2022 20:14:36 - INFO - codeparrot_training - Step 26194: {'lr': 0.0004677495930754685, 'samples': 13411840, 'steps': 26194, 'loss/train': 2.1564548015594482}
-03/04/2022 20:14:39 - INFO - codeparrot_training - Step 26195: {'lr': 0.0004677469858977391, 'samples': 13412352, 'steps': 26195, 'loss/train': 1.7374427318572998}
-03/04/2022 20:14:41 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/04/2022 20:14:44 - INFO - codeparrot_training - Step 26196: {'lr': 0.00046774437862189634, 'samples': 13412864, 'steps': 26196, 'loss/train': 1.7755687236785889}
-03/04/2022 20:14:47 - INFO - codeparrot_training - Step 26197: {'lr': 0.00046774177124794136, 'samples': 13413376, 'steps': 26197, 'loss/train': 2.2434895038604736}
-03/04/2022 20:14:49 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/04/2022 20:14:53 - INFO - codeparrot_training - Step 26198: {'lr': 0.00046773916377587524, 'samples': 13413888, 'steps': 26198, 'loss/train': 1.881919264793396}
-03/04/2022 20:14:56 - INFO - codeparrot_training - Step 26199: {'lr': 0.00046773655620569924, 'samples': 13414400, 'steps': 26199, 'loss/train': 2.724806785583496}
-03/04/2022 20:14:58 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 20:15:01 - INFO - codeparrot_training - Step 26200: {'lr': 0.0004677339485374145, 'samples': 13414912, 'steps': 26200, 'loss/train': 1.735425591468811}
-03/04/2022 20:15:05 - INFO - codeparrot_training - Step 26201: {'lr': 0.00046773134077102217, 'samples': 13415424, 'steps': 26201, 'loss/train': 1.7192927598953247}
-03/04/2022 20:15:07 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/04/2022 20:15:10 - INFO - codeparrot_training - Step 26202: {'lr': 0.00046772873290652344, 'samples': 13415936, 'steps': 26202, 'loss/train': 1.2810925245285034}
-03/04/2022 20:15:13 - INFO - codeparrot_training - Step 26203: {'lr': 0.0004677261249439196, 'samples': 13416448, 'steps': 26203, 'loss/train': 1.9988727569580078}
-03/04/2022 20:15:15 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 20:15:18 - INFO - codeparrot_training - Step 26204: {'lr': 0.0004677235168832117, 'samples': 13416960, 'steps': 26204, 'loss/train': 1.6794885396957397}
-03/04/2022 20:15:21 - INFO - codeparrot_training - Step 26205: {'lr': 0.0004677209087244009, 'samples': 13417472, 'steps': 26205, 'loss/train': 1.7517313957214355}
-03/04/2022 20:15:23 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 20:15:27 - INFO - codeparrot_training - Step 26206: {'lr': 0.0004677183004674884, 'samples': 13417984, 'steps': 26206, 'loss/train': 1.9873133897781372}
-03/04/2022 20:15:30 - INFO - codeparrot_training - Step 26207: {'lr': 0.00046771569211247546, 'samples': 13418496, 'steps': 26207, 'loss/train': 1.7855371236801147}
-03/04/2022 20:15:32 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/04/2022 20:15:35 - INFO - codeparrot_training - Step 26208: {'lr': 0.00046771308365936315, 'samples': 13419008, 'steps': 26208, 'loss/train': 6.60589599609375}
-03/04/2022 20:15:38 - INFO - codeparrot_training - Step 26209: {'lr': 0.00046771047510815267, 'samples': 13419520, 'steps': 26209, 'loss/train': 0.8584921956062317}
-03/04/2022 20:15:41 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/04/2022 20:15:44 - INFO - codeparrot_training - Step 26210: {'lr': 0.0004677078664588452, 'samples': 13420032, 'steps': 26210, 'loss/train': 1.4996936321258545}
-03/04/2022 20:15:47 - INFO - codeparrot_training - Step 26211: {'lr': 0.000467705257711442, 'samples': 13420544, 'steps': 26211, 'loss/train': 1.922645092010498}
-03/04/2022 20:15:49 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 20:15:52 - INFO - codeparrot_training - Step 26212: {'lr': 0.0004677026488659441, 'samples': 13421056, 'steps': 26212, 'loss/train': 1.4073097705841064}
-03/04/2022 20:15:55 - INFO - codeparrot_training - Step 26213: {'lr': 0.0004677000399223528, 'samples': 13421568, 'steps': 26213, 'loss/train': 1.3810511827468872}
-03/04/2022 20:15:58 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/04/2022 20:16:01 - INFO - codeparrot_training - Step 26214: {'lr': 0.0004676974308806692, 'samples': 13422080, 'steps': 26214, 'loss/train': 2.0653762817382812}
-03/04/2022 20:16:04 - INFO - codeparrot_training - Step 26215: {'lr': 0.00046769482174089446, 'samples': 13422592, 'steps': 26215, 'loss/train': 1.5394554138183594}
-03/04/2022 20:16:06 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/04/2022 20:16:09 - INFO - codeparrot_training - Step 26216: {'lr': 0.00046769221250302984, 'samples': 13423104, 'steps': 26216, 'loss/train': 2.15212345123291}
-03/04/2022 20:16:12 - INFO - codeparrot_training - Step 26217: {'lr': 0.0004676896031670764, 'samples': 13423616, 'steps': 26217, 'loss/train': 3.625394582748413}
-03/04/2022 20:16:15 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/04/2022 20:16:17 - INFO - codeparrot_training - Step 26218: {'lr': 0.00046768699373303546, 'samples': 13424128, 'steps': 26218, 'loss/train': 1.6522254943847656}
-03/04/2022 20:16:21 - INFO - codeparrot_training - Step 26219: {'lr': 0.00046768438420090807, 'samples': 13424640, 'steps': 26219, 'loss/train': 1.5275942087173462}
-03/04/2022 20:16:23 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/04/2022 20:16:26 - INFO - codeparrot_training - Step 26220: {'lr': 0.0004676817745706955, 'samples': 13425152, 'steps': 26220, 'loss/train': 1.2405812740325928}
-03/04/2022 20:16:29 - INFO - codeparrot_training - Step 26221: {'lr': 0.0004676791648423989, 'samples': 13425664, 'steps': 26221, 'loss/train': 2.0045218467712402}
-03/04/2022 20:16:31 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/04/2022 20:16:34 - INFO - codeparrot_training - Step 26222: {'lr': 0.00046767655501601935, 'samples': 13426176, 'steps': 26222, 'loss/train': 1.1902238130569458}
-03/04/2022 20:16:37 - INFO - codeparrot_training - Step 26223: {'lr': 0.0004676739450915581, 'samples': 13426688, 'steps': 26223, 'loss/train': 1.1171594858169556}
-03/04/2022 20:16:40 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/04/2022 20:16:43 - INFO - codeparrot_training - Step 26224: {'lr': 0.0004676713350690164, 'samples': 13427200, 'steps': 26224, 'loss/train': 1.0749845504760742}
-03/04/2022 20:16:46 - INFO - codeparrot_training - Step 26225: {'lr': 0.0004676687249483953, 'samples': 13427712, 'steps': 26225, 'loss/train': 0.5352584719657898}
-03/04/2022 20:16:48 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/04/2022 20:16:52 - INFO - codeparrot_training - Step 26226: {'lr': 0.0004676661147296961, 'samples': 13428224, 'steps': 26226, 'loss/train': 1.7981233596801758}
-03/04/2022 20:16:55 - INFO - codeparrot_training - Step 26227: {'lr': 0.00046766350441291985, 'samples': 13428736, 'steps': 26227, 'loss/train': 2.2609095573425293}
-03/04/2022 20:16:58 - INFO - codeparrot_training - Step 26228: {'lr': 0.00046766089399806775, 'samples': 13429248, 'steps': 26228, 'loss/train': 0.5924762487411499}
-03/04/2022 20:16:59 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/04/2022 20:17:04 - INFO - codeparrot_training - Step 26229: {'lr': 0.0004676582834851411, 'samples': 13429760, 'steps': 26229, 'loss/train': 2.2630815505981445}
-03/04/2022 20:17:07 - INFO - codeparrot_training - Step 26230: {'lr': 0.0004676556728741409, 'samples': 13430272, 'steps': 26230, 'loss/train': 1.156329870223999}
-03/04/2022 20:17:09 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 20:17:12 - INFO - codeparrot_training - Step 26231: {'lr': 0.0004676530621650685, 'samples': 13430784, 'steps': 26231, 'loss/train': 2.157087564468384}
-03/04/2022 20:17:15 - INFO - codeparrot_training - Step 26232: {'lr': 0.00046765045135792495, 'samples': 13431296, 'steps': 26232, 'loss/train': 1.550511360168457}
-03/04/2022 20:17:17 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/04/2022 20:17:21 - INFO - codeparrot_training - Step 26233: {'lr': 0.00046764784045271146, 'samples': 13431808, 'steps': 26233, 'loss/train': 1.531336784362793}
-03/04/2022 20:17:24 - INFO - codeparrot_training - Step 26234: {'lr': 0.0004676452294494292, 'samples': 13432320, 'steps': 26234, 'loss/train': 1.3884377479553223}
-03/04/2022 20:17:26 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/04/2022 20:17:29 - INFO - codeparrot_training - Step 26235: {'lr': 0.00046764261834807944, 'samples': 13432832, 'steps': 26235, 'loss/train': 2.040224075317383}
-03/04/2022 20:17:32 - INFO - codeparrot_training - Step 26236: {'lr': 0.0004676400071486632, 'samples': 13433344, 'steps': 26236, 'loss/train': 1.316050410270691}
-03/04/2022 20:17:34 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/04/2022 20:17:37 - INFO - codeparrot_training - Step 26237: {'lr': 0.0004676373958511817, 'samples': 13433856, 'steps': 26237, 'loss/train': 1.649372935295105}
-03/04/2022 20:17:41 - INFO - codeparrot_training - Step 26238: {'lr': 0.00046763478445563617, 'samples': 13434368, 'steps': 26238, 'loss/train': 2.3910179138183594}
-03/04/2022 20:17:43 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 20:17:46 - INFO - codeparrot_training - Step 26239: {'lr': 0.0004676321729620278, 'samples': 13434880, 'steps': 26239, 'loss/train': 1.8172529935836792}
-03/04/2022 20:17:49 - INFO - codeparrot_training - Step 26240: {'lr': 0.0004676295613703577, 'samples': 13435392, 'steps': 26240, 'loss/train': 2.072261095046997}
-03/04/2022 20:17:51 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 20:17:54 - INFO - codeparrot_training - Step 26241: {'lr': 0.00046762694968062706, 'samples': 13435904, 'steps': 26241, 'loss/train': 1.994399070739746}
-03/04/2022 20:17:58 - INFO - codeparrot_training - Step 26242: {'lr': 0.0004676243378928371, 'samples': 13436416, 'steps': 26242, 'loss/train': 2.1013505458831787}
-03/04/2022 20:17:59 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 20:18:03 - INFO - codeparrot_training - Step 26243: {'lr': 0.000467621726006989, 'samples': 13436928, 'steps': 26243, 'loss/train': 1.686649203300476}
-03/04/2022 20:18:06 - INFO - codeparrot_training - Step 26244: {'lr': 0.0004676191140230839, 'samples': 13437440, 'steps': 26244, 'loss/train': 0.7103327512741089}
-03/04/2022 20:18:08 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/04/2022 20:18:12 - INFO - codeparrot_training - Step 26245: {'lr': 0.0004676165019411229, 'samples': 13437952, 'steps': 26245, 'loss/train': 2.7181527614593506}
-03/04/2022 20:18:15 - INFO - codeparrot_training - Step 26246: {'lr': 0.00046761388976110737, 'samples': 13438464, 'steps': 26246, 'loss/train': 2.2713632583618164}
-03/04/2022 20:18:17 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 20:18:20 - INFO - codeparrot_training - Step 26247: {'lr': 0.00046761127748303833, 'samples': 13438976, 'steps': 26247, 'loss/train': 0.38205447793006897}
-03/04/2022 20:18:23 - INFO - codeparrot_training - Step 26248: {'lr': 0.000467608665106917, 'samples': 13439488, 'steps': 26248, 'loss/train': 1.0538963079452515}
-03/04/2022 20:18:26 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 20:18:29 - INFO - codeparrot_training - Step 26249: {'lr': 0.0004676060526327446, 'samples': 13440000, 'steps': 26249, 'loss/train': 2.1698355674743652}
-03/04/2022 20:18:32 - INFO - codeparrot_training - Step 26250: {'lr': 0.00046760344006052223, 'samples': 13440512, 'steps': 26250, 'loss/train': 2.1941206455230713}
-03/04/2022 20:18:35 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/04/2022 20:18:37 - INFO - codeparrot_training - Step 26251: {'lr': 0.00046760082739025113, 'samples': 13441024, 'steps': 26251, 'loss/train': 2.372011184692383}
-03/04/2022 20:18:40 - INFO - codeparrot_training - Step 26252: {'lr': 0.0004675982146219324, 'samples': 13441536, 'steps': 26252, 'loss/train': 1.7368398904800415}
-03/04/2022 20:18:43 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 20:18:45 - INFO - codeparrot_training - Step 26253: {'lr': 0.00046759560175556737, 'samples': 13442048, 'steps': 26253, 'loss/train': 2.2754759788513184}
-03/04/2022 20:18:49 - INFO - codeparrot_training - Step 26254: {'lr': 0.0004675929887911571, 'samples': 13442560, 'steps': 26254, 'loss/train': 1.985810399055481}
-03/04/2022 20:18:51 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/04/2022 20:18:54 - INFO - codeparrot_training - Step 26255: {'lr': 0.0004675903757287027, 'samples': 13443072, 'steps': 26255, 'loss/train': 1.289853811264038}
-03/04/2022 20:18:58 - INFO - codeparrot_training - Step 26256: {'lr': 0.0004675877625682055, 'samples': 13443584, 'steps': 26256, 'loss/train': 0.40469056367874146}
-03/04/2022 20:19:01 - INFO - codeparrot_training - Step 26257: {'lr': 0.00046758514930966664, 'samples': 13444096, 'steps': 26257, 'loss/train': 1.4632779359817505}
-03/04/2022 20:19:01 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/04/2022 20:19:06 - INFO - codeparrot_training - Step 26258: {'lr': 0.0004675825359530872, 'samples': 13444608, 'steps': 26258, 'loss/train': 1.2530070543289185}
-03/04/2022 20:19:09 - INFO - codeparrot_training - Step 26259: {'lr': 0.0004675799224984685, 'samples': 13445120, 'steps': 26259, 'loss/train': 1.3655645847320557}
-03/04/2022 20:19:10 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/04/2022 20:19:14 - INFO - codeparrot_training - Step 26260: {'lr': 0.00046757730894581164, 'samples': 13445632, 'steps': 26260, 'loss/train': 1.6445448398590088}
-03/04/2022 20:19:17 - INFO - codeparrot_training - Step 26261: {'lr': 0.00046757469529511777, 'samples': 13446144, 'steps': 26261, 'loss/train': 2.1156513690948486}
-03/04/2022 20:19:18 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/04/2022 20:19:23 - INFO - codeparrot_training - Step 26262: {'lr': 0.0004675720815463881, 'samples': 13446656, 'steps': 26262, 'loss/train': 2.049163579940796}
-03/04/2022 20:19:26 - INFO - codeparrot_training - Step 26263: {'lr': 0.00046756946769962375, 'samples': 13447168, 'steps': 26263, 'loss/train': 0.6978371143341064}
-03/04/2022 20:19:27 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 20:19:31 - INFO - codeparrot_training - Step 26264: {'lr': 0.000467566853754826, 'samples': 13447680, 'steps': 26264, 'loss/train': 1.615500569343567}
-03/04/2022 20:19:34 - INFO - codeparrot_training - Step 26265: {'lr': 0.00046756423971199603, 'samples': 13448192, 'steps': 26265, 'loss/train': 2.5839827060699463}
-03/04/2022 20:19:35 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/04/2022 20:19:40 - INFO - codeparrot_training - Step 26266: {'lr': 0.0004675616255711349, 'samples': 13448704, 'steps': 26266, 'loss/train': 2.0033435821533203}
-03/04/2022 20:19:43 - INFO - codeparrot_training - Step 26267: {'lr': 0.0004675590113322439, 'samples': 13449216, 'steps': 26267, 'loss/train': 1.0274652242660522}
-03/04/2022 20:19:43 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/04/2022 20:19:48 - INFO - codeparrot_training - Step 26268: {'lr': 0.00046755639699532414, 'samples': 13449728, 'steps': 26268, 'loss/train': 1.7288697957992554}
-03/04/2022 20:19:51 - INFO - codeparrot_training - Step 26269: {'lr': 0.00046755378256037685, 'samples': 13450240, 'steps': 26269, 'loss/train': 2.107079267501831}
-03/04/2022 20:19:52 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/04/2022 20:19:56 - INFO - codeparrot_training - Step 26270: {'lr': 0.00046755116802740316, 'samples': 13450752, 'steps': 26270, 'loss/train': 2.227278470993042}
-03/04/2022 20:20:00 - INFO - codeparrot_training - Step 26271: {'lr': 0.00046754855339640436, 'samples': 13451264, 'steps': 26271, 'loss/train': 1.3240013122558594}
-03/04/2022 20:20:00 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/04/2022 20:20:05 - INFO - codeparrot_training - Step 26272: {'lr': 0.00046754593866738144, 'samples': 13451776, 'steps': 26272, 'loss/train': 0.5232560634613037}
-03/04/2022 20:20:08 - INFO - codeparrot_training - Step 26273: {'lr': 0.0004675433238403357, 'samples': 13452288, 'steps': 26273, 'loss/train': 1.8712949752807617}
-03/04/2022 20:20:10 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/04/2022 20:20:13 - INFO - codeparrot_training - Step 26274: {'lr': 0.0004675407089152683, 'samples': 13452800, 'steps': 26274, 'loss/train': 2.0998947620391846}
-03/04/2022 20:20:17 - INFO - codeparrot_training - Step 26275: {'lr': 0.00046753809389218036, 'samples': 13453312, 'steps': 26275, 'loss/train': 1.2897672653198242}
-03/04/2022 20:20:18 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/04/2022 20:20:22 - INFO - codeparrot_training - Step 26276: {'lr': 0.0004675354787710732, 'samples': 13453824, 'steps': 26276, 'loss/train': 2.0904479026794434}
-03/04/2022 20:20:25 - INFO - codeparrot_training - Step 26277: {'lr': 0.0004675328635519479, 'samples': 13454336, 'steps': 26277, 'loss/train': 1.9342377185821533}
-03/04/2022 20:20:27 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/04/2022 20:20:31 - INFO - codeparrot_training - Step 26278: {'lr': 0.0004675302482348056, 'samples': 13454848, 'steps': 26278, 'loss/train': 1.812187910079956}
-03/04/2022 20:20:34 - INFO - codeparrot_training - Step 26279: {'lr': 0.00046752763281964757, 'samples': 13455360, 'steps': 26279, 'loss/train': 2.391221761703491}
-03/04/2022 20:20:37 - INFO - codeparrot_training - Step 26280: {'lr': 0.0004675250173064749, 'samples': 13455872, 'steps': 26280, 'loss/train': 3.3023781776428223}
-03/04/2022 20:20:37 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/04/2022 20:20:42 - INFO - codeparrot_training - Step 26281: {'lr': 0.0004675224016952888, 'samples': 13456384, 'steps': 26281, 'loss/train': 1.9747198820114136}
-03/04/2022 20:20:45 - INFO - codeparrot_training - Step 26282: {'lr': 0.00046751978598609056, 'samples': 13456896, 'steps': 26282, 'loss/train': 1.89765202999115}
-03/04/2022 20:20:46 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/04/2022 20:20:51 - INFO - codeparrot_training - Step 26283: {'lr': 0.00046751717017888116, 'samples': 13457408, 'steps': 26283, 'loss/train': 2.4452362060546875}
-03/04/2022 20:20:54 - INFO - codeparrot_training - Step 26284: {'lr': 0.00046751455427366194, 'samples': 13457920, 'steps': 26284, 'loss/train': 2.1030516624450684}
-03/04/2022 20:20:54 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 20:20:59 - INFO - codeparrot_training - Step 26285: {'lr': 0.00046751193827043405, 'samples': 13458432, 'steps': 26285, 'loss/train': 1.8388447761535645}
-03/04/2022 20:21:02 - INFO - codeparrot_training - Step 26286: {'lr': 0.0004675093221691985, 'samples': 13458944, 'steps': 26286, 'loss/train': 2.0483851432800293}
-03/04/2022 20:21:02 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/04/2022 20:21:08 - INFO - codeparrot_training - Step 26287: {'lr': 0.0004675067059699567, 'samples': 13459456, 'steps': 26287, 'loss/train': 0.9844334125518799}
-03/04/2022 20:21:11 - INFO - codeparrot_training - Step 26288: {'lr': 0.00046750408967270973, 'samples': 13459968, 'steps': 26288, 'loss/train': 1.2988200187683105}
-03/04/2022 20:21:11 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/04/2022 20:21:16 - INFO - codeparrot_training - Step 26289: {'lr': 0.0004675014732774588, 'samples': 13460480, 'steps': 26289, 'loss/train': 1.4580541849136353}
-03/04/2022 20:21:19 - INFO - codeparrot_training - Step 26290: {'lr': 0.000467498856784205, 'samples': 13460992, 'steps': 26290, 'loss/train': 1.080168604850769}
-03/04/2022 20:21:20 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/04/2022 20:21:24 - INFO - codeparrot_training - Step 26291: {'lr': 0.0004674962401929496, 'samples': 13461504, 'steps': 26291, 'loss/train': 2.468744993209839}
-03/04/2022 20:21:28 - INFO - codeparrot_training - Step 26292: {'lr': 0.0004674936235036938, 'samples': 13462016, 'steps': 26292, 'loss/train': 0.6624350547790527}
-03/04/2022 20:21:29 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 20:21:33 - INFO - codeparrot_training - Step 26293: {'lr': 0.00046749100671643866, 'samples': 13462528, 'steps': 26293, 'loss/train': 2.2161104679107666}
-03/04/2022 20:21:36 - INFO - codeparrot_training - Step 26294: {'lr': 0.00046748838983118546, 'samples': 13463040, 'steps': 26294, 'loss/train': 2.5154502391815186}
-03/04/2022 20:21:37 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 20:21:41 - INFO - codeparrot_training - Step 26295: {'lr': 0.00046748577284793535, 'samples': 13463552, 'steps': 26295, 'loss/train': 1.425231695175171}
-03/04/2022 20:21:45 - INFO - codeparrot_training - Step 26296: {'lr': 0.00046748315576668946, 'samples': 13464064, 'steps': 26296, 'loss/train': 1.9454972743988037}
-03/04/2022 20:21:46 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/04/2022 20:21:50 - INFO - codeparrot_training - Step 26297: {'lr': 0.0004674805385874491, 'samples': 13464576, 'steps': 26297, 'loss/train': 2.0682132244110107}
-03/04/2022 20:21:53 - INFO - codeparrot_training - Step 26298: {'lr': 0.0004674779213102153, 'samples': 13465088, 'steps': 26298, 'loss/train': 1.9246418476104736}
-03/04/2022 20:21:54 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 20:21:58 - INFO - codeparrot_training - Step 26299: {'lr': 0.00046747530393498934, 'samples': 13465600, 'steps': 26299, 'loss/train': 1.5850003957748413}
-03/04/2022 20:22:01 - INFO - codeparrot_training - Step 26300: {'lr': 0.0004674726864617723, 'samples': 13466112, 'steps': 26300, 'loss/train': 2.080498456954956}
-03/04/2022 20:22:07 - INFO - codeparrot_training - Step 26301: {'lr': 0.00046747006889056556, 'samples': 13466624, 'steps': 26301, 'loss/train': 2.675243616104126}
-03/04/2022 20:22:10 - INFO - codeparrot_training - Step 26302: {'lr': 0.00046746745122137, 'samples': 13467136, 'steps': 26302, 'loss/train': 1.72771418094635}
-03/04/2022 20:22:11 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/04/2022 20:22:15 - INFO - codeparrot_training - Step 26303: {'lr': 0.000467464833454187, 'samples': 13467648, 'steps': 26303, 'loss/train': 2.593093156814575}
-03/04/2022 20:22:18 - INFO - codeparrot_training - Step 26304: {'lr': 0.0004674622155890178, 'samples': 13468160, 'steps': 26304, 'loss/train': 1.752964735031128}
-03/04/2022 20:22:20 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/04/2022 20:22:24 - INFO - codeparrot_training - Step 26305: {'lr': 0.00046745959762586344, 'samples': 13468672, 'steps': 26305, 'loss/train': 1.8876134157180786}
-03/04/2022 20:22:27 - INFO - codeparrot_training - Step 26306: {'lr': 0.0004674569795647251, 'samples': 13469184, 'steps': 26306, 'loss/train': 1.6933643817901611}
-03/04/2022 20:22:28 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/04/2022 20:22:32 - INFO - codeparrot_training - Step 26307: {'lr': 0.00046745436140560397, 'samples': 13469696, 'steps': 26307, 'loss/train': 2.034882068634033}
-03/04/2022 20:22:35 - INFO - codeparrot_training - Step 26308: {'lr': 0.00046745174314850136, 'samples': 13470208, 'steps': 26308, 'loss/train': 2.1308157444000244}
-03/04/2022 20:22:37 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/04/2022 20:22:41 - INFO - codeparrot_training - Step 26309: {'lr': 0.00046744912479341826, 'samples': 13470720, 'steps': 26309, 'loss/train': 2.1435434818267822}
-03/04/2022 20:22:44 - INFO - codeparrot_training - Step 26310: {'lr': 0.00046744650634035603, 'samples': 13471232, 'steps': 26310, 'loss/train': 1.6730660200119019}
-03/04/2022 20:22:45 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 20:22:49 - INFO - codeparrot_training - Step 26311: {'lr': 0.0004674438877893157, 'samples': 13471744, 'steps': 26311, 'loss/train': 1.6656420230865479}
-03/04/2022 20:22:52 - INFO - codeparrot_training - Step 26312: {'lr': 0.0004674412691402985, 'samples': 13472256, 'steps': 26312, 'loss/train': 2.204796552658081}
-03/04/2022 20:22:53 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 20:22:57 - INFO - codeparrot_training - Step 26313: {'lr': 0.00046743865039330565, 'samples': 13472768, 'steps': 26313, 'loss/train': 1.7796519994735718}
-03/04/2022 20:23:01 - INFO - codeparrot_training - Step 26314: {'lr': 0.00046743603154833827, 'samples': 13473280, 'steps': 26314, 'loss/train': 1.4883044958114624}
-03/04/2022 20:23:02 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/04/2022 20:23:06 - INFO - codeparrot_training - Step 26315: {'lr': 0.00046743341260539756, 'samples': 13473792, 'steps': 26315, 'loss/train': 1.938624382019043}
-03/04/2022 20:23:09 - INFO - codeparrot_training - Step 26316: {'lr': 0.00046743079356448476, 'samples': 13474304, 'steps': 26316, 'loss/train': 1.7916821241378784}
-03/04/2022 20:23:11 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/04/2022 20:23:14 - INFO - codeparrot_training - Step 26317: {'lr': 0.000467428174425601, 'samples': 13474816, 'steps': 26317, 'loss/train': 0.30272534489631653}
-03/04/2022 20:23:18 - INFO - codeparrot_training - Step 26318: {'lr': 0.0004674255551887474, 'samples': 13475328, 'steps': 26318, 'loss/train': 1.7239028215408325}
-03/04/2022 20:23:19 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 20:23:23 - INFO - codeparrot_training - Step 26319: {'lr': 0.0004674229358539253, 'samples': 13475840, 'steps': 26319, 'loss/train': 1.121082067489624}
-03/04/2022 20:23:26 - INFO - codeparrot_training - Step 26320: {'lr': 0.0004674203164211357, 'samples': 13476352, 'steps': 26320, 'loss/train': 2.201213836669922}
-03/04/2022 20:23:27 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/04/2022 20:23:31 - INFO - codeparrot_training - Step 26321: {'lr': 0.00046741769689037985, 'samples': 13476864, 'steps': 26321, 'loss/train': 2.1501524448394775}
-03/04/2022 20:23:35 - INFO - codeparrot_training - Step 26322: {'lr': 0.0004674150772616589, 'samples': 13477376, 'steps': 26322, 'loss/train': 1.5515556335449219}
-03/04/2022 20:23:36 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/04/2022 20:23:40 - INFO - codeparrot_training - Step 26323: {'lr': 0.0004674124575349742, 'samples': 13477888, 'steps': 26323, 'loss/train': 1.6722420454025269}
-03/04/2022 20:23:43 - INFO - codeparrot_training - Step 26324: {'lr': 0.00046740983771032674, 'samples': 13478400, 'steps': 26324, 'loss/train': 2.2152788639068604}
-03/04/2022 20:23:45 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/04/2022 20:23:48 - INFO - codeparrot_training - Step 26325: {'lr': 0.0004674072177877178, 'samples': 13478912, 'steps': 26325, 'loss/train': 1.9207843542099}
-03/04/2022 20:23:52 - INFO - codeparrot_training - Step 26326: {'lr': 0.0004674045977671484, 'samples': 13479424, 'steps': 26326, 'loss/train': 1.6756205558776855}
-03/04/2022 20:23:53 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 20:23:57 - INFO - codeparrot_training - Step 26327: {'lr': 0.00046740197764862, 'samples': 13479936, 'steps': 26327, 'loss/train': 1.6817835569381714}
-03/04/2022 20:24:00 - INFO - codeparrot_training - Step 26328: {'lr': 0.00046739935743213344, 'samples': 13480448, 'steps': 26328, 'loss/train': 1.5723381042480469}
-03/04/2022 20:24:02 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 20:24:05 - INFO - codeparrot_training - Step 26329: {'lr': 0.00046739673711769026, 'samples': 13480960, 'steps': 26329, 'loss/train': 1.9467318058013916}
-03/04/2022 20:24:08 - INFO - codeparrot_training - Step 26330: {'lr': 0.0004673941167052914, 'samples': 13481472, 'steps': 26330, 'loss/train': 1.6885074377059937}
-03/04/2022 20:24:10 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/04/2022 20:24:14 - INFO - codeparrot_training - Step 26331: {'lr': 0.0004673914961949381, 'samples': 13481984, 'steps': 26331, 'loss/train': 2.7198257446289062}
-03/04/2022 20:24:17 - INFO - codeparrot_training - Step 26332: {'lr': 0.0004673888755866316, 'samples': 13482496, 'steps': 26332, 'loss/train': 2.0507190227508545}
-03/04/2022 20:24:19 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/04/2022 20:24:22 - INFO - codeparrot_training - Step 26333: {'lr': 0.0004673862548803729, 'samples': 13483008, 'steps': 26333, 'loss/train': 2.0036942958831787}
-03/04/2022 20:24:25 - INFO - codeparrot_training - Step 26334: {'lr': 0.0004673836340761634, 'samples': 13483520, 'steps': 26334, 'loss/train': 1.7425588369369507}
-03/04/2022 20:24:27 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/04/2022 20:24:31 - INFO - codeparrot_training - Step 26335: {'lr': 0.00046738101317400415, 'samples': 13484032, 'steps': 26335, 'loss/train': 1.3567665815353394}
-03/04/2022 20:24:34 - INFO - codeparrot_training - Step 26336: {'lr': 0.00046737839217389645, 'samples': 13484544, 'steps': 26336, 'loss/train': 1.6014015674591064}
-03/04/2022 20:24:36 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/04/2022 20:24:39 - INFO - codeparrot_training - Step 26337: {'lr': 0.0004673757710758413, 'samples': 13485056, 'steps': 26337, 'loss/train': 1.9751358032226562}
-03/04/2022 20:24:42 - INFO - codeparrot_training - Step 26338: {'lr': 0.00046737314987984, 'samples': 13485568, 'steps': 26338, 'loss/train': 1.940842628479004}
-03/04/2022 20:24:44 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/04/2022 20:24:47 - INFO - codeparrot_training - Step 26339: {'lr': 0.0004673705285858938, 'samples': 13486080, 'steps': 26339, 'loss/train': 1.567187786102295}
-03/04/2022 20:24:51 - INFO - codeparrot_training - Step 26340: {'lr': 0.00046736790719400373, 'samples': 13486592, 'steps': 26340, 'loss/train': 2.185310125350952}
-03/04/2022 20:24:52 - INFO - codeparrot_training - Skipping example with length 86 (seq_length=1024)
-03/04/2022 20:24:56 - INFO - codeparrot_training - Step 26341: {'lr': 0.000467365285704171, 'samples': 13487104, 'steps': 26341, 'loss/train': 1.4059953689575195}
-03/04/2022 20:24:59 - INFO - codeparrot_training - Step 26342: {'lr': 0.00046736266411639694, 'samples': 13487616, 'steps': 26342, 'loss/train': 1.407268762588501}
-03/04/2022 20:25:00 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/04/2022 20:25:04 - INFO - codeparrot_training - Step 26343: {'lr': 0.00046736004243068255, 'samples': 13488128, 'steps': 26343, 'loss/train': 2.755145311355591}
-03/04/2022 20:25:07 - INFO - codeparrot_training - Step 26344: {'lr': 0.00046735742064702904, 'samples': 13488640, 'steps': 26344, 'loss/train': 1.3670215606689453}
-03/04/2022 20:25:09 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 20:25:13 - INFO - codeparrot_training - Step 26345: {'lr': 0.00046735479876543765, 'samples': 13489152, 'steps': 26345, 'loss/train': 1.0788187980651855}
-03/04/2022 20:25:16 - INFO - codeparrot_training - Step 26346: {'lr': 0.00046735217678590957, 'samples': 13489664, 'steps': 26346, 'loss/train': 0.4471122622489929}
-03/04/2022 20:25:17 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 20:25:21 - INFO - codeparrot_training - Step 26347: {'lr': 0.00046734955470844594, 'samples': 13490176, 'steps': 26347, 'loss/train': 2.2048699855804443}
-03/04/2022 20:25:24 - INFO - codeparrot_training - Step 26348: {'lr': 0.00046734693253304795, 'samples': 13490688, 'steps': 26348, 'loss/train': 0.21905824542045593}
-03/04/2022 20:25:26 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/04/2022 20:25:29 - INFO - codeparrot_training - Step 26349: {'lr': 0.0004673443102597168, 'samples': 13491200, 'steps': 26349, 'loss/train': 1.931807041168213}
-03/04/2022 20:25:33 - INFO - codeparrot_training - Step 26350: {'lr': 0.00046734168788845363, 'samples': 13491712, 'steps': 26350, 'loss/train': 2.1042449474334717}
-03/04/2022 20:25:34 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/04/2022 20:25:38 - INFO - codeparrot_training - Step 26351: {'lr': 0.00046733906541925963, 'samples': 13492224, 'steps': 26351, 'loss/train': 1.430544376373291}
-03/04/2022 20:25:41 - INFO - codeparrot_training - Step 26352: {'lr': 0.00046733644285213604, 'samples': 13492736, 'steps': 26352, 'loss/train': 1.8092010021209717}
-03/04/2022 20:25:42 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 20:25:46 - INFO - codeparrot_training - Step 26353: {'lr': 0.00046733382018708405, 'samples': 13493248, 'steps': 26353, 'loss/train': 2.2483410835266113}
-03/04/2022 20:25:50 - INFO - codeparrot_training - Step 26354: {'lr': 0.00046733119742410476, 'samples': 13493760, 'steps': 26354, 'loss/train': 2.2999935150146484}
-03/04/2022 20:25:52 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/04/2022 20:25:55 - INFO - codeparrot_training - Step 26355: {'lr': 0.0004673285745631993, 'samples': 13494272, 'steps': 26355, 'loss/train': 1.8416318893432617}
-03/04/2022 20:25:58 - INFO - codeparrot_training - Step 26356: {'lr': 0.000467325951604369, 'samples': 13494784, 'steps': 26356, 'loss/train': 2.043569803237915}
-03/04/2022 20:26:00 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 20:26:03 - INFO - codeparrot_training - Step 26357: {'lr': 0.00046732332854761507, 'samples': 13495296, 'steps': 26357, 'loss/train': 2.19012451171875}
-03/04/2022 20:26:06 - INFO - codeparrot_training - Step 26358: {'lr': 0.00046732070539293847, 'samples': 13495808, 'steps': 26358, 'loss/train': 2.1480791568756104}
-03/04/2022 20:26:09 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/04/2022 20:26:12 - INFO - codeparrot_training - Step 26359: {'lr': 0.0004673180821403405, 'samples': 13496320, 'steps': 26359, 'loss/train': 1.4631963968276978}
-03/04/2022 20:26:15 - INFO - codeparrot_training - Step 26360: {'lr': 0.00046731545878982253, 'samples': 13496832, 'steps': 26360, 'loss/train': 1.2111998796463013}
-03/04/2022 20:26:18 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/04/2022 20:26:21 - INFO - codeparrot_training - Step 26361: {'lr': 0.0004673128353413854, 'samples': 13497344, 'steps': 26361, 'loss/train': 0.8602479100227356}
-03/04/2022 20:26:24 - INFO - codeparrot_training - Step 26362: {'lr': 0.00046731021179503054, 'samples': 13497856, 'steps': 26362, 'loss/train': 2.090641975402832}
-03/04/2022 20:26:27 - INFO - codeparrot_training - Step 26363: {'lr': 0.00046730758815075903, 'samples': 13498368, 'steps': 26363, 'loss/train': 0.4611779451370239}
-03/04/2022 20:26:28 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/04/2022 20:26:32 - INFO - codeparrot_training - Step 26364: {'lr': 0.0004673049644085721, 'samples': 13498880, 'steps': 26364, 'loss/train': 2.6320652961730957}
-03/04/2022 20:26:35 - INFO - codeparrot_training - Step 26365: {'lr': 0.00046730234056847084, 'samples': 13499392, 'steps': 26365, 'loss/train': 2.3065810203552246}
-03/04/2022 20:26:36 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/04/2022 20:26:41 - INFO - codeparrot_training - Step 26366: {'lr': 0.00046729971663045654, 'samples': 13499904, 'steps': 26366, 'loss/train': 2.055612564086914}
-03/04/2022 20:26:44 - INFO - codeparrot_training - Step 26367: {'lr': 0.00046729709259453033, 'samples': 13500416, 'steps': 26367, 'loss/train': 1.6176706552505493}
-03/04/2022 20:26:45 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 20:26:50 - INFO - codeparrot_training - Step 26368: {'lr': 0.0004672944684606934, 'samples': 13500928, 'steps': 26368, 'loss/train': 1.3179558515548706}
-03/04/2022 20:26:53 - INFO - codeparrot_training - Step 26369: {'lr': 0.000467291844228947, 'samples': 13501440, 'steps': 26369, 'loss/train': 1.3017600774765015}
-03/04/2022 20:26:55 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/04/2022 20:26:58 - INFO - codeparrot_training - Step 26370: {'lr': 0.00046728921989929215, 'samples': 13501952, 'steps': 26370, 'loss/train': 1.774262547492981}
-03/04/2022 20:27:01 - INFO - codeparrot_training - Step 26371: {'lr': 0.0004672865954717301, 'samples': 13502464, 'steps': 26371, 'loss/train': 2.459853410720825}
-03/04/2022 20:27:04 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/04/2022 20:27:06 - INFO - codeparrot_training - Step 26372: {'lr': 0.00046728397094626217, 'samples': 13502976, 'steps': 26372, 'loss/train': 2.0828793048858643}
-03/04/2022 20:27:10 - INFO - codeparrot_training - Step 26373: {'lr': 0.0004672813463228894, 'samples': 13503488, 'steps': 26373, 'loss/train': 1.922803282737732}
-03/04/2022 20:27:12 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/04/2022 20:27:15 - INFO - codeparrot_training - Step 26374: {'lr': 0.00046727872160161305, 'samples': 13504000, 'steps': 26374, 'loss/train': 1.6921474933624268}
-03/04/2022 20:27:18 - INFO - codeparrot_training - Step 26375: {'lr': 0.0004672760967824342, 'samples': 13504512, 'steps': 26375, 'loss/train': 2.1356189250946045}
-03/04/2022 20:27:20 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/04/2022 20:27:23 - INFO - codeparrot_training - Step 26376: {'lr': 0.0004672734718653541, 'samples': 13505024, 'steps': 26376, 'loss/train': 1.4718737602233887}
-03/04/2022 20:27:26 - INFO - codeparrot_training - Step 26377: {'lr': 0.00046727084685037394, 'samples': 13505536, 'steps': 26377, 'loss/train': 2.175557851791382}
-03/04/2022 20:27:29 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/04/2022 20:27:32 - INFO - codeparrot_training - Step 26378: {'lr': 0.00046726822173749497, 'samples': 13506048, 'steps': 26378, 'loss/train': 2.9148662090301514}
-03/04/2022 20:27:35 - INFO - codeparrot_training - Step 26379: {'lr': 0.0004672655965267182, 'samples': 13506560, 'steps': 26379, 'loss/train': 1.0219379663467407}
-03/04/2022 20:27:38 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/04/2022 20:27:40 - INFO - codeparrot_training - Step 26380: {'lr': 0.0004672629712180448, 'samples': 13507072, 'steps': 26380, 'loss/train': 2.3088953495025635}
-03/04/2022 20:27:43 - INFO - codeparrot_training - Step 26381: {'lr': 0.00046726034581147624, 'samples': 13507584, 'steps': 26381, 'loss/train': 2.821471929550171}
-03/04/2022 20:27:46 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 20:27:49 - INFO - codeparrot_training - Step 26382: {'lr': 0.0004672577203070135, 'samples': 13508096, 'steps': 26382, 'loss/train': 2.200788974761963}
-03/04/2022 20:27:52 - INFO - codeparrot_training - Step 26383: {'lr': 0.0004672550947046577, 'samples': 13508608, 'steps': 26383, 'loss/train': 2.0816233158111572}
-03/04/2022 20:27:55 - INFO - codeparrot_training - Step 26384: {'lr': 0.0004672524690044102, 'samples': 13509120, 'steps': 26384, 'loss/train': 2.0663087368011475}
-03/04/2022 20:27:55 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/04/2022 20:28:00 - INFO - codeparrot_training - Step 26385: {'lr': 0.000467249843206272, 'samples': 13509632, 'steps': 26385, 'loss/train': 2.1231961250305176}
-03/04/2022 20:28:04 - INFO - codeparrot_training - Step 26386: {'lr': 0.00046724721731024446, 'samples': 13510144, 'steps': 26386, 'loss/train': 1.90706467628479}
-03/04/2022 20:28:04 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/04/2022 20:28:09 - INFO - codeparrot_training - Step 26387: {'lr': 0.00046724459131632854, 'samples': 13510656, 'steps': 26387, 'loss/train': 1.4670147895812988}
-03/04/2022 20:28:12 - INFO - codeparrot_training - Step 26388: {'lr': 0.00046724196522452565, 'samples': 13511168, 'steps': 26388, 'loss/train': 1.9441431760787964}
-03/04/2022 20:28:12 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/04/2022 20:28:18 - INFO - codeparrot_training - Step 26389: {'lr': 0.00046723933903483687, 'samples': 13511680, 'steps': 26389, 'loss/train': 1.654375672340393}
-03/04/2022 20:28:21 - INFO - codeparrot_training - Step 26390: {'lr': 0.00046723671274726344, 'samples': 13512192, 'steps': 26390, 'loss/train': 1.3300007581710815}
-03/04/2022 20:28:21 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/04/2022 20:28:26 - INFO - codeparrot_training - Step 26391: {'lr': 0.00046723408636180645, 'samples': 13512704, 'steps': 26391, 'loss/train': 1.7215726375579834}
-03/04/2022 20:28:29 - INFO - codeparrot_training - Step 26392: {'lr': 0.00046723145987846715, 'samples': 13513216, 'steps': 26392, 'loss/train': 1.7362573146820068}
-03/04/2022 20:28:29 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/04/2022 20:28:34 - INFO - codeparrot_training - Step 26393: {'lr': 0.00046722883329724667, 'samples': 13513728, 'steps': 26393, 'loss/train': 1.1911818981170654}
-03/04/2022 20:28:38 - INFO - codeparrot_training - Step 26394: {'lr': 0.0004672262066181463, 'samples': 13514240, 'steps': 26394, 'loss/train': 1.8602632284164429}
-03/04/2022 20:28:38 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/04/2022 20:28:43 - INFO - codeparrot_training - Step 26395: {'lr': 0.00046722357984116717, 'samples': 13514752, 'steps': 26395, 'loss/train': 1.9785295724868774}
-03/04/2022 20:28:46 - INFO - codeparrot_training - Step 26396: {'lr': 0.0004672209529663103, 'samples': 13515264, 'steps': 26396, 'loss/train': 1.8130202293395996}
-03/04/2022 20:28:46 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 20:28:52 - INFO - codeparrot_training - Step 26397: {'lr': 0.00046721832599357717, 'samples': 13515776, 'steps': 26397, 'loss/train': 1.79843008518219}
-03/04/2022 20:28:55 - INFO - codeparrot_training - Step 26398: {'lr': 0.00046721569892296875, 'samples': 13516288, 'steps': 26398, 'loss/train': 2.376918315887451}
-03/04/2022 20:28:55 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/04/2022 20:29:00 - INFO - codeparrot_training - Step 26399: {'lr': 0.00046721307175448626, 'samples': 13516800, 'steps': 26399, 'loss/train': 1.7172563076019287}
-03/04/2022 20:29:03 - INFO - codeparrot_training - Step 26400: {'lr': 0.000467210444488131, 'samples': 13517312, 'steps': 26400, 'loss/train': 1.6288255453109741}
-03/04/2022 20:29:04 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 20:29:09 - INFO - codeparrot_training - Step 26401: {'lr': 0.000467207817123904, 'samples': 13517824, 'steps': 26401, 'loss/train': 1.9853402376174927}
-03/04/2022 20:29:12 - INFO - codeparrot_training - Step 26402: {'lr': 0.0004672051896618065, 'samples': 13518336, 'steps': 26402, 'loss/train': 2.4832844734191895}
-03/04/2022 20:29:12 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/04/2022 20:29:17 - INFO - codeparrot_training - Step 26403: {'lr': 0.0004672025621018397, 'samples': 13518848, 'steps': 26403, 'loss/train': 6.4857330322265625}
-03/04/2022 20:29:20 - INFO - codeparrot_training - Step 26404: {'lr': 0.00046719993444400477, 'samples': 13519360, 'steps': 26404, 'loss/train': 0.782981812953949}
-03/04/2022 20:29:21 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 20:29:26 - INFO - codeparrot_training - Step 26405: {'lr': 0.00046719730668830293, 'samples': 13519872, 'steps': 26405, 'loss/train': 0.9992297291755676}
-03/04/2022 20:29:29 - INFO - codeparrot_training - Step 26406: {'lr': 0.0004671946788347353, 'samples': 13520384, 'steps': 26406, 'loss/train': 0.9563493728637695}
-03/04/2022 20:29:30 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 20:29:34 - INFO - codeparrot_training - Step 26407: {'lr': 0.00046719205088330317, 'samples': 13520896, 'steps': 26407, 'loss/train': 0.8506782054901123}
-03/04/2022 20:29:37 - INFO - codeparrot_training - Step 26408: {'lr': 0.0004671894228340076, 'samples': 13521408, 'steps': 26408, 'loss/train': 1.7318669557571411}
-03/04/2022 20:29:38 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/04/2022 20:29:42 - INFO - codeparrot_training - Step 26409: {'lr': 0.0004671867946868499, 'samples': 13521920, 'steps': 26409, 'loss/train': 1.9564017057418823}
-03/04/2022 20:29:46 - INFO - codeparrot_training - Step 26410: {'lr': 0.000467184166441831, 'samples': 13522432, 'steps': 26410, 'loss/train': 2.875936985015869}
-03/04/2022 20:29:47 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 20:29:51 - INFO - codeparrot_training - Step 26411: {'lr': 0.0004671815380989525, 'samples': 13522944, 'steps': 26411, 'loss/train': 1.4288697242736816}
-03/04/2022 20:29:54 - INFO - codeparrot_training - Step 26412: {'lr': 0.0004671789096582152, 'samples': 13523456, 'steps': 26412, 'loss/train': 1.0903258323669434}
-03/04/2022 20:29:55 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/04/2022 20:29:59 - INFO - codeparrot_training - Step 26413: {'lr': 0.00046717628111962045, 'samples': 13523968, 'steps': 26413, 'loss/train': 2.001708507537842}
-03/04/2022 20:30:02 - INFO - codeparrot_training - Step 26414: {'lr': 0.00046717365248316947, 'samples': 13524480, 'steps': 26414, 'loss/train': 1.982118010520935}
-03/04/2022 20:30:03 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/04/2022 20:30:08 - INFO - codeparrot_training - Step 26415: {'lr': 0.00046717102374886334, 'samples': 13524992, 'steps': 26415, 'loss/train': 2.015167474746704}
-03/04/2022 20:30:11 - INFO - codeparrot_training - Step 26416: {'lr': 0.0004671683949167033, 'samples': 13525504, 'steps': 26416, 'loss/train': 2.158921003341675}
-03/04/2022 20:30:14 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 20:30:17 - INFO - codeparrot_training - Step 26417: {'lr': 0.0004671657659866906, 'samples': 13526016, 'steps': 26417, 'loss/train': 2.13736629486084}
-03/04/2022 20:30:20 - INFO - codeparrot_training - Step 26418: {'lr': 0.00046716313695882626, 'samples': 13526528, 'steps': 26418, 'loss/train': 1.5941184759140015}
-03/04/2022 20:30:22 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 20:30:25 - INFO - codeparrot_training - Step 26419: {'lr': 0.00046716050783311166, 'samples': 13527040, 'steps': 26419, 'loss/train': 1.4115631580352783}
-03/04/2022 20:30:28 - INFO - codeparrot_training - Step 26420: {'lr': 0.00046715787860954785, 'samples': 13527552, 'steps': 26420, 'loss/train': 2.2943177223205566}
-03/04/2022 20:30:31 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 20:30:33 - INFO - codeparrot_training - Step 26421: {'lr': 0.000467155249288136, 'samples': 13528064, 'steps': 26421, 'loss/train': 2.1785802841186523}
-03/04/2022 20:30:37 - INFO - codeparrot_training - Step 26422: {'lr': 0.00046715261986887734, 'samples': 13528576, 'steps': 26422, 'loss/train': 1.9694342613220215}
-03/04/2022 20:30:39 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/04/2022 20:30:42 - INFO - codeparrot_training - Step 26423: {'lr': 0.0004671499903517732, 'samples': 13529088, 'steps': 26423, 'loss/train': 2.3398220539093018}
-03/04/2022 20:30:45 - INFO - codeparrot_training - Step 26424: {'lr': 0.00046714736073682453, 'samples': 13529600, 'steps': 26424, 'loss/train': 2.203522205352783}
-03/04/2022 20:30:47 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/04/2022 20:30:50 - INFO - codeparrot_training - Step 26425: {'lr': 0.00046714473102403255, 'samples': 13530112, 'steps': 26425, 'loss/train': 2.436027765274048}
-03/04/2022 20:30:53 - INFO - codeparrot_training - Step 26426: {'lr': 0.0004671421012133986, 'samples': 13530624, 'steps': 26426, 'loss/train': 2.0419392585754395}
-03/04/2022 20:30:56 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/04/2022 20:30:59 - INFO - codeparrot_training - Step 26427: {'lr': 0.00046713947130492373, 'samples': 13531136, 'steps': 26427, 'loss/train': 1.4386550188064575}
-03/04/2022 20:31:02 - INFO - codeparrot_training - Step 26428: {'lr': 0.0004671368412986091, 'samples': 13531648, 'steps': 26428, 'loss/train': 1.6365159749984741}
-03/04/2022 20:31:04 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 20:31:07 - INFO - codeparrot_training - Step 26429: {'lr': 0.0004671342111944561, 'samples': 13532160, 'steps': 26429, 'loss/train': 2.3108408451080322}
-03/04/2022 20:31:10 - INFO - codeparrot_training - Step 26430: {'lr': 0.00046713158099246564, 'samples': 13532672, 'steps': 26430, 'loss/train': 2.017540693283081}
-03/04/2022 20:31:13 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 20:31:16 - INFO - codeparrot_training - Step 26431: {'lr': 0.00046712895069263917, 'samples': 13533184, 'steps': 26431, 'loss/train': 1.7505096197128296}
-03/04/2022 20:31:19 - INFO - codeparrot_training - Step 26432: {'lr': 0.00046712632029497766, 'samples': 13533696, 'steps': 26432, 'loss/train': 1.755135178565979}
-03/04/2022 20:31:22 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/04/2022 20:31:24 - INFO - codeparrot_training - Step 26433: {'lr': 0.0004671236897994824, 'samples': 13534208, 'steps': 26433, 'loss/train': 1.7604070901870728}
-03/04/2022 20:31:27 - INFO - codeparrot_training - Step 26434: {'lr': 0.00046712105920615455, 'samples': 13534720, 'steps': 26434, 'loss/train': 1.7391496896743774}
-03/04/2022 20:31:30 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/04/2022 20:31:33 - INFO - codeparrot_training - Step 26435: {'lr': 0.00046711842851499533, 'samples': 13535232, 'steps': 26435, 'loss/train': 1.6905876398086548}
-03/04/2022 20:31:36 - INFO - codeparrot_training - Step 26436: {'lr': 0.0004671157977260059, 'samples': 13535744, 'steps': 26436, 'loss/train': 2.1517322063446045}
-03/04/2022 20:31:39 - INFO - codeparrot_training - Step 26437: {'lr': 0.0004671131668391874, 'samples': 13536256, 'steps': 26437, 'loss/train': 0.8955194354057312}
-03/04/2022 20:31:39 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 20:31:44 - INFO - codeparrot_training - Step 26438: {'lr': 0.00046711053585454104, 'samples': 13536768, 'steps': 26438, 'loss/train': 2.2363696098327637}
-03/04/2022 20:31:48 - INFO - codeparrot_training - Step 26439: {'lr': 0.0004671079047720681, 'samples': 13537280, 'steps': 26439, 'loss/train': 1.9852031469345093}
-03/04/2022 20:31:48 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/04/2022 20:31:53 - INFO - codeparrot_training - Step 26440: {'lr': 0.00046710527359176957, 'samples': 13537792, 'steps': 26440, 'loss/train': 1.3503477573394775}
-03/04/2022 20:31:55 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/04/2022 20:31:58 - INFO - codeparrot_training - Step 26441: {'lr': 0.0004671026423136469, 'samples': 13538304, 'steps': 26441, 'loss/train': 2.1063976287841797}
-03/04/2022 20:32:01 - INFO - codeparrot_training - Step 26442: {'lr': 0.00046710001093770107, 'samples': 13538816, 'steps': 26442, 'loss/train': 2.0339794158935547}
-03/04/2022 20:32:04 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/04/2022 20:32:07 - INFO - codeparrot_training - Step 26443: {'lr': 0.0004670973794639333, 'samples': 13539328, 'steps': 26443, 'loss/train': 1.880011796951294}
-03/04/2022 20:32:10 - INFO - codeparrot_training - Step 26444: {'lr': 0.0004670947478923447, 'samples': 13539840, 'steps': 26444, 'loss/train': 1.0665866136550903}
-03/04/2022 20:32:12 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 20:32:15 - INFO - codeparrot_training - Step 26445: {'lr': 0.00046709211622293677, 'samples': 13540352, 'steps': 26445, 'loss/train': 1.7912287712097168}
-03/04/2022 20:32:18 - INFO - codeparrot_training - Step 26446: {'lr': 0.00046708948445571037, 'samples': 13540864, 'steps': 26446, 'loss/train': 2.483994960784912}
-03/04/2022 20:32:21 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/04/2022 20:32:24 - INFO - codeparrot_training - Step 26447: {'lr': 0.0004670868525906668, 'samples': 13541376, 'steps': 26447, 'loss/train': 1.478830099105835}
-03/04/2022 20:32:27 - INFO - codeparrot_training - Step 26448: {'lr': 0.00046708422062780725, 'samples': 13541888, 'steps': 26448, 'loss/train': 1.729313850402832}
-03/04/2022 20:32:30 - INFO - codeparrot_training - Step 26449: {'lr': 0.0004670815885671329, 'samples': 13542400, 'steps': 26449, 'loss/train': 1.9526331424713135}
-03/04/2022 20:32:30 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/04/2022 20:32:35 - INFO - codeparrot_training - Step 26450: {'lr': 0.00046707895640864494, 'samples': 13542912, 'steps': 26450, 'loss/train': 1.9172755479812622}
-03/04/2022 20:32:39 - INFO - codeparrot_training - Step 26451: {'lr': 0.0004670763241523446, 'samples': 13543424, 'steps': 26451, 'loss/train': 1.6826196908950806}
-03/04/2022 20:32:39 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/04/2022 20:32:44 - INFO - codeparrot_training - Step 26452: {'lr': 0.00046707369179823294, 'samples': 13543936, 'steps': 26452, 'loss/train': 2.079040765762329}
-03/04/2022 20:32:47 - INFO - codeparrot_training - Step 26453: {'lr': 0.00046707105934631123, 'samples': 13544448, 'steps': 26453, 'loss/train': 1.9599032402038574}
-03/04/2022 20:32:47 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 20:32:52 - INFO - codeparrot_training - Step 26454: {'lr': 0.00046706842679658067, 'samples': 13544960, 'steps': 26454, 'loss/train': 0.9750809669494629}
-03/04/2022 20:32:55 - INFO - codeparrot_training - Step 26455: {'lr': 0.0004670657941490425, 'samples': 13545472, 'steps': 26455, 'loss/train': 1.2822140455245972}
-03/04/2022 20:32:56 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/04/2022 20:33:01 - INFO - codeparrot_training - Step 26456: {'lr': 0.00046706316140369774, 'samples': 13545984, 'steps': 26456, 'loss/train': 2.9064910411834717}
-03/04/2022 20:33:04 - INFO - codeparrot_training - Step 26457: {'lr': 0.0004670605285605477, 'samples': 13546496, 'steps': 26457, 'loss/train': 2.2233498096466064}
-03/04/2022 20:33:05 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/04/2022 20:33:09 - INFO - codeparrot_training - Step 26458: {'lr': 0.0004670578956195935, 'samples': 13547008, 'steps': 26458, 'loss/train': 3.8833322525024414}
-03/04/2022 20:33:12 - INFO - codeparrot_training - Step 26459: {'lr': 0.00046705526258083643, 'samples': 13547520, 'steps': 26459, 'loss/train': 1.307416558265686}
-03/04/2022 20:33:13 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/04/2022 20:33:18 - INFO - codeparrot_training - Step 26460: {'lr': 0.0004670526294442775, 'samples': 13548032, 'steps': 26460, 'loss/train': 2.1492719650268555}
-03/04/2022 20:33:21 - INFO - codeparrot_training - Step 26461: {'lr': 0.0004670499962099181, 'samples': 13548544, 'steps': 26461, 'loss/train': 2.1291027069091797}
-03/04/2022 20:33:23 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/04/2022 20:33:26 - INFO - codeparrot_training - Step 26462: {'lr': 0.0004670473628777593, 'samples': 13549056, 'steps': 26462, 'loss/train': 1.5550085306167603}
-03/04/2022 20:33:29 - INFO - codeparrot_training - Step 26463: {'lr': 0.0004670447294478023, 'samples': 13549568, 'steps': 26463, 'loss/train': 1.7049188613891602}
-03/04/2022 20:33:31 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/04/2022 20:33:34 - INFO - codeparrot_training - Step 26464: {'lr': 0.0004670420959200483, 'samples': 13550080, 'steps': 26464, 'loss/train': 1.6637805700302124}
-03/04/2022 20:33:38 - INFO - codeparrot_training - Step 26465: {'lr': 0.00046703946229449846, 'samples': 13550592, 'steps': 26465, 'loss/train': 2.4205026626586914}
-03/04/2022 20:33:39 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/04/2022 20:33:43 - INFO - codeparrot_training - Step 26466: {'lr': 0.00046703682857115406, 'samples': 13551104, 'steps': 26466, 'loss/train': 1.1018468141555786}
-03/04/2022 20:33:46 - INFO - codeparrot_training - Step 26467: {'lr': 0.0004670341947500161, 'samples': 13551616, 'steps': 26467, 'loss/train': 1.527510643005371}
-03/04/2022 20:33:47 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/04/2022 20:33:51 - INFO - codeparrot_training - Step 26468: {'lr': 0.00046703156083108597, 'samples': 13552128, 'steps': 26468, 'loss/train': 1.5231901407241821}
-03/04/2022 20:33:54 - INFO - codeparrot_training - Step 26469: {'lr': 0.0004670289268143647, 'samples': 13552640, 'steps': 26469, 'loss/train': 1.6364010572433472}
-03/04/2022 20:33:56 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/04/2022 20:34:00 - INFO - codeparrot_training - Step 26470: {'lr': 0.0004670262926998536, 'samples': 13553152, 'steps': 26470, 'loss/train': 1.6553860902786255}
-03/04/2022 20:34:03 - INFO - codeparrot_training - Step 26471: {'lr': 0.00046702365848755377, 'samples': 13553664, 'steps': 26471, 'loss/train': 0.3026265501976013}
-03/04/2022 20:34:04 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/04/2022 20:34:08 - INFO - codeparrot_training - Step 26472: {'lr': 0.0004670210241774664, 'samples': 13554176, 'steps': 26472, 'loss/train': 2.116995096206665}
-03/04/2022 20:34:11 - INFO - codeparrot_training - Step 26473: {'lr': 0.0004670183897695928, 'samples': 13554688, 'steps': 26473, 'loss/train': 1.4347567558288574}
-03/04/2022 20:34:13 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/04/2022 20:34:17 - INFO - codeparrot_training - Step 26474: {'lr': 0.00046701575526393395, 'samples': 13555200, 'steps': 26474, 'loss/train': 1.3316739797592163}
-03/04/2022 20:34:20 - INFO - codeparrot_training - Step 26475: {'lr': 0.00046701312066049126, 'samples': 13555712, 'steps': 26475, 'loss/train': 2.721540689468384}
-03/04/2022 20:34:21 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/04/2022 20:34:25 - INFO - codeparrot_training - Step 26476: {'lr': 0.00046701048595926574, 'samples': 13556224, 'steps': 26476, 'loss/train': 2.0841526985168457}
-03/04/2022 20:34:28 - INFO - codeparrot_training - Step 26477: {'lr': 0.00046700785116025867, 'samples': 13556736, 'steps': 26477, 'loss/train': 1.8084744215011597}
-03/04/2022 20:34:30 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/04/2022 20:34:33 - INFO - codeparrot_training - Step 26478: {'lr': 0.0004670052162634712, 'samples': 13557248, 'steps': 26478, 'loss/train': 2.3716490268707275}
-03/04/2022 20:34:37 - INFO - codeparrot_training - Step 26479: {'lr': 0.0004670025812689045, 'samples': 13557760, 'steps': 26479, 'loss/train': 2.438819646835327}
-03/04/2022 20:34:38 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/04/2022 20:34:42 - INFO - codeparrot_training - Step 26480: {'lr': 0.00046699994617655985, 'samples': 13558272, 'steps': 26480, 'loss/train': 2.3289902210235596}
-03/04/2022 20:34:45 - INFO - codeparrot_training - Step 26481: {'lr': 0.0004669973109864383, 'samples': 13558784, 'steps': 26481, 'loss/train': 1.9662460088729858}
-03/04/2022 20:34:46 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 20:34:50 - INFO - codeparrot_training - Step 26482: {'lr': 0.00046699467569854115, 'samples': 13559296, 'steps': 26482, 'loss/train': 1.741187572479248}
-03/04/2022 20:34:53 - INFO - codeparrot_training - Step 26483: {'lr': 0.0004669920403128696, 'samples': 13559808, 'steps': 26483, 'loss/train': 2.096268653869629}
-03/04/2022 20:34:55 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/04/2022 20:34:59 - INFO - codeparrot_training - Step 26484: {'lr': 0.00046698940482942466, 'samples': 13560320, 'steps': 26484, 'loss/train': 2.9663467407226562}
-03/04/2022 20:35:02 - INFO - codeparrot_training - Step 26485: {'lr': 0.0004669867692482077, 'samples': 13560832, 'steps': 26485, 'loss/train': 1.6388397216796875}
-03/04/2022 20:35:03 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 20:35:07 - INFO - codeparrot_training - Step 26486: {'lr': 0.00046698413356921985, 'samples': 13561344, 'steps': 26486, 'loss/train': 1.5816243886947632}
-03/04/2022 20:35:11 - INFO - codeparrot_training - Step 26487: {'lr': 0.00046698149779246235, 'samples': 13561856, 'steps': 26487, 'loss/train': 2.0468482971191406}
-03/04/2022 20:35:12 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 20:35:16 - INFO - codeparrot_training - Step 26488: {'lr': 0.0004669788619179363, 'samples': 13562368, 'steps': 26488, 'loss/train': 1.807116150856018}
-03/04/2022 20:35:19 - INFO - codeparrot_training - Step 26489: {'lr': 0.0004669762259456429, 'samples': 13562880, 'steps': 26489, 'loss/train': 2.150627851486206}
-03/04/2022 20:35:21 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 20:35:24 - INFO - codeparrot_training - Step 26490: {'lr': 0.00046697358987558336, 'samples': 13563392, 'steps': 26490, 'loss/train': 2.465322256088257}
-03/04/2022 20:35:27 - INFO - codeparrot_training - Step 26491: {'lr': 0.0004669709537077589, 'samples': 13563904, 'steps': 26491, 'loss/train': 0.7522966861724854}
-03/04/2022 20:35:29 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/04/2022 20:35:33 - INFO - codeparrot_training - Step 26492: {'lr': 0.00046696831744217065, 'samples': 13564416, 'steps': 26492, 'loss/train': 1.259932279586792}
-03/04/2022 20:35:36 - INFO - codeparrot_training - Step 26493: {'lr': 0.0004669656810788199, 'samples': 13564928, 'steps': 26493, 'loss/train': 1.414974570274353}
-03/04/2022 20:35:37 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/04/2022 20:35:41 - INFO - codeparrot_training - Step 26494: {'lr': 0.0004669630446177077, 'samples': 13565440, 'steps': 26494, 'loss/train': 1.3000133037567139}
-03/04/2022 20:35:44 - INFO - codeparrot_training - Step 26495: {'lr': 0.0004669604080588352, 'samples': 13565952, 'steps': 26495, 'loss/train': 1.964637041091919}
-03/04/2022 20:35:46 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/04/2022 20:35:50 - INFO - codeparrot_training - Step 26496: {'lr': 0.0004669577714022039, 'samples': 13566464, 'steps': 26496, 'loss/train': 1.4004921913146973}
-03/04/2022 20:35:53 - INFO - codeparrot_training - Step 26497: {'lr': 0.00046695513464781456, 'samples': 13566976, 'steps': 26497, 'loss/train': 1.7632145881652832}
-03/04/2022 20:35:54 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 20:35:58 - INFO - codeparrot_training - Step 26498: {'lr': 0.00046695249779566875, 'samples': 13567488, 'steps': 26498, 'loss/train': 1.6646251678466797}
-03/04/2022 20:36:01 - INFO - codeparrot_training - Step 26499: {'lr': 0.0004669498608457674, 'samples': 13568000, 'steps': 26499, 'loss/train': 1.4009953737258911}
-03/04/2022 20:36:04 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 20:36:07 - INFO - codeparrot_training - Step 26500: {'lr': 0.0004669472237981118, 'samples': 13568512, 'steps': 26500, 'loss/train': 1.996139645576477}
-03/04/2022 20:36:10 - INFO - codeparrot_training - Step 26501: {'lr': 0.00046694458665270315, 'samples': 13569024, 'steps': 26501, 'loss/train': 1.607911467552185}
-03/04/2022 20:36:12 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/04/2022 20:36:15 - INFO - codeparrot_training - Step 26502: {'lr': 0.0004669419494095426, 'samples': 13569536, 'steps': 26502, 'loss/train': 1.9766838550567627}
-03/04/2022 20:36:18 - INFO - codeparrot_training - Step 26503: {'lr': 0.0004669393120686314, 'samples': 13570048, 'steps': 26503, 'loss/train': 1.6975353956222534}
-03/04/2022 20:36:21 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/04/2022 20:36:23 - INFO - codeparrot_training - Step 26504: {'lr': 0.0004669366746299707, 'samples': 13570560, 'steps': 26504, 'loss/train': 2.2534005641937256}
-03/04/2022 20:36:27 - INFO - codeparrot_training - Step 26505: {'lr': 0.00046693403709356163, 'samples': 13571072, 'steps': 26505, 'loss/train': 1.399840235710144}
-03/04/2022 20:36:29 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/04/2022 20:36:32 - INFO - codeparrot_training - Step 26506: {'lr': 0.00046693139945940546, 'samples': 13571584, 'steps': 26506, 'loss/train': 1.7342591285705566}
-03/04/2022 20:36:35 - INFO - codeparrot_training - Step 26507: {'lr': 0.0004669287617275033, 'samples': 13572096, 'steps': 26507, 'loss/train': 1.2373005151748657}
-03/04/2022 20:36:37 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/04/2022 20:36:40 - INFO - codeparrot_training - Step 26508: {'lr': 0.0004669261238978564, 'samples': 13572608, 'steps': 26508, 'loss/train': 1.493643045425415}
-03/04/2022 20:36:44 - INFO - codeparrot_training - Step 26509: {'lr': 0.00046692348597046596, 'samples': 13573120, 'steps': 26509, 'loss/train': 2.1045961380004883}
-03/04/2022 20:36:46 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/04/2022 20:36:49 - INFO - codeparrot_training - Step 26510: {'lr': 0.0004669208479453332, 'samples': 13573632, 'steps': 26510, 'loss/train': 1.3280003070831299}
-03/04/2022 20:36:52 - INFO - codeparrot_training - Step 26511: {'lr': 0.00046691820982245913, 'samples': 13574144, 'steps': 26511, 'loss/train': 1.4315855503082275}
-03/04/2022 20:36:55 - INFO - codeparrot_training - Step 26512: {'lr': 0.00046691557160184516, 'samples': 13574656, 'steps': 26512, 'loss/train': 1.377063274383545}
-03/04/2022 20:36:56 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 20:37:01 - INFO - codeparrot_training - Step 26513: {'lr': 0.0004669129332834923, 'samples': 13575168, 'steps': 26513, 'loss/train': 1.4692057371139526}
-03/04/2022 20:37:04 - INFO - codeparrot_training - Step 26514: {'lr': 0.0004669102948674019, 'samples': 13575680, 'steps': 26514, 'loss/train': 1.4055215120315552}
-03/04/2022 20:37:05 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/04/2022 20:37:09 - INFO - codeparrot_training - Step 26515: {'lr': 0.000466907656353575, 'samples': 13576192, 'steps': 26515, 'loss/train': 1.5627578496932983}
-03/04/2022 20:37:12 - INFO - codeparrot_training - Step 26516: {'lr': 0.0004669050177420129, 'samples': 13576704, 'steps': 26516, 'loss/train': 1.8977771997451782}
-03/04/2022 20:37:13 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 20:37:18 - INFO - codeparrot_training - Step 26517: {'lr': 0.0004669023790327168, 'samples': 13577216, 'steps': 26517, 'loss/train': 2.461113929748535}
-03/04/2022 20:37:21 - INFO - codeparrot_training - Step 26518: {'lr': 0.0004668997402256877, 'samples': 13577728, 'steps': 26518, 'loss/train': 1.8436012268066406}
-03/04/2022 20:37:22 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/04/2022 20:37:26 - INFO - codeparrot_training - Step 26519: {'lr': 0.00046689710132092704, 'samples': 13578240, 'steps': 26519, 'loss/train': 2.4113199710845947}
-03/04/2022 20:37:29 - INFO - codeparrot_training - Step 26520: {'lr': 0.00046689446231843585, 'samples': 13578752, 'steps': 26520, 'loss/train': 1.2172058820724487}
-03/04/2022 20:37:30 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/04/2022 20:37:35 - INFO - codeparrot_training - Step 26521: {'lr': 0.0004668918232182153, 'samples': 13579264, 'steps': 26521, 'loss/train': 1.2210732698440552}
-03/04/2022 20:37:38 - INFO - codeparrot_training - Step 26522: {'lr': 0.0004668891840202668, 'samples': 13579776, 'steps': 26522, 'loss/train': 2.2023234367370605}
-03/04/2022 20:37:39 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/04/2022 20:37:43 - INFO - codeparrot_training - Step 26523: {'lr': 0.00046688654472459124, 'samples': 13580288, 'steps': 26523, 'loss/train': 1.5736870765686035}
-03/04/2022 20:37:46 - INFO - codeparrot_training - Step 26524: {'lr': 0.00046688390533119003, 'samples': 13580800, 'steps': 26524, 'loss/train': 2.8879246711730957}
-03/04/2022 20:37:47 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/04/2022 20:37:51 - INFO - codeparrot_training - Step 26525: {'lr': 0.00046688126584006425, 'samples': 13581312, 'steps': 26525, 'loss/train': 0.8541378974914551}
-03/04/2022 20:37:55 - INFO - codeparrot_training - Step 26526: {'lr': 0.00046687862625121505, 'samples': 13581824, 'steps': 26526, 'loss/train': 1.7431772947311401}
-03/04/2022 20:37:55 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/04/2022 20:38:00 - INFO - codeparrot_training - Step 26527: {'lr': 0.0004668759865646438, 'samples': 13582336, 'steps': 26527, 'loss/train': 2.386282444000244}
-03/04/2022 20:38:03 - INFO - codeparrot_training - Step 26528: {'lr': 0.00046687334678035153, 'samples': 13582848, 'steps': 26528, 'loss/train': 2.0503463745117188}
-03/04/2022 20:38:03 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/04/2022 20:38:08 - INFO - codeparrot_training - Step 26529: {'lr': 0.00046687070689833943, 'samples': 13583360, 'steps': 26529, 'loss/train': 1.8635592460632324}
-03/04/2022 20:38:12 - INFO - codeparrot_training - Step 26530: {'lr': 0.00046686806691860884, 'samples': 13583872, 'steps': 26530, 'loss/train': 1.4422972202301025}
-03/04/2022 20:38:12 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/04/2022 20:38:17 - INFO - codeparrot_training - Step 26531: {'lr': 0.00046686542684116073, 'samples': 13584384, 'steps': 26531, 'loss/train': 1.7908167839050293}
-03/04/2022 20:38:20 - INFO - codeparrot_training - Step 26532: {'lr': 0.00046686278666599647, 'samples': 13584896, 'steps': 26532, 'loss/train': 2.5626654624938965}
-03/04/2022 20:38:20 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 20:38:25 - INFO - codeparrot_training - Step 26533: {'lr': 0.0004668601463931172, 'samples': 13585408, 'steps': 26533, 'loss/train': 1.3456982374191284}
-03/04/2022 20:38:29 - INFO - codeparrot_training - Step 26534: {'lr': 0.00046685750602252406, 'samples': 13585920, 'steps': 26534, 'loss/train': 1.7075285911560059}
-03/04/2022 20:38:29 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 20:38:34 - INFO - codeparrot_training - Step 26535: {'lr': 0.0004668548655542183, 'samples': 13586432, 'steps': 26535, 'loss/train': 1.6753120422363281}
-03/04/2022 20:38:37 - INFO - codeparrot_training - Step 26536: {'lr': 0.000466852224988201, 'samples': 13586944, 'steps': 26536, 'loss/train': 2.108614444732666}
-03/04/2022 20:38:37 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/04/2022 20:38:42 - INFO - codeparrot_training - Step 26537: {'lr': 0.00046684958432447355, 'samples': 13587456, 'steps': 26537, 'loss/train': 1.1829787492752075}
-03/04/2022 20:38:45 - INFO - codeparrot_training - Step 26538: {'lr': 0.00046684694356303693, 'samples': 13587968, 'steps': 26538, 'loss/train': 2.3334717750549316}
-03/04/2022 20:38:45 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/04/2022 20:38:51 - INFO - codeparrot_training - Step 26539: {'lr': 0.0004668443027038925, 'samples': 13588480, 'steps': 26539, 'loss/train': 2.772888422012329}
-03/04/2022 20:38:54 - INFO - codeparrot_training - Step 26540: {'lr': 0.00046684166174704134, 'samples': 13588992, 'steps': 26540, 'loss/train': 1.4010323286056519}
-03/04/2022 20:38:54 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 20:38:59 - INFO - codeparrot_training - Step 26541: {'lr': 0.00046683902069248465, 'samples': 13589504, 'steps': 26541, 'loss/train': 0.9568489193916321}
-03/04/2022 20:39:02 - INFO - codeparrot_training - Step 26542: {'lr': 0.0004668363795402237, 'samples': 13590016, 'steps': 26542, 'loss/train': 1.8775134086608887}
-03/04/2022 20:39:02 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/04/2022 20:39:08 - INFO - codeparrot_training - Step 26543: {'lr': 0.00046683373829025954, 'samples': 13590528, 'steps': 26543, 'loss/train': 1.5324357748031616}
-03/04/2022 20:39:11 - INFO - codeparrot_training - Step 26544: {'lr': 0.0004668310969425935, 'samples': 13591040, 'steps': 26544, 'loss/train': 1.8269140720367432}
-03/04/2022 20:39:11 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 20:39:16 - INFO - codeparrot_training - Step 26545: {'lr': 0.00046682845549722677, 'samples': 13591552, 'steps': 26545, 'loss/train': 1.9655989408493042}
-03/04/2022 20:39:19 - INFO - codeparrot_training - Step 26546: {'lr': 0.0004668258139541604, 'samples': 13592064, 'steps': 26546, 'loss/train': 2.426006555557251}
-03/04/2022 20:39:19 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 20:39:24 - INFO - codeparrot_training - Step 26547: {'lr': 0.00046682317231339565, 'samples': 13592576, 'steps': 26547, 'loss/train': 1.4301517009735107}
-03/04/2022 20:39:27 - INFO - codeparrot_training - Step 26548: {'lr': 0.00046682053057493377, 'samples': 13593088, 'steps': 26548, 'loss/train': 1.7316124439239502}
-03/04/2022 20:39:28 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/04/2022 20:39:33 - INFO - codeparrot_training - Step 26549: {'lr': 0.00046681788873877595, 'samples': 13593600, 'steps': 26549, 'loss/train': 2.3400120735168457}
-03/04/2022 20:39:36 - INFO - codeparrot_training - Step 26550: {'lr': 0.00046681524680492327, 'samples': 13594112, 'steps': 26550, 'loss/train': 1.68581223487854}
-03/04/2022 20:39:36 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/04/2022 20:39:41 - INFO - codeparrot_training - Step 26551: {'lr': 0.00046681260477337693, 'samples': 13594624, 'steps': 26551, 'loss/train': 1.6424542665481567}
-03/04/2022 20:39:44 - INFO - codeparrot_training - Step 26552: {'lr': 0.0004668099626441383, 'samples': 13595136, 'steps': 26552, 'loss/train': 1.9305063486099243}
-03/04/2022 20:39:45 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/04/2022 20:39:50 - INFO - codeparrot_training - Step 26553: {'lr': 0.00046680732041720836, 'samples': 13595648, 'steps': 26553, 'loss/train': 1.9807507991790771}
-03/04/2022 20:39:53 - INFO - codeparrot_training - Step 26554: {'lr': 0.0004668046780925884, 'samples': 13596160, 'steps': 26554, 'loss/train': 2.6153101921081543}
-03/04/2022 20:39:53 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/04/2022 20:39:58 - INFO - codeparrot_training - Step 26555: {'lr': 0.0004668020356702796, 'samples': 13596672, 'steps': 26555, 'loss/train': 3.038522481918335}
-03/04/2022 20:40:01 - INFO - codeparrot_training - Step 26556: {'lr': 0.0004667993931502832, 'samples': 13597184, 'steps': 26556, 'loss/train': 1.7892401218414307}
-03/04/2022 20:40:02 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 20:40:07 - INFO - codeparrot_training - Step 26557: {'lr': 0.00046679675053260027, 'samples': 13597696, 'steps': 26557, 'loss/train': 2.2638485431671143}
-03/04/2022 20:40:10 - INFO - codeparrot_training - Step 26558: {'lr': 0.00046679410781723206, 'samples': 13598208, 'steps': 26558, 'loss/train': 1.8912955522537231}
-03/04/2022 20:40:11 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 20:40:15 - INFO - codeparrot_training - Step 26559: {'lr': 0.0004667914650041799, 'samples': 13598720, 'steps': 26559, 'loss/train': 2.029426097869873}
-03/04/2022 20:40:18 - INFO - codeparrot_training - Step 26560: {'lr': 0.00046678882209344474, 'samples': 13599232, 'steps': 26560, 'loss/train': 2.237112045288086}
-03/04/2022 20:40:19 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 20:40:24 - INFO - codeparrot_training - Step 26561: {'lr': 0.00046678617908502785, 'samples': 13599744, 'steps': 26561, 'loss/train': 2.0326857566833496}
-03/04/2022 20:40:27 - INFO - codeparrot_training - Step 26562: {'lr': 0.00046678353597893053, 'samples': 13600256, 'steps': 26562, 'loss/train': 1.894349455833435}
-03/04/2022 20:40:27 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 20:40:32 - INFO - codeparrot_training - Step 26563: {'lr': 0.0004667808927751539, 'samples': 13600768, 'steps': 26563, 'loss/train': 1.8986589908599854}
-03/04/2022 20:40:35 - INFO - codeparrot_training - Step 26564: {'lr': 0.00046677824947369907, 'samples': 13601280, 'steps': 26564, 'loss/train': 1.5348010063171387}
-03/04/2022 20:40:36 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/04/2022 20:40:41 - INFO - codeparrot_training - Step 26565: {'lr': 0.0004667756060745674, 'samples': 13601792, 'steps': 26565, 'loss/train': 1.9123196601867676}
-03/04/2022 20:40:44 - INFO - codeparrot_training - Step 26566: {'lr': 0.0004667729625777599, 'samples': 13602304, 'steps': 26566, 'loss/train': 2.6009438037872314}
-03/04/2022 20:40:45 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 20:40:49 - INFO - codeparrot_training - Step 26567: {'lr': 0.0004667703189832779, 'samples': 13602816, 'steps': 26567, 'loss/train': 0.730574369430542}
-03/04/2022 20:40:52 - INFO - codeparrot_training - Step 26568: {'lr': 0.00046676767529112254, 'samples': 13603328, 'steps': 26568, 'loss/train': 1.001646637916565}
-03/04/2022 20:40:53 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/04/2022 20:40:58 - INFO - codeparrot_training - Step 26569: {'lr': 0.000466765031501295, 'samples': 13603840, 'steps': 26569, 'loss/train': 1.1095993518829346}
-03/04/2022 20:41:01 - INFO - codeparrot_training - Step 26570: {'lr': 0.0004667623876137965, 'samples': 13604352, 'steps': 26570, 'loss/train': 1.927314281463623}
-03/04/2022 20:41:01 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/04/2022 20:41:07 - INFO - codeparrot_training - Step 26571: {'lr': 0.00046675974362862815, 'samples': 13604864, 'steps': 26571, 'loss/train': 2.3595004081726074}
-03/04/2022 20:41:10 - INFO - codeparrot_training - Step 26572: {'lr': 0.00046675709954579125, 'samples': 13605376, 'steps': 26572, 'loss/train': 1.8578994274139404}
-03/04/2022 20:41:12 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 20:41:15 - INFO - codeparrot_training - Step 26573: {'lr': 0.0004667544553652869, 'samples': 13605888, 'steps': 26573, 'loss/train': 1.9144315719604492}
-03/04/2022 20:41:18 - INFO - codeparrot_training - Step 26574: {'lr': 0.0004667518110871164, 'samples': 13606400, 'steps': 26574, 'loss/train': 2.3605785369873047}
-03/04/2022 20:41:22 - INFO - codeparrot_training - Step 26575: {'lr': 0.0004667491667112809, 'samples': 13606912, 'steps': 26575, 'loss/train': 3.4777581691741943}
-03/04/2022 20:41:22 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/04/2022 20:41:27 - INFO - codeparrot_training - Step 26576: {'lr': 0.0004667465222377815, 'samples': 13607424, 'steps': 26576, 'loss/train': 2.103983163833618}
-03/04/2022 20:41:30 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 20:41:32 - INFO - codeparrot_training - Step 26577: {'lr': 0.0004667438776666195, 'samples': 13607936, 'steps': 26577, 'loss/train': 1.3853412866592407}
-03/04/2022 20:41:36 - INFO - codeparrot_training - Step 26578: {'lr': 0.00046674123299779603, 'samples': 13608448, 'steps': 26578, 'loss/train': 1.5102964639663696}
-03/04/2022 20:41:38 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/04/2022 20:41:41 - INFO - codeparrot_training - Step 26579: {'lr': 0.0004667385882313123, 'samples': 13608960, 'steps': 26579, 'loss/train': 1.960842490196228}
-03/04/2022 20:41:44 - INFO - codeparrot_training - Step 26580: {'lr': 0.0004667359433671695, 'samples': 13609472, 'steps': 26580, 'loss/train': 2.1305618286132812}
-03/04/2022 20:41:46 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 20:41:49 - INFO - codeparrot_training - Step 26581: {'lr': 0.0004667332984053689, 'samples': 13609984, 'steps': 26581, 'loss/train': 1.7484407424926758}
-03/04/2022 20:41:52 - INFO - codeparrot_training - Step 26582: {'lr': 0.00046673065334591155, 'samples': 13610496, 'steps': 26582, 'loss/train': 1.334031105041504}
-03/04/2022 20:41:55 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/04/2022 20:41:58 - INFO - codeparrot_training - Step 26583: {'lr': 0.00046672800818879873, 'samples': 13611008, 'steps': 26583, 'loss/train': 1.5804671049118042}
-03/04/2022 20:42:01 - INFO - codeparrot_training - Step 26584: {'lr': 0.0004667253629340316, 'samples': 13611520, 'steps': 26584, 'loss/train': 1.7392085790634155}
-03/04/2022 20:42:03 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/04/2022 20:42:06 - INFO - codeparrot_training - Step 26585: {'lr': 0.0004667227175816114, 'samples': 13612032, 'steps': 26585, 'loss/train': 1.8505655527114868}
-03/04/2022 20:42:09 - INFO - codeparrot_training - Step 26586: {'lr': 0.0004667200721315393, 'samples': 13612544, 'steps': 26586, 'loss/train': 2.9690558910369873}
-03/04/2022 20:42:11 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/04/2022 20:42:14 - INFO - codeparrot_training - Step 26587: {'lr': 0.00046671742658381646, 'samples': 13613056, 'steps': 26587, 'loss/train': 1.5246477127075195}
-03/04/2022 20:42:18 - INFO - codeparrot_training - Step 26588: {'lr': 0.000466714780938444, 'samples': 13613568, 'steps': 26588, 'loss/train': 0.9926356673240662}
-03/04/2022 20:42:20 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/04/2022 20:42:23 - INFO - codeparrot_training - Step 26589: {'lr': 0.0004667121351954233, 'samples': 13614080, 'steps': 26589, 'loss/train': 2.129506826400757}
-03/04/2022 20:42:26 - INFO - codeparrot_training - Step 26590: {'lr': 0.00046670948935475544, 'samples': 13614592, 'steps': 26590, 'loss/train': 3.4915058612823486}
-03/04/2022 20:42:30 - INFO - codeparrot_training - Step 26591: {'lr': 0.00046670684341644167, 'samples': 13615104, 'steps': 26591, 'loss/train': 0.5684828758239746}
-03/04/2022 20:42:30 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 20:42:35 - INFO - codeparrot_training - Step 26592: {'lr': 0.0004667041973804831, 'samples': 13615616, 'steps': 26592, 'loss/train': 1.9176748991012573}
-03/04/2022 20:42:38 - INFO - codeparrot_training - Step 26593: {'lr': 0.00046670155124688096, 'samples': 13616128, 'steps': 26593, 'loss/train': 1.37889564037323}
-03/04/2022 20:42:38 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/04/2022 20:42:43 - INFO - codeparrot_training - Step 26594: {'lr': 0.00046669890501563636, 'samples': 13616640, 'steps': 26594, 'loss/train': 1.6936659812927246}
-03/04/2022 20:42:47 - INFO - codeparrot_training - Step 26595: {'lr': 0.0004666962586867507, 'samples': 13617152, 'steps': 26595, 'loss/train': 2.0882515907287598}
-03/04/2022 20:42:47 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 20:42:52 - INFO - codeparrot_training - Step 26596: {'lr': 0.000466693612260225, 'samples': 13617664, 'steps': 26596, 'loss/train': 1.3531520366668701}
-03/04/2022 20:42:55 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/04/2022 20:42:57 - INFO - codeparrot_training - Step 26597: {'lr': 0.00046669096573606053, 'samples': 13618176, 'steps': 26597, 'loss/train': 1.4609912633895874}
-03/04/2022 20:43:01 - INFO - codeparrot_training - Step 26598: {'lr': 0.00046668831911425844, 'samples': 13618688, 'steps': 26598, 'loss/train': 1.0594253540039062}
-03/04/2022 20:43:03 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/04/2022 20:43:06 - INFO - codeparrot_training - Step 26599: {'lr': 0.00046668567239481994, 'samples': 13619200, 'steps': 26599, 'loss/train': 1.6262317895889282}
-03/04/2022 20:43:09 - INFO - codeparrot_training - Step 26600: {'lr': 0.0004666830255777462, 'samples': 13619712, 'steps': 26600, 'loss/train': 6.550108432769775}
-03/04/2022 20:43:12 - INFO - codeparrot_training - Step 26601: {'lr': 0.00046668037866303845, 'samples': 13620224, 'steps': 26601, 'loss/train': 2.1563990116119385}
-03/04/2022 20:43:13 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/04/2022 20:43:17 - INFO - codeparrot_training - Step 26602: {'lr': 0.0004666777316506979, 'samples': 13620736, 'steps': 26602, 'loss/train': 1.7423055171966553}
-03/04/2022 20:43:21 - INFO - codeparrot_training - Step 26603: {'lr': 0.00046667508454072566, 'samples': 13621248, 'steps': 26603, 'loss/train': 1.8265783786773682}
-03/04/2022 20:43:21 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/04/2022 20:43:26 - INFO - codeparrot_training - Step 26604: {'lr': 0.00046667243733312296, 'samples': 13621760, 'steps': 26604, 'loss/train': 1.8406914472579956}
-03/04/2022 20:43:29 - INFO - codeparrot_training - Step 26605: {'lr': 0.000466669790027891, 'samples': 13622272, 'steps': 26605, 'loss/train': 2.4394304752349854}
-03/04/2022 20:43:30 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/04/2022 20:43:34 - INFO - codeparrot_training - Step 26606: {'lr': 0.00046666714262503107, 'samples': 13622784, 'steps': 26606, 'loss/train': 1.874596118927002}
-03/04/2022 20:43:38 - INFO - codeparrot_training - Step 26607: {'lr': 0.00046666449512454416, 'samples': 13623296, 'steps': 26607, 'loss/train': 1.972298264503479}
-03/04/2022 20:43:38 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 20:43:43 - INFO - codeparrot_training - Step 26608: {'lr': 0.0004666618475264316, 'samples': 13623808, 'steps': 26608, 'loss/train': 2.3511786460876465}
-03/04/2022 20:43:46 - INFO - codeparrot_training - Step 26609: {'lr': 0.0004666591998306946, 'samples': 13624320, 'steps': 26609, 'loss/train': 1.5270026922225952}
-03/04/2022 20:43:47 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 20:43:51 - INFO - codeparrot_training - Step 26610: {'lr': 0.0004666565520373343, 'samples': 13624832, 'steps': 26610, 'loss/train': 1.962636947631836}
-03/04/2022 20:43:55 - INFO - codeparrot_training - Step 26611: {'lr': 0.00046665390414635184, 'samples': 13625344, 'steps': 26611, 'loss/train': 1.75454580783844}
-03/04/2022 20:43:56 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/04/2022 20:44:00 - INFO - codeparrot_training - Step 26612: {'lr': 0.0004666512561577485, 'samples': 13625856, 'steps': 26612, 'loss/train': 2.0201120376586914}
-03/04/2022 20:44:03 - INFO - codeparrot_training - Step 26613: {'lr': 0.0004666486080715255, 'samples': 13626368, 'steps': 26613, 'loss/train': 1.7885310649871826}
-03/04/2022 20:44:04 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/04/2022 20:44:08 - INFO - codeparrot_training - Step 26614: {'lr': 0.0004666459598876839, 'samples': 13626880, 'steps': 26614, 'loss/train': 1.5661311149597168}
-03/04/2022 20:44:12 - INFO - codeparrot_training - Step 26615: {'lr': 0.000466643311606225, 'samples': 13627392, 'steps': 26615, 'loss/train': 1.7631574869155884}
-03/04/2022 20:44:13 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/04/2022 20:44:17 - INFO - codeparrot_training - Step 26616: {'lr': 0.00046664066322715006, 'samples': 13627904, 'steps': 26616, 'loss/train': 1.9867814779281616}
-03/04/2022 20:44:20 - INFO - codeparrot_training - Step 26617: {'lr': 0.00046663801475046004, 'samples': 13628416, 'steps': 26617, 'loss/train': 1.7163591384887695}
-03/04/2022 20:44:21 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/04/2022 20:44:25 - INFO - codeparrot_training - Step 26618: {'lr': 0.0004666353661761563, 'samples': 13628928, 'steps': 26618, 'loss/train': 1.7444401979446411}
-03/04/2022 20:44:29 - INFO - codeparrot_training - Step 26619: {'lr': 0.0004666327175042401, 'samples': 13629440, 'steps': 26619, 'loss/train': 2.0086004734039307}
-03/04/2022 20:44:30 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 20:44:34 - INFO - codeparrot_training - Step 26620: {'lr': 0.00046663006873471247, 'samples': 13629952, 'steps': 26620, 'loss/train': 1.8757693767547607}
-03/04/2022 20:44:37 - INFO - codeparrot_training - Step 26621: {'lr': 0.00046662741986757463, 'samples': 13630464, 'steps': 26621, 'loss/train': 1.9343801736831665}
-03/04/2022 20:44:38 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 20:44:42 - INFO - codeparrot_training - Step 26622: {'lr': 0.0004666247709028279, 'samples': 13630976, 'steps': 26622, 'loss/train': 2.0473289489746094}
-03/04/2022 20:44:45 - INFO - codeparrot_training - Step 26623: {'lr': 0.00046662212184047334, 'samples': 13631488, 'steps': 26623, 'loss/train': 2.001615524291992}
-03/04/2022 20:44:47 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 20:44:51 - INFO - codeparrot_training - Step 26624: {'lr': 0.0004666194726805122, 'samples': 13632000, 'steps': 26624, 'loss/train': 1.8757197856903076}
-03/04/2022 20:44:54 - INFO - codeparrot_training - Step 26625: {'lr': 0.0004666168234229457, 'samples': 13632512, 'steps': 26625, 'loss/train': 1.5612101554870605}
-03/04/2022 20:44:55 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/04/2022 20:44:59 - INFO - codeparrot_training - Step 26626: {'lr': 0.000466614174067775, 'samples': 13633024, 'steps': 26626, 'loss/train': 2.1403236389160156}
-03/04/2022 20:45:02 - INFO - codeparrot_training - Step 26627: {'lr': 0.00046661152461500126, 'samples': 13633536, 'steps': 26627, 'loss/train': 1.7003254890441895}
-03/04/2022 20:45:03 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/04/2022 20:45:08 - INFO - codeparrot_training - Step 26628: {'lr': 0.0004666088750646257, 'samples': 13634048, 'steps': 26628, 'loss/train': 1.1554498672485352}
-03/04/2022 20:45:11 - INFO - codeparrot_training - Step 26629: {'lr': 0.0004666062254166496, 'samples': 13634560, 'steps': 26629, 'loss/train': 2.1569178104400635}
-03/04/2022 20:45:12 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/04/2022 20:45:16 - INFO - codeparrot_training - Step 26630: {'lr': 0.000466603575671074, 'samples': 13635072, 'steps': 26630, 'loss/train': 1.2858855724334717}
-03/04/2022 20:45:19 - INFO - codeparrot_training - Step 26631: {'lr': 0.00046660092582790025, 'samples': 13635584, 'steps': 26631, 'loss/train': 2.555605888366699}
-03/04/2022 20:45:20 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/04/2022 20:45:25 - INFO - codeparrot_training - Step 26632: {'lr': 0.0004665982758871294, 'samples': 13636096, 'steps': 26632, 'loss/train': 1.899399995803833}
-03/04/2022 20:45:28 - INFO - codeparrot_training - Step 26633: {'lr': 0.0004665956258487627, 'samples': 13636608, 'steps': 26633, 'loss/train': 0.2395668625831604}
-03/04/2022 20:45:29 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/04/2022 20:45:33 - INFO - codeparrot_training - Step 26634: {'lr': 0.0004665929757128014, 'samples': 13637120, 'steps': 26634, 'loss/train': 2.7183055877685547}
-03/04/2022 20:45:36 - INFO - codeparrot_training - Step 26635: {'lr': 0.0004665903254792466, 'samples': 13637632, 'steps': 26635, 'loss/train': 2.1655919551849365}
-03/04/2022 20:45:37 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/04/2022 20:45:42 - INFO - codeparrot_training - Step 26636: {'lr': 0.0004665876751480996, 'samples': 13638144, 'steps': 26636, 'loss/train': 2.7645320892333984}
-03/04/2022 20:45:45 - INFO - codeparrot_training - Step 26637: {'lr': 0.0004665850247193615, 'samples': 13638656, 'steps': 26637, 'loss/train': 1.8570046424865723}
-03/04/2022 20:45:47 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 20:45:50 - INFO - codeparrot_training - Step 26638: {'lr': 0.0004665823741930335, 'samples': 13639168, 'steps': 26638, 'loss/train': 1.9662957191467285}
-03/04/2022 20:45:53 - INFO - codeparrot_training - Step 26639: {'lr': 0.00046657972356911696, 'samples': 13639680, 'steps': 26639, 'loss/train': 0.148898184299469}
-03/04/2022 20:45:56 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 20:45:59 - INFO - codeparrot_training - Step 26640: {'lr': 0.00046657707284761274, 'samples': 13640192, 'steps': 26640, 'loss/train': 1.6434271335601807}
-03/04/2022 20:46:02 - INFO - codeparrot_training - Step 26641: {'lr': 0.0004665744220285224, 'samples': 13640704, 'steps': 26641, 'loss/train': 1.7147456407546997}
-03/04/2022 20:46:05 - INFO - codeparrot_training - Step 26642: {'lr': 0.0004665717711118469, 'samples': 13641216, 'steps': 26642, 'loss/train': 2.2712020874023438}
-03/04/2022 20:46:05 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/04/2022 20:46:10 - INFO - codeparrot_training - Step 26643: {'lr': 0.00046656912009758743, 'samples': 13641728, 'steps': 26643, 'loss/train': 1.6994085311889648}
-03/04/2022 20:46:13 - INFO - codeparrot_training - Step 26644: {'lr': 0.0004665664689857454, 'samples': 13642240, 'steps': 26644, 'loss/train': 2.0453977584838867}
-03/04/2022 20:46:14 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/04/2022 20:46:19 - INFO - codeparrot_training - Step 26645: {'lr': 0.00046656381777632173, 'samples': 13642752, 'steps': 26645, 'loss/train': 2.4222054481506348}
-03/04/2022 20:46:22 - INFO - codeparrot_training - Step 26646: {'lr': 0.0004665611664693178, 'samples': 13643264, 'steps': 26646, 'loss/train': 0.8537673950195312}
-03/04/2022 20:46:22 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 20:46:27 - INFO - codeparrot_training - Step 26647: {'lr': 0.0004665585150647348, 'samples': 13643776, 'steps': 26647, 'loss/train': 1.301190972328186}
-03/04/2022 20:46:30 - INFO - codeparrot_training - Step 26648: {'lr': 0.0004665558635625738, 'samples': 13644288, 'steps': 26648, 'loss/train': 1.9126513004302979}
-03/04/2022 20:46:31 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/04/2022 20:46:36 - INFO - codeparrot_training - Step 26649: {'lr': 0.00046655321196283604, 'samples': 13644800, 'steps': 26649, 'loss/train': 1.8300268650054932}
-03/04/2022 20:46:39 - INFO - codeparrot_training - Step 26650: {'lr': 0.00046655056026552287, 'samples': 13645312, 'steps': 26650, 'loss/train': 1.8785401582717896}
-03/04/2022 20:46:39 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 20:46:44 - INFO - codeparrot_training - Step 26651: {'lr': 0.0004665479084706353, 'samples': 13645824, 'steps': 26651, 'loss/train': 1.4458609819412231}
-03/04/2022 20:46:47 - INFO - codeparrot_training - Step 26652: {'lr': 0.00046654525657817457, 'samples': 13646336, 'steps': 26652, 'loss/train': 1.6842485666275024}
-03/04/2022 20:46:48 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 20:46:52 - INFO - codeparrot_training - Step 26653: {'lr': 0.0004665426045881419, 'samples': 13646848, 'steps': 26653, 'loss/train': 0.761953592300415}
-03/04/2022 20:46:56 - INFO - codeparrot_training - Step 26654: {'lr': 0.00046653995250053843, 'samples': 13647360, 'steps': 26654, 'loss/train': 2.232832670211792}
-03/04/2022 20:46:56 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/04/2022 20:47:01 - INFO - codeparrot_training - Step 26655: {'lr': 0.00046653730031536545, 'samples': 13647872, 'steps': 26655, 'loss/train': 1.6327837705612183}
-03/04/2022 20:47:04 - INFO - codeparrot_training - Step 26656: {'lr': 0.0004665346480326241, 'samples': 13648384, 'steps': 26656, 'loss/train': 1.8122210502624512}
-03/04/2022 20:47:05 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/04/2022 20:47:09 - INFO - codeparrot_training - Step 26657: {'lr': 0.00046653199565231554, 'samples': 13648896, 'steps': 26657, 'loss/train': 2.063917875289917}
-03/04/2022 20:47:12 - INFO - codeparrot_training - Step 26658: {'lr': 0.00046652934317444104, 'samples': 13649408, 'steps': 26658, 'loss/train': 1.4336347579956055}
-03/04/2022 20:47:13 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/04/2022 20:47:18 - INFO - codeparrot_training - Step 26659: {'lr': 0.00046652669059900174, 'samples': 13649920, 'steps': 26659, 'loss/train': 2.055600166320801}
-03/04/2022 20:47:21 - INFO - codeparrot_training - Step 26660: {'lr': 0.0004665240379259989, 'samples': 13650432, 'steps': 26660, 'loss/train': 0.545746922492981}
-03/04/2022 20:47:22 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 20:47:26 - INFO - codeparrot_training - Step 26661: {'lr': 0.00046652138515543366, 'samples': 13650944, 'steps': 26661, 'loss/train': 1.6737637519836426}
-03/04/2022 20:47:29 - INFO - codeparrot_training - Step 26662: {'lr': 0.00046651873228730715, 'samples': 13651456, 'steps': 26662, 'loss/train': 1.779179334640503}
-03/04/2022 20:47:30 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 20:47:35 - INFO - codeparrot_training - Step 26663: {'lr': 0.0004665160793216207, 'samples': 13651968, 'steps': 26663, 'loss/train': 1.7342503070831299}
-03/04/2022 20:47:38 - INFO - codeparrot_training - Step 26664: {'lr': 0.00046651342625837544, 'samples': 13652480, 'steps': 26664, 'loss/train': 1.9248305559158325}
-03/04/2022 20:47:41 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/04/2022 20:47:44 - INFO - codeparrot_training - Step 26665: {'lr': 0.00046651077309757256, 'samples': 13652992, 'steps': 26665, 'loss/train': 2.652754783630371}
-03/04/2022 20:47:47 - INFO - codeparrot_training - Step 26666: {'lr': 0.0004665081198392133, 'samples': 13653504, 'steps': 26666, 'loss/train': 2.037874221801758}
-03/04/2022 20:47:49 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/04/2022 20:47:52 - INFO - codeparrot_training - Step 26667: {'lr': 0.0004665054664832988, 'samples': 13654016, 'steps': 26667, 'loss/train': 1.7718651294708252}
-03/04/2022 20:47:55 - INFO - codeparrot_training - Step 26668: {'lr': 0.00046650281302983024, 'samples': 13654528, 'steps': 26668, 'loss/train': 1.981916069984436}
-03/04/2022 20:47:58 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 20:48:00 - INFO - codeparrot_training - Step 26669: {'lr': 0.00046650015947880886, 'samples': 13655040, 'steps': 26669, 'loss/train': 1.6942044496536255}
-03/04/2022 20:48:04 - INFO - codeparrot_training - Step 26670: {'lr': 0.00046649750583023595, 'samples': 13655552, 'steps': 26670, 'loss/train': 2.0728018283843994}
-03/04/2022 20:48:07 - INFO - codeparrot_training - Step 26671: {'lr': 0.00046649485208411244, 'samples': 13656064, 'steps': 26671, 'loss/train': 1.7234209775924683}
-03/04/2022 20:48:07 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/04/2022 20:48:12 - INFO - codeparrot_training - Step 26672: {'lr': 0.00046649219824043984, 'samples': 13656576, 'steps': 26672, 'loss/train': 0.9366819262504578}
-03/04/2022 20:48:15 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/04/2022 20:48:17 - INFO - codeparrot_training - Step 26673: {'lr': 0.00046648954429921914, 'samples': 13657088, 'steps': 26673, 'loss/train': 1.784995436668396}
-03/04/2022 20:48:21 - INFO - codeparrot_training - Step 26674: {'lr': 0.00046648689026045157, 'samples': 13657600, 'steps': 26674, 'loss/train': 1.9957302808761597}
-03/04/2022 20:48:24 - INFO - codeparrot_training - Step 26675: {'lr': 0.0004664842361241384, 'samples': 13658112, 'steps': 26675, 'loss/train': 0.6632347106933594}
-03/04/2022 20:48:24 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/04/2022 20:48:29 - INFO - codeparrot_training - Step 26676: {'lr': 0.00046648158189028073, 'samples': 13658624, 'steps': 26676, 'loss/train': 1.3486677408218384}
-03/04/2022 20:48:32 - INFO - codeparrot_training - Step 26677: {'lr': 0.0004664789275588798, 'samples': 13659136, 'steps': 26677, 'loss/train': 0.1966020166873932}
-03/04/2022 20:48:32 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/04/2022 20:48:38 - INFO - codeparrot_training - Step 26678: {'lr': 0.0004664762731299368, 'samples': 13659648, 'steps': 26678, 'loss/train': 1.8229998350143433}
-03/04/2022 20:48:40 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/04/2022 20:48:43 - INFO - codeparrot_training - Step 26679: {'lr': 0.00046647361860345293, 'samples': 13660160, 'steps': 26679, 'loss/train': 1.8731719255447388}
-03/04/2022 20:48:46 - INFO - codeparrot_training - Step 26680: {'lr': 0.00046647096397942945, 'samples': 13660672, 'steps': 26680, 'loss/train': 1.4844691753387451}
-03/04/2022 20:48:49 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 20:48:51 - INFO - codeparrot_training - Step 26681: {'lr': 0.0004664683092578674, 'samples': 13661184, 'steps': 26681, 'loss/train': 1.3100836277008057}
-03/04/2022 20:48:55 - INFO - codeparrot_training - Step 26682: {'lr': 0.00046646565443876815, 'samples': 13661696, 'steps': 26682, 'loss/train': 1.40003502368927}
-03/04/2022 20:48:57 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 20:49:00 - INFO - codeparrot_training - Step 26683: {'lr': 0.00046646299952213277, 'samples': 13662208, 'steps': 26683, 'loss/train': 1.8873366117477417}
-03/04/2022 20:49:03 - INFO - codeparrot_training - Step 26684: {'lr': 0.00046646034450796255, 'samples': 13662720, 'steps': 26684, 'loss/train': 1.8637052774429321}
-03/04/2022 20:49:06 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/04/2022 20:49:08 - INFO - codeparrot_training - Step 26685: {'lr': 0.0004664576893962586, 'samples': 13663232, 'steps': 26685, 'loss/train': 1.2652688026428223}
-03/04/2022 20:49:12 - INFO - codeparrot_training - Step 26686: {'lr': 0.0004664550341870222, 'samples': 13663744, 'steps': 26686, 'loss/train': 0.8165706396102905}
-03/04/2022 20:49:14 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/04/2022 20:49:17 - INFO - codeparrot_training - Step 26687: {'lr': 0.00046645237888025444, 'samples': 13664256, 'steps': 26687, 'loss/train': 1.6000189781188965}
-03/04/2022 20:49:20 - INFO - codeparrot_training - Step 26688: {'lr': 0.0004664497234759566, 'samples': 13664768, 'steps': 26688, 'loss/train': 1.890013575553894}
-03/04/2022 20:49:23 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 20:49:25 - INFO - codeparrot_training - Step 26689: {'lr': 0.00046644706797412984, 'samples': 13665280, 'steps': 26689, 'loss/train': 1.6908893585205078}
-03/04/2022 20:49:29 - INFO - codeparrot_training - Step 26690: {'lr': 0.00046644441237477544, 'samples': 13665792, 'steps': 26690, 'loss/train': 2.1045820713043213}
-03/04/2022 20:49:31 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/04/2022 20:49:34 - INFO - codeparrot_training - Step 26691: {'lr': 0.00046644175667789444, 'samples': 13666304, 'steps': 26691, 'loss/train': 1.4937067031860352}
-03/04/2022 20:49:37 - INFO - codeparrot_training - Step 26692: {'lr': 0.00046643910088348817, 'samples': 13666816, 'steps': 26692, 'loss/train': 1.9463579654693604}
-03/04/2022 20:49:39 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/04/2022 20:49:42 - INFO - codeparrot_training - Step 26693: {'lr': 0.0004664364449915578, 'samples': 13667328, 'steps': 26693, 'loss/train': 1.8870209455490112}
-03/04/2022 20:49:45 - INFO - codeparrot_training - Step 26694: {'lr': 0.0004664337890021044, 'samples': 13667840, 'steps': 26694, 'loss/train': 1.4400068521499634}
-03/04/2022 20:49:48 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/04/2022 20:49:51 - INFO - codeparrot_training - Step 26695: {'lr': 0.0004664311329151294, 'samples': 13668352, 'steps': 26695, 'loss/train': 1.4525578022003174}
-03/04/2022 20:49:54 - INFO - codeparrot_training - Step 26696: {'lr': 0.0004664284767306338, 'samples': 13668864, 'steps': 26696, 'loss/train': 0.8865824341773987}
-03/04/2022 20:49:57 - INFO - codeparrot_training - Step 26697: {'lr': 0.0004664258204486189, 'samples': 13669376, 'steps': 26697, 'loss/train': 1.181544542312622}
-03/04/2022 20:49:58 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/04/2022 20:50:03 - INFO - codeparrot_training - Step 26698: {'lr': 0.0004664231640690859, 'samples': 13669888, 'steps': 26698, 'loss/train': 2.6543309688568115}
-03/04/2022 20:50:06 - INFO - codeparrot_training - Step 26699: {'lr': 0.0004664205075920359, 'samples': 13670400, 'steps': 26699, 'loss/train': 0.8751461505889893}
-03/04/2022 20:50:06 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/04/2022 20:50:11 - INFO - codeparrot_training - Step 26700: {'lr': 0.0004664178510174702, 'samples': 13670912, 'steps': 26700, 'loss/train': 1.6041452884674072}
-03/04/2022 20:50:14 - INFO - codeparrot_training - Step 26701: {'lr': 0.0004664151943453899, 'samples': 13671424, 'steps': 26701, 'loss/train': 1.0287470817565918}
-03/04/2022 20:50:14 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 20:50:19 - INFO - codeparrot_training - Step 26702: {'lr': 0.0004664125375757963, 'samples': 13671936, 'steps': 26702, 'loss/train': 1.899570345878601}
-03/04/2022 20:50:23 - INFO - codeparrot_training - Step 26703: {'lr': 0.00046640988070869053, 'samples': 13672448, 'steps': 26703, 'loss/train': 1.9523086547851562}
-03/04/2022 20:50:23 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/04/2022 20:50:28 - INFO - codeparrot_training - Step 26704: {'lr': 0.00046640722374407384, 'samples': 13672960, 'steps': 26704, 'loss/train': 2.289858341217041}
-03/04/2022 20:50:31 - INFO - codeparrot_training - Step 26705: {'lr': 0.00046640456668194737, 'samples': 13673472, 'steps': 26705, 'loss/train': 2.0405712127685547}
-03/04/2022 20:50:31 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/04/2022 20:50:36 - INFO - codeparrot_training - Step 26706: {'lr': 0.0004664019095223123, 'samples': 13673984, 'steps': 26706, 'loss/train': 1.9924113750457764}
-03/04/2022 20:50:39 - INFO - codeparrot_training - Step 26707: {'lr': 0.00046639925226517, 'samples': 13674496, 'steps': 26707, 'loss/train': 1.671492338180542}
-03/04/2022 20:50:39 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/04/2022 20:50:45 - INFO - codeparrot_training - Step 26708: {'lr': 0.0004663965949105214, 'samples': 13675008, 'steps': 26708, 'loss/train': 2.14054274559021}
-03/04/2022 20:50:48 - INFO - codeparrot_training - Step 26709: {'lr': 0.0004663939374583679, 'samples': 13675520, 'steps': 26709, 'loss/train': 1.7124980688095093}
-03/04/2022 20:50:48 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 20:50:54 - INFO - codeparrot_training - Step 26710: {'lr': 0.00046639127990871055, 'samples': 13676032, 'steps': 26710, 'loss/train': 2.3323233127593994}
-03/04/2022 20:50:57 - INFO - codeparrot_training - Step 26711: {'lr': 0.00046638862226155075, 'samples': 13676544, 'steps': 26711, 'loss/train': 5.955111503601074}
-03/04/2022 20:51:00 - INFO - codeparrot_training - Step 26712: {'lr': 0.0004663859645168895, 'samples': 13677056, 'steps': 26712, 'loss/train': 2.474405527114868}
-03/04/2022 20:51:00 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/04/2022 20:51:05 - INFO - codeparrot_training - Step 26713: {'lr': 0.00046638330667472805, 'samples': 13677568, 'steps': 26713, 'loss/train': 1.805928111076355}
-03/04/2022 20:51:08 - INFO - codeparrot_training - Step 26714: {'lr': 0.0004663806487350677, 'samples': 13678080, 'steps': 26714, 'loss/train': 6.692773818969727}
-03/04/2022 20:51:09 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/04/2022 20:51:14 - INFO - codeparrot_training - Step 26715: {'lr': 0.00046637799069790953, 'samples': 13678592, 'steps': 26715, 'loss/train': 2.2610812187194824}
-03/04/2022 20:51:17 - INFO - codeparrot_training - Step 26716: {'lr': 0.00046637533256325476, 'samples': 13679104, 'steps': 26716, 'loss/train': 1.7981669902801514}
-03/04/2022 20:51:18 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/04/2022 20:51:22 - INFO - codeparrot_training - Step 26717: {'lr': 0.0004663726743311046, 'samples': 13679616, 'steps': 26717, 'loss/train': 6.598403453826904}
-03/04/2022 20:51:25 - INFO - codeparrot_training - Step 26718: {'lr': 0.00046637001600146027, 'samples': 13680128, 'steps': 26718, 'loss/train': 1.973952293395996}
-03/04/2022 20:51:27 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 20:51:31 - INFO - codeparrot_training - Step 26719: {'lr': 0.000466367357574323, 'samples': 13680640, 'steps': 26719, 'loss/train': 1.7913126945495605}
-03/04/2022 20:51:34 - INFO - codeparrot_training - Step 26720: {'lr': 0.00046636469904969387, 'samples': 13681152, 'steps': 26720, 'loss/train': 1.40028715133667}
-03/04/2022 20:51:35 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/04/2022 20:51:39 - INFO - codeparrot_training - Step 26721: {'lr': 0.0004663620404275741, 'samples': 13681664, 'steps': 26721, 'loss/train': 1.4481658935546875}
-03/04/2022 20:51:42 - INFO - codeparrot_training - Step 26722: {'lr': 0.00046635938170796505, 'samples': 13682176, 'steps': 26722, 'loss/train': 0.897899866104126}
-03/04/2022 20:51:44 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/04/2022 20:51:48 - INFO - codeparrot_training - Step 26723: {'lr': 0.00046635672289086774, 'samples': 13682688, 'steps': 26723, 'loss/train': 1.9261603355407715}
-03/04/2022 20:51:51 - INFO - codeparrot_training - Step 26724: {'lr': 0.00046635406397628346, 'samples': 13683200, 'steps': 26724, 'loss/train': 2.3305139541625977}
-03/04/2022 20:51:52 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/04/2022 20:51:56 - INFO - codeparrot_training - Step 26725: {'lr': 0.00046635140496421336, 'samples': 13683712, 'steps': 26725, 'loss/train': 1.206812858581543}
-03/04/2022 20:51:59 - INFO - codeparrot_training - Step 26726: {'lr': 0.0004663487458546586, 'samples': 13684224, 'steps': 26726, 'loss/train': 2.1753625869750977}
-03/04/2022 20:52:02 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/04/2022 20:52:05 - INFO - codeparrot_training - Step 26727: {'lr': 0.0004663460866476205, 'samples': 13684736, 'steps': 26727, 'loss/train': 2.2715835571289062}
-03/04/2022 20:52:08 - INFO - codeparrot_training - Step 26728: {'lr': 0.00046634342734310023, 'samples': 13685248, 'steps': 26728, 'loss/train': 1.3536500930786133}
-03/04/2022 20:52:10 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/04/2022 20:52:13 - INFO - codeparrot_training - Step 26729: {'lr': 0.0004663407679410988, 'samples': 13685760, 'steps': 26729, 'loss/train': 2.0546627044677734}
-03/04/2022 20:52:16 - INFO - codeparrot_training - Step 26730: {'lr': 0.0004663381084416177, 'samples': 13686272, 'steps': 26730, 'loss/train': 1.9673089981079102}
-03/04/2022 20:52:19 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 20:52:22 - INFO - codeparrot_training - Step 26731: {'lr': 0.00046633544884465796, 'samples': 13686784, 'steps': 26731, 'loss/train': 1.8400992155075073}
-03/04/2022 20:52:25 - INFO - codeparrot_training - Step 26732: {'lr': 0.0004663327891502208, 'samples': 13687296, 'steps': 26732, 'loss/train': 1.639454960823059}
-03/04/2022 20:52:27 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 20:52:30 - INFO - codeparrot_training - Step 26733: {'lr': 0.0004663301293583073, 'samples': 13687808, 'steps': 26733, 'loss/train': 1.8162367343902588}
-03/04/2022 20:52:33 - INFO - codeparrot_training - Step 26734: {'lr': 0.000466327469468919, 'samples': 13688320, 'steps': 26734, 'loss/train': 1.559457540512085}
-03/04/2022 20:52:36 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 20:52:38 - INFO - codeparrot_training - Step 26735: {'lr': 0.0004663248094820567, 'samples': 13688832, 'steps': 26735, 'loss/train': 1.785496473312378}
-03/04/2022 20:52:42 - INFO - codeparrot_training - Step 26736: {'lr': 0.00046632214939772187, 'samples': 13689344, 'steps': 26736, 'loss/train': 1.4931201934814453}
-03/04/2022 20:52:44 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 20:52:47 - INFO - codeparrot_training - Step 26737: {'lr': 0.0004663194892159156, 'samples': 13689856, 'steps': 26737, 'loss/train': 1.0998592376708984}
-03/04/2022 20:52:50 - INFO - codeparrot_training - Step 26738: {'lr': 0.0004663168289366391, 'samples': 13690368, 'steps': 26738, 'loss/train': 1.5991463661193848}
-03/04/2022 20:52:53 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/04/2022 20:52:56 - INFO - codeparrot_training - Step 26739: {'lr': 0.0004663141685598936, 'samples': 13690880, 'steps': 26739, 'loss/train': 1.5006264448165894}
-03/04/2022 20:52:59 - INFO - codeparrot_training - Step 26740: {'lr': 0.00046631150808568026, 'samples': 13691392, 'steps': 26740, 'loss/train': 2.0278966426849365}
-03/04/2022 20:53:02 - INFO - codeparrot_training - Step 26741: {'lr': 0.00046630884751400024, 'samples': 13691904, 'steps': 26741, 'loss/train': 2.2093558311462402}
-03/04/2022 20:53:02 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/04/2022 20:53:07 - INFO - codeparrot_training - Step 26742: {'lr': 0.0004663061868448548, 'samples': 13692416, 'steps': 26742, 'loss/train': 2.0519049167633057}
-03/04/2022 20:53:10 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/04/2022 20:53:13 - INFO - codeparrot_training - Step 26743: {'lr': 0.0004663035260782452, 'samples': 13692928, 'steps': 26743, 'loss/train': 1.7872018814086914}
-03/04/2022 20:53:16 - INFO - codeparrot_training - Step 26744: {'lr': 0.0004663008652141726, 'samples': 13693440, 'steps': 26744, 'loss/train': 1.6538136005401611}
-03/04/2022 20:53:19 - INFO - codeparrot_training - Step 26745: {'lr': 0.00046629820425263805, 'samples': 13693952, 'steps': 26745, 'loss/train': 2.3294997215270996}
-03/04/2022 20:53:19 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 20:53:24 - INFO - codeparrot_training - Step 26746: {'lr': 0.00046629554319364293, 'samples': 13694464, 'steps': 26746, 'loss/train': 2.1605207920074463}
-03/04/2022 20:53:27 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/04/2022 20:53:30 - INFO - codeparrot_training - Step 26747: {'lr': 0.00046629288203718834, 'samples': 13694976, 'steps': 26747, 'loss/train': 1.1768008470535278}
-03/04/2022 20:53:33 - INFO - codeparrot_training - Step 26748: {'lr': 0.00046629022078327557, 'samples': 13695488, 'steps': 26748, 'loss/train': 1.8717012405395508}
-03/04/2022 20:53:36 - INFO - codeparrot_training - Step 26749: {'lr': 0.0004662875594319057, 'samples': 13696000, 'steps': 26749, 'loss/train': 1.884063482284546}
-03/04/2022 20:53:36 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/04/2022 20:53:41 - INFO - codeparrot_training - Step 26750: {'lr': 0.00046628489798308006, 'samples': 13696512, 'steps': 26750, 'loss/train': 2.0499110221862793}
-03/04/2022 20:53:45 - INFO - codeparrot_training - Step 26751: {'lr': 0.0004662822364367997, 'samples': 13697024, 'steps': 26751, 'loss/train': 1.9151647090911865}
-03/04/2022 20:53:45 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/04/2022 20:53:50 - INFO - codeparrot_training - Step 26752: {'lr': 0.000466279574793066, 'samples': 13697536, 'steps': 26752, 'loss/train': 0.960995078086853}
-03/04/2022 20:53:53 - INFO - codeparrot_training - Step 26753: {'lr': 0.00046627691305188004, 'samples': 13698048, 'steps': 26753, 'loss/train': 2.462904214859009}
-03/04/2022 20:53:53 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/04/2022 20:53:58 - INFO - codeparrot_training - Step 26754: {'lr': 0.00046627425121324294, 'samples': 13698560, 'steps': 26754, 'loss/train': 1.6544512510299683}
-03/04/2022 20:54:02 - INFO - codeparrot_training - Step 26755: {'lr': 0.0004662715892771561, 'samples': 13699072, 'steps': 26755, 'loss/train': 0.49252554774284363}
-03/04/2022 20:54:02 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 20:54:07 - INFO - codeparrot_training - Step 26756: {'lr': 0.0004662689272436206, 'samples': 13699584, 'steps': 26756, 'loss/train': 1.0155199766159058}
-03/04/2022 20:54:10 - INFO - codeparrot_training - Step 26757: {'lr': 0.00046626626511263764, 'samples': 13700096, 'steps': 26757, 'loss/train': 2.544031858444214}
-03/04/2022 20:54:10 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/04/2022 20:54:15 - INFO - codeparrot_training - Step 26758: {'lr': 0.00046626360288420845, 'samples': 13700608, 'steps': 26758, 'loss/train': 0.5484464764595032}
-03/04/2022 20:54:18 - INFO - codeparrot_training - Step 26759: {'lr': 0.00046626094055833426, 'samples': 13701120, 'steps': 26759, 'loss/train': 1.8377954959869385}
-03/04/2022 20:54:18 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/04/2022 20:54:24 - INFO - codeparrot_training - Step 26760: {'lr': 0.0004662582781350161, 'samples': 13701632, 'steps': 26760, 'loss/train': 1.4961811304092407}
-03/04/2022 20:54:27 - INFO - codeparrot_training - Step 26761: {'lr': 0.00046625561561425543, 'samples': 13702144, 'steps': 26761, 'loss/train': 2.119016647338867}
-03/04/2022 20:54:28 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/04/2022 20:54:32 - INFO - codeparrot_training - Step 26762: {'lr': 0.00046625295299605323, 'samples': 13702656, 'steps': 26762, 'loss/train': 1.8316349983215332}
-03/04/2022 20:54:35 - INFO - codeparrot_training - Step 26763: {'lr': 0.0004662502902804109, 'samples': 13703168, 'steps': 26763, 'loss/train': 1.5876240730285645}
-03/04/2022 20:54:36 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 20:54:41 - INFO - codeparrot_training - Step 26764: {'lr': 0.0004662476274673294, 'samples': 13703680, 'steps': 26764, 'loss/train': 2.1906826496124268}
-03/04/2022 20:54:44 - INFO - codeparrot_training - Step 26765: {'lr': 0.00046624496455681006, 'samples': 13704192, 'steps': 26765, 'loss/train': 1.8430958986282349}
-03/04/2022 20:54:44 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 20:54:49 - INFO - codeparrot_training - Step 26766: {'lr': 0.00046624230154885415, 'samples': 13704704, 'steps': 26766, 'loss/train': 2.269381284713745}
-03/04/2022 20:54:52 - INFO - codeparrot_training - Step 26767: {'lr': 0.0004662396384434627, 'samples': 13705216, 'steps': 26767, 'loss/train': 1.2148300409317017}
-03/04/2022 20:54:53 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/04/2022 20:54:57 - INFO - codeparrot_training - Step 26768: {'lr': 0.00046623697524063713, 'samples': 13705728, 'steps': 26768, 'loss/train': 1.8138720989227295}
-03/04/2022 20:55:01 - INFO - codeparrot_training - Step 26769: {'lr': 0.00046623431194037847, 'samples': 13706240, 'steps': 26769, 'loss/train': 1.5771387815475464}
-03/04/2022 20:55:01 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/04/2022 20:55:06 - INFO - codeparrot_training - Step 26770: {'lr': 0.000466231648542688, 'samples': 13706752, 'steps': 26770, 'loss/train': 2.971315860748291}
-03/04/2022 20:55:09 - INFO - codeparrot_training - Step 26771: {'lr': 0.0004662289850475668, 'samples': 13707264, 'steps': 26771, 'loss/train': 1.7636375427246094}
-03/04/2022 20:55:10 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/04/2022 20:55:14 - INFO - codeparrot_training - Step 26772: {'lr': 0.0004662263214550162, 'samples': 13707776, 'steps': 26772, 'loss/train': 1.9939988851547241}
-03/04/2022 20:55:17 - INFO - codeparrot_training - Step 26773: {'lr': 0.00046622365776503735, 'samples': 13708288, 'steps': 26773, 'loss/train': 1.5807050466537476}
-03/04/2022 20:55:18 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/04/2022 20:55:23 - INFO - codeparrot_training - Step 26774: {'lr': 0.0004662209939776315, 'samples': 13708800, 'steps': 26774, 'loss/train': 1.9121589660644531}
-03/04/2022 20:55:26 - INFO - codeparrot_training - Step 26775: {'lr': 0.0004662183300927997, 'samples': 13709312, 'steps': 26775, 'loss/train': 2.4105429649353027}
-03/04/2022 20:55:27 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/04/2022 20:55:32 - INFO - codeparrot_training - Step 26776: {'lr': 0.0004662156661105433, 'samples': 13709824, 'steps': 26776, 'loss/train': 1.602795958518982}
-03/04/2022 20:55:35 - INFO - codeparrot_training - Step 26777: {'lr': 0.0004662130020308635, 'samples': 13710336, 'steps': 26777, 'loss/train': 1.6779029369354248}
-03/04/2022 20:55:36 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 20:55:40 - INFO - codeparrot_training - Step 26778: {'lr': 0.00046621033785376146, 'samples': 13710848, 'steps': 26778, 'loss/train': 2.1358914375305176}
-03/04/2022 20:55:43 - INFO - codeparrot_training - Step 26779: {'lr': 0.00046620767357923834, 'samples': 13711360, 'steps': 26779, 'loss/train': 1.6286842823028564}
-03/04/2022 20:55:44 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/04/2022 20:55:48 - INFO - codeparrot_training - Step 26780: {'lr': 0.0004662050092072954, 'samples': 13711872, 'steps': 26780, 'loss/train': 1.2755171060562134}
-03/04/2022 20:55:51 - INFO - codeparrot_training - Step 26781: {'lr': 0.0004662023447379338, 'samples': 13712384, 'steps': 26781, 'loss/train': 0.8289638757705688}
-03/04/2022 20:55:53 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 20:55:57 - INFO - codeparrot_training - Step 26782: {'lr': 0.0004661996801711548, 'samples': 13712896, 'steps': 26782, 'loss/train': 2.3932621479034424}
-03/04/2022 20:56:00 - INFO - codeparrot_training - Step 26783: {'lr': 0.0004661970155069595, 'samples': 13713408, 'steps': 26783, 'loss/train': 1.3078304529190063}
-03/04/2022 20:56:01 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 20:56:05 - INFO - codeparrot_training - Step 26784: {'lr': 0.00046619435074534923, 'samples': 13713920, 'steps': 26784, 'loss/train': 2.1332814693450928}
-03/04/2022 20:56:08 - INFO - codeparrot_training - Step 26785: {'lr': 0.0004661916858863251, 'samples': 13714432, 'steps': 26785, 'loss/train': 1.0629059076309204}
-03/04/2022 20:56:09 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/04/2022 20:56:13 - INFO - codeparrot_training - Step 26786: {'lr': 0.00046618902092988824, 'samples': 13714944, 'steps': 26786, 'loss/train': 0.9151431918144226}
-03/04/2022 20:56:17 - INFO - codeparrot_training - Step 26787: {'lr': 0.00046618635587604006, 'samples': 13715456, 'steps': 26787, 'loss/train': 1.870697021484375}
-03/04/2022 20:56:17 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/04/2022 20:56:22 - INFO - codeparrot_training - Step 26788: {'lr': 0.00046618369072478163, 'samples': 13715968, 'steps': 26788, 'loss/train': 1.8286612033843994}
-03/04/2022 20:56:25 - INFO - codeparrot_training - Step 26789: {'lr': 0.0004661810254761141, 'samples': 13716480, 'steps': 26789, 'loss/train': 1.6959599256515503}
-03/04/2022 20:56:25 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 20:56:31 - INFO - codeparrot_training - Step 26790: {'lr': 0.0004661783601300388, 'samples': 13716992, 'steps': 26790, 'loss/train': 1.1813629865646362}
-03/04/2022 20:56:34 - INFO - codeparrot_training - Step 26791: {'lr': 0.00046617569468655686, 'samples': 13717504, 'steps': 26791, 'loss/train': 1.6389458179473877}
-03/04/2022 20:56:37 - INFO - codeparrot_training - Step 26792: {'lr': 0.00046617302914566945, 'samples': 13718016, 'steps': 26792, 'loss/train': 2.364201784133911}
-03/04/2022 20:56:38 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/04/2022 20:56:43 - INFO - codeparrot_training - Step 26793: {'lr': 0.00046617036350737786, 'samples': 13718528, 'steps': 26793, 'loss/train': 1.9508531093597412}
-03/04/2022 20:56:46 - INFO - codeparrot_training - Step 26794: {'lr': 0.0004661676977716832, 'samples': 13719040, 'steps': 26794, 'loss/train': 1.8392504453659058}
-03/04/2022 20:56:46 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/04/2022 20:56:51 - INFO - codeparrot_training - Step 26795: {'lr': 0.0004661650319385867, 'samples': 13719552, 'steps': 26795, 'loss/train': 1.9261102676391602}
-03/04/2022 20:56:54 - INFO - codeparrot_training - Step 26796: {'lr': 0.0004661623660080896, 'samples': 13720064, 'steps': 26796, 'loss/train': 1.9575016498565674}
-03/04/2022 20:56:55 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/04/2022 20:56:59 - INFO - codeparrot_training - Step 26797: {'lr': 0.000466159699980193, 'samples': 13720576, 'steps': 26797, 'loss/train': 1.739269733428955}
-03/04/2022 20:57:03 - INFO - codeparrot_training - Step 26798: {'lr': 0.0004661570338548983, 'samples': 13721088, 'steps': 26798, 'loss/train': 2.4262988567352295}
-03/04/2022 20:57:03 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/04/2022 20:57:08 - INFO - codeparrot_training - Step 26799: {'lr': 0.00046615436763220645, 'samples': 13721600, 'steps': 26799, 'loss/train': 2.1114871501922607}
-03/04/2022 20:57:11 - INFO - codeparrot_training - Step 26800: {'lr': 0.0004661517013121189, 'samples': 13722112, 'steps': 26800, 'loss/train': 1.958483338356018}
-03/04/2022 20:57:11 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/04/2022 20:57:16 - INFO - codeparrot_training - Step 26801: {'lr': 0.00046614903489463667, 'samples': 13722624, 'steps': 26801, 'loss/train': 1.774544596672058}
-03/04/2022 20:57:19 - INFO - codeparrot_training - Step 26802: {'lr': 0.000466146368379761, 'samples': 13723136, 'steps': 26802, 'loss/train': 2.366953134536743}
-03/04/2022 20:57:19 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/04/2022 20:57:25 - INFO - codeparrot_training - Step 26803: {'lr': 0.0004661437017674931, 'samples': 13723648, 'steps': 26803, 'loss/train': 1.7530736923217773}
-03/04/2022 20:57:28 - INFO - codeparrot_training - Step 26804: {'lr': 0.00046614103505783423, 'samples': 13724160, 'steps': 26804, 'loss/train': 1.3962421417236328}
-03/04/2022 20:57:28 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 20:57:33 - INFO - codeparrot_training - Step 26805: {'lr': 0.0004661383682507856, 'samples': 13724672, 'steps': 26805, 'loss/train': 1.9255813360214233}
-03/04/2022 20:57:36 - INFO - codeparrot_training - Step 26806: {'lr': 0.00046613570134634825, 'samples': 13725184, 'steps': 26806, 'loss/train': 2.706526279449463}
-03/04/2022 20:57:36 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 20:57:42 - INFO - codeparrot_training - Step 26807: {'lr': 0.00046613303434452346, 'samples': 13725696, 'steps': 26807, 'loss/train': 1.5704504251480103}
-03/04/2022 20:57:45 - INFO - codeparrot_training - Step 26808: {'lr': 0.00046613036724531254, 'samples': 13726208, 'steps': 26808, 'loss/train': 2.387249708175659}
-03/04/2022 20:57:46 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 20:57:50 - INFO - codeparrot_training - Step 26809: {'lr': 0.00046612770004871663, 'samples': 13726720, 'steps': 26809, 'loss/train': 2.4342329502105713}
-03/04/2022 20:57:53 - INFO - codeparrot_training - Step 26810: {'lr': 0.00046612503275473687, 'samples': 13727232, 'steps': 26810, 'loss/train': 1.8359522819519043}
-03/04/2022 20:57:54 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 20:57:59 - INFO - codeparrot_training - Step 26811: {'lr': 0.00046612236536337456, 'samples': 13727744, 'steps': 26811, 'loss/train': 2.5119807720184326}
-03/04/2022 20:58:02 - INFO - codeparrot_training - Step 26812: {'lr': 0.00046611969787463083, 'samples': 13728256, 'steps': 26812, 'loss/train': 1.1894862651824951}
-03/04/2022 20:58:03 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/04/2022 20:58:07 - INFO - codeparrot_training - Step 26813: {'lr': 0.00046611703028850683, 'samples': 13728768, 'steps': 26813, 'loss/train': 2.3573427200317383}
-03/04/2022 20:58:11 - INFO - codeparrot_training - Step 26814: {'lr': 0.00046611436260500386, 'samples': 13729280, 'steps': 26814, 'loss/train': 1.7114008665084839}
-03/04/2022 20:58:12 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/04/2022 20:58:16 - INFO - codeparrot_training - Step 26815: {'lr': 0.00046611169482412305, 'samples': 13729792, 'steps': 26815, 'loss/train': 1.8820774555206299}
-03/04/2022 20:58:19 - INFO - codeparrot_training - Step 26816: {'lr': 0.00046610902694586576, 'samples': 13730304, 'steps': 26816, 'loss/train': 1.5594134330749512}
-03/04/2022 20:58:21 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/04/2022 20:58:24 - INFO - codeparrot_training - Step 26817: {'lr': 0.00046610635897023303, 'samples': 13730816, 'steps': 26817, 'loss/train': 1.8868751525878906}
-03/04/2022 20:58:28 - INFO - codeparrot_training - Step 26818: {'lr': 0.0004661036908972261, 'samples': 13731328, 'steps': 26818, 'loss/train': 1.5075949430465698}
-03/04/2022 20:58:29 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/04/2022 20:58:33 - INFO - codeparrot_training - Step 26819: {'lr': 0.0004661010227268462, 'samples': 13731840, 'steps': 26819, 'loss/train': 0.6462875604629517}
-03/04/2022 20:58:36 - INFO - codeparrot_training - Step 26820: {'lr': 0.0004660983544590944, 'samples': 13732352, 'steps': 26820, 'loss/train': 1.8443554639816284}
-03/04/2022 20:58:37 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/04/2022 20:58:41 - INFO - codeparrot_training - Step 26821: {'lr': 0.0004660956860939722, 'samples': 13732864, 'steps': 26821, 'loss/train': 1.1227312088012695}
-03/04/2022 20:58:45 - INFO - codeparrot_training - Step 26822: {'lr': 0.0004660930176314805, 'samples': 13733376, 'steps': 26822, 'loss/train': 1.2645559310913086}
-03/04/2022 20:58:46 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/04/2022 20:58:50 - INFO - codeparrot_training - Step 26823: {'lr': 0.0004660903490716206, 'samples': 13733888, 'steps': 26823, 'loss/train': 1.5876251459121704}
-03/04/2022 20:58:53 - INFO - codeparrot_training - Step 26824: {'lr': 0.0004660876804143938, 'samples': 13734400, 'steps': 26824, 'loss/train': 2.0230329036712646}
-03/04/2022 20:58:55 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 20:58:58 - INFO - codeparrot_training - Step 26825: {'lr': 0.0004660850116598012, 'samples': 13734912, 'steps': 26825, 'loss/train': 1.7992655038833618}
-03/04/2022 20:59:01 - INFO - codeparrot_training - Step 26826: {'lr': 0.00046608234280784406, 'samples': 13735424, 'steps': 26826, 'loss/train': 1.691169023513794}
-03/04/2022 20:59:03 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/04/2022 20:59:07 - INFO - codeparrot_training - Step 26827: {'lr': 0.0004660796738585235, 'samples': 13735936, 'steps': 26827, 'loss/train': 1.6293751001358032}
-03/04/2022 20:59:10 - INFO - codeparrot_training - Step 26828: {'lr': 0.0004660770048118408, 'samples': 13736448, 'steps': 26828, 'loss/train': 1.0595265626907349}
-03/04/2022 20:59:12 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/04/2022 20:59:15 - INFO - codeparrot_training - Step 26829: {'lr': 0.00046607433566779713, 'samples': 13736960, 'steps': 26829, 'loss/train': 1.870438575744629}
-03/04/2022 20:59:18 - INFO - codeparrot_training - Step 26830: {'lr': 0.00046607166642639365, 'samples': 13737472, 'steps': 26830, 'loss/train': 2.0925443172454834}
-03/04/2022 20:59:20 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/04/2022 20:59:24 - INFO - codeparrot_training - Step 26831: {'lr': 0.00046606899708763174, 'samples': 13737984, 'steps': 26831, 'loss/train': 2.2272346019744873}
-03/04/2022 20:59:27 - INFO - codeparrot_training - Step 26832: {'lr': 0.0004660663276515124, 'samples': 13738496, 'steps': 26832, 'loss/train': 1.059781789779663}
-03/04/2022 20:59:28 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 20:59:32 - INFO - codeparrot_training - Step 26833: {'lr': 0.00046606365811803686, 'samples': 13739008, 'steps': 26833, 'loss/train': 1.7172563076019287}
-03/04/2022 20:59:35 - INFO - codeparrot_training - Step 26834: {'lr': 0.0004660609884872064, 'samples': 13739520, 'steps': 26834, 'loss/train': 1.5828953981399536}
-03/04/2022 20:59:37 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 20:59:41 - INFO - codeparrot_training - Step 26835: {'lr': 0.00046605831875902215, 'samples': 13740032, 'steps': 26835, 'loss/train': 2.0359396934509277}
-03/04/2022 20:59:44 - INFO - codeparrot_training - Step 26836: {'lr': 0.00046605564893348545, 'samples': 13740544, 'steps': 26836, 'loss/train': 3.368013381958008}
-03/04/2022 20:59:48 - INFO - codeparrot_training - Step 26837: {'lr': 0.0004660529790105974, 'samples': 13741056, 'steps': 26837, 'loss/train': 2.1502716541290283}
-03/04/2022 20:59:49 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/04/2022 20:59:53 - INFO - codeparrot_training - Step 26838: {'lr': 0.00046605030899035915, 'samples': 13741568, 'steps': 26838, 'loss/train': 1.1533163785934448}
-03/04/2022 20:59:56 - INFO - codeparrot_training - Step 26839: {'lr': 0.000466047638872772, 'samples': 13742080, 'steps': 26839, 'loss/train': 1.6251182556152344}
-03/04/2022 20:59:57 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/04/2022 21:00:01 - INFO - codeparrot_training - Step 26840: {'lr': 0.0004660449686578371, 'samples': 13742592, 'steps': 26840, 'loss/train': 1.8646130561828613}
-03/04/2022 21:00:05 - INFO - codeparrot_training - Step 26841: {'lr': 0.0004660422983455557, 'samples': 13743104, 'steps': 26841, 'loss/train': 1.8938318490982056}
-03/04/2022 21:00:06 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 21:00:10 - INFO - codeparrot_training - Step 26842: {'lr': 0.0004660396279359289, 'samples': 13743616, 'steps': 26842, 'loss/train': 1.8495512008666992}
-03/04/2022 21:00:13 - INFO - codeparrot_training - Step 26843: {'lr': 0.000466036957428958, 'samples': 13744128, 'steps': 26843, 'loss/train': 1.705845832824707}
-03/04/2022 21:00:15 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 21:00:18 - INFO - codeparrot_training - Step 26844: {'lr': 0.0004660342868246442, 'samples': 13744640, 'steps': 26844, 'loss/train': 1.7729588747024536}
-03/04/2022 21:00:21 - INFO - codeparrot_training - Step 26845: {'lr': 0.0004660316161229887, 'samples': 13745152, 'steps': 26845, 'loss/train': 2.334062337875366}
-03/04/2022 21:00:23 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/04/2022 21:00:27 - INFO - codeparrot_training - Step 26846: {'lr': 0.00046602894532399275, 'samples': 13745664, 'steps': 26846, 'loss/train': 2.180962324142456}
-03/04/2022 21:00:30 - INFO - codeparrot_training - Step 26847: {'lr': 0.00046602627442765744, 'samples': 13746176, 'steps': 26847, 'loss/train': 1.7380377054214478}
-03/04/2022 21:00:31 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/04/2022 21:00:35 - INFO - codeparrot_training - Step 26848: {'lr': 0.00046602360343398397, 'samples': 13746688, 'steps': 26848, 'loss/train': 1.6574586629867554}
-03/04/2022 21:00:38 - INFO - codeparrot_training - Step 26849: {'lr': 0.0004660209323429736, 'samples': 13747200, 'steps': 26849, 'loss/train': 1.5669090747833252}
-03/04/2022 21:00:40 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 21:00:44 - INFO - codeparrot_training - Step 26850: {'lr': 0.0004660182611546276, 'samples': 13747712, 'steps': 26850, 'loss/train': 1.1924272775650024}
-03/04/2022 21:00:47 - INFO - codeparrot_training - Step 26851: {'lr': 0.0004660155898689471, 'samples': 13748224, 'steps': 26851, 'loss/train': 1.6120572090148926}
-03/04/2022 21:00:49 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/04/2022 21:00:52 - INFO - codeparrot_training - Step 26852: {'lr': 0.0004660129184859332, 'samples': 13748736, 'steps': 26852, 'loss/train': 1.6276812553405762}
-03/04/2022 21:00:55 - INFO - codeparrot_training - Step 26853: {'lr': 0.00046601024700558736, 'samples': 13749248, 'steps': 26853, 'loss/train': 2.6847753524780273}
-03/04/2022 21:00:57 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/04/2022 21:01:01 - INFO - codeparrot_training - Step 26854: {'lr': 0.0004660075754279105, 'samples': 13749760, 'steps': 26854, 'loss/train': 1.4832788705825806}
-03/04/2022 21:01:04 - INFO - codeparrot_training - Step 26855: {'lr': 0.00046600490375290406, 'samples': 13750272, 'steps': 26855, 'loss/train': 1.7771449089050293}
-03/04/2022 21:01:06 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/04/2022 21:01:09 - INFO - codeparrot_training - Step 26856: {'lr': 0.0004660022319805691, 'samples': 13750784, 'steps': 26856, 'loss/train': 1.7487356662750244}
-03/04/2022 21:01:12 - INFO - codeparrot_training - Step 26857: {'lr': 0.0004659995601109069, 'samples': 13751296, 'steps': 26857, 'loss/train': 1.9064791202545166}
-03/04/2022 21:01:14 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 21:01:18 - INFO - codeparrot_training - Step 26858: {'lr': 0.0004659968881439186, 'samples': 13751808, 'steps': 26858, 'loss/train': 2.022096872329712}
-03/04/2022 21:01:21 - INFO - codeparrot_training - Step 26859: {'lr': 0.00046599421607960545, 'samples': 13752320, 'steps': 26859, 'loss/train': 1.6218641996383667}
-03/04/2022 21:01:23 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 21:01:26 - INFO - codeparrot_training - Step 26860: {'lr': 0.0004659915439179686, 'samples': 13752832, 'steps': 26860, 'loss/train': 1.7284876108169556}
-03/04/2022 21:01:29 - INFO - codeparrot_training - Step 26861: {'lr': 0.0004659888716590094, 'samples': 13753344, 'steps': 26861, 'loss/train': 2.1894519329071045}
-03/04/2022 21:01:31 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 21:01:34 - INFO - codeparrot_training - Step 26862: {'lr': 0.00046598619930272883, 'samples': 13753856, 'steps': 26862, 'loss/train': 2.325878858566284}
-03/04/2022 21:01:38 - INFO - codeparrot_training - Step 26863: {'lr': 0.00046598352684912824, 'samples': 13754368, 'steps': 26863, 'loss/train': 2.099714994430542}
-03/04/2022 21:01:40 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/04/2022 21:01:43 - INFO - codeparrot_training - Step 26864: {'lr': 0.0004659808542982088, 'samples': 13754880, 'steps': 26864, 'loss/train': 2.2697854042053223}
-03/04/2022 21:01:46 - INFO - codeparrot_training - Step 26865: {'lr': 0.0004659781816499718, 'samples': 13755392, 'steps': 26865, 'loss/train': 1.641038417816162}
-03/04/2022 21:01:48 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/04/2022 21:01:51 - INFO - codeparrot_training - Step 26866: {'lr': 0.0004659755089044183, 'samples': 13755904, 'steps': 26866, 'loss/train': 1.6898154020309448}
-03/04/2022 21:01:54 - INFO - codeparrot_training - Step 26867: {'lr': 0.00046597283606154957, 'samples': 13756416, 'steps': 26867, 'loss/train': 1.8515864610671997}
-03/04/2022 21:01:57 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/04/2022 21:02:00 - INFO - codeparrot_training - Step 26868: {'lr': 0.0004659701631213668, 'samples': 13756928, 'steps': 26868, 'loss/train': 2.666245460510254}
-03/04/2022 21:02:03 - INFO - codeparrot_training - Step 26869: {'lr': 0.00046596749008387124, 'samples': 13757440, 'steps': 26869, 'loss/train': 2.086841583251953}
-03/04/2022 21:02:05 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 21:02:08 - INFO - codeparrot_training - Step 26870: {'lr': 0.00046596481694906403, 'samples': 13757952, 'steps': 26870, 'loss/train': 2.137169361114502}
-03/04/2022 21:02:11 - INFO - codeparrot_training - Step 26871: {'lr': 0.00046596214371694643, 'samples': 13758464, 'steps': 26871, 'loss/train': 2.2387752532958984}
-03/04/2022 21:02:14 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/04/2022 21:02:17 - INFO - codeparrot_training - Step 26872: {'lr': 0.00046595947038751963, 'samples': 13758976, 'steps': 26872, 'loss/train': 1.7299578189849854}
-03/04/2022 21:02:20 - INFO - codeparrot_training - Step 26873: {'lr': 0.00046595679696078476, 'samples': 13759488, 'steps': 26873, 'loss/train': 1.876828670501709}
-03/04/2022 21:02:22 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/04/2022 21:02:25 - INFO - codeparrot_training - Step 26874: {'lr': 0.00046595412343674317, 'samples': 13760000, 'steps': 26874, 'loss/train': 1.9129383563995361}
-03/04/2022 21:02:28 - INFO - codeparrot_training - Step 26875: {'lr': 0.00046595144981539596, 'samples': 13760512, 'steps': 26875, 'loss/train': 1.3868958950042725}
-03/04/2022 21:02:30 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 21:02:33 - INFO - codeparrot_training - Step 26876: {'lr': 0.00046594877609674437, 'samples': 13761024, 'steps': 26876, 'loss/train': 0.19592063128948212}
-03/04/2022 21:02:37 - INFO - codeparrot_training - Step 26877: {'lr': 0.00046594610228078954, 'samples': 13761536, 'steps': 26877, 'loss/train': 2.623413324356079}
-03/04/2022 21:02:39 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/04/2022 21:02:42 - INFO - codeparrot_training - Step 26878: {'lr': 0.00046594342836753276, 'samples': 13762048, 'steps': 26878, 'loss/train': 2.1538541316986084}
-03/04/2022 21:02:45 - INFO - codeparrot_training - Step 26879: {'lr': 0.0004659407543569752, 'samples': 13762560, 'steps': 26879, 'loss/train': 1.8404595851898193}
-03/04/2022 21:02:48 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/04/2022 21:02:51 - INFO - codeparrot_training - Step 26880: {'lr': 0.0004659380802491181, 'samples': 13763072, 'steps': 26880, 'loss/train': 1.980209231376648}
-03/04/2022 21:02:54 - INFO - codeparrot_training - Step 26881: {'lr': 0.00046593540604396256, 'samples': 13763584, 'steps': 26881, 'loss/train': 1.6889338493347168}
-03/04/2022 21:02:56 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/04/2022 21:02:59 - INFO - codeparrot_training - Step 26882: {'lr': 0.00046593273174150995, 'samples': 13764096, 'steps': 26882, 'loss/train': 2.3550567626953125}
-03/04/2022 21:03:02 - INFO - codeparrot_training - Step 26883: {'lr': 0.0004659300573417613, 'samples': 13764608, 'steps': 26883, 'loss/train': 2.1005825996398926}
-03/04/2022 21:03:04 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/04/2022 21:03:07 - INFO - codeparrot_training - Step 26884: {'lr': 0.00046592738284471794, 'samples': 13765120, 'steps': 26884, 'loss/train': 1.7370342016220093}
-03/04/2022 21:03:11 - INFO - codeparrot_training - Step 26885: {'lr': 0.000465924708250381, 'samples': 13765632, 'steps': 26885, 'loss/train': 1.626375675201416}
-03/04/2022 21:03:13 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/04/2022 21:03:16 - INFO - codeparrot_training - Step 26886: {'lr': 0.00046592203355875177, 'samples': 13766144, 'steps': 26886, 'loss/train': 1.3553518056869507}
-03/04/2022 21:03:19 - INFO - codeparrot_training - Step 26887: {'lr': 0.00046591935876983136, 'samples': 13766656, 'steps': 26887, 'loss/train': 1.6720315217971802}
-03/04/2022 21:03:21 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 21:03:24 - INFO - codeparrot_training - Step 26888: {'lr': 0.0004659166838836211, 'samples': 13767168, 'steps': 26888, 'loss/train': 1.36971914768219}
-03/04/2022 21:03:27 - INFO - codeparrot_training - Step 26889: {'lr': 0.000465914008900122, 'samples': 13767680, 'steps': 26889, 'loss/train': 2.0922796726226807}
-03/04/2022 21:03:30 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 21:03:33 - INFO - codeparrot_training - Step 26890: {'lr': 0.00046591133381933546, 'samples': 13768192, 'steps': 26890, 'loss/train': 1.967210054397583}
-03/04/2022 21:03:36 - INFO - codeparrot_training - Step 26891: {'lr': 0.0004659086586412626, 'samples': 13768704, 'steps': 26891, 'loss/train': 1.7520339488983154}
-03/04/2022 21:03:38 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/04/2022 21:03:41 - INFO - codeparrot_training - Step 26892: {'lr': 0.0004659059833659046, 'samples': 13769216, 'steps': 26892, 'loss/train': 2.4216220378875732}
-03/04/2022 21:03:44 - INFO - codeparrot_training - Step 26893: {'lr': 0.0004659033079932627, 'samples': 13769728, 'steps': 26893, 'loss/train': 1.9866973161697388}
-03/04/2022 21:03:46 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/04/2022 21:03:50 - INFO - codeparrot_training - Step 26894: {'lr': 0.00046590063252333806, 'samples': 13770240, 'steps': 26894, 'loss/train': 1.7901705503463745}
-03/04/2022 21:03:53 - INFO - codeparrot_training - Step 26895: {'lr': 0.000465897956956132, 'samples': 13770752, 'steps': 26895, 'loss/train': 1.4143060445785522}
-03/04/2022 21:03:55 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 21:03:58 - INFO - codeparrot_training - Step 26896: {'lr': 0.0004658952812916456, 'samples': 13771264, 'steps': 26896, 'loss/train': 1.4676921367645264}
-03/04/2022 21:04:01 - INFO - codeparrot_training - Step 26897: {'lr': 0.0004658926055298802, 'samples': 13771776, 'steps': 26897, 'loss/train': 2.439800977706909}
-03/04/2022 21:04:03 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 21:04:07 - INFO - codeparrot_training - Step 26898: {'lr': 0.0004658899296708369, 'samples': 13772288, 'steps': 26898, 'loss/train': 1.5424342155456543}
-03/04/2022 21:04:10 - INFO - codeparrot_training - Step 26899: {'lr': 0.00046588725371451685, 'samples': 13772800, 'steps': 26899, 'loss/train': 1.947596788406372}
-03/04/2022 21:04:12 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/04/2022 21:04:15 - INFO - codeparrot_training - Step 26900: {'lr': 0.00046588457766092134, 'samples': 13773312, 'steps': 26900, 'loss/train': 2.148871898651123}
-03/04/2022 21:04:18 - INFO - codeparrot_training - Step 26901: {'lr': 0.00046588190151005163, 'samples': 13773824, 'steps': 26901, 'loss/train': 1.954790472984314}
-03/04/2022 21:04:21 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/04/2022 21:04:24 - INFO - codeparrot_training - Step 26902: {'lr': 0.00046587922526190883, 'samples': 13774336, 'steps': 26902, 'loss/train': 2.4236133098602295}
-03/04/2022 21:04:27 - INFO - codeparrot_training - Step 26903: {'lr': 0.00046587654891649423, 'samples': 13774848, 'steps': 26903, 'loss/train': 2.181058883666992}
-03/04/2022 21:04:29 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/04/2022 21:04:32 - INFO - codeparrot_training - Step 26904: {'lr': 0.00046587387247380897, 'samples': 13775360, 'steps': 26904, 'loss/train': 1.8829150199890137}
-03/04/2022 21:04:35 - INFO - codeparrot_training - Step 26905: {'lr': 0.00046587119593385424, 'samples': 13775872, 'steps': 26905, 'loss/train': 0.2675618827342987}
-03/04/2022 21:04:37 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/04/2022 21:04:40 - INFO - codeparrot_training - Step 26906: {'lr': 0.00046586851929663134, 'samples': 13776384, 'steps': 26906, 'loss/train': 2.0829412937164307}
-03/04/2022 21:04:44 - INFO - codeparrot_training - Step 26907: {'lr': 0.00046586584256214135, 'samples': 13776896, 'steps': 26907, 'loss/train': 1.401829481124878}
-03/04/2022 21:04:46 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/04/2022 21:04:49 - INFO - codeparrot_training - Step 26908: {'lr': 0.0004658631657303856, 'samples': 13777408, 'steps': 26908, 'loss/train': 2.182494640350342}
-03/04/2022 21:04:52 - INFO - codeparrot_training - Step 26909: {'lr': 0.0004658604888013652, 'samples': 13777920, 'steps': 26909, 'loss/train': 2.0812644958496094}
-03/04/2022 21:04:54 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/04/2022 21:04:58 - INFO - codeparrot_training - Step 26910: {'lr': 0.00046585781177508137, 'samples': 13778432, 'steps': 26910, 'loss/train': 2.4312736988067627}
-03/04/2022 21:05:01 - INFO - codeparrot_training - Step 26911: {'lr': 0.0004658551346515354, 'samples': 13778944, 'steps': 26911, 'loss/train': 1.7564440965652466}
-03/04/2022 21:05:03 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/04/2022 21:05:06 - INFO - codeparrot_training - Step 26912: {'lr': 0.00046585245743072833, 'samples': 13779456, 'steps': 26912, 'loss/train': 1.57561457157135}
-03/04/2022 21:05:09 - INFO - codeparrot_training - Step 26913: {'lr': 0.0004658497801126616, 'samples': 13779968, 'steps': 26913, 'loss/train': 1.9252772331237793}
-03/04/2022 21:05:12 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/04/2022 21:05:14 - INFO - codeparrot_training - Step 26914: {'lr': 0.00046584710269733623, 'samples': 13780480, 'steps': 26914, 'loss/train': 1.9885400533676147}
-03/04/2022 21:05:18 - INFO - codeparrot_training - Step 26915: {'lr': 0.00046584442518475354, 'samples': 13780992, 'steps': 26915, 'loss/train': 1.9810930490493774}
-03/04/2022 21:05:20 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 21:05:23 - INFO - codeparrot_training - Step 26916: {'lr': 0.0004658417475749146, 'samples': 13781504, 'steps': 26916, 'loss/train': 1.447359561920166}
-03/04/2022 21:05:26 - INFO - codeparrot_training - Step 26917: {'lr': 0.00046583906986782074, 'samples': 13782016, 'steps': 26917, 'loss/train': 2.0656986236572266}
-03/04/2022 21:05:28 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/04/2022 21:05:31 - INFO - codeparrot_training - Step 26918: {'lr': 0.0004658363920634732, 'samples': 13782528, 'steps': 26918, 'loss/train': 2.407899856567383}
-03/04/2022 21:05:34 - INFO - codeparrot_training - Step 26919: {'lr': 0.000465833714161873, 'samples': 13783040, 'steps': 26919, 'loss/train': 1.7505202293395996}
-03/04/2022 21:05:37 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/04/2022 21:05:40 - INFO - codeparrot_training - Step 26920: {'lr': 0.00046583103616302146, 'samples': 13783552, 'steps': 26920, 'loss/train': 1.1656569242477417}
-03/04/2022 21:05:43 - INFO - codeparrot_training - Step 26921: {'lr': 0.0004658283580669198, 'samples': 13784064, 'steps': 26921, 'loss/train': 1.9668821096420288}
-03/04/2022 21:05:45 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/04/2022 21:05:48 - INFO - codeparrot_training - Step 26922: {'lr': 0.0004658256798735693, 'samples': 13784576, 'steps': 26922, 'loss/train': 1.6807609796524048}
-03/04/2022 21:05:51 - INFO - codeparrot_training - Step 26923: {'lr': 0.000465823001582971, 'samples': 13785088, 'steps': 26923, 'loss/train': 0.43089497089385986}
-03/04/2022 21:05:54 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/04/2022 21:05:56 - INFO - codeparrot_training - Step 26924: {'lr': 0.00046582032319512624, 'samples': 13785600, 'steps': 26924, 'loss/train': 1.815053939819336}
-03/04/2022 21:06:00 - INFO - codeparrot_training - Step 26925: {'lr': 0.00046581764471003605, 'samples': 13786112, 'steps': 26925, 'loss/train': 1.314481496810913}
-03/04/2022 21:06:02 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/04/2022 21:06:05 - INFO - codeparrot_training - Step 26926: {'lr': 0.0004658149661277019, 'samples': 13786624, 'steps': 26926, 'loss/train': 1.7341303825378418}
-03/04/2022 21:06:08 - INFO - codeparrot_training - Step 26927: {'lr': 0.0004658122874481248, 'samples': 13787136, 'steps': 26927, 'loss/train': 1.8964287042617798}
-03/04/2022 21:06:11 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/04/2022 21:06:13 - INFO - codeparrot_training - Step 26928: {'lr': 0.000465809608671306, 'samples': 13787648, 'steps': 26928, 'loss/train': 1.298348069190979}
-03/04/2022 21:06:17 - INFO - codeparrot_training - Step 26929: {'lr': 0.0004658069297972467, 'samples': 13788160, 'steps': 26929, 'loss/train': 2.526851177215576}
-03/04/2022 21:06:19 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/04/2022 21:06:22 - INFO - codeparrot_training - Step 26930: {'lr': 0.00046580425082594823, 'samples': 13788672, 'steps': 26930, 'loss/train': 1.9725583791732788}
-03/04/2022 21:06:25 - INFO - codeparrot_training - Step 26931: {'lr': 0.00046580157175741155, 'samples': 13789184, 'steps': 26931, 'loss/train': 1.2763549089431763}
-03/04/2022 21:06:29 - INFO - codeparrot_training - Step 26932: {'lr': 0.0004657988925916381, 'samples': 13789696, 'steps': 26932, 'loss/train': 1.5090621709823608}
-03/04/2022 21:06:30 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/04/2022 21:06:34 - INFO - codeparrot_training - Step 26933: {'lr': 0.000465796213328629, 'samples': 13790208, 'steps': 26933, 'loss/train': 1.8929084539413452}
-03/04/2022 21:06:37 - INFO - codeparrot_training - Step 26934: {'lr': 0.00046579353396838545, 'samples': 13790720, 'steps': 26934, 'loss/train': 1.790312647819519}
-03/04/2022 21:06:38 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 21:06:42 - INFO - codeparrot_training - Step 26935: {'lr': 0.00046579085451090864, 'samples': 13791232, 'steps': 26935, 'loss/train': 0.9979751706123352}
-03/04/2022 21:06:45 - INFO - codeparrot_training - Step 26936: {'lr': 0.00046578817495619983, 'samples': 13791744, 'steps': 26936, 'loss/train': 2.4268741607666016}
-03/04/2022 21:06:47 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 21:06:51 - INFO - codeparrot_training - Step 26937: {'lr': 0.0004657854953042602, 'samples': 13792256, 'steps': 26937, 'loss/train': 1.8120075464248657}
-03/04/2022 21:06:54 - INFO - codeparrot_training - Step 26938: {'lr': 0.00046578281555509094, 'samples': 13792768, 'steps': 26938, 'loss/train': 2.019676685333252}
-03/04/2022 21:06:56 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/04/2022 21:06:59 - INFO - codeparrot_training - Step 26939: {'lr': 0.00046578013570869325, 'samples': 13793280, 'steps': 26939, 'loss/train': 1.3692336082458496}
-03/04/2022 21:07:02 - INFO - codeparrot_training - Step 26940: {'lr': 0.00046577745576506844, 'samples': 13793792, 'steps': 26940, 'loss/train': 2.395744800567627}
-03/04/2022 21:07:04 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/04/2022 21:07:08 - INFO - codeparrot_training - Step 26941: {'lr': 0.00046577477572421757, 'samples': 13794304, 'steps': 26941, 'loss/train': 3.3783013820648193}
-03/04/2022 21:07:11 - INFO - codeparrot_training - Step 26942: {'lr': 0.0004657720955861419, 'samples': 13794816, 'steps': 26942, 'loss/train': 1.6694440841674805}
-03/04/2022 21:07:13 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/04/2022 21:07:16 - INFO - codeparrot_training - Step 26943: {'lr': 0.00046576941535084274, 'samples': 13795328, 'steps': 26943, 'loss/train': 1.7654786109924316}
-03/04/2022 21:07:19 - INFO - codeparrot_training - Step 26944: {'lr': 0.0004657667350183211, 'samples': 13795840, 'steps': 26944, 'loss/train': 2.0501928329467773}
-03/04/2022 21:07:21 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/04/2022 21:07:25 - INFO - codeparrot_training - Step 26945: {'lr': 0.00046576405458857836, 'samples': 13796352, 'steps': 26945, 'loss/train': 2.2468926906585693}
-03/04/2022 21:07:28 - INFO - codeparrot_training - Step 26946: {'lr': 0.0004657613740616157, 'samples': 13796864, 'steps': 26946, 'loss/train': 1.9141151905059814}
-03/04/2022 21:07:30 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/04/2022 21:07:33 - INFO - codeparrot_training - Step 26947: {'lr': 0.0004657586934374342, 'samples': 13797376, 'steps': 26947, 'loss/train': 2.0254385471343994}
-03/04/2022 21:07:36 - INFO - codeparrot_training - Step 26948: {'lr': 0.0004657560127160352, 'samples': 13797888, 'steps': 26948, 'loss/train': 0.7585595846176147}
-03/04/2022 21:07:38 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/04/2022 21:07:42 - INFO - codeparrot_training - Step 26949: {'lr': 0.00046575333189741993, 'samples': 13798400, 'steps': 26949, 'loss/train': 2.778754234313965}
-03/04/2022 21:07:45 - INFO - codeparrot_training - Step 26950: {'lr': 0.00046575065098158945, 'samples': 13798912, 'steps': 26950, 'loss/train': 2.0358493328094482}
-03/04/2022 21:07:47 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 21:07:51 - INFO - codeparrot_training - Step 26951: {'lr': 0.0004657479699685451, 'samples': 13799424, 'steps': 26951, 'loss/train': 2.1740055084228516}
-03/04/2022 21:07:54 - INFO - codeparrot_training - Step 26952: {'lr': 0.00046574528885828803, 'samples': 13799936, 'steps': 26952, 'loss/train': 2.1357152462005615}
-03/04/2022 21:07:57 - INFO - codeparrot_training - Step 26953: {'lr': 0.0004657426076508195, 'samples': 13800448, 'steps': 26953, 'loss/train': 0.5794610977172852}
-03/04/2022 21:07:57 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/04/2022 21:08:02 - INFO - codeparrot_training - Step 26954: {'lr': 0.00046573992634614064, 'samples': 13800960, 'steps': 26954, 'loss/train': 2.048552989959717}
-03/04/2022 21:08:05 - INFO - codeparrot_training - Step 26955: {'lr': 0.00046573724494425274, 'samples': 13801472, 'steps': 26955, 'loss/train': 1.7350014448165894}
-03/04/2022 21:08:06 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/04/2022 21:08:11 - INFO - codeparrot_training - Step 26956: {'lr': 0.00046573456344515694, 'samples': 13801984, 'steps': 26956, 'loss/train': 0.8301938772201538}
-03/04/2022 21:08:14 - INFO - codeparrot_training - Step 26957: {'lr': 0.00046573188184885445, 'samples': 13802496, 'steps': 26957, 'loss/train': 1.6894348859786987}
-03/04/2022 21:08:14 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/04/2022 21:08:19 - INFO - codeparrot_training - Step 26958: {'lr': 0.0004657292001553465, 'samples': 13803008, 'steps': 26958, 'loss/train': 0.6227928996086121}
-03/04/2022 21:08:22 - INFO - codeparrot_training - Step 26959: {'lr': 0.0004657265183646344, 'samples': 13803520, 'steps': 26959, 'loss/train': 2.154426336288452}
-03/04/2022 21:08:23 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/04/2022 21:08:28 - INFO - codeparrot_training - Step 26960: {'lr': 0.00046572383647671913, 'samples': 13804032, 'steps': 26960, 'loss/train': 2.224898338317871}
-03/04/2022 21:08:31 - INFO - codeparrot_training - Step 26961: {'lr': 0.0004657211544916021, 'samples': 13804544, 'steps': 26961, 'loss/train': 1.56977117061615}
-03/04/2022 21:08:31 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 21:08:36 - INFO - codeparrot_training - Step 26962: {'lr': 0.00046571847240928444, 'samples': 13805056, 'steps': 26962, 'loss/train': 1.3864017724990845}
-03/04/2022 21:08:39 - INFO - codeparrot_training - Step 26963: {'lr': 0.0004657157902297674, 'samples': 13805568, 'steps': 26963, 'loss/train': 2.0441770553588867}
-03/04/2022 21:08:40 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 21:08:45 - INFO - codeparrot_training - Step 26964: {'lr': 0.00046571310795305213, 'samples': 13806080, 'steps': 26964, 'loss/train': 1.596448540687561}
-03/04/2022 21:08:48 - INFO - codeparrot_training - Step 26965: {'lr': 0.0004657104255791398, 'samples': 13806592, 'steps': 26965, 'loss/train': 1.8522869348526}
-03/04/2022 21:08:48 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/04/2022 21:08:53 - INFO - codeparrot_training - Step 26966: {'lr': 0.0004657077431080317, 'samples': 13807104, 'steps': 26966, 'loss/train': 1.7474335432052612}
-03/04/2022 21:08:56 - INFO - codeparrot_training - Step 26967: {'lr': 0.00046570506053972906, 'samples': 13807616, 'steps': 26967, 'loss/train': 1.3027578592300415}
-03/04/2022 21:08:58 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/04/2022 21:09:02 - INFO - codeparrot_training - Step 26968: {'lr': 0.000465702377874233, 'samples': 13808128, 'steps': 26968, 'loss/train': 1.7368673086166382}
-03/04/2022 21:09:05 - INFO - codeparrot_training - Step 26969: {'lr': 0.00046569969511154485, 'samples': 13808640, 'steps': 26969, 'loss/train': 2.2720043659210205}
-03/04/2022 21:09:06 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 21:09:10 - INFO - codeparrot_training - Step 26970: {'lr': 0.0004656970122516657, 'samples': 13809152, 'steps': 26970, 'loss/train': 2.381481885910034}
-03/04/2022 21:09:13 - INFO - codeparrot_training - Step 26971: {'lr': 0.0004656943292945968, 'samples': 13809664, 'steps': 26971, 'loss/train': 1.7974470853805542}
-03/04/2022 21:09:15 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/04/2022 21:09:18 - INFO - codeparrot_training - Step 26972: {'lr': 0.0004656916462403394, 'samples': 13810176, 'steps': 26972, 'loss/train': 2.350710391998291}
-03/04/2022 21:09:22 - INFO - codeparrot_training - Step 26973: {'lr': 0.0004656889630888946, 'samples': 13810688, 'steps': 26973, 'loss/train': 1.568495512008667}
-03/04/2022 21:09:23 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/04/2022 21:09:27 - INFO - codeparrot_training - Step 26974: {'lr': 0.0004656862798402638, 'samples': 13811200, 'steps': 26974, 'loss/train': 1.280421495437622}
-03/04/2022 21:09:30 - INFO - codeparrot_training - Step 26975: {'lr': 0.00046568359649444796, 'samples': 13811712, 'steps': 26975, 'loss/train': 0.3861537575721741}
-03/04/2022 21:09:32 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 21:09:35 - INFO - codeparrot_training - Step 26976: {'lr': 0.0004656809130514485, 'samples': 13812224, 'steps': 26976, 'loss/train': 1.720929741859436}
-03/04/2022 21:09:39 - INFO - codeparrot_training - Step 26977: {'lr': 0.00046567822951126646, 'samples': 13812736, 'steps': 26977, 'loss/train': 1.8824357986450195}
-03/04/2022 21:09:40 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 21:09:44 - INFO - codeparrot_training - Step 26978: {'lr': 0.00046567554587390324, 'samples': 13813248, 'steps': 26978, 'loss/train': 2.3506133556365967}
-03/04/2022 21:09:47 - INFO - codeparrot_training - Step 26979: {'lr': 0.00046567286213935994, 'samples': 13813760, 'steps': 26979, 'loss/train': 0.2063003033399582}
-03/04/2022 21:09:49 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/04/2022 21:09:52 - INFO - codeparrot_training - Step 26980: {'lr': 0.00046567017830763776, 'samples': 13814272, 'steps': 26980, 'loss/train': 1.8373440504074097}
-03/04/2022 21:09:56 - INFO - codeparrot_training - Step 26981: {'lr': 0.0004656674943787379, 'samples': 13814784, 'steps': 26981, 'loss/train': 0.5863098502159119}
-03/04/2022 21:09:57 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/04/2022 21:10:01 - INFO - codeparrot_training - Step 26982: {'lr': 0.0004656648103526616, 'samples': 13815296, 'steps': 26982, 'loss/train': 1.780055284500122}
-03/04/2022 21:10:04 - INFO - codeparrot_training - Step 26983: {'lr': 0.00046566212622941005, 'samples': 13815808, 'steps': 26983, 'loss/train': 1.87108314037323}
-03/04/2022 21:10:05 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/04/2022 21:10:09 - INFO - codeparrot_training - Step 26984: {'lr': 0.00046565944200898453, 'samples': 13816320, 'steps': 26984, 'loss/train': 1.3122005462646484}
-03/04/2022 21:10:12 - INFO - codeparrot_training - Step 26985: {'lr': 0.00046565675769138614, 'samples': 13816832, 'steps': 26985, 'loss/train': 1.679057002067566}
-03/04/2022 21:10:14 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/04/2022 21:10:18 - INFO - codeparrot_training - Step 26986: {'lr': 0.00046565407327661614, 'samples': 13817344, 'steps': 26986, 'loss/train': 2.113560199737549}
-03/04/2022 21:10:21 - INFO - codeparrot_training - Step 26987: {'lr': 0.0004656513887646758, 'samples': 13817856, 'steps': 26987, 'loss/train': 1.221604824066162}
-03/04/2022 21:10:22 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/04/2022 21:10:26 - INFO - codeparrot_training - Step 26988: {'lr': 0.00046564870415556625, 'samples': 13818368, 'steps': 26988, 'loss/train': 1.9061634540557861}
-03/04/2022 21:10:29 - INFO - codeparrot_training - Step 26989: {'lr': 0.0004656460194492887, 'samples': 13818880, 'steps': 26989, 'loss/train': 1.4639053344726562}
-03/04/2022 21:10:31 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 21:10:34 - INFO - codeparrot_training - Step 26990: {'lr': 0.0004656433346458444, 'samples': 13819392, 'steps': 26990, 'loss/train': 1.6703394651412964}
-03/04/2022 21:10:38 - INFO - codeparrot_training - Step 26991: {'lr': 0.0004656406497452345, 'samples': 13819904, 'steps': 26991, 'loss/train': 1.7555326223373413}
-03/04/2022 21:10:39 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/04/2022 21:10:43 - INFO - codeparrot_training - Step 26992: {'lr': 0.0004656379647474603, 'samples': 13820416, 'steps': 26992, 'loss/train': 2.2461001873016357}
-03/04/2022 21:10:46 - INFO - codeparrot_training - Step 26993: {'lr': 0.0004656352796525229, 'samples': 13820928, 'steps': 26993, 'loss/train': 1.9018021821975708}
-03/04/2022 21:10:47 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 21:10:51 - INFO - codeparrot_training - Step 26994: {'lr': 0.0004656325944604236, 'samples': 13821440, 'steps': 26994, 'loss/train': 1.6641300916671753}
-03/04/2022 21:10:54 - INFO - codeparrot_training - Step 26995: {'lr': 0.00046562990917116366, 'samples': 13821952, 'steps': 26995, 'loss/train': 2.4000017642974854}
-03/04/2022 21:10:55 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/04/2022 21:11:00 - INFO - codeparrot_training - Step 26996: {'lr': 0.0004656272237847441, 'samples': 13822464, 'steps': 26996, 'loss/train': 2.3405776023864746}
-03/04/2022 21:11:03 - INFO - codeparrot_training - Step 26997: {'lr': 0.0004656245383011663, 'samples': 13822976, 'steps': 26997, 'loss/train': 1.660452961921692}
-03/04/2022 21:11:03 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/04/2022 21:11:08 - INFO - codeparrot_training - Step 26998: {'lr': 0.00046562185272043137, 'samples': 13823488, 'steps': 26998, 'loss/train': 1.6345388889312744}
-03/04/2022 21:11:11 - INFO - codeparrot_training - Step 26999: {'lr': 0.00046561916704254057, 'samples': 13824000, 'steps': 26999, 'loss/train': 1.7701505422592163}
-03/04/2022 21:11:12 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 21:11:17 - INFO - codeparrot_training - Step 27000: {'lr': 0.0004656164812674951, 'samples': 13824512, 'steps': 27000, 'loss/train': 1.871762752532959}
-03/04/2022 21:11:20 - INFO - codeparrot_training - Step 27001: {'lr': 0.00046561379539529626, 'samples': 13825024, 'steps': 27001, 'loss/train': 0.6935906410217285}
-03/04/2022 21:11:20 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/04/2022 21:11:25 - INFO - codeparrot_training - Step 27002: {'lr': 0.0004656111094259451, 'samples': 13825536, 'steps': 27002, 'loss/train': 1.907692790031433}
-03/04/2022 21:11:28 - INFO - codeparrot_training - Step 27003: {'lr': 0.0004656084233594429, 'samples': 13826048, 'steps': 27003, 'loss/train': 1.893552303314209}
-03/04/2022 21:11:30 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 21:11:34 - INFO - codeparrot_training - Step 27004: {'lr': 0.0004656057371957908, 'samples': 13826560, 'steps': 27004, 'loss/train': 1.7349058389663696}
-03/04/2022 21:11:37 - INFO - codeparrot_training - Step 27005: {'lr': 0.00046560305093499015, 'samples': 13827072, 'steps': 27005, 'loss/train': 2.0631167888641357}
-03/04/2022 21:11:38 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/04/2022 21:11:42 - INFO - codeparrot_training - Step 27006: {'lr': 0.00046560036457704215, 'samples': 13827584, 'steps': 27006, 'loss/train': 1.9291396141052246}
-03/04/2022 21:11:45 - INFO - codeparrot_training - Step 27007: {'lr': 0.00046559767812194786, 'samples': 13828096, 'steps': 27007, 'loss/train': 1.5850939750671387}
-03/04/2022 21:11:47 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 21:11:51 - INFO - codeparrot_training - Step 27008: {'lr': 0.0004655949915697086, 'samples': 13828608, 'steps': 27008, 'loss/train': 2.109180212020874}
-03/04/2022 21:11:54 - INFO - codeparrot_training - Step 27009: {'lr': 0.0004655923049203256, 'samples': 13829120, 'steps': 27009, 'loss/train': 0.9794557094573975}
-03/04/2022 21:11:58 - INFO - codeparrot_training - Step 27010: {'lr': 0.00046558961817380005, 'samples': 13829632, 'steps': 27010, 'loss/train': 0.9650289416313171}
-03/04/2022 21:11:58 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 21:12:03 - INFO - codeparrot_training - Step 27011: {'lr': 0.00046558693133013306, 'samples': 13830144, 'steps': 27011, 'loss/train': 1.238690733909607}
-03/04/2022 21:12:06 - INFO - codeparrot_training - Step 27012: {'lr': 0.000465584244389326, 'samples': 13830656, 'steps': 27012, 'loss/train': 2.2273831367492676}
-03/04/2022 21:12:06 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/04/2022 21:12:11 - INFO - codeparrot_training - Step 27013: {'lr': 0.00046558155735137996, 'samples': 13831168, 'steps': 27013, 'loss/train': 2.580404758453369}
-03/04/2022 21:12:14 - INFO - codeparrot_training - Step 27014: {'lr': 0.00046557887021629623, 'samples': 13831680, 'steps': 27014, 'loss/train': 1.9690332412719727}
-03/04/2022 21:12:15 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/04/2022 21:12:20 - INFO - codeparrot_training - Step 27015: {'lr': 0.000465576182984076, 'samples': 13832192, 'steps': 27015, 'loss/train': 1.6849416494369507}
-03/04/2022 21:12:23 - INFO - codeparrot_training - Step 27016: {'lr': 0.0004655734956547204, 'samples': 13832704, 'steps': 27016, 'loss/train': 1.5752344131469727}
-03/04/2022 21:12:23 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 21:12:28 - INFO - codeparrot_training - Step 27017: {'lr': 0.00046557080822823076, 'samples': 13833216, 'steps': 27017, 'loss/train': 1.7027051448822021}
-03/04/2022 21:12:31 - INFO - codeparrot_training - Step 27018: {'lr': 0.0004655681207046083, 'samples': 13833728, 'steps': 27018, 'loss/train': 2.068704128265381}
-03/04/2022 21:12:31 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/04/2022 21:12:36 - INFO - codeparrot_training - Step 27019: {'lr': 0.0004655654330838541, 'samples': 13834240, 'steps': 27019, 'loss/train': 1.6756867170333862}
-03/04/2022 21:12:40 - INFO - codeparrot_training - Step 27020: {'lr': 0.00046556274536596945, 'samples': 13834752, 'steps': 27020, 'loss/train': 1.9486370086669922}
-03/04/2022 21:12:40 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/04/2022 21:12:45 - INFO - codeparrot_training - Step 27021: {'lr': 0.00046556005755095555, 'samples': 13835264, 'steps': 27021, 'loss/train': 1.689372181892395}
-03/04/2022 21:12:48 - INFO - codeparrot_training - Step 27022: {'lr': 0.00046555736963881355, 'samples': 13835776, 'steps': 27022, 'loss/train': 1.9235975742340088}
-03/04/2022 21:12:48 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/04/2022 21:12:53 - INFO - codeparrot_training - Step 27023: {'lr': 0.0004655546816295448, 'samples': 13836288, 'steps': 27023, 'loss/train': 1.2673035860061646}
-03/04/2022 21:12:56 - INFO - codeparrot_training - Step 27024: {'lr': 0.0004655519935231505, 'samples': 13836800, 'steps': 27024, 'loss/train': 1.974639892578125}
-03/04/2022 21:12:57 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 21:13:02 - INFO - codeparrot_training - Step 27025: {'lr': 0.00046554930531963166, 'samples': 13837312, 'steps': 27025, 'loss/train': 2.1420445442199707}
-03/04/2022 21:13:05 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/04/2022 21:13:07 - INFO - codeparrot_training - Step 27026: {'lr': 0.0004655466170189897, 'samples': 13837824, 'steps': 27026, 'loss/train': 1.5582914352416992}
-03/04/2022 21:13:10 - INFO - codeparrot_training - Step 27027: {'lr': 0.0004655439286212257, 'samples': 13838336, 'steps': 27027, 'loss/train': 2.1231091022491455}
-03/04/2022 21:13:13 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/04/2022 21:13:16 - INFO - codeparrot_training - Step 27028: {'lr': 0.00046554124012634105, 'samples': 13838848, 'steps': 27028, 'loss/train': 2.5949220657348633}
-03/04/2022 21:13:19 - INFO - codeparrot_training - Step 27029: {'lr': 0.0004655385515343368, 'samples': 13839360, 'steps': 27029, 'loss/train': 0.4669930040836334}
-03/04/2022 21:13:22 - INFO - codeparrot_training - Step 27030: {'lr': 0.0004655358628452142, 'samples': 13839872, 'steps': 27030, 'loss/train': 2.0689239501953125}
-03/04/2022 21:13:27 - INFO - codeparrot_training - Step 27031: {'lr': 0.00046553317405897444, 'samples': 13840384, 'steps': 27031, 'loss/train': 1.818233847618103}
-03/04/2022 21:13:30 - INFO - codeparrot_training - Step 27032: {'lr': 0.0004655304851756188, 'samples': 13840896, 'steps': 27032, 'loss/train': 1.768347978591919}
-03/04/2022 21:13:30 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/04/2022 21:13:36 - INFO - codeparrot_training - Step 27033: {'lr': 0.0004655277961951484, 'samples': 13841408, 'steps': 27033, 'loss/train': 1.8392176628112793}
-03/04/2022 21:13:39 - INFO - codeparrot_training - Step 27034: {'lr': 0.00046552510711756444, 'samples': 13841920, 'steps': 27034, 'loss/train': 1.8600338697433472}
-03/04/2022 21:13:39 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/04/2022 21:13:44 - INFO - codeparrot_training - Step 27035: {'lr': 0.0004655224179428683, 'samples': 13842432, 'steps': 27035, 'loss/train': 0.923130452632904}
-03/04/2022 21:13:47 - INFO - codeparrot_training - Step 27036: {'lr': 0.00046551972867106106, 'samples': 13842944, 'steps': 27036, 'loss/train': 1.545621633529663}
-03/04/2022 21:13:48 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/04/2022 21:13:53 - INFO - codeparrot_training - Step 27037: {'lr': 0.00046551703930214393, 'samples': 13843456, 'steps': 27037, 'loss/train': 2.0888125896453857}
-03/04/2022 21:13:56 - INFO - codeparrot_training - Step 27038: {'lr': 0.00046551434983611823, 'samples': 13843968, 'steps': 27038, 'loss/train': 1.7190394401550293}
-03/04/2022 21:13:56 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/04/2022 21:14:01 - INFO - codeparrot_training - Step 27039: {'lr': 0.00046551166027298505, 'samples': 13844480, 'steps': 27039, 'loss/train': 2.1900062561035156}
-03/04/2022 21:14:04 - INFO - codeparrot_training - Step 27040: {'lr': 0.0004655089706127456, 'samples': 13844992, 'steps': 27040, 'loss/train': 1.9904708862304688}
-03/04/2022 21:14:04 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 21:14:10 - INFO - codeparrot_training - Step 27041: {'lr': 0.00046550628085540114, 'samples': 13845504, 'steps': 27041, 'loss/train': 0.5434851050376892}
-03/04/2022 21:14:13 - INFO - codeparrot_training - Step 27042: {'lr': 0.0004655035910009529, 'samples': 13846016, 'steps': 27042, 'loss/train': 1.2899688482284546}
-03/04/2022 21:14:13 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/04/2022 21:14:18 - INFO - codeparrot_training - Step 27043: {'lr': 0.00046550090104940207, 'samples': 13846528, 'steps': 27043, 'loss/train': 1.204062819480896}
-03/04/2022 21:14:21 - INFO - codeparrot_training - Step 27044: {'lr': 0.00046549821100074987, 'samples': 13847040, 'steps': 27044, 'loss/train': 1.7272709608078003}
-03/04/2022 21:14:21 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/04/2022 21:14:27 - INFO - codeparrot_training - Step 27045: {'lr': 0.0004654955208549975, 'samples': 13847552, 'steps': 27045, 'loss/train': 1.7356256246566772}
-03/04/2022 21:14:29 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/04/2022 21:14:32 - INFO - codeparrot_training - Step 27046: {'lr': 0.0004654928306121461, 'samples': 13848064, 'steps': 27046, 'loss/train': 1.5773513317108154}
-03/04/2022 21:14:35 - INFO - codeparrot_training - Step 27047: {'lr': 0.000465490140272197, 'samples': 13848576, 'steps': 27047, 'loss/train': 1.640571117401123}
-03/04/2022 21:14:38 - INFO - codeparrot_training - Step 27048: {'lr': 0.00046548744983515133, 'samples': 13849088, 'steps': 27048, 'loss/train': 2.0742311477661133}
-03/04/2022 21:14:38 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/04/2022 21:14:43 - INFO - codeparrot_training - Step 27049: {'lr': 0.0004654847593010104, 'samples': 13849600, 'steps': 27049, 'loss/train': 1.584211826324463}
-03/04/2022 21:14:47 - INFO - codeparrot_training - Step 27050: {'lr': 0.0004654820686697754, 'samples': 13850112, 'steps': 27050, 'loss/train': 2.6977977752685547}
-03/04/2022 21:14:47 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 21:14:52 - INFO - codeparrot_training - Step 27051: {'lr': 0.00046547937794144743, 'samples': 13850624, 'steps': 27051, 'loss/train': 2.191925048828125}
-03/04/2022 21:14:55 - INFO - codeparrot_training - Step 27052: {'lr': 0.00046547668711602774, 'samples': 13851136, 'steps': 27052, 'loss/train': 1.3612678050994873}
-03/04/2022 21:14:55 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 21:15:00 - INFO - codeparrot_training - Step 27053: {'lr': 0.0004654739961935177, 'samples': 13851648, 'steps': 27053, 'loss/train': 1.8132718801498413}
-03/04/2022 21:15:03 - INFO - codeparrot_training - Step 27054: {'lr': 0.0004654713051739183, 'samples': 13852160, 'steps': 27054, 'loss/train': 0.7594876885414124}
-03/04/2022 21:15:03 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/04/2022 21:15:09 - INFO - codeparrot_training - Step 27055: {'lr': 0.000465468614057231, 'samples': 13852672, 'steps': 27055, 'loss/train': 2.0670742988586426}
-03/04/2022 21:15:11 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 21:15:14 - INFO - codeparrot_training - Step 27056: {'lr': 0.0004654659228434567, 'samples': 13853184, 'steps': 27056, 'loss/train': 2.2369132041931152}
-03/04/2022 21:15:17 - INFO - codeparrot_training - Step 27057: {'lr': 0.00046546323153259686, 'samples': 13853696, 'steps': 27057, 'loss/train': 1.8082598447799683}
-03/04/2022 21:15:20 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/04/2022 21:15:22 - INFO - codeparrot_training - Step 27058: {'lr': 0.00046546054012465253, 'samples': 13854208, 'steps': 27058, 'loss/train': 0.7171269655227661}
-03/04/2022 21:15:26 - INFO - codeparrot_training - Step 27059: {'lr': 0.00046545784861962516, 'samples': 13854720, 'steps': 27059, 'loss/train': 1.7160779237747192}
-03/04/2022 21:15:28 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 21:15:31 - INFO - codeparrot_training - Step 27060: {'lr': 0.00046545515701751567, 'samples': 13855232, 'steps': 27060, 'loss/train': 2.1785833835601807}
-03/04/2022 21:15:34 - INFO - codeparrot_training - Step 27061: {'lr': 0.00046545246531832547, 'samples': 13855744, 'steps': 27061, 'loss/train': 1.4626277685165405}
-03/04/2022 21:15:37 - INFO - codeparrot_training - Step 27062: {'lr': 0.0004654497735220557, 'samples': 13856256, 'steps': 27062, 'loss/train': 1.1318156719207764}
-03/04/2022 21:15:38 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 21:15:43 - INFO - codeparrot_training - Step 27063: {'lr': 0.0004654470816287076, 'samples': 13856768, 'steps': 27063, 'loss/train': 1.9653629064559937}
-03/04/2022 21:15:46 - INFO - codeparrot_training - Step 27064: {'lr': 0.0004654443896382824, 'samples': 13857280, 'steps': 27064, 'loss/train': 1.7505704164505005}
-03/04/2022 21:15:47 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/04/2022 21:15:51 - INFO - codeparrot_training - Step 27065: {'lr': 0.0004654416975507812, 'samples': 13857792, 'steps': 27065, 'loss/train': 1.4989372491836548}
-03/04/2022 21:15:54 - INFO - codeparrot_training - Step 27066: {'lr': 0.0004654390053662053, 'samples': 13858304, 'steps': 27066, 'loss/train': 1.782608151435852}
-03/04/2022 21:15:55 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 21:16:00 - INFO - codeparrot_training - Step 27067: {'lr': 0.000465436313084556, 'samples': 13858816, 'steps': 27067, 'loss/train': 1.6184111833572388}
-03/04/2022 21:16:03 - INFO - codeparrot_training - Step 27068: {'lr': 0.0004654336207058344, 'samples': 13859328, 'steps': 27068, 'loss/train': 2.031097650527954}
-03/04/2022 21:16:03 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/04/2022 21:16:08 - INFO - codeparrot_training - Step 27069: {'lr': 0.0004654309282300416, 'samples': 13859840, 'steps': 27069, 'loss/train': 1.1097253561019897}
-03/04/2022 21:16:11 - INFO - codeparrot_training - Step 27070: {'lr': 0.00046542823565717914, 'samples': 13860352, 'steps': 27070, 'loss/train': 1.6570360660552979}
-03/04/2022 21:16:12 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/04/2022 21:16:16 - INFO - codeparrot_training - Step 27071: {'lr': 0.00046542554298724793, 'samples': 13860864, 'steps': 27071, 'loss/train': 1.5371021032333374}
-03/04/2022 21:16:20 - INFO - codeparrot_training - Step 27072: {'lr': 0.00046542285022024935, 'samples': 13861376, 'steps': 27072, 'loss/train': 2.0738537311553955}
-03/04/2022 21:16:21 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/04/2022 21:16:25 - INFO - codeparrot_training - Step 27073: {'lr': 0.0004654201573561845, 'samples': 13861888, 'steps': 27073, 'loss/train': 1.6445918083190918}
-03/04/2022 21:16:28 - INFO - codeparrot_training - Step 27074: {'lr': 0.00046541746439505467, 'samples': 13862400, 'steps': 27074, 'loss/train': 1.8079501390457153}
-03/04/2022 21:16:29 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 21:16:33 - INFO - codeparrot_training - Step 27075: {'lr': 0.00046541477133686107, 'samples': 13862912, 'steps': 27075, 'loss/train': 2.4497525691986084}
-03/04/2022 21:16:37 - INFO - codeparrot_training - Step 27076: {'lr': 0.0004654120781816049, 'samples': 13863424, 'steps': 27076, 'loss/train': 2.1270925998687744}
-03/04/2022 21:16:38 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 21:16:42 - INFO - codeparrot_training - Step 27077: {'lr': 0.00046540938492928735, 'samples': 13863936, 'steps': 27077, 'loss/train': 2.105628490447998}
-03/04/2022 21:16:45 - INFO - codeparrot_training - Step 27078: {'lr': 0.0004654066915799097, 'samples': 13864448, 'steps': 27078, 'loss/train': 0.8273047208786011}
-03/04/2022 21:16:47 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/04/2022 21:16:50 - INFO - codeparrot_training - Step 27079: {'lr': 0.000465403998133473, 'samples': 13864960, 'steps': 27079, 'loss/train': 1.7959136962890625}
-03/04/2022 21:16:53 - INFO - codeparrot_training - Step 27080: {'lr': 0.0004654013045899788, 'samples': 13865472, 'steps': 27080, 'loss/train': 1.8930463790893555}
-03/04/2022 21:16:55 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 21:16:59 - INFO - codeparrot_training - Step 27081: {'lr': 0.00046539861094942794, 'samples': 13865984, 'steps': 27081, 'loss/train': 1.768653392791748}
-03/04/2022 21:17:02 - INFO - codeparrot_training - Step 27082: {'lr': 0.00046539591721182175, 'samples': 13866496, 'steps': 27082, 'loss/train': 2.1163735389709473}
-03/04/2022 21:17:03 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/04/2022 21:17:07 - INFO - codeparrot_training - Step 27083: {'lr': 0.00046539322337716153, 'samples': 13867008, 'steps': 27083, 'loss/train': 2.0211970806121826}
-03/04/2022 21:17:10 - INFO - codeparrot_training - Step 27084: {'lr': 0.00046539052944544846, 'samples': 13867520, 'steps': 27084, 'loss/train': 1.2630654573440552}
-03/04/2022 21:17:11 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/04/2022 21:17:15 - INFO - codeparrot_training - Step 27085: {'lr': 0.0004653878354166838, 'samples': 13868032, 'steps': 27085, 'loss/train': 1.2577301263809204}
-03/04/2022 21:17:19 - INFO - codeparrot_training - Step 27086: {'lr': 0.0004653851412908686, 'samples': 13868544, 'steps': 27086, 'loss/train': 1.9790763854980469}
-03/04/2022 21:17:20 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/04/2022 21:17:24 - INFO - codeparrot_training - Step 27087: {'lr': 0.0004653824470680043, 'samples': 13869056, 'steps': 27087, 'loss/train': 2.145411252975464}
-03/04/2022 21:17:27 - INFO - codeparrot_training - Step 27088: {'lr': 0.00046537975274809186, 'samples': 13869568, 'steps': 27088, 'loss/train': 1.602316975593567}
-03/04/2022 21:17:28 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 21:17:32 - INFO - codeparrot_training - Step 27089: {'lr': 0.0004653770583311327, 'samples': 13870080, 'steps': 27089, 'loss/train': 1.7670884132385254}
-03/04/2022 21:17:36 - INFO - codeparrot_training - Step 27090: {'lr': 0.00046537436381712796, 'samples': 13870592, 'steps': 27090, 'loss/train': 1.308382511138916}
-03/04/2022 21:17:36 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/04/2022 21:17:41 - INFO - codeparrot_training - Step 27091: {'lr': 0.00046537166920607886, 'samples': 13871104, 'steps': 27091, 'loss/train': 1.324061393737793}
-03/04/2022 21:17:44 - INFO - codeparrot_training - Step 27092: {'lr': 0.00046536897449798656, 'samples': 13871616, 'steps': 27092, 'loss/train': 1.8986238241195679}
-03/04/2022 21:17:45 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/04/2022 21:17:49 - INFO - codeparrot_training - Step 27093: {'lr': 0.00046536627969285236, 'samples': 13872128, 'steps': 27093, 'loss/train': 1.3568392992019653}
-03/04/2022 21:17:52 - INFO - codeparrot_training - Step 27094: {'lr': 0.0004653635847906774, 'samples': 13872640, 'steps': 27094, 'loss/train': 1.83497154712677}
-03/04/2022 21:17:53 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/04/2022 21:17:58 - INFO - codeparrot_training - Step 27095: {'lr': 0.000465360889791463, 'samples': 13873152, 'steps': 27095, 'loss/train': 0.9121497869491577}
-03/04/2022 21:18:01 - INFO - codeparrot_training - Step 27096: {'lr': 0.0004653581946952103, 'samples': 13873664, 'steps': 27096, 'loss/train': 2.2708756923675537}
-03/04/2022 21:18:02 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/04/2022 21:18:06 - INFO - codeparrot_training - Step 27097: {'lr': 0.0004653554995019205, 'samples': 13874176, 'steps': 27097, 'loss/train': 2.119619607925415}
-03/04/2022 21:18:10 - INFO - codeparrot_training - Step 27098: {'lr': 0.0004653528042115948, 'samples': 13874688, 'steps': 27098, 'loss/train': 1.403655767440796}
-03/04/2022 21:18:12 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/04/2022 21:18:15 - INFO - codeparrot_training - Step 27099: {'lr': 0.0004653501088242345, 'samples': 13875200, 'steps': 27099, 'loss/train': 2.693763494491577}
-03/04/2022 21:18:18 - INFO - codeparrot_training - Step 27100: {'lr': 0.0004653474133398408, 'samples': 13875712, 'steps': 27100, 'loss/train': 1.301839828491211}
-03/04/2022 21:18:20 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/04/2022 21:18:23 - INFO - codeparrot_training - Step 27101: {'lr': 0.00046534471775841474, 'samples': 13876224, 'steps': 27101, 'loss/train': 1.7934544086456299}
-03/04/2022 21:18:26 - INFO - codeparrot_training - Step 27102: {'lr': 0.0004653420220799578, 'samples': 13876736, 'steps': 27102, 'loss/train': 0.9241384863853455}
-03/04/2022 21:18:29 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/04/2022 21:18:32 - INFO - codeparrot_training - Step 27103: {'lr': 0.000465339326304471, 'samples': 13877248, 'steps': 27103, 'loss/train': 2.26963210105896}
-03/04/2022 21:18:35 - INFO - codeparrot_training - Step 27104: {'lr': 0.0004653366304319556, 'samples': 13877760, 'steps': 27104, 'loss/train': 0.38335752487182617}
-03/04/2022 21:18:37 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 21:18:40 - INFO - codeparrot_training - Step 27105: {'lr': 0.0004653339344624129, 'samples': 13878272, 'steps': 27105, 'loss/train': 1.5408906936645508}
-03/04/2022 21:18:43 - INFO - codeparrot_training - Step 27106: {'lr': 0.00046533123839584406, 'samples': 13878784, 'steps': 27106, 'loss/train': 1.9943867921829224}
-03/04/2022 21:18:45 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/04/2022 21:18:48 - INFO - codeparrot_training - Step 27107: {'lr': 0.0004653285422322503, 'samples': 13879296, 'steps': 27107, 'loss/train': 1.378122329711914}
-03/04/2022 21:18:52 - INFO - codeparrot_training - Step 27108: {'lr': 0.00046532584597163275, 'samples': 13879808, 'steps': 27108, 'loss/train': 1.6634700298309326}
-03/04/2022 21:18:54 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 21:18:57 - INFO - codeparrot_training - Step 27109: {'lr': 0.0004653231496139927, 'samples': 13880320, 'steps': 27109, 'loss/train': 1.0929324626922607}
-03/04/2022 21:19:00 - INFO - codeparrot_training - Step 27110: {'lr': 0.0004653204531593315, 'samples': 13880832, 'steps': 27110, 'loss/train': 2.285989999771118}
-03/04/2022 21:19:02 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/04/2022 21:19:05 - INFO - codeparrot_training - Step 27111: {'lr': 0.0004653177566076501, 'samples': 13881344, 'steps': 27111, 'loss/train': 1.6831626892089844}
-03/04/2022 21:19:09 - INFO - codeparrot_training - Step 27112: {'lr': 0.0004653150599589498, 'samples': 13881856, 'steps': 27112, 'loss/train': 1.029488205909729}
-03/04/2022 21:19:11 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 21:19:14 - INFO - codeparrot_training - Step 27113: {'lr': 0.0004653123632132319, 'samples': 13882368, 'steps': 27113, 'loss/train': 1.6527074575424194}
-03/04/2022 21:19:17 - INFO - codeparrot_training - Step 27114: {'lr': 0.0004653096663704976, 'samples': 13882880, 'steps': 27114, 'loss/train': 2.0187742710113525}
-03/04/2022 21:19:19 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/04/2022 21:19:22 - INFO - codeparrot_training - Step 27115: {'lr': 0.0004653069694307481, 'samples': 13883392, 'steps': 27115, 'loss/train': 1.8555246591567993}
-03/04/2022 21:19:25 - INFO - codeparrot_training - Step 27116: {'lr': 0.00046530427239398453, 'samples': 13883904, 'steps': 27116, 'loss/train': 1.7274163961410522}
-03/04/2022 21:19:28 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/04/2022 21:19:31 - INFO - codeparrot_training - Step 27117: {'lr': 0.0004653015752602082, 'samples': 13884416, 'steps': 27117, 'loss/train': 1.8092612028121948}
-03/04/2022 21:19:34 - INFO - codeparrot_training - Step 27118: {'lr': 0.0004652988780294204, 'samples': 13884928, 'steps': 27118, 'loss/train': 0.1930076628923416}
-03/04/2022 21:19:36 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 21:19:39 - INFO - codeparrot_training - Step 27119: {'lr': 0.00046529618070162215, 'samples': 13885440, 'steps': 27119, 'loss/train': 1.7767243385314941}
-03/04/2022 21:19:42 - INFO - codeparrot_training - Step 27120: {'lr': 0.00046529348327681476, 'samples': 13885952, 'steps': 27120, 'loss/train': 1.3183544874191284}
-03/04/2022 21:19:44 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 21:19:48 - INFO - codeparrot_training - Step 27121: {'lr': 0.0004652907857549995, 'samples': 13886464, 'steps': 27121, 'loss/train': 2.04373836517334}
-03/04/2022 21:19:51 - INFO - codeparrot_training - Step 27122: {'lr': 0.0004652880881361775, 'samples': 13886976, 'steps': 27122, 'loss/train': 1.6949533224105835}
-03/04/2022 21:19:53 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/04/2022 21:19:56 - INFO - codeparrot_training - Step 27123: {'lr': 0.00046528539042035, 'samples': 13887488, 'steps': 27123, 'loss/train': 1.097642183303833}
-03/04/2022 21:19:59 - INFO - codeparrot_training - Step 27124: {'lr': 0.0004652826926075183, 'samples': 13888000, 'steps': 27124, 'loss/train': 2.004002332687378}
-03/04/2022 21:20:02 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/04/2022 21:20:05 - INFO - codeparrot_training - Step 27125: {'lr': 0.00046527999469768346, 'samples': 13888512, 'steps': 27125, 'loss/train': 1.1716101169586182}
-03/04/2022 21:20:08 - INFO - codeparrot_training - Step 27126: {'lr': 0.0004652772966908468, 'samples': 13889024, 'steps': 27126, 'loss/train': 2.0120861530303955}
-03/04/2022 21:20:10 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/04/2022 21:20:13 - INFO - codeparrot_training - Step 27127: {'lr': 0.0004652745985870095, 'samples': 13889536, 'steps': 27127, 'loss/train': 1.6473901271820068}
-03/04/2022 21:20:16 - INFO - codeparrot_training - Step 27128: {'lr': 0.0004652719003861728, 'samples': 13890048, 'steps': 27128, 'loss/train': 2.232377529144287}
-03/04/2022 21:20:19 - INFO - codeparrot_training - Step 27129: {'lr': 0.0004652692020883379, 'samples': 13890560, 'steps': 27129, 'loss/train': 1.521709680557251}
-03/04/2022 21:20:19 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/04/2022 21:20:25 - INFO - codeparrot_training - Step 27130: {'lr': 0.00046526650369350605, 'samples': 13891072, 'steps': 27130, 'loss/train': 1.2067619562149048}
-03/04/2022 21:20:28 - INFO - codeparrot_training - Step 27131: {'lr': 0.0004652638052016784, 'samples': 13891584, 'steps': 27131, 'loss/train': 1.9540432691574097}
-03/04/2022 21:20:28 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/04/2022 21:20:33 - INFO - codeparrot_training - Step 27132: {'lr': 0.00046526110661285615, 'samples': 13892096, 'steps': 27132, 'loss/train': 1.8228216171264648}
-03/04/2022 21:20:36 - INFO - codeparrot_training - Step 27133: {'lr': 0.00046525840792704064, 'samples': 13892608, 'steps': 27133, 'loss/train': 2.0725021362304688}
-03/04/2022 21:20:36 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/04/2022 21:20:42 - INFO - codeparrot_training - Step 27134: {'lr': 0.000465255709144233, 'samples': 13893120, 'steps': 27134, 'loss/train': 1.7328137159347534}
-03/04/2022 21:20:45 - INFO - codeparrot_training - Step 27135: {'lr': 0.00046525301026443443, 'samples': 13893632, 'steps': 27135, 'loss/train': 1.2246339321136475}
-03/04/2022 21:20:45 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/04/2022 21:20:50 - INFO - codeparrot_training - Step 27136: {'lr': 0.0004652503112876463, 'samples': 13894144, 'steps': 27136, 'loss/train': 2.04892635345459}
-03/04/2022 21:20:53 - INFO - codeparrot_training - Step 27137: {'lr': 0.00046524761221386956, 'samples': 13894656, 'steps': 27137, 'loss/train': 6.455905914306641}
-03/04/2022 21:20:54 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 21:20:59 - INFO - codeparrot_training - Step 27138: {'lr': 0.0004652449130431056, 'samples': 13895168, 'steps': 27138, 'loss/train': 1.7534172534942627}
-03/04/2022 21:21:02 - INFO - codeparrot_training - Step 27139: {'lr': 0.00046524221377535564, 'samples': 13895680, 'steps': 27139, 'loss/train': 1.3366974592208862}
-03/04/2022 21:21:02 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/04/2022 21:21:07 - INFO - codeparrot_training - Step 27140: {'lr': 0.00046523951441062087, 'samples': 13896192, 'steps': 27140, 'loss/train': 2.079841375350952}
-03/04/2022 21:21:10 - INFO - codeparrot_training - Step 27141: {'lr': 0.0004652368149489024, 'samples': 13896704, 'steps': 27141, 'loss/train': 1.5781397819519043}
-03/04/2022 21:21:11 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/04/2022 21:21:16 - INFO - codeparrot_training - Step 27142: {'lr': 0.0004652341153902016, 'samples': 13897216, 'steps': 27142, 'loss/train': 2.0407118797302246}
-03/04/2022 21:21:19 - INFO - codeparrot_training - Step 27143: {'lr': 0.00046523141573451965, 'samples': 13897728, 'steps': 27143, 'loss/train': 1.6682339906692505}
-03/04/2022 21:21:20 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 21:21:24 - INFO - codeparrot_training - Step 27144: {'lr': 0.0004652287159818577, 'samples': 13898240, 'steps': 27144, 'loss/train': 2.272930383682251}
-03/04/2022 21:21:27 - INFO - codeparrot_training - Step 27145: {'lr': 0.00046522601613221704, 'samples': 13898752, 'steps': 27145, 'loss/train': 2.5399696826934814}
-03/04/2022 21:21:28 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/04/2022 21:21:33 - INFO - codeparrot_training - Step 27146: {'lr': 0.0004652233161855989, 'samples': 13899264, 'steps': 27146, 'loss/train': 1.852360486984253}
-03/04/2022 21:21:36 - INFO - codeparrot_training - Step 27147: {'lr': 0.0004652206161420044, 'samples': 13899776, 'steps': 27147, 'loss/train': 2.4017114639282227}
-03/04/2022 21:21:37 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/04/2022 21:21:41 - INFO - codeparrot_training - Step 27148: {'lr': 0.00046521791600143483, 'samples': 13900288, 'steps': 27148, 'loss/train': 1.9020055532455444}
-03/04/2022 21:21:44 - INFO - codeparrot_training - Step 27149: {'lr': 0.00046521521576389134, 'samples': 13900800, 'steps': 27149, 'loss/train': 0.9204671382904053}
-03/04/2022 21:21:45 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 21:21:49 - INFO - codeparrot_training - Step 27150: {'lr': 0.00046521251542937524, 'samples': 13901312, 'steps': 27150, 'loss/train': 2.2946619987487793}
-03/04/2022 21:21:53 - INFO - codeparrot_training - Step 27151: {'lr': 0.0004652098149978877, 'samples': 13901824, 'steps': 27151, 'loss/train': 2.7079246044158936}
-03/04/2022 21:21:54 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/04/2022 21:21:58 - INFO - codeparrot_training - Step 27152: {'lr': 0.00046520711446943, 'samples': 13902336, 'steps': 27152, 'loss/train': 2.4164223670959473}
-03/04/2022 21:22:01 - INFO - codeparrot_training - Step 27153: {'lr': 0.0004652044138440032, 'samples': 13902848, 'steps': 27153, 'loss/train': 1.6536080837249756}
-03/04/2022 21:22:03 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/04/2022 21:22:06 - INFO - codeparrot_training - Step 27154: {'lr': 0.00046520171312160863, 'samples': 13903360, 'steps': 27154, 'loss/train': 2.0347158908843994}
-03/04/2022 21:22:10 - INFO - codeparrot_training - Step 27155: {'lr': 0.00046519901230224756, 'samples': 13903872, 'steps': 27155, 'loss/train': 1.8984805345535278}
-03/04/2022 21:22:11 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/04/2022 21:22:15 - INFO - codeparrot_training - Step 27156: {'lr': 0.000465196311385921, 'samples': 13904384, 'steps': 27156, 'loss/train': 2.7802813053131104}
-03/04/2022 21:22:18 - INFO - codeparrot_training - Step 27157: {'lr': 0.0004651936103726304, 'samples': 13904896, 'steps': 27157, 'loss/train': 2.2277681827545166}
-03/04/2022 21:22:21 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/04/2022 21:22:23 - INFO - codeparrot_training - Step 27158: {'lr': 0.0004651909092623769, 'samples': 13905408, 'steps': 27158, 'loss/train': 1.6847542524337769}
-03/04/2022 21:22:26 - INFO - codeparrot_training - Step 27159: {'lr': 0.00046518820805516165, 'samples': 13905920, 'steps': 27159, 'loss/train': 0.9047752022743225}
-03/04/2022 21:22:29 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 21:22:32 - INFO - codeparrot_training - Step 27160: {'lr': 0.0004651855067509859, 'samples': 13906432, 'steps': 27160, 'loss/train': 1.1378461122512817}
-03/04/2022 21:22:35 - INFO - codeparrot_training - Step 27161: {'lr': 0.0004651828053498509, 'samples': 13906944, 'steps': 27161, 'loss/train': 1.6713186502456665}
-03/04/2022 21:22:37 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/04/2022 21:22:40 - INFO - codeparrot_training - Step 27162: {'lr': 0.0004651801038517579, 'samples': 13907456, 'steps': 27162, 'loss/train': 2.3976619243621826}
-03/04/2022 21:22:43 - INFO - codeparrot_training - Step 27163: {'lr': 0.000465177402256708, 'samples': 13907968, 'steps': 27163, 'loss/train': 2.3340606689453125}
-03/04/2022 21:22:46 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/04/2022 21:22:49 - INFO - codeparrot_training - Step 27164: {'lr': 0.00046517470056470244, 'samples': 13908480, 'steps': 27164, 'loss/train': 1.6888781785964966}
-03/04/2022 21:22:52 - INFO - codeparrot_training - Step 27165: {'lr': 0.00046517199877574257, 'samples': 13908992, 'steps': 27165, 'loss/train': 1.3941059112548828}
-03/04/2022 21:22:54 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/04/2022 21:22:57 - INFO - codeparrot_training - Step 27166: {'lr': 0.0004651692968898295, 'samples': 13909504, 'steps': 27166, 'loss/train': 0.9268202781677246}
-03/04/2022 21:23:00 - INFO - codeparrot_training - Step 27167: {'lr': 0.00046516659490696444, 'samples': 13910016, 'steps': 27167, 'loss/train': 2.930304527282715}
-03/04/2022 21:23:03 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/04/2022 21:23:06 - INFO - codeparrot_training - Step 27168: {'lr': 0.0004651638928271487, 'samples': 13910528, 'steps': 27168, 'loss/train': 1.8597384691238403}
-03/04/2022 21:23:09 - INFO - codeparrot_training - Step 27169: {'lr': 0.00046516119065038335, 'samples': 13911040, 'steps': 27169, 'loss/train': 1.8607821464538574}
-03/04/2022 21:23:11 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/04/2022 21:23:14 - INFO - codeparrot_training - Step 27170: {'lr': 0.00046515848837666975, 'samples': 13911552, 'steps': 27170, 'loss/train': 1.6070096492767334}
-03/04/2022 21:23:17 - INFO - codeparrot_training - Step 27171: {'lr': 0.00046515578600600895, 'samples': 13912064, 'steps': 27171, 'loss/train': 1.3144350051879883}
-03/04/2022 21:23:20 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 21:23:23 - INFO - codeparrot_training - Step 27172: {'lr': 0.0004651530835384024, 'samples': 13912576, 'steps': 27172, 'loss/train': 2.287173271179199}
-03/04/2022 21:23:26 - INFO - codeparrot_training - Step 27173: {'lr': 0.0004651503809738511, 'samples': 13913088, 'steps': 27173, 'loss/train': 2.231224775314331}
-03/04/2022 21:23:28 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/04/2022 21:23:31 - INFO - codeparrot_training - Step 27174: {'lr': 0.0004651476783123564, 'samples': 13913600, 'steps': 27174, 'loss/train': 1.8622173070907593}
-03/04/2022 21:23:34 - INFO - codeparrot_training - Step 27175: {'lr': 0.00046514497555391946, 'samples': 13914112, 'steps': 27175, 'loss/train': 1.5029879808425903}
-03/04/2022 21:23:37 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/04/2022 21:23:40 - INFO - codeparrot_training - Step 27176: {'lr': 0.0004651422726985415, 'samples': 13914624, 'steps': 27176, 'loss/train': 1.9662816524505615}
-03/04/2022 21:23:43 - INFO - codeparrot_training - Step 27177: {'lr': 0.00046513956974622377, 'samples': 13915136, 'steps': 27177, 'loss/train': 1.4699898958206177}
-03/04/2022 21:23:45 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/04/2022 21:23:48 - INFO - codeparrot_training - Step 27178: {'lr': 0.00046513686669696756, 'samples': 13915648, 'steps': 27178, 'loss/train': 1.7560211420059204}
-03/04/2022 21:23:51 - INFO - codeparrot_training - Step 27179: {'lr': 0.00046513416355077386, 'samples': 13916160, 'steps': 27179, 'loss/train': 1.8316538333892822}
-03/04/2022 21:23:53 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/04/2022 21:23:56 - INFO - codeparrot_training - Step 27180: {'lr': 0.0004651314603076441, 'samples': 13916672, 'steps': 27180, 'loss/train': 2.3957161903381348}
-03/04/2022 21:24:00 - INFO - codeparrot_training - Step 27181: {'lr': 0.00046512875696757937, 'samples': 13917184, 'steps': 27181, 'loss/train': 1.9911634922027588}
-03/04/2022 21:24:02 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 21:24:05 - INFO - codeparrot_training - Step 27182: {'lr': 0.00046512605353058096, 'samples': 13917696, 'steps': 27182, 'loss/train': 1.1965152025222778}
-03/04/2022 21:24:08 - INFO - codeparrot_training - Step 27183: {'lr': 0.00046512334999665006, 'samples': 13918208, 'steps': 27183, 'loss/train': 1.6050702333450317}
-03/04/2022 21:24:11 - INFO - codeparrot_training - Step 27184: {'lr': 0.000465120646365788, 'samples': 13918720, 'steps': 27184, 'loss/train': 1.7720950841903687}
-03/04/2022 21:24:11 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/04/2022 21:24:17 - INFO - codeparrot_training - Step 27185: {'lr': 0.0004651179426379958, 'samples': 13919232, 'steps': 27185, 'loss/train': 1.7109336853027344}
-03/04/2022 21:24:20 - INFO - codeparrot_training - Step 27186: {'lr': 0.00046511523881327476, 'samples': 13919744, 'steps': 27186, 'loss/train': 1.0705214738845825}
-03/04/2022 21:24:20 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 21:24:25 - INFO - codeparrot_training - Step 27187: {'lr': 0.00046511253489162616, 'samples': 13920256, 'steps': 27187, 'loss/train': 2.0839645862579346}
-03/04/2022 21:24:28 - INFO - codeparrot_training - Step 27188: {'lr': 0.00046510983087305114, 'samples': 13920768, 'steps': 27188, 'loss/train': 0.9539011120796204}
-03/04/2022 21:24:28 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 21:24:34 - INFO - codeparrot_training - Step 27189: {'lr': 0.00046510712675755094, 'samples': 13921280, 'steps': 27189, 'loss/train': 1.6290028095245361}
-03/04/2022 21:24:37 - INFO - codeparrot_training - Step 27190: {'lr': 0.00046510442254512686, 'samples': 13921792, 'steps': 27190, 'loss/train': 2.3907692432403564}
-03/04/2022 21:24:37 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 21:24:42 - INFO - codeparrot_training - Step 27191: {'lr': 0.00046510171823578, 'samples': 13922304, 'steps': 27191, 'loss/train': 1.9262198209762573}
-03/04/2022 21:24:45 - INFO - codeparrot_training - Step 27192: {'lr': 0.0004650990138295116, 'samples': 13922816, 'steps': 27192, 'loss/train': 1.788630723953247}
-03/04/2022 21:24:45 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/04/2022 21:24:51 - INFO - codeparrot_training - Step 27193: {'lr': 0.00046509630932632293, 'samples': 13923328, 'steps': 27193, 'loss/train': 1.9480499029159546}
-03/04/2022 21:24:54 - INFO - codeparrot_training - Step 27194: {'lr': 0.0004650936047262152, 'samples': 13923840, 'steps': 27194, 'loss/train': 2.2159295082092285}
-03/04/2022 21:24:54 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 21:24:59 - INFO - codeparrot_training - Step 27195: {'lr': 0.0004650909000291895, 'samples': 13924352, 'steps': 27195, 'loss/train': 1.3598031997680664}
-03/04/2022 21:25:02 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 21:25:05 - INFO - codeparrot_training - Step 27196: {'lr': 0.00046508819523524724, 'samples': 13924864, 'steps': 27196, 'loss/train': 2.1528549194335938}
-03/04/2022 21:25:08 - INFO - codeparrot_training - Step 27197: {'lr': 0.0004650854903443896, 'samples': 13925376, 'steps': 27197, 'loss/train': 1.8450297117233276}
-03/04/2022 21:25:11 - INFO - codeparrot_training - Step 27198: {'lr': 0.00046508278535661775, 'samples': 13925888, 'steps': 27198, 'loss/train': 0.46189242601394653}
-03/04/2022 21:25:16 - INFO - codeparrot_training - Step 27199: {'lr': 0.00046508008027193286, 'samples': 13926400, 'steps': 27199, 'loss/train': 1.4161683320999146}
-03/04/2022 21:25:20 - INFO - codeparrot_training - Step 27200: {'lr': 0.0004650773750903363, 'samples': 13926912, 'steps': 27200, 'loss/train': 1.455668330192566}
-03/04/2022 21:25:20 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/04/2022 21:25:25 - INFO - codeparrot_training - Step 27201: {'lr': 0.0004650746698118291, 'samples': 13927424, 'steps': 27201, 'loss/train': 1.8708664178848267}
-03/04/2022 21:25:28 - INFO - codeparrot_training - Step 27202: {'lr': 0.0004650719644364126, 'samples': 13927936, 'steps': 27202, 'loss/train': 1.7596213817596436}
-03/04/2022 21:25:28 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/04/2022 21:25:33 - INFO - codeparrot_training - Step 27203: {'lr': 0.000465069258964088, 'samples': 13928448, 'steps': 27203, 'loss/train': 1.6614344120025635}
-03/04/2022 21:25:37 - INFO - codeparrot_training - Step 27204: {'lr': 0.0004650665533948565, 'samples': 13928960, 'steps': 27204, 'loss/train': 1.894809365272522}
-03/04/2022 21:25:37 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 21:25:42 - INFO - codeparrot_training - Step 27205: {'lr': 0.00046506384772871935, 'samples': 13929472, 'steps': 27205, 'loss/train': 1.5893926620483398}
-03/04/2022 21:25:45 - INFO - codeparrot_training - Step 27206: {'lr': 0.0004650611419656777, 'samples': 13929984, 'steps': 27206, 'loss/train': 2.292898178100586}
-03/04/2022 21:25:45 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/04/2022 21:25:50 - INFO - codeparrot_training - Step 27207: {'lr': 0.0004650584361057328, 'samples': 13930496, 'steps': 27207, 'loss/train': 1.7369637489318848}
-03/04/2022 21:25:53 - INFO - codeparrot_training - Step 27208: {'lr': 0.00046505573014888604, 'samples': 13931008, 'steps': 27208, 'loss/train': 2.0523242950439453}
-03/04/2022 21:25:54 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/04/2022 21:25:59 - INFO - codeparrot_training - Step 27209: {'lr': 0.0004650530240951383, 'samples': 13931520, 'steps': 27209, 'loss/train': 2.0914368629455566}
-03/04/2022 21:26:02 - INFO - codeparrot_training - Step 27210: {'lr': 0.0004650503179444911, 'samples': 13932032, 'steps': 27210, 'loss/train': 1.8827884197235107}
-03/04/2022 21:26:03 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/04/2022 21:26:07 - INFO - codeparrot_training - Step 27211: {'lr': 0.00046504761169694555, 'samples': 13932544, 'steps': 27211, 'loss/train': 1.5371589660644531}
-03/04/2022 21:26:10 - INFO - codeparrot_training - Step 27212: {'lr': 0.0004650449053525028, 'samples': 13933056, 'steps': 27212, 'loss/train': 1.7822381258010864}
-03/04/2022 21:26:11 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/04/2022 21:26:15 - INFO - codeparrot_training - Step 27213: {'lr': 0.00046504219891116416, 'samples': 13933568, 'steps': 27213, 'loss/train': 1.77534818649292}
-03/04/2022 21:26:19 - INFO - codeparrot_training - Step 27214: {'lr': 0.0004650394923729309, 'samples': 13934080, 'steps': 27214, 'loss/train': 4.209066867828369}
-03/04/2022 21:26:19 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 21:26:24 - INFO - codeparrot_training - Step 27215: {'lr': 0.00046503678573780403, 'samples': 13934592, 'steps': 27215, 'loss/train': 1.6322433948516846}
-03/04/2022 21:26:27 - INFO - codeparrot_training - Step 27216: {'lr': 0.000465034079005785, 'samples': 13935104, 'steps': 27216, 'loss/train': 1.5035631656646729}
-03/04/2022 21:26:27 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 21:26:32 - INFO - codeparrot_training - Step 27217: {'lr': 0.00046503137217687485, 'samples': 13935616, 'steps': 27217, 'loss/train': 0.9212533831596375}
-03/04/2022 21:26:35 - INFO - codeparrot_training - Step 27218: {'lr': 0.0004650286652510749, 'samples': 13936128, 'steps': 27218, 'loss/train': 0.8663285374641418}
-03/04/2022 21:26:36 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/04/2022 21:26:41 - INFO - codeparrot_training - Step 27219: {'lr': 0.0004650259582283864, 'samples': 13936640, 'steps': 27219, 'loss/train': 1.5176759958267212}
-03/04/2022 21:26:44 - INFO - codeparrot_training - Step 27220: {'lr': 0.0004650232511088105, 'samples': 13937152, 'steps': 27220, 'loss/train': 1.5205771923065186}
-03/04/2022 21:26:44 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/04/2022 21:26:49 - INFO - codeparrot_training - Step 27221: {'lr': 0.00046502054389234844, 'samples': 13937664, 'steps': 27221, 'loss/train': 1.086166262626648}
-03/04/2022 21:26:52 - INFO - codeparrot_training - Step 27222: {'lr': 0.0004650178365790014, 'samples': 13938176, 'steps': 27222, 'loss/train': 2.1769015789031982}
-03/04/2022 21:26:52 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 21:26:58 - INFO - codeparrot_training - Step 27223: {'lr': 0.0004650151291687707, 'samples': 13938688, 'steps': 27223, 'loss/train': 1.879853367805481}
-03/04/2022 21:27:01 - INFO - codeparrot_training - Step 27224: {'lr': 0.00046501242166165747, 'samples': 13939200, 'steps': 27224, 'loss/train': 1.0433379411697388}
-03/04/2022 21:27:01 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 21:27:06 - INFO - codeparrot_training - Step 27225: {'lr': 0.000465009714057663, 'samples': 13939712, 'steps': 27225, 'loss/train': 2.0189249515533447}
-03/04/2022 21:27:09 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/04/2022 21:27:11 - INFO - codeparrot_training - Step 27226: {'lr': 0.00046500700635678844, 'samples': 13940224, 'steps': 27226, 'loss/train': 2.252335786819458}
-03/04/2022 21:27:14 - INFO - codeparrot_training - Step 27227: {'lr': 0.000465004298559035, 'samples': 13940736, 'steps': 27227, 'loss/train': 1.1944422721862793}
-03/04/2022 21:27:17 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 21:27:20 - INFO - codeparrot_training - Step 27228: {'lr': 0.00046500159066440404, 'samples': 13941248, 'steps': 27228, 'loss/train': 0.44980719685554504}
-03/04/2022 21:27:23 - INFO - codeparrot_training - Step 27229: {'lr': 0.0004649988826728966, 'samples': 13941760, 'steps': 27229, 'loss/train': 2.0220401287078857}
-03/04/2022 21:27:26 - INFO - codeparrot_training - Step 27230: {'lr': 0.000464996174584514, 'samples': 13942272, 'steps': 27230, 'loss/train': 1.6536790132522583}
-03/04/2022 21:27:26 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 21:27:31 - INFO - codeparrot_training - Step 27231: {'lr': 0.00046499346639925746, 'samples': 13942784, 'steps': 27231, 'loss/train': 1.8055981397628784}
-03/04/2022 21:27:34 - INFO - codeparrot_training - Step 27232: {'lr': 0.0004649907581171282, 'samples': 13943296, 'steps': 27232, 'loss/train': 2.357915163040161}
-03/04/2022 21:27:34 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/04/2022 21:27:40 - INFO - codeparrot_training - Step 27233: {'lr': 0.00046498804973812735, 'samples': 13943808, 'steps': 27233, 'loss/train': 1.428297758102417}
-03/04/2022 21:27:43 - INFO - codeparrot_training - Step 27234: {'lr': 0.00046498534126225625, 'samples': 13944320, 'steps': 27234, 'loss/train': 0.39849698543548584}
-03/04/2022 21:27:44 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/04/2022 21:27:49 - INFO - codeparrot_training - Step 27235: {'lr': 0.0004649826326895161, 'samples': 13944832, 'steps': 27235, 'loss/train': 1.4829034805297852}
-03/04/2022 21:27:52 - INFO - codeparrot_training - Step 27236: {'lr': 0.0004649799240199081, 'samples': 13945344, 'steps': 27236, 'loss/train': 1.4370018243789673}
-03/04/2022 21:27:52 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 21:27:57 - INFO - codeparrot_training - Step 27237: {'lr': 0.0004649772152534334, 'samples': 13945856, 'steps': 27237, 'loss/train': 2.1481642723083496}
-03/04/2022 21:28:00 - INFO - codeparrot_training - Step 27238: {'lr': 0.0004649745063900933, 'samples': 13946368, 'steps': 27238, 'loss/train': 2.4609646797180176}
-03/04/2022 21:28:01 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/04/2022 21:28:05 - INFO - codeparrot_training - Step 27239: {'lr': 0.000464971797429889, 'samples': 13946880, 'steps': 27239, 'loss/train': 1.1149240732192993}
-03/04/2022 21:28:08 - INFO - codeparrot_training - Step 27240: {'lr': 0.00046496908837282173, 'samples': 13947392, 'steps': 27240, 'loss/train': 1.6180450916290283}
-03/04/2022 21:28:09 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/04/2022 21:28:14 - INFO - codeparrot_training - Step 27241: {'lr': 0.00046496637921889276, 'samples': 13947904, 'steps': 27241, 'loss/train': 2.0958292484283447}
-03/04/2022 21:28:17 - INFO - codeparrot_training - Step 27242: {'lr': 0.0004649636699681031, 'samples': 13948416, 'steps': 27242, 'loss/train': 2.075373888015747}
-03/04/2022 21:28:17 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/04/2022 21:28:22 - INFO - codeparrot_training - Step 27243: {'lr': 0.00046496096062045427, 'samples': 13948928, 'steps': 27243, 'loss/train': 1.2011469602584839}
-03/04/2022 21:28:25 - INFO - codeparrot_training - Step 27244: {'lr': 0.00046495825117594735, 'samples': 13949440, 'steps': 27244, 'loss/train': 2.0066211223602295}
-03/04/2022 21:28:26 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/04/2022 21:28:31 - INFO - codeparrot_training - Step 27245: {'lr': 0.0004649555416345835, 'samples': 13949952, 'steps': 27245, 'loss/train': 2.4188411235809326}
-03/04/2022 21:28:34 - INFO - codeparrot_training - Step 27246: {'lr': 0.0004649528319963641, 'samples': 13950464, 'steps': 27246, 'loss/train': 2.104572057723999}
-03/04/2022 21:28:34 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 21:28:39 - INFO - codeparrot_training - Step 27247: {'lr': 0.0004649501222612901, 'samples': 13950976, 'steps': 27247, 'loss/train': 1.0064759254455566}
-03/04/2022 21:28:42 - INFO - codeparrot_training - Step 27248: {'lr': 0.000464947412429363, 'samples': 13951488, 'steps': 27248, 'loss/train': 1.3773727416992188}
-03/04/2022 21:28:42 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/04/2022 21:28:48 - INFO - codeparrot_training - Step 27249: {'lr': 0.000464944702500584, 'samples': 13952000, 'steps': 27249, 'loss/train': 2.1093738079071045}
-03/04/2022 21:28:51 - INFO - codeparrot_training - Step 27250: {'lr': 0.0004649419924749541, 'samples': 13952512, 'steps': 27250, 'loss/train': 1.824320673942566}
-03/04/2022 21:28:52 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 21:28:56 - INFO - codeparrot_training - Step 27251: {'lr': 0.0004649392823524746, 'samples': 13953024, 'steps': 27251, 'loss/train': 1.4800001382827759}
-03/04/2022 21:28:59 - INFO - codeparrot_training - Step 27252: {'lr': 0.0004649365721331469, 'samples': 13953536, 'steps': 27252, 'loss/train': 2.046095371246338}
-03/04/2022 21:29:01 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 21:29:05 - INFO - codeparrot_training - Step 27253: {'lr': 0.00046493386181697206, 'samples': 13954048, 'steps': 27253, 'loss/train': 1.2677292823791504}
-03/04/2022 21:29:08 - INFO - codeparrot_training - Step 27254: {'lr': 0.00046493115140395136, 'samples': 13954560, 'steps': 27254, 'loss/train': 2.1946308612823486}
-03/04/2022 21:29:09 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/04/2022 21:29:13 - INFO - codeparrot_training - Step 27255: {'lr': 0.000464928440894086, 'samples': 13955072, 'steps': 27255, 'loss/train': 1.7067654132843018}
-03/04/2022 21:29:16 - INFO - codeparrot_training - Step 27256: {'lr': 0.00046492573028737716, 'samples': 13955584, 'steps': 27256, 'loss/train': 1.880800485610962}
-03/04/2022 21:29:18 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/04/2022 21:29:22 - INFO - codeparrot_training - Step 27257: {'lr': 0.0004649230195838261, 'samples': 13956096, 'steps': 27257, 'loss/train': 1.8770759105682373}
-03/04/2022 21:29:25 - INFO - codeparrot_training - Step 27258: {'lr': 0.00046492030878343406, 'samples': 13956608, 'steps': 27258, 'loss/train': 1.2926831245422363}
-03/04/2022 21:29:26 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/04/2022 21:29:30 - INFO - codeparrot_training - Step 27259: {'lr': 0.00046491759788620227, 'samples': 13957120, 'steps': 27259, 'loss/train': 2.585660696029663}
-03/04/2022 21:29:33 - INFO - codeparrot_training - Step 27260: {'lr': 0.0004649148868921319, 'samples': 13957632, 'steps': 27260, 'loss/train': 2.572108745574951}
-03/04/2022 21:29:35 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/04/2022 21:29:38 - INFO - codeparrot_training - Step 27261: {'lr': 0.00046491217580122427, 'samples': 13958144, 'steps': 27261, 'loss/train': 1.8491166830062866}
-03/04/2022 21:29:42 - INFO - codeparrot_training - Step 27262: {'lr': 0.00046490946461348045, 'samples': 13958656, 'steps': 27262, 'loss/train': 3.0542492866516113}
-03/04/2022 21:29:43 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/04/2022 21:29:47 - INFO - codeparrot_training - Step 27263: {'lr': 0.00046490675332890177, 'samples': 13959168, 'steps': 27263, 'loss/train': 1.4080657958984375}
-03/04/2022 21:29:50 - INFO - codeparrot_training - Step 27264: {'lr': 0.00046490404194748935, 'samples': 13959680, 'steps': 27264, 'loss/train': 0.6727156639099121}
-03/04/2022 21:29:51 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 21:29:55 - INFO - codeparrot_training - Step 27265: {'lr': 0.00046490133046924457, 'samples': 13960192, 'steps': 27265, 'loss/train': 2.1778900623321533}
-03/04/2022 21:29:59 - INFO - codeparrot_training - Step 27266: {'lr': 0.0004648986188941685, 'samples': 13960704, 'steps': 27266, 'loss/train': 1.8192154169082642}
-03/04/2022 21:30:00 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/04/2022 21:30:04 - INFO - codeparrot_training - Step 27267: {'lr': 0.0004648959072222625, 'samples': 13961216, 'steps': 27267, 'loss/train': 1.500523567199707}
-03/04/2022 21:30:07 - INFO - codeparrot_training - Step 27268: {'lr': 0.0004648931954535277, 'samples': 13961728, 'steps': 27268, 'loss/train': 1.6341878175735474}
-03/04/2022 21:30:08 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 21:30:12 - INFO - codeparrot_training - Step 27269: {'lr': 0.0004648904835879654, 'samples': 13962240, 'steps': 27269, 'loss/train': 1.3035786151885986}
-03/04/2022 21:30:15 - INFO - codeparrot_training - Step 27270: {'lr': 0.0004648877716255766, 'samples': 13962752, 'steps': 27270, 'loss/train': 1.9258136749267578}
-03/04/2022 21:30:17 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/04/2022 21:30:21 - INFO - codeparrot_training - Step 27271: {'lr': 0.00046488505956636286, 'samples': 13963264, 'steps': 27271, 'loss/train': 2.2206928730010986}
-03/04/2022 21:30:24 - INFO - codeparrot_training - Step 27272: {'lr': 0.0004648823474103251, 'samples': 13963776, 'steps': 27272, 'loss/train': 1.7389881610870361}
-03/04/2022 21:30:25 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 21:30:29 - INFO - codeparrot_training - Step 27273: {'lr': 0.0004648796351574648, 'samples': 13964288, 'steps': 27273, 'loss/train': 1.4280964136123657}
-03/04/2022 21:30:32 - INFO - codeparrot_training - Step 27274: {'lr': 0.0004648769228077829, 'samples': 13964800, 'steps': 27274, 'loss/train': 1.5894533395767212}
-03/04/2022 21:30:38 - INFO - codeparrot_training - Step 27275: {'lr': 0.00046487421036128085, 'samples': 13965312, 'steps': 27275, 'loss/train': 1.7295185327529907}
-03/04/2022 21:30:41 - INFO - codeparrot_training - Step 27276: {'lr': 0.00046487149781795976, 'samples': 13965824, 'steps': 27276, 'loss/train': 1.7408370971679688}
-03/04/2022 21:30:42 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/04/2022 21:30:46 - INFO - codeparrot_training - Step 27277: {'lr': 0.00046486878517782094, 'samples': 13966336, 'steps': 27277, 'loss/train': 1.9155091047286987}
-03/04/2022 21:30:49 - INFO - codeparrot_training - Step 27278: {'lr': 0.0004648660724408656, 'samples': 13966848, 'steps': 27278, 'loss/train': 0.5985935926437378}
-03/04/2022 21:30:50 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 21:30:55 - INFO - codeparrot_training - Step 27279: {'lr': 0.00046486335960709485, 'samples': 13967360, 'steps': 27279, 'loss/train': 1.571506381034851}
-03/04/2022 21:30:58 - INFO - codeparrot_training - Step 27280: {'lr': 0.00046486064667651, 'samples': 13967872, 'steps': 27280, 'loss/train': 1.766096830368042}
-03/04/2022 21:30:59 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/04/2022 21:31:03 - INFO - codeparrot_training - Step 27281: {'lr': 0.0004648579336491123, 'samples': 13968384, 'steps': 27281, 'loss/train': 1.37592613697052}
-03/04/2022 21:31:06 - INFO - codeparrot_training - Step 27282: {'lr': 0.0004648552205249029, 'samples': 13968896, 'steps': 27282, 'loss/train': 1.9541445970535278}
-03/04/2022 21:31:07 - INFO - codeparrot_training - Skipping example with length 553 (seq_length=1024)
-03/04/2022 21:31:12 - INFO - codeparrot_training - Step 27283: {'lr': 0.000464852507303883, 'samples': 13969408, 'steps': 27283, 'loss/train': 2.6447255611419678}
-03/04/2022 21:31:15 - INFO - codeparrot_training - Step 27284: {'lr': 0.0004648497939860539, 'samples': 13969920, 'steps': 27284, 'loss/train': 1.3173807859420776}
-03/04/2022 21:31:16 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/04/2022 21:31:20 - INFO - codeparrot_training - Step 27285: {'lr': 0.0004648470805714169, 'samples': 13970432, 'steps': 27285, 'loss/train': 1.6244666576385498}
-03/04/2022 21:31:23 - INFO - codeparrot_training - Step 27286: {'lr': 0.00046484436705997303, 'samples': 13970944, 'steps': 27286, 'loss/train': 2.420758008956909}
-03/04/2022 21:31:25 - INFO - codeparrot_training - Skipping example with length 86 (seq_length=1024)
-03/04/2022 21:31:29 - INFO - codeparrot_training - Step 27287: {'lr': 0.0004648416534517236, 'samples': 13971456, 'steps': 27287, 'loss/train': 1.7559852600097656}
-03/04/2022 21:31:32 - INFO - codeparrot_training - Step 27288: {'lr': 0.00046483893974666983, 'samples': 13971968, 'steps': 27288, 'loss/train': 1.3592007160186768}
-03/04/2022 21:31:33 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/04/2022 21:31:37 - INFO - codeparrot_training - Step 27289: {'lr': 0.000464836225944813, 'samples': 13972480, 'steps': 27289, 'loss/train': 0.6610035300254822}
-03/04/2022 21:31:40 - INFO - codeparrot_training - Step 27290: {'lr': 0.00046483351204615423, 'samples': 13972992, 'steps': 27290, 'loss/train': 0.5085729956626892}
-03/04/2022 21:31:42 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/04/2022 21:31:45 - INFO - codeparrot_training - Step 27291: {'lr': 0.0004648307980506948, 'samples': 13973504, 'steps': 27291, 'loss/train': 1.7768157720565796}
-03/04/2022 21:31:49 - INFO - codeparrot_training - Step 27292: {'lr': 0.00046482808395843594, 'samples': 13974016, 'steps': 27292, 'loss/train': 1.3744535446166992}
-03/04/2022 21:31:50 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/04/2022 21:31:54 - INFO - codeparrot_training - Step 27293: {'lr': 0.0004648253697693789, 'samples': 13974528, 'steps': 27293, 'loss/train': 1.9383039474487305}
-03/04/2022 21:31:57 - INFO - codeparrot_training - Step 27294: {'lr': 0.0004648226554835248, 'samples': 13975040, 'steps': 27294, 'loss/train': 1.004044532775879}
-03/04/2022 21:31:59 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/04/2022 21:32:03 - INFO - codeparrot_training - Step 27295: {'lr': 0.000464819941100875, 'samples': 13975552, 'steps': 27295, 'loss/train': 0.9965910911560059}
-03/04/2022 21:32:06 - INFO - codeparrot_training - Step 27296: {'lr': 0.00046481722662143057, 'samples': 13976064, 'steps': 27296, 'loss/train': 0.9804989099502563}
-03/04/2022 21:32:07 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/04/2022 21:32:11 - INFO - codeparrot_training - Step 27297: {'lr': 0.0004648145120451929, 'samples': 13976576, 'steps': 27297, 'loss/train': 2.134272336959839}
-03/04/2022 21:32:14 - INFO - codeparrot_training - Step 27298: {'lr': 0.000464811797372163, 'samples': 13977088, 'steps': 27298, 'loss/train': 2.401169776916504}
-03/04/2022 21:32:16 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 21:32:20 - INFO - codeparrot_training - Step 27299: {'lr': 0.00046480908260234234, 'samples': 13977600, 'steps': 27299, 'loss/train': 1.2475439310073853}
-03/04/2022 21:32:23 - INFO - codeparrot_training - Step 27300: {'lr': 0.0004648063677357319, 'samples': 13978112, 'steps': 27300, 'loss/train': 2.148590564727783}
-03/04/2022 21:32:24 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 21:32:28 - INFO - codeparrot_training - Step 27301: {'lr': 0.00046480365277233316, 'samples': 13978624, 'steps': 27301, 'loss/train': 3.2269961833953857}
-03/04/2022 21:32:31 - INFO - codeparrot_training - Step 27302: {'lr': 0.00046480093771214716, 'samples': 13979136, 'steps': 27302, 'loss/train': 1.9284334182739258}
-03/04/2022 21:32:33 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 21:32:37 - INFO - codeparrot_training - Step 27303: {'lr': 0.0004647982225551751, 'samples': 13979648, 'steps': 27303, 'loss/train': 2.0808684825897217}
-03/04/2022 21:32:40 - INFO - codeparrot_training - Step 27304: {'lr': 0.0004647955073014184, 'samples': 13980160, 'steps': 27304, 'loss/train': 1.436845064163208}
-03/04/2022 21:32:42 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/04/2022 21:32:45 - INFO - codeparrot_training - Step 27305: {'lr': 0.00046479279195087804, 'samples': 13980672, 'steps': 27305, 'loss/train': 2.772162914276123}
-03/04/2022 21:32:48 - INFO - codeparrot_training - Step 27306: {'lr': 0.0004647900765035554, 'samples': 13981184, 'steps': 27306, 'loss/train': 1.9187259674072266}
-03/04/2022 21:32:50 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 21:32:54 - INFO - codeparrot_training - Step 27307: {'lr': 0.0004647873609594517, 'samples': 13981696, 'steps': 27307, 'loss/train': 2.2711098194122314}
-03/04/2022 21:32:57 - INFO - codeparrot_training - Step 27308: {'lr': 0.0004647846453185681, 'samples': 13982208, 'steps': 27308, 'loss/train': 1.9040457010269165}
-03/04/2022 21:32:59 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/04/2022 21:33:03 - INFO - codeparrot_training - Step 27309: {'lr': 0.0004647819295809059, 'samples': 13982720, 'steps': 27309, 'loss/train': 1.8028217554092407}
-03/04/2022 21:33:06 - INFO - codeparrot_training - Step 27310: {'lr': 0.00046477921374646624, 'samples': 13983232, 'steps': 27310, 'loss/train': 3.1039977073669434}
-03/04/2022 21:33:09 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/04/2022 21:33:11 - INFO - codeparrot_training - Step 27311: {'lr': 0.0004647764978152503, 'samples': 13983744, 'steps': 27311, 'loss/train': 1.920505404472351}
-03/04/2022 21:33:14 - INFO - codeparrot_training - Step 27312: {'lr': 0.0004647737817872595, 'samples': 13984256, 'steps': 27312, 'loss/train': 2.512624502182007}
-03/04/2022 21:33:18 - INFO - codeparrot_training - Step 27313: {'lr': 0.0004647710656624949, 'samples': 13984768, 'steps': 27313, 'loss/train': 0.24730858206748962}
-03/04/2022 21:33:18 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/04/2022 21:33:23 - INFO - codeparrot_training - Step 27314: {'lr': 0.0004647683494409578, 'samples': 13985280, 'steps': 27314, 'loss/train': 2.483790159225464}
-03/04/2022 21:33:26 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/04/2022 21:33:28 - INFO - codeparrot_training - Step 27315: {'lr': 0.0004647656331226494, 'samples': 13985792, 'steps': 27315, 'loss/train': 1.7700674533843994}
-03/04/2022 21:33:31 - INFO - codeparrot_training - Step 27316: {'lr': 0.0004647629167075709, 'samples': 13986304, 'steps': 27316, 'loss/train': 1.3436956405639648}
-03/04/2022 21:33:35 - INFO - codeparrot_training - Step 27317: {'lr': 0.00046476020019572354, 'samples': 13986816, 'steps': 27317, 'loss/train': 1.9957822561264038}
-03/04/2022 21:33:35 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/04/2022 21:33:40 - INFO - codeparrot_training - Step 27318: {'lr': 0.00046475748358710856, 'samples': 13987328, 'steps': 27318, 'loss/train': 1.872269630432129}
-03/04/2022 21:33:43 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/04/2022 21:33:45 - INFO - codeparrot_training - Step 27319: {'lr': 0.0004647547668817271, 'samples': 13987840, 'steps': 27319, 'loss/train': 2.207102060317993}
-03/04/2022 21:33:48 - INFO - codeparrot_training - Step 27320: {'lr': 0.00046475205007958054, 'samples': 13988352, 'steps': 27320, 'loss/train': 2.4627227783203125}
-03/04/2022 21:33:51 - INFO - codeparrot_training - Step 27321: {'lr': 0.00046474933318067004, 'samples': 13988864, 'steps': 27321, 'loss/train': 1.6673823595046997}
-03/04/2022 21:33:51 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/04/2022 21:33:57 - INFO - codeparrot_training - Step 27322: {'lr': 0.0004647466161849968, 'samples': 13989376, 'steps': 27322, 'loss/train': 1.8202558755874634}
-03/04/2022 21:34:00 - INFO - codeparrot_training - Step 27323: {'lr': 0.000464743899092562, 'samples': 13989888, 'steps': 27323, 'loss/train': 2.1119251251220703}
-03/04/2022 21:34:00 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/04/2022 21:34:05 - INFO - codeparrot_training - Step 27324: {'lr': 0.0004647411819033669, 'samples': 13990400, 'steps': 27324, 'loss/train': 2.1649341583251953}
-03/04/2022 21:34:08 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/04/2022 21:34:10 - INFO - codeparrot_training - Step 27325: {'lr': 0.00046473846461741276, 'samples': 13990912, 'steps': 27325, 'loss/train': 1.8168530464172363}
-03/04/2022 21:34:14 - INFO - codeparrot_training - Step 27326: {'lr': 0.0004647357472347008, 'samples': 13991424, 'steps': 27326, 'loss/train': 2.44339919090271}
-03/04/2022 21:34:16 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/04/2022 21:34:19 - INFO - codeparrot_training - Step 27327: {'lr': 0.00046473302975523224, 'samples': 13991936, 'steps': 27327, 'loss/train': 1.5548832416534424}
-03/04/2022 21:34:22 - INFO - codeparrot_training - Step 27328: {'lr': 0.0004647303121790082, 'samples': 13992448, 'steps': 27328, 'loss/train': 1.8480143547058105}
-03/04/2022 21:34:25 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 21:34:27 - INFO - codeparrot_training - Step 27329: {'lr': 0.0004647275945060301, 'samples': 13992960, 'steps': 27329, 'loss/train': 1.090482473373413}
-03/04/2022 21:34:31 - INFO - codeparrot_training - Step 27330: {'lr': 0.000464724876736299, 'samples': 13993472, 'steps': 27330, 'loss/train': 2.0289106369018555}
-03/04/2022 21:34:33 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/04/2022 21:34:36 - INFO - codeparrot_training - Step 27331: {'lr': 0.00046472215886981616, 'samples': 13993984, 'steps': 27331, 'loss/train': 1.5530024766921997}
-03/04/2022 21:34:39 - INFO - codeparrot_training - Step 27332: {'lr': 0.00046471944090658294, 'samples': 13994496, 'steps': 27332, 'loss/train': 1.7373859882354736}
-03/04/2022 21:34:42 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/04/2022 21:34:45 - INFO - codeparrot_training - Step 27333: {'lr': 0.0004647167228466004, 'samples': 13995008, 'steps': 27333, 'loss/train': 2.1907501220703125}
-03/04/2022 21:34:48 - INFO - codeparrot_training - Step 27334: {'lr': 0.0004647140046898697, 'samples': 13995520, 'steps': 27334, 'loss/train': 2.283541679382324}
-03/04/2022 21:34:51 - INFO - codeparrot_training - Step 27335: {'lr': 0.0004647112864363923, 'samples': 13996032, 'steps': 27335, 'loss/train': 3.3142378330230713}
-03/04/2022 21:34:52 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 21:34:56 - INFO - codeparrot_training - Step 27336: {'lr': 0.00046470856808616934, 'samples': 13996544, 'steps': 27336, 'loss/train': 1.3447926044464111}
-03/04/2022 21:34:59 - INFO - codeparrot_training - Step 27337: {'lr': 0.0004647058496392019, 'samples': 13997056, 'steps': 27337, 'loss/train': 1.9790986776351929}
-03/04/2022 21:35:00 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/04/2022 21:35:05 - INFO - codeparrot_training - Step 27338: {'lr': 0.0004647031310954914, 'samples': 13997568, 'steps': 27338, 'loss/train': 2.673316240310669}
-03/04/2022 21:35:08 - INFO - codeparrot_training - Step 27339: {'lr': 0.00046470041245503895, 'samples': 13998080, 'steps': 27339, 'loss/train': 1.678635835647583}
-03/04/2022 21:35:09 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/04/2022 21:35:13 - INFO - codeparrot_training - Step 27340: {'lr': 0.0004646976937178459, 'samples': 13998592, 'steps': 27340, 'loss/train': 1.8614041805267334}
-03/04/2022 21:35:16 - INFO - codeparrot_training - Step 27341: {'lr': 0.0004646949748839132, 'samples': 13999104, 'steps': 27341, 'loss/train': 1.4324384927749634}
-03/04/2022 21:35:18 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/04/2022 21:35:22 - INFO - codeparrot_training - Step 27342: {'lr': 0.0004646922559532424, 'samples': 13999616, 'steps': 27342, 'loss/train': 2.4837899208068848}
-03/04/2022 21:35:25 - INFO - codeparrot_training - Step 27343: {'lr': 0.0004646895369258345, 'samples': 14000128, 'steps': 27343, 'loss/train': 1.9539533853530884}
-03/04/2022 21:35:26 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/04/2022 21:35:30 - INFO - codeparrot_training - Step 27344: {'lr': 0.00046468681780169086, 'samples': 14000640, 'steps': 27344, 'loss/train': 1.9839603900909424}
-03/04/2022 21:35:33 - INFO - codeparrot_training - Step 27345: {'lr': 0.0004646840985808126, 'samples': 14001152, 'steps': 27345, 'loss/train': 1.9265379905700684}
-03/04/2022 21:35:34 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/04/2022 21:35:39 - INFO - codeparrot_training - Step 27346: {'lr': 0.0004646813792632011, 'samples': 14001664, 'steps': 27346, 'loss/train': 1.5810306072235107}
-03/04/2022 21:35:42 - INFO - codeparrot_training - Step 27347: {'lr': 0.00046467865984885736, 'samples': 14002176, 'steps': 27347, 'loss/train': 2.1293587684631348}
-03/04/2022 21:35:45 - INFO - codeparrot_training - Step 27348: {'lr': 0.0004646759403377828, 'samples': 14002688, 'steps': 27348, 'loss/train': 2.6820826530456543}
-03/04/2022 21:35:45 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/04/2022 21:35:51 - INFO - codeparrot_training - Step 27349: {'lr': 0.00046467322072997865, 'samples': 14003200, 'steps': 27349, 'loss/train': 0.4234185218811035}
-03/04/2022 21:35:54 - INFO - codeparrot_training - Step 27350: {'lr': 0.00046467050102544594, 'samples': 14003712, 'steps': 27350, 'loss/train': 2.3875370025634766}
-03/04/2022 21:35:54 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/04/2022 21:35:59 - INFO - codeparrot_training - Step 27351: {'lr': 0.0004646677812241861, 'samples': 14004224, 'steps': 27351, 'loss/train': 1.9230246543884277}
-03/04/2022 21:36:02 - INFO - codeparrot_training - Step 27352: {'lr': 0.0004646650613262001, 'samples': 14004736, 'steps': 27352, 'loss/train': 0.4853203296661377}
-03/04/2022 21:36:03 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/04/2022 21:36:08 - INFO - codeparrot_training - Step 27353: {'lr': 0.00046466234133148957, 'samples': 14005248, 'steps': 27353, 'loss/train': 2.0545365810394287}
-03/04/2022 21:36:11 - INFO - codeparrot_training - Step 27354: {'lr': 0.00046465962124005535, 'samples': 14005760, 'steps': 27354, 'loss/train': 1.6933728456497192}
-03/04/2022 21:36:11 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/04/2022 21:36:16 - INFO - codeparrot_training - Step 27355: {'lr': 0.0004646569010518988, 'samples': 14006272, 'steps': 27355, 'loss/train': 1.5168442726135254}
-03/04/2022 21:36:19 - INFO - codeparrot_training - Step 27356: {'lr': 0.00046465418076702125, 'samples': 14006784, 'steps': 27356, 'loss/train': 2.1320295333862305}
-03/04/2022 21:36:19 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/04/2022 21:36:25 - INFO - codeparrot_training - Step 27357: {'lr': 0.00046465146038542375, 'samples': 14007296, 'steps': 27357, 'loss/train': 2.427990198135376}
-03/04/2022 21:36:28 - INFO - codeparrot_training - Step 27358: {'lr': 0.0004646487399071077, 'samples': 14007808, 'steps': 27358, 'loss/train': 1.6325488090515137}
-03/04/2022 21:36:28 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/04/2022 21:36:33 - INFO - codeparrot_training - Step 27359: {'lr': 0.00046464601933207417, 'samples': 14008320, 'steps': 27359, 'loss/train': 1.868369698524475}
-03/04/2022 21:36:36 - INFO - codeparrot_training - Step 27360: {'lr': 0.0004646432986603245, 'samples': 14008832, 'steps': 27360, 'loss/train': 1.950134515762329}
-03/04/2022 21:36:36 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/04/2022 21:36:42 - INFO - codeparrot_training - Step 27361: {'lr': 0.00046464057789185985, 'samples': 14009344, 'steps': 27361, 'loss/train': 1.0225882530212402}
-03/04/2022 21:36:45 - INFO - codeparrot_training - Step 27362: {'lr': 0.00046463785702668156, 'samples': 14009856, 'steps': 27362, 'loss/train': 1.4361827373504639}
-03/04/2022 21:36:45 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/04/2022 21:36:50 - INFO - codeparrot_training - Step 27363: {'lr': 0.0004646351360647907, 'samples': 14010368, 'steps': 27363, 'loss/train': 2.1005513668060303}
-03/04/2022 21:36:53 - INFO - codeparrot_training - Step 27364: {'lr': 0.00046463241500618846, 'samples': 14010880, 'steps': 27364, 'loss/train': 1.7549381256103516}
-03/04/2022 21:36:53 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 21:36:58 - INFO - codeparrot_training - Step 27365: {'lr': 0.00046462969385087626, 'samples': 14011392, 'steps': 27365, 'loss/train': 1.912890911102295}
-03/04/2022 21:37:02 - INFO - codeparrot_training - Step 27366: {'lr': 0.00046462697259885523, 'samples': 14011904, 'steps': 27366, 'loss/train': 1.626736044883728}
-03/04/2022 21:37:02 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/04/2022 21:37:07 - INFO - codeparrot_training - Step 27367: {'lr': 0.0004646242512501266, 'samples': 14012416, 'steps': 27367, 'loss/train': 0.9463950991630554}
-03/04/2022 21:37:10 - INFO - codeparrot_training - Step 27368: {'lr': 0.0004646215298046916, 'samples': 14012928, 'steps': 27368, 'loss/train': 1.5539534091949463}
-03/04/2022 21:37:10 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/04/2022 21:37:15 - INFO - codeparrot_training - Step 27369: {'lr': 0.00046461880826255143, 'samples': 14013440, 'steps': 27369, 'loss/train': 1.0024809837341309}
-03/04/2022 21:37:19 - INFO - codeparrot_training - Step 27370: {'lr': 0.00046461608662370734, 'samples': 14013952, 'steps': 27370, 'loss/train': 2.000147819519043}
-03/04/2022 21:37:19 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/04/2022 21:37:24 - INFO - codeparrot_training - Step 27371: {'lr': 0.0004646133648881606, 'samples': 14014464, 'steps': 27371, 'loss/train': 1.0557485818862915}
-03/04/2022 21:37:27 - INFO - codeparrot_training - Step 27372: {'lr': 0.00046461064305591235, 'samples': 14014976, 'steps': 27372, 'loss/train': 1.2884052991867065}
-03/04/2022 21:37:27 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 21:37:32 - INFO - codeparrot_training - Step 27373: {'lr': 0.00046460792112696384, 'samples': 14015488, 'steps': 27373, 'loss/train': 1.8098361492156982}
-03/04/2022 21:37:35 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/04/2022 21:37:38 - INFO - codeparrot_training - Step 27374: {'lr': 0.0004646051991013163, 'samples': 14016000, 'steps': 27374, 'loss/train': 1.5951982736587524}
-03/04/2022 21:37:41 - INFO - codeparrot_training - Step 27375: {'lr': 0.000464602476978971, 'samples': 14016512, 'steps': 27375, 'loss/train': 2.246730089187622}
-03/04/2022 21:37:44 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/04/2022 21:37:46 - INFO - codeparrot_training - Step 27376: {'lr': 0.00046459975475992914, 'samples': 14017024, 'steps': 27376, 'loss/train': 2.352454423904419}
-03/04/2022 21:37:49 - INFO - codeparrot_training - Step 27377: {'lr': 0.00046459703244419194, 'samples': 14017536, 'steps': 27377, 'loss/train': 0.49017319083213806}
-03/04/2022 21:37:52 - INFO - codeparrot_training - Step 27378: {'lr': 0.0004645943100317606, 'samples': 14018048, 'steps': 27378, 'loss/train': 1.823350429534912}
-03/04/2022 21:37:52 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/04/2022 21:37:58 - INFO - codeparrot_training - Step 27379: {'lr': 0.00046459158752263643, 'samples': 14018560, 'steps': 27379, 'loss/train': 0.17725194990634918}
-03/04/2022 21:38:01 - INFO - codeparrot_training - Step 27380: {'lr': 0.0004645888649168205, 'samples': 14019072, 'steps': 27380, 'loss/train': 0.8929397463798523}
-03/04/2022 21:38:01 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/04/2022 21:38:06 - INFO - codeparrot_training - Step 27381: {'lr': 0.0004645861422143143, 'samples': 14019584, 'steps': 27381, 'loss/train': 1.661621332168579}
-03/04/2022 21:38:10 - INFO - codeparrot_training - Step 27382: {'lr': 0.0004645834194151187, 'samples': 14020096, 'steps': 27382, 'loss/train': 0.8645858764648438}
-03/04/2022 21:38:10 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/04/2022 21:38:15 - INFO - codeparrot_training - Step 27383: {'lr': 0.0004645806965192353, 'samples': 14020608, 'steps': 27383, 'loss/train': 2.057730197906494}
-03/04/2022 21:38:18 - INFO - codeparrot_training - Step 27384: {'lr': 0.000464577973526665, 'samples': 14021120, 'steps': 27384, 'loss/train': 1.7803815603256226}
-03/04/2022 21:38:18 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/04/2022 21:38:24 - INFO - codeparrot_training - Step 27385: {'lr': 0.00046457525043740926, 'samples': 14021632, 'steps': 27385, 'loss/train': 2.674163579940796}
-03/04/2022 21:38:27 - INFO - codeparrot_training - Step 27386: {'lr': 0.0004645725272514693, 'samples': 14022144, 'steps': 27386, 'loss/train': 1.463183045387268}
-03/04/2022 21:38:27 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 21:38:32 - INFO - codeparrot_training - Step 27387: {'lr': 0.0004645698039688461, 'samples': 14022656, 'steps': 27387, 'loss/train': 2.2811574935913086}
-03/04/2022 21:38:35 - INFO - codeparrot_training - Step 27388: {'lr': 0.00046456708058954116, 'samples': 14023168, 'steps': 27388, 'loss/train': 2.0511343479156494}
-03/04/2022 21:38:36 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/04/2022 21:38:40 - INFO - codeparrot_training - Step 27389: {'lr': 0.0004645643571135556, 'samples': 14023680, 'steps': 27389, 'loss/train': 1.2097456455230713}
-03/04/2022 21:38:44 - INFO - codeparrot_training - Step 27390: {'lr': 0.00046456163354089065, 'samples': 14024192, 'steps': 27390, 'loss/train': 1.3479502201080322}
-03/04/2022 21:38:44 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/04/2022 21:38:49 - INFO - codeparrot_training - Step 27391: {'lr': 0.00046455890987154747, 'samples': 14024704, 'steps': 27391, 'loss/train': 1.5953457355499268}
-03/04/2022 21:38:52 - INFO - codeparrot_training - Step 27392: {'lr': 0.0004645561861055274, 'samples': 14025216, 'steps': 27392, 'loss/train': 1.46274733543396}
-03/04/2022 21:38:53 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/04/2022 21:38:57 - INFO - codeparrot_training - Step 27393: {'lr': 0.00046455346224283167, 'samples': 14025728, 'steps': 27393, 'loss/train': 1.3379813432693481}
-03/04/2022 21:39:00 - INFO - codeparrot_training - Step 27394: {'lr': 0.00046455073828346137, 'samples': 14026240, 'steps': 27394, 'loss/train': 1.7677438259124756}
-03/04/2022 21:39:01 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/04/2022 21:39:06 - INFO - codeparrot_training - Step 27395: {'lr': 0.0004645480142274179, 'samples': 14026752, 'steps': 27395, 'loss/train': 0.8622795939445496}
-03/04/2022 21:39:09 - INFO - codeparrot_training - Step 27396: {'lr': 0.0004645452900747024, 'samples': 14027264, 'steps': 27396, 'loss/train': 1.7063603401184082}
-03/04/2022 21:39:10 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/04/2022 21:39:14 - INFO - codeparrot_training - Step 27397: {'lr': 0.00046454256582531604, 'samples': 14027776, 'steps': 27397, 'loss/train': 1.7681043148040771}
-03/04/2022 21:39:17 - INFO - codeparrot_training - Step 27398: {'lr': 0.0004645398414792602, 'samples': 14028288, 'steps': 27398, 'loss/train': 1.0030204057693481}
-03/04/2022 21:39:18 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 21:39:23 - INFO - codeparrot_training - Step 27399: {'lr': 0.000464537117036536, 'samples': 14028800, 'steps': 27399, 'loss/train': 1.2784544229507446}
-03/04/2022 21:39:26 - INFO - codeparrot_training - Step 27400: {'lr': 0.00046453439249714466, 'samples': 14029312, 'steps': 27400, 'loss/train': 1.9824109077453613}
-03/04/2022 21:39:26 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 21:39:31 - INFO - codeparrot_training - Step 27401: {'lr': 0.00046453166786108736, 'samples': 14029824, 'steps': 27401, 'loss/train': 2.03820538520813}
-03/04/2022 21:39:34 - INFO - codeparrot_training - Step 27402: {'lr': 0.00046452894312836547, 'samples': 14030336, 'steps': 27402, 'loss/train': 2.2694809436798096}
-03/04/2022 21:39:36 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 21:39:40 - INFO - codeparrot_training - Step 27403: {'lr': 0.0004645262182989802, 'samples': 14030848, 'steps': 27403, 'loss/train': 2.384436845779419}
-03/04/2022 21:39:43 - INFO - codeparrot_training - Step 27404: {'lr': 0.0004645234933729327, 'samples': 14031360, 'steps': 27404, 'loss/train': 1.7128311395645142}
-03/04/2022 21:39:44 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 21:39:48 - INFO - codeparrot_training - Step 27405: {'lr': 0.00046452076835022416, 'samples': 14031872, 'steps': 27405, 'loss/train': 1.5785454511642456}
-03/04/2022 21:39:51 - INFO - codeparrot_training - Step 27406: {'lr': 0.0004645180432308559, 'samples': 14032384, 'steps': 27406, 'loss/train': 1.8436830043792725}
-03/04/2022 21:39:52 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 21:39:57 - INFO - codeparrot_training - Step 27407: {'lr': 0.00046451531801482913, 'samples': 14032896, 'steps': 27407, 'loss/train': 2.10463809967041}
-03/04/2022 21:40:00 - INFO - codeparrot_training - Step 27408: {'lr': 0.00046451259270214505, 'samples': 14033408, 'steps': 27408, 'loss/train': 2.0184102058410645}
-03/04/2022 21:40:01 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 21:40:05 - INFO - codeparrot_training - Step 27409: {'lr': 0.00046450986729280495, 'samples': 14033920, 'steps': 27409, 'loss/train': 2.0944406986236572}
-03/04/2022 21:40:08 - INFO - codeparrot_training - Step 27410: {'lr': 0.00046450714178680996, 'samples': 14034432, 'steps': 27410, 'loss/train': 1.5075424909591675}
-03/04/2022 21:40:10 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 21:40:13 - INFO - codeparrot_training - Step 27411: {'lr': 0.0004645044161841614, 'samples': 14034944, 'steps': 27411, 'loss/train': 2.4431211948394775}
-03/04/2022 21:40:17 - INFO - codeparrot_training - Step 27412: {'lr': 0.00046450169048486045, 'samples': 14035456, 'steps': 27412, 'loss/train': 1.0280897617340088}
-03/04/2022 21:40:18 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/04/2022 21:40:22 - INFO - codeparrot_training - Step 27413: {'lr': 0.0004644989646889084, 'samples': 14035968, 'steps': 27413, 'loss/train': 2.125209093093872}
-03/04/2022 21:40:25 - INFO - codeparrot_training - Step 27414: {'lr': 0.0004644962387963063, 'samples': 14036480, 'steps': 27414, 'loss/train': 1.9043469429016113}
-03/04/2022 21:40:26 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/04/2022 21:40:30 - INFO - codeparrot_training - Step 27415: {'lr': 0.0004644935128070556, 'samples': 14036992, 'steps': 27415, 'loss/train': 1.982437252998352}
-03/04/2022 21:40:33 - INFO - codeparrot_training - Step 27416: {'lr': 0.0004644907867211574, 'samples': 14037504, 'steps': 27416, 'loss/train': 2.3460440635681152}
-03/04/2022 21:40:35 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/04/2022 21:40:39 - INFO - codeparrot_training - Step 27417: {'lr': 0.000464488060538613, 'samples': 14038016, 'steps': 27417, 'loss/train': 1.9599082469940186}
-03/04/2022 21:40:42 - INFO - codeparrot_training - Step 27418: {'lr': 0.0004644853342594235, 'samples': 14038528, 'steps': 27418, 'loss/train': 1.8385353088378906}
-03/04/2022 21:40:43 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 21:40:47 - INFO - codeparrot_training - Step 27419: {'lr': 0.0004644826078835903, 'samples': 14039040, 'steps': 27419, 'loss/train': 1.6550085544586182}
-03/04/2022 21:40:50 - INFO - codeparrot_training - Step 27420: {'lr': 0.00046447988141111457, 'samples': 14039552, 'steps': 27420, 'loss/train': 1.5975160598754883}
-03/04/2022 21:40:52 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/04/2022 21:40:56 - INFO - codeparrot_training - Step 27421: {'lr': 0.0004644771548419975, 'samples': 14040064, 'steps': 27421, 'loss/train': 2.035372734069824}
-03/04/2022 21:40:59 - INFO - codeparrot_training - Step 27422: {'lr': 0.0004644744281762403, 'samples': 14040576, 'steps': 27422, 'loss/train': 1.3625017404556274}
-03/04/2022 21:41:01 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/04/2022 21:41:04 - INFO - codeparrot_training - Step 27423: {'lr': 0.0004644717014138442, 'samples': 14041088, 'steps': 27423, 'loss/train': 1.6563042402267456}
-03/04/2022 21:41:07 - INFO - codeparrot_training - Step 27424: {'lr': 0.0004644689745548105, 'samples': 14041600, 'steps': 27424, 'loss/train': 1.3288251161575317}
-03/04/2022 21:41:09 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/04/2022 21:41:13 - INFO - codeparrot_training - Step 27425: {'lr': 0.00046446624759914043, 'samples': 14042112, 'steps': 27425, 'loss/train': 1.6382728815078735}
-03/04/2022 21:41:16 - INFO - codeparrot_training - Step 27426: {'lr': 0.0004644635205468351, 'samples': 14042624, 'steps': 27426, 'loss/train': 1.8266234397888184}
-03/04/2022 21:41:17 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 21:41:21 - INFO - codeparrot_training - Step 27427: {'lr': 0.00046446079339789587, 'samples': 14043136, 'steps': 27427, 'loss/train': 2.0857698917388916}
-03/04/2022 21:41:24 - INFO - codeparrot_training - Step 27428: {'lr': 0.0004644580661523239, 'samples': 14043648, 'steps': 27428, 'loss/train': 1.900187611579895}
-03/04/2022 21:41:26 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/04/2022 21:41:30 - INFO - codeparrot_training - Step 27429: {'lr': 0.00046445533881012043, 'samples': 14044160, 'steps': 27429, 'loss/train': 1.4356448650360107}
-03/04/2022 21:41:33 - INFO - codeparrot_training - Step 27430: {'lr': 0.0004644526113712867, 'samples': 14044672, 'steps': 27430, 'loss/train': 1.57810640335083}
-03/04/2022 21:41:34 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/04/2022 21:41:38 - INFO - codeparrot_training - Step 27431: {'lr': 0.00046444988383582394, 'samples': 14045184, 'steps': 27431, 'loss/train': 0.42720088362693787}
-03/04/2022 21:41:41 - INFO - codeparrot_training - Step 27432: {'lr': 0.0004644471562037333, 'samples': 14045696, 'steps': 27432, 'loss/train': 1.293715238571167}
-03/04/2022 21:41:42 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 21:41:46 - INFO - codeparrot_training - Step 27433: {'lr': 0.0004644444284750162, 'samples': 14046208, 'steps': 27433, 'loss/train': 2.1766974925994873}
-03/04/2022 21:41:50 - INFO - codeparrot_training - Step 27434: {'lr': 0.0004644417006496737, 'samples': 14046720, 'steps': 27434, 'loss/train': 2.537862539291382}
-03/04/2022 21:41:51 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/04/2022 21:41:55 - INFO - codeparrot_training - Step 27435: {'lr': 0.0004644389727277071, 'samples': 14047232, 'steps': 27435, 'loss/train': 0.5788947343826294}
-03/04/2022 21:41:58 - INFO - codeparrot_training - Step 27436: {'lr': 0.00046443624470911754, 'samples': 14047744, 'steps': 27436, 'loss/train': 1.9883496761322021}
-03/04/2022 21:41:59 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/04/2022 21:42:03 - INFO - codeparrot_training - Step 27437: {'lr': 0.00046443351659390637, 'samples': 14048256, 'steps': 27437, 'loss/train': 1.3385837078094482}
-03/04/2022 21:42:06 - INFO - codeparrot_training - Step 27438: {'lr': 0.00046443078838207474, 'samples': 14048768, 'steps': 27438, 'loss/train': 2.25730037689209}
-03/04/2022 21:42:07 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/04/2022 21:42:12 - INFO - codeparrot_training - Step 27439: {'lr': 0.00046442806007362394, 'samples': 14049280, 'steps': 27439, 'loss/train': 1.4275152683258057}
-03/04/2022 21:42:15 - INFO - codeparrot_training - Step 27440: {'lr': 0.00046442533166855517, 'samples': 14049792, 'steps': 27440, 'loss/train': 1.123038649559021}
-03/04/2022 21:42:16 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/04/2022 21:42:20 - INFO - codeparrot_training - Step 27441: {'lr': 0.00046442260316686957, 'samples': 14050304, 'steps': 27441, 'loss/train': 1.8440301418304443}
-03/04/2022 21:42:23 - INFO - codeparrot_training - Step 27442: {'lr': 0.0004644198745685685, 'samples': 14050816, 'steps': 27442, 'loss/train': 1.7701092958450317}
-03/04/2022 21:42:24 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/04/2022 21:42:29 - INFO - codeparrot_training - Step 27443: {'lr': 0.00046441714587365317, 'samples': 14051328, 'steps': 27443, 'loss/train': 1.8733227252960205}
-03/04/2022 21:42:32 - INFO - codeparrot_training - Step 27444: {'lr': 0.00046441441708212477, 'samples': 14051840, 'steps': 27444, 'loss/train': 1.5340734720230103}
-03/04/2022 21:42:33 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/04/2022 21:42:37 - INFO - codeparrot_training - Step 27445: {'lr': 0.00046441168819398457, 'samples': 14052352, 'steps': 27445, 'loss/train': 1.6654702425003052}
-03/04/2022 21:42:40 - INFO - codeparrot_training - Step 27446: {'lr': 0.0004644089592092338, 'samples': 14052864, 'steps': 27446, 'loss/train': 2.098836898803711}
-03/04/2022 21:42:41 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/04/2022 21:42:46 - INFO - codeparrot_training - Step 27447: {'lr': 0.0004644062301278735, 'samples': 14053376, 'steps': 27447, 'loss/train': 1.8823657035827637}
-03/04/2022 21:42:49 - INFO - codeparrot_training - Step 27448: {'lr': 0.0004644035009499052, 'samples': 14053888, 'steps': 27448, 'loss/train': 0.9201361536979675}
-03/04/2022 21:42:51 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 21:42:54 - INFO - codeparrot_training - Step 27449: {'lr': 0.0004644007716753299, 'samples': 14054400, 'steps': 27449, 'loss/train': 1.9657623767852783}
-03/04/2022 21:42:57 - INFO - codeparrot_training - Step 27450: {'lr': 0.00046439804230414904, 'samples': 14054912, 'steps': 27450, 'loss/train': 6.4773478507995605}
-03/04/2022 21:43:00 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 21:43:02 - INFO - codeparrot_training - Step 27451: {'lr': 0.0004643953128363637, 'samples': 14055424, 'steps': 27451, 'loss/train': 1.7805688381195068}
-03/04/2022 21:43:06 - INFO - codeparrot_training - Step 27452: {'lr': 0.0004643925832719751, 'samples': 14055936, 'steps': 27452, 'loss/train': 1.4561102390289307}
-03/04/2022 21:43:08 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/04/2022 21:43:11 - INFO - codeparrot_training - Step 27453: {'lr': 0.0004643898536109845, 'samples': 14056448, 'steps': 27453, 'loss/train': 0.985674262046814}
-03/04/2022 21:43:14 - INFO - codeparrot_training - Step 27454: {'lr': 0.0004643871238533931, 'samples': 14056960, 'steps': 27454, 'loss/train': 1.9698567390441895}
-03/04/2022 21:43:18 - INFO - codeparrot_training - Step 27455: {'lr': 0.0004643843939992022, 'samples': 14057472, 'steps': 27455, 'loss/train': 0.48464033007621765}
-03/04/2022 21:43:18 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 21:43:23 - INFO - codeparrot_training - Step 27456: {'lr': 0.0004643816640484131, 'samples': 14057984, 'steps': 27456, 'loss/train': 2.1968865394592285}
-03/04/2022 21:43:26 - INFO - codeparrot_training - Step 27457: {'lr': 0.0004643789340010268, 'samples': 14058496, 'steps': 27457, 'loss/train': 1.6791248321533203}
-03/04/2022 21:43:26 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/04/2022 21:43:31 - INFO - codeparrot_training - Step 27458: {'lr': 0.00046437620385704476, 'samples': 14059008, 'steps': 27458, 'loss/train': 1.8809698820114136}
-03/04/2022 21:43:35 - INFO - codeparrot_training - Step 27459: {'lr': 0.0004643734736164681, 'samples': 14059520, 'steps': 27459, 'loss/train': 2.0172295570373535}
-03/04/2022 21:43:35 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 21:43:40 - INFO - codeparrot_training - Step 27460: {'lr': 0.00046437074327929795, 'samples': 14060032, 'steps': 27460, 'loss/train': 2.199040651321411}
-03/04/2022 21:43:43 - INFO - codeparrot_training - Step 27461: {'lr': 0.0004643680128455358, 'samples': 14060544, 'steps': 27461, 'loss/train': 2.2491455078125}
-03/04/2022 21:43:43 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 21:43:49 - INFO - codeparrot_training - Step 27462: {'lr': 0.00046436528231518263, 'samples': 14061056, 'steps': 27462, 'loss/train': 2.135902166366577}
-03/04/2022 21:43:52 - INFO - codeparrot_training - Step 27463: {'lr': 0.0004643625516882398, 'samples': 14061568, 'steps': 27463, 'loss/train': 1.595616340637207}
-03/04/2022 21:43:55 - INFO - codeparrot_training - Step 27464: {'lr': 0.0004643598209647085, 'samples': 14062080, 'steps': 27464, 'loss/train': 1.910935878753662}
-03/04/2022 21:43:55 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/04/2022 21:44:01 - INFO - codeparrot_training - Step 27465: {'lr': 0.00046435709014459, 'samples': 14062592, 'steps': 27465, 'loss/train': 0.5192428827285767}
-03/04/2022 21:44:04 - INFO - codeparrot_training - Step 27466: {'lr': 0.0004643543592278855, 'samples': 14063104, 'steps': 27466, 'loss/train': 1.8331623077392578}
-03/04/2022 21:44:04 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/04/2022 21:44:09 - INFO - codeparrot_training - Step 27467: {'lr': 0.0004643516282145962, 'samples': 14063616, 'steps': 27467, 'loss/train': 2.0985190868377686}
-03/04/2022 21:44:12 - INFO - codeparrot_training - Step 27468: {'lr': 0.0004643488971047234, 'samples': 14064128, 'steps': 27468, 'loss/train': 1.8761496543884277}
-03/04/2022 21:44:13 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/04/2022 21:44:17 - INFO - codeparrot_training - Step 27469: {'lr': 0.0004643461658982683, 'samples': 14064640, 'steps': 27469, 'loss/train': 1.3340861797332764}
-03/04/2022 21:44:21 - INFO - codeparrot_training - Step 27470: {'lr': 0.00046434343459523207, 'samples': 14065152, 'steps': 27470, 'loss/train': 2.089254140853882}
-03/04/2022 21:44:21 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 21:44:26 - INFO - codeparrot_training - Step 27471: {'lr': 0.00046434070319561604, 'samples': 14065664, 'steps': 27471, 'loss/train': 1.7469450235366821}
-03/04/2022 21:44:29 - INFO - codeparrot_training - Step 27472: {'lr': 0.0004643379716994214, 'samples': 14066176, 'steps': 27472, 'loss/train': 1.3748592138290405}
-03/04/2022 21:44:29 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 21:44:34 - INFO - codeparrot_training - Step 27473: {'lr': 0.0004643352401066494, 'samples': 14066688, 'steps': 27473, 'loss/train': 0.9277780055999756}
-03/04/2022 21:44:38 - INFO - codeparrot_training - Step 27474: {'lr': 0.00046433250841730123, 'samples': 14067200, 'steps': 27474, 'loss/train': 0.9676547646522522}
-03/04/2022 21:44:38 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/04/2022 21:44:43 - INFO - codeparrot_training - Step 27475: {'lr': 0.0004643297766313781, 'samples': 14067712, 'steps': 27475, 'loss/train': 1.0953902006149292}
-03/04/2022 21:44:46 - INFO - codeparrot_training - Step 27476: {'lr': 0.0004643270447488813, 'samples': 14068224, 'steps': 27476, 'loss/train': 1.6601144075393677}
-03/04/2022 21:44:46 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 21:44:51 - INFO - codeparrot_training - Step 27477: {'lr': 0.000464324312769812, 'samples': 14068736, 'steps': 27477, 'loss/train': 1.5576833486557007}
-03/04/2022 21:44:54 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/04/2022 21:44:57 - INFO - codeparrot_training - Step 27478: {'lr': 0.0004643215806941716, 'samples': 14069248, 'steps': 27478, 'loss/train': 1.5923259258270264}
-03/04/2022 21:45:00 - INFO - codeparrot_training - Step 27479: {'lr': 0.00046431884852196105, 'samples': 14069760, 'steps': 27479, 'loss/train': 1.9775041341781616}
-03/04/2022 21:45:02 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/04/2022 21:45:05 - INFO - codeparrot_training - Step 27480: {'lr': 0.0004643161162531818, 'samples': 14070272, 'steps': 27480, 'loss/train': 1.2686140537261963}
-03/04/2022 21:45:08 - INFO - codeparrot_training - Step 27481: {'lr': 0.00046431338388783504, 'samples': 14070784, 'steps': 27481, 'loss/train': 1.7342884540557861}
-03/04/2022 21:45:11 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/04/2022 21:45:13 - INFO - codeparrot_training - Step 27482: {'lr': 0.000464310651425922, 'samples': 14071296, 'steps': 27482, 'loss/train': 1.9429219961166382}
-03/04/2022 21:45:17 - INFO - codeparrot_training - Step 27483: {'lr': 0.00046430791886744384, 'samples': 14071808, 'steps': 27483, 'loss/train': 1.7062933444976807}
-03/04/2022 21:45:20 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/04/2022 21:45:22 - INFO - codeparrot_training - Step 27484: {'lr': 0.0004643051862124018, 'samples': 14072320, 'steps': 27484, 'loss/train': 1.6051735877990723}
-03/04/2022 21:45:25 - INFO - codeparrot_training - Step 27485: {'lr': 0.0004643024534607973, 'samples': 14072832, 'steps': 27485, 'loss/train': 1.7099019289016724}
-03/04/2022 21:45:28 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 21:45:30 - INFO - codeparrot_training - Step 27486: {'lr': 0.00046429972061263125, 'samples': 14073344, 'steps': 27486, 'loss/train': 1.3505125045776367}
-03/04/2022 21:45:34 - INFO - codeparrot_training - Step 27487: {'lr': 0.0004642969876679051, 'samples': 14073856, 'steps': 27487, 'loss/train': 1.882491111755371}
-03/04/2022 21:45:36 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/04/2022 21:45:39 - INFO - codeparrot_training - Step 27488: {'lr': 0.00046429425462662, 'samples': 14074368, 'steps': 27488, 'loss/train': 1.9467310905456543}
-03/04/2022 21:45:42 - INFO - codeparrot_training - Step 27489: {'lr': 0.00046429152148877727, 'samples': 14074880, 'steps': 27489, 'loss/train': 1.5897464752197266}
-03/04/2022 21:45:44 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/04/2022 21:45:47 - INFO - codeparrot_training - Step 27490: {'lr': 0.00046428878825437815, 'samples': 14075392, 'steps': 27490, 'loss/train': 2.0209341049194336}
-03/04/2022 21:45:51 - INFO - codeparrot_training - Step 27491: {'lr': 0.00046428605492342367, 'samples': 14075904, 'steps': 27491, 'loss/train': 6.542036056518555}
-03/04/2022 21:45:54 - INFO - codeparrot_training - Step 27492: {'lr': 0.00046428332149591535, 'samples': 14076416, 'steps': 27492, 'loss/train': 1.5625042915344238}
-03/04/2022 21:45:54 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/04/2022 21:45:59 - INFO - codeparrot_training - Step 27493: {'lr': 0.00046428058797185417, 'samples': 14076928, 'steps': 27493, 'loss/train': 1.4840084314346313}
-03/04/2022 21:46:02 - INFO - codeparrot_training - Step 27494: {'lr': 0.00046427785435124147, 'samples': 14077440, 'steps': 27494, 'loss/train': 0.6383106112480164}
-03/04/2022 21:46:04 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/04/2022 21:46:08 - INFO - codeparrot_training - Step 27495: {'lr': 0.0004642751206340785, 'samples': 14077952, 'steps': 27495, 'loss/train': 1.5301226377487183}
-03/04/2022 21:46:11 - INFO - codeparrot_training - Step 27496: {'lr': 0.00046427238682036643, 'samples': 14078464, 'steps': 27496, 'loss/train': 1.3929015398025513}
-03/04/2022 21:46:12 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 21:46:16 - INFO - codeparrot_training - Step 27497: {'lr': 0.0004642696529101066, 'samples': 14078976, 'steps': 27497, 'loss/train': 2.1790637969970703}
-03/04/2022 21:46:20 - INFO - codeparrot_training - Step 27498: {'lr': 0.0004642669189033001, 'samples': 14079488, 'steps': 27498, 'loss/train': 1.9886882305145264}
-03/04/2022 21:46:21 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/04/2022 21:46:25 - INFO - codeparrot_training - Step 27499: {'lr': 0.0004642641847999483, 'samples': 14080000, 'steps': 27499, 'loss/train': 1.928977608680725}
-03/04/2022 21:46:28 - INFO - codeparrot_training - Step 27500: {'lr': 0.0004642614506000523, 'samples': 14080512, 'steps': 27500, 'loss/train': 1.7993202209472656}
-03/04/2022 21:46:30 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/04/2022 21:46:33 - INFO - codeparrot_training - Step 27501: {'lr': 0.00046425871630361343, 'samples': 14081024, 'steps': 27501, 'loss/train': 1.6733847856521606}
-03/04/2022 21:46:36 - INFO - codeparrot_training - Step 27502: {'lr': 0.0004642559819106329, 'samples': 14081536, 'steps': 27502, 'loss/train': 2.332489252090454}
-03/04/2022 21:46:38 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 21:46:42 - INFO - codeparrot_training - Step 27503: {'lr': 0.0004642532474211119, 'samples': 14082048, 'steps': 27503, 'loss/train': 2.3540337085723877}
-03/04/2022 21:46:45 - INFO - codeparrot_training - Step 27504: {'lr': 0.0004642505128350517, 'samples': 14082560, 'steps': 27504, 'loss/train': 1.924314022064209}
-03/04/2022 21:46:47 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/04/2022 21:46:50 - INFO - codeparrot_training - Step 27505: {'lr': 0.00046424777815245354, 'samples': 14083072, 'steps': 27505, 'loss/train': 0.6645641922950745}
-03/04/2022 21:46:53 - INFO - codeparrot_training - Step 27506: {'lr': 0.0004642450433733186, 'samples': 14083584, 'steps': 27506, 'loss/train': 1.7985507249832153}
-03/04/2022 21:46:55 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 21:46:58 - INFO - codeparrot_training - Step 27507: {'lr': 0.0004642423084976482, 'samples': 14084096, 'steps': 27507, 'loss/train': 2.5674941539764404}
-03/04/2022 21:47:02 - INFO - codeparrot_training - Step 27508: {'lr': 0.0004642395735254435, 'samples': 14084608, 'steps': 27508, 'loss/train': 0.8497194647789001}
-03/04/2022 21:47:04 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/04/2022 21:47:07 - INFO - codeparrot_training - Step 27509: {'lr': 0.0004642368384567058, 'samples': 14085120, 'steps': 27509, 'loss/train': 1.680609107017517}
-03/04/2022 21:47:10 - INFO - codeparrot_training - Step 27510: {'lr': 0.0004642341032914362, 'samples': 14085632, 'steps': 27510, 'loss/train': 2.2475357055664062}
-03/04/2022 21:47:12 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/04/2022 21:47:15 - INFO - codeparrot_training - Step 27511: {'lr': 0.00046423136802963607, 'samples': 14086144, 'steps': 27511, 'loss/train': 1.122145652770996}
-03/04/2022 21:47:19 - INFO - codeparrot_training - Step 27512: {'lr': 0.0004642286326713065, 'samples': 14086656, 'steps': 27512, 'loss/train': 1.8663039207458496}
-03/04/2022 21:47:21 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/04/2022 21:47:24 - INFO - codeparrot_training - Step 27513: {'lr': 0.000464225897216449, 'samples': 14087168, 'steps': 27513, 'loss/train': 1.2194300889968872}
-03/04/2022 21:47:27 - INFO - codeparrot_training - Step 27514: {'lr': 0.0004642231616650645, 'samples': 14087680, 'steps': 27514, 'loss/train': 1.1292306184768677}
-03/04/2022 21:47:29 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 21:47:32 - INFO - codeparrot_training - Step 27515: {'lr': 0.00046422042601715433, 'samples': 14088192, 'steps': 27515, 'loss/train': 2.3064815998077393}
-03/04/2022 21:47:35 - INFO - codeparrot_training - Step 27516: {'lr': 0.00046421769027271974, 'samples': 14088704, 'steps': 27516, 'loss/train': 1.3717312812805176}
-03/04/2022 21:47:37 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/04/2022 21:47:41 - INFO - codeparrot_training - Step 27517: {'lr': 0.00046421495443176204, 'samples': 14089216, 'steps': 27517, 'loss/train': 1.7045902013778687}
-03/04/2022 21:47:44 - INFO - codeparrot_training - Step 27518: {'lr': 0.0004642122184942824, 'samples': 14089728, 'steps': 27518, 'loss/train': 1.7514593601226807}
-03/04/2022 21:47:45 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/04/2022 21:47:50 - INFO - codeparrot_training - Step 27519: {'lr': 0.00046420948246028194, 'samples': 14090240, 'steps': 27519, 'loss/train': 2.223639726638794}
-03/04/2022 21:47:53 - INFO - codeparrot_training - Step 27520: {'lr': 0.000464206746329762, 'samples': 14090752, 'steps': 27520, 'loss/train': 2.083322763442993}
-03/04/2022 21:47:56 - INFO - codeparrot_training - Step 27521: {'lr': 0.00046420401010272385, 'samples': 14091264, 'steps': 27521, 'loss/train': 1.2613078355789185}
-03/04/2022 21:47:57 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/04/2022 21:48:01 - INFO - codeparrot_training - Step 27522: {'lr': 0.00046420127377916863, 'samples': 14091776, 'steps': 27522, 'loss/train': 1.9479728937149048}
-03/04/2022 21:48:04 - INFO - codeparrot_training - Step 27523: {'lr': 0.0004641985373590977, 'samples': 14092288, 'steps': 27523, 'loss/train': 1.9705098867416382}
-03/04/2022 21:48:05 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 21:48:10 - INFO - codeparrot_training - Step 27524: {'lr': 0.00046419580084251224, 'samples': 14092800, 'steps': 27524, 'loss/train': 2.94038462638855}
-03/04/2022 21:48:13 - INFO - codeparrot_training - Step 27525: {'lr': 0.0004641930642294133, 'samples': 14093312, 'steps': 27525, 'loss/train': 1.4523680210113525}
-03/04/2022 21:48:14 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/04/2022 21:48:18 - INFO - codeparrot_training - Step 27526: {'lr': 0.0004641903275198024, 'samples': 14093824, 'steps': 27526, 'loss/train': 1.8401007652282715}
-03/04/2022 21:48:21 - INFO - codeparrot_training - Step 27527: {'lr': 0.0004641875907136806, 'samples': 14094336, 'steps': 27527, 'loss/train': 1.802200198173523}
-03/04/2022 21:48:23 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/04/2022 21:48:27 - INFO - codeparrot_training - Step 27528: {'lr': 0.0004641848538110492, 'samples': 14094848, 'steps': 27528, 'loss/train': 1.7315595149993896}
-03/04/2022 21:48:30 - INFO - codeparrot_training - Step 27529: {'lr': 0.00046418211681190937, 'samples': 14095360, 'steps': 27529, 'loss/train': 2.416125535964966}
-03/04/2022 21:48:34 - INFO - codeparrot_training - Step 27530: {'lr': 0.00046417937971626245, 'samples': 14095872, 'steps': 27530, 'loss/train': 1.5735355615615845}
-03/04/2022 21:48:34 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 21:48:39 - INFO - codeparrot_training - Step 27531: {'lr': 0.0004641766425241095, 'samples': 14096384, 'steps': 27531, 'loss/train': 2.508897304534912}
-03/04/2022 21:48:42 - INFO - codeparrot_training - Step 27532: {'lr': 0.000464173905235452, 'samples': 14096896, 'steps': 27532, 'loss/train': 1.7210041284561157}
-03/04/2022 21:48:42 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/04/2022 21:48:47 - INFO - codeparrot_training - Step 27533: {'lr': 0.0004641711678502909, 'samples': 14097408, 'steps': 27533, 'loss/train': 0.20753736793994904}
-03/04/2022 21:48:50 - INFO - codeparrot_training - Step 27534: {'lr': 0.00046416843036862766, 'samples': 14097920, 'steps': 27534, 'loss/train': 1.9154161214828491}
-03/04/2022 21:48:51 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 21:48:56 - INFO - codeparrot_training - Step 27535: {'lr': 0.0004641656927904634, 'samples': 14098432, 'steps': 27535, 'loss/train': 1.7031707763671875}
-03/04/2022 21:48:59 - INFO - codeparrot_training - Step 27536: {'lr': 0.00046416295511579944, 'samples': 14098944, 'steps': 27536, 'loss/train': 0.9756758809089661}
-03/04/2022 21:48:59 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/04/2022 21:49:04 - INFO - codeparrot_training - Step 27537: {'lr': 0.0004641602173446369, 'samples': 14099456, 'steps': 27537, 'loss/train': 0.7165545225143433}
-03/04/2022 21:49:07 - INFO - codeparrot_training - Step 27538: {'lr': 0.00046415747947697704, 'samples': 14099968, 'steps': 27538, 'loss/train': 2.6045031547546387}
-03/04/2022 21:49:08 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/04/2022 21:49:13 - INFO - codeparrot_training - Step 27539: {'lr': 0.00046415474151282124, 'samples': 14100480, 'steps': 27539, 'loss/train': 1.4550666809082031}
-03/04/2022 21:49:16 - INFO - codeparrot_training - Step 27540: {'lr': 0.0004641520034521705, 'samples': 14100992, 'steps': 27540, 'loss/train': 2.0749640464782715}
-03/04/2022 21:49:17 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/04/2022 21:49:21 - INFO - codeparrot_training - Step 27541: {'lr': 0.0004641492652950262, 'samples': 14101504, 'steps': 27541, 'loss/train': 1.7656759023666382}
-03/04/2022 21:49:24 - INFO - codeparrot_training - Step 27542: {'lr': 0.0004641465270413896, 'samples': 14102016, 'steps': 27542, 'loss/train': 1.656904935836792}
-03/04/2022 21:49:25 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 21:49:30 - INFO - codeparrot_training - Step 27543: {'lr': 0.00046414378869126185, 'samples': 14102528, 'steps': 27543, 'loss/train': 1.8351272344589233}
-03/04/2022 21:49:33 - INFO - codeparrot_training - Step 27544: {'lr': 0.0004641410502446442, 'samples': 14103040, 'steps': 27544, 'loss/train': 2.211921453475952}
-03/04/2022 21:49:34 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/04/2022 21:49:38 - INFO - codeparrot_training - Step 27545: {'lr': 0.00046413831170153785, 'samples': 14103552, 'steps': 27545, 'loss/train': 2.222635269165039}
-03/04/2022 21:49:41 - INFO - codeparrot_training - Step 27546: {'lr': 0.0004641355730619442, 'samples': 14104064, 'steps': 27546, 'loss/train': 1.6965638399124146}
-03/04/2022 21:49:42 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/04/2022 21:49:46 - INFO - codeparrot_training - Step 27547: {'lr': 0.0004641328343258643, 'samples': 14104576, 'steps': 27547, 'loss/train': 1.911508560180664}
-03/04/2022 21:49:49 - INFO - codeparrot_training - Step 27548: {'lr': 0.00046413009549329946, 'samples': 14105088, 'steps': 27548, 'loss/train': 2.277571201324463}
-03/04/2022 21:49:51 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 21:49:55 - INFO - codeparrot_training - Step 27549: {'lr': 0.0004641273565642509, 'samples': 14105600, 'steps': 27549, 'loss/train': 1.6523603200912476}
-03/04/2022 21:49:58 - INFO - codeparrot_training - Step 27550: {'lr': 0.0004641246175387198, 'samples': 14106112, 'steps': 27550, 'loss/train': 1.9692319631576538}
-03/04/2022 21:49:59 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 21:50:03 - INFO - codeparrot_training - Step 27551: {'lr': 0.0004641218784167075, 'samples': 14106624, 'steps': 27551, 'loss/train': 0.770227313041687}
-03/04/2022 21:50:06 - INFO - codeparrot_training - Step 27552: {'lr': 0.0004641191391982152, 'samples': 14107136, 'steps': 27552, 'loss/train': 2.3484370708465576}
-03/04/2022 21:50:07 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/04/2022 21:50:12 - INFO - codeparrot_training - Step 27553: {'lr': 0.00046411639988324407, 'samples': 14107648, 'steps': 27553, 'loss/train': 1.7093877792358398}
-03/04/2022 21:50:15 - INFO - codeparrot_training - Step 27554: {'lr': 0.00046411366047179547, 'samples': 14108160, 'steps': 27554, 'loss/train': 2.1578946113586426}
-03/04/2022 21:50:16 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 21:50:20 - INFO - codeparrot_training - Step 27555: {'lr': 0.00046411092096387054, 'samples': 14108672, 'steps': 27555, 'loss/train': 1.9369224309921265}
-03/04/2022 21:50:23 - INFO - codeparrot_training - Step 27556: {'lr': 0.0004641081813594705, 'samples': 14109184, 'steps': 27556, 'loss/train': 1.0960320234298706}
-03/04/2022 21:50:24 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/04/2022 21:50:29 - INFO - codeparrot_training - Step 27557: {'lr': 0.0004641054416585966, 'samples': 14109696, 'steps': 27557, 'loss/train': 2.1412601470947266}
-03/04/2022 21:50:32 - INFO - codeparrot_training - Step 27558: {'lr': 0.00046410270186125014, 'samples': 14110208, 'steps': 27558, 'loss/train': 1.4084429740905762}
-03/04/2022 21:50:33 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/04/2022 21:50:37 - INFO - codeparrot_training - Step 27559: {'lr': 0.0004640999619674323, 'samples': 14110720, 'steps': 27559, 'loss/train': 1.7194292545318604}
-03/04/2022 21:50:41 - INFO - codeparrot_training - Step 27560: {'lr': 0.0004640972219771443, 'samples': 14111232, 'steps': 27560, 'loss/train': 3.113382339477539}
-03/04/2022 21:50:41 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/04/2022 21:50:46 - INFO - codeparrot_training - Step 27561: {'lr': 0.00046409448189038737, 'samples': 14111744, 'steps': 27561, 'loss/train': 2.201770305633545}
-03/04/2022 21:50:49 - INFO - codeparrot_training - Step 27562: {'lr': 0.00046409174170716284, 'samples': 14112256, 'steps': 27562, 'loss/train': 0.9841717481613159}
-03/04/2022 21:50:50 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 21:50:54 - INFO - codeparrot_training - Step 27563: {'lr': 0.0004640890014274718, 'samples': 14112768, 'steps': 27563, 'loss/train': 1.768831729888916}
-03/04/2022 21:50:57 - INFO - codeparrot_training - Step 27564: {'lr': 0.0004640862610513156, 'samples': 14113280, 'steps': 27564, 'loss/train': 1.58949613571167}
-03/04/2022 21:50:59 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/04/2022 21:51:03 - INFO - codeparrot_training - Step 27565: {'lr': 0.00046408352057869545, 'samples': 14113792, 'steps': 27565, 'loss/train': 1.4789090156555176}
-03/04/2022 21:51:06 - INFO - codeparrot_training - Step 27566: {'lr': 0.0004640807800096126, 'samples': 14114304, 'steps': 27566, 'loss/train': 2.222676992416382}
-03/04/2022 21:51:07 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/04/2022 21:51:11 - INFO - codeparrot_training - Step 27567: {'lr': 0.0004640780393440682, 'samples': 14114816, 'steps': 27567, 'loss/train': 2.033569574356079}
-03/04/2022 21:51:14 - INFO - codeparrot_training - Step 27568: {'lr': 0.0004640752985820635, 'samples': 14115328, 'steps': 27568, 'loss/train': 2.299964666366577}
-03/04/2022 21:51:16 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/04/2022 21:51:20 - INFO - codeparrot_training - Step 27569: {'lr': 0.0004640725577235998, 'samples': 14115840, 'steps': 27569, 'loss/train': 1.8933861255645752}
-03/04/2022 21:51:23 - INFO - codeparrot_training - Step 27570: {'lr': 0.00046406981676867836, 'samples': 14116352, 'steps': 27570, 'loss/train': 1.6625146865844727}
-03/04/2022 21:51:25 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/04/2022 21:51:28 - INFO - codeparrot_training - Step 27571: {'lr': 0.00046406707571730035, 'samples': 14116864, 'steps': 27571, 'loss/train': 1.603249430656433}
-03/04/2022 21:51:31 - INFO - codeparrot_training - Step 27572: {'lr': 0.000464064334569467, 'samples': 14117376, 'steps': 27572, 'loss/train': 1.9846317768096924}
-03/04/2022 21:51:33 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/04/2022 21:51:36 - INFO - codeparrot_training - Step 27573: {'lr': 0.00046406159332517956, 'samples': 14117888, 'steps': 27573, 'loss/train': 1.8401986360549927}
-03/04/2022 21:51:40 - INFO - codeparrot_training - Step 27574: {'lr': 0.00046405885198443926, 'samples': 14118400, 'steps': 27574, 'loss/train': 1.8662515878677368}
-03/04/2022 21:51:41 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/04/2022 21:51:45 - INFO - codeparrot_training - Step 27575: {'lr': 0.00046405611054724737, 'samples': 14118912, 'steps': 27575, 'loss/train': 1.8286628723144531}
-03/04/2022 21:51:48 - INFO - codeparrot_training - Step 27576: {'lr': 0.00046405336901360507, 'samples': 14119424, 'steps': 27576, 'loss/train': 1.0668145418167114}
-03/04/2022 21:51:50 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/04/2022 21:51:54 - INFO - codeparrot_training - Step 27577: {'lr': 0.00046405062738351366, 'samples': 14119936, 'steps': 27577, 'loss/train': 2.066446542739868}
-03/04/2022 21:51:57 - INFO - codeparrot_training - Step 27578: {'lr': 0.00046404788565697434, 'samples': 14120448, 'steps': 27578, 'loss/train': 1.9912432432174683}
-03/04/2022 21:51:58 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/04/2022 21:52:02 - INFO - codeparrot_training - Step 27579: {'lr': 0.00046404514383398835, 'samples': 14120960, 'steps': 27579, 'loss/train': 2.641558885574341}
-03/04/2022 21:52:05 - INFO - codeparrot_training - Step 27580: {'lr': 0.0004640424019145568, 'samples': 14121472, 'steps': 27580, 'loss/train': 2.41717529296875}
-03/04/2022 21:52:07 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/04/2022 21:52:10 - INFO - codeparrot_training - Step 27581: {'lr': 0.00046403965989868124, 'samples': 14121984, 'steps': 27581, 'loss/train': 2.020951986312866}
-03/04/2022 21:52:14 - INFO - codeparrot_training - Step 27582: {'lr': 0.0004640369177863626, 'samples': 14122496, 'steps': 27582, 'loss/train': 1.296420931816101}
-03/04/2022 21:52:15 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/04/2022 21:52:19 - INFO - codeparrot_training - Step 27583: {'lr': 0.00046403417557760226, 'samples': 14123008, 'steps': 27583, 'loss/train': 1.6932988166809082}
-03/04/2022 21:52:22 - INFO - codeparrot_training - Step 27584: {'lr': 0.00046403143327240136, 'samples': 14123520, 'steps': 27584, 'loss/train': 2.339085817337036}
-03/04/2022 21:52:24 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/04/2022 21:52:27 - INFO - codeparrot_training - Step 27585: {'lr': 0.00046402869087076127, 'samples': 14124032, 'steps': 27585, 'loss/train': 2.1542680263519287}
-03/04/2022 21:52:30 - INFO - codeparrot_training - Step 27586: {'lr': 0.00046402594837268314, 'samples': 14124544, 'steps': 27586, 'loss/train': 1.9707403182983398}
-03/04/2022 21:52:32 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/04/2022 21:52:36 - INFO - codeparrot_training - Step 27587: {'lr': 0.0004640232057781682, 'samples': 14125056, 'steps': 27587, 'loss/train': 1.5464863777160645}
-03/04/2022 21:52:39 - INFO - codeparrot_training - Step 27588: {'lr': 0.00046402046308721776, 'samples': 14125568, 'steps': 27588, 'loss/train': 1.7598837614059448}
-03/04/2022 21:52:41 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/04/2022 21:52:44 - INFO - codeparrot_training - Step 27589: {'lr': 0.0004640177202998329, 'samples': 14126080, 'steps': 27589, 'loss/train': 2.269519805908203}
-03/04/2022 21:52:47 - INFO - codeparrot_training - Step 27590: {'lr': 0.00046401497741601505, 'samples': 14126592, 'steps': 27590, 'loss/train': 3.437429904937744}
-03/04/2022 21:52:49 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/04/2022 21:52:53 - INFO - codeparrot_training - Step 27591: {'lr': 0.00046401223443576537, 'samples': 14127104, 'steps': 27591, 'loss/train': 1.6568045616149902}
-03/04/2022 21:52:56 - INFO - codeparrot_training - Step 27592: {'lr': 0.00046400949135908497, 'samples': 14127616, 'steps': 27592, 'loss/train': 1.5045348405838013}
-03/04/2022 21:52:58 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/04/2022 21:53:01 - INFO - codeparrot_training - Step 27593: {'lr': 0.0004640067481859753, 'samples': 14128128, 'steps': 27593, 'loss/train': 1.4222878217697144}
-03/04/2022 21:53:04 - INFO - codeparrot_training - Step 27594: {'lr': 0.00046400400491643744, 'samples': 14128640, 'steps': 27594, 'loss/train': 1.5131932497024536}
-03/04/2022 21:53:06 - INFO - codeparrot_training - Skipping example with length 1010 (seq_length=1024)
-03/04/2022 21:53:10 - INFO - codeparrot_training - Step 27595: {'lr': 0.00046400126155047265, 'samples': 14129152, 'steps': 27595, 'loss/train': 2.2484421730041504}
-03/04/2022 21:53:13 - INFO - codeparrot_training - Step 27596: {'lr': 0.0004639985180880822, 'samples': 14129664, 'steps': 27596, 'loss/train': 0.7109977006912231}
-03/04/2022 21:53:14 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/04/2022 21:53:18 - INFO - codeparrot_training - Step 27597: {'lr': 0.0004639957745292674, 'samples': 14130176, 'steps': 27597, 'loss/train': 1.857573390007019}
-03/04/2022 21:53:21 - INFO - codeparrot_training - Step 27598: {'lr': 0.00046399303087402935, 'samples': 14130688, 'steps': 27598, 'loss/train': 1.496458888053894}
-03/04/2022 21:53:23 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/04/2022 21:53:26 - INFO - codeparrot_training - Step 27599: {'lr': 0.00046399028712236935, 'samples': 14131200, 'steps': 27599, 'loss/train': 1.9203948974609375}
-03/04/2022 21:53:30 - INFO - codeparrot_training - Step 27600: {'lr': 0.0004639875432742886, 'samples': 14131712, 'steps': 27600, 'loss/train': 1.9752079248428345}
-03/04/2022 21:53:31 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/04/2022 21:53:35 - INFO - codeparrot_training - Step 27601: {'lr': 0.0004639847993297884, 'samples': 14132224, 'steps': 27601, 'loss/train': 2.3917438983917236}
-03/04/2022 21:53:38 - INFO - codeparrot_training - Step 27602: {'lr': 0.00046398205528886994, 'samples': 14132736, 'steps': 27602, 'loss/train': 1.6044554710388184}
-03/04/2022 21:53:40 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/04/2022 21:53:43 - INFO - codeparrot_training - Step 27603: {'lr': 0.00046397931115153444, 'samples': 14133248, 'steps': 27603, 'loss/train': 1.7703933715820312}
-03/04/2022 21:53:46 - INFO - codeparrot_training - Step 27604: {'lr': 0.0004639765669177833, 'samples': 14133760, 'steps': 27604, 'loss/train': 1.1748124361038208}
-03/04/2022 21:53:48 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/04/2022 21:53:52 - INFO - codeparrot_training - Step 27605: {'lr': 0.00046397382258761744, 'samples': 14134272, 'steps': 27605, 'loss/train': 2.083744764328003}
-03/04/2022 21:53:55 - INFO - codeparrot_training - Step 27606: {'lr': 0.0004639710781610384, 'samples': 14134784, 'steps': 27606, 'loss/train': 1.532667636871338}
-03/04/2022 21:53:56 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/04/2022 21:54:00 - INFO - codeparrot_training - Step 27607: {'lr': 0.00046396833363804724, 'samples': 14135296, 'steps': 27607, 'loss/train': 1.4918828010559082}
-03/04/2022 21:54:03 - INFO - codeparrot_training - Step 27608: {'lr': 0.00046396558901864527, 'samples': 14135808, 'steps': 27608, 'loss/train': 1.8344670534133911}
-03/04/2022 21:54:05 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 21:54:08 - INFO - codeparrot_training - Step 27609: {'lr': 0.0004639628443028337, 'samples': 14136320, 'steps': 27609, 'loss/train': 0.4375920295715332}
-03/04/2022 21:54:12 - INFO - codeparrot_training - Step 27610: {'lr': 0.0004639600994906138, 'samples': 14136832, 'steps': 27610, 'loss/train': 1.5562015771865845}
-03/04/2022 21:54:13 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/04/2022 21:54:17 - INFO - codeparrot_training - Step 27611: {'lr': 0.00046395735458198674, 'samples': 14137344, 'steps': 27611, 'loss/train': 1.7201288938522339}
-03/04/2022 21:54:20 - INFO - codeparrot_training - Step 27612: {'lr': 0.0004639546095769538, 'samples': 14137856, 'steps': 27612, 'loss/train': 6.799593925476074}
-03/04/2022 21:54:22 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 21:54:25 - INFO - codeparrot_training - Step 27613: {'lr': 0.00046395186447551617, 'samples': 14138368, 'steps': 27613, 'loss/train': 1.455855131149292}
-03/04/2022 21:54:29 - INFO - codeparrot_training - Step 27614: {'lr': 0.00046394911927767526, 'samples': 14138880, 'steps': 27614, 'loss/train': 1.6548454761505127}
-03/04/2022 21:54:31 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/04/2022 21:54:34 - INFO - codeparrot_training - Step 27615: {'lr': 0.0004639463739834321, 'samples': 14139392, 'steps': 27615, 'loss/train': 0.9600452184677124}
-03/04/2022 21:54:37 - INFO - codeparrot_training - Step 27616: {'lr': 0.00046394362859278793, 'samples': 14139904, 'steps': 27616, 'loss/train': 1.2721601724624634}
-03/04/2022 21:54:39 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/04/2022 21:54:42 - INFO - codeparrot_training - Step 27617: {'lr': 0.00046394088310574416, 'samples': 14140416, 'steps': 27617, 'loss/train': 1.6315211057662964}
-03/04/2022 21:54:46 - INFO - codeparrot_training - Step 27618: {'lr': 0.000463938137522302, 'samples': 14140928, 'steps': 27618, 'loss/train': 1.812462329864502}
-03/04/2022 21:54:48 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/04/2022 21:54:51 - INFO - codeparrot_training - Step 27619: {'lr': 0.00046393539184246246, 'samples': 14141440, 'steps': 27619, 'loss/train': 1.689713716506958}
-03/04/2022 21:54:54 - INFO - codeparrot_training - Step 27620: {'lr': 0.000463932646066227, 'samples': 14141952, 'steps': 27620, 'loss/train': 2.6587886810302734}
-03/04/2022 21:54:56 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/04/2022 21:54:59 - INFO - codeparrot_training - Step 27621: {'lr': 0.0004639299001935968, 'samples': 14142464, 'steps': 27621, 'loss/train': 2.1129837036132812}
-03/04/2022 21:55:02 - INFO - codeparrot_training - Step 27622: {'lr': 0.0004639271542245731, 'samples': 14142976, 'steps': 27622, 'loss/train': 0.19581444561481476}
-03/04/2022 21:55:04 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/04/2022 21:55:08 - INFO - codeparrot_training - Step 27623: {'lr': 0.000463924408159157, 'samples': 14143488, 'steps': 27623, 'loss/train': 0.8398597240447998}
-03/04/2022 21:55:11 - INFO - codeparrot_training - Step 27624: {'lr': 0.00046392166199735, 'samples': 14144000, 'steps': 27624, 'loss/train': 1.8493735790252686}
-03/04/2022 21:55:13 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/04/2022 21:55:16 - INFO - codeparrot_training - Step 27625: {'lr': 0.00046391891573915325, 'samples': 14144512, 'steps': 27625, 'loss/train': 1.7245063781738281}
-03/04/2022 21:55:19 - INFO - codeparrot_training - Step 27626: {'lr': 0.0004639161693845678, 'samples': 14145024, 'steps': 27626, 'loss/train': 2.0746915340423584}
-03/04/2022 21:55:22 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/04/2022 21:55:25 - INFO - codeparrot_training - Step 27627: {'lr': 0.0004639134229335951, 'samples': 14145536, 'steps': 27627, 'loss/train': 1.8795573711395264}
-03/04/2022 21:55:28 - INFO - codeparrot_training - Step 27628: {'lr': 0.0004639106763862363, 'samples': 14146048, 'steps': 27628, 'loss/train': 2.0054335594177246}
-03/04/2022 21:55:30 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/04/2022 21:55:33 - INFO - codeparrot_training - Step 27629: {'lr': 0.00046390792974249263, 'samples': 14146560, 'steps': 27629, 'loss/train': 1.4535967111587524}
-03/04/2022 21:55:36 - INFO - codeparrot_training - Step 27630: {'lr': 0.00046390518300236535, 'samples': 14147072, 'steps': 27630, 'loss/train': 1.7396965026855469}
-03/04/2022 21:55:38 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/04/2022 21:55:41 - INFO - codeparrot_training - Step 27631: {'lr': 0.0004639024361658557, 'samples': 14147584, 'steps': 27631, 'loss/train': 2.5055084228515625}
-03/04/2022 21:55:45 - INFO - codeparrot_training - Step 27632: {'lr': 0.00046389968923296496, 'samples': 14148096, 'steps': 27632, 'loss/train': 1.5569921731948853}
-03/04/2022 21:55:47 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 21:55:50 - INFO - codeparrot_training - Step 27633: {'lr': 0.0004638969422036943, 'samples': 14148608, 'steps': 27633, 'loss/train': 1.5817103385925293}
-03/04/2022 21:55:53 - INFO - codeparrot_training - Step 27634: {'lr': 0.00046389419507804493, 'samples': 14149120, 'steps': 27634, 'loss/train': 2.108802080154419}
-03/04/2022 21:55:55 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/04/2022 21:55:58 - INFO - codeparrot_training - Step 27635: {'lr': 0.00046389144785601813, 'samples': 14149632, 'steps': 27635, 'loss/train': 1.8186153173446655}
-03/04/2022 21:56:02 - INFO - codeparrot_training - Step 27636: {'lr': 0.0004638887005376152, 'samples': 14150144, 'steps': 27636, 'loss/train': 1.2399070262908936}
-03/04/2022 21:56:04 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/04/2022 21:56:07 - INFO - codeparrot_training - Step 27637: {'lr': 0.0004638859531228373, 'samples': 14150656, 'steps': 27637, 'loss/train': 1.5489846467971802}
-03/04/2022 21:56:10 - INFO - codeparrot_training - Step 27638: {'lr': 0.00046388320561168567, 'samples': 14151168, 'steps': 27638, 'loss/train': 1.4304358959197998}
-03/04/2022 21:56:13 - INFO - codeparrot_training - Step 27639: {'lr': 0.00046388045800416157, 'samples': 14151680, 'steps': 27639, 'loss/train': 0.5739402770996094}
-03/04/2022 21:56:14 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/04/2022 21:56:19 - INFO - codeparrot_training - Step 27640: {'lr': 0.00046387771030026627, 'samples': 14152192, 'steps': 27640, 'loss/train': 1.2853105068206787}
-03/04/2022 21:56:22 - INFO - codeparrot_training - Step 27641: {'lr': 0.00046387496250000095, 'samples': 14152704, 'steps': 27641, 'loss/train': 1.532561182975769}
-03/04/2022 21:56:22 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/04/2022 21:56:27 - INFO - codeparrot_training - Step 27642: {'lr': 0.0004638722146033669, 'samples': 14153216, 'steps': 27642, 'loss/train': 1.7510236501693726}
-03/04/2022 21:56:30 - INFO - codeparrot_training - Step 27643: {'lr': 0.0004638694666103653, 'samples': 14153728, 'steps': 27643, 'loss/train': 2.280945062637329}
-03/04/2022 21:56:30 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 21:56:36 - INFO - codeparrot_training - Step 27644: {'lr': 0.00046386671852099743, 'samples': 14154240, 'steps': 27644, 'loss/train': 0.961483895778656}
-03/04/2022 21:56:39 - INFO - codeparrot_training - Step 27645: {'lr': 0.0004638639703352645, 'samples': 14154752, 'steps': 27645, 'loss/train': 2.505633592605591}
-03/04/2022 21:56:39 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/04/2022 21:56:44 - INFO - codeparrot_training - Step 27646: {'lr': 0.00046386122205316783, 'samples': 14155264, 'steps': 27646, 'loss/train': 1.683584213256836}
-03/04/2022 21:56:47 - INFO - codeparrot_training - Step 27647: {'lr': 0.0004638584736747085, 'samples': 14155776, 'steps': 27647, 'loss/train': 1.8131953477859497}
-03/04/2022 21:56:47 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 21:56:52 - INFO - codeparrot_training - Step 27648: {'lr': 0.00046385572519988793, 'samples': 14156288, 'steps': 27648, 'loss/train': 2.177790403366089}
-03/04/2022 21:56:55 - INFO - codeparrot_training - Step 27649: {'lr': 0.00046385297662870716, 'samples': 14156800, 'steps': 27649, 'loss/train': 1.9873101711273193}
-03/04/2022 21:56:55 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 21:57:01 - INFO - codeparrot_training - Step 27650: {'lr': 0.00046385022796116766, 'samples': 14157312, 'steps': 27650, 'loss/train': 1.2463878393173218}
-03/04/2022 21:57:04 - INFO - codeparrot_training - Step 27651: {'lr': 0.0004638474791972705, 'samples': 14157824, 'steps': 27651, 'loss/train': 2.1014769077301025}
-03/04/2022 21:57:04 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 21:57:09 - INFO - codeparrot_training - Step 27652: {'lr': 0.000463844730337017, 'samples': 14158336, 'steps': 27652, 'loss/train': 2.2625844478607178}
-03/04/2022 21:57:12 - INFO - codeparrot_training - Step 27653: {'lr': 0.00046384198138040825, 'samples': 14158848, 'steps': 27653, 'loss/train': 1.9300283193588257}
-03/04/2022 21:57:13 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 21:57:18 - INFO - codeparrot_training - Step 27654: {'lr': 0.00046383923232744565, 'samples': 14159360, 'steps': 27654, 'loss/train': 2.1567187309265137}
-03/04/2022 21:57:21 - INFO - codeparrot_training - Step 27655: {'lr': 0.00046383648317813045, 'samples': 14159872, 'steps': 27655, 'loss/train': 1.30332350730896}
-03/04/2022 21:57:21 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 21:57:26 - INFO - codeparrot_training - Step 27656: {'lr': 0.0004638337339324638, 'samples': 14160384, 'steps': 27656, 'loss/train': 2.142608404159546}
-03/04/2022 21:57:30 - INFO - codeparrot_training - Step 27657: {'lr': 0.00046383098459044697, 'samples': 14160896, 'steps': 27657, 'loss/train': 1.143470287322998}
-03/04/2022 21:57:31 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/04/2022 21:57:35 - INFO - codeparrot_training - Step 27658: {'lr': 0.0004638282351520812, 'samples': 14161408, 'steps': 27658, 'loss/train': 1.9976515769958496}
-03/04/2022 21:57:38 - INFO - codeparrot_training - Step 27659: {'lr': 0.00046382548561736773, 'samples': 14161920, 'steps': 27659, 'loss/train': 1.8706058263778687}
-03/04/2022 21:57:39 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/04/2022 21:57:43 - INFO - codeparrot_training - Step 27660: {'lr': 0.0004638227359863078, 'samples': 14162432, 'steps': 27660, 'loss/train': 1.6258901357650757}
-03/04/2022 21:57:46 - INFO - codeparrot_training - Step 27661: {'lr': 0.0004638199862589026, 'samples': 14162944, 'steps': 27661, 'loss/train': 1.7211793661117554}
-03/04/2022 21:57:48 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/04/2022 21:57:52 - INFO - codeparrot_training - Step 27662: {'lr': 0.0004638172364351535, 'samples': 14163456, 'steps': 27662, 'loss/train': 2.274756908416748}
-03/04/2022 21:57:55 - INFO - codeparrot_training - Step 27663: {'lr': 0.00046381448651506153, 'samples': 14163968, 'steps': 27663, 'loss/train': 0.5946659445762634}
-03/04/2022 21:57:56 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/04/2022 21:58:00 - INFO - codeparrot_training - Step 27664: {'lr': 0.00046381173649862815, 'samples': 14164480, 'steps': 27664, 'loss/train': 1.467079997062683}
-03/04/2022 21:58:03 - INFO - codeparrot_training - Step 27665: {'lr': 0.00046380898638585447, 'samples': 14164992, 'steps': 27665, 'loss/train': 2.2406606674194336}
-03/04/2022 21:58:05 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 21:58:09 - INFO - codeparrot_training - Step 27666: {'lr': 0.0004638062361767418, 'samples': 14165504, 'steps': 27666, 'loss/train': 2.694225788116455}
-03/04/2022 21:58:12 - INFO - codeparrot_training - Step 27667: {'lr': 0.00046380348587129127, 'samples': 14166016, 'steps': 27667, 'loss/train': 2.78141713142395}
-03/04/2022 21:58:13 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/04/2022 21:58:17 - INFO - codeparrot_training - Step 27668: {'lr': 0.0004638007354695042, 'samples': 14166528, 'steps': 27668, 'loss/train': 2.0397236347198486}
-03/04/2022 21:58:20 - INFO - codeparrot_training - Step 27669: {'lr': 0.0004637979849713818, 'samples': 14167040, 'steps': 27669, 'loss/train': 1.8724124431610107}
-03/04/2022 21:58:22 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/04/2022 21:58:26 - INFO - codeparrot_training - Step 27670: {'lr': 0.0004637952343769254, 'samples': 14167552, 'steps': 27670, 'loss/train': 1.954559326171875}
-03/04/2022 21:58:29 - INFO - codeparrot_training - Step 27671: {'lr': 0.00046379248368613615, 'samples': 14168064, 'steps': 27671, 'loss/train': 1.8471759557724}
-03/04/2022 21:58:31 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 21:58:34 - INFO - codeparrot_training - Step 27672: {'lr': 0.0004637897328990153, 'samples': 14168576, 'steps': 27672, 'loss/train': 2.4220101833343506}
-03/04/2022 21:58:37 - INFO - codeparrot_training - Step 27673: {'lr': 0.000463786982015564, 'samples': 14169088, 'steps': 27673, 'loss/train': 1.9231946468353271}
-03/04/2022 21:58:39 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/04/2022 21:58:43 - INFO - codeparrot_training - Step 27674: {'lr': 0.00046378423103578373, 'samples': 14169600, 'steps': 27674, 'loss/train': 1.2739123106002808}
-03/04/2022 21:58:46 - INFO - codeparrot_training - Step 27675: {'lr': 0.0004637814799596755, 'samples': 14170112, 'steps': 27675, 'loss/train': 2.087042808532715}
-03/04/2022 21:58:49 - INFO - codeparrot_training - Step 27676: {'lr': 0.00046377872878724066, 'samples': 14170624, 'steps': 27676, 'loss/train': 0.645000159740448}
-03/04/2022 21:58:49 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/04/2022 21:58:55 - INFO - codeparrot_training - Step 27677: {'lr': 0.0004637759775184804, 'samples': 14171136, 'steps': 27677, 'loss/train': 2.3026845455169678}
-03/04/2022 21:58:58 - INFO - codeparrot_training - Step 27678: {'lr': 0.000463773226153396, 'samples': 14171648, 'steps': 27678, 'loss/train': 1.6942437887191772}
-03/04/2022 21:58:58 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/04/2022 21:59:03 - INFO - codeparrot_training - Step 27679: {'lr': 0.00046377047469198875, 'samples': 14172160, 'steps': 27679, 'loss/train': 1.4253997802734375}
-03/04/2022 21:59:06 - INFO - codeparrot_training - Step 27680: {'lr': 0.00046376772313425974, 'samples': 14172672, 'steps': 27680, 'loss/train': 1.9372918605804443}
-03/04/2022 21:59:07 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/04/2022 21:59:12 - INFO - codeparrot_training - Step 27681: {'lr': 0.0004637649714802102, 'samples': 14173184, 'steps': 27681, 'loss/train': 1.1158498525619507}
-03/04/2022 21:59:15 - INFO - codeparrot_training - Step 27682: {'lr': 0.0004637622197298417, 'samples': 14173696, 'steps': 27682, 'loss/train': 1.6550767421722412}
-03/04/2022 21:59:15 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/04/2022 21:59:20 - INFO - codeparrot_training - Step 27683: {'lr': 0.000463759467883155, 'samples': 14174208, 'steps': 27683, 'loss/train': 3.8308522701263428}
-03/04/2022 21:59:23 - INFO - codeparrot_training - Step 27684: {'lr': 0.0004637567159401518, 'samples': 14174720, 'steps': 27684, 'loss/train': 1.7069790363311768}
-03/04/2022 21:59:24 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/04/2022 21:59:28 - INFO - codeparrot_training - Step 27685: {'lr': 0.00046375396390083303, 'samples': 14175232, 'steps': 27685, 'loss/train': 1.4326366186141968}
-03/04/2022 21:59:32 - INFO - codeparrot_training - Step 27686: {'lr': 0.0004637512117652, 'samples': 14175744, 'steps': 27686, 'loss/train': 1.5388849973678589}
-03/04/2022 21:59:32 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/04/2022 21:59:37 - INFO - codeparrot_training - Step 27687: {'lr': 0.00046374845953325394, 'samples': 14176256, 'steps': 27687, 'loss/train': 2.2025234699249268}
-03/04/2022 21:59:40 - INFO - codeparrot_training - Step 27688: {'lr': 0.0004637457072049962, 'samples': 14176768, 'steps': 27688, 'loss/train': 1.6369661092758179}
-03/04/2022 21:59:41 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 21:59:45 - INFO - codeparrot_training - Step 27689: {'lr': 0.0004637429547804279, 'samples': 14177280, 'steps': 27689, 'loss/train': 1.3149855136871338}
-03/04/2022 21:59:48 - INFO - codeparrot_training - Step 27690: {'lr': 0.0004637402022595503, 'samples': 14177792, 'steps': 27690, 'loss/train': 1.807578682899475}
-03/04/2022 21:59:49 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/04/2022 21:59:54 - INFO - codeparrot_training - Step 27691: {'lr': 0.0004637374496423647, 'samples': 14178304, 'steps': 27691, 'loss/train': 2.0890626907348633}
-03/04/2022 21:59:57 - INFO - codeparrot_training - Step 27692: {'lr': 0.0004637346969288723, 'samples': 14178816, 'steps': 27692, 'loss/train': 1.640377163887024}
-03/04/2022 21:59:57 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/04/2022 22:00:03 - INFO - codeparrot_training - Step 27693: {'lr': 0.0004637319441190743, 'samples': 14179328, 'steps': 27693, 'loss/train': 1.8304755687713623}
-03/04/2022 22:00:06 - INFO - codeparrot_training - Step 27694: {'lr': 0.00046372919121297207, 'samples': 14179840, 'steps': 27694, 'loss/train': 0.16078712046146393}
-03/04/2022 22:00:07 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/04/2022 22:00:11 - INFO - codeparrot_training - Step 27695: {'lr': 0.0004637264382105667, 'samples': 14180352, 'steps': 27695, 'loss/train': 1.9947274923324585}
-03/04/2022 22:00:14 - INFO - codeparrot_training - Step 27696: {'lr': 0.00046372368511185953, 'samples': 14180864, 'steps': 27696, 'loss/train': 2.2045764923095703}
-03/04/2022 22:00:16 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/04/2022 22:00:20 - INFO - codeparrot_training - Step 27697: {'lr': 0.0004637209319168517, 'samples': 14181376, 'steps': 27697, 'loss/train': 1.5442280769348145}
-03/04/2022 22:00:23 - INFO - codeparrot_training - Step 27698: {'lr': 0.0004637181786255446, 'samples': 14181888, 'steps': 27698, 'loss/train': 2.004926919937134}
-03/04/2022 22:00:24 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 22:00:28 - INFO - codeparrot_training - Step 27699: {'lr': 0.0004637154252379394, 'samples': 14182400, 'steps': 27699, 'loss/train': 2.624953508377075}
-03/04/2022 22:00:31 - INFO - codeparrot_training - Step 27700: {'lr': 0.00046371267175403724, 'samples': 14182912, 'steps': 27700, 'loss/train': 1.7273741960525513}
-03/04/2022 22:00:33 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 22:00:37 - INFO - codeparrot_training - Step 27701: {'lr': 0.0004637099181738395, 'samples': 14183424, 'steps': 27701, 'loss/train': 2.193159341812134}
-03/04/2022 22:00:40 - INFO - codeparrot_training - Step 27702: {'lr': 0.00046370716449734733, 'samples': 14183936, 'steps': 27702, 'loss/train': 1.833182454109192}
-03/04/2022 22:00:41 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/04/2022 22:00:45 - INFO - codeparrot_training - Step 27703: {'lr': 0.00046370441072456206, 'samples': 14184448, 'steps': 27703, 'loss/train': 2.585933208465576}
-03/04/2022 22:00:48 - INFO - codeparrot_training - Step 27704: {'lr': 0.00046370165685548484, 'samples': 14184960, 'steps': 27704, 'loss/train': 2.016301155090332}
-03/04/2022 22:00:51 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/04/2022 22:00:54 - INFO - codeparrot_training - Step 27705: {'lr': 0.00046369890289011696, 'samples': 14185472, 'steps': 27705, 'loss/train': 1.347489356994629}
-03/04/2022 22:00:57 - INFO - codeparrot_training - Step 27706: {'lr': 0.0004636961488284597, 'samples': 14185984, 'steps': 27706, 'loss/train': 1.0110247135162354}
-03/04/2022 22:00:59 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/04/2022 22:01:03 - INFO - codeparrot_training - Step 27707: {'lr': 0.0004636933946705142, 'samples': 14186496, 'steps': 27707, 'loss/train': 1.1653650999069214}
-03/04/2022 22:01:06 - INFO - codeparrot_training - Step 27708: {'lr': 0.00046369064041628175, 'samples': 14187008, 'steps': 27708, 'loss/train': 2.1749603748321533}
-03/04/2022 22:01:09 - INFO - codeparrot_training - Step 27709: {'lr': 0.00046368788606576363, 'samples': 14187520, 'steps': 27709, 'loss/train': 1.8301324844360352}
-03/04/2022 22:01:11 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 22:01:15 - INFO - codeparrot_training - Step 27710: {'lr': 0.00046368513161896104, 'samples': 14188032, 'steps': 27710, 'loss/train': 1.616692066192627}
-03/04/2022 22:01:18 - INFO - codeparrot_training - Step 27711: {'lr': 0.0004636823770758752, 'samples': 14188544, 'steps': 27711, 'loss/train': 2.0546274185180664}
-03/04/2022 22:01:20 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/04/2022 22:01:23 - INFO - codeparrot_training - Step 27712: {'lr': 0.0004636796224365074, 'samples': 14189056, 'steps': 27712, 'loss/train': 1.4505919218063354}
-03/04/2022 22:01:26 - INFO - codeparrot_training - Step 27713: {'lr': 0.0004636768677008588, 'samples': 14189568, 'steps': 27713, 'loss/train': 1.7372467517852783}
-03/04/2022 22:01:28 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/04/2022 22:01:31 - INFO - codeparrot_training - Step 27714: {'lr': 0.0004636741128689308, 'samples': 14190080, 'steps': 27714, 'loss/train': 1.6584452390670776}
-03/04/2022 22:01:35 - INFO - codeparrot_training - Step 27715: {'lr': 0.00046367135794072445, 'samples': 14190592, 'steps': 27715, 'loss/train': 2.363029718399048}
-03/04/2022 22:01:37 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/04/2022 22:01:40 - INFO - codeparrot_training - Step 27716: {'lr': 0.0004636686029162411, 'samples': 14191104, 'steps': 27716, 'loss/train': 1.506821870803833}
-03/04/2022 22:01:43 - INFO - codeparrot_training - Step 27717: {'lr': 0.000463665847795482, 'samples': 14191616, 'steps': 27717, 'loss/train': 1.650162696838379}
-03/04/2022 22:01:45 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 22:01:48 - INFO - codeparrot_training - Step 27718: {'lr': 0.0004636630925784484, 'samples': 14192128, 'steps': 27718, 'loss/train': 0.442815899848938}
-03/04/2022 22:01:51 - INFO - codeparrot_training - Step 27719: {'lr': 0.0004636603372651415, 'samples': 14192640, 'steps': 27719, 'loss/train': 2.1814231872558594}
-03/04/2022 22:01:53 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/04/2022 22:01:57 - INFO - codeparrot_training - Step 27720: {'lr': 0.0004636575818555625, 'samples': 14193152, 'steps': 27720, 'loss/train': 1.7144211530685425}
-03/04/2022 22:02:00 - INFO - codeparrot_training - Step 27721: {'lr': 0.00046365482634971275, 'samples': 14193664, 'steps': 27721, 'loss/train': 2.4171338081359863}
-03/04/2022 22:02:02 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 22:02:05 - INFO - codeparrot_training - Step 27722: {'lr': 0.00046365207074759344, 'samples': 14194176, 'steps': 27722, 'loss/train': 1.9996066093444824}
-03/04/2022 22:02:08 - INFO - codeparrot_training - Step 27723: {'lr': 0.0004636493150492057, 'samples': 14194688, 'steps': 27723, 'loss/train': 1.48897123336792}
-03/04/2022 22:02:10 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 22:02:14 - INFO - codeparrot_training - Step 27724: {'lr': 0.00046364655925455094, 'samples': 14195200, 'steps': 27724, 'loss/train': 2.320746898651123}
-03/04/2022 22:02:17 - INFO - codeparrot_training - Step 27725: {'lr': 0.0004636438033636303, 'samples': 14195712, 'steps': 27725, 'loss/train': 2.3675310611724854}
-03/04/2022 22:02:19 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/04/2022 22:02:22 - INFO - codeparrot_training - Step 27726: {'lr': 0.00046364104737644515, 'samples': 14196224, 'steps': 27726, 'loss/train': 1.060471534729004}
-03/04/2022 22:02:25 - INFO - codeparrot_training - Step 27727: {'lr': 0.00046363829129299655, 'samples': 14196736, 'steps': 27727, 'loss/train': 1.4515392780303955}
-03/04/2022 22:02:27 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 22:02:30 - INFO - codeparrot_training - Step 27728: {'lr': 0.0004636355351132859, 'samples': 14197248, 'steps': 27728, 'loss/train': 1.8292841911315918}
-03/04/2022 22:02:34 - INFO - codeparrot_training - Step 27729: {'lr': 0.00046363277883731437, 'samples': 14197760, 'steps': 27729, 'loss/train': 1.8513379096984863}
-03/04/2022 22:02:36 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/04/2022 22:02:39 - INFO - codeparrot_training - Step 27730: {'lr': 0.0004636300224650831, 'samples': 14198272, 'steps': 27730, 'loss/train': 1.7789907455444336}
-03/04/2022 22:02:42 - INFO - codeparrot_training - Step 27731: {'lr': 0.00046362726599659355, 'samples': 14198784, 'steps': 27731, 'loss/train': 0.8972790241241455}
-03/04/2022 22:02:45 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/04/2022 22:02:47 - INFO - codeparrot_training - Step 27732: {'lr': 0.0004636245094318468, 'samples': 14199296, 'steps': 27732, 'loss/train': 3.09785532951355}
-03/04/2022 22:02:51 - INFO - codeparrot_training - Step 27733: {'lr': 0.0004636217527708442, 'samples': 14199808, 'steps': 27733, 'loss/train': 1.6478772163391113}
-03/04/2022 22:02:53 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 22:02:56 - INFO - codeparrot_training - Step 27734: {'lr': 0.0004636189960135869, 'samples': 14200320, 'steps': 27734, 'loss/train': 1.8681186437606812}
-03/04/2022 22:02:59 - INFO - codeparrot_training - Step 27735: {'lr': 0.0004636162391600761, 'samples': 14200832, 'steps': 27735, 'loss/train': 2.36531662940979}
-03/04/2022 22:03:01 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/04/2022 22:03:04 - INFO - codeparrot_training - Step 27736: {'lr': 0.00046361348221031316, 'samples': 14201344, 'steps': 27736, 'loss/train': 1.3374491930007935}
-03/04/2022 22:03:07 - INFO - codeparrot_training - Step 27737: {'lr': 0.00046361072516429936, 'samples': 14201856, 'steps': 27737, 'loss/train': 1.3949568271636963}
-03/04/2022 22:03:10 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/04/2022 22:03:13 - INFO - codeparrot_training - Step 27738: {'lr': 0.0004636079680220358, 'samples': 14202368, 'steps': 27738, 'loss/train': 2.6667675971984863}
-03/04/2022 22:03:16 - INFO - codeparrot_training - Step 27739: {'lr': 0.0004636052107835238, 'samples': 14202880, 'steps': 27739, 'loss/train': 1.5909504890441895}
-03/04/2022 22:03:18 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/04/2022 22:03:21 - INFO - codeparrot_training - Step 27740: {'lr': 0.0004636024534487646, 'samples': 14203392, 'steps': 27740, 'loss/train': 1.7761894464492798}
-03/04/2022 22:03:24 - INFO - codeparrot_training - Step 27741: {'lr': 0.0004635996960177594, 'samples': 14203904, 'steps': 27741, 'loss/train': 1.5329194068908691}
-03/04/2022 22:03:27 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/04/2022 22:03:29 - INFO - codeparrot_training - Step 27742: {'lr': 0.0004635969384905095, 'samples': 14204416, 'steps': 27742, 'loss/train': 2.229836940765381}
-03/04/2022 22:03:33 - INFO - codeparrot_training - Step 27743: {'lr': 0.0004635941808670161, 'samples': 14204928, 'steps': 27743, 'loss/train': 1.1372333765029907}
-03/04/2022 22:03:35 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/04/2022 22:03:38 - INFO - codeparrot_training - Step 27744: {'lr': 0.00046359142314728047, 'samples': 14205440, 'steps': 27744, 'loss/train': 1.7281755208969116}
-03/04/2022 22:03:41 - INFO - codeparrot_training - Step 27745: {'lr': 0.00046358866533130385, 'samples': 14205952, 'steps': 27745, 'loss/train': 1.8930840492248535}
-03/04/2022 22:03:43 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/04/2022 22:03:46 - INFO - codeparrot_training - Step 27746: {'lr': 0.00046358590741908744, 'samples': 14206464, 'steps': 27746, 'loss/train': 1.3337597846984863}
-03/04/2022 22:03:50 - INFO - codeparrot_training - Step 27747: {'lr': 0.0004635831494106325, 'samples': 14206976, 'steps': 27747, 'loss/train': 1.690032720565796}
-03/04/2022 22:03:52 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/04/2022 22:03:55 - INFO - codeparrot_training - Step 27748: {'lr': 0.0004635803913059404, 'samples': 14207488, 'steps': 27748, 'loss/train': 1.4430631399154663}
-03/04/2022 22:03:58 - INFO - codeparrot_training - Step 27749: {'lr': 0.00046357763310501216, 'samples': 14208000, 'steps': 27749, 'loss/train': 1.9462181329727173}
-03/04/2022 22:04:01 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/04/2022 22:04:04 - INFO - codeparrot_training - Step 27750: {'lr': 0.0004635748748078492, 'samples': 14208512, 'steps': 27750, 'loss/train': 1.523032307624817}
-03/04/2022 22:04:07 - INFO - codeparrot_training - Step 27751: {'lr': 0.0004635721164144526, 'samples': 14209024, 'steps': 27751, 'loss/train': 0.42103275656700134}
-03/04/2022 22:04:10 - INFO - codeparrot_training - Step 27752: {'lr': 0.0004635693579248238, 'samples': 14209536, 'steps': 27752, 'loss/train': 2.098022699356079}
-03/04/2022 22:04:10 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 22:04:15 - INFO - codeparrot_training - Step 27753: {'lr': 0.00046356659933896393, 'samples': 14210048, 'steps': 27753, 'loss/train': 2.3072338104248047}
-03/04/2022 22:04:18 - INFO - codeparrot_training - Step 27754: {'lr': 0.0004635638406568742, 'samples': 14210560, 'steps': 27754, 'loss/train': 2.0574228763580322}
-03/04/2022 22:04:19 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 22:04:24 - INFO - codeparrot_training - Step 27755: {'lr': 0.00046356108187855594, 'samples': 14211072, 'steps': 27755, 'loss/train': 1.469580888748169}
-03/04/2022 22:04:27 - INFO - codeparrot_training - Step 27756: {'lr': 0.00046355832300401035, 'samples': 14211584, 'steps': 27756, 'loss/train': 2.01407790184021}
-03/04/2022 22:04:27 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/04/2022 22:04:32 - INFO - codeparrot_training - Step 27757: {'lr': 0.0004635555640332386, 'samples': 14212096, 'steps': 27757, 'loss/train': 2.295642614364624}
-03/04/2022 22:04:35 - INFO - codeparrot_training - Step 27758: {'lr': 0.0004635528049662421, 'samples': 14212608, 'steps': 27758, 'loss/train': 1.5834499597549438}
-03/04/2022 22:04:36 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/04/2022 22:04:41 - INFO - codeparrot_training - Step 27759: {'lr': 0.000463550045803022, 'samples': 14213120, 'steps': 27759, 'loss/train': 2.163318634033203}
-03/04/2022 22:04:44 - INFO - codeparrot_training - Step 27760: {'lr': 0.00046354728654357947, 'samples': 14213632, 'steps': 27760, 'loss/train': 0.6939167976379395}
-03/04/2022 22:04:44 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/04/2022 22:04:49 - INFO - codeparrot_training - Step 27761: {'lr': 0.00046354452718791586, 'samples': 14214144, 'steps': 27761, 'loss/train': 2.087846279144287}
-03/04/2022 22:04:52 - INFO - codeparrot_training - Step 27762: {'lr': 0.0004635417677360324, 'samples': 14214656, 'steps': 27762, 'loss/train': 1.7547439336776733}
-03/04/2022 22:04:53 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/04/2022 22:04:57 - INFO - codeparrot_training - Step 27763: {'lr': 0.0004635390081879303, 'samples': 14215168, 'steps': 27763, 'loss/train': 1.6721590757369995}
-03/04/2022 22:05:01 - INFO - codeparrot_training - Step 27764: {'lr': 0.0004635362485436109, 'samples': 14215680, 'steps': 27764, 'loss/train': 1.5610356330871582}
-03/04/2022 22:05:01 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 22:05:06 - INFO - codeparrot_training - Step 27765: {'lr': 0.00046353348880307524, 'samples': 14216192, 'steps': 27765, 'loss/train': 2.0910394191741943}
-03/04/2022 22:05:09 - INFO - codeparrot_training - Step 27766: {'lr': 0.0004635307289663248, 'samples': 14216704, 'steps': 27766, 'loss/train': 2.2547733783721924}
-03/04/2022 22:05:10 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/04/2022 22:05:15 - INFO - codeparrot_training - Step 27767: {'lr': 0.0004635279690333606, 'samples': 14217216, 'steps': 27767, 'loss/train': 1.8320846557617188}
-03/04/2022 22:05:18 - INFO - codeparrot_training - Step 27768: {'lr': 0.00046352520900418403, 'samples': 14217728, 'steps': 27768, 'loss/train': 1.6263936758041382}
-03/04/2022 22:05:18 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/04/2022 22:05:23 - INFO - codeparrot_training - Step 27769: {'lr': 0.00046352244887879623, 'samples': 14218240, 'steps': 27769, 'loss/train': 2.0929505825042725}
-03/04/2022 22:05:26 - INFO - codeparrot_training - Step 27770: {'lr': 0.0004635196886571986, 'samples': 14218752, 'steps': 27770, 'loss/train': 1.832887053489685}
-03/04/2022 22:05:27 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/04/2022 22:05:31 - INFO - codeparrot_training - Step 27771: {'lr': 0.0004635169283393923, 'samples': 14219264, 'steps': 27771, 'loss/train': 1.312677264213562}
-03/04/2022 22:05:35 - INFO - codeparrot_training - Step 27772: {'lr': 0.0004635141679253785, 'samples': 14219776, 'steps': 27772, 'loss/train': 1.8295867443084717}
-03/04/2022 22:05:35 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 22:05:40 - INFO - codeparrot_training - Step 27773: {'lr': 0.0004635114074151586, 'samples': 14220288, 'steps': 27773, 'loss/train': 2.1418542861938477}
-03/04/2022 22:05:43 - INFO - codeparrot_training - Step 27774: {'lr': 0.00046350864680873375, 'samples': 14220800, 'steps': 27774, 'loss/train': 1.6271815299987793}
-03/04/2022 22:05:43 - INFO - codeparrot_training - Skipping example with length 86 (seq_length=1024)
-03/04/2022 22:05:48 - INFO - codeparrot_training - Step 27775: {'lr': 0.0004635058861061051, 'samples': 14221312, 'steps': 27775, 'loss/train': 2.012097120285034}
-03/04/2022 22:05:52 - INFO - codeparrot_training - Step 27776: {'lr': 0.00046350312530727403, 'samples': 14221824, 'steps': 27776, 'loss/train': 0.13385742902755737}
-03/04/2022 22:05:52 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 22:05:57 - INFO - codeparrot_training - Step 27777: {'lr': 0.00046350036441224175, 'samples': 14222336, 'steps': 27777, 'loss/train': 1.629122018814087}
-03/04/2022 22:06:00 - INFO - codeparrot_training - Step 27778: {'lr': 0.00046349760342100955, 'samples': 14222848, 'steps': 27778, 'loss/train': 1.8312352895736694}
-03/04/2022 22:06:00 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/04/2022 22:06:05 - INFO - codeparrot_training - Step 27779: {'lr': 0.00046349484233357854, 'samples': 14223360, 'steps': 27779, 'loss/train': 1.6179144382476807}
-03/04/2022 22:06:08 - INFO - codeparrot_training - Step 27780: {'lr': 0.0004634920811499501, 'samples': 14223872, 'steps': 27780, 'loss/train': 1.5531561374664307}
-03/04/2022 22:06:08 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/04/2022 22:06:14 - INFO - codeparrot_training - Step 27781: {'lr': 0.00046348931987012543, 'samples': 14224384, 'steps': 27781, 'loss/train': 1.8827059268951416}
-03/04/2022 22:06:17 - INFO - codeparrot_training - Step 27782: {'lr': 0.00046348655849410577, 'samples': 14224896, 'steps': 27782, 'loss/train': 1.1866304874420166}
-03/04/2022 22:06:18 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/04/2022 22:06:22 - INFO - codeparrot_training - Step 27783: {'lr': 0.0004634837970218924, 'samples': 14225408, 'steps': 27783, 'loss/train': 2.3055338859558105}
-03/04/2022 22:06:25 - INFO - codeparrot_training - Step 27784: {'lr': 0.0004634810354534864, 'samples': 14225920, 'steps': 27784, 'loss/train': 1.9569162130355835}
-03/04/2022 22:06:26 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/04/2022 22:06:31 - INFO - codeparrot_training - Step 27785: {'lr': 0.0004634782737888892, 'samples': 14226432, 'steps': 27785, 'loss/train': 1.464118242263794}
-03/04/2022 22:06:34 - INFO - codeparrot_training - Step 27786: {'lr': 0.000463475512028102, 'samples': 14226944, 'steps': 27786, 'loss/train': 2.316864013671875}
-03/04/2022 22:06:34 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/04/2022 22:06:39 - INFO - codeparrot_training - Step 27787: {'lr': 0.000463472750171126, 'samples': 14227456, 'steps': 27787, 'loss/train': 1.9971297979354858}
-03/04/2022 22:06:42 - INFO - codeparrot_training - Step 27788: {'lr': 0.0004634699882179625, 'samples': 14227968, 'steps': 27788, 'loss/train': 1.4182398319244385}
-03/04/2022 22:06:43 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/04/2022 22:06:48 - INFO - codeparrot_training - Step 27789: {'lr': 0.0004634672261686127, 'samples': 14228480, 'steps': 27789, 'loss/train': 1.9485887289047241}
-03/04/2022 22:06:51 - INFO - codeparrot_training - Step 27790: {'lr': 0.0004634644640230779, 'samples': 14228992, 'steps': 27790, 'loss/train': 2.0548746585845947}
-03/04/2022 22:06:51 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/04/2022 22:06:56 - INFO - codeparrot_training - Step 27791: {'lr': 0.0004634617017813593, 'samples': 14229504, 'steps': 27791, 'loss/train': 1.986729383468628}
-03/04/2022 22:06:59 - INFO - codeparrot_training - Step 27792: {'lr': 0.00046345893944345806, 'samples': 14230016, 'steps': 27792, 'loss/train': 2.2010934352874756}
-03/04/2022 22:06:59 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 22:07:04 - INFO - codeparrot_training - Step 27793: {'lr': 0.00046345617700937564, 'samples': 14230528, 'steps': 27793, 'loss/train': 0.4626636803150177}
-03/04/2022 22:07:08 - INFO - codeparrot_training - Step 27794: {'lr': 0.0004634534144791131, 'samples': 14231040, 'steps': 27794, 'loss/train': 1.7331457138061523}
-03/04/2022 22:07:08 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 22:07:13 - INFO - codeparrot_training - Step 27795: {'lr': 0.0004634506518526718, 'samples': 14231552, 'steps': 27795, 'loss/train': 1.4106076955795288}
-03/04/2022 22:07:16 - INFO - codeparrot_training - Step 27796: {'lr': 0.00046344788913005286, 'samples': 14232064, 'steps': 27796, 'loss/train': 1.3276640176773071}
-03/04/2022 22:07:16 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/04/2022 22:07:21 - INFO - codeparrot_training - Step 27797: {'lr': 0.00046344512631125756, 'samples': 14232576, 'steps': 27797, 'loss/train': 1.9046461582183838}
-03/04/2022 22:07:24 - INFO - codeparrot_training - Step 27798: {'lr': 0.00046344236339628724, 'samples': 14233088, 'steps': 27798, 'loss/train': 1.5118050575256348}
-03/04/2022 22:07:24 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/04/2022 22:07:30 - INFO - codeparrot_training - Step 27799: {'lr': 0.0004634396003851431, 'samples': 14233600, 'steps': 27799, 'loss/train': 1.7403936386108398}
-03/04/2022 22:07:33 - INFO - codeparrot_training - Step 27800: {'lr': 0.00046343683727782635, 'samples': 14234112, 'steps': 27800, 'loss/train': 1.4251739978790283}
-03/04/2022 22:07:33 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/04/2022 22:07:38 - INFO - codeparrot_training - Step 27801: {'lr': 0.0004634340740743382, 'samples': 14234624, 'steps': 27801, 'loss/train': 2.0048484802246094}
-03/04/2022 22:07:41 - INFO - codeparrot_training - Step 27802: {'lr': 0.00046343131077468, 'samples': 14235136, 'steps': 27802, 'loss/train': 1.9860423803329468}
-03/04/2022 22:07:41 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/04/2022 22:07:47 - INFO - codeparrot_training - Step 27803: {'lr': 0.00046342854737885296, 'samples': 14235648, 'steps': 27803, 'loss/train': 2.3793885707855225}
-03/04/2022 22:07:49 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 22:07:52 - INFO - codeparrot_training - Step 27804: {'lr': 0.00046342578388685837, 'samples': 14236160, 'steps': 27804, 'loss/train': 2.4320528507232666}
-03/04/2022 22:07:55 - INFO - codeparrot_training - Step 27805: {'lr': 0.0004634230202986973, 'samples': 14236672, 'steps': 27805, 'loss/train': 1.7690705060958862}
-03/04/2022 22:07:58 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/04/2022 22:08:00 - INFO - codeparrot_training - Step 27806: {'lr': 0.0004634202566143712, 'samples': 14237184, 'steps': 27806, 'loss/train': 1.710745930671692}
-03/04/2022 22:08:03 - INFO - codeparrot_training - Step 27807: {'lr': 0.00046341749283388117, 'samples': 14237696, 'steps': 27807, 'loss/train': 1.9012010097503662}
-03/04/2022 22:08:06 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/04/2022 22:08:09 - INFO - codeparrot_training - Step 27808: {'lr': 0.0004634147289572285, 'samples': 14238208, 'steps': 27808, 'loss/train': 1.891396164894104}
-03/04/2022 22:08:12 - INFO - codeparrot_training - Step 27809: {'lr': 0.00046341196498441453, 'samples': 14238720, 'steps': 27809, 'loss/train': 1.6843780279159546}
-03/04/2022 22:08:15 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/04/2022 22:08:17 - INFO - codeparrot_training - Step 27810: {'lr': 0.0004634092009154403, 'samples': 14239232, 'steps': 27810, 'loss/train': 1.9456217288970947}
-03/04/2022 22:08:20 - INFO - codeparrot_training - Step 27811: {'lr': 0.0004634064367503072, 'samples': 14239744, 'steps': 27811, 'loss/train': 1.508108377456665}
-03/04/2022 22:08:23 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/04/2022 22:08:26 - INFO - codeparrot_training - Step 27812: {'lr': 0.00046340367248901655, 'samples': 14240256, 'steps': 27812, 'loss/train': 1.7578274011611938}
-03/04/2022 22:08:29 - INFO - codeparrot_training - Step 27813: {'lr': 0.00046340090813156944, 'samples': 14240768, 'steps': 27813, 'loss/train': 0.723953366279602}
-03/04/2022 22:08:32 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 22:08:34 - INFO - codeparrot_training - Step 27814: {'lr': 0.00046339814367796716, 'samples': 14241280, 'steps': 27814, 'loss/train': 2.3181283473968506}
-03/04/2022 22:08:37 - INFO - codeparrot_training - Step 27815: {'lr': 0.00046339537912821094, 'samples': 14241792, 'steps': 27815, 'loss/train': 1.6481131315231323}
-03/04/2022 22:08:40 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 22:08:43 - INFO - codeparrot_training - Step 27816: {'lr': 0.0004633926144823022, 'samples': 14242304, 'steps': 27816, 'loss/train': 2.20108699798584}
-03/04/2022 22:08:46 - INFO - codeparrot_training - Step 27817: {'lr': 0.0004633898497402419, 'samples': 14242816, 'steps': 27817, 'loss/train': 1.3461902141571045}
-03/04/2022 22:08:49 - INFO - codeparrot_training - Step 27818: {'lr': 0.0004633870849020314, 'samples': 14243328, 'steps': 27818, 'loss/train': 2.112186908721924}
-03/04/2022 22:08:49 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/04/2022 22:08:54 - INFO - codeparrot_training - Step 27819: {'lr': 0.00046338431996767205, 'samples': 14243840, 'steps': 27819, 'loss/train': 1.6549814939498901}
-03/04/2022 22:08:57 - INFO - codeparrot_training - Step 27820: {'lr': 0.00046338155493716503, 'samples': 14244352, 'steps': 27820, 'loss/train': 0.6535369157791138}
-03/04/2022 22:08:58 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/04/2022 22:09:03 - INFO - codeparrot_training - Step 27821: {'lr': 0.0004633787898105115, 'samples': 14244864, 'steps': 27821, 'loss/train': 1.411918044090271}
-03/04/2022 22:09:06 - INFO - codeparrot_training - Step 27822: {'lr': 0.0004633760245877129, 'samples': 14245376, 'steps': 27822, 'loss/train': 1.8394396305084229}
-03/04/2022 22:09:06 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/04/2022 22:09:11 - INFO - codeparrot_training - Step 27823: {'lr': 0.0004633732592687703, 'samples': 14245888, 'steps': 27823, 'loss/train': 2.455958604812622}
-03/04/2022 22:09:15 - INFO - codeparrot_training - Step 27824: {'lr': 0.00046337049385368495, 'samples': 14246400, 'steps': 27824, 'loss/train': 0.4692844748497009}
-03/04/2022 22:09:15 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/04/2022 22:09:20 - INFO - codeparrot_training - Step 27825: {'lr': 0.00046336772834245824, 'samples': 14246912, 'steps': 27825, 'loss/train': 1.6152745485305786}
-03/04/2022 22:09:23 - INFO - codeparrot_training - Step 27826: {'lr': 0.0004633649627350912, 'samples': 14247424, 'steps': 27826, 'loss/train': 2.0641887187957764}
-03/04/2022 22:09:23 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/04/2022 22:09:28 - INFO - codeparrot_training - Step 27827: {'lr': 0.00046336219703158526, 'samples': 14247936, 'steps': 27827, 'loss/train': 1.6779061555862427}
-03/04/2022 22:09:31 - INFO - codeparrot_training - Step 27828: {'lr': 0.00046335943123194164, 'samples': 14248448, 'steps': 27828, 'loss/train': 1.4329558610916138}
-03/04/2022 22:09:31 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/04/2022 22:09:37 - INFO - codeparrot_training - Step 27829: {'lr': 0.0004633566653361615, 'samples': 14248960, 'steps': 27829, 'loss/train': 3.0693910121917725}
-03/04/2022 22:09:40 - INFO - codeparrot_training - Step 27830: {'lr': 0.0004633538993442462, 'samples': 14249472, 'steps': 27830, 'loss/train': 1.9775872230529785}
-03/04/2022 22:09:40 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/04/2022 22:09:45 - INFO - codeparrot_training - Step 27831: {'lr': 0.00046335113325619685, 'samples': 14249984, 'steps': 27831, 'loss/train': 2.1445913314819336}
-03/04/2022 22:09:48 - INFO - codeparrot_training - Step 27832: {'lr': 0.00046334836707201486, 'samples': 14250496, 'steps': 27832, 'loss/train': 1.3260197639465332}
-03/04/2022 22:09:48 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 22:09:53 - INFO - codeparrot_training - Step 27833: {'lr': 0.0004633456007917013, 'samples': 14251008, 'steps': 27833, 'loss/train': 1.877514123916626}
-03/04/2022 22:09:57 - INFO - codeparrot_training - Step 27834: {'lr': 0.0004633428344152576, 'samples': 14251520, 'steps': 27834, 'loss/train': 1.5650569200515747}
-03/04/2022 22:09:57 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/04/2022 22:10:02 - INFO - codeparrot_training - Step 27835: {'lr': 0.0004633400679426848, 'samples': 14252032, 'steps': 27835, 'loss/train': 1.3776929378509521}
-03/04/2022 22:10:05 - INFO - codeparrot_training - Step 27836: {'lr': 0.00046333730137398433, 'samples': 14252544, 'steps': 27836, 'loss/train': 2.5411412715911865}
-03/04/2022 22:10:05 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/04/2022 22:10:10 - INFO - codeparrot_training - Step 27837: {'lr': 0.00046333453470915736, 'samples': 14253056, 'steps': 27837, 'loss/train': 2.2302629947662354}
-03/04/2022 22:10:13 - INFO - codeparrot_training - Step 27838: {'lr': 0.0004633317679482051, 'samples': 14253568, 'steps': 27838, 'loss/train': 1.519649863243103}
-03/04/2022 22:10:14 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/04/2022 22:10:19 - INFO - codeparrot_training - Step 27839: {'lr': 0.00046332900109112893, 'samples': 14254080, 'steps': 27839, 'loss/train': 1.549185037612915}
-03/04/2022 22:10:22 - INFO - codeparrot_training - Step 27840: {'lr': 0.0004633262341379299, 'samples': 14254592, 'steps': 27840, 'loss/train': 0.859388530254364}
-03/04/2022 22:10:22 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/04/2022 22:10:27 - INFO - codeparrot_training - Step 27841: {'lr': 0.0004633234670886094, 'samples': 14255104, 'steps': 27841, 'loss/train': 1.855017066001892}
-03/04/2022 22:10:30 - INFO - codeparrot_training - Step 27842: {'lr': 0.0004633206999431686, 'samples': 14255616, 'steps': 27842, 'loss/train': 1.7508885860443115}
-03/04/2022 22:10:31 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/04/2022 22:10:36 - INFO - codeparrot_training - Step 27843: {'lr': 0.00046331793270160885, 'samples': 14256128, 'steps': 27843, 'loss/train': 2.497023820877075}
-03/04/2022 22:10:39 - INFO - codeparrot_training - Step 27844: {'lr': 0.0004633151653639314, 'samples': 14256640, 'steps': 27844, 'loss/train': 0.954716682434082}
-03/04/2022 22:10:39 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 22:10:44 - INFO - codeparrot_training - Step 27845: {'lr': 0.00046331239793013726, 'samples': 14257152, 'steps': 27845, 'loss/train': 1.5120946168899536}
-03/04/2022 22:10:47 - INFO - codeparrot_training - Step 27846: {'lr': 0.0004633096304002279, 'samples': 14257664, 'steps': 27846, 'loss/train': 2.254528760910034}
-03/04/2022 22:10:47 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/04/2022 22:10:53 - INFO - codeparrot_training - Step 27847: {'lr': 0.00046330686277420454, 'samples': 14258176, 'steps': 27847, 'loss/train': 2.151296615600586}
-03/04/2022 22:10:56 - INFO - codeparrot_training - Step 27848: {'lr': 0.00046330409505206837, 'samples': 14258688, 'steps': 27848, 'loss/train': 2.572255849838257}
-03/04/2022 22:10:56 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/04/2022 22:11:01 - INFO - codeparrot_training - Step 27849: {'lr': 0.00046330132723382066, 'samples': 14259200, 'steps': 27849, 'loss/train': 1.9765233993530273}
-03/04/2022 22:11:04 - INFO - codeparrot_training - Step 27850: {'lr': 0.0004632985593194627, 'samples': 14259712, 'steps': 27850, 'loss/train': 1.3368562459945679}
-03/04/2022 22:11:04 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/04/2022 22:11:10 - INFO - codeparrot_training - Step 27851: {'lr': 0.00046329579130899567, 'samples': 14260224, 'steps': 27851, 'loss/train': 1.6849944591522217}
-03/04/2022 22:11:13 - INFO - codeparrot_training - Step 27852: {'lr': 0.0004632930232024209, 'samples': 14260736, 'steps': 27852, 'loss/train': 1.436474323272705}
-03/04/2022 22:11:13 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 22:11:18 - INFO - codeparrot_training - Step 27853: {'lr': 0.0004632902549997395, 'samples': 14261248, 'steps': 27853, 'loss/train': 1.2919046878814697}
-03/04/2022 22:11:21 - INFO - codeparrot_training - Step 27854: {'lr': 0.00046328748670095287, 'samples': 14261760, 'steps': 27854, 'loss/train': 2.773169994354248}
-03/04/2022 22:11:21 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/04/2022 22:11:27 - INFO - codeparrot_training - Step 27855: {'lr': 0.0004632847183060622, 'samples': 14262272, 'steps': 27855, 'loss/train': 1.354175090789795}
-03/04/2022 22:11:30 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 22:11:32 - INFO - codeparrot_training - Step 27856: {'lr': 0.0004632819498150688, 'samples': 14262784, 'steps': 27856, 'loss/train': 1.643376350402832}
-03/04/2022 22:11:35 - INFO - codeparrot_training - Step 27857: {'lr': 0.00046327918122797363, 'samples': 14263296, 'steps': 27857, 'loss/train': 1.3152709007263184}
-03/04/2022 22:11:38 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/04/2022 22:11:40 - INFO - codeparrot_training - Step 27858: {'lr': 0.00046327641254477833, 'samples': 14263808, 'steps': 27858, 'loss/train': 1.742732286453247}
-03/04/2022 22:11:44 - INFO - codeparrot_training - Step 27859: {'lr': 0.00046327364376548384, 'samples': 14264320, 'steps': 27859, 'loss/train': 1.619951605796814}
-03/04/2022 22:11:46 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 22:11:49 - INFO - codeparrot_training - Step 27860: {'lr': 0.0004632708748900917, 'samples': 14264832, 'steps': 27860, 'loss/train': 2.0265564918518066}
-03/04/2022 22:11:52 - INFO - codeparrot_training - Step 27861: {'lr': 0.00046326810591860285, 'samples': 14265344, 'steps': 27861, 'loss/train': 1.6696511507034302}
-03/04/2022 22:11:55 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 22:11:57 - INFO - codeparrot_training - Step 27862: {'lr': 0.0004632653368510187, 'samples': 14265856, 'steps': 27862, 'loss/train': 1.8721580505371094}
-03/04/2022 22:12:01 - INFO - codeparrot_training - Step 27863: {'lr': 0.00046326256768734053, 'samples': 14266368, 'steps': 27863, 'loss/train': 1.9082244634628296}
-03/04/2022 22:12:04 - INFO - codeparrot_training - Step 27864: {'lr': 0.0004632597984275695, 'samples': 14266880, 'steps': 27864, 'loss/train': 1.9762349128723145}
-03/04/2022 22:12:05 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/04/2022 22:12:09 - INFO - codeparrot_training - Step 27865: {'lr': 0.00046325702907170697, 'samples': 14267392, 'steps': 27865, 'loss/train': 1.7194844484329224}
-03/04/2022 22:12:12 - INFO - codeparrot_training - Step 27866: {'lr': 0.000463254259619754, 'samples': 14267904, 'steps': 27866, 'loss/train': 2.0421030521392822}
-03/04/2022 22:12:13 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/04/2022 22:12:17 - INFO - codeparrot_training - Step 27867: {'lr': 0.000463251490071712, 'samples': 14268416, 'steps': 27867, 'loss/train': 1.0017389059066772}
-03/04/2022 22:12:21 - INFO - codeparrot_training - Step 27868: {'lr': 0.0004632487204275822, 'samples': 14268928, 'steps': 27868, 'loss/train': 1.224450707435608}
-03/04/2022 22:12:22 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/04/2022 22:12:26 - INFO - codeparrot_training - Step 27869: {'lr': 0.0004632459506873658, 'samples': 14269440, 'steps': 27869, 'loss/train': 1.614784836769104}
-03/04/2022 22:12:29 - INFO - codeparrot_training - Step 27870: {'lr': 0.0004632431808510641, 'samples': 14269952, 'steps': 27870, 'loss/train': 2.2245163917541504}
-03/04/2022 22:12:30 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/04/2022 22:12:34 - INFO - codeparrot_training - Step 27871: {'lr': 0.0004632404109186782, 'samples': 14270464, 'steps': 27871, 'loss/train': 2.0076591968536377}
-03/04/2022 22:12:38 - INFO - codeparrot_training - Step 27872: {'lr': 0.0004632376408902096, 'samples': 14270976, 'steps': 27872, 'loss/train': 0.2839256525039673}
-03/04/2022 22:12:39 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/04/2022 22:12:43 - INFO - codeparrot_training - Step 27873: {'lr': 0.0004632348707656593, 'samples': 14271488, 'steps': 27873, 'loss/train': 1.963602066040039}
-03/04/2022 22:12:46 - INFO - codeparrot_training - Step 27874: {'lr': 0.00046323210054502874, 'samples': 14272000, 'steps': 27874, 'loss/train': 1.855611801147461}
-03/04/2022 22:12:47 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/04/2022 22:12:51 - INFO - codeparrot_training - Step 27875: {'lr': 0.00046322933022831903, 'samples': 14272512, 'steps': 27875, 'loss/train': 1.9642767906188965}
-03/04/2022 22:12:55 - INFO - codeparrot_training - Step 27876: {'lr': 0.0004632265598155315, 'samples': 14273024, 'steps': 27876, 'loss/train': 0.16419781744480133}
-03/04/2022 22:12:56 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 22:13:00 - INFO - codeparrot_training - Step 27877: {'lr': 0.00046322378930666736, 'samples': 14273536, 'steps': 27877, 'loss/train': 2.0920801162719727}
-03/04/2022 22:13:03 - INFO - codeparrot_training - Step 27878: {'lr': 0.0004632210187017278, 'samples': 14274048, 'steps': 27878, 'loss/train': 1.591761589050293}
-03/04/2022 22:13:04 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/04/2022 22:13:08 - INFO - codeparrot_training - Step 27879: {'lr': 0.00046321824800071425, 'samples': 14274560, 'steps': 27879, 'loss/train': 1.734160304069519}
-03/04/2022 22:13:11 - INFO - codeparrot_training - Step 27880: {'lr': 0.0004632154772036279, 'samples': 14275072, 'steps': 27880, 'loss/train': 0.7569888234138489}
-03/04/2022 22:13:12 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/04/2022 22:13:17 - INFO - codeparrot_training - Step 27881: {'lr': 0.0004632127063104698, 'samples': 14275584, 'steps': 27881, 'loss/train': 2.0740513801574707}
-03/04/2022 22:13:20 - INFO - codeparrot_training - Step 27882: {'lr': 0.00046320993532124137, 'samples': 14276096, 'steps': 27882, 'loss/train': 1.583892583847046}
-03/04/2022 22:13:21 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/04/2022 22:13:25 - INFO - codeparrot_training - Step 27883: {'lr': 0.0004632071642359439, 'samples': 14276608, 'steps': 27883, 'loss/train': 0.7008077502250671}
-03/04/2022 22:13:28 - INFO - codeparrot_training - Step 27884: {'lr': 0.0004632043930545785, 'samples': 14277120, 'steps': 27884, 'loss/train': 2.089836597442627}
-03/04/2022 22:13:29 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 22:13:34 - INFO - codeparrot_training - Step 27885: {'lr': 0.00046320162177714653, 'samples': 14277632, 'steps': 27885, 'loss/train': 1.4336007833480835}
-03/04/2022 22:13:37 - INFO - codeparrot_training - Step 27886: {'lr': 0.00046319885040364925, 'samples': 14278144, 'steps': 27886, 'loss/train': 1.7551071643829346}
-03/04/2022 22:13:38 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 22:13:42 - INFO - codeparrot_training - Step 27887: {'lr': 0.00046319607893408776, 'samples': 14278656, 'steps': 27887, 'loss/train': 2.4879469871520996}
-03/04/2022 22:13:46 - INFO - codeparrot_training - Step 27888: {'lr': 0.0004631933073684635, 'samples': 14279168, 'steps': 27888, 'loss/train': 0.281965434551239}
-03/04/2022 22:13:48 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 22:13:51 - INFO - codeparrot_training - Step 27889: {'lr': 0.00046319053570677754, 'samples': 14279680, 'steps': 27889, 'loss/train': 1.8241602182388306}
-03/04/2022 22:13:54 - INFO - codeparrot_training - Step 27890: {'lr': 0.0004631877639490313, 'samples': 14280192, 'steps': 27890, 'loss/train': 1.5852327346801758}
-03/04/2022 22:13:56 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/04/2022 22:13:59 - INFO - codeparrot_training - Step 27891: {'lr': 0.0004631849920952259, 'samples': 14280704, 'steps': 27891, 'loss/train': 1.0881717205047607}
-03/04/2022 22:14:02 - INFO - codeparrot_training - Step 27892: {'lr': 0.0004631822201453626, 'samples': 14281216, 'steps': 27892, 'loss/train': 1.511894702911377}
-03/04/2022 22:14:05 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 22:14:08 - INFO - codeparrot_training - Step 27893: {'lr': 0.0004631794480994427, 'samples': 14281728, 'steps': 27893, 'loss/train': 2.1161115169525146}
-03/04/2022 22:14:11 - INFO - codeparrot_training - Step 27894: {'lr': 0.0004631766759574675, 'samples': 14282240, 'steps': 27894, 'loss/train': 1.7565356492996216}
-03/04/2022 22:14:13 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/04/2022 22:14:16 - INFO - codeparrot_training - Step 27895: {'lr': 0.0004631739037194381, 'samples': 14282752, 'steps': 27895, 'loss/train': 2.4350175857543945}
-03/04/2022 22:14:19 - INFO - codeparrot_training - Step 27896: {'lr': 0.00046317113138535584, 'samples': 14283264, 'steps': 27896, 'loss/train': 1.3406541347503662}
-03/04/2022 22:14:22 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 22:14:25 - INFO - codeparrot_training - Step 27897: {'lr': 0.0004631683589552219, 'samples': 14283776, 'steps': 27897, 'loss/train': 0.17141465842723846}
-03/04/2022 22:14:28 - INFO - codeparrot_training - Step 27898: {'lr': 0.00046316558642903774, 'samples': 14284288, 'steps': 27898, 'loss/train': 1.971772313117981}
-03/04/2022 22:14:31 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/04/2022 22:14:33 - INFO - codeparrot_training - Step 27899: {'lr': 0.0004631628138068043, 'samples': 14284800, 'steps': 27899, 'loss/train': 0.5769757628440857}
-03/04/2022 22:14:36 - INFO - codeparrot_training - Step 27900: {'lr': 0.00046316004108852305, 'samples': 14285312, 'steps': 27900, 'loss/train': 1.3511649370193481}
-03/04/2022 22:14:39 - INFO - codeparrot_training - Step 27901: {'lr': 0.0004631572682741952, 'samples': 14285824, 'steps': 27901, 'loss/train': 1.7435011863708496}
-03/04/2022 22:14:39 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/04/2022 22:14:45 - INFO - codeparrot_training - Step 27902: {'lr': 0.0004631544953638219, 'samples': 14286336, 'steps': 27902, 'loss/train': 0.2282589226961136}
-03/04/2022 22:14:48 - INFO - codeparrot_training - Step 27903: {'lr': 0.00046315172235740455, 'samples': 14286848, 'steps': 27903, 'loss/train': 1.8253365755081177}
-03/04/2022 22:14:48 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/04/2022 22:14:53 - INFO - codeparrot_training - Step 27904: {'lr': 0.0004631489492549443, 'samples': 14287360, 'steps': 27904, 'loss/train': 1.9457635879516602}
-03/04/2022 22:14:57 - INFO - codeparrot_training - Step 27905: {'lr': 0.00046314617605644243, 'samples': 14287872, 'steps': 27905, 'loss/train': 1.4312101602554321}
-03/04/2022 22:14:57 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/04/2022 22:15:02 - INFO - codeparrot_training - Step 27906: {'lr': 0.0004631434027619001, 'samples': 14288384, 'steps': 27906, 'loss/train': 1.775363564491272}
-03/04/2022 22:15:05 - INFO - codeparrot_training - Step 27907: {'lr': 0.0004631406293713188, 'samples': 14288896, 'steps': 27907, 'loss/train': 2.2983882427215576}
-03/04/2022 22:15:06 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/04/2022 22:15:10 - INFO - codeparrot_training - Step 27908: {'lr': 0.0004631378558846995, 'samples': 14289408, 'steps': 27908, 'loss/train': 1.6185795068740845}
-03/04/2022 22:15:14 - INFO - codeparrot_training - Step 27909: {'lr': 0.00046313508230204364, 'samples': 14289920, 'steps': 27909, 'loss/train': 1.8852150440216064}
-03/04/2022 22:15:14 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/04/2022 22:15:19 - INFO - codeparrot_training - Step 27910: {'lr': 0.00046313230862335235, 'samples': 14290432, 'steps': 27910, 'loss/train': 1.721232533454895}
-03/04/2022 22:15:22 - INFO - codeparrot_training - Step 27911: {'lr': 0.000463129534848627, 'samples': 14290944, 'steps': 27911, 'loss/train': 1.9536317586898804}
-03/04/2022 22:15:24 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/04/2022 22:15:28 - INFO - codeparrot_training - Step 27912: {'lr': 0.0004631267609778687, 'samples': 14291456, 'steps': 27912, 'loss/train': 1.6025091409683228}
-03/04/2022 22:15:31 - INFO - codeparrot_training - Step 27913: {'lr': 0.0004631239870110788, 'samples': 14291968, 'steps': 27913, 'loss/train': 2.11519193649292}
-03/04/2022 22:15:33 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/04/2022 22:15:36 - INFO - codeparrot_training - Step 27914: {'lr': 0.00046312121294825846, 'samples': 14292480, 'steps': 27914, 'loss/train': 2.1453258991241455}
-03/04/2022 22:15:40 - INFO - codeparrot_training - Step 27915: {'lr': 0.00046311843878940904, 'samples': 14292992, 'steps': 27915, 'loss/train': 2.2039995193481445}
-03/04/2022 22:15:41 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/04/2022 22:15:45 - INFO - codeparrot_training - Step 27916: {'lr': 0.0004631156645345318, 'samples': 14293504, 'steps': 27916, 'loss/train': 1.5869899988174438}
-03/04/2022 22:15:48 - INFO - codeparrot_training - Step 27917: {'lr': 0.0004631128901836278, 'samples': 14294016, 'steps': 27917, 'loss/train': 1.9840222597122192}
-03/04/2022 22:15:50 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/04/2022 22:15:53 - INFO - codeparrot_training - Step 27918: {'lr': 0.0004631101157366985, 'samples': 14294528, 'steps': 27918, 'loss/train': 2.6739704608917236}
-03/04/2022 22:15:56 - INFO - codeparrot_training - Step 27919: {'lr': 0.0004631073411937451, 'samples': 14295040, 'steps': 27919, 'loss/train': 1.8380647897720337}
-03/04/2022 22:15:58 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/04/2022 22:16:02 - INFO - codeparrot_training - Step 27920: {'lr': 0.00046310456655476875, 'samples': 14295552, 'steps': 27920, 'loss/train': 1.934631586074829}
-03/04/2022 22:16:05 - INFO - codeparrot_training - Step 27921: {'lr': 0.0004631017918197709, 'samples': 14296064, 'steps': 27921, 'loss/train': 2.0217432975769043}
-03/04/2022 22:16:06 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/04/2022 22:16:10 - INFO - codeparrot_training - Step 27922: {'lr': 0.00046309901698875244, 'samples': 14296576, 'steps': 27922, 'loss/train': 1.850279688835144}
-03/04/2022 22:16:13 - INFO - codeparrot_training - Step 27923: {'lr': 0.00046309624206171505, 'samples': 14297088, 'steps': 27923, 'loss/train': 0.8564593195915222}
-03/04/2022 22:16:15 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/04/2022 22:16:19 - INFO - codeparrot_training - Step 27924: {'lr': 0.00046309346703865973, 'samples': 14297600, 'steps': 27924, 'loss/train': 1.8524950742721558}
-03/04/2022 22:16:22 - INFO - codeparrot_training - Step 27925: {'lr': 0.00046309069191958775, 'samples': 14298112, 'steps': 27925, 'loss/train': 1.1815844774246216}
-03/04/2022 22:16:23 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 22:16:27 - INFO - codeparrot_training - Step 27926: {'lr': 0.00046308791670450033, 'samples': 14298624, 'steps': 27926, 'loss/train': 1.0284316539764404}
-03/04/2022 22:16:30 - INFO - codeparrot_training - Step 27927: {'lr': 0.00046308514139339896, 'samples': 14299136, 'steps': 27927, 'loss/train': 1.700566053390503}
-03/04/2022 22:16:32 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/04/2022 22:16:35 - INFO - codeparrot_training - Step 27928: {'lr': 0.0004630823659862846, 'samples': 14299648, 'steps': 27928, 'loss/train': 2.0303456783294678}
-03/04/2022 22:16:39 - INFO - codeparrot_training - Step 27929: {'lr': 0.0004630795904831586, 'samples': 14300160, 'steps': 27929, 'loss/train': 1.8341206312179565}
-03/04/2022 22:16:40 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/04/2022 22:16:44 - INFO - codeparrot_training - Step 27930: {'lr': 0.0004630768148840223, 'samples': 14300672, 'steps': 27930, 'loss/train': 0.9762017130851746}
-03/04/2022 22:16:47 - INFO - codeparrot_training - Step 27931: {'lr': 0.0004630740391888768, 'samples': 14301184, 'steps': 27931, 'loss/train': 1.5248593091964722}
-03/04/2022 22:16:49 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/04/2022 22:16:52 - INFO - codeparrot_training - Step 27932: {'lr': 0.0004630712633977234, 'samples': 14301696, 'steps': 27932, 'loss/train': 0.806500256061554}
-03/04/2022 22:16:56 - INFO - codeparrot_training - Step 27933: {'lr': 0.00046306848751056346, 'samples': 14302208, 'steps': 27933, 'loss/train': 1.718628168106079}
-03/04/2022 22:16:57 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/04/2022 22:17:01 - INFO - codeparrot_training - Step 27934: {'lr': 0.0004630657115273981, 'samples': 14302720, 'steps': 27934, 'loss/train': 1.8251714706420898}
-03/04/2022 22:17:04 - INFO - codeparrot_training - Step 27935: {'lr': 0.0004630629354482286, 'samples': 14303232, 'steps': 27935, 'loss/train': 2.0446701049804688}
-03/04/2022 22:17:05 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/04/2022 22:17:09 - INFO - codeparrot_training - Step 27936: {'lr': 0.00046306015927305633, 'samples': 14303744, 'steps': 27936, 'loss/train': 2.2135467529296875}
-03/04/2022 22:17:12 - INFO - codeparrot_training - Step 27937: {'lr': 0.0004630573830018824, 'samples': 14304256, 'steps': 27937, 'loss/train': 1.7606581449508667}
-03/04/2022 22:17:13 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/04/2022 22:17:18 - INFO - codeparrot_training - Step 27938: {'lr': 0.00046305460663470803, 'samples': 14304768, 'steps': 27938, 'loss/train': 2.1651854515075684}
-03/04/2022 22:17:21 - INFO - codeparrot_training - Step 27939: {'lr': 0.0004630518301715346, 'samples': 14305280, 'steps': 27939, 'loss/train': 1.3201555013656616}
-03/04/2022 22:17:22 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/04/2022 22:17:26 - INFO - codeparrot_training - Step 27940: {'lr': 0.00046304905361236335, 'samples': 14305792, 'steps': 27940, 'loss/train': 1.4048999547958374}
-03/04/2022 22:17:29 - INFO - codeparrot_training - Step 27941: {'lr': 0.00046304627695719535, 'samples': 14306304, 'steps': 27941, 'loss/train': 2.0570197105407715}
-03/04/2022 22:17:30 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 22:17:35 - INFO - codeparrot_training - Step 27942: {'lr': 0.0004630435002060321, 'samples': 14306816, 'steps': 27942, 'loss/train': 2.0686562061309814}
-03/04/2022 22:17:38 - INFO - codeparrot_training - Step 27943: {'lr': 0.0004630407233588747, 'samples': 14307328, 'steps': 27943, 'loss/train': 1.516229271888733}
-03/04/2022 22:17:39 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/04/2022 22:17:43 - INFO - codeparrot_training - Step 27944: {'lr': 0.00046303794641572445, 'samples': 14307840, 'steps': 27944, 'loss/train': 2.164670467376709}
-03/04/2022 22:17:46 - INFO - codeparrot_training - Step 27945: {'lr': 0.0004630351693765825, 'samples': 14308352, 'steps': 27945, 'loss/train': 1.1335526704788208}
-03/04/2022 22:17:47 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/04/2022 22:17:52 - INFO - codeparrot_training - Step 27946: {'lr': 0.0004630323922414503, 'samples': 14308864, 'steps': 27946, 'loss/train': 1.6934776306152344}
-03/04/2022 22:17:55 - INFO - codeparrot_training - Step 27947: {'lr': 0.00046302961501032896, 'samples': 14309376, 'steps': 27947, 'loss/train': 1.3476037979125977}
-03/04/2022 22:17:55 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/04/2022 22:18:00 - INFO - codeparrot_training - Step 27948: {'lr': 0.00046302683768321973, 'samples': 14309888, 'steps': 27948, 'loss/train': 1.55656099319458}
-03/04/2022 22:18:03 - INFO - codeparrot_training - Step 27949: {'lr': 0.00046302406026012396, 'samples': 14310400, 'steps': 27949, 'loss/train': 0.8655235767364502}
-03/04/2022 22:18:04 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 22:18:09 - INFO - codeparrot_training - Step 27950: {'lr': 0.0004630212827410428, 'samples': 14310912, 'steps': 27950, 'loss/train': 1.631001353263855}
-03/04/2022 22:18:12 - INFO - codeparrot_training - Step 27951: {'lr': 0.00046301850512597755, 'samples': 14311424, 'steps': 27951, 'loss/train': 2.3786988258361816}
-03/04/2022 22:18:12 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/04/2022 22:18:17 - INFO - codeparrot_training - Step 27952: {'lr': 0.0004630157274149294, 'samples': 14311936, 'steps': 27952, 'loss/train': 1.6180237531661987}
-03/04/2022 22:18:20 - INFO - codeparrot_training - Step 27953: {'lr': 0.0004630129496078997, 'samples': 14312448, 'steps': 27953, 'loss/train': 1.5433504581451416}
-03/04/2022 22:18:21 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 22:18:26 - INFO - codeparrot_training - Step 27954: {'lr': 0.00046301017170488965, 'samples': 14312960, 'steps': 27954, 'loss/train': 2.174212694168091}
-03/04/2022 22:18:29 - INFO - codeparrot_training - Step 27955: {'lr': 0.0004630073937059005, 'samples': 14313472, 'steps': 27955, 'loss/train': 1.6526682376861572}
-03/04/2022 22:18:29 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/04/2022 22:18:34 - INFO - codeparrot_training - Step 27956: {'lr': 0.0004630046156109334, 'samples': 14313984, 'steps': 27956, 'loss/train': 1.9537677764892578}
-03/04/2022 22:18:37 - INFO - codeparrot_training - Step 27957: {'lr': 0.0004630018374199899, 'samples': 14314496, 'steps': 27957, 'loss/train': 1.1786617040634155}
-03/04/2022 22:18:38 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/04/2022 22:18:43 - INFO - codeparrot_training - Step 27958: {'lr': 0.00046299905913307096, 'samples': 14315008, 'steps': 27958, 'loss/train': 1.3849451541900635}
-03/04/2022 22:18:46 - INFO - codeparrot_training - Step 27959: {'lr': 0.00046299628075017785, 'samples': 14315520, 'steps': 27959, 'loss/train': 2.0837199687957764}
-03/04/2022 22:18:47 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/04/2022 22:18:51 - INFO - codeparrot_training - Step 27960: {'lr': 0.000462993502271312, 'samples': 14316032, 'steps': 27960, 'loss/train': 1.7922285795211792}
-03/04/2022 22:18:54 - INFO - codeparrot_training - Step 27961: {'lr': 0.00046299072369647453, 'samples': 14316544, 'steps': 27961, 'loss/train': 2.1117124557495117}
-03/04/2022 22:18:56 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/04/2022 22:19:00 - INFO - codeparrot_training - Step 27962: {'lr': 0.00046298794502566676, 'samples': 14317056, 'steps': 27962, 'loss/train': 1.7747284173965454}
-03/04/2022 22:19:03 - INFO - codeparrot_training - Step 27963: {'lr': 0.0004629851662588899, 'samples': 14317568, 'steps': 27963, 'loss/train': 1.6693531274795532}
-03/04/2022 22:19:04 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/04/2022 22:19:08 - INFO - codeparrot_training - Step 27964: {'lr': 0.00046298238739614524, 'samples': 14318080, 'steps': 27964, 'loss/train': 0.9834689497947693}
-03/04/2022 22:19:11 - INFO - codeparrot_training - Step 27965: {'lr': 0.0004629796084374339, 'samples': 14318592, 'steps': 27965, 'loss/train': 0.5830991268157959}
-03/04/2022 22:19:13 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/04/2022 22:19:16 - INFO - codeparrot_training - Step 27966: {'lr': 0.00046297682938275733, 'samples': 14319104, 'steps': 27966, 'loss/train': 1.0919314622879028}
-03/04/2022 22:19:20 - INFO - codeparrot_training - Step 27967: {'lr': 0.0004629740502321167, 'samples': 14319616, 'steps': 27967, 'loss/train': 3.1301751136779785}
-03/04/2022 22:19:22 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/04/2022 22:19:25 - INFO - codeparrot_training - Step 27968: {'lr': 0.00046297127098551317, 'samples': 14320128, 'steps': 27968, 'loss/train': 2.1403682231903076}
-03/04/2022 22:19:28 - INFO - codeparrot_training - Step 27969: {'lr': 0.00046296849164294816, 'samples': 14320640, 'steps': 27969, 'loss/train': 1.8543730974197388}
-03/04/2022 22:19:30 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 22:19:34 - INFO - codeparrot_training - Step 27970: {'lr': 0.00046296571220442274, 'samples': 14321152, 'steps': 27970, 'loss/train': 0.5319598317146301}
-03/04/2022 22:19:37 - INFO - codeparrot_training - Step 27971: {'lr': 0.00046296293266993833, 'samples': 14321664, 'steps': 27971, 'loss/train': 2.1653618812561035}
-03/04/2022 22:19:39 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 22:19:42 - INFO - codeparrot_training - Step 27972: {'lr': 0.00046296015303949606, 'samples': 14322176, 'steps': 27972, 'loss/train': 2.0075464248657227}
-03/04/2022 22:19:45 - INFO - codeparrot_training - Step 27973: {'lr': 0.0004629573733130973, 'samples': 14322688, 'steps': 27973, 'loss/train': 2.2769131660461426}
-03/04/2022 22:19:47 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/04/2022 22:19:50 - INFO - codeparrot_training - Step 27974: {'lr': 0.00046295459349074316, 'samples': 14323200, 'steps': 27974, 'loss/train': 1.8948166370391846}
-03/04/2022 22:19:54 - INFO - codeparrot_training - Step 27975: {'lr': 0.000462951813572435, 'samples': 14323712, 'steps': 27975, 'loss/train': 2.2822437286376953}
-03/04/2022 22:19:55 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 22:19:59 - INFO - codeparrot_training - Step 27976: {'lr': 0.00046294903355817397, 'samples': 14324224, 'steps': 27976, 'loss/train': 0.23006807267665863}
-03/04/2022 22:20:02 - INFO - codeparrot_training - Step 27977: {'lr': 0.0004629462534479615, 'samples': 14324736, 'steps': 27977, 'loss/train': 2.0448102951049805}
-03/04/2022 22:20:04 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/04/2022 22:20:07 - INFO - codeparrot_training - Step 27978: {'lr': 0.0004629434732417986, 'samples': 14325248, 'steps': 27978, 'loss/train': 1.0648891925811768}
-03/04/2022 22:20:11 - INFO - codeparrot_training - Step 27979: {'lr': 0.0004629406929396868, 'samples': 14325760, 'steps': 27979, 'loss/train': 2.147395610809326}
-03/04/2022 22:20:12 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/04/2022 22:20:17 - INFO - codeparrot_training - Step 27980: {'lr': 0.00046293791254162713, 'samples': 14326272, 'steps': 27980, 'loss/train': 1.997711181640625}
-03/04/2022 22:20:20 - INFO - codeparrot_training - Step 27981: {'lr': 0.0004629351320476209, 'samples': 14326784, 'steps': 27981, 'loss/train': 1.9108020067214966}
-03/04/2022 22:20:23 - INFO - codeparrot_training - Step 27982: {'lr': 0.00046293235145766955, 'samples': 14327296, 'steps': 27982, 'loss/train': 2.2130215167999268}
-03/04/2022 22:20:25 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/04/2022 22:20:29 - INFO - codeparrot_training - Step 27983: {'lr': 0.000462929570771774, 'samples': 14327808, 'steps': 27983, 'loss/train': 1.697169303894043}
-03/04/2022 22:20:32 - INFO - codeparrot_training - Step 27984: {'lr': 0.0004629267899899358, 'samples': 14328320, 'steps': 27984, 'loss/train': 2.050527811050415}
-03/04/2022 22:20:34 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/04/2022 22:20:37 - INFO - codeparrot_training - Step 27985: {'lr': 0.00046292400911215594, 'samples': 14328832, 'steps': 27985, 'loss/train': 2.893350601196289}
-03/04/2022 22:20:40 - INFO - codeparrot_training - Step 27986: {'lr': 0.00046292122813843586, 'samples': 14329344, 'steps': 27986, 'loss/train': 1.1114239692687988}
-03/04/2022 22:20:43 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 22:20:46 - INFO - codeparrot_training - Step 27987: {'lr': 0.00046291844706877674, 'samples': 14329856, 'steps': 27987, 'loss/train': 1.4518760442733765}
-03/04/2022 22:20:49 - INFO - codeparrot_training - Step 27988: {'lr': 0.0004629156659031799, 'samples': 14330368, 'steps': 27988, 'loss/train': 1.8703193664550781}
-03/04/2022 22:20:52 - INFO - codeparrot_training - Step 27989: {'lr': 0.0004629128846416465, 'samples': 14330880, 'steps': 27989, 'loss/train': 0.9988330006599426}
-03/04/2022 22:20:53 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 22:20:58 - INFO - codeparrot_training - Step 27990: {'lr': 0.00046291010328417784, 'samples': 14331392, 'steps': 27990, 'loss/train': 1.769507884979248}
-03/04/2022 22:21:01 - INFO - codeparrot_training - Step 27991: {'lr': 0.0004629073218307752, 'samples': 14331904, 'steps': 27991, 'loss/train': 2.7357914447784424}
-03/04/2022 22:21:01 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/04/2022 22:21:06 - INFO - codeparrot_training - Step 27992: {'lr': 0.0004629045402814398, 'samples': 14332416, 'steps': 27992, 'loss/train': 1.180209755897522}
-03/04/2022 22:21:09 - INFO - codeparrot_training - Step 27993: {'lr': 0.0004629017586361729, 'samples': 14332928, 'steps': 27993, 'loss/train': 1.7916556596755981}
-03/04/2022 22:21:09 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/04/2022 22:21:14 - INFO - codeparrot_training - Step 27994: {'lr': 0.0004628989768949757, 'samples': 14333440, 'steps': 27994, 'loss/train': 1.5045077800750732}
-03/04/2022 22:21:17 - INFO - codeparrot_training - Step 27995: {'lr': 0.0004628961950578496, 'samples': 14333952, 'steps': 27995, 'loss/train': 1.9115160703659058}
-03/04/2022 22:21:18 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 22:21:23 - INFO - codeparrot_training - Step 27996: {'lr': 0.00046289341312479574, 'samples': 14334464, 'steps': 27996, 'loss/train': 1.8505536317825317}
-03/04/2022 22:21:26 - INFO - codeparrot_training - Step 27997: {'lr': 0.0004628906310958153, 'samples': 14334976, 'steps': 27997, 'loss/train': 1.650133728981018}
-03/04/2022 22:21:26 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 22:21:31 - INFO - codeparrot_training - Step 27998: {'lr': 0.00046288784897090973, 'samples': 14335488, 'steps': 27998, 'loss/train': 0.48331236839294434}
-03/04/2022 22:21:34 - INFO - codeparrot_training - Step 27999: {'lr': 0.00046288506675008014, 'samples': 14336000, 'steps': 27999, 'loss/train': 1.9386268854141235}
-03/04/2022 22:21:34 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 22:21:40 - INFO - codeparrot_training - Step 28000: {'lr': 0.0004628822844333278, 'samples': 14336512, 'steps': 28000, 'loss/train': 2.1001925468444824}
-03/04/2022 22:21:43 - INFO - codeparrot_training - Step 28001: {'lr': 0.0004628795020206541, 'samples': 14337024, 'steps': 28001, 'loss/train': 2.069309949874878}
-03/04/2022 22:21:43 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/04/2022 22:21:48 - INFO - codeparrot_training - Step 28002: {'lr': 0.00046287671951206004, 'samples': 14337536, 'steps': 28002, 'loss/train': 1.4137552976608276}
-03/04/2022 22:21:51 - INFO - codeparrot_training - Step 28003: {'lr': 0.0004628739369075471, 'samples': 14338048, 'steps': 28003, 'loss/train': 2.2543540000915527}
-03/04/2022 22:21:51 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 22:21:57 - INFO - codeparrot_training - Step 28004: {'lr': 0.00046287115420711643, 'samples': 14338560, 'steps': 28004, 'loss/train': 1.3900833129882812}
-03/04/2022 22:22:02 - INFO - codeparrot_training - Step 28005: {'lr': 0.00046286837141076934, 'samples': 14339072, 'steps': 28005, 'loss/train': 1.8759207725524902}
-03/04/2022 22:22:05 - INFO - codeparrot_training - Step 28006: {'lr': 0.0004628655885185069, 'samples': 14339584, 'steps': 28006, 'loss/train': 1.685986042022705}
-03/04/2022 22:22:08 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 22:22:10 - INFO - codeparrot_training - Step 28007: {'lr': 0.00046286280553033067, 'samples': 14340096, 'steps': 28007, 'loss/train': 2.1517112255096436}
-03/04/2022 22:22:14 - INFO - codeparrot_training - Step 28008: {'lr': 0.0004628600224462417, 'samples': 14340608, 'steps': 28008, 'loss/train': 1.8084824085235596}
-03/04/2022 22:22:17 - INFO - codeparrot_training - Step 28009: {'lr': 0.00046285723926624126, 'samples': 14341120, 'steps': 28009, 'loss/train': 2.0590226650238037}
-03/04/2022 22:22:17 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 22:22:22 - INFO - codeparrot_training - Step 28010: {'lr': 0.00046285445599033063, 'samples': 14341632, 'steps': 28010, 'loss/train': 2.651611089706421}
-03/04/2022 22:22:25 - INFO - codeparrot_training - Step 28011: {'lr': 0.00046285167261851114, 'samples': 14342144, 'steps': 28011, 'loss/train': 1.8674241304397583}
-03/04/2022 22:22:25 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/04/2022 22:22:31 - INFO - codeparrot_training - Step 28012: {'lr': 0.00046284888915078384, 'samples': 14342656, 'steps': 28012, 'loss/train': 1.6005983352661133}
-03/04/2022 22:22:34 - INFO - codeparrot_training - Step 28013: {'lr': 0.00046284610558715024, 'samples': 14343168, 'steps': 28013, 'loss/train': 1.6902517080307007}
-03/04/2022 22:22:34 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 22:22:39 - INFO - codeparrot_training - Step 28014: {'lr': 0.00046284332192761136, 'samples': 14343680, 'steps': 28014, 'loss/train': 2.5007622241973877}
-03/04/2022 22:22:42 - INFO - codeparrot_training - Step 28015: {'lr': 0.0004628405381721686, 'samples': 14344192, 'steps': 28015, 'loss/train': 1.9219526052474976}
-03/04/2022 22:22:42 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 22:22:48 - INFO - codeparrot_training - Step 28016: {'lr': 0.00046283775432082327, 'samples': 14344704, 'steps': 28016, 'loss/train': 1.7110927104949951}
-03/04/2022 22:22:51 - INFO - codeparrot_training - Step 28017: {'lr': 0.0004628349703735765, 'samples': 14345216, 'steps': 28017, 'loss/train': 2.3022358417510986}
-03/04/2022 22:22:51 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/04/2022 22:22:56 - INFO - codeparrot_training - Step 28018: {'lr': 0.0004628321863304295, 'samples': 14345728, 'steps': 28018, 'loss/train': 2.0060653686523438}
-03/04/2022 22:22:59 - INFO - codeparrot_training - Step 28019: {'lr': 0.00046282940219138366, 'samples': 14346240, 'steps': 28019, 'loss/train': 1.5071872472763062}
-03/04/2022 22:22:59 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/04/2022 22:23:05 - INFO - codeparrot_training - Step 28020: {'lr': 0.0004628266179564401, 'samples': 14346752, 'steps': 28020, 'loss/train': 0.5800417065620422}
-03/04/2022 22:23:08 - INFO - codeparrot_training - Step 28021: {'lr': 0.0004628238336256002, 'samples': 14347264, 'steps': 28021, 'loss/train': 2.117781639099121}
-03/04/2022 22:23:08 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/04/2022 22:23:13 - INFO - codeparrot_training - Step 28022: {'lr': 0.0004628210491988652, 'samples': 14347776, 'steps': 28022, 'loss/train': 1.8395440578460693}
-03/04/2022 22:23:16 - INFO - codeparrot_training - Step 28023: {'lr': 0.0004628182646762363, 'samples': 14348288, 'steps': 28023, 'loss/train': 2.2641303539276123}
-03/04/2022 22:23:16 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/04/2022 22:23:22 - INFO - codeparrot_training - Step 28024: {'lr': 0.00046281548005771476, 'samples': 14348800, 'steps': 28024, 'loss/train': 1.0367774963378906}
-03/04/2022 22:23:25 - INFO - codeparrot_training - Step 28025: {'lr': 0.0004628126953433018, 'samples': 14349312, 'steps': 28025, 'loss/train': 1.7554303407669067}
-03/04/2022 22:23:25 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/04/2022 22:23:30 - INFO - codeparrot_training - Step 28026: {'lr': 0.00046280991053299883, 'samples': 14349824, 'steps': 28026, 'loss/train': 1.0367465019226074}
-03/04/2022 22:23:33 - INFO - codeparrot_training - Step 28027: {'lr': 0.00046280712562680695, 'samples': 14350336, 'steps': 28027, 'loss/train': 1.6584105491638184}
-03/04/2022 22:23:33 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 22:23:39 - INFO - codeparrot_training - Step 28028: {'lr': 0.0004628043406247274, 'samples': 14350848, 'steps': 28028, 'loss/train': 1.6952285766601562}
-03/04/2022 22:23:42 - INFO - codeparrot_training - Step 28029: {'lr': 0.0004628015555267616, 'samples': 14351360, 'steps': 28029, 'loss/train': 2.2824454307556152}
-03/04/2022 22:23:42 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/04/2022 22:23:47 - INFO - codeparrot_training - Step 28030: {'lr': 0.00046279877033291063, 'samples': 14351872, 'steps': 28030, 'loss/train': 1.4954257011413574}
-03/04/2022 22:23:51 - INFO - codeparrot_training - Step 28031: {'lr': 0.0004627959850431759, 'samples': 14352384, 'steps': 28031, 'loss/train': 1.7569440603256226}
-03/04/2022 22:23:51 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/04/2022 22:23:56 - INFO - codeparrot_training - Step 28032: {'lr': 0.0004627931996575585, 'samples': 14352896, 'steps': 28032, 'loss/train': 1.4409431219100952}
-03/04/2022 22:23:59 - INFO - codeparrot_training - Step 28033: {'lr': 0.0004627904141760598, 'samples': 14353408, 'steps': 28033, 'loss/train': 1.2438899278640747}
-03/04/2022 22:24:00 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 22:24:05 - INFO - codeparrot_training - Step 28034: {'lr': 0.000462787628598681, 'samples': 14353920, 'steps': 28034, 'loss/train': 1.4846700429916382}
-03/04/2022 22:24:08 - INFO - codeparrot_training - Step 28035: {'lr': 0.00046278484292542346, 'samples': 14354432, 'steps': 28035, 'loss/train': 0.6266364455223083}
-03/04/2022 22:24:09 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/04/2022 22:24:13 - INFO - codeparrot_training - Step 28036: {'lr': 0.0004627820571562883, 'samples': 14354944, 'steps': 28036, 'loss/train': 2.7089147567749023}
-03/04/2022 22:24:16 - INFO - codeparrot_training - Step 28037: {'lr': 0.0004627792712912768, 'samples': 14355456, 'steps': 28037, 'loss/train': 1.5414420366287231}
-03/04/2022 22:24:17 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/04/2022 22:24:22 - INFO - codeparrot_training - Step 28038: {'lr': 0.0004627764853303902, 'samples': 14355968, 'steps': 28038, 'loss/train': 1.9628666639328003}
-03/04/2022 22:24:25 - INFO - codeparrot_training - Step 28039: {'lr': 0.00046277369927362987, 'samples': 14356480, 'steps': 28039, 'loss/train': 1.6780688762664795}
-03/04/2022 22:24:26 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/04/2022 22:24:30 - INFO - codeparrot_training - Step 28040: {'lr': 0.00046277091312099704, 'samples': 14356992, 'steps': 28040, 'loss/train': 1.309260606765747}
-03/04/2022 22:24:33 - INFO - codeparrot_training - Step 28041: {'lr': 0.00046276812687249283, 'samples': 14357504, 'steps': 28041, 'loss/train': 1.8374944925308228}
-03/04/2022 22:24:34 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 22:24:39 - INFO - codeparrot_training - Step 28042: {'lr': 0.00046276534052811863, 'samples': 14358016, 'steps': 28042, 'loss/train': 2.0515449047088623}
-03/04/2022 22:24:42 - INFO - codeparrot_training - Step 28043: {'lr': 0.00046276255408787565, 'samples': 14358528, 'steps': 28043, 'loss/train': 1.48404061794281}
-03/04/2022 22:24:43 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/04/2022 22:24:47 - INFO - codeparrot_training - Step 28044: {'lr': 0.0004627597675517652, 'samples': 14359040, 'steps': 28044, 'loss/train': 1.839157223701477}
-03/04/2022 22:24:50 - INFO - codeparrot_training - Step 28045: {'lr': 0.00046275698091978836, 'samples': 14359552, 'steps': 28045, 'loss/train': 2.3646225929260254}
-03/04/2022 22:24:51 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 22:24:56 - INFO - codeparrot_training - Step 28046: {'lr': 0.0004627541941919466, 'samples': 14360064, 'steps': 28046, 'loss/train': 2.2540459632873535}
-03/04/2022 22:24:59 - INFO - codeparrot_training - Step 28047: {'lr': 0.00046275140736824104, 'samples': 14360576, 'steps': 28047, 'loss/train': 0.4593677222728729}
-03/04/2022 22:25:00 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/04/2022 22:25:04 - INFO - codeparrot_training - Step 28048: {'lr': 0.000462748620448673, 'samples': 14361088, 'steps': 28048, 'loss/train': 1.189672589302063}
-03/04/2022 22:25:07 - INFO - codeparrot_training - Step 28049: {'lr': 0.0004627458334332437, 'samples': 14361600, 'steps': 28049, 'loss/train': 1.681689739227295}
-03/04/2022 22:25:08 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/04/2022 22:25:12 - INFO - codeparrot_training - Step 28050: {'lr': 0.0004627430463219544, 'samples': 14362112, 'steps': 28050, 'loss/train': 1.5495625734329224}
-03/04/2022 22:25:16 - INFO - codeparrot_training - Step 28051: {'lr': 0.0004627402591148064, 'samples': 14362624, 'steps': 28051, 'loss/train': 2.1977484226226807}
-03/04/2022 22:25:17 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 22:25:21 - INFO - codeparrot_training - Step 28052: {'lr': 0.0004627374718118009, 'samples': 14363136, 'steps': 28052, 'loss/train': 3.241132974624634}
-03/04/2022 22:25:24 - INFO - codeparrot_training - Step 28053: {'lr': 0.0004627346844129392, 'samples': 14363648, 'steps': 28053, 'loss/train': 1.9198987483978271}
-03/04/2022 22:25:25 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/04/2022 22:25:30 - INFO - codeparrot_training - Step 28054: {'lr': 0.0004627318969182225, 'samples': 14364160, 'steps': 28054, 'loss/train': 2.144991874694824}
-03/04/2022 22:25:33 - INFO - codeparrot_training - Step 28055: {'lr': 0.0004627291093276521, 'samples': 14364672, 'steps': 28055, 'loss/train': 1.6902788877487183}
-03/04/2022 22:25:34 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/04/2022 22:25:38 - INFO - codeparrot_training - Step 28056: {'lr': 0.0004627263216412292, 'samples': 14365184, 'steps': 28056, 'loss/train': 1.9141831398010254}
-03/04/2022 22:25:41 - INFO - codeparrot_training - Step 28057: {'lr': 0.00046272353385895515, 'samples': 14365696, 'steps': 28057, 'loss/train': 2.4049510955810547}
-03/04/2022 22:25:42 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/04/2022 22:25:46 - INFO - codeparrot_training - Step 28058: {'lr': 0.0004627207459808312, 'samples': 14366208, 'steps': 28058, 'loss/train': 1.802938461303711}
-03/04/2022 22:25:50 - INFO - codeparrot_training - Step 28059: {'lr': 0.00046271795800685854, 'samples': 14366720, 'steps': 28059, 'loss/train': 1.8242777585983276}
-03/04/2022 22:25:51 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/04/2022 22:25:55 - INFO - codeparrot_training - Step 28060: {'lr': 0.00046271516993703844, 'samples': 14367232, 'steps': 28060, 'loss/train': 1.6778475046157837}
-03/04/2022 22:25:58 - INFO - codeparrot_training - Step 28061: {'lr': 0.00046271238177137216, 'samples': 14367744, 'steps': 28061, 'loss/train': 2.5240142345428467}
-03/04/2022 22:25:59 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/04/2022 22:26:03 - INFO - codeparrot_training - Step 28062: {'lr': 0.00046270959350986095, 'samples': 14368256, 'steps': 28062, 'loss/train': 1.4100782871246338}
-03/04/2022 22:26:06 - INFO - codeparrot_training - Step 28063: {'lr': 0.0004627068051525061, 'samples': 14368768, 'steps': 28063, 'loss/train': 0.25495561957359314}
-03/04/2022 22:26:08 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/04/2022 22:26:12 - INFO - codeparrot_training - Step 28064: {'lr': 0.00046270401669930885, 'samples': 14369280, 'steps': 28064, 'loss/train': 2.4806411266326904}
-03/04/2022 22:26:15 - INFO - codeparrot_training - Step 28065: {'lr': 0.0004627012281502704, 'samples': 14369792, 'steps': 28065, 'loss/train': 1.7448320388793945}
-03/04/2022 22:26:16 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/04/2022 22:26:20 - INFO - codeparrot_training - Step 28066: {'lr': 0.00046269843950539214, 'samples': 14370304, 'steps': 28066, 'loss/train': 2.0208756923675537}
-03/04/2022 22:26:23 - INFO - codeparrot_training - Step 28067: {'lr': 0.00046269565076467517, 'samples': 14370816, 'steps': 28067, 'loss/train': 1.8965331315994263}
-03/04/2022 22:26:25 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/04/2022 22:26:29 - INFO - codeparrot_training - Step 28068: {'lr': 0.0004626928619281209, 'samples': 14371328, 'steps': 28068, 'loss/train': 1.8070625066757202}
-03/04/2022 22:26:32 - INFO - codeparrot_training - Step 28069: {'lr': 0.0004626900729957305, 'samples': 14371840, 'steps': 28069, 'loss/train': 1.7898110151290894}
-03/04/2022 22:26:33 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/04/2022 22:26:37 - INFO - codeparrot_training - Step 28070: {'lr': 0.00046268728396750515, 'samples': 14372352, 'steps': 28070, 'loss/train': 2.071082830429077}
-03/04/2022 22:26:40 - INFO - codeparrot_training - Step 28071: {'lr': 0.0004626844948434462, 'samples': 14372864, 'steps': 28071, 'loss/train': 1.9518851041793823}
-03/04/2022 22:26:42 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 22:26:46 - INFO - codeparrot_training - Step 28072: {'lr': 0.00046268170562355497, 'samples': 14373376, 'steps': 28072, 'loss/train': 1.5169181823730469}
-03/04/2022 22:26:49 - INFO - codeparrot_training - Step 28073: {'lr': 0.0004626789163078327, 'samples': 14373888, 'steps': 28073, 'loss/train': 2.2166080474853516}
-03/04/2022 22:26:52 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/04/2022 22:26:54 - INFO - codeparrot_training - Step 28074: {'lr': 0.00046267612689628046, 'samples': 14374400, 'steps': 28074, 'loss/train': 6.40658712387085}
-03/04/2022 22:26:57 - INFO - codeparrot_training - Step 28075: {'lr': 0.00046267333738889973, 'samples': 14374912, 'steps': 28075, 'loss/train': 1.5569745302200317}
-03/04/2022 22:27:01 - INFO - codeparrot_training - Step 28076: {'lr': 0.00046267054778569163, 'samples': 14375424, 'steps': 28076, 'loss/train': 2.055246353149414}
-03/04/2022 22:27:01 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/04/2022 22:27:06 - INFO - codeparrot_training - Step 28077: {'lr': 0.0004626677580866574, 'samples': 14375936, 'steps': 28077, 'loss/train': 1.1890004873275757}
-03/04/2022 22:27:09 - INFO - codeparrot_training - Step 28078: {'lr': 0.00046266496829179847, 'samples': 14376448, 'steps': 28078, 'loss/train': 1.3166096210479736}
-03/04/2022 22:27:09 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/04/2022 22:27:14 - INFO - codeparrot_training - Step 28079: {'lr': 0.0004626621784011159, 'samples': 14376960, 'steps': 28079, 'loss/train': 2.110304832458496}
-03/04/2022 22:27:18 - INFO - codeparrot_training - Step 28080: {'lr': 0.0004626593884146111, 'samples': 14377472, 'steps': 28080, 'loss/train': 2.522806167602539}
-03/04/2022 22:27:18 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/04/2022 22:27:23 - INFO - codeparrot_training - Step 28081: {'lr': 0.00046265659833228523, 'samples': 14377984, 'steps': 28081, 'loss/train': 1.8437256813049316}
-03/04/2022 22:27:26 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/04/2022 22:27:28 - INFO - codeparrot_training - Step 28082: {'lr': 0.0004626538081541396, 'samples': 14378496, 'steps': 28082, 'loss/train': 1.475285530090332}
-03/04/2022 22:27:31 - INFO - codeparrot_training - Step 28083: {'lr': 0.00046265101788017543, 'samples': 14379008, 'steps': 28083, 'loss/train': 2.596146583557129}
-03/04/2022 22:27:34 - INFO - codeparrot_training - Step 28084: {'lr': 0.00046264822751039406, 'samples': 14379520, 'steps': 28084, 'loss/train': 2.2042605876922607}
-03/04/2022 22:27:35 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 22:27:40 - INFO - codeparrot_training - Step 28085: {'lr': 0.00046264543704479654, 'samples': 14380032, 'steps': 28085, 'loss/train': 1.8914812803268433}
-03/04/2022 22:27:43 - INFO - codeparrot_training - Step 28086: {'lr': 0.0004626426464833844, 'samples': 14380544, 'steps': 28086, 'loss/train': 2.158964157104492}
-03/04/2022 22:27:43 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/04/2022 22:27:48 - INFO - codeparrot_training - Step 28087: {'lr': 0.0004626398558261586, 'samples': 14381056, 'steps': 28087, 'loss/train': 1.6674350500106812}
-03/04/2022 22:27:51 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/04/2022 22:27:54 - INFO - codeparrot_training - Step 28088: {'lr': 0.00046263706507312073, 'samples': 14381568, 'steps': 28088, 'loss/train': 2.0252678394317627}
-03/04/2022 22:27:57 - INFO - codeparrot_training - Step 28089: {'lr': 0.00046263427422427183, 'samples': 14382080, 'steps': 28089, 'loss/train': 1.9319151639938354}
-03/04/2022 22:28:00 - INFO - codeparrot_training - Step 28090: {'lr': 0.00046263148327961324, 'samples': 14382592, 'steps': 28090, 'loss/train': 1.2417149543762207}
-03/04/2022 22:28:01 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/04/2022 22:28:05 - INFO - codeparrot_training - Step 28091: {'lr': 0.00046262869223914613, 'samples': 14383104, 'steps': 28091, 'loss/train': 1.5222437381744385}
-03/04/2022 22:28:08 - INFO - codeparrot_training - Step 28092: {'lr': 0.00046262590110287183, 'samples': 14383616, 'steps': 28092, 'loss/train': 1.9832857847213745}
-03/04/2022 22:28:09 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/04/2022 22:28:14 - INFO - codeparrot_training - Step 28093: {'lr': 0.00046262310987079156, 'samples': 14384128, 'steps': 28093, 'loss/train': 2.2961349487304688}
-03/04/2022 22:28:17 - INFO - codeparrot_training - Step 28094: {'lr': 0.0004626203185429066, 'samples': 14384640, 'steps': 28094, 'loss/train': 0.6584925651550293}
-03/04/2022 22:28:17 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/04/2022 22:28:22 - INFO - codeparrot_training - Step 28095: {'lr': 0.00046261752711921825, 'samples': 14385152, 'steps': 28095, 'loss/train': 2.265442132949829}
-03/04/2022 22:28:25 - INFO - codeparrot_training - Step 28096: {'lr': 0.00046261473559972764, 'samples': 14385664, 'steps': 28096, 'loss/train': 1.9483779668807983}
-03/04/2022 22:28:26 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 22:28:31 - INFO - codeparrot_training - Step 28097: {'lr': 0.00046261194398443617, 'samples': 14386176, 'steps': 28097, 'loss/train': 2.2661020755767822}
-03/04/2022 22:28:34 - INFO - codeparrot_training - Step 28098: {'lr': 0.00046260915227334503, 'samples': 14386688, 'steps': 28098, 'loss/train': 1.6153074502944946}
-03/04/2022 22:28:34 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/04/2022 22:28:39 - INFO - codeparrot_training - Step 28099: {'lr': 0.0004626063604664555, 'samples': 14387200, 'steps': 28099, 'loss/train': 1.4579943418502808}
-03/04/2022 22:28:42 - INFO - codeparrot_training - Step 28100: {'lr': 0.00046260356856376884, 'samples': 14387712, 'steps': 28100, 'loss/train': 2.0567591190338135}
-03/04/2022 22:28:42 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/04/2022 22:28:48 - INFO - codeparrot_training - Step 28101: {'lr': 0.0004626007765652862, 'samples': 14388224, 'steps': 28101, 'loss/train': 2.019024610519409}
-03/04/2022 22:28:51 - INFO - codeparrot_training - Step 28102: {'lr': 0.00046259798447100903, 'samples': 14388736, 'steps': 28102, 'loss/train': 2.5934672355651855}
-03/04/2022 22:28:51 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/04/2022 22:28:56 - INFO - codeparrot_training - Step 28103: {'lr': 0.0004625951922809385, 'samples': 14389248, 'steps': 28103, 'loss/train': 1.6816918849945068}
-03/04/2022 22:28:59 - INFO - codeparrot_training - Step 28104: {'lr': 0.0004625923999950758, 'samples': 14389760, 'steps': 28104, 'loss/train': 2.3240773677825928}
-03/04/2022 22:28:59 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/04/2022 22:29:05 - INFO - codeparrot_training - Step 28105: {'lr': 0.0004625896076134222, 'samples': 14390272, 'steps': 28105, 'loss/train': 1.3406025171279907}
-03/04/2022 22:29:08 - INFO - codeparrot_training - Step 28106: {'lr': 0.00046258681513597913, 'samples': 14390784, 'steps': 28106, 'loss/train': 2.169384479522705}
-03/04/2022 22:29:11 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/04/2022 22:29:13 - INFO - codeparrot_training - Step 28107: {'lr': 0.0004625840225627476, 'samples': 14391296, 'steps': 28107, 'loss/train': 1.4953354597091675}
-03/04/2022 22:29:17 - INFO - codeparrot_training - Step 28108: {'lr': 0.0004625812298937291, 'samples': 14391808, 'steps': 28108, 'loss/train': 2.611284017562866}
-03/04/2022 22:29:19 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/04/2022 22:29:22 - INFO - codeparrot_training - Step 28109: {'lr': 0.0004625784371289247, 'samples': 14392320, 'steps': 28109, 'loss/train': 1.0776478052139282}
-03/04/2022 22:29:25 - INFO - codeparrot_training - Step 28110: {'lr': 0.00046257564426833574, 'samples': 14392832, 'steps': 28110, 'loss/train': 1.6356031894683838}
-03/04/2022 22:29:27 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/04/2022 22:29:30 - INFO - codeparrot_training - Step 28111: {'lr': 0.0004625728513119635, 'samples': 14393344, 'steps': 28111, 'loss/train': 1.6882630586624146}
-03/04/2022 22:29:33 - INFO - codeparrot_training - Step 28112: {'lr': 0.0004625700582598092, 'samples': 14393856, 'steps': 28112, 'loss/train': 3.3646106719970703}
-03/04/2022 22:29:36 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/04/2022 22:29:39 - INFO - codeparrot_training - Step 28113: {'lr': 0.00046256726511187407, 'samples': 14394368, 'steps': 28113, 'loss/train': 2.0795812606811523}
-03/04/2022 22:29:42 - INFO - codeparrot_training - Step 28114: {'lr': 0.0004625644718681595, 'samples': 14394880, 'steps': 28114, 'loss/train': 2.007127523422241}
-03/04/2022 22:29:44 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 22:29:47 - INFO - codeparrot_training - Step 28115: {'lr': 0.0004625616785286666, 'samples': 14395392, 'steps': 28115, 'loss/train': 1.6462960243225098}
-03/04/2022 22:29:50 - INFO - codeparrot_training - Step 28116: {'lr': 0.0004625588850933967, 'samples': 14395904, 'steps': 28116, 'loss/train': 1.7275465726852417}
-03/04/2022 22:29:53 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 22:29:56 - INFO - codeparrot_training - Step 28117: {'lr': 0.00046255609156235105, 'samples': 14396416, 'steps': 28117, 'loss/train': 1.7358933687210083}
-03/04/2022 22:29:59 - INFO - codeparrot_training - Step 28118: {'lr': 0.0004625532979355309, 'samples': 14396928, 'steps': 28118, 'loss/train': 1.6556073427200317}
-03/04/2022 22:30:01 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/04/2022 22:30:04 - INFO - codeparrot_training - Step 28119: {'lr': 0.00046255050421293756, 'samples': 14397440, 'steps': 28119, 'loss/train': 1.7418181896209717}
-03/04/2022 22:30:07 - INFO - codeparrot_training - Step 28120: {'lr': 0.0004625477103945722, 'samples': 14397952, 'steps': 28120, 'loss/train': 1.591454267501831}
-03/04/2022 22:30:09 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/04/2022 22:30:13 - INFO - codeparrot_training - Step 28121: {'lr': 0.00046254491648043604, 'samples': 14398464, 'steps': 28121, 'loss/train': 2.4587764739990234}
-03/04/2022 22:30:16 - INFO - codeparrot_training - Step 28122: {'lr': 0.00046254212247053055, 'samples': 14398976, 'steps': 28122, 'loss/train': 1.5030931234359741}
-03/04/2022 22:30:18 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 22:30:21 - INFO - codeparrot_training - Step 28123: {'lr': 0.0004625393283648568, 'samples': 14399488, 'steps': 28123, 'loss/train': 2.268728733062744}
-03/04/2022 22:30:24 - INFO - codeparrot_training - Step 28124: {'lr': 0.0004625365341634161, 'samples': 14400000, 'steps': 28124, 'loss/train': 2.88309645652771}
-03/04/2022 22:30:26 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/04/2022 22:30:29 - INFO - codeparrot_training - Step 28125: {'lr': 0.00046253373986620985, 'samples': 14400512, 'steps': 28125, 'loss/train': 1.7204844951629639}
-03/04/2022 22:30:32 - INFO - codeparrot_training - Step 28126: {'lr': 0.00046253094547323904, 'samples': 14401024, 'steps': 28126, 'loss/train': 1.458883285522461}
-03/04/2022 22:30:35 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 22:30:38 - INFO - codeparrot_training - Step 28127: {'lr': 0.0004625281509845051, 'samples': 14401536, 'steps': 28127, 'loss/train': 2.3355560302734375}
-03/04/2022 22:30:41 - INFO - codeparrot_training - Step 28128: {'lr': 0.0004625253564000092, 'samples': 14402048, 'steps': 28128, 'loss/train': 2.2517402172088623}
-03/04/2022 22:30:43 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/04/2022 22:30:46 - INFO - codeparrot_training - Step 28129: {'lr': 0.00046252256171975273, 'samples': 14402560, 'steps': 28129, 'loss/train': 1.5643378496170044}
-03/04/2022 22:30:49 - INFO - codeparrot_training - Step 28130: {'lr': 0.0004625197669437368, 'samples': 14403072, 'steps': 28130, 'loss/train': 1.9685091972351074}
-03/04/2022 22:30:51 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/04/2022 22:30:55 - INFO - codeparrot_training - Step 28131: {'lr': 0.0004625169720719628, 'samples': 14403584, 'steps': 28131, 'loss/train': 1.4467720985412598}
-03/04/2022 22:30:58 - INFO - codeparrot_training - Step 28132: {'lr': 0.0004625141771044319, 'samples': 14404096, 'steps': 28132, 'loss/train': 1.6731187105178833}
-03/04/2022 22:31:00 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/04/2022 22:31:03 - INFO - codeparrot_training - Step 28133: {'lr': 0.0004625113820411454, 'samples': 14404608, 'steps': 28133, 'loss/train': 1.5617496967315674}
-03/04/2022 22:31:06 - INFO - codeparrot_training - Step 28134: {'lr': 0.0004625085868821046, 'samples': 14405120, 'steps': 28134, 'loss/train': 1.3026152849197388}
-03/04/2022 22:31:08 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/04/2022 22:31:12 - INFO - codeparrot_training - Step 28135: {'lr': 0.0004625057916273107, 'samples': 14405632, 'steps': 28135, 'loss/train': 1.1610740423202515}
-03/04/2022 22:31:15 - INFO - codeparrot_training - Step 28136: {'lr': 0.00046250299627676486, 'samples': 14406144, 'steps': 28136, 'loss/train': 1.5719972848892212}
-03/04/2022 22:31:17 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/04/2022 22:31:20 - INFO - codeparrot_training - Step 28137: {'lr': 0.0004625002008304685, 'samples': 14406656, 'steps': 28137, 'loss/train': 1.1747713088989258}
-03/04/2022 22:31:23 - INFO - codeparrot_training - Step 28138: {'lr': 0.00046249740528842286, 'samples': 14407168, 'steps': 28138, 'loss/train': 1.5609873533248901}
-03/04/2022 22:31:25 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/04/2022 22:31:28 - INFO - codeparrot_training - Step 28139: {'lr': 0.00046249460965062917, 'samples': 14407680, 'steps': 28139, 'loss/train': 1.4873164892196655}
-03/04/2022 22:31:32 - INFO - codeparrot_training - Step 28140: {'lr': 0.0004624918139170887, 'samples': 14408192, 'steps': 28140, 'loss/train': 2.3407249450683594}
-03/04/2022 22:31:34 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 22:31:37 - INFO - codeparrot_training - Step 28141: {'lr': 0.0004624890180878027, 'samples': 14408704, 'steps': 28141, 'loss/train': 1.74484121799469}
-03/04/2022 22:31:40 - INFO - codeparrot_training - Step 28142: {'lr': 0.00046248622216277235, 'samples': 14409216, 'steps': 28142, 'loss/train': 1.6680779457092285}
-03/04/2022 22:31:42 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/04/2022 22:31:45 - INFO - codeparrot_training - Step 28143: {'lr': 0.0004624834261419991, 'samples': 14409728, 'steps': 28143, 'loss/train': 2.0923094749450684}
-03/04/2022 22:31:49 - INFO - codeparrot_training - Step 28144: {'lr': 0.000462480630025484, 'samples': 14410240, 'steps': 28144, 'loss/train': 1.4857609272003174}
-03/04/2022 22:31:51 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/04/2022 22:31:54 - INFO - codeparrot_training - Step 28145: {'lr': 0.0004624778338132285, 'samples': 14410752, 'steps': 28145, 'loss/train': 1.739702820777893}
-03/04/2022 22:31:57 - INFO - codeparrot_training - Step 28146: {'lr': 0.0004624750375052337, 'samples': 14411264, 'steps': 28146, 'loss/train': 2.859133005142212}
-03/04/2022 22:31:59 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/04/2022 22:32:02 - INFO - codeparrot_training - Step 28147: {'lr': 0.0004624722411015009, 'samples': 14411776, 'steps': 28147, 'loss/train': 1.755147099494934}
-03/04/2022 22:32:06 - INFO - codeparrot_training - Step 28148: {'lr': 0.0004624694446020314, 'samples': 14412288, 'steps': 28148, 'loss/train': 1.7164280414581299}
-03/04/2022 22:32:08 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/04/2022 22:32:11 - INFO - codeparrot_training - Step 28149: {'lr': 0.0004624666480068265, 'samples': 14412800, 'steps': 28149, 'loss/train': 0.9909658432006836}
-03/04/2022 22:32:14 - INFO - codeparrot_training - Step 28150: {'lr': 0.0004624638513158874, 'samples': 14413312, 'steps': 28150, 'loss/train': 2.305788993835449}
-03/04/2022 22:32:16 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/04/2022 22:32:19 - INFO - codeparrot_training - Step 28151: {'lr': 0.0004624610545292154, 'samples': 14413824, 'steps': 28151, 'loss/train': 1.5843918323516846}
-03/04/2022 22:32:22 - INFO - codeparrot_training - Step 28152: {'lr': 0.00046245825764681166, 'samples': 14414336, 'steps': 28152, 'loss/train': 1.8396695852279663}
-03/04/2022 22:32:25 - INFO - codeparrot_training - Skipping example with length 524 (seq_length=1024)
-03/04/2022 22:32:28 - INFO - codeparrot_training - Step 28153: {'lr': 0.0004624554606686775, 'samples': 14414848, 'steps': 28153, 'loss/train': 1.48122239112854}
-03/04/2022 22:32:31 - INFO - codeparrot_training - Step 28154: {'lr': 0.0004624526635948142, 'samples': 14415360, 'steps': 28154, 'loss/train': 1.8700424432754517}
-03/04/2022 22:32:33 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/04/2022 22:32:36 - INFO - codeparrot_training - Step 28155: {'lr': 0.000462449866425223, 'samples': 14415872, 'steps': 28155, 'loss/train': 1.9450435638427734}
-03/04/2022 22:32:39 - INFO - codeparrot_training - Step 28156: {'lr': 0.0004624470691599052, 'samples': 14416384, 'steps': 28156, 'loss/train': 0.6915452480316162}
-03/04/2022 22:32:41 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/04/2022 22:32:45 - INFO - codeparrot_training - Step 28157: {'lr': 0.00046244427179886207, 'samples': 14416896, 'steps': 28157, 'loss/train': 1.5829966068267822}
-03/04/2022 22:32:48 - INFO - codeparrot_training - Step 28158: {'lr': 0.0004624414743420947, 'samples': 14417408, 'steps': 28158, 'loss/train': 1.7616063356399536}
-03/04/2022 22:32:50 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 22:32:53 - INFO - codeparrot_training - Step 28159: {'lr': 0.00046243867678960463, 'samples': 14417920, 'steps': 28159, 'loss/train': 1.8184945583343506}
-03/04/2022 22:32:56 - INFO - codeparrot_training - Step 28160: {'lr': 0.00046243587914139285, 'samples': 14418432, 'steps': 28160, 'loss/train': 1.7058660984039307}
-03/04/2022 22:32:58 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/04/2022 22:33:01 - INFO - codeparrot_training - Step 28161: {'lr': 0.00046243308139746076, 'samples': 14418944, 'steps': 28161, 'loss/train': 2.9440455436706543}
-03/04/2022 22:33:04 - INFO - codeparrot_training - Step 28162: {'lr': 0.00046243028355780967, 'samples': 14419456, 'steps': 28162, 'loss/train': 1.7923601865768433}
-03/04/2022 22:33:06 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/04/2022 22:33:10 - INFO - codeparrot_training - Step 28163: {'lr': 0.00046242748562244076, 'samples': 14419968, 'steps': 28163, 'loss/train': 1.6393907070159912}
-03/04/2022 22:33:13 - INFO - codeparrot_training - Step 28164: {'lr': 0.00046242468759135523, 'samples': 14420480, 'steps': 28164, 'loss/train': 1.514647126197815}
-03/04/2022 22:33:14 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/04/2022 22:33:18 - INFO - codeparrot_training - Step 28165: {'lr': 0.00046242188946455444, 'samples': 14420992, 'steps': 28165, 'loss/train': 1.8699649572372437}
-03/04/2022 22:33:21 - INFO - codeparrot_training - Step 28166: {'lr': 0.0004624190912420397, 'samples': 14421504, 'steps': 28166, 'loss/train': 2.012799024581909}
-03/04/2022 22:33:23 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/04/2022 22:33:27 - INFO - codeparrot_training - Step 28167: {'lr': 0.0004624162929238121, 'samples': 14422016, 'steps': 28167, 'loss/train': 1.6737743616104126}
-03/04/2022 22:33:30 - INFO - codeparrot_training - Step 28168: {'lr': 0.000462413494509873, 'samples': 14422528, 'steps': 28168, 'loss/train': 1.6216694116592407}
-03/04/2022 22:33:31 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 22:33:35 - INFO - codeparrot_training - Step 28169: {'lr': 0.0004624106960002237, 'samples': 14423040, 'steps': 28169, 'loss/train': 2.1164615154266357}
-03/04/2022 22:33:38 - INFO - codeparrot_training - Step 28170: {'lr': 0.0004624078973948654, 'samples': 14423552, 'steps': 28170, 'loss/train': 1.4005062580108643}
-03/04/2022 22:33:40 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 22:33:43 - INFO - codeparrot_training - Step 28171: {'lr': 0.00046240509869379943, 'samples': 14424064, 'steps': 28171, 'loss/train': 2.344982862472534}
-03/04/2022 22:33:47 - INFO - codeparrot_training - Step 28172: {'lr': 0.00046240229989702697, 'samples': 14424576, 'steps': 28172, 'loss/train': 1.9281339645385742}
-03/04/2022 22:33:48 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/04/2022 22:33:52 - INFO - codeparrot_training - Step 28173: {'lr': 0.0004623995010045493, 'samples': 14425088, 'steps': 28173, 'loss/train': 1.7192636728286743}
-03/04/2022 22:33:55 - INFO - codeparrot_training - Step 28174: {'lr': 0.0004623967020163677, 'samples': 14425600, 'steps': 28174, 'loss/train': 1.8230856657028198}
-03/04/2022 22:33:58 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/04/2022 22:34:01 - INFO - codeparrot_training - Step 28175: {'lr': 0.0004623939029324834, 'samples': 14426112, 'steps': 28175, 'loss/train': 2.491098403930664}
-03/04/2022 22:34:04 - INFO - codeparrot_training - Step 28176: {'lr': 0.0004623911037528977, 'samples': 14426624, 'steps': 28176, 'loss/train': 2.131561756134033}
-03/04/2022 22:34:06 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/04/2022 22:34:09 - INFO - codeparrot_training - Step 28177: {'lr': 0.00046238830447761184, 'samples': 14427136, 'steps': 28177, 'loss/train': 1.4753724336624146}
-03/04/2022 22:34:13 - INFO - codeparrot_training - Step 28178: {'lr': 0.0004623855051066271, 'samples': 14427648, 'steps': 28178, 'loss/train': 0.8971425890922546}
-03/04/2022 22:34:16 - INFO - codeparrot_training - Step 28179: {'lr': 0.00046238270563994465, 'samples': 14428160, 'steps': 28179, 'loss/train': 2.506060838699341}
-03/04/2022 22:34:17 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/04/2022 22:34:21 - INFO - codeparrot_training - Step 28180: {'lr': 0.00046237990607756596, 'samples': 14428672, 'steps': 28180, 'loss/train': 1.8267039060592651}
-03/04/2022 22:34:24 - INFO - codeparrot_training - Step 28181: {'lr': 0.0004623771064194921, 'samples': 14429184, 'steps': 28181, 'loss/train': 0.4928413927555084}
-03/04/2022 22:34:25 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/04/2022 22:34:29 - INFO - codeparrot_training - Step 28182: {'lr': 0.0004623743066657244, 'samples': 14429696, 'steps': 28182, 'loss/train': 1.3066824674606323}
-03/04/2022 22:34:33 - INFO - codeparrot_training - Step 28183: {'lr': 0.00046237150681626414, 'samples': 14430208, 'steps': 28183, 'loss/train': 2.079785108566284}
-03/04/2022 22:34:33 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/04/2022 22:34:38 - INFO - codeparrot_training - Step 28184: {'lr': 0.00046236870687111254, 'samples': 14430720, 'steps': 28184, 'loss/train': 2.089653968811035}
-03/04/2022 22:34:41 - INFO - codeparrot_training - Step 28185: {'lr': 0.0004623659068302708, 'samples': 14431232, 'steps': 28185, 'loss/train': 1.5375726222991943}
-03/04/2022 22:34:42 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/04/2022 22:34:46 - INFO - codeparrot_training - Step 28186: {'lr': 0.00046236310669374035, 'samples': 14431744, 'steps': 28186, 'loss/train': 1.521285057067871}
-03/04/2022 22:34:50 - INFO - codeparrot_training - Step 28187: {'lr': 0.0004623603064615223, 'samples': 14432256, 'steps': 28187, 'loss/train': 1.598927617073059}
-03/04/2022 22:34:51 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/04/2022 22:34:55 - INFO - codeparrot_training - Step 28188: {'lr': 0.000462357506133618, 'samples': 14432768, 'steps': 28188, 'loss/train': 1.5292284488677979}
-03/04/2022 22:34:58 - INFO - codeparrot_training - Step 28189: {'lr': 0.00046235470571002877, 'samples': 14433280, 'steps': 28189, 'loss/train': 2.5605599880218506}
-03/04/2022 22:35:00 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/04/2022 22:35:03 - INFO - codeparrot_training - Step 28190: {'lr': 0.00046235190519075564, 'samples': 14433792, 'steps': 28190, 'loss/train': 1.7622976303100586}
-03/04/2022 22:35:06 - INFO - codeparrot_training - Step 28191: {'lr': 0.00046234910457580014, 'samples': 14434304, 'steps': 28191, 'loss/train': 1.7767924070358276}
-03/04/2022 22:35:08 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/04/2022 22:35:12 - INFO - codeparrot_training - Step 28192: {'lr': 0.0004623463038651633, 'samples': 14434816, 'steps': 28192, 'loss/train': 2.2895407676696777}
-03/04/2022 22:35:15 - INFO - codeparrot_training - Step 28193: {'lr': 0.0004623435030588466, 'samples': 14435328, 'steps': 28193, 'loss/train': 1.5818462371826172}
-03/04/2022 22:35:16 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/04/2022 22:35:20 - INFO - codeparrot_training - Step 28194: {'lr': 0.00046234070215685116, 'samples': 14435840, 'steps': 28194, 'loss/train': 2.3772470951080322}
-03/04/2022 22:35:23 - INFO - codeparrot_training - Step 28195: {'lr': 0.0004623379011591782, 'samples': 14436352, 'steps': 28195, 'loss/train': 1.9827202558517456}
-03/04/2022 22:35:25 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 22:35:29 - INFO - codeparrot_training - Step 28196: {'lr': 0.00046233510006582913, 'samples': 14436864, 'steps': 28196, 'loss/train': 2.052654504776001}
-03/04/2022 22:35:32 - INFO - codeparrot_training - Step 28197: {'lr': 0.00046233229887680517, 'samples': 14437376, 'steps': 28197, 'loss/train': 2.301666021347046}
-03/04/2022 22:35:33 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/04/2022 22:35:37 - INFO - codeparrot_training - Step 28198: {'lr': 0.00046232949759210753, 'samples': 14437888, 'steps': 28198, 'loss/train': 2.4367799758911133}
-03/04/2022 22:35:40 - INFO - codeparrot_training - Step 28199: {'lr': 0.00046232669621173745, 'samples': 14438400, 'steps': 28199, 'loss/train': 1.5220845937728882}
-03/04/2022 22:35:42 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 22:35:45 - INFO - codeparrot_training - Step 28200: {'lr': 0.00046232389473569623, 'samples': 14438912, 'steps': 28200, 'loss/train': 2.1719753742218018}
-03/04/2022 22:35:49 - INFO - codeparrot_training - Step 28201: {'lr': 0.0004623210931639852, 'samples': 14439424, 'steps': 28201, 'loss/train': 2.156470775604248}
-03/04/2022 22:35:50 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 22:35:54 - INFO - codeparrot_training - Step 28202: {'lr': 0.00046231829149660553, 'samples': 14439936, 'steps': 28202, 'loss/train': 1.8819589614868164}
-03/04/2022 22:35:57 - INFO - codeparrot_training - Step 28203: {'lr': 0.00046231548973355854, 'samples': 14440448, 'steps': 28203, 'loss/train': 1.222532868385315}
-03/04/2022 22:35:59 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/04/2022 22:36:02 - INFO - codeparrot_training - Step 28204: {'lr': 0.00046231268787484545, 'samples': 14440960, 'steps': 28204, 'loss/train': 1.9642658233642578}
-03/04/2022 22:36:05 - INFO - codeparrot_training - Step 28205: {'lr': 0.0004623098859204675, 'samples': 14441472, 'steps': 28205, 'loss/train': 1.4017316102981567}
-03/04/2022 22:36:07 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 22:36:11 - INFO - codeparrot_training - Step 28206: {'lr': 0.00046230708387042603, 'samples': 14441984, 'steps': 28206, 'loss/train': 1.466529369354248}
-03/04/2022 22:36:14 - INFO - codeparrot_training - Step 28207: {'lr': 0.0004623042817247223, 'samples': 14442496, 'steps': 28207, 'loss/train': 2.9606869220733643}
-03/04/2022 22:36:17 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/04/2022 22:36:20 - INFO - codeparrot_training - Step 28208: {'lr': 0.00046230147948335746, 'samples': 14443008, 'steps': 28208, 'loss/train': 2.59894061088562}
-03/04/2022 22:36:23 - INFO - codeparrot_training - Step 28209: {'lr': 0.0004622986771463329, 'samples': 14443520, 'steps': 28209, 'loss/train': 2.2940847873687744}
-03/04/2022 22:36:25 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/04/2022 22:36:28 - INFO - codeparrot_training - Step 28210: {'lr': 0.0004622958747136498, 'samples': 14444032, 'steps': 28210, 'loss/train': 2.223080635070801}
-03/04/2022 22:36:32 - INFO - codeparrot_training - Step 28211: {'lr': 0.00046229307218530945, 'samples': 14444544, 'steps': 28211, 'loss/train': 1.079291820526123}
-03/04/2022 22:36:34 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/04/2022 22:36:37 - INFO - codeparrot_training - Step 28212: {'lr': 0.0004622902695613131, 'samples': 14445056, 'steps': 28212, 'loss/train': 1.9182860851287842}
-03/04/2022 22:36:40 - INFO - codeparrot_training - Step 28213: {'lr': 0.00046228746684166214, 'samples': 14445568, 'steps': 28213, 'loss/train': 2.2384345531463623}
-03/04/2022 22:36:42 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/04/2022 22:36:45 - INFO - codeparrot_training - Step 28214: {'lr': 0.00046228466402635764, 'samples': 14446080, 'steps': 28214, 'loss/train': 2.224390745162964}
-03/04/2022 22:36:49 - INFO - codeparrot_training - Step 28215: {'lr': 0.0004622818611154009, 'samples': 14446592, 'steps': 28215, 'loss/train': 1.4603514671325684}
-03/04/2022 22:36:51 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/04/2022 22:36:54 - INFO - codeparrot_training - Step 28216: {'lr': 0.00046227905810879334, 'samples': 14447104, 'steps': 28216, 'loss/train': 0.865271806716919}
-03/04/2022 22:36:57 - INFO - codeparrot_training - Step 28217: {'lr': 0.0004622762550065361, 'samples': 14447616, 'steps': 28217, 'loss/train': 1.7706621885299683}
-03/04/2022 22:36:59 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 22:37:02 - INFO - codeparrot_training - Step 28218: {'lr': 0.0004622734518086304, 'samples': 14448128, 'steps': 28218, 'loss/train': 1.6963046789169312}
-03/04/2022 22:37:06 - INFO - codeparrot_training - Step 28219: {'lr': 0.0004622706485150776, 'samples': 14448640, 'steps': 28219, 'loss/train': 1.8714600801467896}
-03/04/2022 22:37:08 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 22:37:11 - INFO - codeparrot_training - Step 28220: {'lr': 0.0004622678451258788, 'samples': 14449152, 'steps': 28220, 'loss/train': 1.5058749914169312}
-03/04/2022 22:37:14 - INFO - codeparrot_training - Step 28221: {'lr': 0.00046226504164103557, 'samples': 14449664, 'steps': 28221, 'loss/train': 1.8998761177062988}
-03/04/2022 22:37:16 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 22:37:19 - INFO - codeparrot_training - Step 28222: {'lr': 0.0004622622380605489, 'samples': 14450176, 'steps': 28222, 'loss/train': 1.2426837682724}
-03/04/2022 22:37:22 - INFO - codeparrot_training - Step 28223: {'lr': 0.0004622594343844201, 'samples': 14450688, 'steps': 28223, 'loss/train': 1.9605756998062134}
-03/04/2022 22:37:25 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 22:37:28 - INFO - codeparrot_training - Step 28224: {'lr': 0.00046225663061265056, 'samples': 14451200, 'steps': 28224, 'loss/train': 2.307708978652954}
-03/04/2022 22:37:31 - INFO - codeparrot_training - Step 28225: {'lr': 0.0004622538267452414, 'samples': 14451712, 'steps': 28225, 'loss/train': 0.9833211302757263}
-03/04/2022 22:37:34 - INFO - codeparrot_training - Step 28226: {'lr': 0.00046225102278219394, 'samples': 14452224, 'steps': 28226, 'loss/train': 2.096790075302124}
-03/04/2022 22:37:35 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 22:37:40 - INFO - codeparrot_training - Step 28227: {'lr': 0.0004622482187235094, 'samples': 14452736, 'steps': 28227, 'loss/train': 0.6535780429840088}
-03/04/2022 22:37:43 - INFO - codeparrot_training - Step 28228: {'lr': 0.00046224541456918916, 'samples': 14453248, 'steps': 28228, 'loss/train': 2.097245216369629}
-03/04/2022 22:37:43 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/04/2022 22:37:48 - INFO - codeparrot_training - Step 28229: {'lr': 0.0004622426103192344, 'samples': 14453760, 'steps': 28229, 'loss/train': 2.073657989501953}
-03/04/2022 22:37:51 - INFO - codeparrot_training - Step 28230: {'lr': 0.00046223980597364647, 'samples': 14454272, 'steps': 28230, 'loss/train': 1.2474056482315063}
-03/04/2022 22:37:52 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/04/2022 22:37:57 - INFO - codeparrot_training - Step 28231: {'lr': 0.0004622370015324264, 'samples': 14454784, 'steps': 28231, 'loss/train': 0.865554690361023}
-03/04/2022 22:38:00 - INFO - codeparrot_training - Step 28232: {'lr': 0.0004622341969955757, 'samples': 14455296, 'steps': 28232, 'loss/train': 1.687196135520935}
-03/04/2022 22:38:01 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/04/2022 22:38:05 - INFO - codeparrot_training - Step 28233: {'lr': 0.00046223139236309553, 'samples': 14455808, 'steps': 28233, 'loss/train': 1.5283609628677368}
-03/04/2022 22:38:08 - INFO - codeparrot_training - Step 28234: {'lr': 0.0004622285876349872, 'samples': 14456320, 'steps': 28234, 'loss/train': 1.8432928323745728}
-03/04/2022 22:38:09 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/04/2022 22:38:13 - INFO - codeparrot_training - Step 28235: {'lr': 0.00046222578281125194, 'samples': 14456832, 'steps': 28235, 'loss/train': 1.8542454242706299}
-03/04/2022 22:38:17 - INFO - codeparrot_training - Step 28236: {'lr': 0.0004622229778918909, 'samples': 14457344, 'steps': 28236, 'loss/train': 2.1417524814605713}
-03/04/2022 22:38:18 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/04/2022 22:38:22 - INFO - codeparrot_training - Step 28237: {'lr': 0.00046222017287690566, 'samples': 14457856, 'steps': 28237, 'loss/train': 1.6115163564682007}
-03/04/2022 22:38:25 - INFO - codeparrot_training - Step 28238: {'lr': 0.00046221736776629713, 'samples': 14458368, 'steps': 28238, 'loss/train': 2.828225612640381}
-03/04/2022 22:38:30 - INFO - codeparrot_training - Step 28239: {'lr': 0.0004622145625600668, 'samples': 14458880, 'steps': 28239, 'loss/train': 1.8400185108184814}
-03/04/2022 22:38:34 - INFO - codeparrot_training - Step 28240: {'lr': 0.00046221175725821585, 'samples': 14459392, 'steps': 28240, 'loss/train': 1.3655014038085938}
-03/04/2022 22:38:35 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/04/2022 22:38:39 - INFO - codeparrot_training - Step 28241: {'lr': 0.00046220895186074553, 'samples': 14459904, 'steps': 28241, 'loss/train': 2.592376470565796}
-03/04/2022 22:38:42 - INFO - codeparrot_training - Step 28242: {'lr': 0.0004622061463676572, 'samples': 14460416, 'steps': 28242, 'loss/train': 1.7200971841812134}
-03/04/2022 22:38:44 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/04/2022 22:38:47 - INFO - codeparrot_training - Step 28243: {'lr': 0.000462203340778952, 'samples': 14460928, 'steps': 28243, 'loss/train': 1.5662012100219727}
-03/04/2022 22:38:51 - INFO - codeparrot_training - Step 28244: {'lr': 0.0004622005350946312, 'samples': 14461440, 'steps': 28244, 'loss/train': 1.8112459182739258}
-03/04/2022 22:38:52 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 22:38:56 - INFO - codeparrot_training - Step 28245: {'lr': 0.00046219772931469617, 'samples': 14461952, 'steps': 28245, 'loss/train': 1.7569890022277832}
-03/04/2022 22:38:59 - INFO - codeparrot_training - Step 28246: {'lr': 0.00046219492343914815, 'samples': 14462464, 'steps': 28246, 'loss/train': 1.9689233303070068}
-03/04/2022 22:39:01 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/04/2022 22:39:04 - INFO - codeparrot_training - Step 28247: {'lr': 0.00046219211746798835, 'samples': 14462976, 'steps': 28247, 'loss/train': 2.222337245941162}
-03/04/2022 22:39:08 - INFO - codeparrot_training - Step 28248: {'lr': 0.000462189311401218, 'samples': 14463488, 'steps': 28248, 'loss/train': 2.4476191997528076}
-03/04/2022 22:39:09 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/04/2022 22:39:13 - INFO - codeparrot_training - Step 28249: {'lr': 0.0004621865052388385, 'samples': 14464000, 'steps': 28249, 'loss/train': 2.217796564102173}
-03/04/2022 22:39:16 - INFO - codeparrot_training - Step 28250: {'lr': 0.00046218369898085097, 'samples': 14464512, 'steps': 28250, 'loss/train': 1.7386078834533691}
-03/04/2022 22:39:17 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/04/2022 22:39:21 - INFO - codeparrot_training - Step 28251: {'lr': 0.0004621808926272568, 'samples': 14465024, 'steps': 28251, 'loss/train': 1.7503645420074463}
-03/04/2022 22:39:24 - INFO - codeparrot_training - Step 28252: {'lr': 0.0004621780861780572, 'samples': 14465536, 'steps': 28252, 'loss/train': 2.030625581741333}
-03/04/2022 22:39:26 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 22:39:30 - INFO - codeparrot_training - Step 28253: {'lr': 0.00046217527963325335, 'samples': 14466048, 'steps': 28253, 'loss/train': 1.4750890731811523}
-03/04/2022 22:39:33 - INFO - codeparrot_training - Step 28254: {'lr': 0.00046217247299284666, 'samples': 14466560, 'steps': 28254, 'loss/train': 2.7053892612457275}
-03/04/2022 22:39:34 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 22:39:38 - INFO - codeparrot_training - Step 28255: {'lr': 0.00046216966625683834, 'samples': 14467072, 'steps': 28255, 'loss/train': 4.57110595703125}
-03/04/2022 22:39:41 - INFO - codeparrot_training - Step 28256: {'lr': 0.00046216685942522957, 'samples': 14467584, 'steps': 28256, 'loss/train': 2.233008861541748}
-03/04/2022 22:39:43 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/04/2022 22:39:47 - INFO - codeparrot_training - Step 28257: {'lr': 0.00046216405249802176, 'samples': 14468096, 'steps': 28257, 'loss/train': 1.7791632413864136}
-03/04/2022 22:39:50 - INFO - codeparrot_training - Step 28258: {'lr': 0.000462161245475216, 'samples': 14468608, 'steps': 28258, 'loss/train': 1.3522037267684937}
-03/04/2022 22:39:52 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/04/2022 22:39:55 - INFO - codeparrot_training - Step 28259: {'lr': 0.0004621584383568137, 'samples': 14469120, 'steps': 28259, 'loss/train': 1.8858468532562256}
-03/04/2022 22:39:58 - INFO - codeparrot_training - Step 28260: {'lr': 0.00046215563114281613, 'samples': 14469632, 'steps': 28260, 'loss/train': 2.0129947662353516}
-03/04/2022 22:40:00 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/04/2022 22:40:04 - INFO - codeparrot_training - Step 28261: {'lr': 0.0004621528238332245, 'samples': 14470144, 'steps': 28261, 'loss/train': 2.110783100128174}
-03/04/2022 22:40:07 - INFO - codeparrot_training - Step 28262: {'lr': 0.00046215001642804, 'samples': 14470656, 'steps': 28262, 'loss/train': 2.002697229385376}
-03/04/2022 22:40:08 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/04/2022 22:40:12 - INFO - codeparrot_training - Step 28263: {'lr': 0.0004621472089272641, 'samples': 14471168, 'steps': 28263, 'loss/train': 1.8643553256988525}
-03/04/2022 22:40:15 - INFO - codeparrot_training - Step 28264: {'lr': 0.0004621444013308979, 'samples': 14471680, 'steps': 28264, 'loss/train': 1.1936086416244507}
-03/04/2022 22:40:17 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/04/2022 22:40:21 - INFO - codeparrot_training - Step 28265: {'lr': 0.00046214159363894264, 'samples': 14472192, 'steps': 28265, 'loss/train': 2.3569729328155518}
-03/04/2022 22:40:24 - INFO - codeparrot_training - Step 28266: {'lr': 0.0004621387858513997, 'samples': 14472704, 'steps': 28266, 'loss/train': 1.794743537902832}
-03/04/2022 22:40:25 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/04/2022 22:40:29 - INFO - codeparrot_training - Step 28267: {'lr': 0.0004621359779682703, 'samples': 14473216, 'steps': 28267, 'loss/train': 1.413746953010559}
-03/04/2022 22:40:32 - INFO - codeparrot_training - Step 28268: {'lr': 0.0004621331699895557, 'samples': 14473728, 'steps': 28268, 'loss/train': 2.150907039642334}
-03/04/2022 22:40:34 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 22:40:37 - INFO - codeparrot_training - Step 28269: {'lr': 0.00046213036191525714, 'samples': 14474240, 'steps': 28269, 'loss/train': 1.8511475324630737}
-03/04/2022 22:40:41 - INFO - codeparrot_training - Step 28270: {'lr': 0.00046212755374537594, 'samples': 14474752, 'steps': 28270, 'loss/train': 1.7172820568084717}
-03/04/2022 22:40:42 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/04/2022 22:40:46 - INFO - codeparrot_training - Step 28271: {'lr': 0.0004621247454799133, 'samples': 14475264, 'steps': 28271, 'loss/train': 2.6843080520629883}
-03/04/2022 22:40:49 - INFO - codeparrot_training - Step 28272: {'lr': 0.0004621219371188706, 'samples': 14475776, 'steps': 28272, 'loss/train': 2.121633529663086}
-03/04/2022 22:40:51 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/04/2022 22:40:54 - INFO - codeparrot_training - Step 28273: {'lr': 0.0004621191286622489, 'samples': 14476288, 'steps': 28273, 'loss/train': 2.1590254306793213}
-03/04/2022 22:40:57 - INFO - codeparrot_training - Step 28274: {'lr': 0.00046211632011004973, 'samples': 14476800, 'steps': 28274, 'loss/train': 1.413214921951294}
-03/04/2022 22:40:59 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/04/2022 22:41:03 - INFO - codeparrot_training - Step 28275: {'lr': 0.0004621135114622742, 'samples': 14477312, 'steps': 28275, 'loss/train': 1.4337598085403442}
-03/04/2022 22:41:06 - INFO - codeparrot_training - Step 28276: {'lr': 0.00046211070271892353, 'samples': 14477824, 'steps': 28276, 'loss/train': 1.1462377309799194}
-03/04/2022 22:41:08 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 22:41:11 - INFO - codeparrot_training - Step 28277: {'lr': 0.00046210789387999906, 'samples': 14478336, 'steps': 28277, 'loss/train': 1.9296038150787354}
-03/04/2022 22:41:14 - INFO - codeparrot_training - Step 28278: {'lr': 0.00046210508494550206, 'samples': 14478848, 'steps': 28278, 'loss/train': 2.719940423965454}
-03/04/2022 22:41:16 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/04/2022 22:41:20 - INFO - codeparrot_training - Step 28279: {'lr': 0.0004621022759154338, 'samples': 14479360, 'steps': 28279, 'loss/train': 2.1380927562713623}
-03/04/2022 22:41:23 - INFO - codeparrot_training - Step 28280: {'lr': 0.0004620994667897955, 'samples': 14479872, 'steps': 28280, 'loss/train': 1.6783688068389893}
-03/04/2022 22:41:25 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/04/2022 22:41:28 - INFO - codeparrot_training - Step 28281: {'lr': 0.0004620966575685885, 'samples': 14480384, 'steps': 28281, 'loss/train': 1.8166375160217285}
-03/04/2022 22:41:31 - INFO - codeparrot_training - Step 28282: {'lr': 0.000462093848251814, 'samples': 14480896, 'steps': 28282, 'loss/train': 2.255211114883423}
-03/04/2022 22:41:34 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/04/2022 22:41:37 - INFO - codeparrot_training - Step 28283: {'lr': 0.00046209103883947323, 'samples': 14481408, 'steps': 28283, 'loss/train': 1.5178070068359375}
-03/04/2022 22:41:40 - INFO - codeparrot_training - Step 28284: {'lr': 0.00046208822933156756, 'samples': 14481920, 'steps': 28284, 'loss/train': 1.7980749607086182}
-03/04/2022 22:41:42 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 22:41:45 - INFO - codeparrot_training - Step 28285: {'lr': 0.00046208541972809824, 'samples': 14482432, 'steps': 28285, 'loss/train': 1.5211321115493774}
-03/04/2022 22:41:48 - INFO - codeparrot_training - Step 28286: {'lr': 0.00046208261002906643, 'samples': 14482944, 'steps': 28286, 'loss/train': 0.6545057892799377}
-03/04/2022 22:41:51 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/04/2022 22:41:54 - INFO - codeparrot_training - Step 28287: {'lr': 0.00046207980023447347, 'samples': 14483456, 'steps': 28287, 'loss/train': 1.665461540222168}
-03/04/2022 22:41:57 - INFO - codeparrot_training - Step 28288: {'lr': 0.0004620769903443207, 'samples': 14483968, 'steps': 28288, 'loss/train': 6.616833686828613}
-03/04/2022 22:42:00 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/04/2022 22:42:02 - INFO - codeparrot_training - Step 28289: {'lr': 0.00046207418035860927, 'samples': 14484480, 'steps': 28289, 'loss/train': 2.1301066875457764}
-03/04/2022 22:42:05 - INFO - codeparrot_training - Step 28290: {'lr': 0.00046207137027734046, 'samples': 14484992, 'steps': 28290, 'loss/train': 2.370570182800293}
-03/04/2022 22:42:08 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/04/2022 22:42:10 - INFO - codeparrot_training - Step 28291: {'lr': 0.00046206856010051555, 'samples': 14485504, 'steps': 28291, 'loss/train': 1.276041030883789}
-03/04/2022 22:42:14 - INFO - codeparrot_training - Step 28292: {'lr': 0.0004620657498281359, 'samples': 14486016, 'steps': 28292, 'loss/train': 1.7905917167663574}
-03/04/2022 22:42:16 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/04/2022 22:42:19 - INFO - codeparrot_training - Step 28293: {'lr': 0.0004620629394602027, 'samples': 14486528, 'steps': 28293, 'loss/train': 2.072216033935547}
-03/04/2022 22:42:22 - INFO - codeparrot_training - Step 28294: {'lr': 0.00046206012899671715, 'samples': 14487040, 'steps': 28294, 'loss/train': 1.9236313104629517}
-03/04/2022 22:42:25 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/04/2022 22:42:28 - INFO - codeparrot_training - Step 28295: {'lr': 0.00046205731843768056, 'samples': 14487552, 'steps': 28295, 'loss/train': 0.5986870527267456}
-03/04/2022 22:42:31 - INFO - codeparrot_training - Step 28296: {'lr': 0.0004620545077830942, 'samples': 14488064, 'steps': 28296, 'loss/train': 1.1816462278366089}
-03/04/2022 22:42:34 - INFO - codeparrot_training - Step 28297: {'lr': 0.00046205169703295945, 'samples': 14488576, 'steps': 28297, 'loss/train': 3.332437753677368}
-03/04/2022 22:42:35 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 22:42:39 - INFO - codeparrot_training - Step 28298: {'lr': 0.00046204888618727743, 'samples': 14489088, 'steps': 28298, 'loss/train': 2.239515542984009}
-03/04/2022 22:42:42 - INFO - codeparrot_training - Step 28299: {'lr': 0.00046204607524604944, 'samples': 14489600, 'steps': 28299, 'loss/train': 1.323746919631958}
-03/04/2022 22:42:43 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 22:42:48 - INFO - codeparrot_training - Step 28300: {'lr': 0.0004620432642092768, 'samples': 14490112, 'steps': 28300, 'loss/train': 2.0938899517059326}
-03/04/2022 22:42:51 - INFO - codeparrot_training - Step 28301: {'lr': 0.00046204045307696065, 'samples': 14490624, 'steps': 28301, 'loss/train': 0.5166608691215515}
-03/04/2022 22:42:51 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 22:42:56 - INFO - codeparrot_training - Step 28302: {'lr': 0.0004620376418491024, 'samples': 14491136, 'steps': 28302, 'loss/train': 1.878035068511963}
-03/04/2022 22:42:59 - INFO - codeparrot_training - Step 28303: {'lr': 0.0004620348305257033, 'samples': 14491648, 'steps': 28303, 'loss/train': 0.6501943469047546}
-03/04/2022 22:43:00 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/04/2022 22:43:05 - INFO - codeparrot_training - Step 28304: {'lr': 0.00046203201910676453, 'samples': 14492160, 'steps': 28304, 'loss/train': 1.6701397895812988}
-03/04/2022 22:43:08 - INFO - codeparrot_training - Step 28305: {'lr': 0.0004620292075922874, 'samples': 14492672, 'steps': 28305, 'loss/train': 2.0548577308654785}
-03/04/2022 22:43:08 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/04/2022 22:43:13 - INFO - codeparrot_training - Step 28306: {'lr': 0.0004620263959822732, 'samples': 14493184, 'steps': 28306, 'loss/train': 1.4954462051391602}
-03/04/2022 22:43:16 - INFO - codeparrot_training - Step 28307: {'lr': 0.00046202358427672313, 'samples': 14493696, 'steps': 28307, 'loss/train': 1.8337366580963135}
-03/04/2022 22:43:16 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/04/2022 22:43:21 - INFO - codeparrot_training - Step 28308: {'lr': 0.0004620207724756386, 'samples': 14494208, 'steps': 28308, 'loss/train': 2.0196423530578613}
-03/04/2022 22:43:25 - INFO - codeparrot_training - Step 28309: {'lr': 0.0004620179605790207, 'samples': 14494720, 'steps': 28309, 'loss/train': 1.3312158584594727}
-03/04/2022 22:43:26 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 22:43:26 - INFO - codeparrot_training - Dataset epoch: 1
-03/04/2022 22:43:30 - INFO - codeparrot_training - Step 28310: {'lr': 0.00046201514858687075, 'samples': 14495232, 'steps': 28310, 'loss/train': 2.1164300441741943}
-03/04/2022 22:43:33 - INFO - codeparrot_training - Step 28311: {'lr': 0.00046201233649919015, 'samples': 14495744, 'steps': 28311, 'loss/train': 1.5374401807785034}
-03/04/2022 22:43:34 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/04/2022 22:43:38 - INFO - codeparrot_training - Step 28312: {'lr': 0.00046200952431598, 'samples': 14496256, 'steps': 28312, 'loss/train': 1.9420329332351685}
-03/04/2022 22:43:41 - INFO - codeparrot_training - Step 28313: {'lr': 0.00046200671203724166, 'samples': 14496768, 'steps': 28313, 'loss/train': 1.5617731809616089}
-03/04/2022 22:43:42 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 22:43:47 - INFO - codeparrot_training - Step 28314: {'lr': 0.00046200389966297633, 'samples': 14497280, 'steps': 28314, 'loss/train': 2.074497699737549}
-03/04/2022 22:43:50 - INFO - codeparrot_training - Step 28315: {'lr': 0.00046200108719318537, 'samples': 14497792, 'steps': 28315, 'loss/train': 1.768312931060791}
-03/04/2022 22:43:51 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/04/2022 22:43:55 - INFO - codeparrot_training - Step 28316: {'lr': 0.0004619982746278699, 'samples': 14498304, 'steps': 28316, 'loss/train': 1.2528194189071655}
-03/04/2022 22:43:58 - INFO - codeparrot_training - Step 28317: {'lr': 0.00046199546196703134, 'samples': 14498816, 'steps': 28317, 'loss/train': 1.548931360244751}
-03/04/2022 22:43:59 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/04/2022 22:44:04 - INFO - codeparrot_training - Step 28318: {'lr': 0.0004619926492106709, 'samples': 14499328, 'steps': 28318, 'loss/train': 2.1215429306030273}
-03/04/2022 22:44:07 - INFO - codeparrot_training - Step 28319: {'lr': 0.0004619898363587899, 'samples': 14499840, 'steps': 28319, 'loss/train': 1.8353849649429321}
-03/04/2022 22:44:08 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/04/2022 22:44:12 - INFO - codeparrot_training - Step 28320: {'lr': 0.00046198702341138944, 'samples': 14500352, 'steps': 28320, 'loss/train': 2.437762498855591}
-03/04/2022 22:44:15 - INFO - codeparrot_training - Step 28321: {'lr': 0.00046198421036847093, 'samples': 14500864, 'steps': 28321, 'loss/train': 1.4762158393859863}
-03/04/2022 22:44:16 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/04/2022 22:44:20 - INFO - codeparrot_training - Step 28322: {'lr': 0.00046198139723003563, 'samples': 14501376, 'steps': 28322, 'loss/train': 2.559457540512085}
-03/04/2022 22:44:24 - INFO - codeparrot_training - Step 28323: {'lr': 0.00046197858399608477, 'samples': 14501888, 'steps': 28323, 'loss/train': 0.9250370264053345}
-03/04/2022 22:44:24 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 22:44:29 - INFO - codeparrot_training - Step 28324: {'lr': 0.00046197577066661965, 'samples': 14502400, 'steps': 28324, 'loss/train': 1.9162812232971191}
-03/04/2022 22:44:32 - INFO - codeparrot_training - Step 28325: {'lr': 0.0004619729572416415, 'samples': 14502912, 'steps': 28325, 'loss/train': 2.0879809856414795}
-03/04/2022 22:44:33 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/04/2022 22:44:37 - INFO - codeparrot_training - Step 28326: {'lr': 0.0004619701437211516, 'samples': 14503424, 'steps': 28326, 'loss/train': 1.8281383514404297}
-03/04/2022 22:44:41 - INFO - codeparrot_training - Step 28327: {'lr': 0.00046196733010515125, 'samples': 14503936, 'steps': 28327, 'loss/train': 2.239240884780884}
-03/04/2022 22:44:41 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/04/2022 22:44:46 - INFO - codeparrot_training - Step 28328: {'lr': 0.0004619645163936417, 'samples': 14504448, 'steps': 28328, 'loss/train': 1.8546830415725708}
-03/04/2022 22:44:49 - INFO - codeparrot_training - Step 28329: {'lr': 0.0004619617025866242, 'samples': 14504960, 'steps': 28329, 'loss/train': 2.183136224746704}
-03/04/2022 22:44:50 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/04/2022 22:44:54 - INFO - codeparrot_training - Step 28330: {'lr': 0.00046195888868409994, 'samples': 14505472, 'steps': 28330, 'loss/train': 1.3057067394256592}
-03/04/2022 22:44:57 - INFO - codeparrot_training - Step 28331: {'lr': 0.0004619560746860704, 'samples': 14505984, 'steps': 28331, 'loss/train': 1.6381313800811768}
-03/04/2022 22:44:58 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 22:45:03 - INFO - codeparrot_training - Step 28332: {'lr': 0.0004619532605925366, 'samples': 14506496, 'steps': 28332, 'loss/train': 1.5500290393829346}
-03/04/2022 22:45:06 - INFO - codeparrot_training - Step 28333: {'lr': 0.00046195044640350003, 'samples': 14507008, 'steps': 28333, 'loss/train': 1.5433707237243652}
-03/04/2022 22:45:06 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 22:45:11 - INFO - codeparrot_training - Step 28334: {'lr': 0.00046194763211896187, 'samples': 14507520, 'steps': 28334, 'loss/train': 0.9608316421508789}
-03/04/2022 22:45:14 - INFO - codeparrot_training - Step 28335: {'lr': 0.0004619448177389233, 'samples': 14508032, 'steps': 28335, 'loss/train': 2.7697536945343018}
-03/04/2022 22:45:14 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/04/2022 22:45:19 - INFO - codeparrot_training - Step 28336: {'lr': 0.0004619420032633857, 'samples': 14508544, 'steps': 28336, 'loss/train': 1.6733633279800415}
-03/04/2022 22:45:23 - INFO - codeparrot_training - Step 28337: {'lr': 0.0004619391886923503, 'samples': 14509056, 'steps': 28337, 'loss/train': 1.8333038091659546}
-03/04/2022 22:45:23 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/04/2022 22:45:28 - INFO - codeparrot_training - Step 28338: {'lr': 0.0004619363740258184, 'samples': 14509568, 'steps': 28338, 'loss/train': 1.6225978136062622}
-03/04/2022 22:45:31 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/04/2022 22:45:33 - INFO - codeparrot_training - Step 28339: {'lr': 0.00046193355926379124, 'samples': 14510080, 'steps': 28339, 'loss/train': 1.8342550992965698}
-03/04/2022 22:45:36 - INFO - codeparrot_training - Step 28340: {'lr': 0.00046193074440627, 'samples': 14510592, 'steps': 28340, 'loss/train': 0.17486226558685303}
-03/04/2022 22:45:39 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/04/2022 22:45:41 - INFO - codeparrot_training - Step 28341: {'lr': 0.0004619279294532561, 'samples': 14511104, 'steps': 28341, 'loss/train': 1.5536885261535645}
-03/04/2022 22:45:45 - INFO - codeparrot_training - Step 28342: {'lr': 0.00046192511440475083, 'samples': 14511616, 'steps': 28342, 'loss/train': 1.8736741542816162}
-03/04/2022 22:45:47 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/04/2022 22:45:50 - INFO - codeparrot_training - Step 28343: {'lr': 0.00046192229926075526, 'samples': 14512128, 'steps': 28343, 'loss/train': 1.3841402530670166}
-03/04/2022 22:45:53 - INFO - codeparrot_training - Step 28344: {'lr': 0.0004619194840212708, 'samples': 14512640, 'steps': 28344, 'loss/train': 1.4966727495193481}
-03/04/2022 22:45:55 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/04/2022 22:45:58 - INFO - codeparrot_training - Step 28345: {'lr': 0.0004619166686862987, 'samples': 14513152, 'steps': 28345, 'loss/train': 1.6909773349761963}
-03/04/2022 22:46:02 - INFO - codeparrot_training - Step 28346: {'lr': 0.0004619138532558402, 'samples': 14513664, 'steps': 28346, 'loss/train': 1.8510650396347046}
-03/04/2022 22:46:04 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/04/2022 22:46:07 - INFO - codeparrot_training - Step 28347: {'lr': 0.00046191103772989664, 'samples': 14514176, 'steps': 28347, 'loss/train': 1.9116324186325073}
-03/04/2022 22:46:10 - INFO - codeparrot_training - Step 28348: {'lr': 0.00046190822210846917, 'samples': 14514688, 'steps': 28348, 'loss/train': 2.1827337741851807}
-03/04/2022 22:46:12 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/04/2022 22:46:15 - INFO - codeparrot_training - Step 28349: {'lr': 0.0004619054063915592, 'samples': 14515200, 'steps': 28349, 'loss/train': 1.698214054107666}
-03/04/2022 22:46:18 - INFO - codeparrot_training - Step 28350: {'lr': 0.00046190259057916786, 'samples': 14515712, 'steps': 28350, 'loss/train': 1.3486562967300415}
-03/04/2022 22:46:20 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/04/2022 22:46:24 - INFO - codeparrot_training - Step 28351: {'lr': 0.0004618997746712965, 'samples': 14516224, 'steps': 28351, 'loss/train': 2.1203606128692627}
-03/04/2022 22:46:27 - INFO - codeparrot_training - Step 28352: {'lr': 0.00046189695866794635, 'samples': 14516736, 'steps': 28352, 'loss/train': 1.3322757482528687}
-03/04/2022 22:46:28 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/04/2022 22:46:32 - INFO - codeparrot_training - Step 28353: {'lr': 0.00046189414256911875, 'samples': 14517248, 'steps': 28353, 'loss/train': 1.6637177467346191}
-03/04/2022 22:46:35 - INFO - codeparrot_training - Step 28354: {'lr': 0.0004618913263748149, 'samples': 14517760, 'steps': 28354, 'loss/train': 2.0440452098846436}
-03/04/2022 22:46:36 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/04/2022 22:46:40 - INFO - codeparrot_training - Step 28355: {'lr': 0.0004618885100850361, 'samples': 14518272, 'steps': 28355, 'loss/train': 1.7147034406661987}
-03/04/2022 22:46:44 - INFO - codeparrot_training - Step 28356: {'lr': 0.0004618856936997836, 'samples': 14518784, 'steps': 28356, 'loss/train': 2.6594667434692383}
-03/04/2022 22:46:45 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/04/2022 22:46:49 - INFO - codeparrot_training - Step 28357: {'lr': 0.0004618828772190586, 'samples': 14519296, 'steps': 28357, 'loss/train': 1.209424376487732}
-03/04/2022 22:46:52 - INFO - codeparrot_training - Step 28358: {'lr': 0.0004618800606428626, 'samples': 14519808, 'steps': 28358, 'loss/train': 2.7648284435272217}
-03/04/2022 22:46:53 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/04/2022 22:46:57 - INFO - codeparrot_training - Step 28359: {'lr': 0.00046187724397119657, 'samples': 14520320, 'steps': 28359, 'loss/train': 1.7226858139038086}
-03/04/2022 22:47:00 - INFO - codeparrot_training - Step 28360: {'lr': 0.000461874427204062, 'samples': 14520832, 'steps': 28360, 'loss/train': 2.4177238941192627}
-03/04/2022 22:47:01 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 22:47:06 - INFO - codeparrot_training - Step 28361: {'lr': 0.00046187161034146, 'samples': 14521344, 'steps': 28361, 'loss/train': 2.15651535987854}
-03/04/2022 22:47:09 - INFO - codeparrot_training - Step 28362: {'lr': 0.00046186879338339207, 'samples': 14521856, 'steps': 28362, 'loss/train': 2.2936675548553467}
-03/04/2022 22:47:10 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/04/2022 22:47:14 - INFO - codeparrot_training - Step 28363: {'lr': 0.0004618659763298592, 'samples': 14522368, 'steps': 28363, 'loss/train': 2.2216598987579346}
-03/04/2022 22:47:17 - INFO - codeparrot_training - Step 28364: {'lr': 0.00046186315918086285, 'samples': 14522880, 'steps': 28364, 'loss/train': 0.9725690484046936}
-03/04/2022 22:47:18 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/04/2022 22:47:23 - INFO - codeparrot_training - Step 28365: {'lr': 0.0004618603419364042, 'samples': 14523392, 'steps': 28365, 'loss/train': 1.909342885017395}
-03/04/2022 22:47:26 - INFO - codeparrot_training - Step 28366: {'lr': 0.00046185752459648456, 'samples': 14523904, 'steps': 28366, 'loss/train': 1.893879771232605}
-03/04/2022 22:47:27 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/04/2022 22:47:31 - INFO - codeparrot_training - Step 28367: {'lr': 0.00046185470716110516, 'samples': 14524416, 'steps': 28367, 'loss/train': 1.3622266054153442}
-03/04/2022 22:47:34 - INFO - codeparrot_training - Step 28368: {'lr': 0.00046185188963026734, 'samples': 14524928, 'steps': 28368, 'loss/train': 1.9037989377975464}
-03/04/2022 22:47:35 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/04/2022 22:47:39 - INFO - codeparrot_training - Step 28369: {'lr': 0.0004618490720039723, 'samples': 14525440, 'steps': 28369, 'loss/train': 1.6392556428909302}
-03/04/2022 22:47:43 - INFO - codeparrot_training - Step 28370: {'lr': 0.0004618462542822214, 'samples': 14525952, 'steps': 28370, 'loss/train': 2.110544204711914}
-03/04/2022 22:47:43 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/04/2022 22:47:48 - INFO - codeparrot_training - Step 28371: {'lr': 0.0004618434364650158, 'samples': 14526464, 'steps': 28371, 'loss/train': 0.12755286693572998}
-03/04/2022 22:47:51 - INFO - codeparrot_training - Step 28372: {'lr': 0.00046184061855235683, 'samples': 14526976, 'steps': 28372, 'loss/train': 1.712847113609314}
-03/04/2022 22:47:51 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/04/2022 22:47:56 - INFO - codeparrot_training - Step 28373: {'lr': 0.00046183780054424574, 'samples': 14527488, 'steps': 28373, 'loss/train': 0.7448714375495911}
-03/04/2022 22:47:59 - INFO - codeparrot_training - Step 28374: {'lr': 0.00046183498244068376, 'samples': 14528000, 'steps': 28374, 'loss/train': 1.497391939163208}
-03/04/2022 22:48:00 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 22:48:05 - INFO - codeparrot_training - Step 28375: {'lr': 0.00046183216424167226, 'samples': 14528512, 'steps': 28375, 'loss/train': 2.7550015449523926}
-03/04/2022 22:48:08 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/04/2022 22:48:10 - INFO - codeparrot_training - Step 28376: {'lr': 0.0004618293459472124, 'samples': 14529024, 'steps': 28376, 'loss/train': 1.7029379606246948}
-03/04/2022 22:48:13 - INFO - codeparrot_training - Step 28377: {'lr': 0.0004618265275573056, 'samples': 14529536, 'steps': 28377, 'loss/train': 1.5451273918151855}
-03/04/2022 22:48:16 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/04/2022 22:48:18 - INFO - codeparrot_training - Step 28378: {'lr': 0.00046182370907195294, 'samples': 14530048, 'steps': 28378, 'loss/train': 1.0116934776306152}
-03/04/2022 22:48:22 - INFO - codeparrot_training - Step 28379: {'lr': 0.00046182089049115585, 'samples': 14530560, 'steps': 28379, 'loss/train': 0.2080044150352478}
-03/04/2022 22:48:24 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/04/2022 22:48:27 - INFO - codeparrot_training - Step 28380: {'lr': 0.0004618180718149155, 'samples': 14531072, 'steps': 28380, 'loss/train': 2.1246297359466553}
-03/04/2022 22:48:30 - INFO - codeparrot_training - Step 28381: {'lr': 0.00046181525304323325, 'samples': 14531584, 'steps': 28381, 'loss/train': 2.2423717975616455}
-03/04/2022 22:48:32 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/04/2022 22:48:35 - INFO - codeparrot_training - Step 28382: {'lr': 0.0004618124341761102, 'samples': 14532096, 'steps': 28382, 'loss/train': 2.007514476776123}
-03/04/2022 22:48:38 - INFO - codeparrot_training - Step 28383: {'lr': 0.0004618096152135478, 'samples': 14532608, 'steps': 28383, 'loss/train': 0.834243893623352}
-03/04/2022 22:48:41 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/04/2022 22:48:44 - INFO - codeparrot_training - Step 28384: {'lr': 0.00046180679615554735, 'samples': 14533120, 'steps': 28384, 'loss/train': 1.4318647384643555}
-03/04/2022 22:48:47 - INFO - codeparrot_training - Step 28385: {'lr': 0.00046180397700210985, 'samples': 14533632, 'steps': 28385, 'loss/train': 0.20897673070430756}
-03/04/2022 22:48:49 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 22:48:52 - INFO - codeparrot_training - Step 28386: {'lr': 0.0004618011577532368, 'samples': 14534144, 'steps': 28386, 'loss/train': 2.137322187423706}
-03/04/2022 22:48:55 - INFO - codeparrot_training - Step 28387: {'lr': 0.0004617983384089295, 'samples': 14534656, 'steps': 28387, 'loss/train': 2.148057222366333}
-03/04/2022 22:48:57 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/04/2022 22:49:00 - INFO - codeparrot_training - Step 28388: {'lr': 0.00046179551896918916, 'samples': 14535168, 'steps': 28388, 'loss/train': 1.7843319177627563}
-03/04/2022 22:49:04 - INFO - codeparrot_training - Step 28389: {'lr': 0.00046179269943401693, 'samples': 14535680, 'steps': 28389, 'loss/train': 2.668386936187744}
-03/04/2022 22:49:06 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/04/2022 22:49:09 - INFO - codeparrot_training - Step 28390: {'lr': 0.00046178987980341414, 'samples': 14536192, 'steps': 28390, 'loss/train': 1.7163957357406616}
-03/04/2022 22:49:12 - INFO - codeparrot_training - Step 28391: {'lr': 0.00046178706007738227, 'samples': 14536704, 'steps': 28391, 'loss/train': 2.1705682277679443}
-03/04/2022 22:49:14 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/04/2022 22:49:17 - INFO - codeparrot_training - Step 28392: {'lr': 0.0004617842402559223, 'samples': 14537216, 'steps': 28392, 'loss/train': 1.45749831199646}
-03/04/2022 22:49:20 - INFO - codeparrot_training - Step 28393: {'lr': 0.0004617814203390356, 'samples': 14537728, 'steps': 28393, 'loss/train': 2.0853567123413086}
-03/04/2022 22:49:22 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/04/2022 22:49:26 - INFO - codeparrot_training - Step 28394: {'lr': 0.0004617786003267235, 'samples': 14538240, 'steps': 28394, 'loss/train': 1.7724525928497314}
-03/04/2022 22:49:29 - INFO - codeparrot_training - Step 28395: {'lr': 0.00046177578021898717, 'samples': 14538752, 'steps': 28395, 'loss/train': 2.6610617637634277}
-03/04/2022 22:49:31 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/04/2022 22:49:34 - INFO - codeparrot_training - Step 28396: {'lr': 0.000461772960015828, 'samples': 14539264, 'steps': 28396, 'loss/train': 0.30445003509521484}
-03/04/2022 22:49:37 - INFO - codeparrot_training - Step 28397: {'lr': 0.00046177013971724723, 'samples': 14539776, 'steps': 28397, 'loss/train': 2.1253702640533447}
-03/04/2022 22:49:40 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 22:49:43 - INFO - codeparrot_training - Step 28398: {'lr': 0.00046176731932324604, 'samples': 14540288, 'steps': 28398, 'loss/train': 2.1879992485046387}
-03/04/2022 22:49:46 - INFO - codeparrot_training - Step 28399: {'lr': 0.0004617644988338258, 'samples': 14540800, 'steps': 28399, 'loss/train': 1.6910182237625122}
-03/04/2022 22:49:48 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/04/2022 22:49:51 - INFO - codeparrot_training - Step 28400: {'lr': 0.0004617616782489877, 'samples': 14541312, 'steps': 28400, 'loss/train': 1.452311635017395}
-03/04/2022 22:49:54 - INFO - codeparrot_training - Step 28401: {'lr': 0.00046175885756873314, 'samples': 14541824, 'steps': 28401, 'loss/train': 1.4132397174835205}
-03/04/2022 22:49:56 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/04/2022 22:49:59 - INFO - codeparrot_training - Step 28402: {'lr': 0.00046175603679306324, 'samples': 14542336, 'steps': 28402, 'loss/train': 1.4782369136810303}
-03/04/2022 22:50:03 - INFO - codeparrot_training - Step 28403: {'lr': 0.0004617532159219794, 'samples': 14542848, 'steps': 28403, 'loss/train': 1.411097764968872}
-03/04/2022 22:50:04 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/04/2022 22:50:08 - INFO - codeparrot_training - Step 28404: {'lr': 0.0004617503949554828, 'samples': 14543360, 'steps': 28404, 'loss/train': 1.7750134468078613}
-03/04/2022 22:50:11 - INFO - codeparrot_training - Step 28405: {'lr': 0.0004617475738935747, 'samples': 14543872, 'steps': 28405, 'loss/train': 2.292668342590332}
-03/04/2022 22:50:12 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/04/2022 22:50:16 - INFO - codeparrot_training - Step 28406: {'lr': 0.0004617447527362564, 'samples': 14544384, 'steps': 28406, 'loss/train': 1.2514328956604004}
-03/04/2022 22:50:19 - INFO - codeparrot_training - Step 28407: {'lr': 0.00046174193148352914, 'samples': 14544896, 'steps': 28407, 'loss/train': 0.8554359078407288}
-03/04/2022 22:50:21 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 22:50:25 - INFO - codeparrot_training - Step 28408: {'lr': 0.00046173911013539437, 'samples': 14545408, 'steps': 28408, 'loss/train': 0.1482871174812317}
-03/04/2022 22:50:28 - INFO - codeparrot_training - Step 28409: {'lr': 0.0004617362886918531, 'samples': 14545920, 'steps': 28409, 'loss/train': 1.4405052661895752}
-03/04/2022 22:50:29 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/04/2022 22:50:33 - INFO - codeparrot_training - Step 28410: {'lr': 0.0004617334671529069, 'samples': 14546432, 'steps': 28410, 'loss/train': 1.8034029006958008}
-03/04/2022 22:50:36 - INFO - codeparrot_training - Step 28411: {'lr': 0.0004617306455185567, 'samples': 14546944, 'steps': 28411, 'loss/train': 1.5738331079483032}
-03/04/2022 22:50:37 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/04/2022 22:50:41 - INFO - codeparrot_training - Step 28412: {'lr': 0.00046172782378880404, 'samples': 14547456, 'steps': 28412, 'loss/train': 1.3957966566085815}
-03/04/2022 22:50:45 - INFO - codeparrot_training - Step 28413: {'lr': 0.00046172500196364996, 'samples': 14547968, 'steps': 28413, 'loss/train': 1.7327498197555542}
-03/04/2022 22:50:46 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/04/2022 22:50:50 - INFO - codeparrot_training - Step 28414: {'lr': 0.000461722180043096, 'samples': 14548480, 'steps': 28414, 'loss/train': 1.4061049222946167}
-03/04/2022 22:50:53 - INFO - codeparrot_training - Step 28415: {'lr': 0.0004617193580271433, 'samples': 14548992, 'steps': 28415, 'loss/train': 1.9827089309692383}
-03/04/2022 22:50:54 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/04/2022 22:50:58 - INFO - codeparrot_training - Step 28416: {'lr': 0.000461716535915793, 'samples': 14549504, 'steps': 28416, 'loss/train': 2.591987133026123}
-03/04/2022 22:51:01 - INFO - codeparrot_training - Step 28417: {'lr': 0.0004617137137090466, 'samples': 14550016, 'steps': 28417, 'loss/train': 1.0727282762527466}
-03/04/2022 22:51:02 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/04/2022 22:51:07 - INFO - codeparrot_training - Step 28418: {'lr': 0.0004617108914069052, 'samples': 14550528, 'steps': 28418, 'loss/train': 1.788729190826416}
-03/04/2022 22:51:10 - INFO - codeparrot_training - Step 28419: {'lr': 0.0004617080690093701, 'samples': 14551040, 'steps': 28419, 'loss/train': 1.5807162523269653}
-03/04/2022 22:51:10 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 22:51:15 - INFO - codeparrot_training - Step 28420: {'lr': 0.00046170524651644276, 'samples': 14551552, 'steps': 28420, 'loss/train': 2.2590601444244385}
-03/04/2022 22:51:18 - INFO - codeparrot_training - Step 28421: {'lr': 0.00046170242392812425, 'samples': 14552064, 'steps': 28421, 'loss/train': 1.6716374158859253}
-03/04/2022 22:51:18 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/04/2022 22:51:23 - INFO - codeparrot_training - Step 28422: {'lr': 0.0004616996012444158, 'samples': 14552576, 'steps': 28422, 'loss/train': 2.3578341007232666}
-03/04/2022 22:51:27 - INFO - codeparrot_training - Step 28423: {'lr': 0.00046169677846531884, 'samples': 14553088, 'steps': 28423, 'loss/train': 2.3878164291381836}
-03/04/2022 22:51:27 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 22:51:32 - INFO - codeparrot_training - Step 28424: {'lr': 0.0004616939555908346, 'samples': 14553600, 'steps': 28424, 'loss/train': 1.8753529787063599}
-03/04/2022 22:51:35 - INFO - codeparrot_training - Step 28425: {'lr': 0.0004616911326209643, 'samples': 14554112, 'steps': 28425, 'loss/train': 2.1106035709381104}
-03/04/2022 22:51:35 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/04/2022 22:51:40 - INFO - codeparrot_training - Step 28426: {'lr': 0.0004616883095557092, 'samples': 14554624, 'steps': 28426, 'loss/train': 2.177588701248169}
-03/04/2022 22:51:43 - INFO - codeparrot_training - Step 28427: {'lr': 0.0004616854863950707, 'samples': 14555136, 'steps': 28427, 'loss/train': 1.2556391954421997}
-03/04/2022 22:51:44 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/04/2022 22:51:49 - INFO - codeparrot_training - Step 28428: {'lr': 0.00046168266313904995, 'samples': 14555648, 'steps': 28428, 'loss/train': 0.1952565759420395}
-03/04/2022 22:51:52 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/04/2022 22:51:54 - INFO - codeparrot_training - Step 28429: {'lr': 0.00046167983978764827, 'samples': 14556160, 'steps': 28429, 'loss/train': 1.4494187831878662}
-03/04/2022 22:51:57 - INFO - codeparrot_training - Step 28430: {'lr': 0.0004616770163408669, 'samples': 14556672, 'steps': 28430, 'loss/train': 1.780761480331421}
-03/04/2022 22:52:00 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/04/2022 22:52:02 - INFO - codeparrot_training - Step 28431: {'lr': 0.00046167419279870715, 'samples': 14557184, 'steps': 28431, 'loss/train': 1.9864543676376343}
-03/04/2022 22:52:06 - INFO - codeparrot_training - Step 28432: {'lr': 0.00046167136916117025, 'samples': 14557696, 'steps': 28432, 'loss/train': 0.8525907397270203}
-03/04/2022 22:52:08 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 22:52:11 - INFO - codeparrot_training - Step 28433: {'lr': 0.00046166854542825756, 'samples': 14558208, 'steps': 28433, 'loss/train': 1.578946828842163}
-03/04/2022 22:52:14 - INFO - codeparrot_training - Step 28434: {'lr': 0.0004616657215999702, 'samples': 14558720, 'steps': 28434, 'loss/train': 1.2968952655792236}
-03/04/2022 22:52:16 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/04/2022 22:52:19 - INFO - codeparrot_training - Step 28435: {'lr': 0.0004616628976763096, 'samples': 14559232, 'steps': 28435, 'loss/train': 1.6871817111968994}
-03/04/2022 22:52:22 - INFO - codeparrot_training - Step 28436: {'lr': 0.0004616600736572769, 'samples': 14559744, 'steps': 28436, 'loss/train': 2.314330577850342}
-03/04/2022 22:52:24 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/04/2022 22:52:28 - INFO - codeparrot_training - Step 28437: {'lr': 0.0004616572495428735, 'samples': 14560256, 'steps': 28437, 'loss/train': 1.055090308189392}
-03/04/2022 22:52:31 - INFO - codeparrot_training - Step 28438: {'lr': 0.0004616544253331006, 'samples': 14560768, 'steps': 28438, 'loss/train': 1.1708316802978516}
-03/04/2022 22:52:33 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/04/2022 22:52:36 - INFO - codeparrot_training - Step 28439: {'lr': 0.00046165160102795943, 'samples': 14561280, 'steps': 28439, 'loss/train': 1.9060810804367065}
-03/04/2022 22:52:39 - INFO - codeparrot_training - Step 28440: {'lr': 0.0004616487766274514, 'samples': 14561792, 'steps': 28440, 'loss/train': 1.8800501823425293}
-03/04/2022 22:52:41 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 22:52:45 - INFO - codeparrot_training - Step 28441: {'lr': 0.0004616459521315777, 'samples': 14562304, 'steps': 28441, 'loss/train': 1.5542160272598267}
-03/04/2022 22:52:48 - INFO - codeparrot_training - Step 28442: {'lr': 0.0004616431275403395, 'samples': 14562816, 'steps': 28442, 'loss/train': 0.7190385460853577}
-03/04/2022 22:52:49 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/04/2022 22:52:53 - INFO - codeparrot_training - Step 28443: {'lr': 0.0004616403028537382, 'samples': 14563328, 'steps': 28443, 'loss/train': 1.2053087949752808}
-03/04/2022 22:52:56 - INFO - codeparrot_training - Step 28444: {'lr': 0.0004616374780717751, 'samples': 14563840, 'steps': 28444, 'loss/train': 2.3801608085632324}
-03/04/2022 22:52:58 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/04/2022 22:53:01 - INFO - codeparrot_training - Step 28445: {'lr': 0.0004616346531944514, 'samples': 14564352, 'steps': 28445, 'loss/train': 1.797059178352356}
-03/04/2022 22:53:05 - INFO - codeparrot_training - Step 28446: {'lr': 0.00046163182822176835, 'samples': 14564864, 'steps': 28446, 'loss/train': 1.571852445602417}
-03/04/2022 22:53:06 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 22:53:10 - INFO - codeparrot_training - Step 28447: {'lr': 0.0004616290031537273, 'samples': 14565376, 'steps': 28447, 'loss/train': 1.5171570777893066}
-03/04/2022 22:53:13 - INFO - codeparrot_training - Step 28448: {'lr': 0.0004616261779903295, 'samples': 14565888, 'steps': 28448, 'loss/train': 1.0717830657958984}
-03/04/2022 22:53:14 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/04/2022 22:53:18 - INFO - codeparrot_training - Step 28449: {'lr': 0.0004616233527315762, 'samples': 14566400, 'steps': 28449, 'loss/train': 1.2439640760421753}
-03/04/2022 22:53:21 - INFO - codeparrot_training - Step 28450: {'lr': 0.0004616205273774686, 'samples': 14566912, 'steps': 28450, 'loss/train': 2.185582160949707}
-03/04/2022 22:53:22 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/04/2022 22:53:27 - INFO - codeparrot_training - Step 28451: {'lr': 0.00046161770192800817, 'samples': 14567424, 'steps': 28451, 'loss/train': 1.9288722276687622}
-03/04/2022 22:53:30 - INFO - codeparrot_training - Step 28452: {'lr': 0.000461614876383196, 'samples': 14567936, 'steps': 28452, 'loss/train': 2.313890218734741}
-03/04/2022 22:53:30 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/04/2022 22:53:35 - INFO - codeparrot_training - Step 28453: {'lr': 0.0004616120507430335, 'samples': 14568448, 'steps': 28453, 'loss/train': 1.4159350395202637}
-03/04/2022 22:53:38 - INFO - codeparrot_training - Step 28454: {'lr': 0.00046160922500752176, 'samples': 14568960, 'steps': 28454, 'loss/train': 1.677953839302063}
-03/04/2022 22:53:38 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/04/2022 22:53:43 - INFO - codeparrot_training - Step 28455: {'lr': 0.0004616063991766623, 'samples': 14569472, 'steps': 28455, 'loss/train': 0.6012064218521118}
-03/04/2022 22:53:47 - INFO - codeparrot_training - Step 28456: {'lr': 0.0004616035732504562, 'samples': 14569984, 'steps': 28456, 'loss/train': 2.0722954273223877}
-03/04/2022 22:53:47 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 22:53:52 - INFO - codeparrot_training - Step 28457: {'lr': 0.0004616007472289048, 'samples': 14570496, 'steps': 28457, 'loss/train': 1.4919414520263672}
-03/04/2022 22:53:55 - INFO - codeparrot_training - Step 28458: {'lr': 0.00046159792111200937, 'samples': 14571008, 'steps': 28458, 'loss/train': 1.0324054956436157}
-03/04/2022 22:53:55 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/04/2022 22:54:00 - INFO - codeparrot_training - Step 28459: {'lr': 0.0004615950948997711, 'samples': 14571520, 'steps': 28459, 'loss/train': 2.5812346935272217}
-03/04/2022 22:54:03 - INFO - codeparrot_training - Step 28460: {'lr': 0.0004615922685921915, 'samples': 14572032, 'steps': 28460, 'loss/train': 0.8905381560325623}
-03/04/2022 22:54:03 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/04/2022 22:54:09 - INFO - codeparrot_training - Step 28461: {'lr': 0.0004615894421892716, 'samples': 14572544, 'steps': 28461, 'loss/train': 1.9900462627410889}
-03/04/2022 22:54:12 - INFO - codeparrot_training - Step 28462: {'lr': 0.0004615866156910128, 'samples': 14573056, 'steps': 28462, 'loss/train': 1.9953563213348389}
-03/04/2022 22:54:12 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/04/2022 22:54:17 - INFO - codeparrot_training - Step 28463: {'lr': 0.00046158378909741626, 'samples': 14573568, 'steps': 28463, 'loss/train': 1.8494478464126587}
-03/04/2022 22:54:20 - INFO - codeparrot_training - Step 28464: {'lr': 0.00046158096240848343, 'samples': 14574080, 'steps': 28464, 'loss/train': 0.9831640720367432}
-03/04/2022 22:54:20 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/04/2022 22:54:26 - INFO - codeparrot_training - Step 28465: {'lr': 0.00046157813562421545, 'samples': 14574592, 'steps': 28465, 'loss/train': 1.8662008047103882}
-03/04/2022 22:54:29 - INFO - codeparrot_training - Step 28466: {'lr': 0.0004615753087446136, 'samples': 14575104, 'steps': 28466, 'loss/train': 2.0512847900390625}
-03/04/2022 22:54:29 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/04/2022 22:54:34 - INFO - codeparrot_training - Step 28467: {'lr': 0.00046157248176967915, 'samples': 14575616, 'steps': 28467, 'loss/train': 2.474247694015503}
-03/04/2022 22:54:38 - INFO - codeparrot_training - Step 28468: {'lr': 0.0004615696546994135, 'samples': 14576128, 'steps': 28468, 'loss/train': 1.91470205783844}
-03/04/2022 22:54:39 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 22:54:43 - INFO - codeparrot_training - Step 28469: {'lr': 0.00046156682753381774, 'samples': 14576640, 'steps': 28469, 'loss/train': 1.0590317249298096}
-03/04/2022 22:54:46 - INFO - codeparrot_training - Step 28470: {'lr': 0.0004615640002728932, 'samples': 14577152, 'steps': 28470, 'loss/train': 1.599726915359497}
-03/04/2022 22:54:47 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 22:54:51 - INFO - codeparrot_training - Step 28471: {'lr': 0.00046156117291664133, 'samples': 14577664, 'steps': 28471, 'loss/train': 1.7394338846206665}
-03/04/2022 22:54:54 - INFO - codeparrot_training - Step 28472: {'lr': 0.0004615583454650632, 'samples': 14578176, 'steps': 28472, 'loss/train': 2.329432487487793}
-03/04/2022 22:54:55 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/04/2022 22:55:00 - INFO - codeparrot_training - Step 28473: {'lr': 0.00046155551791816007, 'samples': 14578688, 'steps': 28473, 'loss/train': 1.5264135599136353}
-03/04/2022 22:55:03 - INFO - codeparrot_training - Step 28474: {'lr': 0.00046155269027593337, 'samples': 14579200, 'steps': 28474, 'loss/train': 2.007673740386963}
-03/04/2022 22:55:03 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 22:55:08 - INFO - codeparrot_training - Step 28475: {'lr': 0.00046154986253838426, 'samples': 14579712, 'steps': 28475, 'loss/train': 1.7036206722259521}
-03/04/2022 22:55:11 - INFO - codeparrot_training - Step 28476: {'lr': 0.00046154703470551405, 'samples': 14580224, 'steps': 28476, 'loss/train': 2.1684207916259766}
-03/04/2022 22:55:12 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/04/2022 22:55:17 - INFO - codeparrot_training - Step 28477: {'lr': 0.000461544206777324, 'samples': 14580736, 'steps': 28477, 'loss/train': 2.1722216606140137}
-03/04/2022 22:55:20 - INFO - codeparrot_training - Step 28478: {'lr': 0.00046154137875381547, 'samples': 14581248, 'steps': 28478, 'loss/train': 1.5086965560913086}
-03/04/2022 22:55:20 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/04/2022 22:55:25 - INFO - codeparrot_training - Step 28479: {'lr': 0.00046153855063498964, 'samples': 14581760, 'steps': 28479, 'loss/train': 1.878096580505371}
-03/04/2022 22:55:28 - INFO - codeparrot_training - Step 28480: {'lr': 0.00046153572242084776, 'samples': 14582272, 'steps': 28480, 'loss/train': 2.5475211143493652}
-03/04/2022 22:55:28 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/04/2022 22:55:33 - INFO - codeparrot_training - Step 28481: {'lr': 0.0004615328941113911, 'samples': 14582784, 'steps': 28481, 'loss/train': 1.6084961891174316}
-03/04/2022 22:55:36 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/04/2022 22:55:39 - INFO - codeparrot_training - Step 28482: {'lr': 0.00046153006570662106, 'samples': 14583296, 'steps': 28482, 'loss/train': 1.972991943359375}
-03/04/2022 22:55:42 - INFO - codeparrot_training - Step 28483: {'lr': 0.0004615272372065388, 'samples': 14583808, 'steps': 28483, 'loss/train': 1.9568727016448975}
-03/04/2022 22:55:44 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/04/2022 22:55:47 - INFO - codeparrot_training - Step 28484: {'lr': 0.0004615244086111456, 'samples': 14584320, 'steps': 28484, 'loss/train': 1.4594602584838867}
-03/04/2022 22:55:50 - INFO - codeparrot_training - Step 28485: {'lr': 0.00046152157992044283, 'samples': 14584832, 'steps': 28485, 'loss/train': 2.522332191467285}
-03/04/2022 22:55:53 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/04/2022 22:55:55 - INFO - codeparrot_training - Step 28486: {'lr': 0.0004615187511344316, 'samples': 14585344, 'steps': 28486, 'loss/train': 0.589413583278656}
-03/04/2022 22:55:59 - INFO - codeparrot_training - Step 28487: {'lr': 0.00046151592225311347, 'samples': 14585856, 'steps': 28487, 'loss/train': 1.6642252206802368}
-03/04/2022 22:56:01 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/04/2022 22:56:04 - INFO - codeparrot_training - Step 28488: {'lr': 0.0004615130932764894, 'samples': 14586368, 'steps': 28488, 'loss/train': 1.789724349975586}
-03/04/2022 22:56:07 - INFO - codeparrot_training - Step 28489: {'lr': 0.0004615102642045608, 'samples': 14586880, 'steps': 28489, 'loss/train': 1.284641146659851}
-03/04/2022 22:56:09 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/04/2022 22:56:12 - INFO - codeparrot_training - Step 28490: {'lr': 0.00046150743503732897, 'samples': 14587392, 'steps': 28490, 'loss/train': 1.8705921173095703}
-03/04/2022 22:56:15 - INFO - codeparrot_training - Step 28491: {'lr': 0.0004615046057747951, 'samples': 14587904, 'steps': 28491, 'loss/train': 2.8348071575164795}
-03/04/2022 22:56:18 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/04/2022 22:56:21 - INFO - codeparrot_training - Step 28492: {'lr': 0.0004615017764169606, 'samples': 14588416, 'steps': 28492, 'loss/train': 0.3164556622505188}
-03/04/2022 22:56:24 - INFO - codeparrot_training - Step 28493: {'lr': 0.00046149894696382655, 'samples': 14588928, 'steps': 28493, 'loss/train': 1.3121024370193481}
-03/04/2022 22:56:27 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/04/2022 22:56:29 - INFO - codeparrot_training - Step 28494: {'lr': 0.00046149611741539445, 'samples': 14589440, 'steps': 28494, 'loss/train': 1.538524866104126}
-03/04/2022 22:56:32 - INFO - codeparrot_training - Step 28495: {'lr': 0.00046149328777166543, 'samples': 14589952, 'steps': 28495, 'loss/train': 1.417362928390503}
-03/04/2022 22:56:35 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/04/2022 22:56:38 - INFO - codeparrot_training - Step 28496: {'lr': 0.0004614904580326408, 'samples': 14590464, 'steps': 28496, 'loss/train': 1.5697916746139526}
-03/04/2022 22:56:41 - INFO - codeparrot_training - Step 28497: {'lr': 0.0004614876281983218, 'samples': 14590976, 'steps': 28497, 'loss/train': 1.3986625671386719}
-03/04/2022 22:56:43 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/04/2022 22:56:46 - INFO - codeparrot_training - Step 28498: {'lr': 0.0004614847982687097, 'samples': 14591488, 'steps': 28498, 'loss/train': 1.5352305173873901}
-03/04/2022 22:56:49 - INFO - codeparrot_training - Step 28499: {'lr': 0.0004614819682438059, 'samples': 14592000, 'steps': 28499, 'loss/train': 1.2939802408218384}
-03/04/2022 22:56:51 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/04/2022 22:56:54 - INFO - codeparrot_training - Step 28500: {'lr': 0.00046147913812361155, 'samples': 14592512, 'steps': 28500, 'loss/train': 1.5529202222824097}
-03/04/2022 22:56:58 - INFO - codeparrot_training - Step 28501: {'lr': 0.000461476307908128, 'samples': 14593024, 'steps': 28501, 'loss/train': 1.1584223508834839}
-03/04/2022 22:56:59 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 22:57:03 - INFO - codeparrot_training - Step 28502: {'lr': 0.00046147347759735647, 'samples': 14593536, 'steps': 28502, 'loss/train': 2.0944275856018066}
-03/04/2022 22:57:06 - INFO - codeparrot_training - Step 28503: {'lr': 0.00046147064719129823, 'samples': 14594048, 'steps': 28503, 'loss/train': 2.059772491455078}
-03/04/2022 22:57:08 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 22:57:11 - INFO - codeparrot_training - Step 28504: {'lr': 0.00046146781668995456, 'samples': 14594560, 'steps': 28504, 'loss/train': 1.6675336360931396}
-03/04/2022 22:57:14 - INFO - codeparrot_training - Step 28505: {'lr': 0.0004614649860933268, 'samples': 14595072, 'steps': 28505, 'loss/train': 2.645833969116211}
-03/04/2022 22:57:16 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/04/2022 22:57:20 - INFO - codeparrot_training - Step 28506: {'lr': 0.0004614621554014162, 'samples': 14595584, 'steps': 28506, 'loss/train': 0.8208023905754089}
-03/04/2022 22:57:23 - INFO - codeparrot_training - Step 28507: {'lr': 0.00046145932461422396, 'samples': 14596096, 'steps': 28507, 'loss/train': 1.9489738941192627}
-03/04/2022 22:57:25 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 22:57:28 - INFO - codeparrot_training - Step 28508: {'lr': 0.00046145649373175145, 'samples': 14596608, 'steps': 28508, 'loss/train': 1.492097020149231}
-03/04/2022 22:57:31 - INFO - codeparrot_training - Step 28509: {'lr': 0.0004614536627539999, 'samples': 14597120, 'steps': 28509, 'loss/train': 1.5528852939605713}
-03/04/2022 22:57:33 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/04/2022 22:57:37 - INFO - codeparrot_training - Step 28510: {'lr': 0.0004614508316809706, 'samples': 14597632, 'steps': 28510, 'loss/train': 2.003201484680176}
-03/04/2022 22:57:40 - INFO - codeparrot_training - Step 28511: {'lr': 0.00046144800051266477, 'samples': 14598144, 'steps': 28511, 'loss/train': 1.5394105911254883}
-03/04/2022 22:57:41 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/04/2022 22:57:45 - INFO - codeparrot_training - Step 28512: {'lr': 0.00046144516924908377, 'samples': 14598656, 'steps': 28512, 'loss/train': 1.510074257850647}
-03/04/2022 22:57:48 - INFO - codeparrot_training - Step 28513: {'lr': 0.0004614423378902289, 'samples': 14599168, 'steps': 28513, 'loss/train': 1.4555315971374512}
-03/04/2022 22:57:50 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/04/2022 22:57:54 - INFO - codeparrot_training - Step 28514: {'lr': 0.0004614395064361013, 'samples': 14599680, 'steps': 28514, 'loss/train': 1.8934745788574219}
-03/04/2022 22:57:57 - INFO - codeparrot_training - Step 28515: {'lr': 0.00046143667488670226, 'samples': 14600192, 'steps': 28515, 'loss/train': 2.277827739715576}
-03/04/2022 22:57:59 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/04/2022 22:58:02 - INFO - codeparrot_training - Step 28516: {'lr': 0.00046143384324203325, 'samples': 14600704, 'steps': 28516, 'loss/train': 2.4954216480255127}
-03/04/2022 22:58:05 - INFO - codeparrot_training - Step 28517: {'lr': 0.00046143101150209533, 'samples': 14601216, 'steps': 28517, 'loss/train': 1.7485748529434204}
-03/04/2022 22:58:07 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/04/2022 22:58:11 - INFO - codeparrot_training - Step 28518: {'lr': 0.0004614281796668899, 'samples': 14601728, 'steps': 28518, 'loss/train': 1.8947330713272095}
-03/04/2022 22:58:14 - INFO - codeparrot_training - Step 28519: {'lr': 0.0004614253477364182, 'samples': 14602240, 'steps': 28519, 'loss/train': 0.4458111524581909}
-03/04/2022 22:58:15 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/04/2022 22:58:19 - INFO - codeparrot_training - Step 28520: {'lr': 0.0004614225157106815, 'samples': 14602752, 'steps': 28520, 'loss/train': 2.479257106781006}
-03/04/2022 22:58:22 - INFO - codeparrot_training - Step 28521: {'lr': 0.00046141968358968103, 'samples': 14603264, 'steps': 28521, 'loss/train': 1.9931385517120361}
-03/04/2022 22:58:24 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/04/2022 22:58:27 - INFO - codeparrot_training - Step 28522: {'lr': 0.00046141685137341814, 'samples': 14603776, 'steps': 28522, 'loss/train': 1.8274396657943726}
-03/04/2022 22:58:30 - INFO - codeparrot_training - Step 28523: {'lr': 0.00046141401906189404, 'samples': 14604288, 'steps': 28523, 'loss/train': 1.5934008359909058}
-03/04/2022 22:58:32 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/04/2022 22:58:36 - INFO - codeparrot_training - Step 28524: {'lr': 0.0004614111866551101, 'samples': 14604800, 'steps': 28524, 'loss/train': 1.8763766288757324}
-03/04/2022 22:58:39 - INFO - codeparrot_training - Step 28525: {'lr': 0.0004614083541530675, 'samples': 14605312, 'steps': 28525, 'loss/train': 1.0894922018051147}
-03/04/2022 22:58:40 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/04/2022 22:58:44 - INFO - codeparrot_training - Step 28526: {'lr': 0.00046140552155576767, 'samples': 14605824, 'steps': 28526, 'loss/train': 2.3152801990509033}
-03/04/2022 22:58:47 - INFO - codeparrot_training - Step 28527: {'lr': 0.0004614026888632116, 'samples': 14606336, 'steps': 28527, 'loss/train': 1.2995717525482178}
-03/04/2022 22:58:48 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/04/2022 22:58:52 - INFO - codeparrot_training - Step 28528: {'lr': 0.00046139985607540087, 'samples': 14606848, 'steps': 28528, 'loss/train': 1.8299880027770996}
-03/04/2022 22:58:56 - INFO - codeparrot_training - Step 28529: {'lr': 0.00046139702319233656, 'samples': 14607360, 'steps': 28529, 'loss/train': 2.5086138248443604}
-03/04/2022 22:58:56 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/04/2022 22:59:01 - INFO - codeparrot_training - Step 28530: {'lr': 0.00046139419021402005, 'samples': 14607872, 'steps': 28530, 'loss/train': 1.9696965217590332}
-03/04/2022 22:59:04 - INFO - codeparrot_training - Step 28531: {'lr': 0.00046139135714045253, 'samples': 14608384, 'steps': 28531, 'loss/train': 1.411405086517334}
-03/04/2022 22:59:05 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 22:59:09 - INFO - codeparrot_training - Step 28532: {'lr': 0.00046138852397163547, 'samples': 14608896, 'steps': 28532, 'loss/train': 1.364651083946228}
-03/04/2022 22:59:12 - INFO - codeparrot_training - Step 28533: {'lr': 0.00046138569070756984, 'samples': 14609408, 'steps': 28533, 'loss/train': 1.2493674755096436}
-03/04/2022 22:59:13 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/04/2022 22:59:18 - INFO - codeparrot_training - Step 28534: {'lr': 0.00046138285734825715, 'samples': 14609920, 'steps': 28534, 'loss/train': 1.67771315574646}
-03/04/2022 22:59:21 - INFO - codeparrot_training - Step 28535: {'lr': 0.0004613800238936986, 'samples': 14610432, 'steps': 28535, 'loss/train': 1.2505425214767456}
-03/04/2022 22:59:22 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/04/2022 22:59:26 - INFO - codeparrot_training - Step 28536: {'lr': 0.0004613771903438955, 'samples': 14610944, 'steps': 28536, 'loss/train': 2.1148691177368164}
-03/04/2022 22:59:29 - INFO - codeparrot_training - Step 28537: {'lr': 0.00046137435669884897, 'samples': 14611456, 'steps': 28537, 'loss/train': 2.1968178749084473}
-03/04/2022 22:59:30 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/04/2022 22:59:35 - INFO - codeparrot_training - Step 28538: {'lr': 0.00046137152295856054, 'samples': 14611968, 'steps': 28538, 'loss/train': 1.8504951000213623}
-03/04/2022 22:59:38 - INFO - codeparrot_training - Step 28539: {'lr': 0.0004613686891230313, 'samples': 14612480, 'steps': 28539, 'loss/train': 1.7645478248596191}
-03/04/2022 22:59:38 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 22:59:43 - INFO - codeparrot_training - Step 28540: {'lr': 0.0004613658551922627, 'samples': 14612992, 'steps': 28540, 'loss/train': 1.5802167654037476}
-03/04/2022 22:59:46 - INFO - codeparrot_training - Step 28541: {'lr': 0.0004613630211662558, 'samples': 14613504, 'steps': 28541, 'loss/train': 1.40403151512146}
-03/04/2022 22:59:46 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 22:59:52 - INFO - codeparrot_training - Step 28542: {'lr': 0.00046136018704501203, 'samples': 14614016, 'steps': 28542, 'loss/train': 1.731514573097229}
-03/04/2022 22:59:55 - INFO - codeparrot_training - Step 28543: {'lr': 0.00046135735282853263, 'samples': 14614528, 'steps': 28543, 'loss/train': 1.297905445098877}
-03/04/2022 22:59:56 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/04/2022 23:00:00 - INFO - codeparrot_training - Step 28544: {'lr': 0.0004613545185168188, 'samples': 14615040, 'steps': 28544, 'loss/train': 0.8428840041160583}
-03/04/2022 23:00:04 - INFO - codeparrot_training - Step 28545: {'lr': 0.0004613516841098719, 'samples': 14615552, 'steps': 28545, 'loss/train': 2.143965244293213}
-03/04/2022 23:00:05 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/04/2022 23:00:09 - INFO - codeparrot_training - Step 28546: {'lr': 0.0004613488496076933, 'samples': 14616064, 'steps': 28546, 'loss/train': 2.10507869720459}
-03/04/2022 23:00:12 - INFO - codeparrot_training - Step 28547: {'lr': 0.00046134601501028404, 'samples': 14616576, 'steps': 28547, 'loss/train': 1.8600928783416748}
-03/04/2022 23:00:13 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/04/2022 23:00:17 - INFO - codeparrot_training - Step 28548: {'lr': 0.0004613431803176456, 'samples': 14617088, 'steps': 28548, 'loss/train': 1.8657844066619873}
-03/04/2022 23:00:21 - INFO - codeparrot_training - Step 28549: {'lr': 0.00046134034552977924, 'samples': 14617600, 'steps': 28549, 'loss/train': 0.9800437688827515}
-03/04/2022 23:00:22 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 23:00:26 - INFO - codeparrot_training - Step 28550: {'lr': 0.00046133751064668605, 'samples': 14618112, 'steps': 28550, 'loss/train': 1.6841028928756714}
-03/04/2022 23:00:29 - INFO - codeparrot_training - Step 28551: {'lr': 0.0004613346756683675, 'samples': 14618624, 'steps': 28551, 'loss/train': 3.004523754119873}
-03/04/2022 23:00:30 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/04/2022 23:00:34 - INFO - codeparrot_training - Step 28552: {'lr': 0.0004613318405948248, 'samples': 14619136, 'steps': 28552, 'loss/train': 1.5826362371444702}
-03/04/2022 23:00:37 - INFO - codeparrot_training - Step 28553: {'lr': 0.00046132900542605925, 'samples': 14619648, 'steps': 28553, 'loss/train': 1.356889009475708}
-03/04/2022 23:00:39 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/04/2022 23:00:43 - INFO - codeparrot_training - Step 28554: {'lr': 0.0004613261701620721, 'samples': 14620160, 'steps': 28554, 'loss/train': 1.6440720558166504}
-03/04/2022 23:00:46 - INFO - codeparrot_training - Step 28555: {'lr': 0.0004613233348028646, 'samples': 14620672, 'steps': 28555, 'loss/train': 1.8009424209594727}
-03/04/2022 23:00:48 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/04/2022 23:00:51 - INFO - codeparrot_training - Step 28556: {'lr': 0.0004613204993484381, 'samples': 14621184, 'steps': 28556, 'loss/train': 1.994805932044983}
-03/04/2022 23:00:54 - INFO - codeparrot_training - Step 28557: {'lr': 0.00046131766379879386, 'samples': 14621696, 'steps': 28557, 'loss/train': 1.1962062120437622}
-03/04/2022 23:00:56 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/04/2022 23:01:00 - INFO - codeparrot_training - Step 28558: {'lr': 0.0004613148281539331, 'samples': 14622208, 'steps': 28558, 'loss/train': 0.7661890387535095}
-03/04/2022 23:01:03 - INFO - codeparrot_training - Step 28559: {'lr': 0.00046131199241385726, 'samples': 14622720, 'steps': 28559, 'loss/train': 1.4039686918258667}
-03/04/2022 23:01:05 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/04/2022 23:01:08 - INFO - codeparrot_training - Step 28560: {'lr': 0.0004613091565785673, 'samples': 14623232, 'steps': 28560, 'loss/train': 1.9979979991912842}
-03/04/2022 23:01:11 - INFO - codeparrot_training - Step 28561: {'lr': 0.0004613063206480649, 'samples': 14623744, 'steps': 28561, 'loss/train': 2.9927990436553955}
-03/04/2022 23:01:13 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 23:01:16 - INFO - codeparrot_training - Step 28562: {'lr': 0.000461303484622351, 'samples': 14624256, 'steps': 28562, 'loss/train': 1.378042459487915}
-03/04/2022 23:01:19 - INFO - codeparrot_training - Step 28563: {'lr': 0.00046130064850142703, 'samples': 14624768, 'steps': 28563, 'loss/train': 1.649056077003479}
-03/04/2022 23:01:21 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/04/2022 23:01:25 - INFO - codeparrot_training - Step 28564: {'lr': 0.0004612978122852942, 'samples': 14625280, 'steps': 28564, 'loss/train': 2.349705696105957}
-03/04/2022 23:01:28 - INFO - codeparrot_training - Step 28565: {'lr': 0.000461294975973954, 'samples': 14625792, 'steps': 28565, 'loss/train': 1.9318636655807495}
-03/04/2022 23:01:29 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/04/2022 23:01:33 - INFO - codeparrot_training - Step 28566: {'lr': 0.0004612921395674074, 'samples': 14626304, 'steps': 28566, 'loss/train': 1.240950107574463}
-03/04/2022 23:01:36 - INFO - codeparrot_training - Step 28567: {'lr': 0.0004612893030656559, 'samples': 14626816, 'steps': 28567, 'loss/train': 1.9817887544631958}
-03/04/2022 23:01:38 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/04/2022 23:01:42 - INFO - codeparrot_training - Step 28568: {'lr': 0.0004612864664687007, 'samples': 14627328, 'steps': 28568, 'loss/train': 1.3493638038635254}
-03/04/2022 23:01:45 - INFO - codeparrot_training - Step 28569: {'lr': 0.0004612836297765429, 'samples': 14627840, 'steps': 28569, 'loss/train': 1.2660952806472778}
-03/04/2022 23:01:46 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/04/2022 23:01:50 - INFO - codeparrot_training - Step 28570: {'lr': 0.00046128079298918414, 'samples': 14628352, 'steps': 28570, 'loss/train': 1.0702208280563354}
-03/04/2022 23:01:53 - INFO - codeparrot_training - Step 28571: {'lr': 0.00046127795610662547, 'samples': 14628864, 'steps': 28571, 'loss/train': 1.3752094507217407}
-03/04/2022 23:01:54 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/04/2022 23:01:58 - INFO - codeparrot_training - Step 28572: {'lr': 0.0004612751191288682, 'samples': 14629376, 'steps': 28572, 'loss/train': 0.5533729791641235}
-03/04/2022 23:02:01 - INFO - codeparrot_training - Step 28573: {'lr': 0.00046127228205591366, 'samples': 14629888, 'steps': 28573, 'loss/train': 2.1714673042297363}
-03/04/2022 23:02:02 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/04/2022 23:02:07 - INFO - codeparrot_training - Step 28574: {'lr': 0.0004612694448877631, 'samples': 14630400, 'steps': 28574, 'loss/train': 2.225487232208252}
-03/04/2022 23:02:10 - INFO - codeparrot_training - Step 28575: {'lr': 0.00046126660762441774, 'samples': 14630912, 'steps': 28575, 'loss/train': 1.105965256690979}
-03/04/2022 23:02:11 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/04/2022 23:02:15 - INFO - codeparrot_training - Step 28576: {'lr': 0.00046126377026587897, 'samples': 14631424, 'steps': 28576, 'loss/train': 1.7449263334274292}
-03/04/2022 23:02:18 - INFO - codeparrot_training - Step 28577: {'lr': 0.0004612609328121479, 'samples': 14631936, 'steps': 28577, 'loss/train': 1.8084131479263306}
-03/04/2022 23:02:19 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/04/2022 23:02:23 - INFO - codeparrot_training - Step 28578: {'lr': 0.000461258095263226, 'samples': 14632448, 'steps': 28578, 'loss/train': 1.202929139137268}
-03/04/2022 23:02:27 - INFO - codeparrot_training - Step 28579: {'lr': 0.00046125525761911445, 'samples': 14632960, 'steps': 28579, 'loss/train': 2.0499606132507324}
-03/04/2022 23:02:27 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/04/2022 23:02:32 - INFO - codeparrot_training - Step 28580: {'lr': 0.00046125241987981445, 'samples': 14633472, 'steps': 28580, 'loss/train': 2.564877510070801}
-03/04/2022 23:02:35 - INFO - codeparrot_training - Step 28581: {'lr': 0.0004612495820453275, 'samples': 14633984, 'steps': 28581, 'loss/train': 1.6800137758255005}
-03/04/2022 23:02:36 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/04/2022 23:02:40 - INFO - codeparrot_training - Step 28582: {'lr': 0.0004612467441156547, 'samples': 14634496, 'steps': 28582, 'loss/train': 2.3042914867401123}
-03/04/2022 23:02:44 - INFO - codeparrot_training - Step 28583: {'lr': 0.00046124390609079735, 'samples': 14635008, 'steps': 28583, 'loss/train': 1.3925615549087524}
-03/04/2022 23:02:44 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/04/2022 23:02:50 - INFO - codeparrot_training - Step 28584: {'lr': 0.00046124106797075683, 'samples': 14635520, 'steps': 28584, 'loss/train': 1.453824758529663}
-03/04/2022 23:02:53 - INFO - codeparrot_training - Step 28585: {'lr': 0.00046123822975553425, 'samples': 14636032, 'steps': 28585, 'loss/train': 1.31509268283844}
-03/04/2022 23:02:55 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/04/2022 23:02:58 - INFO - codeparrot_training - Step 28586: {'lr': 0.00046123539144513103, 'samples': 14636544, 'steps': 28586, 'loss/train': 1.5003575086593628}
-03/04/2022 23:03:01 - INFO - codeparrot_training - Step 28587: {'lr': 0.00046123255303954835, 'samples': 14637056, 'steps': 28587, 'loss/train': 1.305431842803955}
-03/04/2022 23:03:04 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 23:03:06 - INFO - codeparrot_training - Step 28588: {'lr': 0.0004612297145387876, 'samples': 14637568, 'steps': 28588, 'loss/train': 2.311103343963623}
-03/04/2022 23:03:10 - INFO - codeparrot_training - Step 28589: {'lr': 0.00046122687594285, 'samples': 14638080, 'steps': 28589, 'loss/train': 1.3941694498062134}
-03/04/2022 23:03:12 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/04/2022 23:03:15 - INFO - codeparrot_training - Step 28590: {'lr': 0.0004612240372517368, 'samples': 14638592, 'steps': 28590, 'loss/train': 1.9809764623641968}
-03/04/2022 23:03:18 - INFO - codeparrot_training - Step 28591: {'lr': 0.00046122119846544936, 'samples': 14639104, 'steps': 28591, 'loss/train': 1.8237049579620361}
-03/04/2022 23:03:21 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/04/2022 23:03:23 - INFO - codeparrot_training - Step 28592: {'lr': 0.00046121835958398883, 'samples': 14639616, 'steps': 28592, 'loss/train': 1.5348312854766846}
-03/04/2022 23:03:26 - INFO - codeparrot_training - Step 28593: {'lr': 0.0004612155206073566, 'samples': 14640128, 'steps': 28593, 'loss/train': 2.1318936347961426}
-03/04/2022 23:03:29 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/04/2022 23:03:32 - INFO - codeparrot_training - Step 28594: {'lr': 0.000461212681535554, 'samples': 14640640, 'steps': 28594, 'loss/train': 1.4095181226730347}
-03/04/2022 23:03:35 - INFO - codeparrot_training - Step 28595: {'lr': 0.0004612098423685821, 'samples': 14641152, 'steps': 28595, 'loss/train': 1.649467945098877}
-03/04/2022 23:03:37 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/04/2022 23:03:40 - INFO - codeparrot_training - Step 28596: {'lr': 0.0004612070031064424, 'samples': 14641664, 'steps': 28596, 'loss/train': 1.4351922273635864}
-03/04/2022 23:03:43 - INFO - codeparrot_training - Step 28597: {'lr': 0.000461204163749136, 'samples': 14642176, 'steps': 28597, 'loss/train': 2.1127779483795166}
-03/04/2022 23:03:46 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/04/2022 23:03:49 - INFO - codeparrot_training - Step 28598: {'lr': 0.0004612013242966643, 'samples': 14642688, 'steps': 28598, 'loss/train': 2.1396238803863525}
-03/04/2022 23:03:52 - INFO - codeparrot_training - Step 28599: {'lr': 0.0004611984847490285, 'samples': 14643200, 'steps': 28599, 'loss/train': 1.9402045011520386}
-03/04/2022 23:03:54 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/04/2022 23:03:57 - INFO - codeparrot_training - Step 28600: {'lr': 0.00046119564510623, 'samples': 14643712, 'steps': 28600, 'loss/train': 1.1657992601394653}
-03/04/2022 23:04:00 - INFO - codeparrot_training - Step 28601: {'lr': 0.00046119280536827, 'samples': 14644224, 'steps': 28601, 'loss/train': 1.6281999349594116}
-03/04/2022 23:04:02 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 23:04:05 - INFO - codeparrot_training - Step 28602: {'lr': 0.0004611899655351497, 'samples': 14644736, 'steps': 28602, 'loss/train': 0.1884302794933319}
-03/04/2022 23:04:09 - INFO - codeparrot_training - Step 28603: {'lr': 0.0004611871256068705, 'samples': 14645248, 'steps': 28603, 'loss/train': 1.8855360746383667}
-03/04/2022 23:04:11 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 23:04:14 - INFO - codeparrot_training - Step 28604: {'lr': 0.0004611842855834336, 'samples': 14645760, 'steps': 28604, 'loss/train': 2.1736245155334473}
-03/04/2022 23:04:17 - INFO - codeparrot_training - Step 28605: {'lr': 0.00046118144546484043, 'samples': 14646272, 'steps': 28605, 'loss/train': 2.097539186477661}
-03/04/2022 23:04:20 - INFO - codeparrot_training - Step 28606: {'lr': 0.0004611786052510921, 'samples': 14646784, 'steps': 28606, 'loss/train': 1.454010248184204}
-03/04/2022 23:04:20 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 23:04:26 - INFO - codeparrot_training - Step 28607: {'lr': 0.0004611757649421899, 'samples': 14647296, 'steps': 28607, 'loss/train': 2.1387901306152344}
-03/04/2022 23:04:28 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/04/2022 23:04:31 - INFO - codeparrot_training - Step 28608: {'lr': 0.0004611729245381352, 'samples': 14647808, 'steps': 28608, 'loss/train': 1.71255362033844}
-03/04/2022 23:04:34 - INFO - codeparrot_training - Step 28609: {'lr': 0.00046117008403892925, 'samples': 14648320, 'steps': 28609, 'loss/train': 1.5402244329452515}
-03/04/2022 23:04:36 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/04/2022 23:04:39 - INFO - codeparrot_training - Step 28610: {'lr': 0.0004611672434445733, 'samples': 14648832, 'steps': 28610, 'loss/train': 2.221043348312378}
-03/04/2022 23:04:42 - INFO - codeparrot_training - Step 28611: {'lr': 0.0004611644027550687, 'samples': 14649344, 'steps': 28611, 'loss/train': 1.771355152130127}
-03/04/2022 23:04:45 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/04/2022 23:04:48 - INFO - codeparrot_training - Step 28612: {'lr': 0.00046116156197041657, 'samples': 14649856, 'steps': 28612, 'loss/train': 2.7303073406219482}
-03/04/2022 23:04:51 - INFO - codeparrot_training - Step 28613: {'lr': 0.0004611587210906184, 'samples': 14650368, 'steps': 28613, 'loss/train': 1.7049132585525513}
-03/04/2022 23:04:53 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/04/2022 23:04:56 - INFO - codeparrot_training - Step 28614: {'lr': 0.0004611558801156753, 'samples': 14650880, 'steps': 28614, 'loss/train': 1.4431854486465454}
-03/04/2022 23:04:59 - INFO - codeparrot_training - Step 28615: {'lr': 0.0004611530390455887, 'samples': 14651392, 'steps': 28615, 'loss/train': 1.3910313844680786}
-03/04/2022 23:05:01 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 23:05:04 - INFO - codeparrot_training - Step 28616: {'lr': 0.00046115019788035974, 'samples': 14651904, 'steps': 28616, 'loss/train': 1.5558934211730957}
-03/04/2022 23:05:08 - INFO - codeparrot_training - Step 28617: {'lr': 0.00046114735661998975, 'samples': 14652416, 'steps': 28617, 'loss/train': 1.3270963430404663}
-03/04/2022 23:05:10 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/04/2022 23:05:13 - INFO - codeparrot_training - Step 28618: {'lr': 0.0004611445152644801, 'samples': 14652928, 'steps': 28618, 'loss/train': 2.0974578857421875}
-03/04/2022 23:05:16 - INFO - codeparrot_training - Step 28619: {'lr': 0.00046114167381383186, 'samples': 14653440, 'steps': 28619, 'loss/train': 1.9519639015197754}
-03/04/2022 23:05:18 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/04/2022 23:05:21 - INFO - codeparrot_training - Step 28620: {'lr': 0.0004611388322680465, 'samples': 14653952, 'steps': 28620, 'loss/train': 1.351516842842102}
-03/04/2022 23:05:24 - INFO - codeparrot_training - Step 28621: {'lr': 0.0004611359906271253, 'samples': 14654464, 'steps': 28621, 'loss/train': 2.1074767112731934}
-03/04/2022 23:05:26 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/04/2022 23:05:30 - INFO - codeparrot_training - Step 28622: {'lr': 0.0004611331488910694, 'samples': 14654976, 'steps': 28622, 'loss/train': 1.977159023284912}
-03/04/2022 23:05:33 - INFO - codeparrot_training - Step 28623: {'lr': 0.00046113030705988026, 'samples': 14655488, 'steps': 28623, 'loss/train': 0.16818027198314667}
-03/04/2022 23:05:34 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 23:05:38 - INFO - codeparrot_training - Step 28624: {'lr': 0.000461127465133559, 'samples': 14656000, 'steps': 28624, 'loss/train': 1.1417585611343384}
-03/04/2022 23:05:41 - INFO - codeparrot_training - Step 28625: {'lr': 0.0004611246231121069, 'samples': 14656512, 'steps': 28625, 'loss/train': 2.4288015365600586}
-03/04/2022 23:05:42 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 23:05:47 - INFO - codeparrot_training - Step 28626: {'lr': 0.00046112178099552535, 'samples': 14657024, 'steps': 28626, 'loss/train': 1.7648500204086304}
-03/04/2022 23:05:50 - INFO - codeparrot_training - Step 28627: {'lr': 0.0004611189387838156, 'samples': 14657536, 'steps': 28627, 'loss/train': 1.6399967670440674}
-03/04/2022 23:05:52 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/04/2022 23:05:55 - INFO - codeparrot_training - Step 28628: {'lr': 0.00046111609647697893, 'samples': 14658048, 'steps': 28628, 'loss/train': 1.6772977113723755}
-03/04/2022 23:05:59 - INFO - codeparrot_training - Step 28629: {'lr': 0.0004611132540750166, 'samples': 14658560, 'steps': 28629, 'loss/train': 1.4163635969161987}
-03/04/2022 23:06:01 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 23:06:04 - INFO - codeparrot_training - Step 28630: {'lr': 0.00046111041157792987, 'samples': 14659072, 'steps': 28630, 'loss/train': 1.9044311046600342}
-03/04/2022 23:06:07 - INFO - codeparrot_training - Step 28631: {'lr': 0.00046110756898572, 'samples': 14659584, 'steps': 28631, 'loss/train': 1.6293809413909912}
-03/04/2022 23:06:09 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/04/2022 23:06:12 - INFO - codeparrot_training - Step 28632: {'lr': 0.0004611047262983884, 'samples': 14660096, 'steps': 28632, 'loss/train': 1.6695833206176758}
-03/04/2022 23:06:15 - INFO - codeparrot_training - Step 28633: {'lr': 0.00046110188351593625, 'samples': 14660608, 'steps': 28633, 'loss/train': 1.1326595544815063}
-03/04/2022 23:06:18 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/04/2022 23:06:21 - INFO - codeparrot_training - Step 28634: {'lr': 0.0004610990406383648, 'samples': 14661120, 'steps': 28634, 'loss/train': 1.068790078163147}
-03/04/2022 23:06:24 - INFO - codeparrot_training - Step 28635: {'lr': 0.00046109619766567547, 'samples': 14661632, 'steps': 28635, 'loss/train': 1.6011168956756592}
-03/04/2022 23:06:27 - INFO - codeparrot_training - Step 28636: {'lr': 0.0004610933545978694, 'samples': 14662144, 'steps': 28636, 'loss/train': 0.3230849504470825}
-03/04/2022 23:06:27 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/04/2022 23:06:32 - INFO - codeparrot_training - Step 28637: {'lr': 0.0004610905114349478, 'samples': 14662656, 'steps': 28637, 'loss/train': 1.9791392087936401}
-03/04/2022 23:06:35 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/04/2022 23:06:38 - INFO - codeparrot_training - Step 28638: {'lr': 0.0004610876681769123, 'samples': 14663168, 'steps': 28638, 'loss/train': 1.7662285566329956}
-03/04/2022 23:06:41 - INFO - codeparrot_training - Step 28639: {'lr': 0.0004610848248237638, 'samples': 14663680, 'steps': 28639, 'loss/train': 1.9425069093704224}
-03/04/2022 23:06:43 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 23:06:46 - INFO - codeparrot_training - Step 28640: {'lr': 0.00046108198137550377, 'samples': 14664192, 'steps': 28640, 'loss/train': 1.447983980178833}
-03/04/2022 23:06:49 - INFO - codeparrot_training - Step 28641: {'lr': 0.0004610791378321335, 'samples': 14664704, 'steps': 28641, 'loss/train': 1.7699235677719116}
-03/04/2022 23:06:52 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 23:06:55 - INFO - codeparrot_training - Step 28642: {'lr': 0.0004610762941936542, 'samples': 14665216, 'steps': 28642, 'loss/train': 2.1628410816192627}
-03/04/2022 23:06:58 - INFO - codeparrot_training - Step 28643: {'lr': 0.0004610734504600671, 'samples': 14665728, 'steps': 28643, 'loss/train': 2.102304458618164}
-03/04/2022 23:07:00 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/04/2022 23:07:03 - INFO - codeparrot_training - Step 28644: {'lr': 0.00046107060663137366, 'samples': 14666240, 'steps': 28644, 'loss/train': 1.6837979555130005}
-03/04/2022 23:07:06 - INFO - codeparrot_training - Step 28645: {'lr': 0.00046106776270757506, 'samples': 14666752, 'steps': 28645, 'loss/train': 1.6544755697250366}
-03/04/2022 23:07:08 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/04/2022 23:07:11 - INFO - codeparrot_training - Step 28646: {'lr': 0.0004610649186886725, 'samples': 14667264, 'steps': 28646, 'loss/train': 1.214952826499939}
-03/04/2022 23:07:14 - INFO - codeparrot_training - Step 28647: {'lr': 0.00046106207457466744, 'samples': 14667776, 'steps': 28647, 'loss/train': 0.6320163607597351}
-03/04/2022 23:07:16 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/04/2022 23:07:20 - INFO - codeparrot_training - Step 28648: {'lr': 0.0004610592303655611, 'samples': 14668288, 'steps': 28648, 'loss/train': 1.8409264087677002}
-03/04/2022 23:07:23 - INFO - codeparrot_training - Step 28649: {'lr': 0.0004610563860613546, 'samples': 14668800, 'steps': 28649, 'loss/train': 1.0237106084823608}
-03/04/2022 23:07:25 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/04/2022 23:07:28 - INFO - codeparrot_training - Step 28650: {'lr': 0.00046105354166204937, 'samples': 14669312, 'steps': 28650, 'loss/train': 1.8430724143981934}
-03/04/2022 23:07:31 - INFO - codeparrot_training - Step 28651: {'lr': 0.00046105069716764676, 'samples': 14669824, 'steps': 28651, 'loss/train': 2.554124116897583}
-03/04/2022 23:07:33 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 23:07:36 - INFO - codeparrot_training - Step 28652: {'lr': 0.00046104785257814786, 'samples': 14670336, 'steps': 28652, 'loss/train': 1.9458526372909546}
-03/04/2022 23:07:40 - INFO - codeparrot_training - Step 28653: {'lr': 0.0004610450078935541, 'samples': 14670848, 'steps': 28653, 'loss/train': 1.4395183324813843}
-03/04/2022 23:07:41 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/04/2022 23:07:45 - INFO - codeparrot_training - Step 28654: {'lr': 0.00046104216311386676, 'samples': 14671360, 'steps': 28654, 'loss/train': 1.8047356605529785}
-03/04/2022 23:07:48 - INFO - codeparrot_training - Step 28655: {'lr': 0.000461039318239087, 'samples': 14671872, 'steps': 28655, 'loss/train': 0.11996857076883316}
-03/04/2022 23:07:50 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 23:07:53 - INFO - codeparrot_training - Step 28656: {'lr': 0.00046103647326921625, 'samples': 14672384, 'steps': 28656, 'loss/train': 2.1457059383392334}
-03/04/2022 23:07:56 - INFO - codeparrot_training - Step 28657: {'lr': 0.00046103362820425567, 'samples': 14672896, 'steps': 28657, 'loss/train': 1.3384227752685547}
-03/04/2022 23:07:58 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/04/2022 23:08:02 - INFO - codeparrot_training - Step 28658: {'lr': 0.00046103078304420665, 'samples': 14673408, 'steps': 28658, 'loss/train': 1.3913062810897827}
-03/04/2022 23:08:05 - INFO - codeparrot_training - Step 28659: {'lr': 0.0004610279377890704, 'samples': 14673920, 'steps': 28659, 'loss/train': 1.3581987619400024}
-03/04/2022 23:08:06 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 23:08:10 - INFO - codeparrot_training - Step 28660: {'lr': 0.00046102509243884813, 'samples': 14674432, 'steps': 28660, 'loss/train': 2.2495434284210205}
-03/04/2022 23:08:13 - INFO - codeparrot_training - Step 28661: {'lr': 0.0004610222469935413, 'samples': 14674944, 'steps': 28661, 'loss/train': 1.2739447355270386}
-03/04/2022 23:08:14 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/04/2022 23:08:19 - INFO - codeparrot_training - Step 28662: {'lr': 0.000461019401453151, 'samples': 14675456, 'steps': 28662, 'loss/train': 1.962471842765808}
-03/04/2022 23:08:22 - INFO - codeparrot_training - Step 28663: {'lr': 0.00046101655581767874, 'samples': 14675968, 'steps': 28663, 'loss/train': 0.7328404188156128}
-03/04/2022 23:08:23 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/04/2022 23:08:27 - INFO - codeparrot_training - Step 28664: {'lr': 0.0004610137100871257, 'samples': 14676480, 'steps': 28664, 'loss/train': 1.6926188468933105}
-03/04/2022 23:08:30 - INFO - codeparrot_training - Step 28665: {'lr': 0.00046101086426149297, 'samples': 14676992, 'steps': 28665, 'loss/train': 1.5700749158859253}
-03/04/2022 23:08:31 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/04/2022 23:08:35 - INFO - codeparrot_training - Step 28666: {'lr': 0.0004610080183407821, 'samples': 14677504, 'steps': 28666, 'loss/train': 1.2041345834732056}
-03/04/2022 23:08:39 - INFO - codeparrot_training - Step 28667: {'lr': 0.0004610051723249943, 'samples': 14678016, 'steps': 28667, 'loss/train': 2.1835572719573975}
-03/04/2022 23:08:39 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/04/2022 23:08:44 - INFO - codeparrot_training - Step 28668: {'lr': 0.0004610023262141308, 'samples': 14678528, 'steps': 28668, 'loss/train': 2.7377028465270996}
-03/04/2022 23:08:47 - INFO - codeparrot_training - Step 28669: {'lr': 0.00046099948000819294, 'samples': 14679040, 'steps': 28669, 'loss/train': 1.737138032913208}
-03/04/2022 23:08:48 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/04/2022 23:08:52 - INFO - codeparrot_training - Step 28670: {'lr': 0.0004609966337071819, 'samples': 14679552, 'steps': 28670, 'loss/train': 2.2142462730407715}
-03/04/2022 23:08:55 - INFO - codeparrot_training - Step 28671: {'lr': 0.00046099378731109906, 'samples': 14680064, 'steps': 28671, 'loss/train': 0.4541628360748291}
-03/04/2022 23:08:56 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/04/2022 23:09:01 - INFO - codeparrot_training - Step 28672: {'lr': 0.00046099094081994565, 'samples': 14680576, 'steps': 28672, 'loss/train': 1.4846153259277344}
-03/04/2022 23:09:04 - INFO - codeparrot_training - Step 28673: {'lr': 0.000460988094233723, 'samples': 14681088, 'steps': 28673, 'loss/train': 1.8271634578704834}
-03/04/2022 23:09:05 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/04/2022 23:09:09 - INFO - codeparrot_training - Step 28674: {'lr': 0.00046098524755243246, 'samples': 14681600, 'steps': 28674, 'loss/train': 2.1662678718566895}
-03/04/2022 23:09:12 - INFO - codeparrot_training - Step 28675: {'lr': 0.0004609824007760751, 'samples': 14682112, 'steps': 28675, 'loss/train': 1.6646757125854492}
-03/04/2022 23:09:13 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/04/2022 23:09:17 - INFO - codeparrot_training - Step 28676: {'lr': 0.0004609795539046524, 'samples': 14682624, 'steps': 28676, 'loss/train': 0.9444484710693359}
-03/04/2022 23:09:21 - INFO - codeparrot_training - Step 28677: {'lr': 0.0004609767069381655, 'samples': 14683136, 'steps': 28677, 'loss/train': 2.473944664001465}
-03/04/2022 23:09:21 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/04/2022 23:09:26 - INFO - codeparrot_training - Step 28678: {'lr': 0.00046097385987661576, 'samples': 14683648, 'steps': 28678, 'loss/train': 1.2074100971221924}
-03/04/2022 23:09:29 - INFO - codeparrot_training - Step 28679: {'lr': 0.00046097101272000454, 'samples': 14684160, 'steps': 28679, 'loss/train': 0.8830896019935608}
-03/04/2022 23:09:30 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/04/2022 23:09:34 - INFO - codeparrot_training - Step 28680: {'lr': 0.0004609681654683329, 'samples': 14684672, 'steps': 28680, 'loss/train': 2.2301034927368164}
-03/04/2022 23:09:38 - INFO - codeparrot_training - Step 28681: {'lr': 0.0004609653181216024, 'samples': 14685184, 'steps': 28681, 'loss/train': 0.8800235986709595}
-03/04/2022 23:09:38 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/04/2022 23:09:43 - INFO - codeparrot_training - Step 28682: {'lr': 0.0004609624706798141, 'samples': 14685696, 'steps': 28682, 'loss/train': 1.996482014656067}
-03/04/2022 23:09:46 - INFO - codeparrot_training - Step 28683: {'lr': 0.00046095962314296934, 'samples': 14686208, 'steps': 28683, 'loss/train': 1.3534278869628906}
-03/04/2022 23:09:46 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/04/2022 23:09:51 - INFO - codeparrot_training - Step 28684: {'lr': 0.00046095677551106953, 'samples': 14686720, 'steps': 28684, 'loss/train': 1.782173752784729}
-03/04/2022 23:09:54 - INFO - codeparrot_training - Step 28685: {'lr': 0.00046095392778411576, 'samples': 14687232, 'steps': 28685, 'loss/train': 1.7090116739273071}
-03/04/2022 23:09:55 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/04/2022 23:10:00 - INFO - codeparrot_training - Step 28686: {'lr': 0.0004609510799621095, 'samples': 14687744, 'steps': 28686, 'loss/train': 1.865818738937378}
-03/04/2022 23:10:03 - INFO - codeparrot_training - Step 28687: {'lr': 0.0004609482320450519, 'samples': 14688256, 'steps': 28687, 'loss/train': 1.9258365631103516}
-03/04/2022 23:10:03 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/04/2022 23:10:08 - INFO - codeparrot_training - Step 28688: {'lr': 0.00046094538403294416, 'samples': 14688768, 'steps': 28688, 'loss/train': 2.0483596324920654}
-03/04/2022 23:10:11 - INFO - codeparrot_training - Step 28689: {'lr': 0.00046094253592578784, 'samples': 14689280, 'steps': 28689, 'loss/train': 1.2860519886016846}
-03/04/2022 23:10:11 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/04/2022 23:10:16 - INFO - codeparrot_training - Step 28690: {'lr': 0.000460939687723584, 'samples': 14689792, 'steps': 28690, 'loss/train': 0.1934487223625183}
-03/04/2022 23:10:19 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/04/2022 23:10:22 - INFO - codeparrot_training - Step 28691: {'lr': 0.000460936839426334, 'samples': 14690304, 'steps': 28691, 'loss/train': 1.7329027652740479}
-03/04/2022 23:10:25 - INFO - codeparrot_training - Step 28692: {'lr': 0.00046093399103403913, 'samples': 14690816, 'steps': 28692, 'loss/train': 1.8477340936660767}
-03/04/2022 23:10:27 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/04/2022 23:10:30 - INFO - codeparrot_training - Step 28693: {'lr': 0.00046093114254670066, 'samples': 14691328, 'steps': 28693, 'loss/train': 1.7601550817489624}
-03/04/2022 23:10:33 - INFO - codeparrot_training - Step 28694: {'lr': 0.0004609282939643199, 'samples': 14691840, 'steps': 28694, 'loss/train': 2.7514965534210205}
-03/04/2022 23:10:36 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/04/2022 23:10:39 - INFO - codeparrot_training - Step 28695: {'lr': 0.00046092544528689806, 'samples': 14692352, 'steps': 28695, 'loss/train': 1.702709436416626}
-03/04/2022 23:10:42 - INFO - codeparrot_training - Step 28696: {'lr': 0.0004609225965144365, 'samples': 14692864, 'steps': 28696, 'loss/train': 2.0398812294006348}
-03/04/2022 23:10:44 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/04/2022 23:10:47 - INFO - codeparrot_training - Step 28697: {'lr': 0.00046091974764693645, 'samples': 14693376, 'steps': 28697, 'loss/train': 1.0523011684417725}
-03/04/2022 23:10:50 - INFO - codeparrot_training - Step 28698: {'lr': 0.0004609168986843992, 'samples': 14693888, 'steps': 28698, 'loss/train': 2.114043712615967}
-03/04/2022 23:10:53 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 23:10:55 - INFO - codeparrot_training - Step 28699: {'lr': 0.000460914049626826, 'samples': 14694400, 'steps': 28699, 'loss/train': 0.6433330774307251}
-03/04/2022 23:10:59 - INFO - codeparrot_training - Step 28700: {'lr': 0.0004609112004742183, 'samples': 14694912, 'steps': 28700, 'loss/train': 1.68015456199646}
-03/04/2022 23:11:01 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/04/2022 23:11:04 - INFO - codeparrot_training - Step 28701: {'lr': 0.0004609083512265773, 'samples': 14695424, 'steps': 28701, 'loss/train': 2.042311191558838}
-03/04/2022 23:11:07 - INFO - codeparrot_training - Step 28702: {'lr': 0.0004609055018839041, 'samples': 14695936, 'steps': 28702, 'loss/train': 2.185877561569214}
-03/04/2022 23:11:09 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/04/2022 23:11:12 - INFO - codeparrot_training - Step 28703: {'lr': 0.0004609026524462002, 'samples': 14696448, 'steps': 28703, 'loss/train': 1.995223879814148}
-03/04/2022 23:11:16 - INFO - codeparrot_training - Step 28704: {'lr': 0.00046089980291346685, 'samples': 14696960, 'steps': 28704, 'loss/train': 1.329836368560791}
-03/04/2022 23:11:21 - INFO - codeparrot_training - Step 28705: {'lr': 0.00046089695328570523, 'samples': 14697472, 'steps': 28705, 'loss/train': 1.8551639318466187}
-03/04/2022 23:11:24 - INFO - codeparrot_training - Step 28706: {'lr': 0.0004608941035629168, 'samples': 14697984, 'steps': 28706, 'loss/train': 1.5789488554000854}
-03/04/2022 23:11:26 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/04/2022 23:11:29 - INFO - codeparrot_training - Step 28707: {'lr': 0.0004608912537451027, 'samples': 14698496, 'steps': 28707, 'loss/train': 1.8238446712493896}
-03/04/2022 23:11:32 - INFO - codeparrot_training - Step 28708: {'lr': 0.0004608884038322642, 'samples': 14699008, 'steps': 28708, 'loss/train': 1.571372389793396}
-03/04/2022 23:11:35 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/04/2022 23:11:38 - INFO - codeparrot_training - Step 28709: {'lr': 0.00046088555382440275, 'samples': 14699520, 'steps': 28709, 'loss/train': 1.3904154300689697}
-03/04/2022 23:11:41 - INFO - codeparrot_training - Step 28710: {'lr': 0.0004608827037215194, 'samples': 14700032, 'steps': 28710, 'loss/train': 1.2568423748016357}
-03/04/2022 23:11:42 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/04/2022 23:11:46 - INFO - codeparrot_training - Step 28711: {'lr': 0.0004608798535236156, 'samples': 14700544, 'steps': 28711, 'loss/train': 1.2774072885513306}
-03/04/2022 23:11:49 - INFO - codeparrot_training - Step 28712: {'lr': 0.0004608770032306926, 'samples': 14701056, 'steps': 28712, 'loss/train': 2.4083003997802734}
-03/04/2022 23:11:51 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/04/2022 23:11:54 - INFO - codeparrot_training - Step 28713: {'lr': 0.0004608741528427517, 'samples': 14701568, 'steps': 28713, 'loss/train': 0.7753598093986511}
-03/04/2022 23:11:58 - INFO - codeparrot_training - Step 28714: {'lr': 0.0004608713023597941, 'samples': 14702080, 'steps': 28714, 'loss/train': 1.733746886253357}
-03/04/2022 23:11:59 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/04/2022 23:12:03 - INFO - codeparrot_training - Step 28715: {'lr': 0.00046086845178182123, 'samples': 14702592, 'steps': 28715, 'loss/train': 1.154794454574585}
-03/04/2022 23:12:06 - INFO - codeparrot_training - Step 28716: {'lr': 0.00046086560110883423, 'samples': 14703104, 'steps': 28716, 'loss/train': 2.2313344478607178}
-03/04/2022 23:12:07 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/04/2022 23:12:11 - INFO - codeparrot_training - Step 28717: {'lr': 0.00046086275034083453, 'samples': 14703616, 'steps': 28717, 'loss/train': 1.5891374349594116}
-03/04/2022 23:12:14 - INFO - codeparrot_training - Step 28718: {'lr': 0.00046085989947782327, 'samples': 14704128, 'steps': 28718, 'loss/train': 0.9811397194862366}
-03/04/2022 23:12:16 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/04/2022 23:12:20 - INFO - codeparrot_training - Step 28719: {'lr': 0.00046085704851980174, 'samples': 14704640, 'steps': 28719, 'loss/train': 2.756617784500122}
-03/04/2022 23:12:23 - INFO - codeparrot_training - Step 28720: {'lr': 0.00046085419746677136, 'samples': 14705152, 'steps': 28720, 'loss/train': 1.3453677892684937}
-03/04/2022 23:12:24 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 23:12:28 - INFO - codeparrot_training - Step 28721: {'lr': 0.00046085134631873326, 'samples': 14705664, 'steps': 28721, 'loss/train': 1.9104872941970825}
-03/04/2022 23:12:31 - INFO - codeparrot_training - Step 28722: {'lr': 0.0004608484950756888, 'samples': 14706176, 'steps': 28722, 'loss/train': 1.799933671951294}
-03/04/2022 23:12:33 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 23:12:37 - INFO - codeparrot_training - Step 28723: {'lr': 0.0004608456437376393, 'samples': 14706688, 'steps': 28723, 'loss/train': 2.1247329711914062}
-03/04/2022 23:12:40 - INFO - codeparrot_training - Step 28724: {'lr': 0.000460842792304586, 'samples': 14707200, 'steps': 28724, 'loss/train': 1.854982614517212}
-03/04/2022 23:12:41 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/04/2022 23:12:45 - INFO - codeparrot_training - Step 28725: {'lr': 0.00046083994077653024, 'samples': 14707712, 'steps': 28725, 'loss/train': 1.4383118152618408}
-03/04/2022 23:12:48 - INFO - codeparrot_training - Step 28726: {'lr': 0.0004608370891534732, 'samples': 14708224, 'steps': 28726, 'loss/train': 1.284668207168579}
-03/04/2022 23:12:49 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/04/2022 23:12:53 - INFO - codeparrot_training - Step 28727: {'lr': 0.0004608342374354162, 'samples': 14708736, 'steps': 28727, 'loss/train': 1.4197306632995605}
-03/04/2022 23:12:56 - INFO - codeparrot_training - Step 28728: {'lr': 0.0004608313856223606, 'samples': 14709248, 'steps': 28728, 'loss/train': 2.655355453491211}
-03/04/2022 23:12:57 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/04/2022 23:13:02 - INFO - codeparrot_training - Step 28729: {'lr': 0.00046082853371430754, 'samples': 14709760, 'steps': 28729, 'loss/train': 1.5164272785186768}
-03/04/2022 23:13:05 - INFO - codeparrot_training - Step 28730: {'lr': 0.0004608256817112585, 'samples': 14710272, 'steps': 28730, 'loss/train': 1.5647177696228027}
-03/04/2022 23:13:06 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/04/2022 23:13:10 - INFO - codeparrot_training - Step 28731: {'lr': 0.00046082282961321466, 'samples': 14710784, 'steps': 28731, 'loss/train': 2.1676509380340576}
-03/04/2022 23:13:13 - INFO - codeparrot_training - Step 28732: {'lr': 0.00046081997742017725, 'samples': 14711296, 'steps': 28732, 'loss/train': 1.963984727859497}
-03/04/2022 23:13:14 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/04/2022 23:13:18 - INFO - codeparrot_training - Step 28733: {'lr': 0.00046081712513214757, 'samples': 14711808, 'steps': 28733, 'loss/train': 0.7657157182693481}
-03/04/2022 23:13:22 - INFO - codeparrot_training - Step 28734: {'lr': 0.0004608142727491271, 'samples': 14712320, 'steps': 28734, 'loss/train': 2.29250431060791}
-03/04/2022 23:13:22 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 23:13:27 - INFO - codeparrot_training - Step 28735: {'lr': 0.00046081142027111683, 'samples': 14712832, 'steps': 28735, 'loss/train': 1.8452332019805908}
-03/04/2022 23:13:30 - INFO - codeparrot_training - Step 28736: {'lr': 0.0004608085676981182, 'samples': 14713344, 'steps': 28736, 'loss/train': 1.7282874584197998}
-03/04/2022 23:13:32 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/04/2022 23:13:36 - INFO - codeparrot_training - Step 28737: {'lr': 0.0004608057150301326, 'samples': 14713856, 'steps': 28737, 'loss/train': 2.009702205657959}
-03/04/2022 23:13:39 - INFO - codeparrot_training - Step 28738: {'lr': 0.00046080286226716106, 'samples': 14714368, 'steps': 28738, 'loss/train': 0.5559707283973694}
-03/04/2022 23:13:40 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/04/2022 23:13:44 - INFO - codeparrot_training - Step 28739: {'lr': 0.00046080000940920506, 'samples': 14714880, 'steps': 28739, 'loss/train': 1.6263608932495117}
-03/04/2022 23:13:47 - INFO - codeparrot_training - Step 28740: {'lr': 0.00046079715645626584, 'samples': 14715392, 'steps': 28740, 'loss/train': 2.5383145809173584}
-03/04/2022 23:13:49 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/04/2022 23:13:53 - INFO - codeparrot_training - Step 28741: {'lr': 0.00046079430340834467, 'samples': 14715904, 'steps': 28741, 'loss/train': 1.1004078388214111}
-03/04/2022 23:13:56 - INFO - codeparrot_training - Step 28742: {'lr': 0.00046079145026544277, 'samples': 14716416, 'steps': 28742, 'loss/train': 1.4663041830062866}
-03/04/2022 23:13:57 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/04/2022 23:14:01 - INFO - codeparrot_training - Step 28743: {'lr': 0.0004607885970275616, 'samples': 14716928, 'steps': 28743, 'loss/train': 1.6839425563812256}
-03/04/2022 23:14:04 - INFO - codeparrot_training - Step 28744: {'lr': 0.0004607857436947023, 'samples': 14717440, 'steps': 28744, 'loss/train': 1.1125373840332031}
-03/04/2022 23:14:05 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/04/2022 23:14:09 - INFO - codeparrot_training - Step 28745: {'lr': 0.00046078289026686616, 'samples': 14717952, 'steps': 28745, 'loss/train': 1.4777553081512451}
-03/04/2022 23:14:12 - INFO - codeparrot_training - Step 28746: {'lr': 0.00046078003674405457, 'samples': 14718464, 'steps': 28746, 'loss/train': 1.8516452312469482}
-03/04/2022 23:14:13 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/04/2022 23:14:18 - INFO - codeparrot_training - Step 28747: {'lr': 0.0004607771831262687, 'samples': 14718976, 'steps': 28747, 'loss/train': 2.0822913646698}
-03/04/2022 23:14:21 - INFO - codeparrot_training - Step 28748: {'lr': 0.00046077432941350993, 'samples': 14719488, 'steps': 28748, 'loss/train': 1.5656276941299438}
-03/04/2022 23:14:22 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/04/2022 23:14:26 - INFO - codeparrot_training - Step 28749: {'lr': 0.00046077147560577943, 'samples': 14720000, 'steps': 28749, 'loss/train': 1.6378145217895508}
-03/04/2022 23:14:30 - INFO - codeparrot_training - Step 28750: {'lr': 0.0004607686217030786, 'samples': 14720512, 'steps': 28750, 'loss/train': 1.9615832567214966}
-03/04/2022 23:14:31 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/04/2022 23:14:35 - INFO - codeparrot_training - Step 28751: {'lr': 0.00046076576770540865, 'samples': 14721024, 'steps': 28751, 'loss/train': 2.1016452312469482}
-03/04/2022 23:14:38 - INFO - codeparrot_training - Step 28752: {'lr': 0.00046076291361277097, 'samples': 14721536, 'steps': 28752, 'loss/train': 2.2397773265838623}
-03/04/2022 23:14:39 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/04/2022 23:14:43 - INFO - codeparrot_training - Step 28753: {'lr': 0.00046076005942516666, 'samples': 14722048, 'steps': 28753, 'loss/train': 1.5671579837799072}
-03/04/2022 23:14:46 - INFO - codeparrot_training - Step 28754: {'lr': 0.0004607572051425972, 'samples': 14722560, 'steps': 28754, 'loss/train': 1.8208417892456055}
-03/04/2022 23:14:47 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/04/2022 23:14:52 - INFO - codeparrot_training - Step 28755: {'lr': 0.00046075435076506376, 'samples': 14723072, 'steps': 28755, 'loss/train': 1.7257890701293945}
-03/04/2022 23:14:55 - INFO - codeparrot_training - Step 28756: {'lr': 0.0004607514962925677, 'samples': 14723584, 'steps': 28756, 'loss/train': 1.4128739833831787}
-03/04/2022 23:14:56 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/04/2022 23:15:00 - INFO - codeparrot_training - Step 28757: {'lr': 0.00046074864172511025, 'samples': 14724096, 'steps': 28757, 'loss/train': 1.6530588865280151}
-03/04/2022 23:15:03 - INFO - codeparrot_training - Step 28758: {'lr': 0.0004607457870626928, 'samples': 14724608, 'steps': 28758, 'loss/train': 2.0480055809020996}
-03/04/2022 23:15:04 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/04/2022 23:15:09 - INFO - codeparrot_training - Step 28759: {'lr': 0.0004607429323053164, 'samples': 14725120, 'steps': 28759, 'loss/train': 1.8267391920089722}
-03/04/2022 23:15:12 - INFO - codeparrot_training - Step 28760: {'lr': 0.0004607400774529825, 'samples': 14725632, 'steps': 28760, 'loss/train': 1.6826145648956299}
-03/04/2022 23:15:13 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/04/2022 23:15:17 - INFO - codeparrot_training - Step 28761: {'lr': 0.0004607372225056925, 'samples': 14726144, 'steps': 28761, 'loss/train': 1.1681545972824097}
-03/04/2022 23:15:20 - INFO - codeparrot_training - Step 28762: {'lr': 0.00046073436746344744, 'samples': 14726656, 'steps': 28762, 'loss/train': 1.515450358390808}
-03/04/2022 23:15:21 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/04/2022 23:15:25 - INFO - codeparrot_training - Step 28763: {'lr': 0.0004607315123262488, 'samples': 14727168, 'steps': 28763, 'loss/train': 1.999114990234375}
-03/04/2022 23:15:29 - INFO - codeparrot_training - Step 28764: {'lr': 0.0004607286570940977, 'samples': 14727680, 'steps': 28764, 'loss/train': 2.160698890686035}
-03/04/2022 23:15:29 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/04/2022 23:15:34 - INFO - codeparrot_training - Step 28765: {'lr': 0.0004607258017669956, 'samples': 14728192, 'steps': 28765, 'loss/train': 1.7898920774459839}
-03/04/2022 23:15:37 - INFO - codeparrot_training - Step 28766: {'lr': 0.0004607229463449437, 'samples': 14728704, 'steps': 28766, 'loss/train': 1.7552697658538818}
-03/04/2022 23:15:38 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/04/2022 23:15:42 - INFO - codeparrot_training - Step 28767: {'lr': 0.00046072009082794333, 'samples': 14729216, 'steps': 28767, 'loss/train': 1.9466519355773926}
-03/04/2022 23:15:45 - INFO - codeparrot_training - Step 28768: {'lr': 0.00046071723521599563, 'samples': 14729728, 'steps': 28768, 'loss/train': 0.09505000710487366}
-03/04/2022 23:15:46 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/04/2022 23:15:51 - INFO - codeparrot_training - Step 28769: {'lr': 0.000460714379509102, 'samples': 14730240, 'steps': 28769, 'loss/train': 2.1645305156707764}
-03/04/2022 23:15:54 - INFO - codeparrot_training - Step 28770: {'lr': 0.0004607115237072638, 'samples': 14730752, 'steps': 28770, 'loss/train': 1.2728168964385986}
-03/04/2022 23:15:54 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/04/2022 23:15:59 - INFO - codeparrot_training - Step 28771: {'lr': 0.00046070866781048225, 'samples': 14731264, 'steps': 28771, 'loss/train': 1.9268834590911865}
-03/04/2022 23:16:02 - INFO - codeparrot_training - Step 28772: {'lr': 0.0004607058118187586, 'samples': 14731776, 'steps': 28772, 'loss/train': 1.425413966178894}
-03/04/2022 23:16:02 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/04/2022 23:16:08 - INFO - codeparrot_training - Step 28773: {'lr': 0.00046070295573209406, 'samples': 14732288, 'steps': 28773, 'loss/train': 1.2314364910125732}
-03/04/2022 23:16:11 - INFO - codeparrot_training - Step 28774: {'lr': 0.00046070009955049017, 'samples': 14732800, 'steps': 28774, 'loss/train': 1.7822479009628296}
-03/04/2022 23:16:11 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/04/2022 23:16:16 - INFO - codeparrot_training - Step 28775: {'lr': 0.000460697243273948, 'samples': 14733312, 'steps': 28775, 'loss/train': 1.2611836194992065}
-03/04/2022 23:16:19 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/04/2022 23:16:22 - INFO - codeparrot_training - Step 28776: {'lr': 0.0004606943869024689, 'samples': 14733824, 'steps': 28776, 'loss/train': 1.8676648139953613}
-03/04/2022 23:16:25 - INFO - codeparrot_training - Step 28777: {'lr': 0.0004606915304360542, 'samples': 14734336, 'steps': 28777, 'loss/train': 1.5964415073394775}
-03/04/2022 23:16:27 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/04/2022 23:16:30 - INFO - codeparrot_training - Step 28778: {'lr': 0.00046068867387470507, 'samples': 14734848, 'steps': 28778, 'loss/train': 2.027876138687134}
-03/04/2022 23:16:33 - INFO - codeparrot_training - Step 28779: {'lr': 0.00046068581721842294, 'samples': 14735360, 'steps': 28779, 'loss/train': 2.274444580078125}
-03/04/2022 23:16:35 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 23:16:39 - INFO - codeparrot_training - Step 28780: {'lr': 0.00046068296046720904, 'samples': 14735872, 'steps': 28780, 'loss/train': 1.1855027675628662}
-03/04/2022 23:16:42 - INFO - codeparrot_training - Step 28781: {'lr': 0.0004606801036210646, 'samples': 14736384, 'steps': 28781, 'loss/train': 6.455958366394043}
-03/04/2022 23:16:45 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/04/2022 23:16:47 - INFO - codeparrot_training - Step 28782: {'lr': 0.000460677246679991, 'samples': 14736896, 'steps': 28782, 'loss/train': 3.410822629928589}
-03/04/2022 23:16:50 - INFO - codeparrot_training - Step 28783: {'lr': 0.00046067438964398944, 'samples': 14737408, 'steps': 28783, 'loss/train': 2.206223249435425}
-03/04/2022 23:16:53 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/04/2022 23:16:56 - INFO - codeparrot_training - Step 28784: {'lr': 0.00046067153251306127, 'samples': 14737920, 'steps': 28784, 'loss/train': 1.7162508964538574}
-03/04/2022 23:16:59 - INFO - codeparrot_training - Step 28785: {'lr': 0.0004606686752872078, 'samples': 14738432, 'steps': 28785, 'loss/train': 1.594719409942627}
-03/04/2022 23:17:02 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/04/2022 23:17:04 - INFO - codeparrot_training - Step 28786: {'lr': 0.0004606658179664302, 'samples': 14738944, 'steps': 28786, 'loss/train': 1.9938952922821045}
-03/04/2022 23:17:07 - INFO - codeparrot_training - Step 28787: {'lr': 0.00046066296055072986, 'samples': 14739456, 'steps': 28787, 'loss/train': 1.5762356519699097}
-03/04/2022 23:17:09 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/04/2022 23:17:12 - INFO - codeparrot_training - Step 28788: {'lr': 0.0004606601030401081, 'samples': 14739968, 'steps': 28788, 'loss/train': 1.337221622467041}
-03/04/2022 23:17:15 - INFO - codeparrot_training - Step 28789: {'lr': 0.0004606572454345661, 'samples': 14740480, 'steps': 28789, 'loss/train': 1.3102432489395142}
-03/04/2022 23:17:18 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/04/2022 23:17:21 - INFO - codeparrot_training - Step 28790: {'lr': 0.0004606543877341052, 'samples': 14740992, 'steps': 28790, 'loss/train': 0.8645076751708984}
-03/04/2022 23:17:24 - INFO - codeparrot_training - Step 28791: {'lr': 0.00046065152993872665, 'samples': 14741504, 'steps': 28791, 'loss/train': 1.2594149112701416}
-03/04/2022 23:17:27 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/04/2022 23:17:29 - INFO - codeparrot_training - Step 28792: {'lr': 0.0004606486720484318, 'samples': 14742016, 'steps': 28792, 'loss/train': 1.2640281915664673}
-03/04/2022 23:17:32 - INFO - codeparrot_training - Step 28793: {'lr': 0.0004606458140632219, 'samples': 14742528, 'steps': 28793, 'loss/train': 1.5857021808624268}
-03/04/2022 23:17:35 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/04/2022 23:17:38 - INFO - codeparrot_training - Step 28794: {'lr': 0.0004606429559830982, 'samples': 14743040, 'steps': 28794, 'loss/train': 2.1024489402770996}
-03/04/2022 23:17:41 - INFO - codeparrot_training - Step 28795: {'lr': 0.00046064009780806217, 'samples': 14743552, 'steps': 28795, 'loss/train': 1.847525715827942}
-03/04/2022 23:17:44 - INFO - codeparrot_training - Step 28796: {'lr': 0.0004606372395381149, 'samples': 14744064, 'steps': 28796, 'loss/train': 2.113447666168213}
-03/04/2022 23:17:44 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 23:17:50 - INFO - codeparrot_training - Step 28797: {'lr': 0.0004606343811732577, 'samples': 14744576, 'steps': 28797, 'loss/train': 1.7636909484863281}
-03/04/2022 23:17:53 - INFO - codeparrot_training - Step 28798: {'lr': 0.0004606315227134919, 'samples': 14745088, 'steps': 28798, 'loss/train': 1.0039578676223755}
-03/04/2022 23:17:53 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/04/2022 23:17:58 - INFO - codeparrot_training - Step 28799: {'lr': 0.0004606286641588188, 'samples': 14745600, 'steps': 28799, 'loss/train': 1.8828938007354736}
-03/04/2022 23:18:01 - INFO - codeparrot_training - Step 28800: {'lr': 0.0004606258055092397, 'samples': 14746112, 'steps': 28800, 'loss/train': 1.211090087890625}
-03/04/2022 23:18:01 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/04/2022 23:18:07 - INFO - codeparrot_training - Step 28801: {'lr': 0.00046062294676475584, 'samples': 14746624, 'steps': 28801, 'loss/train': 1.0778968334197998}
-03/04/2022 23:18:10 - INFO - codeparrot_training - Step 28802: {'lr': 0.0004606200879253685, 'samples': 14747136, 'steps': 28802, 'loss/train': 2.512801170349121}
-03/04/2022 23:18:11 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/04/2022 23:18:15 - INFO - codeparrot_training - Step 28803: {'lr': 0.00046061722899107905, 'samples': 14747648, 'steps': 28803, 'loss/train': 1.892014503479004}
-03/04/2022 23:18:18 - INFO - codeparrot_training - Step 28804: {'lr': 0.0004606143699618888, 'samples': 14748160, 'steps': 28804, 'loss/train': 1.9535975456237793}
-03/04/2022 23:18:19 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/04/2022 23:18:23 - INFO - codeparrot_training - Step 28805: {'lr': 0.00046061151083779886, 'samples': 14748672, 'steps': 28805, 'loss/train': 1.4053068161010742}
-03/04/2022 23:18:27 - INFO - codeparrot_training - Step 28806: {'lr': 0.0004606086516188106, 'samples': 14749184, 'steps': 28806, 'loss/train': 1.4122319221496582}
-03/04/2022 23:18:28 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 23:18:32 - INFO - codeparrot_training - Step 28807: {'lr': 0.00046060579230492533, 'samples': 14749696, 'steps': 28807, 'loss/train': 1.8122142553329468}
-03/04/2022 23:18:35 - INFO - codeparrot_training - Step 28808: {'lr': 0.0004606029328961444, 'samples': 14750208, 'steps': 28808, 'loss/train': 1.5441874265670776}
-03/04/2022 23:18:36 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/04/2022 23:18:40 - INFO - codeparrot_training - Step 28809: {'lr': 0.000460600073392469, 'samples': 14750720, 'steps': 28809, 'loss/train': 1.4118648767471313}
-03/04/2022 23:18:44 - INFO - codeparrot_training - Step 28810: {'lr': 0.00046059721379390053, 'samples': 14751232, 'steps': 28810, 'loss/train': 1.892203450202942}
-03/04/2022 23:18:44 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/04/2022 23:18:49 - INFO - codeparrot_training - Step 28811: {'lr': 0.0004605943541004401, 'samples': 14751744, 'steps': 28811, 'loss/train': 1.9477064609527588}
-03/04/2022 23:18:52 - INFO - codeparrot_training - Step 28812: {'lr': 0.00046059149431208914, 'samples': 14752256, 'steps': 28812, 'loss/train': 1.6727160215377808}
-03/04/2022 23:18:52 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/04/2022 23:18:57 - INFO - codeparrot_training - Step 28813: {'lr': 0.0004605886344288489, 'samples': 14752768, 'steps': 28813, 'loss/train': 1.6348408460617065}
-03/04/2022 23:19:00 - INFO - codeparrot_training - Step 28814: {'lr': 0.0004605857744507207, 'samples': 14753280, 'steps': 28814, 'loss/train': 1.9410821199417114}
-03/04/2022 23:19:01 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/04/2022 23:19:05 - INFO - codeparrot_training - Step 28815: {'lr': 0.00046058291437770584, 'samples': 14753792, 'steps': 28815, 'loss/train': 1.7436407804489136}
-03/04/2022 23:19:09 - INFO - codeparrot_training - Step 28816: {'lr': 0.0004605800542098054, 'samples': 14754304, 'steps': 28816, 'loss/train': 0.941482424736023}
-03/04/2022 23:19:09 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/04/2022 23:19:14 - INFO - codeparrot_training - Step 28817: {'lr': 0.00046057719394702103, 'samples': 14754816, 'steps': 28817, 'loss/train': 1.7056500911712646}
-03/04/2022 23:19:17 - INFO - codeparrot_training - Step 28818: {'lr': 0.00046057433358935373, 'samples': 14755328, 'steps': 28818, 'loss/train': 2.2137181758880615}
-03/04/2022 23:19:17 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/04/2022 23:19:22 - INFO - codeparrot_training - Step 28819: {'lr': 0.0004605714731368049, 'samples': 14755840, 'steps': 28819, 'loss/train': 1.7460089921951294}
-03/04/2022 23:19:25 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/04/2022 23:19:28 - INFO - codeparrot_training - Step 28820: {'lr': 0.0004605686125893758, 'samples': 14756352, 'steps': 28820, 'loss/train': 2.0048539638519287}
-03/04/2022 23:19:31 - INFO - codeparrot_training - Step 28821: {'lr': 0.00046056575194706773, 'samples': 14756864, 'steps': 28821, 'loss/train': 2.419079065322876}
-03/04/2022 23:19:33 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/04/2022 23:19:36 - INFO - codeparrot_training - Step 28822: {'lr': 0.000460562891209882, 'samples': 14757376, 'steps': 28822, 'loss/train': 2.207127332687378}
-03/04/2022 23:19:39 - INFO - codeparrot_training - Step 28823: {'lr': 0.0004605600303778199, 'samples': 14757888, 'steps': 28823, 'loss/train': 1.8947594165802002}
-03/04/2022 23:19:44 - INFO - codeparrot_training - Step 28824: {'lr': 0.0004605571694508827, 'samples': 14758400, 'steps': 28824, 'loss/train': 1.8431636095046997}
-03/04/2022 23:19:48 - INFO - codeparrot_training - Step 28825: {'lr': 0.0004605543084290716, 'samples': 14758912, 'steps': 28825, 'loss/train': 1.9718064069747925}
-03/04/2022 23:19:51 - INFO - codeparrot_training - Step 28826: {'lr': 0.00046055144731238805, 'samples': 14759424, 'steps': 28826, 'loss/train': 1.2570476531982422}
-03/04/2022 23:19:51 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 23:19:56 - INFO - codeparrot_training - Step 28827: {'lr': 0.00046054858610083325, 'samples': 14759936, 'steps': 28827, 'loss/train': 1.9794161319732666}
-03/04/2022 23:19:59 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/04/2022 23:20:02 - INFO - codeparrot_training - Step 28828: {'lr': 0.0004605457247944086, 'samples': 14760448, 'steps': 28828, 'loss/train': 1.1934902667999268}
-03/04/2022 23:20:05 - INFO - codeparrot_training - Step 28829: {'lr': 0.0004605428633931152, 'samples': 14760960, 'steps': 28829, 'loss/train': 1.9077078104019165}
-03/04/2022 23:20:08 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 23:20:10 - INFO - codeparrot_training - Step 28830: {'lr': 0.00046054000189695444, 'samples': 14761472, 'steps': 28830, 'loss/train': 2.4174952507019043}
-03/04/2022 23:20:13 - INFO - codeparrot_training - Step 28831: {'lr': 0.00046053714030592764, 'samples': 14761984, 'steps': 28831, 'loss/train': 1.5270220041275024}
-03/04/2022 23:20:16 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 23:20:18 - INFO - codeparrot_training - Step 28832: {'lr': 0.0004605342786200359, 'samples': 14762496, 'steps': 28832, 'loss/train': 0.8540604710578918}
-03/04/2022 23:20:22 - INFO - codeparrot_training - Step 28833: {'lr': 0.0004605314168392809, 'samples': 14763008, 'steps': 28833, 'loss/train': 2.799633026123047}
-03/04/2022 23:20:24 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/04/2022 23:20:27 - INFO - codeparrot_training - Step 28834: {'lr': 0.00046052855496366354, 'samples': 14763520, 'steps': 28834, 'loss/train': 1.7184064388275146}
-03/04/2022 23:20:30 - INFO - codeparrot_training - Step 28835: {'lr': 0.0004605256929931853, 'samples': 14764032, 'steps': 28835, 'loss/train': 1.7746673822402954}
-03/04/2022 23:20:32 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/04/2022 23:20:35 - INFO - codeparrot_training - Step 28836: {'lr': 0.0004605228309278474, 'samples': 14764544, 'steps': 28836, 'loss/train': 1.1874452829360962}
-03/04/2022 23:20:39 - INFO - codeparrot_training - Step 28837: {'lr': 0.0004605199687676512, 'samples': 14765056, 'steps': 28837, 'loss/train': 1.7919214963912964}
-03/04/2022 23:20:41 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/04/2022 23:20:44 - INFO - codeparrot_training - Step 28838: {'lr': 0.00046051710651259797, 'samples': 14765568, 'steps': 28838, 'loss/train': 0.9254122376441956}
-03/04/2022 23:20:47 - INFO - codeparrot_training - Step 28839: {'lr': 0.00046051424416268896, 'samples': 14766080, 'steps': 28839, 'loss/train': 1.9852148294448853}
-03/04/2022 23:20:49 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/04/2022 23:20:52 - INFO - codeparrot_training - Step 28840: {'lr': 0.0004605113817179255, 'samples': 14766592, 'steps': 28840, 'loss/train': 1.3051128387451172}
-03/04/2022 23:20:56 - INFO - codeparrot_training - Step 28841: {'lr': 0.00046050851917830884, 'samples': 14767104, 'steps': 28841, 'loss/train': 2.314704656600952}
-03/04/2022 23:20:57 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/04/2022 23:21:01 - INFO - codeparrot_training - Step 28842: {'lr': 0.00046050565654384023, 'samples': 14767616, 'steps': 28842, 'loss/train': 1.473719596862793}
-03/04/2022 23:21:04 - INFO - codeparrot_training - Step 28843: {'lr': 0.0004605027938145211, 'samples': 14768128, 'steps': 28843, 'loss/train': 1.9232053756713867}
-03/04/2022 23:21:06 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/04/2022 23:21:09 - INFO - codeparrot_training - Step 28844: {'lr': 0.0004604999309903526, 'samples': 14768640, 'steps': 28844, 'loss/train': 1.5329201221466064}
-03/04/2022 23:21:12 - INFO - codeparrot_training - Step 28845: {'lr': 0.0004604970680713362, 'samples': 14769152, 'steps': 28845, 'loss/train': 1.8971480131149292}
-03/04/2022 23:21:14 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/04/2022 23:21:18 - INFO - codeparrot_training - Step 28846: {'lr': 0.00046049420505747294, 'samples': 14769664, 'steps': 28846, 'loss/train': 3.4711081981658936}
-03/04/2022 23:21:21 - INFO - codeparrot_training - Step 28847: {'lr': 0.0004604913419487643, 'samples': 14770176, 'steps': 28847, 'loss/train': 0.8581728935241699}
-03/04/2022 23:21:23 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/04/2022 23:21:26 - INFO - codeparrot_training - Step 28848: {'lr': 0.00046048847874521144, 'samples': 14770688, 'steps': 28848, 'loss/train': 1.4948898553848267}
-03/04/2022 23:21:29 - INFO - codeparrot_training - Step 28849: {'lr': 0.00046048561544681575, 'samples': 14771200, 'steps': 28849, 'loss/train': 1.423422932624817}
-03/04/2022 23:21:31 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/04/2022 23:21:35 - INFO - codeparrot_training - Step 28850: {'lr': 0.00046048275205357855, 'samples': 14771712, 'steps': 28850, 'loss/train': 1.3602997064590454}
-03/04/2022 23:21:38 - INFO - codeparrot_training - Step 28851: {'lr': 0.00046047988856550104, 'samples': 14772224, 'steps': 28851, 'loss/train': 2.274324655532837}
-03/04/2022 23:21:39 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/04/2022 23:21:43 - INFO - codeparrot_training - Step 28852: {'lr': 0.00046047702498258446, 'samples': 14772736, 'steps': 28852, 'loss/train': 1.4053928852081299}
-03/04/2022 23:21:46 - INFO - codeparrot_training - Step 28853: {'lr': 0.00046047416130483033, 'samples': 14773248, 'steps': 28853, 'loss/train': 1.1108251810073853}
-03/04/2022 23:21:48 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/04/2022 23:21:52 - INFO - codeparrot_training - Step 28854: {'lr': 0.00046047129753223973, 'samples': 14773760, 'steps': 28854, 'loss/train': 1.1840301752090454}
-03/04/2022 23:21:55 - INFO - codeparrot_training - Step 28855: {'lr': 0.0004604684336648139, 'samples': 14774272, 'steps': 28855, 'loss/train': 1.5065953731536865}
-03/04/2022 23:21:56 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 23:22:00 - INFO - codeparrot_training - Step 28856: {'lr': 0.00046046556970255435, 'samples': 14774784, 'steps': 28856, 'loss/train': 1.762263298034668}
-03/04/2022 23:22:03 - INFO - codeparrot_training - Step 28857: {'lr': 0.0004604627056454622, 'samples': 14775296, 'steps': 28857, 'loss/train': 1.4106866121292114}
-03/04/2022 23:22:04 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/04/2022 23:22:08 - INFO - codeparrot_training - Step 28858: {'lr': 0.00046045984149353894, 'samples': 14775808, 'steps': 28858, 'loss/train': 2.2027719020843506}
-03/04/2022 23:22:11 - INFO - codeparrot_training - Step 28859: {'lr': 0.0004604569772467856, 'samples': 14776320, 'steps': 28859, 'loss/train': 2.154367208480835}
-03/04/2022 23:22:12 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/04/2022 23:22:17 - INFO - codeparrot_training - Step 28860: {'lr': 0.00046045411290520364, 'samples': 14776832, 'steps': 28860, 'loss/train': 2.029752492904663}
-03/04/2022 23:22:20 - INFO - codeparrot_training - Step 28861: {'lr': 0.00046045124846879427, 'samples': 14777344, 'steps': 28861, 'loss/train': 1.7678821086883545}
-03/04/2022 23:22:21 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/04/2022 23:22:25 - INFO - codeparrot_training - Step 28862: {'lr': 0.00046044838393755885, 'samples': 14777856, 'steps': 28862, 'loss/train': 2.0462210178375244}
-03/04/2022 23:22:28 - INFO - codeparrot_training - Step 28863: {'lr': 0.00046044551931149856, 'samples': 14778368, 'steps': 28863, 'loss/train': 0.10074155777692795}
-03/04/2022 23:22:29 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/04/2022 23:22:34 - INFO - codeparrot_training - Step 28864: {'lr': 0.0004604426545906149, 'samples': 14778880, 'steps': 28864, 'loss/train': 1.6035149097442627}
-03/04/2022 23:22:37 - INFO - codeparrot_training - Step 28865: {'lr': 0.0004604397897749089, 'samples': 14779392, 'steps': 28865, 'loss/train': 0.8119407296180725}
-03/04/2022 23:22:38 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/04/2022 23:22:42 - INFO - codeparrot_training - Step 28866: {'lr': 0.00046043692486438207, 'samples': 14779904, 'steps': 28866, 'loss/train': 1.6479127407073975}
-03/04/2022 23:22:45 - INFO - codeparrot_training - Step 28867: {'lr': 0.00046043405985903555, 'samples': 14780416, 'steps': 28867, 'loss/train': 1.6287841796875}
-03/04/2022 23:22:46 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 23:22:51 - INFO - codeparrot_training - Step 28868: {'lr': 0.00046043119475887073, 'samples': 14780928, 'steps': 28868, 'loss/train': 2.0390870571136475}
-03/04/2022 23:22:54 - INFO - codeparrot_training - Step 28869: {'lr': 0.0004604283295638888, 'samples': 14781440, 'steps': 28869, 'loss/train': 2.0804827213287354}
-03/04/2022 23:22:55 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/04/2022 23:22:59 - INFO - codeparrot_training - Step 28870: {'lr': 0.00046042546427409116, 'samples': 14781952, 'steps': 28870, 'loss/train': 0.48635751008987427}
-03/04/2022 23:23:02 - INFO - codeparrot_training - Step 28871: {'lr': 0.000460422598889479, 'samples': 14782464, 'steps': 28871, 'loss/train': 1.7114224433898926}
-03/04/2022 23:23:03 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/04/2022 23:23:08 - INFO - codeparrot_training - Step 28872: {'lr': 0.0004604197334100537, 'samples': 14782976, 'steps': 28872, 'loss/train': 1.4371286630630493}
-03/04/2022 23:23:11 - INFO - codeparrot_training - Step 28873: {'lr': 0.0004604168678358166, 'samples': 14783488, 'steps': 28873, 'loss/train': 1.9294750690460205}
-03/04/2022 23:23:12 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/04/2022 23:23:16 - INFO - codeparrot_training - Step 28874: {'lr': 0.00046041400216676874, 'samples': 14784000, 'steps': 28874, 'loss/train': 2.0808136463165283}
-03/04/2022 23:23:19 - INFO - codeparrot_training - Step 28875: {'lr': 0.0004604111364029118, 'samples': 14784512, 'steps': 28875, 'loss/train': 1.9937310218811035}
-03/04/2022 23:23:20 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 23:23:24 - INFO - codeparrot_training - Step 28876: {'lr': 0.0004604082705442466, 'samples': 14785024, 'steps': 28876, 'loss/train': 1.9463622570037842}
-03/04/2022 23:23:28 - INFO - codeparrot_training - Step 28877: {'lr': 0.00046040540459077483, 'samples': 14785536, 'steps': 28877, 'loss/train': 2.304171323776245}
-03/04/2022 23:23:28 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/04/2022 23:23:33 - INFO - codeparrot_training - Step 28878: {'lr': 0.0004604025385424976, 'samples': 14786048, 'steps': 28878, 'loss/train': 1.8226237297058105}
-03/04/2022 23:23:36 - INFO - codeparrot_training - Step 28879: {'lr': 0.00046039967239941626, 'samples': 14786560, 'steps': 28879, 'loss/train': 1.9959421157836914}
-03/04/2022 23:23:36 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/04/2022 23:23:41 - INFO - codeparrot_training - Step 28880: {'lr': 0.000460396806161532, 'samples': 14787072, 'steps': 28880, 'loss/train': 1.3863372802734375}
-03/04/2022 23:23:44 - INFO - codeparrot_training - Step 28881: {'lr': 0.0004603939398288463, 'samples': 14787584, 'steps': 28881, 'loss/train': 1.9170218706130981}
-03/04/2022 23:23:44 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/04/2022 23:23:50 - INFO - codeparrot_training - Step 28882: {'lr': 0.00046039107340136023, 'samples': 14788096, 'steps': 28882, 'loss/train': 1.4970533847808838}
-03/04/2022 23:23:53 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 23:23:55 - INFO - codeparrot_training - Step 28883: {'lr': 0.00046038820687907523, 'samples': 14788608, 'steps': 28883, 'loss/train': 1.1294101476669312}
-03/04/2022 23:23:58 - INFO - codeparrot_training - Step 28884: {'lr': 0.0004603853402619925, 'samples': 14789120, 'steps': 28884, 'loss/train': 1.9906418323516846}
-03/04/2022 23:24:01 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/04/2022 23:24:03 - INFO - codeparrot_training - Step 28885: {'lr': 0.00046038247355011347, 'samples': 14789632, 'steps': 28885, 'loss/train': 1.4410990476608276}
-03/04/2022 23:24:06 - INFO - codeparrot_training - Step 28886: {'lr': 0.00046037960674343925, 'samples': 14790144, 'steps': 28886, 'loss/train': 2.2478859424591064}
-03/04/2022 23:24:09 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/04/2022 23:24:12 - INFO - codeparrot_training - Step 28887: {'lr': 0.0004603767398419713, 'samples': 14790656, 'steps': 28887, 'loss/train': 2.5621390342712402}
-03/04/2022 23:24:15 - INFO - codeparrot_training - Step 28888: {'lr': 0.0004603738728457109, 'samples': 14791168, 'steps': 28888, 'loss/train': 2.2321207523345947}
-03/04/2022 23:24:17 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/04/2022 23:24:20 - INFO - codeparrot_training - Step 28889: {'lr': 0.0004603710057546592, 'samples': 14791680, 'steps': 28889, 'loss/train': 1.6797950267791748}
-03/04/2022 23:24:23 - INFO - codeparrot_training - Step 28890: {'lr': 0.0004603681385688175, 'samples': 14792192, 'steps': 28890, 'loss/train': 1.9049224853515625}
-03/04/2022 23:24:25 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 23:24:29 - INFO - codeparrot_training - Step 28891: {'lr': 0.00046036527128818724, 'samples': 14792704, 'steps': 28891, 'loss/train': 2.001204490661621}
-03/04/2022 23:24:32 - INFO - codeparrot_training - Step 28892: {'lr': 0.0004603624039127696, 'samples': 14793216, 'steps': 28892, 'loss/train': 2.7873036861419678}
-03/04/2022 23:24:34 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/04/2022 23:24:37 - INFO - codeparrot_training - Step 28893: {'lr': 0.00046035953644256596, 'samples': 14793728, 'steps': 28893, 'loss/train': 1.8191783428192139}
-03/04/2022 23:24:40 - INFO - codeparrot_training - Step 28894: {'lr': 0.00046035666887757755, 'samples': 14794240, 'steps': 28894, 'loss/train': 2.2396652698516846}
-03/04/2022 23:24:42 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/04/2022 23:24:45 - INFO - codeparrot_training - Step 28895: {'lr': 0.00046035380121780563, 'samples': 14794752, 'steps': 28895, 'loss/train': 1.0408203601837158}
-03/04/2022 23:24:48 - INFO - codeparrot_training - Step 28896: {'lr': 0.0004603509334632515, 'samples': 14795264, 'steps': 28896, 'loss/train': 1.150875210762024}
-03/04/2022 23:24:51 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/04/2022 23:24:54 - INFO - codeparrot_training - Step 28897: {'lr': 0.00046034806561391655, 'samples': 14795776, 'steps': 28897, 'loss/train': 1.836584210395813}
-03/04/2022 23:24:57 - INFO - codeparrot_training - Step 28898: {'lr': 0.000460345197669802, 'samples': 14796288, 'steps': 28898, 'loss/train': 1.8709797859191895}
-03/04/2022 23:24:59 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/04/2022 23:25:02 - INFO - codeparrot_training - Step 28899: {'lr': 0.0004603423296309092, 'samples': 14796800, 'steps': 28899, 'loss/train': 0.956364095211029}
-03/04/2022 23:25:05 - INFO - codeparrot_training - Step 28900: {'lr': 0.0004603394614972393, 'samples': 14797312, 'steps': 28900, 'loss/train': 1.3321460485458374}
-03/04/2022 23:25:08 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/04/2022 23:25:11 - INFO - codeparrot_training - Step 28901: {'lr': 0.00046033659326879373, 'samples': 14797824, 'steps': 28901, 'loss/train': 1.9117951393127441}
-03/04/2022 23:25:14 - INFO - codeparrot_training - Step 28902: {'lr': 0.00046033372494557373, 'samples': 14798336, 'steps': 28902, 'loss/train': 2.2139878273010254}
-03/04/2022 23:25:16 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/04/2022 23:25:19 - INFO - codeparrot_training - Step 28903: {'lr': 0.00046033085652758053, 'samples': 14798848, 'steps': 28903, 'loss/train': 1.5712919235229492}
-03/04/2022 23:25:22 - INFO - codeparrot_training - Step 28904: {'lr': 0.00046032798801481564, 'samples': 14799360, 'steps': 28904, 'loss/train': 2.484159469604492}
-03/04/2022 23:25:24 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/04/2022 23:25:27 - INFO - codeparrot_training - Step 28905: {'lr': 0.0004603251194072801, 'samples': 14799872, 'steps': 28905, 'loss/train': 1.4546531438827515}
-03/04/2022 23:25:31 - INFO - codeparrot_training - Step 28906: {'lr': 0.0004603222507049754, 'samples': 14800384, 'steps': 28906, 'loss/train': 1.8969160318374634}
-03/04/2022 23:25:33 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/04/2022 23:25:36 - INFO - codeparrot_training - Step 28907: {'lr': 0.00046031938190790254, 'samples': 14800896, 'steps': 28907, 'loss/train': 1.6149530410766602}
-03/04/2022 23:25:39 - INFO - codeparrot_training - Step 28908: {'lr': 0.0004603165130160633, 'samples': 14801408, 'steps': 28908, 'loss/train': 1.1668694019317627}
-03/04/2022 23:25:41 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/04/2022 23:25:44 - INFO - codeparrot_training - Step 28909: {'lr': 0.0004603136440294584, 'samples': 14801920, 'steps': 28909, 'loss/train': 0.6168772578239441}
-03/04/2022 23:25:47 - INFO - codeparrot_training - Step 28910: {'lr': 0.0004603107749480896, 'samples': 14802432, 'steps': 28910, 'loss/train': 2.043896436691284}
-03/04/2022 23:25:49 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/04/2022 23:25:53 - INFO - codeparrot_training - Step 28911: {'lr': 0.0004603079057719579, 'samples': 14802944, 'steps': 28911, 'loss/train': 2.1559605598449707}
-03/04/2022 23:25:56 - INFO - codeparrot_training - Step 28912: {'lr': 0.0004603050365010648, 'samples': 14803456, 'steps': 28912, 'loss/train': 2.1699044704437256}
-03/04/2022 23:25:57 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/04/2022 23:26:01 - INFO - codeparrot_training - Step 28913: {'lr': 0.00046030216713541147, 'samples': 14803968, 'steps': 28913, 'loss/train': 2.1962292194366455}
-03/04/2022 23:26:04 - INFO - codeparrot_training - Step 28914: {'lr': 0.00046029929767499924, 'samples': 14804480, 'steps': 28914, 'loss/train': 2.6712489128112793}
-03/04/2022 23:26:06 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/04/2022 23:26:10 - INFO - codeparrot_training - Step 28915: {'lr': 0.0004602964281198293, 'samples': 14804992, 'steps': 28915, 'loss/train': 1.5854524374008179}
-03/04/2022 23:26:13 - INFO - codeparrot_training - Step 28916: {'lr': 0.0004602935584699031, 'samples': 14805504, 'steps': 28916, 'loss/train': 2.401256561279297}
-03/04/2022 23:26:14 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/04/2022 23:26:18 - INFO - codeparrot_training - Step 28917: {'lr': 0.00046029068872522185, 'samples': 14806016, 'steps': 28917, 'loss/train': 1.815535068511963}
-03/04/2022 23:26:21 - INFO - codeparrot_training - Step 28918: {'lr': 0.0004602878188857869, 'samples': 14806528, 'steps': 28918, 'loss/train': 2.013997793197632}
-03/04/2022 23:26:22 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/04/2022 23:26:26 - INFO - codeparrot_training - Step 28919: {'lr': 0.0004602849489515995, 'samples': 14807040, 'steps': 28919, 'loss/train': 1.2687535285949707}
-03/04/2022 23:26:30 - INFO - codeparrot_training - Step 28920: {'lr': 0.00046028207892266095, 'samples': 14807552, 'steps': 28920, 'loss/train': 2.077033519744873}
-03/04/2022 23:26:31 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/04/2022 23:26:35 - INFO - codeparrot_training - Step 28921: {'lr': 0.00046027920879897243, 'samples': 14808064, 'steps': 28921, 'loss/train': 1.744291067123413}
-03/04/2022 23:26:38 - INFO - codeparrot_training - Step 28922: {'lr': 0.00046027633858053554, 'samples': 14808576, 'steps': 28922, 'loss/train': 1.5903853178024292}
-03/04/2022 23:26:39 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 23:26:43 - INFO - codeparrot_training - Step 28923: {'lr': 0.0004602734682673512, 'samples': 14809088, 'steps': 28923, 'loss/train': 2.040329933166504}
-03/04/2022 23:26:47 - INFO - codeparrot_training - Step 28924: {'lr': 0.0004602705978594209, 'samples': 14809600, 'steps': 28924, 'loss/train': 2.2472615242004395}
-03/04/2022 23:26:48 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/04/2022 23:26:52 - INFO - codeparrot_training - Step 28925: {'lr': 0.00046026772735674606, 'samples': 14810112, 'steps': 28925, 'loss/train': 0.7313695549964905}
-03/04/2022 23:26:56 - INFO - codeparrot_training - Step 28926: {'lr': 0.00046026485675932765, 'samples': 14810624, 'steps': 28926, 'loss/train': 1.7321163415908813}
-03/04/2022 23:26:58 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/04/2022 23:27:01 - INFO - codeparrot_training - Step 28927: {'lr': 0.0004602619860671672, 'samples': 14811136, 'steps': 28927, 'loss/train': 0.09058800339698792}
-03/04/2022 23:27:04 - INFO - codeparrot_training - Step 28928: {'lr': 0.000460259115280266, 'samples': 14811648, 'steps': 28928, 'loss/train': 1.60804283618927}
-03/04/2022 23:27:06 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/04/2022 23:27:09 - INFO - codeparrot_training - Step 28929: {'lr': 0.00046025624439862523, 'samples': 14812160, 'steps': 28929, 'loss/train': 2.57155179977417}
-03/04/2022 23:27:12 - INFO - codeparrot_training - Step 28930: {'lr': 0.0004602533734222463, 'samples': 14812672, 'steps': 28930, 'loss/train': 1.2357851266860962}
-03/04/2022 23:27:14 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/04/2022 23:27:18 - INFO - codeparrot_training - Step 28931: {'lr': 0.00046025050235113036, 'samples': 14813184, 'steps': 28931, 'loss/train': 1.4776639938354492}
-03/04/2022 23:27:21 - INFO - codeparrot_training - Step 28932: {'lr': 0.00046024763118527885, 'samples': 14813696, 'steps': 28932, 'loss/train': 1.9436545372009277}
-03/04/2022 23:27:23 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/04/2022 23:27:26 - INFO - codeparrot_training - Step 28933: {'lr': 0.00046024475992469295, 'samples': 14814208, 'steps': 28933, 'loss/train': 1.1302376985549927}
-03/04/2022 23:27:29 - INFO - codeparrot_training - Step 28934: {'lr': 0.0004602418885693741, 'samples': 14814720, 'steps': 28934, 'loss/train': 1.7303214073181152}
-03/04/2022 23:27:31 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/04/2022 23:27:35 - INFO - codeparrot_training - Step 28935: {'lr': 0.0004602390171193234, 'samples': 14815232, 'steps': 28935, 'loss/train': 1.2371916770935059}
-03/04/2022 23:27:38 - INFO - codeparrot_training - Step 28936: {'lr': 0.0004602361455745423, 'samples': 14815744, 'steps': 28936, 'loss/train': 1.5670655965805054}
-03/04/2022 23:27:39 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 23:27:43 - INFO - codeparrot_training - Step 28937: {'lr': 0.000460233273935032, 'samples': 14816256, 'steps': 28937, 'loss/train': 1.7954941987991333}
-03/04/2022 23:27:46 - INFO - codeparrot_training - Step 28938: {'lr': 0.00046023040220079383, 'samples': 14816768, 'steps': 28938, 'loss/train': 1.509537696838379}
-03/04/2022 23:27:48 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/04/2022 23:27:51 - INFO - codeparrot_training - Step 28939: {'lr': 0.00046022753037182915, 'samples': 14817280, 'steps': 28939, 'loss/train': 0.5564448833465576}
-03/04/2022 23:27:54 - INFO - codeparrot_training - Step 28940: {'lr': 0.0004602246584481391, 'samples': 14817792, 'steps': 28940, 'loss/train': 1.5839362144470215}
-03/04/2022 23:27:56 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/04/2022 23:28:00 - INFO - codeparrot_training - Step 28941: {'lr': 0.00046022178642972513, 'samples': 14818304, 'steps': 28941, 'loss/train': 0.9965249300003052}
-03/04/2022 23:28:03 - INFO - codeparrot_training - Step 28942: {'lr': 0.00046021891431658845, 'samples': 14818816, 'steps': 28942, 'loss/train': 1.9373211860656738}
-03/04/2022 23:28:04 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/04/2022 23:28:08 - INFO - codeparrot_training - Step 28943: {'lr': 0.00046021604210873035, 'samples': 14819328, 'steps': 28943, 'loss/train': 2.0858917236328125}
-03/04/2022 23:28:11 - INFO - codeparrot_training - Step 28944: {'lr': 0.0004602131698061521, 'samples': 14819840, 'steps': 28944, 'loss/train': 1.8935599327087402}
-03/04/2022 23:28:12 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/04/2022 23:28:16 - INFO - codeparrot_training - Step 28945: {'lr': 0.0004602102974088551, 'samples': 14820352, 'steps': 28945, 'loss/train': 1.888928771018982}
-03/04/2022 23:28:20 - INFO - codeparrot_training - Step 28946: {'lr': 0.00046020742491684067, 'samples': 14820864, 'steps': 28946, 'loss/train': 1.401710033416748}
-03/04/2022 23:28:21 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/04/2022 23:28:25 - INFO - codeparrot_training - Step 28947: {'lr': 0.0004602045523301099, 'samples': 14821376, 'steps': 28947, 'loss/train': 1.9961256980895996}
-03/04/2022 23:28:28 - INFO - codeparrot_training - Step 28948: {'lr': 0.0004602016796486642, 'samples': 14821888, 'steps': 28948, 'loss/train': 1.5738950967788696}
-03/04/2022 23:28:29 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/04/2022 23:28:33 - INFO - codeparrot_training - Step 28949: {'lr': 0.00046019880687250494, 'samples': 14822400, 'steps': 28949, 'loss/train': 2.2601029872894287}
-03/04/2022 23:28:37 - INFO - codeparrot_training - Step 28950: {'lr': 0.0004601959340016333, 'samples': 14822912, 'steps': 28950, 'loss/train': 2.1484766006469727}
-03/04/2022 23:28:38 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/04/2022 23:28:42 - INFO - codeparrot_training - Step 28951: {'lr': 0.0004601930610360506, 'samples': 14823424, 'steps': 28951, 'loss/train': 1.6607630252838135}
-03/04/2022 23:28:45 - INFO - codeparrot_training - Step 28952: {'lr': 0.0004601901879757582, 'samples': 14823936, 'steps': 28952, 'loss/train': 0.8688652515411377}
-03/04/2022 23:28:46 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/04/2022 23:28:50 - INFO - codeparrot_training - Step 28953: {'lr': 0.0004601873148207573, 'samples': 14824448, 'steps': 28953, 'loss/train': 1.5881937742233276}
-03/04/2022 23:28:53 - INFO - codeparrot_training - Step 28954: {'lr': 0.00046018444157104924, 'samples': 14824960, 'steps': 28954, 'loss/train': 1.2198220491409302}
-03/04/2022 23:28:54 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/04/2022 23:28:59 - INFO - codeparrot_training - Step 28955: {'lr': 0.0004601815682266353, 'samples': 14825472, 'steps': 28955, 'loss/train': 2.2297163009643555}
-03/04/2022 23:29:02 - INFO - codeparrot_training - Step 28956: {'lr': 0.00046017869478751685, 'samples': 14825984, 'steps': 28956, 'loss/train': 2.1559975147247314}
-03/04/2022 23:29:02 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/04/2022 23:29:07 - INFO - codeparrot_training - Step 28957: {'lr': 0.00046017582125369505, 'samples': 14826496, 'steps': 28957, 'loss/train': 2.318465232849121}
-03/04/2022 23:29:10 - INFO - codeparrot_training - Step 28958: {'lr': 0.00046017294762517127, 'samples': 14827008, 'steps': 28958, 'loss/train': 1.8619863986968994}
-03/04/2022 23:29:10 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/04/2022 23:29:15 - INFO - codeparrot_training - Step 28959: {'lr': 0.0004601700739019469, 'samples': 14827520, 'steps': 28959, 'loss/train': 2.1109824180603027}
-03/04/2022 23:29:19 - INFO - codeparrot_training - Step 28960: {'lr': 0.000460167200084023, 'samples': 14828032, 'steps': 28960, 'loss/train': 1.3227741718292236}
-03/04/2022 23:29:19 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/04/2022 23:29:24 - INFO - codeparrot_training - Step 28961: {'lr': 0.00046016432617140113, 'samples': 14828544, 'steps': 28961, 'loss/train': 0.16505742073059082}
-03/04/2022 23:29:27 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 23:29:29 - INFO - codeparrot_training - Step 28962: {'lr': 0.0004601614521640824, 'samples': 14829056, 'steps': 28962, 'loss/train': 1.5241373777389526}
-03/04/2022 23:29:32 - INFO - codeparrot_training - Step 28963: {'lr': 0.00046015857806206816, 'samples': 14829568, 'steps': 28963, 'loss/train': 1.9669229984283447}
-03/04/2022 23:29:35 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/04/2022 23:29:38 - INFO - codeparrot_training - Step 28964: {'lr': 0.0004601557038653597, 'samples': 14830080, 'steps': 28964, 'loss/train': 1.9989007711410522}
-03/04/2022 23:29:41 - INFO - codeparrot_training - Step 28965: {'lr': 0.0004601528295739583, 'samples': 14830592, 'steps': 28965, 'loss/train': 2.0891523361206055}
-03/04/2022 23:29:44 - INFO - codeparrot_training - Step 28966: {'lr': 0.00046014995518786536, 'samples': 14831104, 'steps': 28966, 'loss/train': 1.5208605527877808}
-03/04/2022 23:29:45 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/04/2022 23:29:50 - INFO - codeparrot_training - Step 28967: {'lr': 0.000460147080707082, 'samples': 14831616, 'steps': 28967, 'loss/train': 1.9914668798446655}
-03/04/2022 23:29:53 - INFO - codeparrot_training - Step 28968: {'lr': 0.00046014420613160967, 'samples': 14832128, 'steps': 28968, 'loss/train': 1.9894436597824097}
-03/04/2022 23:29:54 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/04/2022 23:29:58 - INFO - codeparrot_training - Step 28969: {'lr': 0.00046014133146144966, 'samples': 14832640, 'steps': 28969, 'loss/train': 1.305442452430725}
-03/04/2022 23:30:01 - INFO - codeparrot_training - Step 28970: {'lr': 0.0004601384566966031, 'samples': 14833152, 'steps': 28970, 'loss/train': 0.08471759408712387}
-03/04/2022 23:30:02 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/04/2022 23:30:06 - INFO - codeparrot_training - Step 28971: {'lr': 0.0004601355818370714, 'samples': 14833664, 'steps': 28971, 'loss/train': 1.3182474374771118}
-03/04/2022 23:30:10 - INFO - codeparrot_training - Step 28972: {'lr': 0.0004601327068828559, 'samples': 14834176, 'steps': 28972, 'loss/train': 1.8941353559494019}
-03/04/2022 23:30:10 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/04/2022 23:30:15 - INFO - codeparrot_training - Step 28973: {'lr': 0.0004601298318339578, 'samples': 14834688, 'steps': 28973, 'loss/train': 0.8339391350746155}
-03/04/2022 23:30:18 - INFO - codeparrot_training - Step 28974: {'lr': 0.0004601269566903785, 'samples': 14835200, 'steps': 28974, 'loss/train': 1.6451183557510376}
-03/04/2022 23:30:19 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 23:30:23 - INFO - codeparrot_training - Step 28975: {'lr': 0.0004601240814521192, 'samples': 14835712, 'steps': 28975, 'loss/train': 6.576481342315674}
-03/04/2022 23:30:27 - INFO - codeparrot_training - Step 28976: {'lr': 0.00046012120611918126, 'samples': 14836224, 'steps': 28976, 'loss/train': 0.4567897915840149}
-03/04/2022 23:30:28 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/04/2022 23:30:32 - INFO - codeparrot_training - Step 28977: {'lr': 0.0004601183306915659, 'samples': 14836736, 'steps': 28977, 'loss/train': 1.4486446380615234}
-03/04/2022 23:30:35 - INFO - codeparrot_training - Step 28978: {'lr': 0.0004601154551692745, 'samples': 14837248, 'steps': 28978, 'loss/train': 2.562648296356201}
-03/04/2022 23:30:36 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/04/2022 23:30:40 - INFO - codeparrot_training - Step 28979: {'lr': 0.00046011257955230826, 'samples': 14837760, 'steps': 28979, 'loss/train': 1.7655466794967651}
-03/04/2022 23:30:43 - INFO - codeparrot_training - Step 28980: {'lr': 0.00046010970384066863, 'samples': 14838272, 'steps': 28980, 'loss/train': 2.069800615310669}
-03/04/2022 23:30:44 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/04/2022 23:30:49 - INFO - codeparrot_training - Step 28981: {'lr': 0.00046010682803435674, 'samples': 14838784, 'steps': 28981, 'loss/train': 2.7180607318878174}
-03/04/2022 23:30:52 - INFO - codeparrot_training - Step 28982: {'lr': 0.000460103952133374, 'samples': 14839296, 'steps': 28982, 'loss/train': 1.030515432357788}
-03/04/2022 23:30:53 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/04/2022 23:30:57 - INFO - codeparrot_training - Step 28983: {'lr': 0.00046010107613772154, 'samples': 14839808, 'steps': 28983, 'loss/train': 2.0299386978149414}
-03/04/2022 23:31:00 - INFO - codeparrot_training - Step 28984: {'lr': 0.0004600982000474009, 'samples': 14840320, 'steps': 28984, 'loss/train': 0.9816235303878784}
-03/04/2022 23:31:01 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/04/2022 23:31:06 - INFO - codeparrot_training - Step 28985: {'lr': 0.0004600953238624133, 'samples': 14840832, 'steps': 28985, 'loss/train': 1.726502537727356}
-03/04/2022 23:31:09 - INFO - codeparrot_training - Step 28986: {'lr': 0.00046009244758275986, 'samples': 14841344, 'steps': 28986, 'loss/train': 1.5209944248199463}
-03/04/2022 23:31:10 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/04/2022 23:31:14 - INFO - codeparrot_training - Step 28987: {'lr': 0.0004600895712084421, 'samples': 14841856, 'steps': 28987, 'loss/train': 1.5486699342727661}
-03/04/2022 23:31:17 - INFO - codeparrot_training - Step 28988: {'lr': 0.0004600866947394611, 'samples': 14842368, 'steps': 28988, 'loss/train': 1.5373567342758179}
-03/04/2022 23:31:18 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/04/2022 23:31:23 - INFO - codeparrot_training - Step 28989: {'lr': 0.0004600838181758184, 'samples': 14842880, 'steps': 28989, 'loss/train': 1.8338567018508911}
-03/04/2022 23:31:26 - INFO - codeparrot_training - Step 28990: {'lr': 0.00046008094151751513, 'samples': 14843392, 'steps': 28990, 'loss/train': 1.3882304430007935}
-03/04/2022 23:31:26 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/04/2022 23:31:31 - INFO - codeparrot_training - Step 28991: {'lr': 0.0004600780647645526, 'samples': 14843904, 'steps': 28991, 'loss/train': 2.097057342529297}
-03/04/2022 23:31:34 - INFO - codeparrot_training - Step 28992: {'lr': 0.0004600751879169321, 'samples': 14844416, 'steps': 28992, 'loss/train': 1.3460090160369873}
-03/04/2022 23:31:34 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/04/2022 23:31:39 - INFO - codeparrot_training - Step 28993: {'lr': 0.00046007231097465505, 'samples': 14844928, 'steps': 28993, 'loss/train': 1.6487737894058228}
-03/04/2022 23:31:42 - INFO - codeparrot_training - Step 28994: {'lr': 0.00046006943393772274, 'samples': 14845440, 'steps': 28994, 'loss/train': 1.7244102954864502}
-03/04/2022 23:31:42 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/04/2022 23:31:48 - INFO - codeparrot_training - Step 28995: {'lr': 0.00046006655680613616, 'samples': 14845952, 'steps': 28995, 'loss/train': 1.002383828163147}
-03/04/2022 23:31:51 - INFO - codeparrot_training - Step 28996: {'lr': 0.00046006367957989705, 'samples': 14846464, 'steps': 28996, 'loss/train': 1.5702049732208252}
-03/04/2022 23:31:51 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 23:31:56 - INFO - codeparrot_training - Step 28997: {'lr': 0.0004600608022590064, 'samples': 14846976, 'steps': 28997, 'loss/train': 1.5067673921585083}
-03/04/2022 23:31:59 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/04/2022 23:32:02 - INFO - codeparrot_training - Step 28998: {'lr': 0.0004600579248434655, 'samples': 14847488, 'steps': 28998, 'loss/train': 1.8597652912139893}
-03/04/2022 23:32:05 - INFO - codeparrot_training - Step 28999: {'lr': 0.0004600550473332759, 'samples': 14848000, 'steps': 28999, 'loss/train': 1.0888842344284058}
-03/04/2022 23:32:08 - INFO - codeparrot_training - Step 29000: {'lr': 0.0004600521697284386, 'samples': 14848512, 'steps': 29000, 'loss/train': 0.45745763182640076}
-03/04/2022 23:32:08 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/04/2022 23:32:13 - INFO - codeparrot_training - Step 29001: {'lr': 0.0004600492920289551, 'samples': 14849024, 'steps': 29001, 'loss/train': 1.805698275566101}
-03/04/2022 23:32:16 - INFO - codeparrot_training - Step 29002: {'lr': 0.00046004641423482665, 'samples': 14849536, 'steps': 29002, 'loss/train': 2.338632583618164}
-03/04/2022 23:32:17 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/04/2022 23:32:22 - INFO - codeparrot_training - Step 29003: {'lr': 0.00046004353634605447, 'samples': 14850048, 'steps': 29003, 'loss/train': 1.0572316646575928}
-03/04/2022 23:32:25 - INFO - codeparrot_training - Step 29004: {'lr': 0.00046004065836263995, 'samples': 14850560, 'steps': 29004, 'loss/train': 1.833466649055481}
-03/04/2022 23:32:25 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/04/2022 23:32:30 - INFO - codeparrot_training - Step 29005: {'lr': 0.00046003778028458434, 'samples': 14851072, 'steps': 29005, 'loss/train': 1.740554928779602}
-03/04/2022 23:32:33 - INFO - codeparrot_training - Step 29006: {'lr': 0.00046003490211188894, 'samples': 14851584, 'steps': 29006, 'loss/train': 0.7715404033660889}
-03/04/2022 23:32:33 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/04/2022 23:32:38 - INFO - codeparrot_training - Step 29007: {'lr': 0.00046003202384455505, 'samples': 14852096, 'steps': 29007, 'loss/train': 1.6751095056533813}
-03/04/2022 23:32:42 - INFO - codeparrot_training - Step 29008: {'lr': 0.000460029145482584, 'samples': 14852608, 'steps': 29008, 'loss/train': 2.3788061141967773}
-03/04/2022 23:32:42 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 23:32:47 - INFO - codeparrot_training - Step 29009: {'lr': 0.00046002626702597706, 'samples': 14853120, 'steps': 29009, 'loss/train': 1.959648847579956}
-03/04/2022 23:32:50 - INFO - codeparrot_training - Step 29010: {'lr': 0.00046002338847473545, 'samples': 14853632, 'steps': 29010, 'loss/train': 1.5642284154891968}
-03/04/2022 23:32:50 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 23:32:55 - INFO - codeparrot_training - Step 29011: {'lr': 0.0004600205098288606, 'samples': 14854144, 'steps': 29011, 'loss/train': 2.116776704788208}
-03/04/2022 23:32:58 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/04/2022 23:33:01 - INFO - codeparrot_training - Step 29012: {'lr': 0.00046001763108835384, 'samples': 14854656, 'steps': 29012, 'loss/train': 2.0821869373321533}
-03/04/2022 23:33:04 - INFO - codeparrot_training - Step 29013: {'lr': 0.0004600147522532162, 'samples': 14855168, 'steps': 29013, 'loss/train': 1.330973744392395}
-03/04/2022 23:33:06 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/04/2022 23:33:09 - INFO - codeparrot_training - Step 29014: {'lr': 0.0004600118733234493, 'samples': 14855680, 'steps': 29014, 'loss/train': 2.320333957672119}
-03/04/2022 23:33:12 - INFO - codeparrot_training - Step 29015: {'lr': 0.0004600089942990542, 'samples': 14856192, 'steps': 29015, 'loss/train': 1.6213715076446533}
-03/04/2022 23:33:15 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/04/2022 23:33:17 - INFO - codeparrot_training - Step 29016: {'lr': 0.00046000611518003234, 'samples': 14856704, 'steps': 29016, 'loss/train': 2.0605733394622803}
-03/04/2022 23:33:20 - INFO - codeparrot_training - Step 29017: {'lr': 0.00046000323596638495, 'samples': 14857216, 'steps': 29017, 'loss/train': 1.866251826286316}
-03/04/2022 23:33:23 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/04/2022 23:33:26 - INFO - codeparrot_training - Step 29018: {'lr': 0.0004600003566581133, 'samples': 14857728, 'steps': 29018, 'loss/train': 2.195990562438965}
-03/04/2022 23:33:29 - INFO - codeparrot_training - Step 29019: {'lr': 0.00045999747725521876, 'samples': 14858240, 'steps': 29019, 'loss/train': 1.3971036672592163}
-03/04/2022 23:33:32 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/04/2022 23:33:34 - INFO - codeparrot_training - Step 29020: {'lr': 0.0004599945977577026, 'samples': 14858752, 'steps': 29020, 'loss/train': 0.46534863114356995}
-03/04/2022 23:33:37 - INFO - codeparrot_training - Step 29021: {'lr': 0.0004599917181655661, 'samples': 14859264, 'steps': 29021, 'loss/train': 2.037235975265503}
-03/04/2022 23:33:40 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/04/2022 23:33:43 - INFO - codeparrot_training - Step 29022: {'lr': 0.00045998883847881057, 'samples': 14859776, 'steps': 29022, 'loss/train': 0.9228793382644653}
-03/04/2022 23:33:46 - INFO - codeparrot_training - Step 29023: {'lr': 0.00045998595869743735, 'samples': 14860288, 'steps': 29023, 'loss/train': 2.0169968605041504}
-03/04/2022 23:33:48 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/04/2022 23:33:51 - INFO - codeparrot_training - Step 29024: {'lr': 0.0004599830788214477, 'samples': 14860800, 'steps': 29024, 'loss/train': 1.5238827466964722}
-03/04/2022 23:33:54 - INFO - codeparrot_training - Step 29025: {'lr': 0.0004599801988508429, 'samples': 14861312, 'steps': 29025, 'loss/train': 1.931234359741211}
-03/04/2022 23:33:57 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/04/2022 23:33:59 - INFO - codeparrot_training - Step 29026: {'lr': 0.00045997731878562423, 'samples': 14861824, 'steps': 29026, 'loss/train': 1.754596471786499}
-03/04/2022 23:34:03 - INFO - codeparrot_training - Step 29027: {'lr': 0.000459974438625793, 'samples': 14862336, 'steps': 29027, 'loss/train': 1.6463311910629272}
-03/04/2022 23:34:05 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/04/2022 23:34:08 - INFO - codeparrot_training - Step 29028: {'lr': 0.0004599715583713506, 'samples': 14862848, 'steps': 29028, 'loss/train': 2.0498368740081787}
-03/04/2022 23:34:11 - INFO - codeparrot_training - Step 29029: {'lr': 0.00045996867802229824, 'samples': 14863360, 'steps': 29029, 'loss/train': 1.9638956785202026}
-03/04/2022 23:34:14 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/04/2022 23:34:17 - INFO - codeparrot_training - Step 29030: {'lr': 0.0004599657975786372, 'samples': 14863872, 'steps': 29030, 'loss/train': 1.0386602878570557}
-03/04/2022 23:34:20 - INFO - codeparrot_training - Step 29031: {'lr': 0.00045996291704036884, 'samples': 14864384, 'steps': 29031, 'loss/train': 1.8849382400512695}
-03/04/2022 23:34:23 - INFO - codeparrot_training - Step 29032: {'lr': 0.00045996003640749446, 'samples': 14864896, 'steps': 29032, 'loss/train': 2.1900837421417236}
-03/04/2022 23:34:23 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 23:34:28 - INFO - codeparrot_training - Step 29033: {'lr': 0.0004599571556800153, 'samples': 14865408, 'steps': 29033, 'loss/train': 1.5591461658477783}
-03/04/2022 23:34:31 - INFO - codeparrot_training - Step 29034: {'lr': 0.00045995427485793263, 'samples': 14865920, 'steps': 29034, 'loss/train': 1.9675546884536743}
-03/04/2022 23:34:32 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/04/2022 23:34:37 - INFO - codeparrot_training - Step 29035: {'lr': 0.00045995139394124784, 'samples': 14866432, 'steps': 29035, 'loss/train': 0.7928702235221863}
-03/04/2022 23:34:40 - INFO - codeparrot_training - Step 29036: {'lr': 0.0004599485129299622, 'samples': 14866944, 'steps': 29036, 'loss/train': 1.9369280338287354}
-03/04/2022 23:34:40 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/04/2022 23:34:45 - INFO - codeparrot_training - Step 29037: {'lr': 0.000459945631824077, 'samples': 14867456, 'steps': 29037, 'loss/train': 2.1295254230499268}
-03/04/2022 23:34:48 - INFO - codeparrot_training - Step 29038: {'lr': 0.0004599427506235936, 'samples': 14867968, 'steps': 29038, 'loss/train': 1.5909072160720825}
-03/04/2022 23:34:48 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/04/2022 23:34:54 - INFO - codeparrot_training - Step 29039: {'lr': 0.0004599398693285132, 'samples': 14868480, 'steps': 29039, 'loss/train': 1.8151884078979492}
-03/04/2022 23:34:57 - INFO - codeparrot_training - Step 29040: {'lr': 0.0004599369879388371, 'samples': 14868992, 'steps': 29040, 'loss/train': 1.6150797605514526}
-03/04/2022 23:34:57 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/04/2022 23:35:02 - INFO - codeparrot_training - Step 29041: {'lr': 0.0004599341064545666, 'samples': 14869504, 'steps': 29041, 'loss/train': 1.6656608581542969}
-03/04/2022 23:35:05 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/04/2022 23:35:07 - INFO - codeparrot_training - Step 29042: {'lr': 0.00045993122487570303, 'samples': 14870016, 'steps': 29042, 'loss/train': 1.389997959136963}
-03/04/2022 23:35:10 - INFO - codeparrot_training - Step 29043: {'lr': 0.00045992834320224773, 'samples': 14870528, 'steps': 29043, 'loss/train': 2.376666307449341}
-03/04/2022 23:35:13 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/04/2022 23:35:16 - INFO - codeparrot_training - Step 29044: {'lr': 0.000459925461434202, 'samples': 14871040, 'steps': 29044, 'loss/train': 2.1094560623168945}
-03/04/2022 23:35:19 - INFO - codeparrot_training - Step 29045: {'lr': 0.00045992257957156704, 'samples': 14871552, 'steps': 29045, 'loss/train': 1.4378043413162231}
-03/04/2022 23:35:22 - INFO - codeparrot_training - Step 29046: {'lr': 0.00045991969761434426, 'samples': 14872064, 'steps': 29046, 'loss/train': 1.391461730003357}
-03/04/2022 23:35:22 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/04/2022 23:35:28 - INFO - codeparrot_training - Step 29047: {'lr': 0.0004599168155625348, 'samples': 14872576, 'steps': 29047, 'loss/train': 1.4817235469818115}
-03/04/2022 23:35:31 - INFO - codeparrot_training - Step 29048: {'lr': 0.00045991393341614017, 'samples': 14873088, 'steps': 29048, 'loss/train': 1.5636444091796875}
-03/04/2022 23:35:31 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/04/2022 23:35:36 - INFO - codeparrot_training - Step 29049: {'lr': 0.0004599110511751615, 'samples': 14873600, 'steps': 29049, 'loss/train': 1.960412859916687}
-03/04/2022 23:35:39 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/04/2022 23:35:41 - INFO - codeparrot_training - Step 29050: {'lr': 0.0004599081688396002, 'samples': 14874112, 'steps': 29050, 'loss/train': 0.9628152847290039}
-03/04/2022 23:35:44 - INFO - codeparrot_training - Step 29051: {'lr': 0.0004599052864094575, 'samples': 14874624, 'steps': 29051, 'loss/train': 1.7646903991699219}
-03/04/2022 23:35:47 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 23:35:50 - INFO - codeparrot_training - Step 29052: {'lr': 0.0004599024038847347, 'samples': 14875136, 'steps': 29052, 'loss/train': 0.6668747067451477}
-03/04/2022 23:35:53 - INFO - codeparrot_training - Step 29053: {'lr': 0.0004598995212654331, 'samples': 14875648, 'steps': 29053, 'loss/train': 0.4553457498550415}
-03/04/2022 23:35:55 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/04/2022 23:35:58 - INFO - codeparrot_training - Step 29054: {'lr': 0.0004598966385515541, 'samples': 14876160, 'steps': 29054, 'loss/train': 2.3059468269348145}
-03/04/2022 23:36:01 - INFO - codeparrot_training - Step 29055: {'lr': 0.00045989375574309875, 'samples': 14876672, 'steps': 29055, 'loss/train': 1.6683145761489868}
-03/04/2022 23:36:04 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/04/2022 23:36:07 - INFO - codeparrot_training - Step 29056: {'lr': 0.00045989087284006863, 'samples': 14877184, 'steps': 29056, 'loss/train': 1.4355348348617554}
-03/04/2022 23:36:10 - INFO - codeparrot_training - Step 29057: {'lr': 0.00045988798984246496, 'samples': 14877696, 'steps': 29057, 'loss/train': 1.6905529499053955}
-03/04/2022 23:36:12 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/04/2022 23:36:15 - INFO - codeparrot_training - Step 29058: {'lr': 0.0004598851067502889, 'samples': 14878208, 'steps': 29058, 'loss/train': 1.843261480331421}
-03/04/2022 23:36:18 - INFO - codeparrot_training - Step 29059: {'lr': 0.00045988222356354186, 'samples': 14878720, 'steps': 29059, 'loss/train': 1.6904810667037964}
-03/04/2022 23:36:21 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/04/2022 23:36:24 - INFO - codeparrot_training - Step 29060: {'lr': 0.00045987934028222515, 'samples': 14879232, 'steps': 29060, 'loss/train': 2.957566976547241}
-03/04/2022 23:36:27 - INFO - codeparrot_training - Step 29061: {'lr': 0.00045987645690634003, 'samples': 14879744, 'steps': 29061, 'loss/train': 0.5805132389068604}
-03/04/2022 23:36:29 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/04/2022 23:36:32 - INFO - codeparrot_training - Step 29062: {'lr': 0.0004598735734358879, 'samples': 14880256, 'steps': 29062, 'loss/train': 1.645241141319275}
-03/04/2022 23:36:35 - INFO - codeparrot_training - Step 29063: {'lr': 0.0004598706898708699, 'samples': 14880768, 'steps': 29063, 'loss/train': 1.8921828269958496}
-03/04/2022 23:36:38 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/04/2022 23:36:40 - INFO - codeparrot_training - Step 29064: {'lr': 0.00045986780621128743, 'samples': 14881280, 'steps': 29064, 'loss/train': 2.7746834754943848}
-03/04/2022 23:36:44 - INFO - codeparrot_training - Step 29065: {'lr': 0.00045986492245714175, 'samples': 14881792, 'steps': 29065, 'loss/train': 1.7760132551193237}
-03/04/2022 23:36:46 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 23:36:49 - INFO - codeparrot_training - Step 29066: {'lr': 0.0004598620386084342, 'samples': 14882304, 'steps': 29066, 'loss/train': 1.8235278129577637}
-03/04/2022 23:36:52 - INFO - codeparrot_training - Step 29067: {'lr': 0.00045985915466516605, 'samples': 14882816, 'steps': 29067, 'loss/train': 2.082853078842163}
-03/04/2022 23:36:54 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/04/2022 23:36:57 - INFO - codeparrot_training - Step 29068: {'lr': 0.0004598562706273386, 'samples': 14883328, 'steps': 29068, 'loss/train': 1.6717555522918701}
-03/04/2022 23:37:00 - INFO - codeparrot_training - Step 29069: {'lr': 0.0004598533864949531, 'samples': 14883840, 'steps': 29069, 'loss/train': 1.9257400035858154}
-03/04/2022 23:37:03 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/04/2022 23:37:06 - INFO - codeparrot_training - Step 29070: {'lr': 0.00045985050226801097, 'samples': 14884352, 'steps': 29070, 'loss/train': 1.6174262762069702}
-03/04/2022 23:37:09 - INFO - codeparrot_training - Step 29071: {'lr': 0.0004598476179465134, 'samples': 14884864, 'steps': 29071, 'loss/train': 2.1745996475219727}
-03/04/2022 23:37:11 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/04/2022 23:37:14 - INFO - codeparrot_training - Step 29072: {'lr': 0.00045984473353046174, 'samples': 14885376, 'steps': 29072, 'loss/train': 1.4382448196411133}
-03/04/2022 23:37:17 - INFO - codeparrot_training - Step 29073: {'lr': 0.00045984184901985735, 'samples': 14885888, 'steps': 29073, 'loss/train': 2.2041072845458984}
-03/04/2022 23:37:20 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/04/2022 23:37:23 - INFO - codeparrot_training - Step 29074: {'lr': 0.00045983896441470143, 'samples': 14886400, 'steps': 29074, 'loss/train': 1.5206266641616821}
-03/04/2022 23:37:26 - INFO - codeparrot_training - Step 29075: {'lr': 0.00045983607971499527, 'samples': 14886912, 'steps': 29075, 'loss/train': 2.209489583969116}
-03/04/2022 23:37:28 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/04/2022 23:37:31 - INFO - codeparrot_training - Step 29076: {'lr': 0.0004598331949207402, 'samples': 14887424, 'steps': 29076, 'loss/train': 2.0450599193573}
-03/04/2022 23:37:34 - INFO - codeparrot_training - Step 29077: {'lr': 0.00045983031003193756, 'samples': 14887936, 'steps': 29077, 'loss/train': 1.074481725692749}
-03/04/2022 23:37:37 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/04/2022 23:37:40 - INFO - codeparrot_training - Step 29078: {'lr': 0.0004598274250485886, 'samples': 14888448, 'steps': 29078, 'loss/train': 1.2844581604003906}
-03/04/2022 23:37:43 - INFO - codeparrot_training - Step 29079: {'lr': 0.00045982453997069463, 'samples': 14888960, 'steps': 29079, 'loss/train': 2.089682102203369}
-03/04/2022 23:37:45 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/04/2022 23:37:48 - INFO - codeparrot_training - Step 29080: {'lr': 0.00045982165479825697, 'samples': 14889472, 'steps': 29080, 'loss/train': 1.7453691959381104}
-03/04/2022 23:37:51 - INFO - codeparrot_training - Step 29081: {'lr': 0.000459818769531277, 'samples': 14889984, 'steps': 29081, 'loss/train': 1.4937694072723389}
-03/04/2022 23:37:53 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/04/2022 23:37:57 - INFO - codeparrot_training - Step 29082: {'lr': 0.00045981588416975583, 'samples': 14890496, 'steps': 29082, 'loss/train': 0.6603583097457886}
-03/04/2022 23:38:00 - INFO - codeparrot_training - Step 29083: {'lr': 0.00045981299871369484, 'samples': 14891008, 'steps': 29083, 'loss/train': 1.9662913084030151}
-03/04/2022 23:38:02 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/04/2022 23:38:05 - INFO - codeparrot_training - Step 29084: {'lr': 0.0004598101131630954, 'samples': 14891520, 'steps': 29084, 'loss/train': 2.0128085613250732}
-03/04/2022 23:38:08 - INFO - codeparrot_training - Step 29085: {'lr': 0.0004598072275179588, 'samples': 14892032, 'steps': 29085, 'loss/train': 2.38871169090271}
-03/04/2022 23:38:10 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/04/2022 23:38:14 - INFO - codeparrot_training - Step 29086: {'lr': 0.00045980434177828625, 'samples': 14892544, 'steps': 29086, 'loss/train': 1.7146490812301636}
-03/04/2022 23:38:17 - INFO - codeparrot_training - Step 29087: {'lr': 0.00045980145594407907, 'samples': 14893056, 'steps': 29087, 'loss/train': 1.5957999229431152}
-03/04/2022 23:38:18 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/04/2022 23:38:22 - INFO - codeparrot_training - Step 29088: {'lr': 0.00045979857001533867, 'samples': 14893568, 'steps': 29088, 'loss/train': 2.280099630355835}
-03/04/2022 23:38:25 - INFO - codeparrot_training - Step 29089: {'lr': 0.0004597956839920662, 'samples': 14894080, 'steps': 29089, 'loss/train': 2.733269453048706}
-03/04/2022 23:38:27 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/04/2022 23:38:30 - INFO - codeparrot_training - Step 29090: {'lr': 0.00045979279787426307, 'samples': 14894592, 'steps': 29090, 'loss/train': 1.5046567916870117}
-03/04/2022 23:38:34 - INFO - codeparrot_training - Step 29091: {'lr': 0.00045978991166193057, 'samples': 14895104, 'steps': 29091, 'loss/train': 1.3361395597457886}
-03/04/2022 23:38:35 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/04/2022 23:38:39 - INFO - codeparrot_training - Step 29092: {'lr': 0.0004597870253550699, 'samples': 14895616, 'steps': 29092, 'loss/train': 2.0014395713806152}
-03/04/2022 23:38:42 - INFO - codeparrot_training - Step 29093: {'lr': 0.0004597841389536825, 'samples': 14896128, 'steps': 29093, 'loss/train': 1.3102402687072754}
-03/04/2022 23:38:44 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/04/2022 23:38:47 - INFO - codeparrot_training - Step 29094: {'lr': 0.00045978125245776957, 'samples': 14896640, 'steps': 29094, 'loss/train': 1.355667233467102}
-03/04/2022 23:38:51 - INFO - codeparrot_training - Step 29095: {'lr': 0.00045977836586733246, 'samples': 14897152, 'steps': 29095, 'loss/train': 1.6419482231140137}
-03/04/2022 23:38:53 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/04/2022 23:38:56 - INFO - codeparrot_training - Step 29096: {'lr': 0.00045977547918237243, 'samples': 14897664, 'steps': 29096, 'loss/train': 2.0282320976257324}
-03/04/2022 23:38:59 - INFO - codeparrot_training - Step 29097: {'lr': 0.0004597725924028908, 'samples': 14898176, 'steps': 29097, 'loss/train': 0.617231547832489}
-03/04/2022 23:39:01 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/04/2022 23:39:04 - INFO - codeparrot_training - Step 29098: {'lr': 0.00045976970552888896, 'samples': 14898688, 'steps': 29098, 'loss/train': 1.2387304306030273}
-03/04/2022 23:39:07 - INFO - codeparrot_training - Step 29099: {'lr': 0.00045976681856036805, 'samples': 14899200, 'steps': 29099, 'loss/train': 2.3988895416259766}
-03/04/2022 23:39:09 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/04/2022 23:39:13 - INFO - codeparrot_training - Step 29100: {'lr': 0.00045976393149732943, 'samples': 14899712, 'steps': 29100, 'loss/train': 1.775471806526184}
-03/04/2022 23:39:16 - INFO - codeparrot_training - Step 29101: {'lr': 0.0004597610443397745, 'samples': 14900224, 'steps': 29101, 'loss/train': 2.2531089782714844}
-03/04/2022 23:39:17 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/04/2022 23:39:21 - INFO - codeparrot_training - Step 29102: {'lr': 0.0004597581570877044, 'samples': 14900736, 'steps': 29102, 'loss/train': 1.7624447345733643}
-03/04/2022 23:39:24 - INFO - codeparrot_training - Step 29103: {'lr': 0.00045975526974112056, 'samples': 14901248, 'steps': 29103, 'loss/train': 2.484616279602051}
-03/04/2022 23:39:26 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/04/2022 23:39:29 - INFO - codeparrot_training - Step 29104: {'lr': 0.0004597523823000243, 'samples': 14901760, 'steps': 29104, 'loss/train': 2.11627459526062}
-03/04/2022 23:39:33 - INFO - codeparrot_training - Step 29105: {'lr': 0.0004597494947644167, 'samples': 14902272, 'steps': 29105, 'loss/train': 1.7344225645065308}
-03/04/2022 23:39:34 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/04/2022 23:39:38 - INFO - codeparrot_training - Step 29106: {'lr': 0.0004597466071342993, 'samples': 14902784, 'steps': 29106, 'loss/train': 1.3737783432006836}
-03/04/2022 23:39:41 - INFO - codeparrot_training - Step 29107: {'lr': 0.0004597437194096733, 'samples': 14903296, 'steps': 29107, 'loss/train': 0.9118130207061768}
-03/04/2022 23:39:42 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 23:39:46 - INFO - codeparrot_training - Step 29108: {'lr': 0.00045974083159054, 'samples': 14903808, 'steps': 29108, 'loss/train': 0.8802109956741333}
-03/04/2022 23:39:50 - INFO - codeparrot_training - Step 29109: {'lr': 0.0004597379436769008, 'samples': 14904320, 'steps': 29109, 'loss/train': 1.9168369770050049}
-03/04/2022 23:39:50 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/04/2022 23:39:55 - INFO - codeparrot_training - Step 29110: {'lr': 0.00045973505566875684, 'samples': 14904832, 'steps': 29110, 'loss/train': 1.999769926071167}
-03/04/2022 23:39:58 - INFO - codeparrot_training - Step 29111: {'lr': 0.00045973216756610945, 'samples': 14905344, 'steps': 29111, 'loss/train': 1.6698222160339355}
-03/04/2022 23:39:59 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/04/2022 23:40:03 - INFO - codeparrot_training - Step 29112: {'lr': 0.00045972927936896007, 'samples': 14905856, 'steps': 29112, 'loss/train': 1.5797452926635742}
-03/04/2022 23:40:06 - INFO - codeparrot_training - Step 29113: {'lr': 0.0004597263910773099, 'samples': 14906368, 'steps': 29113, 'loss/train': 1.504439115524292}
-03/04/2022 23:40:07 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/04/2022 23:40:12 - INFO - codeparrot_training - Step 29114: {'lr': 0.0004597235026911603, 'samples': 14906880, 'steps': 29114, 'loss/train': 1.7676739692687988}
-03/04/2022 23:40:15 - INFO - codeparrot_training - Step 29115: {'lr': 0.0004597206142105124, 'samples': 14907392, 'steps': 29115, 'loss/train': 0.9439258575439453}
-03/04/2022 23:40:15 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/04/2022 23:40:20 - INFO - codeparrot_training - Step 29116: {'lr': 0.0004597177256353677, 'samples': 14907904, 'steps': 29116, 'loss/train': 1.6854532957077026}
-03/04/2022 23:40:23 - INFO - codeparrot_training - Step 29117: {'lr': 0.0004597148369657275, 'samples': 14908416, 'steps': 29117, 'loss/train': 2.058504581451416}
-03/04/2022 23:40:23 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/04/2022 23:40:29 - INFO - codeparrot_training - Step 29118: {'lr': 0.0004597119482015929, 'samples': 14908928, 'steps': 29118, 'loss/train': 1.4069952964782715}
-03/04/2022 23:40:32 - INFO - codeparrot_training - Step 29119: {'lr': 0.00045970905934296537, 'samples': 14909440, 'steps': 29119, 'loss/train': 2.0133395195007324}
-03/04/2022 23:40:32 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/04/2022 23:40:37 - INFO - codeparrot_training - Step 29120: {'lr': 0.0004597061703898462, 'samples': 14909952, 'steps': 29120, 'loss/train': 3.197479009628296}
-03/04/2022 23:40:40 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/04/2022 23:40:43 - INFO - codeparrot_training - Step 29121: {'lr': 0.0004597032813422367, 'samples': 14910464, 'steps': 29121, 'loss/train': 1.5683201551437378}
-03/04/2022 23:40:46 - INFO - codeparrot_training - Step 29122: {'lr': 0.00045970039220013804, 'samples': 14910976, 'steps': 29122, 'loss/train': 0.2565067410469055}
-03/04/2022 23:40:48 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/04/2022 23:40:51 - INFO - codeparrot_training - Step 29123: {'lr': 0.00045969750296355173, 'samples': 14911488, 'steps': 29123, 'loss/train': 2.474449634552002}
-03/04/2022 23:40:54 - INFO - codeparrot_training - Step 29124: {'lr': 0.0004596946136324789, 'samples': 14912000, 'steps': 29124, 'loss/train': 2.0101943016052246}
-03/04/2022 23:40:57 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/04/2022 23:41:00 - INFO - codeparrot_training - Step 29125: {'lr': 0.0004596917242069209, 'samples': 14912512, 'steps': 29125, 'loss/train': 1.7664581537246704}
-03/04/2022 23:41:03 - INFO - codeparrot_training - Step 29126: {'lr': 0.00045968883468687906, 'samples': 14913024, 'steps': 29126, 'loss/train': 1.4397746324539185}
-03/04/2022 23:41:05 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/04/2022 23:41:08 - INFO - codeparrot_training - Step 29127: {'lr': 0.00045968594507235467, 'samples': 14913536, 'steps': 29127, 'loss/train': 0.9504812359809875}
-03/04/2022 23:41:11 - INFO - codeparrot_training - Step 29128: {'lr': 0.00045968305536334906, 'samples': 14914048, 'steps': 29128, 'loss/train': 2.012752056121826}
-03/04/2022 23:41:14 - INFO - codeparrot_training - Step 29129: {'lr': 0.00045968016555986347, 'samples': 14914560, 'steps': 29129, 'loss/train': 1.8824918270111084}
-03/04/2022 23:41:15 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/04/2022 23:41:20 - INFO - codeparrot_training - Step 29130: {'lr': 0.0004596772756618992, 'samples': 14915072, 'steps': 29130, 'loss/train': 1.524677038192749}
-03/04/2022 23:41:23 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/04/2022 23:41:25 - INFO - codeparrot_training - Step 29131: {'lr': 0.0004596743856694576, 'samples': 14915584, 'steps': 29131, 'loss/train': 1.5124056339263916}
-03/04/2022 23:41:28 - INFO - codeparrot_training - Step 29132: {'lr': 0.00045967149558254, 'samples': 14916096, 'steps': 29132, 'loss/train': 1.5541143417358398}
-03/04/2022 23:41:31 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/04/2022 23:41:34 - INFO - codeparrot_training - Step 29133: {'lr': 0.0004596686054011476, 'samples': 14916608, 'steps': 29133, 'loss/train': 2.2409560680389404}
-03/04/2022 23:41:37 - INFO - codeparrot_training - Step 29134: {'lr': 0.0004596657151252819, 'samples': 14917120, 'steps': 29134, 'loss/train': 2.1312177181243896}
-03/04/2022 23:41:39 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/04/2022 23:41:42 - INFO - codeparrot_training - Step 29135: {'lr': 0.0004596628247549439, 'samples': 14917632, 'steps': 29135, 'loss/train': 1.264827847480774}
-03/04/2022 23:41:45 - INFO - codeparrot_training - Step 29136: {'lr': 0.00045965993429013507, 'samples': 14918144, 'steps': 29136, 'loss/train': 1.620897889137268}
-03/04/2022 23:41:47 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 23:41:50 - INFO - codeparrot_training - Step 29137: {'lr': 0.0004596570437308568, 'samples': 14918656, 'steps': 29137, 'loss/train': 1.871425747871399}
-03/04/2022 23:41:53 - INFO - codeparrot_training - Step 29138: {'lr': 0.0004596541530771103, 'samples': 14919168, 'steps': 29138, 'loss/train': 1.6030455827713013}
-03/04/2022 23:41:56 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/04/2022 23:41:59 - INFO - codeparrot_training - Step 29139: {'lr': 0.0004596512623288969, 'samples': 14919680, 'steps': 29139, 'loss/train': 1.4921801090240479}
-03/04/2022 23:42:02 - INFO - codeparrot_training - Step 29140: {'lr': 0.00045964837148621776, 'samples': 14920192, 'steps': 29140, 'loss/train': 1.1856757402420044}
-03/04/2022 23:42:04 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/04/2022 23:42:07 - INFO - codeparrot_training - Step 29141: {'lr': 0.00045964548054907434, 'samples': 14920704, 'steps': 29141, 'loss/train': 2.474169969558716}
-03/04/2022 23:42:10 - INFO - codeparrot_training - Step 29142: {'lr': 0.00045964258951746795, 'samples': 14921216, 'steps': 29142, 'loss/train': 1.8467825651168823}
-03/04/2022 23:42:12 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/04/2022 23:42:16 - INFO - codeparrot_training - Step 29143: {'lr': 0.0004596396983913998, 'samples': 14921728, 'steps': 29143, 'loss/train': 0.1105784997344017}
-03/04/2022 23:42:19 - INFO - codeparrot_training - Step 29144: {'lr': 0.00045963680717087124, 'samples': 14922240, 'steps': 29144, 'loss/train': 0.7168443202972412}
-03/04/2022 23:42:21 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/04/2022 23:42:24 - INFO - codeparrot_training - Step 29145: {'lr': 0.0004596339158558835, 'samples': 14922752, 'steps': 29145, 'loss/train': 0.9533576369285583}
-03/04/2022 23:42:27 - INFO - codeparrot_training - Step 29146: {'lr': 0.0004596310244464381, 'samples': 14923264, 'steps': 29146, 'loss/train': 1.4064027070999146}
-03/04/2022 23:42:29 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 23:42:32 - INFO - codeparrot_training - Step 29147: {'lr': 0.0004596281329425361, 'samples': 14923776, 'steps': 29147, 'loss/train': 3.5055644512176514}
-03/04/2022 23:42:35 - INFO - codeparrot_training - Step 29148: {'lr': 0.0004596252413441789, 'samples': 14924288, 'steps': 29148, 'loss/train': 1.0013046264648438}
-03/04/2022 23:42:37 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/04/2022 23:42:41 - INFO - codeparrot_training - Step 29149: {'lr': 0.00045962234965136783, 'samples': 14924800, 'steps': 29149, 'loss/train': 2.6260547637939453}
-03/04/2022 23:42:44 - INFO - codeparrot_training - Step 29150: {'lr': 0.0004596194578641042, 'samples': 14925312, 'steps': 29150, 'loss/train': 2.0666158199310303}
-03/04/2022 23:42:45 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/04/2022 23:42:49 - INFO - codeparrot_training - Step 29151: {'lr': 0.00045961656598238925, 'samples': 14925824, 'steps': 29151, 'loss/train': 0.7794939875602722}
-03/04/2022 23:42:52 - INFO - codeparrot_training - Step 29152: {'lr': 0.00045961367400622436, 'samples': 14926336, 'steps': 29152, 'loss/train': 1.543593406677246}
-03/04/2022 23:42:54 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/04/2022 23:42:58 - INFO - codeparrot_training - Step 29153: {'lr': 0.00045961078193561066, 'samples': 14926848, 'steps': 29153, 'loss/train': 1.4555134773254395}
-03/04/2022 23:43:01 - INFO - codeparrot_training - Step 29154: {'lr': 0.00045960788977054967, 'samples': 14927360, 'steps': 29154, 'loss/train': 2.217865467071533}
-03/04/2022 23:43:02 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/04/2022 23:43:06 - INFO - codeparrot_training - Step 29155: {'lr': 0.0004596049975110426, 'samples': 14927872, 'steps': 29155, 'loss/train': 1.438384771347046}
-03/04/2022 23:43:09 - INFO - codeparrot_training - Step 29156: {'lr': 0.00045960210515709064, 'samples': 14928384, 'steps': 29156, 'loss/train': 2.174865484237671}
-03/04/2022 23:43:12 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/04/2022 23:43:15 - INFO - codeparrot_training - Step 29157: {'lr': 0.0004595992127086953, 'samples': 14928896, 'steps': 29157, 'loss/train': 2.69874906539917}
-03/04/2022 23:43:18 - INFO - codeparrot_training - Step 29158: {'lr': 0.00045959632016585774, 'samples': 14929408, 'steps': 29158, 'loss/train': 1.6032224893569946}
-03/04/2022 23:43:20 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/04/2022 23:43:23 - INFO - codeparrot_training - Step 29159: {'lr': 0.0004595934275285794, 'samples': 14929920, 'steps': 29159, 'loss/train': 1.3191182613372803}
-03/04/2022 23:43:26 - INFO - codeparrot_training - Step 29160: {'lr': 0.00045959053479686143, 'samples': 14930432, 'steps': 29160, 'loss/train': 2.0268399715423584}
-03/04/2022 23:43:29 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/04/2022 23:43:32 - INFO - codeparrot_training - Step 29161: {'lr': 0.0004595876419707052, 'samples': 14930944, 'steps': 29161, 'loss/train': 1.4555333852767944}
-03/04/2022 23:43:35 - INFO - codeparrot_training - Step 29162: {'lr': 0.00045958474905011205, 'samples': 14931456, 'steps': 29162, 'loss/train': 2.1187734603881836}
-03/04/2022 23:43:37 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/04/2022 23:43:40 - INFO - codeparrot_training - Step 29163: {'lr': 0.0004595818560350832, 'samples': 14931968, 'steps': 29163, 'loss/train': 6.549332141876221}
-03/04/2022 23:43:43 - INFO - codeparrot_training - Step 29164: {'lr': 0.00045957896292562003, 'samples': 14932480, 'steps': 29164, 'loss/train': 2.3962900638580322}
-03/04/2022 23:43:46 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/04/2022 23:43:49 - INFO - codeparrot_training - Step 29165: {'lr': 0.0004595760697217238, 'samples': 14932992, 'steps': 29165, 'loss/train': 1.4033339023590088}
-03/04/2022 23:43:52 - INFO - codeparrot_training - Step 29166: {'lr': 0.0004595731764233958, 'samples': 14933504, 'steps': 29166, 'loss/train': 1.8188443183898926}
-03/04/2022 23:43:55 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/04/2022 23:43:57 - INFO - codeparrot_training - Step 29167: {'lr': 0.0004595702830306374, 'samples': 14934016, 'steps': 29167, 'loss/train': 2.7042882442474365}
-03/04/2022 23:44:00 - INFO - codeparrot_training - Step 29168: {'lr': 0.0004595673895434498, 'samples': 14934528, 'steps': 29168, 'loss/train': 6.605645179748535}
-03/04/2022 23:44:04 - INFO - codeparrot_training - Step 29169: {'lr': 0.00045956449596183446, 'samples': 14935040, 'steps': 29169, 'loss/train': 1.5838942527770996}
-03/04/2022 23:44:04 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 23:44:09 - INFO - codeparrot_training - Step 29170: {'lr': 0.00045956160228579257, 'samples': 14935552, 'steps': 29170, 'loss/train': 2.0275838375091553}
-03/04/2022 23:44:12 - INFO - codeparrot_training - Step 29171: {'lr': 0.00045955870851532545, 'samples': 14936064, 'steps': 29171, 'loss/train': 2.3538730144500732}
-03/04/2022 23:44:12 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/04/2022 23:44:17 - INFO - codeparrot_training - Step 29172: {'lr': 0.0004595558146504344, 'samples': 14936576, 'steps': 29172, 'loss/train': 1.5186928510665894}
-03/04/2022 23:44:20 - INFO - codeparrot_training - Step 29173: {'lr': 0.0004595529206911207, 'samples': 14937088, 'steps': 29173, 'loss/train': 1.537463903427124}
-03/04/2022 23:44:21 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/04/2022 23:44:26 - INFO - codeparrot_training - Step 29174: {'lr': 0.00045955002663738574, 'samples': 14937600, 'steps': 29174, 'loss/train': 2.609567642211914}
-03/04/2022 23:44:29 - INFO - codeparrot_training - Step 29175: {'lr': 0.0004595471324892307, 'samples': 14938112, 'steps': 29175, 'loss/train': 1.4798550605773926}
-03/04/2022 23:44:29 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/04/2022 23:44:34 - INFO - codeparrot_training - Step 29176: {'lr': 0.00045954423824665704, 'samples': 14938624, 'steps': 29176, 'loss/train': 0.16768808662891388}
-03/04/2022 23:44:37 - INFO - codeparrot_training - Step 29177: {'lr': 0.00045954134390966593, 'samples': 14939136, 'steps': 29177, 'loss/train': 1.3351296186447144}
-03/04/2022 23:44:37 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/04/2022 23:44:42 - INFO - codeparrot_training - Step 29178: {'lr': 0.00045953844947825876, 'samples': 14939648, 'steps': 29178, 'loss/train': 1.8945249319076538}
-03/04/2022 23:44:45 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/04/2022 23:44:48 - INFO - codeparrot_training - Step 29179: {'lr': 0.0004595355549524368, 'samples': 14940160, 'steps': 29179, 'loss/train': 2.2088303565979004}
-03/04/2022 23:44:51 - INFO - codeparrot_training - Step 29180: {'lr': 0.0004595326603322013, 'samples': 14940672, 'steps': 29180, 'loss/train': 2.2044198513031006}
-03/04/2022 23:44:53 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/04/2022 23:44:56 - INFO - codeparrot_training - Step 29181: {'lr': 0.00045952976561755365, 'samples': 14941184, 'steps': 29181, 'loss/train': 2.193561553955078}
-03/04/2022 23:44:59 - INFO - codeparrot_training - Step 29182: {'lr': 0.00045952687080849517, 'samples': 14941696, 'steps': 29182, 'loss/train': 1.7539474964141846}
-03/04/2022 23:45:02 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/04/2022 23:45:04 - INFO - codeparrot_training - Step 29183: {'lr': 0.000459523975905027, 'samples': 14942208, 'steps': 29183, 'loss/train': 1.1072354316711426}
-03/04/2022 23:45:08 - INFO - codeparrot_training - Step 29184: {'lr': 0.0004595210809071506, 'samples': 14942720, 'steps': 29184, 'loss/train': 1.3498034477233887}
-03/04/2022 23:45:10 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/04/2022 23:45:13 - INFO - codeparrot_training - Step 29185: {'lr': 0.0004595181858148673, 'samples': 14943232, 'steps': 29185, 'loss/train': 0.6411823034286499}
-03/04/2022 23:45:16 - INFO - codeparrot_training - Step 29186: {'lr': 0.00045951529062817834, 'samples': 14943744, 'steps': 29186, 'loss/train': 1.7613376379013062}
-03/04/2022 23:45:18 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 23:45:21 - INFO - codeparrot_training - Step 29187: {'lr': 0.00045951239534708496, 'samples': 14944256, 'steps': 29187, 'loss/train': 1.896260380744934}
-03/04/2022 23:45:24 - INFO - codeparrot_training - Step 29188: {'lr': 0.0004595094999715885, 'samples': 14944768, 'steps': 29188, 'loss/train': 1.6110234260559082}
-03/04/2022 23:45:27 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/04/2022 23:45:30 - INFO - codeparrot_training - Step 29189: {'lr': 0.00045950660450169034, 'samples': 14945280, 'steps': 29189, 'loss/train': 1.4957785606384277}
-03/04/2022 23:45:33 - INFO - codeparrot_training - Step 29190: {'lr': 0.0004595037089373918, 'samples': 14945792, 'steps': 29190, 'loss/train': 1.7709990739822388}
-03/04/2022 23:45:35 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/04/2022 23:45:38 - INFO - codeparrot_training - Step 29191: {'lr': 0.000459500813278694, 'samples': 14946304, 'steps': 29191, 'loss/train': 1.6369274854660034}
-03/04/2022 23:45:41 - INFO - codeparrot_training - Step 29192: {'lr': 0.0004594979175255984, 'samples': 14946816, 'steps': 29192, 'loss/train': 2.431550979614258}
-03/04/2022 23:45:43 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/04/2022 23:45:46 - INFO - codeparrot_training - Step 29193: {'lr': 0.0004594950216781063, 'samples': 14947328, 'steps': 29193, 'loss/train': 1.165001630783081}
-03/04/2022 23:45:49 - INFO - codeparrot_training - Step 29194: {'lr': 0.000459492125736219, 'samples': 14947840, 'steps': 29194, 'loss/train': 1.9006632566452026}
-03/04/2022 23:45:51 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/04/2022 23:45:55 - INFO - codeparrot_training - Step 29195: {'lr': 0.00045948922969993777, 'samples': 14948352, 'steps': 29195, 'loss/train': 1.828600287437439}
-03/04/2022 23:45:58 - INFO - codeparrot_training - Step 29196: {'lr': 0.0004594863335692639, 'samples': 14948864, 'steps': 29196, 'loss/train': 1.8421552181243896}
-03/04/2022 23:46:00 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/04/2022 23:46:03 - INFO - codeparrot_training - Step 29197: {'lr': 0.00045948343734419873, 'samples': 14949376, 'steps': 29197, 'loss/train': 1.6671466827392578}
-03/04/2022 23:46:06 - INFO - codeparrot_training - Step 29198: {'lr': 0.00045948054102474357, 'samples': 14949888, 'steps': 29198, 'loss/train': 3.118701934814453}
-03/04/2022 23:46:08 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/04/2022 23:46:12 - INFO - codeparrot_training - Step 29199: {'lr': 0.00045947764461089967, 'samples': 14950400, 'steps': 29199, 'loss/train': 0.16215740144252777}
-03/04/2022 23:46:15 - INFO - codeparrot_training - Step 29200: {'lr': 0.00045947474810266844, 'samples': 14950912, 'steps': 29200, 'loss/train': 1.2064462900161743}
-03/04/2022 23:46:16 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/04/2022 23:46:20 - INFO - codeparrot_training - Step 29201: {'lr': 0.00045947185150005106, 'samples': 14951424, 'steps': 29201, 'loss/train': 2.1561901569366455}
-03/04/2022 23:46:23 - INFO - codeparrot_training - Step 29202: {'lr': 0.0004594689548030489, 'samples': 14951936, 'steps': 29202, 'loss/train': 2.059141159057617}
-03/04/2022 23:46:24 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/04/2022 23:46:28 - INFO - codeparrot_training - Step 29203: {'lr': 0.0004594660580116633, 'samples': 14952448, 'steps': 29203, 'loss/train': 1.4568690061569214}
-03/04/2022 23:46:31 - INFO - codeparrot_training - Step 29204: {'lr': 0.00045946316112589546, 'samples': 14952960, 'steps': 29204, 'loss/train': 1.5101159811019897}
-03/04/2022 23:46:32 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/04/2022 23:46:37 - INFO - codeparrot_training - Step 29205: {'lr': 0.0004594602641457468, 'samples': 14953472, 'steps': 29205, 'loss/train': 1.8471393585205078}
-03/04/2022 23:46:40 - INFO - codeparrot_training - Step 29206: {'lr': 0.0004594573670712186, 'samples': 14953984, 'steps': 29206, 'loss/train': 1.5102828741073608}
-03/04/2022 23:46:41 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/04/2022 23:46:45 - INFO - codeparrot_training - Step 29207: {'lr': 0.0004594544699023121, 'samples': 14954496, 'steps': 29207, 'loss/train': 0.9241095185279846}
-03/04/2022 23:46:48 - INFO - codeparrot_training - Step 29208: {'lr': 0.0004594515726390287, 'samples': 14955008, 'steps': 29208, 'loss/train': 1.493963599205017}
-03/04/2022 23:46:49 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/04/2022 23:46:53 - INFO - codeparrot_training - Step 29209: {'lr': 0.00045944867528136956, 'samples': 14955520, 'steps': 29209, 'loss/train': 2.2859549522399902}
-03/04/2022 23:46:57 - INFO - codeparrot_training - Step 29210: {'lr': 0.00045944577782933615, 'samples': 14956032, 'steps': 29210, 'loss/train': 1.8016430139541626}
-03/04/2022 23:46:57 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/04/2022 23:47:02 - INFO - codeparrot_training - Step 29211: {'lr': 0.0004594428802829297, 'samples': 14956544, 'steps': 29211, 'loss/train': 1.4314749240875244}
-03/04/2022 23:47:05 - INFO - codeparrot_training - Step 29212: {'lr': 0.00045943998264215153, 'samples': 14957056, 'steps': 29212, 'loss/train': 1.7682195901870728}
-03/04/2022 23:47:05 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/04/2022 23:47:10 - INFO - codeparrot_training - Step 29213: {'lr': 0.0004594370849070029, 'samples': 14957568, 'steps': 29213, 'loss/train': 2.0264620780944824}
-03/04/2022 23:47:13 - INFO - codeparrot_training - Step 29214: {'lr': 0.00045943418707748517, 'samples': 14958080, 'steps': 29214, 'loss/train': 1.371829628944397}
-03/04/2022 23:47:13 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 23:47:19 - INFO - codeparrot_training - Step 29215: {'lr': 0.00045943128915359966, 'samples': 14958592, 'steps': 29215, 'loss/train': 0.9132925271987915}
-03/04/2022 23:47:21 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/04/2022 23:47:24 - INFO - codeparrot_training - Step 29216: {'lr': 0.0004594283911353476, 'samples': 14959104, 'steps': 29216, 'loss/train': 1.1706929206848145}
-03/04/2022 23:47:27 - INFO - codeparrot_training - Step 29217: {'lr': 0.0004594254930227303, 'samples': 14959616, 'steps': 29217, 'loss/train': 1.4035017490386963}
-03/04/2022 23:47:30 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/04/2022 23:47:32 - INFO - codeparrot_training - Step 29218: {'lr': 0.0004594225948157492, 'samples': 14960128, 'steps': 29218, 'loss/train': 1.3465173244476318}
-03/04/2022 23:47:35 - INFO - codeparrot_training - Step 29219: {'lr': 0.0004594196965144054, 'samples': 14960640, 'steps': 29219, 'loss/train': 1.5257153511047363}
-03/04/2022 23:47:38 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/04/2022 23:47:41 - INFO - codeparrot_training - Step 29220: {'lr': 0.0004594167981187004, 'samples': 14961152, 'steps': 29220, 'loss/train': 2.235862970352173}
-03/04/2022 23:47:44 - INFO - codeparrot_training - Step 29221: {'lr': 0.00045941389962863546, 'samples': 14961664, 'steps': 29221, 'loss/train': 1.472684621810913}
-03/04/2022 23:47:46 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/04/2022 23:47:49 - INFO - codeparrot_training - Step 29222: {'lr': 0.00045941100104421176, 'samples': 14962176, 'steps': 29222, 'loss/train': 2.257507085800171}
-03/04/2022 23:47:52 - INFO - codeparrot_training - Step 29223: {'lr': 0.0004594081023654307, 'samples': 14962688, 'steps': 29223, 'loss/train': 1.8167643547058105}
-03/04/2022 23:47:55 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/04/2022 23:47:57 - INFO - codeparrot_training - Step 29224: {'lr': 0.00045940520359229366, 'samples': 14963200, 'steps': 29224, 'loss/train': 0.5609900951385498}
-03/04/2022 23:48:01 - INFO - codeparrot_training - Step 29225: {'lr': 0.0004594023047248018, 'samples': 14963712, 'steps': 29225, 'loss/train': 1.807757019996643}
-03/04/2022 23:48:03 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/04/2022 23:48:06 - INFO - codeparrot_training - Step 29226: {'lr': 0.0004593994057629565, 'samples': 14964224, 'steps': 29226, 'loss/train': 1.5098109245300293}
-03/04/2022 23:48:09 - INFO - codeparrot_training - Step 29227: {'lr': 0.000459396506706759, 'samples': 14964736, 'steps': 29227, 'loss/train': 1.2664109468460083}
-03/04/2022 23:48:11 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/04/2022 23:48:14 - INFO - codeparrot_training - Step 29228: {'lr': 0.00045939360755621074, 'samples': 14965248, 'steps': 29228, 'loss/train': 2.0569136142730713}
-03/04/2022 23:48:18 - INFO - codeparrot_training - Step 29229: {'lr': 0.00045939070831131293, 'samples': 14965760, 'steps': 29229, 'loss/train': 1.0897387266159058}
-03/04/2022 23:48:20 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/04/2022 23:48:23 - INFO - codeparrot_training - Step 29230: {'lr': 0.00045938780897206686, 'samples': 14966272, 'steps': 29230, 'loss/train': 1.7062350511550903}
-03/04/2022 23:48:26 - INFO - codeparrot_training - Step 29231: {'lr': 0.000459384909538474, 'samples': 14966784, 'steps': 29231, 'loss/train': 1.452660322189331}
-03/04/2022 23:48:28 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/04/2022 23:48:31 - INFO - codeparrot_training - Step 29232: {'lr': 0.00045938201001053546, 'samples': 14967296, 'steps': 29232, 'loss/train': 1.7859289646148682}
-03/04/2022 23:48:34 - INFO - codeparrot_training - Step 29233: {'lr': 0.00045937911038825257, 'samples': 14967808, 'steps': 29233, 'loss/train': 2.056885004043579}
-03/04/2022 23:48:36 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/04/2022 23:48:40 - INFO - codeparrot_training - Step 29234: {'lr': 0.00045937621067162674, 'samples': 14968320, 'steps': 29234, 'loss/train': 1.49907648563385}
-03/04/2022 23:48:43 - INFO - codeparrot_training - Step 29235: {'lr': 0.0004593733108606592, 'samples': 14968832, 'steps': 29235, 'loss/train': 1.9306999444961548}
-03/04/2022 23:48:45 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/04/2022 23:48:48 - INFO - codeparrot_training - Step 29236: {'lr': 0.00045937041095535125, 'samples': 14969344, 'steps': 29236, 'loss/train': 3.049901247024536}
-03/04/2022 23:48:51 - INFO - codeparrot_training - Step 29237: {'lr': 0.00045936751095570426, 'samples': 14969856, 'steps': 29237, 'loss/train': 1.6104816198349}
-03/04/2022 23:48:53 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/04/2022 23:48:56 - INFO - codeparrot_training - Step 29238: {'lr': 0.0004593646108617195, 'samples': 14970368, 'steps': 29238, 'loss/train': 1.4078501462936401}
-03/04/2022 23:48:59 - INFO - codeparrot_training - Step 29239: {'lr': 0.00045936171067339826, 'samples': 14970880, 'steps': 29239, 'loss/train': 1.0141301155090332}
-03/04/2022 23:49:01 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/04/2022 23:49:05 - INFO - codeparrot_training - Step 29240: {'lr': 0.0004593588103907419, 'samples': 14971392, 'steps': 29240, 'loss/train': 1.2019420862197876}
-03/04/2022 23:49:08 - INFO - codeparrot_training - Step 29241: {'lr': 0.00045935591001375163, 'samples': 14971904, 'steps': 29241, 'loss/train': 1.571325659751892}
-03/04/2022 23:49:09 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/04/2022 23:49:13 - INFO - codeparrot_training - Step 29242: {'lr': 0.0004593530095424289, 'samples': 14972416, 'steps': 29242, 'loss/train': 1.2857160568237305}
-03/04/2022 23:49:16 - INFO - codeparrot_training - Step 29243: {'lr': 0.0004593501089767749, 'samples': 14972928, 'steps': 29243, 'loss/train': 1.6300240755081177}
-03/04/2022 23:49:22 - INFO - codeparrot_training - Step 29244: {'lr': 0.00045934720831679093, 'samples': 14973440, 'steps': 29244, 'loss/train': 1.77163827419281}
-03/04/2022 23:49:25 - INFO - codeparrot_training - Step 29245: {'lr': 0.00045934430756247835, 'samples': 14973952, 'steps': 29245, 'loss/train': 1.7497230768203735}
-03/04/2022 23:49:27 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/04/2022 23:49:30 - INFO - codeparrot_training - Step 29246: {'lr': 0.0004593414067138385, 'samples': 14974464, 'steps': 29246, 'loss/train': 1.3070402145385742}
-03/04/2022 23:49:33 - INFO - codeparrot_training - Step 29247: {'lr': 0.0004593385057708726, 'samples': 14974976, 'steps': 29247, 'loss/train': 0.07284893095493317}
-03/04/2022 23:49:35 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/04/2022 23:49:39 - INFO - codeparrot_training - Step 29248: {'lr': 0.00045933560473358206, 'samples': 14975488, 'steps': 29248, 'loss/train': 1.9109457731246948}
-03/04/2022 23:49:42 - INFO - codeparrot_training - Step 29249: {'lr': 0.00045933270360196804, 'samples': 14976000, 'steps': 29249, 'loss/train': 1.7871251106262207}
-03/04/2022 23:49:43 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/04/2022 23:49:47 - INFO - codeparrot_training - Step 29250: {'lr': 0.00045932980237603196, 'samples': 14976512, 'steps': 29250, 'loss/train': 1.1027573347091675}
-03/04/2022 23:49:50 - INFO - codeparrot_training - Step 29251: {'lr': 0.0004593269010557751, 'samples': 14977024, 'steps': 29251, 'loss/train': 1.710270881652832}
-03/04/2022 23:49:52 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/04/2022 23:49:56 - INFO - codeparrot_training - Step 29252: {'lr': 0.00045932399964119884, 'samples': 14977536, 'steps': 29252, 'loss/train': 0.8067901730537415}
-03/04/2022 23:49:59 - INFO - codeparrot_training - Step 29253: {'lr': 0.00045932109813230437, 'samples': 14978048, 'steps': 29253, 'loss/train': 1.3872336149215698}
-03/04/2022 23:50:00 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/04/2022 23:50:04 - INFO - codeparrot_training - Step 29254: {'lr': 0.00045931819652909303, 'samples': 14978560, 'steps': 29254, 'loss/train': 2.0938286781311035}
-03/04/2022 23:50:07 - INFO - codeparrot_training - Step 29255: {'lr': 0.0004593152948315661, 'samples': 14979072, 'steps': 29255, 'loss/train': 1.9173353910446167}
-03/04/2022 23:50:08 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/04/2022 23:50:12 - INFO - codeparrot_training - Step 29256: {'lr': 0.000459312393039725, 'samples': 14979584, 'steps': 29256, 'loss/train': 1.884562373161316}
-03/04/2022 23:50:15 - INFO - codeparrot_training - Step 29257: {'lr': 0.0004593094911535709, 'samples': 14980096, 'steps': 29257, 'loss/train': 1.7618381977081299}
-03/04/2022 23:50:16 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/04/2022 23:50:21 - INFO - codeparrot_training - Step 29258: {'lr': 0.00045930658917310525, 'samples': 14980608, 'steps': 29258, 'loss/train': 0.8617112040519714}
-03/04/2022 23:50:24 - INFO - codeparrot_training - Step 29259: {'lr': 0.0004593036870983293, 'samples': 14981120, 'steps': 29259, 'loss/train': 1.3619742393493652}
-03/04/2022 23:50:25 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/04/2022 23:50:29 - INFO - codeparrot_training - Step 29260: {'lr': 0.0004593007849292442, 'samples': 14981632, 'steps': 29260, 'loss/train': 1.5753803253173828}
-03/04/2022 23:50:32 - INFO - codeparrot_training - Step 29261: {'lr': 0.0004592978826658515, 'samples': 14982144, 'steps': 29261, 'loss/train': 1.4469960927963257}
-03/04/2022 23:50:33 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/04/2022 23:50:38 - INFO - codeparrot_training - Step 29262: {'lr': 0.0004592949803081524, 'samples': 14982656, 'steps': 29262, 'loss/train': 1.370040774345398}
-03/04/2022 23:50:41 - INFO - codeparrot_training - Step 29263: {'lr': 0.0004592920778561481, 'samples': 14983168, 'steps': 29263, 'loss/train': 1.4759734869003296}
-03/04/2022 23:50:42 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/04/2022 23:50:46 - INFO - codeparrot_training - Step 29264: {'lr': 0.00045928917530984014, 'samples': 14983680, 'steps': 29264, 'loss/train': 1.5567537546157837}
-03/04/2022 23:50:49 - INFO - codeparrot_training - Step 29265: {'lr': 0.00045928627266922974, 'samples': 14984192, 'steps': 29265, 'loss/train': 1.8861668109893799}
-03/04/2022 23:50:50 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/04/2022 23:50:54 - INFO - codeparrot_training - Step 29266: {'lr': 0.0004592833699343181, 'samples': 14984704, 'steps': 29266, 'loss/train': 1.1019564867019653}
-03/04/2022 23:50:58 - INFO - codeparrot_training - Step 29267: {'lr': 0.0004592804671051066, 'samples': 14985216, 'steps': 29267, 'loss/train': 1.5800999402999878}
-03/04/2022 23:50:58 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/04/2022 23:51:03 - INFO - codeparrot_training - Step 29268: {'lr': 0.0004592775641815966, 'samples': 14985728, 'steps': 29268, 'loss/train': 2.321160316467285}
-03/04/2022 23:51:06 - INFO - codeparrot_training - Step 29269: {'lr': 0.0004592746611637893, 'samples': 14986240, 'steps': 29269, 'loss/train': 1.6887288093566895}
-03/04/2022 23:51:07 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/04/2022 23:51:11 - INFO - codeparrot_training - Step 29270: {'lr': 0.00045927175805168607, 'samples': 14986752, 'steps': 29270, 'loss/train': 1.3715522289276123}
-03/04/2022 23:51:14 - INFO - codeparrot_training - Step 29271: {'lr': 0.00045926885484528823, 'samples': 14987264, 'steps': 29271, 'loss/train': 1.1664009094238281}
-03/04/2022 23:51:15 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/04/2022 23:51:20 - INFO - codeparrot_training - Step 29272: {'lr': 0.0004592659515445971, 'samples': 14987776, 'steps': 29272, 'loss/train': 2.1006245613098145}
-03/04/2022 23:51:23 - INFO - codeparrot_training - Step 29273: {'lr': 0.00045926304814961397, 'samples': 14988288, 'steps': 29273, 'loss/train': 1.6812574863433838}
-03/04/2022 23:51:23 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/04/2022 23:51:28 - INFO - codeparrot_training - Step 29274: {'lr': 0.00045926014466034004, 'samples': 14988800, 'steps': 29274, 'loss/train': 1.5413551330566406}
-03/04/2022 23:51:31 - INFO - codeparrot_training - Step 29275: {'lr': 0.0004592572410767768, 'samples': 14989312, 'steps': 29275, 'loss/train': 1.401471734046936}
-03/04/2022 23:51:32 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/04/2022 23:51:37 - INFO - codeparrot_training - Step 29276: {'lr': 0.0004592543373989255, 'samples': 14989824, 'steps': 29276, 'loss/train': 2.292088747024536}
-03/04/2022 23:51:40 - INFO - codeparrot_training - Step 29277: {'lr': 0.0004592514336267874, 'samples': 14990336, 'steps': 29277, 'loss/train': 1.968109369277954}
-03/04/2022 23:51:40 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/04/2022 23:51:45 - INFO - codeparrot_training - Step 29278: {'lr': 0.0004592485297603638, 'samples': 14990848, 'steps': 29278, 'loss/train': 1.6951879262924194}
-03/04/2022 23:51:49 - INFO - codeparrot_training - Step 29279: {'lr': 0.0004592456257996561, 'samples': 14991360, 'steps': 29279, 'loss/train': 6.557301044464111}
-03/04/2022 23:51:50 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/04/2022 23:51:54 - INFO - codeparrot_training - Step 29280: {'lr': 0.0004592427217446655, 'samples': 14991872, 'steps': 29280, 'loss/train': 1.8735361099243164}
-03/04/2022 23:51:57 - INFO - codeparrot_training - Step 29281: {'lr': 0.00045923981759539336, 'samples': 14992384, 'steps': 29281, 'loss/train': 1.4063336849212646}
-03/04/2022 23:51:58 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/04/2022 23:52:02 - INFO - codeparrot_training - Step 29282: {'lr': 0.000459236913351841, 'samples': 14992896, 'steps': 29282, 'loss/train': 0.7368330359458923}
-03/04/2022 23:52:05 - INFO - codeparrot_training - Step 29283: {'lr': 0.0004592340090140097, 'samples': 14993408, 'steps': 29283, 'loss/train': 1.0861183404922485}
-03/04/2022 23:52:07 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/04/2022 23:52:11 - INFO - codeparrot_training - Step 29284: {'lr': 0.0004592311045819008, 'samples': 14993920, 'steps': 29284, 'loss/train': 1.5231988430023193}
-03/04/2022 23:52:14 - INFO - codeparrot_training - Step 29285: {'lr': 0.00045922820005551556, 'samples': 14994432, 'steps': 29285, 'loss/train': 0.7439308762550354}
-03/04/2022 23:52:15 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/04/2022 23:52:19 - INFO - codeparrot_training - Step 29286: {'lr': 0.0004592252954348554, 'samples': 14994944, 'steps': 29286, 'loss/train': 1.690280795097351}
-03/04/2022 23:52:22 - INFO - codeparrot_training - Step 29287: {'lr': 0.0004592223907199215, 'samples': 14995456, 'steps': 29287, 'loss/train': 2.8310394287109375}
-03/04/2022 23:52:23 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/04/2022 23:52:28 - INFO - codeparrot_training - Step 29288: {'lr': 0.0004592194859107153, 'samples': 14995968, 'steps': 29288, 'loss/train': 2.448380947113037}
-03/04/2022 23:52:31 - INFO - codeparrot_training - Step 29289: {'lr': 0.0004592165810072379, 'samples': 14996480, 'steps': 29289, 'loss/train': 1.696124792098999}
-03/04/2022 23:52:31 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/04/2022 23:52:36 - INFO - codeparrot_training - Step 29290: {'lr': 0.00045921367600949077, 'samples': 14996992, 'steps': 29290, 'loss/train': 1.7035648822784424}
-03/04/2022 23:52:39 - INFO - codeparrot_training - Step 29291: {'lr': 0.0004592107709174752, 'samples': 14997504, 'steps': 29291, 'loss/train': 1.3913615942001343}
-03/04/2022 23:52:40 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/04/2022 23:52:44 - INFO - codeparrot_training - Step 29292: {'lr': 0.0004592078657311925, 'samples': 14998016, 'steps': 29292, 'loss/train': 1.4456334114074707}
-03/04/2022 23:52:48 - INFO - codeparrot_training - Step 29293: {'lr': 0.000459204960450644, 'samples': 14998528, 'steps': 29293, 'loss/train': 1.8641268014907837}
-03/04/2022 23:52:48 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/04/2022 23:52:53 - INFO - codeparrot_training - Step 29294: {'lr': 0.0004592020550758309, 'samples': 14999040, 'steps': 29294, 'loss/train': 1.8045189380645752}
-03/04/2022 23:52:56 - INFO - codeparrot_training - Step 29295: {'lr': 0.0004591991496067546, 'samples': 14999552, 'steps': 29295, 'loss/train': 1.8933684825897217}
-03/04/2022 23:52:56 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/04/2022 23:53:01 - INFO - codeparrot_training - Step 29296: {'lr': 0.00045919624404341643, 'samples': 15000064, 'steps': 29296, 'loss/train': 1.6170521974563599}
-03/04/2022 23:53:04 - INFO - codeparrot_training - Step 29297: {'lr': 0.00045919333838581757, 'samples': 15000576, 'steps': 29297, 'loss/train': 0.8565620183944702}
-03/04/2022 23:53:04 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/04/2022 23:53:09 - INFO - codeparrot_training - Step 29298: {'lr': 0.00045919043263395953, 'samples': 15001088, 'steps': 29298, 'loss/train': 1.7696832418441772}
-03/04/2022 23:53:13 - INFO - codeparrot_training - Step 29299: {'lr': 0.00045918752678784344, 'samples': 15001600, 'steps': 29299, 'loss/train': 2.1313703060150146}
-03/04/2022 23:53:13 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/04/2022 23:53:18 - INFO - codeparrot_training - Step 29300: {'lr': 0.0004591846208474707, 'samples': 15002112, 'steps': 29300, 'loss/train': 0.11841027438640594}
-03/04/2022 23:53:21 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/04/2022 23:53:23 - INFO - codeparrot_training - Step 29301: {'lr': 0.00045918171481284256, 'samples': 15002624, 'steps': 29301, 'loss/train': 2.164182424545288}
-03/04/2022 23:53:26 - INFO - codeparrot_training - Step 29302: {'lr': 0.0004591788086839604, 'samples': 15003136, 'steps': 29302, 'loss/train': 2.7862143516540527}
-03/04/2022 23:53:29 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/04/2022 23:53:32 - INFO - codeparrot_training - Step 29303: {'lr': 0.0004591759024608255, 'samples': 15003648, 'steps': 29303, 'loss/train': 1.3453686237335205}
-03/04/2022 23:53:35 - INFO - codeparrot_training - Step 29304: {'lr': 0.0004591729961434392, 'samples': 15004160, 'steps': 29304, 'loss/train': 1.5795297622680664}
-03/04/2022 23:53:38 - INFO - codeparrot_training - Step 29305: {'lr': 0.00045917008973180273, 'samples': 15004672, 'steps': 29305, 'loss/train': 2.180284261703491}
-03/04/2022 23:53:39 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/04/2022 23:53:44 - INFO - codeparrot_training - Step 29306: {'lr': 0.0004591671832259174, 'samples': 15005184, 'steps': 29306, 'loss/train': 2.2017552852630615}
-03/04/2022 23:53:47 - INFO - codeparrot_training - Step 29307: {'lr': 0.00045916427662578464, 'samples': 15005696, 'steps': 29307, 'loss/train': 1.3762558698654175}
-03/04/2022 23:53:49 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/04/2022 23:53:52 - INFO - codeparrot_training - Step 29308: {'lr': 0.00045916136993140574, 'samples': 15006208, 'steps': 29308, 'loss/train': 2.163473129272461}
-03/04/2022 23:53:55 - INFO - codeparrot_training - Step 29309: {'lr': 0.00045915846314278187, 'samples': 15006720, 'steps': 29309, 'loss/train': 1.6123850345611572}
-03/04/2022 23:53:57 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/04/2022 23:54:01 - INFO - codeparrot_training - Step 29310: {'lr': 0.0004591555562599144, 'samples': 15007232, 'steps': 29310, 'loss/train': 1.4353289604187012}
-03/04/2022 23:54:04 - INFO - codeparrot_training - Step 29311: {'lr': 0.00045915264928280476, 'samples': 15007744, 'steps': 29311, 'loss/train': 2.267923593521118}
-03/04/2022 23:54:05 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/04/2022 23:54:09 - INFO - codeparrot_training - Step 29312: {'lr': 0.00045914974221145403, 'samples': 15008256, 'steps': 29312, 'loss/train': 1.6344242095947266}
-03/04/2022 23:54:12 - INFO - codeparrot_training - Step 29313: {'lr': 0.00045914683504586374, 'samples': 15008768, 'steps': 29313, 'loss/train': 1.2414194345474243}
-03/04/2022 23:54:13 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/04/2022 23:54:17 - INFO - codeparrot_training - Step 29314: {'lr': 0.0004591439277860351, 'samples': 15009280, 'steps': 29314, 'loss/train': 1.7932771444320679}
-03/04/2022 23:54:21 - INFO - codeparrot_training - Step 29315: {'lr': 0.00045914102043196947, 'samples': 15009792, 'steps': 29315, 'loss/train': 2.549272298812866}
-03/04/2022 23:54:22 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 23:54:26 - INFO - codeparrot_training - Step 29316: {'lr': 0.00045913811298366804, 'samples': 15010304, 'steps': 29316, 'loss/train': 1.155446171760559}
-03/04/2022 23:54:29 - INFO - codeparrot_training - Step 29317: {'lr': 0.0004591352054411323, 'samples': 15010816, 'steps': 29317, 'loss/train': 1.878786325454712}
-03/04/2022 23:54:30 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/04/2022 23:54:34 - INFO - codeparrot_training - Step 29318: {'lr': 0.00045913229780436337, 'samples': 15011328, 'steps': 29318, 'loss/train': 1.4083280563354492}
-03/04/2022 23:54:38 - INFO - codeparrot_training - Step 29319: {'lr': 0.00045912939007336273, 'samples': 15011840, 'steps': 29319, 'loss/train': 1.5641683340072632}
-03/04/2022 23:54:38 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/04/2022 23:54:43 - INFO - codeparrot_training - Step 29320: {'lr': 0.0004591264822481316, 'samples': 15012352, 'steps': 29320, 'loss/train': 1.866489052772522}
-03/04/2022 23:54:46 - INFO - codeparrot_training - Step 29321: {'lr': 0.00045912357432867124, 'samples': 15012864, 'steps': 29321, 'loss/train': 0.9689801931381226}
-03/04/2022 23:54:47 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/04/2022 23:54:51 - INFO - codeparrot_training - Step 29322: {'lr': 0.00045912066631498304, 'samples': 15013376, 'steps': 29322, 'loss/train': 1.7738481760025024}
-03/04/2022 23:54:54 - INFO - codeparrot_training - Step 29323: {'lr': 0.00045911775820706835, 'samples': 15013888, 'steps': 29323, 'loss/train': 1.4786698818206787}
-03/04/2022 23:54:55 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/04/2022 23:55:00 - INFO - codeparrot_training - Step 29324: {'lr': 0.0004591148500049284, 'samples': 15014400, 'steps': 29324, 'loss/train': 2.230304479598999}
-03/04/2022 23:55:03 - INFO - codeparrot_training - Step 29325: {'lr': 0.00045911194170856454, 'samples': 15014912, 'steps': 29325, 'loss/train': 1.7666839361190796}
-03/04/2022 23:55:04 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/04/2022 23:55:08 - INFO - codeparrot_training - Step 29326: {'lr': 0.00045910903331797807, 'samples': 15015424, 'steps': 29326, 'loss/train': 2.009965658187866}
-03/04/2022 23:55:11 - INFO - codeparrot_training - Step 29327: {'lr': 0.00045910612483317025, 'samples': 15015936, 'steps': 29327, 'loss/train': 1.6263728141784668}
-03/04/2022 23:55:12 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/04/2022 23:55:17 - INFO - codeparrot_training - Step 29328: {'lr': 0.00045910321625414245, 'samples': 15016448, 'steps': 29328, 'loss/train': 1.7851859331130981}
-03/04/2022 23:55:20 - INFO - codeparrot_training - Step 29329: {'lr': 0.00045910030758089597, 'samples': 15016960, 'steps': 29329, 'loss/train': 1.5645885467529297}
-03/04/2022 23:55:21 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/04/2022 23:55:25 - INFO - codeparrot_training - Step 29330: {'lr': 0.00045909739881343215, 'samples': 15017472, 'steps': 29330, 'loss/train': 1.4436148405075073}
-03/04/2022 23:55:28 - INFO - codeparrot_training - Step 29331: {'lr': 0.00045909448995175224, 'samples': 15017984, 'steps': 29331, 'loss/train': 2.3456761837005615}
-03/04/2022 23:55:29 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/04/2022 23:55:33 - INFO - codeparrot_training - Step 29332: {'lr': 0.00045909158099585756, 'samples': 15018496, 'steps': 29332, 'loss/train': 2.136915445327759}
-03/04/2022 23:55:37 - INFO - codeparrot_training - Step 29333: {'lr': 0.00045908867194574955, 'samples': 15019008, 'steps': 29333, 'loss/train': 2.6090152263641357}
-03/04/2022 23:55:37 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/04/2022 23:55:42 - INFO - codeparrot_training - Step 29334: {'lr': 0.00045908576280142925, 'samples': 15019520, 'steps': 29334, 'loss/train': 1.0786669254302979}
-03/04/2022 23:55:45 - INFO - codeparrot_training - Step 29335: {'lr': 0.00045908285356289824, 'samples': 15020032, 'steps': 29335, 'loss/train': 1.4498578310012817}
-03/04/2022 23:55:46 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/04/2022 23:55:50 - INFO - codeparrot_training - Step 29336: {'lr': 0.0004590799442301577, 'samples': 15020544, 'steps': 29336, 'loss/train': 1.2504308223724365}
-03/04/2022 23:55:53 - INFO - codeparrot_training - Step 29337: {'lr': 0.00045907703480320894, 'samples': 15021056, 'steps': 29337, 'loss/train': 2.438580274581909}
-03/04/2022 23:55:54 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/04/2022 23:55:59 - INFO - codeparrot_training - Step 29338: {'lr': 0.0004590741252820533, 'samples': 15021568, 'steps': 29338, 'loss/train': 2.110753059387207}
-03/04/2022 23:56:02 - INFO - codeparrot_training - Step 29339: {'lr': 0.00045907121566669216, 'samples': 15022080, 'steps': 29339, 'loss/train': 1.3871588706970215}
-03/04/2022 23:56:02 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/04/2022 23:56:07 - INFO - codeparrot_training - Step 29340: {'lr': 0.0004590683059571267, 'samples': 15022592, 'steps': 29340, 'loss/train': 1.143405795097351}
-03/04/2022 23:56:10 - INFO - codeparrot_training - Step 29341: {'lr': 0.0004590653961533582, 'samples': 15023104, 'steps': 29341, 'loss/train': 1.4088921546936035}
-03/04/2022 23:56:11 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/04/2022 23:56:15 - INFO - codeparrot_training - Step 29342: {'lr': 0.00045906248625538816, 'samples': 15023616, 'steps': 29342, 'loss/train': 0.20147539675235748}
-03/04/2022 23:56:19 - INFO - codeparrot_training - Step 29343: {'lr': 0.00045905957626321775, 'samples': 15024128, 'steps': 29343, 'loss/train': 2.1137566566467285}
-03/04/2022 23:56:19 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/04/2022 23:56:24 - INFO - codeparrot_training - Step 29344: {'lr': 0.0004590566661768484, 'samples': 15024640, 'steps': 29344, 'loss/train': 0.6321955323219299}
-03/04/2022 23:56:27 - INFO - codeparrot_training - Step 29345: {'lr': 0.00045905375599628127, 'samples': 15025152, 'steps': 29345, 'loss/train': 1.2742096185684204}
-03/04/2022 23:56:27 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/04/2022 23:56:32 - INFO - codeparrot_training - Step 29346: {'lr': 0.00045905084572151774, 'samples': 15025664, 'steps': 29346, 'loss/train': 1.6061334609985352}
-03/04/2022 23:56:36 - INFO - codeparrot_training - Step 29347: {'lr': 0.0004590479353525591, 'samples': 15026176, 'steps': 29347, 'loss/train': 1.5192416906356812}
-03/04/2022 23:56:36 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/04/2022 23:56:41 - INFO - codeparrot_training - Step 29348: {'lr': 0.00045904502488940677, 'samples': 15026688, 'steps': 29348, 'loss/train': 1.9727452993392944}
-03/04/2022 23:56:44 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/04/2022 23:56:46 - INFO - codeparrot_training - Step 29349: {'lr': 0.0004590421143320619, 'samples': 15027200, 'steps': 29349, 'loss/train': 1.8296093940734863}
-03/04/2022 23:56:49 - INFO - codeparrot_training - Step 29350: {'lr': 0.0004590392036805259, 'samples': 15027712, 'steps': 29350, 'loss/train': 1.5805566310882568}
-03/04/2022 23:56:52 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/04/2022 23:56:54 - INFO - codeparrot_training - Step 29351: {'lr': 0.0004590362929348001, 'samples': 15028224, 'steps': 29351, 'loss/train': 1.9039947986602783}
-03/04/2022 23:56:57 - INFO - codeparrot_training - Step 29352: {'lr': 0.00045903338209488575, 'samples': 15028736, 'steps': 29352, 'loss/train': 1.7140283584594727}
-03/04/2022 23:57:00 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/04/2022 23:57:03 - INFO - codeparrot_training - Step 29353: {'lr': 0.0004590304711607842, 'samples': 15029248, 'steps': 29353, 'loss/train': 2.059628963470459}
-03/04/2022 23:57:06 - INFO - codeparrot_training - Step 29354: {'lr': 0.0004590275601324967, 'samples': 15029760, 'steps': 29354, 'loss/train': 2.090101957321167}
-03/04/2022 23:57:08 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/04/2022 23:57:11 - INFO - codeparrot_training - Step 29355: {'lr': 0.0004590246490100246, 'samples': 15030272, 'steps': 29355, 'loss/train': 1.8837968111038208}
-03/04/2022 23:57:14 - INFO - codeparrot_training - Step 29356: {'lr': 0.00045902173779336925, 'samples': 15030784, 'steps': 29356, 'loss/train': 1.6638803482055664}
-03/04/2022 23:57:17 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/04/2022 23:57:20 - INFO - codeparrot_training - Step 29357: {'lr': 0.0004590188264825319, 'samples': 15031296, 'steps': 29357, 'loss/train': 1.9209269285202026}
-03/04/2022 23:57:23 - INFO - codeparrot_training - Step 29358: {'lr': 0.00045901591507751393, 'samples': 15031808, 'steps': 29358, 'loss/train': 0.8897549510002136}
-03/04/2022 23:57:25 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/04/2022 23:57:28 - INFO - codeparrot_training - Step 29359: {'lr': 0.00045901300357831666, 'samples': 15032320, 'steps': 29359, 'loss/train': 1.6359342336654663}
-03/04/2022 23:57:31 - INFO - codeparrot_training - Step 29360: {'lr': 0.00045901009198494124, 'samples': 15032832, 'steps': 29360, 'loss/train': 2.4698593616485596}
-03/04/2022 23:57:34 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/04/2022 23:57:37 - INFO - codeparrot_training - Step 29361: {'lr': 0.0004590071802973892, 'samples': 15033344, 'steps': 29361, 'loss/train': 2.366023302078247}
-03/04/2022 23:57:40 - INFO - codeparrot_training - Step 29362: {'lr': 0.0004590042685156617, 'samples': 15033856, 'steps': 29362, 'loss/train': 2.842386484146118}
-03/04/2022 23:57:42 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/04/2022 23:57:45 - INFO - codeparrot_training - Step 29363: {'lr': 0.0004590013566397601, 'samples': 15034368, 'steps': 29363, 'loss/train': 2.3161425590515137}
-03/04/2022 23:57:48 - INFO - codeparrot_training - Step 29364: {'lr': 0.00045899844466968574, 'samples': 15034880, 'steps': 29364, 'loss/train': 1.6863075494766235}
-03/04/2022 23:57:51 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/04/2022 23:57:54 - INFO - codeparrot_training - Step 29365: {'lr': 0.00045899553260543986, 'samples': 15035392, 'steps': 29365, 'loss/train': 0.3066198527812958}
-03/04/2022 23:57:57 - INFO - codeparrot_training - Step 29366: {'lr': 0.0004589926204470238, 'samples': 15035904, 'steps': 29366, 'loss/train': 1.0797796249389648}
-03/04/2022 23:57:59 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/04/2022 23:58:02 - INFO - codeparrot_training - Step 29367: {'lr': 0.000458989708194439, 'samples': 15036416, 'steps': 29367, 'loss/train': 1.6987740993499756}
-03/04/2022 23:58:05 - INFO - codeparrot_training - Step 29368: {'lr': 0.0004589867958476866, 'samples': 15036928, 'steps': 29368, 'loss/train': 1.0507696866989136}
-03/04/2022 23:58:07 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/04/2022 23:58:11 - INFO - codeparrot_training - Step 29369: {'lr': 0.000458983883406768, 'samples': 15037440, 'steps': 29369, 'loss/train': 1.1876485347747803}
-03/04/2022 23:58:14 - INFO - codeparrot_training - Step 29370: {'lr': 0.0004589809708716844, 'samples': 15037952, 'steps': 29370, 'loss/train': 0.9224165081977844}
-03/04/2022 23:58:16 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/04/2022 23:58:19 - INFO - codeparrot_training - Step 29371: {'lr': 0.0004589780582424373, 'samples': 15038464, 'steps': 29371, 'loss/train': 1.6911582946777344}
-03/04/2022 23:58:22 - INFO - codeparrot_training - Step 29372: {'lr': 0.00045897514551902785, 'samples': 15038976, 'steps': 29372, 'loss/train': 1.165657877922058}
-03/04/2022 23:58:24 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/04/2022 23:58:27 - INFO - codeparrot_training - Step 29373: {'lr': 0.0004589722327014575, 'samples': 15039488, 'steps': 29373, 'loss/train': 0.9894626140594482}
-03/04/2022 23:58:30 - INFO - codeparrot_training - Step 29374: {'lr': 0.0004589693197897274, 'samples': 15040000, 'steps': 29374, 'loss/train': 1.0873037576675415}
-03/04/2022 23:58:32 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/04/2022 23:58:36 - INFO - codeparrot_training - Step 29375: {'lr': 0.0004589664067838389, 'samples': 15040512, 'steps': 29375, 'loss/train': 1.1943727731704712}
-03/04/2022 23:58:39 - INFO - codeparrot_training - Step 29376: {'lr': 0.00045896349368379356, 'samples': 15041024, 'steps': 29376, 'loss/train': 1.3523303270339966}
-03/04/2022 23:58:40 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/04/2022 23:58:44 - INFO - codeparrot_training - Step 29377: {'lr': 0.00045896058048959233, 'samples': 15041536, 'steps': 29377, 'loss/train': 1.1251169443130493}
-03/04/2022 23:58:47 - INFO - codeparrot_training - Step 29378: {'lr': 0.00045895766720123677, 'samples': 15042048, 'steps': 29378, 'loss/train': 1.760446310043335}
-03/04/2022 23:58:49 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/04/2022 23:58:53 - INFO - codeparrot_training - Step 29379: {'lr': 0.0004589547538187281, 'samples': 15042560, 'steps': 29379, 'loss/train': 1.7541284561157227}
-03/04/2022 23:58:56 - INFO - codeparrot_training - Step 29380: {'lr': 0.0004589518403420676, 'samples': 15043072, 'steps': 29380, 'loss/train': 1.3408077955245972}
-03/04/2022 23:58:57 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/04/2022 23:59:01 - INFO - codeparrot_training - Step 29381: {'lr': 0.00045894892677125667, 'samples': 15043584, 'steps': 29381, 'loss/train': 1.3243436813354492}
-03/04/2022 23:59:04 - INFO - codeparrot_training - Step 29382: {'lr': 0.0004589460131062965, 'samples': 15044096, 'steps': 29382, 'loss/train': 1.48696768283844}
-03/04/2022 23:59:05 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/04/2022 23:59:10 - INFO - codeparrot_training - Step 29383: {'lr': 0.00045894309934718853, 'samples': 15044608, 'steps': 29383, 'loss/train': 1.6326838731765747}
-03/04/2022 23:59:13 - INFO - codeparrot_training - Step 29384: {'lr': 0.00045894018549393404, 'samples': 15045120, 'steps': 29384, 'loss/train': 1.7004551887512207}
-03/04/2022 23:59:14 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/04/2022 23:59:18 - INFO - codeparrot_training - Step 29385: {'lr': 0.0004589372715465343, 'samples': 15045632, 'steps': 29385, 'loss/train': 1.7546541690826416}
-03/04/2022 23:59:21 - INFO - codeparrot_training - Step 29386: {'lr': 0.0004589343575049907, 'samples': 15046144, 'steps': 29386, 'loss/train': 1.845996379852295}
-03/04/2022 23:59:23 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/04/2022 23:59:27 - INFO - codeparrot_training - Step 29387: {'lr': 0.0004589314433693044, 'samples': 15046656, 'steps': 29387, 'loss/train': 1.858646035194397}
-03/04/2022 23:59:30 - INFO - codeparrot_training - Step 29388: {'lr': 0.0004589285291394769, 'samples': 15047168, 'steps': 29388, 'loss/train': 2.1043648719787598}
-03/04/2022 23:59:31 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/04/2022 23:59:35 - INFO - codeparrot_training - Step 29389: {'lr': 0.00045892561481550943, 'samples': 15047680, 'steps': 29389, 'loss/train': 2.2668938636779785}
-03/04/2022 23:59:38 - INFO - codeparrot_training - Step 29390: {'lr': 0.0004589227003974032, 'samples': 15048192, 'steps': 29390, 'loss/train': 0.5943100452423096}
-03/04/2022 23:59:39 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/04/2022 23:59:43 - INFO - codeparrot_training - Step 29391: {'lr': 0.00045891978588515975, 'samples': 15048704, 'steps': 29391, 'loss/train': 1.4961278438568115}
-03/04/2022 23:59:47 - INFO - codeparrot_training - Step 29392: {'lr': 0.0004589168712787802, 'samples': 15049216, 'steps': 29392, 'loss/train': 1.9302963018417358}
-03/04/2022 23:59:48 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/04/2022 23:59:52 - INFO - codeparrot_training - Step 29393: {'lr': 0.00045891395657826595, 'samples': 15049728, 'steps': 29393, 'loss/train': 1.2685033082962036}
-03/04/2022 23:59:55 - INFO - codeparrot_training - Step 29394: {'lr': 0.0004589110417836183, 'samples': 15050240, 'steps': 29394, 'loss/train': 2.0484282970428467}
-03/04/2022 23:59:56 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/05/2022 00:00:00 - INFO - codeparrot_training - Step 29395: {'lr': 0.0004589081268948386, 'samples': 15050752, 'steps': 29395, 'loss/train': 1.7589514255523682}
-03/05/2022 00:00:04 - INFO - codeparrot_training - Step 29396: {'lr': 0.00045890521191192807, 'samples': 15051264, 'steps': 29396, 'loss/train': 2.22849440574646}
-03/05/2022 00:00:05 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/05/2022 00:00:09 - INFO - codeparrot_training - Step 29397: {'lr': 0.0004589022968348881, 'samples': 15051776, 'steps': 29397, 'loss/train': 1.3926750421524048}
-03/05/2022 00:00:12 - INFO - codeparrot_training - Step 29398: {'lr': 0.0004588993816637199, 'samples': 15052288, 'steps': 29398, 'loss/train': 2.7406697273254395}
-03/05/2022 00:00:14 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 00:00:18 - INFO - codeparrot_training - Step 29399: {'lr': 0.00045889646639842496, 'samples': 15052800, 'steps': 29399, 'loss/train': 0.07882201671600342}
-03/05/2022 00:00:21 - INFO - codeparrot_training - Step 29400: {'lr': 0.0004588935510390045, 'samples': 15053312, 'steps': 29400, 'loss/train': 1.705450177192688}
-03/05/2022 00:00:22 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/05/2022 00:00:26 - INFO - codeparrot_training - Step 29401: {'lr': 0.00045889063558545974, 'samples': 15053824, 'steps': 29401, 'loss/train': 2.498893976211548}
-03/05/2022 00:00:29 - INFO - codeparrot_training - Step 29402: {'lr': 0.0004588877200377921, 'samples': 15054336, 'steps': 29402, 'loss/train': 1.8964338302612305}
-03/05/2022 00:00:30 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/05/2022 00:00:35 - INFO - codeparrot_training - Step 29403: {'lr': 0.000458884804396003, 'samples': 15054848, 'steps': 29403, 'loss/train': 2.4789299964904785}
-03/05/2022 00:00:38 - INFO - codeparrot_training - Step 29404: {'lr': 0.0004588818886600935, 'samples': 15055360, 'steps': 29404, 'loss/train': 2.4294638633728027}
-03/05/2022 00:00:39 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 00:00:43 - INFO - codeparrot_training - Step 29405: {'lr': 0.00045887897283006506, 'samples': 15055872, 'steps': 29405, 'loss/train': 1.401419997215271}
-03/05/2022 00:00:46 - INFO - codeparrot_training - Step 29406: {'lr': 0.00045887605690591904, 'samples': 15056384, 'steps': 29406, 'loss/train': 1.2634106874465942}
-03/05/2022 00:00:48 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/05/2022 00:00:51 - INFO - codeparrot_training - Step 29407: {'lr': 0.0004588731408876566, 'samples': 15056896, 'steps': 29407, 'loss/train': 2.0198323726654053}
-03/05/2022 00:00:55 - INFO - codeparrot_training - Step 29408: {'lr': 0.00045887022477527923, 'samples': 15057408, 'steps': 29408, 'loss/train': 1.6822476387023926}
-03/05/2022 00:00:56 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/05/2022 00:01:00 - INFO - codeparrot_training - Step 29409: {'lr': 0.0004588673085687881, 'samples': 15057920, 'steps': 29409, 'loss/train': 1.9611732959747314}
-03/05/2022 00:01:03 - INFO - codeparrot_training - Step 29410: {'lr': 0.00045886439226818464, 'samples': 15058432, 'steps': 29410, 'loss/train': 1.950826644897461}
-03/05/2022 00:01:04 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/05/2022 00:01:08 - INFO - codeparrot_training - Step 29411: {'lr': 0.0004588614758734701, 'samples': 15058944, 'steps': 29411, 'loss/train': 2.281588315963745}
-03/05/2022 00:01:11 - INFO - codeparrot_training - Step 29412: {'lr': 0.0004588585593846458, 'samples': 15059456, 'steps': 29412, 'loss/train': 1.2941282987594604}
-03/05/2022 00:01:13 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 00:01:17 - INFO - codeparrot_training - Step 29413: {'lr': 0.000458855642801713, 'samples': 15059968, 'steps': 29413, 'loss/train': 1.6963658332824707}
-03/05/2022 00:01:20 - INFO - codeparrot_training - Step 29414: {'lr': 0.00045885272612467313, 'samples': 15060480, 'steps': 29414, 'loss/train': 2.2268877029418945}
-03/05/2022 00:01:21 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/05/2022 00:01:25 - INFO - codeparrot_training - Step 29415: {'lr': 0.0004588498093535274, 'samples': 15060992, 'steps': 29415, 'loss/train': 2.108954906463623}
-03/05/2022 00:01:28 - INFO - codeparrot_training - Step 29416: {'lr': 0.0004588468924882772, 'samples': 15061504, 'steps': 29416, 'loss/train': 1.09861159324646}
-03/05/2022 00:01:29 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/05/2022 00:01:34 - INFO - codeparrot_training - Step 29417: {'lr': 0.0004588439755289238, 'samples': 15062016, 'steps': 29417, 'loss/train': 1.7276639938354492}
-03/05/2022 00:01:37 - INFO - codeparrot_training - Step 29418: {'lr': 0.00045884105847546853, 'samples': 15062528, 'steps': 29418, 'loss/train': 1.8615974187850952}
-03/05/2022 00:01:37 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/05/2022 00:01:42 - INFO - codeparrot_training - Step 29419: {'lr': 0.00045883814132791274, 'samples': 15063040, 'steps': 29419, 'loss/train': 1.5378037691116333}
-03/05/2022 00:01:45 - INFO - codeparrot_training - Step 29420: {'lr': 0.0004588352240862577, 'samples': 15063552, 'steps': 29420, 'loss/train': 1.5039952993392944}
-03/05/2022 00:01:46 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/05/2022 00:01:50 - INFO - codeparrot_training - Step 29421: {'lr': 0.0004588323067505047, 'samples': 15064064, 'steps': 29421, 'loss/train': 1.62093186378479}
-03/05/2022 00:01:53 - INFO - codeparrot_training - Step 29422: {'lr': 0.00045882938932065504, 'samples': 15064576, 'steps': 29422, 'loss/train': 1.1943272352218628}
-03/05/2022 00:01:54 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/05/2022 00:01:59 - INFO - codeparrot_training - Step 29423: {'lr': 0.0004588264717967101, 'samples': 15065088, 'steps': 29423, 'loss/train': 1.4881778955459595}
-03/05/2022 00:02:02 - INFO - codeparrot_training - Step 29424: {'lr': 0.00045882355417867124, 'samples': 15065600, 'steps': 29424, 'loss/train': 1.2962485551834106}
-03/05/2022 00:02:02 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/05/2022 00:02:07 - INFO - codeparrot_training - Step 29425: {'lr': 0.00045882063646653966, 'samples': 15066112, 'steps': 29425, 'loss/train': 1.5608347654342651}
-03/05/2022 00:02:10 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/05/2022 00:02:12 - INFO - codeparrot_training - Step 29426: {'lr': 0.00045881771866031673, 'samples': 15066624, 'steps': 29426, 'loss/train': 1.1243586540222168}
-03/05/2022 00:02:16 - INFO - codeparrot_training - Step 29427: {'lr': 0.00045881480076000376, 'samples': 15067136, 'steps': 29427, 'loss/train': 2.1950507164001465}
-03/05/2022 00:02:18 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/05/2022 00:02:21 - INFO - codeparrot_training - Step 29428: {'lr': 0.00045881188276560204, 'samples': 15067648, 'steps': 29428, 'loss/train': 1.659379243850708}
-03/05/2022 00:02:24 - INFO - codeparrot_training - Step 29429: {'lr': 0.000458808964677113, 'samples': 15068160, 'steps': 29429, 'loss/train': 2.2346880435943604}
-03/05/2022 00:02:26 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 00:02:29 - INFO - codeparrot_training - Step 29430: {'lr': 0.00045880604649453774, 'samples': 15068672, 'steps': 29430, 'loss/train': 1.9851168394088745}
-03/05/2022 00:02:32 - INFO - codeparrot_training - Step 29431: {'lr': 0.00045880312821787775, 'samples': 15069184, 'steps': 29431, 'loss/train': 1.529115080833435}
-03/05/2022 00:02:34 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 00:02:37 - INFO - codeparrot_training - Step 29432: {'lr': 0.00045880020984713434, 'samples': 15069696, 'steps': 29432, 'loss/train': 1.0846222639083862}
-03/05/2022 00:02:41 - INFO - codeparrot_training - Step 29433: {'lr': 0.0004587972913823087, 'samples': 15070208, 'steps': 29433, 'loss/train': 1.2217762470245361}
-03/05/2022 00:02:43 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/05/2022 00:02:46 - INFO - codeparrot_training - Step 29434: {'lr': 0.00045879437282340225, 'samples': 15070720, 'steps': 29434, 'loss/train': 3.139949083328247}
-03/05/2022 00:02:49 - INFO - codeparrot_training - Step 29435: {'lr': 0.00045879145417041623, 'samples': 15071232, 'steps': 29435, 'loss/train': 1.553557276725769}
-03/05/2022 00:02:51 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/05/2022 00:02:54 - INFO - codeparrot_training - Step 29436: {'lr': 0.0004587885354233521, 'samples': 15071744, 'steps': 29436, 'loss/train': 2.011582374572754}
-03/05/2022 00:02:58 - INFO - codeparrot_training - Step 29437: {'lr': 0.0004587856165822111, 'samples': 15072256, 'steps': 29437, 'loss/train': 1.313247799873352}
-03/05/2022 00:02:59 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/05/2022 00:03:03 - INFO - codeparrot_training - Step 29438: {'lr': 0.0004587826976469944, 'samples': 15072768, 'steps': 29438, 'loss/train': 1.4834846258163452}
-03/05/2022 00:03:06 - INFO - codeparrot_training - Step 29439: {'lr': 0.0004587797786177035, 'samples': 15073280, 'steps': 29439, 'loss/train': 1.4459228515625}
-03/05/2022 00:03:08 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/05/2022 00:03:11 - INFO - codeparrot_training - Step 29440: {'lr': 0.0004587768594943396, 'samples': 15073792, 'steps': 29440, 'loss/train': 1.311254620552063}
-03/05/2022 00:03:14 - INFO - codeparrot_training - Step 29441: {'lr': 0.00045877394027690413, 'samples': 15074304, 'steps': 29441, 'loss/train': 2.522144317626953}
-03/05/2022 00:03:16 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 00:03:20 - INFO - codeparrot_training - Step 29442: {'lr': 0.0004587710209653984, 'samples': 15074816, 'steps': 29442, 'loss/train': 1.4157636165618896}
-03/05/2022 00:03:23 - INFO - codeparrot_training - Step 29443: {'lr': 0.0004587681015598235, 'samples': 15075328, 'steps': 29443, 'loss/train': 1.665614366531372}
-03/05/2022 00:03:24 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/05/2022 00:03:28 - INFO - codeparrot_training - Step 29444: {'lr': 0.00045876518206018103, 'samples': 15075840, 'steps': 29444, 'loss/train': 0.6438286304473877}
-03/05/2022 00:03:31 - INFO - codeparrot_training - Step 29445: {'lr': 0.00045876226246647226, 'samples': 15076352, 'steps': 29445, 'loss/train': 1.809487223625183}
-03/05/2022 00:03:33 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 00:03:37 - INFO - codeparrot_training - Step 29446: {'lr': 0.0004587593427786983, 'samples': 15076864, 'steps': 29446, 'loss/train': 1.5561292171478271}
-03/05/2022 00:03:40 - INFO - codeparrot_training - Step 29447: {'lr': 0.0004587564229968606, 'samples': 15077376, 'steps': 29447, 'loss/train': 1.9052890539169312}
-03/05/2022 00:03:41 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/05/2022 00:03:45 - INFO - codeparrot_training - Step 29448: {'lr': 0.00045875350312096053, 'samples': 15077888, 'steps': 29448, 'loss/train': 0.11432677507400513}
-03/05/2022 00:03:48 - INFO - codeparrot_training - Step 29449: {'lr': 0.0004587505831509994, 'samples': 15078400, 'steps': 29449, 'loss/train': 1.7650479078292847}
-03/05/2022 00:03:49 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 00:03:53 - INFO - codeparrot_training - Step 29450: {'lr': 0.0004587476630869784, 'samples': 15078912, 'steps': 29450, 'loss/train': 2.2848503589630127}
-03/05/2022 00:03:57 - INFO - codeparrot_training - Step 29451: {'lr': 0.000458744742928899, 'samples': 15079424, 'steps': 29451, 'loss/train': 0.7896596789360046}
-03/05/2022 00:03:57 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/05/2022 00:04:02 - INFO - codeparrot_training - Step 29452: {'lr': 0.00045874182267676236, 'samples': 15079936, 'steps': 29452, 'loss/train': 1.7087624073028564}
-03/05/2022 00:04:05 - INFO - codeparrot_training - Step 29453: {'lr': 0.0004587389023305699, 'samples': 15080448, 'steps': 29453, 'loss/train': 0.23812542855739594}
-03/05/2022 00:04:06 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/05/2022 00:04:10 - INFO - codeparrot_training - Step 29454: {'lr': 0.00045873598189032295, 'samples': 15080960, 'steps': 29454, 'loss/train': 1.3694045543670654}
-03/05/2022 00:04:13 - INFO - codeparrot_training - Step 29455: {'lr': 0.00045873306135602276, 'samples': 15081472, 'steps': 29455, 'loss/train': 1.7394646406173706}
-03/05/2022 00:04:14 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/05/2022 00:04:19 - INFO - codeparrot_training - Step 29456: {'lr': 0.00045873014072767064, 'samples': 15081984, 'steps': 29456, 'loss/train': 1.5809504985809326}
-03/05/2022 00:04:22 - INFO - codeparrot_training - Step 29457: {'lr': 0.000458727220005268, 'samples': 15082496, 'steps': 29457, 'loss/train': 1.938810110092163}
-03/05/2022 00:04:23 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 00:04:27 - INFO - codeparrot_training - Step 29458: {'lr': 0.00045872429918881606, 'samples': 15083008, 'steps': 29458, 'loss/train': 0.20404241979122162}
-03/05/2022 00:04:30 - INFO - codeparrot_training - Step 29459: {'lr': 0.00045872137827831616, 'samples': 15083520, 'steps': 29459, 'loss/train': 1.9023499488830566}
-03/05/2022 00:04:31 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/05/2022 00:04:36 - INFO - codeparrot_training - Step 29460: {'lr': 0.00045871845727376973, 'samples': 15084032, 'steps': 29460, 'loss/train': 1.2742539644241333}
-03/05/2022 00:04:39 - INFO - codeparrot_training - Step 29461: {'lr': 0.0004587155361751778, 'samples': 15084544, 'steps': 29461, 'loss/train': 1.5251022577285767}
-03/05/2022 00:04:41 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/05/2022 00:04:44 - INFO - codeparrot_training - Step 29462: {'lr': 0.000458712614982542, 'samples': 15085056, 'steps': 29462, 'loss/train': 1.9927170276641846}
-03/05/2022 00:04:47 - INFO - codeparrot_training - Step 29463: {'lr': 0.00045870969369586346, 'samples': 15085568, 'steps': 29463, 'loss/train': 1.6972904205322266}
-03/05/2022 00:04:49 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 00:04:53 - INFO - codeparrot_training - Step 29464: {'lr': 0.00045870677231514356, 'samples': 15086080, 'steps': 29464, 'loss/train': 1.598105549812317}
-03/05/2022 00:04:56 - INFO - codeparrot_training - Step 29465: {'lr': 0.0004587038508403837, 'samples': 15086592, 'steps': 29465, 'loss/train': 1.0332462787628174}
-03/05/2022 00:04:57 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/05/2022 00:05:01 - INFO - codeparrot_training - Step 29466: {'lr': 0.000458700929271585, 'samples': 15087104, 'steps': 29466, 'loss/train': 0.1613921970129013}
-03/05/2022 00:05:05 - INFO - codeparrot_training - Step 29467: {'lr': 0.0004586980076087489, 'samples': 15087616, 'steps': 29467, 'loss/train': 1.0321905612945557}
-03/05/2022 00:05:06 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/05/2022 00:05:10 - INFO - codeparrot_training - Step 29468: {'lr': 0.0004586950858518767, 'samples': 15088128, 'steps': 29468, 'loss/train': 1.592992901802063}
-03/05/2022 00:05:13 - INFO - codeparrot_training - Step 29469: {'lr': 0.0004586921640009697, 'samples': 15088640, 'steps': 29469, 'loss/train': 1.910004734992981}
-03/05/2022 00:05:15 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 00:05:18 - INFO - codeparrot_training - Step 29470: {'lr': 0.0004586892420560294, 'samples': 15089152, 'steps': 29470, 'loss/train': 1.3640133142471313}
-03/05/2022 00:05:21 - INFO - codeparrot_training - Step 29471: {'lr': 0.0004586863200170567, 'samples': 15089664, 'steps': 29471, 'loss/train': 1.0251942873001099}
-03/05/2022 00:05:24 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 00:05:27 - INFO - codeparrot_training - Step 29472: {'lr': 0.00045868339788405333, 'samples': 15090176, 'steps': 29472, 'loss/train': 1.586605429649353}
-03/05/2022 00:05:30 - INFO - codeparrot_training - Step 29473: {'lr': 0.0004586804756570204, 'samples': 15090688, 'steps': 29473, 'loss/train': 1.9300031661987305}
-03/05/2022 00:05:32 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/05/2022 00:05:35 - INFO - codeparrot_training - Step 29474: {'lr': 0.0004586775533359592, 'samples': 15091200, 'steps': 29474, 'loss/train': 2.6338372230529785}
-03/05/2022 00:05:39 - INFO - codeparrot_training - Step 29475: {'lr': 0.00045867463092087116, 'samples': 15091712, 'steps': 29475, 'loss/train': 1.684784173965454}
-03/05/2022 00:05:41 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/05/2022 00:05:44 - INFO - codeparrot_training - Step 29476: {'lr': 0.00045867170841175755, 'samples': 15092224, 'steps': 29476, 'loss/train': 1.5876818895339966}
-03/05/2022 00:05:47 - INFO - codeparrot_training - Step 29477: {'lr': 0.0004586687858086197, 'samples': 15092736, 'steps': 29477, 'loss/train': 1.8086566925048828}
-03/05/2022 00:05:49 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/05/2022 00:05:52 - INFO - codeparrot_training - Step 29478: {'lr': 0.0004586658631114589, 'samples': 15093248, 'steps': 29478, 'loss/train': 2.555069923400879}
-03/05/2022 00:05:55 - INFO - codeparrot_training - Step 29479: {'lr': 0.0004586629403202765, 'samples': 15093760, 'steps': 29479, 'loss/train': 1.3479344844818115}
-03/05/2022 00:05:58 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/05/2022 00:06:01 - INFO - codeparrot_training - Step 29480: {'lr': 0.0004586600174350738, 'samples': 15094272, 'steps': 29480, 'loss/train': 1.6688258647918701}
-03/05/2022 00:06:04 - INFO - codeparrot_training - Step 29481: {'lr': 0.0004586570944558521, 'samples': 15094784, 'steps': 29481, 'loss/train': 2.1818978786468506}
-03/05/2022 00:06:06 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/05/2022 00:06:09 - INFO - codeparrot_training - Step 29482: {'lr': 0.00045865417138261276, 'samples': 15095296, 'steps': 29482, 'loss/train': 2.1142513751983643}
-03/05/2022 00:06:12 - INFO - codeparrot_training - Step 29483: {'lr': 0.00045865124821535704, 'samples': 15095808, 'steps': 29483, 'loss/train': 2.4780969619750977}
-03/05/2022 00:06:14 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/05/2022 00:06:18 - INFO - codeparrot_training - Step 29484: {'lr': 0.00045864832495408624, 'samples': 15096320, 'steps': 29484, 'loss/train': 2.1094555854797363}
-03/05/2022 00:06:21 - INFO - codeparrot_training - Step 29485: {'lr': 0.0004586454015988019, 'samples': 15096832, 'steps': 29485, 'loss/train': 1.250625491142273}
-03/05/2022 00:06:22 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 00:06:26 - INFO - codeparrot_training - Step 29486: {'lr': 0.000458642478149505, 'samples': 15097344, 'steps': 29486, 'loss/train': 1.978638768196106}
-03/05/2022 00:06:29 - INFO - codeparrot_training - Step 29487: {'lr': 0.00045863955460619707, 'samples': 15097856, 'steps': 29487, 'loss/train': 1.8101561069488525}
-03/05/2022 00:06:31 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/05/2022 00:06:34 - INFO - codeparrot_training - Step 29488: {'lr': 0.0004586366309688793, 'samples': 15098368, 'steps': 29488, 'loss/train': 0.8289637565612793}
-03/05/2022 00:06:38 - INFO - codeparrot_training - Step 29489: {'lr': 0.00045863370723755315, 'samples': 15098880, 'steps': 29489, 'loss/train': 1.0590749979019165}
-03/05/2022 00:06:39 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/05/2022 00:06:43 - INFO - codeparrot_training - Step 29490: {'lr': 0.00045863078341221993, 'samples': 15099392, 'steps': 29490, 'loss/train': 0.19803790748119354}
-03/05/2022 00:06:46 - INFO - codeparrot_training - Step 29491: {'lr': 0.0004586278594928808, 'samples': 15099904, 'steps': 29491, 'loss/train': 1.5104310512542725}
-03/05/2022 00:06:48 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 00:06:51 - INFO - codeparrot_training - Step 29492: {'lr': 0.0004586249354795372, 'samples': 15100416, 'steps': 29492, 'loss/train': 1.437464714050293}
-03/05/2022 00:06:54 - INFO - codeparrot_training - Step 29493: {'lr': 0.0004586220113721905, 'samples': 15100928, 'steps': 29493, 'loss/train': 2.1306979656219482}
-03/05/2022 00:06:56 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 00:07:00 - INFO - codeparrot_training - Step 29494: {'lr': 0.0004586190871708419, 'samples': 15101440, 'steps': 29494, 'loss/train': 1.0925543308258057}
-03/05/2022 00:07:03 - INFO - codeparrot_training - Step 29495: {'lr': 0.0004586161628754927, 'samples': 15101952, 'steps': 29495, 'loss/train': 1.2560229301452637}
-03/05/2022 00:07:04 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/05/2022 00:07:08 - INFO - codeparrot_training - Step 29496: {'lr': 0.0004586132384861443, 'samples': 15102464, 'steps': 29496, 'loss/train': 1.743109941482544}
-03/05/2022 00:07:11 - INFO - codeparrot_training - Step 29497: {'lr': 0.000458610314002798, 'samples': 15102976, 'steps': 29497, 'loss/train': 2.0666310787200928}
-03/05/2022 00:07:12 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/05/2022 00:07:16 - INFO - codeparrot_training - Step 29498: {'lr': 0.0004586073894254551, 'samples': 15103488, 'steps': 29498, 'loss/train': 1.0570305585861206}
-03/05/2022 00:07:20 - INFO - codeparrot_training - Step 29499: {'lr': 0.000458604464754117, 'samples': 15104000, 'steps': 29499, 'loss/train': 1.6065893173217773}
-03/05/2022 00:07:21 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/05/2022 00:07:25 - INFO - codeparrot_training - Step 29500: {'lr': 0.0004586015399887849, 'samples': 15104512, 'steps': 29500, 'loss/train': 1.0707597732543945}
-03/05/2022 00:07:28 - INFO - codeparrot_training - Step 29501: {'lr': 0.0004585986151294602, 'samples': 15105024, 'steps': 29501, 'loss/train': 1.6413307189941406}
-03/05/2022 00:07:29 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/05/2022 00:07:33 - INFO - codeparrot_training - Step 29502: {'lr': 0.0004585956901761441, 'samples': 15105536, 'steps': 29502, 'loss/train': 1.4918277263641357}
-03/05/2022 00:07:36 - INFO - codeparrot_training - Step 29503: {'lr': 0.00045859276512883807, 'samples': 15106048, 'steps': 29503, 'loss/train': 0.06658778339624405}
-03/05/2022 00:07:37 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/05/2022 00:07:42 - INFO - codeparrot_training - Step 29504: {'lr': 0.00045858983998754336, 'samples': 15106560, 'steps': 29504, 'loss/train': 1.9468345642089844}
-03/05/2022 00:07:45 - INFO - codeparrot_training - Step 29505: {'lr': 0.0004585869147522612, 'samples': 15107072, 'steps': 29505, 'loss/train': 1.9459869861602783}
-03/05/2022 00:07:46 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/05/2022 00:07:50 - INFO - codeparrot_training - Step 29506: {'lr': 0.00045858398942299306, 'samples': 15107584, 'steps': 29506, 'loss/train': 1.6417884826660156}
-03/05/2022 00:07:53 - INFO - codeparrot_training - Step 29507: {'lr': 0.0004585810639997402, 'samples': 15108096, 'steps': 29507, 'loss/train': 0.7079473733901978}
-03/05/2022 00:07:54 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/05/2022 00:07:59 - INFO - codeparrot_training - Step 29508: {'lr': 0.0004585781384825039, 'samples': 15108608, 'steps': 29508, 'loss/train': 2.4221251010894775}
-03/05/2022 00:08:02 - INFO - codeparrot_training - Step 29509: {'lr': 0.00045857521287128556, 'samples': 15109120, 'steps': 29509, 'loss/train': 1.5184063911437988}
-03/05/2022 00:08:02 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/05/2022 00:08:07 - INFO - codeparrot_training - Step 29510: {'lr': 0.0004585722871660864, 'samples': 15109632, 'steps': 29510, 'loss/train': 1.5314116477966309}
-03/05/2022 00:08:10 - INFO - codeparrot_training - Step 29511: {'lr': 0.0004585693613669078, 'samples': 15110144, 'steps': 29511, 'loss/train': 1.9491839408874512}
-03/05/2022 00:08:11 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/05/2022 00:08:15 - INFO - codeparrot_training - Step 29512: {'lr': 0.0004585664354737511, 'samples': 15110656, 'steps': 29512, 'loss/train': 1.3117051124572754}
-03/05/2022 00:08:19 - INFO - codeparrot_training - Step 29513: {'lr': 0.0004585635094866175, 'samples': 15111168, 'steps': 29513, 'loss/train': 1.8874579668045044}
-03/05/2022 00:08:19 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 00:08:24 - INFO - codeparrot_training - Step 29514: {'lr': 0.0004585605834055084, 'samples': 15111680, 'steps': 29514, 'loss/train': 1.1464364528656006}
-03/05/2022 00:08:27 - INFO - codeparrot_training - Step 29515: {'lr': 0.00045855765723042526, 'samples': 15112192, 'steps': 29515, 'loss/train': 2.029849052429199}
-03/05/2022 00:08:28 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/05/2022 00:08:32 - INFO - codeparrot_training - Step 29516: {'lr': 0.00045855473096136914, 'samples': 15112704, 'steps': 29516, 'loss/train': 0.6989114284515381}
-03/05/2022 00:08:35 - INFO - codeparrot_training - Step 29517: {'lr': 0.00045855180459834153, 'samples': 15113216, 'steps': 29517, 'loss/train': 1.8639788627624512}
-03/05/2022 00:08:36 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/05/2022 00:08:41 - INFO - codeparrot_training - Step 29518: {'lr': 0.0004585488781413437, 'samples': 15113728, 'steps': 29518, 'loss/train': 1.591664433479309}
-03/05/2022 00:08:44 - INFO - codeparrot_training - Step 29519: {'lr': 0.00045854595159037695, 'samples': 15114240, 'steps': 29519, 'loss/train': 1.4009218215942383}
-03/05/2022 00:08:44 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/05/2022 00:08:49 - INFO - codeparrot_training - Step 29520: {'lr': 0.0004585430249454425, 'samples': 15114752, 'steps': 29520, 'loss/train': 1.8163731098175049}
-03/05/2022 00:08:52 - INFO - codeparrot_training - Step 29521: {'lr': 0.000458540098206542, 'samples': 15115264, 'steps': 29521, 'loss/train': 1.7235661745071411}
-03/05/2022 00:08:53 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/05/2022 00:08:58 - INFO - codeparrot_training - Step 29522: {'lr': 0.00045853717137367634, 'samples': 15115776, 'steps': 29522, 'loss/train': 1.4032801389694214}
-03/05/2022 00:09:01 - INFO - codeparrot_training - Step 29523: {'lr': 0.0004585342444468471, 'samples': 15116288, 'steps': 29523, 'loss/train': 1.9199674129486084}
-03/05/2022 00:09:01 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 00:09:06 - INFO - codeparrot_training - Step 29524: {'lr': 0.00045853131742605563, 'samples': 15116800, 'steps': 29524, 'loss/train': 0.11558540165424347}
-03/05/2022 00:09:09 - INFO - codeparrot_training - Step 29525: {'lr': 0.0004585283903113031, 'samples': 15117312, 'steps': 29525, 'loss/train': 2.0342044830322266}
-03/05/2022 00:09:14 - INFO - codeparrot_training - Step 29526: {'lr': 0.00045852546310259093, 'samples': 15117824, 'steps': 29526, 'loss/train': 1.684152364730835}
-03/05/2022 00:09:18 - INFO - codeparrot_training - Step 29527: {'lr': 0.00045852253579992043, 'samples': 15118336, 'steps': 29527, 'loss/train': 0.712755024433136}
-03/05/2022 00:09:18 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/05/2022 00:09:23 - INFO - codeparrot_training - Step 29528: {'lr': 0.0004585196084032928, 'samples': 15118848, 'steps': 29528, 'loss/train': 2.1710665225982666}
-03/05/2022 00:09:26 - INFO - codeparrot_training - Step 29529: {'lr': 0.0004585166809127095, 'samples': 15119360, 'steps': 29529, 'loss/train': 1.670620322227478}
-03/05/2022 00:09:26 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/05/2022 00:09:31 - INFO - codeparrot_training - Step 29530: {'lr': 0.0004585137533281718, 'samples': 15119872, 'steps': 29530, 'loss/train': 0.8960245251655579}
-03/05/2022 00:09:34 - INFO - codeparrot_training - Step 29531: {'lr': 0.00045851082564968103, 'samples': 15120384, 'steps': 29531, 'loss/train': 1.4882266521453857}
-03/05/2022 00:09:34 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/05/2022 00:09:40 - INFO - codeparrot_training - Step 29532: {'lr': 0.0004585078978772385, 'samples': 15120896, 'steps': 29532, 'loss/train': 1.1559669971466064}
-03/05/2022 00:09:43 - INFO - codeparrot_training - Step 29533: {'lr': 0.0004585049700108455, 'samples': 15121408, 'steps': 29533, 'loss/train': 2.140377998352051}
-03/05/2022 00:09:43 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/05/2022 00:09:48 - INFO - codeparrot_training - Step 29534: {'lr': 0.00045850204205050344, 'samples': 15121920, 'steps': 29534, 'loss/train': 2.095122814178467}
-03/05/2022 00:09:51 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/05/2022 00:09:54 - INFO - codeparrot_training - Step 29535: {'lr': 0.0004584991139962135, 'samples': 15122432, 'steps': 29535, 'loss/train': 1.1537307500839233}
-03/05/2022 00:09:57 - INFO - codeparrot_training - Step 29536: {'lr': 0.00045849618584797717, 'samples': 15122944, 'steps': 29536, 'loss/train': 1.6044560670852661}
-03/05/2022 00:10:00 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/05/2022 00:10:02 - INFO - codeparrot_training - Step 29537: {'lr': 0.0004584932576057956, 'samples': 15123456, 'steps': 29537, 'loss/train': 2.026948928833008}
-03/05/2022 00:10:05 - INFO - codeparrot_training - Step 29538: {'lr': 0.00045849032926967016, 'samples': 15123968, 'steps': 29538, 'loss/train': 1.543022871017456}
-03/05/2022 00:10:08 - INFO - codeparrot_training - Step 29539: {'lr': 0.0004584874008396023, 'samples': 15124480, 'steps': 29539, 'loss/train': 0.10876262187957764}
-03/05/2022 00:10:08 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/05/2022 00:10:14 - INFO - codeparrot_training - Step 29540: {'lr': 0.00045848447231559315, 'samples': 15124992, 'steps': 29540, 'loss/train': 4.418543815612793}
-03/05/2022 00:10:17 - INFO - codeparrot_training - Step 29541: {'lr': 0.00045848154369764415, 'samples': 15125504, 'steps': 29541, 'loss/train': 1.3366106748580933}
-03/05/2022 00:10:17 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/05/2022 00:10:22 - INFO - codeparrot_training - Step 29542: {'lr': 0.0004584786149857566, 'samples': 15126016, 'steps': 29542, 'loss/train': 2.273329734802246}
-03/05/2022 00:10:25 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/05/2022 00:10:27 - INFO - codeparrot_training - Step 29543: {'lr': 0.00045847568617993174, 'samples': 15126528, 'steps': 29543, 'loss/train': 0.7684382796287537}
-03/05/2022 00:10:31 - INFO - codeparrot_training - Step 29544: {'lr': 0.000458472757280171, 'samples': 15127040, 'steps': 29544, 'loss/train': 2.2687673568725586}
-03/05/2022 00:10:33 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 00:10:36 - INFO - codeparrot_training - Step 29545: {'lr': 0.0004584698282864757, 'samples': 15127552, 'steps': 29545, 'loss/train': 1.3599854707717896}
-03/05/2022 00:10:39 - INFO - codeparrot_training - Step 29546: {'lr': 0.000458466899198847, 'samples': 15128064, 'steps': 29546, 'loss/train': 1.8748090267181396}
-03/05/2022 00:10:43 - INFO - codeparrot_training - Step 29547: {'lr': 0.0004584639700172863, 'samples': 15128576, 'steps': 29547, 'loss/train': 2.043598175048828}
-03/05/2022 00:10:44 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/05/2022 00:10:48 - INFO - codeparrot_training - Step 29548: {'lr': 0.00045846104074179504, 'samples': 15129088, 'steps': 29548, 'loss/train': 2.306469678878784}
-03/05/2022 00:10:51 - INFO - codeparrot_training - Step 29549: {'lr': 0.00045845811137237445, 'samples': 15129600, 'steps': 29549, 'loss/train': 0.9882426261901855}
-03/05/2022 00:10:52 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/05/2022 00:10:56 - INFO - codeparrot_training - Step 29550: {'lr': 0.0004584551819090259, 'samples': 15130112, 'steps': 29550, 'loss/train': 1.8231916427612305}
-03/05/2022 00:10:59 - INFO - codeparrot_training - Step 29551: {'lr': 0.0004584522523517506, 'samples': 15130624, 'steps': 29551, 'loss/train': 1.5368438959121704}
-03/05/2022 00:11:00 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/05/2022 00:11:04 - INFO - codeparrot_training - Step 29552: {'lr': 0.00045844932270054997, 'samples': 15131136, 'steps': 29552, 'loss/train': 1.6573116779327393}
-03/05/2022 00:11:08 - INFO - codeparrot_training - Step 29553: {'lr': 0.00045844639295542525, 'samples': 15131648, 'steps': 29553, 'loss/train': 1.160616159439087}
-03/05/2022 00:11:09 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/05/2022 00:11:13 - INFO - codeparrot_training - Step 29554: {'lr': 0.0004584434631163779, 'samples': 15132160, 'steps': 29554, 'loss/train': 1.9815462827682495}
-03/05/2022 00:11:16 - INFO - codeparrot_training - Step 29555: {'lr': 0.000458440533183409, 'samples': 15132672, 'steps': 29555, 'loss/train': 2.0560553073883057}
-03/05/2022 00:11:17 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/05/2022 00:11:22 - INFO - codeparrot_training - Step 29556: {'lr': 0.0004584376031565201, 'samples': 15133184, 'steps': 29556, 'loss/train': 1.6338471174240112}
-03/05/2022 00:11:25 - INFO - codeparrot_training - Step 29557: {'lr': 0.0004584346730357124, 'samples': 15133696, 'steps': 29557, 'loss/train': 0.8693658709526062}
-03/05/2022 00:11:26 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/05/2022 00:11:30 - INFO - codeparrot_training - Step 29558: {'lr': 0.0004584317428209872, 'samples': 15134208, 'steps': 29558, 'loss/train': 1.6076276302337646}
-03/05/2022 00:11:33 - INFO - codeparrot_training - Step 29559: {'lr': 0.0004584288125123459, 'samples': 15134720, 'steps': 29559, 'loss/train': 1.7829666137695312}
-03/05/2022 00:11:34 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/05/2022 00:11:38 - INFO - codeparrot_training - Step 29560: {'lr': 0.0004584258821097899, 'samples': 15135232, 'steps': 29560, 'loss/train': 1.1429840326309204}
-03/05/2022 00:11:42 - INFO - codeparrot_training - Step 29561: {'lr': 0.0004584229516133203, 'samples': 15135744, 'steps': 29561, 'loss/train': 1.9897711277008057}
-03/05/2022 00:11:43 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/05/2022 00:11:47 - INFO - codeparrot_training - Step 29562: {'lr': 0.00045842002102293856, 'samples': 15136256, 'steps': 29562, 'loss/train': 0.9868795871734619}
-03/05/2022 00:11:50 - INFO - codeparrot_training - Step 29563: {'lr': 0.000458417090338646, 'samples': 15136768, 'steps': 29563, 'loss/train': 2.8524515628814697}
-03/05/2022 00:11:51 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/05/2022 00:11:55 - INFO - codeparrot_training - Step 29564: {'lr': 0.00045841415956044394, 'samples': 15137280, 'steps': 29564, 'loss/train': 1.781243085861206}
-03/05/2022 00:11:59 - INFO - codeparrot_training - Step 29565: {'lr': 0.0004584112286883336, 'samples': 15137792, 'steps': 29565, 'loss/train': 1.0656503438949585}
-03/05/2022 00:11:59 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/05/2022 00:12:04 - INFO - codeparrot_training - Step 29566: {'lr': 0.0004584082977223164, 'samples': 15138304, 'steps': 29566, 'loss/train': 1.3876230716705322}
-03/05/2022 00:12:07 - INFO - codeparrot_training - Step 29567: {'lr': 0.0004584053666623937, 'samples': 15138816, 'steps': 29567, 'loss/train': 1.4978874921798706}
-03/05/2022 00:12:08 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 00:12:12 - INFO - codeparrot_training - Step 29568: {'lr': 0.00045840243550856666, 'samples': 15139328, 'steps': 29568, 'loss/train': 1.9485430717468262}
-03/05/2022 00:12:15 - INFO - codeparrot_training - Step 29569: {'lr': 0.00045839950426083677, 'samples': 15139840, 'steps': 29569, 'loss/train': 2.9539616107940674}
-03/05/2022 00:12:16 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 00:12:21 - INFO - codeparrot_training - Step 29570: {'lr': 0.0004583965729192052, 'samples': 15140352, 'steps': 29570, 'loss/train': 1.068267822265625}
-03/05/2022 00:12:24 - INFO - codeparrot_training - Step 29571: {'lr': 0.00045839364148367345, 'samples': 15140864, 'steps': 29571, 'loss/train': 1.5929888486862183}
-03/05/2022 00:12:25 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/05/2022 00:12:29 - INFO - codeparrot_training - Step 29572: {'lr': 0.00045839070995424273, 'samples': 15141376, 'steps': 29572, 'loss/train': 0.6068469285964966}
-03/05/2022 00:12:32 - INFO - codeparrot_training - Step 29573: {'lr': 0.00045838777833091425, 'samples': 15141888, 'steps': 29573, 'loss/train': 2.285215377807617}
-03/05/2022 00:12:33 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/05/2022 00:12:37 - INFO - codeparrot_training - Step 29574: {'lr': 0.00045838484661368963, 'samples': 15142400, 'steps': 29574, 'loss/train': 1.169742465019226}
-03/05/2022 00:12:41 - INFO - codeparrot_training - Step 29575: {'lr': 0.00045838191480256985, 'samples': 15142912, 'steps': 29575, 'loss/train': 2.101759910583496}
-03/05/2022 00:12:42 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 00:12:46 - INFO - codeparrot_training - Step 29576: {'lr': 0.00045837898289755654, 'samples': 15143424, 'steps': 29576, 'loss/train': 1.7290599346160889}
-03/05/2022 00:12:49 - INFO - codeparrot_training - Step 29577: {'lr': 0.0004583760508986508, 'samples': 15143936, 'steps': 29577, 'loss/train': 2.44104266166687}
-03/05/2022 00:12:50 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/05/2022 00:12:54 - INFO - codeparrot_training - Step 29578: {'lr': 0.000458373118805854, 'samples': 15144448, 'steps': 29578, 'loss/train': 2.2922070026397705}
-03/05/2022 00:12:58 - INFO - codeparrot_training - Step 29579: {'lr': 0.00045837018661916754, 'samples': 15144960, 'steps': 29579, 'loss/train': 2.013897657394409}
-03/05/2022 00:12:58 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/05/2022 00:13:03 - INFO - codeparrot_training - Step 29580: {'lr': 0.00045836725433859266, 'samples': 15145472, 'steps': 29580, 'loss/train': 0.7683368921279907}
-03/05/2022 00:13:06 - INFO - codeparrot_training - Step 29581: {'lr': 0.0004583643219641307, 'samples': 15145984, 'steps': 29581, 'loss/train': 1.45555579662323}
-03/05/2022 00:13:06 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/05/2022 00:13:12 - INFO - codeparrot_training - Step 29582: {'lr': 0.00045836138949578297, 'samples': 15146496, 'steps': 29582, 'loss/train': 1.0350154638290405}
-03/05/2022 00:13:15 - INFO - codeparrot_training - Step 29583: {'lr': 0.00045835845693355096, 'samples': 15147008, 'steps': 29583, 'loss/train': 1.3677806854248047}
-03/05/2022 00:13:16 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/05/2022 00:13:20 - INFO - codeparrot_training - Step 29584: {'lr': 0.00045835552427743567, 'samples': 15147520, 'steps': 29584, 'loss/train': 1.9622410535812378}
-03/05/2022 00:13:23 - INFO - codeparrot_training - Step 29585: {'lr': 0.00045835259152743866, 'samples': 15148032, 'steps': 29585, 'loss/train': 0.5172232389450073}
-03/05/2022 00:13:25 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/05/2022 00:13:28 - INFO - codeparrot_training - Step 29586: {'lr': 0.0004583496586835612, 'samples': 15148544, 'steps': 29586, 'loss/train': 1.5638020038604736}
-03/05/2022 00:13:32 - INFO - codeparrot_training - Step 29587: {'lr': 0.0004583467257458046, 'samples': 15149056, 'steps': 29587, 'loss/train': 2.2973859310150146}
-03/05/2022 00:13:33 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/05/2022 00:13:37 - INFO - codeparrot_training - Step 29588: {'lr': 0.00045834379271417013, 'samples': 15149568, 'steps': 29588, 'loss/train': 1.674185872077942}
-03/05/2022 00:13:40 - INFO - codeparrot_training - Step 29589: {'lr': 0.0004583408595886592, 'samples': 15150080, 'steps': 29589, 'loss/train': 2.2917025089263916}
-03/05/2022 00:13:42 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/05/2022 00:13:45 - INFO - codeparrot_training - Step 29590: {'lr': 0.0004583379263692732, 'samples': 15150592, 'steps': 29590, 'loss/train': 1.8480969667434692}
-03/05/2022 00:13:48 - INFO - codeparrot_training - Step 29591: {'lr': 0.0004583349930560132, 'samples': 15151104, 'steps': 29591, 'loss/train': 1.8870465755462646}
-03/05/2022 00:13:50 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/05/2022 00:13:54 - INFO - codeparrot_training - Step 29592: {'lr': 0.0004583320596488807, 'samples': 15151616, 'steps': 29592, 'loss/train': 1.9500160217285156}
-03/05/2022 00:13:57 - INFO - codeparrot_training - Step 29593: {'lr': 0.000458329126147877, 'samples': 15152128, 'steps': 29593, 'loss/train': 1.9467270374298096}
-03/05/2022 00:14:00 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/05/2022 00:14:03 - INFO - codeparrot_training - Step 29594: {'lr': 0.00045832619255300344, 'samples': 15152640, 'steps': 29594, 'loss/train': 0.7993493676185608}
-03/05/2022 00:14:06 - INFO - codeparrot_training - Step 29595: {'lr': 0.00045832325886426125, 'samples': 15153152, 'steps': 29595, 'loss/train': 1.691361427307129}
-03/05/2022 00:14:08 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/05/2022 00:14:11 - INFO - codeparrot_training - Step 29596: {'lr': 0.0004583203250816518, 'samples': 15153664, 'steps': 29596, 'loss/train': 2.2305729389190674}
-03/05/2022 00:14:14 - INFO - codeparrot_training - Step 29597: {'lr': 0.0004583173912051765, 'samples': 15154176, 'steps': 29597, 'loss/train': 2.181438684463501}
-03/05/2022 00:14:16 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/05/2022 00:14:19 - INFO - codeparrot_training - Step 29598: {'lr': 0.00045831445723483656, 'samples': 15154688, 'steps': 29598, 'loss/train': 1.5685683488845825}
-03/05/2022 00:14:23 - INFO - codeparrot_training - Step 29599: {'lr': 0.0004583115231706334, 'samples': 15155200, 'steps': 29599, 'loss/train': 1.7535970211029053}
-03/05/2022 00:14:25 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/05/2022 00:14:28 - INFO - codeparrot_training - Step 29600: {'lr': 0.0004583085890125682, 'samples': 15155712, 'steps': 29600, 'loss/train': 2.4371070861816406}
-03/05/2022 00:14:31 - INFO - codeparrot_training - Step 29601: {'lr': 0.0004583056547606424, 'samples': 15156224, 'steps': 29601, 'loss/train': 1.4144538640975952}
-03/05/2022 00:14:33 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/05/2022 00:14:36 - INFO - codeparrot_training - Step 29602: {'lr': 0.0004583027204148573, 'samples': 15156736, 'steps': 29602, 'loss/train': 1.7700753211975098}
-03/05/2022 00:14:40 - INFO - codeparrot_training - Step 29603: {'lr': 0.0004582997859752142, 'samples': 15157248, 'steps': 29603, 'loss/train': 2.3405330181121826}
-03/05/2022 00:14:41 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/05/2022 00:14:45 - INFO - codeparrot_training - Step 29604: {'lr': 0.0004582968514417144, 'samples': 15157760, 'steps': 29604, 'loss/train': 1.399165391921997}
-03/05/2022 00:14:48 - INFO - codeparrot_training - Step 29605: {'lr': 0.00045829391681435926, 'samples': 15158272, 'steps': 29605, 'loss/train': 0.10402455180883408}
-03/05/2022 00:14:50 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/05/2022 00:14:53 - INFO - codeparrot_training - Step 29606: {'lr': 0.0004582909820931501, 'samples': 15158784, 'steps': 29606, 'loss/train': 2.2843778133392334}
-03/05/2022 00:14:56 - INFO - codeparrot_training - Step 29607: {'lr': 0.00045828804727808824, 'samples': 15159296, 'steps': 29607, 'loss/train': 1.6677777767181396}
-03/05/2022 00:14:58 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/05/2022 00:15:02 - INFO - codeparrot_training - Step 29608: {'lr': 0.000458285112369175, 'samples': 15159808, 'steps': 29608, 'loss/train': 1.1638938188552856}
-03/05/2022 00:15:05 - INFO - codeparrot_training - Step 29609: {'lr': 0.0004582821773664118, 'samples': 15160320, 'steps': 29609, 'loss/train': 1.8593134880065918}
-03/05/2022 00:15:06 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/05/2022 00:15:10 - INFO - codeparrot_training - Step 29610: {'lr': 0.0004582792422697997, 'samples': 15160832, 'steps': 29610, 'loss/train': 1.438664197921753}
-03/05/2022 00:15:13 - INFO - codeparrot_training - Step 29611: {'lr': 0.0004582763070793403, 'samples': 15161344, 'steps': 29611, 'loss/train': 1.5748016834259033}
-03/05/2022 00:15:15 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/05/2022 00:15:18 - INFO - codeparrot_training - Step 29612: {'lr': 0.0004582733717950347, 'samples': 15161856, 'steps': 29612, 'loss/train': 1.8385947942733765}
-03/05/2022 00:15:22 - INFO - codeparrot_training - Step 29613: {'lr': 0.00045827043641688444, 'samples': 15162368, 'steps': 29613, 'loss/train': 2.0978434085845947}
-03/05/2022 00:15:23 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/05/2022 00:15:27 - INFO - codeparrot_training - Step 29614: {'lr': 0.00045826750094489065, 'samples': 15162880, 'steps': 29614, 'loss/train': 1.619504451751709}
-03/05/2022 00:15:30 - INFO - codeparrot_training - Step 29615: {'lr': 0.00045826456537905483, 'samples': 15163392, 'steps': 29615, 'loss/train': 1.7345117330551147}
-03/05/2022 00:15:31 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/05/2022 00:15:35 - INFO - codeparrot_training - Step 29616: {'lr': 0.0004582616297193781, 'samples': 15163904, 'steps': 29616, 'loss/train': 2.030402183532715}
-03/05/2022 00:15:39 - INFO - codeparrot_training - Step 29617: {'lr': 0.000458258693965862, 'samples': 15164416, 'steps': 29617, 'loss/train': 2.590390920639038}
-03/05/2022 00:15:40 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/05/2022 00:15:44 - INFO - codeparrot_training - Step 29618: {'lr': 0.0004582557581185077, 'samples': 15164928, 'steps': 29618, 'loss/train': 1.591430425643921}
-03/05/2022 00:15:47 - INFO - codeparrot_training - Step 29619: {'lr': 0.00045825282217731655, 'samples': 15165440, 'steps': 29619, 'loss/train': 2.272411346435547}
-03/05/2022 00:15:48 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/05/2022 00:15:52 - INFO - codeparrot_training - Step 29620: {'lr': 0.00045824988614228995, 'samples': 15165952, 'steps': 29620, 'loss/train': 1.7040380239486694}
-03/05/2022 00:15:55 - INFO - codeparrot_training - Step 29621: {'lr': 0.0004582469500134292, 'samples': 15166464, 'steps': 29621, 'loss/train': 1.5744106769561768}
-03/05/2022 00:15:56 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/05/2022 00:16:01 - INFO - codeparrot_training - Step 29622: {'lr': 0.00045824401379073544, 'samples': 15166976, 'steps': 29622, 'loss/train': 1.8472628593444824}
-03/05/2022 00:16:04 - INFO - codeparrot_training - Step 29623: {'lr': 0.0004582410774742103, 'samples': 15167488, 'steps': 29623, 'loss/train': 1.8156287670135498}
-03/05/2022 00:16:04 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/05/2022 00:16:09 - INFO - codeparrot_training - Step 29624: {'lr': 0.00045823814106385485, 'samples': 15168000, 'steps': 29624, 'loss/train': 1.7630374431610107}
-03/05/2022 00:16:12 - INFO - codeparrot_training - Step 29625: {'lr': 0.0004582352045596705, 'samples': 15168512, 'steps': 29625, 'loss/train': 2.4423153400421143}
-03/05/2022 00:16:13 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/05/2022 00:16:18 - INFO - codeparrot_training - Step 29626: {'lr': 0.0004582322679616586, 'samples': 15169024, 'steps': 29626, 'loss/train': 1.4555785655975342}
-03/05/2022 00:16:21 - INFO - codeparrot_training - Step 29627: {'lr': 0.0004582293312698205, 'samples': 15169536, 'steps': 29627, 'loss/train': 1.271009922027588}
-03/05/2022 00:16:22 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/05/2022 00:16:26 - INFO - codeparrot_training - Step 29628: {'lr': 0.00045822639448415736, 'samples': 15170048, 'steps': 29628, 'loss/train': 1.444993495941162}
-03/05/2022 00:16:30 - INFO - codeparrot_training - Step 29629: {'lr': 0.0004582234576046707, 'samples': 15170560, 'steps': 29629, 'loss/train': 1.9633160829544067}
-03/05/2022 00:16:31 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/05/2022 00:16:35 - INFO - codeparrot_training - Step 29630: {'lr': 0.00045822052063136177, 'samples': 15171072, 'steps': 29630, 'loss/train': 2.0363192558288574}
-03/05/2022 00:16:38 - INFO - codeparrot_training - Step 29631: {'lr': 0.0004582175835642319, 'samples': 15171584, 'steps': 29631, 'loss/train': 2.1065759658813477}
-03/05/2022 00:16:39 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/05/2022 00:16:43 - INFO - codeparrot_training - Step 29632: {'lr': 0.0004582146464032824, 'samples': 15172096, 'steps': 29632, 'loss/train': 1.8479074239730835}
-03/05/2022 00:16:46 - INFO - codeparrot_training - Step 29633: {'lr': 0.0004582117091485145, 'samples': 15172608, 'steps': 29633, 'loss/train': 0.0593196377158165}
-03/05/2022 00:16:48 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/05/2022 00:16:52 - INFO - codeparrot_training - Step 29634: {'lr': 0.0004582087717999297, 'samples': 15173120, 'steps': 29634, 'loss/train': 1.6204078197479248}
-03/05/2022 00:16:55 - INFO - codeparrot_training - Step 29635: {'lr': 0.0004582058343575292, 'samples': 15173632, 'steps': 29635, 'loss/train': 2.0541532039642334}
-03/05/2022 00:16:56 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/05/2022 00:17:00 - INFO - codeparrot_training - Step 29636: {'lr': 0.00045820289682131437, 'samples': 15174144, 'steps': 29636, 'loss/train': 0.6851502060890198}
-03/05/2022 00:17:03 - INFO - codeparrot_training - Step 29637: {'lr': 0.0004581999591912865, 'samples': 15174656, 'steps': 29637, 'loss/train': 1.3127148151397705}
-03/05/2022 00:17:05 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 00:17:09 - INFO - codeparrot_training - Step 29638: {'lr': 0.000458197021467447, 'samples': 15175168, 'steps': 29638, 'loss/train': 1.9174312353134155}
-03/05/2022 00:17:12 - INFO - codeparrot_training - Step 29639: {'lr': 0.00045819408364979714, 'samples': 15175680, 'steps': 29639, 'loss/train': 0.9182990193367004}
-03/05/2022 00:17:13 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 00:17:17 - INFO - codeparrot_training - Step 29640: {'lr': 0.0004581911457383382, 'samples': 15176192, 'steps': 29640, 'loss/train': 1.9126458168029785}
-03/05/2022 00:17:21 - INFO - codeparrot_training - Step 29641: {'lr': 0.0004581882077330716, 'samples': 15176704, 'steps': 29641, 'loss/train': 1.6636160612106323}
-03/05/2022 00:17:23 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/05/2022 00:17:26 - INFO - codeparrot_training - Step 29642: {'lr': 0.0004581852696339985, 'samples': 15177216, 'steps': 29642, 'loss/train': 1.5770938396453857}
-03/05/2022 00:17:29 - INFO - codeparrot_training - Step 29643: {'lr': 0.00045818233144112044, 'samples': 15177728, 'steps': 29643, 'loss/train': 2.2921130657196045}
-03/05/2022 00:17:31 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 00:17:34 - INFO - codeparrot_training - Step 29644: {'lr': 0.00045817939315443855, 'samples': 15178240, 'steps': 29644, 'loss/train': 1.8131349086761475}
-03/05/2022 00:17:37 - INFO - codeparrot_training - Step 29645: {'lr': 0.0004581764547739543, 'samples': 15178752, 'steps': 29645, 'loss/train': 1.7691534757614136}
-03/05/2022 00:17:39 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/05/2022 00:17:43 - INFO - codeparrot_training - Step 29646: {'lr': 0.00045817351629966896, 'samples': 15179264, 'steps': 29646, 'loss/train': 1.7306549549102783}
-03/05/2022 00:17:46 - INFO - codeparrot_training - Step 29647: {'lr': 0.00045817057773158375, 'samples': 15179776, 'steps': 29647, 'loss/train': 1.89664626121521}
-03/05/2022 00:17:48 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/05/2022 00:17:51 - INFO - codeparrot_training - Step 29648: {'lr': 0.0004581676390697002, 'samples': 15180288, 'steps': 29648, 'loss/train': 1.81739342212677}
-03/05/2022 00:17:54 - INFO - codeparrot_training - Step 29649: {'lr': 0.00045816470031401945, 'samples': 15180800, 'steps': 29649, 'loss/train': 1.505497694015503}
-03/05/2022 00:17:56 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/05/2022 00:17:59 - INFO - codeparrot_training - Step 29650: {'lr': 0.00045816176146454296, 'samples': 15181312, 'steps': 29650, 'loss/train': 1.2665773630142212}
-03/05/2022 00:18:03 - INFO - codeparrot_training - Step 29651: {'lr': 0.00045815882252127197, 'samples': 15181824, 'steps': 29651, 'loss/train': 1.7291022539138794}
-03/05/2022 00:18:04 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 00:18:08 - INFO - codeparrot_training - Step 29652: {'lr': 0.0004581558834842078, 'samples': 15182336, 'steps': 29652, 'loss/train': 1.5999352931976318}
-03/05/2022 00:18:11 - INFO - codeparrot_training - Step 29653: {'lr': 0.00045815294435335184, 'samples': 15182848, 'steps': 29653, 'loss/train': 2.4165852069854736}
-03/05/2022 00:18:12 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/05/2022 00:18:16 - INFO - codeparrot_training - Step 29654: {'lr': 0.0004581500051287053, 'samples': 15183360, 'steps': 29654, 'loss/train': 2.910472869873047}
-03/05/2022 00:18:20 - INFO - codeparrot_training - Step 29655: {'lr': 0.00045814706581026967, 'samples': 15183872, 'steps': 29655, 'loss/train': 1.8675283193588257}
-03/05/2022 00:18:21 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/05/2022 00:18:25 - INFO - codeparrot_training - Step 29656: {'lr': 0.0004581441263980461, 'samples': 15184384, 'steps': 29656, 'loss/train': 2.431382417678833}
-03/05/2022 00:18:28 - INFO - codeparrot_training - Step 29657: {'lr': 0.0004581411868920361, 'samples': 15184896, 'steps': 29657, 'loss/train': 1.1192803382873535}
-03/05/2022 00:18:29 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 00:18:33 - INFO - codeparrot_training - Step 29658: {'lr': 0.00045813824729224085, 'samples': 15185408, 'steps': 29658, 'loss/train': 0.33740270137786865}
-03/05/2022 00:18:36 - INFO - codeparrot_training - Step 29659: {'lr': 0.0004581353075986617, 'samples': 15185920, 'steps': 29659, 'loss/train': 1.6104646921157837}
-03/05/2022 00:18:38 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/05/2022 00:18:42 - INFO - codeparrot_training - Step 29660: {'lr': 0.00045813236781129996, 'samples': 15186432, 'steps': 29660, 'loss/train': 2.2894287109375}
-03/05/2022 00:18:45 - INFO - codeparrot_training - Step 29661: {'lr': 0.00045812942793015707, 'samples': 15186944, 'steps': 29661, 'loss/train': 1.7148869037628174}
-03/05/2022 00:18:46 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/05/2022 00:18:50 - INFO - codeparrot_training - Step 29662: {'lr': 0.0004581264879552342, 'samples': 15187456, 'steps': 29662, 'loss/train': 0.7447697520256042}
-03/05/2022 00:18:53 - INFO - codeparrot_training - Step 29663: {'lr': 0.00045812354788653275, 'samples': 15187968, 'steps': 29663, 'loss/train': 1.8524298667907715}
-03/05/2022 00:18:54 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/05/2022 00:18:59 - INFO - codeparrot_training - Step 29664: {'lr': 0.00045812060772405403, 'samples': 15188480, 'steps': 29664, 'loss/train': 1.5619217157363892}
-03/05/2022 00:19:02 - INFO - codeparrot_training - Step 29665: {'lr': 0.0004581176674677995, 'samples': 15188992, 'steps': 29665, 'loss/train': 0.7549598813056946}
-03/05/2022 00:19:03 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/05/2022 00:19:07 - INFO - codeparrot_training - Step 29666: {'lr': 0.00045811472711777026, 'samples': 15189504, 'steps': 29666, 'loss/train': 0.8397639989852905}
-03/05/2022 00:19:10 - INFO - codeparrot_training - Step 29667: {'lr': 0.0004581117866739677, 'samples': 15190016, 'steps': 29667, 'loss/train': 2.2766034603118896}
-03/05/2022 00:19:11 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/05/2022 00:19:15 - INFO - codeparrot_training - Step 29668: {'lr': 0.00045810884613639325, 'samples': 15190528, 'steps': 29668, 'loss/train': 1.3779386281967163}
-03/05/2022 00:19:19 - INFO - codeparrot_training - Step 29669: {'lr': 0.00045810590550504816, 'samples': 15191040, 'steps': 29669, 'loss/train': 1.3402960300445557}
-03/05/2022 00:19:20 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/05/2022 00:19:24 - INFO - codeparrot_training - Step 29670: {'lr': 0.0004581029647799337, 'samples': 15191552, 'steps': 29670, 'loss/train': 1.1934853792190552}
-03/05/2022 00:19:27 - INFO - codeparrot_training - Step 29671: {'lr': 0.0004581000239610513, 'samples': 15192064, 'steps': 29671, 'loss/train': 1.5362460613250732}
-03/05/2022 00:19:28 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 00:19:32 - INFO - codeparrot_training - Step 29672: {'lr': 0.0004580970830484023, 'samples': 15192576, 'steps': 29672, 'loss/train': 1.6032607555389404}
-03/05/2022 00:19:35 - INFO - codeparrot_training - Step 29673: {'lr': 0.00045809414204198785, 'samples': 15193088, 'steps': 29673, 'loss/train': 1.8287689685821533}
-03/05/2022 00:19:37 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/05/2022 00:19:41 - INFO - codeparrot_training - Step 29674: {'lr': 0.00045809120094180946, 'samples': 15193600, 'steps': 29674, 'loss/train': 1.8490982055664062}
-03/05/2022 00:19:44 - INFO - codeparrot_training - Step 29675: {'lr': 0.00045808825974786834, 'samples': 15194112, 'steps': 29675, 'loss/train': 2.54978609085083}
-03/05/2022 00:19:45 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/05/2022 00:19:49 - INFO - codeparrot_training - Step 29676: {'lr': 0.0004580853184601659, 'samples': 15194624, 'steps': 29676, 'loss/train': 2.3288164138793945}
-03/05/2022 00:19:52 - INFO - codeparrot_training - Step 29677: {'lr': 0.0004580823770787034, 'samples': 15195136, 'steps': 29677, 'loss/train': 1.4746782779693604}
-03/05/2022 00:19:53 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/05/2022 00:19:58 - INFO - codeparrot_training - Step 29678: {'lr': 0.0004580794356034822, 'samples': 15195648, 'steps': 29678, 'loss/train': 1.5826754570007324}
-03/05/2022 00:20:01 - INFO - codeparrot_training - Step 29679: {'lr': 0.0004580764940345036, 'samples': 15196160, 'steps': 29679, 'loss/train': 1.5396908521652222}
-03/05/2022 00:20:01 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/05/2022 00:20:06 - INFO - codeparrot_training - Step 29680: {'lr': 0.00045807355237176896, 'samples': 15196672, 'steps': 29680, 'loss/train': 1.6554358005523682}
-03/05/2022 00:20:09 - INFO - codeparrot_training - Step 29681: {'lr': 0.0004580706106152796, 'samples': 15197184, 'steps': 29681, 'loss/train': 1.8935580253601074}
-03/05/2022 00:20:10 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/05/2022 00:20:14 - INFO - codeparrot_training - Step 29682: {'lr': 0.00045806766876503683, 'samples': 15197696, 'steps': 29682, 'loss/train': 2.466559648513794}
-03/05/2022 00:20:18 - INFO - codeparrot_training - Step 29683: {'lr': 0.000458064726821042, 'samples': 15198208, 'steps': 29683, 'loss/train': 0.12548203766345978}
-03/05/2022 00:20:18 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/05/2022 00:20:23 - INFO - codeparrot_training - Step 29684: {'lr': 0.0004580617847832964, 'samples': 15198720, 'steps': 29684, 'loss/train': 1.2880687713623047}
-03/05/2022 00:20:26 - INFO - codeparrot_training - Step 29685: {'lr': 0.0004580588426518013, 'samples': 15199232, 'steps': 29685, 'loss/train': 1.0839146375656128}
-03/05/2022 00:20:27 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/05/2022 00:20:31 - INFO - codeparrot_training - Step 29686: {'lr': 0.0004580559004265582, 'samples': 15199744, 'steps': 29686, 'loss/train': 0.9003174901008606}
-03/05/2022 00:20:35 - INFO - codeparrot_training - Step 29687: {'lr': 0.0004580529581075683, 'samples': 15200256, 'steps': 29687, 'loss/train': 1.7114344835281372}
-03/05/2022 00:20:35 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/05/2022 00:20:40 - INFO - codeparrot_training - Step 29688: {'lr': 0.0004580500156948329, 'samples': 15200768, 'steps': 29688, 'loss/train': 1.1175161600112915}
-03/05/2022 00:20:43 - INFO - codeparrot_training - Step 29689: {'lr': 0.0004580470731883534, 'samples': 15201280, 'steps': 29689, 'loss/train': 1.391488790512085}
-03/05/2022 00:20:45 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/05/2022 00:20:48 - INFO - codeparrot_training - Step 29690: {'lr': 0.0004580441305881311, 'samples': 15201792, 'steps': 29690, 'loss/train': 3.170132637023926}
-03/05/2022 00:20:51 - INFO - codeparrot_training - Step 29691: {'lr': 0.0004580411878941673, 'samples': 15202304, 'steps': 29691, 'loss/train': 1.9590134620666504}
-03/05/2022 00:20:53 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/05/2022 00:20:57 - INFO - codeparrot_training - Step 29692: {'lr': 0.0004580382451064634, 'samples': 15202816, 'steps': 29692, 'loss/train': 2.138234853744507}
-03/05/2022 00:21:00 - INFO - codeparrot_training - Step 29693: {'lr': 0.00045803530222502065, 'samples': 15203328, 'steps': 29693, 'loss/train': 1.8251312971115112}
-03/05/2022 00:21:02 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/05/2022 00:21:05 - INFO - codeparrot_training - Step 29694: {'lr': 0.0004580323592498404, 'samples': 15203840, 'steps': 29694, 'loss/train': 2.222379446029663}
-03/05/2022 00:21:08 - INFO - codeparrot_training - Step 29695: {'lr': 0.00045802941618092397, 'samples': 15204352, 'steps': 29695, 'loss/train': 0.7423340082168579}
-03/05/2022 00:21:10 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/05/2022 00:21:14 - INFO - codeparrot_training - Step 29696: {'lr': 0.0004580264730182727, 'samples': 15204864, 'steps': 29696, 'loss/train': 1.9618735313415527}
-03/05/2022 00:21:17 - INFO - codeparrot_training - Step 29697: {'lr': 0.000458023529761888, 'samples': 15205376, 'steps': 29697, 'loss/train': 2.4216809272766113}
-03/05/2022 00:21:18 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 00:21:22 - INFO - codeparrot_training - Step 29698: {'lr': 0.00045802058641177104, 'samples': 15205888, 'steps': 29698, 'loss/train': 1.8496674299240112}
-03/05/2022 00:21:25 - INFO - codeparrot_training - Step 29699: {'lr': 0.00045801764296792317, 'samples': 15206400, 'steps': 29699, 'loss/train': 1.9643638134002686}
-03/05/2022 00:21:27 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/05/2022 00:21:30 - INFO - codeparrot_training - Step 29700: {'lr': 0.0004580146994303458, 'samples': 15206912, 'steps': 29700, 'loss/train': 2.1131811141967773}
-03/05/2022 00:21:34 - INFO - codeparrot_training - Step 29701: {'lr': 0.0004580117557990402, 'samples': 15207424, 'steps': 29701, 'loss/train': 2.038806200027466}
-03/05/2022 00:21:35 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/05/2022 00:21:39 - INFO - codeparrot_training - Step 29702: {'lr': 0.0004580088120740077, 'samples': 15207936, 'steps': 29702, 'loss/train': 2.4480178356170654}
-03/05/2022 00:21:42 - INFO - codeparrot_training - Step 29703: {'lr': 0.0004580058682552497, 'samples': 15208448, 'steps': 29703, 'loss/train': 1.6460272073745728}
-03/05/2022 00:21:43 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/05/2022 00:21:48 - INFO - codeparrot_training - Step 29704: {'lr': 0.00045800292434276736, 'samples': 15208960, 'steps': 29704, 'loss/train': 1.217252492904663}
-03/05/2022 00:21:51 - INFO - codeparrot_training - Step 29705: {'lr': 0.0004579999803365622, 'samples': 15209472, 'steps': 29705, 'loss/train': 1.1021175384521484}
-03/05/2022 00:21:52 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/05/2022 00:21:56 - INFO - codeparrot_training - Step 29706: {'lr': 0.00045799703623663546, 'samples': 15209984, 'steps': 29706, 'loss/train': 1.5363919734954834}
-03/05/2022 00:21:59 - INFO - codeparrot_training - Step 29707: {'lr': 0.00045799409204298844, 'samples': 15210496, 'steps': 29707, 'loss/train': 1.032495379447937}
-03/05/2022 00:22:01 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/05/2022 00:22:04 - INFO - codeparrot_training - Step 29708: {'lr': 0.00045799114775562245, 'samples': 15211008, 'steps': 29708, 'loss/train': 1.1356053352355957}
-03/05/2022 00:22:07 - INFO - codeparrot_training - Step 29709: {'lr': 0.00045798820337453894, 'samples': 15211520, 'steps': 29709, 'loss/train': 1.7650761604309082}
-03/05/2022 00:22:09 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/05/2022 00:22:13 - INFO - codeparrot_training - Step 29710: {'lr': 0.00045798525889973905, 'samples': 15212032, 'steps': 29710, 'loss/train': 1.5482856035232544}
-03/05/2022 00:22:16 - INFO - codeparrot_training - Step 29711: {'lr': 0.00045798231433122436, 'samples': 15212544, 'steps': 29711, 'loss/train': 2.1354830265045166}
-03/05/2022 00:22:17 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/05/2022 00:22:21 - INFO - codeparrot_training - Step 29712: {'lr': 0.00045797936966899595, 'samples': 15213056, 'steps': 29712, 'loss/train': 1.8377057313919067}
-03/05/2022 00:22:24 - INFO - codeparrot_training - Step 29713: {'lr': 0.00045797642491305523, 'samples': 15213568, 'steps': 29713, 'loss/train': 2.0352139472961426}
-03/05/2022 00:22:25 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/05/2022 00:22:30 - INFO - codeparrot_training - Step 29714: {'lr': 0.0004579734800634036, 'samples': 15214080, 'steps': 29714, 'loss/train': 1.6556828022003174}
-03/05/2022 00:22:33 - INFO - codeparrot_training - Step 29715: {'lr': 0.0004579705351200423, 'samples': 15214592, 'steps': 29715, 'loss/train': 2.6244359016418457}
-03/05/2022 00:22:34 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/05/2022 00:22:38 - INFO - codeparrot_training - Step 29716: {'lr': 0.0004579675900829727, 'samples': 15215104, 'steps': 29716, 'loss/train': 1.44682776927948}
-03/05/2022 00:22:41 - INFO - codeparrot_training - Step 29717: {'lr': 0.00045796464495219614, 'samples': 15215616, 'steps': 29717, 'loss/train': 1.3237671852111816}
-03/05/2022 00:22:42 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/05/2022 00:22:46 - INFO - codeparrot_training - Step 29718: {'lr': 0.00045796169972771387, 'samples': 15216128, 'steps': 29718, 'loss/train': 0.8220032453536987}
-03/05/2022 00:22:49 - INFO - codeparrot_training - Step 29719: {'lr': 0.00045795875440952726, 'samples': 15216640, 'steps': 29719, 'loss/train': 1.8861268758773804}
-03/05/2022 00:22:50 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 00:22:55 - INFO - codeparrot_training - Step 29720: {'lr': 0.00045795580899763767, 'samples': 15217152, 'steps': 29720, 'loss/train': 1.9192782640457153}
-03/05/2022 00:22:58 - INFO - codeparrot_training - Step 29721: {'lr': 0.00045795286349204633, 'samples': 15217664, 'steps': 29721, 'loss/train': 1.7380495071411133}
-03/05/2022 00:22:58 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/05/2022 00:23:03 - INFO - codeparrot_training - Step 29722: {'lr': 0.0004579499178927547, 'samples': 15218176, 'steps': 29722, 'loss/train': 1.0124503374099731}
-03/05/2022 00:23:06 - INFO - codeparrot_training - Step 29723: {'lr': 0.0004579469721997641, 'samples': 15218688, 'steps': 29723, 'loss/train': 1.9146580696105957}
-03/05/2022 00:23:07 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/05/2022 00:23:12 - INFO - codeparrot_training - Step 29724: {'lr': 0.0004579440264130758, 'samples': 15219200, 'steps': 29724, 'loss/train': 1.272321343421936}
-03/05/2022 00:23:15 - INFO - codeparrot_training - Step 29725: {'lr': 0.000457941080532691, 'samples': 15219712, 'steps': 29725, 'loss/train': 0.6490805149078369}
-03/05/2022 00:23:15 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/05/2022 00:23:20 - INFO - codeparrot_training - Step 29726: {'lr': 0.0004579381345586113, 'samples': 15220224, 'steps': 29726, 'loss/train': 1.2653623819351196}
-03/05/2022 00:23:23 - INFO - codeparrot_training - Step 29727: {'lr': 0.0004579351884908378, 'samples': 15220736, 'steps': 29727, 'loss/train': 2.292475938796997}
-03/05/2022 00:23:25 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/05/2022 00:23:29 - INFO - codeparrot_training - Step 29728: {'lr': 0.00045793224232937193, 'samples': 15221248, 'steps': 29728, 'loss/train': 1.8938950300216675}
-03/05/2022 00:23:32 - INFO - codeparrot_training - Step 29729: {'lr': 0.0004579292960742151, 'samples': 15221760, 'steps': 29729, 'loss/train': 1.7529852390289307}
-03/05/2022 00:23:33 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 00:23:37 - INFO - codeparrot_training - Step 29730: {'lr': 0.0004579263497253684, 'samples': 15222272, 'steps': 29730, 'loss/train': 1.7478187084197998}
-03/05/2022 00:23:40 - INFO - codeparrot_training - Step 29731: {'lr': 0.00045792340328283334, 'samples': 15222784, 'steps': 29731, 'loss/train': 1.9145957231521606}
-03/05/2022 00:23:42 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/05/2022 00:23:46 - INFO - codeparrot_training - Step 29732: {'lr': 0.0004579204567466112, 'samples': 15223296, 'steps': 29732, 'loss/train': 2.0138182640075684}
-03/05/2022 00:23:49 - INFO - codeparrot_training - Step 29733: {'lr': 0.0004579175101167033, 'samples': 15223808, 'steps': 29733, 'loss/train': 1.0153049230575562}
-03/05/2022 00:23:50 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/05/2022 00:23:54 - INFO - codeparrot_training - Step 29734: {'lr': 0.000457914563393111, 'samples': 15224320, 'steps': 29734, 'loss/train': 1.529606580734253}
-03/05/2022 00:23:57 - INFO - codeparrot_training - Step 29735: {'lr': 0.00045791161657583555, 'samples': 15224832, 'steps': 29735, 'loss/train': 1.5589978694915771}
-03/05/2022 00:23:58 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/05/2022 00:24:02 - INFO - codeparrot_training - Step 29736: {'lr': 0.00045790866966487843, 'samples': 15225344, 'steps': 29736, 'loss/train': 1.4167641401290894}
-03/05/2022 00:24:06 - INFO - codeparrot_training - Step 29737: {'lr': 0.0004579057226602408, 'samples': 15225856, 'steps': 29737, 'loss/train': 2.1128108501434326}
-03/05/2022 00:24:07 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/05/2022 00:24:11 - INFO - codeparrot_training - Step 29738: {'lr': 0.00045790277556192414, 'samples': 15226368, 'steps': 29738, 'loss/train': 1.8649201393127441}
-03/05/2022 00:24:14 - INFO - codeparrot_training - Step 29739: {'lr': 0.0004578998283699296, 'samples': 15226880, 'steps': 29739, 'loss/train': 1.8969552516937256}
-03/05/2022 00:24:15 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/05/2022 00:24:19 - INFO - codeparrot_training - Step 29740: {'lr': 0.0004578968810842586, 'samples': 15227392, 'steps': 29740, 'loss/train': 1.7157353162765503}
-03/05/2022 00:24:22 - INFO - codeparrot_training - Step 29741: {'lr': 0.0004578939337049126, 'samples': 15227904, 'steps': 29741, 'loss/train': 1.7864376306533813}
-03/05/2022 00:24:23 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/05/2022 00:24:28 - INFO - codeparrot_training - Step 29742: {'lr': 0.0004578909862318927, 'samples': 15228416, 'steps': 29742, 'loss/train': 1.288945198059082}
-03/05/2022 00:24:31 - INFO - codeparrot_training - Step 29743: {'lr': 0.00045788803866520037, 'samples': 15228928, 'steps': 29743, 'loss/train': 0.7327784895896912}
-03/05/2022 00:24:32 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 00:24:36 - INFO - codeparrot_training - Step 29744: {'lr': 0.0004578850910048369, 'samples': 15229440, 'steps': 29744, 'loss/train': 1.9166655540466309}
-03/05/2022 00:24:39 - INFO - codeparrot_training - Step 29745: {'lr': 0.0004578821432508036, 'samples': 15229952, 'steps': 29745, 'loss/train': 2.2561233043670654}
-03/05/2022 00:24:40 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/05/2022 00:24:45 - INFO - codeparrot_training - Step 29746: {'lr': 0.00045787919540310175, 'samples': 15230464, 'steps': 29746, 'loss/train': 0.46884867548942566}
-03/05/2022 00:24:48 - INFO - codeparrot_training - Step 29747: {'lr': 0.0004578762474617328, 'samples': 15230976, 'steps': 29747, 'loss/train': 0.8854328989982605}
-03/05/2022 00:24:53 - INFO - codeparrot_training - Step 29748: {'lr': 0.00045787329942669803, 'samples': 15231488, 'steps': 29748, 'loss/train': 1.5276596546173096}
-03/05/2022 00:24:56 - INFO - codeparrot_training - Step 29749: {'lr': 0.0004578703512979988, 'samples': 15232000, 'steps': 29749, 'loss/train': 2.0027172565460205}
-03/05/2022 00:24:57 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/05/2022 00:25:01 - INFO - codeparrot_training - Step 29750: {'lr': 0.00045786740307563633, 'samples': 15232512, 'steps': 29750, 'loss/train': 1.809160828590393}
-03/05/2022 00:25:05 - INFO - codeparrot_training - Step 29751: {'lr': 0.000457864454759612, 'samples': 15233024, 'steps': 29751, 'loss/train': 2.1877565383911133}
-03/05/2022 00:25:05 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/05/2022 00:25:10 - INFO - codeparrot_training - Step 29752: {'lr': 0.00045786150634992716, 'samples': 15233536, 'steps': 29752, 'loss/train': 1.768035650253296}
-03/05/2022 00:25:13 - INFO - codeparrot_training - Step 29753: {'lr': 0.0004578585578465833, 'samples': 15234048, 'steps': 29753, 'loss/train': 2.0426881313323975}
-03/05/2022 00:25:14 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/05/2022 00:25:18 - INFO - codeparrot_training - Step 29754: {'lr': 0.00045785560924958135, 'samples': 15234560, 'steps': 29754, 'loss/train': 1.62642240524292}
-03/05/2022 00:25:22 - INFO - codeparrot_training - Step 29755: {'lr': 0.00045785266055892296, 'samples': 15235072, 'steps': 29755, 'loss/train': 1.9782161712646484}
-03/05/2022 00:25:22 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/05/2022 00:25:27 - INFO - codeparrot_training - Step 29756: {'lr': 0.0004578497117746094, 'samples': 15235584, 'steps': 29756, 'loss/train': 0.8306182622909546}
-03/05/2022 00:25:30 - INFO - codeparrot_training - Step 29757: {'lr': 0.00045784676289664194, 'samples': 15236096, 'steps': 29757, 'loss/train': 0.8733512163162231}
-03/05/2022 00:25:31 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 00:25:35 - INFO - codeparrot_training - Step 29758: {'lr': 0.00045784381392502193, 'samples': 15236608, 'steps': 29758, 'loss/train': 0.11854469776153564}
-03/05/2022 00:25:39 - INFO - codeparrot_training - Step 29759: {'lr': 0.00045784086485975076, 'samples': 15237120, 'steps': 29759, 'loss/train': 1.9815386533737183}
-03/05/2022 00:25:39 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/05/2022 00:25:44 - INFO - codeparrot_training - Step 29760: {'lr': 0.00045783791570082956, 'samples': 15237632, 'steps': 29760, 'loss/train': 2.071347236633301}
-03/05/2022 00:25:47 - INFO - codeparrot_training - Step 29761: {'lr': 0.00045783496644825997, 'samples': 15238144, 'steps': 29761, 'loss/train': 1.8988083600997925}
-03/05/2022 00:25:47 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/05/2022 00:25:52 - INFO - codeparrot_training - Step 29762: {'lr': 0.000457832017102043, 'samples': 15238656, 'steps': 29762, 'loss/train': 1.7896339893341064}
-03/05/2022 00:25:55 - INFO - codeparrot_training - Step 29763: {'lr': 0.00045782906766218026, 'samples': 15239168, 'steps': 29763, 'loss/train': 2.400224447250366}
-03/05/2022 00:25:56 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/05/2022 00:26:01 - INFO - codeparrot_training - Step 29764: {'lr': 0.00045782611812867285, 'samples': 15239680, 'steps': 29764, 'loss/train': 1.7666404247283936}
-03/05/2022 00:26:04 - INFO - codeparrot_training - Step 29765: {'lr': 0.0004578231685015223, 'samples': 15240192, 'steps': 29765, 'loss/train': 1.6612834930419922}
-03/05/2022 00:26:04 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 00:26:09 - INFO - codeparrot_training - Step 29766: {'lr': 0.00045782021878072976, 'samples': 15240704, 'steps': 29766, 'loss/train': 0.5175473093986511}
-03/05/2022 00:26:12 - INFO - codeparrot_training - Step 29767: {'lr': 0.0004578172689662967, 'samples': 15241216, 'steps': 29767, 'loss/train': 1.9802935123443604}
-03/05/2022 00:26:12 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/05/2022 00:26:17 - INFO - codeparrot_training - Step 29768: {'lr': 0.0004578143190582243, 'samples': 15241728, 'steps': 29768, 'loss/train': 1.9796173572540283}
-03/05/2022 00:26:21 - INFO - codeparrot_training - Step 29769: {'lr': 0.000457811369056514, 'samples': 15242240, 'steps': 29769, 'loss/train': 1.405814290046692}
-03/05/2022 00:26:21 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/05/2022 00:26:26 - INFO - codeparrot_training - Step 29770: {'lr': 0.0004578084189611671, 'samples': 15242752, 'steps': 29770, 'loss/train': 1.1862342357635498}
-03/05/2022 00:26:29 - INFO - codeparrot_training - Step 29771: {'lr': 0.000457805468772185, 'samples': 15243264, 'steps': 29771, 'loss/train': 1.620605707168579}
-03/05/2022 00:26:29 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/05/2022 00:26:34 - INFO - codeparrot_training - Step 29772: {'lr': 0.00045780251848956887, 'samples': 15243776, 'steps': 29772, 'loss/train': 1.3739683628082275}
-03/05/2022 00:26:37 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/05/2022 00:26:40 - INFO - codeparrot_training - Step 29773: {'lr': 0.0004577995681133202, 'samples': 15244288, 'steps': 29773, 'loss/train': 1.7113828659057617}
-03/05/2022 00:26:43 - INFO - codeparrot_training - Step 29774: {'lr': 0.00045779661764344025, 'samples': 15244800, 'steps': 29774, 'loss/train': 1.5478070974349976}
-03/05/2022 00:26:45 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/05/2022 00:26:48 - INFO - codeparrot_training - Step 29775: {'lr': 0.0004577936670799303, 'samples': 15245312, 'steps': 29775, 'loss/train': 1.6475026607513428}
-03/05/2022 00:26:51 - INFO - codeparrot_training - Step 29776: {'lr': 0.00045779071642279177, 'samples': 15245824, 'steps': 29776, 'loss/train': 1.8982794284820557}
-03/05/2022 00:26:53 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/05/2022 00:26:56 - INFO - codeparrot_training - Step 29777: {'lr': 0.00045778776567202597, 'samples': 15246336, 'steps': 29777, 'loss/train': 1.674333095550537}
-03/05/2022 00:26:59 - INFO - codeparrot_training - Step 29778: {'lr': 0.0004577848148276341, 'samples': 15246848, 'steps': 29778, 'loss/train': 2.3123972415924072}
-03/05/2022 00:27:02 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 00:27:05 - INFO - codeparrot_training - Step 29779: {'lr': 0.00045778186388961776, 'samples': 15247360, 'steps': 29779, 'loss/train': 1.2153793573379517}
-03/05/2022 00:27:08 - INFO - codeparrot_training - Step 29780: {'lr': 0.000457778912857978, 'samples': 15247872, 'steps': 29780, 'loss/train': 1.726761817932129}
-03/05/2022 00:27:10 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/05/2022 00:27:13 - INFO - codeparrot_training - Step 29781: {'lr': 0.0004577759617327163, 'samples': 15248384, 'steps': 29781, 'loss/train': 1.901078462600708}
-03/05/2022 00:27:16 - INFO - codeparrot_training - Step 29782: {'lr': 0.000457773010513834, 'samples': 15248896, 'steps': 29782, 'loss/train': 1.9935625791549683}
-03/05/2022 00:27:18 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/05/2022 00:27:22 - INFO - codeparrot_training - Step 29783: {'lr': 0.0004577700592013323, 'samples': 15249408, 'steps': 29783, 'loss/train': 1.8599544763565063}
-03/05/2022 00:27:25 - INFO - codeparrot_training - Step 29784: {'lr': 0.0004577671077952127, 'samples': 15249920, 'steps': 29784, 'loss/train': 2.3417301177978516}
-03/05/2022 00:27:27 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/05/2022 00:27:30 - INFO - codeparrot_training - Step 29785: {'lr': 0.0004577641562954764, 'samples': 15250432, 'steps': 29785, 'loss/train': 1.7938324213027954}
-03/05/2022 00:27:33 - INFO - codeparrot_training - Step 29786: {'lr': 0.00045776120470212477, 'samples': 15250944, 'steps': 29786, 'loss/train': 1.9551998376846313}
-03/05/2022 00:27:35 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/05/2022 00:27:38 - INFO - codeparrot_training - Step 29787: {'lr': 0.00045775825301515923, 'samples': 15251456, 'steps': 29787, 'loss/train': 1.5274182558059692}
-03/05/2022 00:27:42 - INFO - codeparrot_training - Step 29788: {'lr': 0.00045775530123458096, 'samples': 15251968, 'steps': 29788, 'loss/train': 2.371561288833618}
-03/05/2022 00:27:43 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/05/2022 00:27:47 - INFO - codeparrot_training - Step 29789: {'lr': 0.00045775234936039133, 'samples': 15252480, 'steps': 29789, 'loss/train': 1.8421707153320312}
-03/05/2022 00:27:50 - INFO - codeparrot_training - Step 29790: {'lr': 0.00045774939739259173, 'samples': 15252992, 'steps': 29790, 'loss/train': 2.2099366188049316}
-03/05/2022 00:27:52 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 00:27:55 - INFO - codeparrot_training - Step 29791: {'lr': 0.0004577464453311835, 'samples': 15253504, 'steps': 29791, 'loss/train': 1.3780889511108398}
-03/05/2022 00:27:58 - INFO - codeparrot_training - Step 29792: {'lr': 0.00045774349317616786, 'samples': 15254016, 'steps': 29792, 'loss/train': 1.6950688362121582}
-03/05/2022 00:28:00 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/05/2022 00:28:04 - INFO - codeparrot_training - Step 29793: {'lr': 0.00045774054092754624, 'samples': 15254528, 'steps': 29793, 'loss/train': 2.1432509422302246}
-03/05/2022 00:28:07 - INFO - codeparrot_training - Step 29794: {'lr': 0.00045773758858531997, 'samples': 15255040, 'steps': 29794, 'loss/train': 1.6225379705429077}
-03/05/2022 00:28:08 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/05/2022 00:28:12 - INFO - codeparrot_training - Step 29795: {'lr': 0.0004577346361494903, 'samples': 15255552, 'steps': 29795, 'loss/train': 1.5391451120376587}
-03/05/2022 00:28:15 - INFO - codeparrot_training - Step 29796: {'lr': 0.0004577316836200586, 'samples': 15256064, 'steps': 29796, 'loss/train': 1.2449394464492798}
-03/05/2022 00:28:16 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/05/2022 00:28:21 - INFO - codeparrot_training - Step 29797: {'lr': 0.0004577287309970262, 'samples': 15256576, 'steps': 29797, 'loss/train': 1.245635986328125}
-03/05/2022 00:28:24 - INFO - codeparrot_training - Step 29798: {'lr': 0.0004577257782803945, 'samples': 15257088, 'steps': 29798, 'loss/train': 1.5356526374816895}
-03/05/2022 00:28:24 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/05/2022 00:28:29 - INFO - codeparrot_training - Step 29799: {'lr': 0.00045772282547016475, 'samples': 15257600, 'steps': 29799, 'loss/train': 1.12308931350708}
-03/05/2022 00:28:32 - INFO - codeparrot_training - Step 29800: {'lr': 0.0004577198725663383, 'samples': 15258112, 'steps': 29800, 'loss/train': 1.3153727054595947}
-03/05/2022 00:28:33 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/05/2022 00:28:37 - INFO - codeparrot_training - Step 29801: {'lr': 0.00045771691956891645, 'samples': 15258624, 'steps': 29801, 'loss/train': 1.8563051223754883}
-03/05/2022 00:28:40 - INFO - codeparrot_training - Step 29802: {'lr': 0.00045771396647790053, 'samples': 15259136, 'steps': 29802, 'loss/train': 0.5884143710136414}
-03/05/2022 00:28:41 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/05/2022 00:28:46 - INFO - codeparrot_training - Step 29803: {'lr': 0.00045771101329329195, 'samples': 15259648, 'steps': 29803, 'loss/train': 1.2342315912246704}
-03/05/2022 00:28:49 - INFO - codeparrot_training - Step 29804: {'lr': 0.00045770806001509205, 'samples': 15260160, 'steps': 29804, 'loss/train': 2.640705108642578}
-03/05/2022 00:28:50 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/05/2022 00:28:54 - INFO - codeparrot_training - Step 29805: {'lr': 0.00045770510664330203, 'samples': 15260672, 'steps': 29805, 'loss/train': 2.3832898139953613}
-03/05/2022 00:28:57 - INFO - codeparrot_training - Step 29806: {'lr': 0.0004577021531779233, 'samples': 15261184, 'steps': 29806, 'loss/train': 1.4057444334030151}
-03/05/2022 00:28:58 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 00:29:03 - INFO - codeparrot_training - Step 29807: {'lr': 0.00045769919961895716, 'samples': 15261696, 'steps': 29807, 'loss/train': 0.47574424743652344}
-03/05/2022 00:29:06 - INFO - codeparrot_training - Step 29808: {'lr': 0.000457696245966405, 'samples': 15262208, 'steps': 29808, 'loss/train': 1.0762819051742554}
-03/05/2022 00:29:07 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/05/2022 00:29:11 - INFO - codeparrot_training - Step 29809: {'lr': 0.0004576932922202681, 'samples': 15262720, 'steps': 29809, 'loss/train': 1.8180761337280273}
-03/05/2022 00:29:14 - INFO - codeparrot_training - Step 29810: {'lr': 0.00045769033838054783, 'samples': 15263232, 'steps': 29810, 'loss/train': 1.8638055324554443}
-03/05/2022 00:29:15 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/05/2022 00:29:20 - INFO - codeparrot_training - Step 29811: {'lr': 0.0004576873844472455, 'samples': 15263744, 'steps': 29811, 'loss/train': 1.3484022617340088}
-03/05/2022 00:29:23 - INFO - codeparrot_training - Step 29812: {'lr': 0.00045768443042036247, 'samples': 15264256, 'steps': 29812, 'loss/train': 1.748068928718567}
-03/05/2022 00:29:23 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/05/2022 00:29:28 - INFO - codeparrot_training - Step 29813: {'lr': 0.0004576814762999, 'samples': 15264768, 'steps': 29813, 'loss/train': 1.978164792060852}
-03/05/2022 00:29:31 - INFO - codeparrot_training - Step 29814: {'lr': 0.00045767852208585945, 'samples': 15265280, 'steps': 29814, 'loss/train': 1.5703387260437012}
-03/05/2022 00:29:31 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/05/2022 00:29:36 - INFO - codeparrot_training - Step 29815: {'lr': 0.00045767556777824217, 'samples': 15265792, 'steps': 29815, 'loss/train': 1.2389801740646362}
-03/05/2022 00:29:40 - INFO - codeparrot_training - Step 29816: {'lr': 0.00045767261337704946, 'samples': 15266304, 'steps': 29816, 'loss/train': 1.7846262454986572}
-03/05/2022 00:29:40 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/05/2022 00:29:45 - INFO - codeparrot_training - Step 29817: {'lr': 0.00045766965888228273, 'samples': 15266816, 'steps': 29817, 'loss/train': 0.7802075743675232}
-03/05/2022 00:29:48 - INFO - codeparrot_training - Step 29818: {'lr': 0.00045766670429394317, 'samples': 15267328, 'steps': 29818, 'loss/train': 1.8447935581207275}
-03/05/2022 00:29:48 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/05/2022 00:29:54 - INFO - codeparrot_training - Step 29819: {'lr': 0.00045766374961203236, 'samples': 15267840, 'steps': 29819, 'loss/train': 1.563899040222168}
-03/05/2022 00:29:57 - INFO - codeparrot_training - Step 29820: {'lr': 0.0004576607948365513, 'samples': 15268352, 'steps': 29820, 'loss/train': 0.20916035771369934}
-03/05/2022 00:29:57 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/05/2022 00:30:02 - INFO - codeparrot_training - Step 29821: {'lr': 0.0004576578399675015, 'samples': 15268864, 'steps': 29821, 'loss/train': 0.733149528503418}
-03/05/2022 00:30:05 - INFO - codeparrot_training - Step 29822: {'lr': 0.00045765488500488437, 'samples': 15269376, 'steps': 29822, 'loss/train': 1.7109016180038452}
-03/05/2022 00:30:06 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/05/2022 00:30:10 - INFO - codeparrot_training - Step 29823: {'lr': 0.0004576519299487012, 'samples': 15269888, 'steps': 29823, 'loss/train': 1.7575656175613403}
-03/05/2022 00:30:14 - INFO - codeparrot_training - Step 29824: {'lr': 0.00045764897479895315, 'samples': 15270400, 'steps': 29824, 'loss/train': 1.2565714120864868}
-03/05/2022 00:30:14 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/05/2022 00:30:19 - INFO - codeparrot_training - Step 29825: {'lr': 0.0004576460195556418, 'samples': 15270912, 'steps': 29825, 'loss/train': 1.1597185134887695}
-03/05/2022 00:30:22 - INFO - codeparrot_training - Step 29826: {'lr': 0.0004576430642187682, 'samples': 15271424, 'steps': 29826, 'loss/train': 1.9400850534439087}
-03/05/2022 00:30:22 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/05/2022 00:30:27 - INFO - codeparrot_training - Step 29827: {'lr': 0.00045764010878833396, 'samples': 15271936, 'steps': 29827, 'loss/train': 2.006314992904663}
-03/05/2022 00:30:30 - INFO - codeparrot_training - Step 29828: {'lr': 0.00045763715326434023, 'samples': 15272448, 'steps': 29828, 'loss/train': 1.271968126296997}
-03/05/2022 00:30:30 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/05/2022 00:30:36 - INFO - codeparrot_training - Step 29829: {'lr': 0.0004576341976467884, 'samples': 15272960, 'steps': 29829, 'loss/train': 2.4425759315490723}
-03/05/2022 00:30:38 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/05/2022 00:30:41 - INFO - codeparrot_training - Step 29830: {'lr': 0.00045763124193567983, 'samples': 15273472, 'steps': 29830, 'loss/train': 1.6264653205871582}
-03/05/2022 00:30:44 - INFO - codeparrot_training - Step 29831: {'lr': 0.0004576282861310158, 'samples': 15273984, 'steps': 29831, 'loss/train': 1.4065762758255005}
-03/05/2022 00:30:47 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/05/2022 00:30:49 - INFO - codeparrot_training - Step 29832: {'lr': 0.00045762533023279773, 'samples': 15274496, 'steps': 29832, 'loss/train': 1.361911416053772}
-03/05/2022 00:30:52 - INFO - codeparrot_training - Step 29833: {'lr': 0.00045762237424102687, 'samples': 15275008, 'steps': 29833, 'loss/train': 1.993345022201538}
-03/05/2022 00:30:55 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/05/2022 00:30:58 - INFO - codeparrot_training - Step 29834: {'lr': 0.0004576194181557045, 'samples': 15275520, 'steps': 29834, 'loss/train': 1.3203306198120117}
-03/05/2022 00:31:01 - INFO - codeparrot_training - Step 29835: {'lr': 0.00045761646197683216, 'samples': 15276032, 'steps': 29835, 'loss/train': 1.8211629390716553}
-03/05/2022 00:31:04 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/05/2022 00:31:07 - INFO - codeparrot_training - Step 29836: {'lr': 0.00045761350570441096, 'samples': 15276544, 'steps': 29836, 'loss/train': 1.8432252407073975}
-03/05/2022 00:31:10 - INFO - codeparrot_training - Step 29837: {'lr': 0.0004576105493384423, 'samples': 15277056, 'steps': 29837, 'loss/train': 2.1293351650238037}
-03/05/2022 00:31:13 - INFO - codeparrot_training - Step 29838: {'lr': 0.00045760759287892755, 'samples': 15277568, 'steps': 29838, 'loss/train': 1.832953691482544}
-03/05/2022 00:31:14 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/05/2022 00:31:18 - INFO - codeparrot_training - Step 29839: {'lr': 0.000457604636325868, 'samples': 15278080, 'steps': 29839, 'loss/train': 1.5511794090270996}
-03/05/2022 00:31:21 - INFO - codeparrot_training - Step 29840: {'lr': 0.00045760167967926504, 'samples': 15278592, 'steps': 29840, 'loss/train': 1.9861503839492798}
-03/05/2022 00:31:22 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 00:31:27 - INFO - codeparrot_training - Step 29841: {'lr': 0.00045759872293911995, 'samples': 15279104, 'steps': 29841, 'loss/train': 1.2327396869659424}
-03/05/2022 00:31:30 - INFO - codeparrot_training - Step 29842: {'lr': 0.00045759576610543407, 'samples': 15279616, 'steps': 29842, 'loss/train': 1.9080917835235596}
-03/05/2022 00:31:30 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/05/2022 00:31:35 - INFO - codeparrot_training - Step 29843: {'lr': 0.0004575928091782088, 'samples': 15280128, 'steps': 29843, 'loss/train': 1.903252363204956}
-03/05/2022 00:31:38 - INFO - codeparrot_training - Step 29844: {'lr': 0.00045758985215744536, 'samples': 15280640, 'steps': 29844, 'loss/train': 1.5287150144577026}
-03/05/2022 00:31:38 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/05/2022 00:31:44 - INFO - codeparrot_training - Step 29845: {'lr': 0.0004575868950431452, 'samples': 15281152, 'steps': 29845, 'loss/train': 7.017806529998779}
-03/05/2022 00:31:47 - INFO - codeparrot_training - Step 29846: {'lr': 0.0004575839378353095, 'samples': 15281664, 'steps': 29846, 'loss/train': 0.9437267184257507}
-03/05/2022 00:31:48 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/05/2022 00:31:52 - INFO - codeparrot_training - Step 29847: {'lr': 0.0004575809805339397, 'samples': 15282176, 'steps': 29847, 'loss/train': 6.641016483306885}
-03/05/2022 00:31:55 - INFO - codeparrot_training - Step 29848: {'lr': 0.0004575780231390371, 'samples': 15282688, 'steps': 29848, 'loss/train': 1.6209219694137573}
-03/05/2022 00:31:57 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 00:32:00 - INFO - codeparrot_training - Step 29849: {'lr': 0.0004575750656506031, 'samples': 15283200, 'steps': 29849, 'loss/train': 0.634583592414856}
-03/05/2022 00:32:03 - INFO - codeparrot_training - Step 29850: {'lr': 0.00045757210806863895, 'samples': 15283712, 'steps': 29850, 'loss/train': 1.173998236656189}
-03/05/2022 00:32:05 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/05/2022 00:32:09 - INFO - codeparrot_training - Step 29851: {'lr': 0.0004575691503931461, 'samples': 15284224, 'steps': 29851, 'loss/train': 1.6008409261703491}
-03/05/2022 00:32:12 - INFO - codeparrot_training - Step 29852: {'lr': 0.00045756619262412565, 'samples': 15284736, 'steps': 29852, 'loss/train': 1.976826548576355}
-03/05/2022 00:32:13 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/05/2022 00:32:17 - INFO - codeparrot_training - Step 29853: {'lr': 0.0004575632347615791, 'samples': 15285248, 'steps': 29853, 'loss/train': 0.8037336468696594}
-03/05/2022 00:32:20 - INFO - codeparrot_training - Step 29854: {'lr': 0.0004575602768055078, 'samples': 15285760, 'steps': 29854, 'loss/train': 1.617974042892456}
-03/05/2022 00:32:21 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/05/2022 00:32:26 - INFO - codeparrot_training - Step 29855: {'lr': 0.00045755731875591303, 'samples': 15286272, 'steps': 29855, 'loss/train': 1.691144347190857}
-03/05/2022 00:32:29 - INFO - codeparrot_training - Step 29856: {'lr': 0.0004575543606127961, 'samples': 15286784, 'steps': 29856, 'loss/train': 0.07484892010688782}
-03/05/2022 00:32:30 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/05/2022 00:32:34 - INFO - codeparrot_training - Step 29857: {'lr': 0.0004575514023761585, 'samples': 15287296, 'steps': 29857, 'loss/train': 1.8722554445266724}
-03/05/2022 00:32:37 - INFO - codeparrot_training - Step 29858: {'lr': 0.00045754844404600136, 'samples': 15287808, 'steps': 29858, 'loss/train': 1.8896632194519043}
-03/05/2022 00:32:38 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/05/2022 00:32:42 - INFO - codeparrot_training - Step 29859: {'lr': 0.00045754548562232605, 'samples': 15288320, 'steps': 29859, 'loss/train': 2.0749549865722656}
-03/05/2022 00:32:46 - INFO - codeparrot_training - Step 29860: {'lr': 0.00045754252710513397, 'samples': 15288832, 'steps': 29860, 'loss/train': 1.7416914701461792}
-03/05/2022 00:32:46 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 00:32:51 - INFO - codeparrot_training - Step 29861: {'lr': 0.00045753956849442647, 'samples': 15289344, 'steps': 29861, 'loss/train': 0.9600059390068054}
-03/05/2022 00:32:54 - INFO - codeparrot_training - Step 29862: {'lr': 0.00045753660979020485, 'samples': 15289856, 'steps': 29862, 'loss/train': 2.124492645263672}
-03/05/2022 00:32:55 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/05/2022 00:32:59 - INFO - codeparrot_training - Step 29863: {'lr': 0.0004575336509924704, 'samples': 15290368, 'steps': 29863, 'loss/train': 2.2291338443756104}
-03/05/2022 00:33:02 - INFO - codeparrot_training - Step 29864: {'lr': 0.0004575306921012245, 'samples': 15290880, 'steps': 29864, 'loss/train': 3.1992719173431396}
-03/05/2022 00:33:03 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 00:33:08 - INFO - codeparrot_training - Step 29865: {'lr': 0.00045752773311646846, 'samples': 15291392, 'steps': 29865, 'loss/train': 1.3580504655838013}
-03/05/2022 00:33:11 - INFO - codeparrot_training - Step 29866: {'lr': 0.0004575247740382037, 'samples': 15291904, 'steps': 29866, 'loss/train': 1.603963851928711}
-03/05/2022 00:33:11 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/05/2022 00:33:16 - INFO - codeparrot_training - Step 29867: {'lr': 0.0004575218148664314, 'samples': 15292416, 'steps': 29867, 'loss/train': 1.3678820133209229}
-03/05/2022 00:33:19 - INFO - codeparrot_training - Step 29868: {'lr': 0.00045751885560115294, 'samples': 15292928, 'steps': 29868, 'loss/train': 1.4411547183990479}
-03/05/2022 00:33:20 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/05/2022 00:33:25 - INFO - codeparrot_training - Step 29869: {'lr': 0.0004575158962423698, 'samples': 15293440, 'steps': 29869, 'loss/train': 1.8885822296142578}
-03/05/2022 00:33:28 - INFO - codeparrot_training - Step 29870: {'lr': 0.0004575129367900831, 'samples': 15293952, 'steps': 29870, 'loss/train': 7.112231254577637}
-03/05/2022 00:33:28 - INFO - codeparrot_training - Skipping example with length 385 (seq_length=1024)
-03/05/2022 00:33:33 - INFO - codeparrot_training - Step 29871: {'lr': 0.0004575099772442943, 'samples': 15294464, 'steps': 29871, 'loss/train': 1.7824209928512573}
-03/05/2022 00:33:36 - INFO - codeparrot_training - Step 29872: {'lr': 0.0004575070176050047, 'samples': 15294976, 'steps': 29872, 'loss/train': 2.213797092437744}
-03/05/2022 00:33:37 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 00:33:42 - INFO - codeparrot_training - Step 29873: {'lr': 0.00045750405787221566, 'samples': 15295488, 'steps': 29873, 'loss/train': 1.5352163314819336}
-03/05/2022 00:33:45 - INFO - codeparrot_training - Step 29874: {'lr': 0.0004575010980459285, 'samples': 15296000, 'steps': 29874, 'loss/train': 1.5212042331695557}
-03/05/2022 00:33:45 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/05/2022 00:33:50 - INFO - codeparrot_training - Step 29875: {'lr': 0.0004574981381261445, 'samples': 15296512, 'steps': 29875, 'loss/train': 1.6703989505767822}
-03/05/2022 00:33:53 - INFO - codeparrot_training - Step 29876: {'lr': 0.0004574951781128651, 'samples': 15297024, 'steps': 29876, 'loss/train': 1.5002238750457764}
-03/05/2022 00:33:53 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/05/2022 00:33:58 - INFO - codeparrot_training - Step 29877: {'lr': 0.0004574922180060915, 'samples': 15297536, 'steps': 29877, 'loss/train': 2.000081777572632}
-03/05/2022 00:34:02 - INFO - codeparrot_training - Step 29878: {'lr': 0.0004574892578058252, 'samples': 15298048, 'steps': 29878, 'loss/train': 1.456671953201294}
-03/05/2022 00:34:02 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/05/2022 00:34:07 - INFO - codeparrot_training - Step 29879: {'lr': 0.0004574862975120674, 'samples': 15298560, 'steps': 29879, 'loss/train': 1.570813536643982}
-03/05/2022 00:34:10 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 00:34:12 - INFO - codeparrot_training - Step 29880: {'lr': 0.0004574833371248195, 'samples': 15299072, 'steps': 29880, 'loss/train': 1.0843474864959717}
-03/05/2022 00:34:15 - INFO - codeparrot_training - Step 29881: {'lr': 0.00045748037664408275, 'samples': 15299584, 'steps': 29881, 'loss/train': 1.7602812051773071}
-03/05/2022 00:34:18 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/05/2022 00:34:20 - INFO - codeparrot_training - Step 29882: {'lr': 0.0004574774160698586, 'samples': 15300096, 'steps': 29882, 'loss/train': 2.031615734100342}
-03/05/2022 00:34:24 - INFO - codeparrot_training - Step 29883: {'lr': 0.00045747445540214826, 'samples': 15300608, 'steps': 29883, 'loss/train': 1.8771326541900635}
-03/05/2022 00:34:26 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 00:34:29 - INFO - codeparrot_training - Step 29884: {'lr': 0.00045747149464095324, 'samples': 15301120, 'steps': 29884, 'loss/train': 1.2074363231658936}
-03/05/2022 00:34:32 - INFO - codeparrot_training - Step 29885: {'lr': 0.00045746853378627467, 'samples': 15301632, 'steps': 29885, 'loss/train': 2.0074334144592285}
-03/05/2022 00:34:35 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/05/2022 00:34:37 - INFO - codeparrot_training - Step 29886: {'lr': 0.000457465572838114, 'samples': 15302144, 'steps': 29886, 'loss/train': 1.3116018772125244}
-03/05/2022 00:34:41 - INFO - codeparrot_training - Step 29887: {'lr': 0.0004574626117964726, 'samples': 15302656, 'steps': 29887, 'loss/train': 1.064660906791687}
-03/05/2022 00:34:44 - INFO - codeparrot_training - Step 29888: {'lr': 0.00045745965066135163, 'samples': 15303168, 'steps': 29888, 'loss/train': 1.8852994441986084}
-03/05/2022 00:34:44 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/05/2022 00:34:49 - INFO - codeparrot_training - Step 29889: {'lr': 0.00045745668943275266, 'samples': 15303680, 'steps': 29889, 'loss/train': 1.6285513639450073}
-03/05/2022 00:34:52 - INFO - codeparrot_training - Step 29890: {'lr': 0.00045745372811067687, 'samples': 15304192, 'steps': 29890, 'loss/train': 1.9510889053344727}
-03/05/2022 00:34:52 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/05/2022 00:34:58 - INFO - codeparrot_training - Step 29891: {'lr': 0.00045745076669512566, 'samples': 15304704, 'steps': 29891, 'loss/train': 2.5489838123321533}
-03/05/2022 00:35:01 - INFO - codeparrot_training - Step 29892: {'lr': 0.0004574478051861003, 'samples': 15305216, 'steps': 29892, 'loss/train': 1.6912596225738525}
-03/05/2022 00:35:01 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 00:35:06 - INFO - codeparrot_training - Step 29893: {'lr': 0.00045744484358360216, 'samples': 15305728, 'steps': 29893, 'loss/train': 1.9176524877548218}
-03/05/2022 00:35:09 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/05/2022 00:35:11 - INFO - codeparrot_training - Step 29894: {'lr': 0.0004574418818876326, 'samples': 15306240, 'steps': 29894, 'loss/train': 1.7842119932174683}
-03/05/2022 00:35:14 - INFO - codeparrot_training - Step 29895: {'lr': 0.0004574389200981929, 'samples': 15306752, 'steps': 29895, 'loss/train': 2.377946615219116}
-03/05/2022 00:35:17 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/05/2022 00:35:20 - INFO - codeparrot_training - Step 29896: {'lr': 0.00045743595821528437, 'samples': 15307264, 'steps': 29896, 'loss/train': 1.564409852027893}
-03/05/2022 00:35:23 - INFO - codeparrot_training - Step 29897: {'lr': 0.0004574329962389085, 'samples': 15307776, 'steps': 29897, 'loss/train': 1.9296013116836548}
-03/05/2022 00:35:26 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/05/2022 00:35:28 - INFO - codeparrot_training - Step 29898: {'lr': 0.0004574300341690665, 'samples': 15308288, 'steps': 29898, 'loss/train': 0.28194689750671387}
-03/05/2022 00:35:31 - INFO - codeparrot_training - Step 29899: {'lr': 0.00045742707200575975, 'samples': 15308800, 'steps': 29899, 'loss/train': 2.3497543334960938}
-03/05/2022 00:35:34 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/05/2022 00:35:37 - INFO - codeparrot_training - Step 29900: {'lr': 0.00045742410974898947, 'samples': 15309312, 'steps': 29900, 'loss/train': 1.952285885810852}
-03/05/2022 00:35:40 - INFO - codeparrot_training - Step 29901: {'lr': 0.0004574211473987571, 'samples': 15309824, 'steps': 29901, 'loss/train': 1.614179015159607}
-03/05/2022 00:35:42 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/05/2022 00:35:45 - INFO - codeparrot_training - Step 29902: {'lr': 0.00045741818495506403, 'samples': 15310336, 'steps': 29902, 'loss/train': 1.7428537607192993}
-03/05/2022 00:35:48 - INFO - codeparrot_training - Step 29903: {'lr': 0.0004574152224179115, 'samples': 15310848, 'steps': 29903, 'loss/train': 1.290940284729004}
-03/05/2022 00:35:50 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/05/2022 00:35:54 - INFO - codeparrot_training - Step 29904: {'lr': 0.0004574122597873008, 'samples': 15311360, 'steps': 29904, 'loss/train': 1.9227781295776367}
-03/05/2022 00:35:57 - INFO - codeparrot_training - Step 29905: {'lr': 0.0004574092970632335, 'samples': 15311872, 'steps': 29905, 'loss/train': 1.6412632465362549}
-03/05/2022 00:35:59 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 00:36:02 - INFO - codeparrot_training - Step 29906: {'lr': 0.00045740633424571064, 'samples': 15312384, 'steps': 29906, 'loss/train': 1.2250454425811768}
-03/05/2022 00:36:05 - INFO - codeparrot_training - Step 29907: {'lr': 0.00045740337133473374, 'samples': 15312896, 'steps': 29907, 'loss/train': 1.7881981134414673}
-03/05/2022 00:36:07 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 00:36:11 - INFO - codeparrot_training - Step 29908: {'lr': 0.00045740040833030404, 'samples': 15313408, 'steps': 29908, 'loss/train': 1.8580331802368164}
-03/05/2022 00:36:14 - INFO - codeparrot_training - Step 29909: {'lr': 0.00045739744523242294, 'samples': 15313920, 'steps': 29909, 'loss/train': 2.1727869510650635}
-03/05/2022 00:36:17 - INFO - codeparrot_training - Step 29910: {'lr': 0.0004573944820410918, 'samples': 15314432, 'steps': 29910, 'loss/train': 1.52242910861969}
-03/05/2022 00:36:17 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/05/2022 00:36:22 - INFO - codeparrot_training - Step 29911: {'lr': 0.0004573915187563118, 'samples': 15314944, 'steps': 29911, 'loss/train': 1.4623748064041138}
-03/05/2022 00:36:26 - INFO - codeparrot_training - Step 29912: {'lr': 0.00045738855537808443, 'samples': 15315456, 'steps': 29912, 'loss/train': 0.7852261066436768}
-03/05/2022 00:36:26 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/05/2022 00:36:31 - INFO - codeparrot_training - Step 29913: {'lr': 0.000457385591906411, 'samples': 15315968, 'steps': 29913, 'loss/train': 2.221421480178833}
-03/05/2022 00:36:34 - INFO - codeparrot_training - Step 29914: {'lr': 0.00045738262834129283, 'samples': 15316480, 'steps': 29914, 'loss/train': 2.536991596221924}
-03/05/2022 00:36:34 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/05/2022 00:36:39 - INFO - codeparrot_training - Step 29915: {'lr': 0.0004573796646827312, 'samples': 15316992, 'steps': 29915, 'loss/train': 1.4360783100128174}
-03/05/2022 00:36:42 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/05/2022 00:36:45 - INFO - codeparrot_training - Step 29916: {'lr': 0.0004573767009307276, 'samples': 15317504, 'steps': 29916, 'loss/train': 1.3504279851913452}
-03/05/2022 00:36:48 - INFO - codeparrot_training - Step 29917: {'lr': 0.0004573737370852831, 'samples': 15318016, 'steps': 29917, 'loss/train': 1.5515646934509277}
-03/05/2022 00:36:51 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 00:36:53 - INFO - codeparrot_training - Step 29918: {'lr': 0.0004573707731463993, 'samples': 15318528, 'steps': 29918, 'loss/train': 2.1219840049743652}
-03/05/2022 00:36:57 - INFO - codeparrot_training - Step 29919: {'lr': 0.00045736780911407736, 'samples': 15319040, 'steps': 29919, 'loss/train': 6.804988861083984}
-03/05/2022 00:37:00 - INFO - codeparrot_training - Step 29920: {'lr': 0.00045736484498831877, 'samples': 15319552, 'steps': 29920, 'loss/train': 1.5250482559204102}
-03/05/2022 00:37:00 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/05/2022 00:37:05 - INFO - codeparrot_training - Step 29921: {'lr': 0.0004573618807691248, 'samples': 15320064, 'steps': 29921, 'loss/train': 0.03833547234535217}
-03/05/2022 00:37:09 - INFO - codeparrot_training - Step 29922: {'lr': 0.0004573589164564966, 'samples': 15320576, 'steps': 29922, 'loss/train': 2.3265116214752197}
-03/05/2022 00:37:10 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/05/2022 00:37:14 - INFO - codeparrot_training - Step 29923: {'lr': 0.00045735595205043583, 'samples': 15321088, 'steps': 29923, 'loss/train': 1.54251229763031}
-03/05/2022 00:37:17 - INFO - codeparrot_training - Step 29924: {'lr': 0.00045735298755094364, 'samples': 15321600, 'steps': 29924, 'loss/train': 1.8605268001556396}
-03/05/2022 00:37:19 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/05/2022 00:37:22 - INFO - codeparrot_training - Step 29925: {'lr': 0.00045735002295802137, 'samples': 15322112, 'steps': 29925, 'loss/train': 1.5954961776733398}
-03/05/2022 00:37:25 - INFO - codeparrot_training - Step 29926: {'lr': 0.00045734705827167035, 'samples': 15322624, 'steps': 29926, 'loss/train': 1.425561547279358}
-03/05/2022 00:37:27 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/05/2022 00:37:31 - INFO - codeparrot_training - Step 29927: {'lr': 0.000457344093491892, 'samples': 15323136, 'steps': 29927, 'loss/train': 2.0718324184417725}
-03/05/2022 00:37:34 - INFO - codeparrot_training - Step 29928: {'lr': 0.00045734112861868753, 'samples': 15323648, 'steps': 29928, 'loss/train': 1.6861531734466553}
-03/05/2022 00:37:35 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/05/2022 00:37:39 - INFO - codeparrot_training - Step 29929: {'lr': 0.0004573381636520584, 'samples': 15324160, 'steps': 29929, 'loss/train': 1.9465038776397705}
-03/05/2022 00:37:42 - INFO - codeparrot_training - Step 29930: {'lr': 0.0004573351985920059, 'samples': 15324672, 'steps': 29930, 'loss/train': 1.902191400527954}
-03/05/2022 00:37:43 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/05/2022 00:37:48 - INFO - codeparrot_training - Step 29931: {'lr': 0.0004573322334385314, 'samples': 15325184, 'steps': 29931, 'loss/train': 1.6553391218185425}
-03/05/2022 00:37:51 - INFO - codeparrot_training - Step 29932: {'lr': 0.0004573292681916361, 'samples': 15325696, 'steps': 29932, 'loss/train': 1.0357544422149658}
-03/05/2022 00:37:52 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/05/2022 00:37:56 - INFO - codeparrot_training - Step 29933: {'lr': 0.0004573263028513214, 'samples': 15326208, 'steps': 29933, 'loss/train': 2.2017669677734375}
-03/05/2022 00:37:59 - INFO - codeparrot_training - Step 29934: {'lr': 0.0004573233374175888, 'samples': 15326720, 'steps': 29934, 'loss/train': 1.7318389415740967}
-03/05/2022 00:38:00 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 00:38:04 - INFO - codeparrot_training - Step 29935: {'lr': 0.0004573203718904394, 'samples': 15327232, 'steps': 29935, 'loss/train': 1.3272916078567505}
-03/05/2022 00:38:08 - INFO - codeparrot_training - Step 29936: {'lr': 0.00045731740626987473, 'samples': 15327744, 'steps': 29936, 'loss/train': 1.4265285730361938}
-03/05/2022 00:38:08 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/05/2022 00:38:13 - INFO - codeparrot_training - Step 29937: {'lr': 0.00045731444055589597, 'samples': 15328256, 'steps': 29937, 'loss/train': 0.8252424001693726}
-03/05/2022 00:38:16 - INFO - codeparrot_training - Step 29938: {'lr': 0.0004573114747485045, 'samples': 15328768, 'steps': 29938, 'loss/train': 1.7402069568634033}
-03/05/2022 00:38:17 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/05/2022 00:38:21 - INFO - codeparrot_training - Step 29939: {'lr': 0.0004573085088477017, 'samples': 15329280, 'steps': 29939, 'loss/train': 1.616119384765625}
-03/05/2022 00:38:24 - INFO - codeparrot_training - Step 29940: {'lr': 0.0004573055428534889, 'samples': 15329792, 'steps': 29940, 'loss/train': 1.3272995948791504}
-03/05/2022 00:38:25 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/05/2022 00:38:30 - INFO - codeparrot_training - Step 29941: {'lr': 0.00045730257676586747, 'samples': 15330304, 'steps': 29941, 'loss/train': 1.352555274963379}
-03/05/2022 00:38:33 - INFO - codeparrot_training - Step 29942: {'lr': 0.0004572996105848386, 'samples': 15330816, 'steps': 29942, 'loss/train': 1.4182147979736328}
-03/05/2022 00:38:34 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/05/2022 00:38:38 - INFO - codeparrot_training - Step 29943: {'lr': 0.0004572966443104038, 'samples': 15331328, 'steps': 29943, 'loss/train': 1.0883547067642212}
-03/05/2022 00:38:41 - INFO - codeparrot_training - Step 29944: {'lr': 0.00045729367794256434, 'samples': 15331840, 'steps': 29944, 'loss/train': 1.725461483001709}
-03/05/2022 00:38:42 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/05/2022 00:38:47 - INFO - codeparrot_training - Step 29945: {'lr': 0.0004572907114813215, 'samples': 15332352, 'steps': 29945, 'loss/train': 2.173579216003418}
-03/05/2022 00:38:50 - INFO - codeparrot_training - Step 29946: {'lr': 0.0004572877449266767, 'samples': 15332864, 'steps': 29946, 'loss/train': 1.618887186050415}
-03/05/2022 00:38:50 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 00:38:55 - INFO - codeparrot_training - Step 29947: {'lr': 0.0004572847782786312, 'samples': 15333376, 'steps': 29947, 'loss/train': 1.1793477535247803}
-03/05/2022 00:38:58 - INFO - codeparrot_training - Step 29948: {'lr': 0.0004572818115371864, 'samples': 15333888, 'steps': 29948, 'loss/train': 1.466715693473816}
-03/05/2022 00:38:58 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 00:39:03 - INFO - codeparrot_training - Step 29949: {'lr': 0.0004572788447023436, 'samples': 15334400, 'steps': 29949, 'loss/train': 1.5073846578598022}
-03/05/2022 00:39:06 - INFO - codeparrot_training - Step 29950: {'lr': 0.00045727587777410415, 'samples': 15334912, 'steps': 29950, 'loss/train': 1.3496739864349365}
-03/05/2022 00:39:07 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/05/2022 00:39:12 - INFO - codeparrot_training - Step 29951: {'lr': 0.00045727291075246937, 'samples': 15335424, 'steps': 29951, 'loss/train': 1.7845113277435303}
-03/05/2022 00:39:15 - INFO - codeparrot_training - Step 29952: {'lr': 0.0004572699436374407, 'samples': 15335936, 'steps': 29952, 'loss/train': 1.0496718883514404}
-03/05/2022 00:39:15 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/05/2022 00:39:20 - INFO - codeparrot_training - Step 29953: {'lr': 0.00045726697642901925, 'samples': 15336448, 'steps': 29953, 'loss/train': 2.0062108039855957}
-03/05/2022 00:39:23 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 00:39:25 - INFO - codeparrot_training - Step 29954: {'lr': 0.0004572640091272066, 'samples': 15336960, 'steps': 29954, 'loss/train': 1.34402334690094}
-03/05/2022 00:39:28 - INFO - codeparrot_training - Step 29955: {'lr': 0.000457261041732004, 'samples': 15337472, 'steps': 29955, 'loss/train': 2.5742132663726807}
-03/05/2022 00:39:31 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/05/2022 00:39:34 - INFO - codeparrot_training - Step 29956: {'lr': 0.0004572580742434127, 'samples': 15337984, 'steps': 29956, 'loss/train': 2.3087236881256104}
-03/05/2022 00:39:37 - INFO - codeparrot_training - Step 29957: {'lr': 0.00045725510666143424, 'samples': 15338496, 'steps': 29957, 'loss/train': 0.8209245800971985}
-03/05/2022 00:39:40 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/05/2022 00:39:42 - INFO - codeparrot_training - Step 29958: {'lr': 0.0004572521389860697, 'samples': 15339008, 'steps': 29958, 'loss/train': 1.744937539100647}
-03/05/2022 00:39:45 - INFO - codeparrot_training - Step 29959: {'lr': 0.00045724917121732055, 'samples': 15339520, 'steps': 29959, 'loss/train': 1.4647159576416016}
-03/05/2022 00:39:48 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 00:39:51 - INFO - codeparrot_training - Step 29960: {'lr': 0.0004572462033551882, 'samples': 15340032, 'steps': 29960, 'loss/train': 1.565503716468811}
-03/05/2022 00:39:54 - INFO - codeparrot_training - Step 29961: {'lr': 0.00045724323539967385, 'samples': 15340544, 'steps': 29961, 'loss/train': 1.8964900970458984}
-03/05/2022 00:39:56 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/05/2022 00:39:59 - INFO - codeparrot_training - Step 29962: {'lr': 0.00045724026735077886, 'samples': 15341056, 'steps': 29962, 'loss/train': 2.7797446250915527}
-03/05/2022 00:40:02 - INFO - codeparrot_training - Step 29963: {'lr': 0.00045723729920850464, 'samples': 15341568, 'steps': 29963, 'loss/train': 0.4381738603115082}
-03/05/2022 00:40:05 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 00:40:08 - INFO - codeparrot_training - Step 29964: {'lr': 0.00045723433097285247, 'samples': 15342080, 'steps': 29964, 'loss/train': 1.5689224004745483}
-03/05/2022 00:40:11 - INFO - codeparrot_training - Step 29965: {'lr': 0.0004572313626438238, 'samples': 15342592, 'steps': 29965, 'loss/train': 1.2798312902450562}
-03/05/2022 00:40:14 - INFO - codeparrot_training - Step 29966: {'lr': 0.00045722839422141984, 'samples': 15343104, 'steps': 29966, 'loss/train': 2.160632610321045}
-03/05/2022 00:40:14 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/05/2022 00:40:20 - INFO - codeparrot_training - Step 29967: {'lr': 0.000457225425705642, 'samples': 15343616, 'steps': 29967, 'loss/train': 1.5215989351272583}
-03/05/2022 00:40:23 - INFO - codeparrot_training - Step 29968: {'lr': 0.0004572224570964915, 'samples': 15344128, 'steps': 29968, 'loss/train': 1.860026240348816}
-03/05/2022 00:40:23 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/05/2022 00:40:28 - INFO - codeparrot_training - Step 29969: {'lr': 0.0004572194883939697, 'samples': 15344640, 'steps': 29969, 'loss/train': 1.383028507232666}
-03/05/2022 00:40:31 - INFO - codeparrot_training - Step 29970: {'lr': 0.0004572165195980781, 'samples': 15345152, 'steps': 29970, 'loss/train': 1.851492166519165}
-03/05/2022 00:40:31 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/05/2022 00:40:36 - INFO - codeparrot_training - Step 29971: {'lr': 0.0004572135507088179, 'samples': 15345664, 'steps': 29971, 'loss/train': 1.6599832773208618}
-03/05/2022 00:40:40 - INFO - codeparrot_training - Step 29972: {'lr': 0.00045721058172619043, 'samples': 15346176, 'steps': 29972, 'loss/train': 1.6131421327590942}
-03/05/2022 00:40:40 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/05/2022 00:40:45 - INFO - codeparrot_training - Step 29973: {'lr': 0.0004572076126501972, 'samples': 15346688, 'steps': 29973, 'loss/train': 1.864082932472229}
-03/05/2022 00:40:48 - INFO - codeparrot_training - Step 29974: {'lr': 0.00045720464348083937, 'samples': 15347200, 'steps': 29974, 'loss/train': 2.0404343605041504}
-03/05/2022 00:40:49 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/05/2022 00:40:53 - INFO - codeparrot_training - Step 29975: {'lr': 0.0004572016742181182, 'samples': 15347712, 'steps': 29975, 'loss/train': 1.6090868711471558}
-03/05/2022 00:40:57 - INFO - codeparrot_training - Step 29976: {'lr': 0.0004571987048620353, 'samples': 15348224, 'steps': 29976, 'loss/train': 1.8193855285644531}
-03/05/2022 00:40:58 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 00:41:02 - INFO - codeparrot_training - Step 29977: {'lr': 0.0004571957354125918, 'samples': 15348736, 'steps': 29977, 'loss/train': 3.0422651767730713}
-03/05/2022 00:41:05 - INFO - codeparrot_training - Step 29978: {'lr': 0.00045719276586978907, 'samples': 15349248, 'steps': 29978, 'loss/train': 2.032134532928467}
-03/05/2022 00:41:06 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/05/2022 00:41:10 - INFO - codeparrot_training - Step 29979: {'lr': 0.00045718979623362855, 'samples': 15349760, 'steps': 29979, 'loss/train': 2.4302265644073486}
-03/05/2022 00:41:14 - INFO - codeparrot_training - Step 29980: {'lr': 0.00045718682650411146, 'samples': 15350272, 'steps': 29980, 'loss/train': 0.4171745181083679}
-03/05/2022 00:41:14 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/05/2022 00:41:19 - INFO - codeparrot_training - Step 29981: {'lr': 0.0004571838566812392, 'samples': 15350784, 'steps': 29981, 'loss/train': 1.4371411800384521}
-03/05/2022 00:41:22 - INFO - codeparrot_training - Step 29982: {'lr': 0.00045718088676501305, 'samples': 15351296, 'steps': 29982, 'loss/train': 1.8016290664672852}
-03/05/2022 00:41:23 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/05/2022 00:41:27 - INFO - codeparrot_training - Step 29983: {'lr': 0.0004571779167554344, 'samples': 15351808, 'steps': 29983, 'loss/train': 0.9044046998023987}
-03/05/2022 00:41:30 - INFO - codeparrot_training - Step 29984: {'lr': 0.0004571749466525046, 'samples': 15352320, 'steps': 29984, 'loss/train': 1.9681452512741089}
-03/05/2022 00:41:31 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 00:41:36 - INFO - codeparrot_training - Step 29985: {'lr': 0.000457171976456225, 'samples': 15352832, 'steps': 29985, 'loss/train': 1.8412591218948364}
-03/05/2022 00:41:39 - INFO - codeparrot_training - Step 29986: {'lr': 0.00045716900616659686, 'samples': 15353344, 'steps': 29986, 'loss/train': 1.3607157468795776}
-03/05/2022 00:41:39 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/05/2022 00:41:44 - INFO - codeparrot_training - Step 29987: {'lr': 0.00045716603578362157, 'samples': 15353856, 'steps': 29987, 'loss/train': 1.7665804624557495}
-03/05/2022 00:41:47 - INFO - codeparrot_training - Step 29988: {'lr': 0.00045716306530730043, 'samples': 15354368, 'steps': 29988, 'loss/train': 1.1285563707351685}
-03/05/2022 00:41:48 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/05/2022 00:41:53 - INFO - codeparrot_training - Step 29989: {'lr': 0.00045716009473763486, 'samples': 15354880, 'steps': 29989, 'loss/train': 2.236178159713745}
-03/05/2022 00:41:56 - INFO - codeparrot_training - Step 29990: {'lr': 0.0004571571240746262, 'samples': 15355392, 'steps': 29990, 'loss/train': 2.2003471851348877}
-03/05/2022 00:41:56 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/05/2022 00:42:01 - INFO - codeparrot_training - Step 29991: {'lr': 0.00045715415331827564, 'samples': 15355904, 'steps': 29991, 'loss/train': 1.7204599380493164}
-03/05/2022 00:42:04 - INFO - codeparrot_training - Step 29992: {'lr': 0.00045715118246858466, 'samples': 15356416, 'steps': 29992, 'loss/train': 2.0565106868743896}
-03/05/2022 00:42:05 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/05/2022 00:42:09 - INFO - codeparrot_training - Step 29993: {'lr': 0.0004571482115255545, 'samples': 15356928, 'steps': 29993, 'loss/train': 1.5984420776367188}
-03/05/2022 00:42:13 - INFO - codeparrot_training - Step 29994: {'lr': 0.0004571452404891866, 'samples': 15357440, 'steps': 29994, 'loss/train': 1.843674659729004}
-03/05/2022 00:42:13 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/05/2022 00:42:18 - INFO - codeparrot_training - Step 29995: {'lr': 0.0004571422693594822, 'samples': 15357952, 'steps': 29995, 'loss/train': 1.3999497890472412}
-03/05/2022 00:42:21 - INFO - codeparrot_training - Step 29996: {'lr': 0.00045713929813644274, 'samples': 15358464, 'steps': 29996, 'loss/train': 1.836114525794983}
-03/05/2022 00:42:22 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/05/2022 00:42:26 - INFO - codeparrot_training - Step 29997: {'lr': 0.0004571363268200695, 'samples': 15358976, 'steps': 29997, 'loss/train': 1.7641074657440186}
-03/05/2022 00:42:30 - INFO - codeparrot_training - Step 29998: {'lr': 0.0004571333554103638, 'samples': 15359488, 'steps': 29998, 'loss/train': 1.455445408821106}
-03/05/2022 00:42:30 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/05/2022 00:42:35 - INFO - codeparrot_training - Step 29999: {'lr': 0.0004571303839073271, 'samples': 15360000, 'steps': 29999, 'loss/train': 1.5493794679641724}
-03/05/2022 00:42:35 - INFO - codeparrot_training - Evaluating and saving model checkpoint
-03/05/2022 00:42:49 - WARNING - huggingface_hub.repository - Several commits (6) will be pushed upstream.
-03/05/2022 00:42:49 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
-03/05/2022 00:43:16 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/cm_code_clippy
-   20b2be6..8908229  glowing-puddle-3 -> glowing-puddle-3
-
-03/05/2022 00:43:20 - INFO - codeparrot_training - Step 30000: {'lr': 0.00045712741231096054, 'samples': 15360512, 'steps': 30000, 'loss/train': 1.8289461135864258}
-03/05/2022 00:43:20 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/05/2022 00:43:26 - INFO - codeparrot_training - Step 30001: {'lr': 0.0004571244406212656, 'samples': 15361024, 'steps': 30001, 'loss/train': 1.2173447608947754}
-03/05/2022 00:43:29 - INFO - codeparrot_training - Step 30002: {'lr': 0.00045712146883824357, 'samples': 15361536, 'steps': 30002, 'loss/train': 1.5588682889938354}
-03/05/2022 00:43:29 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/05/2022 00:43:34 - INFO - codeparrot_training - Step 30003: {'lr': 0.00045711849696189585, 'samples': 15362048, 'steps': 30003, 'loss/train': 1.0836864709854126}
-03/05/2022 00:43:37 - INFO - codeparrot_training - Step 30004: {'lr': 0.0004571155249922237, 'samples': 15362560, 'steps': 30004, 'loss/train': 1.896442174911499}
-03/05/2022 00:43:38 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/05/2022 00:43:42 - INFO - codeparrot_training - Step 30005: {'lr': 0.00045711255292922847, 'samples': 15363072, 'steps': 30005, 'loss/train': 2.269477605819702}
-03/05/2022 00:43:45 - INFO - codeparrot_training - Step 30006: {'lr': 0.00045710958077291156, 'samples': 15363584, 'steps': 30006, 'loss/train': 2.0160892009735107}
-03/05/2022 00:43:46 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/05/2022 00:43:51 - INFO - codeparrot_training - Step 30007: {'lr': 0.00045710660852327423, 'samples': 15364096, 'steps': 30007, 'loss/train': 1.6335222721099854}
-03/05/2022 00:43:54 - INFO - codeparrot_training - Step 30008: {'lr': 0.00045710363618031783, 'samples': 15364608, 'steps': 30008, 'loss/train': 1.1586971282958984}
-03/05/2022 00:43:54 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/05/2022 00:43:59 - INFO - codeparrot_training - Step 30009: {'lr': 0.0004571006637440438, 'samples': 15365120, 'steps': 30009, 'loss/train': 1.6179038286209106}
-03/05/2022 00:44:02 - INFO - codeparrot_training - Step 30010: {'lr': 0.00045709769121445335, 'samples': 15365632, 'steps': 30010, 'loss/train': 2.0572926998138428}
-03/05/2022 00:44:03 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/05/2022 00:44:08 - INFO - codeparrot_training - Step 30011: {'lr': 0.00045709471859154793, 'samples': 15366144, 'steps': 30011, 'loss/train': 1.8443877696990967}
-03/05/2022 00:44:11 - INFO - codeparrot_training - Step 30012: {'lr': 0.0004570917458753288, 'samples': 15366656, 'steps': 30012, 'loss/train': 1.659393310546875}
-03/05/2022 00:44:12 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/05/2022 00:44:16 - INFO - codeparrot_training - Step 30013: {'lr': 0.00045708877306579733, 'samples': 15367168, 'steps': 30013, 'loss/train': 1.1356165409088135}
-03/05/2022 00:44:19 - INFO - codeparrot_training - Step 30014: {'lr': 0.00045708580016295486, 'samples': 15367680, 'steps': 30014, 'loss/train': 1.8352152109146118}
-03/05/2022 00:44:20 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/05/2022 00:44:24 - INFO - codeparrot_training - Step 30015: {'lr': 0.0004570828271668027, 'samples': 15368192, 'steps': 30015, 'loss/train': 1.8785282373428345}
-03/05/2022 00:44:28 - INFO - codeparrot_training - Step 30016: {'lr': 0.0004570798540773422, 'samples': 15368704, 'steps': 30016, 'loss/train': 1.9754853248596191}
-03/05/2022 00:44:28 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/05/2022 00:44:33 - INFO - codeparrot_training - Step 30017: {'lr': 0.0004570768808945748, 'samples': 15369216, 'steps': 30017, 'loss/train': 1.8309119939804077}
-03/05/2022 00:44:36 - INFO - codeparrot_training - Step 30018: {'lr': 0.00045707390761850163, 'samples': 15369728, 'steps': 30018, 'loss/train': 2.398773670196533}
-03/05/2022 00:44:37 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/05/2022 00:44:41 - INFO - codeparrot_training - Step 30019: {'lr': 0.00045707093424912426, 'samples': 15370240, 'steps': 30019, 'loss/train': 1.9269746541976929}
-03/05/2022 00:44:45 - INFO - codeparrot_training - Step 30020: {'lr': 0.00045706796078644386, 'samples': 15370752, 'steps': 30020, 'loss/train': 2.2926995754241943}
-03/05/2022 00:44:45 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 00:44:50 - INFO - codeparrot_training - Step 30021: {'lr': 0.00045706498723046185, 'samples': 15371264, 'steps': 30021, 'loss/train': 1.957943320274353}
-03/05/2022 00:44:53 - INFO - codeparrot_training - Step 30022: {'lr': 0.0004570620135811795, 'samples': 15371776, 'steps': 30022, 'loss/train': 1.5461033582687378}
-03/05/2022 00:44:53 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/05/2022 00:44:59 - INFO - codeparrot_training - Step 30023: {'lr': 0.0004570590398385983, 'samples': 15372288, 'steps': 30023, 'loss/train': 1.4753776788711548}
-03/05/2022 00:45:02 - INFO - codeparrot_training - Step 30024: {'lr': 0.0004570560660027194, 'samples': 15372800, 'steps': 30024, 'loss/train': 1.3805350065231323}
-03/05/2022 00:45:02 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/05/2022 00:45:07 - INFO - codeparrot_training - Step 30025: {'lr': 0.00045705309207354433, 'samples': 15373312, 'steps': 30025, 'loss/train': 1.6123640537261963}
-03/05/2022 00:45:10 - INFO - codeparrot_training - Step 30026: {'lr': 0.00045705011805107426, 'samples': 15373824, 'steps': 30026, 'loss/train': 1.850448489189148}
-03/05/2022 00:45:10 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/05/2022 00:45:16 - INFO - codeparrot_training - Step 30027: {'lr': 0.00045704714393531064, 'samples': 15374336, 'steps': 30027, 'loss/train': 0.881676971912384}
-03/05/2022 00:45:19 - INFO - codeparrot_training - Step 30028: {'lr': 0.00045704416972625474, 'samples': 15374848, 'steps': 30028, 'loss/train': 2.1063857078552246}
-03/05/2022 00:45:19 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/05/2022 00:45:24 - INFO - codeparrot_training - Step 30029: {'lr': 0.000457041195423908, 'samples': 15375360, 'steps': 30029, 'loss/train': 0.9632497429847717}
-03/05/2022 00:45:28 - INFO - codeparrot_training - Step 30030: {'lr': 0.0004570382210282716, 'samples': 15375872, 'steps': 30030, 'loss/train': 1.6717524528503418}
-03/05/2022 00:45:28 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 00:45:33 - INFO - codeparrot_training - Step 30031: {'lr': 0.00045703524653934705, 'samples': 15376384, 'steps': 30031, 'loss/train': 1.5573110580444336}
-03/05/2022 00:45:36 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/05/2022 00:45:38 - INFO - codeparrot_training - Step 30032: {'lr': 0.0004570322719571355, 'samples': 15376896, 'steps': 30032, 'loss/train': 1.7397286891937256}
-03/05/2022 00:45:41 - INFO - codeparrot_training - Step 30033: {'lr': 0.00045702929728163845, 'samples': 15377408, 'steps': 30033, 'loss/train': 1.4734880924224854}
-03/05/2022 00:45:44 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/05/2022 00:45:46 - INFO - codeparrot_training - Step 30034: {'lr': 0.00045702632251285727, 'samples': 15377920, 'steps': 30034, 'loss/train': 2.11061954498291}
-03/05/2022 00:45:50 - INFO - codeparrot_training - Step 30035: {'lr': 0.0004570233476507931, 'samples': 15378432, 'steps': 30035, 'loss/train': 1.3703136444091797}
-03/05/2022 00:45:52 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/05/2022 00:45:55 - INFO - codeparrot_training - Step 30036: {'lr': 0.0004570203726954475, 'samples': 15378944, 'steps': 30036, 'loss/train': 2.3308465480804443}
-03/05/2022 00:45:58 - INFO - codeparrot_training - Step 30037: {'lr': 0.0004570173976468217, 'samples': 15379456, 'steps': 30037, 'loss/train': 1.9480481147766113}
-03/05/2022 00:46:01 - INFO - codeparrot_training - Step 30038: {'lr': 0.0004570144225049171, 'samples': 15379968, 'steps': 30038, 'loss/train': 0.07623183727264404}
-03/05/2022 00:46:02 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/05/2022 00:46:07 - INFO - codeparrot_training - Step 30039: {'lr': 0.00045701144726973487, 'samples': 15380480, 'steps': 30039, 'loss/train': 1.9388179779052734}
-03/05/2022 00:46:10 - INFO - codeparrot_training - Step 30040: {'lr': 0.0004570084719412766, 'samples': 15380992, 'steps': 30040, 'loss/train': 2.3384456634521484}
-03/05/2022 00:46:10 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/05/2022 00:46:15 - INFO - codeparrot_training - Step 30041: {'lr': 0.00045700549651954344, 'samples': 15381504, 'steps': 30041, 'loss/train': 1.5204285383224487}
-03/05/2022 00:46:18 - INFO - codeparrot_training - Step 30042: {'lr': 0.0004570025210045368, 'samples': 15382016, 'steps': 30042, 'loss/train': 1.5184179544448853}
-03/05/2022 00:46:19 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/05/2022 00:46:24 - INFO - codeparrot_training - Step 30043: {'lr': 0.00045699954539625803, 'samples': 15382528, 'steps': 30043, 'loss/train': 1.788817048072815}
-03/05/2022 00:46:27 - INFO - codeparrot_training - Step 30044: {'lr': 0.0004569965696947085, 'samples': 15383040, 'steps': 30044, 'loss/train': 1.287003517150879}
-03/05/2022 00:46:27 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/05/2022 00:46:33 - INFO - codeparrot_training - Step 30045: {'lr': 0.00045699359389988944, 'samples': 15383552, 'steps': 30045, 'loss/train': 1.7901946306228638}
-03/05/2022 00:46:36 - INFO - codeparrot_training - Step 30046: {'lr': 0.0004569906180118023, 'samples': 15384064, 'steps': 30046, 'loss/train': 1.7433677911758423}
-03/05/2022 00:46:38 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/05/2022 00:46:41 - INFO - codeparrot_training - Step 30047: {'lr': 0.0004569876420304484, 'samples': 15384576, 'steps': 30047, 'loss/train': 2.262643337249756}
-03/05/2022 00:46:44 - INFO - codeparrot_training - Step 30048: {'lr': 0.000456984665955829, 'samples': 15385088, 'steps': 30048, 'loss/train': 1.3046284914016724}
-03/05/2022 00:46:46 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/05/2022 00:46:49 - INFO - codeparrot_training - Step 30049: {'lr': 0.00045698168978794553, 'samples': 15385600, 'steps': 30049, 'loss/train': 2.065197467803955}
-03/05/2022 00:46:53 - INFO - codeparrot_training - Step 30050: {'lr': 0.0004569787135267993, 'samples': 15386112, 'steps': 30050, 'loss/train': 1.3863437175750732}
-03/05/2022 00:46:54 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/05/2022 00:46:58 - INFO - codeparrot_training - Step 30051: {'lr': 0.00045697573717239174, 'samples': 15386624, 'steps': 30051, 'loss/train': 2.091391086578369}
-03/05/2022 00:47:01 - INFO - codeparrot_training - Step 30052: {'lr': 0.0004569727607247239, 'samples': 15387136, 'steps': 30052, 'loss/train': 1.4294064044952393}
-03/05/2022 00:47:02 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/05/2022 00:47:06 - INFO - codeparrot_training - Step 30053: {'lr': 0.00045696978418379754, 'samples': 15387648, 'steps': 30053, 'loss/train': 2.2440483570098877}
-03/05/2022 00:47:09 - INFO - codeparrot_training - Step 30054: {'lr': 0.0004569668075496137, 'samples': 15388160, 'steps': 30054, 'loss/train': 1.721880316734314}
-03/05/2022 00:47:10 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/05/2022 00:47:15 - INFO - codeparrot_training - Step 30055: {'lr': 0.00045696383082217387, 'samples': 15388672, 'steps': 30055, 'loss/train': 1.45264732837677}
-03/05/2022 00:47:18 - INFO - codeparrot_training - Step 30056: {'lr': 0.00045696085400147925, 'samples': 15389184, 'steps': 30056, 'loss/train': 1.2470375299453735}
-03/05/2022 00:47:19 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/05/2022 00:47:23 - INFO - codeparrot_training - Step 30057: {'lr': 0.00045695787708753126, 'samples': 15389696, 'steps': 30057, 'loss/train': 1.4519813060760498}
-03/05/2022 00:47:26 - INFO - codeparrot_training - Step 30058: {'lr': 0.0004569549000803313, 'samples': 15390208, 'steps': 30058, 'loss/train': 0.4629649221897125}
-03/05/2022 00:47:27 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/05/2022 00:47:31 - INFO - codeparrot_training - Step 30059: {'lr': 0.00045695192297988066, 'samples': 15390720, 'steps': 30059, 'loss/train': 2.955383062362671}
-03/05/2022 00:47:35 - INFO - codeparrot_training - Step 30060: {'lr': 0.00045694894578618064, 'samples': 15391232, 'steps': 30060, 'loss/train': 1.5059194564819336}
-03/05/2022 00:47:35 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/05/2022 00:47:40 - INFO - codeparrot_training - Step 30061: {'lr': 0.00045694596849923263, 'samples': 15391744, 'steps': 30061, 'loss/train': 1.7649555206298828}
-03/05/2022 00:47:43 - INFO - codeparrot_training - Step 30062: {'lr': 0.0004569429911190379, 'samples': 15392256, 'steps': 30062, 'loss/train': 1.6643859148025513}
-03/05/2022 00:47:44 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/05/2022 00:47:48 - INFO - codeparrot_training - Step 30063: {'lr': 0.00045694001364559797, 'samples': 15392768, 'steps': 30063, 'loss/train': 1.5236775875091553}
-03/05/2022 00:47:52 - INFO - codeparrot_training - Step 30064: {'lr': 0.00045693703607891403, 'samples': 15393280, 'steps': 30064, 'loss/train': 2.0967564582824707}
-03/05/2022 00:47:52 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/05/2022 00:47:57 - INFO - codeparrot_training - Step 30065: {'lr': 0.0004569340584189874, 'samples': 15393792, 'steps': 30065, 'loss/train': 1.8825595378875732}
-03/05/2022 00:48:00 - INFO - codeparrot_training - Step 30066: {'lr': 0.0004569310806658195, 'samples': 15394304, 'steps': 30066, 'loss/train': 1.6849169731140137}
-03/05/2022 00:48:00 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/05/2022 00:48:05 - INFO - codeparrot_training - Step 30067: {'lr': 0.0004569281028194117, 'samples': 15394816, 'steps': 30067, 'loss/train': 2.5284647941589355}
-03/05/2022 00:48:09 - INFO - codeparrot_training - Step 30068: {'lr': 0.0004569251248797652, 'samples': 15395328, 'steps': 30068, 'loss/train': 1.8243889808654785}
-03/05/2022 00:48:10 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/05/2022 00:48:14 - INFO - codeparrot_training - Step 30069: {'lr': 0.0004569221468468815, 'samples': 15395840, 'steps': 30069, 'loss/train': 0.8982431888580322}
-03/05/2022 00:48:17 - INFO - codeparrot_training - Step 30070: {'lr': 0.0004569191687207618, 'samples': 15396352, 'steps': 30070, 'loss/train': 3.1284542083740234}
-03/05/2022 00:48:19 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/05/2022 00:48:23 - INFO - codeparrot_training - Step 30071: {'lr': 0.0004569161905014076, 'samples': 15396864, 'steps': 30071, 'loss/train': 0.5278277397155762}
-03/05/2022 00:48:26 - INFO - codeparrot_training - Step 30072: {'lr': 0.0004569132121888201, 'samples': 15397376, 'steps': 30072, 'loss/train': 2.1388659477233887}
-03/05/2022 00:48:28 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 00:48:31 - INFO - codeparrot_training - Step 30073: {'lr': 0.0004569102337830007, 'samples': 15397888, 'steps': 30073, 'loss/train': 1.5493289232254028}
-03/05/2022 00:48:34 - INFO - codeparrot_training - Step 30074: {'lr': 0.00045690725528395077, 'samples': 15398400, 'steps': 30074, 'loss/train': 3.477476119995117}
-03/05/2022 00:48:36 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 00:48:39 - INFO - codeparrot_training - Step 30075: {'lr': 0.0004569042766916717, 'samples': 15398912, 'steps': 30075, 'loss/train': 1.8774348497390747}
-03/05/2022 00:48:43 - INFO - codeparrot_training - Step 30076: {'lr': 0.0004569012980061646, 'samples': 15399424, 'steps': 30076, 'loss/train': 1.8760998249053955}
-03/05/2022 00:48:45 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 00:48:48 - INFO - codeparrot_training - Step 30077: {'lr': 0.00045689831922743107, 'samples': 15399936, 'steps': 30077, 'loss/train': 1.7275433540344238}
-03/05/2022 00:48:51 - INFO - codeparrot_training - Step 30078: {'lr': 0.0004568953403554723, 'samples': 15400448, 'steps': 30078, 'loss/train': 1.9771796464920044}
-03/05/2022 00:48:53 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/05/2022 00:48:56 - INFO - codeparrot_training - Step 30079: {'lr': 0.0004568923613902897, 'samples': 15400960, 'steps': 30079, 'loss/train': 1.8651039600372314}
-03/05/2022 00:48:59 - INFO - codeparrot_training - Step 30080: {'lr': 0.0004568893823318846, 'samples': 15401472, 'steps': 30080, 'loss/train': 1.0507383346557617}
-03/05/2022 00:49:01 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/05/2022 00:49:05 - INFO - codeparrot_training - Step 30081: {'lr': 0.0004568864031802583, 'samples': 15401984, 'steps': 30081, 'loss/train': 2.374959945678711}
-03/05/2022 00:49:08 - INFO - codeparrot_training - Step 30082: {'lr': 0.00045688342393541227, 'samples': 15402496, 'steps': 30082, 'loss/train': 0.5805590152740479}
-03/05/2022 00:49:10 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/05/2022 00:49:13 - INFO - codeparrot_training - Step 30083: {'lr': 0.00045688044459734766, 'samples': 15403008, 'steps': 30083, 'loss/train': 1.5638983249664307}
-03/05/2022 00:49:16 - INFO - codeparrot_training - Step 30084: {'lr': 0.000456877465166066, 'samples': 15403520, 'steps': 30084, 'loss/train': 0.7802882790565491}
-03/05/2022 00:49:18 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/05/2022 00:49:21 - INFO - codeparrot_training - Step 30085: {'lr': 0.0004568744856415685, 'samples': 15404032, 'steps': 30085, 'loss/train': 1.0853203535079956}
-03/05/2022 00:49:25 - INFO - codeparrot_training - Step 30086: {'lr': 0.0004568715060238565, 'samples': 15404544, 'steps': 30086, 'loss/train': 1.3193738460540771}
-03/05/2022 00:49:26 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/05/2022 00:49:30 - INFO - codeparrot_training - Step 30087: {'lr': 0.0004568685263129315, 'samples': 15405056, 'steps': 30087, 'loss/train': 1.794023871421814}
-03/05/2022 00:49:33 - INFO - codeparrot_training - Step 30088: {'lr': 0.00045686554650879464, 'samples': 15405568, 'steps': 30088, 'loss/train': 1.9164760112762451}
-03/05/2022 00:49:36 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/05/2022 00:49:38 - INFO - codeparrot_training - Step 30089: {'lr': 0.0004568625666114474, 'samples': 15406080, 'steps': 30089, 'loss/train': 1.6596910953521729}
-03/05/2022 00:49:42 - INFO - codeparrot_training - Step 30090: {'lr': 0.00045685958662089113, 'samples': 15406592, 'steps': 30090, 'loss/train': 1.7234231233596802}
-03/05/2022 00:49:44 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 00:49:47 - INFO - codeparrot_training - Step 30091: {'lr': 0.000456856606537127, 'samples': 15407104, 'steps': 30091, 'loss/train': 2.4382810592651367}
-03/05/2022 00:49:50 - INFO - codeparrot_training - Step 30092: {'lr': 0.00045685362636015657, 'samples': 15407616, 'steps': 30092, 'loss/train': 1.4692848920822144}
-03/05/2022 00:49:52 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/05/2022 00:49:55 - INFO - codeparrot_training - Step 30093: {'lr': 0.00045685064608998107, 'samples': 15408128, 'steps': 30093, 'loss/train': 1.6077817678451538}
-03/05/2022 00:49:58 - INFO - codeparrot_training - Step 30094: {'lr': 0.00045684766572660185, 'samples': 15408640, 'steps': 30094, 'loss/train': 1.5444180965423584}
-03/05/2022 00:50:00 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/05/2022 00:50:04 - INFO - codeparrot_training - Step 30095: {'lr': 0.0004568446852700203, 'samples': 15409152, 'steps': 30095, 'loss/train': 1.5687755346298218}
-03/05/2022 00:50:07 - INFO - codeparrot_training - Step 30096: {'lr': 0.00045684170472023766, 'samples': 15409664, 'steps': 30096, 'loss/train': 2.0847253799438477}
-03/05/2022 00:50:09 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/05/2022 00:50:12 - INFO - codeparrot_training - Step 30097: {'lr': 0.00045683872407725534, 'samples': 15410176, 'steps': 30097, 'loss/train': 2.2411348819732666}
-03/05/2022 00:50:15 - INFO - codeparrot_training - Step 30098: {'lr': 0.00045683574334107473, 'samples': 15410688, 'steps': 30098, 'loss/train': 1.59357488155365}
-03/05/2022 00:50:19 - INFO - codeparrot_training - Step 30099: {'lr': 0.00045683276251169713, 'samples': 15411200, 'steps': 30099, 'loss/train': 2.1585466861724854}
-03/05/2022 00:50:19 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/05/2022 00:50:24 - INFO - codeparrot_training - Step 30100: {'lr': 0.00045682978158912384, 'samples': 15411712, 'steps': 30100, 'loss/train': 0.8039388060569763}
-03/05/2022 00:50:27 - INFO - codeparrot_training - Step 30101: {'lr': 0.0004568268005733562, 'samples': 15412224, 'steps': 30101, 'loss/train': 1.82028067111969}
-03/05/2022 00:50:27 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/05/2022 00:50:32 - INFO - codeparrot_training - Step 30102: {'lr': 0.0004568238194643958, 'samples': 15412736, 'steps': 30102, 'loss/train': 1.6911276578903198}
-03/05/2022 00:50:36 - INFO - codeparrot_training - Step 30103: {'lr': 0.00045682083826224356, 'samples': 15413248, 'steps': 30103, 'loss/train': 1.6601359844207764}
-03/05/2022 00:50:36 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/05/2022 00:50:41 - INFO - codeparrot_training - Step 30104: {'lr': 0.00045681785696690113, 'samples': 15413760, 'steps': 30104, 'loss/train': 1.8160486221313477}
-03/05/2022 00:50:44 - INFO - codeparrot_training - Step 30105: {'lr': 0.0004568148755783698, 'samples': 15414272, 'steps': 30105, 'loss/train': 1.6059305667877197}
-03/05/2022 00:50:46 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 00:50:50 - INFO - codeparrot_training - Step 30106: {'lr': 0.00045681189409665083, 'samples': 15414784, 'steps': 30106, 'loss/train': 2.16241717338562}
-03/05/2022 00:50:53 - INFO - codeparrot_training - Step 30107: {'lr': 0.00045680891252174557, 'samples': 15415296, 'steps': 30107, 'loss/train': 1.1611987352371216}
-03/05/2022 00:50:54 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 00:50:58 - INFO - codeparrot_training - Step 30108: {'lr': 0.0004568059308536554, 'samples': 15415808, 'steps': 30108, 'loss/train': 1.2094054222106934}
-03/05/2022 00:51:01 - INFO - codeparrot_training - Step 30109: {'lr': 0.00045680294909238175, 'samples': 15416320, 'steps': 30109, 'loss/train': 2.348546266555786}
-03/05/2022 00:51:02 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/05/2022 00:51:06 - INFO - codeparrot_training - Step 30110: {'lr': 0.00045679996723792585, 'samples': 15416832, 'steps': 30110, 'loss/train': 1.7360273599624634}
-03/05/2022 00:51:10 - INFO - codeparrot_training - Step 30111: {'lr': 0.00045679698529028906, 'samples': 15417344, 'steps': 30111, 'loss/train': 1.3415448665618896}
-03/05/2022 00:51:11 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/05/2022 00:51:15 - INFO - codeparrot_training - Step 30112: {'lr': 0.00045679400324947274, 'samples': 15417856, 'steps': 30112, 'loss/train': 1.991532325744629}
-03/05/2022 00:51:18 - INFO - codeparrot_training - Step 30113: {'lr': 0.00045679102111547825, 'samples': 15418368, 'steps': 30113, 'loss/train': 1.521023154258728}
-03/05/2022 00:51:19 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/05/2022 00:51:23 - INFO - codeparrot_training - Step 30114: {'lr': 0.00045678803888830687, 'samples': 15418880, 'steps': 30114, 'loss/train': 1.7485442161560059}
-03/05/2022 00:51:26 - INFO - codeparrot_training - Step 30115: {'lr': 0.0004567850565679601, 'samples': 15419392, 'steps': 30115, 'loss/train': 0.4203520119190216}
-03/05/2022 00:51:27 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/05/2022 00:51:32 - INFO - codeparrot_training - Step 30116: {'lr': 0.00045678207415443913, 'samples': 15419904, 'steps': 30116, 'loss/train': 1.745429515838623}
-03/05/2022 00:51:35 - INFO - codeparrot_training - Step 30117: {'lr': 0.0004567790916477453, 'samples': 15420416, 'steps': 30117, 'loss/train': 0.867196798324585}
-03/05/2022 00:51:36 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 00:51:40 - INFO - codeparrot_training - Step 30118: {'lr': 0.00045677610904788004, 'samples': 15420928, 'steps': 30118, 'loss/train': 2.043165445327759}
-03/05/2022 00:51:43 - INFO - codeparrot_training - Step 30119: {'lr': 0.00045677312635484466, 'samples': 15421440, 'steps': 30119, 'loss/train': 1.6716259717941284}
-03/05/2022 00:51:44 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/05/2022 00:51:49 - INFO - codeparrot_training - Step 30120: {'lr': 0.00045677014356864043, 'samples': 15421952, 'steps': 30120, 'loss/train': 1.5415599346160889}
-03/05/2022 00:51:52 - INFO - codeparrot_training - Step 30121: {'lr': 0.0004567671606892688, 'samples': 15422464, 'steps': 30121, 'loss/train': 2.024001121520996}
-03/05/2022 00:51:53 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/05/2022 00:51:57 - INFO - codeparrot_training - Step 30122: {'lr': 0.00045676417771673116, 'samples': 15422976, 'steps': 30122, 'loss/train': 1.776038646697998}
-03/05/2022 00:52:01 - INFO - codeparrot_training - Step 30123: {'lr': 0.0004567611946510287, 'samples': 15423488, 'steps': 30123, 'loss/train': 2.036388874053955}
-03/05/2022 00:52:01 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/05/2022 00:52:06 - INFO - codeparrot_training - Step 30124: {'lr': 0.00045675821149216285, 'samples': 15424000, 'steps': 30124, 'loss/train': 2.1159322261810303}
-03/05/2022 00:52:09 - INFO - codeparrot_training - Step 30125: {'lr': 0.00045675522824013495, 'samples': 15424512, 'steps': 30125, 'loss/train': 2.169635534286499}
-03/05/2022 00:52:09 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/05/2022 00:52:14 - INFO - codeparrot_training - Step 30126: {'lr': 0.00045675224489494633, 'samples': 15425024, 'steps': 30126, 'loss/train': 1.9738236665725708}
-03/05/2022 00:52:17 - INFO - codeparrot_training - Step 30127: {'lr': 0.00045674926145659834, 'samples': 15425536, 'steps': 30127, 'loss/train': 1.6067774295806885}
-03/05/2022 00:52:18 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/05/2022 00:52:23 - INFO - codeparrot_training - Step 30128: {'lr': 0.0004567462779250923, 'samples': 15426048, 'steps': 30128, 'loss/train': 1.0786906480789185}
-03/05/2022 00:52:26 - INFO - codeparrot_training - Step 30129: {'lr': 0.0004567432943004296, 'samples': 15426560, 'steps': 30129, 'loss/train': 1.6639996767044067}
-03/05/2022 00:52:26 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/05/2022 00:52:31 - INFO - codeparrot_training - Step 30130: {'lr': 0.00045674031058261157, 'samples': 15427072, 'steps': 30130, 'loss/train': 0.2703652083873749}
-03/05/2022 00:52:34 - INFO - codeparrot_training - Step 30131: {'lr': 0.0004567373267716395, 'samples': 15427584, 'steps': 30131, 'loss/train': 1.8357006311416626}
-03/05/2022 00:52:35 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/05/2022 00:52:40 - INFO - codeparrot_training - Step 30132: {'lr': 0.0004567343428675148, 'samples': 15428096, 'steps': 30132, 'loss/train': 0.7730497121810913}
-03/05/2022 00:52:43 - INFO - codeparrot_training - Step 30133: {'lr': 0.00045673135887023874, 'samples': 15428608, 'steps': 30133, 'loss/train': 1.355360984802246}
-03/05/2022 00:52:43 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/05/2022 00:52:48 - INFO - codeparrot_training - Step 30134: {'lr': 0.0004567283747798128, 'samples': 15429120, 'steps': 30134, 'loss/train': 1.4444273710250854}
-03/05/2022 00:52:51 - INFO - codeparrot_training - Step 30135: {'lr': 0.0004567253905962383, 'samples': 15429632, 'steps': 30135, 'loss/train': 1.5038108825683594}
-03/05/2022 00:52:52 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/05/2022 00:52:57 - INFO - codeparrot_training - Step 30136: {'lr': 0.00045672240631951645, 'samples': 15430144, 'steps': 30136, 'loss/train': 2.4408342838287354}
-03/05/2022 00:53:00 - INFO - codeparrot_training - Step 30137: {'lr': 0.0004567194219496487, 'samples': 15430656, 'steps': 30137, 'loss/train': 0.2602927088737488}
-03/05/2022 00:53:01 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/05/2022 00:53:05 - INFO - codeparrot_training - Step 30138: {'lr': 0.0004567164374866363, 'samples': 15431168, 'steps': 30138, 'loss/train': 1.7092548608779907}
-03/05/2022 00:53:08 - INFO - codeparrot_training - Step 30139: {'lr': 0.00045671345293048075, 'samples': 15431680, 'steps': 30139, 'loss/train': 1.6997926235198975}
-03/05/2022 00:53:09 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/05/2022 00:53:14 - INFO - codeparrot_training - Step 30140: {'lr': 0.00045671046828118324, 'samples': 15432192, 'steps': 30140, 'loss/train': 2.019731044769287}
-03/05/2022 00:53:17 - INFO - codeparrot_training - Step 30141: {'lr': 0.0004567074835387452, 'samples': 15432704, 'steps': 30141, 'loss/train': 1.9466673135757446}
-03/05/2022 00:53:17 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/05/2022 00:53:22 - INFO - codeparrot_training - Step 30142: {'lr': 0.000456704498703168, 'samples': 15433216, 'steps': 30142, 'loss/train': 1.6673802137374878}
-03/05/2022 00:53:25 - INFO - codeparrot_training - Step 30143: {'lr': 0.0004567015137744529, 'samples': 15433728, 'steps': 30143, 'loss/train': 3.781850814819336}
-03/05/2022 00:53:26 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/05/2022 00:53:30 - INFO - codeparrot_training - Step 30144: {'lr': 0.00045669852875260134, 'samples': 15434240, 'steps': 30144, 'loss/train': 1.9569998979568481}
-03/05/2022 00:53:34 - INFO - codeparrot_training - Step 30145: {'lr': 0.00045669554363761454, 'samples': 15434752, 'steps': 30145, 'loss/train': 1.8220595121383667}
-03/05/2022 00:53:34 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/05/2022 00:53:39 - INFO - codeparrot_training - Step 30146: {'lr': 0.0004566925584294939, 'samples': 15435264, 'steps': 30146, 'loss/train': 2.322819948196411}
-03/05/2022 00:53:42 - INFO - codeparrot_training - Step 30147: {'lr': 0.00045668957312824086, 'samples': 15435776, 'steps': 30147, 'loss/train': 2.182586669921875}
-03/05/2022 00:53:42 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/05/2022 00:53:47 - INFO - codeparrot_training - Step 30148: {'lr': 0.00045668658773385663, 'samples': 15436288, 'steps': 30148, 'loss/train': 0.7960249185562134}
-03/05/2022 00:53:51 - INFO - codeparrot_training - Step 30149: {'lr': 0.00045668360224634263, 'samples': 15436800, 'steps': 30149, 'loss/train': 1.796868920326233}
-03/05/2022 00:53:51 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/05/2022 00:53:56 - INFO - codeparrot_training - Step 30150: {'lr': 0.00045668061666570027, 'samples': 15437312, 'steps': 30150, 'loss/train': 0.5574421882629395}
-03/05/2022 00:53:59 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/05/2022 00:54:01 - INFO - codeparrot_training - Step 30151: {'lr': 0.0004566776309919307, 'samples': 15437824, 'steps': 30151, 'loss/train': 1.5253926515579224}
-03/05/2022 00:54:04 - INFO - codeparrot_training - Step 30152: {'lr': 0.0004566746452250354, 'samples': 15438336, 'steps': 30152, 'loss/train': 1.9378290176391602}
-03/05/2022 00:54:07 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/05/2022 00:54:09 - INFO - codeparrot_training - Step 30153: {'lr': 0.00045667165936501573, 'samples': 15438848, 'steps': 30153, 'loss/train': 1.9853847026824951}
-03/05/2022 00:54:13 - INFO - codeparrot_training - Step 30154: {'lr': 0.000456668673411873, 'samples': 15439360, 'steps': 30154, 'loss/train': 1.8432587385177612}
-03/05/2022 00:54:15 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/05/2022 00:54:18 - INFO - codeparrot_training - Step 30155: {'lr': 0.00045666568736560853, 'samples': 15439872, 'steps': 30155, 'loss/train': 2.5243008136749268}
-03/05/2022 00:54:21 - INFO - codeparrot_training - Step 30156: {'lr': 0.0004566627012262238, 'samples': 15440384, 'steps': 30156, 'loss/train': 1.9896689653396606}
-03/05/2022 00:54:23 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/05/2022 00:54:26 - INFO - codeparrot_training - Step 30157: {'lr': 0.0004566597149937199, 'samples': 15440896, 'steps': 30157, 'loss/train': 1.7000889778137207}
-03/05/2022 00:54:29 - INFO - codeparrot_training - Step 30158: {'lr': 0.00045665672866809835, 'samples': 15441408, 'steps': 30158, 'loss/train': 2.9940712451934814}
-03/05/2022 00:54:32 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 00:54:35 - INFO - codeparrot_training - Step 30159: {'lr': 0.0004566537422493605, 'samples': 15441920, 'steps': 30159, 'loss/train': 1.5751402378082275}
-03/05/2022 00:54:38 - INFO - codeparrot_training - Step 30160: {'lr': 0.00045665075573750764, 'samples': 15442432, 'steps': 30160, 'loss/train': 2.1699953079223633}
-03/05/2022 00:54:40 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/05/2022 00:54:43 - INFO - codeparrot_training - Step 30161: {'lr': 0.00045664776913254115, 'samples': 15442944, 'steps': 30161, 'loss/train': 1.7363845109939575}
-03/05/2022 00:54:46 - INFO - codeparrot_training - Step 30162: {'lr': 0.0004566447824344624, 'samples': 15443456, 'steps': 30162, 'loss/train': 1.8542977571487427}
-03/05/2022 00:54:48 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/05/2022 00:54:52 - INFO - codeparrot_training - Step 30163: {'lr': 0.00045664179564327266, 'samples': 15443968, 'steps': 30163, 'loss/train': 2.0066847801208496}
-03/05/2022 00:54:55 - INFO - codeparrot_training - Step 30164: {'lr': 0.00045663880875897325, 'samples': 15444480, 'steps': 30164, 'loss/train': 1.7360237836837769}
-03/05/2022 00:54:57 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/05/2022 00:55:00 - INFO - codeparrot_training - Step 30165: {'lr': 0.00045663582178156564, 'samples': 15444992, 'steps': 30165, 'loss/train': 1.1062883138656616}
-03/05/2022 00:55:03 - INFO - codeparrot_training - Step 30166: {'lr': 0.00045663283471105115, 'samples': 15445504, 'steps': 30166, 'loss/train': 1.268115758895874}
-03/05/2022 00:55:05 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/05/2022 00:55:09 - INFO - codeparrot_training - Step 30167: {'lr': 0.00045662984754743106, 'samples': 15446016, 'steps': 30167, 'loss/train': 2.4817821979522705}
-03/05/2022 00:55:12 - INFO - codeparrot_training - Step 30168: {'lr': 0.00045662686029070674, 'samples': 15446528, 'steps': 30168, 'loss/train': 1.5153189897537231}
-03/05/2022 00:55:14 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/05/2022 00:55:17 - INFO - codeparrot_training - Step 30169: {'lr': 0.0004566238729408796, 'samples': 15447040, 'steps': 30169, 'loss/train': 2.1652262210845947}
-03/05/2022 00:55:20 - INFO - codeparrot_training - Step 30170: {'lr': 0.00045662088549795087, 'samples': 15447552, 'steps': 30170, 'loss/train': 0.12777474522590637}
-03/05/2022 00:55:22 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/05/2022 00:55:25 - INFO - codeparrot_training - Step 30171: {'lr': 0.000456617897961922, 'samples': 15448064, 'steps': 30171, 'loss/train': 1.5894675254821777}
-03/05/2022 00:55:29 - INFO - codeparrot_training - Step 30172: {'lr': 0.00045661491033279427, 'samples': 15448576, 'steps': 30172, 'loss/train': 2.382303476333618}
-03/05/2022 00:55:30 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 00:55:34 - INFO - codeparrot_training - Step 30173: {'lr': 0.00045661192261056905, 'samples': 15449088, 'steps': 30173, 'loss/train': 0.10404415428638458}
-03/05/2022 00:55:37 - INFO - codeparrot_training - Step 30174: {'lr': 0.00045660893479524767, 'samples': 15449600, 'steps': 30174, 'loss/train': 2.171333074569702}
-03/05/2022 00:55:39 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 00:55:42 - INFO - codeparrot_training - Step 30175: {'lr': 0.00045660594688683154, 'samples': 15450112, 'steps': 30175, 'loss/train': 0.8810412883758545}
-03/05/2022 00:55:46 - INFO - codeparrot_training - Step 30176: {'lr': 0.00045660295888532196, 'samples': 15450624, 'steps': 30176, 'loss/train': 1.6395387649536133}
-03/05/2022 00:55:47 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 00:55:51 - INFO - codeparrot_training - Step 30177: {'lr': 0.00045659997079072024, 'samples': 15451136, 'steps': 30177, 'loss/train': 1.5356953144073486}
-03/05/2022 00:55:54 - INFO - codeparrot_training - Step 30178: {'lr': 0.00045659698260302773, 'samples': 15451648, 'steps': 30178, 'loss/train': 1.5441616773605347}
-03/05/2022 00:55:56 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 00:55:59 - INFO - codeparrot_training - Step 30179: {'lr': 0.00045659399432224583, 'samples': 15452160, 'steps': 30179, 'loss/train': 1.3203091621398926}
-03/05/2022 00:56:02 - INFO - codeparrot_training - Step 30180: {'lr': 0.00045659100594837586, 'samples': 15452672, 'steps': 30180, 'loss/train': 1.2761400938034058}
-03/05/2022 00:56:04 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/05/2022 00:56:08 - INFO - codeparrot_training - Step 30181: {'lr': 0.0004565880174814192, 'samples': 15453184, 'steps': 30181, 'loss/train': 1.816937804222107}
-03/05/2022 00:56:11 - INFO - codeparrot_training - Step 30182: {'lr': 0.0004565850289213772, 'samples': 15453696, 'steps': 30182, 'loss/train': 0.7331827282905579}
-03/05/2022 00:56:13 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/05/2022 00:56:16 - INFO - codeparrot_training - Step 30183: {'lr': 0.0004565820402682511, 'samples': 15454208, 'steps': 30183, 'loss/train': 6.669641017913818}
-03/05/2022 00:56:19 - INFO - codeparrot_training - Step 30184: {'lr': 0.00045657905152204236, 'samples': 15454720, 'steps': 30184, 'loss/train': 2.00179123878479}
-03/05/2022 00:56:22 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/05/2022 00:56:25 - INFO - codeparrot_training - Step 30185: {'lr': 0.0004565760626827523, 'samples': 15455232, 'steps': 30185, 'loss/train': 1.325749397277832}
-03/05/2022 00:56:28 - INFO - codeparrot_training - Step 30186: {'lr': 0.00045657307375038226, 'samples': 15455744, 'steps': 30186, 'loss/train': 1.6459600925445557}
-03/05/2022 00:56:31 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/05/2022 00:56:33 - INFO - codeparrot_training - Step 30187: {'lr': 0.00045657008472493356, 'samples': 15456256, 'steps': 30187, 'loss/train': 1.857986330986023}
-03/05/2022 00:56:36 - INFO - codeparrot_training - Step 30188: {'lr': 0.0004565670956064075, 'samples': 15456768, 'steps': 30188, 'loss/train': 1.1490070819854736}
-03/05/2022 00:56:39 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 00:56:42 - INFO - codeparrot_training - Step 30189: {'lr': 0.00045656410639480563, 'samples': 15457280, 'steps': 30189, 'loss/train': 1.8654168844223022}
-03/05/2022 00:56:45 - INFO - codeparrot_training - Step 30190: {'lr': 0.00045656111709012906, 'samples': 15457792, 'steps': 30190, 'loss/train': 1.9297715425491333}
-03/05/2022 00:56:48 - INFO - codeparrot_training - Step 30191: {'lr': 0.00045655812769237927, 'samples': 15458304, 'steps': 30191, 'loss/train': 1.1933776140213013}
-03/05/2022 00:56:48 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/05/2022 00:56:53 - INFO - codeparrot_training - Step 30192: {'lr': 0.00045655513820155755, 'samples': 15458816, 'steps': 30192, 'loss/train': 2.049964427947998}
-03/05/2022 00:56:57 - INFO - codeparrot_training - Step 30193: {'lr': 0.00045655214861766525, 'samples': 15459328, 'steps': 30193, 'loss/train': 1.4200948476791382}
-03/05/2022 00:56:57 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 00:57:02 - INFO - codeparrot_training - Step 30194: {'lr': 0.0004565491589407038, 'samples': 15459840, 'steps': 30194, 'loss/train': 1.7983677387237549}
-03/05/2022 00:57:04 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/05/2022 00:57:07 - INFO - codeparrot_training - Step 30195: {'lr': 0.0004565461691706745, 'samples': 15460352, 'steps': 30195, 'loss/train': 2.2857582569122314}
-03/05/2022 00:57:10 - INFO - codeparrot_training - Step 30196: {'lr': 0.0004565431793075786, 'samples': 15460864, 'steps': 30196, 'loss/train': 1.6115623712539673}
-03/05/2022 00:57:13 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/05/2022 00:57:15 - INFO - codeparrot_training - Step 30197: {'lr': 0.0004565401893514176, 'samples': 15461376, 'steps': 30197, 'loss/train': 1.582255244255066}
-03/05/2022 00:57:19 - INFO - codeparrot_training - Step 30198: {'lr': 0.0004565371993021927, 'samples': 15461888, 'steps': 30198, 'loss/train': 1.1788573265075684}
-03/05/2022 00:57:21 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/05/2022 00:57:24 - INFO - codeparrot_training - Step 30199: {'lr': 0.00045653420915990546, 'samples': 15462400, 'steps': 30199, 'loss/train': 1.5279617309570312}
-03/05/2022 00:57:27 - INFO - codeparrot_training - Step 30200: {'lr': 0.000456531218924557, 'samples': 15462912, 'steps': 30200, 'loss/train': 0.6642404794692993}
-03/05/2022 00:57:29 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/05/2022 00:57:32 - INFO - codeparrot_training - Step 30201: {'lr': 0.0004565282285961488, 'samples': 15463424, 'steps': 30201, 'loss/train': 1.3005342483520508}
-03/05/2022 00:57:35 - INFO - codeparrot_training - Step 30202: {'lr': 0.0004565252381746821, 'samples': 15463936, 'steps': 30202, 'loss/train': 1.9071435928344727}
-03/05/2022 00:57:38 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/05/2022 00:57:41 - INFO - codeparrot_training - Step 30203: {'lr': 0.0004565222476601584, 'samples': 15464448, 'steps': 30203, 'loss/train': 1.9037094116210938}
-03/05/2022 00:57:44 - INFO - codeparrot_training - Step 30204: {'lr': 0.0004565192570525789, 'samples': 15464960, 'steps': 30204, 'loss/train': 0.8617432117462158}
-03/05/2022 00:57:46 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/05/2022 00:57:49 - INFO - codeparrot_training - Step 30205: {'lr': 0.00045651626635194497, 'samples': 15465472, 'steps': 30205, 'loss/train': 2.136298418045044}
-03/05/2022 00:57:52 - INFO - codeparrot_training - Step 30206: {'lr': 0.0004565132755582581, 'samples': 15465984, 'steps': 30206, 'loss/train': 1.6034797430038452}
-03/05/2022 00:57:55 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/05/2022 00:57:58 - INFO - codeparrot_training - Step 30207: {'lr': 0.0004565102846715195, 'samples': 15466496, 'steps': 30207, 'loss/train': 1.116777777671814}
-03/05/2022 00:58:01 - INFO - codeparrot_training - Step 30208: {'lr': 0.0004565072936917305, 'samples': 15467008, 'steps': 30208, 'loss/train': 1.985948085784912}
-03/05/2022 00:58:03 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 00:58:06 - INFO - codeparrot_training - Step 30209: {'lr': 0.0004565043026188926, 'samples': 15467520, 'steps': 30209, 'loss/train': 2.0067193508148193}
-03/05/2022 00:58:09 - INFO - codeparrot_training - Step 30210: {'lr': 0.000456501311453007, 'samples': 15468032, 'steps': 30210, 'loss/train': 2.190906524658203}
-03/05/2022 00:58:11 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 00:58:14 - INFO - codeparrot_training - Step 30211: {'lr': 0.00045649832019407504, 'samples': 15468544, 'steps': 30211, 'loss/train': 1.8707445859909058}
-03/05/2022 00:58:17 - INFO - codeparrot_training - Step 30212: {'lr': 0.0004564953288420982, 'samples': 15469056, 'steps': 30212, 'loss/train': 1.779178261756897}
-03/05/2022 00:58:19 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/05/2022 00:58:23 - INFO - codeparrot_training - Step 30213: {'lr': 0.00045649233739707774, 'samples': 15469568, 'steps': 30213, 'loss/train': 2.0264296531677246}
-03/05/2022 00:58:26 - INFO - codeparrot_training - Step 30214: {'lr': 0.00045648934585901496, 'samples': 15470080, 'steps': 30214, 'loss/train': 1.3510459661483765}
-03/05/2022 00:58:28 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 00:58:31 - INFO - codeparrot_training - Step 30215: {'lr': 0.0004564863542279113, 'samples': 15470592, 'steps': 30215, 'loss/train': 1.4700790643692017}
-03/05/2022 00:58:35 - INFO - codeparrot_training - Step 30216: {'lr': 0.0004564833625037681, 'samples': 15471104, 'steps': 30216, 'loss/train': 2.0649003982543945}
-03/05/2022 00:58:37 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/05/2022 00:58:40 - INFO - codeparrot_training - Step 30217: {'lr': 0.00045648037068658667, 'samples': 15471616, 'steps': 30217, 'loss/train': 1.567647099494934}
-03/05/2022 00:58:43 - INFO - codeparrot_training - Step 30218: {'lr': 0.00045647737877636834, 'samples': 15472128, 'steps': 30218, 'loss/train': 1.7761714458465576}
-03/05/2022 00:58:45 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/05/2022 00:58:48 - INFO - codeparrot_training - Step 30219: {'lr': 0.0004564743867731145, 'samples': 15472640, 'steps': 30219, 'loss/train': 1.7921855449676514}
-03/05/2022 00:58:51 - INFO - codeparrot_training - Step 30220: {'lr': 0.0004564713946768265, 'samples': 15473152, 'steps': 30220, 'loss/train': 2.465643882751465}
-03/05/2022 00:58:54 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/05/2022 00:58:57 - INFO - codeparrot_training - Step 30221: {'lr': 0.0004564684024875057, 'samples': 15473664, 'steps': 30221, 'loss/train': 1.6221206188201904}
-03/05/2022 00:59:00 - INFO - codeparrot_training - Step 30222: {'lr': 0.0004564654102051534, 'samples': 15474176, 'steps': 30222, 'loss/train': 2.371615409851074}
-03/05/2022 00:59:02 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/05/2022 00:59:05 - INFO - codeparrot_training - Step 30223: {'lr': 0.000456462417829771, 'samples': 15474688, 'steps': 30223, 'loss/train': 0.9984307885169983}
-03/05/2022 00:59:08 - INFO - codeparrot_training - Step 30224: {'lr': 0.0004564594253613598, 'samples': 15475200, 'steps': 30224, 'loss/train': 1.2560369968414307}
-03/05/2022 00:59:10 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/05/2022 00:59:14 - INFO - codeparrot_training - Step 30225: {'lr': 0.0004564564327999211, 'samples': 15475712, 'steps': 30225, 'loss/train': 2.3676202297210693}
-03/05/2022 00:59:17 - INFO - codeparrot_training - Step 30226: {'lr': 0.00045645344014545643, 'samples': 15476224, 'steps': 30226, 'loss/train': 1.9876879453659058}
-03/05/2022 00:59:19 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/05/2022 00:59:22 - INFO - codeparrot_training - Step 30227: {'lr': 0.00045645044739796694, 'samples': 15476736, 'steps': 30227, 'loss/train': 1.4872524738311768}
-03/05/2022 00:59:25 - INFO - codeparrot_training - Step 30228: {'lr': 0.00045644745455745414, 'samples': 15477248, 'steps': 30228, 'loss/train': 0.6331552267074585}
-03/05/2022 00:59:31 - INFO - codeparrot_training - Step 30229: {'lr': 0.0004564444616239193, 'samples': 15477760, 'steps': 30229, 'loss/train': 0.2098829746246338}
-03/05/2022 00:59:34 - INFO - codeparrot_training - Step 30230: {'lr': 0.0004564414685973637, 'samples': 15478272, 'steps': 30230, 'loss/train': 1.7654131650924683}
-03/05/2022 00:59:35 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/05/2022 00:59:39 - INFO - codeparrot_training - Step 30231: {'lr': 0.0004564384754777888, 'samples': 15478784, 'steps': 30231, 'loss/train': 2.1293141841888428}
-03/05/2022 00:59:42 - INFO - codeparrot_training - Step 30232: {'lr': 0.00045643548226519587, 'samples': 15479296, 'steps': 30232, 'loss/train': 1.8077073097229004}
-03/05/2022 00:59:44 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/05/2022 00:59:48 - INFO - codeparrot_training - Step 30233: {'lr': 0.00045643248895958636, 'samples': 15479808, 'steps': 30233, 'loss/train': 1.1070702075958252}
-03/05/2022 00:59:51 - INFO - codeparrot_training - Step 30234: {'lr': 0.00045642949556096146, 'samples': 15480320, 'steps': 30234, 'loss/train': 2.7490386962890625}
-03/05/2022 00:59:52 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/05/2022 00:59:56 - INFO - codeparrot_training - Step 30235: {'lr': 0.0004564265020693227, 'samples': 15480832, 'steps': 30235, 'loss/train': 1.2530138492584229}
-03/05/2022 00:59:59 - INFO - codeparrot_training - Step 30236: {'lr': 0.0004564235084846713, 'samples': 15481344, 'steps': 30236, 'loss/train': 1.2790501117706299}
-03/05/2022 01:00:00 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/05/2022 01:00:04 - INFO - codeparrot_training - Step 30237: {'lr': 0.00045642051480700873, 'samples': 15481856, 'steps': 30237, 'loss/train': 1.438962697982788}
-03/05/2022 01:00:08 - INFO - codeparrot_training - Step 30238: {'lr': 0.0004564175210363362, 'samples': 15482368, 'steps': 30238, 'loss/train': 1.755921721458435}
-03/05/2022 01:00:09 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/05/2022 01:00:13 - INFO - codeparrot_training - Step 30239: {'lr': 0.00045641452717265507, 'samples': 15482880, 'steps': 30239, 'loss/train': 1.8186254501342773}
-03/05/2022 01:00:16 - INFO - codeparrot_training - Step 30240: {'lr': 0.00045641153321596687, 'samples': 15483392, 'steps': 30240, 'loss/train': 1.6997802257537842}
-03/05/2022 01:00:17 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/05/2022 01:00:21 - INFO - codeparrot_training - Step 30241: {'lr': 0.0004564085391662727, 'samples': 15483904, 'steps': 30241, 'loss/train': 0.6641673445701599}
-03/05/2022 01:00:24 - INFO - codeparrot_training - Step 30242: {'lr': 0.00045640554502357413, 'samples': 15484416, 'steps': 30242, 'loss/train': 1.682521939277649}
-03/05/2022 01:00:26 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/05/2022 01:00:30 - INFO - codeparrot_training - Step 30243: {'lr': 0.0004564025507878723, 'samples': 15484928, 'steps': 30243, 'loss/train': 2.0395255088806152}
-03/05/2022 01:00:33 - INFO - codeparrot_training - Step 30244: {'lr': 0.00045639955645916875, 'samples': 15485440, 'steps': 30244, 'loss/train': 2.3381590843200684}
-03/05/2022 01:00:34 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/05/2022 01:00:38 - INFO - codeparrot_training - Step 30245: {'lr': 0.0004563965620374647, 'samples': 15485952, 'steps': 30245, 'loss/train': 1.1800812482833862}
-03/05/2022 01:00:41 - INFO - codeparrot_training - Step 30246: {'lr': 0.0004563935675227615, 'samples': 15486464, 'steps': 30246, 'loss/train': 2.39896559715271}
-03/05/2022 01:00:42 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/05/2022 01:00:47 - INFO - codeparrot_training - Step 30247: {'lr': 0.00045639057291506065, 'samples': 15486976, 'steps': 30247, 'loss/train': 1.636587142944336}
-03/05/2022 01:00:50 - INFO - codeparrot_training - Step 30248: {'lr': 0.0004563875782143633, 'samples': 15487488, 'steps': 30248, 'loss/train': 2.1304707527160645}
-03/05/2022 01:00:51 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 01:00:55 - INFO - codeparrot_training - Step 30249: {'lr': 0.000456384583420671, 'samples': 15488000, 'steps': 30249, 'loss/train': 2.1647915840148926}
-03/05/2022 01:00:58 - INFO - codeparrot_training - Step 30250: {'lr': 0.0004563815885339849, 'samples': 15488512, 'steps': 30250, 'loss/train': 1.878063678741455}
-03/05/2022 01:00:59 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/05/2022 01:01:04 - INFO - codeparrot_training - Step 30251: {'lr': 0.00045637859355430647, 'samples': 15489024, 'steps': 30251, 'loss/train': 1.9763576984405518}
-03/05/2022 01:01:07 - INFO - codeparrot_training - Step 30252: {'lr': 0.000456375598481637, 'samples': 15489536, 'steps': 30252, 'loss/train': 2.1009347438812256}
-03/05/2022 01:01:07 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/05/2022 01:01:12 - INFO - codeparrot_training - Step 30253: {'lr': 0.00045637260331597793, 'samples': 15490048, 'steps': 30253, 'loss/train': 3.047492742538452}
-03/05/2022 01:01:15 - INFO - codeparrot_training - Step 30254: {'lr': 0.00045636960805733054, 'samples': 15490560, 'steps': 30254, 'loss/train': 1.3888639211654663}
-03/05/2022 01:01:16 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/05/2022 01:01:21 - INFO - codeparrot_training - Step 30255: {'lr': 0.0004563666127056961, 'samples': 15491072, 'steps': 30255, 'loss/train': 1.5548039674758911}
-03/05/2022 01:01:24 - INFO - codeparrot_training - Step 30256: {'lr': 0.0004563636172610761, 'samples': 15491584, 'steps': 30256, 'loss/train': 1.9221271276474}
-03/05/2022 01:01:24 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/05/2022 01:01:29 - INFO - codeparrot_training - Step 30257: {'lr': 0.00045636062172347186, 'samples': 15492096, 'steps': 30257, 'loss/train': 1.9878610372543335}
-03/05/2022 01:01:32 - INFO - codeparrot_training - Step 30258: {'lr': 0.0004563576260928847, 'samples': 15492608, 'steps': 30258, 'loss/train': 1.368032455444336}
-03/05/2022 01:01:32 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/05/2022 01:01:37 - INFO - codeparrot_training - Step 30259: {'lr': 0.000456354630369316, 'samples': 15493120, 'steps': 30259, 'loss/train': 1.535534381866455}
-03/05/2022 01:01:40 - INFO - codeparrot_training - Step 30260: {'lr': 0.00045635163455276707, 'samples': 15493632, 'steps': 30260, 'loss/train': 1.5032907724380493}
-03/05/2022 01:01:40 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/05/2022 01:01:46 - INFO - codeparrot_training - Step 30261: {'lr': 0.0004563486386432393, 'samples': 15494144, 'steps': 30261, 'loss/train': 1.9104982614517212}
-03/05/2022 01:01:49 - INFO - codeparrot_training - Step 30262: {'lr': 0.00045634564264073396, 'samples': 15494656, 'steps': 30262, 'loss/train': 3.494652032852173}
-03/05/2022 01:01:49 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/05/2022 01:01:54 - INFO - codeparrot_training - Step 30263: {'lr': 0.0004563426465452525, 'samples': 15495168, 'steps': 30263, 'loss/train': 1.6567870378494263}
-03/05/2022 01:01:57 - INFO - codeparrot_training - Step 30264: {'lr': 0.00045633965035679614, 'samples': 15495680, 'steps': 30264, 'loss/train': 1.900291085243225}
-03/05/2022 01:01:58 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/05/2022 01:02:03 - INFO - codeparrot_training - Step 30265: {'lr': 0.0004563366540753664, 'samples': 15496192, 'steps': 30265, 'loss/train': 1.5593653917312622}
-03/05/2022 01:02:06 - INFO - codeparrot_training - Step 30266: {'lr': 0.00045633365770096456, 'samples': 15496704, 'steps': 30266, 'loss/train': 1.4124549627304077}
-03/05/2022 01:02:06 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/05/2022 01:02:11 - INFO - codeparrot_training - Step 30267: {'lr': 0.000456330661233592, 'samples': 15497216, 'steps': 30267, 'loss/train': 2.317880153656006}
-03/05/2022 01:02:14 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/05/2022 01:02:17 - INFO - codeparrot_training - Step 30268: {'lr': 0.00045632766467324995, 'samples': 15497728, 'steps': 30268, 'loss/train': 1.693334937095642}
-03/05/2022 01:02:20 - INFO - codeparrot_training - Step 30269: {'lr': 0.0004563246680199398, 'samples': 15498240, 'steps': 30269, 'loss/train': 1.5191677808761597}
-03/05/2022 01:02:22 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/05/2022 01:02:25 - INFO - codeparrot_training - Step 30270: {'lr': 0.000456321671273663, 'samples': 15498752, 'steps': 30270, 'loss/train': 1.4728446006774902}
-03/05/2022 01:02:28 - INFO - codeparrot_training - Step 30271: {'lr': 0.00045631867443442084, 'samples': 15499264, 'steps': 30271, 'loss/train': 1.7472803592681885}
-03/05/2022 01:02:31 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/05/2022 01:02:34 - INFO - codeparrot_training - Step 30272: {'lr': 0.00045631567750221465, 'samples': 15499776, 'steps': 30272, 'loss/train': 1.2688239812850952}
-03/05/2022 01:02:37 - INFO - codeparrot_training - Step 30273: {'lr': 0.0004563126804770458, 'samples': 15500288, 'steps': 30273, 'loss/train': 0.9735040068626404}
-03/05/2022 01:02:39 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 01:02:42 - INFO - codeparrot_training - Step 30274: {'lr': 0.00045630968335891564, 'samples': 15500800, 'steps': 30274, 'loss/train': 2.2206263542175293}
-03/05/2022 01:02:45 - INFO - codeparrot_training - Step 30275: {'lr': 0.00045630668614782553, 'samples': 15501312, 'steps': 30275, 'loss/train': 1.1849333047866821}
-03/05/2022 01:02:48 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/05/2022 01:02:50 - INFO - codeparrot_training - Step 30276: {'lr': 0.0004563036888437768, 'samples': 15501824, 'steps': 30276, 'loss/train': 0.4587782919406891}
-03/05/2022 01:02:54 - INFO - codeparrot_training - Step 30277: {'lr': 0.0004563006914467709, 'samples': 15502336, 'steps': 30277, 'loss/train': 1.5043517351150513}
-03/05/2022 01:02:56 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/05/2022 01:02:59 - INFO - codeparrot_training - Step 30278: {'lr': 0.000456297693956809, 'samples': 15502848, 'steps': 30278, 'loss/train': 1.8949087858200073}
-03/05/2022 01:03:02 - INFO - codeparrot_training - Step 30279: {'lr': 0.0004562946963738925, 'samples': 15503360, 'steps': 30279, 'loss/train': 1.8669930696487427}
-03/05/2022 01:03:04 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/05/2022 01:03:07 - INFO - codeparrot_training - Step 30280: {'lr': 0.0004562916986980229, 'samples': 15503872, 'steps': 30280, 'loss/train': 1.2581777572631836}
-03/05/2022 01:03:10 - INFO - codeparrot_training - Step 30281: {'lr': 0.0004562887009292014, 'samples': 15504384, 'steps': 30281, 'loss/train': 0.9684621691703796}
-03/05/2022 01:03:12 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/05/2022 01:03:16 - INFO - codeparrot_training - Step 30282: {'lr': 0.0004562857030674293, 'samples': 15504896, 'steps': 30282, 'loss/train': 1.1793482303619385}
-03/05/2022 01:03:19 - INFO - codeparrot_training - Step 30283: {'lr': 0.0004562827051127082, 'samples': 15505408, 'steps': 30283, 'loss/train': 1.6133840084075928}
-03/05/2022 01:03:21 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/05/2022 01:03:24 - INFO - codeparrot_training - Step 30284: {'lr': 0.0004562797070650392, 'samples': 15505920, 'steps': 30284, 'loss/train': 1.7075990438461304}
-03/05/2022 01:03:27 - INFO - codeparrot_training - Step 30285: {'lr': 0.00045627670892442376, 'samples': 15506432, 'steps': 30285, 'loss/train': 1.4524474143981934}
-03/05/2022 01:03:29 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/05/2022 01:03:32 - INFO - codeparrot_training - Step 30286: {'lr': 0.0004562737106908632, 'samples': 15506944, 'steps': 30286, 'loss/train': 2.1674249172210693}
-03/05/2022 01:03:36 - INFO - codeparrot_training - Step 30287: {'lr': 0.00045627071236435896, 'samples': 15507456, 'steps': 30287, 'loss/train': 1.509385585784912}
-03/05/2022 01:03:37 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/05/2022 01:03:41 - INFO - codeparrot_training - Step 30288: {'lr': 0.0004562677139449123, 'samples': 15507968, 'steps': 30288, 'loss/train': 2.908494710922241}
-03/05/2022 01:03:44 - INFO - codeparrot_training - Step 30289: {'lr': 0.0004562647154325246, 'samples': 15508480, 'steps': 30289, 'loss/train': 2.167825937271118}
-03/05/2022 01:03:46 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 01:03:49 - INFO - codeparrot_training - Step 30290: {'lr': 0.0004562617168271971, 'samples': 15508992, 'steps': 30290, 'loss/train': 1.6798962354660034}
-03/05/2022 01:03:53 - INFO - codeparrot_training - Step 30291: {'lr': 0.0004562587181289314, 'samples': 15509504, 'steps': 30291, 'loss/train': 1.7441438436508179}
-03/05/2022 01:03:54 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/05/2022 01:03:58 - INFO - codeparrot_training - Step 30292: {'lr': 0.00045625571933772857, 'samples': 15510016, 'steps': 30292, 'loss/train': 1.9378803968429565}
-03/05/2022 01:04:01 - INFO - codeparrot_training - Step 30293: {'lr': 0.0004562527204535902, 'samples': 15510528, 'steps': 30293, 'loss/train': 1.5410722494125366}
-03/05/2022 01:04:02 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 01:04:06 - INFO - codeparrot_training - Step 30294: {'lr': 0.00045624972147651746, 'samples': 15511040, 'steps': 30294, 'loss/train': 1.4874112606048584}
-03/05/2022 01:04:09 - INFO - codeparrot_training - Step 30295: {'lr': 0.00045624672240651183, 'samples': 15511552, 'steps': 30295, 'loss/train': 1.9203979969024658}
-03/05/2022 01:04:11 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/05/2022 01:04:15 - INFO - codeparrot_training - Step 30296: {'lr': 0.00045624372324357457, 'samples': 15512064, 'steps': 30296, 'loss/train': 1.7807732820510864}
-03/05/2022 01:04:18 - INFO - codeparrot_training - Step 30297: {'lr': 0.0004562407239877071, 'samples': 15512576, 'steps': 30297, 'loss/train': 1.9081791639328003}
-03/05/2022 01:04:19 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/05/2022 01:04:23 - INFO - codeparrot_training - Step 30298: {'lr': 0.0004562377246389108, 'samples': 15513088, 'steps': 30298, 'loss/train': 1.4249955415725708}
-03/05/2022 01:04:26 - INFO - codeparrot_training - Step 30299: {'lr': 0.00045623472519718683, 'samples': 15513600, 'steps': 30299, 'loss/train': 2.372708559036255}
-03/05/2022 01:04:27 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/05/2022 01:04:32 - INFO - codeparrot_training - Step 30300: {'lr': 0.00045623172566253676, 'samples': 15514112, 'steps': 30300, 'loss/train': 2.2095062732696533}
-03/05/2022 01:04:35 - INFO - codeparrot_training - Step 30301: {'lr': 0.00045622872603496184, 'samples': 15514624, 'steps': 30301, 'loss/train': 1.9211101531982422}
-03/05/2022 01:04:36 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/05/2022 01:04:40 - INFO - codeparrot_training - Step 30302: {'lr': 0.0004562257263144635, 'samples': 15515136, 'steps': 30302, 'loss/train': 1.0406535863876343}
-03/05/2022 01:04:43 - INFO - codeparrot_training - Step 30303: {'lr': 0.0004562227265010429, 'samples': 15515648, 'steps': 30303, 'loss/train': 1.2455202341079712}
-03/05/2022 01:04:45 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/05/2022 01:04:49 - INFO - codeparrot_training - Step 30304: {'lr': 0.00045621972659470156, 'samples': 15516160, 'steps': 30304, 'loss/train': 2.6532111167907715}
-03/05/2022 01:04:52 - INFO - codeparrot_training - Step 30305: {'lr': 0.0004562167265954409, 'samples': 15516672, 'steps': 30305, 'loss/train': 1.954776406288147}
-03/05/2022 01:04:54 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/05/2022 01:04:57 - INFO - codeparrot_training - Step 30306: {'lr': 0.000456213726503262, 'samples': 15517184, 'steps': 30306, 'loss/train': 1.7793982028961182}
-03/05/2022 01:05:00 - INFO - codeparrot_training - Step 30307: {'lr': 0.0004562107263181665, 'samples': 15517696, 'steps': 30307, 'loss/train': 2.420687675476074}
-03/05/2022 01:05:02 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/05/2022 01:05:06 - INFO - codeparrot_training - Step 30308: {'lr': 0.0004562077260401556, 'samples': 15518208, 'steps': 30308, 'loss/train': 1.699628233909607}
-03/05/2022 01:05:09 - INFO - codeparrot_training - Step 30309: {'lr': 0.00045620472566923064, 'samples': 15518720, 'steps': 30309, 'loss/train': 1.8189477920532227}
-03/05/2022 01:05:10 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/05/2022 01:05:14 - INFO - codeparrot_training - Step 30310: {'lr': 0.0004562017252053931, 'samples': 15519232, 'steps': 30310, 'loss/train': 5.373987197875977}
-03/05/2022 01:05:17 - INFO - codeparrot_training - Step 30311: {'lr': 0.0004561987246486442, 'samples': 15519744, 'steps': 30311, 'loss/train': 1.670209527015686}
-03/05/2022 01:05:20 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/05/2022 01:05:23 - INFO - codeparrot_training - Step 30312: {'lr': 0.00045619572399898534, 'samples': 15520256, 'steps': 30312, 'loss/train': 1.5850143432617188}
-03/05/2022 01:05:26 - INFO - codeparrot_training - Step 30313: {'lr': 0.0004561927232564179, 'samples': 15520768, 'steps': 30313, 'loss/train': 1.8503373861312866}
-03/05/2022 01:05:28 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/05/2022 01:05:31 - INFO - codeparrot_training - Step 30314: {'lr': 0.00045618972242094313, 'samples': 15521280, 'steps': 30314, 'loss/train': 1.8182893991470337}
-03/05/2022 01:05:34 - INFO - codeparrot_training - Step 30315: {'lr': 0.00045618672149256244, 'samples': 15521792, 'steps': 30315, 'loss/train': 1.4408502578735352}
-03/05/2022 01:05:36 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/05/2022 01:05:40 - INFO - codeparrot_training - Step 30316: {'lr': 0.0004561837204712773, 'samples': 15522304, 'steps': 30316, 'loss/train': 1.6367123126983643}
-03/05/2022 01:05:43 - INFO - codeparrot_training - Step 30317: {'lr': 0.0004561807193570888, 'samples': 15522816, 'steps': 30317, 'loss/train': 1.8563569784164429}
-03/05/2022 01:05:45 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 01:05:48 - INFO - codeparrot_training - Step 30318: {'lr': 0.0004561777181499986, 'samples': 15523328, 'steps': 30318, 'loss/train': 1.7057815790176392}
-03/05/2022 01:05:51 - INFO - codeparrot_training - Step 30319: {'lr': 0.00045617471685000785, 'samples': 15523840, 'steps': 30319, 'loss/train': 1.831925630569458}
-03/05/2022 01:05:53 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 01:05:56 - INFO - codeparrot_training - Step 30320: {'lr': 0.00045617171545711793, 'samples': 15524352, 'steps': 30320, 'loss/train': 0.0617365762591362}
-03/05/2022 01:06:00 - INFO - codeparrot_training - Step 30321: {'lr': 0.0004561687139713302, 'samples': 15524864, 'steps': 30321, 'loss/train': 1.2955726385116577}
-03/05/2022 01:06:01 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/05/2022 01:06:05 - INFO - codeparrot_training - Step 30322: {'lr': 0.00045616571239264614, 'samples': 15525376, 'steps': 30322, 'loss/train': 1.7771223783493042}
-03/05/2022 01:06:08 - INFO - codeparrot_training - Step 30323: {'lr': 0.0004561627107210669, 'samples': 15525888, 'steps': 30323, 'loss/train': 1.493330478668213}
-03/05/2022 01:06:09 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/05/2022 01:06:13 - INFO - codeparrot_training - Step 30324: {'lr': 0.00045615970895659393, 'samples': 15526400, 'steps': 30324, 'loss/train': 0.9467135667800903}
-03/05/2022 01:06:17 - INFO - codeparrot_training - Step 30325: {'lr': 0.00045615670709922855, 'samples': 15526912, 'steps': 30325, 'loss/train': 1.058262825012207}
-03/05/2022 01:06:18 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/05/2022 01:06:22 - INFO - codeparrot_training - Step 30326: {'lr': 0.0004561537051489722, 'samples': 15527424, 'steps': 30326, 'loss/train': 1.4175759553909302}
-03/05/2022 01:06:25 - INFO - codeparrot_training - Step 30327: {'lr': 0.00045615070310582617, 'samples': 15527936, 'steps': 30327, 'loss/train': 1.2218552827835083}
-03/05/2022 01:06:26 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/05/2022 01:06:31 - INFO - codeparrot_training - Step 30328: {'lr': 0.00045614770096979177, 'samples': 15528448, 'steps': 30328, 'loss/train': 1.2990055084228516}
-03/05/2022 01:06:34 - INFO - codeparrot_training - Step 30329: {'lr': 0.0004561446987408704, 'samples': 15528960, 'steps': 30329, 'loss/train': 1.965140461921692}
-03/05/2022 01:06:36 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/05/2022 01:06:39 - INFO - codeparrot_training - Step 30330: {'lr': 0.00045614169641906344, 'samples': 15529472, 'steps': 30330, 'loss/train': 2.1058785915374756}
-03/05/2022 01:06:42 - INFO - codeparrot_training - Step 30331: {'lr': 0.00045613869400437223, 'samples': 15529984, 'steps': 30331, 'loss/train': 1.4208797216415405}
-03/05/2022 01:06:45 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 01:06:48 - INFO - codeparrot_training - Step 30332: {'lr': 0.000456135691496798, 'samples': 15530496, 'steps': 30332, 'loss/train': 2.1719412803649902}
-03/05/2022 01:06:51 - INFO - codeparrot_training - Step 30333: {'lr': 0.0004561326888963423, 'samples': 15531008, 'steps': 30333, 'loss/train': 0.16385029256343842}
-03/05/2022 01:06:53 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 01:06:56 - INFO - codeparrot_training - Step 30334: {'lr': 0.0004561296862030064, 'samples': 15531520, 'steps': 30334, 'loss/train': 1.8687011003494263}
-03/05/2022 01:06:59 - INFO - codeparrot_training - Step 30335: {'lr': 0.00045612668341679164, 'samples': 15532032, 'steps': 30335, 'loss/train': 0.1145060658454895}
-03/05/2022 01:07:02 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/05/2022 01:07:05 - INFO - codeparrot_training - Step 30336: {'lr': 0.0004561236805376994, 'samples': 15532544, 'steps': 30336, 'loss/train': 1.8252521753311157}
-03/05/2022 01:07:08 - INFO - codeparrot_training - Step 30337: {'lr': 0.00045612067756573097, 'samples': 15533056, 'steps': 30337, 'loss/train': 1.1377383470535278}
-03/05/2022 01:07:10 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/05/2022 01:07:13 - INFO - codeparrot_training - Step 30338: {'lr': 0.0004561176745008877, 'samples': 15533568, 'steps': 30338, 'loss/train': 1.4026397466659546}
-03/05/2022 01:07:16 - INFO - codeparrot_training - Step 30339: {'lr': 0.000456114671343171, 'samples': 15534080, 'steps': 30339, 'loss/train': 2.222360610961914}
-03/05/2022 01:07:18 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/05/2022 01:07:22 - INFO - codeparrot_training - Step 30340: {'lr': 0.00045611166809258227, 'samples': 15534592, 'steps': 30340, 'loss/train': 1.4127634763717651}
-03/05/2022 01:07:25 - INFO - codeparrot_training - Step 30341: {'lr': 0.0004561086647491227, 'samples': 15535104, 'steps': 30341, 'loss/train': 1.526201844215393}
-03/05/2022 01:07:27 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/05/2022 01:07:30 - INFO - codeparrot_training - Step 30342: {'lr': 0.00045610566131279386, 'samples': 15535616, 'steps': 30342, 'loss/train': 1.739932894706726}
-03/05/2022 01:07:33 - INFO - codeparrot_training - Step 30343: {'lr': 0.00045610265778359696, 'samples': 15536128, 'steps': 30343, 'loss/train': 1.7376621961593628}
-03/05/2022 01:07:35 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/05/2022 01:07:39 - INFO - codeparrot_training - Step 30344: {'lr': 0.00045609965416153333, 'samples': 15536640, 'steps': 30344, 'loss/train': 1.795729398727417}
-03/05/2022 01:07:42 - INFO - codeparrot_training - Step 30345: {'lr': 0.0004560966504466044, 'samples': 15537152, 'steps': 30345, 'loss/train': 1.8292362689971924}
-03/05/2022 01:07:44 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 01:07:47 - INFO - codeparrot_training - Step 30346: {'lr': 0.00045609364663881153, 'samples': 15537664, 'steps': 30346, 'loss/train': 1.2304362058639526}
-03/05/2022 01:07:50 - INFO - codeparrot_training - Step 30347: {'lr': 0.000456090642738156, 'samples': 15538176, 'steps': 30347, 'loss/train': 2.116027355194092}
-03/05/2022 01:07:53 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/05/2022 01:07:56 - INFO - codeparrot_training - Step 30348: {'lr': 0.00045608763874463925, 'samples': 15538688, 'steps': 30348, 'loss/train': 0.9933581352233887}
-03/05/2022 01:07:59 - INFO - codeparrot_training - Step 30349: {'lr': 0.00045608463465826257, 'samples': 15539200, 'steps': 30349, 'loss/train': 2.2502827644348145}
-03/05/2022 01:08:01 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/05/2022 01:08:04 - INFO - codeparrot_training - Step 30350: {'lr': 0.0004560816304790274, 'samples': 15539712, 'steps': 30350, 'loss/train': 2.142665147781372}
-03/05/2022 01:08:07 - INFO - codeparrot_training - Step 30351: {'lr': 0.0004560786262069349, 'samples': 15540224, 'steps': 30351, 'loss/train': 2.10463547706604}
-03/05/2022 01:08:10 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/05/2022 01:08:13 - INFO - codeparrot_training - Step 30352: {'lr': 0.00045607562184198666, 'samples': 15540736, 'steps': 30352, 'loss/train': 2.174138307571411}
-03/05/2022 01:08:16 - INFO - codeparrot_training - Step 30353: {'lr': 0.00045607261738418384, 'samples': 15541248, 'steps': 30353, 'loss/train': 2.0719547271728516}
-03/05/2022 01:08:19 - INFO - codeparrot_training - Step 30354: {'lr': 0.00045606961283352793, 'samples': 15541760, 'steps': 30354, 'loss/train': 6.586909294128418}
-03/05/2022 01:08:19 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/05/2022 01:08:24 - INFO - codeparrot_training - Step 30355: {'lr': 0.0004560666081900202, 'samples': 15542272, 'steps': 30355, 'loss/train': 1.7161489725112915}
-03/05/2022 01:08:27 - INFO - codeparrot_training - Step 30356: {'lr': 0.00045606360345366203, 'samples': 15542784, 'steps': 30356, 'loss/train': 1.4627867937088013}
-03/05/2022 01:08:28 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 01:08:33 - INFO - codeparrot_training - Step 30357: {'lr': 0.00045606059862445485, 'samples': 15543296, 'steps': 30357, 'loss/train': 1.872009515762329}
-03/05/2022 01:08:36 - INFO - codeparrot_training - Step 30358: {'lr': 0.0004560575937023999, 'samples': 15543808, 'steps': 30358, 'loss/train': 1.9575735330581665}
-03/05/2022 01:08:36 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/05/2022 01:08:41 - INFO - codeparrot_training - Step 30359: {'lr': 0.0004560545886874986, 'samples': 15544320, 'steps': 30359, 'loss/train': 1.8711278438568115}
-03/05/2022 01:08:44 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/05/2022 01:08:46 - INFO - codeparrot_training - Step 30360: {'lr': 0.00045605158357975225, 'samples': 15544832, 'steps': 30360, 'loss/train': 1.4265213012695312}
-03/05/2022 01:08:50 - INFO - codeparrot_training - Step 30361: {'lr': 0.00045604857837916224, 'samples': 15545344, 'steps': 30361, 'loss/train': 1.7307380437850952}
-03/05/2022 01:08:52 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/05/2022 01:08:55 - INFO - codeparrot_training - Step 30362: {'lr': 0.0004560455730857299, 'samples': 15545856, 'steps': 30362, 'loss/train': 2.065617561340332}
-03/05/2022 01:08:58 - INFO - codeparrot_training - Step 30363: {'lr': 0.0004560425676994566, 'samples': 15546368, 'steps': 30363, 'loss/train': 1.6186941862106323}
-03/05/2022 01:09:00 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/05/2022 01:09:03 - INFO - codeparrot_training - Step 30364: {'lr': 0.00045603956222034384, 'samples': 15546880, 'steps': 30364, 'loss/train': 1.6865589618682861}
-03/05/2022 01:09:06 - INFO - codeparrot_training - Step 30365: {'lr': 0.0004560365566483927, 'samples': 15547392, 'steps': 30365, 'loss/train': 1.2278800010681152}
-03/05/2022 01:09:09 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/05/2022 01:09:12 - INFO - codeparrot_training - Step 30366: {'lr': 0.00045603355098360466, 'samples': 15547904, 'steps': 30366, 'loss/train': 1.0190188884735107}
-03/05/2022 01:09:15 - INFO - codeparrot_training - Step 30367: {'lr': 0.00045603054522598107, 'samples': 15548416, 'steps': 30367, 'loss/train': 1.727705478668213}
-03/05/2022 01:09:17 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/05/2022 01:09:20 - INFO - codeparrot_training - Step 30368: {'lr': 0.0004560275393755233, 'samples': 15548928, 'steps': 30368, 'loss/train': 1.0315419435501099}
-03/05/2022 01:09:23 - INFO - codeparrot_training - Step 30369: {'lr': 0.0004560245334322328, 'samples': 15549440, 'steps': 30369, 'loss/train': 1.7085744142532349}
-03/05/2022 01:09:25 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/05/2022 01:09:29 - INFO - codeparrot_training - Step 30370: {'lr': 0.00045602152739611075, 'samples': 15549952, 'steps': 30370, 'loss/train': 1.881314992904663}
-03/05/2022 01:09:32 - INFO - codeparrot_training - Step 30371: {'lr': 0.0004560185212671586, 'samples': 15550464, 'steps': 30371, 'loss/train': 1.3301869630813599}
-03/05/2022 01:09:34 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/05/2022 01:09:37 - INFO - codeparrot_training - Step 30372: {'lr': 0.00045601551504537765, 'samples': 15550976, 'steps': 30372, 'loss/train': 2.1871769428253174}
-03/05/2022 01:09:40 - INFO - codeparrot_training - Step 30373: {'lr': 0.0004560125087307693, 'samples': 15551488, 'steps': 30373, 'loss/train': 1.5007432699203491}
-03/05/2022 01:09:42 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/05/2022 01:09:46 - INFO - codeparrot_training - Step 30374: {'lr': 0.00045600950232333495, 'samples': 15552000, 'steps': 30374, 'loss/train': 0.9763179421424866}
-03/05/2022 01:09:49 - INFO - codeparrot_training - Step 30375: {'lr': 0.00045600649582307586, 'samples': 15552512, 'steps': 30375, 'loss/train': 2.0295298099517822}
-03/05/2022 01:09:51 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/05/2022 01:09:54 - INFO - codeparrot_training - Step 30376: {'lr': 0.00045600348922999334, 'samples': 15553024, 'steps': 30376, 'loss/train': 2.4519736766815186}
-03/05/2022 01:09:57 - INFO - codeparrot_training - Step 30377: {'lr': 0.0004560004825440889, 'samples': 15553536, 'steps': 30377, 'loss/train': 1.318518042564392}
-03/05/2022 01:10:00 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/05/2022 01:10:03 - INFO - codeparrot_training - Step 30378: {'lr': 0.0004559974757653639, 'samples': 15554048, 'steps': 30378, 'loss/train': 2.206862688064575}
-03/05/2022 01:10:06 - INFO - codeparrot_training - Step 30379: {'lr': 0.0004559944688938195, 'samples': 15554560, 'steps': 30379, 'loss/train': 1.7655829191207886}
-03/05/2022 01:10:08 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/05/2022 01:10:11 - INFO - codeparrot_training - Step 30380: {'lr': 0.0004559914619294572, 'samples': 15555072, 'steps': 30380, 'loss/train': 0.25516730546951294}
-03/05/2022 01:10:14 - INFO - codeparrot_training - Step 30381: {'lr': 0.00045598845487227835, 'samples': 15555584, 'steps': 30381, 'loss/train': 1.504288911819458}
-03/05/2022 01:10:16 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/05/2022 01:10:19 - INFO - codeparrot_training - Step 30382: {'lr': 0.0004559854477222842, 'samples': 15556096, 'steps': 30382, 'loss/train': 1.1959232091903687}
-03/05/2022 01:10:23 - INFO - codeparrot_training - Step 30383: {'lr': 0.0004559824404794763, 'samples': 15556608, 'steps': 30383, 'loss/train': 1.766464114189148}
-03/05/2022 01:10:25 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/05/2022 01:10:28 - INFO - codeparrot_training - Step 30384: {'lr': 0.0004559794331438558, 'samples': 15557120, 'steps': 30384, 'loss/train': 1.9022656679153442}
-03/05/2022 01:10:31 - INFO - codeparrot_training - Step 30385: {'lr': 0.0004559764257154242, 'samples': 15557632, 'steps': 30385, 'loss/train': 1.6189199686050415}
-03/05/2022 01:10:33 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/05/2022 01:10:36 - INFO - codeparrot_training - Step 30386: {'lr': 0.0004559734181941828, 'samples': 15558144, 'steps': 30386, 'loss/train': 2.0789079666137695}
-03/05/2022 01:10:40 - INFO - codeparrot_training - Step 30387: {'lr': 0.0004559704105801329, 'samples': 15558656, 'steps': 30387, 'loss/train': 1.676277756690979}
-03/05/2022 01:10:41 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/05/2022 01:10:45 - INFO - codeparrot_training - Step 30388: {'lr': 0.00045596740287327597, 'samples': 15559168, 'steps': 30388, 'loss/train': 1.4329053163528442}
-03/05/2022 01:10:48 - INFO - codeparrot_training - Step 30389: {'lr': 0.0004559643950736133, 'samples': 15559680, 'steps': 30389, 'loss/train': 2.304358959197998}
-03/05/2022 01:10:50 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/05/2022 01:10:53 - INFO - codeparrot_training - Step 30390: {'lr': 0.00045596138718114626, 'samples': 15560192, 'steps': 30390, 'loss/train': 1.9810020923614502}
-03/05/2022 01:10:56 - INFO - codeparrot_training - Step 30391: {'lr': 0.00045595837919587616, 'samples': 15560704, 'steps': 30391, 'loss/train': 1.020075798034668}
-03/05/2022 01:10:58 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/05/2022 01:11:02 - INFO - codeparrot_training - Step 30392: {'lr': 0.0004559553711178044, 'samples': 15561216, 'steps': 30392, 'loss/train': 1.3351904153823853}
-03/05/2022 01:11:05 - INFO - codeparrot_training - Step 30393: {'lr': 0.00045595236294693236, 'samples': 15561728, 'steps': 30393, 'loss/train': 2.4174575805664062}
-03/05/2022 01:11:06 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/05/2022 01:11:10 - INFO - codeparrot_training - Step 30394: {'lr': 0.00045594935468326137, 'samples': 15562240, 'steps': 30394, 'loss/train': 1.9899287223815918}
-03/05/2022 01:11:13 - INFO - codeparrot_training - Step 30395: {'lr': 0.00045594634632679275, 'samples': 15562752, 'steps': 30395, 'loss/train': 1.2670739889144897}
-03/05/2022 01:11:15 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/05/2022 01:11:18 - INFO - codeparrot_training - Step 30396: {'lr': 0.0004559433378775278, 'samples': 15563264, 'steps': 30396, 'loss/train': 1.4350285530090332}
-03/05/2022 01:11:22 - INFO - codeparrot_training - Step 30397: {'lr': 0.00045594032933546813, 'samples': 15563776, 'steps': 30397, 'loss/train': 1.019887089729309}
-03/05/2022 01:11:23 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/05/2022 01:11:27 - INFO - codeparrot_training - Step 30398: {'lr': 0.00045593732070061484, 'samples': 15564288, 'steps': 30398, 'loss/train': 1.8890637159347534}
-03/05/2022 01:11:30 - INFO - codeparrot_training - Step 30399: {'lr': 0.00045593431197296934, 'samples': 15564800, 'steps': 30399, 'loss/train': 1.0421630144119263}
-03/05/2022 01:11:31 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/05/2022 01:11:35 - INFO - codeparrot_training - Step 30400: {'lr': 0.00045593130315253305, 'samples': 15565312, 'steps': 30400, 'loss/train': 1.8648065328598022}
-03/05/2022 01:11:38 - INFO - codeparrot_training - Step 30401: {'lr': 0.0004559282942393073, 'samples': 15565824, 'steps': 30401, 'loss/train': 2.101236581802368}
-03/05/2022 01:11:40 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/05/2022 01:11:44 - INFO - codeparrot_training - Step 30402: {'lr': 0.00045592528523329346, 'samples': 15566336, 'steps': 30402, 'loss/train': 1.8022751808166504}
-03/05/2022 01:11:47 - INFO - codeparrot_training - Step 30403: {'lr': 0.0004559222761344928, 'samples': 15566848, 'steps': 30403, 'loss/train': 0.08982302248477936}
-03/05/2022 01:11:48 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/05/2022 01:11:52 - INFO - codeparrot_training - Step 30404: {'lr': 0.0004559192669429068, 'samples': 15567360, 'steps': 30404, 'loss/train': 1.9577254056930542}
-03/05/2022 01:11:55 - INFO - codeparrot_training - Step 30405: {'lr': 0.0004559162576585367, 'samples': 15567872, 'steps': 30405, 'loss/train': 0.6883639097213745}
-03/05/2022 01:11:57 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/05/2022 01:12:01 - INFO - codeparrot_training - Step 30406: {'lr': 0.00045591324828138396, 'samples': 15568384, 'steps': 30406, 'loss/train': 1.9827839136123657}
-03/05/2022 01:12:04 - INFO - codeparrot_training - Step 30407: {'lr': 0.0004559102388114499, 'samples': 15568896, 'steps': 30407, 'loss/train': 1.9918971061706543}
-03/05/2022 01:12:05 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/05/2022 01:12:09 - INFO - codeparrot_training - Step 30408: {'lr': 0.00045590722924873585, 'samples': 15569408, 'steps': 30408, 'loss/train': 1.4455137252807617}
-03/05/2022 01:12:12 - INFO - codeparrot_training - Step 30409: {'lr': 0.00045590421959324314, 'samples': 15569920, 'steps': 30409, 'loss/train': 1.2680877447128296}
-03/05/2022 01:12:13 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/05/2022 01:12:17 - INFO - codeparrot_training - Step 30410: {'lr': 0.0004559012098449732, 'samples': 15570432, 'steps': 30410, 'loss/train': 0.12951192259788513}
-03/05/2022 01:12:21 - INFO - codeparrot_training - Step 30411: {'lr': 0.00045589820000392736, 'samples': 15570944, 'steps': 30411, 'loss/train': 0.05925912410020828}
-03/05/2022 01:12:22 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/05/2022 01:12:26 - INFO - codeparrot_training - Step 30412: {'lr': 0.00045589519007010695, 'samples': 15571456, 'steps': 30412, 'loss/train': 2.0319509506225586}
-03/05/2022 01:12:29 - INFO - codeparrot_training - Step 30413: {'lr': 0.0004558921800435133, 'samples': 15571968, 'steps': 30413, 'loss/train': 1.633844256401062}
-03/05/2022 01:12:30 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 01:12:34 - INFO - codeparrot_training - Step 30414: {'lr': 0.00045588916992414784, 'samples': 15572480, 'steps': 30414, 'loss/train': 1.635192632675171}
-03/05/2022 01:12:37 - INFO - codeparrot_training - Step 30415: {'lr': 0.0004558861597120119, 'samples': 15572992, 'steps': 30415, 'loss/train': 2.163285493850708}
-03/05/2022 01:12:38 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/05/2022 01:12:43 - INFO - codeparrot_training - Step 30416: {'lr': 0.00045588314940710683, 'samples': 15573504, 'steps': 30416, 'loss/train': 1.4755897521972656}
-03/05/2022 01:12:46 - INFO - codeparrot_training - Step 30417: {'lr': 0.00045588013900943404, 'samples': 15574016, 'steps': 30417, 'loss/train': 1.805010199546814}
-03/05/2022 01:12:46 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/05/2022 01:12:51 - INFO - codeparrot_training - Step 30418: {'lr': 0.0004558771285189948, 'samples': 15574528, 'steps': 30418, 'loss/train': 1.4233644008636475}
-03/05/2022 01:12:54 - INFO - codeparrot_training - Step 30419: {'lr': 0.00045587411793579047, 'samples': 15575040, 'steps': 30419, 'loss/train': 1.7176231145858765}
-03/05/2022 01:12:55 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/05/2022 01:13:00 - INFO - codeparrot_training - Step 30420: {'lr': 0.0004558711072598225, 'samples': 15575552, 'steps': 30420, 'loss/train': 2.1467010974884033}
-03/05/2022 01:13:03 - INFO - codeparrot_training - Step 30421: {'lr': 0.0004558680964910922, 'samples': 15576064, 'steps': 30421, 'loss/train': 0.9580603837966919}
-03/05/2022 01:13:03 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/05/2022 01:13:08 - INFO - codeparrot_training - Step 30422: {'lr': 0.0004558650856296008, 'samples': 15576576, 'steps': 30422, 'loss/train': 1.9012800455093384}
-03/05/2022 01:13:11 - INFO - codeparrot_training - Step 30423: {'lr': 0.0004558620746753499, 'samples': 15577088, 'steps': 30423, 'loss/train': 1.4355158805847168}
-03/05/2022 01:13:12 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/05/2022 01:13:17 - INFO - codeparrot_training - Step 30424: {'lr': 0.00045585906362834063, 'samples': 15577600, 'steps': 30424, 'loss/train': 1.8312486410140991}
-03/05/2022 01:13:20 - INFO - codeparrot_training - Step 30425: {'lr': 0.00045585605248857456, 'samples': 15578112, 'steps': 30425, 'loss/train': 1.9815820455551147}
-03/05/2022 01:13:21 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/05/2022 01:13:25 - INFO - codeparrot_training - Step 30426: {'lr': 0.00045585304125605276, 'samples': 15578624, 'steps': 30426, 'loss/train': 1.1288591623306274}
-03/05/2022 01:13:28 - INFO - codeparrot_training - Step 30427: {'lr': 0.0004558500299307768, 'samples': 15579136, 'steps': 30427, 'loss/train': 1.4727312326431274}
-03/05/2022 01:13:29 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/05/2022 01:13:34 - INFO - codeparrot_training - Step 30428: {'lr': 0.00045584701851274814, 'samples': 15579648, 'steps': 30428, 'loss/train': 2.0945613384246826}
-03/05/2022 01:13:37 - INFO - codeparrot_training - Step 30429: {'lr': 0.0004558440070019678, 'samples': 15580160, 'steps': 30429, 'loss/train': 4.615679740905762}
-03/05/2022 01:13:38 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/05/2022 01:13:42 - INFO - codeparrot_training - Step 30430: {'lr': 0.0004558409953984375, 'samples': 15580672, 'steps': 30430, 'loss/train': 0.47348663210868835}
-03/05/2022 01:13:45 - INFO - codeparrot_training - Step 30431: {'lr': 0.00045583798370215837, 'samples': 15581184, 'steps': 30431, 'loss/train': 2.1555707454681396}
-03/05/2022 01:13:46 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/05/2022 01:13:50 - INFO - codeparrot_training - Step 30432: {'lr': 0.00045583497191313175, 'samples': 15581696, 'steps': 30432, 'loss/train': 1.8784217834472656}
-03/05/2022 01:13:54 - INFO - codeparrot_training - Step 30433: {'lr': 0.00045583196003135906, 'samples': 15582208, 'steps': 30433, 'loss/train': 1.1608339548110962}
-03/05/2022 01:13:54 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/05/2022 01:13:59 - INFO - codeparrot_training - Step 30434: {'lr': 0.0004558289480568417, 'samples': 15582720, 'steps': 30434, 'loss/train': 1.743011236190796}
-03/05/2022 01:14:02 - INFO - codeparrot_training - Step 30435: {'lr': 0.00045582593598958107, 'samples': 15583232, 'steps': 30435, 'loss/train': 1.3328958749771118}
-03/05/2022 01:14:03 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/05/2022 01:14:07 - INFO - codeparrot_training - Step 30436: {'lr': 0.00045582292382957836, 'samples': 15583744, 'steps': 30436, 'loss/train': 3.0934886932373047}
-03/05/2022 01:14:10 - INFO - codeparrot_training - Step 30437: {'lr': 0.000455819911576835, 'samples': 15584256, 'steps': 30437, 'loss/train': 0.9609709978103638}
-03/05/2022 01:14:11 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/05/2022 01:14:16 - INFO - codeparrot_training - Step 30438: {'lr': 0.00045581689923135247, 'samples': 15584768, 'steps': 30438, 'loss/train': 2.0351412296295166}
-03/05/2022 01:14:19 - INFO - codeparrot_training - Step 30439: {'lr': 0.00045581388679313194, 'samples': 15585280, 'steps': 30439, 'loss/train': 1.8427801132202148}
-03/05/2022 01:14:19 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/05/2022 01:14:24 - INFO - codeparrot_training - Step 30440: {'lr': 0.0004558108742621748, 'samples': 15585792, 'steps': 30440, 'loss/train': 2.178126811981201}
-03/05/2022 01:14:27 - INFO - codeparrot_training - Step 30441: {'lr': 0.00045580786163848254, 'samples': 15586304, 'steps': 30441, 'loss/train': 2.5190231800079346}
-03/05/2022 01:14:27 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/05/2022 01:14:32 - INFO - codeparrot_training - Step 30442: {'lr': 0.00045580484892205643, 'samples': 15586816, 'steps': 30442, 'loss/train': 1.1063358783721924}
-03/05/2022 01:14:36 - INFO - codeparrot_training - Step 30443: {'lr': 0.0004558018361128978, 'samples': 15587328, 'steps': 30443, 'loss/train': 1.6020057201385498}
-03/05/2022 01:14:36 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/05/2022 01:14:41 - INFO - codeparrot_training - Step 30444: {'lr': 0.0004557988232110081, 'samples': 15587840, 'steps': 30444, 'loss/train': 1.659379243850708}
-03/05/2022 01:14:44 - INFO - codeparrot_training - Step 30445: {'lr': 0.00045579581021638855, 'samples': 15588352, 'steps': 30445, 'loss/train': 1.114865779876709}
-03/05/2022 01:14:44 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/05/2022 01:14:49 - INFO - codeparrot_training - Step 30446: {'lr': 0.00045579279712904057, 'samples': 15588864, 'steps': 30446, 'loss/train': 1.7532734870910645}
-03/05/2022 01:14:52 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/05/2022 01:14:55 - INFO - codeparrot_training - Step 30447: {'lr': 0.00045578978394896565, 'samples': 15589376, 'steps': 30447, 'loss/train': 1.9886479377746582}
-03/05/2022 01:14:58 - INFO - codeparrot_training - Step 30448: {'lr': 0.00045578677067616494, 'samples': 15589888, 'steps': 30448, 'loss/train': 1.309191107749939}
-03/05/2022 01:15:01 - INFO - codeparrot_training - Step 30449: {'lr': 0.0004557837573106399, 'samples': 15590400, 'steps': 30449, 'loss/train': 2.432729482650757}
-03/05/2022 01:15:01 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/05/2022 01:15:06 - INFO - codeparrot_training - Step 30450: {'lr': 0.0004557807438523919, 'samples': 15590912, 'steps': 30450, 'loss/train': 1.957144021987915}
-03/05/2022 01:15:10 - INFO - codeparrot_training - Step 30451: {'lr': 0.00045577773030142224, 'samples': 15591424, 'steps': 30451, 'loss/train': 1.6094367504119873}
-03/05/2022 01:15:10 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/05/2022 01:15:15 - INFO - codeparrot_training - Step 30452: {'lr': 0.0004557747166577323, 'samples': 15591936, 'steps': 30452, 'loss/train': 1.1868141889572144}
-03/05/2022 01:15:18 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 01:15:20 - INFO - codeparrot_training - Step 30453: {'lr': 0.0004557717029213234, 'samples': 15592448, 'steps': 30453, 'loss/train': 1.7298978567123413}
-03/05/2022 01:15:23 - INFO - codeparrot_training - Step 30454: {'lr': 0.00045576868909219704, 'samples': 15592960, 'steps': 30454, 'loss/train': 1.0971542596817017}
-03/05/2022 01:15:26 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/05/2022 01:15:29 - INFO - codeparrot_training - Step 30455: {'lr': 0.0004557656751703544, 'samples': 15593472, 'steps': 30455, 'loss/train': 0.8508080840110779}
-03/05/2022 01:15:32 - INFO - codeparrot_training - Step 30456: {'lr': 0.000455762661155797, 'samples': 15593984, 'steps': 30456, 'loss/train': 1.371014952659607}
-03/05/2022 01:15:35 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/05/2022 01:15:37 - INFO - codeparrot_training - Step 30457: {'lr': 0.0004557596470485261, 'samples': 15594496, 'steps': 30457, 'loss/train': 1.753208875656128}
-03/05/2022 01:15:40 - INFO - codeparrot_training - Step 30458: {'lr': 0.0004557566328485431, 'samples': 15595008, 'steps': 30458, 'loss/train': 1.8668346405029297}
-03/05/2022 01:15:43 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/05/2022 01:15:45 - INFO - codeparrot_training - Step 30459: {'lr': 0.00045575361855584927, 'samples': 15595520, 'steps': 30459, 'loss/train': 1.6284278631210327}
-03/05/2022 01:15:49 - INFO - codeparrot_training - Step 30460: {'lr': 0.00045575060417044614, 'samples': 15596032, 'steps': 30460, 'loss/train': 2.095759630203247}
-03/05/2022 01:15:51 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/05/2022 01:15:54 - INFO - codeparrot_training - Step 30461: {'lr': 0.0004557475896923349, 'samples': 15596544, 'steps': 30461, 'loss/train': 1.7722729444503784}
-03/05/2022 01:15:57 - INFO - codeparrot_training - Step 30462: {'lr': 0.0004557445751215169, 'samples': 15597056, 'steps': 30462, 'loss/train': 2.435866117477417}
-03/05/2022 01:16:00 - INFO - codeparrot_training - Step 30463: {'lr': 0.00045574156045799367, 'samples': 15597568, 'steps': 30463, 'loss/train': 2.07511830329895}
-03/05/2022 01:16:00 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/05/2022 01:16:06 - INFO - codeparrot_training - Step 30464: {'lr': 0.0004557385457017664, 'samples': 15598080, 'steps': 30464, 'loss/train': 2.5630083084106445}
-03/05/2022 01:16:09 - INFO - codeparrot_training - Step 30465: {'lr': 0.0004557355308528366, 'samples': 15598592, 'steps': 30465, 'loss/train': 2.3153674602508545}
-03/05/2022 01:16:10 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/05/2022 01:16:14 - INFO - codeparrot_training - Step 30466: {'lr': 0.00045573251591120545, 'samples': 15599104, 'steps': 30466, 'loss/train': 1.7814710140228271}
-03/05/2022 01:16:18 - INFO - codeparrot_training - Step 30467: {'lr': 0.00045572950087687447, 'samples': 15599616, 'steps': 30467, 'loss/train': 2.207195520401001}
-03/05/2022 01:16:18 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 01:16:23 - INFO - codeparrot_training - Step 30468: {'lr': 0.0004557264857498449, 'samples': 15600128, 'steps': 30468, 'loss/train': 2.0599067211151123}
-03/05/2022 01:16:26 - INFO - codeparrot_training - Step 30469: {'lr': 0.0004557234705301182, 'samples': 15600640, 'steps': 30469, 'loss/train': 2.0651638507843018}
-03/05/2022 01:16:26 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/05/2022 01:16:31 - INFO - codeparrot_training - Step 30470: {'lr': 0.0004557204552176957, 'samples': 15601152, 'steps': 30470, 'loss/train': 2.6290104389190674}
-03/05/2022 01:16:34 - INFO - codeparrot_training - Step 30471: {'lr': 0.0004557174398125786, 'samples': 15601664, 'steps': 30471, 'loss/train': 1.8247712850570679}
-03/05/2022 01:16:34 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/05/2022 01:16:40 - INFO - codeparrot_training - Step 30472: {'lr': 0.00045571442431476856, 'samples': 15602176, 'steps': 30472, 'loss/train': 1.9465539455413818}
-03/05/2022 01:16:42 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/05/2022 01:16:45 - INFO - codeparrot_training - Step 30473: {'lr': 0.0004557114087242667, 'samples': 15602688, 'steps': 30473, 'loss/train': 1.3080689907073975}
-03/05/2022 01:16:48 - INFO - codeparrot_training - Step 30474: {'lr': 0.0004557083930410745, 'samples': 15603200, 'steps': 30474, 'loss/train': 1.3806581497192383}
-03/05/2022 01:16:51 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/05/2022 01:16:53 - INFO - codeparrot_training - Step 30475: {'lr': 0.0004557053772651932, 'samples': 15603712, 'steps': 30475, 'loss/train': 1.6152102947235107}
-03/05/2022 01:16:57 - INFO - codeparrot_training - Step 30476: {'lr': 0.00045570236139662426, 'samples': 15604224, 'steps': 30476, 'loss/train': 1.8976211547851562}
-03/05/2022 01:16:59 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/05/2022 01:17:02 - INFO - codeparrot_training - Step 30477: {'lr': 0.000455699345435369, 'samples': 15604736, 'steps': 30477, 'loss/train': 1.6124889850616455}
-03/05/2022 01:17:05 - INFO - codeparrot_training - Step 30478: {'lr': 0.0004556963293814288, 'samples': 15605248, 'steps': 30478, 'loss/train': 2.411875009536743}
-03/05/2022 01:17:08 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/05/2022 01:17:10 - INFO - codeparrot_training - Step 30479: {'lr': 0.000455693313234805, 'samples': 15605760, 'steps': 30479, 'loss/train': 1.7829580307006836}
-03/05/2022 01:17:14 - INFO - codeparrot_training - Step 30480: {'lr': 0.000455690296995499, 'samples': 15606272, 'steps': 30480, 'loss/train': 3.618541717529297}
-03/05/2022 01:17:16 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 01:17:19 - INFO - codeparrot_training - Step 30481: {'lr': 0.00045568728066351205, 'samples': 15606784, 'steps': 30481, 'loss/train': 0.8460149168968201}
-03/05/2022 01:17:22 - INFO - codeparrot_training - Step 30482: {'lr': 0.0004556842642388457, 'samples': 15607296, 'steps': 30482, 'loss/train': 1.5652014017105103}
-03/05/2022 01:17:24 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/05/2022 01:17:27 - INFO - codeparrot_training - Step 30483: {'lr': 0.0004556812477215011, 'samples': 15607808, 'steps': 30483, 'loss/train': 2.0389010906219482}
-03/05/2022 01:17:30 - INFO - codeparrot_training - Step 30484: {'lr': 0.0004556782311114798, 'samples': 15608320, 'steps': 30484, 'loss/train': 1.4681047201156616}
-03/05/2022 01:17:33 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/05/2022 01:17:36 - INFO - codeparrot_training - Step 30485: {'lr': 0.00045567521440878294, 'samples': 15608832, 'steps': 30485, 'loss/train': 1.9434428215026855}
-03/05/2022 01:17:39 - INFO - codeparrot_training - Step 30486: {'lr': 0.000455672197613412, 'samples': 15609344, 'steps': 30486, 'loss/train': 1.3529409170150757}
-03/05/2022 01:17:41 - INFO - codeparrot_training - Skipping example with length 996 (seq_length=1024)
-03/05/2022 01:17:44 - INFO - codeparrot_training - Step 30487: {'lr': 0.00045566918072536844, 'samples': 15609856, 'steps': 30487, 'loss/train': 2.5418858528137207}
-03/05/2022 01:17:48 - INFO - codeparrot_training - Step 30488: {'lr': 0.00045566616374465355, 'samples': 15610368, 'steps': 30488, 'loss/train': 1.7175304889678955}
-03/05/2022 01:17:50 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 01:17:53 - INFO - codeparrot_training - Step 30489: {'lr': 0.0004556631466712686, 'samples': 15610880, 'steps': 30489, 'loss/train': 1.1236913204193115}
-03/05/2022 01:17:56 - INFO - codeparrot_training - Step 30490: {'lr': 0.00045566012950521497, 'samples': 15611392, 'steps': 30490, 'loss/train': 1.595499873161316}
-03/05/2022 01:17:58 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 01:18:01 - INFO - codeparrot_training - Step 30491: {'lr': 0.0004556571122464941, 'samples': 15611904, 'steps': 30491, 'loss/train': 0.9231150150299072}
-03/05/2022 01:18:05 - INFO - codeparrot_training - Step 30492: {'lr': 0.0004556540948951073, 'samples': 15612416, 'steps': 30492, 'loss/train': 1.1141771078109741}
-03/05/2022 01:18:07 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/05/2022 01:18:10 - INFO - codeparrot_training - Step 30493: {'lr': 0.00045565107745105594, 'samples': 15612928, 'steps': 30493, 'loss/train': 1.700252652168274}
-03/05/2022 01:18:13 - INFO - codeparrot_training - Step 30494: {'lr': 0.00045564805991434135, 'samples': 15613440, 'steps': 30494, 'loss/train': 3.7589571475982666}
-03/05/2022 01:18:16 - INFO - codeparrot_training - Step 30495: {'lr': 0.00045564504228496494, 'samples': 15613952, 'steps': 30495, 'loss/train': 1.7340096235275269}
-03/05/2022 01:18:16 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/05/2022 01:18:22 - INFO - codeparrot_training - Step 30496: {'lr': 0.0004556420245629281, 'samples': 15614464, 'steps': 30496, 'loss/train': 1.672154188156128}
-03/05/2022 01:18:25 - INFO - codeparrot_training - Step 30497: {'lr': 0.00045563900674823205, 'samples': 15614976, 'steps': 30497, 'loss/train': 2.5248501300811768}
-03/05/2022 01:18:25 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/05/2022 01:18:30 - INFO - codeparrot_training - Step 30498: {'lr': 0.0004556359888408783, 'samples': 15615488, 'steps': 30498, 'loss/train': 6.580761909484863}
-03/05/2022 01:18:33 - INFO - codeparrot_training - Step 30499: {'lr': 0.00045563297084086807, 'samples': 15616000, 'steps': 30499, 'loss/train': 2.007497787475586}
-03/05/2022 01:18:34 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/05/2022 01:18:39 - INFO - codeparrot_training - Step 30500: {'lr': 0.00045562995274820285, 'samples': 15616512, 'steps': 30500, 'loss/train': 1.5775742530822754}
-03/05/2022 01:18:42 - INFO - codeparrot_training - Step 30501: {'lr': 0.00045562693456288394, 'samples': 15617024, 'steps': 30501, 'loss/train': 1.2036188840866089}
-03/05/2022 01:18:42 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/05/2022 01:18:47 - INFO - codeparrot_training - Step 30502: {'lr': 0.00045562391628491274, 'samples': 15617536, 'steps': 30502, 'loss/train': 1.5936039686203003}
-03/05/2022 01:18:50 - INFO - codeparrot_training - Step 30503: {'lr': 0.00045562089791429056, 'samples': 15618048, 'steps': 30503, 'loss/train': 3.3216190338134766}
-03/05/2022 01:18:51 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/05/2022 01:18:56 - INFO - codeparrot_training - Step 30504: {'lr': 0.00045561787945101875, 'samples': 15618560, 'steps': 30504, 'loss/train': 2.2713258266448975}
-03/05/2022 01:18:59 - INFO - codeparrot_training - Step 30505: {'lr': 0.0004556148608950987, 'samples': 15619072, 'steps': 30505, 'loss/train': 2.04522705078125}
-03/05/2022 01:19:00 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/05/2022 01:19:04 - INFO - codeparrot_training - Step 30506: {'lr': 0.0004556118422465319, 'samples': 15619584, 'steps': 30506, 'loss/train': 0.8919593095779419}
-03/05/2022 01:19:07 - INFO - codeparrot_training - Step 30507: {'lr': 0.00045560882350531936, 'samples': 15620096, 'steps': 30507, 'loss/train': 2.0622689723968506}
-03/05/2022 01:19:08 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/05/2022 01:19:12 - INFO - codeparrot_training - Step 30508: {'lr': 0.00045560580467146275, 'samples': 15620608, 'steps': 30508, 'loss/train': 1.3258651494979858}
-03/05/2022 01:19:15 - INFO - codeparrot_training - Step 30509: {'lr': 0.00045560278574496334, 'samples': 15621120, 'steps': 30509, 'loss/train': 2.6732876300811768}
-03/05/2022 01:19:16 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 01:19:21 - INFO - codeparrot_training - Step 30510: {'lr': 0.0004555997667258225, 'samples': 15621632, 'steps': 30510, 'loss/train': 2.1665115356445312}
-03/05/2022 01:19:24 - INFO - codeparrot_training - Step 30511: {'lr': 0.0004555967476140416, 'samples': 15622144, 'steps': 30511, 'loss/train': 1.3707630634307861}
-03/05/2022 01:19:24 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/05/2022 01:19:29 - INFO - codeparrot_training - Step 30512: {'lr': 0.00045559372840962186, 'samples': 15622656, 'steps': 30512, 'loss/train': 1.9391942024230957}
-03/05/2022 01:19:32 - INFO - codeparrot_training - Step 30513: {'lr': 0.00045559070911256486, 'samples': 15623168, 'steps': 30513, 'loss/train': 1.6365269422531128}
-03/05/2022 01:19:34 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/05/2022 01:19:38 - INFO - codeparrot_training - Step 30514: {'lr': 0.00045558768972287183, 'samples': 15623680, 'steps': 30514, 'loss/train': 1.7687983512878418}
-03/05/2022 01:19:41 - INFO - codeparrot_training - Step 30515: {'lr': 0.0004555846702405442, 'samples': 15624192, 'steps': 30515, 'loss/train': 1.8858639001846313}
-03/05/2022 01:19:42 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 01:19:46 - INFO - codeparrot_training - Step 30516: {'lr': 0.0004555816506655832, 'samples': 15624704, 'steps': 30516, 'loss/train': 2.480917453765869}
-03/05/2022 01:19:49 - INFO - codeparrot_training - Step 30517: {'lr': 0.00045557863099799034, 'samples': 15625216, 'steps': 30517, 'loss/train': 2.493565082550049}
-03/05/2022 01:19:50 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 01:19:55 - INFO - codeparrot_training - Step 30518: {'lr': 0.000455575611237767, 'samples': 15625728, 'steps': 30518, 'loss/train': 1.6163883209228516}
-03/05/2022 01:19:58 - INFO - codeparrot_training - Step 30519: {'lr': 0.00045557259138491435, 'samples': 15626240, 'steps': 30519, 'loss/train': 2.393575668334961}
-03/05/2022 01:19:59 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/05/2022 01:20:03 - INFO - codeparrot_training - Step 30520: {'lr': 0.0004555695714394339, 'samples': 15626752, 'steps': 30520, 'loss/train': 5.482495307922363}
-03/05/2022 01:20:06 - INFO - codeparrot_training - Step 30521: {'lr': 0.00045556655140132696, 'samples': 15627264, 'steps': 30521, 'loss/train': 1.679814338684082}
-03/05/2022 01:20:07 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/05/2022 01:20:12 - INFO - codeparrot_training - Step 30522: {'lr': 0.00045556353127059493, 'samples': 15627776, 'steps': 30522, 'loss/train': 1.9187484979629517}
-03/05/2022 01:20:15 - INFO - codeparrot_training - Step 30523: {'lr': 0.0004555605110472391, 'samples': 15628288, 'steps': 30523, 'loss/train': 3.093512773513794}
-03/05/2022 01:20:15 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/05/2022 01:20:20 - INFO - codeparrot_training - Step 30524: {'lr': 0.0004555574907312609, 'samples': 15628800, 'steps': 30524, 'loss/train': 2.110553741455078}
-03/05/2022 01:20:23 - INFO - codeparrot_training - Step 30525: {'lr': 0.00045555447032266167, 'samples': 15629312, 'steps': 30525, 'loss/train': 1.5908859968185425}
-03/05/2022 01:20:23 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/05/2022 01:20:28 - INFO - codeparrot_training - Step 30526: {'lr': 0.0004555514498214428, 'samples': 15629824, 'steps': 30526, 'loss/train': 1.18439781665802}
-03/05/2022 01:20:32 - INFO - codeparrot_training - Step 30527: {'lr': 0.0004555484292276055, 'samples': 15630336, 'steps': 30527, 'loss/train': 1.8635817766189575}
-03/05/2022 01:20:32 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/05/2022 01:20:37 - INFO - codeparrot_training - Step 30528: {'lr': 0.0004555454085411514, 'samples': 15630848, 'steps': 30528, 'loss/train': 2.3025524616241455}
-03/05/2022 01:20:40 - INFO - codeparrot_training - Step 30529: {'lr': 0.0004555423877620817, 'samples': 15631360, 'steps': 30529, 'loss/train': 6.811587810516357}
-03/05/2022 01:20:41 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 01:20:46 - INFO - codeparrot_training - Step 30530: {'lr': 0.00045553936689039765, 'samples': 15631872, 'steps': 30530, 'loss/train': 0.7969969511032104}
-03/05/2022 01:20:49 - INFO - codeparrot_training - Step 30531: {'lr': 0.00045553634592610084, 'samples': 15632384, 'steps': 30531, 'loss/train': 0.6186039447784424}
-03/05/2022 01:20:49 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 01:20:54 - INFO - codeparrot_training - Step 30532: {'lr': 0.00045553332486919246, 'samples': 15632896, 'steps': 30532, 'loss/train': 0.7514795064926147}
-03/05/2022 01:20:57 - INFO - codeparrot_training - Step 30533: {'lr': 0.000455530303719674, 'samples': 15633408, 'steps': 30533, 'loss/train': 1.7468414306640625}
-03/05/2022 01:20:58 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/05/2022 01:21:02 - INFO - codeparrot_training - Step 30534: {'lr': 0.00045552728247754673, 'samples': 15633920, 'steps': 30534, 'loss/train': 1.3344918489456177}
-03/05/2022 01:21:06 - INFO - codeparrot_training - Step 30535: {'lr': 0.000455524261142812, 'samples': 15634432, 'steps': 30535, 'loss/train': 1.503164529800415}
-03/05/2022 01:21:06 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 01:21:11 - INFO - codeparrot_training - Step 30536: {'lr': 0.00045552123971547123, 'samples': 15634944, 'steps': 30536, 'loss/train': 1.4112521409988403}
-03/05/2022 01:21:14 - INFO - codeparrot_training - Step 30537: {'lr': 0.00045551821819552575, 'samples': 15635456, 'steps': 30537, 'loss/train': 1.826975703239441}
-03/05/2022 01:21:15 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/05/2022 01:21:19 - INFO - codeparrot_training - Step 30538: {'lr': 0.0004555151965829769, 'samples': 15635968, 'steps': 30538, 'loss/train': 0.896876871585846}
-03/05/2022 01:21:23 - INFO - codeparrot_training - Step 30539: {'lr': 0.0004555121748778261, 'samples': 15636480, 'steps': 30539, 'loss/train': 1.764379858970642}
-03/05/2022 01:21:23 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/05/2022 01:21:28 - INFO - codeparrot_training - Step 30540: {'lr': 0.0004555091530800748, 'samples': 15636992, 'steps': 30540, 'loss/train': 2.457692861557007}
-03/05/2022 01:21:31 - INFO - codeparrot_training - Step 30541: {'lr': 0.0004555061311897241, 'samples': 15637504, 'steps': 30541, 'loss/train': 1.7330117225646973}
-03/05/2022 01:21:31 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/05/2022 01:21:36 - INFO - codeparrot_training - Step 30542: {'lr': 0.0004555031092067756, 'samples': 15638016, 'steps': 30542, 'loss/train': 1.2393637895584106}
-03/05/2022 01:21:39 - INFO - codeparrot_training - Step 30543: {'lr': 0.00045550008713123047, 'samples': 15638528, 'steps': 30543, 'loss/train': 1.5893667936325073}
-03/05/2022 01:21:39 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/05/2022 01:21:45 - INFO - codeparrot_training - Step 30544: {'lr': 0.00045549706496309027, 'samples': 15639040, 'steps': 30544, 'loss/train': 2.5014889240264893}
-03/05/2022 01:21:48 - INFO - codeparrot_training - Step 30545: {'lr': 0.0004554940427023562, 'samples': 15639552, 'steps': 30545, 'loss/train': 1.3070255517959595}
-03/05/2022 01:21:48 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 01:21:53 - INFO - codeparrot_training - Step 30546: {'lr': 0.00045549102034902973, 'samples': 15640064, 'steps': 30546, 'loss/train': 1.8866541385650635}
-03/05/2022 01:21:56 - INFO - codeparrot_training - Step 30547: {'lr': 0.0004554879979031121, 'samples': 15640576, 'steps': 30547, 'loss/train': 1.5025571584701538}
-03/05/2022 01:21:56 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/05/2022 01:22:01 - INFO - codeparrot_training - Step 30548: {'lr': 0.00045548497536460487, 'samples': 15641088, 'steps': 30548, 'loss/train': 1.244983196258545}
-03/05/2022 01:22:04 - INFO - codeparrot_training - Step 30549: {'lr': 0.00045548195273350926, 'samples': 15641600, 'steps': 30549, 'loss/train': 1.721570611000061}
-03/05/2022 01:22:05 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/05/2022 01:22:10 - INFO - codeparrot_training - Step 30550: {'lr': 0.0004554789300098265, 'samples': 15642112, 'steps': 30550, 'loss/train': 1.398437738418579}
-03/05/2022 01:22:13 - INFO - codeparrot_training - Step 30551: {'lr': 0.00045547590719355823, 'samples': 15642624, 'steps': 30551, 'loss/train': 1.5419656038284302}
-03/05/2022 01:22:13 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/05/2022 01:22:18 - INFO - codeparrot_training - Step 30552: {'lr': 0.00045547288428470574, 'samples': 15643136, 'steps': 30552, 'loss/train': 1.4432038068771362}
-03/05/2022 01:22:21 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/05/2022 01:22:23 - INFO - codeparrot_training - Step 30553: {'lr': 0.0004554698612832703, 'samples': 15643648, 'steps': 30553, 'loss/train': 1.002095103263855}
-03/05/2022 01:22:26 - INFO - codeparrot_training - Step 30554: {'lr': 0.00045546683818925327, 'samples': 15644160, 'steps': 30554, 'loss/train': 1.3449985980987549}
-03/05/2022 01:22:29 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/05/2022 01:22:32 - INFO - codeparrot_training - Step 30555: {'lr': 0.000455463815002656, 'samples': 15644672, 'steps': 30555, 'loss/train': 0.4842868447303772}
-03/05/2022 01:22:35 - INFO - codeparrot_training - Step 30556: {'lr': 0.00045546079172348, 'samples': 15645184, 'steps': 30556, 'loss/train': 1.6641240119934082}
-03/05/2022 01:22:38 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/05/2022 01:22:40 - INFO - codeparrot_training - Step 30557: {'lr': 0.00045545776835172647, 'samples': 15645696, 'steps': 30557, 'loss/train': 1.3659201860427856}
-03/05/2022 01:22:43 - INFO - codeparrot_training - Step 30558: {'lr': 0.00045545474488739693, 'samples': 15646208, 'steps': 30558, 'loss/train': 1.9520589113235474}
-03/05/2022 01:22:46 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/05/2022 01:22:48 - INFO - codeparrot_training - Step 30559: {'lr': 0.0004554517213304926, 'samples': 15646720, 'steps': 30559, 'loss/train': 2.3407187461853027}
-03/05/2022 01:22:52 - INFO - codeparrot_training - Step 30560: {'lr': 0.00045544869768101486, 'samples': 15647232, 'steps': 30560, 'loss/train': 1.9165687561035156}
-03/05/2022 01:22:54 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/05/2022 01:22:57 - INFO - codeparrot_training - Step 30561: {'lr': 0.0004554456739389652, 'samples': 15647744, 'steps': 30561, 'loss/train': 1.6392617225646973}
-03/05/2022 01:23:00 - INFO - codeparrot_training - Step 30562: {'lr': 0.00045544265010434484, 'samples': 15648256, 'steps': 30562, 'loss/train': 1.3429760932922363}
-03/05/2022 01:23:02 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/05/2022 01:23:05 - INFO - codeparrot_training - Step 30563: {'lr': 0.0004554396261771552, 'samples': 15648768, 'steps': 30563, 'loss/train': 1.4774656295776367}
-03/05/2022 01:23:08 - INFO - codeparrot_training - Step 30564: {'lr': 0.00045543660215739755, 'samples': 15649280, 'steps': 30564, 'loss/train': 1.8188945055007935}
-03/05/2022 01:23:11 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 01:23:14 - INFO - codeparrot_training - Step 30565: {'lr': 0.00045543357804507344, 'samples': 15649792, 'steps': 30565, 'loss/train': 1.3465498685836792}
-03/05/2022 01:23:17 - INFO - codeparrot_training - Step 30566: {'lr': 0.00045543055384018405, 'samples': 15650304, 'steps': 30566, 'loss/train': 1.3827776908874512}
-03/05/2022 01:23:19 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/05/2022 01:23:22 - INFO - codeparrot_training - Step 30567: {'lr': 0.0004554275295427309, 'samples': 15650816, 'steps': 30567, 'loss/train': 0.6985491514205933}
-03/05/2022 01:23:25 - INFO - codeparrot_training - Step 30568: {'lr': 0.0004554245051527153, 'samples': 15651328, 'steps': 30568, 'loss/train': 1.4645559787750244}
-03/05/2022 01:23:27 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/05/2022 01:23:30 - INFO - codeparrot_training - Step 30569: {'lr': 0.0004554214806701384, 'samples': 15651840, 'steps': 30569, 'loss/train': 2.65498685836792}
-03/05/2022 01:23:34 - INFO - codeparrot_training - Step 30570: {'lr': 0.000455418456095002, 'samples': 15652352, 'steps': 30570, 'loss/train': 1.0230474472045898}
-03/05/2022 01:23:36 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/05/2022 01:23:39 - INFO - codeparrot_training - Step 30571: {'lr': 0.000455415431427307, 'samples': 15652864, 'steps': 30571, 'loss/train': 2.5440292358398438}
-03/05/2022 01:23:42 - INFO - codeparrot_training - Step 30572: {'lr': 0.00045541240666705516, 'samples': 15653376, 'steps': 30572, 'loss/train': 0.7069652676582336}
-03/05/2022 01:23:45 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/05/2022 01:23:48 - INFO - codeparrot_training - Step 30573: {'lr': 0.0004554093818142475, 'samples': 15653888, 'steps': 30573, 'loss/train': 1.5299464464187622}
-03/05/2022 01:23:51 - INFO - codeparrot_training - Step 30574: {'lr': 0.0004554063568688857, 'samples': 15654400, 'steps': 30574, 'loss/train': 2.3961970806121826}
-03/05/2022 01:23:54 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/05/2022 01:23:56 - INFO - codeparrot_training - Step 30575: {'lr': 0.0004554033318309708, 'samples': 15654912, 'steps': 30575, 'loss/train': 2.5076241493225098}
-03/05/2022 01:23:59 - INFO - codeparrot_training - Step 30576: {'lr': 0.00045540030670050447, 'samples': 15655424, 'steps': 30576, 'loss/train': 0.21987862884998322}
-03/05/2022 01:24:02 - INFO - codeparrot_training - Step 30577: {'lr': 0.0004553972814774878, 'samples': 15655936, 'steps': 30577, 'loss/train': 2.0527780055999756}
-03/05/2022 01:24:02 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 01:24:08 - INFO - codeparrot_training - Step 30578: {'lr': 0.00045539425616192243, 'samples': 15656448, 'steps': 30578, 'loss/train': 1.390587568283081}
-03/05/2022 01:24:11 - INFO - codeparrot_training - Step 30579: {'lr': 0.0004553912307538095, 'samples': 15656960, 'steps': 30579, 'loss/train': 1.6003605127334595}
-03/05/2022 01:24:11 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/05/2022 01:24:16 - INFO - codeparrot_training - Step 30580: {'lr': 0.0004553882052531504, 'samples': 15657472, 'steps': 30580, 'loss/train': 1.900411605834961}
-03/05/2022 01:24:20 - INFO - codeparrot_training - Step 30581: {'lr': 0.00045538517965994663, 'samples': 15657984, 'steps': 30581, 'loss/train': 2.160693645477295}
-03/05/2022 01:24:20 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 01:24:25 - INFO - codeparrot_training - Step 30582: {'lr': 0.0004553821539741994, 'samples': 15658496, 'steps': 30582, 'loss/train': 1.271679162979126}
-03/05/2022 01:24:28 - INFO - codeparrot_training - Step 30583: {'lr': 0.0004553791281959102, 'samples': 15659008, 'steps': 30583, 'loss/train': 2.137972116470337}
-03/05/2022 01:24:28 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/05/2022 01:24:34 - INFO - codeparrot_training - Step 30584: {'lr': 0.00045537610232508033, 'samples': 15659520, 'steps': 30584, 'loss/train': 1.634616494178772}
-03/05/2022 01:24:37 - INFO - codeparrot_training - Step 30585: {'lr': 0.0004553730763617111, 'samples': 15660032, 'steps': 30585, 'loss/train': 1.8432791233062744}
-03/05/2022 01:24:37 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 01:24:42 - INFO - codeparrot_training - Step 30586: {'lr': 0.000455370050305804, 'samples': 15660544, 'steps': 30586, 'loss/train': 2.2213644981384277}
-03/05/2022 01:24:45 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/05/2022 01:24:47 - INFO - codeparrot_training - Step 30587: {'lr': 0.0004553670241573603, 'samples': 15661056, 'steps': 30587, 'loss/train': 1.3643492460250854}
-03/05/2022 01:24:51 - INFO - codeparrot_training - Step 30588: {'lr': 0.00045536399791638133, 'samples': 15661568, 'steps': 30588, 'loss/train': 0.12203964591026306}
-03/05/2022 01:24:53 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/05/2022 01:24:56 - INFO - codeparrot_training - Step 30589: {'lr': 0.0004553609715828686, 'samples': 15662080, 'steps': 30589, 'loss/train': 2.055931568145752}
-03/05/2022 01:24:59 - INFO - codeparrot_training - Step 30590: {'lr': 0.00045535794515682334, 'samples': 15662592, 'steps': 30590, 'loss/train': 1.9583996534347534}
-03/05/2022 01:25:02 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/05/2022 01:25:04 - INFO - codeparrot_training - Step 30591: {'lr': 0.00045535491863824695, 'samples': 15663104, 'steps': 30591, 'loss/train': 0.9677415490150452}
-03/05/2022 01:25:07 - INFO - codeparrot_training - Step 30592: {'lr': 0.0004553518920271408, 'samples': 15663616, 'steps': 30592, 'loss/train': 1.3254523277282715}
-03/05/2022 01:25:10 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/05/2022 01:25:13 - INFO - codeparrot_training - Step 30593: {'lr': 0.00045534886532350627, 'samples': 15664128, 'steps': 30593, 'loss/train': 2.040125608444214}
-03/05/2022 01:25:16 - INFO - codeparrot_training - Step 30594: {'lr': 0.00045534583852734474, 'samples': 15664640, 'steps': 30594, 'loss/train': 1.9252053499221802}
-03/05/2022 01:25:18 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/05/2022 01:25:21 - INFO - codeparrot_training - Step 30595: {'lr': 0.00045534281163865756, 'samples': 15665152, 'steps': 30595, 'loss/train': 1.4463013410568237}
-03/05/2022 01:25:24 - INFO - codeparrot_training - Step 30596: {'lr': 0.000455339784657446, 'samples': 15665664, 'steps': 30596, 'loss/train': 1.8405228853225708}
-03/05/2022 01:25:26 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 01:25:29 - INFO - codeparrot_training - Step 30597: {'lr': 0.0004553367575837115, 'samples': 15666176, 'steps': 30597, 'loss/train': 1.485500693321228}
-03/05/2022 01:25:33 - INFO - codeparrot_training - Step 30598: {'lr': 0.00045533373041745545, 'samples': 15666688, 'steps': 30598, 'loss/train': 1.8427996635437012}
-03/05/2022 01:25:35 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/05/2022 01:25:38 - INFO - codeparrot_training - Step 30599: {'lr': 0.00045533070315867917, 'samples': 15667200, 'steps': 30599, 'loss/train': 1.323441982269287}
-03/05/2022 01:25:41 - INFO - codeparrot_training - Step 30600: {'lr': 0.0004553276758073841, 'samples': 15667712, 'steps': 30600, 'loss/train': 1.608496904373169}
-03/05/2022 01:25:43 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/05/2022 01:25:46 - INFO - codeparrot_training - Step 30601: {'lr': 0.00045532464836357155, 'samples': 15668224, 'steps': 30601, 'loss/train': 2.0748708248138428}
-03/05/2022 01:25:49 - INFO - codeparrot_training - Step 30602: {'lr': 0.0004553216208272428, 'samples': 15668736, 'steps': 30602, 'loss/train': 1.092337965965271}
-03/05/2022 01:25:51 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/05/2022 01:25:55 - INFO - codeparrot_training - Step 30603: {'lr': 0.0004553185931983994, 'samples': 15669248, 'steps': 30603, 'loss/train': 1.4149433374404907}
-03/05/2022 01:25:58 - INFO - codeparrot_training - Step 30604: {'lr': 0.00045531556547704255, 'samples': 15669760, 'steps': 30604, 'loss/train': 1.3749829530715942}
-03/05/2022 01:26:00 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/05/2022 01:26:03 - INFO - codeparrot_training - Step 30605: {'lr': 0.00045531253766317373, 'samples': 15670272, 'steps': 30605, 'loss/train': 1.5338456630706787}
-03/05/2022 01:26:06 - INFO - codeparrot_training - Step 30606: {'lr': 0.0004553095097567942, 'samples': 15670784, 'steps': 30606, 'loss/train': 2.0647571086883545}
-03/05/2022 01:26:08 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 01:26:11 - INFO - codeparrot_training - Step 30607: {'lr': 0.0004553064817579053, 'samples': 15671296, 'steps': 30607, 'loss/train': 0.8874843716621399}
-03/05/2022 01:26:15 - INFO - codeparrot_training - Step 30608: {'lr': 0.0004553034536665086, 'samples': 15671808, 'steps': 30608, 'loss/train': 1.807150959968567}
-03/05/2022 01:26:16 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/05/2022 01:26:20 - INFO - codeparrot_training - Step 30609: {'lr': 0.0004553004254826053, 'samples': 15672320, 'steps': 30609, 'loss/train': 1.8416059017181396}
-03/05/2022 01:26:23 - INFO - codeparrot_training - Step 30610: {'lr': 0.0004552973972061967, 'samples': 15672832, 'steps': 30610, 'loss/train': 1.0278350114822388}
-03/05/2022 01:26:25 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/05/2022 01:26:28 - INFO - codeparrot_training - Step 30611: {'lr': 0.00045529436883728436, 'samples': 15673344, 'steps': 30611, 'loss/train': 1.6898707151412964}
-03/05/2022 01:26:32 - INFO - codeparrot_training - Step 30612: {'lr': 0.0004552913403758695, 'samples': 15673856, 'steps': 30612, 'loss/train': 1.1349802017211914}
-03/05/2022 01:26:33 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/05/2022 01:26:37 - INFO - codeparrot_training - Step 30613: {'lr': 0.00045528831182195355, 'samples': 15674368, 'steps': 30613, 'loss/train': 1.7550075054168701}
-03/05/2022 01:26:40 - INFO - codeparrot_training - Step 30614: {'lr': 0.00045528528317553786, 'samples': 15674880, 'steps': 30614, 'loss/train': 2.2082571983337402}
-03/05/2022 01:26:41 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/05/2022 01:26:45 - INFO - codeparrot_training - Step 30615: {'lr': 0.0004552822544366238, 'samples': 15675392, 'steps': 30615, 'loss/train': 1.1485567092895508}
-03/05/2022 01:26:48 - INFO - codeparrot_training - Step 30616: {'lr': 0.00045527922560521274, 'samples': 15675904, 'steps': 30616, 'loss/train': 0.07499045878648758}
-03/05/2022 01:26:50 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/05/2022 01:26:54 - INFO - codeparrot_training - Step 30617: {'lr': 0.0004552761966813059, 'samples': 15676416, 'steps': 30617, 'loss/train': 1.6735488176345825}
-03/05/2022 01:26:57 - INFO - codeparrot_training - Step 30618: {'lr': 0.00045527316766490487, 'samples': 15676928, 'steps': 30618, 'loss/train': 1.7222900390625}
-03/05/2022 01:26:58 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/05/2022 01:27:02 - INFO - codeparrot_training - Step 30619: {'lr': 0.000455270138556011, 'samples': 15677440, 'steps': 30619, 'loss/train': 2.4266185760498047}
-03/05/2022 01:27:06 - INFO - codeparrot_training - Step 30620: {'lr': 0.00045526710935462543, 'samples': 15677952, 'steps': 30620, 'loss/train': 2.022840976715088}
-03/05/2022 01:27:07 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/05/2022 01:27:11 - INFO - codeparrot_training - Step 30621: {'lr': 0.00045526408006074973, 'samples': 15678464, 'steps': 30621, 'loss/train': 1.3902665376663208}
-03/05/2022 01:27:14 - INFO - codeparrot_training - Step 30622: {'lr': 0.00045526105067438525, 'samples': 15678976, 'steps': 30622, 'loss/train': 1.7090548276901245}
-03/05/2022 01:27:15 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/05/2022 01:27:19 - INFO - codeparrot_training - Step 30623: {'lr': 0.00045525802119553323, 'samples': 15679488, 'steps': 30623, 'loss/train': 1.6807901859283447}
-03/05/2022 01:27:22 - INFO - codeparrot_training - Step 30624: {'lr': 0.0004552549916241951, 'samples': 15680000, 'steps': 30624, 'loss/train': 2.7836928367614746}
-03/05/2022 01:27:24 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/05/2022 01:27:28 - INFO - codeparrot_training - Step 30625: {'lr': 0.0004552519619603723, 'samples': 15680512, 'steps': 30625, 'loss/train': 1.4765536785125732}
-03/05/2022 01:27:31 - INFO - codeparrot_training - Step 30626: {'lr': 0.00045524893220406617, 'samples': 15681024, 'steps': 30626, 'loss/train': 1.6688754558563232}
-03/05/2022 01:27:32 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/05/2022 01:27:36 - INFO - codeparrot_training - Step 30627: {'lr': 0.00045524590235527796, 'samples': 15681536, 'steps': 30627, 'loss/train': 0.10068529099225998}
-03/05/2022 01:27:39 - INFO - codeparrot_training - Step 30628: {'lr': 0.0004552428724140091, 'samples': 15682048, 'steps': 30628, 'loss/train': 0.657551646232605}
-03/05/2022 01:27:40 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/05/2022 01:27:45 - INFO - codeparrot_training - Step 30629: {'lr': 0.000455239842380261, 'samples': 15682560, 'steps': 30629, 'loss/train': 1.9620801210403442}
-03/05/2022 01:27:48 - INFO - codeparrot_training - Step 30630: {'lr': 0.000455236812254035, 'samples': 15683072, 'steps': 30630, 'loss/train': 0.7647385001182556}
-03/05/2022 01:27:49 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 01:27:53 - INFO - codeparrot_training - Step 30631: {'lr': 0.0004552337820353325, 'samples': 15683584, 'steps': 30631, 'loss/train': 1.2443211078643799}
-03/05/2022 01:27:56 - INFO - codeparrot_training - Step 30632: {'lr': 0.00045523075172415476, 'samples': 15684096, 'steps': 30632, 'loss/train': 1.95291006565094}
-03/05/2022 01:27:57 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/05/2022 01:28:02 - INFO - codeparrot_training - Step 30633: {'lr': 0.0004552277213205032, 'samples': 15684608, 'steps': 30633, 'loss/train': 1.499145746231079}
-03/05/2022 01:28:05 - INFO - codeparrot_training - Step 30634: {'lr': 0.0004552246908243792, 'samples': 15685120, 'steps': 30634, 'loss/train': 1.3935949802398682}
-03/05/2022 01:28:05 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 01:28:10 - INFO - codeparrot_training - Step 30635: {'lr': 0.00045522166023578413, 'samples': 15685632, 'steps': 30635, 'loss/train': 1.4393086433410645}
-03/05/2022 01:28:13 - INFO - codeparrot_training - Step 30636: {'lr': 0.0004552186295547194, 'samples': 15686144, 'steps': 30636, 'loss/train': 1.622164249420166}
-03/05/2022 01:28:14 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 01:28:18 - INFO - codeparrot_training - Step 30637: {'lr': 0.0004552155987811863, 'samples': 15686656, 'steps': 30637, 'loss/train': 1.506044626235962}
-03/05/2022 01:28:22 - INFO - codeparrot_training - Step 30638: {'lr': 0.00045521256791518616, 'samples': 15687168, 'steps': 30638, 'loss/train': 2.505302906036377}
-03/05/2022 01:28:22 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 01:28:27 - INFO - codeparrot_training - Step 30639: {'lr': 0.0004552095369567205, 'samples': 15687680, 'steps': 30639, 'loss/train': 2.5269901752471924}
-03/05/2022 01:28:30 - INFO - codeparrot_training - Step 30640: {'lr': 0.00045520650590579056, 'samples': 15688192, 'steps': 30640, 'loss/train': 0.9382213950157166}
-03/05/2022 01:28:31 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/05/2022 01:28:35 - INFO - codeparrot_training - Step 30641: {'lr': 0.00045520347476239763, 'samples': 15688704, 'steps': 30641, 'loss/train': 1.3851901292800903}
-03/05/2022 01:28:38 - INFO - codeparrot_training - Step 30642: {'lr': 0.00045520044352654335, 'samples': 15689216, 'steps': 30642, 'loss/train': 2.114215850830078}
-03/05/2022 01:28:40 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 01:28:44 - INFO - codeparrot_training - Step 30643: {'lr': 0.0004551974121982288, 'samples': 15689728, 'steps': 30643, 'loss/train': 1.528570294380188}
-03/05/2022 01:28:47 - INFO - codeparrot_training - Step 30644: {'lr': 0.00045519438077745543, 'samples': 15690240, 'steps': 30644, 'loss/train': 1.8173609972000122}
-03/05/2022 01:28:48 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 01:28:52 - INFO - codeparrot_training - Step 30645: {'lr': 0.0004551913492642248, 'samples': 15690752, 'steps': 30645, 'loss/train': 2.14235782623291}
-03/05/2022 01:28:55 - INFO - codeparrot_training - Step 30646: {'lr': 0.00045518831765853796, 'samples': 15691264, 'steps': 30646, 'loss/train': 1.9143075942993164}
-03/05/2022 01:28:56 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/05/2022 01:29:01 - INFO - codeparrot_training - Step 30647: {'lr': 0.0004551852859603965, 'samples': 15691776, 'steps': 30647, 'loss/train': 1.9740931987762451}
-03/05/2022 01:29:04 - INFO - codeparrot_training - Step 30648: {'lr': 0.0004551822541698017, 'samples': 15692288, 'steps': 30648, 'loss/train': 1.8217936754226685}
-03/05/2022 01:29:04 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/05/2022 01:29:09 - INFO - codeparrot_training - Step 30649: {'lr': 0.0004551792222867549, 'samples': 15692800, 'steps': 30649, 'loss/train': 0.904915988445282}
-03/05/2022 01:29:12 - INFO - codeparrot_training - Step 30650: {'lr': 0.0004551761903112576, 'samples': 15693312, 'steps': 30650, 'loss/train': 1.3376164436340332}
-03/05/2022 01:29:13 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/05/2022 01:29:17 - INFO - codeparrot_training - Step 30651: {'lr': 0.000455173158243311, 'samples': 15693824, 'steps': 30651, 'loss/train': 1.5543268918991089}
-03/05/2022 01:29:21 - INFO - codeparrot_training - Step 30652: {'lr': 0.0004551701260829166, 'samples': 15694336, 'steps': 30652, 'loss/train': 1.339518427848816}
-03/05/2022 01:29:21 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/05/2022 01:29:26 - INFO - codeparrot_training - Step 30653: {'lr': 0.00045516709383007563, 'samples': 15694848, 'steps': 30653, 'loss/train': 2.28776216506958}
-03/05/2022 01:29:29 - INFO - codeparrot_training - Step 30654: {'lr': 0.0004551640614847896, 'samples': 15695360, 'steps': 30654, 'loss/train': 1.641797661781311}
-03/05/2022 01:29:29 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/05/2022 01:29:34 - INFO - codeparrot_training - Step 30655: {'lr': 0.00045516102904705983, 'samples': 15695872, 'steps': 30655, 'loss/train': 1.7911276817321777}
-03/05/2022 01:29:38 - INFO - codeparrot_training - Step 30656: {'lr': 0.0004551579965168876, 'samples': 15696384, 'steps': 30656, 'loss/train': 1.9853310585021973}
-03/05/2022 01:29:38 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/05/2022 01:29:43 - INFO - codeparrot_training - Step 30657: {'lr': 0.00045515496389427433, 'samples': 15696896, 'steps': 30657, 'loss/train': 0.0539902038872242}
-03/05/2022 01:29:46 - INFO - codeparrot_training - Step 30658: {'lr': 0.0004551519311792215, 'samples': 15697408, 'steps': 30658, 'loss/train': 2.108579158782959}
-03/05/2022 01:29:46 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/05/2022 01:29:51 - INFO - codeparrot_training - Step 30659: {'lr': 0.00045514889837173025, 'samples': 15697920, 'steps': 30659, 'loss/train': 2.070024013519287}
-03/05/2022 01:29:54 - INFO - codeparrot_training - Step 30660: {'lr': 0.00045514586547180214, 'samples': 15698432, 'steps': 30660, 'loss/train': 1.6773465871810913}
-03/05/2022 01:29:55 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/05/2022 01:30:00 - INFO - codeparrot_training - Step 30661: {'lr': 0.0004551428324794385, 'samples': 15698944, 'steps': 30661, 'loss/train': 1.616902470588684}
-03/05/2022 01:30:03 - INFO - codeparrot_training - Step 30662: {'lr': 0.00045513979939464056, 'samples': 15699456, 'steps': 30662, 'loss/train': 1.0830869674682617}
-03/05/2022 01:30:04 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/05/2022 01:30:09 - INFO - codeparrot_training - Step 30663: {'lr': 0.0004551367662174099, 'samples': 15699968, 'steps': 30663, 'loss/train': 2.3653385639190674}
-03/05/2022 01:30:12 - INFO - codeparrot_training - Step 30664: {'lr': 0.0004551337329477477, 'samples': 15700480, 'steps': 30664, 'loss/train': 1.9005095958709717}
-03/05/2022 01:30:14 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/05/2022 01:30:17 - INFO - codeparrot_training - Step 30665: {'lr': 0.00045513069958565545, 'samples': 15700992, 'steps': 30665, 'loss/train': 2.3354227542877197}
-03/05/2022 01:30:20 - INFO - codeparrot_training - Step 30666: {'lr': 0.00045512766613113457, 'samples': 15701504, 'steps': 30666, 'loss/train': 2.1672818660736084}
-03/05/2022 01:30:22 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 01:30:26 - INFO - codeparrot_training - Step 30667: {'lr': 0.00045512463258418615, 'samples': 15702016, 'steps': 30667, 'loss/train': 1.9206382036209106}
-03/05/2022 01:30:30 - INFO - codeparrot_training - Step 30668: {'lr': 0.00045512159894481183, 'samples': 15702528, 'steps': 30668, 'loss/train': 2.0869898796081543}
-03/05/2022 01:30:33 - INFO - codeparrot_training - Step 30669: {'lr': 0.00045511856521301286, 'samples': 15703040, 'steps': 30669, 'loss/train': 2.0879571437835693}
-03/05/2022 01:30:35 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/05/2022 01:30:38 - INFO - codeparrot_training - Step 30670: {'lr': 0.0004551155313887906, 'samples': 15703552, 'steps': 30670, 'loss/train': 1.6553771495819092}
-03/05/2022 01:30:41 - INFO - codeparrot_training - Step 30671: {'lr': 0.0004551124974721465, 'samples': 15704064, 'steps': 30671, 'loss/train': 2.672435998916626}
-03/05/2022 01:30:43 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 01:30:47 - INFO - codeparrot_training - Step 30672: {'lr': 0.00045510946346308186, 'samples': 15704576, 'steps': 30672, 'loss/train': 1.914102554321289}
-03/05/2022 01:30:50 - INFO - codeparrot_training - Step 30673: {'lr': 0.0004551064293615981, 'samples': 15705088, 'steps': 30673, 'loss/train': 1.2157970666885376}
-03/05/2022 01:30:52 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/05/2022 01:30:55 - INFO - codeparrot_training - Step 30674: {'lr': 0.00045510339516769647, 'samples': 15705600, 'steps': 30674, 'loss/train': 1.1249303817749023}
-03/05/2022 01:30:58 - INFO - codeparrot_training - Step 30675: {'lr': 0.0004551003608813784, 'samples': 15706112, 'steps': 30675, 'loss/train': 1.545224905014038}
-03/05/2022 01:31:00 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 01:31:03 - INFO - codeparrot_training - Step 30676: {'lr': 0.00045509732650264535, 'samples': 15706624, 'steps': 30676, 'loss/train': 1.7151719331741333}
-03/05/2022 01:31:06 - INFO - codeparrot_training - Step 30677: {'lr': 0.00045509429203149856, 'samples': 15707136, 'steps': 30677, 'loss/train': 1.8859766721725464}
-03/05/2022 01:31:08 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/05/2022 01:31:12 - INFO - codeparrot_training - Step 30678: {'lr': 0.00045509125746793946, 'samples': 15707648, 'steps': 30678, 'loss/train': 1.9827067852020264}
-03/05/2022 01:31:15 - INFO - codeparrot_training - Step 30679: {'lr': 0.00045508822281196937, 'samples': 15708160, 'steps': 30679, 'loss/train': 2.3717947006225586}
-03/05/2022 01:31:16 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/05/2022 01:31:20 - INFO - codeparrot_training - Step 30680: {'lr': 0.0004550851880635898, 'samples': 15708672, 'steps': 30680, 'loss/train': 1.8342174291610718}
-03/05/2022 01:31:23 - INFO - codeparrot_training - Step 30681: {'lr': 0.0004550821532228019, 'samples': 15709184, 'steps': 30681, 'loss/train': 1.468177318572998}
-03/05/2022 01:31:25 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/05/2022 01:31:29 - INFO - codeparrot_training - Step 30682: {'lr': 0.00045507911828960717, 'samples': 15709696, 'steps': 30682, 'loss/train': 1.5448837280273438}
-03/05/2022 01:31:32 - INFO - codeparrot_training - Step 30683: {'lr': 0.000455076083264007, 'samples': 15710208, 'steps': 30683, 'loss/train': 1.6553038358688354}
-03/05/2022 01:31:33 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/05/2022 01:31:37 - INFO - codeparrot_training - Step 30684: {'lr': 0.0004550730481460027, 'samples': 15710720, 'steps': 30684, 'loss/train': 1.1296297311782837}
-03/05/2022 01:31:40 - INFO - codeparrot_training - Step 30685: {'lr': 0.0004550700129355956, 'samples': 15711232, 'steps': 30685, 'loss/train': 1.7094225883483887}
-03/05/2022 01:31:42 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/05/2022 01:31:46 - INFO - codeparrot_training - Step 30686: {'lr': 0.0004550669776327871, 'samples': 15711744, 'steps': 30686, 'loss/train': 1.2141731977462769}
-03/05/2022 01:31:49 - INFO - codeparrot_training - Step 30687: {'lr': 0.00045506394223757867, 'samples': 15712256, 'steps': 30687, 'loss/train': 1.1551674604415894}
-03/05/2022 01:31:51 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 01:31:54 - INFO - codeparrot_training - Step 30688: {'lr': 0.00045506090674997157, 'samples': 15712768, 'steps': 30688, 'loss/train': 2.256469249725342}
-03/05/2022 01:31:57 - INFO - codeparrot_training - Step 30689: {'lr': 0.00045505787116996714, 'samples': 15713280, 'steps': 30689, 'loss/train': 1.6092214584350586}
-03/05/2022 01:31:59 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 01:32:03 - INFO - codeparrot_training - Step 30690: {'lr': 0.0004550548354975669, 'samples': 15713792, 'steps': 30690, 'loss/train': 2.069202184677124}
-03/05/2022 01:32:06 - INFO - codeparrot_training - Step 30691: {'lr': 0.000455051799732772, 'samples': 15714304, 'steps': 30691, 'loss/train': 1.7116682529449463}
-03/05/2022 01:32:08 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/05/2022 01:32:11 - INFO - codeparrot_training - Step 30692: {'lr': 0.000455048763875584, 'samples': 15714816, 'steps': 30692, 'loss/train': 1.3455792665481567}
-03/05/2022 01:32:14 - INFO - codeparrot_training - Step 30693: {'lr': 0.00045504572792600415, 'samples': 15715328, 'steps': 30693, 'loss/train': 1.4055207967758179}
-03/05/2022 01:32:16 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/05/2022 01:32:19 - INFO - codeparrot_training - Step 30694: {'lr': 0.00045504269188403386, 'samples': 15715840, 'steps': 30694, 'loss/train': 2.097240924835205}
-03/05/2022 01:32:23 - INFO - codeparrot_training - Step 30695: {'lr': 0.00045503965574967447, 'samples': 15716352, 'steps': 30695, 'loss/train': 1.2251014709472656}
-03/05/2022 01:32:24 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 01:32:28 - INFO - codeparrot_training - Step 30696: {'lr': 0.0004550366195229274, 'samples': 15716864, 'steps': 30696, 'loss/train': 1.4036637544631958}
-03/05/2022 01:32:31 - INFO - codeparrot_training - Step 30697: {'lr': 0.00045503358320379405, 'samples': 15717376, 'steps': 30697, 'loss/train': 0.11962788552045822}
-03/05/2022 01:32:33 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/05/2022 01:32:36 - INFO - codeparrot_training - Step 30698: {'lr': 0.00045503054679227567, 'samples': 15717888, 'steps': 30698, 'loss/train': 1.3659809827804565}
-03/05/2022 01:32:39 - INFO - codeparrot_training - Step 30699: {'lr': 0.00045502751028837367, 'samples': 15718400, 'steps': 30699, 'loss/train': 1.77561616897583}
-03/05/2022 01:32:41 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 01:32:44 - INFO - codeparrot_training - Step 30700: {'lr': 0.00045502447369208957, 'samples': 15718912, 'steps': 30700, 'loss/train': 1.814879298210144}
-03/05/2022 01:32:48 - INFO - codeparrot_training - Step 30701: {'lr': 0.00045502143700342445, 'samples': 15719424, 'steps': 30701, 'loss/train': 1.8131507635116577}
-03/05/2022 01:32:49 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/05/2022 01:32:53 - INFO - codeparrot_training - Step 30702: {'lr': 0.0004550184002223799, 'samples': 15719936, 'steps': 30702, 'loss/train': 1.9509031772613525}
-03/05/2022 01:32:56 - INFO - codeparrot_training - Step 30703: {'lr': 0.0004550153633489572, 'samples': 15720448, 'steps': 30703, 'loss/train': 1.8368234634399414}
-03/05/2022 01:32:57 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/05/2022 01:33:01 - INFO - codeparrot_training - Step 30704: {'lr': 0.0004550123263831578, 'samples': 15720960, 'steps': 30704, 'loss/train': 2.391666889190674}
-03/05/2022 01:33:05 - INFO - codeparrot_training - Step 30705: {'lr': 0.0004550092893249829, 'samples': 15721472, 'steps': 30705, 'loss/train': 1.7643426656723022}
-03/05/2022 01:33:05 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/05/2022 01:33:10 - INFO - codeparrot_training - Step 30706: {'lr': 0.00045500625217443404, 'samples': 15721984, 'steps': 30706, 'loss/train': 1.8344625234603882}
-03/05/2022 01:33:13 - INFO - codeparrot_training - Step 30707: {'lr': 0.0004550032149315125, 'samples': 15722496, 'steps': 30707, 'loss/train': 2.1288981437683105}
-03/05/2022 01:33:13 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/05/2022 01:33:18 - INFO - codeparrot_training - Step 30708: {'lr': 0.00045500017759621974, 'samples': 15723008, 'steps': 30708, 'loss/train': 1.791182041168213}
-03/05/2022 01:33:21 - INFO - codeparrot_training - Step 30709: {'lr': 0.00045499714016855705, 'samples': 15723520, 'steps': 30709, 'loss/train': 1.3242042064666748}
-03/05/2022 01:33:22 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/05/2022 01:33:27 - INFO - codeparrot_training - Step 30710: {'lr': 0.0004549941026485258, 'samples': 15724032, 'steps': 30710, 'loss/train': 2.5675158500671387}
-03/05/2022 01:33:30 - INFO - codeparrot_training - Step 30711: {'lr': 0.00045499106503612733, 'samples': 15724544, 'steps': 30711, 'loss/train': 1.8594111204147339}
-03/05/2022 01:33:30 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/05/2022 01:33:35 - INFO - codeparrot_training - Step 30712: {'lr': 0.00045498802733136306, 'samples': 15725056, 'steps': 30712, 'loss/train': 1.6014914512634277}
-03/05/2022 01:33:38 - INFO - codeparrot_training - Step 30713: {'lr': 0.0004549849895342344, 'samples': 15725568, 'steps': 30713, 'loss/train': 1.6373192071914673}
-03/05/2022 01:33:39 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/05/2022 01:33:43 - INFO - codeparrot_training - Step 30714: {'lr': 0.00045498195164474264, 'samples': 15726080, 'steps': 30714, 'loss/train': 2.4185588359832764}
-03/05/2022 01:33:47 - INFO - codeparrot_training - Step 30715: {'lr': 0.00045497891366288914, 'samples': 15726592, 'steps': 30715, 'loss/train': 2.04469895362854}
-03/05/2022 01:33:47 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/05/2022 01:33:52 - INFO - codeparrot_training - Step 30716: {'lr': 0.0004549758755886754, 'samples': 15727104, 'steps': 30716, 'loss/train': 2.1772382259368896}
-03/05/2022 01:33:55 - INFO - codeparrot_training - Step 30717: {'lr': 0.00045497283742210263, 'samples': 15727616, 'steps': 30717, 'loss/train': 1.9544272422790527}
-03/05/2022 01:33:55 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/05/2022 01:34:00 - INFO - codeparrot_training - Step 30718: {'lr': 0.0004549697991631722, 'samples': 15728128, 'steps': 30718, 'loss/train': 1.6482875347137451}
-03/05/2022 01:34:03 - INFO - codeparrot_training - Step 30719: {'lr': 0.0004549667608118856, 'samples': 15728640, 'steps': 30719, 'loss/train': 1.7668979167938232}
-03/05/2022 01:34:04 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 01:34:09 - INFO - codeparrot_training - Step 30720: {'lr': 0.0004549637223682441, 'samples': 15729152, 'steps': 30720, 'loss/train': 1.7266249656677246}
-03/05/2022 01:34:12 - INFO - codeparrot_training - Step 30721: {'lr': 0.0004549606838322492, 'samples': 15729664, 'steps': 30721, 'loss/train': 2.2422211170196533}
-03/05/2022 01:34:12 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/05/2022 01:34:17 - INFO - codeparrot_training - Step 30722: {'lr': 0.00045495764520390216, 'samples': 15730176, 'steps': 30722, 'loss/train': 1.8698594570159912}
-03/05/2022 01:34:20 - INFO - codeparrot_training - Step 30723: {'lr': 0.0004549546064832043, 'samples': 15730688, 'steps': 30723, 'loss/train': 1.5902607440948486}
-03/05/2022 01:34:20 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/05/2022 01:34:25 - INFO - codeparrot_training - Step 30724: {'lr': 0.0004549515676701571, 'samples': 15731200, 'steps': 30724, 'loss/train': 1.7164030075073242}
-03/05/2022 01:34:29 - INFO - codeparrot_training - Step 30725: {'lr': 0.0004549485287647619, 'samples': 15731712, 'steps': 30725, 'loss/train': 1.4147449731826782}
-03/05/2022 01:34:29 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/05/2022 01:34:34 - INFO - codeparrot_training - Step 30726: {'lr': 0.00045494548976702, 'samples': 15732224, 'steps': 30726, 'loss/train': 1.250527262687683}
-03/05/2022 01:34:37 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/05/2022 01:34:39 - INFO - codeparrot_training - Step 30727: {'lr': 0.0004549424506769329, 'samples': 15732736, 'steps': 30727, 'loss/train': 1.1734340190887451}
-03/05/2022 01:34:42 - INFO - codeparrot_training - Step 30728: {'lr': 0.00045493941149450185, 'samples': 15733248, 'steps': 30728, 'loss/train': 1.4060382843017578}
-03/05/2022 01:34:45 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/05/2022 01:34:48 - INFO - codeparrot_training - Step 30729: {'lr': 0.00045493637221972826, 'samples': 15733760, 'steps': 30729, 'loss/train': 1.8554925918579102}
-03/05/2022 01:34:51 - INFO - codeparrot_training - Step 30730: {'lr': 0.0004549333328526135, 'samples': 15734272, 'steps': 30730, 'loss/train': 2.0124828815460205}
-03/05/2022 01:34:53 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 01:34:56 - INFO - codeparrot_training - Step 30731: {'lr': 0.0004549302933931589, 'samples': 15734784, 'steps': 30731, 'loss/train': 1.2990275621414185}
-03/05/2022 01:34:59 - INFO - codeparrot_training - Step 30732: {'lr': 0.000454927253841366, 'samples': 15735296, 'steps': 30732, 'loss/train': 0.2546718716621399}
-03/05/2022 01:35:01 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 01:35:05 - INFO - codeparrot_training - Step 30733: {'lr': 0.00045492421419723595, 'samples': 15735808, 'steps': 30733, 'loss/train': 2.787313222885132}
-03/05/2022 01:35:08 - INFO - codeparrot_training - Step 30734: {'lr': 0.00045492117446077027, 'samples': 15736320, 'steps': 30734, 'loss/train': 1.8052736520767212}
-03/05/2022 01:35:10 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/05/2022 01:35:13 - INFO - codeparrot_training - Step 30735: {'lr': 0.0004549181346319702, 'samples': 15736832, 'steps': 30735, 'loss/train': 1.6567161083221436}
-03/05/2022 01:35:16 - INFO - codeparrot_training - Step 30736: {'lr': 0.00045491509471083717, 'samples': 15737344, 'steps': 30736, 'loss/train': 1.5889817476272583}
-03/05/2022 01:35:18 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 01:35:22 - INFO - codeparrot_training - Step 30737: {'lr': 0.00045491205469737263, 'samples': 15737856, 'steps': 30737, 'loss/train': 1.2483335733413696}
-03/05/2022 01:35:25 - INFO - codeparrot_training - Step 30738: {'lr': 0.00045490901459157787, 'samples': 15738368, 'steps': 30738, 'loss/train': 1.6420953273773193}
-03/05/2022 01:35:26 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/05/2022 01:35:30 - INFO - codeparrot_training - Step 30739: {'lr': 0.0004549059743934543, 'samples': 15738880, 'steps': 30739, 'loss/train': 2.5171022415161133}
-03/05/2022 01:35:33 - INFO - codeparrot_training - Step 30740: {'lr': 0.00045490293410300315, 'samples': 15739392, 'steps': 30740, 'loss/train': 1.0917596817016602}
-03/05/2022 01:35:35 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/05/2022 01:35:38 - INFO - codeparrot_training - Step 30741: {'lr': 0.000454899893720226, 'samples': 15739904, 'steps': 30741, 'loss/train': 1.8663716316223145}
-03/05/2022 01:35:41 - INFO - codeparrot_training - Step 30742: {'lr': 0.000454896853245124, 'samples': 15740416, 'steps': 30742, 'loss/train': 1.6075266599655151}
-03/05/2022 01:35:43 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/05/2022 01:35:47 - INFO - codeparrot_training - Step 30743: {'lr': 0.00045489381267769873, 'samples': 15740928, 'steps': 30743, 'loss/train': 1.824425458908081}
-03/05/2022 01:35:50 - INFO - codeparrot_training - Step 30744: {'lr': 0.00045489077201795147, 'samples': 15741440, 'steps': 30744, 'loss/train': 1.8720935583114624}
-03/05/2022 01:35:51 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/05/2022 01:35:55 - INFO - codeparrot_training - Step 30745: {'lr': 0.0004548877312658836, 'samples': 15741952, 'steps': 30745, 'loss/train': 1.1346352100372314}
-03/05/2022 01:35:58 - INFO - codeparrot_training - Step 30746: {'lr': 0.0004548846904214964, 'samples': 15742464, 'steps': 30746, 'loss/train': 2.5220839977264404}
-03/05/2022 01:36:00 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/05/2022 01:36:04 - INFO - codeparrot_training - Step 30747: {'lr': 0.00045488164948479144, 'samples': 15742976, 'steps': 30747, 'loss/train': 2.026585102081299}
-03/05/2022 01:36:07 - INFO - codeparrot_training - Step 30748: {'lr': 0.0004548786084557699, 'samples': 15743488, 'steps': 30748, 'loss/train': 1.0012116432189941}
-03/05/2022 01:36:09 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/05/2022 01:36:12 - INFO - codeparrot_training - Step 30749: {'lr': 0.00045487556733443327, 'samples': 15744000, 'steps': 30749, 'loss/train': 1.69420325756073}
-03/05/2022 01:36:15 - INFO - codeparrot_training - Step 30750: {'lr': 0.0004548725261207828, 'samples': 15744512, 'steps': 30750, 'loss/train': 1.476548671722412}
-03/05/2022 01:36:17 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 01:36:21 - INFO - codeparrot_training - Step 30751: {'lr': 0.0004548694848148199, 'samples': 15745024, 'steps': 30751, 'loss/train': 1.6244127750396729}
-03/05/2022 01:36:24 - INFO - codeparrot_training - Step 30752: {'lr': 0.0004548664434165461, 'samples': 15745536, 'steps': 30752, 'loss/train': 2.8528285026550293}
-03/05/2022 01:36:26 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/05/2022 01:36:29 - INFO - codeparrot_training - Step 30753: {'lr': 0.0004548634019259625, 'samples': 15746048, 'steps': 30753, 'loss/train': 1.7841558456420898}
-03/05/2022 01:36:32 - INFO - codeparrot_training - Step 30754: {'lr': 0.0004548603603430708, 'samples': 15746560, 'steps': 30754, 'loss/train': 4.050764083862305}
-03/05/2022 01:36:34 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/05/2022 01:36:38 - INFO - codeparrot_training - Step 30755: {'lr': 0.00045485731866787206, 'samples': 15747072, 'steps': 30755, 'loss/train': 1.7684123516082764}
-03/05/2022 01:36:41 - INFO - codeparrot_training - Step 30756: {'lr': 0.00045485427690036774, 'samples': 15747584, 'steps': 30756, 'loss/train': 0.7266432642936707}
-03/05/2022 01:36:43 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/05/2022 01:36:46 - INFO - codeparrot_training - Step 30757: {'lr': 0.0004548512350405593, 'samples': 15748096, 'steps': 30757, 'loss/train': 2.1709625720977783}
-03/05/2022 01:36:49 - INFO - codeparrot_training - Step 30758: {'lr': 0.00045484819308844806, 'samples': 15748608, 'steps': 30758, 'loss/train': 1.403503179550171}
-03/05/2022 01:36:51 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/05/2022 01:36:54 - INFO - codeparrot_training - Step 30759: {'lr': 0.00045484515104403535, 'samples': 15749120, 'steps': 30759, 'loss/train': 2.087512969970703}
-03/05/2022 01:36:57 - INFO - codeparrot_training - Step 30760: {'lr': 0.00045484210890732257, 'samples': 15749632, 'steps': 30760, 'loss/train': 2.247074842453003}
-03/05/2022 01:36:59 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/05/2022 01:37:03 - INFO - codeparrot_training - Step 30761: {'lr': 0.0004548390666783111, 'samples': 15750144, 'steps': 30761, 'loss/train': 1.4539896249771118}
-03/05/2022 01:37:06 - INFO - codeparrot_training - Step 30762: {'lr': 0.00045483602435700233, 'samples': 15750656, 'steps': 30762, 'loss/train': 1.6335994005203247}
-03/05/2022 01:37:07 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/05/2022 01:37:11 - INFO - codeparrot_training - Step 30763: {'lr': 0.0004548329819433976, 'samples': 15751168, 'steps': 30763, 'loss/train': 2.28214955329895}
-03/05/2022 01:37:14 - INFO - codeparrot_training - Step 30764: {'lr': 0.00045482993943749835, 'samples': 15751680, 'steps': 30764, 'loss/train': 0.16114500164985657}
-03/05/2022 01:37:16 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/05/2022 01:37:20 - INFO - codeparrot_training - Step 30765: {'lr': 0.0004548268968393058, 'samples': 15752192, 'steps': 30765, 'loss/train': 1.8494385480880737}
-03/05/2022 01:37:23 - INFO - codeparrot_training - Step 30766: {'lr': 0.0004548238541488214, 'samples': 15752704, 'steps': 30766, 'loss/train': 2.242034673690796}
-03/05/2022 01:37:24 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/05/2022 01:37:28 - INFO - codeparrot_training - Step 30767: {'lr': 0.00045482081136604665, 'samples': 15753216, 'steps': 30767, 'loss/train': 1.715653657913208}
-03/05/2022 01:37:31 - INFO - codeparrot_training - Step 30768: {'lr': 0.0004548177684909827, 'samples': 15753728, 'steps': 30768, 'loss/train': 1.5245997905731201}
-03/05/2022 01:37:33 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/05/2022 01:37:37 - INFO - codeparrot_training - Step 30769: {'lr': 0.0004548147255236311, 'samples': 15754240, 'steps': 30769, 'loss/train': 1.3396127223968506}
-03/05/2022 01:37:40 - INFO - codeparrot_training - Step 30770: {'lr': 0.0004548116824639931, 'samples': 15754752, 'steps': 30770, 'loss/train': 1.587066888809204}
-03/05/2022 01:37:41 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/05/2022 01:37:45 - INFO - codeparrot_training - Step 30771: {'lr': 0.00045480863931207004, 'samples': 15755264, 'steps': 30771, 'loss/train': 1.6513841152191162}
-03/05/2022 01:37:48 - INFO - codeparrot_training - Step 30772: {'lr': 0.0004548055960678635, 'samples': 15755776, 'steps': 30772, 'loss/train': 2.532830238342285}
-03/05/2022 01:37:49 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 01:37:54 - INFO - codeparrot_training - Step 30773: {'lr': 0.0004548025527313746, 'samples': 15756288, 'steps': 30773, 'loss/train': 1.7222899198532104}
-03/05/2022 01:37:57 - INFO - codeparrot_training - Step 30774: {'lr': 0.00045479950930260495, 'samples': 15756800, 'steps': 30774, 'loss/train': 1.7327982187271118}
-03/05/2022 01:38:00 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/05/2022 01:38:03 - INFO - codeparrot_training - Step 30775: {'lr': 0.0004547964657815558, 'samples': 15757312, 'steps': 30775, 'loss/train': 1.6850329637527466}
-03/05/2022 01:38:06 - INFO - codeparrot_training - Step 30776: {'lr': 0.0004547934221682284, 'samples': 15757824, 'steps': 30776, 'loss/train': 2.104546546936035}
-03/05/2022 01:38:08 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/05/2022 01:38:11 - INFO - codeparrot_training - Step 30777: {'lr': 0.00045479037846262436, 'samples': 15758336, 'steps': 30777, 'loss/train': 1.4078751802444458}
-03/05/2022 01:38:14 - INFO - codeparrot_training - Step 30778: {'lr': 0.00045478733466474487, 'samples': 15758848, 'steps': 30778, 'loss/train': 1.4667441844940186}
-03/05/2022 01:38:17 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 01:38:20 - INFO - codeparrot_training - Step 30779: {'lr': 0.0004547842907745914, 'samples': 15759360, 'steps': 30779, 'loss/train': 1.3903471231460571}
-03/05/2022 01:38:23 - INFO - codeparrot_training - Step 30780: {'lr': 0.00045478124679216523, 'samples': 15759872, 'steps': 30780, 'loss/train': 2.5658891201019287}
-03/05/2022 01:38:25 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/05/2022 01:38:28 - INFO - codeparrot_training - Step 30781: {'lr': 0.00045477820271746784, 'samples': 15760384, 'steps': 30781, 'loss/train': 1.8569996356964111}
-03/05/2022 01:38:31 - INFO - codeparrot_training - Step 30782: {'lr': 0.00045477515855050056, 'samples': 15760896, 'steps': 30782, 'loss/train': 1.5852731466293335}
-03/05/2022 01:38:33 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/05/2022 01:38:36 - INFO - codeparrot_training - Step 30783: {'lr': 0.0004547721142912647, 'samples': 15761408, 'steps': 30783, 'loss/train': 1.8996022939682007}
-03/05/2022 01:38:39 - INFO - codeparrot_training - Step 30784: {'lr': 0.00045476906993976177, 'samples': 15761920, 'steps': 30784, 'loss/train': 2.065929651260376}
-03/05/2022 01:38:41 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/05/2022 01:38:45 - INFO - codeparrot_training - Step 30785: {'lr': 0.000454766025495993, 'samples': 15762432, 'steps': 30785, 'loss/train': 2.305896043777466}
-03/05/2022 01:38:49 - INFO - codeparrot_training - Step 30786: {'lr': 0.00045476298095995985, 'samples': 15762944, 'steps': 30786, 'loss/train': 1.1659975051879883}
-03/05/2022 01:38:52 - INFO - codeparrot_training - Step 30787: {'lr': 0.00045475993633166357, 'samples': 15763456, 'steps': 30787, 'loss/train': 1.3043948411941528}
-03/05/2022 01:38:53 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/05/2022 01:38:57 - INFO - codeparrot_training - Step 30788: {'lr': 0.00045475689161110565, 'samples': 15763968, 'steps': 30788, 'loss/train': 2.368839979171753}
-03/05/2022 01:39:00 - INFO - codeparrot_training - Step 30789: {'lr': 0.0004547538467982876, 'samples': 15764480, 'steps': 30789, 'loss/train': 2.1915481090545654}
-03/05/2022 01:39:01 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/05/2022 01:39:05 - INFO - codeparrot_training - Step 30790: {'lr': 0.00045475080189321044, 'samples': 15764992, 'steps': 30790, 'loss/train': 1.7539169788360596}
-03/05/2022 01:39:08 - INFO - codeparrot_training - Step 30791: {'lr': 0.00045474775689587576, 'samples': 15765504, 'steps': 30791, 'loss/train': 1.6622904539108276}
-03/05/2022 01:39:10 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/05/2022 01:39:14 - INFO - codeparrot_training - Step 30792: {'lr': 0.00045474471180628496, 'samples': 15766016, 'steps': 30792, 'loss/train': 1.3842405080795288}
-03/05/2022 01:39:17 - INFO - codeparrot_training - Step 30793: {'lr': 0.0004547416666244393, 'samples': 15766528, 'steps': 30793, 'loss/train': 2.1315224170684814}
-03/05/2022 01:39:18 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 01:39:22 - INFO - codeparrot_training - Step 30794: {'lr': 0.00045473862135034026, 'samples': 15767040, 'steps': 30794, 'loss/train': 1.0336943864822388}
-03/05/2022 01:39:25 - INFO - codeparrot_training - Step 30795: {'lr': 0.0004547355759839891, 'samples': 15767552, 'steps': 30795, 'loss/train': 2.08406662940979}
-03/05/2022 01:39:27 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/05/2022 01:39:31 - INFO - codeparrot_training - Step 30796: {'lr': 0.00045473253052538725, 'samples': 15768064, 'steps': 30796, 'loss/train': 2.0980448722839355}
-03/05/2022 01:39:34 - INFO - codeparrot_training - Step 30797: {'lr': 0.00045472948497453613, 'samples': 15768576, 'steps': 30797, 'loss/train': 1.688066005706787}
-03/05/2022 01:39:35 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/05/2022 01:39:39 - INFO - codeparrot_training - Step 30798: {'lr': 0.00045472643933143703, 'samples': 15769088, 'steps': 30798, 'loss/train': 1.7532328367233276}
-03/05/2022 01:39:42 - INFO - codeparrot_training - Step 30799: {'lr': 0.0004547233935960914, 'samples': 15769600, 'steps': 30799, 'loss/train': 0.9880354404449463}
-03/05/2022 01:39:43 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/05/2022 01:39:48 - INFO - codeparrot_training - Step 30800: {'lr': 0.00045472034776850045, 'samples': 15770112, 'steps': 30800, 'loss/train': 1.9037271738052368}
-03/05/2022 01:39:51 - INFO - codeparrot_training - Step 30801: {'lr': 0.0004547173018486658, 'samples': 15770624, 'steps': 30801, 'loss/train': 1.7513142824172974}
-03/05/2022 01:39:52 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/05/2022 01:39:56 - INFO - codeparrot_training - Step 30802: {'lr': 0.0004547142558365887, 'samples': 15771136, 'steps': 30802, 'loss/train': 1.4180409908294678}
-03/05/2022 01:39:59 - INFO - codeparrot_training - Step 30803: {'lr': 0.0004547112097322704, 'samples': 15771648, 'steps': 30803, 'loss/train': 2.2047057151794434}
-03/05/2022 01:40:00 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 01:40:04 - INFO - codeparrot_training - Step 30804: {'lr': 0.00045470816353571244, 'samples': 15772160, 'steps': 30804, 'loss/train': 2.505270004272461}
-03/05/2022 01:40:07 - INFO - codeparrot_training - Step 30805: {'lr': 0.00045470511724691613, 'samples': 15772672, 'steps': 30805, 'loss/train': 2.587362289428711}
-03/05/2022 01:40:08 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/05/2022 01:40:13 - INFO - codeparrot_training - Step 30806: {'lr': 0.0004547020708658829, 'samples': 15773184, 'steps': 30806, 'loss/train': 1.6315616369247437}
-03/05/2022 01:40:16 - INFO - codeparrot_training - Step 30807: {'lr': 0.000454699024392614, 'samples': 15773696, 'steps': 30807, 'loss/train': 0.7758349776268005}
-03/05/2022 01:40:16 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/05/2022 01:40:21 - INFO - codeparrot_training - Step 30808: {'lr': 0.0004546959778271109, 'samples': 15774208, 'steps': 30808, 'loss/train': 2.0164811611175537}
-03/05/2022 01:40:24 - INFO - codeparrot_training - Step 30809: {'lr': 0.00045469293116937504, 'samples': 15774720, 'steps': 30809, 'loss/train': 0.0774369165301323}
-03/05/2022 01:40:24 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/05/2022 01:40:30 - INFO - codeparrot_training - Step 30810: {'lr': 0.0004546898844194076, 'samples': 15775232, 'steps': 30810, 'loss/train': 1.8789349794387817}
-03/05/2022 01:40:33 - INFO - codeparrot_training - Step 30811: {'lr': 0.00045468683757721005, 'samples': 15775744, 'steps': 30811, 'loss/train': 1.7523642778396606}
-03/05/2022 01:40:33 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/05/2022 01:40:38 - INFO - codeparrot_training - Step 30812: {'lr': 0.0004546837906427839, 'samples': 15776256, 'steps': 30812, 'loss/train': 2.1858878135681152}
-03/05/2022 01:40:41 - INFO - codeparrot_training - Step 30813: {'lr': 0.00045468074361613026, 'samples': 15776768, 'steps': 30813, 'loss/train': 2.0944786071777344}
-03/05/2022 01:40:41 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/05/2022 01:40:47 - INFO - codeparrot_training - Step 30814: {'lr': 0.0004546776964972507, 'samples': 15777280, 'steps': 30814, 'loss/train': 2.180429697036743}
-03/05/2022 01:40:50 - INFO - codeparrot_training - Step 30815: {'lr': 0.00045467464928614657, 'samples': 15777792, 'steps': 30815, 'loss/train': 2.359980821609497}
-03/05/2022 01:40:50 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/05/2022 01:40:55 - INFO - codeparrot_training - Step 30816: {'lr': 0.0004546716019828191, 'samples': 15778304, 'steps': 30816, 'loss/train': 1.452144980430603}
-03/05/2022 01:40:58 - INFO - codeparrot_training - Step 30817: {'lr': 0.00045466855458726975, 'samples': 15778816, 'steps': 30817, 'loss/train': 0.07422531396150589}
-03/05/2022 01:40:58 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/05/2022 01:41:04 - INFO - codeparrot_training - Step 30818: {'lr': 0.0004546655070995, 'samples': 15779328, 'steps': 30818, 'loss/train': 0.13780811429023743}
-03/05/2022 01:41:07 - INFO - codeparrot_training - Step 30819: {'lr': 0.0004546624595195111, 'samples': 15779840, 'steps': 30819, 'loss/train': 1.803411602973938}
-03/05/2022 01:41:07 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/05/2022 01:41:12 - INFO - codeparrot_training - Step 30820: {'lr': 0.0004546594118473044, 'samples': 15780352, 'steps': 30820, 'loss/train': 2.544556140899658}
-03/05/2022 01:41:15 - INFO - codeparrot_training - Step 30821: {'lr': 0.0004546563640828814, 'samples': 15780864, 'steps': 30821, 'loss/train': 2.0499353408813477}
-03/05/2022 01:41:15 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/05/2022 01:41:21 - INFO - codeparrot_training - Step 30822: {'lr': 0.0004546533162262434, 'samples': 15781376, 'steps': 30822, 'loss/train': 2.396827220916748}
-03/05/2022 01:41:24 - INFO - codeparrot_training - Step 30823: {'lr': 0.00045465026827739175, 'samples': 15781888, 'steps': 30823, 'loss/train': 1.6210488080978394}
-03/05/2022 01:41:24 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 01:41:29 - INFO - codeparrot_training - Step 30824: {'lr': 0.00045464722023632784, 'samples': 15782400, 'steps': 30824, 'loss/train': 1.2770367860794067}
-03/05/2022 01:41:32 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/05/2022 01:41:35 - INFO - codeparrot_training - Step 30825: {'lr': 0.00045464417210305303, 'samples': 15782912, 'steps': 30825, 'loss/train': 1.3899425268173218}
-03/05/2022 01:41:38 - INFO - codeparrot_training - Step 30826: {'lr': 0.0004546411238775687, 'samples': 15783424, 'steps': 30826, 'loss/train': 2.4950389862060547}
-03/05/2022 01:41:40 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/05/2022 01:41:43 - INFO - codeparrot_training - Step 30827: {'lr': 0.00045463807555987633, 'samples': 15783936, 'steps': 30827, 'loss/train': 1.692447543144226}
-03/05/2022 01:41:46 - INFO - codeparrot_training - Step 30828: {'lr': 0.0004546350271499772, 'samples': 15784448, 'steps': 30828, 'loss/train': 1.7099703550338745}
-03/05/2022 01:41:49 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/05/2022 01:41:52 - INFO - codeparrot_training - Step 30829: {'lr': 0.0004546319786478726, 'samples': 15784960, 'steps': 30829, 'loss/train': 0.6490452885627747}
-03/05/2022 01:41:55 - INFO - codeparrot_training - Step 30830: {'lr': 0.000454628930053564, 'samples': 15785472, 'steps': 30830, 'loss/train': 0.9680806398391724}
-03/05/2022 01:41:57 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/05/2022 01:42:00 - INFO - codeparrot_training - Step 30831: {'lr': 0.0004546258813670528, 'samples': 15785984, 'steps': 30831, 'loss/train': 2.004863739013672}
-03/05/2022 01:42:03 - INFO - codeparrot_training - Step 30832: {'lr': 0.0004546228325883403, 'samples': 15786496, 'steps': 30832, 'loss/train': 0.37108874320983887}
-03/05/2022 01:42:06 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/05/2022 01:42:08 - INFO - codeparrot_training - Step 30833: {'lr': 0.00045461978371742794, 'samples': 15787008, 'steps': 30833, 'loss/train': 1.5389811992645264}
-03/05/2022 01:42:12 - INFO - codeparrot_training - Step 30834: {'lr': 0.00045461673475431704, 'samples': 15787520, 'steps': 30834, 'loss/train': 1.280617594718933}
-03/05/2022 01:42:14 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 01:42:17 - INFO - codeparrot_training - Step 30835: {'lr': 0.000454613685699009, 'samples': 15788032, 'steps': 30835, 'loss/train': 2.5214040279388428}
-03/05/2022 01:42:20 - INFO - codeparrot_training - Step 30836: {'lr': 0.0004546106365515052, 'samples': 15788544, 'steps': 30836, 'loss/train': 1.7270100116729736}
-03/05/2022 01:42:22 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/05/2022 01:42:25 - INFO - codeparrot_training - Step 30837: {'lr': 0.000454607587311807, 'samples': 15789056, 'steps': 30837, 'loss/train': 2.416752338409424}
-03/05/2022 01:42:29 - INFO - codeparrot_training - Step 30838: {'lr': 0.00045460453797991577, 'samples': 15789568, 'steps': 30838, 'loss/train': 1.8838835954666138}
-03/05/2022 01:42:31 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/05/2022 01:42:34 - INFO - codeparrot_training - Step 30839: {'lr': 0.00045460148855583295, 'samples': 15790080, 'steps': 30839, 'loss/train': 1.6490662097930908}
-03/05/2022 01:42:37 - INFO - codeparrot_training - Step 30840: {'lr': 0.00045459843903955977, 'samples': 15790592, 'steps': 30840, 'loss/train': 1.2708324193954468}
-03/05/2022 01:42:39 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/05/2022 01:42:42 - INFO - codeparrot_training - Step 30841: {'lr': 0.00045459538943109774, 'samples': 15791104, 'steps': 30841, 'loss/train': 2.188490152359009}
-03/05/2022 01:42:45 - INFO - codeparrot_training - Step 30842: {'lr': 0.0004545923397304482, 'samples': 15791616, 'steps': 30842, 'loss/train': 2.501016139984131}
-03/05/2022 01:42:47 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/05/2022 01:42:51 - INFO - codeparrot_training - Step 30843: {'lr': 0.0004545892899376125, 'samples': 15792128, 'steps': 30843, 'loss/train': 1.1459052562713623}
-03/05/2022 01:42:54 - INFO - codeparrot_training - Step 30844: {'lr': 0.000454586240052592, 'samples': 15792640, 'steps': 30844, 'loss/train': 1.919549584388733}
-03/05/2022 01:42:56 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/05/2022 01:42:59 - INFO - codeparrot_training - Step 30845: {'lr': 0.00045458319007538804, 'samples': 15793152, 'steps': 30845, 'loss/train': 1.5615907907485962}
-03/05/2022 01:43:02 - INFO - codeparrot_training - Step 30846: {'lr': 0.00045458014000600213, 'samples': 15793664, 'steps': 30846, 'loss/train': 1.6484390497207642}
-03/05/2022 01:43:05 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/05/2022 01:43:08 - INFO - codeparrot_training - Step 30847: {'lr': 0.00045457708984443556, 'samples': 15794176, 'steps': 30847, 'loss/train': 1.230629801750183}
-03/05/2022 01:43:11 - INFO - codeparrot_training - Step 30848: {'lr': 0.0004545740395906897, 'samples': 15794688, 'steps': 30848, 'loss/train': 2.2825987339019775}
-03/05/2022 01:43:14 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/05/2022 01:43:16 - INFO - codeparrot_training - Step 30849: {'lr': 0.0004545709892447659, 'samples': 15795200, 'steps': 30849, 'loss/train': 1.4703425168991089}
-03/05/2022 01:43:19 - INFO - codeparrot_training - Step 30850: {'lr': 0.00045456793880666556, 'samples': 15795712, 'steps': 30850, 'loss/train': 2.123150110244751}
-03/05/2022 01:43:22 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/05/2022 01:43:25 - INFO - codeparrot_training - Step 30851: {'lr': 0.0004545648882763902, 'samples': 15796224, 'steps': 30851, 'loss/train': 1.6535041332244873}
-03/05/2022 01:43:28 - INFO - codeparrot_training - Step 30852: {'lr': 0.0004545618376539409, 'samples': 15796736, 'steps': 30852, 'loss/train': 1.6485791206359863}
-03/05/2022 01:43:30 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/05/2022 01:43:33 - INFO - codeparrot_training - Step 30853: {'lr': 0.0004545587869393193, 'samples': 15797248, 'steps': 30853, 'loss/train': 1.8848695755004883}
-03/05/2022 01:43:36 - INFO - codeparrot_training - Step 30854: {'lr': 0.00045455573613252667, 'samples': 15797760, 'steps': 30854, 'loss/train': 1.846081018447876}
-03/05/2022 01:43:38 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 01:43:41 - INFO - codeparrot_training - Step 30855: {'lr': 0.0004545526852335643, 'samples': 15798272, 'steps': 30855, 'loss/train': 1.1993454694747925}
-03/05/2022 01:43:45 - INFO - codeparrot_training - Step 30856: {'lr': 0.0004545496342424337, 'samples': 15798784, 'steps': 30856, 'loss/train': 0.997812032699585}
-03/05/2022 01:43:46 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/05/2022 01:43:50 - INFO - codeparrot_training - Step 30857: {'lr': 0.00045454658315913617, 'samples': 15799296, 'steps': 30857, 'loss/train': 1.7588779926300049}
-03/05/2022 01:43:53 - INFO - codeparrot_training - Step 30858: {'lr': 0.0004545435319836731, 'samples': 15799808, 'steps': 30858, 'loss/train': 1.8263434171676636}
-03/05/2022 01:43:55 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/05/2022 01:43:58 - INFO - codeparrot_training - Step 30859: {'lr': 0.00045454048071604593, 'samples': 15800320, 'steps': 30859, 'loss/train': 2.0573976039886475}
-03/05/2022 01:44:02 - INFO - codeparrot_training - Step 30860: {'lr': 0.0004545374293562559, 'samples': 15800832, 'steps': 30860, 'loss/train': 1.8035696744918823}
-03/05/2022 01:44:03 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/05/2022 01:44:07 - INFO - codeparrot_training - Step 30861: {'lr': 0.00045453437790430446, 'samples': 15801344, 'steps': 30861, 'loss/train': 2.455286741256714}
-03/05/2022 01:44:10 - INFO - codeparrot_training - Step 30862: {'lr': 0.000454531326360193, 'samples': 15801856, 'steps': 30862, 'loss/train': 1.5836222171783447}
-03/05/2022 01:44:12 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/05/2022 01:44:15 - INFO - codeparrot_training - Step 30863: {'lr': 0.00045452827472392286, 'samples': 15802368, 'steps': 30863, 'loss/train': 1.4403066635131836}
-03/05/2022 01:44:19 - INFO - codeparrot_training - Step 30864: {'lr': 0.0004545252229954955, 'samples': 15802880, 'steps': 30864, 'loss/train': 1.3540735244750977}
-03/05/2022 01:44:20 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/05/2022 01:44:24 - INFO - codeparrot_training - Step 30865: {'lr': 0.00045452217117491225, 'samples': 15803392, 'steps': 30865, 'loss/train': 2.195787191390991}
-03/05/2022 01:44:27 - INFO - codeparrot_training - Step 30866: {'lr': 0.00045451911926217437, 'samples': 15803904, 'steps': 30866, 'loss/train': 0.8510196805000305}
-03/05/2022 01:44:29 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/05/2022 01:44:32 - INFO - codeparrot_training - Step 30867: {'lr': 0.00045451606725728337, 'samples': 15804416, 'steps': 30867, 'loss/train': 1.405698299407959}
-03/05/2022 01:44:36 - INFO - codeparrot_training - Step 30868: {'lr': 0.0004545130151602406, 'samples': 15804928, 'steps': 30868, 'loss/train': 1.5107038021087646}
-03/05/2022 01:44:37 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/05/2022 01:44:41 - INFO - codeparrot_training - Step 30869: {'lr': 0.00045450996297104743, 'samples': 15805440, 'steps': 30869, 'loss/train': 1.181347370147705}
-03/05/2022 01:44:44 - INFO - codeparrot_training - Step 30870: {'lr': 0.00045450691068970515, 'samples': 15805952, 'steps': 30870, 'loss/train': 2.0976436138153076}
-03/05/2022 01:44:45 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/05/2022 01:44:49 - INFO - codeparrot_training - Step 30871: {'lr': 0.00045450385831621534, 'samples': 15806464, 'steps': 30871, 'loss/train': 0.9618310928344727}
-03/05/2022 01:44:52 - INFO - codeparrot_training - Step 30872: {'lr': 0.0004545008058505792, 'samples': 15806976, 'steps': 30872, 'loss/train': 1.975067377090454}
-03/05/2022 01:44:53 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/05/2022 01:44:57 - INFO - codeparrot_training - Step 30873: {'lr': 0.0004544977532927981, 'samples': 15807488, 'steps': 30873, 'loss/train': 2.111354112625122}
-03/05/2022 01:45:01 - INFO - codeparrot_training - Step 30874: {'lr': 0.0004544947006428735, 'samples': 15808000, 'steps': 30874, 'loss/train': 2.0299127101898193}
-03/05/2022 01:45:02 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 01:45:06 - INFO - codeparrot_training - Step 30875: {'lr': 0.00045449164790080675, 'samples': 15808512, 'steps': 30875, 'loss/train': 1.534213662147522}
-03/05/2022 01:45:09 - INFO - codeparrot_training - Step 30876: {'lr': 0.00045448859506659926, 'samples': 15809024, 'steps': 30876, 'loss/train': 0.6772264242172241}
-03/05/2022 01:45:10 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/05/2022 01:45:14 - INFO - codeparrot_training - Step 30877: {'lr': 0.0004544855421402523, 'samples': 15809536, 'steps': 30877, 'loss/train': 1.5088136196136475}
-03/05/2022 01:45:17 - INFO - codeparrot_training - Step 30878: {'lr': 0.00045448248912176726, 'samples': 15810048, 'steps': 30878, 'loss/train': 2.041574239730835}
-03/05/2022 01:45:18 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 01:45:23 - INFO - codeparrot_training - Step 30879: {'lr': 0.00045447943601114563, 'samples': 15810560, 'steps': 30879, 'loss/train': 1.9911890029907227}
-03/05/2022 01:45:26 - INFO - codeparrot_training - Step 30880: {'lr': 0.00045447638280838877, 'samples': 15811072, 'steps': 30880, 'loss/train': 1.328418254852295}
-03/05/2022 01:45:26 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 01:45:31 - INFO - codeparrot_training - Step 30881: {'lr': 0.000454473329513498, 'samples': 15811584, 'steps': 30881, 'loss/train': 1.6789195537567139}
-03/05/2022 01:45:34 - INFO - codeparrot_training - Step 30882: {'lr': 0.0004544702761264746, 'samples': 15812096, 'steps': 30882, 'loss/train': 1.9404628276824951}
-03/05/2022 01:45:34 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/05/2022 01:45:39 - INFO - codeparrot_training - Step 30883: {'lr': 0.0004544672226473201, 'samples': 15812608, 'steps': 30883, 'loss/train': 2.4385030269622803}
-03/05/2022 01:45:43 - INFO - codeparrot_training - Step 30884: {'lr': 0.00045446416907603585, 'samples': 15813120, 'steps': 30884, 'loss/train': 1.62992525100708}
-03/05/2022 01:45:43 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/05/2022 01:45:48 - INFO - codeparrot_training - Step 30885: {'lr': 0.00045446111541262317, 'samples': 15813632, 'steps': 30885, 'loss/train': 0.2488349825143814}
-03/05/2022 01:45:51 - INFO - codeparrot_training - Step 30886: {'lr': 0.0004544580616570835, 'samples': 15814144, 'steps': 30886, 'loss/train': 1.811905860900879}
-03/05/2022 01:45:51 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/05/2022 01:45:56 - INFO - codeparrot_training - Step 30887: {'lr': 0.0004544550078094182, 'samples': 15814656, 'steps': 30887, 'loss/train': 1.7952262163162231}
-03/05/2022 01:46:00 - INFO - codeparrot_training - Step 30888: {'lr': 0.00045445195386962855, 'samples': 15815168, 'steps': 30888, 'loss/train': 1.796083927154541}
-03/05/2022 01:46:00 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 01:46:05 - INFO - codeparrot_training - Step 30889: {'lr': 0.0004544488998377161, 'samples': 15815680, 'steps': 30889, 'loss/train': 2.588817596435547}
-03/05/2022 01:46:08 - INFO - codeparrot_training - Step 30890: {'lr': 0.000454445845713682, 'samples': 15816192, 'steps': 30890, 'loss/train': 1.9734289646148682}
-03/05/2022 01:46:08 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/05/2022 01:46:13 - INFO - codeparrot_training - Step 30891: {'lr': 0.0004544427914975279, 'samples': 15816704, 'steps': 30891, 'loss/train': 2.2133333683013916}
-03/05/2022 01:46:16 - INFO - codeparrot_training - Step 30892: {'lr': 0.0004544397371892549, 'samples': 15817216, 'steps': 30892, 'loss/train': 2.083092212677002}
-03/05/2022 01:46:17 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/05/2022 01:46:22 - INFO - codeparrot_training - Step 30893: {'lr': 0.00045443668278886463, 'samples': 15817728, 'steps': 30893, 'loss/train': 0.8700692653656006}
-03/05/2022 01:46:25 - INFO - codeparrot_training - Step 30894: {'lr': 0.00045443362829635826, 'samples': 15818240, 'steps': 30894, 'loss/train': 1.9676061868667603}
-03/05/2022 01:46:25 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/05/2022 01:46:30 - INFO - codeparrot_training - Step 30895: {'lr': 0.00045443057371173727, 'samples': 15818752, 'steps': 30895, 'loss/train': 2.025254726409912}
-03/05/2022 01:46:33 - INFO - codeparrot_training - Step 30896: {'lr': 0.00045442751903500305, 'samples': 15819264, 'steps': 30896, 'loss/train': 2.0144519805908203}
-03/05/2022 01:46:33 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/05/2022 01:46:39 - INFO - codeparrot_training - Step 30897: {'lr': 0.0004544244642661569, 'samples': 15819776, 'steps': 30897, 'loss/train': 1.6518577337265015}
-03/05/2022 01:46:42 - INFO - codeparrot_training - Step 30898: {'lr': 0.00045442140940520027, 'samples': 15820288, 'steps': 30898, 'loss/train': 2.2372217178344727}
-03/05/2022 01:46:43 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/05/2022 01:46:47 - INFO - codeparrot_training - Step 30899: {'lr': 0.0004544183544521345, 'samples': 15820800, 'steps': 30899, 'loss/train': 1.3643090724945068}
-03/05/2022 01:46:50 - INFO - codeparrot_training - Step 30900: {'lr': 0.00045441529940696104, 'samples': 15821312, 'steps': 30900, 'loss/train': 1.5926587581634521}
-03/05/2022 01:46:51 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/05/2022 01:46:55 - INFO - codeparrot_training - Step 30901: {'lr': 0.0004544122442696811, 'samples': 15821824, 'steps': 30901, 'loss/train': 2.7287845611572266}
-03/05/2022 01:46:59 - INFO - codeparrot_training - Step 30902: {'lr': 0.0004544091890402962, 'samples': 15822336, 'steps': 30902, 'loss/train': 1.090118408203125}
-03/05/2022 01:46:59 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 01:47:04 - INFO - codeparrot_training - Step 30903: {'lr': 0.0004544061337188077, 'samples': 15822848, 'steps': 30903, 'loss/train': 1.7343541383743286}
-03/05/2022 01:47:07 - INFO - codeparrot_training - Step 30904: {'lr': 0.0004544030783052169, 'samples': 15823360, 'steps': 30904, 'loss/train': 1.6753623485565186}
-03/05/2022 01:47:07 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/05/2022 01:47:12 - INFO - codeparrot_training - Step 30905: {'lr': 0.0004544000227995253, 'samples': 15823872, 'steps': 30905, 'loss/train': 1.3007274866104126}
-03/05/2022 01:47:15 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/05/2022 01:47:17 - INFO - codeparrot_training - Step 30906: {'lr': 0.00045439696720173405, 'samples': 15824384, 'steps': 30906, 'loss/train': 1.2722312211990356}
-03/05/2022 01:47:21 - INFO - codeparrot_training - Step 30907: {'lr': 0.00045439391151184483, 'samples': 15824896, 'steps': 30907, 'loss/train': 1.3966833353042603}
-03/05/2022 01:47:23 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/05/2022 01:47:26 - INFO - codeparrot_training - Step 30908: {'lr': 0.0004543908557298588, 'samples': 15825408, 'steps': 30908, 'loss/train': 1.4870173931121826}
-03/05/2022 01:47:29 - INFO - codeparrot_training - Step 30909: {'lr': 0.0004543877998557775, 'samples': 15825920, 'steps': 30909, 'loss/train': 0.7243610620498657}
-03/05/2022 01:47:32 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 01:47:34 - INFO - codeparrot_training - Step 30910: {'lr': 0.00045438474388960205, 'samples': 15826432, 'steps': 30910, 'loss/train': 2.09417986869812}
-03/05/2022 01:47:37 - INFO - codeparrot_training - Step 30911: {'lr': 0.0004543816878313341, 'samples': 15826944, 'steps': 30911, 'loss/train': 2.2226531505584717}
-03/05/2022 01:47:40 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/05/2022 01:47:43 - INFO - codeparrot_training - Step 30912: {'lr': 0.0004543786316809749, 'samples': 15827456, 'steps': 30912, 'loss/train': 1.6105252504348755}
-03/05/2022 01:47:46 - INFO - codeparrot_training - Step 30913: {'lr': 0.0004543755754385258, 'samples': 15827968, 'steps': 30913, 'loss/train': 1.6186732053756714}
-03/05/2022 01:47:49 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/05/2022 01:47:51 - INFO - codeparrot_training - Step 30914: {'lr': 0.00045437251910398824, 'samples': 15828480, 'steps': 30914, 'loss/train': 1.6683251857757568}
-03/05/2022 01:47:54 - INFO - codeparrot_training - Step 30915: {'lr': 0.00045436946267736364, 'samples': 15828992, 'steps': 30915, 'loss/train': 2.114124298095703}
-03/05/2022 01:47:57 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/05/2022 01:48:00 - INFO - codeparrot_training - Step 30916: {'lr': 0.0004543664061586532, 'samples': 15829504, 'steps': 30916, 'loss/train': 1.229833960533142}
-03/05/2022 01:48:03 - INFO - codeparrot_training - Step 30917: {'lr': 0.00045436334954785854, 'samples': 15830016, 'steps': 30917, 'loss/train': 1.546056866645813}
-03/05/2022 01:48:05 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/05/2022 01:48:08 - INFO - codeparrot_training - Step 30918: {'lr': 0.0004543602928449808, 'samples': 15830528, 'steps': 30918, 'loss/train': 1.2573237419128418}
-03/05/2022 01:48:11 - INFO - codeparrot_training - Step 30919: {'lr': 0.00045435723605002156, 'samples': 15831040, 'steps': 30919, 'loss/train': 1.9178073406219482}
-03/05/2022 01:48:14 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/05/2022 01:48:16 - INFO - codeparrot_training - Step 30920: {'lr': 0.00045435417916298205, 'samples': 15831552, 'steps': 30920, 'loss/train': 1.5800565481185913}
-03/05/2022 01:48:20 - INFO - codeparrot_training - Step 30921: {'lr': 0.00045435112218386364, 'samples': 15832064, 'steps': 30921, 'loss/train': 1.99652099609375}
-03/05/2022 01:48:22 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 01:48:25 - INFO - codeparrot_training - Step 30922: {'lr': 0.00045434806511266784, 'samples': 15832576, 'steps': 30922, 'loss/train': 2.527116298675537}
-03/05/2022 01:48:28 - INFO - codeparrot_training - Step 30923: {'lr': 0.0004543450079493959, 'samples': 15833088, 'steps': 30923, 'loss/train': 1.7062276601791382}
-03/05/2022 01:48:30 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/05/2022 01:48:33 - INFO - codeparrot_training - Step 30924: {'lr': 0.0004543419506940494, 'samples': 15833600, 'steps': 30924, 'loss/train': 2.6366090774536133}
-03/05/2022 01:48:37 - INFO - codeparrot_training - Step 30925: {'lr': 0.0004543388933466294, 'samples': 15834112, 'steps': 30925, 'loss/train': 1.983325719833374}
-03/05/2022 01:48:40 - INFO - codeparrot_training - Step 30926: {'lr': 0.00045433583590713756, 'samples': 15834624, 'steps': 30926, 'loss/train': 0.17568804323673248}
-03/05/2022 01:48:40 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/05/2022 01:48:45 - INFO - codeparrot_training - Step 30927: {'lr': 0.0004543327783755751, 'samples': 15835136, 'steps': 30927, 'loss/train': 1.6338725090026855}
-03/05/2022 01:48:48 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/05/2022 01:48:50 - INFO - codeparrot_training - Step 30928: {'lr': 0.0004543297207519434, 'samples': 15835648, 'steps': 30928, 'loss/train': 1.9122414588928223}
-03/05/2022 01:48:54 - INFO - codeparrot_training - Step 30929: {'lr': 0.0004543266630362439, 'samples': 15836160, 'steps': 30929, 'loss/train': 2.424015998840332}
-03/05/2022 01:48:56 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 01:48:59 - INFO - codeparrot_training - Step 30930: {'lr': 0.00045432360522847803, 'samples': 15836672, 'steps': 30930, 'loss/train': 2.0605716705322266}
-03/05/2022 01:49:02 - INFO - codeparrot_training - Step 30931: {'lr': 0.000454320547328647, 'samples': 15837184, 'steps': 30931, 'loss/train': 1.8656967878341675}
-03/05/2022 01:49:06 - INFO - codeparrot_training - Step 30932: {'lr': 0.00045431748933675236, 'samples': 15837696, 'steps': 30932, 'loss/train': 0.9715030193328857}
-03/05/2022 01:49:06 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 01:49:11 - INFO - codeparrot_training - Step 30933: {'lr': 0.00045431443125279534, 'samples': 15838208, 'steps': 30933, 'loss/train': 1.5591328144073486}
-03/05/2022 01:49:14 - INFO - codeparrot_training - Step 30934: {'lr': 0.00045431137307677753, 'samples': 15838720, 'steps': 30934, 'loss/train': 2.092139959335327}
-03/05/2022 01:49:15 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 01:49:20 - INFO - codeparrot_training - Step 30935: {'lr': 0.00045430831480870005, 'samples': 15839232, 'steps': 30935, 'loss/train': 1.1295056343078613}
-03/05/2022 01:49:23 - INFO - codeparrot_training - Step 30936: {'lr': 0.0004543052564485644, 'samples': 15839744, 'steps': 30936, 'loss/train': 2.2334303855895996}
-03/05/2022 01:49:23 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 01:49:28 - INFO - codeparrot_training - Step 30937: {'lr': 0.00045430219799637197, 'samples': 15840256, 'steps': 30937, 'loss/train': 1.2963814735412598}
-03/05/2022 01:49:31 - INFO - codeparrot_training - Step 30938: {'lr': 0.0004542991394521241, 'samples': 15840768, 'steps': 30938, 'loss/train': 1.444502830505371}
-03/05/2022 01:49:31 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 01:49:37 - INFO - codeparrot_training - Step 30939: {'lr': 0.00045429608081582216, 'samples': 15841280, 'steps': 30939, 'loss/train': 1.8565610647201538}
-03/05/2022 01:49:40 - INFO - codeparrot_training - Step 30940: {'lr': 0.0004542930220874677, 'samples': 15841792, 'steps': 30940, 'loss/train': 2.0522801876068115}
-03/05/2022 01:49:40 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/05/2022 01:49:45 - INFO - codeparrot_training - Step 30941: {'lr': 0.00045428996326706185, 'samples': 15842304, 'steps': 30941, 'loss/train': 2.016282320022583}
-03/05/2022 01:49:48 - INFO - codeparrot_training - Step 30942: {'lr': 0.0004542869043546061, 'samples': 15842816, 'steps': 30942, 'loss/train': 1.8218531608581543}
-03/05/2022 01:49:48 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/05/2022 01:49:53 - INFO - codeparrot_training - Step 30943: {'lr': 0.0004542838453501018, 'samples': 15843328, 'steps': 30943, 'loss/train': 0.8377234935760498}
-03/05/2022 01:49:57 - INFO - codeparrot_training - Step 30944: {'lr': 0.0004542807862535504, 'samples': 15843840, 'steps': 30944, 'loss/train': 1.2963526248931885}
-03/05/2022 01:49:57 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/05/2022 01:50:02 - INFO - codeparrot_training - Step 30945: {'lr': 0.0004542777270649533, 'samples': 15844352, 'steps': 30945, 'loss/train': 2.0030367374420166}
-03/05/2022 01:50:05 - INFO - codeparrot_training - Step 30946: {'lr': 0.0004542746677843117, 'samples': 15844864, 'steps': 30946, 'loss/train': 0.07478119432926178}
-03/05/2022 01:50:05 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/05/2022 01:50:10 - INFO - codeparrot_training - Step 30947: {'lr': 0.0004542716084116271, 'samples': 15845376, 'steps': 30947, 'loss/train': 1.6268080472946167}
-03/05/2022 01:50:13 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/05/2022 01:50:16 - INFO - codeparrot_training - Step 30948: {'lr': 0.0004542685489469008, 'samples': 15845888, 'steps': 30948, 'loss/train': 1.643465518951416}
-03/05/2022 01:50:19 - INFO - codeparrot_training - Step 30949: {'lr': 0.0004542654893901344, 'samples': 15846400, 'steps': 30949, 'loss/train': 1.7122445106506348}
-03/05/2022 01:50:22 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/05/2022 01:50:24 - INFO - codeparrot_training - Step 30950: {'lr': 0.00045426242974132904, 'samples': 15846912, 'steps': 30950, 'loss/train': 2.2826390266418457}
-03/05/2022 01:50:27 - INFO - codeparrot_training - Step 30951: {'lr': 0.0004542593700004862, 'samples': 15847424, 'steps': 30951, 'loss/train': 1.8122682571411133}
-03/05/2022 01:50:31 - INFO - codeparrot_training - Step 30952: {'lr': 0.0004542563101676072, 'samples': 15847936, 'steps': 30952, 'loss/train': 1.7694283723831177}
-03/05/2022 01:50:31 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/05/2022 01:50:36 - INFO - codeparrot_training - Step 30953: {'lr': 0.0004542532502426935, 'samples': 15848448, 'steps': 30953, 'loss/train': 0.6644503474235535}
-03/05/2022 01:50:39 - INFO - codeparrot_training - Step 30954: {'lr': 0.0004542501902257464, 'samples': 15848960, 'steps': 30954, 'loss/train': 2.0675861835479736}
-03/05/2022 01:50:39 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 01:50:44 - INFO - codeparrot_training - Step 30955: {'lr': 0.0004542471301167673, 'samples': 15849472, 'steps': 30955, 'loss/train': 2.1627542972564697}
-03/05/2022 01:50:47 - INFO - codeparrot_training - Step 30956: {'lr': 0.0004542440699157577, 'samples': 15849984, 'steps': 30956, 'loss/train': 0.9101678133010864}
-03/05/2022 01:50:48 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/05/2022 01:50:53 - INFO - codeparrot_training - Step 30957: {'lr': 0.00045424100962271883, 'samples': 15850496, 'steps': 30957, 'loss/train': 0.7713713049888611}
-03/05/2022 01:50:56 - INFO - codeparrot_training - Step 30958: {'lr': 0.00045423794923765204, 'samples': 15851008, 'steps': 30958, 'loss/train': 2.854386806488037}
-03/05/2022 01:50:56 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/05/2022 01:51:01 - INFO - codeparrot_training - Step 30959: {'lr': 0.00045423488876055883, 'samples': 15851520, 'steps': 30959, 'loss/train': 1.8214255571365356}
-03/05/2022 01:51:04 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 01:51:06 - INFO - codeparrot_training - Step 30960: {'lr': 0.00045423182819144054, 'samples': 15852032, 'steps': 30960, 'loss/train': 0.833591639995575}
-03/05/2022 01:51:10 - INFO - codeparrot_training - Step 30961: {'lr': 0.00045422876753029853, 'samples': 15852544, 'steps': 30961, 'loss/train': 1.5145734548568726}
-03/05/2022 01:51:13 - INFO - codeparrot_training - Step 30962: {'lr': 0.0004542257067771342, 'samples': 15853056, 'steps': 30962, 'loss/train': 1.9908989667892456}
-03/05/2022 01:51:13 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/05/2022 01:51:18 - INFO - codeparrot_training - Step 30963: {'lr': 0.0004542226459319489, 'samples': 15853568, 'steps': 30963, 'loss/train': 2.1853761672973633}
-03/05/2022 01:51:21 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/05/2022 01:51:23 - INFO - codeparrot_training - Step 30964: {'lr': 0.000454219584994744, 'samples': 15854080, 'steps': 30964, 'loss/train': 1.9599518775939941}
-03/05/2022 01:51:27 - INFO - codeparrot_training - Step 30965: {'lr': 0.00045421652396552094, 'samples': 15854592, 'steps': 30965, 'loss/train': 1.5561466217041016}
-03/05/2022 01:51:30 - INFO - codeparrot_training - Step 30966: {'lr': 0.0004542134628442811, 'samples': 15855104, 'steps': 30966, 'loss/train': 1.2308969497680664}
-03/05/2022 01:51:30 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/05/2022 01:51:35 - INFO - codeparrot_training - Step 30967: {'lr': 0.0004542104016310258, 'samples': 15855616, 'steps': 30967, 'loss/train': 1.7305328845977783}
-03/05/2022 01:51:38 - INFO - codeparrot_training - Step 30968: {'lr': 0.0004542073403257564, 'samples': 15856128, 'steps': 30968, 'loss/train': 1.3858481645584106}
-03/05/2022 01:51:38 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 01:51:43 - INFO - codeparrot_training - Step 30969: {'lr': 0.0004542042789284744, 'samples': 15856640, 'steps': 30969, 'loss/train': 1.6783955097198486}
-03/05/2022 01:51:46 - INFO - codeparrot_training - Step 30970: {'lr': 0.0004542012174391811, 'samples': 15857152, 'steps': 30970, 'loss/train': 1.8002711534500122}
-03/05/2022 01:51:47 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/05/2022 01:51:52 - INFO - codeparrot_training - Step 30971: {'lr': 0.0004541981558578778, 'samples': 15857664, 'steps': 30971, 'loss/train': 2.291543960571289}
-03/05/2022 01:51:55 - INFO - codeparrot_training - Step 30972: {'lr': 0.00045419509418456603, 'samples': 15858176, 'steps': 30972, 'loss/train': 2.367621421813965}
-03/05/2022 01:51:55 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/05/2022 01:52:00 - INFO - codeparrot_training - Step 30973: {'lr': 0.00045419203241924705, 'samples': 15858688, 'steps': 30973, 'loss/train': 1.5764976739883423}
-03/05/2022 01:52:03 - INFO - codeparrot_training - Step 30974: {'lr': 0.00045418897056192234, 'samples': 15859200, 'steps': 30974, 'loss/train': 1.3960379362106323}
-03/05/2022 01:52:04 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/05/2022 01:52:09 - INFO - codeparrot_training - Step 30975: {'lr': 0.00045418590861259317, 'samples': 15859712, 'steps': 30975, 'loss/train': 0.8297275304794312}
-03/05/2022 01:52:12 - INFO - codeparrot_training - Step 30976: {'lr': 0.0004541828465712611, 'samples': 15860224, 'steps': 30976, 'loss/train': 0.06625861674547195}
-03/05/2022 01:52:12 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/05/2022 01:52:17 - INFO - codeparrot_training - Step 30977: {'lr': 0.0004541797844379273, 'samples': 15860736, 'steps': 30977, 'loss/train': 1.4072949886322021}
-03/05/2022 01:52:20 - INFO - codeparrot_training - Step 30978: {'lr': 0.0004541767222125932, 'samples': 15861248, 'steps': 30978, 'loss/train': 1.5770609378814697}
-03/05/2022 01:52:20 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/05/2022 01:52:26 - INFO - codeparrot_training - Step 30979: {'lr': 0.0004541736598952603, 'samples': 15861760, 'steps': 30979, 'loss/train': 1.1852333545684814}
-03/05/2022 01:52:29 - INFO - codeparrot_training - Step 30980: {'lr': 0.0004541705974859298, 'samples': 15862272, 'steps': 30980, 'loss/train': 1.466752290725708}
-03/05/2022 01:52:29 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/05/2022 01:52:34 - INFO - codeparrot_training - Step 30981: {'lr': 0.0004541675349846033, 'samples': 15862784, 'steps': 30981, 'loss/train': 1.243790626525879}
-03/05/2022 01:52:37 - INFO - codeparrot_training - Step 30982: {'lr': 0.000454164472391282, 'samples': 15863296, 'steps': 30982, 'loss/train': 1.6239548921585083}
-03/05/2022 01:52:37 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/05/2022 01:52:43 - INFO - codeparrot_training - Step 30983: {'lr': 0.00045416140970596736, 'samples': 15863808, 'steps': 30983, 'loss/train': 1.53493070602417}
-03/05/2022 01:52:46 - INFO - codeparrot_training - Step 30984: {'lr': 0.0004541583469286607, 'samples': 15864320, 'steps': 30984, 'loss/train': 1.5314464569091797}
-03/05/2022 01:52:46 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/05/2022 01:52:51 - INFO - codeparrot_training - Step 30985: {'lr': 0.00045415528405936347, 'samples': 15864832, 'steps': 30985, 'loss/train': 2.0324625968933105}
-03/05/2022 01:52:54 - INFO - codeparrot_training - Step 30986: {'lr': 0.000454152221098077, 'samples': 15865344, 'steps': 30986, 'loss/train': 2.337380886077881}
-03/05/2022 01:52:54 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/05/2022 01:52:59 - INFO - codeparrot_training - Step 30987: {'lr': 0.0004541491580448027, 'samples': 15865856, 'steps': 30987, 'loss/train': 2.3334641456604004}
-03/05/2022 01:53:02 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 01:53:05 - INFO - codeparrot_training - Step 30988: {'lr': 0.00045414609489954195, 'samples': 15866368, 'steps': 30988, 'loss/train': 1.7933517694473267}
-03/05/2022 01:53:08 - INFO - codeparrot_training - Step 30989: {'lr': 0.00045414303166229616, 'samples': 15866880, 'steps': 30989, 'loss/train': 1.2874490022659302}
-03/05/2022 01:53:10 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/05/2022 01:53:13 - INFO - codeparrot_training - Step 30990: {'lr': 0.0004541399683330666, 'samples': 15867392, 'steps': 30990, 'loss/train': 0.8950868844985962}
-03/05/2022 01:53:16 - INFO - codeparrot_training - Step 30991: {'lr': 0.00045413690491185476, 'samples': 15867904, 'steps': 30991, 'loss/train': 1.63676917552948}
-03/05/2022 01:53:19 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/05/2022 01:53:21 - INFO - codeparrot_training - Step 30992: {'lr': 0.00045413384139866196, 'samples': 15868416, 'steps': 30992, 'loss/train': 1.4612616300582886}
-03/05/2022 01:53:25 - INFO - codeparrot_training - Step 30993: {'lr': 0.0004541307777934896, 'samples': 15868928, 'steps': 30993, 'loss/train': 2.029505968093872}
-03/05/2022 01:53:27 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/05/2022 01:53:30 - INFO - codeparrot_training - Step 30994: {'lr': 0.00045412771409633905, 'samples': 15869440, 'steps': 30994, 'loss/train': 1.956223487854004}
-03/05/2022 01:53:33 - INFO - codeparrot_training - Step 30995: {'lr': 0.0004541246503072117, 'samples': 15869952, 'steps': 30995, 'loss/train': 2.00334095954895}
-03/05/2022 01:53:35 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/05/2022 01:53:38 - INFO - codeparrot_training - Step 30996: {'lr': 0.000454121586426109, 'samples': 15870464, 'steps': 30996, 'loss/train': 1.388145923614502}
-03/05/2022 01:53:42 - INFO - codeparrot_training - Step 30997: {'lr': 0.0004541185224530322, 'samples': 15870976, 'steps': 30997, 'loss/train': 0.17015931010246277}
-03/05/2022 01:53:44 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 01:53:47 - INFO - codeparrot_training - Step 30998: {'lr': 0.00045411545838798273, 'samples': 15871488, 'steps': 30998, 'loss/train': 1.5545047521591187}
-03/05/2022 01:53:50 - INFO - codeparrot_training - Step 30999: {'lr': 0.00045411239423096206, 'samples': 15872000, 'steps': 30999, 'loss/train': 1.5775765180587769}
-03/05/2022 01:53:52 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/05/2022 01:53:55 - INFO - codeparrot_training - Step 31000: {'lr': 0.0004541093299819714, 'samples': 15872512, 'steps': 31000, 'loss/train': 1.723979115486145}
-03/05/2022 01:53:59 - INFO - codeparrot_training - Step 31001: {'lr': 0.0004541062656410123, 'samples': 15873024, 'steps': 31001, 'loss/train': 1.4222108125686646}
-03/05/2022 01:54:01 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/05/2022 01:54:04 - INFO - codeparrot_training - Step 31002: {'lr': 0.000454103201208086, 'samples': 15873536, 'steps': 31002, 'loss/train': 1.3299506902694702}
-03/05/2022 01:54:07 - INFO - codeparrot_training - Step 31003: {'lr': 0.00045410013668319404, 'samples': 15874048, 'steps': 31003, 'loss/train': 1.6875066757202148}
-03/05/2022 01:54:09 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 01:54:12 - INFO - codeparrot_training - Step 31004: {'lr': 0.00045409707206633764, 'samples': 15874560, 'steps': 31004, 'loss/train': 1.080405354499817}
-03/05/2022 01:54:15 - INFO - codeparrot_training - Step 31005: {'lr': 0.0004540940073575183, 'samples': 15875072, 'steps': 31005, 'loss/train': 1.7155218124389648}
-03/05/2022 01:54:18 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 01:54:21 - INFO - codeparrot_training - Step 31006: {'lr': 0.00045409094255673734, 'samples': 15875584, 'steps': 31006, 'loss/train': 1.581612229347229}
-03/05/2022 01:54:24 - INFO - codeparrot_training - Step 31007: {'lr': 0.00045408787766399605, 'samples': 15876096, 'steps': 31007, 'loss/train': 1.2886601686477661}
-03/05/2022 01:54:26 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/05/2022 01:54:29 - INFO - codeparrot_training - Step 31008: {'lr': 0.00045408481267929604, 'samples': 15876608, 'steps': 31008, 'loss/train': 1.9097386598587036}
-03/05/2022 01:54:33 - INFO - codeparrot_training - Step 31009: {'lr': 0.0004540817476026385, 'samples': 15877120, 'steps': 31009, 'loss/train': 2.1265344619750977}
-03/05/2022 01:54:35 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/05/2022 01:54:38 - INFO - codeparrot_training - Step 31010: {'lr': 0.00045407868243402483, 'samples': 15877632, 'steps': 31010, 'loss/train': 1.6197446584701538}
-03/05/2022 01:54:41 - INFO - codeparrot_training - Step 31011: {'lr': 0.0004540756171734565, 'samples': 15878144, 'steps': 31011, 'loss/train': 2.1251659393310547}
-03/05/2022 01:54:43 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 01:54:46 - INFO - codeparrot_training - Step 31012: {'lr': 0.0004540725518209349, 'samples': 15878656, 'steps': 31012, 'loss/train': 1.3918331861495972}
-03/05/2022 01:54:49 - INFO - codeparrot_training - Step 31013: {'lr': 0.0004540694863764613, 'samples': 15879168, 'steps': 31013, 'loss/train': 1.3065340518951416}
-03/05/2022 01:54:51 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/05/2022 01:54:55 - INFO - codeparrot_training - Step 31014: {'lr': 0.0004540664208400371, 'samples': 15879680, 'steps': 31014, 'loss/train': 1.8788014650344849}
-03/05/2022 01:54:58 - INFO - codeparrot_training - Step 31015: {'lr': 0.0004540633552116638, 'samples': 15880192, 'steps': 31015, 'loss/train': 1.3577966690063477}
-03/05/2022 01:55:00 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/05/2022 01:55:03 - INFO - codeparrot_training - Step 31016: {'lr': 0.0004540602894913427, 'samples': 15880704, 'steps': 31016, 'loss/train': 1.5502246618270874}
-03/05/2022 01:55:06 - INFO - codeparrot_training - Step 31017: {'lr': 0.0004540572236790751, 'samples': 15881216, 'steps': 31017, 'loss/train': 1.9129462242126465}
-03/05/2022 01:55:08 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/05/2022 01:55:12 - INFO - codeparrot_training - Step 31018: {'lr': 0.0004540541577748625, 'samples': 15881728, 'steps': 31018, 'loss/train': 0.9524648189544678}
-03/05/2022 01:55:15 - INFO - codeparrot_training - Step 31019: {'lr': 0.0004540510917787063, 'samples': 15882240, 'steps': 31019, 'loss/train': 1.6206148862838745}
-03/05/2022 01:55:18 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/05/2022 01:55:20 - INFO - codeparrot_training - Step 31020: {'lr': 0.00045404802569060776, 'samples': 15882752, 'steps': 31020, 'loss/train': 0.23085585236549377}
-03/05/2022 01:55:23 - INFO - codeparrot_training - Step 31021: {'lr': 0.00045404495951056835, 'samples': 15883264, 'steps': 31021, 'loss/train': 1.185053825378418}
-03/05/2022 01:55:26 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/05/2022 01:55:29 - INFO - codeparrot_training - Step 31022: {'lr': 0.00045404189323858946, 'samples': 15883776, 'steps': 31022, 'loss/train': 2.0368337631225586}
-03/05/2022 01:55:32 - INFO - codeparrot_training - Step 31023: {'lr': 0.0004540388268746724, 'samples': 15884288, 'steps': 31023, 'loss/train': 0.5062656998634338}
-03/05/2022 01:55:35 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/05/2022 01:55:37 - INFO - codeparrot_training - Step 31024: {'lr': 0.0004540357604188186, 'samples': 15884800, 'steps': 31024, 'loss/train': 1.846888780593872}
-03/05/2022 01:55:41 - INFO - codeparrot_training - Step 31025: {'lr': 0.0004540326938710295, 'samples': 15885312, 'steps': 31025, 'loss/train': 2.523287296295166}
-03/05/2022 01:55:43 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/05/2022 01:55:46 - INFO - codeparrot_training - Step 31026: {'lr': 0.0004540296272313064, 'samples': 15885824, 'steps': 31026, 'loss/train': 1.6225273609161377}
-03/05/2022 01:55:49 - INFO - codeparrot_training - Step 31027: {'lr': 0.00045402656049965055, 'samples': 15886336, 'steps': 31027, 'loss/train': 1.668952226638794}
-03/05/2022 01:55:51 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/05/2022 01:55:54 - INFO - codeparrot_training - Step 31028: {'lr': 0.0004540234936760636, 'samples': 15886848, 'steps': 31028, 'loss/train': 1.7061861753463745}
-03/05/2022 01:55:57 - INFO - codeparrot_training - Step 31029: {'lr': 0.00045402042676054684, 'samples': 15887360, 'steps': 31029, 'loss/train': 1.356921911239624}
-03/05/2022 01:56:00 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/05/2022 01:56:03 - INFO - codeparrot_training - Step 31030: {'lr': 0.0004540173597531015, 'samples': 15887872, 'steps': 31030, 'loss/train': 0.9442176818847656}
-03/05/2022 01:56:06 - INFO - codeparrot_training - Step 31031: {'lr': 0.00045401429265372925, 'samples': 15888384, 'steps': 31031, 'loss/train': 0.9786296486854553}
-03/05/2022 01:56:08 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/05/2022 01:56:11 - INFO - codeparrot_training - Step 31032: {'lr': 0.0004540112254624312, 'samples': 15888896, 'steps': 31032, 'loss/train': 2.161379098892212}
-03/05/2022 01:56:14 - INFO - codeparrot_training - Step 31033: {'lr': 0.0004540081581792089, 'samples': 15889408, 'steps': 31033, 'loss/train': 1.3048256635665894}
-03/05/2022 01:56:17 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/05/2022 01:56:20 - INFO - codeparrot_training - Step 31034: {'lr': 0.0004540050908040636, 'samples': 15889920, 'steps': 31034, 'loss/train': 1.5006375312805176}
-03/05/2022 01:56:23 - INFO - codeparrot_training - Step 31035: {'lr': 0.0004540020233369968, 'samples': 15890432, 'steps': 31035, 'loss/train': 2.5797078609466553}
-03/05/2022 01:56:25 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/05/2022 01:56:28 - INFO - codeparrot_training - Step 31036: {'lr': 0.00045399895577800985, 'samples': 15890944, 'steps': 31036, 'loss/train': 1.9128408432006836}
-03/05/2022 01:56:31 - INFO - codeparrot_training - Step 31037: {'lr': 0.00045399588812710415, 'samples': 15891456, 'steps': 31037, 'loss/train': 2.336669445037842}
-03/05/2022 01:56:33 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/05/2022 01:56:36 - INFO - codeparrot_training - Step 31038: {'lr': 0.0004539928203842809, 'samples': 15891968, 'steps': 31038, 'loss/train': 2.016925096511841}
-03/05/2022 01:56:39 - INFO - codeparrot_training - Step 31039: {'lr': 0.0004539897525495418, 'samples': 15892480, 'steps': 31039, 'loss/train': 2.2826406955718994}
-03/05/2022 01:56:42 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/05/2022 01:56:45 - INFO - codeparrot_training - Step 31040: {'lr': 0.0004539866846228879, 'samples': 15892992, 'steps': 31040, 'loss/train': 1.7109838724136353}
-03/05/2022 01:56:48 - INFO - codeparrot_training - Step 31041: {'lr': 0.0004539836166043209, 'samples': 15893504, 'steps': 31041, 'loss/train': 0.2107848972082138}
-03/05/2022 01:56:50 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/05/2022 01:56:53 - INFO - codeparrot_training - Step 31042: {'lr': 0.00045398054849384197, 'samples': 15894016, 'steps': 31042, 'loss/train': 2.0768253803253174}
-03/05/2022 01:56:56 - INFO - codeparrot_training - Step 31043: {'lr': 0.0004539774802914526, 'samples': 15894528, 'steps': 31043, 'loss/train': 2.1518638134002686}
-03/05/2022 01:56:58 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/05/2022 01:57:02 - INFO - codeparrot_training - Step 31044: {'lr': 0.00045397441199715406, 'samples': 15895040, 'steps': 31044, 'loss/train': 2.0035881996154785}
-03/05/2022 01:57:05 - INFO - codeparrot_training - Step 31045: {'lr': 0.0004539713436109478, 'samples': 15895552, 'steps': 31045, 'loss/train': 1.3785030841827393}
-03/05/2022 01:57:07 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/05/2022 01:57:10 - INFO - codeparrot_training - Step 31046: {'lr': 0.0004539682751328352, 'samples': 15896064, 'steps': 31046, 'loss/train': 1.39830482006073}
-03/05/2022 01:57:13 - INFO - codeparrot_training - Step 31047: {'lr': 0.0004539652065628177, 'samples': 15896576, 'steps': 31047, 'loss/train': 2.4769535064697266}
-03/05/2022 01:57:15 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/05/2022 01:57:19 - INFO - codeparrot_training - Step 31048: {'lr': 0.00045396213790089657, 'samples': 15897088, 'steps': 31048, 'loss/train': 1.1181715726852417}
-03/05/2022 01:57:22 - INFO - codeparrot_training - Step 31049: {'lr': 0.0004539590691470733, 'samples': 15897600, 'steps': 31049, 'loss/train': 2.0698914527893066}
-03/05/2022 01:57:24 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/05/2022 01:57:27 - INFO - codeparrot_training - Step 31050: {'lr': 0.0004539560003013492, 'samples': 15898112, 'steps': 31050, 'loss/train': 1.4740917682647705}
-03/05/2022 01:57:30 - INFO - codeparrot_training - Step 31051: {'lr': 0.0004539529313637256, 'samples': 15898624, 'steps': 31051, 'loss/train': 0.8870312571525574}
-03/05/2022 01:57:32 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 01:57:35 - INFO - codeparrot_training - Step 31052: {'lr': 0.0004539498623342041, 'samples': 15899136, 'steps': 31052, 'loss/train': 2.3583619594573975}
-03/05/2022 01:57:39 - INFO - codeparrot_training - Step 31053: {'lr': 0.0004539467932127858, 'samples': 15899648, 'steps': 31053, 'loss/train': 1.639033317565918}
-03/05/2022 01:57:40 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 01:57:44 - INFO - codeparrot_training - Step 31054: {'lr': 0.00045394372399947225, 'samples': 15900160, 'steps': 31054, 'loss/train': 1.6291180849075317}
-03/05/2022 01:57:47 - INFO - codeparrot_training - Step 31055: {'lr': 0.0004539406546942649, 'samples': 15900672, 'steps': 31055, 'loss/train': 0.5368399024009705}
-03/05/2022 01:57:49 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/05/2022 01:57:52 - INFO - codeparrot_training - Step 31056: {'lr': 0.00045393758529716497, 'samples': 15901184, 'steps': 31056, 'loss/train': 0.30685704946517944}
-03/05/2022 01:57:55 - INFO - codeparrot_training - Step 31057: {'lr': 0.0004539345158081739, 'samples': 15901696, 'steps': 31057, 'loss/train': 1.618955135345459}
-03/05/2022 01:57:57 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/05/2022 01:58:01 - INFO - codeparrot_training - Step 31058: {'lr': 0.0004539314462272931, 'samples': 15902208, 'steps': 31058, 'loss/train': 2.251624345779419}
-03/05/2022 01:58:04 - INFO - codeparrot_training - Step 31059: {'lr': 0.0004539283765545239, 'samples': 15902720, 'steps': 31059, 'loss/train': 2.048711061477661}
-03/05/2022 01:58:06 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/05/2022 01:58:09 - INFO - codeparrot_training - Step 31060: {'lr': 0.00045392530678986775, 'samples': 15903232, 'steps': 31060, 'loss/train': 1.6102041006088257}
-03/05/2022 01:58:12 - INFO - codeparrot_training - Step 31061: {'lr': 0.00045392223693332604, 'samples': 15903744, 'steps': 31061, 'loss/train': 2.021141767501831}
-03/05/2022 01:58:14 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/05/2022 01:58:17 - INFO - codeparrot_training - Step 31062: {'lr': 0.0004539191669849001, 'samples': 15904256, 'steps': 31062, 'loss/train': 2.0053646564483643}
-03/05/2022 01:58:21 - INFO - codeparrot_training - Step 31063: {'lr': 0.0004539160969445913, 'samples': 15904768, 'steps': 31063, 'loss/train': 1.594766616821289}
-03/05/2022 01:58:22 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/05/2022 01:58:26 - INFO - codeparrot_training - Step 31064: {'lr': 0.0004539130268124011, 'samples': 15905280, 'steps': 31064, 'loss/train': 1.4969077110290527}
-03/05/2022 01:58:29 - INFO - codeparrot_training - Step 31065: {'lr': 0.0004539099565883308, 'samples': 15905792, 'steps': 31065, 'loss/train': 2.3274800777435303}
-03/05/2022 01:58:30 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/05/2022 01:58:34 - INFO - codeparrot_training - Step 31066: {'lr': 0.0004539068862723818, 'samples': 15906304, 'steps': 31066, 'loss/train': 1.3392586708068848}
-03/05/2022 01:58:37 - INFO - codeparrot_training - Step 31067: {'lr': 0.0004539038158645555, 'samples': 15906816, 'steps': 31067, 'loss/train': 1.635895013809204}
-03/05/2022 01:58:38 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/05/2022 01:58:43 - INFO - codeparrot_training - Step 31068: {'lr': 0.00045390074536485336, 'samples': 15907328, 'steps': 31068, 'loss/train': 1.365620493888855}
-03/05/2022 01:58:46 - INFO - codeparrot_training - Step 31069: {'lr': 0.00045389767477327657, 'samples': 15907840, 'steps': 31069, 'loss/train': 0.15375058352947235}
-03/05/2022 01:58:47 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/05/2022 01:58:51 - INFO - codeparrot_training - Step 31070: {'lr': 0.00045389460408982676, 'samples': 15908352, 'steps': 31070, 'loss/train': 2.339210271835327}
-03/05/2022 01:58:54 - INFO - codeparrot_training - Step 31071: {'lr': 0.0004538915333145052, 'samples': 15908864, 'steps': 31071, 'loss/train': 1.7322310209274292}
-03/05/2022 01:58:55 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/05/2022 01:58:59 - INFO - codeparrot_training - Step 31072: {'lr': 0.00045388846244731314, 'samples': 15909376, 'steps': 31072, 'loss/train': 1.9424974918365479}
-03/05/2022 01:59:03 - INFO - codeparrot_training - Step 31073: {'lr': 0.00045388539148825214, 'samples': 15909888, 'steps': 31073, 'loss/train': 1.668043613433838}
-03/05/2022 01:59:03 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/05/2022 01:59:08 - INFO - codeparrot_training - Step 31074: {'lr': 0.0004538823204373235, 'samples': 15910400, 'steps': 31074, 'loss/train': 1.9071142673492432}
-03/05/2022 01:59:11 - INFO - codeparrot_training - Step 31075: {'lr': 0.00045387924929452873, 'samples': 15910912, 'steps': 31075, 'loss/train': 2.2375648021698}
-03/05/2022 01:59:12 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/05/2022 01:59:16 - INFO - codeparrot_training - Step 31076: {'lr': 0.000453876178059869, 'samples': 15911424, 'steps': 31076, 'loss/train': 1.8308181762695312}
-03/05/2022 01:59:19 - INFO - codeparrot_training - Step 31077: {'lr': 0.0004538731067333459, 'samples': 15911936, 'steps': 31077, 'loss/train': 1.0102323293685913}
-03/05/2022 01:59:25 - INFO - codeparrot_training - Step 31078: {'lr': 0.00045387003531496064, 'samples': 15912448, 'steps': 31078, 'loss/train': 1.622928500175476}
-03/05/2022 01:59:28 - INFO - codeparrot_training - Step 31079: {'lr': 0.00045386696380471473, 'samples': 15912960, 'steps': 31079, 'loss/train': 2.0409433841705322}
-03/05/2022 01:59:28 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 01:59:33 - INFO - codeparrot_training - Step 31080: {'lr': 0.0004538638922026095, 'samples': 15913472, 'steps': 31080, 'loss/train': 2.378960371017456}
-03/05/2022 01:59:36 - INFO - codeparrot_training - Step 31081: {'lr': 0.0004538608205086464, 'samples': 15913984, 'steps': 31081, 'loss/train': 1.8667718172073364}
-03/05/2022 01:59:37 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 01:59:42 - INFO - codeparrot_training - Step 31082: {'lr': 0.0004538577487228267, 'samples': 15914496, 'steps': 31082, 'loss/train': 2.2108724117279053}
-03/05/2022 01:59:45 - INFO - codeparrot_training - Step 31083: {'lr': 0.00045385467684515193, 'samples': 15915008, 'steps': 31083, 'loss/train': 2.2047266960144043}
-03/05/2022 01:59:45 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/05/2022 01:59:50 - INFO - codeparrot_training - Step 31084: {'lr': 0.0004538516048756233, 'samples': 15915520, 'steps': 31084, 'loss/train': 2.0003206729888916}
-03/05/2022 01:59:53 - INFO - codeparrot_training - Step 31085: {'lr': 0.00045384853281424235, 'samples': 15916032, 'steps': 31085, 'loss/train': 0.9549766182899475}
-03/05/2022 01:59:53 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/05/2022 01:59:59 - INFO - codeparrot_training - Step 31086: {'lr': 0.0004538454606610103, 'samples': 15916544, 'steps': 31086, 'loss/train': 1.8502594232559204}
-03/05/2022 02:00:02 - INFO - codeparrot_training - Step 31087: {'lr': 0.0004538423884159287, 'samples': 15917056, 'steps': 31087, 'loss/train': 2.1873044967651367}
-03/05/2022 02:00:02 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/05/2022 02:00:07 - INFO - codeparrot_training - Step 31088: {'lr': 0.0004538393160789988, 'samples': 15917568, 'steps': 31088, 'loss/train': 1.227258324623108}
-03/05/2022 02:00:10 - INFO - codeparrot_training - Step 31089: {'lr': 0.0004538362436502221, 'samples': 15918080, 'steps': 31089, 'loss/train': 1.5615841150283813}
-03/05/2022 02:00:10 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/05/2022 02:00:16 - INFO - codeparrot_training - Step 31090: {'lr': 0.00045383317112959997, 'samples': 15918592, 'steps': 31090, 'loss/train': 1.8077309131622314}
-03/05/2022 02:00:19 - INFO - codeparrot_training - Step 31091: {'lr': 0.0004538300985171337, 'samples': 15919104, 'steps': 31091, 'loss/train': 0.5859639048576355}
-03/05/2022 02:00:19 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/05/2022 02:00:24 - INFO - codeparrot_training - Step 31092: {'lr': 0.00045382702581282477, 'samples': 15919616, 'steps': 31092, 'loss/train': 1.071000099182129}
-03/05/2022 02:00:27 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/05/2022 02:00:29 - INFO - codeparrot_training - Step 31093: {'lr': 0.0004538239530166745, 'samples': 15920128, 'steps': 31093, 'loss/train': 1.5428143739700317}
-03/05/2022 02:00:32 - INFO - codeparrot_training - Step 31094: {'lr': 0.0004538208801286843, 'samples': 15920640, 'steps': 31094, 'loss/train': 2.3137831687927246}
-03/05/2022 02:00:35 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/05/2022 02:00:38 - INFO - codeparrot_training - Step 31095: {'lr': 0.0004538178071488556, 'samples': 15921152, 'steps': 31095, 'loss/train': 1.9550915956497192}
-03/05/2022 02:00:41 - INFO - codeparrot_training - Step 31096: {'lr': 0.00045381473407718963, 'samples': 15921664, 'steps': 31096, 'loss/train': 1.4543966054916382}
-03/05/2022 02:00:44 - INFO - codeparrot_training - Step 31097: {'lr': 0.000453811660913688, 'samples': 15922176, 'steps': 31097, 'loss/train': 1.9568668603897095}
-03/05/2022 02:00:44 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 02:00:49 - INFO - codeparrot_training - Step 31098: {'lr': 0.000453808587658352, 'samples': 15922688, 'steps': 31098, 'loss/train': 2.397277593612671}
-03/05/2022 02:00:52 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/05/2022 02:00:55 - INFO - codeparrot_training - Step 31099: {'lr': 0.0004538055143111829, 'samples': 15923200, 'steps': 31099, 'loss/train': 1.4020473957061768}
-03/05/2022 02:00:58 - INFO - codeparrot_training - Step 31100: {'lr': 0.00045380244087218224, 'samples': 15923712, 'steps': 31100, 'loss/train': 1.963415265083313}
-03/05/2022 02:01:01 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/05/2022 02:01:03 - INFO - codeparrot_training - Step 31101: {'lr': 0.0004537993673413513, 'samples': 15924224, 'steps': 31101, 'loss/train': 2.28629994392395}
-03/05/2022 02:01:06 - INFO - codeparrot_training - Step 31102: {'lr': 0.0004537962937186916, 'samples': 15924736, 'steps': 31102, 'loss/train': 1.4422993659973145}
-03/05/2022 02:01:09 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 02:01:11 - INFO - codeparrot_training - Step 31103: {'lr': 0.00045379322000420433, 'samples': 15925248, 'steps': 31103, 'loss/train': 1.5797686576843262}
-03/05/2022 02:01:15 - INFO - codeparrot_training - Step 31104: {'lr': 0.00045379014619789106, 'samples': 15925760, 'steps': 31104, 'loss/train': 1.93656587600708}
-03/05/2022 02:01:17 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/05/2022 02:01:20 - INFO - codeparrot_training - Step 31105: {'lr': 0.00045378707229975303, 'samples': 15926272, 'steps': 31105, 'loss/train': 0.9083523154258728}
-03/05/2022 02:01:23 - INFO - codeparrot_training - Step 31106: {'lr': 0.0004537839983097917, 'samples': 15926784, 'steps': 31106, 'loss/train': 2.0974676609039307}
-03/05/2022 02:01:25 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 02:01:28 - INFO - codeparrot_training - Step 31107: {'lr': 0.0004537809242280085, 'samples': 15927296, 'steps': 31107, 'loss/train': 1.553531527519226}
-03/05/2022 02:01:31 - INFO - codeparrot_training - Step 31108: {'lr': 0.0004537778500544047, 'samples': 15927808, 'steps': 31108, 'loss/train': 2.1052277088165283}
-03/05/2022 02:01:34 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 02:01:37 - INFO - codeparrot_training - Step 31109: {'lr': 0.0004537747757889817, 'samples': 15928320, 'steps': 31109, 'loss/train': 0.12641894817352295}
-03/05/2022 02:01:40 - INFO - codeparrot_training - Step 31110: {'lr': 0.0004537717014317411, 'samples': 15928832, 'steps': 31110, 'loss/train': 1.6423856019973755}
-03/05/2022 02:01:42 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/05/2022 02:01:45 - INFO - codeparrot_training - Step 31111: {'lr': 0.00045376862698268393, 'samples': 15929344, 'steps': 31111, 'loss/train': 1.6166242361068726}
-03/05/2022 02:01:48 - INFO - codeparrot_training - Step 31112: {'lr': 0.0004537655524418119, 'samples': 15929856, 'steps': 31112, 'loss/train': 0.6394819617271423}
-03/05/2022 02:01:51 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/05/2022 02:01:54 - INFO - codeparrot_training - Step 31113: {'lr': 0.00045376247780912616, 'samples': 15930368, 'steps': 31113, 'loss/train': 1.6246287822723389}
-03/05/2022 02:01:57 - INFO - codeparrot_training - Step 31114: {'lr': 0.00045375940308462826, 'samples': 15930880, 'steps': 31114, 'loss/train': 2.0412142276763916}
-03/05/2022 02:02:00 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/05/2022 02:02:02 - INFO - codeparrot_training - Step 31115: {'lr': 0.00045375632826831947, 'samples': 15931392, 'steps': 31115, 'loss/train': 1.929744005203247}
-03/05/2022 02:02:05 - INFO - codeparrot_training - Step 31116: {'lr': 0.00045375325336020124, 'samples': 15931904, 'steps': 31116, 'loss/train': 1.6718261241912842}
-03/05/2022 02:02:08 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/05/2022 02:02:10 - INFO - codeparrot_training - Step 31117: {'lr': 0.000453750178360275, 'samples': 15932416, 'steps': 31117, 'loss/train': 0.9813358783721924}
-03/05/2022 02:02:14 - INFO - codeparrot_training - Step 31118: {'lr': 0.00045374710326854194, 'samples': 15932928, 'steps': 31118, 'loss/train': 2.6160011291503906}
-03/05/2022 02:02:16 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/05/2022 02:02:19 - INFO - codeparrot_training - Step 31119: {'lr': 0.0004537440280850037, 'samples': 15933440, 'steps': 31119, 'loss/train': 2.3415873050689697}
-03/05/2022 02:02:22 - INFO - codeparrot_training - Step 31120: {'lr': 0.00045374095280966147, 'samples': 15933952, 'steps': 31120, 'loss/train': 1.3892284631729126}
-03/05/2022 02:02:24 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/05/2022 02:02:27 - INFO - codeparrot_training - Step 31121: {'lr': 0.00045373787744251677, 'samples': 15934464, 'steps': 31121, 'loss/train': 1.7189258337020874}
-03/05/2022 02:02:30 - INFO - codeparrot_training - Step 31122: {'lr': 0.0004537348019835709, 'samples': 15934976, 'steps': 31122, 'loss/train': 2.0913403034210205}
-03/05/2022 02:02:33 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/05/2022 02:02:36 - INFO - codeparrot_training - Step 31123: {'lr': 0.0004537317264328252, 'samples': 15935488, 'steps': 31123, 'loss/train': 1.1791996955871582}
-03/05/2022 02:02:39 - INFO - codeparrot_training - Step 31124: {'lr': 0.00045372865079028123, 'samples': 15936000, 'steps': 31124, 'loss/train': 1.0934760570526123}
-03/05/2022 02:02:41 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/05/2022 02:02:44 - INFO - codeparrot_training - Step 31125: {'lr': 0.00045372557505594024, 'samples': 15936512, 'steps': 31125, 'loss/train': 2.094167947769165}
-03/05/2022 02:02:47 - INFO - codeparrot_training - Step 31126: {'lr': 0.0004537224992298037, 'samples': 15937024, 'steps': 31126, 'loss/train': 2.194850206375122}
-03/05/2022 02:02:50 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/05/2022 02:02:53 - INFO - codeparrot_training - Step 31127: {'lr': 0.00045371942331187286, 'samples': 15937536, 'steps': 31127, 'loss/train': 1.3411511182785034}
-03/05/2022 02:02:56 - INFO - codeparrot_training - Step 31128: {'lr': 0.00045371634730214923, 'samples': 15938048, 'steps': 31128, 'loss/train': 1.4223006963729858}
-03/05/2022 02:02:58 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/05/2022 02:03:01 - INFO - codeparrot_training - Step 31129: {'lr': 0.00045371327120063417, 'samples': 15938560, 'steps': 31129, 'loss/train': 1.844749093055725}
-03/05/2022 02:03:04 - INFO - codeparrot_training - Step 31130: {'lr': 0.00045371019500732904, 'samples': 15939072, 'steps': 31130, 'loss/train': 1.2477525472640991}
-03/05/2022 02:03:06 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/05/2022 02:03:09 - INFO - codeparrot_training - Step 31131: {'lr': 0.00045370711872223525, 'samples': 15939584, 'steps': 31131, 'loss/train': 1.799143671989441}
-03/05/2022 02:03:13 - INFO - codeparrot_training - Step 31132: {'lr': 0.00045370404234535414, 'samples': 15940096, 'steps': 31132, 'loss/train': 1.3410942554473877}
-03/05/2022 02:03:15 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/05/2022 02:03:18 - INFO - codeparrot_training - Step 31133: {'lr': 0.00045370096587668714, 'samples': 15940608, 'steps': 31133, 'loss/train': 1.060439109802246}
-03/05/2022 02:03:21 - INFO - codeparrot_training - Step 31134: {'lr': 0.0004536978893162357, 'samples': 15941120, 'steps': 31134, 'loss/train': 1.4308747053146362}
-03/05/2022 02:03:23 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/05/2022 02:03:26 - INFO - codeparrot_training - Step 31135: {'lr': 0.000453694812664001, 'samples': 15941632, 'steps': 31135, 'loss/train': 1.652655005455017}
-03/05/2022 02:03:29 - INFO - codeparrot_training - Step 31136: {'lr': 0.00045369173591998466, 'samples': 15942144, 'steps': 31136, 'loss/train': 1.6214581727981567}
-03/05/2022 02:03:31 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/05/2022 02:03:35 - INFO - codeparrot_training - Step 31137: {'lr': 0.00045368865908418794, 'samples': 15942656, 'steps': 31137, 'loss/train': 2.6861472129821777}
-03/05/2022 02:03:38 - INFO - codeparrot_training - Step 31138: {'lr': 0.00045368558215661225, 'samples': 15943168, 'steps': 31138, 'loss/train': 2.5820486545562744}
-03/05/2022 02:03:39 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/05/2022 02:03:43 - INFO - codeparrot_training - Step 31139: {'lr': 0.00045368250513725896, 'samples': 15943680, 'steps': 31139, 'loss/train': 1.6927965879440308}
-03/05/2022 02:03:46 - INFO - codeparrot_training - Step 31140: {'lr': 0.00045367942802612953, 'samples': 15944192, 'steps': 31140, 'loss/train': 2.1222760677337646}
-03/05/2022 02:03:48 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/05/2022 02:03:52 - INFO - codeparrot_training - Step 31141: {'lr': 0.0004536763508232252, 'samples': 15944704, 'steps': 31141, 'loss/train': 2.0758845806121826}
-03/05/2022 02:03:55 - INFO - codeparrot_training - Step 31142: {'lr': 0.0004536732735285476, 'samples': 15945216, 'steps': 31142, 'loss/train': 1.521748661994934}
-03/05/2022 02:03:56 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/05/2022 02:04:00 - INFO - codeparrot_training - Step 31143: {'lr': 0.00045367019614209783, 'samples': 15945728, 'steps': 31143, 'loss/train': 1.296442985534668}
-03/05/2022 02:04:03 - INFO - codeparrot_training - Step 31144: {'lr': 0.0004536671186638775, 'samples': 15946240, 'steps': 31144, 'loss/train': 0.681323230266571}
-03/05/2022 02:04:04 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/05/2022 02:04:08 - INFO - codeparrot_training - Step 31145: {'lr': 0.0004536640410938879, 'samples': 15946752, 'steps': 31145, 'loss/train': 1.9207953214645386}
-03/05/2022 02:04:12 - INFO - codeparrot_training - Step 31146: {'lr': 0.00045366096343213034, 'samples': 15947264, 'steps': 31146, 'loss/train': 1.1354986429214478}
-03/05/2022 02:04:13 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/05/2022 02:04:17 - INFO - codeparrot_training - Step 31147: {'lr': 0.0004536578856786064, 'samples': 15947776, 'steps': 31147, 'loss/train': 2.243995428085327}
-03/05/2022 02:04:20 - INFO - codeparrot_training - Step 31148: {'lr': 0.0004536548078333172, 'samples': 15948288, 'steps': 31148, 'loss/train': 2.109376907348633}
-03/05/2022 02:04:21 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/05/2022 02:04:25 - INFO - codeparrot_training - Step 31149: {'lr': 0.0004536517298962645, 'samples': 15948800, 'steps': 31149, 'loss/train': 1.9802937507629395}
-03/05/2022 02:04:28 - INFO - codeparrot_training - Step 31150: {'lr': 0.00045364865186744936, 'samples': 15949312, 'steps': 31150, 'loss/train': 1.0325675010681152}
-03/05/2022 02:04:30 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/05/2022 02:04:34 - INFO - codeparrot_training - Step 31151: {'lr': 0.0004536455737468733, 'samples': 15949824, 'steps': 31151, 'loss/train': 2.50885009765625}
-03/05/2022 02:04:37 - INFO - codeparrot_training - Step 31152: {'lr': 0.00045364249553453764, 'samples': 15950336, 'steps': 31152, 'loss/train': 1.30526864528656}
-03/05/2022 02:04:38 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/05/2022 02:04:42 - INFO - codeparrot_training - Step 31153: {'lr': 0.00045363941723044386, 'samples': 15950848, 'steps': 31153, 'loss/train': 1.4854711294174194}
-03/05/2022 02:04:45 - INFO - codeparrot_training - Step 31154: {'lr': 0.0004536363388345933, 'samples': 15951360, 'steps': 31154, 'loss/train': 2.256815195083618}
-03/05/2022 02:04:46 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/05/2022 02:04:51 - INFO - codeparrot_training - Step 31155: {'lr': 0.0004536332603469873, 'samples': 15951872, 'steps': 31155, 'loss/train': 1.4689518213272095}
-03/05/2022 02:04:54 - INFO - codeparrot_training - Step 31156: {'lr': 0.0004536301817676274, 'samples': 15952384, 'steps': 31156, 'loss/train': 0.9998283982276917}
-03/05/2022 02:04:54 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/05/2022 02:04:59 - INFO - codeparrot_training - Step 31157: {'lr': 0.0004536271030965148, 'samples': 15952896, 'steps': 31157, 'loss/train': 1.9493473768234253}
-03/05/2022 02:05:02 - INFO - codeparrot_training - Step 31158: {'lr': 0.00045362402433365094, 'samples': 15953408, 'steps': 31158, 'loss/train': 1.440495491027832}
-03/05/2022 02:05:03 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/05/2022 02:05:07 - INFO - codeparrot_training - Step 31159: {'lr': 0.0004536209454790373, 'samples': 15953920, 'steps': 31159, 'loss/train': 0.06311877816915512}
-03/05/2022 02:05:11 - INFO - codeparrot_training - Step 31160: {'lr': 0.00045361786653267517, 'samples': 15954432, 'steps': 31160, 'loss/train': 1.8373218774795532}
-03/05/2022 02:05:11 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/05/2022 02:05:16 - INFO - codeparrot_training - Step 31161: {'lr': 0.00045361478749456595, 'samples': 15954944, 'steps': 31161, 'loss/train': 2.5531375408172607}
-03/05/2022 02:05:19 - INFO - codeparrot_training - Step 31162: {'lr': 0.0004536117083647111, 'samples': 15955456, 'steps': 31162, 'loss/train': 1.3080500364303589}
-03/05/2022 02:05:19 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/05/2022 02:05:24 - INFO - codeparrot_training - Step 31163: {'lr': 0.00045360862914311194, 'samples': 15955968, 'steps': 31163, 'loss/train': 1.6087499856948853}
-03/05/2022 02:05:27 - INFO - codeparrot_training - Step 31164: {'lr': 0.0004536055498297699, 'samples': 15956480, 'steps': 31164, 'loss/train': 1.876952886581421}
-03/05/2022 02:05:28 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/05/2022 02:05:33 - INFO - codeparrot_training - Step 31165: {'lr': 0.00045360247042468635, 'samples': 15956992, 'steps': 31165, 'loss/train': 1.6783844232559204}
-03/05/2022 02:05:35 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 02:05:38 - INFO - codeparrot_training - Step 31166: {'lr': 0.0004535993909278626, 'samples': 15957504, 'steps': 31166, 'loss/train': 1.0046114921569824}
-03/05/2022 02:05:41 - INFO - codeparrot_training - Step 31167: {'lr': 0.00045359631133930016, 'samples': 15958016, 'steps': 31167, 'loss/train': 1.724531888961792}
-03/05/2022 02:05:44 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/05/2022 02:05:46 - INFO - codeparrot_training - Step 31168: {'lr': 0.0004535932316590003, 'samples': 15958528, 'steps': 31168, 'loss/train': 1.582970380783081}
-03/05/2022 02:05:49 - INFO - codeparrot_training - Step 31169: {'lr': 0.00045359015188696457, 'samples': 15959040, 'steps': 31169, 'loss/train': 1.6183720827102661}
-03/05/2022 02:05:52 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/05/2022 02:05:55 - INFO - codeparrot_training - Step 31170: {'lr': 0.00045358707202319414, 'samples': 15959552, 'steps': 31170, 'loss/train': 1.1541517972946167}
-03/05/2022 02:05:58 - INFO - codeparrot_training - Step 31171: {'lr': 0.0004535839920676906, 'samples': 15960064, 'steps': 31171, 'loss/train': 1.2418867349624634}
-03/05/2022 02:06:01 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/05/2022 02:06:03 - INFO - codeparrot_training - Step 31172: {'lr': 0.0004535809120204553, 'samples': 15960576, 'steps': 31172, 'loss/train': 1.5746601819992065}
-03/05/2022 02:06:06 - INFO - codeparrot_training - Step 31173: {'lr': 0.0004535778318814895, 'samples': 15961088, 'steps': 31173, 'loss/train': 2.203705072402954}
-03/05/2022 02:06:09 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/05/2022 02:06:12 - INFO - codeparrot_training - Step 31174: {'lr': 0.0004535747516507947, 'samples': 15961600, 'steps': 31174, 'loss/train': 1.0623031854629517}
-03/05/2022 02:06:15 - INFO - codeparrot_training - Step 31175: {'lr': 0.00045357167132837223, 'samples': 15962112, 'steps': 31175, 'loss/train': 1.5531258583068848}
-03/05/2022 02:06:17 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/05/2022 02:06:20 - INFO - codeparrot_training - Step 31176: {'lr': 0.00045356859091422354, 'samples': 15962624, 'steps': 31176, 'loss/train': 1.5580382347106934}
-03/05/2022 02:06:23 - INFO - codeparrot_training - Step 31177: {'lr': 0.00045356551040835, 'samples': 15963136, 'steps': 31177, 'loss/train': 2.2512400150299072}
-03/05/2022 02:06:26 - INFO - codeparrot_training - Step 31178: {'lr': 0.0004535624298107529, 'samples': 15963648, 'steps': 31178, 'loss/train': 1.2703704833984375}
-03/05/2022 02:06:27 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/05/2022 02:06:32 - INFO - codeparrot_training - Step 31179: {'lr': 0.00045355934912143383, 'samples': 15964160, 'steps': 31179, 'loss/train': 1.8403284549713135}
-03/05/2022 02:06:35 - INFO - codeparrot_training - Step 31180: {'lr': 0.00045355626834039394, 'samples': 15964672, 'steps': 31180, 'loss/train': 1.495927333831787}
-03/05/2022 02:06:35 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/05/2022 02:06:40 - INFO - codeparrot_training - Step 31181: {'lr': 0.00045355318746763477, 'samples': 15965184, 'steps': 31181, 'loss/train': 2.033578872680664}
-03/05/2022 02:06:43 - INFO - codeparrot_training - Step 31182: {'lr': 0.0004535501065031577, 'samples': 15965696, 'steps': 31182, 'loss/train': 1.8074513673782349}
-03/05/2022 02:06:44 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/05/2022 02:06:49 - INFO - codeparrot_training - Step 31183: {'lr': 0.0004535470254469641, 'samples': 15966208, 'steps': 31183, 'loss/train': 1.4288966655731201}
-03/05/2022 02:06:52 - INFO - codeparrot_training - Step 31184: {'lr': 0.00045354394429905534, 'samples': 15966720, 'steps': 31184, 'loss/train': 1.8764216899871826}
-03/05/2022 02:06:52 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/05/2022 02:06:57 - INFO - codeparrot_training - Step 31185: {'lr': 0.0004535408630594328, 'samples': 15967232, 'steps': 31185, 'loss/train': 3.076322555541992}
-03/05/2022 02:07:00 - INFO - codeparrot_training - Step 31186: {'lr': 0.0004535377817280979, 'samples': 15967744, 'steps': 31186, 'loss/train': 2.0013303756713867}
-03/05/2022 02:07:01 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/05/2022 02:07:06 - INFO - codeparrot_training - Step 31187: {'lr': 0.0004535347003050521, 'samples': 15968256, 'steps': 31187, 'loss/train': 2.2167117595672607}
-03/05/2022 02:07:09 - INFO - codeparrot_training - Step 31188: {'lr': 0.0004535316187902966, 'samples': 15968768, 'steps': 31188, 'loss/train': 1.4744330644607544}
-03/05/2022 02:07:09 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/05/2022 02:07:14 - INFO - codeparrot_training - Step 31189: {'lr': 0.00045352853718383287, 'samples': 15969280, 'steps': 31189, 'loss/train': 2.1889350414276123}
-03/05/2022 02:07:17 - INFO - codeparrot_training - Step 31190: {'lr': 0.00045352545548566235, 'samples': 15969792, 'steps': 31190, 'loss/train': 1.952658772468567}
-03/05/2022 02:07:17 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/05/2022 02:07:22 - INFO - codeparrot_training - Step 31191: {'lr': 0.00045352237369578643, 'samples': 15970304, 'steps': 31191, 'loss/train': 2.1785707473754883}
-03/05/2022 02:07:25 - INFO - codeparrot_training - Step 31192: {'lr': 0.00045351929181420647, 'samples': 15970816, 'steps': 31192, 'loss/train': 2.016024351119995}
-03/05/2022 02:07:25 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 02:07:31 - INFO - codeparrot_training - Step 31193: {'lr': 0.0004535162098409238, 'samples': 15971328, 'steps': 31193, 'loss/train': 2.1145870685577393}
-03/05/2022 02:07:34 - INFO - codeparrot_training - Step 31194: {'lr': 0.00045351312777593995, 'samples': 15971840, 'steps': 31194, 'loss/train': 1.5336185693740845}
-03/05/2022 02:07:34 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/05/2022 02:07:39 - INFO - codeparrot_training - Step 31195: {'lr': 0.0004535100456192562, 'samples': 15972352, 'steps': 31195, 'loss/train': 1.689664602279663}
-03/05/2022 02:07:42 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/05/2022 02:07:45 - INFO - codeparrot_training - Step 31196: {'lr': 0.00045350696337087396, 'samples': 15972864, 'steps': 31196, 'loss/train': 1.7903504371643066}
-03/05/2022 02:07:48 - INFO - codeparrot_training - Step 31197: {'lr': 0.0004535038810307946, 'samples': 15973376, 'steps': 31197, 'loss/train': 1.7612403631210327}
-03/05/2022 02:07:51 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/05/2022 02:07:53 - INFO - codeparrot_training - Step 31198: {'lr': 0.00045350079859901956, 'samples': 15973888, 'steps': 31198, 'loss/train': 0.21661192178726196}
-03/05/2022 02:07:56 - INFO - codeparrot_training - Step 31199: {'lr': 0.00045349771607555017, 'samples': 15974400, 'steps': 31199, 'loss/train': 1.3992919921875}
-03/05/2022 02:08:00 - INFO - codeparrot_training - Step 31200: {'lr': 0.0004534946334603879, 'samples': 15974912, 'steps': 31200, 'loss/train': 1.5382903814315796}
-03/05/2022 02:08:00 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/05/2022 02:08:05 - INFO - codeparrot_training - Step 31201: {'lr': 0.000453491550753534, 'samples': 15975424, 'steps': 31201, 'loss/train': 1.9669768810272217}
-03/05/2022 02:08:08 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/05/2022 02:08:10 - INFO - codeparrot_training - Step 31202: {'lr': 0.00045348846795499, 'samples': 15975936, 'steps': 31202, 'loss/train': 1.3622984886169434}
-03/05/2022 02:08:13 - INFO - codeparrot_training - Step 31203: {'lr': 0.0004534853850647572, 'samples': 15976448, 'steps': 31203, 'loss/train': 1.906019687652588}
-03/05/2022 02:08:16 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/05/2022 02:08:19 - INFO - codeparrot_training - Step 31204: {'lr': 0.00045348230208283716, 'samples': 15976960, 'steps': 31204, 'loss/train': 2.3006138801574707}
-03/05/2022 02:08:22 - INFO - codeparrot_training - Step 31205: {'lr': 0.000453479219009231, 'samples': 15977472, 'steps': 31205, 'loss/train': 1.388038158416748}
-03/05/2022 02:08:25 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/05/2022 02:08:27 - INFO - codeparrot_training - Step 31206: {'lr': 0.00045347613584394034, 'samples': 15977984, 'steps': 31206, 'loss/train': 1.5862382650375366}
-03/05/2022 02:08:30 - INFO - codeparrot_training - Step 31207: {'lr': 0.0004534730525869664, 'samples': 15978496, 'steps': 31207, 'loss/train': 2.2657642364501953}
-03/05/2022 02:08:34 - INFO - codeparrot_training - Step 31208: {'lr': 0.0004534699692383106, 'samples': 15979008, 'steps': 31208, 'loss/train': 1.9134202003479004}
-03/05/2022 02:08:34 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/05/2022 02:08:39 - INFO - codeparrot_training - Step 31209: {'lr': 0.00045346688579797444, 'samples': 15979520, 'steps': 31209, 'loss/train': 2.785701274871826}
-03/05/2022 02:08:42 - INFO - codeparrot_training - Step 31210: {'lr': 0.0004534638022659592, 'samples': 15980032, 'steps': 31210, 'loss/train': 2.153606414794922}
-03/05/2022 02:08:42 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/05/2022 02:08:47 - INFO - codeparrot_training - Step 31211: {'lr': 0.00045346071864226634, 'samples': 15980544, 'steps': 31211, 'loss/train': 1.8848086595535278}
-03/05/2022 02:08:50 - INFO - codeparrot_training - Step 31212: {'lr': 0.0004534576349268973, 'samples': 15981056, 'steps': 31212, 'loss/train': 1.7241636514663696}
-03/05/2022 02:08:51 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 02:08:56 - INFO - codeparrot_training - Step 31213: {'lr': 0.00045345455111985326, 'samples': 15981568, 'steps': 31213, 'loss/train': 1.588283896446228}
-03/05/2022 02:08:59 - INFO - codeparrot_training - Step 31214: {'lr': 0.0004534514672211358, 'samples': 15982080, 'steps': 31214, 'loss/train': 0.2839645743370056}
-03/05/2022 02:08:59 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/05/2022 02:09:04 - INFO - codeparrot_training - Step 31215: {'lr': 0.0004534483832307462, 'samples': 15982592, 'steps': 31215, 'loss/train': 0.888735294342041}
-03/05/2022 02:09:07 - INFO - codeparrot_training - Step 31216: {'lr': 0.00045344529914868593, 'samples': 15983104, 'steps': 31216, 'loss/train': 2.0720736980438232}
-03/05/2022 02:09:09 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 02:09:13 - INFO - codeparrot_training - Step 31217: {'lr': 0.0004534422149749564, 'samples': 15983616, 'steps': 31217, 'loss/train': 1.3915958404541016}
-03/05/2022 02:09:16 - INFO - codeparrot_training - Step 31218: {'lr': 0.0004534391307095589, 'samples': 15984128, 'steps': 31218, 'loss/train': 1.2616907358169556}
-03/05/2022 02:09:17 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 02:09:21 - INFO - codeparrot_training - Step 31219: {'lr': 0.0004534360463524948, 'samples': 15984640, 'steps': 31219, 'loss/train': 1.9746536016464233}
-03/05/2022 02:09:24 - INFO - codeparrot_training - Step 31220: {'lr': 0.00045343296190376566, 'samples': 15985152, 'steps': 31220, 'loss/train': 1.8314369916915894}
-03/05/2022 02:09:26 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/05/2022 02:09:30 - INFO - codeparrot_training - Step 31221: {'lr': 0.0004534298773633727, 'samples': 15985664, 'steps': 31221, 'loss/train': 1.94963800907135}
-03/05/2022 02:09:33 - INFO - codeparrot_training - Step 31222: {'lr': 0.00045342679273131743, 'samples': 15986176, 'steps': 31222, 'loss/train': 1.6512612104415894}
-03/05/2022 02:09:34 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/05/2022 02:09:38 - INFO - codeparrot_training - Step 31223: {'lr': 0.0004534237080076011, 'samples': 15986688, 'steps': 31223, 'loss/train': 1.544721007347107}
-03/05/2022 02:09:41 - INFO - codeparrot_training - Step 31224: {'lr': 0.0004534206231922253, 'samples': 15987200, 'steps': 31224, 'loss/train': 1.469767451286316}
-03/05/2022 02:09:42 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/05/2022 02:09:46 - INFO - codeparrot_training - Step 31225: {'lr': 0.0004534175382851913, 'samples': 15987712, 'steps': 31225, 'loss/train': 1.243323564529419}
-03/05/2022 02:09:49 - INFO - codeparrot_training - Step 31226: {'lr': 0.0004534144532865004, 'samples': 15988224, 'steps': 31226, 'loss/train': 1.938773274421692}
-03/05/2022 02:09:50 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/05/2022 02:09:55 - INFO - codeparrot_training - Step 31227: {'lr': 0.00045341136819615415, 'samples': 15988736, 'steps': 31227, 'loss/train': 1.9212853908538818}
-03/05/2022 02:09:58 - INFO - codeparrot_training - Step 31228: {'lr': 0.0004534082830141538, 'samples': 15989248, 'steps': 31228, 'loss/train': 1.1477086544036865}
-03/05/2022 02:09:59 - INFO - codeparrot_training - Skipping example with length 86 (seq_length=1024)
-03/05/2022 02:10:03 - INFO - codeparrot_training - Step 31229: {'lr': 0.00045340519774050093, 'samples': 15989760, 'steps': 31229, 'loss/train': 1.0667884349822998}
-03/05/2022 02:10:06 - INFO - codeparrot_training - Step 31230: {'lr': 0.0004534021123751968, 'samples': 15990272, 'steps': 31230, 'loss/train': 1.9355428218841553}
-03/05/2022 02:10:07 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/05/2022 02:10:12 - INFO - codeparrot_training - Step 31231: {'lr': 0.00045339902691824275, 'samples': 15990784, 'steps': 31231, 'loss/train': 1.748635172843933}
-03/05/2022 02:10:15 - INFO - codeparrot_training - Step 31232: {'lr': 0.0004533959413696402, 'samples': 15991296, 'steps': 31232, 'loss/train': 2.0622451305389404}
-03/05/2022 02:10:15 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 02:10:20 - INFO - codeparrot_training - Step 31233: {'lr': 0.0004533928557293907, 'samples': 15991808, 'steps': 31233, 'loss/train': 1.6732925176620483}
-03/05/2022 02:10:23 - INFO - codeparrot_training - Step 31234: {'lr': 0.00045338976999749546, 'samples': 15992320, 'steps': 31234, 'loss/train': 1.7939825057983398}
-03/05/2022 02:10:24 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/05/2022 02:10:29 - INFO - codeparrot_training - Step 31235: {'lr': 0.00045338668417395595, 'samples': 15992832, 'steps': 31235, 'loss/train': 1.3740499019622803}
-03/05/2022 02:10:32 - INFO - codeparrot_training - Step 31236: {'lr': 0.0004533835982587735, 'samples': 15993344, 'steps': 31236, 'loss/train': 1.6959775686264038}
-03/05/2022 02:10:32 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/05/2022 02:10:37 - INFO - codeparrot_training - Step 31237: {'lr': 0.00045338051225194954, 'samples': 15993856, 'steps': 31237, 'loss/train': 1.2128299474716187}
-03/05/2022 02:10:40 - INFO - codeparrot_training - Step 31238: {'lr': 0.0004533774261534855, 'samples': 15994368, 'steps': 31238, 'loss/train': 2.155068874359131}
-03/05/2022 02:10:40 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/05/2022 02:10:46 - INFO - codeparrot_training - Step 31239: {'lr': 0.00045337433996338274, 'samples': 15994880, 'steps': 31239, 'loss/train': 2.0498902797698975}
-03/05/2022 02:10:49 - INFO - codeparrot_training - Step 31240: {'lr': 0.0004533712536816426, 'samples': 15995392, 'steps': 31240, 'loss/train': 1.4867193698883057}
-03/05/2022 02:10:49 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 02:10:54 - INFO - codeparrot_training - Step 31241: {'lr': 0.0004533681673082665, 'samples': 15995904, 'steps': 31241, 'loss/train': 2.2967164516448975}
-03/05/2022 02:10:57 - INFO - codeparrot_training - Step 31242: {'lr': 0.00045336508084325587, 'samples': 15996416, 'steps': 31242, 'loss/train': 1.5800848007202148}
-03/05/2022 02:10:57 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 02:11:03 - INFO - codeparrot_training - Step 31243: {'lr': 0.0004533619942866121, 'samples': 15996928, 'steps': 31243, 'loss/train': 2.5654125213623047}
-03/05/2022 02:11:06 - INFO - codeparrot_training - Step 31244: {'lr': 0.00045335890763833646, 'samples': 15997440, 'steps': 31244, 'loss/train': 2.2336838245391846}
-03/05/2022 02:11:06 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/05/2022 02:11:11 - INFO - codeparrot_training - Step 31245: {'lr': 0.0004533558208984305, 'samples': 15997952, 'steps': 31245, 'loss/train': 2.403945207595825}
-03/05/2022 02:11:14 - INFO - codeparrot_training - Step 31246: {'lr': 0.0004533527340668956, 'samples': 15998464, 'steps': 31246, 'loss/train': 0.5994052886962891}
-03/05/2022 02:11:14 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/05/2022 02:11:19 - INFO - codeparrot_training - Step 31247: {'lr': 0.000453349647143733, 'samples': 15998976, 'steps': 31247, 'loss/train': 1.2113748788833618}
-03/05/2022 02:11:23 - INFO - codeparrot_training - Step 31248: {'lr': 0.00045334656012894424, 'samples': 15999488, 'steps': 31248, 'loss/train': 1.7672685384750366}
-03/05/2022 02:11:23 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/05/2022 02:11:28 - INFO - codeparrot_training - Step 31249: {'lr': 0.00045334347302253064, 'samples': 16000000, 'steps': 31249, 'loss/train': 1.8587634563446045}
-03/05/2022 02:11:31 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/05/2022 02:11:33 - INFO - codeparrot_training - Step 31250: {'lr': 0.00045334038582449355, 'samples': 16000512, 'steps': 31250, 'loss/train': 1.4035993814468384}
-03/05/2022 02:11:36 - INFO - codeparrot_training - Step 31251: {'lr': 0.0004533372985348345, 'samples': 16001024, 'steps': 31251, 'loss/train': 2.10274600982666}
-03/05/2022 02:11:39 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/05/2022 02:11:41 - INFO - codeparrot_training - Step 31252: {'lr': 0.00045333421115355477, 'samples': 16001536, 'steps': 31252, 'loss/train': 1.3081153631210327}
-03/05/2022 02:11:45 - INFO - codeparrot_training - Step 31253: {'lr': 0.00045333112368065585, 'samples': 16002048, 'steps': 31253, 'loss/train': 1.151039719581604}
-03/05/2022 02:11:47 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 02:11:50 - INFO - codeparrot_training - Step 31254: {'lr': 0.00045332803611613896, 'samples': 16002560, 'steps': 31254, 'loss/train': 1.4762095212936401}
-03/05/2022 02:11:53 - INFO - codeparrot_training - Step 31255: {'lr': 0.00045332494846000564, 'samples': 16003072, 'steps': 31255, 'loss/train': 0.829897403717041}
-03/05/2022 02:11:56 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/05/2022 02:11:58 - INFO - codeparrot_training - Step 31256: {'lr': 0.00045332186071225724, 'samples': 16003584, 'steps': 31256, 'loss/train': 1.4992725849151611}
-03/05/2022 02:12:02 - INFO - codeparrot_training - Step 31257: {'lr': 0.00045331877287289516, 'samples': 16004096, 'steps': 31257, 'loss/train': 1.9860498905181885}
-03/05/2022 02:12:04 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/05/2022 02:12:07 - INFO - codeparrot_training - Step 31258: {'lr': 0.00045331568494192076, 'samples': 16004608, 'steps': 31258, 'loss/train': 1.2602415084838867}
-03/05/2022 02:12:10 - INFO - codeparrot_training - Step 31259: {'lr': 0.00045331259691933545, 'samples': 16005120, 'steps': 31259, 'loss/train': 1.5225762128829956}
-03/05/2022 02:12:12 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 02:12:15 - INFO - codeparrot_training - Step 31260: {'lr': 0.00045330950880514065, 'samples': 16005632, 'steps': 31260, 'loss/train': 1.94674551486969}
-03/05/2022 02:12:18 - INFO - codeparrot_training - Step 31261: {'lr': 0.0004533064205993377, 'samples': 16006144, 'steps': 31261, 'loss/train': 2.097560167312622}
-03/05/2022 02:12:20 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/05/2022 02:12:24 - INFO - codeparrot_training - Step 31262: {'lr': 0.000453303332301928, 'samples': 16006656, 'steps': 31262, 'loss/train': 1.7939579486846924}
-03/05/2022 02:12:27 - INFO - codeparrot_training - Step 31263: {'lr': 0.00045330024391291294, 'samples': 16007168, 'steps': 31263, 'loss/train': 1.6667006015777588}
-03/05/2022 02:12:29 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/05/2022 02:12:32 - INFO - codeparrot_training - Step 31264: {'lr': 0.00045329715543229396, 'samples': 16007680, 'steps': 31264, 'loss/train': 1.5476551055908203}
-03/05/2022 02:12:35 - INFO - codeparrot_training - Step 31265: {'lr': 0.0004532940668600724, 'samples': 16008192, 'steps': 31265, 'loss/train': 2.3178257942199707}
-03/05/2022 02:12:37 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/05/2022 02:12:40 - INFO - codeparrot_training - Step 31266: {'lr': 0.00045329097819624966, 'samples': 16008704, 'steps': 31266, 'loss/train': 1.9833815097808838}
-03/05/2022 02:12:44 - INFO - codeparrot_training - Step 31267: {'lr': 0.00045328788944082717, 'samples': 16009216, 'steps': 31267, 'loss/train': 1.0968315601348877}
-03/05/2022 02:12:45 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 02:12:49 - INFO - codeparrot_training - Step 31268: {'lr': 0.0004532848005938063, 'samples': 16009728, 'steps': 31268, 'loss/train': 0.5411005616188049}
-03/05/2022 02:12:52 - INFO - codeparrot_training - Step 31269: {'lr': 0.0004532817116551884, 'samples': 16010240, 'steps': 31269, 'loss/train': 0.9187597632408142}
-03/05/2022 02:12:54 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/05/2022 02:12:57 - INFO - codeparrot_training - Step 31270: {'lr': 0.00045327862262497495, 'samples': 16010752, 'steps': 31270, 'loss/train': 1.0253801345825195}
-03/05/2022 02:13:01 - INFO - codeparrot_training - Step 31271: {'lr': 0.00045327553350316726, 'samples': 16011264, 'steps': 31271, 'loss/train': 0.2541907727718353}
-03/05/2022 02:13:02 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/05/2022 02:13:06 - INFO - codeparrot_training - Step 31272: {'lr': 0.00045327244428976677, 'samples': 16011776, 'steps': 31272, 'loss/train': 0.7192752361297607}
-03/05/2022 02:13:09 - INFO - codeparrot_training - Step 31273: {'lr': 0.00045326935498477477, 'samples': 16012288, 'steps': 31273, 'loss/train': 1.8638173341751099}
-03/05/2022 02:13:11 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/05/2022 02:13:14 - INFO - codeparrot_training - Step 31274: {'lr': 0.00045326626558819284, 'samples': 16012800, 'steps': 31274, 'loss/train': 2.1817362308502197}
-03/05/2022 02:13:18 - INFO - codeparrot_training - Step 31275: {'lr': 0.00045326317610002223, 'samples': 16013312, 'steps': 31275, 'loss/train': 1.6549276113510132}
-03/05/2022 02:13:20 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/05/2022 02:13:23 - INFO - codeparrot_training - Step 31276: {'lr': 0.00045326008652026435, 'samples': 16013824, 'steps': 31276, 'loss/train': 1.3947818279266357}
-03/05/2022 02:13:26 - INFO - codeparrot_training - Step 31277: {'lr': 0.00045325699684892065, 'samples': 16014336, 'steps': 31277, 'loss/train': 2.360452651977539}
-03/05/2022 02:13:28 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/05/2022 02:13:31 - INFO - codeparrot_training - Step 31278: {'lr': 0.00045325390708599245, 'samples': 16014848, 'steps': 31278, 'loss/train': 1.9629563093185425}
-03/05/2022 02:13:35 - INFO - codeparrot_training - Step 31279: {'lr': 0.0004532508172314812, 'samples': 16015360, 'steps': 31279, 'loss/train': 1.4060941934585571}
-03/05/2022 02:13:37 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/05/2022 02:13:40 - INFO - codeparrot_training - Step 31280: {'lr': 0.0004532477272853882, 'samples': 16015872, 'steps': 31280, 'loss/train': 1.2763826847076416}
-03/05/2022 02:13:43 - INFO - codeparrot_training - Step 31281: {'lr': 0.000453244637247715, 'samples': 16016384, 'steps': 31281, 'loss/train': 1.9019306898117065}
-03/05/2022 02:13:46 - INFO - codeparrot_training - Step 31282: {'lr': 0.0004532415471184629, 'samples': 16016896, 'steps': 31282, 'loss/train': 1.9329885244369507}
-03/05/2022 02:13:46 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/05/2022 02:13:52 - INFO - codeparrot_training - Step 31283: {'lr': 0.0004532384568976332, 'samples': 16017408, 'steps': 31283, 'loss/train': 1.425925850868225}
-03/05/2022 02:13:54 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/05/2022 02:13:57 - INFO - codeparrot_training - Step 31284: {'lr': 0.00045323536658522747, 'samples': 16017920, 'steps': 31284, 'loss/train': 1.7288312911987305}
-03/05/2022 02:14:00 - INFO - codeparrot_training - Step 31285: {'lr': 0.00045323227618124695, 'samples': 16018432, 'steps': 31285, 'loss/train': 1.0297415256500244}
-03/05/2022 02:14:03 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/05/2022 02:14:05 - INFO - codeparrot_training - Step 31286: {'lr': 0.00045322918568569315, 'samples': 16018944, 'steps': 31286, 'loss/train': 1.5664710998535156}
-03/05/2022 02:14:09 - INFO - codeparrot_training - Step 31287: {'lr': 0.0004532260950985675, 'samples': 16019456, 'steps': 31287, 'loss/train': 2.3907506465911865}
-03/05/2022 02:14:12 - INFO - codeparrot_training - Step 31288: {'lr': 0.0004532230044198712, 'samples': 16019968, 'steps': 31288, 'loss/train': 2.0103282928466797}
-03/05/2022 02:14:12 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/05/2022 02:14:17 - INFO - codeparrot_training - Step 31289: {'lr': 0.00045321991364960577, 'samples': 16020480, 'steps': 31289, 'loss/train': 1.5371465682983398}
-03/05/2022 02:14:20 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/05/2022 02:14:23 - INFO - codeparrot_training - Step 31290: {'lr': 0.00045321682278777253, 'samples': 16020992, 'steps': 31290, 'loss/train': 2.0595197677612305}
-03/05/2022 02:14:26 - INFO - codeparrot_training - Step 31291: {'lr': 0.00045321373183437305, 'samples': 16021504, 'steps': 31291, 'loss/train': 2.4261631965637207}
-03/05/2022 02:14:29 - INFO - codeparrot_training - Step 31292: {'lr': 0.0004532106407894085, 'samples': 16022016, 'steps': 31292, 'loss/train': 2.2770328521728516}
-03/05/2022 02:14:29 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 02:14:34 - INFO - codeparrot_training - Step 31293: {'lr': 0.0004532075496528804, 'samples': 16022528, 'steps': 31293, 'loss/train': 1.899196982383728}
-03/05/2022 02:14:37 - INFO - codeparrot_training - Step 31294: {'lr': 0.0004532044584247901, 'samples': 16023040, 'steps': 31294, 'loss/train': 1.940315842628479}
-03/05/2022 02:14:37 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 02:14:43 - INFO - codeparrot_training - Step 31295: {'lr': 0.00045320136710513907, 'samples': 16023552, 'steps': 31295, 'loss/train': 2.3629398345947266}
-03/05/2022 02:14:46 - INFO - codeparrot_training - Step 31296: {'lr': 0.00045319827569392855, 'samples': 16024064, 'steps': 31296, 'loss/train': 2.0255892276763916}
-03/05/2022 02:14:46 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 02:14:51 - INFO - codeparrot_training - Step 31297: {'lr': 0.00045319518419116014, 'samples': 16024576, 'steps': 31297, 'loss/train': 2.358577251434326}
-03/05/2022 02:14:55 - INFO - codeparrot_training - Step 31298: {'lr': 0.00045319209259683503, 'samples': 16025088, 'steps': 31298, 'loss/train': 2.255451202392578}
-03/05/2022 02:14:55 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/05/2022 02:15:00 - INFO - codeparrot_training - Step 31299: {'lr': 0.0004531890009109547, 'samples': 16025600, 'steps': 31299, 'loss/train': 1.9258549213409424}
-03/05/2022 02:15:03 - INFO - codeparrot_training - Step 31300: {'lr': 0.0004531859091335205, 'samples': 16026112, 'steps': 31300, 'loss/train': 1.7282050848007202}
-03/05/2022 02:15:03 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 02:15:08 - INFO - codeparrot_training - Step 31301: {'lr': 0.00045318281726453393, 'samples': 16026624, 'steps': 31301, 'loss/train': 1.7986574172973633}
-03/05/2022 02:15:11 - INFO - codeparrot_training - Step 31302: {'lr': 0.00045317972530399634, 'samples': 16027136, 'steps': 31302, 'loss/train': 3.4930503368377686}
-03/05/2022 02:15:11 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 02:15:17 - INFO - codeparrot_training - Step 31303: {'lr': 0.00045317663325190904, 'samples': 16027648, 'steps': 31303, 'loss/train': 1.911583423614502}
-03/05/2022 02:15:20 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/05/2022 02:15:22 - INFO - codeparrot_training - Step 31304: {'lr': 0.00045317354110827344, 'samples': 16028160, 'steps': 31304, 'loss/train': 1.2248088121414185}
-03/05/2022 02:15:25 - INFO - codeparrot_training - Step 31305: {'lr': 0.0004531704488730911, 'samples': 16028672, 'steps': 31305, 'loss/train': 0.12408903241157532}
-03/05/2022 02:15:28 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/05/2022 02:15:30 - INFO - codeparrot_training - Step 31306: {'lr': 0.0004531673565463632, 'samples': 16029184, 'steps': 31306, 'loss/train': 1.8158921003341675}
-03/05/2022 02:15:34 - INFO - codeparrot_training - Step 31307: {'lr': 0.0004531642641280913, 'samples': 16029696, 'steps': 31307, 'loss/train': 0.13636095821857452}
-03/05/2022 02:15:37 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/05/2022 02:15:39 - INFO - codeparrot_training - Step 31308: {'lr': 0.0004531611716182767, 'samples': 16030208, 'steps': 31308, 'loss/train': 2.266716957092285}
-03/05/2022 02:15:42 - INFO - codeparrot_training - Step 31309: {'lr': 0.0004531580790169207, 'samples': 16030720, 'steps': 31309, 'loss/train': 1.81352961063385}
-03/05/2022 02:15:45 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/05/2022 02:15:47 - INFO - codeparrot_training - Step 31310: {'lr': 0.00045315498632402494, 'samples': 16031232, 'steps': 31310, 'loss/train': 0.7700819373130798}
-03/05/2022 02:15:51 - INFO - codeparrot_training - Step 31311: {'lr': 0.0004531518935395906, 'samples': 16031744, 'steps': 31311, 'loss/train': 1.8370335102081299}
-03/05/2022 02:15:53 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/05/2022 02:15:56 - INFO - codeparrot_training - Step 31312: {'lr': 0.00045314880066361923, 'samples': 16032256, 'steps': 31312, 'loss/train': 1.4086246490478516}
-03/05/2022 02:15:59 - INFO - codeparrot_training - Step 31313: {'lr': 0.00045314570769611207, 'samples': 16032768, 'steps': 31313, 'loss/train': 1.8708747625350952}
-03/05/2022 02:16:02 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/05/2022 02:16:04 - INFO - codeparrot_training - Step 31314: {'lr': 0.00045314261463707064, 'samples': 16033280, 'steps': 31314, 'loss/train': 2.1223835945129395}
-03/05/2022 02:16:07 - INFO - codeparrot_training - Step 31315: {'lr': 0.00045313952148649626, 'samples': 16033792, 'steps': 31315, 'loss/train': 1.892887830734253}
-03/05/2022 02:16:10 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/05/2022 02:16:13 - INFO - codeparrot_training - Step 31316: {'lr': 0.0004531364282443904, 'samples': 16034304, 'steps': 31316, 'loss/train': 1.6936484575271606}
-03/05/2022 02:16:16 - INFO - codeparrot_training - Step 31317: {'lr': 0.00045313333491075433, 'samples': 16034816, 'steps': 31317, 'loss/train': 1.6351993083953857}
-03/05/2022 02:16:18 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 02:16:21 - INFO - codeparrot_training - Step 31318: {'lr': 0.0004531302414855895, 'samples': 16035328, 'steps': 31318, 'loss/train': 0.8834212422370911}
-03/05/2022 02:16:24 - INFO - codeparrot_training - Step 31319: {'lr': 0.0004531271479688974, 'samples': 16035840, 'steps': 31319, 'loss/train': 1.852533221244812}
-03/05/2022 02:16:27 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/05/2022 02:16:29 - INFO - codeparrot_training - Step 31320: {'lr': 0.00045312405436067927, 'samples': 16036352, 'steps': 31320, 'loss/train': 1.9280599355697632}
-03/05/2022 02:16:33 - INFO - codeparrot_training - Step 31321: {'lr': 0.00045312096066093654, 'samples': 16036864, 'steps': 31321, 'loss/train': 1.5642390251159668}
-03/05/2022 02:16:35 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/05/2022 02:16:38 - INFO - codeparrot_training - Step 31322: {'lr': 0.0004531178668696707, 'samples': 16037376, 'steps': 31322, 'loss/train': 2.000910758972168}
-03/05/2022 02:16:41 - INFO - codeparrot_training - Step 31323: {'lr': 0.00045311477298688306, 'samples': 16037888, 'steps': 31323, 'loss/train': 0.7024642825126648}
-03/05/2022 02:16:43 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/05/2022 02:16:46 - INFO - codeparrot_training - Step 31324: {'lr': 0.0004531116790125751, 'samples': 16038400, 'steps': 31324, 'loss/train': 1.7582299709320068}
-03/05/2022 02:16:50 - INFO - codeparrot_training - Step 31325: {'lr': 0.00045310858494674813, 'samples': 16038912, 'steps': 31325, 'loss/train': 0.2537677586078644}
-03/05/2022 02:16:51 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/05/2022 02:16:55 - INFO - codeparrot_training - Step 31326: {'lr': 0.00045310549078940356, 'samples': 16039424, 'steps': 31326, 'loss/train': 1.4679514169692993}
-03/05/2022 02:16:58 - INFO - codeparrot_training - Step 31327: {'lr': 0.00045310239654054274, 'samples': 16039936, 'steps': 31327, 'loss/train': 2.0579328536987305}
-03/05/2022 02:17:00 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/05/2022 02:17:03 - INFO - codeparrot_training - Step 31328: {'lr': 0.0004530993022001672, 'samples': 16040448, 'steps': 31328, 'loss/train': 2.586130380630493}
-03/05/2022 02:17:06 - INFO - codeparrot_training - Step 31329: {'lr': 0.00045309620776827817, 'samples': 16040960, 'steps': 31329, 'loss/train': 1.7450212240219116}
-03/05/2022 02:17:08 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/05/2022 02:17:12 - INFO - codeparrot_training - Step 31330: {'lr': 0.00045309311324487713, 'samples': 16041472, 'steps': 31330, 'loss/train': 2.352889060974121}
-03/05/2022 02:17:15 - INFO - codeparrot_training - Step 31331: {'lr': 0.0004530900186299655, 'samples': 16041984, 'steps': 31331, 'loss/train': 2.0452089309692383}
-03/05/2022 02:17:17 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/05/2022 02:17:20 - INFO - codeparrot_training - Step 31332: {'lr': 0.0004530869239235446, 'samples': 16042496, 'steps': 31332, 'loss/train': 1.4178394079208374}
-03/05/2022 02:17:23 - INFO - codeparrot_training - Step 31333: {'lr': 0.0004530838291256159, 'samples': 16043008, 'steps': 31333, 'loss/train': 1.6011756658554077}
-03/05/2022 02:17:25 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/05/2022 02:17:28 - INFO - codeparrot_training - Step 31334: {'lr': 0.0004530807342361807, 'samples': 16043520, 'steps': 31334, 'loss/train': 1.2463372945785522}
-03/05/2022 02:17:32 - INFO - codeparrot_training - Step 31335: {'lr': 0.0004530776392552406, 'samples': 16044032, 'steps': 31335, 'loss/train': 0.9086995720863342}
-03/05/2022 02:17:33 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/05/2022 02:17:37 - INFO - codeparrot_training - Step 31336: {'lr': 0.0004530745441827967, 'samples': 16044544, 'steps': 31336, 'loss/train': 1.0100091695785522}
-03/05/2022 02:17:40 - INFO - codeparrot_training - Step 31337: {'lr': 0.0004530714490188506, 'samples': 16045056, 'steps': 31337, 'loss/train': 1.6336041688919067}
-03/05/2022 02:17:42 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/05/2022 02:17:45 - INFO - codeparrot_training - Step 31338: {'lr': 0.00045306835376340366, 'samples': 16045568, 'steps': 31338, 'loss/train': 2.1312601566314697}
-03/05/2022 02:17:48 - INFO - codeparrot_training - Step 31339: {'lr': 0.00045306525841645723, 'samples': 16046080, 'steps': 31339, 'loss/train': 1.2842655181884766}
-03/05/2022 02:17:50 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/05/2022 02:17:54 - INFO - codeparrot_training - Step 31340: {'lr': 0.0004530621629780127, 'samples': 16046592, 'steps': 31340, 'loss/train': 1.949377417564392}
-03/05/2022 02:17:57 - INFO - codeparrot_training - Step 31341: {'lr': 0.00045305906744807156, 'samples': 16047104, 'steps': 31341, 'loss/train': 1.6233694553375244}
-03/05/2022 02:17:59 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/05/2022 02:18:02 - INFO - codeparrot_training - Step 31342: {'lr': 0.0004530559718266351, 'samples': 16047616, 'steps': 31342, 'loss/train': 1.977818489074707}
-03/05/2022 02:18:06 - INFO - codeparrot_training - Step 31343: {'lr': 0.0004530528761137047, 'samples': 16048128, 'steps': 31343, 'loss/train': 1.9165534973144531}
-03/05/2022 02:18:08 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/05/2022 02:18:11 - INFO - codeparrot_training - Step 31344: {'lr': 0.0004530497803092819, 'samples': 16048640, 'steps': 31344, 'loss/train': 0.1004122644662857}
-03/05/2022 02:18:14 - INFO - codeparrot_training - Step 31345: {'lr': 0.000453046684413368, 'samples': 16049152, 'steps': 31345, 'loss/train': 1.3429678678512573}
-03/05/2022 02:18:16 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/05/2022 02:18:19 - INFO - codeparrot_training - Step 31346: {'lr': 0.0004530435884259644, 'samples': 16049664, 'steps': 31346, 'loss/train': 1.2767664194107056}
-03/05/2022 02:18:22 - INFO - codeparrot_training - Step 31347: {'lr': 0.0004530404923470724, 'samples': 16050176, 'steps': 31347, 'loss/train': 1.4328128099441528}
-03/05/2022 02:18:24 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/05/2022 02:18:28 - INFO - codeparrot_training - Step 31348: {'lr': 0.0004530373961766935, 'samples': 16050688, 'steps': 31348, 'loss/train': 2.261796236038208}
-03/05/2022 02:18:31 - INFO - codeparrot_training - Step 31349: {'lr': 0.00045303429991482914, 'samples': 16051200, 'steps': 31349, 'loss/train': 1.5826224088668823}
-03/05/2022 02:18:33 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/05/2022 02:18:36 - INFO - codeparrot_training - Step 31350: {'lr': 0.00045303120356148067, 'samples': 16051712, 'steps': 31350, 'loss/train': 1.5257384777069092}
-03/05/2022 02:18:39 - INFO - codeparrot_training - Step 31351: {'lr': 0.00045302810711664944, 'samples': 16052224, 'steps': 31351, 'loss/train': 2.089235544204712}
-03/05/2022 02:18:41 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/05/2022 02:18:44 - INFO - codeparrot_training - Step 31352: {'lr': 0.00045302501058033687, 'samples': 16052736, 'steps': 31352, 'loss/train': 1.0850471258163452}
-03/05/2022 02:18:48 - INFO - codeparrot_training - Step 31353: {'lr': 0.0004530219139525444, 'samples': 16053248, 'steps': 31353, 'loss/train': 1.3114135265350342}
-03/05/2022 02:18:49 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/05/2022 02:18:53 - INFO - codeparrot_training - Step 31354: {'lr': 0.0004530188172332733, 'samples': 16053760, 'steps': 31354, 'loss/train': 1.7622098922729492}
-03/05/2022 02:18:56 - INFO - codeparrot_training - Step 31355: {'lr': 0.00045301572042252516, 'samples': 16054272, 'steps': 31355, 'loss/train': 1.7171176671981812}
-03/05/2022 02:18:58 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 02:19:01 - INFO - codeparrot_training - Step 31356: {'lr': 0.00045301262352030123, 'samples': 16054784, 'steps': 31356, 'loss/train': 1.5141102075576782}
-03/05/2022 02:19:05 - INFO - codeparrot_training - Step 31357: {'lr': 0.00045300952652660296, 'samples': 16055296, 'steps': 31357, 'loss/train': 2.0707833766937256}
-03/05/2022 02:19:06 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/05/2022 02:19:10 - INFO - codeparrot_training - Step 31358: {'lr': 0.0004530064294414317, 'samples': 16055808, 'steps': 31358, 'loss/train': 0.7106841802597046}
-03/05/2022 02:19:13 - INFO - codeparrot_training - Step 31359: {'lr': 0.00045300333226478887, 'samples': 16056320, 'steps': 31359, 'loss/train': 1.8802953958511353}
-03/05/2022 02:19:16 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/05/2022 02:19:18 - INFO - codeparrot_training - Step 31360: {'lr': 0.0004530002349966759, 'samples': 16056832, 'steps': 31360, 'loss/train': 1.8785624504089355}
-03/05/2022 02:19:22 - INFO - codeparrot_training - Step 31361: {'lr': 0.0004529971376370941, 'samples': 16057344, 'steps': 31361, 'loss/train': 1.9405207633972168}
-03/05/2022 02:19:25 - INFO - codeparrot_training - Step 31362: {'lr': 0.00045299404018604494, 'samples': 16057856, 'steps': 31362, 'loss/train': 2.0269734859466553}
-03/05/2022 02:19:25 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/05/2022 02:19:30 - INFO - codeparrot_training - Step 31363: {'lr': 0.00045299094264352987, 'samples': 16058368, 'steps': 31363, 'loss/train': 1.0510669946670532}
-03/05/2022 02:19:33 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/05/2022 02:19:35 - INFO - codeparrot_training - Step 31364: {'lr': 0.00045298784500955014, 'samples': 16058880, 'steps': 31364, 'loss/train': 1.7317931652069092}
-03/05/2022 02:19:39 - INFO - codeparrot_training - Step 31365: {'lr': 0.0004529847472841073, 'samples': 16059392, 'steps': 31365, 'loss/train': 1.490064024925232}
-03/05/2022 02:19:41 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/05/2022 02:19:44 - INFO - codeparrot_training - Step 31366: {'lr': 0.00045298164946720254, 'samples': 16059904, 'steps': 31366, 'loss/train': 1.401496410369873}
-03/05/2022 02:19:47 - INFO - codeparrot_training - Step 31367: {'lr': 0.0004529785515588375, 'samples': 16060416, 'steps': 31367, 'loss/train': 0.9100533723831177}
-03/05/2022 02:19:50 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/05/2022 02:19:52 - INFO - codeparrot_training - Step 31368: {'lr': 0.00045297545355901336, 'samples': 16060928, 'steps': 31368, 'loss/train': 1.887742280960083}
-03/05/2022 02:19:56 - INFO - codeparrot_training - Step 31369: {'lr': 0.00045297235546773175, 'samples': 16061440, 'steps': 31369, 'loss/train': 1.6553266048431396}
-03/05/2022 02:19:58 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/05/2022 02:20:01 - INFO - codeparrot_training - Step 31370: {'lr': 0.0004529692572849938, 'samples': 16061952, 'steps': 31370, 'loss/train': 2.5361480712890625}
-03/05/2022 02:20:04 - INFO - codeparrot_training - Step 31371: {'lr': 0.00045296615901080107, 'samples': 16062464, 'steps': 31371, 'loss/train': 1.845834493637085}
-03/05/2022 02:20:07 - INFO - codeparrot_training - Step 31372: {'lr': 0.00045296306064515493, 'samples': 16062976, 'steps': 31372, 'loss/train': 1.5230488777160645}
-03/05/2022 02:20:07 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/05/2022 02:20:13 - INFO - codeparrot_training - Step 31373: {'lr': 0.0004529599621880567, 'samples': 16063488, 'steps': 31373, 'loss/train': 1.9418060779571533}
-03/05/2022 02:20:15 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/05/2022 02:20:18 - INFO - codeparrot_training - Step 31374: {'lr': 0.00045295686363950796, 'samples': 16064000, 'steps': 31374, 'loss/train': 1.7991875410079956}
-03/05/2022 02:20:21 - INFO - codeparrot_training - Step 31375: {'lr': 0.0004529537649995099, 'samples': 16064512, 'steps': 31375, 'loss/train': 1.326756477355957}
-03/05/2022 02:20:24 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 02:20:26 - INFO - codeparrot_training - Step 31376: {'lr': 0.0004529506662680641, 'samples': 16065024, 'steps': 31376, 'loss/train': 2.5800676345825195}
-03/05/2022 02:20:29 - INFO - codeparrot_training - Step 31377: {'lr': 0.00045294756744517173, 'samples': 16065536, 'steps': 31377, 'loss/train': 2.0321543216705322}
-03/05/2022 02:20:32 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 02:20:35 - INFO - codeparrot_training - Step 31378: {'lr': 0.00045294446853083446, 'samples': 16066048, 'steps': 31378, 'loss/train': 1.50870680809021}
-03/05/2022 02:20:38 - INFO - codeparrot_training - Step 31379: {'lr': 0.00045294136952505346, 'samples': 16066560, 'steps': 31379, 'loss/train': 0.0714663416147232}
-03/05/2022 02:20:41 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 02:20:43 - INFO - codeparrot_training - Step 31380: {'lr': 0.0004529382704278302, 'samples': 16067072, 'steps': 31380, 'loss/train': 1.7470999956130981}
-03/05/2022 02:20:46 - INFO - codeparrot_training - Step 31381: {'lr': 0.0004529351712391661, 'samples': 16067584, 'steps': 31381, 'loss/train': 1.7038586139678955}
-03/05/2022 02:20:49 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/05/2022 02:20:52 - INFO - codeparrot_training - Step 31382: {'lr': 0.0004529320719590626, 'samples': 16068096, 'steps': 31382, 'loss/train': 1.7704042196273804}
-03/05/2022 02:20:55 - INFO - codeparrot_training - Step 31383: {'lr': 0.00045292897258752095, 'samples': 16068608, 'steps': 31383, 'loss/train': 1.6985880136489868}
-03/05/2022 02:20:58 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/05/2022 02:21:00 - INFO - codeparrot_training - Step 31384: {'lr': 0.0004529258731245427, 'samples': 16069120, 'steps': 31384, 'loss/train': 1.2498353719711304}
-03/05/2022 02:21:03 - INFO - codeparrot_training - Step 31385: {'lr': 0.0004529227735701291, 'samples': 16069632, 'steps': 31385, 'loss/train': 1.8348861932754517}
-03/05/2022 02:21:06 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 02:21:08 - INFO - codeparrot_training - Step 31386: {'lr': 0.00045291967392428175, 'samples': 16070144, 'steps': 31386, 'loss/train': 1.1844439506530762}
-03/05/2022 02:21:12 - INFO - codeparrot_training - Step 31387: {'lr': 0.0004529165741870018, 'samples': 16070656, 'steps': 31387, 'loss/train': 0.6403480768203735}
-03/05/2022 02:21:14 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/05/2022 02:21:17 - INFO - codeparrot_training - Step 31388: {'lr': 0.00045291347435829087, 'samples': 16071168, 'steps': 31388, 'loss/train': 1.7669285535812378}
-03/05/2022 02:21:20 - INFO - codeparrot_training - Step 31389: {'lr': 0.0004529103744381503, 'samples': 16071680, 'steps': 31389, 'loss/train': 1.2361047267913818}
-03/05/2022 02:21:22 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 02:21:25 - INFO - codeparrot_training - Step 31390: {'lr': 0.0004529072744265813, 'samples': 16072192, 'steps': 31390, 'loss/train': 2.1734917163848877}
-03/05/2022 02:21:28 - INFO - codeparrot_training - Step 31391: {'lr': 0.00045290417432358553, 'samples': 16072704, 'steps': 31391, 'loss/train': 1.6103997230529785}
-03/05/2022 02:21:31 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/05/2022 02:21:34 - INFO - codeparrot_training - Step 31392: {'lr': 0.00045290107412916425, 'samples': 16073216, 'steps': 31392, 'loss/train': 1.0613278150558472}
-03/05/2022 02:21:37 - INFO - codeparrot_training - Step 31393: {'lr': 0.0004528979738433189, 'samples': 16073728, 'steps': 31393, 'loss/train': 1.2625161409378052}
-03/05/2022 02:21:39 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 02:21:42 - INFO - codeparrot_training - Step 31394: {'lr': 0.00045289487346605075, 'samples': 16074240, 'steps': 31394, 'loss/train': 1.0009559392929077}
-03/05/2022 02:21:45 - INFO - codeparrot_training - Step 31395: {'lr': 0.0004528917729973614, 'samples': 16074752, 'steps': 31395, 'loss/train': 1.4855663776397705}
-03/05/2022 02:21:48 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/05/2022 02:21:51 - INFO - codeparrot_training - Step 31396: {'lr': 0.00045288867243725207, 'samples': 16075264, 'steps': 31396, 'loss/train': 0.6834126710891724}
-03/05/2022 02:21:54 - INFO - codeparrot_training - Step 31397: {'lr': 0.00045288557178572433, 'samples': 16075776, 'steps': 31397, 'loss/train': 0.7422385811805725}
-03/05/2022 02:21:56 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 02:21:59 - INFO - codeparrot_training - Step 31398: {'lr': 0.00045288247104277937, 'samples': 16076288, 'steps': 31398, 'loss/train': 1.700618863105774}
-03/05/2022 02:22:02 - INFO - codeparrot_training - Step 31399: {'lr': 0.0004528793702084187, 'samples': 16076800, 'steps': 31399, 'loss/train': 2.016258716583252}
-03/05/2022 02:22:04 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/05/2022 02:22:07 - INFO - codeparrot_training - Step 31400: {'lr': 0.0004528762692826439, 'samples': 16077312, 'steps': 31400, 'loss/train': 1.2520030736923218}
-03/05/2022 02:22:11 - INFO - codeparrot_training - Step 31401: {'lr': 0.000452873168265456, 'samples': 16077824, 'steps': 31401, 'loss/train': 0.11095746606588364}
-03/05/2022 02:22:13 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/05/2022 02:22:16 - INFO - codeparrot_training - Step 31402: {'lr': 0.00045287006715685665, 'samples': 16078336, 'steps': 31402, 'loss/train': 1.6106799840927124}
-03/05/2022 02:22:19 - INFO - codeparrot_training - Step 31403: {'lr': 0.0004528669659568472, 'samples': 16078848, 'steps': 31403, 'loss/train': 1.9911088943481445}
-03/05/2022 02:22:21 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/05/2022 02:22:24 - INFO - codeparrot_training - Step 31404: {'lr': 0.00045286386466542896, 'samples': 16079360, 'steps': 31404, 'loss/train': 1.654862880706787}
-03/05/2022 02:22:28 - INFO - codeparrot_training - Step 31405: {'lr': 0.0004528607632826034, 'samples': 16079872, 'steps': 31405, 'loss/train': 1.80656898021698}
-03/05/2022 02:22:30 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/05/2022 02:22:33 - INFO - codeparrot_training - Step 31406: {'lr': 0.00045285766180837197, 'samples': 16080384, 'steps': 31406, 'loss/train': 2.141064167022705}
-03/05/2022 02:22:36 - INFO - codeparrot_training - Step 31407: {'lr': 0.000452854560242736, 'samples': 16080896, 'steps': 31407, 'loss/train': 2.1619699001312256}
-03/05/2022 02:22:39 - INFO - codeparrot_training - Step 31408: {'lr': 0.0004528514585856968, 'samples': 16081408, 'steps': 31408, 'loss/train': 0.9550679326057434}
-03/05/2022 02:22:40 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/05/2022 02:22:45 - INFO - codeparrot_training - Step 31409: {'lr': 0.0004528483568372559, 'samples': 16081920, 'steps': 31409, 'loss/train': 1.1090449094772339}
-03/05/2022 02:22:48 - INFO - codeparrot_training - Step 31410: {'lr': 0.00045284525499741474, 'samples': 16082432, 'steps': 31410, 'loss/train': 2.4411656856536865}
-03/05/2022 02:22:49 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/05/2022 02:22:53 - INFO - codeparrot_training - Step 31411: {'lr': 0.0004528421530661746, 'samples': 16082944, 'steps': 31411, 'loss/train': 1.6110491752624512}
-03/05/2022 02:22:56 - INFO - codeparrot_training - Step 31412: {'lr': 0.0004528390510435368, 'samples': 16083456, 'steps': 31412, 'loss/train': 2.5272371768951416}
-03/05/2022 02:22:57 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/05/2022 02:23:02 - INFO - codeparrot_training - Step 31413: {'lr': 0.0004528359489295031, 'samples': 16083968, 'steps': 31413, 'loss/train': 2.122628688812256}
-03/05/2022 02:23:05 - INFO - codeparrot_training - Step 31414: {'lr': 0.00045283284672407444, 'samples': 16084480, 'steps': 31414, 'loss/train': 1.2907477617263794}
-03/05/2022 02:23:05 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/05/2022 02:23:10 - INFO - codeparrot_training - Step 31415: {'lr': 0.0004528297444272525, 'samples': 16084992, 'steps': 31415, 'loss/train': 2.3552942276000977}
-03/05/2022 02:23:13 - INFO - codeparrot_training - Step 31416: {'lr': 0.0004528266420390386, 'samples': 16085504, 'steps': 31416, 'loss/train': 1.0455079078674316}
-03/05/2022 02:23:14 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 02:23:18 - INFO - codeparrot_training - Step 31417: {'lr': 0.00045282353955943417, 'samples': 16086016, 'steps': 31417, 'loss/train': 1.358640432357788}
-03/05/2022 02:23:22 - INFO - codeparrot_training - Step 31418: {'lr': 0.00045282043698844054, 'samples': 16086528, 'steps': 31418, 'loss/train': 1.064713716506958}
-03/05/2022 02:23:22 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/05/2022 02:23:27 - INFO - codeparrot_training - Step 31419: {'lr': 0.0004528173343260592, 'samples': 16087040, 'steps': 31419, 'loss/train': 1.6776224374771118}
-03/05/2022 02:23:30 - INFO - codeparrot_training - Step 31420: {'lr': 0.0004528142315722915, 'samples': 16087552, 'steps': 31420, 'loss/train': 1.3401951789855957}
-03/05/2022 02:23:30 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/05/2022 02:23:35 - INFO - codeparrot_training - Step 31421: {'lr': 0.0004528111287271388, 'samples': 16088064, 'steps': 31421, 'loss/train': 3.579611301422119}
-03/05/2022 02:23:39 - INFO - codeparrot_training - Step 31422: {'lr': 0.00045280802579060253, 'samples': 16088576, 'steps': 31422, 'loss/train': 1.321414589881897}
-03/05/2022 02:23:39 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/05/2022 02:23:44 - INFO - codeparrot_training - Step 31423: {'lr': 0.00045280492276268414, 'samples': 16089088, 'steps': 31423, 'loss/train': 1.0094287395477295}
-03/05/2022 02:23:47 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/05/2022 02:23:49 - INFO - codeparrot_training - Step 31424: {'lr': 0.0004528018196433849, 'samples': 16089600, 'steps': 31424, 'loss/train': 1.6512426137924194}
-03/05/2022 02:23:52 - INFO - codeparrot_training - Step 31425: {'lr': 0.0004527987164327063, 'samples': 16090112, 'steps': 31425, 'loss/train': 0.055026277899742126}
-03/05/2022 02:23:55 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/05/2022 02:23:57 - INFO - codeparrot_training - Step 31426: {'lr': 0.0004527956131306498, 'samples': 16090624, 'steps': 31426, 'loss/train': 2.124762773513794}
-03/05/2022 02:24:01 - INFO - codeparrot_training - Step 31427: {'lr': 0.0004527925097372168, 'samples': 16091136, 'steps': 31427, 'loss/train': 2.246474027633667}
-03/05/2022 02:24:03 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/05/2022 02:24:06 - INFO - codeparrot_training - Step 31428: {'lr': 0.0004527894062524084, 'samples': 16091648, 'steps': 31428, 'loss/train': 2.1902942657470703}
-03/05/2022 02:24:09 - INFO - codeparrot_training - Step 31429: {'lr': 0.00045278630267622637, 'samples': 16092160, 'steps': 31429, 'loss/train': 2.8574414253234863}
-03/05/2022 02:24:12 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 02:24:15 - INFO - codeparrot_training - Step 31430: {'lr': 0.0004527831990086719, 'samples': 16092672, 'steps': 31430, 'loss/train': 1.695055365562439}
-03/05/2022 02:24:18 - INFO - codeparrot_training - Step 31431: {'lr': 0.0004527800952497465, 'samples': 16093184, 'steps': 31431, 'loss/train': 5.8778486251831055}
-03/05/2022 02:24:21 - INFO - codeparrot_training - Step 31432: {'lr': 0.0004527769913994515, 'samples': 16093696, 'steps': 31432, 'loss/train': 1.026113748550415}
-03/05/2022 02:24:22 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/05/2022 02:24:26 - INFO - codeparrot_training - Step 31433: {'lr': 0.00045277388745778836, 'samples': 16094208, 'steps': 31433, 'loss/train': 2.012977123260498}
-03/05/2022 02:24:29 - INFO - codeparrot_training - Step 31434: {'lr': 0.00045277078342475835, 'samples': 16094720, 'steps': 31434, 'loss/train': 1.8157670497894287}
-03/05/2022 02:24:31 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/05/2022 02:24:35 - INFO - codeparrot_training - Step 31435: {'lr': 0.000452767679300363, 'samples': 16095232, 'steps': 31435, 'loss/train': 1.6247193813323975}
-03/05/2022 02:24:38 - INFO - codeparrot_training - Step 31436: {'lr': 0.00045276457508460367, 'samples': 16095744, 'steps': 31436, 'loss/train': 1.0068397521972656}
-03/05/2022 02:24:39 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/05/2022 02:24:43 - INFO - codeparrot_training - Step 31437: {'lr': 0.00045276147077748176, 'samples': 16096256, 'steps': 31437, 'loss/train': 2.2893378734588623}
-03/05/2022 02:24:46 - INFO - codeparrot_training - Step 31438: {'lr': 0.0004527583663789986, 'samples': 16096768, 'steps': 31438, 'loss/train': 1.5257594585418701}
-03/05/2022 02:24:47 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/05/2022 02:24:51 - INFO - codeparrot_training - Step 31439: {'lr': 0.0004527552618891557, 'samples': 16097280, 'steps': 31439, 'loss/train': 1.161664605140686}
-03/05/2022 02:24:55 - INFO - codeparrot_training - Step 31440: {'lr': 0.0004527521573079544, 'samples': 16097792, 'steps': 31440, 'loss/train': 1.1855353116989136}
-03/05/2022 02:24:55 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/05/2022 02:25:00 - INFO - codeparrot_training - Step 31441: {'lr': 0.0004527490526353961, 'samples': 16098304, 'steps': 31441, 'loss/train': 1.4499212503433228}
-03/05/2022 02:25:03 - INFO - codeparrot_training - Step 31442: {'lr': 0.0004527459478714822, 'samples': 16098816, 'steps': 31442, 'loss/train': 2.2350080013275146}
-03/05/2022 02:25:04 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/05/2022 02:25:08 - INFO - codeparrot_training - Step 31443: {'lr': 0.00045274284301621414, 'samples': 16099328, 'steps': 31443, 'loss/train': 1.9113391637802124}
-03/05/2022 02:25:11 - INFO - codeparrot_training - Step 31444: {'lr': 0.00045273973806959325, 'samples': 16099840, 'steps': 31444, 'loss/train': 1.4769452810287476}
-03/05/2022 02:25:12 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/05/2022 02:25:17 - INFO - codeparrot_training - Step 31445: {'lr': 0.00045273663303162096, 'samples': 16100352, 'steps': 31445, 'loss/train': 1.4200798273086548}
-03/05/2022 02:25:20 - INFO - codeparrot_training - Step 31446: {'lr': 0.00045273352790229873, 'samples': 16100864, 'steps': 31446, 'loss/train': 2.1596243381500244}
-03/05/2022 02:25:21 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/05/2022 02:25:25 - INFO - codeparrot_training - Step 31447: {'lr': 0.0004527304226816278, 'samples': 16101376, 'steps': 31447, 'loss/train': 1.6071414947509766}
-03/05/2022 02:25:28 - INFO - codeparrot_training - Step 31448: {'lr': 0.0004527273173696097, 'samples': 16101888, 'steps': 31448, 'loss/train': 1.4654426574707031}
-03/05/2022 02:25:29 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/05/2022 02:25:34 - INFO - codeparrot_training - Step 31449: {'lr': 0.0004527242119662458, 'samples': 16102400, 'steps': 31449, 'loss/train': 2.3628480434417725}
-03/05/2022 02:25:37 - INFO - codeparrot_training - Step 31450: {'lr': 0.00045272110647153754, 'samples': 16102912, 'steps': 31450, 'loss/train': 7.240050315856934}
-03/05/2022 02:25:38 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/05/2022 02:25:42 - INFO - codeparrot_training - Step 31451: {'lr': 0.00045271800088548625, 'samples': 16103424, 'steps': 31451, 'loss/train': 2.433006525039673}
-03/05/2022 02:25:45 - INFO - codeparrot_training - Step 31452: {'lr': 0.00045271489520809337, 'samples': 16103936, 'steps': 31452, 'loss/train': 2.3132221698760986}
-03/05/2022 02:25:47 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 02:25:50 - INFO - codeparrot_training - Step 31453: {'lr': 0.0004527117894393603, 'samples': 16104448, 'steps': 31453, 'loss/train': 1.756961703300476}
-03/05/2022 02:25:54 - INFO - codeparrot_training - Step 31454: {'lr': 0.0004527086835792884, 'samples': 16104960, 'steps': 31454, 'loss/train': 1.503247618675232}
-03/05/2022 02:25:55 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/05/2022 02:25:59 - INFO - codeparrot_training - Step 31455: {'lr': 0.0004527055776278791, 'samples': 16105472, 'steps': 31455, 'loss/train': 2.0916385650634766}
-03/05/2022 02:26:02 - INFO - codeparrot_training - Step 31456: {'lr': 0.00045270247158513377, 'samples': 16105984, 'steps': 31456, 'loss/train': 1.5416643619537354}
-03/05/2022 02:26:03 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/05/2022 02:26:07 - INFO - codeparrot_training - Step 31457: {'lr': 0.00045269936545105384, 'samples': 16106496, 'steps': 31457, 'loss/train': 1.729301929473877}
-03/05/2022 02:26:11 - INFO - codeparrot_training - Step 31458: {'lr': 0.0004526962592256407, 'samples': 16107008, 'steps': 31458, 'loss/train': 5.931805610656738}
-03/05/2022 02:26:12 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 02:26:16 - INFO - codeparrot_training - Step 31459: {'lr': 0.00045269315290889583, 'samples': 16107520, 'steps': 31459, 'loss/train': 1.5502777099609375}
-03/05/2022 02:26:19 - INFO - codeparrot_training - Step 31460: {'lr': 0.00045269004650082045, 'samples': 16108032, 'steps': 31460, 'loss/train': 2.217634916305542}
-03/05/2022 02:26:21 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/05/2022 02:26:24 - INFO - codeparrot_training - Step 31461: {'lr': 0.0004526869400014162, 'samples': 16108544, 'steps': 31461, 'loss/train': 0.8402490019798279}
-03/05/2022 02:26:27 - INFO - codeparrot_training - Step 31462: {'lr': 0.0004526838334106842, 'samples': 16109056, 'steps': 31462, 'loss/train': 1.3982808589935303}
-03/05/2022 02:26:29 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/05/2022 02:26:33 - INFO - codeparrot_training - Step 31463: {'lr': 0.000452680726728626, 'samples': 16109568, 'steps': 31463, 'loss/train': 1.1845130920410156}
-03/05/2022 02:26:36 - INFO - codeparrot_training - Step 31464: {'lr': 0.00045267761995524314, 'samples': 16110080, 'steps': 31464, 'loss/train': 1.7911897897720337}
-03/05/2022 02:26:37 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 02:26:41 - INFO - codeparrot_training - Step 31465: {'lr': 0.00045267451309053677, 'samples': 16110592, 'steps': 31465, 'loss/train': 1.4127013683319092}
-03/05/2022 02:26:44 - INFO - codeparrot_training - Step 31466: {'lr': 0.0004526714061345084, 'samples': 16111104, 'steps': 31466, 'loss/train': 1.9185951948165894}
-03/05/2022 02:26:45 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/05/2022 02:26:49 - INFO - codeparrot_training - Step 31467: {'lr': 0.0004526682990871593, 'samples': 16111616, 'steps': 31467, 'loss/train': 1.6776704788208008}
-03/05/2022 02:26:52 - INFO - codeparrot_training - Step 31468: {'lr': 0.0004526651919484912, 'samples': 16112128, 'steps': 31468, 'loss/train': 1.3298616409301758}
-03/05/2022 02:26:54 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/05/2022 02:26:58 - INFO - codeparrot_training - Step 31469: {'lr': 0.00045266208471850516, 'samples': 16112640, 'steps': 31469, 'loss/train': 1.3723582029342651}
-03/05/2022 02:27:01 - INFO - codeparrot_training - Step 31470: {'lr': 0.00045265897739720277, 'samples': 16113152, 'steps': 31470, 'loss/train': 0.07018920034170151}
-03/05/2022 02:27:03 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/05/2022 02:27:06 - INFO - codeparrot_training - Step 31471: {'lr': 0.00045265586998458534, 'samples': 16113664, 'steps': 31471, 'loss/train': 1.3505792617797852}
-03/05/2022 02:27:09 - INFO - codeparrot_training - Step 31472: {'lr': 0.00045265276248065436, 'samples': 16114176, 'steps': 31472, 'loss/train': 1.9902453422546387}
-03/05/2022 02:27:11 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/05/2022 02:27:15 - INFO - codeparrot_training - Step 31473: {'lr': 0.0004526496548854111, 'samples': 16114688, 'steps': 31473, 'loss/train': 1.7543225288391113}
-03/05/2022 02:27:18 - INFO - codeparrot_training - Step 31474: {'lr': 0.000452646547198857, 'samples': 16115200, 'steps': 31474, 'loss/train': 1.383806586265564}
-03/05/2022 02:27:19 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 02:27:23 - INFO - codeparrot_training - Step 31475: {'lr': 0.0004526434394209936, 'samples': 16115712, 'steps': 31475, 'loss/train': 1.9744014739990234}
-03/05/2022 02:27:26 - INFO - codeparrot_training - Step 31476: {'lr': 0.00045264033155182216, 'samples': 16116224, 'steps': 31476, 'loss/train': 1.5867058038711548}
-03/05/2022 02:27:27 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/05/2022 02:27:31 - INFO - codeparrot_training - Step 31477: {'lr': 0.0004526372235913441, 'samples': 16116736, 'steps': 31477, 'loss/train': 1.89089035987854}
-03/05/2022 02:27:35 - INFO - codeparrot_training - Step 31478: {'lr': 0.0004526341155395608, 'samples': 16117248, 'steps': 31478, 'loss/train': 2.182331085205078}
-03/05/2022 02:27:35 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/05/2022 02:27:40 - INFO - codeparrot_training - Step 31479: {'lr': 0.00045263100739647373, 'samples': 16117760, 'steps': 31479, 'loss/train': 1.7235870361328125}
-03/05/2022 02:27:43 - INFO - codeparrot_training - Step 31480: {'lr': 0.00045262789916208424, 'samples': 16118272, 'steps': 31480, 'loss/train': 1.7351253032684326}
-03/05/2022 02:27:43 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/05/2022 02:27:48 - INFO - codeparrot_training - Step 31481: {'lr': 0.00045262479083639376, 'samples': 16118784, 'steps': 31481, 'loss/train': 1.9240679740905762}
-03/05/2022 02:27:51 - INFO - codeparrot_training - Step 31482: {'lr': 0.0004526216824194037, 'samples': 16119296, 'steps': 31482, 'loss/train': 1.544216275215149}
-03/05/2022 02:27:52 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/05/2022 02:27:57 - INFO - codeparrot_training - Step 31483: {'lr': 0.00045261857391111536, 'samples': 16119808, 'steps': 31483, 'loss/train': 1.9310578107833862}
-03/05/2022 02:28:00 - INFO - codeparrot_training - Step 31484: {'lr': 0.0004526154653115303, 'samples': 16120320, 'steps': 31484, 'loss/train': 1.6664706468582153}
-03/05/2022 02:28:00 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/05/2022 02:28:05 - INFO - codeparrot_training - Step 31485: {'lr': 0.0004526123566206498, 'samples': 16120832, 'steps': 31485, 'loss/train': 2.1433777809143066}
-03/05/2022 02:28:08 - INFO - codeparrot_training - Step 31486: {'lr': 0.0004526092478384753, 'samples': 16121344, 'steps': 31486, 'loss/train': 1.5464683771133423}
-03/05/2022 02:28:09 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/05/2022 02:28:14 - INFO - codeparrot_training - Step 31487: {'lr': 0.00045260613896500827, 'samples': 16121856, 'steps': 31487, 'loss/train': 0.8201708793640137}
-03/05/2022 02:28:17 - INFO - codeparrot_training - Step 31488: {'lr': 0.00045260303000024994, 'samples': 16122368, 'steps': 31488, 'loss/train': 1.764509916305542}
-03/05/2022 02:28:17 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 02:28:22 - INFO - codeparrot_training - Step 31489: {'lr': 0.0004525999209442018, 'samples': 16122880, 'steps': 31489, 'loss/train': 1.4597769975662231}
-03/05/2022 02:28:25 - INFO - codeparrot_training - Step 31490: {'lr': 0.0004525968117968653, 'samples': 16123392, 'steps': 31490, 'loss/train': 1.5814138650894165}
-03/05/2022 02:28:26 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 02:28:31 - INFO - codeparrot_training - Step 31491: {'lr': 0.00045259370255824183, 'samples': 16123904, 'steps': 31491, 'loss/train': 1.0628573894500732}
-03/05/2022 02:28:34 - INFO - codeparrot_training - Step 31492: {'lr': 0.0004525905932283327, 'samples': 16124416, 'steps': 31492, 'loss/train': 1.9792927503585815}
-03/05/2022 02:28:34 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/05/2022 02:28:39 - INFO - codeparrot_training - Step 31493: {'lr': 0.00045258748380713943, 'samples': 16124928, 'steps': 31493, 'loss/train': 0.2514106035232544}
-03/05/2022 02:28:42 - INFO - codeparrot_training - Step 31494: {'lr': 0.00045258437429466337, 'samples': 16125440, 'steps': 31494, 'loss/train': 2.0028598308563232}
-03/05/2022 02:28:43 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/05/2022 02:28:48 - INFO - codeparrot_training - Step 31495: {'lr': 0.0004525812646909059, 'samples': 16125952, 'steps': 31495, 'loss/train': 1.779821515083313}
-03/05/2022 02:28:51 - INFO - codeparrot_training - Step 31496: {'lr': 0.0004525781549958684, 'samples': 16126464, 'steps': 31496, 'loss/train': 1.7870286703109741}
-03/05/2022 02:28:51 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 02:28:56 - INFO - codeparrot_training - Step 31497: {'lr': 0.0004525750452095524, 'samples': 16126976, 'steps': 31497, 'loss/train': 0.7611998915672302}
-03/05/2022 02:28:59 - INFO - codeparrot_training - Step 31498: {'lr': 0.00045257193533195916, 'samples': 16127488, 'steps': 31498, 'loss/train': 1.86409592628479}
-03/05/2022 02:29:00 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/05/2022 02:29:04 - INFO - codeparrot_training - Step 31499: {'lr': 0.0004525688253630901, 'samples': 16128000, 'steps': 31499, 'loss/train': 1.889346718788147}
-03/05/2022 02:29:08 - INFO - codeparrot_training - Step 31500: {'lr': 0.00045256571530294664, 'samples': 16128512, 'steps': 31500, 'loss/train': 1.037628412246704}
-03/05/2022 02:29:08 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/05/2022 02:29:13 - INFO - codeparrot_training - Step 31501: {'lr': 0.0004525626051515302, 'samples': 16129024, 'steps': 31501, 'loss/train': 1.702979564666748}
-03/05/2022 02:29:16 - INFO - codeparrot_training - Step 31502: {'lr': 0.0004525594949088423, 'samples': 16129536, 'steps': 31502, 'loss/train': 2.212418794631958}
-03/05/2022 02:29:16 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/05/2022 02:29:21 - INFO - codeparrot_training - Step 31503: {'lr': 0.00045255638457488415, 'samples': 16130048, 'steps': 31503, 'loss/train': 1.2664870023727417}
-03/05/2022 02:29:24 - INFO - codeparrot_training - Step 31504: {'lr': 0.0004525532741496572, 'samples': 16130560, 'steps': 31504, 'loss/train': 1.8271229267120361}
-03/05/2022 02:29:25 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/05/2022 02:29:30 - INFO - codeparrot_training - Step 31505: {'lr': 0.0004525501636331628, 'samples': 16131072, 'steps': 31505, 'loss/train': 1.6227223873138428}
-03/05/2022 02:29:33 - INFO - codeparrot_training - Step 31506: {'lr': 0.00045254705302540257, 'samples': 16131584, 'steps': 31506, 'loss/train': 1.7760080099105835}
-03/05/2022 02:29:33 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 02:29:38 - INFO - codeparrot_training - Step 31507: {'lr': 0.00045254394232637765, 'samples': 16132096, 'steps': 31507, 'loss/train': 2.1856863498687744}
-03/05/2022 02:29:41 - INFO - codeparrot_training - Step 31508: {'lr': 0.0004525408315360896, 'samples': 16132608, 'steps': 31508, 'loss/train': 1.5976295471191406}
-03/05/2022 02:29:41 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 02:29:47 - INFO - codeparrot_training - Step 31509: {'lr': 0.00045253772065453977, 'samples': 16133120, 'steps': 31509, 'loss/train': 1.5793099403381348}
-03/05/2022 02:29:50 - INFO - codeparrot_training - Step 31510: {'lr': 0.00045253460968172957, 'samples': 16133632, 'steps': 31510, 'loss/train': 2.1575217247009277}
-03/05/2022 02:29:51 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/05/2022 02:29:55 - INFO - codeparrot_training - Step 31511: {'lr': 0.0004525314986176604, 'samples': 16134144, 'steps': 31511, 'loss/train': 2.10465931892395}
-03/05/2022 02:29:58 - INFO - codeparrot_training - Step 31512: {'lr': 0.0004525283874623336, 'samples': 16134656, 'steps': 31512, 'loss/train': 0.7757741808891296}
-03/05/2022 02:29:59 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/05/2022 02:30:04 - INFO - codeparrot_training - Step 31513: {'lr': 0.00045252527621575075, 'samples': 16135168, 'steps': 31513, 'loss/train': 1.1073167324066162}
-03/05/2022 02:30:07 - INFO - codeparrot_training - Step 31514: {'lr': 0.0004525221648779131, 'samples': 16135680, 'steps': 31514, 'loss/train': 1.7409639358520508}
-03/05/2022 02:30:08 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/05/2022 02:30:12 - INFO - codeparrot_training - Step 31515: {'lr': 0.00045251905344882205, 'samples': 16136192, 'steps': 31515, 'loss/train': 1.4306128025054932}
-03/05/2022 02:30:15 - INFO - codeparrot_training - Step 31516: {'lr': 0.000452515941928479, 'samples': 16136704, 'steps': 31516, 'loss/train': 0.8161985874176025}
-03/05/2022 02:30:16 - INFO - codeparrot_training - Skipping example with length 86 (seq_length=1024)
-03/05/2022 02:30:21 - INFO - codeparrot_training - Step 31517: {'lr': 0.0004525128303168855, 'samples': 16137216, 'steps': 31517, 'loss/train': 1.7841342687606812}
-03/05/2022 02:30:24 - INFO - codeparrot_training - Step 31518: {'lr': 0.00045250971861404276, 'samples': 16137728, 'steps': 31518, 'loss/train': 1.29667067527771}
-03/05/2022 02:30:25 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/05/2022 02:30:29 - INFO - codeparrot_training - Step 31519: {'lr': 0.0004525066068199523, 'samples': 16138240, 'steps': 31519, 'loss/train': 2.8187217712402344}
-03/05/2022 02:30:32 - INFO - codeparrot_training - Step 31520: {'lr': 0.0004525034949346155, 'samples': 16138752, 'steps': 31520, 'loss/train': 0.9589388966560364}
-03/05/2022 02:30:34 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/05/2022 02:30:38 - INFO - codeparrot_training - Step 31521: {'lr': 0.0004525003829580337, 'samples': 16139264, 'steps': 31521, 'loss/train': 0.21540480852127075}
-03/05/2022 02:30:41 - INFO - codeparrot_training - Step 31522: {'lr': 0.0004524972708902084, 'samples': 16139776, 'steps': 31522, 'loss/train': 2.310816764831543}
-03/05/2022 02:30:42 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 02:30:46 - INFO - codeparrot_training - Step 31523: {'lr': 0.0004524941587311409, 'samples': 16140288, 'steps': 31523, 'loss/train': 1.138566493988037}
-03/05/2022 02:30:49 - INFO - codeparrot_training - Step 31524: {'lr': 0.0004524910464808327, 'samples': 16140800, 'steps': 31524, 'loss/train': 1.5954649448394775}
-03/05/2022 02:30:50 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/05/2022 02:30:55 - INFO - codeparrot_training - Step 31525: {'lr': 0.00045248793413928514, 'samples': 16141312, 'steps': 31525, 'loss/train': 1.9546318054199219}
-03/05/2022 02:30:58 - INFO - codeparrot_training - Step 31526: {'lr': 0.0004524848217064997, 'samples': 16141824, 'steps': 31526, 'loss/train': 1.6697877645492554}
-03/05/2022 02:30:58 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/05/2022 02:31:03 - INFO - codeparrot_training - Step 31527: {'lr': 0.0004524817091824777, 'samples': 16142336, 'steps': 31527, 'loss/train': 1.5212364196777344}
-03/05/2022 02:31:06 - INFO - codeparrot_training - Step 31528: {'lr': 0.00045247859656722056, 'samples': 16142848, 'steps': 31528, 'loss/train': 1.5788440704345703}
-03/05/2022 02:31:07 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 02:31:11 - INFO - codeparrot_training - Step 31529: {'lr': 0.0004524754838607297, 'samples': 16143360, 'steps': 31529, 'loss/train': 1.4034253358840942}
-03/05/2022 02:31:14 - INFO - codeparrot_training - Step 31530: {'lr': 0.0004524723710630064, 'samples': 16143872, 'steps': 31530, 'loss/train': 0.907260000705719}
-03/05/2022 02:31:15 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/05/2022 02:31:20 - INFO - codeparrot_training - Step 31531: {'lr': 0.0004524692581740523, 'samples': 16144384, 'steps': 31531, 'loss/train': 1.6518443822860718}
-03/05/2022 02:31:23 - INFO - codeparrot_training - Step 31532: {'lr': 0.00045246614519386865, 'samples': 16144896, 'steps': 31532, 'loss/train': 1.483202576637268}
-03/05/2022 02:31:23 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/05/2022 02:31:28 - INFO - codeparrot_training - Step 31533: {'lr': 0.0004524630321224569, 'samples': 16145408, 'steps': 31533, 'loss/train': 2.475306510925293}
-03/05/2022 02:31:31 - INFO - codeparrot_training - Step 31534: {'lr': 0.0004524599189598183, 'samples': 16145920, 'steps': 31534, 'loss/train': 1.823412537574768}
-03/05/2022 02:31:31 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/05/2022 02:31:37 - INFO - codeparrot_training - Step 31535: {'lr': 0.0004524568057059545, 'samples': 16146432, 'steps': 31535, 'loss/train': 1.9083024263381958}
-03/05/2022 02:31:40 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/05/2022 02:31:42 - INFO - codeparrot_training - Step 31536: {'lr': 0.00045245369236086673, 'samples': 16146944, 'steps': 31536, 'loss/train': 1.4512388706207275}
-03/05/2022 02:31:45 - INFO - codeparrot_training - Step 31537: {'lr': 0.00045245057892455653, 'samples': 16147456, 'steps': 31537, 'loss/train': 1.086375117301941}
-03/05/2022 02:31:48 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/05/2022 02:31:51 - INFO - codeparrot_training - Step 31538: {'lr': 0.0004524474653970252, 'samples': 16147968, 'steps': 31538, 'loss/train': 1.460856556892395}
-03/05/2022 02:31:54 - INFO - codeparrot_training - Step 31539: {'lr': 0.00045244435177827413, 'samples': 16148480, 'steps': 31539, 'loss/train': 0.9275199174880981}
-03/05/2022 02:31:56 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/05/2022 02:31:59 - INFO - codeparrot_training - Step 31540: {'lr': 0.00045244123806830486, 'samples': 16148992, 'steps': 31540, 'loss/train': 1.2342435121536255}
-03/05/2022 02:32:02 - INFO - codeparrot_training - Step 31541: {'lr': 0.00045243812426711856, 'samples': 16149504, 'steps': 31541, 'loss/train': 1.7118326425552368}
-03/05/2022 02:32:06 - INFO - codeparrot_training - Step 31542: {'lr': 0.0004524350103747168, 'samples': 16150016, 'steps': 31542, 'loss/train': 1.819670557975769}
-03/05/2022 02:32:07 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 02:32:11 - INFO - codeparrot_training - Step 31543: {'lr': 0.00045243189639110093, 'samples': 16150528, 'steps': 31543, 'loss/train': 2.029788017272949}
-03/05/2022 02:32:14 - INFO - codeparrot_training - Step 31544: {'lr': 0.00045242878231627247, 'samples': 16151040, 'steps': 31544, 'loss/train': 1.5326788425445557}
-03/05/2022 02:32:15 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/05/2022 02:32:19 - INFO - codeparrot_training - Step 31545: {'lr': 0.0004524256681502327, 'samples': 16151552, 'steps': 31545, 'loss/train': 2.779707908630371}
-03/05/2022 02:32:22 - INFO - codeparrot_training - Step 31546: {'lr': 0.0004524225538929829, 'samples': 16152064, 'steps': 31546, 'loss/train': 2.1954147815704346}
-03/05/2022 02:32:23 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/05/2022 02:32:28 - INFO - codeparrot_training - Step 31547: {'lr': 0.0004524194395445248, 'samples': 16152576, 'steps': 31547, 'loss/train': 1.8565536737442017}
-03/05/2022 02:32:31 - INFO - codeparrot_training - Step 31548: {'lr': 0.0004524163251048595, 'samples': 16153088, 'steps': 31548, 'loss/train': 1.7719902992248535}
-03/05/2022 02:32:31 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/05/2022 02:32:36 - INFO - codeparrot_training - Step 31549: {'lr': 0.0004524132105739886, 'samples': 16153600, 'steps': 31549, 'loss/train': 2.031679153442383}
-03/05/2022 02:32:39 - INFO - codeparrot_training - Step 31550: {'lr': 0.0004524100959519134, 'samples': 16154112, 'steps': 31550, 'loss/train': 2.2447915077209473}
-03/05/2022 02:32:40 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/05/2022 02:32:45 - INFO - codeparrot_training - Step 31551: {'lr': 0.00045240698123863535, 'samples': 16154624, 'steps': 31551, 'loss/train': 1.6978462934494019}
-03/05/2022 02:32:48 - INFO - codeparrot_training - Step 31552: {'lr': 0.0004524038664341558, 'samples': 16155136, 'steps': 31552, 'loss/train': 2.2094690799713135}
-03/05/2022 02:32:48 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 02:32:53 - INFO - codeparrot_training - Step 31553: {'lr': 0.00045240075153847625, 'samples': 16155648, 'steps': 31553, 'loss/train': 1.6636077165603638}
-03/05/2022 02:32:56 - INFO - codeparrot_training - Step 31554: {'lr': 0.00045239763655159805, 'samples': 16156160, 'steps': 31554, 'loss/train': 2.162144660949707}
-03/05/2022 02:32:56 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/05/2022 02:33:01 - INFO - codeparrot_training - Step 31555: {'lr': 0.00045239452147352257, 'samples': 16156672, 'steps': 31555, 'loss/train': 2.5454466342926025}
-03/05/2022 02:33:05 - INFO - codeparrot_training - Step 31556: {'lr': 0.0004523914063042512, 'samples': 16157184, 'steps': 31556, 'loss/train': 1.7178024053573608}
-03/05/2022 02:33:05 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/05/2022 02:33:10 - INFO - codeparrot_training - Step 31557: {'lr': 0.00045238829104378545, 'samples': 16157696, 'steps': 31557, 'loss/train': 1.5884954929351807}
-03/05/2022 02:33:13 - INFO - codeparrot_training - Step 31558: {'lr': 0.0004523851756921266, 'samples': 16158208, 'steps': 31558, 'loss/train': 1.2498162984848022}
-03/05/2022 02:33:13 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/05/2022 02:33:18 - INFO - codeparrot_training - Step 31559: {'lr': 0.00045238206024927614, 'samples': 16158720, 'steps': 31559, 'loss/train': 1.784096360206604}
-03/05/2022 02:33:21 - INFO - codeparrot_training - Step 31560: {'lr': 0.00045237894471523543, 'samples': 16159232, 'steps': 31560, 'loss/train': 2.0154409408569336}
-03/05/2022 02:33:22 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 02:33:27 - INFO - codeparrot_training - Step 31561: {'lr': 0.00045237582909000594, 'samples': 16159744, 'steps': 31561, 'loss/train': 1.7307534217834473}
-03/05/2022 02:33:30 - INFO - codeparrot_training - Step 31562: {'lr': 0.00045237271337358897, 'samples': 16160256, 'steps': 31562, 'loss/train': 0.08814364671707153}
-03/05/2022 02:33:30 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/05/2022 02:33:35 - INFO - codeparrot_training - Step 31563: {'lr': 0.00045236959756598605, 'samples': 16160768, 'steps': 31563, 'loss/train': 1.4843617677688599}
-03/05/2022 02:33:38 - INFO - codeparrot_training - Step 31564: {'lr': 0.0004523664816671985, 'samples': 16161280, 'steps': 31564, 'loss/train': 2.5114407539367676}
-03/05/2022 02:33:38 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/05/2022 02:33:44 - INFO - codeparrot_training - Step 31565: {'lr': 0.0004523633656772277, 'samples': 16161792, 'steps': 31565, 'loss/train': 2.127631902694702}
-03/05/2022 02:33:47 - INFO - codeparrot_training - Step 31566: {'lr': 0.00045236024959607505, 'samples': 16162304, 'steps': 31566, 'loss/train': 0.7544247508049011}
-03/05/2022 02:33:52 - INFO - codeparrot_training - Step 31567: {'lr': 0.00045235713342374207, 'samples': 16162816, 'steps': 31567, 'loss/train': 1.0428247451782227}
-03/05/2022 02:33:55 - INFO - codeparrot_training - Step 31568: {'lr': 0.00045235401716023, 'samples': 16163328, 'steps': 31568, 'loss/train': 1.611209511756897}
-03/05/2022 02:33:55 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/05/2022 02:34:01 - INFO - codeparrot_training - Step 31569: {'lr': 0.0004523509008055404, 'samples': 16163840, 'steps': 31569, 'loss/train': 1.7495619058609009}
-03/05/2022 02:34:03 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/05/2022 02:34:06 - INFO - codeparrot_training - Step 31570: {'lr': 0.0004523477843596746, 'samples': 16164352, 'steps': 31570, 'loss/train': 1.6653902530670166}
-03/05/2022 02:34:09 - INFO - codeparrot_training - Step 31571: {'lr': 0.00045234466782263403, 'samples': 16164864, 'steps': 31571, 'loss/train': 2.2409536838531494}
-03/05/2022 02:34:12 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/05/2022 02:34:14 - INFO - codeparrot_training - Step 31572: {'lr': 0.00045234155119442, 'samples': 16165376, 'steps': 31572, 'loss/train': 1.4114336967468262}
-03/05/2022 02:34:17 - INFO - codeparrot_training - Step 31573: {'lr': 0.00045233843447503407, 'samples': 16165888, 'steps': 31573, 'loss/train': 1.610561490058899}
-03/05/2022 02:34:20 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/05/2022 02:34:23 - INFO - codeparrot_training - Step 31574: {'lr': 0.00045233531766447757, 'samples': 16166400, 'steps': 31574, 'loss/train': 1.8955681324005127}
-03/05/2022 02:34:26 - INFO - codeparrot_training - Step 31575: {'lr': 0.00045233220076275186, 'samples': 16166912, 'steps': 31575, 'loss/train': 1.3955235481262207}
-03/05/2022 02:34:29 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/05/2022 02:34:31 - INFO - codeparrot_training - Step 31576: {'lr': 0.0004523290837698583, 'samples': 16167424, 'steps': 31576, 'loss/train': 1.9330998659133911}
-03/05/2022 02:34:34 - INFO - codeparrot_training - Step 31577: {'lr': 0.0004523259666857985, 'samples': 16167936, 'steps': 31577, 'loss/train': 1.482001543045044}
-03/05/2022 02:34:37 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/05/2022 02:34:40 - INFO - codeparrot_training - Step 31578: {'lr': 0.00045232284951057366, 'samples': 16168448, 'steps': 31578, 'loss/train': 1.8246978521347046}
-03/05/2022 02:34:43 - INFO - codeparrot_training - Step 31579: {'lr': 0.00045231973224418533, 'samples': 16168960, 'steps': 31579, 'loss/train': 1.6417876482009888}
-03/05/2022 02:34:45 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/05/2022 02:34:48 - INFO - codeparrot_training - Step 31580: {'lr': 0.00045231661488663485, 'samples': 16169472, 'steps': 31580, 'loss/train': 2.2487080097198486}
-03/05/2022 02:34:51 - INFO - codeparrot_training - Step 31581: {'lr': 0.0004523134974379236, 'samples': 16169984, 'steps': 31581, 'loss/train': 1.3140310049057007}
-03/05/2022 02:34:54 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/05/2022 02:34:57 - INFO - codeparrot_training - Step 31582: {'lr': 0.000452310379898053, 'samples': 16170496, 'steps': 31582, 'loss/train': 1.2727608680725098}
-03/05/2022 02:35:00 - INFO - codeparrot_training - Step 31583: {'lr': 0.00045230726226702444, 'samples': 16171008, 'steps': 31583, 'loss/train': 1.4434789419174194}
-03/05/2022 02:35:02 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 02:35:05 - INFO - codeparrot_training - Step 31584: {'lr': 0.0004523041445448394, 'samples': 16171520, 'steps': 31584, 'loss/train': 1.6618921756744385}
-03/05/2022 02:35:08 - INFO - codeparrot_training - Step 31585: {'lr': 0.00045230102673149923, 'samples': 16172032, 'steps': 31585, 'loss/train': 0.2651282548904419}
-03/05/2022 02:35:10 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/05/2022 02:35:13 - INFO - codeparrot_training - Step 31586: {'lr': 0.00045229790882700535, 'samples': 16172544, 'steps': 31586, 'loss/train': 2.008523464202881}
-03/05/2022 02:35:17 - INFO - codeparrot_training - Step 31587: {'lr': 0.00045229479083135917, 'samples': 16173056, 'steps': 31587, 'loss/train': 1.728901982307434}
-03/05/2022 02:35:18 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/05/2022 02:35:22 - INFO - codeparrot_training - Step 31588: {'lr': 0.000452291672744562, 'samples': 16173568, 'steps': 31588, 'loss/train': 1.3938950300216675}
-03/05/2022 02:35:25 - INFO - codeparrot_training - Step 31589: {'lr': 0.0004522885545666153, 'samples': 16174080, 'steps': 31589, 'loss/train': 1.6727291345596313}
-03/05/2022 02:35:27 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/05/2022 02:35:30 - INFO - codeparrot_training - Step 31590: {'lr': 0.0004522854362975206, 'samples': 16174592, 'steps': 31590, 'loss/train': 1.5963608026504517}
-03/05/2022 02:35:33 - INFO - codeparrot_training - Step 31591: {'lr': 0.00045228231793727924, 'samples': 16175104, 'steps': 31591, 'loss/train': 1.9077171087265015}
-03/05/2022 02:35:35 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/05/2022 02:35:39 - INFO - codeparrot_training - Step 31592: {'lr': 0.00045227919948589247, 'samples': 16175616, 'steps': 31592, 'loss/train': 1.5408475399017334}
-03/05/2022 02:35:42 - INFO - codeparrot_training - Step 31593: {'lr': 0.0004522760809433619, 'samples': 16176128, 'steps': 31593, 'loss/train': 0.8038286566734314}
-03/05/2022 02:35:43 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/05/2022 02:35:47 - INFO - codeparrot_training - Step 31594: {'lr': 0.0004522729623096888, 'samples': 16176640, 'steps': 31594, 'loss/train': 2.239734649658203}
-03/05/2022 02:35:50 - INFO - codeparrot_training - Step 31595: {'lr': 0.0004522698435848747, 'samples': 16177152, 'steps': 31595, 'loss/train': 1.4663687944412231}
-03/05/2022 02:35:52 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/05/2022 02:35:56 - INFO - codeparrot_training - Step 31596: {'lr': 0.0004522667247689208, 'samples': 16177664, 'steps': 31596, 'loss/train': 0.953043520450592}
-03/05/2022 02:35:59 - INFO - codeparrot_training - Step 31597: {'lr': 0.0004522636058618287, 'samples': 16178176, 'steps': 31597, 'loss/train': 3.4511659145355225}
-03/05/2022 02:36:00 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/05/2022 02:36:04 - INFO - codeparrot_training - Step 31598: {'lr': 0.0004522604868635998, 'samples': 16178688, 'steps': 31598, 'loss/train': 1.5698630809783936}
-03/05/2022 02:36:07 - INFO - codeparrot_training - Step 31599: {'lr': 0.0004522573677742353, 'samples': 16179200, 'steps': 31599, 'loss/train': 2.0832760334014893}
-03/05/2022 02:36:08 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 02:36:13 - INFO - codeparrot_training - Step 31600: {'lr': 0.0004522542485937369, 'samples': 16179712, 'steps': 31600, 'loss/train': 3.816641092300415}
-03/05/2022 02:36:16 - INFO - codeparrot_training - Step 31601: {'lr': 0.0004522511293221058, 'samples': 16180224, 'steps': 31601, 'loss/train': 1.0312228202819824}
-03/05/2022 02:36:17 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/05/2022 02:36:21 - INFO - codeparrot_training - Step 31602: {'lr': 0.00045224800995934345, 'samples': 16180736, 'steps': 31602, 'loss/train': 1.321639060974121}
-03/05/2022 02:36:24 - INFO - codeparrot_training - Step 31603: {'lr': 0.00045224489050545125, 'samples': 16181248, 'steps': 31603, 'loss/train': 1.55818510055542}
-03/05/2022 02:36:25 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/05/2022 02:36:29 - INFO - codeparrot_training - Step 31604: {'lr': 0.0004522417709604306, 'samples': 16181760, 'steps': 31604, 'loss/train': 2.2859675884246826}
-03/05/2022 02:36:32 - INFO - codeparrot_training - Step 31605: {'lr': 0.000452238651324283, 'samples': 16182272, 'steps': 31605, 'loss/train': 1.0731604099273682}
-03/05/2022 02:36:33 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/05/2022 02:36:38 - INFO - codeparrot_training - Step 31606: {'lr': 0.0004522355315970098, 'samples': 16182784, 'steps': 31606, 'loss/train': 1.0644035339355469}
-03/05/2022 02:36:41 - INFO - codeparrot_training - Step 31607: {'lr': 0.0004522324117786123, 'samples': 16183296, 'steps': 31607, 'loss/train': 1.5141433477401733}
-03/05/2022 02:36:42 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/05/2022 02:36:46 - INFO - codeparrot_training - Step 31608: {'lr': 0.0004522292918690921, 'samples': 16183808, 'steps': 31608, 'loss/train': 1.7121999263763428}
-03/05/2022 02:36:49 - INFO - codeparrot_training - Step 31609: {'lr': 0.0004522261718684504, 'samples': 16184320, 'steps': 31609, 'loss/train': 1.3490097522735596}
-03/05/2022 02:36:50 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/05/2022 02:36:55 - INFO - codeparrot_training - Step 31610: {'lr': 0.00045222305177668875, 'samples': 16184832, 'steps': 31610, 'loss/train': 1.2012062072753906}
-03/05/2022 02:36:58 - INFO - codeparrot_training - Step 31611: {'lr': 0.00045221993159380857, 'samples': 16185344, 'steps': 31611, 'loss/train': 0.3338894844055176}
-03/05/2022 02:36:58 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/05/2022 02:37:03 - INFO - codeparrot_training - Step 31612: {'lr': 0.00045221681131981116, 'samples': 16185856, 'steps': 31612, 'loss/train': 2.153427839279175}
-03/05/2022 02:37:06 - INFO - codeparrot_training - Step 31613: {'lr': 0.00045221369095469795, 'samples': 16186368, 'steps': 31613, 'loss/train': 1.3791075944900513}
-03/05/2022 02:37:07 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/05/2022 02:37:11 - INFO - codeparrot_training - Step 31614: {'lr': 0.00045221057049847044, 'samples': 16186880, 'steps': 31614, 'loss/train': 1.8150585889816284}
-03/05/2022 02:37:15 - INFO - codeparrot_training - Step 31615: {'lr': 0.0004522074499511299, 'samples': 16187392, 'steps': 31615, 'loss/train': 1.8745017051696777}
-03/05/2022 02:37:15 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/05/2022 02:37:20 - INFO - codeparrot_training - Step 31616: {'lr': 0.0004522043293126778, 'samples': 16187904, 'steps': 31616, 'loss/train': 1.9404397010803223}
-03/05/2022 02:37:23 - INFO - codeparrot_training - Step 31617: {'lr': 0.00045220120858311557, 'samples': 16188416, 'steps': 31617, 'loss/train': 1.2991234064102173}
-03/05/2022 02:37:23 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/05/2022 02:37:28 - INFO - codeparrot_training - Step 31618: {'lr': 0.0004521980877624446, 'samples': 16188928, 'steps': 31618, 'loss/train': 1.9995251893997192}
-03/05/2022 02:37:31 - INFO - codeparrot_training - Step 31619: {'lr': 0.0004521949668506663, 'samples': 16189440, 'steps': 31619, 'loss/train': 0.3885086476802826}
-03/05/2022 02:37:32 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/05/2022 02:37:37 - INFO - codeparrot_training - Step 31620: {'lr': 0.00045219184584778207, 'samples': 16189952, 'steps': 31620, 'loss/train': 2.1185600757598877}
-03/05/2022 02:37:40 - INFO - codeparrot_training - Step 31621: {'lr': 0.0004521887247537933, 'samples': 16190464, 'steps': 31621, 'loss/train': 1.615657925605774}
-03/05/2022 02:37:42 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/05/2022 02:37:45 - INFO - codeparrot_training - Step 31622: {'lr': 0.00045218560356870144, 'samples': 16190976, 'steps': 31622, 'loss/train': 0.8194131851196289}
-03/05/2022 02:37:48 - INFO - codeparrot_training - Step 31623: {'lr': 0.0004521824822925078, 'samples': 16191488, 'steps': 31623, 'loss/train': 1.7549269199371338}
-03/05/2022 02:37:50 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/05/2022 02:37:54 - INFO - codeparrot_training - Step 31624: {'lr': 0.00045217936092521396, 'samples': 16192000, 'steps': 31624, 'loss/train': 2.2579245567321777}
-03/05/2022 02:37:57 - INFO - codeparrot_training - Step 31625: {'lr': 0.00045217623946682114, 'samples': 16192512, 'steps': 31625, 'loss/train': 1.7576595544815063}
-03/05/2022 02:37:58 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/05/2022 02:38:02 - INFO - codeparrot_training - Step 31626: {'lr': 0.00045217311791733084, 'samples': 16193024, 'steps': 31626, 'loss/train': 2.0874361991882324}
-03/05/2022 02:38:05 - INFO - codeparrot_training - Step 31627: {'lr': 0.00045216999627674436, 'samples': 16193536, 'steps': 31627, 'loss/train': 1.617950201034546}
-03/05/2022 02:38:07 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 02:38:10 - INFO - codeparrot_training - Step 31628: {'lr': 0.0004521668745450633, 'samples': 16194048, 'steps': 31628, 'loss/train': 2.156216859817505}
-03/05/2022 02:38:14 - INFO - codeparrot_training - Step 31629: {'lr': 0.00045216375272228907, 'samples': 16194560, 'steps': 31629, 'loss/train': 2.022632598876953}
-03/05/2022 02:38:15 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/05/2022 02:38:19 - INFO - codeparrot_training - Step 31630: {'lr': 0.00045216063080842287, 'samples': 16195072, 'steps': 31630, 'loss/train': 1.9324945211410522}
-03/05/2022 02:38:22 - INFO - codeparrot_training - Step 31631: {'lr': 0.00045215750880346617, 'samples': 16195584, 'steps': 31631, 'loss/train': 0.046376414597034454}
-03/05/2022 02:38:24 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/05/2022 02:38:27 - INFO - codeparrot_training - Step 31632: {'lr': 0.00045215438670742045, 'samples': 16196096, 'steps': 31632, 'loss/train': 0.10948921740055084}
-03/05/2022 02:38:31 - INFO - codeparrot_training - Step 31633: {'lr': 0.00045215126452028705, 'samples': 16196608, 'steps': 31633, 'loss/train': 2.4237914085388184}
-03/05/2022 02:38:32 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/05/2022 02:38:36 - INFO - codeparrot_training - Step 31634: {'lr': 0.00045214814224206744, 'samples': 16197120, 'steps': 31634, 'loss/train': 0.959520697593689}
-03/05/2022 02:38:39 - INFO - codeparrot_training - Step 31635: {'lr': 0.00045214501987276304, 'samples': 16197632, 'steps': 31635, 'loss/train': 1.5569958686828613}
-03/05/2022 02:38:40 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/05/2022 02:38:44 - INFO - codeparrot_training - Step 31636: {'lr': 0.0004521418974123751, 'samples': 16198144, 'steps': 31636, 'loss/train': 1.9874142408370972}
-03/05/2022 02:38:47 - INFO - codeparrot_training - Step 31637: {'lr': 0.00045213877486090524, 'samples': 16198656, 'steps': 31637, 'loss/train': 0.5747865438461304}
-03/05/2022 02:38:48 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/05/2022 02:38:53 - INFO - codeparrot_training - Step 31638: {'lr': 0.00045213565221835473, 'samples': 16199168, 'steps': 31638, 'loss/train': 1.9332669973373413}
-03/05/2022 02:38:56 - INFO - codeparrot_training - Step 31639: {'lr': 0.00045213252948472505, 'samples': 16199680, 'steps': 31639, 'loss/train': 1.9183270931243896}
-03/05/2022 02:38:57 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/05/2022 02:39:01 - INFO - codeparrot_training - Step 31640: {'lr': 0.0004521294066600175, 'samples': 16200192, 'steps': 31640, 'loss/train': 1.2080668210983276}
-03/05/2022 02:39:04 - INFO - codeparrot_training - Step 31641: {'lr': 0.0004521262837442336, 'samples': 16200704, 'steps': 31641, 'loss/train': 2.2235372066497803}
-03/05/2022 02:39:05 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/05/2022 02:39:09 - INFO - codeparrot_training - Step 31642: {'lr': 0.0004521231607373747, 'samples': 16201216, 'steps': 31642, 'loss/train': 1.5852410793304443}
-03/05/2022 02:39:13 - INFO - codeparrot_training - Step 31643: {'lr': 0.00045212003763944226, 'samples': 16201728, 'steps': 31643, 'loss/train': 1.962286114692688}
-03/05/2022 02:39:13 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/05/2022 02:39:18 - INFO - codeparrot_training - Step 31644: {'lr': 0.00045211691445043765, 'samples': 16202240, 'steps': 31644, 'loss/train': 1.8435064554214478}
-03/05/2022 02:39:21 - INFO - codeparrot_training - Step 31645: {'lr': 0.0004521137911703622, 'samples': 16202752, 'steps': 31645, 'loss/train': 1.9495258331298828}
-03/05/2022 02:39:21 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/05/2022 02:39:26 - INFO - codeparrot_training - Step 31646: {'lr': 0.0004521106677992175, 'samples': 16203264, 'steps': 31646, 'loss/train': 2.007026195526123}
-03/05/2022 02:39:29 - INFO - codeparrot_training - Step 31647: {'lr': 0.0004521075443370048, 'samples': 16203776, 'steps': 31647, 'loss/train': 1.3651809692382812}
-03/05/2022 02:39:30 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/05/2022 02:39:35 - INFO - codeparrot_training - Step 31648: {'lr': 0.0004521044207837256, 'samples': 16204288, 'steps': 31648, 'loss/train': 1.7581672668457031}
-03/05/2022 02:39:38 - INFO - codeparrot_training - Step 31649: {'lr': 0.0004521012971393812, 'samples': 16204800, 'steps': 31649, 'loss/train': 1.9649947881698608}
-03/05/2022 02:39:38 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/05/2022 02:39:43 - INFO - codeparrot_training - Step 31650: {'lr': 0.0004520981734039731, 'samples': 16205312, 'steps': 31650, 'loss/train': 1.0028561353683472}
-03/05/2022 02:39:46 - INFO - codeparrot_training - Step 31651: {'lr': 0.0004520950495775027, 'samples': 16205824, 'steps': 31651, 'loss/train': 2.3872528076171875}
-03/05/2022 02:39:46 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/05/2022 02:39:52 - INFO - codeparrot_training - Step 31652: {'lr': 0.00045209192565997137, 'samples': 16206336, 'steps': 31652, 'loss/train': 2.0773656368255615}
-03/05/2022 02:39:55 - INFO - codeparrot_training - Step 31653: {'lr': 0.00045208880165138054, 'samples': 16206848, 'steps': 31653, 'loss/train': 1.9626826047897339}
-03/05/2022 02:39:55 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/05/2022 02:40:00 - INFO - codeparrot_training - Step 31654: {'lr': 0.0004520856775517316, 'samples': 16207360, 'steps': 31654, 'loss/train': 3.0475759506225586}
-03/05/2022 02:40:03 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/05/2022 02:40:05 - INFO - codeparrot_training - Step 31655: {'lr': 0.00045208255336102597, 'samples': 16207872, 'steps': 31655, 'loss/train': 2.127302646636963}
-03/05/2022 02:40:08 - INFO - codeparrot_training - Step 31656: {'lr': 0.0004520794290792651, 'samples': 16208384, 'steps': 31656, 'loss/train': 1.8837140798568726}
-03/05/2022 02:40:11 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 02:40:14 - INFO - codeparrot_training - Step 31657: {'lr': 0.0004520763047064503, 'samples': 16208896, 'steps': 31657, 'loss/train': 1.559601068496704}
-03/05/2022 02:40:17 - INFO - codeparrot_training - Step 31658: {'lr': 0.0004520731802425831, 'samples': 16209408, 'steps': 31658, 'loss/train': 1.8940517902374268}
-03/05/2022 02:40:20 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/05/2022 02:40:22 - INFO - codeparrot_training - Step 31659: {'lr': 0.0004520700556876648, 'samples': 16209920, 'steps': 31659, 'loss/train': 1.4561841487884521}
-03/05/2022 02:40:25 - INFO - codeparrot_training - Step 31660: {'lr': 0.0004520669310416969, 'samples': 16210432, 'steps': 31660, 'loss/train': 1.7505598068237305}
-03/05/2022 02:40:28 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 02:40:31 - INFO - codeparrot_training - Step 31661: {'lr': 0.0004520638063046807, 'samples': 16210944, 'steps': 31661, 'loss/train': 1.4576059579849243}
-03/05/2022 02:40:34 - INFO - codeparrot_training - Step 31662: {'lr': 0.0004520606814766177, 'samples': 16211456, 'steps': 31662, 'loss/train': 1.0030043125152588}
-03/05/2022 02:40:36 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/05/2022 02:40:39 - INFO - codeparrot_training - Step 31663: {'lr': 0.00045205755655750924, 'samples': 16211968, 'steps': 31663, 'loss/train': 1.9131088256835938}
-03/05/2022 02:40:42 - INFO - codeparrot_training - Step 31664: {'lr': 0.0004520544315473568, 'samples': 16212480, 'steps': 31664, 'loss/train': 1.380644679069519}
-03/05/2022 02:40:44 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 02:40:47 - INFO - codeparrot_training - Step 31665: {'lr': 0.00045205130644616177, 'samples': 16212992, 'steps': 31665, 'loss/train': 1.4131038188934326}
-03/05/2022 02:40:51 - INFO - codeparrot_training - Step 31666: {'lr': 0.0004520481812539255, 'samples': 16213504, 'steps': 31666, 'loss/train': 1.496529221534729}
-03/05/2022 02:40:53 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/05/2022 02:40:56 - INFO - codeparrot_training - Step 31667: {'lr': 0.00045204505597064943, 'samples': 16214016, 'steps': 31667, 'loss/train': 0.12706409394741058}
-03/05/2022 02:40:59 - INFO - codeparrot_training - Step 31668: {'lr': 0.00045204193059633505, 'samples': 16214528, 'steps': 31668, 'loss/train': 2.0271198749542236}
-03/05/2022 02:41:01 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/05/2022 02:41:04 - INFO - codeparrot_training - Step 31669: {'lr': 0.0004520388051309836, 'samples': 16215040, 'steps': 31669, 'loss/train': 2.3709213733673096}
-03/05/2022 02:41:07 - INFO - codeparrot_training - Step 31670: {'lr': 0.00045203567957459657, 'samples': 16215552, 'steps': 31670, 'loss/train': 1.4888590574264526}
-03/05/2022 02:41:09 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 02:41:13 - INFO - codeparrot_training - Step 31671: {'lr': 0.00045203255392717545, 'samples': 16216064, 'steps': 31671, 'loss/train': 2.06488037109375}
-03/05/2022 02:41:16 - INFO - codeparrot_training - Step 31672: {'lr': 0.00045202942818872157, 'samples': 16216576, 'steps': 31672, 'loss/train': 1.5083506107330322}
-03/05/2022 02:41:18 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/05/2022 02:41:21 - INFO - codeparrot_training - Step 31673: {'lr': 0.0004520263023592363, 'samples': 16217088, 'steps': 31673, 'loss/train': 1.8850589990615845}
-03/05/2022 02:41:24 - INFO - codeparrot_training - Step 31674: {'lr': 0.00045202317643872113, 'samples': 16217600, 'steps': 31674, 'loss/train': 2.0380096435546875}
-03/05/2022 02:41:26 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/05/2022 02:41:29 - INFO - codeparrot_training - Step 31675: {'lr': 0.00045202005042717743, 'samples': 16218112, 'steps': 31675, 'loss/train': 2.1981077194213867}
-03/05/2022 02:41:32 - INFO - codeparrot_training - Step 31676: {'lr': 0.0004520169243246066, 'samples': 16218624, 'steps': 31676, 'loss/train': 1.7429442405700684}
-03/05/2022 02:41:34 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/05/2022 02:41:38 - INFO - codeparrot_training - Step 31677: {'lr': 0.0004520137981310101, 'samples': 16219136, 'steps': 31677, 'loss/train': 1.3953373432159424}
-03/05/2022 02:41:41 - INFO - codeparrot_training - Step 31678: {'lr': 0.0004520106718463893, 'samples': 16219648, 'steps': 31678, 'loss/train': 1.905089259147644}
-03/05/2022 02:41:42 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/05/2022 02:41:46 - INFO - codeparrot_training - Step 31679: {'lr': 0.0004520075454707456, 'samples': 16220160, 'steps': 31679, 'loss/train': 1.4570354223251343}
-03/05/2022 02:41:49 - INFO - codeparrot_training - Step 31680: {'lr': 0.0004520044190040804, 'samples': 16220672, 'steps': 31680, 'loss/train': 1.72770357131958}
-03/05/2022 02:41:51 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 02:41:55 - INFO - codeparrot_training - Step 31681: {'lr': 0.0004520012924463951, 'samples': 16221184, 'steps': 31681, 'loss/train': 0.7951334118843079}
-03/05/2022 02:41:58 - INFO - codeparrot_training - Step 31682: {'lr': 0.0004519981657976912, 'samples': 16221696, 'steps': 31682, 'loss/train': 1.2828333377838135}
-03/05/2022 02:41:59 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/05/2022 02:42:03 - INFO - codeparrot_training - Step 31683: {'lr': 0.00045199503905797, 'samples': 16222208, 'steps': 31683, 'loss/train': 1.8788996934890747}
-03/05/2022 02:42:06 - INFO - codeparrot_training - Step 31684: {'lr': 0.0004519919122272329, 'samples': 16222720, 'steps': 31684, 'loss/train': 2.659221887588501}
-03/05/2022 02:42:07 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 02:42:11 - INFO - codeparrot_training - Step 31685: {'lr': 0.00045198878530548146, 'samples': 16223232, 'steps': 31685, 'loss/train': 2.2966699600219727}
-03/05/2022 02:42:15 - INFO - codeparrot_training - Step 31686: {'lr': 0.0004519856582927169, 'samples': 16223744, 'steps': 31686, 'loss/train': 1.558124303817749}
-03/05/2022 02:42:16 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/05/2022 02:42:20 - INFO - codeparrot_training - Step 31687: {'lr': 0.00045198253118894084, 'samples': 16224256, 'steps': 31687, 'loss/train': 2.451099157333374}
-03/05/2022 02:42:23 - INFO - codeparrot_training - Step 31688: {'lr': 0.0004519794039941545, 'samples': 16224768, 'steps': 31688, 'loss/train': 1.467653512954712}
-03/05/2022 02:42:24 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/05/2022 02:42:28 - INFO - codeparrot_training - Step 31689: {'lr': 0.0004519762767083593, 'samples': 16225280, 'steps': 31689, 'loss/train': 1.9793176651000977}
-03/05/2022 02:42:32 - INFO - codeparrot_training - Step 31690: {'lr': 0.00045197314933155677, 'samples': 16225792, 'steps': 31690, 'loss/train': 1.5835257768630981}
-03/05/2022 02:42:33 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/05/2022 02:42:37 - INFO - codeparrot_training - Step 31691: {'lr': 0.0004519700218637482, 'samples': 16226304, 'steps': 31691, 'loss/train': 1.8030756711959839}
-03/05/2022 02:42:40 - INFO - codeparrot_training - Step 31692: {'lr': 0.00045196689430493516, 'samples': 16226816, 'steps': 31692, 'loss/train': 1.190625548362732}
-03/05/2022 02:42:41 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/05/2022 02:42:45 - INFO - codeparrot_training - Step 31693: {'lr': 0.00045196376665511883, 'samples': 16227328, 'steps': 31693, 'loss/train': 0.9631977081298828}
-03/05/2022 02:42:48 - INFO - codeparrot_training - Step 31694: {'lr': 0.00045196063891430086, 'samples': 16227840, 'steps': 31694, 'loss/train': 1.2497475147247314}
-03/05/2022 02:42:50 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/05/2022 02:42:54 - INFO - codeparrot_training - Step 31695: {'lr': 0.0004519575110824825, 'samples': 16228352, 'steps': 31695, 'loss/train': 1.792426347732544}
-03/05/2022 02:42:57 - INFO - codeparrot_training - Step 31696: {'lr': 0.0004519543831596652, 'samples': 16228864, 'steps': 31696, 'loss/train': 1.5987141132354736}
-03/05/2022 02:42:58 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/05/2022 02:43:02 - INFO - codeparrot_training - Step 31697: {'lr': 0.0004519512551458503, 'samples': 16229376, 'steps': 31697, 'loss/train': 2.129547119140625}
-03/05/2022 02:43:05 - INFO - codeparrot_training - Step 31698: {'lr': 0.0004519481270410394, 'samples': 16229888, 'steps': 31698, 'loss/train': 2.1524972915649414}
-03/05/2022 02:43:06 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/05/2022 02:43:11 - INFO - codeparrot_training - Step 31699: {'lr': 0.00045194499884523376, 'samples': 16230400, 'steps': 31699, 'loss/train': 2.0305118560791016}
-03/05/2022 02:43:14 - INFO - codeparrot_training - Step 31700: {'lr': 0.0004519418705584348, 'samples': 16230912, 'steps': 31700, 'loss/train': 0.8260295391082764}
-03/05/2022 02:43:15 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/05/2022 02:43:19 - INFO - codeparrot_training - Step 31701: {'lr': 0.0004519387421806439, 'samples': 16231424, 'steps': 31701, 'loss/train': 2.1808745861053467}
-03/05/2022 02:43:22 - INFO - codeparrot_training - Step 31702: {'lr': 0.0004519356137118625, 'samples': 16231936, 'steps': 31702, 'loss/train': 1.8498154878616333}
-03/05/2022 02:43:24 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/05/2022 02:43:28 - INFO - codeparrot_training - Step 31703: {'lr': 0.00045193248515209216, 'samples': 16232448, 'steps': 31703, 'loss/train': 1.867157220840454}
-03/05/2022 02:43:31 - INFO - codeparrot_training - Step 31704: {'lr': 0.0004519293565013341, 'samples': 16232960, 'steps': 31704, 'loss/train': 1.7759273052215576}
-03/05/2022 02:43:32 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/05/2022 02:43:36 - INFO - codeparrot_training - Step 31705: {'lr': 0.0004519262277595898, 'samples': 16233472, 'steps': 31705, 'loss/train': 1.4876981973648071}
-03/05/2022 02:43:39 - INFO - codeparrot_training - Step 31706: {'lr': 0.0004519230989268606, 'samples': 16233984, 'steps': 31706, 'loss/train': 1.9603303670883179}
-03/05/2022 02:43:40 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/05/2022 02:43:45 - INFO - codeparrot_training - Step 31707: {'lr': 0.000451919970003148, 'samples': 16234496, 'steps': 31707, 'loss/train': 1.3129453659057617}
-03/05/2022 02:43:48 - INFO - codeparrot_training - Step 31708: {'lr': 0.0004519168409884534, 'samples': 16235008, 'steps': 31708, 'loss/train': 1.6527740955352783}
-03/05/2022 02:43:49 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/05/2022 02:43:53 - INFO - codeparrot_training - Step 31709: {'lr': 0.00045191371188277817, 'samples': 16235520, 'steps': 31709, 'loss/train': 1.511582851409912}
-03/05/2022 02:43:56 - INFO - codeparrot_training - Step 31710: {'lr': 0.0004519105826861237, 'samples': 16236032, 'steps': 31710, 'loss/train': 1.9950817823410034}
-03/05/2022 02:43:58 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 02:44:02 - INFO - codeparrot_training - Step 31711: {'lr': 0.0004519074533984915, 'samples': 16236544, 'steps': 31711, 'loss/train': 1.0954766273498535}
-03/05/2022 02:44:05 - INFO - codeparrot_training - Step 31712: {'lr': 0.0004519043240198829, 'samples': 16237056, 'steps': 31712, 'loss/train': 2.137829303741455}
-03/05/2022 02:44:08 - INFO - codeparrot_training - Step 31713: {'lr': 0.0004519011945502993, 'samples': 16237568, 'steps': 31713, 'loss/train': 1.3465287685394287}
-03/05/2022 02:44:08 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 02:44:14 - INFO - codeparrot_training - Step 31714: {'lr': 0.00045189806498974216, 'samples': 16238080, 'steps': 31714, 'loss/train': 1.7914372682571411}
-03/05/2022 02:44:17 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/05/2022 02:44:19 - INFO - codeparrot_training - Step 31715: {'lr': 0.00045189493533821285, 'samples': 16238592, 'steps': 31715, 'loss/train': 1.8237380981445312}
-03/05/2022 02:44:22 - INFO - codeparrot_training - Step 31716: {'lr': 0.0004518918055957128, 'samples': 16239104, 'steps': 31716, 'loss/train': 2.1610751152038574}
-03/05/2022 02:44:25 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/05/2022 02:44:27 - INFO - codeparrot_training - Step 31717: {'lr': 0.0004518886757622435, 'samples': 16239616, 'steps': 31717, 'loss/train': 1.9940295219421387}
-03/05/2022 02:44:31 - INFO - codeparrot_training - Step 31718: {'lr': 0.0004518855458378062, 'samples': 16240128, 'steps': 31718, 'loss/train': 1.4362796545028687}
-03/05/2022 02:44:33 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/05/2022 02:44:36 - INFO - codeparrot_training - Step 31719: {'lr': 0.0004518824158224023, 'samples': 16240640, 'steps': 31719, 'loss/train': 1.6215218305587769}
-03/05/2022 02:44:39 - INFO - codeparrot_training - Step 31720: {'lr': 0.00045187928571603343, 'samples': 16241152, 'steps': 31720, 'loss/train': 1.430087924003601}
-03/05/2022 02:44:41 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/05/2022 02:44:44 - INFO - codeparrot_training - Step 31721: {'lr': 0.0004518761555187008, 'samples': 16241664, 'steps': 31721, 'loss/train': 2.02836012840271}
-03/05/2022 02:44:47 - INFO - codeparrot_training - Step 31722: {'lr': 0.00045187302523040597, 'samples': 16242176, 'steps': 31722, 'loss/train': 1.0167558193206787}
-03/05/2022 02:44:50 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/05/2022 02:44:53 - INFO - codeparrot_training - Step 31723: {'lr': 0.00045186989485115014, 'samples': 16242688, 'steps': 31723, 'loss/train': 1.7651481628417969}
-03/05/2022 02:44:56 - INFO - codeparrot_training - Step 31724: {'lr': 0.000451866764380935, 'samples': 16243200, 'steps': 31724, 'loss/train': 0.2187340259552002}
-03/05/2022 02:44:58 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/05/2022 02:45:01 - INFO - codeparrot_training - Step 31725: {'lr': 0.0004518636338197617, 'samples': 16243712, 'steps': 31725, 'loss/train': 1.924948811531067}
-03/05/2022 02:45:04 - INFO - codeparrot_training - Step 31726: {'lr': 0.00045186050316763186, 'samples': 16244224, 'steps': 31726, 'loss/train': 1.245557188987732}
-03/05/2022 02:45:06 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/05/2022 02:45:10 - INFO - codeparrot_training - Step 31727: {'lr': 0.0004518573724245467, 'samples': 16244736, 'steps': 31727, 'loss/train': 1.7461291551589966}
-03/05/2022 02:45:13 - INFO - codeparrot_training - Step 31728: {'lr': 0.00045185424159050776, 'samples': 16245248, 'steps': 31728, 'loss/train': 2.007668972015381}
-03/05/2022 02:45:15 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/05/2022 02:45:18 - INFO - codeparrot_training - Step 31729: {'lr': 0.00045185111066551643, 'samples': 16245760, 'steps': 31729, 'loss/train': 1.9318382740020752}
-03/05/2022 02:45:21 - INFO - codeparrot_training - Step 31730: {'lr': 0.0004518479796495741, 'samples': 16246272, 'steps': 31730, 'loss/train': 4.010793209075928}
-03/05/2022 02:45:23 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/05/2022 02:45:27 - INFO - codeparrot_training - Step 31731: {'lr': 0.00045184484854268216, 'samples': 16246784, 'steps': 31731, 'loss/train': 1.8899635076522827}
-03/05/2022 02:45:30 - INFO - codeparrot_training - Step 31732: {'lr': 0.00045184171734484203, 'samples': 16247296, 'steps': 31732, 'loss/train': 1.649454116821289}
-03/05/2022 02:45:33 - INFO - codeparrot_training - Step 31733: {'lr': 0.00045183858605605517, 'samples': 16247808, 'steps': 31733, 'loss/train': 2.162670135498047}
-03/05/2022 02:45:33 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/05/2022 02:45:39 - INFO - codeparrot_training - Step 31734: {'lr': 0.00045183545467632295, 'samples': 16248320, 'steps': 31734, 'loss/train': 1.5207518339157104}
-03/05/2022 02:45:42 - INFO - codeparrot_training - Step 31735: {'lr': 0.0004518323232056468, 'samples': 16248832, 'steps': 31735, 'loss/train': 1.4781872034072876}
-03/05/2022 02:45:47 - INFO - codeparrot_training - Step 31736: {'lr': 0.0004518291916440281, 'samples': 16249344, 'steps': 31736, 'loss/train': 1.7404606342315674}
-03/05/2022 02:45:50 - INFO - codeparrot_training - Step 31737: {'lr': 0.0004518260599914683, 'samples': 16249856, 'steps': 31737, 'loss/train': 2.054672956466675}
-03/05/2022 02:45:50 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/05/2022 02:45:55 - INFO - codeparrot_training - Step 31738: {'lr': 0.0004518229282479688, 'samples': 16250368, 'steps': 31738, 'loss/train': 1.5744974613189697}
-03/05/2022 02:45:58 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/05/2022 02:46:01 - INFO - codeparrot_training - Step 31739: {'lr': 0.000451819796413531, 'samples': 16250880, 'steps': 31739, 'loss/train': 1.680079460144043}
-03/05/2022 02:46:04 - INFO - codeparrot_training - Step 31740: {'lr': 0.0004518166644881563, 'samples': 16251392, 'steps': 31740, 'loss/train': 1.8072750568389893}
-03/05/2022 02:46:07 - INFO - codeparrot_training - Step 31741: {'lr': 0.0004518135324718461, 'samples': 16251904, 'steps': 31741, 'loss/train': 1.5976402759552002}
-03/05/2022 02:46:07 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/05/2022 02:46:13 - INFO - codeparrot_training - Step 31742: {'lr': 0.00045181040036460185, 'samples': 16252416, 'steps': 31742, 'loss/train': 2.039569854736328}
-03/05/2022 02:46:16 - INFO - codeparrot_training - Step 31743: {'lr': 0.0004518072681664249, 'samples': 16252928, 'steps': 31743, 'loss/train': 1.698258638381958}
-03/05/2022 02:46:16 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/05/2022 02:46:21 - INFO - codeparrot_training - Step 31744: {'lr': 0.0004518041358773168, 'samples': 16253440, 'steps': 31744, 'loss/train': 1.7008917331695557}
-03/05/2022 02:46:24 - INFO - codeparrot_training - Step 31745: {'lr': 0.0004518010034972788, 'samples': 16253952, 'steps': 31745, 'loss/train': 1.7665826082229614}
-03/05/2022 02:46:24 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/05/2022 02:46:30 - INFO - codeparrot_training - Step 31746: {'lr': 0.0004517978710263124, 'samples': 16254464, 'steps': 31746, 'loss/train': 1.3124279975891113}
-03/05/2022 02:46:33 - INFO - codeparrot_training - Step 31747: {'lr': 0.0004517947384644191, 'samples': 16254976, 'steps': 31747, 'loss/train': 1.766959309577942}
-03/05/2022 02:46:33 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/05/2022 02:46:38 - INFO - codeparrot_training - Step 31748: {'lr': 0.00045179160581160005, 'samples': 16255488, 'steps': 31748, 'loss/train': 1.5297390222549438}
-03/05/2022 02:46:41 - INFO - codeparrot_training - Step 31749: {'lr': 0.0004517884730678569, 'samples': 16256000, 'steps': 31749, 'loss/train': 2.06141996383667}
-03/05/2022 02:46:41 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/05/2022 02:46:46 - INFO - codeparrot_training - Step 31750: {'lr': 0.00045178534023319097, 'samples': 16256512, 'steps': 31750, 'loss/train': 1.2325838804244995}
-03/05/2022 02:46:49 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/05/2022 02:46:52 - INFO - codeparrot_training - Step 31751: {'lr': 0.00045178220730760367, 'samples': 16257024, 'steps': 31751, 'loss/train': 1.4560389518737793}
-03/05/2022 02:46:55 - INFO - codeparrot_training - Step 31752: {'lr': 0.0004517790742910964, 'samples': 16257536, 'steps': 31752, 'loss/train': 1.7231682538986206}
-03/05/2022 02:46:58 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/05/2022 02:47:00 - INFO - codeparrot_training - Step 31753: {'lr': 0.0004517759411836706, 'samples': 16258048, 'steps': 31753, 'loss/train': 2.8942039012908936}
-03/05/2022 02:47:03 - INFO - codeparrot_training - Step 31754: {'lr': 0.0004517728079853277, 'samples': 16258560, 'steps': 31754, 'loss/train': 0.2740870714187622}
-03/05/2022 02:47:06 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/05/2022 02:47:09 - INFO - codeparrot_training - Step 31755: {'lr': 0.0004517696746960691, 'samples': 16259072, 'steps': 31755, 'loss/train': 2.1802561283111572}
-03/05/2022 02:47:12 - INFO - codeparrot_training - Step 31756: {'lr': 0.00045176654131589617, 'samples': 16259584, 'steps': 31756, 'loss/train': 1.7064852714538574}
-03/05/2022 02:47:15 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/05/2022 02:47:17 - INFO - codeparrot_training - Step 31757: {'lr': 0.0004517634078448103, 'samples': 16260096, 'steps': 31757, 'loss/train': 1.633244514465332}
-03/05/2022 02:47:20 - INFO - codeparrot_training - Step 31758: {'lr': 0.0004517602742828131, 'samples': 16260608, 'steps': 31758, 'loss/train': 1.0179920196533203}
-03/05/2022 02:47:23 - INFO - codeparrot_training - Skipping example with length 462 (seq_length=1024)
-03/05/2022 02:47:25 - INFO - codeparrot_training - Step 31759: {'lr': 0.0004517571406299057, 'samples': 16261120, 'steps': 31759, 'loss/train': 0.5536475777626038}
-03/05/2022 02:47:29 - INFO - codeparrot_training - Step 31760: {'lr': 0.0004517540068860897, 'samples': 16261632, 'steps': 31760, 'loss/train': 1.843300461769104}
-03/05/2022 02:47:31 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/05/2022 02:47:34 - INFO - codeparrot_training - Step 31761: {'lr': 0.0004517508730513664, 'samples': 16262144, 'steps': 31761, 'loss/train': 1.1719732284545898}
-03/05/2022 02:47:37 - INFO - codeparrot_training - Step 31762: {'lr': 0.00045174773912573735, 'samples': 16262656, 'steps': 31762, 'loss/train': 1.827906847000122}
-03/05/2022 02:47:40 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/05/2022 02:47:42 - INFO - codeparrot_training - Step 31763: {'lr': 0.00045174460510920386, 'samples': 16263168, 'steps': 31763, 'loss/train': 2.518206834793091}
-03/05/2022 02:47:45 - INFO - codeparrot_training - Step 31764: {'lr': 0.00045174147100176734, 'samples': 16263680, 'steps': 31764, 'loss/train': 1.5004510879516602}
-03/05/2022 02:47:48 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/05/2022 02:47:51 - INFO - codeparrot_training - Step 31765: {'lr': 0.00045173833680342925, 'samples': 16264192, 'steps': 31765, 'loss/train': 1.0793771743774414}
-03/05/2022 02:47:54 - INFO - codeparrot_training - Step 31766: {'lr': 0.00045173520251419095, 'samples': 16264704, 'steps': 31766, 'loss/train': 1.4264402389526367}
-03/05/2022 02:47:56 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/05/2022 02:47:59 - INFO - codeparrot_training - Step 31767: {'lr': 0.0004517320681340539, 'samples': 16265216, 'steps': 31767, 'loss/train': 1.2054189443588257}
-03/05/2022 02:48:03 - INFO - codeparrot_training - Step 31768: {'lr': 0.0004517289336630195, 'samples': 16265728, 'steps': 31768, 'loss/train': 1.71027410030365}
-03/05/2022 02:48:05 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/05/2022 02:48:08 - INFO - codeparrot_training - Step 31769: {'lr': 0.0004517257991010891, 'samples': 16266240, 'steps': 31769, 'loss/train': 1.573933720588684}
-03/05/2022 02:48:11 - INFO - codeparrot_training - Step 31770: {'lr': 0.0004517226644482642, 'samples': 16266752, 'steps': 31770, 'loss/train': 2.0494937896728516}
-03/05/2022 02:48:14 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 02:48:16 - INFO - codeparrot_training - Step 31771: {'lr': 0.00045171952970454623, 'samples': 16267264, 'steps': 31771, 'loss/train': 2.298218250274658}
-03/05/2022 02:48:20 - INFO - codeparrot_training - Step 31772: {'lr': 0.0004517163948699365, 'samples': 16267776, 'steps': 31772, 'loss/train': 0.05792680382728577}
-03/05/2022 02:48:22 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/05/2022 02:48:25 - INFO - codeparrot_training - Step 31773: {'lr': 0.00045171325994443644, 'samples': 16268288, 'steps': 31773, 'loss/train': 1.6810221672058105}
-03/05/2022 02:48:28 - INFO - codeparrot_training - Step 31774: {'lr': 0.00045171012492804753, 'samples': 16268800, 'steps': 31774, 'loss/train': 1.402950644493103}
-03/05/2022 02:48:30 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/05/2022 02:48:33 - INFO - codeparrot_training - Step 31775: {'lr': 0.0004517069898207712, 'samples': 16269312, 'steps': 31775, 'loss/train': 1.2547709941864014}
-03/05/2022 02:48:36 - INFO - codeparrot_training - Step 31776: {'lr': 0.00045170385462260876, 'samples': 16269824, 'steps': 31776, 'loss/train': 1.9468953609466553}
-03/05/2022 02:48:39 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/05/2022 02:48:42 - INFO - codeparrot_training - Step 31777: {'lr': 0.0004517007193335617, 'samples': 16270336, 'steps': 31777, 'loss/train': 1.9092763662338257}
-03/05/2022 02:48:45 - INFO - codeparrot_training - Step 31778: {'lr': 0.0004516975839536314, 'samples': 16270848, 'steps': 31778, 'loss/train': 1.630836844444275}
-03/05/2022 02:48:47 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/05/2022 02:48:50 - INFO - codeparrot_training - Step 31779: {'lr': 0.0004516944484828193, 'samples': 16271360, 'steps': 31779, 'loss/train': 0.8185743093490601}
-03/05/2022 02:48:53 - INFO - codeparrot_training - Step 31780: {'lr': 0.0004516913129211268, 'samples': 16271872, 'steps': 31780, 'loss/train': 1.7097927331924438}
-03/05/2022 02:48:55 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/05/2022 02:48:59 - INFO - codeparrot_training - Step 31781: {'lr': 0.00045168817726855525, 'samples': 16272384, 'steps': 31781, 'loss/train': 1.8957138061523438}
-03/05/2022 02:49:02 - INFO - codeparrot_training - Step 31782: {'lr': 0.0004516850415251061, 'samples': 16272896, 'steps': 31782, 'loss/train': 1.4866905212402344}
-03/05/2022 02:49:03 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/05/2022 02:49:07 - INFO - codeparrot_training - Step 31783: {'lr': 0.0004516819056907809, 'samples': 16273408, 'steps': 31783, 'loss/train': 2.675497531890869}
-03/05/2022 02:49:10 - INFO - codeparrot_training - Step 31784: {'lr': 0.0004516787697655809, 'samples': 16273920, 'steps': 31784, 'loss/train': 1.717115044593811}
-03/05/2022 02:49:12 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/05/2022 02:49:16 - INFO - codeparrot_training - Step 31785: {'lr': 0.0004516756337495075, 'samples': 16274432, 'steps': 31785, 'loss/train': 2.263826847076416}
-03/05/2022 02:49:19 - INFO - codeparrot_training - Step 31786: {'lr': 0.0004516724976425622, 'samples': 16274944, 'steps': 31786, 'loss/train': 1.6937733888626099}
-03/05/2022 02:49:21 - INFO - codeparrot_training - Skipping example with length 1004 (seq_length=1024)
-03/05/2022 02:49:24 - INFO - codeparrot_training - Step 31787: {'lr': 0.0004516693614447464, 'samples': 16275456, 'steps': 31787, 'loss/train': 2.688793420791626}
-03/05/2022 02:49:27 - INFO - codeparrot_training - Step 31788: {'lr': 0.0004516662251560615, 'samples': 16275968, 'steps': 31788, 'loss/train': 1.3521760702133179}
-03/05/2022 02:49:30 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/05/2022 02:49:32 - INFO - codeparrot_training - Step 31789: {'lr': 0.0004516630887765089, 'samples': 16276480, 'steps': 31789, 'loss/train': 2.153630018234253}
-03/05/2022 02:49:35 - INFO - codeparrot_training - Step 31790: {'lr': 0.00045165995230609003, 'samples': 16276992, 'steps': 31790, 'loss/train': 1.2454617023468018}
-03/05/2022 02:49:38 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/05/2022 02:49:41 - INFO - codeparrot_training - Step 31791: {'lr': 0.0004516568157448063, 'samples': 16277504, 'steps': 31791, 'loss/train': 1.1172261238098145}
-03/05/2022 02:49:44 - INFO - codeparrot_training - Step 31792: {'lr': 0.00045165367909265916, 'samples': 16278016, 'steps': 31792, 'loss/train': 0.7798632979393005}
-03/05/2022 02:49:47 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/05/2022 02:49:49 - INFO - codeparrot_training - Step 31793: {'lr': 0.00045165054234964984, 'samples': 16278528, 'steps': 31793, 'loss/train': 2.2542359828948975}
-03/05/2022 02:49:53 - INFO - codeparrot_training - Step 31794: {'lr': 0.0004516474055157801, 'samples': 16279040, 'steps': 31794, 'loss/train': 1.832531213760376}
-03/05/2022 02:49:55 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/05/2022 02:49:58 - INFO - codeparrot_training - Step 31795: {'lr': 0.000451644268591051, 'samples': 16279552, 'steps': 31795, 'loss/train': 1.1278120279312134}
-03/05/2022 02:50:01 - INFO - codeparrot_training - Step 31796: {'lr': 0.00045164113157546414, 'samples': 16280064, 'steps': 31796, 'loss/train': 1.618048071861267}
-03/05/2022 02:50:04 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/05/2022 02:50:06 - INFO - codeparrot_training - Step 31797: {'lr': 0.0004516379944690209, 'samples': 16280576, 'steps': 31797, 'loss/train': 1.7062360048294067}
-03/05/2022 02:50:09 - INFO - codeparrot_training - Step 31798: {'lr': 0.0004516348572717227, 'samples': 16281088, 'steps': 31798, 'loss/train': 1.5274795293807983}
-03/05/2022 02:50:12 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/05/2022 02:50:15 - INFO - codeparrot_training - Step 31799: {'lr': 0.000451631719983571, 'samples': 16281600, 'steps': 31799, 'loss/train': 1.377568006515503}
-03/05/2022 02:50:18 - INFO - codeparrot_training - Step 31800: {'lr': 0.00045162858260456705, 'samples': 16282112, 'steps': 31800, 'loss/train': 1.6362025737762451}
-03/05/2022 02:50:20 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/05/2022 02:50:23 - INFO - codeparrot_training - Step 31801: {'lr': 0.0004516254451347125, 'samples': 16282624, 'steps': 31801, 'loss/train': 1.8461443185806274}
-03/05/2022 02:50:26 - INFO - codeparrot_training - Step 31802: {'lr': 0.0004516223075740085, 'samples': 16283136, 'steps': 31802, 'loss/train': 0.619382917881012}
-03/05/2022 02:50:29 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/05/2022 02:50:32 - INFO - codeparrot_training - Step 31803: {'lr': 0.00045161916992245664, 'samples': 16283648, 'steps': 31803, 'loss/train': 0.8664124608039856}
-03/05/2022 02:50:35 - INFO - codeparrot_training - Step 31804: {'lr': 0.0004516160321800584, 'samples': 16284160, 'steps': 31804, 'loss/train': 0.5236685872077942}
-03/05/2022 02:50:37 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/05/2022 02:50:40 - INFO - codeparrot_training - Step 31805: {'lr': 0.000451612894346815, 'samples': 16284672, 'steps': 31805, 'loss/train': 1.8693708181381226}
-03/05/2022 02:50:43 - INFO - codeparrot_training - Step 31806: {'lr': 0.00045160975642272795, 'samples': 16285184, 'steps': 31806, 'loss/train': 1.828359603881836}
-03/05/2022 02:50:46 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/05/2022 02:50:49 - INFO - codeparrot_training - Step 31807: {'lr': 0.0004516066184077986, 'samples': 16285696, 'steps': 31807, 'loss/train': 0.054384298622608185}
-03/05/2022 02:50:52 - INFO - codeparrot_training - Step 31808: {'lr': 0.0004516034803020285, 'samples': 16286208, 'steps': 31808, 'loss/train': 1.6048599481582642}
-03/05/2022 02:50:55 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/05/2022 02:50:57 - INFO - codeparrot_training - Step 31809: {'lr': 0.0004516003421054189, 'samples': 16286720, 'steps': 31809, 'loss/train': 1.9228047132492065}
-03/05/2022 02:51:01 - INFO - codeparrot_training - Step 31810: {'lr': 0.0004515972038179714, 'samples': 16287232, 'steps': 31810, 'loss/train': 1.960437297821045}
-03/05/2022 02:51:03 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 02:51:06 - INFO - codeparrot_training - Step 31811: {'lr': 0.0004515940654396872, 'samples': 16287744, 'steps': 31811, 'loss/train': 1.6252107620239258}
-03/05/2022 02:51:09 - INFO - codeparrot_training - Step 31812: {'lr': 0.00045159092697056794, 'samples': 16288256, 'steps': 31812, 'loss/train': 1.6809409856796265}
-03/05/2022 02:51:11 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/05/2022 02:51:14 - INFO - codeparrot_training - Step 31813: {'lr': 0.00045158778841061483, 'samples': 16288768, 'steps': 31813, 'loss/train': 1.8418540954589844}
-03/05/2022 02:51:18 - INFO - codeparrot_training - Step 31814: {'lr': 0.0004515846497598294, 'samples': 16289280, 'steps': 31814, 'loss/train': 1.7240734100341797}
-03/05/2022 02:51:20 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/05/2022 02:51:23 - INFO - codeparrot_training - Step 31815: {'lr': 0.000451581511018213, 'samples': 16289792, 'steps': 31815, 'loss/train': 1.0928095579147339}
-03/05/2022 02:51:26 - INFO - codeparrot_training - Step 31816: {'lr': 0.00045157837218576713, 'samples': 16290304, 'steps': 31816, 'loss/train': 1.6573946475982666}
-03/05/2022 02:51:28 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/05/2022 02:51:31 - INFO - codeparrot_training - Step 31817: {'lr': 0.00045157523326249316, 'samples': 16290816, 'steps': 31817, 'loss/train': 1.8898624181747437}
-03/05/2022 02:51:35 - INFO - codeparrot_training - Step 31818: {'lr': 0.00045157209424839253, 'samples': 16291328, 'steps': 31818, 'loss/train': 1.8430675268173218}
-03/05/2022 02:51:37 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/05/2022 02:51:40 - INFO - codeparrot_training - Step 31819: {'lr': 0.0004515689551434665, 'samples': 16291840, 'steps': 31819, 'loss/train': 1.8320001363754272}
-03/05/2022 02:51:43 - INFO - codeparrot_training - Step 31820: {'lr': 0.00045156581594771675, 'samples': 16292352, 'steps': 31820, 'loss/train': 2.5847766399383545}
-03/05/2022 02:51:45 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/05/2022 02:51:48 - INFO - codeparrot_training - Step 31821: {'lr': 0.00045156267666114446, 'samples': 16292864, 'steps': 31821, 'loss/train': 1.9770170450210571}
-03/05/2022 02:51:51 - INFO - codeparrot_training - Step 31822: {'lr': 0.0004515595372837512, 'samples': 16293376, 'steps': 31822, 'loss/train': 1.488275408744812}
-03/05/2022 02:51:53 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/05/2022 02:51:57 - INFO - codeparrot_training - Step 31823: {'lr': 0.00045155639781553825, 'samples': 16293888, 'steps': 31823, 'loss/train': 1.2861467599868774}
-03/05/2022 02:52:00 - INFO - codeparrot_training - Step 31824: {'lr': 0.00045155325825650715, 'samples': 16294400, 'steps': 31824, 'loss/train': 1.4563275575637817}
-03/05/2022 02:52:02 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/05/2022 02:52:06 - INFO - codeparrot_training - Step 31825: {'lr': 0.00045155011860665927, 'samples': 16294912, 'steps': 31825, 'loss/train': 2.0736804008483887}
-03/05/2022 02:52:09 - INFO - codeparrot_training - Step 31826: {'lr': 0.00045154697886599606, 'samples': 16295424, 'steps': 31826, 'loss/train': 1.8365153074264526}
-03/05/2022 02:52:12 - INFO - codeparrot_training - Step 31827: {'lr': 0.0004515438390345188, 'samples': 16295936, 'steps': 31827, 'loss/train': 0.157594695687294}
-03/05/2022 02:52:12 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/05/2022 02:52:17 - INFO - codeparrot_training - Step 31828: {'lr': 0.00045154069911222905, 'samples': 16296448, 'steps': 31828, 'loss/train': 1.3065181970596313}
-03/05/2022 02:52:20 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/05/2022 02:52:23 - INFO - codeparrot_training - Step 31829: {'lr': 0.0004515375590991281, 'samples': 16296960, 'steps': 31829, 'loss/train': 2.2466864585876465}
-03/05/2022 02:52:26 - INFO - codeparrot_training - Step 31830: {'lr': 0.0004515344189952175, 'samples': 16297472, 'steps': 31830, 'loss/train': 2.1473350524902344}
-03/05/2022 02:52:29 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/05/2022 02:52:31 - INFO - codeparrot_training - Step 31831: {'lr': 0.0004515312788004986, 'samples': 16297984, 'steps': 31831, 'loss/train': 1.6698858737945557}
-03/05/2022 02:52:34 - INFO - codeparrot_training - Step 31832: {'lr': 0.00045152813851497274, 'samples': 16298496, 'steps': 31832, 'loss/train': 0.07000356167554855}
-03/05/2022 02:52:37 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/05/2022 02:52:40 - INFO - codeparrot_training - Step 31833: {'lr': 0.0004515249981386416, 'samples': 16299008, 'steps': 31833, 'loss/train': 1.4705886840820312}
-03/05/2022 02:52:43 - INFO - codeparrot_training - Step 31834: {'lr': 0.0004515218576715062, 'samples': 16299520, 'steps': 31834, 'loss/train': 1.3666563034057617}
-03/05/2022 02:52:45 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/05/2022 02:52:48 - INFO - codeparrot_training - Step 31835: {'lr': 0.00045151871711356827, 'samples': 16300032, 'steps': 31835, 'loss/train': 1.2498530149459839}
-03/05/2022 02:52:51 - INFO - codeparrot_training - Step 31836: {'lr': 0.0004515155764648291, 'samples': 16300544, 'steps': 31836, 'loss/train': 1.845923662185669}
-03/05/2022 02:52:53 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/05/2022 02:52:57 - INFO - codeparrot_training - Step 31837: {'lr': 0.0004515124357252901, 'samples': 16301056, 'steps': 31837, 'loss/train': 1.0130943059921265}
-03/05/2022 02:53:00 - INFO - codeparrot_training - Step 31838: {'lr': 0.0004515092948949527, 'samples': 16301568, 'steps': 31838, 'loss/train': 1.9048171043395996}
-03/05/2022 02:53:02 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/05/2022 02:53:05 - INFO - codeparrot_training - Step 31839: {'lr': 0.00045150615397381835, 'samples': 16302080, 'steps': 31839, 'loss/train': 1.3387864828109741}
-03/05/2022 02:53:08 - INFO - codeparrot_training - Step 31840: {'lr': 0.0004515030129618884, 'samples': 16302592, 'steps': 31840, 'loss/train': 1.932776689529419}
-03/05/2022 02:53:11 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/05/2022 02:53:14 - INFO - codeparrot_training - Step 31841: {'lr': 0.0004514998718591643, 'samples': 16303104, 'steps': 31841, 'loss/train': 1.77843177318573}
-03/05/2022 02:53:17 - INFO - codeparrot_training - Step 31842: {'lr': 0.0004514967306656475, 'samples': 16303616, 'steps': 31842, 'loss/train': 1.7404714822769165}
-03/05/2022 02:53:19 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/05/2022 02:53:22 - INFO - codeparrot_training - Step 31843: {'lr': 0.0004514935893813394, 'samples': 16304128, 'steps': 31843, 'loss/train': 1.1077680587768555}
-03/05/2022 02:53:26 - INFO - codeparrot_training - Step 31844: {'lr': 0.00045149044800624135, 'samples': 16304640, 'steps': 31844, 'loss/train': 1.3739569187164307}
-03/05/2022 02:53:28 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/05/2022 02:53:31 - INFO - codeparrot_training - Step 31845: {'lr': 0.0004514873065403549, 'samples': 16305152, 'steps': 31845, 'loss/train': 1.5432828664779663}
-03/05/2022 02:53:34 - INFO - codeparrot_training - Step 31846: {'lr': 0.0004514841649836813, 'samples': 16305664, 'steps': 31846, 'loss/train': 1.8257838487625122}
-03/05/2022 02:53:37 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 02:53:39 - INFO - codeparrot_training - Step 31847: {'lr': 0.000451481023336222, 'samples': 16306176, 'steps': 31847, 'loss/train': 1.4391939640045166}
-03/05/2022 02:53:43 - INFO - codeparrot_training - Step 31848: {'lr': 0.0004514778815979785, 'samples': 16306688, 'steps': 31848, 'loss/train': 2.4059624671936035}
-03/05/2022 02:53:45 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/05/2022 02:53:48 - INFO - codeparrot_training - Step 31849: {'lr': 0.0004514747397689522, 'samples': 16307200, 'steps': 31849, 'loss/train': 1.5942658185958862}
-03/05/2022 02:53:51 - INFO - codeparrot_training - Step 31850: {'lr': 0.0004514715978491445, 'samples': 16307712, 'steps': 31850, 'loss/train': 1.565090298652649}
-03/05/2022 02:53:53 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/05/2022 02:53:56 - INFO - codeparrot_training - Step 31851: {'lr': 0.0004514684558385568, 'samples': 16308224, 'steps': 31851, 'loss/train': 1.8012075424194336}
-03/05/2022 02:53:59 - INFO - codeparrot_training - Step 31852: {'lr': 0.0004514653137371905, 'samples': 16308736, 'steps': 31852, 'loss/train': 1.3229076862335205}
-03/05/2022 02:54:02 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/05/2022 02:54:05 - INFO - codeparrot_training - Step 31853: {'lr': 0.000451462171545047, 'samples': 16309248, 'steps': 31853, 'loss/train': 1.7128969430923462}
-03/05/2022 02:54:08 - INFO - codeparrot_training - Step 31854: {'lr': 0.00045145902926212785, 'samples': 16309760, 'steps': 31854, 'loss/train': 1.7368899583816528}
-03/05/2022 02:54:10 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/05/2022 02:54:13 - INFO - codeparrot_training - Step 31855: {'lr': 0.0004514558868884343, 'samples': 16310272, 'steps': 31855, 'loss/train': 1.469285249710083}
-03/05/2022 02:54:16 - INFO - codeparrot_training - Step 31856: {'lr': 0.00045145274442396786, 'samples': 16310784, 'steps': 31856, 'loss/train': 1.583849310874939}
-03/05/2022 02:54:19 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/05/2022 02:54:21 - INFO - codeparrot_training - Step 31857: {'lr': 0.00045144960186872996, 'samples': 16311296, 'steps': 31857, 'loss/train': 0.09570786356925964}
-03/05/2022 02:54:25 - INFO - codeparrot_training - Step 31858: {'lr': 0.0004514464592227219, 'samples': 16311808, 'steps': 31858, 'loss/train': 1.2518233060836792}
-03/05/2022 02:54:27 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/05/2022 02:54:30 - INFO - codeparrot_training - Step 31859: {'lr': 0.0004514433164859453, 'samples': 16312320, 'steps': 31859, 'loss/train': 0.09363142400979996}
-03/05/2022 02:54:33 - INFO - codeparrot_training - Step 31860: {'lr': 0.0004514401736584013, 'samples': 16312832, 'steps': 31860, 'loss/train': 2.0139875411987305}
-03/05/2022 02:54:35 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/05/2022 02:54:39 - INFO - codeparrot_training - Step 31861: {'lr': 0.0004514370307400916, 'samples': 16313344, 'steps': 31861, 'loss/train': 2.1147162914276123}
-03/05/2022 02:54:42 - INFO - codeparrot_training - Step 31862: {'lr': 0.00045143388773101733, 'samples': 16313856, 'steps': 31862, 'loss/train': 1.9519046545028687}
-03/05/2022 02:54:44 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/05/2022 02:54:47 - INFO - codeparrot_training - Step 31863: {'lr': 0.0004514307446311802, 'samples': 16314368, 'steps': 31863, 'loss/train': 2.2852942943573}
-03/05/2022 02:54:50 - INFO - codeparrot_training - Step 31864: {'lr': 0.0004514276014405814, 'samples': 16314880, 'steps': 31864, 'loss/train': 2.569105863571167}
-03/05/2022 02:54:52 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/05/2022 02:54:56 - INFO - codeparrot_training - Step 31865: {'lr': 0.00045142445815922244, 'samples': 16315392, 'steps': 31865, 'loss/train': 1.76587975025177}
-03/05/2022 02:54:59 - INFO - codeparrot_training - Step 31866: {'lr': 0.0004514213147871047, 'samples': 16315904, 'steps': 31866, 'loss/train': 0.7369840145111084}
-03/05/2022 02:55:00 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/05/2022 02:55:04 - INFO - codeparrot_training - Step 31867: {'lr': 0.00045141817132422974, 'samples': 16316416, 'steps': 31867, 'loss/train': 1.6868627071380615}
-03/05/2022 02:55:07 - INFO - codeparrot_training - Step 31868: {'lr': 0.0004514150277705988, 'samples': 16316928, 'steps': 31868, 'loss/train': 1.293117642402649}
-03/05/2022 02:55:09 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/05/2022 02:55:12 - INFO - codeparrot_training - Step 31869: {'lr': 0.0004514118841262133, 'samples': 16317440, 'steps': 31869, 'loss/train': 1.6722594499588013}
-03/05/2022 02:55:15 - INFO - codeparrot_training - Step 31870: {'lr': 0.0004514087403910748, 'samples': 16317952, 'steps': 31870, 'loss/train': 0.3640415370464325}
-03/05/2022 02:55:17 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/05/2022 02:55:21 - INFO - codeparrot_training - Step 31871: {'lr': 0.00045140559656518456, 'samples': 16318464, 'steps': 31871, 'loss/train': 1.4758586883544922}
-03/05/2022 02:55:24 - INFO - codeparrot_training - Step 31872: {'lr': 0.0004514024526485441, 'samples': 16318976, 'steps': 31872, 'loss/train': 1.2275573015213013}
-03/05/2022 02:55:25 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/05/2022 02:55:29 - INFO - codeparrot_training - Step 31873: {'lr': 0.0004513993086411548, 'samples': 16319488, 'steps': 31873, 'loss/train': 1.9309337139129639}
-03/05/2022 02:55:32 - INFO - codeparrot_training - Step 31874: {'lr': 0.00045139616454301806, 'samples': 16320000, 'steps': 31874, 'loss/train': 0.6806849241256714}
-03/05/2022 02:55:34 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/05/2022 02:55:38 - INFO - codeparrot_training - Step 31875: {'lr': 0.00045139302035413534, 'samples': 16320512, 'steps': 31875, 'loss/train': 1.2036634683609009}
-03/05/2022 02:55:41 - INFO - codeparrot_training - Step 31876: {'lr': 0.00045138987607450803, 'samples': 16321024, 'steps': 31876, 'loss/train': 1.948067307472229}
-03/05/2022 02:55:42 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/05/2022 02:55:46 - INFO - codeparrot_training - Step 31877: {'lr': 0.00045138673170413756, 'samples': 16321536, 'steps': 31877, 'loss/train': 2.4430065155029297}
-03/05/2022 02:55:49 - INFO - codeparrot_training - Step 31878: {'lr': 0.0004513835872430253, 'samples': 16322048, 'steps': 31878, 'loss/train': 0.8089848160743713}
-03/05/2022 02:55:51 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 02:55:55 - INFO - codeparrot_training - Step 31879: {'lr': 0.0004513804426911727, 'samples': 16322560, 'steps': 31879, 'loss/train': 1.3781253099441528}
-03/05/2022 02:55:58 - INFO - codeparrot_training - Step 31880: {'lr': 0.00045137729804858124, 'samples': 16323072, 'steps': 31880, 'loss/train': 1.7367064952850342}
-03/05/2022 02:55:59 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 02:56:03 - INFO - codeparrot_training - Step 31881: {'lr': 0.00045137415331525225, 'samples': 16323584, 'steps': 31881, 'loss/train': 1.9250236749649048}
-03/05/2022 02:56:06 - INFO - codeparrot_training - Step 31882: {'lr': 0.0004513710084911872, 'samples': 16324096, 'steps': 31882, 'loss/train': 1.8302488327026367}
-03/05/2022 02:56:08 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/05/2022 02:56:12 - INFO - codeparrot_training - Step 31883: {'lr': 0.00045136786357638736, 'samples': 16324608, 'steps': 31883, 'loss/train': 2.6210012435913086}
-03/05/2022 02:56:15 - INFO - codeparrot_training - Step 31884: {'lr': 0.00045136471857085435, 'samples': 16325120, 'steps': 31884, 'loss/train': 0.5416684746742249}
-03/05/2022 02:56:16 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/05/2022 02:56:20 - INFO - codeparrot_training - Step 31885: {'lr': 0.0004513615734745895, 'samples': 16325632, 'steps': 31885, 'loss/train': 1.5893045663833618}
-03/05/2022 02:56:23 - INFO - codeparrot_training - Step 31886: {'lr': 0.00045135842828759426, 'samples': 16326144, 'steps': 31886, 'loss/train': 1.335083246231079}
-03/05/2022 02:56:26 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/05/2022 02:56:29 - INFO - codeparrot_training - Step 31887: {'lr': 0.00045135528300987006, 'samples': 16326656, 'steps': 31887, 'loss/train': 0.7847394347190857}
-03/05/2022 02:56:32 - INFO - codeparrot_training - Step 31888: {'lr': 0.00045135213764141814, 'samples': 16327168, 'steps': 31888, 'loss/train': 1.9699671268463135}
-03/05/2022 02:56:35 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 02:56:37 - INFO - codeparrot_training - Step 31889: {'lr': 0.00045134899218224014, 'samples': 16327680, 'steps': 31889, 'loss/train': 2.086529016494751}
-03/05/2022 02:56:40 - INFO - codeparrot_training - Step 31890: {'lr': 0.0004513458466323374, 'samples': 16328192, 'steps': 31890, 'loss/train': 1.7125701904296875}
-03/05/2022 02:56:43 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/05/2022 02:56:46 - INFO - codeparrot_training - Step 31891: {'lr': 0.0004513427009917113, 'samples': 16328704, 'steps': 31891, 'loss/train': 2.791313886642456}
-03/05/2022 02:56:49 - INFO - codeparrot_training - Step 31892: {'lr': 0.0004513395552603633, 'samples': 16329216, 'steps': 31892, 'loss/train': 2.0405433177948}
-03/05/2022 02:56:51 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 02:56:54 - INFO - codeparrot_training - Step 31893: {'lr': 0.0004513364094382948, 'samples': 16329728, 'steps': 31893, 'loss/train': 1.044501543045044}
-03/05/2022 02:56:57 - INFO - codeparrot_training - Step 31894: {'lr': 0.00045133326352550724, 'samples': 16330240, 'steps': 31894, 'loss/train': 0.7635440826416016}
-03/05/2022 02:57:00 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/05/2022 02:57:03 - INFO - codeparrot_training - Step 31895: {'lr': 0.000451330117522002, 'samples': 16330752, 'steps': 31895, 'loss/train': 2.0208373069763184}
-03/05/2022 02:57:06 - INFO - codeparrot_training - Step 31896: {'lr': 0.00045132697142778044, 'samples': 16331264, 'steps': 31896, 'loss/train': 1.7065905332565308}
-03/05/2022 02:57:08 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 02:57:11 - INFO - codeparrot_training - Step 31897: {'lr': 0.0004513238252428442, 'samples': 16331776, 'steps': 31897, 'loss/train': 1.441049337387085}
-03/05/2022 02:57:14 - INFO - codeparrot_training - Step 31898: {'lr': 0.0004513206789671945, 'samples': 16332288, 'steps': 31898, 'loss/train': 0.9508504867553711}
-03/05/2022 02:57:17 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 02:57:19 - INFO - codeparrot_training - Step 31899: {'lr': 0.00045131753260083276, 'samples': 16332800, 'steps': 31899, 'loss/train': 1.6174496412277222}
-03/05/2022 02:57:23 - INFO - codeparrot_training - Step 31900: {'lr': 0.0004513143861437605, 'samples': 16333312, 'steps': 31900, 'loss/train': 2.327481508255005}
-03/05/2022 02:57:25 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/05/2022 02:57:28 - INFO - codeparrot_training - Step 31901: {'lr': 0.00045131123959597905, 'samples': 16333824, 'steps': 31901, 'loss/train': 1.7458815574645996}
-03/05/2022 02:57:31 - INFO - codeparrot_training - Step 31902: {'lr': 0.0004513080929574899, 'samples': 16334336, 'steps': 31902, 'loss/train': 1.8604228496551514}
-03/05/2022 02:57:34 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 02:57:36 - INFO - codeparrot_training - Step 31903: {'lr': 0.0004513049462282943, 'samples': 16334848, 'steps': 31903, 'loss/train': 0.8403961062431335}
-03/05/2022 02:57:39 - INFO - codeparrot_training - Step 31904: {'lr': 0.00045130179940839395, 'samples': 16335360, 'steps': 31904, 'loss/train': 1.2440351247787476}
-03/05/2022 02:57:42 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 02:57:45 - INFO - codeparrot_training - Step 31905: {'lr': 0.00045129865249779, 'samples': 16335872, 'steps': 31905, 'loss/train': 1.4054588079452515}
-03/05/2022 02:57:48 - INFO - codeparrot_training - Step 31906: {'lr': 0.0004512955054964841, 'samples': 16336384, 'steps': 31906, 'loss/train': 0.8889415860176086}
-03/05/2022 02:57:51 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/05/2022 02:57:53 - INFO - codeparrot_training - Step 31907: {'lr': 0.0004512923584044775, 'samples': 16336896, 'steps': 31907, 'loss/train': 1.014445185661316}
-03/05/2022 02:57:56 - INFO - codeparrot_training - Step 31908: {'lr': 0.0004512892112217717, 'samples': 16337408, 'steps': 31908, 'loss/train': 1.7877353429794312}
-03/05/2022 02:57:59 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/05/2022 02:58:02 - INFO - codeparrot_training - Step 31909: {'lr': 0.00045128606394836805, 'samples': 16337920, 'steps': 31909, 'loss/train': 1.9404898881912231}
-03/05/2022 02:58:05 - INFO - codeparrot_training - Step 31910: {'lr': 0.00045128291658426796, 'samples': 16338432, 'steps': 31910, 'loss/train': 0.6479689478874207}
-03/05/2022 02:58:08 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/05/2022 02:58:10 - INFO - codeparrot_training - Step 31911: {'lr': 0.00045127976912947296, 'samples': 16338944, 'steps': 31911, 'loss/train': 0.15872105956077576}
-03/05/2022 02:58:14 - INFO - codeparrot_training - Step 31912: {'lr': 0.00045127662158398434, 'samples': 16339456, 'steps': 31912, 'loss/train': 2.273942470550537}
-03/05/2022 02:58:16 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 02:58:19 - INFO - codeparrot_training - Step 31913: {'lr': 0.00045127347394780367, 'samples': 16339968, 'steps': 31913, 'loss/train': 2.3919310569763184}
-03/05/2022 02:58:22 - INFO - codeparrot_training - Step 31914: {'lr': 0.00045127032622093225, 'samples': 16340480, 'steps': 31914, 'loss/train': 1.34188973903656}
-03/05/2022 02:58:25 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 02:58:27 - INFO - codeparrot_training - Step 31915: {'lr': 0.0004512671784033715, 'samples': 16340992, 'steps': 31915, 'loss/train': 1.8171836137771606}
-03/05/2022 02:58:30 - INFO - codeparrot_training - Step 31916: {'lr': 0.00045126403049512286, 'samples': 16341504, 'steps': 31916, 'loss/train': 1.0759696960449219}
-03/05/2022 02:58:33 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 02:58:36 - INFO - codeparrot_training - Step 31917: {'lr': 0.0004512608824961878, 'samples': 16342016, 'steps': 31917, 'loss/train': 1.2252100706100464}
-03/05/2022 02:58:39 - INFO - codeparrot_training - Step 31918: {'lr': 0.00045125773440656756, 'samples': 16342528, 'steps': 31918, 'loss/train': 1.8207192420959473}
-03/05/2022 02:58:41 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/05/2022 02:58:44 - INFO - codeparrot_training - Step 31919: {'lr': 0.0004512545862262638, 'samples': 16343040, 'steps': 31919, 'loss/train': 1.904942512512207}
-03/05/2022 02:58:47 - INFO - codeparrot_training - Step 31920: {'lr': 0.0004512514379552779, 'samples': 16343552, 'steps': 31920, 'loss/train': 1.6376686096191406}
-03/05/2022 02:58:50 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/05/2022 02:58:52 - INFO - codeparrot_training - Step 31921: {'lr': 0.0004512482895936111, 'samples': 16344064, 'steps': 31921, 'loss/train': 1.5099483728408813}
-03/05/2022 02:58:56 - INFO - codeparrot_training - Step 31922: {'lr': 0.00045124514114126493, 'samples': 16344576, 'steps': 31922, 'loss/train': 2.0737662315368652}
-03/05/2022 02:58:58 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/05/2022 02:59:01 - INFO - codeparrot_training - Step 31923: {'lr': 0.0004512419925982408, 'samples': 16345088, 'steps': 31923, 'loss/train': 1.7070953845977783}
-03/05/2022 02:59:04 - INFO - codeparrot_training - Step 31924: {'lr': 0.0004512388439645402, 'samples': 16345600, 'steps': 31924, 'loss/train': 2.2826290130615234}
-03/05/2022 02:59:06 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/05/2022 02:59:09 - INFO - codeparrot_training - Step 31925: {'lr': 0.00045123569524016446, 'samples': 16346112, 'steps': 31925, 'loss/train': 1.769502878189087}
-03/05/2022 02:59:12 - INFO - codeparrot_training - Step 31926: {'lr': 0.00045123254642511504, 'samples': 16346624, 'steps': 31926, 'loss/train': 1.940051555633545}
-03/05/2022 02:59:15 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/05/2022 02:59:18 - INFO - codeparrot_training - Step 31927: {'lr': 0.0004512293975193933, 'samples': 16347136, 'steps': 31927, 'loss/train': 0.769180417060852}
-03/05/2022 02:59:21 - INFO - codeparrot_training - Step 31928: {'lr': 0.0004512262485230007, 'samples': 16347648, 'steps': 31928, 'loss/train': 2.6771113872528076}
-03/05/2022 02:59:23 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 02:59:26 - INFO - codeparrot_training - Step 31929: {'lr': 0.00045122309943593865, 'samples': 16348160, 'steps': 31929, 'loss/train': 2.009106159210205}
-03/05/2022 02:59:29 - INFO - codeparrot_training - Step 31930: {'lr': 0.0004512199502582086, 'samples': 16348672, 'steps': 31930, 'loss/train': 0.8217947483062744}
-03/05/2022 02:59:31 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/05/2022 02:59:34 - INFO - codeparrot_training - Step 31931: {'lr': 0.00045121680098981186, 'samples': 16349184, 'steps': 31931, 'loss/train': 0.3093494176864624}
-03/05/2022 02:59:38 - INFO - codeparrot_training - Step 31932: {'lr': 0.00045121365163075007, 'samples': 16349696, 'steps': 31932, 'loss/train': 0.16149555146694183}
-03/05/2022 02:59:40 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/05/2022 02:59:43 - INFO - codeparrot_training - Step 31933: {'lr': 0.0004512105021810244, 'samples': 16350208, 'steps': 31933, 'loss/train': 0.8143050670623779}
-03/05/2022 02:59:46 - INFO - codeparrot_training - Step 31934: {'lr': 0.0004512073526406365, 'samples': 16350720, 'steps': 31934, 'loss/train': 1.5129972696304321}
-03/05/2022 02:59:48 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/05/2022 02:59:51 - INFO - codeparrot_training - Step 31935: {'lr': 0.0004512042030095876, 'samples': 16351232, 'steps': 31935, 'loss/train': 1.7157049179077148}
-03/05/2022 02:59:55 - INFO - codeparrot_training - Step 31936: {'lr': 0.0004512010532878792, 'samples': 16351744, 'steps': 31936, 'loss/train': 1.8498201370239258}
-03/05/2022 02:59:56 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/05/2022 03:00:00 - INFO - codeparrot_training - Step 31937: {'lr': 0.0004511979034755127, 'samples': 16352256, 'steps': 31937, 'loss/train': 1.2360297441482544}
-03/05/2022 03:00:03 - INFO - codeparrot_training - Step 31938: {'lr': 0.0004511947535724895, 'samples': 16352768, 'steps': 31938, 'loss/train': 1.9999516010284424}
-03/05/2022 03:00:05 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/05/2022 03:00:08 - INFO - codeparrot_training - Step 31939: {'lr': 0.00045119160357881105, 'samples': 16353280, 'steps': 31939, 'loss/train': 1.838710904121399}
-03/05/2022 03:00:11 - INFO - codeparrot_training - Step 31940: {'lr': 0.0004511884534944789, 'samples': 16353792, 'steps': 31940, 'loss/train': 1.921875}
-03/05/2022 03:00:13 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 03:00:17 - INFO - codeparrot_training - Step 31941: {'lr': 0.0004511853033194942, 'samples': 16354304, 'steps': 31941, 'loss/train': 1.2046767473220825}
-03/05/2022 03:00:20 - INFO - codeparrot_training - Step 31942: {'lr': 0.00045118215305385855, 'samples': 16354816, 'steps': 31942, 'loss/train': 2.4072768688201904}
-03/05/2022 03:00:21 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 03:00:25 - INFO - codeparrot_training - Step 31943: {'lr': 0.0004511790026975733, 'samples': 16355328, 'steps': 31943, 'loss/train': 1.9124397039413452}
-03/05/2022 03:00:28 - INFO - codeparrot_training - Step 31944: {'lr': 0.00045117585225063996, 'samples': 16355840, 'steps': 31944, 'loss/train': 1.20439612865448}
-03/05/2022 03:00:30 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/05/2022 03:00:34 - INFO - codeparrot_training - Step 31945: {'lr': 0.0004511727017130598, 'samples': 16356352, 'steps': 31945, 'loss/train': 2.1158857345581055}
-03/05/2022 03:00:37 - INFO - codeparrot_training - Step 31946: {'lr': 0.00045116955108483436, 'samples': 16356864, 'steps': 31946, 'loss/train': 1.375718355178833}
-03/05/2022 03:00:38 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 03:00:42 - INFO - codeparrot_training - Step 31947: {'lr': 0.00045116640036596507, 'samples': 16357376, 'steps': 31947, 'loss/train': 1.270947813987732}
-03/05/2022 03:00:45 - INFO - codeparrot_training - Step 31948: {'lr': 0.0004511632495564533, 'samples': 16357888, 'steps': 31948, 'loss/train': 1.7259471416473389}
-03/05/2022 03:00:47 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/05/2022 03:00:51 - INFO - codeparrot_training - Step 31949: {'lr': 0.00045116009865630034, 'samples': 16358400, 'steps': 31949, 'loss/train': 1.0533421039581299}
-03/05/2022 03:00:54 - INFO - codeparrot_training - Step 31950: {'lr': 0.0004511569476655079, 'samples': 16358912, 'steps': 31950, 'loss/train': 1.9342403411865234}
-03/05/2022 03:00:56 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 03:00:59 - INFO - codeparrot_training - Step 31951: {'lr': 0.00045115379658407717, 'samples': 16359424, 'steps': 31951, 'loss/train': 1.0411666631698608}
-03/05/2022 03:01:02 - INFO - codeparrot_training - Step 31952: {'lr': 0.0004511506454120097, 'samples': 16359936, 'steps': 31952, 'loss/train': 2.016972064971924}
-03/05/2022 03:01:04 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/05/2022 03:01:08 - INFO - codeparrot_training - Step 31953: {'lr': 0.00045114749414930676, 'samples': 16360448, 'steps': 31953, 'loss/train': 1.6155586242675781}
-03/05/2022 03:01:11 - INFO - codeparrot_training - Step 31954: {'lr': 0.00045114434279596994, 'samples': 16360960, 'steps': 31954, 'loss/train': 2.150050640106201}
-03/05/2022 03:01:14 - INFO - codeparrot_training - Step 31955: {'lr': 0.0004511411913520006, 'samples': 16361472, 'steps': 31955, 'loss/train': 1.2652933597564697}
-03/05/2022 03:01:15 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/05/2022 03:01:20 - INFO - codeparrot_training - Step 31956: {'lr': 0.0004511380398174001, 'samples': 16361984, 'steps': 31956, 'loss/train': 2.127192735671997}
-03/05/2022 03:01:23 - INFO - codeparrot_training - Step 31957: {'lr': 0.00045113488819216983, 'samples': 16362496, 'steps': 31957, 'loss/train': 1.540175199508667}
-03/05/2022 03:01:24 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/05/2022 03:01:28 - INFO - codeparrot_training - Step 31958: {'lr': 0.00045113173647631143, 'samples': 16363008, 'steps': 31958, 'loss/train': 1.9785131216049194}
-03/05/2022 03:01:31 - INFO - codeparrot_training - Step 31959: {'lr': 0.0004511285846698261, 'samples': 16363520, 'steps': 31959, 'loss/train': 3.0094780921936035}
-03/05/2022 03:01:32 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/05/2022 03:01:37 - INFO - codeparrot_training - Step 31960: {'lr': 0.0004511254327727153, 'samples': 16364032, 'steps': 31960, 'loss/train': 2.643731117248535}
-03/05/2022 03:01:40 - INFO - codeparrot_training - Step 31961: {'lr': 0.00045112228078498053, 'samples': 16364544, 'steps': 31961, 'loss/train': 1.668400764465332}
-03/05/2022 03:01:41 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/05/2022 03:01:45 - INFO - codeparrot_training - Step 31962: {'lr': 0.0004511191287066232, 'samples': 16365056, 'steps': 31962, 'loss/train': 1.620114803314209}
-03/05/2022 03:01:48 - INFO - codeparrot_training - Step 31963: {'lr': 0.00045111597653764456, 'samples': 16365568, 'steps': 31963, 'loss/train': 2.171884298324585}
-03/05/2022 03:01:49 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 03:01:54 - INFO - codeparrot_training - Step 31964: {'lr': 0.00045111282427804636, 'samples': 16366080, 'steps': 31964, 'loss/train': 2.3800129890441895}
-03/05/2022 03:01:57 - INFO - codeparrot_training - Step 31965: {'lr': 0.0004511096719278297, 'samples': 16366592, 'steps': 31965, 'loss/train': 1.117672324180603}
-03/05/2022 03:01:58 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/05/2022 03:02:02 - INFO - codeparrot_training - Step 31966: {'lr': 0.0004511065194869961, 'samples': 16367104, 'steps': 31966, 'loss/train': 1.6424318552017212}
-03/05/2022 03:02:05 - INFO - codeparrot_training - Step 31967: {'lr': 0.00045110336695554707, 'samples': 16367616, 'steps': 31967, 'loss/train': 2.04544997215271}
-03/05/2022 03:02:06 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/05/2022 03:02:11 - INFO - codeparrot_training - Step 31968: {'lr': 0.0004511002143334839, 'samples': 16368128, 'steps': 31968, 'loss/train': 1.5337709188461304}
-03/05/2022 03:02:14 - INFO - codeparrot_training - Step 31969: {'lr': 0.0004510970616208081, 'samples': 16368640, 'steps': 31969, 'loss/train': 1.6760246753692627}
-03/05/2022 03:02:14 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/05/2022 03:02:19 - INFO - codeparrot_training - Step 31970: {'lr': 0.0004510939088175211, 'samples': 16369152, 'steps': 31970, 'loss/train': 1.6577661037445068}
-03/05/2022 03:02:22 - INFO - codeparrot_training - Step 31971: {'lr': 0.00045109075592362433, 'samples': 16369664, 'steps': 31971, 'loss/train': 1.203108549118042}
-03/05/2022 03:02:22 - INFO - codeparrot_training - Skipping example with length 463 (seq_length=1024)
-03/05/2022 03:02:27 - INFO - codeparrot_training - Step 31972: {'lr': 0.0004510876029391191, 'samples': 16370176, 'steps': 31972, 'loss/train': 1.574049472808838}
-03/05/2022 03:02:31 - INFO - codeparrot_training - Step 31973: {'lr': 0.00045108444986400687, 'samples': 16370688, 'steps': 31973, 'loss/train': 2.646047592163086}
-03/05/2022 03:02:31 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/05/2022 03:02:36 - INFO - codeparrot_training - Step 31974: {'lr': 0.0004510812966982892, 'samples': 16371200, 'steps': 31974, 'loss/train': 0.47657230496406555}
-03/05/2022 03:02:39 - INFO - codeparrot_training - Step 31975: {'lr': 0.0004510781434419673, 'samples': 16371712, 'steps': 31975, 'loss/train': 0.2866252362728119}
-03/05/2022 03:02:40 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/05/2022 03:02:45 - INFO - codeparrot_training - Step 31976: {'lr': 0.0004510749900950427, 'samples': 16372224, 'steps': 31976, 'loss/train': 1.8011785745620728}
-03/05/2022 03:02:48 - INFO - codeparrot_training - Step 31977: {'lr': 0.00045107183665751686, 'samples': 16372736, 'steps': 31977, 'loss/train': 1.935043454170227}
-03/05/2022 03:02:48 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/05/2022 03:02:53 - INFO - codeparrot_training - Step 31978: {'lr': 0.00045106868312939116, 'samples': 16373248, 'steps': 31978, 'loss/train': 1.5222426652908325}
-03/05/2022 03:02:56 - INFO - codeparrot_training - Step 31979: {'lr': 0.0004510655295106669, 'samples': 16373760, 'steps': 31979, 'loss/train': 2.7634658813476562}
-03/05/2022 03:02:56 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 03:03:02 - INFO - codeparrot_training - Step 31980: {'lr': 0.00045106237580134573, 'samples': 16374272, 'steps': 31980, 'loss/train': 3.5076136589050293}
-03/05/2022 03:03:05 - INFO - codeparrot_training - Step 31981: {'lr': 0.000451059222001429, 'samples': 16374784, 'steps': 31981, 'loss/train': 0.8543733954429626}
-03/05/2022 03:03:05 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/05/2022 03:03:10 - INFO - codeparrot_training - Step 31982: {'lr': 0.0004510560681109179, 'samples': 16375296, 'steps': 31982, 'loss/train': 2.0498600006103516}
-03/05/2022 03:03:13 - INFO - codeparrot_training - Step 31983: {'lr': 0.0004510529141298142, 'samples': 16375808, 'steps': 31983, 'loss/train': 1.1351772546768188}
-03/05/2022 03:03:13 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/05/2022 03:03:18 - INFO - codeparrot_training - Step 31984: {'lr': 0.00045104976005811917, 'samples': 16376320, 'steps': 31984, 'loss/train': 2.2497880458831787}
-03/05/2022 03:03:21 - INFO - codeparrot_training - Step 31985: {'lr': 0.00045104660589583413, 'samples': 16376832, 'steps': 31985, 'loss/train': 1.893570899963379}
-03/05/2022 03:03:22 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/05/2022 03:03:27 - INFO - codeparrot_training - Step 31986: {'lr': 0.0004510434516429606, 'samples': 16377344, 'steps': 31986, 'loss/train': 1.8835066556930542}
-03/05/2022 03:03:30 - INFO - codeparrot_training - Step 31987: {'lr': 0.0004510402972995, 'samples': 16377856, 'steps': 31987, 'loss/train': 2.057553768157959}
-03/05/2022 03:03:30 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/05/2022 03:03:35 - INFO - codeparrot_training - Step 31988: {'lr': 0.0004510371428654538, 'samples': 16378368, 'steps': 31988, 'loss/train': 1.7688745260238647}
-03/05/2022 03:03:38 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/05/2022 03:03:40 - INFO - codeparrot_training - Step 31989: {'lr': 0.00045103398834082334, 'samples': 16378880, 'steps': 31989, 'loss/train': 2.055570602416992}
-03/05/2022 03:03:44 - INFO - codeparrot_training - Step 31990: {'lr': 0.00045103083372561003, 'samples': 16379392, 'steps': 31990, 'loss/train': 2.4414494037628174}
-03/05/2022 03:03:46 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/05/2022 03:03:49 - INFO - codeparrot_training - Step 31991: {'lr': 0.0004510276790198153, 'samples': 16379904, 'steps': 31991, 'loss/train': 1.2987937927246094}
-03/05/2022 03:03:52 - INFO - codeparrot_training - Step 31992: {'lr': 0.00045102452422344065, 'samples': 16380416, 'steps': 31992, 'loss/train': 1.8898197412490845}
-03/05/2022 03:03:55 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/05/2022 03:03:57 - INFO - codeparrot_training - Step 31993: {'lr': 0.0004510213693364875, 'samples': 16380928, 'steps': 31993, 'loss/train': 1.2637690305709839}
-03/05/2022 03:04:00 - INFO - codeparrot_training - Step 31994: {'lr': 0.0004510182143589572, 'samples': 16381440, 'steps': 31994, 'loss/train': 1.151983618736267}
-03/05/2022 03:04:03 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 03:04:06 - INFO - codeparrot_training - Step 31995: {'lr': 0.0004510150592908511, 'samples': 16381952, 'steps': 31995, 'loss/train': 1.811228632926941}
-03/05/2022 03:04:09 - INFO - codeparrot_training - Step 31996: {'lr': 0.00045101190413217085, 'samples': 16382464, 'steps': 31996, 'loss/train': 1.4244699478149414}
-03/05/2022 03:04:11 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/05/2022 03:04:14 - INFO - codeparrot_training - Step 31997: {'lr': 0.0004510087488829177, 'samples': 16382976, 'steps': 31997, 'loss/train': 1.6233900785446167}
-03/05/2022 03:04:17 - INFO - codeparrot_training - Step 31998: {'lr': 0.000451005593543093, 'samples': 16383488, 'steps': 31998, 'loss/train': 2.252574920654297}
-03/05/2022 03:04:20 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 03:04:23 - INFO - codeparrot_training - Step 31999: {'lr': 0.00045100243811269834, 'samples': 16384000, 'steps': 31999, 'loss/train': 2.0426595211029053}
-03/05/2022 03:04:26 - INFO - codeparrot_training - Step 32000: {'lr': 0.00045099928259173516, 'samples': 16384512, 'steps': 32000, 'loss/train': 0.8855448961257935}
-03/05/2022 03:04:29 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/05/2022 03:04:31 - INFO - codeparrot_training - Step 32001: {'lr': 0.0004509961269802048, 'samples': 16385024, 'steps': 32001, 'loss/train': 1.4176315069198608}
-03/05/2022 03:04:34 - INFO - codeparrot_training - Step 32002: {'lr': 0.00045099297127810855, 'samples': 16385536, 'steps': 32002, 'loss/train': 6.000682353973389}
-03/05/2022 03:04:37 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/05/2022 03:04:39 - INFO - codeparrot_training - Step 32003: {'lr': 0.0004509898154854481, 'samples': 16386048, 'steps': 32003, 'loss/train': 1.8179643154144287}
-03/05/2022 03:04:43 - INFO - codeparrot_training - Step 32004: {'lr': 0.00045098665960222474, 'samples': 16386560, 'steps': 32004, 'loss/train': 2.8642096519470215}
-03/05/2022 03:04:45 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/05/2022 03:04:48 - INFO - codeparrot_training - Step 32005: {'lr': 0.00045098350362843975, 'samples': 16387072, 'steps': 32005, 'loss/train': 1.7400468587875366}
-03/05/2022 03:04:51 - INFO - codeparrot_training - Step 32006: {'lr': 0.0004509803475640948, 'samples': 16387584, 'steps': 32006, 'loss/train': 1.5226988792419434}
-03/05/2022 03:04:54 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/05/2022 03:04:56 - INFO - codeparrot_training - Step 32007: {'lr': 0.00045097719140919126, 'samples': 16388096, 'steps': 32007, 'loss/train': 1.3183097839355469}
-03/05/2022 03:04:59 - INFO - codeparrot_training - Step 32008: {'lr': 0.0004509740351637304, 'samples': 16388608, 'steps': 32008, 'loss/train': 0.863994836807251}
-03/05/2022 03:05:02 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/05/2022 03:05:05 - INFO - codeparrot_training - Step 32009: {'lr': 0.0004509708788277138, 'samples': 16389120, 'steps': 32009, 'loss/train': 1.5725955963134766}
-03/05/2022 03:05:08 - INFO - codeparrot_training - Step 32010: {'lr': 0.0004509677224011428, 'samples': 16389632, 'steps': 32010, 'loss/train': 0.5772419571876526}
-03/05/2022 03:05:10 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/05/2022 03:05:13 - INFO - codeparrot_training - Step 32011: {'lr': 0.00045096456588401883, 'samples': 16390144, 'steps': 32011, 'loss/train': 1.0410505533218384}
-03/05/2022 03:05:16 - INFO - codeparrot_training - Step 32012: {'lr': 0.0004509614092763434, 'samples': 16390656, 'steps': 32012, 'loss/train': 2.3063197135925293}
-03/05/2022 03:05:19 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/05/2022 03:05:22 - INFO - codeparrot_training - Step 32013: {'lr': 0.00045095825257811776, 'samples': 16391168, 'steps': 32013, 'loss/train': 1.93497633934021}
-03/05/2022 03:05:25 - INFO - codeparrot_training - Step 32014: {'lr': 0.00045095509578934353, 'samples': 16391680, 'steps': 32014, 'loss/train': 1.7996841669082642}
-03/05/2022 03:05:27 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/05/2022 03:05:30 - INFO - codeparrot_training - Step 32015: {'lr': 0.00045095193891002194, 'samples': 16392192, 'steps': 32015, 'loss/train': 1.7910690307617188}
-03/05/2022 03:05:33 - INFO - codeparrot_training - Step 32016: {'lr': 0.00045094878194015456, 'samples': 16392704, 'steps': 32016, 'loss/train': 1.9506921768188477}
-03/05/2022 03:05:36 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/05/2022 03:05:39 - INFO - codeparrot_training - Step 32017: {'lr': 0.0004509456248797428, 'samples': 16393216, 'steps': 32017, 'loss/train': 2.1983065605163574}
-03/05/2022 03:05:42 - INFO - codeparrot_training - Step 32018: {'lr': 0.000450942467728788, 'samples': 16393728, 'steps': 32018, 'loss/train': 1.274975061416626}
-03/05/2022 03:05:45 - INFO - codeparrot_training - Step 32019: {'lr': 0.00045093931048729156, 'samples': 16394240, 'steps': 32019, 'loss/train': 1.5938899517059326}
-03/05/2022 03:05:45 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 03:05:50 - INFO - codeparrot_training - Step 32020: {'lr': 0.00045093615315525506, 'samples': 16394752, 'steps': 32020, 'loss/train': 0.08673045784235}
-03/05/2022 03:05:54 - INFO - codeparrot_training - Step 32021: {'lr': 0.00045093299573267977, 'samples': 16395264, 'steps': 32021, 'loss/train': 1.2798175811767578}
-03/05/2022 03:05:54 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/05/2022 03:05:59 - INFO - codeparrot_training - Step 32022: {'lr': 0.00045092983821956725, 'samples': 16395776, 'steps': 32022, 'loss/train': 2.2171990871429443}
-03/05/2022 03:06:02 - INFO - codeparrot_training - Step 32023: {'lr': 0.00045092668061591875, 'samples': 16396288, 'steps': 32023, 'loss/train': 1.9794648885726929}
-03/05/2022 03:06:02 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/05/2022 03:06:07 - INFO - codeparrot_training - Step 32024: {'lr': 0.00045092352292173585, 'samples': 16396800, 'steps': 32024, 'loss/train': 1.6061415672302246}
-03/05/2022 03:06:10 - INFO - codeparrot_training - Step 32025: {'lr': 0.00045092036513701985, 'samples': 16397312, 'steps': 32025, 'loss/train': 1.6197881698608398}
-03/05/2022 03:06:11 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/05/2022 03:06:16 - INFO - codeparrot_training - Step 32026: {'lr': 0.0004509172072617723, 'samples': 16397824, 'steps': 32026, 'loss/train': 1.9297541379928589}
-03/05/2022 03:06:19 - INFO - codeparrot_training - Step 32027: {'lr': 0.00045091404929599455, 'samples': 16398336, 'steps': 32027, 'loss/train': 1.1923638582229614}
-03/05/2022 03:06:19 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/05/2022 03:06:24 - INFO - codeparrot_training - Step 32028: {'lr': 0.00045091089123968796, 'samples': 16398848, 'steps': 32028, 'loss/train': 2.594214916229248}
-03/05/2022 03:06:27 - INFO - codeparrot_training - Step 32029: {'lr': 0.0004509077330928541, 'samples': 16399360, 'steps': 32029, 'loss/train': 1.6268155574798584}
-03/05/2022 03:06:27 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/05/2022 03:06:33 - INFO - codeparrot_training - Step 32030: {'lr': 0.0004509045748554943, 'samples': 16399872, 'steps': 32030, 'loss/train': 2.0086452960968018}
-03/05/2022 03:06:36 - INFO - codeparrot_training - Step 32031: {'lr': 0.00045090141652760995, 'samples': 16400384, 'steps': 32031, 'loss/train': 1.6971648931503296}
-03/05/2022 03:06:36 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/05/2022 03:06:41 - INFO - codeparrot_training - Step 32032: {'lr': 0.0004508982581092026, 'samples': 16400896, 'steps': 32032, 'loss/train': 0.9273979663848877}
-03/05/2022 03:06:44 - INFO - codeparrot_training - Step 32033: {'lr': 0.00045089509960027354, 'samples': 16401408, 'steps': 32033, 'loss/train': 2.099200487136841}
-03/05/2022 03:06:45 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/05/2022 03:06:50 - INFO - codeparrot_training - Step 32034: {'lr': 0.00045089194100082433, 'samples': 16401920, 'steps': 32034, 'loss/train': 2.1232099533081055}
-03/05/2022 03:06:53 - INFO - codeparrot_training - Step 32035: {'lr': 0.00045088878231085616, 'samples': 16402432, 'steps': 32035, 'loss/train': 2.4728918075561523}
-03/05/2022 03:06:53 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 03:06:58 - INFO - codeparrot_training - Step 32036: {'lr': 0.00045088562353037077, 'samples': 16402944, 'steps': 32036, 'loss/train': 0.8891081809997559}
-03/05/2022 03:07:01 - INFO - codeparrot_training - Step 32037: {'lr': 0.00045088246465936936, 'samples': 16403456, 'steps': 32037, 'loss/train': 1.6939873695373535}
-03/05/2022 03:07:02 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/05/2022 03:07:06 - INFO - codeparrot_training - Step 32038: {'lr': 0.0004508793056978534, 'samples': 16403968, 'steps': 32038, 'loss/train': 1.4837018251419067}
-03/05/2022 03:07:10 - INFO - codeparrot_training - Step 32039: {'lr': 0.00045087614664582424, 'samples': 16404480, 'steps': 32039, 'loss/train': 1.4713070392608643}
-03/05/2022 03:07:10 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/05/2022 03:07:15 - INFO - codeparrot_training - Step 32040: {'lr': 0.0004508729875032834, 'samples': 16404992, 'steps': 32040, 'loss/train': 1.4132156372070312}
-03/05/2022 03:07:18 - INFO - codeparrot_training - Step 32041: {'lr': 0.0004508698282702324, 'samples': 16405504, 'steps': 32041, 'loss/train': 2.021090269088745}
-03/05/2022 03:07:19 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/05/2022 03:07:23 - INFO - codeparrot_training - Step 32042: {'lr': 0.0004508666689466725, 'samples': 16406016, 'steps': 32042, 'loss/train': 1.9056329727172852}
-03/05/2022 03:07:27 - INFO - codeparrot_training - Step 32043: {'lr': 0.00045086350953260526, 'samples': 16406528, 'steps': 32043, 'loss/train': 1.1744017601013184}
-03/05/2022 03:07:27 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/05/2022 03:07:32 - INFO - codeparrot_training - Step 32044: {'lr': 0.0004508603500280319, 'samples': 16407040, 'steps': 32044, 'loss/train': 1.8305118083953857}
-03/05/2022 03:07:35 - INFO - codeparrot_training - Step 32045: {'lr': 0.00045085719043295406, 'samples': 16407552, 'steps': 32045, 'loss/train': 0.06139529123902321}
-03/05/2022 03:07:35 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/05/2022 03:07:40 - INFO - codeparrot_training - Step 32046: {'lr': 0.00045085403074737295, 'samples': 16408064, 'steps': 32046, 'loss/train': 2.9418563842773438}
-03/05/2022 03:07:43 - INFO - codeparrot_training - Step 32047: {'lr': 0.0004508508709712902, 'samples': 16408576, 'steps': 32047, 'loss/train': 1.8753360509872437}
-03/05/2022 03:07:43 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/05/2022 03:07:49 - INFO - codeparrot_training - Step 32048: {'lr': 0.00045084771110470717, 'samples': 16409088, 'steps': 32048, 'loss/train': 1.6443184614181519}
-03/05/2022 03:07:52 - INFO - codeparrot_training - Step 32049: {'lr': 0.00045084455114762525, 'samples': 16409600, 'steps': 32049, 'loss/train': 0.7787325978279114}
-03/05/2022 03:07:52 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/05/2022 03:07:57 - INFO - codeparrot_training - Step 32050: {'lr': 0.00045084139110004585, 'samples': 16410112, 'steps': 32050, 'loss/train': 1.8579407930374146}
-03/05/2022 03:08:00 - INFO - codeparrot_training - Step 32051: {'lr': 0.0004508382309619704, 'samples': 16410624, 'steps': 32051, 'loss/train': 1.9255794286727905}
-03/05/2022 03:08:01 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/05/2022 03:08:06 - INFO - codeparrot_training - Step 32052: {'lr': 0.0004508350707334004, 'samples': 16411136, 'steps': 32052, 'loss/train': 1.5080236196517944}
-03/05/2022 03:08:09 - INFO - codeparrot_training - Step 32053: {'lr': 0.00045083191041433713, 'samples': 16411648, 'steps': 32053, 'loss/train': 2.131565809249878}
-03/05/2022 03:08:09 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/05/2022 03:08:14 - INFO - codeparrot_training - Step 32054: {'lr': 0.00045082875000478214, 'samples': 16412160, 'steps': 32054, 'loss/train': 1.1241240501403809}
-03/05/2022 03:08:17 - INFO - codeparrot_training - Step 32055: {'lr': 0.0004508255895047368, 'samples': 16412672, 'steps': 32055, 'loss/train': 1.5277467966079712}
-03/05/2022 03:08:17 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/05/2022 03:08:23 - INFO - codeparrot_training - Step 32056: {'lr': 0.0004508224289142026, 'samples': 16413184, 'steps': 32056, 'loss/train': 2.0874884128570557}
-03/05/2022 03:08:26 - INFO - codeparrot_training - Step 32057: {'lr': 0.0004508192682331809, 'samples': 16413696, 'steps': 32057, 'loss/train': 0.8028739094734192}
-03/05/2022 03:08:26 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/05/2022 03:08:31 - INFO - codeparrot_training - Step 32058: {'lr': 0.0004508161074616731, 'samples': 16414208, 'steps': 32058, 'loss/train': 1.8901517391204834}
-03/05/2022 03:08:34 - INFO - codeparrot_training - Step 32059: {'lr': 0.0004508129465996806, 'samples': 16414720, 'steps': 32059, 'loss/train': 1.7314239740371704}
-03/05/2022 03:08:34 - INFO - codeparrot_training - Skipping example with length 7 (seq_length=1024)
-03/05/2022 03:08:39 - INFO - codeparrot_training - Step 32060: {'lr': 0.00045080978564720505, 'samples': 16415232, 'steps': 32060, 'loss/train': 1.623302936553955}
-03/05/2022 03:08:42 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/05/2022 03:08:45 - INFO - codeparrot_training - Step 32061: {'lr': 0.0004508066246042476, 'samples': 16415744, 'steps': 32061, 'loss/train': 1.3772215843200684}
-03/05/2022 03:08:48 - INFO - codeparrot_training - Step 32062: {'lr': 0.0004508034634708098, 'samples': 16416256, 'steps': 32062, 'loss/train': 2.013273239135742}
-03/05/2022 03:08:51 - INFO - codeparrot_training - Step 32063: {'lr': 0.0004508003022468931, 'samples': 16416768, 'steps': 32063, 'loss/train': 0.7460302114486694}
-03/05/2022 03:08:52 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 03:08:57 - INFO - codeparrot_training - Step 32064: {'lr': 0.00045079714093249887, 'samples': 16417280, 'steps': 32064, 'loss/train': 2.743365526199341}
-03/05/2022 03:09:00 - INFO - codeparrot_training - Step 32065: {'lr': 0.00045079397952762845, 'samples': 16417792, 'steps': 32065, 'loss/train': 1.7845908403396606}
-03/05/2022 03:09:00 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/05/2022 03:09:05 - INFO - codeparrot_training - Step 32066: {'lr': 0.0004507908180322835, 'samples': 16418304, 'steps': 32066, 'loss/train': 1.0195339918136597}
-03/05/2022 03:09:08 - INFO - codeparrot_training - Step 32067: {'lr': 0.00045078765644646524, 'samples': 16418816, 'steps': 32067, 'loss/train': 0.47019922733306885}
-03/05/2022 03:09:09 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/05/2022 03:09:13 - INFO - codeparrot_training - Step 32068: {'lr': 0.00045078449477017516, 'samples': 16419328, 'steps': 32068, 'loss/train': 1.6027827262878418}
-03/05/2022 03:09:16 - INFO - codeparrot_training - Step 32069: {'lr': 0.0004507813330034147, 'samples': 16419840, 'steps': 32069, 'loss/train': 1.9164011478424072}
-03/05/2022 03:09:17 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/05/2022 03:09:22 - INFO - codeparrot_training - Step 32070: {'lr': 0.00045077817114618526, 'samples': 16420352, 'steps': 32070, 'loss/train': 1.0379717350006104}
-03/05/2022 03:09:25 - INFO - codeparrot_training - Step 32071: {'lr': 0.00045077500919848826, 'samples': 16420864, 'steps': 32071, 'loss/train': 0.3108794391155243}
-03/05/2022 03:09:25 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/05/2022 03:09:30 - INFO - codeparrot_training - Step 32072: {'lr': 0.00045077184716032516, 'samples': 16421376, 'steps': 32072, 'loss/train': 0.29869237542152405}
-03/05/2022 03:09:33 - INFO - codeparrot_training - Step 32073: {'lr': 0.0004507686850316973, 'samples': 16421888, 'steps': 32073, 'loss/train': 0.6080016493797302}
-03/05/2022 03:09:34 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/05/2022 03:09:39 - INFO - codeparrot_training - Step 32074: {'lr': 0.00045076552281260625, 'samples': 16422400, 'steps': 32074, 'loss/train': 1.23614501953125}
-03/05/2022 03:09:42 - INFO - codeparrot_training - Step 32075: {'lr': 0.0004507623605030533, 'samples': 16422912, 'steps': 32075, 'loss/train': 1.9865936040878296}
-03/05/2022 03:09:42 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/05/2022 03:09:47 - INFO - codeparrot_training - Step 32076: {'lr': 0.00045075919810304, 'samples': 16423424, 'steps': 32076, 'loss/train': 1.4212244749069214}
-03/05/2022 03:09:50 - INFO - codeparrot_training - Step 32077: {'lr': 0.0004507560356125676, 'samples': 16423936, 'steps': 32077, 'loss/train': 2.2919249534606934}
-03/05/2022 03:09:51 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 03:09:56 - INFO - codeparrot_training - Step 32078: {'lr': 0.0004507528730316377, 'samples': 16424448, 'steps': 32078, 'loss/train': 6.587907791137695}
-03/05/2022 03:09:59 - INFO - codeparrot_training - Step 32079: {'lr': 0.0004507497103602517, 'samples': 16424960, 'steps': 32079, 'loss/train': 1.9072664976119995}
-03/05/2022 03:10:00 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/05/2022 03:10:05 - INFO - codeparrot_training - Step 32080: {'lr': 0.00045074654759841087, 'samples': 16425472, 'steps': 32080, 'loss/train': 1.9068021774291992}
-03/05/2022 03:10:08 - INFO - codeparrot_training - Step 32081: {'lr': 0.00045074338474611683, 'samples': 16425984, 'steps': 32081, 'loss/train': 2.1290552616119385}
-03/05/2022 03:10:11 - INFO - codeparrot_training - Step 32082: {'lr': 0.00045074022180337085, 'samples': 16426496, 'steps': 32082, 'loss/train': 1.9639488458633423}
-03/05/2022 03:10:12 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/05/2022 03:10:16 - INFO - codeparrot_training - Step 32083: {'lr': 0.0004507370587701745, 'samples': 16427008, 'steps': 32083, 'loss/train': 1.4790430068969727}
-03/05/2022 03:10:20 - INFO - codeparrot_training - Step 32084: {'lr': 0.000450733895646529, 'samples': 16427520, 'steps': 32084, 'loss/train': 2.458078384399414}
-03/05/2022 03:10:20 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/05/2022 03:10:25 - INFO - codeparrot_training - Step 32085: {'lr': 0.00045073073243243603, 'samples': 16428032, 'steps': 32085, 'loss/train': 1.3728265762329102}
-03/05/2022 03:10:28 - INFO - codeparrot_training - Step 32086: {'lr': 0.0004507275691278968, 'samples': 16428544, 'steps': 32086, 'loss/train': 1.599483847618103}
-03/05/2022 03:10:29 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/05/2022 03:10:33 - INFO - codeparrot_training - Step 32087: {'lr': 0.00045072440573291293, 'samples': 16429056, 'steps': 32087, 'loss/train': 1.1276015043258667}
-03/05/2022 03:10:36 - INFO - codeparrot_training - Step 32088: {'lr': 0.0004507212422474857, 'samples': 16429568, 'steps': 32088, 'loss/train': 2.040832042694092}
-03/05/2022 03:10:38 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/05/2022 03:10:42 - INFO - codeparrot_training - Step 32089: {'lr': 0.0004507180786716165, 'samples': 16430080, 'steps': 32089, 'loss/train': 1.717200517654419}
-03/05/2022 03:10:45 - INFO - codeparrot_training - Step 32090: {'lr': 0.00045071491500530694, 'samples': 16430592, 'steps': 32090, 'loss/train': 1.8143031597137451}
-03/05/2022 03:10:46 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/05/2022 03:10:50 - INFO - codeparrot_training - Step 32091: {'lr': 0.0004507117512485582, 'samples': 16431104, 'steps': 32091, 'loss/train': 1.9190293550491333}
-03/05/2022 03:10:53 - INFO - codeparrot_training - Step 32092: {'lr': 0.000450708587401372, 'samples': 16431616, 'steps': 32092, 'loss/train': 1.321264386177063}
-03/05/2022 03:10:54 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 03:10:59 - INFO - codeparrot_training - Step 32093: {'lr': 0.0004507054234637495, 'samples': 16432128, 'steps': 32093, 'loss/train': 2.015144109725952}
-03/05/2022 03:11:02 - INFO - codeparrot_training - Step 32094: {'lr': 0.0004507022594356922, 'samples': 16432640, 'steps': 32094, 'loss/train': 1.2830841541290283}
-03/05/2022 03:11:02 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/05/2022 03:11:07 - INFO - codeparrot_training - Step 32095: {'lr': 0.00045069909531720166, 'samples': 16433152, 'steps': 32095, 'loss/train': 1.311087965965271}
-03/05/2022 03:11:10 - INFO - codeparrot_training - Step 32096: {'lr': 0.0004506959311082792, 'samples': 16433664, 'steps': 32096, 'loss/train': 2.7646584510803223}
-03/05/2022 03:11:12 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/05/2022 03:11:16 - INFO - codeparrot_training - Step 32097: {'lr': 0.00045069276680892624, 'samples': 16434176, 'steps': 32097, 'loss/train': 2.0605690479278564}
-03/05/2022 03:11:19 - INFO - codeparrot_training - Step 32098: {'lr': 0.00045068960241914413, 'samples': 16434688, 'steps': 32098, 'loss/train': 1.7242608070373535}
-03/05/2022 03:11:20 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/05/2022 03:11:24 - INFO - codeparrot_training - Step 32099: {'lr': 0.00045068643793893447, 'samples': 16435200, 'steps': 32099, 'loss/train': 1.7715922594070435}
-03/05/2022 03:11:27 - INFO - codeparrot_training - Step 32100: {'lr': 0.0004506832733682986, 'samples': 16435712, 'steps': 32100, 'loss/train': 0.8491368889808655}
-03/05/2022 03:11:28 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/05/2022 03:11:32 - INFO - codeparrot_training - Step 32101: {'lr': 0.00045068010870723783, 'samples': 16436224, 'steps': 32101, 'loss/train': 2.4156553745269775}
-03/05/2022 03:11:36 - INFO - codeparrot_training - Step 32102: {'lr': 0.00045067694395575385, 'samples': 16436736, 'steps': 32102, 'loss/train': 1.5904183387756348}
-03/05/2022 03:11:37 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/05/2022 03:11:41 - INFO - codeparrot_training - Step 32103: {'lr': 0.0004506737791138479, 'samples': 16437248, 'steps': 32103, 'loss/train': 1.099422812461853}
-03/05/2022 03:11:44 - INFO - codeparrot_training - Step 32104: {'lr': 0.00045067061418152136, 'samples': 16437760, 'steps': 32104, 'loss/train': 1.9458777904510498}
-03/05/2022 03:11:45 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/05/2022 03:11:49 - INFO - codeparrot_training - Step 32105: {'lr': 0.00045066744915877585, 'samples': 16438272, 'steps': 32105, 'loss/train': 2.10386323928833}
-03/05/2022 03:11:53 - INFO - codeparrot_training - Step 32106: {'lr': 0.0004506642840456126, 'samples': 16438784, 'steps': 32106, 'loss/train': 1.757859468460083}
-03/05/2022 03:11:54 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/05/2022 03:11:58 - INFO - codeparrot_training - Step 32107: {'lr': 0.00045066111884203315, 'samples': 16439296, 'steps': 32107, 'loss/train': 1.5780664682388306}
-03/05/2022 03:12:01 - INFO - codeparrot_training - Step 32108: {'lr': 0.0004506579535480389, 'samples': 16439808, 'steps': 32108, 'loss/train': 1.497854232788086}
-03/05/2022 03:12:02 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/05/2022 03:12:06 - INFO - codeparrot_training - Step 32109: {'lr': 0.00045065478816363124, 'samples': 16440320, 'steps': 32109, 'loss/train': 2.388638496398926}
-03/05/2022 03:12:09 - INFO - codeparrot_training - Step 32110: {'lr': 0.00045065162268881164, 'samples': 16440832, 'steps': 32110, 'loss/train': 1.997281789779663}
-03/05/2022 03:12:10 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/05/2022 03:12:15 - INFO - codeparrot_training - Step 32111: {'lr': 0.0004506484571235816, 'samples': 16441344, 'steps': 32111, 'loss/train': 1.5788021087646484}
-03/05/2022 03:12:18 - INFO - codeparrot_training - Step 32112: {'lr': 0.00045064529146794234, 'samples': 16441856, 'steps': 32112, 'loss/train': 2.4255483150482178}
-03/05/2022 03:12:19 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/05/2022 03:12:23 - INFO - codeparrot_training - Step 32113: {'lr': 0.0004506421257218955, 'samples': 16442368, 'steps': 32113, 'loss/train': 2.302644729614258}
-03/05/2022 03:12:27 - INFO - codeparrot_training - Step 32114: {'lr': 0.00045063895988544235, 'samples': 16442880, 'steps': 32114, 'loss/train': 2.1795966625213623}
-03/05/2022 03:12:28 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/05/2022 03:12:32 - INFO - codeparrot_training - Step 32115: {'lr': 0.00045063579395858444, 'samples': 16443392, 'steps': 32115, 'loss/train': 1.6226500272750854}
-03/05/2022 03:12:35 - INFO - codeparrot_training - Step 32116: {'lr': 0.0004506326279413231, 'samples': 16443904, 'steps': 32116, 'loss/train': 1.461987018585205}
-03/05/2022 03:12:36 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/05/2022 03:12:40 - INFO - codeparrot_training - Step 32117: {'lr': 0.0004506294618336598, 'samples': 16444416, 'steps': 32117, 'loss/train': 1.177091121673584}
-03/05/2022 03:12:43 - INFO - codeparrot_training - Step 32118: {'lr': 0.00045062629563559595, 'samples': 16444928, 'steps': 32118, 'loss/train': 1.8922208547592163}
-03/05/2022 03:12:45 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 03:12:49 - INFO - codeparrot_training - Step 32119: {'lr': 0.00045062312934713303, 'samples': 16445440, 'steps': 32119, 'loss/train': 1.8817964792251587}
-03/05/2022 03:12:52 - INFO - codeparrot_training - Step 32120: {'lr': 0.00045061996296827237, 'samples': 16445952, 'steps': 32120, 'loss/train': 1.4593420028686523}
-03/05/2022 03:12:54 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/05/2022 03:12:57 - INFO - codeparrot_training - Step 32121: {'lr': 0.00045061679649901543, 'samples': 16446464, 'steps': 32121, 'loss/train': 1.780485987663269}
-03/05/2022 03:13:00 - INFO - codeparrot_training - Step 32122: {'lr': 0.00045061362993936374, 'samples': 16446976, 'steps': 32122, 'loss/train': 1.5574488639831543}
-03/05/2022 03:13:02 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/05/2022 03:13:05 - INFO - codeparrot_training - Step 32123: {'lr': 0.0004506104632893185, 'samples': 16447488, 'steps': 32123, 'loss/train': 2.1572587490081787}
-03/05/2022 03:13:09 - INFO - codeparrot_training - Step 32124: {'lr': 0.00045060729654888143, 'samples': 16448000, 'steps': 32124, 'loss/train': 1.518384575843811}
-03/05/2022 03:13:10 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/05/2022 03:13:14 - INFO - codeparrot_training - Step 32125: {'lr': 0.00045060412971805375, 'samples': 16448512, 'steps': 32125, 'loss/train': 2.67118763923645}
-03/05/2022 03:13:17 - INFO - codeparrot_training - Step 32126: {'lr': 0.00045060096279683694, 'samples': 16449024, 'steps': 32126, 'loss/train': 2.283170461654663}
-03/05/2022 03:13:19 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/05/2022 03:13:22 - INFO - codeparrot_training - Step 32127: {'lr': 0.0004505977957852325, 'samples': 16449536, 'steps': 32127, 'loss/train': 1.9854600429534912}
-03/05/2022 03:13:26 - INFO - codeparrot_training - Step 32128: {'lr': 0.00045059462868324177, 'samples': 16450048, 'steps': 32128, 'loss/train': 2.2117459774017334}
-03/05/2022 03:13:28 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/05/2022 03:13:31 - INFO - codeparrot_training - Step 32129: {'lr': 0.00045059146149086605, 'samples': 16450560, 'steps': 32129, 'loss/train': 1.4528615474700928}
-03/05/2022 03:13:34 - INFO - codeparrot_training - Step 32130: {'lr': 0.00045058829420810707, 'samples': 16451072, 'steps': 32130, 'loss/train': 1.0567272901535034}
-03/05/2022 03:13:37 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/05/2022 03:13:39 - INFO - codeparrot_training - Step 32131: {'lr': 0.00045058512683496607, 'samples': 16451584, 'steps': 32131, 'loss/train': 2.081271171569824}
-03/05/2022 03:13:42 - INFO - codeparrot_training - Step 32132: {'lr': 0.00045058195937144446, 'samples': 16452096, 'steps': 32132, 'loss/train': 1.5891145467758179}
-03/05/2022 03:13:45 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/05/2022 03:13:48 - INFO - codeparrot_training - Step 32133: {'lr': 0.00045057879181754375, 'samples': 16452608, 'steps': 32133, 'loss/train': 1.8834021091461182}
-03/05/2022 03:13:51 - INFO - codeparrot_training - Step 32134: {'lr': 0.0004505756241732653, 'samples': 16453120, 'steps': 32134, 'loss/train': 1.3042086362838745}
-03/05/2022 03:13:53 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/05/2022 03:13:56 - INFO - codeparrot_training - Step 32135: {'lr': 0.0004505724564386106, 'samples': 16453632, 'steps': 32135, 'loss/train': 1.8343548774719238}
-03/05/2022 03:13:59 - INFO - codeparrot_training - Step 32136: {'lr': 0.00045056928861358106, 'samples': 16454144, 'steps': 32136, 'loss/train': 2.023365020751953}
-03/05/2022 03:14:02 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/05/2022 03:14:05 - INFO - codeparrot_training - Step 32137: {'lr': 0.000450566120698178, 'samples': 16454656, 'steps': 32137, 'loss/train': 1.7368501424789429}
-03/05/2022 03:14:08 - INFO - codeparrot_training - Step 32138: {'lr': 0.0004505629526924031, 'samples': 16455168, 'steps': 32138, 'loss/train': 2.8090903759002686}
-03/05/2022 03:14:10 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/05/2022 03:14:13 - INFO - codeparrot_training - Step 32139: {'lr': 0.0004505597845962575, 'samples': 16455680, 'steps': 32139, 'loss/train': 2.1710009574890137}
-03/05/2022 03:14:16 - INFO - codeparrot_training - Step 32140: {'lr': 0.0004505566164097428, 'samples': 16456192, 'steps': 32140, 'loss/train': 1.9724067449569702}
-03/05/2022 03:14:19 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/05/2022 03:14:21 - INFO - codeparrot_training - Step 32141: {'lr': 0.0004505534481328604, 'samples': 16456704, 'steps': 32141, 'loss/train': 0.9738463759422302}
-03/05/2022 03:14:25 - INFO - codeparrot_training - Step 32142: {'lr': 0.0004505502797656117, 'samples': 16457216, 'steps': 32142, 'loss/train': 0.8872283101081848}
-03/05/2022 03:14:27 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 03:14:30 - INFO - codeparrot_training - Step 32143: {'lr': 0.00045054711130799806, 'samples': 16457728, 'steps': 32143, 'loss/train': 1.1109455823898315}
-03/05/2022 03:14:33 - INFO - codeparrot_training - Step 32144: {'lr': 0.00045054394276002106, 'samples': 16458240, 'steps': 32144, 'loss/train': 1.1003745794296265}
-03/05/2022 03:14:35 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/05/2022 03:14:38 - INFO - codeparrot_training - Step 32145: {'lr': 0.00045054077412168215, 'samples': 16458752, 'steps': 32145, 'loss/train': 2.4092071056365967}
-03/05/2022 03:14:41 - INFO - codeparrot_training - Step 32146: {'lr': 0.0004505376053929825, 'samples': 16459264, 'steps': 32146, 'loss/train': 1.9454472064971924}
-03/05/2022 03:14:44 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/05/2022 03:14:47 - INFO - codeparrot_training - Step 32147: {'lr': 0.0004505344365739238, 'samples': 16459776, 'steps': 32147, 'loss/train': 2.153879165649414}
-03/05/2022 03:14:50 - INFO - codeparrot_training - Step 32148: {'lr': 0.0004505312676645073, 'samples': 16460288, 'steps': 32148, 'loss/train': 2.1145272254943848}
-03/05/2022 03:14:52 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/05/2022 03:14:55 - INFO - codeparrot_training - Step 32149: {'lr': 0.00045052809866473454, 'samples': 16460800, 'steps': 32149, 'loss/train': 0.2470967024564743}
-03/05/2022 03:14:58 - INFO - codeparrot_training - Step 32150: {'lr': 0.00045052492957460696, 'samples': 16461312, 'steps': 32150, 'loss/train': 2.1979258060455322}
-03/05/2022 03:15:00 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/05/2022 03:15:03 - INFO - codeparrot_training - Step 32151: {'lr': 0.00045052176039412587, 'samples': 16461824, 'steps': 32151, 'loss/train': 0.9724978804588318}
-03/05/2022 03:15:07 - INFO - codeparrot_training - Step 32152: {'lr': 0.0004505185911232928, 'samples': 16462336, 'steps': 32152, 'loss/train': 1.855562448501587}
-03/05/2022 03:15:08 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/05/2022 03:15:12 - INFO - codeparrot_training - Step 32153: {'lr': 0.00045051542176210914, 'samples': 16462848, 'steps': 32153, 'loss/train': 2.0042941570281982}
-03/05/2022 03:15:15 - INFO - codeparrot_training - Step 32154: {'lr': 0.0004505122523105764, 'samples': 16463360, 'steps': 32154, 'loss/train': 0.3884555995464325}
-03/05/2022 03:15:17 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/05/2022 03:15:20 - INFO - codeparrot_training - Step 32155: {'lr': 0.00045050908276869585, 'samples': 16463872, 'steps': 32155, 'loss/train': 2.0705671310424805}
-03/05/2022 03:15:23 - INFO - codeparrot_training - Step 32156: {'lr': 0.0004505059131364689, 'samples': 16464384, 'steps': 32156, 'loss/train': 2.1798617839813232}
-03/05/2022 03:15:25 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/05/2022 03:15:29 - INFO - codeparrot_training - Step 32157: {'lr': 0.00045050274341389726, 'samples': 16464896, 'steps': 32157, 'loss/train': 2.2720835208892822}
-03/05/2022 03:15:32 - INFO - codeparrot_training - Step 32158: {'lr': 0.00045049957360098207, 'samples': 16465408, 'steps': 32158, 'loss/train': 0.6701028943061829}
-03/05/2022 03:15:34 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/05/2022 03:15:37 - INFO - codeparrot_training - Step 32159: {'lr': 0.0004504964036977249, 'samples': 16465920, 'steps': 32159, 'loss/train': 1.919608235359192}
-03/05/2022 03:15:40 - INFO - codeparrot_training - Step 32160: {'lr': 0.00045049323370412723, 'samples': 16466432, 'steps': 32160, 'loss/train': 1.891566276550293}
-03/05/2022 03:15:42 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 03:15:46 - INFO - codeparrot_training - Step 32161: {'lr': 0.0004504900636201903, 'samples': 16466944, 'steps': 32161, 'loss/train': 0.7414053678512573}
-03/05/2022 03:15:49 - INFO - codeparrot_training - Step 32162: {'lr': 0.00045048689344591566, 'samples': 16467456, 'steps': 32162, 'loss/train': 1.5685561895370483}
-03/05/2022 03:15:50 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/05/2022 03:15:54 - INFO - codeparrot_training - Step 32163: {'lr': 0.0004504837231813047, 'samples': 16467968, 'steps': 32163, 'loss/train': 1.1673611402511597}
-03/05/2022 03:15:57 - INFO - codeparrot_training - Step 32164: {'lr': 0.0004504805528263589, 'samples': 16468480, 'steps': 32164, 'loss/train': 1.5249865055084229}
-03/05/2022 03:15:58 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/05/2022 03:16:02 - INFO - codeparrot_training - Step 32165: {'lr': 0.00045047738238107967, 'samples': 16468992, 'steps': 32165, 'loss/train': 2.3334567546844482}
-03/05/2022 03:16:06 - INFO - codeparrot_training - Step 32166: {'lr': 0.00045047421184546844, 'samples': 16469504, 'steps': 32166, 'loss/train': 2.0946598052978516}
-03/05/2022 03:16:07 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 03:16:11 - INFO - codeparrot_training - Step 32167: {'lr': 0.0004504710412195265, 'samples': 16470016, 'steps': 32167, 'loss/train': 1.774285912513733}
-03/05/2022 03:16:14 - INFO - codeparrot_training - Step 32168: {'lr': 0.00045046787050325555, 'samples': 16470528, 'steps': 32168, 'loss/train': 1.5887900590896606}
-03/05/2022 03:16:15 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/05/2022 03:16:19 - INFO - codeparrot_training - Step 32169: {'lr': 0.0004504646996966568, 'samples': 16471040, 'steps': 32169, 'loss/train': 1.6910507678985596}
-03/05/2022 03:16:22 - INFO - codeparrot_training - Step 32170: {'lr': 0.0004504615287997318, 'samples': 16471552, 'steps': 32170, 'loss/train': 2.180844783782959}
-03/05/2022 03:16:24 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/05/2022 03:16:28 - INFO - codeparrot_training - Step 32171: {'lr': 0.00045045835781248184, 'samples': 16472064, 'steps': 32171, 'loss/train': 2.855029582977295}
-03/05/2022 03:16:31 - INFO - codeparrot_training - Step 32172: {'lr': 0.0004504551867349085, 'samples': 16472576, 'steps': 32172, 'loss/train': 1.0955774784088135}
-03/05/2022 03:16:33 - INFO - codeparrot_training - Skipping example with length 628 (seq_length=1024)
-03/05/2022 03:16:36 - INFO - codeparrot_training - Step 32173: {'lr': 0.0004504520155670131, 'samples': 16473088, 'steps': 32173, 'loss/train': 1.2767086029052734}
-03/05/2022 03:16:39 - INFO - codeparrot_training - Step 32174: {'lr': 0.0004504488443087972, 'samples': 16473600, 'steps': 32174, 'loss/train': 2.0411813259124756}
-03/05/2022 03:16:41 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/05/2022 03:16:45 - INFO - codeparrot_training - Step 32175: {'lr': 0.00045044567296026206, 'samples': 16474112, 'steps': 32175, 'loss/train': 1.4554191827774048}
-03/05/2022 03:16:48 - INFO - codeparrot_training - Step 32176: {'lr': 0.0004504425015214092, 'samples': 16474624, 'steps': 32176, 'loss/train': 1.8240692615509033}
-03/05/2022 03:16:49 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/05/2022 03:16:53 - INFO - codeparrot_training - Step 32177: {'lr': 0.00045043932999224015, 'samples': 16475136, 'steps': 32177, 'loss/train': 1.536206841468811}
-03/05/2022 03:16:56 - INFO - codeparrot_training - Step 32178: {'lr': 0.00045043615837275607, 'samples': 16475648, 'steps': 32178, 'loss/train': 1.7384963035583496}
-03/05/2022 03:16:58 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/05/2022 03:17:02 - INFO - codeparrot_training - Step 32179: {'lr': 0.0004504329866629586, 'samples': 16476160, 'steps': 32179, 'loss/train': 1.7710537910461426}
-03/05/2022 03:17:05 - INFO - codeparrot_training - Step 32180: {'lr': 0.0004504298148628492, 'samples': 16476672, 'steps': 32180, 'loss/train': 2.001732587814331}
-03/05/2022 03:17:07 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/05/2022 03:17:10 - INFO - codeparrot_training - Step 32181: {'lr': 0.0004504266429724292, 'samples': 16477184, 'steps': 32181, 'loss/train': 1.115587830543518}
-03/05/2022 03:17:14 - INFO - codeparrot_training - Step 32182: {'lr': 0.0004504234709917, 'samples': 16477696, 'steps': 32182, 'loss/train': 2.181873321533203}
-03/05/2022 03:17:16 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/05/2022 03:17:19 - INFO - codeparrot_training - Step 32183: {'lr': 0.00045042029892066306, 'samples': 16478208, 'steps': 32183, 'loss/train': 0.6127412915229797}
-03/05/2022 03:17:22 - INFO - codeparrot_training - Step 32184: {'lr': 0.00045041712675931983, 'samples': 16478720, 'steps': 32184, 'loss/train': 0.10254140198230743}
-03/05/2022 03:17:24 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/05/2022 03:17:27 - INFO - codeparrot_training - Step 32185: {'lr': 0.0004504139545076717, 'samples': 16479232, 'steps': 32185, 'loss/train': 1.8352134227752686}
-03/05/2022 03:17:30 - INFO - codeparrot_training - Step 32186: {'lr': 0.0004504107821657203, 'samples': 16479744, 'steps': 32186, 'loss/train': 2.150118112564087}
-03/05/2022 03:17:32 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/05/2022 03:17:36 - INFO - codeparrot_training - Step 32187: {'lr': 0.00045040760973346673, 'samples': 16480256, 'steps': 32187, 'loss/train': 2.707380533218384}
-03/05/2022 03:17:39 - INFO - codeparrot_training - Step 32188: {'lr': 0.00045040443721091266, 'samples': 16480768, 'steps': 32188, 'loss/train': 1.8270772695541382}
-03/05/2022 03:17:41 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/05/2022 03:17:44 - INFO - codeparrot_training - Step 32189: {'lr': 0.0004504012645980594, 'samples': 16481280, 'steps': 32189, 'loss/train': 0.22897309064865112}
-03/05/2022 03:17:47 - INFO - codeparrot_training - Step 32190: {'lr': 0.0004503980918949085, 'samples': 16481792, 'steps': 32190, 'loss/train': 1.241885781288147}
-03/05/2022 03:17:49 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/05/2022 03:17:53 - INFO - codeparrot_training - Step 32191: {'lr': 0.00045039491910146124, 'samples': 16482304, 'steps': 32191, 'loss/train': 1.7181458473205566}
-03/05/2022 03:17:56 - INFO - codeparrot_training - Step 32192: {'lr': 0.00045039174621771915, 'samples': 16482816, 'steps': 32192, 'loss/train': 2.6758923530578613}
-03/05/2022 03:17:57 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/05/2022 03:18:01 - INFO - codeparrot_training - Step 32193: {'lr': 0.00045038857324368367, 'samples': 16483328, 'steps': 32193, 'loss/train': 0.6276638507843018}
-03/05/2022 03:18:04 - INFO - codeparrot_training - Step 32194: {'lr': 0.0004503854001793561, 'samples': 16483840, 'steps': 32194, 'loss/train': 0.07944183051586151}
-03/05/2022 03:18:06 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/05/2022 03:18:10 - INFO - codeparrot_training - Step 32195: {'lr': 0.00045038222702473797, 'samples': 16484352, 'steps': 32195, 'loss/train': 2.2628095149993896}
-03/05/2022 03:18:13 - INFO - codeparrot_training - Step 32196: {'lr': 0.0004503790537798308, 'samples': 16484864, 'steps': 32196, 'loss/train': 1.309360384941101}
-03/05/2022 03:18:14 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/05/2022 03:18:18 - INFO - codeparrot_training - Step 32197: {'lr': 0.00045037588044463586, 'samples': 16485376, 'steps': 32197, 'loss/train': 1.5654950141906738}
-03/05/2022 03:18:21 - INFO - codeparrot_training - Step 32198: {'lr': 0.00045037270701915464, 'samples': 16485888, 'steps': 32198, 'loss/train': 2.325202226638794}
-03/05/2022 03:18:22 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/05/2022 03:18:26 - INFO - codeparrot_training - Step 32199: {'lr': 0.0004503695335033885, 'samples': 16486400, 'steps': 32199, 'loss/train': 1.2658920288085938}
-03/05/2022 03:18:30 - INFO - codeparrot_training - Step 32200: {'lr': 0.00045036635989733904, 'samples': 16486912, 'steps': 32200, 'loss/train': 1.9737051725387573}
-03/05/2022 03:18:31 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/05/2022 03:18:35 - INFO - codeparrot_training - Step 32201: {'lr': 0.0004503631862010076, 'samples': 16487424, 'steps': 32201, 'loss/train': 1.3811358213424683}
-03/05/2022 03:18:38 - INFO - codeparrot_training - Step 32202: {'lr': 0.0004503600124143955, 'samples': 16487936, 'steps': 32202, 'loss/train': 1.3133983612060547}
-03/05/2022 03:18:39 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/05/2022 03:18:43 - INFO - codeparrot_training - Step 32203: {'lr': 0.0004503568385375043, 'samples': 16488448, 'steps': 32203, 'loss/train': 1.7754358053207397}
-03/05/2022 03:18:46 - INFO - codeparrot_training - Step 32204: {'lr': 0.00045035366457033546, 'samples': 16488960, 'steps': 32204, 'loss/train': 1.7398165464401245}
-03/05/2022 03:18:47 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 03:18:52 - INFO - codeparrot_training - Step 32205: {'lr': 0.00045035049051289037, 'samples': 16489472, 'steps': 32205, 'loss/train': 1.4337958097457886}
-03/05/2022 03:18:55 - INFO - codeparrot_training - Step 32206: {'lr': 0.00045034731636517036, 'samples': 16489984, 'steps': 32206, 'loss/train': 1.1567484140396118}
-03/05/2022 03:18:55 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/05/2022 03:19:00 - INFO - codeparrot_training - Step 32207: {'lr': 0.0004503441421271769, 'samples': 16490496, 'steps': 32207, 'loss/train': 1.896597981452942}
-03/05/2022 03:19:03 - INFO - codeparrot_training - Step 32208: {'lr': 0.0004503409677989115, 'samples': 16491008, 'steps': 32208, 'loss/train': 1.7100908756256104}
-03/05/2022 03:19:04 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/05/2022 03:19:08 - INFO - codeparrot_training - Step 32209: {'lr': 0.00045033779338037565, 'samples': 16491520, 'steps': 32209, 'loss/train': 1.4443621635437012}
-03/05/2022 03:19:12 - INFO - codeparrot_training - Step 32210: {'lr': 0.0004503346188715706, 'samples': 16492032, 'steps': 32210, 'loss/train': 1.5934430360794067}
-03/05/2022 03:19:12 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/05/2022 03:19:17 - INFO - codeparrot_training - Step 32211: {'lr': 0.0004503314442724979, 'samples': 16492544, 'steps': 32211, 'loss/train': 1.5583096742630005}
-03/05/2022 03:19:20 - INFO - codeparrot_training - Step 32212: {'lr': 0.0004503282695831589, 'samples': 16493056, 'steps': 32212, 'loss/train': 1.3145238161087036}
-03/05/2022 03:19:21 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/05/2022 03:19:25 - INFO - codeparrot_training - Step 32213: {'lr': 0.0004503250948035551, 'samples': 16493568, 'steps': 32213, 'loss/train': 1.9637290239334106}
-03/05/2022 03:19:29 - INFO - codeparrot_training - Step 32214: {'lr': 0.0004503219199336879, 'samples': 16494080, 'steps': 32214, 'loss/train': 1.4416959285736084}
-03/05/2022 03:19:29 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/05/2022 03:19:34 - INFO - codeparrot_training - Step 32215: {'lr': 0.00045031874497355876, 'samples': 16494592, 'steps': 32215, 'loss/train': 0.8577883839607239}
-03/05/2022 03:19:37 - INFO - codeparrot_training - Step 32216: {'lr': 0.000450315569923169, 'samples': 16495104, 'steps': 32216, 'loss/train': 2.0951616764068604}
-03/05/2022 03:19:37 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/05/2022 03:19:42 - INFO - codeparrot_training - Step 32217: {'lr': 0.00045031239478252017, 'samples': 16495616, 'steps': 32217, 'loss/train': 0.8503124117851257}
-03/05/2022 03:19:46 - INFO - codeparrot_training - Step 32218: {'lr': 0.00045030921955161373, 'samples': 16496128, 'steps': 32218, 'loss/train': 2.3442375659942627}
-03/05/2022 03:19:46 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/05/2022 03:19:51 - INFO - codeparrot_training - Step 32219: {'lr': 0.000450306044230451, 'samples': 16496640, 'steps': 32219, 'loss/train': 1.560167670249939}
-03/05/2022 03:19:54 - INFO - codeparrot_training - Step 32220: {'lr': 0.0004503028688190335, 'samples': 16497152, 'steps': 32220, 'loss/train': 1.4374396800994873}
-03/05/2022 03:19:54 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/05/2022 03:19:59 - INFO - codeparrot_training - Step 32221: {'lr': 0.00045029969331736254, 'samples': 16497664, 'steps': 32221, 'loss/train': 1.1682209968566895}
-03/05/2022 03:20:02 - INFO - codeparrot_training - Step 32222: {'lr': 0.00045029651772543965, 'samples': 16498176, 'steps': 32222, 'loss/train': 1.8078739643096924}
-03/05/2022 03:20:02 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/05/2022 03:20:08 - INFO - codeparrot_training - Step 32223: {'lr': 0.0004502933420432662, 'samples': 16498688, 'steps': 32223, 'loss/train': 2.119680166244507}
-03/05/2022 03:20:11 - INFO - codeparrot_training - Step 32224: {'lr': 0.0004502901662708437, 'samples': 16499200, 'steps': 32224, 'loss/train': 1.6902843713760376}
-03/05/2022 03:20:12 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/05/2022 03:20:16 - INFO - codeparrot_training - Step 32225: {'lr': 0.0004502869904081736, 'samples': 16499712, 'steps': 32225, 'loss/train': 1.5183053016662598}
-03/05/2022 03:20:20 - INFO - codeparrot_training - Step 32226: {'lr': 0.00045028381445525725, 'samples': 16500224, 'steps': 32226, 'loss/train': 2.439406156539917}
-03/05/2022 03:20:20 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/05/2022 03:20:25 - INFO - codeparrot_training - Step 32227: {'lr': 0.0004502806384120961, 'samples': 16500736, 'steps': 32227, 'loss/train': 1.5894701480865479}
-03/05/2022 03:20:28 - INFO - codeparrot_training - Step 32228: {'lr': 0.0004502774622786915, 'samples': 16501248, 'steps': 32228, 'loss/train': 2.3167834281921387}
-03/05/2022 03:20:29 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/05/2022 03:20:33 - INFO - codeparrot_training - Step 32229: {'lr': 0.00045027428605504507, 'samples': 16501760, 'steps': 32229, 'loss/train': 2.0827436447143555}
-03/05/2022 03:20:37 - INFO - codeparrot_training - Step 32230: {'lr': 0.00045027110974115814, 'samples': 16502272, 'steps': 32230, 'loss/train': 1.519816279411316}
-03/05/2022 03:20:37 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 03:20:42 - INFO - codeparrot_training - Step 32231: {'lr': 0.0004502679333370321, 'samples': 16502784, 'steps': 32231, 'loss/train': 1.6383501291275024}
-03/05/2022 03:20:45 - INFO - codeparrot_training - Step 32232: {'lr': 0.0004502647568426684, 'samples': 16503296, 'steps': 32232, 'loss/train': 1.9301764965057373}
-03/05/2022 03:20:46 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/05/2022 03:20:50 - INFO - codeparrot_training - Step 32233: {'lr': 0.0004502615802580685, 'samples': 16503808, 'steps': 32233, 'loss/train': 2.0161755084991455}
-03/05/2022 03:20:53 - INFO - codeparrot_training - Step 32234: {'lr': 0.0004502584035832338, 'samples': 16504320, 'steps': 32234, 'loss/train': 0.96965491771698}
-03/05/2022 03:20:54 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/05/2022 03:20:59 - INFO - codeparrot_training - Step 32235: {'lr': 0.00045025522681816586, 'samples': 16504832, 'steps': 32235, 'loss/train': 2.043834924697876}
-03/05/2022 03:21:02 - INFO - codeparrot_training - Step 32236: {'lr': 0.0004502520499628659, 'samples': 16505344, 'steps': 32236, 'loss/train': 1.6013840436935425}
-03/05/2022 03:21:02 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/05/2022 03:21:07 - INFO - codeparrot_training - Step 32237: {'lr': 0.00045024887301733555, 'samples': 16505856, 'steps': 32237, 'loss/train': 2.0295398235321045}
-03/05/2022 03:21:10 - INFO - codeparrot_training - Step 32238: {'lr': 0.0004502456959815761, 'samples': 16506368, 'steps': 32238, 'loss/train': 2.553128719329834}
-03/05/2022 03:21:11 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/05/2022 03:21:15 - INFO - codeparrot_training - Step 32239: {'lr': 0.000450242518855589, 'samples': 16506880, 'steps': 32239, 'loss/train': 1.6728880405426025}
-03/05/2022 03:21:19 - INFO - codeparrot_training - Step 32240: {'lr': 0.00045023934163937565, 'samples': 16507392, 'steps': 32240, 'loss/train': 1.971681833267212}
-03/05/2022 03:21:19 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/05/2022 03:21:24 - INFO - codeparrot_training - Step 32241: {'lr': 0.00045023616433293763, 'samples': 16507904, 'steps': 32241, 'loss/train': 2.336901903152466}
-03/05/2022 03:21:27 - INFO - codeparrot_training - Step 32242: {'lr': 0.00045023298693627626, 'samples': 16508416, 'steps': 32242, 'loss/train': 1.8789466619491577}
-03/05/2022 03:21:27 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/05/2022 03:21:32 - INFO - codeparrot_training - Step 32243: {'lr': 0.000450229809449393, 'samples': 16508928, 'steps': 32243, 'loss/train': 1.7914034128189087}
-03/05/2022 03:21:36 - INFO - codeparrot_training - Step 32244: {'lr': 0.00045022663187228927, 'samples': 16509440, 'steps': 32244, 'loss/train': 1.4560041427612305}
-03/05/2022 03:21:36 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 03:21:41 - INFO - codeparrot_training - Step 32245: {'lr': 0.0004502234542049666, 'samples': 16509952, 'steps': 32245, 'loss/train': 1.5970028638839722}
-03/05/2022 03:21:44 - INFO - codeparrot_training - Step 32246: {'lr': 0.00045022027644742624, 'samples': 16510464, 'steps': 32246, 'loss/train': 1.4289735555648804}
-03/05/2022 03:21:44 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/05/2022 03:21:49 - INFO - codeparrot_training - Step 32247: {'lr': 0.0004502170985996697, 'samples': 16510976, 'steps': 32247, 'loss/train': 1.6264692544937134}
-03/05/2022 03:21:53 - INFO - codeparrot_training - Step 32248: {'lr': 0.00045021392066169844, 'samples': 16511488, 'steps': 32248, 'loss/train': 1.421189546585083}
-03/05/2022 03:21:53 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/05/2022 03:21:58 - INFO - codeparrot_training - Step 32249: {'lr': 0.0004502107426335139, 'samples': 16512000, 'steps': 32249, 'loss/train': 2.609271287918091}
-03/05/2022 03:22:01 - INFO - codeparrot_training - Step 32250: {'lr': 0.0004502075645151175, 'samples': 16512512, 'steps': 32250, 'loss/train': 1.727664589881897}
-03/05/2022 03:22:01 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 03:22:07 - INFO - codeparrot_training - Step 32251: {'lr': 0.0004502043863065106, 'samples': 16513024, 'steps': 32251, 'loss/train': 1.205125331878662}
-03/05/2022 03:22:10 - INFO - codeparrot_training - Step 32252: {'lr': 0.00045020120800769474, 'samples': 16513536, 'steps': 32252, 'loss/train': 2.233844757080078}
-03/05/2022 03:22:12 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/05/2022 03:22:16 - INFO - codeparrot_training - Step 32253: {'lr': 0.0004501980296186713, 'samples': 16514048, 'steps': 32253, 'loss/train': 1.241442322731018}
-03/05/2022 03:22:20 - INFO - codeparrot_training - Step 32254: {'lr': 0.0004501948511394417, 'samples': 16514560, 'steps': 32254, 'loss/train': 1.125423550605774}
-03/05/2022 03:22:23 - INFO - codeparrot_training - Step 32255: {'lr': 0.0004501916725700074, 'samples': 16515072, 'steps': 32255, 'loss/train': 0.8903215527534485}
-03/05/2022 03:22:25 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/05/2022 03:22:28 - INFO - codeparrot_training - Step 32256: {'lr': 0.00045018849391036987, 'samples': 16515584, 'steps': 32256, 'loss/train': 0.8482746481895447}
-03/05/2022 03:22:31 - INFO - codeparrot_training - Step 32257: {'lr': 0.00045018531516053046, 'samples': 16516096, 'steps': 32257, 'loss/train': 0.825526773929596}
-03/05/2022 03:22:33 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/05/2022 03:22:36 - INFO - codeparrot_training - Step 32258: {'lr': 0.0004501821363204906, 'samples': 16516608, 'steps': 32258, 'loss/train': 1.883768916130066}
-03/05/2022 03:22:39 - INFO - codeparrot_training - Step 32259: {'lr': 0.00045017895739025185, 'samples': 16517120, 'steps': 32259, 'loss/train': 1.5496797561645508}
-03/05/2022 03:22:41 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/05/2022 03:22:45 - INFO - codeparrot_training - Step 32260: {'lr': 0.0004501757783698154, 'samples': 16517632, 'steps': 32260, 'loss/train': 1.793108582496643}
-03/05/2022 03:22:48 - INFO - codeparrot_training - Step 32261: {'lr': 0.00045017259925918295, 'samples': 16518144, 'steps': 32261, 'loss/train': 1.7173904180526733}
-03/05/2022 03:22:52 - INFO - codeparrot_training - Step 32262: {'lr': 0.0004501694200583558, 'samples': 16518656, 'steps': 32262, 'loss/train': 1.8365219831466675}
-03/05/2022 03:22:52 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/05/2022 03:22:57 - INFO - codeparrot_training - Step 32263: {'lr': 0.0004501662407673354, 'samples': 16519168, 'steps': 32263, 'loss/train': 2.000492572784424}
-03/05/2022 03:23:00 - INFO - codeparrot_training - Step 32264: {'lr': 0.00045016306138612313, 'samples': 16519680, 'steps': 32264, 'loss/train': 1.648452877998352}
-03/05/2022 03:23:00 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/05/2022 03:23:05 - INFO - codeparrot_training - Step 32265: {'lr': 0.0004501598819147205, 'samples': 16520192, 'steps': 32265, 'loss/train': 0.06549766659736633}
-03/05/2022 03:23:08 - INFO - codeparrot_training - Step 32266: {'lr': 0.00045015670235312895, 'samples': 16520704, 'steps': 32266, 'loss/train': 2.324337959289551}
-03/05/2022 03:23:09 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/05/2022 03:23:14 - INFO - codeparrot_training - Step 32267: {'lr': 0.0004501535227013498, 'samples': 16521216, 'steps': 32267, 'loss/train': 1.3472681045532227}
-03/05/2022 03:23:17 - INFO - codeparrot_training - Step 32268: {'lr': 0.0004501503429593846, 'samples': 16521728, 'steps': 32268, 'loss/train': 1.4270840883255005}
-03/05/2022 03:23:17 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/05/2022 03:23:22 - INFO - codeparrot_training - Step 32269: {'lr': 0.0004501471631272348, 'samples': 16522240, 'steps': 32269, 'loss/train': 2.351712465286255}
-03/05/2022 03:23:25 - INFO - codeparrot_training - Step 32270: {'lr': 0.00045014398320490173, 'samples': 16522752, 'steps': 32270, 'loss/train': 1.6424205303192139}
-03/05/2022 03:23:25 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/05/2022 03:23:30 - INFO - codeparrot_training - Step 32271: {'lr': 0.00045014080319238686, 'samples': 16523264, 'steps': 32271, 'loss/train': 1.97561776638031}
-03/05/2022 03:23:34 - INFO - codeparrot_training - Step 32272: {'lr': 0.00045013762308969164, 'samples': 16523776, 'steps': 32272, 'loss/train': 2.1698272228240967}
-03/05/2022 03:23:34 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/05/2022 03:23:39 - INFO - codeparrot_training - Step 32273: {'lr': 0.00045013444289681757, 'samples': 16524288, 'steps': 32273, 'loss/train': 1.9056363105773926}
-03/05/2022 03:23:42 - INFO - codeparrot_training - Skipping example with length 553 (seq_length=1024)
-03/05/2022 03:23:44 - INFO - codeparrot_training - Step 32274: {'lr': 0.0004501312626137659, 'samples': 16524800, 'steps': 32274, 'loss/train': 1.9683963060379028}
-03/05/2022 03:23:47 - INFO - codeparrot_training - Step 32275: {'lr': 0.0004501280822405382, 'samples': 16525312, 'steps': 32275, 'loss/train': 2.3114662170410156}
-03/05/2022 03:23:50 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/05/2022 03:23:52 - INFO - codeparrot_training - Step 32276: {'lr': 0.00045012490177713586, 'samples': 16525824, 'steps': 32276, 'loss/train': 0.7880001664161682}
-03/05/2022 03:23:56 - INFO - codeparrot_training - Step 32277: {'lr': 0.00045012172122356036, 'samples': 16526336, 'steps': 32277, 'loss/train': 1.8203128576278687}
-03/05/2022 03:23:59 - INFO - codeparrot_training - Step 32278: {'lr': 0.0004501185405798131, 'samples': 16526848, 'steps': 32278, 'loss/train': 1.8460109233856201}
-03/05/2022 03:23:59 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/05/2022 03:24:04 - INFO - codeparrot_training - Step 32279: {'lr': 0.00045011535984589544, 'samples': 16527360, 'steps': 32279, 'loss/train': 1.252022385597229}
-03/05/2022 03:24:07 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/05/2022 03:24:09 - INFO - codeparrot_training - Step 32280: {'lr': 0.000450112179021809, 'samples': 16527872, 'steps': 32280, 'loss/train': 1.2211589813232422}
-03/05/2022 03:24:13 - INFO - codeparrot_training - Step 32281: {'lr': 0.00045010899810755506, 'samples': 16528384, 'steps': 32281, 'loss/train': 2.2352893352508545}
-03/05/2022 03:24:15 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/05/2022 03:24:18 - INFO - codeparrot_training - Step 32282: {'lr': 0.00045010581710313506, 'samples': 16528896, 'steps': 32282, 'loss/train': 1.7220207452774048}
-03/05/2022 03:24:21 - INFO - codeparrot_training - Step 32283: {'lr': 0.0004501026360085505, 'samples': 16529408, 'steps': 32283, 'loss/train': 1.5309308767318726}
-03/05/2022 03:24:24 - INFO - codeparrot_training - Step 32284: {'lr': 0.0004500994548238028, 'samples': 16529920, 'steps': 32284, 'loss/train': 2.028325080871582}
-03/05/2022 03:24:25 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/05/2022 03:24:29 - INFO - codeparrot_training - Step 32285: {'lr': 0.00045009627354889337, 'samples': 16530432, 'steps': 32285, 'loss/train': 1.9448999166488647}
-03/05/2022 03:24:33 - INFO - codeparrot_training - Step 32286: {'lr': 0.0004500930921838236, 'samples': 16530944, 'steps': 32286, 'loss/train': 1.9928890466690063}
-03/05/2022 03:24:33 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 03:24:38 - INFO - codeparrot_training - Step 32287: {'lr': 0.000450089910728595, 'samples': 16531456, 'steps': 32287, 'loss/train': 1.5635994672775269}
-03/05/2022 03:24:41 - INFO - codeparrot_training - Step 32288: {'lr': 0.0004500867291832089, 'samples': 16531968, 'steps': 32288, 'loss/train': 2.0142176151275635}
-03/05/2022 03:24:41 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/05/2022 03:24:46 - INFO - codeparrot_training - Step 32289: {'lr': 0.00045008354754766687, 'samples': 16532480, 'steps': 32289, 'loss/train': 1.439382553100586}
-03/05/2022 03:24:49 - INFO - codeparrot_training - Step 32290: {'lr': 0.0004500803658219703, 'samples': 16532992, 'steps': 32290, 'loss/train': 1.4623559713363647}
-03/05/2022 03:24:50 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/05/2022 03:24:55 - INFO - codeparrot_training - Step 32291: {'lr': 0.0004500771840061206, 'samples': 16533504, 'steps': 32291, 'loss/train': 1.6388386487960815}
-03/05/2022 03:24:58 - INFO - codeparrot_training - Step 32292: {'lr': 0.00045007400210011925, 'samples': 16534016, 'steps': 32292, 'loss/train': 3.134432077407837}
-03/05/2022 03:24:59 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 03:25:03 - INFO - codeparrot_training - Step 32293: {'lr': 0.0004500708201039676, 'samples': 16534528, 'steps': 32293, 'loss/train': 0.8969138264656067}
-03/05/2022 03:25:06 - INFO - codeparrot_training - Step 32294: {'lr': 0.0004500676380176671, 'samples': 16535040, 'steps': 32294, 'loss/train': 1.2729841470718384}
-03/05/2022 03:25:07 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/05/2022 03:25:12 - INFO - codeparrot_training - Step 32295: {'lr': 0.00045006445584121923, 'samples': 16535552, 'steps': 32295, 'loss/train': 1.509150505065918}
-03/05/2022 03:25:15 - INFO - codeparrot_training - Step 32296: {'lr': 0.00045006127357462533, 'samples': 16536064, 'steps': 32296, 'loss/train': 2.2414145469665527}
-03/05/2022 03:25:15 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/05/2022 03:25:20 - INFO - codeparrot_training - Step 32297: {'lr': 0.000450058091217887, 'samples': 16536576, 'steps': 32297, 'loss/train': 2.2631585597991943}
-03/05/2022 03:25:23 - INFO - codeparrot_training - Step 32298: {'lr': 0.0004500549087710056, 'samples': 16537088, 'steps': 32298, 'loss/train': 1.9179980754852295}
-03/05/2022 03:25:23 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/05/2022 03:25:28 - INFO - codeparrot_training - Step 32299: {'lr': 0.0004500517262339825, 'samples': 16537600, 'steps': 32299, 'loss/train': 2.2595155239105225}
-03/05/2022 03:25:32 - INFO - codeparrot_training - Step 32300: {'lr': 0.0004500485436068191, 'samples': 16538112, 'steps': 32300, 'loss/train': 1.7985758781433105}
-03/05/2022 03:25:32 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/05/2022 03:25:37 - INFO - codeparrot_training - Step 32301: {'lr': 0.0004500453608895171, 'samples': 16538624, 'steps': 32301, 'loss/train': 1.3893694877624512}
-03/05/2022 03:25:39 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/05/2022 03:25:42 - INFO - codeparrot_training - Step 32302: {'lr': 0.00045004217808207757, 'samples': 16539136, 'steps': 32302, 'loss/train': 1.904556393623352}
-03/05/2022 03:25:45 - INFO - codeparrot_training - Step 32303: {'lr': 0.0004500389951845022, 'samples': 16539648, 'steps': 32303, 'loss/train': 0.8378501534461975}
-03/05/2022 03:25:48 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/05/2022 03:25:50 - INFO - codeparrot_training - Step 32304: {'lr': 0.00045003581219679235, 'samples': 16540160, 'steps': 32304, 'loss/train': 1.7698394060134888}
-03/05/2022 03:25:54 - INFO - codeparrot_training - Step 32305: {'lr': 0.00045003262911894943, 'samples': 16540672, 'steps': 32305, 'loss/train': 1.7045574188232422}
-03/05/2022 03:25:56 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 03:25:59 - INFO - codeparrot_training - Step 32306: {'lr': 0.00045002944595097494, 'samples': 16541184, 'steps': 32306, 'loss/train': 1.4119954109191895}
-03/05/2022 03:26:02 - INFO - codeparrot_training - Step 32307: {'lr': 0.00045002626269287024, 'samples': 16541696, 'steps': 32307, 'loss/train': 1.9988905191421509}
-03/05/2022 03:26:05 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/05/2022 03:26:07 - INFO - codeparrot_training - Step 32308: {'lr': 0.00045002307934463673, 'samples': 16542208, 'steps': 32308, 'loss/train': 1.3723077774047852}
-03/05/2022 03:26:11 - INFO - codeparrot_training - Step 32309: {'lr': 0.000450019895906276, 'samples': 16542720, 'steps': 32309, 'loss/train': 1.920534610748291}
-03/05/2022 03:26:13 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/05/2022 03:26:16 - INFO - codeparrot_training - Step 32310: {'lr': 0.0004500167123777894, 'samples': 16543232, 'steps': 32310, 'loss/train': 1.4552727937698364}
-03/05/2022 03:26:19 - INFO - codeparrot_training - Step 32311: {'lr': 0.00045001352875917824, 'samples': 16543744, 'steps': 32311, 'loss/train': 1.1241849660873413}
-03/05/2022 03:26:22 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/05/2022 03:26:24 - INFO - codeparrot_training - Step 32312: {'lr': 0.00045001034505044415, 'samples': 16544256, 'steps': 32312, 'loss/train': 1.3802741765975952}
-03/05/2022 03:26:28 - INFO - codeparrot_training - Step 32313: {'lr': 0.00045000716125158846, 'samples': 16544768, 'steps': 32313, 'loss/train': 1.64714777469635}
-03/05/2022 03:26:30 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/05/2022 03:26:33 - INFO - codeparrot_training - Step 32314: {'lr': 0.0004500039773626127, 'samples': 16545280, 'steps': 32314, 'loss/train': 1.0032775402069092}
-03/05/2022 03:26:36 - INFO - codeparrot_training - Step 32315: {'lr': 0.00045000079338351805, 'samples': 16545792, 'steps': 32315, 'loss/train': 1.7638407945632935}
-03/05/2022 03:26:38 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/05/2022 03:26:41 - INFO - codeparrot_training - Step 32316: {'lr': 0.0004499976093143063, 'samples': 16546304, 'steps': 32316, 'loss/train': 1.1470493078231812}
-03/05/2022 03:26:44 - INFO - codeparrot_training - Step 32317: {'lr': 0.00044999442515497866, 'samples': 16546816, 'steps': 32317, 'loss/train': 0.05779756233096123}
-03/05/2022 03:26:47 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/05/2022 03:26:50 - INFO - codeparrot_training - Step 32318: {'lr': 0.0004499912409055367, 'samples': 16547328, 'steps': 32318, 'loss/train': 1.5817676782608032}
-03/05/2022 03:26:53 - INFO - codeparrot_training - Step 32319: {'lr': 0.0004499880565659816, 'samples': 16547840, 'steps': 32319, 'loss/train': 1.6074827909469604}
-03/05/2022 03:26:55 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 03:26:58 - INFO - codeparrot_training - Step 32320: {'lr': 0.0004499848721363151, 'samples': 16548352, 'steps': 32320, 'loss/train': 0.7577037811279297}
-03/05/2022 03:27:01 - INFO - codeparrot_training - Step 32321: {'lr': 0.0004499816876165385, 'samples': 16548864, 'steps': 32321, 'loss/train': 1.8371872901916504}
-03/05/2022 03:27:03 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/05/2022 03:27:06 - INFO - codeparrot_training - Step 32322: {'lr': 0.0004499785030066532, 'samples': 16549376, 'steps': 32322, 'loss/train': 1.3737050294876099}
-03/05/2022 03:27:10 - INFO - codeparrot_training - Step 32323: {'lr': 0.00044997531830666073, 'samples': 16549888, 'steps': 32323, 'loss/train': 1.1425515413284302}
-03/05/2022 03:27:11 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/05/2022 03:27:15 - INFO - codeparrot_training - Step 32324: {'lr': 0.00044997213351656237, 'samples': 16550400, 'steps': 32324, 'loss/train': 2.078904151916504}
-03/05/2022 03:27:18 - INFO - codeparrot_training - Step 32325: {'lr': 0.00044996894863635965, 'samples': 16550912, 'steps': 32325, 'loss/train': 1.033521294593811}
-03/05/2022 03:27:19 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 03:27:23 - INFO - codeparrot_training - Step 32326: {'lr': 0.00044996576366605415, 'samples': 16551424, 'steps': 32326, 'loss/train': 1.375506043434143}
-03/05/2022 03:27:27 - INFO - codeparrot_training - Step 32327: {'lr': 0.00044996257860564705, 'samples': 16551936, 'steps': 32327, 'loss/train': 1.5657107830047607}
-03/05/2022 03:27:28 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/05/2022 03:27:32 - INFO - codeparrot_training - Step 32328: {'lr': 0.0004499593934551399, 'samples': 16552448, 'steps': 32328, 'loss/train': 0.695310652256012}
-03/05/2022 03:27:35 - INFO - codeparrot_training - Step 32329: {'lr': 0.00044995620821453416, 'samples': 16552960, 'steps': 32329, 'loss/train': 2.174541711807251}
-03/05/2022 03:27:37 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/05/2022 03:27:40 - INFO - codeparrot_training - Step 32330: {'lr': 0.00044995302288383123, 'samples': 16553472, 'steps': 32330, 'loss/train': 1.5241491794586182}
-03/05/2022 03:27:44 - INFO - codeparrot_training - Step 32331: {'lr': 0.0004499498374630325, 'samples': 16553984, 'steps': 32331, 'loss/train': 0.1514754742383957}
-03/05/2022 03:27:45 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/05/2022 03:27:49 - INFO - codeparrot_training - Step 32332: {'lr': 0.0004499466519521396, 'samples': 16554496, 'steps': 32332, 'loss/train': 1.6864006519317627}
-03/05/2022 03:27:52 - INFO - codeparrot_training - Step 32333: {'lr': 0.00044994346635115367, 'samples': 16555008, 'steps': 32333, 'loss/train': 2.1539382934570312}
-03/05/2022 03:27:54 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/05/2022 03:27:57 - INFO - codeparrot_training - Step 32334: {'lr': 0.00044994028066007636, 'samples': 16555520, 'steps': 32334, 'loss/train': 1.7117948532104492}
-03/05/2022 03:28:00 - INFO - codeparrot_training - Step 32335: {'lr': 0.00044993709487890906, 'samples': 16556032, 'steps': 32335, 'loss/train': 1.5427757501602173}
-03/05/2022 03:28:02 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 03:28:06 - INFO - codeparrot_training - Step 32336: {'lr': 0.0004499339090076532, 'samples': 16556544, 'steps': 32336, 'loss/train': 2.479074716567993}
-03/05/2022 03:28:09 - INFO - codeparrot_training - Step 32337: {'lr': 0.0004499307230463102, 'samples': 16557056, 'steps': 32337, 'loss/train': 0.3770645558834076}
-03/05/2022 03:28:10 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/05/2022 03:28:14 - INFO - codeparrot_training - Step 32338: {'lr': 0.0004499275369948814, 'samples': 16557568, 'steps': 32338, 'loss/train': 1.9286540746688843}
-03/05/2022 03:28:17 - INFO - codeparrot_training - Step 32339: {'lr': 0.0004499243508533685, 'samples': 16558080, 'steps': 32339, 'loss/train': 1.272286295890808}
-03/05/2022 03:28:19 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/05/2022 03:28:22 - INFO - codeparrot_training - Step 32340: {'lr': 0.0004499211646217727, 'samples': 16558592, 'steps': 32340, 'loss/train': 1.1806715726852417}
-03/05/2022 03:28:26 - INFO - codeparrot_training - Step 32341: {'lr': 0.00044991797830009543, 'samples': 16559104, 'steps': 32341, 'loss/train': 1.5442988872528076}
-03/05/2022 03:28:27 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/05/2022 03:28:31 - INFO - codeparrot_training - Step 32342: {'lr': 0.00044991479188833826, 'samples': 16559616, 'steps': 32342, 'loss/train': 1.6451743841171265}
-03/05/2022 03:28:34 - INFO - codeparrot_training - Step 32343: {'lr': 0.0004499116053865026, 'samples': 16560128, 'steps': 32343, 'loss/train': 1.5627999305725098}
-03/05/2022 03:28:36 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/05/2022 03:28:39 - INFO - codeparrot_training - Step 32344: {'lr': 0.0004499084187945899, 'samples': 16560640, 'steps': 32344, 'loss/train': 1.28183114528656}
-03/05/2022 03:28:43 - INFO - codeparrot_training - Step 32345: {'lr': 0.0004499052321126015, 'samples': 16561152, 'steps': 32345, 'loss/train': 1.1448712348937988}
-03/05/2022 03:28:44 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/05/2022 03:28:48 - INFO - codeparrot_training - Step 32346: {'lr': 0.0004499020453405388, 'samples': 16561664, 'steps': 32346, 'loss/train': 1.6410918235778809}
-03/05/2022 03:28:51 - INFO - codeparrot_training - Step 32347: {'lr': 0.00044989885847840344, 'samples': 16562176, 'steps': 32347, 'loss/train': 0.5534372329711914}
-03/05/2022 03:28:53 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/05/2022 03:28:56 - INFO - codeparrot_training - Step 32348: {'lr': 0.0004498956715261967, 'samples': 16562688, 'steps': 32348, 'loss/train': 1.2939332723617554}
-03/05/2022 03:29:00 - INFO - codeparrot_training - Step 32349: {'lr': 0.00044989248448392007, 'samples': 16563200, 'steps': 32349, 'loss/train': 2.1184158325195312}
-03/05/2022 03:29:01 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/05/2022 03:29:05 - INFO - codeparrot_training - Step 32350: {'lr': 0.000449889297351575, 'samples': 16563712, 'steps': 32350, 'loss/train': 1.7678813934326172}
-03/05/2022 03:29:08 - INFO - codeparrot_training - Step 32351: {'lr': 0.0004498861101291628, 'samples': 16564224, 'steps': 32351, 'loss/train': 1.0438998937606812}
-03/05/2022 03:29:09 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/05/2022 03:29:13 - INFO - codeparrot_training - Step 32352: {'lr': 0.0004498829228166851, 'samples': 16564736, 'steps': 32352, 'loss/train': 2.2826428413391113}
-03/05/2022 03:29:16 - INFO - codeparrot_training - Step 32353: {'lr': 0.0004498797354141432, 'samples': 16565248, 'steps': 32353, 'loss/train': 1.643843650817871}
-03/05/2022 03:29:18 - INFO - codeparrot_training - Skipping example with length 7 (seq_length=1024)
-03/05/2022 03:29:21 - INFO - codeparrot_training - Step 32354: {'lr': 0.00044987654792153853, 'samples': 16565760, 'steps': 32354, 'loss/train': 1.048097848892212}
-03/05/2022 03:29:25 - INFO - codeparrot_training - Step 32355: {'lr': 0.0004498733603388726, 'samples': 16566272, 'steps': 32355, 'loss/train': 1.6934741735458374}
-03/05/2022 03:29:26 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/05/2022 03:29:30 - INFO - codeparrot_training - Step 32356: {'lr': 0.00044987017266614684, 'samples': 16566784, 'steps': 32356, 'loss/train': 2.504734516143799}
-03/05/2022 03:29:33 - INFO - codeparrot_training - Step 32357: {'lr': 0.00044986698490336263, 'samples': 16567296, 'steps': 32357, 'loss/train': 1.7436622381210327}
-03/05/2022 03:29:34 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 03:29:38 - INFO - codeparrot_training - Step 32358: {'lr': 0.0004498637970505215, 'samples': 16567808, 'steps': 32358, 'loss/train': 1.7143983840942383}
-03/05/2022 03:29:41 - INFO - codeparrot_training - Step 32359: {'lr': 0.0004498606091076248, 'samples': 16568320, 'steps': 32359, 'loss/train': 1.8568686246871948}
-03/05/2022 03:29:42 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/05/2022 03:29:47 - INFO - codeparrot_training - Step 32360: {'lr': 0.000449857421074674, 'samples': 16568832, 'steps': 32360, 'loss/train': 2.122437000274658}
-03/05/2022 03:29:50 - INFO - codeparrot_training - Step 32361: {'lr': 0.0004498542329516705, 'samples': 16569344, 'steps': 32361, 'loss/train': 1.5481361150741577}
-03/05/2022 03:29:52 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/05/2022 03:29:55 - INFO - codeparrot_training - Step 32362: {'lr': 0.00044985104473861583, 'samples': 16569856, 'steps': 32362, 'loss/train': 1.305768609046936}
-03/05/2022 03:29:58 - INFO - codeparrot_training - Step 32363: {'lr': 0.0004498478564355113, 'samples': 16570368, 'steps': 32363, 'loss/train': 1.6269898414611816}
-03/05/2022 03:30:00 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/05/2022 03:30:04 - INFO - codeparrot_training - Step 32364: {'lr': 0.0004498446680423584, 'samples': 16570880, 'steps': 32364, 'loss/train': 1.9101046323776245}
-03/05/2022 03:30:07 - INFO - codeparrot_training - Step 32365: {'lr': 0.0004498414795591586, 'samples': 16571392, 'steps': 32365, 'loss/train': 1.536567211151123}
-03/05/2022 03:30:09 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/05/2022 03:30:12 - INFO - codeparrot_training - Step 32366: {'lr': 0.00044983829098591336, 'samples': 16571904, 'steps': 32366, 'loss/train': 1.50094735622406}
-03/05/2022 03:30:15 - INFO - codeparrot_training - Step 32367: {'lr': 0.00044983510232262405, 'samples': 16572416, 'steps': 32367, 'loss/train': 1.4778085947036743}
-03/05/2022 03:30:17 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 03:30:21 - INFO - codeparrot_training - Step 32368: {'lr': 0.0004498319135692921, 'samples': 16572928, 'steps': 32368, 'loss/train': 2.0233843326568604}
-03/05/2022 03:30:24 - INFO - codeparrot_training - Step 32369: {'lr': 0.00044982872472591897, 'samples': 16573440, 'steps': 32369, 'loss/train': 1.9142979383468628}
-03/05/2022 03:30:25 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/05/2022 03:30:29 - INFO - codeparrot_training - Step 32370: {'lr': 0.00044982553579250606, 'samples': 16573952, 'steps': 32370, 'loss/train': 2.364659547805786}
-03/05/2022 03:30:32 - INFO - codeparrot_training - Step 32371: {'lr': 0.0004498223467690549, 'samples': 16574464, 'steps': 32371, 'loss/train': 1.2702393531799316}
-03/05/2022 03:30:34 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/05/2022 03:30:38 - INFO - codeparrot_training - Step 32372: {'lr': 0.0004498191576555669, 'samples': 16574976, 'steps': 32372, 'loss/train': 2.0149991512298584}
-03/05/2022 03:30:41 - INFO - codeparrot_training - Step 32373: {'lr': 0.00044981596845204344, 'samples': 16575488, 'steps': 32373, 'loss/train': 1.873853325843811}
-03/05/2022 03:30:43 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/05/2022 03:30:46 - INFO - codeparrot_training - Step 32374: {'lr': 0.00044981277915848595, 'samples': 16576000, 'steps': 32374, 'loss/train': 0.9891318082809448}
-03/05/2022 03:30:49 - INFO - codeparrot_training - Step 32375: {'lr': 0.00044980958977489593, 'samples': 16576512, 'steps': 32375, 'loss/train': 1.9771904945373535}
-03/05/2022 03:30:51 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/05/2022 03:30:54 - INFO - codeparrot_training - Step 32376: {'lr': 0.00044980640030127484, 'samples': 16577024, 'steps': 32376, 'loss/train': 1.327635645866394}
-03/05/2022 03:30:57 - INFO - codeparrot_training - Step 32377: {'lr': 0.00044980321073762405, 'samples': 16577536, 'steps': 32377, 'loss/train': 1.2788350582122803}
-03/05/2022 03:30:59 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/05/2022 03:31:03 - INFO - codeparrot_training - Step 32378: {'lr': 0.00044980002108394496, 'samples': 16578048, 'steps': 32378, 'loss/train': 1.1805237531661987}
-03/05/2022 03:31:06 - INFO - codeparrot_training - Step 32379: {'lr': 0.0004497968313402391, 'samples': 16578560, 'steps': 32379, 'loss/train': 1.724697232246399}
-03/05/2022 03:31:07 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/05/2022 03:31:11 - INFO - codeparrot_training - Step 32380: {'lr': 0.00044979364150650794, 'samples': 16579072, 'steps': 32380, 'loss/train': 2.061079978942871}
-03/05/2022 03:31:14 - INFO - codeparrot_training - Step 32381: {'lr': 0.00044979045158275273, 'samples': 16579584, 'steps': 32381, 'loss/train': 1.7152940034866333}
-03/05/2022 03:31:16 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/05/2022 03:31:20 - INFO - codeparrot_training - Step 32382: {'lr': 0.0004497872615689751, 'samples': 16580096, 'steps': 32382, 'loss/train': 1.9621801376342773}
-03/05/2022 03:31:23 - INFO - codeparrot_training - Step 32383: {'lr': 0.00044978407146517634, 'samples': 16580608, 'steps': 32383, 'loss/train': 0.3224453032016754}
-03/05/2022 03:31:24 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/05/2022 03:31:28 - INFO - codeparrot_training - Step 32384: {'lr': 0.0004497808812713581, 'samples': 16581120, 'steps': 32384, 'loss/train': 1.7872172594070435}
-03/05/2022 03:31:31 - INFO - codeparrot_training - Step 32385: {'lr': 0.00044977769098752154, 'samples': 16581632, 'steps': 32385, 'loss/train': 0.6527504920959473}
-03/05/2022 03:31:33 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/05/2022 03:31:37 - INFO - codeparrot_training - Step 32386: {'lr': 0.0004497745006136683, 'samples': 16582144, 'steps': 32386, 'loss/train': 1.9129481315612793}
-03/05/2022 03:31:40 - INFO - codeparrot_training - Step 32387: {'lr': 0.00044977131014979974, 'samples': 16582656, 'steps': 32387, 'loss/train': 1.2443722486495972}
-03/05/2022 03:31:41 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/05/2022 03:31:45 - INFO - codeparrot_training - Step 32388: {'lr': 0.0004497681195959173, 'samples': 16583168, 'steps': 32388, 'loss/train': 1.3849151134490967}
-03/05/2022 03:31:48 - INFO - codeparrot_training - Step 32389: {'lr': 0.0004497649289520224, 'samples': 16583680, 'steps': 32389, 'loss/train': 0.22375613451004028}
-03/05/2022 03:31:50 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/05/2022 03:31:54 - INFO - codeparrot_training - Step 32390: {'lr': 0.00044976173821811654, 'samples': 16584192, 'steps': 32390, 'loss/train': 1.9322353601455688}
-03/05/2022 03:31:57 - INFO - codeparrot_training - Step 32391: {'lr': 0.0004497585473942011, 'samples': 16584704, 'steps': 32391, 'loss/train': 2.339860439300537}
-03/05/2022 03:31:59 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/05/2022 03:32:02 - INFO - codeparrot_training - Step 32392: {'lr': 0.0004497553564802776, 'samples': 16585216, 'steps': 32392, 'loss/train': 1.9951239824295044}
-03/05/2022 03:32:05 - INFO - codeparrot_training - Step 32393: {'lr': 0.0004497521654763474, 'samples': 16585728, 'steps': 32393, 'loss/train': 1.1290035247802734}
-03/05/2022 03:32:07 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 03:32:10 - INFO - codeparrot_training - Step 32394: {'lr': 0.0004497489743824119, 'samples': 16586240, 'steps': 32394, 'loss/train': 2.451751470565796}
-03/05/2022 03:32:14 - INFO - codeparrot_training - Step 32395: {'lr': 0.0004497457831984727, 'samples': 16586752, 'steps': 32395, 'loss/train': 1.840139389038086}
-03/05/2022 03:32:15 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/05/2022 03:32:19 - INFO - codeparrot_training - Step 32396: {'lr': 0.00044974259192453103, 'samples': 16587264, 'steps': 32396, 'loss/train': 3.2688207626342773}
-03/05/2022 03:32:22 - INFO - codeparrot_training - Step 32397: {'lr': 0.0004497394005605885, 'samples': 16587776, 'steps': 32397, 'loss/train': 1.2105220556259155}
-03/05/2022 03:32:23 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/05/2022 03:32:27 - INFO - codeparrot_training - Step 32398: {'lr': 0.00044973620910664645, 'samples': 16588288, 'steps': 32398, 'loss/train': 1.652271032333374}
-03/05/2022 03:32:30 - INFO - codeparrot_training - Step 32399: {'lr': 0.00044973301756270635, 'samples': 16588800, 'steps': 32399, 'loss/train': 1.8055057525634766}
-03/05/2022 03:32:32 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/05/2022 03:32:36 - INFO - codeparrot_training - Step 32400: {'lr': 0.0004497298259287696, 'samples': 16589312, 'steps': 32400, 'loss/train': 1.1664719581604004}
-03/05/2022 03:32:39 - INFO - codeparrot_training - Step 32401: {'lr': 0.00044972663420483774, 'samples': 16589824, 'steps': 32401, 'loss/train': 1.8694703578948975}
-03/05/2022 03:32:40 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/05/2022 03:32:44 - INFO - codeparrot_training - Step 32402: {'lr': 0.00044972344239091206, 'samples': 16590336, 'steps': 32402, 'loss/train': 0.6922139525413513}
-03/05/2022 03:32:47 - INFO - codeparrot_training - Step 32403: {'lr': 0.0004497202504869941, 'samples': 16590848, 'steps': 32403, 'loss/train': 2.0953924655914307}
-03/05/2022 03:32:49 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/05/2022 03:32:53 - INFO - codeparrot_training - Step 32404: {'lr': 0.0004497170584930853, 'samples': 16591360, 'steps': 32404, 'loss/train': 1.4079786539077759}
-03/05/2022 03:32:56 - INFO - codeparrot_training - Step 32405: {'lr': 0.0004497138664091871, 'samples': 16591872, 'steps': 32405, 'loss/train': 1.5663923025131226}
-03/05/2022 03:32:59 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/05/2022 03:33:01 - INFO - codeparrot_training - Step 32406: {'lr': 0.00044971067423530087, 'samples': 16592384, 'steps': 32406, 'loss/train': 2.1109795570373535}
-03/05/2022 03:33:05 - INFO - codeparrot_training - Step 32407: {'lr': 0.0004497074819714281, 'samples': 16592896, 'steps': 32407, 'loss/train': 1.9000605344772339}
-03/05/2022 03:33:07 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/05/2022 03:33:10 - INFO - codeparrot_training - Step 32408: {'lr': 0.00044970428961757026, 'samples': 16593408, 'steps': 32408, 'loss/train': 1.4713932275772095}
-03/05/2022 03:33:13 - INFO - codeparrot_training - Step 32409: {'lr': 0.00044970109717372864, 'samples': 16593920, 'steps': 32409, 'loss/train': 2.370283603668213}
-03/05/2022 03:33:15 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/05/2022 03:33:18 - INFO - codeparrot_training - Step 32410: {'lr': 0.0004496979046399049, 'samples': 16594432, 'steps': 32410, 'loss/train': 2.0688838958740234}
-03/05/2022 03:33:21 - INFO - codeparrot_training - Step 32411: {'lr': 0.00044969471201610037, 'samples': 16594944, 'steps': 32411, 'loss/train': 1.4880917072296143}
-03/05/2022 03:33:24 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/05/2022 03:33:27 - INFO - codeparrot_training - Step 32412: {'lr': 0.00044969151930231643, 'samples': 16595456, 'steps': 32412, 'loss/train': 1.0462182760238647}
-03/05/2022 03:33:30 - INFO - codeparrot_training - Step 32413: {'lr': 0.00044968832649855455, 'samples': 16595968, 'steps': 32413, 'loss/train': 1.2924472093582153}
-03/05/2022 03:33:32 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/05/2022 03:33:35 - INFO - codeparrot_training - Step 32414: {'lr': 0.00044968513360481624, 'samples': 16596480, 'steps': 32414, 'loss/train': 2.191091775894165}
-03/05/2022 03:33:39 - INFO - codeparrot_training - Step 32415: {'lr': 0.0004496819406211029, 'samples': 16596992, 'steps': 32415, 'loss/train': 1.7938324213027954}
-03/05/2022 03:33:41 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/05/2022 03:33:44 - INFO - codeparrot_training - Step 32416: {'lr': 0.0004496787475474159, 'samples': 16597504, 'steps': 32416, 'loss/train': 1.386800765991211}
-03/05/2022 03:33:47 - INFO - codeparrot_training - Step 32417: {'lr': 0.00044967555438375675, 'samples': 16598016, 'steps': 32417, 'loss/train': 1.829301118850708}
-03/05/2022 03:33:50 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/05/2022 03:33:52 - INFO - codeparrot_training - Step 32418: {'lr': 0.0004496723611301269, 'samples': 16598528, 'steps': 32418, 'loss/train': 2.0702104568481445}
-03/05/2022 03:33:55 - INFO - codeparrot_training - Step 32419: {'lr': 0.00044966916778652776, 'samples': 16599040, 'steps': 32419, 'loss/train': 1.859232783317566}
-03/05/2022 03:33:58 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/05/2022 03:34:01 - INFO - codeparrot_training - Step 32420: {'lr': 0.0004496659743529608, 'samples': 16599552, 'steps': 32420, 'loss/train': 2.0355241298675537}
-03/05/2022 03:34:04 - INFO - codeparrot_training - Step 32421: {'lr': 0.00044966278082942746, 'samples': 16600064, 'steps': 32421, 'loss/train': 2.117018938064575}
-03/05/2022 03:34:07 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/05/2022 03:34:09 - INFO - codeparrot_training - Step 32422: {'lr': 0.000449659587215929, 'samples': 16600576, 'steps': 32422, 'loss/train': 1.6251906156539917}
-03/05/2022 03:34:12 - INFO - codeparrot_training - Step 32423: {'lr': 0.0004496563935124672, 'samples': 16601088, 'steps': 32423, 'loss/train': 1.58332097530365}
-03/05/2022 03:34:15 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 03:34:18 - INFO - codeparrot_training - Step 32424: {'lr': 0.0004496531997190432, 'samples': 16601600, 'steps': 32424, 'loss/train': 1.653906226158142}
-03/05/2022 03:34:21 - INFO - codeparrot_training - Step 32425: {'lr': 0.0004496500058356586, 'samples': 16602112, 'steps': 32425, 'loss/train': 2.4441323280334473}
-03/05/2022 03:34:23 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/05/2022 03:34:26 - INFO - codeparrot_training - Step 32426: {'lr': 0.00044964681186231473, 'samples': 16602624, 'steps': 32426, 'loss/train': 2.017547607421875}
-03/05/2022 03:34:29 - INFO - codeparrot_training - Step 32427: {'lr': 0.0004496436177990131, 'samples': 16603136, 'steps': 32427, 'loss/train': 1.3357704877853394}
-03/05/2022 03:34:31 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/05/2022 03:34:34 - INFO - codeparrot_training - Step 32428: {'lr': 0.0004496404236457552, 'samples': 16603648, 'steps': 32428, 'loss/train': 1.8977664709091187}
-03/05/2022 03:34:37 - INFO - codeparrot_training - Step 32429: {'lr': 0.0004496372294025424, 'samples': 16604160, 'steps': 32429, 'loss/train': 1.779232382774353}
-03/05/2022 03:34:40 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/05/2022 03:34:43 - INFO - codeparrot_training - Step 32430: {'lr': 0.00044963403506937603, 'samples': 16604672, 'steps': 32430, 'loss/train': 1.7111198902130127}
-03/05/2022 03:34:46 - INFO - codeparrot_training - Step 32431: {'lr': 0.00044963084064625775, 'samples': 16605184, 'steps': 32431, 'loss/train': 2.3616256713867188}
-03/05/2022 03:34:49 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 03:34:51 - INFO - codeparrot_training - Step 32432: {'lr': 0.00044962764613318886, 'samples': 16605696, 'steps': 32432, 'loss/train': 1.4934982061386108}
-03/05/2022 03:34:54 - INFO - codeparrot_training - Step 32433: {'lr': 0.00044962445153017087, 'samples': 16606208, 'steps': 32433, 'loss/train': 1.1801294088363647}
-03/05/2022 03:34:57 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/05/2022 03:35:00 - INFO - codeparrot_training - Step 32434: {'lr': 0.00044962125683720513, 'samples': 16606720, 'steps': 32434, 'loss/train': 1.0857094526290894}
-03/05/2022 03:35:03 - INFO - codeparrot_training - Step 32435: {'lr': 0.0004496180620542931, 'samples': 16607232, 'steps': 32435, 'loss/train': 2.293895721435547}
-03/05/2022 03:35:05 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/05/2022 03:35:08 - INFO - codeparrot_training - Step 32436: {'lr': 0.00044961486718143634, 'samples': 16607744, 'steps': 32436, 'loss/train': 1.5313867330551147}
-03/05/2022 03:35:12 - INFO - codeparrot_training - Step 32437: {'lr': 0.0004496116722186362, 'samples': 16608256, 'steps': 32437, 'loss/train': 1.0509016513824463}
-03/05/2022 03:35:14 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/05/2022 03:35:17 - INFO - codeparrot_training - Step 32438: {'lr': 0.00044960847716589403, 'samples': 16608768, 'steps': 32438, 'loss/train': 0.3248491883277893}
-03/05/2022 03:35:20 - INFO - codeparrot_training - Step 32439: {'lr': 0.00044960528202321143, 'samples': 16609280, 'steps': 32439, 'loss/train': 2.612558126449585}
-03/05/2022 03:35:23 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/05/2022 03:35:25 - INFO - codeparrot_training - Step 32440: {'lr': 0.0004496020867905898, 'samples': 16609792, 'steps': 32440, 'loss/train': 1.4358925819396973}
-03/05/2022 03:35:28 - INFO - codeparrot_training - Step 32441: {'lr': 0.00044959889146803047, 'samples': 16610304, 'steps': 32441, 'loss/train': 0.838768720626831}
-03/05/2022 03:35:31 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/05/2022 03:35:34 - INFO - codeparrot_training - Step 32442: {'lr': 0.00044959569605553494, 'samples': 16610816, 'steps': 32442, 'loss/train': 1.6564538478851318}
-03/05/2022 03:35:37 - INFO - codeparrot_training - Step 32443: {'lr': 0.00044959250055310473, 'samples': 16611328, 'steps': 32443, 'loss/train': 6.891471862792969}
-03/05/2022 03:35:40 - INFO - codeparrot_training - Step 32444: {'lr': 0.00044958930496074125, 'samples': 16611840, 'steps': 32444, 'loss/train': 1.9294989109039307}
-03/05/2022 03:35:40 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 03:35:45 - INFO - codeparrot_training - Step 32445: {'lr': 0.0004495861092784459, 'samples': 16612352, 'steps': 32445, 'loss/train': 2.1351335048675537}
-03/05/2022 03:35:48 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/05/2022 03:35:51 - INFO - codeparrot_training - Step 32446: {'lr': 0.00044958291350622007, 'samples': 16612864, 'steps': 32446, 'loss/train': 1.3726168870925903}
-03/05/2022 03:35:54 - INFO - codeparrot_training - Step 32447: {'lr': 0.0004495797176440653, 'samples': 16613376, 'steps': 32447, 'loss/train': 0.21007169783115387}
-03/05/2022 03:35:56 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/05/2022 03:35:59 - INFO - codeparrot_training - Step 32448: {'lr': 0.000449576521691983, 'samples': 16613888, 'steps': 32448, 'loss/train': 0.7761363387107849}
-03/05/2022 03:36:02 - INFO - codeparrot_training - Step 32449: {'lr': 0.00044957332564997453, 'samples': 16614400, 'steps': 32449, 'loss/train': 1.8157480955123901}
-03/05/2022 03:36:05 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/05/2022 03:36:08 - INFO - codeparrot_training - Step 32450: {'lr': 0.0004495701295180414, 'samples': 16614912, 'steps': 32450, 'loss/train': 0.6970478296279907}
-03/05/2022 03:36:11 - INFO - codeparrot_training - Step 32451: {'lr': 0.0004495669332961852, 'samples': 16615424, 'steps': 32451, 'loss/train': 2.6068992614746094}
-03/05/2022 03:36:13 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/05/2022 03:36:16 - INFO - codeparrot_training - Step 32452: {'lr': 0.0004495637369844071, 'samples': 16615936, 'steps': 32452, 'loss/train': 1.5784298181533813}
-03/05/2022 03:36:19 - INFO - codeparrot_training - Step 32453: {'lr': 0.0004495605405827087, 'samples': 16616448, 'steps': 32453, 'loss/train': 2.0984599590301514}
-03/05/2022 03:36:22 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/05/2022 03:36:25 - INFO - codeparrot_training - Step 32454: {'lr': 0.00044955734409109135, 'samples': 16616960, 'steps': 32454, 'loss/train': 1.4528424739837646}
-03/05/2022 03:36:28 - INFO - codeparrot_training - Step 32455: {'lr': 0.0004495541475095566, 'samples': 16617472, 'steps': 32455, 'loss/train': 1.8714102506637573}
-03/05/2022 03:36:30 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/05/2022 03:36:33 - INFO - codeparrot_training - Step 32456: {'lr': 0.0004495509508381058, 'samples': 16617984, 'steps': 32456, 'loss/train': 1.0773853063583374}
-03/05/2022 03:36:36 - INFO - codeparrot_training - Step 32457: {'lr': 0.00044954775407674035, 'samples': 16618496, 'steps': 32457, 'loss/train': 1.935227870941162}
-03/05/2022 03:36:39 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/05/2022 03:36:42 - INFO - codeparrot_training - Step 32458: {'lr': 0.00044954455722546186, 'samples': 16619008, 'steps': 32458, 'loss/train': 1.594394564628601}
-03/05/2022 03:36:45 - INFO - codeparrot_training - Step 32459: {'lr': 0.0004495413602842716, 'samples': 16619520, 'steps': 32459, 'loss/train': 1.6186305284500122}
-03/05/2022 03:36:47 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/05/2022 03:36:50 - INFO - codeparrot_training - Step 32460: {'lr': 0.00044953816325317116, 'samples': 16620032, 'steps': 32460, 'loss/train': 2.327622413635254}
-03/05/2022 03:36:53 - INFO - codeparrot_training - Step 32461: {'lr': 0.0004495349661321618, 'samples': 16620544, 'steps': 32461, 'loss/train': 1.9374125003814697}
-03/05/2022 03:36:56 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/05/2022 03:36:58 - INFO - codeparrot_training - Step 32462: {'lr': 0.0004495317689212452, 'samples': 16621056, 'steps': 32462, 'loss/train': 2.392763137817383}
-03/05/2022 03:37:02 - INFO - codeparrot_training - Step 32463: {'lr': 0.0004495285716204226, 'samples': 16621568, 'steps': 32463, 'loss/train': 1.5358927249908447}
-03/05/2022 03:37:04 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/05/2022 03:37:07 - INFO - codeparrot_training - Step 32464: {'lr': 0.00044952537422969545, 'samples': 16622080, 'steps': 32464, 'loss/train': 1.72659170627594}
-03/05/2022 03:37:10 - INFO - codeparrot_training - Step 32465: {'lr': 0.0004495221767490653, 'samples': 16622592, 'steps': 32465, 'loss/train': 1.0177475214004517}
-03/05/2022 03:37:12 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/05/2022 03:37:15 - INFO - codeparrot_training - Step 32466: {'lr': 0.00044951897917853355, 'samples': 16623104, 'steps': 32466, 'loss/train': 1.385553002357483}
-03/05/2022 03:37:19 - INFO - codeparrot_training - Step 32467: {'lr': 0.0004495157815181016, 'samples': 16623616, 'steps': 32467, 'loss/train': 2.412515640258789}
-03/05/2022 03:37:20 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/05/2022 03:37:24 - INFO - codeparrot_training - Step 32468: {'lr': 0.00044951258376777094, 'samples': 16624128, 'steps': 32468, 'loss/train': 2.292073965072632}
-03/05/2022 03:37:27 - INFO - codeparrot_training - Step 32469: {'lr': 0.00044950938592754297, 'samples': 16624640, 'steps': 32469, 'loss/train': 2.0912930965423584}
-03/05/2022 03:37:29 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/05/2022 03:37:32 - INFO - codeparrot_training - Step 32470: {'lr': 0.00044950618799741913, 'samples': 16625152, 'steps': 32470, 'loss/train': 1.9644982814788818}
-03/05/2022 03:37:35 - INFO - codeparrot_training - Step 32471: {'lr': 0.0004495029899774009, 'samples': 16625664, 'steps': 32471, 'loss/train': 1.2476348876953125}
-03/05/2022 03:37:37 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 03:37:41 - INFO - codeparrot_training - Step 32472: {'lr': 0.00044949979186748967, 'samples': 16626176, 'steps': 32472, 'loss/train': 1.8012356758117676}
-03/05/2022 03:37:44 - INFO - codeparrot_training - Step 32473: {'lr': 0.00044949659366768697, 'samples': 16626688, 'steps': 32473, 'loss/train': 1.7679799795150757}
-03/05/2022 03:37:46 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 03:37:49 - INFO - codeparrot_training - Step 32474: {'lr': 0.00044949339537799415, 'samples': 16627200, 'steps': 32474, 'loss/train': 1.7883752584457397}
-03/05/2022 03:37:52 - INFO - codeparrot_training - Step 32475: {'lr': 0.0004494901969984127, 'samples': 16627712, 'steps': 32475, 'loss/train': 2.003964900970459}
-03/05/2022 03:37:54 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/05/2022 03:37:58 - INFO - codeparrot_training - Step 32476: {'lr': 0.000449486998528944, 'samples': 16628224, 'steps': 32476, 'loss/train': 0.9493886828422546}
-03/05/2022 03:38:01 - INFO - codeparrot_training - Step 32477: {'lr': 0.00044948379996958963, 'samples': 16628736, 'steps': 32477, 'loss/train': 2.0646250247955322}
-03/05/2022 03:38:02 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/05/2022 03:38:06 - INFO - codeparrot_training - Step 32478: {'lr': 0.00044948060132035087, 'samples': 16629248, 'steps': 32478, 'loss/train': 0.6245011687278748}
-03/05/2022 03:38:09 - INFO - codeparrot_training - Step 32479: {'lr': 0.00044947740258122925, 'samples': 16629760, 'steps': 32479, 'loss/train': 1.4211345911026}
-03/05/2022 03:38:11 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/05/2022 03:38:14 - INFO - codeparrot_training - Step 32480: {'lr': 0.00044947420375222614, 'samples': 16630272, 'steps': 32480, 'loss/train': 2.0545804500579834}
-03/05/2022 03:38:18 - INFO - codeparrot_training - Step 32481: {'lr': 0.00044947100483334315, 'samples': 16630784, 'steps': 32481, 'loss/train': 1.4362703561782837}
-03/05/2022 03:38:19 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/05/2022 03:38:23 - INFO - codeparrot_training - Step 32482: {'lr': 0.0004494678058245815, 'samples': 16631296, 'steps': 32482, 'loss/train': 1.420967936515808}
-03/05/2022 03:38:26 - INFO - codeparrot_training - Step 32483: {'lr': 0.00044946460672594277, 'samples': 16631808, 'steps': 32483, 'loss/train': 1.9648367166519165}
-03/05/2022 03:38:27 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/05/2022 03:38:31 - INFO - codeparrot_training - Step 32484: {'lr': 0.0004494614075374283, 'samples': 16632320, 'steps': 32484, 'loss/train': 1.3338794708251953}
-03/05/2022 03:38:34 - INFO - codeparrot_training - Step 32485: {'lr': 0.0004494582082590397, 'samples': 16632832, 'steps': 32485, 'loss/train': 1.271061897277832}
-03/05/2022 03:38:36 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/05/2022 03:38:40 - INFO - codeparrot_training - Step 32486: {'lr': 0.0004494550088907783, 'samples': 16633344, 'steps': 32486, 'loss/train': 2.485957145690918}
-03/05/2022 03:38:43 - INFO - codeparrot_training - Step 32487: {'lr': 0.00044945180943264544, 'samples': 16633856, 'steps': 32487, 'loss/train': 1.375436782836914}
-03/05/2022 03:38:44 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/05/2022 03:38:48 - INFO - codeparrot_training - Step 32488: {'lr': 0.00044944860988464276, 'samples': 16634368, 'steps': 32488, 'loss/train': 1.2037006616592407}
-03/05/2022 03:38:51 - INFO - codeparrot_training - Step 32489: {'lr': 0.0004494454102467716, 'samples': 16634880, 'steps': 32489, 'loss/train': 1.753919243812561}
-03/05/2022 03:38:52 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/05/2022 03:38:56 - INFO - codeparrot_training - Step 32490: {'lr': 0.00044944221051903345, 'samples': 16635392, 'steps': 32490, 'loss/train': 1.0960522890090942}
-03/05/2022 03:38:59 - INFO - codeparrot_training - Step 32491: {'lr': 0.0004494390107014297, 'samples': 16635904, 'steps': 32491, 'loss/train': 2.0408830642700195}
-03/05/2022 03:39:01 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/05/2022 03:39:05 - INFO - codeparrot_training - Step 32492: {'lr': 0.0004494358107939618, 'samples': 16636416, 'steps': 32492, 'loss/train': 1.9325721263885498}
-03/05/2022 03:39:08 - INFO - codeparrot_training - Step 32493: {'lr': 0.0004494326107966311, 'samples': 16636928, 'steps': 32493, 'loss/train': 2.104515790939331}
-03/05/2022 03:39:09 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 03:39:13 - INFO - codeparrot_training - Step 32494: {'lr': 0.0004494294107094393, 'samples': 16637440, 'steps': 32494, 'loss/train': 1.7816121578216553}
-03/05/2022 03:39:16 - INFO - codeparrot_training - Step 32495: {'lr': 0.00044942621053238764, 'samples': 16637952, 'steps': 32495, 'loss/train': 2.0925283432006836}
-03/05/2022 03:39:18 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/05/2022 03:39:22 - INFO - codeparrot_training - Step 32496: {'lr': 0.00044942301026547755, 'samples': 16638464, 'steps': 32496, 'loss/train': 1.8603712320327759}
-03/05/2022 03:39:25 - INFO - codeparrot_training - Step 32497: {'lr': 0.0004494198099087106, 'samples': 16638976, 'steps': 32497, 'loss/train': 2.3530497550964355}
-03/05/2022 03:39:26 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 03:39:30 - INFO - codeparrot_training - Step 32498: {'lr': 0.00044941660946208806, 'samples': 16639488, 'steps': 32498, 'loss/train': 1.3806134462356567}
-03/05/2022 03:39:33 - INFO - codeparrot_training - Step 32499: {'lr': 0.00044941340892561154, 'samples': 16640000, 'steps': 32499, 'loss/train': 1.5196136236190796}
-03/05/2022 03:39:35 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/05/2022 03:39:39 - INFO - codeparrot_training - Step 32500: {'lr': 0.00044941020829928247, 'samples': 16640512, 'steps': 32500, 'loss/train': 1.8932324647903442}
-03/05/2022 03:39:42 - INFO - codeparrot_training - Step 32501: {'lr': 0.00044940700758310214, 'samples': 16641024, 'steps': 32501, 'loss/train': 0.6498285531997681}
-03/05/2022 03:39:43 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/05/2022 03:39:47 - INFO - codeparrot_training - Step 32502: {'lr': 0.00044940380677707214, 'samples': 16641536, 'steps': 32502, 'loss/train': 0.18013617396354675}
-03/05/2022 03:39:51 - INFO - codeparrot_training - Step 32503: {'lr': 0.00044940060588119393, 'samples': 16642048, 'steps': 32503, 'loss/train': 2.164668560028076}
-03/05/2022 03:39:53 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/05/2022 03:39:56 - INFO - codeparrot_training - Step 32504: {'lr': 0.00044939740489546875, 'samples': 16642560, 'steps': 32504, 'loss/train': 1.910035252571106}
-03/05/2022 03:39:59 - INFO - codeparrot_training - Step 32505: {'lr': 0.0004493942038198983, 'samples': 16643072, 'steps': 32505, 'loss/train': 1.783010482788086}
-03/05/2022 03:40:01 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/05/2022 03:40:04 - INFO - codeparrot_training - Step 32506: {'lr': 0.0004493910026544838, 'samples': 16643584, 'steps': 32506, 'loss/train': 1.813146710395813}
-03/05/2022 03:40:07 - INFO - codeparrot_training - Step 32507: {'lr': 0.0004493878013992268, 'samples': 16644096, 'steps': 32507, 'loss/train': 1.222377061843872}
-03/05/2022 03:40:09 - INFO - codeparrot_training - Skipping example with length 983 (seq_length=1024)
-03/05/2022 03:40:13 - INFO - codeparrot_training - Step 32508: {'lr': 0.0004493846000541287, 'samples': 16644608, 'steps': 32508, 'loss/train': 2.4136996269226074}
-03/05/2022 03:40:16 - INFO - codeparrot_training - Step 32509: {'lr': 0.00044938139861919115, 'samples': 16645120, 'steps': 32509, 'loss/train': 1.6823498010635376}
-03/05/2022 03:40:18 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 03:40:21 - INFO - codeparrot_training - Step 32510: {'lr': 0.00044937819709441523, 'samples': 16645632, 'steps': 32510, 'loss/train': 1.9083900451660156}
-03/05/2022 03:40:24 - INFO - codeparrot_training - Step 32511: {'lr': 0.00044937499547980265, 'samples': 16646144, 'steps': 32511, 'loss/train': 1.6409327983856201}
-03/05/2022 03:40:26 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/05/2022 03:40:30 - INFO - codeparrot_training - Step 32512: {'lr': 0.00044937179377535475, 'samples': 16646656, 'steps': 32512, 'loss/train': 1.6740772724151611}
-03/05/2022 03:40:33 - INFO - codeparrot_training - Step 32513: {'lr': 0.00044936859198107306, 'samples': 16647168, 'steps': 32513, 'loss/train': 2.3721959590911865}
-03/05/2022 03:40:34 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/05/2022 03:40:38 - INFO - codeparrot_training - Step 32514: {'lr': 0.0004493653900969589, 'samples': 16647680, 'steps': 32514, 'loss/train': 1.899351954460144}
-03/05/2022 03:40:41 - INFO - codeparrot_training - Step 32515: {'lr': 0.0004493621881230138, 'samples': 16648192, 'steps': 32515, 'loss/train': 2.058785915374756}
-03/05/2022 03:40:44 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/05/2022 03:40:46 - INFO - codeparrot_training - Step 32516: {'lr': 0.00044935898605923916, 'samples': 16648704, 'steps': 32516, 'loss/train': 1.2470084428787231}
-03/05/2022 03:40:50 - INFO - codeparrot_training - Step 32517: {'lr': 0.0004493557839056364, 'samples': 16649216, 'steps': 32517, 'loss/train': 1.9156990051269531}
-03/05/2022 03:40:52 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/05/2022 03:40:55 - INFO - codeparrot_training - Step 32518: {'lr': 0.00044935258166220704, 'samples': 16649728, 'steps': 32518, 'loss/train': 1.7598196268081665}
-03/05/2022 03:40:58 - INFO - codeparrot_training - Step 32519: {'lr': 0.00044934937932895246, 'samples': 16650240, 'steps': 32519, 'loss/train': 2.3987717628479004}
-03/05/2022 03:41:00 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 03:41:03 - INFO - codeparrot_training - Step 32520: {'lr': 0.0004493461769058742, 'samples': 16650752, 'steps': 32520, 'loss/train': 1.7775099277496338}
-03/05/2022 03:41:07 - INFO - codeparrot_training - Step 32521: {'lr': 0.00044934297439297357, 'samples': 16651264, 'steps': 32521, 'loss/train': 1.3451353311538696}
-03/05/2022 03:41:08 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/05/2022 03:41:12 - INFO - codeparrot_training - Step 32522: {'lr': 0.0004493397717902521, 'samples': 16651776, 'steps': 32522, 'loss/train': 0.7490481734275818}
-03/05/2022 03:41:15 - INFO - codeparrot_training - Step 32523: {'lr': 0.00044933656909771117, 'samples': 16652288, 'steps': 32523, 'loss/train': 1.1000535488128662}
-03/05/2022 03:41:18 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/05/2022 03:41:20 - INFO - codeparrot_training - Step 32524: {'lr': 0.00044933336631535224, 'samples': 16652800, 'steps': 32524, 'loss/train': 1.5737924575805664}
-03/05/2022 03:41:24 - INFO - codeparrot_training - Step 32525: {'lr': 0.0004493301634431768, 'samples': 16653312, 'steps': 32525, 'loss/train': 2.393526315689087}
-03/05/2022 03:41:26 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/05/2022 03:41:29 - INFO - codeparrot_training - Step 32526: {'lr': 0.0004493269604811863, 'samples': 16653824, 'steps': 32526, 'loss/train': 1.6190117597579956}
-03/05/2022 03:41:32 - INFO - codeparrot_training - Step 32527: {'lr': 0.000449323757429382, 'samples': 16654336, 'steps': 32527, 'loss/train': 1.4296857118606567}
-03/05/2022 03:41:34 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/05/2022 03:41:37 - INFO - codeparrot_training - Step 32528: {'lr': 0.00044932055428776566, 'samples': 16654848, 'steps': 32528, 'loss/train': 0.22194428741931915}
-03/05/2022 03:41:40 - INFO - codeparrot_training - Step 32529: {'lr': 0.00044931735105633853, 'samples': 16655360, 'steps': 32529, 'loss/train': 1.9686369895935059}
-03/05/2022 03:41:42 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 03:41:46 - INFO - codeparrot_training - Step 32530: {'lr': 0.00044931414773510207, 'samples': 16655872, 'steps': 32530, 'loss/train': 2.4895174503326416}
-03/05/2022 03:41:49 - INFO - codeparrot_training - Step 32531: {'lr': 0.00044931094432405766, 'samples': 16656384, 'steps': 32531, 'loss/train': 0.12578052282333374}
-03/05/2022 03:41:51 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/05/2022 03:41:54 - INFO - codeparrot_training - Step 32532: {'lr': 0.00044930774082320684, 'samples': 16656896, 'steps': 32532, 'loss/train': 1.8606159687042236}
-03/05/2022 03:41:57 - INFO - codeparrot_training - Step 32533: {'lr': 0.00044930453723255107, 'samples': 16657408, 'steps': 32533, 'loss/train': 1.4303772449493408}
-03/05/2022 03:41:59 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/05/2022 03:42:03 - INFO - codeparrot_training - Step 32534: {'lr': 0.0004493013335520917, 'samples': 16657920, 'steps': 32534, 'loss/train': 1.8415628671646118}
-03/05/2022 03:42:06 - INFO - codeparrot_training - Step 32535: {'lr': 0.00044929812978183024, 'samples': 16658432, 'steps': 32535, 'loss/train': 1.287062644958496}
-03/05/2022 03:42:08 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 03:42:11 - INFO - codeparrot_training - Step 32536: {'lr': 0.0004492949259217681, 'samples': 16658944, 'steps': 32536, 'loss/train': 1.820600986480713}
-03/05/2022 03:42:14 - INFO - codeparrot_training - Step 32537: {'lr': 0.00044929172197190684, 'samples': 16659456, 'steps': 32537, 'loss/train': 0.12635044753551483}
-03/05/2022 03:42:16 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/05/2022 03:42:20 - INFO - codeparrot_training - Step 32538: {'lr': 0.00044928851793224765, 'samples': 16659968, 'steps': 32538, 'loss/train': 1.5570791959762573}
-03/05/2022 03:42:23 - INFO - codeparrot_training - Step 32539: {'lr': 0.00044928531380279224, 'samples': 16660480, 'steps': 32539, 'loss/train': 2.6861183643341064}
-03/05/2022 03:42:25 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 03:42:28 - INFO - codeparrot_training - Step 32540: {'lr': 0.00044928210958354196, 'samples': 16660992, 'steps': 32540, 'loss/train': 1.9324324131011963}
-03/05/2022 03:42:31 - INFO - codeparrot_training - Step 32541: {'lr': 0.0004492789052744982, 'samples': 16661504, 'steps': 32541, 'loss/train': 1.546565055847168}
-03/05/2022 03:42:33 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/05/2022 03:42:37 - INFO - codeparrot_training - Step 32542: {'lr': 0.0004492757008756624, 'samples': 16662016, 'steps': 32542, 'loss/train': 2.003206968307495}
-03/05/2022 03:42:40 - INFO - codeparrot_training - Step 32543: {'lr': 0.0004492724963870361, 'samples': 16662528, 'steps': 32543, 'loss/train': 1.0537060499191284}
-03/05/2022 03:42:42 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/05/2022 03:42:46 - INFO - codeparrot_training - Step 32544: {'lr': 0.00044926929180862064, 'samples': 16663040, 'steps': 32544, 'loss/train': 1.7150063514709473}
-03/05/2022 03:42:49 - INFO - codeparrot_training - Step 32545: {'lr': 0.00044926608714041763, 'samples': 16663552, 'steps': 32545, 'loss/train': 2.3302531242370605}
-03/05/2022 03:42:52 - INFO - codeparrot_training - Step 32546: {'lr': 0.0004492628823824282, 'samples': 16664064, 'steps': 32546, 'loss/train': 1.3007757663726807}
-03/05/2022 03:42:54 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/05/2022 03:42:57 - INFO - codeparrot_training - Step 32547: {'lr': 0.0004492596775346541, 'samples': 16664576, 'steps': 32547, 'loss/train': 1.6382144689559937}
-03/05/2022 03:43:01 - INFO - codeparrot_training - Step 32548: {'lr': 0.0004492564725970967, 'samples': 16665088, 'steps': 32548, 'loss/train': 1.7310819625854492}
-03/05/2022 03:43:02 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/05/2022 03:43:06 - INFO - codeparrot_training - Step 32549: {'lr': 0.00044925326756975736, 'samples': 16665600, 'steps': 32549, 'loss/train': 2.4321587085723877}
-03/05/2022 03:43:09 - INFO - codeparrot_training - Step 32550: {'lr': 0.00044925006245263757, 'samples': 16666112, 'steps': 32550, 'loss/train': 0.09825701266527176}
-03/05/2022 03:43:11 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 03:43:14 - INFO - codeparrot_training - Step 32551: {'lr': 0.0004492468572457388, 'samples': 16666624, 'steps': 32551, 'loss/train': 1.290374517440796}
-03/05/2022 03:43:18 - INFO - codeparrot_training - Step 32552: {'lr': 0.0004492436519490625, 'samples': 16667136, 'steps': 32552, 'loss/train': 1.6578922271728516}
-03/05/2022 03:43:19 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/05/2022 03:43:23 - INFO - codeparrot_training - Step 32553: {'lr': 0.00044924044656260997, 'samples': 16667648, 'steps': 32553, 'loss/train': 1.7882187366485596}
-03/05/2022 03:43:26 - INFO - codeparrot_training - Step 32554: {'lr': 0.00044923724108638285, 'samples': 16668160, 'steps': 32554, 'loss/train': 1.343475341796875}
-03/05/2022 03:43:27 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 03:43:31 - INFO - codeparrot_training - Step 32555: {'lr': 0.00044923403552038255, 'samples': 16668672, 'steps': 32555, 'loss/train': 1.6840152740478516}
-03/05/2022 03:43:34 - INFO - codeparrot_training - Step 32556: {'lr': 0.0004492308298646104, 'samples': 16669184, 'steps': 32556, 'loss/train': 1.643323302268982}
-03/05/2022 03:43:36 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/05/2022 03:43:40 - INFO - codeparrot_training - Step 32557: {'lr': 0.0004492276241190679, 'samples': 16669696, 'steps': 32557, 'loss/train': 2.28226375579834}
-03/05/2022 03:43:43 - INFO - codeparrot_training - Step 32558: {'lr': 0.0004492244182837565, 'samples': 16670208, 'steps': 32558, 'loss/train': 1.1694397926330566}
-03/05/2022 03:43:44 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/05/2022 03:43:48 - INFO - codeparrot_training - Step 32559: {'lr': 0.00044922121235867776, 'samples': 16670720, 'steps': 32559, 'loss/train': 1.9928205013275146}
-03/05/2022 03:43:51 - INFO - codeparrot_training - Step 32560: {'lr': 0.00044921800634383294, 'samples': 16671232, 'steps': 32560, 'loss/train': 1.6142312288284302}
-03/05/2022 03:43:52 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/05/2022 03:43:57 - INFO - codeparrot_training - Step 32561: {'lr': 0.0004492148002392235, 'samples': 16671744, 'steps': 32561, 'loss/train': 2.203921318054199}
-03/05/2022 03:44:00 - INFO - codeparrot_training - Step 32562: {'lr': 0.000449211594044851, 'samples': 16672256, 'steps': 32562, 'loss/train': 1.9882726669311523}
-03/05/2022 03:44:01 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/05/2022 03:44:05 - INFO - codeparrot_training - Step 32563: {'lr': 0.0004492083877607168, 'samples': 16672768, 'steps': 32563, 'loss/train': 1.7191581726074219}
-03/05/2022 03:44:08 - INFO - codeparrot_training - Step 32564: {'lr': 0.00044920518138682244, 'samples': 16673280, 'steps': 32564, 'loss/train': 1.5999605655670166}
-03/05/2022 03:44:09 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/05/2022 03:44:13 - INFO - codeparrot_training - Step 32565: {'lr': 0.00044920197492316925, 'samples': 16673792, 'steps': 32565, 'loss/train': 1.6284418106079102}
-03/05/2022 03:44:17 - INFO - codeparrot_training - Step 32566: {'lr': 0.00044919876836975876, 'samples': 16674304, 'steps': 32566, 'loss/train': 1.8037230968475342}
-03/05/2022 03:44:18 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/05/2022 03:44:22 - INFO - codeparrot_training - Step 32567: {'lr': 0.0004491955617265924, 'samples': 16674816, 'steps': 32567, 'loss/train': 1.6405211687088013}
-03/05/2022 03:44:26 - INFO - codeparrot_training - Step 32568: {'lr': 0.0004491923549936715, 'samples': 16675328, 'steps': 32568, 'loss/train': 2.170546770095825}
-03/05/2022 03:44:29 - INFO - codeparrot_training - Step 32569: {'lr': 0.0004491891481709977, 'samples': 16675840, 'steps': 32569, 'loss/train': 0.10429401695728302}
-03/05/2022 03:44:29 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/05/2022 03:44:34 - INFO - codeparrot_training - Step 32570: {'lr': 0.0004491859412585723, 'samples': 16676352, 'steps': 32570, 'loss/train': 1.8292902708053589}
-03/05/2022 03:44:37 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/05/2022 03:44:39 - INFO - codeparrot_training - Step 32571: {'lr': 0.0004491827342563968, 'samples': 16676864, 'steps': 32571, 'loss/train': 1.5793107748031616}
-03/05/2022 03:44:43 - INFO - codeparrot_training - Step 32572: {'lr': 0.0004491795271644726, 'samples': 16677376, 'steps': 32572, 'loss/train': 1.586366057395935}
-03/05/2022 03:44:45 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/05/2022 03:44:48 - INFO - codeparrot_training - Step 32573: {'lr': 0.0004491763199828012, 'samples': 16677888, 'steps': 32573, 'loss/train': 2.0771255493164062}
-03/05/2022 03:44:51 - INFO - codeparrot_training - Step 32574: {'lr': 0.00044917311271138393, 'samples': 16678400, 'steps': 32574, 'loss/train': 1.9533355236053467}
-03/05/2022 03:44:54 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 03:44:56 - INFO - codeparrot_training - Step 32575: {'lr': 0.00044916990535022244, 'samples': 16678912, 'steps': 32575, 'loss/train': 0.7579390406608582}
-03/05/2022 03:44:59 - INFO - codeparrot_training - Step 32576: {'lr': 0.00044916669789931806, 'samples': 16679424, 'steps': 32576, 'loss/train': 1.5620167255401611}
-03/05/2022 03:45:02 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/05/2022 03:45:05 - INFO - codeparrot_training - Step 32577: {'lr': 0.0004491634903586722, 'samples': 16679936, 'steps': 32577, 'loss/train': 1.672410249710083}
-03/05/2022 03:45:08 - INFO - codeparrot_training - Step 32578: {'lr': 0.00044916028272828636, 'samples': 16680448, 'steps': 32578, 'loss/train': 1.8122777938842773}
-03/05/2022 03:45:10 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/05/2022 03:45:13 - INFO - codeparrot_training - Step 32579: {'lr': 0.00044915707500816206, 'samples': 16680960, 'steps': 32579, 'loss/train': 1.3082588911056519}
-03/05/2022 03:45:16 - INFO - codeparrot_training - Step 32580: {'lr': 0.0004491538671983005, 'samples': 16681472, 'steps': 32580, 'loss/train': 3.292508363723755}
-03/05/2022 03:45:19 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/05/2022 03:45:21 - INFO - codeparrot_training - Step 32581: {'lr': 0.00044915065929870335, 'samples': 16681984, 'steps': 32581, 'loss/train': 1.6692408323287964}
-03/05/2022 03:45:25 - INFO - codeparrot_training - Step 32582: {'lr': 0.00044914745130937204, 'samples': 16682496, 'steps': 32582, 'loss/train': 1.2074205875396729}
-03/05/2022 03:45:27 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/05/2022 03:45:30 - INFO - codeparrot_training - Step 32583: {'lr': 0.0004491442432303079, 'samples': 16683008, 'steps': 32583, 'loss/train': 1.8213645219802856}
-03/05/2022 03:45:33 - INFO - codeparrot_training - Step 32584: {'lr': 0.0004491410350615124, 'samples': 16683520, 'steps': 32584, 'loss/train': 1.433095097541809}
-03/05/2022 03:45:35 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/05/2022 03:45:38 - INFO - codeparrot_training - Step 32585: {'lr': 0.0004491378268029871, 'samples': 16684032, 'steps': 32585, 'loss/train': 1.6470701694488525}
-03/05/2022 03:45:42 - INFO - codeparrot_training - Step 32586: {'lr': 0.00044913461845473335, 'samples': 16684544, 'steps': 32586, 'loss/train': 1.6011825799942017}
-03/05/2022 03:45:43 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/05/2022 03:45:47 - INFO - codeparrot_training - Step 32587: {'lr': 0.0004491314100167526, 'samples': 16685056, 'steps': 32587, 'loss/train': 1.8967292308807373}
-03/05/2022 03:45:50 - INFO - codeparrot_training - Step 32588: {'lr': 0.00044912820148904634, 'samples': 16685568, 'steps': 32588, 'loss/train': 1.568588376045227}
-03/05/2022 03:45:52 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/05/2022 03:45:55 - INFO - codeparrot_training - Step 32589: {'lr': 0.0004491249928716159, 'samples': 16686080, 'steps': 32589, 'loss/train': 1.8458131551742554}
-03/05/2022 03:45:58 - INFO - codeparrot_training - Step 32590: {'lr': 0.0004491217841644629, 'samples': 16686592, 'steps': 32590, 'loss/train': 1.2073935270309448}
-03/05/2022 03:46:00 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/05/2022 03:46:04 - INFO - codeparrot_training - Step 32591: {'lr': 0.0004491185753675886, 'samples': 16687104, 'steps': 32591, 'loss/train': 1.447007417678833}
-03/05/2022 03:46:07 - INFO - codeparrot_training - Step 32592: {'lr': 0.0004491153664809947, 'samples': 16687616, 'steps': 32592, 'loss/train': 1.4809558391571045}
-03/05/2022 03:46:09 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 03:46:12 - INFO - codeparrot_training - Step 32593: {'lr': 0.00044911215750468236, 'samples': 16688128, 'steps': 32593, 'loss/train': 1.675031065940857}
-03/05/2022 03:46:15 - INFO - codeparrot_training - Step 32594: {'lr': 0.0004491089484386531, 'samples': 16688640, 'steps': 32594, 'loss/train': 1.9420222043991089}
-03/05/2022 03:46:17 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 03:46:21 - INFO - codeparrot_training - Step 32595: {'lr': 0.0004491057392829086, 'samples': 16689152, 'steps': 32595, 'loss/train': 1.6752437353134155}
-03/05/2022 03:46:24 - INFO - codeparrot_training - Step 32596: {'lr': 0.00044910253003745007, 'samples': 16689664, 'steps': 32596, 'loss/train': 0.919418454170227}
-03/05/2022 03:46:26 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/05/2022 03:46:29 - INFO - codeparrot_training - Step 32597: {'lr': 0.00044909932070227887, 'samples': 16690176, 'steps': 32597, 'loss/train': 1.9615058898925781}
-03/05/2022 03:46:32 - INFO - codeparrot_training - Step 32598: {'lr': 0.00044909611127739676, 'samples': 16690688, 'steps': 32598, 'loss/train': 1.6287546157836914}
-03/05/2022 03:46:34 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/05/2022 03:46:38 - INFO - codeparrot_training - Step 32599: {'lr': 0.00044909290176280495, 'samples': 16691200, 'steps': 32599, 'loss/train': 2.3242855072021484}
-03/05/2022 03:46:41 - INFO - codeparrot_training - Step 32600: {'lr': 0.00044908969215850495, 'samples': 16691712, 'steps': 32600, 'loss/train': 1.300263524055481}
-03/05/2022 03:46:43 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/05/2022 03:46:46 - INFO - codeparrot_training - Step 32601: {'lr': 0.0004490864824644982, 'samples': 16692224, 'steps': 32601, 'loss/train': 1.586312174797058}
-03/05/2022 03:46:49 - INFO - codeparrot_training - Step 32602: {'lr': 0.0004490832726807862, 'samples': 16692736, 'steps': 32602, 'loss/train': 1.4740346670150757}
-03/05/2022 03:46:51 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/05/2022 03:46:55 - INFO - codeparrot_training - Step 32603: {'lr': 0.0004490800628073703, 'samples': 16693248, 'steps': 32603, 'loss/train': 2.284289836883545}
-03/05/2022 03:46:58 - INFO - codeparrot_training - Step 32604: {'lr': 0.000449076852844252, 'samples': 16693760, 'steps': 32604, 'loss/train': 2.293776750564575}
-03/05/2022 03:47:03 - INFO - codeparrot_training - Step 32605: {'lr': 0.0004490736427914327, 'samples': 16694272, 'steps': 32605, 'loss/train': 2.3977556228637695}
-03/05/2022 03:47:06 - INFO - codeparrot_training - Step 32606: {'lr': 0.000449070432648914, 'samples': 16694784, 'steps': 32606, 'loss/train': 2.1151010990142822}
-03/05/2022 03:47:08 - INFO - codeparrot_training - Skipping example with length 285 (seq_length=1024)
-03/05/2022 03:47:11 - INFO - codeparrot_training - Step 32607: {'lr': 0.0004490672224166972, 'samples': 16695296, 'steps': 32607, 'loss/train': 2.4286179542541504}
-03/05/2022 03:47:15 - INFO - codeparrot_training - Step 32608: {'lr': 0.00044906401209478367, 'samples': 16695808, 'steps': 32608, 'loss/train': 2.4963057041168213}
-03/05/2022 03:47:16 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/05/2022 03:47:20 - INFO - codeparrot_training - Step 32609: {'lr': 0.00044906080168317507, 'samples': 16696320, 'steps': 32609, 'loss/train': 1.8330910205841064}
-03/05/2022 03:47:23 - INFO - codeparrot_training - Step 32610: {'lr': 0.0004490575911818727, 'samples': 16696832, 'steps': 32610, 'loss/train': 0.46499234437942505}
-03/05/2022 03:47:25 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/05/2022 03:47:28 - INFO - codeparrot_training - Step 32611: {'lr': 0.0004490543805908781, 'samples': 16697344, 'steps': 32611, 'loss/train': 0.8260604739189148}
-03/05/2022 03:47:32 - INFO - codeparrot_training - Step 32612: {'lr': 0.00044905116991019264, 'samples': 16697856, 'steps': 32612, 'loss/train': 2.194272994995117}
-03/05/2022 03:47:33 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 03:47:37 - INFO - codeparrot_training - Step 32613: {'lr': 0.00044904795913981775, 'samples': 16698368, 'steps': 32613, 'loss/train': 0.8410437703132629}
-03/05/2022 03:47:40 - INFO - codeparrot_training - Step 32614: {'lr': 0.00044904474827975506, 'samples': 16698880, 'steps': 32614, 'loss/train': 2.218437433242798}
-03/05/2022 03:47:42 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/05/2022 03:47:45 - INFO - codeparrot_training - Step 32615: {'lr': 0.00044904153733000575, 'samples': 16699392, 'steps': 32615, 'loss/train': 1.7397236824035645}
-03/05/2022 03:47:49 - INFO - codeparrot_training - Step 32616: {'lr': 0.0004490383262905714, 'samples': 16699904, 'steps': 32616, 'loss/train': 1.3464069366455078}
-03/05/2022 03:47:50 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/05/2022 03:47:54 - INFO - codeparrot_training - Step 32617: {'lr': 0.00044903511516145353, 'samples': 16700416, 'steps': 32617, 'loss/train': 1.8454314470291138}
-03/05/2022 03:47:57 - INFO - codeparrot_training - Step 32618: {'lr': 0.0004490319039426535, 'samples': 16700928, 'steps': 32618, 'loss/train': 1.8288780450820923}
-03/05/2022 03:47:59 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/05/2022 03:48:03 - INFO - codeparrot_training - Step 32619: {'lr': 0.0004490286926341727, 'samples': 16701440, 'steps': 32619, 'loss/train': 1.689068078994751}
-03/05/2022 03:48:06 - INFO - codeparrot_training - Step 32620: {'lr': 0.0004490254812360126, 'samples': 16701952, 'steps': 32620, 'loss/train': 1.2634406089782715}
-03/05/2022 03:48:11 - INFO - codeparrot_training - Step 32621: {'lr': 0.0004490222697481748, 'samples': 16702464, 'steps': 32621, 'loss/train': 1.8520931005477905}
-03/05/2022 03:48:14 - INFO - codeparrot_training - Step 32622: {'lr': 0.00044901905817066055, 'samples': 16702976, 'steps': 32622, 'loss/train': 1.114019751548767}
-03/05/2022 03:48:16 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 03:48:20 - INFO - codeparrot_training - Step 32623: {'lr': 0.00044901584650347147, 'samples': 16703488, 'steps': 32623, 'loss/train': 1.8870620727539062}
-03/05/2022 03:48:23 - INFO - codeparrot_training - Step 32624: {'lr': 0.00044901263474660894, 'samples': 16704000, 'steps': 32624, 'loss/train': 2.325376510620117}
-03/05/2022 03:48:24 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/05/2022 03:48:28 - INFO - codeparrot_training - Step 32625: {'lr': 0.0004490094229000743, 'samples': 16704512, 'steps': 32625, 'loss/train': 2.400545120239258}
-03/05/2022 03:48:31 - INFO - codeparrot_training - Step 32626: {'lr': 0.00044900621096386904, 'samples': 16705024, 'steps': 32626, 'loss/train': 2.415570020675659}
-03/05/2022 03:48:33 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/05/2022 03:48:37 - INFO - codeparrot_training - Step 32627: {'lr': 0.00044900299893799476, 'samples': 16705536, 'steps': 32627, 'loss/train': 1.5444202423095703}
-03/05/2022 03:48:40 - INFO - codeparrot_training - Step 32628: {'lr': 0.0004489997868224528, 'samples': 16706048, 'steps': 32628, 'loss/train': 1.923972725868225}
-03/05/2022 03:48:41 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/05/2022 03:48:45 - INFO - codeparrot_training - Step 32629: {'lr': 0.00044899657461724453, 'samples': 16706560, 'steps': 32629, 'loss/train': 1.7271745204925537}
-03/05/2022 03:48:48 - INFO - codeparrot_training - Step 32630: {'lr': 0.00044899336232237156, 'samples': 16707072, 'steps': 32630, 'loss/train': 1.820676326751709}
-03/05/2022 03:48:50 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 03:48:54 - INFO - codeparrot_training - Step 32631: {'lr': 0.0004489901499378352, 'samples': 16707584, 'steps': 32631, 'loss/train': 1.829119086265564}
-03/05/2022 03:48:57 - INFO - codeparrot_training - Step 32632: {'lr': 0.00044898693746363695, 'samples': 16708096, 'steps': 32632, 'loss/train': 1.2774642705917358}
-03/05/2022 03:48:59 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/05/2022 03:49:02 - INFO - codeparrot_training - Step 32633: {'lr': 0.00044898372489977825, 'samples': 16708608, 'steps': 32633, 'loss/train': 1.8329066038131714}
-03/05/2022 03:49:05 - INFO - codeparrot_training - Step 32634: {'lr': 0.0004489805122462606, 'samples': 16709120, 'steps': 32634, 'loss/train': 2.4088149070739746}
-03/05/2022 03:49:07 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/05/2022 03:49:11 - INFO - codeparrot_training - Step 32635: {'lr': 0.0004489772995030853, 'samples': 16709632, 'steps': 32635, 'loss/train': 2.5353541374206543}
-03/05/2022 03:49:14 - INFO - codeparrot_training - Step 32636: {'lr': 0.00044897408667025397, 'samples': 16710144, 'steps': 32636, 'loss/train': 1.9096039533615112}
-03/05/2022 03:49:15 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/05/2022 03:49:19 - INFO - codeparrot_training - Step 32637: {'lr': 0.000448970873747768, 'samples': 16710656, 'steps': 32637, 'loss/train': 1.9969711303710938}
-03/05/2022 03:49:22 - INFO - codeparrot_training - Step 32638: {'lr': 0.0004489676607356288, 'samples': 16711168, 'steps': 32638, 'loss/train': 1.8620306253433228}
-03/05/2022 03:49:23 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/05/2022 03:49:28 - INFO - codeparrot_training - Step 32639: {'lr': 0.00044896444763383787, 'samples': 16711680, 'steps': 32639, 'loss/train': 1.1733413934707642}
-03/05/2022 03:49:31 - INFO - codeparrot_training - Step 32640: {'lr': 0.00044896123444239654, 'samples': 16712192, 'steps': 32640, 'loss/train': 1.7918188571929932}
-03/05/2022 03:49:32 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/05/2022 03:49:36 - INFO - codeparrot_training - Step 32641: {'lr': 0.00044895802116130644, 'samples': 16712704, 'steps': 32641, 'loss/train': 1.6710946559906006}
-03/05/2022 03:49:39 - INFO - codeparrot_training - Step 32642: {'lr': 0.0004489548077905689, 'samples': 16713216, 'steps': 32642, 'loss/train': 0.8930895328521729}
-03/05/2022 03:49:41 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/05/2022 03:49:45 - INFO - codeparrot_training - Step 32643: {'lr': 0.0004489515943301854, 'samples': 16713728, 'steps': 32643, 'loss/train': 1.493677020072937}
-03/05/2022 03:49:48 - INFO - codeparrot_training - Step 32644: {'lr': 0.0004489483807801574, 'samples': 16714240, 'steps': 32644, 'loss/train': 2.630521774291992}
-03/05/2022 03:49:49 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/05/2022 03:49:53 - INFO - codeparrot_training - Step 32645: {'lr': 0.00044894516714048626, 'samples': 16714752, 'steps': 32645, 'loss/train': 1.6930238008499146}
-03/05/2022 03:49:56 - INFO - codeparrot_training - Step 32646: {'lr': 0.0004489419534111736, 'samples': 16715264, 'steps': 32646, 'loss/train': 2.1759676933288574}
-03/05/2022 03:49:58 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/05/2022 03:50:02 - INFO - codeparrot_training - Step 32647: {'lr': 0.0004489387395922207, 'samples': 16715776, 'steps': 32647, 'loss/train': 1.4858109951019287}
-03/05/2022 03:50:05 - INFO - codeparrot_training - Step 32648: {'lr': 0.00044893552568362903, 'samples': 16716288, 'steps': 32648, 'loss/train': 1.5872927904129028}
-03/05/2022 03:50:06 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/05/2022 03:50:10 - INFO - codeparrot_training - Step 32649: {'lr': 0.0004489323116854002, 'samples': 16716800, 'steps': 32649, 'loss/train': 1.7567414045333862}
-03/05/2022 03:50:13 - INFO - codeparrot_training - Step 32650: {'lr': 0.00044892909759753545, 'samples': 16717312, 'steps': 32650, 'loss/train': 2.0136494636535645}
-03/05/2022 03:50:15 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/05/2022 03:50:18 - INFO - codeparrot_training - Step 32651: {'lr': 0.00044892588342003637, 'samples': 16717824, 'steps': 32651, 'loss/train': 2.0238683223724365}
-03/05/2022 03:50:22 - INFO - codeparrot_training - Step 32652: {'lr': 0.00044892266915290435, 'samples': 16718336, 'steps': 32652, 'loss/train': 2.0528876781463623}
-03/05/2022 03:50:23 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/05/2022 03:50:27 - INFO - codeparrot_training - Step 32653: {'lr': 0.00044891945479614084, 'samples': 16718848, 'steps': 32653, 'loss/train': 2.0141665935516357}
-03/05/2022 03:50:30 - INFO - codeparrot_training - Step 32654: {'lr': 0.00044891624034974726, 'samples': 16719360, 'steps': 32654, 'loss/train': 2.152963638305664}
-03/05/2022 03:50:32 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/05/2022 03:50:35 - INFO - codeparrot_training - Step 32655: {'lr': 0.00044891302581372513, 'samples': 16719872, 'steps': 32655, 'loss/train': 1.153235673904419}
-03/05/2022 03:50:39 - INFO - codeparrot_training - Step 32656: {'lr': 0.00044890981118807585, 'samples': 16720384, 'steps': 32656, 'loss/train': 1.2853738069534302}
-03/05/2022 03:50:40 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 03:50:44 - INFO - codeparrot_training - Step 32657: {'lr': 0.00044890659647280084, 'samples': 16720896, 'steps': 32657, 'loss/train': 2.67225980758667}
-03/05/2022 03:50:47 - INFO - codeparrot_training - Step 32658: {'lr': 0.0004489033816679016, 'samples': 16721408, 'steps': 32658, 'loss/train': 0.6578690409660339}
-03/05/2022 03:50:49 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/05/2022 03:50:52 - INFO - codeparrot_training - Step 32659: {'lr': 0.0004489001667733796, 'samples': 16721920, 'steps': 32659, 'loss/train': 1.5650949478149414}
-03/05/2022 03:50:55 - INFO - codeparrot_training - Step 32660: {'lr': 0.0004488969517892363, 'samples': 16722432, 'steps': 32660, 'loss/train': 2.210993528366089}
-03/05/2022 03:50:57 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/05/2022 03:51:01 - INFO - codeparrot_training - Step 32661: {'lr': 0.000448893736715473, 'samples': 16722944, 'steps': 32661, 'loss/train': 1.9084727764129639}
-03/05/2022 03:51:04 - INFO - codeparrot_training - Step 32662: {'lr': 0.0004488905215520913, 'samples': 16723456, 'steps': 32662, 'loss/train': 2.1088318824768066}
-03/05/2022 03:51:05 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/05/2022 03:51:09 - INFO - codeparrot_training - Step 32663: {'lr': 0.00044888730629909256, 'samples': 16723968, 'steps': 32663, 'loss/train': 1.6365065574645996}
-03/05/2022 03:51:12 - INFO - codeparrot_training - Step 32664: {'lr': 0.00044888409095647833, 'samples': 16724480, 'steps': 32664, 'loss/train': 2.3002421855926514}
-03/05/2022 03:51:13 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/05/2022 03:51:18 - INFO - codeparrot_training - Step 32665: {'lr': 0.00044888087552424997, 'samples': 16724992, 'steps': 32665, 'loss/train': 3.2875540256500244}
-03/05/2022 03:51:21 - INFO - codeparrot_training - Step 32666: {'lr': 0.00044887766000240893, 'samples': 16725504, 'steps': 32666, 'loss/train': 1.6707509756088257}
-03/05/2022 03:51:22 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/05/2022 03:51:26 - INFO - codeparrot_training - Step 32667: {'lr': 0.0004488744443909567, 'samples': 16726016, 'steps': 32667, 'loss/train': 1.344260573387146}
-03/05/2022 03:51:29 - INFO - codeparrot_training - Step 32668: {'lr': 0.0004488712286898947, 'samples': 16726528, 'steps': 32668, 'loss/train': 0.09129302948713303}
-03/05/2022 03:51:31 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/05/2022 03:51:35 - INFO - codeparrot_training - Step 32669: {'lr': 0.0004488680128992244, 'samples': 16727040, 'steps': 32669, 'loss/train': 1.31582772731781}
-03/05/2022 03:51:38 - INFO - codeparrot_training - Step 32670: {'lr': 0.00044886479701894736, 'samples': 16727552, 'steps': 32670, 'loss/train': 1.8459174633026123}
-03/05/2022 03:51:40 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/05/2022 03:51:43 - INFO - codeparrot_training - Step 32671: {'lr': 0.00044886158104906476, 'samples': 16728064, 'steps': 32671, 'loss/train': 1.97783362865448}
-03/05/2022 03:51:46 - INFO - codeparrot_training - Step 32672: {'lr': 0.0004488583649895782, 'samples': 16728576, 'steps': 32672, 'loss/train': 1.5821096897125244}
-03/05/2022 03:51:48 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/05/2022 03:51:52 - INFO - codeparrot_training - Step 32673: {'lr': 0.00044885514884048926, 'samples': 16729088, 'steps': 32673, 'loss/train': 1.4637360572814941}
-03/05/2022 03:51:55 - INFO - codeparrot_training - Step 32674: {'lr': 0.0004488519326017991, 'samples': 16729600, 'steps': 32674, 'loss/train': 1.3454618453979492}
-03/05/2022 03:51:57 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/05/2022 03:52:00 - INFO - codeparrot_training - Step 32675: {'lr': 0.0004488487162735094, 'samples': 16730112, 'steps': 32675, 'loss/train': 2.1471030712127686}
-03/05/2022 03:52:03 - INFO - codeparrot_training - Step 32676: {'lr': 0.00044884549985562165, 'samples': 16730624, 'steps': 32676, 'loss/train': 1.0928417444229126}
-03/05/2022 03:52:05 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/05/2022 03:52:08 - INFO - codeparrot_training - Step 32677: {'lr': 0.000448842283348137, 'samples': 16731136, 'steps': 32677, 'loss/train': 2.022397518157959}
-03/05/2022 03:52:12 - INFO - codeparrot_training - Step 32678: {'lr': 0.0004488390667510572, 'samples': 16731648, 'steps': 32678, 'loss/train': 1.9457756280899048}
-03/05/2022 03:52:13 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/05/2022 03:52:17 - INFO - codeparrot_training - Step 32679: {'lr': 0.00044883585006438354, 'samples': 16732160, 'steps': 32679, 'loss/train': 1.6074765920639038}
-03/05/2022 03:52:20 - INFO - codeparrot_training - Step 32680: {'lr': 0.0004488326332881175, 'samples': 16732672, 'steps': 32680, 'loss/train': 1.228408694267273}
-03/05/2022 03:52:23 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/05/2022 03:52:26 - INFO - codeparrot_training - Step 32681: {'lr': 0.0004488294164222606, 'samples': 16733184, 'steps': 32681, 'loss/train': 1.343674659729004}
-03/05/2022 03:52:29 - INFO - codeparrot_training - Step 32682: {'lr': 0.0004488261994668142, 'samples': 16733696, 'steps': 32682, 'loss/train': 2.043595314025879}
-03/05/2022 03:52:31 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/05/2022 03:52:34 - INFO - codeparrot_training - Step 32683: {'lr': 0.00044882298242177976, 'samples': 16734208, 'steps': 32683, 'loss/train': 1.8504143953323364}
-03/05/2022 03:52:37 - INFO - codeparrot_training - Step 32684: {'lr': 0.00044881976528715877, 'samples': 16734720, 'steps': 32684, 'loss/train': 1.6843420267105103}
-03/05/2022 03:52:40 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/05/2022 03:52:42 - INFO - codeparrot_training - Step 32685: {'lr': 0.0004488165480629527, 'samples': 16735232, 'steps': 32685, 'loss/train': 2.2880945205688477}
-03/05/2022 03:52:46 - INFO - codeparrot_training - Step 32686: {'lr': 0.00044881333074916287, 'samples': 16735744, 'steps': 32686, 'loss/train': 2.1325109004974365}
-03/05/2022 03:52:48 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/05/2022 03:52:51 - INFO - codeparrot_training - Step 32687: {'lr': 0.00044881011334579093, 'samples': 16736256, 'steps': 32687, 'loss/train': 1.9747942686080933}
-03/05/2022 03:52:54 - INFO - codeparrot_training - Step 32688: {'lr': 0.0004488068958528382, 'samples': 16736768, 'steps': 32688, 'loss/train': 0.12265545129776001}
-03/05/2022 03:52:57 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/05/2022 03:52:59 - INFO - codeparrot_training - Step 32689: {'lr': 0.0004488036782703061, 'samples': 16737280, 'steps': 32689, 'loss/train': 2.0384621620178223}
-03/05/2022 03:53:03 - INFO - codeparrot_training - Step 32690: {'lr': 0.00044880046059819615, 'samples': 16737792, 'steps': 32690, 'loss/train': 1.7089682817459106}
-03/05/2022 03:53:05 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/05/2022 03:53:08 - INFO - codeparrot_training - Step 32691: {'lr': 0.00044879724283650976, 'samples': 16738304, 'steps': 32691, 'loss/train': 1.405125379562378}
-03/05/2022 03:53:11 - INFO - codeparrot_training - Step 32692: {'lr': 0.0004487940249852484, 'samples': 16738816, 'steps': 32692, 'loss/train': 1.1829493045806885}
-03/05/2022 03:53:13 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 03:53:17 - INFO - codeparrot_training - Step 32693: {'lr': 0.0004487908070444136, 'samples': 16739328, 'steps': 32693, 'loss/train': 1.746406078338623}
-03/05/2022 03:53:20 - INFO - codeparrot_training - Step 32694: {'lr': 0.00044878758901400665, 'samples': 16739840, 'steps': 32694, 'loss/train': 1.3655046224594116}
-03/05/2022 03:53:22 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 03:53:25 - INFO - codeparrot_training - Step 32695: {'lr': 0.00044878437089402906, 'samples': 16740352, 'steps': 32695, 'loss/train': 1.2845758199691772}
-03/05/2022 03:53:28 - INFO - codeparrot_training - Step 32696: {'lr': 0.0004487811526844824, 'samples': 16740864, 'steps': 32696, 'loss/train': 2.1204659938812256}
-03/05/2022 03:53:30 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 03:53:33 - INFO - codeparrot_training - Step 32697: {'lr': 0.0004487779343853679, 'samples': 16741376, 'steps': 32697, 'loss/train': 1.5406386852264404}
-03/05/2022 03:53:37 - INFO - codeparrot_training - Step 32698: {'lr': 0.00044877471599668716, 'samples': 16741888, 'steps': 32698, 'loss/train': 1.820219874382019}
-03/05/2022 03:53:39 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/05/2022 03:53:42 - INFO - codeparrot_training - Step 32699: {'lr': 0.00044877149751844164, 'samples': 16742400, 'steps': 32699, 'loss/train': 1.6553469896316528}
-03/05/2022 03:53:45 - INFO - codeparrot_training - Step 32700: {'lr': 0.00044876827895063277, 'samples': 16742912, 'steps': 32700, 'loss/train': 0.047965291887521744}
-03/05/2022 03:53:47 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/05/2022 03:53:50 - INFO - codeparrot_training - Step 32701: {'lr': 0.0004487650602932619, 'samples': 16743424, 'steps': 32701, 'loss/train': 2.5701000690460205}
-03/05/2022 03:53:54 - INFO - codeparrot_training - Step 32702: {'lr': 0.00044876184154633066, 'samples': 16743936, 'steps': 32702, 'loss/train': 1.9226176738739014}
-03/05/2022 03:53:56 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/05/2022 03:53:59 - INFO - codeparrot_training - Step 32703: {'lr': 0.00044875862270984035, 'samples': 16744448, 'steps': 32703, 'loss/train': 1.3878147602081299}
-03/05/2022 03:54:02 - INFO - codeparrot_training - Step 32704: {'lr': 0.0004487554037837925, 'samples': 16744960, 'steps': 32704, 'loss/train': 1.6687870025634766}
-03/05/2022 03:54:04 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/05/2022 03:54:07 - INFO - codeparrot_training - Step 32705: {'lr': 0.00044875218476818845, 'samples': 16745472, 'steps': 32705, 'loss/train': 0.13286301493644714}
-03/05/2022 03:54:11 - INFO - codeparrot_training - Step 32706: {'lr': 0.0004487489656630298, 'samples': 16745984, 'steps': 32706, 'loss/train': 2.061570882797241}
-03/05/2022 03:54:12 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/05/2022 03:54:16 - INFO - codeparrot_training - Step 32707: {'lr': 0.00044874574646831794, 'samples': 16746496, 'steps': 32707, 'loss/train': 1.7554301023483276}
-03/05/2022 03:54:19 - INFO - codeparrot_training - Step 32708: {'lr': 0.0004487425271840543, 'samples': 16747008, 'steps': 32708, 'loss/train': 1.3654509782791138}
-03/05/2022 03:54:20 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/05/2022 03:54:24 - INFO - codeparrot_training - Step 32709: {'lr': 0.0004487393078102403, 'samples': 16747520, 'steps': 32709, 'loss/train': 1.493709921836853}
-03/05/2022 03:54:27 - INFO - codeparrot_training - Step 32710: {'lr': 0.00044873608834687754, 'samples': 16748032, 'steps': 32710, 'loss/train': 2.0046284198760986}
-03/05/2022 03:54:29 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/05/2022 03:54:33 - INFO - codeparrot_training - Step 32711: {'lr': 0.00044873286879396724, 'samples': 16748544, 'steps': 32711, 'loss/train': 1.7019821405410767}
-03/05/2022 03:54:36 - INFO - codeparrot_training - Step 32712: {'lr': 0.00044872964915151106, 'samples': 16749056, 'steps': 32712, 'loss/train': 1.5509377717971802}
-03/05/2022 03:54:37 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/05/2022 03:54:41 - INFO - codeparrot_training - Step 32713: {'lr': 0.00044872642941951035, 'samples': 16749568, 'steps': 32713, 'loss/train': 2.696380138397217}
-03/05/2022 03:54:44 - INFO - codeparrot_training - Step 32714: {'lr': 0.0004487232095979666, 'samples': 16750080, 'steps': 32714, 'loss/train': 1.6360069513320923}
-03/05/2022 03:54:46 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/05/2022 03:54:50 - INFO - codeparrot_training - Step 32715: {'lr': 0.0004487199896868812, 'samples': 16750592, 'steps': 32715, 'loss/train': 1.5997015237808228}
-03/05/2022 03:54:53 - INFO - codeparrot_training - Step 32716: {'lr': 0.00044871676968625564, 'samples': 16751104, 'steps': 32716, 'loss/train': 1.1536569595336914}
-03/05/2022 03:54:54 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/05/2022 03:54:58 - INFO - codeparrot_training - Step 32717: {'lr': 0.00044871354959609135, 'samples': 16751616, 'steps': 32717, 'loss/train': 1.2594804763793945}
-03/05/2022 03:55:01 - INFO - codeparrot_training - Step 32718: {'lr': 0.00044871032941638984, 'samples': 16752128, 'steps': 32718, 'loss/train': 1.242711067199707}
-03/05/2022 03:55:02 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/05/2022 03:55:06 - INFO - codeparrot_training - Step 32719: {'lr': 0.00044870710914715254, 'samples': 16752640, 'steps': 32719, 'loss/train': 2.034914255142212}
-03/05/2022 03:55:09 - INFO - codeparrot_training - Step 32720: {'lr': 0.00044870388878838084, 'samples': 16753152, 'steps': 32720, 'loss/train': 1.8568755388259888}
-03/05/2022 03:55:11 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/05/2022 03:55:15 - INFO - codeparrot_training - Step 32721: {'lr': 0.00044870066834007627, 'samples': 16753664, 'steps': 32721, 'loss/train': 1.9558056592941284}
-03/05/2022 03:55:18 - INFO - codeparrot_training - Step 32722: {'lr': 0.0004486974478022402, 'samples': 16754176, 'steps': 32722, 'loss/train': 2.210042715072632}
-03/05/2022 03:55:19 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/05/2022 03:55:23 - INFO - codeparrot_training - Step 32723: {'lr': 0.0004486942271748742, 'samples': 16754688, 'steps': 32723, 'loss/train': 2.743617296218872}
-03/05/2022 03:55:26 - INFO - codeparrot_training - Step 32724: {'lr': 0.0004486910064579796, 'samples': 16755200, 'steps': 32724, 'loss/train': 1.5356628894805908}
-03/05/2022 03:55:27 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/05/2022 03:55:32 - INFO - codeparrot_training - Step 32725: {'lr': 0.00044868778565155783, 'samples': 16755712, 'steps': 32725, 'loss/train': 1.792995810508728}
-03/05/2022 03:55:35 - INFO - codeparrot_training - Step 32726: {'lr': 0.00044868456475561047, 'samples': 16756224, 'steps': 32726, 'loss/train': 1.8955814838409424}
-03/05/2022 03:55:36 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/05/2022 03:55:40 - INFO - codeparrot_training - Step 32727: {'lr': 0.0004486813437701389, 'samples': 16756736, 'steps': 32727, 'loss/train': 1.643625020980835}
-03/05/2022 03:55:43 - INFO - codeparrot_training - Step 32728: {'lr': 0.0004486781226951446, 'samples': 16757248, 'steps': 32728, 'loss/train': 2.0542855262756348}
-03/05/2022 03:55:44 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/05/2022 03:55:48 - INFO - codeparrot_training - Step 32729: {'lr': 0.000448674901530629, 'samples': 16757760, 'steps': 32729, 'loss/train': 1.3662149906158447}
-03/05/2022 03:55:52 - INFO - codeparrot_training - Step 32730: {'lr': 0.00044867168027659356, 'samples': 16758272, 'steps': 32730, 'loss/train': 1.1919394731521606}
-03/05/2022 03:55:52 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/05/2022 03:55:57 - INFO - codeparrot_training - Step 32731: {'lr': 0.00044866845893303973, 'samples': 16758784, 'steps': 32731, 'loss/train': 0.7135829925537109}
-03/05/2022 03:56:00 - INFO - codeparrot_training - Step 32732: {'lr': 0.00044866523749996897, 'samples': 16759296, 'steps': 32732, 'loss/train': 1.944987177848816}
-03/05/2022 03:56:02 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/05/2022 03:56:06 - INFO - codeparrot_training - Step 32733: {'lr': 0.0004486620159773827, 'samples': 16759808, 'steps': 32733, 'loss/train': 2.688162088394165}
-03/05/2022 03:56:09 - INFO - codeparrot_training - Step 32734: {'lr': 0.0004486587943652823, 'samples': 16760320, 'steps': 32734, 'loss/train': 1.6266406774520874}
-03/05/2022 03:56:11 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/05/2022 03:56:14 - INFO - codeparrot_training - Step 32735: {'lr': 0.00044865557266366953, 'samples': 16760832, 'steps': 32735, 'loss/train': 1.9560359716415405}
-03/05/2022 03:56:17 - INFO - codeparrot_training - Step 32736: {'lr': 0.0004486523508725454, 'samples': 16761344, 'steps': 32736, 'loss/train': 1.807797908782959}
-03/05/2022 03:56:19 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/05/2022 03:56:23 - INFO - codeparrot_training - Step 32737: {'lr': 0.00044864912899191174, 'samples': 16761856, 'steps': 32737, 'loss/train': 3.4237112998962402}
-03/05/2022 03:56:26 - INFO - codeparrot_training - Step 32738: {'lr': 0.00044864590702176977, 'samples': 16762368, 'steps': 32738, 'loss/train': 2.1485090255737305}
-03/05/2022 03:56:28 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/05/2022 03:56:31 - INFO - codeparrot_training - Step 32739: {'lr': 0.000448642684962121, 'samples': 16762880, 'steps': 32739, 'loss/train': 1.5788065195083618}
-03/05/2022 03:56:34 - INFO - codeparrot_training - Step 32740: {'lr': 0.000448639462812967, 'samples': 16763392, 'steps': 32740, 'loss/train': 1.4504294395446777}
-03/05/2022 03:56:36 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/05/2022 03:56:40 - INFO - codeparrot_training - Step 32741: {'lr': 0.0004486362405743091, 'samples': 16763904, 'steps': 32741, 'loss/train': 1.064976453781128}
-03/05/2022 03:56:43 - INFO - codeparrot_training - Step 32742: {'lr': 0.0004486330182461487, 'samples': 16764416, 'steps': 32742, 'loss/train': 1.6573737859725952}
-03/05/2022 03:56:45 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 03:56:48 - INFO - codeparrot_training - Step 32743: {'lr': 0.0004486297958284874, 'samples': 16764928, 'steps': 32743, 'loss/train': 1.679376482963562}
-03/05/2022 03:56:51 - INFO - codeparrot_training - Step 32744: {'lr': 0.0004486265733213265, 'samples': 16765440, 'steps': 32744, 'loss/train': 1.9473892450332642}
-03/05/2022 03:56:53 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/05/2022 03:56:56 - INFO - codeparrot_training - Step 32745: {'lr': 0.00044862335072466767, 'samples': 16765952, 'steps': 32745, 'loss/train': 1.3998804092407227}
-03/05/2022 03:57:00 - INFO - codeparrot_training - Step 32746: {'lr': 0.00044862012803851203, 'samples': 16766464, 'steps': 32746, 'loss/train': 1.9323163032531738}
-03/05/2022 03:57:01 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/05/2022 03:57:05 - INFO - codeparrot_training - Step 32747: {'lr': 0.00044861690526286135, 'samples': 16766976, 'steps': 32747, 'loss/train': 1.2599306106567383}
-03/05/2022 03:57:09 - INFO - codeparrot_training - Step 32748: {'lr': 0.00044861368239771694, 'samples': 16767488, 'steps': 32748, 'loss/train': 2.1158111095428467}
-03/05/2022 03:57:10 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/05/2022 03:57:14 - INFO - codeparrot_training - Step 32749: {'lr': 0.00044861045944308026, 'samples': 16768000, 'steps': 32749, 'loss/train': 1.5830293893814087}
-03/05/2022 03:57:17 - INFO - codeparrot_training - Step 32750: {'lr': 0.0004486072363989528, 'samples': 16768512, 'steps': 32750, 'loss/train': 0.0596163235604763}
-03/05/2022 03:57:19 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/05/2022 03:57:22 - INFO - codeparrot_training - Step 32751: {'lr': 0.00044860401326533595, 'samples': 16769024, 'steps': 32751, 'loss/train': 1.6744040250778198}
-03/05/2022 03:57:25 - INFO - codeparrot_training - Step 32752: {'lr': 0.0004486007900422312, 'samples': 16769536, 'steps': 32752, 'loss/train': 2.0595200061798096}
-03/05/2022 03:57:27 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/05/2022 03:57:31 - INFO - codeparrot_training - Step 32753: {'lr': 0.00044859756672964, 'samples': 16770048, 'steps': 32753, 'loss/train': 1.6305497884750366}
-03/05/2022 03:57:34 - INFO - codeparrot_training - Step 32754: {'lr': 0.00044859434332756383, 'samples': 16770560, 'steps': 32754, 'loss/train': 2.1313297748565674}
-03/05/2022 03:57:36 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/05/2022 03:57:39 - INFO - codeparrot_training - Step 32755: {'lr': 0.0004485911198360041, 'samples': 16771072, 'steps': 32755, 'loss/train': 1.8246662616729736}
-03/05/2022 03:57:42 - INFO - codeparrot_training - Step 32756: {'lr': 0.0004485878962549622, 'samples': 16771584, 'steps': 32756, 'loss/train': 1.6334152221679688}
-03/05/2022 03:57:44 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/05/2022 03:57:48 - INFO - codeparrot_training - Step 32757: {'lr': 0.0004485846725844398, 'samples': 16772096, 'steps': 32757, 'loss/train': 2.1353466510772705}
-03/05/2022 03:57:51 - INFO - codeparrot_training - Step 32758: {'lr': 0.0004485814488244381, 'samples': 16772608, 'steps': 32758, 'loss/train': 1.4135867357254028}
-03/05/2022 03:57:53 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/05/2022 03:57:56 - INFO - codeparrot_training - Step 32759: {'lr': 0.0004485782249749587, 'samples': 16773120, 'steps': 32759, 'loss/train': 1.8091596364974976}
-03/05/2022 03:57:59 - INFO - codeparrot_training - Step 32760: {'lr': 0.00044857500103600304, 'samples': 16773632, 'steps': 32760, 'loss/train': 2.317765235900879}
-03/05/2022 03:58:01 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/05/2022 03:58:05 - INFO - codeparrot_training - Step 32761: {'lr': 0.00044857177700757247, 'samples': 16774144, 'steps': 32761, 'loss/train': 1.1527115106582642}
-03/05/2022 03:58:08 - INFO - codeparrot_training - Step 32762: {'lr': 0.00044856855288966856, 'samples': 16774656, 'steps': 32762, 'loss/train': 1.5814310312271118}
-03/05/2022 03:58:09 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/05/2022 03:58:13 - INFO - codeparrot_training - Step 32763: {'lr': 0.0004485653286822927, 'samples': 16775168, 'steps': 32763, 'loss/train': 0.9628899097442627}
-03/05/2022 03:58:16 - INFO - codeparrot_training - Step 32764: {'lr': 0.0004485621043854465, 'samples': 16775680, 'steps': 32764, 'loss/train': 1.5995169878005981}
-03/05/2022 03:58:17 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/05/2022 03:58:21 - INFO - codeparrot_training - Step 32765: {'lr': 0.0004485588799991311, 'samples': 16776192, 'steps': 32765, 'loss/train': 1.2330594062805176}
-03/05/2022 03:58:25 - INFO - codeparrot_training - Step 32766: {'lr': 0.0004485556555233483, 'samples': 16776704, 'steps': 32766, 'loss/train': 1.987736701965332}
-03/05/2022 03:58:26 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 03:58:30 - INFO - codeparrot_training - Step 32767: {'lr': 0.0004485524309580993, 'samples': 16777216, 'steps': 32767, 'loss/train': 2.2815704345703125}
-03/05/2022 03:58:33 - INFO - codeparrot_training - Step 32768: {'lr': 0.0004485492063033856, 'samples': 16777728, 'steps': 32768, 'loss/train': 0.10674573481082916}
-03/05/2022 03:58:35 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/05/2022 03:58:38 - INFO - codeparrot_training - Step 32769: {'lr': 0.0004485459815592087, 'samples': 16778240, 'steps': 32769, 'loss/train': 1.229867696762085}
-03/05/2022 03:58:42 - INFO - codeparrot_training - Step 32770: {'lr': 0.0004485427567255701, 'samples': 16778752, 'steps': 32770, 'loss/train': 2.820906400680542}
-03/05/2022 03:58:43 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/05/2022 03:58:47 - INFO - codeparrot_training - Step 32771: {'lr': 0.0004485395318024712, 'samples': 16779264, 'steps': 32771, 'loss/train': 1.6190396547317505}
-03/05/2022 03:58:50 - INFO - codeparrot_training - Step 32772: {'lr': 0.00044853630678991344, 'samples': 16779776, 'steps': 32772, 'loss/train': 1.6512805223464966}
-03/05/2022 03:58:51 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/05/2022 03:58:55 - INFO - codeparrot_training - Step 32773: {'lr': 0.00044853308168789824, 'samples': 16780288, 'steps': 32773, 'loss/train': 1.3366000652313232}
-03/05/2022 03:58:58 - INFO - codeparrot_training - Step 32774: {'lr': 0.00044852985649642714, 'samples': 16780800, 'steps': 32774, 'loss/train': 1.9807907342910767}
-03/05/2022 03:58:59 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 03:59:04 - INFO - codeparrot_training - Step 32775: {'lr': 0.0004485266312155015, 'samples': 16781312, 'steps': 32775, 'loss/train': 2.06160044670105}
-03/05/2022 03:59:07 - INFO - codeparrot_training - Step 32776: {'lr': 0.00044852340584512285, 'samples': 16781824, 'steps': 32776, 'loss/train': 1.2140681743621826}
-03/05/2022 03:59:08 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/05/2022 03:59:12 - INFO - codeparrot_training - Step 32777: {'lr': 0.00044852018038529264, 'samples': 16782336, 'steps': 32777, 'loss/train': 1.6866059303283691}
-03/05/2022 03:59:16 - INFO - codeparrot_training - Step 32778: {'lr': 0.00044851695483601227, 'samples': 16782848, 'steps': 32778, 'loss/train': 1.1241260766983032}
-03/05/2022 03:59:16 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/05/2022 03:59:21 - INFO - codeparrot_training - Step 32779: {'lr': 0.0004485137291972833, 'samples': 16783360, 'steps': 32779, 'loss/train': 1.7784221172332764}
-03/05/2022 03:59:24 - INFO - codeparrot_training - Step 32780: {'lr': 0.00044851050346910706, 'samples': 16783872, 'steps': 32780, 'loss/train': 2.2918736934661865}
-03/05/2022 03:59:25 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/05/2022 03:59:29 - INFO - codeparrot_training - Step 32781: {'lr': 0.00044850727765148504, 'samples': 16784384, 'steps': 32781, 'loss/train': 1.7876278162002563}
-03/05/2022 03:59:33 - INFO - codeparrot_training - Step 32782: {'lr': 0.00044850405174441866, 'samples': 16784896, 'steps': 32782, 'loss/train': 1.8087859153747559}
-03/05/2022 03:59:34 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 03:59:38 - INFO - codeparrot_training - Step 32783: {'lr': 0.00044850082574790945, 'samples': 16785408, 'steps': 32783, 'loss/train': 2.3987033367156982}
-03/05/2022 03:59:41 - INFO - codeparrot_training - Step 32784: {'lr': 0.0004484975996619589, 'samples': 16785920, 'steps': 32784, 'loss/train': 2.1207242012023926}
-03/05/2022 03:59:42 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/05/2022 03:59:46 - INFO - codeparrot_training - Step 32785: {'lr': 0.0004484943734865683, 'samples': 16786432, 'steps': 32785, 'loss/train': 2.3311638832092285}
-03/05/2022 03:59:49 - INFO - codeparrot_training - Step 32786: {'lr': 0.0004484911472217392, 'samples': 16786944, 'steps': 32786, 'loss/train': 2.0124664306640625}
-03/05/2022 03:59:50 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/05/2022 03:59:55 - INFO - codeparrot_training - Step 32787: {'lr': 0.0004484879208674731, 'samples': 16787456, 'steps': 32787, 'loss/train': 2.211538314819336}
-03/05/2022 03:59:58 - INFO - codeparrot_training - Step 32788: {'lr': 0.0004484846944237714, 'samples': 16787968, 'steps': 32788, 'loss/train': 1.4898900985717773}
-03/05/2022 03:59:59 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/05/2022 04:00:03 - INFO - codeparrot_training - Step 32789: {'lr': 0.0004484814678906355, 'samples': 16788480, 'steps': 32789, 'loss/train': 1.68108332157135}
-03/05/2022 04:00:06 - INFO - codeparrot_training - Step 32790: {'lr': 0.00044847824126806703, 'samples': 16788992, 'steps': 32790, 'loss/train': 1.9250514507293701}
-03/05/2022 04:00:07 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 04:00:12 - INFO - codeparrot_training - Step 32791: {'lr': 0.0004484750145560672, 'samples': 16789504, 'steps': 32791, 'loss/train': 5.070474624633789}
-03/05/2022 04:00:15 - INFO - codeparrot_training - Step 32792: {'lr': 0.0004484717877546377, 'samples': 16790016, 'steps': 32792, 'loss/train': 2.026045322418213}
-03/05/2022 04:00:17 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/05/2022 04:00:20 - INFO - codeparrot_training - Step 32793: {'lr': 0.0004484685608637798, 'samples': 16790528, 'steps': 32793, 'loss/train': 2.200256109237671}
-03/05/2022 04:00:23 - INFO - codeparrot_training - Step 32794: {'lr': 0.00044846533388349507, 'samples': 16791040, 'steps': 32794, 'loss/train': 2.316960573196411}
-03/05/2022 04:00:25 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/05/2022 04:00:29 - INFO - codeparrot_training - Step 32795: {'lr': 0.00044846210681378487, 'samples': 16791552, 'steps': 32795, 'loss/train': 3.859579086303711}
-03/05/2022 04:00:32 - INFO - codeparrot_training - Step 32796: {'lr': 0.00044845887965465076, 'samples': 16792064, 'steps': 32796, 'loss/train': 1.2751544713974}
-03/05/2022 04:00:34 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/05/2022 04:00:37 - INFO - codeparrot_training - Step 32797: {'lr': 0.0004484556524060941, 'samples': 16792576, 'steps': 32797, 'loss/train': 2.0813605785369873}
-03/05/2022 04:00:41 - INFO - codeparrot_training - Step 32798: {'lr': 0.00044845242506811646, 'samples': 16793088, 'steps': 32798, 'loss/train': 1.368618130683899}
-03/05/2022 04:00:44 - INFO - codeparrot_training - Step 32799: {'lr': 0.0004484491976407192, 'samples': 16793600, 'steps': 32799, 'loss/train': 1.979921579360962}
-03/05/2022 04:00:44 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 04:00:49 - INFO - codeparrot_training - Step 32800: {'lr': 0.00044844597012390374, 'samples': 16794112, 'steps': 32800, 'loss/train': 1.2909562587738037}
-03/05/2022 04:00:52 - INFO - codeparrot_training - Step 32801: {'lr': 0.0004484427425176716, 'samples': 16794624, 'steps': 32801, 'loss/train': 1.80970299243927}
-03/05/2022 04:00:52 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/05/2022 04:00:57 - INFO - codeparrot_training - Step 32802: {'lr': 0.0004484395148220243, 'samples': 16795136, 'steps': 32802, 'loss/train': 1.514662504196167}
-03/05/2022 04:01:01 - INFO - codeparrot_training - Step 32803: {'lr': 0.000448436287036963, 'samples': 16795648, 'steps': 32803, 'loss/train': 2.1822876930236816}
-03/05/2022 04:01:01 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/05/2022 04:01:06 - INFO - codeparrot_training - Step 32804: {'lr': 0.0004484330591624896, 'samples': 16796160, 'steps': 32804, 'loss/train': 1.836177945137024}
-03/05/2022 04:01:09 - INFO - codeparrot_training - Step 32805: {'lr': 0.00044842983119860525, 'samples': 16796672, 'steps': 32805, 'loss/train': 2.757866144180298}
-03/05/2022 04:01:10 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/05/2022 04:01:14 - INFO - codeparrot_training - Step 32806: {'lr': 0.00044842660314531145, 'samples': 16797184, 'steps': 32806, 'loss/train': 2.1904819011688232}
-03/05/2022 04:01:18 - INFO - codeparrot_training - Step 32807: {'lr': 0.0004484233750026098, 'samples': 16797696, 'steps': 32807, 'loss/train': 1.824310064315796}
-03/05/2022 04:01:18 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/05/2022 04:01:23 - INFO - codeparrot_training - Step 32808: {'lr': 0.00044842014677050145, 'samples': 16798208, 'steps': 32808, 'loss/train': 2.2862887382507324}
-03/05/2022 04:01:26 - INFO - codeparrot_training - Step 32809: {'lr': 0.0004484169184489882, 'samples': 16798720, 'steps': 32809, 'loss/train': 2.0309438705444336}
-03/05/2022 04:01:27 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/05/2022 04:01:31 - INFO - codeparrot_training - Step 32810: {'lr': 0.0004484136900380713, 'samples': 16799232, 'steps': 32810, 'loss/train': 1.4617422819137573}
-03/05/2022 04:01:35 - INFO - codeparrot_training - Step 32811: {'lr': 0.00044841046153775224, 'samples': 16799744, 'steps': 32811, 'loss/train': 0.5655346512794495}
-03/05/2022 04:01:35 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/05/2022 04:01:40 - INFO - codeparrot_training - Step 32812: {'lr': 0.0004484072329480325, 'samples': 16800256, 'steps': 32812, 'loss/train': 1.6036378145217896}
-03/05/2022 04:01:43 - INFO - codeparrot_training - Step 32813: {'lr': 0.00044840400426891347, 'samples': 16800768, 'steps': 32813, 'loss/train': 1.8214073181152344}
-03/05/2022 04:01:44 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/05/2022 04:01:48 - INFO - codeparrot_training - Step 32814: {'lr': 0.00044840077550039676, 'samples': 16801280, 'steps': 32814, 'loss/train': 1.649049997329712}
-03/05/2022 04:01:51 - INFO - codeparrot_training - Step 32815: {'lr': 0.0004483975466424837, 'samples': 16801792, 'steps': 32815, 'loss/train': 0.9569042921066284}
-03/05/2022 04:01:52 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/05/2022 04:01:57 - INFO - codeparrot_training - Step 32816: {'lr': 0.0004483943176951757, 'samples': 16802304, 'steps': 32816, 'loss/train': 1.8066608905792236}
-03/05/2022 04:02:00 - INFO - codeparrot_training - Step 32817: {'lr': 0.0004483910886584743, 'samples': 16802816, 'steps': 32817, 'loss/train': 1.1769850254058838}
-03/05/2022 04:02:00 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/05/2022 04:02:05 - INFO - codeparrot_training - Step 32818: {'lr': 0.00044838785953238094, 'samples': 16803328, 'steps': 32818, 'loss/train': 1.6284947395324707}
-03/05/2022 04:02:08 - INFO - codeparrot_training - Step 32819: {'lr': 0.0004483846303168971, 'samples': 16803840, 'steps': 32819, 'loss/train': 1.8191710710525513}
-03/05/2022 04:02:09 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 04:02:14 - INFO - codeparrot_training - Step 32820: {'lr': 0.0004483814010120242, 'samples': 16804352, 'steps': 32820, 'loss/train': 1.59821617603302}
-03/05/2022 04:02:17 - INFO - codeparrot_training - Step 32821: {'lr': 0.00044837817161776366, 'samples': 16804864, 'steps': 32821, 'loss/train': 2.291229248046875}
-03/05/2022 04:02:18 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/05/2022 04:02:22 - INFO - codeparrot_training - Step 32822: {'lr': 0.000448374942134117, 'samples': 16805376, 'steps': 32822, 'loss/train': 1.7003612518310547}
-03/05/2022 04:02:25 - INFO - codeparrot_training - Step 32823: {'lr': 0.0004483717125610857, 'samples': 16805888, 'steps': 32823, 'loss/train': 1.4782660007476807}
-03/05/2022 04:02:26 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 04:02:31 - INFO - codeparrot_training - Step 32824: {'lr': 0.0004483684828986712, 'samples': 16806400, 'steps': 32824, 'loss/train': 2.4041008949279785}
-03/05/2022 04:02:34 - INFO - codeparrot_training - Step 32825: {'lr': 0.00044836525314687477, 'samples': 16806912, 'steps': 32825, 'loss/train': 1.981614589691162}
-03/05/2022 04:02:35 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 04:02:39 - INFO - codeparrot_training - Step 32826: {'lr': 0.0004483620233056981, 'samples': 16807424, 'steps': 32826, 'loss/train': 1.7828078269958496}
-03/05/2022 04:02:42 - INFO - codeparrot_training - Step 32827: {'lr': 0.00044835879337514254, 'samples': 16807936, 'steps': 32827, 'loss/train': 0.46749308705329895}
-03/05/2022 04:02:43 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/05/2022 04:02:47 - INFO - codeparrot_training - Step 32828: {'lr': 0.0004483555633552096, 'samples': 16808448, 'steps': 32828, 'loss/train': 1.4670099020004272}
-03/05/2022 04:02:51 - INFO - codeparrot_training - Step 32829: {'lr': 0.00044835233324590077, 'samples': 16808960, 'steps': 32829, 'loss/train': 1.3449726104736328}
-03/05/2022 04:02:51 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/05/2022 04:02:56 - INFO - codeparrot_training - Step 32830: {'lr': 0.0004483491030472173, 'samples': 16809472, 'steps': 32830, 'loss/train': 0.9999790191650391}
-03/05/2022 04:02:59 - INFO - codeparrot_training - Step 32831: {'lr': 0.00044834587275916084, 'samples': 16809984, 'steps': 32831, 'loss/train': 2.293489933013916}
-03/05/2022 04:03:00 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/05/2022 04:03:04 - INFO - codeparrot_training - Step 32832: {'lr': 0.00044834264238173283, 'samples': 16810496, 'steps': 32832, 'loss/train': 1.4310274124145508}
-03/05/2022 04:03:07 - INFO - codeparrot_training - Step 32833: {'lr': 0.00044833941191493463, 'samples': 16811008, 'steps': 32833, 'loss/train': 1.4755841493606567}
-03/05/2022 04:03:08 - INFO - codeparrot_training - Skipping example with length 983 (seq_length=1024)
-03/05/2022 04:03:13 - INFO - codeparrot_training - Step 32834: {'lr': 0.0004483361813587678, 'samples': 16811520, 'steps': 32834, 'loss/train': 1.912050724029541}
-03/05/2022 04:03:16 - INFO - codeparrot_training - Step 32835: {'lr': 0.0004483329507132337, 'samples': 16812032, 'steps': 32835, 'loss/train': 0.9388858675956726}
-03/05/2022 04:03:17 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/05/2022 04:03:21 - INFO - codeparrot_training - Step 32836: {'lr': 0.0004483297199783338, 'samples': 16812544, 'steps': 32836, 'loss/train': 3.141925096511841}
-03/05/2022 04:03:24 - INFO - codeparrot_training - Step 32837: {'lr': 0.0004483264891540697, 'samples': 16813056, 'steps': 32837, 'loss/train': 1.3589732646942139}
-03/05/2022 04:03:25 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 04:03:29 - INFO - codeparrot_training - Step 32838: {'lr': 0.00044832325824044274, 'samples': 16813568, 'steps': 32838, 'loss/train': 1.9961891174316406}
-03/05/2022 04:03:33 - INFO - codeparrot_training - Step 32839: {'lr': 0.0004483200272374543, 'samples': 16814080, 'steps': 32839, 'loss/train': 2.361741304397583}
-03/05/2022 04:03:33 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/05/2022 04:03:38 - INFO - codeparrot_training - Step 32840: {'lr': 0.0004483167961451059, 'samples': 16814592, 'steps': 32840, 'loss/train': 1.9078457355499268}
-03/05/2022 04:03:41 - INFO - codeparrot_training - Step 32841: {'lr': 0.00044831356496339913, 'samples': 16815104, 'steps': 32841, 'loss/train': 0.7789722681045532}
-03/05/2022 04:03:42 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/05/2022 04:03:46 - INFO - codeparrot_training - Step 32842: {'lr': 0.0004483103336923352, 'samples': 16815616, 'steps': 32842, 'loss/train': 2.1905312538146973}
-03/05/2022 04:03:49 - INFO - codeparrot_training - Step 32843: {'lr': 0.00044830710233191573, 'samples': 16816128, 'steps': 32843, 'loss/train': 1.7192633152008057}
-03/05/2022 04:03:50 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/05/2022 04:03:55 - INFO - codeparrot_training - Step 32844: {'lr': 0.0004483038708821422, 'samples': 16816640, 'steps': 32844, 'loss/train': 1.3239785432815552}
-03/05/2022 04:03:58 - INFO - codeparrot_training - Step 32845: {'lr': 0.00044830063934301603, 'samples': 16817152, 'steps': 32845, 'loss/train': 2.708096981048584}
-03/05/2022 04:03:58 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 04:04:03 - INFO - codeparrot_training - Step 32846: {'lr': 0.0004482974077145385, 'samples': 16817664, 'steps': 32846, 'loss/train': 1.8473336696624756}
-03/05/2022 04:04:06 - INFO - codeparrot_training - Step 32847: {'lr': 0.0004482941759967113, 'samples': 16818176, 'steps': 32847, 'loss/train': 1.0972201824188232}
-03/05/2022 04:04:07 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/05/2022 04:04:12 - INFO - codeparrot_training - Step 32848: {'lr': 0.00044829094418953586, 'samples': 16818688, 'steps': 32848, 'loss/train': 1.987696886062622}
-03/05/2022 04:04:15 - INFO - codeparrot_training - Step 32849: {'lr': 0.00044828771229301354, 'samples': 16819200, 'steps': 32849, 'loss/train': 1.7891756296157837}
-03/05/2022 04:04:15 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 04:04:20 - INFO - codeparrot_training - Step 32850: {'lr': 0.0004482844803071458, 'samples': 16819712, 'steps': 32850, 'loss/train': 1.7835396528244019}
-03/05/2022 04:04:23 - INFO - codeparrot_training - Step 32851: {'lr': 0.00044828124823193417, 'samples': 16820224, 'steps': 32851, 'loss/train': 1.7560997009277344}
-03/05/2022 04:04:24 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/05/2022 04:04:29 - INFO - codeparrot_training - Step 32852: {'lr': 0.00044827801606738004, 'samples': 16820736, 'steps': 32852, 'loss/train': 5.391373634338379}
-03/05/2022 04:04:32 - INFO - codeparrot_training - Step 32853: {'lr': 0.00044827478381348495, 'samples': 16821248, 'steps': 32853, 'loss/train': 2.0404882431030273}
-03/05/2022 04:04:32 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/05/2022 04:04:37 - INFO - codeparrot_training - Step 32854: {'lr': 0.00044827155147025025, 'samples': 16821760, 'steps': 32854, 'loss/train': 1.9201496839523315}
-03/05/2022 04:04:40 - INFO - codeparrot_training - Step 32855: {'lr': 0.00044826831903767745, 'samples': 16822272, 'steps': 32855, 'loss/train': 1.5028250217437744}
-03/05/2022 04:04:41 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/05/2022 04:04:45 - INFO - codeparrot_training - Step 32856: {'lr': 0.000448265086515768, 'samples': 16822784, 'steps': 32856, 'loss/train': 1.9948362112045288}
-03/05/2022 04:04:49 - INFO - codeparrot_training - Step 32857: {'lr': 0.0004482618539045234, 'samples': 16823296, 'steps': 32857, 'loss/train': 1.8896045684814453}
-03/05/2022 04:04:49 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/05/2022 04:04:54 - INFO - codeparrot_training - Step 32858: {'lr': 0.00044825862120394504, 'samples': 16823808, 'steps': 32858, 'loss/train': 1.2678031921386719}
-03/05/2022 04:04:57 - INFO - codeparrot_training - Step 32859: {'lr': 0.00044825538841403444, 'samples': 16824320, 'steps': 32859, 'loss/train': 1.913914442062378}
-03/05/2022 04:04:58 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 04:05:02 - INFO - codeparrot_training - Step 32860: {'lr': 0.000448252155534793, 'samples': 16824832, 'steps': 32860, 'loss/train': 1.2840266227722168}
-03/05/2022 04:05:05 - INFO - codeparrot_training - Step 32861: {'lr': 0.0004482489225662222, 'samples': 16825344, 'steps': 32861, 'loss/train': 1.8806462287902832}
-03/05/2022 04:05:06 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/05/2022 04:05:11 - INFO - codeparrot_training - Step 32862: {'lr': 0.00044824568950832343, 'samples': 16825856, 'steps': 32862, 'loss/train': 0.8809359669685364}
-03/05/2022 04:05:14 - INFO - codeparrot_training - Step 32863: {'lr': 0.0004482424563610983, 'samples': 16826368, 'steps': 32863, 'loss/train': 1.1482504606246948}
-03/05/2022 04:05:14 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/05/2022 04:05:19 - INFO - codeparrot_training - Step 32864: {'lr': 0.00044823922312454815, 'samples': 16826880, 'steps': 32864, 'loss/train': 1.9535433053970337}
-03/05/2022 04:05:22 - INFO - codeparrot_training - Step 32865: {'lr': 0.00044823598979867445, 'samples': 16827392, 'steps': 32865, 'loss/train': 2.1363930702209473}
-03/05/2022 04:05:22 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/05/2022 04:05:27 - INFO - codeparrot_training - Step 32866: {'lr': 0.0004482327563834787, 'samples': 16827904, 'steps': 32866, 'loss/train': 0.9224907755851746}
-03/05/2022 04:05:30 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/05/2022 04:05:33 - INFO - codeparrot_training - Step 32867: {'lr': 0.00044822952287896237, 'samples': 16828416, 'steps': 32867, 'loss/train': 2.0211193561553955}
-03/05/2022 04:05:36 - INFO - codeparrot_training - Step 32868: {'lr': 0.00044822628928512675, 'samples': 16828928, 'steps': 32868, 'loss/train': 0.8293685913085938}
-03/05/2022 04:05:39 - INFO - codeparrot_training - Step 32869: {'lr': 0.0004482230556019735, 'samples': 16829440, 'steps': 32869, 'loss/train': 0.07612051069736481}
-03/05/2022 04:05:39 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 04:05:45 - INFO - codeparrot_training - Step 32870: {'lr': 0.00044821982182950405, 'samples': 16829952, 'steps': 32870, 'loss/train': 1.3174169063568115}
-03/05/2022 04:05:48 - INFO - codeparrot_training - Step 32871: {'lr': 0.0004482165879677197, 'samples': 16830464, 'steps': 32871, 'loss/train': 1.7359033823013306}
-03/05/2022 04:05:48 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/05/2022 04:05:53 - INFO - codeparrot_training - Step 32872: {'lr': 0.0004482133540166221, 'samples': 16830976, 'steps': 32872, 'loss/train': 1.622950792312622}
-03/05/2022 04:05:56 - INFO - codeparrot_training - Skipping example with length 643 (seq_length=1024)
-03/05/2022 04:05:58 - INFO - codeparrot_training - Step 32873: {'lr': 0.00044821011997621255, 'samples': 16831488, 'steps': 32873, 'loss/train': 1.4304238557815552}
-03/05/2022 04:06:01 - INFO - codeparrot_training - Step 32874: {'lr': 0.0004482068858464926, 'samples': 16832000, 'steps': 32874, 'loss/train': 1.420791745185852}
-03/05/2022 04:06:04 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/05/2022 04:06:07 - INFO - codeparrot_training - Step 32875: {'lr': 0.00044820365162746373, 'samples': 16832512, 'steps': 32875, 'loss/train': 2.7937448024749756}
-03/05/2022 04:06:10 - INFO - codeparrot_training - Step 32876: {'lr': 0.00044820041731912733, 'samples': 16833024, 'steps': 32876, 'loss/train': 0.967921257019043}
-03/05/2022 04:06:12 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/05/2022 04:06:15 - INFO - codeparrot_training - Step 32877: {'lr': 0.0004481971829214848, 'samples': 16833536, 'steps': 32877, 'loss/train': 1.5176584720611572}
-03/05/2022 04:06:18 - INFO - codeparrot_training - Step 32878: {'lr': 0.0004481939484345378, 'samples': 16834048, 'steps': 32878, 'loss/train': 2.285003662109375}
-03/05/2022 04:06:21 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 04:06:24 - INFO - codeparrot_training - Step 32879: {'lr': 0.0004481907138582876, 'samples': 16834560, 'steps': 32879, 'loss/train': 1.7813334465026855}
-03/05/2022 04:06:27 - INFO - codeparrot_training - Step 32880: {'lr': 0.00044818747919273574, 'samples': 16835072, 'steps': 32880, 'loss/train': 1.9654215574264526}
-03/05/2022 04:06:29 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/05/2022 04:06:32 - INFO - codeparrot_training - Step 32881: {'lr': 0.0004481842444378837, 'samples': 16835584, 'steps': 32881, 'loss/train': 1.2609437704086304}
-03/05/2022 04:06:35 - INFO - codeparrot_training - Step 32882: {'lr': 0.0004481810095937329, 'samples': 16836096, 'steps': 32882, 'loss/train': 0.6035986542701721}
-03/05/2022 04:06:37 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/05/2022 04:06:41 - INFO - codeparrot_training - Step 32883: {'lr': 0.00044817777466028467, 'samples': 16836608, 'steps': 32883, 'loss/train': 1.7963297367095947}
-03/05/2022 04:06:44 - INFO - codeparrot_training - Step 32884: {'lr': 0.0004481745396375407, 'samples': 16837120, 'steps': 32884, 'loss/train': 1.2177305221557617}
-03/05/2022 04:06:47 - INFO - codeparrot_training - Step 32885: {'lr': 0.0004481713045255023, 'samples': 16837632, 'steps': 32885, 'loss/train': 1.4318976402282715}
-03/05/2022 04:06:50 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/05/2022 04:06:52 - INFO - codeparrot_training - Step 32886: {'lr': 0.000448168069324171, 'samples': 16838144, 'steps': 32886, 'loss/train': 1.370668888092041}
-03/05/2022 04:06:56 - INFO - codeparrot_training - Step 32887: {'lr': 0.0004481648340335482, 'samples': 16838656, 'steps': 32887, 'loss/train': 1.574015498161316}
-03/05/2022 04:06:59 - INFO - codeparrot_training - Step 32888: {'lr': 0.0004481615986536354, 'samples': 16839168, 'steps': 32888, 'loss/train': 2.401139497756958}
-03/05/2022 04:06:59 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/05/2022 04:07:04 - INFO - codeparrot_training - Step 32889: {'lr': 0.000448158363184434, 'samples': 16839680, 'steps': 32889, 'loss/train': 2.0068302154541016}
-03/05/2022 04:07:07 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/05/2022 04:07:09 - INFO - codeparrot_training - Step 32890: {'lr': 0.00044815512762594556, 'samples': 16840192, 'steps': 32890, 'loss/train': 1.8892120122909546}
-03/05/2022 04:07:13 - INFO - codeparrot_training - Step 32891: {'lr': 0.00044815189197817143, 'samples': 16840704, 'steps': 32891, 'loss/train': 1.3384286165237427}
-03/05/2022 04:07:15 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/05/2022 04:07:18 - INFO - codeparrot_training - Step 32892: {'lr': 0.0004481486562411131, 'samples': 16841216, 'steps': 32892, 'loss/train': 1.219661831855774}
-03/05/2022 04:07:21 - INFO - codeparrot_training - Step 32893: {'lr': 0.0004481454204147721, 'samples': 16841728, 'steps': 32893, 'loss/train': 2.2584476470947266}
-03/05/2022 04:07:24 - INFO - codeparrot_training - Step 32894: {'lr': 0.0004481421844991498, 'samples': 16842240, 'steps': 32894, 'loss/train': 2.880666494369507}
-03/05/2022 04:07:24 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/05/2022 04:07:29 - INFO - codeparrot_training - Step 32895: {'lr': 0.00044813894849424777, 'samples': 16842752, 'steps': 32895, 'loss/train': 1.37331223487854}
-03/05/2022 04:07:32 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/05/2022 04:07:35 - INFO - codeparrot_training - Step 32896: {'lr': 0.0004481357124000672, 'samples': 16843264, 'steps': 32896, 'loss/train': 2.0404725074768066}
-03/05/2022 04:07:38 - INFO - codeparrot_training - Step 32897: {'lr': 0.0004481324762166099, 'samples': 16843776, 'steps': 32897, 'loss/train': 2.410694122314453}
-03/05/2022 04:07:41 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/05/2022 04:07:43 - INFO - codeparrot_training - Step 32898: {'lr': 0.0004481292399438771, 'samples': 16844288, 'steps': 32898, 'loss/train': 1.8052374124526978}
-03/05/2022 04:07:46 - INFO - codeparrot_training - Step 32899: {'lr': 0.0004481260035818704, 'samples': 16844800, 'steps': 32899, 'loss/train': 1.1577407121658325}
-03/05/2022 04:07:49 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 04:07:52 - INFO - codeparrot_training - Step 32900: {'lr': 0.00044812276713059106, 'samples': 16845312, 'steps': 32900, 'loss/train': 1.1407105922698975}
-03/05/2022 04:07:55 - INFO - codeparrot_training - Step 32901: {'lr': 0.00044811953059004073, 'samples': 16845824, 'steps': 32901, 'loss/train': 3.0366439819335938}
-03/05/2022 04:07:58 - INFO - codeparrot_training - Step 32902: {'lr': 0.0004481162939602208, 'samples': 16846336, 'steps': 32902, 'loss/train': 1.4314132928848267}
-03/05/2022 04:07:58 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 04:08:03 - INFO - codeparrot_training - Step 32903: {'lr': 0.0004481130572411327, 'samples': 16846848, 'steps': 32903, 'loss/train': 1.3393806219100952}
-03/05/2022 04:08:07 - INFO - codeparrot_training - Step 32904: {'lr': 0.00044810982043277795, 'samples': 16847360, 'steps': 32904, 'loss/train': 2.32403826713562}
-03/05/2022 04:08:07 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/05/2022 04:08:12 - INFO - codeparrot_training - Step 32905: {'lr': 0.0004481065835351579, 'samples': 16847872, 'steps': 32905, 'loss/train': 1.1604489088058472}
-03/05/2022 04:08:15 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/05/2022 04:08:18 - INFO - codeparrot_training - Step 32906: {'lr': 0.0004481033465482741, 'samples': 16848384, 'steps': 32906, 'loss/train': 1.3880707025527954}
-03/05/2022 04:08:21 - INFO - codeparrot_training - Step 32907: {'lr': 0.00044810010947212803, 'samples': 16848896, 'steps': 32907, 'loss/train': 1.631986379623413}
-03/05/2022 04:08:24 - INFO - codeparrot_training - Step 32908: {'lr': 0.00044809687230672115, 'samples': 16849408, 'steps': 32908, 'loss/train': 1.8036261796951294}
-03/05/2022 04:08:24 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 04:08:29 - INFO - codeparrot_training - Step 32909: {'lr': 0.0004480936350520548, 'samples': 16849920, 'steps': 32909, 'loss/train': 2.1829309463500977}
-03/05/2022 04:08:32 - INFO - codeparrot_training - Step 32910: {'lr': 0.0004480903977081305, 'samples': 16850432, 'steps': 32910, 'loss/train': 1.823407530784607}
-03/05/2022 04:08:33 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/05/2022 04:08:38 - INFO - codeparrot_training - Step 32911: {'lr': 0.00044808716027494973, 'samples': 16850944, 'steps': 32911, 'loss/train': 0.08967943489551544}
-03/05/2022 04:08:41 - INFO - codeparrot_training - Step 32912: {'lr': 0.000448083922752514, 'samples': 16851456, 'steps': 32912, 'loss/train': 2.0421366691589355}
-03/05/2022 04:08:41 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/05/2022 04:08:46 - INFO - codeparrot_training - Step 32913: {'lr': 0.00044808068514082467, 'samples': 16851968, 'steps': 32913, 'loss/train': 1.7712178230285645}
-03/05/2022 04:08:50 - INFO - codeparrot_training - Step 32914: {'lr': 0.0004480774474398832, 'samples': 16852480, 'steps': 32914, 'loss/train': 1.859857439994812}
-03/05/2022 04:08:50 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/05/2022 04:08:55 - INFO - codeparrot_training - Step 32915: {'lr': 0.00044807420964969113, 'samples': 16852992, 'steps': 32915, 'loss/train': 0.33804088830947876}
-03/05/2022 04:08:58 - INFO - codeparrot_training - Step 32916: {'lr': 0.0004480709717702499, 'samples': 16853504, 'steps': 32916, 'loss/train': 2.5722317695617676}
-03/05/2022 04:08:59 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/05/2022 04:09:03 - INFO - codeparrot_training - Step 32917: {'lr': 0.000448067733801561, 'samples': 16854016, 'steps': 32917, 'loss/train': 1.5674976110458374}
-03/05/2022 04:09:07 - INFO - codeparrot_training - Step 32918: {'lr': 0.00044806449574362575, 'samples': 16854528, 'steps': 32918, 'loss/train': 1.0514800548553467}
-03/05/2022 04:09:08 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/05/2022 04:09:12 - INFO - codeparrot_training - Step 32919: {'lr': 0.00044806125759644567, 'samples': 16855040, 'steps': 32919, 'loss/train': 1.8234845399856567}
-03/05/2022 04:09:15 - INFO - codeparrot_training - Step 32920: {'lr': 0.00044805801936002225, 'samples': 16855552, 'steps': 32920, 'loss/train': 2.082367181777954}
-03/05/2022 04:09:16 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/05/2022 04:09:20 - INFO - codeparrot_training - Step 32921: {'lr': 0.00044805478103435707, 'samples': 16856064, 'steps': 32921, 'loss/train': 2.083266496658325}
-03/05/2022 04:09:23 - INFO - codeparrot_training - Step 32922: {'lr': 0.0004480515426194513, 'samples': 16856576, 'steps': 32922, 'loss/train': 1.7718514204025269}
-03/05/2022 04:09:24 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/05/2022 04:09:29 - INFO - codeparrot_training - Step 32923: {'lr': 0.0004480483041153066, 'samples': 16857088, 'steps': 32923, 'loss/train': 1.1922067403793335}
-03/05/2022 04:09:32 - INFO - codeparrot_training - Step 32924: {'lr': 0.00044804506552192447, 'samples': 16857600, 'steps': 32924, 'loss/train': 2.181920289993286}
-03/05/2022 04:09:32 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/05/2022 04:09:37 - INFO - codeparrot_training - Step 32925: {'lr': 0.0004480418268393062, 'samples': 16858112, 'steps': 32925, 'loss/train': 1.1025288105010986}
-03/05/2022 04:09:40 - INFO - codeparrot_training - Step 32926: {'lr': 0.0004480385880674534, 'samples': 16858624, 'steps': 32926, 'loss/train': 0.1388394832611084}
-03/05/2022 04:09:41 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/05/2022 04:09:46 - INFO - codeparrot_training - Step 32927: {'lr': 0.00044803534920636744, 'samples': 16859136, 'steps': 32927, 'loss/train': 1.7906074523925781}
-03/05/2022 04:09:49 - INFO - codeparrot_training - Step 32928: {'lr': 0.00044803211025604985, 'samples': 16859648, 'steps': 32928, 'loss/train': 5.568546295166016}
-03/05/2022 04:09:49 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/05/2022 04:09:54 - INFO - codeparrot_training - Step 32929: {'lr': 0.000448028871216502, 'samples': 16860160, 'steps': 32929, 'loss/train': 0.21931499242782593}
-03/05/2022 04:09:57 - INFO - codeparrot_training - Step 32930: {'lr': 0.0004480256320877254, 'samples': 16860672, 'steps': 32930, 'loss/train': 1.9319590330123901}
-03/05/2022 04:09:58 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/05/2022 04:10:02 - INFO - codeparrot_training - Step 32931: {'lr': 0.00044802239286972147, 'samples': 16861184, 'steps': 32931, 'loss/train': 0.9951972961425781}
-03/05/2022 04:10:06 - INFO - codeparrot_training - Step 32932: {'lr': 0.0004480191535624918, 'samples': 16861696, 'steps': 32932, 'loss/train': 1.1043416261672974}
-03/05/2022 04:10:06 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 04:10:11 - INFO - codeparrot_training - Step 32933: {'lr': 0.0004480159141660377, 'samples': 16862208, 'steps': 32933, 'loss/train': 1.8001677989959717}
-03/05/2022 04:10:14 - INFO - codeparrot_training - Step 32934: {'lr': 0.00044801267468036064, 'samples': 16862720, 'steps': 32934, 'loss/train': 2.076057195663452}
-03/05/2022 04:10:14 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/05/2022 04:10:19 - INFO - codeparrot_training - Step 32935: {'lr': 0.0004480094351054622, 'samples': 16863232, 'steps': 32935, 'loss/train': 1.3910447359085083}
-03/05/2022 04:10:22 - INFO - codeparrot_training - Step 32936: {'lr': 0.00044800619544134375, 'samples': 16863744, 'steps': 32936, 'loss/train': 2.0677878856658936}
-03/05/2022 04:10:22 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/05/2022 04:10:28 - INFO - codeparrot_training - Step 32937: {'lr': 0.00044800295568800673, 'samples': 16864256, 'steps': 32937, 'loss/train': 1.7169177532196045}
-03/05/2022 04:10:31 - INFO - codeparrot_training - Step 32938: {'lr': 0.0004479997158454526, 'samples': 16864768, 'steps': 32938, 'loss/train': 1.739062786102295}
-03/05/2022 04:10:31 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/05/2022 04:10:36 - INFO - codeparrot_training - Step 32939: {'lr': 0.00044799647591368296, 'samples': 16865280, 'steps': 32939, 'loss/train': 1.8108279705047607}
-03/05/2022 04:10:39 - INFO - codeparrot_training - Step 32940: {'lr': 0.00044799323589269914, 'samples': 16865792, 'steps': 32940, 'loss/train': 1.9718165397644043}
-03/05/2022 04:10:39 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/05/2022 04:10:45 - INFO - codeparrot_training - Step 32941: {'lr': 0.00044798999578250255, 'samples': 16866304, 'steps': 32941, 'loss/train': 1.542114019393921}
-03/05/2022 04:10:48 - INFO - codeparrot_training - Step 32942: {'lr': 0.0004479867555830948, 'samples': 16866816, 'steps': 32942, 'loss/train': 1.9566525220870972}
-03/05/2022 04:10:48 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/05/2022 04:10:53 - INFO - codeparrot_training - Step 32943: {'lr': 0.0004479835152944772, 'samples': 16867328, 'steps': 32943, 'loss/train': 2.2091989517211914}
-03/05/2022 04:10:56 - INFO - codeparrot_training - Step 32944: {'lr': 0.00044798027491665135, 'samples': 16867840, 'steps': 32944, 'loss/train': 2.3931496143341064}
-03/05/2022 04:11:02 - INFO - codeparrot_training - Step 32945: {'lr': 0.00044797703444961857, 'samples': 16868352, 'steps': 32945, 'loss/train': 2.2849676609039307}
-03/05/2022 04:11:05 - INFO - codeparrot_training - Step 32946: {'lr': 0.00044797379389338045, 'samples': 16868864, 'steps': 32946, 'loss/train': 1.1501230001449585}
-03/05/2022 04:11:05 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/05/2022 04:11:10 - INFO - codeparrot_training - Step 32947: {'lr': 0.0004479705532479384, 'samples': 16869376, 'steps': 32947, 'loss/train': 1.5604846477508545}
-03/05/2022 04:11:13 - INFO - codeparrot_training - Step 32948: {'lr': 0.0004479673125132938, 'samples': 16869888, 'steps': 32948, 'loss/train': 1.7970181703567505}
-03/05/2022 04:11:14 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/05/2022 04:11:19 - INFO - codeparrot_training - Step 32949: {'lr': 0.0004479640716894483, 'samples': 16870400, 'steps': 32949, 'loss/train': 0.5720889568328857}
-03/05/2022 04:11:22 - INFO - codeparrot_training - Step 32950: {'lr': 0.00044796083077640314, 'samples': 16870912, 'steps': 32950, 'loss/train': 1.4395393133163452}
-03/05/2022 04:11:22 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/05/2022 04:11:27 - INFO - codeparrot_training - Step 32951: {'lr': 0.00044795758977416, 'samples': 16871424, 'steps': 32951, 'loss/train': 1.7781352996826172}
-03/05/2022 04:11:30 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/05/2022 04:11:32 - INFO - codeparrot_training - Step 32952: {'lr': 0.0004479543486827201, 'samples': 16871936, 'steps': 32952, 'loss/train': 1.1561284065246582}
-03/05/2022 04:11:35 - INFO - codeparrot_training - Step 32953: {'lr': 0.0004479511075020851, 'samples': 16872448, 'steps': 32953, 'loss/train': 1.6943188905715942}
-03/05/2022 04:11:38 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/05/2022 04:11:41 - INFO - codeparrot_training - Step 32954: {'lr': 0.00044794786623225636, 'samples': 16872960, 'steps': 32954, 'loss/train': 0.9862486720085144}
-03/05/2022 04:11:44 - INFO - codeparrot_training - Step 32955: {'lr': 0.0004479446248732354, 'samples': 16873472, 'steps': 32955, 'loss/train': 1.4168609380722046}
-03/05/2022 04:11:46 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 04:11:49 - INFO - codeparrot_training - Step 32956: {'lr': 0.00044794138342502354, 'samples': 16873984, 'steps': 32956, 'loss/train': 0.8822023272514343}
-03/05/2022 04:11:52 - INFO - codeparrot_training - Step 32957: {'lr': 0.0004479381418876225, 'samples': 16874496, 'steps': 32957, 'loss/train': 1.8924466371536255}
-03/05/2022 04:11:55 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 04:11:57 - INFO - codeparrot_training - Step 32958: {'lr': 0.00044793490026103346, 'samples': 16875008, 'steps': 32958, 'loss/train': 1.4720741510391235}
-03/05/2022 04:12:01 - INFO - codeparrot_training - Step 32959: {'lr': 0.0004479316585452581, 'samples': 16875520, 'steps': 32959, 'loss/train': 1.7246819734573364}
-03/05/2022 04:12:03 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 04:12:06 - INFO - codeparrot_training - Step 32960: {'lr': 0.0004479284167402977, 'samples': 16876032, 'steps': 32960, 'loss/train': 1.6629647016525269}
-03/05/2022 04:12:09 - INFO - codeparrot_training - Step 32961: {'lr': 0.00044792517484615384, 'samples': 16876544, 'steps': 32961, 'loss/train': 1.6395092010498047}
-03/05/2022 04:12:11 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/05/2022 04:12:15 - INFO - codeparrot_training - Step 32962: {'lr': 0.000447921932862828, 'samples': 16877056, 'steps': 32962, 'loss/train': 1.8148956298828125}
-03/05/2022 04:12:18 - INFO - codeparrot_training - Step 32963: {'lr': 0.00044791869079032154, 'samples': 16877568, 'steps': 32963, 'loss/train': 2.174255609512329}
-03/05/2022 04:12:21 - INFO - codeparrot_training - Step 32964: {'lr': 0.000447915448628636, 'samples': 16878080, 'steps': 32964, 'loss/train': 5.452362060546875}
-03/05/2022 04:12:22 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 04:12:26 - INFO - codeparrot_training - Step 32965: {'lr': 0.0004479122063777728, 'samples': 16878592, 'steps': 32965, 'loss/train': 2.160876989364624}
-03/05/2022 04:12:29 - INFO - codeparrot_training - Step 32966: {'lr': 0.0004479089640377334, 'samples': 16879104, 'steps': 32966, 'loss/train': 1.7248125076293945}
-03/05/2022 04:12:30 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/05/2022 04:12:35 - INFO - codeparrot_training - Step 32967: {'lr': 0.00044790572160851926, 'samples': 16879616, 'steps': 32967, 'loss/train': 1.7237592935562134}
-03/05/2022 04:12:38 - INFO - codeparrot_training - Step 32968: {'lr': 0.00044790247909013195, 'samples': 16880128, 'steps': 32968, 'loss/train': 1.6506916284561157}
-03/05/2022 04:12:38 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/05/2022 04:12:43 - INFO - codeparrot_training - Step 32969: {'lr': 0.0004478992364825728, 'samples': 16880640, 'steps': 32969, 'loss/train': 2.5072579383850098}
-03/05/2022 04:12:46 - INFO - codeparrot_training - Step 32970: {'lr': 0.00044789599378584324, 'samples': 16881152, 'steps': 32970, 'loss/train': 0.46988773345947266}
-03/05/2022 04:12:47 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/05/2022 04:12:52 - INFO - codeparrot_training - Step 32971: {'lr': 0.0004478927509999449, 'samples': 16881664, 'steps': 32971, 'loss/train': 1.8728784322738647}
-03/05/2022 04:12:55 - INFO - codeparrot_training - Step 32972: {'lr': 0.00044788950812487907, 'samples': 16882176, 'steps': 32972, 'loss/train': 1.9999496936798096}
-03/05/2022 04:12:55 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 04:13:00 - INFO - codeparrot_training - Step 32973: {'lr': 0.0004478862651606472, 'samples': 16882688, 'steps': 32973, 'loss/train': 0.8502224683761597}
-03/05/2022 04:13:03 - INFO - codeparrot_training - Step 32974: {'lr': 0.000447883022107251, 'samples': 16883200, 'steps': 32974, 'loss/train': 1.6958385705947876}
-03/05/2022 04:13:04 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/05/2022 04:13:08 - INFO - codeparrot_training - Step 32975: {'lr': 0.00044787977896469167, 'samples': 16883712, 'steps': 32975, 'loss/train': 1.6159026622772217}
-03/05/2022 04:13:12 - INFO - codeparrot_training - Step 32976: {'lr': 0.0004478765357329708, 'samples': 16884224, 'steps': 32976, 'loss/train': 1.754978060722351}
-03/05/2022 04:13:12 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/05/2022 04:13:17 - INFO - codeparrot_training - Step 32977: {'lr': 0.0004478732924120897, 'samples': 16884736, 'steps': 32977, 'loss/train': 2.27590274810791}
-03/05/2022 04:13:20 - INFO - codeparrot_training - Step 32978: {'lr': 0.0004478700490020501, 'samples': 16885248, 'steps': 32978, 'loss/train': 1.645606517791748}
-03/05/2022 04:13:20 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/05/2022 04:13:25 - INFO - codeparrot_training - Step 32979: {'lr': 0.0004478668055028533, 'samples': 16885760, 'steps': 32979, 'loss/train': 1.6534570455551147}
-03/05/2022 04:13:28 - INFO - codeparrot_training - Step 32980: {'lr': 0.0004478635619145007, 'samples': 16886272, 'steps': 32980, 'loss/train': 1.9479100704193115}
-03/05/2022 04:13:29 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 04:13:34 - INFO - codeparrot_training - Step 32981: {'lr': 0.00044786031823699384, 'samples': 16886784, 'steps': 32981, 'loss/train': 2.95906662940979}
-03/05/2022 04:13:37 - INFO - codeparrot_training - Step 32982: {'lr': 0.0004478570744703342, 'samples': 16887296, 'steps': 32982, 'loss/train': 1.5737457275390625}
-03/05/2022 04:13:37 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/05/2022 04:13:42 - INFO - codeparrot_training - Step 32983: {'lr': 0.00044785383061452324, 'samples': 16887808, 'steps': 32983, 'loss/train': 2.577038049697876}
-03/05/2022 04:13:45 - INFO - codeparrot_training - Step 32984: {'lr': 0.00044785058666956234, 'samples': 16888320, 'steps': 32984, 'loss/train': 1.4159278869628906}
-03/05/2022 04:13:45 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/05/2022 04:13:50 - INFO - codeparrot_training - Step 32985: {'lr': 0.000447847342635453, 'samples': 16888832, 'steps': 32985, 'loss/train': 1.6427963972091675}
-03/05/2022 04:13:53 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/05/2022 04:13:56 - INFO - codeparrot_training - Step 32986: {'lr': 0.00044784409851219675, 'samples': 16889344, 'steps': 32986, 'loss/train': 2.015334367752075}
-03/05/2022 04:13:59 - INFO - codeparrot_training - Step 32987: {'lr': 0.00044784085429979504, 'samples': 16889856, 'steps': 32987, 'loss/train': 1.1424051523208618}
-03/05/2022 04:14:02 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 04:14:04 - INFO - codeparrot_training - Step 32988: {'lr': 0.00044783760999824926, 'samples': 16890368, 'steps': 32988, 'loss/train': 1.9466280937194824}
-03/05/2022 04:14:07 - INFO - codeparrot_training - Step 32989: {'lr': 0.00044783436560756086, 'samples': 16890880, 'steps': 32989, 'loss/train': 1.3393410444259644}
-03/05/2022 04:14:10 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 04:14:12 - INFO - codeparrot_training - Step 32990: {'lr': 0.00044783112112773137, 'samples': 16891392, 'steps': 32990, 'loss/train': 1.3325341939926147}
-03/05/2022 04:14:16 - INFO - codeparrot_training - Step 32991: {'lr': 0.0004478278765587623, 'samples': 16891904, 'steps': 32991, 'loss/train': 1.4183118343353271}
-03/05/2022 04:14:18 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/05/2022 04:14:21 - INFO - codeparrot_training - Step 32992: {'lr': 0.000447824631900655, 'samples': 16892416, 'steps': 32992, 'loss/train': 2.4589672088623047}
-03/05/2022 04:14:24 - INFO - codeparrot_training - Step 32993: {'lr': 0.00044782138715341094, 'samples': 16892928, 'steps': 32993, 'loss/train': 1.7131288051605225}
-03/05/2022 04:14:26 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 04:14:29 - INFO - codeparrot_training - Step 32994: {'lr': 0.00044781814231703164, 'samples': 16893440, 'steps': 32994, 'loss/train': 1.8118724822998047}
-03/05/2022 04:14:32 - INFO - codeparrot_training - Step 32995: {'lr': 0.00044781489739151856, 'samples': 16893952, 'steps': 32995, 'loss/train': 1.2344074249267578}
-03/05/2022 04:14:35 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/05/2022 04:14:38 - INFO - codeparrot_training - Step 32996: {'lr': 0.00044781165237687306, 'samples': 16894464, 'steps': 32996, 'loss/train': 1.0614559650421143}
-03/05/2022 04:14:41 - INFO - codeparrot_training - Step 32997: {'lr': 0.00044780840727309676, 'samples': 16894976, 'steps': 32997, 'loss/train': 1.1566686630249023}
-03/05/2022 04:14:43 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 04:14:46 - INFO - codeparrot_training - Step 32998: {'lr': 0.000447805162080191, 'samples': 16895488, 'steps': 32998, 'loss/train': 1.7748897075653076}
-03/05/2022 04:14:49 - INFO - codeparrot_training - Step 32999: {'lr': 0.0004478019167981573, 'samples': 16896000, 'steps': 32999, 'loss/train': 1.5093451738357544}
-03/05/2022 04:14:51 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/05/2022 04:14:55 - INFO - codeparrot_training - Step 33000: {'lr': 0.00044779867142699713, 'samples': 16896512, 'steps': 33000, 'loss/train': 1.4905484914779663}
-03/05/2022 04:14:58 - INFO - codeparrot_training - Step 33001: {'lr': 0.0004477954259667119, 'samples': 16897024, 'steps': 33001, 'loss/train': 2.0186970233917236}
-03/05/2022 04:15:00 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/05/2022 04:15:03 - INFO - codeparrot_training - Step 33002: {'lr': 0.00044779218041730314, 'samples': 16897536, 'steps': 33002, 'loss/train': 2.1597375869750977}
-03/05/2022 04:15:06 - INFO - codeparrot_training - Step 33003: {'lr': 0.00044778893477877225, 'samples': 16898048, 'steps': 33003, 'loss/train': 1.7150853872299194}
-03/05/2022 04:15:09 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/05/2022 04:15:11 - INFO - codeparrot_training - Step 33004: {'lr': 0.0004477856890511207, 'samples': 16898560, 'steps': 33004, 'loss/train': 1.1960991621017456}
-03/05/2022 04:15:15 - INFO - codeparrot_training - Step 33005: {'lr': 0.00044778244323435, 'samples': 16899072, 'steps': 33005, 'loss/train': 2.00954008102417}
-03/05/2022 04:15:17 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/05/2022 04:15:20 - INFO - codeparrot_training - Step 33006: {'lr': 0.0004477791973284616, 'samples': 16899584, 'steps': 33006, 'loss/train': 2.0102460384368896}
-03/05/2022 04:15:23 - INFO - codeparrot_training - Step 33007: {'lr': 0.00044777595133345686, 'samples': 16900096, 'steps': 33007, 'loss/train': 0.05891214683651924}
-03/05/2022 04:15:25 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/05/2022 04:15:28 - INFO - codeparrot_training - Step 33008: {'lr': 0.0004477727052493374, 'samples': 16900608, 'steps': 33008, 'loss/train': 1.1184289455413818}
-03/05/2022 04:15:32 - INFO - codeparrot_training - Step 33009: {'lr': 0.0004477694590761046, 'samples': 16901120, 'steps': 33009, 'loss/train': 0.05224824696779251}
-03/05/2022 04:15:34 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 04:15:37 - INFO - codeparrot_training - Step 33010: {'lr': 0.00044776621281375994, 'samples': 16901632, 'steps': 33010, 'loss/train': 1.8125286102294922}
-03/05/2022 04:15:40 - INFO - codeparrot_training - Step 33011: {'lr': 0.00044776296646230487, 'samples': 16902144, 'steps': 33011, 'loss/train': 2.3796088695526123}
-03/05/2022 04:15:42 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/05/2022 04:15:45 - INFO - codeparrot_training - Step 33012: {'lr': 0.00044775972002174085, 'samples': 16902656, 'steps': 33012, 'loss/train': 1.739351749420166}
-03/05/2022 04:15:48 - INFO - codeparrot_training - Step 33013: {'lr': 0.0004477564734920694, 'samples': 16903168, 'steps': 33013, 'loss/train': 0.966182291507721}
-03/05/2022 04:15:50 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/05/2022 04:15:54 - INFO - codeparrot_training - Step 33014: {'lr': 0.0004477532268732919, 'samples': 16903680, 'steps': 33014, 'loss/train': 1.606831431388855}
-03/05/2022 04:15:57 - INFO - codeparrot_training - Step 33015: {'lr': 0.00044774998016540977, 'samples': 16904192, 'steps': 33015, 'loss/train': 1.6030378341674805}
-03/05/2022 04:15:58 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/05/2022 04:16:03 - INFO - codeparrot_training - Step 33016: {'lr': 0.00044774673336842464, 'samples': 16904704, 'steps': 33016, 'loss/train': 2.202526330947876}
-03/05/2022 04:16:06 - INFO - codeparrot_training - Step 33017: {'lr': 0.0004477434864823379, 'samples': 16905216, 'steps': 33017, 'loss/train': 1.2800613641738892}
-03/05/2022 04:16:09 - INFO - codeparrot_training - Step 33018: {'lr': 0.00044774023950715095, 'samples': 16905728, 'steps': 33018, 'loss/train': 1.3114080429077148}
-03/05/2022 04:16:10 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/05/2022 04:16:14 - INFO - codeparrot_training - Step 33019: {'lr': 0.0004477369924428653, 'samples': 16906240, 'steps': 33019, 'loss/train': 1.9431343078613281}
-03/05/2022 04:16:17 - INFO - codeparrot_training - Step 33020: {'lr': 0.0004477337452894824, 'samples': 16906752, 'steps': 33020, 'loss/train': 1.983815312385559}
-03/05/2022 04:16:18 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 04:16:23 - INFO - codeparrot_training - Step 33021: {'lr': 0.0004477304980470038, 'samples': 16907264, 'steps': 33021, 'loss/train': 0.5019639730453491}
-03/05/2022 04:16:26 - INFO - codeparrot_training - Step 33022: {'lr': 0.0004477272507154308, 'samples': 16907776, 'steps': 33022, 'loss/train': 1.659754991531372}
-03/05/2022 04:16:26 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/05/2022 04:16:31 - INFO - codeparrot_training - Step 33023: {'lr': 0.00044772400329476505, 'samples': 16908288, 'steps': 33023, 'loss/train': 1.7549325227737427}
-03/05/2022 04:16:34 - INFO - codeparrot_training - Step 33024: {'lr': 0.0004477207557850078, 'samples': 16908800, 'steps': 33024, 'loss/train': 0.8928710222244263}
-03/05/2022 04:16:35 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/05/2022 04:16:39 - INFO - codeparrot_training - Step 33025: {'lr': 0.00044771750818616067, 'samples': 16909312, 'steps': 33025, 'loss/train': 1.886451244354248}
-03/05/2022 04:16:43 - INFO - codeparrot_training - Step 33026: {'lr': 0.0004477142604982251, 'samples': 16909824, 'steps': 33026, 'loss/train': 1.3175508975982666}
-03/05/2022 04:16:43 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/05/2022 04:16:48 - INFO - codeparrot_training - Step 33027: {'lr': 0.0004477110127212025, 'samples': 16910336, 'steps': 33027, 'loss/train': 2.170865297317505}
-03/05/2022 04:16:51 - INFO - codeparrot_training - Step 33028: {'lr': 0.00044770776485509445, 'samples': 16910848, 'steps': 33028, 'loss/train': 1.8284481763839722}
-03/05/2022 04:16:51 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/05/2022 04:16:56 - INFO - codeparrot_training - Step 33029: {'lr': 0.00044770451689990227, 'samples': 16911360, 'steps': 33029, 'loss/train': 2.1039533615112305}
-03/05/2022 04:16:59 - INFO - codeparrot_training - Step 33030: {'lr': 0.0004477012688556275, 'samples': 16911872, 'steps': 33030, 'loss/train': 1.4315627813339233}
-03/05/2022 04:16:59 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/05/2022 04:17:05 - INFO - codeparrot_training - Step 33031: {'lr': 0.0004476980207222716, 'samples': 16912384, 'steps': 33031, 'loss/train': 1.7976057529449463}
-03/05/2022 04:17:08 - INFO - codeparrot_training - Step 33032: {'lr': 0.00044769477249983596, 'samples': 16912896, 'steps': 33032, 'loss/train': 1.3541350364685059}
-03/05/2022 04:17:08 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/05/2022 04:17:13 - INFO - codeparrot_training - Step 33033: {'lr': 0.00044769152418832215, 'samples': 16913408, 'steps': 33033, 'loss/train': 0.954656183719635}
-03/05/2022 04:17:16 - INFO - codeparrot_training - Step 33034: {'lr': 0.00044768827578773164, 'samples': 16913920, 'steps': 33034, 'loss/train': 1.6620924472808838}
-03/05/2022 04:17:16 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/05/2022 04:17:22 - INFO - codeparrot_training - Step 33035: {'lr': 0.00044768502729806574, 'samples': 16914432, 'steps': 33035, 'loss/train': 0.0657031387090683}
-03/05/2022 04:17:25 - INFO - codeparrot_training - Step 33036: {'lr': 0.0004476817787193261, 'samples': 16914944, 'steps': 33036, 'loss/train': 2.6146161556243896}
-03/05/2022 04:17:25 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/05/2022 04:17:30 - INFO - codeparrot_training - Step 33037: {'lr': 0.0004476785300515141, 'samples': 16915456, 'steps': 33037, 'loss/train': 1.4477626085281372}
-03/05/2022 04:17:33 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/05/2022 04:17:35 - INFO - codeparrot_training - Step 33038: {'lr': 0.0004476752812946312, 'samples': 16915968, 'steps': 33038, 'loss/train': 1.442064642906189}
-03/05/2022 04:17:38 - INFO - codeparrot_training - Step 33039: {'lr': 0.0004476720324486788, 'samples': 16916480, 'steps': 33039, 'loss/train': 0.7201438546180725}
-03/05/2022 04:17:41 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 04:17:44 - INFO - codeparrot_training - Step 33040: {'lr': 0.0004476687835136585, 'samples': 16916992, 'steps': 33040, 'loss/train': 0.7878016829490662}
-03/05/2022 04:17:47 - INFO - codeparrot_training - Step 33041: {'lr': 0.0004476655344895717, 'samples': 16917504, 'steps': 33041, 'loss/train': 1.5895615816116333}
-03/05/2022 04:17:50 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/05/2022 04:17:52 - INFO - codeparrot_training - Step 33042: {'lr': 0.0004476622853764198, 'samples': 16918016, 'steps': 33042, 'loss/train': 2.5252041816711426}
-03/05/2022 04:17:55 - INFO - codeparrot_training - Step 33043: {'lr': 0.00044765903617420436, 'samples': 16918528, 'steps': 33043, 'loss/train': 2.5129315853118896}
-03/05/2022 04:17:58 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/05/2022 04:18:01 - INFO - codeparrot_training - Step 33044: {'lr': 0.00044765578688292686, 'samples': 16919040, 'steps': 33044, 'loss/train': 2.534588098526001}
-03/05/2022 04:18:04 - INFO - codeparrot_training - Step 33045: {'lr': 0.0004476525375025886, 'samples': 16919552, 'steps': 33045, 'loss/train': 1.2728670835494995}
-03/05/2022 04:18:07 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/05/2022 04:18:09 - INFO - codeparrot_training - Step 33046: {'lr': 0.00044764928803319126, 'samples': 16920064, 'steps': 33046, 'loss/train': 1.235376238822937}
-03/05/2022 04:18:12 - INFO - codeparrot_training - Step 33047: {'lr': 0.00044764603847473615, 'samples': 16920576, 'steps': 33047, 'loss/train': 1.8117481470108032}
-03/05/2022 04:18:15 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/05/2022 04:18:17 - INFO - codeparrot_training - Step 33048: {'lr': 0.0004476427888272248, 'samples': 16921088, 'steps': 33048, 'loss/train': 1.74118971824646}
-03/05/2022 04:18:21 - INFO - codeparrot_training - Step 33049: {'lr': 0.0004476395390906586, 'samples': 16921600, 'steps': 33049, 'loss/train': 1.5807212591171265}
-03/05/2022 04:18:23 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/05/2022 04:18:26 - INFO - codeparrot_training - Step 33050: {'lr': 0.0004476362892650392, 'samples': 16922112, 'steps': 33050, 'loss/train': 1.9261671304702759}
-03/05/2022 04:18:29 - INFO - codeparrot_training - Step 33051: {'lr': 0.0004476330393503678, 'samples': 16922624, 'steps': 33051, 'loss/train': 1.978813886642456}
-03/05/2022 04:18:31 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/05/2022 04:18:34 - INFO - codeparrot_training - Step 33052: {'lr': 0.0004476297893466461, 'samples': 16923136, 'steps': 33052, 'loss/train': 1.574313759803772}
-03/05/2022 04:18:37 - INFO - codeparrot_training - Step 33053: {'lr': 0.0004476265392538754, 'samples': 16923648, 'steps': 33053, 'loss/train': 2.2591452598571777}
-03/05/2022 04:18:40 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/05/2022 04:18:43 - INFO - codeparrot_training - Step 33054: {'lr': 0.0004476232890720573, 'samples': 16924160, 'steps': 33054, 'loss/train': 0.21593250334262848}
-03/05/2022 04:18:46 - INFO - codeparrot_training - Step 33055: {'lr': 0.0004476200388011932, 'samples': 16924672, 'steps': 33055, 'loss/train': 2.560988187789917}
-03/05/2022 04:18:48 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/05/2022 04:18:51 - INFO - codeparrot_training - Step 33056: {'lr': 0.0004476167884412845, 'samples': 16925184, 'steps': 33056, 'loss/train': 1.9278711080551147}
-03/05/2022 04:18:54 - INFO - codeparrot_training - Step 33057: {'lr': 0.00044761353799233273, 'samples': 16925696, 'steps': 33057, 'loss/train': 0.09464825689792633}
-03/05/2022 04:18:57 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/05/2022 04:19:00 - INFO - codeparrot_training - Step 33058: {'lr': 0.00044761028745433934, 'samples': 16926208, 'steps': 33058, 'loss/train': 1.5981062650680542}
-03/05/2022 04:19:03 - INFO - codeparrot_training - Step 33059: {'lr': 0.00044760703682730584, 'samples': 16926720, 'steps': 33059, 'loss/train': 0.5028110146522522}
-03/05/2022 04:19:05 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/05/2022 04:19:08 - INFO - codeparrot_training - Step 33060: {'lr': 0.00044760378611123365, 'samples': 16927232, 'steps': 33060, 'loss/train': 1.439496397972107}
-03/05/2022 04:19:11 - INFO - codeparrot_training - Step 33061: {'lr': 0.0004476005353061242, 'samples': 16927744, 'steps': 33061, 'loss/train': 2.2588398456573486}
-03/05/2022 04:19:14 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/05/2022 04:19:16 - INFO - codeparrot_training - Step 33062: {'lr': 0.00044759728441197904, 'samples': 16928256, 'steps': 33062, 'loss/train': 1.6910161972045898}
-03/05/2022 04:19:20 - INFO - codeparrot_training - Step 33063: {'lr': 0.0004475940334287996, 'samples': 16928768, 'steps': 33063, 'loss/train': 2.3105356693267822}
-03/05/2022 04:19:22 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 04:19:25 - INFO - codeparrot_training - Step 33064: {'lr': 0.0004475907823565873, 'samples': 16929280, 'steps': 33064, 'loss/train': 2.732370615005493}
-03/05/2022 04:19:28 - INFO - codeparrot_training - Step 33065: {'lr': 0.00044758753119534373, 'samples': 16929792, 'steps': 33065, 'loss/train': 2.0259897708892822}
-03/05/2022 04:19:31 - INFO - codeparrot_training - Step 33066: {'lr': 0.0004475842799450702, 'samples': 16930304, 'steps': 33066, 'loss/train': 2.103271007537842}
-03/05/2022 04:19:31 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/05/2022 04:19:37 - INFO - codeparrot_training - Step 33067: {'lr': 0.0004475810286057682, 'samples': 16930816, 'steps': 33067, 'loss/train': 0.9005130529403687}
-03/05/2022 04:19:39 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 04:19:42 - INFO - codeparrot_training - Step 33068: {'lr': 0.0004475777771774393, 'samples': 16931328, 'steps': 33068, 'loss/train': 1.537448525428772}
-03/05/2022 04:19:45 - INFO - codeparrot_training - Step 33069: {'lr': 0.00044757452566008497, 'samples': 16931840, 'steps': 33069, 'loss/train': 1.4250881671905518}
-03/05/2022 04:19:48 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/05/2022 04:19:50 - INFO - codeparrot_training - Step 33070: {'lr': 0.00044757127405370645, 'samples': 16932352, 'steps': 33070, 'loss/train': 1.5197818279266357}
-03/05/2022 04:19:53 - INFO - codeparrot_training - Step 33071: {'lr': 0.00044756802235830544, 'samples': 16932864, 'steps': 33071, 'loss/train': 1.6353663206100464}
-03/05/2022 04:19:56 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 04:19:59 - INFO - codeparrot_training - Step 33072: {'lr': 0.00044756477057388336, 'samples': 16933376, 'steps': 33072, 'loss/train': 0.8650037050247192}
-03/05/2022 04:20:02 - INFO - codeparrot_training - Step 33073: {'lr': 0.0004475615187004416, 'samples': 16933888, 'steps': 33073, 'loss/train': 1.7573469877243042}
-03/05/2022 04:20:04 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/05/2022 04:20:07 - INFO - codeparrot_training - Step 33074: {'lr': 0.0004475582667379817, 'samples': 16934400, 'steps': 33074, 'loss/train': 1.3492982387542725}
-03/05/2022 04:20:10 - INFO - codeparrot_training - Step 33075: {'lr': 0.0004475550146865051, 'samples': 16934912, 'steps': 33075, 'loss/train': 1.9725797176361084}
-03/05/2022 04:20:13 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/05/2022 04:20:16 - INFO - codeparrot_training - Step 33076: {'lr': 0.00044755176254601323, 'samples': 16935424, 'steps': 33076, 'loss/train': 1.2180640697479248}
-03/05/2022 04:20:19 - INFO - codeparrot_training - Step 33077: {'lr': 0.00044754851031650756, 'samples': 16935936, 'steps': 33077, 'loss/train': 1.948065996170044}
-03/05/2022 04:20:21 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/05/2022 04:20:24 - INFO - codeparrot_training - Step 33078: {'lr': 0.0004475452579979896, 'samples': 16936448, 'steps': 33078, 'loss/train': 1.8464277982711792}
-03/05/2022 04:20:27 - INFO - codeparrot_training - Step 33079: {'lr': 0.00044754200559046076, 'samples': 16936960, 'steps': 33079, 'loss/train': 1.9367538690567017}
-03/05/2022 04:20:29 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/05/2022 04:20:33 - INFO - codeparrot_training - Step 33080: {'lr': 0.0004475387530939226, 'samples': 16937472, 'steps': 33080, 'loss/train': 2.307396173477173}
-03/05/2022 04:20:36 - INFO - codeparrot_training - Step 33081: {'lr': 0.00044753550050837654, 'samples': 16937984, 'steps': 33081, 'loss/train': 1.8598867654800415}
-03/05/2022 04:20:38 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/05/2022 04:20:41 - INFO - codeparrot_training - Step 33082: {'lr': 0.00044753224783382394, 'samples': 16938496, 'steps': 33082, 'loss/train': 2.262383460998535}
-03/05/2022 04:20:45 - INFO - codeparrot_training - Step 33083: {'lr': 0.00044752899507026646, 'samples': 16939008, 'steps': 33083, 'loss/train': 1.4210560321807861}
-03/05/2022 04:20:48 - INFO - codeparrot_training - Step 33084: {'lr': 0.00044752574221770537, 'samples': 16939520, 'steps': 33084, 'loss/train': 1.2933735847473145}
-03/05/2022 04:20:48 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 04:20:53 - INFO - codeparrot_training - Step 33085: {'lr': 0.0004475224892761423, 'samples': 16940032, 'steps': 33085, 'loss/train': 1.797582983970642}
-03/05/2022 04:20:56 - INFO - codeparrot_training - Step 33086: {'lr': 0.00044751923624557866, 'samples': 16940544, 'steps': 33086, 'loss/train': 0.8822979927062988}
-03/05/2022 04:20:57 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/05/2022 04:21:01 - INFO - codeparrot_training - Step 33087: {'lr': 0.0004475159831260158, 'samples': 16941056, 'steps': 33087, 'loss/train': 1.564642310142517}
-03/05/2022 04:21:05 - INFO - codeparrot_training - Step 33088: {'lr': 0.00044751272991745537, 'samples': 16941568, 'steps': 33088, 'loss/train': 1.5531375408172607}
-03/05/2022 04:21:05 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/05/2022 04:21:10 - INFO - codeparrot_training - Step 33089: {'lr': 0.00044750947661989873, 'samples': 16942080, 'steps': 33089, 'loss/train': 1.2890675067901611}
-03/05/2022 04:21:13 - INFO - codeparrot_training - Step 33090: {'lr': 0.0004475062232333474, 'samples': 16942592, 'steps': 33090, 'loss/train': 1.044869065284729}
-03/05/2022 04:21:13 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/05/2022 04:21:18 - INFO - codeparrot_training - Step 33091: {'lr': 0.00044750296975780277, 'samples': 16943104, 'steps': 33091, 'loss/train': 1.585540771484375}
-03/05/2022 04:21:22 - INFO - codeparrot_training - Step 33092: {'lr': 0.00044749971619326633, 'samples': 16943616, 'steps': 33092, 'loss/train': 2.3870625495910645}
-03/05/2022 04:21:22 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/05/2022 04:21:27 - INFO - codeparrot_training - Step 33093: {'lr': 0.0004474964625397396, 'samples': 16944128, 'steps': 33093, 'loss/train': 2.506782293319702}
-03/05/2022 04:21:30 - INFO - codeparrot_training - Step 33094: {'lr': 0.000447493208797224, 'samples': 16944640, 'steps': 33094, 'loss/train': 1.5199761390686035}
-03/05/2022 04:21:30 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/05/2022 04:21:35 - INFO - codeparrot_training - Step 33095: {'lr': 0.00044748995496572105, 'samples': 16945152, 'steps': 33095, 'loss/train': 1.9823384284973145}
-03/05/2022 04:21:39 - INFO - codeparrot_training - Step 33096: {'lr': 0.0004474867010452321, 'samples': 16945664, 'steps': 33096, 'loss/train': 1.3394315242767334}
-03/05/2022 04:21:39 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 04:21:44 - INFO - codeparrot_training - Step 33097: {'lr': 0.0004474834470357587, 'samples': 16946176, 'steps': 33097, 'loss/train': 1.5819625854492188}
-03/05/2022 04:21:47 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 04:21:49 - INFO - codeparrot_training - Step 33098: {'lr': 0.00044748019293730236, 'samples': 16946688, 'steps': 33098, 'loss/train': 0.9642543196678162}
-03/05/2022 04:21:52 - INFO - codeparrot_training - Step 33099: {'lr': 0.0004474769387498645, 'samples': 16947200, 'steps': 33099, 'loss/train': 2.053542375564575}
-03/05/2022 04:21:55 - INFO - codeparrot_training - Step 33100: {'lr': 0.0004474736844734465, 'samples': 16947712, 'steps': 33100, 'loss/train': 1.1247843503952026}
-03/05/2022 04:21:56 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/05/2022 04:22:01 - INFO - codeparrot_training - Step 33101: {'lr': 0.00044747043010805, 'samples': 16948224, 'steps': 33101, 'loss/train': 2.1274490356445312}
-03/05/2022 04:22:04 - INFO - codeparrot_training - Step 33102: {'lr': 0.0004474671756536763, 'samples': 16948736, 'steps': 33102, 'loss/train': 2.713592290878296}
-03/05/2022 04:22:04 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 04:22:09 - INFO - codeparrot_training - Step 33103: {'lr': 0.00044746392111032695, 'samples': 16949248, 'steps': 33103, 'loss/train': 2.0415961742401123}
-03/05/2022 04:22:12 - INFO - codeparrot_training - Step 33104: {'lr': 0.00044746066647800343, 'samples': 16949760, 'steps': 33104, 'loss/train': 1.6582971811294556}
-03/05/2022 04:22:12 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/05/2022 04:22:17 - INFO - codeparrot_training - Step 33105: {'lr': 0.0004474574117567072, 'samples': 16950272, 'steps': 33105, 'loss/train': 1.3262115716934204}
-03/05/2022 04:22:21 - INFO - codeparrot_training - Step 33106: {'lr': 0.00044745415694643964, 'samples': 16950784, 'steps': 33106, 'loss/train': 1.4172344207763672}
-03/05/2022 04:22:21 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 04:22:26 - INFO - codeparrot_training - Step 33107: {'lr': 0.0004474509020472023, 'samples': 16951296, 'steps': 33107, 'loss/train': 6.424846172332764}
-03/05/2022 04:22:29 - INFO - codeparrot_training - Step 33108: {'lr': 0.0004474476470589967, 'samples': 16951808, 'steps': 33108, 'loss/train': 1.4720209836959839}
-03/05/2022 04:22:31 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/05/2022 04:22:35 - INFO - codeparrot_training - Step 33109: {'lr': 0.0004474443919818241, 'samples': 16952320, 'steps': 33109, 'loss/train': 1.9591988325119019}
-03/05/2022 04:22:38 - INFO - codeparrot_training - Step 33110: {'lr': 0.0004474411368156862, 'samples': 16952832, 'steps': 33110, 'loss/train': 1.7638566493988037}
-03/05/2022 04:22:39 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/05/2022 04:22:44 - INFO - codeparrot_training - Step 33111: {'lr': 0.00044743788156058437, 'samples': 16953344, 'steps': 33111, 'loss/train': 1.6902018785476685}
-03/05/2022 04:22:47 - INFO - codeparrot_training - Step 33112: {'lr': 0.00044743462621652007, 'samples': 16953856, 'steps': 33112, 'loss/train': 1.8489786386489868}
-03/05/2022 04:22:49 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/05/2022 04:22:52 - INFO - codeparrot_training - Step 33113: {'lr': 0.0004474313707834947, 'samples': 16954368, 'steps': 33113, 'loss/train': 1.8566254377365112}
-03/05/2022 04:22:55 - INFO - codeparrot_training - Step 33114: {'lr': 0.00044742811526150996, 'samples': 16954880, 'steps': 33114, 'loss/train': 1.3113315105438232}
-03/05/2022 04:22:57 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 04:23:01 - INFO - codeparrot_training - Step 33115: {'lr': 0.000447424859650567, 'samples': 16955392, 'steps': 33115, 'loss/train': 1.6944289207458496}
-03/05/2022 04:23:04 - INFO - codeparrot_training - Step 33116: {'lr': 0.00044742160395066756, 'samples': 16955904, 'steps': 33116, 'loss/train': 1.5802167654037476}
-03/05/2022 04:23:07 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 04:23:09 - INFO - codeparrot_training - Step 33117: {'lr': 0.0004474183481618129, 'samples': 16956416, 'steps': 33117, 'loss/train': 1.2100180387496948}
-03/05/2022 04:23:12 - INFO - codeparrot_training - Step 33118: {'lr': 0.00044741509228400465, 'samples': 16956928, 'steps': 33118, 'loss/train': 0.3639983534812927}
-03/05/2022 04:23:15 - INFO - codeparrot_training - Step 33119: {'lr': 0.0004474118363172441, 'samples': 16957440, 'steps': 33119, 'loss/train': 1.4498764276504517}
-03/05/2022 04:23:16 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/05/2022 04:23:21 - INFO - codeparrot_training - Step 33120: {'lr': 0.000447408580261533, 'samples': 16957952, 'steps': 33120, 'loss/train': 1.8144738674163818}
-03/05/2022 04:23:24 - INFO - codeparrot_training - Step 33121: {'lr': 0.0004474053241168725, 'samples': 16958464, 'steps': 33121, 'loss/train': 1.6722996234893799}
-03/05/2022 04:23:24 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/05/2022 04:23:29 - INFO - codeparrot_training - Step 33122: {'lr': 0.00044740206788326423, 'samples': 16958976, 'steps': 33122, 'loss/train': 1.9530354738235474}
-03/05/2022 04:23:32 - INFO - codeparrot_training - Step 33123: {'lr': 0.0004473988115607097, 'samples': 16959488, 'steps': 33123, 'loss/train': 1.8632655143737793}
-03/05/2022 04:23:38 - INFO - codeparrot_training - Step 33124: {'lr': 0.00044739555514921025, 'samples': 16960000, 'steps': 33124, 'loss/train': 1.59609055519104}
-03/05/2022 04:23:41 - INFO - codeparrot_training - Step 33125: {'lr': 0.0004473922986487674, 'samples': 16960512, 'steps': 33125, 'loss/train': 1.8414554595947266}
-03/05/2022 04:23:41 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/05/2022 04:23:46 - INFO - codeparrot_training - Step 33126: {'lr': 0.00044738904205938264, 'samples': 16961024, 'steps': 33126, 'loss/train': 1.814988613128662}
-03/05/2022 04:23:49 - INFO - codeparrot_training - Step 33127: {'lr': 0.00044738578538105746, 'samples': 16961536, 'steps': 33127, 'loss/train': 2.1402242183685303}
-03/05/2022 04:23:49 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/05/2022 04:23:55 - INFO - codeparrot_training - Step 33128: {'lr': 0.0004473825286137933, 'samples': 16962048, 'steps': 33128, 'loss/train': 1.9264236688613892}
-03/05/2022 04:23:58 - INFO - codeparrot_training - Step 33129: {'lr': 0.0004473792717575915, 'samples': 16962560, 'steps': 33129, 'loss/train': 1.0212764739990234}
-03/05/2022 04:23:58 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 04:24:03 - INFO - codeparrot_training - Step 33130: {'lr': 0.00044737601481245376, 'samples': 16963072, 'steps': 33130, 'loss/train': 1.0782076120376587}
-03/05/2022 04:24:06 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/05/2022 04:24:08 - INFO - codeparrot_training - Step 33131: {'lr': 0.00044737275777838136, 'samples': 16963584, 'steps': 33131, 'loss/train': 1.4459834098815918}
-03/05/2022 04:24:12 - INFO - codeparrot_training - Step 33132: {'lr': 0.0004473695006553759, 'samples': 16964096, 'steps': 33132, 'loss/train': 2.4437780380249023}
-03/05/2022 04:24:14 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/05/2022 04:24:17 - INFO - codeparrot_training - Step 33133: {'lr': 0.0004473662434434388, 'samples': 16964608, 'steps': 33133, 'loss/train': 1.305116891860962}
-03/05/2022 04:24:20 - INFO - codeparrot_training - Step 33134: {'lr': 0.00044736298614257144, 'samples': 16965120, 'steps': 33134, 'loss/train': 2.374018907546997}
-03/05/2022 04:24:23 - INFO - codeparrot_training - Step 33135: {'lr': 0.0004473597287527754, 'samples': 16965632, 'steps': 33135, 'loss/train': 1.4758410453796387}
-03/05/2022 04:24:24 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 04:24:29 - INFO - codeparrot_training - Step 33136: {'lr': 0.00044735647127405216, 'samples': 16966144, 'steps': 33136, 'loss/train': 2.0594801902770996}
-03/05/2022 04:24:32 - INFO - codeparrot_training - Step 33137: {'lr': 0.00044735321370640316, 'samples': 16966656, 'steps': 33137, 'loss/train': 1.5817471742630005}
-03/05/2022 04:24:32 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/05/2022 04:24:37 - INFO - codeparrot_training - Step 33138: {'lr': 0.00044734995604982973, 'samples': 16967168, 'steps': 33138, 'loss/train': 1.5470978021621704}
-03/05/2022 04:24:40 - INFO - codeparrot_training - Step 33139: {'lr': 0.0004473466983043335, 'samples': 16967680, 'steps': 33139, 'loss/train': 2.2806003093719482}
-03/05/2022 04:24:40 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/05/2022 04:24:45 - INFO - codeparrot_training - Step 33140: {'lr': 0.0004473434404699159, 'samples': 16968192, 'steps': 33140, 'loss/train': 1.482629418373108}
-03/05/2022 04:24:48 - INFO - codeparrot_training - Step 33141: {'lr': 0.00044734018254657845, 'samples': 16968704, 'steps': 33141, 'loss/train': 1.1464323997497559}
-03/05/2022 04:24:49 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 04:24:54 - INFO - codeparrot_training - Step 33142: {'lr': 0.00044733692453432253, 'samples': 16969216, 'steps': 33142, 'loss/train': 1.6330277919769287}
-03/05/2022 04:24:57 - INFO - codeparrot_training - Step 33143: {'lr': 0.00044733366643314956, 'samples': 16969728, 'steps': 33143, 'loss/train': 0.7457121014595032}
-03/05/2022 04:24:58 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/05/2022 04:25:02 - INFO - codeparrot_training - Step 33144: {'lr': 0.00044733040824306117, 'samples': 16970240, 'steps': 33144, 'loss/train': 1.621644377708435}
-03/05/2022 04:25:06 - INFO - codeparrot_training - Step 33145: {'lr': 0.00044732714996405866, 'samples': 16970752, 'steps': 33145, 'loss/train': 1.2490003108978271}
-03/05/2022 04:25:06 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/05/2022 04:25:11 - INFO - codeparrot_training - Step 33146: {'lr': 0.0004473238915961436, 'samples': 16971264, 'steps': 33146, 'loss/train': 1.9932024478912354}
-03/05/2022 04:25:14 - INFO - codeparrot_training - Step 33147: {'lr': 0.0004473206331393175, 'samples': 16971776, 'steps': 33147, 'loss/train': 1.0518676042556763}
-03/05/2022 04:25:14 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/05/2022 04:25:19 - INFO - codeparrot_training - Step 33148: {'lr': 0.0004473173745935818, 'samples': 16972288, 'steps': 33148, 'loss/train': 2.415705919265747}
-03/05/2022 04:25:23 - INFO - codeparrot_training - Step 33149: {'lr': 0.00044731411595893785, 'samples': 16972800, 'steps': 33149, 'loss/train': 1.2922922372817993}
-03/05/2022 04:25:23 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/05/2022 04:25:28 - INFO - codeparrot_training - Step 33150: {'lr': 0.00044731085723538725, 'samples': 16973312, 'steps': 33150, 'loss/train': 1.4215087890625}
-03/05/2022 04:25:31 - INFO - codeparrot_training - Step 33151: {'lr': 0.00044730759842293136, 'samples': 16973824, 'steps': 33151, 'loss/train': 1.6480581760406494}
-03/05/2022 04:25:31 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 04:25:36 - INFO - codeparrot_training - Step 33152: {'lr': 0.0004473043395215718, 'samples': 16974336, 'steps': 33152, 'loss/train': 1.6556274890899658}
-03/05/2022 04:25:39 - INFO - codeparrot_training - Step 33153: {'lr': 0.00044730108053130986, 'samples': 16974848, 'steps': 33153, 'loss/train': 0.8544706702232361}
-03/05/2022 04:25:39 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/05/2022 04:25:45 - INFO - codeparrot_training - Step 33154: {'lr': 0.00044729782145214717, 'samples': 16975360, 'steps': 33154, 'loss/train': 1.3904697895050049}
-03/05/2022 04:25:48 - INFO - codeparrot_training - Step 33155: {'lr': 0.00044729456228408506, 'samples': 16975872, 'steps': 33155, 'loss/train': 2.405191421508789}
-03/05/2022 04:25:48 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/05/2022 04:25:53 - INFO - codeparrot_training - Step 33156: {'lr': 0.00044729130302712504, 'samples': 16976384, 'steps': 33156, 'loss/train': 0.6117886900901794}
-03/05/2022 04:25:56 - INFO - codeparrot_training - Step 33157: {'lr': 0.00044728804368126873, 'samples': 16976896, 'steps': 33157, 'loss/train': 1.6728873252868652}
-03/05/2022 04:25:57 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/05/2022 04:26:02 - INFO - codeparrot_training - Step 33158: {'lr': 0.00044728478424651744, 'samples': 16977408, 'steps': 33158, 'loss/train': 1.8064402341842651}
-03/05/2022 04:26:05 - INFO - codeparrot_training - Step 33159: {'lr': 0.0004472815247228726, 'samples': 16977920, 'steps': 33159, 'loss/train': 1.4956008195877075}
-03/05/2022 04:26:06 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 04:26:10 - INFO - codeparrot_training - Step 33160: {'lr': 0.00044727826511033577, 'samples': 16978432, 'steps': 33160, 'loss/train': 1.8971668481826782}
-03/05/2022 04:26:13 - INFO - codeparrot_training - Step 33161: {'lr': 0.0004472750054089084, 'samples': 16978944, 'steps': 33161, 'loss/train': 0.687340259552002}
-03/05/2022 04:26:14 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/05/2022 04:26:19 - INFO - codeparrot_training - Step 33162: {'lr': 0.00044727174561859194, 'samples': 16979456, 'steps': 33162, 'loss/train': 1.8402913808822632}
-03/05/2022 04:26:22 - INFO - codeparrot_training - Step 33163: {'lr': 0.00044726848573938796, 'samples': 16979968, 'steps': 33163, 'loss/train': 3.331056833267212}
-03/05/2022 04:26:22 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/05/2022 04:26:27 - INFO - codeparrot_training - Step 33164: {'lr': 0.0004472652257712978, 'samples': 16980480, 'steps': 33164, 'loss/train': 2.099949836730957}
-03/05/2022 04:26:30 - INFO - codeparrot_training - Step 33165: {'lr': 0.0004472619657143229, 'samples': 16980992, 'steps': 33165, 'loss/train': 1.7522810697555542}
-03/05/2022 04:26:30 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/05/2022 04:26:36 - INFO - codeparrot_training - Step 33166: {'lr': 0.00044725870556846495, 'samples': 16981504, 'steps': 33166, 'loss/train': 0.6204085350036621}
-03/05/2022 04:26:38 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 04:26:41 - INFO - codeparrot_training - Step 33167: {'lr': 0.00044725544533372516, 'samples': 16982016, 'steps': 33167, 'loss/train': 1.8202327489852905}
-03/05/2022 04:26:44 - INFO - codeparrot_training - Step 33168: {'lr': 0.00044725218501010514, 'samples': 16982528, 'steps': 33168, 'loss/train': 2.160159111022949}
-03/05/2022 04:26:47 - INFO - codeparrot_training - Step 33169: {'lr': 0.0004472489245976063, 'samples': 16983040, 'steps': 33169, 'loss/train': 1.1060634851455688}
-03/05/2022 04:26:47 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/05/2022 04:26:53 - INFO - codeparrot_training - Step 33170: {'lr': 0.00044724566409623013, 'samples': 16983552, 'steps': 33170, 'loss/train': 1.4933899641036987}
-03/05/2022 04:26:56 - INFO - codeparrot_training - Step 33171: {'lr': 0.0004472424035059782, 'samples': 16984064, 'steps': 33171, 'loss/train': 1.1600592136383057}
-03/05/2022 04:26:56 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/05/2022 04:27:01 - INFO - codeparrot_training - Step 33172: {'lr': 0.0004472391428268518, 'samples': 16984576, 'steps': 33172, 'loss/train': 0.935180127620697}
-03/05/2022 04:27:04 - INFO - codeparrot_training - Step 33173: {'lr': 0.00044723588205885254, 'samples': 16985088, 'steps': 33173, 'loss/train': 1.3908851146697998}
-03/05/2022 04:27:04 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/05/2022 04:27:09 - INFO - codeparrot_training - Step 33174: {'lr': 0.00044723262120198177, 'samples': 16985600, 'steps': 33174, 'loss/train': 2.400458335876465}
-03/05/2022 04:27:13 - INFO - codeparrot_training - Step 33175: {'lr': 0.00044722936025624107, 'samples': 16986112, 'steps': 33175, 'loss/train': 1.163452386856079}
-03/05/2022 04:27:13 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/05/2022 04:27:18 - INFO - codeparrot_training - Step 33176: {'lr': 0.00044722609922163184, 'samples': 16986624, 'steps': 33176, 'loss/train': 1.6472268104553223}
-03/05/2022 04:27:21 - INFO - codeparrot_training - Step 33177: {'lr': 0.0004472228380981556, 'samples': 16987136, 'steps': 33177, 'loss/train': 1.6158864498138428}
-03/05/2022 04:27:21 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/05/2022 04:27:26 - INFO - codeparrot_training - Step 33178: {'lr': 0.0004472195768858138, 'samples': 16987648, 'steps': 33178, 'loss/train': 1.4883235692977905}
-03/05/2022 04:27:29 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/05/2022 04:27:32 - INFO - codeparrot_training - Step 33179: {'lr': 0.0004472163155846078, 'samples': 16988160, 'steps': 33179, 'loss/train': 1.5981900691986084}
-03/05/2022 04:27:35 - INFO - codeparrot_training - Step 33180: {'lr': 0.0004472130541945393, 'samples': 16988672, 'steps': 33180, 'loss/train': 1.588862419128418}
-03/05/2022 04:27:38 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/05/2022 04:27:40 - INFO - codeparrot_training - Step 33181: {'lr': 0.00044720979271560963, 'samples': 16989184, 'steps': 33181, 'loss/train': 1.939510464668274}
-03/05/2022 04:27:43 - INFO - codeparrot_training - Step 33182: {'lr': 0.00044720653114782024, 'samples': 16989696, 'steps': 33182, 'loss/train': 1.5683015584945679}
-03/05/2022 04:27:46 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/05/2022 04:27:49 - INFO - codeparrot_training - Step 33183: {'lr': 0.0004472032694911726, 'samples': 16990208, 'steps': 33183, 'loss/train': 1.6475050449371338}
-03/05/2022 04:27:52 - INFO - codeparrot_training - Step 33184: {'lr': 0.0004472000077456683, 'samples': 16990720, 'steps': 33184, 'loss/train': 2.097450017929077}
-03/05/2022 04:27:54 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/05/2022 04:27:57 - INFO - codeparrot_training - Step 33185: {'lr': 0.0004471967459113086, 'samples': 16991232, 'steps': 33185, 'loss/train': 1.6029285192489624}
-03/05/2022 04:28:00 - INFO - codeparrot_training - Step 33186: {'lr': 0.0004471934839880951, 'samples': 16991744, 'steps': 33186, 'loss/train': 3.058795690536499}
-03/05/2022 04:28:03 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/05/2022 04:28:05 - INFO - codeparrot_training - Step 33187: {'lr': 0.00044719022197602933, 'samples': 16992256, 'steps': 33187, 'loss/train': 2.059544086456299}
-03/05/2022 04:28:08 - INFO - codeparrot_training - Step 33188: {'lr': 0.0004471869598751127, 'samples': 16992768, 'steps': 33188, 'loss/train': 2.651294231414795}
-03/05/2022 04:28:11 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/05/2022 04:28:14 - INFO - codeparrot_training - Step 33189: {'lr': 0.0004471836976853466, 'samples': 16993280, 'steps': 33189, 'loss/train': 2.556591510772705}
-03/05/2022 04:28:17 - INFO - codeparrot_training - Step 33190: {'lr': 0.00044718043540673257, 'samples': 16993792, 'steps': 33190, 'loss/train': 1.1929570436477661}
-03/05/2022 04:28:20 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/05/2022 04:28:22 - INFO - codeparrot_training - Step 33191: {'lr': 0.0004471771730392722, 'samples': 16994304, 'steps': 33191, 'loss/train': 1.7729196548461914}
-03/05/2022 04:28:25 - INFO - codeparrot_training - Step 33192: {'lr': 0.0004471739105829667, 'samples': 16994816, 'steps': 33192, 'loss/train': 1.9572309255599976}
-03/05/2022 04:28:28 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/05/2022 04:28:30 - INFO - codeparrot_training - Step 33193: {'lr': 0.00044717064803781773, 'samples': 16995328, 'steps': 33193, 'loss/train': 1.5869766473770142}
-03/05/2022 04:28:34 - INFO - codeparrot_training - Step 33194: {'lr': 0.00044716738540382674, 'samples': 16995840, 'steps': 33194, 'loss/train': 2.144937753677368}
-03/05/2022 04:28:36 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/05/2022 04:28:39 - INFO - codeparrot_training - Step 33195: {'lr': 0.0004471641226809951, 'samples': 16996352, 'steps': 33195, 'loss/train': 0.8947886228561401}
-03/05/2022 04:28:42 - INFO - codeparrot_training - Step 33196: {'lr': 0.0004471608598693244, 'samples': 16996864, 'steps': 33196, 'loss/train': 2.214202642440796}
-03/05/2022 04:28:45 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/05/2022 04:28:47 - INFO - codeparrot_training - Step 33197: {'lr': 0.000447157596968816, 'samples': 16997376, 'steps': 33197, 'loss/train': 1.1589488983154297}
-03/05/2022 04:28:50 - INFO - codeparrot_training - Step 33198: {'lr': 0.0004471543339794715, 'samples': 16997888, 'steps': 33198, 'loss/train': 1.6613566875457764}
-03/05/2022 04:28:53 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/05/2022 04:28:56 - INFO - codeparrot_training - Step 33199: {'lr': 0.00044715107090129223, 'samples': 16998400, 'steps': 33199, 'loss/train': 1.3289883136749268}
-03/05/2022 04:28:59 - INFO - codeparrot_training - Step 33200: {'lr': 0.00044714780773427975, 'samples': 16998912, 'steps': 33200, 'loss/train': 1.175379753112793}
-03/05/2022 04:29:02 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/05/2022 04:29:04 - INFO - codeparrot_training - Step 33201: {'lr': 0.00044714454447843555, 'samples': 16999424, 'steps': 33201, 'loss/train': 1.8422783613204956}
-03/05/2022 04:29:07 - INFO - codeparrot_training - Step 33202: {'lr': 0.0004471412811337611, 'samples': 16999936, 'steps': 33202, 'loss/train': 2.581817150115967}
-03/05/2022 04:29:10 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 04:29:13 - INFO - codeparrot_training - Step 33203: {'lr': 0.00044713801770025774, 'samples': 17000448, 'steps': 33203, 'loss/train': 1.3269267082214355}
-03/05/2022 04:29:16 - INFO - codeparrot_training - Step 33204: {'lr': 0.00044713475417792705, 'samples': 17000960, 'steps': 33204, 'loss/train': 1.0786504745483398}
-03/05/2022 04:29:18 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 04:29:21 - INFO - codeparrot_training - Step 33205: {'lr': 0.0004471314905667705, 'samples': 17001472, 'steps': 33205, 'loss/train': 2.004253625869751}
-03/05/2022 04:29:24 - INFO - codeparrot_training - Step 33206: {'lr': 0.00044712822686678955, 'samples': 17001984, 'steps': 33206, 'loss/train': 1.311555027961731}
-03/05/2022 04:29:27 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/05/2022 04:29:29 - INFO - codeparrot_training - Step 33207: {'lr': 0.00044712496307798566, 'samples': 17002496, 'steps': 33207, 'loss/train': 1.9221293926239014}
-03/05/2022 04:29:32 - INFO - codeparrot_training - Step 33208: {'lr': 0.0004471216992003603, 'samples': 17003008, 'steps': 33208, 'loss/train': 2.0810890197753906}
-03/05/2022 04:29:35 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/05/2022 04:29:38 - INFO - codeparrot_training - Step 33209: {'lr': 0.0004471184352339149, 'samples': 17003520, 'steps': 33209, 'loss/train': 1.4921197891235352}
-03/05/2022 04:29:41 - INFO - codeparrot_training - Step 33210: {'lr': 0.00044711517117865105, 'samples': 17004032, 'steps': 33210, 'loss/train': 1.4429517984390259}
-03/05/2022 04:29:43 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/05/2022 04:29:47 - INFO - codeparrot_training - Step 33211: {'lr': 0.00044711190703457005, 'samples': 17004544, 'steps': 33211, 'loss/train': 2.0883426666259766}
-03/05/2022 04:29:50 - INFO - codeparrot_training - Step 33212: {'lr': 0.00044710864280167353, 'samples': 17005056, 'steps': 33212, 'loss/train': 1.9144353866577148}
-03/05/2022 04:29:52 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/05/2022 04:29:55 - INFO - codeparrot_training - Step 33213: {'lr': 0.0004471053784799629, 'samples': 17005568, 'steps': 33213, 'loss/train': 1.1978492736816406}
-03/05/2022 04:29:58 - INFO - codeparrot_training - Step 33214: {'lr': 0.0004471021140694396, 'samples': 17006080, 'steps': 33214, 'loss/train': 1.7336554527282715}
-03/05/2022 04:30:00 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 04:30:03 - INFO - codeparrot_training - Step 33215: {'lr': 0.0004470988495701052, 'samples': 17006592, 'steps': 33215, 'loss/train': 2.7905797958374023}
-03/05/2022 04:30:07 - INFO - codeparrot_training - Step 33216: {'lr': 0.00044709558498196104, 'samples': 17007104, 'steps': 33216, 'loss/train': 2.2112233638763428}
-03/05/2022 04:30:08 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/05/2022 04:30:12 - INFO - codeparrot_training - Step 33217: {'lr': 0.00044709232030500865, 'samples': 17007616, 'steps': 33217, 'loss/train': 0.7260366082191467}
-03/05/2022 04:30:15 - INFO - codeparrot_training - Step 33218: {'lr': 0.0004470890555392495, 'samples': 17008128, 'steps': 33218, 'loss/train': 1.4261099100112915}
-03/05/2022 04:30:17 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/05/2022 04:30:21 - INFO - codeparrot_training - Step 33219: {'lr': 0.00044708579068468505, 'samples': 17008640, 'steps': 33219, 'loss/train': 1.6846941709518433}
-03/05/2022 04:30:24 - INFO - codeparrot_training - Step 33220: {'lr': 0.0004470825257413168, 'samples': 17009152, 'steps': 33220, 'loss/train': 1.5941340923309326}
-03/05/2022 04:30:25 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/05/2022 04:30:29 - INFO - codeparrot_training - Step 33221: {'lr': 0.00044707926070914624, 'samples': 17009664, 'steps': 33221, 'loss/train': 1.6662383079528809}
-03/05/2022 04:30:32 - INFO - codeparrot_training - Step 33222: {'lr': 0.0004470759955881748, 'samples': 17010176, 'steps': 33222, 'loss/train': 1.9865210056304932}
-03/05/2022 04:30:34 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 04:30:37 - INFO - codeparrot_training - Step 33223: {'lr': 0.0004470727303784039, 'samples': 17010688, 'steps': 33223, 'loss/train': 1.568503737449646}
-03/05/2022 04:30:41 - INFO - codeparrot_training - Step 33224: {'lr': 0.00044706946507983513, 'samples': 17011200, 'steps': 33224, 'loss/train': 1.9292640686035156}
-03/05/2022 04:30:42 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/05/2022 04:30:46 - INFO - codeparrot_training - Step 33225: {'lr': 0.00044706619969246984, 'samples': 17011712, 'steps': 33225, 'loss/train': 1.674340844154358}
-03/05/2022 04:30:49 - INFO - codeparrot_training - Step 33226: {'lr': 0.0004470629342163096, 'samples': 17012224, 'steps': 33226, 'loss/train': 1.9835761785507202}
-03/05/2022 04:30:50 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/05/2022 04:30:54 - INFO - codeparrot_training - Step 33227: {'lr': 0.00044705966865135583, 'samples': 17012736, 'steps': 33227, 'loss/train': 1.2123897075653076}
-03/05/2022 04:30:57 - INFO - codeparrot_training - Step 33228: {'lr': 0.00044705640299761004, 'samples': 17013248, 'steps': 33228, 'loss/train': 2.29453182220459}
-03/05/2022 04:30:59 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/05/2022 04:31:03 - INFO - codeparrot_training - Step 33229: {'lr': 0.0004470531372550736, 'samples': 17013760, 'steps': 33229, 'loss/train': 2.295593738555908}
-03/05/2022 04:31:06 - INFO - codeparrot_training - Step 33230: {'lr': 0.00044704987142374814, 'samples': 17014272, 'steps': 33230, 'loss/train': 1.7721439599990845}
-03/05/2022 04:31:07 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/05/2022 04:31:11 - INFO - codeparrot_training - Step 33231: {'lr': 0.00044704660550363507, 'samples': 17014784, 'steps': 33231, 'loss/train': 1.7082793712615967}
-03/05/2022 04:31:14 - INFO - codeparrot_training - Step 33232: {'lr': 0.00044704333949473576, 'samples': 17015296, 'steps': 33232, 'loss/train': 1.4916679859161377}
-03/05/2022 04:31:15 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/05/2022 04:31:19 - INFO - codeparrot_training - Step 33233: {'lr': 0.0004470400733970518, 'samples': 17015808, 'steps': 33233, 'loss/train': 2.416391134262085}
-03/05/2022 04:31:23 - INFO - codeparrot_training - Step 33234: {'lr': 0.0004470368072105846, 'samples': 17016320, 'steps': 33234, 'loss/train': 2.341555595397949}
-03/05/2022 04:31:23 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/05/2022 04:31:28 - INFO - codeparrot_training - Step 33235: {'lr': 0.00044703354093533564, 'samples': 17016832, 'steps': 33235, 'loss/train': 0.9006397724151611}
-03/05/2022 04:31:31 - INFO - codeparrot_training - Step 33236: {'lr': 0.0004470302745713065, 'samples': 17017344, 'steps': 33236, 'loss/train': 1.2152900695800781}
-03/05/2022 04:31:32 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/05/2022 04:31:36 - INFO - codeparrot_training - Step 33237: {'lr': 0.0004470270081184985, 'samples': 17017856, 'steps': 33237, 'loss/train': 0.8020053505897522}
-03/05/2022 04:31:40 - INFO - codeparrot_training - Step 33238: {'lr': 0.00044702374157691316, 'samples': 17018368, 'steps': 33238, 'loss/train': 2.1624271869659424}
-03/05/2022 04:31:41 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/05/2022 04:31:45 - INFO - codeparrot_training - Step 33239: {'lr': 0.00044702047494655194, 'samples': 17018880, 'steps': 33239, 'loss/train': 1.036012887954712}
-03/05/2022 04:31:48 - INFO - codeparrot_training - Step 33240: {'lr': 0.0004470172082274164, 'samples': 17019392, 'steps': 33240, 'loss/train': 1.9231829643249512}
-03/05/2022 04:31:50 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/05/2022 04:31:53 - INFO - codeparrot_training - Step 33241: {'lr': 0.0004470139414195079, 'samples': 17019904, 'steps': 33241, 'loss/train': 1.0617188215255737}
-03/05/2022 04:31:57 - INFO - codeparrot_training - Step 33242: {'lr': 0.00044701067452282796, 'samples': 17020416, 'steps': 33242, 'loss/train': 2.1453857421875}
-03/05/2022 04:31:59 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/05/2022 04:32:02 - INFO - codeparrot_training - Step 33243: {'lr': 0.00044700740753737806, 'samples': 17020928, 'steps': 33243, 'loss/train': 1.3970568180084229}
-03/05/2022 04:32:05 - INFO - codeparrot_training - Step 33244: {'lr': 0.0004470041404631597, 'samples': 17021440, 'steps': 33244, 'loss/train': 1.851447343826294}
-03/05/2022 04:32:08 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/05/2022 04:32:10 - INFO - codeparrot_training - Step 33245: {'lr': 0.0004470008733001742, 'samples': 17021952, 'steps': 33245, 'loss/train': 0.7055865526199341}
-03/05/2022 04:32:14 - INFO - codeparrot_training - Step 33246: {'lr': 0.0004469976060484233, 'samples': 17022464, 'steps': 33246, 'loss/train': 1.4836117029190063}
-03/05/2022 04:32:16 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 04:32:19 - INFO - codeparrot_training - Step 33247: {'lr': 0.00044699433870790817, 'samples': 17022976, 'steps': 33247, 'loss/train': 1.7269686460494995}
-03/05/2022 04:32:22 - INFO - codeparrot_training - Step 33248: {'lr': 0.00044699107127863056, 'samples': 17023488, 'steps': 33248, 'loss/train': 2.044891595840454}
-03/05/2022 04:32:25 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/05/2022 04:32:27 - INFO - codeparrot_training - Step 33249: {'lr': 0.0004469878037605917, 'samples': 17024000, 'steps': 33249, 'loss/train': 1.8798165321350098}
-03/05/2022 04:32:31 - INFO - codeparrot_training - Step 33250: {'lr': 0.0004469845361537933, 'samples': 17024512, 'steps': 33250, 'loss/train': 0.14328764379024506}
-03/05/2022 04:32:33 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/05/2022 04:32:36 - INFO - codeparrot_training - Step 33251: {'lr': 0.0004469812684582366, 'samples': 17025024, 'steps': 33251, 'loss/train': 1.9625693559646606}
-03/05/2022 04:32:39 - INFO - codeparrot_training - Step 33252: {'lr': 0.00044697800067392327, 'samples': 17025536, 'steps': 33252, 'loss/train': 1.0423429012298584}
-03/05/2022 04:32:42 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/05/2022 04:32:44 - INFO - codeparrot_training - Step 33253: {'lr': 0.00044697473280085455, 'samples': 17026048, 'steps': 33253, 'loss/train': 1.9206043481826782}
-03/05/2022 04:32:47 - INFO - codeparrot_training - Step 33254: {'lr': 0.0004469714648390322, 'samples': 17026560, 'steps': 33254, 'loss/train': 1.9566144943237305}
-03/05/2022 04:32:50 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/05/2022 04:32:53 - INFO - codeparrot_training - Step 33255: {'lr': 0.00044696819678845744, 'samples': 17027072, 'steps': 33255, 'loss/train': 1.5201117992401123}
-03/05/2022 04:32:56 - INFO - codeparrot_training - Step 33256: {'lr': 0.000446964928649132, 'samples': 17027584, 'steps': 33256, 'loss/train': 0.567852258682251}
-03/05/2022 04:32:58 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 04:33:01 - INFO - codeparrot_training - Step 33257: {'lr': 0.00044696166042105704, 'samples': 17028096, 'steps': 33257, 'loss/train': 1.8542073965072632}
-03/05/2022 04:33:04 - INFO - codeparrot_training - Step 33258: {'lr': 0.0004469583921042343, 'samples': 17028608, 'steps': 33258, 'loss/train': 1.3847225904464722}
-03/05/2022 04:33:07 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/05/2022 04:33:10 - INFO - codeparrot_training - Step 33259: {'lr': 0.0004469551236986651, 'samples': 17029120, 'steps': 33259, 'loss/train': 1.7156076431274414}
-03/05/2022 04:33:13 - INFO - codeparrot_training - Step 33260: {'lr': 0.00044695185520435087, 'samples': 17029632, 'steps': 33260, 'loss/train': 2.145132064819336}
-03/05/2022 04:33:15 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/05/2022 04:33:18 - INFO - codeparrot_training - Step 33261: {'lr': 0.00044694858662129333, 'samples': 17030144, 'steps': 33261, 'loss/train': 1.4747002124786377}
-03/05/2022 04:33:21 - INFO - codeparrot_training - Step 33262: {'lr': 0.0004469453179494938, 'samples': 17030656, 'steps': 33262, 'loss/train': 1.712813138961792}
-03/05/2022 04:33:24 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/05/2022 04:33:27 - INFO - codeparrot_training - Step 33263: {'lr': 0.00044694204918895367, 'samples': 17031168, 'steps': 33263, 'loss/train': 1.0600396394729614}
-03/05/2022 04:33:30 - INFO - codeparrot_training - Step 33264: {'lr': 0.0004469387803396745, 'samples': 17031680, 'steps': 33264, 'loss/train': 1.320888876914978}
-03/05/2022 04:33:32 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/05/2022 04:33:35 - INFO - codeparrot_training - Step 33265: {'lr': 0.0004469355114016577, 'samples': 17032192, 'steps': 33265, 'loss/train': 1.923216462135315}
-03/05/2022 04:33:38 - INFO - codeparrot_training - Step 33266: {'lr': 0.00044693224237490485, 'samples': 17032704, 'steps': 33266, 'loss/train': 1.7750978469848633}
-03/05/2022 04:33:41 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/05/2022 04:33:43 - INFO - codeparrot_training - Step 33267: {'lr': 0.00044692897325941737, 'samples': 17033216, 'steps': 33267, 'loss/train': 1.8400615453720093}
-03/05/2022 04:33:47 - INFO - codeparrot_training - Step 33268: {'lr': 0.00044692570405519683, 'samples': 17033728, 'steps': 33268, 'loss/train': 2.481304407119751}
-03/05/2022 04:33:49 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/05/2022 04:33:52 - INFO - codeparrot_training - Step 33269: {'lr': 0.0004469224347622445, 'samples': 17034240, 'steps': 33269, 'loss/train': 0.9251644611358643}
-03/05/2022 04:33:55 - INFO - codeparrot_training - Step 33270: {'lr': 0.000446919165380562, 'samples': 17034752, 'steps': 33270, 'loss/train': 2.0589897632598877}
-03/05/2022 04:33:59 - INFO - codeparrot_training - Step 33271: {'lr': 0.0004469158959101507, 'samples': 17035264, 'steps': 33271, 'loss/train': 1.8704736232757568}
-03/05/2022 04:33:59 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/05/2022 04:34:04 - INFO - codeparrot_training - Step 33272: {'lr': 0.00044691262635101223, 'samples': 17035776, 'steps': 33272, 'loss/train': 0.5479095578193665}
-03/05/2022 04:34:07 - INFO - codeparrot_training - Step 33273: {'lr': 0.0004469093567031479, 'samples': 17036288, 'steps': 33273, 'loss/train': 1.7991565465927124}
-03/05/2022 04:34:07 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/05/2022 04:34:12 - INFO - codeparrot_training - Step 33274: {'lr': 0.00044690608696655923, 'samples': 17036800, 'steps': 33274, 'loss/train': 1.4176887273788452}
-03/05/2022 04:34:15 - INFO - codeparrot_training - Step 33275: {'lr': 0.0004469028171412478, 'samples': 17037312, 'steps': 33275, 'loss/train': 1.7971992492675781}
-03/05/2022 04:34:15 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/05/2022 04:34:21 - INFO - codeparrot_training - Step 33276: {'lr': 0.00044689954722721494, 'samples': 17037824, 'steps': 33276, 'loss/train': 1.417471170425415}
-03/05/2022 04:34:23 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/05/2022 04:34:26 - INFO - codeparrot_training - Step 33277: {'lr': 0.0004468962772244622, 'samples': 17038336, 'steps': 33277, 'loss/train': 3.3851616382598877}
-03/05/2022 04:34:29 - INFO - codeparrot_training - Step 33278: {'lr': 0.00044689300713299105, 'samples': 17038848, 'steps': 33278, 'loss/train': 1.1838024854660034}
-03/05/2022 04:34:32 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/05/2022 04:34:34 - INFO - codeparrot_training - Step 33279: {'lr': 0.0004468897369528029, 'samples': 17039360, 'steps': 33279, 'loss/train': 2.1633739471435547}
-03/05/2022 04:34:37 - INFO - codeparrot_training - Step 33280: {'lr': 0.00044688646668389933, 'samples': 17039872, 'steps': 33280, 'loss/train': 1.347037672996521}
-03/05/2022 04:34:40 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/05/2022 04:34:43 - INFO - codeparrot_training - Step 33281: {'lr': 0.0004468831963262817, 'samples': 17040384, 'steps': 33281, 'loss/train': 2.2109601497650146}
-03/05/2022 04:34:46 - INFO - codeparrot_training - Step 33282: {'lr': 0.00044687992587995155, 'samples': 17040896, 'steps': 33282, 'loss/train': 1.8926875591278076}
-03/05/2022 04:34:48 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/05/2022 04:34:51 - INFO - codeparrot_training - Step 33283: {'lr': 0.0004468766553449104, 'samples': 17041408, 'steps': 33283, 'loss/train': 1.2865020036697388}
-03/05/2022 04:34:54 - INFO - codeparrot_training - Step 33284: {'lr': 0.00044687338472115964, 'samples': 17041920, 'steps': 33284, 'loss/train': 1.406243920326233}
-03/05/2022 04:34:57 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/05/2022 04:35:00 - INFO - codeparrot_training - Step 33285: {'lr': 0.00044687011400870074, 'samples': 17042432, 'steps': 33285, 'loss/train': 1.6059579849243164}
-03/05/2022 04:35:03 - INFO - codeparrot_training - Step 33286: {'lr': 0.00044686684320753524, 'samples': 17042944, 'steps': 33286, 'loss/train': 1.5593130588531494}
-03/05/2022 04:35:05 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/05/2022 04:35:08 - INFO - codeparrot_training - Step 33287: {'lr': 0.00044686357231766454, 'samples': 17043456, 'steps': 33287, 'loss/train': 1.787016749382019}
-03/05/2022 04:35:11 - INFO - codeparrot_training - Step 33288: {'lr': 0.00044686030133909017, 'samples': 17043968, 'steps': 33288, 'loss/train': 1.9975470304489136}
-03/05/2022 04:35:14 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/05/2022 04:35:17 - INFO - codeparrot_training - Step 33289: {'lr': 0.00044685703027181364, 'samples': 17044480, 'steps': 33289, 'loss/train': 1.8950200080871582}
-03/05/2022 04:35:20 - INFO - codeparrot_training - Step 33290: {'lr': 0.0004468537591158363, 'samples': 17044992, 'steps': 33290, 'loss/train': 1.9059292078018188}
-03/05/2022 04:35:22 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/05/2022 04:35:25 - INFO - codeparrot_training - Step 33291: {'lr': 0.0004468504878711597, 'samples': 17045504, 'steps': 33291, 'loss/train': 1.7182505130767822}
-03/05/2022 04:35:28 - INFO - codeparrot_training - Step 33292: {'lr': 0.00044684721653778537, 'samples': 17046016, 'steps': 33292, 'loss/train': 1.0436699390411377}
-03/05/2022 04:35:31 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/05/2022 04:35:33 - INFO - codeparrot_training - Step 33293: {'lr': 0.00044684394511571463, 'samples': 17046528, 'steps': 33293, 'loss/train': 1.7925264835357666}
-03/05/2022 04:35:37 - INFO - codeparrot_training - Step 33294: {'lr': 0.00044684067360494905, 'samples': 17047040, 'steps': 33294, 'loss/train': 1.5657933950424194}
-03/05/2022 04:35:39 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/05/2022 04:35:42 - INFO - codeparrot_training - Step 33295: {'lr': 0.00044683740200549015, 'samples': 17047552, 'steps': 33295, 'loss/train': 1.1063350439071655}
-03/05/2022 04:35:45 - INFO - codeparrot_training - Step 33296: {'lr': 0.00044683413031733945, 'samples': 17048064, 'steps': 33296, 'loss/train': 1.6962965726852417}
-03/05/2022 04:35:48 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/05/2022 04:35:50 - INFO - codeparrot_training - Step 33297: {'lr': 0.00044683085854049814, 'samples': 17048576, 'steps': 33297, 'loss/train': 2.3267552852630615}
-03/05/2022 04:35:54 - INFO - codeparrot_training - Step 33298: {'lr': 0.00044682758667496806, 'samples': 17049088, 'steps': 33298, 'loss/train': 2.485488176345825}
-03/05/2022 04:35:56 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/05/2022 04:35:59 - INFO - codeparrot_training - Step 33299: {'lr': 0.00044682431472075035, 'samples': 17049600, 'steps': 33299, 'loss/train': 2.0528550148010254}
-03/05/2022 04:36:02 - INFO - codeparrot_training - Step 33300: {'lr': 0.00044682104267784674, 'samples': 17050112, 'steps': 33300, 'loss/train': 1.6780948638916016}
-03/05/2022 04:36:04 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/05/2022 04:36:07 - INFO - codeparrot_training - Step 33301: {'lr': 0.0004468177705462585, 'samples': 17050624, 'steps': 33301, 'loss/train': 2.031189203262329}
-03/05/2022 04:36:10 - INFO - codeparrot_training - Step 33302: {'lr': 0.0004468144983259873, 'samples': 17051136, 'steps': 33302, 'loss/train': 2.366976022720337}
-03/05/2022 04:36:13 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/05/2022 04:36:16 - INFO - codeparrot_training - Step 33303: {'lr': 0.0004468112260170345, 'samples': 17051648, 'steps': 33303, 'loss/train': 2.0559298992156982}
-03/05/2022 04:36:19 - INFO - codeparrot_training - Step 33304: {'lr': 0.0004468079536194016, 'samples': 17052160, 'steps': 33304, 'loss/train': 1.322758674621582}
-03/05/2022 04:36:21 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/05/2022 04:36:24 - INFO - codeparrot_training - Step 33305: {'lr': 0.00044680468113309006, 'samples': 17052672, 'steps': 33305, 'loss/train': 1.6497762203216553}
-03/05/2022 04:36:27 - INFO - codeparrot_training - Step 33306: {'lr': 0.0004468014085581014, 'samples': 17053184, 'steps': 33306, 'loss/train': 1.5704318284988403}
-03/05/2022 04:36:30 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/05/2022 04:36:33 - INFO - codeparrot_training - Step 33307: {'lr': 0.0004467981358944371, 'samples': 17053696, 'steps': 33307, 'loss/train': 2.2079720497131348}
-03/05/2022 04:36:36 - INFO - codeparrot_training - Step 33308: {'lr': 0.0004467948631420985, 'samples': 17054208, 'steps': 33308, 'loss/train': 2.0205180644989014}
-03/05/2022 04:36:38 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 04:36:41 - INFO - codeparrot_training - Step 33309: {'lr': 0.0004467915903010872, 'samples': 17054720, 'steps': 33309, 'loss/train': 1.8146395683288574}
-03/05/2022 04:36:44 - INFO - codeparrot_training - Step 33310: {'lr': 0.0004467883173714047, 'samples': 17055232, 'steps': 33310, 'loss/train': 1.1737422943115234}
-03/05/2022 04:36:46 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/05/2022 04:36:49 - INFO - codeparrot_training - Step 33311: {'lr': 0.0004467850443530523, 'samples': 17055744, 'steps': 33311, 'loss/train': 1.9512014389038086}
-03/05/2022 04:36:53 - INFO - codeparrot_training - Step 33312: {'lr': 0.0004467817712460317, 'samples': 17056256, 'steps': 33312, 'loss/train': 1.3705593347549438}
-03/05/2022 04:36:55 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/05/2022 04:36:58 - INFO - codeparrot_training - Step 33313: {'lr': 0.00044677849805034424, 'samples': 17056768, 'steps': 33313, 'loss/train': 1.1737432479858398}
-03/05/2022 04:37:01 - INFO - codeparrot_training - Step 33314: {'lr': 0.0004467752247659914, 'samples': 17057280, 'steps': 33314, 'loss/train': 1.5484893321990967}
-03/05/2022 04:37:03 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/05/2022 04:37:06 - INFO - codeparrot_training - Step 33315: {'lr': 0.00044677195139297476, 'samples': 17057792, 'steps': 33315, 'loss/train': 0.7366610765457153}
-03/05/2022 04:37:09 - INFO - codeparrot_training - Step 33316: {'lr': 0.00044676867793129574, 'samples': 17058304, 'steps': 33316, 'loss/train': 1.3753629922866821}
-03/05/2022 04:37:12 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/05/2022 04:37:15 - INFO - codeparrot_training - Step 33317: {'lr': 0.00044676540438095565, 'samples': 17058816, 'steps': 33317, 'loss/train': 1.3672655820846558}
-03/05/2022 04:37:18 - INFO - codeparrot_training - Step 33318: {'lr': 0.0004467621307419562, 'samples': 17059328, 'steps': 33318, 'loss/train': 1.6080365180969238}
-03/05/2022 04:37:20 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 04:37:23 - INFO - codeparrot_training - Step 33319: {'lr': 0.00044675885701429873, 'samples': 17059840, 'steps': 33319, 'loss/train': 1.674177646636963}
-03/05/2022 04:37:26 - INFO - codeparrot_training - Step 33320: {'lr': 0.00044675558319798477, 'samples': 17060352, 'steps': 33320, 'loss/train': 1.8963091373443604}
-03/05/2022 04:37:28 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/05/2022 04:37:31 - INFO - codeparrot_training - Step 33321: {'lr': 0.00044675230929301575, 'samples': 17060864, 'steps': 33321, 'loss/train': 1.3053467273712158}
-03/05/2022 04:37:34 - INFO - codeparrot_training - Step 33322: {'lr': 0.0004467490352993932, 'samples': 17061376, 'steps': 33322, 'loss/train': 1.0580475330352783}
-03/05/2022 04:37:36 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 04:37:40 - INFO - codeparrot_training - Step 33323: {'lr': 0.00044674576121711855, 'samples': 17061888, 'steps': 33323, 'loss/train': 0.9874007105827332}
-03/05/2022 04:37:43 - INFO - codeparrot_training - Step 33324: {'lr': 0.00044674248704619333, 'samples': 17062400, 'steps': 33324, 'loss/train': 0.4970065653324127}
-03/05/2022 04:37:45 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/05/2022 04:37:49 - INFO - codeparrot_training - Step 33325: {'lr': 0.000446739212786619, 'samples': 17062912, 'steps': 33325, 'loss/train': 1.5615367889404297}
-03/05/2022 04:37:52 - INFO - codeparrot_training - Step 33326: {'lr': 0.000446735938438397, 'samples': 17063424, 'steps': 33326, 'loss/train': 0.8223859667778015}
-03/05/2022 04:37:55 - INFO - codeparrot_training - Step 33327: {'lr': 0.0004467326640015288, 'samples': 17063936, 'steps': 33327, 'loss/train': 6.371712684631348}
-03/05/2022 04:37:57 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/05/2022 04:38:01 - INFO - codeparrot_training - Step 33328: {'lr': 0.00044672938947601593, 'samples': 17064448, 'steps': 33328, 'loss/train': 1.2918379306793213}
-03/05/2022 04:38:04 - INFO - codeparrot_training - Step 33329: {'lr': 0.00044672611486185976, 'samples': 17064960, 'steps': 33329, 'loss/train': 1.909144401550293}
-03/05/2022 04:38:05 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/05/2022 04:38:09 - INFO - codeparrot_training - Step 33330: {'lr': 0.0004467228401590619, 'samples': 17065472, 'steps': 33330, 'loss/train': 0.6293220520019531}
-03/05/2022 04:38:12 - INFO - codeparrot_training - Step 33331: {'lr': 0.00044671956536762375, 'samples': 17065984, 'steps': 33331, 'loss/train': 1.6965147256851196}
-03/05/2022 04:38:14 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/05/2022 04:38:18 - INFO - codeparrot_training - Step 33332: {'lr': 0.00044671629048754683, 'samples': 17066496, 'steps': 33332, 'loss/train': 1.2985069751739502}
-03/05/2022 04:38:21 - INFO - codeparrot_training - Step 33333: {'lr': 0.00044671301551883253, 'samples': 17067008, 'steps': 33333, 'loss/train': 1.6386150121688843}
-03/05/2022 04:38:23 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/05/2022 04:38:26 - INFO - codeparrot_training - Step 33334: {'lr': 0.0004467097404614824, 'samples': 17067520, 'steps': 33334, 'loss/train': 1.2853312492370605}
-03/05/2022 04:38:29 - INFO - codeparrot_training - Step 33335: {'lr': 0.0004467064653154979, 'samples': 17068032, 'steps': 33335, 'loss/train': 1.718184232711792}
-03/05/2022 04:38:31 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/05/2022 04:38:35 - INFO - codeparrot_training - Step 33336: {'lr': 0.0004467031900808805, 'samples': 17068544, 'steps': 33336, 'loss/train': 1.5432883501052856}
-03/05/2022 04:38:38 - INFO - codeparrot_training - Step 33337: {'lr': 0.00044669991475763173, 'samples': 17069056, 'steps': 33337, 'loss/train': 1.5116682052612305}
-03/05/2022 04:38:41 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 04:38:43 - INFO - codeparrot_training - Step 33338: {'lr': 0.00044669663934575294, 'samples': 17069568, 'steps': 33338, 'loss/train': 1.0382428169250488}
-03/05/2022 04:38:46 - INFO - codeparrot_training - Step 33339: {'lr': 0.0004466933638452457, 'samples': 17070080, 'steps': 33339, 'loss/train': 1.6291375160217285}
-03/05/2022 04:38:49 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/05/2022 04:38:52 - INFO - codeparrot_training - Step 33340: {'lr': 0.0004466900882561115, 'samples': 17070592, 'steps': 33340, 'loss/train': 1.359604835510254}
-03/05/2022 04:38:55 - INFO - codeparrot_training - Step 33341: {'lr': 0.00044668681257835173, 'samples': 17071104, 'steps': 33341, 'loss/train': 1.8115434646606445}
-03/05/2022 04:38:57 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/05/2022 04:39:00 - INFO - codeparrot_training - Step 33342: {'lr': 0.00044668353681196794, 'samples': 17071616, 'steps': 33342, 'loss/train': 1.2806613445281982}
-03/05/2022 04:39:03 - INFO - codeparrot_training - Step 33343: {'lr': 0.0004466802609569616, 'samples': 17072128, 'steps': 33343, 'loss/train': 1.1015074253082275}
-03/05/2022 04:39:06 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 04:39:09 - INFO - codeparrot_training - Step 33344: {'lr': 0.00044667698501333415, 'samples': 17072640, 'steps': 33344, 'loss/train': 1.0961458683013916}
-03/05/2022 04:39:12 - INFO - codeparrot_training - Step 33345: {'lr': 0.0004466737089810871, 'samples': 17073152, 'steps': 33345, 'loss/train': 1.7168333530426025}
-03/05/2022 04:39:15 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/05/2022 04:39:17 - INFO - codeparrot_training - Step 33346: {'lr': 0.00044667043286022193, 'samples': 17073664, 'steps': 33346, 'loss/train': 2.0690042972564697}
-03/05/2022 04:39:20 - INFO - codeparrot_training - Step 33347: {'lr': 0.00044666715665074, 'samples': 17074176, 'steps': 33347, 'loss/train': 0.11862774938344955}
-03/05/2022 04:39:23 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/05/2022 04:39:26 - INFO - codeparrot_training - Step 33348: {'lr': 0.0004466638803526429, 'samples': 17074688, 'steps': 33348, 'loss/train': 1.5842550992965698}
-03/05/2022 04:39:29 - INFO - codeparrot_training - Step 33349: {'lr': 0.0004466606039659322, 'samples': 17075200, 'steps': 33349, 'loss/train': 1.3628886938095093}
-03/05/2022 04:39:32 - INFO - codeparrot_training - Step 33350: {'lr': 0.0004466573274906092, 'samples': 17075712, 'steps': 33350, 'loss/train': 0.8586089015007019}
-03/05/2022 04:39:32 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/05/2022 04:39:37 - INFO - codeparrot_training - Step 33351: {'lr': 0.0004466540509266754, 'samples': 17076224, 'steps': 33351, 'loss/train': 2.026029586791992}
-03/05/2022 04:39:41 - INFO - codeparrot_training - Step 33352: {'lr': 0.0004466507742741325, 'samples': 17076736, 'steps': 33352, 'loss/train': 1.7219226360321045}
-03/05/2022 04:39:41 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/05/2022 04:39:46 - INFO - codeparrot_training - Step 33353: {'lr': 0.0004466474975329816, 'samples': 17077248, 'steps': 33353, 'loss/train': 1.8644887208938599}
-03/05/2022 04:39:49 - INFO - codeparrot_training - Step 33354: {'lr': 0.0004466442207032244, 'samples': 17077760, 'steps': 33354, 'loss/train': 2.2709760665893555}
-03/05/2022 04:39:49 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/05/2022 04:39:54 - INFO - codeparrot_training - Step 33355: {'lr': 0.00044664094378486243, 'samples': 17078272, 'steps': 33355, 'loss/train': 1.9272695779800415}
-03/05/2022 04:39:57 - INFO - codeparrot_training - Step 33356: {'lr': 0.00044663766677789706, 'samples': 17078784, 'steps': 33356, 'loss/train': 1.887320876121521}
-03/05/2022 04:39:57 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/05/2022 04:40:03 - INFO - codeparrot_training - Step 33357: {'lr': 0.0004466343896823297, 'samples': 17079296, 'steps': 33357, 'loss/train': 1.4393413066864014}
-03/05/2022 04:40:06 - INFO - codeparrot_training - Step 33358: {'lr': 0.000446631112498162, 'samples': 17079808, 'steps': 33358, 'loss/train': 1.8494728803634644}
-03/05/2022 04:40:06 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/05/2022 04:40:11 - INFO - codeparrot_training - Step 33359: {'lr': 0.0004466278352253954, 'samples': 17080320, 'steps': 33359, 'loss/train': 1.3775429725646973}
-03/05/2022 04:40:14 - INFO - codeparrot_training - Step 33360: {'lr': 0.00044662455786403124, 'samples': 17080832, 'steps': 33360, 'loss/train': 1.511925220489502}
-03/05/2022 04:40:14 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/05/2022 04:40:20 - INFO - codeparrot_training - Step 33361: {'lr': 0.0004466212804140711, 'samples': 17081344, 'steps': 33361, 'loss/train': 1.0644581317901611}
-03/05/2022 04:40:23 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/05/2022 04:40:25 - INFO - codeparrot_training - Step 33362: {'lr': 0.00044661800287551653, 'samples': 17081856, 'steps': 33362, 'loss/train': 2.0496010780334473}
-03/05/2022 04:40:28 - INFO - codeparrot_training - Step 33363: {'lr': 0.00044661472524836886, 'samples': 17082368, 'steps': 33363, 'loss/train': 2.2401201725006104}
-03/05/2022 04:40:31 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/05/2022 04:40:34 - INFO - codeparrot_training - Step 33364: {'lr': 0.00044661144753262963, 'samples': 17082880, 'steps': 33364, 'loss/train': 1.7566076517105103}
-03/05/2022 04:40:37 - INFO - codeparrot_training - Step 33365: {'lr': 0.0004466081697283003, 'samples': 17083392, 'steps': 33365, 'loss/train': 2.299621105194092}
-03/05/2022 04:40:40 - INFO - codeparrot_training - Step 33366: {'lr': 0.00044660489183538237, 'samples': 17083904, 'steps': 33366, 'loss/train': 1.6577858924865723}
-03/05/2022 04:40:40 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 04:40:45 - INFO - codeparrot_training - Step 33367: {'lr': 0.0004466016138538773, 'samples': 17084416, 'steps': 33367, 'loss/train': 2.9881908893585205}
-03/05/2022 04:40:49 - INFO - codeparrot_training - Step 33368: {'lr': 0.0004465983357837866, 'samples': 17084928, 'steps': 33368, 'loss/train': 1.9357060194015503}
-03/05/2022 04:40:49 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/05/2022 04:40:54 - INFO - codeparrot_training - Step 33369: {'lr': 0.00044659505762511176, 'samples': 17085440, 'steps': 33369, 'loss/train': 1.5760473012924194}
-03/05/2022 04:40:57 - INFO - codeparrot_training - Step 33370: {'lr': 0.00044659177937785417, 'samples': 17085952, 'steps': 33370, 'loss/train': 1.2440972328186035}
-03/05/2022 04:40:57 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 04:41:03 - INFO - codeparrot_training - Step 33371: {'lr': 0.0004465885010420154, 'samples': 17086464, 'steps': 33371, 'loss/train': 1.8743789196014404}
-03/05/2022 04:41:06 - INFO - codeparrot_training - Step 33372: {'lr': 0.0004465852226175968, 'samples': 17086976, 'steps': 33372, 'loss/train': 0.9144407510757446}
-03/05/2022 04:41:07 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/05/2022 04:41:11 - INFO - codeparrot_training - Step 33373: {'lr': 0.00044658194410460004, 'samples': 17087488, 'steps': 33373, 'loss/train': 1.1332484483718872}
-03/05/2022 04:41:14 - INFO - codeparrot_training - Step 33374: {'lr': 0.0004465786655030264, 'samples': 17088000, 'steps': 33374, 'loss/train': 1.340173602104187}
-03/05/2022 04:41:15 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/05/2022 04:41:19 - INFO - codeparrot_training - Step 33375: {'lr': 0.00044657538681287746, 'samples': 17088512, 'steps': 33375, 'loss/train': 2.267954111099243}
-03/05/2022 04:41:23 - INFO - codeparrot_training - Step 33376: {'lr': 0.0004465721080341547, 'samples': 17089024, 'steps': 33376, 'loss/train': 1.4547932147979736}
-03/05/2022 04:41:23 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 04:41:28 - INFO - codeparrot_training - Step 33377: {'lr': 0.0004465688291668596, 'samples': 17089536, 'steps': 33377, 'loss/train': 1.074089527130127}
-03/05/2022 04:41:31 - INFO - codeparrot_training - Step 33378: {'lr': 0.00044656555021099363, 'samples': 17090048, 'steps': 33378, 'loss/train': 1.950627326965332}
-03/05/2022 04:41:31 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/05/2022 04:41:36 - INFO - codeparrot_training - Step 33379: {'lr': 0.00044656227116655824, 'samples': 17090560, 'steps': 33379, 'loss/train': 2.3485255241394043}
-03/05/2022 04:41:39 - INFO - codeparrot_training - Step 33380: {'lr': 0.00044655899203355486, 'samples': 17091072, 'steps': 33380, 'loss/train': 1.6018450260162354}
-03/05/2022 04:41:40 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/05/2022 04:41:45 - INFO - codeparrot_training - Step 33381: {'lr': 0.0004465557128119852, 'samples': 17091584, 'steps': 33381, 'loss/train': 0.8849830031394958}
-03/05/2022 04:41:48 - INFO - codeparrot_training - Step 33382: {'lr': 0.00044655243350185037, 'samples': 17092096, 'steps': 33382, 'loss/train': 1.4541374444961548}
-03/05/2022 04:41:49 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/05/2022 04:41:54 - INFO - codeparrot_training - Step 33383: {'lr': 0.0004465491541031522, 'samples': 17092608, 'steps': 33383, 'loss/train': 1.1984227895736694}
-03/05/2022 04:41:57 - INFO - codeparrot_training - Step 33384: {'lr': 0.00044654587461589193, 'samples': 17093120, 'steps': 33384, 'loss/train': 1.6082019805908203}
-03/05/2022 04:42:00 - INFO - codeparrot_training - Step 33385: {'lr': 0.0004465425950400711, 'samples': 17093632, 'steps': 33385, 'loss/train': 2.2624125480651855}
-03/05/2022 04:42:00 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/05/2022 04:42:05 - INFO - codeparrot_training - Step 33386: {'lr': 0.00044653931537569125, 'samples': 17094144, 'steps': 33386, 'loss/train': 1.5172392129898071}
-03/05/2022 04:42:08 - INFO - codeparrot_training - Step 33387: {'lr': 0.0004465360356227538, 'samples': 17094656, 'steps': 33387, 'loss/train': 1.4819080829620361}
-03/05/2022 04:42:08 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/05/2022 04:42:14 - INFO - codeparrot_training - Step 33388: {'lr': 0.0004465327557812603, 'samples': 17095168, 'steps': 33388, 'loss/train': 2.3148624897003174}
-03/05/2022 04:42:17 - INFO - codeparrot_training - Step 33389: {'lr': 0.0004465294758512121, 'samples': 17095680, 'steps': 33389, 'loss/train': 2.1063382625579834}
-03/05/2022 04:42:17 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/05/2022 04:42:22 - INFO - codeparrot_training - Step 33390: {'lr': 0.0004465261958326108, 'samples': 17096192, 'steps': 33390, 'loss/train': 1.6761436462402344}
-03/05/2022 04:42:25 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/05/2022 04:42:28 - INFO - codeparrot_training - Step 33391: {'lr': 0.0004465229157254578, 'samples': 17096704, 'steps': 33391, 'loss/train': 2.060272216796875}
-03/05/2022 04:42:31 - INFO - codeparrot_training - Step 33392: {'lr': 0.0004465196355297546, 'samples': 17097216, 'steps': 33392, 'loss/train': 1.938143253326416}
-03/05/2022 04:42:34 - INFO - codeparrot_training - Step 33393: {'lr': 0.0004465163552455027, 'samples': 17097728, 'steps': 33393, 'loss/train': 1.614751935005188}
-03/05/2022 04:42:34 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/05/2022 04:42:39 - INFO - codeparrot_training - Step 33394: {'lr': 0.0004465130748727036, 'samples': 17098240, 'steps': 33394, 'loss/train': 1.8033032417297363}
-03/05/2022 04:42:42 - INFO - codeparrot_training - Step 33395: {'lr': 0.0004465097944113587, 'samples': 17098752, 'steps': 33395, 'loss/train': 1.4509755373001099}
-03/05/2022 04:42:43 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 04:42:48 - INFO - codeparrot_training - Step 33396: {'lr': 0.00044650651386146954, 'samples': 17099264, 'steps': 33396, 'loss/train': 1.9044692516326904}
-03/05/2022 04:42:51 - INFO - codeparrot_training - Step 33397: {'lr': 0.00044650323322303757, 'samples': 17099776, 'steps': 33397, 'loss/train': 1.2850303649902344}
-03/05/2022 04:42:51 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/05/2022 04:42:56 - INFO - codeparrot_training - Step 33398: {'lr': 0.0004464999524960642, 'samples': 17100288, 'steps': 33398, 'loss/train': 1.4102160930633545}
-03/05/2022 04:42:59 - INFO - codeparrot_training - Step 33399: {'lr': 0.0004464966716805511, 'samples': 17100800, 'steps': 33399, 'loss/train': 1.8585915565490723}
-03/05/2022 04:42:59 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/05/2022 04:43:05 - INFO - codeparrot_training - Step 33400: {'lr': 0.0004464933907764996, 'samples': 17101312, 'steps': 33400, 'loss/train': 2.7101783752441406}
-03/05/2022 04:43:07 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/05/2022 04:43:10 - INFO - codeparrot_training - Step 33401: {'lr': 0.0004464901097839112, 'samples': 17101824, 'steps': 33401, 'loss/train': 1.620274543762207}
-03/05/2022 04:43:13 - INFO - codeparrot_training - Step 33402: {'lr': 0.00044648682870278733, 'samples': 17102336, 'steps': 33402, 'loss/train': 1.240896224975586}
-03/05/2022 04:43:18 - INFO - codeparrot_training - Step 33403: {'lr': 0.0004464835475331296, 'samples': 17102848, 'steps': 33403, 'loss/train': 1.7425428628921509}
-03/05/2022 04:43:21 - INFO - codeparrot_training - Step 33404: {'lr': 0.0004464802662749394, 'samples': 17103360, 'steps': 33404, 'loss/train': 0.7599107623100281}
-03/05/2022 04:43:24 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/05/2022 04:43:27 - INFO - codeparrot_training - Step 33405: {'lr': 0.00044647698492821826, 'samples': 17103872, 'steps': 33405, 'loss/train': 1.1987831592559814}
-03/05/2022 04:43:30 - INFO - codeparrot_training - Step 33406: {'lr': 0.00044647370349296757, 'samples': 17104384, 'steps': 33406, 'loss/train': 1.1481199264526367}
-03/05/2022 04:43:32 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/05/2022 04:43:35 - INFO - codeparrot_training - Step 33407: {'lr': 0.00044647042196918884, 'samples': 17104896, 'steps': 33407, 'loss/train': 1.1245368719100952}
-03/05/2022 04:43:38 - INFO - codeparrot_training - Step 33408: {'lr': 0.00044646714035688365, 'samples': 17105408, 'steps': 33408, 'loss/train': 1.613560438156128}
-03/05/2022 04:43:41 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/05/2022 04:43:44 - INFO - codeparrot_training - Step 33409: {'lr': 0.00044646385865605335, 'samples': 17105920, 'steps': 33409, 'loss/train': 0.648435115814209}
-03/05/2022 04:43:47 - INFO - codeparrot_training - Step 33410: {'lr': 0.0004464605768666995, 'samples': 17106432, 'steps': 33410, 'loss/train': 2.1573431491851807}
-03/05/2022 04:43:49 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/05/2022 04:43:52 - INFO - codeparrot_training - Step 33411: {'lr': 0.0004464572949888235, 'samples': 17106944, 'steps': 33411, 'loss/train': 1.7899521589279175}
-03/05/2022 04:43:55 - INFO - codeparrot_training - Step 33412: {'lr': 0.0004464540130224268, 'samples': 17107456, 'steps': 33412, 'loss/train': 1.4265230894088745}
-03/05/2022 04:43:57 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/05/2022 04:44:00 - INFO - codeparrot_training - Step 33413: {'lr': 0.0004464507309675111, 'samples': 17107968, 'steps': 33413, 'loss/train': 0.9691981673240662}
-03/05/2022 04:44:04 - INFO - codeparrot_training - Step 33414: {'lr': 0.00044644744882407767, 'samples': 17108480, 'steps': 33414, 'loss/train': 1.7132285833358765}
-03/05/2022 04:44:06 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/05/2022 04:44:09 - INFO - codeparrot_training - Step 33415: {'lr': 0.00044644416659212806, 'samples': 17108992, 'steps': 33415, 'loss/train': 1.0552632808685303}
-03/05/2022 04:44:12 - INFO - codeparrot_training - Step 33416: {'lr': 0.00044644088427166375, 'samples': 17109504, 'steps': 33416, 'loss/train': 2.1172711849212646}
-03/05/2022 04:44:14 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/05/2022 04:44:17 - INFO - codeparrot_training - Step 33417: {'lr': 0.00044643760186268615, 'samples': 17110016, 'steps': 33417, 'loss/train': 2.0257163047790527}
-03/05/2022 04:44:20 - INFO - codeparrot_training - Step 33418: {'lr': 0.00044643431936519683, 'samples': 17110528, 'steps': 33418, 'loss/train': 1.0607872009277344}
-03/05/2022 04:44:23 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/05/2022 04:44:26 - INFO - codeparrot_training - Step 33419: {'lr': 0.00044643103677919726, 'samples': 17111040, 'steps': 33419, 'loss/train': 1.671301245689392}
-03/05/2022 04:44:29 - INFO - codeparrot_training - Step 33420: {'lr': 0.00044642775410468896, 'samples': 17111552, 'steps': 33420, 'loss/train': 0.9080524444580078}
-03/05/2022 04:44:31 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/05/2022 04:44:34 - INFO - codeparrot_training - Step 33421: {'lr': 0.00044642447134167316, 'samples': 17112064, 'steps': 33421, 'loss/train': 1.5299229621887207}
-03/05/2022 04:44:37 - INFO - codeparrot_training - Step 33422: {'lr': 0.00044642118849015167, 'samples': 17112576, 'steps': 33422, 'loss/train': 1.1376054286956787}
-03/05/2022 04:44:40 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/05/2022 04:44:43 - INFO - codeparrot_training - Step 33423: {'lr': 0.0004464179055501258, 'samples': 17113088, 'steps': 33423, 'loss/train': 2.105508327484131}
-03/05/2022 04:44:46 - INFO - codeparrot_training - Step 33424: {'lr': 0.00044641462252159705, 'samples': 17113600, 'steps': 33424, 'loss/train': 1.3555563688278198}
-03/05/2022 04:44:51 - INFO - codeparrot_training - Step 33425: {'lr': 0.0004464113394045669, 'samples': 17114112, 'steps': 33425, 'loss/train': 1.564305067062378}
-03/05/2022 04:44:54 - INFO - codeparrot_training - Step 33426: {'lr': 0.00044640805619903677, 'samples': 17114624, 'steps': 33426, 'loss/train': 1.4706215858459473}
-03/05/2022 04:44:56 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/05/2022 04:45:00 - INFO - codeparrot_training - Step 33427: {'lr': 0.00044640477290500824, 'samples': 17115136, 'steps': 33427, 'loss/train': 1.8843681812286377}
-03/05/2022 04:45:03 - INFO - codeparrot_training - Step 33428: {'lr': 0.00044640148952248285, 'samples': 17115648, 'steps': 33428, 'loss/train': 1.6479525566101074}
-03/05/2022 04:45:05 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 04:45:08 - INFO - codeparrot_training - Step 33429: {'lr': 0.00044639820605146184, 'samples': 17116160, 'steps': 33429, 'loss/train': 2.1154611110687256}
-03/05/2022 04:45:11 - INFO - codeparrot_training - Step 33430: {'lr': 0.0004463949224919469, 'samples': 17116672, 'steps': 33430, 'loss/train': 1.2566444873809814}
-03/05/2022 04:45:13 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/05/2022 04:45:16 - INFO - codeparrot_training - Step 33431: {'lr': 0.0004463916388439394, 'samples': 17117184, 'steps': 33431, 'loss/train': 1.4414485692977905}
-03/05/2022 04:45:20 - INFO - codeparrot_training - Step 33432: {'lr': 0.00044638835510744094, 'samples': 17117696, 'steps': 33432, 'loss/train': 1.686241626739502}
-03/05/2022 04:45:21 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 04:45:25 - INFO - codeparrot_training - Step 33433: {'lr': 0.0004463850712824528, 'samples': 17118208, 'steps': 33433, 'loss/train': 2.1638596057891846}
-03/05/2022 04:45:28 - INFO - codeparrot_training - Step 33434: {'lr': 0.0004463817873689766, 'samples': 17118720, 'steps': 33434, 'loss/train': 1.3323029279708862}
-03/05/2022 04:45:30 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/05/2022 04:45:33 - INFO - codeparrot_training - Step 33435: {'lr': 0.00044637850336701386, 'samples': 17119232, 'steps': 33435, 'loss/train': 1.509308099746704}
-03/05/2022 04:45:37 - INFO - codeparrot_training - Step 33436: {'lr': 0.000446375219276566, 'samples': 17119744, 'steps': 33436, 'loss/train': 1.8432215452194214}
-03/05/2022 04:45:38 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 04:45:42 - INFO - codeparrot_training - Step 33437: {'lr': 0.0004463719350976344, 'samples': 17120256, 'steps': 33437, 'loss/train': 1.8857122659683228}
-03/05/2022 04:45:45 - INFO - codeparrot_training - Step 33438: {'lr': 0.0004463686508302207, 'samples': 17120768, 'steps': 33438, 'loss/train': 0.5965262651443481}
-03/05/2022 04:45:47 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 04:45:50 - INFO - codeparrot_training - Step 33439: {'lr': 0.00044636536647432636, 'samples': 17121280, 'steps': 33439, 'loss/train': 1.1440011262893677}
-03/05/2022 04:45:53 - INFO - codeparrot_training - Step 33440: {'lr': 0.00044636208202995277, 'samples': 17121792, 'steps': 33440, 'loss/train': 1.6265612840652466}
-03/05/2022 04:45:55 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/05/2022 04:45:59 - INFO - codeparrot_training - Step 33441: {'lr': 0.0004463587974971014, 'samples': 17122304, 'steps': 33441, 'loss/train': 1.9647272825241089}
-03/05/2022 04:46:02 - INFO - codeparrot_training - Step 33442: {'lr': 0.0004463555128757739, 'samples': 17122816, 'steps': 33442, 'loss/train': 1.262209415435791}
-03/05/2022 04:46:03 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/05/2022 04:46:07 - INFO - codeparrot_training - Step 33443: {'lr': 0.00044635222816597153, 'samples': 17123328, 'steps': 33443, 'loss/train': 1.3243591785430908}
-03/05/2022 04:46:10 - INFO - codeparrot_training - Step 33444: {'lr': 0.0004463489433676959, 'samples': 17123840, 'steps': 33444, 'loss/train': 1.7063919305801392}
-03/05/2022 04:46:12 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/05/2022 04:46:16 - INFO - codeparrot_training - Step 33445: {'lr': 0.00044634565848094854, 'samples': 17124352, 'steps': 33445, 'loss/train': 0.9963560104370117}
-03/05/2022 04:46:19 - INFO - codeparrot_training - Step 33446: {'lr': 0.0004463423735057308, 'samples': 17124864, 'steps': 33446, 'loss/train': 1.8027663230895996}
-03/05/2022 04:46:21 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 04:46:24 - INFO - codeparrot_training - Step 33447: {'lr': 0.00044633908844204424, 'samples': 17125376, 'steps': 33447, 'loss/train': 1.5296945571899414}
-03/05/2022 04:46:27 - INFO - codeparrot_training - Step 33448: {'lr': 0.0004463358032898903, 'samples': 17125888, 'steps': 33448, 'loss/train': 2.0157408714294434}
-03/05/2022 04:46:29 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/05/2022 04:46:32 - INFO - codeparrot_training - Step 33449: {'lr': 0.00044633251804927044, 'samples': 17126400, 'steps': 33449, 'loss/train': 3.288628578186035}
-03/05/2022 04:46:36 - INFO - codeparrot_training - Step 33450: {'lr': 0.0004463292327201862, 'samples': 17126912, 'steps': 33450, 'loss/train': 2.045158863067627}
-03/05/2022 04:46:37 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/05/2022 04:46:41 - INFO - codeparrot_training - Step 33451: {'lr': 0.0004463259473026391, 'samples': 17127424, 'steps': 33451, 'loss/train': 2.069981098175049}
-03/05/2022 04:46:44 - INFO - codeparrot_training - Step 33452: {'lr': 0.0004463226617966305, 'samples': 17127936, 'steps': 33452, 'loss/train': 1.3332791328430176}
-03/05/2022 04:46:46 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/05/2022 04:46:49 - INFO - codeparrot_training - Step 33453: {'lr': 0.00044631937620216196, 'samples': 17128448, 'steps': 33453, 'loss/train': 1.7970229387283325}
-03/05/2022 04:46:53 - INFO - codeparrot_training - Step 33454: {'lr': 0.00044631609051923494, 'samples': 17128960, 'steps': 33454, 'loss/train': 1.7123819589614868}
-03/05/2022 04:46:54 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/05/2022 04:46:58 - INFO - codeparrot_training - Step 33455: {'lr': 0.00044631280474785086, 'samples': 17129472, 'steps': 33455, 'loss/train': 1.5462727546691895}
-03/05/2022 04:47:01 - INFO - codeparrot_training - Step 33456: {'lr': 0.0004463095188880113, 'samples': 17129984, 'steps': 33456, 'loss/train': 1.3446537256240845}
-03/05/2022 04:47:02 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/05/2022 04:47:06 - INFO - codeparrot_training - Step 33457: {'lr': 0.00044630623293971775, 'samples': 17130496, 'steps': 33457, 'loss/train': 1.1698766946792603}
-03/05/2022 04:47:09 - INFO - codeparrot_training - Step 33458: {'lr': 0.0004463029469029716, 'samples': 17131008, 'steps': 33458, 'loss/train': 1.8038116693496704}
-03/05/2022 04:47:11 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 04:47:14 - INFO - codeparrot_training - Step 33459: {'lr': 0.0004462996607777743, 'samples': 17131520, 'steps': 33459, 'loss/train': 1.4883025884628296}
-03/05/2022 04:47:18 - INFO - codeparrot_training - Step 33460: {'lr': 0.00044629637456412754, 'samples': 17132032, 'steps': 33460, 'loss/train': 1.9204295873641968}
-03/05/2022 04:47:19 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/05/2022 04:47:23 - INFO - codeparrot_training - Step 33461: {'lr': 0.0004462930882620325, 'samples': 17132544, 'steps': 33461, 'loss/train': 1.6651878356933594}
-03/05/2022 04:47:26 - INFO - codeparrot_training - Step 33462: {'lr': 0.0004462898018714909, 'samples': 17133056, 'steps': 33462, 'loss/train': 1.9412455558776855}
-03/05/2022 04:47:27 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/05/2022 04:47:32 - INFO - codeparrot_training - Step 33463: {'lr': 0.0004462865153925042, 'samples': 17133568, 'steps': 33463, 'loss/train': 1.9131163358688354}
-03/05/2022 04:47:35 - INFO - codeparrot_training - Step 33464: {'lr': 0.00044628322882507375, 'samples': 17134080, 'steps': 33464, 'loss/train': 6.435811519622803}
-03/05/2022 04:47:36 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/05/2022 04:47:40 - INFO - codeparrot_training - Step 33465: {'lr': 0.0004462799421692012, 'samples': 17134592, 'steps': 33465, 'loss/train': 2.3551957607269287}
-03/05/2022 04:47:43 - INFO - codeparrot_training - Step 33466: {'lr': 0.0004462766554248878, 'samples': 17135104, 'steps': 33466, 'loss/train': 1.803325891494751}
-03/05/2022 04:47:45 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 04:47:48 - INFO - codeparrot_training - Step 33467: {'lr': 0.0004462733685921353, 'samples': 17135616, 'steps': 33467, 'loss/train': 1.8293875455856323}
-03/05/2022 04:47:51 - INFO - codeparrot_training - Step 33468: {'lr': 0.000446270081670945, 'samples': 17136128, 'steps': 33468, 'loss/train': 2.119594097137451}
-03/05/2022 04:47:53 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/05/2022 04:47:57 - INFO - codeparrot_training - Step 33469: {'lr': 0.0004462667946613184, 'samples': 17136640, 'steps': 33469, 'loss/train': 2.3080646991729736}
-03/05/2022 04:48:00 - INFO - codeparrot_training - Step 33470: {'lr': 0.00044626350756325707, 'samples': 17137152, 'steps': 33470, 'loss/train': 2.174365520477295}
-03/05/2022 04:48:01 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/05/2022 04:48:05 - INFO - codeparrot_training - Step 33471: {'lr': 0.0004462602203767624, 'samples': 17137664, 'steps': 33471, 'loss/train': 1.5706700086593628}
-03/05/2022 04:48:08 - INFO - codeparrot_training - Step 33472: {'lr': 0.0004462569331018359, 'samples': 17138176, 'steps': 33472, 'loss/train': 2.118823528289795}
-03/05/2022 04:48:10 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/05/2022 04:48:14 - INFO - codeparrot_training - Step 33473: {'lr': 0.00044625364573847904, 'samples': 17138688, 'steps': 33473, 'loss/train': 3.0985913276672363}
-03/05/2022 04:48:17 - INFO - codeparrot_training - Step 33474: {'lr': 0.0004462503582866933, 'samples': 17139200, 'steps': 33474, 'loss/train': 1.7558958530426025}
-03/05/2022 04:48:19 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/05/2022 04:48:22 - INFO - codeparrot_training - Step 33475: {'lr': 0.00044624707074648017, 'samples': 17139712, 'steps': 33475, 'loss/train': 4.688785076141357}
-03/05/2022 04:48:25 - INFO - codeparrot_training - Step 33476: {'lr': 0.0004462437831178412, 'samples': 17140224, 'steps': 33476, 'loss/train': 1.8062219619750977}
-03/05/2022 04:48:27 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/05/2022 04:48:31 - INFO - codeparrot_training - Step 33477: {'lr': 0.00044624049540077784, 'samples': 17140736, 'steps': 33477, 'loss/train': 1.7763456106185913}
-03/05/2022 04:48:34 - INFO - codeparrot_training - Step 33478: {'lr': 0.0004462372075952914, 'samples': 17141248, 'steps': 33478, 'loss/train': 1.7571529150009155}
-03/05/2022 04:48:36 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/05/2022 04:48:39 - INFO - codeparrot_training - Step 33479: {'lr': 0.0004462339197013836, 'samples': 17141760, 'steps': 33479, 'loss/train': 1.3733891248703003}
-03/05/2022 04:48:42 - INFO - codeparrot_training - Step 33480: {'lr': 0.00044623063171905585, 'samples': 17142272, 'steps': 33480, 'loss/train': 1.0368611812591553}
-03/05/2022 04:48:44 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 04:48:47 - INFO - codeparrot_training - Step 33481: {'lr': 0.0004462273436483095, 'samples': 17142784, 'steps': 33481, 'loss/train': 1.9818273782730103}
-03/05/2022 04:48:51 - INFO - codeparrot_training - Step 33482: {'lr': 0.00044622405548914627, 'samples': 17143296, 'steps': 33482, 'loss/train': 4.651758670806885}
-03/05/2022 04:48:53 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/05/2022 04:48:56 - INFO - codeparrot_training - Step 33483: {'lr': 0.00044622076724156747, 'samples': 17143808, 'steps': 33483, 'loss/train': 1.781371831893921}
-03/05/2022 04:48:59 - INFO - codeparrot_training - Step 33484: {'lr': 0.00044621747890557454, 'samples': 17144320, 'steps': 33484, 'loss/train': 2.4993910789489746}
-03/05/2022 04:49:01 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 04:49:04 - INFO - codeparrot_training - Step 33485: {'lr': 0.0004462141904811691, 'samples': 17144832, 'steps': 33485, 'loss/train': 1.9342212677001953}
-03/05/2022 04:49:08 - INFO - codeparrot_training - Step 33486: {'lr': 0.00044621090196835254, 'samples': 17145344, 'steps': 33486, 'loss/train': 0.09061639755964279}
-03/05/2022 04:49:09 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/05/2022 04:49:13 - INFO - codeparrot_training - Step 33487: {'lr': 0.00044620761336712646, 'samples': 17145856, 'steps': 33487, 'loss/train': 2.005896806716919}
-03/05/2022 04:49:16 - INFO - codeparrot_training - Step 33488: {'lr': 0.00044620432467749215, 'samples': 17146368, 'steps': 33488, 'loss/train': 1.2757248878479004}
-03/05/2022 04:49:18 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/05/2022 04:49:22 - INFO - codeparrot_training - Step 33489: {'lr': 0.0004462010358994513, 'samples': 17146880, 'steps': 33489, 'loss/train': 1.0555795431137085}
-03/05/2022 04:49:25 - INFO - codeparrot_training - Step 33490: {'lr': 0.0004461977470330052, 'samples': 17147392, 'steps': 33490, 'loss/train': 1.8667715787887573}
-03/05/2022 04:49:28 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/05/2022 04:49:30 - INFO - codeparrot_training - Step 33491: {'lr': 0.00044619445807815545, 'samples': 17147904, 'steps': 33491, 'loss/train': 0.5039077997207642}
-03/05/2022 04:49:33 - INFO - codeparrot_training - Step 33492: {'lr': 0.00044619116903490356, 'samples': 17148416, 'steps': 33492, 'loss/train': 1.5600253343582153}
-03/05/2022 04:49:36 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 04:49:39 - INFO - codeparrot_training - Step 33493: {'lr': 0.00044618787990325086, 'samples': 17148928, 'steps': 33493, 'loss/train': 1.9713783264160156}
-03/05/2022 04:49:42 - INFO - codeparrot_training - Step 33494: {'lr': 0.000446184590683199, 'samples': 17149440, 'steps': 33494, 'loss/train': 1.550588607788086}
-03/05/2022 04:49:44 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 04:49:47 - INFO - codeparrot_training - Step 33495: {'lr': 0.00044618130137474935, 'samples': 17149952, 'steps': 33495, 'loss/train': 1.7003018856048584}
-03/05/2022 04:49:50 - INFO - codeparrot_training - Step 33496: {'lr': 0.0004461780119779034, 'samples': 17150464, 'steps': 33496, 'loss/train': 1.414426326751709}
-03/05/2022 04:49:53 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/05/2022 04:49:55 - INFO - codeparrot_training - Step 33497: {'lr': 0.0004461747224926628, 'samples': 17150976, 'steps': 33497, 'loss/train': 1.8659199476242065}
-03/05/2022 04:49:59 - INFO - codeparrot_training - Step 33498: {'lr': 0.0004461714329190288, 'samples': 17151488, 'steps': 33498, 'loss/train': 2.3922362327575684}
-03/05/2022 04:50:01 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/05/2022 04:50:04 - INFO - codeparrot_training - Step 33499: {'lr': 0.00044616814325700293, 'samples': 17152000, 'steps': 33499, 'loss/train': 1.8888484239578247}
-03/05/2022 04:50:07 - INFO - codeparrot_training - Step 33500: {'lr': 0.0004461648535065869, 'samples': 17152512, 'steps': 33500, 'loss/train': 2.139421224594116}
-03/05/2022 04:50:10 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/05/2022 04:50:13 - INFO - codeparrot_training - Step 33501: {'lr': 0.0004461615636677818, 'samples': 17153024, 'steps': 33501, 'loss/train': 1.6973953247070312}
-03/05/2022 04:50:16 - INFO - codeparrot_training - Step 33502: {'lr': 0.0004461582737405895, 'samples': 17153536, 'steps': 33502, 'loss/train': 1.3614157438278198}
-03/05/2022 04:50:18 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/05/2022 04:50:21 - INFO - codeparrot_training - Step 33503: {'lr': 0.00044615498372501116, 'samples': 17154048, 'steps': 33503, 'loss/train': 1.9766550064086914}
-03/05/2022 04:50:24 - INFO - codeparrot_training - Step 33504: {'lr': 0.00044615169362104856, 'samples': 17154560, 'steps': 33504, 'loss/train': 2.0890936851501465}
-03/05/2022 04:50:27 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/05/2022 04:50:30 - INFO - codeparrot_training - Step 33505: {'lr': 0.00044614840342870293, 'samples': 17155072, 'steps': 33505, 'loss/train': 1.7183324098587036}
-03/05/2022 04:50:33 - INFO - codeparrot_training - Step 33506: {'lr': 0.0004461451131479759, 'samples': 17155584, 'steps': 33506, 'loss/train': 1.9086568355560303}
-03/05/2022 04:50:35 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/05/2022 04:50:38 - INFO - codeparrot_training - Step 33507: {'lr': 0.0004461418227788689, 'samples': 17156096, 'steps': 33507, 'loss/train': 2.0103378295898438}
-03/05/2022 04:50:41 - INFO - codeparrot_training - Step 33508: {'lr': 0.00044613853232138343, 'samples': 17156608, 'steps': 33508, 'loss/train': 1.9204638004302979}
-03/05/2022 04:50:43 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/05/2022 04:50:47 - INFO - codeparrot_training - Step 33509: {'lr': 0.0004461352417755209, 'samples': 17157120, 'steps': 33509, 'loss/train': 2.0305142402648926}
-03/05/2022 04:50:50 - INFO - codeparrot_training - Step 33510: {'lr': 0.0004461319511412829, 'samples': 17157632, 'steps': 33510, 'loss/train': 1.619326114654541}
-03/05/2022 04:50:52 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/05/2022 04:50:55 - INFO - codeparrot_training - Step 33511: {'lr': 0.00044612866041867093, 'samples': 17158144, 'steps': 33511, 'loss/train': 2.0225210189819336}
-03/05/2022 04:50:58 - INFO - codeparrot_training - Step 33512: {'lr': 0.0004461253696076863, 'samples': 17158656, 'steps': 33512, 'loss/train': 1.3889366388320923}
-03/05/2022 04:51:00 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/05/2022 04:51:04 - INFO - codeparrot_training - Step 33513: {'lr': 0.00044612207870833073, 'samples': 17159168, 'steps': 33513, 'loss/train': 1.4979047775268555}
-03/05/2022 04:51:07 - INFO - codeparrot_training - Step 33514: {'lr': 0.0004461187877206055, 'samples': 17159680, 'steps': 33514, 'loss/train': 1.6080878973007202}
-03/05/2022 04:51:09 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/05/2022 04:51:12 - INFO - codeparrot_training - Step 33515: {'lr': 0.00044611549664451216, 'samples': 17160192, 'steps': 33515, 'loss/train': 1.774382472038269}
-03/05/2022 04:51:15 - INFO - codeparrot_training - Step 33516: {'lr': 0.0004461122054800522, 'samples': 17160704, 'steps': 33516, 'loss/train': 1.6848671436309814}
-03/05/2022 04:51:17 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 04:51:20 - INFO - codeparrot_training - Step 33517: {'lr': 0.00044610891422722714, 'samples': 17161216, 'steps': 33517, 'loss/train': 1.154137134552002}
-03/05/2022 04:51:24 - INFO - codeparrot_training - Step 33518: {'lr': 0.00044610562288603846, 'samples': 17161728, 'steps': 33518, 'loss/train': 1.846269130706787}
-03/05/2022 04:51:26 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/05/2022 04:51:29 - INFO - codeparrot_training - Step 33519: {'lr': 0.00044610233145648756, 'samples': 17162240, 'steps': 33519, 'loss/train': 1.8281073570251465}
-03/05/2022 04:51:32 - INFO - codeparrot_training - Step 33520: {'lr': 0.00044609903993857603, 'samples': 17162752, 'steps': 33520, 'loss/train': 1.4997453689575195}
-03/05/2022 04:51:34 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/05/2022 04:51:37 - INFO - codeparrot_training - Step 33521: {'lr': 0.0004460957483323052, 'samples': 17163264, 'steps': 33521, 'loss/train': 2.154050827026367}
-03/05/2022 04:51:40 - INFO - codeparrot_training - Step 33522: {'lr': 0.0004460924566376767, 'samples': 17163776, 'steps': 33522, 'loss/train': 1.5889368057250977}
-03/05/2022 04:51:43 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/05/2022 04:51:46 - INFO - codeparrot_training - Step 33523: {'lr': 0.00044608916485469195, 'samples': 17164288, 'steps': 33523, 'loss/train': 1.9227056503295898}
-03/05/2022 04:51:49 - INFO - codeparrot_training - Step 33524: {'lr': 0.0004460858729833525, 'samples': 17164800, 'steps': 33524, 'loss/train': 1.7285442352294922}
-03/05/2022 04:51:51 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/05/2022 04:51:54 - INFO - codeparrot_training - Step 33525: {'lr': 0.0004460825810236598, 'samples': 17165312, 'steps': 33525, 'loss/train': 1.899969458580017}
-03/05/2022 04:51:57 - INFO - codeparrot_training - Step 33526: {'lr': 0.00044607928897561524, 'samples': 17165824, 'steps': 33526, 'loss/train': 2.687861204147339}
-03/05/2022 04:52:03 - INFO - codeparrot_training - Step 33527: {'lr': 0.0004460759968392204, 'samples': 17166336, 'steps': 33527, 'loss/train': 1.2853384017944336}
-03/05/2022 04:52:06 - INFO - codeparrot_training - Step 33528: {'lr': 0.0004460727046144768, 'samples': 17166848, 'steps': 33528, 'loss/train': 2.344062089920044}
-03/05/2022 04:52:09 - INFO - codeparrot_training - Step 33529: {'lr': 0.00044606941230138574, 'samples': 17167360, 'steps': 33529, 'loss/train': 1.0734360218048096}
-03/05/2022 04:52:09 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/05/2022 04:52:14 - INFO - codeparrot_training - Step 33530: {'lr': 0.0004460661198999489, 'samples': 17167872, 'steps': 33530, 'loss/train': 1.2307394742965698}
-03/05/2022 04:52:18 - INFO - codeparrot_training - Step 33531: {'lr': 0.0004460628274101677, 'samples': 17168384, 'steps': 33531, 'loss/train': 1.8025763034820557}
-03/05/2022 04:52:18 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/05/2022 04:52:23 - INFO - codeparrot_training - Step 33532: {'lr': 0.0004460595348320436, 'samples': 17168896, 'steps': 33532, 'loss/train': 1.5134105682373047}
-03/05/2022 04:52:26 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/05/2022 04:52:28 - INFO - codeparrot_training - Step 33533: {'lr': 0.0004460562421655782, 'samples': 17169408, 'steps': 33533, 'loss/train': 1.0199304819107056}
-03/05/2022 04:52:31 - INFO - codeparrot_training - Step 33534: {'lr': 0.0004460529494107727, 'samples': 17169920, 'steps': 33534, 'loss/train': 1.6037136316299438}
-03/05/2022 04:52:35 - INFO - codeparrot_training - Step 33535: {'lr': 0.00044604965656762884, 'samples': 17170432, 'steps': 33535, 'loss/train': 1.4356862306594849}
-03/05/2022 04:52:35 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 04:52:40 - INFO - codeparrot_training - Step 33536: {'lr': 0.0004460463636361481, 'samples': 17170944, 'steps': 33536, 'loss/train': 2.2424275875091553}
-03/05/2022 04:52:43 - INFO - codeparrot_training - Step 33537: {'lr': 0.00044604307061633187, 'samples': 17171456, 'steps': 33537, 'loss/train': 1.8621257543563843}
-03/05/2022 04:52:43 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/05/2022 04:52:48 - INFO - codeparrot_training - Step 33538: {'lr': 0.0004460397775081816, 'samples': 17171968, 'steps': 33538, 'loss/train': 2.135127305984497}
-03/05/2022 04:52:52 - INFO - codeparrot_training - Step 33539: {'lr': 0.00044603648431169884, 'samples': 17172480, 'steps': 33539, 'loss/train': 1.007950782775879}
-03/05/2022 04:52:52 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/05/2022 04:52:58 - INFO - codeparrot_training - Step 33540: {'lr': 0.0004460331910268851, 'samples': 17172992, 'steps': 33540, 'loss/train': 0.6041748523712158}
-03/05/2022 04:53:01 - INFO - codeparrot_training - Step 33541: {'lr': 0.0004460298976537418, 'samples': 17173504, 'steps': 33541, 'loss/train': 2.115260362625122}
-03/05/2022 04:53:04 - INFO - codeparrot_training - Step 33542: {'lr': 0.00044602660419227046, 'samples': 17174016, 'steps': 33542, 'loss/train': 1.0270541906356812}
-03/05/2022 04:53:04 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/05/2022 04:53:09 - INFO - codeparrot_training - Step 33543: {'lr': 0.0004460233106424726, 'samples': 17174528, 'steps': 33543, 'loss/train': 0.8249497413635254}
-03/05/2022 04:53:12 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/05/2022 04:53:15 - INFO - codeparrot_training - Step 33544: {'lr': 0.00044602001700434963, 'samples': 17175040, 'steps': 33544, 'loss/train': 1.8265620470046997}
-03/05/2022 04:53:18 - INFO - codeparrot_training - Step 33545: {'lr': 0.00044601672327790304, 'samples': 17175552, 'steps': 33545, 'loss/train': 2.3485727310180664}
-03/05/2022 04:53:21 - INFO - codeparrot_training - Step 33546: {'lr': 0.00044601342946313437, 'samples': 17176064, 'steps': 33546, 'loss/train': 1.3221460580825806}
-03/05/2022 04:53:21 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/05/2022 04:53:26 - INFO - codeparrot_training - Step 33547: {'lr': 0.0004460101355600451, 'samples': 17176576, 'steps': 33547, 'loss/train': 0.8309028744697571}
-03/05/2022 04:53:29 - INFO - codeparrot_training - Step 33548: {'lr': 0.0004460068415686366, 'samples': 17177088, 'steps': 33548, 'loss/train': 2.366419553756714}
-03/05/2022 04:53:29 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/05/2022 04:53:35 - INFO - codeparrot_training - Step 33549: {'lr': 0.0004460035474889105, 'samples': 17177600, 'steps': 33549, 'loss/train': 1.4740426540374756}
-03/05/2022 04:53:38 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/05/2022 04:53:40 - INFO - codeparrot_training - Step 33550: {'lr': 0.00044600025332086824, 'samples': 17178112, 'steps': 33550, 'loss/train': 2.2679879665374756}
-03/05/2022 04:53:43 - INFO - codeparrot_training - Step 33551: {'lr': 0.0004459969590645113, 'samples': 17178624, 'steps': 33551, 'loss/train': 2.0823307037353516}
-03/05/2022 04:53:46 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/05/2022 04:53:48 - INFO - codeparrot_training - Step 33552: {'lr': 0.000445993664719841, 'samples': 17179136, 'steps': 33552, 'loss/train': 1.7948023080825806}
-03/05/2022 04:53:52 - INFO - codeparrot_training - Step 33553: {'lr': 0.0004459903702868592, 'samples': 17179648, 'steps': 33553, 'loss/train': 1.6942301988601685}
-03/05/2022 04:53:55 - INFO - codeparrot_training - Step 33554: {'lr': 0.00044598707576556706, 'samples': 17180160, 'steps': 33554, 'loss/train': 1.7522468566894531}
-03/05/2022 04:53:55 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/05/2022 04:54:01 - INFO - codeparrot_training - Step 33555: {'lr': 0.00044598378115596614, 'samples': 17180672, 'steps': 33555, 'loss/train': 2.0756826400756836}
-03/05/2022 04:54:04 - INFO - codeparrot_training - Step 33556: {'lr': 0.000445980486458058, 'samples': 17181184, 'steps': 33556, 'loss/train': 2.170283317565918}
-03/05/2022 04:54:07 - INFO - codeparrot_training - Step 33557: {'lr': 0.0004459771916718441, 'samples': 17181696, 'steps': 33557, 'loss/train': 2.1352639198303223}
-03/05/2022 04:54:07 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/05/2022 04:54:12 - INFO - codeparrot_training - Step 33558: {'lr': 0.0004459738967973258, 'samples': 17182208, 'steps': 33558, 'loss/train': 1.466123104095459}
-03/05/2022 04:54:15 - INFO - codeparrot_training - Step 33559: {'lr': 0.00044597060183450477, 'samples': 17182720, 'steps': 33559, 'loss/train': 1.218019723892212}
-03/05/2022 04:54:15 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/05/2022 04:54:21 - INFO - codeparrot_training - Step 33560: {'lr': 0.00044596730678338236, 'samples': 17183232, 'steps': 33560, 'loss/train': 1.660805106163025}
-03/05/2022 04:54:24 - INFO - codeparrot_training - Step 33561: {'lr': 0.0004459640116439602, 'samples': 17183744, 'steps': 33561, 'loss/train': 1.7097482681274414}
-03/05/2022 04:54:24 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/05/2022 04:54:29 - INFO - codeparrot_training - Step 33562: {'lr': 0.0004459607164162396, 'samples': 17184256, 'steps': 33562, 'loss/train': 1.9240474700927734}
-03/05/2022 04:54:32 - INFO - codeparrot_training - Step 33563: {'lr': 0.00044595742110022216, 'samples': 17184768, 'steps': 33563, 'loss/train': 1.6915699243545532}
-03/05/2022 04:54:32 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/05/2022 04:54:38 - INFO - codeparrot_training - Step 33564: {'lr': 0.00044595412569590934, 'samples': 17185280, 'steps': 33564, 'loss/train': 1.898544192314148}
-03/05/2022 04:54:40 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 04:54:43 - INFO - codeparrot_training - Step 33565: {'lr': 0.0004459508302033025, 'samples': 17185792, 'steps': 33565, 'loss/train': 1.4834462404251099}
-03/05/2022 04:54:46 - INFO - codeparrot_training - Step 33566: {'lr': 0.00044594753462240335, 'samples': 17186304, 'steps': 33566, 'loss/train': 1.7808737754821777}
-03/05/2022 04:54:49 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/05/2022 04:54:51 - INFO - codeparrot_training - Step 33567: {'lr': 0.0004459442389532132, 'samples': 17186816, 'steps': 33567, 'loss/train': 1.721524953842163}
-03/05/2022 04:54:55 - INFO - codeparrot_training - Step 33568: {'lr': 0.0004459409431957337, 'samples': 17187328, 'steps': 33568, 'loss/train': 4.255745887756348}
-03/05/2022 04:54:58 - INFO - codeparrot_training - Step 33569: {'lr': 0.00044593764734996615, 'samples': 17187840, 'steps': 33569, 'loss/train': 2.6696643829345703}
-03/05/2022 04:54:58 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/05/2022 04:55:03 - INFO - codeparrot_training - Step 33570: {'lr': 0.00044593435141591215, 'samples': 17188352, 'steps': 33570, 'loss/train': 2.147439956665039}
-03/05/2022 04:55:06 - INFO - codeparrot_training - Step 33571: {'lr': 0.00044593105539357313, 'samples': 17188864, 'steps': 33571, 'loss/train': 1.6487151384353638}
-03/05/2022 04:55:07 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/05/2022 04:55:12 - INFO - codeparrot_training - Step 33572: {'lr': 0.00044592775928295063, 'samples': 17189376, 'steps': 33572, 'loss/train': 1.1814044713974}
-03/05/2022 04:55:15 - INFO - codeparrot_training - Step 33573: {'lr': 0.0004459244630840461, 'samples': 17189888, 'steps': 33573, 'loss/train': 1.4722651243209839}
-03/05/2022 04:55:16 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/05/2022 04:55:20 - INFO - codeparrot_training - Step 33574: {'lr': 0.000445921166796861, 'samples': 17190400, 'steps': 33574, 'loss/train': 2.474961042404175}
-03/05/2022 04:55:24 - INFO - codeparrot_training - Step 33575: {'lr': 0.00044591787042139684, 'samples': 17190912, 'steps': 33575, 'loss/train': 2.0909111499786377}
-03/05/2022 04:55:25 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/05/2022 04:55:29 - INFO - codeparrot_training - Step 33576: {'lr': 0.0004459145739576552, 'samples': 17191424, 'steps': 33576, 'loss/train': 1.3652796745300293}
-03/05/2022 04:55:32 - INFO - codeparrot_training - Step 33577: {'lr': 0.0004459112774056374, 'samples': 17191936, 'steps': 33577, 'loss/train': 1.6046525239944458}
-03/05/2022 04:55:33 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 04:55:37 - INFO - codeparrot_training - Step 33578: {'lr': 0.000445907980765345, 'samples': 17192448, 'steps': 33578, 'loss/train': 1.1817234754562378}
-03/05/2022 04:55:41 - INFO - codeparrot_training - Step 33579: {'lr': 0.00044590468403677954, 'samples': 17192960, 'steps': 33579, 'loss/train': 2.0022499561309814}
-03/05/2022 04:55:42 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/05/2022 04:55:46 - INFO - codeparrot_training - Step 33580: {'lr': 0.00044590138721994243, 'samples': 17193472, 'steps': 33580, 'loss/train': 1.7402523756027222}
-03/05/2022 04:55:49 - INFO - codeparrot_training - Step 33581: {'lr': 0.00044589809031483517, 'samples': 17193984, 'steps': 33581, 'loss/train': 0.8934062719345093}
-03/05/2022 04:55:50 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/05/2022 04:55:54 - INFO - codeparrot_training - Step 33582: {'lr': 0.0004458947933214592, 'samples': 17194496, 'steps': 33582, 'loss/train': 1.0886738300323486}
-03/05/2022 04:55:57 - INFO - codeparrot_training - Step 33583: {'lr': 0.0004458914962398162, 'samples': 17195008, 'steps': 33583, 'loss/train': 1.9218090772628784}
-03/05/2022 04:55:59 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/05/2022 04:56:03 - INFO - codeparrot_training - Step 33584: {'lr': 0.0004458881990699074, 'samples': 17195520, 'steps': 33584, 'loss/train': 1.6360738277435303}
-03/05/2022 04:56:06 - INFO - codeparrot_training - Step 33585: {'lr': 0.00044588490181173435, 'samples': 17196032, 'steps': 33585, 'loss/train': 2.3009421825408936}
-03/05/2022 04:56:07 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/05/2022 04:56:11 - INFO - codeparrot_training - Step 33586: {'lr': 0.0004458816044652987, 'samples': 17196544, 'steps': 33586, 'loss/train': 1.613369345664978}
-03/05/2022 04:56:14 - INFO - codeparrot_training - Step 33587: {'lr': 0.00044587830703060176, 'samples': 17197056, 'steps': 33587, 'loss/train': 1.50320565700531}
-03/05/2022 04:56:16 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/05/2022 04:56:20 - INFO - codeparrot_training - Step 33588: {'lr': 0.00044587500950764514, 'samples': 17197568, 'steps': 33588, 'loss/train': 1.6947509050369263}
-03/05/2022 04:56:23 - INFO - codeparrot_training - Step 33589: {'lr': 0.0004458717118964302, 'samples': 17198080, 'steps': 33589, 'loss/train': 1.8883278369903564}
-03/05/2022 04:56:24 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/05/2022 04:56:28 - INFO - codeparrot_training - Step 33590: {'lr': 0.0004458684141969585, 'samples': 17198592, 'steps': 33590, 'loss/train': 2.057932138442993}
-03/05/2022 04:56:31 - INFO - codeparrot_training - Step 33591: {'lr': 0.0004458651164092315, 'samples': 17199104, 'steps': 33591, 'loss/train': 1.848440408706665}
-03/05/2022 04:56:32 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/05/2022 04:56:36 - INFO - codeparrot_training - Step 33592: {'lr': 0.00044586181853325076, 'samples': 17199616, 'steps': 33592, 'loss/train': 1.581458330154419}
-03/05/2022 04:56:40 - INFO - codeparrot_training - Step 33593: {'lr': 0.0004458585205690177, 'samples': 17200128, 'steps': 33593, 'loss/train': 1.6954840421676636}
-03/05/2022 04:56:40 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/05/2022 04:56:45 - INFO - codeparrot_training - Step 33594: {'lr': 0.0004458552225165338, 'samples': 17200640, 'steps': 33594, 'loss/train': 1.615804672241211}
-03/05/2022 04:56:48 - INFO - codeparrot_training - Step 33595: {'lr': 0.00044585192437580044, 'samples': 17201152, 'steps': 33595, 'loss/train': 1.721587061882019}
-03/05/2022 04:56:49 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/05/2022 04:56:53 - INFO - codeparrot_training - Step 33596: {'lr': 0.0004458486261468194, 'samples': 17201664, 'steps': 33596, 'loss/train': 2.47548246383667}
-03/05/2022 04:56:56 - INFO - codeparrot_training - Step 33597: {'lr': 0.0004458453278295919, 'samples': 17202176, 'steps': 33597, 'loss/train': 1.5795776844024658}
-03/05/2022 04:56:57 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/05/2022 04:57:02 - INFO - codeparrot_training - Step 33598: {'lr': 0.00044584202942411956, 'samples': 17202688, 'steps': 33598, 'loss/train': 0.5867262482643127}
-03/05/2022 04:57:05 - INFO - codeparrot_training - Step 33599: {'lr': 0.00044583873093040376, 'samples': 17203200, 'steps': 33599, 'loss/train': 1.1657555103302002}
-03/05/2022 04:57:06 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/05/2022 04:57:10 - INFO - codeparrot_training - Step 33600: {'lr': 0.00044583543234844616, 'samples': 17203712, 'steps': 33600, 'loss/train': 1.5614173412322998}
-03/05/2022 04:57:13 - INFO - codeparrot_training - Step 33601: {'lr': 0.00044583213367824806, 'samples': 17204224, 'steps': 33601, 'loss/train': 1.2548081874847412}
-03/05/2022 04:57:14 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 04:57:19 - INFO - codeparrot_training - Step 33602: {'lr': 0.00044582883491981097, 'samples': 17204736, 'steps': 33602, 'loss/train': 1.2465648651123047}
-03/05/2022 04:57:22 - INFO - codeparrot_training - Step 33603: {'lr': 0.0004458255360731365, 'samples': 17205248, 'steps': 33603, 'loss/train': 6.62829065322876}
-03/05/2022 04:57:23 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/05/2022 04:57:27 - INFO - codeparrot_training - Step 33604: {'lr': 0.00044582223713822606, 'samples': 17205760, 'steps': 33604, 'loss/train': 1.3546030521392822}
-03/05/2022 04:57:30 - INFO - codeparrot_training - Step 33605: {'lr': 0.0004458189381150811, 'samples': 17206272, 'steps': 33605, 'loss/train': 0.9507414698600769}
-03/05/2022 04:57:32 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/05/2022 04:57:35 - INFO - codeparrot_training - Step 33606: {'lr': 0.00044581563900370326, 'samples': 17206784, 'steps': 33606, 'loss/train': 1.8144936561584473}
-03/05/2022 04:57:39 - INFO - codeparrot_training - Step 33607: {'lr': 0.0004458123398040938, 'samples': 17207296, 'steps': 33607, 'loss/train': 1.7711725234985352}
-03/05/2022 04:57:40 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/05/2022 04:57:44 - INFO - codeparrot_training - Step 33608: {'lr': 0.0004458090405162544, 'samples': 17207808, 'steps': 33608, 'loss/train': 2.3273074626922607}
-03/05/2022 04:57:47 - INFO - codeparrot_training - Step 33609: {'lr': 0.0004458057411401864, 'samples': 17208320, 'steps': 33609, 'loss/train': 1.1190072298049927}
-03/05/2022 04:57:48 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/05/2022 04:57:52 - INFO - codeparrot_training - Step 33610: {'lr': 0.00044580244167589136, 'samples': 17208832, 'steps': 33610, 'loss/train': 1.1245813369750977}
-03/05/2022 04:57:55 - INFO - codeparrot_training - Step 33611: {'lr': 0.00044579914212337083, 'samples': 17209344, 'steps': 33611, 'loss/train': 1.9975531101226807}
-03/05/2022 04:57:57 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/05/2022 04:58:01 - INFO - codeparrot_training - Step 33612: {'lr': 0.00044579584248262617, 'samples': 17209856, 'steps': 33612, 'loss/train': 0.705410361289978}
-03/05/2022 04:58:04 - INFO - codeparrot_training - Step 33613: {'lr': 0.0004457925427536589, 'samples': 17210368, 'steps': 33613, 'loss/train': 0.8843287229537964}
-03/05/2022 04:58:05 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/05/2022 04:58:09 - INFO - codeparrot_training - Step 33614: {'lr': 0.0004457892429364706, 'samples': 17210880, 'steps': 33614, 'loss/train': 3.421769142150879}
-03/05/2022 04:58:12 - INFO - codeparrot_training - Step 33615: {'lr': 0.00044578594303106266, 'samples': 17211392, 'steps': 33615, 'loss/train': 2.469468116760254}
-03/05/2022 04:58:14 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/05/2022 04:58:18 - INFO - codeparrot_training - Step 33616: {'lr': 0.00044578264303743654, 'samples': 17211904, 'steps': 33616, 'loss/train': 2.1370832920074463}
-03/05/2022 04:58:21 - INFO - codeparrot_training - Step 33617: {'lr': 0.00044577934295559387, 'samples': 17212416, 'steps': 33617, 'loss/train': 1.5723105669021606}
-03/05/2022 04:58:22 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/05/2022 04:58:26 - INFO - codeparrot_training - Step 33618: {'lr': 0.000445776042785536, 'samples': 17212928, 'steps': 33618, 'loss/train': 1.4440356492996216}
-03/05/2022 04:58:29 - INFO - codeparrot_training - Step 33619: {'lr': 0.00044577274252726454, 'samples': 17213440, 'steps': 33619, 'loss/train': 2.382261276245117}
-03/05/2022 04:58:30 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/05/2022 04:58:34 - INFO - codeparrot_training - Step 33620: {'lr': 0.00044576944218078075, 'samples': 17213952, 'steps': 33620, 'loss/train': 2.131185293197632}
-03/05/2022 04:58:38 - INFO - codeparrot_training - Step 33621: {'lr': 0.00044576614174608644, 'samples': 17214464, 'steps': 33621, 'loss/train': 0.9500150680541992}
-03/05/2022 04:58:39 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/05/2022 04:58:43 - INFO - codeparrot_training - Step 33622: {'lr': 0.0004457628412231828, 'samples': 17214976, 'steps': 33622, 'loss/train': 1.390385627746582}
-03/05/2022 04:58:46 - INFO - codeparrot_training - Step 33623: {'lr': 0.0004457595406120715, 'samples': 17215488, 'steps': 33623, 'loss/train': 0.5399864315986633}
-03/05/2022 04:58:47 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/05/2022 04:58:51 - INFO - codeparrot_training - Step 33624: {'lr': 0.000445756239912754, 'samples': 17216000, 'steps': 33624, 'loss/train': 1.595068335533142}
-03/05/2022 04:58:54 - INFO - codeparrot_training - Step 33625: {'lr': 0.00044575293912523173, 'samples': 17216512, 'steps': 33625, 'loss/train': 1.950323462486267}
-03/05/2022 04:58:55 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/05/2022 04:59:00 - INFO - codeparrot_training - Step 33626: {'lr': 0.0004457496382495062, 'samples': 17217024, 'steps': 33626, 'loss/train': 1.7496206760406494}
-03/05/2022 04:59:03 - INFO - codeparrot_training - Step 33627: {'lr': 0.00044574633728557887, 'samples': 17217536, 'steps': 33627, 'loss/train': 1.1294909715652466}
-03/05/2022 04:59:04 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/05/2022 04:59:08 - INFO - codeparrot_training - Step 33628: {'lr': 0.0004457430362334513, 'samples': 17218048, 'steps': 33628, 'loss/train': 1.6096266508102417}
-03/05/2022 04:59:11 - INFO - codeparrot_training - Step 33629: {'lr': 0.00044573973509312494, 'samples': 17218560, 'steps': 33629, 'loss/train': 1.583948016166687}
-03/05/2022 04:59:12 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/05/2022 04:59:16 - INFO - codeparrot_training - Step 33630: {'lr': 0.00044573643386460127, 'samples': 17219072, 'steps': 33630, 'loss/train': 1.1936426162719727}
-03/05/2022 04:59:20 - INFO - codeparrot_training - Step 33631: {'lr': 0.00044573313254788176, 'samples': 17219584, 'steps': 33631, 'loss/train': 1.6899062395095825}
-03/05/2022 04:59:20 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 04:59:25 - INFO - codeparrot_training - Step 33632: {'lr': 0.00044572983114296794, 'samples': 17220096, 'steps': 33632, 'loss/train': 0.1501224786043167}
-03/05/2022 04:59:28 - INFO - codeparrot_training - Step 33633: {'lr': 0.00044572652964986126, 'samples': 17220608, 'steps': 33633, 'loss/train': 2.015028953552246}
-03/05/2022 04:59:29 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/05/2022 04:59:33 - INFO - codeparrot_training - Step 33634: {'lr': 0.0004457232280685633, 'samples': 17221120, 'steps': 33634, 'loss/train': 0.7074772119522095}
-03/05/2022 04:59:37 - INFO - codeparrot_training - Step 33635: {'lr': 0.0004457199263990754, 'samples': 17221632, 'steps': 33635, 'loss/train': 1.3326743841171265}
-03/05/2022 04:59:37 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 04:59:42 - INFO - codeparrot_training - Step 33636: {'lr': 0.0004457166246413992, 'samples': 17222144, 'steps': 33636, 'loss/train': 1.376373052597046}
-03/05/2022 04:59:45 - INFO - codeparrot_training - Step 33637: {'lr': 0.000445713322795536, 'samples': 17222656, 'steps': 33637, 'loss/train': 2.1918740272521973}
-03/05/2022 04:59:46 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/05/2022 04:59:50 - INFO - codeparrot_training - Step 33638: {'lr': 0.0004457100208614875, 'samples': 17223168, 'steps': 33638, 'loss/train': 2.098397970199585}
-03/05/2022 04:59:54 - INFO - codeparrot_training - Step 33639: {'lr': 0.00044570671883925497, 'samples': 17223680, 'steps': 33639, 'loss/train': 1.5802254676818848}
-03/05/2022 04:59:54 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/05/2022 04:59:59 - INFO - codeparrot_training - Step 33640: {'lr': 0.00044570341672884006, 'samples': 17224192, 'steps': 33640, 'loss/train': 1.905474305152893}
-03/05/2022 05:00:02 - INFO - codeparrot_training - Step 33641: {'lr': 0.0004457001145302443, 'samples': 17224704, 'steps': 33641, 'loss/train': 1.2486696243286133}
-03/05/2022 05:00:03 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 05:00:07 - INFO - codeparrot_training - Step 33642: {'lr': 0.00044569681224346897, 'samples': 17225216, 'steps': 33642, 'loss/train': 1.3094062805175781}
-03/05/2022 05:00:11 - INFO - codeparrot_training - Step 33643: {'lr': 0.0004456935098685158, 'samples': 17225728, 'steps': 33643, 'loss/train': 1.9922659397125244}
-03/05/2022 05:00:11 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 05:00:16 - INFO - codeparrot_training - Step 33644: {'lr': 0.000445690207405386, 'samples': 17226240, 'steps': 33644, 'loss/train': 1.4570302963256836}
-03/05/2022 05:00:19 - INFO - codeparrot_training - Step 33645: {'lr': 0.00044568690485408125, 'samples': 17226752, 'steps': 33645, 'loss/train': 0.9996280074119568}
-03/05/2022 05:00:19 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/05/2022 05:00:24 - INFO - codeparrot_training - Step 33646: {'lr': 0.0004456836022146031, 'samples': 17227264, 'steps': 33646, 'loss/train': 2.374741315841675}
-03/05/2022 05:00:27 - INFO - codeparrot_training - Step 33647: {'lr': 0.00044568029948695287, 'samples': 17227776, 'steps': 33647, 'loss/train': 2.6301186084747314}
-03/05/2022 05:00:27 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/05/2022 05:00:33 - INFO - codeparrot_training - Step 33648: {'lr': 0.0004456769966711321, 'samples': 17228288, 'steps': 33648, 'loss/train': 2.1099252700805664}
-03/05/2022 05:00:36 - INFO - codeparrot_training - Step 33649: {'lr': 0.00044567369376714226, 'samples': 17228800, 'steps': 33649, 'loss/train': 2.3198187351226807}
-03/05/2022 05:00:36 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/05/2022 05:00:41 - INFO - codeparrot_training - Step 33650: {'lr': 0.00044567039077498497, 'samples': 17229312, 'steps': 33650, 'loss/train': 1.2144025564193726}
-03/05/2022 05:00:44 - INFO - codeparrot_training - Step 33651: {'lr': 0.00044566708769466155, 'samples': 17229824, 'steps': 33651, 'loss/train': 2.1446759700775146}
-03/05/2022 05:00:44 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/05/2022 05:00:50 - INFO - codeparrot_training - Step 33652: {'lr': 0.00044566378452617363, 'samples': 17230336, 'steps': 33652, 'loss/train': 1.5498212575912476}
-03/05/2022 05:00:53 - INFO - codeparrot_training - Step 33653: {'lr': 0.0004456604812695226, 'samples': 17230848, 'steps': 33653, 'loss/train': 1.553038239479065}
-03/05/2022 05:00:53 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/05/2022 05:00:58 - INFO - codeparrot_training - Step 33654: {'lr': 0.0004456571779247099, 'samples': 17231360, 'steps': 33654, 'loss/train': 2.5553789138793945}
-03/05/2022 05:01:01 - INFO - codeparrot_training - Step 33655: {'lr': 0.0004456538744917372, 'samples': 17231872, 'steps': 33655, 'loss/train': 1.6805498600006104}
-03/05/2022 05:01:01 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/05/2022 05:01:07 - INFO - codeparrot_training - Step 33656: {'lr': 0.0004456505709706059, 'samples': 17232384, 'steps': 33656, 'loss/train': 1.2175822257995605}
-03/05/2022 05:01:10 - INFO - codeparrot_training - Step 33657: {'lr': 0.0004456472673613174, 'samples': 17232896, 'steps': 33657, 'loss/train': 1.2269105911254883}
-03/05/2022 05:01:10 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/05/2022 05:01:15 - INFO - codeparrot_training - Step 33658: {'lr': 0.00044564396366387327, 'samples': 17233408, 'steps': 33658, 'loss/train': 1.058402180671692}
-03/05/2022 05:01:18 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/05/2022 05:01:20 - INFO - codeparrot_training - Step 33659: {'lr': 0.000445640659878275, 'samples': 17233920, 'steps': 33659, 'loss/train': 1.510990858078003}
-03/05/2022 05:01:24 - INFO - codeparrot_training - Step 33660: {'lr': 0.00044563735600452407, 'samples': 17234432, 'steps': 33660, 'loss/train': 1.5986733436584473}
-03/05/2022 05:01:26 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/05/2022 05:01:29 - INFO - codeparrot_training - Step 33661: {'lr': 0.000445634052042622, 'samples': 17234944, 'steps': 33661, 'loss/train': 2.0537829399108887}
-03/05/2022 05:01:32 - INFO - codeparrot_training - Step 33662: {'lr': 0.00044563074799257015, 'samples': 17235456, 'steps': 33662, 'loss/train': 1.6863192319869995}
-03/05/2022 05:01:35 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/05/2022 05:01:38 - INFO - codeparrot_training - Step 33663: {'lr': 0.0004456274438543702, 'samples': 17235968, 'steps': 33663, 'loss/train': 1.6375967264175415}
-03/05/2022 05:01:41 - INFO - codeparrot_training - Step 33664: {'lr': 0.0004456241396280234, 'samples': 17236480, 'steps': 33664, 'loss/train': 1.3035353422164917}
-03/05/2022 05:01:43 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/05/2022 05:01:46 - INFO - codeparrot_training - Step 33665: {'lr': 0.00044562083531353154, 'samples': 17236992, 'steps': 33665, 'loss/train': 1.5329054594039917}
-03/05/2022 05:01:49 - INFO - codeparrot_training - Step 33666: {'lr': 0.00044561753091089585, 'samples': 17237504, 'steps': 33666, 'loss/train': 1.654770016670227}
-03/05/2022 05:01:52 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/05/2022 05:01:55 - INFO - codeparrot_training - Step 33667: {'lr': 0.00044561422642011794, 'samples': 17238016, 'steps': 33667, 'loss/train': 1.2918373346328735}
-03/05/2022 05:01:58 - INFO - codeparrot_training - Step 33668: {'lr': 0.00044561092184119933, 'samples': 17238528, 'steps': 33668, 'loss/train': 2.4394679069519043}
-03/05/2022 05:02:01 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/05/2022 05:02:03 - INFO - codeparrot_training - Step 33669: {'lr': 0.00044560761717414143, 'samples': 17239040, 'steps': 33669, 'loss/train': 1.4597721099853516}
-03/05/2022 05:02:06 - INFO - codeparrot_training - Step 33670: {'lr': 0.0004456043124189458, 'samples': 17239552, 'steps': 33670, 'loss/train': 2.2803752422332764}
-03/05/2022 05:02:09 - INFO - codeparrot_training - Step 33671: {'lr': 0.00044560100757561386, 'samples': 17240064, 'steps': 33671, 'loss/train': 1.3685790300369263}
-03/05/2022 05:02:09 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/05/2022 05:02:15 - INFO - codeparrot_training - Step 33672: {'lr': 0.000445597702644147, 'samples': 17240576, 'steps': 33672, 'loss/train': 2.761289596557617}
-03/05/2022 05:02:18 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/05/2022 05:02:20 - INFO - codeparrot_training - Step 33673: {'lr': 0.000445594397624547, 'samples': 17241088, 'steps': 33673, 'loss/train': 0.3266843855381012}
-03/05/2022 05:02:23 - INFO - codeparrot_training - Step 33674: {'lr': 0.0004455910925168151, 'samples': 17241600, 'steps': 33674, 'loss/train': 2.0801889896392822}
-03/05/2022 05:02:26 - INFO - codeparrot_training - Step 33675: {'lr': 0.0004455877873209529, 'samples': 17242112, 'steps': 33675, 'loss/train': 1.4737094640731812}
-03/05/2022 05:02:26 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/05/2022 05:02:32 - INFO - codeparrot_training - Step 33676: {'lr': 0.00044558448203696184, 'samples': 17242624, 'steps': 33676, 'loss/train': 1.157250165939331}
-03/05/2022 05:02:35 - INFO - codeparrot_training - Step 33677: {'lr': 0.0004455811766648434, 'samples': 17243136, 'steps': 33677, 'loss/train': 1.2672345638275146}
-03/05/2022 05:02:35 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 05:02:40 - INFO - codeparrot_training - Step 33678: {'lr': 0.0004455778712045992, 'samples': 17243648, 'steps': 33678, 'loss/train': 1.787611722946167}
-03/05/2022 05:02:44 - INFO - codeparrot_training - Step 33679: {'lr': 0.0004455745656562306, 'samples': 17244160, 'steps': 33679, 'loss/train': 1.708083152770996}
-03/05/2022 05:02:44 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/05/2022 05:02:49 - INFO - codeparrot_training - Step 33680: {'lr': 0.000445571260019739, 'samples': 17244672, 'steps': 33680, 'loss/train': 1.9811404943466187}
-03/05/2022 05:02:52 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/05/2022 05:02:54 - INFO - codeparrot_training - Step 33681: {'lr': 0.00044556795429512617, 'samples': 17245184, 'steps': 33681, 'loss/train': 1.4627286195755005}
-03/05/2022 05:02:57 - INFO - codeparrot_training - Step 33682: {'lr': 0.0004455646484823933, 'samples': 17245696, 'steps': 33682, 'loss/train': 1.8636199235916138}
-03/05/2022 05:03:00 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/05/2022 05:03:03 - INFO - codeparrot_training - Step 33683: {'lr': 0.00044556134258154215, 'samples': 17246208, 'steps': 33683, 'loss/train': 1.9720185995101929}
-03/05/2022 05:03:06 - INFO - codeparrot_training - Step 33684: {'lr': 0.000445558036592574, 'samples': 17246720, 'steps': 33684, 'loss/train': 1.9168349504470825}
-03/05/2022 05:03:09 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/05/2022 05:03:11 - INFO - codeparrot_training - Step 33685: {'lr': 0.0004455547305154904, 'samples': 17247232, 'steps': 33685, 'loss/train': 1.6605573892593384}
-03/05/2022 05:03:14 - INFO - codeparrot_training - Step 33686: {'lr': 0.00044555142435029284, 'samples': 17247744, 'steps': 33686, 'loss/train': 1.5331995487213135}
-03/05/2022 05:03:17 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/05/2022 05:03:19 - INFO - codeparrot_training - Step 33687: {'lr': 0.0004455481180969829, 'samples': 17248256, 'steps': 33687, 'loss/train': 1.9314182996749878}
-03/05/2022 05:03:23 - INFO - codeparrot_training - Step 33688: {'lr': 0.00044554481175556194, 'samples': 17248768, 'steps': 33688, 'loss/train': 1.829451084136963}
-03/05/2022 05:03:25 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/05/2022 05:03:28 - INFO - codeparrot_training - Step 33689: {'lr': 0.00044554150532603154, 'samples': 17249280, 'steps': 33689, 'loss/train': 1.144074559211731}
-03/05/2022 05:03:31 - INFO - codeparrot_training - Step 33690: {'lr': 0.00044553819880839313, 'samples': 17249792, 'steps': 33690, 'loss/train': 0.22657983005046844}
-03/05/2022 05:03:34 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/05/2022 05:03:36 - INFO - codeparrot_training - Step 33691: {'lr': 0.0004455348922026483, 'samples': 17250304, 'steps': 33691, 'loss/train': 1.9718066453933716}
-03/05/2022 05:03:40 - INFO - codeparrot_training - Step 33692: {'lr': 0.00044553158550879833, 'samples': 17250816, 'steps': 33692, 'loss/train': 1.3945564031600952}
-03/05/2022 05:03:42 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 05:03:45 - INFO - codeparrot_training - Step 33693: {'lr': 0.00044552827872684493, 'samples': 17251328, 'steps': 33693, 'loss/train': 1.8999449014663696}
-03/05/2022 05:03:48 - INFO - codeparrot_training - Step 33694: {'lr': 0.00044552497185678953, 'samples': 17251840, 'steps': 33694, 'loss/train': 1.8301559686660767}
-03/05/2022 05:03:51 - INFO - codeparrot_training - Step 33695: {'lr': 0.00044552166489863354, 'samples': 17252352, 'steps': 33695, 'loss/train': 1.7804909944534302}
-03/05/2022 05:03:52 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/05/2022 05:03:57 - INFO - codeparrot_training - Step 33696: {'lr': 0.0004455183578523785, 'samples': 17252864, 'steps': 33696, 'loss/train': 2.107941150665283}
-03/05/2022 05:04:00 - INFO - codeparrot_training - Step 33697: {'lr': 0.00044551505071802587, 'samples': 17253376, 'steps': 33697, 'loss/train': 1.8297739028930664}
-03/05/2022 05:04:00 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/05/2022 05:04:05 - INFO - codeparrot_training - Step 33698: {'lr': 0.00044551174349557733, 'samples': 17253888, 'steps': 33698, 'loss/train': 1.0970057249069214}
-03/05/2022 05:04:08 - INFO - codeparrot_training - Step 33699: {'lr': 0.0004455084361850341, 'samples': 17254400, 'steps': 33699, 'loss/train': 1.9417939186096191}
-03/05/2022 05:04:09 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 05:04:14 - INFO - codeparrot_training - Step 33700: {'lr': 0.00044550512878639784, 'samples': 17254912, 'steps': 33700, 'loss/train': 1.7972487211227417}
-03/05/2022 05:04:17 - INFO - codeparrot_training - Step 33701: {'lr': 0.0004455018212996699, 'samples': 17255424, 'steps': 33701, 'loss/train': 2.2850606441497803}
-03/05/2022 05:04:17 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/05/2022 05:04:22 - INFO - codeparrot_training - Step 33702: {'lr': 0.0004454985137248519, 'samples': 17255936, 'steps': 33702, 'loss/train': 1.8021314144134521}
-03/05/2022 05:04:25 - INFO - codeparrot_training - Step 33703: {'lr': 0.00044549520606194525, 'samples': 17256448, 'steps': 33703, 'loss/train': 1.2692856788635254}
-03/05/2022 05:04:25 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/05/2022 05:04:31 - INFO - codeparrot_training - Step 33704: {'lr': 0.00044549189831095157, 'samples': 17256960, 'steps': 33704, 'loss/train': 1.375137209892273}
-03/05/2022 05:04:34 - INFO - codeparrot_training - Step 33705: {'lr': 0.0004454885904718722, 'samples': 17257472, 'steps': 33705, 'loss/train': 1.8190932273864746}
-03/05/2022 05:04:34 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/05/2022 05:04:39 - INFO - codeparrot_training - Step 33706: {'lr': 0.0004454852825447087, 'samples': 17257984, 'steps': 33706, 'loss/train': 1.2892558574676514}
-03/05/2022 05:04:42 - INFO - codeparrot_training - Step 33707: {'lr': 0.0004454819745294625, 'samples': 17258496, 'steps': 33707, 'loss/train': 1.6673616170883179}
-03/05/2022 05:04:42 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/05/2022 05:04:47 - INFO - codeparrot_training - Step 33708: {'lr': 0.0004454786664261352, 'samples': 17259008, 'steps': 33708, 'loss/train': 2.1652064323425293}
-03/05/2022 05:04:51 - INFO - codeparrot_training - Step 33709: {'lr': 0.0004454753582347282, 'samples': 17259520, 'steps': 33709, 'loss/train': 2.2581276893615723}
-03/05/2022 05:04:51 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/05/2022 05:04:56 - INFO - codeparrot_training - Step 33710: {'lr': 0.00044547204995524305, 'samples': 17260032, 'steps': 33710, 'loss/train': 1.7837741374969482}
-03/05/2022 05:04:59 - INFO - codeparrot_training - Step 33711: {'lr': 0.00044546874158768115, 'samples': 17260544, 'steps': 33711, 'loss/train': 0.9483580589294434}
-03/05/2022 05:05:00 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 05:05:05 - INFO - codeparrot_training - Step 33712: {'lr': 0.00044546543313204415, 'samples': 17261056, 'steps': 33712, 'loss/train': 1.9283761978149414}
-03/05/2022 05:05:08 - INFO - codeparrot_training - Step 33713: {'lr': 0.00044546212458833334, 'samples': 17261568, 'steps': 33713, 'loss/train': 0.5830368995666504}
-03/05/2022 05:05:08 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/05/2022 05:05:13 - INFO - codeparrot_training - Step 33714: {'lr': 0.00044545881595655035, 'samples': 17262080, 'steps': 33714, 'loss/train': 1.3765771389007568}
-03/05/2022 05:05:16 - INFO - codeparrot_training - Step 33715: {'lr': 0.00044545550723669664, 'samples': 17262592, 'steps': 33715, 'loss/train': 1.6600160598754883}
-03/05/2022 05:05:17 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/05/2022 05:05:22 - INFO - codeparrot_training - Step 33716: {'lr': 0.00044545219842877373, 'samples': 17263104, 'steps': 33716, 'loss/train': 1.7852420806884766}
-03/05/2022 05:05:25 - INFO - codeparrot_training - Step 33717: {'lr': 0.000445448889532783, 'samples': 17263616, 'steps': 33717, 'loss/train': 1.0261931419372559}
-03/05/2022 05:05:26 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/05/2022 05:05:30 - INFO - codeparrot_training - Step 33718: {'lr': 0.0004454455805487261, 'samples': 17264128, 'steps': 33718, 'loss/train': 1.9580744504928589}
-03/05/2022 05:05:33 - INFO - codeparrot_training - Step 33719: {'lr': 0.0004454422714766043, 'samples': 17264640, 'steps': 33719, 'loss/train': 0.932378888130188}
-03/05/2022 05:05:34 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 05:05:39 - INFO - codeparrot_training - Step 33720: {'lr': 0.00044543896231641935, 'samples': 17265152, 'steps': 33720, 'loss/train': 1.8244143724441528}
-03/05/2022 05:05:42 - INFO - codeparrot_training - Step 33721: {'lr': 0.00044543565306817256, 'samples': 17265664, 'steps': 33721, 'loss/train': 1.4012575149536133}
-03/05/2022 05:05:42 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/05/2022 05:05:47 - INFO - codeparrot_training - Step 33722: {'lr': 0.00044543234373186556, 'samples': 17266176, 'steps': 33722, 'loss/train': 1.9865909814834595}
-03/05/2022 05:05:50 - INFO - codeparrot_training - Step 33723: {'lr': 0.0004454290343074997, 'samples': 17266688, 'steps': 33723, 'loss/train': 1.8939869403839111}
-03/05/2022 05:05:51 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/05/2022 05:05:56 - INFO - codeparrot_training - Step 33724: {'lr': 0.00044542572479507655, 'samples': 17267200, 'steps': 33724, 'loss/train': 1.3141834735870361}
-03/05/2022 05:05:59 - INFO - codeparrot_training - Step 33725: {'lr': 0.00044542241519459757, 'samples': 17267712, 'steps': 33725, 'loss/train': 0.9781323075294495}
-03/05/2022 05:05:59 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/05/2022 05:06:04 - INFO - codeparrot_training - Step 33726: {'lr': 0.0004454191055060643, 'samples': 17268224, 'steps': 33726, 'loss/train': 0.10506538301706314}
-03/05/2022 05:06:07 - INFO - codeparrot_training - Step 33727: {'lr': 0.00044541579572947814, 'samples': 17268736, 'steps': 33727, 'loss/train': 0.9335793852806091}
-03/05/2022 05:06:07 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/05/2022 05:06:12 - INFO - codeparrot_training - Step 33728: {'lr': 0.0004454124858648407, 'samples': 17269248, 'steps': 33728, 'loss/train': 2.2470526695251465}
-03/05/2022 05:06:15 - INFO - codeparrot_training - Step 33729: {'lr': 0.00044540917591215335, 'samples': 17269760, 'steps': 33729, 'loss/train': 2.5497844219207764}
-03/05/2022 05:06:16 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/05/2022 05:06:21 - INFO - codeparrot_training - Step 33730: {'lr': 0.0004454058658714177, 'samples': 17270272, 'steps': 33730, 'loss/train': 1.4950462579727173}
-03/05/2022 05:06:24 - INFO - codeparrot_training - Step 33731: {'lr': 0.0004454025557426351, 'samples': 17270784, 'steps': 33731, 'loss/train': 1.3171472549438477}
-03/05/2022 05:06:24 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/05/2022 05:06:29 - INFO - codeparrot_training - Step 33732: {'lr': 0.00044539924552580723, 'samples': 17271296, 'steps': 33732, 'loss/train': 1.650871992111206}
-03/05/2022 05:06:32 - INFO - codeparrot_training - Step 33733: {'lr': 0.0004453959352209354, 'samples': 17271808, 'steps': 33733, 'loss/train': 2.8467471599578857}
-03/05/2022 05:06:33 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/05/2022 05:06:38 - INFO - codeparrot_training - Step 33734: {'lr': 0.0004453926248280212, 'samples': 17272320, 'steps': 33734, 'loss/train': 2.093609571456909}
-03/05/2022 05:06:41 - INFO - codeparrot_training - Step 33735: {'lr': 0.0004453893143470661, 'samples': 17272832, 'steps': 33735, 'loss/train': 1.088821291923523}
-03/05/2022 05:06:41 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/05/2022 05:06:46 - INFO - codeparrot_training - Step 33736: {'lr': 0.0004453860037780716, 'samples': 17273344, 'steps': 33736, 'loss/train': 1.8031758069992065}
-03/05/2022 05:06:49 - INFO - codeparrot_training - Step 33737: {'lr': 0.00044538269312103916, 'samples': 17273856, 'steps': 33737, 'loss/train': 1.9554144144058228}
-03/05/2022 05:06:50 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/05/2022 05:06:55 - INFO - codeparrot_training - Step 33738: {'lr': 0.00044537938237597033, 'samples': 17274368, 'steps': 33738, 'loss/train': 1.7630200386047363}
-03/05/2022 05:06:58 - INFO - codeparrot_training - Step 33739: {'lr': 0.00044537607154286645, 'samples': 17274880, 'steps': 33739, 'loss/train': 1.7588212490081787}
-03/05/2022 05:06:58 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/05/2022 05:07:03 - INFO - codeparrot_training - Step 33740: {'lr': 0.00044537276062172926, 'samples': 17275392, 'steps': 33740, 'loss/train': 0.8729655742645264}
-03/05/2022 05:07:06 - INFO - codeparrot_training - Step 33741: {'lr': 0.0004453694496125601, 'samples': 17275904, 'steps': 33741, 'loss/train': 1.7710518836975098}
-03/05/2022 05:07:07 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/05/2022 05:07:11 - INFO - codeparrot_training - Step 33742: {'lr': 0.0004453661385153604, 'samples': 17276416, 'steps': 33742, 'loss/train': 1.3548460006713867}
-03/05/2022 05:07:15 - INFO - codeparrot_training - Step 33743: {'lr': 0.0004453628273301318, 'samples': 17276928, 'steps': 33743, 'loss/train': 2.101663112640381}
-03/05/2022 05:07:15 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/05/2022 05:07:20 - INFO - codeparrot_training - Step 33744: {'lr': 0.0004453595160568757, 'samples': 17277440, 'steps': 33744, 'loss/train': 1.1055561304092407}
-03/05/2022 05:07:23 - INFO - codeparrot_training - Step 33745: {'lr': 0.0004453562046955937, 'samples': 17277952, 'steps': 33745, 'loss/train': 1.6239638328552246}
-03/05/2022 05:07:23 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/05/2022 05:07:28 - INFO - codeparrot_training - Step 33746: {'lr': 0.00044535289324628704, 'samples': 17278464, 'steps': 33746, 'loss/train': 1.0564157962799072}
-03/05/2022 05:07:31 - INFO - codeparrot_training - Step 33747: {'lr': 0.00044534958170895753, 'samples': 17278976, 'steps': 33747, 'loss/train': 2.8480093479156494}
-03/05/2022 05:07:31 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 05:07:37 - INFO - codeparrot_training - Step 33748: {'lr': 0.0004453462700836064, 'samples': 17279488, 'steps': 33748, 'loss/train': 1.6007373332977295}
-03/05/2022 05:07:39 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 05:07:42 - INFO - codeparrot_training - Step 33749: {'lr': 0.0004453429583702353, 'samples': 17280000, 'steps': 33749, 'loss/train': 1.042931079864502}
-03/05/2022 05:07:45 - INFO - codeparrot_training - Step 33750: {'lr': 0.0004453396465688457, 'samples': 17280512, 'steps': 33750, 'loss/train': 1.9030508995056152}
-03/05/2022 05:07:48 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/05/2022 05:07:50 - INFO - codeparrot_training - Step 33751: {'lr': 0.00044533633467943906, 'samples': 17281024, 'steps': 33751, 'loss/train': 1.9037073850631714}
-03/05/2022 05:07:53 - INFO - codeparrot_training - Step 33752: {'lr': 0.00044533302270201693, 'samples': 17281536, 'steps': 33752, 'loss/train': 2.302919387817383}
-03/05/2022 05:07:56 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/05/2022 05:07:59 - INFO - codeparrot_training - Step 33753: {'lr': 0.00044532971063658067, 'samples': 17282048, 'steps': 33753, 'loss/train': 0.705392599105835}
-03/05/2022 05:08:02 - INFO - codeparrot_training - Step 33754: {'lr': 0.00044532639848313187, 'samples': 17282560, 'steps': 33754, 'loss/train': 1.4967677593231201}
-03/05/2022 05:08:05 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 05:08:07 - INFO - codeparrot_training - Step 33755: {'lr': 0.0004453230862416721, 'samples': 17283072, 'steps': 33755, 'loss/train': 2.220360040664673}
-03/05/2022 05:08:10 - INFO - codeparrot_training - Step 33756: {'lr': 0.00044531977391220267, 'samples': 17283584, 'steps': 33756, 'loss/train': 2.1588869094848633}
-03/05/2022 05:08:13 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/05/2022 05:08:16 - INFO - codeparrot_training - Step 33757: {'lr': 0.00044531646149472516, 'samples': 17284096, 'steps': 33757, 'loss/train': 1.6332528591156006}
-03/05/2022 05:08:19 - INFO - codeparrot_training - Step 33758: {'lr': 0.00044531314898924116, 'samples': 17284608, 'steps': 33758, 'loss/train': 1.7397618293762207}
-03/05/2022 05:08:22 - INFO - codeparrot_training - Step 33759: {'lr': 0.00044530983639575193, 'samples': 17285120, 'steps': 33759, 'loss/train': 1.399461030960083}
-03/05/2022 05:08:22 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/05/2022 05:08:27 - INFO - codeparrot_training - Step 33760: {'lr': 0.00044530652371425916, 'samples': 17285632, 'steps': 33760, 'loss/train': 2.4070591926574707}
-03/05/2022 05:08:30 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/05/2022 05:08:33 - INFO - codeparrot_training - Step 33761: {'lr': 0.00044530321094476434, 'samples': 17286144, 'steps': 33761, 'loss/train': 1.8661472797393799}
-03/05/2022 05:08:36 - INFO - codeparrot_training - Step 33762: {'lr': 0.0004452998980872689, 'samples': 17286656, 'steps': 33762, 'loss/train': 1.3632087707519531}
-03/05/2022 05:08:39 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/05/2022 05:08:41 - INFO - codeparrot_training - Step 33763: {'lr': 0.0004452965851417743, 'samples': 17287168, 'steps': 33763, 'loss/train': 2.6672725677490234}
-03/05/2022 05:08:44 - INFO - codeparrot_training - Step 33764: {'lr': 0.000445293272108282, 'samples': 17287680, 'steps': 33764, 'loss/train': 0.23788543045520782}
-03/05/2022 05:08:47 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/05/2022 05:08:50 - INFO - codeparrot_training - Step 33765: {'lr': 0.0004452899589867937, 'samples': 17288192, 'steps': 33765, 'loss/train': 1.3549383878707886}
-03/05/2022 05:08:53 - INFO - codeparrot_training - Step 33766: {'lr': 0.00044528664577731073, 'samples': 17288704, 'steps': 33766, 'loss/train': 1.8650872707366943}
-03/05/2022 05:08:55 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/05/2022 05:08:58 - INFO - codeparrot_training - Step 33767: {'lr': 0.00044528333247983456, 'samples': 17289216, 'steps': 33767, 'loss/train': 1.3714998960494995}
-03/05/2022 05:09:01 - INFO - codeparrot_training - Step 33768: {'lr': 0.0004452800190943667, 'samples': 17289728, 'steps': 33768, 'loss/train': 1.5167347192764282}
-03/05/2022 05:09:04 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/05/2022 05:09:07 - INFO - codeparrot_training - Step 33769: {'lr': 0.0004452767056209087, 'samples': 17290240, 'steps': 33769, 'loss/train': 1.6627153158187866}
-03/05/2022 05:09:10 - INFO - codeparrot_training - Step 33770: {'lr': 0.0004452733920594621, 'samples': 17290752, 'steps': 33770, 'loss/train': 1.0002191066741943}
-03/05/2022 05:09:13 - INFO - codeparrot_training - Step 33771: {'lr': 0.0004452700784100283, 'samples': 17291264, 'steps': 33771, 'loss/train': 0.8183153867721558}
-03/05/2022 05:09:15 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/05/2022 05:09:19 - INFO - codeparrot_training - Step 33772: {'lr': 0.0004452667646726088, 'samples': 17291776, 'steps': 33772, 'loss/train': 0.31996601819992065}
-03/05/2022 05:09:22 - INFO - codeparrot_training - Step 33773: {'lr': 0.0004452634508472051, 'samples': 17292288, 'steps': 33773, 'loss/train': 2.0209522247314453}
-03/05/2022 05:09:23 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/05/2022 05:09:27 - INFO - codeparrot_training - Step 33774: {'lr': 0.0004452601369338187, 'samples': 17292800, 'steps': 33774, 'loss/train': 1.5735650062561035}
-03/05/2022 05:09:30 - INFO - codeparrot_training - Step 33775: {'lr': 0.00044525682293245107, 'samples': 17293312, 'steps': 33775, 'loss/train': 2.001319169998169}
-03/05/2022 05:09:32 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/05/2022 05:09:36 - INFO - codeparrot_training - Step 33776: {'lr': 0.0004452535088431038, 'samples': 17293824, 'steps': 33776, 'loss/train': 1.1613801717758179}
-03/05/2022 05:09:39 - INFO - codeparrot_training - Step 33777: {'lr': 0.00044525019466577824, 'samples': 17294336, 'steps': 33777, 'loss/train': 1.7528420686721802}
-03/05/2022 05:09:40 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/05/2022 05:09:44 - INFO - codeparrot_training - Step 33778: {'lr': 0.000445246880400476, 'samples': 17294848, 'steps': 33778, 'loss/train': 2.7505130767822266}
-03/05/2022 05:09:47 - INFO - codeparrot_training - Step 33779: {'lr': 0.0004452435660471985, 'samples': 17295360, 'steps': 33779, 'loss/train': 1.506622076034546}
-03/05/2022 05:09:49 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 05:09:53 - INFO - codeparrot_training - Step 33780: {'lr': 0.00044524025160594735, 'samples': 17295872, 'steps': 33780, 'loss/train': 2.2383944988250732}
-03/05/2022 05:09:56 - INFO - codeparrot_training - Step 33781: {'lr': 0.00044523693707672384, 'samples': 17296384, 'steps': 33781, 'loss/train': 1.7786693572998047}
-03/05/2022 05:09:57 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/05/2022 05:10:01 - INFO - codeparrot_training - Step 33782: {'lr': 0.0004452336224595296, 'samples': 17296896, 'steps': 33782, 'loss/train': 1.6716578006744385}
-03/05/2022 05:10:04 - INFO - codeparrot_training - Step 33783: {'lr': 0.00044523030775436617, 'samples': 17297408, 'steps': 33783, 'loss/train': 1.7751421928405762}
-03/05/2022 05:10:06 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/05/2022 05:10:09 - INFO - codeparrot_training - Step 33784: {'lr': 0.00044522699296123495, 'samples': 17297920, 'steps': 33784, 'loss/train': 2.1053643226623535}
-03/05/2022 05:10:12 - INFO - codeparrot_training - Step 33785: {'lr': 0.0004452236780801374, 'samples': 17298432, 'steps': 33785, 'loss/train': 1.61186945438385}
-03/05/2022 05:10:14 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/05/2022 05:10:18 - INFO - codeparrot_training - Step 33786: {'lr': 0.00044522036311107514, 'samples': 17298944, 'steps': 33786, 'loss/train': 1.1602447032928467}
-03/05/2022 05:10:21 - INFO - codeparrot_training - Step 33787: {'lr': 0.0004452170480540496, 'samples': 17299456, 'steps': 33787, 'loss/train': 1.4661749601364136}
-03/05/2022 05:10:22 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/05/2022 05:10:26 - INFO - codeparrot_training - Step 33788: {'lr': 0.0004452137329090622, 'samples': 17299968, 'steps': 33788, 'loss/train': 1.896278738975525}
-03/05/2022 05:10:29 - INFO - codeparrot_training - Step 33789: {'lr': 0.0004452104176761146, 'samples': 17300480, 'steps': 33789, 'loss/train': 1.8350512981414795}
-03/05/2022 05:10:30 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/05/2022 05:10:34 - INFO - codeparrot_training - Step 33790: {'lr': 0.0004452071023552081, 'samples': 17300992, 'steps': 33790, 'loss/train': 1.6936326026916504}
-03/05/2022 05:10:38 - INFO - codeparrot_training - Step 33791: {'lr': 0.0004452037869463443, 'samples': 17301504, 'steps': 33791, 'loss/train': 0.8472153544425964}
-03/05/2022 05:10:39 - INFO - codeparrot_training - Skipping example with length 5 (seq_length=1024)
-03/05/2022 05:10:43 - INFO - codeparrot_training - Step 33792: {'lr': 0.0004452004714495248, 'samples': 17302016, 'steps': 33792, 'loss/train': 1.3669425249099731}
-03/05/2022 05:10:46 - INFO - codeparrot_training - Step 33793: {'lr': 0.00044519715586475083, 'samples': 17302528, 'steps': 33793, 'loss/train': 1.0535948276519775}
-03/05/2022 05:10:47 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/05/2022 05:10:51 - INFO - codeparrot_training - Step 33794: {'lr': 0.0004451938401920241, 'samples': 17303040, 'steps': 33794, 'loss/train': 2.0635149478912354}
-03/05/2022 05:10:54 - INFO - codeparrot_training - Step 33795: {'lr': 0.0004451905244313461, 'samples': 17303552, 'steps': 33795, 'loss/train': 2.5287692546844482}
-03/05/2022 05:10:55 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/05/2022 05:11:00 - INFO - codeparrot_training - Step 33796: {'lr': 0.0004451872085827182, 'samples': 17304064, 'steps': 33796, 'loss/train': 2.070211410522461}
-03/05/2022 05:11:03 - INFO - codeparrot_training - Step 33797: {'lr': 0.000445183892646142, 'samples': 17304576, 'steps': 33797, 'loss/train': 1.8657327890396118}
-03/05/2022 05:11:03 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 05:11:08 - INFO - codeparrot_training - Step 33798: {'lr': 0.0004451805766216189, 'samples': 17305088, 'steps': 33798, 'loss/train': 1.003869891166687}
-03/05/2022 05:11:11 - INFO - codeparrot_training - Step 33799: {'lr': 0.00044517726050915044, 'samples': 17305600, 'steps': 33799, 'loss/train': 1.5238442420959473}
-03/05/2022 05:11:12 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/05/2022 05:11:16 - INFO - codeparrot_training - Step 33800: {'lr': 0.0004451739443087381, 'samples': 17306112, 'steps': 33800, 'loss/train': 2.31925630569458}
-03/05/2022 05:11:20 - INFO - codeparrot_training - Step 33801: {'lr': 0.0004451706280203834, 'samples': 17306624, 'steps': 33801, 'loss/train': 1.0048564672470093}
-03/05/2022 05:11:20 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/05/2022 05:11:25 - INFO - codeparrot_training - Step 33802: {'lr': 0.0004451673116440879, 'samples': 17307136, 'steps': 33802, 'loss/train': 1.9859715700149536}
-03/05/2022 05:11:28 - INFO - codeparrot_training - Step 33803: {'lr': 0.00044516399517985296, 'samples': 17307648, 'steps': 33803, 'loss/train': 1.88052237033844}
-03/05/2022 05:11:28 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/05/2022 05:11:33 - INFO - codeparrot_training - Step 33804: {'lr': 0.00044516067862768015, 'samples': 17308160, 'steps': 33804, 'loss/train': 1.3802179098129272}
-03/05/2022 05:11:37 - INFO - codeparrot_training - Step 33805: {'lr': 0.00044515736198757095, 'samples': 17308672, 'steps': 33805, 'loss/train': 1.5742433071136475}
-03/05/2022 05:11:37 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/05/2022 05:11:42 - INFO - codeparrot_training - Step 33806: {'lr': 0.0004451540452595268, 'samples': 17309184, 'steps': 33806, 'loss/train': 1.2189489603042603}
-03/05/2022 05:11:45 - INFO - codeparrot_training - Step 33807: {'lr': 0.0004451507284435494, 'samples': 17309696, 'steps': 33807, 'loss/train': 1.7029753923416138}
-03/05/2022 05:11:45 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/05/2022 05:11:50 - INFO - codeparrot_training - Step 33808: {'lr': 0.00044514741153964, 'samples': 17310208, 'steps': 33808, 'loss/train': 2.2779147624969482}
-03/05/2022 05:11:54 - INFO - codeparrot_training - Step 33809: {'lr': 0.00044514409454780016, 'samples': 17310720, 'steps': 33809, 'loss/train': 1.4496430158615112}
-03/05/2022 05:11:54 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/05/2022 05:11:59 - INFO - codeparrot_training - Step 33810: {'lr': 0.0004451407774680314, 'samples': 17311232, 'steps': 33810, 'loss/train': 1.0583422183990479}
-03/05/2022 05:12:02 - INFO - codeparrot_training - Step 33811: {'lr': 0.0004451374603003353, 'samples': 17311744, 'steps': 33811, 'loss/train': 1.4394686222076416}
-03/05/2022 05:12:02 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/05/2022 05:12:08 - INFO - codeparrot_training - Step 33812: {'lr': 0.0004451341430447132, 'samples': 17312256, 'steps': 33812, 'loss/train': 1.8045791387557983}
-03/05/2022 05:12:11 - INFO - codeparrot_training - Step 33813: {'lr': 0.0004451308257011667, 'samples': 17312768, 'steps': 33813, 'loss/train': 1.6149893999099731}
-03/05/2022 05:12:11 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/05/2022 05:12:16 - INFO - codeparrot_training - Step 33814: {'lr': 0.00044512750826969724, 'samples': 17313280, 'steps': 33814, 'loss/train': 2.0532898902893066}
-03/05/2022 05:12:19 - INFO - codeparrot_training - Step 33815: {'lr': 0.0004451241907503063, 'samples': 17313792, 'steps': 33815, 'loss/train': 1.2666285037994385}
-03/05/2022 05:12:19 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/05/2022 05:12:24 - INFO - codeparrot_training - Step 33816: {'lr': 0.0004451208731429954, 'samples': 17314304, 'steps': 33816, 'loss/train': 2.2859816551208496}
-03/05/2022 05:12:28 - INFO - codeparrot_training - Step 33817: {'lr': 0.00044511755544776615, 'samples': 17314816, 'steps': 33817, 'loss/train': 2.349276304244995}
-03/05/2022 05:12:28 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/05/2022 05:12:33 - INFO - codeparrot_training - Step 33818: {'lr': 0.0004451142376646199, 'samples': 17315328, 'steps': 33818, 'loss/train': 1.9633797407150269}
-03/05/2022 05:12:36 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/05/2022 05:12:38 - INFO - codeparrot_training - Step 33819: {'lr': 0.0004451109197935582, 'samples': 17315840, 'steps': 33819, 'loss/train': 1.80086350440979}
-03/05/2022 05:12:41 - INFO - codeparrot_training - Step 33820: {'lr': 0.0004451076018345824, 'samples': 17316352, 'steps': 33820, 'loss/train': 2.1896166801452637}
-03/05/2022 05:12:45 - INFO - codeparrot_training - Step 33821: {'lr': 0.0004451042837876943, 'samples': 17316864, 'steps': 33821, 'loss/train': 1.811818242073059}
-03/05/2022 05:12:45 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/05/2022 05:12:50 - INFO - codeparrot_training - Step 33822: {'lr': 0.00044510096565289513, 'samples': 17317376, 'steps': 33822, 'loss/train': 2.7449123859405518}
-03/05/2022 05:12:53 - INFO - codeparrot_training - Step 33823: {'lr': 0.0004450976474301865, 'samples': 17317888, 'steps': 33823, 'loss/train': 1.874610185623169}
-03/05/2022 05:12:53 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/05/2022 05:12:58 - INFO - codeparrot_training - Step 33824: {'lr': 0.0004450943291195698, 'samples': 17318400, 'steps': 33824, 'loss/train': 1.9042495489120483}
-03/05/2022 05:13:02 - INFO - codeparrot_training - Step 33825: {'lr': 0.0004450910107210467, 'samples': 17318912, 'steps': 33825, 'loss/train': 2.4449896812438965}
-03/05/2022 05:13:02 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/05/2022 05:13:07 - INFO - codeparrot_training - Step 33826: {'lr': 0.00044508769223461863, 'samples': 17319424, 'steps': 33826, 'loss/train': 2.013458251953125}
-03/05/2022 05:13:10 - INFO - codeparrot_training - Step 33827: {'lr': 0.00044508437366028695, 'samples': 17319936, 'steps': 33827, 'loss/train': 0.8128820061683655}
-03/05/2022 05:13:10 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/05/2022 05:13:15 - INFO - codeparrot_training - Step 33828: {'lr': 0.00044508105499805337, 'samples': 17320448, 'steps': 33828, 'loss/train': 1.38637375831604}
-03/05/2022 05:13:18 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/05/2022 05:13:21 - INFO - codeparrot_training - Step 33829: {'lr': 0.0004450777362479192, 'samples': 17320960, 'steps': 33829, 'loss/train': 1.8780635595321655}
-03/05/2022 05:13:24 - INFO - codeparrot_training - Step 33830: {'lr': 0.000445074417409886, 'samples': 17321472, 'steps': 33830, 'loss/train': 2.2296218872070312}
-03/05/2022 05:13:27 - INFO - codeparrot_training - Step 33831: {'lr': 0.0004450710984839553, 'samples': 17321984, 'steps': 33831, 'loss/train': 1.9975776672363281}
-03/05/2022 05:13:27 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/05/2022 05:13:32 - INFO - codeparrot_training - Step 33832: {'lr': 0.00044506777947012863, 'samples': 17322496, 'steps': 33832, 'loss/train': 1.4816038608551025}
-03/05/2022 05:13:36 - INFO - codeparrot_training - Step 33833: {'lr': 0.0004450644603684074, 'samples': 17323008, 'steps': 33833, 'loss/train': 2.418100595474243}
-03/05/2022 05:13:36 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 05:13:41 - INFO - codeparrot_training - Step 33834: {'lr': 0.0004450611411787931, 'samples': 17323520, 'steps': 33834, 'loss/train': 1.075097680091858}
-03/05/2022 05:13:44 - INFO - codeparrot_training - Step 33835: {'lr': 0.0004450578219012873, 'samples': 17324032, 'steps': 33835, 'loss/train': 1.541085958480835}
-03/05/2022 05:13:44 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/05/2022 05:13:49 - INFO - codeparrot_training - Step 33836: {'lr': 0.00044505450253589144, 'samples': 17324544, 'steps': 33836, 'loss/train': 1.6833947896957397}
-03/05/2022 05:13:52 - INFO - codeparrot_training - Step 33837: {'lr': 0.00044505118308260693, 'samples': 17325056, 'steps': 33837, 'loss/train': 2.0897908210754395}
-03/05/2022 05:13:52 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/05/2022 05:13:58 - INFO - codeparrot_training - Step 33838: {'lr': 0.0004450478635414355, 'samples': 17325568, 'steps': 33838, 'loss/train': 1.2983777523040771}
-03/05/2022 05:14:01 - INFO - codeparrot_training - Step 33839: {'lr': 0.0004450445439123785, 'samples': 17326080, 'steps': 33839, 'loss/train': 2.220438241958618}
-03/05/2022 05:14:01 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 05:14:06 - INFO - codeparrot_training - Step 33840: {'lr': 0.0004450412241954374, 'samples': 17326592, 'steps': 33840, 'loss/train': 0.99775230884552}
-03/05/2022 05:14:09 - INFO - codeparrot_training - Step 33841: {'lr': 0.00044503790439061374, 'samples': 17327104, 'steps': 33841, 'loss/train': 1.569477915763855}
-03/05/2022 05:14:09 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/05/2022 05:14:15 - INFO - codeparrot_training - Step 33842: {'lr': 0.000445034584497909, 'samples': 17327616, 'steps': 33842, 'loss/train': 2.365832805633545}
-03/05/2022 05:14:18 - INFO - codeparrot_training - Step 33843: {'lr': 0.00044503126451732474, 'samples': 17328128, 'steps': 33843, 'loss/train': 1.1935734748840332}
-03/05/2022 05:14:18 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/05/2022 05:14:23 - INFO - codeparrot_training - Step 33844: {'lr': 0.00044502794444886234, 'samples': 17328640, 'steps': 33844, 'loss/train': 2.0076255798339844}
-03/05/2022 05:14:26 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 05:14:28 - INFO - codeparrot_training - Step 33845: {'lr': 0.00044502462429252336, 'samples': 17329152, 'steps': 33845, 'loss/train': 2.0417819023132324}
-03/05/2022 05:14:32 - INFO - codeparrot_training - Step 33846: {'lr': 0.0004450213040483093, 'samples': 17329664, 'steps': 33846, 'loss/train': 1.806931972503662}
-03/05/2022 05:14:34 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/05/2022 05:14:37 - INFO - codeparrot_training - Step 33847: {'lr': 0.00044501798371622173, 'samples': 17330176, 'steps': 33847, 'loss/train': 1.3489655256271362}
-03/05/2022 05:14:40 - INFO - codeparrot_training - Step 33848: {'lr': 0.00044501466329626197, 'samples': 17330688, 'steps': 33848, 'loss/train': 1.4489156007766724}
-03/05/2022 05:14:42 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/05/2022 05:14:45 - INFO - codeparrot_training - Step 33849: {'lr': 0.0004450113427884317, 'samples': 17331200, 'steps': 33849, 'loss/train': 1.8033791780471802}
-03/05/2022 05:14:48 - INFO - codeparrot_training - Step 33850: {'lr': 0.00044500802219273224, 'samples': 17331712, 'steps': 33850, 'loss/train': 1.6496083736419678}
-03/05/2022 05:14:51 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/05/2022 05:14:54 - INFO - codeparrot_training - Step 33851: {'lr': 0.00044500470150916514, 'samples': 17332224, 'steps': 33851, 'loss/train': 2.935706377029419}
-03/05/2022 05:14:57 - INFO - codeparrot_training - Step 33852: {'lr': 0.000445001380737732, 'samples': 17332736, 'steps': 33852, 'loss/train': 1.1448179483413696}
-03/05/2022 05:14:59 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/05/2022 05:15:02 - INFO - codeparrot_training - Step 33853: {'lr': 0.0004449980598784343, 'samples': 17333248, 'steps': 33853, 'loss/train': 1.5741881132125854}
-03/05/2022 05:15:06 - INFO - codeparrot_training - Step 33854: {'lr': 0.0004449947389312734, 'samples': 17333760, 'steps': 33854, 'loss/train': 1.3452973365783691}
-03/05/2022 05:15:08 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/05/2022 05:15:11 - INFO - codeparrot_training - Step 33855: {'lr': 0.00044499141789625086, 'samples': 17334272, 'steps': 33855, 'loss/train': 1.4021207094192505}
-03/05/2022 05:15:14 - INFO - codeparrot_training - Step 33856: {'lr': 0.0004449880967733683, 'samples': 17334784, 'steps': 33856, 'loss/train': 2.03263258934021}
-03/05/2022 05:15:17 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/05/2022 05:15:19 - INFO - codeparrot_training - Step 33857: {'lr': 0.0004449847755626271, 'samples': 17335296, 'steps': 33857, 'loss/train': 1.3333001136779785}
-03/05/2022 05:15:22 - INFO - codeparrot_training - Step 33858: {'lr': 0.0004449814542640287, 'samples': 17335808, 'steps': 33858, 'loss/train': 2.0181546211242676}
-03/05/2022 05:15:25 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/05/2022 05:15:28 - INFO - codeparrot_training - Step 33859: {'lr': 0.0004449781328775746, 'samples': 17336320, 'steps': 33859, 'loss/train': 1.504160761833191}
-03/05/2022 05:15:31 - INFO - codeparrot_training - Step 33860: {'lr': 0.0004449748114032665, 'samples': 17336832, 'steps': 33860, 'loss/train': 1.5570697784423828}
-03/05/2022 05:15:33 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/05/2022 05:15:36 - INFO - codeparrot_training - Step 33861: {'lr': 0.00044497148984110567, 'samples': 17337344, 'steps': 33861, 'loss/train': 4.030794620513916}
-03/05/2022 05:15:39 - INFO - codeparrot_training - Step 33862: {'lr': 0.00044496816819109377, 'samples': 17337856, 'steps': 33862, 'loss/train': 1.4438660144805908}
-03/05/2022 05:15:42 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/05/2022 05:15:45 - INFO - codeparrot_training - Step 33863: {'lr': 0.0004449648464532322, 'samples': 17338368, 'steps': 33863, 'loss/train': 0.9434030055999756}
-03/05/2022 05:15:48 - INFO - codeparrot_training - Step 33864: {'lr': 0.0004449615246275225, 'samples': 17338880, 'steps': 33864, 'loss/train': 2.2798163890838623}
-03/05/2022 05:15:50 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/05/2022 05:15:53 - INFO - codeparrot_training - Step 33865: {'lr': 0.000444958202713966, 'samples': 17339392, 'steps': 33865, 'loss/train': 2.1741957664489746}
-03/05/2022 05:15:56 - INFO - codeparrot_training - Step 33866: {'lr': 0.0004449548807125645, 'samples': 17339904, 'steps': 33866, 'loss/train': 1.5737000703811646}
-03/05/2022 05:15:58 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/05/2022 05:16:01 - INFO - codeparrot_training - Step 33867: {'lr': 0.0004449515586233193, 'samples': 17340416, 'steps': 33867, 'loss/train': 1.1860430240631104}
-03/05/2022 05:16:05 - INFO - codeparrot_training - Step 33868: {'lr': 0.0004449482364462319, 'samples': 17340928, 'steps': 33868, 'loss/train': 1.6067126989364624}
-03/05/2022 05:16:07 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/05/2022 05:16:10 - INFO - codeparrot_training - Step 33869: {'lr': 0.0004449449141813039, 'samples': 17341440, 'steps': 33869, 'loss/train': 2.393869400024414}
-03/05/2022 05:16:13 - INFO - codeparrot_training - Step 33870: {'lr': 0.00044494159182853667, 'samples': 17341952, 'steps': 33870, 'loss/train': 1.7750999927520752}
-03/05/2022 05:16:15 - INFO - codeparrot_training - Skipping example with length 983 (seq_length=1024)
-03/05/2022 05:16:18 - INFO - codeparrot_training - Step 33871: {'lr': 0.0004449382693879318, 'samples': 17342464, 'steps': 33871, 'loss/train': 1.7189499139785767}
-03/05/2022 05:16:21 - INFO - codeparrot_training - Step 33872: {'lr': 0.0004449349468594908, 'samples': 17342976, 'steps': 33872, 'loss/train': 2.0160794258117676}
-03/05/2022 05:16:24 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 05:16:27 - INFO - codeparrot_training - Step 33873: {'lr': 0.000444931624243215, 'samples': 17343488, 'steps': 33873, 'loss/train': 1.6569578647613525}
-03/05/2022 05:16:30 - INFO - codeparrot_training - Step 33874: {'lr': 0.0004449283015391061, 'samples': 17344000, 'steps': 33874, 'loss/train': 0.6907163262367249}
-03/05/2022 05:16:33 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/05/2022 05:16:35 - INFO - codeparrot_training - Step 33875: {'lr': 0.0004449249787471655, 'samples': 17344512, 'steps': 33875, 'loss/train': 1.870224118232727}
-03/05/2022 05:16:38 - INFO - codeparrot_training - Step 33876: {'lr': 0.0004449216558673947, 'samples': 17345024, 'steps': 33876, 'loss/train': 1.4474776983261108}
-03/05/2022 05:16:41 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/05/2022 05:16:44 - INFO - codeparrot_training - Step 33877: {'lr': 0.0004449183328997952, 'samples': 17345536, 'steps': 33877, 'loss/train': 1.9273661375045776}
-03/05/2022 05:16:47 - INFO - codeparrot_training - Step 33878: {'lr': 0.0004449150098443685, 'samples': 17346048, 'steps': 33878, 'loss/train': 1.457001805305481}
-03/05/2022 05:16:50 - INFO - codeparrot_training - Step 33879: {'lr': 0.00044491168670111615, 'samples': 17346560, 'steps': 33879, 'loss/train': 1.9852187633514404}
-03/05/2022 05:16:50 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/05/2022 05:16:55 - INFO - codeparrot_training - Step 33880: {'lr': 0.0004449083634700396, 'samples': 17347072, 'steps': 33880, 'loss/train': 1.6012510061264038}
-03/05/2022 05:16:59 - INFO - codeparrot_training - Step 33881: {'lr': 0.00044490504015114033, 'samples': 17347584, 'steps': 33881, 'loss/train': 1.7568929195404053}
-03/05/2022 05:16:59 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/05/2022 05:17:04 - INFO - codeparrot_training - Step 33882: {'lr': 0.0004449017167444198, 'samples': 17348096, 'steps': 33882, 'loss/train': 1.164212942123413}
-03/05/2022 05:17:07 - INFO - codeparrot_training - Step 33883: {'lr': 0.0004448983932498797, 'samples': 17348608, 'steps': 33883, 'loss/train': 1.2414915561676025}
-03/05/2022 05:17:07 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/05/2022 05:17:13 - INFO - codeparrot_training - Step 33884: {'lr': 0.00044489506966752127, 'samples': 17349120, 'steps': 33884, 'loss/train': 2.0429930686950684}
-03/05/2022 05:17:16 - INFO - codeparrot_training - Step 33885: {'lr': 0.00044489174599734614, 'samples': 17349632, 'steps': 33885, 'loss/train': 0.07579810172319412}
-03/05/2022 05:17:16 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/05/2022 05:17:21 - INFO - codeparrot_training - Step 33886: {'lr': 0.0004448884222393559, 'samples': 17350144, 'steps': 33886, 'loss/train': 2.0461721420288086}
-03/05/2022 05:17:24 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/05/2022 05:17:26 - INFO - codeparrot_training - Step 33887: {'lr': 0.00044488509839355183, 'samples': 17350656, 'steps': 33887, 'loss/train': 1.5489851236343384}
-03/05/2022 05:17:30 - INFO - codeparrot_training - Step 33888: {'lr': 0.00044488177445993563, 'samples': 17351168, 'steps': 33888, 'loss/train': 1.3924423456192017}
-03/05/2022 05:17:32 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/05/2022 05:17:35 - INFO - codeparrot_training - Step 33889: {'lr': 0.0004448784504385086, 'samples': 17351680, 'steps': 33889, 'loss/train': 1.1904181241989136}
-03/05/2022 05:17:38 - INFO - codeparrot_training - Step 33890: {'lr': 0.0004448751263292724, 'samples': 17352192, 'steps': 33890, 'loss/train': 2.004229784011841}
-03/05/2022 05:17:40 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/05/2022 05:17:43 - INFO - codeparrot_training - Step 33891: {'lr': 0.0004448718021322285, 'samples': 17352704, 'steps': 33891, 'loss/train': 1.819656252861023}
-03/05/2022 05:17:47 - INFO - codeparrot_training - Step 33892: {'lr': 0.0004448684778473784, 'samples': 17353216, 'steps': 33892, 'loss/train': 1.5756034851074219}
-03/05/2022 05:17:49 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/05/2022 05:17:52 - INFO - codeparrot_training - Step 33893: {'lr': 0.0004448651534747235, 'samples': 17353728, 'steps': 33893, 'loss/train': 1.8945651054382324}
-03/05/2022 05:17:55 - INFO - codeparrot_training - Step 33894: {'lr': 0.0004448618290142654, 'samples': 17354240, 'steps': 33894, 'loss/train': 1.8333640098571777}
-03/05/2022 05:17:58 - INFO - codeparrot_training - Step 33895: {'lr': 0.0004448585044660055, 'samples': 17354752, 'steps': 33895, 'loss/train': 1.2428842782974243}
-03/05/2022 05:17:58 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 05:18:04 - INFO - codeparrot_training - Step 33896: {'lr': 0.0004448551798299455, 'samples': 17355264, 'steps': 33896, 'loss/train': 2.686734199523926}
-03/05/2022 05:18:07 - INFO - codeparrot_training - Step 33897: {'lr': 0.00044485185510608665, 'samples': 17355776, 'steps': 33897, 'loss/train': 0.8780430555343628}
-03/05/2022 05:18:09 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/05/2022 05:18:12 - INFO - codeparrot_training - Step 33898: {'lr': 0.0004448485302944306, 'samples': 17356288, 'steps': 33898, 'loss/train': 1.5389349460601807}
-03/05/2022 05:18:16 - INFO - codeparrot_training - Step 33899: {'lr': 0.0004448452053949789, 'samples': 17356800, 'steps': 33899, 'loss/train': 0.6446228623390198}
-03/05/2022 05:18:16 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/05/2022 05:18:21 - INFO - codeparrot_training - Step 33900: {'lr': 0.0004448418804077328, 'samples': 17357312, 'steps': 33900, 'loss/train': 1.3159321546554565}
-03/05/2022 05:18:24 - INFO - codeparrot_training - Step 33901: {'lr': 0.000444838555332694, 'samples': 17357824, 'steps': 33901, 'loss/train': 1.3943349123001099}
-03/05/2022 05:18:25 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/05/2022 05:18:29 - INFO - codeparrot_training - Step 33902: {'lr': 0.000444835230169864, 'samples': 17358336, 'steps': 33902, 'loss/train': 2.0463690757751465}
-03/05/2022 05:18:32 - INFO - codeparrot_training - Step 33903: {'lr': 0.00044483190491924427, 'samples': 17358848, 'steps': 33903, 'loss/train': 0.8285592198371887}
-03/05/2022 05:18:33 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/05/2022 05:18:38 - INFO - codeparrot_training - Step 33904: {'lr': 0.0004448285795808362, 'samples': 17359360, 'steps': 33904, 'loss/train': 1.7008635997772217}
-03/05/2022 05:18:41 - INFO - codeparrot_training - Step 33905: {'lr': 0.00044482525415464144, 'samples': 17359872, 'steps': 33905, 'loss/train': 1.963705062866211}
-03/05/2022 05:18:41 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/05/2022 05:18:46 - INFO - codeparrot_training - Step 33906: {'lr': 0.0004448219286406614, 'samples': 17360384, 'steps': 33906, 'loss/train': 1.6571139097213745}
-03/05/2022 05:18:49 - INFO - codeparrot_training - Step 33907: {'lr': 0.00044481860303889766, 'samples': 17360896, 'steps': 33907, 'loss/train': 1.851084589958191}
-03/05/2022 05:18:50 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/05/2022 05:18:55 - INFO - codeparrot_training - Step 33908: {'lr': 0.0004448152773493516, 'samples': 17361408, 'steps': 33908, 'loss/train': 1.447405457496643}
-03/05/2022 05:18:58 - INFO - codeparrot_training - Step 33909: {'lr': 0.0004448119515720248, 'samples': 17361920, 'steps': 33909, 'loss/train': 1.2948707342147827}
-03/05/2022 05:18:59 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/05/2022 05:19:03 - INFO - codeparrot_training - Step 33910: {'lr': 0.0004448086257069187, 'samples': 17362432, 'steps': 33910, 'loss/train': 1.6074893474578857}
-03/05/2022 05:19:06 - INFO - codeparrot_training - Step 33911: {'lr': 0.00044480529975403496, 'samples': 17362944, 'steps': 33911, 'loss/train': 1.473939061164856}
-03/05/2022 05:19:08 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/05/2022 05:19:11 - INFO - codeparrot_training - Step 33912: {'lr': 0.00044480197371337484, 'samples': 17363456, 'steps': 33912, 'loss/train': 1.9812458753585815}
-03/05/2022 05:19:15 - INFO - codeparrot_training - Step 33913: {'lr': 0.00044479864758494004, 'samples': 17363968, 'steps': 33913, 'loss/train': 1.9686212539672852}
-03/05/2022 05:19:16 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/05/2022 05:19:20 - INFO - codeparrot_training - Step 33914: {'lr': 0.0004447953213687319, 'samples': 17364480, 'steps': 33914, 'loss/train': 1.6838384866714478}
-03/05/2022 05:19:23 - INFO - codeparrot_training - Step 33915: {'lr': 0.00044479199506475205, 'samples': 17364992, 'steps': 33915, 'loss/train': 1.1965010166168213}
-03/05/2022 05:19:25 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/05/2022 05:19:28 - INFO - codeparrot_training - Step 33916: {'lr': 0.0004447886686730019, 'samples': 17365504, 'steps': 33916, 'loss/train': 0.9995692372322083}
-03/05/2022 05:19:32 - INFO - codeparrot_training - Step 33917: {'lr': 0.00044478534219348297, 'samples': 17366016, 'steps': 33917, 'loss/train': 0.9128006100654602}
-03/05/2022 05:19:33 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/05/2022 05:19:37 - INFO - codeparrot_training - Step 33918: {'lr': 0.0004447820156261968, 'samples': 17366528, 'steps': 33918, 'loss/train': 0.792133092880249}
-03/05/2022 05:19:40 - INFO - codeparrot_training - Step 33919: {'lr': 0.0004447786889711449, 'samples': 17367040, 'steps': 33919, 'loss/train': 1.4905247688293457}
-03/05/2022 05:19:41 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/05/2022 05:19:45 - INFO - codeparrot_training - Step 33920: {'lr': 0.00044477536222832867, 'samples': 17367552, 'steps': 33920, 'loss/train': 1.7355396747589111}
-03/05/2022 05:19:48 - INFO - codeparrot_training - Step 33921: {'lr': 0.0004447720353977497, 'samples': 17368064, 'steps': 33921, 'loss/train': 0.7810866832733154}
-03/05/2022 05:19:50 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/05/2022 05:19:54 - INFO - codeparrot_training - Step 33922: {'lr': 0.0004447687084794094, 'samples': 17368576, 'steps': 33922, 'loss/train': 1.4040842056274414}
-03/05/2022 05:19:57 - INFO - codeparrot_training - Step 33923: {'lr': 0.00044476538147330934, 'samples': 17369088, 'steps': 33923, 'loss/train': 1.759506344795227}
-03/05/2022 05:19:58 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/05/2022 05:20:02 - INFO - codeparrot_training - Step 33924: {'lr': 0.00044476205437945105, 'samples': 17369600, 'steps': 33924, 'loss/train': 1.163450837135315}
-03/05/2022 05:20:05 - INFO - codeparrot_training - Step 33925: {'lr': 0.0004447587271978359, 'samples': 17370112, 'steps': 33925, 'loss/train': 2.066434144973755}
-03/05/2022 05:20:06 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/05/2022 05:20:11 - INFO - codeparrot_training - Step 33926: {'lr': 0.0004447553999284656, 'samples': 17370624, 'steps': 33926, 'loss/train': 0.9701665639877319}
-03/05/2022 05:20:14 - INFO - codeparrot_training - Step 33927: {'lr': 0.00044475207257134143, 'samples': 17371136, 'steps': 33927, 'loss/train': 1.9336720705032349}
-03/05/2022 05:20:15 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/05/2022 05:20:19 - INFO - codeparrot_training - Step 33928: {'lr': 0.000444748745126465, 'samples': 17371648, 'steps': 33928, 'loss/train': 1.7401714324951172}
-03/05/2022 05:20:22 - INFO - codeparrot_training - Step 33929: {'lr': 0.0004447454175938378, 'samples': 17372160, 'steps': 33929, 'loss/train': 1.6509641408920288}
-03/05/2022 05:20:23 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/05/2022 05:20:28 - INFO - codeparrot_training - Step 33930: {'lr': 0.00044474208997346133, 'samples': 17372672, 'steps': 33930, 'loss/train': 1.3041768074035645}
-03/05/2022 05:20:31 - INFO - codeparrot_training - Step 33931: {'lr': 0.00044473876226533703, 'samples': 17373184, 'steps': 33931, 'loss/train': 0.6916566491127014}
-03/05/2022 05:20:32 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/05/2022 05:20:36 - INFO - codeparrot_training - Step 33932: {'lr': 0.0004447354344694665, 'samples': 17373696, 'steps': 33932, 'loss/train': 2.3519835472106934}
-03/05/2022 05:20:40 - INFO - codeparrot_training - Step 33933: {'lr': 0.0004447321065858512, 'samples': 17374208, 'steps': 33933, 'loss/train': 1.5290069580078125}
-03/05/2022 05:20:41 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/05/2022 05:20:45 - INFO - codeparrot_training - Step 33934: {'lr': 0.00044472877861449257, 'samples': 17374720, 'steps': 33934, 'loss/train': 1.1738260984420776}
-03/05/2022 05:20:48 - INFO - codeparrot_training - Step 33935: {'lr': 0.00044472545055539213, 'samples': 17375232, 'steps': 33935, 'loss/train': 1.2830862998962402}
-03/05/2022 05:20:49 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/05/2022 05:20:53 - INFO - codeparrot_training - Step 33936: {'lr': 0.00044472212240855155, 'samples': 17375744, 'steps': 33936, 'loss/train': 1.4994702339172363}
-03/05/2022 05:20:56 - INFO - codeparrot_training - Step 33937: {'lr': 0.0004447187941739721, 'samples': 17376256, 'steps': 33937, 'loss/train': 1.1862730979919434}
-03/05/2022 05:20:58 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/05/2022 05:21:02 - INFO - codeparrot_training - Step 33938: {'lr': 0.00044471546585165536, 'samples': 17376768, 'steps': 33938, 'loss/train': 1.1888177394866943}
-03/05/2022 05:21:05 - INFO - codeparrot_training - Step 33939: {'lr': 0.0004447121374416028, 'samples': 17377280, 'steps': 33939, 'loss/train': 1.9602402448654175}
-03/05/2022 05:21:06 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 05:21:10 - INFO - codeparrot_training - Step 33940: {'lr': 0.000444708808943816, 'samples': 17377792, 'steps': 33940, 'loss/train': 1.697003960609436}
-03/05/2022 05:21:13 - INFO - codeparrot_training - Step 33941: {'lr': 0.00044470548035829637, 'samples': 17378304, 'steps': 33941, 'loss/train': 0.17559204995632172}
-03/05/2022 05:21:14 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 05:21:19 - INFO - codeparrot_training - Step 33942: {'lr': 0.00044470215168504554, 'samples': 17378816, 'steps': 33942, 'loss/train': 2.0348830223083496}
-03/05/2022 05:21:22 - INFO - codeparrot_training - Step 33943: {'lr': 0.0004446988229240648, 'samples': 17379328, 'steps': 33943, 'loss/train': 0.7638850212097168}
-03/05/2022 05:21:23 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/05/2022 05:21:27 - INFO - codeparrot_training - Step 33944: {'lr': 0.00044469549407535593, 'samples': 17379840, 'steps': 33944, 'loss/train': 1.419360637664795}
-03/05/2022 05:21:30 - INFO - codeparrot_training - Step 33945: {'lr': 0.0004446921651389202, 'samples': 17380352, 'steps': 33945, 'loss/train': 0.07543662935495377}
-03/05/2022 05:21:31 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/05/2022 05:21:35 - INFO - codeparrot_training - Step 33946: {'lr': 0.00044468883611475913, 'samples': 17380864, 'steps': 33946, 'loss/train': 2.2713510990142822}
-03/05/2022 05:21:39 - INFO - codeparrot_training - Step 33947: {'lr': 0.00044468550700287436, 'samples': 17381376, 'steps': 33947, 'loss/train': 1.3508340120315552}
-03/05/2022 05:21:40 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/05/2022 05:21:44 - INFO - codeparrot_training - Step 33948: {'lr': 0.00044468217780326724, 'samples': 17381888, 'steps': 33948, 'loss/train': 1.675719976425171}
-03/05/2022 05:21:47 - INFO - codeparrot_training - Step 33949: {'lr': 0.0004446788485159393, 'samples': 17382400, 'steps': 33949, 'loss/train': 0.7711401581764221}
-03/05/2022 05:21:48 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/05/2022 05:21:52 - INFO - codeparrot_training - Step 33950: {'lr': 0.00044467551914089223, 'samples': 17382912, 'steps': 33950, 'loss/train': 1.340704083442688}
-03/05/2022 05:21:56 - INFO - codeparrot_training - Step 33951: {'lr': 0.0004446721896781273, 'samples': 17383424, 'steps': 33951, 'loss/train': 0.13692378997802734}
-03/05/2022 05:21:56 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/05/2022 05:22:01 - INFO - codeparrot_training - Step 33952: {'lr': 0.00044466886012764603, 'samples': 17383936, 'steps': 33952, 'loss/train': 2.5945584774017334}
-03/05/2022 05:22:04 - INFO - codeparrot_training - Step 33953: {'lr': 0.00044466553048944996, 'samples': 17384448, 'steps': 33953, 'loss/train': 1.5927963256835938}
-03/05/2022 05:22:05 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/05/2022 05:22:09 - INFO - codeparrot_training - Step 33954: {'lr': 0.0004446622007635407, 'samples': 17384960, 'steps': 33954, 'loss/train': 2.176279067993164}
-03/05/2022 05:22:12 - INFO - codeparrot_training - Step 33955: {'lr': 0.0004446588709499196, 'samples': 17385472, 'steps': 33955, 'loss/train': 1.946581482887268}
-03/05/2022 05:22:13 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/05/2022 05:22:18 - INFO - codeparrot_training - Step 33956: {'lr': 0.00044465554104858817, 'samples': 17385984, 'steps': 33956, 'loss/train': 1.9513555765151978}
-03/05/2022 05:22:21 - INFO - codeparrot_training - Step 33957: {'lr': 0.0004446522110595481, 'samples': 17386496, 'steps': 33957, 'loss/train': 1.7858421802520752}
-03/05/2022 05:22:22 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 05:22:26 - INFO - codeparrot_training - Step 33958: {'lr': 0.00044464888098280067, 'samples': 17387008, 'steps': 33958, 'loss/train': 1.6601685285568237}
-03/05/2022 05:22:29 - INFO - codeparrot_training - Step 33959: {'lr': 0.00044464555081834745, 'samples': 17387520, 'steps': 33959, 'loss/train': 1.634395956993103}
-03/05/2022 05:22:30 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/05/2022 05:22:35 - INFO - codeparrot_training - Step 33960: {'lr': 0.00044464222056618996, 'samples': 17388032, 'steps': 33960, 'loss/train': 1.9958555698394775}
-03/05/2022 05:22:38 - INFO - codeparrot_training - Step 33961: {'lr': 0.00044463889022632963, 'samples': 17388544, 'steps': 33961, 'loss/train': 2.1417324542999268}
-03/05/2022 05:22:39 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 05:22:43 - INFO - codeparrot_training - Step 33962: {'lr': 0.0004446355597987681, 'samples': 17389056, 'steps': 33962, 'loss/train': 1.9063613414764404}
-03/05/2022 05:22:46 - INFO - codeparrot_training - Step 33963: {'lr': 0.00044463222928350677, 'samples': 17389568, 'steps': 33963, 'loss/train': 2.9024369716644287}
-03/05/2022 05:22:47 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/05/2022 05:22:51 - INFO - codeparrot_training - Step 33964: {'lr': 0.0004446288986805471, 'samples': 17390080, 'steps': 33964, 'loss/train': 1.6557780504226685}
-03/05/2022 05:22:55 - INFO - codeparrot_training - Step 33965: {'lr': 0.0004446255679898907, 'samples': 17390592, 'steps': 33965, 'loss/train': 1.6633977890014648}
-03/05/2022 05:22:55 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/05/2022 05:23:00 - INFO - codeparrot_training - Step 33966: {'lr': 0.000444622237211539, 'samples': 17391104, 'steps': 33966, 'loss/train': 1.3186196088790894}
-03/05/2022 05:23:03 - INFO - codeparrot_training - Step 33967: {'lr': 0.00044461890634549364, 'samples': 17391616, 'steps': 33967, 'loss/train': 1.8880226612091064}
-03/05/2022 05:23:04 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 05:23:08 - INFO - codeparrot_training - Step 33968: {'lr': 0.00044461557539175587, 'samples': 17392128, 'steps': 33968, 'loss/train': 1.1651276350021362}
-03/05/2022 05:23:11 - INFO - codeparrot_training - Step 33969: {'lr': 0.0004446122443503274, 'samples': 17392640, 'steps': 33969, 'loss/train': 1.0649319887161255}
-03/05/2022 05:23:12 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/05/2022 05:23:17 - INFO - codeparrot_training - Step 33970: {'lr': 0.00044460891322120963, 'samples': 17393152, 'steps': 33970, 'loss/train': 1.6299347877502441}
-03/05/2022 05:23:20 - INFO - codeparrot_training - Step 33971: {'lr': 0.000444605582004404, 'samples': 17393664, 'steps': 33971, 'loss/train': 0.9564369320869446}
-03/05/2022 05:23:20 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/05/2022 05:23:25 - INFO - codeparrot_training - Step 33972: {'lr': 0.0004446022506999122, 'samples': 17394176, 'steps': 33972, 'loss/train': 1.629865288734436}
-03/05/2022 05:23:28 - INFO - codeparrot_training - Step 33973: {'lr': 0.0004445989193077356, 'samples': 17394688, 'steps': 33973, 'loss/train': 1.9565603733062744}
-03/05/2022 05:23:29 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/05/2022 05:23:34 - INFO - codeparrot_training - Step 33974: {'lr': 0.0004445955878278758, 'samples': 17395200, 'steps': 33974, 'loss/train': 1.9195678234100342}
-03/05/2022 05:23:37 - INFO - codeparrot_training - Step 33975: {'lr': 0.00044459225626033413, 'samples': 17395712, 'steps': 33975, 'loss/train': 0.9503218531608582}
-03/05/2022 05:23:37 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/05/2022 05:23:42 - INFO - codeparrot_training - Step 33976: {'lr': 0.00044458892460511225, 'samples': 17396224, 'steps': 33976, 'loss/train': 2.525550127029419}
-03/05/2022 05:23:45 - INFO - codeparrot_training - Step 33977: {'lr': 0.0004445855928622116, 'samples': 17396736, 'steps': 33977, 'loss/train': 1.1452312469482422}
-03/05/2022 05:23:45 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/05/2022 05:23:50 - INFO - codeparrot_training - Step 33978: {'lr': 0.00044458226103163365, 'samples': 17397248, 'steps': 33978, 'loss/train': 0.6207029223442078}
-03/05/2022 05:23:54 - INFO - codeparrot_training - Step 33979: {'lr': 0.0004445789291133799, 'samples': 17397760, 'steps': 33979, 'loss/train': 1.4539440870285034}
-03/05/2022 05:23:54 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/05/2022 05:23:59 - INFO - codeparrot_training - Step 33980: {'lr': 0.0004445755971074519, 'samples': 17398272, 'steps': 33980, 'loss/train': 1.0375241041183472}
-03/05/2022 05:24:02 - INFO - codeparrot_training - Step 33981: {'lr': 0.0004445722650138512, 'samples': 17398784, 'steps': 33981, 'loss/train': 1.9532052278518677}
-03/05/2022 05:24:02 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/05/2022 05:24:07 - INFO - codeparrot_training - Step 33982: {'lr': 0.00044456893283257925, 'samples': 17399296, 'steps': 33982, 'loss/train': 1.2587968111038208}
-03/05/2022 05:24:10 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/05/2022 05:24:13 - INFO - codeparrot_training - Step 33983: {'lr': 0.00044456560056363746, 'samples': 17399808, 'steps': 33983, 'loss/train': 1.5715456008911133}
-03/05/2022 05:24:16 - INFO - codeparrot_training - Step 33984: {'lr': 0.0004445622682070275, 'samples': 17400320, 'steps': 33984, 'loss/train': 1.4688823223114014}
-03/05/2022 05:24:19 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/05/2022 05:24:21 - INFO - codeparrot_training - Step 33985: {'lr': 0.00044455893576275077, 'samples': 17400832, 'steps': 33985, 'loss/train': 1.5532448291778564}
-03/05/2022 05:24:24 - INFO - codeparrot_training - Step 33986: {'lr': 0.00044455560323080874, 'samples': 17401344, 'steps': 33986, 'loss/train': 2.2441117763519287}
-03/05/2022 05:24:30 - INFO - codeparrot_training - Step 33987: {'lr': 0.00044455227061120296, 'samples': 17401856, 'steps': 33987, 'loss/train': 2.274519920349121}
-03/05/2022 05:24:33 - INFO - codeparrot_training - Step 33988: {'lr': 0.000444548937903935, 'samples': 17402368, 'steps': 33988, 'loss/train': 1.8789424896240234}
-03/05/2022 05:24:36 - INFO - codeparrot_training - Step 33989: {'lr': 0.0004445456051090062, 'samples': 17402880, 'steps': 33989, 'loss/train': 1.7000093460083008}
-03/05/2022 05:24:36 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/05/2022 05:24:41 - INFO - codeparrot_training - Step 33990: {'lr': 0.0004445422722264182, 'samples': 17403392, 'steps': 33990, 'loss/train': 2.164118766784668}
-03/05/2022 05:24:44 - INFO - codeparrot_training - Step 33991: {'lr': 0.0004445389392561724, 'samples': 17403904, 'steps': 33991, 'loss/train': 1.7376148700714111}
-03/05/2022 05:24:44 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/05/2022 05:24:50 - INFO - codeparrot_training - Step 33992: {'lr': 0.0004445356061982704, 'samples': 17404416, 'steps': 33992, 'loss/train': 1.6368515491485596}
-03/05/2022 05:24:53 - INFO - codeparrot_training - Step 33993: {'lr': 0.0004445322730527137, 'samples': 17404928, 'steps': 33993, 'loss/train': 1.713008999824524}
-03/05/2022 05:24:53 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/05/2022 05:24:58 - INFO - codeparrot_training - Step 33994: {'lr': 0.0004445289398195037, 'samples': 17405440, 'steps': 33994, 'loss/train': 0.6787934303283691}
-03/05/2022 05:25:01 - INFO - codeparrot_training - Step 33995: {'lr': 0.000444525606498642, 'samples': 17405952, 'steps': 33995, 'loss/train': 1.6441653966903687}
-03/05/2022 05:25:02 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 05:25:06 - INFO - codeparrot_training - Step 33996: {'lr': 0.00044452227309013003, 'samples': 17406464, 'steps': 33996, 'loss/train': 3.624610662460327}
-03/05/2022 05:25:10 - INFO - codeparrot_training - Step 33997: {'lr': 0.0004445189395939694, 'samples': 17406976, 'steps': 33997, 'loss/train': 1.5357794761657715}
-03/05/2022 05:25:10 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 05:25:15 - INFO - codeparrot_training - Step 33998: {'lr': 0.0004445156060101614, 'samples': 17407488, 'steps': 33998, 'loss/train': 1.9015567302703857}
-03/05/2022 05:25:18 - INFO - codeparrot_training - Step 33999: {'lr': 0.0004445122723387077, 'samples': 17408000, 'steps': 33999, 'loss/train': 2.327850341796875}
-03/05/2022 05:25:18 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/05/2022 05:25:23 - INFO - codeparrot_training - Step 34000: {'lr': 0.0004445089385796099, 'samples': 17408512, 'steps': 34000, 'loss/train': 2.517242670059204}
-03/05/2022 05:25:27 - INFO - codeparrot_training - Step 34001: {'lr': 0.0004445056047328693, 'samples': 17409024, 'steps': 34001, 'loss/train': 0.8967128992080688}
-03/05/2022 05:25:27 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/05/2022 05:25:32 - INFO - codeparrot_training - Step 34002: {'lr': 0.0004445022707984874, 'samples': 17409536, 'steps': 34002, 'loss/train': 1.659019947052002}
-03/05/2022 05:25:35 - INFO - codeparrot_training - Step 34003: {'lr': 0.0004444989367764659, 'samples': 17410048, 'steps': 34003, 'loss/train': 1.7482949495315552}
-03/05/2022 05:25:36 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/05/2022 05:25:40 - INFO - codeparrot_training - Step 34004: {'lr': 0.0004444956026668061, 'samples': 17410560, 'steps': 34004, 'loss/train': 1.5374693870544434}
-03/05/2022 05:25:43 - INFO - codeparrot_training - Step 34005: {'lr': 0.00044449226846950964, 'samples': 17411072, 'steps': 34005, 'loss/train': 1.5551549196243286}
-03/05/2022 05:25:44 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 05:25:49 - INFO - codeparrot_training - Step 34006: {'lr': 0.00044448893418457794, 'samples': 17411584, 'steps': 34006, 'loss/train': 0.5738779902458191}
-03/05/2022 05:25:52 - INFO - codeparrot_training - Step 34007: {'lr': 0.00044448559981201256, 'samples': 17412096, 'steps': 34007, 'loss/train': 1.4854726791381836}
-03/05/2022 05:25:52 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/05/2022 05:25:57 - INFO - codeparrot_training - Step 34008: {'lr': 0.00044448226535181485, 'samples': 17412608, 'steps': 34008, 'loss/train': 2.1169748306274414}
-03/05/2022 05:26:00 - INFO - codeparrot_training - Step 34009: {'lr': 0.0004444789308039865, 'samples': 17413120, 'steps': 34009, 'loss/train': 1.4246947765350342}
-03/05/2022 05:26:00 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/05/2022 05:26:06 - INFO - codeparrot_training - Step 34010: {'lr': 0.00044447559616852893, 'samples': 17413632, 'steps': 34010, 'loss/train': 1.1972066164016724}
-03/05/2022 05:26:09 - INFO - codeparrot_training - Step 34011: {'lr': 0.0004444722614454437, 'samples': 17414144, 'steps': 34011, 'loss/train': 1.5975327491760254}
-03/05/2022 05:26:09 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/05/2022 05:26:14 - INFO - codeparrot_training - Step 34012: {'lr': 0.00044446892663473227, 'samples': 17414656, 'steps': 34012, 'loss/train': 1.0017327070236206}
-03/05/2022 05:26:17 - INFO - codeparrot_training - Step 34013: {'lr': 0.0004444655917363961, 'samples': 17415168, 'steps': 34013, 'loss/train': 1.9199111461639404}
-03/05/2022 05:26:18 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/05/2022 05:26:23 - INFO - codeparrot_training - Step 34014: {'lr': 0.00044446225675043684, 'samples': 17415680, 'steps': 34014, 'loss/train': 2.266388177871704}
-03/05/2022 05:26:26 - INFO - codeparrot_training - Step 34015: {'lr': 0.0004444589216768558, 'samples': 17416192, 'steps': 34015, 'loss/train': 2.0375964641571045}
-03/05/2022 05:26:27 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/05/2022 05:26:31 - INFO - codeparrot_training - Step 34016: {'lr': 0.0004444555865156545, 'samples': 17416704, 'steps': 34016, 'loss/train': 1.4140856266021729}
-03/05/2022 05:26:34 - INFO - codeparrot_training - Step 34017: {'lr': 0.0004444522512668346, 'samples': 17417216, 'steps': 34017, 'loss/train': 1.0430351495742798}
-03/05/2022 05:26:35 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/05/2022 05:26:40 - INFO - codeparrot_training - Step 34018: {'lr': 0.0004444489159303976, 'samples': 17417728, 'steps': 34018, 'loss/train': 1.5708619356155396}
-03/05/2022 05:26:43 - INFO - codeparrot_training - Step 34019: {'lr': 0.0004444455805063448, 'samples': 17418240, 'steps': 34019, 'loss/train': 1.9042675495147705}
-03/05/2022 05:26:43 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/05/2022 05:26:48 - INFO - codeparrot_training - Step 34020: {'lr': 0.00044444224499467784, 'samples': 17418752, 'steps': 34020, 'loss/train': 2.2518444061279297}
-03/05/2022 05:26:51 - INFO - codeparrot_training - Step 34021: {'lr': 0.0004444389093953982, 'samples': 17419264, 'steps': 34021, 'loss/train': 1.9457601308822632}
-03/05/2022 05:26:52 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/05/2022 05:26:57 - INFO - codeparrot_training - Step 34022: {'lr': 0.00044443557370850743, 'samples': 17419776, 'steps': 34022, 'loss/train': 1.21356201171875}
-03/05/2022 05:27:00 - INFO - codeparrot_training - Step 34023: {'lr': 0.00044443223793400695, 'samples': 17420288, 'steps': 34023, 'loss/train': 1.6199712753295898}
-03/05/2022 05:27:00 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/05/2022 05:27:05 - INFO - codeparrot_training - Step 34024: {'lr': 0.0004444289020718983, 'samples': 17420800, 'steps': 34024, 'loss/train': 1.809503197669983}
-03/05/2022 05:27:08 - INFO - codeparrot_training - Step 34025: {'lr': 0.000444425566122183, 'samples': 17421312, 'steps': 34025, 'loss/train': 1.568223476409912}
-03/05/2022 05:27:09 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/05/2022 05:27:13 - INFO - codeparrot_training - Step 34026: {'lr': 0.0004444222300848626, 'samples': 17421824, 'steps': 34026, 'loss/train': 1.978883147239685}
-03/05/2022 05:27:17 - INFO - codeparrot_training - Step 34027: {'lr': 0.00044441889395993844, 'samples': 17422336, 'steps': 34027, 'loss/train': 1.7291051149368286}
-03/05/2022 05:27:17 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/05/2022 05:27:22 - INFO - codeparrot_training - Step 34028: {'lr': 0.00044441555774741215, 'samples': 17422848, 'steps': 34028, 'loss/train': 1.868433952331543}
-03/05/2022 05:27:25 - INFO - codeparrot_training - Step 34029: {'lr': 0.00044441222144728525, 'samples': 17423360, 'steps': 34029, 'loss/train': 2.080197811126709}
-03/05/2022 05:27:25 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/05/2022 05:27:30 - INFO - codeparrot_training - Step 34030: {'lr': 0.00044440888505955926, 'samples': 17423872, 'steps': 34030, 'loss/train': 1.055450677871704}
-03/05/2022 05:27:34 - INFO - codeparrot_training - Step 34031: {'lr': 0.00044440554858423553, 'samples': 17424384, 'steps': 34031, 'loss/train': 1.1946673393249512}
-03/05/2022 05:27:34 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/05/2022 05:27:39 - INFO - codeparrot_training - Step 34032: {'lr': 0.0004444022120213157, 'samples': 17424896, 'steps': 34032, 'loss/train': 2.417046546936035}
-03/05/2022 05:27:42 - INFO - codeparrot_training - Step 34033: {'lr': 0.00044439887537080116, 'samples': 17425408, 'steps': 34033, 'loss/train': 1.494907259941101}
-03/05/2022 05:27:42 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 05:27:47 - INFO - codeparrot_training - Step 34034: {'lr': 0.00044439553863269356, 'samples': 17425920, 'steps': 34034, 'loss/train': 0.11388105154037476}
-03/05/2022 05:27:51 - INFO - codeparrot_training - Step 34035: {'lr': 0.00044439220180699434, 'samples': 17426432, 'steps': 34035, 'loss/train': 1.883411169052124}
-03/05/2022 05:27:51 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/05/2022 05:27:56 - INFO - codeparrot_training - Step 34036: {'lr': 0.00044438886489370493, 'samples': 17426944, 'steps': 34036, 'loss/train': 2.4596474170684814}
-03/05/2022 05:27:59 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/05/2022 05:28:01 - INFO - codeparrot_training - Step 34037: {'lr': 0.00044438552789282694, 'samples': 17427456, 'steps': 34037, 'loss/train': 1.4283480644226074}
-03/05/2022 05:28:04 - INFO - codeparrot_training - Step 34038: {'lr': 0.00044438219080436184, 'samples': 17427968, 'steps': 34038, 'loss/train': 2.1580395698547363}
-03/05/2022 05:28:07 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/05/2022 05:28:10 - INFO - codeparrot_training - Step 34039: {'lr': 0.0004443788536283111, 'samples': 17428480, 'steps': 34039, 'loss/train': 1.7696539163589478}
-03/05/2022 05:28:13 - INFO - codeparrot_training - Step 34040: {'lr': 0.0004443755163646762, 'samples': 17428992, 'steps': 34040, 'loss/train': 1.4342762231826782}
-03/05/2022 05:28:15 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/05/2022 05:28:18 - INFO - codeparrot_training - Step 34041: {'lr': 0.00044437217901345885, 'samples': 17429504, 'steps': 34041, 'loss/train': 1.6364816427230835}
-03/05/2022 05:28:22 - INFO - codeparrot_training - Step 34042: {'lr': 0.0004443688415746602, 'samples': 17430016, 'steps': 34042, 'loss/train': 6.383542060852051}
-03/05/2022 05:28:25 - INFO - codeparrot_training - Step 34043: {'lr': 0.00044436550404828207, 'samples': 17430528, 'steps': 34043, 'loss/train': 1.1378906965255737}
-03/05/2022 05:28:25 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/05/2022 05:28:30 - INFO - codeparrot_training - Step 34044: {'lr': 0.0004443621664343258, 'samples': 17431040, 'steps': 34044, 'loss/train': 2.4452288150787354}
-03/05/2022 05:28:33 - INFO - codeparrot_training - Step 34045: {'lr': 0.000444358828732793, 'samples': 17431552, 'steps': 34045, 'loss/train': 1.940739631652832}
-03/05/2022 05:28:34 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/05/2022 05:28:38 - INFO - codeparrot_training - Step 34046: {'lr': 0.000444355490943685, 'samples': 17432064, 'steps': 34046, 'loss/train': 1.7151546478271484}
-03/05/2022 05:28:42 - INFO - codeparrot_training - Step 34047: {'lr': 0.0004443521530670035, 'samples': 17432576, 'steps': 34047, 'loss/train': 1.630328893661499}
-03/05/2022 05:28:42 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/05/2022 05:28:47 - INFO - codeparrot_training - Step 34048: {'lr': 0.00044434881510274995, 'samples': 17433088, 'steps': 34048, 'loss/train': 0.8149397373199463}
-03/05/2022 05:28:50 - INFO - codeparrot_training - Step 34049: {'lr': 0.00044434547705092574, 'samples': 17433600, 'steps': 34049, 'loss/train': 1.8687498569488525}
-03/05/2022 05:28:51 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 05:28:55 - INFO - codeparrot_training - Step 34050: {'lr': 0.0004443421389115325, 'samples': 17434112, 'steps': 34050, 'loss/train': 1.3824677467346191}
-03/05/2022 05:28:59 - INFO - codeparrot_training - Step 34051: {'lr': 0.00044433880068457166, 'samples': 17434624, 'steps': 34051, 'loss/train': 1.6641342639923096}
-03/05/2022 05:28:59 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/05/2022 05:29:04 - INFO - codeparrot_training - Step 34052: {'lr': 0.0004443354623700447, 'samples': 17435136, 'steps': 34052, 'loss/train': 1.1805343627929688}
-03/05/2022 05:29:07 - INFO - codeparrot_training - Step 34053: {'lr': 0.0004443321239679533, 'samples': 17435648, 'steps': 34053, 'loss/train': 1.2358131408691406}
-03/05/2022 05:29:08 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/05/2022 05:29:12 - INFO - codeparrot_training - Step 34054: {'lr': 0.0004443287854782988, 'samples': 17436160, 'steps': 34054, 'loss/train': 3.921879768371582}
-03/05/2022 05:29:15 - INFO - codeparrot_training - Step 34055: {'lr': 0.0004443254469010828, 'samples': 17436672, 'steps': 34055, 'loss/train': 1.191489338874817}
-03/05/2022 05:29:16 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/05/2022 05:29:21 - INFO - codeparrot_training - Step 34056: {'lr': 0.0004443221082363067, 'samples': 17437184, 'steps': 34056, 'loss/train': 2.0300021171569824}
-03/05/2022 05:29:24 - INFO - codeparrot_training - Step 34057: {'lr': 0.000444318769483972, 'samples': 17437696, 'steps': 34057, 'loss/train': 0.5210140347480774}
-03/05/2022 05:29:24 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/05/2022 05:29:29 - INFO - codeparrot_training - Step 34058: {'lr': 0.0004443154306440803, 'samples': 17438208, 'steps': 34058, 'loss/train': 2.4055397510528564}
-03/05/2022 05:29:32 - INFO - codeparrot_training - Step 34059: {'lr': 0.00044431209171663313, 'samples': 17438720, 'steps': 34059, 'loss/train': 2.0263545513153076}
-03/05/2022 05:29:33 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/05/2022 05:29:38 - INFO - codeparrot_training - Step 34060: {'lr': 0.00044430875270163185, 'samples': 17439232, 'steps': 34060, 'loss/train': 2.1843109130859375}
-03/05/2022 05:29:41 - INFO - codeparrot_training - Step 34061: {'lr': 0.00044430541359907804, 'samples': 17439744, 'steps': 34061, 'loss/train': 2.376917600631714}
-03/05/2022 05:29:41 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/05/2022 05:29:46 - INFO - codeparrot_training - Step 34062: {'lr': 0.0004443020744089733, 'samples': 17440256, 'steps': 34062, 'loss/train': 2.157226800918579}
-03/05/2022 05:29:49 - INFO - codeparrot_training - Step 34063: {'lr': 0.00044429873513131897, 'samples': 17440768, 'steps': 34063, 'loss/train': 1.7049163579940796}
-03/05/2022 05:29:50 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/05/2022 05:29:54 - INFO - codeparrot_training - Step 34064: {'lr': 0.00044429539576611664, 'samples': 17441280, 'steps': 34064, 'loss/train': 1.0562320947647095}
-03/05/2022 05:29:58 - INFO - codeparrot_training - Step 34065: {'lr': 0.0004442920563133678, 'samples': 17441792, 'steps': 34065, 'loss/train': 1.3266373872756958}
-03/05/2022 05:29:58 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/05/2022 05:30:03 - INFO - codeparrot_training - Step 34066: {'lr': 0.000444288716773074, 'samples': 17442304, 'steps': 34066, 'loss/train': 1.7700921297073364}
-03/05/2022 05:30:06 - INFO - codeparrot_training - Step 34067: {'lr': 0.00044428537714523664, 'samples': 17442816, 'steps': 34067, 'loss/train': 2.31009840965271}
-03/05/2022 05:30:06 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/05/2022 05:30:11 - INFO - codeparrot_training - Step 34068: {'lr': 0.00044428203742985734, 'samples': 17443328, 'steps': 34068, 'loss/train': 1.738326907157898}
-03/05/2022 05:30:14 - INFO - codeparrot_training - Step 34069: {'lr': 0.0004442786976269375, 'samples': 17443840, 'steps': 34069, 'loss/train': 1.696182131767273}
-03/05/2022 05:30:15 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/05/2022 05:30:20 - INFO - codeparrot_training - Step 34070: {'lr': 0.0004442753577364788, 'samples': 17444352, 'steps': 34070, 'loss/train': 1.6762832403182983}
-03/05/2022 05:30:23 - INFO - codeparrot_training - Step 34071: {'lr': 0.00044427201775848246, 'samples': 17444864, 'steps': 34071, 'loss/train': 2.6324005126953125}
-03/05/2022 05:30:23 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/05/2022 05:30:28 - INFO - codeparrot_training - Step 34072: {'lr': 0.0004442686776929502, 'samples': 17445376, 'steps': 34072, 'loss/train': 2.109015464782715}
-03/05/2022 05:30:32 - INFO - codeparrot_training - Step 34073: {'lr': 0.0004442653375398835, 'samples': 17445888, 'steps': 34073, 'loss/train': 0.7658395171165466}
-03/05/2022 05:30:32 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/05/2022 05:30:37 - INFO - codeparrot_training - Step 34074: {'lr': 0.0004442619972992838, 'samples': 17446400, 'steps': 34074, 'loss/train': 1.2794744968414307}
-03/05/2022 05:30:40 - INFO - codeparrot_training - Step 34075: {'lr': 0.00044425865697115266, 'samples': 17446912, 'steps': 34075, 'loss/train': 1.7137771844863892}
-03/05/2022 05:30:41 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 05:30:45 - INFO - codeparrot_training - Step 34076: {'lr': 0.00044425531655549157, 'samples': 17447424, 'steps': 34076, 'loss/train': 3.111297369003296}
-03/05/2022 05:30:48 - INFO - codeparrot_training - Step 34077: {'lr': 0.0004442519760523021, 'samples': 17447936, 'steps': 34077, 'loss/train': 1.9399579763412476}
-03/05/2022 05:30:49 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 05:30:54 - INFO - codeparrot_training - Step 34078: {'lr': 0.00044424863546158554, 'samples': 17448448, 'steps': 34078, 'loss/train': 1.8226441144943237}
-03/05/2022 05:30:57 - INFO - codeparrot_training - Step 34079: {'lr': 0.00044424529478334364, 'samples': 17448960, 'steps': 34079, 'loss/train': 1.540472149848938}
-03/05/2022 05:30:57 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 05:31:02 - INFO - codeparrot_training - Step 34080: {'lr': 0.0004442419540175778, 'samples': 17449472, 'steps': 34080, 'loss/train': 1.758059024810791}
-03/05/2022 05:31:05 - INFO - codeparrot_training - Step 34081: {'lr': 0.0004442386131642895, 'samples': 17449984, 'steps': 34081, 'loss/train': 1.5499799251556396}
-03/05/2022 05:31:06 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/05/2022 05:31:11 - INFO - codeparrot_training - Step 34082: {'lr': 0.0004442352722234803, 'samples': 17450496, 'steps': 34082, 'loss/train': 1.8947174549102783}
-03/05/2022 05:31:14 - INFO - codeparrot_training - Step 34083: {'lr': 0.0004442319311951517, 'samples': 17451008, 'steps': 34083, 'loss/train': 1.7237558364868164}
-03/05/2022 05:31:14 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/05/2022 05:31:19 - INFO - codeparrot_training - Step 34084: {'lr': 0.00044422859007930515, 'samples': 17451520, 'steps': 34084, 'loss/train': 2.104606866836548}
-03/05/2022 05:31:22 - INFO - codeparrot_training - Step 34085: {'lr': 0.00044422524887594223, 'samples': 17452032, 'steps': 34085, 'loss/train': 2.273200750350952}
-03/05/2022 05:31:23 - INFO - codeparrot_training - Skipping example with length 548 (seq_length=1024)
-03/05/2022 05:31:28 - INFO - codeparrot_training - Step 34086: {'lr': 0.0004442219075850644, 'samples': 17452544, 'steps': 34086, 'loss/train': 1.4440802335739136}
-03/05/2022 05:31:31 - INFO - codeparrot_training - Step 34087: {'lr': 0.0004442185662066731, 'samples': 17453056, 'steps': 34087, 'loss/train': 1.655002474784851}
-03/05/2022 05:31:31 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/05/2022 05:31:36 - INFO - codeparrot_training - Step 34088: {'lr': 0.00044421522474077, 'samples': 17453568, 'steps': 34088, 'loss/train': 1.9454220533370972}
-03/05/2022 05:31:39 - INFO - codeparrot_training - Step 34089: {'lr': 0.0004442118831873565, 'samples': 17454080, 'steps': 34089, 'loss/train': 0.9859744906425476}
-03/05/2022 05:31:40 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 05:31:44 - INFO - codeparrot_training - Step 34090: {'lr': 0.00044420854154643413, 'samples': 17454592, 'steps': 34090, 'loss/train': 2.5611069202423096}
-03/05/2022 05:31:48 - INFO - codeparrot_training - Step 34091: {'lr': 0.00044420519981800446, 'samples': 17455104, 'steps': 34091, 'loss/train': 1.5908671617507935}
-03/05/2022 05:31:48 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/05/2022 05:31:53 - INFO - codeparrot_training - Step 34092: {'lr': 0.0004442018580020688, 'samples': 17455616, 'steps': 34092, 'loss/train': 1.4729499816894531}
-03/05/2022 05:31:56 - INFO - codeparrot_training - Step 34093: {'lr': 0.0004441985160986288, 'samples': 17456128, 'steps': 34093, 'loss/train': 1.5146385431289673}
-03/05/2022 05:31:56 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/05/2022 05:32:02 - INFO - codeparrot_training - Step 34094: {'lr': 0.00044419517410768594, 'samples': 17456640, 'steps': 34094, 'loss/train': 1.671014428138733}
-03/05/2022 05:32:05 - INFO - codeparrot_training - Step 34095: {'lr': 0.0004441918320292418, 'samples': 17457152, 'steps': 34095, 'loss/train': 1.6886521577835083}
-03/05/2022 05:32:05 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/05/2022 05:32:10 - INFO - codeparrot_training - Step 34096: {'lr': 0.00044418848986329775, 'samples': 17457664, 'steps': 34096, 'loss/train': 1.3938440084457397}
-03/05/2022 05:32:13 - INFO - codeparrot_training - Step 34097: {'lr': 0.0004441851476098554, 'samples': 17458176, 'steps': 34097, 'loss/train': 1.5952064990997314}
-03/05/2022 05:32:13 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/05/2022 05:32:18 - INFO - codeparrot_training - Step 34098: {'lr': 0.0004441818052689162, 'samples': 17458688, 'steps': 34098, 'loss/train': 2.0440635681152344}
-03/05/2022 05:32:21 - INFO - codeparrot_training - Step 34099: {'lr': 0.0004441784628404817, 'samples': 17459200, 'steps': 34099, 'loss/train': 1.7776108980178833}
-03/05/2022 05:32:22 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/05/2022 05:32:27 - INFO - codeparrot_training - Step 34100: {'lr': 0.0004441751203245533, 'samples': 17459712, 'steps': 34100, 'loss/train': 1.8822574615478516}
-03/05/2022 05:32:30 - INFO - codeparrot_training - Step 34101: {'lr': 0.0004441717777211327, 'samples': 17460224, 'steps': 34101, 'loss/train': 2.3708813190460205}
-03/05/2022 05:32:30 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/05/2022 05:32:35 - INFO - codeparrot_training - Step 34102: {'lr': 0.00044416843503022126, 'samples': 17460736, 'steps': 34102, 'loss/train': 0.9929918646812439}
-03/05/2022 05:32:38 - INFO - codeparrot_training - Step 34103: {'lr': 0.00044416509225182044, 'samples': 17461248, 'steps': 34103, 'loss/train': 2.3612778186798096}
-03/05/2022 05:32:38 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/05/2022 05:32:43 - INFO - codeparrot_training - Step 34104: {'lr': 0.0004441617493859319, 'samples': 17461760, 'steps': 34104, 'loss/train': 1.6196959018707275}
-03/05/2022 05:32:47 - INFO - codeparrot_training - Step 34105: {'lr': 0.0004441584064325571, 'samples': 17462272, 'steps': 34105, 'loss/train': 1.9568370580673218}
-03/05/2022 05:32:47 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/05/2022 05:32:52 - INFO - codeparrot_training - Step 34106: {'lr': 0.0004441550633916975, 'samples': 17462784, 'steps': 34106, 'loss/train': 0.5889873504638672}
-03/05/2022 05:32:55 - INFO - codeparrot_training - Step 34107: {'lr': 0.0004441517202633546, 'samples': 17463296, 'steps': 34107, 'loss/train': 0.9713134765625}
-03/05/2022 05:33:00 - INFO - codeparrot_training - Step 34108: {'lr': 0.0004441483770475299, 'samples': 17463808, 'steps': 34108, 'loss/train': 2.0026438236236572}
-03/05/2022 05:33:03 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/05/2022 05:33:06 - INFO - codeparrot_training - Step 34109: {'lr': 0.000444145033744225, 'samples': 17464320, 'steps': 34109, 'loss/train': 2.3801803588867188}
-03/05/2022 05:33:09 - INFO - codeparrot_training - Step 34110: {'lr': 0.0004441416903534413, 'samples': 17464832, 'steps': 34110, 'loss/train': 1.7913153171539307}
-03/05/2022 05:33:12 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 05:33:14 - INFO - codeparrot_training - Step 34111: {'lr': 0.00044413834687518034, 'samples': 17465344, 'steps': 34111, 'loss/train': 1.6845449209213257}
-03/05/2022 05:33:17 - INFO - codeparrot_training - Step 34112: {'lr': 0.00044413500330944366, 'samples': 17465856, 'steps': 34112, 'loss/train': 2.147451162338257}
-03/05/2022 05:33:21 - INFO - codeparrot_training - Step 34113: {'lr': 0.00044413165965623275, 'samples': 17466368, 'steps': 34113, 'loss/train': 2.1855807304382324}
-03/05/2022 05:33:21 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/05/2022 05:33:26 - INFO - codeparrot_training - Step 34114: {'lr': 0.00044412831591554916, 'samples': 17466880, 'steps': 34114, 'loss/train': 2.339319944381714}
-03/05/2022 05:33:29 - INFO - codeparrot_training - Step 34115: {'lr': 0.0004441249720873942, 'samples': 17467392, 'steps': 34115, 'loss/train': 1.0943936109542847}
-03/05/2022 05:33:29 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/05/2022 05:33:34 - INFO - codeparrot_training - Step 34116: {'lr': 0.00044412162817176966, 'samples': 17467904, 'steps': 34116, 'loss/train': 1.85038423538208}
-03/05/2022 05:33:37 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 05:33:40 - INFO - codeparrot_training - Step 34117: {'lr': 0.00044411828416867684, 'samples': 17468416, 'steps': 34117, 'loss/train': 1.950211524963379}
-03/05/2022 05:33:43 - INFO - codeparrot_training - Step 34118: {'lr': 0.00044411494007811736, 'samples': 17468928, 'steps': 34118, 'loss/train': 0.8425441384315491}
-03/05/2022 05:33:46 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/05/2022 05:33:48 - INFO - codeparrot_training - Step 34119: {'lr': 0.00044411159590009263, 'samples': 17469440, 'steps': 34119, 'loss/train': 1.7786281108856201}
-03/05/2022 05:33:52 - INFO - codeparrot_training - Step 34120: {'lr': 0.0004441082516346043, 'samples': 17469952, 'steps': 34120, 'loss/train': 2.330460548400879}
-03/05/2022 05:33:54 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/05/2022 05:33:57 - INFO - codeparrot_training - Step 34121: {'lr': 0.0004441049072816537, 'samples': 17470464, 'steps': 34121, 'loss/train': 1.8122012615203857}
-03/05/2022 05:34:00 - INFO - codeparrot_training - Step 34122: {'lr': 0.0004441015628412425, 'samples': 17470976, 'steps': 34122, 'loss/train': 1.9550861120224}
-03/05/2022 05:34:02 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/05/2022 05:34:05 - INFO - codeparrot_training - Step 34123: {'lr': 0.0004440982183133721, 'samples': 17471488, 'steps': 34123, 'loss/train': 1.4404162168502808}
-03/05/2022 05:34:08 - INFO - codeparrot_training - Step 34124: {'lr': 0.00044409487369804395, 'samples': 17472000, 'steps': 34124, 'loss/train': 1.7190989255905151}
-03/05/2022 05:34:11 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/05/2022 05:34:14 - INFO - codeparrot_training - Step 34125: {'lr': 0.00044409152899525973, 'samples': 17472512, 'steps': 34125, 'loss/train': 1.7323949337005615}
-03/05/2022 05:34:17 - INFO - codeparrot_training - Step 34126: {'lr': 0.00044408818420502085, 'samples': 17473024, 'steps': 34126, 'loss/train': 0.8039728999137878}
-03/05/2022 05:34:19 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/05/2022 05:34:22 - INFO - codeparrot_training - Step 34127: {'lr': 0.00044408483932732886, 'samples': 17473536, 'steps': 34127, 'loss/train': 2.007296085357666}
-03/05/2022 05:34:25 - INFO - codeparrot_training - Step 34128: {'lr': 0.00044408149436218523, 'samples': 17474048, 'steps': 34128, 'loss/train': 1.5064901113510132}
-03/05/2022 05:34:28 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 05:34:31 - INFO - codeparrot_training - Step 34129: {'lr': 0.00044407814930959137, 'samples': 17474560, 'steps': 34129, 'loss/train': 1.8547723293304443}
-03/05/2022 05:34:34 - INFO - codeparrot_training - Step 34130: {'lr': 0.000444074804169549, 'samples': 17475072, 'steps': 34130, 'loss/train': 1.7464185953140259}
-03/05/2022 05:34:36 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/05/2022 05:34:39 - INFO - codeparrot_training - Step 34131: {'lr': 0.00044407145894205947, 'samples': 17475584, 'steps': 34131, 'loss/train': 2.269740581512451}
-03/05/2022 05:34:42 - INFO - codeparrot_training - Step 34132: {'lr': 0.0004440681136271244, 'samples': 17476096, 'steps': 34132, 'loss/train': 2.106044054031372}
-03/05/2022 05:34:45 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/05/2022 05:34:47 - INFO - codeparrot_training - Step 34133: {'lr': 0.0004440647682247452, 'samples': 17476608, 'steps': 34133, 'loss/train': 1.6214338541030884}
-03/05/2022 05:34:51 - INFO - codeparrot_training - Step 34134: {'lr': 0.00044406142273492334, 'samples': 17477120, 'steps': 34134, 'loss/train': 1.1986275911331177}
-03/05/2022 05:34:53 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/05/2022 05:34:56 - INFO - codeparrot_training - Step 34135: {'lr': 0.00044405807715766047, 'samples': 17477632, 'steps': 34135, 'loss/train': 0.2201683670282364}
-03/05/2022 05:34:59 - INFO - codeparrot_training - Step 34136: {'lr': 0.00044405473149295804, 'samples': 17478144, 'steps': 34136, 'loss/train': 2.3020589351654053}
-03/05/2022 05:35:01 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/05/2022 05:35:04 - INFO - codeparrot_training - Step 34137: {'lr': 0.0004440513857408175, 'samples': 17478656, 'steps': 34137, 'loss/train': 1.0189393758773804}
-03/05/2022 05:35:07 - INFO - codeparrot_training - Step 34138: {'lr': 0.0004440480399012404, 'samples': 17479168, 'steps': 34138, 'loss/train': 1.8139852285385132}
-03/05/2022 05:35:09 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/05/2022 05:35:13 - INFO - codeparrot_training - Step 34139: {'lr': 0.00044404469397422823, 'samples': 17479680, 'steps': 34139, 'loss/train': 1.9736565351486206}
-03/05/2022 05:35:16 - INFO - codeparrot_training - Step 34140: {'lr': 0.00044404134795978257, 'samples': 17480192, 'steps': 34140, 'loss/train': 1.5291110277175903}
-03/05/2022 05:35:17 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/05/2022 05:35:21 - INFO - codeparrot_training - Step 34141: {'lr': 0.0004440380018579049, 'samples': 17480704, 'steps': 34141, 'loss/train': 1.5795916318893433}
-03/05/2022 05:35:24 - INFO - codeparrot_training - Step 34142: {'lr': 0.00044403465566859656, 'samples': 17481216, 'steps': 34142, 'loss/train': 2.210779905319214}
-03/05/2022 05:35:26 - INFO - codeparrot_training - Skipping example with length 524 (seq_length=1024)
-03/05/2022 05:35:29 - INFO - codeparrot_training - Step 34143: {'lr': 0.0004440313093918593, 'samples': 17481728, 'steps': 34143, 'loss/train': 1.5776442289352417}
-03/05/2022 05:35:33 - INFO - codeparrot_training - Step 34144: {'lr': 0.00044402796302769453, 'samples': 17482240, 'steps': 34144, 'loss/train': 1.3823585510253906}
-03/05/2022 05:35:34 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 05:35:38 - INFO - codeparrot_training - Step 34145: {'lr': 0.0004440246165761037, 'samples': 17482752, 'steps': 34145, 'loss/train': 0.8426879048347473}
-03/05/2022 05:35:41 - INFO - codeparrot_training - Step 34146: {'lr': 0.00044402127003708846, 'samples': 17483264, 'steps': 34146, 'loss/train': 2.297863006591797}
-03/05/2022 05:35:42 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/05/2022 05:35:47 - INFO - codeparrot_training - Step 34147: {'lr': 0.0004440179234106502, 'samples': 17483776, 'steps': 34147, 'loss/train': 5.218173980712891}
-03/05/2022 05:35:50 - INFO - codeparrot_training - Step 34148: {'lr': 0.00044401457669679043, 'samples': 17484288, 'steps': 34148, 'loss/train': 1.0703234672546387}
-03/05/2022 05:35:52 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/05/2022 05:35:55 - INFO - codeparrot_training - Step 34149: {'lr': 0.0004440112298955107, 'samples': 17484800, 'steps': 34149, 'loss/train': 1.0748257637023926}
-03/05/2022 05:35:58 - INFO - codeparrot_training - Step 34150: {'lr': 0.0004440078830068125, 'samples': 17485312, 'steps': 34150, 'loss/train': 1.4391534328460693}
-03/05/2022 05:36:00 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/05/2022 05:36:03 - INFO - codeparrot_training - Step 34151: {'lr': 0.00044400453603069727, 'samples': 17485824, 'steps': 34151, 'loss/train': 0.8661510348320007}
-03/05/2022 05:36:07 - INFO - codeparrot_training - Step 34152: {'lr': 0.0004440011889671667, 'samples': 17486336, 'steps': 34152, 'loss/train': 1.792608618736267}
-03/05/2022 05:36:08 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/05/2022 05:36:12 - INFO - codeparrot_training - Step 34153: {'lr': 0.00044399784181622216, 'samples': 17486848, 'steps': 34153, 'loss/train': 2.131106376647949}
-03/05/2022 05:36:15 - INFO - codeparrot_training - Step 34154: {'lr': 0.0004439944945778651, 'samples': 17487360, 'steps': 34154, 'loss/train': 1.5413190126419067}
-03/05/2022 05:36:17 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 05:36:20 - INFO - codeparrot_training - Step 34155: {'lr': 0.0004439911472520972, 'samples': 17487872, 'steps': 34155, 'loss/train': 1.3426002264022827}
-03/05/2022 05:36:23 - INFO - codeparrot_training - Step 34156: {'lr': 0.0004439877998389199, 'samples': 17488384, 'steps': 34156, 'loss/train': 1.57003915309906}
-03/05/2022 05:36:25 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/05/2022 05:36:29 - INFO - codeparrot_training - Step 34157: {'lr': 0.0004439844523383346, 'samples': 17488896, 'steps': 34157, 'loss/train': 1.2894264459609985}
-03/05/2022 05:36:32 - INFO - codeparrot_training - Step 34158: {'lr': 0.000443981104750343, 'samples': 17489408, 'steps': 34158, 'loss/train': 0.39746251702308655}
-03/05/2022 05:36:34 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/05/2022 05:36:37 - INFO - codeparrot_training - Step 34159: {'lr': 0.0004439777570749465, 'samples': 17489920, 'steps': 34159, 'loss/train': 0.6969925165176392}
-03/05/2022 05:36:40 - INFO - codeparrot_training - Step 34160: {'lr': 0.0004439744093121465, 'samples': 17490432, 'steps': 34160, 'loss/train': 1.8490140438079834}
-03/05/2022 05:36:42 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/05/2022 05:36:46 - INFO - codeparrot_training - Step 34161: {'lr': 0.00044397106146194473, 'samples': 17490944, 'steps': 34161, 'loss/train': 0.4180835485458374}
-03/05/2022 05:36:49 - INFO - codeparrot_training - Step 34162: {'lr': 0.00044396771352434256, 'samples': 17491456, 'steps': 34162, 'loss/train': 1.2257460355758667}
-03/05/2022 05:36:52 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/05/2022 05:36:54 - INFO - codeparrot_training - Step 34163: {'lr': 0.00044396436549934155, 'samples': 17491968, 'steps': 34163, 'loss/train': 1.9260871410369873}
-03/05/2022 05:36:58 - INFO - codeparrot_training - Step 34164: {'lr': 0.00044396101738694316, 'samples': 17492480, 'steps': 34164, 'loss/train': 1.8775568008422852}
-03/05/2022 05:37:01 - INFO - codeparrot_training - Step 34165: {'lr': 0.000443957669187149, 'samples': 17492992, 'steps': 34165, 'loss/train': 1.9550294876098633}
-03/05/2022 05:37:01 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 05:37:06 - INFO - codeparrot_training - Step 34166: {'lr': 0.0004439543208999604, 'samples': 17493504, 'steps': 34166, 'loss/train': 2.0865559577941895}
-03/05/2022 05:37:10 - INFO - codeparrot_training - Step 34167: {'lr': 0.00044395097252537905, 'samples': 17494016, 'steps': 34167, 'loss/train': 0.9504692554473877}
-03/05/2022 05:37:11 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 05:37:15 - INFO - codeparrot_training - Step 34168: {'lr': 0.0004439476240634064, 'samples': 17494528, 'steps': 34168, 'loss/train': 2.2714765071868896}
-03/05/2022 05:37:18 - INFO - codeparrot_training - Step 34169: {'lr': 0.00044394427551404386, 'samples': 17495040, 'steps': 34169, 'loss/train': 1.9800372123718262}
-03/05/2022 05:37:19 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/05/2022 05:37:23 - INFO - codeparrot_training - Step 34170: {'lr': 0.00044394092687729305, 'samples': 17495552, 'steps': 34170, 'loss/train': 1.8309171199798584}
-03/05/2022 05:37:26 - INFO - codeparrot_training - Step 34171: {'lr': 0.0004439375781531555, 'samples': 17496064, 'steps': 34171, 'loss/train': 2.181962728500366}
-03/05/2022 05:37:28 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/05/2022 05:37:31 - INFO - codeparrot_training - Step 34172: {'lr': 0.00044393422934163265, 'samples': 17496576, 'steps': 34172, 'loss/train': 1.0602643489837646}
-03/05/2022 05:37:35 - INFO - codeparrot_training - Step 34173: {'lr': 0.000443930880442726, 'samples': 17497088, 'steps': 34173, 'loss/train': 1.1460702419281006}
-03/05/2022 05:37:36 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/05/2022 05:37:40 - INFO - codeparrot_training - Step 34174: {'lr': 0.0004439275314564371, 'samples': 17497600, 'steps': 34174, 'loss/train': 1.664525032043457}
-03/05/2022 05:37:43 - INFO - codeparrot_training - Step 34175: {'lr': 0.0004439241823827674, 'samples': 17498112, 'steps': 34175, 'loss/train': 2.226043224334717}
-03/05/2022 05:37:45 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/05/2022 05:37:48 - INFO - codeparrot_training - Step 34176: {'lr': 0.0004439208332217186, 'samples': 17498624, 'steps': 34176, 'loss/train': 1.8547481298446655}
-03/05/2022 05:37:52 - INFO - codeparrot_training - Step 34177: {'lr': 0.00044391748397329194, 'samples': 17499136, 'steps': 34177, 'loss/train': 2.1341235637664795}
-03/05/2022 05:37:53 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/05/2022 05:37:57 - INFO - codeparrot_training - Step 34178: {'lr': 0.0004439141346374891, 'samples': 17499648, 'steps': 34178, 'loss/train': 5.807307720184326}
-03/05/2022 05:38:00 - INFO - codeparrot_training - Step 34179: {'lr': 0.0004439107852143115, 'samples': 17500160, 'steps': 34179, 'loss/train': 1.5781409740447998}
-03/05/2022 05:38:02 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/05/2022 05:38:05 - INFO - codeparrot_training - Step 34180: {'lr': 0.0004439074357037607, 'samples': 17500672, 'steps': 34180, 'loss/train': 2.3529586791992188}
-03/05/2022 05:38:09 - INFO - codeparrot_training - Step 34181: {'lr': 0.0004439040861058383, 'samples': 17501184, 'steps': 34181, 'loss/train': 2.0639467239379883}
-03/05/2022 05:38:11 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/05/2022 05:38:14 - INFO - codeparrot_training - Step 34182: {'lr': 0.00044390073642054564, 'samples': 17501696, 'steps': 34182, 'loss/train': 1.917283296585083}
-03/05/2022 05:38:17 - INFO - codeparrot_training - Step 34183: {'lr': 0.00044389738664788424, 'samples': 17502208, 'steps': 34183, 'loss/train': 1.2364617586135864}
-03/05/2022 05:38:19 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/05/2022 05:38:22 - INFO - codeparrot_training - Step 34184: {'lr': 0.00044389403678785576, 'samples': 17502720, 'steps': 34184, 'loss/train': 1.7462048530578613}
-03/05/2022 05:38:25 - INFO - codeparrot_training - Step 34185: {'lr': 0.0004438906868404616, 'samples': 17503232, 'steps': 34185, 'loss/train': 2.254133939743042}
-03/05/2022 05:38:27 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/05/2022 05:38:31 - INFO - codeparrot_training - Step 34186: {'lr': 0.00044388733680570324, 'samples': 17503744, 'steps': 34186, 'loss/train': 1.0031273365020752}
-03/05/2022 05:38:34 - INFO - codeparrot_training - Step 34187: {'lr': 0.00044388398668358234, 'samples': 17504256, 'steps': 34187, 'loss/train': 1.5295847654342651}
-03/05/2022 05:38:35 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 05:38:39 - INFO - codeparrot_training - Step 34188: {'lr': 0.00044388063647410016, 'samples': 17504768, 'steps': 34188, 'loss/train': 1.9227910041809082}
-03/05/2022 05:38:42 - INFO - codeparrot_training - Step 34189: {'lr': 0.00044387728617725845, 'samples': 17505280, 'steps': 34189, 'loss/train': 2.4586002826690674}
-03/05/2022 05:38:44 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/05/2022 05:38:48 - INFO - codeparrot_training - Step 34190: {'lr': 0.0004438739357930586, 'samples': 17505792, 'steps': 34190, 'loss/train': 2.033339023590088}
-03/05/2022 05:38:51 - INFO - codeparrot_training - Step 34191: {'lr': 0.00044387058532150217, 'samples': 17506304, 'steps': 34191, 'loss/train': 1.110052227973938}
-03/05/2022 05:38:52 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/05/2022 05:38:56 - INFO - codeparrot_training - Step 34192: {'lr': 0.0004438672347625907, 'samples': 17506816, 'steps': 34192, 'loss/train': 1.0906049013137817}
-03/05/2022 05:38:59 - INFO - codeparrot_training - Step 34193: {'lr': 0.0004438638841163255, 'samples': 17507328, 'steps': 34193, 'loss/train': 1.8400697708129883}
-03/05/2022 05:39:00 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 05:39:04 - INFO - codeparrot_training - Step 34194: {'lr': 0.0004438605333827083, 'samples': 17507840, 'steps': 34194, 'loss/train': 1.9471436738967896}
-03/05/2022 05:39:08 - INFO - codeparrot_training - Step 34195: {'lr': 0.00044385718256174055, 'samples': 17508352, 'steps': 34195, 'loss/train': 1.6939191818237305}
-03/05/2022 05:39:09 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/05/2022 05:39:13 - INFO - codeparrot_training - Step 34196: {'lr': 0.0004438538316534237, 'samples': 17508864, 'steps': 34196, 'loss/train': 2.4373652935028076}
-03/05/2022 05:39:16 - INFO - codeparrot_training - Step 34197: {'lr': 0.0004438504806577594, 'samples': 17509376, 'steps': 34197, 'loss/train': 1.7957028150558472}
-03/05/2022 05:39:17 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/05/2022 05:39:21 - INFO - codeparrot_training - Step 34198: {'lr': 0.000443847129574749, 'samples': 17509888, 'steps': 34198, 'loss/train': 0.06292540580034256}
-03/05/2022 05:39:25 - INFO - codeparrot_training - Step 34199: {'lr': 0.0004438437784043941, 'samples': 17510400, 'steps': 34199, 'loss/train': 1.7774512767791748}
-03/05/2022 05:39:26 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 05:39:30 - INFO - codeparrot_training - Step 34200: {'lr': 0.00044384042714669614, 'samples': 17510912, 'steps': 34200, 'loss/train': 1.7547448873519897}
-03/05/2022 05:39:33 - INFO - codeparrot_training - Step 34201: {'lr': 0.0004438370758016567, 'samples': 17511424, 'steps': 34201, 'loss/train': 1.7959250211715698}
-03/05/2022 05:39:34 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/05/2022 05:39:38 - INFO - codeparrot_training - Step 34202: {'lr': 0.00044383372436927727, 'samples': 17511936, 'steps': 34202, 'loss/train': 2.1022074222564697}
-03/05/2022 05:39:41 - INFO - codeparrot_training - Step 34203: {'lr': 0.00044383037284955937, 'samples': 17512448, 'steps': 34203, 'loss/train': 1.398281455039978}
-03/05/2022 05:39:42 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/05/2022 05:39:47 - INFO - codeparrot_training - Step 34204: {'lr': 0.00044382702124250444, 'samples': 17512960, 'steps': 34204, 'loss/train': 1.6356000900268555}
-03/05/2022 05:39:50 - INFO - codeparrot_training - Step 34205: {'lr': 0.0004438236695481141, 'samples': 17513472, 'steps': 34205, 'loss/train': 1.6093099117279053}
-03/05/2022 05:39:51 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/05/2022 05:39:55 - INFO - codeparrot_training - Step 34206: {'lr': 0.00044382031776638974, 'samples': 17513984, 'steps': 34206, 'loss/train': 1.7206929922103882}
-03/05/2022 05:39:59 - INFO - codeparrot_training - Step 34207: {'lr': 0.000443816965897333, 'samples': 17514496, 'steps': 34207, 'loss/train': 0.7779200673103333}
-03/05/2022 05:39:59 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 05:40:04 - INFO - codeparrot_training - Step 34208: {'lr': 0.0004438136139409453, 'samples': 17515008, 'steps': 34208, 'loss/train': 1.8553944826126099}
-03/05/2022 05:40:07 - INFO - codeparrot_training - Step 34209: {'lr': 0.00044381026189722824, 'samples': 17515520, 'steps': 34209, 'loss/train': 0.8115091323852539}
-03/05/2022 05:40:08 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/05/2022 05:40:12 - INFO - codeparrot_training - Step 34210: {'lr': 0.0004438069097661832, 'samples': 17516032, 'steps': 34210, 'loss/train': 2.2580177783966064}
-03/05/2022 05:40:15 - INFO - codeparrot_training - Step 34211: {'lr': 0.0004438035575478118, 'samples': 17516544, 'steps': 34211, 'loss/train': 1.4521112442016602}
-03/05/2022 05:40:16 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/05/2022 05:40:21 - INFO - codeparrot_training - Step 34212: {'lr': 0.0004438002052421154, 'samples': 17517056, 'steps': 34212, 'loss/train': 1.8690000772476196}
-03/05/2022 05:40:24 - INFO - codeparrot_training - Step 34213: {'lr': 0.00044379685284909575, 'samples': 17517568, 'steps': 34213, 'loss/train': 1.5044785737991333}
-03/05/2022 05:40:24 - INFO - codeparrot_training - Skipping example with length 292 (seq_length=1024)
-03/05/2022 05:40:29 - INFO - codeparrot_training - Step 34214: {'lr': 0.00044379350036875413, 'samples': 17518080, 'steps': 34214, 'loss/train': 1.6928565502166748}
-03/05/2022 05:40:32 - INFO - codeparrot_training - Step 34215: {'lr': 0.00044379014780109217, 'samples': 17518592, 'steps': 34215, 'loss/train': 1.7167913913726807}
-03/05/2022 05:40:33 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/05/2022 05:40:38 - INFO - codeparrot_training - Step 34216: {'lr': 0.00044378679514611144, 'samples': 17519104, 'steps': 34216, 'loss/train': 1.9740239381790161}
-03/05/2022 05:40:41 - INFO - codeparrot_training - Step 34217: {'lr': 0.0004437834424038133, 'samples': 17519616, 'steps': 34217, 'loss/train': 1.097809910774231}
-03/05/2022 05:40:41 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/05/2022 05:40:46 - INFO - codeparrot_training - Step 34218: {'lr': 0.00044378008957419936, 'samples': 17520128, 'steps': 34218, 'loss/train': 2.2368226051330566}
-03/05/2022 05:40:49 - INFO - codeparrot_training - Step 34219: {'lr': 0.00044377673665727105, 'samples': 17520640, 'steps': 34219, 'loss/train': 1.9591455459594727}
-03/05/2022 05:40:49 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/05/2022 05:40:54 - INFO - codeparrot_training - Step 34220: {'lr': 0.00044377338365303, 'samples': 17521152, 'steps': 34220, 'loss/train': 1.9518258571624756}
-03/05/2022 05:40:58 - INFO - codeparrot_training - Step 34221: {'lr': 0.00044377003056147757, 'samples': 17521664, 'steps': 34221, 'loss/train': 0.06462162733078003}
-03/05/2022 05:40:58 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/05/2022 05:41:03 - INFO - codeparrot_training - Step 34222: {'lr': 0.00044376667738261545, 'samples': 17522176, 'steps': 34222, 'loss/train': 0.47106412053108215}
-03/05/2022 05:41:06 - INFO - codeparrot_training - Step 34223: {'lr': 0.000443763324116445, 'samples': 17522688, 'steps': 34223, 'loss/train': 1.8936957120895386}
-03/05/2022 05:41:06 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/05/2022 05:41:12 - INFO - codeparrot_training - Step 34224: {'lr': 0.00044375997076296774, 'samples': 17523200, 'steps': 34224, 'loss/train': 1.8771260976791382}
-03/05/2022 05:41:15 - INFO - codeparrot_training - Step 34225: {'lr': 0.0004437566173221853, 'samples': 17523712, 'steps': 34225, 'loss/train': 2.251481056213379}
-03/05/2022 05:41:15 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/05/2022 05:41:20 - INFO - codeparrot_training - Step 34226: {'lr': 0.0004437532637940991, 'samples': 17524224, 'steps': 34226, 'loss/train': 1.5564502477645874}
-03/05/2022 05:41:23 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/05/2022 05:41:25 - INFO - codeparrot_training - Step 34227: {'lr': 0.0004437499101787107, 'samples': 17524736, 'steps': 34227, 'loss/train': 1.6151272058486938}
-03/05/2022 05:41:28 - INFO - codeparrot_training - Step 34228: {'lr': 0.00044374655647602153, 'samples': 17525248, 'steps': 34228, 'loss/train': 1.7380579710006714}
-03/05/2022 05:41:31 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/05/2022 05:41:34 - INFO - codeparrot_training - Step 34229: {'lr': 0.0004437432026860332, 'samples': 17525760, 'steps': 34229, 'loss/train': 0.642063558101654}
-03/05/2022 05:41:37 - INFO - codeparrot_training - Step 34230: {'lr': 0.00044373984880874705, 'samples': 17526272, 'steps': 34230, 'loss/train': 2.1146881580352783}
-03/05/2022 05:41:39 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/05/2022 05:41:42 - INFO - codeparrot_training - Step 34231: {'lr': 0.0004437364948441649, 'samples': 17526784, 'steps': 34231, 'loss/train': 1.0028339624404907}
-03/05/2022 05:41:45 - INFO - codeparrot_training - Step 34232: {'lr': 0.00044373314079228796, 'samples': 17527296, 'steps': 34232, 'loss/train': 1.3107696771621704}
-03/05/2022 05:41:49 - INFO - codeparrot_training - Step 34233: {'lr': 0.0004437297866531179, 'samples': 17527808, 'steps': 34233, 'loss/train': 1.8322502374649048}
-03/05/2022 05:41:49 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/05/2022 05:41:54 - INFO - codeparrot_training - Step 34234: {'lr': 0.0004437264324266561, 'samples': 17528320, 'steps': 34234, 'loss/train': 0.8838863968849182}
-03/05/2022 05:41:57 - INFO - codeparrot_training - Step 34235: {'lr': 0.00044372307811290425, 'samples': 17528832, 'steps': 34235, 'loss/train': 2.091601848602295}
-03/05/2022 05:41:57 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/05/2022 05:42:02 - INFO - codeparrot_training - Step 34236: {'lr': 0.00044371972371186374, 'samples': 17529344, 'steps': 34236, 'loss/train': 0.8373674750328064}
-03/05/2022 05:42:05 - INFO - codeparrot_training - Step 34237: {'lr': 0.0004437163692235361, 'samples': 17529856, 'steps': 34237, 'loss/train': 1.7728911638259888}
-03/05/2022 05:42:06 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/05/2022 05:42:11 - INFO - codeparrot_training - Step 34238: {'lr': 0.0004437130146479229, 'samples': 17530368, 'steps': 34238, 'loss/train': 1.5088465213775635}
-03/05/2022 05:42:14 - INFO - codeparrot_training - Step 34239: {'lr': 0.00044370965998502554, 'samples': 17530880, 'steps': 34239, 'loss/train': 1.45180082321167}
-03/05/2022 05:42:14 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 05:42:19 - INFO - codeparrot_training - Step 34240: {'lr': 0.0004437063052348457, 'samples': 17531392, 'steps': 34240, 'loss/train': 1.8537890911102295}
-03/05/2022 05:42:22 - INFO - codeparrot_training - Step 34241: {'lr': 0.0004437029503973847, 'samples': 17531904, 'steps': 34241, 'loss/train': 1.139745831489563}
-03/05/2022 05:42:22 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/05/2022 05:42:28 - INFO - codeparrot_training - Step 34242: {'lr': 0.00044369959547264416, 'samples': 17532416, 'steps': 34242, 'loss/train': 1.970870018005371}
-03/05/2022 05:42:31 - INFO - codeparrot_training - Step 34243: {'lr': 0.0004436962404606255, 'samples': 17532928, 'steps': 34243, 'loss/train': 1.0133898258209229}
-03/05/2022 05:42:31 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/05/2022 05:42:36 - INFO - codeparrot_training - Step 34244: {'lr': 0.0004436928853613304, 'samples': 17533440, 'steps': 34244, 'loss/train': 1.857613205909729}
-03/05/2022 05:42:39 - INFO - codeparrot_training - Step 34245: {'lr': 0.0004436895301747602, 'samples': 17533952, 'steps': 34245, 'loss/train': 1.3862278461456299}
-03/05/2022 05:42:40 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/05/2022 05:42:45 - INFO - codeparrot_training - Step 34246: {'lr': 0.00044368617490091655, 'samples': 17534464, 'steps': 34246, 'loss/train': 0.9862126708030701}
-03/05/2022 05:42:48 - INFO - codeparrot_training - Step 34247: {'lr': 0.0004436828195398009, 'samples': 17534976, 'steps': 34247, 'loss/train': 1.0331921577453613}
-03/05/2022 05:42:49 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/05/2022 05:42:53 - INFO - codeparrot_training - Step 34248: {'lr': 0.0004436794640914148, 'samples': 17535488, 'steps': 34248, 'loss/train': 1.9212638139724731}
-03/05/2022 05:42:56 - INFO - codeparrot_training - Step 34249: {'lr': 0.00044367610855575965, 'samples': 17536000, 'steps': 34249, 'loss/train': 2.0165295600891113}
-03/05/2022 05:42:57 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 05:43:01 - INFO - codeparrot_training - Step 34250: {'lr': 0.00044367275293283705, 'samples': 17536512, 'steps': 34250, 'loss/train': 1.4806463718414307}
-03/05/2022 05:43:05 - INFO - codeparrot_training - Step 34251: {'lr': 0.00044366939722264843, 'samples': 17537024, 'steps': 34251, 'loss/train': 1.6289920806884766}
-03/05/2022 05:43:05 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/05/2022 05:43:10 - INFO - codeparrot_training - Step 34252: {'lr': 0.00044366604142519547, 'samples': 17537536, 'steps': 34252, 'loss/train': 2.0826120376586914}
-03/05/2022 05:43:13 - INFO - codeparrot_training - Step 34253: {'lr': 0.0004436626855404796, 'samples': 17538048, 'steps': 34253, 'loss/train': 2.0340754985809326}
-03/05/2022 05:43:14 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/05/2022 05:43:18 - INFO - codeparrot_training - Step 34254: {'lr': 0.0004436593295685022, 'samples': 17538560, 'steps': 34254, 'loss/train': 1.880374550819397}
-03/05/2022 05:43:22 - INFO - codeparrot_training - Step 34255: {'lr': 0.00044365597350926495, 'samples': 17539072, 'steps': 34255, 'loss/train': 1.6729193925857544}
-03/05/2022 05:43:22 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/05/2022 05:43:27 - INFO - codeparrot_training - Step 34256: {'lr': 0.0004436526173627693, 'samples': 17539584, 'steps': 34256, 'loss/train': 1.50307297706604}
-03/05/2022 05:43:30 - INFO - codeparrot_training - Step 34257: {'lr': 0.00044364926112901675, 'samples': 17540096, 'steps': 34257, 'loss/train': 1.5444446802139282}
-03/05/2022 05:43:30 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/05/2022 05:43:35 - INFO - codeparrot_training - Step 34258: {'lr': 0.0004436459048080089, 'samples': 17540608, 'steps': 34258, 'loss/train': 1.6453111171722412}
-03/05/2022 05:43:38 - INFO - codeparrot_training - Step 34259: {'lr': 0.00044364254839974717, 'samples': 17541120, 'steps': 34259, 'loss/train': 1.885575771331787}
-03/05/2022 05:43:39 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 05:43:44 - INFO - codeparrot_training - Step 34260: {'lr': 0.0004436391919042331, 'samples': 17541632, 'steps': 34260, 'loss/train': 2.1808481216430664}
-03/05/2022 05:43:47 - INFO - codeparrot_training - Step 34261: {'lr': 0.00044363583532146814, 'samples': 17542144, 'steps': 34261, 'loss/train': 2.3671934604644775}
-03/05/2022 05:43:47 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/05/2022 05:43:52 - INFO - codeparrot_training - Step 34262: {'lr': 0.0004436324786514538, 'samples': 17542656, 'steps': 34262, 'loss/train': 2.110642194747925}
-03/05/2022 05:43:55 - INFO - codeparrot_training - Step 34263: {'lr': 0.0004436291218941918, 'samples': 17543168, 'steps': 34263, 'loss/train': 1.900086760520935}
-03/05/2022 05:43:55 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/05/2022 05:44:01 - INFO - codeparrot_training - Step 34264: {'lr': 0.00044362576504968344, 'samples': 17543680, 'steps': 34264, 'loss/train': 2.3246779441833496}
-03/05/2022 05:44:03 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/05/2022 05:44:06 - INFO - codeparrot_training - Step 34265: {'lr': 0.0004436224081179303, 'samples': 17544192, 'steps': 34265, 'loss/train': 1.9526376724243164}
-03/05/2022 05:44:09 - INFO - codeparrot_training - Step 34266: {'lr': 0.00044361905109893397, 'samples': 17544704, 'steps': 34266, 'loss/train': 1.129917025566101}
-03/05/2022 05:44:12 - INFO - codeparrot_training - Step 34267: {'lr': 0.00044361569399269574, 'samples': 17545216, 'steps': 34267, 'loss/train': 0.5088042616844177}
-03/05/2022 05:44:12 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/05/2022 05:44:17 - INFO - codeparrot_training - Step 34268: {'lr': 0.0004436123367992174, 'samples': 17545728, 'steps': 34268, 'loss/train': 1.6535800695419312}
-03/05/2022 05:44:21 - INFO - codeparrot_training - Step 34269: {'lr': 0.0004436089795185003, 'samples': 17546240, 'steps': 34269, 'loss/train': 1.4636188745498657}
-03/05/2022 05:44:21 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/05/2022 05:44:26 - INFO - codeparrot_training - Step 34270: {'lr': 0.0004436056221505459, 'samples': 17546752, 'steps': 34270, 'loss/train': 2.0245325565338135}
-03/05/2022 05:44:29 - INFO - codeparrot_training - Step 34271: {'lr': 0.00044360226469535583, 'samples': 17547264, 'steps': 34271, 'loss/train': 2.298933744430542}
-03/05/2022 05:44:29 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 05:44:34 - INFO - codeparrot_training - Step 34272: {'lr': 0.0004435989071529316, 'samples': 17547776, 'steps': 34272, 'loss/train': 1.7053426504135132}
-03/05/2022 05:44:37 - INFO - codeparrot_training - Step 34273: {'lr': 0.0004435955495232746, 'samples': 17548288, 'steps': 34273, 'loss/train': 1.9695854187011719}
-03/05/2022 05:44:38 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 05:44:43 - INFO - codeparrot_training - Step 34274: {'lr': 0.00044359219180638656, 'samples': 17548800, 'steps': 34274, 'loss/train': 1.5016789436340332}
-03/05/2022 05:44:46 - INFO - codeparrot_training - Step 34275: {'lr': 0.0004435888340022688, 'samples': 17549312, 'steps': 34275, 'loss/train': 1.553998589515686}
-03/05/2022 05:44:46 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/05/2022 05:44:51 - INFO - codeparrot_training - Step 34276: {'lr': 0.0004435854761109229, 'samples': 17549824, 'steps': 34276, 'loss/train': 2.1069953441619873}
-03/05/2022 05:44:54 - INFO - codeparrot_training - Step 34277: {'lr': 0.00044358211813235046, 'samples': 17550336, 'steps': 34277, 'loss/train': 1.1969993114471436}
-03/05/2022 05:44:54 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 05:45:00 - INFO - codeparrot_training - Step 34278: {'lr': 0.0004435787600665528, 'samples': 17550848, 'steps': 34278, 'loss/train': 1.773040771484375}
-03/05/2022 05:45:03 - INFO - codeparrot_training - Step 34279: {'lr': 0.0004435754019135315, 'samples': 17551360, 'steps': 34279, 'loss/train': 2.3009142875671387}
-03/05/2022 05:45:03 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/05/2022 05:45:08 - INFO - codeparrot_training - Step 34280: {'lr': 0.0004435720436732882, 'samples': 17551872, 'steps': 34280, 'loss/train': 1.7082451581954956}
-03/05/2022 05:45:11 - INFO - codeparrot_training - Step 34281: {'lr': 0.0004435686853458243, 'samples': 17552384, 'steps': 34281, 'loss/train': 1.6464056968688965}
-03/05/2022 05:45:12 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 05:45:17 - INFO - codeparrot_training - Step 34282: {'lr': 0.0004435653269311414, 'samples': 17552896, 'steps': 34282, 'loss/train': 2.080547332763672}
-03/05/2022 05:45:20 - INFO - codeparrot_training - Step 34283: {'lr': 0.00044356196842924086, 'samples': 17553408, 'steps': 34283, 'loss/train': 1.6106858253479004}
-03/05/2022 05:45:20 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/05/2022 05:45:25 - INFO - codeparrot_training - Step 34284: {'lr': 0.0004435586098401243, 'samples': 17553920, 'steps': 34284, 'loss/train': 1.7904860973358154}
-03/05/2022 05:45:28 - INFO - codeparrot_training - Step 34285: {'lr': 0.00044355525116379326, 'samples': 17554432, 'steps': 34285, 'loss/train': 1.9045751094818115}
-03/05/2022 05:45:28 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/05/2022 05:45:33 - INFO - codeparrot_training - Step 34286: {'lr': 0.00044355189240024917, 'samples': 17554944, 'steps': 34286, 'loss/train': 0.3161822557449341}
-03/05/2022 05:45:37 - INFO - codeparrot_training - Step 34287: {'lr': 0.00044354853354949353, 'samples': 17555456, 'steps': 34287, 'loss/train': 0.8550520539283752}
-03/05/2022 05:45:37 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/05/2022 05:45:42 - INFO - codeparrot_training - Step 34288: {'lr': 0.000443545174611528, 'samples': 17555968, 'steps': 34288, 'loss/train': 1.2666447162628174}
-03/05/2022 05:45:45 - INFO - codeparrot_training - Step 34289: {'lr': 0.000443541815586354, 'samples': 17556480, 'steps': 34289, 'loss/train': 1.4957973957061768}
-03/05/2022 05:45:45 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/05/2022 05:45:51 - INFO - codeparrot_training - Step 34290: {'lr': 0.0004435384564739729, 'samples': 17556992, 'steps': 34290, 'loss/train': 1.529710054397583}
-03/05/2022 05:45:54 - INFO - codeparrot_training - Step 34291: {'lr': 0.00044353509727438657, 'samples': 17557504, 'steps': 34291, 'loss/train': 1.7087292671203613}
-03/05/2022 05:45:54 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/05/2022 05:45:59 - INFO - codeparrot_training - Step 34292: {'lr': 0.00044353173798759616, 'samples': 17558016, 'steps': 34292, 'loss/train': 1.639023780822754}
-03/05/2022 05:46:02 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/05/2022 05:46:04 - INFO - codeparrot_training - Step 34293: {'lr': 0.0004435283786136034, 'samples': 17558528, 'steps': 34293, 'loss/train': 1.2677940130233765}
-03/05/2022 05:46:08 - INFO - codeparrot_training - Step 34294: {'lr': 0.0004435250191524097, 'samples': 17559040, 'steps': 34294, 'loss/train': 1.6011766195297241}
-03/05/2022 05:46:11 - INFO - codeparrot_training - Step 34295: {'lr': 0.0004435216596040167, 'samples': 17559552, 'steps': 34295, 'loss/train': 1.6702256202697754}
-03/05/2022 05:46:11 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/05/2022 05:46:16 - INFO - codeparrot_training - Step 34296: {'lr': 0.00044351829996842575, 'samples': 17560064, 'steps': 34296, 'loss/train': 0.8600285053253174}
-03/05/2022 05:46:19 - INFO - codeparrot_training - Step 34297: {'lr': 0.00044351494024563845, 'samples': 17560576, 'steps': 34297, 'loss/train': 1.9177359342575073}
-03/05/2022 05:46:19 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/05/2022 05:46:24 - INFO - codeparrot_training - Step 34298: {'lr': 0.0004435115804356563, 'samples': 17561088, 'steps': 34298, 'loss/train': 0.8987356424331665}
-03/05/2022 05:46:28 - INFO - codeparrot_training - Step 34299: {'lr': 0.0004435082205384808, 'samples': 17561600, 'steps': 34299, 'loss/train': 1.7946609258651733}
-03/05/2022 05:46:28 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/05/2022 05:46:33 - INFO - codeparrot_training - Step 34300: {'lr': 0.00044350486055411354, 'samples': 17562112, 'steps': 34300, 'loss/train': 1.2640492916107178}
-03/05/2022 05:46:36 - INFO - codeparrot_training - Step 34301: {'lr': 0.000443501500482556, 'samples': 17562624, 'steps': 34301, 'loss/train': 3.3504762649536133}
-03/05/2022 05:46:37 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/05/2022 05:46:41 - INFO - codeparrot_training - Step 34302: {'lr': 0.0004434981403238096, 'samples': 17563136, 'steps': 34302, 'loss/train': 1.7024686336517334}
-03/05/2022 05:46:45 - INFO - codeparrot_training - Step 34303: {'lr': 0.0004434947800778759, 'samples': 17563648, 'steps': 34303, 'loss/train': 1.0958644151687622}
-03/05/2022 05:46:45 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/05/2022 05:46:50 - INFO - codeparrot_training - Step 34304: {'lr': 0.0004434914197447565, 'samples': 17564160, 'steps': 34304, 'loss/train': 1.7085331678390503}
-03/05/2022 05:46:53 - INFO - codeparrot_training - Step 34305: {'lr': 0.0004434880593244528, 'samples': 17564672, 'steps': 34305, 'loss/train': 0.06464465707540512}
-03/05/2022 05:46:53 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/05/2022 05:46:58 - INFO - codeparrot_training - Step 34306: {'lr': 0.0004434846988169664, 'samples': 17565184, 'steps': 34306, 'loss/train': 1.4451203346252441}
-03/05/2022 05:47:02 - INFO - codeparrot_training - Step 34307: {'lr': 0.0004434813382222989, 'samples': 17565696, 'steps': 34307, 'loss/train': 1.5405151844024658}
-03/05/2022 05:47:02 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/05/2022 05:47:07 - INFO - codeparrot_training - Step 34308: {'lr': 0.0004434779775404515, 'samples': 17566208, 'steps': 34308, 'loss/train': 1.9971555471420288}
-03/05/2022 05:47:10 - INFO - codeparrot_training - Step 34309: {'lr': 0.000443474616771426, 'samples': 17566720, 'steps': 34309, 'loss/train': 2.0689680576324463}
-03/05/2022 05:47:10 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/05/2022 05:47:16 - INFO - codeparrot_training - Step 34310: {'lr': 0.00044347125591522377, 'samples': 17567232, 'steps': 34310, 'loss/train': 1.8060925006866455}
-03/05/2022 05:47:19 - INFO - codeparrot_training - Step 34311: {'lr': 0.00044346789497184643, 'samples': 17567744, 'steps': 34311, 'loss/train': 1.0623342990875244}
-03/05/2022 05:47:20 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/05/2022 05:47:24 - INFO - codeparrot_training - Step 34312: {'lr': 0.0004434645339412954, 'samples': 17568256, 'steps': 34312, 'loss/train': 1.2388983964920044}
-03/05/2022 05:47:27 - INFO - codeparrot_training - Step 34313: {'lr': 0.0004434611728235722, 'samples': 17568768, 'steps': 34313, 'loss/train': 2.177865505218506}
-03/05/2022 05:47:28 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 05:47:33 - INFO - codeparrot_training - Step 34314: {'lr': 0.0004434578116186785, 'samples': 17569280, 'steps': 34314, 'loss/train': 1.789249300956726}
-03/05/2022 05:47:36 - INFO - codeparrot_training - Step 34315: {'lr': 0.00044345445032661565, 'samples': 17569792, 'steps': 34315, 'loss/train': 1.8509910106658936}
-03/05/2022 05:47:37 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/05/2022 05:47:41 - INFO - codeparrot_training - Step 34316: {'lr': 0.0004434510889473852, 'samples': 17570304, 'steps': 34316, 'loss/train': 2.1319479942321777}
-03/05/2022 05:47:44 - INFO - codeparrot_training - Step 34317: {'lr': 0.00044344772748098867, 'samples': 17570816, 'steps': 34317, 'loss/train': 1.7488441467285156}
-03/05/2022 05:47:45 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/05/2022 05:47:50 - INFO - codeparrot_training - Step 34318: {'lr': 0.00044344436592742755, 'samples': 17571328, 'steps': 34318, 'loss/train': 2.176799774169922}
-03/05/2022 05:47:53 - INFO - codeparrot_training - Step 34319: {'lr': 0.0004434410042867034, 'samples': 17571840, 'steps': 34319, 'loss/train': 0.9293532967567444}
-03/05/2022 05:47:53 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/05/2022 05:47:58 - INFO - codeparrot_training - Step 34320: {'lr': 0.0004434376425588178, 'samples': 17572352, 'steps': 34320, 'loss/train': 1.8992440700531006}
-03/05/2022 05:48:01 - INFO - codeparrot_training - Step 34321: {'lr': 0.00044343428074377207, 'samples': 17572864, 'steps': 34321, 'loss/train': 0.9902983903884888}
-03/05/2022 05:48:02 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/05/2022 05:48:06 - INFO - codeparrot_training - Step 34322: {'lr': 0.0004434309188415679, 'samples': 17573376, 'steps': 34322, 'loss/train': 1.4456440210342407}
-03/05/2022 05:48:10 - INFO - codeparrot_training - Step 34323: {'lr': 0.0004434275568522067, 'samples': 17573888, 'steps': 34323, 'loss/train': 1.9827333688735962}
-03/05/2022 05:48:10 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/05/2022 05:48:15 - INFO - codeparrot_training - Step 34324: {'lr': 0.0004434241947756901, 'samples': 17574400, 'steps': 34324, 'loss/train': 1.8385484218597412}
-03/05/2022 05:48:18 - INFO - codeparrot_training - Step 34325: {'lr': 0.0004434208326120195, 'samples': 17574912, 'steps': 34325, 'loss/train': 2.059199333190918}
-03/05/2022 05:48:19 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/05/2022 05:48:23 - INFO - codeparrot_training - Step 34326: {'lr': 0.0004434174703611964, 'samples': 17575424, 'steps': 34326, 'loss/train': 1.24283766746521}
-03/05/2022 05:48:27 - INFO - codeparrot_training - Step 34327: {'lr': 0.00044341410802322247, 'samples': 17575936, 'steps': 34327, 'loss/train': 1.4816592931747437}
-03/05/2022 05:48:27 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 05:48:32 - INFO - codeparrot_training - Step 34328: {'lr': 0.00044341074559809903, 'samples': 17576448, 'steps': 34328, 'loss/train': 1.7746317386627197}
-03/05/2022 05:48:35 - INFO - codeparrot_training - Step 34329: {'lr': 0.00044340738308582775, 'samples': 17576960, 'steps': 34329, 'loss/train': 2.00506591796875}
-03/05/2022 05:48:36 - INFO - codeparrot_training - Skipping example with length 233 (seq_length=1024)
-03/05/2022 05:48:40 - INFO - codeparrot_training - Step 34330: {'lr': 0.0004434040204864101, 'samples': 17577472, 'steps': 34330, 'loss/train': 1.7405996322631836}
-03/05/2022 05:48:43 - INFO - codeparrot_training - Step 34331: {'lr': 0.00044340065779984757, 'samples': 17577984, 'steps': 34331, 'loss/train': 2.0547502040863037}
-03/05/2022 05:48:44 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 05:48:49 - INFO - codeparrot_training - Step 34332: {'lr': 0.0004433972950261417, 'samples': 17578496, 'steps': 34332, 'loss/train': 1.6941430568695068}
-03/05/2022 05:48:52 - INFO - codeparrot_training - Step 34333: {'lr': 0.00044339393216529394, 'samples': 17579008, 'steps': 34333, 'loss/train': 1.4666920900344849}
-03/05/2022 05:48:52 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/05/2022 05:48:57 - INFO - codeparrot_training - Step 34334: {'lr': 0.00044339056921730593, 'samples': 17579520, 'steps': 34334, 'loss/train': 0.9629276990890503}
-03/05/2022 05:49:00 - INFO - codeparrot_training - Step 34335: {'lr': 0.000443387206182179, 'samples': 17580032, 'steps': 34335, 'loss/train': 1.7317924499511719}
-03/05/2022 05:49:01 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/05/2022 05:49:06 - INFO - codeparrot_training - Step 34336: {'lr': 0.0004433838430599149, 'samples': 17580544, 'steps': 34336, 'loss/train': 1.4611281156539917}
-03/05/2022 05:49:09 - INFO - codeparrot_training - Step 34337: {'lr': 0.000443380479850515, 'samples': 17581056, 'steps': 34337, 'loss/train': 1.758908987045288}
-03/05/2022 05:49:09 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/05/2022 05:49:14 - INFO - codeparrot_training - Step 34338: {'lr': 0.00044337711655398083, 'samples': 17581568, 'steps': 34338, 'loss/train': 1.1988584995269775}
-03/05/2022 05:49:17 - INFO - codeparrot_training - Step 34339: {'lr': 0.00044337375317031393, 'samples': 17582080, 'steps': 34339, 'loss/train': 1.847428798675537}
-03/05/2022 05:49:17 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/05/2022 05:49:22 - INFO - codeparrot_training - Step 34340: {'lr': 0.0004433703896995157, 'samples': 17582592, 'steps': 34340, 'loss/train': 1.344567894935608}
-03/05/2022 05:49:25 - INFO - codeparrot_training - Step 34341: {'lr': 0.0004433670261415879, 'samples': 17583104, 'steps': 34341, 'loss/train': 1.682849645614624}
-03/05/2022 05:49:26 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/05/2022 05:49:31 - INFO - codeparrot_training - Step 34342: {'lr': 0.0004433636624965318, 'samples': 17583616, 'steps': 34342, 'loss/train': 2.6633098125457764}
-03/05/2022 05:49:34 - INFO - codeparrot_training - Step 34343: {'lr': 0.0004433602987643491, 'samples': 17584128, 'steps': 34343, 'loss/train': 0.10058866441249847}
-03/05/2022 05:49:35 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 05:49:39 - INFO - codeparrot_training - Step 34344: {'lr': 0.00044335693494504115, 'samples': 17584640, 'steps': 34344, 'loss/train': 1.789832592010498}
-03/05/2022 05:49:43 - INFO - codeparrot_training - Step 34345: {'lr': 0.00044335357103860964, 'samples': 17585152, 'steps': 34345, 'loss/train': 2.1360182762145996}
-03/05/2022 05:49:44 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/05/2022 05:49:48 - INFO - codeparrot_training - Step 34346: {'lr': 0.0004433502070450559, 'samples': 17585664, 'steps': 34346, 'loss/train': 2.0114269256591797}
-03/05/2022 05:49:51 - INFO - codeparrot_training - Step 34347: {'lr': 0.0004433468429643816, 'samples': 17586176, 'steps': 34347, 'loss/train': 1.6056681871414185}
-03/05/2022 05:49:52 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/05/2022 05:49:56 - INFO - codeparrot_training - Step 34348: {'lr': 0.00044334347879658817, 'samples': 17586688, 'steps': 34348, 'loss/train': 1.8490829467773438}
-03/05/2022 05:50:00 - INFO - codeparrot_training - Step 34349: {'lr': 0.0004433401145416771, 'samples': 17587200, 'steps': 34349, 'loss/train': 1.1431628465652466}
-03/05/2022 05:50:01 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 05:50:05 - INFO - codeparrot_training - Step 34350: {'lr': 0.00044333675019965, 'samples': 17587712, 'steps': 34350, 'loss/train': 1.0035871267318726}
-03/05/2022 05:50:08 - INFO - codeparrot_training - Step 34351: {'lr': 0.00044333338577050844, 'samples': 17588224, 'steps': 34351, 'loss/train': 3.328921318054199}
-03/05/2022 05:50:10 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/05/2022 05:50:14 - INFO - codeparrot_training - Step 34352: {'lr': 0.0004433300212542537, 'samples': 17588736, 'steps': 34352, 'loss/train': 0.7708403468132019}
-03/05/2022 05:50:17 - INFO - codeparrot_training - Step 34353: {'lr': 0.00044332665665088755, 'samples': 17589248, 'steps': 34353, 'loss/train': 1.471516728401184}
-03/05/2022 05:50:19 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/05/2022 05:50:22 - INFO - codeparrot_training - Step 34354: {'lr': 0.00044332329196041133, 'samples': 17589760, 'steps': 34354, 'loss/train': 0.1122208759188652}
-03/05/2022 05:50:25 - INFO - codeparrot_training - Step 34355: {'lr': 0.0004433199271828267, 'samples': 17590272, 'steps': 34355, 'loss/train': 1.0844810009002686}
-03/05/2022 05:50:27 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 05:50:31 - INFO - codeparrot_training - Step 34356: {'lr': 0.0004433165623181349, 'samples': 17590784, 'steps': 34356, 'loss/train': 1.5952184200286865}
-03/05/2022 05:50:34 - INFO - codeparrot_training - Step 34357: {'lr': 0.0004433131973663378, 'samples': 17591296, 'steps': 34357, 'loss/train': 1.9786046743392944}
-03/05/2022 05:50:35 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/05/2022 05:50:39 - INFO - codeparrot_training - Step 34358: {'lr': 0.0004433098323274367, 'samples': 17591808, 'steps': 34358, 'loss/train': 0.9796678423881531}
-03/05/2022 05:50:42 - INFO - codeparrot_training - Step 34359: {'lr': 0.00044330646720143317, 'samples': 17592320, 'steps': 34359, 'loss/train': 1.2841209173202515}
-03/05/2022 05:50:44 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/05/2022 05:50:47 - INFO - codeparrot_training - Step 34360: {'lr': 0.0004433031019883288, 'samples': 17592832, 'steps': 34360, 'loss/train': 2.4441580772399902}
-03/05/2022 05:50:51 - INFO - codeparrot_training - Step 34361: {'lr': 0.00044329973668812497, 'samples': 17593344, 'steps': 34361, 'loss/train': 2.3340935707092285}
-03/05/2022 05:50:52 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/05/2022 05:50:56 - INFO - codeparrot_training - Step 34362: {'lr': 0.00044329637130082324, 'samples': 17593856, 'steps': 34362, 'loss/train': 1.3810921907424927}
-03/05/2022 05:50:59 - INFO - codeparrot_training - Step 34363: {'lr': 0.00044329300582642516, 'samples': 17594368, 'steps': 34363, 'loss/train': 1.4531831741333008}
-03/05/2022 05:51:00 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/05/2022 05:51:04 - INFO - codeparrot_training - Step 34364: {'lr': 0.0004432896402649323, 'samples': 17594880, 'steps': 34364, 'loss/train': 1.7095104455947876}
-03/05/2022 05:51:07 - INFO - codeparrot_training - Step 34365: {'lr': 0.0004432862746163461, 'samples': 17595392, 'steps': 34365, 'loss/train': 1.4555608034133911}
-03/05/2022 05:51:09 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/05/2022 05:51:13 - INFO - codeparrot_training - Step 34366: {'lr': 0.000443282908880668, 'samples': 17595904, 'steps': 34366, 'loss/train': 1.9329689741134644}
-03/05/2022 05:51:16 - INFO - codeparrot_training - Step 34367: {'lr': 0.00044327954305789963, 'samples': 17596416, 'steps': 34367, 'loss/train': 1.521092414855957}
-03/05/2022 05:51:17 - INFO - codeparrot_training - Skipping example with length 5 (seq_length=1024)
-03/05/2022 05:51:21 - INFO - codeparrot_training - Step 34368: {'lr': 0.0004432761771480426, 'samples': 17596928, 'steps': 34368, 'loss/train': 0.47753584384918213}
-03/05/2022 05:51:24 - INFO - codeparrot_training - Step 34369: {'lr': 0.0004432728111510982, 'samples': 17597440, 'steps': 34369, 'loss/train': 1.56006920337677}
-03/05/2022 05:51:25 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/05/2022 05:51:29 - INFO - codeparrot_training - Step 34370: {'lr': 0.000443269445067068, 'samples': 17597952, 'steps': 34370, 'loss/train': 1.8805415630340576}
-03/05/2022 05:51:33 - INFO - codeparrot_training - Step 34371: {'lr': 0.0004432660788959537, 'samples': 17598464, 'steps': 34371, 'loss/train': 2.6906087398529053}
-03/05/2022 05:51:34 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/05/2022 05:51:38 - INFO - codeparrot_training - Step 34372: {'lr': 0.00044326271263775657, 'samples': 17598976, 'steps': 34372, 'loss/train': 1.870263695716858}
-03/05/2022 05:51:41 - INFO - codeparrot_training - Step 34373: {'lr': 0.0004432593462924783, 'samples': 17599488, 'steps': 34373, 'loss/train': 2.1580281257629395}
-03/05/2022 05:51:42 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/05/2022 05:51:46 - INFO - codeparrot_training - Step 34374: {'lr': 0.0004432559798601203, 'samples': 17600000, 'steps': 34374, 'loss/train': 1.7139902114868164}
-03/05/2022 05:51:49 - INFO - codeparrot_training - Step 34375: {'lr': 0.0004432526133406842, 'samples': 17600512, 'steps': 34375, 'loss/train': 1.9820737838745117}
-03/05/2022 05:51:50 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/05/2022 05:51:55 - INFO - codeparrot_training - Step 34376: {'lr': 0.0004432492467341715, 'samples': 17601024, 'steps': 34376, 'loss/train': 1.0611504316329956}
-03/05/2022 05:51:58 - INFO - codeparrot_training - Step 34377: {'lr': 0.00044324588004058364, 'samples': 17601536, 'steps': 34377, 'loss/train': 0.07836358994245529}
-03/05/2022 05:51:59 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/05/2022 05:52:03 - INFO - codeparrot_training - Step 34378: {'lr': 0.00044324251325992214, 'samples': 17602048, 'steps': 34378, 'loss/train': 1.802234172821045}
-03/05/2022 05:52:06 - INFO - codeparrot_training - Step 34379: {'lr': 0.0004432391463921885, 'samples': 17602560, 'steps': 34379, 'loss/train': 0.8240492939949036}
-03/05/2022 05:52:07 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/05/2022 05:52:12 - INFO - codeparrot_training - Step 34380: {'lr': 0.00044323577943738437, 'samples': 17603072, 'steps': 34380, 'loss/train': 2.1280899047851562}
-03/05/2022 05:52:15 - INFO - codeparrot_training - Step 34381: {'lr': 0.00044323241239551113, 'samples': 17603584, 'steps': 34381, 'loss/train': 1.7750048637390137}
-03/05/2022 05:52:16 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/05/2022 05:52:20 - INFO - codeparrot_training - Step 34382: {'lr': 0.0004432290452665704, 'samples': 17604096, 'steps': 34382, 'loss/train': 1.799130916595459}
-03/05/2022 05:52:23 - INFO - codeparrot_training - Step 34383: {'lr': 0.00044322567805056356, 'samples': 17604608, 'steps': 34383, 'loss/train': 1.7529054880142212}
-03/05/2022 05:52:24 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/05/2022 05:52:29 - INFO - codeparrot_training - Step 34384: {'lr': 0.00044322231074749225, 'samples': 17605120, 'steps': 34384, 'loss/train': 1.4071407318115234}
-03/05/2022 05:52:32 - INFO - codeparrot_training - Step 34385: {'lr': 0.0004432189433573579, 'samples': 17605632, 'steps': 34385, 'loss/train': 0.5387511849403381}
-03/05/2022 05:52:33 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/05/2022 05:52:37 - INFO - codeparrot_training - Step 34386: {'lr': 0.00044321557588016214, 'samples': 17606144, 'steps': 34386, 'loss/train': 1.0450592041015625}
-03/05/2022 05:52:40 - INFO - codeparrot_training - Step 34387: {'lr': 0.0004432122083159065, 'samples': 17606656, 'steps': 34387, 'loss/train': 1.3318291902542114}
-03/05/2022 05:52:41 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/05/2022 05:52:45 - INFO - codeparrot_training - Step 34388: {'lr': 0.0004432088406645922, 'samples': 17607168, 'steps': 34388, 'loss/train': 1.5386408567428589}
-03/05/2022 05:52:48 - INFO - codeparrot_training - Step 34389: {'lr': 0.00044320547292622114, 'samples': 17607680, 'steps': 34389, 'loss/train': 1.052255630493164}
-03/05/2022 05:52:49 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/05/2022 05:52:54 - INFO - codeparrot_training - Step 34390: {'lr': 0.0004432021051007946, 'samples': 17608192, 'steps': 34390, 'loss/train': 2.951464891433716}
-03/05/2022 05:52:57 - INFO - codeparrot_training - Step 34391: {'lr': 0.00044319873718831425, 'samples': 17608704, 'steps': 34391, 'loss/train': 2.170942544937134}
-03/05/2022 05:52:58 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/05/2022 05:53:02 - INFO - codeparrot_training - Step 34392: {'lr': 0.00044319536918878156, 'samples': 17609216, 'steps': 34392, 'loss/train': 2.1667444705963135}
-03/05/2022 05:53:05 - INFO - codeparrot_training - Step 34393: {'lr': 0.00044319200110219794, 'samples': 17609728, 'steps': 34393, 'loss/train': 1.8097416162490845}
-03/05/2022 05:53:07 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/05/2022 05:53:11 - INFO - codeparrot_training - Step 34394: {'lr': 0.000443188632928565, 'samples': 17610240, 'steps': 34394, 'loss/train': 1.1077992916107178}
-03/05/2022 05:53:14 - INFO - codeparrot_training - Step 34395: {'lr': 0.0004431852646678842, 'samples': 17610752, 'steps': 34395, 'loss/train': 2.0320076942443848}
-03/05/2022 05:53:15 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/05/2022 05:53:19 - INFO - codeparrot_training - Step 34396: {'lr': 0.00044318189632015716, 'samples': 17611264, 'steps': 34396, 'loss/train': 1.2975411415100098}
-03/05/2022 05:53:22 - INFO - codeparrot_training - Step 34397: {'lr': 0.0004431785278853853, 'samples': 17611776, 'steps': 34397, 'loss/train': 2.9047763347625732}
-03/05/2022 05:53:23 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/05/2022 05:53:27 - INFO - codeparrot_training - Step 34398: {'lr': 0.0004431751593635702, 'samples': 17612288, 'steps': 34398, 'loss/train': 1.077797770500183}
-03/05/2022 05:53:31 - INFO - codeparrot_training - Step 34399: {'lr': 0.00044317179075471335, 'samples': 17612800, 'steps': 34399, 'loss/train': 0.564679741859436}
-03/05/2022 05:53:31 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/05/2022 05:53:36 - INFO - codeparrot_training - Step 34400: {'lr': 0.00044316842205881625, 'samples': 17613312, 'steps': 34400, 'loss/train': 1.935970425605774}
-03/05/2022 05:53:39 - INFO - codeparrot_training - Step 34401: {'lr': 0.00044316505327588054, 'samples': 17613824, 'steps': 34401, 'loss/train': 2.5713207721710205}
-03/05/2022 05:53:39 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/05/2022 05:53:44 - INFO - codeparrot_training - Step 34402: {'lr': 0.00044316168440590757, 'samples': 17614336, 'steps': 34402, 'loss/train': 1.9616584777832031}
-03/05/2022 05:53:47 - INFO - codeparrot_training - Step 34403: {'lr': 0.00044315831544889886, 'samples': 17614848, 'steps': 34403, 'loss/train': 0.3963319957256317}
-03/05/2022 05:53:48 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/05/2022 05:53:53 - INFO - codeparrot_training - Step 34404: {'lr': 0.0004431549464048561, 'samples': 17615360, 'steps': 34404, 'loss/train': 2.0712599754333496}
-03/05/2022 05:53:56 - INFO - codeparrot_training - Step 34405: {'lr': 0.0004431515772737806, 'samples': 17615872, 'steps': 34405, 'loss/train': 1.9355063438415527}
-03/05/2022 05:53:57 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/05/2022 05:54:01 - INFO - codeparrot_training - Step 34406: {'lr': 0.000443148208055674, 'samples': 17616384, 'steps': 34406, 'loss/train': 1.78676438331604}
-03/05/2022 05:54:04 - INFO - codeparrot_training - Step 34407: {'lr': 0.0004431448387505379, 'samples': 17616896, 'steps': 34407, 'loss/train': 1.5852714776992798}
-03/05/2022 05:54:05 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/05/2022 05:54:10 - INFO - codeparrot_training - Step 34408: {'lr': 0.00044314146935837365, 'samples': 17617408, 'steps': 34408, 'loss/train': 2.192098617553711}
-03/05/2022 05:54:13 - INFO - codeparrot_training - Step 34409: {'lr': 0.0004431380998791828, 'samples': 17617920, 'steps': 34409, 'loss/train': 1.824895977973938}
-03/05/2022 05:54:14 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/05/2022 05:54:18 - INFO - codeparrot_training - Step 34410: {'lr': 0.0004431347303129669, 'samples': 17618432, 'steps': 34410, 'loss/train': 1.9701175689697266}
-03/05/2022 05:54:21 - INFO - codeparrot_training - Step 34411: {'lr': 0.00044313136065972754, 'samples': 17618944, 'steps': 34411, 'loss/train': 0.8751137852668762}
-03/05/2022 05:54:22 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/05/2022 05:54:27 - INFO - codeparrot_training - Step 34412: {'lr': 0.0004431279909194661, 'samples': 17619456, 'steps': 34412, 'loss/train': 1.698349118232727}
-03/05/2022 05:54:30 - INFO - codeparrot_training - Step 34413: {'lr': 0.00044312462109218423, 'samples': 17619968, 'steps': 34413, 'loss/train': 1.0718051195144653}
-03/05/2022 05:54:31 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/05/2022 05:54:35 - INFO - codeparrot_training - Step 34414: {'lr': 0.0004431212511778834, 'samples': 17620480, 'steps': 34414, 'loss/train': 1.3571727275848389}
-03/05/2022 05:54:38 - INFO - codeparrot_training - Step 34415: {'lr': 0.000443117881176565, 'samples': 17620992, 'steps': 34415, 'loss/train': 1.6778255701065063}
-03/05/2022 05:54:39 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/05/2022 05:54:43 - INFO - codeparrot_training - Step 34416: {'lr': 0.00044311451108823075, 'samples': 17621504, 'steps': 34416, 'loss/train': 0.9632115364074707}
-03/05/2022 05:54:47 - INFO - codeparrot_training - Step 34417: {'lr': 0.00044311114091288205, 'samples': 17622016, 'steps': 34417, 'loss/train': 1.2326486110687256}
-03/05/2022 05:54:47 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/05/2022 05:54:52 - INFO - codeparrot_training - Step 34418: {'lr': 0.0004431077706505205, 'samples': 17622528, 'steps': 34418, 'loss/train': 1.995125412940979}
-03/05/2022 05:54:55 - INFO - codeparrot_training - Step 34419: {'lr': 0.0004431044003011475, 'samples': 17623040, 'steps': 34419, 'loss/train': 1.4261152744293213}
-03/05/2022 05:54:55 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/05/2022 05:55:00 - INFO - codeparrot_training - Step 34420: {'lr': 0.00044310102986476463, 'samples': 17623552, 'steps': 34420, 'loss/train': 1.9545880556106567}
-03/05/2022 05:55:03 - INFO - codeparrot_training - Step 34421: {'lr': 0.0004430976593413735, 'samples': 17624064, 'steps': 34421, 'loss/train': 1.7602641582489014}
-03/05/2022 05:55:04 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/05/2022 05:55:09 - INFO - codeparrot_training - Step 34422: {'lr': 0.0004430942887309755, 'samples': 17624576, 'steps': 34422, 'loss/train': 1.4113630056381226}
-03/05/2022 05:55:12 - INFO - codeparrot_training - Step 34423: {'lr': 0.00044309091803357216, 'samples': 17625088, 'steps': 34423, 'loss/train': 1.584171175956726}
-03/05/2022 05:55:12 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 05:55:17 - INFO - codeparrot_training - Step 34424: {'lr': 0.0004430875472491651, 'samples': 17625600, 'steps': 34424, 'loss/train': 1.815016746520996}
-03/05/2022 05:55:20 - INFO - codeparrot_training - Step 34425: {'lr': 0.0004430841763777557, 'samples': 17626112, 'steps': 34425, 'loss/train': 2.3161253929138184}
-03/05/2022 05:55:20 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/05/2022 05:55:25 - INFO - codeparrot_training - Step 34426: {'lr': 0.0004430808054193456, 'samples': 17626624, 'steps': 34426, 'loss/train': 1.9756784439086914}
-03/05/2022 05:55:28 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/05/2022 05:55:31 - INFO - codeparrot_training - Step 34427: {'lr': 0.00044307743437393623, 'samples': 17627136, 'steps': 34427, 'loss/train': 1.6235538721084595}
-03/05/2022 05:55:34 - INFO - codeparrot_training - Step 34428: {'lr': 0.0004430740632415292, 'samples': 17627648, 'steps': 34428, 'loss/train': 1.426363468170166}
-03/05/2022 05:55:37 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 05:55:39 - INFO - codeparrot_training - Step 34429: {'lr': 0.0004430706920221259, 'samples': 17628160, 'steps': 34429, 'loss/train': 1.7427458763122559}
-03/05/2022 05:55:42 - INFO - codeparrot_training - Step 34430: {'lr': 0.00044306732071572796, 'samples': 17628672, 'steps': 34430, 'loss/train': 2.6821250915527344}
-03/05/2022 05:55:45 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/05/2022 05:55:48 - INFO - codeparrot_training - Step 34431: {'lr': 0.00044306394932233694, 'samples': 17629184, 'steps': 34431, 'loss/train': 1.5240299701690674}
-03/05/2022 05:55:51 - INFO - codeparrot_training - Step 34432: {'lr': 0.0004430605778419542, 'samples': 17629696, 'steps': 34432, 'loss/train': 1.8086680173873901}
-03/05/2022 05:55:53 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/05/2022 05:55:56 - INFO - codeparrot_training - Step 34433: {'lr': 0.00044305720627458136, 'samples': 17630208, 'steps': 34433, 'loss/train': 1.9986445903778076}
-03/05/2022 05:55:59 - INFO - codeparrot_training - Step 34434: {'lr': 0.00044305383462022, 'samples': 17630720, 'steps': 34434, 'loss/train': 1.1556581258773804}
-03/05/2022 05:56:02 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/05/2022 05:56:04 - INFO - codeparrot_training - Step 34435: {'lr': 0.0004430504628788714, 'samples': 17631232, 'steps': 34435, 'loss/train': 1.813632845878601}
-03/05/2022 05:56:08 - INFO - codeparrot_training - Step 34436: {'lr': 0.0004430470910505373, 'samples': 17631744, 'steps': 34436, 'loss/train': 1.6379098892211914}
-03/05/2022 05:56:10 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 05:56:13 - INFO - codeparrot_training - Step 34437: {'lr': 0.00044304371913521926, 'samples': 17632256, 'steps': 34437, 'loss/train': 1.3613522052764893}
-03/05/2022 05:56:16 - INFO - codeparrot_training - Step 34438: {'lr': 0.0004430403471329186, 'samples': 17632768, 'steps': 34438, 'loss/train': 1.427315592765808}
-03/05/2022 05:56:19 - INFO - codeparrot_training - Skipping example with length 266 (seq_length=1024)
-03/05/2022 05:56:21 - INFO - codeparrot_training - Step 34439: {'lr': 0.0004430369750436369, 'samples': 17633280, 'steps': 34439, 'loss/train': 1.2265994548797607}
-03/05/2022 05:56:24 - INFO - codeparrot_training - Step 34440: {'lr': 0.0004430336028673758, 'samples': 17633792, 'steps': 34440, 'loss/train': 1.8094308376312256}
-03/05/2022 05:56:27 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 05:56:30 - INFO - codeparrot_training - Step 34441: {'lr': 0.00044303023060413677, 'samples': 17634304, 'steps': 34441, 'loss/train': 1.7392663955688477}
-03/05/2022 05:56:33 - INFO - codeparrot_training - Step 34442: {'lr': 0.0004430268582539212, 'samples': 17634816, 'steps': 34442, 'loss/train': 0.80379718542099}
-03/05/2022 05:56:35 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/05/2022 05:56:38 - INFO - codeparrot_training - Step 34443: {'lr': 0.0004430234858167308, 'samples': 17635328, 'steps': 34443, 'loss/train': 0.9262971878051758}
-03/05/2022 05:56:41 - INFO - codeparrot_training - Step 34444: {'lr': 0.000443020113292567, 'samples': 17635840, 'steps': 34444, 'loss/train': 0.8795902132987976}
-03/05/2022 05:56:44 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/05/2022 05:56:47 - INFO - codeparrot_training - Step 34445: {'lr': 0.0004430167406814312, 'samples': 17636352, 'steps': 34445, 'loss/train': 1.2451926469802856}
-03/05/2022 05:56:50 - INFO - codeparrot_training - Step 34446: {'lr': 0.0004430133679833251, 'samples': 17636864, 'steps': 34446, 'loss/train': 1.6805188655853271}
-03/05/2022 05:56:52 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/05/2022 05:56:55 - INFO - codeparrot_training - Step 34447: {'lr': 0.00044300999519825016, 'samples': 17637376, 'steps': 34447, 'loss/train': 1.478570580482483}
-03/05/2022 05:56:58 - INFO - codeparrot_training - Step 34448: {'lr': 0.00044300662232620784, 'samples': 17637888, 'steps': 34448, 'loss/train': 2.1637840270996094}
-03/05/2022 05:57:00 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/05/2022 05:57:03 - INFO - codeparrot_training - Step 34449: {'lr': 0.0004430032493671998, 'samples': 17638400, 'steps': 34449, 'loss/train': 2.482656478881836}
-03/05/2022 05:57:07 - INFO - codeparrot_training - Step 34450: {'lr': 0.0004429998763212274, 'samples': 17638912, 'steps': 34450, 'loss/train': 1.4891188144683838}
-03/05/2022 05:57:08 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/05/2022 05:57:12 - INFO - codeparrot_training - Step 34451: {'lr': 0.00044299650318829233, 'samples': 17639424, 'steps': 34451, 'loss/train': 1.8637944459915161}
-03/05/2022 05:57:15 - INFO - codeparrot_training - Step 34452: {'lr': 0.0004429931299683959, 'samples': 17639936, 'steps': 34452, 'loss/train': 1.5967692136764526}
-03/05/2022 05:57:17 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 05:57:20 - INFO - codeparrot_training - Step 34453: {'lr': 0.0004429897566615398, 'samples': 17640448, 'steps': 34453, 'loss/train': 1.0530067682266235}
-03/05/2022 05:57:24 - INFO - codeparrot_training - Step 34454: {'lr': 0.0004429863832677255, 'samples': 17640960, 'steps': 34454, 'loss/train': 2.082125186920166}
-03/05/2022 05:57:26 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/05/2022 05:57:29 - INFO - codeparrot_training - Step 34455: {'lr': 0.0004429830097869545, 'samples': 17641472, 'steps': 34455, 'loss/train': 0.6839268207550049}
-03/05/2022 05:57:32 - INFO - codeparrot_training - Step 34456: {'lr': 0.0004429796362192283, 'samples': 17641984, 'steps': 34456, 'loss/train': 1.8771288394927979}
-03/05/2022 05:57:34 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/05/2022 05:57:38 - INFO - codeparrot_training - Step 34457: {'lr': 0.0004429762625645485, 'samples': 17642496, 'steps': 34457, 'loss/train': 2.4734363555908203}
-03/05/2022 05:57:41 - INFO - codeparrot_training - Step 34458: {'lr': 0.0004429728888229166, 'samples': 17643008, 'steps': 34458, 'loss/train': 2.0212860107421875}
-03/05/2022 05:57:43 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/05/2022 05:57:46 - INFO - codeparrot_training - Step 34459: {'lr': 0.000442969514994334, 'samples': 17643520, 'steps': 34459, 'loss/train': 2.442194938659668}
-03/05/2022 05:57:49 - INFO - codeparrot_training - Step 34460: {'lr': 0.0004429661410788024, 'samples': 17644032, 'steps': 34460, 'loss/train': 1.4718222618103027}
-03/05/2022 05:57:51 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/05/2022 05:57:54 - INFO - codeparrot_training - Step 34461: {'lr': 0.00044296276707632323, 'samples': 17644544, 'steps': 34461, 'loss/train': 1.0123987197875977}
-03/05/2022 05:57:58 - INFO - codeparrot_training - Step 34462: {'lr': 0.000442959392986898, 'samples': 17645056, 'steps': 34462, 'loss/train': 1.391916275024414}
-03/05/2022 05:57:59 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/05/2022 05:58:03 - INFO - codeparrot_training - Step 34463: {'lr': 0.0004429560188105282, 'samples': 17645568, 'steps': 34463, 'loss/train': 1.7734508514404297}
-03/05/2022 05:58:06 - INFO - codeparrot_training - Step 34464: {'lr': 0.00044295264454721544, 'samples': 17646080, 'steps': 34464, 'loss/train': 1.8301419019699097}
-03/05/2022 05:58:09 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 05:58:11 - INFO - codeparrot_training - Step 34465: {'lr': 0.0004429492701969612, 'samples': 17646592, 'steps': 34465, 'loss/train': 1.7986633777618408}
-03/05/2022 05:58:15 - INFO - codeparrot_training - Step 34466: {'lr': 0.00044294589575976696, 'samples': 17647104, 'steps': 34466, 'loss/train': 1.6322604417800903}
-03/05/2022 05:58:17 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 05:58:20 - INFO - codeparrot_training - Step 34467: {'lr': 0.00044294252123563434, 'samples': 17647616, 'steps': 34467, 'loss/train': 1.8993381261825562}
-03/05/2022 05:58:23 - INFO - codeparrot_training - Step 34468: {'lr': 0.00044293914662456475, 'samples': 17648128, 'steps': 34468, 'loss/train': 2.0840775966644287}
-03/05/2022 05:58:25 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 05:58:28 - INFO - codeparrot_training - Step 34469: {'lr': 0.00044293577192655977, 'samples': 17648640, 'steps': 34469, 'loss/train': 1.587438702583313}
-03/05/2022 05:58:32 - INFO - codeparrot_training - Step 34470: {'lr': 0.0004429323971416209, 'samples': 17649152, 'steps': 34470, 'loss/train': 1.7007900476455688}
-03/05/2022 05:58:34 - INFO - codeparrot_training - Skipping example with length 920 (seq_length=1024)
-03/05/2022 05:58:37 - INFO - codeparrot_training - Step 34471: {'lr': 0.0004429290222697497, 'samples': 17649664, 'steps': 34471, 'loss/train': 1.5698492527008057}
-03/05/2022 05:58:40 - INFO - codeparrot_training - Step 34472: {'lr': 0.0004429256473109476, 'samples': 17650176, 'steps': 34472, 'loss/train': 1.1360188722610474}
-03/05/2022 05:58:42 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/05/2022 05:58:45 - INFO - codeparrot_training - Step 34473: {'lr': 0.0004429222722652162, 'samples': 17650688, 'steps': 34473, 'loss/train': 2.3210785388946533}
-03/05/2022 05:58:48 - INFO - codeparrot_training - Step 34474: {'lr': 0.0004429188971325571, 'samples': 17651200, 'steps': 34474, 'loss/train': 1.236336350440979}
-03/05/2022 05:58:51 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 05:58:54 - INFO - codeparrot_training - Step 34475: {'lr': 0.00044291552191297155, 'samples': 17651712, 'steps': 34475, 'loss/train': 2.191598415374756}
-03/05/2022 05:58:57 - INFO - codeparrot_training - Step 34476: {'lr': 0.0004429121466064614, 'samples': 17652224, 'steps': 34476, 'loss/train': 1.911533236503601}
-03/05/2022 05:58:59 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/05/2022 05:59:02 - INFO - codeparrot_training - Step 34477: {'lr': 0.0004429087712130279, 'samples': 17652736, 'steps': 34477, 'loss/train': 2.01478910446167}
-03/05/2022 05:59:05 - INFO - codeparrot_training - Step 34478: {'lr': 0.00044290539573267276, 'samples': 17653248, 'steps': 34478, 'loss/train': 2.3136849403381348}
-03/05/2022 05:59:07 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 05:59:11 - INFO - codeparrot_training - Step 34479: {'lr': 0.00044290202016539736, 'samples': 17653760, 'steps': 34479, 'loss/train': 2.9014499187469482}
-03/05/2022 05:59:14 - INFO - codeparrot_training - Step 34480: {'lr': 0.0004428986445112033, 'samples': 17654272, 'steps': 34480, 'loss/train': 1.076346516609192}
-03/05/2022 05:59:16 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/05/2022 05:59:19 - INFO - codeparrot_training - Step 34481: {'lr': 0.00044289526877009213, 'samples': 17654784, 'steps': 34481, 'loss/train': 1.359923005104065}
-03/05/2022 05:59:22 - INFO - codeparrot_training - Step 34482: {'lr': 0.00044289189294206534, 'samples': 17655296, 'steps': 34482, 'loss/train': 1.3713167905807495}
-03/05/2022 05:59:25 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 05:59:28 - INFO - codeparrot_training - Step 34483: {'lr': 0.0004428885170271244, 'samples': 17655808, 'steps': 34483, 'loss/train': 2.030492067337036}
-03/05/2022 05:59:31 - INFO - codeparrot_training - Step 34484: {'lr': 0.0004428851410252709, 'samples': 17656320, 'steps': 34484, 'loss/train': 2.152890205383301}
-03/05/2022 05:59:33 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/05/2022 05:59:36 - INFO - codeparrot_training - Step 34485: {'lr': 0.0004428817649365063, 'samples': 17656832, 'steps': 34485, 'loss/train': 2.473890542984009}
-03/05/2022 05:59:39 - INFO - codeparrot_training - Step 34486: {'lr': 0.0004428783887608321, 'samples': 17657344, 'steps': 34486, 'loss/train': 1.3030574321746826}
-03/05/2022 05:59:42 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/05/2022 05:59:44 - INFO - codeparrot_training - Step 34487: {'lr': 0.00044287501249824996, 'samples': 17657856, 'steps': 34487, 'loss/train': 1.1493401527404785}
-03/05/2022 05:59:48 - INFO - codeparrot_training - Step 34488: {'lr': 0.0004428716361487613, 'samples': 17658368, 'steps': 34488, 'loss/train': 1.7590959072113037}
-03/05/2022 05:59:50 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/05/2022 05:59:53 - INFO - codeparrot_training - Step 34489: {'lr': 0.0004428682597123677, 'samples': 17658880, 'steps': 34489, 'loss/train': 0.6687783002853394}
-03/05/2022 05:59:56 - INFO - codeparrot_training - Step 34490: {'lr': 0.0004428648831890705, 'samples': 17659392, 'steps': 34490, 'loss/train': 1.8729727268218994}
-03/05/2022 05:59:59 - INFO - codeparrot_training - Step 34491: {'lr': 0.0004428615065788715, 'samples': 17659904, 'steps': 34491, 'loss/train': 1.6569838523864746}
-03/05/2022 06:00:00 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/05/2022 06:00:05 - INFO - codeparrot_training - Step 34492: {'lr': 0.00044285812988177197, 'samples': 17660416, 'steps': 34492, 'loss/train': 1.2252579927444458}
-03/05/2022 06:00:08 - INFO - codeparrot_training - Step 34493: {'lr': 0.0004428547530977736, 'samples': 17660928, 'steps': 34493, 'loss/train': 1.933573842048645}
-03/05/2022 06:00:08 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/05/2022 06:00:13 - INFO - codeparrot_training - Step 34494: {'lr': 0.0004428513762268779, 'samples': 17661440, 'steps': 34494, 'loss/train': 1.1966859102249146}
-03/05/2022 06:00:16 - INFO - codeparrot_training - Step 34495: {'lr': 0.00044284799926908627, 'samples': 17661952, 'steps': 34495, 'loss/train': 1.6820588111877441}
-03/05/2022 06:00:17 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 06:00:22 - INFO - codeparrot_training - Step 34496: {'lr': 0.0004428446222244004, 'samples': 17662464, 'steps': 34496, 'loss/train': 1.6945387125015259}
-03/05/2022 06:00:25 - INFO - codeparrot_training - Step 34497: {'lr': 0.0004428412450928216, 'samples': 17662976, 'steps': 34497, 'loss/train': 1.37456476688385}
-03/05/2022 06:00:25 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/05/2022 06:00:30 - INFO - codeparrot_training - Step 34498: {'lr': 0.00044283786787435156, 'samples': 17663488, 'steps': 34498, 'loss/train': 1.9964081048965454}
-03/05/2022 06:00:33 - INFO - codeparrot_training - Step 34499: {'lr': 0.0004428344905689917, 'samples': 17664000, 'steps': 34499, 'loss/train': 1.551255464553833}
-03/05/2022 06:00:34 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/05/2022 06:00:38 - INFO - codeparrot_training - Step 34500: {'lr': 0.0004428311131767437, 'samples': 17664512, 'steps': 34500, 'loss/train': 1.8067249059677124}
-03/05/2022 06:00:42 - INFO - codeparrot_training - Step 34501: {'lr': 0.0004428277356976089, 'samples': 17665024, 'steps': 34501, 'loss/train': 2.3206627368927}
-03/05/2022 06:00:42 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 06:00:47 - INFO - codeparrot_training - Step 34502: {'lr': 0.0004428243581315889, 'samples': 17665536, 'steps': 34502, 'loss/train': 1.9363330602645874}
-03/05/2022 06:00:50 - INFO - codeparrot_training - Step 34503: {'lr': 0.0004428209804786853, 'samples': 17666048, 'steps': 34503, 'loss/train': 1.4331533908843994}
-03/05/2022 06:00:51 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/05/2022 06:00:55 - INFO - codeparrot_training - Step 34504: {'lr': 0.0004428176027388995, 'samples': 17666560, 'steps': 34504, 'loss/train': 1.2737483978271484}
-03/05/2022 06:00:58 - INFO - codeparrot_training - Step 34505: {'lr': 0.0004428142249122331, 'samples': 17667072, 'steps': 34505, 'loss/train': 1.9564390182495117}
-03/05/2022 06:00:59 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/05/2022 06:01:04 - INFO - codeparrot_training - Step 34506: {'lr': 0.00044281084699868747, 'samples': 17667584, 'steps': 34506, 'loss/train': 2.270721435546875}
-03/05/2022 06:01:07 - INFO - codeparrot_training - Step 34507: {'lr': 0.0004428074689982643, 'samples': 17668096, 'steps': 34507, 'loss/train': 1.6944383382797241}
-03/05/2022 06:01:08 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/05/2022 06:01:12 - INFO - codeparrot_training - Step 34508: {'lr': 0.0004428040909109651, 'samples': 17668608, 'steps': 34508, 'loss/train': 1.8433403968811035}
-03/05/2022 06:01:15 - INFO - codeparrot_training - Step 34509: {'lr': 0.00044280071273679133, 'samples': 17669120, 'steps': 34509, 'loss/train': 0.9025130867958069}
-03/05/2022 06:01:16 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/05/2022 06:01:21 - INFO - codeparrot_training - Step 34510: {'lr': 0.00044279733447574456, 'samples': 17669632, 'steps': 34510, 'loss/train': 1.6995915174484253}
-03/05/2022 06:01:24 - INFO - codeparrot_training - Step 34511: {'lr': 0.00044279395612782625, 'samples': 17670144, 'steps': 34511, 'loss/train': 1.9385913610458374}
-03/05/2022 06:01:24 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/05/2022 06:01:29 - INFO - codeparrot_training - Step 34512: {'lr': 0.0004427905776930379, 'samples': 17670656, 'steps': 34512, 'loss/train': 2.012213945388794}
-03/05/2022 06:01:32 - INFO - codeparrot_training - Step 34513: {'lr': 0.0004427871991713812, 'samples': 17671168, 'steps': 34513, 'loss/train': 2.0768423080444336}
-03/05/2022 06:01:32 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/05/2022 06:01:37 - INFO - codeparrot_training - Step 34514: {'lr': 0.0004427838205628575, 'samples': 17671680, 'steps': 34514, 'loss/train': 0.9320793747901917}
-03/05/2022 06:01:41 - INFO - codeparrot_training - Step 34515: {'lr': 0.0004427804418674684, 'samples': 17672192, 'steps': 34515, 'loss/train': 1.0418295860290527}
-03/05/2022 06:01:41 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/05/2022 06:01:46 - INFO - codeparrot_training - Step 34516: {'lr': 0.00044277706308521543, 'samples': 17672704, 'steps': 34516, 'loss/train': 2.046491861343384}
-03/05/2022 06:01:49 - INFO - codeparrot_training - Step 34517: {'lr': 0.0004427736842161001, 'samples': 17673216, 'steps': 34517, 'loss/train': 0.33359941840171814}
-03/05/2022 06:01:49 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/05/2022 06:01:55 - INFO - codeparrot_training - Step 34518: {'lr': 0.00044277030526012386, 'samples': 17673728, 'steps': 34518, 'loss/train': 2.0205187797546387}
-03/05/2022 06:01:58 - INFO - codeparrot_training - Step 34519: {'lr': 0.0004427669262172883, 'samples': 17674240, 'steps': 34519, 'loss/train': 2.1777687072753906}
-03/05/2022 06:02:00 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/05/2022 06:02:03 - INFO - codeparrot_training - Step 34520: {'lr': 0.000442763547087595, 'samples': 17674752, 'steps': 34520, 'loss/train': 1.5915614366531372}
-03/05/2022 06:02:06 - INFO - codeparrot_training - Step 34521: {'lr': 0.00044276016787104535, 'samples': 17675264, 'steps': 34521, 'loss/train': 2.315542221069336}
-03/05/2022 06:02:09 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/05/2022 06:02:12 - INFO - codeparrot_training - Step 34522: {'lr': 0.000442756788567641, 'samples': 17675776, 'steps': 34522, 'loss/train': 1.3581876754760742}
-03/05/2022 06:02:15 - INFO - codeparrot_training - Step 34523: {'lr': 0.0004427534091773834, 'samples': 17676288, 'steps': 34523, 'loss/train': 1.4427965879440308}
-03/05/2022 06:02:17 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 06:02:20 - INFO - codeparrot_training - Step 34524: {'lr': 0.00044275002970027403, 'samples': 17676800, 'steps': 34524, 'loss/train': 0.5988059043884277}
-03/05/2022 06:02:23 - INFO - codeparrot_training - Step 34525: {'lr': 0.00044274665013631457, 'samples': 17677312, 'steps': 34525, 'loss/train': 2.2581124305725098}
-03/05/2022 06:02:26 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/05/2022 06:02:29 - INFO - codeparrot_training - Step 34526: {'lr': 0.0004427432704855064, 'samples': 17677824, 'steps': 34526, 'loss/train': 2.050006151199341}
-03/05/2022 06:02:32 - INFO - codeparrot_training - Step 34527: {'lr': 0.000442739890747851, 'samples': 17678336, 'steps': 34527, 'loss/train': 1.5434801578521729}
-03/05/2022 06:02:34 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/05/2022 06:02:37 - INFO - codeparrot_training - Step 34528: {'lr': 0.0004427365109233502, 'samples': 17678848, 'steps': 34528, 'loss/train': 1.1500861644744873}
-03/05/2022 06:02:40 - INFO - codeparrot_training - Step 34529: {'lr': 0.00044273313101200507, 'samples': 17679360, 'steps': 34529, 'loss/train': 1.921228289604187}
-03/05/2022 06:02:42 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/05/2022 06:02:45 - INFO - codeparrot_training - Step 34530: {'lr': 0.00044272975101381754, 'samples': 17679872, 'steps': 34530, 'loss/train': 1.23170006275177}
-03/05/2022 06:02:49 - INFO - codeparrot_training - Step 34531: {'lr': 0.0004427263709287889, 'samples': 17680384, 'steps': 34531, 'loss/train': 1.8685948848724365}
-03/05/2022 06:02:51 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/05/2022 06:02:54 - INFO - codeparrot_training - Step 34532: {'lr': 0.00044272299075692067, 'samples': 17680896, 'steps': 34532, 'loss/train': 1.5906106233596802}
-03/05/2022 06:02:57 - INFO - codeparrot_training - Step 34533: {'lr': 0.0004427196104982145, 'samples': 17681408, 'steps': 34533, 'loss/train': 0.545563280582428}
-03/05/2022 06:02:59 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/05/2022 06:03:02 - INFO - codeparrot_training - Step 34534: {'lr': 0.0004427162301526718, 'samples': 17681920, 'steps': 34534, 'loss/train': 1.0510560274124146}
-03/05/2022 06:03:06 - INFO - codeparrot_training - Step 34535: {'lr': 0.0004427128497202941, 'samples': 17682432, 'steps': 34535, 'loss/train': 1.3369512557983398}
-03/05/2022 06:03:08 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/05/2022 06:03:11 - INFO - codeparrot_training - Step 34536: {'lr': 0.00044270946920108305, 'samples': 17682944, 'steps': 34536, 'loss/train': 1.617935299873352}
-03/05/2022 06:03:14 - INFO - codeparrot_training - Step 34537: {'lr': 0.00044270608859504006, 'samples': 17683456, 'steps': 34537, 'loss/train': 0.6327489614486694}
-03/05/2022 06:03:16 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/05/2022 06:03:19 - INFO - codeparrot_training - Step 34538: {'lr': 0.0004427027079021667, 'samples': 17683968, 'steps': 34538, 'loss/train': 0.8658568263053894}
-03/05/2022 06:03:22 - INFO - codeparrot_training - Step 34539: {'lr': 0.0004426993271224645, 'samples': 17684480, 'steps': 34539, 'loss/train': 1.9620453119277954}
-03/05/2022 06:03:24 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/05/2022 06:03:28 - INFO - codeparrot_training - Step 34540: {'lr': 0.0004426959462559349, 'samples': 17684992, 'steps': 34540, 'loss/train': 1.5879038572311401}
-03/05/2022 06:03:31 - INFO - codeparrot_training - Step 34541: {'lr': 0.0004426925653025795, 'samples': 17685504, 'steps': 34541, 'loss/train': 2.1064929962158203}
-03/05/2022 06:03:33 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/05/2022 06:03:36 - INFO - codeparrot_training - Step 34542: {'lr': 0.0004426891842623998, 'samples': 17686016, 'steps': 34542, 'loss/train': 1.9624521732330322}
-03/05/2022 06:03:39 - INFO - codeparrot_training - Step 34543: {'lr': 0.0004426858031353973, 'samples': 17686528, 'steps': 34543, 'loss/train': 2.1045734882354736}
-03/05/2022 06:03:41 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/05/2022 06:03:44 - INFO - codeparrot_training - Step 34544: {'lr': 0.0004426824219215736, 'samples': 17687040, 'steps': 34544, 'loss/train': 1.2236227989196777}
-03/05/2022 06:03:48 - INFO - codeparrot_training - Step 34545: {'lr': 0.00044267904062093014, 'samples': 17687552, 'steps': 34545, 'loss/train': 1.5783729553222656}
-03/05/2022 06:03:49 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/05/2022 06:03:53 - INFO - codeparrot_training - Step 34546: {'lr': 0.0004426756592334685, 'samples': 17688064, 'steps': 34546, 'loss/train': 1.6775139570236206}
-03/05/2022 06:03:56 - INFO - codeparrot_training - Step 34547: {'lr': 0.0004426722777591902, 'samples': 17688576, 'steps': 34547, 'loss/train': 1.333911657333374}
-03/05/2022 06:03:58 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 06:04:01 - INFO - codeparrot_training - Step 34548: {'lr': 0.00044266889619809665, 'samples': 17689088, 'steps': 34548, 'loss/train': 1.4337565898895264}
-03/05/2022 06:04:05 - INFO - codeparrot_training - Step 34549: {'lr': 0.00044266551455018953, 'samples': 17689600, 'steps': 34549, 'loss/train': 1.3708990812301636}
-03/05/2022 06:04:06 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/05/2022 06:04:10 - INFO - codeparrot_training - Step 34550: {'lr': 0.0004426621328154703, 'samples': 17690112, 'steps': 34550, 'loss/train': 1.552330493927002}
-03/05/2022 06:04:13 - INFO - codeparrot_training - Step 34551: {'lr': 0.0004426587509939405, 'samples': 17690624, 'steps': 34551, 'loss/train': 1.8199992179870605}
-03/05/2022 06:04:14 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/05/2022 06:04:18 - INFO - codeparrot_training - Step 34552: {'lr': 0.0004426553690856016, 'samples': 17691136, 'steps': 34552, 'loss/train': 0.3973861336708069}
-03/05/2022 06:04:22 - INFO - codeparrot_training - Step 34553: {'lr': 0.0004426519870904552, 'samples': 17691648, 'steps': 34553, 'loss/train': 1.7761049270629883}
-03/05/2022 06:04:23 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/05/2022 06:04:27 - INFO - codeparrot_training - Step 34554: {'lr': 0.0004426486050085028, 'samples': 17692160, 'steps': 34554, 'loss/train': 1.829074740409851}
-03/05/2022 06:04:30 - INFO - codeparrot_training - Step 34555: {'lr': 0.0004426452228397458, 'samples': 17692672, 'steps': 34555, 'loss/train': 0.055017683655023575}
-03/05/2022 06:04:31 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/05/2022 06:04:35 - INFO - codeparrot_training - Step 34556: {'lr': 0.000442641840584186, 'samples': 17693184, 'steps': 34556, 'loss/train': 1.1627459526062012}
-03/05/2022 06:04:38 - INFO - codeparrot_training - Step 34557: {'lr': 0.00044263845824182467, 'samples': 17693696, 'steps': 34557, 'loss/train': 2.321988582611084}
-03/05/2022 06:04:40 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/05/2022 06:04:44 - INFO - codeparrot_training - Step 34558: {'lr': 0.0004426350758126634, 'samples': 17694208, 'steps': 34558, 'loss/train': 1.952880859375}
-03/05/2022 06:04:47 - INFO - codeparrot_training - Step 34559: {'lr': 0.0004426316932967038, 'samples': 17694720, 'steps': 34559, 'loss/train': 1.6647371053695679}
-03/05/2022 06:04:48 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/05/2022 06:04:52 - INFO - codeparrot_training - Step 34560: {'lr': 0.0004426283106939473, 'samples': 17695232, 'steps': 34560, 'loss/train': 0.7882624864578247}
-03/05/2022 06:04:55 - INFO - codeparrot_training - Step 34561: {'lr': 0.00044262492800439547, 'samples': 17695744, 'steps': 34561, 'loss/train': 1.3706730604171753}
-03/05/2022 06:04:56 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 06:05:01 - INFO - codeparrot_training - Step 34562: {'lr': 0.00044262154522804986, 'samples': 17696256, 'steps': 34562, 'loss/train': 0.4932713806629181}
-03/05/2022 06:05:04 - INFO - codeparrot_training - Step 34563: {'lr': 0.00044261816236491186, 'samples': 17696768, 'steps': 34563, 'loss/train': 1.73300039768219}
-03/05/2022 06:05:05 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/05/2022 06:05:09 - INFO - codeparrot_training - Step 34564: {'lr': 0.00044261477941498316, 'samples': 17697280, 'steps': 34564, 'loss/train': 1.480662226676941}
-03/05/2022 06:05:12 - INFO - codeparrot_training - Step 34565: {'lr': 0.0004426113963782652, 'samples': 17697792, 'steps': 34565, 'loss/train': 1.805383324623108}
-03/05/2022 06:05:14 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/05/2022 06:05:18 - INFO - codeparrot_training - Step 34566: {'lr': 0.00044260801325475953, 'samples': 17698304, 'steps': 34566, 'loss/train': 2.316495180130005}
-03/05/2022 06:05:21 - INFO - codeparrot_training - Step 34567: {'lr': 0.0004426046300444676, 'samples': 17698816, 'steps': 34567, 'loss/train': 1.5681407451629639}
-03/05/2022 06:05:22 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 06:05:26 - INFO - codeparrot_training - Step 34568: {'lr': 0.000442601246747391, 'samples': 17699328, 'steps': 34568, 'loss/train': 1.744669795036316}
-03/05/2022 06:05:29 - INFO - codeparrot_training - Step 34569: {'lr': 0.0004425978633635313, 'samples': 17699840, 'steps': 34569, 'loss/train': 1.7447888851165771}
-03/05/2022 06:05:31 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/05/2022 06:05:34 - INFO - codeparrot_training - Step 34570: {'lr': 0.0004425944798928899, 'samples': 17700352, 'steps': 34570, 'loss/train': 1.3900948762893677}
-03/05/2022 06:05:38 - INFO - codeparrot_training - Step 34571: {'lr': 0.0004425910963354685, 'samples': 17700864, 'steps': 34571, 'loss/train': 1.8431289196014404}
-03/05/2022 06:05:39 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/05/2022 06:05:43 - INFO - codeparrot_training - Step 34572: {'lr': 0.0004425877126912685, 'samples': 17701376, 'steps': 34572, 'loss/train': 1.8359674215316772}
-03/05/2022 06:05:46 - INFO - codeparrot_training - Step 34573: {'lr': 0.00044258432896029145, 'samples': 17701888, 'steps': 34573, 'loss/train': 1.255735993385315}
-03/05/2022 06:05:48 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/05/2022 06:05:52 - INFO - codeparrot_training - Step 34574: {'lr': 0.00044258094514253876, 'samples': 17702400, 'steps': 34574, 'loss/train': 1.9837300777435303}
-03/05/2022 06:05:55 - INFO - codeparrot_training - Step 34575: {'lr': 0.00044257756123801216, 'samples': 17702912, 'steps': 34575, 'loss/train': 0.6697525382041931}
-03/05/2022 06:05:56 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/05/2022 06:06:00 - INFO - codeparrot_training - Step 34576: {'lr': 0.0004425741772467131, 'samples': 17703424, 'steps': 34576, 'loss/train': 1.7515296936035156}
-03/05/2022 06:06:03 - INFO - codeparrot_training - Step 34577: {'lr': 0.0004425707931686431, 'samples': 17703936, 'steps': 34577, 'loss/train': 1.8513121604919434}
-03/05/2022 06:06:05 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/05/2022 06:06:09 - INFO - codeparrot_training - Step 34578: {'lr': 0.00044256740900380364, 'samples': 17704448, 'steps': 34578, 'loss/train': 1.9542770385742188}
-03/05/2022 06:06:12 - INFO - codeparrot_training - Step 34579: {'lr': 0.0004425640247521963, 'samples': 17704960, 'steps': 34579, 'loss/train': 1.866998314857483}
-03/05/2022 06:06:14 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/05/2022 06:06:17 - INFO - codeparrot_training - Step 34580: {'lr': 0.00044256064041382255, 'samples': 17705472, 'steps': 34580, 'loss/train': 1.4035999774932861}
-03/05/2022 06:06:20 - INFO - codeparrot_training - Step 34581: {'lr': 0.0004425572559886839, 'samples': 17705984, 'steps': 34581, 'loss/train': 2.0088398456573486}
-03/05/2022 06:06:23 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/05/2022 06:06:26 - INFO - codeparrot_training - Step 34582: {'lr': 0.00044255387147678206, 'samples': 17706496, 'steps': 34582, 'loss/train': 1.5861475467681885}
-03/05/2022 06:06:29 - INFO - codeparrot_training - Step 34583: {'lr': 0.0004425504868781183, 'samples': 17707008, 'steps': 34583, 'loss/train': 1.9714163541793823}
-03/05/2022 06:06:31 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 06:06:34 - INFO - codeparrot_training - Step 34584: {'lr': 0.0004425471021926943, 'samples': 17707520, 'steps': 34584, 'loss/train': 2.1568093299865723}
-03/05/2022 06:06:37 - INFO - codeparrot_training - Step 34585: {'lr': 0.0004425437174205115, 'samples': 17708032, 'steps': 34585, 'loss/train': 1.5789313316345215}
-03/05/2022 06:06:40 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 06:06:43 - INFO - codeparrot_training - Step 34586: {'lr': 0.00044254033256157154, 'samples': 17708544, 'steps': 34586, 'loss/train': 1.2729425430297852}
-03/05/2022 06:06:46 - INFO - codeparrot_training - Step 34587: {'lr': 0.0004425369476158759, 'samples': 17709056, 'steps': 34587, 'loss/train': 1.4998366832733154}
-03/05/2022 06:06:48 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/05/2022 06:06:51 - INFO - codeparrot_training - Step 34588: {'lr': 0.000442533562583426, 'samples': 17709568, 'steps': 34588, 'loss/train': 1.6784372329711914}
-03/05/2022 06:06:54 - INFO - codeparrot_training - Step 34589: {'lr': 0.00044253017746422355, 'samples': 17710080, 'steps': 34589, 'loss/train': 2.341175079345703}
-03/05/2022 06:06:56 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 06:07:00 - INFO - codeparrot_training - Step 34590: {'lr': 0.00044252679225826984, 'samples': 17710592, 'steps': 34590, 'loss/train': 1.6452728509902954}
-03/05/2022 06:07:03 - INFO - codeparrot_training - Step 34591: {'lr': 0.0004425234069655666, 'samples': 17711104, 'steps': 34591, 'loss/train': 1.3519376516342163}
-03/05/2022 06:07:05 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/05/2022 06:07:08 - INFO - codeparrot_training - Step 34592: {'lr': 0.0004425200215861153, 'samples': 17711616, 'steps': 34592, 'loss/train': 0.897087037563324}
-03/05/2022 06:07:11 - INFO - codeparrot_training - Step 34593: {'lr': 0.00044251663611991743, 'samples': 17712128, 'steps': 34593, 'loss/train': 0.7061640620231628}
-03/05/2022 06:07:13 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/05/2022 06:07:16 - INFO - codeparrot_training - Step 34594: {'lr': 0.0004425132505669745, 'samples': 17712640, 'steps': 34594, 'loss/train': 1.88649320602417}
-03/05/2022 06:07:19 - INFO - codeparrot_training - Step 34595: {'lr': 0.00044250986492728805, 'samples': 17713152, 'steps': 34595, 'loss/train': 1.4049944877624512}
-03/05/2022 06:07:22 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/05/2022 06:07:25 - INFO - codeparrot_training - Step 34596: {'lr': 0.0004425064792008597, 'samples': 17713664, 'steps': 34596, 'loss/train': 0.05822386220097542}
-03/05/2022 06:07:28 - INFO - codeparrot_training - Step 34597: {'lr': 0.0004425030933876909, 'samples': 17714176, 'steps': 34597, 'loss/train': 1.9433174133300781}
-03/05/2022 06:07:30 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 06:07:33 - INFO - codeparrot_training - Step 34598: {'lr': 0.0004424997074877831, 'samples': 17714688, 'steps': 34598, 'loss/train': 1.0996251106262207}
-03/05/2022 06:07:36 - INFO - codeparrot_training - Step 34599: {'lr': 0.00044249632150113806, 'samples': 17715200, 'steps': 34599, 'loss/train': 2.2290470600128174}
-03/05/2022 06:07:38 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/05/2022 06:07:42 - INFO - codeparrot_training - Step 34600: {'lr': 0.000442492935427757, 'samples': 17715712, 'steps': 34600, 'loss/train': 1.7642180919647217}
-03/05/2022 06:07:45 - INFO - codeparrot_training - Step 34601: {'lr': 0.00044248954926764164, 'samples': 17716224, 'steps': 34601, 'loss/train': 1.7567397356033325}
-03/05/2022 06:07:47 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/05/2022 06:07:50 - INFO - codeparrot_training - Step 34602: {'lr': 0.0004424861630207935, 'samples': 17716736, 'steps': 34602, 'loss/train': 2.0870018005371094}
-03/05/2022 06:07:53 - INFO - codeparrot_training - Step 34603: {'lr': 0.00044248277668721396, 'samples': 17717248, 'steps': 34603, 'loss/train': 1.5389583110809326}
-03/05/2022 06:07:55 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/05/2022 06:07:59 - INFO - codeparrot_training - Step 34604: {'lr': 0.00044247939026690475, 'samples': 17717760, 'steps': 34604, 'loss/train': 1.2625257968902588}
-03/05/2022 06:08:02 - INFO - codeparrot_training - Step 34605: {'lr': 0.0004424760037598673, 'samples': 17718272, 'steps': 34605, 'loss/train': 1.3623377084732056}
-03/05/2022 06:08:04 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/05/2022 06:08:07 - INFO - codeparrot_training - Step 34606: {'lr': 0.00044247261716610307, 'samples': 17718784, 'steps': 34606, 'loss/train': 1.6758027076721191}
-03/05/2022 06:08:11 - INFO - codeparrot_training - Step 34607: {'lr': 0.0004424692304856136, 'samples': 17719296, 'steps': 34607, 'loss/train': 2.121821403503418}
-03/05/2022 06:08:13 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/05/2022 06:08:16 - INFO - codeparrot_training - Step 34608: {'lr': 0.0004424658437184006, 'samples': 17719808, 'steps': 34608, 'loss/train': 6.4753804206848145}
-03/05/2022 06:08:19 - INFO - codeparrot_training - Step 34609: {'lr': 0.0004424624568644654, 'samples': 17720320, 'steps': 34609, 'loss/train': 2.092836856842041}
-03/05/2022 06:08:22 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 06:08:24 - INFO - codeparrot_training - Step 34610: {'lr': 0.00044245906992380955, 'samples': 17720832, 'steps': 34610, 'loss/train': 2.1099298000335693}
-03/05/2022 06:08:27 - INFO - codeparrot_training - Step 34611: {'lr': 0.0004424556828964347, 'samples': 17721344, 'steps': 34611, 'loss/train': 0.7350862622261047}
-03/05/2022 06:08:30 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/05/2022 06:08:33 - INFO - codeparrot_training - Step 34612: {'lr': 0.0004424522957823422, 'samples': 17721856, 'steps': 34612, 'loss/train': 1.220876932144165}
-03/05/2022 06:08:36 - INFO - codeparrot_training - Step 34613: {'lr': 0.00044244890858153376, 'samples': 17722368, 'steps': 34613, 'loss/train': 1.487913966178894}
-03/05/2022 06:08:38 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 06:08:41 - INFO - codeparrot_training - Step 34614: {'lr': 0.00044244552129401075, 'samples': 17722880, 'steps': 34614, 'loss/train': 0.24374724924564362}
-03/05/2022 06:08:44 - INFO - codeparrot_training - Step 34615: {'lr': 0.0004424421339197747, 'samples': 17723392, 'steps': 34615, 'loss/train': 1.81853187084198}
-03/05/2022 06:08:47 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/05/2022 06:08:49 - INFO - codeparrot_training - Step 34616: {'lr': 0.00044243874645882733, 'samples': 17723904, 'steps': 34616, 'loss/train': 1.776626706123352}
-03/05/2022 06:08:53 - INFO - codeparrot_training - Step 34617: {'lr': 0.0004424353589111699, 'samples': 17724416, 'steps': 34617, 'loss/train': 2.194687843322754}
-03/05/2022 06:08:55 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 06:08:58 - INFO - codeparrot_training - Step 34618: {'lr': 0.0004424319712768041, 'samples': 17724928, 'steps': 34618, 'loss/train': 1.2187559604644775}
-03/05/2022 06:09:01 - INFO - codeparrot_training - Step 34619: {'lr': 0.00044242858355573143, 'samples': 17725440, 'steps': 34619, 'loss/train': 2.320472002029419}
-03/05/2022 06:09:05 - INFO - codeparrot_training - Step 34620: {'lr': 0.00044242519574795347, 'samples': 17725952, 'steps': 34620, 'loss/train': 1.5902724266052246}
-03/05/2022 06:09:06 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/05/2022 06:09:10 - INFO - codeparrot_training - Step 34621: {'lr': 0.00044242180785347164, 'samples': 17726464, 'steps': 34621, 'loss/train': 1.8483232259750366}
-03/05/2022 06:09:13 - INFO - codeparrot_training - Step 34622: {'lr': 0.00044241841987228747, 'samples': 17726976, 'steps': 34622, 'loss/train': 2.2183682918548584}
-03/05/2022 06:09:14 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 06:09:18 - INFO - codeparrot_training - Step 34623: {'lr': 0.00044241503180440263, 'samples': 17727488, 'steps': 34623, 'loss/train': 1.461199164390564}
-03/05/2022 06:09:22 - INFO - codeparrot_training - Step 34624: {'lr': 0.0004424116436498185, 'samples': 17728000, 'steps': 34624, 'loss/train': 1.8575831651687622}
-03/05/2022 06:09:23 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/05/2022 06:09:27 - INFO - codeparrot_training - Step 34625: {'lr': 0.0004424082554085366, 'samples': 17728512, 'steps': 34625, 'loss/train': 2.330263376235962}
-03/05/2022 06:09:30 - INFO - codeparrot_training - Step 34626: {'lr': 0.0004424048670805586, 'samples': 17729024, 'steps': 34626, 'loss/train': 0.7419248819351196}
-03/05/2022 06:09:31 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 06:09:35 - INFO - codeparrot_training - Step 34627: {'lr': 0.0004424014786658859, 'samples': 17729536, 'steps': 34627, 'loss/train': 0.8694044351577759}
-03/05/2022 06:09:38 - INFO - codeparrot_training - Step 34628: {'lr': 0.00044239809016452, 'samples': 17730048, 'steps': 34628, 'loss/train': 1.6624994277954102}
-03/05/2022 06:09:40 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/05/2022 06:09:44 - INFO - codeparrot_training - Step 34629: {'lr': 0.00044239470157646254, 'samples': 17730560, 'steps': 34629, 'loss/train': 1.5681383609771729}
-03/05/2022 06:09:47 - INFO - codeparrot_training - Step 34630: {'lr': 0.000442391312901715, 'samples': 17731072, 'steps': 34630, 'loss/train': 1.7738909721374512}
-03/05/2022 06:09:48 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 06:09:52 - INFO - codeparrot_training - Step 34631: {'lr': 0.0004423879241402788, 'samples': 17731584, 'steps': 34631, 'loss/train': 1.7575047016143799}
-03/05/2022 06:09:55 - INFO - codeparrot_training - Step 34632: {'lr': 0.00044238453529215575, 'samples': 17732096, 'steps': 34632, 'loss/train': 0.6281212568283081}
-03/05/2022 06:09:57 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/05/2022 06:10:01 - INFO - codeparrot_training - Step 34633: {'lr': 0.00044238114635734713, 'samples': 17732608, 'steps': 34633, 'loss/train': 1.2663601636886597}
-03/05/2022 06:10:04 - INFO - codeparrot_training - Step 34634: {'lr': 0.0004423777573358545, 'samples': 17733120, 'steps': 34634, 'loss/train': 0.7107919454574585}
-03/05/2022 06:10:05 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/05/2022 06:10:09 - INFO - codeparrot_training - Step 34635: {'lr': 0.0004423743682276794, 'samples': 17733632, 'steps': 34635, 'loss/train': 0.693023681640625}
-03/05/2022 06:10:12 - INFO - codeparrot_training - Step 34636: {'lr': 0.0004423709790328235, 'samples': 17734144, 'steps': 34636, 'loss/train': 2.307650327682495}
-03/05/2022 06:10:14 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/05/2022 06:10:18 - INFO - codeparrot_training - Step 34637: {'lr': 0.0004423675897512881, 'samples': 17734656, 'steps': 34637, 'loss/train': 0.9209141731262207}
-03/05/2022 06:10:21 - INFO - codeparrot_training - Step 34638: {'lr': 0.0004423642003830748, 'samples': 17735168, 'steps': 34638, 'loss/train': 1.7870094776153564}
-03/05/2022 06:10:22 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/05/2022 06:10:26 - INFO - codeparrot_training - Step 34639: {'lr': 0.00044236081092818527, 'samples': 17735680, 'steps': 34639, 'loss/train': 1.7178212404251099}
-03/05/2022 06:10:29 - INFO - codeparrot_training - Step 34640: {'lr': 0.00044235742138662085, 'samples': 17736192, 'steps': 34640, 'loss/train': 1.360457420349121}
-03/05/2022 06:10:31 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/05/2022 06:10:35 - INFO - codeparrot_training - Step 34641: {'lr': 0.0004423540317583832, 'samples': 17736704, 'steps': 34641, 'loss/train': 1.5048810243606567}
-03/05/2022 06:10:38 - INFO - codeparrot_training - Step 34642: {'lr': 0.00044235064204347377, 'samples': 17737216, 'steps': 34642, 'loss/train': 1.6018308401107788}
-03/05/2022 06:10:40 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/05/2022 06:10:43 - INFO - codeparrot_training - Step 34643: {'lr': 0.0004423472522418941, 'samples': 17737728, 'steps': 34643, 'loss/train': 1.799862265586853}
-03/05/2022 06:10:46 - INFO - codeparrot_training - Step 34644: {'lr': 0.0004423438623536457, 'samples': 17738240, 'steps': 34644, 'loss/train': 1.9152681827545166}
-03/05/2022 06:10:48 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 06:10:51 - INFO - codeparrot_training - Step 34645: {'lr': 0.0004423404723787301, 'samples': 17738752, 'steps': 34645, 'loss/train': 1.3875528573989868}
-03/05/2022 06:10:55 - INFO - codeparrot_training - Step 34646: {'lr': 0.000442337082317149, 'samples': 17739264, 'steps': 34646, 'loss/train': 2.1265366077423096}
-03/05/2022 06:10:57 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/05/2022 06:11:00 - INFO - codeparrot_training - Step 34647: {'lr': 0.0004423336921689036, 'samples': 17739776, 'steps': 34647, 'loss/train': 0.784816324710846}
-03/05/2022 06:11:03 - INFO - codeparrot_training - Step 34648: {'lr': 0.0004423303019339957, 'samples': 17740288, 'steps': 34648, 'loss/train': 0.8291152715682983}
-03/05/2022 06:11:05 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 06:11:08 - INFO - codeparrot_training - Step 34649: {'lr': 0.0004423269116124267, 'samples': 17740800, 'steps': 34649, 'loss/train': 1.6914132833480835}
-03/05/2022 06:11:11 - INFO - codeparrot_training - Step 34650: {'lr': 0.0004423235212041982, 'samples': 17741312, 'steps': 34650, 'loss/train': 1.378540277481079}
-03/05/2022 06:11:13 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/05/2022 06:11:17 - INFO - codeparrot_training - Step 34651: {'lr': 0.00044232013070931165, 'samples': 17741824, 'steps': 34651, 'loss/train': 0.6377180814743042}
-03/05/2022 06:11:20 - INFO - codeparrot_training - Step 34652: {'lr': 0.00044231674012776864, 'samples': 17742336, 'steps': 34652, 'loss/train': 1.2246763706207275}
-03/05/2022 06:11:22 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/05/2022 06:11:25 - INFO - codeparrot_training - Step 34653: {'lr': 0.0004423133494595707, 'samples': 17742848, 'steps': 34653, 'loss/train': 2.167185068130493}
-03/05/2022 06:11:28 - INFO - codeparrot_training - Step 34654: {'lr': 0.00044230995870471923, 'samples': 17743360, 'steps': 34654, 'loss/train': 0.6286876201629639}
-03/05/2022 06:11:30 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/05/2022 06:11:34 - INFO - codeparrot_training - Step 34655: {'lr': 0.000442306567863216, 'samples': 17743872, 'steps': 34655, 'loss/train': 1.2910902500152588}
-03/05/2022 06:11:37 - INFO - codeparrot_training - Step 34656: {'lr': 0.00044230317693506226, 'samples': 17744384, 'steps': 34656, 'loss/train': 1.2925772666931152}
-03/05/2022 06:11:39 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/05/2022 06:11:42 - INFO - codeparrot_training - Step 34657: {'lr': 0.00044229978592025975, 'samples': 17744896, 'steps': 34657, 'loss/train': 2.401838779449463}
-03/05/2022 06:11:46 - INFO - codeparrot_training - Step 34658: {'lr': 0.00044229639481881, 'samples': 17745408, 'steps': 34658, 'loss/train': 1.6781604290008545}
-03/05/2022 06:11:47 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 06:11:51 - INFO - codeparrot_training - Step 34659: {'lr': 0.00044229300363071434, 'samples': 17745920, 'steps': 34659, 'loss/train': 1.4354958534240723}
-03/05/2022 06:11:54 - INFO - codeparrot_training - Step 34660: {'lr': 0.0004422896123559744, 'samples': 17746432, 'steps': 34660, 'loss/train': 1.2898335456848145}
-03/05/2022 06:11:56 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/05/2022 06:11:59 - INFO - codeparrot_training - Step 34661: {'lr': 0.00044228622099459183, 'samples': 17746944, 'steps': 34661, 'loss/train': 2.530094623565674}
-03/05/2022 06:12:03 - INFO - codeparrot_training - Step 34662: {'lr': 0.000442282829546568, 'samples': 17747456, 'steps': 34662, 'loss/train': 1.5053707361221313}
-03/05/2022 06:12:04 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/05/2022 06:12:08 - INFO - codeparrot_training - Step 34663: {'lr': 0.00044227943801190454, 'samples': 17747968, 'steps': 34663, 'loss/train': 1.0806703567504883}
-03/05/2022 06:12:11 - INFO - codeparrot_training - Step 34664: {'lr': 0.0004422760463906029, 'samples': 17748480, 'steps': 34664, 'loss/train': 1.530690312385559}
-03/05/2022 06:12:13 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 06:12:16 - INFO - codeparrot_training - Step 34665: {'lr': 0.00044227265468266464, 'samples': 17748992, 'steps': 34665, 'loss/train': 1.824294924736023}
-03/05/2022 06:12:20 - INFO - codeparrot_training - Step 34666: {'lr': 0.0004422692628880913, 'samples': 17749504, 'steps': 34666, 'loss/train': 1.8913726806640625}
-03/05/2022 06:12:21 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/05/2022 06:12:25 - INFO - codeparrot_training - Step 34667: {'lr': 0.00044226587100688436, 'samples': 17750016, 'steps': 34667, 'loss/train': 0.0817064642906189}
-03/05/2022 06:12:28 - INFO - codeparrot_training - Step 34668: {'lr': 0.0004422624790390454, 'samples': 17750528, 'steps': 34668, 'loss/train': 1.9480189085006714}
-03/05/2022 06:12:29 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/05/2022 06:12:33 - INFO - codeparrot_training - Step 34669: {'lr': 0.000442259086984576, 'samples': 17751040, 'steps': 34669, 'loss/train': 2.4002320766448975}
-03/05/2022 06:12:37 - INFO - codeparrot_training - Step 34670: {'lr': 0.00044225569484347753, 'samples': 17751552, 'steps': 34670, 'loss/train': 0.9600015878677368}
-03/05/2022 06:12:42 - INFO - codeparrot_training - Step 34671: {'lr': 0.00044225230261575165, 'samples': 17752064, 'steps': 34671, 'loss/train': 1.6734172105789185}
-03/05/2022 06:12:45 - INFO - codeparrot_training - Step 34672: {'lr': 0.00044224891030139986, 'samples': 17752576, 'steps': 34672, 'loss/train': 1.072651982307434}
-03/05/2022 06:12:50 - INFO - codeparrot_training - Step 34673: {'lr': 0.0004422455179004237, 'samples': 17753088, 'steps': 34673, 'loss/train': 1.556174397468567}
-03/05/2022 06:12:53 - INFO - codeparrot_training - Step 34674: {'lr': 0.00044224212541282463, 'samples': 17753600, 'steps': 34674, 'loss/train': 0.7710404992103577}
-03/05/2022 06:12:55 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/05/2022 06:12:59 - INFO - codeparrot_training - Step 34675: {'lr': 0.0004422387328386042, 'samples': 17754112, 'steps': 34675, 'loss/train': 1.2669563293457031}
-03/05/2022 06:13:02 - INFO - codeparrot_training - Step 34676: {'lr': 0.000442235340177764, 'samples': 17754624, 'steps': 34676, 'loss/train': 2.039918899536133}
-03/05/2022 06:13:03 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/05/2022 06:13:07 - INFO - codeparrot_training - Step 34677: {'lr': 0.00044223194743030556, 'samples': 17755136, 'steps': 34677, 'loss/train': 1.0990524291992188}
-03/05/2022 06:13:10 - INFO - codeparrot_training - Step 34678: {'lr': 0.00044222855459623034, 'samples': 17755648, 'steps': 34678, 'loss/train': 1.5621976852416992}
-03/05/2022 06:13:11 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/05/2022 06:13:15 - INFO - codeparrot_training - Step 34679: {'lr': 0.00044222516167553985, 'samples': 17756160, 'steps': 34679, 'loss/train': 1.59064781665802}
-03/05/2022 06:13:19 - INFO - codeparrot_training - Step 34680: {'lr': 0.0004422217686682357, 'samples': 17756672, 'steps': 34680, 'loss/train': 1.2528200149536133}
-03/05/2022 06:13:24 - INFO - codeparrot_training - Step 34681: {'lr': 0.00044221837557431945, 'samples': 17757184, 'steps': 34681, 'loss/train': 0.7929532527923584}
-03/05/2022 06:13:27 - INFO - codeparrot_training - Step 34682: {'lr': 0.00044221498239379247, 'samples': 17757696, 'steps': 34682, 'loss/train': 1.9037834405899048}
-03/05/2022 06:13:28 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/05/2022 06:13:32 - INFO - codeparrot_training - Step 34683: {'lr': 0.0004422115891266565, 'samples': 17758208, 'steps': 34683, 'loss/train': 2.475658416748047}
-03/05/2022 06:13:36 - INFO - codeparrot_training - Step 34684: {'lr': 0.00044220819577291283, 'samples': 17758720, 'steps': 34684, 'loss/train': 2.007002115249634}
-03/05/2022 06:13:37 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/05/2022 06:13:41 - INFO - codeparrot_training - Step 34685: {'lr': 0.00044220480233256315, 'samples': 17759232, 'steps': 34685, 'loss/train': 1.4666168689727783}
-03/05/2022 06:13:44 - INFO - codeparrot_training - Step 34686: {'lr': 0.00044220140880560897, 'samples': 17759744, 'steps': 34686, 'loss/train': 1.1131591796875}
-03/05/2022 06:13:45 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/05/2022 06:13:49 - INFO - codeparrot_training - Step 34687: {'lr': 0.0004421980151920518, 'samples': 17760256, 'steps': 34687, 'loss/train': 2.0053248405456543}
-03/05/2022 06:13:53 - INFO - codeparrot_training - Step 34688: {'lr': 0.00044219462149189313, 'samples': 17760768, 'steps': 34688, 'loss/train': 1.8689898252487183}
-03/05/2022 06:13:53 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 06:13:58 - INFO - codeparrot_training - Step 34689: {'lr': 0.0004421912277051346, 'samples': 17761280, 'steps': 34689, 'loss/train': 1.8633910417556763}
-03/05/2022 06:14:01 - INFO - codeparrot_training - Step 34690: {'lr': 0.00044218783383177763, 'samples': 17761792, 'steps': 34690, 'loss/train': 1.4913395643234253}
-03/05/2022 06:14:02 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/05/2022 06:14:06 - INFO - codeparrot_training - Step 34691: {'lr': 0.00044218443987182384, 'samples': 17762304, 'steps': 34691, 'loss/train': 1.578671932220459}
-03/05/2022 06:14:09 - INFO - codeparrot_training - Step 34692: {'lr': 0.0004421810458252746, 'samples': 17762816, 'steps': 34692, 'loss/train': 1.354146122932434}
-03/05/2022 06:14:10 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/05/2022 06:14:15 - INFO - codeparrot_training - Step 34693: {'lr': 0.00044217765169213166, 'samples': 17763328, 'steps': 34693, 'loss/train': 1.4421546459197998}
-03/05/2022 06:14:18 - INFO - codeparrot_training - Step 34694: {'lr': 0.00044217425747239636, 'samples': 17763840, 'steps': 34694, 'loss/train': 1.170554757118225}
-03/05/2022 06:14:18 - INFO - codeparrot_training - Skipping example with length 37 (seq_length=1024)
-03/05/2022 06:14:23 - INFO - codeparrot_training - Step 34695: {'lr': 0.00044217086316607033, 'samples': 17764352, 'steps': 34695, 'loss/train': 1.7306098937988281}
-03/05/2022 06:14:26 - INFO - codeparrot_training - Step 34696: {'lr': 0.00044216746877315504, 'samples': 17764864, 'steps': 34696, 'loss/train': 1.713168740272522}
-03/05/2022 06:14:27 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/05/2022 06:14:32 - INFO - codeparrot_training - Step 34697: {'lr': 0.0004421640742936521, 'samples': 17765376, 'steps': 34697, 'loss/train': 3.4272780418395996}
-03/05/2022 06:14:35 - INFO - codeparrot_training - Step 34698: {'lr': 0.000442160679727563, 'samples': 17765888, 'steps': 34698, 'loss/train': 2.222865581512451}
-03/05/2022 06:14:35 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/05/2022 06:14:40 - INFO - codeparrot_training - Step 34699: {'lr': 0.0004421572850748893, 'samples': 17766400, 'steps': 34699, 'loss/train': 1.9602172374725342}
-03/05/2022 06:14:43 - INFO - codeparrot_training - Step 34700: {'lr': 0.00044215389033563235, 'samples': 17766912, 'steps': 34700, 'loss/train': 1.9322041273117065}
-03/05/2022 06:14:45 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/05/2022 06:14:49 - INFO - codeparrot_training - Step 34701: {'lr': 0.00044215049550979394, 'samples': 17767424, 'steps': 34701, 'loss/train': 1.4731426239013672}
-03/05/2022 06:14:52 - INFO - codeparrot_training - Step 34702: {'lr': 0.0004421471005973755, 'samples': 17767936, 'steps': 34702, 'loss/train': 1.500730037689209}
-03/05/2022 06:14:53 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/05/2022 06:14:57 - INFO - codeparrot_training - Step 34703: {'lr': 0.0004421437055983785, 'samples': 17768448, 'steps': 34703, 'loss/train': 1.727432131767273}
-03/05/2022 06:15:00 - INFO - codeparrot_training - Step 34704: {'lr': 0.0004421403105128045, 'samples': 17768960, 'steps': 34704, 'loss/train': 2.3604538440704346}
-03/05/2022 06:15:01 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/05/2022 06:15:05 - INFO - codeparrot_training - Step 34705: {'lr': 0.00044213691534065503, 'samples': 17769472, 'steps': 34705, 'loss/train': 1.733148455619812}
-03/05/2022 06:15:09 - INFO - codeparrot_training - Step 34706: {'lr': 0.0004421335200819316, 'samples': 17769984, 'steps': 34706, 'loss/train': 2.107748031616211}
-03/05/2022 06:15:10 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/05/2022 06:15:14 - INFO - codeparrot_training - Step 34707: {'lr': 0.00044213012473663584, 'samples': 17770496, 'steps': 34707, 'loss/train': 2.013026237487793}
-03/05/2022 06:15:17 - INFO - codeparrot_training - Step 34708: {'lr': 0.0004421267293047692, 'samples': 17771008, 'steps': 34708, 'loss/train': 2.3180277347564697}
-03/05/2022 06:15:18 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/05/2022 06:15:23 - INFO - codeparrot_training - Step 34709: {'lr': 0.0004421233337863332, 'samples': 17771520, 'steps': 34709, 'loss/train': 1.822326421737671}
-03/05/2022 06:15:26 - INFO - codeparrot_training - Step 34710: {'lr': 0.0004421199381813293, 'samples': 17772032, 'steps': 34710, 'loss/train': 1.1826245784759521}
-03/05/2022 06:15:27 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/05/2022 06:15:31 - INFO - codeparrot_training - Step 34711: {'lr': 0.0004421165424897593, 'samples': 17772544, 'steps': 34711, 'loss/train': 2.132946491241455}
-03/05/2022 06:15:34 - INFO - codeparrot_training - Step 34712: {'lr': 0.00044211314671162446, 'samples': 17773056, 'steps': 34712, 'loss/train': 1.8319579362869263}
-03/05/2022 06:15:35 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/05/2022 06:15:39 - INFO - codeparrot_training - Step 34713: {'lr': 0.0004421097508469264, 'samples': 17773568, 'steps': 34713, 'loss/train': 1.5415055751800537}
-03/05/2022 06:15:43 - INFO - codeparrot_training - Step 34714: {'lr': 0.0004421063548956666, 'samples': 17774080, 'steps': 34714, 'loss/train': 1.4501134157180786}
-03/05/2022 06:15:43 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 06:15:48 - INFO - codeparrot_training - Step 34715: {'lr': 0.0004421029588578468, 'samples': 17774592, 'steps': 34715, 'loss/train': 1.2714436054229736}
-03/05/2022 06:15:51 - INFO - codeparrot_training - Step 34716: {'lr': 0.00044209956273346816, 'samples': 17775104, 'steps': 34716, 'loss/train': 1.5021438598632812}
-03/05/2022 06:15:52 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/05/2022 06:15:56 - INFO - codeparrot_training - Step 34717: {'lr': 0.0004420961665225326, 'samples': 17775616, 'steps': 34717, 'loss/train': 1.8067482709884644}
-03/05/2022 06:15:59 - INFO - codeparrot_training - Step 34718: {'lr': 0.0004420927702250414, 'samples': 17776128, 'steps': 34718, 'loss/train': 2.017714738845825}
-03/05/2022 06:16:00 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/05/2022 06:16:05 - INFO - codeparrot_training - Step 34719: {'lr': 0.00044208937384099614, 'samples': 17776640, 'steps': 34719, 'loss/train': 1.4139554500579834}
-03/05/2022 06:16:08 - INFO - codeparrot_training - Step 34720: {'lr': 0.0004420859773703985, 'samples': 17777152, 'steps': 34720, 'loss/train': 1.0347590446472168}
-03/05/2022 06:16:08 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 06:16:13 - INFO - codeparrot_training - Step 34721: {'lr': 0.0004420825808132497, 'samples': 17777664, 'steps': 34721, 'loss/train': 0.8553276658058167}
-03/05/2022 06:16:16 - INFO - codeparrot_training - Step 34722: {'lr': 0.0004420791841695515, 'samples': 17778176, 'steps': 34722, 'loss/train': 1.979260802268982}
-03/05/2022 06:16:18 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/05/2022 06:16:22 - INFO - codeparrot_training - Step 34723: {'lr': 0.00044207578743930544, 'samples': 17778688, 'steps': 34723, 'loss/train': 1.5269734859466553}
-03/05/2022 06:16:25 - INFO - codeparrot_training - Step 34724: {'lr': 0.00044207239062251297, 'samples': 17779200, 'steps': 34724, 'loss/train': 1.002009630203247}
-03/05/2022 06:16:26 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/05/2022 06:16:30 - INFO - codeparrot_training - Step 34725: {'lr': 0.00044206899371917563, 'samples': 17779712, 'steps': 34725, 'loss/train': 1.8381508588790894}
-03/05/2022 06:16:33 - INFO - codeparrot_training - Step 34726: {'lr': 0.00044206559672929505, 'samples': 17780224, 'steps': 34726, 'loss/train': 0.971093475818634}
-03/05/2022 06:16:34 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/05/2022 06:16:38 - INFO - codeparrot_training - Step 34727: {'lr': 0.00044206219965287253, 'samples': 17780736, 'steps': 34727, 'loss/train': 1.3300241231918335}
-03/05/2022 06:16:42 - INFO - codeparrot_training - Step 34728: {'lr': 0.0004420588024899098, 'samples': 17781248, 'steps': 34728, 'loss/train': 1.9163177013397217}
-03/05/2022 06:16:42 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/05/2022 06:16:47 - INFO - codeparrot_training - Step 34729: {'lr': 0.00044205540524040846, 'samples': 17781760, 'steps': 34729, 'loss/train': 2.20051646232605}
-03/05/2022 06:16:50 - INFO - codeparrot_training - Step 34730: {'lr': 0.0004420520079043698, 'samples': 17782272, 'steps': 34730, 'loss/train': 1.244758129119873}
-03/05/2022 06:16:51 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/05/2022 06:16:55 - INFO - codeparrot_training - Step 34731: {'lr': 0.00044204861048179544, 'samples': 17782784, 'steps': 34731, 'loss/train': 2.03043532371521}
-03/05/2022 06:16:58 - INFO - codeparrot_training - Step 34732: {'lr': 0.000442045212972687, 'samples': 17783296, 'steps': 34732, 'loss/train': 2.111168622970581}
-03/05/2022 06:16:59 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/05/2022 06:17:04 - INFO - codeparrot_training - Step 34733: {'lr': 0.00044204181537704594, 'samples': 17783808, 'steps': 34733, 'loss/train': 2.1760730743408203}
-03/05/2022 06:17:07 - INFO - codeparrot_training - Step 34734: {'lr': 0.0004420384176948738, 'samples': 17784320, 'steps': 34734, 'loss/train': 1.9002472162246704}
-03/05/2022 06:17:08 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/05/2022 06:17:12 - INFO - codeparrot_training - Step 34735: {'lr': 0.0004420350199261721, 'samples': 17784832, 'steps': 34735, 'loss/train': 1.3317527770996094}
-03/05/2022 06:17:15 - INFO - codeparrot_training - Step 34736: {'lr': 0.0004420316220709424, 'samples': 17785344, 'steps': 34736, 'loss/train': 2.1146278381347656}
-03/05/2022 06:17:17 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/05/2022 06:17:21 - INFO - codeparrot_training - Step 34737: {'lr': 0.0004420282241291862, 'samples': 17785856, 'steps': 34737, 'loss/train': 2.235307455062866}
-03/05/2022 06:17:24 - INFO - codeparrot_training - Step 34738: {'lr': 0.0004420248261009051, 'samples': 17786368, 'steps': 34738, 'loss/train': 2.1142139434814453}
-03/05/2022 06:17:25 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/05/2022 06:17:29 - INFO - codeparrot_training - Step 34739: {'lr': 0.0004420214279861005, 'samples': 17786880, 'steps': 34739, 'loss/train': 1.6127471923828125}
-03/05/2022 06:17:32 - INFO - codeparrot_training - Step 34740: {'lr': 0.000442018029784774, 'samples': 17787392, 'steps': 34740, 'loss/train': 1.2814568281173706}
-03/05/2022 06:17:33 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 06:17:37 - INFO - codeparrot_training - Step 34741: {'lr': 0.00044201463149692725, 'samples': 17787904, 'steps': 34741, 'loss/train': 2.0485661029815674}
-03/05/2022 06:17:41 - INFO - codeparrot_training - Step 34742: {'lr': 0.0004420112331225616, 'samples': 17788416, 'steps': 34742, 'loss/train': 0.7049129009246826}
-03/05/2022 06:17:42 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/05/2022 06:17:46 - INFO - codeparrot_training - Step 34743: {'lr': 0.0004420078346616786, 'samples': 17788928, 'steps': 34743, 'loss/train': 2.3652329444885254}
-03/05/2022 06:17:49 - INFO - codeparrot_training - Step 34744: {'lr': 0.00044200443611427985, 'samples': 17789440, 'steps': 34744, 'loss/train': 1.6950198411941528}
-03/05/2022 06:17:50 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/05/2022 06:17:54 - INFO - codeparrot_training - Step 34745: {'lr': 0.000442001037480367, 'samples': 17789952, 'steps': 34745, 'loss/train': 1.8679709434509277}
-03/05/2022 06:17:57 - INFO - codeparrot_training - Step 34746: {'lr': 0.0004419976387599413, 'samples': 17790464, 'steps': 34746, 'loss/train': 2.327646493911743}
-03/05/2022 06:17:58 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/05/2022 06:18:03 - INFO - codeparrot_training - Step 34747: {'lr': 0.0004419942399530045, 'samples': 17790976, 'steps': 34747, 'loss/train': 1.438119649887085}
-03/05/2022 06:18:06 - INFO - codeparrot_training - Step 34748: {'lr': 0.000441990841059558, 'samples': 17791488, 'steps': 34748, 'loss/train': 1.0234674215316772}
-03/05/2022 06:18:06 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/05/2022 06:18:11 - INFO - codeparrot_training - Step 34749: {'lr': 0.0004419874420796034, 'samples': 17792000, 'steps': 34749, 'loss/train': 1.802757978439331}
-03/05/2022 06:18:14 - INFO - codeparrot_training - Step 34750: {'lr': 0.00044198404301314223, 'samples': 17792512, 'steps': 34750, 'loss/train': 1.5785678625106812}
-03/05/2022 06:18:14 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/05/2022 06:18:19 - INFO - codeparrot_training - Step 34751: {'lr': 0.000441980643860176, 'samples': 17793024, 'steps': 34751, 'loss/train': 0.638883650302887}
-03/05/2022 06:18:23 - INFO - codeparrot_training - Step 34752: {'lr': 0.0004419772446207063, 'samples': 17793536, 'steps': 34752, 'loss/train': 2.0817904472351074}
-03/05/2022 06:18:23 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/05/2022 06:18:28 - INFO - codeparrot_training - Step 34753: {'lr': 0.0004419738452947346, 'samples': 17794048, 'steps': 34753, 'loss/train': 1.991413950920105}
-03/05/2022 06:18:31 - INFO - codeparrot_training - Step 34754: {'lr': 0.00044197044588226245, 'samples': 17794560, 'steps': 34754, 'loss/train': 1.5427950620651245}
-03/05/2022 06:18:32 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/05/2022 06:18:36 - INFO - codeparrot_training - Step 34755: {'lr': 0.00044196704638329134, 'samples': 17795072, 'steps': 34755, 'loss/train': 1.6483997106552124}
-03/05/2022 06:18:40 - INFO - codeparrot_training - Step 34756: {'lr': 0.00044196364679782284, 'samples': 17795584, 'steps': 34756, 'loss/train': 1.0142407417297363}
-03/05/2022 06:18:40 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/05/2022 06:18:45 - INFO - codeparrot_training - Step 34757: {'lr': 0.00044196024712585854, 'samples': 17796096, 'steps': 34757, 'loss/train': 1.6757601499557495}
-03/05/2022 06:18:48 - INFO - codeparrot_training - Step 34758: {'lr': 0.0004419568473673999, 'samples': 17796608, 'steps': 34758, 'loss/train': 2.249492645263672}
-03/05/2022 06:18:49 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/05/2022 06:18:53 - INFO - codeparrot_training - Step 34759: {'lr': 0.00044195344752244844, 'samples': 17797120, 'steps': 34759, 'loss/train': 2.4136264324188232}
-03/05/2022 06:18:57 - INFO - codeparrot_training - Step 34760: {'lr': 0.0004419500475910057, 'samples': 17797632, 'steps': 34760, 'loss/train': 1.2814266681671143}
-03/05/2022 06:18:58 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/05/2022 06:19:02 - INFO - codeparrot_training - Step 34761: {'lr': 0.0004419466475730732, 'samples': 17798144, 'steps': 34761, 'loss/train': 1.8868883848190308}
-03/05/2022 06:19:05 - INFO - codeparrot_training - Step 34762: {'lr': 0.00044194324746865265, 'samples': 17798656, 'steps': 34762, 'loss/train': 1.704897403717041}
-03/05/2022 06:19:06 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/05/2022 06:19:10 - INFO - codeparrot_training - Step 34763: {'lr': 0.00044193984727774533, 'samples': 17799168, 'steps': 34763, 'loss/train': 1.2163739204406738}
-03/05/2022 06:19:13 - INFO - codeparrot_training - Step 34764: {'lr': 0.0004419364470003529, 'samples': 17799680, 'steps': 34764, 'loss/train': 1.9033769369125366}
-03/05/2022 06:19:14 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/05/2022 06:19:19 - INFO - codeparrot_training - Step 34765: {'lr': 0.00044193304663647684, 'samples': 17800192, 'steps': 34765, 'loss/train': 1.9086840152740479}
-03/05/2022 06:19:22 - INFO - codeparrot_training - Step 34766: {'lr': 0.00044192964618611875, 'samples': 17800704, 'steps': 34766, 'loss/train': 2.563309907913208}
-03/05/2022 06:19:22 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/05/2022 06:19:27 - INFO - codeparrot_training - Step 34767: {'lr': 0.0004419262456492801, 'samples': 17801216, 'steps': 34767, 'loss/train': 1.6083649396896362}
-03/05/2022 06:19:31 - INFO - codeparrot_training - Step 34768: {'lr': 0.0004419228450259625, 'samples': 17801728, 'steps': 34768, 'loss/train': 0.8915947675704956}
-03/05/2022 06:19:32 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 06:19:36 - INFO - codeparrot_training - Step 34769: {'lr': 0.00044191944431616734, 'samples': 17802240, 'steps': 34769, 'loss/train': 1.388028860092163}
-03/05/2022 06:19:39 - INFO - codeparrot_training - Step 34770: {'lr': 0.0004419160435198963, 'samples': 17802752, 'steps': 34770, 'loss/train': 1.617478370666504}
-03/05/2022 06:19:40 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/05/2022 06:19:45 - INFO - codeparrot_training - Step 34771: {'lr': 0.00044191264263715083, 'samples': 17803264, 'steps': 34771, 'loss/train': 1.431685209274292}
-03/05/2022 06:19:48 - INFO - codeparrot_training - Step 34772: {'lr': 0.00044190924166793245, 'samples': 17803776, 'steps': 34772, 'loss/train': 1.5003126859664917}
-03/05/2022 06:19:49 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/05/2022 06:19:53 - INFO - codeparrot_training - Step 34773: {'lr': 0.00044190584061224277, 'samples': 17804288, 'steps': 34773, 'loss/train': 6.4721550941467285}
-03/05/2022 06:19:56 - INFO - codeparrot_training - Step 34774: {'lr': 0.0004419024394700833, 'samples': 17804800, 'steps': 34774, 'loss/train': 1.7067549228668213}
-03/05/2022 06:19:59 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/05/2022 06:20:01 - INFO - codeparrot_training - Step 34775: {'lr': 0.0004418990382414555, 'samples': 17805312, 'steps': 34775, 'loss/train': 2.051708698272705}
-03/05/2022 06:20:05 - INFO - codeparrot_training - Step 34776: {'lr': 0.000441895636926361, 'samples': 17805824, 'steps': 34776, 'loss/train': 1.4361144304275513}
-03/05/2022 06:20:07 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/05/2022 06:20:10 - INFO - codeparrot_training - Step 34777: {'lr': 0.0004418922355248013, 'samples': 17806336, 'steps': 34777, 'loss/train': 1.7085236310958862}
-03/05/2022 06:20:13 - INFO - codeparrot_training - Step 34778: {'lr': 0.00044188883403677783, 'samples': 17806848, 'steps': 34778, 'loss/train': 2.1923513412475586}
-03/05/2022 06:20:15 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/05/2022 06:20:18 - INFO - codeparrot_training - Step 34779: {'lr': 0.0004418854324622923, 'samples': 17807360, 'steps': 34779, 'loss/train': 1.9976255893707275}
-03/05/2022 06:20:21 - INFO - codeparrot_training - Step 34780: {'lr': 0.0004418820308013461, 'samples': 17807872, 'steps': 34780, 'loss/train': 2.2966229915618896}
-03/05/2022 06:20:23 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/05/2022 06:20:27 - INFO - codeparrot_training - Step 34781: {'lr': 0.0004418786290539408, 'samples': 17808384, 'steps': 34781, 'loss/train': 0.49917879700660706}
-03/05/2022 06:20:30 - INFO - codeparrot_training - Step 34782: {'lr': 0.000441875227220078, 'samples': 17808896, 'steps': 34782, 'loss/train': 1.8395239114761353}
-03/05/2022 06:20:32 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/05/2022 06:20:35 - INFO - codeparrot_training - Step 34783: {'lr': 0.00044187182529975924, 'samples': 17809408, 'steps': 34783, 'loss/train': 1.547330617904663}
-03/05/2022 06:20:39 - INFO - codeparrot_training - Step 34784: {'lr': 0.00044186842329298594, 'samples': 17809920, 'steps': 34784, 'loss/train': 2.057607412338257}
-03/05/2022 06:20:41 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/05/2022 06:20:44 - INFO - codeparrot_training - Step 34785: {'lr': 0.0004418650211997596, 'samples': 17810432, 'steps': 34785, 'loss/train': 2.403320550918579}
-03/05/2022 06:20:47 - INFO - codeparrot_training - Step 34786: {'lr': 0.00044186161902008193, 'samples': 17810944, 'steps': 34786, 'loss/train': 1.6032514572143555}
-03/05/2022 06:20:49 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 06:20:52 - INFO - codeparrot_training - Step 34787: {'lr': 0.0004418582167539544, 'samples': 17811456, 'steps': 34787, 'loss/train': 2.04004168510437}
-03/05/2022 06:20:55 - INFO - codeparrot_training - Step 34788: {'lr': 0.00044185481440137846, 'samples': 17811968, 'steps': 34788, 'loss/train': 1.5111654996871948}
-03/05/2022 06:20:58 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/05/2022 06:21:01 - INFO - codeparrot_training - Step 34789: {'lr': 0.0004418514119623557, 'samples': 17812480, 'steps': 34789, 'loss/train': 1.140149712562561}
-03/05/2022 06:21:04 - INFO - codeparrot_training - Step 34790: {'lr': 0.00044184800943688774, 'samples': 17812992, 'steps': 34790, 'loss/train': 3.132916212081909}
-03/05/2022 06:21:06 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/05/2022 06:21:09 - INFO - codeparrot_training - Step 34791: {'lr': 0.00044184460682497595, 'samples': 17813504, 'steps': 34791, 'loss/train': 2.01381778717041}
-03/05/2022 06:21:12 - INFO - codeparrot_training - Step 34792: {'lr': 0.00044184120412662196, 'samples': 17814016, 'steps': 34792, 'loss/train': 2.316624402999878}
-03/05/2022 06:21:15 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/05/2022 06:21:18 - INFO - codeparrot_training - Step 34793: {'lr': 0.00044183780134182725, 'samples': 17814528, 'steps': 34793, 'loss/train': 1.9853283166885376}
-03/05/2022 06:21:21 - INFO - codeparrot_training - Step 34794: {'lr': 0.0004418343984705935, 'samples': 17815040, 'steps': 34794, 'loss/train': 1.3579590320587158}
-03/05/2022 06:21:23 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 06:21:26 - INFO - codeparrot_training - Step 34795: {'lr': 0.000441830995512922, 'samples': 17815552, 'steps': 34795, 'loss/train': 2.7011172771453857}
-03/05/2022 06:21:29 - INFO - codeparrot_training - Step 34796: {'lr': 0.00044182759246881446, 'samples': 17816064, 'steps': 34796, 'loss/train': 0.963615894317627}
-03/05/2022 06:21:31 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 06:21:34 - INFO - codeparrot_training - Step 34797: {'lr': 0.0004418241893382724, 'samples': 17816576, 'steps': 34797, 'loss/train': 1.7839312553405762}
-03/05/2022 06:21:38 - INFO - codeparrot_training - Step 34798: {'lr': 0.0004418207861212973, 'samples': 17817088, 'steps': 34798, 'loss/train': 2.1674461364746094}
-03/05/2022 06:21:39 - INFO - codeparrot_training - Skipping example with length 822 (seq_length=1024)
-03/05/2022 06:21:43 - INFO - codeparrot_training - Step 34799: {'lr': 0.0004418173828178906, 'samples': 17817600, 'steps': 34799, 'loss/train': 1.9776021242141724}
-03/05/2022 06:21:46 - INFO - codeparrot_training - Step 34800: {'lr': 0.0004418139794280541, 'samples': 17818112, 'steps': 34800, 'loss/train': 1.7851351499557495}
-03/05/2022 06:21:48 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/05/2022 06:21:51 - INFO - codeparrot_training - Step 34801: {'lr': 0.0004418105759517892, 'samples': 17818624, 'steps': 34801, 'loss/train': 1.4928101301193237}
-03/05/2022 06:21:55 - INFO - codeparrot_training - Step 34802: {'lr': 0.0004418071723890973, 'samples': 17819136, 'steps': 34802, 'loss/train': 1.4727814197540283}
-03/05/2022 06:21:57 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 06:22:00 - INFO - codeparrot_training - Step 34803: {'lr': 0.0004418037687399801, 'samples': 17819648, 'steps': 34803, 'loss/train': 1.5155882835388184}
-03/05/2022 06:22:03 - INFO - codeparrot_training - Step 34804: {'lr': 0.0004418003650044391, 'samples': 17820160, 'steps': 34804, 'loss/train': 0.5956745743751526}
-03/05/2022 06:22:05 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/05/2022 06:22:08 - INFO - codeparrot_training - Step 34805: {'lr': 0.0004417969611824758, 'samples': 17820672, 'steps': 34805, 'loss/train': 0.6937854290008545}
-03/05/2022 06:22:11 - INFO - codeparrot_training - Step 34806: {'lr': 0.00044179355727409173, 'samples': 17821184, 'steps': 34806, 'loss/train': 1.4317811727523804}
-03/05/2022 06:22:13 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/05/2022 06:22:17 - INFO - codeparrot_training - Step 34807: {'lr': 0.00044179015327928847, 'samples': 17821696, 'steps': 34807, 'loss/train': 1.8110909461975098}
-03/05/2022 06:22:20 - INFO - codeparrot_training - Step 34808: {'lr': 0.0004417867491980675, 'samples': 17822208, 'steps': 34808, 'loss/train': 1.2459276914596558}
-03/05/2022 06:22:21 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/05/2022 06:22:25 - INFO - codeparrot_training - Step 34809: {'lr': 0.0004417833450304304, 'samples': 17822720, 'steps': 34809, 'loss/train': 1.4649474620819092}
-03/05/2022 06:22:28 - INFO - codeparrot_training - Step 34810: {'lr': 0.0004417799407763786, 'samples': 17823232, 'steps': 34810, 'loss/train': 1.9763818979263306}
-03/05/2022 06:22:30 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/05/2022 06:22:33 - INFO - codeparrot_training - Step 34811: {'lr': 0.00044177653643591387, 'samples': 17823744, 'steps': 34811, 'loss/train': 2.1348869800567627}
-03/05/2022 06:22:37 - INFO - codeparrot_training - Step 34812: {'lr': 0.00044177313200903745, 'samples': 17824256, 'steps': 34812, 'loss/train': 1.6223477125167847}
-03/05/2022 06:22:38 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/05/2022 06:22:42 - INFO - codeparrot_training - Step 34813: {'lr': 0.0004417697274957511, 'samples': 17824768, 'steps': 34813, 'loss/train': 1.8909236192703247}
-03/05/2022 06:22:45 - INFO - codeparrot_training - Step 34814: {'lr': 0.0004417663228960562, 'samples': 17825280, 'steps': 34814, 'loss/train': 1.661768913269043}
-03/05/2022 06:22:46 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/05/2022 06:22:50 - INFO - codeparrot_training - Step 34815: {'lr': 0.0004417629182099545, 'samples': 17825792, 'steps': 34815, 'loss/train': 0.7484272122383118}
-03/05/2022 06:22:53 - INFO - codeparrot_training - Step 34816: {'lr': 0.00044175951343744725, 'samples': 17826304, 'steps': 34816, 'loss/train': 2.1084091663360596}
-03/05/2022 06:22:55 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/05/2022 06:22:59 - INFO - codeparrot_training - Step 34817: {'lr': 0.0004417561085785362, 'samples': 17826816, 'steps': 34817, 'loss/train': 1.6282190084457397}
-03/05/2022 06:23:02 - INFO - codeparrot_training - Step 34818: {'lr': 0.0004417527036332227, 'samples': 17827328, 'steps': 34818, 'loss/train': 1.4261828660964966}
-03/05/2022 06:23:04 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/05/2022 06:23:07 - INFO - codeparrot_training - Step 34819: {'lr': 0.0004417492986015085, 'samples': 17827840, 'steps': 34819, 'loss/train': 1.8855311870574951}
-03/05/2022 06:23:10 - INFO - codeparrot_training - Step 34820: {'lr': 0.000441745893483395, 'samples': 17828352, 'steps': 34820, 'loss/train': 1.7528315782546997}
-03/05/2022 06:23:12 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/05/2022 06:23:16 - INFO - codeparrot_training - Step 34821: {'lr': 0.00044174248827888376, 'samples': 17828864, 'steps': 34821, 'loss/train': 2.0814781188964844}
-03/05/2022 06:23:19 - INFO - codeparrot_training - Step 34822: {'lr': 0.00044173908298797627, 'samples': 17829376, 'steps': 34822, 'loss/train': 1.948156476020813}
-03/05/2022 06:23:21 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/05/2022 06:23:24 - INFO - codeparrot_training - Step 34823: {'lr': 0.0004417356776106741, 'samples': 17829888, 'steps': 34823, 'loss/train': 2.0892181396484375}
-03/05/2022 06:23:27 - INFO - codeparrot_training - Step 34824: {'lr': 0.00044173227214697885, 'samples': 17830400, 'steps': 34824, 'loss/train': 2.120286703109741}
-03/05/2022 06:23:30 - INFO - codeparrot_training - Skipping example with length 996 (seq_length=1024)
-03/05/2022 06:23:32 - INFO - codeparrot_training - Step 34825: {'lr': 0.000441728866596892, 'samples': 17830912, 'steps': 34825, 'loss/train': 1.2275387048721313}
-03/05/2022 06:23:36 - INFO - codeparrot_training - Step 34826: {'lr': 0.00044172546096041504, 'samples': 17831424, 'steps': 34826, 'loss/train': 1.0015193223953247}
-03/05/2022 06:23:38 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/05/2022 06:23:41 - INFO - codeparrot_training - Step 34827: {'lr': 0.0004417220552375496, 'samples': 17831936, 'steps': 34827, 'loss/train': 0.7252134680747986}
-03/05/2022 06:23:44 - INFO - codeparrot_training - Step 34828: {'lr': 0.00044171864942829707, 'samples': 17832448, 'steps': 34828, 'loss/train': 1.033115267753601}
-03/05/2022 06:23:46 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/05/2022 06:23:49 - INFO - codeparrot_training - Step 34829: {'lr': 0.0004417152435326591, 'samples': 17832960, 'steps': 34829, 'loss/train': 1.0243782997131348}
-03/05/2022 06:23:53 - INFO - codeparrot_training - Step 34830: {'lr': 0.00044171183755063726, 'samples': 17833472, 'steps': 34830, 'loss/train': 2.412767171859741}
-03/05/2022 06:23:55 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/05/2022 06:23:58 - INFO - codeparrot_training - Step 34831: {'lr': 0.00044170843148223305, 'samples': 17833984, 'steps': 34831, 'loss/train': 2.0161173343658447}
-03/05/2022 06:24:01 - INFO - codeparrot_training - Step 34832: {'lr': 0.0004417050253274479, 'samples': 17834496, 'steps': 34832, 'loss/train': 1.3677895069122314}
-03/05/2022 06:24:03 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/05/2022 06:24:06 - INFO - codeparrot_training - Step 34833: {'lr': 0.00044170161908628345, 'samples': 17835008, 'steps': 34833, 'loss/train': 2.1176159381866455}
-03/05/2022 06:24:09 - INFO - codeparrot_training - Step 34834: {'lr': 0.0004416982127587412, 'samples': 17835520, 'steps': 34834, 'loss/train': 2.0389223098754883}
-03/05/2022 06:24:11 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/05/2022 06:24:15 - INFO - codeparrot_training - Step 34835: {'lr': 0.00044169480634482274, 'samples': 17836032, 'steps': 34835, 'loss/train': 1.626057744026184}
-03/05/2022 06:24:18 - INFO - codeparrot_training - Step 34836: {'lr': 0.0004416913998445294, 'samples': 17836544, 'steps': 34836, 'loss/train': 1.3532754182815552}
-03/05/2022 06:24:20 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/05/2022 06:24:23 - INFO - codeparrot_training - Step 34837: {'lr': 0.000441687993257863, 'samples': 17837056, 'steps': 34837, 'loss/train': 1.734352469444275}
-03/05/2022 06:24:27 - INFO - codeparrot_training - Step 34838: {'lr': 0.000441684586584825, 'samples': 17837568, 'steps': 34838, 'loss/train': 1.7379499673843384}
-03/05/2022 06:24:28 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 06:24:32 - INFO - codeparrot_training - Step 34839: {'lr': 0.0004416811798254168, 'samples': 17838080, 'steps': 34839, 'loss/train': 1.6498956680297852}
-03/05/2022 06:24:35 - INFO - codeparrot_training - Step 34840: {'lr': 0.00044167777297964006, 'samples': 17838592, 'steps': 34840, 'loss/train': 2.126178026199341}
-03/05/2022 06:24:37 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/05/2022 06:24:40 - INFO - codeparrot_training - Step 34841: {'lr': 0.0004416743660474962, 'samples': 17839104, 'steps': 34841, 'loss/train': 2.112391948699951}
-03/05/2022 06:24:44 - INFO - codeparrot_training - Step 34842: {'lr': 0.0004416709590289869, 'samples': 17839616, 'steps': 34842, 'loss/train': 1.608580231666565}
-03/05/2022 06:24:46 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 06:24:49 - INFO - codeparrot_training - Step 34843: {'lr': 0.00044166755192411364, 'samples': 17840128, 'steps': 34843, 'loss/train': 1.6516684293746948}
-03/05/2022 06:24:52 - INFO - codeparrot_training - Step 34844: {'lr': 0.00044166414473287784, 'samples': 17840640, 'steps': 34844, 'loss/train': 1.9520206451416016}
-03/05/2022 06:24:54 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/05/2022 06:24:57 - INFO - codeparrot_training - Step 34845: {'lr': 0.0004416607374552812, 'samples': 17841152, 'steps': 34845, 'loss/train': 0.8440061807632446}
-03/05/2022 06:25:01 - INFO - codeparrot_training - Step 34846: {'lr': 0.00044165733009132524, 'samples': 17841664, 'steps': 34846, 'loss/train': 0.5976382493972778}
-03/05/2022 06:25:03 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/05/2022 06:25:06 - INFO - codeparrot_training - Step 34847: {'lr': 0.00044165392264101136, 'samples': 17842176, 'steps': 34847, 'loss/train': 1.5502822399139404}
-03/05/2022 06:25:09 - INFO - codeparrot_training - Step 34848: {'lr': 0.0004416505151043412, 'samples': 17842688, 'steps': 34848, 'loss/train': 1.9006861448287964}
-03/05/2022 06:25:11 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/05/2022 06:25:14 - INFO - codeparrot_training - Step 34849: {'lr': 0.0004416471074813163, 'samples': 17843200, 'steps': 34849, 'loss/train': 1.16095769405365}
-03/05/2022 06:25:17 - INFO - codeparrot_training - Step 34850: {'lr': 0.0004416436997719382, 'samples': 17843712, 'steps': 34850, 'loss/train': 0.833154559135437}
-03/05/2022 06:25:19 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/05/2022 06:25:22 - INFO - codeparrot_training - Step 34851: {'lr': 0.0004416402919762084, 'samples': 17844224, 'steps': 34851, 'loss/train': 2.4870381355285645}
-03/05/2022 06:25:26 - INFO - codeparrot_training - Step 34852: {'lr': 0.00044163688409412833, 'samples': 17844736, 'steps': 34852, 'loss/train': 2.227492570877075}
-03/05/2022 06:25:27 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/05/2022 06:25:31 - INFO - codeparrot_training - Step 34853: {'lr': 0.0004416334761256997, 'samples': 17845248, 'steps': 34853, 'loss/train': 1.3923370838165283}
-03/05/2022 06:25:34 - INFO - codeparrot_training - Step 34854: {'lr': 0.000441630068070924, 'samples': 17845760, 'steps': 34854, 'loss/train': 0.9838761687278748}
-03/05/2022 06:25:37 - INFO - codeparrot_training - Step 34855: {'lr': 0.0004416266599298028, 'samples': 17846272, 'steps': 34855, 'loss/train': 1.393255591392517}
-03/05/2022 06:25:37 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/05/2022 06:25:43 - INFO - codeparrot_training - Step 34856: {'lr': 0.00044162325170233745, 'samples': 17846784, 'steps': 34856, 'loss/train': 1.5085633993148804}
-03/05/2022 06:25:46 - INFO - codeparrot_training - Step 34857: {'lr': 0.00044161984338852967, 'samples': 17847296, 'steps': 34857, 'loss/train': 1.5105082988739014}
-03/05/2022 06:25:47 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 06:25:52 - INFO - codeparrot_training - Step 34858: {'lr': 0.000441616434988381, 'samples': 17847808, 'steps': 34858, 'loss/train': 1.9892284870147705}
-03/05/2022 06:25:55 - INFO - codeparrot_training - Step 34859: {'lr': 0.00044161302650189295, 'samples': 17848320, 'steps': 34859, 'loss/train': 1.1708277463912964}
-03/05/2022 06:25:56 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/05/2022 06:26:00 - INFO - codeparrot_training - Step 34860: {'lr': 0.00044160961792906694, 'samples': 17848832, 'steps': 34860, 'loss/train': 0.7018491625785828}
-03/05/2022 06:26:03 - INFO - codeparrot_training - Step 34861: {'lr': 0.00044160620926990456, 'samples': 17849344, 'steps': 34861, 'loss/train': 2.1297495365142822}
-03/05/2022 06:26:04 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/05/2022 06:26:09 - INFO - codeparrot_training - Step 34862: {'lr': 0.0004416028005244075, 'samples': 17849856, 'steps': 34862, 'loss/train': 2.461374282836914}
-03/05/2022 06:26:12 - INFO - codeparrot_training - Step 34863: {'lr': 0.0004415993916925771, 'samples': 17850368, 'steps': 34863, 'loss/train': 1.8185118436813354}
-03/05/2022 06:26:13 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/05/2022 06:26:17 - INFO - codeparrot_training - Step 34864: {'lr': 0.000441595982774415, 'samples': 17850880, 'steps': 34864, 'loss/train': 1.9066054821014404}
-03/05/2022 06:26:20 - INFO - codeparrot_training - Step 34865: {'lr': 0.00044159257376992267, 'samples': 17851392, 'steps': 34865, 'loss/train': 0.8716073632240295}
-03/05/2022 06:26:21 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/05/2022 06:26:25 - INFO - codeparrot_training - Step 34866: {'lr': 0.0004415891646791017, 'samples': 17851904, 'steps': 34866, 'loss/train': 2.6436846256256104}
-03/05/2022 06:26:29 - INFO - codeparrot_training - Step 34867: {'lr': 0.0004415857555019536, 'samples': 17852416, 'steps': 34867, 'loss/train': 1.5450636148452759}
-03/05/2022 06:26:30 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/05/2022 06:26:34 - INFO - codeparrot_training - Step 34868: {'lr': 0.00044158234623847993, 'samples': 17852928, 'steps': 34868, 'loss/train': 0.5596045851707458}
-03/05/2022 06:26:37 - INFO - codeparrot_training - Step 34869: {'lr': 0.00044157893688868223, 'samples': 17853440, 'steps': 34869, 'loss/train': 1.8349541425704956}
-03/05/2022 06:26:38 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/05/2022 06:26:42 - INFO - codeparrot_training - Step 34870: {'lr': 0.00044157552745256203, 'samples': 17853952, 'steps': 34870, 'loss/train': 1.8813645839691162}
-03/05/2022 06:26:46 - INFO - codeparrot_training - Step 34871: {'lr': 0.0004415721179301208, 'samples': 17854464, 'steps': 34871, 'loss/train': 2.0009145736694336}
-03/05/2022 06:26:47 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/05/2022 06:26:51 - INFO - codeparrot_training - Step 34872: {'lr': 0.00044156870832136015, 'samples': 17854976, 'steps': 34872, 'loss/train': 1.7372632026672363}
-03/05/2022 06:26:54 - INFO - codeparrot_training - Step 34873: {'lr': 0.00044156529862628157, 'samples': 17855488, 'steps': 34873, 'loss/train': 2.6415295600891113}
-03/05/2022 06:26:55 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/05/2022 06:26:59 - INFO - codeparrot_training - Step 34874: {'lr': 0.00044156188884488667, 'samples': 17856000, 'steps': 34874, 'loss/train': 1.8939578533172607}
-03/05/2022 06:27:02 - INFO - codeparrot_training - Step 34875: {'lr': 0.0004415584789771769, 'samples': 17856512, 'steps': 34875, 'loss/train': 2.014019012451172}
-03/05/2022 06:27:03 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 06:27:08 - INFO - codeparrot_training - Step 34876: {'lr': 0.0004415550690231539, 'samples': 17857024, 'steps': 34876, 'loss/train': 1.6249971389770508}
-03/05/2022 06:27:11 - INFO - codeparrot_training - Step 34877: {'lr': 0.0004415516589828191, 'samples': 17857536, 'steps': 34877, 'loss/train': 1.6736602783203125}
-03/05/2022 06:27:12 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/05/2022 06:27:16 - INFO - codeparrot_training - Step 34878: {'lr': 0.00044154824885617405, 'samples': 17858048, 'steps': 34878, 'loss/train': 1.391919732093811}
-03/05/2022 06:27:19 - INFO - codeparrot_training - Step 34879: {'lr': 0.0004415448386432204, 'samples': 17858560, 'steps': 34879, 'loss/train': 1.7402628660202026}
-03/05/2022 06:27:20 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/05/2022 06:27:24 - INFO - codeparrot_training - Step 34880: {'lr': 0.00044154142834395947, 'samples': 17859072, 'steps': 34880, 'loss/train': 1.3522852659225464}
-03/05/2022 06:27:28 - INFO - codeparrot_training - Step 34881: {'lr': 0.00044153801795839296, 'samples': 17859584, 'steps': 34881, 'loss/train': 1.4678255319595337}
-03/05/2022 06:27:29 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/05/2022 06:27:33 - INFO - codeparrot_training - Step 34882: {'lr': 0.00044153460748652245, 'samples': 17860096, 'steps': 34882, 'loss/train': 2.2553961277008057}
-03/05/2022 06:27:36 - INFO - codeparrot_training - Step 34883: {'lr': 0.00044153119692834944, 'samples': 17860608, 'steps': 34883, 'loss/train': 1.4326810836791992}
-03/05/2022 06:27:37 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/05/2022 06:27:41 - INFO - codeparrot_training - Step 34884: {'lr': 0.0004415277862838753, 'samples': 17861120, 'steps': 34884, 'loss/train': 1.4568833112716675}
-03/05/2022 06:27:44 - INFO - codeparrot_training - Step 34885: {'lr': 0.00044152437555310174, 'samples': 17861632, 'steps': 34885, 'loss/train': 1.6534831523895264}
-03/05/2022 06:27:45 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/05/2022 06:27:50 - INFO - codeparrot_training - Step 34886: {'lr': 0.00044152096473603025, 'samples': 17862144, 'steps': 34886, 'loss/train': 2.23323655128479}
-03/05/2022 06:27:53 - INFO - codeparrot_training - Step 34887: {'lr': 0.00044151755383266234, 'samples': 17862656, 'steps': 34887, 'loss/train': 1.913790225982666}
-03/05/2022 06:27:53 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/05/2022 06:27:58 - INFO - codeparrot_training - Step 34888: {'lr': 0.0004415141428429997, 'samples': 17863168, 'steps': 34888, 'loss/train': 1.3857903480529785}
-03/05/2022 06:28:01 - INFO - codeparrot_training - Step 34889: {'lr': 0.0004415107317670436, 'samples': 17863680, 'steps': 34889, 'loss/train': 2.1948859691619873}
-03/05/2022 06:28:02 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/05/2022 06:28:07 - INFO - codeparrot_training - Step 34890: {'lr': 0.0004415073206047958, 'samples': 17864192, 'steps': 34890, 'loss/train': 0.27649974822998047}
-03/05/2022 06:28:10 - INFO - codeparrot_training - Step 34891: {'lr': 0.0004415039093562577, 'samples': 17864704, 'steps': 34891, 'loss/train': 1.521222710609436}
-03/05/2022 06:28:11 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/05/2022 06:28:15 - INFO - codeparrot_training - Step 34892: {'lr': 0.00044150049802143095, 'samples': 17865216, 'steps': 34892, 'loss/train': 2.058128833770752}
-03/05/2022 06:28:18 - INFO - codeparrot_training - Step 34893: {'lr': 0.00044149708660031704, 'samples': 17865728, 'steps': 34893, 'loss/train': 1.9542064666748047}
-03/05/2022 06:28:20 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/05/2022 06:28:24 - INFO - codeparrot_training - Step 34894: {'lr': 0.0004414936750929174, 'samples': 17866240, 'steps': 34894, 'loss/train': 2.216167449951172}
-03/05/2022 06:28:27 - INFO - codeparrot_training - Step 34895: {'lr': 0.0004414902634992338, 'samples': 17866752, 'steps': 34895, 'loss/train': 1.5830042362213135}
-03/05/2022 06:28:28 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/05/2022 06:28:32 - INFO - codeparrot_training - Step 34896: {'lr': 0.0004414868518192675, 'samples': 17867264, 'steps': 34896, 'loss/train': 1.9079699516296387}
-03/05/2022 06:28:35 - INFO - codeparrot_training - Step 34897: {'lr': 0.0004414834400530203, 'samples': 17867776, 'steps': 34897, 'loss/train': 1.9057271480560303}
-03/05/2022 06:28:36 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/05/2022 06:28:40 - INFO - codeparrot_training - Step 34898: {'lr': 0.00044148002820049354, 'samples': 17868288, 'steps': 34898, 'loss/train': 1.3559982776641846}
-03/05/2022 06:28:44 - INFO - codeparrot_training - Step 34899: {'lr': 0.00044147661626168887, 'samples': 17868800, 'steps': 34899, 'loss/train': 1.4642717838287354}
-03/05/2022 06:28:44 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/05/2022 06:28:49 - INFO - codeparrot_training - Step 34900: {'lr': 0.0004414732042366078, 'samples': 17869312, 'steps': 34900, 'loss/train': 1.8140931129455566}
-03/05/2022 06:28:52 - INFO - codeparrot_training - Step 34901: {'lr': 0.00044146979212525184, 'samples': 17869824, 'steps': 34901, 'loss/train': 1.3249456882476807}
-03/05/2022 06:28:53 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/05/2022 06:28:57 - INFO - codeparrot_training - Step 34902: {'lr': 0.0004414663799276225, 'samples': 17870336, 'steps': 34902, 'loss/train': 1.7898298501968384}
-03/05/2022 06:29:01 - INFO - codeparrot_training - Step 34903: {'lr': 0.0004414629676437214, 'samples': 17870848, 'steps': 34903, 'loss/train': 1.941007375717163}
-03/05/2022 06:29:01 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/05/2022 06:29:06 - INFO - codeparrot_training - Step 34904: {'lr': 0.00044145955527355007, 'samples': 17871360, 'steps': 34904, 'loss/train': 2.0956506729125977}
-03/05/2022 06:29:09 - INFO - codeparrot_training - Step 34905: {'lr': 0.00044145614281711, 'samples': 17871872, 'steps': 34905, 'loss/train': 1.3394807577133179}
-03/05/2022 06:29:11 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/05/2022 06:29:14 - INFO - codeparrot_training - Step 34906: {'lr': 0.00044145273027440275, 'samples': 17872384, 'steps': 34906, 'loss/train': 1.3507471084594727}
-03/05/2022 06:29:17 - INFO - codeparrot_training - Step 34907: {'lr': 0.0004414493176454298, 'samples': 17872896, 'steps': 34907, 'loss/train': 1.6828564405441284}
-03/05/2022 06:29:19 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/05/2022 06:29:23 - INFO - codeparrot_training - Step 34908: {'lr': 0.0004414459049301929, 'samples': 17873408, 'steps': 34908, 'loss/train': 1.4212250709533691}
-03/05/2022 06:29:26 - INFO - codeparrot_training - Step 34909: {'lr': 0.00044144249212869327, 'samples': 17873920, 'steps': 34909, 'loss/train': 1.5350430011749268}
-03/05/2022 06:29:27 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/05/2022 06:29:31 - INFO - codeparrot_training - Step 34910: {'lr': 0.0004414390792409326, 'samples': 17874432, 'steps': 34910, 'loss/train': 1.6525355577468872}
-03/05/2022 06:29:34 - INFO - codeparrot_training - Step 34911: {'lr': 0.0004414356662669126, 'samples': 17874944, 'steps': 34911, 'loss/train': 2.043109893798828}
-03/05/2022 06:29:36 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/05/2022 06:29:40 - INFO - codeparrot_training - Step 34912: {'lr': 0.0004414322532066345, 'samples': 17875456, 'steps': 34912, 'loss/train': 1.9442780017852783}
-03/05/2022 06:29:43 - INFO - codeparrot_training - Step 34913: {'lr': 0.0004414288400601, 'samples': 17875968, 'steps': 34913, 'loss/train': 1.5154223442077637}
-03/05/2022 06:29:44 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/05/2022 06:29:48 - INFO - codeparrot_training - Step 34914: {'lr': 0.0004414254268273107, 'samples': 17876480, 'steps': 34914, 'loss/train': 1.9016990661621094}
-03/05/2022 06:29:51 - INFO - codeparrot_training - Step 34915: {'lr': 0.0004414220135082679, 'samples': 17876992, 'steps': 34915, 'loss/train': 1.9976986646652222}
-03/05/2022 06:29:52 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/05/2022 06:29:56 - INFO - codeparrot_training - Step 34916: {'lr': 0.0004414186001029734, 'samples': 17877504, 'steps': 34916, 'loss/train': 2.005429983139038}
-03/05/2022 06:30:00 - INFO - codeparrot_training - Step 34917: {'lr': 0.00044141518661142864, 'samples': 17878016, 'steps': 34917, 'loss/train': 1.9350430965423584}
-03/05/2022 06:30:01 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/05/2022 06:30:05 - INFO - codeparrot_training - Step 34918: {'lr': 0.0004414117730336351, 'samples': 17878528, 'steps': 34918, 'loss/train': 2.531646966934204}
-03/05/2022 06:30:08 - INFO - codeparrot_training - Step 34919: {'lr': 0.0004414083593695944, 'samples': 17879040, 'steps': 34919, 'loss/train': 1.0820378065109253}
-03/05/2022 06:30:09 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/05/2022 06:30:13 - INFO - codeparrot_training - Step 34920: {'lr': 0.0004414049456193081, 'samples': 17879552, 'steps': 34920, 'loss/train': 2.08001446723938}
-03/05/2022 06:30:17 - INFO - codeparrot_training - Step 34921: {'lr': 0.00044140153178277765, 'samples': 17880064, 'steps': 34921, 'loss/train': 1.464718222618103}
-03/05/2022 06:30:22 - INFO - codeparrot_training - Step 34922: {'lr': 0.0004413981178600046, 'samples': 17880576, 'steps': 34922, 'loss/train': 1.1355311870574951}
-03/05/2022 06:30:25 - INFO - codeparrot_training - Step 34923: {'lr': 0.00044139470385099047, 'samples': 17881088, 'steps': 34923, 'loss/train': 2.5171875953674316}
-03/05/2022 06:30:26 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 06:30:30 - INFO - codeparrot_training - Step 34924: {'lr': 0.0004413912897557369, 'samples': 17881600, 'steps': 34924, 'loss/train': 1.6745734214782715}
-03/05/2022 06:30:34 - INFO - codeparrot_training - Step 34925: {'lr': 0.0004413878755742454, 'samples': 17882112, 'steps': 34925, 'loss/train': 2.324354410171509}
-03/05/2022 06:30:34 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/05/2022 06:30:39 - INFO - codeparrot_training - Step 34926: {'lr': 0.00044138446130651736, 'samples': 17882624, 'steps': 34926, 'loss/train': 1.5801204442977905}
-03/05/2022 06:30:42 - INFO - codeparrot_training - Step 34927: {'lr': 0.00044138104695255455, 'samples': 17883136, 'steps': 34927, 'loss/train': 0.6715707778930664}
-03/05/2022 06:30:43 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/05/2022 06:30:47 - INFO - codeparrot_training - Step 34928: {'lr': 0.00044137763251235837, 'samples': 17883648, 'steps': 34928, 'loss/train': 1.1433969736099243}
-03/05/2022 06:30:50 - INFO - codeparrot_training - Step 34929: {'lr': 0.0004413742179859304, 'samples': 17884160, 'steps': 34929, 'loss/train': 1.5350388288497925}
-03/05/2022 06:30:51 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/05/2022 06:30:56 - INFO - codeparrot_training - Step 34930: {'lr': 0.00044137080337327205, 'samples': 17884672, 'steps': 34930, 'loss/train': 1.422473669052124}
-03/05/2022 06:30:59 - INFO - codeparrot_training - Step 34931: {'lr': 0.000441367388674385, 'samples': 17885184, 'steps': 34931, 'loss/train': 1.985186219215393}
-03/05/2022 06:31:00 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 06:31:04 - INFO - codeparrot_training - Step 34932: {'lr': 0.00044136397388927083, 'samples': 17885696, 'steps': 34932, 'loss/train': 1.69344961643219}
-03/05/2022 06:31:07 - INFO - codeparrot_training - Step 34933: {'lr': 0.000441360559017931, 'samples': 17886208, 'steps': 34933, 'loss/train': 0.6037330031394958}
-03/05/2022 06:31:08 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/05/2022 06:31:13 - INFO - codeparrot_training - Step 34934: {'lr': 0.00044135714406036696, 'samples': 17886720, 'steps': 34934, 'loss/train': 1.2142333984375}
-03/05/2022 06:31:16 - INFO - codeparrot_training - Step 34935: {'lr': 0.00044135372901658046, 'samples': 17887232, 'steps': 34935, 'loss/train': 2.2215306758880615}
-03/05/2022 06:31:17 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/05/2022 06:31:21 - INFO - codeparrot_training - Step 34936: {'lr': 0.0004413503138865729, 'samples': 17887744, 'steps': 34936, 'loss/train': 1.8244150876998901}
-03/05/2022 06:31:24 - INFO - codeparrot_training - Step 34937: {'lr': 0.00044134689867034583, 'samples': 17888256, 'steps': 34937, 'loss/train': 1.8244725465774536}
-03/05/2022 06:31:25 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/05/2022 06:31:29 - INFO - codeparrot_training - Step 34938: {'lr': 0.00044134348336790074, 'samples': 17888768, 'steps': 34938, 'loss/train': 2.8450660705566406}
-03/05/2022 06:31:33 - INFO - codeparrot_training - Step 34939: {'lr': 0.0004413400679792393, 'samples': 17889280, 'steps': 34939, 'loss/train': 1.809972882270813}
-03/05/2022 06:31:34 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/05/2022 06:31:38 - INFO - codeparrot_training - Step 34940: {'lr': 0.00044133665250436295, 'samples': 17889792, 'steps': 34940, 'loss/train': 1.190192699432373}
-03/05/2022 06:31:41 - INFO - codeparrot_training - Step 34941: {'lr': 0.00044133323694327324, 'samples': 17890304, 'steps': 34941, 'loss/train': 1.6284505128860474}
-03/05/2022 06:31:42 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/05/2022 06:31:46 - INFO - codeparrot_training - Step 34942: {'lr': 0.0004413298212959718, 'samples': 17890816, 'steps': 34942, 'loss/train': 2.1109745502471924}
-03/05/2022 06:31:49 - INFO - codeparrot_training - Step 34943: {'lr': 0.00044132640556246, 'samples': 17891328, 'steps': 34943, 'loss/train': 2.0893192291259766}
-03/05/2022 06:31:50 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/05/2022 06:31:55 - INFO - codeparrot_training - Step 34944: {'lr': 0.00044132298974273955, 'samples': 17891840, 'steps': 34944, 'loss/train': 1.3159205913543701}
-03/05/2022 06:31:58 - INFO - codeparrot_training - Step 34945: {'lr': 0.00044131957383681186, 'samples': 17892352, 'steps': 34945, 'loss/train': 1.7453482151031494}
-03/05/2022 06:31:59 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/05/2022 06:32:03 - INFO - codeparrot_training - Step 34946: {'lr': 0.0004413161578446785, 'samples': 17892864, 'steps': 34946, 'loss/train': 1.7412831783294678}
-03/05/2022 06:32:06 - INFO - codeparrot_training - Step 34947: {'lr': 0.00044131274176634113, 'samples': 17893376, 'steps': 34947, 'loss/train': 2.1667580604553223}
-03/05/2022 06:32:07 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/05/2022 06:32:12 - INFO - codeparrot_training - Step 34948: {'lr': 0.00044130932560180114, 'samples': 17893888, 'steps': 34948, 'loss/train': 1.0999799966812134}
-03/05/2022 06:32:15 - INFO - codeparrot_training - Step 34949: {'lr': 0.0004413059093510601, 'samples': 17894400, 'steps': 34949, 'loss/train': 6.522251605987549}
-03/05/2022 06:32:17 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/05/2022 06:32:20 - INFO - codeparrot_training - Step 34950: {'lr': 0.00044130249301411957, 'samples': 17894912, 'steps': 34950, 'loss/train': 1.9802055358886719}
-03/05/2022 06:32:23 - INFO - codeparrot_training - Step 34951: {'lr': 0.0004412990765909811, 'samples': 17895424, 'steps': 34951, 'loss/train': 1.7496472597122192}
-03/05/2022 06:32:25 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/05/2022 06:32:29 - INFO - codeparrot_training - Step 34952: {'lr': 0.0004412956600816462, 'samples': 17895936, 'steps': 34952, 'loss/train': 1.7567912340164185}
-03/05/2022 06:32:32 - INFO - codeparrot_training - Step 34953: {'lr': 0.00044129224348611644, 'samples': 17896448, 'steps': 34953, 'loss/train': 1.2723947763442993}
-03/05/2022 06:32:33 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/05/2022 06:32:37 - INFO - codeparrot_training - Step 34954: {'lr': 0.0004412888268043934, 'samples': 17896960, 'steps': 34954, 'loss/train': 1.2555564641952515}
-03/05/2022 06:32:40 - INFO - codeparrot_training - Step 34955: {'lr': 0.0004412854100364785, 'samples': 17897472, 'steps': 34955, 'loss/train': 1.5003790855407715}
-03/05/2022 06:32:42 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/05/2022 06:32:45 - INFO - codeparrot_training - Step 34956: {'lr': 0.0004412819931823734, 'samples': 17897984, 'steps': 34956, 'loss/train': 2.3147830963134766}
-03/05/2022 06:32:49 - INFO - codeparrot_training - Step 34957: {'lr': 0.0004412785762420795, 'samples': 17898496, 'steps': 34957, 'loss/train': 0.25216546654701233}
-03/05/2022 06:32:51 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/05/2022 06:32:54 - INFO - codeparrot_training - Step 34958: {'lr': 0.0004412751592155985, 'samples': 17899008, 'steps': 34958, 'loss/train': 2.6953213214874268}
-03/05/2022 06:32:57 - INFO - codeparrot_training - Step 34959: {'lr': 0.00044127174210293186, 'samples': 17899520, 'steps': 34959, 'loss/train': 2.280088424682617}
-03/05/2022 06:32:59 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/05/2022 06:33:02 - INFO - codeparrot_training - Step 34960: {'lr': 0.0004412683249040811, 'samples': 17900032, 'steps': 34960, 'loss/train': 2.6089258193969727}
-03/05/2022 06:33:06 - INFO - codeparrot_training - Step 34961: {'lr': 0.0004412649076190478, 'samples': 17900544, 'steps': 34961, 'loss/train': 1.863905668258667}
-03/05/2022 06:33:08 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 06:33:11 - INFO - codeparrot_training - Step 34962: {'lr': 0.00044126149024783346, 'samples': 17901056, 'steps': 34962, 'loss/train': 2.5443789958953857}
-03/05/2022 06:33:14 - INFO - codeparrot_training - Step 34963: {'lr': 0.0004412580727904396, 'samples': 17901568, 'steps': 34963, 'loss/train': 1.5223264694213867}
-03/05/2022 06:33:17 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/05/2022 06:33:19 - INFO - codeparrot_training - Step 34964: {'lr': 0.0004412546552468679, 'samples': 17902080, 'steps': 34964, 'loss/train': 1.4610614776611328}
-03/05/2022 06:33:23 - INFO - codeparrot_training - Step 34965: {'lr': 0.00044125123761711975, 'samples': 17902592, 'steps': 34965, 'loss/train': 1.9106993675231934}
-03/05/2022 06:33:25 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/05/2022 06:33:28 - INFO - codeparrot_training - Step 34966: {'lr': 0.00044124781990119677, 'samples': 17903104, 'steps': 34966, 'loss/train': 1.859367847442627}
-03/05/2022 06:33:31 - INFO - codeparrot_training - Step 34967: {'lr': 0.0004412444020991004, 'samples': 17903616, 'steps': 34967, 'loss/train': 1.2246556282043457}
-03/05/2022 06:33:33 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/05/2022 06:33:36 - INFO - codeparrot_training - Step 34968: {'lr': 0.0004412409842108324, 'samples': 17904128, 'steps': 34968, 'loss/train': 1.358432412147522}
-03/05/2022 06:33:40 - INFO - codeparrot_training - Step 34969: {'lr': 0.0004412375662363941, 'samples': 17904640, 'steps': 34969, 'loss/train': 2.53106951713562}
-03/05/2022 06:33:42 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/05/2022 06:33:45 - INFO - codeparrot_training - Step 34970: {'lr': 0.00044123414817578705, 'samples': 17905152, 'steps': 34970, 'loss/train': 1.6233115196228027}
-03/05/2022 06:33:48 - INFO - codeparrot_training - Step 34971: {'lr': 0.00044123073002901286, 'samples': 17905664, 'steps': 34971, 'loss/train': 1.4780207872390747}
-03/05/2022 06:33:50 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/05/2022 06:33:53 - INFO - codeparrot_training - Step 34972: {'lr': 0.0004412273117960731, 'samples': 17906176, 'steps': 34972, 'loss/train': 1.4425920248031616}
-03/05/2022 06:33:56 - INFO - codeparrot_training - Step 34973: {'lr': 0.00044122389347696925, 'samples': 17906688, 'steps': 34973, 'loss/train': 1.4676014184951782}
-03/05/2022 06:33:59 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/05/2022 06:34:02 - INFO - codeparrot_training - Step 34974: {'lr': 0.0004412204750717028, 'samples': 17907200, 'steps': 34974, 'loss/train': 1.9555248022079468}
-03/05/2022 06:34:05 - INFO - codeparrot_training - Step 34975: {'lr': 0.00044121705658027545, 'samples': 17907712, 'steps': 34975, 'loss/train': 1.5807853937149048}
-03/05/2022 06:34:07 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/05/2022 06:34:10 - INFO - codeparrot_training - Step 34976: {'lr': 0.00044121363800268853, 'samples': 17908224, 'steps': 34976, 'loss/train': 1.85499107837677}
-03/05/2022 06:34:13 - INFO - codeparrot_training - Step 34977: {'lr': 0.0004412102193389438, 'samples': 17908736, 'steps': 34977, 'loss/train': 1.8151769638061523}
-03/05/2022 06:34:16 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/05/2022 06:34:18 - INFO - codeparrot_training - Step 34978: {'lr': 0.0004412068005890427, 'samples': 17909248, 'steps': 34978, 'loss/train': 1.7757508754730225}
-03/05/2022 06:34:22 - INFO - codeparrot_training - Step 34979: {'lr': 0.0004412033817529867, 'samples': 17909760, 'steps': 34979, 'loss/train': 0.6116886138916016}
-03/05/2022 06:34:24 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/05/2022 06:34:27 - INFO - codeparrot_training - Step 34980: {'lr': 0.0004411999628307775, 'samples': 17910272, 'steps': 34980, 'loss/train': 1.2069125175476074}
-03/05/2022 06:34:30 - INFO - codeparrot_training - Step 34981: {'lr': 0.0004411965438224164, 'samples': 17910784, 'steps': 34981, 'loss/train': 1.580447793006897}
-03/05/2022 06:34:33 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/05/2022 06:34:35 - INFO - codeparrot_training - Step 34982: {'lr': 0.0004411931247279052, 'samples': 17911296, 'steps': 34982, 'loss/train': 0.15457546710968018}
-03/05/2022 06:34:38 - INFO - codeparrot_training - Step 34983: {'lr': 0.00044118970554724523, 'samples': 17911808, 'steps': 34983, 'loss/train': 1.6314420700073242}
-03/05/2022 06:34:41 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/05/2022 06:34:44 - INFO - codeparrot_training - Step 34984: {'lr': 0.0004411862862804382, 'samples': 17912320, 'steps': 34984, 'loss/train': 0.7085153460502625}
-03/05/2022 06:34:47 - INFO - codeparrot_training - Step 34985: {'lr': 0.0004411828669274856, 'samples': 17912832, 'steps': 34985, 'loss/train': 1.6789199113845825}
-03/05/2022 06:34:50 - INFO - codeparrot_training - Step 34986: {'lr': 0.0004411794474883889, 'samples': 17913344, 'steps': 34986, 'loss/train': 1.7990858554840088}
-03/05/2022 06:34:50 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/05/2022 06:34:56 - INFO - codeparrot_training - Step 34987: {'lr': 0.0004411760279631497, 'samples': 17913856, 'steps': 34987, 'loss/train': 1.3297609090805054}
-03/05/2022 06:34:58 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/05/2022 06:35:01 - INFO - codeparrot_training - Step 34988: {'lr': 0.0004411726083517696, 'samples': 17914368, 'steps': 34988, 'loss/train': 1.4986047744750977}
-03/05/2022 06:35:04 - INFO - codeparrot_training - Step 34989: {'lr': 0.00044116918865425004, 'samples': 17914880, 'steps': 34989, 'loss/train': 1.6168302297592163}
-03/05/2022 06:35:07 - INFO - codeparrot_training - Step 34990: {'lr': 0.00044116576887059255, 'samples': 17915392, 'steps': 34990, 'loss/train': 1.833122968673706}
-03/05/2022 06:35:13 - INFO - codeparrot_training - Step 34991: {'lr': 0.0004411623490007988, 'samples': 17915904, 'steps': 34991, 'loss/train': 1.6909750699996948}
-03/05/2022 06:35:16 - INFO - codeparrot_training - Step 34992: {'lr': 0.0004411589290448701, 'samples': 17916416, 'steps': 34992, 'loss/train': 2.2682623863220215}
-03/05/2022 06:35:16 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/05/2022 06:35:21 - INFO - codeparrot_training - Step 34993: {'lr': 0.0004411555090028082, 'samples': 17916928, 'steps': 34993, 'loss/train': 1.3395839929580688}
-03/05/2022 06:35:24 - INFO - codeparrot_training - Step 34994: {'lr': 0.00044115208887461464, 'samples': 17917440, 'steps': 34994, 'loss/train': 1.7266957759857178}
-03/05/2022 06:35:25 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/05/2022 06:35:30 - INFO - codeparrot_training - Step 34995: {'lr': 0.00044114866866029086, 'samples': 17917952, 'steps': 34995, 'loss/train': 1.4539505243301392}
-03/05/2022 06:35:33 - INFO - codeparrot_training - Step 34996: {'lr': 0.00044114524835983844, 'samples': 17918464, 'steps': 34996, 'loss/train': 1.9073495864868164}
-03/05/2022 06:35:34 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/05/2022 06:35:38 - INFO - codeparrot_training - Step 34997: {'lr': 0.00044114182797325884, 'samples': 17918976, 'steps': 34997, 'loss/train': 1.963602900505066}
-03/05/2022 06:35:41 - INFO - codeparrot_training - Step 34998: {'lr': 0.0004411384075005538, 'samples': 17919488, 'steps': 34998, 'loss/train': 0.9859839081764221}
-03/05/2022 06:35:42 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/05/2022 06:35:47 - INFO - codeparrot_training - Step 34999: {'lr': 0.0004411349869417247, 'samples': 17920000, 'steps': 34999, 'loss/train': 1.3265409469604492}
-03/05/2022 06:35:47 - INFO - codeparrot_training - Evaluating and saving model checkpoint
-03/05/2022 06:36:01 - WARNING - huggingface_hub.repository - Several commits (7) will be pushed upstream.
-03/05/2022 06:36:01 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
-03/05/2022 06:36:26 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/cm_code_clippy
-   8908229..eeb78f1  glowing-puddle-3 -> glowing-puddle-3
-
-03/05/2022 06:36:31 - INFO - codeparrot_training - Step 35000: {'lr': 0.00044113156629677313, 'samples': 17920512, 'steps': 35000, 'loss/train': 2.0515060424804688}
-03/05/2022 06:36:32 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/05/2022 06:36:37 - INFO - codeparrot_training - Step 35001: {'lr': 0.00044112814556570066, 'samples': 17921024, 'steps': 35001, 'loss/train': 1.841289758682251}
-03/05/2022 06:36:40 - INFO - codeparrot_training - Step 35002: {'lr': 0.00044112472474850875, 'samples': 17921536, 'steps': 35002, 'loss/train': 1.5218960046768188}
-03/05/2022 06:36:40 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/05/2022 06:36:45 - INFO - codeparrot_training - Step 35003: {'lr': 0.000441121303845199, 'samples': 17922048, 'steps': 35003, 'loss/train': 2.270785331726074}
-03/05/2022 06:36:48 - INFO - codeparrot_training - Step 35004: {'lr': 0.0004411178828557729, 'samples': 17922560, 'steps': 35004, 'loss/train': 1.8769875764846802}
-03/05/2022 06:36:49 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/05/2022 06:36:53 - INFO - codeparrot_training - Step 35005: {'lr': 0.00044111446178023205, 'samples': 17923072, 'steps': 35005, 'loss/train': 1.5740808248519897}
-03/05/2022 06:36:57 - INFO - codeparrot_training - Step 35006: {'lr': 0.000441111040618578, 'samples': 17923584, 'steps': 35006, 'loss/train': 1.4152005910873413}
-03/05/2022 06:36:57 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/05/2022 06:37:02 - INFO - codeparrot_training - Step 35007: {'lr': 0.0004411076193708122, 'samples': 17924096, 'steps': 35007, 'loss/train': 2.161975622177124}
-03/05/2022 06:37:05 - INFO - codeparrot_training - Step 35008: {'lr': 0.00044110419803693635, 'samples': 17924608, 'steps': 35008, 'loss/train': 1.4361581802368164}
-03/05/2022 06:37:05 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 06:37:10 - INFO - codeparrot_training - Step 35009: {'lr': 0.00044110077661695194, 'samples': 17925120, 'steps': 35009, 'loss/train': 1.1023637056350708}
-03/05/2022 06:37:13 - INFO - codeparrot_training - Step 35010: {'lr': 0.00044109735511086036, 'samples': 17925632, 'steps': 35010, 'loss/train': 0.7857583165168762}
-03/05/2022 06:37:14 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/05/2022 06:37:19 - INFO - codeparrot_training - Step 35011: {'lr': 0.00044109393351866324, 'samples': 17926144, 'steps': 35011, 'loss/train': 1.357399344444275}
-03/05/2022 06:37:22 - INFO - codeparrot_training - Step 35012: {'lr': 0.0004410905118403622, 'samples': 17926656, 'steps': 35012, 'loss/train': 1.7133471965789795}
-03/05/2022 06:37:22 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 06:37:27 - INFO - codeparrot_training - Step 35013: {'lr': 0.0004410870900759587, 'samples': 17927168, 'steps': 35013, 'loss/train': 1.2567002773284912}
-03/05/2022 06:37:30 - INFO - codeparrot_training - Step 35014: {'lr': 0.0004410836682254543, 'samples': 17927680, 'steps': 35014, 'loss/train': 1.4750494956970215}
-03/05/2022 06:37:30 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/05/2022 06:37:36 - INFO - codeparrot_training - Step 35015: {'lr': 0.0004410802462888506, 'samples': 17928192, 'steps': 35015, 'loss/train': 1.8269269466400146}
-03/05/2022 06:37:39 - INFO - codeparrot_training - Step 35016: {'lr': 0.00044107682426614903, 'samples': 17928704, 'steps': 35016, 'loss/train': 1.7890626192092896}
-03/05/2022 06:37:39 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/05/2022 06:37:44 - INFO - codeparrot_training - Step 35017: {'lr': 0.00044107340215735125, 'samples': 17929216, 'steps': 35017, 'loss/train': 1.8668313026428223}
-03/05/2022 06:37:47 - INFO - codeparrot_training - Step 35018: {'lr': 0.00044106997996245866, 'samples': 17929728, 'steps': 35018, 'loss/train': 0.7927989363670349}
-03/05/2022 06:37:48 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/05/2022 06:37:53 - INFO - codeparrot_training - Step 35019: {'lr': 0.000441066557681473, 'samples': 17930240, 'steps': 35019, 'loss/train': 1.561155915260315}
-03/05/2022 06:37:56 - INFO - codeparrot_training - Step 35020: {'lr': 0.00044106313531439565, 'samples': 17930752, 'steps': 35020, 'loss/train': 1.696244716644287}
-03/05/2022 06:37:56 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/05/2022 06:38:01 - INFO - codeparrot_training - Step 35021: {'lr': 0.00044105971286122816, 'samples': 17931264, 'steps': 35021, 'loss/train': 1.4708157777786255}
-03/05/2022 06:38:04 - INFO - codeparrot_training - Step 35022: {'lr': 0.00044105629032197214, 'samples': 17931776, 'steps': 35022, 'loss/train': 1.0895287990570068}
-03/05/2022 06:38:04 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/05/2022 06:38:09 - INFO - codeparrot_training - Step 35023: {'lr': 0.0004410528676966291, 'samples': 17932288, 'steps': 35023, 'loss/train': 2.0822582244873047}
-03/05/2022 06:38:12 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 06:38:15 - INFO - codeparrot_training - Step 35024: {'lr': 0.00044104944498520054, 'samples': 17932800, 'steps': 35024, 'loss/train': 2.231043577194214}
-03/05/2022 06:38:18 - INFO - codeparrot_training - Step 35025: {'lr': 0.00044104602218768805, 'samples': 17933312, 'steps': 35025, 'loss/train': 0.7925736904144287}
-03/05/2022 06:38:21 - INFO - codeparrot_training - Step 35026: {'lr': 0.0004410425993040933, 'samples': 17933824, 'steps': 35026, 'loss/train': 0.7658699750900269}
-03/05/2022 06:38:21 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/05/2022 06:38:26 - INFO - codeparrot_training - Step 35027: {'lr': 0.0004410391763344176, 'samples': 17934336, 'steps': 35027, 'loss/train': 1.8230595588684082}
-03/05/2022 06:38:29 - INFO - codeparrot_training - Step 35028: {'lr': 0.00044103575327866264, 'samples': 17934848, 'steps': 35028, 'loss/train': 0.8513350486755371}
-03/05/2022 06:38:30 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/05/2022 06:38:35 - INFO - codeparrot_training - Step 35029: {'lr': 0.0004410323301368299, 'samples': 17935360, 'steps': 35029, 'loss/train': 1.2549076080322266}
-03/05/2022 06:38:38 - INFO - codeparrot_training - Step 35030: {'lr': 0.0004410289069089209, 'samples': 17935872, 'steps': 35030, 'loss/train': 0.9950276017189026}
-03/05/2022 06:38:38 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/05/2022 06:38:43 - INFO - codeparrot_training - Step 35031: {'lr': 0.0004410254835949372, 'samples': 17936384, 'steps': 35031, 'loss/train': 1.5624009370803833}
-03/05/2022 06:38:46 - INFO - codeparrot_training - Step 35032: {'lr': 0.00044102206019488045, 'samples': 17936896, 'steps': 35032, 'loss/train': 1.736935019493103}
-03/05/2022 06:38:46 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/05/2022 06:38:51 - INFO - codeparrot_training - Step 35033: {'lr': 0.00044101863670875207, 'samples': 17937408, 'steps': 35033, 'loss/train': 1.5070401430130005}
-03/05/2022 06:38:55 - INFO - codeparrot_training - Step 35034: {'lr': 0.0004410152131365536, 'samples': 17937920, 'steps': 35034, 'loss/train': 1.9382750988006592}
-03/05/2022 06:38:55 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/05/2022 06:39:00 - INFO - codeparrot_training - Step 35035: {'lr': 0.00044101178947828667, 'samples': 17938432, 'steps': 35035, 'loss/train': 1.5708887577056885}
-03/05/2022 06:39:03 - INFO - codeparrot_training - Step 35036: {'lr': 0.0004410083657339528, 'samples': 17938944, 'steps': 35036, 'loss/train': 0.526353657245636}
-03/05/2022 06:39:03 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/05/2022 06:39:09 - INFO - codeparrot_training - Step 35037: {'lr': 0.00044100494190355347, 'samples': 17939456, 'steps': 35037, 'loss/train': 1.95433509349823}
-03/05/2022 06:39:12 - INFO - codeparrot_training - Step 35038: {'lr': 0.0004410015179870903, 'samples': 17939968, 'steps': 35038, 'loss/train': 2.5283753871917725}
-03/05/2022 06:39:12 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/05/2022 06:39:17 - INFO - codeparrot_training - Step 35039: {'lr': 0.0004409980939845647, 'samples': 17940480, 'steps': 35039, 'loss/train': 0.9857442378997803}
-03/05/2022 06:39:20 - INFO - codeparrot_training - Step 35040: {'lr': 0.00044099466989597837, 'samples': 17940992, 'steps': 35040, 'loss/train': 1.505144715309143}
-03/05/2022 06:39:20 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/05/2022 06:39:25 - INFO - codeparrot_training - Step 35041: {'lr': 0.00044099124572133283, 'samples': 17941504, 'steps': 35041, 'loss/train': 0.5281742215156555}
-03/05/2022 06:39:29 - INFO - codeparrot_training - Step 35042: {'lr': 0.00044098782146062955, 'samples': 17942016, 'steps': 35042, 'loss/train': 2.0821478366851807}
-03/05/2022 06:39:29 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 06:39:34 - INFO - codeparrot_training - Step 35043: {'lr': 0.00044098439711387006, 'samples': 17942528, 'steps': 35043, 'loss/train': 1.319618821144104}
-03/05/2022 06:39:37 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/05/2022 06:39:39 - INFO - codeparrot_training - Step 35044: {'lr': 0.000440980972681056, 'samples': 17943040, 'steps': 35044, 'loss/train': 1.1478744745254517}
-03/05/2022 06:39:42 - INFO - codeparrot_training - Step 35045: {'lr': 0.0004409775481621888, 'samples': 17943552, 'steps': 35045, 'loss/train': 2.1830549240112305}
-03/05/2022 06:39:46 - INFO - codeparrot_training - Step 35046: {'lr': 0.0004409741235572701, 'samples': 17944064, 'steps': 35046, 'loss/train': 1.6463422775268555}
-03/05/2022 06:39:47 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/05/2022 06:39:51 - INFO - codeparrot_training - Step 35047: {'lr': 0.0004409706988663015, 'samples': 17944576, 'steps': 35047, 'loss/train': 1.2908602952957153}
-03/05/2022 06:39:54 - INFO - codeparrot_training - Step 35048: {'lr': 0.00044096727408928426, 'samples': 17945088, 'steps': 35048, 'loss/train': 2.0445375442504883}
-03/05/2022 06:39:55 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/05/2022 06:40:00 - INFO - codeparrot_training - Step 35049: {'lr': 0.0004409638492262202, 'samples': 17945600, 'steps': 35049, 'loss/train': 0.5649662017822266}
-03/05/2022 06:40:03 - INFO - codeparrot_training - Step 35050: {'lr': 0.0004409604242771108, 'samples': 17946112, 'steps': 35050, 'loss/train': 0.9336749911308289}
-03/05/2022 06:40:05 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/05/2022 06:40:08 - INFO - codeparrot_training - Step 35051: {'lr': 0.0004409569992419576, 'samples': 17946624, 'steps': 35051, 'loss/train': 1.5632200241088867}
-03/05/2022 06:40:11 - INFO - codeparrot_training - Step 35052: {'lr': 0.0004409535741207621, 'samples': 17947136, 'steps': 35052, 'loss/train': 1.0504883527755737}
-03/05/2022 06:40:14 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/05/2022 06:40:17 - INFO - codeparrot_training - Step 35053: {'lr': 0.00044095014891352584, 'samples': 17947648, 'steps': 35053, 'loss/train': 1.9159879684448242}
-03/05/2022 06:40:20 - INFO - codeparrot_training - Step 35054: {'lr': 0.0004409467236202505, 'samples': 17948160, 'steps': 35054, 'loss/train': 2.7451696395874023}
-03/05/2022 06:40:23 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/05/2022 06:40:25 - INFO - codeparrot_training - Step 35055: {'lr': 0.0004409432982409374, 'samples': 17948672, 'steps': 35055, 'loss/train': 1.2476372718811035}
-03/05/2022 06:40:28 - INFO - codeparrot_training - Step 35056: {'lr': 0.0004409398727755882, 'samples': 17949184, 'steps': 35056, 'loss/train': 1.654170036315918}
-03/05/2022 06:40:31 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/05/2022 06:40:34 - INFO - codeparrot_training - Step 35057: {'lr': 0.00044093644722420445, 'samples': 17949696, 'steps': 35057, 'loss/train': 1.350480079650879}
-03/05/2022 06:40:37 - INFO - codeparrot_training - Step 35058: {'lr': 0.00044093302158678766, 'samples': 17950208, 'steps': 35058, 'loss/train': 2.369255542755127}
-03/05/2022 06:40:40 - INFO - codeparrot_training - Step 35059: {'lr': 0.0004409295958633394, 'samples': 17950720, 'steps': 35059, 'loss/train': 1.305041790008545}
-03/05/2022 06:40:40 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 06:40:45 - INFO - codeparrot_training - Step 35060: {'lr': 0.00044092617005386125, 'samples': 17951232, 'steps': 35060, 'loss/train': 0.16362528502941132}
-03/05/2022 06:40:48 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/05/2022 06:40:51 - INFO - codeparrot_training - Step 35061: {'lr': 0.00044092274415835473, 'samples': 17951744, 'steps': 35061, 'loss/train': 2.0974016189575195}
-03/05/2022 06:40:54 - INFO - codeparrot_training - Step 35062: {'lr': 0.0004409193181768213, 'samples': 17952256, 'steps': 35062, 'loss/train': 1.3911359310150146}
-03/05/2022 06:40:57 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 06:40:59 - INFO - codeparrot_training - Step 35063: {'lr': 0.00044091589210926266, 'samples': 17952768, 'steps': 35063, 'loss/train': 1.4589629173278809}
-03/05/2022 06:41:03 - INFO - codeparrot_training - Step 35064: {'lr': 0.00044091246595568025, 'samples': 17953280, 'steps': 35064, 'loss/train': 1.43472421169281}
-03/05/2022 06:41:05 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/05/2022 06:41:08 - INFO - codeparrot_training - Step 35065: {'lr': 0.00044090903971607555, 'samples': 17953792, 'steps': 35065, 'loss/train': 1.3697776794433594}
-03/05/2022 06:41:11 - INFO - codeparrot_training - Step 35066: {'lr': 0.0004409056133904502, 'samples': 17954304, 'steps': 35066, 'loss/train': 1.565011978149414}
-03/05/2022 06:41:14 - INFO - codeparrot_training - Step 35067: {'lr': 0.00044090218697880577, 'samples': 17954816, 'steps': 35067, 'loss/train': 2.194840669631958}
-03/05/2022 06:41:15 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/05/2022 06:41:20 - INFO - codeparrot_training - Step 35068: {'lr': 0.0004408987604811437, 'samples': 17955328, 'steps': 35068, 'loss/train': 1.7123676538467407}
-03/05/2022 06:41:23 - INFO - codeparrot_training - Step 35069: {'lr': 0.00044089533389746573, 'samples': 17955840, 'steps': 35069, 'loss/train': 1.6059235334396362}
-03/05/2022 06:41:23 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/05/2022 06:41:28 - INFO - codeparrot_training - Step 35070: {'lr': 0.00044089190722777316, 'samples': 17956352, 'steps': 35070, 'loss/train': 0.9541943669319153}
-03/05/2022 06:41:31 - INFO - codeparrot_training - Step 35071: {'lr': 0.00044088848047206763, 'samples': 17956864, 'steps': 35071, 'loss/train': 1.0749815702438354}
-03/05/2022 06:41:32 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/05/2022 06:41:36 - INFO - codeparrot_training - Step 35072: {'lr': 0.0004408850536303507, 'samples': 17957376, 'steps': 35072, 'loss/train': 0.786578357219696}
-03/05/2022 06:41:40 - INFO - codeparrot_training - Step 35073: {'lr': 0.000440881626702624, 'samples': 17957888, 'steps': 35073, 'loss/train': 1.417797565460205}
-03/05/2022 06:41:40 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/05/2022 06:41:45 - INFO - codeparrot_training - Step 35074: {'lr': 0.00044087819968888887, 'samples': 17958400, 'steps': 35074, 'loss/train': 1.875423550605774}
-03/05/2022 06:41:48 - INFO - codeparrot_training - Step 35075: {'lr': 0.00044087477258914696, 'samples': 17958912, 'steps': 35075, 'loss/train': 1.9950605630874634}
-03/05/2022 06:41:48 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 06:41:53 - INFO - codeparrot_training - Step 35076: {'lr': 0.00044087134540339996, 'samples': 17959424, 'steps': 35076, 'loss/train': 1.7342673540115356}
-03/05/2022 06:41:56 - INFO - codeparrot_training - Step 35077: {'lr': 0.00044086791813164916, 'samples': 17959936, 'steps': 35077, 'loss/train': 1.705446720123291}
-03/05/2022 06:41:56 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/05/2022 06:42:02 - INFO - codeparrot_training - Step 35078: {'lr': 0.00044086449077389636, 'samples': 17960448, 'steps': 35078, 'loss/train': 0.1058739721775055}
-03/05/2022 06:42:05 - INFO - codeparrot_training - Step 35079: {'lr': 0.0004408610633301428, 'samples': 17960960, 'steps': 35079, 'loss/train': 1.584465742111206}
-03/05/2022 06:42:10 - INFO - codeparrot_training - Step 35080: {'lr': 0.00044085763580039027, 'samples': 17961472, 'steps': 35080, 'loss/train': 1.4333089590072632}
-03/05/2022 06:42:13 - INFO - codeparrot_training - Step 35081: {'lr': 0.0004408542081846402, 'samples': 17961984, 'steps': 35081, 'loss/train': 1.781825304031372}
-03/05/2022 06:42:13 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/05/2022 06:42:19 - INFO - codeparrot_training - Step 35082: {'lr': 0.0004408507804828942, 'samples': 17962496, 'steps': 35082, 'loss/train': 1.1559191942214966}
-03/05/2022 06:42:22 - INFO - codeparrot_training - Step 35083: {'lr': 0.00044084735269515375, 'samples': 17963008, 'steps': 35083, 'loss/train': 1.3996740579605103}
-03/05/2022 06:42:22 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/05/2022 06:42:27 - INFO - codeparrot_training - Step 35084: {'lr': 0.0004408439248214205, 'samples': 17963520, 'steps': 35084, 'loss/train': 1.9162170886993408}
-03/05/2022 06:42:30 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/05/2022 06:42:32 - INFO - codeparrot_training - Step 35085: {'lr': 0.00044084049686169584, 'samples': 17964032, 'steps': 35085, 'loss/train': 1.9303969144821167}
-03/05/2022 06:42:36 - INFO - codeparrot_training - Step 35086: {'lr': 0.00044083706881598147, 'samples': 17964544, 'steps': 35086, 'loss/train': 1.463670253753662}
-03/05/2022 06:42:38 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/05/2022 06:42:41 - INFO - codeparrot_training - Step 35087: {'lr': 0.00044083364068427875, 'samples': 17965056, 'steps': 35087, 'loss/train': 2.4930057525634766}
-03/05/2022 06:42:44 - INFO - codeparrot_training - Step 35088: {'lr': 0.0004408302124665894, 'samples': 17965568, 'steps': 35088, 'loss/train': 1.467700481414795}
-03/05/2022 06:42:47 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/05/2022 06:42:49 - INFO - codeparrot_training - Step 35089: {'lr': 0.00044082678416291495, 'samples': 17966080, 'steps': 35089, 'loss/train': 0.14983738958835602}
-03/05/2022 06:42:53 - INFO - codeparrot_training - Step 35090: {'lr': 0.00044082335577325685, 'samples': 17966592, 'steps': 35090, 'loss/train': 1.2743892669677734}
-03/05/2022 06:42:55 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/05/2022 06:42:58 - INFO - codeparrot_training - Step 35091: {'lr': 0.0004408199272976167, 'samples': 17967104, 'steps': 35091, 'loss/train': 1.7178865671157837}
-03/05/2022 06:43:01 - INFO - codeparrot_training - Step 35092: {'lr': 0.00044081649873599604, 'samples': 17967616, 'steps': 35092, 'loss/train': 1.4637819528579712}
-03/05/2022 06:43:03 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/05/2022 06:43:06 - INFO - codeparrot_training - Step 35093: {'lr': 0.0004408130700883964, 'samples': 17968128, 'steps': 35093, 'loss/train': 1.6614797115325928}
-03/05/2022 06:43:09 - INFO - codeparrot_training - Step 35094: {'lr': 0.0004408096413548193, 'samples': 17968640, 'steps': 35094, 'loss/train': 2.067784309387207}
-03/05/2022 06:43:11 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/05/2022 06:43:15 - INFO - codeparrot_training - Step 35095: {'lr': 0.00044080621253526637, 'samples': 17969152, 'steps': 35095, 'loss/train': 1.471561074256897}
-03/05/2022 06:43:18 - INFO - codeparrot_training - Step 35096: {'lr': 0.00044080278362973913, 'samples': 17969664, 'steps': 35096, 'loss/train': 1.6416233777999878}
-03/05/2022 06:43:20 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/05/2022 06:43:23 - INFO - codeparrot_training - Step 35097: {'lr': 0.00044079935463823904, 'samples': 17970176, 'steps': 35097, 'loss/train': 1.6243948936462402}
-03/05/2022 06:43:26 - INFO - codeparrot_training - Step 35098: {'lr': 0.00044079592556076774, 'samples': 17970688, 'steps': 35098, 'loss/train': 0.5875405669212341}
-03/05/2022 06:43:30 - INFO - codeparrot_training - Step 35099: {'lr': 0.00044079249639732664, 'samples': 17971200, 'steps': 35099, 'loss/train': 1.6715366840362549}
-03/05/2022 06:43:30 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/05/2022 06:43:35 - INFO - codeparrot_training - Step 35100: {'lr': 0.00044078906714791757, 'samples': 17971712, 'steps': 35100, 'loss/train': 2.206998109817505}
-03/05/2022 06:43:38 - INFO - codeparrot_training - Step 35101: {'lr': 0.0004407856378125418, 'samples': 17972224, 'steps': 35101, 'loss/train': 2.1837384700775146}
-03/05/2022 06:43:38 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 06:43:44 - INFO - codeparrot_training - Step 35102: {'lr': 0.00044078220839120086, 'samples': 17972736, 'steps': 35102, 'loss/train': 1.177858591079712}
-03/05/2022 06:43:46 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/05/2022 06:43:49 - INFO - codeparrot_training - Step 35103: {'lr': 0.0004407787788838966, 'samples': 17973248, 'steps': 35103, 'loss/train': 1.4679001569747925}
-03/05/2022 06:43:52 - INFO - codeparrot_training - Step 35104: {'lr': 0.00044077534929063024, 'samples': 17973760, 'steps': 35104, 'loss/train': 1.8608607053756714}
-03/05/2022 06:43:55 - INFO - codeparrot_training - Step 35105: {'lr': 0.00044077191961140337, 'samples': 17974272, 'steps': 35105, 'loss/train': 1.519514799118042}
-03/05/2022 06:43:55 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/05/2022 06:44:01 - INFO - codeparrot_training - Step 35106: {'lr': 0.00044076848984621775, 'samples': 17974784, 'steps': 35106, 'loss/train': 1.794328212738037}
-03/05/2022 06:44:04 - INFO - codeparrot_training - Step 35107: {'lr': 0.00044076505999507474, 'samples': 17975296, 'steps': 35107, 'loss/train': 1.7238179445266724}
-03/05/2022 06:44:04 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 06:44:09 - INFO - codeparrot_training - Step 35108: {'lr': 0.00044076163005797597, 'samples': 17975808, 'steps': 35108, 'loss/train': 1.834072470664978}
-03/05/2022 06:44:12 - INFO - codeparrot_training - Step 35109: {'lr': 0.00044075820003492295, 'samples': 17976320, 'steps': 35109, 'loss/train': 1.9181102514266968}
-03/05/2022 06:44:12 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/05/2022 06:44:17 - INFO - codeparrot_training - Step 35110: {'lr': 0.0004407547699259173, 'samples': 17976832, 'steps': 35110, 'loss/train': 3.2535603046417236}
-03/05/2022 06:44:21 - INFO - codeparrot_training - Step 35111: {'lr': 0.0004407513397309604, 'samples': 17977344, 'steps': 35111, 'loss/train': 1.0164982080459595}
-03/05/2022 06:44:21 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/05/2022 06:44:26 - INFO - codeparrot_training - Step 35112: {'lr': 0.0004407479094500539, 'samples': 17977856, 'steps': 35112, 'loss/train': 1.3741482496261597}
-03/05/2022 06:44:29 - INFO - codeparrot_training - Step 35113: {'lr': 0.00044074447908319935, 'samples': 17978368, 'steps': 35113, 'loss/train': 1.7950351238250732}
-03/05/2022 06:44:29 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/05/2022 06:44:34 - INFO - codeparrot_training - Step 35114: {'lr': 0.0004407410486303983, 'samples': 17978880, 'steps': 35114, 'loss/train': 1.2568387985229492}
-03/05/2022 06:44:37 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/05/2022 06:44:40 - INFO - codeparrot_training - Step 35115: {'lr': 0.0004407376180916522, 'samples': 17979392, 'steps': 35115, 'loss/train': 1.7677689790725708}
-03/05/2022 06:44:43 - INFO - codeparrot_training - Step 35116: {'lr': 0.0004407341874669627, 'samples': 17979904, 'steps': 35116, 'loss/train': 1.66059148311615}
-03/05/2022 06:44:46 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/05/2022 06:44:48 - INFO - codeparrot_training - Step 35117: {'lr': 0.00044073075675633134, 'samples': 17980416, 'steps': 35117, 'loss/train': 1.6717792749404907}
-03/05/2022 06:44:51 - INFO - codeparrot_training - Step 35118: {'lr': 0.0004407273259597597, 'samples': 17980928, 'steps': 35118, 'loss/train': 2.05826473236084}
-03/05/2022 06:44:54 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/05/2022 06:44:57 - INFO - codeparrot_training - Step 35119: {'lr': 0.0004407238950772492, 'samples': 17981440, 'steps': 35119, 'loss/train': 1.5202373266220093}
-03/05/2022 06:45:00 - INFO - codeparrot_training - Step 35120: {'lr': 0.00044072046410880143, 'samples': 17981952, 'steps': 35120, 'loss/train': 1.5986127853393555}
-03/05/2022 06:45:02 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/05/2022 06:45:05 - INFO - codeparrot_training - Step 35121: {'lr': 0.000440717033054418, 'samples': 17982464, 'steps': 35121, 'loss/train': 1.7005702257156372}
-03/05/2022 06:45:08 - INFO - codeparrot_training - Step 35122: {'lr': 0.0004407136019141005, 'samples': 17982976, 'steps': 35122, 'loss/train': 0.833538293838501}
-03/05/2022 06:45:11 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 06:45:13 - INFO - codeparrot_training - Step 35123: {'lr': 0.0004407101706878502, 'samples': 17983488, 'steps': 35123, 'loss/train': 1.7292698621749878}
-03/05/2022 06:45:17 - INFO - codeparrot_training - Step 35124: {'lr': 0.000440706739375669, 'samples': 17984000, 'steps': 35124, 'loss/train': 2.265519380569458}
-03/05/2022 06:45:19 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/05/2022 06:45:22 - INFO - codeparrot_training - Step 35125: {'lr': 0.00044070330797755825, 'samples': 17984512, 'steps': 35125, 'loss/train': 1.659589171409607}
-03/05/2022 06:45:25 - INFO - codeparrot_training - Step 35126: {'lr': 0.0004406998764935195, 'samples': 17985024, 'steps': 35126, 'loss/train': 2.4351227283477783}
-03/05/2022 06:45:27 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/05/2022 06:45:30 - INFO - codeparrot_training - Step 35127: {'lr': 0.0004406964449235544, 'samples': 17985536, 'steps': 35127, 'loss/train': 1.5124415159225464}
-03/05/2022 06:45:34 - INFO - codeparrot_training - Step 35128: {'lr': 0.00044069301326766434, 'samples': 17986048, 'steps': 35128, 'loss/train': 1.4938569068908691}
-03/05/2022 06:45:36 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/05/2022 06:45:39 - INFO - codeparrot_training - Step 35129: {'lr': 0.00044068958152585104, 'samples': 17986560, 'steps': 35129, 'loss/train': 1.3420312404632568}
-03/05/2022 06:45:42 - INFO - codeparrot_training - Step 35130: {'lr': 0.00044068614969811586, 'samples': 17987072, 'steps': 35130, 'loss/train': 0.8191577792167664}
-03/05/2022 06:45:45 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/05/2022 06:45:48 - INFO - codeparrot_training - Step 35131: {'lr': 0.0004406827177844605, 'samples': 17987584, 'steps': 35131, 'loss/train': 2.0152664184570312}
-03/05/2022 06:45:51 - INFO - codeparrot_training - Step 35132: {'lr': 0.00044067928578488645, 'samples': 17988096, 'steps': 35132, 'loss/train': 1.3087942600250244}
-03/05/2022 06:45:53 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/05/2022 06:45:56 - INFO - codeparrot_training - Step 35133: {'lr': 0.0004406758536993952, 'samples': 17988608, 'steps': 35133, 'loss/train': 2.6158320903778076}
-03/05/2022 06:45:59 - INFO - codeparrot_training - Step 35134: {'lr': 0.00044067242152798843, 'samples': 17989120, 'steps': 35134, 'loss/train': 1.7170389890670776}
-03/05/2022 06:46:02 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/05/2022 06:46:04 - INFO - codeparrot_training - Step 35135: {'lr': 0.00044066898927066757, 'samples': 17989632, 'steps': 35135, 'loss/train': 0.961797297000885}
-03/05/2022 06:46:08 - INFO - codeparrot_training - Step 35136: {'lr': 0.0004406655569274342, 'samples': 17990144, 'steps': 35136, 'loss/train': 2.1463520526885986}
-03/05/2022 06:46:10 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/05/2022 06:46:13 - INFO - codeparrot_training - Step 35137: {'lr': 0.0004406621244982899, 'samples': 17990656, 'steps': 35137, 'loss/train': 1.3117103576660156}
-03/05/2022 06:46:16 - INFO - codeparrot_training - Step 35138: {'lr': 0.00044065869198323614, 'samples': 17991168, 'steps': 35138, 'loss/train': 1.9598625898361206}
-03/05/2022 06:46:18 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/05/2022 06:46:21 - INFO - codeparrot_training - Step 35139: {'lr': 0.0004406552593822746, 'samples': 17991680, 'steps': 35139, 'loss/train': 1.6232032775878906}
-03/05/2022 06:46:24 - INFO - codeparrot_training - Step 35140: {'lr': 0.00044065182669540665, 'samples': 17992192, 'steps': 35140, 'loss/train': 1.843003749847412}
-03/05/2022 06:46:27 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/05/2022 06:46:30 - INFO - codeparrot_training - Step 35141: {'lr': 0.000440648393922634, 'samples': 17992704, 'steps': 35141, 'loss/train': 2.109143018722534}
-03/05/2022 06:46:33 - INFO - codeparrot_training - Step 35142: {'lr': 0.0004406449610639581, 'samples': 17993216, 'steps': 35142, 'loss/train': 1.9507811069488525}
-03/05/2022 06:46:36 - INFO - codeparrot_training - Step 35143: {'lr': 0.0004406415281193805, 'samples': 17993728, 'steps': 35143, 'loss/train': 1.6532790660858154}
-03/05/2022 06:46:36 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/05/2022 06:46:42 - INFO - codeparrot_training - Step 35144: {'lr': 0.0004406380950889027, 'samples': 17994240, 'steps': 35144, 'loss/train': 1.553581953048706}
-03/05/2022 06:46:45 - INFO - codeparrot_training - Step 35145: {'lr': 0.0004406346619725265, 'samples': 17994752, 'steps': 35145, 'loss/train': 1.8314599990844727}
-03/05/2022 06:46:45 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 06:46:50 - INFO - codeparrot_training - Step 35146: {'lr': 0.00044063122877025315, 'samples': 17995264, 'steps': 35146, 'loss/train': 2.3224868774414062}
-03/05/2022 06:46:53 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/05/2022 06:46:56 - INFO - codeparrot_training - Step 35147: {'lr': 0.0004406277954820843, 'samples': 17995776, 'steps': 35147, 'loss/train': 1.8385311365127563}
-03/05/2022 06:46:59 - INFO - codeparrot_training - Step 35148: {'lr': 0.0004406243621080216, 'samples': 17996288, 'steps': 35148, 'loss/train': 2.3053135871887207}
-03/05/2022 06:47:01 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/05/2022 06:47:04 - INFO - codeparrot_training - Step 35149: {'lr': 0.00044062092864806634, 'samples': 17996800, 'steps': 35149, 'loss/train': 1.9078410863876343}
-03/05/2022 06:47:07 - INFO - codeparrot_training - Step 35150: {'lr': 0.00044061749510222037, 'samples': 17997312, 'steps': 35150, 'loss/train': 1.633927822113037}
-03/05/2022 06:47:10 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/05/2022 06:47:12 - INFO - codeparrot_training - Step 35151: {'lr': 0.00044061406147048504, 'samples': 17997824, 'steps': 35151, 'loss/train': 2.0847232341766357}
-03/05/2022 06:47:16 - INFO - codeparrot_training - Step 35152: {'lr': 0.000440610627752862, 'samples': 17998336, 'steps': 35152, 'loss/train': 2.969688653945923}
-03/05/2022 06:47:18 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 06:47:21 - INFO - codeparrot_training - Step 35153: {'lr': 0.00044060719394935265, 'samples': 17998848, 'steps': 35153, 'loss/train': 2.382965087890625}
-03/05/2022 06:47:24 - INFO - codeparrot_training - Step 35154: {'lr': 0.0004406037600599588, 'samples': 17999360, 'steps': 35154, 'loss/train': 2.2540781497955322}
-03/05/2022 06:47:26 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/05/2022 06:47:29 - INFO - codeparrot_training - Step 35155: {'lr': 0.0004406003260846817, 'samples': 17999872, 'steps': 35155, 'loss/train': 1.8190860748291016}
-03/05/2022 06:47:32 - INFO - codeparrot_training - Step 35156: {'lr': 0.0004405968920235231, 'samples': 18000384, 'steps': 35156, 'loss/train': 1.9425158500671387}
-03/05/2022 06:47:35 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/05/2022 06:47:38 - INFO - codeparrot_training - Step 35157: {'lr': 0.0004405934578764845, 'samples': 18000896, 'steps': 35157, 'loss/train': 2.1428630352020264}
-03/05/2022 06:47:41 - INFO - codeparrot_training - Step 35158: {'lr': 0.0004405900236435674, 'samples': 18001408, 'steps': 35158, 'loss/train': 1.6020028591156006}
-03/05/2022 06:47:43 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 06:47:46 - INFO - codeparrot_training - Step 35159: {'lr': 0.00044058658932477336, 'samples': 18001920, 'steps': 35159, 'loss/train': 1.2939059734344482}
-03/05/2022 06:47:49 - INFO - codeparrot_training - Step 35160: {'lr': 0.0004405831549201039, 'samples': 18002432, 'steps': 35160, 'loss/train': 1.7397069931030273}
-03/05/2022 06:47:51 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/05/2022 06:47:55 - INFO - codeparrot_training - Step 35161: {'lr': 0.0004405797204295607, 'samples': 18002944, 'steps': 35161, 'loss/train': 1.682003140449524}
-03/05/2022 06:47:58 - INFO - codeparrot_training - Step 35162: {'lr': 0.0004405762858531451, 'samples': 18003456, 'steps': 35162, 'loss/train': 2.0181326866149902}
-03/05/2022 06:48:00 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 06:48:03 - INFO - codeparrot_training - Step 35163: {'lr': 0.00044057285119085887, 'samples': 18003968, 'steps': 35163, 'loss/train': 2.097601890563965}
-03/05/2022 06:48:06 - INFO - codeparrot_training - Step 35164: {'lr': 0.0004405694164427035, 'samples': 18004480, 'steps': 35164, 'loss/train': 0.9529314637184143}
-03/05/2022 06:48:08 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/05/2022 06:48:11 - INFO - codeparrot_training - Step 35165: {'lr': 0.0004405659816086804, 'samples': 18004992, 'steps': 35165, 'loss/train': 1.4942588806152344}
-03/05/2022 06:48:15 - INFO - codeparrot_training - Step 35166: {'lr': 0.00044056254668879127, 'samples': 18005504, 'steps': 35166, 'loss/train': 2.0905256271362305}
-03/05/2022 06:48:17 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/05/2022 06:48:20 - INFO - codeparrot_training - Step 35167: {'lr': 0.00044055911168303753, 'samples': 18006016, 'steps': 35167, 'loss/train': 1.5813617706298828}
-03/05/2022 06:48:23 - INFO - codeparrot_training - Step 35168: {'lr': 0.00044055567659142083, 'samples': 18006528, 'steps': 35168, 'loss/train': 2.3200302124023438}
-03/05/2022 06:48:26 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 06:48:29 - INFO - codeparrot_training - Step 35169: {'lr': 0.0004405522414139427, 'samples': 18007040, 'steps': 35169, 'loss/train': 2.1776938438415527}
-03/05/2022 06:48:32 - INFO - codeparrot_training - Step 35170: {'lr': 0.0004405488061506047, 'samples': 18007552, 'steps': 35170, 'loss/train': 1.9812142848968506}
-03/05/2022 06:48:35 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/05/2022 06:48:37 - INFO - codeparrot_training - Step 35171: {'lr': 0.0004405453708014082, 'samples': 18008064, 'steps': 35171, 'loss/train': 2.974316120147705}
-03/05/2022 06:48:40 - INFO - codeparrot_training - Step 35172: {'lr': 0.00044054193536635503, 'samples': 18008576, 'steps': 35172, 'loss/train': 0.9614003896713257}
-03/05/2022 06:48:44 - INFO - codeparrot_training - Step 35173: {'lr': 0.00044053849984544653, 'samples': 18009088, 'steps': 35173, 'loss/train': 1.5257419347763062}
-03/05/2022 06:48:44 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/05/2022 06:48:49 - INFO - codeparrot_training - Step 35174: {'lr': 0.0004405350642386844, 'samples': 18009600, 'steps': 35174, 'loss/train': 1.924976110458374}
-03/05/2022 06:48:52 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/05/2022 06:48:55 - INFO - codeparrot_training - Step 35175: {'lr': 0.00044053162854607004, 'samples': 18010112, 'steps': 35175, 'loss/train': 2.0167171955108643}
-03/05/2022 06:48:58 - INFO - codeparrot_training - Step 35176: {'lr': 0.0004405281927676051, 'samples': 18010624, 'steps': 35176, 'loss/train': 0.6707471609115601}
-03/05/2022 06:49:01 - INFO - codeparrot_training - Step 35177: {'lr': 0.0004405247569032911, 'samples': 18011136, 'steps': 35177, 'loss/train': 0.6019644141197205}
-03/05/2022 06:49:03 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/05/2022 06:49:06 - INFO - codeparrot_training - Step 35178: {'lr': 0.00044052132095312956, 'samples': 18011648, 'steps': 35178, 'loss/train': 1.0000718832015991}
-03/05/2022 06:49:10 - INFO - codeparrot_training - Step 35179: {'lr': 0.0004405178849171221, 'samples': 18012160, 'steps': 35179, 'loss/train': 1.952765941619873}
-03/05/2022 06:49:11 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 06:49:15 - INFO - codeparrot_training - Step 35180: {'lr': 0.00044051444879527013, 'samples': 18012672, 'steps': 35180, 'loss/train': 1.752365231513977}
-03/05/2022 06:49:18 - INFO - codeparrot_training - Step 35181: {'lr': 0.00044051101258757544, 'samples': 18013184, 'steps': 35181, 'loss/train': 1.7537517547607422}
-03/05/2022 06:49:20 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/05/2022 06:49:23 - INFO - codeparrot_training - Step 35182: {'lr': 0.0004405075762940393, 'samples': 18013696, 'steps': 35182, 'loss/train': 1.0589922666549683}
-03/05/2022 06:49:26 - INFO - codeparrot_training - Step 35183: {'lr': 0.00044050413991466344, 'samples': 18014208, 'steps': 35183, 'loss/train': 0.8382319808006287}
-03/05/2022 06:49:28 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 06:49:32 - INFO - codeparrot_training - Step 35184: {'lr': 0.0004405007034494494, 'samples': 18014720, 'steps': 35184, 'loss/train': 2.4702956676483154}
-03/05/2022 06:49:35 - INFO - codeparrot_training - Step 35185: {'lr': 0.00044049726689839854, 'samples': 18015232, 'steps': 35185, 'loss/train': 2.3381457328796387}
-03/05/2022 06:49:36 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/05/2022 06:49:40 - INFO - codeparrot_training - Step 35186: {'lr': 0.0004404938302615126, 'samples': 18015744, 'steps': 35186, 'loss/train': 2.3969335556030273}
-03/05/2022 06:49:43 - INFO - codeparrot_training - Step 35187: {'lr': 0.00044049039353879317, 'samples': 18016256, 'steps': 35187, 'loss/train': 1.9619604349136353}
-03/05/2022 06:49:45 - INFO - codeparrot_training - Skipping example with length 309 (seq_length=1024)
-03/05/2022 06:49:48 - INFO - codeparrot_training - Step 35188: {'lr': 0.00044048695673024166, 'samples': 18016768, 'steps': 35188, 'loss/train': 2.0386698246002197}
-03/05/2022 06:49:52 - INFO - codeparrot_training - Step 35189: {'lr': 0.00044048351983585966, 'samples': 18017280, 'steps': 35189, 'loss/train': 2.782304525375366}
-03/05/2022 06:49:53 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/05/2022 06:49:57 - INFO - codeparrot_training - Step 35190: {'lr': 0.00044048008285564865, 'samples': 18017792, 'steps': 35190, 'loss/train': 1.0566166639328003}
-03/05/2022 06:50:00 - INFO - codeparrot_training - Step 35191: {'lr': 0.0004404766457896104, 'samples': 18018304, 'steps': 35191, 'loss/train': 2.2477879524230957}
-03/05/2022 06:50:01 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/05/2022 06:50:06 - INFO - codeparrot_training - Step 35192: {'lr': 0.0004404732086377462, 'samples': 18018816, 'steps': 35192, 'loss/train': 2.0718581676483154}
-03/05/2022 06:50:09 - INFO - codeparrot_training - Step 35193: {'lr': 0.00044046977140005774, 'samples': 18019328, 'steps': 35193, 'loss/train': 1.7784464359283447}
-03/05/2022 06:50:10 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/05/2022 06:50:14 - INFO - codeparrot_training - Step 35194: {'lr': 0.00044046633407654657, 'samples': 18019840, 'steps': 35194, 'loss/train': 1.4552630186080933}
-03/05/2022 06:50:17 - INFO - codeparrot_training - Step 35195: {'lr': 0.0004404628966672142, 'samples': 18020352, 'steps': 35195, 'loss/train': 1.3339378833770752}
-03/05/2022 06:50:22 - INFO - codeparrot_training - Step 35196: {'lr': 0.0004404594591720622, 'samples': 18020864, 'steps': 35196, 'loss/train': 2.127044439315796}
-03/05/2022 06:50:26 - INFO - codeparrot_training - Step 35197: {'lr': 0.00044045602159109207, 'samples': 18021376, 'steps': 35197, 'loss/train': 2.4092276096343994}
-03/05/2022 06:50:26 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/05/2022 06:50:31 - INFO - codeparrot_training - Step 35198: {'lr': 0.0004404525839243054, 'samples': 18021888, 'steps': 35198, 'loss/train': 2.0275094509124756}
-03/05/2022 06:50:34 - INFO - codeparrot_training - Step 35199: {'lr': 0.00044044914617170374, 'samples': 18022400, 'steps': 35199, 'loss/train': 1.4127453565597534}
-03/05/2022 06:50:35 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/05/2022 06:50:39 - INFO - codeparrot_training - Step 35200: {'lr': 0.00044044570833328865, 'samples': 18022912, 'steps': 35200, 'loss/train': 1.365465760231018}
-03/05/2022 06:50:43 - INFO - codeparrot_training - Step 35201: {'lr': 0.00044044227040906166, 'samples': 18023424, 'steps': 35201, 'loss/train': 1.4684242010116577}
-03/05/2022 06:50:44 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/05/2022 06:50:48 - INFO - codeparrot_training - Step 35202: {'lr': 0.00044043883239902425, 'samples': 18023936, 'steps': 35202, 'loss/train': 2.4370481967926025}
-03/05/2022 06:50:51 - INFO - codeparrot_training - Step 35203: {'lr': 0.00044043539430317814, 'samples': 18024448, 'steps': 35203, 'loss/train': 1.5070427656173706}
-03/05/2022 06:50:52 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/05/2022 06:50:56 - INFO - codeparrot_training - Step 35204: {'lr': 0.00044043195612152475, 'samples': 18024960, 'steps': 35204, 'loss/train': 1.3770948648452759}
-03/05/2022 06:50:59 - INFO - codeparrot_training - Step 35205: {'lr': 0.0004404285178540657, 'samples': 18025472, 'steps': 35205, 'loss/train': 1.5335878133773804}
-03/05/2022 06:51:00 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/05/2022 06:51:05 - INFO - codeparrot_training - Step 35206: {'lr': 0.0004404250795008024, 'samples': 18025984, 'steps': 35206, 'loss/train': 1.5627869367599487}
-03/05/2022 06:51:08 - INFO - codeparrot_training - Step 35207: {'lr': 0.00044042164106173655, 'samples': 18026496, 'steps': 35207, 'loss/train': 1.9812368154525757}
-03/05/2022 06:51:09 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/05/2022 06:51:13 - INFO - codeparrot_training - Step 35208: {'lr': 0.00044041820253686964, 'samples': 18027008, 'steps': 35208, 'loss/train': 1.741363763809204}
-03/05/2022 06:51:16 - INFO - codeparrot_training - Step 35209: {'lr': 0.0004404147639262032, 'samples': 18027520, 'steps': 35209, 'loss/train': 1.1975996494293213}
-03/05/2022 06:51:17 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 06:51:22 - INFO - codeparrot_training - Step 35210: {'lr': 0.00044041132522973885, 'samples': 18028032, 'steps': 35210, 'loss/train': 1.5243034362792969}
-03/05/2022 06:51:25 - INFO - codeparrot_training - Step 35211: {'lr': 0.0004404078864474781, 'samples': 18028544, 'steps': 35211, 'loss/train': 1.6824908256530762}
-03/05/2022 06:51:26 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/05/2022 06:51:30 - INFO - codeparrot_training - Step 35212: {'lr': 0.00044040444757942245, 'samples': 18029056, 'steps': 35212, 'loss/train': 1.688216209411621}
-03/05/2022 06:51:33 - INFO - codeparrot_training - Step 35213: {'lr': 0.00044040100862557355, 'samples': 18029568, 'steps': 35213, 'loss/train': 1.4389698505401611}
-03/05/2022 06:51:34 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/05/2022 06:51:39 - INFO - codeparrot_training - Step 35214: {'lr': 0.00044039756958593287, 'samples': 18030080, 'steps': 35214, 'loss/train': 1.472037434577942}
-03/05/2022 06:51:42 - INFO - codeparrot_training - Step 35215: {'lr': 0.000440394130460502, 'samples': 18030592, 'steps': 35215, 'loss/train': 2.4172937870025635}
-03/05/2022 06:51:42 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/05/2022 06:51:47 - INFO - codeparrot_training - Step 35216: {'lr': 0.00044039069124928245, 'samples': 18031104, 'steps': 35216, 'loss/train': 1.5323917865753174}
-03/05/2022 06:51:50 - INFO - codeparrot_training - Step 35217: {'lr': 0.0004403872519522758, 'samples': 18031616, 'steps': 35217, 'loss/train': 2.048283100128174}
-03/05/2022 06:51:51 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/05/2022 06:51:55 - INFO - codeparrot_training - Step 35218: {'lr': 0.00044038381256948357, 'samples': 18032128, 'steps': 35218, 'loss/train': 1.6273083686828613}
-03/05/2022 06:51:59 - INFO - codeparrot_training - Step 35219: {'lr': 0.00044038037310090736, 'samples': 18032640, 'steps': 35219, 'loss/train': 1.68900728225708}
-03/05/2022 06:52:00 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/05/2022 06:52:04 - INFO - codeparrot_training - Step 35220: {'lr': 0.00044037693354654863, 'samples': 18033152, 'steps': 35220, 'loss/train': 2.021061658859253}
-03/05/2022 06:52:07 - INFO - codeparrot_training - Step 35221: {'lr': 0.0004403734939064091, 'samples': 18033664, 'steps': 35221, 'loss/train': 0.6436805725097656}
-03/05/2022 06:52:08 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/05/2022 06:52:12 - INFO - codeparrot_training - Step 35222: {'lr': 0.00044037005418049016, 'samples': 18034176, 'steps': 35222, 'loss/train': 1.8494211435317993}
-03/05/2022 06:52:16 - INFO - codeparrot_training - Step 35223: {'lr': 0.00044036661436879334, 'samples': 18034688, 'steps': 35223, 'loss/train': 2.0721592903137207}
-03/05/2022 06:52:17 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/05/2022 06:52:21 - INFO - codeparrot_training - Step 35224: {'lr': 0.00044036317447132035, 'samples': 18035200, 'steps': 35224, 'loss/train': 1.4143296480178833}
-03/05/2022 06:52:24 - INFO - codeparrot_training - Step 35225: {'lr': 0.00044035973448807266, 'samples': 18035712, 'steps': 35225, 'loss/train': 0.7082532048225403}
-03/05/2022 06:52:26 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/05/2022 06:52:30 - INFO - codeparrot_training - Step 35226: {'lr': 0.00044035629441905173, 'samples': 18036224, 'steps': 35226, 'loss/train': 1.7323354482650757}
-03/05/2022 06:52:33 - INFO - codeparrot_training - Step 35227: {'lr': 0.0004403528542642592, 'samples': 18036736, 'steps': 35227, 'loss/train': 1.7430179119110107}
-03/05/2022 06:52:34 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/05/2022 06:52:38 - INFO - codeparrot_training - Step 35228: {'lr': 0.00044034941402369666, 'samples': 18037248, 'steps': 35228, 'loss/train': 1.3191050291061401}
-03/05/2022 06:52:41 - INFO - codeparrot_training - Step 35229: {'lr': 0.0004403459736973656, 'samples': 18037760, 'steps': 35229, 'loss/train': 0.10687405616044998}
-03/05/2022 06:52:42 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/05/2022 06:52:46 - INFO - codeparrot_training - Step 35230: {'lr': 0.00044034253328526765, 'samples': 18038272, 'steps': 35230, 'loss/train': 1.659721851348877}
-03/05/2022 06:52:50 - INFO - codeparrot_training - Step 35231: {'lr': 0.00044033909278740416, 'samples': 18038784, 'steps': 35231, 'loss/train': 1.411044955253601}
-03/05/2022 06:52:51 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/05/2022 06:52:55 - INFO - codeparrot_training - Step 35232: {'lr': 0.0004403356522037769, 'samples': 18039296, 'steps': 35232, 'loss/train': 1.7962654829025269}
-03/05/2022 06:52:58 - INFO - codeparrot_training - Step 35233: {'lr': 0.00044033221153438727, 'samples': 18039808, 'steps': 35233, 'loss/train': 2.097933530807495}
-03/05/2022 06:52:59 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/05/2022 06:53:03 - INFO - codeparrot_training - Step 35234: {'lr': 0.00044032877077923696, 'samples': 18040320, 'steps': 35234, 'loss/train': 1.517199993133545}
-03/05/2022 06:53:07 - INFO - codeparrot_training - Step 35235: {'lr': 0.0004403253299383274, 'samples': 18040832, 'steps': 35235, 'loss/train': 1.7494125366210938}
-03/05/2022 06:53:07 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/05/2022 06:53:12 - INFO - codeparrot_training - Step 35236: {'lr': 0.00044032188901166016, 'samples': 18041344, 'steps': 35236, 'loss/train': 1.896111011505127}
-03/05/2022 06:53:15 - INFO - codeparrot_training - Step 35237: {'lr': 0.0004403184479992368, 'samples': 18041856, 'steps': 35237, 'loss/train': 1.6752750873565674}
-03/05/2022 06:53:16 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/05/2022 06:53:20 - INFO - codeparrot_training - Step 35238: {'lr': 0.000440315006901059, 'samples': 18042368, 'steps': 35238, 'loss/train': 1.8756252527236938}
-03/05/2022 06:53:23 - INFO - codeparrot_training - Step 35239: {'lr': 0.00044031156571712807, 'samples': 18042880, 'steps': 35239, 'loss/train': 0.886452853679657}
-03/05/2022 06:53:24 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/05/2022 06:53:29 - INFO - codeparrot_training - Step 35240: {'lr': 0.0004403081244474457, 'samples': 18043392, 'steps': 35240, 'loss/train': 1.243628740310669}
-03/05/2022 06:53:32 - INFO - codeparrot_training - Step 35241: {'lr': 0.00044030468309201354, 'samples': 18043904, 'steps': 35241, 'loss/train': 1.7641898393630981}
-03/05/2022 06:53:34 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/05/2022 06:53:37 - INFO - codeparrot_training - Step 35242: {'lr': 0.0004403012416508329, 'samples': 18044416, 'steps': 35242, 'loss/train': 1.3685418367385864}
-03/05/2022 06:53:41 - INFO - codeparrot_training - Step 35243: {'lr': 0.00044029780012390553, 'samples': 18044928, 'steps': 35243, 'loss/train': 1.3318215608596802}
-03/05/2022 06:53:42 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/05/2022 06:53:46 - INFO - codeparrot_training - Step 35244: {'lr': 0.0004402943585112329, 'samples': 18045440, 'steps': 35244, 'loss/train': 1.5533034801483154}
-03/05/2022 06:53:49 - INFO - codeparrot_training - Step 35245: {'lr': 0.0004402909168128165, 'samples': 18045952, 'steps': 35245, 'loss/train': 0.696471095085144}
-03/05/2022 06:53:51 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/05/2022 06:53:54 - INFO - codeparrot_training - Step 35246: {'lr': 0.00044028747502865794, 'samples': 18046464, 'steps': 35246, 'loss/train': 2.0247786045074463}
-03/05/2022 06:53:58 - INFO - codeparrot_training - Step 35247: {'lr': 0.0004402840331587589, 'samples': 18046976, 'steps': 35247, 'loss/train': 1.5530458688735962}
-03/05/2022 06:53:59 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/05/2022 06:54:03 - INFO - codeparrot_training - Step 35248: {'lr': 0.0004402805912031207, 'samples': 18047488, 'steps': 35248, 'loss/train': 2.408391237258911}
-03/05/2022 06:54:06 - INFO - codeparrot_training - Step 35249: {'lr': 0.0004402771491617451, 'samples': 18048000, 'steps': 35249, 'loss/train': 1.8934053182601929}
-03/05/2022 06:54:07 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/05/2022 06:54:11 - INFO - codeparrot_training - Step 35250: {'lr': 0.0004402737070346335, 'samples': 18048512, 'steps': 35250, 'loss/train': 1.3560611009597778}
-03/05/2022 06:54:14 - INFO - codeparrot_training - Step 35251: {'lr': 0.0004402702648217875, 'samples': 18049024, 'steps': 35251, 'loss/train': 1.8378825187683105}
-03/05/2022 06:54:16 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/05/2022 06:54:20 - INFO - codeparrot_training - Step 35252: {'lr': 0.00044026682252320864, 'samples': 18049536, 'steps': 35252, 'loss/train': 2.0805418491363525}
-03/05/2022 06:54:23 - INFO - codeparrot_training - Step 35253: {'lr': 0.00044026338013889853, 'samples': 18050048, 'steps': 35253, 'loss/train': 1.6716229915618896}
-03/05/2022 06:54:27 - INFO - codeparrot_training - Step 35254: {'lr': 0.00044025993766885866, 'samples': 18050560, 'steps': 35254, 'loss/train': 1.2776844501495361}
-03/05/2022 06:54:27 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/05/2022 06:54:32 - INFO - codeparrot_training - Step 35255: {'lr': 0.00044025649511309064, 'samples': 18051072, 'steps': 35255, 'loss/train': 1.305182695388794}
-03/05/2022 06:54:35 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/05/2022 06:54:37 - INFO - codeparrot_training - Step 35256: {'lr': 0.00044025305247159585, 'samples': 18051584, 'steps': 35256, 'loss/train': 1.637816071510315}
-03/05/2022 06:54:41 - INFO - codeparrot_training - Step 35257: {'lr': 0.00044024960974437606, 'samples': 18052096, 'steps': 35257, 'loss/train': 2.3576536178588867}
-03/05/2022 06:54:44 - INFO - codeparrot_training - Step 35258: {'lr': 0.0004402461669314327, 'samples': 18052608, 'steps': 35258, 'loss/train': 0.06298601627349854}
-03/05/2022 06:54:44 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/05/2022 06:54:49 - INFO - codeparrot_training - Step 35259: {'lr': 0.0004402427240327674, 'samples': 18053120, 'steps': 35259, 'loss/train': 2.0097126960754395}
-03/05/2022 06:54:52 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/05/2022 06:54:54 - INFO - codeparrot_training - Step 35260: {'lr': 0.0004402392810483816, 'samples': 18053632, 'steps': 35260, 'loss/train': 1.7525627613067627}
-03/05/2022 06:54:57 - INFO - codeparrot_training - Step 35261: {'lr': 0.000440235837978277, 'samples': 18054144, 'steps': 35261, 'loss/train': 2.146052837371826}
-03/05/2022 06:54:59 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/05/2022 06:55:03 - INFO - codeparrot_training - Step 35262: {'lr': 0.00044023239482245504, 'samples': 18054656, 'steps': 35262, 'loss/train': 1.607692003250122}
-03/05/2022 06:55:06 - INFO - codeparrot_training - Step 35263: {'lr': 0.0004402289515809172, 'samples': 18055168, 'steps': 35263, 'loss/train': 2.072352647781372}
-03/05/2022 06:55:07 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 06:55:11 - INFO - codeparrot_training - Step 35264: {'lr': 0.00044022550825366526, 'samples': 18055680, 'steps': 35264, 'loss/train': 2.176309585571289}
-03/05/2022 06:55:14 - INFO - codeparrot_training - Step 35265: {'lr': 0.0004402220648407006, 'samples': 18056192, 'steps': 35265, 'loss/train': 1.2910398244857788}
-03/05/2022 06:55:16 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/05/2022 06:55:20 - INFO - codeparrot_training - Step 35266: {'lr': 0.00044021862134202485, 'samples': 18056704, 'steps': 35266, 'loss/train': 1.8105504512786865}
-03/05/2022 06:55:23 - INFO - codeparrot_training - Step 35267: {'lr': 0.00044021517775763943, 'samples': 18057216, 'steps': 35267, 'loss/train': 2.2113943099975586}
-03/05/2022 06:55:26 - INFO - codeparrot_training - Step 35268: {'lr': 0.00044021173408754604, 'samples': 18057728, 'steps': 35268, 'loss/train': 1.9094796180725098}
-03/05/2022 06:55:27 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/05/2022 06:55:31 - INFO - codeparrot_training - Step 35269: {'lr': 0.00044020829033174615, 'samples': 18058240, 'steps': 35269, 'loss/train': 1.143203616142273}
-03/05/2022 06:55:35 - INFO - codeparrot_training - Step 35270: {'lr': 0.0004402048464902414, 'samples': 18058752, 'steps': 35270, 'loss/train': 2.0604827404022217}
-03/05/2022 06:55:35 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 06:55:40 - INFO - codeparrot_training - Step 35271: {'lr': 0.0004402014025630332, 'samples': 18059264, 'steps': 35271, 'loss/train': 1.8925144672393799}
-03/05/2022 06:55:43 - INFO - codeparrot_training - Step 35272: {'lr': 0.00044019795855012325, 'samples': 18059776, 'steps': 35272, 'loss/train': 1.9194886684417725}
-03/05/2022 06:55:43 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/05/2022 06:55:48 - INFO - codeparrot_training - Step 35273: {'lr': 0.00044019451445151305, 'samples': 18060288, 'steps': 35273, 'loss/train': 1.029765009880066}
-03/05/2022 06:55:51 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/05/2022 06:55:54 - INFO - codeparrot_training - Step 35274: {'lr': 0.00044019107026720404, 'samples': 18060800, 'steps': 35274, 'loss/train': 2.251084089279175}
-03/05/2022 06:55:57 - INFO - codeparrot_training - Step 35275: {'lr': 0.00044018762599719796, 'samples': 18061312, 'steps': 35275, 'loss/train': 3.465636730194092}
-03/05/2022 06:56:00 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 06:56:02 - INFO - codeparrot_training - Step 35276: {'lr': 0.0004401841816414962, 'samples': 18061824, 'steps': 35276, 'loss/train': 1.4118013381958008}
-03/05/2022 06:56:05 - INFO - codeparrot_training - Step 35277: {'lr': 0.0004401807372001004, 'samples': 18062336, 'steps': 35277, 'loss/train': 1.5762361288070679}
-03/05/2022 06:56:08 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 06:56:11 - INFO - codeparrot_training - Step 35278: {'lr': 0.0004401772926730122, 'samples': 18062848, 'steps': 35278, 'loss/train': 1.6931037902832031}
-03/05/2022 06:56:14 - INFO - codeparrot_training - Step 35279: {'lr': 0.0004401738480602329, 'samples': 18063360, 'steps': 35279, 'loss/train': 2.070978879928589}
-03/05/2022 06:56:16 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/05/2022 06:56:19 - INFO - codeparrot_training - Step 35280: {'lr': 0.0004401704033617643, 'samples': 18063872, 'steps': 35280, 'loss/train': 2.350919485092163}
-03/05/2022 06:56:22 - INFO - codeparrot_training - Step 35281: {'lr': 0.0004401669585776078, 'samples': 18064384, 'steps': 35281, 'loss/train': 1.8100520372390747}
-03/05/2022 06:56:25 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/05/2022 06:56:27 - INFO - codeparrot_training - Step 35282: {'lr': 0.000440163513707765, 'samples': 18064896, 'steps': 35282, 'loss/train': 1.4309860467910767}
-03/05/2022 06:56:31 - INFO - codeparrot_training - Step 35283: {'lr': 0.00044016006875223745, 'samples': 18065408, 'steps': 35283, 'loss/train': 1.3934221267700195}
-03/05/2022 06:56:33 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/05/2022 06:56:36 - INFO - codeparrot_training - Step 35284: {'lr': 0.00044015662371102676, 'samples': 18065920, 'steps': 35284, 'loss/train': 1.2196741104125977}
-03/05/2022 06:56:39 - INFO - codeparrot_training - Step 35285: {'lr': 0.0004401531785841344, 'samples': 18066432, 'steps': 35285, 'loss/train': 0.1861148178577423}
-03/05/2022 06:56:42 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/05/2022 06:56:44 - INFO - codeparrot_training - Step 35286: {'lr': 0.00044014973337156197, 'samples': 18066944, 'steps': 35286, 'loss/train': 1.5490472316741943}
-03/05/2022 06:56:48 - INFO - codeparrot_training - Step 35287: {'lr': 0.0004401462880733109, 'samples': 18067456, 'steps': 35287, 'loss/train': 0.8867214322090149}
-03/05/2022 06:56:50 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/05/2022 06:56:53 - INFO - codeparrot_training - Step 35288: {'lr': 0.000440142842689383, 'samples': 18067968, 'steps': 35288, 'loss/train': 0.9408214092254639}
-03/05/2022 06:56:56 - INFO - codeparrot_training - Step 35289: {'lr': 0.00044013939721977957, 'samples': 18068480, 'steps': 35289, 'loss/train': 1.046529769897461}
-03/05/2022 06:56:58 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/05/2022 06:57:02 - INFO - codeparrot_training - Step 35290: {'lr': 0.0004401359516645023, 'samples': 18068992, 'steps': 35290, 'loss/train': 1.8166972398757935}
-03/05/2022 06:57:05 - INFO - codeparrot_training - Step 35291: {'lr': 0.0004401325060235527, 'samples': 18069504, 'steps': 35291, 'loss/train': 2.0292959213256836}
-03/05/2022 06:57:07 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/05/2022 06:57:10 - INFO - codeparrot_training - Step 35292: {'lr': 0.00044012906029693236, 'samples': 18070016, 'steps': 35292, 'loss/train': 2.0658133029937744}
-03/05/2022 06:57:13 - INFO - codeparrot_training - Step 35293: {'lr': 0.0004401256144846427, 'samples': 18070528, 'steps': 35293, 'loss/train': 1.2539781332015991}
-03/05/2022 06:57:15 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/05/2022 06:57:18 - INFO - codeparrot_training - Step 35294: {'lr': 0.0004401221685866854, 'samples': 18071040, 'steps': 35294, 'loss/train': 1.4674147367477417}
-03/05/2022 06:57:22 - INFO - codeparrot_training - Step 35295: {'lr': 0.00044011872260306205, 'samples': 18071552, 'steps': 35295, 'loss/train': 1.7095365524291992}
-03/05/2022 06:57:23 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 06:57:27 - INFO - codeparrot_training - Step 35296: {'lr': 0.00044011527653377416, 'samples': 18072064, 'steps': 35296, 'loss/train': 2.2766706943511963}
-03/05/2022 06:57:30 - INFO - codeparrot_training - Step 35297: {'lr': 0.0004401118303788232, 'samples': 18072576, 'steps': 35297, 'loss/train': 1.571519374847412}
-03/05/2022 06:57:32 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/05/2022 06:57:36 - INFO - codeparrot_training - Step 35298: {'lr': 0.00044010838413821075, 'samples': 18073088, 'steps': 35298, 'loss/train': 1.028382420539856}
-03/05/2022 06:57:39 - INFO - codeparrot_training - Step 35299: {'lr': 0.0004401049378119384, 'samples': 18073600, 'steps': 35299, 'loss/train': 1.6650125980377197}
-03/05/2022 06:57:43 - INFO - codeparrot_training - Step 35300: {'lr': 0.0004401014914000078, 'samples': 18074112, 'steps': 35300, 'loss/train': 1.7972372770309448}
-03/05/2022 06:57:44 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/05/2022 06:57:48 - INFO - codeparrot_training - Step 35301: {'lr': 0.00044009804490242026, 'samples': 18074624, 'steps': 35301, 'loss/train': 1.3866076469421387}
-03/05/2022 06:57:51 - INFO - codeparrot_training - Step 35302: {'lr': 0.00044009459831917755, 'samples': 18075136, 'steps': 35302, 'loss/train': 1.3412504196166992}
-03/05/2022 06:57:52 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/05/2022 06:57:56 - INFO - codeparrot_training - Step 35303: {'lr': 0.00044009115165028113, 'samples': 18075648, 'steps': 35303, 'loss/train': 1.9598032236099243}
-03/05/2022 06:58:00 - INFO - codeparrot_training - Step 35304: {'lr': 0.0004400877048957326, 'samples': 18076160, 'steps': 35304, 'loss/train': 2.306246280670166}
-03/05/2022 06:58:01 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/05/2022 06:58:05 - INFO - codeparrot_training - Step 35305: {'lr': 0.00044008425805553347, 'samples': 18076672, 'steps': 35305, 'loss/train': 2.0815351009368896}
-03/05/2022 06:58:08 - INFO - codeparrot_training - Step 35306: {'lr': 0.00044008081112968537, 'samples': 18077184, 'steps': 35306, 'loss/train': 1.9238163232803345}
-03/05/2022 06:58:09 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/05/2022 06:58:13 - INFO - codeparrot_training - Step 35307: {'lr': 0.0004400773641181897, 'samples': 18077696, 'steps': 35307, 'loss/train': 1.2600516080856323}
-03/05/2022 06:58:16 - INFO - codeparrot_training - Step 35308: {'lr': 0.0004400739170210481, 'samples': 18078208, 'steps': 35308, 'loss/train': 1.9850765466690063}
-03/05/2022 06:58:18 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/05/2022 06:58:22 - INFO - codeparrot_training - Step 35309: {'lr': 0.00044007046983826213, 'samples': 18078720, 'steps': 35309, 'loss/train': 1.2172423601150513}
-03/05/2022 06:58:25 - INFO - codeparrot_training - Step 35310: {'lr': 0.0004400670225698333, 'samples': 18079232, 'steps': 35310, 'loss/train': 1.993540644645691}
-03/05/2022 06:58:27 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/05/2022 06:58:30 - INFO - codeparrot_training - Step 35311: {'lr': 0.00044006357521576334, 'samples': 18079744, 'steps': 35311, 'loss/train': 1.8923696279525757}
-03/05/2022 06:58:33 - INFO - codeparrot_training - Step 35312: {'lr': 0.0004400601277760536, 'samples': 18080256, 'steps': 35312, 'loss/train': 2.0124077796936035}
-03/05/2022 06:58:35 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/05/2022 06:58:39 - INFO - codeparrot_training - Step 35313: {'lr': 0.0004400566802507057, 'samples': 18080768, 'steps': 35313, 'loss/train': 1.5543030500411987}
-03/05/2022 06:58:42 - INFO - codeparrot_training - Step 35314: {'lr': 0.0004400532326397211, 'samples': 18081280, 'steps': 35314, 'loss/train': 2.284696340560913}
-03/05/2022 06:58:43 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 06:58:47 - INFO - codeparrot_training - Step 35315: {'lr': 0.00044004978494310154, 'samples': 18081792, 'steps': 35315, 'loss/train': 1.8311705589294434}
-03/05/2022 06:58:50 - INFO - codeparrot_training - Step 35316: {'lr': 0.00044004633716084854, 'samples': 18082304, 'steps': 35316, 'loss/train': 1.121253490447998}
-03/05/2022 06:58:52 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/05/2022 06:58:56 - INFO - codeparrot_training - Step 35317: {'lr': 0.0004400428892929635, 'samples': 18082816, 'steps': 35317, 'loss/train': 0.7658836841583252}
-03/05/2022 06:58:59 - INFO - codeparrot_training - Step 35318: {'lr': 0.00044003944133944804, 'samples': 18083328, 'steps': 35318, 'loss/train': 1.0751616954803467}
-03/05/2022 06:59:01 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 06:59:04 - INFO - codeparrot_training - Step 35319: {'lr': 0.00044003599330030385, 'samples': 18083840, 'steps': 35319, 'loss/train': 1.7972129583358765}
-03/05/2022 06:59:07 - INFO - codeparrot_training - Step 35320: {'lr': 0.00044003254517553225, 'samples': 18084352, 'steps': 35320, 'loss/train': 2.182401418685913}
-03/05/2022 06:59:09 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/05/2022 06:59:13 - INFO - codeparrot_training - Step 35321: {'lr': 0.000440029096965135, 'samples': 18084864, 'steps': 35321, 'loss/train': 2.3707339763641357}
-03/05/2022 06:59:16 - INFO - codeparrot_training - Step 35322: {'lr': 0.0004400256486691135, 'samples': 18085376, 'steps': 35322, 'loss/train': 0.9176000356674194}
-03/05/2022 06:59:17 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/05/2022 06:59:21 - INFO - codeparrot_training - Step 35323: {'lr': 0.0004400222002874695, 'samples': 18085888, 'steps': 35323, 'loss/train': 1.3983089923858643}
-03/05/2022 06:59:24 - INFO - codeparrot_training - Step 35324: {'lr': 0.0004400187518202043, 'samples': 18086400, 'steps': 35324, 'loss/train': 2.0238094329833984}
-03/05/2022 06:59:26 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/05/2022 06:59:30 - INFO - codeparrot_training - Step 35325: {'lr': 0.00044001530326731966, 'samples': 18086912, 'steps': 35325, 'loss/train': 1.357438325881958}
-03/05/2022 06:59:33 - INFO - codeparrot_training - Step 35326: {'lr': 0.00044001185462881707, 'samples': 18087424, 'steps': 35326, 'loss/train': 1.9831361770629883}
-03/05/2022 06:59:38 - INFO - codeparrot_training - Step 35327: {'lr': 0.000440008405904698, 'samples': 18087936, 'steps': 35327, 'loss/train': 2.250537872314453}
-03/05/2022 06:59:41 - INFO - codeparrot_training - Step 35328: {'lr': 0.0004400049570949641, 'samples': 18088448, 'steps': 35328, 'loss/train': 2.08791184425354}
-03/05/2022 06:59:43 - INFO - codeparrot_training - Skipping example with length 750 (seq_length=1024)
-03/05/2022 06:59:47 - INFO - codeparrot_training - Step 35329: {'lr': 0.0004400015081996169, 'samples': 18088960, 'steps': 35329, 'loss/train': 0.4197874069213867}
-03/05/2022 06:59:50 - INFO - codeparrot_training - Step 35330: {'lr': 0.000439998059218658, 'samples': 18089472, 'steps': 35330, 'loss/train': 0.9868565797805786}
-03/05/2022 06:59:51 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/05/2022 06:59:55 - INFO - codeparrot_training - Step 35331: {'lr': 0.0004399946101520889, 'samples': 18089984, 'steps': 35331, 'loss/train': 1.6940288543701172}
-03/05/2022 06:59:58 - INFO - codeparrot_training - Step 35332: {'lr': 0.0004399911609999111, 'samples': 18090496, 'steps': 35332, 'loss/train': 0.921269416809082}
-03/05/2022 07:00:00 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/05/2022 07:00:03 - INFO - codeparrot_training - Step 35333: {'lr': 0.0004399877117621262, 'samples': 18091008, 'steps': 35333, 'loss/train': 1.8890599012374878}
-03/05/2022 07:00:07 - INFO - codeparrot_training - Step 35334: {'lr': 0.0004399842624387358, 'samples': 18091520, 'steps': 35334, 'loss/train': 1.8547402620315552}
-03/05/2022 07:00:08 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/05/2022 07:00:12 - INFO - codeparrot_training - Step 35335: {'lr': 0.0004399808130297415, 'samples': 18092032, 'steps': 35335, 'loss/train': 1.7220582962036133}
-03/05/2022 07:00:15 - INFO - codeparrot_training - Step 35336: {'lr': 0.0004399773635351446, 'samples': 18092544, 'steps': 35336, 'loss/train': 1.0082073211669922}
-03/05/2022 07:00:16 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/05/2022 07:00:20 - INFO - codeparrot_training - Step 35337: {'lr': 0.000439973913954947, 'samples': 18093056, 'steps': 35337, 'loss/train': 1.9139010906219482}
-03/05/2022 07:00:24 - INFO - codeparrot_training - Step 35338: {'lr': 0.00043997046428915, 'samples': 18093568, 'steps': 35338, 'loss/train': 1.4447370767593384}
-03/05/2022 07:00:25 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 07:00:29 - INFO - codeparrot_training - Step 35339: {'lr': 0.00043996701453775526, 'samples': 18094080, 'steps': 35339, 'loss/train': 1.6520748138427734}
-03/05/2022 07:00:32 - INFO - codeparrot_training - Step 35340: {'lr': 0.0004399635647007643, 'samples': 18094592, 'steps': 35340, 'loss/train': 1.9704729318618774}
-03/05/2022 07:00:33 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/05/2022 07:00:37 - INFO - codeparrot_training - Step 35341: {'lr': 0.00043996011477817875, 'samples': 18095104, 'steps': 35341, 'loss/train': 0.7786961793899536}
-03/05/2022 07:00:41 - INFO - codeparrot_training - Step 35342: {'lr': 0.0004399566647700001, 'samples': 18095616, 'steps': 35342, 'loss/train': 1.8221663236618042}
-03/05/2022 07:00:42 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/05/2022 07:00:46 - INFO - codeparrot_training - Step 35343: {'lr': 0.00043995321467622984, 'samples': 18096128, 'steps': 35343, 'loss/train': 2.1878201961517334}
-03/05/2022 07:00:49 - INFO - codeparrot_training - Step 35344: {'lr': 0.00043994976449686964, 'samples': 18096640, 'steps': 35344, 'loss/train': 1.6983578205108643}
-03/05/2022 07:00:50 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/05/2022 07:00:54 - INFO - codeparrot_training - Step 35345: {'lr': 0.000439946314231921, 'samples': 18097152, 'steps': 35345, 'loss/train': 2.1267080307006836}
-03/05/2022 07:00:58 - INFO - codeparrot_training - Step 35346: {'lr': 0.00043994286388138545, 'samples': 18097664, 'steps': 35346, 'loss/train': 1.5404174327850342}
-03/05/2022 07:00:58 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/05/2022 07:01:03 - INFO - codeparrot_training - Step 35347: {'lr': 0.00043993941344526455, 'samples': 18098176, 'steps': 35347, 'loss/train': 1.4122116565704346}
-03/05/2022 07:01:06 - INFO - codeparrot_training - Step 35348: {'lr': 0.00043993596292356, 'samples': 18098688, 'steps': 35348, 'loss/train': 1.5588442087173462}
-03/05/2022 07:01:07 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/05/2022 07:01:12 - INFO - codeparrot_training - Step 35349: {'lr': 0.00043993251231627315, 'samples': 18099200, 'steps': 35349, 'loss/train': 0.6924774646759033}
-03/05/2022 07:01:15 - INFO - codeparrot_training - Step 35350: {'lr': 0.00043992906162340563, 'samples': 18099712, 'steps': 35350, 'loss/train': 1.5470616817474365}
-03/05/2022 07:01:16 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/05/2022 07:01:20 - INFO - codeparrot_training - Step 35351: {'lr': 0.00043992561084495906, 'samples': 18100224, 'steps': 35351, 'loss/train': 1.2256709337234497}
-03/05/2022 07:01:23 - INFO - codeparrot_training - Step 35352: {'lr': 0.0004399221599809349, 'samples': 18100736, 'steps': 35352, 'loss/train': 1.5401110649108887}
-03/05/2022 07:01:24 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/05/2022 07:01:28 - INFO - codeparrot_training - Step 35353: {'lr': 0.0004399187090313348, 'samples': 18101248, 'steps': 35353, 'loss/train': 1.2445257902145386}
-03/05/2022 07:01:31 - INFO - codeparrot_training - Step 35354: {'lr': 0.00043991525799616017, 'samples': 18101760, 'steps': 35354, 'loss/train': 1.0015606880187988}
-03/05/2022 07:01:33 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/05/2022 07:01:37 - INFO - codeparrot_training - Step 35355: {'lr': 0.0004399118068754127, 'samples': 18102272, 'steps': 35355, 'loss/train': 1.7397176027297974}
-03/05/2022 07:01:40 - INFO - codeparrot_training - Step 35356: {'lr': 0.0004399083556690939, 'samples': 18102784, 'steps': 35356, 'loss/train': 1.5548946857452393}
-03/05/2022 07:01:42 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/05/2022 07:01:45 - INFO - codeparrot_training - Step 35357: {'lr': 0.0004399049043772053, 'samples': 18103296, 'steps': 35357, 'loss/train': 1.9874422550201416}
-03/05/2022 07:01:48 - INFO - codeparrot_training - Step 35358: {'lr': 0.00043990145299974853, 'samples': 18103808, 'steps': 35358, 'loss/train': 1.2755451202392578}
-03/05/2022 07:01:50 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/05/2022 07:01:54 - INFO - codeparrot_training - Step 35359: {'lr': 0.0004398980015367251, 'samples': 18104320, 'steps': 35359, 'loss/train': 1.3763563632965088}
-03/05/2022 07:01:57 - INFO - codeparrot_training - Step 35360: {'lr': 0.00043989454998813655, 'samples': 18104832, 'steps': 35360, 'loss/train': 1.8528356552124023}
-03/05/2022 07:01:58 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/05/2022 07:02:03 - INFO - codeparrot_training - Step 35361: {'lr': 0.00043989109835398444, 'samples': 18105344, 'steps': 35361, 'loss/train': 1.833365797996521}
-03/05/2022 07:02:06 - INFO - codeparrot_training - Step 35362: {'lr': 0.0004398876466342703, 'samples': 18105856, 'steps': 35362, 'loss/train': 2.0001299381256104}
-03/05/2022 07:02:08 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/05/2022 07:02:11 - INFO - codeparrot_training - Step 35363: {'lr': 0.0004398841948289958, 'samples': 18106368, 'steps': 35363, 'loss/train': 1.8641129732131958}
-03/05/2022 07:02:14 - INFO - codeparrot_training - Step 35364: {'lr': 0.0004398807429381623, 'samples': 18106880, 'steps': 35364, 'loss/train': 1.8249119520187378}
-03/05/2022 07:02:17 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 07:02:20 - INFO - codeparrot_training - Step 35365: {'lr': 0.0004398772909617715, 'samples': 18107392, 'steps': 35365, 'loss/train': 2.0784218311309814}
-03/05/2022 07:02:23 - INFO - codeparrot_training - Step 35366: {'lr': 0.00043987383889982495, 'samples': 18107904, 'steps': 35366, 'loss/train': 2.1477928161621094}
-03/05/2022 07:02:28 - INFO - codeparrot_training - Step 35367: {'lr': 0.00043987038675232415, 'samples': 18108416, 'steps': 35367, 'loss/train': 2.054490327835083}
-03/05/2022 07:02:31 - INFO - codeparrot_training - Step 35368: {'lr': 0.00043986693451927074, 'samples': 18108928, 'steps': 35368, 'loss/train': 1.482446312904358}
-03/05/2022 07:02:33 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/05/2022 07:02:36 - INFO - codeparrot_training - Step 35369: {'lr': 0.0004398634822006662, 'samples': 18109440, 'steps': 35369, 'loss/train': 1.7927310466766357}
-03/05/2022 07:02:39 - INFO - codeparrot_training - Step 35370: {'lr': 0.0004398600297965121, 'samples': 18109952, 'steps': 35370, 'loss/train': 1.8192603588104248}
-03/05/2022 07:02:41 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/05/2022 07:02:45 - INFO - codeparrot_training - Step 35371: {'lr': 0.00043985657730680997, 'samples': 18110464, 'steps': 35371, 'loss/train': 1.9959499835968018}
-03/05/2022 07:02:48 - INFO - codeparrot_training - Step 35372: {'lr': 0.00043985312473156143, 'samples': 18110976, 'steps': 35372, 'loss/train': 1.8132721185684204}
-03/05/2022 07:02:50 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/05/2022 07:02:53 - INFO - codeparrot_training - Step 35373: {'lr': 0.000439849672070768, 'samples': 18111488, 'steps': 35373, 'loss/train': 1.3391412496566772}
-03/05/2022 07:02:56 - INFO - codeparrot_training - Step 35374: {'lr': 0.00043984621932443115, 'samples': 18112000, 'steps': 35374, 'loss/train': 1.7567896842956543}
-03/05/2022 07:02:58 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/05/2022 07:03:02 - INFO - codeparrot_training - Step 35375: {'lr': 0.0004398427664925526, 'samples': 18112512, 'steps': 35375, 'loss/train': 1.798269510269165}
-03/05/2022 07:03:05 - INFO - codeparrot_training - Step 35376: {'lr': 0.0004398393135751338, 'samples': 18113024, 'steps': 35376, 'loss/train': 1.3682106733322144}
-03/05/2022 07:03:07 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/05/2022 07:03:10 - INFO - codeparrot_training - Step 35377: {'lr': 0.0004398358605721764, 'samples': 18113536, 'steps': 35377, 'loss/train': 1.4039280414581299}
-03/05/2022 07:03:14 - INFO - codeparrot_training - Step 35378: {'lr': 0.00043983240748368186, 'samples': 18114048, 'steps': 35378, 'loss/train': 1.766485571861267}
-03/05/2022 07:03:16 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/05/2022 07:03:19 - INFO - codeparrot_training - Step 35379: {'lr': 0.0004398289543096518, 'samples': 18114560, 'steps': 35379, 'loss/train': 1.9724292755126953}
-03/05/2022 07:03:22 - INFO - codeparrot_training - Step 35380: {'lr': 0.0004398255010500877, 'samples': 18115072, 'steps': 35380, 'loss/train': 1.424758791923523}
-03/05/2022 07:03:24 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/05/2022 07:03:27 - INFO - codeparrot_training - Step 35381: {'lr': 0.00043982204770499114, 'samples': 18115584, 'steps': 35381, 'loss/train': 1.5251657962799072}
-03/05/2022 07:03:30 - INFO - codeparrot_training - Step 35382: {'lr': 0.0004398185942743637, 'samples': 18116096, 'steps': 35382, 'loss/train': 1.8977800607681274}
-03/05/2022 07:03:32 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/05/2022 07:03:36 - INFO - codeparrot_training - Step 35383: {'lr': 0.00043981514075820693, 'samples': 18116608, 'steps': 35383, 'loss/train': 2.8138232231140137}
-03/05/2022 07:03:39 - INFO - codeparrot_training - Step 35384: {'lr': 0.0004398116871565224, 'samples': 18117120, 'steps': 35384, 'loss/train': 2.2875161170959473}
-03/05/2022 07:03:42 - INFO - codeparrot_training - Step 35385: {'lr': 0.0004398082334693116, 'samples': 18117632, 'steps': 35385, 'loss/train': 1.1356678009033203}
-03/05/2022 07:03:43 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/05/2022 07:03:48 - INFO - codeparrot_training - Step 35386: {'lr': 0.0004398047796965762, 'samples': 18118144, 'steps': 35386, 'loss/train': 1.838055968284607}
-03/05/2022 07:03:51 - INFO - codeparrot_training - Step 35387: {'lr': 0.0004398013258383177, 'samples': 18118656, 'steps': 35387, 'loss/train': 1.5081732273101807}
-03/05/2022 07:03:51 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/05/2022 07:03:56 - INFO - codeparrot_training - Step 35388: {'lr': 0.0004397978718945377, 'samples': 18119168, 'steps': 35388, 'loss/train': 1.5435891151428223}
-03/05/2022 07:03:59 - INFO - codeparrot_training - Step 35389: {'lr': 0.0004397944178652376, 'samples': 18119680, 'steps': 35389, 'loss/train': 1.090344786643982}
-03/05/2022 07:04:00 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/05/2022 07:04:04 - INFO - codeparrot_training - Step 35390: {'lr': 0.0004397909637504191, 'samples': 18120192, 'steps': 35390, 'loss/train': 1.2470654249191284}
-03/05/2022 07:04:08 - INFO - codeparrot_training - Step 35391: {'lr': 0.00043978750955008374, 'samples': 18120704, 'steps': 35391, 'loss/train': 1.9085487127304077}
-03/05/2022 07:04:08 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/05/2022 07:04:13 - INFO - codeparrot_training - Step 35392: {'lr': 0.00043978405526423305, 'samples': 18121216, 'steps': 35392, 'loss/train': 1.8536357879638672}
-03/05/2022 07:04:16 - INFO - codeparrot_training - Step 35393: {'lr': 0.0004397806008928686, 'samples': 18121728, 'steps': 35393, 'loss/train': 2.1193811893463135}
-03/05/2022 07:04:17 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/05/2022 07:04:21 - INFO - codeparrot_training - Step 35394: {'lr': 0.00043977714643599194, 'samples': 18122240, 'steps': 35394, 'loss/train': 2.59478759765625}
-03/05/2022 07:04:25 - INFO - codeparrot_training - Step 35395: {'lr': 0.0004397736918936046, 'samples': 18122752, 'steps': 35395, 'loss/train': 2.2446210384368896}
-03/05/2022 07:04:25 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 07:04:30 - INFO - codeparrot_training - Step 35396: {'lr': 0.0004397702372657082, 'samples': 18123264, 'steps': 35396, 'loss/train': 2.155799388885498}
-03/05/2022 07:04:33 - INFO - codeparrot_training - Step 35397: {'lr': 0.00043976678255230417, 'samples': 18123776, 'steps': 35397, 'loss/train': 1.3293895721435547}
-03/05/2022 07:04:33 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/05/2022 07:04:38 - INFO - codeparrot_training - Step 35398: {'lr': 0.0004397633277533942, 'samples': 18124288, 'steps': 35398, 'loss/train': 2.1473093032836914}
-03/05/2022 07:04:41 - INFO - codeparrot_training - Step 35399: {'lr': 0.0004397598728689799, 'samples': 18124800, 'steps': 35399, 'loss/train': 0.9424858093261719}
-03/05/2022 07:04:41 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/05/2022 07:04:47 - INFO - codeparrot_training - Step 35400: {'lr': 0.0004397564178990626, 'samples': 18125312, 'steps': 35400, 'loss/train': 1.1495715379714966}
-03/05/2022 07:04:50 - INFO - codeparrot_training - Step 35401: {'lr': 0.0004397529628436441, 'samples': 18125824, 'steps': 35401, 'loss/train': 1.5135173797607422}
-03/05/2022 07:04:50 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/05/2022 07:04:55 - INFO - codeparrot_training - Step 35402: {'lr': 0.0004397495077027258, 'samples': 18126336, 'steps': 35402, 'loss/train': 1.9945933818817139}
-03/05/2022 07:04:58 - INFO - codeparrot_training - Step 35403: {'lr': 0.0004397460524763093, 'samples': 18126848, 'steps': 35403, 'loss/train': 1.6207804679870605}
-03/05/2022 07:04:58 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/05/2022 07:05:04 - INFO - codeparrot_training - Step 35404: {'lr': 0.00043974259716439613, 'samples': 18127360, 'steps': 35404, 'loss/train': 1.6628955602645874}
-03/05/2022 07:05:06 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/05/2022 07:05:09 - INFO - codeparrot_training - Step 35405: {'lr': 0.0004397391417669878, 'samples': 18127872, 'steps': 35405, 'loss/train': 0.11123427748680115}
-03/05/2022 07:05:12 - INFO - codeparrot_training - Step 35406: {'lr': 0.0004397356862840861, 'samples': 18128384, 'steps': 35406, 'loss/train': 2.481821060180664}
-03/05/2022 07:05:15 - INFO - codeparrot_training - Step 35407: {'lr': 0.00043973223071569234, 'samples': 18128896, 'steps': 35407, 'loss/train': 1.215630054473877}
-03/05/2022 07:05:16 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/05/2022 07:05:21 - INFO - codeparrot_training - Step 35408: {'lr': 0.0004397287750618082, 'samples': 18129408, 'steps': 35408, 'loss/train': 1.9810402393341064}
-03/05/2022 07:05:24 - INFO - codeparrot_training - Step 35409: {'lr': 0.00043972531932243516, 'samples': 18129920, 'steps': 35409, 'loss/train': 1.8107131719589233}
-03/05/2022 07:05:24 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/05/2022 07:05:29 - INFO - codeparrot_training - Step 35410: {'lr': 0.00043972186349757484, 'samples': 18130432, 'steps': 35410, 'loss/train': 2.0783777236938477}
-03/05/2022 07:05:32 - INFO - codeparrot_training - Step 35411: {'lr': 0.0004397184075872288, 'samples': 18130944, 'steps': 35411, 'loss/train': 1.9865747690200806}
-03/05/2022 07:05:32 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/05/2022 07:05:38 - INFO - codeparrot_training - Step 35412: {'lr': 0.0004397149515913985, 'samples': 18131456, 'steps': 35412, 'loss/train': 1.385214924812317}
-03/05/2022 07:05:41 - INFO - codeparrot_training - Step 35413: {'lr': 0.0004397114955100856, 'samples': 18131968, 'steps': 35413, 'loss/train': 1.933100700378418}
-03/05/2022 07:05:41 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/05/2022 07:05:46 - INFO - codeparrot_training - Step 35414: {'lr': 0.00043970803934329167, 'samples': 18132480, 'steps': 35414, 'loss/train': 1.5497139692306519}
-03/05/2022 07:05:49 - INFO - codeparrot_training - Step 35415: {'lr': 0.00043970458309101825, 'samples': 18132992, 'steps': 35415, 'loss/train': 1.764042615890503}
-03/05/2022 07:05:50 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 07:05:55 - INFO - codeparrot_training - Step 35416: {'lr': 0.0004397011267532668, 'samples': 18133504, 'steps': 35416, 'loss/train': 1.5525791645050049}
-03/05/2022 07:05:58 - INFO - codeparrot_training - Step 35417: {'lr': 0.00043969767033003894, 'samples': 18134016, 'steps': 35417, 'loss/train': 1.6743561029434204}
-03/05/2022 07:05:58 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/05/2022 07:06:03 - INFO - codeparrot_training - Step 35418: {'lr': 0.0004396942138213363, 'samples': 18134528, 'steps': 35418, 'loss/train': 1.0302960872650146}
-03/05/2022 07:06:06 - INFO - codeparrot_training - Step 35419: {'lr': 0.00043969075722716033, 'samples': 18135040, 'steps': 35419, 'loss/train': 0.9071533679962158}
-03/05/2022 07:06:07 - INFO - codeparrot_training - Skipping example with length 578 (seq_length=1024)
-03/05/2022 07:06:12 - INFO - codeparrot_training - Step 35420: {'lr': 0.0004396873005475127, 'samples': 18135552, 'steps': 35420, 'loss/train': 1.0570669174194336}
-03/05/2022 07:06:15 - INFO - codeparrot_training - Step 35421: {'lr': 0.00043968384378239477, 'samples': 18136064, 'steps': 35421, 'loss/train': 1.7101402282714844}
-03/05/2022 07:06:15 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/05/2022 07:06:20 - INFO - codeparrot_training - Step 35422: {'lr': 0.00043968038693180834, 'samples': 18136576, 'steps': 35422, 'loss/train': 1.5428553819656372}
-03/05/2022 07:06:23 - INFO - codeparrot_training - Step 35423: {'lr': 0.00043967692999575484, 'samples': 18137088, 'steps': 35423, 'loss/train': 1.3712791204452515}
-03/05/2022 07:06:24 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/05/2022 07:06:28 - INFO - codeparrot_training - Step 35424: {'lr': 0.00043967347297423575, 'samples': 18137600, 'steps': 35424, 'loss/train': 2.416916608810425}
-03/05/2022 07:06:32 - INFO - codeparrot_training - Step 35425: {'lr': 0.0004396700158672528, 'samples': 18138112, 'steps': 35425, 'loss/train': 1.770281434059143}
-03/05/2022 07:06:32 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 07:06:37 - INFO - codeparrot_training - Step 35426: {'lr': 0.0004396665586748075, 'samples': 18138624, 'steps': 35426, 'loss/train': 1.5821340084075928}
-03/05/2022 07:06:40 - INFO - codeparrot_training - Step 35427: {'lr': 0.0004396631013969013, 'samples': 18139136, 'steps': 35427, 'loss/train': 2.406684398651123}
-03/05/2022 07:06:42 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/05/2022 07:06:46 - INFO - codeparrot_training - Step 35428: {'lr': 0.0004396596440335359, 'samples': 18139648, 'steps': 35428, 'loss/train': 1.2668864727020264}
-03/05/2022 07:06:49 - INFO - codeparrot_training - Step 35429: {'lr': 0.00043965618658471276, 'samples': 18140160, 'steps': 35429, 'loss/train': 2.0522406101226807}
-03/05/2022 07:06:51 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/05/2022 07:06:55 - INFO - codeparrot_training - Step 35430: {'lr': 0.0004396527290504334, 'samples': 18140672, 'steps': 35430, 'loss/train': 2.2182958126068115}
-03/05/2022 07:06:58 - INFO - codeparrot_training - Step 35431: {'lr': 0.00043964927143069955, 'samples': 18141184, 'steps': 35431, 'loss/train': 1.9079910516738892}
-03/05/2022 07:07:01 - INFO - codeparrot_training - Step 35432: {'lr': 0.0004396458137255126, 'samples': 18141696, 'steps': 35432, 'loss/train': 2.1030709743499756}
-03/05/2022 07:07:02 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/05/2022 07:07:06 - INFO - codeparrot_training - Step 35433: {'lr': 0.0004396423559348742, 'samples': 18142208, 'steps': 35433, 'loss/train': 1.1751620769500732}
-03/05/2022 07:07:09 - INFO - codeparrot_training - Step 35434: {'lr': 0.0004396388980587859, 'samples': 18142720, 'steps': 35434, 'loss/train': 6.445013999938965}
-03/05/2022 07:07:11 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/05/2022 07:07:15 - INFO - codeparrot_training - Step 35435: {'lr': 0.0004396354400972492, 'samples': 18143232, 'steps': 35435, 'loss/train': 2.357273817062378}
-03/05/2022 07:07:18 - INFO - codeparrot_training - Step 35436: {'lr': 0.0004396319820502657, 'samples': 18143744, 'steps': 35436, 'loss/train': 1.5290404558181763}
-03/05/2022 07:07:19 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 07:07:23 - INFO - codeparrot_training - Step 35437: {'lr': 0.000439628523917837, 'samples': 18144256, 'steps': 35437, 'loss/train': 1.7425615787506104}
-03/05/2022 07:07:26 - INFO - codeparrot_training - Step 35438: {'lr': 0.0004396250656999646, 'samples': 18144768, 'steps': 35438, 'loss/train': 1.2589610815048218}
-03/05/2022 07:07:28 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/05/2022 07:07:32 - INFO - codeparrot_training - Step 35439: {'lr': 0.00043962160739665, 'samples': 18145280, 'steps': 35439, 'loss/train': 1.6665329933166504}
-03/05/2022 07:07:35 - INFO - codeparrot_training - Step 35440: {'lr': 0.0004396181490078949, 'samples': 18145792, 'steps': 35440, 'loss/train': 1.3968522548675537}
-03/05/2022 07:07:36 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/05/2022 07:07:40 - INFO - codeparrot_training - Step 35441: {'lr': 0.0004396146905337008, 'samples': 18146304, 'steps': 35441, 'loss/train': 2.1200029850006104}
-03/05/2022 07:07:43 - INFO - codeparrot_training - Step 35442: {'lr': 0.0004396112319740692, 'samples': 18146816, 'steps': 35442, 'loss/train': 1.8281176090240479}
-03/05/2022 07:07:44 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/05/2022 07:07:49 - INFO - codeparrot_training - Step 35443: {'lr': 0.0004396077733290017, 'samples': 18147328, 'steps': 35443, 'loss/train': 2.0901455879211426}
-03/05/2022 07:07:52 - INFO - codeparrot_training - Step 35444: {'lr': 0.00043960431459849993, 'samples': 18147840, 'steps': 35444, 'loss/train': 2.52892804145813}
-03/05/2022 07:07:52 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/05/2022 07:07:57 - INFO - codeparrot_training - Step 35445: {'lr': 0.00043960085578256537, 'samples': 18148352, 'steps': 35445, 'loss/train': 1.5809903144836426}
-03/05/2022 07:08:00 - INFO - codeparrot_training - Step 35446: {'lr': 0.0004395973968811995, 'samples': 18148864, 'steps': 35446, 'loss/train': 2.4038071632385254}
-03/05/2022 07:08:01 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/05/2022 07:08:05 - INFO - codeparrot_training - Step 35447: {'lr': 0.00043959393789440407, 'samples': 18149376, 'steps': 35447, 'loss/train': 0.4924311935901642}
-03/05/2022 07:08:09 - INFO - codeparrot_training - Step 35448: {'lr': 0.0004395904788221805, 'samples': 18149888, 'steps': 35448, 'loss/train': 1.245524287223816}
-03/05/2022 07:08:09 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/05/2022 07:08:14 - INFO - codeparrot_training - Step 35449: {'lr': 0.00043958701966453033, 'samples': 18150400, 'steps': 35449, 'loss/train': 2.1025407314300537}
-03/05/2022 07:08:17 - INFO - codeparrot_training - Step 35450: {'lr': 0.00043958356042145524, 'samples': 18150912, 'steps': 35450, 'loss/train': 2.7735891342163086}
-03/05/2022 07:08:18 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/05/2022 07:08:23 - INFO - codeparrot_training - Step 35451: {'lr': 0.0004395801010929567, 'samples': 18151424, 'steps': 35451, 'loss/train': 2.761763572692871}
-03/05/2022 07:08:26 - INFO - codeparrot_training - Step 35452: {'lr': 0.0004395766416790363, 'samples': 18151936, 'steps': 35452, 'loss/train': 2.127596616744995}
-03/05/2022 07:08:27 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 07:08:31 - INFO - codeparrot_training - Step 35453: {'lr': 0.0004395731821796956, 'samples': 18152448, 'steps': 35453, 'loss/train': 0.496438205242157}
-03/05/2022 07:08:34 - INFO - codeparrot_training - Step 35454: {'lr': 0.00043956972259493615, 'samples': 18152960, 'steps': 35454, 'loss/train': 1.444140076637268}
-03/05/2022 07:08:35 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/05/2022 07:08:40 - INFO - codeparrot_training - Step 35455: {'lr': 0.0004395662629247595, 'samples': 18153472, 'steps': 35455, 'loss/train': 2.186835527420044}
-03/05/2022 07:08:43 - INFO - codeparrot_training - Step 35456: {'lr': 0.0004395628031691672, 'samples': 18153984, 'steps': 35456, 'loss/train': 2.2724175453186035}
-03/05/2022 07:08:44 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/05/2022 07:08:48 - INFO - codeparrot_training - Step 35457: {'lr': 0.00043955934332816083, 'samples': 18154496, 'steps': 35457, 'loss/train': 1.7552236318588257}
-03/05/2022 07:08:51 - INFO - codeparrot_training - Step 35458: {'lr': 0.00043955588340174195, 'samples': 18155008, 'steps': 35458, 'loss/train': 1.7095812559127808}
-03/05/2022 07:08:52 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/05/2022 07:08:56 - INFO - codeparrot_training - Step 35459: {'lr': 0.00043955242338991217, 'samples': 18155520, 'steps': 35459, 'loss/train': 1.1616950035095215}
-03/05/2022 07:08:59 - INFO - codeparrot_training - Step 35460: {'lr': 0.0004395489632926729, 'samples': 18156032, 'steps': 35460, 'loss/train': 2.2740976810455322}
-03/05/2022 07:09:01 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/05/2022 07:09:05 - INFO - codeparrot_training - Step 35461: {'lr': 0.0004395455031100258, 'samples': 18156544, 'steps': 35461, 'loss/train': 1.907161831855774}
-03/05/2022 07:09:08 - INFO - codeparrot_training - Step 35462: {'lr': 0.0004395420428419725, 'samples': 18157056, 'steps': 35462, 'loss/train': 1.5770634412765503}
-03/05/2022 07:09:09 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/05/2022 07:09:13 - INFO - codeparrot_training - Step 35463: {'lr': 0.0004395385824885144, 'samples': 18157568, 'steps': 35463, 'loss/train': 1.1826404333114624}
-03/05/2022 07:09:17 - INFO - codeparrot_training - Step 35464: {'lr': 0.0004395351220496532, 'samples': 18158080, 'steps': 35464, 'loss/train': 1.6916604042053223}
-03/05/2022 07:09:18 - INFO - codeparrot_training - Skipping example with length 103 (seq_length=1024)
-03/05/2022 07:09:22 - INFO - codeparrot_training - Step 35465: {'lr': 0.00043953166152539035, 'samples': 18158592, 'steps': 35465, 'loss/train': 1.3167383670806885}
-03/05/2022 07:09:25 - INFO - codeparrot_training - Step 35466: {'lr': 0.00043952820091572753, 'samples': 18159104, 'steps': 35466, 'loss/train': 1.7261786460876465}
-03/05/2022 07:09:26 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 07:09:31 - INFO - codeparrot_training - Step 35467: {'lr': 0.0004395247402206662, 'samples': 18159616, 'steps': 35467, 'loss/train': 1.892163872718811}
-03/05/2022 07:09:34 - INFO - codeparrot_training - Step 35468: {'lr': 0.0004395212794402079, 'samples': 18160128, 'steps': 35468, 'loss/train': 1.805734634399414}
-03/05/2022 07:09:35 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/05/2022 07:09:40 - INFO - codeparrot_training - Step 35469: {'lr': 0.00043951781857435424, 'samples': 18160640, 'steps': 35469, 'loss/train': 1.634075403213501}
-03/05/2022 07:09:43 - INFO - codeparrot_training - Step 35470: {'lr': 0.00043951435762310686, 'samples': 18161152, 'steps': 35470, 'loss/train': 1.328317642211914}
-03/05/2022 07:09:46 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/05/2022 07:09:48 - INFO - codeparrot_training - Step 35471: {'lr': 0.0004395108965864671, 'samples': 18161664, 'steps': 35471, 'loss/train': 1.683003306388855}
-03/05/2022 07:09:51 - INFO - codeparrot_training - Step 35472: {'lr': 0.00043950743546443676, 'samples': 18162176, 'steps': 35472, 'loss/train': 2.213649272918701}
-03/05/2022 07:09:54 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/05/2022 07:09:57 - INFO - codeparrot_training - Step 35473: {'lr': 0.0004395039742570173, 'samples': 18162688, 'steps': 35473, 'loss/train': 0.5966029167175293}
-03/05/2022 07:10:00 - INFO - codeparrot_training - Step 35474: {'lr': 0.00043950051296421023, 'samples': 18163200, 'steps': 35474, 'loss/train': 2.132533311843872}
-03/05/2022 07:10:02 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/05/2022 07:10:05 - INFO - codeparrot_training - Step 35475: {'lr': 0.00043949705158601715, 'samples': 18163712, 'steps': 35475, 'loss/train': 2.346548557281494}
-03/05/2022 07:10:08 - INFO - codeparrot_training - Step 35476: {'lr': 0.00043949359012243963, 'samples': 18164224, 'steps': 35476, 'loss/train': 0.19669486582279205}
-03/05/2022 07:10:11 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 07:10:14 - INFO - codeparrot_training - Step 35477: {'lr': 0.00043949012857347924, 'samples': 18164736, 'steps': 35477, 'loss/train': 2.09114670753479}
-03/05/2022 07:10:17 - INFO - codeparrot_training - Step 35478: {'lr': 0.0004394866669391375, 'samples': 18165248, 'steps': 35478, 'loss/train': 0.9605236649513245}
-03/05/2022 07:10:19 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/05/2022 07:10:23 - INFO - codeparrot_training - Step 35479: {'lr': 0.00043948320521941596, 'samples': 18165760, 'steps': 35479, 'loss/train': 2.3185317516326904}
-03/05/2022 07:10:26 - INFO - codeparrot_training - Step 35480: {'lr': 0.00043947974341431627, 'samples': 18166272, 'steps': 35480, 'loss/train': 1.4365769624710083}
-03/05/2022 07:10:29 - INFO - codeparrot_training - Step 35481: {'lr': 0.0004394762815238399, 'samples': 18166784, 'steps': 35481, 'loss/train': 0.5044175982475281}
-03/05/2022 07:10:29 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/05/2022 07:10:34 - INFO - codeparrot_training - Step 35482: {'lr': 0.00043947281954798844, 'samples': 18167296, 'steps': 35482, 'loss/train': 1.957090139389038}
-03/05/2022 07:10:38 - INFO - codeparrot_training - Step 35483: {'lr': 0.0004394693574867635, 'samples': 18167808, 'steps': 35483, 'loss/train': 1.3616678714752197}
-03/05/2022 07:10:38 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/05/2022 07:10:43 - INFO - codeparrot_training - Step 35484: {'lr': 0.0004394658953401666, 'samples': 18168320, 'steps': 35484, 'loss/train': 0.8078387975692749}
-03/05/2022 07:10:46 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/05/2022 07:10:49 - INFO - codeparrot_training - Step 35485: {'lr': 0.0004394624331081992, 'samples': 18168832, 'steps': 35485, 'loss/train': 1.4853671789169312}
-03/05/2022 07:10:52 - INFO - codeparrot_training - Step 35486: {'lr': 0.00043945897079086295, 'samples': 18169344, 'steps': 35486, 'loss/train': 1.071881890296936}
-03/05/2022 07:10:55 - INFO - codeparrot_training - Step 35487: {'lr': 0.00043945550838815953, 'samples': 18169856, 'steps': 35487, 'loss/train': 1.9065582752227783}
-03/05/2022 07:10:56 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 07:11:00 - INFO - codeparrot_training - Step 35488: {'lr': 0.00043945204590009027, 'samples': 18170368, 'steps': 35488, 'loss/train': 1.715984582901001}
-03/05/2022 07:11:03 - INFO - codeparrot_training - Step 35489: {'lr': 0.0004394485833266569, 'samples': 18170880, 'steps': 35489, 'loss/train': 2.254807710647583}
-03/05/2022 07:11:04 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/05/2022 07:11:09 - INFO - codeparrot_training - Step 35490: {'lr': 0.0004394451206678609, 'samples': 18171392, 'steps': 35490, 'loss/train': 1.1345527172088623}
-03/05/2022 07:11:12 - INFO - codeparrot_training - Step 35491: {'lr': 0.00043944165792370385, 'samples': 18171904, 'steps': 35491, 'loss/train': 1.626334547996521}
-03/05/2022 07:11:13 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/05/2022 07:11:17 - INFO - codeparrot_training - Step 35492: {'lr': 0.00043943819509418723, 'samples': 18172416, 'steps': 35492, 'loss/train': 2.012094497680664}
-03/05/2022 07:11:20 - INFO - codeparrot_training - Step 35493: {'lr': 0.00043943473217931283, 'samples': 18172928, 'steps': 35493, 'loss/train': 1.216780424118042}
-03/05/2022 07:11:21 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/05/2022 07:11:26 - INFO - codeparrot_training - Step 35494: {'lr': 0.0004394312691790821, 'samples': 18173440, 'steps': 35494, 'loss/train': 0.43173399567604065}
-03/05/2022 07:11:29 - INFO - codeparrot_training - Step 35495: {'lr': 0.00043942780609349636, 'samples': 18173952, 'steps': 35495, 'loss/train': 1.4299708604812622}
-03/05/2022 07:11:29 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/05/2022 07:11:34 - INFO - codeparrot_training - Step 35496: {'lr': 0.0004394243429225575, 'samples': 18174464, 'steps': 35496, 'loss/train': 6.322597026824951}
-03/05/2022 07:11:37 - INFO - codeparrot_training - Step 35497: {'lr': 0.0004394208796662669, 'samples': 18174976, 'steps': 35497, 'loss/train': 1.6650282144546509}
-03/05/2022 07:11:38 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/05/2022 07:11:43 - INFO - codeparrot_training - Step 35498: {'lr': 0.00043941741632462625, 'samples': 18175488, 'steps': 35498, 'loss/train': 1.5233014822006226}
-03/05/2022 07:11:46 - INFO - codeparrot_training - Step 35499: {'lr': 0.000439413952897637, 'samples': 18176000, 'steps': 35499, 'loss/train': 0.5743542909622192}
-03/05/2022 07:11:46 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/05/2022 07:11:51 - INFO - codeparrot_training - Step 35500: {'lr': 0.0004394104893853007, 'samples': 18176512, 'steps': 35500, 'loss/train': 1.6607469320297241}
-03/05/2022 07:11:54 - INFO - codeparrot_training - Step 35501: {'lr': 0.00043940702578761906, 'samples': 18177024, 'steps': 35501, 'loss/train': 2.5239627361297607}
-03/05/2022 07:11:55 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/05/2022 07:11:59 - INFO - codeparrot_training - Step 35502: {'lr': 0.00043940356210459344, 'samples': 18177536, 'steps': 35502, 'loss/train': 2.0733163356781006}
-03/05/2022 07:12:03 - INFO - codeparrot_training - Step 35503: {'lr': 0.0004394000983362255, 'samples': 18178048, 'steps': 35503, 'loss/train': 1.381777048110962}
-03/05/2022 07:12:03 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/05/2022 07:12:08 - INFO - codeparrot_training - Step 35504: {'lr': 0.0004393966344825168, 'samples': 18178560, 'steps': 35504, 'loss/train': 2.083183765411377}
-03/05/2022 07:12:11 - INFO - codeparrot_training - Step 35505: {'lr': 0.00043939317054346894, 'samples': 18179072, 'steps': 35505, 'loss/train': 1.6750946044921875}
-03/05/2022 07:12:12 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 07:12:16 - INFO - codeparrot_training - Step 35506: {'lr': 0.00043938970651908346, 'samples': 18179584, 'steps': 35506, 'loss/train': 1.3924260139465332}
-03/05/2022 07:12:19 - INFO - codeparrot_training - Step 35507: {'lr': 0.0004393862424093619, 'samples': 18180096, 'steps': 35507, 'loss/train': 1.8256967067718506}
-03/05/2022 07:12:20 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/05/2022 07:12:25 - INFO - codeparrot_training - Step 35508: {'lr': 0.0004393827782143057, 'samples': 18180608, 'steps': 35508, 'loss/train': 1.2805529832839966}
-03/05/2022 07:12:28 - INFO - codeparrot_training - Step 35509: {'lr': 0.00043937931393391667, 'samples': 18181120, 'steps': 35509, 'loss/train': 2.308640718460083}
-03/05/2022 07:12:28 - INFO - codeparrot_training - Skipping example with length 178 (seq_length=1024)
-03/05/2022 07:12:33 - INFO - codeparrot_training - Step 35510: {'lr': 0.0004393758495681962, 'samples': 18181632, 'steps': 35510, 'loss/train': 1.4325696229934692}
-03/05/2022 07:12:37 - INFO - codeparrot_training - Step 35511: {'lr': 0.0004393723851171459, 'samples': 18182144, 'steps': 35511, 'loss/train': 1.8442778587341309}
-03/05/2022 07:12:37 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/05/2022 07:12:42 - INFO - codeparrot_training - Step 35512: {'lr': 0.0004393689205807673, 'samples': 18182656, 'steps': 35512, 'loss/train': 1.6317551136016846}
-03/05/2022 07:12:45 - INFO - codeparrot_training - Step 35513: {'lr': 0.00043936545595906206, 'samples': 18183168, 'steps': 35513, 'loss/train': 2.220817804336548}
-03/05/2022 07:12:45 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/05/2022 07:12:50 - INFO - codeparrot_training - Step 35514: {'lr': 0.00043936199125203156, 'samples': 18183680, 'steps': 35514, 'loss/train': 1.5724210739135742}
-03/05/2022 07:12:53 - INFO - codeparrot_training - Step 35515: {'lr': 0.00043935852645967755, 'samples': 18184192, 'steps': 35515, 'loss/train': 0.8419063687324524}
-03/05/2022 07:12:54 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/05/2022 07:12:59 - INFO - codeparrot_training - Step 35516: {'lr': 0.00043935506158200143, 'samples': 18184704, 'steps': 35516, 'loss/train': 1.531604290008545}
-03/05/2022 07:13:03 - INFO - codeparrot_training - Step 35517: {'lr': 0.000439351596619005, 'samples': 18185216, 'steps': 35517, 'loss/train': 2.169106960296631}
-03/05/2022 07:13:06 - INFO - codeparrot_training - Step 35518: {'lr': 0.00043934813157068956, 'samples': 18185728, 'steps': 35518, 'loss/train': 1.196284532546997}
-03/05/2022 07:13:06 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/05/2022 07:13:11 - INFO - codeparrot_training - Step 35519: {'lr': 0.00043934466643705673, 'samples': 18186240, 'steps': 35519, 'loss/train': 1.7818623781204224}
-03/05/2022 07:13:15 - INFO - codeparrot_training - Step 35520: {'lr': 0.00043934120121810814, 'samples': 18186752, 'steps': 35520, 'loss/train': 1.0350135564804077}
-03/05/2022 07:13:15 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/05/2022 07:13:20 - INFO - codeparrot_training - Step 35521: {'lr': 0.0004393377359138454, 'samples': 18187264, 'steps': 35521, 'loss/train': 1.635295033454895}
-03/05/2022 07:13:23 - INFO - codeparrot_training - Step 35522: {'lr': 0.00043933427052426986, 'samples': 18187776, 'steps': 35522, 'loss/train': 1.3483483791351318}
-03/05/2022 07:13:23 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 07:13:28 - INFO - codeparrot_training - Step 35523: {'lr': 0.00043933080504938337, 'samples': 18188288, 'steps': 35523, 'loss/train': 2.1573848724365234}
-03/05/2022 07:13:32 - INFO - codeparrot_training - Step 35524: {'lr': 0.00043932733948918724, 'samples': 18188800, 'steps': 35524, 'loss/train': 0.502007007598877}
-03/05/2022 07:13:32 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/05/2022 07:13:37 - INFO - codeparrot_training - Step 35525: {'lr': 0.0004393238738436832, 'samples': 18189312, 'steps': 35525, 'loss/train': 1.383028507232666}
-03/05/2022 07:13:40 - INFO - codeparrot_training - Step 35526: {'lr': 0.00043932040811287264, 'samples': 18189824, 'steps': 35526, 'loss/train': 1.2182127237319946}
-03/05/2022 07:13:41 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/05/2022 07:13:45 - INFO - codeparrot_training - Step 35527: {'lr': 0.0004393169422967573, 'samples': 18190336, 'steps': 35527, 'loss/train': 1.360651969909668}
-03/05/2022 07:13:49 - INFO - codeparrot_training - Step 35528: {'lr': 0.0004393134763953387, 'samples': 18190848, 'steps': 35528, 'loss/train': 1.233083724975586}
-03/05/2022 07:13:49 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/05/2022 07:13:54 - INFO - codeparrot_training - Step 35529: {'lr': 0.00043931001040861835, 'samples': 18191360, 'steps': 35529, 'loss/train': 2.583538770675659}
-03/05/2022 07:13:57 - INFO - codeparrot_training - Step 35530: {'lr': 0.00043930654433659775, 'samples': 18191872, 'steps': 35530, 'loss/train': 1.9437367916107178}
-03/05/2022 07:13:58 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/05/2022 07:14:03 - INFO - codeparrot_training - Step 35531: {'lr': 0.0004393030781792787, 'samples': 18192384, 'steps': 35531, 'loss/train': 0.9135006666183472}
-03/05/2022 07:14:06 - INFO - codeparrot_training - Step 35532: {'lr': 0.00043929961193666246, 'samples': 18192896, 'steps': 35532, 'loss/train': 2.134550094604492}
-03/05/2022 07:14:07 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/05/2022 07:14:11 - INFO - codeparrot_training - Step 35533: {'lr': 0.0004392961456087508, 'samples': 18193408, 'steps': 35533, 'loss/train': 1.5983855724334717}
-03/05/2022 07:14:14 - INFO - codeparrot_training - Step 35534: {'lr': 0.00043929267919554516, 'samples': 18193920, 'steps': 35534, 'loss/train': 2.3285133838653564}
-03/05/2022 07:14:16 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 07:14:20 - INFO - codeparrot_training - Step 35535: {'lr': 0.00043928921269704725, 'samples': 18194432, 'steps': 35535, 'loss/train': 1.2281553745269775}
-03/05/2022 07:14:23 - INFO - codeparrot_training - Step 35536: {'lr': 0.00043928574611325845, 'samples': 18194944, 'steps': 35536, 'loss/train': 0.7840021848678589}
-03/05/2022 07:14:25 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/05/2022 07:14:28 - INFO - codeparrot_training - Step 35537: {'lr': 0.00043928227944418046, 'samples': 18195456, 'steps': 35537, 'loss/train': 1.269748330116272}
-03/05/2022 07:14:31 - INFO - codeparrot_training - Step 35538: {'lr': 0.00043927881268981484, 'samples': 18195968, 'steps': 35538, 'loss/train': 2.0974810123443604}
-03/05/2022 07:14:33 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 07:14:37 - INFO - codeparrot_training - Step 35539: {'lr': 0.00043927534585016305, 'samples': 18196480, 'steps': 35539, 'loss/train': 1.9360780715942383}
-03/05/2022 07:14:40 - INFO - codeparrot_training - Step 35540: {'lr': 0.0004392718789252267, 'samples': 18196992, 'steps': 35540, 'loss/train': 0.7840116620063782}
-03/05/2022 07:14:41 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 07:14:45 - INFO - codeparrot_training - Step 35541: {'lr': 0.0004392684119150074, 'samples': 18197504, 'steps': 35541, 'loss/train': 0.9602648019790649}
-03/05/2022 07:14:48 - INFO - codeparrot_training - Step 35542: {'lr': 0.0004392649448195066, 'samples': 18198016, 'steps': 35542, 'loss/train': 1.4598722457885742}
-03/05/2022 07:14:49 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/05/2022 07:14:54 - INFO - codeparrot_training - Step 35543: {'lr': 0.000439261477638726, 'samples': 18198528, 'steps': 35543, 'loss/train': 1.2526623010635376}
-03/05/2022 07:14:57 - INFO - codeparrot_training - Step 35544: {'lr': 0.0004392580103726671, 'samples': 18199040, 'steps': 35544, 'loss/train': 1.5337557792663574}
-03/05/2022 07:14:59 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/05/2022 07:15:02 - INFO - codeparrot_training - Step 35545: {'lr': 0.0004392545430213315, 'samples': 18199552, 'steps': 35545, 'loss/train': 1.4768348932266235}
-03/05/2022 07:15:06 - INFO - codeparrot_training - Step 35546: {'lr': 0.00043925107558472065, 'samples': 18200064, 'steps': 35546, 'loss/train': 1.4838359355926514}
-03/05/2022 07:15:08 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/05/2022 07:15:11 - INFO - codeparrot_training - Step 35547: {'lr': 0.0004392476080628363, 'samples': 18200576, 'steps': 35547, 'loss/train': 0.7412009835243225}
-03/05/2022 07:15:14 - INFO - codeparrot_training - Step 35548: {'lr': 0.00043924414045567973, 'samples': 18201088, 'steps': 35548, 'loss/train': 2.0830180644989014}
-03/05/2022 07:15:16 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/05/2022 07:15:19 - INFO - codeparrot_training - Step 35549: {'lr': 0.00043924067276325274, 'samples': 18201600, 'steps': 35549, 'loss/train': 0.8914379477500916}
-03/05/2022 07:15:22 - INFO - codeparrot_training - Step 35550: {'lr': 0.0004392372049855569, 'samples': 18202112, 'steps': 35550, 'loss/train': 1.7571898698806763}
-03/05/2022 07:15:25 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/05/2022 07:15:28 - INFO - codeparrot_training - Step 35551: {'lr': 0.0004392337371225936, 'samples': 18202624, 'steps': 35551, 'loss/train': 1.8011308908462524}
-03/05/2022 07:15:31 - INFO - codeparrot_training - Step 35552: {'lr': 0.0004392302691743645, 'samples': 18203136, 'steps': 35552, 'loss/train': 1.298619031906128}
-03/05/2022 07:15:33 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/05/2022 07:15:36 - INFO - codeparrot_training - Step 35553: {'lr': 0.0004392268011408712, 'samples': 18203648, 'steps': 35553, 'loss/train': 0.891318142414093}
-03/05/2022 07:15:39 - INFO - codeparrot_training - Step 35554: {'lr': 0.0004392233330221152, 'samples': 18204160, 'steps': 35554, 'loss/train': 1.9722446203231812}
-03/05/2022 07:15:42 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 07:15:45 - INFO - codeparrot_training - Step 35555: {'lr': 0.0004392198648180981, 'samples': 18204672, 'steps': 35555, 'loss/train': 1.735204815864563}
-03/05/2022 07:15:48 - INFO - codeparrot_training - Step 35556: {'lr': 0.0004392163965288215, 'samples': 18205184, 'steps': 35556, 'loss/train': 1.578781247138977}
-03/05/2022 07:15:50 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/05/2022 07:15:53 - INFO - codeparrot_training - Step 35557: {'lr': 0.0004392129281542868, 'samples': 18205696, 'steps': 35557, 'loss/train': 1.948217749595642}
-03/05/2022 07:15:56 - INFO - codeparrot_training - Step 35558: {'lr': 0.00043920945969449577, 'samples': 18206208, 'steps': 35558, 'loss/train': 1.560465931892395}
-03/05/2022 07:15:58 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/05/2022 07:16:02 - INFO - codeparrot_training - Step 35559: {'lr': 0.0004392059911494498, 'samples': 18206720, 'steps': 35559, 'loss/train': 1.9493038654327393}
-03/05/2022 07:16:05 - INFO - codeparrot_training - Step 35560: {'lr': 0.0004392025225191506, 'samples': 18207232, 'steps': 35560, 'loss/train': 1.4980286359786987}
-03/05/2022 07:16:07 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 07:16:10 - INFO - codeparrot_training - Step 35561: {'lr': 0.0004391990538035996, 'samples': 18207744, 'steps': 35561, 'loss/train': 1.2428779602050781}
-03/05/2022 07:16:13 - INFO - codeparrot_training - Step 35562: {'lr': 0.00043919558500279845, 'samples': 18208256, 'steps': 35562, 'loss/train': 1.3592733144760132}
-03/05/2022 07:16:15 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 07:16:18 - INFO - codeparrot_training - Step 35563: {'lr': 0.0004391921161167487, 'samples': 18208768, 'steps': 35563, 'loss/train': 1.3949799537658691}
-03/05/2022 07:16:22 - INFO - codeparrot_training - Step 35564: {'lr': 0.00043918864714545194, 'samples': 18209280, 'steps': 35564, 'loss/train': 2.0902833938598633}
-03/05/2022 07:16:27 - INFO - codeparrot_training - Step 35565: {'lr': 0.00043918517808890964, 'samples': 18209792, 'steps': 35565, 'loss/train': 1.7150702476501465}
-03/05/2022 07:16:30 - INFO - codeparrot_training - Step 35566: {'lr': 0.0004391817089471234, 'samples': 18210304, 'steps': 35566, 'loss/train': 1.2185090780258179}
-03/05/2022 07:16:32 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/05/2022 07:16:35 - INFO - codeparrot_training - Step 35567: {'lr': 0.0004391782397200949, 'samples': 18210816, 'steps': 35567, 'loss/train': 1.7002531290054321}
-03/05/2022 07:16:38 - INFO - codeparrot_training - Step 35568: {'lr': 0.0004391747704078255, 'samples': 18211328, 'steps': 35568, 'loss/train': 1.7351813316345215}
-03/05/2022 07:16:41 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/05/2022 07:16:44 - INFO - codeparrot_training - Step 35569: {'lr': 0.0004391713010103169, 'samples': 18211840, 'steps': 35569, 'loss/train': 2.4453492164611816}
-03/05/2022 07:16:47 - INFO - codeparrot_training - Step 35570: {'lr': 0.0004391678315275706, 'samples': 18212352, 'steps': 35570, 'loss/train': 1.2943658828735352}
-03/05/2022 07:16:49 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/05/2022 07:16:52 - INFO - codeparrot_training - Step 35571: {'lr': 0.00043916436195958825, 'samples': 18212864, 'steps': 35571, 'loss/train': 1.8873891830444336}
-03/05/2022 07:16:55 - INFO - codeparrot_training - Step 35572: {'lr': 0.00043916089230637133, 'samples': 18213376, 'steps': 35572, 'loss/train': 1.5061194896697998}
-03/05/2022 07:16:57 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 07:17:01 - INFO - codeparrot_training - Step 35573: {'lr': 0.0004391574225679215, 'samples': 18213888, 'steps': 35573, 'loss/train': 1.7620962858200073}
-03/05/2022 07:17:04 - INFO - codeparrot_training - Step 35574: {'lr': 0.0004391539527442401, 'samples': 18214400, 'steps': 35574, 'loss/train': 1.66138756275177}
-03/05/2022 07:17:06 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/05/2022 07:17:09 - INFO - codeparrot_training - Step 35575: {'lr': 0.000439150482835329, 'samples': 18214912, 'steps': 35575, 'loss/train': 2.205457925796509}
-03/05/2022 07:17:12 - INFO - codeparrot_training - Step 35576: {'lr': 0.0004391470128411895, 'samples': 18215424, 'steps': 35576, 'loss/train': 2.679546594619751}
-03/05/2022 07:17:14 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/05/2022 07:17:17 - INFO - codeparrot_training - Step 35577: {'lr': 0.00043914354276182335, 'samples': 18215936, 'steps': 35577, 'loss/train': 1.6146609783172607}
-03/05/2022 07:17:21 - INFO - codeparrot_training - Step 35578: {'lr': 0.00043914007259723196, 'samples': 18216448, 'steps': 35578, 'loss/train': 1.694009780883789}
-03/05/2022 07:17:22 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/05/2022 07:17:26 - INFO - codeparrot_training - Step 35579: {'lr': 0.000439136602347417, 'samples': 18216960, 'steps': 35579, 'loss/train': 2.3900341987609863}
-03/05/2022 07:17:29 - INFO - codeparrot_training - Step 35580: {'lr': 0.00043913313201238017, 'samples': 18217472, 'steps': 35580, 'loss/train': 1.9951441287994385}
-03/05/2022 07:17:34 - INFO - codeparrot_training - Step 35581: {'lr': 0.00043912966159212263, 'samples': 18217984, 'steps': 35581, 'loss/train': 1.2046443223953247}
-03/05/2022 07:17:37 - INFO - codeparrot_training - Step 35582: {'lr': 0.0004391261910866463, 'samples': 18218496, 'steps': 35582, 'loss/train': 2.3222105503082275}
-03/05/2022 07:17:39 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 07:17:43 - INFO - codeparrot_training - Step 35583: {'lr': 0.0004391227204959526, 'samples': 18219008, 'steps': 35583, 'loss/train': 2.3945767879486084}
-03/05/2022 07:17:46 - INFO - codeparrot_training - Step 35584: {'lr': 0.00043911924982004315, 'samples': 18219520, 'steps': 35584, 'loss/train': 0.5633180141448975}
-03/05/2022 07:17:48 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/05/2022 07:17:51 - INFO - codeparrot_training - Step 35585: {'lr': 0.0004391157790589195, 'samples': 18220032, 'steps': 35585, 'loss/train': 0.3848421573638916}
-03/05/2022 07:17:55 - INFO - codeparrot_training - Step 35586: {'lr': 0.00043911230821258313, 'samples': 18220544, 'steps': 35586, 'loss/train': 3.2703511714935303}
-03/05/2022 07:17:57 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/05/2022 07:18:00 - INFO - codeparrot_training - Step 35587: {'lr': 0.00043910883728103575, 'samples': 18221056, 'steps': 35587, 'loss/train': 0.9034063816070557}
-03/05/2022 07:18:03 - INFO - codeparrot_training - Step 35588: {'lr': 0.0004391053662642788, 'samples': 18221568, 'steps': 35588, 'loss/train': 1.2314529418945312}
-03/05/2022 07:18:05 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/05/2022 07:18:08 - INFO - codeparrot_training - Step 35589: {'lr': 0.00043910189516231386, 'samples': 18222080, 'steps': 35589, 'loss/train': 2.209214448928833}
-03/05/2022 07:18:11 - INFO - codeparrot_training - Step 35590: {'lr': 0.00043909842397514255, 'samples': 18222592, 'steps': 35590, 'loss/train': 1.742717981338501}
-03/05/2022 07:18:13 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/05/2022 07:18:17 - INFO - codeparrot_training - Step 35591: {'lr': 0.00043909495270276646, 'samples': 18223104, 'steps': 35591, 'loss/train': 0.9844104051589966}
-03/05/2022 07:18:20 - INFO - codeparrot_training - Step 35592: {'lr': 0.00043909148134518703, 'samples': 18223616, 'steps': 35592, 'loss/train': 1.893539309501648}
-03/05/2022 07:18:22 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/05/2022 07:18:25 - INFO - codeparrot_training - Step 35593: {'lr': 0.0004390880099024059, 'samples': 18224128, 'steps': 35593, 'loss/train': 1.1582869291305542}
-03/05/2022 07:18:29 - INFO - codeparrot_training - Step 35594: {'lr': 0.00043908453837442464, 'samples': 18224640, 'steps': 35594, 'loss/train': 1.4650366306304932}
-03/05/2022 07:18:31 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 07:18:34 - INFO - codeparrot_training - Step 35595: {'lr': 0.0004390810667612448, 'samples': 18225152, 'steps': 35595, 'loss/train': 1.613234281539917}
-03/05/2022 07:18:37 - INFO - codeparrot_training - Step 35596: {'lr': 0.00043907759506286797, 'samples': 18225664, 'steps': 35596, 'loss/train': 2.4216630458831787}
-03/05/2022 07:18:39 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/05/2022 07:18:42 - INFO - codeparrot_training - Step 35597: {'lr': 0.00043907412327929575, 'samples': 18226176, 'steps': 35597, 'loss/train': 1.9293183088302612}
-03/05/2022 07:18:45 - INFO - codeparrot_training - Step 35598: {'lr': 0.00043907065141052953, 'samples': 18226688, 'steps': 35598, 'loss/train': 1.966095209121704}
-03/05/2022 07:18:47 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 07:18:51 - INFO - codeparrot_training - Step 35599: {'lr': 0.00043906717945657104, 'samples': 18227200, 'steps': 35599, 'loss/train': 1.903415560722351}
-03/05/2022 07:18:54 - INFO - codeparrot_training - Step 35600: {'lr': 0.00043906370741742185, 'samples': 18227712, 'steps': 35600, 'loss/train': 1.459360122680664}
-03/05/2022 07:18:56 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/05/2022 07:18:59 - INFO - codeparrot_training - Step 35601: {'lr': 0.0004390602352930834, 'samples': 18228224, 'steps': 35601, 'loss/train': 1.2528719902038574}
-03/05/2022 07:19:03 - INFO - codeparrot_training - Step 35602: {'lr': 0.00043905676308355734, 'samples': 18228736, 'steps': 35602, 'loss/train': 3.0356974601745605}
-03/05/2022 07:19:05 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/05/2022 07:19:08 - INFO - codeparrot_training - Step 35603: {'lr': 0.00043905329078884527, 'samples': 18229248, 'steps': 35603, 'loss/train': 0.8444804549217224}
-03/05/2022 07:19:11 - INFO - codeparrot_training - Step 35604: {'lr': 0.00043904981840894863, 'samples': 18229760, 'steps': 35604, 'loss/train': 2.0784029960632324}
-03/05/2022 07:19:14 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/05/2022 07:19:16 - INFO - codeparrot_training - Step 35605: {'lr': 0.0004390463459438691, 'samples': 18230272, 'steps': 35605, 'loss/train': 1.8745253086090088}
-03/05/2022 07:19:19 - INFO - codeparrot_training - Step 35606: {'lr': 0.0004390428733936082, 'samples': 18230784, 'steps': 35606, 'loss/train': 1.8388772010803223}
-03/05/2022 07:19:25 - INFO - codeparrot_training - Step 35607: {'lr': 0.0004390394007581675, 'samples': 18231296, 'steps': 35607, 'loss/train': 1.691643476486206}
-03/05/2022 07:19:28 - INFO - codeparrot_training - Step 35608: {'lr': 0.00043903592803754856, 'samples': 18231808, 'steps': 35608, 'loss/train': 1.3373836278915405}
-03/05/2022 07:19:31 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/05/2022 07:19:33 - INFO - codeparrot_training - Step 35609: {'lr': 0.00043903245523175296, 'samples': 18232320, 'steps': 35609, 'loss/train': 2.0462119579315186}
-03/05/2022 07:19:36 - INFO - codeparrot_training - Step 35610: {'lr': 0.00043902898234078223, 'samples': 18232832, 'steps': 35610, 'loss/train': 1.7619023323059082}
-03/05/2022 07:19:39 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/05/2022 07:19:42 - INFO - codeparrot_training - Step 35611: {'lr': 0.000439025509364638, 'samples': 18233344, 'steps': 35611, 'loss/train': 0.6433806419372559}
-03/05/2022 07:19:45 - INFO - codeparrot_training - Step 35612: {'lr': 0.0004390220363033217, 'samples': 18233856, 'steps': 35612, 'loss/train': 6.154721260070801}
-03/05/2022 07:19:47 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/05/2022 07:19:50 - INFO - codeparrot_training - Step 35613: {'lr': 0.0004390185631568351, 'samples': 18234368, 'steps': 35613, 'loss/train': 1.7400320768356323}
-03/05/2022 07:19:53 - INFO - codeparrot_training - Step 35614: {'lr': 0.00043901508992517956, 'samples': 18234880, 'steps': 35614, 'loss/train': 1.95522940158844}
-03/05/2022 07:19:55 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/05/2022 07:19:59 - INFO - codeparrot_training - Step 35615: {'lr': 0.0004390116166083568, 'samples': 18235392, 'steps': 35615, 'loss/train': 1.9352779388427734}
-03/05/2022 07:20:02 - INFO - codeparrot_training - Step 35616: {'lr': 0.00043900814320636827, 'samples': 18235904, 'steps': 35616, 'loss/train': 0.711889922618866}
-03/05/2022 07:20:04 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 07:20:07 - INFO - codeparrot_training - Step 35617: {'lr': 0.00043900466971921563, 'samples': 18236416, 'steps': 35617, 'loss/train': 1.5717843770980835}
-03/05/2022 07:20:10 - INFO - codeparrot_training - Step 35618: {'lr': 0.00043900119614690043, 'samples': 18236928, 'steps': 35618, 'loss/train': 1.1290003061294556}
-03/05/2022 07:20:13 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/05/2022 07:20:16 - INFO - codeparrot_training - Step 35619: {'lr': 0.00043899772248942413, 'samples': 18237440, 'steps': 35619, 'loss/train': 1.0690252780914307}
-03/05/2022 07:20:19 - INFO - codeparrot_training - Step 35620: {'lr': 0.0004389942487467884, 'samples': 18237952, 'steps': 35620, 'loss/train': 2.1186439990997314}
-03/05/2022 07:20:23 - INFO - codeparrot_training - Step 35621: {'lr': 0.00043899077491899485, 'samples': 18238464, 'steps': 35621, 'loss/train': 2.1440682411193848}
-03/05/2022 07:20:24 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/05/2022 07:20:28 - INFO - codeparrot_training - Step 35622: {'lr': 0.0004389873010060449, 'samples': 18238976, 'steps': 35622, 'loss/train': 0.7072810530662537}
-03/05/2022 07:20:31 - INFO - codeparrot_training - Step 35623: {'lr': 0.00043898382700794015, 'samples': 18239488, 'steps': 35623, 'loss/train': 1.4474983215332031}
-03/05/2022 07:20:33 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/05/2022 07:20:36 - INFO - codeparrot_training - Step 35624: {'lr': 0.0004389803529246823, 'samples': 18240000, 'steps': 35624, 'loss/train': 2.4290003776550293}
-03/05/2022 07:20:40 - INFO - codeparrot_training - Step 35625: {'lr': 0.00043897687875627277, 'samples': 18240512, 'steps': 35625, 'loss/train': 1.6359623670578003}
-03/05/2022 07:20:42 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/05/2022 07:20:45 - INFO - codeparrot_training - Step 35626: {'lr': 0.00043897340450271317, 'samples': 18241024, 'steps': 35626, 'loss/train': 0.7164183259010315}
-03/05/2022 07:20:48 - INFO - codeparrot_training - Step 35627: {'lr': 0.0004389699301640051, 'samples': 18241536, 'steps': 35627, 'loss/train': 2.275535821914673}
-03/05/2022 07:20:50 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/05/2022 07:20:53 - INFO - codeparrot_training - Step 35628: {'lr': 0.00043896645574015004, 'samples': 18242048, 'steps': 35628, 'loss/train': 2.32814359664917}
-03/05/2022 07:20:57 - INFO - codeparrot_training - Step 35629: {'lr': 0.00043896298123114965, 'samples': 18242560, 'steps': 35629, 'loss/train': 1.890061378479004}
-03/05/2022 07:20:58 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/05/2022 07:21:02 - INFO - codeparrot_training - Step 35630: {'lr': 0.00043895950663700546, 'samples': 18243072, 'steps': 35630, 'loss/train': 1.9485187530517578}
-03/05/2022 07:21:05 - INFO - codeparrot_training - Step 35631: {'lr': 0.000438956031957719, 'samples': 18243584, 'steps': 35631, 'loss/train': 1.4140589237213135}
-03/05/2022 07:21:07 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/05/2022 07:21:10 - INFO - codeparrot_training - Step 35632: {'lr': 0.0004389525571932919, 'samples': 18244096, 'steps': 35632, 'loss/train': 2.2518224716186523}
-03/05/2022 07:21:13 - INFO - codeparrot_training - Step 35633: {'lr': 0.00043894908234372564, 'samples': 18244608, 'steps': 35633, 'loss/train': 2.2509548664093018}
-03/05/2022 07:21:15 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/05/2022 07:21:19 - INFO - codeparrot_training - Step 35634: {'lr': 0.0004389456074090219, 'samples': 18245120, 'steps': 35634, 'loss/train': 1.710856318473816}
-03/05/2022 07:21:22 - INFO - codeparrot_training - Step 35635: {'lr': 0.0004389421323891822, 'samples': 18245632, 'steps': 35635, 'loss/train': 0.9506700038909912}
-03/05/2022 07:21:24 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/05/2022 07:21:27 - INFO - codeparrot_training - Step 35636: {'lr': 0.000438938657284208, 'samples': 18246144, 'steps': 35636, 'loss/train': 1.5618674755096436}
-03/05/2022 07:21:30 - INFO - codeparrot_training - Step 35637: {'lr': 0.000438935182094101, 'samples': 18246656, 'steps': 35637, 'loss/train': 1.8619160652160645}
-03/05/2022 07:21:33 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/05/2022 07:21:36 - INFO - codeparrot_training - Step 35638: {'lr': 0.0004389317068188628, 'samples': 18247168, 'steps': 35638, 'loss/train': 0.7068888545036316}
-03/05/2022 07:21:39 - INFO - codeparrot_training - Step 35639: {'lr': 0.0004389282314584948, 'samples': 18247680, 'steps': 35639, 'loss/train': 2.058039426803589}
-03/05/2022 07:21:41 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/05/2022 07:21:44 - INFO - codeparrot_training - Step 35640: {'lr': 0.0004389247560129987, 'samples': 18248192, 'steps': 35640, 'loss/train': 2.0194778442382812}
-03/05/2022 07:21:47 - INFO - codeparrot_training - Step 35641: {'lr': 0.000438921280482376, 'samples': 18248704, 'steps': 35641, 'loss/train': 2.144296169281006}
-03/05/2022 07:21:49 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/05/2022 07:21:52 - INFO - codeparrot_training - Step 35642: {'lr': 0.00043891780486662825, 'samples': 18249216, 'steps': 35642, 'loss/train': 2.3053619861602783}
-03/05/2022 07:21:55 - INFO - codeparrot_training - Step 35643: {'lr': 0.00043891432916575714, 'samples': 18249728, 'steps': 35643, 'loss/train': 1.8547847270965576}
-03/05/2022 07:21:58 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/05/2022 07:22:01 - INFO - codeparrot_training - Step 35644: {'lr': 0.0004389108533797641, 'samples': 18250240, 'steps': 35644, 'loss/train': 2.2515838146209717}
-03/05/2022 07:22:04 - INFO - codeparrot_training - Step 35645: {'lr': 0.00043890737750865074, 'samples': 18250752, 'steps': 35645, 'loss/train': 1.921485424041748}
-03/05/2022 07:22:06 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 07:22:09 - INFO - codeparrot_training - Step 35646: {'lr': 0.0004389039015524186, 'samples': 18251264, 'steps': 35646, 'loss/train': 2.322957754135132}
-03/05/2022 07:22:13 - INFO - codeparrot_training - Step 35647: {'lr': 0.0004389004255110693, 'samples': 18251776, 'steps': 35647, 'loss/train': 2.6784703731536865}
-03/05/2022 07:22:15 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/05/2022 07:22:18 - INFO - codeparrot_training - Step 35648: {'lr': 0.0004388969493846044, 'samples': 18252288, 'steps': 35648, 'loss/train': 1.5431900024414062}
-03/05/2022 07:22:21 - INFO - codeparrot_training - Step 35649: {'lr': 0.00043889347317302543, 'samples': 18252800, 'steps': 35649, 'loss/train': 1.628823161125183}
-03/05/2022 07:22:23 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/05/2022 07:22:26 - INFO - codeparrot_training - Step 35650: {'lr': 0.000438889996876334, 'samples': 18253312, 'steps': 35650, 'loss/train': 0.5356725454330444}
-03/05/2022 07:22:29 - INFO - codeparrot_training - Step 35651: {'lr': 0.00043888652049453163, 'samples': 18253824, 'steps': 35651, 'loss/train': 1.8715674877166748}
-03/05/2022 07:22:31 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/05/2022 07:22:35 - INFO - codeparrot_training - Step 35652: {'lr': 0.0004388830440276199, 'samples': 18254336, 'steps': 35652, 'loss/train': 1.2664936780929565}
-03/05/2022 07:22:38 - INFO - codeparrot_training - Step 35653: {'lr': 0.0004388795674756004, 'samples': 18254848, 'steps': 35653, 'loss/train': 1.775356650352478}
-03/05/2022 07:22:39 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/05/2022 07:22:43 - INFO - codeparrot_training - Step 35654: {'lr': 0.0004388760908384747, 'samples': 18255360, 'steps': 35654, 'loss/train': 0.935798704624176}
-03/05/2022 07:22:46 - INFO - codeparrot_training - Step 35655: {'lr': 0.00043887261411624433, 'samples': 18255872, 'steps': 35655, 'loss/train': 1.4448611736297607}
-03/05/2022 07:22:48 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/05/2022 07:22:52 - INFO - codeparrot_training - Step 35656: {'lr': 0.00043886913730891087, 'samples': 18256384, 'steps': 35656, 'loss/train': 2.3188467025756836}
-03/05/2022 07:22:55 - INFO - codeparrot_training - Step 35657: {'lr': 0.00043886566041647593, 'samples': 18256896, 'steps': 35657, 'loss/train': 1.8766250610351562}
-03/05/2022 07:22:56 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/05/2022 07:23:00 - INFO - codeparrot_training - Step 35658: {'lr': 0.000438862183438941, 'samples': 18257408, 'steps': 35658, 'loss/train': 1.5627849102020264}
-03/05/2022 07:23:03 - INFO - codeparrot_training - Step 35659: {'lr': 0.00043885870637630763, 'samples': 18257920, 'steps': 35659, 'loss/train': 1.8145678043365479}
-03/05/2022 07:23:05 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/05/2022 07:23:08 - INFO - codeparrot_training - Step 35660: {'lr': 0.00043885522922857757, 'samples': 18258432, 'steps': 35660, 'loss/train': 1.4663059711456299}
-03/05/2022 07:23:12 - INFO - codeparrot_training - Step 35661: {'lr': 0.00043885175199575216, 'samples': 18258944, 'steps': 35661, 'loss/train': 1.478531837463379}
-03/05/2022 07:23:13 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/05/2022 07:23:17 - INFO - codeparrot_training - Step 35662: {'lr': 0.00043884827467783303, 'samples': 18259456, 'steps': 35662, 'loss/train': 1.6084387302398682}
-03/05/2022 07:23:20 - INFO - codeparrot_training - Step 35663: {'lr': 0.00043884479727482193, 'samples': 18259968, 'steps': 35663, 'loss/train': 1.3304052352905273}
-03/05/2022 07:23:21 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/05/2022 07:23:25 - INFO - codeparrot_training - Step 35664: {'lr': 0.00043884131978672014, 'samples': 18260480, 'steps': 35664, 'loss/train': 1.6129413843154907}
-03/05/2022 07:23:28 - INFO - codeparrot_training - Step 35665: {'lr': 0.00043883784221352947, 'samples': 18260992, 'steps': 35665, 'loss/train': 0.9870860576629639}
-03/05/2022 07:23:30 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 07:23:34 - INFO - codeparrot_training - Step 35666: {'lr': 0.00043883436455525125, 'samples': 18261504, 'steps': 35666, 'loss/train': 1.9057637453079224}
-03/05/2022 07:23:37 - INFO - codeparrot_training - Step 35667: {'lr': 0.0004388308868118873, 'samples': 18262016, 'steps': 35667, 'loss/train': 1.8430458307266235}
-03/05/2022 07:23:38 - INFO - codeparrot_training - Skipping example with length 160 (seq_length=1024)
-03/05/2022 07:23:42 - INFO - codeparrot_training - Step 35668: {'lr': 0.00043882740898343905, 'samples': 18262528, 'steps': 35668, 'loss/train': 1.4988353252410889}
-03/05/2022 07:23:45 - INFO - codeparrot_training - Step 35669: {'lr': 0.00043882393106990804, 'samples': 18263040, 'steps': 35669, 'loss/train': 0.7078030109405518}
-03/05/2022 07:23:46 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/05/2022 07:23:51 - INFO - codeparrot_training - Step 35670: {'lr': 0.0004388204530712959, 'samples': 18263552, 'steps': 35670, 'loss/train': 2.078819990158081}
-03/05/2022 07:23:54 - INFO - codeparrot_training - Step 35671: {'lr': 0.0004388169749876042, 'samples': 18264064, 'steps': 35671, 'loss/train': 1.9951900243759155}
-03/05/2022 07:23:55 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/05/2022 07:23:59 - INFO - codeparrot_training - Step 35672: {'lr': 0.0004388134968188344, 'samples': 18264576, 'steps': 35672, 'loss/train': 1.3254313468933105}
-03/05/2022 07:24:02 - INFO - codeparrot_training - Step 35673: {'lr': 0.00043881001856498823, 'samples': 18265088, 'steps': 35673, 'loss/train': 1.6378891468048096}
-03/05/2022 07:24:03 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/05/2022 07:24:07 - INFO - codeparrot_training - Step 35674: {'lr': 0.0004388065402260672, 'samples': 18265600, 'steps': 35674, 'loss/train': 1.0619419813156128}
-03/05/2022 07:24:11 - INFO - codeparrot_training - Step 35675: {'lr': 0.0004388030618020729, 'samples': 18266112, 'steps': 35675, 'loss/train': 1.3701406717300415}
-03/05/2022 07:24:11 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/05/2022 07:24:16 - INFO - codeparrot_training - Step 35676: {'lr': 0.0004387995832930067, 'samples': 18266624, 'steps': 35676, 'loss/train': 2.228940010070801}
-03/05/2022 07:24:19 - INFO - codeparrot_training - Step 35677: {'lr': 0.00043879610469887043, 'samples': 18267136, 'steps': 35677, 'loss/train': 0.3754729628562927}
-03/05/2022 07:24:20 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/05/2022 07:24:24 - INFO - codeparrot_training - Step 35678: {'lr': 0.00043879262601966544, 'samples': 18267648, 'steps': 35678, 'loss/train': 1.2399615049362183}
-03/05/2022 07:24:27 - INFO - codeparrot_training - Step 35679: {'lr': 0.00043878914725539356, 'samples': 18268160, 'steps': 35679, 'loss/train': 2.027195930480957}
-03/05/2022 07:24:28 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/05/2022 07:24:33 - INFO - codeparrot_training - Step 35680: {'lr': 0.00043878566840605606, 'samples': 18268672, 'steps': 35680, 'loss/train': 1.48850417137146}
-03/05/2022 07:24:36 - INFO - codeparrot_training - Step 35681: {'lr': 0.0004387821894716547, 'samples': 18269184, 'steps': 35681, 'loss/train': 3.1597840785980225}
-03/05/2022 07:24:37 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/05/2022 07:24:41 - INFO - codeparrot_training - Step 35682: {'lr': 0.000438778710452191, 'samples': 18269696, 'steps': 35682, 'loss/train': 1.5944234132766724}
-03/05/2022 07:24:44 - INFO - codeparrot_training - Step 35683: {'lr': 0.00043877523134766664, 'samples': 18270208, 'steps': 35683, 'loss/train': 0.15570977330207825}
-03/05/2022 07:24:45 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/05/2022 07:24:50 - INFO - codeparrot_training - Step 35684: {'lr': 0.0004387717521580829, 'samples': 18270720, 'steps': 35684, 'loss/train': 2.090160608291626}
-03/05/2022 07:24:53 - INFO - codeparrot_training - Step 35685: {'lr': 0.00043876827288344156, 'samples': 18271232, 'steps': 35685, 'loss/train': 0.8165982365608215}
-03/05/2022 07:24:53 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 07:24:58 - INFO - codeparrot_training - Step 35686: {'lr': 0.00043876479352374423, 'samples': 18271744, 'steps': 35686, 'loss/train': 1.2597475051879883}
-03/05/2022 07:25:01 - INFO - codeparrot_training - Step 35687: {'lr': 0.00043876131407899233, 'samples': 18272256, 'steps': 35687, 'loss/train': 1.1014387607574463}
-03/05/2022 07:25:02 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/05/2022 07:25:07 - INFO - codeparrot_training - Step 35688: {'lr': 0.00043875783454918753, 'samples': 18272768, 'steps': 35688, 'loss/train': 1.2481452226638794}
-03/05/2022 07:25:10 - INFO - codeparrot_training - Step 35689: {'lr': 0.00043875435493433135, 'samples': 18273280, 'steps': 35689, 'loss/train': 1.2008436918258667}
-03/05/2022 07:25:10 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/05/2022 07:25:15 - INFO - codeparrot_training - Step 35690: {'lr': 0.00043875087523442537, 'samples': 18273792, 'steps': 35690, 'loss/train': 2.7257983684539795}
-03/05/2022 07:25:18 - INFO - codeparrot_training - Step 35691: {'lr': 0.0004387473954494712, 'samples': 18274304, 'steps': 35691, 'loss/train': 0.4964764714241028}
-03/05/2022 07:25:18 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/05/2022 07:25:23 - INFO - codeparrot_training - Step 35692: {'lr': 0.00043874391557947027, 'samples': 18274816, 'steps': 35692, 'loss/train': 2.1800122261047363}
-03/05/2022 07:25:27 - INFO - codeparrot_training - Step 35693: {'lr': 0.0004387404356244243, 'samples': 18275328, 'steps': 35693, 'loss/train': 1.1795260906219482}
-03/05/2022 07:25:27 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/05/2022 07:25:32 - INFO - codeparrot_training - Step 35694: {'lr': 0.0004387369555843348, 'samples': 18275840, 'steps': 35694, 'loss/train': 2.9811110496520996}
-03/05/2022 07:25:35 - INFO - codeparrot_training - Step 35695: {'lr': 0.00043873347545920333, 'samples': 18276352, 'steps': 35695, 'loss/train': 1.864378571510315}
-03/05/2022 07:25:35 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/05/2022 07:25:40 - INFO - codeparrot_training - Step 35696: {'lr': 0.00043872999524903147, 'samples': 18276864, 'steps': 35696, 'loss/train': 1.05726158618927}
-03/05/2022 07:25:44 - INFO - codeparrot_training - Step 35697: {'lr': 0.00043872651495382076, 'samples': 18277376, 'steps': 35697, 'loss/train': 1.5211248397827148}
-03/05/2022 07:25:44 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/05/2022 07:25:49 - INFO - codeparrot_training - Step 35698: {'lr': 0.00043872303457357287, 'samples': 18277888, 'steps': 35698, 'loss/train': 0.8609614372253418}
-03/05/2022 07:25:52 - INFO - codeparrot_training - Step 35699: {'lr': 0.0004387195541082892, 'samples': 18278400, 'steps': 35699, 'loss/train': 2.2257816791534424}
-03/05/2022 07:25:52 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/05/2022 07:25:57 - INFO - codeparrot_training - Step 35700: {'lr': 0.0004387160735579715, 'samples': 18278912, 'steps': 35700, 'loss/train': 0.5324477553367615}
-03/05/2022 07:26:00 - INFO - codeparrot_training - Step 35701: {'lr': 0.0004387125929226212, 'samples': 18279424, 'steps': 35701, 'loss/train': 1.7016823291778564}
-03/05/2022 07:26:01 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/05/2022 07:26:06 - INFO - codeparrot_training - Step 35702: {'lr': 0.00043870911220224, 'samples': 18279936, 'steps': 35702, 'loss/train': 2.3088417053222656}
-03/05/2022 07:26:09 - INFO - codeparrot_training - Step 35703: {'lr': 0.0004387056313968293, 'samples': 18280448, 'steps': 35703, 'loss/train': 1.4109809398651123}
-03/05/2022 07:26:09 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/05/2022 07:26:14 - INFO - codeparrot_training - Step 35704: {'lr': 0.00043870215050639073, 'samples': 18280960, 'steps': 35704, 'loss/train': 0.6389027237892151}
-03/05/2022 07:26:17 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/05/2022 07:26:19 - INFO - codeparrot_training - Step 35705: {'lr': 0.00043869866953092593, 'samples': 18281472, 'steps': 35705, 'loss/train': 1.3436239957809448}
-03/05/2022 07:26:22 - INFO - codeparrot_training - Step 35706: {'lr': 0.00043869518847043643, 'samples': 18281984, 'steps': 35706, 'loss/train': 0.90720534324646}
-03/05/2022 07:26:25 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 07:26:28 - INFO - codeparrot_training - Step 35707: {'lr': 0.0004386917073249237, 'samples': 18282496, 'steps': 35707, 'loss/train': 1.7344626188278198}
-03/05/2022 07:26:31 - INFO - codeparrot_training - Step 35708: {'lr': 0.00043868822609438953, 'samples': 18283008, 'steps': 35708, 'loss/train': 1.26978600025177}
-03/05/2022 07:26:33 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/05/2022 07:26:36 - INFO - codeparrot_training - Step 35709: {'lr': 0.00043868474477883523, 'samples': 18283520, 'steps': 35709, 'loss/train': 1.5480319261550903}
-03/05/2022 07:26:39 - INFO - codeparrot_training - Step 35710: {'lr': 0.0004386812633782626, 'samples': 18284032, 'steps': 35710, 'loss/train': 2.3695502281188965}
-03/05/2022 07:26:41 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/05/2022 07:26:45 - INFO - codeparrot_training - Step 35711: {'lr': 0.00043867778189267306, 'samples': 18284544, 'steps': 35711, 'loss/train': 0.054140251129865646}
-03/05/2022 07:26:48 - INFO - codeparrot_training - Step 35712: {'lr': 0.0004386743003220682, 'samples': 18285056, 'steps': 35712, 'loss/train': 2.1086080074310303}
-03/05/2022 07:26:50 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 07:26:53 - INFO - codeparrot_training - Step 35713: {'lr': 0.0004386708186664496, 'samples': 18285568, 'steps': 35713, 'loss/train': 1.4662047624588013}
-03/05/2022 07:26:56 - INFO - codeparrot_training - Step 35714: {'lr': 0.00043866733692581896, 'samples': 18286080, 'steps': 35714, 'loss/train': 2.4179627895355225}
-03/05/2022 07:26:59 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/05/2022 07:27:01 - INFO - codeparrot_training - Step 35715: {'lr': 0.0004386638551001777, 'samples': 18286592, 'steps': 35715, 'loss/train': 1.7502223253250122}
-03/05/2022 07:27:05 - INFO - codeparrot_training - Step 35716: {'lr': 0.00043866037318952735, 'samples': 18287104, 'steps': 35716, 'loss/train': 1.7414695024490356}
-03/05/2022 07:27:07 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/05/2022 07:27:10 - INFO - codeparrot_training - Step 35717: {'lr': 0.0004386568911938695, 'samples': 18287616, 'steps': 35717, 'loss/train': 1.2179512977600098}
-03/05/2022 07:27:13 - INFO - codeparrot_training - Step 35718: {'lr': 0.0004386534091132059, 'samples': 18288128, 'steps': 35718, 'loss/train': 2.3164379596710205}
-03/05/2022 07:27:15 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 07:27:18 - INFO - codeparrot_training - Step 35719: {'lr': 0.0004386499269475379, 'samples': 18288640, 'steps': 35719, 'loss/train': 1.5551913976669312}
-03/05/2022 07:27:22 - INFO - codeparrot_training - Step 35720: {'lr': 0.00043864644469686717, 'samples': 18289152, 'steps': 35720, 'loss/train': 1.8597856760025024}
-03/05/2022 07:27:24 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/05/2022 07:27:27 - INFO - codeparrot_training - Step 35721: {'lr': 0.0004386429623611953, 'samples': 18289664, 'steps': 35721, 'loss/train': 1.6464550495147705}
-03/05/2022 07:27:30 - INFO - codeparrot_training - Step 35722: {'lr': 0.0004386394799405238, 'samples': 18290176, 'steps': 35722, 'loss/train': 0.6548097133636475}
-03/05/2022 07:27:32 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/05/2022 07:27:35 - INFO - codeparrot_training - Step 35723: {'lr': 0.00043863599743485416, 'samples': 18290688, 'steps': 35723, 'loss/train': 2.060009479522705}
-03/05/2022 07:27:38 - INFO - codeparrot_training - Step 35724: {'lr': 0.0004386325148441882, 'samples': 18291200, 'steps': 35724, 'loss/train': 1.272027850151062}
-03/05/2022 07:27:40 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/05/2022 07:27:44 - INFO - codeparrot_training - Step 35725: {'lr': 0.00043862903216852723, 'samples': 18291712, 'steps': 35725, 'loss/train': 0.8226000666618347}
-03/05/2022 07:27:47 - INFO - codeparrot_training - Step 35726: {'lr': 0.00043862554940787303, 'samples': 18292224, 'steps': 35726, 'loss/train': 1.268876314163208}
-03/05/2022 07:27:49 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/05/2022 07:27:52 - INFO - codeparrot_training - Step 35727: {'lr': 0.000438622066562227, 'samples': 18292736, 'steps': 35727, 'loss/train': 0.7049694061279297}
-03/05/2022 07:27:55 - INFO - codeparrot_training - Step 35728: {'lr': 0.0004386185836315908, 'samples': 18293248, 'steps': 35728, 'loss/train': 1.185179352760315}
-03/05/2022 07:27:57 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 07:28:00 - INFO - codeparrot_training - Step 35729: {'lr': 0.0004386151006159659, 'samples': 18293760, 'steps': 35729, 'loss/train': 3.206468105316162}
-03/05/2022 07:28:04 - INFO - codeparrot_training - Step 35730: {'lr': 0.00043861161751535406, 'samples': 18294272, 'steps': 35730, 'loss/train': 0.8603824973106384}
-03/05/2022 07:28:05 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/05/2022 07:28:09 - INFO - codeparrot_training - Step 35731: {'lr': 0.0004386081343297567, 'samples': 18294784, 'steps': 35731, 'loss/train': 2.553220272064209}
-03/05/2022 07:28:12 - INFO - codeparrot_training - Step 35732: {'lr': 0.0004386046510591754, 'samples': 18295296, 'steps': 35732, 'loss/train': 2.065293312072754}
-03/05/2022 07:28:14 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/05/2022 07:28:17 - INFO - codeparrot_training - Step 35733: {'lr': 0.0004386011677036118, 'samples': 18295808, 'steps': 35733, 'loss/train': 2.0429577827453613}
-03/05/2022 07:28:20 - INFO - codeparrot_training - Step 35734: {'lr': 0.00043859768426306737, 'samples': 18296320, 'steps': 35734, 'loss/train': 1.7138265371322632}
-03/05/2022 07:28:22 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/05/2022 07:28:26 - INFO - codeparrot_training - Step 35735: {'lr': 0.00043859420073754377, 'samples': 18296832, 'steps': 35735, 'loss/train': 1.628240704536438}
-03/05/2022 07:28:29 - INFO - codeparrot_training - Step 35736: {'lr': 0.0004385907171270425, 'samples': 18297344, 'steps': 35736, 'loss/train': 1.752416968345642}
-03/05/2022 07:28:30 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 07:28:34 - INFO - codeparrot_training - Step 35737: {'lr': 0.00043858723343156514, 'samples': 18297856, 'steps': 35737, 'loss/train': 1.7866249084472656}
-03/05/2022 07:28:37 - INFO - codeparrot_training - Step 35738: {'lr': 0.00043858374965111336, 'samples': 18298368, 'steps': 35738, 'loss/train': 0.9406494498252869}
-03/05/2022 07:28:39 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/05/2022 07:28:43 - INFO - codeparrot_training - Step 35739: {'lr': 0.00043858026578568864, 'samples': 18298880, 'steps': 35739, 'loss/train': 2.0512239933013916}
-03/05/2022 07:28:46 - INFO - codeparrot_training - Step 35740: {'lr': 0.00043857678183529256, 'samples': 18299392, 'steps': 35740, 'loss/train': 1.4369585514068604}
-03/05/2022 07:28:47 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/05/2022 07:28:51 - INFO - codeparrot_training - Step 35741: {'lr': 0.0004385732977999266, 'samples': 18299904, 'steps': 35741, 'loss/train': 1.4000229835510254}
-03/05/2022 07:28:54 - INFO - codeparrot_training - Step 35742: {'lr': 0.0004385698136795926, 'samples': 18300416, 'steps': 35742, 'loss/train': 2.050995349884033}
-03/05/2022 07:28:55 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/05/2022 07:28:59 - INFO - codeparrot_training - Step 35743: {'lr': 0.00043856632947429175, 'samples': 18300928, 'steps': 35743, 'loss/train': 0.8691539764404297}
-03/05/2022 07:29:03 - INFO - codeparrot_training - Step 35744: {'lr': 0.00043856284518402594, 'samples': 18301440, 'steps': 35744, 'loss/train': 1.6727403402328491}
-03/05/2022 07:29:04 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/05/2022 07:29:08 - INFO - codeparrot_training - Step 35745: {'lr': 0.00043855936080879667, 'samples': 18301952, 'steps': 35745, 'loss/train': 2.5223805904388428}
-03/05/2022 07:29:11 - INFO - codeparrot_training - Step 35746: {'lr': 0.0004385558763486053, 'samples': 18302464, 'steps': 35746, 'loss/train': 2.0352156162261963}
-03/05/2022 07:29:12 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/05/2022 07:29:16 - INFO - codeparrot_training - Step 35747: {'lr': 0.00043855239180345376, 'samples': 18302976, 'steps': 35747, 'loss/train': 1.8072291612625122}
-03/05/2022 07:29:19 - INFO - codeparrot_training - Step 35748: {'lr': 0.00043854890717334326, 'samples': 18303488, 'steps': 35748, 'loss/train': 1.5871286392211914}
-03/05/2022 07:29:21 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/05/2022 07:29:25 - INFO - codeparrot_training - Step 35749: {'lr': 0.00043854542245827554, 'samples': 18304000, 'steps': 35749, 'loss/train': 1.2172420024871826}
-03/05/2022 07:29:28 - INFO - codeparrot_training - Step 35750: {'lr': 0.00043854193765825223, 'samples': 18304512, 'steps': 35750, 'loss/train': 1.8148852586746216}
-03/05/2022 07:29:29 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/05/2022 07:29:33 - INFO - codeparrot_training - Step 35751: {'lr': 0.00043853845277327485, 'samples': 18305024, 'steps': 35751, 'loss/train': 2.3539435863494873}
-03/05/2022 07:29:36 - INFO - codeparrot_training - Step 35752: {'lr': 0.0004385349678033449, 'samples': 18305536, 'steps': 35752, 'loss/train': 1.6744474172592163}
-03/05/2022 07:29:37 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 07:29:42 - INFO - codeparrot_training - Step 35753: {'lr': 0.000438531482748464, 'samples': 18306048, 'steps': 35753, 'loss/train': 1.3685208559036255}
-03/05/2022 07:29:45 - INFO - codeparrot_training - Step 35754: {'lr': 0.00043852799760863375, 'samples': 18306560, 'steps': 35754, 'loss/train': 1.461417555809021}
-03/05/2022 07:29:46 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/05/2022 07:29:50 - INFO - codeparrot_training - Step 35755: {'lr': 0.0004385245123838557, 'samples': 18307072, 'steps': 35755, 'loss/train': 1.2356294393539429}
-03/05/2022 07:29:53 - INFO - codeparrot_training - Step 35756: {'lr': 0.00043852102707413144, 'samples': 18307584, 'steps': 35756, 'loss/train': 1.5272518396377563}
-03/05/2022 07:29:54 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/05/2022 07:29:58 - INFO - codeparrot_training - Step 35757: {'lr': 0.00043851754167946244, 'samples': 18308096, 'steps': 35757, 'loss/train': 1.9455064535140991}
-03/05/2022 07:30:02 - INFO - codeparrot_training - Step 35758: {'lr': 0.00043851405619985037, 'samples': 18308608, 'steps': 35758, 'loss/train': 0.501350998878479}
-03/05/2022 07:30:03 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/05/2022 07:30:07 - INFO - codeparrot_training - Step 35759: {'lr': 0.00043851057063529675, 'samples': 18309120, 'steps': 35759, 'loss/train': 1.8252297639846802}
-03/05/2022 07:30:10 - INFO - codeparrot_training - Step 35760: {'lr': 0.00043850708498580326, 'samples': 18309632, 'steps': 35760, 'loss/train': 1.6695834398269653}
-03/05/2022 07:30:11 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/05/2022 07:30:16 - INFO - codeparrot_training - Step 35761: {'lr': 0.00043850359925137126, 'samples': 18310144, 'steps': 35761, 'loss/train': 1.1442546844482422}
-03/05/2022 07:30:19 - INFO - codeparrot_training - Step 35762: {'lr': 0.0004385001134320026, 'samples': 18310656, 'steps': 35762, 'loss/train': 3.042152166366577}
-03/05/2022 07:30:22 - INFO - codeparrot_training - Step 35763: {'lr': 0.0004384966275276986, 'samples': 18311168, 'steps': 35763, 'loss/train': 1.663593053817749}
-03/05/2022 07:30:22 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 07:30:27 - INFO - codeparrot_training - Step 35764: {'lr': 0.00043849314153846094, 'samples': 18311680, 'steps': 35764, 'loss/train': 1.6578134298324585}
-03/05/2022 07:30:30 - INFO - codeparrot_training - Step 35765: {'lr': 0.0004384896554642912, 'samples': 18312192, 'steps': 35765, 'loss/train': 1.4540376663208008}
-03/05/2022 07:30:30 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/05/2022 07:30:36 - INFO - codeparrot_training - Step 35766: {'lr': 0.00043848616930519094, 'samples': 18312704, 'steps': 35766, 'loss/train': 2.3329668045043945}
-03/05/2022 07:30:38 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/05/2022 07:30:41 - INFO - codeparrot_training - Step 35767: {'lr': 0.0004384826830611617, 'samples': 18313216, 'steps': 35767, 'loss/train': 1.8129961490631104}
-03/05/2022 07:30:44 - INFO - codeparrot_training - Step 35768: {'lr': 0.00043847919673220504, 'samples': 18313728, 'steps': 35768, 'loss/train': 1.4120835065841675}
-03/05/2022 07:30:47 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/05/2022 07:30:49 - INFO - codeparrot_training - Step 35769: {'lr': 0.00043847571031832257, 'samples': 18314240, 'steps': 35769, 'loss/train': 1.8716576099395752}
-03/05/2022 07:30:53 - INFO - codeparrot_training - Step 35770: {'lr': 0.0004384722238195159, 'samples': 18314752, 'steps': 35770, 'loss/train': 1.860042691230774}
-03/05/2022 07:30:55 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 07:30:58 - INFO - codeparrot_training - Step 35771: {'lr': 0.0004384687372357865, 'samples': 18315264, 'steps': 35771, 'loss/train': 1.718870759010315}
-03/05/2022 07:31:01 - INFO - codeparrot_training - Step 35772: {'lr': 0.000438465250567136, 'samples': 18315776, 'steps': 35772, 'loss/train': 1.545990228652954}
-03/05/2022 07:31:03 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/05/2022 07:31:06 - INFO - codeparrot_training - Step 35773: {'lr': 0.00043846176381356607, 'samples': 18316288, 'steps': 35773, 'loss/train': 1.1574318408966064}
-03/05/2022 07:31:09 - INFO - codeparrot_training - Step 35774: {'lr': 0.000438458276975078, 'samples': 18316800, 'steps': 35774, 'loss/train': 1.547105312347412}
-03/05/2022 07:31:12 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/05/2022 07:31:15 - INFO - codeparrot_training - Step 35775: {'lr': 0.0004384547900516737, 'samples': 18317312, 'steps': 35775, 'loss/train': 1.7088549137115479}
-03/05/2022 07:31:18 - INFO - codeparrot_training - Step 35776: {'lr': 0.00043845130304335454, 'samples': 18317824, 'steps': 35776, 'loss/train': 2.0230493545532227}
-03/05/2022 07:31:20 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/05/2022 07:31:23 - INFO - codeparrot_training - Step 35777: {'lr': 0.00043844781595012204, 'samples': 18318336, 'steps': 35777, 'loss/train': 0.9689851403236389}
-03/05/2022 07:31:26 - INFO - codeparrot_training - Step 35778: {'lr': 0.0004384443287719779, 'samples': 18318848, 'steps': 35778, 'loss/train': 2.340423107147217}
-03/05/2022 07:31:28 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/05/2022 07:31:31 - INFO - codeparrot_training - Step 35779: {'lr': 0.0004384408415089237, 'samples': 18319360, 'steps': 35779, 'loss/train': 2.063995361328125}
-03/05/2022 07:31:35 - INFO - codeparrot_training - Step 35780: {'lr': 0.000438437354160961, 'samples': 18319872, 'steps': 35780, 'loss/train': 0.8279281854629517}
-03/05/2022 07:31:37 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/05/2022 07:31:40 - INFO - codeparrot_training - Step 35781: {'lr': 0.00043843386672809127, 'samples': 18320384, 'steps': 35781, 'loss/train': 1.667568564414978}
-03/05/2022 07:31:43 - INFO - codeparrot_training - Step 35782: {'lr': 0.00043843037921031616, 'samples': 18320896, 'steps': 35782, 'loss/train': 1.1954513788223267}
-03/05/2022 07:31:45 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/05/2022 07:31:49 - INFO - codeparrot_training - Step 35783: {'lr': 0.00043842689160763723, 'samples': 18321408, 'steps': 35783, 'loss/train': 2.2057087421417236}
-03/05/2022 07:31:52 - INFO - codeparrot_training - Step 35784: {'lr': 0.00043842340392005605, 'samples': 18321920, 'steps': 35784, 'loss/train': 0.9788277745246887}
-03/05/2022 07:31:54 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 07:31:57 - INFO - codeparrot_training - Step 35785: {'lr': 0.00043841991614757415, 'samples': 18322432, 'steps': 35785, 'loss/train': 1.2413392066955566}
-03/05/2022 07:32:00 - INFO - codeparrot_training - Step 35786: {'lr': 0.00043841642829019325, 'samples': 18322944, 'steps': 35786, 'loss/train': 1.8858823776245117}
-03/05/2022 07:32:02 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/05/2022 07:32:05 - INFO - codeparrot_training - Step 35787: {'lr': 0.00043841294034791466, 'samples': 18323456, 'steps': 35787, 'loss/train': 1.3625431060791016}
-03/05/2022 07:32:08 - INFO - codeparrot_training - Step 35788: {'lr': 0.0004384094523207403, 'samples': 18323968, 'steps': 35788, 'loss/train': 2.3667798042297363}
-03/05/2022 07:32:10 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/05/2022 07:32:14 - INFO - codeparrot_training - Step 35789: {'lr': 0.0004384059642086714, 'samples': 18324480, 'steps': 35789, 'loss/train': 2.4646449089050293}
-03/05/2022 07:32:17 - INFO - codeparrot_training - Step 35790: {'lr': 0.00043840247601170966, 'samples': 18324992, 'steps': 35790, 'loss/train': 1.4158660173416138}
-03/05/2022 07:32:19 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/05/2022 07:32:22 - INFO - codeparrot_training - Step 35791: {'lr': 0.0004383989877298568, 'samples': 18325504, 'steps': 35791, 'loss/train': 1.6519218683242798}
-03/05/2022 07:32:25 - INFO - codeparrot_training - Step 35792: {'lr': 0.0004383954993631142, 'samples': 18326016, 'steps': 35792, 'loss/train': 2.056934118270874}
-03/05/2022 07:32:27 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/05/2022 07:32:31 - INFO - codeparrot_training - Step 35793: {'lr': 0.0004383920109114835, 'samples': 18326528, 'steps': 35793, 'loss/train': 1.6480445861816406}
-03/05/2022 07:32:34 - INFO - codeparrot_training - Step 35794: {'lr': 0.00043838852237496626, 'samples': 18327040, 'steps': 35794, 'loss/train': 1.8572678565979004}
-03/05/2022 07:32:35 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/05/2022 07:32:39 - INFO - codeparrot_training - Step 35795: {'lr': 0.000438385033753564, 'samples': 18327552, 'steps': 35795, 'loss/train': 1.688754677772522}
-03/05/2022 07:32:42 - INFO - codeparrot_training - Step 35796: {'lr': 0.00043838154504727847, 'samples': 18328064, 'steps': 35796, 'loss/train': 1.3485699892044067}
-03/05/2022 07:32:44 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/05/2022 07:32:47 - INFO - codeparrot_training - Step 35797: {'lr': 0.00043837805625611105, 'samples': 18328576, 'steps': 35797, 'loss/train': 1.211952567100525}
-03/05/2022 07:32:51 - INFO - codeparrot_training - Step 35798: {'lr': 0.0004383745673800634, 'samples': 18329088, 'steps': 35798, 'loss/train': 2.014723300933838}
-03/05/2022 07:32:52 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/05/2022 07:32:56 - INFO - codeparrot_training - Step 35799: {'lr': 0.000438371078419137, 'samples': 18329600, 'steps': 35799, 'loss/train': 1.5385650396347046}
-03/05/2022 07:32:59 - INFO - codeparrot_training - Step 35800: {'lr': 0.00043836758937333366, 'samples': 18330112, 'steps': 35800, 'loss/train': 1.8218685388565063}
-03/05/2022 07:33:01 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 07:33:04 - INFO - codeparrot_training - Step 35801: {'lr': 0.0004383641002426547, 'samples': 18330624, 'steps': 35801, 'loss/train': 2.1332199573516846}
-03/05/2022 07:33:07 - INFO - codeparrot_training - Step 35802: {'lr': 0.0004383606110271018, 'samples': 18331136, 'steps': 35802, 'loss/train': 1.9530038833618164}
-03/05/2022 07:33:09 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/05/2022 07:33:13 - INFO - codeparrot_training - Step 35803: {'lr': 0.00043835712172667643, 'samples': 18331648, 'steps': 35803, 'loss/train': 1.552128791809082}
-03/05/2022 07:33:16 - INFO - codeparrot_training - Step 35804: {'lr': 0.00043835363234138037, 'samples': 18332160, 'steps': 35804, 'loss/train': 1.414260983467102}
-03/05/2022 07:33:17 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/05/2022 07:33:22 - INFO - codeparrot_training - Step 35805: {'lr': 0.00043835014287121497, 'samples': 18332672, 'steps': 35805, 'loss/train': 1.9430971145629883}
-03/05/2022 07:33:25 - INFO - codeparrot_training - Step 35806: {'lr': 0.00043834665331618196, 'samples': 18333184, 'steps': 35806, 'loss/train': 2.01493763923645}
-03/05/2022 07:33:28 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/05/2022 07:33:30 - INFO - codeparrot_training - Step 35807: {'lr': 0.00043834316367628287, 'samples': 18333696, 'steps': 35807, 'loss/train': 2.5154149532318115}
-03/05/2022 07:33:33 - INFO - codeparrot_training - Step 35808: {'lr': 0.0004383396739515192, 'samples': 18334208, 'steps': 35808, 'loss/train': 1.9666022062301636}
-03/05/2022 07:33:36 - INFO - codeparrot_training - Step 35809: {'lr': 0.00043833618414189265, 'samples': 18334720, 'steps': 35809, 'loss/train': 2.1317696571350098}
-03/05/2022 07:33:36 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 07:33:42 - INFO - codeparrot_training - Step 35810: {'lr': 0.0004383326942474046, 'samples': 18335232, 'steps': 35810, 'loss/train': 1.656234622001648}
-03/05/2022 07:33:45 - INFO - codeparrot_training - Step 35811: {'lr': 0.0004383292042680569, 'samples': 18335744, 'steps': 35811, 'loss/train': 1.6465381383895874}
-03/05/2022 07:33:45 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/05/2022 07:33:50 - INFO - codeparrot_training - Step 35812: {'lr': 0.0004383257142038509, 'samples': 18336256, 'steps': 35812, 'loss/train': 0.8864298462867737}
-03/05/2022 07:33:53 - INFO - codeparrot_training - Step 35813: {'lr': 0.0004383222240547882, 'samples': 18336768, 'steps': 35813, 'loss/train': 1.8521597385406494}
-03/05/2022 07:33:54 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 07:33:59 - INFO - codeparrot_training - Step 35814: {'lr': 0.00043831873382087043, 'samples': 18337280, 'steps': 35814, 'loss/train': 1.9385435581207275}
-03/05/2022 07:34:02 - INFO - codeparrot_training - Step 35815: {'lr': 0.0004383152435020992, 'samples': 18337792, 'steps': 35815, 'loss/train': 0.9484081268310547}
-03/05/2022 07:34:02 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/05/2022 07:34:08 - INFO - codeparrot_training - Step 35816: {'lr': 0.0004383117530984759, 'samples': 18338304, 'steps': 35816, 'loss/train': 2.141054630279541}
-03/05/2022 07:34:11 - INFO - codeparrot_training - Step 35817: {'lr': 0.0004383082626100024, 'samples': 18338816, 'steps': 35817, 'loss/train': 1.7957396507263184}
-03/05/2022 07:34:13 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/05/2022 07:34:16 - INFO - codeparrot_training - Step 35818: {'lr': 0.00043830477203668, 'samples': 18339328, 'steps': 35818, 'loss/train': 1.8486052751541138}
-03/05/2022 07:34:19 - INFO - codeparrot_training - Step 35819: {'lr': 0.0004383012813785104, 'samples': 18339840, 'steps': 35819, 'loss/train': 1.1866755485534668}
-03/05/2022 07:34:21 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 07:34:24 - INFO - codeparrot_training - Step 35820: {'lr': 0.00043829779063549515, 'samples': 18340352, 'steps': 35820, 'loss/train': 1.4330103397369385}
-03/05/2022 07:34:28 - INFO - codeparrot_training - Step 35821: {'lr': 0.0004382942998076358, 'samples': 18340864, 'steps': 35821, 'loss/train': 1.8692923784255981}
-03/05/2022 07:34:30 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/05/2022 07:34:33 - INFO - codeparrot_training - Step 35822: {'lr': 0.000438290808894934, 'samples': 18341376, 'steps': 35822, 'loss/train': 1.7344541549682617}
-03/05/2022 07:34:36 - INFO - codeparrot_training - Step 35823: {'lr': 0.0004382873178973912, 'samples': 18341888, 'steps': 35823, 'loss/train': 1.2696970701217651}
-03/05/2022 07:34:38 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/05/2022 07:34:41 - INFO - codeparrot_training - Step 35824: {'lr': 0.00043828382681500907, 'samples': 18342400, 'steps': 35824, 'loss/train': 1.3480753898620605}
-03/05/2022 07:34:45 - INFO - codeparrot_training - Step 35825: {'lr': 0.0004382803356477891, 'samples': 18342912, 'steps': 35825, 'loss/train': 1.7241772413253784}
-03/05/2022 07:34:46 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/05/2022 07:34:50 - INFO - codeparrot_training - Step 35826: {'lr': 0.000438276844395733, 'samples': 18343424, 'steps': 35826, 'loss/train': 1.0532060861587524}
-03/05/2022 07:34:53 - INFO - codeparrot_training - Step 35827: {'lr': 0.0004382733530588422, 'samples': 18343936, 'steps': 35827, 'loss/train': 1.5139710903167725}
-03/05/2022 07:34:55 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/05/2022 07:34:58 - INFO - codeparrot_training - Step 35828: {'lr': 0.00043826986163711835, 'samples': 18344448, 'steps': 35828, 'loss/train': 0.5515784621238708}
-03/05/2022 07:35:02 - INFO - codeparrot_training - Step 35829: {'lr': 0.000438266370130563, 'samples': 18344960, 'steps': 35829, 'loss/train': 2.2003138065338135}
-03/05/2022 07:35:03 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/05/2022 07:35:07 - INFO - codeparrot_training - Step 35830: {'lr': 0.0004382628785391778, 'samples': 18345472, 'steps': 35830, 'loss/train': 1.5054694414138794}
-03/05/2022 07:35:10 - INFO - codeparrot_training - Step 35831: {'lr': 0.00043825938686296417, 'samples': 18345984, 'steps': 35831, 'loss/train': 0.11516143381595612}
-03/05/2022 07:35:12 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/05/2022 07:35:15 - INFO - codeparrot_training - Step 35832: {'lr': 0.00043825589510192376, 'samples': 18346496, 'steps': 35832, 'loss/train': 6.5704755783081055}
-03/05/2022 07:35:18 - INFO - codeparrot_training - Step 35833: {'lr': 0.0004382524032560582, 'samples': 18347008, 'steps': 35833, 'loss/train': 1.3933088779449463}
-03/05/2022 07:35:20 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/05/2022 07:35:24 - INFO - codeparrot_training - Step 35834: {'lr': 0.000438248911325369, 'samples': 18347520, 'steps': 35834, 'loss/train': 1.6931428909301758}
-03/05/2022 07:35:27 - INFO - codeparrot_training - Step 35835: {'lr': 0.00043824541930985775, 'samples': 18348032, 'steps': 35835, 'loss/train': 1.0527546405792236}
-03/05/2022 07:35:28 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 07:35:32 - INFO - codeparrot_training - Step 35836: {'lr': 0.0004382419272095259, 'samples': 18348544, 'steps': 35836, 'loss/train': 1.5860486030578613}
-03/05/2022 07:35:35 - INFO - codeparrot_training - Step 35837: {'lr': 0.00043823843502437533, 'samples': 18349056, 'steps': 35837, 'loss/train': 2.004103183746338}
-03/05/2022 07:35:37 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/05/2022 07:35:40 - INFO - codeparrot_training - Step 35838: {'lr': 0.00043823494275440733, 'samples': 18349568, 'steps': 35838, 'loss/train': 2.264207124710083}
-03/05/2022 07:35:44 - INFO - codeparrot_training - Step 35839: {'lr': 0.0004382314503996236, 'samples': 18350080, 'steps': 35839, 'loss/train': 1.4864553213119507}
-03/05/2022 07:35:45 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 07:35:49 - INFO - codeparrot_training - Step 35840: {'lr': 0.0004382279579600256, 'samples': 18350592, 'steps': 35840, 'loss/train': 1.1642504930496216}
-03/05/2022 07:35:52 - INFO - codeparrot_training - Step 35841: {'lr': 0.0004382244654356151, 'samples': 18351104, 'steps': 35841, 'loss/train': 0.34490540623664856}
-03/05/2022 07:35:53 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/05/2022 07:35:57 - INFO - codeparrot_training - Step 35842: {'lr': 0.0004382209728263935, 'samples': 18351616, 'steps': 35842, 'loss/train': 3.0427041053771973}
-03/05/2022 07:36:01 - INFO - codeparrot_training - Step 35843: {'lr': 0.0004382174801323624, 'samples': 18352128, 'steps': 35843, 'loss/train': 1.7474128007888794}
-03/05/2022 07:36:02 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/05/2022 07:36:06 - INFO - codeparrot_training - Step 35844: {'lr': 0.00043821398735352344, 'samples': 18352640, 'steps': 35844, 'loss/train': 1.0553959608078003}
-03/05/2022 07:36:09 - INFO - codeparrot_training - Step 35845: {'lr': 0.0004382104944898782, 'samples': 18353152, 'steps': 35845, 'loss/train': 1.8082078695297241}
-03/05/2022 07:36:11 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/05/2022 07:36:14 - INFO - codeparrot_training - Step 35846: {'lr': 0.00043820700154142825, 'samples': 18353664, 'steps': 35846, 'loss/train': 1.3046081066131592}
-03/05/2022 07:36:17 - INFO - codeparrot_training - Step 35847: {'lr': 0.00043820350850817504, 'samples': 18354176, 'steps': 35847, 'loss/train': 0.22505730390548706}
-03/05/2022 07:36:19 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/05/2022 07:36:23 - INFO - codeparrot_training - Step 35848: {'lr': 0.00043820001539012025, 'samples': 18354688, 'steps': 35848, 'loss/train': 0.8354507684707642}
-03/05/2022 07:36:26 - INFO - codeparrot_training - Step 35849: {'lr': 0.00043819652218726545, 'samples': 18355200, 'steps': 35849, 'loss/train': 1.2859764099121094}
-03/05/2022 07:36:27 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 07:36:31 - INFO - codeparrot_training - Step 35850: {'lr': 0.0004381930288996122, 'samples': 18355712, 'steps': 35850, 'loss/train': 1.8417073488235474}
-03/05/2022 07:36:34 - INFO - codeparrot_training - Step 35851: {'lr': 0.0004381895355271621, 'samples': 18356224, 'steps': 35851, 'loss/train': 2.1338348388671875}
-03/05/2022 07:36:36 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/05/2022 07:36:39 - INFO - codeparrot_training - Step 35852: {'lr': 0.00043818604206991664, 'samples': 18356736, 'steps': 35852, 'loss/train': 1.8656824827194214}
-03/05/2022 07:36:43 - INFO - codeparrot_training - Step 35853: {'lr': 0.0004381825485278775, 'samples': 18357248, 'steps': 35853, 'loss/train': 0.5284648537635803}
-03/05/2022 07:36:44 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/05/2022 07:36:48 - INFO - codeparrot_training - Step 35854: {'lr': 0.00043817905490104613, 'samples': 18357760, 'steps': 35854, 'loss/train': 1.9920260906219482}
-03/05/2022 07:36:51 - INFO - codeparrot_training - Step 35855: {'lr': 0.00043817556118942426, 'samples': 18358272, 'steps': 35855, 'loss/train': 2.0864834785461426}
-03/05/2022 07:36:53 - INFO - codeparrot_training - Skipping example with length 1023 (seq_length=1024)
-03/05/2022 07:36:56 - INFO - codeparrot_training - Step 35856: {'lr': 0.0004381720673930134, 'samples': 18358784, 'steps': 35856, 'loss/train': 1.747823715209961}
-03/05/2022 07:37:00 - INFO - codeparrot_training - Step 35857: {'lr': 0.00043816857351181503, 'samples': 18359296, 'steps': 35857, 'loss/train': 0.8852327466011047}
-03/05/2022 07:37:01 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/05/2022 07:37:05 - INFO - codeparrot_training - Step 35858: {'lr': 0.0004381650795458309, 'samples': 18359808, 'steps': 35858, 'loss/train': 1.6517338752746582}
-03/05/2022 07:37:08 - INFO - codeparrot_training - Step 35859: {'lr': 0.0004381615854950625, 'samples': 18360320, 'steps': 35859, 'loss/train': 1.780535101890564}
-03/05/2022 07:37:10 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 07:37:13 - INFO - codeparrot_training - Step 35860: {'lr': 0.0004381580913595113, 'samples': 18360832, 'steps': 35860, 'loss/train': 1.717444658279419}
-03/05/2022 07:37:16 - INFO - codeparrot_training - Step 35861: {'lr': 0.000438154597139179, 'samples': 18361344, 'steps': 35861, 'loss/train': 1.301609992980957}
-03/05/2022 07:37:18 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/05/2022 07:37:22 - INFO - codeparrot_training - Step 35862: {'lr': 0.0004381511028340671, 'samples': 18361856, 'steps': 35862, 'loss/train': 1.6359411478042603}
-03/05/2022 07:37:25 - INFO - codeparrot_training - Step 35863: {'lr': 0.0004381476084441773, 'samples': 18362368, 'steps': 35863, 'loss/train': 1.61943519115448}
-03/05/2022 07:37:27 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/05/2022 07:37:30 - INFO - codeparrot_training - Step 35864: {'lr': 0.00043814411396951103, 'samples': 18362880, 'steps': 35864, 'loss/train': 2.1041910648345947}
-03/05/2022 07:37:34 - INFO - codeparrot_training - Step 35865: {'lr': 0.00043814061941007, 'samples': 18363392, 'steps': 35865, 'loss/train': 2.032467842102051}
-03/05/2022 07:37:36 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/05/2022 07:37:39 - INFO - codeparrot_training - Step 35866: {'lr': 0.00043813712476585564, 'samples': 18363904, 'steps': 35866, 'loss/train': 2.0797317028045654}
-03/05/2022 07:37:42 - INFO - codeparrot_training - Step 35867: {'lr': 0.00043813363003686963, 'samples': 18364416, 'steps': 35867, 'loss/train': 2.0738637447357178}
-03/05/2022 07:37:44 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/05/2022 07:37:47 - INFO - codeparrot_training - Step 35868: {'lr': 0.00043813013522311353, 'samples': 18364928, 'steps': 35868, 'loss/train': 2.203000783920288}
-03/05/2022 07:37:51 - INFO - codeparrot_training - Step 35869: {'lr': 0.0004381266403245888, 'samples': 18365440, 'steps': 35869, 'loss/train': 1.9345464706420898}
-03/05/2022 07:37:53 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/05/2022 07:37:56 - INFO - codeparrot_training - Step 35870: {'lr': 0.00043812314534129716, 'samples': 18365952, 'steps': 35870, 'loss/train': 2.2334775924682617}
-03/05/2022 07:37:59 - INFO - codeparrot_training - Step 35871: {'lr': 0.0004381196502732402, 'samples': 18366464, 'steps': 35871, 'loss/train': 1.7445776462554932}
-03/05/2022 07:38:01 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/05/2022 07:38:04 - INFO - codeparrot_training - Step 35872: {'lr': 0.00043811615512041934, 'samples': 18366976, 'steps': 35872, 'loss/train': 1.575972080230713}
-03/05/2022 07:38:07 - INFO - codeparrot_training - Step 35873: {'lr': 0.00043811265988283625, 'samples': 18367488, 'steps': 35873, 'loss/train': 1.6200170516967773}
-03/05/2022 07:38:09 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/05/2022 07:38:13 - INFO - codeparrot_training - Step 35874: {'lr': 0.00043810916456049257, 'samples': 18368000, 'steps': 35874, 'loss/train': 1.4898769855499268}
-03/05/2022 07:38:16 - INFO - codeparrot_training - Step 35875: {'lr': 0.00043810566915338965, 'samples': 18368512, 'steps': 35875, 'loss/train': 2.4805665016174316}
-03/05/2022 07:38:19 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 07:38:21 - INFO - codeparrot_training - Step 35876: {'lr': 0.0004381021736615294, 'samples': 18369024, 'steps': 35876, 'loss/train': 1.5496997833251953}
-03/05/2022 07:38:24 - INFO - codeparrot_training - Step 35877: {'lr': 0.0004380986780849131, 'samples': 18369536, 'steps': 35877, 'loss/train': 1.1166820526123047}
-03/05/2022 07:38:27 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/05/2022 07:38:30 - INFO - codeparrot_training - Step 35878: {'lr': 0.0004380951824235425, 'samples': 18370048, 'steps': 35878, 'loss/train': 2.17287015914917}
-03/05/2022 07:38:33 - INFO - codeparrot_training - Step 35879: {'lr': 0.00043809168667741907, 'samples': 18370560, 'steps': 35879, 'loss/train': 1.0047917366027832}
-03/05/2022 07:38:35 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/05/2022 07:38:38 - INFO - codeparrot_training - Step 35880: {'lr': 0.0004380881908465445, 'samples': 18371072, 'steps': 35880, 'loss/train': 1.731549859046936}
-03/05/2022 07:38:41 - INFO - codeparrot_training - Step 35881: {'lr': 0.0004380846949309202, 'samples': 18371584, 'steps': 35881, 'loss/train': 1.6601622104644775}
-03/05/2022 07:38:44 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/05/2022 07:38:47 - INFO - codeparrot_training - Step 35882: {'lr': 0.00043808119893054787, 'samples': 18372096, 'steps': 35882, 'loss/train': 2.103219985961914}
-03/05/2022 07:38:50 - INFO - codeparrot_training - Step 35883: {'lr': 0.0004380777028454291, 'samples': 18372608, 'steps': 35883, 'loss/train': 1.5138561725616455}
-03/05/2022 07:38:52 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/05/2022 07:38:55 - INFO - codeparrot_training - Step 35884: {'lr': 0.0004380742066755654, 'samples': 18373120, 'steps': 35884, 'loss/train': 1.8518624305725098}
-03/05/2022 07:38:58 - INFO - codeparrot_training - Step 35885: {'lr': 0.0004380707104209583, 'samples': 18373632, 'steps': 35885, 'loss/train': 2.2512545585632324}
-03/05/2022 07:39:01 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/05/2022 07:39:04 - INFO - codeparrot_training - Step 35886: {'lr': 0.0004380672140816095, 'samples': 18374144, 'steps': 35886, 'loss/train': 1.4925892353057861}
-03/05/2022 07:39:07 - INFO - codeparrot_training - Step 35887: {'lr': 0.0004380637176575205, 'samples': 18374656, 'steps': 35887, 'loss/train': 3.4840660095214844}
-03/05/2022 07:39:10 - INFO - codeparrot_training - Step 35888: {'lr': 0.00043806022114869294, 'samples': 18375168, 'steps': 35888, 'loss/train': 1.579998254776001}
-03/05/2022 07:39:12 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/05/2022 07:39:16 - INFO - codeparrot_training - Step 35889: {'lr': 0.0004380567245551282, 'samples': 18375680, 'steps': 35889, 'loss/train': 2.1771109104156494}
-03/05/2022 07:39:19 - INFO - codeparrot_training - Step 35890: {'lr': 0.0004380532278768282, 'samples': 18376192, 'steps': 35890, 'loss/train': 1.5604552030563354}
-03/05/2022 07:39:20 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/05/2022 07:39:24 - INFO - codeparrot_training - Step 35891: {'lr': 0.0004380497311137942, 'samples': 18376704, 'steps': 35891, 'loss/train': 1.2612354755401611}
-03/05/2022 07:39:27 - INFO - codeparrot_training - Step 35892: {'lr': 0.00043804623426602784, 'samples': 18377216, 'steps': 35892, 'loss/train': 0.9987308382987976}
-03/05/2022 07:39:33 - INFO - codeparrot_training - Step 35893: {'lr': 0.00043804273733353085, 'samples': 18377728, 'steps': 35893, 'loss/train': 1.0788992643356323}
-03/05/2022 07:39:36 - INFO - codeparrot_training - Step 35894: {'lr': 0.0004380392403163047, 'samples': 18378240, 'steps': 35894, 'loss/train': 1.6755306720733643}
-03/05/2022 07:39:36 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/05/2022 07:39:41 - INFO - codeparrot_training - Step 35895: {'lr': 0.00043803574321435093, 'samples': 18378752, 'steps': 35895, 'loss/train': 1.776163101196289}
-03/05/2022 07:39:44 - INFO - codeparrot_training - Step 35896: {'lr': 0.00043803224602767115, 'samples': 18379264, 'steps': 35896, 'loss/train': 1.473827600479126}
-03/05/2022 07:39:47 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/05/2022 07:39:50 - INFO - codeparrot_training - Step 35897: {'lr': 0.000438028748756267, 'samples': 18379776, 'steps': 35897, 'loss/train': 1.7761696577072144}
-03/05/2022 07:39:53 - INFO - codeparrot_training - Step 35898: {'lr': 0.00043802525140013994, 'samples': 18380288, 'steps': 35898, 'loss/train': 1.7302769422531128}
-03/05/2022 07:39:57 - INFO - codeparrot_training - Step 35899: {'lr': 0.00043802175395929156, 'samples': 18380800, 'steps': 35899, 'loss/train': 6.198789596557617}
-03/05/2022 07:39:59 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/05/2022 07:40:02 - INFO - codeparrot_training - Step 35900: {'lr': 0.00043801825643372363, 'samples': 18381312, 'steps': 35900, 'loss/train': 2.493941068649292}
-03/05/2022 07:40:05 - INFO - codeparrot_training - Step 35901: {'lr': 0.00043801475882343743, 'samples': 18381824, 'steps': 35901, 'loss/train': 0.8849452137947083}
-03/05/2022 07:40:07 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/05/2022 07:40:10 - INFO - codeparrot_training - Step 35902: {'lr': 0.0004380112611284347, 'samples': 18382336, 'steps': 35902, 'loss/train': 1.8997044563293457}
-03/05/2022 07:40:13 - INFO - codeparrot_training - Step 35903: {'lr': 0.00043800776334871705, 'samples': 18382848, 'steps': 35903, 'loss/train': 0.8492888808250427}
-03/05/2022 07:40:16 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/05/2022 07:40:19 - INFO - codeparrot_training - Step 35904: {'lr': 0.000438004265484286, 'samples': 18383360, 'steps': 35904, 'loss/train': 2.1476662158966064}
-03/05/2022 07:40:22 - INFO - codeparrot_training - Step 35905: {'lr': 0.0004380007675351431, 'samples': 18383872, 'steps': 35905, 'loss/train': 2.3244035243988037}
-03/05/2022 07:40:24 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/05/2022 07:40:27 - INFO - codeparrot_training - Step 35906: {'lr': 0.00043799726950128997, 'samples': 18384384, 'steps': 35906, 'loss/train': 1.8167943954467773}
-03/05/2022 07:40:31 - INFO - codeparrot_training - Step 35907: {'lr': 0.0004379937713827282, 'samples': 18384896, 'steps': 35907, 'loss/train': 3.1521358489990234}
-03/05/2022 07:40:33 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/05/2022 07:40:36 - INFO - codeparrot_training - Step 35908: {'lr': 0.0004379902731794593, 'samples': 18385408, 'steps': 35908, 'loss/train': 1.706661581993103}
-03/05/2022 07:40:39 - INFO - codeparrot_training - Step 35909: {'lr': 0.00043798677489148487, 'samples': 18385920, 'steps': 35909, 'loss/train': 1.45589017868042}
-03/05/2022 07:40:41 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/05/2022 07:40:44 - INFO - codeparrot_training - Step 35910: {'lr': 0.0004379832765188065, 'samples': 18386432, 'steps': 35910, 'loss/train': 0.8694603443145752}
-03/05/2022 07:40:47 - INFO - codeparrot_training - Step 35911: {'lr': 0.00043797977806142585, 'samples': 18386944, 'steps': 35911, 'loss/train': 2.3876607418060303}
-03/05/2022 07:40:50 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 07:40:53 - INFO - codeparrot_training - Step 35912: {'lr': 0.0004379762795193443, 'samples': 18387456, 'steps': 35912, 'loss/train': 1.6392831802368164}
-03/05/2022 07:40:56 - INFO - codeparrot_training - Step 35913: {'lr': 0.0004379727808925636, 'samples': 18387968, 'steps': 35913, 'loss/train': 1.2126848697662354}
-03/05/2022 07:41:00 - INFO - codeparrot_training - Step 35914: {'lr': 0.00043796928218108527, 'samples': 18388480, 'steps': 35914, 'loss/train': 2.2581064701080322}
-03/05/2022 07:41:01 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/05/2022 07:41:05 - INFO - codeparrot_training - Step 35915: {'lr': 0.0004379657833849109, 'samples': 18388992, 'steps': 35915, 'loss/train': 0.9591162800788879}
-03/05/2022 07:41:08 - INFO - codeparrot_training - Step 35916: {'lr': 0.000437962284504042, 'samples': 18389504, 'steps': 35916, 'loss/train': 0.829038679599762}
-03/05/2022 07:41:09 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/05/2022 07:41:13 - INFO - codeparrot_training - Step 35917: {'lr': 0.00043795878553848025, 'samples': 18390016, 'steps': 35917, 'loss/train': 2.1771657466888428}
-03/05/2022 07:41:16 - INFO - codeparrot_training - Step 35918: {'lr': 0.0004379552864882271, 'samples': 18390528, 'steps': 35918, 'loss/train': 1.8311961889266968}
-03/05/2022 07:41:18 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/05/2022 07:41:22 - INFO - codeparrot_training - Step 35919: {'lr': 0.00043795178735328425, 'samples': 18391040, 'steps': 35919, 'loss/train': 1.9642060995101929}
-03/05/2022 07:41:25 - INFO - codeparrot_training - Step 35920: {'lr': 0.0004379482881336532, 'samples': 18391552, 'steps': 35920, 'loss/train': 1.6833932399749756}
-03/05/2022 07:41:26 - INFO - codeparrot_training - Skipping example with length 433 (seq_length=1024)
-03/05/2022 07:41:30 - INFO - codeparrot_training - Step 35921: {'lr': 0.0004379447888293355, 'samples': 18392064, 'steps': 35921, 'loss/train': 1.6987532377243042}
-03/05/2022 07:41:33 - INFO - codeparrot_training - Step 35922: {'lr': 0.0004379412894403328, 'samples': 18392576, 'steps': 35922, 'loss/train': 2.100895643234253}
-03/05/2022 07:41:34 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/05/2022 07:41:39 - INFO - codeparrot_training - Step 35923: {'lr': 0.0004379377899666468, 'samples': 18393088, 'steps': 35923, 'loss/train': 1.6641383171081543}
-03/05/2022 07:41:42 - INFO - codeparrot_training - Step 35924: {'lr': 0.0004379342904082788, 'samples': 18393600, 'steps': 35924, 'loss/train': 2.1020548343658447}
-03/05/2022 07:41:43 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/05/2022 07:41:47 - INFO - codeparrot_training - Step 35925: {'lr': 0.00043793079076523053, 'samples': 18394112, 'steps': 35925, 'loss/train': 0.6086430549621582}
-03/05/2022 07:41:50 - INFO - codeparrot_training - Step 35926: {'lr': 0.0004379272910375035, 'samples': 18394624, 'steps': 35926, 'loss/train': 0.35656875371932983}
-03/05/2022 07:41:52 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/05/2022 07:41:56 - INFO - codeparrot_training - Step 35927: {'lr': 0.0004379237912250994, 'samples': 18395136, 'steps': 35927, 'loss/train': 1.3075683116912842}
-03/05/2022 07:41:59 - INFO - codeparrot_training - Step 35928: {'lr': 0.0004379202913280197, 'samples': 18395648, 'steps': 35928, 'loss/train': 1.9781527519226074}
-03/05/2022 07:42:01 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/05/2022 07:42:04 - INFO - codeparrot_training - Step 35929: {'lr': 0.0004379167913462661, 'samples': 18396160, 'steps': 35929, 'loss/train': 2.9559319019317627}
-03/05/2022 07:42:07 - INFO - codeparrot_training - Step 35930: {'lr': 0.00043791329127984004, 'samples': 18396672, 'steps': 35930, 'loss/train': 2.3536975383758545}
-03/05/2022 07:42:09 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 07:42:12 - INFO - codeparrot_training - Step 35931: {'lr': 0.0004379097911287431, 'samples': 18397184, 'steps': 35931, 'loss/train': 1.2417542934417725}
-03/05/2022 07:42:16 - INFO - codeparrot_training - Step 35932: {'lr': 0.000437906290892977, 'samples': 18397696, 'steps': 35932, 'loss/train': 2.0973689556121826}
-03/05/2022 07:42:17 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/05/2022 07:42:21 - INFO - codeparrot_training - Step 35933: {'lr': 0.00043790279057254314, 'samples': 18398208, 'steps': 35933, 'loss/train': 1.8377655744552612}
-03/05/2022 07:42:24 - INFO - codeparrot_training - Step 35934: {'lr': 0.00043789929016744324, 'samples': 18398720, 'steps': 35934, 'loss/train': 1.5965042114257812}
-03/05/2022 07:42:26 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 07:42:29 - INFO - codeparrot_training - Step 35935: {'lr': 0.0004378957896776787, 'samples': 18399232, 'steps': 35935, 'loss/train': 2.51243257522583}
-03/05/2022 07:42:32 - INFO - codeparrot_training - Step 35936: {'lr': 0.0004378922891032514, 'samples': 18399744, 'steps': 35936, 'loss/train': 1.9373443126678467}
-03/05/2022 07:42:34 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/05/2022 07:42:38 - INFO - codeparrot_training - Step 35937: {'lr': 0.0004378887884441626, 'samples': 18400256, 'steps': 35937, 'loss/train': 1.3188179731369019}
-03/05/2022 07:42:41 - INFO - codeparrot_training - Step 35938: {'lr': 0.000437885287700414, 'samples': 18400768, 'steps': 35938, 'loss/train': 2.3480968475341797}
-03/05/2022 07:42:43 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/05/2022 07:42:46 - INFO - codeparrot_training - Step 35939: {'lr': 0.0004378817868720073, 'samples': 18401280, 'steps': 35939, 'loss/train': 1.3014940023422241}
-03/05/2022 07:42:49 - INFO - codeparrot_training - Step 35940: {'lr': 0.0004378782859589439, 'samples': 18401792, 'steps': 35940, 'loss/train': 0.8093006014823914}
-03/05/2022 07:42:51 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/05/2022 07:42:55 - INFO - codeparrot_training - Step 35941: {'lr': 0.00043787478496122546, 'samples': 18402304, 'steps': 35941, 'loss/train': 1.4561192989349365}
-03/05/2022 07:42:58 - INFO - codeparrot_training - Step 35942: {'lr': 0.0004378712838788536, 'samples': 18402816, 'steps': 35942, 'loss/train': 1.4554587602615356}
-03/05/2022 07:43:00 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/05/2022 07:43:03 - INFO - codeparrot_training - Step 35943: {'lr': 0.0004378677827118297, 'samples': 18403328, 'steps': 35943, 'loss/train': 1.6701472997665405}
-03/05/2022 07:43:06 - INFO - codeparrot_training - Step 35944: {'lr': 0.0004378642814601556, 'samples': 18403840, 'steps': 35944, 'loss/train': 2.287165641784668}
-03/05/2022 07:43:08 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 07:43:11 - INFO - codeparrot_training - Step 35945: {'lr': 0.0004378607801238327, 'samples': 18404352, 'steps': 35945, 'loss/train': 1.367347002029419}
-03/05/2022 07:43:15 - INFO - codeparrot_training - Step 35946: {'lr': 0.00043785727870286265, 'samples': 18404864, 'steps': 35946, 'loss/train': 1.82753586769104}
-03/05/2022 07:43:16 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/05/2022 07:43:20 - INFO - codeparrot_training - Step 35947: {'lr': 0.00043785377719724697, 'samples': 18405376, 'steps': 35947, 'loss/train': 1.7543127536773682}
-03/05/2022 07:43:23 - INFO - codeparrot_training - Step 35948: {'lr': 0.0004378502756069873, 'samples': 18405888, 'steps': 35948, 'loss/train': 2.7939560413360596}
-03/05/2022 07:43:25 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/05/2022 07:43:28 - INFO - codeparrot_training - Step 35949: {'lr': 0.0004378467739320852, 'samples': 18406400, 'steps': 35949, 'loss/train': 2.0785772800445557}
-03/05/2022 07:43:31 - INFO - codeparrot_training - Step 35950: {'lr': 0.0004378432721725422, 'samples': 18406912, 'steps': 35950, 'loss/train': 1.8044590950012207}
-03/05/2022 07:43:33 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/05/2022 07:43:37 - INFO - codeparrot_training - Step 35951: {'lr': 0.00043783977032836, 'samples': 18407424, 'steps': 35951, 'loss/train': 1.4472506046295166}
-03/05/2022 07:43:40 - INFO - codeparrot_training - Step 35952: {'lr': 0.00043783626839954005, 'samples': 18407936, 'steps': 35952, 'loss/train': 1.9294869899749756}
-03/05/2022 07:43:42 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/05/2022 07:43:45 - INFO - codeparrot_training - Step 35953: {'lr': 0.0004378327663860839, 'samples': 18408448, 'steps': 35953, 'loss/train': 2.2978625297546387}
-03/05/2022 07:43:48 - INFO - codeparrot_training - Step 35954: {'lr': 0.00043782926428799333, 'samples': 18408960, 'steps': 35954, 'loss/train': 2.6325531005859375}
-03/05/2022 07:43:50 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/05/2022 07:43:54 - INFO - codeparrot_training - Step 35955: {'lr': 0.0004378257621052698, 'samples': 18409472, 'steps': 35955, 'loss/train': 1.1020407676696777}
-03/05/2022 07:43:57 - INFO - codeparrot_training - Step 35956: {'lr': 0.0004378222598379148, 'samples': 18409984, 'steps': 35956, 'loss/train': 1.9964470863342285}
-03/05/2022 07:43:59 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 07:44:02 - INFO - codeparrot_training - Step 35957: {'lr': 0.00043781875748593, 'samples': 18410496, 'steps': 35957, 'loss/train': 1.7800228595733643}
-03/05/2022 07:44:05 - INFO - codeparrot_training - Step 35958: {'lr': 0.000437815255049317, 'samples': 18411008, 'steps': 35958, 'loss/train': 1.2472730875015259}
-03/05/2022 07:44:07 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/05/2022 07:44:11 - INFO - codeparrot_training - Step 35959: {'lr': 0.0004378117525280773, 'samples': 18411520, 'steps': 35959, 'loss/train': 1.005857229232788}
-03/05/2022 07:44:14 - INFO - codeparrot_training - Step 35960: {'lr': 0.00043780824992221257, 'samples': 18412032, 'steps': 35960, 'loss/train': 2.2238831520080566}
-03/05/2022 07:44:15 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 07:44:19 - INFO - codeparrot_training - Step 35961: {'lr': 0.00043780474723172433, 'samples': 18412544, 'steps': 35961, 'loss/train': 1.3160045146942139}
-03/05/2022 07:44:22 - INFO - codeparrot_training - Step 35962: {'lr': 0.00043780124445661416, 'samples': 18413056, 'steps': 35962, 'loss/train': 1.106994390487671}
-03/05/2022 07:44:24 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/05/2022 07:44:28 - INFO - codeparrot_training - Step 35963: {'lr': 0.00043779774159688364, 'samples': 18413568, 'steps': 35963, 'loss/train': 1.735798716545105}
-03/05/2022 07:44:31 - INFO - codeparrot_training - Step 35964: {'lr': 0.00043779423865253434, 'samples': 18414080, 'steps': 35964, 'loss/train': 1.217540979385376}
-03/05/2022 07:44:32 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/05/2022 07:44:36 - INFO - codeparrot_training - Step 35965: {'lr': 0.00043779073562356783, 'samples': 18414592, 'steps': 35965, 'loss/train': 2.442396640777588}
-03/05/2022 07:44:39 - INFO - codeparrot_training - Step 35966: {'lr': 0.0004377872325099858, 'samples': 18415104, 'steps': 35966, 'loss/train': 1.8784565925598145}
-03/05/2022 07:44:41 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/05/2022 07:44:45 - INFO - codeparrot_training - Step 35967: {'lr': 0.00043778372931178974, 'samples': 18415616, 'steps': 35967, 'loss/train': 0.4709174633026123}
-03/05/2022 07:44:48 - INFO - codeparrot_training - Step 35968: {'lr': 0.00043778022602898115, 'samples': 18416128, 'steps': 35968, 'loss/train': 1.527003526687622}
-03/05/2022 07:44:50 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 07:44:53 - INFO - codeparrot_training - Step 35969: {'lr': 0.0004377767226615617, 'samples': 18416640, 'steps': 35969, 'loss/train': 0.8941778540611267}
-03/05/2022 07:44:56 - INFO - codeparrot_training - Step 35970: {'lr': 0.000437773219209533, 'samples': 18417152, 'steps': 35970, 'loss/train': 1.0317169427871704}
-03/05/2022 07:44:58 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/05/2022 07:45:02 - INFO - codeparrot_training - Step 35971: {'lr': 0.00043776971567289656, 'samples': 18417664, 'steps': 35971, 'loss/train': 1.9350649118423462}
-03/05/2022 07:45:05 - INFO - codeparrot_training - Step 35972: {'lr': 0.00043776621205165404, 'samples': 18418176, 'steps': 35972, 'loss/train': 1.9036024808883667}
-03/05/2022 07:45:07 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/05/2022 07:45:10 - INFO - codeparrot_training - Step 35973: {'lr': 0.0004377627083458069, 'samples': 18418688, 'steps': 35973, 'loss/train': 1.7550768852233887}
-03/05/2022 07:45:13 - INFO - codeparrot_training - Step 35974: {'lr': 0.0004377592045553568, 'samples': 18419200, 'steps': 35974, 'loss/train': 1.9465960264205933}
-03/05/2022 07:45:15 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/05/2022 07:45:18 - INFO - codeparrot_training - Step 35975: {'lr': 0.00043775570068030524, 'samples': 18419712, 'steps': 35975, 'loss/train': 2.381316900253296}
-03/05/2022 07:45:22 - INFO - codeparrot_training - Step 35976: {'lr': 0.0004377521967206539, 'samples': 18420224, 'steps': 35976, 'loss/train': 1.018899917602539}
-03/05/2022 07:45:23 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/05/2022 07:45:27 - INFO - codeparrot_training - Step 35977: {'lr': 0.00043774869267640436, 'samples': 18420736, 'steps': 35977, 'loss/train': 0.7942408323287964}
-03/05/2022 07:45:30 - INFO - codeparrot_training - Step 35978: {'lr': 0.0004377451885475581, 'samples': 18421248, 'steps': 35978, 'loss/train': 1.923218011856079}
-03/05/2022 07:45:32 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/05/2022 07:45:36 - INFO - codeparrot_training - Step 35979: {'lr': 0.0004377416843341168, 'samples': 18421760, 'steps': 35979, 'loss/train': 1.3333343267440796}
-03/05/2022 07:45:39 - INFO - codeparrot_training - Step 35980: {'lr': 0.00043773818003608203, 'samples': 18422272, 'steps': 35980, 'loss/train': 1.4476085901260376}
-03/05/2022 07:45:41 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/05/2022 07:45:44 - INFO - codeparrot_training - Step 35981: {'lr': 0.00043773467565345523, 'samples': 18422784, 'steps': 35981, 'loss/train': 1.7924728393554688}
-03/05/2022 07:45:47 - INFO - codeparrot_training - Step 35982: {'lr': 0.0004377311711862381, 'samples': 18423296, 'steps': 35982, 'loss/train': 1.518284559249878}
-03/05/2022 07:45:50 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 07:45:53 - INFO - codeparrot_training - Step 35983: {'lr': 0.0004377276666344322, 'samples': 18423808, 'steps': 35983, 'loss/train': 2.0242831707000732}
-03/05/2022 07:45:56 - INFO - codeparrot_training - Step 35984: {'lr': 0.00043772416199803924, 'samples': 18424320, 'steps': 35984, 'loss/train': 1.7766319513320923}
-03/05/2022 07:45:59 - INFO - codeparrot_training - Step 35985: {'lr': 0.00043772065727706053, 'samples': 18424832, 'steps': 35985, 'loss/train': 2.3376874923706055}
-03/05/2022 07:46:00 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/05/2022 07:46:05 - INFO - codeparrot_training - Step 35986: {'lr': 0.0004377171524714978, 'samples': 18425344, 'steps': 35986, 'loss/train': 1.4031537771224976}
-03/05/2022 07:46:08 - INFO - codeparrot_training - Step 35987: {'lr': 0.0004377136475813527, 'samples': 18425856, 'steps': 35987, 'loss/train': 1.650159239768982}
-03/05/2022 07:46:08 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/05/2022 07:46:13 - INFO - codeparrot_training - Step 35988: {'lr': 0.0004377101426066266, 'samples': 18426368, 'steps': 35988, 'loss/train': 1.8247898817062378}
-03/05/2022 07:46:16 - INFO - codeparrot_training - Step 35989: {'lr': 0.0004377066375473213, 'samples': 18426880, 'steps': 35989, 'loss/train': 1.8686864376068115}
-03/05/2022 07:46:17 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/05/2022 07:46:22 - INFO - codeparrot_training - Step 35990: {'lr': 0.00043770313240343826, 'samples': 18427392, 'steps': 35990, 'loss/train': 1.5913472175598145}
-03/05/2022 07:46:25 - INFO - codeparrot_training - Step 35991: {'lr': 0.00043769962717497916, 'samples': 18427904, 'steps': 35991, 'loss/train': 0.7668764591217041}
-03/05/2022 07:46:25 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/05/2022 07:46:30 - INFO - codeparrot_training - Step 35992: {'lr': 0.0004376961218619454, 'samples': 18428416, 'steps': 35992, 'loss/train': 2.1044797897338867}
-03/05/2022 07:46:33 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/05/2022 07:46:35 - INFO - codeparrot_training - Step 35993: {'lr': 0.00043769261646433867, 'samples': 18428928, 'steps': 35993, 'loss/train': 2.0589356422424316}
-03/05/2022 07:46:39 - INFO - codeparrot_training - Step 35994: {'lr': 0.0004376891109821606, 'samples': 18429440, 'steps': 35994, 'loss/train': 2.0715579986572266}
-03/05/2022 07:46:41 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/05/2022 07:46:44 - INFO - codeparrot_training - Step 35995: {'lr': 0.0004376856054154127, 'samples': 18429952, 'steps': 35995, 'loss/train': 0.7547063827514648}
-03/05/2022 07:46:47 - INFO - codeparrot_training - Step 35996: {'lr': 0.00043768209976409645, 'samples': 18430464, 'steps': 35996, 'loss/train': 1.2887649536132812}
-03/05/2022 07:46:50 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 07:46:52 - INFO - codeparrot_training - Step 35997: {'lr': 0.0004376785940282137, 'samples': 18430976, 'steps': 35997, 'loss/train': 1.4761664867401123}
-03/05/2022 07:46:55 - INFO - codeparrot_training - Step 35998: {'lr': 0.0004376750882077658, 'samples': 18431488, 'steps': 35998, 'loss/train': 1.7713323831558228}
-03/05/2022 07:46:58 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 07:47:01 - INFO - codeparrot_training - Step 35999: {'lr': 0.0004376715823027544, 'samples': 18432000, 'steps': 35999, 'loss/train': 1.7673873901367188}
-03/05/2022 07:47:04 - INFO - codeparrot_training - Step 36000: {'lr': 0.0004376680763131811, 'samples': 18432512, 'steps': 36000, 'loss/train': 2.2958476543426514}
-03/05/2022 07:47:07 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/05/2022 07:47:09 - INFO - codeparrot_training - Step 36001: {'lr': 0.0004376645702390475, 'samples': 18433024, 'steps': 36001, 'loss/train': 2.097511053085327}
-03/05/2022 07:47:12 - INFO - codeparrot_training - Step 36002: {'lr': 0.00043766106408035506, 'samples': 18433536, 'steps': 36002, 'loss/train': 1.776561975479126}
-03/05/2022 07:47:15 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/05/2022 07:47:18 - INFO - codeparrot_training - Step 36003: {'lr': 0.0004376575578371055, 'samples': 18434048, 'steps': 36003, 'loss/train': 1.5307483673095703}
-03/05/2022 07:47:21 - INFO - codeparrot_training - Step 36004: {'lr': 0.0004376540515093003, 'samples': 18434560, 'steps': 36004, 'loss/train': 2.2224555015563965}
-03/05/2022 07:47:24 - INFO - codeparrot_training - Step 36005: {'lr': 0.0004376505450969411, 'samples': 18435072, 'steps': 36005, 'loss/train': 1.0934361219406128}
-03/05/2022 07:47:24 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/05/2022 07:47:30 - INFO - codeparrot_training - Step 36006: {'lr': 0.0004376470386000294, 'samples': 18435584, 'steps': 36006, 'loss/train': 1.42449152469635}
-03/05/2022 07:47:33 - INFO - codeparrot_training - Step 36007: {'lr': 0.0004376435320185669, 'samples': 18436096, 'steps': 36007, 'loss/train': 0.8030275702476501}
-03/05/2022 07:47:34 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/05/2022 07:47:38 - INFO - codeparrot_training - Step 36008: {'lr': 0.0004376400253525551, 'samples': 18436608, 'steps': 36008, 'loss/train': 1.8778250217437744}
-03/05/2022 07:47:41 - INFO - codeparrot_training - Step 36009: {'lr': 0.0004376365186019956, 'samples': 18437120, 'steps': 36009, 'loss/train': 1.8812497854232788}
-03/05/2022 07:47:42 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 07:47:46 - INFO - codeparrot_training - Step 36010: {'lr': 0.00043763301176689, 'samples': 18437632, 'steps': 36010, 'loss/train': 1.4928123950958252}
-03/05/2022 07:47:50 - INFO - codeparrot_training - Step 36011: {'lr': 0.0004376295048472399, 'samples': 18438144, 'steps': 36011, 'loss/train': 1.6759164333343506}
-03/05/2022 07:47:51 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 07:47:55 - INFO - codeparrot_training - Step 36012: {'lr': 0.0004376259978430468, 'samples': 18438656, 'steps': 36012, 'loss/train': 2.0091207027435303}
-03/05/2022 07:47:58 - INFO - codeparrot_training - Step 36013: {'lr': 0.0004376224907543123, 'samples': 18439168, 'steps': 36013, 'loss/train': 1.7162997722625732}
-03/05/2022 07:47:59 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/05/2022 07:48:03 - INFO - codeparrot_training - Step 36014: {'lr': 0.00043761898358103804, 'samples': 18439680, 'steps': 36014, 'loss/train': 1.0046173334121704}
-03/05/2022 07:48:06 - INFO - codeparrot_training - Step 36015: {'lr': 0.0004376154763232255, 'samples': 18440192, 'steps': 36015, 'loss/train': 1.843575358390808}
-03/05/2022 07:48:08 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/05/2022 07:48:12 - INFO - codeparrot_training - Step 36016: {'lr': 0.0004376119689808764, 'samples': 18440704, 'steps': 36016, 'loss/train': 1.7849065065383911}
-03/05/2022 07:48:15 - INFO - codeparrot_training - Step 36017: {'lr': 0.00043760846155399216, 'samples': 18441216, 'steps': 36017, 'loss/train': 2.235692262649536}
-03/05/2022 07:48:16 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/05/2022 07:48:20 - INFO - codeparrot_training - Step 36018: {'lr': 0.0004376049540425745, 'samples': 18441728, 'steps': 36018, 'loss/train': 1.2385354042053223}
-03/05/2022 07:48:23 - INFO - codeparrot_training - Step 36019: {'lr': 0.0004376014464466249, 'samples': 18442240, 'steps': 36019, 'loss/train': 1.3960278034210205}
-03/05/2022 07:48:25 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/05/2022 07:48:29 - INFO - codeparrot_training - Step 36020: {'lr': 0.0004375979387661451, 'samples': 18442752, 'steps': 36020, 'loss/train': 2.5139732360839844}
-03/05/2022 07:48:32 - INFO - codeparrot_training - Step 36021: {'lr': 0.0004375944310011364, 'samples': 18443264, 'steps': 36021, 'loss/train': 1.8864893913269043}
-03/05/2022 07:48:33 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 07:48:37 - INFO - codeparrot_training - Step 36022: {'lr': 0.00043759092315160064, 'samples': 18443776, 'steps': 36022, 'loss/train': 1.771661639213562}
-03/05/2022 07:48:40 - INFO - codeparrot_training - Step 36023: {'lr': 0.00043758741521753925, 'samples': 18444288, 'steps': 36023, 'loss/train': 1.9043145179748535}
-03/05/2022 07:48:41 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/05/2022 07:48:46 - INFO - codeparrot_training - Step 36024: {'lr': 0.0004375839071989539, 'samples': 18444800, 'steps': 36024, 'loss/train': 1.9852889776229858}
-03/05/2022 07:48:49 - INFO - codeparrot_training - Step 36025: {'lr': 0.00043758039909584613, 'samples': 18445312, 'steps': 36025, 'loss/train': 1.680732011795044}
-03/05/2022 07:48:50 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/05/2022 07:48:54 - INFO - codeparrot_training - Step 36026: {'lr': 0.0004375768909082175, 'samples': 18445824, 'steps': 36026, 'loss/train': 2.077925682067871}
-03/05/2022 07:48:57 - INFO - codeparrot_training - Step 36027: {'lr': 0.0004375733826360697, 'samples': 18446336, 'steps': 36027, 'loss/train': 1.7050411701202393}
-03/05/2022 07:48:59 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 07:49:03 - INFO - codeparrot_training - Step 36028: {'lr': 0.0004375698742794042, 'samples': 18446848, 'steps': 36028, 'loss/train': 0.2357165366411209}
-03/05/2022 07:49:06 - INFO - codeparrot_training - Step 36029: {'lr': 0.0004375663658382225, 'samples': 18447360, 'steps': 36029, 'loss/train': 1.7269304990768433}
-03/05/2022 07:49:08 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/05/2022 07:49:11 - INFO - codeparrot_training - Step 36030: {'lr': 0.0004375628573125264, 'samples': 18447872, 'steps': 36030, 'loss/train': 1.5712928771972656}
-03/05/2022 07:49:14 - INFO - codeparrot_training - Step 36031: {'lr': 0.0004375593487023174, 'samples': 18448384, 'steps': 36031, 'loss/train': 1.0479099750518799}
-03/05/2022 07:49:17 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 07:49:20 - INFO - codeparrot_training - Step 36032: {'lr': 0.00043755584000759696, 'samples': 18448896, 'steps': 36032, 'loss/train': 0.9133749008178711}
-03/05/2022 07:49:23 - INFO - codeparrot_training - Step 36033: {'lr': 0.0004375523312283668, 'samples': 18449408, 'steps': 36033, 'loss/train': 1.503010869026184}
-03/05/2022 07:49:25 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/05/2022 07:49:28 - INFO - codeparrot_training - Step 36034: {'lr': 0.00043754882236462844, 'samples': 18449920, 'steps': 36034, 'loss/train': 2.320054054260254}
-03/05/2022 07:49:31 - INFO - codeparrot_training - Step 36035: {'lr': 0.00043754531341638346, 'samples': 18450432, 'steps': 36035, 'loss/train': 2.1610043048858643}
-03/05/2022 07:49:34 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 07:49:37 - INFO - codeparrot_training - Step 36036: {'lr': 0.00043754180438363344, 'samples': 18450944, 'steps': 36036, 'loss/train': 2.3736748695373535}
-03/05/2022 07:49:40 - INFO - codeparrot_training - Step 36037: {'lr': 0.00043753829526638, 'samples': 18451456, 'steps': 36037, 'loss/train': 2.0576727390289307}
-03/05/2022 07:49:42 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 07:49:45 - INFO - codeparrot_training - Step 36038: {'lr': 0.0004375347860646247, 'samples': 18451968, 'steps': 36038, 'loss/train': 0.9850777387619019}
-03/05/2022 07:49:48 - INFO - codeparrot_training - Step 36039: {'lr': 0.00043753127677836917, 'samples': 18452480, 'steps': 36039, 'loss/train': 1.829777717590332}
-03/05/2022 07:49:51 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/05/2022 07:49:53 - INFO - codeparrot_training - Step 36040: {'lr': 0.0004375277674076149, 'samples': 18452992, 'steps': 36040, 'loss/train': 2.5125606060028076}
-03/05/2022 07:49:57 - INFO - codeparrot_training - Step 36041: {'lr': 0.0004375242579523635, 'samples': 18453504, 'steps': 36041, 'loss/train': 0.8594634532928467}
-03/05/2022 07:49:59 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/05/2022 07:50:02 - INFO - codeparrot_training - Step 36042: {'lr': 0.0004375207484126166, 'samples': 18454016, 'steps': 36042, 'loss/train': 1.9077296257019043}
-03/05/2022 07:50:05 - INFO - codeparrot_training - Step 36043: {'lr': 0.0004375172387883757, 'samples': 18454528, 'steps': 36043, 'loss/train': 1.8142083883285522}
-03/05/2022 07:50:07 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/05/2022 07:50:10 - INFO - codeparrot_training - Step 36044: {'lr': 0.00043751372907964247, 'samples': 18455040, 'steps': 36044, 'loss/train': 1.7211384773254395}
-03/05/2022 07:50:13 - INFO - codeparrot_training - Step 36045: {'lr': 0.00043751021928641845, 'samples': 18455552, 'steps': 36045, 'loss/train': 0.13927248120307922}
-03/05/2022 07:50:16 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/05/2022 07:50:19 - INFO - codeparrot_training - Step 36046: {'lr': 0.0004375067094087051, 'samples': 18456064, 'steps': 36046, 'loss/train': 1.8733571767807007}
-03/05/2022 07:50:22 - INFO - codeparrot_training - Step 36047: {'lr': 0.0004375031994465042, 'samples': 18456576, 'steps': 36047, 'loss/train': 1.6457723379135132}
-03/05/2022 07:50:24 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/05/2022 07:50:27 - INFO - codeparrot_training - Step 36048: {'lr': 0.00043749968939981734, 'samples': 18457088, 'steps': 36048, 'loss/train': 1.310285210609436}
-03/05/2022 07:50:31 - INFO - codeparrot_training - Step 36049: {'lr': 0.0004374961792686459, 'samples': 18457600, 'steps': 36049, 'loss/train': 2.435058832168579}
-03/05/2022 07:50:32 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 07:50:36 - INFO - codeparrot_training - Step 36050: {'lr': 0.00043749266905299155, 'samples': 18458112, 'steps': 36050, 'loss/train': 0.5977001786231995}
-03/05/2022 07:50:39 - INFO - codeparrot_training - Step 36051: {'lr': 0.000437489158752856, 'samples': 18458624, 'steps': 36051, 'loss/train': 1.969411015510559}
-03/05/2022 07:50:42 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/05/2022 07:50:45 - INFO - codeparrot_training - Step 36052: {'lr': 0.00043748564836824065, 'samples': 18459136, 'steps': 36052, 'loss/train': 0.9437122941017151}
-03/05/2022 07:50:48 - INFO - codeparrot_training - Step 36053: {'lr': 0.0004374821378991473, 'samples': 18459648, 'steps': 36053, 'loss/train': 2.2931623458862305}
-03/05/2022 07:50:50 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/05/2022 07:50:53 - INFO - codeparrot_training - Step 36054: {'lr': 0.0004374786273455772, 'samples': 18460160, 'steps': 36054, 'loss/train': 1.9026390314102173}
-03/05/2022 07:50:56 - INFO - codeparrot_training - Step 36055: {'lr': 0.0004374751167075322, 'samples': 18460672, 'steps': 36055, 'loss/train': 1.6958110332489014}
-03/05/2022 07:50:59 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/05/2022 07:51:02 - INFO - codeparrot_training - Step 36056: {'lr': 0.0004374716059850138, 'samples': 18461184, 'steps': 36056, 'loss/train': 1.5859400033950806}
-03/05/2022 07:51:05 - INFO - codeparrot_training - Step 36057: {'lr': 0.0004374680951780236, 'samples': 18461696, 'steps': 36057, 'loss/train': 0.7874780893325806}
-03/05/2022 07:51:07 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/05/2022 07:51:10 - INFO - codeparrot_training - Step 36058: {'lr': 0.00043746458428656324, 'samples': 18462208, 'steps': 36058, 'loss/train': 2.397481918334961}
-03/05/2022 07:51:13 - INFO - codeparrot_training - Step 36059: {'lr': 0.00043746107331063414, 'samples': 18462720, 'steps': 36059, 'loss/train': 1.4412318468093872}
-03/05/2022 07:51:16 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/05/2022 07:51:18 - INFO - codeparrot_training - Step 36060: {'lr': 0.000437457562250238, 'samples': 18463232, 'steps': 36060, 'loss/train': 1.8971121311187744}
-03/05/2022 07:51:21 - INFO - codeparrot_training - Step 36061: {'lr': 0.0004374540511053763, 'samples': 18463744, 'steps': 36061, 'loss/train': 1.9326227903366089}
-03/05/2022 07:51:24 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/05/2022 07:51:27 - INFO - codeparrot_training - Step 36062: {'lr': 0.00043745053987605075, 'samples': 18464256, 'steps': 36062, 'loss/train': 2.0043246746063232}
-03/05/2022 07:51:30 - INFO - codeparrot_training - Step 36063: {'lr': 0.00043744702856226295, 'samples': 18464768, 'steps': 36063, 'loss/train': 2.230461597442627}
-03/05/2022 07:51:33 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/05/2022 07:51:35 - INFO - codeparrot_training - Step 36064: {'lr': 0.0004374435171640144, 'samples': 18465280, 'steps': 36064, 'loss/train': 2.3074138164520264}
-03/05/2022 07:51:38 - INFO - codeparrot_training - Step 36065: {'lr': 0.0004374400056813066, 'samples': 18465792, 'steps': 36065, 'loss/train': 2.333336114883423}
-03/05/2022 07:51:42 - INFO - codeparrot_training - Step 36066: {'lr': 0.0004374364941141413, 'samples': 18466304, 'steps': 36066, 'loss/train': 1.0370543003082275}
-03/05/2022 07:51:42 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/05/2022 07:51:47 - INFO - codeparrot_training - Step 36067: {'lr': 0.00043743298246251994, 'samples': 18466816, 'steps': 36067, 'loss/train': 2.4303033351898193}
-03/05/2022 07:51:50 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/05/2022 07:51:52 - INFO - codeparrot_training - Step 36068: {'lr': 0.00043742947072644424, 'samples': 18467328, 'steps': 36068, 'loss/train': 1.48797607421875}
-03/05/2022 07:51:56 - INFO - codeparrot_training - Step 36069: {'lr': 0.0004374259589059157, 'samples': 18467840, 'steps': 36069, 'loss/train': 0.5635892748832703}
-03/05/2022 07:51:58 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/05/2022 07:52:01 - INFO - codeparrot_training - Step 36070: {'lr': 0.0004374224470009359, 'samples': 18468352, 'steps': 36070, 'loss/train': 2.4696810245513916}
-03/05/2022 07:52:04 - INFO - codeparrot_training - Step 36071: {'lr': 0.00043741893501150644, 'samples': 18468864, 'steps': 36071, 'loss/train': 1.4809744358062744}
-03/05/2022 07:52:07 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/05/2022 07:52:09 - INFO - codeparrot_training - Step 36072: {'lr': 0.0004374154229376289, 'samples': 18469376, 'steps': 36072, 'loss/train': 1.4185858964920044}
-03/05/2022 07:52:13 - INFO - codeparrot_training - Step 36073: {'lr': 0.00043741191077930486, 'samples': 18469888, 'steps': 36073, 'loss/train': 0.6192315220832825}
-03/05/2022 07:52:15 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/05/2022 07:52:18 - INFO - codeparrot_training - Step 36074: {'lr': 0.00043740839853653594, 'samples': 18470400, 'steps': 36074, 'loss/train': 1.89198899269104}
-03/05/2022 07:52:21 - INFO - codeparrot_training - Step 36075: {'lr': 0.0004374048862093236, 'samples': 18470912, 'steps': 36075, 'loss/train': 2.2146034240722656}
-03/05/2022 07:52:24 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 07:52:26 - INFO - codeparrot_training - Step 36076: {'lr': 0.00043740137379766954, 'samples': 18471424, 'steps': 36076, 'loss/train': 1.3566384315490723}
-03/05/2022 07:52:30 - INFO - codeparrot_training - Step 36077: {'lr': 0.0004373978613015753, 'samples': 18471936, 'steps': 36077, 'loss/train': 1.6380304098129272}
-03/05/2022 07:52:32 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/05/2022 07:52:35 - INFO - codeparrot_training - Step 36078: {'lr': 0.00043739434872104257, 'samples': 18472448, 'steps': 36078, 'loss/train': 2.2891197204589844}
-03/05/2022 07:52:38 - INFO - codeparrot_training - Step 36079: {'lr': 0.00043739083605607275, 'samples': 18472960, 'steps': 36079, 'loss/train': 2.049835443496704}
-03/05/2022 07:52:40 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/05/2022 07:52:43 - INFO - codeparrot_training - Step 36080: {'lr': 0.0004373873233066676, 'samples': 18473472, 'steps': 36080, 'loss/train': 1.891786813735962}
-03/05/2022 07:52:46 - INFO - codeparrot_training - Step 36081: {'lr': 0.00043738381047282856, 'samples': 18473984, 'steps': 36081, 'loss/train': 1.8513660430908203}
-03/05/2022 07:52:49 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 07:52:52 - INFO - codeparrot_training - Step 36082: {'lr': 0.00043738029755455724, 'samples': 18474496, 'steps': 36082, 'loss/train': 1.5867093801498413}
-03/05/2022 07:52:55 - INFO - codeparrot_training - Step 36083: {'lr': 0.00043737678455185524, 'samples': 18475008, 'steps': 36083, 'loss/train': 1.4178807735443115}
-03/05/2022 07:52:57 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 07:53:00 - INFO - codeparrot_training - Step 36084: {'lr': 0.0004373732714647242, 'samples': 18475520, 'steps': 36084, 'loss/train': 5.296960353851318}
-03/05/2022 07:53:03 - INFO - codeparrot_training - Step 36085: {'lr': 0.0004373697582931657, 'samples': 18476032, 'steps': 36085, 'loss/train': 1.0003697872161865}
-03/05/2022 07:53:06 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 07:53:08 - INFO - codeparrot_training - Step 36086: {'lr': 0.0004373662450371812, 'samples': 18476544, 'steps': 36086, 'loss/train': 1.9179296493530273}
-03/05/2022 07:53:12 - INFO - codeparrot_training - Step 36087: {'lr': 0.0004373627316967723, 'samples': 18477056, 'steps': 36087, 'loss/train': 2.0919015407562256}
-03/05/2022 07:53:14 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/05/2022 07:53:17 - INFO - codeparrot_training - Step 36088: {'lr': 0.0004373592182719408, 'samples': 18477568, 'steps': 36088, 'loss/train': 1.6749885082244873}
-03/05/2022 07:53:20 - INFO - codeparrot_training - Step 36089: {'lr': 0.00043735570476268804, 'samples': 18478080, 'steps': 36089, 'loss/train': 0.06244316324591637}
-03/05/2022 07:53:23 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/05/2022 07:53:25 - INFO - codeparrot_training - Step 36090: {'lr': 0.0004373521911690157, 'samples': 18478592, 'steps': 36090, 'loss/train': 1.9964382648468018}
-03/05/2022 07:53:29 - INFO - codeparrot_training - Step 36091: {'lr': 0.00043734867749092534, 'samples': 18479104, 'steps': 36091, 'loss/train': 2.279146194458008}
-03/05/2022 07:53:31 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/05/2022 07:53:34 - INFO - codeparrot_training - Step 36092: {'lr': 0.0004373451637284186, 'samples': 18479616, 'steps': 36092, 'loss/train': 1.8983275890350342}
-03/05/2022 07:53:37 - INFO - codeparrot_training - Step 36093: {'lr': 0.0004373416498814969, 'samples': 18480128, 'steps': 36093, 'loss/train': 2.1691272258758545}
-03/05/2022 07:53:39 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/05/2022 07:53:42 - INFO - codeparrot_training - Step 36094: {'lr': 0.0004373381359501621, 'samples': 18480640, 'steps': 36094, 'loss/train': 1.713473916053772}
-03/05/2022 07:53:45 - INFO - codeparrot_training - Step 36095: {'lr': 0.00043733462193441553, 'samples': 18481152, 'steps': 36095, 'loss/train': 2.030616521835327}
-03/05/2022 07:53:48 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/05/2022 07:53:51 - INFO - codeparrot_training - Step 36096: {'lr': 0.00043733110783425894, 'samples': 18481664, 'steps': 36096, 'loss/train': 1.8648601770401}
-03/05/2022 07:53:54 - INFO - codeparrot_training - Step 36097: {'lr': 0.00043732759364969374, 'samples': 18482176, 'steps': 36097, 'loss/train': 2.78861665725708}
-03/05/2022 07:53:56 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/05/2022 07:53:59 - INFO - codeparrot_training - Step 36098: {'lr': 0.0004373240793807217, 'samples': 18482688, 'steps': 36098, 'loss/train': 1.8727775812149048}
-03/05/2022 07:54:02 - INFO - codeparrot_training - Step 36099: {'lr': 0.00043732056502734435, 'samples': 18483200, 'steps': 36099, 'loss/train': 1.3359142541885376}
-03/05/2022 07:54:04 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/05/2022 07:54:07 - INFO - codeparrot_training - Step 36100: {'lr': 0.0004373170505895632, 'samples': 18483712, 'steps': 36100, 'loss/train': 1.5899838209152222}
-03/05/2022 07:54:11 - INFO - codeparrot_training - Step 36101: {'lr': 0.0004373135360673799, 'samples': 18484224, 'steps': 36101, 'loss/train': 1.8244878053665161}
-03/05/2022 07:54:12 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 07:54:16 - INFO - codeparrot_training - Step 36102: {'lr': 0.000437310021460796, 'samples': 18484736, 'steps': 36102, 'loss/train': 1.494297981262207}
-03/05/2022 07:54:20 - INFO - codeparrot_training - Step 36103: {'lr': 0.000437306506769813, 'samples': 18485248, 'steps': 36103, 'loss/train': 6.3272624015808105}
-03/05/2022 07:54:23 - INFO - codeparrot_training - Step 36104: {'lr': 0.0004373029919944327, 'samples': 18485760, 'steps': 36104, 'loss/train': 6.188086032867432}
-03/05/2022 07:54:24 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/05/2022 07:54:28 - INFO - codeparrot_training - Step 36105: {'lr': 0.00043729947713465653, 'samples': 18486272, 'steps': 36105, 'loss/train': 1.921324372291565}
-03/05/2022 07:54:31 - INFO - codeparrot_training - Step 36106: {'lr': 0.00043729596219048607, 'samples': 18486784, 'steps': 36106, 'loss/train': 1.467881441116333}
-03/05/2022 07:54:33 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/05/2022 07:54:36 - INFO - codeparrot_training - Step 36107: {'lr': 0.000437292447161923, 'samples': 18487296, 'steps': 36107, 'loss/train': 1.6574931144714355}
-03/05/2022 07:54:40 - INFO - codeparrot_training - Step 36108: {'lr': 0.0004372889320489688, 'samples': 18487808, 'steps': 36108, 'loss/train': 0.5765967965126038}
-03/05/2022 07:54:41 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/05/2022 07:54:45 - INFO - codeparrot_training - Step 36109: {'lr': 0.00043728541685162503, 'samples': 18488320, 'steps': 36109, 'loss/train': 0.6162421107292175}
-03/05/2022 07:54:48 - INFO - codeparrot_training - Step 36110: {'lr': 0.0004372819015698934, 'samples': 18488832, 'steps': 36110, 'loss/train': 0.9898927211761475}
-03/05/2022 07:54:49 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/05/2022 07:54:53 - INFO - codeparrot_training - Step 36111: {'lr': 0.0004372783862037755, 'samples': 18489344, 'steps': 36111, 'loss/train': 1.8901020288467407}
-03/05/2022 07:54:57 - INFO - codeparrot_training - Step 36112: {'lr': 0.00043727487075327285, 'samples': 18489856, 'steps': 36112, 'loss/train': 0.48207321763038635}
-03/05/2022 07:54:58 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/05/2022 07:55:02 - INFO - codeparrot_training - Step 36113: {'lr': 0.00043727135521838697, 'samples': 18490368, 'steps': 36113, 'loss/train': 2.088308334350586}
-03/05/2022 07:55:05 - INFO - codeparrot_training - Step 36114: {'lr': 0.00043726783959911953, 'samples': 18490880, 'steps': 36114, 'loss/train': 2.0448715686798096}
-03/05/2022 07:55:06 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/05/2022 07:55:10 - INFO - codeparrot_training - Step 36115: {'lr': 0.00043726432389547205, 'samples': 18491392, 'steps': 36115, 'loss/train': 1.8767093420028687}
-03/05/2022 07:55:13 - INFO - codeparrot_training - Step 36116: {'lr': 0.00043726080810744616, 'samples': 18491904, 'steps': 36116, 'loss/train': 0.7940533757209778}
-03/05/2022 07:55:15 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/05/2022 07:55:19 - INFO - codeparrot_training - Step 36117: {'lr': 0.0004372572922350435, 'samples': 18492416, 'steps': 36117, 'loss/train': 1.7426447868347168}
-03/05/2022 07:55:22 - INFO - codeparrot_training - Step 36118: {'lr': 0.0004372537762782656, 'samples': 18492928, 'steps': 36118, 'loss/train': 1.850325345993042}
-03/05/2022 07:55:23 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/05/2022 07:55:28 - INFO - codeparrot_training - Step 36119: {'lr': 0.00043725026023711395, 'samples': 18493440, 'steps': 36119, 'loss/train': 1.9192856550216675}
-03/05/2022 07:55:31 - INFO - codeparrot_training - Step 36120: {'lr': 0.0004372467441115903, 'samples': 18493952, 'steps': 36120, 'loss/train': 0.9669541120529175}
-03/05/2022 07:55:33 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/05/2022 07:55:36 - INFO - codeparrot_training - Step 36121: {'lr': 0.00043724322790169613, 'samples': 18494464, 'steps': 36121, 'loss/train': 1.629615068435669}
-03/05/2022 07:55:39 - INFO - codeparrot_training - Step 36122: {'lr': 0.00043723971160743305, 'samples': 18494976, 'steps': 36122, 'loss/train': 2.334636926651001}
-03/05/2022 07:55:41 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 07:55:44 - INFO - codeparrot_training - Step 36123: {'lr': 0.00043723619522880266, 'samples': 18495488, 'steps': 36123, 'loss/train': 2.4031403064727783}
-03/05/2022 07:55:47 - INFO - codeparrot_training - Step 36124: {'lr': 0.0004372326787658065, 'samples': 18496000, 'steps': 36124, 'loss/train': 1.3550822734832764}
-03/05/2022 07:55:49 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/05/2022 07:55:53 - INFO - codeparrot_training - Step 36125: {'lr': 0.00043722916221844617, 'samples': 18496512, 'steps': 36125, 'loss/train': 1.5701971054077148}
-03/05/2022 07:55:56 - INFO - codeparrot_training - Step 36126: {'lr': 0.0004372256455867233, 'samples': 18497024, 'steps': 36126, 'loss/train': 1.6868315935134888}
-03/05/2022 07:55:58 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/05/2022 07:56:01 - INFO - codeparrot_training - Step 36127: {'lr': 0.0004372221288706394, 'samples': 18497536, 'steps': 36127, 'loss/train': 1.7051806449890137}
-03/05/2022 07:56:04 - INFO - codeparrot_training - Step 36128: {'lr': 0.0004372186120701962, 'samples': 18498048, 'steps': 36128, 'loss/train': 1.2342878580093384}
-03/05/2022 07:56:06 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/05/2022 07:56:10 - INFO - codeparrot_training - Step 36129: {'lr': 0.00043721509518539507, 'samples': 18498560, 'steps': 36129, 'loss/train': 1.768221139907837}
-03/05/2022 07:56:13 - INFO - codeparrot_training - Step 36130: {'lr': 0.0004372115782162378, 'samples': 18499072, 'steps': 36130, 'loss/train': 2.062828779220581}
-03/05/2022 07:56:14 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/05/2022 07:56:18 - INFO - codeparrot_training - Step 36131: {'lr': 0.00043720806116272584, 'samples': 18499584, 'steps': 36131, 'loss/train': 2.4220993518829346}
-03/05/2022 07:56:21 - INFO - codeparrot_training - Step 36132: {'lr': 0.00043720454402486076, 'samples': 18500096, 'steps': 36132, 'loss/train': 1.1807063817977905}
-03/05/2022 07:56:23 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/05/2022 07:56:27 - INFO - codeparrot_training - Step 36133: {'lr': 0.00043720102680264427, 'samples': 18500608, 'steps': 36133, 'loss/train': 2.1760871410369873}
-03/05/2022 07:56:30 - INFO - codeparrot_training - Step 36134: {'lr': 0.0004371975094960778, 'samples': 18501120, 'steps': 36134, 'loss/train': 1.9262043237686157}
-03/05/2022 07:56:31 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 07:56:35 - INFO - codeparrot_training - Step 36135: {'lr': 0.0004371939921051632, 'samples': 18501632, 'steps': 36135, 'loss/train': 0.9442529678344727}
-03/05/2022 07:56:38 - INFO - codeparrot_training - Step 36136: {'lr': 0.00043719047462990174, 'samples': 18502144, 'steps': 36136, 'loss/train': 0.7386095523834229}
-03/05/2022 07:56:40 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/05/2022 07:56:44 - INFO - codeparrot_training - Step 36137: {'lr': 0.0004371869570702952, 'samples': 18502656, 'steps': 36137, 'loss/train': 2.030130624771118}
-03/05/2022 07:56:47 - INFO - codeparrot_training - Step 36138: {'lr': 0.0004371834394263451, 'samples': 18503168, 'steps': 36138, 'loss/train': 1.6054258346557617}
-03/05/2022 07:56:49 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 07:56:52 - INFO - codeparrot_training - Step 36139: {'lr': 0.000437179921698053, 'samples': 18503680, 'steps': 36139, 'loss/train': 2.243959665298462}
-03/05/2022 07:56:55 - INFO - codeparrot_training - Step 36140: {'lr': 0.00043717640388542045, 'samples': 18504192, 'steps': 36140, 'loss/train': 2.0341453552246094}
-03/05/2022 07:56:57 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 07:57:01 - INFO - codeparrot_training - Step 36141: {'lr': 0.00043717288598844916, 'samples': 18504704, 'steps': 36141, 'loss/train': 1.5884000062942505}
-03/05/2022 07:57:04 - INFO - codeparrot_training - Step 36142: {'lr': 0.0004371693680071407, 'samples': 18505216, 'steps': 36142, 'loss/train': 1.0458205938339233}
-03/05/2022 07:57:05 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/05/2022 07:57:09 - INFO - codeparrot_training - Step 36143: {'lr': 0.00043716584994149657, 'samples': 18505728, 'steps': 36143, 'loss/train': 1.2511316537857056}
-03/05/2022 07:57:12 - INFO - codeparrot_training - Step 36144: {'lr': 0.0004371623317915184, 'samples': 18506240, 'steps': 36144, 'loss/train': 2.0580060482025146}
-03/05/2022 07:57:14 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/05/2022 07:57:17 - INFO - codeparrot_training - Step 36145: {'lr': 0.00043715881355720776, 'samples': 18506752, 'steps': 36145, 'loss/train': 1.7831703424453735}
-03/05/2022 07:57:21 - INFO - codeparrot_training - Step 36146: {'lr': 0.0004371552952385663, 'samples': 18507264, 'steps': 36146, 'loss/train': 0.20688287913799286}
-03/05/2022 07:57:22 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 07:57:26 - INFO - codeparrot_training - Step 36147: {'lr': 0.00043715177683559546, 'samples': 18507776, 'steps': 36147, 'loss/train': 1.8477839231491089}
-03/05/2022 07:57:29 - INFO - codeparrot_training - Step 36148: {'lr': 0.000437148258348297, 'samples': 18508288, 'steps': 36148, 'loss/train': 1.1993651390075684}
-03/05/2022 07:57:30 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/05/2022 07:57:34 - INFO - codeparrot_training - Step 36149: {'lr': 0.0004371447397766724, 'samples': 18508800, 'steps': 36149, 'loss/train': 1.7000675201416016}
-03/05/2022 07:57:37 - INFO - codeparrot_training - Step 36150: {'lr': 0.0004371412211207233, 'samples': 18509312, 'steps': 36150, 'loss/train': 1.796218752861023}
-03/05/2022 07:57:39 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 07:57:43 - INFO - codeparrot_training - Step 36151: {'lr': 0.0004371377023804512, 'samples': 18509824, 'steps': 36151, 'loss/train': 2.0572822093963623}
-03/05/2022 07:57:46 - INFO - codeparrot_training - Step 36152: {'lr': 0.0004371341835558578, 'samples': 18510336, 'steps': 36152, 'loss/train': 2.4493465423583984}
-03/05/2022 07:57:47 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/05/2022 07:57:51 - INFO - codeparrot_training - Step 36153: {'lr': 0.0004371306646469445, 'samples': 18510848, 'steps': 36153, 'loss/train': 2.734365463256836}
-03/05/2022 07:57:54 - INFO - codeparrot_training - Step 36154: {'lr': 0.00043712714565371315, 'samples': 18511360, 'steps': 36154, 'loss/train': 1.4431241750717163}
-03/05/2022 07:57:56 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 07:58:00 - INFO - codeparrot_training - Step 36155: {'lr': 0.0004371236265761651, 'samples': 18511872, 'steps': 36155, 'loss/train': 1.902875304222107}
-03/05/2022 07:58:03 - INFO - codeparrot_training - Step 36156: {'lr': 0.0004371201074143021, 'samples': 18512384, 'steps': 36156, 'loss/train': 1.6863436698913574}
-03/05/2022 07:58:04 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/05/2022 07:58:08 - INFO - codeparrot_training - Step 36157: {'lr': 0.0004371165881681256, 'samples': 18512896, 'steps': 36157, 'loss/train': 2.6713547706604004}
-03/05/2022 07:58:11 - INFO - codeparrot_training - Step 36158: {'lr': 0.0004371130688376373, 'samples': 18513408, 'steps': 36158, 'loss/train': 2.0085086822509766}
-03/05/2022 07:58:14 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/05/2022 07:58:17 - INFO - codeparrot_training - Step 36159: {'lr': 0.00043710954942283875, 'samples': 18513920, 'steps': 36159, 'loss/train': 1.138684630393982}
-03/05/2022 07:58:20 - INFO - codeparrot_training - Step 36160: {'lr': 0.0004371060299237315, 'samples': 18514432, 'steps': 36160, 'loss/train': 2.2627556324005127}
-03/05/2022 07:58:22 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/05/2022 07:58:25 - INFO - codeparrot_training - Step 36161: {'lr': 0.00043710251034031713, 'samples': 18514944, 'steps': 36161, 'loss/train': 2.3857369422912598}
-03/05/2022 07:58:28 - INFO - codeparrot_training - Step 36162: {'lr': 0.0004370989906725973, 'samples': 18515456, 'steps': 36162, 'loss/train': 1.485427737236023}
-03/05/2022 07:58:31 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 07:58:34 - INFO - codeparrot_training - Step 36163: {'lr': 0.00043709547092057356, 'samples': 18515968, 'steps': 36163, 'loss/train': 0.8569915294647217}
-03/05/2022 07:58:37 - INFO - codeparrot_training - Step 36164: {'lr': 0.00043709195108424746, 'samples': 18516480, 'steps': 36164, 'loss/train': 1.4065744876861572}
-03/05/2022 07:58:40 - INFO - codeparrot_training - Step 36165: {'lr': 0.0004370884311636206, 'samples': 18516992, 'steps': 36165, 'loss/train': 1.8016481399536133}
-03/05/2022 07:58:40 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 07:58:45 - INFO - codeparrot_training - Step 36166: {'lr': 0.0004370849111586946, 'samples': 18517504, 'steps': 36166, 'loss/train': 1.5769487619400024}
-03/05/2022 07:58:48 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/05/2022 07:58:51 - INFO - codeparrot_training - Step 36167: {'lr': 0.000437081391069471, 'samples': 18518016, 'steps': 36167, 'loss/train': 2.027282238006592}
-03/05/2022 07:58:54 - INFO - codeparrot_training - Step 36168: {'lr': 0.0004370778708959514, 'samples': 18518528, 'steps': 36168, 'loss/train': 1.6011186838150024}
-03/05/2022 07:58:56 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/05/2022 07:58:59 - INFO - codeparrot_training - Step 36169: {'lr': 0.00043707435063813747, 'samples': 18519040, 'steps': 36169, 'loss/train': 1.950432538986206}
-03/05/2022 07:59:02 - INFO - codeparrot_training - Step 36170: {'lr': 0.0004370708302960307, 'samples': 18519552, 'steps': 36170, 'loss/train': 1.6154985427856445}
-03/05/2022 07:59:06 - INFO - codeparrot_training - Step 36171: {'lr': 0.00043706730986963274, 'samples': 18520064, 'steps': 36171, 'loss/train': 2.0862300395965576}
-03/05/2022 07:59:06 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/05/2022 07:59:11 - INFO - codeparrot_training - Step 36172: {'lr': 0.0004370637893589451, 'samples': 18520576, 'steps': 36172, 'loss/train': 0.3163149654865265}
-03/05/2022 07:59:14 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/05/2022 07:59:16 - INFO - codeparrot_training - Step 36173: {'lr': 0.0004370602687639693, 'samples': 18521088, 'steps': 36173, 'loss/train': 1.359409213066101}
-03/05/2022 07:59:19 - INFO - codeparrot_training - Step 36174: {'lr': 0.00043705674808470715, 'samples': 18521600, 'steps': 36174, 'loss/train': 1.6837157011032104}
-03/05/2022 07:59:22 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/05/2022 07:59:25 - INFO - codeparrot_training - Step 36175: {'lr': 0.00043705322732116007, 'samples': 18522112, 'steps': 36175, 'loss/train': 1.4574109315872192}
-03/05/2022 07:59:28 - INFO - codeparrot_training - Step 36176: {'lr': 0.00043704970647332977, 'samples': 18522624, 'steps': 36176, 'loss/train': 1.7398953437805176}
-03/05/2022 07:59:31 - INFO - codeparrot_training - Skipping example with length 795 (seq_length=1024)
-03/05/2022 07:59:33 - INFO - codeparrot_training - Step 36177: {'lr': 0.00043704618554121766, 'samples': 18523136, 'steps': 36177, 'loss/train': 1.567387342453003}
-03/05/2022 07:59:36 - INFO - codeparrot_training - Step 36178: {'lr': 0.0004370426645248254, 'samples': 18523648, 'steps': 36178, 'loss/train': 2.372109889984131}
-03/05/2022 07:59:40 - INFO - codeparrot_training - Step 36179: {'lr': 0.00043703914342415473, 'samples': 18524160, 'steps': 36179, 'loss/train': 1.7951995134353638}
-03/05/2022 07:59:40 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/05/2022 07:59:45 - INFO - codeparrot_training - Step 36180: {'lr': 0.000437035622239207, 'samples': 18524672, 'steps': 36180, 'loss/train': 1.779437780380249}
-03/05/2022 07:59:48 - INFO - codeparrot_training - Step 36181: {'lr': 0.00043703210096998396, 'samples': 18525184, 'steps': 36181, 'loss/train': 2.1929433345794678}
-03/05/2022 07:59:48 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/05/2022 07:59:53 - INFO - codeparrot_training - Step 36182: {'lr': 0.00043702857961648713, 'samples': 18525696, 'steps': 36182, 'loss/train': 1.0545645952224731}
-03/05/2022 07:59:57 - INFO - codeparrot_training - Step 36183: {'lr': 0.0004370250581787181, 'samples': 18526208, 'steps': 36183, 'loss/train': 1.8496661186218262}
-03/05/2022 07:59:57 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/05/2022 08:00:02 - INFO - codeparrot_training - Step 36184: {'lr': 0.00043702153665667846, 'samples': 18526720, 'steps': 36184, 'loss/train': 0.7489533424377441}
-03/05/2022 08:00:05 - INFO - codeparrot_training - Step 36185: {'lr': 0.0004370180150503698, 'samples': 18527232, 'steps': 36185, 'loss/train': 1.9026918411254883}
-03/05/2022 08:00:05 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/05/2022 08:00:10 - INFO - codeparrot_training - Step 36186: {'lr': 0.0004370144933597938, 'samples': 18527744, 'steps': 36186, 'loss/train': 1.7665891647338867}
-03/05/2022 08:00:13 - INFO - codeparrot_training - Step 36187: {'lr': 0.00043701097158495186, 'samples': 18528256, 'steps': 36187, 'loss/train': 1.2755967378616333}
-03/05/2022 08:00:14 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/05/2022 08:00:19 - INFO - codeparrot_training - Step 36188: {'lr': 0.0004370074497258456, 'samples': 18528768, 'steps': 36188, 'loss/train': 1.1353886127471924}
-03/05/2022 08:00:22 - INFO - codeparrot_training - Step 36189: {'lr': 0.00043700392778247676, 'samples': 18529280, 'steps': 36189, 'loss/train': 1.8752729892730713}
-03/05/2022 08:00:23 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/05/2022 08:00:27 - INFO - codeparrot_training - Step 36190: {'lr': 0.0004370004057548468, 'samples': 18529792, 'steps': 36190, 'loss/train': 2.0424540042877197}
-03/05/2022 08:00:30 - INFO - codeparrot_training - Step 36191: {'lr': 0.0004369968836429574, 'samples': 18530304, 'steps': 36191, 'loss/train': 2.411482810974121}
-03/05/2022 08:00:31 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 08:00:36 - INFO - codeparrot_training - Step 36192: {'lr': 0.0004369933614468101, 'samples': 18530816, 'steps': 36192, 'loss/train': 1.0778470039367676}
-03/05/2022 08:00:39 - INFO - codeparrot_training - Step 36193: {'lr': 0.0004369898391664064, 'samples': 18531328, 'steps': 36193, 'loss/train': 1.1295086145401}
-03/05/2022 08:00:39 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 08:00:44 - INFO - codeparrot_training - Step 36194: {'lr': 0.000436986316801748, 'samples': 18531840, 'steps': 36194, 'loss/train': 2.2310383319854736}
-03/05/2022 08:00:47 - INFO - codeparrot_training - Step 36195: {'lr': 0.00043698279435283637, 'samples': 18532352, 'steps': 36195, 'loss/train': 2.482656240463257}
-03/05/2022 08:00:47 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/05/2022 08:00:53 - INFO - codeparrot_training - Step 36196: {'lr': 0.0004369792718196733, 'samples': 18532864, 'steps': 36196, 'loss/train': 2.0867481231689453}
-03/05/2022 08:00:56 - INFO - codeparrot_training - Step 36197: {'lr': 0.0004369757492022602, 'samples': 18533376, 'steps': 36197, 'loss/train': 3.106039047241211}
-03/05/2022 08:00:56 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/05/2022 08:01:01 - INFO - codeparrot_training - Step 36198: {'lr': 0.00043697222650059876, 'samples': 18533888, 'steps': 36198, 'loss/train': 0.714049756526947}
-03/05/2022 08:01:04 - INFO - codeparrot_training - Step 36199: {'lr': 0.00043696870371469045, 'samples': 18534400, 'steps': 36199, 'loss/train': 1.5154335498809814}
-03/05/2022 08:01:04 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/05/2022 08:01:10 - INFO - codeparrot_training - Step 36200: {'lr': 0.000436965180844537, 'samples': 18534912, 'steps': 36200, 'loss/train': 1.8014168739318848}
-03/05/2022 08:01:13 - INFO - codeparrot_training - Step 36201: {'lr': 0.00043696165789013986, 'samples': 18535424, 'steps': 36201, 'loss/train': 1.4415826797485352}
-03/05/2022 08:01:13 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/05/2022 08:01:18 - INFO - codeparrot_training - Step 36202: {'lr': 0.0004369581348515007, 'samples': 18535936, 'steps': 36202, 'loss/train': 1.9209561347961426}
-03/05/2022 08:01:21 - INFO - codeparrot_training - Step 36203: {'lr': 0.00043695461172862113, 'samples': 18536448, 'steps': 36203, 'loss/train': 1.7839361429214478}
-03/05/2022 08:01:21 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/05/2022 08:01:27 - INFO - codeparrot_training - Step 36204: {'lr': 0.0004369510885215026, 'samples': 18536960, 'steps': 36204, 'loss/train': 0.8831709623336792}
-03/05/2022 08:01:29 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/05/2022 08:01:32 - INFO - codeparrot_training - Step 36205: {'lr': 0.0004369475652301469, 'samples': 18537472, 'steps': 36205, 'loss/train': 0.9231879115104675}
-03/05/2022 08:01:35 - INFO - codeparrot_training - Step 36206: {'lr': 0.0004369440418545555, 'samples': 18537984, 'steps': 36206, 'loss/train': 1.405003309249878}
-03/05/2022 08:01:38 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/05/2022 08:01:40 - INFO - codeparrot_training - Step 36207: {'lr': 0.00043694051839472995, 'samples': 18538496, 'steps': 36207, 'loss/train': 1.5588219165802002}
-03/05/2022 08:01:43 - INFO - codeparrot_training - Step 36208: {'lr': 0.00043693699485067186, 'samples': 18539008, 'steps': 36208, 'loss/train': 0.14335809648036957}
-03/05/2022 08:01:46 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/05/2022 08:01:49 - INFO - codeparrot_training - Step 36209: {'lr': 0.0004369334712223829, 'samples': 18539520, 'steps': 36209, 'loss/train': 1.48665452003479}
-03/05/2022 08:01:52 - INFO - codeparrot_training - Step 36210: {'lr': 0.0004369299475098646, 'samples': 18540032, 'steps': 36210, 'loss/train': 1.774695634841919}
-03/05/2022 08:01:54 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/05/2022 08:01:57 - INFO - codeparrot_training - Step 36211: {'lr': 0.00043692642371311854, 'samples': 18540544, 'steps': 36211, 'loss/train': 1.3025870323181152}
-03/05/2022 08:02:00 - INFO - codeparrot_training - Step 36212: {'lr': 0.00043692289983214626, 'samples': 18541056, 'steps': 36212, 'loss/train': 0.9386810064315796}
-03/05/2022 08:02:02 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/05/2022 08:02:05 - INFO - codeparrot_training - Step 36213: {'lr': 0.0004369193758669495, 'samples': 18541568, 'steps': 36213, 'loss/train': 2.5086231231689453}
-03/05/2022 08:02:09 - INFO - codeparrot_training - Step 36214: {'lr': 0.0004369158518175297, 'samples': 18542080, 'steps': 36214, 'loss/train': 1.4386712312698364}
-03/05/2022 08:02:14 - INFO - codeparrot_training - Step 36215: {'lr': 0.00043691232768388856, 'samples': 18542592, 'steps': 36215, 'loss/train': 0.8185907006263733}
-03/05/2022 08:02:17 - INFO - codeparrot_training - Step 36216: {'lr': 0.00043690880346602755, 'samples': 18543104, 'steps': 36216, 'loss/train': 2.100632667541504}
-03/05/2022 08:02:19 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/05/2022 08:02:23 - INFO - codeparrot_training - Step 36217: {'lr': 0.0004369052791639483, 'samples': 18543616, 'steps': 36217, 'loss/train': 2.7359654903411865}
-03/05/2022 08:02:26 - INFO - codeparrot_training - Step 36218: {'lr': 0.0004369017547776525, 'samples': 18544128, 'steps': 36218, 'loss/train': 2.3105406761169434}
-03/05/2022 08:02:29 - INFO - codeparrot_training - Step 36219: {'lr': 0.0004368982303071416, 'samples': 18544640, 'steps': 36219, 'loss/train': 0.2777814269065857}
-03/05/2022 08:02:31 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/05/2022 08:02:35 - INFO - codeparrot_training - Step 36220: {'lr': 0.0004368947057524173, 'samples': 18545152, 'steps': 36220, 'loss/train': 0.5430562496185303}
-03/05/2022 08:02:38 - INFO - codeparrot_training - Step 36221: {'lr': 0.00043689118111348105, 'samples': 18545664, 'steps': 36221, 'loss/train': 1.5130711793899536}
-03/05/2022 08:02:39 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 08:02:43 - INFO - codeparrot_training - Step 36222: {'lr': 0.00043688765639033456, 'samples': 18546176, 'steps': 36222, 'loss/train': 1.687487006187439}
-03/05/2022 08:02:46 - INFO - codeparrot_training - Step 36223: {'lr': 0.00043688413158297934, 'samples': 18546688, 'steps': 36223, 'loss/train': 1.8386186361312866}
-03/05/2022 08:02:48 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/05/2022 08:02:51 - INFO - codeparrot_training - Step 36224: {'lr': 0.00043688060669141705, 'samples': 18547200, 'steps': 36224, 'loss/train': 0.5818009376525879}
-03/05/2022 08:02:54 - INFO - codeparrot_training - Step 36225: {'lr': 0.00043687708171564923, 'samples': 18547712, 'steps': 36225, 'loss/train': 0.5071030259132385}
-03/05/2022 08:02:56 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/05/2022 08:03:00 - INFO - codeparrot_training - Step 36226: {'lr': 0.00043687355665567745, 'samples': 18548224, 'steps': 36226, 'loss/train': 2.066742181777954}
-03/05/2022 08:03:03 - INFO - codeparrot_training - Step 36227: {'lr': 0.0004368700315115034, 'samples': 18548736, 'steps': 36227, 'loss/train': 2.1796653270721436}
-03/05/2022 08:03:05 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/05/2022 08:03:08 - INFO - codeparrot_training - Step 36228: {'lr': 0.00043686650628312854, 'samples': 18549248, 'steps': 36228, 'loss/train': 1.6563241481781006}
-03/05/2022 08:03:11 - INFO - codeparrot_training - Step 36229: {'lr': 0.00043686298097055456, 'samples': 18549760, 'steps': 36229, 'loss/train': 1.921481728553772}
-03/05/2022 08:03:13 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/05/2022 08:03:17 - INFO - codeparrot_training - Step 36230: {'lr': 0.0004368594555737829, 'samples': 18550272, 'steps': 36230, 'loss/train': 1.4369345903396606}
-03/05/2022 08:03:20 - INFO - codeparrot_training - Step 36231: {'lr': 0.0004368559300928153, 'samples': 18550784, 'steps': 36231, 'loss/train': 2.365375280380249}
-03/05/2022 08:03:22 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/05/2022 08:03:25 - INFO - codeparrot_training - Step 36232: {'lr': 0.0004368524045276534, 'samples': 18551296, 'steps': 36232, 'loss/train': 1.371537446975708}
-03/05/2022 08:03:28 - INFO - codeparrot_training - Step 36233: {'lr': 0.00043684887887829863, 'samples': 18551808, 'steps': 36233, 'loss/train': 1.244019627571106}
-03/05/2022 08:03:30 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/05/2022 08:03:34 - INFO - codeparrot_training - Step 36234: {'lr': 0.0004368453531447526, 'samples': 18552320, 'steps': 36234, 'loss/train': 1.665464997291565}
-03/05/2022 08:03:37 - INFO - codeparrot_training - Step 36235: {'lr': 0.00043684182732701694, 'samples': 18552832, 'steps': 36235, 'loss/train': 1.2097283601760864}
-03/05/2022 08:03:39 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/05/2022 08:03:42 - INFO - codeparrot_training - Step 36236: {'lr': 0.00043683830142509327, 'samples': 18553344, 'steps': 36236, 'loss/train': 1.4860055446624756}
-03/05/2022 08:03:45 - INFO - codeparrot_training - Step 36237: {'lr': 0.00043683477543898314, 'samples': 18553856, 'steps': 36237, 'loss/train': 1.096606731414795}
-03/05/2022 08:03:47 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/05/2022 08:03:50 - INFO - codeparrot_training - Step 36238: {'lr': 0.0004368312493686881, 'samples': 18554368, 'steps': 36238, 'loss/train': 1.7119722366333008}
-03/05/2022 08:03:54 - INFO - codeparrot_training - Step 36239: {'lr': 0.0004368277232142098, 'samples': 18554880, 'steps': 36239, 'loss/train': 1.7283732891082764}
-03/05/2022 08:03:55 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/05/2022 08:03:59 - INFO - codeparrot_training - Step 36240: {'lr': 0.00043682419697554985, 'samples': 18555392, 'steps': 36240, 'loss/train': 2.4775230884552}
-03/05/2022 08:04:02 - INFO - codeparrot_training - Step 36241: {'lr': 0.0004368206706527098, 'samples': 18555904, 'steps': 36241, 'loss/train': 1.2291070222854614}
-03/05/2022 08:04:04 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/05/2022 08:04:07 - INFO - codeparrot_training - Step 36242: {'lr': 0.00043681714424569117, 'samples': 18556416, 'steps': 36242, 'loss/train': 1.6486002206802368}
-03/05/2022 08:04:10 - INFO - codeparrot_training - Step 36243: {'lr': 0.0004368136177544957, 'samples': 18556928, 'steps': 36243, 'loss/train': 2.1133370399475098}
-03/05/2022 08:04:12 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/05/2022 08:04:16 - INFO - codeparrot_training - Step 36244: {'lr': 0.00043681009117912484, 'samples': 18557440, 'steps': 36244, 'loss/train': 2.095912218093872}
-03/05/2022 08:04:19 - INFO - codeparrot_training - Step 36245: {'lr': 0.0004368065645195803, 'samples': 18557952, 'steps': 36245, 'loss/train': 0.3720453083515167}
-03/05/2022 08:04:21 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/05/2022 08:04:24 - INFO - codeparrot_training - Step 36246: {'lr': 0.0004368030377758636, 'samples': 18558464, 'steps': 36246, 'loss/train': 1.4571070671081543}
-03/05/2022 08:04:27 - INFO - codeparrot_training - Step 36247: {'lr': 0.0004367995109479763, 'samples': 18558976, 'steps': 36247, 'loss/train': 1.5462771654129028}
-03/05/2022 08:04:29 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/05/2022 08:04:33 - INFO - codeparrot_training - Step 36248: {'lr': 0.00043679598403592, 'samples': 18559488, 'steps': 36248, 'loss/train': 1.2162226438522339}
-03/05/2022 08:04:36 - INFO - codeparrot_training - Step 36249: {'lr': 0.00043679245703969627, 'samples': 18560000, 'steps': 36249, 'loss/train': 1.5518146753311157}
-03/05/2022 08:04:38 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/05/2022 08:04:41 - INFO - codeparrot_training - Step 36250: {'lr': 0.00043678892995930685, 'samples': 18560512, 'steps': 36250, 'loss/train': 1.7710063457489014}
-03/05/2022 08:04:44 - INFO - codeparrot_training - Step 36251: {'lr': 0.00043678540279475314, 'samples': 18561024, 'steps': 36251, 'loss/train': 2.0098659992218018}
-03/05/2022 08:04:47 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 08:04:50 - INFO - codeparrot_training - Step 36252: {'lr': 0.0004367818755460369, 'samples': 18561536, 'steps': 36252, 'loss/train': 2.060177803039551}
-03/05/2022 08:04:53 - INFO - codeparrot_training - Step 36253: {'lr': 0.00043677834821315956, 'samples': 18562048, 'steps': 36253, 'loss/train': 2.0443012714385986}
-03/05/2022 08:04:55 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/05/2022 08:04:58 - INFO - codeparrot_training - Step 36254: {'lr': 0.00043677482079612276, 'samples': 18562560, 'steps': 36254, 'loss/train': 1.756696343421936}
-03/05/2022 08:05:01 - INFO - codeparrot_training - Step 36255: {'lr': 0.00043677129329492814, 'samples': 18563072, 'steps': 36255, 'loss/train': 1.474064588546753}
-03/05/2022 08:05:03 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/05/2022 08:05:06 - INFO - codeparrot_training - Step 36256: {'lr': 0.00043676776570957725, 'samples': 18563584, 'steps': 36256, 'loss/train': 1.7547359466552734}
-03/05/2022 08:05:10 - INFO - codeparrot_training - Step 36257: {'lr': 0.0004367642380400717, 'samples': 18564096, 'steps': 36257, 'loss/train': 2.2343010902404785}
-03/05/2022 08:05:12 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/05/2022 08:05:15 - INFO - codeparrot_training - Step 36258: {'lr': 0.0004367607102864131, 'samples': 18564608, 'steps': 36258, 'loss/train': 1.624328851699829}
-03/05/2022 08:05:18 - INFO - codeparrot_training - Step 36259: {'lr': 0.00043675718244860296, 'samples': 18565120, 'steps': 36259, 'loss/train': 1.786456823348999}
-03/05/2022 08:05:20 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/05/2022 08:05:23 - INFO - codeparrot_training - Step 36260: {'lr': 0.00043675365452664286, 'samples': 18565632, 'steps': 36260, 'loss/train': 1.4165698289871216}
-03/05/2022 08:05:26 - INFO - codeparrot_training - Step 36261: {'lr': 0.0004367501265205345, 'samples': 18566144, 'steps': 36261, 'loss/train': 2.088470935821533}
-03/05/2022 08:05:28 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/05/2022 08:05:32 - INFO - codeparrot_training - Step 36262: {'lr': 0.0004367465984302794, 'samples': 18566656, 'steps': 36262, 'loss/train': 1.8781400918960571}
-03/05/2022 08:05:35 - INFO - codeparrot_training - Step 36263: {'lr': 0.0004367430702558792, 'samples': 18567168, 'steps': 36263, 'loss/train': 1.334175705909729}
-03/05/2022 08:05:37 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/05/2022 08:05:40 - INFO - codeparrot_training - Step 36264: {'lr': 0.0004367395419973355, 'samples': 18567680, 'steps': 36264, 'loss/train': 1.8411093950271606}
-03/05/2022 08:05:43 - INFO - codeparrot_training - Step 36265: {'lr': 0.00043673601365464975, 'samples': 18568192, 'steps': 36265, 'loss/train': 1.7900177240371704}
-03/05/2022 08:05:45 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 08:05:49 - INFO - codeparrot_training - Step 36266: {'lr': 0.00043673248522782364, 'samples': 18568704, 'steps': 36266, 'loss/train': 1.3390437364578247}
-03/05/2022 08:05:52 - INFO - codeparrot_training - Step 36267: {'lr': 0.0004367289567168588, 'samples': 18569216, 'steps': 36267, 'loss/train': 2.2274889945983887}
-03/05/2022 08:05:53 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/05/2022 08:05:57 - INFO - codeparrot_training - Step 36268: {'lr': 0.00043672542812175675, 'samples': 18569728, 'steps': 36268, 'loss/train': 1.308266520500183}
-03/05/2022 08:06:00 - INFO - codeparrot_training - Step 36269: {'lr': 0.00043672189944251905, 'samples': 18570240, 'steps': 36269, 'loss/train': 1.2786180973052979}
-03/05/2022 08:06:01 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/05/2022 08:06:05 - INFO - codeparrot_training - Step 36270: {'lr': 0.0004367183706791474, 'samples': 18570752, 'steps': 36270, 'loss/train': 1.9468998908996582}
-03/05/2022 08:06:09 - INFO - codeparrot_training - Step 36271: {'lr': 0.0004367148418316434, 'samples': 18571264, 'steps': 36271, 'loss/train': 2.235231876373291}
-03/05/2022 08:06:10 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/05/2022 08:06:14 - INFO - codeparrot_training - Step 36272: {'lr': 0.0004367113129000085, 'samples': 18571776, 'steps': 36272, 'loss/train': 1.8377752304077148}
-03/05/2022 08:06:17 - INFO - codeparrot_training - Step 36273: {'lr': 0.00043670778388424434, 'samples': 18572288, 'steps': 36273, 'loss/train': 1.2235463857650757}
-03/05/2022 08:06:18 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 08:06:22 - INFO - codeparrot_training - Step 36274: {'lr': 0.00043670425478435263, 'samples': 18572800, 'steps': 36274, 'loss/train': 1.6768476963043213}
-03/05/2022 08:06:25 - INFO - codeparrot_training - Step 36275: {'lr': 0.00043670072560033474, 'samples': 18573312, 'steps': 36275, 'loss/train': 1.6523325443267822}
-03/05/2022 08:06:27 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 08:06:31 - INFO - codeparrot_training - Step 36276: {'lr': 0.00043669719633219247, 'samples': 18573824, 'steps': 36276, 'loss/train': 1.4076370000839233}
-03/05/2022 08:06:34 - INFO - codeparrot_training - Step 36277: {'lr': 0.0004366936669799273, 'samples': 18574336, 'steps': 36277, 'loss/train': 1.6886093616485596}
-03/05/2022 08:06:35 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/05/2022 08:06:39 - INFO - codeparrot_training - Step 36278: {'lr': 0.0004366901375435408, 'samples': 18574848, 'steps': 36278, 'loss/train': 2.163445234298706}
-03/05/2022 08:06:42 - INFO - codeparrot_training - Step 36279: {'lr': 0.0004366866080230347, 'samples': 18575360, 'steps': 36279, 'loss/train': 2.326011896133423}
-03/05/2022 08:06:43 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/05/2022 08:06:48 - INFO - codeparrot_training - Step 36280: {'lr': 0.0004366830784184104, 'samples': 18575872, 'steps': 36280, 'loss/train': 1.7870368957519531}
-03/05/2022 08:06:51 - INFO - codeparrot_training - Step 36281: {'lr': 0.00043667954872966965, 'samples': 18576384, 'steps': 36281, 'loss/train': 1.8372423648834229}
-03/05/2022 08:06:52 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/05/2022 08:06:56 - INFO - codeparrot_training - Step 36282: {'lr': 0.000436676018956814, 'samples': 18576896, 'steps': 36282, 'loss/train': 1.413135051727295}
-03/05/2022 08:06:59 - INFO - codeparrot_training - Step 36283: {'lr': 0.0004366724890998449, 'samples': 18577408, 'steps': 36283, 'loss/train': 1.738130807876587}
-03/05/2022 08:07:00 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 08:07:05 - INFO - codeparrot_training - Step 36284: {'lr': 0.00043666895915876416, 'samples': 18577920, 'steps': 36284, 'loss/train': 1.5071176290512085}
-03/05/2022 08:07:08 - INFO - codeparrot_training - Step 36285: {'lr': 0.0004366654291335732, 'samples': 18578432, 'steps': 36285, 'loss/train': 1.9544986486434937}
-03/05/2022 08:07:08 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/05/2022 08:07:13 - INFO - codeparrot_training - Step 36286: {'lr': 0.00043666189902427367, 'samples': 18578944, 'steps': 36286, 'loss/train': 1.8722658157348633}
-03/05/2022 08:07:16 - INFO - codeparrot_training - Step 36287: {'lr': 0.00043665836883086725, 'samples': 18579456, 'steps': 36287, 'loss/train': 1.608252763748169}
-03/05/2022 08:07:17 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/05/2022 08:07:21 - INFO - codeparrot_training - Step 36288: {'lr': 0.0004366548385533554, 'samples': 18579968, 'steps': 36288, 'loss/train': 1.3547999858856201}
-03/05/2022 08:07:24 - INFO - codeparrot_training - Step 36289: {'lr': 0.0004366513081917398, 'samples': 18580480, 'steps': 36289, 'loss/train': 0.4692898392677307}
-03/05/2022 08:07:25 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/05/2022 08:07:30 - INFO - codeparrot_training - Step 36290: {'lr': 0.00043664777774602196, 'samples': 18580992, 'steps': 36290, 'loss/train': 2.0046756267547607}
-03/05/2022 08:07:33 - INFO - codeparrot_training - Step 36291: {'lr': 0.00043664424721620354, 'samples': 18581504, 'steps': 36291, 'loss/train': 2.0737833976745605}
-03/05/2022 08:07:34 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/05/2022 08:07:38 - INFO - codeparrot_training - Step 36292: {'lr': 0.00043664071660228605, 'samples': 18582016, 'steps': 36292, 'loss/train': 1.5705592632293701}
-03/05/2022 08:07:41 - INFO - codeparrot_training - Step 36293: {'lr': 0.00043663718590427117, 'samples': 18582528, 'steps': 36293, 'loss/train': 1.6932003498077393}
-03/05/2022 08:07:42 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/05/2022 08:07:47 - INFO - codeparrot_training - Step 36294: {'lr': 0.0004366336551221605, 'samples': 18583040, 'steps': 36294, 'loss/train': 1.143328070640564}
-03/05/2022 08:07:50 - INFO - codeparrot_training - Step 36295: {'lr': 0.0004366301242559555, 'samples': 18583552, 'steps': 36295, 'loss/train': 1.4513932466506958}
-03/05/2022 08:07:51 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/05/2022 08:07:55 - INFO - codeparrot_training - Step 36296: {'lr': 0.00043662659330565793, 'samples': 18584064, 'steps': 36296, 'loss/train': 1.858394980430603}
-03/05/2022 08:07:58 - INFO - codeparrot_training - Step 36297: {'lr': 0.00043662306227126917, 'samples': 18584576, 'steps': 36297, 'loss/train': 1.4701273441314697}
-03/05/2022 08:07:59 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 08:08:04 - INFO - codeparrot_training - Step 36298: {'lr': 0.00043661953115279104, 'samples': 18585088, 'steps': 36298, 'loss/train': 1.7239980697631836}
-03/05/2022 08:08:07 - INFO - codeparrot_training - Step 36299: {'lr': 0.000436615999950225, 'samples': 18585600, 'steps': 36299, 'loss/train': 0.7496588826179504}
-03/05/2022 08:08:07 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/05/2022 08:08:12 - INFO - codeparrot_training - Step 36300: {'lr': 0.0004366124686635727, 'samples': 18586112, 'steps': 36300, 'loss/train': 1.3273167610168457}
-03/05/2022 08:08:15 - INFO - codeparrot_training - Step 36301: {'lr': 0.00043660893729283564, 'samples': 18586624, 'steps': 36301, 'loss/train': 1.5453933477401733}
-03/05/2022 08:08:15 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/05/2022 08:08:20 - INFO - codeparrot_training - Step 36302: {'lr': 0.0004366054058380155, 'samples': 18587136, 'steps': 36302, 'loss/train': 2.1349544525146484}
-03/05/2022 08:08:24 - INFO - codeparrot_training - Step 36303: {'lr': 0.0004366018742991139, 'samples': 18587648, 'steps': 36303, 'loss/train': 0.9301701188087463}
-03/05/2022 08:08:24 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/05/2022 08:08:29 - INFO - codeparrot_training - Step 36304: {'lr': 0.00043659834267613227, 'samples': 18588160, 'steps': 36304, 'loss/train': 0.515778660774231}
-03/05/2022 08:08:32 - INFO - codeparrot_training - Step 36305: {'lr': 0.0004365948109690724, 'samples': 18588672, 'steps': 36305, 'loss/train': 1.6533077955245972}
-03/05/2022 08:08:32 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/05/2022 08:08:37 - INFO - codeparrot_training - Step 36306: {'lr': 0.0004365912791779357, 'samples': 18589184, 'steps': 36306, 'loss/train': 1.8672386407852173}
-03/05/2022 08:08:40 - INFO - codeparrot_training - Step 36307: {'lr': 0.00043658774730272393, 'samples': 18589696, 'steps': 36307, 'loss/train': 1.7598237991333008}
-03/05/2022 08:08:40 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/05/2022 08:08:46 - INFO - codeparrot_training - Step 36308: {'lr': 0.00043658421534343856, 'samples': 18590208, 'steps': 36308, 'loss/train': 1.6849849224090576}
-03/05/2022 08:08:49 - INFO - codeparrot_training - Step 36309: {'lr': 0.0004365806833000813, 'samples': 18590720, 'steps': 36309, 'loss/train': 0.6293301582336426}
-03/05/2022 08:08:49 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/05/2022 08:08:54 - INFO - codeparrot_training - Step 36310: {'lr': 0.0004365771511726535, 'samples': 18591232, 'steps': 36310, 'loss/train': 2.0196645259857178}
-03/05/2022 08:08:57 - INFO - codeparrot_training - Step 36311: {'lr': 0.00043657361896115706, 'samples': 18591744, 'steps': 36311, 'loss/train': 1.78727126121521}
-03/05/2022 08:08:57 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/05/2022 08:09:03 - INFO - codeparrot_training - Step 36312: {'lr': 0.0004365700866655934, 'samples': 18592256, 'steps': 36312, 'loss/train': 1.4854425191879272}
-03/05/2022 08:09:06 - INFO - codeparrot_training - Step 36313: {'lr': 0.00043656655428596407, 'samples': 18592768, 'steps': 36313, 'loss/train': 0.8980157971382141}
-03/05/2022 08:09:06 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/05/2022 08:09:11 - INFO - codeparrot_training - Step 36314: {'lr': 0.0004365630218222708, 'samples': 18593280, 'steps': 36314, 'loss/train': 1.9378106594085693}
-03/05/2022 08:09:14 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/05/2022 08:09:16 - INFO - codeparrot_training - Step 36315: {'lr': 0.00043655948927451505, 'samples': 18593792, 'steps': 36315, 'loss/train': 2.2859151363372803}
-03/05/2022 08:09:20 - INFO - codeparrot_training - Step 36316: {'lr': 0.0004365559566426985, 'samples': 18594304, 'steps': 36316, 'loss/train': 1.8438653945922852}
-03/05/2022 08:09:22 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/05/2022 08:09:25 - INFO - codeparrot_training - Step 36317: {'lr': 0.0004365524239268227, 'samples': 18594816, 'steps': 36317, 'loss/train': 0.5921840071678162}
-03/05/2022 08:09:28 - INFO - codeparrot_training - Step 36318: {'lr': 0.00043654889112688933, 'samples': 18595328, 'steps': 36318, 'loss/train': 1.5405128002166748}
-03/05/2022 08:09:30 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/05/2022 08:09:33 - INFO - codeparrot_training - Step 36319: {'lr': 0.00043654535824289985, 'samples': 18595840, 'steps': 36319, 'loss/train': 1.8545513153076172}
-03/05/2022 08:09:36 - INFO - codeparrot_training - Step 36320: {'lr': 0.0004365418252748559, 'samples': 18596352, 'steps': 36320, 'loss/train': 1.483264684677124}
-03/05/2022 08:09:39 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/05/2022 08:09:42 - INFO - codeparrot_training - Step 36321: {'lr': 0.0004365382922227591, 'samples': 18596864, 'steps': 36321, 'loss/train': 1.6875332593917847}
-03/05/2022 08:09:45 - INFO - codeparrot_training - Step 36322: {'lr': 0.000436534759086611, 'samples': 18597376, 'steps': 36322, 'loss/train': 1.8684985637664795}
-03/05/2022 08:09:47 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/05/2022 08:09:51 - INFO - codeparrot_training - Step 36323: {'lr': 0.00043653122586641323, 'samples': 18597888, 'steps': 36323, 'loss/train': 1.4339921474456787}
-03/05/2022 08:09:54 - INFO - codeparrot_training - Step 36324: {'lr': 0.0004365276925621674, 'samples': 18598400, 'steps': 36324, 'loss/train': 1.404528260231018}
-03/05/2022 08:09:57 - INFO - codeparrot_training - Step 36325: {'lr': 0.0004365241591738751, 'samples': 18598912, 'steps': 36325, 'loss/train': 1.858699083328247}
-03/05/2022 08:09:57 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/05/2022 08:10:02 - INFO - codeparrot_training - Step 36326: {'lr': 0.0004365206257015378, 'samples': 18599424, 'steps': 36326, 'loss/train': 1.9349026679992676}
-03/05/2022 08:10:05 - INFO - codeparrot_training - Step 36327: {'lr': 0.0004365170921451572, 'samples': 18599936, 'steps': 36327, 'loss/train': 1.8397786617279053}
-03/05/2022 08:10:05 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/05/2022 08:10:11 - INFO - codeparrot_training - Step 36328: {'lr': 0.00043651355850473495, 'samples': 18600448, 'steps': 36328, 'loss/train': 0.9702200889587402}
-03/05/2022 08:10:14 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/05/2022 08:10:16 - INFO - codeparrot_training - Step 36329: {'lr': 0.0004365100247802725, 'samples': 18600960, 'steps': 36329, 'loss/train': 1.6092218160629272}
-03/05/2022 08:10:19 - INFO - codeparrot_training - Step 36330: {'lr': 0.0004365064909717715, 'samples': 18601472, 'steps': 36330, 'loss/train': 2.0911831855773926}
-03/05/2022 08:10:22 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/05/2022 08:10:24 - INFO - codeparrot_training - Step 36331: {'lr': 0.0004365029570792336, 'samples': 18601984, 'steps': 36331, 'loss/train': 2.138514518737793}
-03/05/2022 08:10:28 - INFO - codeparrot_training - Step 36332: {'lr': 0.00043649942310266035, 'samples': 18602496, 'steps': 36332, 'loss/train': 1.4679571390151978}
-03/05/2022 08:10:30 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 08:10:33 - INFO - codeparrot_training - Step 36333: {'lr': 0.00043649588904205326, 'samples': 18603008, 'steps': 36333, 'loss/train': 1.8132022619247437}
-03/05/2022 08:10:36 - INFO - codeparrot_training - Step 36334: {'lr': 0.0004364923548974141, 'samples': 18603520, 'steps': 36334, 'loss/train': 1.5014220476150513}
-03/05/2022 08:10:38 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/05/2022 08:10:41 - INFO - codeparrot_training - Step 36335: {'lr': 0.0004364888206687443, 'samples': 18604032, 'steps': 36335, 'loss/train': 2.2461609840393066}
-03/05/2022 08:10:44 - INFO - codeparrot_training - Step 36336: {'lr': 0.00043648528635604556, 'samples': 18604544, 'steps': 36336, 'loss/train': 1.0545272827148438}
-03/05/2022 08:10:47 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/05/2022 08:10:50 - INFO - codeparrot_training - Step 36337: {'lr': 0.00043648175195931937, 'samples': 18605056, 'steps': 36337, 'loss/train': 1.5806584358215332}
-03/05/2022 08:10:53 - INFO - codeparrot_training - Step 36338: {'lr': 0.0004364782174785674, 'samples': 18605568, 'steps': 36338, 'loss/train': 1.6582310199737549}
-03/05/2022 08:10:55 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/05/2022 08:10:58 - INFO - codeparrot_training - Step 36339: {'lr': 0.0004364746829137912, 'samples': 18606080, 'steps': 36339, 'loss/train': 2.021883726119995}
-03/05/2022 08:11:01 - INFO - codeparrot_training - Step 36340: {'lr': 0.0004364711482649925, 'samples': 18606592, 'steps': 36340, 'loss/train': 3.045445680618286}
-03/05/2022 08:11:05 - INFO - codeparrot_training - Step 36341: {'lr': 0.00043646761353217266, 'samples': 18607104, 'steps': 36341, 'loss/train': 1.5278230905532837}
-03/05/2022 08:11:05 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 08:11:10 - INFO - codeparrot_training - Step 36342: {'lr': 0.0004364640787153334, 'samples': 18607616, 'steps': 36342, 'loss/train': 2.2994656562805176}
-03/05/2022 08:11:13 - INFO - codeparrot_training - Step 36343: {'lr': 0.0004364605438144764, 'samples': 18608128, 'steps': 36343, 'loss/train': 2.1982994079589844}
-03/05/2022 08:11:13 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 08:11:19 - INFO - codeparrot_training - Step 36344: {'lr': 0.000436457008829603, 'samples': 18608640, 'steps': 36344, 'loss/train': 1.7848387956619263}
-03/05/2022 08:11:22 - INFO - codeparrot_training - Step 36345: {'lr': 0.00043645347376071507, 'samples': 18609152, 'steps': 36345, 'loss/train': 1.7005219459533691}
-03/05/2022 08:11:22 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 08:11:27 - INFO - codeparrot_training - Step 36346: {'lr': 0.0004364499386078141, 'samples': 18609664, 'steps': 36346, 'loss/train': 0.48749107122421265}
-03/05/2022 08:11:30 - INFO - codeparrot_training - Step 36347: {'lr': 0.00043644640337090157, 'samples': 18610176, 'steps': 36347, 'loss/train': 1.3196015357971191}
-03/05/2022 08:11:31 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 08:11:36 - INFO - codeparrot_training - Step 36348: {'lr': 0.0004364428680499792, 'samples': 18610688, 'steps': 36348, 'loss/train': 1.7109352350234985}
-03/05/2022 08:11:39 - INFO - codeparrot_training - Step 36349: {'lr': 0.0004364393326450486, 'samples': 18611200, 'steps': 36349, 'loss/train': 0.6692292094230652}
-03/05/2022 08:11:40 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/05/2022 08:11:44 - INFO - codeparrot_training - Step 36350: {'lr': 0.00043643579715611124, 'samples': 18611712, 'steps': 36350, 'loss/train': 1.216480016708374}
-03/05/2022 08:11:47 - INFO - codeparrot_training - Step 36351: {'lr': 0.00043643226158316886, 'samples': 18612224, 'steps': 36351, 'loss/train': 1.5163134336471558}
-03/05/2022 08:11:48 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/05/2022 08:11:53 - INFO - codeparrot_training - Step 36352: {'lr': 0.00043642872592622293, 'samples': 18612736, 'steps': 36352, 'loss/train': 1.9495559930801392}
-03/05/2022 08:11:56 - INFO - codeparrot_training - Step 36353: {'lr': 0.0004364251901852751, 'samples': 18613248, 'steps': 36353, 'loss/train': 1.3938871622085571}
-03/05/2022 08:11:57 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/05/2022 08:12:01 - INFO - codeparrot_training - Step 36354: {'lr': 0.000436421654360327, 'samples': 18613760, 'steps': 36354, 'loss/train': 1.9398480653762817}
-03/05/2022 08:12:04 - INFO - codeparrot_training - Step 36355: {'lr': 0.00043641811845138016, 'samples': 18614272, 'steps': 36355, 'loss/train': 1.7702665328979492}
-03/05/2022 08:12:05 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/05/2022 08:12:10 - INFO - codeparrot_training - Step 36356: {'lr': 0.0004364145824584361, 'samples': 18614784, 'steps': 36356, 'loss/train': 1.406023383140564}
-03/05/2022 08:12:13 - INFO - codeparrot_training - Step 36357: {'lr': 0.00043641104638149656, 'samples': 18615296, 'steps': 36357, 'loss/train': 1.6168336868286133}
-03/05/2022 08:12:13 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/05/2022 08:12:18 - INFO - codeparrot_training - Step 36358: {'lr': 0.00043640751022056316, 'samples': 18615808, 'steps': 36358, 'loss/train': 0.1653549075126648}
-03/05/2022 08:12:21 - INFO - codeparrot_training - Step 36359: {'lr': 0.00043640397397563737, 'samples': 18616320, 'steps': 36359, 'loss/train': 1.7235809564590454}
-03/05/2022 08:12:22 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/05/2022 08:12:27 - INFO - codeparrot_training - Step 36360: {'lr': 0.00043640043764672077, 'samples': 18616832, 'steps': 36360, 'loss/train': 2.0967001914978027}
-03/05/2022 08:12:30 - INFO - codeparrot_training - Step 36361: {'lr': 0.00043639690123381503, 'samples': 18617344, 'steps': 36361, 'loss/train': 1.8273653984069824}
-03/05/2022 08:12:30 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/05/2022 08:12:35 - INFO - codeparrot_training - Step 36362: {'lr': 0.00043639336473692174, 'samples': 18617856, 'steps': 36362, 'loss/train': 1.6305148601531982}
-03/05/2022 08:12:38 - INFO - codeparrot_training - Step 36363: {'lr': 0.00043638982815604247, 'samples': 18618368, 'steps': 36363, 'loss/train': 1.1789758205413818}
-03/05/2022 08:12:39 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/05/2022 08:12:44 - INFO - codeparrot_training - Step 36364: {'lr': 0.00043638629149117883, 'samples': 18618880, 'steps': 36364, 'loss/train': 0.12033513933420181}
-03/05/2022 08:12:47 - INFO - codeparrot_training - Step 36365: {'lr': 0.0004363827547423324, 'samples': 18619392, 'steps': 36365, 'loss/train': 1.8419135808944702}
-03/05/2022 08:12:47 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/05/2022 08:12:52 - INFO - codeparrot_training - Step 36366: {'lr': 0.00043637921790950476, 'samples': 18619904, 'steps': 36366, 'loss/train': 1.9991563558578491}
-03/05/2022 08:12:55 - INFO - codeparrot_training - Step 36367: {'lr': 0.00043637568099269753, 'samples': 18620416, 'steps': 36367, 'loss/train': 1.2050448656082153}
-03/05/2022 08:12:55 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 08:13:01 - INFO - codeparrot_training - Step 36368: {'lr': 0.00043637214399191234, 'samples': 18620928, 'steps': 36368, 'loss/train': 0.7002370953559875}
-03/05/2022 08:13:04 - INFO - codeparrot_training - Step 36369: {'lr': 0.00043636860690715064, 'samples': 18621440, 'steps': 36369, 'loss/train': 1.7460111379623413}
-03/05/2022 08:13:04 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/05/2022 08:13:09 - INFO - codeparrot_training - Step 36370: {'lr': 0.00043636506973841424, 'samples': 18621952, 'steps': 36370, 'loss/train': 1.8994289636611938}
-03/05/2022 08:13:12 - INFO - codeparrot_training - Step 36371: {'lr': 0.00043636153248570453, 'samples': 18622464, 'steps': 36371, 'loss/train': 1.7057499885559082}
-03/05/2022 08:13:13 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/05/2022 08:13:18 - INFO - codeparrot_training - Step 36372: {'lr': 0.0004363579951490232, 'samples': 18622976, 'steps': 36372, 'loss/train': 1.9976303577423096}
-03/05/2022 08:13:21 - INFO - codeparrot_training - Step 36373: {'lr': 0.0004363544577283718, 'samples': 18623488, 'steps': 36373, 'loss/train': 1.1317470073699951}
-03/05/2022 08:13:21 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/05/2022 08:13:26 - INFO - codeparrot_training - Step 36374: {'lr': 0.0004363509202237521, 'samples': 18624000, 'steps': 36374, 'loss/train': 1.1167805194854736}
-03/05/2022 08:13:30 - INFO - codeparrot_training - Step 36375: {'lr': 0.0004363473826351654, 'samples': 18624512, 'steps': 36375, 'loss/train': 1.3876641988754272}
-03/05/2022 08:13:30 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/05/2022 08:13:35 - INFO - codeparrot_training - Step 36376: {'lr': 0.0004363438449626135, 'samples': 18625024, 'steps': 36376, 'loss/train': 1.874290943145752}
-03/05/2022 08:13:38 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/05/2022 08:13:40 - INFO - codeparrot_training - Step 36377: {'lr': 0.000436340307206098, 'samples': 18625536, 'steps': 36377, 'loss/train': 1.3832041025161743}
-03/05/2022 08:13:43 - INFO - codeparrot_training - Step 36378: {'lr': 0.00043633676936562026, 'samples': 18626048, 'steps': 36378, 'loss/train': 1.6721936464309692}
-03/05/2022 08:13:46 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/05/2022 08:13:49 - INFO - codeparrot_training - Step 36379: {'lr': 0.0004363332314411822, 'samples': 18626560, 'steps': 36379, 'loss/train': 1.7718744277954102}
-03/05/2022 08:13:52 - INFO - codeparrot_training - Step 36380: {'lr': 0.0004363296934327852, 'samples': 18627072, 'steps': 36380, 'loss/train': 1.2038774490356445}
-03/05/2022 08:13:55 - INFO - codeparrot_training - Step 36381: {'lr': 0.00043632615534043096, 'samples': 18627584, 'steps': 36381, 'loss/train': 1.9615819454193115}
-03/05/2022 08:13:55 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/05/2022 08:14:01 - INFO - codeparrot_training - Step 36382: {'lr': 0.00043632261716412097, 'samples': 18628096, 'steps': 36382, 'loss/train': 2.1924550533294678}
-03/05/2022 08:14:04 - INFO - codeparrot_training - Step 36383: {'lr': 0.0004363190789038569, 'samples': 18628608, 'steps': 36383, 'loss/train': 0.7029555439949036}
-03/05/2022 08:14:04 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/05/2022 08:14:09 - INFO - codeparrot_training - Step 36384: {'lr': 0.0004363155405596404, 'samples': 18629120, 'steps': 36384, 'loss/train': 1.7869279384613037}
-03/05/2022 08:14:12 - INFO - codeparrot_training - Step 36385: {'lr': 0.00043631200213147296, 'samples': 18629632, 'steps': 36385, 'loss/train': 2.1007018089294434}
-03/05/2022 08:14:13 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/05/2022 08:14:18 - INFO - codeparrot_training - Step 36386: {'lr': 0.0004363084636193561, 'samples': 18630144, 'steps': 36386, 'loss/train': 1.021134614944458}
-03/05/2022 08:14:21 - INFO - codeparrot_training - Step 36387: {'lr': 0.0004363049250232917, 'samples': 18630656, 'steps': 36387, 'loss/train': 1.9525604248046875}
-03/05/2022 08:14:21 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/05/2022 08:14:26 - INFO - codeparrot_training - Step 36388: {'lr': 0.000436301386343281, 'samples': 18631168, 'steps': 36388, 'loss/train': 1.8891663551330566}
-03/05/2022 08:14:29 - INFO - codeparrot_training - Step 36389: {'lr': 0.0004362978475793259, 'samples': 18631680, 'steps': 36389, 'loss/train': 1.3433079719543457}
-03/05/2022 08:14:35 - INFO - codeparrot_training - Step 36390: {'lr': 0.00043629430873142773, 'samples': 18632192, 'steps': 36390, 'loss/train': 1.395236849784851}
-03/05/2022 08:14:38 - INFO - codeparrot_training - Step 36391: {'lr': 0.00043629076979958837, 'samples': 18632704, 'steps': 36391, 'loss/train': 2.234822988510132}
-03/05/2022 08:14:38 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/05/2022 08:14:43 - INFO - codeparrot_training - Step 36392: {'lr': 0.00043628723078380916, 'samples': 18633216, 'steps': 36392, 'loss/train': 1.5440551042556763}
-03/05/2022 08:14:46 - INFO - codeparrot_training - Step 36393: {'lr': 0.0004362836916840919, 'samples': 18633728, 'steps': 36393, 'loss/train': 1.6897200345993042}
-03/05/2022 08:14:46 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/05/2022 08:14:51 - INFO - codeparrot_training - Step 36394: {'lr': 0.00043628015250043794, 'samples': 18634240, 'steps': 36394, 'loss/train': 2.107179880142212}
-03/05/2022 08:14:55 - INFO - codeparrot_training - Step 36395: {'lr': 0.00043627661323284914, 'samples': 18634752, 'steps': 36395, 'loss/train': 1.2568882703781128}
-03/05/2022 08:14:55 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/05/2022 08:15:00 - INFO - codeparrot_training - Step 36396: {'lr': 0.00043627307388132693, 'samples': 18635264, 'steps': 36396, 'loss/train': 0.2920355796813965}
-03/05/2022 08:15:04 - INFO - codeparrot_training - Step 36397: {'lr': 0.0004362695344458729, 'samples': 18635776, 'steps': 36397, 'loss/train': 1.8889368772506714}
-03/05/2022 08:15:06 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/05/2022 08:15:09 - INFO - codeparrot_training - Step 36398: {'lr': 0.00043626599492648877, 'samples': 18636288, 'steps': 36398, 'loss/train': 1.6631898880004883}
-03/05/2022 08:15:12 - INFO - codeparrot_training - Step 36399: {'lr': 0.000436262455323176, 'samples': 18636800, 'steps': 36399, 'loss/train': 0.8209893107414246}
-03/05/2022 08:15:15 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/05/2022 08:15:17 - INFO - codeparrot_training - Step 36400: {'lr': 0.0004362589156359363, 'samples': 18637312, 'steps': 36400, 'loss/train': 1.342013955116272}
-03/05/2022 08:15:21 - INFO - codeparrot_training - Step 36401: {'lr': 0.00043625537586477114, 'samples': 18637824, 'steps': 36401, 'loss/train': 1.9050298929214478}
-03/05/2022 08:15:23 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/05/2022 08:15:26 - INFO - codeparrot_training - Step 36402: {'lr': 0.00043625183600968224, 'samples': 18638336, 'steps': 36402, 'loss/train': 1.2861864566802979}
-03/05/2022 08:15:29 - INFO - codeparrot_training - Step 36403: {'lr': 0.00043624829607067105, 'samples': 18638848, 'steps': 36403, 'loss/train': 3.06931209564209}
-03/05/2022 08:15:31 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 08:15:34 - INFO - codeparrot_training - Step 36404: {'lr': 0.0004362447560477394, 'samples': 18639360, 'steps': 36404, 'loss/train': 1.612502098083496}
-03/05/2022 08:15:38 - INFO - codeparrot_training - Step 36405: {'lr': 0.0004362412159408886, 'samples': 18639872, 'steps': 36405, 'loss/train': 2.355491876602173}
-03/05/2022 08:15:39 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/05/2022 08:15:43 - INFO - codeparrot_training - Step 36406: {'lr': 0.0004362376757501205, 'samples': 18640384, 'steps': 36406, 'loss/train': 1.8124324083328247}
-03/05/2022 08:15:46 - INFO - codeparrot_training - Step 36407: {'lr': 0.00043623413547543645, 'samples': 18640896, 'steps': 36407, 'loss/train': 2.078056812286377}
-03/05/2022 08:15:48 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/05/2022 08:15:51 - INFO - codeparrot_training - Step 36408: {'lr': 0.00043623059511683826, 'samples': 18641408, 'steps': 36408, 'loss/train': 1.318961501121521}
-03/05/2022 08:15:54 - INFO - codeparrot_training - Step 36409: {'lr': 0.0004362270546743274, 'samples': 18641920, 'steps': 36409, 'loss/train': 1.718108892440796}
-03/05/2022 08:15:56 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/05/2022 08:16:00 - INFO - codeparrot_training - Step 36410: {'lr': 0.0004362235141479055, 'samples': 18642432, 'steps': 36410, 'loss/train': 1.808218002319336}
-03/05/2022 08:16:03 - INFO - codeparrot_training - Step 36411: {'lr': 0.0004362199735375742, 'samples': 18642944, 'steps': 36411, 'loss/train': 1.0177865028381348}
-03/05/2022 08:16:04 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/05/2022 08:16:08 - INFO - codeparrot_training - Step 36412: {'lr': 0.000436216432843335, 'samples': 18643456, 'steps': 36412, 'loss/train': 1.6219316720962524}
-03/05/2022 08:16:11 - INFO - codeparrot_training - Step 36413: {'lr': 0.00043621289206518957, 'samples': 18643968, 'steps': 36413, 'loss/train': 2.119952917098999}
-03/05/2022 08:16:12 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/05/2022 08:16:17 - INFO - codeparrot_training - Step 36414: {'lr': 0.00043620935120313955, 'samples': 18644480, 'steps': 36414, 'loss/train': 2.138293981552124}
-03/05/2022 08:16:20 - INFO - codeparrot_training - Step 36415: {'lr': 0.0004362058102571864, 'samples': 18644992, 'steps': 36415, 'loss/train': 1.6566400527954102}
-03/05/2022 08:16:23 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 08:16:25 - INFO - codeparrot_training - Step 36416: {'lr': 0.00043620226922733174, 'samples': 18645504, 'steps': 36416, 'loss/train': 1.754294991493225}
-03/05/2022 08:16:28 - INFO - codeparrot_training - Step 36417: {'lr': 0.0004361987281135773, 'samples': 18646016, 'steps': 36417, 'loss/train': 1.889129877090454}
-03/05/2022 08:16:31 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/05/2022 08:16:34 - INFO - codeparrot_training - Step 36418: {'lr': 0.00043619518691592453, 'samples': 18646528, 'steps': 36418, 'loss/train': 1.7421029806137085}
-03/05/2022 08:16:37 - INFO - codeparrot_training - Step 36419: {'lr': 0.00043619164563437506, 'samples': 18647040, 'steps': 36419, 'loss/train': 2.045658826828003}
-03/05/2022 08:16:39 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/05/2022 08:16:42 - INFO - codeparrot_training - Step 36420: {'lr': 0.0004361881042689306, 'samples': 18647552, 'steps': 36420, 'loss/train': 1.760764241218567}
-03/05/2022 08:16:45 - INFO - codeparrot_training - Step 36421: {'lr': 0.00043618456281959263, 'samples': 18648064, 'steps': 36421, 'loss/train': 1.3869388103485107}
-03/05/2022 08:16:48 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/05/2022 08:16:50 - INFO - codeparrot_training - Step 36422: {'lr': 0.0004361810212863627, 'samples': 18648576, 'steps': 36422, 'loss/train': 2.0745608806610107}
-03/05/2022 08:16:54 - INFO - codeparrot_training - Step 36423: {'lr': 0.0004361774796692425, 'samples': 18649088, 'steps': 36423, 'loss/train': 1.7216525077819824}
-03/05/2022 08:16:56 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/05/2022 08:16:59 - INFO - codeparrot_training - Step 36424: {'lr': 0.00043617393796823367, 'samples': 18649600, 'steps': 36424, 'loss/train': 2.081608533859253}
-03/05/2022 08:17:03 - INFO - codeparrot_training - Step 36425: {'lr': 0.00043617039618333765, 'samples': 18650112, 'steps': 36425, 'loss/train': 1.8802214860916138}
-03/05/2022 08:17:06 - INFO - codeparrot_training - Step 36426: {'lr': 0.00043616685431455615, 'samples': 18650624, 'steps': 36426, 'loss/train': 0.8684747219085693}
-03/05/2022 08:17:06 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/05/2022 08:17:11 - INFO - codeparrot_training - Step 36427: {'lr': 0.0004361633123618908, 'samples': 18651136, 'steps': 36427, 'loss/train': 1.3209688663482666}
-03/05/2022 08:17:14 - INFO - codeparrot_training - Step 36428: {'lr': 0.00043615977032534305, 'samples': 18651648, 'steps': 36428, 'loss/train': 1.95578134059906}
-03/05/2022 08:17:15 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/05/2022 08:17:19 - INFO - codeparrot_training - Step 36429: {'lr': 0.00043615622820491464, 'samples': 18652160, 'steps': 36429, 'loss/train': 0.7057967782020569}
-03/05/2022 08:17:23 - INFO - codeparrot_training - Step 36430: {'lr': 0.00043615268600060705, 'samples': 18652672, 'steps': 36430, 'loss/train': 1.0346256494522095}
-03/05/2022 08:17:23 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 08:17:28 - INFO - codeparrot_training - Step 36431: {'lr': 0.000436149143712422, 'samples': 18653184, 'steps': 36431, 'loss/train': 2.3508975505828857}
-03/05/2022 08:17:31 - INFO - codeparrot_training - Step 36432: {'lr': 0.0004361456013403609, 'samples': 18653696, 'steps': 36432, 'loss/train': 2.1107289791107178}
-03/05/2022 08:17:31 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/05/2022 08:17:36 - INFO - codeparrot_training - Step 36433: {'lr': 0.00043614205888442553, 'samples': 18654208, 'steps': 36433, 'loss/train': 1.9675672054290771}
-03/05/2022 08:17:40 - INFO - codeparrot_training - Step 36434: {'lr': 0.00043613851634461743, 'samples': 18654720, 'steps': 36434, 'loss/train': 1.5066264867782593}
-03/05/2022 08:17:40 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/05/2022 08:17:45 - INFO - codeparrot_training - Step 36435: {'lr': 0.00043613497372093827, 'samples': 18655232, 'steps': 36435, 'loss/train': 1.3592115640640259}
-03/05/2022 08:17:48 - INFO - codeparrot_training - Step 36436: {'lr': 0.0004361314310133894, 'samples': 18655744, 'steps': 36436, 'loss/train': 1.8794151544570923}
-03/05/2022 08:17:48 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/05/2022 08:17:53 - INFO - codeparrot_training - Step 36437: {'lr': 0.00043612788822197266, 'samples': 18656256, 'steps': 36437, 'loss/train': 0.9860595464706421}
-03/05/2022 08:17:56 - INFO - codeparrot_training - Step 36438: {'lr': 0.0004361243453466896, 'samples': 18656768, 'steps': 36438, 'loss/train': 2.216850996017456}
-03/05/2022 08:17:56 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 08:18:02 - INFO - codeparrot_training - Step 36439: {'lr': 0.0004361208023875417, 'samples': 18657280, 'steps': 36439, 'loss/train': 1.891960859298706}
-03/05/2022 08:18:05 - INFO - codeparrot_training - Step 36440: {'lr': 0.00043611725934453074, 'samples': 18657792, 'steps': 36440, 'loss/train': 1.984387755393982}
-03/05/2022 08:18:05 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/05/2022 08:18:10 - INFO - codeparrot_training - Step 36441: {'lr': 0.00043611371621765817, 'samples': 18658304, 'steps': 36441, 'loss/train': 2.078974723815918}
-03/05/2022 08:18:13 - INFO - codeparrot_training - Step 36442: {'lr': 0.0004361101730069256, 'samples': 18658816, 'steps': 36442, 'loss/train': 2.079745292663574}
-03/05/2022 08:18:14 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/05/2022 08:18:19 - INFO - codeparrot_training - Step 36443: {'lr': 0.00043610662971233465, 'samples': 18659328, 'steps': 36443, 'loss/train': 2.5560784339904785}
-03/05/2022 08:18:22 - INFO - codeparrot_training - Step 36444: {'lr': 0.00043610308633388695, 'samples': 18659840, 'steps': 36444, 'loss/train': 1.658698320388794}
-03/05/2022 08:18:22 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/05/2022 08:18:27 - INFO - codeparrot_training - Step 36445: {'lr': 0.0004360995428715841, 'samples': 18660352, 'steps': 36445, 'loss/train': 1.7069393396377563}
-03/05/2022 08:18:31 - INFO - codeparrot_training - Step 36446: {'lr': 0.00043609599932542764, 'samples': 18660864, 'steps': 36446, 'loss/train': 1.7503266334533691}
-03/05/2022 08:18:31 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 08:18:36 - INFO - codeparrot_training - Step 36447: {'lr': 0.00043609245569541924, 'samples': 18661376, 'steps': 36447, 'loss/train': 2.0942459106445312}
-03/05/2022 08:18:39 - INFO - codeparrot_training - Step 36448: {'lr': 0.00043608891198156037, 'samples': 18661888, 'steps': 36448, 'loss/train': 2.0832314491271973}
-03/05/2022 08:18:40 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/05/2022 08:18:44 - INFO - codeparrot_training - Step 36449: {'lr': 0.0004360853681838528, 'samples': 18662400, 'steps': 36449, 'loss/train': 2.1019678115844727}
-03/05/2022 08:18:48 - INFO - codeparrot_training - Step 36450: {'lr': 0.0004360818243022979, 'samples': 18662912, 'steps': 36450, 'loss/train': 1.008339762687683}
-03/05/2022 08:18:48 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/05/2022 08:18:53 - INFO - codeparrot_training - Step 36451: {'lr': 0.00043607828033689753, 'samples': 18663424, 'steps': 36451, 'loss/train': 2.0179286003112793}
-03/05/2022 08:18:56 - INFO - codeparrot_training - Step 36452: {'lr': 0.000436074736287653, 'samples': 18663936, 'steps': 36452, 'loss/train': 1.8818203210830688}
-03/05/2022 08:18:56 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/05/2022 08:19:01 - INFO - codeparrot_training - Step 36453: {'lr': 0.00043607119215456625, 'samples': 18664448, 'steps': 36453, 'loss/train': 1.5660171508789062}
-03/05/2022 08:19:05 - INFO - codeparrot_training - Step 36454: {'lr': 0.00043606764793763865, 'samples': 18664960, 'steps': 36454, 'loss/train': 2.4266164302825928}
-03/05/2022 08:19:05 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/05/2022 08:19:10 - INFO - codeparrot_training - Step 36455: {'lr': 0.00043606410363687177, 'samples': 18665472, 'steps': 36455, 'loss/train': 1.7144031524658203}
-03/05/2022 08:19:13 - INFO - codeparrot_training - Step 36456: {'lr': 0.00043606055925226727, 'samples': 18665984, 'steps': 36456, 'loss/train': 1.6253248453140259}
-03/05/2022 08:19:13 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/05/2022 08:19:18 - INFO - codeparrot_training - Step 36457: {'lr': 0.0004360570147838269, 'samples': 18666496, 'steps': 36457, 'loss/train': 1.2984052896499634}
-03/05/2022 08:19:21 - INFO - codeparrot_training - Step 36458: {'lr': 0.00043605347023155193, 'samples': 18667008, 'steps': 36458, 'loss/train': 1.856462836265564}
-03/05/2022 08:19:21 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 08:19:27 - INFO - codeparrot_training - Step 36459: {'lr': 0.0004360499255954442, 'samples': 18667520, 'steps': 36459, 'loss/train': 2.132575273513794}
-03/05/2022 08:19:30 - INFO - codeparrot_training - Step 36460: {'lr': 0.0004360463808755053, 'samples': 18668032, 'steps': 36460, 'loss/train': 1.800743579864502}
-03/05/2022 08:19:31 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/05/2022 08:19:35 - INFO - codeparrot_training - Step 36461: {'lr': 0.00043604283607173673, 'samples': 18668544, 'steps': 36461, 'loss/train': 2.295856237411499}
-03/05/2022 08:19:39 - INFO - codeparrot_training - Step 36462: {'lr': 0.0004360392911841401, 'samples': 18669056, 'steps': 36462, 'loss/train': 2.181933879852295}
-03/05/2022 08:19:39 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 08:19:44 - INFO - codeparrot_training - Step 36463: {'lr': 0.0004360357462127171, 'samples': 18669568, 'steps': 36463, 'loss/train': 2.0423195362091064}
-03/05/2022 08:19:47 - INFO - codeparrot_training - Step 36464: {'lr': 0.0004360322011574692, 'samples': 18670080, 'steps': 36464, 'loss/train': 1.2879196405410767}
-03/05/2022 08:19:48 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/05/2022 08:19:52 - INFO - codeparrot_training - Step 36465: {'lr': 0.00043602865601839817, 'samples': 18670592, 'steps': 36465, 'loss/train': 2.839481830596924}
-03/05/2022 08:19:56 - INFO - codeparrot_training - Step 36466: {'lr': 0.00043602511079550535, 'samples': 18671104, 'steps': 36466, 'loss/train': 1.4449669122695923}
-03/05/2022 08:19:56 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/05/2022 08:20:01 - INFO - codeparrot_training - Step 36467: {'lr': 0.0004360215654887926, 'samples': 18671616, 'steps': 36467, 'loss/train': 0.723706066608429}
-03/05/2022 08:20:04 - INFO - codeparrot_training - Step 36468: {'lr': 0.0004360180200982613, 'samples': 18672128, 'steps': 36468, 'loss/train': 2.1930384635925293}
-03/05/2022 08:20:04 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/05/2022 08:20:09 - INFO - codeparrot_training - Step 36469: {'lr': 0.00043601447462391317, 'samples': 18672640, 'steps': 36469, 'loss/train': 0.9871241450309753}
-03/05/2022 08:20:12 - INFO - codeparrot_training - Step 36470: {'lr': 0.00043601092906574986, 'samples': 18673152, 'steps': 36470, 'loss/train': 1.6151540279388428}
-03/05/2022 08:20:13 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/05/2022 08:20:18 - INFO - codeparrot_training - Step 36471: {'lr': 0.0004360073834237729, 'samples': 18673664, 'steps': 36471, 'loss/train': 2.4731557369232178}
-03/05/2022 08:20:21 - INFO - codeparrot_training - Step 36472: {'lr': 0.0004360038376979838, 'samples': 18674176, 'steps': 36472, 'loss/train': 1.1814765930175781}
-03/05/2022 08:20:21 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/05/2022 08:20:26 - INFO - codeparrot_training - Step 36473: {'lr': 0.0004360002918883843, 'samples': 18674688, 'steps': 36473, 'loss/train': 2.267200469970703}
-03/05/2022 08:20:29 - INFO - codeparrot_training - Step 36474: {'lr': 0.00043599674599497593, 'samples': 18675200, 'steps': 36474, 'loss/train': 1.9048576354980469}
-03/05/2022 08:20:29 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/05/2022 08:20:35 - INFO - codeparrot_training - Step 36475: {'lr': 0.00043599320001776025, 'samples': 18675712, 'steps': 36475, 'loss/train': 1.8426743745803833}
-03/05/2022 08:20:38 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/05/2022 08:20:40 - INFO - codeparrot_training - Step 36476: {'lr': 0.00043598965395673893, 'samples': 18676224, 'steps': 36476, 'loss/train': 0.9498752355575562}
-03/05/2022 08:20:43 - INFO - codeparrot_training - Step 36477: {'lr': 0.0004359861078119136, 'samples': 18676736, 'steps': 36477, 'loss/train': 2.2847163677215576}
-03/05/2022 08:20:46 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/05/2022 08:20:48 - INFO - codeparrot_training - Step 36478: {'lr': 0.00043598256158328575, 'samples': 18677248, 'steps': 36478, 'loss/train': 2.398782968521118}
-03/05/2022 08:20:52 - INFO - codeparrot_training - Step 36479: {'lr': 0.00043597901527085703, 'samples': 18677760, 'steps': 36479, 'loss/train': 2.351871967315674}
-03/05/2022 08:20:54 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/05/2022 08:20:57 - INFO - codeparrot_training - Step 36480: {'lr': 0.000435975468874629, 'samples': 18678272, 'steps': 36480, 'loss/train': 2.591935396194458}
-03/05/2022 08:21:00 - INFO - codeparrot_training - Step 36481: {'lr': 0.00043597192239460336, 'samples': 18678784, 'steps': 36481, 'loss/train': 1.418365716934204}
-03/05/2022 08:21:03 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 08:21:05 - INFO - codeparrot_training - Step 36482: {'lr': 0.00043596837583078165, 'samples': 18679296, 'steps': 36482, 'loss/train': 1.7946773767471313}
-03/05/2022 08:21:09 - INFO - codeparrot_training - Step 36483: {'lr': 0.0004359648291831654, 'samples': 18679808, 'steps': 36483, 'loss/train': 2.006937026977539}
-03/05/2022 08:21:11 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/05/2022 08:21:14 - INFO - codeparrot_training - Step 36484: {'lr': 0.0004359612824517563, 'samples': 18680320, 'steps': 36484, 'loss/train': 1.4025856256484985}
-03/05/2022 08:21:17 - INFO - codeparrot_training - Step 36485: {'lr': 0.0004359577356365559, 'samples': 18680832, 'steps': 36485, 'loss/train': 1.3273124694824219}
-03/05/2022 08:21:20 - INFO - codeparrot_training - Step 36486: {'lr': 0.00043595418873756584, 'samples': 18681344, 'steps': 36486, 'loss/train': 2.4480807781219482}
-03/05/2022 08:21:21 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/05/2022 08:21:26 - INFO - codeparrot_training - Step 36487: {'lr': 0.0004359506417547876, 'samples': 18681856, 'steps': 36487, 'loss/train': 1.8371868133544922}
-03/05/2022 08:21:29 - INFO - codeparrot_training - Step 36488: {'lr': 0.000435947094688223, 'samples': 18682368, 'steps': 36488, 'loss/train': 1.5153156518936157}
-03/05/2022 08:21:29 - INFO - codeparrot_training - Skipping example with length 370 (seq_length=1024)
-03/05/2022 08:21:34 - INFO - codeparrot_training - Step 36489: {'lr': 0.0004359435475378735, 'samples': 18682880, 'steps': 36489, 'loss/train': 1.9459608793258667}
-03/05/2022 08:21:37 - INFO - codeparrot_training - Step 36490: {'lr': 0.0004359400003037406, 'samples': 18683392, 'steps': 36490, 'loss/train': 1.829288363456726}
-03/05/2022 08:21:37 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/05/2022 08:21:42 - INFO - codeparrot_training - Step 36491: {'lr': 0.0004359364529858261, 'samples': 18683904, 'steps': 36491, 'loss/train': 0.6640675663948059}
-03/05/2022 08:21:46 - INFO - codeparrot_training - Step 36492: {'lr': 0.00043593290558413143, 'samples': 18684416, 'steps': 36492, 'loss/train': 1.7837222814559937}
-03/05/2022 08:21:46 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/05/2022 08:21:51 - INFO - codeparrot_training - Step 36493: {'lr': 0.0004359293580986583, 'samples': 18684928, 'steps': 36493, 'loss/train': 1.5377029180526733}
-03/05/2022 08:21:54 - INFO - codeparrot_training - Step 36494: {'lr': 0.0004359258105294083, 'samples': 18685440, 'steps': 36494, 'loss/train': 1.5339992046356201}
-03/05/2022 08:21:54 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/05/2022 08:21:59 - INFO - codeparrot_training - Step 36495: {'lr': 0.0004359222628763829, 'samples': 18685952, 'steps': 36495, 'loss/train': 1.7072575092315674}
-03/05/2022 08:22:02 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/05/2022 08:22:04 - INFO - codeparrot_training - Step 36496: {'lr': 0.0004359187151395839, 'samples': 18686464, 'steps': 36496, 'loss/train': 1.6416996717453003}
-03/05/2022 08:22:08 - INFO - codeparrot_training - Step 36497: {'lr': 0.0004359151673190127, 'samples': 18686976, 'steps': 36497, 'loss/train': 2.264662742614746}
-03/05/2022 08:22:11 - INFO - codeparrot_training - Step 36498: {'lr': 0.0004359116194146711, 'samples': 18687488, 'steps': 36498, 'loss/train': 1.6730828285217285}
-03/05/2022 08:22:11 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 08:22:16 - INFO - codeparrot_training - Step 36499: {'lr': 0.0004359080714265605, 'samples': 18688000, 'steps': 36499, 'loss/train': 0.8470184803009033}
-03/05/2022 08:22:19 - INFO - codeparrot_training - Step 36500: {'lr': 0.00043590452335468265, 'samples': 18688512, 'steps': 36500, 'loss/train': 1.1176906824111938}
-03/05/2022 08:22:19 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/05/2022 08:22:24 - INFO - codeparrot_training - Step 36501: {'lr': 0.00043590097519903917, 'samples': 18689024, 'steps': 36501, 'loss/train': 1.8993022441864014}
-03/05/2022 08:22:27 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/05/2022 08:22:30 - INFO - codeparrot_training - Step 36502: {'lr': 0.0004358974269596314, 'samples': 18689536, 'steps': 36502, 'loss/train': 0.9637288451194763}
-03/05/2022 08:22:33 - INFO - codeparrot_training - Step 36503: {'lr': 0.00043589387863646125, 'samples': 18690048, 'steps': 36503, 'loss/train': 1.8415104150772095}
-03/05/2022 08:22:36 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/05/2022 08:22:38 - INFO - codeparrot_training - Step 36504: {'lr': 0.0004358903302295301, 'samples': 18690560, 'steps': 36504, 'loss/train': 1.1889461278915405}
-03/05/2022 08:22:41 - INFO - codeparrot_training - Step 36505: {'lr': 0.0004358867817388397, 'samples': 18691072, 'steps': 36505, 'loss/train': 1.4950592517852783}
-03/05/2022 08:22:44 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/05/2022 08:22:47 - INFO - codeparrot_training - Step 36506: {'lr': 0.0004358832331643916, 'samples': 18691584, 'steps': 36506, 'loss/train': 1.5029492378234863}
-03/05/2022 08:22:50 - INFO - codeparrot_training - Step 36507: {'lr': 0.0004358796845061873, 'samples': 18692096, 'steps': 36507, 'loss/train': 1.5153765678405762}
-03/05/2022 08:22:52 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/05/2022 08:22:55 - INFO - codeparrot_training - Step 36508: {'lr': 0.00043587613576422855, 'samples': 18692608, 'steps': 36508, 'loss/train': 1.9874777793884277}
-03/05/2022 08:22:58 - INFO - codeparrot_training - Step 36509: {'lr': 0.00043587258693851685, 'samples': 18693120, 'steps': 36509, 'loss/train': 1.3859539031982422}
-03/05/2022 08:23:01 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/05/2022 08:23:03 - INFO - codeparrot_training - Step 36510: {'lr': 0.0004358690380290539, 'samples': 18693632, 'steps': 36510, 'loss/train': 1.749043583869934}
-03/05/2022 08:23:07 - INFO - codeparrot_training - Step 36511: {'lr': 0.00043586548903584113, 'samples': 18694144, 'steps': 36511, 'loss/train': 1.6331743001937866}
-03/05/2022 08:23:09 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/05/2022 08:23:12 - INFO - codeparrot_training - Step 36512: {'lr': 0.0004358619399588802, 'samples': 18694656, 'steps': 36512, 'loss/train': 1.7348130941390991}
-03/05/2022 08:23:15 - INFO - codeparrot_training - Step 36513: {'lr': 0.0004358583907981729, 'samples': 18695168, 'steps': 36513, 'loss/train': 1.2049554586410522}
-03/05/2022 08:23:18 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/05/2022 08:23:20 - INFO - codeparrot_training - Step 36514: {'lr': 0.0004358548415537206, 'samples': 18695680, 'steps': 36514, 'loss/train': 1.5076621770858765}
-03/05/2022 08:23:24 - INFO - codeparrot_training - Step 36515: {'lr': 0.000435851292225525, 'samples': 18696192, 'steps': 36515, 'loss/train': 1.8108024597167969}
-03/05/2022 08:23:26 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 08:23:29 - INFO - codeparrot_training - Step 36516: {'lr': 0.0004358477428135876, 'samples': 18696704, 'steps': 36516, 'loss/train': 1.4344950914382935}
-03/05/2022 08:23:32 - INFO - codeparrot_training - Step 36517: {'lr': 0.00043584419331791014, 'samples': 18697216, 'steps': 36517, 'loss/train': 1.6297340393066406}
-03/05/2022 08:23:34 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/05/2022 08:23:37 - INFO - codeparrot_training - Step 36518: {'lr': 0.0004358406437384942, 'samples': 18697728, 'steps': 36518, 'loss/train': 1.5512477159500122}
-03/05/2022 08:23:40 - INFO - codeparrot_training - Step 36519: {'lr': 0.0004358370940753412, 'samples': 18698240, 'steps': 36519, 'loss/train': 2.119971990585327}
-03/05/2022 08:23:43 - INFO - codeparrot_training - Skipping example with length 233 (seq_length=1024)
-03/05/2022 08:23:46 - INFO - codeparrot_training - Step 36520: {'lr': 0.000435833544328453, 'samples': 18698752, 'steps': 36520, 'loss/train': 0.6191155314445496}
-03/05/2022 08:23:49 - INFO - codeparrot_training - Step 36521: {'lr': 0.00043582999449783103, 'samples': 18699264, 'steps': 36521, 'loss/train': 2.4470598697662354}
-03/05/2022 08:23:52 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/05/2022 08:23:54 - INFO - codeparrot_training - Step 36522: {'lr': 0.0004358264445834769, 'samples': 18699776, 'steps': 36522, 'loss/train': 2.3127388954162598}
-03/05/2022 08:23:58 - INFO - codeparrot_training - Step 36523: {'lr': 0.00043582289458539224, 'samples': 18700288, 'steps': 36523, 'loss/train': 2.3628015518188477}
-03/05/2022 08:24:00 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/05/2022 08:24:03 - INFO - codeparrot_training - Step 36524: {'lr': 0.00043581934450357876, 'samples': 18700800, 'steps': 36524, 'loss/train': 1.8854731321334839}
-03/05/2022 08:24:06 - INFO - codeparrot_training - Step 36525: {'lr': 0.0004358157943380379, 'samples': 18701312, 'steps': 36525, 'loss/train': 1.24105703830719}
-03/05/2022 08:24:08 - INFO - codeparrot_training - Skipping example with length 822 (seq_length=1024)
-03/05/2022 08:24:11 - INFO - codeparrot_training - Step 36526: {'lr': 0.00043581224408877116, 'samples': 18701824, 'steps': 36526, 'loss/train': 1.6562447547912598}
-03/05/2022 08:24:14 - INFO - codeparrot_training - Step 36527: {'lr': 0.00043580869375578046, 'samples': 18702336, 'steps': 36527, 'loss/train': 1.2891017198562622}
-03/05/2022 08:24:17 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/05/2022 08:24:20 - INFO - codeparrot_training - Step 36528: {'lr': 0.00043580514333906717, 'samples': 18702848, 'steps': 36528, 'loss/train': 0.8692784309387207}
-03/05/2022 08:24:23 - INFO - codeparrot_training - Step 36529: {'lr': 0.000435801592838633, 'samples': 18703360, 'steps': 36529, 'loss/train': 1.0447176694869995}
-03/05/2022 08:24:25 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/05/2022 08:24:28 - INFO - codeparrot_training - Step 36530: {'lr': 0.0004357980422544794, 'samples': 18703872, 'steps': 36530, 'loss/train': 1.8964654207229614}
-03/05/2022 08:24:31 - INFO - codeparrot_training - Step 36531: {'lr': 0.00043579449158660815, 'samples': 18704384, 'steps': 36531, 'loss/train': 2.418860673904419}
-03/05/2022 08:24:33 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/05/2022 08:24:37 - INFO - codeparrot_training - Step 36532: {'lr': 0.0004357909408350208, 'samples': 18704896, 'steps': 36532, 'loss/train': 2.0499579906463623}
-03/05/2022 08:24:40 - INFO - codeparrot_training - Step 36533: {'lr': 0.00043578738999971886, 'samples': 18705408, 'steps': 36533, 'loss/train': 2.485102891921997}
-03/05/2022 08:24:42 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 08:24:45 - INFO - codeparrot_training - Step 36534: {'lr': 0.000435783839080704, 'samples': 18705920, 'steps': 36534, 'loss/train': 1.6127310991287231}
-03/05/2022 08:24:48 - INFO - codeparrot_training - Step 36535: {'lr': 0.00043578028807797774, 'samples': 18706432, 'steps': 36535, 'loss/train': 1.5184998512268066}
-03/05/2022 08:24:50 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/05/2022 08:24:54 - INFO - codeparrot_training - Step 36536: {'lr': 0.0004357767369915419, 'samples': 18706944, 'steps': 36536, 'loss/train': 2.1432178020477295}
-03/05/2022 08:24:57 - INFO - codeparrot_training - Step 36537: {'lr': 0.0004357731858213978, 'samples': 18707456, 'steps': 36537, 'loss/train': 0.7013729810714722}
-03/05/2022 08:24:59 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/05/2022 08:25:02 - INFO - codeparrot_training - Step 36538: {'lr': 0.0004357696345675472, 'samples': 18707968, 'steps': 36538, 'loss/train': 1.1529698371887207}
-03/05/2022 08:25:05 - INFO - codeparrot_training - Step 36539: {'lr': 0.00043576608322999167, 'samples': 18708480, 'steps': 36539, 'loss/train': 0.6617556810379028}
-03/05/2022 08:25:07 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/05/2022 08:25:11 - INFO - codeparrot_training - Step 36540: {'lr': 0.0004357625318087328, 'samples': 18708992, 'steps': 36540, 'loss/train': 1.403743028640747}
-03/05/2022 08:25:14 - INFO - codeparrot_training - Step 36541: {'lr': 0.00043575898030377225, 'samples': 18709504, 'steps': 36541, 'loss/train': 1.7805424928665161}
-03/05/2022 08:25:15 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/05/2022 08:25:19 - INFO - codeparrot_training - Step 36542: {'lr': 0.00043575542871511155, 'samples': 18710016, 'steps': 36542, 'loss/train': 1.4902095794677734}
-03/05/2022 08:25:22 - INFO - codeparrot_training - Step 36543: {'lr': 0.00043575187704275234, 'samples': 18710528, 'steps': 36543, 'loss/train': 1.4140548706054688}
-03/05/2022 08:25:24 - INFO - codeparrot_training - Skipping example with length 150 (seq_length=1024)
-03/05/2022 08:25:28 - INFO - codeparrot_training - Step 36544: {'lr': 0.0004357483252866961, 'samples': 18711040, 'steps': 36544, 'loss/train': 1.5703848600387573}
-03/05/2022 08:25:31 - INFO - codeparrot_training - Step 36545: {'lr': 0.00043574477344694463, 'samples': 18711552, 'steps': 36545, 'loss/train': 1.5440270900726318}
-03/05/2022 08:25:33 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 08:25:36 - INFO - codeparrot_training - Step 36546: {'lr': 0.0004357412215234994, 'samples': 18712064, 'steps': 36546, 'loss/train': 1.915827751159668}
-03/05/2022 08:25:39 - INFO - codeparrot_training - Step 36547: {'lr': 0.00043573766951636206, 'samples': 18712576, 'steps': 36547, 'loss/train': 1.4978708028793335}
-03/05/2022 08:25:41 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/05/2022 08:25:45 - INFO - codeparrot_training - Step 36548: {'lr': 0.00043573411742553415, 'samples': 18713088, 'steps': 36548, 'loss/train': 1.4757479429244995}
-03/05/2022 08:25:48 - INFO - codeparrot_training - Step 36549: {'lr': 0.0004357305652510174, 'samples': 18713600, 'steps': 36549, 'loss/train': 1.2901889085769653}
-03/05/2022 08:25:49 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/05/2022 08:25:53 - INFO - codeparrot_training - Step 36550: {'lr': 0.00043572701299281327, 'samples': 18714112, 'steps': 36550, 'loss/train': 1.7883002758026123}
-03/05/2022 08:25:56 - INFO - codeparrot_training - Step 36551: {'lr': 0.0004357234606509234, 'samples': 18714624, 'steps': 36551, 'loss/train': 1.737593650817871}
-03/05/2022 08:25:58 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/05/2022 08:26:02 - INFO - codeparrot_training - Step 36552: {'lr': 0.00043571990822534936, 'samples': 18715136, 'steps': 36552, 'loss/train': 2.0328991413116455}
-03/05/2022 08:26:05 - INFO - codeparrot_training - Step 36553: {'lr': 0.00043571635571609287, 'samples': 18715648, 'steps': 36553, 'loss/train': 1.2090493440628052}
-03/05/2022 08:26:06 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/05/2022 08:26:10 - INFO - codeparrot_training - Step 36554: {'lr': 0.00043571280312315543, 'samples': 18716160, 'steps': 36554, 'loss/train': 1.7943819761276245}
-03/05/2022 08:26:13 - INFO - codeparrot_training - Step 36555: {'lr': 0.0004357092504465386, 'samples': 18716672, 'steps': 36555, 'loss/train': 2.533794641494751}
-03/05/2022 08:26:14 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/05/2022 08:26:18 - INFO - codeparrot_training - Step 36556: {'lr': 0.00043570569768624416, 'samples': 18717184, 'steps': 36556, 'loss/train': 2.2103922367095947}
-03/05/2022 08:26:22 - INFO - codeparrot_training - Step 36557: {'lr': 0.00043570214484227353, 'samples': 18717696, 'steps': 36557, 'loss/train': 1.3598906993865967}
-03/05/2022 08:26:22 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/05/2022 08:26:27 - INFO - codeparrot_training - Step 36558: {'lr': 0.00043569859191462847, 'samples': 18718208, 'steps': 36558, 'loss/train': 2.7311465740203857}
-03/05/2022 08:26:30 - INFO - codeparrot_training - Step 36559: {'lr': 0.0004356950389033104, 'samples': 18718720, 'steps': 36559, 'loss/train': 1.8683820962905884}
-03/05/2022 08:26:31 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/05/2022 08:26:35 - INFO - codeparrot_training - Step 36560: {'lr': 0.0004356914858083211, 'samples': 18719232, 'steps': 36560, 'loss/train': 1.4868749380111694}
-03/05/2022 08:26:38 - INFO - codeparrot_training - Step 36561: {'lr': 0.00043568793262966195, 'samples': 18719744, 'steps': 36561, 'loss/train': 2.323687791824341}
-03/05/2022 08:26:39 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/05/2022 08:26:44 - INFO - codeparrot_training - Step 36562: {'lr': 0.00043568437936733473, 'samples': 18720256, 'steps': 36562, 'loss/train': 1.4781105518341064}
-03/05/2022 08:26:47 - INFO - codeparrot_training - Step 36563: {'lr': 0.0004356808260213411, 'samples': 18720768, 'steps': 36563, 'loss/train': 1.5390191078186035}
-03/05/2022 08:26:49 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 08:26:52 - INFO - codeparrot_training - Step 36564: {'lr': 0.00043567727259168244, 'samples': 18721280, 'steps': 36564, 'loss/train': 1.2240735292434692}
-03/05/2022 08:26:56 - INFO - codeparrot_training - Step 36565: {'lr': 0.0004356737190783605, 'samples': 18721792, 'steps': 36565, 'loss/train': 1.2456129789352417}
-03/05/2022 08:26:58 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/05/2022 08:27:01 - INFO - codeparrot_training - Step 36566: {'lr': 0.00043567016548137685, 'samples': 18722304, 'steps': 36566, 'loss/train': 2.0442705154418945}
-03/05/2022 08:27:04 - INFO - codeparrot_training - Step 36567: {'lr': 0.00043566661180073304, 'samples': 18722816, 'steps': 36567, 'loss/train': 1.5831828117370605}
-03/05/2022 08:27:06 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/05/2022 08:27:09 - INFO - codeparrot_training - Step 36568: {'lr': 0.00043566305803643073, 'samples': 18723328, 'steps': 36568, 'loss/train': 1.5288282632827759}
-03/05/2022 08:27:12 - INFO - codeparrot_training - Step 36569: {'lr': 0.00043565950418847154, 'samples': 18723840, 'steps': 36569, 'loss/train': 0.8193228840827942}
-03/05/2022 08:27:14 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/05/2022 08:27:18 - INFO - codeparrot_training - Step 36570: {'lr': 0.00043565595025685705, 'samples': 18724352, 'steps': 36570, 'loss/train': 2.4879138469696045}
-03/05/2022 08:27:21 - INFO - codeparrot_training - Step 36571: {'lr': 0.0004356523962415889, 'samples': 18724864, 'steps': 36571, 'loss/train': 1.8944706916809082}
-03/05/2022 08:27:23 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/05/2022 08:27:26 - INFO - codeparrot_training - Step 36572: {'lr': 0.00043564884214266855, 'samples': 18725376, 'steps': 36572, 'loss/train': 1.8711698055267334}
-03/05/2022 08:27:29 - INFO - codeparrot_training - Step 36573: {'lr': 0.00043564528796009774, 'samples': 18725888, 'steps': 36573, 'loss/train': 1.1864264011383057}
-03/05/2022 08:27:31 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/05/2022 08:27:35 - INFO - codeparrot_training - Step 36574: {'lr': 0.00043564173369387807, 'samples': 18726400, 'steps': 36574, 'loss/train': 2.058751344680786}
-03/05/2022 08:27:38 - INFO - codeparrot_training - Step 36575: {'lr': 0.00043563817934401107, 'samples': 18726912, 'steps': 36575, 'loss/train': 1.9796102046966553}
-03/05/2022 08:27:39 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/05/2022 08:27:43 - INFO - codeparrot_training - Step 36576: {'lr': 0.0004356346249104983, 'samples': 18727424, 'steps': 36576, 'loss/train': 1.809995174407959}
-03/05/2022 08:27:46 - INFO - codeparrot_training - Step 36577: {'lr': 0.0004356310703933415, 'samples': 18727936, 'steps': 36577, 'loss/train': 1.9293798208236694}
-03/05/2022 08:27:48 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/05/2022 08:27:51 - INFO - codeparrot_training - Step 36578: {'lr': 0.00043562751579254215, 'samples': 18728448, 'steps': 36578, 'loss/train': 1.7188117504119873}
-03/05/2022 08:27:54 - INFO - codeparrot_training - Step 36579: {'lr': 0.00043562396110810196, 'samples': 18728960, 'steps': 36579, 'loss/train': 1.7587697505950928}
-03/05/2022 08:27:56 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/05/2022 08:28:00 - INFO - codeparrot_training - Step 36580: {'lr': 0.00043562040634002245, 'samples': 18729472, 'steps': 36580, 'loss/train': 1.9747369289398193}
-03/05/2022 08:28:03 - INFO - codeparrot_training - Step 36581: {'lr': 0.0004356168514883053, 'samples': 18729984, 'steps': 36581, 'loss/train': 2.058427333831787}
-03/05/2022 08:28:05 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 08:28:08 - INFO - codeparrot_training - Step 36582: {'lr': 0.000435613296552952, 'samples': 18730496, 'steps': 36582, 'loss/train': 1.7490038871765137}
-03/05/2022 08:28:12 - INFO - codeparrot_training - Step 36583: {'lr': 0.0004356097415339643, 'samples': 18731008, 'steps': 36583, 'loss/train': 1.5420913696289062}
-03/05/2022 08:28:14 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/05/2022 08:28:17 - INFO - codeparrot_training - Step 36584: {'lr': 0.0004356061864313436, 'samples': 18731520, 'steps': 36584, 'loss/train': 1.319744348526001}
-03/05/2022 08:28:20 - INFO - codeparrot_training - Step 36585: {'lr': 0.0004356026312450917, 'samples': 18732032, 'steps': 36585, 'loss/train': 2.2613534927368164}
-03/05/2022 08:28:23 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/05/2022 08:28:25 - INFO - codeparrot_training - Step 36586: {'lr': 0.00043559907597521007, 'samples': 18732544, 'steps': 36586, 'loss/train': 2.1069462299346924}
-03/05/2022 08:28:28 - INFO - codeparrot_training - Step 36587: {'lr': 0.00043559552062170037, 'samples': 18733056, 'steps': 36587, 'loss/train': 2.013767719268799}
-03/05/2022 08:28:31 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/05/2022 08:28:34 - INFO - codeparrot_training - Step 36588: {'lr': 0.00043559196518456425, 'samples': 18733568, 'steps': 36588, 'loss/train': 1.4833972454071045}
-03/05/2022 08:28:37 - INFO - codeparrot_training - Step 36589: {'lr': 0.0004355884096638032, 'samples': 18734080, 'steps': 36589, 'loss/train': 2.004408359527588}
-03/05/2022 08:28:39 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/05/2022 08:28:42 - INFO - codeparrot_training - Step 36590: {'lr': 0.0004355848540594188, 'samples': 18734592, 'steps': 36590, 'loss/train': 2.231391191482544}
-03/05/2022 08:28:45 - INFO - codeparrot_training - Step 36591: {'lr': 0.00043558129837141285, 'samples': 18735104, 'steps': 36591, 'loss/train': 1.957297921180725}
-03/05/2022 08:28:48 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/05/2022 08:28:50 - INFO - codeparrot_training - Step 36592: {'lr': 0.0004355777425997868, 'samples': 18735616, 'steps': 36592, 'loss/train': 1.3269720077514648}
-03/05/2022 08:28:54 - INFO - codeparrot_training - Step 36593: {'lr': 0.0004355741867445423, 'samples': 18736128, 'steps': 36593, 'loss/train': 1.8008546829223633}
-03/05/2022 08:28:56 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/05/2022 08:28:59 - INFO - codeparrot_training - Step 36594: {'lr': 0.00043557063080568094, 'samples': 18736640, 'steps': 36594, 'loss/train': 1.4983978271484375}
-03/05/2022 08:29:02 - INFO - codeparrot_training - Step 36595: {'lr': 0.00043556707478320425, 'samples': 18737152, 'steps': 36595, 'loss/train': 2.248431921005249}
-03/05/2022 08:29:04 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/05/2022 08:29:07 - INFO - codeparrot_training - Step 36596: {'lr': 0.000435563518677114, 'samples': 18737664, 'steps': 36596, 'loss/train': 1.5486775636672974}
-03/05/2022 08:29:11 - INFO - codeparrot_training - Step 36597: {'lr': 0.00043555996248741157, 'samples': 18738176, 'steps': 36597, 'loss/train': 1.726602554321289}
-03/05/2022 08:29:12 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/05/2022 08:29:16 - INFO - codeparrot_training - Step 36598: {'lr': 0.00043555640621409874, 'samples': 18738688, 'steps': 36598, 'loss/train': 1.7763574123382568}
-03/05/2022 08:29:19 - INFO - codeparrot_training - Step 36599: {'lr': 0.000435552849857177, 'samples': 18739200, 'steps': 36599, 'loss/train': 1.971351146697998}
-03/05/2022 08:29:21 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/05/2022 08:29:24 - INFO - codeparrot_training - Step 36600: {'lr': 0.0004355492934166481, 'samples': 18739712, 'steps': 36600, 'loss/train': 1.71782386302948}
-03/05/2022 08:29:27 - INFO - codeparrot_training - Step 36601: {'lr': 0.00043554573689251355, 'samples': 18740224, 'steps': 36601, 'loss/train': 0.5695029497146606}
-03/05/2022 08:29:30 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/05/2022 08:29:33 - INFO - codeparrot_training - Step 36602: {'lr': 0.00043554218028477493, 'samples': 18740736, 'steps': 36602, 'loss/train': 1.830383539199829}
-03/05/2022 08:29:36 - INFO - codeparrot_training - Step 36603: {'lr': 0.0004355386235934339, 'samples': 18741248, 'steps': 36603, 'loss/train': 1.4319417476654053}
-03/05/2022 08:29:38 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/05/2022 08:29:41 - INFO - codeparrot_training - Step 36604: {'lr': 0.0004355350668184919, 'samples': 18741760, 'steps': 36604, 'loss/train': 2.0565261840820312}
-03/05/2022 08:29:44 - INFO - codeparrot_training - Step 36605: {'lr': 0.0004355315099599508, 'samples': 18742272, 'steps': 36605, 'loss/train': 1.1882394552230835}
-03/05/2022 08:29:46 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/05/2022 08:29:49 - INFO - codeparrot_training - Step 36606: {'lr': 0.000435527953017812, 'samples': 18742784, 'steps': 36606, 'loss/train': 0.7650132179260254}
-03/05/2022 08:29:53 - INFO - codeparrot_training - Step 36607: {'lr': 0.00043552439599207714, 'samples': 18743296, 'steps': 36607, 'loss/train': 1.7250149250030518}
-03/05/2022 08:29:55 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 08:29:58 - INFO - codeparrot_training - Step 36608: {'lr': 0.00043552083888274794, 'samples': 18743808, 'steps': 36608, 'loss/train': 1.855858564376831}
-03/05/2022 08:30:01 - INFO - codeparrot_training - Step 36609: {'lr': 0.00043551728168982583, 'samples': 18744320, 'steps': 36609, 'loss/train': 1.6502448320388794}
-03/05/2022 08:30:03 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/05/2022 08:30:06 - INFO - codeparrot_training - Step 36610: {'lr': 0.0004355137244133126, 'samples': 18744832, 'steps': 36610, 'loss/train': 0.7300519347190857}
-03/05/2022 08:30:10 - INFO - codeparrot_training - Step 36611: {'lr': 0.00043551016705320965, 'samples': 18745344, 'steps': 36611, 'loss/train': 1.4427647590637207}
-03/05/2022 08:30:11 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/05/2022 08:30:15 - INFO - codeparrot_training - Step 36612: {'lr': 0.00043550660960951874, 'samples': 18745856, 'steps': 36612, 'loss/train': 2.145141363143921}
-03/05/2022 08:30:18 - INFO - codeparrot_training - Step 36613: {'lr': 0.0004355030520822414, 'samples': 18746368, 'steps': 36613, 'loss/train': 1.865956425666809}
-03/05/2022 08:30:20 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/05/2022 08:30:23 - INFO - codeparrot_training - Step 36614: {'lr': 0.00043549949447137915, 'samples': 18746880, 'steps': 36614, 'loss/train': 1.9670602083206177}
-03/05/2022 08:30:27 - INFO - codeparrot_training - Step 36615: {'lr': 0.00043549593677693385, 'samples': 18747392, 'steps': 36615, 'loss/train': 0.4524717926979065}
-03/05/2022 08:30:28 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/05/2022 08:30:32 - INFO - codeparrot_training - Step 36616: {'lr': 0.0004354923789989068, 'samples': 18747904, 'steps': 36616, 'loss/train': 2.0643012523651123}
-03/05/2022 08:30:35 - INFO - codeparrot_training - Step 36617: {'lr': 0.0004354888211372998, 'samples': 18748416, 'steps': 36617, 'loss/train': 1.5244133472442627}
-03/05/2022 08:30:37 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/05/2022 08:30:40 - INFO - codeparrot_training - Step 36618: {'lr': 0.0004354852631921145, 'samples': 18748928, 'steps': 36618, 'loss/train': 2.306825876235962}
-03/05/2022 08:30:43 - INFO - codeparrot_training - Step 36619: {'lr': 0.0004354817051633523, 'samples': 18749440, 'steps': 36619, 'loss/train': 1.7672079801559448}
-03/05/2022 08:30:45 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/05/2022 08:30:49 - INFO - codeparrot_training - Step 36620: {'lr': 0.00043547814705101486, 'samples': 18749952, 'steps': 36620, 'loss/train': 1.7525672912597656}
-03/05/2022 08:30:52 - INFO - codeparrot_training - Step 36621: {'lr': 0.00043547458885510393, 'samples': 18750464, 'steps': 36621, 'loss/train': 2.43685245513916}
-03/05/2022 08:30:53 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/05/2022 08:30:57 - INFO - codeparrot_training - Step 36622: {'lr': 0.00043547103057562097, 'samples': 18750976, 'steps': 36622, 'loss/train': 2.3709559440612793}
-03/05/2022 08:31:00 - INFO - codeparrot_training - Step 36623: {'lr': 0.00043546747221256764, 'samples': 18751488, 'steps': 36623, 'loss/train': 2.236823797225952}
-03/05/2022 08:31:02 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/05/2022 08:31:06 - INFO - codeparrot_training - Step 36624: {'lr': 0.00043546391376594553, 'samples': 18752000, 'steps': 36624, 'loss/train': 0.8149133920669556}
-03/05/2022 08:31:09 - INFO - codeparrot_training - Step 36625: {'lr': 0.0004354603552357562, 'samples': 18752512, 'steps': 36625, 'loss/train': 2.5442864894866943}
-03/05/2022 08:31:10 - INFO - codeparrot_training - Skipping example with length 714 (seq_length=1024)
-03/05/2022 08:31:14 - INFO - codeparrot_training - Step 36626: {'lr': 0.0004354567966220013, 'samples': 18753024, 'steps': 36626, 'loss/train': 1.8254780769348145}
-03/05/2022 08:31:17 - INFO - codeparrot_training - Step 36627: {'lr': 0.0004354532379246825, 'samples': 18753536, 'steps': 36627, 'loss/train': 2.0811667442321777}
-03/05/2022 08:31:19 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/05/2022 08:31:22 - INFO - codeparrot_training - Step 36628: {'lr': 0.0004354496791438013, 'samples': 18754048, 'steps': 36628, 'loss/train': 1.9770479202270508}
-03/05/2022 08:31:26 - INFO - codeparrot_training - Step 36629: {'lr': 0.0004354461202793593, 'samples': 18754560, 'steps': 36629, 'loss/train': 1.8774384260177612}
-03/05/2022 08:31:27 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/05/2022 08:31:31 - INFO - codeparrot_training - Step 36630: {'lr': 0.00043544256133135815, 'samples': 18755072, 'steps': 36630, 'loss/train': 1.4496067762374878}
-03/05/2022 08:31:34 - INFO - codeparrot_training - Step 36631: {'lr': 0.0004354390022997995, 'samples': 18755584, 'steps': 36631, 'loss/train': 1.600720763206482}
-03/05/2022 08:31:36 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/05/2022 08:31:39 - INFO - codeparrot_training - Step 36632: {'lr': 0.0004354354431846848, 'samples': 18756096, 'steps': 36632, 'loss/train': 1.5415774583816528}
-03/05/2022 08:31:42 - INFO - codeparrot_training - Step 36633: {'lr': 0.00043543188398601586, 'samples': 18756608, 'steps': 36633, 'loss/train': 2.1242449283599854}
-03/05/2022 08:31:44 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/05/2022 08:31:48 - INFO - codeparrot_training - Step 36634: {'lr': 0.00043542832470379415, 'samples': 18757120, 'steps': 36634, 'loss/train': 1.3364808559417725}
-03/05/2022 08:31:51 - INFO - codeparrot_training - Step 36635: {'lr': 0.0004354247653380212, 'samples': 18757632, 'steps': 36635, 'loss/train': 1.8590220212936401}
-03/05/2022 08:31:52 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/05/2022 08:31:56 - INFO - codeparrot_training - Step 36636: {'lr': 0.00043542120588869885, 'samples': 18758144, 'steps': 36636, 'loss/train': 2.547084093093872}
-03/05/2022 08:31:59 - INFO - codeparrot_training - Step 36637: {'lr': 0.0004354176463558284, 'samples': 18758656, 'steps': 36637, 'loss/train': 1.783582329750061}
-03/05/2022 08:32:01 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/05/2022 08:32:05 - INFO - codeparrot_training - Step 36638: {'lr': 0.00043541408673941173, 'samples': 18759168, 'steps': 36638, 'loss/train': 0.7238414287567139}
-03/05/2022 08:32:08 - INFO - codeparrot_training - Step 36639: {'lr': 0.00043541052703945034, 'samples': 18759680, 'steps': 36639, 'loss/train': 2.013413190841675}
-03/05/2022 08:32:09 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/05/2022 08:32:13 - INFO - codeparrot_training - Step 36640: {'lr': 0.0004354069672559458, 'samples': 18760192, 'steps': 36640, 'loss/train': 1.586073398590088}
-03/05/2022 08:32:16 - INFO - codeparrot_training - Step 36641: {'lr': 0.0004354034073888997, 'samples': 18760704, 'steps': 36641, 'loss/train': 2.944774866104126}
-03/05/2022 08:32:19 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/05/2022 08:32:22 - INFO - codeparrot_training - Step 36642: {'lr': 0.00043539984743831375, 'samples': 18761216, 'steps': 36642, 'loss/train': 1.4330339431762695}
-03/05/2022 08:32:25 - INFO - codeparrot_training - Step 36643: {'lr': 0.0004353962874041895, 'samples': 18761728, 'steps': 36643, 'loss/train': 2.499502182006836}
-03/05/2022 08:32:28 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/05/2022 08:32:30 - INFO - codeparrot_training - Step 36644: {'lr': 0.0004353927272865285, 'samples': 18762240, 'steps': 36644, 'loss/train': 1.3408678770065308}
-03/05/2022 08:32:33 - INFO - codeparrot_training - Step 36645: {'lr': 0.0004353891670853324, 'samples': 18762752, 'steps': 36645, 'loss/train': 2.179685592651367}
-03/05/2022 08:32:36 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/05/2022 08:32:39 - INFO - codeparrot_training - Step 36646: {'lr': 0.00043538560680060287, 'samples': 18763264, 'steps': 36646, 'loss/train': 1.1304265260696411}
-03/05/2022 08:32:42 - INFO - codeparrot_training - Step 36647: {'lr': 0.00043538204643234137, 'samples': 18763776, 'steps': 36647, 'loss/train': 1.6504698991775513}
-03/05/2022 08:32:44 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/05/2022 08:32:47 - INFO - codeparrot_training - Step 36648: {'lr': 0.0004353784859805496, 'samples': 18764288, 'steps': 36648, 'loss/train': 1.3401870727539062}
-03/05/2022 08:32:50 - INFO - codeparrot_training - Step 36649: {'lr': 0.00043537492544522917, 'samples': 18764800, 'steps': 36649, 'loss/train': 1.0732760429382324}
-03/05/2022 08:32:53 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/05/2022 08:32:56 - INFO - codeparrot_training - Step 36650: {'lr': 0.0004353713648263816, 'samples': 18765312, 'steps': 36650, 'loss/train': 1.5390355587005615}
-03/05/2022 08:32:59 - INFO - codeparrot_training - Step 36651: {'lr': 0.00043536780412400857, 'samples': 18765824, 'steps': 36651, 'loss/train': 1.8621513843536377}
-03/05/2022 08:33:02 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/05/2022 08:33:04 - INFO - codeparrot_training - Step 36652: {'lr': 0.0004353642433381117, 'samples': 18766336, 'steps': 36652, 'loss/train': 2.1783015727996826}
-03/05/2022 08:33:07 - INFO - codeparrot_training - Step 36653: {'lr': 0.00043536068246869254, 'samples': 18766848, 'steps': 36653, 'loss/train': 1.9883053302764893}
-03/05/2022 08:33:10 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/05/2022 08:33:13 - INFO - codeparrot_training - Step 36654: {'lr': 0.00043535712151575274, 'samples': 18767360, 'steps': 36654, 'loss/train': 1.2596718072891235}
-03/05/2022 08:33:16 - INFO - codeparrot_training - Step 36655: {'lr': 0.00043535356047929387, 'samples': 18767872, 'steps': 36655, 'loss/train': 2.145206928253174}
-03/05/2022 08:33:18 - INFO - codeparrot_training - Skipping example with length 242 (seq_length=1024)
-03/05/2022 08:33:21 - INFO - codeparrot_training - Step 36656: {'lr': 0.0004353499993593176, 'samples': 18768384, 'steps': 36656, 'loss/train': 1.0523627996444702}
-03/05/2022 08:33:24 - INFO - codeparrot_training - Step 36657: {'lr': 0.0004353464381558254, 'samples': 18768896, 'steps': 36657, 'loss/train': 1.7637388706207275}
-03/05/2022 08:33:26 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/05/2022 08:33:29 - INFO - codeparrot_training - Step 36658: {'lr': 0.00043534287686881895, 'samples': 18769408, 'steps': 36658, 'loss/train': 1.6951905488967896}
-03/05/2022 08:33:33 - INFO - codeparrot_training - Step 36659: {'lr': 0.00043533931549829993, 'samples': 18769920, 'steps': 36659, 'loss/train': 2.221018075942993}
-03/05/2022 08:33:35 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/05/2022 08:33:38 - INFO - codeparrot_training - Step 36660: {'lr': 0.00043533575404426986, 'samples': 18770432, 'steps': 36660, 'loss/train': 2.1294572353363037}
-03/05/2022 08:33:41 - INFO - codeparrot_training - Step 36661: {'lr': 0.0004353321925067303, 'samples': 18770944, 'steps': 36661, 'loss/train': 1.4282238483428955}
-03/05/2022 08:33:43 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 08:33:46 - INFO - codeparrot_training - Step 36662: {'lr': 0.0004353286308856829, 'samples': 18771456, 'steps': 36662, 'loss/train': 1.5797237157821655}
-03/05/2022 08:33:49 - INFO - codeparrot_training - Step 36663: {'lr': 0.00043532506918112933, 'samples': 18771968, 'steps': 36663, 'loss/train': 1.6038144826889038}
-03/05/2022 08:33:51 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/05/2022 08:33:55 - INFO - codeparrot_training - Step 36664: {'lr': 0.0004353215073930712, 'samples': 18772480, 'steps': 36664, 'loss/train': 0.9530586004257202}
-03/05/2022 08:33:58 - INFO - codeparrot_training - Step 36665: {'lr': 0.00043531794552150994, 'samples': 18772992, 'steps': 36665, 'loss/train': 2.021253824234009}
-03/05/2022 08:34:00 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/05/2022 08:34:03 - INFO - codeparrot_training - Step 36666: {'lr': 0.0004353143835664474, 'samples': 18773504, 'steps': 36666, 'loss/train': 2.064541816711426}
-03/05/2022 08:34:06 - INFO - codeparrot_training - Step 36667: {'lr': 0.00043531082152788495, 'samples': 18774016, 'steps': 36667, 'loss/train': 1.6886372566223145}
-03/05/2022 08:34:08 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/05/2022 08:34:12 - INFO - codeparrot_training - Step 36668: {'lr': 0.0004353072594058243, 'samples': 18774528, 'steps': 36668, 'loss/train': 2.5402162075042725}
-03/05/2022 08:34:15 - INFO - codeparrot_training - Step 36669: {'lr': 0.0004353036972002671, 'samples': 18775040, 'steps': 36669, 'loss/train': 2.001192569732666}
-03/05/2022 08:34:17 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/05/2022 08:34:20 - INFO - codeparrot_training - Step 36670: {'lr': 0.00043530013491121497, 'samples': 18775552, 'steps': 36670, 'loss/train': 1.9092366695404053}
-03/05/2022 08:34:23 - INFO - codeparrot_training - Step 36671: {'lr': 0.00043529657253866936, 'samples': 18776064, 'steps': 36671, 'loss/train': 1.537556767463684}
-03/05/2022 08:34:25 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/05/2022 08:34:29 - INFO - codeparrot_training - Step 36672: {'lr': 0.000435293010082632, 'samples': 18776576, 'steps': 36672, 'loss/train': 0.7188050150871277}
-03/05/2022 08:34:32 - INFO - codeparrot_training - Step 36673: {'lr': 0.0004352894475431045, 'samples': 18777088, 'steps': 36673, 'loss/train': 0.49456536769866943}
-03/05/2022 08:34:34 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/05/2022 08:34:37 - INFO - codeparrot_training - Step 36674: {'lr': 0.0004352858849200885, 'samples': 18777600, 'steps': 36674, 'loss/train': 1.6767886877059937}
-03/05/2022 08:34:41 - INFO - codeparrot_training - Step 36675: {'lr': 0.0004352823222135854, 'samples': 18778112, 'steps': 36675, 'loss/train': 1.0852221250534058}
-03/05/2022 08:34:42 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/05/2022 08:34:46 - INFO - codeparrot_training - Step 36676: {'lr': 0.00043527875942359697, 'samples': 18778624, 'steps': 36676, 'loss/train': 1.648712396621704}
-03/05/2022 08:34:49 - INFO - codeparrot_training - Step 36677: {'lr': 0.0004352751965501248, 'samples': 18779136, 'steps': 36677, 'loss/train': 1.6284223794937134}
-03/05/2022 08:34:51 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 08:34:54 - INFO - codeparrot_training - Step 36678: {'lr': 0.0004352716335931706, 'samples': 18779648, 'steps': 36678, 'loss/train': 2.3753294944763184}
-03/05/2022 08:34:58 - INFO - codeparrot_training - Step 36679: {'lr': 0.0004352680705527357, 'samples': 18780160, 'steps': 36679, 'loss/train': 1.6806747913360596}
-03/05/2022 08:35:00 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/05/2022 08:35:03 - INFO - codeparrot_training - Step 36680: {'lr': 0.00043526450742882193, 'samples': 18780672, 'steps': 36680, 'loss/train': 2.032686233520508}
-03/05/2022 08:35:06 - INFO - codeparrot_training - Step 36681: {'lr': 0.0004352609442214309, 'samples': 18781184, 'steps': 36681, 'loss/train': 1.3099148273468018}
-03/05/2022 08:35:08 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/05/2022 08:35:11 - INFO - codeparrot_training - Step 36682: {'lr': 0.00043525738093056404, 'samples': 18781696, 'steps': 36682, 'loss/train': 2.1943650245666504}
-03/05/2022 08:35:14 - INFO - codeparrot_training - Step 36683: {'lr': 0.0004352538175562231, 'samples': 18782208, 'steps': 36683, 'loss/train': 1.966793179512024}
-03/05/2022 08:35:17 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/05/2022 08:35:20 - INFO - codeparrot_training - Step 36684: {'lr': 0.00043525025409840967, 'samples': 18782720, 'steps': 36684, 'loss/train': 1.1217139959335327}
-03/05/2022 08:35:23 - INFO - codeparrot_training - Step 36685: {'lr': 0.00043524669055712534, 'samples': 18783232, 'steps': 36685, 'loss/train': 1.6760820150375366}
-03/05/2022 08:35:26 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/05/2022 08:35:28 - INFO - codeparrot_training - Step 36686: {'lr': 0.00043524312693237166, 'samples': 18783744, 'steps': 36686, 'loss/train': 0.9233697056770325}
-03/05/2022 08:35:31 - INFO - codeparrot_training - Step 36687: {'lr': 0.0004352395632241504, 'samples': 18784256, 'steps': 36687, 'loss/train': 1.7965147495269775}
-03/05/2022 08:35:34 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/05/2022 08:35:37 - INFO - codeparrot_training - Step 36688: {'lr': 0.00043523599943246297, 'samples': 18784768, 'steps': 36688, 'loss/train': 1.6315757036209106}
-03/05/2022 08:35:40 - INFO - codeparrot_training - Step 36689: {'lr': 0.00043523243555731094, 'samples': 18785280, 'steps': 36689, 'loss/train': 1.9857407808303833}
-03/05/2022 08:35:42 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/05/2022 08:35:45 - INFO - codeparrot_training - Step 36690: {'lr': 0.00043522887159869617, 'samples': 18785792, 'steps': 36690, 'loss/train': 1.612954020500183}
-03/05/2022 08:35:48 - INFO - codeparrot_training - Step 36691: {'lr': 0.00043522530755662017, 'samples': 18786304, 'steps': 36691, 'loss/train': 1.1465319395065308}
-03/05/2022 08:35:50 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/05/2022 08:35:54 - INFO - codeparrot_training - Step 36692: {'lr': 0.00043522174343108445, 'samples': 18786816, 'steps': 36692, 'loss/train': 2.0332961082458496}
-03/05/2022 08:35:57 - INFO - codeparrot_training - Step 36693: {'lr': 0.00043521817922209064, 'samples': 18787328, 'steps': 36693, 'loss/train': 1.6126130819320679}
-03/05/2022 08:35:59 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/05/2022 08:36:02 - INFO - codeparrot_training - Step 36694: {'lr': 0.00043521461492964037, 'samples': 18787840, 'steps': 36694, 'loss/train': 1.2714495658874512}
-03/05/2022 08:36:05 - INFO - codeparrot_training - Step 36695: {'lr': 0.00043521105055373526, 'samples': 18788352, 'steps': 36695, 'loss/train': 1.5185444355010986}
-03/05/2022 08:36:07 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/05/2022 08:36:11 - INFO - codeparrot_training - Step 36696: {'lr': 0.000435207486094377, 'samples': 18788864, 'steps': 36696, 'loss/train': 1.5647741556167603}
-03/05/2022 08:36:14 - INFO - codeparrot_training - Step 36697: {'lr': 0.00043520392155156694, 'samples': 18789376, 'steps': 36697, 'loss/train': 1.5304478406906128}
-03/05/2022 08:36:16 - INFO - codeparrot_training - Skipping example with length 169 (seq_length=1024)
-03/05/2022 08:36:19 - INFO - codeparrot_training - Step 36698: {'lr': 0.000435200356925307, 'samples': 18789888, 'steps': 36698, 'loss/train': 1.0248026847839355}
-03/05/2022 08:36:22 - INFO - codeparrot_training - Step 36699: {'lr': 0.0004351967922155986, 'samples': 18790400, 'steps': 36699, 'loss/train': 1.649327278137207}
-03/05/2022 08:36:24 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/05/2022 08:36:27 - INFO - codeparrot_training - Step 36700: {'lr': 0.0004351932274224434, 'samples': 18790912, 'steps': 36700, 'loss/train': 1.4625699520111084}
-03/05/2022 08:36:31 - INFO - codeparrot_training - Step 36701: {'lr': 0.0004351896625458429, 'samples': 18791424, 'steps': 36701, 'loss/train': 1.0550603866577148}
-03/05/2022 08:36:33 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/05/2022 08:36:36 - INFO - codeparrot_training - Step 36702: {'lr': 0.0004351860975857989, 'samples': 18791936, 'steps': 36702, 'loss/train': 1.3552054166793823}
-03/05/2022 08:36:39 - INFO - codeparrot_training - Step 36703: {'lr': 0.00043518253254231276, 'samples': 18792448, 'steps': 36703, 'loss/train': 1.5167899131774902}
-03/05/2022 08:36:41 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/05/2022 08:36:44 - INFO - codeparrot_training - Step 36704: {'lr': 0.00043517896741538634, 'samples': 18792960, 'steps': 36704, 'loss/train': 1.8610939979553223}
-03/05/2022 08:36:47 - INFO - codeparrot_training - Step 36705: {'lr': 0.0004351754022050212, 'samples': 18793472, 'steps': 36705, 'loss/train': 2.204897880554199}
-03/05/2022 08:36:50 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/05/2022 08:36:53 - INFO - codeparrot_training - Step 36706: {'lr': 0.00043517183691121875, 'samples': 18793984, 'steps': 36706, 'loss/train': 1.5272445678710938}
-03/05/2022 08:36:56 - INFO - codeparrot_training - Step 36707: {'lr': 0.00043516827153398073, 'samples': 18794496, 'steps': 36707, 'loss/train': 1.2016654014587402}
-03/05/2022 08:36:58 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/05/2022 08:37:01 - INFO - codeparrot_training - Step 36708: {'lr': 0.0004351647060733088, 'samples': 18795008, 'steps': 36708, 'loss/train': 1.6325432062149048}
-03/05/2022 08:37:04 - INFO - codeparrot_training - Step 36709: {'lr': 0.00043516114052920453, 'samples': 18795520, 'steps': 36709, 'loss/train': 1.5337028503417969}
-03/05/2022 08:37:06 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/05/2022 08:37:10 - INFO - codeparrot_training - Step 36710: {'lr': 0.00043515757490166944, 'samples': 18796032, 'steps': 36710, 'loss/train': 1.787655234336853}
-03/05/2022 08:37:13 - INFO - codeparrot_training - Step 36711: {'lr': 0.00043515400919070526, 'samples': 18796544, 'steps': 36711, 'loss/train': 1.1704010963439941}
-03/05/2022 08:37:16 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/05/2022 08:37:19 - INFO - codeparrot_training - Step 36712: {'lr': 0.0004351504433963135, 'samples': 18797056, 'steps': 36712, 'loss/train': 0.24939727783203125}
-03/05/2022 08:37:22 - INFO - codeparrot_training - Step 36713: {'lr': 0.0004351468775184959, 'samples': 18797568, 'steps': 36713, 'loss/train': 3.1073429584503174}
-03/05/2022 08:37:25 - INFO - codeparrot_training - Step 36714: {'lr': 0.0004351433115572538, 'samples': 18798080, 'steps': 36714, 'loss/train': 1.1566107273101807}
-03/05/2022 08:37:25 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/05/2022 08:37:30 - INFO - codeparrot_training - Step 36715: {'lr': 0.00043513974551258913, 'samples': 18798592, 'steps': 36715, 'loss/train': 2.4987802505493164}
-03/05/2022 08:37:33 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/05/2022 08:37:36 - INFO - codeparrot_training - Step 36716: {'lr': 0.00043513617938450327, 'samples': 18799104, 'steps': 36716, 'loss/train': 1.4679028987884521}
-03/05/2022 08:37:39 - INFO - codeparrot_training - Step 36717: {'lr': 0.00043513261317299797, 'samples': 18799616, 'steps': 36717, 'loss/train': 2.269044876098633}
-03/05/2022 08:37:42 - INFO - codeparrot_training - Step 36718: {'lr': 0.00043512904687807475, 'samples': 18800128, 'steps': 36718, 'loss/train': 2.2696533203125}
-03/05/2022 08:37:43 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/05/2022 08:37:47 - INFO - codeparrot_training - Step 36719: {'lr': 0.00043512548049973523, 'samples': 18800640, 'steps': 36719, 'loss/train': 1.6756986379623413}
-03/05/2022 08:37:51 - INFO - codeparrot_training - Step 36720: {'lr': 0.00043512191403798095, 'samples': 18801152, 'steps': 36720, 'loss/train': 1.552201509475708}
-03/05/2022 08:37:51 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 08:37:56 - INFO - codeparrot_training - Step 36721: {'lr': 0.0004351183474928137, 'samples': 18801664, 'steps': 36721, 'loss/train': 1.1354302167892456}
-03/05/2022 08:37:59 - INFO - codeparrot_training - Step 36722: {'lr': 0.00043511478086423493, 'samples': 18802176, 'steps': 36722, 'loss/train': 1.8882936239242554}
-03/05/2022 08:38:00 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/05/2022 08:38:04 - INFO - codeparrot_training - Step 36723: {'lr': 0.0004351112141522463, 'samples': 18802688, 'steps': 36723, 'loss/train': 1.8290765285491943}
-03/05/2022 08:38:08 - INFO - codeparrot_training - Step 36724: {'lr': 0.00043510764735684945, 'samples': 18803200, 'steps': 36724, 'loss/train': 1.184261441230774}
-03/05/2022 08:38:08 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/05/2022 08:38:13 - INFO - codeparrot_training - Step 36725: {'lr': 0.0004351040804780459, 'samples': 18803712, 'steps': 36725, 'loss/train': 1.8711128234863281}
-03/05/2022 08:38:16 - INFO - codeparrot_training - Step 36726: {'lr': 0.00043510051351583733, 'samples': 18804224, 'steps': 36726, 'loss/train': 1.0512408018112183}
-03/05/2022 08:38:17 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/05/2022 08:38:21 - INFO - codeparrot_training - Step 36727: {'lr': 0.0004350969464702254, 'samples': 18804736, 'steps': 36727, 'loss/train': 1.9921079874038696}
-03/05/2022 08:38:24 - INFO - codeparrot_training - Step 36728: {'lr': 0.0004350933793412115, 'samples': 18805248, 'steps': 36728, 'loss/train': 0.132417693734169}
-03/05/2022 08:38:25 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/05/2022 08:38:30 - INFO - codeparrot_training - Step 36729: {'lr': 0.00043508981212879737, 'samples': 18805760, 'steps': 36729, 'loss/train': 1.6533011198043823}
-03/05/2022 08:38:33 - INFO - codeparrot_training - Step 36730: {'lr': 0.0004350862448329848, 'samples': 18806272, 'steps': 36730, 'loss/train': 1.3240827322006226}
-03/05/2022 08:38:33 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/05/2022 08:38:38 - INFO - codeparrot_training - Step 36731: {'lr': 0.00043508267745377504, 'samples': 18806784, 'steps': 36731, 'loss/train': 1.3252646923065186}
-03/05/2022 08:38:41 - INFO - codeparrot_training - Step 36732: {'lr': 0.00043507910999117003, 'samples': 18807296, 'steps': 36732, 'loss/train': 0.8646374344825745}
-03/05/2022 08:38:42 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/05/2022 08:38:46 - INFO - codeparrot_training - Step 36733: {'lr': 0.00043507554244517113, 'samples': 18807808, 'steps': 36733, 'loss/train': 2.1603941917419434}
-03/05/2022 08:38:50 - INFO - codeparrot_training - Step 36734: {'lr': 0.0004350719748157801, 'samples': 18808320, 'steps': 36734, 'loss/train': 1.5149245262145996}
-03/05/2022 08:38:50 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/05/2022 08:38:55 - INFO - codeparrot_training - Step 36735: {'lr': 0.00043506840710299844, 'samples': 18808832, 'steps': 36735, 'loss/train': 1.9402501583099365}
-03/05/2022 08:38:58 - INFO - codeparrot_training - Step 36736: {'lr': 0.00043506483930682785, 'samples': 18809344, 'steps': 36736, 'loss/train': 1.213230848312378}
-03/05/2022 08:38:58 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/05/2022 08:39:03 - INFO - codeparrot_training - Step 36737: {'lr': 0.0004350612714272699, 'samples': 18809856, 'steps': 36737, 'loss/train': 0.8067896962165833}
-03/05/2022 08:39:06 - INFO - codeparrot_training - Step 36738: {'lr': 0.0004350577034643262, 'samples': 18810368, 'steps': 36738, 'loss/train': 1.1526211500167847}
-03/05/2022 08:39:07 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/05/2022 08:39:12 - INFO - codeparrot_training - Step 36739: {'lr': 0.0004350541354179983, 'samples': 18810880, 'steps': 36739, 'loss/train': 2.2019336223602295}
-03/05/2022 08:39:15 - INFO - codeparrot_training - Step 36740: {'lr': 0.00043505056728828794, 'samples': 18811392, 'steps': 36740, 'loss/train': 1.470820426940918}
-03/05/2022 08:39:15 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/05/2022 08:39:20 - INFO - codeparrot_training - Step 36741: {'lr': 0.0004350469990751966, 'samples': 18811904, 'steps': 36741, 'loss/train': 1.558790922164917}
-03/05/2022 08:39:23 - INFO - codeparrot_training - Step 36742: {'lr': 0.000435043430778726, 'samples': 18812416, 'steps': 36742, 'loss/train': 1.9770536422729492}
-03/05/2022 08:39:23 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/05/2022 08:39:28 - INFO - codeparrot_training - Step 36743: {'lr': 0.00043503986239887765, 'samples': 18812928, 'steps': 36743, 'loss/train': 1.3653024435043335}
-03/05/2022 08:39:32 - INFO - codeparrot_training - Step 36744: {'lr': 0.0004350362939356532, 'samples': 18813440, 'steps': 36744, 'loss/train': 1.638286828994751}
-03/05/2022 08:39:32 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/05/2022 08:39:37 - INFO - codeparrot_training - Step 36745: {'lr': 0.00043503272538905423, 'samples': 18813952, 'steps': 36745, 'loss/train': 1.5700247287750244}
-03/05/2022 08:39:40 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/05/2022 08:39:42 - INFO - codeparrot_training - Step 36746: {'lr': 0.0004350291567590824, 'samples': 18814464, 'steps': 36746, 'loss/train': 1.4321941137313843}
-03/05/2022 08:39:45 - INFO - codeparrot_training - Step 36747: {'lr': 0.00043502558804573924, 'samples': 18814976, 'steps': 36747, 'loss/train': 1.7214068174362183}
-03/05/2022 08:39:48 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/05/2022 08:39:51 - INFO - codeparrot_training - Step 36748: {'lr': 0.0004350220192490264, 'samples': 18815488, 'steps': 36748, 'loss/train': 1.472598910331726}
-03/05/2022 08:39:54 - INFO - codeparrot_training - Step 36749: {'lr': 0.00043501845036894555, 'samples': 18816000, 'steps': 36749, 'loss/train': 2.095392942428589}
-03/05/2022 08:39:56 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/05/2022 08:39:59 - INFO - codeparrot_training - Step 36750: {'lr': 0.00043501488140549824, 'samples': 18816512, 'steps': 36750, 'loss/train': 1.8702508211135864}
-03/05/2022 08:40:02 - INFO - codeparrot_training - Step 36751: {'lr': 0.000435011312358686, 'samples': 18817024, 'steps': 36751, 'loss/train': 1.7569918632507324}
-03/05/2022 08:40:05 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 08:40:07 - INFO - codeparrot_training - Step 36752: {'lr': 0.0004350077432285106, 'samples': 18817536, 'steps': 36752, 'loss/train': 2.292306661605835}
-03/05/2022 08:40:11 - INFO - codeparrot_training - Step 36753: {'lr': 0.0004350041740149735, 'samples': 18818048, 'steps': 36753, 'loss/train': 1.3701976537704468}
-03/05/2022 08:40:13 - INFO - codeparrot_training - Skipping example with length 25 (seq_length=1024)
-03/05/2022 08:40:16 - INFO - codeparrot_training - Step 36754: {'lr': 0.00043500060471807645, 'samples': 18818560, 'steps': 36754, 'loss/train': 1.4870412349700928}
-03/05/2022 08:40:19 - INFO - codeparrot_training - Step 36755: {'lr': 0.000434997035337821, 'samples': 18819072, 'steps': 36755, 'loss/train': 1.5104273557662964}
-03/05/2022 08:40:22 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/05/2022 08:40:24 - INFO - codeparrot_training - Step 36756: {'lr': 0.0004349934658742086, 'samples': 18819584, 'steps': 36756, 'loss/train': 1.3527086973190308}
-03/05/2022 08:40:27 - INFO - codeparrot_training - Step 36757: {'lr': 0.00043498989632724105, 'samples': 18820096, 'steps': 36757, 'loss/train': 1.6256399154663086}
-03/05/2022 08:40:30 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/05/2022 08:40:33 - INFO - codeparrot_training - Step 36758: {'lr': 0.00043498632669692, 'samples': 18820608, 'steps': 36758, 'loss/train': 1.9504210948944092}
-03/05/2022 08:40:36 - INFO - codeparrot_training - Step 36759: {'lr': 0.0004349827569832469, 'samples': 18821120, 'steps': 36759, 'loss/train': 2.1131386756896973}
-03/05/2022 08:40:39 - INFO - codeparrot_training - Step 36760: {'lr': 0.00043497918718622344, 'samples': 18821632, 'steps': 36760, 'loss/train': 1.8500378131866455}
-03/05/2022 08:40:41 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 08:40:45 - INFO - codeparrot_training - Step 36761: {'lr': 0.0004349756173058512, 'samples': 18822144, 'steps': 36761, 'loss/train': 2.0238864421844482}
-03/05/2022 08:40:48 - INFO - codeparrot_training - Step 36762: {'lr': 0.0004349720473421318, 'samples': 18822656, 'steps': 36762, 'loss/train': 1.518053412437439}
-03/05/2022 08:40:49 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/05/2022 08:40:53 - INFO - codeparrot_training - Step 36763: {'lr': 0.00043496847729506685, 'samples': 18823168, 'steps': 36763, 'loss/train': 1.8443150520324707}
-03/05/2022 08:40:56 - INFO - codeparrot_training - Step 36764: {'lr': 0.000434964907164658, 'samples': 18823680, 'steps': 36764, 'loss/train': 2.555396556854248}
-03/05/2022 08:40:58 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/05/2022 08:41:02 - INFO - codeparrot_training - Step 36765: {'lr': 0.0004349613369509067, 'samples': 18824192, 'steps': 36765, 'loss/train': 1.7638988494873047}
-03/05/2022 08:41:05 - INFO - codeparrot_training - Step 36766: {'lr': 0.0004349577666538148, 'samples': 18824704, 'steps': 36766, 'loss/train': 2.237107992172241}
-03/05/2022 08:41:06 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/05/2022 08:41:10 - INFO - codeparrot_training - Step 36767: {'lr': 0.0004349541962733837, 'samples': 18825216, 'steps': 36767, 'loss/train': 1.9983699321746826}
-03/05/2022 08:41:13 - INFO - codeparrot_training - Step 36768: {'lr': 0.0004349506258096152, 'samples': 18825728, 'steps': 36768, 'loss/train': 1.5734697580337524}
-03/05/2022 08:41:15 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/05/2022 08:41:19 - INFO - codeparrot_training - Step 36769: {'lr': 0.00043494705526251064, 'samples': 18826240, 'steps': 36769, 'loss/train': 1.0660656690597534}
-03/05/2022 08:41:22 - INFO - codeparrot_training - Step 36770: {'lr': 0.00043494348463207197, 'samples': 18826752, 'steps': 36770, 'loss/train': 1.5581581592559814}
-03/05/2022 08:41:23 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/05/2022 08:41:27 - INFO - codeparrot_training - Step 36771: {'lr': 0.0004349399139183005, 'samples': 18827264, 'steps': 36771, 'loss/train': 0.9426736831665039}
-03/05/2022 08:41:30 - INFO - codeparrot_training - Step 36772: {'lr': 0.000434936343121198, 'samples': 18827776, 'steps': 36772, 'loss/train': 1.6663047075271606}
-03/05/2022 08:41:32 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/05/2022 08:41:35 - INFO - codeparrot_training - Step 36773: {'lr': 0.000434932772240766, 'samples': 18828288, 'steps': 36773, 'loss/train': 0.2263745814561844}
-03/05/2022 08:41:39 - INFO - codeparrot_training - Step 36774: {'lr': 0.0004349292012770062, 'samples': 18828800, 'steps': 36774, 'loss/train': 1.420348048210144}
-03/05/2022 08:41:40 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 08:41:44 - INFO - codeparrot_training - Step 36775: {'lr': 0.00043492563022992013, 'samples': 18829312, 'steps': 36775, 'loss/train': 1.5060628652572632}
-03/05/2022 08:41:47 - INFO - codeparrot_training - Step 36776: {'lr': 0.00043492205909950943, 'samples': 18829824, 'steps': 36776, 'loss/train': 1.8419787883758545}
-03/05/2022 08:41:48 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/05/2022 08:41:52 - INFO - codeparrot_training - Step 36777: {'lr': 0.0004349184878857757, 'samples': 18830336, 'steps': 36777, 'loss/train': 1.6692277193069458}
-03/05/2022 08:41:56 - INFO - codeparrot_training - Step 36778: {'lr': 0.0004349149165887205, 'samples': 18830848, 'steps': 36778, 'loss/train': 1.6683770418167114}
-03/05/2022 08:41:57 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/05/2022 08:42:01 - INFO - codeparrot_training - Step 36779: {'lr': 0.0004349113452083456, 'samples': 18831360, 'steps': 36779, 'loss/train': 0.6113933324813843}
-03/05/2022 08:42:04 - INFO - codeparrot_training - Step 36780: {'lr': 0.00043490777374465244, 'samples': 18831872, 'steps': 36780, 'loss/train': 1.6047180891036987}
-03/05/2022 08:42:05 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/05/2022 08:42:09 - INFO - codeparrot_training - Step 36781: {'lr': 0.0004349042021976427, 'samples': 18832384, 'steps': 36781, 'loss/train': 1.9414072036743164}
-03/05/2022 08:42:12 - INFO - codeparrot_training - Step 36782: {'lr': 0.000434900630567318, 'samples': 18832896, 'steps': 36782, 'loss/train': 1.4783483743667603}
-03/05/2022 08:42:14 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/05/2022 08:42:18 - INFO - codeparrot_training - Step 36783: {'lr': 0.00043489705885367986, 'samples': 18833408, 'steps': 36783, 'loss/train': 1.5761252641677856}
-03/05/2022 08:42:21 - INFO - codeparrot_training - Step 36784: {'lr': 0.00043489348705673, 'samples': 18833920, 'steps': 36784, 'loss/train': 2.3001670837402344}
-03/05/2022 08:42:22 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 08:42:27 - INFO - codeparrot_training - Step 36785: {'lr': 0.00043488991517647, 'samples': 18834432, 'steps': 36785, 'loss/train': 2.4192380905151367}
-03/05/2022 08:42:30 - INFO - codeparrot_training - Step 36786: {'lr': 0.00043488634321290146, 'samples': 18834944, 'steps': 36786, 'loss/train': 1.9931823015213013}
-03/05/2022 08:42:33 - INFO - codeparrot_training - Step 36787: {'lr': 0.000434882771166026, 'samples': 18835456, 'steps': 36787, 'loss/train': 0.9560977816581726}
-03/05/2022 08:42:33 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/05/2022 08:42:38 - INFO - codeparrot_training - Step 36788: {'lr': 0.00043487919903584515, 'samples': 18835968, 'steps': 36788, 'loss/train': 1.1297003030776978}
-03/05/2022 08:42:41 - INFO - codeparrot_training - Step 36789: {'lr': 0.00043487562682236066, 'samples': 18836480, 'steps': 36789, 'loss/train': 1.416741132736206}
-03/05/2022 08:42:41 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 08:42:47 - INFO - codeparrot_training - Step 36790: {'lr': 0.000434872054525574, 'samples': 18836992, 'steps': 36790, 'loss/train': 1.4848045110702515}
-03/05/2022 08:42:49 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 08:42:52 - INFO - codeparrot_training - Step 36791: {'lr': 0.00043486848214548693, 'samples': 18837504, 'steps': 36791, 'loss/train': 1.6882257461547852}
-03/05/2022 08:42:55 - INFO - codeparrot_training - Step 36792: {'lr': 0.0004348649096821009, 'samples': 18838016, 'steps': 36792, 'loss/train': 1.5576146841049194}
-03/05/2022 08:42:58 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/05/2022 08:43:00 - INFO - codeparrot_training - Step 36793: {'lr': 0.0004348613371354176, 'samples': 18838528, 'steps': 36793, 'loss/train': 1.9979488849639893}
-03/05/2022 08:43:04 - INFO - codeparrot_training - Step 36794: {'lr': 0.0004348577645054387, 'samples': 18839040, 'steps': 36794, 'loss/train': 2.000835657119751}
-03/05/2022 08:43:06 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/05/2022 08:43:09 - INFO - codeparrot_training - Step 36795: {'lr': 0.0004348541917921657, 'samples': 18839552, 'steps': 36795, 'loss/train': 1.9691299200057983}
-03/05/2022 08:43:12 - INFO - codeparrot_training - Step 36796: {'lr': 0.0004348506189956002, 'samples': 18840064, 'steps': 36796, 'loss/train': 2.1404619216918945}
-03/05/2022 08:43:15 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/05/2022 08:43:17 - INFO - codeparrot_training - Step 36797: {'lr': 0.0004348470461157439, 'samples': 18840576, 'steps': 36797, 'loss/train': 1.600678563117981}
-03/05/2022 08:43:21 - INFO - codeparrot_training - Step 36798: {'lr': 0.0004348434731525984, 'samples': 18841088, 'steps': 36798, 'loss/train': 1.7130168676376343}
-03/05/2022 08:43:23 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 08:43:26 - INFO - codeparrot_training - Step 36799: {'lr': 0.00043483990010616524, 'samples': 18841600, 'steps': 36799, 'loss/train': 1.6656779050827026}
-03/05/2022 08:43:29 - INFO - codeparrot_training - Step 36800: {'lr': 0.00043483632697644616, 'samples': 18842112, 'steps': 36800, 'loss/train': 1.653520107269287}
-03/05/2022 08:43:32 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 08:43:34 - INFO - codeparrot_training - Step 36801: {'lr': 0.00043483275376344257, 'samples': 18842624, 'steps': 36801, 'loss/train': 0.8258717656135559}
-03/05/2022 08:43:37 - INFO - codeparrot_training - Step 36802: {'lr': 0.00043482918046715627, 'samples': 18843136, 'steps': 36802, 'loss/train': 0.6811335682868958}
-03/05/2022 08:43:40 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/05/2022 08:43:43 - INFO - codeparrot_training - Step 36803: {'lr': 0.00043482560708758876, 'samples': 18843648, 'steps': 36803, 'loss/train': 1.8351478576660156}
-03/05/2022 08:43:46 - INFO - codeparrot_training - Step 36804: {'lr': 0.0004348220336247417, 'samples': 18844160, 'steps': 36804, 'loss/train': 2.422506332397461}
-03/05/2022 08:43:48 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/05/2022 08:43:51 - INFO - codeparrot_training - Step 36805: {'lr': 0.0004348184600786167, 'samples': 18844672, 'steps': 36805, 'loss/train': 1.8859761953353882}
-03/05/2022 08:43:54 - INFO - codeparrot_training - Step 36806: {'lr': 0.0004348148864492153, 'samples': 18845184, 'steps': 36806, 'loss/train': 2.145763635635376}
-03/05/2022 08:43:57 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/05/2022 08:44:00 - INFO - codeparrot_training - Step 36807: {'lr': 0.00043481131273653926, 'samples': 18845696, 'steps': 36807, 'loss/train': 1.997817039489746}
-03/05/2022 08:44:03 - INFO - codeparrot_training - Step 36808: {'lr': 0.00043480773894059, 'samples': 18846208, 'steps': 36808, 'loss/train': 1.3425543308258057}
-03/05/2022 08:44:05 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/05/2022 08:44:08 - INFO - codeparrot_training - Step 36809: {'lr': 0.0004348041650613692, 'samples': 18846720, 'steps': 36809, 'loss/train': 1.0338274240493774}
-03/05/2022 08:44:11 - INFO - codeparrot_training - Step 36810: {'lr': 0.0004348005910988786, 'samples': 18847232, 'steps': 36810, 'loss/train': 1.562526822090149}
-03/05/2022 08:44:13 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/05/2022 08:44:16 - INFO - codeparrot_training - Step 36811: {'lr': 0.0004347970170531197, 'samples': 18847744, 'steps': 36811, 'loss/train': 1.9032257795333862}
-03/05/2022 08:44:20 - INFO - codeparrot_training - Step 36812: {'lr': 0.000434793442924094, 'samples': 18848256, 'steps': 36812, 'loss/train': 0.7825396656990051}
-03/05/2022 08:44:21 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/05/2022 08:44:25 - INFO - codeparrot_training - Step 36813: {'lr': 0.0004347898687118033, 'samples': 18848768, 'steps': 36813, 'loss/train': 1.714695692062378}
-03/05/2022 08:44:28 - INFO - codeparrot_training - Step 36814: {'lr': 0.0004347862944162492, 'samples': 18849280, 'steps': 36814, 'loss/train': 1.0270723104476929}
-03/05/2022 08:44:30 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/05/2022 08:44:33 - INFO - codeparrot_training - Step 36815: {'lr': 0.00043478272003743315, 'samples': 18849792, 'steps': 36815, 'loss/train': 1.754807710647583}
-03/05/2022 08:44:37 - INFO - codeparrot_training - Step 36816: {'lr': 0.0004347791455753569, 'samples': 18850304, 'steps': 36816, 'loss/train': 1.785197138786316}
-03/05/2022 08:44:39 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/05/2022 08:44:42 - INFO - codeparrot_training - Step 36817: {'lr': 0.00043477557103002197, 'samples': 18850816, 'steps': 36817, 'loss/train': 1.464093804359436}
-03/05/2022 08:44:45 - INFO - codeparrot_training - Step 36818: {'lr': 0.00043477199640143004, 'samples': 18851328, 'steps': 36818, 'loss/train': 2.0849695205688477}
-03/05/2022 08:44:47 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/05/2022 08:44:50 - INFO - codeparrot_training - Step 36819: {'lr': 0.00043476842168958276, 'samples': 18851840, 'steps': 36819, 'loss/train': 1.8952441215515137}
-03/05/2022 08:44:53 - INFO - codeparrot_training - Step 36820: {'lr': 0.0004347648468944816, 'samples': 18852352, 'steps': 36820, 'loss/train': 1.5244258642196655}
-03/05/2022 08:44:56 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/05/2022 08:44:59 - INFO - codeparrot_training - Step 36821: {'lr': 0.0004347612720161283, 'samples': 18852864, 'steps': 36821, 'loss/train': 2.0413427352905273}
-03/05/2022 08:45:02 - INFO - codeparrot_training - Step 36822: {'lr': 0.00043475769705452437, 'samples': 18853376, 'steps': 36822, 'loss/train': 2.0477137565612793}
-03/05/2022 08:45:04 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 08:45:07 - INFO - codeparrot_training - Step 36823: {'lr': 0.00043475412200967155, 'samples': 18853888, 'steps': 36823, 'loss/train': 1.9837555885314941}
-03/05/2022 08:45:10 - INFO - codeparrot_training - Step 36824: {'lr': 0.00043475054688157136, 'samples': 18854400, 'steps': 36824, 'loss/train': 1.7392351627349854}
-03/05/2022 08:45:13 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/05/2022 08:45:16 - INFO - codeparrot_training - Step 36825: {'lr': 0.00043474697167022536, 'samples': 18854912, 'steps': 36825, 'loss/train': 1.266484260559082}
-03/05/2022 08:45:19 - INFO - codeparrot_training - Step 36826: {'lr': 0.0004347433963756353, 'samples': 18855424, 'steps': 36826, 'loss/train': 1.501827597618103}
-03/05/2022 08:45:21 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/05/2022 08:45:24 - INFO - codeparrot_training - Step 36827: {'lr': 0.0004347398209978027, 'samples': 18855936, 'steps': 36827, 'loss/train': 2.126845121383667}
-03/05/2022 08:45:27 - INFO - codeparrot_training - Step 36828: {'lr': 0.0004347362455367292, 'samples': 18856448, 'steps': 36828, 'loss/train': 1.9292513132095337}
-03/05/2022 08:45:29 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 08:45:32 - INFO - codeparrot_training - Step 36829: {'lr': 0.0004347326699924163, 'samples': 18856960, 'steps': 36829, 'loss/train': 2.057068347930908}
-03/05/2022 08:45:36 - INFO - codeparrot_training - Step 36830: {'lr': 0.0004347290943648658, 'samples': 18857472, 'steps': 36830, 'loss/train': 2.2075035572052}
-03/05/2022 08:45:37 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/05/2022 08:45:41 - INFO - codeparrot_training - Step 36831: {'lr': 0.00043472551865407917, 'samples': 18857984, 'steps': 36831, 'loss/train': 1.630979299545288}
-03/05/2022 08:45:44 - INFO - codeparrot_training - Step 36832: {'lr': 0.0004347219428600581, 'samples': 18858496, 'steps': 36832, 'loss/train': 1.6228761672973633}
-03/05/2022 08:45:46 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/05/2022 08:45:49 - INFO - codeparrot_training - Step 36833: {'lr': 0.0004347183669828042, 'samples': 18859008, 'steps': 36833, 'loss/train': 1.7341316938400269}
-03/05/2022 08:45:52 - INFO - codeparrot_training - Step 36834: {'lr': 0.00043471479102231904, 'samples': 18859520, 'steps': 36834, 'loss/train': 2.6173717975616455}
-03/05/2022 08:45:54 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/05/2022 08:45:58 - INFO - codeparrot_training - Step 36835: {'lr': 0.0004347112149786042, 'samples': 18860032, 'steps': 36835, 'loss/train': 1.555933952331543}
-03/05/2022 08:46:01 - INFO - codeparrot_training - Step 36836: {'lr': 0.0004347076388516614, 'samples': 18860544, 'steps': 36836, 'loss/train': 0.9737286567687988}
-03/05/2022 08:46:02 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 08:46:06 - INFO - codeparrot_training - Step 36837: {'lr': 0.00043470406264149215, 'samples': 18861056, 'steps': 36837, 'loss/train': 2.0914418697357178}
-03/05/2022 08:46:09 - INFO - codeparrot_training - Step 36838: {'lr': 0.00043470048634809813, 'samples': 18861568, 'steps': 36838, 'loss/train': 1.548585057258606}
-03/05/2022 08:46:11 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/05/2022 08:46:15 - INFO - codeparrot_training - Step 36839: {'lr': 0.00043469690997148086, 'samples': 18862080, 'steps': 36839, 'loss/train': 1.297490119934082}
-03/05/2022 08:46:18 - INFO - codeparrot_training - Step 36840: {'lr': 0.00043469333351164207, 'samples': 18862592, 'steps': 36840, 'loss/train': 1.2585265636444092}
-03/05/2022 08:46:19 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/05/2022 08:46:23 - INFO - codeparrot_training - Step 36841: {'lr': 0.0004346897569685833, 'samples': 18863104, 'steps': 36841, 'loss/train': 1.389769434928894}
-03/05/2022 08:46:26 - INFO - codeparrot_training - Step 36842: {'lr': 0.00043468618034230613, 'samples': 18863616, 'steps': 36842, 'loss/train': 1.8585312366485596}
-03/05/2022 08:46:27 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 08:46:31 - INFO - codeparrot_training - Step 36843: {'lr': 0.00043468260363281234, 'samples': 18864128, 'steps': 36843, 'loss/train': 1.4459878206253052}
-03/05/2022 08:46:34 - INFO - codeparrot_training - Step 36844: {'lr': 0.0004346790268401033, 'samples': 18864640, 'steps': 36844, 'loss/train': 1.455426573753357}
-03/05/2022 08:46:36 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/05/2022 08:46:40 - INFO - codeparrot_training - Step 36845: {'lr': 0.00043467544996418075, 'samples': 18865152, 'steps': 36845, 'loss/train': 1.1576275825500488}
-03/05/2022 08:46:43 - INFO - codeparrot_training - Step 36846: {'lr': 0.0004346718730050463, 'samples': 18865664, 'steps': 36846, 'loss/train': 1.2133681774139404}
-03/05/2022 08:46:44 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/05/2022 08:46:48 - INFO - codeparrot_training - Step 36847: {'lr': 0.0004346682959627016, 'samples': 18866176, 'steps': 36847, 'loss/train': 1.1080384254455566}
-03/05/2022 08:46:51 - INFO - codeparrot_training - Step 36848: {'lr': 0.0004346647188371482, 'samples': 18866688, 'steps': 36848, 'loss/train': 1.8695937395095825}
-03/05/2022 08:46:53 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/05/2022 08:46:57 - INFO - codeparrot_training - Step 36849: {'lr': 0.00043466114162838765, 'samples': 18867200, 'steps': 36849, 'loss/train': 1.1918002367019653}
-03/05/2022 08:47:00 - INFO - codeparrot_training - Step 36850: {'lr': 0.00043465756433642175, 'samples': 18867712, 'steps': 36850, 'loss/train': 1.6666258573532104}
-03/05/2022 08:47:01 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/05/2022 08:47:05 - INFO - codeparrot_training - Step 36851: {'lr': 0.0004346539869612519, 'samples': 18868224, 'steps': 36851, 'loss/train': 2.2172508239746094}
-03/05/2022 08:47:08 - INFO - codeparrot_training - Step 36852: {'lr': 0.0004346504095028799, 'samples': 18868736, 'steps': 36852, 'loss/train': 1.7251343727111816}
-03/05/2022 08:47:09 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 08:47:13 - INFO - codeparrot_training - Step 36853: {'lr': 0.00043464683196130726, 'samples': 18869248, 'steps': 36853, 'loss/train': 3.0868568420410156}
-03/05/2022 08:47:17 - INFO - codeparrot_training - Step 36854: {'lr': 0.00043464325433653563, 'samples': 18869760, 'steps': 36854, 'loss/train': 0.5785963535308838}
-03/05/2022 08:47:17 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/05/2022 08:47:22 - INFO - codeparrot_training - Step 36855: {'lr': 0.0004346396766285665, 'samples': 18870272, 'steps': 36855, 'loss/train': 1.2966419458389282}
-03/05/2022 08:47:25 - INFO - codeparrot_training - Step 36856: {'lr': 0.0004346360988374016, 'samples': 18870784, 'steps': 36856, 'loss/train': 1.8204244375228882}
-03/05/2022 08:47:27 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/05/2022 08:47:30 - INFO - codeparrot_training - Step 36857: {'lr': 0.0004346325209630426, 'samples': 18871296, 'steps': 36857, 'loss/train': 1.231301188468933}
-03/05/2022 08:47:34 - INFO - codeparrot_training - Step 36858: {'lr': 0.00043462894300549097, 'samples': 18871808, 'steps': 36858, 'loss/train': 2.390886068344116}
-03/05/2022 08:47:35 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 08:47:39 - INFO - codeparrot_training - Step 36859: {'lr': 0.0004346253649647485, 'samples': 18872320, 'steps': 36859, 'loss/train': 1.7816247940063477}
-03/05/2022 08:47:42 - INFO - codeparrot_training - Step 36860: {'lr': 0.00043462178684081657, 'samples': 18872832, 'steps': 36860, 'loss/train': 1.5157221555709839}
-03/05/2022 08:47:43 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 08:47:47 - INFO - codeparrot_training - Step 36861: {'lr': 0.00043461820863369697, 'samples': 18873344, 'steps': 36861, 'loss/train': 0.31511035561561584}
-03/05/2022 08:47:50 - INFO - codeparrot_training - Step 36862: {'lr': 0.0004346146303433912, 'samples': 18873856, 'steps': 36862, 'loss/train': 1.6753982305526733}
-03/05/2022 08:47:51 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/05/2022 08:47:56 - INFO - codeparrot_training - Step 36863: {'lr': 0.00043461105196990093, 'samples': 18874368, 'steps': 36863, 'loss/train': 1.4402275085449219}
-03/05/2022 08:47:59 - INFO - codeparrot_training - Step 36864: {'lr': 0.0004346074735132278, 'samples': 18874880, 'steps': 36864, 'loss/train': 1.2896029949188232}
-03/05/2022 08:48:00 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 08:48:04 - INFO - codeparrot_training - Step 36865: {'lr': 0.0004346038949733734, 'samples': 18875392, 'steps': 36865, 'loss/train': 1.9609742164611816}
-03/05/2022 08:48:07 - INFO - codeparrot_training - Step 36866: {'lr': 0.0004346003163503393, 'samples': 18875904, 'steps': 36866, 'loss/train': 2.161099672317505}
-03/05/2022 08:48:08 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/05/2022 08:48:12 - INFO - codeparrot_training - Step 36867: {'lr': 0.00043459673764412713, 'samples': 18876416, 'steps': 36867, 'loss/train': 1.4677633047103882}
-03/05/2022 08:48:16 - INFO - codeparrot_training - Step 36868: {'lr': 0.0004345931588547386, 'samples': 18876928, 'steps': 36868, 'loss/train': 1.6497422456741333}
-03/05/2022 08:48:16 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/05/2022 08:48:21 - INFO - codeparrot_training - Step 36869: {'lr': 0.00043458957998217517, 'samples': 18877440, 'steps': 36869, 'loss/train': 1.5824792385101318}
-03/05/2022 08:48:24 - INFO - codeparrot_training - Step 36870: {'lr': 0.0004345860010264385, 'samples': 18877952, 'steps': 36870, 'loss/train': 1.2303905487060547}
-03/05/2022 08:48:26 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/05/2022 08:48:30 - INFO - codeparrot_training - Step 36871: {'lr': 0.00043458242198753035, 'samples': 18878464, 'steps': 36871, 'loss/train': 2.087001323699951}
-03/05/2022 08:48:33 - INFO - codeparrot_training - Step 36872: {'lr': 0.00043457884286545216, 'samples': 18878976, 'steps': 36872, 'loss/train': 1.6326885223388672}
-03/05/2022 08:48:38 - INFO - codeparrot_training - Step 36873: {'lr': 0.0004345752636602055, 'samples': 18879488, 'steps': 36873, 'loss/train': 2.3659703731536865}
-03/05/2022 08:48:41 - INFO - codeparrot_training - Step 36874: {'lr': 0.00043457168437179217, 'samples': 18880000, 'steps': 36874, 'loss/train': 2.2185091972351074}
-03/05/2022 08:48:43 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/05/2022 08:48:46 - INFO - codeparrot_training - Step 36875: {'lr': 0.00043456810500021363, 'samples': 18880512, 'steps': 36875, 'loss/train': 1.7475706338882446}
-03/05/2022 08:48:49 - INFO - codeparrot_training - Step 36876: {'lr': 0.00043456452554547153, 'samples': 18881024, 'steps': 36876, 'loss/train': 2.0513062477111816}
-03/05/2022 08:48:51 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/05/2022 08:48:55 - INFO - codeparrot_training - Step 36877: {'lr': 0.0004345609460075676, 'samples': 18881536, 'steps': 36877, 'loss/train': 2.246486186981201}
-03/05/2022 08:48:58 - INFO - codeparrot_training - Step 36878: {'lr': 0.00043455736638650335, 'samples': 18882048, 'steps': 36878, 'loss/train': 1.3590720891952515}
-03/05/2022 08:48:59 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/05/2022 08:49:03 - INFO - codeparrot_training - Step 36879: {'lr': 0.0004345537866822803, 'samples': 18882560, 'steps': 36879, 'loss/train': 2.12926983833313}
-03/05/2022 08:49:06 - INFO - codeparrot_training - Step 36880: {'lr': 0.0004345502068949002, 'samples': 18883072, 'steps': 36880, 'loss/train': 1.9532108306884766}
-03/05/2022 08:49:08 - INFO - codeparrot_training - Skipping example with length 822 (seq_length=1024)
-03/05/2022 08:49:12 - INFO - codeparrot_training - Step 36881: {'lr': 0.0004345466270243646, 'samples': 18883584, 'steps': 36881, 'loss/train': 1.7815518379211426}
-03/05/2022 08:49:15 - INFO - codeparrot_training - Step 36882: {'lr': 0.0004345430470706753, 'samples': 18884096, 'steps': 36882, 'loss/train': 1.7593061923980713}
-03/05/2022 08:49:16 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/05/2022 08:49:20 - INFO - codeparrot_training - Step 36883: {'lr': 0.00043453946703383354, 'samples': 18884608, 'steps': 36883, 'loss/train': 3.3658955097198486}
-03/05/2022 08:49:23 - INFO - codeparrot_training - Step 36884: {'lr': 0.00043453588691384125, 'samples': 18885120, 'steps': 36884, 'loss/train': 1.5409979820251465}
-03/05/2022 08:49:24 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/05/2022 08:49:28 - INFO - codeparrot_training - Step 36885: {'lr': 0.0004345323067106999, 'samples': 18885632, 'steps': 36885, 'loss/train': 1.5530903339385986}
-03/05/2022 08:49:32 - INFO - codeparrot_training - Step 36886: {'lr': 0.00043452872642441124, 'samples': 18886144, 'steps': 36886, 'loss/train': 1.4350181818008423}
-03/05/2022 08:49:33 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/05/2022 08:49:37 - INFO - codeparrot_training - Step 36887: {'lr': 0.0004345251460549766, 'samples': 18886656, 'steps': 36887, 'loss/train': 1.5833184719085693}
-03/05/2022 08:49:40 - INFO - codeparrot_training - Step 36888: {'lr': 0.0004345215656023979, 'samples': 18887168, 'steps': 36888, 'loss/train': 1.290075421333313}
-03/05/2022 08:49:42 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/05/2022 08:49:45 - INFO - codeparrot_training - Step 36889: {'lr': 0.0004345179850666766, 'samples': 18887680, 'steps': 36889, 'loss/train': 1.770676612854004}
-03/05/2022 08:49:49 - INFO - codeparrot_training - Step 36890: {'lr': 0.0004345144044478144, 'samples': 18888192, 'steps': 36890, 'loss/train': 1.5681612491607666}
-03/05/2022 08:49:50 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 08:49:54 - INFO - codeparrot_training - Step 36891: {'lr': 0.0004345108237458128, 'samples': 18888704, 'steps': 36891, 'loss/train': 2.8903255462646484}
-03/05/2022 08:49:57 - INFO - codeparrot_training - Step 36892: {'lr': 0.00043450724296067344, 'samples': 18889216, 'steps': 36892, 'loss/train': 1.852860450744629}
-03/05/2022 08:49:59 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/05/2022 08:50:02 - INFO - codeparrot_training - Step 36893: {'lr': 0.00043450366209239803, 'samples': 18889728, 'steps': 36893, 'loss/train': 1.6656923294067383}
-03/05/2022 08:50:05 - INFO - codeparrot_training - Step 36894: {'lr': 0.0004345000811409881, 'samples': 18890240, 'steps': 36894, 'loss/train': 1.9010053873062134}
-03/05/2022 08:50:07 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/05/2022 08:50:11 - INFO - codeparrot_training - Step 36895: {'lr': 0.0004344965001064453, 'samples': 18890752, 'steps': 36895, 'loss/train': 1.136331558227539}
-03/05/2022 08:50:14 - INFO - codeparrot_training - Step 36896: {'lr': 0.0004344929189887712, 'samples': 18891264, 'steps': 36896, 'loss/train': 1.5710711479187012}
-03/05/2022 08:50:15 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/05/2022 08:50:19 - INFO - codeparrot_training - Step 36897: {'lr': 0.0004344893377879674, 'samples': 18891776, 'steps': 36897, 'loss/train': 1.7728002071380615}
-03/05/2022 08:50:22 - INFO - codeparrot_training - Step 36898: {'lr': 0.00043448575650403555, 'samples': 18892288, 'steps': 36898, 'loss/train': 1.6509506702423096}
-03/05/2022 08:50:24 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/05/2022 08:50:28 - INFO - codeparrot_training - Step 36899: {'lr': 0.00043448217513697727, 'samples': 18892800, 'steps': 36899, 'loss/train': 1.4198256731033325}
-03/05/2022 08:50:31 - INFO - codeparrot_training - Step 36900: {'lr': 0.0004344785936867942, 'samples': 18893312, 'steps': 36900, 'loss/train': 1.507174015045166}
-03/05/2022 08:50:32 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/05/2022 08:50:36 - INFO - codeparrot_training - Step 36901: {'lr': 0.00043447501215348794, 'samples': 18893824, 'steps': 36901, 'loss/train': 1.853712558746338}
-03/05/2022 08:50:40 - INFO - codeparrot_training - Step 36902: {'lr': 0.00043447143053706007, 'samples': 18894336, 'steps': 36902, 'loss/train': 1.724510669708252}
-03/05/2022 08:50:41 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 08:50:45 - INFO - codeparrot_training - Step 36903: {'lr': 0.00043446784883751223, 'samples': 18894848, 'steps': 36903, 'loss/train': 1.555845022201538}
-03/05/2022 08:50:48 - INFO - codeparrot_training - Step 36904: {'lr': 0.000434464267054846, 'samples': 18895360, 'steps': 36904, 'loss/train': 1.8463436365127563}
-03/05/2022 08:50:50 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/05/2022 08:50:53 - INFO - codeparrot_training - Step 36905: {'lr': 0.000434460685189063, 'samples': 18895872, 'steps': 36905, 'loss/train': 1.5736523866653442}
-03/05/2022 08:50:56 - INFO - codeparrot_training - Step 36906: {'lr': 0.0004344571032401649, 'samples': 18896384, 'steps': 36906, 'loss/train': 2.0981554985046387}
-03/05/2022 08:50:58 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/05/2022 08:51:02 - INFO - codeparrot_training - Step 36907: {'lr': 0.0004344535212081533, 'samples': 18896896, 'steps': 36907, 'loss/train': 0.8352473974227905}
-03/05/2022 08:51:05 - INFO - codeparrot_training - Step 36908: {'lr': 0.0004344499390930298, 'samples': 18897408, 'steps': 36908, 'loss/train': 1.240767240524292}
-03/05/2022 08:51:06 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/05/2022 08:51:10 - INFO - codeparrot_training - Step 36909: {'lr': 0.0004344463568947959, 'samples': 18897920, 'steps': 36909, 'loss/train': 1.0035650730133057}
-03/05/2022 08:51:13 - INFO - codeparrot_training - Step 36910: {'lr': 0.0004344427746134534, 'samples': 18898432, 'steps': 36910, 'loss/train': 2.763331890106201}
-03/05/2022 08:51:15 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/05/2022 08:51:19 - INFO - codeparrot_training - Step 36911: {'lr': 0.0004344391922490037, 'samples': 18898944, 'steps': 36911, 'loss/train': 0.28242018818855286}
-03/05/2022 08:51:22 - INFO - codeparrot_training - Step 36912: {'lr': 0.0004344356098014487, 'samples': 18899456, 'steps': 36912, 'loss/train': 1.8394434452056885}
-03/05/2022 08:51:23 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/05/2022 08:51:27 - INFO - codeparrot_training - Step 36913: {'lr': 0.0004344320272707898, 'samples': 18899968, 'steps': 36913, 'loss/train': 1.5607521533966064}
-03/05/2022 08:51:30 - INFO - codeparrot_training - Step 36914: {'lr': 0.0004344284446570287, 'samples': 18900480, 'steps': 36914, 'loss/train': 1.938348412513733}
-03/05/2022 08:51:32 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/05/2022 08:51:36 - INFO - codeparrot_training - Step 36915: {'lr': 0.00043442486196016697, 'samples': 18900992, 'steps': 36915, 'loss/train': 0.8162152171134949}
-03/05/2022 08:51:39 - INFO - codeparrot_training - Step 36916: {'lr': 0.00043442127918020624, 'samples': 18901504, 'steps': 36916, 'loss/train': 1.7783260345458984}
-03/05/2022 08:51:41 - INFO - codeparrot_training - Skipping example with length 892 (seq_length=1024)
-03/05/2022 08:51:44 - INFO - codeparrot_training - Step 36917: {'lr': 0.00043441769631714813, 'samples': 18902016, 'steps': 36917, 'loss/train': 1.477062702178955}
-03/05/2022 08:51:47 - INFO - codeparrot_training - Step 36918: {'lr': 0.0004344141133709943, 'samples': 18902528, 'steps': 36918, 'loss/train': 1.8917760848999023}
-03/05/2022 08:51:49 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/05/2022 08:51:53 - INFO - codeparrot_training - Step 36919: {'lr': 0.00043441053034174625, 'samples': 18903040, 'steps': 36919, 'loss/train': 1.86081862449646}
-03/05/2022 08:51:56 - INFO - codeparrot_training - Step 36920: {'lr': 0.00043440694722940567, 'samples': 18903552, 'steps': 36920, 'loss/train': 0.9477598667144775}
-03/05/2022 08:51:58 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/05/2022 08:52:01 - INFO - codeparrot_training - Step 36921: {'lr': 0.00043440336403397417, 'samples': 18904064, 'steps': 36921, 'loss/train': 2.010540008544922}
-03/05/2022 08:52:04 - INFO - codeparrot_training - Step 36922: {'lr': 0.00043439978075545337, 'samples': 18904576, 'steps': 36922, 'loss/train': 1.3981226682662964}
-03/05/2022 08:52:06 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/05/2022 08:52:09 - INFO - codeparrot_training - Step 36923: {'lr': 0.0004343961973938449, 'samples': 18905088, 'steps': 36923, 'loss/train': 0.2985639274120331}
-03/05/2022 08:52:13 - INFO - codeparrot_training - Step 36924: {'lr': 0.00043439261394915033, 'samples': 18905600, 'steps': 36924, 'loss/train': 1.7021766901016235}
-03/05/2022 08:52:15 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/05/2022 08:52:18 - INFO - codeparrot_training - Step 36925: {'lr': 0.0004343890304213713, 'samples': 18906112, 'steps': 36925, 'loss/train': 2.1532468795776367}
-03/05/2022 08:52:21 - INFO - codeparrot_training - Step 36926: {'lr': 0.0004343854468105094, 'samples': 18906624, 'steps': 36926, 'loss/train': 0.13509312272071838}
-03/05/2022 08:52:23 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/05/2022 08:52:26 - INFO - codeparrot_training - Step 36927: {'lr': 0.00043438186311656624, 'samples': 18907136, 'steps': 36927, 'loss/train': 1.26718270778656}
-03/05/2022 08:52:29 - INFO - codeparrot_training - Step 36928: {'lr': 0.0004343782793395435, 'samples': 18907648, 'steps': 36928, 'loss/train': 1.7199846506118774}
-03/05/2022 08:52:31 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/05/2022 08:52:35 - INFO - codeparrot_training - Step 36929: {'lr': 0.00043437469547944277, 'samples': 18908160, 'steps': 36929, 'loss/train': 0.8998398184776306}
-03/05/2022 08:52:38 - INFO - codeparrot_training - Step 36930: {'lr': 0.0004343711115362656, 'samples': 18908672, 'steps': 36930, 'loss/train': 1.9931837320327759}
-03/05/2022 08:52:40 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/05/2022 08:52:43 - INFO - codeparrot_training - Step 36931: {'lr': 0.00043436752751001365, 'samples': 18909184, 'steps': 36931, 'loss/train': 2.208766222000122}
-03/05/2022 08:52:46 - INFO - codeparrot_training - Step 36932: {'lr': 0.0004343639434006885, 'samples': 18909696, 'steps': 36932, 'loss/train': 2.4634196758270264}
-03/05/2022 08:52:48 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/05/2022 08:52:52 - INFO - codeparrot_training - Step 36933: {'lr': 0.00043436035920829186, 'samples': 18910208, 'steps': 36933, 'loss/train': 1.3468936681747437}
-03/05/2022 08:52:55 - INFO - codeparrot_training - Step 36934: {'lr': 0.0004343567749328253, 'samples': 18910720, 'steps': 36934, 'loss/train': 1.2916488647460938}
-03/05/2022 08:52:56 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/05/2022 08:53:00 - INFO - codeparrot_training - Step 36935: {'lr': 0.00043435319057429046, 'samples': 18911232, 'steps': 36935, 'loss/train': 0.9071429967880249}
-03/05/2022 08:53:03 - INFO - codeparrot_training - Step 36936: {'lr': 0.0004343496061326888, 'samples': 18911744, 'steps': 36936, 'loss/train': 1.9391156435012817}
-03/05/2022 08:53:05 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/05/2022 08:53:09 - INFO - codeparrot_training - Step 36937: {'lr': 0.0004343460216080221, 'samples': 18912256, 'steps': 36937, 'loss/train': 2.0201051235198975}
-03/05/2022 08:53:12 - INFO - codeparrot_training - Step 36938: {'lr': 0.00043434243700029196, 'samples': 18912768, 'steps': 36938, 'loss/train': 1.5541919469833374}
-03/05/2022 08:53:14 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 08:53:17 - INFO - codeparrot_training - Step 36939: {'lr': 0.0004343388523095, 'samples': 18913280, 'steps': 36939, 'loss/train': 1.6733759641647339}
-03/05/2022 08:53:20 - INFO - codeparrot_training - Step 36940: {'lr': 0.00043433526753564766, 'samples': 18913792, 'steps': 36940, 'loss/train': 1.7549951076507568}
-03/05/2022 08:53:22 - INFO - codeparrot_training - Skipping example with length 703 (seq_length=1024)
-03/05/2022 08:53:25 - INFO - codeparrot_training - Step 36941: {'lr': 0.00043433168267873677, 'samples': 18914304, 'steps': 36941, 'loss/train': 1.5112932920455933}
-03/05/2022 08:53:29 - INFO - codeparrot_training - Step 36942: {'lr': 0.0004343280977387689, 'samples': 18914816, 'steps': 36942, 'loss/train': 1.7803874015808105}
-03/05/2022 08:53:30 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/05/2022 08:53:34 - INFO - codeparrot_training - Step 36943: {'lr': 0.0004343245127157456, 'samples': 18915328, 'steps': 36943, 'loss/train': 1.4912039041519165}
-03/05/2022 08:53:37 - INFO - codeparrot_training - Step 36944: {'lr': 0.0004343209276096686, 'samples': 18915840, 'steps': 36944, 'loss/train': 1.2793132066726685}
-03/05/2022 08:53:39 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/05/2022 08:53:42 - INFO - codeparrot_training - Step 36945: {'lr': 0.00043431734242053933, 'samples': 18916352, 'steps': 36945, 'loss/train': 1.7445441484451294}
-03/05/2022 08:53:46 - INFO - codeparrot_training - Step 36946: {'lr': 0.0004343137571483595, 'samples': 18916864, 'steps': 36946, 'loss/train': 1.3764079809188843}
-03/05/2022 08:53:47 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/05/2022 08:53:51 - INFO - codeparrot_training - Step 36947: {'lr': 0.00043431017179313075, 'samples': 18917376, 'steps': 36947, 'loss/train': 1.7874045372009277}
-03/05/2022 08:53:54 - INFO - codeparrot_training - Step 36948: {'lr': 0.0004343065863548548, 'samples': 18917888, 'steps': 36948, 'loss/train': 1.9605122804641724}
-03/05/2022 08:53:55 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/05/2022 08:53:59 - INFO - codeparrot_training - Step 36949: {'lr': 0.000434303000833533, 'samples': 18918400, 'steps': 36949, 'loss/train': 1.806005597114563}
-03/05/2022 08:54:02 - INFO - codeparrot_training - Step 36950: {'lr': 0.00043429941522916715, 'samples': 18918912, 'steps': 36950, 'loss/train': 1.300453543663025}
-03/05/2022 08:54:04 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/05/2022 08:54:08 - INFO - codeparrot_training - Step 36951: {'lr': 0.0004342958295417588, 'samples': 18919424, 'steps': 36951, 'loss/train': 2.21132230758667}
-03/05/2022 08:54:11 - INFO - codeparrot_training - Step 36952: {'lr': 0.00043429224377130964, 'samples': 18919936, 'steps': 36952, 'loss/train': 1.340383529663086}
-03/05/2022 08:54:12 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/05/2022 08:54:16 - INFO - codeparrot_training - Step 36953: {'lr': 0.00043428865791782126, 'samples': 18920448, 'steps': 36953, 'loss/train': 1.6192365884780884}
-03/05/2022 08:54:19 - INFO - codeparrot_training - Step 36954: {'lr': 0.0004342850719812952, 'samples': 18920960, 'steps': 36954, 'loss/train': 0.864309549331665}
-03/05/2022 08:54:20 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/05/2022 08:54:25 - INFO - codeparrot_training - Step 36955: {'lr': 0.00043428148596173316, 'samples': 18921472, 'steps': 36955, 'loss/train': 1.9933805465698242}
-03/05/2022 08:54:28 - INFO - codeparrot_training - Step 36956: {'lr': 0.00043427789985913675, 'samples': 18921984, 'steps': 36956, 'loss/train': 1.7541875839233398}
-03/05/2022 08:54:29 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 08:54:33 - INFO - codeparrot_training - Step 36957: {'lr': 0.00043427431367350753, 'samples': 18922496, 'steps': 36957, 'loss/train': 1.5491714477539062}
-03/05/2022 08:54:36 - INFO - codeparrot_training - Step 36958: {'lr': 0.0004342707274048472, 'samples': 18923008, 'steps': 36958, 'loss/train': 1.2090696096420288}
-03/05/2022 08:54:38 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/05/2022 08:54:41 - INFO - codeparrot_training - Step 36959: {'lr': 0.0004342671410531572, 'samples': 18923520, 'steps': 36959, 'loss/train': 1.5083037614822388}
-03/05/2022 08:54:45 - INFO - codeparrot_training - Step 36960: {'lr': 0.00043426355461843934, 'samples': 18924032, 'steps': 36960, 'loss/train': 1.7884770631790161}
-03/05/2022 08:54:46 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 08:54:50 - INFO - codeparrot_training - Step 36961: {'lr': 0.00043425996810069525, 'samples': 18924544, 'steps': 36961, 'loss/train': 1.6233292818069458}
-03/05/2022 08:54:53 - INFO - codeparrot_training - Step 36962: {'lr': 0.0004342563814999264, 'samples': 18925056, 'steps': 36962, 'loss/train': 2.9792420864105225}
-03/05/2022 08:54:55 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/05/2022 08:54:58 - INFO - codeparrot_training - Step 36963: {'lr': 0.0004342527948161344, 'samples': 18925568, 'steps': 36963, 'loss/train': 1.538663387298584}
-03/05/2022 08:55:02 - INFO - codeparrot_training - Step 36964: {'lr': 0.000434249208049321, 'samples': 18926080, 'steps': 36964, 'loss/train': 2.0222537517547607}
-03/05/2022 08:55:03 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/05/2022 08:55:07 - INFO - codeparrot_training - Step 36965: {'lr': 0.0004342456211994877, 'samples': 18926592, 'steps': 36965, 'loss/train': 1.4356895685195923}
-03/05/2022 08:55:10 - INFO - codeparrot_training - Step 36966: {'lr': 0.00043424203426663623, 'samples': 18927104, 'steps': 36966, 'loss/train': 2.4743618965148926}
-03/05/2022 08:55:11 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/05/2022 08:55:15 - INFO - codeparrot_training - Step 36967: {'lr': 0.0004342384472507681, 'samples': 18927616, 'steps': 36967, 'loss/train': 1.3574460744857788}
-03/05/2022 08:55:18 - INFO - codeparrot_training - Step 36968: {'lr': 0.00043423486015188497, 'samples': 18928128, 'steps': 36968, 'loss/train': 1.7307296991348267}
-03/05/2022 08:55:19 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/05/2022 08:55:24 - INFO - codeparrot_training - Step 36969: {'lr': 0.00043423127296998845, 'samples': 18928640, 'steps': 36969, 'loss/train': 1.3685864210128784}
-03/05/2022 08:55:27 - INFO - codeparrot_training - Step 36970: {'lr': 0.0004342276857050802, 'samples': 18929152, 'steps': 36970, 'loss/train': 2.4496963024139404}
-03/05/2022 08:55:28 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/05/2022 08:55:32 - INFO - codeparrot_training - Step 36971: {'lr': 0.00043422409835716175, 'samples': 18929664, 'steps': 36971, 'loss/train': 1.1316324472427368}
-03/05/2022 08:55:35 - INFO - codeparrot_training - Step 36972: {'lr': 0.00043422051092623483, 'samples': 18930176, 'steps': 36972, 'loss/train': 1.441063404083252}
-03/05/2022 08:55:37 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/05/2022 08:55:41 - INFO - codeparrot_training - Step 36973: {'lr': 0.0004342169234123009, 'samples': 18930688, 'steps': 36973, 'loss/train': 0.9314203858375549}
-03/05/2022 08:55:44 - INFO - codeparrot_training - Step 36974: {'lr': 0.0004342133358153617, 'samples': 18931200, 'steps': 36974, 'loss/train': 0.6991536617279053}
-03/05/2022 08:55:45 - INFO - codeparrot_training - Skipping example with length 576 (seq_length=1024)
-03/05/2022 08:55:49 - INFO - codeparrot_training - Step 36975: {'lr': 0.0004342097481354189, 'samples': 18931712, 'steps': 36975, 'loss/train': 2.3606317043304443}
-03/05/2022 08:55:52 - INFO - codeparrot_training - Step 36976: {'lr': 0.00043420616037247395, 'samples': 18932224, 'steps': 36976, 'loss/train': 0.542598307132721}
-03/05/2022 08:55:54 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/05/2022 08:55:57 - INFO - codeparrot_training - Step 36977: {'lr': 0.0004342025725265285, 'samples': 18932736, 'steps': 36977, 'loss/train': 1.2886065244674683}
-03/05/2022 08:56:01 - INFO - codeparrot_training - Step 36978: {'lr': 0.00043419898459758435, 'samples': 18933248, 'steps': 36978, 'loss/train': 1.5825302600860596}
-03/05/2022 08:56:02 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/05/2022 08:56:06 - INFO - codeparrot_training - Step 36979: {'lr': 0.00043419539658564286, 'samples': 18933760, 'steps': 36979, 'loss/train': 1.5334430932998657}
-03/05/2022 08:56:09 - INFO - codeparrot_training - Step 36980: {'lr': 0.0004341918084907058, 'samples': 18934272, 'steps': 36980, 'loss/train': 1.674171805381775}
-03/05/2022 08:56:11 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/05/2022 08:56:14 - INFO - codeparrot_training - Step 36981: {'lr': 0.0004341882203127747, 'samples': 18934784, 'steps': 36981, 'loss/train': 2.4014501571655273}
-03/05/2022 08:56:17 - INFO - codeparrot_training - Step 36982: {'lr': 0.00043418463205185134, 'samples': 18935296, 'steps': 36982, 'loss/train': 1.3597460985183716}
-03/05/2022 08:56:19 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/05/2022 08:56:23 - INFO - codeparrot_training - Step 36983: {'lr': 0.0004341810437079372, 'samples': 18935808, 'steps': 36983, 'loss/train': 1.4551383256912231}
-03/05/2022 08:56:26 - INFO - codeparrot_training - Step 36984: {'lr': 0.0004341774552810339, 'samples': 18936320, 'steps': 36984, 'loss/train': 2.1680328845977783}
-03/05/2022 08:56:27 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/05/2022 08:56:31 - INFO - codeparrot_training - Step 36985: {'lr': 0.0004341738667711431, 'samples': 18936832, 'steps': 36985, 'loss/train': 1.3458517789840698}
-03/05/2022 08:56:34 - INFO - codeparrot_training - Step 36986: {'lr': 0.0004341702781782664, 'samples': 18937344, 'steps': 36986, 'loss/train': 1.6814838647842407}
-03/05/2022 08:56:36 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/05/2022 08:56:40 - INFO - codeparrot_training - Step 36987: {'lr': 0.00043416668950240536, 'samples': 18937856, 'steps': 36987, 'loss/train': 0.5219226479530334}
-03/05/2022 08:56:43 - INFO - codeparrot_training - Step 36988: {'lr': 0.0004341631007435617, 'samples': 18938368, 'steps': 36988, 'loss/train': 1.1871252059936523}
-03/05/2022 08:56:44 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/05/2022 08:56:48 - INFO - codeparrot_training - Step 36989: {'lr': 0.00043415951190173697, 'samples': 18938880, 'steps': 36989, 'loss/train': 1.1446117162704468}
-03/05/2022 08:56:51 - INFO - codeparrot_training - Step 36990: {'lr': 0.00043415592297693276, 'samples': 18939392, 'steps': 36990, 'loss/train': 1.5315895080566406}
-03/05/2022 08:56:53 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 08:56:57 - INFO - codeparrot_training - Step 36991: {'lr': 0.00043415233396915077, 'samples': 18939904, 'steps': 36991, 'loss/train': 1.7417967319488525}
-03/05/2022 08:57:00 - INFO - codeparrot_training - Step 36992: {'lr': 0.0004341487448783926, 'samples': 18940416, 'steps': 36992, 'loss/train': 1.8231290578842163}
-03/05/2022 08:57:01 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/05/2022 08:57:05 - INFO - codeparrot_training - Step 36993: {'lr': 0.00043414515570465987, 'samples': 18940928, 'steps': 36993, 'loss/train': 1.130030632019043}
-03/05/2022 08:57:08 - INFO - codeparrot_training - Step 36994: {'lr': 0.0004341415664479541, 'samples': 18941440, 'steps': 36994, 'loss/train': 0.88246750831604}
-03/05/2022 08:57:09 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/05/2022 08:57:13 - INFO - codeparrot_training - Step 36995: {'lr': 0.00043413797710827707, 'samples': 18941952, 'steps': 36995, 'loss/train': 2.098619222640991}
-03/05/2022 08:57:17 - INFO - codeparrot_training - Step 36996: {'lr': 0.00043413438768563026, 'samples': 18942464, 'steps': 36996, 'loss/train': 1.8001807928085327}
-03/05/2022 08:57:18 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/05/2022 08:57:22 - INFO - codeparrot_training - Step 36997: {'lr': 0.0004341307981800153, 'samples': 18942976, 'steps': 36997, 'loss/train': 1.505990982055664}
-03/05/2022 08:57:25 - INFO - codeparrot_training - Step 36998: {'lr': 0.0004341272085914339, 'samples': 18943488, 'steps': 36998, 'loss/train': 1.2024465799331665}
-03/05/2022 08:57:26 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/05/2022 08:57:30 - INFO - codeparrot_training - Step 36999: {'lr': 0.00043412361891988763, 'samples': 18944000, 'steps': 36999, 'loss/train': 1.759675145149231}
-03/05/2022 08:57:34 - INFO - codeparrot_training - Step 37000: {'lr': 0.0004341200291653781, 'samples': 18944512, 'steps': 37000, 'loss/train': 1.2698192596435547}
-03/05/2022 08:57:35 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/05/2022 08:57:39 - INFO - codeparrot_training - Step 37001: {'lr': 0.00043411643932790686, 'samples': 18945024, 'steps': 37001, 'loss/train': 1.6138778924942017}
-03/05/2022 08:57:42 - INFO - codeparrot_training - Step 37002: {'lr': 0.0004341128494074756, 'samples': 18945536, 'steps': 37002, 'loss/train': 1.8181004524230957}
-03/05/2022 08:57:43 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/05/2022 08:57:47 - INFO - codeparrot_training - Step 37003: {'lr': 0.00043410925940408595, 'samples': 18946048, 'steps': 37003, 'loss/train': 1.2387021780014038}
-03/05/2022 08:57:50 - INFO - codeparrot_training - Step 37004: {'lr': 0.00043410566931773953, 'samples': 18946560, 'steps': 37004, 'loss/train': 6.483454704284668}
-03/05/2022 08:57:51 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 08:57:56 - INFO - codeparrot_training - Step 37005: {'lr': 0.000434102079148438, 'samples': 18947072, 'steps': 37005, 'loss/train': 2.2539703845977783}
-03/05/2022 08:57:59 - INFO - codeparrot_training - Step 37006: {'lr': 0.0004340984888961828, 'samples': 18947584, 'steps': 37006, 'loss/train': 1.6834895610809326}
-03/05/2022 08:57:59 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/05/2022 08:58:04 - INFO - codeparrot_training - Step 37007: {'lr': 0.00043409489856097573, 'samples': 18948096, 'steps': 37007, 'loss/train': 1.2216817140579224}
-03/05/2022 08:58:07 - INFO - codeparrot_training - Step 37008: {'lr': 0.0004340913081428183, 'samples': 18948608, 'steps': 37008, 'loss/train': 2.1062488555908203}
-03/05/2022 08:58:08 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 08:58:13 - INFO - codeparrot_training - Step 37009: {'lr': 0.00043408771764171216, 'samples': 18949120, 'steps': 37009, 'loss/train': 1.6886597871780396}
-03/05/2022 08:58:16 - INFO - codeparrot_training - Step 37010: {'lr': 0.000434084127057659, 'samples': 18949632, 'steps': 37010, 'loss/train': 1.2066068649291992}
-03/05/2022 08:58:16 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/05/2022 08:58:21 - INFO - codeparrot_training - Step 37011: {'lr': 0.0004340805363906603, 'samples': 18950144, 'steps': 37011, 'loss/train': 1.5570777654647827}
-03/05/2022 08:58:24 - INFO - codeparrot_training - Step 37012: {'lr': 0.00043407694564071773, 'samples': 18950656, 'steps': 37012, 'loss/train': 2.297395944595337}
-03/05/2022 08:58:24 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/05/2022 08:58:29 - INFO - codeparrot_training - Step 37013: {'lr': 0.00043407335480783306, 'samples': 18951168, 'steps': 37013, 'loss/train': 1.80231511592865}
-03/05/2022 08:58:32 - INFO - codeparrot_training - Step 37014: {'lr': 0.0004340697638920077, 'samples': 18951680, 'steps': 37014, 'loss/train': 1.4516441822052002}
-03/05/2022 08:58:33 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/05/2022 08:58:38 - INFO - codeparrot_training - Step 37015: {'lr': 0.0004340661728932433, 'samples': 18952192, 'steps': 37015, 'loss/train': 2.000248908996582}
-03/05/2022 08:58:41 - INFO - codeparrot_training - Step 37016: {'lr': 0.0004340625818115416, 'samples': 18952704, 'steps': 37016, 'loss/train': 1.497079610824585}
-03/05/2022 08:58:41 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 08:58:46 - INFO - codeparrot_training - Step 37017: {'lr': 0.00043405899064690405, 'samples': 18953216, 'steps': 37017, 'loss/train': 0.7666917443275452}
-03/05/2022 08:58:49 - INFO - codeparrot_training - Step 37018: {'lr': 0.0004340553993993325, 'samples': 18953728, 'steps': 37018, 'loss/train': 2.00129771232605}
-03/05/2022 08:58:49 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/05/2022 08:58:55 - INFO - codeparrot_training - Step 37019: {'lr': 0.0004340518080688283, 'samples': 18954240, 'steps': 37019, 'loss/train': 1.7645634412765503}
-03/05/2022 08:58:58 - INFO - codeparrot_training - Step 37020: {'lr': 0.0004340482166553932, 'samples': 18954752, 'steps': 37020, 'loss/train': 1.5914667844772339}
-03/05/2022 08:58:58 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/05/2022 08:59:03 - INFO - codeparrot_training - Step 37021: {'lr': 0.0004340446251590289, 'samples': 18955264, 'steps': 37021, 'loss/train': 1.7521941661834717}
-03/05/2022 08:59:06 - INFO - codeparrot_training - Step 37022: {'lr': 0.00043404103357973684, 'samples': 18955776, 'steps': 37022, 'loss/train': 1.4570995569229126}
-03/05/2022 08:59:07 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/05/2022 08:59:12 - INFO - codeparrot_training - Step 37023: {'lr': 0.0004340374419175188, 'samples': 18956288, 'steps': 37023, 'loss/train': 2.462038278579712}
-03/05/2022 08:59:15 - INFO - codeparrot_training - Step 37024: {'lr': 0.0004340338501723763, 'samples': 18956800, 'steps': 37024, 'loss/train': 0.6929447650909424}
-03/05/2022 08:59:15 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 08:59:20 - INFO - codeparrot_training - Step 37025: {'lr': 0.00043403025834431097, 'samples': 18957312, 'steps': 37025, 'loss/train': 2.1161837577819824}
-03/05/2022 08:59:23 - INFO - codeparrot_training - Step 37026: {'lr': 0.00043402666643332444, 'samples': 18957824, 'steps': 37026, 'loss/train': 1.7541412115097046}
-03/05/2022 08:59:23 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/05/2022 08:59:29 - INFO - codeparrot_training - Step 37027: {'lr': 0.00043402307443941835, 'samples': 18958336, 'steps': 37027, 'loss/train': 1.326864242553711}
-03/05/2022 08:59:32 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/05/2022 08:59:34 - INFO - codeparrot_training - Step 37028: {'lr': 0.00043401948236259437, 'samples': 18958848, 'steps': 37028, 'loss/train': 0.7695289850234985}
-03/05/2022 08:59:37 - INFO - codeparrot_training - Step 37029: {'lr': 0.000434015890202854, 'samples': 18959360, 'steps': 37029, 'loss/train': 1.2580878734588623}
-03/05/2022 08:59:40 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 08:59:42 - INFO - codeparrot_training - Step 37030: {'lr': 0.0004340122979601989, 'samples': 18959872, 'steps': 37030, 'loss/train': 1.5722442865371704}
-03/05/2022 08:59:46 - INFO - codeparrot_training - Step 37031: {'lr': 0.0004340087056346307, 'samples': 18960384, 'steps': 37031, 'loss/train': 1.861557126045227}
-03/05/2022 08:59:48 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 08:59:51 - INFO - codeparrot_training - Step 37032: {'lr': 0.000434005113226151, 'samples': 18960896, 'steps': 37032, 'loss/train': 1.598203182220459}
-03/05/2022 08:59:54 - INFO - codeparrot_training - Step 37033: {'lr': 0.0004340015207347614, 'samples': 18961408, 'steps': 37033, 'loss/train': 1.875545620918274}
-03/05/2022 08:59:57 - INFO - codeparrot_training - Step 37034: {'lr': 0.0004339979281604636, 'samples': 18961920, 'steps': 37034, 'loss/train': 2.1928367614746094}
-03/05/2022 08:59:57 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/05/2022 09:00:03 - INFO - codeparrot_training - Step 37035: {'lr': 0.00043399433550325917, 'samples': 18962432, 'steps': 37035, 'loss/train': 1.6792798042297363}
-03/05/2022 09:00:06 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/05/2022 09:00:08 - INFO - codeparrot_training - Step 37036: {'lr': 0.00043399074276314974, 'samples': 18962944, 'steps': 37036, 'loss/train': 2.3481316566467285}
-03/05/2022 09:00:11 - INFO - codeparrot_training - Step 37037: {'lr': 0.00043398714994013696, 'samples': 18963456, 'steps': 37037, 'loss/train': 4.65722131729126}
-03/05/2022 09:00:14 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/05/2022 09:00:16 - INFO - codeparrot_training - Step 37038: {'lr': 0.00043398355703422233, 'samples': 18963968, 'steps': 37038, 'loss/train': 1.3179608583450317}
-03/05/2022 09:00:20 - INFO - codeparrot_training - Step 37039: {'lr': 0.0004339799640454076, 'samples': 18964480, 'steps': 37039, 'loss/train': 2.0236051082611084}
-03/05/2022 09:00:22 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/05/2022 09:00:25 - INFO - codeparrot_training - Step 37040: {'lr': 0.00043397637097369434, 'samples': 18964992, 'steps': 37040, 'loss/train': 6.31903076171875}
-03/05/2022 09:00:28 - INFO - codeparrot_training - Step 37041: {'lr': 0.0004339727778190842, 'samples': 18965504, 'steps': 37041, 'loss/train': 0.9385872483253479}
-03/05/2022 09:00:31 - INFO - codeparrot_training - Step 37042: {'lr': 0.0004339691845815786, 'samples': 18966016, 'steps': 37042, 'loss/train': 2.352531909942627}
-03/05/2022 09:00:32 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 09:00:37 - INFO - codeparrot_training - Step 37043: {'lr': 0.0004339655912611795, 'samples': 18966528, 'steps': 37043, 'loss/train': 2.636232852935791}
-03/05/2022 09:00:40 - INFO - codeparrot_training - Step 37044: {'lr': 0.00043396199785788824, 'samples': 18967040, 'steps': 37044, 'loss/train': 1.0448858737945557}
-03/05/2022 09:00:40 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/05/2022 09:00:45 - INFO - codeparrot_training - Step 37045: {'lr': 0.00043395840437170666, 'samples': 18967552, 'steps': 37045, 'loss/train': 1.8448022603988647}
-03/05/2022 09:00:48 - INFO - codeparrot_training - Step 37046: {'lr': 0.00043395481080263614, 'samples': 18968064, 'steps': 37046, 'loss/train': 2.050145149230957}
-03/05/2022 09:00:48 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 09:00:53 - INFO - codeparrot_training - Step 37047: {'lr': 0.0004339512171506785, 'samples': 18968576, 'steps': 37047, 'loss/train': 1.3320791721343994}
-03/05/2022 09:00:57 - INFO - codeparrot_training - Step 37048: {'lr': 0.0004339476234158352, 'samples': 18969088, 'steps': 37048, 'loss/train': 2.093526601791382}
-03/05/2022 09:00:57 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/05/2022 09:01:02 - INFO - codeparrot_training - Step 37049: {'lr': 0.00043394402959810795, 'samples': 18969600, 'steps': 37049, 'loss/train': 1.3402888774871826}
-03/05/2022 09:01:05 - INFO - codeparrot_training - Step 37050: {'lr': 0.00043394043569749843, 'samples': 18970112, 'steps': 37050, 'loss/train': 1.6390565633773804}
-03/05/2022 09:01:05 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/05/2022 09:01:10 - INFO - codeparrot_training - Step 37051: {'lr': 0.00043393684171400817, 'samples': 18970624, 'steps': 37051, 'loss/train': 1.8414937257766724}
-03/05/2022 09:01:13 - INFO - codeparrot_training - Step 37052: {'lr': 0.00043393324764763873, 'samples': 18971136, 'steps': 37052, 'loss/train': 1.9456350803375244}
-03/05/2022 09:01:14 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/05/2022 09:01:19 - INFO - codeparrot_training - Step 37053: {'lr': 0.0004339296534983919, 'samples': 18971648, 'steps': 37053, 'loss/train': 2.578043222427368}
-03/05/2022 09:01:22 - INFO - codeparrot_training - Step 37054: {'lr': 0.00043392605926626914, 'samples': 18972160, 'steps': 37054, 'loss/train': 0.452314168214798}
-03/05/2022 09:01:22 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/05/2022 09:01:27 - INFO - codeparrot_training - Step 37055: {'lr': 0.0004339224649512722, 'samples': 18972672, 'steps': 37055, 'loss/train': 1.5404256582260132}
-03/05/2022 09:01:30 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 09:01:33 - INFO - codeparrot_training - Step 37056: {'lr': 0.00043391887055340263, 'samples': 18973184, 'steps': 37056, 'loss/train': 1.4709910154342651}
-03/05/2022 09:01:36 - INFO - codeparrot_training - Step 37057: {'lr': 0.000433915276072662, 'samples': 18973696, 'steps': 37057, 'loss/train': 2.0538721084594727}
-03/05/2022 09:01:39 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/05/2022 09:01:41 - INFO - codeparrot_training - Step 37058: {'lr': 0.00043391168150905203, 'samples': 18974208, 'steps': 37058, 'loss/train': 0.6300174593925476}
-03/05/2022 09:01:44 - INFO - codeparrot_training - Step 37059: {'lr': 0.0004339080868625743, 'samples': 18974720, 'steps': 37059, 'loss/train': 1.4279366731643677}
-03/05/2022 09:01:48 - INFO - codeparrot_training - Step 37060: {'lr': 0.0004339044921332304, 'samples': 18975232, 'steps': 37060, 'loss/train': 1.7105212211608887}
-03/05/2022 09:01:48 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/05/2022 09:01:53 - INFO - codeparrot_training - Step 37061: {'lr': 0.000433900897321022, 'samples': 18975744, 'steps': 37061, 'loss/train': 0.9826271533966064}
-03/05/2022 09:01:56 - INFO - codeparrot_training - Step 37062: {'lr': 0.0004338973024259506, 'samples': 18976256, 'steps': 37062, 'loss/train': 1.8923547267913818}
-03/05/2022 09:01:56 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/05/2022 09:02:01 - INFO - codeparrot_training - Step 37063: {'lr': 0.00043389370744801806, 'samples': 18976768, 'steps': 37063, 'loss/train': 2.0814192295074463}
-03/05/2022 09:02:04 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/05/2022 09:02:07 - INFO - codeparrot_training - Step 37064: {'lr': 0.00043389011238722575, 'samples': 18977280, 'steps': 37064, 'loss/train': 1.6772959232330322}
-03/05/2022 09:02:10 - INFO - codeparrot_training - Step 37065: {'lr': 0.0004338865172435754, 'samples': 18977792, 'steps': 37065, 'loss/train': 2.094710111618042}
-03/05/2022 09:02:13 - INFO - codeparrot_training - Step 37066: {'lr': 0.00043388292201706867, 'samples': 18978304, 'steps': 37066, 'loss/train': 1.1918777227401733}
-03/05/2022 09:02:14 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/05/2022 09:02:18 - INFO - codeparrot_training - Step 37067: {'lr': 0.0004338793267077071, 'samples': 18978816, 'steps': 37067, 'loss/train': 1.4953997135162354}
-03/05/2022 09:02:22 - INFO - codeparrot_training - Step 37068: {'lr': 0.0004338757313154923, 'samples': 18979328, 'steps': 37068, 'loss/train': 1.210745096206665}
-03/05/2022 09:02:22 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/05/2022 09:02:27 - INFO - codeparrot_training - Step 37069: {'lr': 0.000433872135840426, 'samples': 18979840, 'steps': 37069, 'loss/train': 1.6313426494598389}
-03/05/2022 09:02:30 - INFO - codeparrot_training - Step 37070: {'lr': 0.00043386854028250977, 'samples': 18980352, 'steps': 37070, 'loss/train': 1.7846847772598267}
-03/05/2022 09:02:31 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/05/2022 09:02:35 - INFO - codeparrot_training - Step 37071: {'lr': 0.00043386494464174515, 'samples': 18980864, 'steps': 37071, 'loss/train': 1.1558401584625244}
-03/05/2022 09:02:39 - INFO - codeparrot_training - Step 37072: {'lr': 0.0004338613489181338, 'samples': 18981376, 'steps': 37072, 'loss/train': 2.019453763961792}
-03/05/2022 09:02:39 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/05/2022 09:02:44 - INFO - codeparrot_training - Step 37073: {'lr': 0.00043385775311167746, 'samples': 18981888, 'steps': 37073, 'loss/train': 1.5930427312850952}
-03/05/2022 09:02:47 - INFO - codeparrot_training - Step 37074: {'lr': 0.00043385415722237765, 'samples': 18982400, 'steps': 37074, 'loss/train': 2.278592824935913}
-03/05/2022 09:02:48 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/05/2022 09:02:52 - INFO - codeparrot_training - Step 37075: {'lr': 0.0004338505612502359, 'samples': 18982912, 'steps': 37075, 'loss/train': 1.1396745443344116}
-03/05/2022 09:02:55 - INFO - codeparrot_training - Step 37076: {'lr': 0.000433846965195254, 'samples': 18983424, 'steps': 37076, 'loss/train': 1.8427760601043701}
-03/05/2022 09:02:56 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/05/2022 09:03:01 - INFO - codeparrot_training - Step 37077: {'lr': 0.00043384336905743343, 'samples': 18983936, 'steps': 37077, 'loss/train': 1.382001280784607}
-03/05/2022 09:03:04 - INFO - codeparrot_training - Step 37078: {'lr': 0.0004338397728367759, 'samples': 18984448, 'steps': 37078, 'loss/train': 0.9638236165046692}
-03/05/2022 09:03:05 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/05/2022 09:03:09 - INFO - codeparrot_training - Step 37079: {'lr': 0.000433836176533283, 'samples': 18984960, 'steps': 37079, 'loss/train': 2.134312868118286}
-03/05/2022 09:03:12 - INFO - codeparrot_training - Step 37080: {'lr': 0.0004338325801469564, 'samples': 18985472, 'steps': 37080, 'loss/train': 1.6404387950897217}
-03/05/2022 09:03:13 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/05/2022 09:03:17 - INFO - codeparrot_training - Step 37081: {'lr': 0.00043382898367779767, 'samples': 18985984, 'steps': 37081, 'loss/train': 2.837474822998047}
-03/05/2022 09:03:21 - INFO - codeparrot_training - Step 37082: {'lr': 0.00043382538712580845, 'samples': 18986496, 'steps': 37082, 'loss/train': 1.774423360824585}
-03/05/2022 09:03:21 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/05/2022 09:03:26 - INFO - codeparrot_training - Step 37083: {'lr': 0.00043382179049099024, 'samples': 18987008, 'steps': 37083, 'loss/train': 2.0665252208709717}
-03/05/2022 09:03:29 - INFO - codeparrot_training - Step 37084: {'lr': 0.00043381819377334485, 'samples': 18987520, 'steps': 37084, 'loss/train': 1.8939987421035767}
-03/05/2022 09:03:30 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/05/2022 09:03:34 - INFO - codeparrot_training - Step 37085: {'lr': 0.00043381459697287383, 'samples': 18988032, 'steps': 37085, 'loss/train': 1.8019187450408936}
-03/05/2022 09:03:37 - INFO - codeparrot_training - Step 37086: {'lr': 0.0004338110000895787, 'samples': 18988544, 'steps': 37086, 'loss/train': 1.7120757102966309}
-03/05/2022 09:03:38 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/05/2022 09:03:43 - INFO - codeparrot_training - Step 37087: {'lr': 0.00043380740312346135, 'samples': 18989056, 'steps': 37087, 'loss/train': 2.1594691276550293}
-03/05/2022 09:03:46 - INFO - codeparrot_training - Step 37088: {'lr': 0.00043380380607452307, 'samples': 18989568, 'steps': 37088, 'loss/train': 1.8559999465942383}
-03/05/2022 09:03:46 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/05/2022 09:03:51 - INFO - codeparrot_training - Step 37089: {'lr': 0.0004338002089427657, 'samples': 18990080, 'steps': 37089, 'loss/train': 1.9000734090805054}
-03/05/2022 09:03:54 - INFO - codeparrot_training - Step 37090: {'lr': 0.00043379661172819075, 'samples': 18990592, 'steps': 37090, 'loss/train': 1.9134142398834229}
-03/05/2022 09:03:55 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/05/2022 09:04:00 - INFO - codeparrot_training - Step 37091: {'lr': 0.0004337930144307999, 'samples': 18991104, 'steps': 37091, 'loss/train': 1.127015471458435}
-03/05/2022 09:04:03 - INFO - codeparrot_training - Step 37092: {'lr': 0.0004337894170505947, 'samples': 18991616, 'steps': 37092, 'loss/train': 1.6810263395309448}
-03/05/2022 09:04:04 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/05/2022 09:04:08 - INFO - codeparrot_training - Step 37093: {'lr': 0.0004337858195875769, 'samples': 18992128, 'steps': 37093, 'loss/train': 1.7631961107254028}
-03/05/2022 09:04:11 - INFO - codeparrot_training - Step 37094: {'lr': 0.00043378222204174807, 'samples': 18992640, 'steps': 37094, 'loss/train': 1.349923014640808}
-03/05/2022 09:04:13 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 09:04:17 - INFO - codeparrot_training - Step 37095: {'lr': 0.0004337786244131097, 'samples': 18993152, 'steps': 37095, 'loss/train': 2.4047088623046875}
-03/05/2022 09:04:20 - INFO - codeparrot_training - Step 37096: {'lr': 0.00043377502670166357, 'samples': 18993664, 'steps': 37096, 'loss/train': 1.925308346748352}
-03/05/2022 09:04:21 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/05/2022 09:04:25 - INFO - codeparrot_training - Step 37097: {'lr': 0.0004337714289074113, 'samples': 18994176, 'steps': 37097, 'loss/train': 1.716721773147583}
-03/05/2022 09:04:28 - INFO - codeparrot_training - Step 37098: {'lr': 0.0004337678310303544, 'samples': 18994688, 'steps': 37098, 'loss/train': 1.7418791055679321}
-03/05/2022 09:04:30 - INFO - codeparrot_training - Skipping example with length 285 (seq_length=1024)
-03/05/2022 09:04:34 - INFO - codeparrot_training - Step 37099: {'lr': 0.00043376423307049455, 'samples': 18995200, 'steps': 37099, 'loss/train': 1.6615022420883179}
-03/05/2022 09:04:37 - INFO - codeparrot_training - Step 37100: {'lr': 0.00043376063502783337, 'samples': 18995712, 'steps': 37100, 'loss/train': 1.8112053871154785}
-03/05/2022 09:04:38 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/05/2022 09:04:42 - INFO - codeparrot_training - Step 37101: {'lr': 0.00043375703690237254, 'samples': 18996224, 'steps': 37101, 'loss/train': 1.8027398586273193}
-03/05/2022 09:04:45 - INFO - codeparrot_training - Step 37102: {'lr': 0.0004337534386941135, 'samples': 18996736, 'steps': 37102, 'loss/train': 1.7639185190200806}
-03/05/2022 09:04:46 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/05/2022 09:04:50 - INFO - codeparrot_training - Step 37103: {'lr': 0.00043374984040305816, 'samples': 18997248, 'steps': 37103, 'loss/train': 1.823492169380188}
-03/05/2022 09:04:54 - INFO - codeparrot_training - Step 37104: {'lr': 0.00043374624202920786, 'samples': 18997760, 'steps': 37104, 'loss/train': 1.4477523565292358}
-03/05/2022 09:04:55 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/05/2022 09:04:59 - INFO - codeparrot_training - Step 37105: {'lr': 0.0004337426435725644, 'samples': 18998272, 'steps': 37105, 'loss/train': 0.8837972283363342}
-03/05/2022 09:05:02 - INFO - codeparrot_training - Step 37106: {'lr': 0.00043373904503312934, 'samples': 18998784, 'steps': 37106, 'loss/train': 1.530753254890442}
-03/05/2022 09:05:03 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/05/2022 09:05:07 - INFO - codeparrot_training - Step 37107: {'lr': 0.0004337354464109042, 'samples': 18999296, 'steps': 37107, 'loss/train': 1.6046457290649414}
-03/05/2022 09:05:11 - INFO - codeparrot_training - Step 37108: {'lr': 0.0004337318477058908, 'samples': 18999808, 'steps': 37108, 'loss/train': 1.0146933794021606}
-03/05/2022 09:05:12 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/05/2022 09:05:16 - INFO - codeparrot_training - Step 37109: {'lr': 0.0004337282489180907, 'samples': 19000320, 'steps': 37109, 'loss/train': 2.0390138626098633}
-03/05/2022 09:05:19 - INFO - codeparrot_training - Step 37110: {'lr': 0.0004337246500475054, 'samples': 19000832, 'steps': 37110, 'loss/train': 1.3324987888336182}
-03/05/2022 09:05:20 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/05/2022 09:05:24 - INFO - codeparrot_training - Step 37111: {'lr': 0.0004337210510941366, 'samples': 19001344, 'steps': 37111, 'loss/train': 1.435253620147705}
-03/05/2022 09:05:27 - INFO - codeparrot_training - Step 37112: {'lr': 0.000433717452057986, 'samples': 19001856, 'steps': 37112, 'loss/train': 1.1810600757598877}
-03/05/2022 09:05:29 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 09:05:33 - INFO - codeparrot_training - Step 37113: {'lr': 0.00043371385293905517, 'samples': 19002368, 'steps': 37113, 'loss/train': 5.195160865783691}
-03/05/2022 09:05:36 - INFO - codeparrot_training - Step 37114: {'lr': 0.0004337102537373456, 'samples': 19002880, 'steps': 37114, 'loss/train': 1.6097990274429321}
-03/05/2022 09:05:38 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 09:05:41 - INFO - codeparrot_training - Step 37115: {'lr': 0.0004337066544528591, 'samples': 19003392, 'steps': 37115, 'loss/train': 1.4061896800994873}
-03/05/2022 09:05:44 - INFO - codeparrot_training - Step 37116: {'lr': 0.00043370305508559723, 'samples': 19003904, 'steps': 37116, 'loss/train': 4.303162097930908}
-03/05/2022 09:05:46 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/05/2022 09:05:50 - INFO - codeparrot_training - Step 37117: {'lr': 0.00043369945563556157, 'samples': 19004416, 'steps': 37117, 'loss/train': 1.7049157619476318}
-03/05/2022 09:05:53 - INFO - codeparrot_training - Step 37118: {'lr': 0.00043369585610275374, 'samples': 19004928, 'steps': 37118, 'loss/train': 2.2402255535125732}
-03/05/2022 09:05:54 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/05/2022 09:05:58 - INFO - codeparrot_training - Step 37119: {'lr': 0.0004336922564871755, 'samples': 19005440, 'steps': 37119, 'loss/train': 2.4325311183929443}
-03/05/2022 09:06:01 - INFO - codeparrot_training - Step 37120: {'lr': 0.00043368865678882824, 'samples': 19005952, 'steps': 37120, 'loss/train': 1.8013064861297607}
-03/05/2022 09:06:03 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 09:06:06 - INFO - codeparrot_training - Step 37121: {'lr': 0.00043368505700771377, 'samples': 19006464, 'steps': 37121, 'loss/train': 2.6308374404907227}
-03/05/2022 09:06:10 - INFO - codeparrot_training - Step 37122: {'lr': 0.00043368145714383364, 'samples': 19006976, 'steps': 37122, 'loss/train': 1.3473470211029053}
-03/05/2022 09:06:11 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/05/2022 09:06:15 - INFO - codeparrot_training - Step 37123: {'lr': 0.00043367785719718947, 'samples': 19007488, 'steps': 37123, 'loss/train': 2.3524458408355713}
-03/05/2022 09:06:18 - INFO - codeparrot_training - Step 37124: {'lr': 0.0004336742571677829, 'samples': 19008000, 'steps': 37124, 'loss/train': 1.8188061714172363}
-03/05/2022 09:06:20 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 09:06:23 - INFO - codeparrot_training - Step 37125: {'lr': 0.00043367065705561547, 'samples': 19008512, 'steps': 37125, 'loss/train': 2.0739035606384277}
-03/05/2022 09:06:27 - INFO - codeparrot_training - Step 37126: {'lr': 0.00043366705686068895, 'samples': 19009024, 'steps': 37126, 'loss/train': 1.7980880737304688}
-03/05/2022 09:06:28 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/05/2022 09:06:32 - INFO - codeparrot_training - Step 37127: {'lr': 0.0004336634565830049, 'samples': 19009536, 'steps': 37127, 'loss/train': 1.8266270160675049}
-03/05/2022 09:06:35 - INFO - codeparrot_training - Step 37128: {'lr': 0.0004336598562225649, 'samples': 19010048, 'steps': 37128, 'loss/train': 1.9881590604782104}
-03/05/2022 09:06:36 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/05/2022 09:06:40 - INFO - codeparrot_training - Step 37129: {'lr': 0.00043365625577937065, 'samples': 19010560, 'steps': 37129, 'loss/train': 1.5430338382720947}
-03/05/2022 09:06:43 - INFO - codeparrot_training - Step 37130: {'lr': 0.00043365265525342365, 'samples': 19011072, 'steps': 37130, 'loss/train': 1.7834327220916748}
-03/05/2022 09:06:45 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/05/2022 09:06:49 - INFO - codeparrot_training - Step 37131: {'lr': 0.00043364905464472563, 'samples': 19011584, 'steps': 37131, 'loss/train': 2.231950044631958}
-03/05/2022 09:06:52 - INFO - codeparrot_training - Step 37132: {'lr': 0.0004336454539532782, 'samples': 19012096, 'steps': 37132, 'loss/train': 0.37439656257629395}
-03/05/2022 09:06:54 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/05/2022 09:06:57 - INFO - codeparrot_training - Step 37133: {'lr': 0.00043364185317908296, 'samples': 19012608, 'steps': 37133, 'loss/train': 1.3625109195709229}
-03/05/2022 09:07:00 - INFO - codeparrot_training - Step 37134: {'lr': 0.0004336382523221415, 'samples': 19013120, 'steps': 37134, 'loss/train': 2.1972014904022217}
-03/05/2022 09:07:02 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 09:07:06 - INFO - codeparrot_training - Step 37135: {'lr': 0.0004336346513824555, 'samples': 19013632, 'steps': 37135, 'loss/train': 1.7125988006591797}
-03/05/2022 09:07:09 - INFO - codeparrot_training - Step 37136: {'lr': 0.0004336310503600266, 'samples': 19014144, 'steps': 37136, 'loss/train': 1.155924677848816}
-03/05/2022 09:07:11 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/05/2022 09:07:14 - INFO - codeparrot_training - Step 37137: {'lr': 0.0004336274492548563, 'samples': 19014656, 'steps': 37137, 'loss/train': 1.2122522592544556}
-03/05/2022 09:07:17 - INFO - codeparrot_training - Step 37138: {'lr': 0.0004336238480669463, 'samples': 19015168, 'steps': 37138, 'loss/train': 3.2225561141967773}
-03/05/2022 09:07:20 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/05/2022 09:07:23 - INFO - codeparrot_training - Step 37139: {'lr': 0.0004336202467962983, 'samples': 19015680, 'steps': 37139, 'loss/train': 0.8786723613739014}
-03/05/2022 09:07:26 - INFO - codeparrot_training - Step 37140: {'lr': 0.0004336166454429139, 'samples': 19016192, 'steps': 37140, 'loss/train': 0.8320361375808716}
-03/05/2022 09:07:28 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 09:07:31 - INFO - codeparrot_training - Step 37141: {'lr': 0.0004336130440067946, 'samples': 19016704, 'steps': 37141, 'loss/train': 1.0584031343460083}
-03/05/2022 09:07:34 - INFO - codeparrot_training - Step 37142: {'lr': 0.000433609442487942, 'samples': 19017216, 'steps': 37142, 'loss/train': 1.1211755275726318}
-03/05/2022 09:07:36 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/05/2022 09:07:39 - INFO - codeparrot_training - Step 37143: {'lr': 0.00043360584088635804, 'samples': 19017728, 'steps': 37143, 'loss/train': 2.1521003246307373}
-03/05/2022 09:07:43 - INFO - codeparrot_training - Step 37144: {'lr': 0.0004336022392020439, 'samples': 19018240, 'steps': 37144, 'loss/train': 1.4619868993759155}
-03/05/2022 09:07:44 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 09:07:48 - INFO - codeparrot_training - Step 37145: {'lr': 0.0004335986374350015, 'samples': 19018752, 'steps': 37145, 'loss/train': 0.9908483028411865}
-03/05/2022 09:07:51 - INFO - codeparrot_training - Step 37146: {'lr': 0.00043359503558523246, 'samples': 19019264, 'steps': 37146, 'loss/train': 2.0730772018432617}
-03/05/2022 09:07:53 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/05/2022 09:07:56 - INFO - codeparrot_training - Step 37147: {'lr': 0.0004335914336527382, 'samples': 19019776, 'steps': 37147, 'loss/train': 1.8659542798995972}
-03/05/2022 09:07:59 - INFO - codeparrot_training - Step 37148: {'lr': 0.0004335878316375206, 'samples': 19020288, 'steps': 37148, 'loss/train': 1.8043835163116455}
-03/05/2022 09:08:01 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/05/2022 09:08:05 - INFO - codeparrot_training - Step 37149: {'lr': 0.0004335842295395811, 'samples': 19020800, 'steps': 37149, 'loss/train': 1.260195016860962}
-03/05/2022 09:08:08 - INFO - codeparrot_training - Step 37150: {'lr': 0.0004335806273589214, 'samples': 19021312, 'steps': 37150, 'loss/train': 1.5253543853759766}
-03/05/2022 09:08:10 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/05/2022 09:08:13 - INFO - codeparrot_training - Step 37151: {'lr': 0.0004335770250955431, 'samples': 19021824, 'steps': 37151, 'loss/train': 1.5623302459716797}
-03/05/2022 09:08:16 - INFO - codeparrot_training - Step 37152: {'lr': 0.0004335734227494478, 'samples': 19022336, 'steps': 37152, 'loss/train': 1.019531011581421}
-03/05/2022 09:08:18 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/05/2022 09:08:22 - INFO - codeparrot_training - Step 37153: {'lr': 0.0004335698203206372, 'samples': 19022848, 'steps': 37153, 'loss/train': 1.488417148590088}
-03/05/2022 09:08:25 - INFO - codeparrot_training - Step 37154: {'lr': 0.00043356621780911273, 'samples': 19023360, 'steps': 37154, 'loss/train': 2.2847955226898193}
-03/05/2022 09:08:27 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/05/2022 09:08:30 - INFO - codeparrot_training - Step 37155: {'lr': 0.0004335626152148763, 'samples': 19023872, 'steps': 37155, 'loss/train': 1.5035854578018188}
-03/05/2022 09:08:33 - INFO - codeparrot_training - Step 37156: {'lr': 0.0004335590125379293, 'samples': 19024384, 'steps': 37156, 'loss/train': 2.558440923690796}
-03/05/2022 09:08:36 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/05/2022 09:08:39 - INFO - codeparrot_training - Step 37157: {'lr': 0.00043355540977827356, 'samples': 19024896, 'steps': 37157, 'loss/train': 2.4427340030670166}
-03/05/2022 09:08:42 - INFO - codeparrot_training - Step 37158: {'lr': 0.0004335518069359105, 'samples': 19025408, 'steps': 37158, 'loss/train': 1.1898554563522339}
-03/05/2022 09:08:44 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/05/2022 09:08:47 - INFO - codeparrot_training - Step 37159: {'lr': 0.0004335482040108418, 'samples': 19025920, 'steps': 37159, 'loss/train': 1.855122447013855}
-03/05/2022 09:08:50 - INFO - codeparrot_training - Step 37160: {'lr': 0.00043354460100306915, 'samples': 19026432, 'steps': 37160, 'loss/train': 0.7699187994003296}
-03/05/2022 09:08:52 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/05/2022 09:08:55 - INFO - codeparrot_training - Step 37161: {'lr': 0.00043354099791259414, 'samples': 19026944, 'steps': 37161, 'loss/train': 1.342292070388794}
-03/05/2022 09:08:59 - INFO - codeparrot_training - Step 37162: {'lr': 0.00043353739473941846, 'samples': 19027456, 'steps': 37162, 'loss/train': 1.8867727518081665}
-03/05/2022 09:09:01 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/05/2022 09:09:04 - INFO - codeparrot_training - Step 37163: {'lr': 0.0004335337914835435, 'samples': 19027968, 'steps': 37163, 'loss/train': 1.7273555994033813}
-03/05/2022 09:09:07 - INFO - codeparrot_training - Step 37164: {'lr': 0.0004335301881449711, 'samples': 19028480, 'steps': 37164, 'loss/train': 2.3171653747558594}
-03/05/2022 09:09:09 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/05/2022 09:09:12 - INFO - codeparrot_training - Step 37165: {'lr': 0.00043352658472370294, 'samples': 19028992, 'steps': 37165, 'loss/train': 1.138758897781372}
-03/05/2022 09:09:15 - INFO - codeparrot_training - Step 37166: {'lr': 0.00043352298121974043, 'samples': 19029504, 'steps': 37166, 'loss/train': 2.079317331314087}
-03/05/2022 09:09:17 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/05/2022 09:09:21 - INFO - codeparrot_training - Step 37167: {'lr': 0.00043351937763308533, 'samples': 19030016, 'steps': 37167, 'loss/train': 1.6257760524749756}
-03/05/2022 09:09:24 - INFO - codeparrot_training - Step 37168: {'lr': 0.0004335157739637392, 'samples': 19030528, 'steps': 37168, 'loss/train': 1.5245778560638428}
-03/05/2022 09:09:26 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/05/2022 09:09:29 - INFO - codeparrot_training - Step 37169: {'lr': 0.0004335121702117038, 'samples': 19031040, 'steps': 37169, 'loss/train': 1.6117690801620483}
-03/05/2022 09:09:32 - INFO - codeparrot_training - Step 37170: {'lr': 0.0004335085663769805, 'samples': 19031552, 'steps': 37170, 'loss/train': 1.4633811712265015}
-03/05/2022 09:09:35 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/05/2022 09:09:38 - INFO - codeparrot_training - Step 37171: {'lr': 0.00043350496245957116, 'samples': 19032064, 'steps': 37171, 'loss/train': 1.8071073293685913}
-03/05/2022 09:09:41 - INFO - codeparrot_training - Step 37172: {'lr': 0.00043350135845947725, 'samples': 19032576, 'steps': 37172, 'loss/train': 2.6616435050964355}
-03/05/2022 09:09:44 - INFO - codeparrot_training - Step 37173: {'lr': 0.00043349775437670046, 'samples': 19033088, 'steps': 37173, 'loss/train': 1.2873822450637817}
-03/05/2022 09:09:44 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/05/2022 09:09:49 - INFO - codeparrot_training - Step 37174: {'lr': 0.0004334941502112425, 'samples': 19033600, 'steps': 37174, 'loss/train': 1.9465914964675903}
-03/05/2022 09:09:53 - INFO - codeparrot_training - Step 37175: {'lr': 0.0004334905459631049, 'samples': 19034112, 'steps': 37175, 'loss/train': 1.5150432586669922}
-03/05/2022 09:09:53 - INFO - codeparrot_training - Skipping example with length 1005 (seq_length=1024)
-03/05/2022 09:09:58 - INFO - codeparrot_training - Step 37176: {'lr': 0.0004334869416322892, 'samples': 19034624, 'steps': 37176, 'loss/train': 0.9372521042823792}
-03/05/2022 09:10:01 - INFO - codeparrot_training - Step 37177: {'lr': 0.0004334833372187972, 'samples': 19035136, 'steps': 37177, 'loss/train': 3.279226779937744}
-03/05/2022 09:10:01 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/05/2022 09:10:06 - INFO - codeparrot_training - Step 37178: {'lr': 0.0004334797327226304, 'samples': 19035648, 'steps': 37178, 'loss/train': 0.5276676416397095}
-03/05/2022 09:10:09 - INFO - codeparrot_training - Step 37179: {'lr': 0.00043347612814379047, 'samples': 19036160, 'steps': 37179, 'loss/train': 1.4646509885787964}
-03/05/2022 09:10:09 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/05/2022 09:10:15 - INFO - codeparrot_training - Step 37180: {'lr': 0.000433472523482279, 'samples': 19036672, 'steps': 37180, 'loss/train': 1.7994753122329712}
-03/05/2022 09:10:17 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/05/2022 09:10:20 - INFO - codeparrot_training - Step 37181: {'lr': 0.0004334689187380977, 'samples': 19037184, 'steps': 37181, 'loss/train': 2.0101513862609863}
-03/05/2022 09:10:23 - INFO - codeparrot_training - Step 37182: {'lr': 0.0004334653139112481, 'samples': 19037696, 'steps': 37182, 'loss/train': 1.8706097602844238}
-03/05/2022 09:10:26 - INFO - codeparrot_training - Skipping example with length 59 (seq_length=1024)
-03/05/2022 09:10:28 - INFO - codeparrot_training - Step 37183: {'lr': 0.0004334617090017319, 'samples': 19038208, 'steps': 37183, 'loss/train': 0.9321692585945129}
-03/05/2022 09:10:32 - INFO - codeparrot_training - Step 37184: {'lr': 0.0004334581040095506, 'samples': 19038720, 'steps': 37184, 'loss/train': 1.9465187788009644}
-03/05/2022 09:10:34 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/05/2022 09:10:37 - INFO - codeparrot_training - Step 37185: {'lr': 0.00043345449893470594, 'samples': 19039232, 'steps': 37185, 'loss/train': 1.8337160348892212}
-03/05/2022 09:10:40 - INFO - codeparrot_training - Step 37186: {'lr': 0.00043345089377719954, 'samples': 19039744, 'steps': 37186, 'loss/train': 1.20099675655365}
-03/05/2022 09:10:43 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/05/2022 09:10:45 - INFO - codeparrot_training - Step 37187: {'lr': 0.00043344728853703297, 'samples': 19040256, 'steps': 37187, 'loss/train': 1.42197585105896}
-03/05/2022 09:10:48 - INFO - codeparrot_training - Step 37188: {'lr': 0.0004334436832142079, 'samples': 19040768, 'steps': 37188, 'loss/train': 1.7639576196670532}
-03/05/2022 09:10:51 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/05/2022 09:10:54 - INFO - codeparrot_training - Step 37189: {'lr': 0.000433440077808726, 'samples': 19041280, 'steps': 37189, 'loss/train': 1.499832272529602}
-03/05/2022 09:10:57 - INFO - codeparrot_training - Step 37190: {'lr': 0.00043343647232058877, 'samples': 19041792, 'steps': 37190, 'loss/train': 1.8163385391235352}
-03/05/2022 09:10:59 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/05/2022 09:11:02 - INFO - codeparrot_training - Step 37191: {'lr': 0.0004334328667497979, 'samples': 19042304, 'steps': 37191, 'loss/train': 1.8642280101776123}
-03/05/2022 09:11:05 - INFO - codeparrot_training - Step 37192: {'lr': 0.00043342926109635497, 'samples': 19042816, 'steps': 37192, 'loss/train': 1.150327444076538}
-03/05/2022 09:11:08 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/05/2022 09:11:11 - INFO - codeparrot_training - Step 37193: {'lr': 0.0004334256553602617, 'samples': 19043328, 'steps': 37193, 'loss/train': 1.3464022874832153}
-03/05/2022 09:11:14 - INFO - codeparrot_training - Step 37194: {'lr': 0.00043342204954151963, 'samples': 19043840, 'steps': 37194, 'loss/train': 0.9517424702644348}
-03/05/2022 09:11:16 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/05/2022 09:11:19 - INFO - codeparrot_training - Step 37195: {'lr': 0.00043341844364013047, 'samples': 19044352, 'steps': 37195, 'loss/train': 1.779246211051941}
-03/05/2022 09:11:22 - INFO - codeparrot_training - Step 37196: {'lr': 0.00043341483765609566, 'samples': 19044864, 'steps': 37196, 'loss/train': 1.291870355606079}
-03/05/2022 09:11:24 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/05/2022 09:11:27 - INFO - codeparrot_training - Step 37197: {'lr': 0.0004334112315894171, 'samples': 19045376, 'steps': 37197, 'loss/train': 2.047727108001709}
-03/05/2022 09:11:31 - INFO - codeparrot_training - Step 37198: {'lr': 0.00043340762544009627, 'samples': 19045888, 'steps': 37198, 'loss/train': 1.1536909341812134}
-03/05/2022 09:11:33 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/05/2022 09:11:36 - INFO - codeparrot_training - Step 37199: {'lr': 0.0004334040192081347, 'samples': 19046400, 'steps': 37199, 'loss/train': 1.740929126739502}
-03/05/2022 09:11:39 - INFO - codeparrot_training - Step 37200: {'lr': 0.00043340041289353416, 'samples': 19046912, 'steps': 37200, 'loss/train': 2.8420591354370117}
-03/05/2022 09:11:41 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/05/2022 09:11:44 - INFO - codeparrot_training - Step 37201: {'lr': 0.0004333968064962962, 'samples': 19047424, 'steps': 37201, 'loss/train': 1.2579494714736938}
-03/05/2022 09:11:47 - INFO - codeparrot_training - Step 37202: {'lr': 0.00043339320001642244, 'samples': 19047936, 'steps': 37202, 'loss/train': 0.5379994511604309}
-03/05/2022 09:11:49 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/05/2022 09:11:53 - INFO - codeparrot_training - Step 37203: {'lr': 0.0004333895934539146, 'samples': 19048448, 'steps': 37203, 'loss/train': 2.1487693786621094}
-03/05/2022 09:11:56 - INFO - codeparrot_training - Step 37204: {'lr': 0.00043338598680877423, 'samples': 19048960, 'steps': 37204, 'loss/train': 2.5150232315063477}
-03/05/2022 09:11:58 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 09:12:01 - INFO - codeparrot_training - Step 37205: {'lr': 0.00043338238008100297, 'samples': 19049472, 'steps': 37205, 'loss/train': 1.4111640453338623}
-03/05/2022 09:12:04 - INFO - codeparrot_training - Step 37206: {'lr': 0.0004333787732706024, 'samples': 19049984, 'steps': 37206, 'loss/train': 0.6248279809951782}
-03/05/2022 09:12:06 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/05/2022 09:12:10 - INFO - codeparrot_training - Step 37207: {'lr': 0.00043337516637757416, 'samples': 19050496, 'steps': 37207, 'loss/train': 1.9875731468200684}
-03/05/2022 09:12:13 - INFO - codeparrot_training - Step 37208: {'lr': 0.00043337155940191996, 'samples': 19051008, 'steps': 37208, 'loss/train': 1.2876697778701782}
-03/05/2022 09:12:15 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/05/2022 09:12:18 - INFO - codeparrot_training - Step 37209: {'lr': 0.0004333679523436413, 'samples': 19051520, 'steps': 37209, 'loss/train': 1.8852626085281372}
-03/05/2022 09:12:21 - INFO - codeparrot_training - Step 37210: {'lr': 0.0004333643452027399, 'samples': 19052032, 'steps': 37210, 'loss/train': 1.2152680158615112}
-03/05/2022 09:12:24 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/05/2022 09:12:27 - INFO - codeparrot_training - Step 37211: {'lr': 0.00043336073797921743, 'samples': 19052544, 'steps': 37211, 'loss/train': 2.0774142742156982}
-03/05/2022 09:12:30 - INFO - codeparrot_training - Step 37212: {'lr': 0.0004333571306730754, 'samples': 19053056, 'steps': 37212, 'loss/train': 1.1418336629867554}
-03/05/2022 09:12:32 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/05/2022 09:12:35 - INFO - codeparrot_training - Step 37213: {'lr': 0.00043335352328431544, 'samples': 19053568, 'steps': 37213, 'loss/train': 2.3217196464538574}
-03/05/2022 09:12:38 - INFO - codeparrot_training - Step 37214: {'lr': 0.00043334991581293924, 'samples': 19054080, 'steps': 37214, 'loss/train': 1.5781137943267822}
-03/05/2022 09:12:40 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/05/2022 09:12:44 - INFO - codeparrot_training - Step 37215: {'lr': 0.0004333463082589484, 'samples': 19054592, 'steps': 37215, 'loss/train': 0.8202218413352966}
-03/05/2022 09:12:47 - INFO - codeparrot_training - Step 37216: {'lr': 0.0004333427006223445, 'samples': 19055104, 'steps': 37216, 'loss/train': 2.125861883163452}
-03/05/2022 09:12:49 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/05/2022 09:12:52 - INFO - codeparrot_training - Step 37217: {'lr': 0.00043333909290312923, 'samples': 19055616, 'steps': 37217, 'loss/train': 2.398944139480591}
-03/05/2022 09:12:55 - INFO - codeparrot_training - Step 37218: {'lr': 0.00043333548510130426, 'samples': 19056128, 'steps': 37218, 'loss/train': 1.9081380367279053}
-03/05/2022 09:12:58 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/05/2022 09:13:00 - INFO - codeparrot_training - Step 37219: {'lr': 0.00043333187721687104, 'samples': 19056640, 'steps': 37219, 'loss/train': 1.366235613822937}
-03/05/2022 09:13:04 - INFO - codeparrot_training - Step 37220: {'lr': 0.0004333282692498314, 'samples': 19057152, 'steps': 37220, 'loss/train': 1.055216908454895}
-03/05/2022 09:13:06 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 09:13:09 - INFO - codeparrot_training - Step 37221: {'lr': 0.00043332466120018685, 'samples': 19057664, 'steps': 37221, 'loss/train': 1.3197872638702393}
-03/05/2022 09:13:12 - INFO - codeparrot_training - Step 37222: {'lr': 0.000433321053067939, 'samples': 19058176, 'steps': 37222, 'loss/train': 1.0913422107696533}
-03/05/2022 09:13:15 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/05/2022 09:13:17 - INFO - codeparrot_training - Step 37223: {'lr': 0.00043331744485308954, 'samples': 19058688, 'steps': 37223, 'loss/train': 2.7695372104644775}
-03/05/2022 09:13:20 - INFO - codeparrot_training - Step 37224: {'lr': 0.00043331383655564003, 'samples': 19059200, 'steps': 37224, 'loss/train': 1.3819255828857422}
-03/05/2022 09:13:23 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/05/2022 09:13:26 - INFO - codeparrot_training - Step 37225: {'lr': 0.0004333102281755922, 'samples': 19059712, 'steps': 37225, 'loss/train': 1.5102075338363647}
-03/05/2022 09:13:29 - INFO - codeparrot_training - Step 37226: {'lr': 0.0004333066197129475, 'samples': 19060224, 'steps': 37226, 'loss/train': 1.6563533544540405}
-03/05/2022 09:13:32 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/05/2022 09:13:34 - INFO - codeparrot_training - Step 37227: {'lr': 0.00043330301116770777, 'samples': 19060736, 'steps': 37227, 'loss/train': 1.7835414409637451}
-03/05/2022 09:13:37 - INFO - codeparrot_training - Step 37228: {'lr': 0.0004332994025398745, 'samples': 19061248, 'steps': 37228, 'loss/train': 0.7525253295898438}
-03/05/2022 09:13:40 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/05/2022 09:13:43 - INFO - codeparrot_training - Step 37229: {'lr': 0.0004332957938294493, 'samples': 19061760, 'steps': 37229, 'loss/train': 1.8023426532745361}
-03/05/2022 09:13:46 - INFO - codeparrot_training - Step 37230: {'lr': 0.0004332921850364339, 'samples': 19062272, 'steps': 37230, 'loss/train': 0.955630362033844}
-03/05/2022 09:13:48 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 09:13:51 - INFO - codeparrot_training - Step 37231: {'lr': 0.00043328857616082986, 'samples': 19062784, 'steps': 37231, 'loss/train': 1.55934739112854}
-03/05/2022 09:13:54 - INFO - codeparrot_training - Step 37232: {'lr': 0.0004332849672026388, 'samples': 19063296, 'steps': 37232, 'loss/train': 1.3324642181396484}
-03/05/2022 09:13:57 - INFO - codeparrot_training - Skipping example with length 260 (seq_length=1024)
-03/05/2022 09:14:00 - INFO - codeparrot_training - Step 37233: {'lr': 0.0004332813581618624, 'samples': 19063808, 'steps': 37233, 'loss/train': 1.6999443769454956}
-03/05/2022 09:14:03 - INFO - codeparrot_training - Step 37234: {'lr': 0.00043327774903850226, 'samples': 19064320, 'steps': 37234, 'loss/train': 1.1778486967086792}
-03/05/2022 09:14:05 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/05/2022 09:14:08 - INFO - codeparrot_training - Step 37235: {'lr': 0.0004332741398325599, 'samples': 19064832, 'steps': 37235, 'loss/train': 1.6891238689422607}
-03/05/2022 09:14:11 - INFO - codeparrot_training - Step 37236: {'lr': 0.00043327053054403707, 'samples': 19065344, 'steps': 37236, 'loss/train': 1.519893765449524}
-03/05/2022 09:14:14 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 09:14:16 - INFO - codeparrot_training - Step 37237: {'lr': 0.0004332669211729354, 'samples': 19065856, 'steps': 37237, 'loss/train': 1.3129029273986816}
-03/05/2022 09:14:20 - INFO - codeparrot_training - Step 37238: {'lr': 0.00043326331171925656, 'samples': 19066368, 'steps': 37238, 'loss/train': 1.398112416267395}
-03/05/2022 09:14:22 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/05/2022 09:14:25 - INFO - codeparrot_training - Step 37239: {'lr': 0.000433259702183002, 'samples': 19066880, 'steps': 37239, 'loss/train': 1.9617180824279785}
-03/05/2022 09:14:28 - INFO - codeparrot_training - Step 37240: {'lr': 0.0004332560925641734, 'samples': 19067392, 'steps': 37240, 'loss/train': 3.2054178714752197}
-03/05/2022 09:14:30 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/05/2022 09:14:33 - INFO - codeparrot_training - Step 37241: {'lr': 0.0004332524828627725, 'samples': 19067904, 'steps': 37241, 'loss/train': 1.6829006671905518}
-03/05/2022 09:14:37 - INFO - codeparrot_training - Step 37242: {'lr': 0.0004332488730788009, 'samples': 19068416, 'steps': 37242, 'loss/train': 1.6495716571807861}
-03/05/2022 09:14:39 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/05/2022 09:14:42 - INFO - codeparrot_training - Step 37243: {'lr': 0.0004332452632122601, 'samples': 19068928, 'steps': 37243, 'loss/train': 1.2926064729690552}
-03/05/2022 09:14:45 - INFO - codeparrot_training - Step 37244: {'lr': 0.0004332416532631519, 'samples': 19069440, 'steps': 37244, 'loss/train': 1.1981189250946045}
-03/05/2022 09:14:47 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/05/2022 09:14:50 - INFO - codeparrot_training - Step 37245: {'lr': 0.00043323804323147777, 'samples': 19069952, 'steps': 37245, 'loss/train': 1.364798665046692}
-03/05/2022 09:14:53 - INFO - codeparrot_training - Step 37246: {'lr': 0.0004332344331172394, 'samples': 19070464, 'steps': 37246, 'loss/train': 1.69232976436615}
-03/05/2022 09:14:56 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 09:14:59 - INFO - codeparrot_training - Step 37247: {'lr': 0.0004332308229204385, 'samples': 19070976, 'steps': 37247, 'loss/train': 1.5967638492584229}
-03/05/2022 09:15:02 - INFO - codeparrot_training - Step 37248: {'lr': 0.00043322721264107657, 'samples': 19071488, 'steps': 37248, 'loss/train': 1.9966073036193848}
-03/05/2022 09:15:04 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/05/2022 09:15:07 - INFO - codeparrot_training - Step 37249: {'lr': 0.00043322360227915526, 'samples': 19072000, 'steps': 37249, 'loss/train': 1.4784129858016968}
-03/05/2022 09:15:10 - INFO - codeparrot_training - Step 37250: {'lr': 0.0004332199918346763, 'samples': 19072512, 'steps': 37250, 'loss/train': 1.0774372816085815}
-03/05/2022 09:15:13 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 09:15:16 - INFO - codeparrot_training - Step 37251: {'lr': 0.00043321638130764116, 'samples': 19073024, 'steps': 37251, 'loss/train': 2.132511854171753}
-03/05/2022 09:15:19 - INFO - codeparrot_training - Step 37252: {'lr': 0.00043321277069805153, 'samples': 19073536, 'steps': 37252, 'loss/train': 2.3566572666168213}
-03/05/2022 09:15:21 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/05/2022 09:15:24 - INFO - codeparrot_training - Step 37253: {'lr': 0.0004332091600059091, 'samples': 19074048, 'steps': 37253, 'loss/train': 1.4322679042816162}
-03/05/2022 09:15:27 - INFO - codeparrot_training - Step 37254: {'lr': 0.00043320554923121545, 'samples': 19074560, 'steps': 37254, 'loss/train': 1.9493342638015747}
-03/05/2022 09:15:29 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/05/2022 09:15:33 - INFO - codeparrot_training - Step 37255: {'lr': 0.0004332019383739722, 'samples': 19075072, 'steps': 37255, 'loss/train': 1.4963582754135132}
-03/05/2022 09:15:36 - INFO - codeparrot_training - Step 37256: {'lr': 0.000433198327434181, 'samples': 19075584, 'steps': 37256, 'loss/train': 0.601830005645752}
-03/05/2022 09:15:38 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/05/2022 09:15:41 - INFO - codeparrot_training - Step 37257: {'lr': 0.0004331947164118434, 'samples': 19076096, 'steps': 37257, 'loss/train': 1.796028971672058}
-03/05/2022 09:15:44 - INFO - codeparrot_training - Step 37258: {'lr': 0.00043319110530696116, 'samples': 19076608, 'steps': 37258, 'loss/train': 1.6336404085159302}
-03/05/2022 09:15:46 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/05/2022 09:15:50 - INFO - codeparrot_training - Step 37259: {'lr': 0.00043318749411953584, 'samples': 19077120, 'steps': 37259, 'loss/train': 0.884859561920166}
-03/05/2022 09:15:53 - INFO - codeparrot_training - Step 37260: {'lr': 0.000433183882849569, 'samples': 19077632, 'steps': 37260, 'loss/train': 0.9211164712905884}
-03/05/2022 09:15:56 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/05/2022 09:15:59 - INFO - codeparrot_training - Step 37261: {'lr': 0.0004331802714970624, 'samples': 19078144, 'steps': 37261, 'loss/train': 1.486607313156128}
-03/05/2022 09:16:02 - INFO - codeparrot_training - Step 37262: {'lr': 0.0004331766600620175, 'samples': 19078656, 'steps': 37262, 'loss/train': 1.5779222249984741}
-03/05/2022 09:16:04 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 09:16:07 - INFO - codeparrot_training - Step 37263: {'lr': 0.00043317304854443607, 'samples': 19079168, 'steps': 37263, 'loss/train': 1.4708834886550903}
-03/05/2022 09:16:10 - INFO - codeparrot_training - Step 37264: {'lr': 0.0004331694369443197, 'samples': 19079680, 'steps': 37264, 'loss/train': 1.3905649185180664}
-03/05/2022 09:16:12 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/05/2022 09:16:16 - INFO - codeparrot_training - Step 37265: {'lr': 0.00043316582526167004, 'samples': 19080192, 'steps': 37265, 'loss/train': 2.2101755142211914}
-03/05/2022 09:16:19 - INFO - codeparrot_training - Step 37266: {'lr': 0.0004331622134964887, 'samples': 19080704, 'steps': 37266, 'loss/train': 1.789198637008667}
-03/05/2022 09:16:21 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/05/2022 09:16:24 - INFO - codeparrot_training - Step 37267: {'lr': 0.0004331586016487772, 'samples': 19081216, 'steps': 37267, 'loss/train': 1.5984159708023071}
-03/05/2022 09:16:27 - INFO - codeparrot_training - Step 37268: {'lr': 0.00043315498971853726, 'samples': 19081728, 'steps': 37268, 'loss/train': 1.887995719909668}
-03/05/2022 09:16:29 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 09:16:33 - INFO - codeparrot_training - Step 37269: {'lr': 0.0004331513777057706, 'samples': 19082240, 'steps': 37269, 'loss/train': 2.2215378284454346}
-03/05/2022 09:16:36 - INFO - codeparrot_training - Step 37270: {'lr': 0.00043314776561047865, 'samples': 19082752, 'steps': 37270, 'loss/train': 2.156205177307129}
-03/05/2022 09:16:40 - INFO - codeparrot_training - Step 37271: {'lr': 0.0004331441534326632, 'samples': 19083264, 'steps': 37271, 'loss/train': 2.110055685043335}
-03/05/2022 09:16:41 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/05/2022 09:16:45 - INFO - codeparrot_training - Step 37272: {'lr': 0.0004331405411723258, 'samples': 19083776, 'steps': 37272, 'loss/train': 1.8781111240386963}
-03/05/2022 09:16:48 - INFO - codeparrot_training - Step 37273: {'lr': 0.0004331369288294681, 'samples': 19084288, 'steps': 37273, 'loss/train': 2.123711585998535}
-03/05/2022 09:16:50 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/05/2022 09:16:53 - INFO - codeparrot_training - Step 37274: {'lr': 0.0004331333164040918, 'samples': 19084800, 'steps': 37274, 'loss/train': 1.5526198148727417}
-03/05/2022 09:16:56 - INFO - codeparrot_training - Step 37275: {'lr': 0.0004331297038961984, 'samples': 19085312, 'steps': 37275, 'loss/train': 2.1994760036468506}
-03/05/2022 09:16:58 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/05/2022 09:17:02 - INFO - codeparrot_training - Step 37276: {'lr': 0.00043312609130578963, 'samples': 19085824, 'steps': 37276, 'loss/train': 1.8799238204956055}
-03/05/2022 09:17:05 - INFO - codeparrot_training - Step 37277: {'lr': 0.000433122478632867, 'samples': 19086336, 'steps': 37277, 'loss/train': 0.898362398147583}
-03/05/2022 09:17:08 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/05/2022 09:17:10 - INFO - codeparrot_training - Step 37278: {'lr': 0.0004331188658774322, 'samples': 19086848, 'steps': 37278, 'loss/train': 0.8972975611686707}
-03/05/2022 09:17:14 - INFO - codeparrot_training - Step 37279: {'lr': 0.00043311525303948685, 'samples': 19087360, 'steps': 37279, 'loss/train': 0.7990037798881531}
-03/05/2022 09:17:16 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/05/2022 09:17:19 - INFO - codeparrot_training - Step 37280: {'lr': 0.0004331116401190327, 'samples': 19087872, 'steps': 37280, 'loss/train': 1.9313828945159912}
-03/05/2022 09:17:22 - INFO - codeparrot_training - Step 37281: {'lr': 0.0004331080271160712, 'samples': 19088384, 'steps': 37281, 'loss/train': 3.274109363555908}
-03/05/2022 09:17:25 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/05/2022 09:17:27 - INFO - codeparrot_training - Step 37282: {'lr': 0.00043310441403060404, 'samples': 19088896, 'steps': 37282, 'loss/train': 3.413198947906494}
-03/05/2022 09:17:31 - INFO - codeparrot_training - Step 37283: {'lr': 0.00043310080086263284, 'samples': 19089408, 'steps': 37283, 'loss/train': 0.8329365253448486}
-03/05/2022 09:17:33 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/05/2022 09:17:36 - INFO - codeparrot_training - Step 37284: {'lr': 0.0004330971876121593, 'samples': 19089920, 'steps': 37284, 'loss/train': 1.246399164199829}
-03/05/2022 09:17:39 - INFO - codeparrot_training - Step 37285: {'lr': 0.0004330935742791849, 'samples': 19090432, 'steps': 37285, 'loss/train': 1.1021398305892944}
-03/05/2022 09:17:42 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/05/2022 09:17:45 - INFO - codeparrot_training - Step 37286: {'lr': 0.00043308996086371146, 'samples': 19090944, 'steps': 37286, 'loss/train': 1.8378922939300537}
-03/05/2022 09:17:48 - INFO - codeparrot_training - Step 37287: {'lr': 0.0004330863473657405, 'samples': 19091456, 'steps': 37287, 'loss/train': 1.7196879386901855}
-03/05/2022 09:17:50 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/05/2022 09:17:53 - INFO - codeparrot_training - Step 37288: {'lr': 0.00043308273378527364, 'samples': 19091968, 'steps': 37288, 'loss/train': 1.3377351760864258}
-03/05/2022 09:17:56 - INFO - codeparrot_training - Step 37289: {'lr': 0.00043307912012231255, 'samples': 19092480, 'steps': 37289, 'loss/train': 1.8187739849090576}
-03/05/2022 09:17:58 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/05/2022 09:18:02 - INFO - codeparrot_training - Step 37290: {'lr': 0.0004330755063768588, 'samples': 19092992, 'steps': 37290, 'loss/train': 1.7614995241165161}
-03/05/2022 09:18:05 - INFO - codeparrot_training - Step 37291: {'lr': 0.000433071892548914, 'samples': 19093504, 'steps': 37291, 'loss/train': 2.087303876876831}
-03/05/2022 09:18:07 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/05/2022 09:18:10 - INFO - codeparrot_training - Step 37292: {'lr': 0.00043306827863847985, 'samples': 19094016, 'steps': 37292, 'loss/train': 1.9073433876037598}
-03/05/2022 09:18:13 - INFO - codeparrot_training - Step 37293: {'lr': 0.00043306466464555803, 'samples': 19094528, 'steps': 37293, 'loss/train': 1.662179708480835}
-03/05/2022 09:18:16 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/05/2022 09:18:19 - INFO - codeparrot_training - Step 37294: {'lr': 0.0004330610505701501, 'samples': 19095040, 'steps': 37294, 'loss/train': 1.7765673398971558}
-03/05/2022 09:18:22 - INFO - codeparrot_training - Step 37295: {'lr': 0.00043305743641225766, 'samples': 19095552, 'steps': 37295, 'loss/train': 1.4252513647079468}
-03/05/2022 09:18:25 - INFO - codeparrot_training - Step 37296: {'lr': 0.00043305382217188225, 'samples': 19096064, 'steps': 37296, 'loss/train': 1.893965244293213}
-03/05/2022 09:18:25 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/05/2022 09:18:30 - INFO - codeparrot_training - Step 37297: {'lr': 0.0004330502078490258, 'samples': 19096576, 'steps': 37297, 'loss/train': 1.280961513519287}
-03/05/2022 09:18:33 - INFO - codeparrot_training - Step 37298: {'lr': 0.0004330465934436896, 'samples': 19097088, 'steps': 37298, 'loss/train': 1.750510811805725}
-03/05/2022 09:18:34 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/05/2022 09:18:39 - INFO - codeparrot_training - Step 37299: {'lr': 0.00043304297895587553, 'samples': 19097600, 'steps': 37299, 'loss/train': 1.2805050611495972}
-03/05/2022 09:18:42 - INFO - codeparrot_training - Step 37300: {'lr': 0.0004330393643855851, 'samples': 19098112, 'steps': 37300, 'loss/train': 1.9552524089813232}
-03/05/2022 09:18:42 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/05/2022 09:18:48 - INFO - codeparrot_training - Step 37301: {'lr': 0.0004330357497328199, 'samples': 19098624, 'steps': 37301, 'loss/train': 1.4127495288848877}
-03/05/2022 09:18:51 - INFO - codeparrot_training - Step 37302: {'lr': 0.00043303213499758166, 'samples': 19099136, 'steps': 37302, 'loss/train': 1.7767469882965088}
-03/05/2022 09:18:51 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 09:18:56 - INFO - codeparrot_training - Step 37303: {'lr': 0.00043302852017987196, 'samples': 19099648, 'steps': 37303, 'loss/train': 2.5363333225250244}
-03/05/2022 09:18:59 - INFO - codeparrot_training - Step 37304: {'lr': 0.0004330249052796924, 'samples': 19100160, 'steps': 37304, 'loss/train': 1.5441447496414185}
-03/05/2022 09:19:00 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/05/2022 09:19:04 - INFO - codeparrot_training - Step 37305: {'lr': 0.0004330212902970447, 'samples': 19100672, 'steps': 37305, 'loss/train': 1.6807595491409302}
-03/05/2022 09:19:07 - INFO - codeparrot_training - Step 37306: {'lr': 0.0004330176752319304, 'samples': 19101184, 'steps': 37306, 'loss/train': 1.852253794670105}
-03/05/2022 09:19:08 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/05/2022 09:19:13 - INFO - codeparrot_training - Step 37307: {'lr': 0.0004330140600843512, 'samples': 19101696, 'steps': 37307, 'loss/train': 1.1957494020462036}
-03/05/2022 09:19:16 - INFO - codeparrot_training - Step 37308: {'lr': 0.0004330104448543086, 'samples': 19102208, 'steps': 37308, 'loss/train': 1.0698621273040771}
-03/05/2022 09:19:17 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/05/2022 09:19:21 - INFO - codeparrot_training - Step 37309: {'lr': 0.0004330068295418044, 'samples': 19102720, 'steps': 37309, 'loss/train': 1.8032397031784058}
-03/05/2022 09:19:25 - INFO - codeparrot_training - Step 37310: {'lr': 0.0004330032141468401, 'samples': 19103232, 'steps': 37310, 'loss/train': 1.57412588596344}
-03/05/2022 09:19:26 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/05/2022 09:19:30 - INFO - codeparrot_training - Step 37311: {'lr': 0.0004329995986694174, 'samples': 19103744, 'steps': 37311, 'loss/train': 1.9955803155899048}
-03/05/2022 09:19:33 - INFO - codeparrot_training - Step 37312: {'lr': 0.00043299598310953793, 'samples': 19104256, 'steps': 37312, 'loss/train': 1.413143515586853}
-03/05/2022 09:19:34 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/05/2022 09:19:38 - INFO - codeparrot_training - Step 37313: {'lr': 0.0004329923674672032, 'samples': 19104768, 'steps': 37313, 'loss/train': 3.051741600036621}
-03/05/2022 09:19:42 - INFO - codeparrot_training - Step 37314: {'lr': 0.00043298875174241504, 'samples': 19105280, 'steps': 37314, 'loss/train': 1.1036561727523804}
-03/05/2022 09:19:43 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/05/2022 09:19:47 - INFO - codeparrot_training - Step 37315: {'lr': 0.00043298513593517483, 'samples': 19105792, 'steps': 37315, 'loss/train': 1.422577977180481}
-03/05/2022 09:19:50 - INFO - codeparrot_training - Step 37316: {'lr': 0.0004329815200454845, 'samples': 19106304, 'steps': 37316, 'loss/train': 1.7480827569961548}
-03/05/2022 09:19:51 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/05/2022 09:19:55 - INFO - codeparrot_training - Step 37317: {'lr': 0.00043297790407334545, 'samples': 19106816, 'steps': 37317, 'loss/train': 1.4802038669586182}
-03/05/2022 09:19:58 - INFO - codeparrot_training - Step 37318: {'lr': 0.0004329742880187594, 'samples': 19107328, 'steps': 37318, 'loss/train': 1.5103607177734375}
-03/05/2022 09:20:00 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/05/2022 09:20:04 - INFO - codeparrot_training - Step 37319: {'lr': 0.0004329706718817279, 'samples': 19107840, 'steps': 37319, 'loss/train': 1.5711520910263062}
-03/05/2022 09:20:07 - INFO - codeparrot_training - Step 37320: {'lr': 0.00043296705566225267, 'samples': 19108352, 'steps': 37320, 'loss/train': 1.523724913597107}
-03/05/2022 09:20:08 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/05/2022 09:20:12 - INFO - codeparrot_training - Step 37321: {'lr': 0.00043296343936033535, 'samples': 19108864, 'steps': 37321, 'loss/train': 1.620537281036377}
-03/05/2022 09:20:15 - INFO - codeparrot_training - Step 37322: {'lr': 0.0004329598229759775, 'samples': 19109376, 'steps': 37322, 'loss/train': 2.179577589035034}
-03/05/2022 09:20:16 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/05/2022 09:20:21 - INFO - codeparrot_training - Step 37323: {'lr': 0.00043295620650918076, 'samples': 19109888, 'steps': 37323, 'loss/train': 1.6708800792694092}
-03/05/2022 09:20:24 - INFO - codeparrot_training - Step 37324: {'lr': 0.0004329525899599468, 'samples': 19110400, 'steps': 37324, 'loss/train': 1.5076006650924683}
-03/05/2022 09:20:25 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/05/2022 09:20:29 - INFO - codeparrot_training - Step 37325: {'lr': 0.0004329489733282772, 'samples': 19110912, 'steps': 37325, 'loss/train': 1.8476492166519165}
-03/05/2022 09:20:32 - INFO - codeparrot_training - Step 37326: {'lr': 0.0004329453566141737, 'samples': 19111424, 'steps': 37326, 'loss/train': 1.854279637336731}
-03/05/2022 09:20:33 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/05/2022 09:20:38 - INFO - codeparrot_training - Step 37327: {'lr': 0.00043294173981763776, 'samples': 19111936, 'steps': 37327, 'loss/train': 1.4228854179382324}
-03/05/2022 09:20:41 - INFO - codeparrot_training - Step 37328: {'lr': 0.00043293812293867113, 'samples': 19112448, 'steps': 37328, 'loss/train': 1.4969847202301025}
-03/05/2022 09:20:41 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 09:20:46 - INFO - codeparrot_training - Step 37329: {'lr': 0.0004329345059772754, 'samples': 19112960, 'steps': 37329, 'loss/train': 1.905001163482666}
-03/05/2022 09:20:49 - INFO - codeparrot_training - Step 37330: {'lr': 0.0004329308889334522, 'samples': 19113472, 'steps': 37330, 'loss/train': 1.6224944591522217}
-03/05/2022 09:20:50 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 09:20:54 - INFO - codeparrot_training - Step 37331: {'lr': 0.00043292727180720315, 'samples': 19113984, 'steps': 37331, 'loss/train': 1.2870073318481445}
-03/05/2022 09:20:57 - INFO - codeparrot_training - Step 37332: {'lr': 0.0004329236545985299, 'samples': 19114496, 'steps': 37332, 'loss/train': 1.8432685136795044}
-03/05/2022 09:20:58 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/05/2022 09:21:03 - INFO - codeparrot_training - Step 37333: {'lr': 0.000432920037307434, 'samples': 19115008, 'steps': 37333, 'loss/train': 1.5295342206954956}
-03/05/2022 09:21:06 - INFO - codeparrot_training - Step 37334: {'lr': 0.00043291641993391727, 'samples': 19115520, 'steps': 37334, 'loss/train': 1.4443494081497192}
-03/05/2022 09:21:07 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/05/2022 09:21:11 - INFO - codeparrot_training - Step 37335: {'lr': 0.0004329128024779812, 'samples': 19116032, 'steps': 37335, 'loss/train': 1.9981673955917358}
-03/05/2022 09:21:14 - INFO - codeparrot_training - Step 37336: {'lr': 0.0004329091849396274, 'samples': 19116544, 'steps': 37336, 'loss/train': 1.437608003616333}
-03/05/2022 09:21:15 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/05/2022 09:21:20 - INFO - codeparrot_training - Step 37337: {'lr': 0.00043290556731885756, 'samples': 19117056, 'steps': 37337, 'loss/train': 1.7902567386627197}
-03/05/2022 09:21:23 - INFO - codeparrot_training - Step 37338: {'lr': 0.0004329019496156733, 'samples': 19117568, 'steps': 37338, 'loss/train': 1.0266045331954956}
-03/05/2022 09:21:24 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 09:21:28 - INFO - codeparrot_training - Step 37339: {'lr': 0.0004328983318300763, 'samples': 19118080, 'steps': 37339, 'loss/train': 1.2862045764923096}
-03/05/2022 09:21:31 - INFO - codeparrot_training - Step 37340: {'lr': 0.00043289471396206803, 'samples': 19118592, 'steps': 37340, 'loss/train': 1.4169723987579346}
-03/05/2022 09:21:32 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 09:21:37 - INFO - codeparrot_training - Step 37341: {'lr': 0.0004328910960116503, 'samples': 19119104, 'steps': 37341, 'loss/train': 1.9036922454833984}
-03/05/2022 09:21:40 - INFO - codeparrot_training - Step 37342: {'lr': 0.00043288747797882467, 'samples': 19119616, 'steps': 37342, 'loss/train': 1.794769525527954}
-03/05/2022 09:21:40 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/05/2022 09:21:45 - INFO - codeparrot_training - Step 37343: {'lr': 0.00043288385986359266, 'samples': 19120128, 'steps': 37343, 'loss/train': 1.5126090049743652}
-03/05/2022 09:21:48 - INFO - codeparrot_training - Step 37344: {'lr': 0.00043288024166595614, 'samples': 19120640, 'steps': 37344, 'loss/train': 1.6213328838348389}
-03/05/2022 09:21:49 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/05/2022 09:21:53 - INFO - codeparrot_training - Step 37345: {'lr': 0.00043287662338591657, 'samples': 19121152, 'steps': 37345, 'loss/train': 0.5524718761444092}
-03/05/2022 09:21:57 - INFO - codeparrot_training - Step 37346: {'lr': 0.0004328730050234756, 'samples': 19121664, 'steps': 37346, 'loss/train': 1.0178579092025757}
-03/05/2022 09:21:57 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 09:22:02 - INFO - codeparrot_training - Step 37347: {'lr': 0.00043286938657863483, 'samples': 19122176, 'steps': 37347, 'loss/train': 1.230108380317688}
-03/05/2022 09:22:05 - INFO - codeparrot_training - Step 37348: {'lr': 0.00043286576805139597, 'samples': 19122688, 'steps': 37348, 'loss/train': 2.077693462371826}
-03/05/2022 09:22:05 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/05/2022 09:22:11 - INFO - codeparrot_training - Step 37349: {'lr': 0.0004328621494417606, 'samples': 19123200, 'steps': 37349, 'loss/train': 1.875444769859314}
-03/05/2022 09:22:14 - INFO - codeparrot_training - Step 37350: {'lr': 0.0004328585307497304, 'samples': 19123712, 'steps': 37350, 'loss/train': 2.4255075454711914}
-03/05/2022 09:22:17 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 09:22:19 - INFO - codeparrot_training - Step 37351: {'lr': 0.00043285491197530694, 'samples': 19124224, 'steps': 37351, 'loss/train': 1.4060009717941284}
-03/05/2022 09:22:22 - INFO - codeparrot_training - Step 37352: {'lr': 0.00043285129311849193, 'samples': 19124736, 'steps': 37352, 'loss/train': 1.169861912727356}
-03/05/2022 09:22:25 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/05/2022 09:22:28 - INFO - codeparrot_training - Step 37353: {'lr': 0.0004328476741792869, 'samples': 19125248, 'steps': 37353, 'loss/train': 1.882831335067749}
-03/05/2022 09:22:31 - INFO - codeparrot_training - Step 37354: {'lr': 0.00043284405515769356, 'samples': 19125760, 'steps': 37354, 'loss/train': 0.7923739552497864}
-03/05/2022 09:22:33 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/05/2022 09:22:36 - INFO - codeparrot_training - Step 37355: {'lr': 0.00043284043605371346, 'samples': 19126272, 'steps': 37355, 'loss/train': 0.6531121134757996}
-03/05/2022 09:22:39 - INFO - codeparrot_training - Step 37356: {'lr': 0.0004328368168673483, 'samples': 19126784, 'steps': 37356, 'loss/train': 2.312175750732422}
-03/05/2022 09:22:43 - INFO - codeparrot_training - Step 37357: {'lr': 0.00043283319759859974, 'samples': 19127296, 'steps': 37357, 'loss/train': 0.9761717915534973}
-03/05/2022 09:22:43 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/05/2022 09:22:48 - INFO - codeparrot_training - Step 37358: {'lr': 0.0004328295782474693, 'samples': 19127808, 'steps': 37358, 'loss/train': 1.2190566062927246}
-03/05/2022 09:22:51 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/05/2022 09:22:53 - INFO - codeparrot_training - Step 37359: {'lr': 0.0004328259588139587, 'samples': 19128320, 'steps': 37359, 'loss/train': 1.9386810064315796}
-03/05/2022 09:22:56 - INFO - codeparrot_training - Step 37360: {'lr': 0.0004328223392980696, 'samples': 19128832, 'steps': 37360, 'loss/train': 1.3403894901275635}
-03/05/2022 09:22:59 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/05/2022 09:23:02 - INFO - codeparrot_training - Step 37361: {'lr': 0.00043281871969980346, 'samples': 19129344, 'steps': 37361, 'loss/train': 1.8786331415176392}
-03/05/2022 09:23:05 - INFO - codeparrot_training - Step 37362: {'lr': 0.00043281510001916214, 'samples': 19129856, 'steps': 37362, 'loss/train': 2.19429874420166}
-03/05/2022 09:23:08 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/05/2022 09:23:10 - INFO - codeparrot_training - Step 37363: {'lr': 0.0004328114802561471, 'samples': 19130368, 'steps': 37363, 'loss/train': 1.758787751197815}
-03/05/2022 09:23:13 - INFO - codeparrot_training - Step 37364: {'lr': 0.00043280786041076006, 'samples': 19130880, 'steps': 37364, 'loss/train': 0.8903200626373291}
-03/05/2022 09:23:16 - INFO - codeparrot_training - Step 37365: {'lr': 0.0004328042404830026, 'samples': 19131392, 'steps': 37365, 'loss/train': 1.2765926122665405}
-03/05/2022 09:23:16 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/05/2022 09:23:22 - INFO - codeparrot_training - Step 37366: {'lr': 0.0004328006204728763, 'samples': 19131904, 'steps': 37366, 'loss/train': 1.6903386116027832}
-03/05/2022 09:23:25 - INFO - codeparrot_training - Step 37367: {'lr': 0.00043279700038038296, 'samples': 19132416, 'steps': 37367, 'loss/train': 1.1962471008300781}
-03/05/2022 09:23:25 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/05/2022 09:23:31 - INFO - codeparrot_training - Step 37368: {'lr': 0.0004327933802055241, 'samples': 19132928, 'steps': 37368, 'loss/train': 1.5294065475463867}
-03/05/2022 09:23:34 - INFO - codeparrot_training - Step 37369: {'lr': 0.0004327897599483013, 'samples': 19133440, 'steps': 37369, 'loss/train': 1.8739827871322632}
-03/05/2022 09:23:35 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/05/2022 09:23:39 - INFO - codeparrot_training - Step 37370: {'lr': 0.00043278613960871624, 'samples': 19133952, 'steps': 37370, 'loss/train': 1.888419508934021}
-03/05/2022 09:23:42 - INFO - codeparrot_training - Step 37371: {'lr': 0.00043278251918677066, 'samples': 19134464, 'steps': 37371, 'loss/train': 2.161224842071533}
-03/05/2022 09:23:44 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/05/2022 09:23:47 - INFO - codeparrot_training - Step 37372: {'lr': 0.00043277889868246605, 'samples': 19134976, 'steps': 37372, 'loss/train': 1.6573903560638428}
-03/05/2022 09:23:51 - INFO - codeparrot_training - Step 37373: {'lr': 0.0004327752780958041, 'samples': 19135488, 'steps': 37373, 'loss/train': 2.260578155517578}
-03/05/2022 09:23:52 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/05/2022 09:23:56 - INFO - codeparrot_training - Step 37374: {'lr': 0.0004327716574267864, 'samples': 19136000, 'steps': 37374, 'loss/train': 2.3852336406707764}
-03/05/2022 09:23:59 - INFO - codeparrot_training - Step 37375: {'lr': 0.00043276803667541465, 'samples': 19136512, 'steps': 37375, 'loss/train': 1.8652197122573853}
-03/05/2022 09:24:00 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/05/2022 09:24:04 - INFO - codeparrot_training - Step 37376: {'lr': 0.0004327644158416905, 'samples': 19137024, 'steps': 37376, 'loss/train': 2.2459471225738525}
-03/05/2022 09:24:07 - INFO - codeparrot_training - Step 37377: {'lr': 0.0004327607949256154, 'samples': 19137536, 'steps': 37377, 'loss/train': 0.8888918161392212}
-03/05/2022 09:24:09 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/05/2022 09:24:13 - INFO - codeparrot_training - Step 37378: {'lr': 0.00043275717392719115, 'samples': 19138048, 'steps': 37378, 'loss/train': 1.9757126569747925}
-03/05/2022 09:24:16 - INFO - codeparrot_training - Step 37379: {'lr': 0.0004327535528464194, 'samples': 19138560, 'steps': 37379, 'loss/train': 1.7740944623947144}
-03/05/2022 09:24:16 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/05/2022 09:24:22 - INFO - codeparrot_training - Step 37380: {'lr': 0.0004327499316833016, 'samples': 19139072, 'steps': 37380, 'loss/train': 2.1439859867095947}
-03/05/2022 09:24:25 - INFO - codeparrot_training - Step 37381: {'lr': 0.0004327463104378395, 'samples': 19139584, 'steps': 37381, 'loss/train': 1.8235187530517578}
-03/05/2022 09:24:28 - INFO - codeparrot_training - Step 37382: {'lr': 0.0004327426891100349, 'samples': 19140096, 'steps': 37382, 'loss/train': 2.2670650482177734}
-03/05/2022 09:24:28 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/05/2022 09:24:33 - INFO - codeparrot_training - Step 37383: {'lr': 0.0004327390676998891, 'samples': 19140608, 'steps': 37383, 'loss/train': 2.193467617034912}
-03/05/2022 09:24:37 - INFO - codeparrot_training - Step 37384: {'lr': 0.000432735446207404, 'samples': 19141120, 'steps': 37384, 'loss/train': 1.4015774726867676}
-03/05/2022 09:24:37 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/05/2022 09:24:42 - INFO - codeparrot_training - Step 37385: {'lr': 0.0004327318246325811, 'samples': 19141632, 'steps': 37385, 'loss/train': 1.4087187051773071}
-03/05/2022 09:24:45 - INFO - codeparrot_training - Step 37386: {'lr': 0.000432728202975422, 'samples': 19142144, 'steps': 37386, 'loss/train': 0.49444064497947693}
-03/05/2022 09:24:45 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 09:24:50 - INFO - codeparrot_training - Step 37387: {'lr': 0.0004327245812359285, 'samples': 19142656, 'steps': 37387, 'loss/train': 2.367577075958252}
-03/05/2022 09:24:53 - INFO - codeparrot_training - Step 37388: {'lr': 0.000432720959414102, 'samples': 19143168, 'steps': 37388, 'loss/train': 1.1622065305709839}
-03/05/2022 09:24:54 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/05/2022 09:24:59 - INFO - codeparrot_training - Step 37389: {'lr': 0.00043271733750994436, 'samples': 19143680, 'steps': 37389, 'loss/train': 1.7819451093673706}
-03/05/2022 09:25:02 - INFO - codeparrot_training - Step 37390: {'lr': 0.00043271371552345704, 'samples': 19144192, 'steps': 37390, 'loss/train': 2.125990867614746}
-03/05/2022 09:25:02 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/05/2022 09:25:07 - INFO - codeparrot_training - Step 37391: {'lr': 0.00043271009345464175, 'samples': 19144704, 'steps': 37391, 'loss/train': 0.4303770065307617}
-03/05/2022 09:25:10 - INFO - codeparrot_training - Step 37392: {'lr': 0.0004327064713035002, 'samples': 19145216, 'steps': 37392, 'loss/train': 0.6421830654144287}
-03/05/2022 09:25:11 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/05/2022 09:25:15 - INFO - codeparrot_training - Step 37393: {'lr': 0.00043270284907003377, 'samples': 19145728, 'steps': 37393, 'loss/train': 1.5644527673721313}
-03/05/2022 09:25:19 - INFO - codeparrot_training - Step 37394: {'lr': 0.0004326992267542443, 'samples': 19146240, 'steps': 37394, 'loss/train': 1.5239957571029663}
-03/05/2022 09:25:19 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/05/2022 09:25:24 - INFO - codeparrot_training - Step 37395: {'lr': 0.0004326956043561335, 'samples': 19146752, 'steps': 37395, 'loss/train': 1.8742051124572754}
-03/05/2022 09:25:27 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/05/2022 09:25:29 - INFO - codeparrot_training - Step 37396: {'lr': 0.0004326919818757028, 'samples': 19147264, 'steps': 37396, 'loss/train': 1.6692909002304077}
-03/05/2022 09:25:32 - INFO - codeparrot_training - Step 37397: {'lr': 0.00043268835931295393, 'samples': 19147776, 'steps': 37397, 'loss/train': 2.424363374710083}
-03/05/2022 09:25:36 - INFO - codeparrot_training - Step 37398: {'lr': 0.00043268473666788844, 'samples': 19148288, 'steps': 37398, 'loss/train': 1.2113555669784546}
-03/05/2022 09:25:36 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/05/2022 09:25:41 - INFO - codeparrot_training - Step 37399: {'lr': 0.0004326811139405081, 'samples': 19148800, 'steps': 37399, 'loss/train': 1.6166456937789917}
-03/05/2022 09:25:44 - INFO - codeparrot_training - Step 37400: {'lr': 0.0004326774911308145, 'samples': 19149312, 'steps': 37400, 'loss/train': 1.489588975906372}
-03/05/2022 09:25:44 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/05/2022 09:25:49 - INFO - codeparrot_training - Step 37401: {'lr': 0.00043267386823880904, 'samples': 19149824, 'steps': 37401, 'loss/train': 1.8628411293029785}
-03/05/2022 09:25:52 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/05/2022 09:25:55 - INFO - codeparrot_training - Step 37402: {'lr': 0.00043267024526449374, 'samples': 19150336, 'steps': 37402, 'loss/train': 1.6013396978378296}
-03/05/2022 09:25:58 - INFO - codeparrot_training - Step 37403: {'lr': 0.00043266662220787003, 'samples': 19150848, 'steps': 37403, 'loss/train': 1.6813979148864746}
-03/05/2022 09:26:01 - INFO - codeparrot_training - Step 37404: {'lr': 0.0004326629990689395, 'samples': 19151360, 'steps': 37404, 'loss/train': 1.1357797384262085}
-03/05/2022 09:26:01 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 09:26:06 - INFO - codeparrot_training - Step 37405: {'lr': 0.0004326593758477039, 'samples': 19151872, 'steps': 37405, 'loss/train': 2.0731494426727295}
-03/05/2022 09:26:09 - INFO - codeparrot_training - Step 37406: {'lr': 0.0004326557525441648, 'samples': 19152384, 'steps': 37406, 'loss/train': 1.6206623315811157}
-03/05/2022 09:26:09 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/05/2022 09:26:15 - INFO - codeparrot_training - Step 37407: {'lr': 0.00043265212915832374, 'samples': 19152896, 'steps': 37407, 'loss/train': 0.9375823736190796}
-03/05/2022 09:26:18 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/05/2022 09:26:20 - INFO - codeparrot_training - Step 37408: {'lr': 0.00043264850569018254, 'samples': 19153408, 'steps': 37408, 'loss/train': 1.8092085123062134}
-03/05/2022 09:26:23 - INFO - codeparrot_training - Step 37409: {'lr': 0.00043264488213974275, 'samples': 19153920, 'steps': 37409, 'loss/train': 1.822318434715271}
-03/05/2022 09:26:26 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/05/2022 09:26:28 - INFO - codeparrot_training - Step 37410: {'lr': 0.000432641258507006, 'samples': 19154432, 'steps': 37410, 'loss/train': 2.377807855606079}
-03/05/2022 09:26:32 - INFO - codeparrot_training - Step 37411: {'lr': 0.0004326376347919738, 'samples': 19154944, 'steps': 37411, 'loss/train': 1.078521728515625}
-03/05/2022 09:26:34 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/05/2022 09:26:37 - INFO - codeparrot_training - Step 37412: {'lr': 0.00043263401099464805, 'samples': 19155456, 'steps': 37412, 'loss/train': 1.5230066776275635}
-03/05/2022 09:26:40 - INFO - codeparrot_training - Step 37413: {'lr': 0.00043263038711503017, 'samples': 19155968, 'steps': 37413, 'loss/train': 1.4974355697631836}
-03/05/2022 09:26:43 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/05/2022 09:26:45 - INFO - codeparrot_training - Step 37414: {'lr': 0.00043262676315312183, 'samples': 19156480, 'steps': 37414, 'loss/train': 1.9302799701690674}
-03/05/2022 09:26:49 - INFO - codeparrot_training - Step 37415: {'lr': 0.0004326231391089247, 'samples': 19156992, 'steps': 37415, 'loss/train': 0.581866979598999}
-03/05/2022 09:26:52 - INFO - codeparrot_training - Step 37416: {'lr': 0.00043261951498244045, 'samples': 19157504, 'steps': 37416, 'loss/train': 2.203850030899048}
-03/05/2022 09:26:52 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/05/2022 09:26:57 - INFO - codeparrot_training - Step 37417: {'lr': 0.0004326158907736706, 'samples': 19158016, 'steps': 37417, 'loss/train': 1.3513565063476562}
-03/05/2022 09:27:00 - INFO - codeparrot_training - Step 37418: {'lr': 0.00043261226648261687, 'samples': 19158528, 'steps': 37418, 'loss/train': 1.1556529998779297}
-03/05/2022 09:27:01 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/05/2022 09:27:06 - INFO - codeparrot_training - Step 37419: {'lr': 0.0004326086421092809, 'samples': 19159040, 'steps': 37419, 'loss/train': 2.027801513671875}
-03/05/2022 09:27:09 - INFO - codeparrot_training - Step 37420: {'lr': 0.00043260501765366425, 'samples': 19159552, 'steps': 37420, 'loss/train': 1.628307819366455}
-03/05/2022 09:27:09 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/05/2022 09:27:14 - INFO - codeparrot_training - Step 37421: {'lr': 0.00043260139311576863, 'samples': 19160064, 'steps': 37421, 'loss/train': 1.086280345916748}
-03/05/2022 09:27:17 - INFO - codeparrot_training - Step 37422: {'lr': 0.0004325977684955956, 'samples': 19160576, 'steps': 37422, 'loss/train': 2.0649948120117188}
-03/05/2022 09:27:17 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/05/2022 09:27:22 - INFO - codeparrot_training - Step 37423: {'lr': 0.0004325941437931469, 'samples': 19161088, 'steps': 37423, 'loss/train': 1.108130693435669}
-03/05/2022 09:27:25 - INFO - codeparrot_training - Step 37424: {'lr': 0.0004325905190084241, 'samples': 19161600, 'steps': 37424, 'loss/train': 1.203427791595459}
-03/05/2022 09:27:26 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/05/2022 09:27:31 - INFO - codeparrot_training - Step 37425: {'lr': 0.00043258689414142875, 'samples': 19162112, 'steps': 37425, 'loss/train': 2.662029504776001}
-03/05/2022 09:27:34 - INFO - codeparrot_training - Step 37426: {'lr': 0.0004325832691921626, 'samples': 19162624, 'steps': 37426, 'loss/train': 3.108893632888794}
-03/05/2022 09:27:34 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/05/2022 09:27:39 - INFO - codeparrot_training - Step 37427: {'lr': 0.00043257964416062723, 'samples': 19163136, 'steps': 37427, 'loss/train': 3.2600698471069336}
-03/05/2022 09:27:43 - INFO - codeparrot_training - Step 37428: {'lr': 0.0004325760190468243, 'samples': 19163648, 'steps': 37428, 'loss/train': 2.409083843231201}
-03/05/2022 09:27:43 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/05/2022 09:27:48 - INFO - codeparrot_training - Step 37429: {'lr': 0.0004325723938507555, 'samples': 19164160, 'steps': 37429, 'loss/train': 1.5136232376098633}
-03/05/2022 09:27:51 - INFO - codeparrot_training - Step 37430: {'lr': 0.0004325687685724223, 'samples': 19164672, 'steps': 37430, 'loss/train': 1.3081026077270508}
-03/05/2022 09:27:51 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/05/2022 09:27:57 - INFO - codeparrot_training - Step 37431: {'lr': 0.0004325651432118265, 'samples': 19165184, 'steps': 37431, 'loss/train': 1.9557230472564697}
-03/05/2022 09:28:00 - INFO - codeparrot_training - Step 37432: {'lr': 0.00043256151776896955, 'samples': 19165696, 'steps': 37432, 'loss/train': 1.540717601776123}
-03/05/2022 09:28:00 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/05/2022 09:28:05 - INFO - codeparrot_training - Step 37433: {'lr': 0.0004325578922438533, 'samples': 19166208, 'steps': 37433, 'loss/train': 2.069904327392578}
-03/05/2022 09:28:08 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/05/2022 09:28:10 - INFO - codeparrot_training - Step 37434: {'lr': 0.0004325542666364793, 'samples': 19166720, 'steps': 37434, 'loss/train': 1.5535534620285034}
-03/05/2022 09:28:14 - INFO - codeparrot_training - Step 37435: {'lr': 0.00043255064094684917, 'samples': 19167232, 'steps': 37435, 'loss/train': 0.9031588435173035}
-03/05/2022 09:28:16 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/05/2022 09:28:19 - INFO - codeparrot_training - Step 37436: {'lr': 0.0004325470151749644, 'samples': 19167744, 'steps': 37436, 'loss/train': 1.0802795886993408}
-03/05/2022 09:28:22 - INFO - codeparrot_training - Step 37437: {'lr': 0.00043254338932082696, 'samples': 19168256, 'steps': 37437, 'loss/train': 0.5024791955947876}
-03/05/2022 09:28:24 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/05/2022 09:28:27 - INFO - codeparrot_training - Step 37438: {'lr': 0.00043253976338443814, 'samples': 19168768, 'steps': 37438, 'loss/train': 1.8215317726135254}
-03/05/2022 09:28:30 - INFO - codeparrot_training - Step 37439: {'lr': 0.00043253613736579975, 'samples': 19169280, 'steps': 37439, 'loss/train': 1.8153842687606812}
-03/05/2022 09:28:33 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/05/2022 09:28:36 - INFO - codeparrot_training - Step 37440: {'lr': 0.0004325325112649134, 'samples': 19169792, 'steps': 37440, 'loss/train': 1.5196151733398438}
-03/05/2022 09:28:39 - INFO - codeparrot_training - Step 37441: {'lr': 0.00043252888508178066, 'samples': 19170304, 'steps': 37441, 'loss/train': 1.6854519844055176}
-03/05/2022 09:28:41 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/05/2022 09:28:44 - INFO - codeparrot_training - Step 37442: {'lr': 0.0004325252588164033, 'samples': 19170816, 'steps': 37442, 'loss/train': 1.7017935514450073}
-03/05/2022 09:28:47 - INFO - codeparrot_training - Step 37443: {'lr': 0.00043252163246878286, 'samples': 19171328, 'steps': 37443, 'loss/train': 1.8897960186004639}
-03/05/2022 09:28:50 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/05/2022 09:28:53 - INFO - codeparrot_training - Step 37444: {'lr': 0.000432518006038921, 'samples': 19171840, 'steps': 37444, 'loss/train': 1.2633941173553467}
-03/05/2022 09:28:56 - INFO - codeparrot_training - Step 37445: {'lr': 0.00043251437952681926, 'samples': 19172352, 'steps': 37445, 'loss/train': 2.384800910949707}
-03/05/2022 09:28:58 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/05/2022 09:29:01 - INFO - codeparrot_training - Step 37446: {'lr': 0.0004325107529324795, 'samples': 19172864, 'steps': 37446, 'loss/train': 1.2917897701263428}
-03/05/2022 09:29:04 - INFO - codeparrot_training - Step 37447: {'lr': 0.0004325071262559031, 'samples': 19173376, 'steps': 37447, 'loss/train': 1.393094539642334}
-03/05/2022 09:29:06 - INFO - codeparrot_training - Skipping example with length 585 (seq_length=1024)
-03/05/2022 09:29:10 - INFO - codeparrot_training - Step 37448: {'lr': 0.00043250349949709184, 'samples': 19173888, 'steps': 37448, 'loss/train': 0.7384893298149109}
-03/05/2022 09:29:13 - INFO - codeparrot_training - Step 37449: {'lr': 0.0004324998726560473, 'samples': 19174400, 'steps': 37449, 'loss/train': 1.1492565870285034}
-03/05/2022 09:29:15 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 09:29:18 - INFO - codeparrot_training - Step 37450: {'lr': 0.0004324962457327712, 'samples': 19174912, 'steps': 37450, 'loss/train': 2.8066797256469727}
-03/05/2022 09:29:21 - INFO - codeparrot_training - Step 37451: {'lr': 0.00043249261872726504, 'samples': 19175424, 'steps': 37451, 'loss/train': 2.434494972229004}
-03/05/2022 09:29:24 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/05/2022 09:29:26 - INFO - codeparrot_training - Step 37452: {'lr': 0.0004324889916395305, 'samples': 19175936, 'steps': 37452, 'loss/train': 1.1735317707061768}
-03/05/2022 09:29:30 - INFO - codeparrot_training - Step 37453: {'lr': 0.0004324853644695693, 'samples': 19176448, 'steps': 37453, 'loss/train': 1.2539751529693604}
-03/05/2022 09:29:32 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 09:29:35 - INFO - codeparrot_training - Step 37454: {'lr': 0.000432481737217383, 'samples': 19176960, 'steps': 37454, 'loss/train': 2.0843911170959473}
-03/05/2022 09:29:38 - INFO - codeparrot_training - Step 37455: {'lr': 0.0004324781098829732, 'samples': 19177472, 'steps': 37455, 'loss/train': 1.8575918674468994}
-03/05/2022 09:29:40 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/05/2022 09:29:44 - INFO - codeparrot_training - Step 37456: {'lr': 0.0004324744824663417, 'samples': 19177984, 'steps': 37456, 'loss/train': 1.7395952939987183}
-03/05/2022 09:29:47 - INFO - codeparrot_training - Step 37457: {'lr': 0.00043247085496748983, 'samples': 19178496, 'steps': 37457, 'loss/train': 2.257606267929077}
-03/05/2022 09:29:49 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/05/2022 09:29:52 - INFO - codeparrot_training - Step 37458: {'lr': 0.0004324672273864195, 'samples': 19179008, 'steps': 37458, 'loss/train': 1.938042163848877}
-03/05/2022 09:29:55 - INFO - codeparrot_training - Step 37459: {'lr': 0.00043246359972313233, 'samples': 19179520, 'steps': 37459, 'loss/train': 1.6560139656066895}
-03/05/2022 09:29:58 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/05/2022 09:30:01 - INFO - codeparrot_training - Step 37460: {'lr': 0.0004324599719776298, 'samples': 19180032, 'steps': 37460, 'loss/train': 1.7937334775924683}
-03/05/2022 09:30:04 - INFO - codeparrot_training - Step 37461: {'lr': 0.00043245634414991365, 'samples': 19180544, 'steps': 37461, 'loss/train': 1.9208468198776245}
-03/05/2022 09:30:06 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 09:30:09 - INFO - codeparrot_training - Step 37462: {'lr': 0.0004324527162399854, 'samples': 19181056, 'steps': 37462, 'loss/train': 1.4209200143814087}
-03/05/2022 09:30:12 - INFO - codeparrot_training - Step 37463: {'lr': 0.0004324490882478469, 'samples': 19181568, 'steps': 37463, 'loss/train': 1.706996202468872}
-03/05/2022 09:30:14 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/05/2022 09:30:17 - INFO - codeparrot_training - Step 37464: {'lr': 0.0004324454601734995, 'samples': 19182080, 'steps': 37464, 'loss/train': 1.937192440032959}
-03/05/2022 09:30:21 - INFO - codeparrot_training - Step 37465: {'lr': 0.0004324418320169451, 'samples': 19182592, 'steps': 37465, 'loss/train': 1.8528603315353394}
-03/05/2022 09:30:23 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/05/2022 09:30:26 - INFO - codeparrot_training - Step 37466: {'lr': 0.00043243820377818524, 'samples': 19183104, 'steps': 37466, 'loss/train': 1.6546454429626465}
-03/05/2022 09:30:29 - INFO - codeparrot_training - Step 37467: {'lr': 0.0004324345754572215, 'samples': 19183616, 'steps': 37467, 'loss/train': 1.8930600881576538}
-03/05/2022 09:30:31 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/05/2022 09:30:34 - INFO - codeparrot_training - Step 37468: {'lr': 0.00043243094705405554, 'samples': 19184128, 'steps': 37468, 'loss/train': 1.9466514587402344}
-03/05/2022 09:30:37 - INFO - codeparrot_training - Step 37469: {'lr': 0.0004324273185686891, 'samples': 19184640, 'steps': 37469, 'loss/train': 1.7030160427093506}
-03/05/2022 09:30:40 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 09:30:43 - INFO - codeparrot_training - Step 37470: {'lr': 0.00043242369000112365, 'samples': 19185152, 'steps': 37470, 'loss/train': 1.3260201215744019}
-03/05/2022 09:30:46 - INFO - codeparrot_training - Step 37471: {'lr': 0.00043242006135136093, 'samples': 19185664, 'steps': 37471, 'loss/train': 1.7834943532943726}
-03/05/2022 09:30:48 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/05/2022 09:30:51 - INFO - codeparrot_training - Step 37472: {'lr': 0.00043241643261940246, 'samples': 19186176, 'steps': 37472, 'loss/train': 1.5661413669586182}
-03/05/2022 09:30:54 - INFO - codeparrot_training - Step 37473: {'lr': 0.00043241280380525003, 'samples': 19186688, 'steps': 37473, 'loss/train': 1.5868439674377441}
-03/05/2022 09:30:56 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/05/2022 09:31:00 - INFO - codeparrot_training - Step 37474: {'lr': 0.0004324091749089052, 'samples': 19187200, 'steps': 37474, 'loss/train': 2.5541281700134277}
-03/05/2022 09:31:03 - INFO - codeparrot_training - Step 37475: {'lr': 0.0004324055459303696, 'samples': 19187712, 'steps': 37475, 'loss/train': 1.5561670064926147}
-03/05/2022 09:31:05 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 09:31:08 - INFO - codeparrot_training - Step 37476: {'lr': 0.00043240191686964494, 'samples': 19188224, 'steps': 37476, 'loss/train': 1.0318560600280762}
-03/05/2022 09:31:11 - INFO - codeparrot_training - Step 37477: {'lr': 0.00043239828772673276, 'samples': 19188736, 'steps': 37477, 'loss/train': 0.7365391850471497}
-03/05/2022 09:31:13 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/05/2022 09:31:17 - INFO - codeparrot_training - Step 37478: {'lr': 0.0004323946585016347, 'samples': 19189248, 'steps': 37478, 'loss/train': 2.1114883422851562}
-03/05/2022 09:31:20 - INFO - codeparrot_training - Step 37479: {'lr': 0.00043239102919435235, 'samples': 19189760, 'steps': 37479, 'loss/train': 2.0043885707855225}
-03/05/2022 09:31:22 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/05/2022 09:31:26 - INFO - codeparrot_training - Step 37480: {'lr': 0.0004323873998048875, 'samples': 19190272, 'steps': 37480, 'loss/train': 2.0010740756988525}
-03/05/2022 09:31:29 - INFO - codeparrot_training - Step 37481: {'lr': 0.00043238377033324175, 'samples': 19190784, 'steps': 37481, 'loss/train': 0.9142195582389832}
-03/05/2022 09:31:32 - INFO - codeparrot_training - Step 37482: {'lr': 0.00043238014077941656, 'samples': 19191296, 'steps': 37482, 'loss/train': 2.0439987182617188}
-03/05/2022 09:31:33 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 09:31:37 - INFO - codeparrot_training - Step 37483: {'lr': 0.00043237651114341383, 'samples': 19191808, 'steps': 37483, 'loss/train': 2.0177478790283203}
-03/05/2022 09:31:40 - INFO - codeparrot_training - Step 37484: {'lr': 0.00043237288142523503, 'samples': 19192320, 'steps': 37484, 'loss/train': 1.9741607904434204}
-03/05/2022 09:31:42 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/05/2022 09:31:46 - INFO - codeparrot_training - Step 37485: {'lr': 0.00043236925162488173, 'samples': 19192832, 'steps': 37485, 'loss/train': 1.295021653175354}
-03/05/2022 09:31:49 - INFO - codeparrot_training - Step 37486: {'lr': 0.0004323656217423557, 'samples': 19193344, 'steps': 37486, 'loss/train': 1.6139222383499146}
-03/05/2022 09:31:50 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/05/2022 09:31:54 - INFO - codeparrot_training - Step 37487: {'lr': 0.00043236199177765856, 'samples': 19193856, 'steps': 37487, 'loss/train': 1.3925421237945557}
-03/05/2022 09:31:57 - INFO - codeparrot_training - Step 37488: {'lr': 0.0004323583617307919, 'samples': 19194368, 'steps': 37488, 'loss/train': 1.7477308511734009}
-03/05/2022 09:31:59 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/05/2022 09:32:03 - INFO - codeparrot_training - Step 37489: {'lr': 0.00043235473160175745, 'samples': 19194880, 'steps': 37489, 'loss/train': 0.7363441586494446}
-03/05/2022 09:32:06 - INFO - codeparrot_training - Step 37490: {'lr': 0.0004323511013905567, 'samples': 19195392, 'steps': 37490, 'loss/train': 1.5590685606002808}
-03/05/2022 09:32:07 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 09:32:11 - INFO - codeparrot_training - Step 37491: {'lr': 0.0004323474710971913, 'samples': 19195904, 'steps': 37491, 'loss/train': 0.8319467902183533}
-03/05/2022 09:32:14 - INFO - codeparrot_training - Step 37492: {'lr': 0.0004323438407216631, 'samples': 19196416, 'steps': 37492, 'loss/train': 1.8525711297988892}
-03/05/2022 09:32:16 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 09:32:19 - INFO - codeparrot_training - Step 37493: {'lr': 0.0004323402102639734, 'samples': 19196928, 'steps': 37493, 'loss/train': 0.8309668898582458}
-03/05/2022 09:32:23 - INFO - codeparrot_training - Step 37494: {'lr': 0.00043233657972412414, 'samples': 19197440, 'steps': 37494, 'loss/train': 1.7445950508117676}
-03/05/2022 09:32:24 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/05/2022 09:32:28 - INFO - codeparrot_training - Step 37495: {'lr': 0.00043233294910211684, 'samples': 19197952, 'steps': 37495, 'loss/train': 1.6145466566085815}
-03/05/2022 09:32:31 - INFO - codeparrot_training - Step 37496: {'lr': 0.0004323293183979531, 'samples': 19198464, 'steps': 37496, 'loss/train': 2.1352810859680176}
-03/05/2022 09:32:33 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/05/2022 09:32:36 - INFO - codeparrot_training - Step 37497: {'lr': 0.0004323256876116345, 'samples': 19198976, 'steps': 37497, 'loss/train': 1.6139819622039795}
-03/05/2022 09:32:40 - INFO - codeparrot_training - Step 37498: {'lr': 0.0004323220567431628, 'samples': 19199488, 'steps': 37498, 'loss/train': 1.8670103549957275}
-03/05/2022 09:32:41 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 09:32:45 - INFO - codeparrot_training - Step 37499: {'lr': 0.0004323184257925397, 'samples': 19200000, 'steps': 37499, 'loss/train': 2.119373083114624}
-03/05/2022 09:32:48 - INFO - codeparrot_training - Step 37500: {'lr': 0.0004323147947597667, 'samples': 19200512, 'steps': 37500, 'loss/train': 1.26805579662323}
-03/05/2022 09:32:49 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/05/2022 09:32:53 - INFO - codeparrot_training - Step 37501: {'lr': 0.00043231116364484534, 'samples': 19201024, 'steps': 37501, 'loss/train': 1.3774335384368896}
-03/05/2022 09:32:56 - INFO - codeparrot_training - Step 37502: {'lr': 0.00043230753244777743, 'samples': 19201536, 'steps': 37502, 'loss/train': 1.7888596057891846}
-03/05/2022 09:32:58 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/05/2022 09:33:02 - INFO - codeparrot_training - Step 37503: {'lr': 0.00043230390116856467, 'samples': 19202048, 'steps': 37503, 'loss/train': 1.1760632991790771}
-03/05/2022 09:33:05 - INFO - codeparrot_training - Step 37504: {'lr': 0.00043230026980720847, 'samples': 19202560, 'steps': 37504, 'loss/train': 1.0543557405471802}
-03/05/2022 09:33:07 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/05/2022 09:33:10 - INFO - codeparrot_training - Step 37505: {'lr': 0.00043229663836371056, 'samples': 19203072, 'steps': 37505, 'loss/train': 2.2733519077301025}
-03/05/2022 09:33:13 - INFO - codeparrot_training - Step 37506: {'lr': 0.0004322930068380727, 'samples': 19203584, 'steps': 37506, 'loss/train': 1.0625003576278687}
-03/05/2022 09:33:15 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/05/2022 09:33:19 - INFO - codeparrot_training - Step 37507: {'lr': 0.00043228937523029636, 'samples': 19204096, 'steps': 37507, 'loss/train': 2.0091893672943115}
-03/05/2022 09:33:22 - INFO - codeparrot_training - Step 37508: {'lr': 0.00043228574354038326, 'samples': 19204608, 'steps': 37508, 'loss/train': 1.6610870361328125}
-03/05/2022 09:33:23 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 09:33:27 - INFO - codeparrot_training - Step 37509: {'lr': 0.00043228211176833496, 'samples': 19205120, 'steps': 37509, 'loss/train': 2.087128162384033}
-03/05/2022 09:33:30 - INFO - codeparrot_training - Step 37510: {'lr': 0.00043227847991415326, 'samples': 19205632, 'steps': 37510, 'loss/train': 0.7618759870529175}
-03/05/2022 09:33:32 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/05/2022 09:33:36 - INFO - codeparrot_training - Step 37511: {'lr': 0.00043227484797783965, 'samples': 19206144, 'steps': 37511, 'loss/train': 1.8809733390808105}
-03/05/2022 09:33:39 - INFO - codeparrot_training - Step 37512: {'lr': 0.0004322712159593958, 'samples': 19206656, 'steps': 37512, 'loss/train': 1.8175616264343262}
-03/05/2022 09:33:40 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/05/2022 09:33:44 - INFO - codeparrot_training - Step 37513: {'lr': 0.0004322675838588234, 'samples': 19207168, 'steps': 37513, 'loss/train': 1.6241227388381958}
-03/05/2022 09:33:47 - INFO - codeparrot_training - Step 37514: {'lr': 0.0004322639516761239, 'samples': 19207680, 'steps': 37514, 'loss/train': 1.305985927581787}
-03/05/2022 09:33:48 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/05/2022 09:33:53 - INFO - codeparrot_training - Step 37515: {'lr': 0.0004322603194112992, 'samples': 19208192, 'steps': 37515, 'loss/train': 2.0368423461914062}
-03/05/2022 09:33:56 - INFO - codeparrot_training - Step 37516: {'lr': 0.00043225668706435073, 'samples': 19208704, 'steps': 37516, 'loss/train': 1.499269962310791}
-03/05/2022 09:33:57 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 09:34:01 - INFO - codeparrot_training - Step 37517: {'lr': 0.0004322530546352803, 'samples': 19209216, 'steps': 37517, 'loss/train': 1.9702339172363281}
-03/05/2022 09:34:04 - INFO - codeparrot_training - Step 37518: {'lr': 0.0004322494221240894, 'samples': 19209728, 'steps': 37518, 'loss/train': 0.7950683832168579}
-03/05/2022 09:34:05 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/05/2022 09:34:09 - INFO - codeparrot_training - Step 37519: {'lr': 0.0004322457895307797, 'samples': 19210240, 'steps': 37519, 'loss/train': 1.7383122444152832}
-03/05/2022 09:34:13 - INFO - codeparrot_training - Step 37520: {'lr': 0.00043224215685535287, 'samples': 19210752, 'steps': 37520, 'loss/train': 0.86811363697052}
-03/05/2022 09:34:14 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/05/2022 09:34:18 - INFO - codeparrot_training - Step 37521: {'lr': 0.0004322385240978106, 'samples': 19211264, 'steps': 37521, 'loss/train': 1.3301078081130981}
-03/05/2022 09:34:21 - INFO - codeparrot_training - Step 37522: {'lr': 0.0004322348912581544, 'samples': 19211776, 'steps': 37522, 'loss/train': 1.0161796808242798}
-03/05/2022 09:34:25 - INFO - codeparrot_training - Step 37523: {'lr': 0.000432231258336386, 'samples': 19212288, 'steps': 37523, 'loss/train': 0.1943114995956421}
-03/05/2022 09:34:25 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/05/2022 09:34:30 - INFO - codeparrot_training - Step 37524: {'lr': 0.000432227625332507, 'samples': 19212800, 'steps': 37524, 'loss/train': 1.4971718788146973}
-03/05/2022 09:34:33 - INFO - codeparrot_training - Step 37525: {'lr': 0.000432223992246519, 'samples': 19213312, 'steps': 37525, 'loss/train': 1.5043072700500488}
-03/05/2022 09:34:33 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/05/2022 09:34:38 - INFO - codeparrot_training - Step 37526: {'lr': 0.0004322203590784237, 'samples': 19213824, 'steps': 37526, 'loss/train': 2.3293063640594482}
-03/05/2022 09:34:42 - INFO - codeparrot_training - Step 37527: {'lr': 0.0004322167258282228, 'samples': 19214336, 'steps': 37527, 'loss/train': 1.7127904891967773}
-03/05/2022 09:34:47 - INFO - codeparrot_training - Step 37528: {'lr': 0.0004322130924959178, 'samples': 19214848, 'steps': 37528, 'loss/train': 2.4229848384857178}
-03/05/2022 09:34:50 - INFO - codeparrot_training - Step 37529: {'lr': 0.0004322094590815104, 'samples': 19215360, 'steps': 37529, 'loss/train': 1.373903512954712}
-03/05/2022 09:34:50 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/05/2022 09:34:55 - INFO - codeparrot_training - Step 37530: {'lr': 0.00043220582558500223, 'samples': 19215872, 'steps': 37530, 'loss/train': 1.893951177597046}
-03/05/2022 09:34:59 - INFO - codeparrot_training - Step 37531: {'lr': 0.00043220219200639485, 'samples': 19216384, 'steps': 37531, 'loss/train': 1.2898346185684204}
-03/05/2022 09:34:59 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/05/2022 09:35:04 - INFO - codeparrot_training - Step 37532: {'lr': 0.00043219855834569006, 'samples': 19216896, 'steps': 37532, 'loss/train': 2.3175241947174072}
-03/05/2022 09:35:07 - INFO - codeparrot_training - Step 37533: {'lr': 0.00043219492460288937, 'samples': 19217408, 'steps': 37533, 'loss/train': 1.6545515060424805}
-03/05/2022 09:35:07 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/05/2022 09:35:12 - INFO - codeparrot_training - Step 37534: {'lr': 0.00043219129077799447, 'samples': 19217920, 'steps': 37534, 'loss/train': 1.0107697248458862}
-03/05/2022 09:35:16 - INFO - codeparrot_training - Step 37535: {'lr': 0.000432187656871007, 'samples': 19218432, 'steps': 37535, 'loss/train': 1.9901726245880127}
-03/05/2022 09:35:16 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/05/2022 09:35:21 - INFO - codeparrot_training - Step 37536: {'lr': 0.0004321840228819286, 'samples': 19218944, 'steps': 37536, 'loss/train': 1.5239471197128296}
-03/05/2022 09:35:24 - INFO - codeparrot_training - Step 37537: {'lr': 0.0004321803888107608, 'samples': 19219456, 'steps': 37537, 'loss/train': 1.41885507106781}
-03/05/2022 09:35:24 - INFO - codeparrot_training - Skipping example with length 230 (seq_length=1024)
-03/05/2022 09:35:30 - INFO - codeparrot_training - Step 37538: {'lr': 0.0004321767546575054, 'samples': 19219968, 'steps': 37538, 'loss/train': 1.091214895248413}
-03/05/2022 09:35:33 - INFO - codeparrot_training - Step 37539: {'lr': 0.000432173120422164, 'samples': 19220480, 'steps': 37539, 'loss/train': 1.9895609617233276}
-03/05/2022 09:35:33 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/05/2022 09:35:38 - INFO - codeparrot_training - Step 37540: {'lr': 0.00043216948610473816, 'samples': 19220992, 'steps': 37540, 'loss/train': 1.8979796171188354}
-03/05/2022 09:35:41 - INFO - codeparrot_training - Step 37541: {'lr': 0.0004321658517052296, 'samples': 19221504, 'steps': 37541, 'loss/train': 2.4974050521850586}
-03/05/2022 09:35:41 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/05/2022 09:35:46 - INFO - codeparrot_training - Step 37542: {'lr': 0.00043216221722363983, 'samples': 19222016, 'steps': 37542, 'loss/train': 1.7077895402908325}
-03/05/2022 09:35:50 - INFO - codeparrot_training - Step 37543: {'lr': 0.00043215858265997065, 'samples': 19222528, 'steps': 37543, 'loss/train': 2.459596872329712}
-03/05/2022 09:35:50 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 09:35:55 - INFO - codeparrot_training - Step 37544: {'lr': 0.0004321549480142236, 'samples': 19223040, 'steps': 37544, 'loss/train': 1.4157896041870117}
-03/05/2022 09:35:58 - INFO - codeparrot_training - Step 37545: {'lr': 0.0004321513132864003, 'samples': 19223552, 'steps': 37545, 'loss/train': 1.6512104272842407}
-03/05/2022 09:35:58 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/05/2022 09:36:03 - INFO - codeparrot_training - Step 37546: {'lr': 0.0004321476784765025, 'samples': 19224064, 'steps': 37546, 'loss/train': 1.4934146404266357}
-03/05/2022 09:36:07 - INFO - codeparrot_training - Step 37547: {'lr': 0.00043214404358453174, 'samples': 19224576, 'steps': 37547, 'loss/train': 2.1848220825195312}
-03/05/2022 09:36:07 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/05/2022 09:36:12 - INFO - codeparrot_training - Step 37548: {'lr': 0.0004321404086104897, 'samples': 19225088, 'steps': 37548, 'loss/train': 1.0849947929382324}
-03/05/2022 09:36:15 - INFO - codeparrot_training - Step 37549: {'lr': 0.00043213677355437795, 'samples': 19225600, 'steps': 37549, 'loss/train': 1.5723587274551392}
-03/05/2022 09:36:15 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/05/2022 09:36:21 - INFO - codeparrot_training - Step 37550: {'lr': 0.0004321331384161983, 'samples': 19226112, 'steps': 37550, 'loss/train': 1.5870014429092407}
-03/05/2022 09:36:23 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/05/2022 09:36:26 - INFO - codeparrot_training - Step 37551: {'lr': 0.00043212950319595215, 'samples': 19226624, 'steps': 37551, 'loss/train': 1.150944709777832}
-03/05/2022 09:36:29 - INFO - codeparrot_training - Step 37552: {'lr': 0.0004321258678936413, 'samples': 19227136, 'steps': 37552, 'loss/train': 1.9063167572021484}
-03/05/2022 09:36:32 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/05/2022 09:36:34 - INFO - codeparrot_training - Step 37553: {'lr': 0.00043212223250926727, 'samples': 19227648, 'steps': 37553, 'loss/train': 1.9986827373504639}
-03/05/2022 09:36:37 - INFO - codeparrot_training - Step 37554: {'lr': 0.00043211859704283184, 'samples': 19228160, 'steps': 37554, 'loss/train': 1.2354141473770142}
-03/05/2022 09:36:40 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/05/2022 09:36:43 - INFO - codeparrot_training - Step 37555: {'lr': 0.0004321149614943366, 'samples': 19228672, 'steps': 37555, 'loss/train': 2.132129192352295}
-03/05/2022 09:36:46 - INFO - codeparrot_training - Step 37556: {'lr': 0.0004321113258637832, 'samples': 19229184, 'steps': 37556, 'loss/train': 1.7102023363113403}
-03/05/2022 09:36:48 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/05/2022 09:36:51 - INFO - codeparrot_training - Step 37557: {'lr': 0.0004321076901511731, 'samples': 19229696, 'steps': 37557, 'loss/train': 1.96870756149292}
-03/05/2022 09:36:54 - INFO - codeparrot_training - Step 37558: {'lr': 0.0004321040543565082, 'samples': 19230208, 'steps': 37558, 'loss/train': 1.890367031097412}
-03/05/2022 09:36:57 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/05/2022 09:36:59 - INFO - codeparrot_training - Step 37559: {'lr': 0.00043210041847979003, 'samples': 19230720, 'steps': 37559, 'loss/train': 1.7443681955337524}
-03/05/2022 09:37:03 - INFO - codeparrot_training - Step 37560: {'lr': 0.0004320967825210202, 'samples': 19231232, 'steps': 37560, 'loss/train': 1.8006112575531006}
-03/05/2022 09:37:05 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 09:37:08 - INFO - codeparrot_training - Step 37561: {'lr': 0.00043209314648020035, 'samples': 19231744, 'steps': 37561, 'loss/train': 2.002596139907837}
-03/05/2022 09:37:11 - INFO - codeparrot_training - Step 37562: {'lr': 0.0004320895103573321, 'samples': 19232256, 'steps': 37562, 'loss/train': 1.851914882659912}
-03/05/2022 09:37:14 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/05/2022 09:37:16 - INFO - codeparrot_training - Step 37563: {'lr': 0.00043208587415241725, 'samples': 19232768, 'steps': 37563, 'loss/train': 1.6936287879943848}
-03/05/2022 09:37:20 - INFO - codeparrot_training - Step 37564: {'lr': 0.00043208223786545723, 'samples': 19233280, 'steps': 37564, 'loss/train': 1.9661991596221924}
-03/05/2022 09:37:22 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/05/2022 09:37:25 - INFO - codeparrot_training - Step 37565: {'lr': 0.0004320786014964538, 'samples': 19233792, 'steps': 37565, 'loss/train': 1.6039819717407227}
-03/05/2022 09:37:28 - INFO - codeparrot_training - Step 37566: {'lr': 0.0004320749650454085, 'samples': 19234304, 'steps': 37566, 'loss/train': 1.5569870471954346}
-03/05/2022 09:37:31 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/05/2022 09:37:33 - INFO - codeparrot_training - Step 37567: {'lr': 0.0004320713285123231, 'samples': 19234816, 'steps': 37567, 'loss/train': 2.1060752868652344}
-03/05/2022 09:37:37 - INFO - codeparrot_training - Step 37568: {'lr': 0.0004320676918971991, 'samples': 19235328, 'steps': 37568, 'loss/train': 2.1094367504119873}
-03/05/2022 09:37:39 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/05/2022 09:37:42 - INFO - codeparrot_training - Step 37569: {'lr': 0.00043206405520003824, 'samples': 19235840, 'steps': 37569, 'loss/train': 1.2407015562057495}
-03/05/2022 09:37:45 - INFO - codeparrot_training - Step 37570: {'lr': 0.00043206041842084214, 'samples': 19236352, 'steps': 37570, 'loss/train': 1.5935955047607422}
-03/05/2022 09:37:48 - INFO - codeparrot_training - Step 37571: {'lr': 0.00043205678155961244, 'samples': 19236864, 'steps': 37571, 'loss/train': 0.7627046704292297}
-03/05/2022 09:37:48 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 09:37:54 - INFO - codeparrot_training - Step 37572: {'lr': 0.0004320531446163507, 'samples': 19237376, 'steps': 37572, 'loss/train': 1.795957088470459}
-03/05/2022 09:37:57 - INFO - codeparrot_training - Step 37573: {'lr': 0.00043204950759105865, 'samples': 19237888, 'steps': 37573, 'loss/train': 1.1871663331985474}
-03/05/2022 09:37:57 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/05/2022 09:38:02 - INFO - codeparrot_training - Step 37574: {'lr': 0.0004320458704837379, 'samples': 19238400, 'steps': 37574, 'loss/train': 1.407565951347351}
-03/05/2022 09:38:05 - INFO - codeparrot_training - Step 37575: {'lr': 0.00043204223329439015, 'samples': 19238912, 'steps': 37575, 'loss/train': 1.3326168060302734}
-03/05/2022 09:38:05 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/05/2022 09:38:10 - INFO - codeparrot_training - Step 37576: {'lr': 0.00043203859602301695, 'samples': 19239424, 'steps': 37576, 'loss/train': 1.0775507688522339}
-03/05/2022 09:38:14 - INFO - codeparrot_training - Step 37577: {'lr': 0.00043203495866961996, 'samples': 19239936, 'steps': 37577, 'loss/train': 1.785317063331604}
-03/05/2022 09:38:14 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 09:38:19 - INFO - codeparrot_training - Step 37578: {'lr': 0.00043203132123420074, 'samples': 19240448, 'steps': 37578, 'loss/train': 3.5797009468078613}
-03/05/2022 09:38:22 - INFO - codeparrot_training - Step 37579: {'lr': 0.00043202768371676113, 'samples': 19240960, 'steps': 37579, 'loss/train': 2.3938326835632324}
-03/05/2022 09:38:22 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/05/2022 09:38:27 - INFO - codeparrot_training - Step 37580: {'lr': 0.0004320240461173026, 'samples': 19241472, 'steps': 37580, 'loss/train': 2.0764517784118652}
-03/05/2022 09:38:31 - INFO - codeparrot_training - Step 37581: {'lr': 0.00043202040843582685, 'samples': 19241984, 'steps': 37581, 'loss/train': 1.7297992706298828}
-03/05/2022 09:38:31 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/05/2022 09:38:36 - INFO - codeparrot_training - Step 37582: {'lr': 0.00043201677067233554, 'samples': 19242496, 'steps': 37582, 'loss/train': 1.4367398023605347}
-03/05/2022 09:38:39 - INFO - codeparrot_training - Step 37583: {'lr': 0.00043201313282683024, 'samples': 19243008, 'steps': 37583, 'loss/train': 1.9547196626663208}
-03/05/2022 09:38:39 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/05/2022 09:38:44 - INFO - codeparrot_training - Step 37584: {'lr': 0.0004320094948993127, 'samples': 19243520, 'steps': 37584, 'loss/train': 1.7415258884429932}
-03/05/2022 09:38:47 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 09:38:49 - INFO - codeparrot_training - Step 37585: {'lr': 0.00043200585688978445, 'samples': 19244032, 'steps': 37585, 'loss/train': 1.7008999586105347}
-03/05/2022 09:38:53 - INFO - codeparrot_training - Step 37586: {'lr': 0.00043200221879824706, 'samples': 19244544, 'steps': 37586, 'loss/train': 2.7623813152313232}
-03/05/2022 09:38:55 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 09:38:58 - INFO - codeparrot_training - Step 37587: {'lr': 0.0004319985806247024, 'samples': 19245056, 'steps': 37587, 'loss/train': 1.3866840600967407}
-03/05/2022 09:39:01 - INFO - codeparrot_training - Step 37588: {'lr': 0.00043199494236915206, 'samples': 19245568, 'steps': 37588, 'loss/train': 1.6045198440551758}
-03/05/2022 09:39:04 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 09:39:06 - INFO - codeparrot_training - Step 37589: {'lr': 0.0004319913040315975, 'samples': 19246080, 'steps': 37589, 'loss/train': 2.2629575729370117}
-03/05/2022 09:39:10 - INFO - codeparrot_training - Step 37590: {'lr': 0.00043198766561204047, 'samples': 19246592, 'steps': 37590, 'loss/train': 1.629794716835022}
-03/05/2022 09:39:12 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/05/2022 09:39:15 - INFO - codeparrot_training - Step 37591: {'lr': 0.0004319840271104826, 'samples': 19247104, 'steps': 37591, 'loss/train': 1.5631990432739258}
-03/05/2022 09:39:18 - INFO - codeparrot_training - Step 37592: {'lr': 0.0004319803885269256, 'samples': 19247616, 'steps': 37592, 'loss/train': 1.793030858039856}
-03/05/2022 09:39:21 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/05/2022 09:39:23 - INFO - codeparrot_training - Step 37593: {'lr': 0.0004319767498613709, 'samples': 19248128, 'steps': 37593, 'loss/train': 0.9188294410705566}
-03/05/2022 09:39:27 - INFO - codeparrot_training - Step 37594: {'lr': 0.00043197311111382045, 'samples': 19248640, 'steps': 37594, 'loss/train': 1.8722147941589355}
-03/05/2022 09:39:29 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/05/2022 09:39:32 - INFO - codeparrot_training - Step 37595: {'lr': 0.00043196947228427564, 'samples': 19249152, 'steps': 37595, 'loss/train': 0.9693514704704285}
-03/05/2022 09:39:35 - INFO - codeparrot_training - Step 37596: {'lr': 0.0004319658333727382, 'samples': 19249664, 'steps': 37596, 'loss/train': 1.1033308506011963}
-03/05/2022 09:39:37 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/05/2022 09:39:40 - INFO - codeparrot_training - Step 37597: {'lr': 0.0004319621943792098, 'samples': 19250176, 'steps': 37597, 'loss/train': 1.750913381576538}
-03/05/2022 09:39:43 - INFO - codeparrot_training - Step 37598: {'lr': 0.000431958555303692, 'samples': 19250688, 'steps': 37598, 'loss/train': 1.601717472076416}
-03/05/2022 09:39:45 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/05/2022 09:39:49 - INFO - codeparrot_training - Step 37599: {'lr': 0.00043195491614618655, 'samples': 19251200, 'steps': 37599, 'loss/train': 1.671321153640747}
-03/05/2022 09:39:52 - INFO - codeparrot_training - Step 37600: {'lr': 0.00043195127690669486, 'samples': 19251712, 'steps': 37600, 'loss/train': 2.0962648391723633}
-03/05/2022 09:39:54 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/05/2022 09:39:57 - INFO - codeparrot_training - Step 37601: {'lr': 0.00043194763758521896, 'samples': 19252224, 'steps': 37601, 'loss/train': 1.908949375152588}
-03/05/2022 09:40:00 - INFO - codeparrot_training - Step 37602: {'lr': 0.00043194399818176013, 'samples': 19252736, 'steps': 37602, 'loss/train': 2.277860403060913}
-03/05/2022 09:40:02 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/05/2022 09:40:06 - INFO - codeparrot_training - Step 37603: {'lr': 0.00043194035869632017, 'samples': 19253248, 'steps': 37603, 'loss/train': 1.6188175678253174}
-03/05/2022 09:40:09 - INFO - codeparrot_training - Step 37604: {'lr': 0.00043193671912890064, 'samples': 19253760, 'steps': 37604, 'loss/train': 0.15518000721931458}
-03/05/2022 09:40:11 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/05/2022 09:40:14 - INFO - codeparrot_training - Step 37605: {'lr': 0.0004319330794795033, 'samples': 19254272, 'steps': 37605, 'loss/train': 2.093111515045166}
-03/05/2022 09:40:17 - INFO - codeparrot_training - Step 37606: {'lr': 0.0004319294397481297, 'samples': 19254784, 'steps': 37606, 'loss/train': 0.5295997262001038}
-03/05/2022 09:40:19 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/05/2022 09:40:22 - INFO - codeparrot_training - Step 37607: {'lr': 0.0004319257999347815, 'samples': 19255296, 'steps': 37607, 'loss/train': 2.154928207397461}
-03/05/2022 09:40:26 - INFO - codeparrot_training - Step 37608: {'lr': 0.0004319221600394603, 'samples': 19255808, 'steps': 37608, 'loss/train': 1.4473485946655273}
-03/05/2022 09:40:27 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/05/2022 09:40:31 - INFO - codeparrot_training - Step 37609: {'lr': 0.0004319185200621678, 'samples': 19256320, 'steps': 37609, 'loss/train': 1.3819894790649414}
-03/05/2022 09:40:34 - INFO - codeparrot_training - Step 37610: {'lr': 0.0004319148800029057, 'samples': 19256832, 'steps': 37610, 'loss/train': 1.1123124361038208}
-03/05/2022 09:40:36 - INFO - codeparrot_training - Skipping example with length 732 (seq_length=1024)
-03/05/2022 09:40:39 - INFO - codeparrot_training - Step 37611: {'lr': 0.0004319112398616755, 'samples': 19257344, 'steps': 37611, 'loss/train': 2.336869716644287}
-03/05/2022 09:40:43 - INFO - codeparrot_training - Step 37612: {'lr': 0.00043190759963847894, 'samples': 19257856, 'steps': 37612, 'loss/train': 1.7621959447860718}
-03/05/2022 09:40:44 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/05/2022 09:40:48 - INFO - codeparrot_training - Step 37613: {'lr': 0.00043190395933331757, 'samples': 19258368, 'steps': 37613, 'loss/train': 2.209055185317993}
-03/05/2022 09:40:51 - INFO - codeparrot_training - Step 37614: {'lr': 0.00043190031894619306, 'samples': 19258880, 'steps': 37614, 'loss/train': 1.5879660844802856}
-03/05/2022 09:40:53 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/05/2022 09:40:56 - INFO - codeparrot_training - Step 37615: {'lr': 0.0004318966784771071, 'samples': 19259392, 'steps': 37615, 'loss/train': 1.498449444770813}
-03/05/2022 09:40:59 - INFO - codeparrot_training - Step 37616: {'lr': 0.00043189303792606136, 'samples': 19259904, 'steps': 37616, 'loss/train': 2.973716974258423}
-03/05/2022 09:41:02 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/05/2022 09:41:05 - INFO - codeparrot_training - Step 37617: {'lr': 0.0004318893972930574, 'samples': 19260416, 'steps': 37617, 'loss/train': 1.7208435535430908}
-03/05/2022 09:41:08 - INFO - codeparrot_training - Step 37618: {'lr': 0.00043188575657809685, 'samples': 19260928, 'steps': 37618, 'loss/train': 1.855859637260437}
-03/05/2022 09:41:10 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 09:41:13 - INFO - codeparrot_training - Step 37619: {'lr': 0.00043188211578118143, 'samples': 19261440, 'steps': 37619, 'loss/train': 0.889819324016571}
-03/05/2022 09:41:16 - INFO - codeparrot_training - Step 37620: {'lr': 0.0004318784749023127, 'samples': 19261952, 'steps': 37620, 'loss/train': 1.6071275472640991}
-03/05/2022 09:41:19 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/05/2022 09:41:22 - INFO - codeparrot_training - Step 37621: {'lr': 0.0004318748339414923, 'samples': 19262464, 'steps': 37621, 'loss/train': 1.5687029361724854}
-03/05/2022 09:41:25 - INFO - codeparrot_training - Step 37622: {'lr': 0.000431871192898722, 'samples': 19262976, 'steps': 37622, 'loss/train': 1.8093433380126953}
-03/05/2022 09:41:28 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/05/2022 09:41:30 - INFO - codeparrot_training - Step 37623: {'lr': 0.0004318675517740033, 'samples': 19263488, 'steps': 37623, 'loss/train': 0.7689558267593384}
-03/05/2022 09:41:33 - INFO - codeparrot_training - Step 37624: {'lr': 0.0004318639105673379, 'samples': 19264000, 'steps': 37624, 'loss/train': 2.152623414993286}
-03/05/2022 09:41:36 - INFO - codeparrot_training - Skipping example with length 371 (seq_length=1024)
-03/05/2022 09:41:39 - INFO - codeparrot_training - Step 37625: {'lr': 0.00043186026927872736, 'samples': 19264512, 'steps': 37625, 'loss/train': 0.4563499391078949}
-03/05/2022 09:41:42 - INFO - codeparrot_training - Step 37626: {'lr': 0.0004318566279081735, 'samples': 19265024, 'steps': 37626, 'loss/train': 2.188025951385498}
-03/05/2022 09:41:44 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/05/2022 09:41:47 - INFO - codeparrot_training - Step 37627: {'lr': 0.0004318529864556777, 'samples': 19265536, 'steps': 37627, 'loss/train': 0.14094699919223785}
-03/05/2022 09:41:50 - INFO - codeparrot_training - Step 37628: {'lr': 0.0004318493449212419, 'samples': 19266048, 'steps': 37628, 'loss/train': 2.102076768875122}
-03/05/2022 09:41:52 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/05/2022 09:41:56 - INFO - codeparrot_training - Step 37629: {'lr': 0.00043184570330486756, 'samples': 19266560, 'steps': 37629, 'loss/train': 1.6116771697998047}
-03/05/2022 09:41:59 - INFO - codeparrot_training - Step 37630: {'lr': 0.0004318420616065563, 'samples': 19267072, 'steps': 37630, 'loss/train': 2.1827826499938965}
-03/05/2022 09:42:02 - INFO - codeparrot_training - Step 37631: {'lr': 0.0004318384198263099, 'samples': 19267584, 'steps': 37631, 'loss/train': 1.6048632860183716}
-03/05/2022 09:42:03 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 09:42:07 - INFO - codeparrot_training - Step 37632: {'lr': 0.0004318347779641298, 'samples': 19268096, 'steps': 37632, 'loss/train': 2.236224412918091}
-03/05/2022 09:42:11 - INFO - codeparrot_training - Step 37633: {'lr': 0.00043183113602001777, 'samples': 19268608, 'steps': 37633, 'loss/train': 1.839824914932251}
-03/05/2022 09:42:12 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/05/2022 09:42:16 - INFO - codeparrot_training - Step 37634: {'lr': 0.0004318274939939755, 'samples': 19269120, 'steps': 37634, 'loss/train': 1.442491888999939}
-03/05/2022 09:42:19 - INFO - codeparrot_training - Step 37635: {'lr': 0.00043182385188600457, 'samples': 19269632, 'steps': 37635, 'loss/train': 2.23506498336792}
-03/05/2022 09:42:20 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/05/2022 09:42:24 - INFO - codeparrot_training - Step 37636: {'lr': 0.0004318202096961066, 'samples': 19270144, 'steps': 37636, 'loss/train': 1.7184643745422363}
-03/05/2022 09:42:28 - INFO - codeparrot_training - Step 37637: {'lr': 0.0004318165674242832, 'samples': 19270656, 'steps': 37637, 'loss/train': 1.5109783411026}
-03/05/2022 09:42:29 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/05/2022 09:42:33 - INFO - codeparrot_training - Step 37638: {'lr': 0.0004318129250705361, 'samples': 19271168, 'steps': 37638, 'loss/train': 1.7208701372146606}
-03/05/2022 09:42:36 - INFO - codeparrot_training - Step 37639: {'lr': 0.0004318092826348669, 'samples': 19271680, 'steps': 37639, 'loss/train': 2.121558427810669}
-03/05/2022 09:42:37 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 09:42:41 - INFO - codeparrot_training - Step 37640: {'lr': 0.0004318056401172772, 'samples': 19272192, 'steps': 37640, 'loss/train': 2.3769032955169678}
-03/05/2022 09:42:45 - INFO - codeparrot_training - Step 37641: {'lr': 0.0004318019975177688, 'samples': 19272704, 'steps': 37641, 'loss/train': 2.73527193069458}
-03/05/2022 09:42:45 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/05/2022 09:42:50 - INFO - codeparrot_training - Step 37642: {'lr': 0.0004317983548363431, 'samples': 19273216, 'steps': 37642, 'loss/train': 2.0738365650177}
-03/05/2022 09:42:53 - INFO - codeparrot_training - Step 37643: {'lr': 0.0004317947120730019, 'samples': 19273728, 'steps': 37643, 'loss/train': 1.6203736066818237}
-03/05/2022 09:42:54 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/05/2022 09:42:58 - INFO - codeparrot_training - Step 37644: {'lr': 0.0004317910692277469, 'samples': 19274240, 'steps': 37644, 'loss/train': 1.735791802406311}
-03/05/2022 09:43:01 - INFO - codeparrot_training - Step 37645: {'lr': 0.0004317874263005795, 'samples': 19274752, 'steps': 37645, 'loss/train': 1.9624476432800293}
-03/05/2022 09:43:02 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/05/2022 09:43:07 - INFO - codeparrot_training - Step 37646: {'lr': 0.0004317837832915016, 'samples': 19275264, 'steps': 37646, 'loss/train': 2.015181541442871}
-03/05/2022 09:43:10 - INFO - codeparrot_training - Step 37647: {'lr': 0.0004317801402005147, 'samples': 19275776, 'steps': 37647, 'loss/train': 1.9798939228057861}
-03/05/2022 09:43:10 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/05/2022 09:43:15 - INFO - codeparrot_training - Step 37648: {'lr': 0.00043177649702762043, 'samples': 19276288, 'steps': 37648, 'loss/train': 1.3488126993179321}
-03/05/2022 09:43:18 - INFO - codeparrot_training - Step 37649: {'lr': 0.0004317728537728206, 'samples': 19276800, 'steps': 37649, 'loss/train': 1.7996190786361694}
-03/05/2022 09:43:18 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/05/2022 09:43:23 - INFO - codeparrot_training - Step 37650: {'lr': 0.0004317692104361166, 'samples': 19277312, 'steps': 37650, 'loss/train': 2.3607280254364014}
-03/05/2022 09:43:27 - INFO - codeparrot_training - Step 37651: {'lr': 0.0004317655670175102, 'samples': 19277824, 'steps': 37651, 'loss/train': 1.8736376762390137}
-03/05/2022 09:43:27 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/05/2022 09:43:32 - INFO - codeparrot_training - Step 37652: {'lr': 0.0004317619235170032, 'samples': 19278336, 'steps': 37652, 'loss/train': 1.449759602546692}
-03/05/2022 09:43:35 - INFO - codeparrot_training - Step 37653: {'lr': 0.00043175827993459696, 'samples': 19278848, 'steps': 37653, 'loss/train': 2.090639352798462}
-03/05/2022 09:43:35 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/05/2022 09:43:40 - INFO - codeparrot_training - Step 37654: {'lr': 0.0004317546362702932, 'samples': 19279360, 'steps': 37654, 'loss/train': 0.8621086478233337}
-03/05/2022 09:43:43 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/05/2022 09:43:46 - INFO - codeparrot_training - Step 37655: {'lr': 0.0004317509925240937, 'samples': 19279872, 'steps': 37655, 'loss/train': 1.5566388368606567}
-03/05/2022 09:43:49 - INFO - codeparrot_training - Step 37656: {'lr': 0.00043174734869599993, 'samples': 19280384, 'steps': 37656, 'loss/train': 2.6040854454040527}
-03/05/2022 09:43:52 - INFO - codeparrot_training - Step 37657: {'lr': 0.0004317437047860137, 'samples': 19280896, 'steps': 37657, 'loss/train': 1.002683401107788}
-03/05/2022 09:43:52 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/05/2022 09:43:57 - INFO - codeparrot_training - Step 37658: {'lr': 0.0004317400607941364, 'samples': 19281408, 'steps': 37658, 'loss/train': 1.2695149183273315}
-03/05/2022 09:44:00 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/05/2022 09:44:03 - INFO - codeparrot_training - Step 37659: {'lr': 0.00043173641672037, 'samples': 19281920, 'steps': 37659, 'loss/train': 2.4506208896636963}
-03/05/2022 09:44:06 - INFO - codeparrot_training - Step 37660: {'lr': 0.00043173277256471586, 'samples': 19282432, 'steps': 37660, 'loss/train': 1.2594867944717407}
-03/05/2022 09:44:09 - INFO - codeparrot_training - Step 37661: {'lr': 0.0004317291283271758, 'samples': 19282944, 'steps': 37661, 'loss/train': 2.516892194747925}
-03/05/2022 09:44:09 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/05/2022 09:44:15 - INFO - codeparrot_training - Step 37662: {'lr': 0.0004317254840077514, 'samples': 19283456, 'steps': 37662, 'loss/train': 2.185739278793335}
-03/05/2022 09:44:17 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/05/2022 09:44:20 - INFO - codeparrot_training - Step 37663: {'lr': 0.0004317218396064443, 'samples': 19283968, 'steps': 37663, 'loss/train': 2.31020188331604}
-03/05/2022 09:44:23 - INFO - codeparrot_training - Step 37664: {'lr': 0.00043171819512325614, 'samples': 19284480, 'steps': 37664, 'loss/train': 1.3380119800567627}
-03/05/2022 09:44:26 - INFO - codeparrot_training - Step 37665: {'lr': 0.00043171455055818854, 'samples': 19284992, 'steps': 37665, 'loss/train': 0.15655094385147095}
-03/05/2022 09:44:26 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/05/2022 09:44:32 - INFO - codeparrot_training - Step 37666: {'lr': 0.0004317109059112432, 'samples': 19285504, 'steps': 37666, 'loss/train': 1.5209444761276245}
-03/05/2022 09:44:35 - INFO - codeparrot_training - Step 37667: {'lr': 0.00043170726118242164, 'samples': 19286016, 'steps': 37667, 'loss/train': 1.9107359647750854}
-03/05/2022 09:44:35 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/05/2022 09:44:40 - INFO - codeparrot_training - Step 37668: {'lr': 0.0004317036163717257, 'samples': 19286528, 'steps': 37668, 'loss/train': 2.0399527549743652}
-03/05/2022 09:44:43 - INFO - codeparrot_training - Step 37669: {'lr': 0.0004316999714791569, 'samples': 19287040, 'steps': 37669, 'loss/train': 1.8827881813049316}
-03/05/2022 09:44:43 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 09:44:48 - INFO - codeparrot_training - Step 37670: {'lr': 0.0004316963265047169, 'samples': 19287552, 'steps': 37670, 'loss/train': 1.4759833812713623}
-03/05/2022 09:44:51 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/05/2022 09:44:54 - INFO - codeparrot_training - Step 37671: {'lr': 0.00043169268144840726, 'samples': 19288064, 'steps': 37671, 'loss/train': 1.2252402305603027}
-03/05/2022 09:44:57 - INFO - codeparrot_training - Step 37672: {'lr': 0.0004316890363102298, 'samples': 19288576, 'steps': 37672, 'loss/train': 2.0363316535949707}
-03/05/2022 09:45:00 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/05/2022 09:45:02 - INFO - codeparrot_training - Step 37673: {'lr': 0.000431685391090186, 'samples': 19289088, 'steps': 37673, 'loss/train': 2.3227334022521973}
-03/05/2022 09:45:05 - INFO - codeparrot_training - Step 37674: {'lr': 0.00043168174578827755, 'samples': 19289600, 'steps': 37674, 'loss/train': 1.842089056968689}
-03/05/2022 09:45:08 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/05/2022 09:45:11 - INFO - codeparrot_training - Step 37675: {'lr': 0.00043167810040450617, 'samples': 19290112, 'steps': 37675, 'loss/train': 2.183668375015259}
-03/05/2022 09:45:14 - INFO - codeparrot_training - Step 37676: {'lr': 0.00043167445493887347, 'samples': 19290624, 'steps': 37676, 'loss/train': 0.7465007901191711}
-03/05/2022 09:45:17 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/05/2022 09:45:19 - INFO - codeparrot_training - Step 37677: {'lr': 0.000431670809391381, 'samples': 19291136, 'steps': 37677, 'loss/train': 0.5453247427940369}
-03/05/2022 09:45:22 - INFO - codeparrot_training - Step 37678: {'lr': 0.00043166716376203047, 'samples': 19291648, 'steps': 37678, 'loss/train': 2.140970468521118}
-03/05/2022 09:45:25 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/05/2022 09:45:28 - INFO - codeparrot_training - Step 37679: {'lr': 0.0004316635180508235, 'samples': 19292160, 'steps': 37679, 'loss/train': 1.0217266082763672}
-03/05/2022 09:45:31 - INFO - codeparrot_training - Step 37680: {'lr': 0.0004316598722577618, 'samples': 19292672, 'steps': 37680, 'loss/train': 2.5661678314208984}
-03/05/2022 09:45:34 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/05/2022 09:45:36 - INFO - codeparrot_training - Step 37681: {'lr': 0.000431656226382847, 'samples': 19293184, 'steps': 37681, 'loss/train': 1.9702166318893433}
-03/05/2022 09:45:39 - INFO - codeparrot_training - Step 37682: {'lr': 0.00043165258042608055, 'samples': 19293696, 'steps': 37682, 'loss/train': 1.8913568258285522}
-03/05/2022 09:45:42 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/05/2022 09:45:45 - INFO - codeparrot_training - Step 37683: {'lr': 0.0004316489343874644, 'samples': 19294208, 'steps': 37683, 'loss/train': 1.447848916053772}
-03/05/2022 09:45:48 - INFO - codeparrot_training - Step 37684: {'lr': 0.000431645288267, 'samples': 19294720, 'steps': 37684, 'loss/train': 1.0389361381530762}
-03/05/2022 09:45:51 - INFO - codeparrot_training - Step 37685: {'lr': 0.00043164164206468904, 'samples': 19295232, 'steps': 37685, 'loss/train': 1.556795597076416}
-03/05/2022 09:45:51 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/05/2022 09:45:56 - INFO - codeparrot_training - Step 37686: {'lr': 0.00043163799578053313, 'samples': 19295744, 'steps': 37686, 'loss/train': 1.0446492433547974}
-03/05/2022 09:45:59 - INFO - codeparrot_training - Step 37687: {'lr': 0.00043163434941453395, 'samples': 19296256, 'steps': 37687, 'loss/train': 1.7491613626480103}
-03/05/2022 09:46:00 - INFO - codeparrot_training - Skipping example with length 340 (seq_length=1024)
-03/05/2022 09:46:05 - INFO - codeparrot_training - Step 37688: {'lr': 0.00043163070296669317, 'samples': 19296768, 'steps': 37688, 'loss/train': 2.305279016494751}
-03/05/2022 09:46:08 - INFO - codeparrot_training - Step 37689: {'lr': 0.00043162705643701236, 'samples': 19297280, 'steps': 37689, 'loss/train': 0.9249650835990906}
-03/05/2022 09:46:08 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/05/2022 09:46:13 - INFO - codeparrot_training - Step 37690: {'lr': 0.00043162340982549327, 'samples': 19297792, 'steps': 37690, 'loss/train': 1.4148107767105103}
-03/05/2022 09:46:16 - INFO - codeparrot_training - Step 37691: {'lr': 0.00043161976313213735, 'samples': 19298304, 'steps': 37691, 'loss/train': 1.9970656633377075}
-03/05/2022 09:46:16 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/05/2022 09:46:21 - INFO - codeparrot_training - Step 37692: {'lr': 0.0004316161163569465, 'samples': 19298816, 'steps': 37692, 'loss/train': 1.244062066078186}
-03/05/2022 09:46:25 - INFO - codeparrot_training - Step 37693: {'lr': 0.0004316124694999222, 'samples': 19299328, 'steps': 37693, 'loss/train': 2.284325361251831}
-03/05/2022 09:46:25 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 09:46:30 - INFO - codeparrot_training - Step 37694: {'lr': 0.000431608822561066, 'samples': 19299840, 'steps': 37694, 'loss/train': 2.0238091945648193}
-03/05/2022 09:46:33 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/05/2022 09:46:35 - INFO - codeparrot_training - Step 37695: {'lr': 0.0004316051755403798, 'samples': 19300352, 'steps': 37695, 'loss/train': 0.8627633452415466}
-03/05/2022 09:46:38 - INFO - codeparrot_training - Step 37696: {'lr': 0.000431601528437865, 'samples': 19300864, 'steps': 37696, 'loss/train': 1.9638502597808838}
-03/05/2022 09:46:41 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/05/2022 09:46:44 - INFO - codeparrot_training - Step 37697: {'lr': 0.00043159788125352353, 'samples': 19301376, 'steps': 37697, 'loss/train': 1.6519570350646973}
-03/05/2022 09:46:47 - INFO - codeparrot_training - Step 37698: {'lr': 0.0004315942339873567, 'samples': 19301888, 'steps': 37698, 'loss/train': 1.934112310409546}
-03/05/2022 09:46:49 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/05/2022 09:46:52 - INFO - codeparrot_training - Step 37699: {'lr': 0.00043159058663936635, 'samples': 19302400, 'steps': 37699, 'loss/train': 2.563800096511841}
-03/05/2022 09:46:55 - INFO - codeparrot_training - Step 37700: {'lr': 0.0004315869392095542, 'samples': 19302912, 'steps': 37700, 'loss/train': 0.9338539838790894}
-03/05/2022 09:46:58 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/05/2022 09:47:01 - INFO - codeparrot_training - Step 37701: {'lr': 0.0004315832916979216, 'samples': 19303424, 'steps': 37701, 'loss/train': 2.3548097610473633}
-03/05/2022 09:47:04 - INFO - codeparrot_training - Step 37702: {'lr': 0.00043157964410447047, 'samples': 19303936, 'steps': 37702, 'loss/train': 2.1663315296173096}
-03/05/2022 09:47:07 - INFO - codeparrot_training - Step 37703: {'lr': 0.0004315759964292023, 'samples': 19304448, 'steps': 37703, 'loss/train': 1.0427130460739136}
-03/05/2022 09:47:08 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/05/2022 09:47:12 - INFO - codeparrot_training - Step 37704: {'lr': 0.0004315723486721188, 'samples': 19304960, 'steps': 37704, 'loss/train': 2.257753372192383}
-03/05/2022 09:47:15 - INFO - codeparrot_training - Step 37705: {'lr': 0.00043156870083322166, 'samples': 19305472, 'steps': 37705, 'loss/train': 2.2345669269561768}
-03/05/2022 09:47:16 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/05/2022 09:47:21 - INFO - codeparrot_training - Step 37706: {'lr': 0.00043156505291251234, 'samples': 19305984, 'steps': 37706, 'loss/train': 1.7618998289108276}
-03/05/2022 09:47:24 - INFO - codeparrot_training - Step 37707: {'lr': 0.00043156140490999275, 'samples': 19306496, 'steps': 37707, 'loss/train': 1.9862146377563477}
-03/05/2022 09:47:24 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/05/2022 09:47:29 - INFO - codeparrot_training - Step 37708: {'lr': 0.0004315577568256643, 'samples': 19307008, 'steps': 37708, 'loss/train': 1.8448580503463745}
-03/05/2022 09:47:32 - INFO - codeparrot_training - Step 37709: {'lr': 0.0004315541086595288, 'samples': 19307520, 'steps': 37709, 'loss/train': 1.2533881664276123}
-03/05/2022 09:47:33 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/05/2022 09:47:38 - INFO - codeparrot_training - Step 37710: {'lr': 0.00043155046041158776, 'samples': 19308032, 'steps': 37710, 'loss/train': 1.3395535945892334}
-03/05/2022 09:47:41 - INFO - codeparrot_training - Step 37711: {'lr': 0.0004315468120818429, 'samples': 19308544, 'steps': 37711, 'loss/train': 2.15299129486084}
-03/05/2022 09:47:41 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/05/2022 09:47:46 - INFO - codeparrot_training - Step 37712: {'lr': 0.0004315431636702959, 'samples': 19309056, 'steps': 37712, 'loss/train': 1.5401694774627686}
-03/05/2022 09:47:49 - INFO - codeparrot_training - Step 37713: {'lr': 0.00043153951517694824, 'samples': 19309568, 'steps': 37713, 'loss/train': 1.1506346464157104}
-03/05/2022 09:47:50 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/05/2022 09:47:55 - INFO - codeparrot_training - Step 37714: {'lr': 0.0004315358666018018, 'samples': 19310080, 'steps': 37714, 'loss/train': 1.6552873849868774}
-03/05/2022 09:47:58 - INFO - codeparrot_training - Step 37715: {'lr': 0.00043153221794485795, 'samples': 19310592, 'steps': 37715, 'loss/train': 1.3020331859588623}
-03/05/2022 09:47:59 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 09:48:03 - INFO - codeparrot_training - Step 37716: {'lr': 0.0004315285692061186, 'samples': 19311104, 'steps': 37716, 'loss/train': 1.6908332109451294}
-03/05/2022 09:48:06 - INFO - codeparrot_training - Step 37717: {'lr': 0.00043152492038558526, 'samples': 19311616, 'steps': 37717, 'loss/train': 1.7883599996566772}
-03/05/2022 09:48:07 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/05/2022 09:48:12 - INFO - codeparrot_training - Step 37718: {'lr': 0.00043152127148325957, 'samples': 19312128, 'steps': 37718, 'loss/train': 1.509145736694336}
-03/05/2022 09:48:15 - INFO - codeparrot_training - Step 37719: {'lr': 0.00043151762249914324, 'samples': 19312640, 'steps': 37719, 'loss/train': 1.5560741424560547}
-03/05/2022 09:48:15 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/05/2022 09:48:20 - INFO - codeparrot_training - Step 37720: {'lr': 0.00043151397343323784, 'samples': 19313152, 'steps': 37720, 'loss/train': 2.2463555335998535}
-03/05/2022 09:48:23 - INFO - codeparrot_training - Step 37721: {'lr': 0.00043151032428554505, 'samples': 19313664, 'steps': 37721, 'loss/train': 1.599293828010559}
-03/05/2022 09:48:23 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 09:48:29 - INFO - codeparrot_training - Step 37722: {'lr': 0.0004315066750560665, 'samples': 19314176, 'steps': 37722, 'loss/train': 0.6030313372612}
-03/05/2022 09:48:32 - INFO - codeparrot_training - Step 37723: {'lr': 0.0004315030257448038, 'samples': 19314688, 'steps': 37723, 'loss/train': 0.8725462555885315}
-03/05/2022 09:48:32 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/05/2022 09:48:37 - INFO - codeparrot_training - Step 37724: {'lr': 0.00043149937635175874, 'samples': 19315200, 'steps': 37724, 'loss/train': 2.121915102005005}
-03/05/2022 09:48:40 - INFO - codeparrot_training - Step 37725: {'lr': 0.0004314957268769328, 'samples': 19315712, 'steps': 37725, 'loss/train': 2.5113537311553955}
-03/05/2022 09:48:41 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/05/2022 09:48:45 - INFO - codeparrot_training - Step 37726: {'lr': 0.00043149207732032767, 'samples': 19316224, 'steps': 37726, 'loss/train': 1.9718410968780518}
-03/05/2022 09:48:49 - INFO - codeparrot_training - Step 37727: {'lr': 0.00043148842768194503, 'samples': 19316736, 'steps': 37727, 'loss/train': 1.9268851280212402}
-03/05/2022 09:48:50 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/05/2022 09:48:54 - INFO - codeparrot_training - Step 37728: {'lr': 0.0004314847779617865, 'samples': 19317248, 'steps': 37728, 'loss/train': 1.3978252410888672}
-03/05/2022 09:48:57 - INFO - codeparrot_training - Step 37729: {'lr': 0.00043148112815985377, 'samples': 19317760, 'steps': 37729, 'loss/train': 1.919399380683899}
-03/05/2022 09:48:58 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/05/2022 09:49:02 - INFO - codeparrot_training - Step 37730: {'lr': 0.0004314774782761484, 'samples': 19318272, 'steps': 37730, 'loss/train': 1.531058430671692}
-03/05/2022 09:49:05 - INFO - codeparrot_training - Step 37731: {'lr': 0.00043147382831067204, 'samples': 19318784, 'steps': 37731, 'loss/train': 1.4913954734802246}
-03/05/2022 09:49:07 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 09:49:11 - INFO - codeparrot_training - Step 37732: {'lr': 0.0004314701782634264, 'samples': 19319296, 'steps': 37732, 'loss/train': 3.1708483695983887}
-03/05/2022 09:49:14 - INFO - codeparrot_training - Step 37733: {'lr': 0.0004314665281344132, 'samples': 19319808, 'steps': 37733, 'loss/train': 1.2305701971054077}
-03/05/2022 09:49:15 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/05/2022 09:49:19 - INFO - codeparrot_training - Step 37734: {'lr': 0.0004314628779236339, 'samples': 19320320, 'steps': 37734, 'loss/train': 1.623321771621704}
-03/05/2022 09:49:22 - INFO - codeparrot_training - Step 37735: {'lr': 0.00043145922763109017, 'samples': 19320832, 'steps': 37735, 'loss/train': 2.278578758239746}
-03/05/2022 09:49:24 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/05/2022 09:49:28 - INFO - codeparrot_training - Step 37736: {'lr': 0.0004314555772567838, 'samples': 19321344, 'steps': 37736, 'loss/train': 1.3956269025802612}
-03/05/2022 09:49:31 - INFO - codeparrot_training - Step 37737: {'lr': 0.0004314519268007163, 'samples': 19321856, 'steps': 37737, 'loss/train': 1.6231944561004639}
-03/05/2022 09:49:32 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/05/2022 09:49:36 - INFO - codeparrot_training - Step 37738: {'lr': 0.00043144827626288943, 'samples': 19322368, 'steps': 37738, 'loss/train': 0.38999781012535095}
-03/05/2022 09:49:39 - INFO - codeparrot_training - Step 37739: {'lr': 0.00043144462564330464, 'samples': 19322880, 'steps': 37739, 'loss/train': 1.5829609632492065}
-03/05/2022 09:49:41 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 09:49:44 - INFO - codeparrot_training - Step 37740: {'lr': 0.0004314409749419638, 'samples': 19323392, 'steps': 37740, 'loss/train': 1.763595461845398}
-03/05/2022 09:49:48 - INFO - codeparrot_training - Step 37741: {'lr': 0.00043143732415886843, 'samples': 19323904, 'steps': 37741, 'loss/train': 1.9644676446914673}
-03/05/2022 09:49:49 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 09:49:53 - INFO - codeparrot_training - Step 37742: {'lr': 0.0004314336732940202, 'samples': 19324416, 'steps': 37742, 'loss/train': 2.000657081604004}
-03/05/2022 09:49:56 - INFO - codeparrot_training - Step 37743: {'lr': 0.0004314300223474208, 'samples': 19324928, 'steps': 37743, 'loss/train': 1.6981432437896729}
-03/05/2022 09:49:58 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 09:50:01 - INFO - codeparrot_training - Step 37744: {'lr': 0.0004314263713190718, 'samples': 19325440, 'steps': 37744, 'loss/train': 1.6584651470184326}
-03/05/2022 09:50:05 - INFO - codeparrot_training - Step 37745: {'lr': 0.00043142272020897486, 'samples': 19325952, 'steps': 37745, 'loss/train': 1.766785740852356}
-03/05/2022 09:50:07 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/05/2022 09:50:10 - INFO - codeparrot_training - Step 37746: {'lr': 0.0004314190690171317, 'samples': 19326464, 'steps': 37746, 'loss/train': 0.4846493899822235}
-03/05/2022 09:50:13 - INFO - codeparrot_training - Step 37747: {'lr': 0.0004314154177435438, 'samples': 19326976, 'steps': 37747, 'loss/train': 2.2789077758789062}
-03/05/2022 09:50:15 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/05/2022 09:50:18 - INFO - codeparrot_training - Step 37748: {'lr': 0.000431411766388213, 'samples': 19327488, 'steps': 37748, 'loss/train': 1.3124229907989502}
-03/05/2022 09:50:22 - INFO - codeparrot_training - Step 37749: {'lr': 0.0004314081149511409, 'samples': 19328000, 'steps': 37749, 'loss/train': 1.511587381362915}
-03/05/2022 09:50:24 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/05/2022 09:50:27 - INFO - codeparrot_training - Step 37750: {'lr': 0.00043140446343232895, 'samples': 19328512, 'steps': 37750, 'loss/train': 2.342555284500122}
-03/05/2022 09:50:30 - INFO - codeparrot_training - Step 37751: {'lr': 0.000431400811831779, 'samples': 19329024, 'steps': 37751, 'loss/train': 1.2448031902313232}
-03/05/2022 09:50:32 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 09:50:36 - INFO - codeparrot_training - Step 37752: {'lr': 0.0004313971601494927, 'samples': 19329536, 'steps': 37752, 'loss/train': 1.5074920654296875}
-03/05/2022 09:50:39 - INFO - codeparrot_training - Step 37753: {'lr': 0.0004313935083854716, 'samples': 19330048, 'steps': 37753, 'loss/train': 2.204068183898926}
-03/05/2022 09:50:41 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/05/2022 09:50:44 - INFO - codeparrot_training - Step 37754: {'lr': 0.0004313898565397174, 'samples': 19330560, 'steps': 37754, 'loss/train': 0.6262397170066833}
-03/05/2022 09:50:47 - INFO - codeparrot_training - Step 37755: {'lr': 0.00043138620461223175, 'samples': 19331072, 'steps': 37755, 'loss/train': 2.0114166736602783}
-03/05/2022 09:50:50 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/05/2022 09:50:52 - INFO - codeparrot_training - Step 37756: {'lr': 0.00043138255260301625, 'samples': 19331584, 'steps': 37756, 'loss/train': 1.8662606477737427}
-03/05/2022 09:50:56 - INFO - codeparrot_training - Step 37757: {'lr': 0.0004313789005120725, 'samples': 19332096, 'steps': 37757, 'loss/train': 2.6365272998809814}
-03/05/2022 09:50:58 - INFO - codeparrot_training - Skipping example with length 934 (seq_length=1024)
-03/05/2022 09:51:01 - INFO - codeparrot_training - Step 37758: {'lr': 0.00043137524833940233, 'samples': 19332608, 'steps': 37758, 'loss/train': 1.6917839050292969}
-03/05/2022 09:51:04 - INFO - codeparrot_training - Step 37759: {'lr': 0.0004313715960850072, 'samples': 19333120, 'steps': 37759, 'loss/train': 2.211031436920166}
-03/05/2022 09:51:06 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/05/2022 09:51:09 - INFO - codeparrot_training - Step 37760: {'lr': 0.00043136794374888887, 'samples': 19333632, 'steps': 37760, 'loss/train': 2.454784631729126}
-03/05/2022 09:51:12 - INFO - codeparrot_training - Step 37761: {'lr': 0.0004313642913310489, 'samples': 19334144, 'steps': 37761, 'loss/train': 1.8556796312332153}
-03/05/2022 09:51:14 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 09:51:18 - INFO - codeparrot_training - Step 37762: {'lr': 0.00043136063883148905, 'samples': 19334656, 'steps': 37762, 'loss/train': 1.6991041898727417}
-03/05/2022 09:51:21 - INFO - codeparrot_training - Step 37763: {'lr': 0.00043135698625021093, 'samples': 19335168, 'steps': 37763, 'loss/train': 2.8453540802001953}
-03/05/2022 09:51:23 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/05/2022 09:51:26 - INFO - codeparrot_training - Step 37764: {'lr': 0.000431353333587216, 'samples': 19335680, 'steps': 37764, 'loss/train': 0.9973475337028503}
-03/05/2022 09:51:29 - INFO - codeparrot_training - Step 37765: {'lr': 0.00043134968084250616, 'samples': 19336192, 'steps': 37765, 'loss/train': 1.4388701915740967}
-03/05/2022 09:51:31 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/05/2022 09:51:34 - INFO - codeparrot_training - Step 37766: {'lr': 0.00043134602801608293, 'samples': 19336704, 'steps': 37766, 'loss/train': 1.4616645574569702}
-03/05/2022 09:51:38 - INFO - codeparrot_training - Step 37767: {'lr': 0.00043134237510794794, 'samples': 19337216, 'steps': 37767, 'loss/train': 1.5076266527175903}
-03/05/2022 09:51:39 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/05/2022 09:51:43 - INFO - codeparrot_training - Step 37768: {'lr': 0.0004313387221181029, 'samples': 19337728, 'steps': 37768, 'loss/train': 0.6607352495193481}
-03/05/2022 09:51:46 - INFO - codeparrot_training - Step 37769: {'lr': 0.0004313350690465495, 'samples': 19338240, 'steps': 37769, 'loss/train': 1.7684088945388794}
-03/05/2022 09:51:48 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/05/2022 09:51:51 - INFO - codeparrot_training - Step 37770: {'lr': 0.00043133141589328923, 'samples': 19338752, 'steps': 37770, 'loss/train': 2.2141733169555664}
-03/05/2022 09:51:54 - INFO - codeparrot_training - Step 37771: {'lr': 0.0004313277626583239, 'samples': 19339264, 'steps': 37771, 'loss/train': 0.8748182654380798}
-03/05/2022 09:51:56 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/05/2022 09:52:00 - INFO - codeparrot_training - Step 37772: {'lr': 0.000431324109341655, 'samples': 19339776, 'steps': 37772, 'loss/train': 1.0755783319473267}
-03/05/2022 09:52:03 - INFO - codeparrot_training - Step 37773: {'lr': 0.0004313204559432842, 'samples': 19340288, 'steps': 37773, 'loss/train': 2.25142240524292}
-03/05/2022 09:52:04 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/05/2022 09:52:08 - INFO - codeparrot_training - Step 37774: {'lr': 0.0004313168024632133, 'samples': 19340800, 'steps': 37774, 'loss/train': 1.0825450420379639}
-03/05/2022 09:52:11 - INFO - codeparrot_training - Step 37775: {'lr': 0.00043131314890144386, 'samples': 19341312, 'steps': 37775, 'loss/train': 1.0785362720489502}
-03/05/2022 09:52:13 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/05/2022 09:52:17 - INFO - codeparrot_training - Step 37776: {'lr': 0.0004313094952579775, 'samples': 19341824, 'steps': 37776, 'loss/train': 1.680455207824707}
-03/05/2022 09:52:20 - INFO - codeparrot_training - Step 37777: {'lr': 0.0004313058415328158, 'samples': 19342336, 'steps': 37777, 'loss/train': 3.060363531112671}
-03/05/2022 09:52:21 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/05/2022 09:52:25 - INFO - codeparrot_training - Step 37778: {'lr': 0.00043130218772596053, 'samples': 19342848, 'steps': 37778, 'loss/train': 1.8972012996673584}
-03/05/2022 09:52:28 - INFO - codeparrot_training - Step 37779: {'lr': 0.00043129853383741334, 'samples': 19343360, 'steps': 37779, 'loss/train': 2.1065475940704346}
-03/05/2022 09:52:29 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/05/2022 09:52:33 - INFO - codeparrot_training - Step 37780: {'lr': 0.00043129487986717574, 'samples': 19343872, 'steps': 37780, 'loss/train': 1.882871389389038}
-03/05/2022 09:52:37 - INFO - codeparrot_training - Step 37781: {'lr': 0.00043129122581524957, 'samples': 19344384, 'steps': 37781, 'loss/train': 1.4573744535446167}
-03/05/2022 09:52:38 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/05/2022 09:52:42 - INFO - codeparrot_training - Step 37782: {'lr': 0.0004312875716816363, 'samples': 19344896, 'steps': 37782, 'loss/train': 1.7316608428955078}
-03/05/2022 09:52:45 - INFO - codeparrot_training - Step 37783: {'lr': 0.0004312839174663377, 'samples': 19345408, 'steps': 37783, 'loss/train': 2.343803882598877}
-03/05/2022 09:52:46 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/05/2022 09:52:50 - INFO - codeparrot_training - Step 37784: {'lr': 0.0004312802631693553, 'samples': 19345920, 'steps': 37784, 'loss/train': 1.6742995977401733}
-03/05/2022 09:52:54 - INFO - codeparrot_training - Step 37785: {'lr': 0.00043127660879069084, 'samples': 19346432, 'steps': 37785, 'loss/train': 2.2473838329315186}
-03/05/2022 09:52:55 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/05/2022 09:52:59 - INFO - codeparrot_training - Step 37786: {'lr': 0.00043127295433034594, 'samples': 19346944, 'steps': 37786, 'loss/train': 2.232743740081787}
-03/05/2022 09:53:02 - INFO - codeparrot_training - Step 37787: {'lr': 0.00043126929978832217, 'samples': 19347456, 'steps': 37787, 'loss/train': 1.3695499897003174}
-03/05/2022 09:53:03 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/05/2022 09:53:07 - INFO - codeparrot_training - Step 37788: {'lr': 0.00043126564516462134, 'samples': 19347968, 'steps': 37788, 'loss/train': 2.0778491497039795}
-03/05/2022 09:53:10 - INFO - codeparrot_training - Step 37789: {'lr': 0.000431261990459245, 'samples': 19348480, 'steps': 37789, 'loss/train': 1.8352696895599365}
-03/05/2022 09:53:11 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/05/2022 09:53:16 - INFO - codeparrot_training - Step 37790: {'lr': 0.0004312583356721948, 'samples': 19348992, 'steps': 37790, 'loss/train': 1.71046781539917}
-03/05/2022 09:53:19 - INFO - codeparrot_training - Step 37791: {'lr': 0.0004312546808034724, 'samples': 19349504, 'steps': 37791, 'loss/train': 1.7724194526672363}
-03/05/2022 09:53:20 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/05/2022 09:53:24 - INFO - codeparrot_training - Step 37792: {'lr': 0.0004312510258530794, 'samples': 19350016, 'steps': 37792, 'loss/train': 2.159608840942383}
-03/05/2022 09:53:27 - INFO - codeparrot_training - Step 37793: {'lr': 0.0004312473708210175, 'samples': 19350528, 'steps': 37793, 'loss/train': 1.398200273513794}
-03/05/2022 09:53:29 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/05/2022 09:53:33 - INFO - codeparrot_training - Step 37794: {'lr': 0.0004312437157072884, 'samples': 19351040, 'steps': 37794, 'loss/train': 1.6174712181091309}
-03/05/2022 09:53:36 - INFO - codeparrot_training - Step 37795: {'lr': 0.00043124006051189356, 'samples': 19351552, 'steps': 37795, 'loss/train': 1.7893608808517456}
-03/05/2022 09:53:37 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/05/2022 09:53:41 - INFO - codeparrot_training - Step 37796: {'lr': 0.0004312364052348348, 'samples': 19352064, 'steps': 37796, 'loss/train': 1.3551431894302368}
-03/05/2022 09:53:44 - INFO - codeparrot_training - Step 37797: {'lr': 0.0004312327498761137, 'samples': 19352576, 'steps': 37797, 'loss/train': 1.1525990962982178}
-03/05/2022 09:53:46 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/05/2022 09:53:50 - INFO - codeparrot_training - Step 37798: {'lr': 0.000431229094435732, 'samples': 19353088, 'steps': 37798, 'loss/train': 1.3771398067474365}
-03/05/2022 09:53:53 - INFO - codeparrot_training - Step 37799: {'lr': 0.0004312254389136911, 'samples': 19353600, 'steps': 37799, 'loss/train': 1.6611214876174927}
-03/05/2022 09:53:54 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/05/2022 09:53:59 - INFO - codeparrot_training - Step 37800: {'lr': 0.00043122178330999296, 'samples': 19354112, 'steps': 37800, 'loss/train': 2.1442809104919434}
-03/05/2022 09:54:02 - INFO - codeparrot_training - Step 37801: {'lr': 0.0004312181276246391, 'samples': 19354624, 'steps': 37801, 'loss/train': 2.297694206237793}
-03/05/2022 09:54:05 - INFO - codeparrot_training - Step 37802: {'lr': 0.00043121447185763106, 'samples': 19355136, 'steps': 37802, 'loss/train': 1.4977821111679077}
-03/05/2022 09:54:06 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/05/2022 09:54:10 - INFO - codeparrot_training - Step 37803: {'lr': 0.0004312108160089706, 'samples': 19355648, 'steps': 37803, 'loss/train': 1.7507095336914062}
-03/05/2022 09:54:14 - INFO - codeparrot_training - Step 37804: {'lr': 0.00043120716007865933, 'samples': 19356160, 'steps': 37804, 'loss/train': 2.108715295791626}
-03/05/2022 09:54:14 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/05/2022 09:54:19 - INFO - codeparrot_training - Step 37805: {'lr': 0.0004312035040666989, 'samples': 19356672, 'steps': 37805, 'loss/train': 1.2766791582107544}
-03/05/2022 09:54:22 - INFO - codeparrot_training - Step 37806: {'lr': 0.000431199847973091, 'samples': 19357184, 'steps': 37806, 'loss/train': 2.2332565784454346}
-03/05/2022 09:54:23 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/05/2022 09:54:28 - INFO - codeparrot_training - Step 37807: {'lr': 0.0004311961917978372, 'samples': 19357696, 'steps': 37807, 'loss/train': 0.2978323698043823}
-03/05/2022 09:54:31 - INFO - codeparrot_training - Step 37808: {'lr': 0.0004311925355409393, 'samples': 19358208, 'steps': 37808, 'loss/train': 1.5337976217269897}
-03/05/2022 09:54:32 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/05/2022 09:54:36 - INFO - codeparrot_training - Step 37809: {'lr': 0.00043118887920239876, 'samples': 19358720, 'steps': 37809, 'loss/train': 1.8254008293151855}
-03/05/2022 09:54:39 - INFO - codeparrot_training - Step 37810: {'lr': 0.00043118522278221726, 'samples': 19359232, 'steps': 37810, 'loss/train': 1.9307475090026855}
-03/05/2022 09:54:41 - INFO - codeparrot_training - Skipping example with length 683 (seq_length=1024)
-03/05/2022 09:54:45 - INFO - codeparrot_training - Step 37811: {'lr': 0.0004311815662803966, 'samples': 19359744, 'steps': 37811, 'loss/train': 1.9755327701568604}
-03/05/2022 09:54:48 - INFO - codeparrot_training - Step 37812: {'lr': 0.00043117790969693826, 'samples': 19360256, 'steps': 37812, 'loss/train': 2.0319652557373047}
-03/05/2022 09:54:49 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/05/2022 09:54:53 - INFO - codeparrot_training - Step 37813: {'lr': 0.00043117425303184395, 'samples': 19360768, 'steps': 37813, 'loss/train': 1.4949917793273926}
-03/05/2022 09:54:56 - INFO - codeparrot_training - Step 37814: {'lr': 0.0004311705962851153, 'samples': 19361280, 'steps': 37814, 'loss/train': 2.1020655632019043}
-03/05/2022 09:54:57 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/05/2022 09:55:01 - INFO - codeparrot_training - Step 37815: {'lr': 0.000431166939456754, 'samples': 19361792, 'steps': 37815, 'loss/train': 1.9416307210922241}
-03/05/2022 09:55:05 - INFO - codeparrot_training - Step 37816: {'lr': 0.0004311632825467617, 'samples': 19362304, 'steps': 37816, 'loss/train': 2.0847034454345703}
-03/05/2022 09:55:06 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/05/2022 09:55:10 - INFO - codeparrot_training - Step 37817: {'lr': 0.00043115962555514, 'samples': 19362816, 'steps': 37817, 'loss/train': 0.7069443464279175}
-03/05/2022 09:55:13 - INFO - codeparrot_training - Step 37818: {'lr': 0.0004311559684818905, 'samples': 19363328, 'steps': 37818, 'loss/train': 1.5219447612762451}
-03/05/2022 09:55:14 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/05/2022 09:55:18 - INFO - codeparrot_training - Step 37819: {'lr': 0.000431152311327015, 'samples': 19363840, 'steps': 37819, 'loss/train': 0.9714227318763733}
-03/05/2022 09:55:21 - INFO - codeparrot_training - Step 37820: {'lr': 0.00043114865409051505, 'samples': 19364352, 'steps': 37820, 'loss/train': 1.3239413499832153}
-03/05/2022 09:55:23 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/05/2022 09:55:27 - INFO - codeparrot_training - Step 37821: {'lr': 0.0004311449967723923, 'samples': 19364864, 'steps': 37821, 'loss/train': 1.6976454257965088}
-03/05/2022 09:55:30 - INFO - codeparrot_training - Step 37822: {'lr': 0.00043114133937264843, 'samples': 19365376, 'steps': 37822, 'loss/train': 2.0362679958343506}
-03/05/2022 09:55:31 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/05/2022 09:55:35 - INFO - codeparrot_training - Step 37823: {'lr': 0.000431137681891285, 'samples': 19365888, 'steps': 37823, 'loss/train': 2.265512228012085}
-03/05/2022 09:55:39 - INFO - codeparrot_training - Step 37824: {'lr': 0.0004311340243283038, 'samples': 19366400, 'steps': 37824, 'loss/train': 2.2506303787231445}
-03/05/2022 09:55:41 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/05/2022 09:55:44 - INFO - codeparrot_training - Step 37825: {'lr': 0.0004311303666837064, 'samples': 19366912, 'steps': 37825, 'loss/train': 1.6736390590667725}
-03/05/2022 09:55:47 - INFO - codeparrot_training - Step 37826: {'lr': 0.0004311267089574944, 'samples': 19367424, 'steps': 37826, 'loss/train': 2.86852765083313}
-03/05/2022 09:55:49 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/05/2022 09:55:52 - INFO - codeparrot_training - Step 37827: {'lr': 0.00043112305114966957, 'samples': 19367936, 'steps': 37827, 'loss/train': 1.225523591041565}
-03/05/2022 09:55:56 - INFO - codeparrot_training - Step 37828: {'lr': 0.0004311193932602334, 'samples': 19368448, 'steps': 37828, 'loss/train': 1.3334112167358398}
-03/05/2022 09:55:57 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/05/2022 09:56:01 - INFO - codeparrot_training - Step 37829: {'lr': 0.0004311157352891877, 'samples': 19368960, 'steps': 37829, 'loss/train': 0.9887212514877319}
-03/05/2022 09:56:04 - INFO - codeparrot_training - Step 37830: {'lr': 0.000431112077236534, 'samples': 19369472, 'steps': 37830, 'loss/train': 1.583834171295166}
-03/05/2022 09:56:06 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/05/2022 09:56:09 - INFO - codeparrot_training - Step 37831: {'lr': 0.0004311084191022741, 'samples': 19369984, 'steps': 37831, 'loss/train': 0.7535305023193359}
-03/05/2022 09:56:12 - INFO - codeparrot_training - Step 37832: {'lr': 0.00043110476088640935, 'samples': 19370496, 'steps': 37832, 'loss/train': 1.9746586084365845}
-03/05/2022 09:56:14 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/05/2022 09:56:18 - INFO - codeparrot_training - Step 37833: {'lr': 0.00043110110258894177, 'samples': 19371008, 'steps': 37833, 'loss/train': 1.4196697473526}
-03/05/2022 09:56:21 - INFO - codeparrot_training - Step 37834: {'lr': 0.00043109744420987274, 'samples': 19371520, 'steps': 37834, 'loss/train': 2.1329185962677}
-03/05/2022 09:56:23 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/05/2022 09:56:26 - INFO - codeparrot_training - Step 37835: {'lr': 0.000431093785749204, 'samples': 19372032, 'steps': 37835, 'loss/train': 1.0034433603286743}
-03/05/2022 09:56:29 - INFO - codeparrot_training - Step 37836: {'lr': 0.00043109012720693717, 'samples': 19372544, 'steps': 37836, 'loss/train': 1.9124420881271362}
-03/05/2022 09:56:31 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/05/2022 09:56:35 - INFO - codeparrot_training - Step 37837: {'lr': 0.000431086468583074, 'samples': 19373056, 'steps': 37837, 'loss/train': 1.365955114364624}
-03/05/2022 09:56:38 - INFO - codeparrot_training - Step 37838: {'lr': 0.00043108280987761593, 'samples': 19373568, 'steps': 37838, 'loss/train': 1.408068060874939}
-03/05/2022 09:56:39 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/05/2022 09:56:43 - INFO - codeparrot_training - Step 37839: {'lr': 0.0004310791510905649, 'samples': 19374080, 'steps': 37839, 'loss/train': 0.8463644981384277}
-03/05/2022 09:56:46 - INFO - codeparrot_training - Step 37840: {'lr': 0.00043107549222192235, 'samples': 19374592, 'steps': 37840, 'loss/train': 0.7807109355926514}
-03/05/2022 09:56:48 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/05/2022 09:56:52 - INFO - codeparrot_training - Step 37841: {'lr': 0.0004310718332716899, 'samples': 19375104, 'steps': 37841, 'loss/train': 2.167212724685669}
-03/05/2022 09:56:55 - INFO - codeparrot_training - Step 37842: {'lr': 0.00043106817423986933, 'samples': 19375616, 'steps': 37842, 'loss/train': 2.1488988399505615}
-03/05/2022 09:56:59 - INFO - codeparrot_training - Step 37843: {'lr': 0.00043106451512646226, 'samples': 19376128, 'steps': 37843, 'loss/train': 2.0155699253082275}
-03/05/2022 09:56:59 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/05/2022 09:57:04 - INFO - codeparrot_training - Step 37844: {'lr': 0.00043106085593147027, 'samples': 19376640, 'steps': 37844, 'loss/train': 1.9916726350784302}
-03/05/2022 09:57:07 - INFO - codeparrot_training - Step 37845: {'lr': 0.00043105719665489505, 'samples': 19377152, 'steps': 37845, 'loss/train': 1.4611812829971313}
-03/05/2022 09:57:08 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/05/2022 09:57:13 - INFO - codeparrot_training - Step 37846: {'lr': 0.0004310535372967383, 'samples': 19377664, 'steps': 37846, 'loss/train': 1.6552391052246094}
-03/05/2022 09:57:16 - INFO - codeparrot_training - Step 37847: {'lr': 0.0004310498778570016, 'samples': 19378176, 'steps': 37847, 'loss/train': 1.7216873168945312}
-03/05/2022 09:57:16 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 09:57:21 - INFO - codeparrot_training - Step 37848: {'lr': 0.0004310462183356866, 'samples': 19378688, 'steps': 37848, 'loss/train': 1.8481634855270386}
-03/05/2022 09:57:24 - INFO - codeparrot_training - Step 37849: {'lr': 0.00043104255873279497, 'samples': 19379200, 'steps': 37849, 'loss/train': 0.41859790682792664}
-03/05/2022 09:57:25 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 09:57:30 - INFO - codeparrot_training - Step 37850: {'lr': 0.00043103889904832837, 'samples': 19379712, 'steps': 37850, 'loss/train': 1.8630810976028442}
-03/05/2022 09:57:33 - INFO - codeparrot_training - Step 37851: {'lr': 0.0004310352392822884, 'samples': 19380224, 'steps': 37851, 'loss/train': 1.5084508657455444}
-03/05/2022 09:57:33 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 09:57:38 - INFO - codeparrot_training - Step 37852: {'lr': 0.00043103157943467674, 'samples': 19380736, 'steps': 37852, 'loss/train': 1.2454826831817627}
-03/05/2022 09:57:41 - INFO - codeparrot_training - Step 37853: {'lr': 0.00043102791950549513, 'samples': 19381248, 'steps': 37853, 'loss/train': 2.375488519668579}
-03/05/2022 09:57:42 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 09:57:46 - INFO - codeparrot_training - Step 37854: {'lr': 0.00043102425949474504, 'samples': 19381760, 'steps': 37854, 'loss/train': 1.4127804040908813}
-03/05/2022 09:57:50 - INFO - codeparrot_training - Step 37855: {'lr': 0.00043102059940242825, 'samples': 19382272, 'steps': 37855, 'loss/train': 1.1573930978775024}
-03/05/2022 09:57:50 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 09:57:55 - INFO - codeparrot_training - Step 37856: {'lr': 0.0004310169392285464, 'samples': 19382784, 'steps': 37856, 'loss/train': 1.4555232524871826}
-03/05/2022 09:57:58 - INFO - codeparrot_training - Step 37857: {'lr': 0.0004310132789731011, 'samples': 19383296, 'steps': 37857, 'loss/train': 2.1113319396972656}
-03/05/2022 09:57:58 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/05/2022 09:58:03 - INFO - codeparrot_training - Step 37858: {'lr': 0.000431009618636094, 'samples': 19383808, 'steps': 37858, 'loss/train': 0.9203762412071228}
-03/05/2022 09:58:06 - INFO - codeparrot_training - Step 37859: {'lr': 0.00043100595821752674, 'samples': 19384320, 'steps': 37859, 'loss/train': 0.479248970746994}
-03/05/2022 09:58:06 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/05/2022 09:58:12 - INFO - codeparrot_training - Step 37860: {'lr': 0.00043100229771740096, 'samples': 19384832, 'steps': 37860, 'loss/train': 2.3405745029449463}
-03/05/2022 09:58:15 - INFO - codeparrot_training - Step 37861: {'lr': 0.0004309986371357184, 'samples': 19385344, 'steps': 37861, 'loss/train': 1.7067760229110718}
-03/05/2022 09:58:15 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/05/2022 09:58:20 - INFO - codeparrot_training - Step 37862: {'lr': 0.00043099497647248065, 'samples': 19385856, 'steps': 37862, 'loss/train': 1.9136826992034912}
-03/05/2022 09:58:23 - INFO - codeparrot_training - Step 37863: {'lr': 0.00043099131572768936, 'samples': 19386368, 'steps': 37863, 'loss/train': 2.0518929958343506}
-03/05/2022 09:58:23 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/05/2022 09:58:29 - INFO - codeparrot_training - Step 37864: {'lr': 0.00043098765490134607, 'samples': 19386880, 'steps': 37864, 'loss/train': 1.5379780530929565}
-03/05/2022 09:58:32 - INFO - codeparrot_training - Step 37865: {'lr': 0.00043098399399345267, 'samples': 19387392, 'steps': 37865, 'loss/train': 2.418001651763916}
-03/05/2022 09:58:32 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/05/2022 09:58:37 - INFO - codeparrot_training - Step 37866: {'lr': 0.0004309803330040106, 'samples': 19387904, 'steps': 37866, 'loss/train': 1.712828516960144}
-03/05/2022 09:58:40 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/05/2022 09:58:42 - INFO - codeparrot_training - Step 37867: {'lr': 0.0004309766719330216, 'samples': 19388416, 'steps': 37867, 'loss/train': 1.4560084342956543}
-03/05/2022 09:58:45 - INFO - codeparrot_training - Step 37868: {'lr': 0.00043097301078048736, 'samples': 19388928, 'steps': 37868, 'loss/train': 2.5097904205322266}
-03/05/2022 09:58:48 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/05/2022 09:58:51 - INFO - codeparrot_training - Step 37869: {'lr': 0.00043096934954640935, 'samples': 19389440, 'steps': 37869, 'loss/train': 1.4404182434082031}
-03/05/2022 09:58:55 - INFO - codeparrot_training - Step 37870: {'lr': 0.0004309656882307894, 'samples': 19389952, 'steps': 37870, 'loss/train': 2.1487138271331787}
-03/05/2022 09:58:58 - INFO - codeparrot_training - Step 37871: {'lr': 0.0004309620268336292, 'samples': 19390464, 'steps': 37871, 'loss/train': 2.233774423599243}
-03/05/2022 09:59:00 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/05/2022 09:59:03 - INFO - codeparrot_training - Step 37872: {'lr': 0.0004309583653549302, 'samples': 19390976, 'steps': 37872, 'loss/train': 1.2517735958099365}
-03/05/2022 09:59:06 - INFO - codeparrot_training - Step 37873: {'lr': 0.0004309547037946941, 'samples': 19391488, 'steps': 37873, 'loss/train': 2.06913161277771}
-03/05/2022 09:59:09 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 09:59:12 - INFO - codeparrot_training - Step 37874: {'lr': 0.0004309510421529227, 'samples': 19392000, 'steps': 37874, 'loss/train': 0.6754811406135559}
-03/05/2022 09:59:15 - INFO - codeparrot_training - Step 37875: {'lr': 0.00043094738042961754, 'samples': 19392512, 'steps': 37875, 'loss/train': 1.6046569347381592}
-03/05/2022 09:59:18 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/05/2022 09:59:20 - INFO - codeparrot_training - Step 37876: {'lr': 0.0004309437186247803, 'samples': 19393024, 'steps': 37876, 'loss/train': 0.9485911726951599}
-03/05/2022 09:59:23 - INFO - codeparrot_training - Step 37877: {'lr': 0.00043094005673841257, 'samples': 19393536, 'steps': 37877, 'loss/train': 1.1992535591125488}
-03/05/2022 09:59:26 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/05/2022 09:59:28 - INFO - codeparrot_training - Step 37878: {'lr': 0.00043093639477051606, 'samples': 19394048, 'steps': 37878, 'loss/train': 1.6024229526519775}
-03/05/2022 09:59:32 - INFO - codeparrot_training - Step 37879: {'lr': 0.0004309327327210923, 'samples': 19394560, 'steps': 37879, 'loss/train': 0.654205858707428}
-03/05/2022 09:59:35 - INFO - codeparrot_training - Step 37880: {'lr': 0.00043092907059014325, 'samples': 19395072, 'steps': 37880, 'loss/train': 0.5172398686408997}
-03/05/2022 09:59:35 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 09:59:40 - INFO - codeparrot_training - Step 37881: {'lr': 0.00043092540837767025, 'samples': 19395584, 'steps': 37881, 'loss/train': 1.5750616788864136}
-03/05/2022 09:59:43 - INFO - codeparrot_training - Step 37882: {'lr': 0.000430921746083675, 'samples': 19396096, 'steps': 37882, 'loss/train': 1.0613892078399658}
-03/05/2022 09:59:43 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/05/2022 09:59:49 - INFO - codeparrot_training - Step 37883: {'lr': 0.00043091808370815935, 'samples': 19396608, 'steps': 37883, 'loss/train': 1.5158919095993042}
-03/05/2022 09:59:51 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/05/2022 09:59:54 - INFO - codeparrot_training - Step 37884: {'lr': 0.0004309144212511246, 'samples': 19397120, 'steps': 37884, 'loss/train': 1.949298620223999}
-03/05/2022 09:59:57 - INFO - codeparrot_training - Step 37885: {'lr': 0.00043091075871257275, 'samples': 19397632, 'steps': 37885, 'loss/train': 0.6992967128753662}
-03/05/2022 10:00:00 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/05/2022 10:00:02 - INFO - codeparrot_training - Step 37886: {'lr': 0.0004309070960925052, 'samples': 19398144, 'steps': 37886, 'loss/train': 1.865713119506836}
-03/05/2022 10:00:06 - INFO - codeparrot_training - Step 37887: {'lr': 0.0004309034333909238, 'samples': 19398656, 'steps': 37887, 'loss/train': 1.5458478927612305}
-03/05/2022 10:00:08 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/05/2022 10:00:11 - INFO - codeparrot_training - Step 37888: {'lr': 0.0004308997706078301, 'samples': 19399168, 'steps': 37888, 'loss/train': 1.2711635828018188}
-03/05/2022 10:00:14 - INFO - codeparrot_training - Step 37889: {'lr': 0.00043089610774322575, 'samples': 19399680, 'steps': 37889, 'loss/train': 1.9903497695922852}
-03/05/2022 10:00:16 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 10:00:19 - INFO - codeparrot_training - Step 37890: {'lr': 0.00043089244479711233, 'samples': 19400192, 'steps': 37890, 'loss/train': 1.5419869422912598}
-03/05/2022 10:00:22 - INFO - codeparrot_training - Step 37891: {'lr': 0.00043088878176949163, 'samples': 19400704, 'steps': 37891, 'loss/train': 1.056033730506897}
-03/05/2022 10:00:25 - INFO - codeparrot_training - Skipping example with length 540 (seq_length=1024)
-03/05/2022 10:00:28 - INFO - codeparrot_training - Step 37892: {'lr': 0.0004308851186603652, 'samples': 19401216, 'steps': 37892, 'loss/train': 1.2840379476547241}
-03/05/2022 10:00:31 - INFO - codeparrot_training - Step 37893: {'lr': 0.0004308814554697348, 'samples': 19401728, 'steps': 37893, 'loss/train': 1.9513486623764038}
-03/05/2022 10:00:33 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/05/2022 10:00:36 - INFO - codeparrot_training - Step 37894: {'lr': 0.0004308777921976019, 'samples': 19402240, 'steps': 37894, 'loss/train': 1.9178094863891602}
-03/05/2022 10:00:39 - INFO - codeparrot_training - Step 37895: {'lr': 0.00043087412884396835, 'samples': 19402752, 'steps': 37895, 'loss/train': 2.4974148273468018}
-03/05/2022 10:00:42 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/05/2022 10:00:45 - INFO - codeparrot_training - Step 37896: {'lr': 0.0004308704654088357, 'samples': 19403264, 'steps': 37896, 'loss/train': 1.3881484270095825}
-03/05/2022 10:00:48 - INFO - codeparrot_training - Step 37897: {'lr': 0.00043086680189220554, 'samples': 19403776, 'steps': 37897, 'loss/train': 1.8198308944702148}
-03/05/2022 10:00:50 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/05/2022 10:00:53 - INFO - codeparrot_training - Step 37898: {'lr': 0.00043086313829407966, 'samples': 19404288, 'steps': 37898, 'loss/train': 1.6075712442398071}
-03/05/2022 10:00:56 - INFO - codeparrot_training - Step 37899: {'lr': 0.0004308594746144596, 'samples': 19404800, 'steps': 37899, 'loss/train': 1.4757670164108276}
-03/05/2022 10:00:59 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/05/2022 10:01:02 - INFO - codeparrot_training - Step 37900: {'lr': 0.0004308558108533471, 'samples': 19405312, 'steps': 37900, 'loss/train': 2.1862990856170654}
-03/05/2022 10:01:05 - INFO - codeparrot_training - Step 37901: {'lr': 0.0004308521470107437, 'samples': 19405824, 'steps': 37901, 'loss/train': 1.7562228441238403}
-03/05/2022 10:01:07 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 10:01:10 - INFO - codeparrot_training - Step 37902: {'lr': 0.00043084848308665115, 'samples': 19406336, 'steps': 37902, 'loss/train': 0.6028088331222534}
-03/05/2022 10:01:13 - INFO - codeparrot_training - Step 37903: {'lr': 0.00043084481908107103, 'samples': 19406848, 'steps': 37903, 'loss/train': 1.7737396955490112}
-03/05/2022 10:01:16 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/05/2022 10:01:18 - INFO - codeparrot_training - Step 37904: {'lr': 0.00043084115499400505, 'samples': 19407360, 'steps': 37904, 'loss/train': 1.7592620849609375}
-03/05/2022 10:01:22 - INFO - codeparrot_training - Step 37905: {'lr': 0.0004308374908254549, 'samples': 19407872, 'steps': 37905, 'loss/train': 1.9128062725067139}
-03/05/2022 10:01:24 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/05/2022 10:01:27 - INFO - codeparrot_training - Step 37906: {'lr': 0.000430833826575422, 'samples': 19408384, 'steps': 37906, 'loss/train': 1.6850887537002563}
-03/05/2022 10:01:30 - INFO - codeparrot_training - Step 37907: {'lr': 0.0004308301622439083, 'samples': 19408896, 'steps': 37907, 'loss/train': 1.5409479141235352}
-03/05/2022 10:01:34 - INFO - codeparrot_training - Step 37908: {'lr': 0.0004308264978309153, 'samples': 19409408, 'steps': 37908, 'loss/train': 2.578800678253174}
-03/05/2022 10:01:34 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 10:01:39 - INFO - codeparrot_training - Step 37909: {'lr': 0.0004308228333364447, 'samples': 19409920, 'steps': 37909, 'loss/train': 0.9439515471458435}
-03/05/2022 10:01:42 - INFO - codeparrot_training - Step 37910: {'lr': 0.000430819168760498, 'samples': 19410432, 'steps': 37910, 'loss/train': 2.389791250228882}
-03/05/2022 10:01:42 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 10:01:47 - INFO - codeparrot_training - Step 37911: {'lr': 0.0004308155041030771, 'samples': 19410944, 'steps': 37911, 'loss/train': 1.799576997756958}
-03/05/2022 10:01:50 - INFO - codeparrot_training - Step 37912: {'lr': 0.00043081183936418343, 'samples': 19411456, 'steps': 37912, 'loss/train': 1.7143737077713013}
-03/05/2022 10:01:51 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/05/2022 10:01:56 - INFO - codeparrot_training - Step 37913: {'lr': 0.0004308081745438188, 'samples': 19411968, 'steps': 37913, 'loss/train': 1.6213486194610596}
-03/05/2022 10:01:59 - INFO - codeparrot_training - Step 37914: {'lr': 0.00043080450964198483, 'samples': 19412480, 'steps': 37914, 'loss/train': 1.3872851133346558}
-03/05/2022 10:02:00 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 10:02:04 - INFO - codeparrot_training - Step 37915: {'lr': 0.00043080084465868307, 'samples': 19412992, 'steps': 37915, 'loss/train': 2.8674635887145996}
-03/05/2022 10:02:07 - INFO - codeparrot_training - Step 37916: {'lr': 0.0004307971795939152, 'samples': 19413504, 'steps': 37916, 'loss/train': 1.8053076267242432}
-03/05/2022 10:02:08 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/05/2022 10:02:13 - INFO - codeparrot_training - Step 37917: {'lr': 0.000430793514447683, 'samples': 19414016, 'steps': 37917, 'loss/train': 1.7051365375518799}
-03/05/2022 10:02:16 - INFO - codeparrot_training - Step 37918: {'lr': 0.000430789849219988, 'samples': 19414528, 'steps': 37918, 'loss/train': 2.388674259185791}
-03/05/2022 10:02:17 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 10:02:21 - INFO - codeparrot_training - Step 37919: {'lr': 0.0004307861839108319, 'samples': 19415040, 'steps': 37919, 'loss/train': 2.0870227813720703}
-03/05/2022 10:02:24 - INFO - codeparrot_training - Step 37920: {'lr': 0.00043078251852021634, 'samples': 19415552, 'steps': 37920, 'loss/train': 1.7244954109191895}
-03/05/2022 10:02:26 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/05/2022 10:02:29 - INFO - codeparrot_training - Step 37921: {'lr': 0.0004307788530481429, 'samples': 19416064, 'steps': 37921, 'loss/train': 1.7325867414474487}
-03/05/2022 10:02:33 - INFO - codeparrot_training - Step 37922: {'lr': 0.00043077518749461336, 'samples': 19416576, 'steps': 37922, 'loss/train': 2.560762643814087}
-03/05/2022 10:02:34 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/05/2022 10:02:38 - INFO - codeparrot_training - Step 37923: {'lr': 0.00043077152185962933, 'samples': 19417088, 'steps': 37923, 'loss/train': 0.9312105178833008}
-03/05/2022 10:02:41 - INFO - codeparrot_training - Step 37924: {'lr': 0.00043076785614319234, 'samples': 19417600, 'steps': 37924, 'loss/train': 1.1721289157867432}
-03/05/2022 10:02:42 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/05/2022 10:02:46 - INFO - codeparrot_training - Step 37925: {'lr': 0.0004307641903453042, 'samples': 19418112, 'steps': 37925, 'loss/train': 1.2373802661895752}
-03/05/2022 10:02:49 - INFO - codeparrot_training - Step 37926: {'lr': 0.00043076052446596656, 'samples': 19418624, 'steps': 37926, 'loss/train': 1.4676055908203125}
-03/05/2022 10:02:51 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/05/2022 10:02:55 - INFO - codeparrot_training - Step 37927: {'lr': 0.000430756858505181, 'samples': 19419136, 'steps': 37927, 'loss/train': 1.3450775146484375}
-03/05/2022 10:02:58 - INFO - codeparrot_training - Step 37928: {'lr': 0.00043075319246294914, 'samples': 19419648, 'steps': 37928, 'loss/train': 1.497881293296814}
-03/05/2022 10:03:00 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/05/2022 10:03:03 - INFO - codeparrot_training - Step 37929: {'lr': 0.0004307495263392727, 'samples': 19420160, 'steps': 37929, 'loss/train': 1.7660783529281616}
-03/05/2022 10:03:06 - INFO - codeparrot_training - Step 37930: {'lr': 0.00043074586013415337, 'samples': 19420672, 'steps': 37930, 'loss/train': 1.8334081172943115}
-03/05/2022 10:03:08 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/05/2022 10:03:12 - INFO - codeparrot_training - Step 37931: {'lr': 0.0004307421938475926, 'samples': 19421184, 'steps': 37931, 'loss/train': 1.2816463708877563}
-03/05/2022 10:03:15 - INFO - codeparrot_training - Step 37932: {'lr': 0.0004307385274795923, 'samples': 19421696, 'steps': 37932, 'loss/train': 1.2902185916900635}
-03/05/2022 10:03:17 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/05/2022 10:03:20 - INFO - codeparrot_training - Step 37933: {'lr': 0.000430734861030154, 'samples': 19422208, 'steps': 37933, 'loss/train': 1.2918124198913574}
-03/05/2022 10:03:23 - INFO - codeparrot_training - Step 37934: {'lr': 0.0004307311944992793, 'samples': 19422720, 'steps': 37934, 'loss/train': 1.2767144441604614}
-03/05/2022 10:03:26 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/05/2022 10:03:29 - INFO - codeparrot_training - Step 37935: {'lr': 0.00043072752788697003, 'samples': 19423232, 'steps': 37935, 'loss/train': 1.543299674987793}
-03/05/2022 10:03:32 - INFO - codeparrot_training - Step 37936: {'lr': 0.0004307238611932276, 'samples': 19423744, 'steps': 37936, 'loss/train': 2.0173611640930176}
-03/05/2022 10:03:35 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/05/2022 10:03:37 - INFO - codeparrot_training - Step 37937: {'lr': 0.00043072019441805386, 'samples': 19424256, 'steps': 37937, 'loss/train': 1.5570237636566162}
-03/05/2022 10:03:40 - INFO - codeparrot_training - Step 37938: {'lr': 0.00043071652756145035, 'samples': 19424768, 'steps': 37938, 'loss/train': 2.2263429164886475}
-03/05/2022 10:03:43 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/05/2022 10:03:45 - INFO - codeparrot_training - Step 37939: {'lr': 0.0004307128606234188, 'samples': 19425280, 'steps': 37939, 'loss/train': 1.314713478088379}
-03/05/2022 10:03:49 - INFO - codeparrot_training - Step 37940: {'lr': 0.00043070919360396076, 'samples': 19425792, 'steps': 37940, 'loss/train': 1.3388396501541138}
-03/05/2022 10:03:51 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/05/2022 10:03:54 - INFO - codeparrot_training - Step 37941: {'lr': 0.00043070552650307804, 'samples': 19426304, 'steps': 37941, 'loss/train': 1.635088562965393}
-03/05/2022 10:03:57 - INFO - codeparrot_training - Step 37942: {'lr': 0.0004307018593207721, 'samples': 19426816, 'steps': 37942, 'loss/train': 1.5173020362854004}
-03/05/2022 10:04:00 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/05/2022 10:04:02 - INFO - codeparrot_training - Step 37943: {'lr': 0.0004306981920570447, 'samples': 19427328, 'steps': 37943, 'loss/train': 1.4404644966125488}
-03/05/2022 10:04:06 - INFO - codeparrot_training - Step 37944: {'lr': 0.00043069452471189765, 'samples': 19427840, 'steps': 37944, 'loss/train': 1.4728060960769653}
-03/05/2022 10:04:08 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/05/2022 10:04:11 - INFO - codeparrot_training - Step 37945: {'lr': 0.00043069085728533225, 'samples': 19428352, 'steps': 37945, 'loss/train': 1.2332886457443237}
-03/05/2022 10:04:14 - INFO - codeparrot_training - Step 37946: {'lr': 0.0004306871897773504, 'samples': 19428864, 'steps': 37946, 'loss/train': 0.8373779654502869}
-03/05/2022 10:04:16 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 10:04:19 - INFO - codeparrot_training - Step 37947: {'lr': 0.0004306835221879537, 'samples': 19429376, 'steps': 37947, 'loss/train': 1.0834929943084717}
-03/05/2022 10:04:23 - INFO - codeparrot_training - Step 37948: {'lr': 0.00043067985451714373, 'samples': 19429888, 'steps': 37948, 'loss/train': 1.9333170652389526}
-03/05/2022 10:04:25 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/05/2022 10:04:28 - INFO - codeparrot_training - Step 37949: {'lr': 0.0004306761867649223, 'samples': 19430400, 'steps': 37949, 'loss/train': 0.6583194136619568}
-03/05/2022 10:04:31 - INFO - codeparrot_training - Step 37950: {'lr': 0.0004306725189312909, 'samples': 19430912, 'steps': 37950, 'loss/train': 2.0297975540161133}
-03/05/2022 10:04:33 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/05/2022 10:04:36 - INFO - codeparrot_training - Step 37951: {'lr': 0.00043066885101625133, 'samples': 19431424, 'steps': 37951, 'loss/train': 1.6340519189834595}
-03/05/2022 10:04:39 - INFO - codeparrot_training - Step 37952: {'lr': 0.00043066518301980504, 'samples': 19431936, 'steps': 37952, 'loss/train': 1.442530632019043}
-03/05/2022 10:04:42 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/05/2022 10:04:45 - INFO - codeparrot_training - Step 37953: {'lr': 0.00043066151494195387, 'samples': 19432448, 'steps': 37953, 'loss/train': 1.726385235786438}
-03/05/2022 10:04:48 - INFO - codeparrot_training - Step 37954: {'lr': 0.00043065784678269944, 'samples': 19432960, 'steps': 37954, 'loss/train': 1.6143455505371094}
-03/05/2022 10:04:50 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 10:04:53 - INFO - codeparrot_training - Step 37955: {'lr': 0.00043065417854204333, 'samples': 19433472, 'steps': 37955, 'loss/train': 1.7574493885040283}
-03/05/2022 10:04:56 - INFO - codeparrot_training - Step 37956: {'lr': 0.0004306505102199872, 'samples': 19433984, 'steps': 37956, 'loss/train': 0.9709206819534302}
-03/05/2022 10:04:59 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 10:05:02 - INFO - codeparrot_training - Step 37957: {'lr': 0.0004306468418165328, 'samples': 19434496, 'steps': 37957, 'loss/train': 2.6438684463500977}
-03/05/2022 10:05:05 - INFO - codeparrot_training - Step 37958: {'lr': 0.0004306431733316817, 'samples': 19435008, 'steps': 37958, 'loss/train': 0.70161372423172}
-03/05/2022 10:05:07 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/05/2022 10:05:10 - INFO - codeparrot_training - Step 37959: {'lr': 0.00043063950476543563, 'samples': 19435520, 'steps': 37959, 'loss/train': 1.897818922996521}
-03/05/2022 10:05:13 - INFO - codeparrot_training - Step 37960: {'lr': 0.0004306358361177961, 'samples': 19436032, 'steps': 37960, 'loss/train': 1.259172797203064}
-03/05/2022 10:05:15 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/05/2022 10:05:18 - INFO - codeparrot_training - Step 37961: {'lr': 0.00043063216738876487, 'samples': 19436544, 'steps': 37961, 'loss/train': 2.1958703994750977}
-03/05/2022 10:05:22 - INFO - codeparrot_training - Step 37962: {'lr': 0.0004306284985783436, 'samples': 19437056, 'steps': 37962, 'loss/train': 1.7720119953155518}
-03/05/2022 10:05:24 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/05/2022 10:05:27 - INFO - codeparrot_training - Step 37963: {'lr': 0.00043062482968653394, 'samples': 19437568, 'steps': 37963, 'loss/train': 1.9559146165847778}
-03/05/2022 10:05:30 - INFO - codeparrot_training - Step 37964: {'lr': 0.00043062116071333745, 'samples': 19438080, 'steps': 37964, 'loss/train': 1.357301950454712}
-03/05/2022 10:05:32 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/05/2022 10:05:35 - INFO - codeparrot_training - Step 37965: {'lr': 0.0004306174916587559, 'samples': 19438592, 'steps': 37965, 'loss/train': 1.9595907926559448}
-03/05/2022 10:05:39 - INFO - codeparrot_training - Step 37966: {'lr': 0.0004306138225227909, 'samples': 19439104, 'steps': 37966, 'loss/train': 2.7268028259277344}
-03/05/2022 10:05:41 - INFO - codeparrot_training - Skipping example with length 519 (seq_length=1024)
-03/05/2022 10:05:44 - INFO - codeparrot_training - Step 37967: {'lr': 0.0004306101533054441, 'samples': 19439616, 'steps': 37967, 'loss/train': 1.7862026691436768}
-03/05/2022 10:05:47 - INFO - codeparrot_training - Step 37968: {'lr': 0.0004306064840067171, 'samples': 19440128, 'steps': 37968, 'loss/train': 1.9523568153381348}
-03/05/2022 10:05:49 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 10:05:52 - INFO - codeparrot_training - Step 37969: {'lr': 0.00043060281462661165, 'samples': 19440640, 'steps': 37969, 'loss/train': 0.8942475914955139}
-03/05/2022 10:05:56 - INFO - codeparrot_training - Step 37970: {'lr': 0.0004305991451651293, 'samples': 19441152, 'steps': 37970, 'loss/train': 1.7197656631469727}
-03/05/2022 10:05:57 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/05/2022 10:06:01 - INFO - codeparrot_training - Step 37971: {'lr': 0.00043059547562227185, 'samples': 19441664, 'steps': 37971, 'loss/train': 1.4768589735031128}
-03/05/2022 10:06:04 - INFO - codeparrot_training - Step 37972: {'lr': 0.0004305918059980408, 'samples': 19442176, 'steps': 37972, 'loss/train': 1.7680021524429321}
-03/05/2022 10:06:06 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/05/2022 10:06:09 - INFO - codeparrot_training - Step 37973: {'lr': 0.00043058813629243787, 'samples': 19442688, 'steps': 37973, 'loss/train': 1.9044512510299683}
-03/05/2022 10:06:12 - INFO - codeparrot_training - Step 37974: {'lr': 0.0004305844665054648, 'samples': 19443200, 'steps': 37974, 'loss/train': 1.1323875188827515}
-03/05/2022 10:06:14 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/05/2022 10:06:18 - INFO - codeparrot_training - Step 37975: {'lr': 0.00043058079663712304, 'samples': 19443712, 'steps': 37975, 'loss/train': 2.3119680881500244}
-03/05/2022 10:06:21 - INFO - codeparrot_training - Step 37976: {'lr': 0.00043057712668741443, 'samples': 19444224, 'steps': 37976, 'loss/train': 0.06984040141105652}
-03/05/2022 10:06:23 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/05/2022 10:06:26 - INFO - codeparrot_training - Step 37977: {'lr': 0.0004305734566563405, 'samples': 19444736, 'steps': 37977, 'loss/train': 0.8590648174285889}
-03/05/2022 10:06:30 - INFO - codeparrot_training - Step 37978: {'lr': 0.000430569786543903, 'samples': 19445248, 'steps': 37978, 'loss/train': 0.6823554039001465}
-03/05/2022 10:06:32 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/05/2022 10:06:35 - INFO - codeparrot_training - Step 37979: {'lr': 0.00043056611635010355, 'samples': 19445760, 'steps': 37979, 'loss/train': 1.363161325454712}
-03/05/2022 10:06:38 - INFO - codeparrot_training - Step 37980: {'lr': 0.00043056244607494375, 'samples': 19446272, 'steps': 37980, 'loss/train': 1.6660517454147339}
-03/05/2022 10:06:40 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/05/2022 10:06:43 - INFO - codeparrot_training - Step 37981: {'lr': 0.0004305587757184254, 'samples': 19446784, 'steps': 37981, 'loss/train': 0.1975853443145752}
-03/05/2022 10:06:46 - INFO - codeparrot_training - Step 37982: {'lr': 0.0004305551052805499, 'samples': 19447296, 'steps': 37982, 'loss/train': 1.9760558605194092}
-03/05/2022 10:06:48 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/05/2022 10:06:52 - INFO - codeparrot_training - Step 37983: {'lr': 0.0004305514347613191, 'samples': 19447808, 'steps': 37983, 'loss/train': 1.937135100364685}
-03/05/2022 10:06:55 - INFO - codeparrot_training - Step 37984: {'lr': 0.0004305477641607347, 'samples': 19448320, 'steps': 37984, 'loss/train': 1.763716220855713}
-03/05/2022 10:06:57 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/05/2022 10:07:00 - INFO - codeparrot_training - Step 37985: {'lr': 0.0004305440934787982, 'samples': 19448832, 'steps': 37985, 'loss/train': 0.0665673241019249}
-03/05/2022 10:07:03 - INFO - codeparrot_training - Step 37986: {'lr': 0.0004305404227155113, 'samples': 19449344, 'steps': 37986, 'loss/train': 1.5655131340026855}
-03/05/2022 10:07:05 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/05/2022 10:07:09 - INFO - codeparrot_training - Step 37987: {'lr': 0.0004305367518708757, 'samples': 19449856, 'steps': 37987, 'loss/train': 2.1082358360290527}
-03/05/2022 10:07:12 - INFO - codeparrot_training - Step 37988: {'lr': 0.000430533080944893, 'samples': 19450368, 'steps': 37988, 'loss/train': 1.0807193517684937}
-03/05/2022 10:07:14 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 10:07:17 - INFO - codeparrot_training - Step 37989: {'lr': 0.00043052940993756493, 'samples': 19450880, 'steps': 37989, 'loss/train': 1.4271621704101562}
-03/05/2022 10:07:20 - INFO - codeparrot_training - Step 37990: {'lr': 0.00043052573884889305, 'samples': 19451392, 'steps': 37990, 'loss/train': 1.86587655544281}
-03/05/2022 10:07:23 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/05/2022 10:07:26 - INFO - codeparrot_training - Step 37991: {'lr': 0.00043052206767887907, 'samples': 19451904, 'steps': 37991, 'loss/train': 0.9810808300971985}
-03/05/2022 10:07:29 - INFO - codeparrot_training - Step 37992: {'lr': 0.00043051839642752466, 'samples': 19452416, 'steps': 37992, 'loss/train': 1.541760802268982}
-03/05/2022 10:07:31 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/05/2022 10:07:34 - INFO - codeparrot_training - Step 37993: {'lr': 0.00043051472509483135, 'samples': 19452928, 'steps': 37993, 'loss/train': 1.4545832872390747}
-03/05/2022 10:07:37 - INFO - codeparrot_training - Step 37994: {'lr': 0.00043051105368080103, 'samples': 19453440, 'steps': 37994, 'loss/train': 0.8379783630371094}
-03/05/2022 10:07:39 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/05/2022 10:07:42 - INFO - codeparrot_training - Step 37995: {'lr': 0.00043050738218543505, 'samples': 19453952, 'steps': 37995, 'loss/train': 1.8295984268188477}
-03/05/2022 10:07:45 - INFO - codeparrot_training - Step 37996: {'lr': 0.00043050371060873537, 'samples': 19454464, 'steps': 37996, 'loss/train': 1.9095585346221924}
-03/05/2022 10:07:47 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/05/2022 10:07:51 - INFO - codeparrot_training - Step 37997: {'lr': 0.00043050003895070345, 'samples': 19454976, 'steps': 37997, 'loss/train': 1.7113313674926758}
-03/05/2022 10:07:54 - INFO - codeparrot_training - Step 37998: {'lr': 0.000430496367211341, 'samples': 19455488, 'steps': 37998, 'loss/train': 1.446597933769226}
-03/05/2022 10:07:55 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/05/2022 10:07:59 - INFO - codeparrot_training - Step 37999: {'lr': 0.00043049269539064967, 'samples': 19456000, 'steps': 37999, 'loss/train': 1.3205163478851318}
-03/05/2022 10:08:02 - INFO - codeparrot_training - Step 38000: {'lr': 0.0004304890234886311, 'samples': 19456512, 'steps': 38000, 'loss/train': 0.43644800782203674}
-03/05/2022 10:08:04 - INFO - codeparrot_training - Skipping example with length 156 (seq_length=1024)
-03/05/2022 10:08:08 - INFO - codeparrot_training - Step 38001: {'lr': 0.000430485351505287, 'samples': 19457024, 'steps': 38001, 'loss/train': 2.2119436264038086}
-03/05/2022 10:08:11 - INFO - codeparrot_training - Step 38002: {'lr': 0.000430481679440619, 'samples': 19457536, 'steps': 38002, 'loss/train': 1.445844054222107}
-03/05/2022 10:08:12 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 10:08:16 - INFO - codeparrot_training - Step 38003: {'lr': 0.0004304780072946287, 'samples': 19458048, 'steps': 38003, 'loss/train': 1.1881942749023438}
-03/05/2022 10:08:19 - INFO - codeparrot_training - Step 38004: {'lr': 0.00043047433506731783, 'samples': 19458560, 'steps': 38004, 'loss/train': 1.8692299127578735}
-03/05/2022 10:08:21 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/05/2022 10:08:25 - INFO - codeparrot_training - Step 38005: {'lr': 0.00043047066275868795, 'samples': 19459072, 'steps': 38005, 'loss/train': 1.516891360282898}
-03/05/2022 10:08:28 - INFO - codeparrot_training - Step 38006: {'lr': 0.0004304669903687408, 'samples': 19459584, 'steps': 38006, 'loss/train': 1.7022420167922974}
-03/05/2022 10:08:29 - INFO - codeparrot_training - Skipping example with length 39 (seq_length=1024)
-03/05/2022 10:08:33 - INFO - codeparrot_training - Step 38007: {'lr': 0.000430463317897478, 'samples': 19460096, 'steps': 38007, 'loss/train': 0.8942084312438965}
-03/05/2022 10:08:36 - INFO - codeparrot_training - Step 38008: {'lr': 0.0004304596453449012, 'samples': 19460608, 'steps': 38008, 'loss/train': 1.6661148071289062}
-03/05/2022 10:08:38 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/05/2022 10:08:42 - INFO - codeparrot_training - Step 38009: {'lr': 0.0004304559727110121, 'samples': 19461120, 'steps': 38009, 'loss/train': 0.599915087223053}
-03/05/2022 10:08:45 - INFO - codeparrot_training - Step 38010: {'lr': 0.0004304522999958124, 'samples': 19461632, 'steps': 38010, 'loss/train': 1.0640931129455566}
-03/05/2022 10:08:46 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 10:08:50 - INFO - codeparrot_training - Step 38011: {'lr': 0.00043044862719930356, 'samples': 19462144, 'steps': 38011, 'loss/train': 2.4148948192596436}
-03/05/2022 10:08:53 - INFO - codeparrot_training - Step 38012: {'lr': 0.0004304449543214874, 'samples': 19462656, 'steps': 38012, 'loss/train': 1.7904378175735474}
-03/05/2022 10:08:55 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 10:08:58 - INFO - codeparrot_training - Step 38013: {'lr': 0.0004304412813623655, 'samples': 19463168, 'steps': 38013, 'loss/train': 1.827587366104126}
-03/05/2022 10:09:02 - INFO - codeparrot_training - Step 38014: {'lr': 0.0004304376083219396, 'samples': 19463680, 'steps': 38014, 'loss/train': 2.2927942276000977}
-03/05/2022 10:09:03 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/05/2022 10:09:07 - INFO - codeparrot_training - Step 38015: {'lr': 0.00043043393520021125, 'samples': 19464192, 'steps': 38015, 'loss/train': 2.10367488861084}
-03/05/2022 10:09:10 - INFO - codeparrot_training - Step 38016: {'lr': 0.0004304302619971822, 'samples': 19464704, 'steps': 38016, 'loss/train': 2.2790417671203613}
-03/05/2022 10:09:12 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/05/2022 10:09:15 - INFO - codeparrot_training - Step 38017: {'lr': 0.000430426588712854, 'samples': 19465216, 'steps': 38017, 'loss/train': 1.7684578895568848}
-03/05/2022 10:09:18 - INFO - codeparrot_training - Step 38018: {'lr': 0.0004304229153472283, 'samples': 19465728, 'steps': 38018, 'loss/train': 1.3615593910217285}
-03/05/2022 10:09:20 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/05/2022 10:09:24 - INFO - codeparrot_training - Step 38019: {'lr': 0.0004304192419003069, 'samples': 19466240, 'steps': 38019, 'loss/train': 1.5945992469787598}
-03/05/2022 10:09:27 - INFO - codeparrot_training - Step 38020: {'lr': 0.0004304155683720914, 'samples': 19466752, 'steps': 38020, 'loss/train': 1.4171319007873535}
-03/05/2022 10:09:29 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/05/2022 10:09:32 - INFO - codeparrot_training - Step 38021: {'lr': 0.0004304118947625835, 'samples': 19467264, 'steps': 38021, 'loss/train': 1.90484619140625}
-03/05/2022 10:09:36 - INFO - codeparrot_training - Step 38022: {'lr': 0.00043040822107178465, 'samples': 19467776, 'steps': 38022, 'loss/train': 1.8489912748336792}
-03/05/2022 10:09:37 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/05/2022 10:09:41 - INFO - codeparrot_training - Step 38023: {'lr': 0.0004304045472996966, 'samples': 19468288, 'steps': 38023, 'loss/train': 1.2445861101150513}
-03/05/2022 10:09:44 - INFO - codeparrot_training - Step 38024: {'lr': 0.0004304008734463212, 'samples': 19468800, 'steps': 38024, 'loss/train': 1.8997186422348022}
-03/05/2022 10:09:46 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 10:09:49 - INFO - codeparrot_training - Step 38025: {'lr': 0.00043039719951165986, 'samples': 19469312, 'steps': 38025, 'loss/train': 1.5180245637893677}
-03/05/2022 10:09:52 - INFO - codeparrot_training - Step 38026: {'lr': 0.0004303935254957143, 'samples': 19469824, 'steps': 38026, 'loss/train': 1.5014299154281616}
-03/05/2022 10:09:54 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/05/2022 10:09:58 - INFO - codeparrot_training - Step 38027: {'lr': 0.0004303898513984863, 'samples': 19470336, 'steps': 38027, 'loss/train': 2.1215882301330566}
-03/05/2022 10:10:01 - INFO - codeparrot_training - Step 38028: {'lr': 0.0004303861772199773, 'samples': 19470848, 'steps': 38028, 'loss/train': 1.5143530368804932}
-03/05/2022 10:10:04 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/05/2022 10:10:07 - INFO - codeparrot_training - Step 38029: {'lr': 0.00043038250296018916, 'samples': 19471360, 'steps': 38029, 'loss/train': 1.985036015510559}
-03/05/2022 10:10:10 - INFO - codeparrot_training - Step 38030: {'lr': 0.00043037882861912344, 'samples': 19471872, 'steps': 38030, 'loss/train': 1.5242153406143188}
-03/05/2022 10:10:13 - INFO - codeparrot_training - Step 38031: {'lr': 0.00043037515419678174, 'samples': 19472384, 'steps': 38031, 'loss/train': 1.4357268810272217}
-03/05/2022 10:10:13 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/05/2022 10:10:18 - INFO - codeparrot_training - Step 38032: {'lr': 0.0004303714796931658, 'samples': 19472896, 'steps': 38032, 'loss/train': 0.2413451075553894}
-03/05/2022 10:10:21 - INFO - codeparrot_training - Step 38033: {'lr': 0.0004303678051082773, 'samples': 19473408, 'steps': 38033, 'loss/train': 2.067565679550171}
-03/05/2022 10:10:21 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/05/2022 10:10:27 - INFO - codeparrot_training - Step 38034: {'lr': 0.00043036413044211786, 'samples': 19473920, 'steps': 38034, 'loss/train': 1.5207383632659912}
-03/05/2022 10:10:30 - INFO - codeparrot_training - Step 38035: {'lr': 0.0004303604556946891, 'samples': 19474432, 'steps': 38035, 'loss/train': 1.1377378702163696}
-03/05/2022 10:10:30 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 10:10:35 - INFO - codeparrot_training - Step 38036: {'lr': 0.00043035678086599265, 'samples': 19474944, 'steps': 38036, 'loss/train': 1.7207690477371216}
-03/05/2022 10:10:38 - INFO - codeparrot_training - Step 38037: {'lr': 0.00043035310595603026, 'samples': 19475456, 'steps': 38037, 'loss/train': 1.878233790397644}
-03/05/2022 10:10:39 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/05/2022 10:10:44 - INFO - codeparrot_training - Step 38038: {'lr': 0.00043034943096480357, 'samples': 19475968, 'steps': 38038, 'loss/train': 1.380743145942688}
-03/05/2022 10:10:47 - INFO - codeparrot_training - Step 38039: {'lr': 0.0004303457558923142, 'samples': 19476480, 'steps': 38039, 'loss/train': 1.5217046737670898}
-03/05/2022 10:10:48 - INFO - codeparrot_training - Skipping example with length 5 (seq_length=1024)
-03/05/2022 10:10:52 - INFO - codeparrot_training - Step 38040: {'lr': 0.00043034208073856374, 'samples': 19476992, 'steps': 38040, 'loss/train': 2.0249781608581543}
-03/05/2022 10:10:55 - INFO - codeparrot_training - Step 38041: {'lr': 0.000430338405503554, 'samples': 19477504, 'steps': 38041, 'loss/train': 2.0000715255737305}
-03/05/2022 10:10:56 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/05/2022 10:11:01 - INFO - codeparrot_training - Step 38042: {'lr': 0.00043033473018728655, 'samples': 19478016, 'steps': 38042, 'loss/train': 1.8912651538848877}
-03/05/2022 10:11:04 - INFO - codeparrot_training - Step 38043: {'lr': 0.00043033105478976306, 'samples': 19478528, 'steps': 38043, 'loss/train': 1.4762508869171143}
-03/05/2022 10:11:04 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/05/2022 10:11:09 - INFO - codeparrot_training - Step 38044: {'lr': 0.00043032737931098517, 'samples': 19479040, 'steps': 38044, 'loss/train': 2.386420965194702}
-03/05/2022 10:11:12 - INFO - codeparrot_training - Step 38045: {'lr': 0.0004303237037509545, 'samples': 19479552, 'steps': 38045, 'loss/train': 0.9421160817146301}
-03/05/2022 10:11:13 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 10:11:17 - INFO - codeparrot_training - Step 38046: {'lr': 0.0004303200281096727, 'samples': 19480064, 'steps': 38046, 'loss/train': 2.018425464630127}
-03/05/2022 10:11:21 - INFO - codeparrot_training - Step 38047: {'lr': 0.00043031635238714163, 'samples': 19480576, 'steps': 38047, 'loss/train': 1.9391707181930542}
-03/05/2022 10:11:21 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/05/2022 10:11:26 - INFO - codeparrot_training - Step 38048: {'lr': 0.00043031267658336276, 'samples': 19481088, 'steps': 38048, 'loss/train': 1.9107561111450195}
-03/05/2022 10:11:29 - INFO - codeparrot_training - Step 38049: {'lr': 0.00043030900069833774, 'samples': 19481600, 'steps': 38049, 'loss/train': 1.5236433744430542}
-03/05/2022 10:11:34 - INFO - codeparrot_training - Step 38050: {'lr': 0.0004303053247320683, 'samples': 19482112, 'steps': 38050, 'loss/train': 1.9727452993392944}
-03/05/2022 10:11:37 - INFO - codeparrot_training - Step 38051: {'lr': 0.000430301648684556, 'samples': 19482624, 'steps': 38051, 'loss/train': 1.4848424196243286}
-03/05/2022 10:11:38 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/05/2022 10:11:43 - INFO - codeparrot_training - Step 38052: {'lr': 0.0004302979725558026, 'samples': 19483136, 'steps': 38052, 'loss/train': 1.338963270187378}
-03/05/2022 10:11:46 - INFO - codeparrot_training - Step 38053: {'lr': 0.0004302942963458097, 'samples': 19483648, 'steps': 38053, 'loss/train': 1.6960563659667969}
-03/05/2022 10:11:46 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/05/2022 10:11:51 - INFO - codeparrot_training - Step 38054: {'lr': 0.00043029062005457897, 'samples': 19484160, 'steps': 38054, 'loss/train': 1.7523781061172485}
-03/05/2022 10:11:54 - INFO - codeparrot_training - Step 38055: {'lr': 0.00043028694368211216, 'samples': 19484672, 'steps': 38055, 'loss/train': 1.1035007238388062}
-03/05/2022 10:11:55 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/05/2022 10:12:00 - INFO - codeparrot_training - Step 38056: {'lr': 0.00043028326722841073, 'samples': 19485184, 'steps': 38056, 'loss/train': 1.5697715282440186}
-03/05/2022 10:12:03 - INFO - codeparrot_training - Step 38057: {'lr': 0.00043027959069347644, 'samples': 19485696, 'steps': 38057, 'loss/train': 1.475107192993164}
-03/05/2022 10:12:03 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/05/2022 10:12:08 - INFO - codeparrot_training - Step 38058: {'lr': 0.00043027591407731106, 'samples': 19486208, 'steps': 38058, 'loss/train': 2.2208268642425537}
-03/05/2022 10:12:11 - INFO - codeparrot_training - Step 38059: {'lr': 0.000430272237379916, 'samples': 19486720, 'steps': 38059, 'loss/train': 2.2744526863098145}
-03/05/2022 10:12:11 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/05/2022 10:12:16 - INFO - codeparrot_training - Step 38060: {'lr': 0.00043026856060129307, 'samples': 19487232, 'steps': 38060, 'loss/train': 2.045475959777832}
-03/05/2022 10:12:20 - INFO - codeparrot_training - Step 38061: {'lr': 0.00043026488374144404, 'samples': 19487744, 'steps': 38061, 'loss/train': 1.6731675863265991}
-03/05/2022 10:12:20 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/05/2022 10:12:25 - INFO - codeparrot_training - Step 38062: {'lr': 0.00043026120680037026, 'samples': 19488256, 'steps': 38062, 'loss/train': 2.1057446002960205}
-03/05/2022 10:12:28 - INFO - codeparrot_training - Step 38063: {'lr': 0.00043025752977807365, 'samples': 19488768, 'steps': 38063, 'loss/train': 1.4114596843719482}
-03/05/2022 10:12:28 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/05/2022 10:12:33 - INFO - codeparrot_training - Step 38064: {'lr': 0.00043025385267455576, 'samples': 19489280, 'steps': 38064, 'loss/train': 1.6377941370010376}
-03/05/2022 10:12:37 - INFO - codeparrot_training - Step 38065: {'lr': 0.0004302501754898183, 'samples': 19489792, 'steps': 38065, 'loss/train': 1.6610007286071777}
-03/05/2022 10:12:37 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/05/2022 10:12:42 - INFO - codeparrot_training - Step 38066: {'lr': 0.00043024649822386284, 'samples': 19490304, 'steps': 38066, 'loss/train': 0.8098395466804504}
-03/05/2022 10:12:45 - INFO - codeparrot_training - Step 38067: {'lr': 0.00043024282087669106, 'samples': 19490816, 'steps': 38067, 'loss/train': 0.6418740749359131}
-03/05/2022 10:12:45 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/05/2022 10:12:50 - INFO - codeparrot_training - Step 38068: {'lr': 0.0004302391434483048, 'samples': 19491328, 'steps': 38068, 'loss/train': 1.94647216796875}
-03/05/2022 10:12:53 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/05/2022 10:12:56 - INFO - codeparrot_training - Step 38069: {'lr': 0.00043023546593870543, 'samples': 19491840, 'steps': 38069, 'loss/train': 1.2817102670669556}
-03/05/2022 10:12:59 - INFO - codeparrot_training - Step 38070: {'lr': 0.00043023178834789477, 'samples': 19492352, 'steps': 38070, 'loss/train': 1.5265451669692993}
-03/05/2022 10:13:02 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/05/2022 10:13:04 - INFO - codeparrot_training - Step 38071: {'lr': 0.0004302281106758745, 'samples': 19492864, 'steps': 38071, 'loss/train': 2.166799783706665}
-03/05/2022 10:13:07 - INFO - codeparrot_training - Step 38072: {'lr': 0.00043022443292264613, 'samples': 19493376, 'steps': 38072, 'loss/train': 2.004671573638916}
-03/05/2022 10:13:10 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/05/2022 10:13:12 - INFO - codeparrot_training - Step 38073: {'lr': 0.00043022075508821145, 'samples': 19493888, 'steps': 38073, 'loss/train': 1.847042441368103}
-03/05/2022 10:13:16 - INFO - codeparrot_training - Step 38074: {'lr': 0.0004302170771725721, 'samples': 19494400, 'steps': 38074, 'loss/train': 1.8174740076065063}
-03/05/2022 10:13:18 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/05/2022 10:13:21 - INFO - codeparrot_training - Step 38075: {'lr': 0.0004302133991757297, 'samples': 19494912, 'steps': 38075, 'loss/train': 1.4159934520721436}
-03/05/2022 10:13:24 - INFO - codeparrot_training - Step 38076: {'lr': 0.000430209721097686, 'samples': 19495424, 'steps': 38076, 'loss/train': 2.125657558441162}
-03/05/2022 10:13:27 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/05/2022 10:13:29 - INFO - codeparrot_training - Step 38077: {'lr': 0.00043020604293844244, 'samples': 19495936, 'steps': 38077, 'loss/train': 1.245300054550171}
-03/05/2022 10:13:32 - INFO - codeparrot_training - Step 38078: {'lr': 0.0004302023646980009, 'samples': 19496448, 'steps': 38078, 'loss/train': 1.9822871685028076}
-03/05/2022 10:13:35 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/05/2022 10:13:38 - INFO - codeparrot_training - Step 38079: {'lr': 0.00043019868637636294, 'samples': 19496960, 'steps': 38079, 'loss/train': 1.8194363117218018}
-03/05/2022 10:13:41 - INFO - codeparrot_training - Step 38080: {'lr': 0.0004301950079735302, 'samples': 19497472, 'steps': 38080, 'loss/train': 2.4744622707366943}
-03/05/2022 10:13:43 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/05/2022 10:13:46 - INFO - codeparrot_training - Step 38081: {'lr': 0.00043019132948950443, 'samples': 19497984, 'steps': 38081, 'loss/train': 1.3772854804992676}
-03/05/2022 10:13:49 - INFO - codeparrot_training - Step 38082: {'lr': 0.0004301876509242872, 'samples': 19498496, 'steps': 38082, 'loss/train': 1.797467827796936}
-03/05/2022 10:13:51 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/05/2022 10:13:55 - INFO - codeparrot_training - Step 38083: {'lr': 0.0004301839722778802, 'samples': 19499008, 'steps': 38083, 'loss/train': 1.9844164848327637}
-03/05/2022 10:13:58 - INFO - codeparrot_training - Step 38084: {'lr': 0.0004301802935502851, 'samples': 19499520, 'steps': 38084, 'loss/train': 1.7103025913238525}
-03/05/2022 10:14:00 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/05/2022 10:14:03 - INFO - codeparrot_training - Step 38085: {'lr': 0.00043017661474150347, 'samples': 19500032, 'steps': 38085, 'loss/train': 2.346693515777588}
-03/05/2022 10:14:06 - INFO - codeparrot_training - Step 38086: {'lr': 0.0004301729358515371, 'samples': 19500544, 'steps': 38086, 'loss/train': 1.3317945003509521}
-03/05/2022 10:14:08 - INFO - codeparrot_training - Skipping example with length 973 (seq_length=1024)
-03/05/2022 10:14:12 - INFO - codeparrot_training - Step 38087: {'lr': 0.00043016925688038756, 'samples': 19501056, 'steps': 38087, 'loss/train': 1.9408619403839111}
-03/05/2022 10:14:15 - INFO - codeparrot_training - Step 38088: {'lr': 0.00043016557782805655, 'samples': 19501568, 'steps': 38088, 'loss/train': 1.227591872215271}
-03/05/2022 10:14:17 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 10:14:20 - INFO - codeparrot_training - Step 38089: {'lr': 0.0004301618986945457, 'samples': 19502080, 'steps': 38089, 'loss/train': 1.296087384223938}
-03/05/2022 10:14:23 - INFO - codeparrot_training - Step 38090: {'lr': 0.0004301582194798567, 'samples': 19502592, 'steps': 38090, 'loss/train': 1.4857016801834106}
-03/05/2022 10:14:25 - INFO - codeparrot_training - Skipping example with length 999 (seq_length=1024)
-03/05/2022 10:14:28 - INFO - codeparrot_training - Step 38091: {'lr': 0.00043015454018399115, 'samples': 19503104, 'steps': 38091, 'loss/train': 1.1398205757141113}
-03/05/2022 10:14:32 - INFO - codeparrot_training - Step 38092: {'lr': 0.00043015086080695075, 'samples': 19503616, 'steps': 38092, 'loss/train': 1.7836833000183105}
-03/05/2022 10:14:33 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/05/2022 10:14:37 - INFO - codeparrot_training - Step 38093: {'lr': 0.0004301471813487372, 'samples': 19504128, 'steps': 38093, 'loss/train': 2.334439277648926}
-03/05/2022 10:14:40 - INFO - codeparrot_training - Step 38094: {'lr': 0.00043014350180935207, 'samples': 19504640, 'steps': 38094, 'loss/train': 1.0010154247283936}
-03/05/2022 10:14:42 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 10:14:45 - INFO - codeparrot_training - Step 38095: {'lr': 0.0004301398221887971, 'samples': 19505152, 'steps': 38095, 'loss/train': 1.8115538358688354}
-03/05/2022 10:14:49 - INFO - codeparrot_training - Step 38096: {'lr': 0.0004301361424870739, 'samples': 19505664, 'steps': 38096, 'loss/train': 2.4744937419891357}
-03/05/2022 10:14:50 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/05/2022 10:14:54 - INFO - codeparrot_training - Step 38097: {'lr': 0.00043013246270418406, 'samples': 19506176, 'steps': 38097, 'loss/train': 1.8701446056365967}
-03/05/2022 10:14:57 - INFO - codeparrot_training - Step 38098: {'lr': 0.00043012878284012936, 'samples': 19506688, 'steps': 38098, 'loss/train': 0.5405595302581787}
-03/05/2022 10:14:59 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/05/2022 10:15:02 - INFO - codeparrot_training - Step 38099: {'lr': 0.0004301251028949114, 'samples': 19507200, 'steps': 38099, 'loss/train': 1.9475120306015015}
-03/05/2022 10:15:06 - INFO - codeparrot_training - Step 38100: {'lr': 0.00043012142286853185, 'samples': 19507712, 'steps': 38100, 'loss/train': 2.3827965259552}
-03/05/2022 10:15:07 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/05/2022 10:15:11 - INFO - codeparrot_training - Step 38101: {'lr': 0.00043011774276099235, 'samples': 19508224, 'steps': 38101, 'loss/train': 0.4602147042751312}
-03/05/2022 10:15:14 - INFO - codeparrot_training - Step 38102: {'lr': 0.0004301140625722946, 'samples': 19508736, 'steps': 38102, 'loss/train': 1.29271399974823}
-03/05/2022 10:15:16 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 10:15:19 - INFO - codeparrot_training - Step 38103: {'lr': 0.0004301103823024403, 'samples': 19509248, 'steps': 38103, 'loss/train': 0.7816430330276489}
-03/05/2022 10:15:23 - INFO - codeparrot_training - Step 38104: {'lr': 0.0004301067019514309, 'samples': 19509760, 'steps': 38104, 'loss/train': 1.677298903465271}
-03/05/2022 10:15:24 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/05/2022 10:15:28 - INFO - codeparrot_training - Step 38105: {'lr': 0.0004301030215192683, 'samples': 19510272, 'steps': 38105, 'loss/train': 1.1386585235595703}
-03/05/2022 10:15:31 - INFO - codeparrot_training - Step 38106: {'lr': 0.00043009934100595403, 'samples': 19510784, 'steps': 38106, 'loss/train': 2.16165828704834}
-03/05/2022 10:15:33 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/05/2022 10:15:36 - INFO - codeparrot_training - Step 38107: {'lr': 0.00043009566041148973, 'samples': 19511296, 'steps': 38107, 'loss/train': 2.050820827484131}
-03/05/2022 10:15:40 - INFO - codeparrot_training - Step 38108: {'lr': 0.0004300919797358772, 'samples': 19511808, 'steps': 38108, 'loss/train': 2.3823142051696777}
-03/05/2022 10:15:41 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/05/2022 10:15:45 - INFO - codeparrot_training - Step 38109: {'lr': 0.00043008829897911796, 'samples': 19512320, 'steps': 38109, 'loss/train': 1.2240188121795654}
-03/05/2022 10:15:48 - INFO - codeparrot_training - Step 38110: {'lr': 0.0004300846181412137, 'samples': 19512832, 'steps': 38110, 'loss/train': 1.2134724855422974}
-03/05/2022 10:15:50 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 10:15:53 - INFO - codeparrot_training - Step 38111: {'lr': 0.00043008093722216603, 'samples': 19513344, 'steps': 38111, 'loss/train': 1.4284002780914307}
-03/05/2022 10:15:56 - INFO - codeparrot_training - Step 38112: {'lr': 0.00043007725622197675, 'samples': 19513856, 'steps': 38112, 'loss/train': 2.0763683319091797}
-03/05/2022 10:15:58 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/05/2022 10:16:02 - INFO - codeparrot_training - Step 38113: {'lr': 0.0004300735751406474, 'samples': 19514368, 'steps': 38113, 'loss/train': 1.9253026247024536}
-03/05/2022 10:16:05 - INFO - codeparrot_training - Step 38114: {'lr': 0.00043006989397817967, 'samples': 19514880, 'steps': 38114, 'loss/train': 1.320953369140625}
-03/05/2022 10:16:06 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/05/2022 10:16:10 - INFO - codeparrot_training - Step 38115: {'lr': 0.00043006621273457523, 'samples': 19515392, 'steps': 38115, 'loss/train': 1.3291610479354858}
-03/05/2022 10:16:13 - INFO - codeparrot_training - Step 38116: {'lr': 0.0004300625314098358, 'samples': 19515904, 'steps': 38116, 'loss/train': 1.5463697910308838}
-03/05/2022 10:16:15 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/05/2022 10:16:19 - INFO - codeparrot_training - Step 38117: {'lr': 0.0004300588500039629, 'samples': 19516416, 'steps': 38117, 'loss/train': 1.4944273233413696}
-03/05/2022 10:16:22 - INFO - codeparrot_training - Step 38118: {'lr': 0.0004300551685169583, 'samples': 19516928, 'steps': 38118, 'loss/train': 1.9958827495574951}
-03/05/2022 10:16:23 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 10:16:27 - INFO - codeparrot_training - Step 38119: {'lr': 0.0004300514869488236, 'samples': 19517440, 'steps': 38119, 'loss/train': 1.5339068174362183}
-03/05/2022 10:16:30 - INFO - codeparrot_training - Step 38120: {'lr': 0.00043004780529956046, 'samples': 19517952, 'steps': 38120, 'loss/train': 1.806308388710022}
-03/05/2022 10:16:31 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/05/2022 10:16:35 - INFO - codeparrot_training - Step 38121: {'lr': 0.00043004412356917055, 'samples': 19518464, 'steps': 38121, 'loss/train': 2.0159950256347656}
-03/05/2022 10:16:38 - INFO - codeparrot_training - Step 38122: {'lr': 0.0004300404417576556, 'samples': 19518976, 'steps': 38122, 'loss/train': 1.9803131818771362}
-03/05/2022 10:16:40 - INFO - codeparrot_training - Skipping example with length 405 (seq_length=1024)
-03/05/2022 10:16:44 - INFO - codeparrot_training - Step 38123: {'lr': 0.00043003675986501717, 'samples': 19519488, 'steps': 38123, 'loss/train': 1.88717782497406}
-03/05/2022 10:16:47 - INFO - codeparrot_training - Step 38124: {'lr': 0.00043003307789125694, 'samples': 19520000, 'steps': 38124, 'loss/train': 2.2744219303131104}
-03/05/2022 10:16:48 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/05/2022 10:16:52 - INFO - codeparrot_training - Step 38125: {'lr': 0.0004300293958363766, 'samples': 19520512, 'steps': 38125, 'loss/train': 1.4435806274414062}
-03/05/2022 10:16:55 - INFO - codeparrot_training - Step 38126: {'lr': 0.00043002571370037777, 'samples': 19521024, 'steps': 38126, 'loss/train': 1.696510910987854}
-03/05/2022 10:16:57 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/05/2022 10:17:01 - INFO - codeparrot_training - Step 38127: {'lr': 0.00043002203148326213, 'samples': 19521536, 'steps': 38127, 'loss/train': 1.5090446472167969}
-03/05/2022 10:17:04 - INFO - codeparrot_training - Step 38128: {'lr': 0.0004300183491850314, 'samples': 19522048, 'steps': 38128, 'loss/train': 2.0730791091918945}
-03/05/2022 10:17:05 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/05/2022 10:17:10 - INFO - codeparrot_training - Step 38129: {'lr': 0.0004300146668056871, 'samples': 19522560, 'steps': 38129, 'loss/train': 1.605167031288147}
-03/05/2022 10:17:13 - INFO - codeparrot_training - Step 38130: {'lr': 0.00043001098434523107, 'samples': 19523072, 'steps': 38130, 'loss/train': 2.2721474170684814}
-03/05/2022 10:17:15 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/05/2022 10:17:18 - INFO - codeparrot_training - Step 38131: {'lr': 0.0004300073018036648, 'samples': 19523584, 'steps': 38131, 'loss/train': 2.1520752906799316}
-03/05/2022 10:17:21 - INFO - codeparrot_training - Step 38132: {'lr': 0.00043000361918099, 'samples': 19524096, 'steps': 38132, 'loss/train': 1.0600160360336304}
-03/05/2022 10:17:23 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/05/2022 10:17:26 - INFO - codeparrot_training - Step 38133: {'lr': 0.00042999993647720836, 'samples': 19524608, 'steps': 38133, 'loss/train': 1.5030423402786255}
-03/05/2022 10:17:30 - INFO - codeparrot_training - Step 38134: {'lr': 0.0004299962536923215, 'samples': 19525120, 'steps': 38134, 'loss/train': 1.732623815536499}
-03/05/2022 10:17:31 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/05/2022 10:17:35 - INFO - codeparrot_training - Step 38135: {'lr': 0.0004299925708263312, 'samples': 19525632, 'steps': 38135, 'loss/train': 1.343214988708496}
-03/05/2022 10:17:38 - INFO - codeparrot_training - Step 38136: {'lr': 0.00042998888787923895, 'samples': 19526144, 'steps': 38136, 'loss/train': 1.5132626295089722}
-03/05/2022 10:17:40 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/05/2022 10:17:43 - INFO - codeparrot_training - Step 38137: {'lr': 0.0004299852048510465, 'samples': 19526656, 'steps': 38137, 'loss/train': 1.7135881185531616}
-03/05/2022 10:17:46 - INFO - codeparrot_training - Step 38138: {'lr': 0.00042998152174175555, 'samples': 19527168, 'steps': 38138, 'loss/train': 1.5525445938110352}
-03/05/2022 10:17:48 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/05/2022 10:17:52 - INFO - codeparrot_training - Step 38139: {'lr': 0.0004299778385513676, 'samples': 19527680, 'steps': 38139, 'loss/train': 2.096250534057617}
-03/05/2022 10:17:55 - INFO - codeparrot_training - Step 38140: {'lr': 0.0004299741552798845, 'samples': 19528192, 'steps': 38140, 'loss/train': 0.9714369773864746}
-03/05/2022 10:17:56 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/05/2022 10:18:00 - INFO - codeparrot_training - Step 38141: {'lr': 0.0004299704719273078, 'samples': 19528704, 'steps': 38141, 'loss/train': 1.9438979625701904}
-03/05/2022 10:18:03 - INFO - codeparrot_training - Step 38142: {'lr': 0.00042996678849363914, 'samples': 19529216, 'steps': 38142, 'loss/train': 1.6587756872177124}
-03/05/2022 10:18:05 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 10:18:09 - INFO - codeparrot_training - Step 38143: {'lr': 0.00042996310497888025, 'samples': 19529728, 'steps': 38143, 'loss/train': 0.6900030374526978}
-03/05/2022 10:18:12 - INFO - codeparrot_training - Step 38144: {'lr': 0.00042995942138303274, 'samples': 19530240, 'steps': 38144, 'loss/train': 1.8848631381988525}
-03/05/2022 10:18:13 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/05/2022 10:18:17 - INFO - codeparrot_training - Step 38145: {'lr': 0.0004299557377060983, 'samples': 19530752, 'steps': 38145, 'loss/train': 1.169919490814209}
-03/05/2022 10:18:21 - INFO - codeparrot_training - Step 38146: {'lr': 0.00042995205394807864, 'samples': 19531264, 'steps': 38146, 'loss/train': 0.8233879804611206}
-03/05/2022 10:18:23 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/05/2022 10:18:26 - INFO - codeparrot_training - Step 38147: {'lr': 0.00042994837010897524, 'samples': 19531776, 'steps': 38147, 'loss/train': 2.076493501663208}
-03/05/2022 10:18:29 - INFO - codeparrot_training - Step 38148: {'lr': 0.00042994468618879, 'samples': 19532288, 'steps': 38148, 'loss/train': 2.4107954502105713}
-03/05/2022 10:18:32 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/05/2022 10:18:35 - INFO - codeparrot_training - Step 38149: {'lr': 0.0004299410021875244, 'samples': 19532800, 'steps': 38149, 'loss/train': 1.5858122110366821}
-03/05/2022 10:18:38 - INFO - codeparrot_training - Step 38150: {'lr': 0.00042993731810518025, 'samples': 19533312, 'steps': 38150, 'loss/train': 1.7968353033065796}
-03/05/2022 10:18:40 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/05/2022 10:18:43 - INFO - codeparrot_training - Step 38151: {'lr': 0.00042993363394175897, 'samples': 19533824, 'steps': 38151, 'loss/train': 1.3285233974456787}
-03/05/2022 10:18:46 - INFO - codeparrot_training - Step 38152: {'lr': 0.0004299299496972625, 'samples': 19534336, 'steps': 38152, 'loss/train': 2.783716917037964}
-03/05/2022 10:18:49 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 10:18:51 - INFO - codeparrot_training - Step 38153: {'lr': 0.0004299262653716923, 'samples': 19534848, 'steps': 38153, 'loss/train': 1.533878207206726}
-03/05/2022 10:18:55 - INFO - codeparrot_training - Step 38154: {'lr': 0.0004299225809650501, 'samples': 19535360, 'steps': 38154, 'loss/train': 1.8411775827407837}
-03/05/2022 10:18:57 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/05/2022 10:19:00 - INFO - codeparrot_training - Step 38155: {'lr': 0.0004299188964773376, 'samples': 19535872, 'steps': 38155, 'loss/train': 1.5124545097351074}
-03/05/2022 10:19:03 - INFO - codeparrot_training - Step 38156: {'lr': 0.0004299152119085564, 'samples': 19536384, 'steps': 38156, 'loss/train': 1.3971705436706543}
-03/05/2022 10:19:06 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/05/2022 10:19:08 - INFO - codeparrot_training - Step 38157: {'lr': 0.0004299115272587082, 'samples': 19536896, 'steps': 38157, 'loss/train': 2.054316520690918}
-03/05/2022 10:19:11 - INFO - codeparrot_training - Step 38158: {'lr': 0.0004299078425277947, 'samples': 19537408, 'steps': 38158, 'loss/train': 1.35747230052948}
-03/05/2022 10:19:14 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/05/2022 10:19:17 - INFO - codeparrot_training - Step 38159: {'lr': 0.00042990415771581734, 'samples': 19537920, 'steps': 38159, 'loss/train': 1.604402780532837}
-03/05/2022 10:19:20 - INFO - codeparrot_training - Step 38160: {'lr': 0.0004299004728227781, 'samples': 19538432, 'steps': 38160, 'loss/train': 1.2720932960510254}
-03/05/2022 10:19:23 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/05/2022 10:19:25 - INFO - codeparrot_training - Step 38161: {'lr': 0.0004298967878486784, 'samples': 19538944, 'steps': 38161, 'loss/train': 1.8828601837158203}
-03/05/2022 10:19:28 - INFO - codeparrot_training - Step 38162: {'lr': 0.00042989310279352, 'samples': 19539456, 'steps': 38162, 'loss/train': 1.9576854705810547}
-03/05/2022 10:19:31 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/05/2022 10:19:34 - INFO - codeparrot_training - Step 38163: {'lr': 0.0004298894176573046, 'samples': 19539968, 'steps': 38163, 'loss/train': 2.1857919692993164}
-03/05/2022 10:19:37 - INFO - codeparrot_training - Step 38164: {'lr': 0.0004298857324400337, 'samples': 19540480, 'steps': 38164, 'loss/train': 1.766544222831726}
-03/05/2022 10:19:39 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/05/2022 10:19:42 - INFO - codeparrot_training - Step 38165: {'lr': 0.0004298820471417091, 'samples': 19540992, 'steps': 38165, 'loss/train': 2.026407480239868}
-03/05/2022 10:19:45 - INFO - codeparrot_training - Step 38166: {'lr': 0.00042987836176233246, 'samples': 19541504, 'steps': 38166, 'loss/train': 1.0265092849731445}
-03/05/2022 10:19:48 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 10:19:51 - INFO - codeparrot_training - Step 38167: {'lr': 0.0004298746763019054, 'samples': 19542016, 'steps': 38167, 'loss/train': 1.5174959897994995}
-03/05/2022 10:19:54 - INFO - codeparrot_training - Step 38168: {'lr': 0.0004298709907604296, 'samples': 19542528, 'steps': 38168, 'loss/train': 0.5158788561820984}
-03/05/2022 10:19:56 - INFO - codeparrot_training - Skipping example with length 982 (seq_length=1024)
-03/05/2022 10:19:59 - INFO - codeparrot_training - Step 38169: {'lr': 0.0004298673051379066, 'samples': 19543040, 'steps': 38169, 'loss/train': 1.688212513923645}
-03/05/2022 10:20:02 - INFO - codeparrot_training - Step 38170: {'lr': 0.0004298636194343383, 'samples': 19543552, 'steps': 38170, 'loss/train': 1.5990475416183472}
-03/05/2022 10:20:05 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/05/2022 10:20:08 - INFO - codeparrot_training - Step 38171: {'lr': 0.0004298599336497262, 'samples': 19544064, 'steps': 38171, 'loss/train': 2.0844388008117676}
-03/05/2022 10:20:11 - INFO - codeparrot_training - Step 38172: {'lr': 0.00042985624778407196, 'samples': 19544576, 'steps': 38172, 'loss/train': 1.901390552520752}
-03/05/2022 10:20:13 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 10:20:16 - INFO - codeparrot_training - Step 38173: {'lr': 0.00042985256183737723, 'samples': 19545088, 'steps': 38173, 'loss/train': 1.5261445045471191}
-03/05/2022 10:20:19 - INFO - codeparrot_training - Step 38174: {'lr': 0.00042984887580964376, 'samples': 19545600, 'steps': 38174, 'loss/train': 2.038256883621216}
-03/05/2022 10:20:22 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/05/2022 10:20:25 - INFO - codeparrot_training - Step 38175: {'lr': 0.00042984518970087316, 'samples': 19546112, 'steps': 38175, 'loss/train': 1.355778455734253}
-03/05/2022 10:20:28 - INFO - codeparrot_training - Step 38176: {'lr': 0.0004298415035110671, 'samples': 19546624, 'steps': 38176, 'loss/train': 2.02291202545166}
-03/05/2022 10:20:31 - INFO - codeparrot_training - Step 38177: {'lr': 0.00042983781724022723, 'samples': 19547136, 'steps': 38177, 'loss/train': 0.4312288165092468}
-03/05/2022 10:20:31 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/05/2022 10:20:36 - INFO - codeparrot_training - Step 38178: {'lr': 0.0004298341308883552, 'samples': 19547648, 'steps': 38178, 'loss/train': 1.4607990980148315}
-03/05/2022 10:20:40 - INFO - codeparrot_training - Step 38179: {'lr': 0.0004298304444554527, 'samples': 19548160, 'steps': 38179, 'loss/train': 1.7812511920928955}
-03/05/2022 10:20:40 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 10:20:45 - INFO - codeparrot_training - Step 38180: {'lr': 0.00042982675794152135, 'samples': 19548672, 'steps': 38180, 'loss/train': 1.5163365602493286}
-03/05/2022 10:20:48 - INFO - codeparrot_training - Step 38181: {'lr': 0.0004298230713465629, 'samples': 19549184, 'steps': 38181, 'loss/train': 0.7158980965614319}
-03/05/2022 10:20:48 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/05/2022 10:20:53 - INFO - codeparrot_training - Step 38182: {'lr': 0.00042981938467057893, 'samples': 19549696, 'steps': 38182, 'loss/train': 1.9785288572311401}
-03/05/2022 10:20:56 - INFO - codeparrot_training - Step 38183: {'lr': 0.0004298156979135711, 'samples': 19550208, 'steps': 38183, 'loss/train': 1.6510062217712402}
-03/05/2022 10:20:56 - INFO - codeparrot_training - Skipping example with length 117 (seq_length=1024)
-03/05/2022 10:21:01 - INFO - codeparrot_training - Step 38184: {'lr': 0.000429812011075541, 'samples': 19550720, 'steps': 38184, 'loss/train': 2.0987019538879395}
-03/05/2022 10:21:05 - INFO - codeparrot_training - Step 38185: {'lr': 0.0004298083241564905, 'samples': 19551232, 'steps': 38185, 'loss/train': 0.8264381289482117}
-03/05/2022 10:21:05 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/05/2022 10:21:10 - INFO - codeparrot_training - Step 38186: {'lr': 0.00042980463715642115, 'samples': 19551744, 'steps': 38186, 'loss/train': 1.7903589010238647}
-03/05/2022 10:21:14 - INFO - codeparrot_training - Step 38187: {'lr': 0.0004298009500753346, 'samples': 19552256, 'steps': 38187, 'loss/train': 3.2278077602386475}
-03/05/2022 10:21:15 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/05/2022 10:21:19 - INFO - codeparrot_training - Step 38188: {'lr': 0.00042979726291323246, 'samples': 19552768, 'steps': 38188, 'loss/train': 1.6065139770507812}
-03/05/2022 10:21:22 - INFO - codeparrot_training - Step 38189: {'lr': 0.00042979357567011643, 'samples': 19553280, 'steps': 38189, 'loss/train': 0.9445589184761047}
-03/05/2022 10:21:23 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/05/2022 10:21:27 - INFO - codeparrot_training - Step 38190: {'lr': 0.0004297898883459883, 'samples': 19553792, 'steps': 38190, 'loss/train': 2.360586643218994}
-03/05/2022 10:21:31 - INFO - codeparrot_training - Step 38191: {'lr': 0.00042978620094084955, 'samples': 19554304, 'steps': 38191, 'loss/train': 1.8124327659606934}
-03/05/2022 10:21:32 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/05/2022 10:21:36 - INFO - codeparrot_training - Step 38192: {'lr': 0.00042978251345470185, 'samples': 19554816, 'steps': 38192, 'loss/train': 1.7657251358032227}
-03/05/2022 10:21:39 - INFO - codeparrot_training - Step 38193: {'lr': 0.000429778825887547, 'samples': 19555328, 'steps': 38193, 'loss/train': 2.0249710083007812}
-03/05/2022 10:21:40 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/05/2022 10:21:44 - INFO - codeparrot_training - Step 38194: {'lr': 0.00042977513823938665, 'samples': 19555840, 'steps': 38194, 'loss/train': 1.8225529193878174}
-03/05/2022 10:21:48 - INFO - codeparrot_training - Step 38195: {'lr': 0.00042977145051022224, 'samples': 19556352, 'steps': 38195, 'loss/train': 1.400360345840454}
-03/05/2022 10:21:49 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/05/2022 10:21:53 - INFO - codeparrot_training - Step 38196: {'lr': 0.0004297677627000557, 'samples': 19556864, 'steps': 38196, 'loss/train': 2.1804728507995605}
-03/05/2022 10:21:56 - INFO - codeparrot_training - Step 38197: {'lr': 0.0004297640748088886, 'samples': 19557376, 'steps': 38197, 'loss/train': 1.9173269271850586}
-03/05/2022 10:21:57 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/05/2022 10:22:01 - INFO - codeparrot_training - Step 38198: {'lr': 0.0004297603868367225, 'samples': 19557888, 'steps': 38198, 'loss/train': 0.14692805707454681}
-03/05/2022 10:22:04 - INFO - codeparrot_training - Step 38199: {'lr': 0.00042975669878355917, 'samples': 19558400, 'steps': 38199, 'loss/train': 1.710673213005066}
-03/05/2022 10:22:06 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/05/2022 10:22:10 - INFO - codeparrot_training - Step 38200: {'lr': 0.00042975301064940026, 'samples': 19558912, 'steps': 38200, 'loss/train': 2.148225784301758}
-03/05/2022 10:22:13 - INFO - codeparrot_training - Step 38201: {'lr': 0.00042974932243424743, 'samples': 19559424, 'steps': 38201, 'loss/train': 1.3002058267593384}
-03/05/2022 10:22:14 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/05/2022 10:22:18 - INFO - codeparrot_training - Step 38202: {'lr': 0.0004297456341381023, 'samples': 19559936, 'steps': 38202, 'loss/train': 1.3662004470825195}
-03/05/2022 10:22:22 - INFO - codeparrot_training - Step 38203: {'lr': 0.0004297419457609666, 'samples': 19560448, 'steps': 38203, 'loss/train': 1.8153409957885742}
-03/05/2022 10:22:22 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 10:22:27 - INFO - codeparrot_training - Step 38204: {'lr': 0.0004297382573028419, 'samples': 19560960, 'steps': 38204, 'loss/train': 2.665128707885742}
-03/05/2022 10:22:30 - INFO - codeparrot_training - Step 38205: {'lr': 0.0004297345687637299, 'samples': 19561472, 'steps': 38205, 'loss/train': 2.403273344039917}
-03/05/2022 10:22:31 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/05/2022 10:22:35 - INFO - codeparrot_training - Step 38206: {'lr': 0.00042973088014363237, 'samples': 19561984, 'steps': 38206, 'loss/train': 2.2563891410827637}
-03/05/2022 10:22:38 - INFO - codeparrot_training - Step 38207: {'lr': 0.0004297271914425508, 'samples': 19562496, 'steps': 38207, 'loss/train': 1.6115695238113403}
-03/05/2022 10:22:39 - INFO - codeparrot_training - Skipping example with length 297 (seq_length=1024)
-03/05/2022 10:22:44 - INFO - codeparrot_training - Step 38208: {'lr': 0.00042972350266048693, 'samples': 19563008, 'steps': 38208, 'loss/train': 2.0249693393707275}
-03/05/2022 10:22:47 - INFO - codeparrot_training - Step 38209: {'lr': 0.0004297198137974425, 'samples': 19563520, 'steps': 38209, 'loss/train': 1.094769835472107}
-03/05/2022 10:22:48 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/05/2022 10:22:52 - INFO - codeparrot_training - Step 38210: {'lr': 0.00042971612485341896, 'samples': 19564032, 'steps': 38210, 'loss/train': 3.092541456222534}
-03/05/2022 10:22:55 - INFO - codeparrot_training - Step 38211: {'lr': 0.00042971243582841823, 'samples': 19564544, 'steps': 38211, 'loss/train': 1.446276068687439}
-03/05/2022 10:22:56 - INFO - codeparrot_training - Skipping example with length 7 (seq_length=1024)
-03/05/2022 10:23:01 - INFO - codeparrot_training - Step 38212: {'lr': 0.0004297087467224418, 'samples': 19565056, 'steps': 38212, 'loss/train': 1.038641333580017}
-03/05/2022 10:23:04 - INFO - codeparrot_training - Step 38213: {'lr': 0.0004297050575354914, 'samples': 19565568, 'steps': 38213, 'loss/train': 1.6101264953613281}
-03/05/2022 10:23:04 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/05/2022 10:23:09 - INFO - codeparrot_training - Step 38214: {'lr': 0.0004297013682675687, 'samples': 19566080, 'steps': 38214, 'loss/train': 2.107543706893921}
-03/05/2022 10:23:12 - INFO - codeparrot_training - Step 38215: {'lr': 0.0004296976789186753, 'samples': 19566592, 'steps': 38215, 'loss/train': 1.2800267934799194}
-03/05/2022 10:23:13 - INFO - codeparrot_training - Skipping example with length 1010 (seq_length=1024)
-03/05/2022 10:23:17 - INFO - codeparrot_training - Step 38216: {'lr': 0.00042969398948881286, 'samples': 19567104, 'steps': 38216, 'loss/train': 2.109590530395508}
-03/05/2022 10:23:21 - INFO - codeparrot_training - Step 38217: {'lr': 0.00042969029997798314, 'samples': 19567616, 'steps': 38217, 'loss/train': 0.638293445110321}
-03/05/2022 10:23:21 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/05/2022 10:23:26 - INFO - codeparrot_training - Step 38218: {'lr': 0.00042968661038618775, 'samples': 19568128, 'steps': 38218, 'loss/train': 1.866135597229004}
-03/05/2022 10:23:29 - INFO - codeparrot_training - Step 38219: {'lr': 0.0004296829207134283, 'samples': 19568640, 'steps': 38219, 'loss/train': 1.626603126525879}
-03/05/2022 10:23:30 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/05/2022 10:23:35 - INFO - codeparrot_training - Step 38220: {'lr': 0.0004296792309597065, 'samples': 19569152, 'steps': 38220, 'loss/train': 1.5221202373504639}
-03/05/2022 10:23:38 - INFO - codeparrot_training - Step 38221: {'lr': 0.00042967554112502404, 'samples': 19569664, 'steps': 38221, 'loss/train': 1.7357590198516846}
-03/05/2022 10:23:39 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/05/2022 10:23:43 - INFO - codeparrot_training - Step 38222: {'lr': 0.00042967185120938256, 'samples': 19570176, 'steps': 38222, 'loss/train': 1.359134554862976}
-03/05/2022 10:23:46 - INFO - codeparrot_training - Step 38223: {'lr': 0.00042966816121278365, 'samples': 19570688, 'steps': 38223, 'loss/train': 1.3038883209228516}
-03/05/2022 10:23:47 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/05/2022 10:23:51 - INFO - codeparrot_training - Step 38224: {'lr': 0.0004296644711352291, 'samples': 19571200, 'steps': 38224, 'loss/train': 1.785362958908081}
-03/05/2022 10:23:55 - INFO - codeparrot_training - Step 38225: {'lr': 0.0004296607809767205, 'samples': 19571712, 'steps': 38225, 'loss/train': 2.0929696559906006}
-03/05/2022 10:23:56 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/05/2022 10:24:00 - INFO - codeparrot_training - Step 38226: {'lr': 0.00042965709073725957, 'samples': 19572224, 'steps': 38226, 'loss/train': 2.1142191886901855}
-03/05/2022 10:24:03 - INFO - codeparrot_training - Step 38227: {'lr': 0.00042965340041684785, 'samples': 19572736, 'steps': 38227, 'loss/train': 2.672612190246582}
-03/05/2022 10:24:04 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 10:24:08 - INFO - codeparrot_training - Step 38228: {'lr': 0.00042964971001548715, 'samples': 19573248, 'steps': 38228, 'loss/train': 2.0597496032714844}
-03/05/2022 10:24:11 - INFO - codeparrot_training - Step 38229: {'lr': 0.00042964601953317895, 'samples': 19573760, 'steps': 38229, 'loss/train': 1.2374943494796753}
-03/05/2022 10:24:12 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/05/2022 10:24:17 - INFO - codeparrot_training - Step 38230: {'lr': 0.0004296423289699252, 'samples': 19574272, 'steps': 38230, 'loss/train': 1.5440378189086914}
-03/05/2022 10:24:20 - INFO - codeparrot_training - Step 38231: {'lr': 0.00042963863832572727, 'samples': 19574784, 'steps': 38231, 'loss/train': 2.032487154006958}
-03/05/2022 10:24:20 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 10:24:25 - INFO - codeparrot_training - Step 38232: {'lr': 0.0004296349476005869, 'samples': 19575296, 'steps': 38232, 'loss/train': 1.525044322013855}
-03/05/2022 10:24:28 - INFO - codeparrot_training - Step 38233: {'lr': 0.0004296312567945059, 'samples': 19575808, 'steps': 38233, 'loss/train': 1.6452269554138184}
-03/05/2022 10:24:30 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/05/2022 10:24:34 - INFO - codeparrot_training - Step 38234: {'lr': 0.0004296275659074858, 'samples': 19576320, 'steps': 38234, 'loss/train': 1.5290149450302124}
-03/05/2022 10:24:37 - INFO - codeparrot_training - Step 38235: {'lr': 0.00042962387493952823, 'samples': 19576832, 'steps': 38235, 'loss/train': 1.7374461889266968}
-03/05/2022 10:24:40 - INFO - codeparrot_training - Step 38236: {'lr': 0.00042962018389063495, 'samples': 19577344, 'steps': 38236, 'loss/train': 1.8442904949188232}
-03/05/2022 10:24:41 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/05/2022 10:24:46 - INFO - codeparrot_training - Step 38237: {'lr': 0.0004296164927608076, 'samples': 19577856, 'steps': 38237, 'loss/train': 2.214616537094116}
-03/05/2022 10:24:49 - INFO - codeparrot_training - Step 38238: {'lr': 0.00042961280155004786, 'samples': 19578368, 'steps': 38238, 'loss/train': 2.2062056064605713}
-03/05/2022 10:24:49 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 10:24:54 - INFO - codeparrot_training - Step 38239: {'lr': 0.0004296091102583573, 'samples': 19578880, 'steps': 38239, 'loss/train': 2.2183449268341064}
-03/05/2022 10:24:57 - INFO - codeparrot_training - Step 38240: {'lr': 0.0004296054188857377, 'samples': 19579392, 'steps': 38240, 'loss/train': 2.102518081665039}
-03/05/2022 10:24:58 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/05/2022 10:25:03 - INFO - codeparrot_training - Step 38241: {'lr': 0.0004296017274321906, 'samples': 19579904, 'steps': 38241, 'loss/train': 0.6505129933357239}
-03/05/2022 10:25:06 - INFO - codeparrot_training - Step 38242: {'lr': 0.0004295980358977178, 'samples': 19580416, 'steps': 38242, 'loss/train': 1.6552292108535767}
-03/05/2022 10:25:06 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/05/2022 10:25:11 - INFO - codeparrot_training - Step 38243: {'lr': 0.0004295943442823209, 'samples': 19580928, 'steps': 38243, 'loss/train': 2.0696794986724854}
-03/05/2022 10:25:14 - INFO - codeparrot_training - Step 38244: {'lr': 0.0004295906525860015, 'samples': 19581440, 'steps': 38244, 'loss/train': 1.598634123802185}
-03/05/2022 10:25:14 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/05/2022 10:25:20 - INFO - codeparrot_training - Step 38245: {'lr': 0.00042958696080876136, 'samples': 19581952, 'steps': 38245, 'loss/train': 2.4667675495147705}
-03/05/2022 10:25:23 - INFO - codeparrot_training - Step 38246: {'lr': 0.00042958326895060206, 'samples': 19582464, 'steps': 38246, 'loss/train': 1.4917136430740356}
-03/05/2022 10:25:23 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 10:25:28 - INFO - codeparrot_training - Step 38247: {'lr': 0.0004295795770115254, 'samples': 19582976, 'steps': 38247, 'loss/train': 2.1322760581970215}
-03/05/2022 10:25:31 - INFO - codeparrot_training - Step 38248: {'lr': 0.0004295758849915329, 'samples': 19583488, 'steps': 38248, 'loss/train': 1.540297508239746}
-03/05/2022 10:25:31 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/05/2022 10:25:37 - INFO - codeparrot_training - Step 38249: {'lr': 0.00042957219289062635, 'samples': 19584000, 'steps': 38249, 'loss/train': 2.0867114067077637}
-03/05/2022 10:25:39 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/05/2022 10:25:42 - INFO - codeparrot_training - Step 38250: {'lr': 0.0004295685007088072, 'samples': 19584512, 'steps': 38250, 'loss/train': 1.8317899703979492}
-03/05/2022 10:25:45 - INFO - codeparrot_training - Step 38251: {'lr': 0.00042956480844607734, 'samples': 19585024, 'steps': 38251, 'loss/train': 1.069628357887268}
-03/05/2022 10:25:48 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/05/2022 10:25:50 - INFO - codeparrot_training - Step 38252: {'lr': 0.00042956111610243833, 'samples': 19585536, 'steps': 38252, 'loss/train': 1.6579670906066895}
-03/05/2022 10:25:54 - INFO - codeparrot_training - Step 38253: {'lr': 0.0004295574236778919, 'samples': 19586048, 'steps': 38253, 'loss/train': 1.2710665464401245}
-03/05/2022 10:25:56 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 10:25:59 - INFO - codeparrot_training - Step 38254: {'lr': 0.00042955373117243954, 'samples': 19586560, 'steps': 38254, 'loss/train': 1.9285047054290771}
-03/05/2022 10:26:02 - INFO - codeparrot_training - Step 38255: {'lr': 0.0004295500385860832, 'samples': 19587072, 'steps': 38255, 'loss/train': 2.205305337905884}
-03/05/2022 10:26:04 - INFO - codeparrot_training - Skipping example with length 870 (seq_length=1024)
-03/05/2022 10:26:07 - INFO - codeparrot_training - Step 38256: {'lr': 0.0004295463459188243, 'samples': 19587584, 'steps': 38256, 'loss/train': 1.8881876468658447}
-03/05/2022 10:26:10 - INFO - codeparrot_training - Step 38257: {'lr': 0.00042954265317066457, 'samples': 19588096, 'steps': 38257, 'loss/train': 1.8493458032608032}
-03/05/2022 10:26:13 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/05/2022 10:26:16 - INFO - codeparrot_training - Step 38258: {'lr': 0.0004295389603416057, 'samples': 19588608, 'steps': 38258, 'loss/train': 1.1372871398925781}
-03/05/2022 10:26:19 - INFO - codeparrot_training - Step 38259: {'lr': 0.0004295352674316494, 'samples': 19589120, 'steps': 38259, 'loss/train': 2.3027684688568115}
-03/05/2022 10:26:21 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/05/2022 10:26:24 - INFO - codeparrot_training - Step 38260: {'lr': 0.0004295315744407972, 'samples': 19589632, 'steps': 38260, 'loss/train': 1.7547498941421509}
-03/05/2022 10:26:27 - INFO - codeparrot_training - Step 38261: {'lr': 0.0004295278813690509, 'samples': 19590144, 'steps': 38261, 'loss/train': 0.9920597672462463}
-03/05/2022 10:26:30 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/05/2022 10:26:33 - INFO - codeparrot_training - Step 38262: {'lr': 0.0004295241882164121, 'samples': 19590656, 'steps': 38262, 'loss/train': 2.0222606658935547}
-03/05/2022 10:26:36 - INFO - codeparrot_training - Step 38263: {'lr': 0.0004295204949828825, 'samples': 19591168, 'steps': 38263, 'loss/train': 0.5052517056465149}
-03/05/2022 10:26:38 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/05/2022 10:26:41 - INFO - codeparrot_training - Step 38264: {'lr': 0.0004295168016684636, 'samples': 19591680, 'steps': 38264, 'loss/train': 2.0428943634033203}
-03/05/2022 10:26:44 - INFO - codeparrot_training - Step 38265: {'lr': 0.0004295131082731574, 'samples': 19592192, 'steps': 38265, 'loss/train': 2.049250841140747}
-03/05/2022 10:26:47 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/05/2022 10:26:50 - INFO - codeparrot_training - Step 38266: {'lr': 0.0004295094147969652, 'samples': 19592704, 'steps': 38266, 'loss/train': 2.2261714935302734}
-03/05/2022 10:26:53 - INFO - codeparrot_training - Step 38267: {'lr': 0.0004295057212398889, 'samples': 19593216, 'steps': 38267, 'loss/train': 2.0380611419677734}
-03/05/2022 10:26:55 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/05/2022 10:26:58 - INFO - codeparrot_training - Step 38268: {'lr': 0.00042950202760193003, 'samples': 19593728, 'steps': 38268, 'loss/train': 1.4096884727478027}
-03/05/2022 10:27:01 - INFO - codeparrot_training - Step 38269: {'lr': 0.0004294983338830904, 'samples': 19594240, 'steps': 38269, 'loss/train': 1.6578811407089233}
-03/05/2022 10:27:04 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/05/2022 10:27:06 - INFO - codeparrot_training - Step 38270: {'lr': 0.0004294946400833716, 'samples': 19594752, 'steps': 38270, 'loss/train': 1.9715553522109985}
-03/05/2022 10:27:10 - INFO - codeparrot_training - Step 38271: {'lr': 0.0004294909462027752, 'samples': 19595264, 'steps': 38271, 'loss/train': 2.314692258834839}
-03/05/2022 10:27:12 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/05/2022 10:27:15 - INFO - codeparrot_training - Step 38272: {'lr': 0.000429487252241303, 'samples': 19595776, 'steps': 38272, 'loss/train': 0.666504442691803}
-03/05/2022 10:27:18 - INFO - codeparrot_training - Step 38273: {'lr': 0.00042948355819895655, 'samples': 19596288, 'steps': 38273, 'loss/train': 1.4557350873947144}
-03/05/2022 10:27:21 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/05/2022 10:27:23 - INFO - codeparrot_training - Step 38274: {'lr': 0.0004294798640757377, 'samples': 19596800, 'steps': 38274, 'loss/train': 1.6731847524642944}
-03/05/2022 10:27:27 - INFO - codeparrot_training - Step 38275: {'lr': 0.00042947616987164787, 'samples': 19597312, 'steps': 38275, 'loss/train': 0.686585545539856}
-03/05/2022 10:27:29 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/05/2022 10:27:32 - INFO - codeparrot_training - Step 38276: {'lr': 0.00042947247558668887, 'samples': 19597824, 'steps': 38276, 'loss/train': 2.279735803604126}
-03/05/2022 10:27:35 - INFO - codeparrot_training - Step 38277: {'lr': 0.00042946878122086243, 'samples': 19598336, 'steps': 38277, 'loss/train': 1.514905333518982}
-03/05/2022 10:27:37 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/05/2022 10:27:40 - INFO - codeparrot_training - Step 38278: {'lr': 0.00042946508677417007, 'samples': 19598848, 'steps': 38278, 'loss/train': 2.3469104766845703}
-03/05/2022 10:27:43 - INFO - codeparrot_training - Step 38279: {'lr': 0.0004294613922466135, 'samples': 19599360, 'steps': 38279, 'loss/train': 2.026970386505127}
-03/05/2022 10:27:46 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/05/2022 10:27:49 - INFO - codeparrot_training - Step 38280: {'lr': 0.0004294576976381944, 'samples': 19599872, 'steps': 38280, 'loss/train': 0.8599165678024292}
-03/05/2022 10:27:52 - INFO - codeparrot_training - Step 38281: {'lr': 0.00042945400294891445, 'samples': 19600384, 'steps': 38281, 'loss/train': 2.026340961456299}
-03/05/2022 10:27:54 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/05/2022 10:27:57 - INFO - codeparrot_training - Step 38282: {'lr': 0.0004294503081787753, 'samples': 19600896, 'steps': 38282, 'loss/train': 2.039402723312378}
-03/05/2022 10:28:00 - INFO - codeparrot_training - Step 38283: {'lr': 0.0004294466133277786, 'samples': 19601408, 'steps': 38283, 'loss/train': 1.7858246564865112}
-03/05/2022 10:28:03 - INFO - codeparrot_training - Step 38284: {'lr': 0.00042944291839592597, 'samples': 19601920, 'steps': 38284, 'loss/train': 1.2764191627502441}
-03/05/2022 10:28:03 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/05/2022 10:28:09 - INFO - codeparrot_training - Step 38285: {'lr': 0.0004294392233832192, 'samples': 19602432, 'steps': 38285, 'loss/train': 1.5788668394088745}
-03/05/2022 10:28:12 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/05/2022 10:28:14 - INFO - codeparrot_training - Step 38286: {'lr': 0.0004294355282896599, 'samples': 19602944, 'steps': 38286, 'loss/train': 1.8752431869506836}
-03/05/2022 10:28:17 - INFO - codeparrot_training - Step 38287: {'lr': 0.00042943183311524967, 'samples': 19603456, 'steps': 38287, 'loss/train': 1.8779851198196411}
-03/05/2022 10:28:20 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/05/2022 10:28:22 - INFO - codeparrot_training - Step 38288: {'lr': 0.0004294281378599902, 'samples': 19603968, 'steps': 38288, 'loss/train': 1.5274173021316528}
-03/05/2022 10:28:26 - INFO - codeparrot_training - Step 38289: {'lr': 0.00042942444252388323, 'samples': 19604480, 'steps': 38289, 'loss/train': 1.2565371990203857}
-03/05/2022 10:28:28 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/05/2022 10:28:31 - INFO - codeparrot_training - Step 38290: {'lr': 0.0004294207471069304, 'samples': 19604992, 'steps': 38290, 'loss/train': 1.9365266561508179}
-03/05/2022 10:28:34 - INFO - codeparrot_training - Step 38291: {'lr': 0.0004294170516091332, 'samples': 19605504, 'steps': 38291, 'loss/train': 1.2148891687393188}
-03/05/2022 10:28:37 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 10:28:39 - INFO - codeparrot_training - Step 38292: {'lr': 0.0004294133560304936, 'samples': 19606016, 'steps': 38292, 'loss/train': 1.6216410398483276}
-03/05/2022 10:28:43 - INFO - codeparrot_training - Step 38293: {'lr': 0.00042940966037101314, 'samples': 19606528, 'steps': 38293, 'loss/train': 2.0366060733795166}
-03/05/2022 10:28:45 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 10:28:48 - INFO - codeparrot_training - Step 38294: {'lr': 0.00042940596463069336, 'samples': 19607040, 'steps': 38294, 'loss/train': 0.9560814499855042}
-03/05/2022 10:28:51 - INFO - codeparrot_training - Step 38295: {'lr': 0.00042940226880953605, 'samples': 19607552, 'steps': 38295, 'loss/train': 2.7686333656311035}
-03/05/2022 10:28:54 - INFO - codeparrot_training - Step 38296: {'lr': 0.0004293985729075428, 'samples': 19608064, 'steps': 38296, 'loss/train': 1.8770229816436768}
-03/05/2022 10:28:54 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/05/2022 10:29:00 - INFO - codeparrot_training - Step 38297: {'lr': 0.00042939487692471534, 'samples': 19608576, 'steps': 38297, 'loss/train': 1.306634783744812}
-03/05/2022 10:29:03 - INFO - codeparrot_training - Step 38298: {'lr': 0.0004293911808610554, 'samples': 19609088, 'steps': 38298, 'loss/train': 1.466132402420044}
-03/05/2022 10:29:03 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/05/2022 10:29:08 - INFO - codeparrot_training - Step 38299: {'lr': 0.0004293874847165645, 'samples': 19609600, 'steps': 38299, 'loss/train': 1.5298848152160645}
-03/05/2022 10:29:11 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/05/2022 10:29:13 - INFO - codeparrot_training - Step 38300: {'lr': 0.0004293837884912444, 'samples': 19610112, 'steps': 38300, 'loss/train': 2.3378098011016846}
-03/05/2022 10:29:17 - INFO - codeparrot_training - Step 38301: {'lr': 0.00042938009218509667, 'samples': 19610624, 'steps': 38301, 'loss/train': 0.7045778036117554}
-03/05/2022 10:29:20 - INFO - codeparrot_training - Step 38302: {'lr': 0.00042937639579812304, 'samples': 19611136, 'steps': 38302, 'loss/train': 1.4344048500061035}
-03/05/2022 10:29:20 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/05/2022 10:29:25 - INFO - codeparrot_training - Step 38303: {'lr': 0.0004293726993303252, 'samples': 19611648, 'steps': 38303, 'loss/train': 1.5720622539520264}
-03/05/2022 10:29:28 - INFO - codeparrot_training - Step 38304: {'lr': 0.0004293690027817048, 'samples': 19612160, 'steps': 38304, 'loss/train': 1.8113373517990112}
-03/05/2022 10:29:28 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/05/2022 10:29:34 - INFO - codeparrot_training - Step 38305: {'lr': 0.00042936530615226355, 'samples': 19612672, 'steps': 38305, 'loss/train': 1.8836528062820435}
-03/05/2022 10:29:37 - INFO - codeparrot_training - Step 38306: {'lr': 0.00042936160944200295, 'samples': 19613184, 'steps': 38306, 'loss/train': 1.197272777557373}
-03/05/2022 10:29:37 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 10:29:42 - INFO - codeparrot_training - Step 38307: {'lr': 0.00042935791265092483, 'samples': 19613696, 'steps': 38307, 'loss/train': 1.8337063789367676}
-03/05/2022 10:29:45 - INFO - codeparrot_training - Step 38308: {'lr': 0.0004293542157790308, 'samples': 19614208, 'steps': 38308, 'loss/train': 1.720285177230835}
-03/05/2022 10:29:45 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 10:29:51 - INFO - codeparrot_training - Step 38309: {'lr': 0.00042935051882632245, 'samples': 19614720, 'steps': 38309, 'loss/train': 1.3284389972686768}
-03/05/2022 10:29:54 - INFO - codeparrot_training - Step 38310: {'lr': 0.0004293468217928017, 'samples': 19615232, 'steps': 38310, 'loss/train': 1.8689329624176025}
-03/05/2022 10:29:54 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/05/2022 10:29:59 - INFO - codeparrot_training - Step 38311: {'lr': 0.0004293431246784699, 'samples': 19615744, 'steps': 38311, 'loss/train': 1.2637889385223389}
-03/05/2022 10:30:02 - INFO - codeparrot_training - Step 38312: {'lr': 0.0004293394274833289, 'samples': 19616256, 'steps': 38312, 'loss/train': 1.6548107862472534}
-03/05/2022 10:30:03 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/05/2022 10:30:07 - INFO - codeparrot_training - Step 38313: {'lr': 0.0004293357302073804, 'samples': 19616768, 'steps': 38313, 'loss/train': 1.5874419212341309}
-03/05/2022 10:30:11 - INFO - codeparrot_training - Step 38314: {'lr': 0.00042933203285062585, 'samples': 19617280, 'steps': 38314, 'loss/train': 1.9115970134735107}
-03/05/2022 10:30:11 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/05/2022 10:30:16 - INFO - codeparrot_training - Step 38315: {'lr': 0.00042932833541306704, 'samples': 19617792, 'steps': 38315, 'loss/train': 1.9426833391189575}
-03/05/2022 10:30:19 - INFO - codeparrot_training - Step 38316: {'lr': 0.0004293246378947058, 'samples': 19618304, 'steps': 38316, 'loss/train': 1.7364038228988647}
-03/05/2022 10:30:19 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 10:30:24 - INFO - codeparrot_training - Step 38317: {'lr': 0.00042932094029554354, 'samples': 19618816, 'steps': 38317, 'loss/train': 1.488792896270752}
-03/05/2022 10:30:27 - INFO - codeparrot_training - Step 38318: {'lr': 0.00042931724261558205, 'samples': 19619328, 'steps': 38318, 'loss/train': 1.5331729650497437}
-03/05/2022 10:30:27 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/05/2022 10:30:33 - INFO - codeparrot_training - Step 38319: {'lr': 0.000429313544854823, 'samples': 19619840, 'steps': 38319, 'loss/train': 1.2963359355926514}
-03/05/2022 10:30:36 - INFO - codeparrot_training - Step 38320: {'lr': 0.00042930984701326796, 'samples': 19620352, 'steps': 38320, 'loss/train': 1.8010696172714233}
-03/05/2022 10:30:36 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/05/2022 10:30:41 - INFO - codeparrot_training - Step 38321: {'lr': 0.0004293061490909187, 'samples': 19620864, 'steps': 38321, 'loss/train': 1.9893141984939575}
-03/05/2022 10:30:44 - INFO - codeparrot_training - Step 38322: {'lr': 0.0004293024510877769, 'samples': 19621376, 'steps': 38322, 'loss/train': 1.6426589488983154}
-03/05/2022 10:30:44 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/05/2022 10:30:50 - INFO - codeparrot_training - Step 38323: {'lr': 0.00042929875300384417, 'samples': 19621888, 'steps': 38323, 'loss/train': 0.11464940011501312}
-03/05/2022 10:30:53 - INFO - codeparrot_training - Step 38324: {'lr': 0.0004292950548391222, 'samples': 19622400, 'steps': 38324, 'loss/train': 1.034578800201416}
-03/05/2022 10:30:53 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/05/2022 10:30:58 - INFO - codeparrot_training - Step 38325: {'lr': 0.00042929135659361265, 'samples': 19622912, 'steps': 38325, 'loss/train': 1.389309048652649}
-03/05/2022 10:31:01 - INFO - codeparrot_training - Step 38326: {'lr': 0.0004292876582673171, 'samples': 19623424, 'steps': 38326, 'loss/train': 1.9555165767669678}
-03/05/2022 10:31:01 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/05/2022 10:31:06 - INFO - codeparrot_training - Step 38327: {'lr': 0.0004292839598602374, 'samples': 19623936, 'steps': 38327, 'loss/train': 1.489870548248291}
-03/05/2022 10:31:09 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/05/2022 10:31:12 - INFO - codeparrot_training - Step 38328: {'lr': 0.000429280261372375, 'samples': 19624448, 'steps': 38328, 'loss/train': 1.5003352165222168}
-03/05/2022 10:31:15 - INFO - codeparrot_training - Step 38329: {'lr': 0.00042927656280373176, 'samples': 19624960, 'steps': 38329, 'loss/train': 6.536158561706543}
-03/05/2022 10:31:18 - INFO - codeparrot_training - Step 38330: {'lr': 0.00042927286415430933, 'samples': 19625472, 'steps': 38330, 'loss/train': 1.9757002592086792}
-03/05/2022 10:31:20 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/05/2022 10:31:23 - INFO - codeparrot_training - Step 38331: {'lr': 0.0004292691654241092, 'samples': 19625984, 'steps': 38331, 'loss/train': 2.4778330326080322}
-03/05/2022 10:31:27 - INFO - codeparrot_training - Step 38332: {'lr': 0.00042926546661313313, 'samples': 19626496, 'steps': 38332, 'loss/train': 1.966078519821167}
-03/05/2022 10:31:28 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/05/2022 10:31:32 - INFO - codeparrot_training - Step 38333: {'lr': 0.00042926176772138295, 'samples': 19627008, 'steps': 38333, 'loss/train': 4.749517440795898}
-03/05/2022 10:31:35 - INFO - codeparrot_training - Step 38334: {'lr': 0.0004292580687488601, 'samples': 19627520, 'steps': 38334, 'loss/train': 1.9996683597564697}
-03/05/2022 10:31:36 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/05/2022 10:31:40 - INFO - codeparrot_training - Step 38335: {'lr': 0.0004292543696955663, 'samples': 19628032, 'steps': 38335, 'loss/train': 2.3912599086761475}
-03/05/2022 10:31:43 - INFO - codeparrot_training - Step 38336: {'lr': 0.00042925067056150324, 'samples': 19628544, 'steps': 38336, 'loss/train': 1.6615673303604126}
-03/05/2022 10:31:45 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/05/2022 10:31:49 - INFO - codeparrot_training - Step 38337: {'lr': 0.0004292469713466727, 'samples': 19629056, 'steps': 38337, 'loss/train': 1.4507231712341309}
-03/05/2022 10:31:52 - INFO - codeparrot_training - Step 38338: {'lr': 0.00042924327205107616, 'samples': 19629568, 'steps': 38338, 'loss/train': 4.09354305267334}
-03/05/2022 10:31:53 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/05/2022 10:31:57 - INFO - codeparrot_training - Step 38339: {'lr': 0.00042923957267471536, 'samples': 19630080, 'steps': 38339, 'loss/train': 2.3709399700164795}
-03/05/2022 10:32:00 - INFO - codeparrot_training - Step 38340: {'lr': 0.000429235873217592, 'samples': 19630592, 'steps': 38340, 'loss/train': 1.7215328216552734}
-03/05/2022 10:32:02 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/05/2022 10:32:06 - INFO - codeparrot_training - Step 38341: {'lr': 0.0004292321736797077, 'samples': 19631104, 'steps': 38341, 'loss/train': 2.362046957015991}
-03/05/2022 10:32:09 - INFO - codeparrot_training - Step 38342: {'lr': 0.0004292284740610642, 'samples': 19631616, 'steps': 38342, 'loss/train': 1.0728541612625122}
-03/05/2022 10:32:10 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/05/2022 10:32:14 - INFO - codeparrot_training - Step 38343: {'lr': 0.0004292247743616631, 'samples': 19632128, 'steps': 38343, 'loss/train': 1.2901664972305298}
-03/05/2022 10:32:17 - INFO - codeparrot_training - Step 38344: {'lr': 0.00042922107458150604, 'samples': 19632640, 'steps': 38344, 'loss/train': 1.4820536375045776}
-03/05/2022 10:32:19 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/05/2022 10:32:23 - INFO - codeparrot_training - Step 38345: {'lr': 0.00042921737472059474, 'samples': 19633152, 'steps': 38345, 'loss/train': 2.4663703441619873}
-03/05/2022 10:32:26 - INFO - codeparrot_training - Step 38346: {'lr': 0.0004292136747789309, 'samples': 19633664, 'steps': 38346, 'loss/train': 2.121039628982544}
-03/05/2022 10:32:27 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/05/2022 10:32:31 - INFO - codeparrot_training - Step 38347: {'lr': 0.00042920997475651607, 'samples': 19634176, 'steps': 38347, 'loss/train': 0.7485745549201965}
-03/05/2022 10:32:34 - INFO - codeparrot_training - Step 38348: {'lr': 0.00042920627465335205, 'samples': 19634688, 'steps': 38348, 'loss/train': 2.2158560752868652}
-03/05/2022 10:32:35 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/05/2022 10:32:39 - INFO - codeparrot_training - Step 38349: {'lr': 0.00042920257446944044, 'samples': 19635200, 'steps': 38349, 'loss/train': 2.546020030975342}
-03/05/2022 10:32:43 - INFO - codeparrot_training - Step 38350: {'lr': 0.0004291988742047829, 'samples': 19635712, 'steps': 38350, 'loss/train': 1.5706251859664917}
-03/05/2022 10:32:43 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/05/2022 10:32:48 - INFO - codeparrot_training - Step 38351: {'lr': 0.0004291951738593811, 'samples': 19636224, 'steps': 38351, 'loss/train': 1.5542936325073242}
-03/05/2022 10:32:51 - INFO - codeparrot_training - Step 38352: {'lr': 0.0004291914734332367, 'samples': 19636736, 'steps': 38352, 'loss/train': 1.4142167568206787}
-03/05/2022 10:32:52 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/05/2022 10:32:56 - INFO - codeparrot_training - Step 38353: {'lr': 0.0004291877729263515, 'samples': 19637248, 'steps': 38353, 'loss/train': 1.2176845073699951}
-03/05/2022 10:32:59 - INFO - codeparrot_training - Step 38354: {'lr': 0.0004291840723387269, 'samples': 19637760, 'steps': 38354, 'loss/train': 0.9256685376167297}
-03/05/2022 10:33:00 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 10:33:05 - INFO - codeparrot_training - Step 38355: {'lr': 0.0004291803716703648, 'samples': 19638272, 'steps': 38355, 'loss/train': 2.225929021835327}
-03/05/2022 10:33:08 - INFO - codeparrot_training - Step 38356: {'lr': 0.0004291766709212668, 'samples': 19638784, 'steps': 38356, 'loss/train': 1.197957158088684}
-03/05/2022 10:33:09 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/05/2022 10:33:13 - INFO - codeparrot_training - Step 38357: {'lr': 0.00042917297009143455, 'samples': 19639296, 'steps': 38357, 'loss/train': 2.3322348594665527}
-03/05/2022 10:33:16 - INFO - codeparrot_training - Step 38358: {'lr': 0.00042916926918086973, 'samples': 19639808, 'steps': 38358, 'loss/train': 1.159559726715088}
-03/05/2022 10:33:17 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/05/2022 10:33:22 - INFO - codeparrot_training - Step 38359: {'lr': 0.000429165568189574, 'samples': 19640320, 'steps': 38359, 'loss/train': 2.478180408477783}
-03/05/2022 10:33:25 - INFO - codeparrot_training - Step 38360: {'lr': 0.000429161867117549, 'samples': 19640832, 'steps': 38360, 'loss/train': 1.1967761516571045}
-03/05/2022 10:33:26 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/05/2022 10:33:30 - INFO - codeparrot_training - Step 38361: {'lr': 0.0004291581659647965, 'samples': 19641344, 'steps': 38361, 'loss/train': 1.6914615631103516}
-03/05/2022 10:33:33 - INFO - codeparrot_training - Step 38362: {'lr': 0.00042915446473131805, 'samples': 19641856, 'steps': 38362, 'loss/train': 2.3513453006744385}
-03/05/2022 10:33:34 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 10:33:39 - INFO - codeparrot_training - Step 38363: {'lr': 0.0004291507634171153, 'samples': 19642368, 'steps': 38363, 'loss/train': 2.2858219146728516}
-03/05/2022 10:33:42 - INFO - codeparrot_training - Step 38364: {'lr': 0.0004291470620221901, 'samples': 19642880, 'steps': 38364, 'loss/train': 0.5959856510162354}
-03/05/2022 10:33:42 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/05/2022 10:33:47 - INFO - codeparrot_training - Step 38365: {'lr': 0.0004291433605465439, 'samples': 19643392, 'steps': 38365, 'loss/train': 2.391291856765747}
-03/05/2022 10:33:50 - INFO - codeparrot_training - Step 38366: {'lr': 0.00042913965899017855, 'samples': 19643904, 'steps': 38366, 'loss/train': 2.0616636276245117}
-03/05/2022 10:33:51 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/05/2022 10:33:55 - INFO - codeparrot_training - Step 38367: {'lr': 0.0004291359573530956, 'samples': 19644416, 'steps': 38367, 'loss/train': 1.4300143718719482}
-03/05/2022 10:33:59 - INFO - codeparrot_training - Step 38368: {'lr': 0.0004291322556352967, 'samples': 19644928, 'steps': 38368, 'loss/train': 1.7643640041351318}
-03/05/2022 10:34:00 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/05/2022 10:34:04 - INFO - codeparrot_training - Step 38369: {'lr': 0.00042912855383678365, 'samples': 19645440, 'steps': 38369, 'loss/train': 1.811132788658142}
-03/05/2022 10:34:07 - INFO - codeparrot_training - Step 38370: {'lr': 0.000429124851957558, 'samples': 19645952, 'steps': 38370, 'loss/train': 2.6342947483062744}
-03/05/2022 10:34:08 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/05/2022 10:34:12 - INFO - codeparrot_training - Step 38371: {'lr': 0.0004291211499976214, 'samples': 19646464, 'steps': 38371, 'loss/train': 0.6090827584266663}
-03/05/2022 10:34:15 - INFO - codeparrot_training - Step 38372: {'lr': 0.0004291174479569757, 'samples': 19646976, 'steps': 38372, 'loss/train': 2.2093231678009033}
-03/05/2022 10:34:16 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/05/2022 10:34:21 - INFO - codeparrot_training - Step 38373: {'lr': 0.00042911374583562233, 'samples': 19647488, 'steps': 38373, 'loss/train': 1.0194138288497925}
-03/05/2022 10:34:24 - INFO - codeparrot_training - Step 38374: {'lr': 0.0004291100436335631, 'samples': 19648000, 'steps': 38374, 'loss/train': 1.4219602346420288}
-03/05/2022 10:34:25 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/05/2022 10:34:29 - INFO - codeparrot_training - Step 38375: {'lr': 0.00042910634135079963, 'samples': 19648512, 'steps': 38375, 'loss/train': 0.8629974722862244}
-03/05/2022 10:34:32 - INFO - codeparrot_training - Step 38376: {'lr': 0.00042910263898733364, 'samples': 19649024, 'steps': 38376, 'loss/train': 1.8268239498138428}
-03/05/2022 10:34:33 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 10:34:38 - INFO - codeparrot_training - Step 38377: {'lr': 0.0004290989365431668, 'samples': 19649536, 'steps': 38377, 'loss/train': 1.638385534286499}
-03/05/2022 10:34:41 - INFO - codeparrot_training - Step 38378: {'lr': 0.0004290952340183007, 'samples': 19650048, 'steps': 38378, 'loss/train': 1.6871306896209717}
-03/05/2022 10:34:41 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/05/2022 10:34:46 - INFO - codeparrot_training - Step 38379: {'lr': 0.00042909153141273705, 'samples': 19650560, 'steps': 38379, 'loss/train': 1.151309847831726}
-03/05/2022 10:34:49 - INFO - codeparrot_training - Step 38380: {'lr': 0.0004290878287264775, 'samples': 19651072, 'steps': 38380, 'loss/train': 1.0523532629013062}
-03/05/2022 10:34:50 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/05/2022 10:34:55 - INFO - codeparrot_training - Step 38381: {'lr': 0.0004290841259595237, 'samples': 19651584, 'steps': 38381, 'loss/train': 1.8185559511184692}
-03/05/2022 10:34:58 - INFO - codeparrot_training - Step 38382: {'lr': 0.00042908042311187744, 'samples': 19652096, 'steps': 38382, 'loss/train': 0.4950217306613922}
-03/05/2022 10:34:58 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 10:35:03 - INFO - codeparrot_training - Step 38383: {'lr': 0.00042907672018354027, 'samples': 19652608, 'steps': 38383, 'loss/train': 0.7234829068183899}
-03/05/2022 10:35:06 - INFO - codeparrot_training - Step 38384: {'lr': 0.00042907301717451396, 'samples': 19653120, 'steps': 38384, 'loss/train': 1.62031888961792}
-03/05/2022 10:35:07 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/05/2022 10:35:11 - INFO - codeparrot_training - Step 38385: {'lr': 0.0004290693140848, 'samples': 19653632, 'steps': 38385, 'loss/train': 1.875291347503662}
-03/05/2022 10:35:15 - INFO - codeparrot_training - Step 38386: {'lr': 0.0004290656109144003, 'samples': 19654144, 'steps': 38386, 'loss/train': 1.7963448762893677}
-03/05/2022 10:35:15 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/05/2022 10:35:20 - INFO - codeparrot_training - Step 38387: {'lr': 0.0004290619076633163, 'samples': 19654656, 'steps': 38387, 'loss/train': 1.1610013246536255}
-03/05/2022 10:35:23 - INFO - codeparrot_training - Step 38388: {'lr': 0.0004290582043315498, 'samples': 19655168, 'steps': 38388, 'loss/train': 1.3825302124023438}
-03/05/2022 10:35:23 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/05/2022 10:35:28 - INFO - codeparrot_training - Step 38389: {'lr': 0.0004290545009191024, 'samples': 19655680, 'steps': 38389, 'loss/train': 1.243184208869934}
-03/05/2022 10:35:32 - INFO - codeparrot_training - Step 38390: {'lr': 0.0004290507974259759, 'samples': 19656192, 'steps': 38390, 'loss/train': 2.1244990825653076}
-03/05/2022 10:35:32 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 10:35:37 - INFO - codeparrot_training - Step 38391: {'lr': 0.0004290470938521718, 'samples': 19656704, 'steps': 38391, 'loss/train': 1.3065741062164307}
-03/05/2022 10:35:40 - INFO - codeparrot_training - Step 38392: {'lr': 0.0004290433901976918, 'samples': 19657216, 'steps': 38392, 'loss/train': 1.8737469911575317}
-03/05/2022 10:35:40 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/05/2022 10:35:46 - INFO - codeparrot_training - Step 38393: {'lr': 0.0004290396864625377, 'samples': 19657728, 'steps': 38393, 'loss/train': 1.0331001281738281}
-03/05/2022 10:35:49 - INFO - codeparrot_training - Step 38394: {'lr': 0.000429035982646711, 'samples': 19658240, 'steps': 38394, 'loss/train': 1.5800210237503052}
-03/05/2022 10:35:49 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/05/2022 10:35:54 - INFO - codeparrot_training - Step 38395: {'lr': 0.0004290322787502135, 'samples': 19658752, 'steps': 38395, 'loss/train': 2.151383638381958}
-03/05/2022 10:35:57 - INFO - codeparrot_training - Step 38396: {'lr': 0.0004290285747730468, 'samples': 19659264, 'steps': 38396, 'loss/train': 1.99385666847229}
-03/05/2022 10:35:57 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/05/2022 10:36:03 - INFO - codeparrot_training - Step 38397: {'lr': 0.00042902487071521257, 'samples': 19659776, 'steps': 38397, 'loss/train': 1.6579667329788208}
-03/05/2022 10:36:06 - INFO - codeparrot_training - Step 38398: {'lr': 0.0004290211665767125, 'samples': 19660288, 'steps': 38398, 'loss/train': 1.331533670425415}
-03/05/2022 10:36:06 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/05/2022 10:36:11 - INFO - codeparrot_training - Step 38399: {'lr': 0.00042901746235754837, 'samples': 19660800, 'steps': 38399, 'loss/train': 2.3798375129699707}
-03/05/2022 10:36:14 - INFO - codeparrot_training - Step 38400: {'lr': 0.0004290137580577216, 'samples': 19661312, 'steps': 38400, 'loss/train': 2.1654205322265625}
-03/05/2022 10:36:14 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/05/2022 10:36:20 - INFO - codeparrot_training - Step 38401: {'lr': 0.000429010053677234, 'samples': 19661824, 'steps': 38401, 'loss/train': 1.4910234212875366}
-03/05/2022 10:36:23 - INFO - codeparrot_training - Step 38402: {'lr': 0.00042900634921608726, 'samples': 19662336, 'steps': 38402, 'loss/train': 1.06117582321167}
-03/05/2022 10:36:23 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/05/2022 10:36:28 - INFO - codeparrot_training - Step 38403: {'lr': 0.0004290026446742831, 'samples': 19662848, 'steps': 38403, 'loss/train': 1.4278509616851807}
-03/05/2022 10:36:31 - INFO - codeparrot_training - Step 38404: {'lr': 0.00042899894005182294, 'samples': 19663360, 'steps': 38404, 'loss/train': 1.6785449981689453}
-03/05/2022 10:36:31 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/05/2022 10:36:37 - INFO - codeparrot_training - Step 38405: {'lr': 0.0004289952353487088, 'samples': 19663872, 'steps': 38405, 'loss/train': 1.9514307975769043}
-03/05/2022 10:36:40 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/05/2022 10:36:42 - INFO - codeparrot_training - Step 38406: {'lr': 0.000428991530564942, 'samples': 19664384, 'steps': 38406, 'loss/train': 1.7903854846954346}
-03/05/2022 10:36:45 - INFO - codeparrot_training - Step 38407: {'lr': 0.00042898782570052453, 'samples': 19664896, 'steps': 38407, 'loss/train': 1.4764090776443481}
-03/05/2022 10:36:48 - INFO - codeparrot_training - Step 38408: {'lr': 0.0004289841207554578, 'samples': 19665408, 'steps': 38408, 'loss/train': 2.009769916534424}
-03/05/2022 10:36:48 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 10:36:54 - INFO - codeparrot_training - Step 38409: {'lr': 0.00042898041572974363, 'samples': 19665920, 'steps': 38409, 'loss/train': 1.007509708404541}
-03/05/2022 10:36:57 - INFO - codeparrot_training - Step 38410: {'lr': 0.0004289767106233836, 'samples': 19666432, 'steps': 38410, 'loss/train': 2.185873508453369}
-03/05/2022 10:36:57 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 10:37:02 - INFO - codeparrot_training - Step 38411: {'lr': 0.0004289730054363795, 'samples': 19666944, 'steps': 38411, 'loss/train': 1.8891595602035522}
-03/05/2022 10:37:05 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/05/2022 10:37:07 - INFO - codeparrot_training - Step 38412: {'lr': 0.00042896930016873293, 'samples': 19667456, 'steps': 38412, 'loss/train': 1.914839267730713}
-03/05/2022 10:37:11 - INFO - codeparrot_training - Step 38413: {'lr': 0.0004289655948204455, 'samples': 19667968, 'steps': 38413, 'loss/train': 1.4405065774917603}
-03/05/2022 10:37:13 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/05/2022 10:37:16 - INFO - codeparrot_training - Step 38414: {'lr': 0.00042896188939151893, 'samples': 19668480, 'steps': 38414, 'loss/train': 2.356462001800537}
-03/05/2022 10:37:19 - INFO - codeparrot_training - Step 38415: {'lr': 0.00042895818388195497, 'samples': 19668992, 'steps': 38415, 'loss/train': 1.7206308841705322}
-03/05/2022 10:37:22 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 10:37:24 - INFO - codeparrot_training - Step 38416: {'lr': 0.00042895447829175516, 'samples': 19669504, 'steps': 38416, 'loss/train': 1.2121211290359497}
-03/05/2022 10:37:27 - INFO - codeparrot_training - Step 38417: {'lr': 0.00042895077262092117, 'samples': 19670016, 'steps': 38417, 'loss/train': 1.2586681842803955}
-03/05/2022 10:37:33 - INFO - codeparrot_training - Step 38418: {'lr': 0.00042894706686945485, 'samples': 19670528, 'steps': 38418, 'loss/train': 1.6650660037994385}
-03/05/2022 10:37:36 - INFO - codeparrot_training - Step 38419: {'lr': 0.00042894336103735766, 'samples': 19671040, 'steps': 38419, 'loss/train': 1.1475378274917603}
-03/05/2022 10:37:39 - INFO - codeparrot_training - Step 38420: {'lr': 0.0004289396551246313, 'samples': 19671552, 'steps': 38420, 'loss/train': 1.2205075025558472}
-03/05/2022 10:37:40 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 10:37:44 - INFO - codeparrot_training - Step 38421: {'lr': 0.0004289359491312776, 'samples': 19672064, 'steps': 38421, 'loss/train': 1.6022918224334717}
-03/05/2022 10:37:48 - INFO - codeparrot_training - Step 38422: {'lr': 0.00042893224305729806, 'samples': 19672576, 'steps': 38422, 'loss/train': 0.9790200591087341}
-03/05/2022 10:37:48 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 10:37:53 - INFO - codeparrot_training - Step 38423: {'lr': 0.0004289285369026944, 'samples': 19673088, 'steps': 38423, 'loss/train': 2.402050018310547}
-03/05/2022 10:37:56 - INFO - codeparrot_training - Step 38424: {'lr': 0.00042892483066746836, 'samples': 19673600, 'steps': 38424, 'loss/train': 0.5828243494033813}
-03/05/2022 10:37:56 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/05/2022 10:38:01 - INFO - codeparrot_training - Step 38425: {'lr': 0.0004289211243516216, 'samples': 19674112, 'steps': 38425, 'loss/train': 1.963414192199707}
-03/05/2022 10:38:05 - INFO - codeparrot_training - Step 38426: {'lr': 0.0004289174179551556, 'samples': 19674624, 'steps': 38426, 'loss/train': 1.612033724784851}
-03/05/2022 10:38:05 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/05/2022 10:38:10 - INFO - codeparrot_training - Step 38427: {'lr': 0.0004289137114780722, 'samples': 19675136, 'steps': 38427, 'loss/train': 1.9628162384033203}
-03/05/2022 10:38:13 - INFO - codeparrot_training - Step 38428: {'lr': 0.00042891000492037315, 'samples': 19675648, 'steps': 38428, 'loss/train': 1.6535027027130127}
-03/05/2022 10:38:13 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/05/2022 10:38:18 - INFO - codeparrot_training - Step 38429: {'lr': 0.00042890629828205997, 'samples': 19676160, 'steps': 38429, 'loss/train': 0.8594965934753418}
-03/05/2022 10:38:21 - INFO - codeparrot_training - Step 38430: {'lr': 0.0004289025915631343, 'samples': 19676672, 'steps': 38430, 'loss/train': 2.3969826698303223}
-03/05/2022 10:38:22 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/05/2022 10:38:27 - INFO - codeparrot_training - Step 38431: {'lr': 0.00042889888476359793, 'samples': 19677184, 'steps': 38431, 'loss/train': 6.413302421569824}
-03/05/2022 10:38:30 - INFO - codeparrot_training - Step 38432: {'lr': 0.0004288951778834525, 'samples': 19677696, 'steps': 38432, 'loss/train': 1.6811875104904175}
-03/05/2022 10:38:31 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/05/2022 10:38:35 - INFO - codeparrot_training - Step 38433: {'lr': 0.00042889147092269964, 'samples': 19678208, 'steps': 38433, 'loss/train': 0.9800106287002563}
-03/05/2022 10:38:39 - INFO - codeparrot_training - Step 38434: {'lr': 0.0004288877638813411, 'samples': 19678720, 'steps': 38434, 'loss/train': 1.6396557092666626}
-03/05/2022 10:38:39 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 10:38:44 - INFO - codeparrot_training - Step 38435: {'lr': 0.00042888405675937843, 'samples': 19679232, 'steps': 38435, 'loss/train': 1.7083581686019897}
-03/05/2022 10:38:47 - INFO - codeparrot_training - Step 38436: {'lr': 0.00042888034955681337, 'samples': 19679744, 'steps': 38436, 'loss/train': 2.1615352630615234}
-03/05/2022 10:38:48 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 10:38:52 - INFO - codeparrot_training - Step 38437: {'lr': 0.0004288766422736476, 'samples': 19680256, 'steps': 38437, 'loss/train': 1.7751213312149048}
-03/05/2022 10:38:56 - INFO - codeparrot_training - Step 38438: {'lr': 0.00042887293490988276, 'samples': 19680768, 'steps': 38438, 'loss/train': 1.7572563886642456}
-03/05/2022 10:38:56 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/05/2022 10:39:01 - INFO - codeparrot_training - Step 38439: {'lr': 0.00042886922746552056, 'samples': 19681280, 'steps': 38439, 'loss/train': 2.136826276779175}
-03/05/2022 10:39:04 - INFO - codeparrot_training - Step 38440: {'lr': 0.0004288655199405626, 'samples': 19681792, 'steps': 38440, 'loss/train': 1.478708267211914}
-03/05/2022 10:39:04 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/05/2022 10:39:09 - INFO - codeparrot_training - Step 38441: {'lr': 0.00042886181233501067, 'samples': 19682304, 'steps': 38441, 'loss/train': 2.2431581020355225}
-03/05/2022 10:39:12 - INFO - codeparrot_training - Step 38442: {'lr': 0.00042885810464886635, 'samples': 19682816, 'steps': 38442, 'loss/train': 2.1431119441986084}
-03/05/2022 10:39:13 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 10:39:18 - INFO - codeparrot_training - Step 38443: {'lr': 0.0004288543968821312, 'samples': 19683328, 'steps': 38443, 'loss/train': 1.6908425092697144}
-03/05/2022 10:39:21 - INFO - codeparrot_training - Step 38444: {'lr': 0.00042885068903480717, 'samples': 19683840, 'steps': 38444, 'loss/train': 0.6604570150375366}
-03/05/2022 10:39:21 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/05/2022 10:39:26 - INFO - codeparrot_training - Step 38445: {'lr': 0.00042884698110689574, 'samples': 19684352, 'steps': 38445, 'loss/train': 0.9049607515335083}
-03/05/2022 10:39:29 - INFO - codeparrot_training - Step 38446: {'lr': 0.00042884327309839865, 'samples': 19684864, 'steps': 38446, 'loss/train': 1.7797797918319702}
-03/05/2022 10:39:29 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/05/2022 10:39:34 - INFO - codeparrot_training - Step 38447: {'lr': 0.0004288395650093174, 'samples': 19685376, 'steps': 38447, 'loss/train': 1.7316081523895264}
-03/05/2022 10:39:37 - INFO - codeparrot_training - Step 38448: {'lr': 0.000428835856839654, 'samples': 19685888, 'steps': 38448, 'loss/train': 1.2837438583374023}
-03/05/2022 10:39:38 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/05/2022 10:39:43 - INFO - codeparrot_training - Step 38449: {'lr': 0.0004288321485894098, 'samples': 19686400, 'steps': 38449, 'loss/train': 0.8910672068595886}
-03/05/2022 10:39:46 - INFO - codeparrot_training - Step 38450: {'lr': 0.0004288284402585866, 'samples': 19686912, 'steps': 38450, 'loss/train': 3.5198237895965576}
-03/05/2022 10:39:46 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/05/2022 10:39:51 - INFO - codeparrot_training - Step 38451: {'lr': 0.0004288247318471861, 'samples': 19687424, 'steps': 38451, 'loss/train': 1.235252022743225}
-03/05/2022 10:39:54 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/05/2022 10:39:56 - INFO - codeparrot_training - Step 38452: {'lr': 0.0004288210233552099, 'samples': 19687936, 'steps': 38452, 'loss/train': 1.6333867311477661}
-03/05/2022 10:40:00 - INFO - codeparrot_training - Step 38453: {'lr': 0.00042881731478265975, 'samples': 19688448, 'steps': 38453, 'loss/train': 1.8736987113952637}
-03/05/2022 10:40:02 - INFO - codeparrot_training - Skipping example with length 920 (seq_length=1024)
-03/05/2022 10:40:05 - INFO - codeparrot_training - Step 38454: {'lr': 0.00042881360612953724, 'samples': 19688960, 'steps': 38454, 'loss/train': 1.6093828678131104}
-03/05/2022 10:40:08 - INFO - codeparrot_training - Step 38455: {'lr': 0.0004288098973958441, 'samples': 19689472, 'steps': 38455, 'loss/train': 1.8442496061325073}
-03/05/2022 10:40:11 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/05/2022 10:40:13 - INFO - codeparrot_training - Step 38456: {'lr': 0.000428806188581582, 'samples': 19689984, 'steps': 38456, 'loss/train': 2.321953773498535}
-03/05/2022 10:40:17 - INFO - codeparrot_training - Step 38457: {'lr': 0.00042880247968675255, 'samples': 19690496, 'steps': 38457, 'loss/train': 2.0819449424743652}
-03/05/2022 10:40:19 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/05/2022 10:40:22 - INFO - codeparrot_training - Step 38458: {'lr': 0.00042879877071135746, 'samples': 19691008, 'steps': 38458, 'loss/train': 2.7108960151672363}
-03/05/2022 10:40:25 - INFO - codeparrot_training - Step 38459: {'lr': 0.0004287950616553984, 'samples': 19691520, 'steps': 38459, 'loss/train': 2.0531153678894043}
-03/05/2022 10:40:28 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/05/2022 10:40:30 - INFO - codeparrot_training - Step 38460: {'lr': 0.0004287913525188771, 'samples': 19692032, 'steps': 38460, 'loss/train': 2.273984432220459}
-03/05/2022 10:40:34 - INFO - codeparrot_training - Step 38461: {'lr': 0.0004287876433017951, 'samples': 19692544, 'steps': 38461, 'loss/train': 2.0924222469329834}
-03/05/2022 10:40:36 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/05/2022 10:40:39 - INFO - codeparrot_training - Step 38462: {'lr': 0.0004287839340041542, 'samples': 19693056, 'steps': 38462, 'loss/train': 1.4327436685562134}
-03/05/2022 10:40:42 - INFO - codeparrot_training - Step 38463: {'lr': 0.000428780224625956, 'samples': 19693568, 'steps': 38463, 'loss/train': 1.6557176113128662}
-03/05/2022 10:40:45 - INFO - codeparrot_training - Step 38464: {'lr': 0.00042877651516720215, 'samples': 19694080, 'steps': 38464, 'loss/train': 1.746933937072754}
-03/05/2022 10:40:46 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/05/2022 10:40:51 - INFO - codeparrot_training - Step 38465: {'lr': 0.0004287728056278944, 'samples': 19694592, 'steps': 38465, 'loss/train': 1.970833659172058}
-03/05/2022 10:40:54 - INFO - codeparrot_training - Step 38466: {'lr': 0.00042876909600803444, 'samples': 19695104, 'steps': 38466, 'loss/train': 0.1481592208147049}
-03/05/2022 10:40:54 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/05/2022 10:40:59 - INFO - codeparrot_training - Step 38467: {'lr': 0.00042876538630762386, 'samples': 19695616, 'steps': 38467, 'loss/train': 2.0764636993408203}
-03/05/2022 10:41:02 - INFO - codeparrot_training - Step 38468: {'lr': 0.00042876167652666433, 'samples': 19696128, 'steps': 38468, 'loss/train': 2.1492557525634766}
-03/05/2022 10:41:03 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/05/2022 10:41:08 - INFO - codeparrot_training - Step 38469: {'lr': 0.0004287579666651575, 'samples': 19696640, 'steps': 38469, 'loss/train': 2.0843088626861572}
-03/05/2022 10:41:11 - INFO - codeparrot_training - Step 38470: {'lr': 0.00042875425672310506, 'samples': 19697152, 'steps': 38470, 'loss/train': 1.6615303754806519}
-03/05/2022 10:41:11 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/05/2022 10:41:16 - INFO - codeparrot_training - Step 38471: {'lr': 0.00042875054670050885, 'samples': 19697664, 'steps': 38471, 'loss/train': 0.22629989683628082}
-03/05/2022 10:41:19 - INFO - codeparrot_training - Step 38472: {'lr': 0.00042874683659737035, 'samples': 19698176, 'steps': 38472, 'loss/train': 1.711127519607544}
-03/05/2022 10:41:20 - INFO - codeparrot_training - Skipping example with length 674 (seq_length=1024)
-03/05/2022 10:41:25 - INFO - codeparrot_training - Step 38473: {'lr': 0.0004287431264136913, 'samples': 19698688, 'steps': 38473, 'loss/train': 1.490905523300171}
-03/05/2022 10:41:28 - INFO - codeparrot_training - Step 38474: {'lr': 0.0004287394161494733, 'samples': 19699200, 'steps': 38474, 'loss/train': 0.2891647219657898}
-03/05/2022 10:41:28 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/05/2022 10:41:33 - INFO - codeparrot_training - Step 38475: {'lr': 0.0004287357058047181, 'samples': 19699712, 'steps': 38475, 'loss/train': 2.259152412414551}
-03/05/2022 10:41:36 - INFO - codeparrot_training - Step 38476: {'lr': 0.00042873199537942733, 'samples': 19700224, 'steps': 38476, 'loss/train': 1.9291691780090332}
-03/05/2022 10:41:37 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/05/2022 10:41:42 - INFO - codeparrot_training - Step 38477: {'lr': 0.0004287282848736027, 'samples': 19700736, 'steps': 38477, 'loss/train': 1.4054182767868042}
-03/05/2022 10:41:45 - INFO - codeparrot_training - Step 38478: {'lr': 0.00042872457428724586, 'samples': 19701248, 'steps': 38478, 'loss/train': 1.7675607204437256}
-03/05/2022 10:41:45 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/05/2022 10:41:50 - INFO - codeparrot_training - Step 38479: {'lr': 0.00042872086362035844, 'samples': 19701760, 'steps': 38479, 'loss/train': 1.40352201461792}
-03/05/2022 10:41:53 - INFO - codeparrot_training - Step 38480: {'lr': 0.00042871715287294223, 'samples': 19702272, 'steps': 38480, 'loss/train': 1.5122416019439697}
-03/05/2022 10:41:54 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/05/2022 10:41:58 - INFO - codeparrot_training - Step 38481: {'lr': 0.00042871344204499886, 'samples': 19702784, 'steps': 38481, 'loss/train': 1.637404441833496}
-03/05/2022 10:42:02 - INFO - codeparrot_training - Step 38482: {'lr': 0.0004287097311365299, 'samples': 19703296, 'steps': 38482, 'loss/train': 1.4677963256835938}
-03/05/2022 10:42:02 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/05/2022 10:42:07 - INFO - codeparrot_training - Step 38483: {'lr': 0.00042870602014753707, 'samples': 19703808, 'steps': 38483, 'loss/train': 1.6970757246017456}
-03/05/2022 10:42:10 - INFO - codeparrot_training - Step 38484: {'lr': 0.0004287023090780221, 'samples': 19704320, 'steps': 38484, 'loss/train': 1.9356173276901245}
-03/05/2022 10:42:11 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/05/2022 10:42:15 - INFO - codeparrot_training - Step 38485: {'lr': 0.0004286985979279866, 'samples': 19704832, 'steps': 38485, 'loss/train': 2.162578582763672}
-03/05/2022 10:42:18 - INFO - codeparrot_training - Step 38486: {'lr': 0.0004286948866974323, 'samples': 19705344, 'steps': 38486, 'loss/train': 1.7900238037109375}
-03/05/2022 10:42:19 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/05/2022 10:42:24 - INFO - codeparrot_training - Step 38487: {'lr': 0.0004286911753863608, 'samples': 19705856, 'steps': 38487, 'loss/train': 1.3912684917449951}
-03/05/2022 10:42:27 - INFO - codeparrot_training - Step 38488: {'lr': 0.0004286874639947739, 'samples': 19706368, 'steps': 38488, 'loss/train': 1.6374905109405518}
-03/05/2022 10:42:27 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/05/2022 10:42:32 - INFO - codeparrot_training - Step 38489: {'lr': 0.0004286837525226731, 'samples': 19706880, 'steps': 38489, 'loss/train': 1.323987364768982}
-03/05/2022 10:42:35 - INFO - codeparrot_training - Step 38490: {'lr': 0.0004286800409700602, 'samples': 19707392, 'steps': 38490, 'loss/train': 1.8008346557617188}
-03/05/2022 10:42:36 - INFO - codeparrot_training - Skipping example with length 860 (seq_length=1024)
-03/05/2022 10:42:41 - INFO - codeparrot_training - Step 38491: {'lr': 0.0004286763293369369, 'samples': 19707904, 'steps': 38491, 'loss/train': 2.441908836364746}
-03/05/2022 10:42:44 - INFO - codeparrot_training - Step 38492: {'lr': 0.00042867261762330466, 'samples': 19708416, 'steps': 38492, 'loss/train': 1.6079301834106445}
-03/05/2022 10:42:44 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/05/2022 10:42:49 - INFO - codeparrot_training - Step 38493: {'lr': 0.0004286689058291654, 'samples': 19708928, 'steps': 38493, 'loss/train': 1.8984520435333252}
-03/05/2022 10:42:52 - INFO - codeparrot_training - Step 38494: {'lr': 0.00042866519395452063, 'samples': 19709440, 'steps': 38494, 'loss/train': 0.376102089881897}
-03/05/2022 10:42:52 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/05/2022 10:42:57 - INFO - codeparrot_training - Step 38495: {'lr': 0.00042866148199937216, 'samples': 19709952, 'steps': 38495, 'loss/train': 1.2295597791671753}
-03/05/2022 10:43:01 - INFO - codeparrot_training - Step 38496: {'lr': 0.00042865776996372146, 'samples': 19710464, 'steps': 38496, 'loss/train': 1.580771565437317}
-03/05/2022 10:43:01 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/05/2022 10:43:06 - INFO - codeparrot_training - Step 38497: {'lr': 0.00042865405784757037, 'samples': 19710976, 'steps': 38497, 'loss/train': 2.090898036956787}
-03/05/2022 10:43:09 - INFO - codeparrot_training - Step 38498: {'lr': 0.0004286503456509206, 'samples': 19711488, 'steps': 38498, 'loss/train': 1.4580153226852417}
-03/05/2022 10:43:09 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/05/2022 10:43:14 - INFO - codeparrot_training - Step 38499: {'lr': 0.0004286466333737737, 'samples': 19712000, 'steps': 38499, 'loss/train': 1.817798137664795}
-03/05/2022 10:43:17 - INFO - codeparrot_training - Step 38500: {'lr': 0.00042864292101613133, 'samples': 19712512, 'steps': 38500, 'loss/train': 1.8921886682510376}
-03/05/2022 10:43:18 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/05/2022 10:43:23 - INFO - codeparrot_training - Step 38501: {'lr': 0.0004286392085779953, 'samples': 19713024, 'steps': 38501, 'loss/train': 2.1208791732788086}
-03/05/2022 10:43:26 - INFO - codeparrot_training - Step 38502: {'lr': 0.00042863549605936716, 'samples': 19713536, 'steps': 38502, 'loss/train': 1.3319653272628784}
-03/05/2022 10:43:26 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/05/2022 10:43:31 - INFO - codeparrot_training - Step 38503: {'lr': 0.00042863178346024856, 'samples': 19714048, 'steps': 38503, 'loss/train': 1.7979694604873657}
-03/05/2022 10:43:34 - INFO - codeparrot_training - Step 38504: {'lr': 0.00042862807078064124, 'samples': 19714560, 'steps': 38504, 'loss/train': 1.5656987428665161}
-03/05/2022 10:43:35 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/05/2022 10:43:40 - INFO - codeparrot_training - Step 38505: {'lr': 0.00042862435802054703, 'samples': 19715072, 'steps': 38505, 'loss/train': 1.709275245666504}
-03/05/2022 10:43:43 - INFO - codeparrot_training - Step 38506: {'lr': 0.00042862064517996723, 'samples': 19715584, 'steps': 38506, 'loss/train': 2.639859199523926}
-03/05/2022 10:43:44 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/05/2022 10:43:48 - INFO - codeparrot_training - Step 38507: {'lr': 0.00042861693225890385, 'samples': 19716096, 'steps': 38507, 'loss/train': 1.8164652585983276}
-03/05/2022 10:43:51 - INFO - codeparrot_training - Step 38508: {'lr': 0.0004286132192573584, 'samples': 19716608, 'steps': 38508, 'loss/train': 0.7617395520210266}
-03/05/2022 10:43:52 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/05/2022 10:43:56 - INFO - codeparrot_training - Step 38509: {'lr': 0.0004286095061753326, 'samples': 19717120, 'steps': 38509, 'loss/train': 0.7710505127906799}
-03/05/2022 10:44:00 - INFO - codeparrot_training - Step 38510: {'lr': 0.0004286057930128281, 'samples': 19717632, 'steps': 38510, 'loss/train': 1.682903528213501}
-03/05/2022 10:44:00 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/05/2022 10:44:05 - INFO - codeparrot_training - Step 38511: {'lr': 0.00042860207976984664, 'samples': 19718144, 'steps': 38511, 'loss/train': 0.6496201753616333}
-03/05/2022 10:44:08 - INFO - codeparrot_training - Step 38512: {'lr': 0.00042859836644638976, 'samples': 19718656, 'steps': 38512, 'loss/train': 2.3134231567382812}
-03/05/2022 10:44:08 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/05/2022 10:44:13 - INFO - codeparrot_training - Step 38513: {'lr': 0.00042859465304245927, 'samples': 19719168, 'steps': 38513, 'loss/train': 1.6611865758895874}
-03/05/2022 10:44:16 - INFO - codeparrot_training - Step 38514: {'lr': 0.00042859093955805675, 'samples': 19719680, 'steps': 38514, 'loss/train': 2.065661907196045}
-03/05/2022 10:44:17 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/05/2022 10:44:22 - INFO - codeparrot_training - Step 38515: {'lr': 0.0004285872259931839, 'samples': 19720192, 'steps': 38515, 'loss/train': 2.535715103149414}
-03/05/2022 10:44:25 - INFO - codeparrot_training - Step 38516: {'lr': 0.00042858351234784244, 'samples': 19720704, 'steps': 38516, 'loss/train': 1.2711677551269531}
-03/05/2022 10:44:26 - INFO - codeparrot_training - Skipping example with length 660 (seq_length=1024)
-03/05/2022 10:44:30 - INFO - codeparrot_training - Step 38517: {'lr': 0.000428579798622034, 'samples': 19721216, 'steps': 38517, 'loss/train': 1.7173043489456177}
-03/05/2022 10:44:33 - INFO - codeparrot_training - Step 38518: {'lr': 0.0004285760848157603, 'samples': 19721728, 'steps': 38518, 'loss/train': 2.0105934143066406}
-03/05/2022 10:44:34 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 10:44:39 - INFO - codeparrot_training - Step 38519: {'lr': 0.00042857237092902285, 'samples': 19722240, 'steps': 38519, 'loss/train': 1.2959085702896118}
-03/05/2022 10:44:42 - INFO - codeparrot_training - Step 38520: {'lr': 0.0004285686569618235, 'samples': 19722752, 'steps': 38520, 'loss/train': 1.2316933870315552}
-03/05/2022 10:44:43 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/05/2022 10:44:47 - INFO - codeparrot_training - Step 38521: {'lr': 0.0004285649429141639, 'samples': 19723264, 'steps': 38521, 'loss/train': 1.1378589868545532}
-03/05/2022 10:44:50 - INFO - codeparrot_training - Step 38522: {'lr': 0.00042856122878604566, 'samples': 19723776, 'steps': 38522, 'loss/train': 1.3588716983795166}
-03/05/2022 10:44:51 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/05/2022 10:44:56 - INFO - codeparrot_training - Step 38523: {'lr': 0.0004285575145774705, 'samples': 19724288, 'steps': 38523, 'loss/train': 2.0566439628601074}
-03/05/2022 10:44:59 - INFO - codeparrot_training - Step 38524: {'lr': 0.00042855380028844004, 'samples': 19724800, 'steps': 38524, 'loss/train': 0.7114560604095459}
-03/05/2022 10:44:59 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/05/2022 10:45:04 - INFO - codeparrot_training - Step 38525: {'lr': 0.00042855008591895607, 'samples': 19725312, 'steps': 38525, 'loss/train': 1.9563223123550415}
-03/05/2022 10:45:07 - INFO - codeparrot_training - Step 38526: {'lr': 0.00042854637146902007, 'samples': 19725824, 'steps': 38526, 'loss/train': 1.7133357524871826}
-03/05/2022 10:45:08 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/05/2022 10:45:12 - INFO - codeparrot_training - Step 38527: {'lr': 0.00042854265693863394, 'samples': 19726336, 'steps': 38527, 'loss/train': 1.6425504684448242}
-03/05/2022 10:45:16 - INFO - codeparrot_training - Step 38528: {'lr': 0.00042853894232779924, 'samples': 19726848, 'steps': 38528, 'loss/train': 1.8225189447402954}
-03/05/2022 10:45:16 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 10:45:21 - INFO - codeparrot_training - Step 38529: {'lr': 0.00042853522763651767, 'samples': 19727360, 'steps': 38529, 'loss/train': 1.9709175825119019}
-03/05/2022 10:45:24 - INFO - codeparrot_training - Step 38530: {'lr': 0.00042853151286479074, 'samples': 19727872, 'steps': 38530, 'loss/train': 1.6245200634002686}
-03/05/2022 10:45:25 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/05/2022 10:45:29 - INFO - codeparrot_training - Step 38531: {'lr': 0.0004285277980126204, 'samples': 19728384, 'steps': 38531, 'loss/train': 1.5797756910324097}
-03/05/2022 10:45:33 - INFO - codeparrot_training - Step 38532: {'lr': 0.0004285240830800081, 'samples': 19728896, 'steps': 38532, 'loss/train': 2.071545362472534}
-03/05/2022 10:45:33 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/05/2022 10:45:38 - INFO - codeparrot_training - Step 38533: {'lr': 0.00042852036806695565, 'samples': 19729408, 'steps': 38533, 'loss/train': 1.8840982913970947}
-03/05/2022 10:45:41 - INFO - codeparrot_training - Step 38534: {'lr': 0.0004285166529734647, 'samples': 19729920, 'steps': 38534, 'loss/train': 2.6631252765655518}
-03/05/2022 10:45:42 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/05/2022 10:45:46 - INFO - codeparrot_training - Step 38535: {'lr': 0.0004285129377995369, 'samples': 19730432, 'steps': 38535, 'loss/train': 1.1916284561157227}
-03/05/2022 10:45:50 - INFO - codeparrot_training - Step 38536: {'lr': 0.0004285092225451739, 'samples': 19730944, 'steps': 38536, 'loss/train': 1.9457544088363647}
-03/05/2022 10:45:50 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/05/2022 10:45:55 - INFO - codeparrot_training - Step 38537: {'lr': 0.0004285055072103774, 'samples': 19731456, 'steps': 38537, 'loss/train': 1.4813554286956787}
-03/05/2022 10:45:58 - INFO - codeparrot_training - Step 38538: {'lr': 0.00042850179179514906, 'samples': 19731968, 'steps': 38538, 'loss/train': 1.2885469198226929}
-03/05/2022 10:45:59 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 10:46:03 - INFO - codeparrot_training - Step 38539: {'lr': 0.00042849807629949057, 'samples': 19732480, 'steps': 38539, 'loss/train': 3.231980562210083}
-03/05/2022 10:46:06 - INFO - codeparrot_training - Step 38540: {'lr': 0.0004284943607234036, 'samples': 19732992, 'steps': 38540, 'loss/train': 1.4474661350250244}
-03/05/2022 10:46:07 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/05/2022 10:46:12 - INFO - codeparrot_training - Step 38541: {'lr': 0.00042849064506688984, 'samples': 19733504, 'steps': 38541, 'loss/train': 1.5721244812011719}
-03/05/2022 10:46:15 - INFO - codeparrot_training - Step 38542: {'lr': 0.00042848692932995094, 'samples': 19734016, 'steps': 38542, 'loss/train': 1.6909945011138916}
-03/05/2022 10:46:15 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/05/2022 10:46:20 - INFO - codeparrot_training - Step 38543: {'lr': 0.0004284832135125886, 'samples': 19734528, 'steps': 38543, 'loss/train': 2.103565216064453}
-03/05/2022 10:46:24 - INFO - codeparrot_training - Step 38544: {'lr': 0.0004284794976148044, 'samples': 19735040, 'steps': 38544, 'loss/train': 0.9235674738883972}
-03/05/2022 10:46:25 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/05/2022 10:46:29 - INFO - codeparrot_training - Step 38545: {'lr': 0.00042847578163660016, 'samples': 19735552, 'steps': 38545, 'loss/train': 1.887497901916504}
-03/05/2022 10:46:32 - INFO - codeparrot_training - Step 38546: {'lr': 0.0004284720655779775, 'samples': 19736064, 'steps': 38546, 'loss/train': 1.1920284032821655}
-03/05/2022 10:46:34 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/05/2022 10:46:37 - INFO - codeparrot_training - Step 38547: {'lr': 0.00042846834943893806, 'samples': 19736576, 'steps': 38547, 'loss/train': 1.0208882093429565}
-03/05/2022 10:46:41 - INFO - codeparrot_training - Step 38548: {'lr': 0.0004284646332194836, 'samples': 19737088, 'steps': 38548, 'loss/train': 1.93416166305542}
-03/05/2022 10:46:42 - INFO - codeparrot_training - Skipping example with length 64 (seq_length=1024)
-03/05/2022 10:46:46 - INFO - codeparrot_training - Step 38549: {'lr': 0.0004284609169196156, 'samples': 19737600, 'steps': 38549, 'loss/train': 1.3960152864456177}
-03/05/2022 10:46:49 - INFO - codeparrot_training - Step 38550: {'lr': 0.000428457200539336, 'samples': 19738112, 'steps': 38550, 'loss/train': 1.6571820974349976}
-03/05/2022 10:46:50 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/05/2022 10:46:54 - INFO - codeparrot_training - Step 38551: {'lr': 0.0004284534840786463, 'samples': 19738624, 'steps': 38551, 'loss/train': 2.549018621444702}
-03/05/2022 10:46:57 - INFO - codeparrot_training - Step 38552: {'lr': 0.0004284497675375482, 'samples': 19739136, 'steps': 38552, 'loss/train': 1.8719671964645386}
-03/05/2022 10:46:59 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/05/2022 10:47:03 - INFO - codeparrot_training - Step 38553: {'lr': 0.0004284460509160433, 'samples': 19739648, 'steps': 38553, 'loss/train': 1.4957520961761475}
-03/05/2022 10:47:06 - INFO - codeparrot_training - Step 38554: {'lr': 0.0004284423342141335, 'samples': 19740160, 'steps': 38554, 'loss/train': 1.7202802896499634}
-03/05/2022 10:47:07 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/05/2022 10:47:11 - INFO - codeparrot_training - Step 38555: {'lr': 0.0004284386174318202, 'samples': 19740672, 'steps': 38555, 'loss/train': 1.4221858978271484}
-03/05/2022 10:47:14 - INFO - codeparrot_training - Step 38556: {'lr': 0.00042843490056910534, 'samples': 19741184, 'steps': 38556, 'loss/train': 2.270695447921753}
-03/05/2022 10:47:16 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/05/2022 10:47:20 - INFO - codeparrot_training - Step 38557: {'lr': 0.00042843118362599045, 'samples': 19741696, 'steps': 38557, 'loss/train': 0.9776784777641296}
-03/05/2022 10:47:23 - INFO - codeparrot_training - Step 38558: {'lr': 0.0004284274666024772, 'samples': 19742208, 'steps': 38558, 'loss/train': 1.7199122905731201}
-03/05/2022 10:47:25 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/05/2022 10:47:28 - INFO - codeparrot_training - Step 38559: {'lr': 0.0004284237494985672, 'samples': 19742720, 'steps': 38559, 'loss/train': 2.3708810806274414}
-03/05/2022 10:47:31 - INFO - codeparrot_training - Step 38560: {'lr': 0.0004284200323142623, 'samples': 19743232, 'steps': 38560, 'loss/train': 1.0397006273269653}
-03/05/2022 10:47:33 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/05/2022 10:47:36 - INFO - codeparrot_training - Step 38561: {'lr': 0.0004284163150495641, 'samples': 19743744, 'steps': 38561, 'loss/train': 1.5603466033935547}
-03/05/2022 10:47:40 - INFO - codeparrot_training - Step 38562: {'lr': 0.00042841259770447427, 'samples': 19744256, 'steps': 38562, 'loss/train': 1.3002595901489258}
-03/05/2022 10:47:42 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/05/2022 10:47:45 - INFO - codeparrot_training - Step 38563: {'lr': 0.00042840888027899436, 'samples': 19744768, 'steps': 38563, 'loss/train': 1.3120273351669312}
-03/05/2022 10:47:48 - INFO - codeparrot_training - Step 38564: {'lr': 0.0004284051627731263, 'samples': 19745280, 'steps': 38564, 'loss/train': 1.7188363075256348}
-03/05/2022 10:47:50 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 10:47:53 - INFO - codeparrot_training - Step 38565: {'lr': 0.0004284014451868716, 'samples': 19745792, 'steps': 38565, 'loss/train': 1.7081656455993652}
-03/05/2022 10:47:57 - INFO - codeparrot_training - Step 38566: {'lr': 0.0004283977275202319, 'samples': 19746304, 'steps': 38566, 'loss/train': 1.6099004745483398}
-03/05/2022 10:47:59 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 10:48:02 - INFO - codeparrot_training - Step 38567: {'lr': 0.00042839400977320895, 'samples': 19746816, 'steps': 38567, 'loss/train': 2.3459300994873047}
-03/05/2022 10:48:05 - INFO - codeparrot_training - Step 38568: {'lr': 0.00042839029194580446, 'samples': 19747328, 'steps': 38568, 'loss/train': 1.554349422454834}
-03/05/2022 10:48:08 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 10:48:10 - INFO - codeparrot_training - Step 38569: {'lr': 0.0004283865740380201, 'samples': 19747840, 'steps': 38569, 'loss/train': 0.7890869975090027}
-03/05/2022 10:48:13 - INFO - codeparrot_training - Step 38570: {'lr': 0.0004283828560498574, 'samples': 19748352, 'steps': 38570, 'loss/train': 1.869735598564148}
-03/05/2022 10:48:16 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 10:48:19 - INFO - codeparrot_training - Step 38571: {'lr': 0.0004283791379813181, 'samples': 19748864, 'steps': 38571, 'loss/train': 1.8651947975158691}
-03/05/2022 10:48:22 - INFO - codeparrot_training - Step 38572: {'lr': 0.000428375419832404, 'samples': 19749376, 'steps': 38572, 'loss/train': 1.8675826787948608}
-03/05/2022 10:48:24 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 10:48:27 - INFO - codeparrot_training - Step 38573: {'lr': 0.0004283717016031167, 'samples': 19749888, 'steps': 38573, 'loss/train': 2.1053853034973145}
-03/05/2022 10:48:30 - INFO - codeparrot_training - Step 38574: {'lr': 0.0004283679832934578, 'samples': 19750400, 'steps': 38574, 'loss/train': 0.6932262182235718}
-03/05/2022 10:48:33 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/05/2022 10:48:36 - INFO - codeparrot_training - Step 38575: {'lr': 0.0004283642649034291, 'samples': 19750912, 'steps': 38575, 'loss/train': 0.21700908243656158}
-03/05/2022 10:48:39 - INFO - codeparrot_training - Step 38576: {'lr': 0.00042836054643303226, 'samples': 19751424, 'steps': 38576, 'loss/train': 1.4597054719924927}
-03/05/2022 10:48:41 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/05/2022 10:48:44 - INFO - codeparrot_training - Step 38577: {'lr': 0.0004283568278822688, 'samples': 19751936, 'steps': 38577, 'loss/train': 1.5350946187973022}
-03/05/2022 10:48:47 - INFO - codeparrot_training - Step 38578: {'lr': 0.0004283531092511405, 'samples': 19752448, 'steps': 38578, 'loss/train': 2.6010589599609375}
-03/05/2022 10:48:50 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/05/2022 10:48:52 - INFO - codeparrot_training - Step 38579: {'lr': 0.0004283493905396491, 'samples': 19752960, 'steps': 38579, 'loss/train': 1.8193868398666382}
-03/05/2022 10:48:56 - INFO - codeparrot_training - Step 38580: {'lr': 0.00042834567174779623, 'samples': 19753472, 'steps': 38580, 'loss/train': 1.417906403541565}
-03/05/2022 10:48:58 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/05/2022 10:49:01 - INFO - codeparrot_training - Step 38581: {'lr': 0.00042834195287558356, 'samples': 19753984, 'steps': 38581, 'loss/train': 2.005946636199951}
-03/05/2022 10:49:04 - INFO - codeparrot_training - Step 38582: {'lr': 0.00042833823392301264, 'samples': 19754496, 'steps': 38582, 'loss/train': 1.4937937259674072}
-03/05/2022 10:49:07 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 10:49:09 - INFO - codeparrot_training - Step 38583: {'lr': 0.00042833451489008537, 'samples': 19755008, 'steps': 38583, 'loss/train': 2.0779855251312256}
-03/05/2022 10:49:13 - INFO - codeparrot_training - Step 38584: {'lr': 0.00042833079577680327, 'samples': 19755520, 'steps': 38584, 'loss/train': 1.7298463582992554}
-03/05/2022 10:49:15 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/05/2022 10:49:18 - INFO - codeparrot_training - Step 38585: {'lr': 0.0004283270765831682, 'samples': 19756032, 'steps': 38585, 'loss/train': 1.1656309366226196}
-03/05/2022 10:49:21 - INFO - codeparrot_training - Step 38586: {'lr': 0.00042832335730918147, 'samples': 19756544, 'steps': 38586, 'loss/train': 1.3866567611694336}
-03/05/2022 10:49:23 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/05/2022 10:49:26 - INFO - codeparrot_training - Step 38587: {'lr': 0.0004283196379548451, 'samples': 19757056, 'steps': 38587, 'loss/train': 1.151247501373291}
-03/05/2022 10:49:29 - INFO - codeparrot_training - Step 38588: {'lr': 0.0004283159185201607, 'samples': 19757568, 'steps': 38588, 'loss/train': 0.9604315161705017}
-03/05/2022 10:49:32 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/05/2022 10:49:35 - INFO - codeparrot_training - Step 38589: {'lr': 0.00042831219900512984, 'samples': 19758080, 'steps': 38589, 'loss/train': 1.278340220451355}
-03/05/2022 10:49:38 - INFO - codeparrot_training - Step 38590: {'lr': 0.0004283084794097543, 'samples': 19758592, 'steps': 38590, 'loss/train': 2.15201997756958}
-03/05/2022 10:49:40 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/05/2022 10:49:43 - INFO - codeparrot_training - Step 38591: {'lr': 0.00042830475973403573, 'samples': 19759104, 'steps': 38591, 'loss/train': 1.961279273033142}
-03/05/2022 10:49:46 - INFO - codeparrot_training - Step 38592: {'lr': 0.0004283010399779757, 'samples': 19759616, 'steps': 38592, 'loss/train': 1.8723347187042236}
-03/05/2022 10:49:49 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/05/2022 10:49:52 - INFO - codeparrot_training - Step 38593: {'lr': 0.000428297320141576, 'samples': 19760128, 'steps': 38593, 'loss/train': 1.3374814987182617}
-03/05/2022 10:49:55 - INFO - codeparrot_training - Step 38594: {'lr': 0.0004282936002248383, 'samples': 19760640, 'steps': 38594, 'loss/train': 1.701419472694397}
-03/05/2022 10:49:57 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/05/2022 10:50:00 - INFO - codeparrot_training - Step 38595: {'lr': 0.00042828988022776426, 'samples': 19761152, 'steps': 38595, 'loss/train': 1.9581539630889893}
-03/05/2022 10:50:03 - INFO - codeparrot_training - Step 38596: {'lr': 0.00042828616015035554, 'samples': 19761664, 'steps': 38596, 'loss/train': 2.0897247791290283}
-03/05/2022 10:50:05 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/05/2022 10:50:08 - INFO - codeparrot_training - Step 38597: {'lr': 0.00042828243999261384, 'samples': 19762176, 'steps': 38597, 'loss/train': 1.3530045747756958}
-03/05/2022 10:50:12 - INFO - codeparrot_training - Step 38598: {'lr': 0.0004282787197545408, 'samples': 19762688, 'steps': 38598, 'loss/train': 1.7269246578216553}
-03/05/2022 10:50:14 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/05/2022 10:50:17 - INFO - codeparrot_training - Step 38599: {'lr': 0.00042827499943613815, 'samples': 19763200, 'steps': 38599, 'loss/train': 1.3811802864074707}
-03/05/2022 10:50:20 - INFO - codeparrot_training - Step 38600: {'lr': 0.00042827127903740747, 'samples': 19763712, 'steps': 38600, 'loss/train': 1.5921295881271362}
-03/05/2022 10:50:22 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/05/2022 10:50:25 - INFO - codeparrot_training - Step 38601: {'lr': 0.00042826755855835053, 'samples': 19764224, 'steps': 38601, 'loss/train': 2.2554805278778076}
-03/05/2022 10:50:28 - INFO - codeparrot_training - Step 38602: {'lr': 0.00042826383799896906, 'samples': 19764736, 'steps': 38602, 'loss/train': 1.2390189170837402}
-03/05/2022 10:50:30 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 10:50:34 - INFO - codeparrot_training - Step 38603: {'lr': 0.0004282601173592646, 'samples': 19765248, 'steps': 38603, 'loss/train': 1.8256912231445312}
-03/05/2022 10:50:37 - INFO - codeparrot_training - Step 38604: {'lr': 0.0004282563966392389, 'samples': 19765760, 'steps': 38604, 'loss/train': 1.633636236190796}
-03/05/2022 10:50:39 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/05/2022 10:50:42 - INFO - codeparrot_training - Step 38605: {'lr': 0.00042825267583889354, 'samples': 19766272, 'steps': 38605, 'loss/train': 1.9993391036987305}
-03/05/2022 10:50:45 - INFO - codeparrot_training - Step 38606: {'lr': 0.00042824895495823033, 'samples': 19766784, 'steps': 38606, 'loss/train': 1.3982343673706055}
-03/05/2022 10:50:47 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/05/2022 10:50:51 - INFO - codeparrot_training - Step 38607: {'lr': 0.0004282452339972509, 'samples': 19767296, 'steps': 38607, 'loss/train': 0.9934396743774414}
-03/05/2022 10:50:54 - INFO - codeparrot_training - Step 38608: {'lr': 0.00042824151295595695, 'samples': 19767808, 'steps': 38608, 'loss/train': 1.7043061256408691}
-03/05/2022 10:50:56 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/05/2022 10:50:59 - INFO - codeparrot_training - Step 38609: {'lr': 0.0004282377918343501, 'samples': 19768320, 'steps': 38609, 'loss/train': 1.615700125694275}
-03/05/2022 10:51:02 - INFO - codeparrot_training - Step 38610: {'lr': 0.00042823407063243197, 'samples': 19768832, 'steps': 38610, 'loss/train': 2.120128870010376}
-03/05/2022 10:51:04 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/05/2022 10:51:08 - INFO - codeparrot_training - Step 38611: {'lr': 0.0004282303493502044, 'samples': 19769344, 'steps': 38611, 'loss/train': 1.086856484413147}
-03/05/2022 10:51:11 - INFO - codeparrot_training - Step 38612: {'lr': 0.000428226627987669, 'samples': 19769856, 'steps': 38612, 'loss/train': 2.3484725952148438}
-03/05/2022 10:51:13 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/05/2022 10:51:16 - INFO - codeparrot_training - Step 38613: {'lr': 0.0004282229065448273, 'samples': 19770368, 'steps': 38613, 'loss/train': 1.9675817489624023}
-03/05/2022 10:51:19 - INFO - codeparrot_training - Step 38614: {'lr': 0.0004282191850216812, 'samples': 19770880, 'steps': 38614, 'loss/train': 1.7232468128204346}
-03/05/2022 10:51:21 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/05/2022 10:51:25 - INFO - codeparrot_training - Step 38615: {'lr': 0.00042821546341823236, 'samples': 19771392, 'steps': 38615, 'loss/train': 1.9659581184387207}
-03/05/2022 10:51:28 - INFO - codeparrot_training - Step 38616: {'lr': 0.0004282117417344823, 'samples': 19771904, 'steps': 38616, 'loss/train': 1.4936696290969849}
-03/05/2022 10:51:29 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/05/2022 10:51:33 - INFO - codeparrot_training - Step 38617: {'lr': 0.00042820801997043277, 'samples': 19772416, 'steps': 38617, 'loss/train': 1.7274147272109985}
-03/05/2022 10:51:36 - INFO - codeparrot_training - Step 38618: {'lr': 0.0004282042981260855, 'samples': 19772928, 'steps': 38618, 'loss/train': 1.0664881467819214}
-03/05/2022 10:51:38 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/05/2022 10:51:41 - INFO - codeparrot_training - Step 38619: {'lr': 0.00042820057620144214, 'samples': 19773440, 'steps': 38619, 'loss/train': 1.968578815460205}
-03/05/2022 10:51:45 - INFO - codeparrot_training - Step 38620: {'lr': 0.00042819685419650427, 'samples': 19773952, 'steps': 38620, 'loss/train': 1.3703964948654175}
-03/05/2022 10:51:46 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/05/2022 10:51:50 - INFO - codeparrot_training - Step 38621: {'lr': 0.0004281931321112737, 'samples': 19774464, 'steps': 38621, 'loss/train': 2.0736982822418213}
-03/05/2022 10:51:53 - INFO - codeparrot_training - Step 38622: {'lr': 0.0004281894099457521, 'samples': 19774976, 'steps': 38622, 'loss/train': 1.7980878353118896}
-03/05/2022 10:51:55 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/05/2022 10:51:58 - INFO - codeparrot_training - Step 38623: {'lr': 0.00042818568769994103, 'samples': 19775488, 'steps': 38623, 'loss/train': 1.9836076498031616}
-03/05/2022 10:52:02 - INFO - codeparrot_training - Step 38624: {'lr': 0.00042818196537384225, 'samples': 19776000, 'steps': 38624, 'loss/train': 1.7218974828720093}
-03/05/2022 10:52:03 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/05/2022 10:52:07 - INFO - codeparrot_training - Step 38625: {'lr': 0.0004281782429674574, 'samples': 19776512, 'steps': 38625, 'loss/train': 1.5606465339660645}
-03/05/2022 10:52:10 - INFO - codeparrot_training - Step 38626: {'lr': 0.0004281745204807882, 'samples': 19777024, 'steps': 38626, 'loss/train': 1.6349729299545288}
-03/05/2022 10:52:11 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/05/2022 10:52:16 - INFO - codeparrot_training - Step 38627: {'lr': 0.00042817079791383636, 'samples': 19777536, 'steps': 38627, 'loss/train': 1.1947542428970337}
-03/05/2022 10:52:19 - INFO - codeparrot_training - Step 38628: {'lr': 0.00042816707526660346, 'samples': 19778048, 'steps': 38628, 'loss/train': 2.1859982013702393}
-03/05/2022 10:52:22 - INFO - codeparrot_training - Step 38629: {'lr': 0.00042816335253909125, 'samples': 19778560, 'steps': 38629, 'loss/train': 1.2326762676239014}
-03/05/2022 10:52:23 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/05/2022 10:52:27 - INFO - codeparrot_training - Step 38630: {'lr': 0.00042815962973130134, 'samples': 19779072, 'steps': 38630, 'loss/train': 1.9942691326141357}
-03/05/2022 10:52:31 - INFO - codeparrot_training - Step 38631: {'lr': 0.00042815590684323554, 'samples': 19779584, 'steps': 38631, 'loss/train': 1.3765051364898682}
-03/05/2022 10:52:32 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/05/2022 10:52:36 - INFO - codeparrot_training - Step 38632: {'lr': 0.00042815218387489535, 'samples': 19780096, 'steps': 38632, 'loss/train': 1.4062714576721191}
-03/05/2022 10:52:39 - INFO - codeparrot_training - Step 38633: {'lr': 0.00042814846082628256, 'samples': 19780608, 'steps': 38633, 'loss/train': 1.376347541809082}
-03/05/2022 10:52:40 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/05/2022 10:52:44 - INFO - codeparrot_training - Step 38634: {'lr': 0.0004281447376973988, 'samples': 19781120, 'steps': 38634, 'loss/train': 0.3564392626285553}
-03/05/2022 10:52:48 - INFO - codeparrot_training - Step 38635: {'lr': 0.00042814101448824583, 'samples': 19781632, 'steps': 38635, 'loss/train': 0.6985551714897156}
-03/05/2022 10:52:49 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/05/2022 10:52:53 - INFO - codeparrot_training - Step 38636: {'lr': 0.0004281372911988253, 'samples': 19782144, 'steps': 38636, 'loss/train': 1.8874304294586182}
-03/05/2022 10:52:56 - INFO - codeparrot_training - Step 38637: {'lr': 0.0004281335678291387, 'samples': 19782656, 'steps': 38637, 'loss/train': 0.5189992785453796}
-03/05/2022 10:52:57 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/05/2022 10:53:01 - INFO - codeparrot_training - Step 38638: {'lr': 0.000428129844379188, 'samples': 19783168, 'steps': 38638, 'loss/train': 2.2223095893859863}
-03/05/2022 10:53:04 - INFO - codeparrot_training - Step 38639: {'lr': 0.0004281261208489747, 'samples': 19783680, 'steps': 38639, 'loss/train': 1.2589397430419922}
-03/05/2022 10:53:06 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/05/2022 10:53:10 - INFO - codeparrot_training - Step 38640: {'lr': 0.0004281223972385004, 'samples': 19784192, 'steps': 38640, 'loss/train': 2.13358736038208}
-03/05/2022 10:53:13 - INFO - codeparrot_training - Step 38641: {'lr': 0.00042811867354776705, 'samples': 19784704, 'steps': 38641, 'loss/train': 1.143943428993225}
-03/05/2022 10:53:14 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/05/2022 10:53:18 - INFO - codeparrot_training - Step 38642: {'lr': 0.0004281149497767761, 'samples': 19785216, 'steps': 38642, 'loss/train': 2.351257801055908}
-03/05/2022 10:53:21 - INFO - codeparrot_training - Step 38643: {'lr': 0.00042811122592552943, 'samples': 19785728, 'steps': 38643, 'loss/train': 1.195041298866272}
-03/05/2022 10:53:23 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/05/2022 10:53:27 - INFO - codeparrot_training - Step 38644: {'lr': 0.0004281075019940285, 'samples': 19786240, 'steps': 38644, 'loss/train': 1.746843695640564}
-03/05/2022 10:53:30 - INFO - codeparrot_training - Step 38645: {'lr': 0.00042810377798227506, 'samples': 19786752, 'steps': 38645, 'loss/train': 1.6408380270004272}
-03/05/2022 10:53:32 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/05/2022 10:53:35 - INFO - codeparrot_training - Step 38646: {'lr': 0.00042810005389027077, 'samples': 19787264, 'steps': 38646, 'loss/train': 1.030151128768921}
-03/05/2022 10:53:38 - INFO - codeparrot_training - Step 38647: {'lr': 0.0004280963297180174, 'samples': 19787776, 'steps': 38647, 'loss/train': 2.090975761413574}
-03/05/2022 10:53:40 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/05/2022 10:53:44 - INFO - codeparrot_training - Step 38648: {'lr': 0.0004280926054655165, 'samples': 19788288, 'steps': 38648, 'loss/train': 1.7622849941253662}
-03/05/2022 10:53:47 - INFO - codeparrot_training - Step 38649: {'lr': 0.00042808888113277, 'samples': 19788800, 'steps': 38649, 'loss/train': 1.4865052700042725}
-03/05/2022 10:53:48 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/05/2022 10:53:52 - INFO - codeparrot_training - Step 38650: {'lr': 0.0004280851567197792, 'samples': 19789312, 'steps': 38650, 'loss/train': 2.0519843101501465}
-03/05/2022 10:53:55 - INFO - codeparrot_training - Step 38651: {'lr': 0.0004280814322265461, 'samples': 19789824, 'steps': 38651, 'loss/train': 1.7303141355514526}
-03/05/2022 10:53:57 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/05/2022 10:54:00 - INFO - codeparrot_training - Step 38652: {'lr': 0.00042807770765307217, 'samples': 19790336, 'steps': 38652, 'loss/train': 1.8099050521850586}
-03/05/2022 10:54:03 - INFO - codeparrot_training - Step 38653: {'lr': 0.00042807398299935927, 'samples': 19790848, 'steps': 38653, 'loss/train': 1.7953767776489258}
-03/05/2022 10:54:05 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 10:54:09 - INFO - codeparrot_training - Step 38654: {'lr': 0.0004280702582654089, 'samples': 19791360, 'steps': 38654, 'loss/train': 1.7514424324035645}
-03/05/2022 10:54:12 - INFO - codeparrot_training - Step 38655: {'lr': 0.00042806653345122287, 'samples': 19791872, 'steps': 38655, 'loss/train': 2.2963011264801025}
-03/05/2022 10:54:13 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 10:54:18 - INFO - codeparrot_training - Step 38656: {'lr': 0.0004280628085568028, 'samples': 19792384, 'steps': 38656, 'loss/train': 2.1349875926971436}
-03/05/2022 10:54:21 - INFO - codeparrot_training - Step 38657: {'lr': 0.0004280590835821503, 'samples': 19792896, 'steps': 38657, 'loss/train': 1.9335001707077026}
-03/05/2022 10:54:24 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/05/2022 10:54:26 - INFO - codeparrot_training - Step 38658: {'lr': 0.0004280553585272672, 'samples': 19793408, 'steps': 38658, 'loss/train': 2.258563756942749}
-03/05/2022 10:54:29 - INFO - codeparrot_training - Step 38659: {'lr': 0.0004280516333921551, 'samples': 19793920, 'steps': 38659, 'loss/train': 1.7108283042907715}
-03/05/2022 10:54:32 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/05/2022 10:54:34 - INFO - codeparrot_training - Step 38660: {'lr': 0.00042804790817681574, 'samples': 19794432, 'steps': 38660, 'loss/train': 1.5322532653808594}
-03/05/2022 10:54:38 - INFO - codeparrot_training - Step 38661: {'lr': 0.0004280441828812506, 'samples': 19794944, 'steps': 38661, 'loss/train': 2.0229928493499756}
-03/05/2022 10:54:40 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/05/2022 10:54:43 - INFO - codeparrot_training - Step 38662: {'lr': 0.0004280404575054616, 'samples': 19795456, 'steps': 38662, 'loss/train': 2.127798557281494}
-03/05/2022 10:54:46 - INFO - codeparrot_training - Step 38663: {'lr': 0.00042803673204945027, 'samples': 19795968, 'steps': 38663, 'loss/train': 1.6988143920898438}
-03/05/2022 10:54:49 - INFO - codeparrot_training - Step 38664: {'lr': 0.0004280330065132184, 'samples': 19796480, 'steps': 38664, 'loss/train': 1.4765651226043701}
-03/05/2022 10:54:49 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/05/2022 10:54:55 - INFO - codeparrot_training - Step 38665: {'lr': 0.0004280292808967675, 'samples': 19796992, 'steps': 38665, 'loss/train': 1.7284808158874512}
-03/05/2022 10:54:58 - INFO - codeparrot_training - Step 38666: {'lr': 0.00042802555520009945, 'samples': 19797504, 'steps': 38666, 'loss/train': 1.4485489130020142}
-03/05/2022 10:54:58 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/05/2022 10:55:03 - INFO - codeparrot_training - Step 38667: {'lr': 0.00042802182942321576, 'samples': 19798016, 'steps': 38667, 'loss/train': 1.9016871452331543}
-03/05/2022 10:55:06 - INFO - codeparrot_training - Step 38668: {'lr': 0.0004280181035661182, 'samples': 19798528, 'steps': 38668, 'loss/train': 1.8893183469772339}
-03/05/2022 10:55:06 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/05/2022 10:55:12 - INFO - codeparrot_training - Step 38669: {'lr': 0.0004280143776288085, 'samples': 19799040, 'steps': 38669, 'loss/train': 1.8285330533981323}
-03/05/2022 10:55:15 - INFO - codeparrot_training - Step 38670: {'lr': 0.00042801065161128814, 'samples': 19799552, 'steps': 38670, 'loss/train': 1.621121883392334}
-03/05/2022 10:55:15 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/05/2022 10:55:20 - INFO - codeparrot_training - Step 38671: {'lr': 0.000428006925513559, 'samples': 19800064, 'steps': 38671, 'loss/train': 1.0969856977462769}
-03/05/2022 10:55:23 - INFO - codeparrot_training - Step 38672: {'lr': 0.0004280031993356227, 'samples': 19800576, 'steps': 38672, 'loss/train': 1.7955394983291626}
-03/05/2022 10:55:23 - INFO - codeparrot_training - Skipping example with length 933 (seq_length=1024)
-03/05/2022 10:55:29 - INFO - codeparrot_training - Step 38673: {'lr': 0.00042799947307748087, 'samples': 19801088, 'steps': 38673, 'loss/train': 1.721825361251831}
-03/05/2022 10:55:32 - INFO - codeparrot_training - Step 38674: {'lr': 0.0004279957467391353, 'samples': 19801600, 'steps': 38674, 'loss/train': 1.8524703979492188}
-03/05/2022 10:55:32 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/05/2022 10:55:37 - INFO - codeparrot_training - Step 38675: {'lr': 0.0004279920203205875, 'samples': 19802112, 'steps': 38675, 'loss/train': 1.9428575038909912}
-03/05/2022 10:55:40 - INFO - codeparrot_training - Step 38676: {'lr': 0.0004279882938218393, 'samples': 19802624, 'steps': 38676, 'loss/train': 1.6895110607147217}
-03/05/2022 10:55:41 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 10:55:46 - INFO - codeparrot_training - Step 38677: {'lr': 0.00042798456724289227, 'samples': 19803136, 'steps': 38677, 'loss/train': 1.3026678562164307}
-03/05/2022 10:55:49 - INFO - codeparrot_training - Step 38678: {'lr': 0.0004279808405837482, 'samples': 19803648, 'steps': 38678, 'loss/train': 1.7309794425964355}
-03/05/2022 10:55:49 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/05/2022 10:55:54 - INFO - codeparrot_training - Step 38679: {'lr': 0.00042797711384440863, 'samples': 19804160, 'steps': 38679, 'loss/train': 0.68036288022995}
-03/05/2022 10:55:57 - INFO - codeparrot_training - Step 38680: {'lr': 0.0004279733870248754, 'samples': 19804672, 'steps': 38680, 'loss/train': 0.11509339511394501}
-03/05/2022 10:55:58 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/05/2022 10:56:03 - INFO - codeparrot_training - Step 38681: {'lr': 0.00042796966012515007, 'samples': 19805184, 'steps': 38681, 'loss/train': 1.5195715427398682}
-03/05/2022 10:56:06 - INFO - codeparrot_training - Step 38682: {'lr': 0.00042796593314523435, 'samples': 19805696, 'steps': 38682, 'loss/train': 1.5905025005340576}
-03/05/2022 10:56:06 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/05/2022 10:56:11 - INFO - codeparrot_training - Step 38683: {'lr': 0.0004279622060851299, 'samples': 19806208, 'steps': 38683, 'loss/train': 1.454941749572754}
-03/05/2022 10:56:14 - INFO - codeparrot_training - Step 38684: {'lr': 0.0004279584789448385, 'samples': 19806720, 'steps': 38684, 'loss/train': 1.9202710390090942}
-03/05/2022 10:56:14 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/05/2022 10:56:20 - INFO - codeparrot_training - Step 38685: {'lr': 0.0004279547517243617, 'samples': 19807232, 'steps': 38685, 'loss/train': 1.9013594388961792}
-03/05/2022 10:56:23 - INFO - codeparrot_training - Step 38686: {'lr': 0.00042795102442370127, 'samples': 19807744, 'steps': 38686, 'loss/train': 1.8321306705474854}
-03/05/2022 10:56:25 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/05/2022 10:56:28 - INFO - codeparrot_training - Step 38687: {'lr': 0.0004279472970428588, 'samples': 19808256, 'steps': 38687, 'loss/train': 0.45099449157714844}
-03/05/2022 10:56:31 - INFO - codeparrot_training - Step 38688: {'lr': 0.0004279435695818361, 'samples': 19808768, 'steps': 38688, 'loss/train': 2.146911144256592}
-03/05/2022 10:56:33 - INFO - codeparrot_training - Skipping example with length 719 (seq_length=1024)
-03/05/2022 10:56:37 - INFO - codeparrot_training - Step 38689: {'lr': 0.00042793984204063477, 'samples': 19809280, 'steps': 38689, 'loss/train': 0.9639469385147095}
-03/05/2022 10:56:40 - INFO - codeparrot_training - Step 38690: {'lr': 0.0004279361144192565, 'samples': 19809792, 'steps': 38690, 'loss/train': 2.060373306274414}
-03/05/2022 10:56:42 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/05/2022 10:56:45 - INFO - codeparrot_training - Step 38691: {'lr': 0.00042793238671770285, 'samples': 19810304, 'steps': 38691, 'loss/train': 1.6125714778900146}
-03/05/2022 10:56:48 - INFO - codeparrot_training - Step 38692: {'lr': 0.0004279286589359757, 'samples': 19810816, 'steps': 38692, 'loss/train': 2.0662548542022705}
-03/05/2022 10:56:50 - INFO - codeparrot_training - Skipping example with length 403 (seq_length=1024)
-03/05/2022 10:56:53 - INFO - codeparrot_training - Step 38693: {'lr': 0.00042792493107407666, 'samples': 19811328, 'steps': 38693, 'loss/train': 1.3314414024353027}
-03/05/2022 10:56:57 - INFO - codeparrot_training - Step 38694: {'lr': 0.0004279212031320073, 'samples': 19811840, 'steps': 38694, 'loss/train': 1.3986852169036865}
-03/05/2022 10:56:58 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 10:57:02 - INFO - codeparrot_training - Step 38695: {'lr': 0.00042791747510976955, 'samples': 19812352, 'steps': 38695, 'loss/train': 2.0740137100219727}
-03/05/2022 10:57:05 - INFO - codeparrot_training - Step 38696: {'lr': 0.0004279137470073648, 'samples': 19812864, 'steps': 38696, 'loss/train': 1.3599504232406616}
-03/05/2022 10:57:07 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/05/2022 10:57:10 - INFO - codeparrot_training - Step 38697: {'lr': 0.00042791001882479485, 'samples': 19813376, 'steps': 38697, 'loss/train': 1.604630470275879}
-03/05/2022 10:57:13 - INFO - codeparrot_training - Step 38698: {'lr': 0.0004279062905620614, 'samples': 19813888, 'steps': 38698, 'loss/train': 2.0248091220855713}
-03/05/2022 10:57:15 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/05/2022 10:57:19 - INFO - codeparrot_training - Step 38699: {'lr': 0.0004279025622191662, 'samples': 19814400, 'steps': 38699, 'loss/train': 1.6676723957061768}
-03/05/2022 10:57:22 - INFO - codeparrot_training - Step 38700: {'lr': 0.00042789883379611084, 'samples': 19814912, 'steps': 38700, 'loss/train': 1.0747770071029663}
-03/05/2022 10:57:23 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/05/2022 10:57:27 - INFO - codeparrot_training - Step 38701: {'lr': 0.000427895105292897, 'samples': 19815424, 'steps': 38701, 'loss/train': 2.4207370281219482}
-03/05/2022 10:57:30 - INFO - codeparrot_training - Step 38702: {'lr': 0.00042789137670952627, 'samples': 19815936, 'steps': 38702, 'loss/train': 1.5905373096466064}
-03/05/2022 10:57:32 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/05/2022 10:57:36 - INFO - codeparrot_training - Step 38703: {'lr': 0.00042788764804600055, 'samples': 19816448, 'steps': 38703, 'loss/train': 1.7638393640518188}
-03/05/2022 10:57:39 - INFO - codeparrot_training - Step 38704: {'lr': 0.0004278839193023214, 'samples': 19816960, 'steps': 38704, 'loss/train': 2.8547465801239014}
-03/05/2022 10:57:40 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/05/2022 10:57:44 - INFO - codeparrot_training - Step 38705: {'lr': 0.0004278801904784904, 'samples': 19817472, 'steps': 38705, 'loss/train': 1.4887999296188354}
-03/05/2022 10:57:47 - INFO - codeparrot_training - Step 38706: {'lr': 0.00042787646157450946, 'samples': 19817984, 'steps': 38706, 'loss/train': 1.9794522523880005}
-03/05/2022 10:57:49 - INFO - codeparrot_training - Skipping example with length 925 (seq_length=1024)
-03/05/2022 10:57:53 - INFO - codeparrot_training - Step 38707: {'lr': 0.00042787273259038, 'samples': 19818496, 'steps': 38707, 'loss/train': 1.415533185005188}
-03/05/2022 10:57:56 - INFO - codeparrot_training - Step 38708: {'lr': 0.00042786900352610393, 'samples': 19819008, 'steps': 38708, 'loss/train': 1.7790294885635376}
-03/05/2022 10:57:57 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/05/2022 10:58:01 - INFO - codeparrot_training - Step 38709: {'lr': 0.0004278652743816828, 'samples': 19819520, 'steps': 38709, 'loss/train': 1.8970950841903687}
-03/05/2022 10:58:05 - INFO - codeparrot_training - Step 38710: {'lr': 0.00042786154515711826, 'samples': 19820032, 'steps': 38710, 'loss/train': 0.8318291306495667}
-03/05/2022 10:58:08 - INFO - codeparrot_training - Step 38711: {'lr': 0.0004278578158524121, 'samples': 19820544, 'steps': 38711, 'loss/train': 1.8872073888778687}
-03/05/2022 10:58:08 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/05/2022 10:58:13 - INFO - codeparrot_training - Step 38712: {'lr': 0.00042785408646756594, 'samples': 19821056, 'steps': 38712, 'loss/train': 1.2877286672592163}
-03/05/2022 10:58:16 - INFO - codeparrot_training - Step 38713: {'lr': 0.0004278503570025816, 'samples': 19821568, 'steps': 38713, 'loss/train': 1.9119843244552612}
-03/05/2022 10:58:16 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/05/2022 10:58:21 - INFO - codeparrot_training - Step 38714: {'lr': 0.0004278466274574605, 'samples': 19822080, 'steps': 38714, 'loss/train': 0.7957173585891724}
-03/05/2022 10:58:25 - INFO - codeparrot_training - Step 38715: {'lr': 0.0004278428978322044, 'samples': 19822592, 'steps': 38715, 'loss/train': 2.0226762294769287}
-03/05/2022 10:58:25 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/05/2022 10:58:30 - INFO - codeparrot_training - Step 38716: {'lr': 0.00042783916812681516, 'samples': 19823104, 'steps': 38716, 'loss/train': 1.6795921325683594}
-03/05/2022 10:58:33 - INFO - codeparrot_training - Step 38717: {'lr': 0.0004278354383412943, 'samples': 19823616, 'steps': 38717, 'loss/train': 2.1372222900390625}
-03/05/2022 10:58:33 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/05/2022 10:58:38 - INFO - codeparrot_training - Step 38718: {'lr': 0.0004278317084756435, 'samples': 19824128, 'steps': 38718, 'loss/train': 1.7832385301589966}
-03/05/2022 10:58:41 - INFO - codeparrot_training - Step 38719: {'lr': 0.00042782797852986454, 'samples': 19824640, 'steps': 38719, 'loss/train': 1.4587024450302124}
-03/05/2022 10:58:42 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/05/2022 10:58:47 - INFO - codeparrot_training - Step 38720: {'lr': 0.00042782424850395894, 'samples': 19825152, 'steps': 38720, 'loss/train': 2.503936529159546}
-03/05/2022 10:58:50 - INFO - codeparrot_training - Step 38721: {'lr': 0.00042782051839792857, 'samples': 19825664, 'steps': 38721, 'loss/train': 2.0494422912597656}
-03/05/2022 10:58:50 - INFO - codeparrot_training - Skipping example with length 832 (seq_length=1024)
-03/05/2022 10:58:55 - INFO - codeparrot_training - Step 38722: {'lr': 0.000427816788211775, 'samples': 19826176, 'steps': 38722, 'loss/train': 2.220364570617676}
-03/05/2022 10:58:58 - INFO - codeparrot_training - Step 38723: {'lr': 0.00042781305794549994, 'samples': 19826688, 'steps': 38723, 'loss/train': 1.3216047286987305}
-03/05/2022 10:58:59 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/05/2022 10:59:04 - INFO - codeparrot_training - Step 38724: {'lr': 0.00042780932759910504, 'samples': 19827200, 'steps': 38724, 'loss/train': 1.5483509302139282}
-03/05/2022 10:59:07 - INFO - codeparrot_training - Step 38725: {'lr': 0.00042780559717259194, 'samples': 19827712, 'steps': 38725, 'loss/train': 2.1423680782318115}
-03/05/2022 10:59:07 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/05/2022 10:59:12 - INFO - codeparrot_training - Step 38726: {'lr': 0.0004278018666659624, 'samples': 19828224, 'steps': 38726, 'loss/train': 1.7244632244110107}
-03/05/2022 10:59:15 - INFO - codeparrot_training - Step 38727: {'lr': 0.0004277981360792182, 'samples': 19828736, 'steps': 38727, 'loss/train': 1.848299503326416}
-03/05/2022 10:59:15 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/05/2022 10:59:21 - INFO - codeparrot_training - Step 38728: {'lr': 0.0004277944054123608, 'samples': 19829248, 'steps': 38728, 'loss/train': 1.1198168992996216}
-03/05/2022 10:59:24 - INFO - codeparrot_training - Step 38729: {'lr': 0.000427790674665392, 'samples': 19829760, 'steps': 38729, 'loss/train': 0.4736887514591217}
-03/05/2022 10:59:24 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/05/2022 10:59:29 - INFO - codeparrot_training - Step 38730: {'lr': 0.00042778694383831354, 'samples': 19830272, 'steps': 38730, 'loss/train': 1.9365711212158203}
-03/05/2022 10:59:32 - INFO - codeparrot_training - Step 38731: {'lr': 0.0004277832129311269, 'samples': 19830784, 'steps': 38731, 'loss/train': 1.593790054321289}
-03/05/2022 10:59:33 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 10:59:38 - INFO - codeparrot_training - Step 38732: {'lr': 0.000427779481943834, 'samples': 19831296, 'steps': 38732, 'loss/train': 1.5448980331420898}
-03/05/2022 10:59:41 - INFO - codeparrot_training - Step 38733: {'lr': 0.0004277757508764363, 'samples': 19831808, 'steps': 38733, 'loss/train': 1.2443255186080933}
-03/05/2022 10:59:42 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/05/2022 10:59:46 - INFO - codeparrot_training - Step 38734: {'lr': 0.00042777201972893564, 'samples': 19832320, 'steps': 38734, 'loss/train': 2.218656063079834}
-03/05/2022 10:59:49 - INFO - codeparrot_training - Step 38735: {'lr': 0.00042776828850133364, 'samples': 19832832, 'steps': 38735, 'loss/train': 1.4080146551132202}
-03/05/2022 10:59:51 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/05/2022 10:59:55 - INFO - codeparrot_training - Step 38736: {'lr': 0.0004277645571936321, 'samples': 19833344, 'steps': 38736, 'loss/train': 1.1761796474456787}
-03/05/2022 10:59:58 - INFO - codeparrot_training - Step 38737: {'lr': 0.0004277608258058324, 'samples': 19833856, 'steps': 38737, 'loss/train': 1.2972103357315063}
-03/05/2022 10:59:59 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 11:00:03 - INFO - codeparrot_training - Step 38738: {'lr': 0.00042775709433793657, 'samples': 19834368, 'steps': 38738, 'loss/train': 2.1323394775390625}
-03/05/2022 11:00:06 - INFO - codeparrot_training - Step 38739: {'lr': 0.0004277533627899461, 'samples': 19834880, 'steps': 38739, 'loss/train': 1.8756883144378662}
-03/05/2022 11:00:08 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 11:00:11 - INFO - codeparrot_training - Step 38740: {'lr': 0.00042774963116186274, 'samples': 19835392, 'steps': 38740, 'loss/train': 0.9966974258422852}
-03/05/2022 11:00:15 - INFO - codeparrot_training - Step 38741: {'lr': 0.000427745899453688, 'samples': 19835904, 'steps': 38741, 'loss/train': 1.609127163887024}
-03/05/2022 11:00:16 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/05/2022 11:00:20 - INFO - codeparrot_training - Step 38742: {'lr': 0.00042774216766542386, 'samples': 19836416, 'steps': 38742, 'loss/train': 1.3716981410980225}
-03/05/2022 11:00:23 - INFO - codeparrot_training - Step 38743: {'lr': 0.0004277384357970717, 'samples': 19836928, 'steps': 38743, 'loss/train': 1.5405213832855225}
-03/05/2022 11:00:24 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/05/2022 11:00:28 - INFO - codeparrot_training - Step 38744: {'lr': 0.00042773470384863344, 'samples': 19837440, 'steps': 38744, 'loss/train': 1.5490622520446777}
-03/05/2022 11:00:32 - INFO - codeparrot_training - Step 38745: {'lr': 0.0004277309718201107, 'samples': 19837952, 'steps': 38745, 'loss/train': 1.298251986503601}
-03/05/2022 11:00:33 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/05/2022 11:00:37 - INFO - codeparrot_training - Step 38746: {'lr': 0.000427727239711505, 'samples': 19838464, 'steps': 38746, 'loss/train': 0.7143335938453674}
-03/05/2022 11:00:40 - INFO - codeparrot_training - Step 38747: {'lr': 0.00042772350752281823, 'samples': 19838976, 'steps': 38747, 'loss/train': 1.5477380752563477}
-03/05/2022 11:00:41 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/05/2022 11:00:45 - INFO - codeparrot_training - Step 38748: {'lr': 0.000427719775254052, 'samples': 19839488, 'steps': 38748, 'loss/train': 0.8484777808189392}
-03/05/2022 11:00:48 - INFO - codeparrot_training - Step 38749: {'lr': 0.00042771604290520795, 'samples': 19840000, 'steps': 38749, 'loss/train': 2.1488730907440186}
-03/05/2022 11:00:50 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/05/2022 11:00:54 - INFO - codeparrot_training - Step 38750: {'lr': 0.00042771231047628776, 'samples': 19840512, 'steps': 38750, 'loss/train': 1.8218976259231567}
-03/05/2022 11:00:57 - INFO - codeparrot_training - Step 38751: {'lr': 0.0004277085779672932, 'samples': 19841024, 'steps': 38751, 'loss/train': 1.9549795389175415}
-03/05/2022 11:00:58 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/05/2022 11:01:02 - INFO - codeparrot_training - Step 38752: {'lr': 0.0004277048453782259, 'samples': 19841536, 'steps': 38752, 'loss/train': 1.8467975854873657}
-03/05/2022 11:01:05 - INFO - codeparrot_training - Step 38753: {'lr': 0.0004277011127090875, 'samples': 19842048, 'steps': 38753, 'loss/train': 0.9890680909156799}
-03/05/2022 11:01:06 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/05/2022 11:01:11 - INFO - codeparrot_training - Step 38754: {'lr': 0.0004276973799598798, 'samples': 19842560, 'steps': 38754, 'loss/train': 1.738882303237915}
-03/05/2022 11:01:14 - INFO - codeparrot_training - Step 38755: {'lr': 0.0004276936471306043, 'samples': 19843072, 'steps': 38755, 'loss/train': 2.3517298698425293}
-03/05/2022 11:01:14 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 11:01:19 - INFO - codeparrot_training - Step 38756: {'lr': 0.00042768991422126285, 'samples': 19843584, 'steps': 38756, 'loss/train': 1.0692189931869507}
-03/05/2022 11:01:22 - INFO - codeparrot_training - Step 38757: {'lr': 0.00042768618123185703, 'samples': 19844096, 'steps': 38757, 'loss/train': 1.149498701095581}
-03/05/2022 11:01:23 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 11:01:27 - INFO - codeparrot_training - Step 38758: {'lr': 0.00042768244816238863, 'samples': 19844608, 'steps': 38758, 'loss/train': 1.8293123245239258}
-03/05/2022 11:01:31 - INFO - codeparrot_training - Step 38759: {'lr': 0.00042767871501285916, 'samples': 19845120, 'steps': 38759, 'loss/train': 1.8742057085037231}
-03/05/2022 11:01:31 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 11:01:36 - INFO - codeparrot_training - Step 38760: {'lr': 0.00042767498178327047, 'samples': 19845632, 'steps': 38760, 'loss/train': 0.9085041284561157}
-03/05/2022 11:01:39 - INFO - codeparrot_training - Step 38761: {'lr': 0.00042767124847362413, 'samples': 19846144, 'steps': 38761, 'loss/train': 0.607943594455719}
-03/05/2022 11:01:39 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/05/2022 11:01:44 - INFO - codeparrot_training - Step 38762: {'lr': 0.00042766751508392187, 'samples': 19846656, 'steps': 38762, 'loss/train': 1.7551029920578003}
-03/05/2022 11:01:47 - INFO - codeparrot_training - Step 38763: {'lr': 0.00042766378161416543, 'samples': 19847168, 'steps': 38763, 'loss/train': 2.536116123199463}
-03/05/2022 11:01:48 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/05/2022 11:01:53 - INFO - codeparrot_training - Step 38764: {'lr': 0.00042766004806435643, 'samples': 19847680, 'steps': 38764, 'loss/train': 1.4861551523208618}
-03/05/2022 11:01:56 - INFO - codeparrot_training - Step 38765: {'lr': 0.0004276563144344965, 'samples': 19848192, 'steps': 38765, 'loss/train': 1.4665184020996094}
-03/05/2022 11:01:56 - INFO - codeparrot_training - Skipping example with length 972 (seq_length=1024)
-03/05/2022 11:02:01 - INFO - codeparrot_training - Step 38766: {'lr': 0.00042765258072458733, 'samples': 19848704, 'steps': 38766, 'loss/train': 1.761582374572754}
-03/05/2022 11:02:04 - INFO - codeparrot_training - Step 38767: {'lr': 0.00042764884693463075, 'samples': 19849216, 'steps': 38767, 'loss/train': 1.673612117767334}
-03/05/2022 11:02:04 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/05/2022 11:02:09 - INFO - codeparrot_training - Step 38768: {'lr': 0.0004276451130646283, 'samples': 19849728, 'steps': 38768, 'loss/train': 2.0063512325286865}
-03/05/2022 11:02:13 - INFO - codeparrot_training - Step 38769: {'lr': 0.0004276413791145817, 'samples': 19850240, 'steps': 38769, 'loss/train': 1.526882290840149}
-03/05/2022 11:02:13 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 11:02:18 - INFO - codeparrot_training - Step 38770: {'lr': 0.00042763764508449263, 'samples': 19850752, 'steps': 38770, 'loss/train': 1.1674095392227173}
-03/05/2022 11:02:21 - INFO - codeparrot_training - Step 38771: {'lr': 0.0004276339109743628, 'samples': 19851264, 'steps': 38771, 'loss/train': 2.281853437423706}
-03/05/2022 11:02:21 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/05/2022 11:02:26 - INFO - codeparrot_training - Step 38772: {'lr': 0.0004276301767841939, 'samples': 19851776, 'steps': 38772, 'loss/train': 1.3355110883712769}
-03/05/2022 11:02:30 - INFO - codeparrot_training - Step 38773: {'lr': 0.00042762644251398755, 'samples': 19852288, 'steps': 38773, 'loss/train': 1.3679935932159424}
-03/05/2022 11:02:30 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 11:02:35 - INFO - codeparrot_training - Step 38774: {'lr': 0.0004276227081637454, 'samples': 19852800, 'steps': 38774, 'loss/train': 2.0201175212860107}
-03/05/2022 11:02:38 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/05/2022 11:02:40 - INFO - codeparrot_training - Step 38775: {'lr': 0.00042761897373346923, 'samples': 19853312, 'steps': 38775, 'loss/train': 1.4436979293823242}
-03/05/2022 11:02:43 - INFO - codeparrot_training - Step 38776: {'lr': 0.0004276152392231608, 'samples': 19853824, 'steps': 38776, 'loss/train': 1.448146104812622}
-03/05/2022 11:02:46 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/05/2022 11:02:49 - INFO - codeparrot_training - Step 38777: {'lr': 0.00042761150463282164, 'samples': 19854336, 'steps': 38777, 'loss/train': 0.18870750069618225}
-03/05/2022 11:02:52 - INFO - codeparrot_training - Step 38778: {'lr': 0.0004276077699624534, 'samples': 19854848, 'steps': 38778, 'loss/train': 1.9507322311401367}
-03/05/2022 11:02:55 - INFO - codeparrot_training - Step 38779: {'lr': 0.0004276040352120578, 'samples': 19855360, 'steps': 38779, 'loss/train': 1.7470334768295288}
-03/05/2022 11:02:55 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/05/2022 11:03:00 - INFO - codeparrot_training - Step 38780: {'lr': 0.0004276003003816367, 'samples': 19855872, 'steps': 38780, 'loss/train': 1.4377894401550293}
-03/05/2022 11:03:04 - INFO - codeparrot_training - Step 38781: {'lr': 0.0004275965654711916, 'samples': 19856384, 'steps': 38781, 'loss/train': 1.9451509714126587}
-03/05/2022 11:03:04 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/05/2022 11:03:09 - INFO - codeparrot_training - Step 38782: {'lr': 0.0004275928304807242, 'samples': 19856896, 'steps': 38782, 'loss/train': 2.2601380348205566}
-03/05/2022 11:03:12 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/05/2022 11:03:14 - INFO - codeparrot_training - Step 38783: {'lr': 0.0004275890954102362, 'samples': 19857408, 'steps': 38783, 'loss/train': 1.978162169456482}
-03/05/2022 11:03:17 - INFO - codeparrot_training - Step 38784: {'lr': 0.0004275853602597294, 'samples': 19857920, 'steps': 38784, 'loss/train': 1.5639010667800903}
-03/05/2022 11:03:20 - INFO - codeparrot_training - Step 38785: {'lr': 0.00042758162502920527, 'samples': 19858432, 'steps': 38785, 'loss/train': 4.148996353149414}
-03/05/2022 11:03:20 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 11:03:26 - INFO - codeparrot_training - Step 38786: {'lr': 0.0004275778897186656, 'samples': 19858944, 'steps': 38786, 'loss/train': 1.1092439889907837}
-03/05/2022 11:03:29 - INFO - codeparrot_training - Step 38787: {'lr': 0.0004275741543281121, 'samples': 19859456, 'steps': 38787, 'loss/train': 1.6421773433685303}
-03/05/2022 11:03:29 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/05/2022 11:03:34 - INFO - codeparrot_training - Step 38788: {'lr': 0.0004275704188575464, 'samples': 19859968, 'steps': 38788, 'loss/train': 1.2379320859909058}
-03/05/2022 11:03:38 - INFO - codeparrot_training - Step 38789: {'lr': 0.00042756668330697024, 'samples': 19860480, 'steps': 38789, 'loss/train': 1.6653393507003784}
-03/05/2022 11:03:38 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 11:03:43 - INFO - codeparrot_training - Step 38790: {'lr': 0.00042756294767638527, 'samples': 19860992, 'steps': 38790, 'loss/train': 1.7198596000671387}
-03/05/2022 11:03:46 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/05/2022 11:03:48 - INFO - codeparrot_training - Step 38791: {'lr': 0.00042755921196579316, 'samples': 19861504, 'steps': 38791, 'loss/train': 1.2671146392822266}
-03/05/2022 11:03:51 - INFO - codeparrot_training - Step 38792: {'lr': 0.0004275554761751956, 'samples': 19862016, 'steps': 38792, 'loss/train': 2.116487979888916}
-03/05/2022 11:03:54 - INFO - codeparrot_training - Skipping example with length 610 (seq_length=1024)
-03/05/2022 11:03:57 - INFO - codeparrot_training - Step 38793: {'lr': 0.0004275517403045943, 'samples': 19862528, 'steps': 38793, 'loss/train': 2.010054588317871}
-03/05/2022 11:04:00 - INFO - codeparrot_training - Step 38794: {'lr': 0.000427548004353991, 'samples': 19863040, 'steps': 38794, 'loss/train': 1.5263394117355347}
-03/05/2022 11:04:03 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/05/2022 11:04:05 - INFO - codeparrot_training - Step 38795: {'lr': 0.00042754426832338724, 'samples': 19863552, 'steps': 38795, 'loss/train': 3.899728298187256}
-03/05/2022 11:04:08 - INFO - codeparrot_training - Step 38796: {'lr': 0.00042754053221278476, 'samples': 19864064, 'steps': 38796, 'loss/train': 2.0442090034484863}
-03/05/2022 11:04:11 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/05/2022 11:04:13 - INFO - codeparrot_training - Step 38797: {'lr': 0.0004275367960221853, 'samples': 19864576, 'steps': 38797, 'loss/train': 1.4188014268875122}
-03/05/2022 11:04:17 - INFO - codeparrot_training - Step 38798: {'lr': 0.0004275330597515904, 'samples': 19865088, 'steps': 38798, 'loss/train': 1.745062232017517}
-03/05/2022 11:04:19 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 11:04:22 - INFO - codeparrot_training - Step 38799: {'lr': 0.00042752932340100195, 'samples': 19865600, 'steps': 38799, 'loss/train': 1.4455066919326782}
-03/05/2022 11:04:25 - INFO - codeparrot_training - Step 38800: {'lr': 0.00042752558697042143, 'samples': 19866112, 'steps': 38800, 'loss/train': 1.895833134651184}
-03/05/2022 11:04:27 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/05/2022 11:04:30 - INFO - codeparrot_training - Step 38801: {'lr': 0.0004275218504598507, 'samples': 19866624, 'steps': 38801, 'loss/train': 1.1686111688613892}
-03/05/2022 11:04:33 - INFO - codeparrot_training - Step 38802: {'lr': 0.0004275181138692914, 'samples': 19867136, 'steps': 38802, 'loss/train': 1.7747619152069092}
-03/05/2022 11:04:36 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/05/2022 11:04:39 - INFO - codeparrot_training - Step 38803: {'lr': 0.0004275143771987451, 'samples': 19867648, 'steps': 38803, 'loss/train': 1.614460825920105}
-03/05/2022 11:04:42 - INFO - codeparrot_training - Step 38804: {'lr': 0.00042751064044821354, 'samples': 19868160, 'steps': 38804, 'loss/train': 1.4653425216674805}
-03/05/2022 11:04:45 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/05/2022 11:04:47 - INFO - codeparrot_training - Step 38805: {'lr': 0.0004275069036176985, 'samples': 19868672, 'steps': 38805, 'loss/train': 1.609207034111023}
-03/05/2022 11:04:50 - INFO - codeparrot_training - Step 38806: {'lr': 0.0004275031667072015, 'samples': 19869184, 'steps': 38806, 'loss/train': 0.9228640794754028}
-03/05/2022 11:04:53 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/05/2022 11:04:56 - INFO - codeparrot_training - Step 38807: {'lr': 0.0004274994297167244, 'samples': 19869696, 'steps': 38807, 'loss/train': 1.5836750268936157}
-03/05/2022 11:04:59 - INFO - codeparrot_training - Step 38808: {'lr': 0.00042749569264626875, 'samples': 19870208, 'steps': 38808, 'loss/train': 1.6864134073257446}
-03/05/2022 11:05:01 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/05/2022 11:05:04 - INFO - codeparrot_training - Step 38809: {'lr': 0.0004274919554958363, 'samples': 19870720, 'steps': 38809, 'loss/train': 2.057582139968872}
-03/05/2022 11:05:07 - INFO - codeparrot_training - Step 38810: {'lr': 0.00042748821826542875, 'samples': 19871232, 'steps': 38810, 'loss/train': 1.1315243244171143}
-03/05/2022 11:05:10 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/05/2022 11:05:13 - INFO - codeparrot_training - Step 38811: {'lr': 0.00042748448095504765, 'samples': 19871744, 'steps': 38811, 'loss/train': 1.936607003211975}
-03/05/2022 11:05:16 - INFO - codeparrot_training - Step 38812: {'lr': 0.0004274807435646948, 'samples': 19872256, 'steps': 38812, 'loss/train': 1.7052066326141357}
-03/05/2022 11:05:18 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 11:05:21 - INFO - codeparrot_training - Step 38813: {'lr': 0.0004274770060943719, 'samples': 19872768, 'steps': 38813, 'loss/train': 1.3649488687515259}
-03/05/2022 11:05:24 - INFO - codeparrot_training - Step 38814: {'lr': 0.00042747326854408063, 'samples': 19873280, 'steps': 38814, 'loss/train': 1.6063501834869385}
-03/05/2022 11:05:27 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/05/2022 11:05:29 - INFO - codeparrot_training - Step 38815: {'lr': 0.00042746953091382254, 'samples': 19873792, 'steps': 38815, 'loss/train': 2.1427087783813477}
-03/05/2022 11:05:33 - INFO - codeparrot_training - Step 38816: {'lr': 0.00042746579320359956, 'samples': 19874304, 'steps': 38816, 'loss/train': 2.024057388305664}
-03/05/2022 11:05:36 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/05/2022 11:05:38 - INFO - codeparrot_training - Step 38817: {'lr': 0.00042746205541341315, 'samples': 19874816, 'steps': 38817, 'loss/train': 0.9468193054199219}
-03/05/2022 11:05:41 - INFO - codeparrot_training - Step 38818: {'lr': 0.0004274583175432651, 'samples': 19875328, 'steps': 38818, 'loss/train': 1.0230181217193604}
-03/05/2022 11:05:44 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/05/2022 11:05:46 - INFO - codeparrot_training - Step 38819: {'lr': 0.000427454579593157, 'samples': 19875840, 'steps': 38819, 'loss/train': 1.914709210395813}
-03/05/2022 11:05:50 - INFO - codeparrot_training - Step 38820: {'lr': 0.00042745084156309065, 'samples': 19876352, 'steps': 38820, 'loss/train': 1.675291895866394}
-03/05/2022 11:05:52 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/05/2022 11:05:55 - INFO - codeparrot_training - Step 38821: {'lr': 0.00042744710345306774, 'samples': 19876864, 'steps': 38821, 'loss/train': 2.1141064167022705}
-03/05/2022 11:05:58 - INFO - codeparrot_training - Step 38822: {'lr': 0.00042744336526308986, 'samples': 19877376, 'steps': 38822, 'loss/train': 1.5119497776031494}
-03/05/2022 11:06:01 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/05/2022 11:06:03 - INFO - codeparrot_training - Step 38823: {'lr': 0.0004274396269931587, 'samples': 19877888, 'steps': 38823, 'loss/train': 2.0717127323150635}
-03/05/2022 11:06:07 - INFO - codeparrot_training - Step 38824: {'lr': 0.0004274358886432761, 'samples': 19878400, 'steps': 38824, 'loss/train': 1.378435730934143}
-03/05/2022 11:06:09 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 11:06:12 - INFO - codeparrot_training - Step 38825: {'lr': 0.0004274321502134435, 'samples': 19878912, 'steps': 38825, 'loss/train': 1.9915697574615479}
-03/05/2022 11:06:15 - INFO - codeparrot_training - Step 38826: {'lr': 0.00042742841170366274, 'samples': 19879424, 'steps': 38826, 'loss/train': 1.9072010517120361}
-03/05/2022 11:06:18 - INFO - codeparrot_training - Step 38827: {'lr': 0.0004274246731139355, 'samples': 19879936, 'steps': 38827, 'loss/train': 0.8838217854499817}
-03/05/2022 11:06:18 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/05/2022 11:06:24 - INFO - codeparrot_training - Step 38828: {'lr': 0.0004274209344442634, 'samples': 19880448, 'steps': 38828, 'loss/train': 1.9953337907791138}
-03/05/2022 11:06:27 - INFO - codeparrot_training - Step 38829: {'lr': 0.00042741719569464834, 'samples': 19880960, 'steps': 38829, 'loss/train': 1.7629108428955078}
-03/05/2022 11:06:27 - INFO - codeparrot_training - Skipping example with length 409 (seq_length=1024)
-03/05/2022 11:06:32 - INFO - codeparrot_training - Step 38830: {'lr': 0.0004274134568650916, 'samples': 19881472, 'steps': 38830, 'loss/train': 2.0384504795074463}
-03/05/2022 11:06:35 - INFO - codeparrot_training - Step 38831: {'lr': 0.00042740971795559527, 'samples': 19881984, 'steps': 38831, 'loss/train': 1.5537960529327393}
-03/05/2022 11:06:35 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/05/2022 11:06:41 - INFO - codeparrot_training - Step 38832: {'lr': 0.00042740597896616075, 'samples': 19882496, 'steps': 38832, 'loss/train': 0.09074151515960693}
-03/05/2022 11:06:44 - INFO - codeparrot_training - Step 38833: {'lr': 0.00042740223989678984, 'samples': 19883008, 'steps': 38833, 'loss/train': 1.9083868265151978}
-03/05/2022 11:06:44 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/05/2022 11:06:49 - INFO - codeparrot_training - Step 38834: {'lr': 0.0004273985007474842, 'samples': 19883520, 'steps': 38834, 'loss/train': 2.390120029449463}
-03/05/2022 11:06:52 - INFO - codeparrot_training - Step 38835: {'lr': 0.00042739476151824565, 'samples': 19884032, 'steps': 38835, 'loss/train': 1.0216453075408936}
-03/05/2022 11:06:52 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/05/2022 11:06:58 - INFO - codeparrot_training - Step 38836: {'lr': 0.00042739102220907567, 'samples': 19884544, 'steps': 38836, 'loss/train': 1.9429576396942139}
-03/05/2022 11:07:00 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 11:07:04 - INFO - codeparrot_training - Step 38837: {'lr': 0.000427387282819976, 'samples': 19885056, 'steps': 38837, 'loss/train': 1.8225210905075073}
-03/05/2022 11:07:07 - INFO - codeparrot_training - Step 38838: {'lr': 0.0004273835433509484, 'samples': 19885568, 'steps': 38838, 'loss/train': 2.1098668575286865}
-03/05/2022 11:07:10 - INFO - codeparrot_training - Step 38839: {'lr': 0.0004273798038019945, 'samples': 19886080, 'steps': 38839, 'loss/train': 2.106077194213867}
-03/05/2022 11:07:13 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/05/2022 11:07:15 - INFO - codeparrot_training - Step 38840: {'lr': 0.000427376064173116, 'samples': 19886592, 'steps': 38840, 'loss/train': 1.0053428411483765}
-03/05/2022 11:07:18 - INFO - codeparrot_training - Step 38841: {'lr': 0.0004273723244643146, 'samples': 19887104, 'steps': 38841, 'loss/train': 1.7379900217056274}
-03/05/2022 11:07:21 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/05/2022 11:07:24 - INFO - codeparrot_training - Step 38842: {'lr': 0.000427368584675592, 'samples': 19887616, 'steps': 38842, 'loss/train': 0.8685247302055359}
-03/05/2022 11:07:27 - INFO - codeparrot_training - Step 38843: {'lr': 0.0004273648448069498, 'samples': 19888128, 'steps': 38843, 'loss/train': 1.1872957944869995}
-03/05/2022 11:07:30 - INFO - codeparrot_training - Skipping example with length 43 (seq_length=1024)
-03/05/2022 11:07:32 - INFO - codeparrot_training - Step 38844: {'lr': 0.00042736110485838973, 'samples': 19888640, 'steps': 38844, 'loss/train': 0.15888711810112}
-03/05/2022 11:07:36 - INFO - codeparrot_training - Step 38845: {'lr': 0.0004273573648299135, 'samples': 19889152, 'steps': 38845, 'loss/train': 0.06848172843456268}
-03/05/2022 11:07:38 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/05/2022 11:07:41 - INFO - codeparrot_training - Step 38846: {'lr': 0.0004273536247215227, 'samples': 19889664, 'steps': 38846, 'loss/train': 1.6705498695373535}
-03/05/2022 11:07:44 - INFO - codeparrot_training - Step 38847: {'lr': 0.00042734988453321923, 'samples': 19890176, 'steps': 38847, 'loss/train': 2.401719808578491}
-03/05/2022 11:07:47 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/05/2022 11:07:49 - INFO - codeparrot_training - Step 38848: {'lr': 0.0004273461442650046, 'samples': 19890688, 'steps': 38848, 'loss/train': 2.2269763946533203}
-03/05/2022 11:07:53 - INFO - codeparrot_training - Step 38849: {'lr': 0.0004273424039168805, 'samples': 19891200, 'steps': 38849, 'loss/train': 1.3912190198898315}
-03/05/2022 11:07:55 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 11:07:58 - INFO - codeparrot_training - Step 38850: {'lr': 0.00042733866348884864, 'samples': 19891712, 'steps': 38850, 'loss/train': 1.7977155447006226}
-03/05/2022 11:08:01 - INFO - codeparrot_training - Step 38851: {'lr': 0.0004273349229809108, 'samples': 19892224, 'steps': 38851, 'loss/train': 1.1809056997299194}
-03/05/2022 11:08:03 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/05/2022 11:08:06 - INFO - codeparrot_training - Step 38852: {'lr': 0.00042733118239306845, 'samples': 19892736, 'steps': 38852, 'loss/train': 1.5782252550125122}
-03/05/2022 11:08:09 - INFO - codeparrot_training - Step 38853: {'lr': 0.0004273274417253235, 'samples': 19893248, 'steps': 38853, 'loss/train': 1.4937671422958374}
-03/05/2022 11:08:12 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/05/2022 11:08:15 - INFO - codeparrot_training - Step 38854: {'lr': 0.00042732370097767756, 'samples': 19893760, 'steps': 38854, 'loss/train': 1.1941438913345337}
-03/05/2022 11:08:18 - INFO - codeparrot_training - Step 38855: {'lr': 0.0004273199601501322, 'samples': 19894272, 'steps': 38855, 'loss/train': 1.5130765438079834}
-03/05/2022 11:08:20 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 11:08:23 - INFO - codeparrot_training - Step 38856: {'lr': 0.0004273162192426893, 'samples': 19894784, 'steps': 38856, 'loss/train': 1.9100626707077026}
-03/05/2022 11:08:26 - INFO - codeparrot_training - Step 38857: {'lr': 0.00042731247825535037, 'samples': 19895296, 'steps': 38857, 'loss/train': 0.5294350385665894}
-03/05/2022 11:08:28 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/05/2022 11:08:32 - INFO - codeparrot_training - Step 38858: {'lr': 0.00042730873718811724, 'samples': 19895808, 'steps': 38858, 'loss/train': 1.096190333366394}
-03/05/2022 11:08:35 - INFO - codeparrot_training - Step 38859: {'lr': 0.0004273049960409915, 'samples': 19896320, 'steps': 38859, 'loss/train': 2.002255916595459}
-03/05/2022 11:08:37 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/05/2022 11:08:40 - INFO - codeparrot_training - Step 38860: {'lr': 0.00042730125481397487, 'samples': 19896832, 'steps': 38860, 'loss/train': 2.0559184551239014}
-03/05/2022 11:08:43 - INFO - codeparrot_training - Step 38861: {'lr': 0.00042729751350706905, 'samples': 19897344, 'steps': 38861, 'loss/train': 1.495954155921936}
-03/05/2022 11:08:45 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/05/2022 11:08:48 - INFO - codeparrot_training - Step 38862: {'lr': 0.00042729377212027557, 'samples': 19897856, 'steps': 38862, 'loss/train': 2.0471136569976807}
-03/05/2022 11:08:52 - INFO - codeparrot_training - Step 38863: {'lr': 0.0004272900306535964, 'samples': 19898368, 'steps': 38863, 'loss/train': 0.8550220727920532}
-03/05/2022 11:08:54 - INFO - codeparrot_training - Skipping example with length 198 (seq_length=1024)
-03/05/2022 11:08:57 - INFO - codeparrot_training - Step 38864: {'lr': 0.00042728628910703305, 'samples': 19898880, 'steps': 38864, 'loss/train': 2.3690879344940186}
-03/05/2022 11:09:00 - INFO - codeparrot_training - Step 38865: {'lr': 0.0004272825474805872, 'samples': 19899392, 'steps': 38865, 'loss/train': 1.5645257234573364}
-03/05/2022 11:09:03 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/05/2022 11:09:05 - INFO - codeparrot_training - Step 38866: {'lr': 0.0004272788057742606, 'samples': 19899904, 'steps': 38866, 'loss/train': 1.7530213594436646}
-03/05/2022 11:09:08 - INFO - codeparrot_training - Step 38867: {'lr': 0.0004272750639880549, 'samples': 19900416, 'steps': 38867, 'loss/train': 1.3539156913757324}
-03/05/2022 11:09:11 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/05/2022 11:09:14 - INFO - codeparrot_training - Step 38868: {'lr': 0.0004272713221219718, 'samples': 19900928, 'steps': 38868, 'loss/train': 2.2932496070861816}
-03/05/2022 11:09:17 - INFO - codeparrot_training - Step 38869: {'lr': 0.00042726758017601297, 'samples': 19901440, 'steps': 38869, 'loss/train': 2.219136953353882}
-03/05/2022 11:09:19 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/05/2022 11:09:22 - INFO - codeparrot_training - Step 38870: {'lr': 0.00042726383815018006, 'samples': 19901952, 'steps': 38870, 'loss/train': 1.5567244291305542}
-03/05/2022 11:09:25 - INFO - codeparrot_training - Step 38871: {'lr': 0.00042726009604447484, 'samples': 19902464, 'steps': 38871, 'loss/train': 2.2527847290039062}
-03/05/2022 11:09:28 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/05/2022 11:09:31 - INFO - codeparrot_training - Step 38872: {'lr': 0.00042725635385889893, 'samples': 19902976, 'steps': 38872, 'loss/train': 1.7845951318740845}
-03/05/2022 11:09:34 - INFO - codeparrot_training - Step 38873: {'lr': 0.0004272526115934541, 'samples': 19903488, 'steps': 38873, 'loss/train': 1.5938351154327393}
-03/05/2022 11:09:36 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/05/2022 11:09:39 - INFO - codeparrot_training - Step 38874: {'lr': 0.0004272488692481419, 'samples': 19904000, 'steps': 38874, 'loss/train': 2.0254082679748535}
-03/05/2022 11:09:42 - INFO - codeparrot_training - Step 38875: {'lr': 0.00042724512682296416, 'samples': 19904512, 'steps': 38875, 'loss/train': 0.8528100252151489}
-03/05/2022 11:09:44 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/05/2022 11:09:47 - INFO - codeparrot_training - Step 38876: {'lr': 0.00042724138431792245, 'samples': 19905024, 'steps': 38876, 'loss/train': 1.939806580543518}
-03/05/2022 11:09:50 - INFO - codeparrot_training - Step 38877: {'lr': 0.0004272376417330186, 'samples': 19905536, 'steps': 38877, 'loss/train': 1.611383080482483}
-03/05/2022 11:09:52 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/05/2022 11:09:56 - INFO - codeparrot_training - Step 38878: {'lr': 0.00042723389906825415, 'samples': 19906048, 'steps': 38878, 'loss/train': 1.7664685249328613}
-03/05/2022 11:09:59 - INFO - codeparrot_training - Step 38879: {'lr': 0.0004272301563236308, 'samples': 19906560, 'steps': 38879, 'loss/train': 1.7835584878921509}
-03/05/2022 11:10:01 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 11:10:04 - INFO - codeparrot_training - Step 38880: {'lr': 0.0004272264134991503, 'samples': 19907072, 'steps': 38880, 'loss/train': 2.6062960624694824}
-03/05/2022 11:10:07 - INFO - codeparrot_training - Step 38881: {'lr': 0.0004272226705948143, 'samples': 19907584, 'steps': 38881, 'loss/train': 1.4331471920013428}
-03/05/2022 11:10:09 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/05/2022 11:10:13 - INFO - codeparrot_training - Step 38882: {'lr': 0.00042721892761062453, 'samples': 19908096, 'steps': 38882, 'loss/train': 1.6260648965835571}
-03/05/2022 11:10:16 - INFO - codeparrot_training - Step 38883: {'lr': 0.00042721518454658265, 'samples': 19908608, 'steps': 38883, 'loss/train': 2.2704081535339355}
-03/05/2022 11:10:18 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/05/2022 11:10:21 - INFO - codeparrot_training - Step 38884: {'lr': 0.0004272114414026903, 'samples': 19909120, 'steps': 38884, 'loss/train': 0.8609506487846375}
-03/05/2022 11:10:24 - INFO - codeparrot_training - Step 38885: {'lr': 0.00042720769817894926, 'samples': 19909632, 'steps': 38885, 'loss/train': 1.3536765575408936}
-03/05/2022 11:10:26 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/05/2022 11:10:29 - INFO - codeparrot_training - Step 38886: {'lr': 0.00042720395487536115, 'samples': 19910144, 'steps': 38886, 'loss/train': 1.5734316110610962}
-03/05/2022 11:10:33 - INFO - codeparrot_training - Step 38887: {'lr': 0.0004272002114919277, 'samples': 19910656, 'steps': 38887, 'loss/train': 1.7789583206176758}
-03/05/2022 11:10:34 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/05/2022 11:10:38 - INFO - codeparrot_training - Step 38888: {'lr': 0.0004271964680286505, 'samples': 19911168, 'steps': 38888, 'loss/train': 1.5227296352386475}
-03/05/2022 11:10:41 - INFO - codeparrot_training - Step 38889: {'lr': 0.00042719272448553137, 'samples': 19911680, 'steps': 38889, 'loss/train': 2.528425931930542}
-03/05/2022 11:10:43 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/05/2022 11:10:47 - INFO - codeparrot_training - Step 38890: {'lr': 0.00042718898086257183, 'samples': 19912192, 'steps': 38890, 'loss/train': 1.3084510564804077}
-03/05/2022 11:10:50 - INFO - codeparrot_training - Step 38891: {'lr': 0.0004271852371597738, 'samples': 19912704, 'steps': 38891, 'loss/train': 2.1403250694274902}
-03/05/2022 11:10:53 - INFO - codeparrot_training - Step 38892: {'lr': 0.00042718149337713873, 'samples': 19913216, 'steps': 38892, 'loss/train': 6.25106143951416}
-03/05/2022 11:10:56 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/05/2022 11:10:59 - INFO - codeparrot_training - Step 38893: {'lr': 0.0004271777495146685, 'samples': 19913728, 'steps': 38893, 'loss/train': 2.2443454265594482}
-03/05/2022 11:11:02 - INFO - codeparrot_training - Step 38894: {'lr': 0.00042717400557236467, 'samples': 19914240, 'steps': 38894, 'loss/train': 1.8351449966430664}
-03/05/2022 11:11:05 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 11:11:07 - INFO - codeparrot_training - Step 38895: {'lr': 0.000427170261550229, 'samples': 19914752, 'steps': 38895, 'loss/train': 1.4891761541366577}
-03/05/2022 11:11:11 - INFO - codeparrot_training - Step 38896: {'lr': 0.0004271665174482631, 'samples': 19915264, 'steps': 38896, 'loss/train': 1.907853364944458}
-03/05/2022 11:11:13 - INFO - codeparrot_training - Skipping example with length 904 (seq_length=1024)
-03/05/2022 11:11:16 - INFO - codeparrot_training - Step 38897: {'lr': 0.0004271627732664687, 'samples': 19915776, 'steps': 38897, 'loss/train': 1.8562076091766357}
-03/05/2022 11:11:19 - INFO - codeparrot_training - Step 38898: {'lr': 0.0004271590290048475, 'samples': 19916288, 'steps': 38898, 'loss/train': 1.7378627061843872}
-03/05/2022 11:11:22 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/05/2022 11:11:24 - INFO - codeparrot_training - Step 38899: {'lr': 0.00042715528466340117, 'samples': 19916800, 'steps': 38899, 'loss/train': 1.1246466636657715}
-03/05/2022 11:11:28 - INFO - codeparrot_training - Step 38900: {'lr': 0.00042715154024213143, 'samples': 19917312, 'steps': 38900, 'loss/train': 1.6148508787155151}
-03/05/2022 11:11:31 - INFO - codeparrot_training - Step 38901: {'lr': 0.0004271477957410399, 'samples': 19917824, 'steps': 38901, 'loss/train': 1.4736651182174683}
-03/05/2022 11:11:31 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/05/2022 11:11:36 - INFO - codeparrot_training - Step 38902: {'lr': 0.00042714405116012834, 'samples': 19918336, 'steps': 38902, 'loss/train': 2.015329122543335}
-03/05/2022 11:11:39 - INFO - codeparrot_training - Step 38903: {'lr': 0.0004271403064993984, 'samples': 19918848, 'steps': 38903, 'loss/train': 2.12369704246521}
-03/05/2022 11:11:39 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/05/2022 11:11:45 - INFO - codeparrot_training - Step 38904: {'lr': 0.00042713656175885173, 'samples': 19919360, 'steps': 38904, 'loss/train': 1.616765022277832}
-03/05/2022 11:11:48 - INFO - codeparrot_training - Step 38905: {'lr': 0.00042713281693849015, 'samples': 19919872, 'steps': 38905, 'loss/train': 2.083192825317383}
-03/05/2022 11:11:48 - INFO - codeparrot_training - Skipping example with length 354 (seq_length=1024)
-03/05/2022 11:11:53 - INFO - codeparrot_training - Step 38906: {'lr': 0.0004271290720383152, 'samples': 19920384, 'steps': 38906, 'loss/train': 2.3888847827911377}
-03/05/2022 11:11:56 - INFO - codeparrot_training - Step 38907: {'lr': 0.00042712532705832865, 'samples': 19920896, 'steps': 38907, 'loss/train': 2.012119770050049}
-03/05/2022 11:11:56 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/05/2022 11:12:02 - INFO - codeparrot_training - Step 38908: {'lr': 0.0004271215819985321, 'samples': 19921408, 'steps': 38908, 'loss/train': 1.7760659456253052}
-03/05/2022 11:12:05 - INFO - codeparrot_training - Step 38909: {'lr': 0.0004271178368589273, 'samples': 19921920, 'steps': 38909, 'loss/train': 1.8998491764068604}
-03/05/2022 11:12:05 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/05/2022 11:12:10 - INFO - codeparrot_training - Step 38910: {'lr': 0.000427114091639516, 'samples': 19922432, 'steps': 38910, 'loss/train': 0.3795957565307617}
-03/05/2022 11:12:13 - INFO - codeparrot_training - Step 38911: {'lr': 0.0004271103463402998, 'samples': 19922944, 'steps': 38911, 'loss/train': 0.9166125059127808}
-03/05/2022 11:12:13 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/05/2022 11:12:18 - INFO - codeparrot_training - Step 38912: {'lr': 0.0004271066009612804, 'samples': 19923456, 'steps': 38912, 'loss/train': 2.433647871017456}
-03/05/2022 11:12:22 - INFO - codeparrot_training - Step 38913: {'lr': 0.0004271028555024594, 'samples': 19923968, 'steps': 38913, 'loss/train': 2.044684410095215}
-03/05/2022 11:12:22 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/05/2022 11:12:27 - INFO - codeparrot_training - Step 38914: {'lr': 0.0004270991099638387, 'samples': 19924480, 'steps': 38914, 'loss/train': 1.634007453918457}
-03/05/2022 11:12:30 - INFO - codeparrot_training - Step 38915: {'lr': 0.0004270953643454199, 'samples': 19924992, 'steps': 38915, 'loss/train': 1.565908432006836}
-03/05/2022 11:12:31 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/05/2022 11:12:36 - INFO - codeparrot_training - Step 38916: {'lr': 0.0004270916186472046, 'samples': 19925504, 'steps': 38916, 'loss/train': 2.8455967903137207}
-03/05/2022 11:12:39 - INFO - codeparrot_training - Step 38917: {'lr': 0.0004270878728691946, 'samples': 19926016, 'steps': 38917, 'loss/train': 1.6197147369384766}
-03/05/2022 11:12:44 - INFO - codeparrot_training - Step 38918: {'lr': 0.00042708412701139147, 'samples': 19926528, 'steps': 38918, 'loss/train': 2.579059362411499}
-03/05/2022 11:12:47 - INFO - codeparrot_training - Step 38919: {'lr': 0.000427080381073797, 'samples': 19927040, 'steps': 38919, 'loss/train': 1.97496497631073}
-03/05/2022 11:12:48 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/05/2022 11:12:52 - INFO - codeparrot_training - Step 38920: {'lr': 0.00042707663505641287, 'samples': 19927552, 'steps': 38920, 'loss/train': 2.032160997390747}
-03/05/2022 11:12:56 - INFO - codeparrot_training - Step 38921: {'lr': 0.00042707288895924066, 'samples': 19928064, 'steps': 38921, 'loss/train': 1.2271091938018799}
-03/05/2022 11:12:57 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/05/2022 11:13:01 - INFO - codeparrot_training - Step 38922: {'lr': 0.0004270691427822823, 'samples': 19928576, 'steps': 38922, 'loss/train': 2.431943655014038}
-03/05/2022 11:13:04 - INFO - codeparrot_training - Step 38923: {'lr': 0.0004270653965255391, 'samples': 19929088, 'steps': 38923, 'loss/train': 2.5251169204711914}
-03/05/2022 11:13:05 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/05/2022 11:13:10 - INFO - codeparrot_training - Step 38924: {'lr': 0.0004270616501890131, 'samples': 19929600, 'steps': 38924, 'loss/train': 1.6960768699645996}
-03/05/2022 11:13:13 - INFO - codeparrot_training - Step 38925: {'lr': 0.0004270579037727058, 'samples': 19930112, 'steps': 38925, 'loss/train': 2.3554043769836426}
-03/05/2022 11:13:14 - INFO - codeparrot_training - Skipping example with length 301 (seq_length=1024)
-03/05/2022 11:13:18 - INFO - codeparrot_training - Step 38926: {'lr': 0.000427054157276619, 'samples': 19930624, 'steps': 38926, 'loss/train': 2.3110921382904053}
-03/05/2022 11:13:21 - INFO - codeparrot_training - Step 38927: {'lr': 0.00042705041070075433, 'samples': 19931136, 'steps': 38927, 'loss/train': 0.9900491833686829}
-03/05/2022 11:13:22 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/05/2022 11:13:26 - INFO - codeparrot_training - Step 38928: {'lr': 0.00042704666404511343, 'samples': 19931648, 'steps': 38928, 'loss/train': 2.4232592582702637}
-03/05/2022 11:13:30 - INFO - codeparrot_training - Step 38929: {'lr': 0.000427042917309698, 'samples': 19932160, 'steps': 38929, 'loss/train': 2.4030957221984863}
-03/05/2022 11:13:30 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/05/2022 11:13:35 - INFO - codeparrot_training - Step 38930: {'lr': 0.00042703917049450983, 'samples': 19932672, 'steps': 38930, 'loss/train': 1.1503387689590454}
-03/05/2022 11:13:38 - INFO - codeparrot_training - Step 38931: {'lr': 0.0004270354235995505, 'samples': 19933184, 'steps': 38931, 'loss/train': 1.704493761062622}
-03/05/2022 11:13:39 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 11:13:43 - INFO - codeparrot_training - Step 38932: {'lr': 0.0004270316766248218, 'samples': 19933696, 'steps': 38932, 'loss/train': 2.5988523960113525}
-03/05/2022 11:13:46 - INFO - codeparrot_training - Step 38933: {'lr': 0.0004270279295703253, 'samples': 19934208, 'steps': 38933, 'loss/train': 1.9948276281356812}
-03/05/2022 11:13:47 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 11:13:52 - INFO - codeparrot_training - Step 38934: {'lr': 0.00042702418243606275, 'samples': 19934720, 'steps': 38934, 'loss/train': 1.9496855735778809}
-03/05/2022 11:13:55 - INFO - codeparrot_training - Step 38935: {'lr': 0.00042702043522203594, 'samples': 19935232, 'steps': 38935, 'loss/train': 1.516800045967102}
-03/05/2022 11:13:55 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/05/2022 11:14:00 - INFO - codeparrot_training - Step 38936: {'lr': 0.00042701668792824633, 'samples': 19935744, 'steps': 38936, 'loss/train': 2.778306007385254}
-03/05/2022 11:14:03 - INFO - codeparrot_training - Step 38937: {'lr': 0.00042701294055469576, 'samples': 19936256, 'steps': 38937, 'loss/train': 1.4200353622436523}
-03/05/2022 11:14:04 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 11:14:08 - INFO - codeparrot_training - Step 38938: {'lr': 0.0004270091931013859, 'samples': 19936768, 'steps': 38938, 'loss/train': 1.2574478387832642}
-03/05/2022 11:14:12 - INFO - codeparrot_training - Step 38939: {'lr': 0.00042700544556831846, 'samples': 19937280, 'steps': 38939, 'loss/train': 2.2507317066192627}
-03/05/2022 11:14:12 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/05/2022 11:14:17 - INFO - codeparrot_training - Step 38940: {'lr': 0.00042700169795549504, 'samples': 19937792, 'steps': 38940, 'loss/train': 1.9035097360610962}
-03/05/2022 11:14:20 - INFO - codeparrot_training - Step 38941: {'lr': 0.00042699795026291743, 'samples': 19938304, 'steps': 38941, 'loss/train': 1.7899919748306274}
-03/05/2022 11:14:20 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/05/2022 11:14:25 - INFO - codeparrot_training - Step 38942: {'lr': 0.0004269942024905872, 'samples': 19938816, 'steps': 38942, 'loss/train': 1.7130547761917114}
-03/05/2022 11:14:28 - INFO - codeparrot_training - Step 38943: {'lr': 0.00042699045463850623, 'samples': 19939328, 'steps': 38943, 'loss/train': 1.6139165163040161}
-03/05/2022 11:14:28 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/05/2022 11:14:34 - INFO - codeparrot_training - Step 38944: {'lr': 0.000426986706706676, 'samples': 19939840, 'steps': 38944, 'loss/train': 1.3511327505111694}
-03/05/2022 11:14:37 - INFO - codeparrot_training - Step 38945: {'lr': 0.00042698295869509836, 'samples': 19940352, 'steps': 38945, 'loss/train': 1.525887131690979}
-03/05/2022 11:14:37 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/05/2022 11:14:42 - INFO - codeparrot_training - Step 38946: {'lr': 0.0004269792106037749, 'samples': 19940864, 'steps': 38946, 'loss/train': 1.5700898170471191}
-03/05/2022 11:14:45 - INFO - codeparrot_training - Step 38947: {'lr': 0.0004269754624327073, 'samples': 19941376, 'steps': 38947, 'loss/train': 2.463099241256714}
-03/05/2022 11:14:45 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/05/2022 11:14:50 - INFO - codeparrot_training - Step 38948: {'lr': 0.0004269717141818973, 'samples': 19941888, 'steps': 38948, 'loss/train': 1.9206347465515137}
-03/05/2022 11:14:54 - INFO - codeparrot_training - Step 38949: {'lr': 0.0004269679658513466, 'samples': 19942400, 'steps': 38949, 'loss/train': 1.4782088994979858}
-03/05/2022 11:14:54 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/05/2022 11:14:59 - INFO - codeparrot_training - Step 38950: {'lr': 0.00042696421744105686, 'samples': 19942912, 'steps': 38950, 'loss/train': 1.3907102346420288}
-03/05/2022 11:15:02 - INFO - codeparrot_training - Step 38951: {'lr': 0.0004269604689510298, 'samples': 19943424, 'steps': 38951, 'loss/train': 1.508575439453125}
-03/05/2022 11:15:02 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/05/2022 11:15:08 - INFO - codeparrot_training - Step 38952: {'lr': 0.0004269567203812671, 'samples': 19943936, 'steps': 38952, 'loss/train': 2.0267443656921387}
-03/05/2022 11:15:10 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/05/2022 11:15:13 - INFO - codeparrot_training - Step 38953: {'lr': 0.00042695297173177033, 'samples': 19944448, 'steps': 38953, 'loss/train': 1.5165950059890747}
-03/05/2022 11:15:16 - INFO - codeparrot_training - Step 38954: {'lr': 0.0004269492230025413, 'samples': 19944960, 'steps': 38954, 'loss/train': 1.3401706218719482}
-03/05/2022 11:15:19 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 11:15:21 - INFO - codeparrot_training - Step 38955: {'lr': 0.0004269454741935818, 'samples': 19945472, 'steps': 38955, 'loss/train': 2.094369888305664}
-03/05/2022 11:15:24 - INFO - codeparrot_training - Step 38956: {'lr': 0.00042694172530489326, 'samples': 19945984, 'steps': 38956, 'loss/train': 0.9254721403121948}
-03/05/2022 11:15:27 - INFO - codeparrot_training - Skipping example with length 996 (seq_length=1024)
-03/05/2022 11:15:30 - INFO - codeparrot_training - Step 38957: {'lr': 0.00042693797633647755, 'samples': 19946496, 'steps': 38957, 'loss/train': 1.9181885719299316}
-03/05/2022 11:15:33 - INFO - codeparrot_training - Step 38958: {'lr': 0.00042693422728833644, 'samples': 19947008, 'steps': 38958, 'loss/train': 1.57408607006073}
-03/05/2022 11:15:35 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 11:15:38 - INFO - codeparrot_training - Step 38959: {'lr': 0.00042693047816047135, 'samples': 19947520, 'steps': 38959, 'loss/train': 1.039240837097168}
-03/05/2022 11:15:41 - INFO - codeparrot_training - Step 38960: {'lr': 0.0004269267289528842, 'samples': 19948032, 'steps': 38960, 'loss/train': 1.9586362838745117}
-03/05/2022 11:15:44 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/05/2022 11:15:47 - INFO - codeparrot_training - Step 38961: {'lr': 0.00042692297966557657, 'samples': 19948544, 'steps': 38961, 'loss/train': 1.9032374620437622}
-03/05/2022 11:15:50 - INFO - codeparrot_training - Step 38962: {'lr': 0.0004269192302985502, 'samples': 19949056, 'steps': 38962, 'loss/train': 1.4384634494781494}
-03/05/2022 11:15:52 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/05/2022 11:15:55 - INFO - codeparrot_training - Step 38963: {'lr': 0.00042691548085180666, 'samples': 19949568, 'steps': 38963, 'loss/train': 2.0511012077331543}
-03/05/2022 11:15:58 - INFO - codeparrot_training - Step 38964: {'lr': 0.00042691173132534775, 'samples': 19950080, 'steps': 38964, 'loss/train': 1.5592284202575684}
-03/05/2022 11:16:00 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/05/2022 11:16:03 - INFO - codeparrot_training - Step 38965: {'lr': 0.0004269079817191752, 'samples': 19950592, 'steps': 38965, 'loss/train': 1.1896001100540161}
-03/05/2022 11:16:07 - INFO - codeparrot_training - Step 38966: {'lr': 0.00042690423203329067, 'samples': 19951104, 'steps': 38966, 'loss/train': 1.00688898563385}
-03/05/2022 11:16:09 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/05/2022 11:16:12 - INFO - codeparrot_training - Step 38967: {'lr': 0.0004269004822676958, 'samples': 19951616, 'steps': 38967, 'loss/train': 1.901790738105774}
-03/05/2022 11:16:15 - INFO - codeparrot_training - Step 38968: {'lr': 0.0004268967324223922, 'samples': 19952128, 'steps': 38968, 'loss/train': 1.801607608795166}
-03/05/2022 11:16:17 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 11:16:20 - INFO - codeparrot_training - Step 38969: {'lr': 0.00042689298249738185, 'samples': 19952640, 'steps': 38969, 'loss/train': 2.147698163986206}
-03/05/2022 11:16:23 - INFO - codeparrot_training - Step 38970: {'lr': 0.00042688923249266614, 'samples': 19953152, 'steps': 38970, 'loss/train': 1.6063201427459717}
-03/05/2022 11:16:27 - INFO - codeparrot_training - Step 38971: {'lr': 0.00042688548240824687, 'samples': 19953664, 'steps': 38971, 'loss/train': 2.185361862182617}
-03/05/2022 11:16:27 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/05/2022 11:16:32 - INFO - codeparrot_training - Step 38972: {'lr': 0.00042688173224412573, 'samples': 19954176, 'steps': 38972, 'loss/train': 2.025792360305786}
-03/05/2022 11:16:35 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/05/2022 11:16:37 - INFO - codeparrot_training - Step 38973: {'lr': 0.00042687798200030446, 'samples': 19954688, 'steps': 38973, 'loss/train': 1.676720142364502}
-03/05/2022 11:16:40 - INFO - codeparrot_training - Step 38974: {'lr': 0.00042687423167678463, 'samples': 19955200, 'steps': 38974, 'loss/train': 2.049980401992798}
-03/05/2022 11:16:44 - INFO - codeparrot_training - Step 38975: {'lr': 0.0004268704812735681, 'samples': 19955712, 'steps': 38975, 'loss/train': 1.6502013206481934}
-03/05/2022 11:16:44 - INFO - codeparrot_training - Skipping example with length 799 (seq_length=1024)
-03/05/2022 11:16:49 - INFO - codeparrot_training - Step 38976: {'lr': 0.00042686673079065637, 'samples': 19956224, 'steps': 38976, 'loss/train': 1.1977686882019043}
-03/05/2022 11:16:52 - INFO - codeparrot_training - Step 38977: {'lr': 0.00042686298022805126, 'samples': 19956736, 'steps': 38977, 'loss/train': 0.8904712796211243}
-03/05/2022 11:16:52 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/05/2022 11:16:57 - INFO - codeparrot_training - Step 38978: {'lr': 0.0004268592295857544, 'samples': 19957248, 'steps': 38978, 'loss/train': 1.970947504043579}
-03/05/2022 11:17:00 - INFO - codeparrot_training - Step 38979: {'lr': 0.0004268554788637675, 'samples': 19957760, 'steps': 38979, 'loss/train': 1.9199877977371216}
-03/05/2022 11:17:01 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/05/2022 11:17:06 - INFO - codeparrot_training - Step 38980: {'lr': 0.0004268517280620923, 'samples': 19958272, 'steps': 38980, 'loss/train': 0.5075897574424744}
-03/05/2022 11:17:09 - INFO - codeparrot_training - Step 38981: {'lr': 0.0004268479771807303, 'samples': 19958784, 'steps': 38981, 'loss/train': 1.8086477518081665}
-03/05/2022 11:17:09 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 11:17:14 - INFO - codeparrot_training - Step 38982: {'lr': 0.00042684422621968346, 'samples': 19959296, 'steps': 38982, 'loss/train': 1.1092634201049805}
-03/05/2022 11:17:17 - INFO - codeparrot_training - Step 38983: {'lr': 0.0004268404751789533, 'samples': 19959808, 'steps': 38983, 'loss/train': 0.6658592820167542}
-03/05/2022 11:17:17 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 11:17:23 - INFO - codeparrot_training - Step 38984: {'lr': 0.0004268367240585416, 'samples': 19960320, 'steps': 38984, 'loss/train': 1.5414124727249146}
-03/05/2022 11:17:26 - INFO - codeparrot_training - Step 38985: {'lr': 0.0004268329728584499, 'samples': 19960832, 'steps': 38985, 'loss/train': 1.8811044692993164}
-03/05/2022 11:17:26 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/05/2022 11:17:31 - INFO - codeparrot_training - Step 38986: {'lr': 0.0004268292215786801, 'samples': 19961344, 'steps': 38986, 'loss/train': 1.8472638130187988}
-03/05/2022 11:17:34 - INFO - codeparrot_training - Step 38987: {'lr': 0.0004268254702192337, 'samples': 19961856, 'steps': 38987, 'loss/train': 1.2741777896881104}
-03/05/2022 11:17:34 - INFO - codeparrot_training - Skipping example with length 470 (seq_length=1024)
-03/05/2022 11:17:40 - INFO - codeparrot_training - Step 38988: {'lr': 0.00042682171878011255, 'samples': 19962368, 'steps': 38988, 'loss/train': 0.5593450665473938}
-03/05/2022 11:17:43 - INFO - codeparrot_training - Step 38989: {'lr': 0.00042681796726131815, 'samples': 19962880, 'steps': 38989, 'loss/train': 0.12118187546730042}
-03/05/2022 11:17:43 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/05/2022 11:17:48 - INFO - codeparrot_training - Step 38990: {'lr': 0.0004268142156628524, 'samples': 19963392, 'steps': 38990, 'loss/train': 1.288893461227417}
-03/05/2022 11:17:51 - INFO - codeparrot_training - Step 38991: {'lr': 0.00042681046398471693, 'samples': 19963904, 'steps': 38991, 'loss/train': 2.1073215007781982}
-03/05/2022 11:17:52 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/05/2022 11:17:57 - INFO - codeparrot_training - Step 38992: {'lr': 0.00042680671222691325, 'samples': 19964416, 'steps': 38992, 'loss/train': 1.733243703842163}
-03/05/2022 11:18:00 - INFO - codeparrot_training - Step 38993: {'lr': 0.0004268029603894433, 'samples': 19964928, 'steps': 38993, 'loss/train': 2.208637237548828}
-03/05/2022 11:18:00 - INFO - codeparrot_training - Skipping example with length 107 (seq_length=1024)
-03/05/2022 11:18:05 - INFO - codeparrot_training - Step 38994: {'lr': 0.00042679920847230865, 'samples': 19965440, 'steps': 38994, 'loss/train': 1.5811805725097656}
-03/05/2022 11:18:08 - INFO - codeparrot_training - Step 38995: {'lr': 0.000426795456475511, 'samples': 19965952, 'steps': 38995, 'loss/train': 1.5416536331176758}
-03/05/2022 11:18:08 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/05/2022 11:18:14 - INFO - codeparrot_training - Step 38996: {'lr': 0.00042679170439905204, 'samples': 19966464, 'steps': 38996, 'loss/train': 1.6714760065078735}
-03/05/2022 11:18:17 - INFO - codeparrot_training - Step 38997: {'lr': 0.0004267879522429334, 'samples': 19966976, 'steps': 38997, 'loss/train': 1.8261314630508423}
-03/05/2022 11:18:17 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/05/2022 11:18:22 - INFO - codeparrot_training - Step 38998: {'lr': 0.00042678420000715687, 'samples': 19967488, 'steps': 38998, 'loss/train': 2.248667001724243}
-03/05/2022 11:18:25 - INFO - codeparrot_training - Step 38999: {'lr': 0.0004267804476917242, 'samples': 19968000, 'steps': 38999, 'loss/train': 2.644012212753296}
-03/05/2022 11:18:25 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/05/2022 11:18:31 - INFO - codeparrot_training - Step 39000: {'lr': 0.00042677669529663686, 'samples': 19968512, 'steps': 39000, 'loss/train': 1.4423401355743408}
-03/05/2022 11:18:34 - INFO - codeparrot_training - Step 39001: {'lr': 0.0004267729428218968, 'samples': 19969024, 'steps': 39001, 'loss/train': 1.3501769304275513}
-03/05/2022 11:18:35 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/05/2022 11:18:39 - INFO - codeparrot_training - Step 39002: {'lr': 0.0004267691902675055, 'samples': 19969536, 'steps': 39002, 'loss/train': 1.4146558046340942}
-03/05/2022 11:18:42 - INFO - codeparrot_training - Step 39003: {'lr': 0.0004267654376334647, 'samples': 19970048, 'steps': 39003, 'loss/train': 1.7157591581344604}
-03/05/2022 11:18:43 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/05/2022 11:18:48 - INFO - codeparrot_training - Step 39004: {'lr': 0.00042676168491977617, 'samples': 19970560, 'steps': 39004, 'loss/train': 2.011533498764038}
-03/05/2022 11:18:51 - INFO - codeparrot_training - Step 39005: {'lr': 0.00042675793212644156, 'samples': 19971072, 'steps': 39005, 'loss/train': 0.9007067084312439}
-03/05/2022 11:18:52 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/05/2022 11:18:56 - INFO - codeparrot_training - Step 39006: {'lr': 0.00042675417925346255, 'samples': 19971584, 'steps': 39006, 'loss/train': 1.8242809772491455}
-03/05/2022 11:18:59 - INFO - codeparrot_training - Step 39007: {'lr': 0.0004267504263008408, 'samples': 19972096, 'steps': 39007, 'loss/train': 1.398826241493225}
-03/05/2022 11:19:00 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/05/2022 11:19:04 - INFO - codeparrot_training - Step 39008: {'lr': 0.0004267466732685781, 'samples': 19972608, 'steps': 39008, 'loss/train': 1.4457794427871704}
-03/05/2022 11:19:08 - INFO - codeparrot_training - Step 39009: {'lr': 0.000426742920156676, 'samples': 19973120, 'steps': 39009, 'loss/train': 1.3705793619155884}
-03/05/2022 11:19:08 - INFO - codeparrot_training - Skipping example with length 506 (seq_length=1024)
-03/05/2022 11:19:13 - INFO - codeparrot_training - Step 39010: {'lr': 0.00042673916696513625, 'samples': 19973632, 'steps': 39010, 'loss/train': 1.8823187351226807}
-03/05/2022 11:19:16 - INFO - codeparrot_training - Step 39011: {'lr': 0.0004267354136939607, 'samples': 19974144, 'steps': 39011, 'loss/train': 2.3398311138153076}
-03/05/2022 11:19:16 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 11:19:21 - INFO - codeparrot_training - Step 39012: {'lr': 0.0004267316603431508, 'samples': 19974656, 'steps': 39012, 'loss/train': 1.3488638401031494}
-03/05/2022 11:19:24 - INFO - codeparrot_training - Step 39013: {'lr': 0.00042672790691270835, 'samples': 19975168, 'steps': 39013, 'loss/train': 1.4324791431427002}
-03/05/2022 11:19:24 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/05/2022 11:19:30 - INFO - codeparrot_training - Step 39014: {'lr': 0.00042672415340263507, 'samples': 19975680, 'steps': 39014, 'loss/train': 1.1562247276306152}
-03/05/2022 11:19:33 - INFO - codeparrot_training - Step 39015: {'lr': 0.00042672039981293255, 'samples': 19976192, 'steps': 39015, 'loss/train': 2.0197999477386475}
-03/05/2022 11:19:34 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/05/2022 11:19:38 - INFO - codeparrot_training - Step 39016: {'lr': 0.0004267166461436025, 'samples': 19976704, 'steps': 39016, 'loss/train': 0.9053488969802856}
-03/05/2022 11:19:41 - INFO - codeparrot_training - Step 39017: {'lr': 0.0004267128923946468, 'samples': 19977216, 'steps': 39017, 'loss/train': 1.7771810293197632}
-03/05/2022 11:19:42 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/05/2022 11:19:47 - INFO - codeparrot_training - Step 39018: {'lr': 0.00042670913856606693, 'samples': 19977728, 'steps': 39018, 'loss/train': 1.502582311630249}
-03/05/2022 11:19:50 - INFO - codeparrot_training - Step 39019: {'lr': 0.0004267053846578646, 'samples': 19978240, 'steps': 39019, 'loss/train': 1.471237301826477}
-03/05/2022 11:19:50 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/05/2022 11:19:55 - INFO - codeparrot_training - Step 39020: {'lr': 0.00042670163067004156, 'samples': 19978752, 'steps': 39020, 'loss/train': 1.9652624130249023}
-03/05/2022 11:19:59 - INFO - codeparrot_training - Step 39021: {'lr': 0.00042669787660259956, 'samples': 19979264, 'steps': 39021, 'loss/train': 0.4530816972255707}
-03/05/2022 11:19:59 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/05/2022 11:20:04 - INFO - codeparrot_training - Step 39022: {'lr': 0.0004266941224555402, 'samples': 19979776, 'steps': 39022, 'loss/train': 2.6839938163757324}
-03/05/2022 11:20:07 - INFO - codeparrot_training - Step 39023: {'lr': 0.0004266903682288652, 'samples': 19980288, 'steps': 39023, 'loss/train': 1.3970366716384888}
-03/05/2022 11:20:08 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/05/2022 11:20:12 - INFO - codeparrot_training - Step 39024: {'lr': 0.00042668661392257626, 'samples': 19980800, 'steps': 39024, 'loss/train': 1.744213342666626}
-03/05/2022 11:20:15 - INFO - codeparrot_training - Step 39025: {'lr': 0.00042668285953667497, 'samples': 19981312, 'steps': 39025, 'loss/train': 1.6673506498336792}
-03/05/2022 11:20:16 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/05/2022 11:20:21 - INFO - codeparrot_training - Step 39026: {'lr': 0.0004266791050711632, 'samples': 19981824, 'steps': 39026, 'loss/train': 2.0671377182006836}
-03/05/2022 11:20:24 - INFO - codeparrot_training - Step 39027: {'lr': 0.0004266753505260425, 'samples': 19982336, 'steps': 39027, 'loss/train': 1.5908591747283936}
-03/05/2022 11:20:25 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/05/2022 11:20:29 - INFO - codeparrot_training - Step 39028: {'lr': 0.00042667159590131467, 'samples': 19982848, 'steps': 39028, 'loss/train': 2.464757204055786}
-03/05/2022 11:20:32 - INFO - codeparrot_training - Step 39029: {'lr': 0.0004266678411969813, 'samples': 19983360, 'steps': 39029, 'loss/train': 1.2391139268875122}
-03/05/2022 11:20:33 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 11:20:38 - INFO - codeparrot_training - Step 39030: {'lr': 0.0004266640864130441, 'samples': 19983872, 'steps': 39030, 'loss/train': 2.689448356628418}
-03/05/2022 11:20:41 - INFO - codeparrot_training - Step 39031: {'lr': 0.00042666033154950485, 'samples': 19984384, 'steps': 39031, 'loss/train': 2.36437726020813}
-03/05/2022 11:20:41 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/05/2022 11:20:46 - INFO - codeparrot_training - Step 39032: {'lr': 0.00042665657660636517, 'samples': 19984896, 'steps': 39032, 'loss/train': 1.2376725673675537}
-03/05/2022 11:20:49 - INFO - codeparrot_training - Step 39033: {'lr': 0.0004266528215836267, 'samples': 19985408, 'steps': 39033, 'loss/train': 1.7314574718475342}
-03/05/2022 11:20:50 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/05/2022 11:20:54 - INFO - codeparrot_training - Step 39034: {'lr': 0.0004266490664812913, 'samples': 19985920, 'steps': 39034, 'loss/train': 2.633453607559204}
-03/05/2022 11:20:58 - INFO - codeparrot_training - Step 39035: {'lr': 0.00042664531129936044, 'samples': 19986432, 'steps': 39035, 'loss/train': 1.098887324333191}
-03/05/2022 11:20:58 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/05/2022 11:21:03 - INFO - codeparrot_training - Step 39036: {'lr': 0.00042664155603783606, 'samples': 19986944, 'steps': 39036, 'loss/train': 1.9525142908096313}
-03/05/2022 11:21:06 - INFO - codeparrot_training - Step 39037: {'lr': 0.00042663780069671965, 'samples': 19987456, 'steps': 39037, 'loss/train': 1.3510466814041138}
-03/05/2022 11:21:06 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 11:21:11 - INFO - codeparrot_training - Step 39038: {'lr': 0.00042663404527601293, 'samples': 19987968, 'steps': 39038, 'loss/train': 1.695973515510559}
-03/05/2022 11:21:14 - INFO - codeparrot_training - Step 39039: {'lr': 0.00042663028977571774, 'samples': 19988480, 'steps': 39039, 'loss/train': 1.1089729070663452}
-03/05/2022 11:21:15 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/05/2022 11:21:20 - INFO - codeparrot_training - Step 39040: {'lr': 0.0004266265341958355, 'samples': 19988992, 'steps': 39040, 'loss/train': 1.50751793384552}
-03/05/2022 11:21:23 - INFO - codeparrot_training - Step 39041: {'lr': 0.0004266227785363682, 'samples': 19989504, 'steps': 39041, 'loss/train': 1.5025349855422974}
-03/05/2022 11:21:23 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/05/2022 11:21:28 - INFO - codeparrot_training - Step 39042: {'lr': 0.0004266190227973174, 'samples': 19990016, 'steps': 39042, 'loss/train': 1.910841941833496}
-03/05/2022 11:21:31 - INFO - codeparrot_training - Step 39043: {'lr': 0.00042661526697868475, 'samples': 19990528, 'steps': 39043, 'loss/train': 1.483147144317627}
-03/05/2022 11:21:31 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/05/2022 11:21:36 - INFO - codeparrot_training - Step 39044: {'lr': 0.000426611511080472, 'samples': 19991040, 'steps': 39044, 'loss/train': 0.8413196802139282}
-03/05/2022 11:21:39 - INFO - codeparrot_training - Step 39045: {'lr': 0.0004266077551026809, 'samples': 19991552, 'steps': 39045, 'loss/train': 1.4697948694229126}
-03/05/2022 11:21:40 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/05/2022 11:21:45 - INFO - codeparrot_training - Step 39046: {'lr': 0.000426603999045313, 'samples': 19992064, 'steps': 39046, 'loss/train': 1.2267876863479614}
-03/05/2022 11:21:48 - INFO - codeparrot_training - Step 39047: {'lr': 0.00042660024290837003, 'samples': 19992576, 'steps': 39047, 'loss/train': 1.883570671081543}
-03/05/2022 11:21:48 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/05/2022 11:21:53 - INFO - codeparrot_training - Step 39048: {'lr': 0.00042659648669185376, 'samples': 19993088, 'steps': 39048, 'loss/train': 0.9740869998931885}
-03/05/2022 11:21:56 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/05/2022 11:21:58 - INFO - codeparrot_training - Step 39049: {'lr': 0.0004265927303957658, 'samples': 19993600, 'steps': 39049, 'loss/train': 1.70529305934906}
-03/05/2022 11:22:02 - INFO - codeparrot_training - Step 39050: {'lr': 0.0004265889740201079, 'samples': 19994112, 'steps': 39050, 'loss/train': 1.9013792276382446}
-03/05/2022 11:22:05 - INFO - codeparrot_training - Step 39051: {'lr': 0.0004265852175648818, 'samples': 19994624, 'steps': 39051, 'loss/train': 2.120541572570801}
-03/05/2022 11:22:05 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/05/2022 11:22:10 - INFO - codeparrot_training - Step 39052: {'lr': 0.00042658146103008904, 'samples': 19995136, 'steps': 39052, 'loss/train': 2.5940370559692383}
-03/05/2022 11:22:13 - INFO - codeparrot_training - Step 39053: {'lr': 0.0004265777044157314, 'samples': 19995648, 'steps': 39053, 'loss/train': 2.0096001625061035}
-03/05/2022 11:22:14 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/05/2022 11:22:18 - INFO - codeparrot_training - Step 39054: {'lr': 0.0004265739477218106, 'samples': 19996160, 'steps': 39054, 'loss/train': 1.5099202394485474}
-03/05/2022 11:22:22 - INFO - codeparrot_training - Step 39055: {'lr': 0.0004265701909483283, 'samples': 19996672, 'steps': 39055, 'loss/train': 1.1148078441619873}
-03/05/2022 11:22:22 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/05/2022 11:22:27 - INFO - codeparrot_training - Step 39056: {'lr': 0.0004265664340952862, 'samples': 19997184, 'steps': 39056, 'loss/train': 1.7687036991119385}
-03/05/2022 11:22:30 - INFO - codeparrot_training - Step 39057: {'lr': 0.00042656267716268596, 'samples': 19997696, 'steps': 39057, 'loss/train': 2.134798049926758}
-03/05/2022 11:22:30 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/05/2022 11:22:35 - INFO - codeparrot_training - Step 39058: {'lr': 0.00042655892015052945, 'samples': 19998208, 'steps': 39058, 'loss/train': 1.2702082395553589}
-03/05/2022 11:22:38 - INFO - codeparrot_training - Step 39059: {'lr': 0.00042655516305881803, 'samples': 19998720, 'steps': 39059, 'loss/train': 2.060908317565918}
-03/05/2022 11:22:39 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/05/2022 11:22:44 - INFO - codeparrot_training - Step 39060: {'lr': 0.00042655140588755366, 'samples': 19999232, 'steps': 39060, 'loss/train': 2.0070769786834717}
-03/05/2022 11:22:47 - INFO - codeparrot_training - Step 39061: {'lr': 0.0004265476486367379, 'samples': 19999744, 'steps': 39061, 'loss/train': 2.6038737297058105}
-03/05/2022 11:22:48 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 11:22:52 - INFO - codeparrot_training - Step 39062: {'lr': 0.00042654389130637255, 'samples': 20000256, 'steps': 39062, 'loss/train': 1.4936790466308594}
-03/05/2022 11:22:55 - INFO - codeparrot_training - Step 39063: {'lr': 0.0004265401338964592, 'samples': 20000768, 'steps': 39063, 'loss/train': 1.6675760746002197}
-03/05/2022 11:22:56 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/05/2022 11:23:01 - INFO - codeparrot_training - Step 39064: {'lr': 0.0004265363764069997, 'samples': 20001280, 'steps': 39064, 'loss/train': 1.8414729833602905}
-03/05/2022 11:23:04 - INFO - codeparrot_training - Step 39065: {'lr': 0.0004265326188379955, 'samples': 20001792, 'steps': 39065, 'loss/train': 1.8442939519882202}
-03/05/2022 11:23:05 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/05/2022 11:23:09 - INFO - codeparrot_training - Step 39066: {'lr': 0.00042652886118944844, 'samples': 20002304, 'steps': 39066, 'loss/train': 2.2264957427978516}
-03/05/2022 11:23:12 - INFO - codeparrot_training - Step 39067: {'lr': 0.0004265251034613603, 'samples': 20002816, 'steps': 39067, 'loss/train': 1.5313924551010132}
-03/05/2022 11:23:13 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 11:23:18 - INFO - codeparrot_training - Step 39068: {'lr': 0.0004265213456537326, 'samples': 20003328, 'steps': 39068, 'loss/train': 2.2438547611236572}
-03/05/2022 11:23:21 - INFO - codeparrot_training - Step 39069: {'lr': 0.0004265175877665671, 'samples': 20003840, 'steps': 39069, 'loss/train': 0.401152104139328}
-03/05/2022 11:23:21 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/05/2022 11:23:26 - INFO - codeparrot_training - Step 39070: {'lr': 0.0004265138297998655, 'samples': 20004352, 'steps': 39070, 'loss/train': 2.0953726768493652}
-03/05/2022 11:23:29 - INFO - codeparrot_training - Step 39071: {'lr': 0.0004265100717536295, 'samples': 20004864, 'steps': 39071, 'loss/train': 1.6544808149337769}
-03/05/2022 11:23:30 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/05/2022 11:23:35 - INFO - codeparrot_training - Step 39072: {'lr': 0.0004265063136278608, 'samples': 20005376, 'steps': 39072, 'loss/train': 0.7623831629753113}
-03/05/2022 11:23:38 - INFO - codeparrot_training - Step 39073: {'lr': 0.00042650255542256107, 'samples': 20005888, 'steps': 39073, 'loss/train': 1.9172495603561401}
-03/05/2022 11:23:38 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/05/2022 11:23:43 - INFO - codeparrot_training - Step 39074: {'lr': 0.000426498797137732, 'samples': 20006400, 'steps': 39074, 'loss/train': 1.7618412971496582}
-03/05/2022 11:23:46 - INFO - codeparrot_training - Step 39075: {'lr': 0.00042649503877337523, 'samples': 20006912, 'steps': 39075, 'loss/train': 1.6913955211639404}
-03/05/2022 11:23:47 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/05/2022 11:23:51 - INFO - codeparrot_training - Step 39076: {'lr': 0.0004264912803294926, 'samples': 20007424, 'steps': 39076, 'loss/train': 1.1596757173538208}
-03/05/2022 11:23:54 - INFO - codeparrot_training - Step 39077: {'lr': 0.0004264875218060857, 'samples': 20007936, 'steps': 39077, 'loss/train': 1.4177894592285156}
-03/05/2022 11:23:55 - INFO - codeparrot_training - Skipping example with length 140 (seq_length=1024)
-03/05/2022 11:24:00 - INFO - codeparrot_training - Step 39078: {'lr': 0.00042648376320315634, 'samples': 20008448, 'steps': 39078, 'loss/train': 2.1967215538024902}
-03/05/2022 11:24:03 - INFO - codeparrot_training - Step 39079: {'lr': 0.000426480004520706, 'samples': 20008960, 'steps': 39079, 'loss/train': 1.406382441520691}
-03/05/2022 11:24:03 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/05/2022 11:24:08 - INFO - codeparrot_training - Step 39080: {'lr': 0.00042647624575873656, 'samples': 20009472, 'steps': 39080, 'loss/train': 1.7468113899230957}
-03/05/2022 11:24:12 - INFO - codeparrot_training - Step 39081: {'lr': 0.0004264724869172496, 'samples': 20009984, 'steps': 39081, 'loss/train': 1.6698496341705322}
-03/05/2022 11:24:12 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/05/2022 11:24:17 - INFO - codeparrot_training - Step 39082: {'lr': 0.00042646872799624694, 'samples': 20010496, 'steps': 39082, 'loss/train': 2.103158473968506}
-03/05/2022 11:24:20 - INFO - codeparrot_training - Step 39083: {'lr': 0.00042646496899573005, 'samples': 20011008, 'steps': 39083, 'loss/train': 1.3880624771118164}
-03/05/2022 11:24:20 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/05/2022 11:24:25 - INFO - codeparrot_training - Step 39084: {'lr': 0.0004264612099157009, 'samples': 20011520, 'steps': 39084, 'loss/train': 1.5436391830444336}
-03/05/2022 11:24:28 - INFO - codeparrot_training - Step 39085: {'lr': 0.00042645745075616106, 'samples': 20012032, 'steps': 39085, 'loss/train': 1.1677860021591187}
-03/05/2022 11:24:29 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/05/2022 11:24:34 - INFO - codeparrot_training - Step 39086: {'lr': 0.0004264536915171121, 'samples': 20012544, 'steps': 39086, 'loss/train': 0.7436908483505249}
-03/05/2022 11:24:37 - INFO - codeparrot_training - Step 39087: {'lr': 0.0004264499321985559, 'samples': 20013056, 'steps': 39087, 'loss/train': 1.8198416233062744}
-03/05/2022 11:24:37 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/05/2022 11:24:42 - INFO - codeparrot_training - Step 39088: {'lr': 0.0004264461728004941, 'samples': 20013568, 'steps': 39088, 'loss/train': 1.9524335861206055}
-03/05/2022 11:24:45 - INFO - codeparrot_training - Step 39089: {'lr': 0.0004264424133229283, 'samples': 20014080, 'steps': 39089, 'loss/train': 2.121626615524292}
-03/05/2022 11:24:45 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/05/2022 11:24:51 - INFO - codeparrot_training - Step 39090: {'lr': 0.0004264386537658603, 'samples': 20014592, 'steps': 39090, 'loss/train': 1.7298251390457153}
-03/05/2022 11:24:54 - INFO - codeparrot_training - Step 39091: {'lr': 0.0004264348941292919, 'samples': 20015104, 'steps': 39091, 'loss/train': 1.5489697456359863}
-03/05/2022 11:24:54 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/05/2022 11:24:59 - INFO - codeparrot_training - Step 39092: {'lr': 0.0004264311344132245, 'samples': 20015616, 'steps': 39092, 'loss/train': 1.9535722732543945}
-03/05/2022 11:25:02 - INFO - codeparrot_training - Step 39093: {'lr': 0.00042642737461766003, 'samples': 20016128, 'steps': 39093, 'loss/train': 0.5044448971748352}
-03/05/2022 11:25:03 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/05/2022 11:25:08 - INFO - codeparrot_training - Step 39094: {'lr': 0.0004264236147426, 'samples': 20016640, 'steps': 39094, 'loss/train': 1.9438934326171875}
-03/05/2022 11:25:11 - INFO - codeparrot_training - Step 39095: {'lr': 0.0004264198547880464, 'samples': 20017152, 'steps': 39095, 'loss/train': 1.9148969650268555}
-03/05/2022 11:25:11 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/05/2022 11:25:16 - INFO - codeparrot_training - Step 39096: {'lr': 0.00042641609475400054, 'samples': 20017664, 'steps': 39096, 'loss/train': 0.7560935020446777}
-03/05/2022 11:25:19 - INFO - codeparrot_training - Step 39097: {'lr': 0.0004264123346404644, 'samples': 20018176, 'steps': 39097, 'loss/train': 1.0892333984375}
-03/05/2022 11:25:19 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/05/2022 11:25:25 - INFO - codeparrot_training - Step 39098: {'lr': 0.0004264085744474396, 'samples': 20018688, 'steps': 39098, 'loss/train': 1.7393109798431396}
-03/05/2022 11:25:28 - INFO - codeparrot_training - Step 39099: {'lr': 0.0004264048141749278, 'samples': 20019200, 'steps': 39099, 'loss/train': 1.998140573501587}
-03/05/2022 11:25:28 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/05/2022 11:25:33 - INFO - codeparrot_training - Step 39100: {'lr': 0.00042640105382293073, 'samples': 20019712, 'steps': 39100, 'loss/train': 1.3697302341461182}
-03/05/2022 11:25:36 - INFO - codeparrot_training - Step 39101: {'lr': 0.00042639729339145004, 'samples': 20020224, 'steps': 39101, 'loss/train': 1.869065761566162}
-03/05/2022 11:25:36 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/05/2022 11:25:42 - INFO - codeparrot_training - Step 39102: {'lr': 0.0004263935328804874, 'samples': 20020736, 'steps': 39102, 'loss/train': 1.7753989696502686}
-03/05/2022 11:25:44 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/05/2022 11:25:47 - INFO - codeparrot_training - Step 39103: {'lr': 0.0004263897722900447, 'samples': 20021248, 'steps': 39103, 'loss/train': 0.828503429889679}
-03/05/2022 11:25:50 - INFO - codeparrot_training - Step 39104: {'lr': 0.0004263860116201234, 'samples': 20021760, 'steps': 39104, 'loss/train': 1.2966006994247437}
-03/05/2022 11:25:54 - INFO - codeparrot_training - Step 39105: {'lr': 0.00042638225087072523, 'samples': 20022272, 'steps': 39105, 'loss/train': 1.6922987699508667}
-03/05/2022 11:25:54 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/05/2022 11:25:59 - INFO - codeparrot_training - Step 39106: {'lr': 0.00042637849004185203, 'samples': 20022784, 'steps': 39106, 'loss/train': 1.375722050666809}
-03/05/2022 11:26:02 - INFO - codeparrot_training - Step 39107: {'lr': 0.0004263747291335054, 'samples': 20023296, 'steps': 39107, 'loss/train': 1.4237117767333984}
-03/05/2022 11:26:02 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 11:26:07 - INFO - codeparrot_training - Step 39108: {'lr': 0.00042637096814568696, 'samples': 20023808, 'steps': 39108, 'loss/train': 1.5423437356948853}
-03/05/2022 11:26:10 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/05/2022 11:26:13 - INFO - codeparrot_training - Step 39109: {'lr': 0.0004263672070783986, 'samples': 20024320, 'steps': 39109, 'loss/train': 0.9405554533004761}
-03/05/2022 11:26:16 - INFO - codeparrot_training - Step 39110: {'lr': 0.0004263634459316418, 'samples': 20024832, 'steps': 39110, 'loss/train': 1.620505690574646}
-03/05/2022 11:26:19 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/05/2022 11:26:21 - INFO - codeparrot_training - Step 39111: {'lr': 0.0004263596847054184, 'samples': 20025344, 'steps': 39111, 'loss/train': 2.268878221511841}
-03/05/2022 11:26:24 - INFO - codeparrot_training - Step 39112: {'lr': 0.00042635592339973006, 'samples': 20025856, 'steps': 39112, 'loss/train': 2.8147025108337402}
-03/05/2022 11:26:27 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 11:26:29 - INFO - codeparrot_training - Step 39113: {'lr': 0.00042635216201457836, 'samples': 20026368, 'steps': 39113, 'loss/train': 2.2718677520751953}
-03/05/2022 11:26:33 - INFO - codeparrot_training - Step 39114: {'lr': 0.00042634840054996527, 'samples': 20026880, 'steps': 39114, 'loss/train': 1.9831773042678833}
-03/05/2022 11:26:35 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/05/2022 11:26:38 - INFO - codeparrot_training - Step 39115: {'lr': 0.00042634463900589214, 'samples': 20027392, 'steps': 39115, 'loss/train': 1.8290053606033325}
-03/05/2022 11:26:41 - INFO - codeparrot_training - Step 39116: {'lr': 0.0004263408773823609, 'samples': 20027904, 'steps': 39116, 'loss/train': 1.9194083213806152}
-03/05/2022 11:26:44 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/05/2022 11:26:47 - INFO - codeparrot_training - Step 39117: {'lr': 0.00042633711567937325, 'samples': 20028416, 'steps': 39117, 'loss/train': 0.9745329022407532}
-03/05/2022 11:26:50 - INFO - codeparrot_training - Step 39118: {'lr': 0.00042633335389693073, 'samples': 20028928, 'steps': 39118, 'loss/train': 2.0196757316589355}
-03/05/2022 11:26:53 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/05/2022 11:26:55 - INFO - codeparrot_training - Step 39119: {'lr': 0.0004263295920350352, 'samples': 20029440, 'steps': 39119, 'loss/train': 1.5921719074249268}
-03/05/2022 11:26:58 - INFO - codeparrot_training - Step 39120: {'lr': 0.0004263258300936882, 'samples': 20029952, 'steps': 39120, 'loss/train': 0.736976683139801}
-03/05/2022 11:27:01 - INFO - codeparrot_training - Skipping example with length 589 (seq_length=1024)
-03/05/2022 11:27:03 - INFO - codeparrot_training - Step 39121: {'lr': 0.00042632206807289154, 'samples': 20030464, 'steps': 39121, 'loss/train': 1.0121369361877441}
-03/05/2022 11:27:07 - INFO - codeparrot_training - Step 39122: {'lr': 0.00042631830597264687, 'samples': 20030976, 'steps': 39122, 'loss/train': 2.478888511657715}
-03/05/2022 11:27:09 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 11:27:12 - INFO - codeparrot_training - Step 39123: {'lr': 0.0004263145437929559, 'samples': 20031488, 'steps': 39123, 'loss/train': 1.665016531944275}
-03/05/2022 11:27:15 - INFO - codeparrot_training - Step 39124: {'lr': 0.0004263107815338203, 'samples': 20032000, 'steps': 39124, 'loss/train': 2.112304449081421}
-03/05/2022 11:27:19 - INFO - codeparrot_training - Step 39125: {'lr': 0.00042630701919524176, 'samples': 20032512, 'steps': 39125, 'loss/train': 1.4886009693145752}
-03/05/2022 11:27:20 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/05/2022 11:27:24 - INFO - codeparrot_training - Step 39126: {'lr': 0.00042630325677722204, 'samples': 20033024, 'steps': 39126, 'loss/train': 1.041352391242981}
-03/05/2022 11:27:27 - INFO - codeparrot_training - Step 39127: {'lr': 0.0004262994942797628, 'samples': 20033536, 'steps': 39127, 'loss/train': 2.1906192302703857}
-03/05/2022 11:27:28 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/05/2022 11:27:32 - INFO - codeparrot_training - Step 39128: {'lr': 0.0004262957317028657, 'samples': 20034048, 'steps': 39128, 'loss/train': 1.2582366466522217}
-03/05/2022 11:27:36 - INFO - codeparrot_training - Step 39129: {'lr': 0.00042629196904653245, 'samples': 20034560, 'steps': 39129, 'loss/train': 1.5137524604797363}
-03/05/2022 11:27:37 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/05/2022 11:27:41 - INFO - codeparrot_training - Step 39130: {'lr': 0.00042628820631076484, 'samples': 20035072, 'steps': 39130, 'loss/train': 1.637446403503418}
-03/05/2022 11:27:44 - INFO - codeparrot_training - Step 39131: {'lr': 0.0004262844434955644, 'samples': 20035584, 'steps': 39131, 'loss/train': 1.9151180982589722}
-03/05/2022 11:27:45 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/05/2022 11:27:49 - INFO - codeparrot_training - Step 39132: {'lr': 0.00042628068060093294, 'samples': 20036096, 'steps': 39132, 'loss/train': 1.630250096321106}
-03/05/2022 11:27:52 - INFO - codeparrot_training - Step 39133: {'lr': 0.0004262769176268722, 'samples': 20036608, 'steps': 39133, 'loss/train': 1.9063870906829834}
-03/05/2022 11:27:53 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 11:27:58 - INFO - codeparrot_training - Step 39134: {'lr': 0.0004262731545733837, 'samples': 20037120, 'steps': 39134, 'loss/train': 1.768835186958313}
-03/05/2022 11:28:01 - INFO - codeparrot_training - Step 39135: {'lr': 0.0004262693914404692, 'samples': 20037632, 'steps': 39135, 'loss/train': 1.9593032598495483}
-03/05/2022 11:28:02 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 11:28:06 - INFO - codeparrot_training - Step 39136: {'lr': 0.0004262656282281305, 'samples': 20038144, 'steps': 39136, 'loss/train': 1.2500556707382202}
-03/05/2022 11:28:09 - INFO - codeparrot_training - Step 39137: {'lr': 0.0004262618649363692, 'samples': 20038656, 'steps': 39137, 'loss/train': 1.6795276403427124}
-03/05/2022 11:28:10 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/05/2022 11:28:14 - INFO - codeparrot_training - Step 39138: {'lr': 0.0004262581015651871, 'samples': 20039168, 'steps': 39138, 'loss/train': 1.1863007545471191}
-03/05/2022 11:28:18 - INFO - codeparrot_training - Step 39139: {'lr': 0.0004262543381145857, 'samples': 20039680, 'steps': 39139, 'loss/train': 2.330703020095825}
-03/05/2022 11:28:18 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 11:28:23 - INFO - codeparrot_training - Step 39140: {'lr': 0.0004262505745845669, 'samples': 20040192, 'steps': 39140, 'loss/train': 1.2345930337905884}
-03/05/2022 11:28:26 - INFO - codeparrot_training - Step 39141: {'lr': 0.0004262468109751323, 'samples': 20040704, 'steps': 39141, 'loss/train': 1.7980554103851318}
-03/05/2022 11:28:27 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/05/2022 11:28:31 - INFO - codeparrot_training - Step 39142: {'lr': 0.0004262430472862836, 'samples': 20041216, 'steps': 39142, 'loss/train': 1.4580658674240112}
-03/05/2022 11:28:34 - INFO - codeparrot_training - Step 39143: {'lr': 0.00042623928351802245, 'samples': 20041728, 'steps': 39143, 'loss/train': 1.6295183897018433}
-03/05/2022 11:28:35 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/05/2022 11:28:40 - INFO - codeparrot_training - Step 39144: {'lr': 0.00042623551967035066, 'samples': 20042240, 'steps': 39144, 'loss/train': 2.397862434387207}
-03/05/2022 11:28:43 - INFO - codeparrot_training - Step 39145: {'lr': 0.0004262317557432699, 'samples': 20042752, 'steps': 39145, 'loss/train': 1.4817488193511963}
-03/05/2022 11:28:43 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/05/2022 11:28:48 - INFO - codeparrot_training - Step 39146: {'lr': 0.0004262279917367817, 'samples': 20043264, 'steps': 39146, 'loss/train': 1.7306450605392456}
-03/05/2022 11:28:51 - INFO - codeparrot_training - Step 39147: {'lr': 0.00042622422765088805, 'samples': 20043776, 'steps': 39147, 'loss/train': 1.9909801483154297}
-03/05/2022 11:28:51 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 11:28:57 - INFO - codeparrot_training - Step 39148: {'lr': 0.00042622046348559034, 'samples': 20044288, 'steps': 39148, 'loss/train': 1.649040699005127}
-03/05/2022 11:29:00 - INFO - codeparrot_training - Step 39149: {'lr': 0.00042621669924089044, 'samples': 20044800, 'steps': 39149, 'loss/train': 0.8156708478927612}
-03/05/2022 11:29:00 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 11:29:05 - INFO - codeparrot_training - Step 39150: {'lr': 0.00042621293491679007, 'samples': 20045312, 'steps': 39150, 'loss/train': 1.2928657531738281}
-03/05/2022 11:29:08 - INFO - codeparrot_training - Step 39151: {'lr': 0.00042620917051329086, 'samples': 20045824, 'steps': 39151, 'loss/train': 2.0366790294647217}
-03/05/2022 11:29:09 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 11:29:14 - INFO - codeparrot_training - Step 39152: {'lr': 0.0004262054060303945, 'samples': 20046336, 'steps': 39152, 'loss/train': 2.18139386177063}
-03/05/2022 11:29:17 - INFO - codeparrot_training - Step 39153: {'lr': 0.00042620164146810267, 'samples': 20046848, 'steps': 39153, 'loss/train': 3.1144769191741943}
-03/05/2022 11:29:18 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/05/2022 11:29:22 - INFO - codeparrot_training - Step 39154: {'lr': 0.0004261978768264172, 'samples': 20047360, 'steps': 39154, 'loss/train': 1.9984711408615112}
-03/05/2022 11:29:25 - INFO - codeparrot_training - Step 39155: {'lr': 0.00042619411210533957, 'samples': 20047872, 'steps': 39155, 'loss/train': 2.014003038406372}
-03/05/2022 11:29:26 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 11:29:30 - INFO - codeparrot_training - Step 39156: {'lr': 0.00042619034730487167, 'samples': 20048384, 'steps': 39156, 'loss/train': 1.2428696155548096}
-03/05/2022 11:29:34 - INFO - codeparrot_training - Step 39157: {'lr': 0.00042618658242501507, 'samples': 20048896, 'steps': 39157, 'loss/train': 1.401235580444336}
-03/05/2022 11:29:34 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 11:29:39 - INFO - codeparrot_training - Step 39158: {'lr': 0.0004261828174657716, 'samples': 20049408, 'steps': 39158, 'loss/train': 1.4573992490768433}
-03/05/2022 11:29:42 - INFO - codeparrot_training - Step 39159: {'lr': 0.0004261790524271427, 'samples': 20049920, 'steps': 39159, 'loss/train': 1.9141509532928467}
-03/05/2022 11:29:43 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/05/2022 11:29:47 - INFO - codeparrot_training - Step 39160: {'lr': 0.00042617528730913036, 'samples': 20050432, 'steps': 39160, 'loss/train': 1.8278671503067017}
-03/05/2022 11:29:51 - INFO - codeparrot_training - Step 39161: {'lr': 0.00042617152211173615, 'samples': 20050944, 'steps': 39161, 'loss/train': 2.496934175491333}
-03/05/2022 11:29:53 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/05/2022 11:29:56 - INFO - codeparrot_training - Step 39162: {'lr': 0.0004261677568349618, 'samples': 20051456, 'steps': 39162, 'loss/train': 1.7759982347488403}
-03/05/2022 11:29:59 - INFO - codeparrot_training - Step 39163: {'lr': 0.0004261639914788089, 'samples': 20051968, 'steps': 39163, 'loss/train': 2.133173704147339}
-03/05/2022 11:30:01 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/05/2022 11:30:04 - INFO - codeparrot_training - Step 39164: {'lr': 0.0004261602260432792, 'samples': 20052480, 'steps': 39164, 'loss/train': 1.7375026941299438}
-03/05/2022 11:30:07 - INFO - codeparrot_training - Step 39165: {'lr': 0.0004261564605283745, 'samples': 20052992, 'steps': 39165, 'loss/train': 1.407943844795227}
-03/05/2022 11:30:09 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/05/2022 11:30:13 - INFO - codeparrot_training - Step 39166: {'lr': 0.0004261526949340965, 'samples': 20053504, 'steps': 39166, 'loss/train': 1.604474425315857}
-03/05/2022 11:30:16 - INFO - codeparrot_training - Step 39167: {'lr': 0.0004261489292604467, 'samples': 20054016, 'steps': 39167, 'loss/train': 1.9670841693878174}
-03/05/2022 11:30:21 - INFO - codeparrot_training - Step 39168: {'lr': 0.0004261451635074269, 'samples': 20054528, 'steps': 39168, 'loss/train': 1.29154372215271}
-03/05/2022 11:30:24 - INFO - codeparrot_training - Step 39169: {'lr': 0.0004261413976750388, 'samples': 20055040, 'steps': 39169, 'loss/train': 1.3283538818359375}
-03/05/2022 11:30:26 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/05/2022 11:30:29 - INFO - codeparrot_training - Step 39170: {'lr': 0.00042613763176328415, 'samples': 20055552, 'steps': 39170, 'loss/train': 1.0437188148498535}
-03/05/2022 11:30:33 - INFO - codeparrot_training - Step 39171: {'lr': 0.00042613386577216455, 'samples': 20056064, 'steps': 39171, 'loss/train': 1.861180067062378}
-03/05/2022 11:30:34 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/05/2022 11:30:38 - INFO - codeparrot_training - Step 39172: {'lr': 0.0004261300997016818, 'samples': 20056576, 'steps': 39172, 'loss/train': 1.7584348917007446}
-03/05/2022 11:30:41 - INFO - codeparrot_training - Step 39173: {'lr': 0.0004261263335518375, 'samples': 20057088, 'steps': 39173, 'loss/train': 2.1167593002319336}
-03/05/2022 11:30:43 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/05/2022 11:30:46 - INFO - codeparrot_training - Step 39174: {'lr': 0.00042612256732263345, 'samples': 20057600, 'steps': 39174, 'loss/train': 2.011868715286255}
-03/05/2022 11:30:50 - INFO - codeparrot_training - Step 39175: {'lr': 0.0004261188010140712, 'samples': 20058112, 'steps': 39175, 'loss/train': 2.1888649463653564}
-03/05/2022 11:30:51 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/05/2022 11:30:55 - INFO - codeparrot_training - Step 39176: {'lr': 0.00042611503462615266, 'samples': 20058624, 'steps': 39176, 'loss/train': 2.2671525478363037}
-03/05/2022 11:30:58 - INFO - codeparrot_training - Step 39177: {'lr': 0.0004261112681588793, 'samples': 20059136, 'steps': 39177, 'loss/train': 1.8337476253509521}
-03/05/2022 11:30:59 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/05/2022 11:31:03 - INFO - codeparrot_training - Step 39178: {'lr': 0.000426107501612253, 'samples': 20059648, 'steps': 39178, 'loss/train': 1.7727893590927124}
-03/05/2022 11:31:06 - INFO - codeparrot_training - Step 39179: {'lr': 0.0004261037349862753, 'samples': 20060160, 'steps': 39179, 'loss/train': 0.7417510747909546}
-03/05/2022 11:31:07 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/05/2022 11:31:12 - INFO - codeparrot_training - Step 39180: {'lr': 0.000426099968280948, 'samples': 20060672, 'steps': 39180, 'loss/train': 1.3271936178207397}
-03/05/2022 11:31:15 - INFO - codeparrot_training - Step 39181: {'lr': 0.00042609620149627284, 'samples': 20061184, 'steps': 39181, 'loss/train': 1.4863970279693604}
-03/05/2022 11:31:16 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/05/2022 11:31:20 - INFO - codeparrot_training - Step 39182: {'lr': 0.00042609243463225134, 'samples': 20061696, 'steps': 39182, 'loss/train': 1.324421763420105}
-03/05/2022 11:31:23 - INFO - codeparrot_training - Step 39183: {'lr': 0.00042608866768888533, 'samples': 20062208, 'steps': 39183, 'loss/train': 2.060624122619629}
-03/05/2022 11:31:24 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/05/2022 11:31:29 - INFO - codeparrot_training - Step 39184: {'lr': 0.0004260849006661765, 'samples': 20062720, 'steps': 39184, 'loss/train': 0.9789690375328064}
-03/05/2022 11:31:32 - INFO - codeparrot_training - Step 39185: {'lr': 0.0004260811335641266, 'samples': 20063232, 'steps': 39185, 'loss/train': 0.10304628312587738}
-03/05/2022 11:31:33 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/05/2022 11:31:37 - INFO - codeparrot_training - Step 39186: {'lr': 0.0004260773663827372, 'samples': 20063744, 'steps': 39186, 'loss/train': 0.888137698173523}
-03/05/2022 11:31:40 - INFO - codeparrot_training - Step 39187: {'lr': 0.00042607359912201004, 'samples': 20064256, 'steps': 39187, 'loss/train': 2.519382953643799}
-03/05/2022 11:31:41 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/05/2022 11:31:46 - INFO - codeparrot_training - Step 39188: {'lr': 0.0004260698317819468, 'samples': 20064768, 'steps': 39188, 'loss/train': 1.6876165866851807}
-03/05/2022 11:31:49 - INFO - codeparrot_training - Step 39189: {'lr': 0.00042606606436254926, 'samples': 20065280, 'steps': 39189, 'loss/train': 2.177304267883301}
-03/05/2022 11:31:50 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/05/2022 11:31:54 - INFO - codeparrot_training - Step 39190: {'lr': 0.000426062296863819, 'samples': 20065792, 'steps': 39190, 'loss/train': 1.6838548183441162}
-03/05/2022 11:31:57 - INFO - codeparrot_training - Step 39191: {'lr': 0.00042605852928575796, 'samples': 20066304, 'steps': 39191, 'loss/train': 1.455576777458191}
-03/05/2022 11:31:58 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/05/2022 11:32:02 - INFO - codeparrot_training - Step 39192: {'lr': 0.00042605476162836756, 'samples': 20066816, 'steps': 39192, 'loss/train': 1.828658103942871}
-03/05/2022 11:32:06 - INFO - codeparrot_training - Step 39193: {'lr': 0.00042605099389164957, 'samples': 20067328, 'steps': 39193, 'loss/train': 1.7807128429412842}
-03/05/2022 11:32:06 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/05/2022 11:32:11 - INFO - codeparrot_training - Step 39194: {'lr': 0.00042604722607560575, 'samples': 20067840, 'steps': 39194, 'loss/train': 1.7363500595092773}
-03/05/2022 11:32:14 - INFO - codeparrot_training - Step 39195: {'lr': 0.0004260434581802377, 'samples': 20068352, 'steps': 39195, 'loss/train': 0.9399168491363525}
-03/05/2022 11:32:14 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 11:32:19 - INFO - codeparrot_training - Step 39196: {'lr': 0.0004260396902055473, 'samples': 20068864, 'steps': 39196, 'loss/train': 1.4609107971191406}
-03/05/2022 11:32:22 - INFO - codeparrot_training - Step 39197: {'lr': 0.0004260359221515361, 'samples': 20069376, 'steps': 39197, 'loss/train': 1.13994300365448}
-03/05/2022 11:32:23 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/05/2022 11:32:28 - INFO - codeparrot_training - Step 39198: {'lr': 0.0004260321540182057, 'samples': 20069888, 'steps': 39198, 'loss/train': 1.7611937522888184}
-03/05/2022 11:32:31 - INFO - codeparrot_training - Step 39199: {'lr': 0.00042602838580555814, 'samples': 20070400, 'steps': 39199, 'loss/train': 1.859106183052063}
-03/05/2022 11:32:32 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/05/2022 11:32:36 - INFO - codeparrot_training - Step 39200: {'lr': 0.0004260246175135948, 'samples': 20070912, 'steps': 39200, 'loss/train': 1.0504287481307983}
-03/05/2022 11:32:39 - INFO - codeparrot_training - Step 39201: {'lr': 0.00042602084914231743, 'samples': 20071424, 'steps': 39201, 'loss/train': 1.8610565662384033}
-03/05/2022 11:32:40 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/05/2022 11:32:45 - INFO - codeparrot_training - Step 39202: {'lr': 0.0004260170806917278, 'samples': 20071936, 'steps': 39202, 'loss/train': 0.9496520757675171}
-03/05/2022 11:32:48 - INFO - codeparrot_training - Step 39203: {'lr': 0.0004260133121618276, 'samples': 20072448, 'steps': 39203, 'loss/train': 1.821781873703003}
-03/05/2022 11:32:48 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/05/2022 11:32:53 - INFO - codeparrot_training - Step 39204: {'lr': 0.0004260095435526186, 'samples': 20072960, 'steps': 39204, 'loss/train': 1.6188546419143677}
-03/05/2022 11:32:56 - INFO - codeparrot_training - Step 39205: {'lr': 0.0004260057748641024, 'samples': 20073472, 'steps': 39205, 'loss/train': 1.6171358823776245}
-03/05/2022 11:32:57 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 11:33:02 - INFO - codeparrot_training - Step 39206: {'lr': 0.00042600200609628063, 'samples': 20073984, 'steps': 39206, 'loss/train': 1.3141547441482544}
-03/05/2022 11:33:05 - INFO - codeparrot_training - Step 39207: {'lr': 0.0004259982372491551, 'samples': 20074496, 'steps': 39207, 'loss/train': 1.2619725465774536}
-03/05/2022 11:33:05 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/05/2022 11:33:10 - INFO - codeparrot_training - Step 39208: {'lr': 0.00042599446832272746, 'samples': 20075008, 'steps': 39208, 'loss/train': 1.1962252855300903}
-03/05/2022 11:33:13 - INFO - codeparrot_training - Step 39209: {'lr': 0.0004259906993169995, 'samples': 20075520, 'steps': 39209, 'loss/train': 1.0370994806289673}
-03/05/2022 11:33:13 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/05/2022 11:33:18 - INFO - codeparrot_training - Step 39210: {'lr': 0.00042598693023197283, 'samples': 20076032, 'steps': 39210, 'loss/train': 1.5981732606887817}
-03/05/2022 11:33:21 - INFO - codeparrot_training - Step 39211: {'lr': 0.00042598316106764913, 'samples': 20076544, 'steps': 39211, 'loss/train': 0.6616408824920654}
-03/05/2022 11:33:22 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/05/2022 11:33:27 - INFO - codeparrot_training - Step 39212: {'lr': 0.0004259793918240302, 'samples': 20077056, 'steps': 39212, 'loss/train': 1.0613933801651}
-03/05/2022 11:33:30 - INFO - codeparrot_training - Step 39213: {'lr': 0.00042597562250111753, 'samples': 20077568, 'steps': 39213, 'loss/train': 1.500213623046875}
-03/05/2022 11:33:30 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/05/2022 11:33:35 - INFO - codeparrot_training - Step 39214: {'lr': 0.00042597185309891305, 'samples': 20078080, 'steps': 39214, 'loss/train': 1.5688179731369019}
-03/05/2022 11:33:38 - INFO - codeparrot_training - Step 39215: {'lr': 0.0004259680836174184, 'samples': 20078592, 'steps': 39215, 'loss/train': 1.468929409980774}
-03/05/2022 11:33:39 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/05/2022 11:33:44 - INFO - codeparrot_training - Step 39216: {'lr': 0.0004259643140566352, 'samples': 20079104, 'steps': 39216, 'loss/train': 1.2566858530044556}
-03/05/2022 11:33:47 - INFO - codeparrot_training - Step 39217: {'lr': 0.0004259605444165652, 'samples': 20079616, 'steps': 39217, 'loss/train': 1.6865615844726562}
-03/05/2022 11:33:47 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 11:33:52 - INFO - codeparrot_training - Step 39218: {'lr': 0.0004259567746972101, 'samples': 20080128, 'steps': 39218, 'loss/train': 1.6043339967727661}
-03/05/2022 11:33:55 - INFO - codeparrot_training - Step 39219: {'lr': 0.00042595300489857164, 'samples': 20080640, 'steps': 39219, 'loss/train': 1.5585455894470215}
-03/05/2022 11:33:56 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/05/2022 11:34:01 - INFO - codeparrot_training - Step 39220: {'lr': 0.0004259492350206514, 'samples': 20081152, 'steps': 39220, 'loss/train': 1.396196722984314}
-03/05/2022 11:34:04 - INFO - codeparrot_training - Step 39221: {'lr': 0.00042594546506345124, 'samples': 20081664, 'steps': 39221, 'loss/train': 1.6927073001861572}
-03/05/2022 11:34:04 - INFO - codeparrot_training - Skipping example with length 774 (seq_length=1024)
-03/05/2022 11:34:09 - INFO - codeparrot_training - Step 39222: {'lr': 0.00042594169502697265, 'samples': 20082176, 'steps': 39222, 'loss/train': 1.2485873699188232}
-03/05/2022 11:34:12 - INFO - codeparrot_training - Step 39223: {'lr': 0.00042593792491121753, 'samples': 20082688, 'steps': 39223, 'loss/train': 1.6447014808654785}
-03/05/2022 11:34:12 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/05/2022 11:34:17 - INFO - codeparrot_training - Step 39224: {'lr': 0.00042593415471618744, 'samples': 20083200, 'steps': 39224, 'loss/train': 2.443131923675537}
-03/05/2022 11:34:21 - INFO - codeparrot_training - Step 39225: {'lr': 0.0004259303844418841, 'samples': 20083712, 'steps': 39225, 'loss/train': 1.5844464302062988}
-03/05/2022 11:34:21 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/05/2022 11:34:26 - INFO - codeparrot_training - Step 39226: {'lr': 0.00042592661408830937, 'samples': 20084224, 'steps': 39226, 'loss/train': 1.7553945779800415}
-03/05/2022 11:34:29 - INFO - codeparrot_training - Step 39227: {'lr': 0.00042592284365546474, 'samples': 20084736, 'steps': 39227, 'loss/train': 1.4026416540145874}
-03/05/2022 11:34:29 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 11:34:34 - INFO - codeparrot_training - Step 39228: {'lr': 0.00042591907314335197, 'samples': 20085248, 'steps': 39228, 'loss/train': 1.144972324371338}
-03/05/2022 11:34:38 - INFO - codeparrot_training - Step 39229: {'lr': 0.00042591530255197286, 'samples': 20085760, 'steps': 39229, 'loss/train': 2.1506900787353516}
-03/05/2022 11:34:38 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 11:34:43 - INFO - codeparrot_training - Step 39230: {'lr': 0.00042591153188132903, 'samples': 20086272, 'steps': 39230, 'loss/train': 1.4605000019073486}
-03/05/2022 11:34:46 - INFO - codeparrot_training - Step 39231: {'lr': 0.00042590776113142216, 'samples': 20086784, 'steps': 39231, 'loss/train': 1.7237632274627686}
-03/05/2022 11:34:46 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/05/2022 11:34:51 - INFO - codeparrot_training - Step 39232: {'lr': 0.00042590399030225393, 'samples': 20087296, 'steps': 39232, 'loss/train': 1.3452601432800293}
-03/05/2022 11:34:55 - INFO - codeparrot_training - Step 39233: {'lr': 0.0004259002193938261, 'samples': 20087808, 'steps': 39233, 'loss/train': 0.7326532602310181}
-03/05/2022 11:34:55 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/05/2022 11:35:00 - INFO - codeparrot_training - Step 39234: {'lr': 0.0004258964484061403, 'samples': 20088320, 'steps': 39234, 'loss/train': 2.176058292388916}
-03/05/2022 11:35:04 - INFO - codeparrot_training - Step 39235: {'lr': 0.00042589267733919833, 'samples': 20088832, 'steps': 39235, 'loss/train': 2.362720012664795}
-03/05/2022 11:35:06 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/05/2022 11:35:09 - INFO - codeparrot_training - Step 39236: {'lr': 0.0004258889061930018, 'samples': 20089344, 'steps': 39236, 'loss/train': 1.4387102127075195}
-03/05/2022 11:35:12 - INFO - codeparrot_training - Step 39237: {'lr': 0.0004258851349675524, 'samples': 20089856, 'steps': 39237, 'loss/train': 1.5271624326705933}
-03/05/2022 11:35:15 - INFO - codeparrot_training - Step 39238: {'lr': 0.00042588136366285197, 'samples': 20090368, 'steps': 39238, 'loss/train': 2.0519814491271973}
-03/05/2022 11:35:15 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/05/2022 11:35:20 - INFO - codeparrot_training - Step 39239: {'lr': 0.0004258775922789021, 'samples': 20090880, 'steps': 39239, 'loss/train': 1.9903273582458496}
-03/05/2022 11:35:24 - INFO - codeparrot_training - Step 39240: {'lr': 0.0004258738208157045, 'samples': 20091392, 'steps': 39240, 'loss/train': 1.733928918838501}
-03/05/2022 11:35:24 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/05/2022 11:35:29 - INFO - codeparrot_training - Step 39241: {'lr': 0.0004258700492732608, 'samples': 20091904, 'steps': 39241, 'loss/train': 1.7905579805374146}
-03/05/2022 11:35:32 - INFO - codeparrot_training - Step 39242: {'lr': 0.0004258662776515728, 'samples': 20092416, 'steps': 39242, 'loss/train': 1.8215301036834717}
-03/05/2022 11:35:32 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/05/2022 11:35:37 - INFO - codeparrot_training - Step 39243: {'lr': 0.00042586250595064216, 'samples': 20092928, 'steps': 39243, 'loss/train': 2.164107084274292}
-03/05/2022 11:35:40 - INFO - codeparrot_training - Step 39244: {'lr': 0.0004258587341704706, 'samples': 20093440, 'steps': 39244, 'loss/train': 1.5649827718734741}
-03/05/2022 11:35:41 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/05/2022 11:35:46 - INFO - codeparrot_training - Step 39245: {'lr': 0.00042585496231105986, 'samples': 20093952, 'steps': 39245, 'loss/train': 1.9379334449768066}
-03/05/2022 11:35:49 - INFO - codeparrot_training - Step 39246: {'lr': 0.00042585119037241156, 'samples': 20094464, 'steps': 39246, 'loss/train': 1.90833580493927}
-03/05/2022 11:35:49 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/05/2022 11:35:54 - INFO - codeparrot_training - Step 39247: {'lr': 0.00042584741835452743, 'samples': 20094976, 'steps': 39247, 'loss/train': 1.798171877861023}
-03/05/2022 11:35:57 - INFO - codeparrot_training - Step 39248: {'lr': 0.0004258436462574091, 'samples': 20095488, 'steps': 39248, 'loss/train': 2.4061174392700195}
-03/05/2022 11:35:58 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/05/2022 11:36:03 - INFO - codeparrot_training - Step 39249: {'lr': 0.0004258398740810584, 'samples': 20096000, 'steps': 39249, 'loss/train': 1.8006937503814697}
-03/05/2022 11:36:06 - INFO - codeparrot_training - Step 39250: {'lr': 0.00042583610182547694, 'samples': 20096512, 'steps': 39250, 'loss/train': 1.4761786460876465}
-03/05/2022 11:36:07 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/05/2022 11:36:11 - INFO - codeparrot_training - Step 39251: {'lr': 0.0004258323294906665, 'samples': 20097024, 'steps': 39251, 'loss/train': 1.3168997764587402}
-03/05/2022 11:36:14 - INFO - codeparrot_training - Step 39252: {'lr': 0.00042582855707662864, 'samples': 20097536, 'steps': 39252, 'loss/train': 2.300650119781494}
-03/05/2022 11:36:15 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/05/2022 11:36:19 - INFO - codeparrot_training - Step 39253: {'lr': 0.00042582478458336523, 'samples': 20098048, 'steps': 39253, 'loss/train': 1.4646955728530884}
-03/05/2022 11:36:23 - INFO - codeparrot_training - Step 39254: {'lr': 0.00042582101201087786, 'samples': 20098560, 'steps': 39254, 'loss/train': 1.3625543117523193}
-03/05/2022 11:36:23 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/05/2022 11:36:28 - INFO - codeparrot_training - Step 39255: {'lr': 0.00042581723935916817, 'samples': 20099072, 'steps': 39255, 'loss/train': 0.42943254113197327}
-03/05/2022 11:36:31 - INFO - codeparrot_training - Step 39256: {'lr': 0.00042581346662823804, 'samples': 20099584, 'steps': 39256, 'loss/train': 1.3863340616226196}
-03/05/2022 11:36:32 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/05/2022 11:36:36 - INFO - codeparrot_training - Step 39257: {'lr': 0.00042580969381808906, 'samples': 20100096, 'steps': 39257, 'loss/train': 1.898044228553772}
-03/05/2022 11:36:39 - INFO - codeparrot_training - Step 39258: {'lr': 0.00042580592092872295, 'samples': 20100608, 'steps': 39258, 'loss/train': 2.029705047607422}
-03/05/2022 11:36:40 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/05/2022 11:36:45 - INFO - codeparrot_training - Step 39259: {'lr': 0.0004258021479601414, 'samples': 20101120, 'steps': 39259, 'loss/train': 0.9702457785606384}
-03/05/2022 11:36:48 - INFO - codeparrot_training - Step 39260: {'lr': 0.0004257983749123461, 'samples': 20101632, 'steps': 39260, 'loss/train': 1.1560468673706055}
-03/05/2022 11:36:48 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/05/2022 11:36:53 - INFO - codeparrot_training - Step 39261: {'lr': 0.00042579460178533875, 'samples': 20102144, 'steps': 39261, 'loss/train': 1.7540640830993652}
-03/05/2022 11:36:56 - INFO - codeparrot_training - Step 39262: {'lr': 0.0004257908285791211, 'samples': 20102656, 'steps': 39262, 'loss/train': 0.9023854732513428}
-03/05/2022 11:36:56 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/05/2022 11:37:01 - INFO - codeparrot_training - Step 39263: {'lr': 0.00042578705529369476, 'samples': 20103168, 'steps': 39263, 'loss/train': 1.1134076118469238}
-03/05/2022 11:37:04 - INFO - codeparrot_training - Step 39264: {'lr': 0.00042578328192906153, 'samples': 20103680, 'steps': 39264, 'loss/train': 1.8323874473571777}
-03/05/2022 11:37:04 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 11:37:10 - INFO - codeparrot_training - Step 39265: {'lr': 0.00042577950848522305, 'samples': 20104192, 'steps': 39265, 'loss/train': 1.6415808200836182}
-03/05/2022 11:37:13 - INFO - codeparrot_training - Step 39266: {'lr': 0.0004257757349621811, 'samples': 20104704, 'steps': 39266, 'loss/train': 1.2471224069595337}
-03/05/2022 11:37:13 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/05/2022 11:37:18 - INFO - codeparrot_training - Step 39267: {'lr': 0.0004257719613599372, 'samples': 20105216, 'steps': 39267, 'loss/train': 1.4800223112106323}
-03/05/2022 11:37:21 - INFO - codeparrot_training - Step 39268: {'lr': 0.0004257681876784932, 'samples': 20105728, 'steps': 39268, 'loss/train': 1.3436870574951172}
-03/05/2022 11:37:21 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 11:37:27 - INFO - codeparrot_training - Step 39269: {'lr': 0.0004257644139178508, 'samples': 20106240, 'steps': 39269, 'loss/train': 1.1068660020828247}
-03/05/2022 11:37:30 - INFO - codeparrot_training - Step 39270: {'lr': 0.0004257606400780117, 'samples': 20106752, 'steps': 39270, 'loss/train': 1.8305110931396484}
-03/05/2022 11:37:31 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/05/2022 11:37:36 - INFO - codeparrot_training - Step 39271: {'lr': 0.0004257568661589775, 'samples': 20107264, 'steps': 39271, 'loss/train': 2.0048723220825195}
-03/05/2022 11:37:39 - INFO - codeparrot_training - Step 39272: {'lr': 0.00042575309216074997, 'samples': 20107776, 'steps': 39272, 'loss/train': 1.9744149446487427}
-03/05/2022 11:37:40 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/05/2022 11:37:44 - INFO - codeparrot_training - Step 39273: {'lr': 0.00042574931808333095, 'samples': 20108288, 'steps': 39273, 'loss/train': 1.496464729309082}
-03/05/2022 11:37:47 - INFO - codeparrot_training - Step 39274: {'lr': 0.0004257455439267218, 'samples': 20108800, 'steps': 39274, 'loss/train': 1.4168360233306885}
-03/05/2022 11:37:48 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/05/2022 11:37:52 - INFO - codeparrot_training - Step 39275: {'lr': 0.00042574176969092454, 'samples': 20109312, 'steps': 39275, 'loss/train': 0.6922250986099243}
-03/05/2022 11:37:56 - INFO - codeparrot_training - Step 39276: {'lr': 0.0004257379953759407, 'samples': 20109824, 'steps': 39276, 'loss/train': 1.5159292221069336}
-03/05/2022 11:37:57 - INFO - codeparrot_training - Skipping example with length 757 (seq_length=1024)
-03/05/2022 11:38:01 - INFO - codeparrot_training - Step 39277: {'lr': 0.00042573422098177204, 'samples': 20110336, 'steps': 39277, 'loss/train': 2.0649304389953613}
-03/05/2022 11:38:04 - INFO - codeparrot_training - Step 39278: {'lr': 0.0004257304465084203, 'samples': 20110848, 'steps': 39278, 'loss/train': 1.8487310409545898}
-03/05/2022 11:38:05 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/05/2022 11:38:09 - INFO - codeparrot_training - Step 39279: {'lr': 0.0004257266719558871, 'samples': 20111360, 'steps': 39279, 'loss/train': 1.920003056526184}
-03/05/2022 11:38:12 - INFO - codeparrot_training - Step 39280: {'lr': 0.0004257228973241741, 'samples': 20111872, 'steps': 39280, 'loss/train': 1.4649440050125122}
-03/05/2022 11:38:13 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/05/2022 11:38:18 - INFO - codeparrot_training - Step 39281: {'lr': 0.00042571912261328315, 'samples': 20112384, 'steps': 39281, 'loss/train': 2.0862770080566406}
-03/05/2022 11:38:21 - INFO - codeparrot_training - Step 39282: {'lr': 0.00042571534782321593, 'samples': 20112896, 'steps': 39282, 'loss/train': 1.8228590488433838}
-03/05/2022 11:38:22 - INFO - codeparrot_training - Skipping example with length 148 (seq_length=1024)
-03/05/2022 11:38:27 - INFO - codeparrot_training - Step 39283: {'lr': 0.000425711572953974, 'samples': 20113408, 'steps': 39283, 'loss/train': 1.0335910320281982}
-03/05/2022 11:38:30 - INFO - codeparrot_training - Step 39284: {'lr': 0.00042570779800555914, 'samples': 20113920, 'steps': 39284, 'loss/train': 0.5983594655990601}
-03/05/2022 11:38:32 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/05/2022 11:38:35 - INFO - codeparrot_training - Step 39285: {'lr': 0.00042570402297797304, 'samples': 20114432, 'steps': 39285, 'loss/train': 2.1930768489837646}
-03/05/2022 11:38:38 - INFO - codeparrot_training - Step 39286: {'lr': 0.0004257002478712175, 'samples': 20114944, 'steps': 39286, 'loss/train': 2.088867664337158}
-03/05/2022 11:38:41 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/05/2022 11:38:44 - INFO - codeparrot_training - Step 39287: {'lr': 0.0004256964726852941, 'samples': 20115456, 'steps': 39287, 'loss/train': 1.509057641029358}
-03/05/2022 11:38:47 - INFO - codeparrot_training - Step 39288: {'lr': 0.0004256926974202046, 'samples': 20115968, 'steps': 39288, 'loss/train': 1.154793620109558}
-03/05/2022 11:38:49 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/05/2022 11:38:52 - INFO - codeparrot_training - Step 39289: {'lr': 0.00042568892207595066, 'samples': 20116480, 'steps': 39289, 'loss/train': 1.3559041023254395}
-03/05/2022 11:38:55 - INFO - codeparrot_training - Step 39290: {'lr': 0.000425685146652534, 'samples': 20116992, 'steps': 39290, 'loss/train': 0.9894947409629822}
-03/05/2022 11:38:57 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/05/2022 11:39:00 - INFO - codeparrot_training - Step 39291: {'lr': 0.00042568137114995633, 'samples': 20117504, 'steps': 39291, 'loss/train': 1.4956916570663452}
-03/05/2022 11:39:04 - INFO - codeparrot_training - Step 39292: {'lr': 0.00042567759556821937, 'samples': 20118016, 'steps': 39292, 'loss/train': 2.0803685188293457}
-03/05/2022 11:39:06 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/05/2022 11:39:09 - INFO - codeparrot_training - Step 39293: {'lr': 0.00042567381990732476, 'samples': 20118528, 'steps': 39293, 'loss/train': 0.6321213841438293}
-03/05/2022 11:39:12 - INFO - codeparrot_training - Step 39294: {'lr': 0.0004256700441672743, 'samples': 20119040, 'steps': 39294, 'loss/train': 1.3099424839019775}
-03/05/2022 11:39:16 - INFO - codeparrot_training - Step 39295: {'lr': 0.0004256662683480695, 'samples': 20119552, 'steps': 39295, 'loss/train': 2.103403091430664}
-03/05/2022 11:39:16 - INFO - codeparrot_training - Skipping example with length 694 (seq_length=1024)
-03/05/2022 11:39:21 - INFO - codeparrot_training - Step 39296: {'lr': 0.00042566249244971235, 'samples': 20120064, 'steps': 39296, 'loss/train': 1.986287236213684}
-03/05/2022 11:39:24 - INFO - codeparrot_training - Step 39297: {'lr': 0.0004256587164722043, 'samples': 20120576, 'steps': 39297, 'loss/train': 1.5257185697555542}
-03/05/2022 11:39:25 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 11:39:29 - INFO - codeparrot_training - Step 39298: {'lr': 0.0004256549404155471, 'samples': 20121088, 'steps': 39298, 'loss/train': 0.9372047781944275}
-03/05/2022 11:39:32 - INFO - codeparrot_training - Step 39299: {'lr': 0.0004256511642797426, 'samples': 20121600, 'steps': 39299, 'loss/train': 1.356652855873108}
-03/05/2022 11:39:33 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 11:39:38 - INFO - codeparrot_training - Step 39300: {'lr': 0.0004256473880647923, 'samples': 20122112, 'steps': 39300, 'loss/train': 1.2373672723770142}
-03/05/2022 11:39:41 - INFO - codeparrot_training - Step 39301: {'lr': 0.0004256436117706981, 'samples': 20122624, 'steps': 39301, 'loss/train': 2.090449571609497}
-03/05/2022 11:39:42 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/05/2022 11:39:46 - INFO - codeparrot_training - Step 39302: {'lr': 0.0004256398353974615, 'samples': 20123136, 'steps': 39302, 'loss/train': 2.259685516357422}
-03/05/2022 11:39:49 - INFO - codeparrot_training - Step 39303: {'lr': 0.00042563605894508434, 'samples': 20123648, 'steps': 39303, 'loss/train': 1.4122346639633179}
-03/05/2022 11:39:50 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/05/2022 11:39:55 - INFO - codeparrot_training - Step 39304: {'lr': 0.00042563228241356834, 'samples': 20124160, 'steps': 39304, 'loss/train': 1.8796900510787964}
-03/05/2022 11:39:58 - INFO - codeparrot_training - Step 39305: {'lr': 0.000425628505802915, 'samples': 20124672, 'steps': 39305, 'loss/train': 1.5217339992523193}
-03/05/2022 11:39:59 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/05/2022 11:40:03 - INFO - codeparrot_training - Step 39306: {'lr': 0.0004256247291131263, 'samples': 20125184, 'steps': 39306, 'loss/train': 1.08473539352417}
-03/05/2022 11:40:06 - INFO - codeparrot_training - Step 39307: {'lr': 0.00042562095234420375, 'samples': 20125696, 'steps': 39307, 'loss/train': 0.43585866689682007}
-03/05/2022 11:40:07 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 11:40:11 - INFO - codeparrot_training - Step 39308: {'lr': 0.00042561717549614907, 'samples': 20126208, 'steps': 39308, 'loss/train': 1.2756831645965576}
-03/05/2022 11:40:15 - INFO - codeparrot_training - Step 39309: {'lr': 0.0004256133985689641, 'samples': 20126720, 'steps': 39309, 'loss/train': 1.2425265312194824}
-03/05/2022 11:40:15 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/05/2022 11:40:20 - INFO - codeparrot_training - Step 39310: {'lr': 0.0004256096215626504, 'samples': 20127232, 'steps': 39310, 'loss/train': 2.195155382156372}
-03/05/2022 11:40:23 - INFO - codeparrot_training - Step 39311: {'lr': 0.0004256058444772097, 'samples': 20127744, 'steps': 39311, 'loss/train': 1.2797623872756958}
-03/05/2022 11:40:24 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/05/2022 11:40:28 - INFO - codeparrot_training - Step 39312: {'lr': 0.0004256020673126437, 'samples': 20128256, 'steps': 39312, 'loss/train': 1.314859390258789}
-03/05/2022 11:40:32 - INFO - codeparrot_training - Step 39313: {'lr': 0.0004255982900689541, 'samples': 20128768, 'steps': 39313, 'loss/train': 2.400352716445923}
-03/05/2022 11:40:32 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 11:40:37 - INFO - codeparrot_training - Step 39314: {'lr': 0.0004255945127461427, 'samples': 20129280, 'steps': 39314, 'loss/train': 1.6714900732040405}
-03/05/2022 11:40:40 - INFO - codeparrot_training - Step 39315: {'lr': 0.00042559073534421114, 'samples': 20129792, 'steps': 39315, 'loss/train': 1.3838931322097778}
-03/05/2022 11:40:41 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/05/2022 11:40:45 - INFO - codeparrot_training - Step 39316: {'lr': 0.00042558695786316106, 'samples': 20130304, 'steps': 39316, 'loss/train': 1.8757010698318481}
-03/05/2022 11:40:48 - INFO - codeparrot_training - Step 39317: {'lr': 0.00042558318030299415, 'samples': 20130816, 'steps': 39317, 'loss/train': 2.2323172092437744}
-03/05/2022 11:40:49 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/05/2022 11:40:54 - INFO - codeparrot_training - Step 39318: {'lr': 0.0004255794026637122, 'samples': 20131328, 'steps': 39318, 'loss/train': 1.6905714273452759}
-03/05/2022 11:40:57 - INFO - codeparrot_training - Step 39319: {'lr': 0.0004255756249453169, 'samples': 20131840, 'steps': 39319, 'loss/train': 2.1668126583099365}
-03/05/2022 11:40:58 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/05/2022 11:41:03 - INFO - codeparrot_training - Step 39320: {'lr': 0.00042557184714780993, 'samples': 20132352, 'steps': 39320, 'loss/train': 1.5185813903808594}
-03/05/2022 11:41:06 - INFO - codeparrot_training - Step 39321: {'lr': 0.000425568069271193, 'samples': 20132864, 'steps': 39321, 'loss/train': 2.3960683345794678}
-03/05/2022 11:41:07 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/05/2022 11:41:11 - INFO - codeparrot_training - Step 39322: {'lr': 0.00042556429131546775, 'samples': 20133376, 'steps': 39322, 'loss/train': 2.1479358673095703}
-03/05/2022 11:41:14 - INFO - codeparrot_training - Step 39323: {'lr': 0.000425560513280636, 'samples': 20133888, 'steps': 39323, 'loss/train': 1.4379756450653076}
-03/05/2022 11:41:15 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/05/2022 11:41:19 - INFO - codeparrot_training - Step 39324: {'lr': 0.00042555673516669933, 'samples': 20134400, 'steps': 39324, 'loss/train': 1.374849796295166}
-03/05/2022 11:41:23 - INFO - codeparrot_training - Step 39325: {'lr': 0.0004255529569736596, 'samples': 20134912, 'steps': 39325, 'loss/train': 1.0687437057495117}
-03/05/2022 11:41:24 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/05/2022 11:41:28 - INFO - codeparrot_training - Step 39326: {'lr': 0.0004255491787015183, 'samples': 20135424, 'steps': 39326, 'loss/train': 1.6843093633651733}
-03/05/2022 11:41:31 - INFO - codeparrot_training - Step 39327: {'lr': 0.0004255454003502774, 'samples': 20135936, 'steps': 39327, 'loss/train': 6.155123233795166}
-03/05/2022 11:41:32 - INFO - codeparrot_training - Skipping example with length 24 (seq_length=1024)
-03/05/2022 11:41:36 - INFO - codeparrot_training - Step 39328: {'lr': 0.0004255416219199384, 'samples': 20136448, 'steps': 39328, 'loss/train': 1.7958861589431763}
-03/05/2022 11:41:40 - INFO - codeparrot_training - Step 39329: {'lr': 0.0004255378434105029, 'samples': 20136960, 'steps': 39329, 'loss/train': 1.5802282094955444}
-03/05/2022 11:41:41 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/05/2022 11:41:45 - INFO - codeparrot_training - Step 39330: {'lr': 0.00042553406482197297, 'samples': 20137472, 'steps': 39330, 'loss/train': 1.2636702060699463}
-03/05/2022 11:41:48 - INFO - codeparrot_training - Step 39331: {'lr': 0.00042553028615434997, 'samples': 20137984, 'steps': 39331, 'loss/train': 1.2248021364212036}
-03/05/2022 11:41:49 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 11:41:53 - INFO - codeparrot_training - Step 39332: {'lr': 0.0004255265074076358, 'samples': 20138496, 'steps': 39332, 'loss/train': 2.1438958644866943}
-03/05/2022 11:41:56 - INFO - codeparrot_training - Step 39333: {'lr': 0.00042552272858183203, 'samples': 20139008, 'steps': 39333, 'loss/train': 1.1343510150909424}
-03/05/2022 11:41:58 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/05/2022 11:42:02 - INFO - codeparrot_training - Step 39334: {'lr': 0.0004255189496769405, 'samples': 20139520, 'steps': 39334, 'loss/train': 1.6371914148330688}
-03/05/2022 11:42:05 - INFO - codeparrot_training - Step 39335: {'lr': 0.00042551517069296276, 'samples': 20140032, 'steps': 39335, 'loss/train': 1.1965466737747192}
-03/05/2022 11:42:06 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/05/2022 11:42:10 - INFO - codeparrot_training - Step 39336: {'lr': 0.00042551139162990065, 'samples': 20140544, 'steps': 39336, 'loss/train': 1.686252474784851}
-03/05/2022 11:42:13 - INFO - codeparrot_training - Step 39337: {'lr': 0.0004255076124877558, 'samples': 20141056, 'steps': 39337, 'loss/train': 1.7307718992233276}
-03/05/2022 11:42:15 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/05/2022 11:42:19 - INFO - codeparrot_training - Step 39338: {'lr': 0.0004255038332665299, 'samples': 20141568, 'steps': 39338, 'loss/train': 1.2093846797943115}
-03/05/2022 11:42:22 - INFO - codeparrot_training - Step 39339: {'lr': 0.0004255000539662247, 'samples': 20142080, 'steps': 39339, 'loss/train': 2.201260805130005}
-03/05/2022 11:42:23 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/05/2022 11:42:27 - INFO - codeparrot_training - Step 39340: {'lr': 0.0004254962745868419, 'samples': 20142592, 'steps': 39340, 'loss/train': 1.7000435590744019}
-03/05/2022 11:42:30 - INFO - codeparrot_training - Step 39341: {'lr': 0.00042549249512838325, 'samples': 20143104, 'steps': 39341, 'loss/train': 1.7388160228729248}
-03/05/2022 11:42:31 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/05/2022 11:42:36 - INFO - codeparrot_training - Step 39342: {'lr': 0.00042548871559085026, 'samples': 20143616, 'steps': 39342, 'loss/train': 1.0788383483886719}
-03/05/2022 11:42:39 - INFO - codeparrot_training - Step 39343: {'lr': 0.0004254849359742449, 'samples': 20144128, 'steps': 39343, 'loss/train': 1.23121976852417}
-03/05/2022 11:42:41 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/05/2022 11:42:44 - INFO - codeparrot_training - Step 39344: {'lr': 0.0004254811562785686, 'samples': 20144640, 'steps': 39344, 'loss/train': 1.9464435577392578}
-03/05/2022 11:42:47 - INFO - codeparrot_training - Step 39345: {'lr': 0.00042547737650382324, 'samples': 20145152, 'steps': 39345, 'loss/train': 1.6882463693618774}
-03/05/2022 11:42:49 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/05/2022 11:42:53 - INFO - codeparrot_training - Step 39346: {'lr': 0.0004254735966500105, 'samples': 20145664, 'steps': 39346, 'loss/train': 1.6875114440917969}
-03/05/2022 11:42:56 - INFO - codeparrot_training - Step 39347: {'lr': 0.00042546981671713206, 'samples': 20146176, 'steps': 39347, 'loss/train': 1.6980832815170288}
-03/05/2022 11:42:58 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/05/2022 11:43:01 - INFO - codeparrot_training - Step 39348: {'lr': 0.0004254660367051896, 'samples': 20146688, 'steps': 39348, 'loss/train': 2.1431195735931396}
-03/05/2022 11:43:04 - INFO - codeparrot_training - Step 39349: {'lr': 0.0004254622566141849, 'samples': 20147200, 'steps': 39349, 'loss/train': 1.6874592304229736}
-03/05/2022 11:43:06 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/05/2022 11:43:09 - INFO - codeparrot_training - Step 39350: {'lr': 0.0004254584764441196, 'samples': 20147712, 'steps': 39350, 'loss/train': 1.8927046060562134}
-03/05/2022 11:43:13 - INFO - codeparrot_training - Step 39351: {'lr': 0.00042545469619499545, 'samples': 20148224, 'steps': 39351, 'loss/train': 2.6127960681915283}
-03/05/2022 11:43:14 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/05/2022 11:43:18 - INFO - codeparrot_training - Step 39352: {'lr': 0.00042545091586681404, 'samples': 20148736, 'steps': 39352, 'loss/train': 1.507682204246521}
-03/05/2022 11:43:21 - INFO - codeparrot_training - Step 39353: {'lr': 0.0004254471354595772, 'samples': 20149248, 'steps': 39353, 'loss/train': 2.062753915786743}
-03/05/2022 11:43:23 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/05/2022 11:43:26 - INFO - codeparrot_training - Step 39354: {'lr': 0.0004254433549732866, 'samples': 20149760, 'steps': 39354, 'loss/train': 2.1917827129364014}
-03/05/2022 11:43:30 - INFO - codeparrot_training - Step 39355: {'lr': 0.0004254395744079439, 'samples': 20150272, 'steps': 39355, 'loss/train': 0.8095563650131226}
-03/05/2022 11:43:31 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/05/2022 11:43:35 - INFO - codeparrot_training - Step 39356: {'lr': 0.0004254357937635509, 'samples': 20150784, 'steps': 39356, 'loss/train': 1.4243088960647583}
-03/05/2022 11:43:38 - INFO - codeparrot_training - Step 39357: {'lr': 0.00042543201304010914, 'samples': 20151296, 'steps': 39357, 'loss/train': 1.434818983078003}
-03/05/2022 11:43:40 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/05/2022 11:43:43 - INFO - codeparrot_training - Step 39358: {'lr': 0.0004254282322376205, 'samples': 20151808, 'steps': 39358, 'loss/train': 2.1282331943511963}
-03/05/2022 11:43:46 - INFO - codeparrot_training - Step 39359: {'lr': 0.0004254244513560866, 'samples': 20152320, 'steps': 39359, 'loss/train': 2.13814377784729}
-03/05/2022 11:43:48 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 11:43:52 - INFO - codeparrot_training - Step 39360: {'lr': 0.00042542067039550916, 'samples': 20152832, 'steps': 39360, 'loss/train': 2.2471859455108643}
-03/05/2022 11:43:55 - INFO - codeparrot_training - Step 39361: {'lr': 0.00042541688935588984, 'samples': 20153344, 'steps': 39361, 'loss/train': 2.309373617172241}
-03/05/2022 11:43:56 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/05/2022 11:44:00 - INFO - codeparrot_training - Step 39362: {'lr': 0.00042541310823723035, 'samples': 20153856, 'steps': 39362, 'loss/train': 0.11443085968494415}
-03/05/2022 11:44:03 - INFO - codeparrot_training - Step 39363: {'lr': 0.00042540932703953246, 'samples': 20154368, 'steps': 39363, 'loss/train': 1.9737426042556763}
-03/05/2022 11:44:04 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/05/2022 11:44:08 - INFO - codeparrot_training - Step 39364: {'lr': 0.00042540554576279776, 'samples': 20154880, 'steps': 39364, 'loss/train': 2.025761842727661}
-03/05/2022 11:44:12 - INFO - codeparrot_training - Step 39365: {'lr': 0.0004254017644070282, 'samples': 20155392, 'steps': 39365, 'loss/train': 1.2585152387619019}
-03/05/2022 11:44:13 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/05/2022 11:44:17 - INFO - codeparrot_training - Step 39366: {'lr': 0.0004253979829722251, 'samples': 20155904, 'steps': 39366, 'loss/train': 2.368009090423584}
-03/05/2022 11:44:20 - INFO - codeparrot_training - Step 39367: {'lr': 0.00042539420145839055, 'samples': 20156416, 'steps': 39367, 'loss/train': 1.731242060661316}
-03/05/2022 11:44:21 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/05/2022 11:44:25 - INFO - codeparrot_training - Step 39368: {'lr': 0.00042539041986552596, 'samples': 20156928, 'steps': 39368, 'loss/train': 0.7698107957839966}
-03/05/2022 11:44:28 - INFO - codeparrot_training - Step 39369: {'lr': 0.00042538663819363323, 'samples': 20157440, 'steps': 39369, 'loss/train': 1.2990303039550781}
-03/05/2022 11:44:29 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/05/2022 11:44:34 - INFO - codeparrot_training - Step 39370: {'lr': 0.000425382856442714, 'samples': 20157952, 'steps': 39370, 'loss/train': 1.7373076677322388}
-03/05/2022 11:44:37 - INFO - codeparrot_training - Step 39371: {'lr': 0.0004253790746127699, 'samples': 20158464, 'steps': 39371, 'loss/train': 1.1799730062484741}
-03/05/2022 11:44:37 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/05/2022 11:44:42 - INFO - codeparrot_training - Step 39372: {'lr': 0.0004253752927038027, 'samples': 20158976, 'steps': 39372, 'loss/train': 1.6194026470184326}
-03/05/2022 11:44:45 - INFO - codeparrot_training - Step 39373: {'lr': 0.0004253715107158141, 'samples': 20159488, 'steps': 39373, 'loss/train': 1.5046091079711914}
-03/05/2022 11:44:46 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/05/2022 11:44:51 - INFO - codeparrot_training - Step 39374: {'lr': 0.0004253677286488058, 'samples': 20160000, 'steps': 39374, 'loss/train': 2.1779208183288574}
-03/05/2022 11:44:54 - INFO - codeparrot_training - Step 39375: {'lr': 0.00042536394650277953, 'samples': 20160512, 'steps': 39375, 'loss/train': 1.377008080482483}
-03/05/2022 11:44:54 - INFO - codeparrot_training - Skipping example with length 807 (seq_length=1024)
-03/05/2022 11:44:59 - INFO - codeparrot_training - Step 39376: {'lr': 0.000425360164277737, 'samples': 20161024, 'steps': 39376, 'loss/train': 1.7654107809066772}
-03/05/2022 11:45:02 - INFO - codeparrot_training - Step 39377: {'lr': 0.00042535638197367984, 'samples': 20161536, 'steps': 39377, 'loss/train': 1.1904605627059937}
-03/05/2022 11:45:02 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/05/2022 11:45:07 - INFO - codeparrot_training - Step 39378: {'lr': 0.0004253525995906098, 'samples': 20162048, 'steps': 39378, 'loss/train': 1.7329192161560059}
-03/05/2022 11:45:10 - INFO - codeparrot_training - Step 39379: {'lr': 0.00042534881712852856, 'samples': 20162560, 'steps': 39379, 'loss/train': 2.0125482082366943}
-03/05/2022 11:45:11 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 11:45:16 - INFO - codeparrot_training - Step 39380: {'lr': 0.0004253450345874379, 'samples': 20163072, 'steps': 39380, 'loss/train': 0.6299535632133484}
-03/05/2022 11:45:19 - INFO - codeparrot_training - Step 39381: {'lr': 0.00042534125196733955, 'samples': 20163584, 'steps': 39381, 'loss/train': 1.694901466369629}
-03/05/2022 11:45:19 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/05/2022 11:45:24 - INFO - codeparrot_training - Step 39382: {'lr': 0.000425337469268235, 'samples': 20164096, 'steps': 39382, 'loss/train': 1.9881478548049927}
-03/05/2022 11:45:27 - INFO - codeparrot_training - Step 39383: {'lr': 0.00042533368649012615, 'samples': 20164608, 'steps': 39383, 'loss/train': 1.6406105756759644}
-03/05/2022 11:45:27 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 11:45:33 - INFO - codeparrot_training - Step 39384: {'lr': 0.0004253299036330146, 'samples': 20165120, 'steps': 39384, 'loss/train': 1.6849263906478882}
-03/05/2022 11:45:36 - INFO - codeparrot_training - Step 39385: {'lr': 0.00042532612069690214, 'samples': 20165632, 'steps': 39385, 'loss/train': 1.8215641975402832}
-03/05/2022 11:45:36 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/05/2022 11:45:41 - INFO - codeparrot_training - Step 39386: {'lr': 0.0004253223376817904, 'samples': 20166144, 'steps': 39386, 'loss/train': 1.7656104564666748}
-03/05/2022 11:45:44 - INFO - codeparrot_training - Step 39387: {'lr': 0.0004253185545876812, 'samples': 20166656, 'steps': 39387, 'loss/train': 2.0673701763153076}
-03/05/2022 11:45:44 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/05/2022 11:45:49 - INFO - codeparrot_training - Step 39388: {'lr': 0.0004253147714145761, 'samples': 20167168, 'steps': 39388, 'loss/train': 1.419786810874939}
-03/05/2022 11:45:53 - INFO - codeparrot_training - Step 39389: {'lr': 0.00042531098816247695, 'samples': 20167680, 'steps': 39389, 'loss/train': 1.9667061567306519}
-03/05/2022 11:45:53 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 11:45:58 - INFO - codeparrot_training - Step 39390: {'lr': 0.00042530720483138524, 'samples': 20168192, 'steps': 39390, 'loss/train': 1.2702560424804688}
-03/05/2022 11:46:01 - INFO - codeparrot_training - Step 39391: {'lr': 0.00042530342142130283, 'samples': 20168704, 'steps': 39391, 'loss/train': 1.3592029809951782}
-03/05/2022 11:46:01 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 11:46:06 - INFO - codeparrot_training - Step 39392: {'lr': 0.0004252996379322315, 'samples': 20169216, 'steps': 39392, 'loss/train': 2.2078804969787598}
-03/05/2022 11:46:09 - INFO - codeparrot_training - Step 39393: {'lr': 0.0004252958543641728, 'samples': 20169728, 'steps': 39393, 'loss/train': 1.2153912782669067}
-03/05/2022 11:46:10 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 11:46:15 - INFO - codeparrot_training - Step 39394: {'lr': 0.0004252920707171285, 'samples': 20170240, 'steps': 39394, 'loss/train': 1.4317548274993896}
-03/05/2022 11:46:18 - INFO - codeparrot_training - Step 39395: {'lr': 0.00042528828699110033, 'samples': 20170752, 'steps': 39395, 'loss/train': 1.7917567491531372}
-03/05/2022 11:46:18 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/05/2022 11:46:23 - INFO - codeparrot_training - Step 39396: {'lr': 0.0004252845031860899, 'samples': 20171264, 'steps': 39396, 'loss/train': 1.4303711652755737}
-03/05/2022 11:46:26 - INFO - codeparrot_training - Step 39397: {'lr': 0.000425280719302099, 'samples': 20171776, 'steps': 39397, 'loss/train': 1.2609963417053223}
-03/05/2022 11:46:26 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/05/2022 11:46:32 - INFO - codeparrot_training - Step 39398: {'lr': 0.0004252769353391294, 'samples': 20172288, 'steps': 39398, 'loss/train': 0.9504624605178833}
-03/05/2022 11:46:35 - INFO - codeparrot_training - Step 39399: {'lr': 0.00042527315129718257, 'samples': 20172800, 'steps': 39399, 'loss/train': 2.1288347244262695}
-03/05/2022 11:46:35 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/05/2022 11:46:40 - INFO - codeparrot_training - Step 39400: {'lr': 0.00042526936717626046, 'samples': 20173312, 'steps': 39400, 'loss/train': 1.4981889724731445}
-03/05/2022 11:46:43 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/05/2022 11:46:45 - INFO - codeparrot_training - Step 39401: {'lr': 0.00042526558297636464, 'samples': 20173824, 'steps': 39401, 'loss/train': 1.59617280960083}
-03/05/2022 11:46:49 - INFO - codeparrot_training - Step 39402: {'lr': 0.0004252617986974969, 'samples': 20174336, 'steps': 39402, 'loss/train': 1.5019707679748535}
-03/05/2022 11:46:51 - INFO - codeparrot_training - Skipping example with length 937 (seq_length=1024)
-03/05/2022 11:46:54 - INFO - codeparrot_training - Step 39403: {'lr': 0.00042525801433965883, 'samples': 20174848, 'steps': 39403, 'loss/train': 2.0933539867401123}
-03/05/2022 11:46:57 - INFO - codeparrot_training - Step 39404: {'lr': 0.00042525422990285225, 'samples': 20175360, 'steps': 39404, 'loss/train': 1.7473613023757935}
-03/05/2022 11:47:00 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 11:47:02 - INFO - codeparrot_training - Step 39405: {'lr': 0.0004252504453870788, 'samples': 20175872, 'steps': 39405, 'loss/train': 1.5347460508346558}
-03/05/2022 11:47:05 - INFO - codeparrot_training - Step 39406: {'lr': 0.0004252466607923402, 'samples': 20176384, 'steps': 39406, 'loss/train': 1.3275331258773804}
-03/05/2022 11:47:08 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/05/2022 11:47:11 - INFO - codeparrot_training - Step 39407: {'lr': 0.0004252428761186382, 'samples': 20176896, 'steps': 39407, 'loss/train': 1.8536207675933838}
-03/05/2022 11:47:14 - INFO - codeparrot_training - Step 39408: {'lr': 0.0004252390913659744, 'samples': 20177408, 'steps': 39408, 'loss/train': 0.9683761596679688}
-03/05/2022 11:47:16 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/05/2022 11:47:19 - INFO - codeparrot_training - Step 39409: {'lr': 0.0004252353065343506, 'samples': 20177920, 'steps': 39409, 'loss/train': 1.8689212799072266}
-03/05/2022 11:47:22 - INFO - codeparrot_training - Step 39410: {'lr': 0.0004252315216237684, 'samples': 20178432, 'steps': 39410, 'loss/train': 2.4282302856445312}
-03/05/2022 11:47:25 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/05/2022 11:47:27 - INFO - codeparrot_training - Step 39411: {'lr': 0.00042522773663422977, 'samples': 20178944, 'steps': 39411, 'loss/train': 2.317436456680298}
-03/05/2022 11:47:31 - INFO - codeparrot_training - Step 39412: {'lr': 0.000425223951565736, 'samples': 20179456, 'steps': 39412, 'loss/train': 1.8731043338775635}
-03/05/2022 11:47:33 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/05/2022 11:47:36 - INFO - codeparrot_training - Step 39413: {'lr': 0.0004252201664182892, 'samples': 20179968, 'steps': 39413, 'loss/train': 2.163546562194824}
-03/05/2022 11:47:39 - INFO - codeparrot_training - Step 39414: {'lr': 0.0004252163811918909, 'samples': 20180480, 'steps': 39414, 'loss/train': 2.5090956687927246}
-03/05/2022 11:47:42 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/05/2022 11:47:44 - INFO - codeparrot_training - Step 39415: {'lr': 0.00042521259588654264, 'samples': 20180992, 'steps': 39415, 'loss/train': 1.4590951204299927}
-03/05/2022 11:47:48 - INFO - codeparrot_training - Step 39416: {'lr': 0.00042520881050224637, 'samples': 20181504, 'steps': 39416, 'loss/train': 1.3714085817337036}
-03/05/2022 11:47:50 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/05/2022 11:47:53 - INFO - codeparrot_training - Step 39417: {'lr': 0.0004252050250390037, 'samples': 20182016, 'steps': 39417, 'loss/train': 1.9139841794967651}
-03/05/2022 11:47:56 - INFO - codeparrot_training - Step 39418: {'lr': 0.0004252012394968164, 'samples': 20182528, 'steps': 39418, 'loss/train': 1.552201747894287}
-03/05/2022 11:47:59 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/05/2022 11:48:01 - INFO - codeparrot_training - Step 39419: {'lr': 0.0004251974538756861, 'samples': 20183040, 'steps': 39419, 'loss/train': 2.104349374771118}
-03/05/2022 11:48:05 - INFO - codeparrot_training - Step 39420: {'lr': 0.00042519366817561453, 'samples': 20183552, 'steps': 39420, 'loss/train': 0.8928677439689636}
-03/05/2022 11:48:07 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/05/2022 11:48:10 - INFO - codeparrot_training - Step 39421: {'lr': 0.0004251898823966034, 'samples': 20184064, 'steps': 39421, 'loss/train': 1.7101434469223022}
-03/05/2022 11:48:13 - INFO - codeparrot_training - Step 39422: {'lr': 0.00042518609653865444, 'samples': 20184576, 'steps': 39422, 'loss/train': 1.8460896015167236}
-03/05/2022 11:48:15 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/05/2022 11:48:18 - INFO - codeparrot_training - Step 39423: {'lr': 0.00042518231060176926, 'samples': 20185088, 'steps': 39423, 'loss/train': 2.041424036026001}
-03/05/2022 11:48:22 - INFO - codeparrot_training - Step 39424: {'lr': 0.00042517852458594967, 'samples': 20185600, 'steps': 39424, 'loss/train': 1.5133206844329834}
-03/05/2022 11:48:25 - INFO - codeparrot_training - Step 39425: {'lr': 0.00042517473849119734, 'samples': 20186112, 'steps': 39425, 'loss/train': 2.581056594848633}
-03/05/2022 11:48:25 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/05/2022 11:48:30 - INFO - codeparrot_training - Step 39426: {'lr': 0.000425170952317514, 'samples': 20186624, 'steps': 39426, 'loss/train': 1.7612334489822388}
-03/05/2022 11:48:33 - INFO - codeparrot_training - Step 39427: {'lr': 0.0004251671660649013, 'samples': 20187136, 'steps': 39427, 'loss/train': 1.3517612218856812}
-03/05/2022 11:48:33 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 11:48:39 - INFO - codeparrot_training - Step 39428: {'lr': 0.000425163379733361, 'samples': 20187648, 'steps': 39428, 'loss/train': 2.1660208702087402}
-03/05/2022 11:48:42 - INFO - codeparrot_training - Step 39429: {'lr': 0.00042515959332289476, 'samples': 20188160, 'steps': 39429, 'loss/train': 4.261512279510498}
-03/05/2022 11:48:42 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 11:48:47 - INFO - codeparrot_training - Step 39430: {'lr': 0.0004251558068335043, 'samples': 20188672, 'steps': 39430, 'loss/train': 2.3418679237365723}
-03/05/2022 11:48:50 - INFO - codeparrot_training - Step 39431: {'lr': 0.00042515202026519136, 'samples': 20189184, 'steps': 39431, 'loss/train': 1.4312385320663452}
-03/05/2022 11:48:51 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/05/2022 11:48:56 - INFO - codeparrot_training - Step 39432: {'lr': 0.00042514823361795764, 'samples': 20189696, 'steps': 39432, 'loss/train': 2.2210516929626465}
-03/05/2022 11:48:59 - INFO - codeparrot_training - Step 39433: {'lr': 0.0004251444468918048, 'samples': 20190208, 'steps': 39433, 'loss/train': 2.286592960357666}
-03/05/2022 11:48:59 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/05/2022 11:49:04 - INFO - codeparrot_training - Step 39434: {'lr': 0.0004251406600867346, 'samples': 20190720, 'steps': 39434, 'loss/train': 0.8650291562080383}
-03/05/2022 11:49:07 - INFO - codeparrot_training - Step 39435: {'lr': 0.00042513687320274866, 'samples': 20191232, 'steps': 39435, 'loss/train': 2.496098279953003}
-03/05/2022 11:49:07 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/05/2022 11:49:12 - INFO - codeparrot_training - Step 39436: {'lr': 0.0004251330862398488, 'samples': 20191744, 'steps': 39436, 'loss/train': 2.2240986824035645}
-03/05/2022 11:49:16 - INFO - codeparrot_training - Step 39437: {'lr': 0.0004251292991980367, 'samples': 20192256, 'steps': 39437, 'loss/train': 1.410704255104065}
-03/05/2022 11:49:16 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 11:49:21 - INFO - codeparrot_training - Step 39438: {'lr': 0.000425125512077314, 'samples': 20192768, 'steps': 39438, 'loss/train': 2.734102964401245}
-03/05/2022 11:49:24 - INFO - codeparrot_training - Step 39439: {'lr': 0.00042512172487768244, 'samples': 20193280, 'steps': 39439, 'loss/train': 1.113688349723816}
-03/05/2022 11:49:24 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/05/2022 11:49:29 - INFO - codeparrot_training - Step 39440: {'lr': 0.00042511793759914375, 'samples': 20193792, 'steps': 39440, 'loss/train': 1.6318929195404053}
-03/05/2022 11:49:32 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/05/2022 11:49:34 - INFO - codeparrot_training - Step 39441: {'lr': 0.0004251141502416996, 'samples': 20194304, 'steps': 39441, 'loss/train': 1.8793796300888062}
-03/05/2022 11:49:38 - INFO - codeparrot_training - Step 39442: {'lr': 0.0004251103628053517, 'samples': 20194816, 'steps': 39442, 'loss/train': 1.4843800067901611}
-03/05/2022 11:49:40 - INFO - codeparrot_training - Skipping example with length 220 (seq_length=1024)
-03/05/2022 11:49:43 - INFO - codeparrot_training - Step 39443: {'lr': 0.0004251065752901018, 'samples': 20195328, 'steps': 39443, 'loss/train': 1.0333086252212524}
-03/05/2022 11:49:46 - INFO - codeparrot_training - Step 39444: {'lr': 0.0004251027876959516, 'samples': 20195840, 'steps': 39444, 'loss/train': 1.5853588581085205}
-03/05/2022 11:49:49 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/05/2022 11:49:51 - INFO - codeparrot_training - Step 39445: {'lr': 0.0004250990000229028, 'samples': 20196352, 'steps': 39445, 'loss/train': 1.4762051105499268}
-03/05/2022 11:49:54 - INFO - codeparrot_training - Step 39446: {'lr': 0.00042509521227095706, 'samples': 20196864, 'steps': 39446, 'loss/train': 1.1447510719299316}
-03/05/2022 11:49:57 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/05/2022 11:50:00 - INFO - codeparrot_training - Step 39447: {'lr': 0.0004250914244401161, 'samples': 20197376, 'steps': 39447, 'loss/train': 1.9971071481704712}
-03/05/2022 11:50:03 - INFO - codeparrot_training - Step 39448: {'lr': 0.00042508763653038167, 'samples': 20197888, 'steps': 39448, 'loss/train': 1.7649434804916382}
-03/05/2022 11:50:06 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/05/2022 11:50:08 - INFO - codeparrot_training - Step 39449: {'lr': 0.0004250838485417554, 'samples': 20198400, 'steps': 39449, 'loss/train': 1.7123974561691284}
-03/05/2022 11:50:11 - INFO - codeparrot_training - Step 39450: {'lr': 0.00042508006047423916, 'samples': 20198912, 'steps': 39450, 'loss/train': 2.8729848861694336}
-03/05/2022 11:50:14 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/05/2022 11:50:17 - INFO - codeparrot_training - Step 39451: {'lr': 0.0004250762723278344, 'samples': 20199424, 'steps': 39451, 'loss/train': 1.2746347188949585}
-03/05/2022 11:50:20 - INFO - codeparrot_training - Step 39452: {'lr': 0.00042507248410254307, 'samples': 20199936, 'steps': 39452, 'loss/train': 2.23582124710083}
-03/05/2022 11:50:22 - INFO - codeparrot_training - Skipping example with length 268 (seq_length=1024)
-03/05/2022 11:50:25 - INFO - codeparrot_training - Step 39453: {'lr': 0.0004250686957983668, 'samples': 20200448, 'steps': 39453, 'loss/train': 1.8270596265792847}
-03/05/2022 11:50:28 - INFO - codeparrot_training - Step 39454: {'lr': 0.00042506490741530724, 'samples': 20200960, 'steps': 39454, 'loss/train': 2.107948064804077}
-03/05/2022 11:50:31 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/05/2022 11:50:33 - INFO - codeparrot_training - Step 39455: {'lr': 0.00042506111895336616, 'samples': 20201472, 'steps': 39455, 'loss/train': 1.8282709121704102}
-03/05/2022 11:50:37 - INFO - codeparrot_training - Step 39456: {'lr': 0.00042505733041254526, 'samples': 20201984, 'steps': 39456, 'loss/train': 2.855403184890747}
-03/05/2022 11:50:39 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/05/2022 11:50:42 - INFO - codeparrot_training - Step 39457: {'lr': 0.00042505354179284615, 'samples': 20202496, 'steps': 39457, 'loss/train': 1.669367790222168}
-03/05/2022 11:50:46 - INFO - codeparrot_training - Step 39458: {'lr': 0.00042504975309427064, 'samples': 20203008, 'steps': 39458, 'loss/train': 2.22339129447937}
-03/05/2022 11:50:49 - INFO - codeparrot_training - Step 39459: {'lr': 0.0004250459643168204, 'samples': 20203520, 'steps': 39459, 'loss/train': 1.855828046798706}
-03/05/2022 11:50:50 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 11:50:54 - INFO - codeparrot_training - Step 39460: {'lr': 0.0004250421754604972, 'samples': 20204032, 'steps': 39460, 'loss/train': 1.3507159948349}
-03/05/2022 11:50:57 - INFO - codeparrot_training - Step 39461: {'lr': 0.0004250383865253027, 'samples': 20204544, 'steps': 39461, 'loss/train': 1.6053780317306519}
-03/05/2022 11:50:59 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/05/2022 11:51:03 - INFO - codeparrot_training - Step 39462: {'lr': 0.00042503459751123854, 'samples': 20205056, 'steps': 39462, 'loss/train': 2.222770929336548}
-03/05/2022 11:51:06 - INFO - codeparrot_training - Step 39463: {'lr': 0.00042503080841830654, 'samples': 20205568, 'steps': 39463, 'loss/train': 2.216947078704834}
-03/05/2022 11:51:07 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/05/2022 11:51:11 - INFO - codeparrot_training - Step 39464: {'lr': 0.0004250270192465083, 'samples': 20206080, 'steps': 39464, 'loss/train': 1.7197332382202148}
-03/05/2022 11:51:14 - INFO - codeparrot_training - Step 39465: {'lr': 0.0004250232299958456, 'samples': 20206592, 'steps': 39465, 'loss/train': 1.95314359664917}
-03/05/2022 11:51:16 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/05/2022 11:51:19 - INFO - codeparrot_training - Step 39466: {'lr': 0.0004250194406663203, 'samples': 20207104, 'steps': 39466, 'loss/train': 1.0625832080841064}
-03/05/2022 11:51:23 - INFO - codeparrot_training - Step 39467: {'lr': 0.00042501565125793375, 'samples': 20207616, 'steps': 39467, 'loss/train': 1.4129672050476074}
-03/05/2022 11:51:28 - INFO - codeparrot_training - Step 39468: {'lr': 0.0004250118617706879, 'samples': 20208128, 'steps': 39468, 'loss/train': 1.4999332427978516}
-03/05/2022 11:51:31 - INFO - codeparrot_training - Step 39469: {'lr': 0.0004250080722045844, 'samples': 20208640, 'steps': 39469, 'loss/train': 1.7277971506118774}
-03/05/2022 11:51:32 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/05/2022 11:51:37 - INFO - codeparrot_training - Step 39470: {'lr': 0.000425004282559625, 'samples': 20209152, 'steps': 39470, 'loss/train': 2.629648447036743}
-03/05/2022 11:51:40 - INFO - codeparrot_training - Step 39471: {'lr': 0.0004250004928358113, 'samples': 20209664, 'steps': 39471, 'loss/train': 0.9873744249343872}
-03/05/2022 11:51:43 - INFO - codeparrot_training - Step 39472: {'lr': 0.0004249967030331451, 'samples': 20210176, 'steps': 39472, 'loss/train': 1.040157675743103}
-03/05/2022 11:51:43 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/05/2022 11:51:48 - INFO - codeparrot_training - Step 39473: {'lr': 0.0004249929131516281, 'samples': 20210688, 'steps': 39473, 'loss/train': 2.040724039077759}
-03/05/2022 11:51:51 - INFO - codeparrot_training - Step 39474: {'lr': 0.00042498912319126206, 'samples': 20211200, 'steps': 39474, 'loss/train': 1.758864164352417}
-03/05/2022 11:51:52 - INFO - codeparrot_training - Skipping example with length 604 (seq_length=1024)
-03/05/2022 11:51:57 - INFO - codeparrot_training - Step 39475: {'lr': 0.00042498533315204855, 'samples': 20211712, 'steps': 39475, 'loss/train': 2.1586499214172363}
-03/05/2022 11:52:00 - INFO - codeparrot_training - Step 39476: {'lr': 0.0004249815430339894, 'samples': 20212224, 'steps': 39476, 'loss/train': 1.8622807264328003}
-03/05/2022 11:52:00 - INFO - codeparrot_training - Skipping example with length 69 (seq_length=1024)
-03/05/2022 11:52:05 - INFO - codeparrot_training - Step 39477: {'lr': 0.0004249777528370862, 'samples': 20212736, 'steps': 39477, 'loss/train': 1.7885797023773193}
-03/05/2022 11:52:08 - INFO - codeparrot_training - Step 39478: {'lr': 0.00042497396256134073, 'samples': 20213248, 'steps': 39478, 'loss/train': 1.6299128532409668}
-03/05/2022 11:52:09 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/05/2022 11:52:14 - INFO - codeparrot_training - Step 39479: {'lr': 0.0004249701722067547, 'samples': 20213760, 'steps': 39479, 'loss/train': 1.1913502216339111}
-03/05/2022 11:52:17 - INFO - codeparrot_training - Step 39480: {'lr': 0.0004249663817733298, 'samples': 20214272, 'steps': 39480, 'loss/train': 2.6169216632843018}
-03/05/2022 11:52:18 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/05/2022 11:52:22 - INFO - codeparrot_training - Step 39481: {'lr': 0.00042496259126106786, 'samples': 20214784, 'steps': 39481, 'loss/train': 2.060624599456787}
-03/05/2022 11:52:25 - INFO - codeparrot_training - Step 39482: {'lr': 0.0004249588006699704, 'samples': 20215296, 'steps': 39482, 'loss/train': 1.0312587022781372}
-03/05/2022 11:52:26 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/05/2022 11:52:30 - INFO - codeparrot_training - Step 39483: {'lr': 0.0004249550100000392, 'samples': 20215808, 'steps': 39483, 'loss/train': 2.4456348419189453}
-03/05/2022 11:52:34 - INFO - codeparrot_training - Step 39484: {'lr': 0.0004249512192512759, 'samples': 20216320, 'steps': 39484, 'loss/train': 2.171936273574829}
-03/05/2022 11:52:35 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/05/2022 11:52:39 - INFO - codeparrot_training - Step 39485: {'lr': 0.0004249474284236824, 'samples': 20216832, 'steps': 39485, 'loss/train': 2.120490789413452}
-03/05/2022 11:52:42 - INFO - codeparrot_training - Step 39486: {'lr': 0.0004249436375172602, 'samples': 20217344, 'steps': 39486, 'loss/train': 1.7743561267852783}
-03/05/2022 11:52:43 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/05/2022 11:52:47 - INFO - codeparrot_training - Step 39487: {'lr': 0.0004249398465320111, 'samples': 20217856, 'steps': 39487, 'loss/train': 1.7385261058807373}
-03/05/2022 11:52:50 - INFO - codeparrot_training - Step 39488: {'lr': 0.0004249360554679369, 'samples': 20218368, 'steps': 39488, 'loss/train': 1.34467613697052}
-03/05/2022 11:52:51 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/05/2022 11:52:56 - INFO - codeparrot_training - Step 39489: {'lr': 0.00042493226432503917, 'samples': 20218880, 'steps': 39489, 'loss/train': 1.5516873598098755}
-03/05/2022 11:52:59 - INFO - codeparrot_training - Step 39490: {'lr': 0.00042492847310331963, 'samples': 20219392, 'steps': 39490, 'loss/train': 1.0296729803085327}
-03/05/2022 11:53:00 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/05/2022 11:53:04 - INFO - codeparrot_training - Step 39491: {'lr': 0.00042492468180278, 'samples': 20219904, 'steps': 39491, 'loss/train': 1.2881265878677368}
-03/05/2022 11:53:07 - INFO - codeparrot_training - Step 39492: {'lr': 0.000424920890423422, 'samples': 20220416, 'steps': 39492, 'loss/train': 0.13477547466754913}
-03/05/2022 11:53:08 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 11:53:13 - INFO - codeparrot_training - Step 39493: {'lr': 0.0004249170989652474, 'samples': 20220928, 'steps': 39493, 'loss/train': 1.692677617073059}
-03/05/2022 11:53:16 - INFO - codeparrot_training - Step 39494: {'lr': 0.00042491330742825783, 'samples': 20221440, 'steps': 39494, 'loss/train': 1.644914984703064}
-03/05/2022 11:53:17 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/05/2022 11:53:21 - INFO - codeparrot_training - Step 39495: {'lr': 0.0004249095158124551, 'samples': 20221952, 'steps': 39495, 'loss/train': 1.5115821361541748}
-03/05/2022 11:53:24 - INFO - codeparrot_training - Step 39496: {'lr': 0.0004249057241178407, 'samples': 20222464, 'steps': 39496, 'loss/train': 1.1253011226654053}
-03/05/2022 11:53:25 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/05/2022 11:53:30 - INFO - codeparrot_training - Step 39497: {'lr': 0.00042490193234441656, 'samples': 20222976, 'steps': 39497, 'loss/train': 1.4406445026397705}
-03/05/2022 11:53:33 - INFO - codeparrot_training - Step 39498: {'lr': 0.00042489814049218434, 'samples': 20223488, 'steps': 39498, 'loss/train': 1.6908156871795654}
-03/05/2022 11:53:33 - INFO - codeparrot_training - Skipping example with length 910 (seq_length=1024)
-03/05/2022 11:53:38 - INFO - codeparrot_training - Step 39499: {'lr': 0.00042489434856114565, 'samples': 20224000, 'steps': 39499, 'loss/train': 1.869831919670105}
-03/05/2022 11:53:41 - INFO - codeparrot_training - Step 39500: {'lr': 0.00042489055655130226, 'samples': 20224512, 'steps': 39500, 'loss/train': 1.6268796920776367}
-03/05/2022 11:53:42 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 11:53:46 - INFO - codeparrot_training - Step 39501: {'lr': 0.00042488676446265596, 'samples': 20225024, 'steps': 39501, 'loss/train': 1.6019048690795898}
-03/05/2022 11:53:50 - INFO - codeparrot_training - Step 39502: {'lr': 0.00042488297229520834, 'samples': 20225536, 'steps': 39502, 'loss/train': 1.501145362854004}
-03/05/2022 11:53:50 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/05/2022 11:53:55 - INFO - codeparrot_training - Step 39503: {'lr': 0.00042487918004896117, 'samples': 20226048, 'steps': 39503, 'loss/train': 2.0185112953186035}
-03/05/2022 11:53:58 - INFO - codeparrot_training - Step 39504: {'lr': 0.0004248753877239161, 'samples': 20226560, 'steps': 39504, 'loss/train': 1.2451941967010498}
-03/05/2022 11:53:59 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/05/2022 11:54:04 - INFO - codeparrot_training - Step 39505: {'lr': 0.0004248715953200749, 'samples': 20227072, 'steps': 39505, 'loss/train': 1.0127921104431152}
-03/05/2022 11:54:07 - INFO - codeparrot_training - Step 39506: {'lr': 0.00042486780283743927, 'samples': 20227584, 'steps': 39506, 'loss/train': 1.2920727729797363}
-03/05/2022 11:54:07 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/05/2022 11:54:12 - INFO - codeparrot_training - Step 39507: {'lr': 0.00042486401027601084, 'samples': 20228096, 'steps': 39507, 'loss/train': 1.7099744081497192}
-03/05/2022 11:54:15 - INFO - codeparrot_training - Step 39508: {'lr': 0.0004248602176357915, 'samples': 20228608, 'steps': 39508, 'loss/train': 1.0340852737426758}
-03/05/2022 11:54:16 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 11:54:20 - INFO - codeparrot_training - Step 39509: {'lr': 0.0004248564249167828, 'samples': 20229120, 'steps': 39509, 'loss/train': 1.9557068347930908}
-03/05/2022 11:54:24 - INFO - codeparrot_training - Step 39510: {'lr': 0.00042485263211898647, 'samples': 20229632, 'steps': 39510, 'loss/train': 1.3115252256393433}
-03/05/2022 11:54:24 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/05/2022 11:54:29 - INFO - codeparrot_training - Step 39511: {'lr': 0.00042484883924240427, 'samples': 20230144, 'steps': 39511, 'loss/train': 1.6810437440872192}
-03/05/2022 11:54:32 - INFO - codeparrot_training - Step 39512: {'lr': 0.0004248450462870378, 'samples': 20230656, 'steps': 39512, 'loss/train': 1.4425575733184814}
-03/05/2022 11:54:32 - INFO - codeparrot_training - Skipping example with length 644 (seq_length=1024)
-03/05/2022 11:54:37 - INFO - codeparrot_training - Step 39513: {'lr': 0.0004248412532528889, 'samples': 20231168, 'steps': 39513, 'loss/train': 1.3789643049240112}
-03/05/2022 11:54:40 - INFO - codeparrot_training - Step 39514: {'lr': 0.00042483746013995924, 'samples': 20231680, 'steps': 39514, 'loss/train': 1.0510631799697876}
-03/05/2022 11:54:41 - INFO - codeparrot_training - Skipping example with length 756 (seq_length=1024)
-03/05/2022 11:54:46 - INFO - codeparrot_training - Step 39515: {'lr': 0.00042483366694825054, 'samples': 20232192, 'steps': 39515, 'loss/train': 1.113072395324707}
-03/05/2022 11:54:49 - INFO - codeparrot_training - Step 39516: {'lr': 0.0004248298736777645, 'samples': 20232704, 'steps': 39516, 'loss/train': 2.0469138622283936}
-03/05/2022 11:54:49 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/05/2022 11:54:54 - INFO - codeparrot_training - Step 39517: {'lr': 0.00042482608032850275, 'samples': 20233216, 'steps': 39517, 'loss/train': 1.9167791604995728}
-03/05/2022 11:54:57 - INFO - codeparrot_training - Step 39518: {'lr': 0.0004248222869004671, 'samples': 20233728, 'steps': 39518, 'loss/train': 1.6522334814071655}
-03/05/2022 11:54:58 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/05/2022 11:55:03 - INFO - codeparrot_training - Step 39519: {'lr': 0.0004248184933936592, 'samples': 20234240, 'steps': 39519, 'loss/train': 1.650833010673523}
-03/05/2022 11:55:06 - INFO - codeparrot_training - Step 39520: {'lr': 0.0004248146998080808, 'samples': 20234752, 'steps': 39520, 'loss/train': 1.7325822114944458}
-03/05/2022 11:55:06 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/05/2022 11:55:11 - INFO - codeparrot_training - Step 39521: {'lr': 0.00042481090614373364, 'samples': 20235264, 'steps': 39521, 'loss/train': 1.1291372776031494}
-03/05/2022 11:55:14 - INFO - codeparrot_training - Step 39522: {'lr': 0.00042480711240061933, 'samples': 20235776, 'steps': 39522, 'loss/train': 1.198961615562439}
-03/05/2022 11:55:15 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/05/2022 11:55:19 - INFO - codeparrot_training - Step 39523: {'lr': 0.0004248033185787397, 'samples': 20236288, 'steps': 39523, 'loss/train': 1.5488234758377075}
-03/05/2022 11:55:23 - INFO - codeparrot_training - Step 39524: {'lr': 0.00042479952467809623, 'samples': 20236800, 'steps': 39524, 'loss/train': 1.844227910041809}
-03/05/2022 11:55:23 - INFO - codeparrot_training - Skipping example with length 733 (seq_length=1024)
-03/05/2022 11:55:28 - INFO - codeparrot_training - Step 39525: {'lr': 0.00042479573069869095, 'samples': 20237312, 'steps': 39525, 'loss/train': 1.8904612064361572}
-03/05/2022 11:55:31 - INFO - codeparrot_training - Step 39526: {'lr': 0.0004247919366405253, 'samples': 20237824, 'steps': 39526, 'loss/train': 2.221334457397461}
-03/05/2022 11:55:31 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/05/2022 11:55:36 - INFO - codeparrot_training - Step 39527: {'lr': 0.0004247881425036012, 'samples': 20238336, 'steps': 39527, 'loss/train': 1.5650317668914795}
-03/05/2022 11:55:40 - INFO - codeparrot_training - Step 39528: {'lr': 0.00042478434828792025, 'samples': 20238848, 'steps': 39528, 'loss/train': 1.0806422233581543}
-03/05/2022 11:55:40 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/05/2022 11:55:45 - INFO - codeparrot_training - Step 39529: {'lr': 0.00042478055399348415, 'samples': 20239360, 'steps': 39529, 'loss/train': 1.3216396570205688}
-03/05/2022 11:55:48 - INFO - codeparrot_training - Step 39530: {'lr': 0.0004247767596202946, 'samples': 20239872, 'steps': 39530, 'loss/train': 1.5908998250961304}
-03/05/2022 11:55:48 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/05/2022 11:55:53 - INFO - codeparrot_training - Step 39531: {'lr': 0.00042477296516835335, 'samples': 20240384, 'steps': 39531, 'loss/train': 1.744179368019104}
-03/05/2022 11:55:57 - INFO - codeparrot_training - Step 39532: {'lr': 0.00042476917063766207, 'samples': 20240896, 'steps': 39532, 'loss/train': 1.5387765169143677}
-03/05/2022 11:55:57 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/05/2022 11:56:02 - INFO - codeparrot_training - Step 39533: {'lr': 0.0004247653760282225, 'samples': 20241408, 'steps': 39533, 'loss/train': 1.7099334001541138}
-03/05/2022 11:56:05 - INFO - codeparrot_training - Step 39534: {'lr': 0.0004247615813400364, 'samples': 20241920, 'steps': 39534, 'loss/train': 1.4926204681396484}
-03/05/2022 11:56:05 - INFO - codeparrot_training - Skipping example with length 889 (seq_length=1024)
-03/05/2022 11:56:10 - INFO - codeparrot_training - Step 39535: {'lr': 0.0004247577865731055, 'samples': 20242432, 'steps': 39535, 'loss/train': 1.567651629447937}
-03/05/2022 11:56:13 - INFO - codeparrot_training - Step 39536: {'lr': 0.00042475399172743134, 'samples': 20242944, 'steps': 39536, 'loss/train': 1.1760225296020508}
-03/05/2022 11:56:14 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 11:56:19 - INFO - codeparrot_training - Step 39537: {'lr': 0.0004247501968030157, 'samples': 20243456, 'steps': 39537, 'loss/train': 1.4166630506515503}
-03/05/2022 11:56:22 - INFO - codeparrot_training - Step 39538: {'lr': 0.00042474640179986035, 'samples': 20243968, 'steps': 39538, 'loss/train': 1.446031928062439}
-03/05/2022 11:56:22 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/05/2022 11:56:27 - INFO - codeparrot_training - Step 39539: {'lr': 0.00042474260671796697, 'samples': 20244480, 'steps': 39539, 'loss/train': 1.656272292137146}
-03/05/2022 11:56:30 - INFO - codeparrot_training - Step 39540: {'lr': 0.0004247388115573373, 'samples': 20244992, 'steps': 39540, 'loss/train': 2.3414535522460938}
-03/05/2022 11:56:31 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/05/2022 11:56:36 - INFO - codeparrot_training - Step 39541: {'lr': 0.00042473501631797294, 'samples': 20245504, 'steps': 39541, 'loss/train': 4.964019775390625}
-03/05/2022 11:56:39 - INFO - codeparrot_training - Step 39542: {'lr': 0.0004247312209998758, 'samples': 20246016, 'steps': 39542, 'loss/train': 1.6206120252609253}
-03/05/2022 11:56:39 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 11:56:44 - INFO - codeparrot_training - Step 39543: {'lr': 0.00042472742560304734, 'samples': 20246528, 'steps': 39543, 'loss/train': 1.6710517406463623}
-03/05/2022 11:56:47 - INFO - codeparrot_training - Step 39544: {'lr': 0.00042472363012748947, 'samples': 20247040, 'steps': 39544, 'loss/train': 1.3930811882019043}
-03/05/2022 11:56:48 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/05/2022 11:56:53 - INFO - codeparrot_training - Step 39545: {'lr': 0.00042471983457320384, 'samples': 20247552, 'steps': 39545, 'loss/train': 0.7628999352455139}
-03/05/2022 11:56:56 - INFO - codeparrot_training - Step 39546: {'lr': 0.00042471603894019206, 'samples': 20248064, 'steps': 39546, 'loss/train': 1.9054125547409058}
-03/05/2022 11:56:57 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/05/2022 11:57:01 - INFO - codeparrot_training - Step 39547: {'lr': 0.00042471224322845603, 'samples': 20248576, 'steps': 39547, 'loss/train': 1.6174657344818115}
-03/05/2022 11:57:04 - INFO - codeparrot_training - Step 39548: {'lr': 0.00042470844743799734, 'samples': 20249088, 'steps': 39548, 'loss/train': 1.5804929733276367}
-03/05/2022 11:57:05 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/05/2022 11:57:10 - INFO - codeparrot_training - Step 39549: {'lr': 0.00042470465156881765, 'samples': 20249600, 'steps': 39549, 'loss/train': 1.9246913194656372}
-03/05/2022 11:57:13 - INFO - codeparrot_training - Step 39550: {'lr': 0.00042470085562091887, 'samples': 20250112, 'steps': 39550, 'loss/train': 1.4813987016677856}
-03/05/2022 11:57:13 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/05/2022 11:57:18 - INFO - codeparrot_training - Step 39551: {'lr': 0.0004246970595943025, 'samples': 20250624, 'steps': 39551, 'loss/train': 1.9544329643249512}
-03/05/2022 11:57:21 - INFO - codeparrot_training - Step 39552: {'lr': 0.0004246932634889703, 'samples': 20251136, 'steps': 39552, 'loss/train': 2.1707763671875}
-03/05/2022 11:57:22 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/05/2022 11:57:26 - INFO - codeparrot_training - Step 39553: {'lr': 0.00042468946730492404, 'samples': 20251648, 'steps': 39553, 'loss/train': 2.0041427612304688}
-03/05/2022 11:57:30 - INFO - codeparrot_training - Step 39554: {'lr': 0.00042468567104216536, 'samples': 20252160, 'steps': 39554, 'loss/train': 2.112600088119507}
-03/05/2022 11:57:30 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 11:57:35 - INFO - codeparrot_training - Step 39555: {'lr': 0.0004246818747006961, 'samples': 20252672, 'steps': 39555, 'loss/train': 1.4566302299499512}
-03/05/2022 11:57:38 - INFO - codeparrot_training - Step 39556: {'lr': 0.00042467807828051787, 'samples': 20253184, 'steps': 39556, 'loss/train': 1.1891714334487915}
-03/05/2022 11:57:38 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/05/2022 11:57:43 - INFO - codeparrot_training - Step 39557: {'lr': 0.0004246742817816323, 'samples': 20253696, 'steps': 39557, 'loss/train': 0.3847522735595703}
-03/05/2022 11:57:47 - INFO - codeparrot_training - Step 39558: {'lr': 0.00042467048520404126, 'samples': 20254208, 'steps': 39558, 'loss/train': 2.243648052215576}
-03/05/2022 11:57:52 - INFO - codeparrot_training - Step 39559: {'lr': 0.00042466668854774636, 'samples': 20254720, 'steps': 39559, 'loss/train': 1.6022562980651855}
-03/05/2022 11:57:55 - INFO - codeparrot_training - Step 39560: {'lr': 0.00042466289181274943, 'samples': 20255232, 'steps': 39560, 'loss/train': 1.8534235954284668}
-03/05/2022 11:57:55 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 11:58:00 - INFO - codeparrot_training - Step 39561: {'lr': 0.00042465909499905206, 'samples': 20255744, 'steps': 39561, 'loss/train': 1.7306753396987915}
-03/05/2022 11:58:03 - INFO - codeparrot_training - Step 39562: {'lr': 0.0004246552981066559, 'samples': 20256256, 'steps': 39562, 'loss/train': 1.179840326309204}
-03/05/2022 11:58:03 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/05/2022 11:58:09 - INFO - codeparrot_training - Step 39563: {'lr': 0.0004246515011355629, 'samples': 20256768, 'steps': 39563, 'loss/train': 2.085270881652832}
-03/05/2022 11:58:12 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/05/2022 11:58:14 - INFO - codeparrot_training - Step 39564: {'lr': 0.0004246477040857746, 'samples': 20257280, 'steps': 39564, 'loss/train': 1.5155251026153564}
-03/05/2022 11:58:17 - INFO - codeparrot_training - Step 39565: {'lr': 0.0004246439069572926, 'samples': 20257792, 'steps': 39565, 'loss/train': 1.6817643642425537}
-03/05/2022 11:58:20 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/05/2022 11:58:22 - INFO - codeparrot_training - Step 39566: {'lr': 0.00042464010975011893, 'samples': 20258304, 'steps': 39566, 'loss/train': 1.6983777284622192}
-03/05/2022 11:58:26 - INFO - codeparrot_training - Step 39567: {'lr': 0.00042463631246425504, 'samples': 20258816, 'steps': 39567, 'loss/train': 1.594313383102417}
-03/05/2022 11:58:28 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/05/2022 11:58:31 - INFO - codeparrot_training - Step 39568: {'lr': 0.0004246325150997027, 'samples': 20259328, 'steps': 39568, 'loss/train': 1.844613790512085}
-03/05/2022 11:58:34 - INFO - codeparrot_training - Step 39569: {'lr': 0.0004246287176564637, 'samples': 20259840, 'steps': 39569, 'loss/train': 3.7851123809814453}
-03/05/2022 11:58:37 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/05/2022 11:58:39 - INFO - codeparrot_training - Step 39570: {'lr': 0.0004246249201345397, 'samples': 20260352, 'steps': 39570, 'loss/train': 1.89006769657135}
-03/05/2022 11:58:43 - INFO - codeparrot_training - Step 39571: {'lr': 0.0004246211225339323, 'samples': 20260864, 'steps': 39571, 'loss/train': 2.365574598312378}
-03/05/2022 11:58:45 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/05/2022 11:58:48 - INFO - codeparrot_training - Step 39572: {'lr': 0.0004246173248546434, 'samples': 20261376, 'steps': 39572, 'loss/train': 1.5291794538497925}
-03/05/2022 11:58:51 - INFO - codeparrot_training - Step 39573: {'lr': 0.0004246135270966747, 'samples': 20261888, 'steps': 39573, 'loss/train': 1.8303419351577759}
-03/05/2022 11:58:54 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/05/2022 11:58:56 - INFO - codeparrot_training - Step 39574: {'lr': 0.00042460972926002774, 'samples': 20262400, 'steps': 39574, 'loss/train': 1.794812560081482}
-03/05/2022 11:59:00 - INFO - codeparrot_training - Step 39575: {'lr': 0.00042460593134470426, 'samples': 20262912, 'steps': 39575, 'loss/train': 1.5292181968688965}
-03/05/2022 11:59:02 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/05/2022 11:59:05 - INFO - codeparrot_training - Step 39576: {'lr': 0.0004246021333507062, 'samples': 20263424, 'steps': 39576, 'loss/train': 2.067171812057495}
-03/05/2022 11:59:08 - INFO - codeparrot_training - Step 39577: {'lr': 0.00042459833527803503, 'samples': 20263936, 'steps': 39577, 'loss/train': 1.3167665004730225}
-03/05/2022 11:59:11 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/05/2022 11:59:13 - INFO - codeparrot_training - Step 39578: {'lr': 0.00042459453712669255, 'samples': 20264448, 'steps': 39578, 'loss/train': 1.8588565587997437}
-03/05/2022 11:59:16 - INFO - codeparrot_training - Step 39579: {'lr': 0.0004245907388966804, 'samples': 20264960, 'steps': 39579, 'loss/train': 1.0150758028030396}
-03/05/2022 11:59:19 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 11:59:22 - INFO - codeparrot_training - Step 39580: {'lr': 0.0004245869405880005, 'samples': 20265472, 'steps': 39580, 'loss/train': 1.5160540342330933}
-03/05/2022 11:59:25 - INFO - codeparrot_training - Step 39581: {'lr': 0.0004245831422006543, 'samples': 20265984, 'steps': 39581, 'loss/train': 1.8087637424468994}
-03/05/2022 11:59:27 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/05/2022 11:59:30 - INFO - codeparrot_training - Step 39582: {'lr': 0.0004245793437346437, 'samples': 20266496, 'steps': 39582, 'loss/train': 1.4180867671966553}
-03/05/2022 11:59:33 - INFO - codeparrot_training - Step 39583: {'lr': 0.0004245755451899703, 'samples': 20267008, 'steps': 39583, 'loss/train': 1.6178076267242432}
-03/05/2022 11:59:35 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 11:59:38 - INFO - codeparrot_training - Step 39584: {'lr': 0.0004245717465666359, 'samples': 20267520, 'steps': 39584, 'loss/train': 1.2121411561965942}
-03/05/2022 11:59:42 - INFO - codeparrot_training - Step 39585: {'lr': 0.0004245679478646421, 'samples': 20268032, 'steps': 39585, 'loss/train': 2.4329044818878174}
-03/05/2022 11:59:44 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/05/2022 11:59:47 - INFO - codeparrot_training - Step 39586: {'lr': 0.00042456414908399075, 'samples': 20268544, 'steps': 39586, 'loss/train': 3.139448404312134}
-03/05/2022 11:59:50 - INFO - codeparrot_training - Step 39587: {'lr': 0.00042456035022468344, 'samples': 20269056, 'steps': 39587, 'loss/train': 1.6371091604232788}
-03/05/2022 11:59:52 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/05/2022 11:59:55 - INFO - codeparrot_training - Step 39588: {'lr': 0.0004245565512867219, 'samples': 20269568, 'steps': 39588, 'loss/train': 0.5925611853599548}
-03/05/2022 11:59:58 - INFO - codeparrot_training - Step 39589: {'lr': 0.000424552752270108, 'samples': 20270080, 'steps': 39589, 'loss/train': 1.1517635583877563}
-03/05/2022 12:00:00 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/05/2022 12:00:04 - INFO - codeparrot_training - Step 39590: {'lr': 0.0004245489531748432, 'samples': 20270592, 'steps': 39590, 'loss/train': 1.3761332035064697}
-03/05/2022 12:00:07 - INFO - codeparrot_training - Step 39591: {'lr': 0.00042454515400092944, 'samples': 20271104, 'steps': 39591, 'loss/train': 3.053755521774292}
-03/05/2022 12:00:09 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/05/2022 12:00:12 - INFO - codeparrot_training - Step 39592: {'lr': 0.00042454135474836817, 'samples': 20271616, 'steps': 39592, 'loss/train': 0.9860255122184753}
-03/05/2022 12:00:15 - INFO - codeparrot_training - Step 39593: {'lr': 0.0004245375554171613, 'samples': 20272128, 'steps': 39593, 'loss/train': 1.7060869932174683}
-03/05/2022 12:00:17 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 12:00:21 - INFO - codeparrot_training - Step 39594: {'lr': 0.00042453375600731057, 'samples': 20272640, 'steps': 39594, 'loss/train': 1.8741410970687866}
-03/05/2022 12:00:24 - INFO - codeparrot_training - Step 39595: {'lr': 0.00042452995651881764, 'samples': 20273152, 'steps': 39595, 'loss/train': 1.7867883443832397}
-03/05/2022 12:00:26 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 12:00:29 - INFO - codeparrot_training - Step 39596: {'lr': 0.0004245261569516842, 'samples': 20273664, 'steps': 39596, 'loss/train': 1.765379548072815}
-03/05/2022 12:00:32 - INFO - codeparrot_training - Step 39597: {'lr': 0.00042452235730591195, 'samples': 20274176, 'steps': 39597, 'loss/train': 2.8699889183044434}
-03/05/2022 12:00:34 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/05/2022 12:00:38 - INFO - codeparrot_training - Step 39598: {'lr': 0.00042451855758150254, 'samples': 20274688, 'steps': 39598, 'loss/train': 1.326201319694519}
-03/05/2022 12:00:41 - INFO - codeparrot_training - Step 39599: {'lr': 0.00042451475777845784, 'samples': 20275200, 'steps': 39599, 'loss/train': 2.5599732398986816}
-03/05/2022 12:00:45 - INFO - codeparrot_training - Step 39600: {'lr': 0.00042451095789677943, 'samples': 20275712, 'steps': 39600, 'loss/train': 0.4435458779335022}
-03/05/2022 12:00:45 - INFO - codeparrot_training - Skipping example with length 440 (seq_length=1024)
-03/05/2022 12:00:50 - INFO - codeparrot_training - Step 39601: {'lr': 0.0004245071579364691, 'samples': 20276224, 'steps': 39601, 'loss/train': 1.8608115911483765}
-03/05/2022 12:00:53 - INFO - codeparrot_training - Step 39602: {'lr': 0.0004245033578975286, 'samples': 20276736, 'steps': 39602, 'loss/train': 1.898787498474121}
-03/05/2022 12:00:54 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/05/2022 12:00:58 - INFO - codeparrot_training - Step 39603: {'lr': 0.00042449955777995954, 'samples': 20277248, 'steps': 39603, 'loss/train': 1.3378511667251587}
-03/05/2022 12:01:01 - INFO - codeparrot_training - Step 39604: {'lr': 0.0004244957575837636, 'samples': 20277760, 'steps': 39604, 'loss/train': 1.4231407642364502}
-03/05/2022 12:01:02 - INFO - codeparrot_training - Skipping example with length 121 (seq_length=1024)
-03/05/2022 12:01:07 - INFO - codeparrot_training - Step 39605: {'lr': 0.00042449195730894266, 'samples': 20278272, 'steps': 39605, 'loss/train': 1.2702012062072754}
-03/05/2022 12:01:10 - INFO - codeparrot_training - Step 39606: {'lr': 0.00042448815695549823, 'samples': 20278784, 'steps': 39606, 'loss/train': 1.491012692451477}
-03/05/2022 12:01:11 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/05/2022 12:01:15 - INFO - codeparrot_training - Step 39607: {'lr': 0.00042448435652343223, 'samples': 20279296, 'steps': 39607, 'loss/train': 0.8863868713378906}
-03/05/2022 12:01:18 - INFO - codeparrot_training - Step 39608: {'lr': 0.0004244805560127463, 'samples': 20279808, 'steps': 39608, 'loss/train': 1.8586546182632446}
-03/05/2022 12:01:19 - INFO - codeparrot_training - Skipping example with length 740 (seq_length=1024)
-03/05/2022 12:01:23 - INFO - codeparrot_training - Step 39609: {'lr': 0.00042447675542344203, 'samples': 20280320, 'steps': 39609, 'loss/train': 2.4568965435028076}
-03/05/2022 12:01:27 - INFO - codeparrot_training - Step 39610: {'lr': 0.0004244729547555213, 'samples': 20280832, 'steps': 39610, 'loss/train': 1.5476725101470947}
-03/05/2022 12:01:27 - INFO - codeparrot_training - Skipping example with length 450 (seq_length=1024)
-03/05/2022 12:01:32 - INFO - codeparrot_training - Step 39611: {'lr': 0.00042446915400898565, 'samples': 20281344, 'steps': 39611, 'loss/train': 1.7416270971298218}
-03/05/2022 12:01:35 - INFO - codeparrot_training - Step 39612: {'lr': 0.00042446535318383695, 'samples': 20281856, 'steps': 39612, 'loss/train': 1.463618516921997}
-03/05/2022 12:01:35 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/05/2022 12:01:40 - INFO - codeparrot_training - Step 39613: {'lr': 0.00042446155228007687, 'samples': 20282368, 'steps': 39613, 'loss/train': 1.0853447914123535}
-03/05/2022 12:01:43 - INFO - codeparrot_training - Step 39614: {'lr': 0.0004244577512977071, 'samples': 20282880, 'steps': 39614, 'loss/train': 2.3059446811676025}
-03/05/2022 12:01:44 - INFO - codeparrot_training - Skipping example with length 680 (seq_length=1024)
-03/05/2022 12:01:49 - INFO - codeparrot_training - Step 39615: {'lr': 0.00042445395023672935, 'samples': 20283392, 'steps': 39615, 'loss/train': 1.810790777206421}
-03/05/2022 12:01:52 - INFO - codeparrot_training - Step 39616: {'lr': 0.0004244501490971454, 'samples': 20283904, 'steps': 39616, 'loss/train': 1.2429416179656982}
-03/05/2022 12:01:53 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/05/2022 12:01:57 - INFO - codeparrot_training - Step 39617: {'lr': 0.0004244463478789568, 'samples': 20284416, 'steps': 39617, 'loss/train': 0.4531399607658386}
-03/05/2022 12:02:00 - INFO - codeparrot_training - Step 39618: {'lr': 0.0004244425465821654, 'samples': 20284928, 'steps': 39618, 'loss/train': 1.4985302686691284}
-03/05/2022 12:02:01 - INFO - codeparrot_training - Skipping example with length 255 (seq_length=1024)
-03/05/2022 12:02:06 - INFO - codeparrot_training - Step 39619: {'lr': 0.0004244387452067729, 'samples': 20285440, 'steps': 39619, 'loss/train': 2.573594570159912}
-03/05/2022 12:02:09 - INFO - codeparrot_training - Step 39620: {'lr': 0.000424434943752781, 'samples': 20285952, 'steps': 39620, 'loss/train': 1.0906153917312622}
-03/05/2022 12:02:10 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 12:02:14 - INFO - codeparrot_training - Step 39621: {'lr': 0.0004244311422201914, 'samples': 20286464, 'steps': 39621, 'loss/train': 1.4890276193618774}
-03/05/2022 12:02:17 - INFO - codeparrot_training - Step 39622: {'lr': 0.0004244273406090058, 'samples': 20286976, 'steps': 39622, 'loss/train': 1.946203351020813}
-03/05/2022 12:02:18 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/05/2022 12:02:22 - INFO - codeparrot_training - Step 39623: {'lr': 0.000424423538919226, 'samples': 20287488, 'steps': 39623, 'loss/train': 0.9325276017189026}
-03/05/2022 12:02:26 - INFO - codeparrot_training - Step 39624: {'lr': 0.0004244197371508536, 'samples': 20288000, 'steps': 39624, 'loss/train': 1.359408974647522}
-03/05/2022 12:02:26 - INFO - codeparrot_training - Skipping example with length 462 (seq_length=1024)
-03/05/2022 12:02:31 - INFO - codeparrot_training - Step 39625: {'lr': 0.00042441593530389025, 'samples': 20288512, 'steps': 39625, 'loss/train': 1.4853960275650024}
-03/05/2022 12:02:34 - INFO - codeparrot_training - Step 39626: {'lr': 0.0004244121333783379, 'samples': 20289024, 'steps': 39626, 'loss/train': 1.8192424774169922}
-03/05/2022 12:02:35 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 12:02:39 - INFO - codeparrot_training - Step 39627: {'lr': 0.0004244083313741981, 'samples': 20289536, 'steps': 39627, 'loss/train': 1.5496728420257568}
-03/05/2022 12:02:43 - INFO - codeparrot_training - Step 39628: {'lr': 0.0004244045292914726, 'samples': 20290048, 'steps': 39628, 'loss/train': 1.4731743335723877}
-03/05/2022 12:02:43 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 12:02:48 - INFO - codeparrot_training - Step 39629: {'lr': 0.00042440072713016317, 'samples': 20290560, 'steps': 39629, 'loss/train': 2.234647750854492}
-03/05/2022 12:02:51 - INFO - codeparrot_training - Step 39630: {'lr': 0.00042439692489027136, 'samples': 20291072, 'steps': 39630, 'loss/train': 1.787954330444336}
-03/05/2022 12:02:51 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/05/2022 12:02:56 - INFO - codeparrot_training - Step 39631: {'lr': 0.000424393122571799, 'samples': 20291584, 'steps': 39631, 'loss/train': 1.6617506742477417}
-03/05/2022 12:02:59 - INFO - codeparrot_training - Step 39632: {'lr': 0.00042438932017474783, 'samples': 20292096, 'steps': 39632, 'loss/train': 1.6118909120559692}
-03/05/2022 12:03:00 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/05/2022 12:03:05 - INFO - codeparrot_training - Step 39633: {'lr': 0.0004243855176991195, 'samples': 20292608, 'steps': 39633, 'loss/train': 1.5251413583755493}
-03/05/2022 12:03:08 - INFO - codeparrot_training - Step 39634: {'lr': 0.0004243817151449158, 'samples': 20293120, 'steps': 39634, 'loss/train': 1.9425326585769653}
-03/05/2022 12:03:09 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/05/2022 12:03:13 - INFO - codeparrot_training - Step 39635: {'lr': 0.0004243779125121383, 'samples': 20293632, 'steps': 39635, 'loss/train': 2.352893352508545}
-03/05/2022 12:03:16 - INFO - codeparrot_training - Step 39636: {'lr': 0.00042437410980078894, 'samples': 20294144, 'steps': 39636, 'loss/train': 1.277471899986267}
-03/05/2022 12:03:17 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/05/2022 12:03:22 - INFO - codeparrot_training - Step 39637: {'lr': 0.0004243703070108692, 'samples': 20294656, 'steps': 39637, 'loss/train': 2.8633956909179688}
-03/05/2022 12:03:25 - INFO - codeparrot_training - Step 39638: {'lr': 0.00042436650414238086, 'samples': 20295168, 'steps': 39638, 'loss/train': 1.0687415599822998}
-03/05/2022 12:03:25 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/05/2022 12:03:30 - INFO - codeparrot_training - Step 39639: {'lr': 0.0004243627011953257, 'samples': 20295680, 'steps': 39639, 'loss/train': 1.515476942062378}
-03/05/2022 12:03:33 - INFO - codeparrot_training - Step 39640: {'lr': 0.0004243588981697054, 'samples': 20296192, 'steps': 39640, 'loss/train': 6.564723968505859}
-03/05/2022 12:03:35 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 12:03:39 - INFO - codeparrot_training - Step 39641: {'lr': 0.0004243550950655217, 'samples': 20296704, 'steps': 39641, 'loss/train': 1.58370840549469}
-03/05/2022 12:03:42 - INFO - codeparrot_training - Step 39642: {'lr': 0.00042435129188277625, 'samples': 20297216, 'steps': 39642, 'loss/train': 1.7251659631729126}
-03/05/2022 12:03:43 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/05/2022 12:03:47 - INFO - codeparrot_training - Step 39643: {'lr': 0.0004243474886214708, 'samples': 20297728, 'steps': 39643, 'loss/train': 1.701038122177124}
-03/05/2022 12:03:51 - INFO - codeparrot_training - Step 39644: {'lr': 0.0004243436852816071, 'samples': 20298240, 'steps': 39644, 'loss/train': 1.881474494934082}
-03/05/2022 12:03:52 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/05/2022 12:03:56 - INFO - codeparrot_training - Step 39645: {'lr': 0.0004243398818631868, 'samples': 20298752, 'steps': 39645, 'loss/train': 2.44671368598938}
-03/05/2022 12:03:59 - INFO - codeparrot_training - Step 39646: {'lr': 0.0004243360783662116, 'samples': 20299264, 'steps': 39646, 'loss/train': 1.7211681604385376}
-03/05/2022 12:04:01 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/05/2022 12:04:04 - INFO - codeparrot_training - Step 39647: {'lr': 0.0004243322747906833, 'samples': 20299776, 'steps': 39647, 'loss/train': 1.1366709470748901}
-03/05/2022 12:04:07 - INFO - codeparrot_training - Step 39648: {'lr': 0.00042432847113660355, 'samples': 20300288, 'steps': 39648, 'loss/train': 1.6064825057983398}
-03/05/2022 12:04:09 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 12:04:13 - INFO - codeparrot_training - Step 39649: {'lr': 0.0004243246674039741, 'samples': 20300800, 'steps': 39649, 'loss/train': 0.4563363492488861}
-03/05/2022 12:04:16 - INFO - codeparrot_training - Step 39650: {'lr': 0.00042432086359279667, 'samples': 20301312, 'steps': 39650, 'loss/train': 1.8283206224441528}
-03/05/2022 12:04:18 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/05/2022 12:04:21 - INFO - codeparrot_training - Step 39651: {'lr': 0.0004243170597030729, 'samples': 20301824, 'steps': 39651, 'loss/train': 1.2380365133285522}
-03/05/2022 12:04:25 - INFO - codeparrot_training - Step 39652: {'lr': 0.0004243132557348045, 'samples': 20302336, 'steps': 39652, 'loss/train': 1.6816068887710571}
-03/05/2022 12:04:27 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 12:04:30 - INFO - codeparrot_training - Step 39653: {'lr': 0.00042430945168799326, 'samples': 20302848, 'steps': 39653, 'loss/train': 1.7905917167663574}
-03/05/2022 12:04:33 - INFO - codeparrot_training - Step 39654: {'lr': 0.000424305647562641, 'samples': 20303360, 'steps': 39654, 'loss/train': 1.890445590019226}
-03/05/2022 12:04:35 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 12:04:38 - INFO - codeparrot_training - Step 39655: {'lr': 0.00042430184335874924, 'samples': 20303872, 'steps': 39655, 'loss/train': 2.282672643661499}
-03/05/2022 12:04:41 - INFO - codeparrot_training - Step 39656: {'lr': 0.0004242980390763197, 'samples': 20304384, 'steps': 39656, 'loss/train': 1.4861336946487427}
-03/05/2022 12:04:43 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 12:04:47 - INFO - codeparrot_training - Step 39657: {'lr': 0.0004242942347153542, 'samples': 20304896, 'steps': 39657, 'loss/train': 1.4821876287460327}
-03/05/2022 12:04:50 - INFO - codeparrot_training - Step 39658: {'lr': 0.00042429043027585435, 'samples': 20305408, 'steps': 39658, 'loss/train': 1.8780018091201782}
-03/05/2022 12:04:52 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/05/2022 12:04:55 - INFO - codeparrot_training - Step 39659: {'lr': 0.000424286625757822, 'samples': 20305920, 'steps': 39659, 'loss/train': 1.7281097173690796}
-03/05/2022 12:04:58 - INFO - codeparrot_training - Step 39660: {'lr': 0.00042428282116125873, 'samples': 20306432, 'steps': 39660, 'loss/train': 1.4897396564483643}
-03/05/2022 12:05:01 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/05/2022 12:05:03 - INFO - codeparrot_training - Step 39661: {'lr': 0.0004242790164861663, 'samples': 20306944, 'steps': 39661, 'loss/train': 1.6603518724441528}
-03/05/2022 12:05:07 - INFO - codeparrot_training - Step 39662: {'lr': 0.0004242752117325465, 'samples': 20307456, 'steps': 39662, 'loss/train': 1.2492740154266357}
-03/05/2022 12:05:09 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/05/2022 12:05:12 - INFO - codeparrot_training - Step 39663: {'lr': 0.000424271406900401, 'samples': 20307968, 'steps': 39663, 'loss/train': 1.711969017982483}
-03/05/2022 12:05:15 - INFO - codeparrot_training - Step 39664: {'lr': 0.0004242676019897314, 'samples': 20308480, 'steps': 39664, 'loss/train': 1.6771366596221924}
-03/05/2022 12:05:17 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 12:05:20 - INFO - codeparrot_training - Step 39665: {'lr': 0.00042426379700053954, 'samples': 20308992, 'steps': 39665, 'loss/train': 1.3521363735198975}
-03/05/2022 12:05:23 - INFO - codeparrot_training - Step 39666: {'lr': 0.00042425999193282713, 'samples': 20309504, 'steps': 39666, 'loss/train': 1.3631165027618408}
-03/05/2022 12:05:26 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/05/2022 12:05:29 - INFO - codeparrot_training - Step 39667: {'lr': 0.0004242561867865958, 'samples': 20310016, 'steps': 39667, 'loss/train': 1.9747333526611328}
-03/05/2022 12:05:32 - INFO - codeparrot_training - Step 39668: {'lr': 0.0004242523815618473, 'samples': 20310528, 'steps': 39668, 'loss/train': 2.31093692779541}
-03/05/2022 12:05:34 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/05/2022 12:05:37 - INFO - codeparrot_training - Step 39669: {'lr': 0.0004242485762585835, 'samples': 20311040, 'steps': 39669, 'loss/train': 1.7373601198196411}
-03/05/2022 12:05:40 - INFO - codeparrot_training - Step 39670: {'lr': 0.0004242447708768059, 'samples': 20311552, 'steps': 39670, 'loss/train': 1.2160422801971436}
-03/05/2022 12:05:42 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/05/2022 12:05:46 - INFO - codeparrot_training - Step 39671: {'lr': 0.0004242409654165163, 'samples': 20312064, 'steps': 39671, 'loss/train': 1.7019891738891602}
-03/05/2022 12:05:49 - INFO - codeparrot_training - Step 39672: {'lr': 0.00042423715987771637, 'samples': 20312576, 'steps': 39672, 'loss/train': 1.844173789024353}
-03/05/2022 12:05:51 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/05/2022 12:05:54 - INFO - codeparrot_training - Step 39673: {'lr': 0.0004242333542604079, 'samples': 20313088, 'steps': 39673, 'loss/train': 0.939050018787384}
-03/05/2022 12:05:57 - INFO - codeparrot_training - Step 39674: {'lr': 0.0004242295485645926, 'samples': 20313600, 'steps': 39674, 'loss/train': 2.218341827392578}
-03/05/2022 12:05:59 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 12:06:03 - INFO - codeparrot_training - Step 39675: {'lr': 0.0004242257427902721, 'samples': 20314112, 'steps': 39675, 'loss/train': 1.836511492729187}
-03/05/2022 12:06:06 - INFO - codeparrot_training - Step 39676: {'lr': 0.00042422193693744827, 'samples': 20314624, 'steps': 39676, 'loss/train': 1.3674324750900269}
-03/05/2022 12:06:08 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/05/2022 12:06:11 - INFO - codeparrot_training - Step 39677: {'lr': 0.0004242181310061226, 'samples': 20315136, 'steps': 39677, 'loss/train': 1.8510347604751587}
-03/05/2022 12:06:14 - INFO - codeparrot_training - Step 39678: {'lr': 0.000424214324996297, 'samples': 20315648, 'steps': 39678, 'loss/train': 1.9550224542617798}
-03/05/2022 12:06:16 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 12:06:19 - INFO - codeparrot_training - Step 39679: {'lr': 0.000424210518907973, 'samples': 20316160, 'steps': 39679, 'loss/train': 1.650903582572937}
-03/05/2022 12:06:23 - INFO - codeparrot_training - Step 39680: {'lr': 0.0004242067127411525, 'samples': 20316672, 'steps': 39680, 'loss/train': 2.426980495452881}
-03/05/2022 12:06:24 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/05/2022 12:06:28 - INFO - codeparrot_training - Step 39681: {'lr': 0.0004242029064958372, 'samples': 20317184, 'steps': 39681, 'loss/train': 1.849934458732605}
-03/05/2022 12:06:31 - INFO - codeparrot_training - Step 39682: {'lr': 0.0004241991001720287, 'samples': 20317696, 'steps': 39682, 'loss/train': 2.3181679248809814}
-03/05/2022 12:06:33 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/05/2022 12:06:36 - INFO - codeparrot_training - Step 39683: {'lr': 0.00042419529376972885, 'samples': 20318208, 'steps': 39683, 'loss/train': 1.6174503564834595}
-03/05/2022 12:06:39 - INFO - codeparrot_training - Step 39684: {'lr': 0.0004241914872889392, 'samples': 20318720, 'steps': 39684, 'loss/train': 1.1796391010284424}
-03/05/2022 12:06:41 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/05/2022 12:06:45 - INFO - codeparrot_training - Step 39685: {'lr': 0.00042418768072966163, 'samples': 20319232, 'steps': 39685, 'loss/train': 1.582139253616333}
-03/05/2022 12:06:48 - INFO - codeparrot_training - Step 39686: {'lr': 0.0004241838740918977, 'samples': 20319744, 'steps': 39686, 'loss/train': 1.881881833076477}
-03/05/2022 12:06:50 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/05/2022 12:06:53 - INFO - codeparrot_training - Step 39687: {'lr': 0.00042418006737564924, 'samples': 20320256, 'steps': 39687, 'loss/train': 1.5180909633636475}
-03/05/2022 12:06:56 - INFO - codeparrot_training - Step 39688: {'lr': 0.0004241762605809179, 'samples': 20320768, 'steps': 39688, 'loss/train': 2.111886739730835}
-03/05/2022 12:06:58 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/05/2022 12:07:02 - INFO - codeparrot_training - Step 39689: {'lr': 0.00042417245370770547, 'samples': 20321280, 'steps': 39689, 'loss/train': 1.8964176177978516}
-03/05/2022 12:07:05 - INFO - codeparrot_training - Step 39690: {'lr': 0.00042416864675601365, 'samples': 20321792, 'steps': 39690, 'loss/train': 1.6332628726959229}
-03/05/2022 12:07:07 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/05/2022 12:07:10 - INFO - codeparrot_training - Step 39691: {'lr': 0.0004241648397258441, 'samples': 20322304, 'steps': 39691, 'loss/train': 1.363561749458313}
-03/05/2022 12:07:14 - INFO - codeparrot_training - Step 39692: {'lr': 0.0004241610326171985, 'samples': 20322816, 'steps': 39692, 'loss/train': 1.6554824113845825}
-03/05/2022 12:07:16 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/05/2022 12:07:19 - INFO - codeparrot_training - Step 39693: {'lr': 0.0004241572254300786, 'samples': 20323328, 'steps': 39693, 'loss/train': 1.4589018821716309}
-03/05/2022 12:07:22 - INFO - codeparrot_training - Step 39694: {'lr': 0.00042415341816448625, 'samples': 20323840, 'steps': 39694, 'loss/train': 1.7236828804016113}
-03/05/2022 12:07:24 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/05/2022 12:07:27 - INFO - codeparrot_training - Step 39695: {'lr': 0.000424149610820423, 'samples': 20324352, 'steps': 39695, 'loss/train': 2.154867172241211}
-03/05/2022 12:07:31 - INFO - codeparrot_training - Step 39696: {'lr': 0.00042414580339789065, 'samples': 20324864, 'steps': 39696, 'loss/train': 1.4296166896820068}
-03/05/2022 12:07:33 - INFO - codeparrot_training - Skipping example with length 621 (seq_length=1024)
-03/05/2022 12:07:37 - INFO - codeparrot_training - Step 39697: {'lr': 0.00042414199589689084, 'samples': 20325376, 'steps': 39697, 'loss/train': 2.0093579292297363}
-03/05/2022 12:07:40 - INFO - codeparrot_training - Step 39698: {'lr': 0.0004241381883174254, 'samples': 20325888, 'steps': 39698, 'loss/train': 1.9618418216705322}
-03/05/2022 12:07:43 - INFO - codeparrot_training - Step 39699: {'lr': 0.00042413438065949595, 'samples': 20326400, 'steps': 39699, 'loss/train': 2.1491880416870117}
-03/05/2022 12:07:44 - INFO - codeparrot_training - Skipping example with length 305 (seq_length=1024)
-03/05/2022 12:07:48 - INFO - codeparrot_training - Step 39700: {'lr': 0.0004241305729231042, 'samples': 20326912, 'steps': 39700, 'loss/train': 1.3722018003463745}
-03/05/2022 12:07:51 - INFO - codeparrot_training - Step 39701: {'lr': 0.00042412676510825197, 'samples': 20327424, 'steps': 39701, 'loss/train': 2.1167895793914795}
-03/05/2022 12:07:53 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/05/2022 12:07:57 - INFO - codeparrot_training - Step 39702: {'lr': 0.00042412295721494086, 'samples': 20327936, 'steps': 39702, 'loss/train': 2.2206218242645264}
-03/05/2022 12:08:00 - INFO - codeparrot_training - Step 39703: {'lr': 0.00042411914924317265, 'samples': 20328448, 'steps': 39703, 'loss/train': 1.7333424091339111}
-03/05/2022 12:08:01 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/05/2022 12:08:05 - INFO - codeparrot_training - Step 39704: {'lr': 0.00042411534119294903, 'samples': 20328960, 'steps': 39704, 'loss/train': 1.5960036516189575}
-03/05/2022 12:08:08 - INFO - codeparrot_training - Step 39705: {'lr': 0.0004241115330642717, 'samples': 20329472, 'steps': 39705, 'loss/train': 1.3677841424942017}
-03/05/2022 12:08:13 - INFO - codeparrot_training - Step 39706: {'lr': 0.0004241077248571424, 'samples': 20329984, 'steps': 39706, 'loss/train': 2.119549036026001}
-03/05/2022 12:08:17 - INFO - codeparrot_training - Step 39707: {'lr': 0.0004241039165715629, 'samples': 20330496, 'steps': 39707, 'loss/train': 1.2594550848007202}
-03/05/2022 12:08:18 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/05/2022 12:08:22 - INFO - codeparrot_training - Step 39708: {'lr': 0.00042410010820753485, 'samples': 20331008, 'steps': 39708, 'loss/train': 1.325139045715332}
-03/05/2022 12:08:25 - INFO - codeparrot_training - Step 39709: {'lr': 0.00042409629976505994, 'samples': 20331520, 'steps': 39709, 'loss/train': 1.6221920251846313}
-03/05/2022 12:08:27 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/05/2022 12:08:30 - INFO - codeparrot_training - Step 39710: {'lr': 0.00042409249124414, 'samples': 20332032, 'steps': 39710, 'loss/train': 1.640898585319519}
-03/05/2022 12:08:34 - INFO - codeparrot_training - Step 39711: {'lr': 0.00042408868264477657, 'samples': 20332544, 'steps': 39711, 'loss/train': 1.203019142150879}
-03/05/2022 12:08:36 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/05/2022 12:08:39 - INFO - codeparrot_training - Step 39712: {'lr': 0.00042408487396697147, 'samples': 20333056, 'steps': 39712, 'loss/train': 1.7528810501098633}
-03/05/2022 12:08:42 - INFO - codeparrot_training - Step 39713: {'lr': 0.0004240810652107265, 'samples': 20333568, 'steps': 39713, 'loss/train': 2.0723767280578613}
-03/05/2022 12:08:44 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 12:08:47 - INFO - codeparrot_training - Step 39714: {'lr': 0.0004240772563760432, 'samples': 20334080, 'steps': 39714, 'loss/train': 2.3668529987335205}
-03/05/2022 12:08:51 - INFO - codeparrot_training - Step 39715: {'lr': 0.00042407344746292345, 'samples': 20334592, 'steps': 39715, 'loss/train': 2.5309340953826904}
-03/05/2022 12:08:53 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/05/2022 12:08:56 - INFO - codeparrot_training - Step 39716: {'lr': 0.00042406963847136883, 'samples': 20335104, 'steps': 39716, 'loss/train': 1.3066926002502441}
-03/05/2022 12:08:59 - INFO - codeparrot_training - Step 39717: {'lr': 0.0004240658294013812, 'samples': 20335616, 'steps': 39717, 'loss/train': 0.31821590662002563}
-03/05/2022 12:09:01 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 12:09:05 - INFO - codeparrot_training - Step 39718: {'lr': 0.00042406202025296213, 'samples': 20336128, 'steps': 39718, 'loss/train': 1.5786982774734497}
-03/05/2022 12:09:08 - INFO - codeparrot_training - Step 39719: {'lr': 0.00042405821102611336, 'samples': 20336640, 'steps': 39719, 'loss/train': 1.7996127605438232}
-03/05/2022 12:09:10 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/05/2022 12:09:13 - INFO - codeparrot_training - Step 39720: {'lr': 0.0004240544017208367, 'samples': 20337152, 'steps': 39720, 'loss/train': 2.0658388137817383}
-03/05/2022 12:09:16 - INFO - codeparrot_training - Step 39721: {'lr': 0.0004240505923371338, 'samples': 20337664, 'steps': 39721, 'loss/train': 0.9575673937797546}
-03/05/2022 12:09:18 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/05/2022 12:09:21 - INFO - codeparrot_training - Step 39722: {'lr': 0.0004240467828750064, 'samples': 20338176, 'steps': 39722, 'loss/train': 1.9698398113250732}
-03/05/2022 12:09:25 - INFO - codeparrot_training - Step 39723: {'lr': 0.0004240429733344562, 'samples': 20338688, 'steps': 39723, 'loss/train': 1.0356611013412476}
-03/05/2022 12:09:26 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 12:09:30 - INFO - codeparrot_training - Step 39724: {'lr': 0.0004240391637154849, 'samples': 20339200, 'steps': 39724, 'loss/train': 0.6929736137390137}
-03/05/2022 12:09:33 - INFO - codeparrot_training - Step 39725: {'lr': 0.0004240353540180942, 'samples': 20339712, 'steps': 39725, 'loss/train': 2.0943732261657715}
-03/05/2022 12:09:35 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/05/2022 12:09:38 - INFO - codeparrot_training - Step 39726: {'lr': 0.00042403154424228596, 'samples': 20340224, 'steps': 39726, 'loss/train': 6.650343418121338}
-03/05/2022 12:09:41 - INFO - codeparrot_training - Step 39727: {'lr': 0.00042402773438806175, 'samples': 20340736, 'steps': 39727, 'loss/train': 2.104301929473877}
-03/05/2022 12:09:43 - INFO - codeparrot_training - Skipping example with length 988 (seq_length=1024)
-03/05/2022 12:09:47 - INFO - codeparrot_training - Step 39728: {'lr': 0.00042402392445542333, 'samples': 20341248, 'steps': 39728, 'loss/train': 0.5483896136283875}
-03/05/2022 12:09:50 - INFO - codeparrot_training - Step 39729: {'lr': 0.0004240201144443724, 'samples': 20341760, 'steps': 39729, 'loss/train': 1.8378880023956299}
-03/05/2022 12:09:51 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/05/2022 12:09:55 - INFO - codeparrot_training - Step 39730: {'lr': 0.00042401630435491073, 'samples': 20342272, 'steps': 39730, 'loss/train': 1.8550362586975098}
-03/05/2022 12:09:58 - INFO - codeparrot_training - Step 39731: {'lr': 0.00042401249418703996, 'samples': 20342784, 'steps': 39731, 'loss/train': 1.6491514444351196}
-03/05/2022 12:10:00 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/05/2022 12:10:04 - INFO - codeparrot_training - Step 39732: {'lr': 0.00042400868394076185, 'samples': 20343296, 'steps': 39732, 'loss/train': 1.980665922164917}
-03/05/2022 12:10:07 - INFO - codeparrot_training - Step 39733: {'lr': 0.0004240048736160781, 'samples': 20343808, 'steps': 39733, 'loss/train': 2.1470589637756348}
-03/05/2022 12:10:09 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/05/2022 12:10:12 - INFO - codeparrot_training - Step 39734: {'lr': 0.0004240010632129905, 'samples': 20344320, 'steps': 39734, 'loss/train': 1.5302097797393799}
-03/05/2022 12:10:15 - INFO - codeparrot_training - Step 39735: {'lr': 0.00042399725273150056, 'samples': 20344832, 'steps': 39735, 'loss/train': 1.196291208267212}
-03/05/2022 12:10:17 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/05/2022 12:10:20 - INFO - codeparrot_training - Step 39736: {'lr': 0.0004239934421716103, 'samples': 20345344, 'steps': 39736, 'loss/train': 1.7782800197601318}
-03/05/2022 12:10:24 - INFO - codeparrot_training - Step 39737: {'lr': 0.00042398963153332124, 'samples': 20345856, 'steps': 39737, 'loss/train': 1.6377003192901611}
-03/05/2022 12:10:25 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/05/2022 12:10:29 - INFO - codeparrot_training - Step 39738: {'lr': 0.00042398582081663513, 'samples': 20346368, 'steps': 39738, 'loss/train': 2.029045343399048}
-03/05/2022 12:10:32 - INFO - codeparrot_training - Step 39739: {'lr': 0.0004239820100215537, 'samples': 20346880, 'steps': 39739, 'loss/train': 1.489431619644165}
-03/05/2022 12:10:37 - INFO - codeparrot_training - Step 39740: {'lr': 0.00042397819914807855, 'samples': 20347392, 'steps': 39740, 'loss/train': 1.8223440647125244}
-03/05/2022 12:10:41 - INFO - codeparrot_training - Step 39741: {'lr': 0.00042397438819621164, 'samples': 20347904, 'steps': 39741, 'loss/train': 2.48219895362854}
-03/05/2022 12:10:42 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/05/2022 12:10:46 - INFO - codeparrot_training - Step 39742: {'lr': 0.0004239705771659545, 'samples': 20348416, 'steps': 39742, 'loss/train': 1.0197758674621582}
-03/05/2022 12:10:49 - INFO - codeparrot_training - Step 39743: {'lr': 0.000423966766057309, 'samples': 20348928, 'steps': 39743, 'loss/train': 1.537539005279541}
-03/05/2022 12:10:51 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/05/2022 12:10:55 - INFO - codeparrot_training - Step 39744: {'lr': 0.00042396295487027666, 'samples': 20349440, 'steps': 39744, 'loss/train': 1.895847201347351}
-03/05/2022 12:10:58 - INFO - codeparrot_training - Step 39745: {'lr': 0.0004239591436048593, 'samples': 20349952, 'steps': 39745, 'loss/train': 2.3189613819122314}
-03/05/2022 12:10:59 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/05/2022 12:11:03 - INFO - codeparrot_training - Step 39746: {'lr': 0.0004239553322610586, 'samples': 20350464, 'steps': 39746, 'loss/train': 1.871346116065979}
-03/05/2022 12:11:06 - INFO - codeparrot_training - Step 39747: {'lr': 0.0004239515208388764, 'samples': 20350976, 'steps': 39747, 'loss/train': 0.7931369543075562}
-03/05/2022 12:11:08 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/05/2022 12:11:11 - INFO - codeparrot_training - Step 39748: {'lr': 0.00042394770933831425, 'samples': 20351488, 'steps': 39748, 'loss/train': 1.5695595741271973}
-03/05/2022 12:11:14 - INFO - codeparrot_training - Step 39749: {'lr': 0.00042394389775937403, 'samples': 20352000, 'steps': 39749, 'loss/train': 1.582062840461731}
-03/05/2022 12:11:16 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/05/2022 12:11:20 - INFO - codeparrot_training - Step 39750: {'lr': 0.0004239400861020574, 'samples': 20352512, 'steps': 39750, 'loss/train': 1.7411938905715942}
-03/05/2022 12:11:23 - INFO - codeparrot_training - Step 39751: {'lr': 0.00042393627436636597, 'samples': 20353024, 'steps': 39751, 'loss/train': 1.994664192199707}
-03/05/2022 12:11:24 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/05/2022 12:11:28 - INFO - codeparrot_training - Step 39752: {'lr': 0.0004239324625523015, 'samples': 20353536, 'steps': 39752, 'loss/train': 1.2105003595352173}
-03/05/2022 12:11:31 - INFO - codeparrot_training - Step 39753: {'lr': 0.00042392865065986573, 'samples': 20354048, 'steps': 39753, 'loss/train': 1.6135072708129883}
-03/05/2022 12:11:32 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/05/2022 12:11:36 - INFO - codeparrot_training - Step 39754: {'lr': 0.00042392483868906053, 'samples': 20354560, 'steps': 39754, 'loss/train': 1.0073846578598022}
-03/05/2022 12:11:40 - INFO - codeparrot_training - Step 39755: {'lr': 0.0004239210266398874, 'samples': 20355072, 'steps': 39755, 'loss/train': 1.5900074243545532}
-03/05/2022 12:11:41 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/05/2022 12:11:45 - INFO - codeparrot_training - Step 39756: {'lr': 0.0004239172145123481, 'samples': 20355584, 'steps': 39756, 'loss/train': 2.815011501312256}
-03/05/2022 12:11:48 - INFO - codeparrot_training - Step 39757: {'lr': 0.0004239134023064445, 'samples': 20356096, 'steps': 39757, 'loss/train': 0.9682260155677795}
-03/05/2022 12:11:49 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/05/2022 12:11:53 - INFO - codeparrot_training - Step 39758: {'lr': 0.0004239095900221781, 'samples': 20356608, 'steps': 39758, 'loss/train': 1.469543218612671}
-03/05/2022 12:11:57 - INFO - codeparrot_training - Step 39759: {'lr': 0.00042390577765955077, 'samples': 20357120, 'steps': 39759, 'loss/train': 1.7951879501342773}
-03/05/2022 12:11:58 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/05/2022 12:12:02 - INFO - codeparrot_training - Step 39760: {'lr': 0.00042390196521856417, 'samples': 20357632, 'steps': 39760, 'loss/train': 1.8760440349578857}
-03/05/2022 12:12:05 - INFO - codeparrot_training - Step 39761: {'lr': 0.00042389815269922005, 'samples': 20358144, 'steps': 39761, 'loss/train': 1.5235909223556519}
-03/05/2022 12:12:07 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/05/2022 12:12:10 - INFO - codeparrot_training - Step 39762: {'lr': 0.0004238943401015201, 'samples': 20358656, 'steps': 39762, 'loss/train': 0.9513997435569763}
-03/05/2022 12:12:14 - INFO - codeparrot_training - Step 39763: {'lr': 0.0004238905274254661, 'samples': 20359168, 'steps': 39763, 'loss/train': 1.8673384189605713}
-03/05/2022 12:12:15 - INFO - codeparrot_training - Skipping example with length 639 (seq_length=1024)
-03/05/2022 12:12:19 - INFO - codeparrot_training - Step 39764: {'lr': 0.0004238867146710596, 'samples': 20359680, 'steps': 39764, 'loss/train': 0.9310447573661804}
-03/05/2022 12:12:22 - INFO - codeparrot_training - Step 39765: {'lr': 0.0004238829018383025, 'samples': 20360192, 'steps': 39765, 'loss/train': 1.4351699352264404}
-03/05/2022 12:12:23 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/05/2022 12:12:27 - INFO - codeparrot_training - Step 39766: {'lr': 0.0004238790889271964, 'samples': 20360704, 'steps': 39766, 'loss/train': 1.0077195167541504}
-03/05/2022 12:12:30 - INFO - codeparrot_training - Step 39767: {'lr': 0.0004238752759377431, 'samples': 20361216, 'steps': 39767, 'loss/train': 1.8727296590805054}
-03/05/2022 12:12:32 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/05/2022 12:12:36 - INFO - codeparrot_training - Step 39768: {'lr': 0.0004238714628699443, 'samples': 20361728, 'steps': 39768, 'loss/train': 1.916914701461792}
-03/05/2022 12:12:39 - INFO - codeparrot_training - Step 39769: {'lr': 0.00042386764972380164, 'samples': 20362240, 'steps': 39769, 'loss/train': 0.6778926253318787}
-03/05/2022 12:12:40 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/05/2022 12:12:44 - INFO - codeparrot_training - Step 39770: {'lr': 0.00042386383649931693, 'samples': 20362752, 'steps': 39770, 'loss/train': 2.377271890640259}
-03/05/2022 12:12:47 - INFO - codeparrot_training - Step 39771: {'lr': 0.00042386002319649184, 'samples': 20363264, 'steps': 39771, 'loss/train': 1.6341294050216675}
-03/05/2022 12:12:48 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/05/2022 12:12:52 - INFO - codeparrot_training - Step 39772: {'lr': 0.0004238562098153281, 'samples': 20363776, 'steps': 39772, 'loss/train': 1.7641915082931519}
-03/05/2022 12:12:56 - INFO - codeparrot_training - Step 39773: {'lr': 0.0004238523963558275, 'samples': 20364288, 'steps': 39773, 'loss/train': 1.123089075088501}
-03/05/2022 12:12:57 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/05/2022 12:13:01 - INFO - codeparrot_training - Step 39774: {'lr': 0.0004238485828179917, 'samples': 20364800, 'steps': 39774, 'loss/train': 1.668440818786621}
-03/05/2022 12:13:04 - INFO - codeparrot_training - Step 39775: {'lr': 0.00042384476920182234, 'samples': 20365312, 'steps': 39775, 'loss/train': 1.8428784608840942}
-03/05/2022 12:13:05 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/05/2022 12:13:09 - INFO - codeparrot_training - Step 39776: {'lr': 0.0004238409555073212, 'samples': 20365824, 'steps': 39776, 'loss/train': 1.9015308618545532}
-03/05/2022 12:13:13 - INFO - codeparrot_training - Step 39777: {'lr': 0.00042383714173449007, 'samples': 20366336, 'steps': 39777, 'loss/train': 2.2158849239349365}
-03/05/2022 12:13:14 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/05/2022 12:13:18 - INFO - codeparrot_training - Step 39778: {'lr': 0.00042383332788333055, 'samples': 20366848, 'steps': 39778, 'loss/train': 2.553380250930786}
-03/05/2022 12:13:21 - INFO - codeparrot_training - Step 39779: {'lr': 0.0004238295139538445, 'samples': 20367360, 'steps': 39779, 'loss/train': 1.5504097938537598}
-03/05/2022 12:13:22 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/05/2022 12:13:26 - INFO - codeparrot_training - Step 39780: {'lr': 0.0004238256999460335, 'samples': 20367872, 'steps': 39780, 'loss/train': 1.0681391954421997}
-03/05/2022 12:13:29 - INFO - codeparrot_training - Step 39781: {'lr': 0.00042382188585989933, 'samples': 20368384, 'steps': 39781, 'loss/train': 1.8137515783309937}
-03/05/2022 12:13:30 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 12:13:35 - INFO - codeparrot_training - Step 39782: {'lr': 0.0004238180716954436, 'samples': 20368896, 'steps': 39782, 'loss/train': 1.5131499767303467}
-03/05/2022 12:13:38 - INFO - codeparrot_training - Step 39783: {'lr': 0.0004238142574526683, 'samples': 20369408, 'steps': 39783, 'loss/train': 1.202422857284546}
-03/05/2022 12:13:38 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/05/2022 12:13:43 - INFO - codeparrot_training - Step 39784: {'lr': 0.0004238104431315749, 'samples': 20369920, 'steps': 39784, 'loss/train': 1.8084338903427124}
-03/05/2022 12:13:46 - INFO - codeparrot_training - Step 39785: {'lr': 0.00042380662873216517, 'samples': 20370432, 'steps': 39785, 'loss/train': 2.018679618835449}
-03/05/2022 12:13:47 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/05/2022 12:13:51 - INFO - codeparrot_training - Step 39786: {'lr': 0.00042380281425444087, 'samples': 20370944, 'steps': 39786, 'loss/train': 4.231381416320801}
-03/05/2022 12:13:55 - INFO - codeparrot_training - Step 39787: {'lr': 0.0004237989996984037, 'samples': 20371456, 'steps': 39787, 'loss/train': 2.237713575363159}
-03/05/2022 12:13:55 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/05/2022 12:14:00 - INFO - codeparrot_training - Step 39788: {'lr': 0.0004237951850640555, 'samples': 20371968, 'steps': 39788, 'loss/train': 1.5606929063796997}
-03/05/2022 12:14:03 - INFO - codeparrot_training - Step 39789: {'lr': 0.0004237913703513977, 'samples': 20372480, 'steps': 39789, 'loss/train': 1.7312358617782593}
-03/05/2022 12:14:03 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/05/2022 12:14:08 - INFO - codeparrot_training - Step 39790: {'lr': 0.00042378755556043225, 'samples': 20372992, 'steps': 39790, 'loss/train': 1.643588900566101}
-03/05/2022 12:14:11 - INFO - codeparrot_training - Step 39791: {'lr': 0.0004237837406911608, 'samples': 20373504, 'steps': 39791, 'loss/train': 1.759361743927002}
-03/05/2022 12:14:12 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/05/2022 12:14:17 - INFO - codeparrot_training - Step 39792: {'lr': 0.00042377992574358514, 'samples': 20374016, 'steps': 39792, 'loss/train': 1.719692349433899}
-03/05/2022 12:14:20 - INFO - codeparrot_training - Step 39793: {'lr': 0.0004237761107177068, 'samples': 20374528, 'steps': 39793, 'loss/train': 2.2635529041290283}
-03/05/2022 12:14:20 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/05/2022 12:14:25 - INFO - codeparrot_training - Step 39794: {'lr': 0.00042377229561352774, 'samples': 20375040, 'steps': 39794, 'loss/train': 1.7810338735580444}
-03/05/2022 12:14:28 - INFO - codeparrot_training - Step 39795: {'lr': 0.00042376848043104953, 'samples': 20375552, 'steps': 39795, 'loss/train': 1.7315396070480347}
-03/05/2022 12:14:29 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 12:14:34 - INFO - codeparrot_training - Step 39796: {'lr': 0.00042376466517027387, 'samples': 20376064, 'steps': 39796, 'loss/train': 1.4263797998428345}
-03/05/2022 12:14:37 - INFO - codeparrot_training - Step 39797: {'lr': 0.00042376084983120266, 'samples': 20376576, 'steps': 39797, 'loss/train': 1.4127750396728516}
-03/05/2022 12:14:38 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/05/2022 12:14:42 - INFO - codeparrot_training - Step 39798: {'lr': 0.0004237570344138374, 'samples': 20377088, 'steps': 39798, 'loss/train': 0.5726118087768555}
-03/05/2022 12:14:45 - INFO - codeparrot_training - Step 39799: {'lr': 0.00042375321891818, 'samples': 20377600, 'steps': 39799, 'loss/train': 1.66351318359375}
-03/05/2022 12:14:46 - INFO - codeparrot_training - Skipping example with length 551 (seq_length=1024)
-03/05/2022 12:14:51 - INFO - codeparrot_training - Step 39800: {'lr': 0.00042374940334423194, 'samples': 20378112, 'steps': 39800, 'loss/train': 1.4546575546264648}
-03/05/2022 12:14:54 - INFO - codeparrot_training - Step 39801: {'lr': 0.00042374558769199517, 'samples': 20378624, 'steps': 39801, 'loss/train': 5.476089000701904}
-03/05/2022 12:14:57 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/05/2022 12:15:00 - INFO - codeparrot_training - Step 39802: {'lr': 0.0004237417719614713, 'samples': 20379136, 'steps': 39802, 'loss/train': 1.785767674446106}
-03/05/2022 12:15:03 - INFO - codeparrot_training - Step 39803: {'lr': 0.000423737956152662, 'samples': 20379648, 'steps': 39803, 'loss/train': 1.060845971107483}
-03/05/2022 12:15:06 - INFO - codeparrot_training - Step 39804: {'lr': 0.0004237341402655692, 'samples': 20380160, 'steps': 39804, 'loss/train': 2.177276372909546}
-03/05/2022 12:15:06 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 12:15:11 - INFO - codeparrot_training - Step 39805: {'lr': 0.00042373032430019443, 'samples': 20380672, 'steps': 39805, 'loss/train': 2.085352897644043}
-03/05/2022 12:15:14 - INFO - codeparrot_training - Step 39806: {'lr': 0.00042372650825653937, 'samples': 20381184, 'steps': 39806, 'loss/train': 0.6967990398406982}
-03/05/2022 12:15:14 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/05/2022 12:15:20 - INFO - codeparrot_training - Step 39807: {'lr': 0.0004237226921346059, 'samples': 20381696, 'steps': 39807, 'loss/train': 1.8778609037399292}
-03/05/2022 12:15:23 - INFO - codeparrot_training - Step 39808: {'lr': 0.0004237188759343956, 'samples': 20382208, 'steps': 39808, 'loss/train': 1.7179851531982422}
-03/05/2022 12:15:23 - INFO - codeparrot_training - Skipping example with length 534 (seq_length=1024)
-03/05/2022 12:15:28 - INFO - codeparrot_training - Step 39809: {'lr': 0.0004237150596559103, 'samples': 20382720, 'steps': 39809, 'loss/train': 1.1935399770736694}
-03/05/2022 12:15:31 - INFO - codeparrot_training - Step 39810: {'lr': 0.00042371124329915167, 'samples': 20383232, 'steps': 39810, 'loss/train': 2.141422748565674}
-03/05/2022 12:15:31 - INFO - codeparrot_training - Skipping example with length 109 (seq_length=1024)
-03/05/2022 12:15:37 - INFO - codeparrot_training - Step 39811: {'lr': 0.0004237074268641215, 'samples': 20383744, 'steps': 39811, 'loss/train': 1.2997610569000244}
-03/05/2022 12:15:40 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/05/2022 12:15:42 - INFO - codeparrot_training - Step 39812: {'lr': 0.00042370361035082136, 'samples': 20384256, 'steps': 39812, 'loss/train': 2.148790121078491}
-03/05/2022 12:15:45 - INFO - codeparrot_training - Step 39813: {'lr': 0.000423699793759253, 'samples': 20384768, 'steps': 39813, 'loss/train': 2.8612000942230225}
-03/05/2022 12:15:48 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/05/2022 12:15:50 - INFO - codeparrot_training - Step 39814: {'lr': 0.0004236959770894183, 'samples': 20385280, 'steps': 39814, 'loss/train': 1.7612874507904053}
-03/05/2022 12:15:54 - INFO - codeparrot_training - Step 39815: {'lr': 0.00042369216034131887, 'samples': 20385792, 'steps': 39815, 'loss/train': 1.492950439453125}
-03/05/2022 12:15:57 - INFO - codeparrot_training - Step 39816: {'lr': 0.0004236883435149564, 'samples': 20386304, 'steps': 39816, 'loss/train': 1.4257001876831055}
-03/05/2022 12:15:57 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/05/2022 12:16:02 - INFO - codeparrot_training - Step 39817: {'lr': 0.0004236845266103327, 'samples': 20386816, 'steps': 39817, 'loss/train': 2.480581283569336}
-03/05/2022 12:16:05 - INFO - codeparrot_training - Step 39818: {'lr': 0.00042368070962744937, 'samples': 20387328, 'steps': 39818, 'loss/train': 1.4131630659103394}
-03/05/2022 12:16:05 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/05/2022 12:16:10 - INFO - codeparrot_training - Step 39819: {'lr': 0.0004236768925663082, 'samples': 20387840, 'steps': 39819, 'loss/train': 1.248265266418457}
-03/05/2022 12:16:14 - INFO - codeparrot_training - Step 39820: {'lr': 0.0004236730754269109, 'samples': 20388352, 'steps': 39820, 'loss/train': 2.3671958446502686}
-03/05/2022 12:16:14 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/05/2022 12:16:19 - INFO - codeparrot_training - Step 39821: {'lr': 0.00042366925820925915, 'samples': 20388864, 'steps': 39821, 'loss/train': 1.500373125076294}
-03/05/2022 12:16:22 - INFO - codeparrot_training - Step 39822: {'lr': 0.0004236654409133548, 'samples': 20389376, 'steps': 39822, 'loss/train': 1.9576431512832642}
-03/05/2022 12:16:22 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/05/2022 12:16:27 - INFO - codeparrot_training - Step 39823: {'lr': 0.0004236616235391995, 'samples': 20389888, 'steps': 39823, 'loss/train': 1.5787209272384644}
-03/05/2022 12:16:30 - INFO - codeparrot_training - Step 39824: {'lr': 0.0004236578060867949, 'samples': 20390400, 'steps': 39824, 'loss/train': 0.5418258905410767}
-03/05/2022 12:16:31 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 12:16:36 - INFO - codeparrot_training - Step 39825: {'lr': 0.0004236539885561427, 'samples': 20390912, 'steps': 39825, 'loss/train': 1.3942497968673706}
-03/05/2022 12:16:39 - INFO - codeparrot_training - Step 39826: {'lr': 0.0004236501709472448, 'samples': 20391424, 'steps': 39826, 'loss/train': 1.8778427839279175}
-03/05/2022 12:16:39 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/05/2022 12:16:44 - INFO - codeparrot_training - Step 39827: {'lr': 0.00042364635326010277, 'samples': 20391936, 'steps': 39827, 'loss/train': 1.8485225439071655}
-03/05/2022 12:16:47 - INFO - codeparrot_training - Step 39828: {'lr': 0.0004236425354947183, 'samples': 20392448, 'steps': 39828, 'loss/train': 1.3074642419815063}
-03/05/2022 12:16:47 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 12:16:53 - INFO - codeparrot_training - Step 39829: {'lr': 0.0004236387176510933, 'samples': 20392960, 'steps': 39829, 'loss/train': 1.85964035987854}
-03/05/2022 12:16:56 - INFO - codeparrot_training - Step 39830: {'lr': 0.00042363489972922937, 'samples': 20393472, 'steps': 39830, 'loss/train': 1.464102864265442}
-03/05/2022 12:16:56 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/05/2022 12:17:01 - INFO - codeparrot_training - Step 39831: {'lr': 0.00042363108172912824, 'samples': 20393984, 'steps': 39831, 'loss/train': 2.4689626693725586}
-03/05/2022 12:17:04 - INFO - codeparrot_training - Step 39832: {'lr': 0.0004236272636507915, 'samples': 20394496, 'steps': 39832, 'loss/train': 1.969588041305542}
-03/05/2022 12:17:04 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/05/2022 12:17:10 - INFO - codeparrot_training - Step 39833: {'lr': 0.0004236234454942211, 'samples': 20395008, 'steps': 39833, 'loss/train': 0.7124606370925903}
-03/05/2022 12:17:12 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 12:17:15 - INFO - codeparrot_training - Step 39834: {'lr': 0.0004236196272594186, 'samples': 20395520, 'steps': 39834, 'loss/train': 1.5215046405792236}
-03/05/2022 12:17:18 - INFO - codeparrot_training - Step 39835: {'lr': 0.00042361580894638586, 'samples': 20396032, 'steps': 39835, 'loss/train': 2.6861088275909424}
-03/05/2022 12:17:21 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/05/2022 12:17:23 - INFO - codeparrot_training - Step 39836: {'lr': 0.0004236119905551244, 'samples': 20396544, 'steps': 39836, 'loss/train': 1.7392479181289673}
-03/05/2022 12:17:27 - INFO - codeparrot_training - Step 39837: {'lr': 0.0004236081720856362, 'samples': 20397056, 'steps': 39837, 'loss/train': 1.983737826347351}
-03/05/2022 12:17:29 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/05/2022 12:17:32 - INFO - codeparrot_training - Step 39838: {'lr': 0.0004236043535379227, 'samples': 20397568, 'steps': 39838, 'loss/train': 1.3157191276550293}
-03/05/2022 12:17:35 - INFO - codeparrot_training - Step 39839: {'lr': 0.0004236005349119858, 'samples': 20398080, 'steps': 39839, 'loss/train': 1.9999973773956299}
-03/05/2022 12:17:38 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/05/2022 12:17:40 - INFO - codeparrot_training - Step 39840: {'lr': 0.0004235967162078272, 'samples': 20398592, 'steps': 39840, 'loss/train': 1.8136247396469116}
-03/05/2022 12:17:43 - INFO - codeparrot_training - Step 39841: {'lr': 0.0004235928974254486, 'samples': 20399104, 'steps': 39841, 'loss/train': 1.6259191036224365}
-03/05/2022 12:17:46 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 12:17:49 - INFO - codeparrot_training - Step 39842: {'lr': 0.00042358907856485166, 'samples': 20399616, 'steps': 39842, 'loss/train': 1.8064451217651367}
-03/05/2022 12:17:52 - INFO - codeparrot_training - Step 39843: {'lr': 0.0004235852596260382, 'samples': 20400128, 'steps': 39843, 'loss/train': 0.7688383460044861}
-03/05/2022 12:17:54 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 12:17:57 - INFO - codeparrot_training - Step 39844: {'lr': 0.0004235814406090099, 'samples': 20400640, 'steps': 39844, 'loss/train': 1.9100489616394043}
-03/05/2022 12:18:00 - INFO - codeparrot_training - Step 39845: {'lr': 0.0004235776215137686, 'samples': 20401152, 'steps': 39845, 'loss/train': 1.6196867227554321}
-03/05/2022 12:18:03 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/05/2022 12:18:06 - INFO - codeparrot_training - Step 39846: {'lr': 0.0004235738023403157, 'samples': 20401664, 'steps': 39846, 'loss/train': 2.053760051727295}
-03/05/2022 12:18:09 - INFO - codeparrot_training - Step 39847: {'lr': 0.00042356998308865323, 'samples': 20402176, 'steps': 39847, 'loss/train': 1.964150309562683}
-03/05/2022 12:18:11 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 12:18:14 - INFO - codeparrot_training - Step 39848: {'lr': 0.00042356616375878274, 'samples': 20402688, 'steps': 39848, 'loss/train': 1.5895428657531738}
-03/05/2022 12:18:17 - INFO - codeparrot_training - Step 39849: {'lr': 0.00042356234435070604, 'samples': 20403200, 'steps': 39849, 'loss/train': 1.8729695081710815}
-03/05/2022 12:18:19 - INFO - codeparrot_training - Skipping example with length 465 (seq_length=1024)
-03/05/2022 12:18:22 - INFO - codeparrot_training - Step 39850: {'lr': 0.0004235585248644249, 'samples': 20403712, 'steps': 39850, 'loss/train': 1.1836236715316772}
-03/05/2022 12:18:25 - INFO - codeparrot_training - Step 39851: {'lr': 0.0004235547052999409, 'samples': 20404224, 'steps': 39851, 'loss/train': 1.8481007814407349}
-03/05/2022 12:18:28 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/05/2022 12:18:31 - INFO - codeparrot_training - Step 39852: {'lr': 0.00042355088565725584, 'samples': 20404736, 'steps': 39852, 'loss/train': 2.1526317596435547}
-03/05/2022 12:18:34 - INFO - codeparrot_training - Step 39853: {'lr': 0.0004235470659363714, 'samples': 20405248, 'steps': 39853, 'loss/train': 1.782456636428833}
-03/05/2022 12:18:36 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/05/2022 12:18:39 - INFO - codeparrot_training - Step 39854: {'lr': 0.0004235432461372894, 'samples': 20405760, 'steps': 39854, 'loss/train': 1.5759862661361694}
-03/05/2022 12:18:42 - INFO - codeparrot_training - Step 39855: {'lr': 0.0004235394262600114, 'samples': 20406272, 'steps': 39855, 'loss/train': 2.2514705657958984}
-03/05/2022 12:18:45 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/05/2022 12:18:48 - INFO - codeparrot_training - Step 39856: {'lr': 0.0004235356063045393, 'samples': 20406784, 'steps': 39856, 'loss/train': 1.3339650630950928}
-03/05/2022 12:18:51 - INFO - codeparrot_training - Step 39857: {'lr': 0.0004235317862708747, 'samples': 20407296, 'steps': 39857, 'loss/train': 1.9962352514266968}
-03/05/2022 12:18:53 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/05/2022 12:18:56 - INFO - codeparrot_training - Step 39858: {'lr': 0.00042352796615901937, 'samples': 20407808, 'steps': 39858, 'loss/train': 2.3052124977111816}
-03/05/2022 12:18:59 - INFO - codeparrot_training - Step 39859: {'lr': 0.000423524145968975, 'samples': 20408320, 'steps': 39859, 'loss/train': 1.4809904098510742}
-03/05/2022 12:19:01 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/05/2022 12:19:04 - INFO - codeparrot_training - Step 39860: {'lr': 0.00042352032570074327, 'samples': 20408832, 'steps': 39860, 'loss/train': 1.9197373390197754}
-03/05/2022 12:19:08 - INFO - codeparrot_training - Step 39861: {'lr': 0.00042351650535432607, 'samples': 20409344, 'steps': 39861, 'loss/train': 1.754490613937378}
-03/05/2022 12:19:10 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/05/2022 12:19:13 - INFO - codeparrot_training - Step 39862: {'lr': 0.00042351268492972494, 'samples': 20409856, 'steps': 39862, 'loss/train': 1.7043520212173462}
-03/05/2022 12:19:16 - INFO - codeparrot_training - Step 39863: {'lr': 0.0004235088644269417, 'samples': 20410368, 'steps': 39863, 'loss/train': 1.731917142868042}
-03/05/2022 12:19:18 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 12:19:21 - INFO - codeparrot_training - Step 39864: {'lr': 0.00042350504384597803, 'samples': 20410880, 'steps': 39864, 'loss/train': 2.481557846069336}
-03/05/2022 12:19:24 - INFO - codeparrot_training - Step 39865: {'lr': 0.0004235012231868357, 'samples': 20411392, 'steps': 39865, 'loss/train': 1.0871659517288208}
-03/05/2022 12:19:26 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 12:19:30 - INFO - codeparrot_training - Step 39866: {'lr': 0.0004234974024495163, 'samples': 20411904, 'steps': 39866, 'loss/train': 1.4249085187911987}
-03/05/2022 12:19:33 - INFO - codeparrot_training - Step 39867: {'lr': 0.00042349358163402175, 'samples': 20412416, 'steps': 39867, 'loss/train': 1.5193296670913696}
-03/05/2022 12:19:34 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/05/2022 12:19:38 - INFO - codeparrot_training - Step 39868: {'lr': 0.0004234897607403536, 'samples': 20412928, 'steps': 39868, 'loss/train': 1.5914673805236816}
-03/05/2022 12:19:41 - INFO - codeparrot_training - Step 39869: {'lr': 0.0004234859397685137, 'samples': 20413440, 'steps': 39869, 'loss/train': 1.0556252002716064}
-03/05/2022 12:19:43 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/05/2022 12:19:46 - INFO - codeparrot_training - Step 39870: {'lr': 0.0004234821187185036, 'samples': 20413952, 'steps': 39870, 'loss/train': 1.638780117034912}
-03/05/2022 12:19:50 - INFO - codeparrot_training - Step 39871: {'lr': 0.0004234782975903253, 'samples': 20414464, 'steps': 39871, 'loss/train': 1.2710968255996704}
-03/05/2022 12:19:51 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 12:19:55 - INFO - codeparrot_training - Step 39872: {'lr': 0.00042347447638398024, 'samples': 20414976, 'steps': 39872, 'loss/train': 1.6201248168945312}
-03/05/2022 12:19:58 - INFO - codeparrot_training - Step 39873: {'lr': 0.00042347065509947023, 'samples': 20415488, 'steps': 39873, 'loss/train': 1.504025936126709}
-03/05/2022 12:20:00 - INFO - codeparrot_training - Skipping example with length 959 (seq_length=1024)
-03/05/2022 12:20:03 - INFO - codeparrot_training - Step 39874: {'lr': 0.0004234668337367971, 'samples': 20416000, 'steps': 39874, 'loss/train': 2.002636671066284}
-03/05/2022 12:20:07 - INFO - codeparrot_training - Step 39875: {'lr': 0.0004234630122959625, 'samples': 20416512, 'steps': 39875, 'loss/train': 1.569145679473877}
-03/05/2022 12:20:08 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/05/2022 12:20:12 - INFO - codeparrot_training - Step 39876: {'lr': 0.0004234591907769681, 'samples': 20417024, 'steps': 39876, 'loss/train': 1.638311505317688}
-03/05/2022 12:20:15 - INFO - codeparrot_training - Step 39877: {'lr': 0.0004234553691798156, 'samples': 20417536, 'steps': 39877, 'loss/train': 1.7621586322784424}
-03/05/2022 12:20:16 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/05/2022 12:20:20 - INFO - codeparrot_training - Step 39878: {'lr': 0.000423451547504507, 'samples': 20418048, 'steps': 39878, 'loss/train': 1.1588932275772095}
-03/05/2022 12:20:23 - INFO - codeparrot_training - Step 39879: {'lr': 0.0004234477257510436, 'samples': 20418560, 'steps': 39879, 'loss/train': 1.3031576871871948}
-03/05/2022 12:20:25 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 12:20:29 - INFO - codeparrot_training - Step 39880: {'lr': 0.00042344390391942745, 'samples': 20419072, 'steps': 39880, 'loss/train': 2.274768590927124}
-03/05/2022 12:20:32 - INFO - codeparrot_training - Step 39881: {'lr': 0.0004234400820096601, 'samples': 20419584, 'steps': 39881, 'loss/train': 2.0333662033081055}
-03/05/2022 12:20:33 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/05/2022 12:20:37 - INFO - codeparrot_training - Step 39882: {'lr': 0.0004234362600217433, 'samples': 20420096, 'steps': 39882, 'loss/train': 1.5558302402496338}
-03/05/2022 12:20:40 - INFO - codeparrot_training - Step 39883: {'lr': 0.0004234324379556789, 'samples': 20420608, 'steps': 39883, 'loss/train': 2.177628517150879}
-03/05/2022 12:20:41 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/05/2022 12:20:46 - INFO - codeparrot_training - Step 39884: {'lr': 0.0004234286158114684, 'samples': 20421120, 'steps': 39884, 'loss/train': 1.6624616384506226}
-03/05/2022 12:20:49 - INFO - codeparrot_training - Step 39885: {'lr': 0.0004234247935891137, 'samples': 20421632, 'steps': 39885, 'loss/train': 1.874732255935669}
-03/05/2022 12:20:50 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/05/2022 12:20:54 - INFO - codeparrot_training - Step 39886: {'lr': 0.00042342097128861647, 'samples': 20422144, 'steps': 39886, 'loss/train': 1.5031816959381104}
-03/05/2022 12:20:57 - INFO - codeparrot_training - Step 39887: {'lr': 0.0004234171489099784, 'samples': 20422656, 'steps': 39887, 'loss/train': 0.5505874156951904}
-03/05/2022 12:20:58 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 12:21:02 - INFO - codeparrot_training - Step 39888: {'lr': 0.00042341332645320126, 'samples': 20423168, 'steps': 39888, 'loss/train': 1.8063597679138184}
-03/05/2022 12:21:06 - INFO - codeparrot_training - Step 39889: {'lr': 0.0004234095039182867, 'samples': 20423680, 'steps': 39889, 'loss/train': 1.8304696083068848}
-03/05/2022 12:21:06 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 12:21:11 - INFO - codeparrot_training - Step 39890: {'lr': 0.00042340568130523653, 'samples': 20424192, 'steps': 39890, 'loss/train': 1.739630103111267}
-03/05/2022 12:21:14 - INFO - codeparrot_training - Step 39891: {'lr': 0.0004234018586140525, 'samples': 20424704, 'steps': 39891, 'loss/train': 1.8207424879074097}
-03/05/2022 12:21:15 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/05/2022 12:21:19 - INFO - codeparrot_training - Step 39892: {'lr': 0.00042339803584473626, 'samples': 20425216, 'steps': 39892, 'loss/train': 0.5967734456062317}
-03/05/2022 12:21:23 - INFO - codeparrot_training - Step 39893: {'lr': 0.0004233942129972894, 'samples': 20425728, 'steps': 39893, 'loss/train': 1.7384788990020752}
-03/05/2022 12:21:23 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/05/2022 12:21:28 - INFO - codeparrot_training - Step 39894: {'lr': 0.00042339039007171386, 'samples': 20426240, 'steps': 39894, 'loss/train': 1.5008829832077026}
-03/05/2022 12:21:31 - INFO - codeparrot_training - Step 39895: {'lr': 0.00042338656706801135, 'samples': 20426752, 'steps': 39895, 'loss/train': 1.4284151792526245}
-03/05/2022 12:21:32 - INFO - codeparrot_training - Skipping example with length 138 (seq_length=1024)
-03/05/2022 12:21:36 - INFO - codeparrot_training - Step 39896: {'lr': 0.00042338274398618346, 'samples': 20427264, 'steps': 39896, 'loss/train': 1.5959205627441406}
-03/05/2022 12:21:39 - INFO - codeparrot_training - Step 39897: {'lr': 0.000423378920826232, 'samples': 20427776, 'steps': 39897, 'loss/train': 1.7940974235534668}
-03/05/2022 12:21:41 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/05/2022 12:21:45 - INFO - codeparrot_training - Step 39898: {'lr': 0.0004233750975881587, 'samples': 20428288, 'steps': 39898, 'loss/train': 0.6617526412010193}
-03/05/2022 12:21:48 - INFO - codeparrot_training - Step 39899: {'lr': 0.0004233712742719652, 'samples': 20428800, 'steps': 39899, 'loss/train': 1.0486679077148438}
-03/05/2022 12:21:49 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/05/2022 12:21:53 - INFO - codeparrot_training - Step 39900: {'lr': 0.0004233674508776533, 'samples': 20429312, 'steps': 39900, 'loss/train': 2.1548430919647217}
-03/05/2022 12:21:56 - INFO - codeparrot_training - Step 39901: {'lr': 0.00042336362740522473, 'samples': 20429824, 'steps': 39901, 'loss/train': 1.3083045482635498}
-03/05/2022 12:21:57 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/05/2022 12:22:02 - INFO - codeparrot_training - Step 39902: {'lr': 0.0004233598038546812, 'samples': 20430336, 'steps': 39902, 'loss/train': 1.673642873764038}
-03/05/2022 12:22:05 - INFO - codeparrot_training - Step 39903: {'lr': 0.0004233559802260244, 'samples': 20430848, 'steps': 39903, 'loss/train': 0.718710720539093}
-03/05/2022 12:22:06 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/05/2022 12:22:10 - INFO - codeparrot_training - Step 39904: {'lr': 0.000423352156519256, 'samples': 20431360, 'steps': 39904, 'loss/train': 1.0814151763916016}
-03/05/2022 12:22:13 - INFO - codeparrot_training - Step 39905: {'lr': 0.0004233483327343779, 'samples': 20431872, 'steps': 39905, 'loss/train': 0.939109206199646}
-03/05/2022 12:22:14 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/05/2022 12:22:18 - INFO - codeparrot_training - Step 39906: {'lr': 0.0004233445088713916, 'samples': 20432384, 'steps': 39906, 'loss/train': 1.83853280544281}
-03/05/2022 12:22:22 - INFO - codeparrot_training - Step 39907: {'lr': 0.000423340684930299, 'samples': 20432896, 'steps': 39907, 'loss/train': 1.2977674007415771}
-03/05/2022 12:22:23 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/05/2022 12:22:27 - INFO - codeparrot_training - Step 39908: {'lr': 0.0004233368609111018, 'samples': 20433408, 'steps': 39908, 'loss/train': 0.5411314964294434}
-03/05/2022 12:22:30 - INFO - codeparrot_training - Step 39909: {'lr': 0.00042333303681380165, 'samples': 20433920, 'steps': 39909, 'loss/train': 1.551157832145691}
-03/05/2022 12:22:31 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 12:22:35 - INFO - codeparrot_training - Step 39910: {'lr': 0.0004233292126384003, 'samples': 20434432, 'steps': 39910, 'loss/train': 2.000868797302246}
-03/05/2022 12:22:38 - INFO - codeparrot_training - Step 39911: {'lr': 0.00042332538838489955, 'samples': 20434944, 'steps': 39911, 'loss/train': 1.230790615081787}
-03/05/2022 12:22:39 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/05/2022 12:22:44 - INFO - codeparrot_training - Step 39912: {'lr': 0.0004233215640533009, 'samples': 20435456, 'steps': 39912, 'loss/train': 1.4630919694900513}
-03/05/2022 12:22:47 - INFO - codeparrot_training - Step 39913: {'lr': 0.0004233177396436064, 'samples': 20435968, 'steps': 39913, 'loss/train': 1.5157220363616943}
-03/05/2022 12:22:48 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/05/2022 12:22:52 - INFO - codeparrot_training - Step 39914: {'lr': 0.00042331391515581753, 'samples': 20436480, 'steps': 39914, 'loss/train': 2.0832200050354004}
-03/05/2022 12:22:55 - INFO - codeparrot_training - Step 39915: {'lr': 0.00042331009058993604, 'samples': 20436992, 'steps': 39915, 'loss/train': 2.32243013381958}
-03/05/2022 12:22:56 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/05/2022 12:23:01 - INFO - codeparrot_training - Step 39916: {'lr': 0.00042330626594596374, 'samples': 20437504, 'steps': 39916, 'loss/train': 1.1027271747589111}
-03/05/2022 12:23:04 - INFO - codeparrot_training - Step 39917: {'lr': 0.00042330244122390227, 'samples': 20438016, 'steps': 39917, 'loss/train': 5.9371418952941895}
-03/05/2022 12:23:05 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/05/2022 12:23:09 - INFO - codeparrot_training - Step 39918: {'lr': 0.00042329861642375347, 'samples': 20438528, 'steps': 39918, 'loss/train': 1.3348546028137207}
-03/05/2022 12:23:12 - INFO - codeparrot_training - Step 39919: {'lr': 0.00042329479154551897, 'samples': 20439040, 'steps': 39919, 'loss/train': 1.5316449403762817}
-03/05/2022 12:23:13 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/05/2022 12:23:18 - INFO - codeparrot_training - Step 39920: {'lr': 0.0004232909665892005, 'samples': 20439552, 'steps': 39920, 'loss/train': 1.6895968914031982}
-03/05/2022 12:23:21 - INFO - codeparrot_training - Step 39921: {'lr': 0.00042328714155479973, 'samples': 20440064, 'steps': 39921, 'loss/train': 1.8034844398498535}
-03/05/2022 12:23:22 - INFO - codeparrot_training - Skipping example with length 54 (seq_length=1024)
-03/05/2022 12:23:26 - INFO - codeparrot_training - Step 39922: {'lr': 0.0004232833164423185, 'samples': 20440576, 'steps': 39922, 'loss/train': 1.015723705291748}
-03/05/2022 12:23:29 - INFO - codeparrot_training - Step 39923: {'lr': 0.00042327949125175844, 'samples': 20441088, 'steps': 39923, 'loss/train': 0.6590255498886108}
-03/05/2022 12:23:30 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/05/2022 12:23:34 - INFO - codeparrot_training - Step 39924: {'lr': 0.0004232756659831214, 'samples': 20441600, 'steps': 39924, 'loss/train': 1.729242205619812}
-03/05/2022 12:23:38 - INFO - codeparrot_training - Step 39925: {'lr': 0.000423271840636409, 'samples': 20442112, 'steps': 39925, 'loss/train': 2.239431142807007}
-03/05/2022 12:23:38 - INFO - codeparrot_training - Skipping example with length 227 (seq_length=1024)
-03/05/2022 12:23:43 - INFO - codeparrot_training - Step 39926: {'lr': 0.00042326801521162295, 'samples': 20442624, 'steps': 39926, 'loss/train': 1.656354546546936}
-03/05/2022 12:23:46 - INFO - codeparrot_training - Step 39927: {'lr': 0.000423264189708765, 'samples': 20443136, 'steps': 39927, 'loss/train': 2.0217373371124268}
-03/05/2022 12:23:46 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 12:23:51 - INFO - codeparrot_training - Step 39928: {'lr': 0.0004232603641278369, 'samples': 20443648, 'steps': 39928, 'loss/train': 1.474001407623291}
-03/05/2022 12:23:54 - INFO - codeparrot_training - Step 39929: {'lr': 0.00042325653846884037, 'samples': 20444160, 'steps': 39929, 'loss/train': 0.26926377415657043}
-03/05/2022 12:23:55 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/05/2022 12:24:00 - INFO - codeparrot_training - Step 39930: {'lr': 0.00042325271273177707, 'samples': 20444672, 'steps': 39930, 'loss/train': 0.8286953568458557}
-03/05/2022 12:24:03 - INFO - codeparrot_training - Step 39931: {'lr': 0.0004232488869166488, 'samples': 20445184, 'steps': 39931, 'loss/train': 1.9618321657180786}
-03/05/2022 12:24:03 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 12:24:08 - INFO - codeparrot_training - Step 39932: {'lr': 0.0004232450610234573, 'samples': 20445696, 'steps': 39932, 'loss/train': 2.256718873977661}
-03/05/2022 12:24:12 - INFO - codeparrot_training - Step 39933: {'lr': 0.00042324123505220414, 'samples': 20446208, 'steps': 39933, 'loss/train': 1.951131820678711}
-03/05/2022 12:24:12 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 12:24:17 - INFO - codeparrot_training - Step 39934: {'lr': 0.0004232374090028912, 'samples': 20446720, 'steps': 39934, 'loss/train': 1.7848600149154663}
-03/05/2022 12:24:20 - INFO - codeparrot_training - Step 39935: {'lr': 0.00042323358287552017, 'samples': 20447232, 'steps': 39935, 'loss/train': 1.392089605331421}
-03/05/2022 12:24:20 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/05/2022 12:24:25 - INFO - codeparrot_training - Step 39936: {'lr': 0.0004232297566700928, 'samples': 20447744, 'steps': 39936, 'loss/train': 1.9984300136566162}
-03/05/2022 12:24:28 - INFO - codeparrot_training - Step 39937: {'lr': 0.00042322593038661074, 'samples': 20448256, 'steps': 39937, 'loss/train': 1.966238021850586}
-03/05/2022 12:24:29 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/05/2022 12:24:34 - INFO - codeparrot_training - Step 39938: {'lr': 0.0004232221040250758, 'samples': 20448768, 'steps': 39938, 'loss/train': 2.114082098007202}
-03/05/2022 12:24:37 - INFO - codeparrot_training - Step 39939: {'lr': 0.00042321827758548953, 'samples': 20449280, 'steps': 39939, 'loss/train': 2.5734524726867676}
-03/05/2022 12:24:37 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/05/2022 12:24:42 - INFO - codeparrot_training - Step 39940: {'lr': 0.00042321445106785385, 'samples': 20449792, 'steps': 39940, 'loss/train': 1.3465629816055298}
-03/05/2022 12:24:45 - INFO - codeparrot_training - Step 39941: {'lr': 0.0004232106244721704, 'samples': 20450304, 'steps': 39941, 'loss/train': 1.9060834646224976}
-03/05/2022 12:24:46 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/05/2022 12:24:51 - INFO - codeparrot_training - Step 39942: {'lr': 0.0004232067977984409, 'samples': 20450816, 'steps': 39942, 'loss/train': 2.0072197914123535}
-03/05/2022 12:24:54 - INFO - codeparrot_training - Step 39943: {'lr': 0.0004232029710466671, 'samples': 20451328, 'steps': 39943, 'loss/train': 1.4308189153671265}
-03/05/2022 12:24:54 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/05/2022 12:24:59 - INFO - codeparrot_training - Step 39944: {'lr': 0.00042319914421685067, 'samples': 20451840, 'steps': 39944, 'loss/train': 1.8284645080566406}
-03/05/2022 12:25:02 - INFO - codeparrot_training - Step 39945: {'lr': 0.0004231953173089935, 'samples': 20452352, 'steps': 39945, 'loss/train': 0.23620784282684326}
-03/05/2022 12:25:02 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/05/2022 12:25:08 - INFO - codeparrot_training - Step 39946: {'lr': 0.00042319149032309713, 'samples': 20452864, 'steps': 39946, 'loss/train': 1.7196310758590698}
-03/05/2022 12:25:11 - INFO - codeparrot_training - Step 39947: {'lr': 0.00042318766325916336, 'samples': 20453376, 'steps': 39947, 'loss/train': 0.1941543072462082}
-03/05/2022 12:25:11 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/05/2022 12:25:16 - INFO - codeparrot_training - Step 39948: {'lr': 0.00042318383611719386, 'samples': 20453888, 'steps': 39948, 'loss/train': 1.1694891452789307}
-03/05/2022 12:25:19 - INFO - codeparrot_training - Step 39949: {'lr': 0.00042318000889719044, 'samples': 20454400, 'steps': 39949, 'loss/train': 1.7814993858337402}
-03/05/2022 12:25:19 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/05/2022 12:25:25 - INFO - codeparrot_training - Step 39950: {'lr': 0.0004231761815991547, 'samples': 20454912, 'steps': 39950, 'loss/train': 2.330383062362671}
-03/05/2022 12:25:28 - INFO - codeparrot_training - Step 39951: {'lr': 0.0004231723542230885, 'samples': 20455424, 'steps': 39951, 'loss/train': 1.6803061962127686}
-03/05/2022 12:25:28 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/05/2022 12:25:33 - INFO - codeparrot_training - Step 39952: {'lr': 0.0004231685267689935, 'samples': 20455936, 'steps': 39952, 'loss/train': 1.5172549486160278}
-03/05/2022 12:25:37 - INFO - codeparrot_training - Step 39953: {'lr': 0.0004231646992368715, 'samples': 20456448, 'steps': 39953, 'loss/train': 0.7732665538787842}
-03/05/2022 12:25:37 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 12:25:42 - INFO - codeparrot_training - Step 39954: {'lr': 0.00042316087162672415, 'samples': 20456960, 'steps': 39954, 'loss/train': 1.7542901039123535}
-03/05/2022 12:25:45 - INFO - codeparrot_training - Step 39955: {'lr': 0.0004231570439385531, 'samples': 20457472, 'steps': 39955, 'loss/train': 1.266332745552063}
-03/05/2022 12:25:45 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/05/2022 12:25:50 - INFO - codeparrot_training - Step 39956: {'lr': 0.0004231532161723602, 'samples': 20457984, 'steps': 39956, 'loss/train': 1.6283401250839233}
-03/05/2022 12:25:54 - INFO - codeparrot_training - Step 39957: {'lr': 0.0004231493883281471, 'samples': 20458496, 'steps': 39957, 'loss/train': 1.474109411239624}
-03/05/2022 12:25:54 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/05/2022 12:25:59 - INFO - codeparrot_training - Step 39958: {'lr': 0.00042314556040591567, 'samples': 20459008, 'steps': 39958, 'loss/train': 1.4236756563186646}
-03/05/2022 12:26:02 - INFO - codeparrot_training - Step 39959: {'lr': 0.0004231417324056674, 'samples': 20459520, 'steps': 39959, 'loss/train': 1.503373622894287}
-03/05/2022 12:26:03 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/05/2022 12:26:07 - INFO - codeparrot_training - Step 39960: {'lr': 0.00042313790432740416, 'samples': 20460032, 'steps': 39960, 'loss/train': 1.8329119682312012}
-03/05/2022 12:26:11 - INFO - codeparrot_training - Step 39961: {'lr': 0.00042313407617112765, 'samples': 20460544, 'steps': 39961, 'loss/train': 1.270346760749817}
-03/05/2022 12:26:12 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/05/2022 12:26:16 - INFO - codeparrot_training - Step 39962: {'lr': 0.00042313024793683965, 'samples': 20461056, 'steps': 39962, 'loss/train': 1.2669391632080078}
-03/05/2022 12:26:19 - INFO - codeparrot_training - Step 39963: {'lr': 0.0004231264196245418, 'samples': 20461568, 'steps': 39963, 'loss/train': 0.5560345649719238}
-03/05/2022 12:26:21 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/05/2022 12:26:24 - INFO - codeparrot_training - Step 39964: {'lr': 0.00042312259123423584, 'samples': 20462080, 'steps': 39964, 'loss/train': 1.206254243850708}
-03/05/2022 12:26:27 - INFO - codeparrot_training - Step 39965: {'lr': 0.00042311876276592355, 'samples': 20462592, 'steps': 39965, 'loss/train': 2.0872819423675537}
-03/05/2022 12:26:29 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 12:26:33 - INFO - codeparrot_training - Step 39966: {'lr': 0.00042311493421960656, 'samples': 20463104, 'steps': 39966, 'loss/train': 1.771786093711853}
-03/05/2022 12:26:36 - INFO - codeparrot_training - Step 39967: {'lr': 0.0004231111055952867, 'samples': 20463616, 'steps': 39967, 'loss/train': 1.4013031721115112}
-03/05/2022 12:26:38 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/05/2022 12:26:41 - INFO - codeparrot_training - Step 39968: {'lr': 0.00042310727689296563, 'samples': 20464128, 'steps': 39968, 'loss/train': 1.8335704803466797}
-03/05/2022 12:26:44 - INFO - codeparrot_training - Step 39969: {'lr': 0.0004231034481126451, 'samples': 20464640, 'steps': 39969, 'loss/train': 2.144958019256592}
-03/05/2022 12:26:46 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 12:26:50 - INFO - codeparrot_training - Step 39970: {'lr': 0.0004230996192543268, 'samples': 20465152, 'steps': 39970, 'loss/train': 2.2452504634857178}
-03/05/2022 12:26:53 - INFO - codeparrot_training - Step 39971: {'lr': 0.0004230957903180125, 'samples': 20465664, 'steps': 39971, 'loss/train': 1.6215338706970215}
-03/05/2022 12:26:55 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/05/2022 12:26:58 - INFO - codeparrot_training - Step 39972: {'lr': 0.00042309196130370396, 'samples': 20466176, 'steps': 39972, 'loss/train': 2.400557518005371}
-03/05/2022 12:27:01 - INFO - codeparrot_training - Step 39973: {'lr': 0.00042308813221140275, 'samples': 20466688, 'steps': 39973, 'loss/train': 1.5071148872375488}
-03/05/2022 12:27:04 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/05/2022 12:27:06 - INFO - codeparrot_training - Step 39974: {'lr': 0.00042308430304111076, 'samples': 20467200, 'steps': 39974, 'loss/train': 1.9544938802719116}
-03/05/2022 12:27:10 - INFO - codeparrot_training - Step 39975: {'lr': 0.00042308047379282967, 'samples': 20467712, 'steps': 39975, 'loss/train': 2.3968615531921387}
-03/05/2022 12:27:12 - INFO - codeparrot_training - Skipping example with length 411 (seq_length=1024)
-03/05/2022 12:27:15 - INFO - codeparrot_training - Step 39976: {'lr': 0.00042307664446656116, 'samples': 20468224, 'steps': 39976, 'loss/train': 1.7354118824005127}
-03/05/2022 12:27:18 - INFO - codeparrot_training - Step 39977: {'lr': 0.000423072815062307, 'samples': 20468736, 'steps': 39977, 'loss/train': 1.2915846109390259}
-03/05/2022 12:27:20 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/05/2022 12:27:23 - INFO - codeparrot_training - Step 39978: {'lr': 0.0004230689855800689, 'samples': 20469248, 'steps': 39978, 'loss/train': 2.4140164852142334}
-03/05/2022 12:27:26 - INFO - codeparrot_training - Step 39979: {'lr': 0.0004230651560198486, 'samples': 20469760, 'steps': 39979, 'loss/train': 2.227933883666992}
-03/05/2022 12:27:28 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/05/2022 12:27:32 - INFO - codeparrot_training - Step 39980: {'lr': 0.0004230613263816478, 'samples': 20470272, 'steps': 39980, 'loss/train': 1.7130097150802612}
-03/05/2022 12:27:35 - INFO - codeparrot_training - Step 39981: {'lr': 0.0004230574966654682, 'samples': 20470784, 'steps': 39981, 'loss/train': 1.5346124172210693}
-03/05/2022 12:27:37 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/05/2022 12:27:40 - INFO - codeparrot_training - Step 39982: {'lr': 0.0004230536668713116, 'samples': 20471296, 'steps': 39982, 'loss/train': 1.1819233894348145}
-03/05/2022 12:27:43 - INFO - codeparrot_training - Step 39983: {'lr': 0.00042304983699917965, 'samples': 20471808, 'steps': 39983, 'loss/train': 1.9265443086624146}
-03/05/2022 12:27:45 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/05/2022 12:27:49 - INFO - codeparrot_training - Step 39984: {'lr': 0.00042304600704907416, 'samples': 20472320, 'steps': 39984, 'loss/train': 1.5331470966339111}
-03/05/2022 12:27:52 - INFO - codeparrot_training - Step 39985: {'lr': 0.0004230421770209968, 'samples': 20472832, 'steps': 39985, 'loss/train': 1.3011888265609741}
-03/05/2022 12:27:54 - INFO - codeparrot_training - Skipping example with length 1019 (seq_length=1024)
-03/05/2022 12:27:57 - INFO - codeparrot_training - Step 39986: {'lr': 0.0004230383469149493, 'samples': 20473344, 'steps': 39986, 'loss/train': 0.3527682423591614}
-03/05/2022 12:28:00 - INFO - codeparrot_training - Step 39987: {'lr': 0.0004230345167309334, 'samples': 20473856, 'steps': 39987, 'loss/train': 2.1957151889801025}
-03/05/2022 12:28:02 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/05/2022 12:28:06 - INFO - codeparrot_training - Step 39988: {'lr': 0.00042303068646895077, 'samples': 20474368, 'steps': 39988, 'loss/train': 0.8951796889305115}
-03/05/2022 12:28:09 - INFO - codeparrot_training - Step 39989: {'lr': 0.0004230268561290032, 'samples': 20474880, 'steps': 39989, 'loss/train': 2.2042088508605957}
-03/05/2022 12:28:11 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/05/2022 12:28:14 - INFO - codeparrot_training - Step 39990: {'lr': 0.0004230230257110924, 'samples': 20475392, 'steps': 39990, 'loss/train': 1.936219334602356}
-03/05/2022 12:28:17 - INFO - codeparrot_training - Step 39991: {'lr': 0.00042301919521522014, 'samples': 20475904, 'steps': 39991, 'loss/train': 1.3299697637557983}
-03/05/2022 12:28:19 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/05/2022 12:28:23 - INFO - codeparrot_training - Step 39992: {'lr': 0.0004230153646413881, 'samples': 20476416, 'steps': 39992, 'loss/train': 1.776450753211975}
-03/05/2022 12:28:26 - INFO - codeparrot_training - Step 39993: {'lr': 0.000423011533989598, 'samples': 20476928, 'steps': 39993, 'loss/train': 1.0705969333648682}
-03/05/2022 12:28:29 - INFO - codeparrot_training - Step 39994: {'lr': 0.0004230077032598515, 'samples': 20477440, 'steps': 39994, 'loss/train': 1.501052737236023}
-03/05/2022 12:28:30 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 12:28:34 - INFO - codeparrot_training - Step 39995: {'lr': 0.00042300387245215043, 'samples': 20477952, 'steps': 39995, 'loss/train': 1.7614675760269165}
-03/05/2022 12:28:37 - INFO - codeparrot_training - Step 39996: {'lr': 0.00042300004156649654, 'samples': 20478464, 'steps': 39996, 'loss/train': 1.4517847299575806}
-03/05/2022 12:28:38 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/05/2022 12:28:43 - INFO - codeparrot_training - Step 39997: {'lr': 0.0004229962106028914, 'samples': 20478976, 'steps': 39997, 'loss/train': 1.92573881149292}
-03/05/2022 12:28:46 - INFO - codeparrot_training - Step 39998: {'lr': 0.0004229923795613369, 'samples': 20479488, 'steps': 39998, 'loss/train': 1.906799554824829}
-03/05/2022 12:28:46 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/05/2022 12:28:51 - INFO - codeparrot_training - Step 39999: {'lr': 0.00042298854844183476, 'samples': 20480000, 'steps': 39999, 'loss/train': 1.882041096687317}
-03/05/2022 12:28:51 - INFO - codeparrot_training - Evaluating and saving model checkpoint
-03/05/2022 12:29:06 - WARNING - huggingface_hub.repository - Several commits (8) will be pushed upstream.
-03/05/2022 12:29:06 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
-03/05/2022 12:29:29 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/cm_code_clippy
-   eeb78f1..7a07393  glowing-puddle-3 -> glowing-puddle-3
-
-03/05/2022 12:29:33 - INFO - codeparrot_training - Step 40000: {'lr': 0.0004229847172443866, 'samples': 20480512, 'steps': 40000, 'loss/train': 1.982017993927002}
-03/05/2022 12:29:34 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 12:29:38 - INFO - codeparrot_training - Step 40001: {'lr': 0.0004229808859689941, 'samples': 20481024, 'steps': 40001, 'loss/train': 1.7813818454742432}
-03/05/2022 12:29:41 - INFO - codeparrot_training - Step 40002: {'lr': 0.0004229770546156592, 'samples': 20481536, 'steps': 40002, 'loss/train': 1.8193222284317017}
-03/05/2022 12:29:42 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/05/2022 12:29:47 - INFO - codeparrot_training - Step 40003: {'lr': 0.00042297322318438345, 'samples': 20482048, 'steps': 40003, 'loss/train': 0.20749032497406006}
-03/05/2022 12:29:50 - INFO - codeparrot_training - Step 40004: {'lr': 0.0004229693916751687, 'samples': 20482560, 'steps': 40004, 'loss/train': 0.14177154004573822}
-03/05/2022 12:29:51 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 12:29:55 - INFO - codeparrot_training - Step 40005: {'lr': 0.00042296556008801663, 'samples': 20483072, 'steps': 40005, 'loss/train': 1.8099523782730103}
-03/05/2022 12:29:59 - INFO - codeparrot_training - Step 40006: {'lr': 0.0004229617284229289, 'samples': 20483584, 'steps': 40006, 'loss/train': 1.6427102088928223}
-03/05/2022 12:29:59 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/05/2022 12:30:04 - INFO - codeparrot_training - Step 40007: {'lr': 0.00042295789667990726, 'samples': 20484096, 'steps': 40007, 'loss/train': 0.9013746976852417}
-03/05/2022 12:30:07 - INFO - codeparrot_training - Step 40008: {'lr': 0.00042295406485895346, 'samples': 20484608, 'steps': 40008, 'loss/train': 1.6865116357803345}
-03/05/2022 12:30:08 - INFO - codeparrot_training - Skipping example with length 382 (seq_length=1024)
-03/05/2022 12:30:13 - INFO - codeparrot_training - Step 40009: {'lr': 0.0004229502329600692, 'samples': 20485120, 'steps': 40009, 'loss/train': 1.8931599855422974}
-03/05/2022 12:30:16 - INFO - codeparrot_training - Step 40010: {'lr': 0.0004229464009832563, 'samples': 20485632, 'steps': 40010, 'loss/train': 2.002829074859619}
-03/05/2022 12:30:16 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 12:30:21 - INFO - codeparrot_training - Step 40011: {'lr': 0.0004229425689285163, 'samples': 20486144, 'steps': 40011, 'loss/train': 1.4560149908065796}
-03/05/2022 12:30:24 - INFO - codeparrot_training - Step 40012: {'lr': 0.00042293873679585125, 'samples': 20486656, 'steps': 40012, 'loss/train': 1.9236010313034058}
-03/05/2022 12:30:25 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/05/2022 12:30:30 - INFO - codeparrot_training - Step 40013: {'lr': 0.00042293490458526257, 'samples': 20487168, 'steps': 40013, 'loss/train': 1.3040850162506104}
-03/05/2022 12:30:33 - INFO - codeparrot_training - Step 40014: {'lr': 0.0004229310722967521, 'samples': 20487680, 'steps': 40014, 'loss/train': 1.6971408128738403}
-03/05/2022 12:30:33 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 12:30:38 - INFO - codeparrot_training - Step 40015: {'lr': 0.00042292723993032157, 'samples': 20488192, 'steps': 40015, 'loss/train': 7.169426918029785}
-03/05/2022 12:30:42 - INFO - codeparrot_training - Step 40016: {'lr': 0.0004229234074859726, 'samples': 20488704, 'steps': 40016, 'loss/train': 1.8417553901672363}
-03/05/2022 12:30:43 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/05/2022 12:30:47 - INFO - codeparrot_training - Step 40017: {'lr': 0.00042291957496370713, 'samples': 20489216, 'steps': 40017, 'loss/train': 1.4970208406448364}
-03/05/2022 12:30:50 - INFO - codeparrot_training - Step 40018: {'lr': 0.0004229157423635267, 'samples': 20489728, 'steps': 40018, 'loss/train': 1.6064833402633667}
-03/05/2022 12:30:51 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/05/2022 12:30:55 - INFO - codeparrot_training - Step 40019: {'lr': 0.00042291190968543315, 'samples': 20490240, 'steps': 40019, 'loss/train': 1.817595362663269}
-03/05/2022 12:30:58 - INFO - codeparrot_training - Step 40020: {'lr': 0.0004229080769294281, 'samples': 20490752, 'steps': 40020, 'loss/train': 2.1051650047302246}
-03/05/2022 12:30:59 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/05/2022 12:31:04 - INFO - codeparrot_training - Step 40021: {'lr': 0.00042290424409551343, 'samples': 20491264, 'steps': 40021, 'loss/train': 2.0216541290283203}
-03/05/2022 12:31:07 - INFO - codeparrot_training - Step 40022: {'lr': 0.0004229004111836907, 'samples': 20491776, 'steps': 40022, 'loss/train': 0.9492252469062805}
-03/05/2022 12:31:08 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/05/2022 12:31:12 - INFO - codeparrot_training - Step 40023: {'lr': 0.0004228965781939617, 'samples': 20492288, 'steps': 40023, 'loss/train': 1.4902007579803467}
-03/05/2022 12:31:15 - INFO - codeparrot_training - Step 40024: {'lr': 0.00042289274512632817, 'samples': 20492800, 'steps': 40024, 'loss/train': 1.2674927711486816}
-03/05/2022 12:31:16 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/05/2022 12:31:21 - INFO - codeparrot_training - Step 40025: {'lr': 0.00042288891198079194, 'samples': 20493312, 'steps': 40025, 'loss/train': 1.5982645750045776}
-03/05/2022 12:31:24 - INFO - codeparrot_training - Step 40026: {'lr': 0.00042288507875735455, 'samples': 20493824, 'steps': 40026, 'loss/train': 1.1172744035720825}
-03/05/2022 12:31:25 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/05/2022 12:31:29 - INFO - codeparrot_training - Step 40027: {'lr': 0.0004228812454560178, 'samples': 20494336, 'steps': 40027, 'loss/train': 1.5279732942581177}
-03/05/2022 12:31:32 - INFO - codeparrot_training - Step 40028: {'lr': 0.0004228774120767835, 'samples': 20494848, 'steps': 40028, 'loss/train': 1.5613210201263428}
-03/05/2022 12:31:33 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/05/2022 12:31:37 - INFO - codeparrot_training - Step 40029: {'lr': 0.00042287357861965326, 'samples': 20495360, 'steps': 40029, 'loss/train': 2.1684770584106445}
-03/05/2022 12:31:41 - INFO - codeparrot_training - Step 40030: {'lr': 0.00042286974508462885, 'samples': 20495872, 'steps': 40030, 'loss/train': 1.9535554647445679}
-03/05/2022 12:31:41 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 12:31:46 - INFO - codeparrot_training - Step 40031: {'lr': 0.000422865911471712, 'samples': 20496384, 'steps': 40031, 'loss/train': 1.8874787092208862}
-03/05/2022 12:31:49 - INFO - codeparrot_training - Step 40032: {'lr': 0.00042286207778090447, 'samples': 20496896, 'steps': 40032, 'loss/train': 1.6239120960235596}
-03/05/2022 12:31:49 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/05/2022 12:31:54 - INFO - codeparrot_training - Step 40033: {'lr': 0.00042285824401220787, 'samples': 20497408, 'steps': 40033, 'loss/train': 1.7153030633926392}
-03/05/2022 12:31:57 - INFO - codeparrot_training - Step 40034: {'lr': 0.0004228544101656241, 'samples': 20497920, 'steps': 40034, 'loss/train': 1.1692639589309692}
-03/05/2022 12:31:58 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/05/2022 12:32:03 - INFO - codeparrot_training - Step 40035: {'lr': 0.00042285057624115473, 'samples': 20498432, 'steps': 40035, 'loss/train': 1.8297556638717651}
-03/05/2022 12:32:06 - INFO - codeparrot_training - Step 40036: {'lr': 0.0004228467422388016, 'samples': 20498944, 'steps': 40036, 'loss/train': 2.065459728240967}
-03/05/2022 12:32:07 - INFO - codeparrot_training - Skipping example with length 217 (seq_length=1024)
-03/05/2022 12:32:11 - INFO - codeparrot_training - Step 40037: {'lr': 0.0004228429081585664, 'samples': 20499456, 'steps': 40037, 'loss/train': 1.5635398626327515}
-03/05/2022 12:32:14 - INFO - codeparrot_training - Step 40038: {'lr': 0.00042283907400045084, 'samples': 20499968, 'steps': 40038, 'loss/train': 2.088895082473755}
-03/05/2022 12:32:15 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/05/2022 12:32:20 - INFO - codeparrot_training - Step 40039: {'lr': 0.0004228352397644567, 'samples': 20500480, 'steps': 40039, 'loss/train': 0.4609100818634033}
-03/05/2022 12:32:23 - INFO - codeparrot_training - Step 40040: {'lr': 0.0004228314054505856, 'samples': 20500992, 'steps': 40040, 'loss/train': 1.338619589805603}
-03/05/2022 12:32:24 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/05/2022 12:32:28 - INFO - codeparrot_training - Step 40041: {'lr': 0.0004228275710588394, 'samples': 20501504, 'steps': 40041, 'loss/train': 2.011685848236084}
-03/05/2022 12:32:31 - INFO - codeparrot_training - Step 40042: {'lr': 0.0004228237365892197, 'samples': 20502016, 'steps': 40042, 'loss/train': 0.653678834438324}
-03/05/2022 12:32:32 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/05/2022 12:32:36 - INFO - codeparrot_training - Step 40043: {'lr': 0.00042281990204172837, 'samples': 20502528, 'steps': 40043, 'loss/train': 2.355133295059204}
-03/05/2022 12:32:40 - INFO - codeparrot_training - Step 40044: {'lr': 0.000422816067416367, 'samples': 20503040, 'steps': 40044, 'loss/train': 2.189216375350952}
-03/05/2022 12:32:40 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/05/2022 12:32:45 - INFO - codeparrot_training - Step 40045: {'lr': 0.00042281223271313734, 'samples': 20503552, 'steps': 40045, 'loss/train': 1.884752869606018}
-03/05/2022 12:32:48 - INFO - codeparrot_training - Step 40046: {'lr': 0.0004228083979320412, 'samples': 20504064, 'steps': 40046, 'loss/train': 1.824157953262329}
-03/05/2022 12:32:49 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/05/2022 12:32:53 - INFO - codeparrot_training - Step 40047: {'lr': 0.00042280456307308034, 'samples': 20504576, 'steps': 40047, 'loss/train': 2.1382288932800293}
-03/05/2022 12:32:57 - INFO - codeparrot_training - Step 40048: {'lr': 0.0004228007281362563, 'samples': 20505088, 'steps': 40048, 'loss/train': 2.0494191646575928}
-03/05/2022 12:32:58 - INFO - codeparrot_training - Skipping example with length 396 (seq_length=1024)
-03/05/2022 12:33:02 - INFO - codeparrot_training - Step 40049: {'lr': 0.0004227968931215709, 'samples': 20505600, 'steps': 40049, 'loss/train': 1.1707737445831299}
-03/05/2022 12:33:05 - INFO - codeparrot_training - Step 40050: {'lr': 0.000422793058029026, 'samples': 20506112, 'steps': 40050, 'loss/train': 1.9375284910202026}
-03/05/2022 12:33:06 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/05/2022 12:33:10 - INFO - codeparrot_training - Step 40051: {'lr': 0.0004227892228586231, 'samples': 20506624, 'steps': 40051, 'loss/train': 2.786980628967285}
-03/05/2022 12:33:14 - INFO - codeparrot_training - Step 40052: {'lr': 0.0004227853876103641, 'samples': 20507136, 'steps': 40052, 'loss/train': 1.707208514213562}
-03/05/2022 12:33:15 - INFO - codeparrot_training - Skipping example with length 945 (seq_length=1024)
-03/05/2022 12:33:19 - INFO - codeparrot_training - Step 40053: {'lr': 0.0004227815522842507, 'samples': 20507648, 'steps': 40053, 'loss/train': 1.6560243368148804}
-03/05/2022 12:33:22 - INFO - codeparrot_training - Step 40054: {'lr': 0.00042277771688028457, 'samples': 20508160, 'steps': 40054, 'loss/train': 1.6504963636398315}
-03/05/2022 12:33:23 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/05/2022 12:33:28 - INFO - codeparrot_training - Step 40055: {'lr': 0.0004227738813984675, 'samples': 20508672, 'steps': 40055, 'loss/train': 1.3405498266220093}
-03/05/2022 12:33:31 - INFO - codeparrot_training - Step 40056: {'lr': 0.0004227700458388011, 'samples': 20509184, 'steps': 40056, 'loss/train': 1.5012426376342773}
-03/05/2022 12:33:32 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/05/2022 12:33:36 - INFO - codeparrot_training - Step 40057: {'lr': 0.00042276621020128724, 'samples': 20509696, 'steps': 40057, 'loss/train': 1.8666256666183472}
-03/05/2022 12:33:39 - INFO - codeparrot_training - Step 40058: {'lr': 0.0004227623744859276, 'samples': 20510208, 'steps': 40058, 'loss/train': 2.1589877605438232}
-03/05/2022 12:33:40 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/05/2022 12:33:44 - INFO - codeparrot_training - Step 40059: {'lr': 0.0004227585386927239, 'samples': 20510720, 'steps': 40059, 'loss/train': 1.2905285358428955}
-03/05/2022 12:33:47 - INFO - codeparrot_training - Step 40060: {'lr': 0.0004227547028216778, 'samples': 20511232, 'steps': 40060, 'loss/train': 1.4985536336898804}
-03/05/2022 12:33:48 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/05/2022 12:33:53 - INFO - codeparrot_training - Step 40061: {'lr': 0.00042275086687279116, 'samples': 20511744, 'steps': 40061, 'loss/train': 1.3976259231567383}
-03/05/2022 12:33:56 - INFO - codeparrot_training - Step 40062: {'lr': 0.0004227470308460657, 'samples': 20512256, 'steps': 40062, 'loss/train': 1.9555387496948242}
-03/05/2022 12:33:57 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 12:34:01 - INFO - codeparrot_training - Step 40063: {'lr': 0.000422743194741503, 'samples': 20512768, 'steps': 40063, 'loss/train': 0.6598406434059143}
-03/05/2022 12:34:04 - INFO - codeparrot_training - Step 40064: {'lr': 0.00042273935855910487, 'samples': 20513280, 'steps': 40064, 'loss/train': 1.7276569604873657}
-03/05/2022 12:34:05 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/05/2022 12:34:09 - INFO - codeparrot_training - Step 40065: {'lr': 0.00042273552229887313, 'samples': 20513792, 'steps': 40065, 'loss/train': 1.597737431526184}
-03/05/2022 12:34:13 - INFO - codeparrot_training - Step 40066: {'lr': 0.00042273168596080934, 'samples': 20514304, 'steps': 40066, 'loss/train': 2.3827953338623047}
-03/05/2022 12:34:13 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 12:34:18 - INFO - codeparrot_training - Step 40067: {'lr': 0.0004227278495449154, 'samples': 20514816, 'steps': 40067, 'loss/train': 1.7025450468063354}
-03/05/2022 12:34:21 - INFO - codeparrot_training - Step 40068: {'lr': 0.0004227240130511929, 'samples': 20515328, 'steps': 40068, 'loss/train': 1.2661598920822144}
-03/05/2022 12:34:22 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/05/2022 12:34:26 - INFO - codeparrot_training - Step 40069: {'lr': 0.0004227201764796437, 'samples': 20515840, 'steps': 40069, 'loss/train': 1.8638112545013428}
-03/05/2022 12:34:29 - INFO - codeparrot_training - Step 40070: {'lr': 0.00042271633983026935, 'samples': 20516352, 'steps': 40070, 'loss/train': 1.9659042358398438}
-03/05/2022 12:34:30 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/05/2022 12:34:35 - INFO - codeparrot_training - Step 40071: {'lr': 0.00042271250310307174, 'samples': 20516864, 'steps': 40071, 'loss/train': 1.7575346231460571}
-03/05/2022 12:34:38 - INFO - codeparrot_training - Step 40072: {'lr': 0.0004227086662980525, 'samples': 20517376, 'steps': 40072, 'loss/train': 2.0858993530273438}
-03/05/2022 12:34:39 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/05/2022 12:34:43 - INFO - codeparrot_training - Step 40073: {'lr': 0.00042270482941521347, 'samples': 20517888, 'steps': 40073, 'loss/train': 1.6693480014801025}
-03/05/2022 12:34:46 - INFO - codeparrot_training - Step 40074: {'lr': 0.0004227009924545563, 'samples': 20518400, 'steps': 40074, 'loss/train': 1.7536224126815796}
-03/05/2022 12:34:47 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/05/2022 12:34:52 - INFO - codeparrot_training - Step 40075: {'lr': 0.00042269715541608265, 'samples': 20518912, 'steps': 40075, 'loss/train': 1.4964795112609863}
-03/05/2022 12:34:55 - INFO - codeparrot_training - Step 40076: {'lr': 0.0004226933182997944, 'samples': 20519424, 'steps': 40076, 'loss/train': 1.1757622957229614}
-03/05/2022 12:34:56 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/05/2022 12:35:00 - INFO - codeparrot_training - Step 40077: {'lr': 0.00042268948110569317, 'samples': 20519936, 'steps': 40077, 'loss/train': 1.8408674001693726}
-03/05/2022 12:35:04 - INFO - codeparrot_training - Step 40078: {'lr': 0.00042268564383378073, 'samples': 20520448, 'steps': 40078, 'loss/train': 1.9779270887374878}
-03/05/2022 12:35:06 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/05/2022 12:35:09 - INFO - codeparrot_training - Step 40079: {'lr': 0.00042268180648405884, 'samples': 20520960, 'steps': 40079, 'loss/train': 1.5238009691238403}
-03/05/2022 12:35:12 - INFO - codeparrot_training - Step 40080: {'lr': 0.00042267796905652924, 'samples': 20521472, 'steps': 40080, 'loss/train': 1.7198408842086792}
-03/05/2022 12:35:15 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/05/2022 12:35:18 - INFO - codeparrot_training - Step 40081: {'lr': 0.0004226741315511935, 'samples': 20521984, 'steps': 40081, 'loss/train': 1.4137829542160034}
-03/05/2022 12:35:21 - INFO - codeparrot_training - Step 40082: {'lr': 0.00042267029396805345, 'samples': 20522496, 'steps': 40082, 'loss/train': 1.7004022598266602}
-03/05/2022 12:35:23 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/05/2022 12:35:26 - INFO - codeparrot_training - Step 40083: {'lr': 0.0004226664563071109, 'samples': 20523008, 'steps': 40083, 'loss/train': 1.3843481540679932}
-03/05/2022 12:35:29 - INFO - codeparrot_training - Step 40084: {'lr': 0.0004226626185683675, 'samples': 20523520, 'steps': 40084, 'loss/train': 1.5956250429153442}
-03/05/2022 12:35:32 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/05/2022 12:35:35 - INFO - codeparrot_training - Step 40085: {'lr': 0.00042265878075182497, 'samples': 20524032, 'steps': 40085, 'loss/train': 3.077409029006958}
-03/05/2022 12:35:38 - INFO - codeparrot_training - Step 40086: {'lr': 0.0004226549428574851, 'samples': 20524544, 'steps': 40086, 'loss/train': 1.7898083925247192}
-03/05/2022 12:35:40 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/05/2022 12:35:43 - INFO - codeparrot_training - Step 40087: {'lr': 0.0004226511048853495, 'samples': 20525056, 'steps': 40087, 'loss/train': 1.8427422046661377}
-03/05/2022 12:35:46 - INFO - codeparrot_training - Step 40088: {'lr': 0.00042264726683542, 'samples': 20525568, 'steps': 40088, 'loss/train': 1.1510858535766602}
-03/05/2022 12:35:48 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/05/2022 12:35:51 - INFO - codeparrot_training - Step 40089: {'lr': 0.00042264342870769835, 'samples': 20526080, 'steps': 40089, 'loss/train': 1.1904371976852417}
-03/05/2022 12:35:55 - INFO - codeparrot_training - Step 40090: {'lr': 0.0004226395905021862, 'samples': 20526592, 'steps': 40090, 'loss/train': 3.0607223510742188}
-03/05/2022 12:35:57 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/05/2022 12:36:00 - INFO - codeparrot_training - Step 40091: {'lr': 0.0004226357522188853, 'samples': 20527104, 'steps': 40091, 'loss/train': 1.9740082025527954}
-03/05/2022 12:36:03 - INFO - codeparrot_training - Step 40092: {'lr': 0.0004226319138577974, 'samples': 20527616, 'steps': 40092, 'loss/train': 0.8607341647148132}
-03/05/2022 12:36:05 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/05/2022 12:36:08 - INFO - codeparrot_training - Step 40093: {'lr': 0.0004226280754189243, 'samples': 20528128, 'steps': 40093, 'loss/train': 2.1337058544158936}
-03/05/2022 12:36:11 - INFO - codeparrot_training - Step 40094: {'lr': 0.0004226242369022676, 'samples': 20528640, 'steps': 40094, 'loss/train': 1.6986380815505981}
-03/05/2022 12:36:14 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/05/2022 12:36:17 - INFO - codeparrot_training - Step 40095: {'lr': 0.00042262039830782906, 'samples': 20529152, 'steps': 40095, 'loss/train': 1.4544637203216553}
-03/05/2022 12:36:20 - INFO - codeparrot_training - Step 40096: {'lr': 0.00042261655963561043, 'samples': 20529664, 'steps': 40096, 'loss/train': 0.5990719199180603}
-03/05/2022 12:36:22 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/05/2022 12:36:25 - INFO - codeparrot_training - Step 40097: {'lr': 0.0004226127208856134, 'samples': 20530176, 'steps': 40097, 'loss/train': 1.8629103899002075}
-03/05/2022 12:36:28 - INFO - codeparrot_training - Step 40098: {'lr': 0.0004226088820578399, 'samples': 20530688, 'steps': 40098, 'loss/train': 2.90800142288208}
-03/05/2022 12:36:30 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/05/2022 12:36:34 - INFO - codeparrot_training - Step 40099: {'lr': 0.00042260504315229136, 'samples': 20531200, 'steps': 40099, 'loss/train': 2.4964165687561035}
-03/05/2022 12:36:37 - INFO - codeparrot_training - Step 40100: {'lr': 0.00042260120416896975, 'samples': 20531712, 'steps': 40100, 'loss/train': 1.4463250637054443}
-03/05/2022 12:36:39 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 12:36:42 - INFO - codeparrot_training - Step 40101: {'lr': 0.0004225973651078766, 'samples': 20532224, 'steps': 40101, 'loss/train': 2.009486198425293}
-03/05/2022 12:36:45 - INFO - codeparrot_training - Step 40102: {'lr': 0.0004225935259690138, 'samples': 20532736, 'steps': 40102, 'loss/train': 6.392016410827637}
-03/05/2022 12:36:49 - INFO - codeparrot_training - Step 40103: {'lr': 0.00042258968675238295, 'samples': 20533248, 'steps': 40103, 'loss/train': 1.937026858329773}
-03/05/2022 12:36:49 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/05/2022 12:36:54 - INFO - codeparrot_training - Step 40104: {'lr': 0.00042258584745798595, 'samples': 20533760, 'steps': 40104, 'loss/train': 2.071216344833374}
-03/05/2022 12:36:57 - INFO - codeparrot_training - Step 40105: {'lr': 0.00042258200808582434, 'samples': 20534272, 'steps': 40105, 'loss/train': 1.7090741395950317}
-03/05/2022 12:36:57 - INFO - codeparrot_training - Skipping example with length 983 (seq_length=1024)
-03/05/2022 12:37:02 - INFO - codeparrot_training - Step 40106: {'lr': 0.00042257816863590006, 'samples': 20534784, 'steps': 40106, 'loss/train': 2.1346094608306885}
-03/05/2022 12:37:05 - INFO - codeparrot_training - Step 40107: {'lr': 0.0004225743291082146, 'samples': 20535296, 'steps': 40107, 'loss/train': 1.561100721359253}
-03/05/2022 12:37:06 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/05/2022 12:37:11 - INFO - codeparrot_training - Step 40108: {'lr': 0.0004225704895027699, 'samples': 20535808, 'steps': 40108, 'loss/train': 1.9655472040176392}
-03/05/2022 12:37:14 - INFO - codeparrot_training - Step 40109: {'lr': 0.0004225666498195675, 'samples': 20536320, 'steps': 40109, 'loss/train': 1.828470230102539}
-03/05/2022 12:37:15 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/05/2022 12:37:19 - INFO - codeparrot_training - Step 40110: {'lr': 0.0004225628100586093, 'samples': 20536832, 'steps': 40110, 'loss/train': 2.2743496894836426}
-03/05/2022 12:37:22 - INFO - codeparrot_training - Step 40111: {'lr': 0.00042255897021989695, 'samples': 20537344, 'steps': 40111, 'loss/train': 0.999409019947052}
-03/05/2022 12:37:23 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 12:37:28 - INFO - codeparrot_training - Step 40112: {'lr': 0.0004225551303034322, 'samples': 20537856, 'steps': 40112, 'loss/train': 3.1471493244171143}
-03/05/2022 12:37:31 - INFO - codeparrot_training - Step 40113: {'lr': 0.00042255129030921673, 'samples': 20538368, 'steps': 40113, 'loss/train': 0.32940083742141724}
-03/05/2022 12:37:32 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/05/2022 12:37:36 - INFO - codeparrot_training - Step 40114: {'lr': 0.0004225474502372524, 'samples': 20538880, 'steps': 40114, 'loss/train': 1.0865380764007568}
-03/05/2022 12:37:39 - INFO - codeparrot_training - Step 40115: {'lr': 0.00042254361008754076, 'samples': 20539392, 'steps': 40115, 'loss/train': 1.8155457973480225}
-03/05/2022 12:37:44 - INFO - codeparrot_training - Step 40116: {'lr': 0.0004225397698600837, 'samples': 20539904, 'steps': 40116, 'loss/train': 2.086334228515625}
-03/05/2022 12:37:48 - INFO - codeparrot_training - Step 40117: {'lr': 0.0004225359295548828, 'samples': 20540416, 'steps': 40117, 'loss/train': 1.52240788936615}
-03/05/2022 12:37:49 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/05/2022 12:37:53 - INFO - codeparrot_training - Step 40118: {'lr': 0.0004225320891719399, 'samples': 20540928, 'steps': 40118, 'loss/train': 1.6929336786270142}
-03/05/2022 12:37:56 - INFO - codeparrot_training - Step 40119: {'lr': 0.0004225282487112567, 'samples': 20541440, 'steps': 40119, 'loss/train': 2.1643548011779785}
-03/05/2022 12:37:57 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/05/2022 12:38:01 - INFO - codeparrot_training - Step 40120: {'lr': 0.000422524408172835, 'samples': 20541952, 'steps': 40120, 'loss/train': 1.766913652420044}
-03/05/2022 12:38:05 - INFO - codeparrot_training - Step 40121: {'lr': 0.0004225205675566765, 'samples': 20542464, 'steps': 40121, 'loss/train': 1.7677667140960693}
-03/05/2022 12:38:05 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/05/2022 12:38:10 - INFO - codeparrot_training - Step 40122: {'lr': 0.00042251672686278275, 'samples': 20542976, 'steps': 40122, 'loss/train': 1.4917700290679932}
-03/05/2022 12:38:13 - INFO - codeparrot_training - Step 40123: {'lr': 0.0004225128860911557, 'samples': 20543488, 'steps': 40123, 'loss/train': 1.9835234880447388}
-03/05/2022 12:38:14 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/05/2022 12:38:18 - INFO - codeparrot_training - Step 40124: {'lr': 0.00042250904524179697, 'samples': 20544000, 'steps': 40124, 'loss/train': 2.0760698318481445}
-03/05/2022 12:38:21 - INFO - codeparrot_training - Step 40125: {'lr': 0.00042250520431470827, 'samples': 20544512, 'steps': 40125, 'loss/train': 2.111795425415039}
-03/05/2022 12:38:22 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/05/2022 12:38:27 - INFO - codeparrot_training - Step 40126: {'lr': 0.00042250136330989154, 'samples': 20545024, 'steps': 40126, 'loss/train': 1.3340188264846802}
-03/05/2022 12:38:30 - INFO - codeparrot_training - Step 40127: {'lr': 0.00042249752222734826, 'samples': 20545536, 'steps': 40127, 'loss/train': 0.8474777936935425}
-03/05/2022 12:38:31 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/05/2022 12:38:35 - INFO - codeparrot_training - Step 40128: {'lr': 0.0004224936810670803, 'samples': 20546048, 'steps': 40128, 'loss/train': 1.2117540836334229}
-03/05/2022 12:38:38 - INFO - codeparrot_training - Step 40129: {'lr': 0.0004224898398290893, 'samples': 20546560, 'steps': 40129, 'loss/train': 1.5462563037872314}
-03/05/2022 12:38:39 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/05/2022 12:38:44 - INFO - codeparrot_training - Step 40130: {'lr': 0.0004224859985133771, 'samples': 20547072, 'steps': 40130, 'loss/train': 0.8715566992759705}
-03/05/2022 12:38:47 - INFO - codeparrot_training - Step 40131: {'lr': 0.0004224821571199453, 'samples': 20547584, 'steps': 40131, 'loss/train': 1.8059865236282349}
-03/05/2022 12:38:48 - INFO - codeparrot_training - Skipping example with length 213 (seq_length=1024)
-03/05/2022 12:38:52 - INFO - codeparrot_training - Step 40132: {'lr': 0.0004224783156487958, 'samples': 20548096, 'steps': 40132, 'loss/train': 2.555755853652954}
-03/05/2022 12:38:55 - INFO - codeparrot_training - Step 40133: {'lr': 0.0004224744740999302, 'samples': 20548608, 'steps': 40133, 'loss/train': 1.2180461883544922}
-03/05/2022 12:38:56 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 12:39:00 - INFO - codeparrot_training - Step 40134: {'lr': 0.0004224706324733502, 'samples': 20549120, 'steps': 40134, 'loss/train': 1.474763035774231}
-03/05/2022 12:39:04 - INFO - codeparrot_training - Step 40135: {'lr': 0.00042246679076905763, 'samples': 20549632, 'steps': 40135, 'loss/train': 1.5892252922058105}
-03/05/2022 12:39:04 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/05/2022 12:39:09 - INFO - codeparrot_training - Step 40136: {'lr': 0.00042246294898705416, 'samples': 20550144, 'steps': 40136, 'loss/train': 2.395535945892334}
-03/05/2022 12:39:12 - INFO - codeparrot_training - Step 40137: {'lr': 0.0004224591071273416, 'samples': 20550656, 'steps': 40137, 'loss/train': 2.1740994453430176}
-03/05/2022 12:39:13 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 12:39:17 - INFO - codeparrot_training - Step 40138: {'lr': 0.00042245526518992164, 'samples': 20551168, 'steps': 40138, 'loss/train': 1.3885573148727417}
-03/05/2022 12:39:21 - INFO - codeparrot_training - Step 40139: {'lr': 0.0004224514231747959, 'samples': 20551680, 'steps': 40139, 'loss/train': 0.794738233089447}
-03/05/2022 12:39:21 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/05/2022 12:39:26 - INFO - codeparrot_training - Step 40140: {'lr': 0.00042244758108196635, 'samples': 20552192, 'steps': 40140, 'loss/train': 1.0422838926315308}
-03/05/2022 12:39:29 - INFO - codeparrot_training - Step 40141: {'lr': 0.00042244373891143453, 'samples': 20552704, 'steps': 40141, 'loss/train': 1.9386508464813232}
-03/05/2022 12:39:29 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/05/2022 12:39:34 - INFO - codeparrot_training - Step 40142: {'lr': 0.00042243989666320217, 'samples': 20553216, 'steps': 40142, 'loss/train': 1.5855708122253418}
-03/05/2022 12:39:37 - INFO - codeparrot_training - Step 40143: {'lr': 0.00042243605433727106, 'samples': 20553728, 'steps': 40143, 'loss/train': 1.4137191772460938}
-03/05/2022 12:39:38 - INFO - codeparrot_training - Skipping example with length 302 (seq_length=1024)
-03/05/2022 12:39:43 - INFO - codeparrot_training - Step 40144: {'lr': 0.0004224322119336429, 'samples': 20554240, 'steps': 40144, 'loss/train': 1.9725868701934814}
-03/05/2022 12:39:46 - INFO - codeparrot_training - Step 40145: {'lr': 0.0004224283694523195, 'samples': 20554752, 'steps': 40145, 'loss/train': 1.1569421291351318}
-03/05/2022 12:39:46 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/05/2022 12:39:51 - INFO - codeparrot_training - Step 40146: {'lr': 0.0004224245268933025, 'samples': 20555264, 'steps': 40146, 'loss/train': 1.5679454803466797}
-03/05/2022 12:39:54 - INFO - codeparrot_training - Step 40147: {'lr': 0.0004224206842565937, 'samples': 20555776, 'steps': 40147, 'loss/train': 1.7620419263839722}
-03/05/2022 12:39:54 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/05/2022 12:40:00 - INFO - codeparrot_training - Step 40148: {'lr': 0.0004224168415421948, 'samples': 20556288, 'steps': 40148, 'loss/train': 1.6999926567077637}
-03/05/2022 12:40:03 - INFO - codeparrot_training - Step 40149: {'lr': 0.0004224129987501075, 'samples': 20556800, 'steps': 40149, 'loss/train': 1.3701801300048828}
-03/05/2022 12:40:03 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/05/2022 12:40:08 - INFO - codeparrot_training - Step 40150: {'lr': 0.0004224091558803337, 'samples': 20557312, 'steps': 40150, 'loss/train': 0.7844430804252625}
-03/05/2022 12:40:11 - INFO - codeparrot_training - Step 40151: {'lr': 0.0004224053129328748, 'samples': 20557824, 'steps': 40151, 'loss/train': 0.7366156578063965}
-03/05/2022 12:40:11 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/05/2022 12:40:16 - INFO - codeparrot_training - Step 40152: {'lr': 0.0004224014699077329, 'samples': 20558336, 'steps': 40152, 'loss/train': 1.378142237663269}
-03/05/2022 12:40:19 - INFO - codeparrot_training - Step 40153: {'lr': 0.00042239762680490944, 'samples': 20558848, 'steps': 40153, 'loss/train': 1.6801011562347412}
-03/05/2022 12:40:20 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/05/2022 12:40:25 - INFO - codeparrot_training - Step 40154: {'lr': 0.00042239378362440627, 'samples': 20559360, 'steps': 40154, 'loss/train': 0.9654422998428345}
-03/05/2022 12:40:28 - INFO - codeparrot_training - Step 40155: {'lr': 0.0004223899403662251, 'samples': 20559872, 'steps': 40155, 'loss/train': 2.0935287475585938}
-03/05/2022 12:40:28 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/05/2022 12:40:33 - INFO - codeparrot_training - Step 40156: {'lr': 0.0004223860970303678, 'samples': 20560384, 'steps': 40156, 'loss/train': 1.410354495048523}
-03/05/2022 12:40:36 - INFO - codeparrot_training - Step 40157: {'lr': 0.00042238225361683593, 'samples': 20560896, 'steps': 40157, 'loss/train': 1.3500657081604004}
-03/05/2022 12:40:36 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/05/2022 12:40:42 - INFO - codeparrot_training - Step 40158: {'lr': 0.00042237841012563126, 'samples': 20561408, 'steps': 40158, 'loss/train': 1.7577975988388062}
-03/05/2022 12:40:45 - INFO - codeparrot_training - Step 40159: {'lr': 0.00042237456655675555, 'samples': 20561920, 'steps': 40159, 'loss/train': 2.228916883468628}
-03/05/2022 12:40:45 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/05/2022 12:40:50 - INFO - codeparrot_training - Step 40160: {'lr': 0.0004223707229102105, 'samples': 20562432, 'steps': 40160, 'loss/train': 1.876413106918335}
-03/05/2022 12:40:53 - INFO - codeparrot_training - Step 40161: {'lr': 0.0004223668791859979, 'samples': 20562944, 'steps': 40161, 'loss/train': 2.4925155639648438}
-03/05/2022 12:40:53 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/05/2022 12:40:59 - INFO - codeparrot_training - Step 40162: {'lr': 0.00042236303538411934, 'samples': 20563456, 'steps': 40162, 'loss/train': 1.9710724353790283}
-03/05/2022 12:41:02 - INFO - codeparrot_training - Step 40163: {'lr': 0.0004223591915045768, 'samples': 20563968, 'steps': 40163, 'loss/train': 1.6714404821395874}
-03/05/2022 12:41:02 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/05/2022 12:41:07 - INFO - codeparrot_training - Step 40164: {'lr': 0.0004223553475473718, 'samples': 20564480, 'steps': 40164, 'loss/train': 1.1864397525787354}
-03/05/2022 12:41:10 - INFO - codeparrot_training - Step 40165: {'lr': 0.00042235150351250617, 'samples': 20564992, 'steps': 40165, 'loss/train': 1.390030026435852}
-03/05/2022 12:41:10 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/05/2022 12:41:15 - INFO - codeparrot_training - Step 40166: {'lr': 0.00042234765939998156, 'samples': 20565504, 'steps': 40166, 'loss/train': 1.4653346538543701}
-03/05/2022 12:41:18 - INFO - codeparrot_training - Step 40167: {'lr': 0.00042234381520979983, 'samples': 20566016, 'steps': 40167, 'loss/train': 1.2761303186416626}
-03/05/2022 12:41:24 - INFO - codeparrot_training - Step 40168: {'lr': 0.0004223399709419625, 'samples': 20566528, 'steps': 40168, 'loss/train': 1.78235924243927}
-03/05/2022 12:41:27 - INFO - codeparrot_training - Step 40169: {'lr': 0.0004223361265964716, 'samples': 20567040, 'steps': 40169, 'loss/train': 1.2955230474472046}
-03/05/2022 12:41:27 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/05/2022 12:41:32 - INFO - codeparrot_training - Step 40170: {'lr': 0.0004223322821733286, 'samples': 20567552, 'steps': 40170, 'loss/train': 2.638183355331421}
-03/05/2022 12:41:35 - INFO - codeparrot_training - Step 40171: {'lr': 0.0004223284376725354, 'samples': 20568064, 'steps': 40171, 'loss/train': 2.005826711654663}
-03/05/2022 12:41:36 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/05/2022 12:41:41 - INFO - codeparrot_training - Step 40172: {'lr': 0.00042232459309409355, 'samples': 20568576, 'steps': 40172, 'loss/train': 1.723232626914978}
-03/05/2022 12:41:44 - INFO - codeparrot_training - Step 40173: {'lr': 0.00042232074843800494, 'samples': 20569088, 'steps': 40173, 'loss/train': 2.195824146270752}
-03/05/2022 12:41:44 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/05/2022 12:41:49 - INFO - codeparrot_training - Step 40174: {'lr': 0.00042231690370427135, 'samples': 20569600, 'steps': 40174, 'loss/train': 1.312303900718689}
-03/05/2022 12:41:52 - INFO - codeparrot_training - Step 40175: {'lr': 0.00042231305889289437, 'samples': 20570112, 'steps': 40175, 'loss/train': 1.787569284439087}
-03/05/2022 12:41:52 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/05/2022 12:41:58 - INFO - codeparrot_training - Step 40176: {'lr': 0.00042230921400387576, 'samples': 20570624, 'steps': 40176, 'loss/train': 2.1782748699188232}
-03/05/2022 12:42:00 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 12:42:03 - INFO - codeparrot_training - Step 40177: {'lr': 0.0004223053690372173, 'samples': 20571136, 'steps': 40177, 'loss/train': 1.4381171464920044}
-03/05/2022 12:42:06 - INFO - codeparrot_training - Step 40178: {'lr': 0.00042230152399292065, 'samples': 20571648, 'steps': 40178, 'loss/train': 1.6184061765670776}
-03/05/2022 12:42:10 - INFO - codeparrot_training - Step 40179: {'lr': 0.00042229767887098766, 'samples': 20572160, 'steps': 40179, 'loss/train': 2.133863687515259}
-03/05/2022 12:42:11 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 12:42:15 - INFO - codeparrot_training - Step 40180: {'lr': 0.00042229383367142, 'samples': 20572672, 'steps': 40180, 'loss/train': 1.8218458890914917}
-03/05/2022 12:42:18 - INFO - codeparrot_training - Step 40181: {'lr': 0.0004222899883942194, 'samples': 20573184, 'steps': 40181, 'loss/train': 1.4018020629882812}
-03/05/2022 12:42:20 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/05/2022 12:42:23 - INFO - codeparrot_training - Step 40182: {'lr': 0.0004222861430393875, 'samples': 20573696, 'steps': 40182, 'loss/train': 2.0200421810150146}
-03/05/2022 12:42:27 - INFO - codeparrot_training - Step 40183: {'lr': 0.0004222822976069262, 'samples': 20574208, 'steps': 40183, 'loss/train': 1.0286396741867065}
-03/05/2022 12:42:28 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/05/2022 12:42:32 - INFO - codeparrot_training - Step 40184: {'lr': 0.0004222784520968371, 'samples': 20574720, 'steps': 40184, 'loss/train': 1.369282603263855}
-03/05/2022 12:42:35 - INFO - codeparrot_training - Step 40185: {'lr': 0.0004222746065091221, 'samples': 20575232, 'steps': 40185, 'loss/train': 1.4660123586654663}
-03/05/2022 12:42:36 - INFO - codeparrot_training - Skipping example with length 269 (seq_length=1024)
-03/05/2022 12:42:40 - INFO - codeparrot_training - Step 40186: {'lr': 0.0004222707608437827, 'samples': 20575744, 'steps': 40186, 'loss/train': 1.8770731687545776}
-03/05/2022 12:42:44 - INFO - codeparrot_training - Step 40187: {'lr': 0.00042226691510082083, 'samples': 20576256, 'steps': 40187, 'loss/train': 2.175034523010254}
-03/05/2022 12:42:45 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/05/2022 12:42:49 - INFO - codeparrot_training - Step 40188: {'lr': 0.0004222630692802381, 'samples': 20576768, 'steps': 40188, 'loss/train': 0.8981433510780334}
-03/05/2022 12:42:52 - INFO - codeparrot_training - Step 40189: {'lr': 0.00042225922338203625, 'samples': 20577280, 'steps': 40189, 'loss/train': 1.7281867265701294}
-03/05/2022 12:42:53 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/05/2022 12:42:57 - INFO - codeparrot_training - Step 40190: {'lr': 0.00042225537740621713, 'samples': 20577792, 'steps': 40190, 'loss/train': 1.393416166305542}
-03/05/2022 12:43:01 - INFO - codeparrot_training - Step 40191: {'lr': 0.00042225153135278236, 'samples': 20578304, 'steps': 40191, 'loss/train': 1.6467995643615723}
-03/05/2022 12:43:02 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/05/2022 12:43:06 - INFO - codeparrot_training - Step 40192: {'lr': 0.00042224768522173374, 'samples': 20578816, 'steps': 40192, 'loss/train': 2.472520351409912}
-03/05/2022 12:43:09 - INFO - codeparrot_training - Step 40193: {'lr': 0.00042224383901307293, 'samples': 20579328, 'steps': 40193, 'loss/train': 0.19825619459152222}
-03/05/2022 12:43:11 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/05/2022 12:43:15 - INFO - codeparrot_training - Step 40194: {'lr': 0.0004222399927268018, 'samples': 20579840, 'steps': 40194, 'loss/train': 1.455000400543213}
-03/05/2022 12:43:18 - INFO - codeparrot_training - Step 40195: {'lr': 0.0004222361463629218, 'samples': 20580352, 'steps': 40195, 'loss/train': 2.1388959884643555}
-03/05/2022 12:43:20 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/05/2022 12:43:23 - INFO - codeparrot_training - Step 40196: {'lr': 0.00042223229992143505, 'samples': 20580864, 'steps': 40196, 'loss/train': 2.0254151821136475}
-03/05/2022 12:43:26 - INFO - codeparrot_training - Step 40197: {'lr': 0.00042222845340234293, 'samples': 20581376, 'steps': 40197, 'loss/train': 0.4651538133621216}
-03/05/2022 12:43:28 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/05/2022 12:43:31 - INFO - codeparrot_training - Step 40198: {'lr': 0.00042222460680564747, 'samples': 20581888, 'steps': 40198, 'loss/train': 2.1400110721588135}
-03/05/2022 12:43:35 - INFO - codeparrot_training - Step 40199: {'lr': 0.0004222207601313501, 'samples': 20582400, 'steps': 40199, 'loss/train': 1.599306344985962}
-03/05/2022 12:43:37 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/05/2022 12:43:40 - INFO - codeparrot_training - Step 40200: {'lr': 0.00042221691337945285, 'samples': 20582912, 'steps': 40200, 'loss/train': 1.5169196128845215}
-03/05/2022 12:43:43 - INFO - codeparrot_training - Step 40201: {'lr': 0.0004222130665499573, 'samples': 20583424, 'steps': 40201, 'loss/train': 3.047896146774292}
-03/05/2022 12:43:45 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/05/2022 12:43:48 - INFO - codeparrot_training - Step 40202: {'lr': 0.0004222092196428651, 'samples': 20583936, 'steps': 40202, 'loss/train': 2.149799108505249}
-03/05/2022 12:43:52 - INFO - codeparrot_training - Step 40203: {'lr': 0.0004222053726581782, 'samples': 20584448, 'steps': 40203, 'loss/train': 1.1042876243591309}
-03/05/2022 12:43:54 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/05/2022 12:43:57 - INFO - codeparrot_training - Step 40204: {'lr': 0.0004222015255958981, 'samples': 20584960, 'steps': 40204, 'loss/train': 1.1554042100906372}
-03/05/2022 12:44:00 - INFO - codeparrot_training - Step 40205: {'lr': 0.0004221976784560267, 'samples': 20585472, 'steps': 40205, 'loss/train': 1.6719025373458862}
-03/05/2022 12:44:02 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 12:44:05 - INFO - codeparrot_training - Step 40206: {'lr': 0.0004221938312385657, 'samples': 20585984, 'steps': 40206, 'loss/train': 0.94319748878479}
-03/05/2022 12:44:09 - INFO - codeparrot_training - Step 40207: {'lr': 0.00042218998394351684, 'samples': 20586496, 'steps': 40207, 'loss/train': 1.8789873123168945}
-03/05/2022 12:44:10 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 12:44:14 - INFO - codeparrot_training - Step 40208: {'lr': 0.0004221861365708818, 'samples': 20587008, 'steps': 40208, 'loss/train': 1.6031830310821533}
-03/05/2022 12:44:17 - INFO - codeparrot_training - Step 40209: {'lr': 0.0004221822891206623, 'samples': 20587520, 'steps': 40209, 'loss/train': 2.490661859512329}
-03/05/2022 12:44:20 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/05/2022 12:44:22 - INFO - codeparrot_training - Step 40210: {'lr': 0.00042217844159286015, 'samples': 20588032, 'steps': 40210, 'loss/train': 2.1415233612060547}
-03/05/2022 12:44:26 - INFO - codeparrot_training - Step 40211: {'lr': 0.00042217459398747703, 'samples': 20588544, 'steps': 40211, 'loss/train': 1.0633940696716309}
-03/05/2022 12:44:28 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/05/2022 12:44:31 - INFO - codeparrot_training - Step 40212: {'lr': 0.0004221707463045148, 'samples': 20589056, 'steps': 40212, 'loss/train': 2.316683053970337}
-03/05/2022 12:44:34 - INFO - codeparrot_training - Step 40213: {'lr': 0.0004221668985439749, 'samples': 20589568, 'steps': 40213, 'loss/train': 1.1005949974060059}
-03/05/2022 12:44:37 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/05/2022 12:44:39 - INFO - codeparrot_training - Step 40214: {'lr': 0.00042216305070585946, 'samples': 20590080, 'steps': 40214, 'loss/train': 1.2847903966903687}
-03/05/2022 12:44:42 - INFO - codeparrot_training - Step 40215: {'lr': 0.00042215920279016993, 'samples': 20590592, 'steps': 40215, 'loss/train': 2.0846872329711914}
-03/05/2022 12:44:45 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/05/2022 12:44:48 - INFO - codeparrot_training - Step 40216: {'lr': 0.00042215535479690807, 'samples': 20591104, 'steps': 40216, 'loss/train': 0.8156063556671143}
-03/05/2022 12:44:51 - INFO - codeparrot_training - Step 40217: {'lr': 0.0004221515067260757, 'samples': 20591616, 'steps': 40217, 'loss/train': 0.7461385130882263}
-03/05/2022 12:44:56 - INFO - codeparrot_training - Step 40218: {'lr': 0.0004221476585776745, 'samples': 20592128, 'steps': 40218, 'loss/train': 1.6894958019256592}
-03/05/2022 12:44:59 - INFO - codeparrot_training - Step 40219: {'lr': 0.00042214381035170624, 'samples': 20592640, 'steps': 40219, 'loss/train': 2.781083106994629}
-03/05/2022 12:45:02 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/05/2022 12:45:05 - INFO - codeparrot_training - Step 40220: {'lr': 0.0004221399620481726, 'samples': 20593152, 'steps': 40220, 'loss/train': 1.8164409399032593}
-03/05/2022 12:45:08 - INFO - codeparrot_training - Step 40221: {'lr': 0.00042213611366707547, 'samples': 20593664, 'steps': 40221, 'loss/train': 1.8897675275802612}
-03/05/2022 12:45:11 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/05/2022 12:45:13 - INFO - codeparrot_training - Step 40222: {'lr': 0.0004221322652084163, 'samples': 20594176, 'steps': 40222, 'loss/train': 1.7072744369506836}
-03/05/2022 12:45:16 - INFO - codeparrot_training - Step 40223: {'lr': 0.0004221284166721971, 'samples': 20594688, 'steps': 40223, 'loss/train': 1.7959158420562744}
-03/05/2022 12:45:19 - INFO - codeparrot_training - Skipping example with length 346 (seq_length=1024)
-03/05/2022 12:45:21 - INFO - codeparrot_training - Step 40224: {'lr': 0.00042212456805841944, 'samples': 20595200, 'steps': 40224, 'loss/train': 1.5631266832351685}
-03/05/2022 12:45:25 - INFO - codeparrot_training - Step 40225: {'lr': 0.00042212071936708506, 'samples': 20595712, 'steps': 40225, 'loss/train': 1.8987339735031128}
-03/05/2022 12:45:28 - INFO - codeparrot_training - Step 40226: {'lr': 0.0004221168705981958, 'samples': 20596224, 'steps': 40226, 'loss/train': 2.4004874229431152}
-03/05/2022 12:45:28 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/05/2022 12:45:33 - INFO - codeparrot_training - Step 40227: {'lr': 0.00042211302175175334, 'samples': 20596736, 'steps': 40227, 'loss/train': 1.5915488004684448}
-03/05/2022 12:45:36 - INFO - codeparrot_training - Step 40228: {'lr': 0.0004221091728277595, 'samples': 20597248, 'steps': 40228, 'loss/train': 1.2016637325286865}
-03/05/2022 12:45:37 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 12:45:42 - INFO - codeparrot_training - Step 40229: {'lr': 0.0004221053238262158, 'samples': 20597760, 'steps': 40229, 'loss/train': 2.1468186378479004}
-03/05/2022 12:45:45 - INFO - codeparrot_training - Step 40230: {'lr': 0.0004221014747471241, 'samples': 20598272, 'steps': 40230, 'loss/train': 1.2492948770523071}
-03/05/2022 12:45:45 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/05/2022 12:45:50 - INFO - codeparrot_training - Step 40231: {'lr': 0.0004220976255904861, 'samples': 20598784, 'steps': 40231, 'loss/train': 1.9653582572937012}
-03/05/2022 12:45:53 - INFO - codeparrot_training - Step 40232: {'lr': 0.00042209377635630364, 'samples': 20599296, 'steps': 40232, 'loss/train': 2.0514402389526367}
-03/05/2022 12:45:54 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/05/2022 12:45:59 - INFO - codeparrot_training - Step 40233: {'lr': 0.00042208992704457837, 'samples': 20599808, 'steps': 40233, 'loss/train': 1.984248161315918}
-03/05/2022 12:46:02 - INFO - codeparrot_training - Step 40234: {'lr': 0.00042208607765531204, 'samples': 20600320, 'steps': 40234, 'loss/train': 0.4056980609893799}
-03/05/2022 12:46:02 - INFO - codeparrot_training - Skipping example with length 909 (seq_length=1024)
-03/05/2022 12:46:07 - INFO - codeparrot_training - Step 40235: {'lr': 0.00042208222818850634, 'samples': 20600832, 'steps': 40235, 'loss/train': 1.567301630973816}
-03/05/2022 12:46:10 - INFO - codeparrot_training - Step 40236: {'lr': 0.0004220783786441631, 'samples': 20601344, 'steps': 40236, 'loss/train': 1.6031955480575562}
-03/05/2022 12:46:10 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 12:46:16 - INFO - codeparrot_training - Step 40237: {'lr': 0.0004220745290222839, 'samples': 20601856, 'steps': 40237, 'loss/train': 1.9657427072525024}
-03/05/2022 12:46:19 - INFO - codeparrot_training - Step 40238: {'lr': 0.00042207067932287066, 'samples': 20602368, 'steps': 40238, 'loss/train': 0.7697015404701233}
-03/05/2022 12:46:19 - INFO - codeparrot_training - Skipping example with length 386 (seq_length=1024)
-03/05/2022 12:46:24 - INFO - codeparrot_training - Step 40239: {'lr': 0.00042206682954592503, 'samples': 20602880, 'steps': 40239, 'loss/train': 1.86000394821167}
-03/05/2022 12:46:29 - INFO - codeparrot_training - Step 40240: {'lr': 0.0004220629796914487, 'samples': 20603392, 'steps': 40240, 'loss/train': 1.21883225440979}
-03/05/2022 12:46:32 - INFO - codeparrot_training - Step 40241: {'lr': 0.00042205912975944344, 'samples': 20603904, 'steps': 40241, 'loss/train': 2.1045234203338623}
-03/05/2022 12:46:35 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/05/2022 12:46:38 - INFO - codeparrot_training - Step 40242: {'lr': 0.00042205527974991096, 'samples': 20604416, 'steps': 40242, 'loss/train': 1.9751604795455933}
-03/05/2022 12:46:41 - INFO - codeparrot_training - Step 40243: {'lr': 0.00042205142966285315, 'samples': 20604928, 'steps': 40243, 'loss/train': 1.3504664897918701}
-03/05/2022 12:46:44 - INFO - codeparrot_training - Step 40244: {'lr': 0.0004220475794982716, 'samples': 20605440, 'steps': 40244, 'loss/train': 1.7863941192626953}
-03/05/2022 12:46:44 - INFO - codeparrot_training - Skipping example with length 867 (seq_length=1024)
-03/05/2022 12:46:50 - INFO - codeparrot_training - Step 40245: {'lr': 0.00042204372925616797, 'samples': 20605952, 'steps': 40245, 'loss/train': 1.7033005952835083}
-03/05/2022 12:46:53 - INFO - codeparrot_training - Step 40246: {'lr': 0.0004220398789365441, 'samples': 20606464, 'steps': 40246, 'loss/train': 2.4130101203918457}
-03/05/2022 12:46:53 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/05/2022 12:46:58 - INFO - codeparrot_training - Step 40247: {'lr': 0.0004220360285394017, 'samples': 20606976, 'steps': 40247, 'loss/train': 0.6802616715431213}
-03/05/2022 12:47:01 - INFO - codeparrot_training - Step 40248: {'lr': 0.0004220321780647426, 'samples': 20607488, 'steps': 40248, 'loss/train': 1.4052786827087402}
-03/05/2022 12:47:01 - INFO - codeparrot_training - Skipping example with length 373 (seq_length=1024)
-03/05/2022 12:47:07 - INFO - codeparrot_training - Step 40249: {'lr': 0.00042202832751256846, 'samples': 20608000, 'steps': 40249, 'loss/train': 2.135979175567627}
-03/05/2022 12:47:10 - INFO - codeparrot_training - Step 40250: {'lr': 0.0004220244768828809, 'samples': 20608512, 'steps': 40250, 'loss/train': 1.4819645881652832}
-03/05/2022 12:47:10 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/05/2022 12:47:15 - INFO - codeparrot_training - Step 40251: {'lr': 0.0004220206261756819, 'samples': 20609024, 'steps': 40251, 'loss/train': 1.1301878690719604}
-03/05/2022 12:47:18 - INFO - codeparrot_training - Step 40252: {'lr': 0.00042201677539097294, 'samples': 20609536, 'steps': 40252, 'loss/train': 1.7582886219024658}
-03/05/2022 12:47:18 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/05/2022 12:47:24 - INFO - codeparrot_training - Step 40253: {'lr': 0.00042201292452875595, 'samples': 20610048, 'steps': 40253, 'loss/train': 1.7708183526992798}
-03/05/2022 12:47:27 - INFO - codeparrot_training - Step 40254: {'lr': 0.00042200907358903264, 'samples': 20610560, 'steps': 40254, 'loss/train': 1.255233883857727}
-03/05/2022 12:47:27 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/05/2022 12:47:32 - INFO - codeparrot_training - Step 40255: {'lr': 0.0004220052225718046, 'samples': 20611072, 'steps': 40255, 'loss/train': 1.8493973016738892}
-03/05/2022 12:47:35 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 12:47:37 - INFO - codeparrot_training - Step 40256: {'lr': 0.0004220013714770737, 'samples': 20611584, 'steps': 40256, 'loss/train': 1.7493174076080322}
-03/05/2022 12:47:41 - INFO - codeparrot_training - Step 40257: {'lr': 0.0004219975203048416, 'samples': 20612096, 'steps': 40257, 'loss/train': 1.768437385559082}
-03/05/2022 12:47:43 - INFO - codeparrot_training - Skipping example with length 385 (seq_length=1024)
-03/05/2022 12:47:46 - INFO - codeparrot_training - Step 40258: {'lr': 0.0004219936690551101, 'samples': 20612608, 'steps': 40258, 'loss/train': 1.8031048774719238}
-03/05/2022 12:47:49 - INFO - codeparrot_training - Step 40259: {'lr': 0.0004219898177278809, 'samples': 20613120, 'steps': 40259, 'loss/train': 1.0127263069152832}
-03/05/2022 12:47:52 - INFO - codeparrot_training - Step 40260: {'lr': 0.00042198596632315576, 'samples': 20613632, 'steps': 40260, 'loss/train': 2.4111196994781494}
-03/05/2022 12:47:52 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/05/2022 12:47:58 - INFO - codeparrot_training - Step 40261: {'lr': 0.0004219821148409364, 'samples': 20614144, 'steps': 40261, 'loss/train': 1.9793587923049927}
-03/05/2022 12:48:01 - INFO - codeparrot_training - Step 40262: {'lr': 0.00042197826328122456, 'samples': 20614656, 'steps': 40262, 'loss/train': 1.9395338296890259}
-03/05/2022 12:48:02 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/05/2022 12:48:07 - INFO - codeparrot_training - Step 40263: {'lr': 0.00042197441164402197, 'samples': 20615168, 'steps': 40263, 'loss/train': 1.5725336074829102}
-03/05/2022 12:48:10 - INFO - codeparrot_training - Step 40264: {'lr': 0.0004219705599293303, 'samples': 20615680, 'steps': 40264, 'loss/train': 1.6913716793060303}
-03/05/2022 12:48:11 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/05/2022 12:48:15 - INFO - codeparrot_training - Step 40265: {'lr': 0.00042196670813715137, 'samples': 20616192, 'steps': 40265, 'loss/train': 0.9745018482208252}
-03/05/2022 12:48:18 - INFO - codeparrot_training - Step 40266: {'lr': 0.0004219628562674869, 'samples': 20616704, 'steps': 40266, 'loss/train': 0.7311116456985474}
-03/05/2022 12:48:19 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 12:48:23 - INFO - codeparrot_training - Step 40267: {'lr': 0.00042195900432033865, 'samples': 20617216, 'steps': 40267, 'loss/train': 1.4652647972106934}
-03/05/2022 12:48:27 - INFO - codeparrot_training - Step 40268: {'lr': 0.00042195515229570833, 'samples': 20617728, 'steps': 40268, 'loss/train': 1.67008376121521}
-03/05/2022 12:48:27 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/05/2022 12:48:32 - INFO - codeparrot_training - Step 40269: {'lr': 0.0004219513001935976, 'samples': 20618240, 'steps': 40269, 'loss/train': 1.4139922857284546}
-03/05/2022 12:48:35 - INFO - codeparrot_training - Step 40270: {'lr': 0.00042194744801400837, 'samples': 20618752, 'steps': 40270, 'loss/train': 2.2401371002197266}
-03/05/2022 12:48:37 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/05/2022 12:48:41 - INFO - codeparrot_training - Step 40271: {'lr': 0.0004219435957569422, 'samples': 20619264, 'steps': 40271, 'loss/train': 1.7601525783538818}
-03/05/2022 12:48:44 - INFO - codeparrot_training - Step 40272: {'lr': 0.0004219397434224009, 'samples': 20619776, 'steps': 40272, 'loss/train': 1.7022475004196167}
-03/05/2022 12:48:46 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/05/2022 12:48:49 - INFO - codeparrot_training - Step 40273: {'lr': 0.0004219358910103862, 'samples': 20620288, 'steps': 40273, 'loss/train': 1.2593765258789062}
-03/05/2022 12:48:52 - INFO - codeparrot_training - Step 40274: {'lr': 0.00042193203852089993, 'samples': 20620800, 'steps': 40274, 'loss/train': 1.4984902143478394}
-03/05/2022 12:48:54 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/05/2022 12:48:57 - INFO - codeparrot_training - Step 40275: {'lr': 0.00042192818595394367, 'samples': 20621312, 'steps': 40275, 'loss/train': 1.2564425468444824}
-03/05/2022 12:49:01 - INFO - codeparrot_training - Step 40276: {'lr': 0.00042192433330951926, 'samples': 20621824, 'steps': 40276, 'loss/train': 1.3420233726501465}
-03/05/2022 12:49:02 - INFO - codeparrot_training - Skipping example with length 86 (seq_length=1024)
-03/05/2022 12:49:06 - INFO - codeparrot_training - Step 40277: {'lr': 0.00042192048058762834, 'samples': 20622336, 'steps': 40277, 'loss/train': 1.660277009010315}
-03/05/2022 12:49:09 - INFO - codeparrot_training - Step 40278: {'lr': 0.00042191662778827275, 'samples': 20622848, 'steps': 40278, 'loss/train': 1.7961219549179077}
-03/05/2022 12:49:11 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/05/2022 12:49:14 - INFO - codeparrot_training - Step 40279: {'lr': 0.0004219127749114541, 'samples': 20623360, 'steps': 40279, 'loss/train': 0.9085057377815247}
-03/05/2022 12:49:17 - INFO - codeparrot_training - Step 40280: {'lr': 0.00042190892195717426, 'samples': 20623872, 'steps': 40280, 'loss/train': 1.5079188346862793}
-03/05/2022 12:49:19 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/05/2022 12:49:23 - INFO - codeparrot_training - Step 40281: {'lr': 0.000421905068925435, 'samples': 20624384, 'steps': 40281, 'loss/train': 1.2070930004119873}
-03/05/2022 12:49:26 - INFO - codeparrot_training - Step 40282: {'lr': 0.00042190121581623784, 'samples': 20624896, 'steps': 40282, 'loss/train': 1.6784605979919434}
-03/05/2022 12:49:27 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/05/2022 12:49:31 - INFO - codeparrot_training - Step 40283: {'lr': 0.0004218973626295847, 'samples': 20625408, 'steps': 40283, 'loss/train': 1.5749303102493286}
-03/05/2022 12:49:34 - INFO - codeparrot_training - Step 40284: {'lr': 0.0004218935093654772, 'samples': 20625920, 'steps': 40284, 'loss/train': 1.6060492992401123}
-03/05/2022 12:49:36 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/05/2022 12:49:40 - INFO - codeparrot_training - Step 40285: {'lr': 0.00042188965602391726, 'samples': 20626432, 'steps': 40285, 'loss/train': 2.050286054611206}
-03/05/2022 12:49:43 - INFO - codeparrot_training - Step 40286: {'lr': 0.0004218858026049064, 'samples': 20626944, 'steps': 40286, 'loss/train': 0.8168420791625977}
-03/05/2022 12:49:44 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/05/2022 12:49:48 - INFO - codeparrot_training - Step 40287: {'lr': 0.00042188194910844644, 'samples': 20627456, 'steps': 40287, 'loss/train': 1.77615225315094}
-03/05/2022 12:49:51 - INFO - codeparrot_training - Step 40288: {'lr': 0.0004218780955345392, 'samples': 20627968, 'steps': 40288, 'loss/train': 1.5234456062316895}
-03/05/2022 12:49:52 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/05/2022 12:49:57 - INFO - codeparrot_training - Step 40289: {'lr': 0.0004218742418831863, 'samples': 20628480, 'steps': 40289, 'loss/train': 1.285285234451294}
-03/05/2022 12:50:00 - INFO - codeparrot_training - Step 40290: {'lr': 0.0004218703881543895, 'samples': 20628992, 'steps': 40290, 'loss/train': 1.875503659248352}
-03/05/2022 12:50:01 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/05/2022 12:50:05 - INFO - codeparrot_training - Step 40291: {'lr': 0.0004218665343481506, 'samples': 20629504, 'steps': 40291, 'loss/train': 1.5325589179992676}
-03/05/2022 12:50:08 - INFO - codeparrot_training - Step 40292: {'lr': 0.00042186268046447124, 'samples': 20630016, 'steps': 40292, 'loss/train': 1.9097596406936646}
-03/05/2022 12:50:09 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/05/2022 12:50:13 - INFO - codeparrot_training - Step 40293: {'lr': 0.0004218588265033533, 'samples': 20630528, 'steps': 40293, 'loss/train': 2.6795494556427}
-03/05/2022 12:50:17 - INFO - codeparrot_training - Step 40294: {'lr': 0.0004218549724647983, 'samples': 20631040, 'steps': 40294, 'loss/train': 1.7871052026748657}
-03/05/2022 12:50:17 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/05/2022 12:50:22 - INFO - codeparrot_training - Step 40295: {'lr': 0.0004218511183488082, 'samples': 20631552, 'steps': 40295, 'loss/train': 2.957859516143799}
-03/05/2022 12:50:25 - INFO - codeparrot_training - Step 40296: {'lr': 0.00042184726415538457, 'samples': 20632064, 'steps': 40296, 'loss/train': 1.789513111114502}
-03/05/2022 12:50:25 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/05/2022 12:50:30 - INFO - codeparrot_training - Step 40297: {'lr': 0.00042184340988452924, 'samples': 20632576, 'steps': 40297, 'loss/train': 1.6110070943832397}
-03/05/2022 12:50:33 - INFO - codeparrot_training - Step 40298: {'lr': 0.00042183955553624393, 'samples': 20633088, 'steps': 40298, 'loss/train': 0.9351043701171875}
-03/05/2022 12:50:33 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/05/2022 12:50:39 - INFO - codeparrot_training - Step 40299: {'lr': 0.0004218357011105304, 'samples': 20633600, 'steps': 40299, 'loss/train': 1.9298216104507446}
-03/05/2022 12:50:42 - INFO - codeparrot_training - Step 40300: {'lr': 0.00042183184660739027, 'samples': 20634112, 'steps': 40300, 'loss/train': 1.3387579917907715}
-03/05/2022 12:50:42 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 12:50:47 - INFO - codeparrot_training - Step 40301: {'lr': 0.00042182799202682543, 'samples': 20634624, 'steps': 40301, 'loss/train': 1.7560116052627563}
-03/05/2022 12:50:50 - INFO - codeparrot_training - Step 40302: {'lr': 0.0004218241373688375, 'samples': 20635136, 'steps': 40302, 'loss/train': 0.708766520023346}
-03/05/2022 12:50:50 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/05/2022 12:50:55 - INFO - codeparrot_training - Step 40303: {'lr': 0.0004218202826334283, 'samples': 20635648, 'steps': 40303, 'loss/train': 0.47029706835746765}
-03/05/2022 12:50:58 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/05/2022 12:51:01 - INFO - codeparrot_training - Step 40304: {'lr': 0.0004218164278205995, 'samples': 20636160, 'steps': 40304, 'loss/train': 2.161125421524048}
-03/05/2022 12:51:04 - INFO - codeparrot_training - Step 40305: {'lr': 0.00042181257293035293, 'samples': 20636672, 'steps': 40305, 'loss/train': 1.8054277896881104}
-03/05/2022 12:51:07 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/05/2022 12:51:09 - INFO - codeparrot_training - Step 40306: {'lr': 0.00042180871796269025, 'samples': 20637184, 'steps': 40306, 'loss/train': 0.5323250889778137}
-03/05/2022 12:51:12 - INFO - codeparrot_training - Step 40307: {'lr': 0.00042180486291761314, 'samples': 20637696, 'steps': 40307, 'loss/train': 1.5488289594650269}
-03/05/2022 12:51:15 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 12:51:18 - INFO - codeparrot_training - Step 40308: {'lr': 0.0004218010077951235, 'samples': 20638208, 'steps': 40308, 'loss/train': 1.853540062904358}
-03/05/2022 12:51:21 - INFO - codeparrot_training - Step 40309: {'lr': 0.00042179715259522293, 'samples': 20638720, 'steps': 40309, 'loss/train': 2.5182223320007324}
-03/05/2022 12:51:24 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/05/2022 12:51:26 - INFO - codeparrot_training - Step 40310: {'lr': 0.00042179329731791324, 'samples': 20639232, 'steps': 40310, 'loss/train': 2.00529146194458}
-03/05/2022 12:51:29 - INFO - codeparrot_training - Step 40311: {'lr': 0.0004217894419631961, 'samples': 20639744, 'steps': 40311, 'loss/train': 1.5842262506484985}
-03/05/2022 12:51:33 - INFO - codeparrot_training - Step 40312: {'lr': 0.00042178558653107337, 'samples': 20640256, 'steps': 40312, 'loss/train': 1.5957057476043701}
-03/05/2022 12:51:33 - INFO - codeparrot_training - Skipping example with length 619 (seq_length=1024)
-03/05/2022 12:51:38 - INFO - codeparrot_training - Step 40313: {'lr': 0.0004217817310215466, 'samples': 20640768, 'steps': 40313, 'loss/train': 2.4080498218536377}
-03/05/2022 12:51:41 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 12:51:43 - INFO - codeparrot_training - Step 40314: {'lr': 0.00042177787543461767, 'samples': 20641280, 'steps': 40314, 'loss/train': 1.6943702697753906}
-03/05/2022 12:51:46 - INFO - codeparrot_training - Step 40315: {'lr': 0.0004217740197702883, 'samples': 20641792, 'steps': 40315, 'loss/train': 2.04622220993042}
-03/05/2022 12:51:49 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 12:51:51 - INFO - codeparrot_training - Step 40316: {'lr': 0.00042177016402856023, 'samples': 20642304, 'steps': 40316, 'loss/train': 1.220918893814087}
-03/05/2022 12:51:55 - INFO - codeparrot_training - Step 40317: {'lr': 0.00042176630820943515, 'samples': 20642816, 'steps': 40317, 'loss/train': 2.8290717601776123}
-03/05/2022 12:51:57 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 12:52:00 - INFO - codeparrot_training - Step 40318: {'lr': 0.0004217624523129148, 'samples': 20643328, 'steps': 40318, 'loss/train': 2.869656562805176}
-03/05/2022 12:52:03 - INFO - codeparrot_training - Step 40319: {'lr': 0.0004217585963390009, 'samples': 20643840, 'steps': 40319, 'loss/train': 1.237679362297058}
-03/05/2022 12:52:06 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 12:52:08 - INFO - codeparrot_training - Step 40320: {'lr': 0.00042175474028769534, 'samples': 20644352, 'steps': 40320, 'loss/train': 1.5363487005233765}
-03/05/2022 12:52:11 - INFO - codeparrot_training - Step 40321: {'lr': 0.00042175088415899963, 'samples': 20644864, 'steps': 40321, 'loss/train': 2.3435394763946533}
-03/05/2022 12:52:14 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/05/2022 12:52:17 - INFO - codeparrot_training - Step 40322: {'lr': 0.00042174702795291574, 'samples': 20645376, 'steps': 40322, 'loss/train': 1.8248348236083984}
-03/05/2022 12:52:20 - INFO - codeparrot_training - Step 40323: {'lr': 0.0004217431716694452, 'samples': 20645888, 'steps': 40323, 'loss/train': 1.5584944486618042}
-03/05/2022 12:52:23 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/05/2022 12:52:25 - INFO - codeparrot_training - Step 40324: {'lr': 0.00042173931530858986, 'samples': 20646400, 'steps': 40324, 'loss/train': 1.779521107673645}
-03/05/2022 12:52:28 - INFO - codeparrot_training - Step 40325: {'lr': 0.00042173545887035145, 'samples': 20646912, 'steps': 40325, 'loss/train': 1.5679527521133423}
-03/05/2022 12:52:31 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/05/2022 12:52:34 - INFO - codeparrot_training - Step 40326: {'lr': 0.0004217316023547317, 'samples': 20647424, 'steps': 40326, 'loss/train': 2.856717109680176}
-03/05/2022 12:52:37 - INFO - codeparrot_training - Step 40327: {'lr': 0.00042172774576173226, 'samples': 20647936, 'steps': 40327, 'loss/train': 1.3751329183578491}
-03/05/2022 12:52:40 - INFO - codeparrot_training - Step 40328: {'lr': 0.00042172388909135505, 'samples': 20648448, 'steps': 40328, 'loss/train': 1.240923285484314}
-03/05/2022 12:52:40 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/05/2022 12:52:45 - INFO - codeparrot_training - Step 40329: {'lr': 0.0004217200323436017, 'samples': 20648960, 'steps': 40329, 'loss/train': 1.105275273323059}
-03/05/2022 12:52:49 - INFO - codeparrot_training - Step 40330: {'lr': 0.00042171617551847387, 'samples': 20649472, 'steps': 40330, 'loss/train': 1.6173230409622192}
-03/05/2022 12:52:49 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/05/2022 12:52:54 - INFO - codeparrot_training - Step 40331: {'lr': 0.0004217123186159735, 'samples': 20649984, 'steps': 40331, 'loss/train': 3.351693630218506}
-03/05/2022 12:52:58 - INFO - codeparrot_training - Step 40332: {'lr': 0.0004217084616361021, 'samples': 20650496, 'steps': 40332, 'loss/train': 1.0710575580596924}
-03/05/2022 12:53:00 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/05/2022 12:53:03 - INFO - codeparrot_training - Step 40333: {'lr': 0.0004217046045788615, 'samples': 20651008, 'steps': 40333, 'loss/train': 0.9402898550033569}
-03/05/2022 12:53:06 - INFO - codeparrot_training - Step 40334: {'lr': 0.0004217007474442535, 'samples': 20651520, 'steps': 40334, 'loss/train': 1.787232756614685}
-03/05/2022 12:53:08 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 12:53:11 - INFO - codeparrot_training - Step 40335: {'lr': 0.00042169689023227987, 'samples': 20652032, 'steps': 40335, 'loss/train': 2.142812728881836}
-03/05/2022 12:53:14 - INFO - codeparrot_training - Step 40336: {'lr': 0.00042169303294294216, 'samples': 20652544, 'steps': 40336, 'loss/train': 0.7325757741928101}
-03/05/2022 12:53:16 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 12:53:20 - INFO - codeparrot_training - Step 40337: {'lr': 0.0004216891755762423, 'samples': 20653056, 'steps': 40337, 'loss/train': 2.296633243560791}
-03/05/2022 12:53:23 - INFO - codeparrot_training - Step 40338: {'lr': 0.00042168531813218193, 'samples': 20653568, 'steps': 40338, 'loss/train': 1.2176541090011597}
-03/05/2022 12:53:25 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/05/2022 12:53:28 - INFO - codeparrot_training - Step 40339: {'lr': 0.0004216814606107627, 'samples': 20654080, 'steps': 40339, 'loss/train': 2.2222280502319336}
-03/05/2022 12:53:31 - INFO - codeparrot_training - Step 40340: {'lr': 0.00042167760301198656, 'samples': 20654592, 'steps': 40340, 'loss/train': 1.4149153232574463}
-03/05/2022 12:53:33 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/05/2022 12:53:37 - INFO - codeparrot_training - Step 40341: {'lr': 0.0004216737453358551, 'samples': 20655104, 'steps': 40341, 'loss/train': 1.9043769836425781}
-03/05/2022 12:53:40 - INFO - codeparrot_training - Step 40342: {'lr': 0.00042166988758237013, 'samples': 20655616, 'steps': 40342, 'loss/train': 2.356032371520996}
-03/05/2022 12:53:42 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/05/2022 12:53:45 - INFO - codeparrot_training - Step 40343: {'lr': 0.00042166602975153333, 'samples': 20656128, 'steps': 40343, 'loss/train': 2.0854787826538086}
-03/05/2022 12:53:48 - INFO - codeparrot_training - Step 40344: {'lr': 0.0004216621718433465, 'samples': 20656640, 'steps': 40344, 'loss/train': 1.160915732383728}
-03/05/2022 12:53:51 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/05/2022 12:53:54 - INFO - codeparrot_training - Step 40345: {'lr': 0.0004216583138578113, 'samples': 20657152, 'steps': 40345, 'loss/train': 1.7056429386138916}
-03/05/2022 12:53:57 - INFO - codeparrot_training - Step 40346: {'lr': 0.00042165445579492956, 'samples': 20657664, 'steps': 40346, 'loss/train': 1.211523175239563}
-03/05/2022 12:53:59 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/05/2022 12:54:02 - INFO - codeparrot_training - Step 40347: {'lr': 0.00042165059765470294, 'samples': 20658176, 'steps': 40347, 'loss/train': 1.269286870956421}
-03/05/2022 12:54:05 - INFO - codeparrot_training - Step 40348: {'lr': 0.0004216467394371333, 'samples': 20658688, 'steps': 40348, 'loss/train': 2.2034244537353516}
-03/05/2022 12:54:08 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/05/2022 12:54:11 - INFO - codeparrot_training - Step 40349: {'lr': 0.00042164288114222213, 'samples': 20659200, 'steps': 40349, 'loss/train': 0.9977911710739136}
-03/05/2022 12:54:14 - INFO - codeparrot_training - Step 40350: {'lr': 0.0004216390227699714, 'samples': 20659712, 'steps': 40350, 'loss/train': 1.3264919519424438}
-03/05/2022 12:54:17 - INFO - codeparrot_training - Step 40351: {'lr': 0.0004216351643203828, 'samples': 20660224, 'steps': 40351, 'loss/train': 1.4736515283584595}
-03/05/2022 12:54:18 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/05/2022 12:54:23 - INFO - codeparrot_training - Step 40352: {'lr': 0.000421631305793458, 'samples': 20660736, 'steps': 40352, 'loss/train': 2.7394800186157227}
-03/05/2022 12:54:26 - INFO - codeparrot_training - Step 40353: {'lr': 0.00042162744718919875, 'samples': 20661248, 'steps': 40353, 'loss/train': 1.6738702058792114}
-03/05/2022 12:54:27 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/05/2022 12:54:31 - INFO - codeparrot_training - Step 40354: {'lr': 0.0004216235885076069, 'samples': 20661760, 'steps': 40354, 'loss/train': 0.9687190055847168}
-03/05/2022 12:54:34 - INFO - codeparrot_training - Step 40355: {'lr': 0.00042161972974868415, 'samples': 20662272, 'steps': 40355, 'loss/train': 2.260641574859619}
-03/05/2022 12:54:35 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 12:54:40 - INFO - codeparrot_training - Step 40356: {'lr': 0.00042161587091243215, 'samples': 20662784, 'steps': 40356, 'loss/train': 0.9091039896011353}
-03/05/2022 12:54:43 - INFO - codeparrot_training - Step 40357: {'lr': 0.00042161201199885257, 'samples': 20663296, 'steps': 40357, 'loss/train': 1.64747154712677}
-03/05/2022 12:54:44 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/05/2022 12:54:48 - INFO - codeparrot_training - Step 40358: {'lr': 0.0004216081530079474, 'samples': 20663808, 'steps': 40358, 'loss/train': 1.711816430091858}
-03/05/2022 12:54:51 - INFO - codeparrot_training - Step 40359: {'lr': 0.0004216042939397182, 'samples': 20664320, 'steps': 40359, 'loss/train': 1.868990421295166}
-03/05/2022 12:54:52 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/05/2022 12:54:57 - INFO - codeparrot_training - Step 40360: {'lr': 0.00042160043479416676, 'samples': 20664832, 'steps': 40360, 'loss/train': 1.6425817012786865}
-03/05/2022 12:55:00 - INFO - codeparrot_training - Step 40361: {'lr': 0.00042159657557129483, 'samples': 20665344, 'steps': 40361, 'loss/train': 1.5550633668899536}
-03/05/2022 12:55:00 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 12:55:05 - INFO - codeparrot_training - Step 40362: {'lr': 0.0004215927162711041, 'samples': 20665856, 'steps': 40362, 'loss/train': 1.6908413171768188}
-03/05/2022 12:55:08 - INFO - codeparrot_training - Step 40363: {'lr': 0.00042158885689359637, 'samples': 20666368, 'steps': 40363, 'loss/train': 3.022095203399658}
-03/05/2022 12:55:08 - INFO - codeparrot_training - Skipping example with length 903 (seq_length=1024)
-03/05/2022 12:55:13 - INFO - codeparrot_training - Step 40364: {'lr': 0.0004215849974387733, 'samples': 20666880, 'steps': 40364, 'loss/train': 1.7659708261489868}
-03/05/2022 12:55:17 - INFO - codeparrot_training - Step 40365: {'lr': 0.0004215811379066367, 'samples': 20667392, 'steps': 40365, 'loss/train': 1.6003681421279907}
-03/05/2022 12:55:17 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/05/2022 12:55:22 - INFO - codeparrot_training - Step 40366: {'lr': 0.00042157727829718827, 'samples': 20667904, 'steps': 40366, 'loss/train': 2.088017225265503}
-03/05/2022 12:55:25 - INFO - codeparrot_training - Step 40367: {'lr': 0.00042157341861042986, 'samples': 20668416, 'steps': 40367, 'loss/train': 2.4340786933898926}
-03/05/2022 12:55:25 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 12:55:30 - INFO - codeparrot_training - Step 40368: {'lr': 0.00042156955884636307, 'samples': 20668928, 'steps': 40368, 'loss/train': 1.2669000625610352}
-03/05/2022 12:55:34 - INFO - codeparrot_training - Step 40369: {'lr': 0.0004215656990049896, 'samples': 20669440, 'steps': 40369, 'loss/train': 0.949313759803772}
-03/05/2022 12:55:34 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/05/2022 12:55:39 - INFO - codeparrot_training - Step 40370: {'lr': 0.0004215618390863114, 'samples': 20669952, 'steps': 40370, 'loss/train': 1.9419571161270142}
-03/05/2022 12:55:42 - INFO - codeparrot_training - Step 40371: {'lr': 0.00042155797909033, 'samples': 20670464, 'steps': 40371, 'loss/train': 1.8753588199615479}
-03/05/2022 12:55:42 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/05/2022 12:55:47 - INFO - codeparrot_training - Step 40372: {'lr': 0.00042155411901704723, 'samples': 20670976, 'steps': 40372, 'loss/train': 1.2074916362762451}
-03/05/2022 12:55:51 - INFO - codeparrot_training - Step 40373: {'lr': 0.0004215502588664648, 'samples': 20671488, 'steps': 40373, 'loss/train': 1.6162254810333252}
-03/05/2022 12:55:51 - INFO - codeparrot_training - Skipping example with length 992 (seq_length=1024)
-03/05/2022 12:55:56 - INFO - codeparrot_training - Step 40374: {'lr': 0.0004215463986385845, 'samples': 20672000, 'steps': 40374, 'loss/train': 1.6806952953338623}
-03/05/2022 12:55:59 - INFO - codeparrot_training - Step 40375: {'lr': 0.0004215425383334081, 'samples': 20672512, 'steps': 40375, 'loss/train': 1.0073401927947998}
-03/05/2022 12:55:59 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/05/2022 12:56:05 - INFO - codeparrot_training - Step 40376: {'lr': 0.00042153867795093714, 'samples': 20673024, 'steps': 40376, 'loss/train': 1.6950125694274902}
-03/05/2022 12:56:08 - INFO - codeparrot_training - Step 40377: {'lr': 0.0004215348174911736, 'samples': 20673536, 'steps': 40377, 'loss/train': 0.7287610173225403}
-03/05/2022 12:56:08 - INFO - codeparrot_training - Skipping example with length 225 (seq_length=1024)
-03/05/2022 12:56:13 - INFO - codeparrot_training - Step 40378: {'lr': 0.0004215309569541191, 'samples': 20674048, 'steps': 40378, 'loss/train': 1.9431819915771484}
-03/05/2022 12:56:16 - INFO - codeparrot_training - Step 40379: {'lr': 0.00042152709633977545, 'samples': 20674560, 'steps': 40379, 'loss/train': 1.4730685949325562}
-03/05/2022 12:56:16 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/05/2022 12:56:22 - INFO - codeparrot_training - Step 40380: {'lr': 0.0004215232356481442, 'samples': 20675072, 'steps': 40380, 'loss/train': 1.224008560180664}
-03/05/2022 12:56:25 - INFO - codeparrot_training - Step 40381: {'lr': 0.0004215193748792273, 'samples': 20675584, 'steps': 40381, 'loss/train': 1.7239350080490112}
-03/05/2022 12:56:25 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/05/2022 12:56:30 - INFO - codeparrot_training - Step 40382: {'lr': 0.00042151551403302645, 'samples': 20676096, 'steps': 40382, 'loss/train': 1.7135679721832275}
-03/05/2022 12:56:33 - INFO - codeparrot_training - Step 40383: {'lr': 0.00042151165310954335, 'samples': 20676608, 'steps': 40383, 'loss/train': 0.8786811828613281}
-03/05/2022 12:56:33 - INFO - codeparrot_training - Skipping example with length 205 (seq_length=1024)
-03/05/2022 12:56:39 - INFO - codeparrot_training - Step 40384: {'lr': 0.0004215077921087798, 'samples': 20677120, 'steps': 40384, 'loss/train': 1.348458170890808}
-03/05/2022 12:56:42 - INFO - codeparrot_training - Step 40385: {'lr': 0.00042150393103073736, 'samples': 20677632, 'steps': 40385, 'loss/train': 1.6739588975906372}
-03/05/2022 12:56:43 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 12:56:47 - INFO - codeparrot_training - Step 40386: {'lr': 0.00042150006987541795, 'samples': 20678144, 'steps': 40386, 'loss/train': 1.393949031829834}
-03/05/2022 12:56:50 - INFO - codeparrot_training - Step 40387: {'lr': 0.0004214962086428232, 'samples': 20678656, 'steps': 40387, 'loss/train': 1.1483789682388306}
-03/05/2022 12:56:51 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/05/2022 12:56:55 - INFO - codeparrot_training - Step 40388: {'lr': 0.00042149234733295497, 'samples': 20679168, 'steps': 40388, 'loss/train': 2.563614845275879}
-03/05/2022 12:56:59 - INFO - codeparrot_training - Step 40389: {'lr': 0.00042148848594581503, 'samples': 20679680, 'steps': 40389, 'loss/train': 1.7633692026138306}
-03/05/2022 12:56:59 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 12:57:04 - INFO - codeparrot_training - Step 40390: {'lr': 0.00042148462448140487, 'samples': 20680192, 'steps': 40390, 'loss/train': 1.609235405921936}
-03/05/2022 12:57:07 - INFO - codeparrot_training - Step 40391: {'lr': 0.0004214807629397264, 'samples': 20680704, 'steps': 40391, 'loss/train': 1.716700553894043}
-03/05/2022 12:57:08 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 12:57:13 - INFO - codeparrot_training - Step 40392: {'lr': 0.00042147690132078136, 'samples': 20681216, 'steps': 40392, 'loss/train': 1.8902121782302856}
-03/05/2022 12:57:16 - INFO - codeparrot_training - Step 40393: {'lr': 0.0004214730396245715, 'samples': 20681728, 'steps': 40393, 'loss/train': 1.286687970161438}
-03/05/2022 12:57:16 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/05/2022 12:57:21 - INFO - codeparrot_training - Step 40394: {'lr': 0.0004214691778510985, 'samples': 20682240, 'steps': 40394, 'loss/train': 1.6278773546218872}
-03/05/2022 12:57:24 - INFO - codeparrot_training - Step 40395: {'lr': 0.0004214653160003642, 'samples': 20682752, 'steps': 40395, 'loss/train': 1.3448028564453125}
-03/05/2022 12:57:24 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/05/2022 12:57:29 - INFO - codeparrot_training - Step 40396: {'lr': 0.00042146145407237023, 'samples': 20683264, 'steps': 40396, 'loss/train': 1.7101707458496094}
-03/05/2022 12:57:33 - INFO - codeparrot_training - Step 40397: {'lr': 0.00042145759206711834, 'samples': 20683776, 'steps': 40397, 'loss/train': 1.7709565162658691}
-03/05/2022 12:57:33 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/05/2022 12:57:39 - INFO - codeparrot_training - Step 40398: {'lr': 0.0004214537299846104, 'samples': 20684288, 'steps': 40398, 'loss/train': 1.4574381113052368}
-03/05/2022 12:57:42 - INFO - codeparrot_training - Step 40399: {'lr': 0.00042144986782484796, 'samples': 20684800, 'steps': 40399, 'loss/train': 2.3374555110931396}
-03/05/2022 12:57:44 - INFO - codeparrot_training - Skipping example with length 1010 (seq_length=1024)
-03/05/2022 12:57:47 - INFO - codeparrot_training - Step 40400: {'lr': 0.00042144600558783284, 'samples': 20685312, 'steps': 40400, 'loss/train': 1.3583827018737793}
-03/05/2022 12:57:50 - INFO - codeparrot_training - Step 40401: {'lr': 0.0004214421432735669, 'samples': 20685824, 'steps': 40401, 'loss/train': 1.7995244264602661}
-03/05/2022 12:57:53 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 12:57:55 - INFO - codeparrot_training - Step 40402: {'lr': 0.0004214382808820517, 'samples': 20686336, 'steps': 40402, 'loss/train': 1.208327054977417}
-03/05/2022 12:57:59 - INFO - codeparrot_training - Step 40403: {'lr': 0.0004214344184132891, 'samples': 20686848, 'steps': 40403, 'loss/train': 2.945127487182617}
-03/05/2022 12:58:01 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/05/2022 12:58:04 - INFO - codeparrot_training - Step 40404: {'lr': 0.0004214305558672808, 'samples': 20687360, 'steps': 40404, 'loss/train': 1.7858608961105347}
-03/05/2022 12:58:07 - INFO - codeparrot_training - Step 40405: {'lr': 0.0004214266932440285, 'samples': 20687872, 'steps': 40405, 'loss/train': 2.7339656352996826}
-03/05/2022 12:58:10 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 12:58:13 - INFO - codeparrot_training - Step 40406: {'lr': 0.000421422830543534, 'samples': 20688384, 'steps': 40406, 'loss/train': 0.13135404884815216}
-03/05/2022 12:58:16 - INFO - codeparrot_training - Step 40407: {'lr': 0.00042141896776579904, 'samples': 20688896, 'steps': 40407, 'loss/train': 1.8912774324417114}
-03/05/2022 12:58:19 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/05/2022 12:58:21 - INFO - codeparrot_training - Step 40408: {'lr': 0.0004214151049108252, 'samples': 20689408, 'steps': 40408, 'loss/train': 3.0950307846069336}
-03/05/2022 12:58:24 - INFO - codeparrot_training - Step 40409: {'lr': 0.00042141124197861456, 'samples': 20689920, 'steps': 40409, 'loss/train': 1.602133870124817}
-03/05/2022 12:58:27 - INFO - codeparrot_training - Skipping example with length 814 (seq_length=1024)
-03/05/2022 12:58:30 - INFO - codeparrot_training - Step 40410: {'lr': 0.0004214073789691686, 'samples': 20690432, 'steps': 40410, 'loss/train': 1.0112121105194092}
-03/05/2022 12:58:33 - INFO - codeparrot_training - Step 40411: {'lr': 0.00042140351588248906, 'samples': 20690944, 'steps': 40411, 'loss/train': 0.4828191101551056}
-03/05/2022 12:58:35 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/05/2022 12:58:38 - INFO - codeparrot_training - Step 40412: {'lr': 0.00042139965271857774, 'samples': 20691456, 'steps': 40412, 'loss/train': 1.8102251291275024}
-03/05/2022 12:58:41 - INFO - codeparrot_training - Step 40413: {'lr': 0.0004213957894774364, 'samples': 20691968, 'steps': 40413, 'loss/train': 0.9536743760108948}
-03/05/2022 12:58:44 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/05/2022 12:58:47 - INFO - codeparrot_training - Step 40414: {'lr': 0.0004213919261590667, 'samples': 20692480, 'steps': 40414, 'loss/train': 2.5317165851593018}
-03/05/2022 12:58:50 - INFO - codeparrot_training - Step 40415: {'lr': 0.0004213880627634705, 'samples': 20692992, 'steps': 40415, 'loss/train': 1.9899123907089233}
-03/05/2022 12:58:52 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/05/2022 12:58:55 - INFO - codeparrot_training - Step 40416: {'lr': 0.0004213841992906496, 'samples': 20693504, 'steps': 40416, 'loss/train': 1.7682116031646729}
-03/05/2022 12:58:58 - INFO - codeparrot_training - Step 40417: {'lr': 0.0004213803357406055, 'samples': 20694016, 'steps': 40417, 'loss/train': 1.7396270036697388}
-03/05/2022 12:59:00 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/05/2022 12:59:03 - INFO - codeparrot_training - Step 40418: {'lr': 0.00042137647211334007, 'samples': 20694528, 'steps': 40418, 'loss/train': 1.9525171518325806}
-03/05/2022 12:59:07 - INFO - codeparrot_training - Step 40419: {'lr': 0.000421372608408855, 'samples': 20695040, 'steps': 40419, 'loss/train': 1.0113167762756348}
-03/05/2022 12:59:09 - INFO - codeparrot_training - Skipping example with length 1011 (seq_length=1024)
-03/05/2022 12:59:12 - INFO - codeparrot_training - Step 40420: {'lr': 0.0004213687446271522, 'samples': 20695552, 'steps': 40420, 'loss/train': 2.3042619228363037}
-03/05/2022 12:59:15 - INFO - codeparrot_training - Step 40421: {'lr': 0.0004213648807682332, 'samples': 20696064, 'steps': 40421, 'loss/train': 1.7643669843673706}
-03/05/2022 12:59:18 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/05/2022 12:59:20 - INFO - codeparrot_training - Step 40422: {'lr': 0.00042136101683209993, 'samples': 20696576, 'steps': 40422, 'loss/train': 1.6008896827697754}
-03/05/2022 12:59:24 - INFO - codeparrot_training - Step 40423: {'lr': 0.00042135715281875393, 'samples': 20697088, 'steps': 40423, 'loss/train': 1.5414414405822754}
-03/05/2022 12:59:26 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/05/2022 12:59:29 - INFO - codeparrot_training - Step 40424: {'lr': 0.000421353288728197, 'samples': 20697600, 'steps': 40424, 'loss/train': 2.1668522357940674}
-03/05/2022 12:59:32 - INFO - codeparrot_training - Step 40425: {'lr': 0.00042134942456043104, 'samples': 20698112, 'steps': 40425, 'loss/train': 1.9574054479599}
-03/05/2022 12:59:35 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/05/2022 12:59:37 - INFO - codeparrot_training - Step 40426: {'lr': 0.00042134556031545755, 'samples': 20698624, 'steps': 40426, 'loss/train': 1.439299464225769}
-03/05/2022 12:59:41 - INFO - codeparrot_training - Step 40427: {'lr': 0.0004213416959932785, 'samples': 20699136, 'steps': 40427, 'loss/train': 1.8368465900421143}
-03/05/2022 12:59:43 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/05/2022 12:59:46 - INFO - codeparrot_training - Step 40428: {'lr': 0.0004213378315938955, 'samples': 20699648, 'steps': 40428, 'loss/train': 2.3524179458618164}
-03/05/2022 12:59:49 - INFO - codeparrot_training - Step 40429: {'lr': 0.0004213339671173103, 'samples': 20700160, 'steps': 40429, 'loss/train': 1.7115963697433472}
-03/05/2022 12:59:52 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/05/2022 12:59:55 - INFO - codeparrot_training - Step 40430: {'lr': 0.00042133010256352466, 'samples': 20700672, 'steps': 40430, 'loss/train': 0.7688522338867188}
-03/05/2022 12:59:58 - INFO - codeparrot_training - Step 40431: {'lr': 0.00042132623793254034, 'samples': 20701184, 'steps': 40431, 'loss/train': 2.027472496032715}
-03/05/2022 13:00:01 - INFO - codeparrot_training - Step 40432: {'lr': 0.0004213223732243591, 'samples': 20701696, 'steps': 40432, 'loss/train': 2.3814525604248047}
-03/05/2022 13:00:02 - INFO - codeparrot_training - Skipping example with length 663 (seq_length=1024)
-03/05/2022 13:00:06 - INFO - codeparrot_training - Step 40433: {'lr': 0.00042131850843898255, 'samples': 20702208, 'steps': 40433, 'loss/train': 2.0063397884368896}
-03/05/2022 13:00:09 - INFO - codeparrot_training - Step 40434: {'lr': 0.0004213146435764126, 'samples': 20702720, 'steps': 40434, 'loss/train': 1.459519624710083}
-03/05/2022 13:00:10 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/05/2022 13:00:15 - INFO - codeparrot_training - Step 40435: {'lr': 0.00042131077863665086, 'samples': 20703232, 'steps': 40435, 'loss/train': 1.7103214263916016}
-03/05/2022 13:00:18 - INFO - codeparrot_training - Step 40436: {'lr': 0.00042130691361969914, 'samples': 20703744, 'steps': 40436, 'loss/train': 1.070001482963562}
-03/05/2022 13:00:18 - INFO - codeparrot_training - Skipping example with length 633 (seq_length=1024)
-03/05/2022 13:00:23 - INFO - codeparrot_training - Step 40437: {'lr': 0.00042130304852555916, 'samples': 20704256, 'steps': 40437, 'loss/train': 1.699519157409668}
-03/05/2022 13:00:26 - INFO - codeparrot_training - Step 40438: {'lr': 0.00042129918335423265, 'samples': 20704768, 'steps': 40438, 'loss/train': 2.064394235610962}
-03/05/2022 13:00:27 - INFO - codeparrot_training - Skipping example with length 938 (seq_length=1024)
-03/05/2022 13:00:32 - INFO - codeparrot_training - Step 40439: {'lr': 0.0004212953181057214, 'samples': 20705280, 'steps': 40439, 'loss/train': 1.8346575498580933}
-03/05/2022 13:00:35 - INFO - codeparrot_training - Step 40440: {'lr': 0.0004212914527800272, 'samples': 20705792, 'steps': 40440, 'loss/train': 1.8808594942092896}
-03/05/2022 13:00:35 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/05/2022 13:00:40 - INFO - codeparrot_training - Step 40441: {'lr': 0.0004212875873771516, 'samples': 20706304, 'steps': 40441, 'loss/train': 1.5219106674194336}
-03/05/2022 13:00:43 - INFO - codeparrot_training - Step 40442: {'lr': 0.0004212837218970965, 'samples': 20706816, 'steps': 40442, 'loss/train': 2.1068472862243652}
-03/05/2022 13:00:44 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/05/2022 13:00:49 - INFO - codeparrot_training - Step 40443: {'lr': 0.00042127985633986365, 'samples': 20707328, 'steps': 40443, 'loss/train': 2.0398902893066406}
-03/05/2022 13:00:52 - INFO - codeparrot_training - Step 40444: {'lr': 0.0004212759907054546, 'samples': 20707840, 'steps': 40444, 'loss/train': 2.1075222492218018}
-03/05/2022 13:00:52 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/05/2022 13:00:58 - INFO - codeparrot_training - Step 40445: {'lr': 0.00042127212499387136, 'samples': 20708352, 'steps': 40445, 'loss/train': 0.8281036019325256}
-03/05/2022 13:01:01 - INFO - codeparrot_training - Step 40446: {'lr': 0.0004212682592051155, 'samples': 20708864, 'steps': 40446, 'loss/train': 0.5361807942390442}
-03/05/2022 13:01:02 - INFO - codeparrot_training - Skipping example with length 775 (seq_length=1024)
-03/05/2022 13:01:06 - INFO - codeparrot_training - Step 40447: {'lr': 0.0004212643933391888, 'samples': 20709376, 'steps': 40447, 'loss/train': 1.4625929594039917}
-03/05/2022 13:01:09 - INFO - codeparrot_training - Step 40448: {'lr': 0.000421260527396093, 'samples': 20709888, 'steps': 40448, 'loss/train': 0.3280651569366455}
-03/05/2022 13:01:11 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/05/2022 13:01:15 - INFO - codeparrot_training - Step 40449: {'lr': 0.0004212566613758299, 'samples': 20710400, 'steps': 40449, 'loss/train': 1.0910710096359253}
-03/05/2022 13:01:18 - INFO - codeparrot_training - Step 40450: {'lr': 0.00042125279527840124, 'samples': 20710912, 'steps': 40450, 'loss/train': 1.8031296730041504}
-03/05/2022 13:01:20 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/05/2022 13:01:23 - INFO - codeparrot_training - Step 40451: {'lr': 0.0004212489291038085, 'samples': 20711424, 'steps': 40451, 'loss/train': 1.6279146671295166}
-03/05/2022 13:01:26 - INFO - codeparrot_training - Step 40452: {'lr': 0.0004212450628520538, 'samples': 20711936, 'steps': 40452, 'loss/train': 2.129652976989746}
-03/05/2022 13:01:28 - INFO - codeparrot_training - Skipping example with length 754 (seq_length=1024)
-03/05/2022 13:01:32 - INFO - codeparrot_training - Step 40453: {'lr': 0.0004212411965231387, 'samples': 20712448, 'steps': 40453, 'loss/train': 1.7844544649124146}
-03/05/2022 13:01:35 - INFO - codeparrot_training - Step 40454: {'lr': 0.0004212373301170649, 'samples': 20712960, 'steps': 40454, 'loss/train': 0.6720020174980164}
-03/05/2022 13:01:37 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/05/2022 13:01:40 - INFO - codeparrot_training - Step 40455: {'lr': 0.00042123346363383426, 'samples': 20713472, 'steps': 40455, 'loss/train': 1.6479519605636597}
-03/05/2022 13:01:43 - INFO - codeparrot_training - Step 40456: {'lr': 0.0004212295970734484, 'samples': 20713984, 'steps': 40456, 'loss/train': 1.8850681781768799}
-03/05/2022 13:01:45 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/05/2022 13:01:49 - INFO - codeparrot_training - Step 40457: {'lr': 0.00042122573043590925, 'samples': 20714496, 'steps': 40457, 'loss/train': 1.4840099811553955}
-03/05/2022 13:01:52 - INFO - codeparrot_training - Step 40458: {'lr': 0.0004212218637212183, 'samples': 20715008, 'steps': 40458, 'loss/train': 1.8641413450241089}
-03/05/2022 13:01:54 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 13:01:57 - INFO - codeparrot_training - Step 40459: {'lr': 0.00042121799692937747, 'samples': 20715520, 'steps': 40459, 'loss/train': 2.2151408195495605}
-03/05/2022 13:02:00 - INFO - codeparrot_training - Step 40460: {'lr': 0.00042121413006038845, 'samples': 20716032, 'steps': 40460, 'loss/train': 2.5388576984405518}
-03/05/2022 13:02:02 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/05/2022 13:02:06 - INFO - codeparrot_training - Step 40461: {'lr': 0.000421210263114253, 'samples': 20716544, 'steps': 40461, 'loss/train': 0.24657876789569855}
-03/05/2022 13:02:09 - INFO - codeparrot_training - Step 40462: {'lr': 0.00042120639609097277, 'samples': 20717056, 'steps': 40462, 'loss/train': 1.4923537969589233}
-03/05/2022 13:02:11 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/05/2022 13:02:14 - INFO - codeparrot_training - Step 40463: {'lr': 0.0004212025289905497, 'samples': 20717568, 'steps': 40463, 'loss/train': 1.5568737983703613}
-03/05/2022 13:02:17 - INFO - codeparrot_training - Step 40464: {'lr': 0.0004211986618129854, 'samples': 20718080, 'steps': 40464, 'loss/train': 1.427642583847046}
-03/05/2022 13:02:19 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/05/2022 13:02:22 - INFO - codeparrot_training - Step 40465: {'lr': 0.00042119479455828153, 'samples': 20718592, 'steps': 40465, 'loss/train': 2.0156407356262207}
-03/05/2022 13:02:26 - INFO - codeparrot_training - Step 40466: {'lr': 0.00042119092722644, 'samples': 20719104, 'steps': 40466, 'loss/train': 1.5152536630630493}
-03/05/2022 13:02:27 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/05/2022 13:02:31 - INFO - codeparrot_training - Step 40467: {'lr': 0.0004211870598174624, 'samples': 20719616, 'steps': 40467, 'loss/train': 1.8197591304779053}
-03/05/2022 13:02:34 - INFO - codeparrot_training - Step 40468: {'lr': 0.0004211831923313506, 'samples': 20720128, 'steps': 40468, 'loss/train': 0.12048035115003586}
-03/05/2022 13:02:36 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/05/2022 13:02:40 - INFO - codeparrot_training - Step 40469: {'lr': 0.0004211793247681064, 'samples': 20720640, 'steps': 40469, 'loss/train': 2.8310811519622803}
-03/05/2022 13:02:43 - INFO - codeparrot_training - Step 40470: {'lr': 0.0004211754571277313, 'samples': 20721152, 'steps': 40470, 'loss/train': 1.6204134225845337}
-03/05/2022 13:02:45 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/05/2022 13:02:48 - INFO - codeparrot_training - Step 40471: {'lr': 0.0004211715894102272, 'samples': 20721664, 'steps': 40471, 'loss/train': 0.06425996124744415}
-03/05/2022 13:02:51 - INFO - codeparrot_training - Step 40472: {'lr': 0.00042116772161559585, 'samples': 20722176, 'steps': 40472, 'loss/train': 1.3094398975372314}
-03/05/2022 13:02:54 - INFO - codeparrot_training - Skipping example with length 390 (seq_length=1024)
-03/05/2022 13:02:57 - INFO - codeparrot_training - Step 40473: {'lr': 0.0004211638537438389, 'samples': 20722688, 'steps': 40473, 'loss/train': 2.0183467864990234}
-03/05/2022 13:03:00 - INFO - codeparrot_training - Step 40474: {'lr': 0.0004211599857949583, 'samples': 20723200, 'steps': 40474, 'loss/train': 1.3488357067108154}
-03/05/2022 13:03:03 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/05/2022 13:03:05 - INFO - codeparrot_training - Step 40475: {'lr': 0.00042115611776895556, 'samples': 20723712, 'steps': 40475, 'loss/train': 1.3609415292739868}
-03/05/2022 13:03:08 - INFO - codeparrot_training - Step 40476: {'lr': 0.00042115224966583255, 'samples': 20724224, 'steps': 40476, 'loss/train': 1.0609122514724731}
-03/05/2022 13:03:11 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 13:03:14 - INFO - codeparrot_training - Step 40477: {'lr': 0.00042114838148559093, 'samples': 20724736, 'steps': 40477, 'loss/train': 2.4370596408843994}
-03/05/2022 13:03:17 - INFO - codeparrot_training - Step 40478: {'lr': 0.0004211445132282325, 'samples': 20725248, 'steps': 40478, 'loss/train': 1.23561429977417}
-03/05/2022 13:03:19 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/05/2022 13:03:22 - INFO - codeparrot_training - Step 40479: {'lr': 0.000421140644893759, 'samples': 20725760, 'steps': 40479, 'loss/train': 1.4060800075531006}
-03/05/2022 13:03:25 - INFO - codeparrot_training - Step 40480: {'lr': 0.0004211367764821722, 'samples': 20726272, 'steps': 40480, 'loss/train': 1.4225828647613525}
-03/05/2022 13:03:28 - INFO - codeparrot_training - Skipping example with length 493 (seq_length=1024)
-03/05/2022 13:03:31 - INFO - codeparrot_training - Step 40481: {'lr': 0.00042113290799347376, 'samples': 20726784, 'steps': 40481, 'loss/train': 1.8455241918563843}
-03/05/2022 13:03:34 - INFO - codeparrot_training - Step 40482: {'lr': 0.00042112903942766546, 'samples': 20727296, 'steps': 40482, 'loss/train': 1.7216932773590088}
-03/05/2022 13:03:36 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/05/2022 13:03:39 - INFO - codeparrot_training - Step 40483: {'lr': 0.00042112517078474914, 'samples': 20727808, 'steps': 40483, 'loss/train': 1.8887310028076172}
-03/05/2022 13:03:42 - INFO - codeparrot_training - Step 40484: {'lr': 0.0004211213020647264, 'samples': 20728320, 'steps': 40484, 'loss/train': 1.6480332612991333}
-03/05/2022 13:03:44 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/05/2022 13:03:48 - INFO - codeparrot_training - Step 40485: {'lr': 0.00042111743326759903, 'samples': 20728832, 'steps': 40485, 'loss/train': 1.9263304471969604}
-03/05/2022 13:03:51 - INFO - codeparrot_training - Step 40486: {'lr': 0.00042111356439336877, 'samples': 20729344, 'steps': 40486, 'loss/train': 1.3970844745635986}
-03/05/2022 13:03:53 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/05/2022 13:03:56 - INFO - codeparrot_training - Step 40487: {'lr': 0.0004211096954420375, 'samples': 20729856, 'steps': 40487, 'loss/train': 2.2267203330993652}
-03/05/2022 13:03:59 - INFO - codeparrot_training - Step 40488: {'lr': 0.0004211058264136067, 'samples': 20730368, 'steps': 40488, 'loss/train': 1.5073891878128052}
-03/05/2022 13:04:02 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/05/2022 13:04:05 - INFO - codeparrot_training - Step 40489: {'lr': 0.0004211019573080783, 'samples': 20730880, 'steps': 40489, 'loss/train': 2.1810362339019775}
-03/05/2022 13:04:08 - INFO - codeparrot_training - Step 40490: {'lr': 0.00042109808812545405, 'samples': 20731392, 'steps': 40490, 'loss/train': 1.982108235359192}
-03/05/2022 13:04:10 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/05/2022 13:04:13 - INFO - codeparrot_training - Step 40491: {'lr': 0.0004210942188657356, 'samples': 20731904, 'steps': 40491, 'loss/train': 1.579054832458496}
-03/05/2022 13:04:16 - INFO - codeparrot_training - Step 40492: {'lr': 0.00042109034952892473, 'samples': 20732416, 'steps': 40492, 'loss/train': 1.6329907178878784}
-03/05/2022 13:04:18 - INFO - codeparrot_training - Skipping example with length 332 (seq_length=1024)
-03/05/2022 13:04:22 - INFO - codeparrot_training - Step 40493: {'lr': 0.00042108648011502314, 'samples': 20732928, 'steps': 40493, 'loss/train': 0.17180968821048737}
-03/05/2022 13:04:25 - INFO - codeparrot_training - Step 40494: {'lr': 0.00042108261062403276, 'samples': 20733440, 'steps': 40494, 'loss/train': 6.234177112579346}
-03/05/2022 13:04:26 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/05/2022 13:04:30 - INFO - codeparrot_training - Step 40495: {'lr': 0.00042107874105595507, 'samples': 20733952, 'steps': 40495, 'loss/train': 1.6370471715927124}
-03/05/2022 13:04:33 - INFO - codeparrot_training - Step 40496: {'lr': 0.00042107487141079206, 'samples': 20734464, 'steps': 40496, 'loss/train': 1.680106282234192}
-03/05/2022 13:04:35 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/05/2022 13:04:39 - INFO - codeparrot_training - Step 40497: {'lr': 0.00042107100168854516, 'samples': 20734976, 'steps': 40497, 'loss/train': 1.5704518556594849}
-03/05/2022 13:04:42 - INFO - codeparrot_training - Step 40498: {'lr': 0.00042106713188921647, 'samples': 20735488, 'steps': 40498, 'loss/train': 0.9190590977668762}
-03/05/2022 13:04:45 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/05/2022 13:04:47 - INFO - codeparrot_training - Step 40499: {'lr': 0.00042106326201280756, 'samples': 20736000, 'steps': 40499, 'loss/train': 1.778525710105896}
-03/05/2022 13:04:50 - INFO - codeparrot_training - Step 40500: {'lr': 0.0004210593920593201, 'samples': 20736512, 'steps': 40500, 'loss/train': 2.459087371826172}
-03/05/2022 13:04:53 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/05/2022 13:04:56 - INFO - codeparrot_training - Step 40501: {'lr': 0.000421055522028756, 'samples': 20737024, 'steps': 40501, 'loss/train': 1.4212647676467896}
-03/05/2022 13:04:59 - INFO - codeparrot_training - Step 40502: {'lr': 0.00042105165192111684, 'samples': 20737536, 'steps': 40502, 'loss/train': 1.6367316246032715}
-03/05/2022 13:05:01 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/05/2022 13:05:04 - INFO - codeparrot_training - Step 40503: {'lr': 0.00042104778173640453, 'samples': 20738048, 'steps': 40503, 'loss/train': 1.6660511493682861}
-03/05/2022 13:05:07 - INFO - codeparrot_training - Step 40504: {'lr': 0.0004210439114746206, 'samples': 20738560, 'steps': 40504, 'loss/train': 1.747920036315918}
-03/05/2022 13:05:10 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/05/2022 13:05:13 - INFO - codeparrot_training - Step 40505: {'lr': 0.00042104004113576707, 'samples': 20739072, 'steps': 40505, 'loss/train': 1.8140813112258911}
-03/05/2022 13:05:16 - INFO - codeparrot_training - Step 40506: {'lr': 0.00042103617071984544, 'samples': 20739584, 'steps': 40506, 'loss/train': 2.1517508029937744}
-03/05/2022 13:05:18 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/05/2022 13:05:21 - INFO - codeparrot_training - Step 40507: {'lr': 0.00042103230022685765, 'samples': 20740096, 'steps': 40507, 'loss/train': 1.3578181266784668}
-03/05/2022 13:05:24 - INFO - codeparrot_training - Step 40508: {'lr': 0.0004210284296568052, 'samples': 20740608, 'steps': 40508, 'loss/train': 2.1557819843292236}
-03/05/2022 13:05:26 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/05/2022 13:05:29 - INFO - codeparrot_training - Step 40509: {'lr': 0.0004210245590096901, 'samples': 20741120, 'steps': 40509, 'loss/train': 1.4781718254089355}
-03/05/2022 13:05:33 - INFO - codeparrot_training - Step 40510: {'lr': 0.000421020688285514, 'samples': 20741632, 'steps': 40510, 'loss/train': 1.686828374862671}
-03/05/2022 13:05:35 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/05/2022 13:05:38 - INFO - codeparrot_training - Step 40511: {'lr': 0.0004210168174842785, 'samples': 20742144, 'steps': 40511, 'loss/train': 1.8903236389160156}
-03/05/2022 13:05:41 - INFO - codeparrot_training - Step 40512: {'lr': 0.00042101294660598556, 'samples': 20742656, 'steps': 40512, 'loss/train': 0.7560727596282959}
-03/05/2022 13:05:44 - INFO - codeparrot_training - Step 40513: {'lr': 0.0004210090756506367, 'samples': 20743168, 'steps': 40513, 'loss/train': 2.10577392578125}
-03/05/2022 13:05:45 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 13:05:50 - INFO - codeparrot_training - Step 40514: {'lr': 0.0004210052046182339, 'samples': 20743680, 'steps': 40514, 'loss/train': 2.329699754714966}
-03/05/2022 13:05:53 - INFO - codeparrot_training - Step 40515: {'lr': 0.0004210013335087787, 'samples': 20744192, 'steps': 40515, 'loss/train': 1.962345004081726}
-03/05/2022 13:05:53 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/05/2022 13:05:58 - INFO - codeparrot_training - Step 40516: {'lr': 0.000420997462322273, 'samples': 20744704, 'steps': 40516, 'loss/train': 1.3428285121917725}
-03/05/2022 13:06:01 - INFO - codeparrot_training - Step 40517: {'lr': 0.00042099359105871856, 'samples': 20745216, 'steps': 40517, 'loss/train': 1.6272666454315186}
-03/05/2022 13:06:02 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/05/2022 13:06:07 - INFO - codeparrot_training - Step 40518: {'lr': 0.00042098971971811695, 'samples': 20745728, 'steps': 40518, 'loss/train': 1.5761278867721558}
-03/05/2022 13:06:10 - INFO - codeparrot_training - Step 40519: {'lr': 0.00042098584830047004, 'samples': 20746240, 'steps': 40519, 'loss/train': 1.4719390869140625}
-03/05/2022 13:06:10 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/05/2022 13:06:15 - INFO - codeparrot_training - Step 40520: {'lr': 0.00042098197680577956, 'samples': 20746752, 'steps': 40520, 'loss/train': 0.7827234864234924}
-03/05/2022 13:06:18 - INFO - codeparrot_training - Step 40521: {'lr': 0.00042097810523404714, 'samples': 20747264, 'steps': 40521, 'loss/train': 1.4584271907806396}
-03/05/2022 13:06:19 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 13:06:24 - INFO - codeparrot_training - Step 40522: {'lr': 0.0004209742335852747, 'samples': 20747776, 'steps': 40522, 'loss/train': 1.4485782384872437}
-03/05/2022 13:06:27 - INFO - codeparrot_training - Step 40523: {'lr': 0.0004209703618594639, 'samples': 20748288, 'steps': 40523, 'loss/train': 1.7003995180130005}
-03/05/2022 13:06:27 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/05/2022 13:06:32 - INFO - codeparrot_training - Step 40524: {'lr': 0.00042096649005661654, 'samples': 20748800, 'steps': 40524, 'loss/train': 1.6282175779342651}
-03/05/2022 13:06:35 - INFO - codeparrot_training - Step 40525: {'lr': 0.00042096261817673423, 'samples': 20749312, 'steps': 40525, 'loss/train': 1.5166821479797363}
-03/05/2022 13:06:36 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/05/2022 13:06:41 - INFO - codeparrot_training - Step 40526: {'lr': 0.0004209587462198189, 'samples': 20749824, 'steps': 40526, 'loss/train': 1.4901609420776367}
-03/05/2022 13:06:44 - INFO - codeparrot_training - Step 40527: {'lr': 0.0004209548741858721, 'samples': 20750336, 'steps': 40527, 'loss/train': 1.5285699367523193}
-03/05/2022 13:06:46 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/05/2022 13:06:49 - INFO - codeparrot_training - Step 40528: {'lr': 0.00042095100207489573, 'samples': 20750848, 'steps': 40528, 'loss/train': 1.6518371105194092}
-03/05/2022 13:06:52 - INFO - codeparrot_training - Step 40529: {'lr': 0.0004209471298868914, 'samples': 20751360, 'steps': 40529, 'loss/train': 1.4010772705078125}
-03/05/2022 13:06:54 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/05/2022 13:06:58 - INFO - codeparrot_training - Step 40530: {'lr': 0.00042094325762186103, 'samples': 20751872, 'steps': 40530, 'loss/train': 1.8935110569000244}
-03/05/2022 13:07:01 - INFO - codeparrot_training - Step 40531: {'lr': 0.0004209393852798062, 'samples': 20752384, 'steps': 40531, 'loss/train': 1.6770039796829224}
-03/05/2022 13:07:02 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/05/2022 13:07:06 - INFO - codeparrot_training - Step 40532: {'lr': 0.00042093551286072887, 'samples': 20752896, 'steps': 40532, 'loss/train': 1.8970285654067993}
-03/05/2022 13:07:09 - INFO - codeparrot_training - Step 40533: {'lr': 0.00042093164036463045, 'samples': 20753408, 'steps': 40533, 'loss/train': 1.2001363039016724}
-03/05/2022 13:07:11 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/05/2022 13:07:15 - INFO - codeparrot_training - Step 40534: {'lr': 0.0004209277677915129, 'samples': 20753920, 'steps': 40534, 'loss/train': 0.7736743688583374}
-03/05/2022 13:07:18 - INFO - codeparrot_training - Step 40535: {'lr': 0.000420923895141378, 'samples': 20754432, 'steps': 40535, 'loss/train': 0.4928356111049652}
-03/05/2022 13:07:20 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/05/2022 13:07:23 - INFO - codeparrot_training - Step 40536: {'lr': 0.0004209200224142274, 'samples': 20754944, 'steps': 40536, 'loss/train': 1.9714469909667969}
-03/05/2022 13:07:26 - INFO - codeparrot_training - Step 40537: {'lr': 0.0004209161496100629, 'samples': 20755456, 'steps': 40537, 'loss/train': 1.5068094730377197}
-03/05/2022 13:07:29 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 13:07:32 - INFO - codeparrot_training - Step 40538: {'lr': 0.00042091227672888624, 'samples': 20755968, 'steps': 40538, 'loss/train': 2.025617837905884}
-03/05/2022 13:07:35 - INFO - codeparrot_training - Step 40539: {'lr': 0.00042090840377069906, 'samples': 20756480, 'steps': 40539, 'loss/train': 0.833613395690918}
-03/05/2022 13:07:37 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 13:07:40 - INFO - codeparrot_training - Step 40540: {'lr': 0.00042090453073550323, 'samples': 20756992, 'steps': 40540, 'loss/train': 2.2700655460357666}
-03/05/2022 13:07:43 - INFO - codeparrot_training - Step 40541: {'lr': 0.0004209006576233004, 'samples': 20757504, 'steps': 40541, 'loss/train': 1.6403255462646484}
-03/05/2022 13:07:45 - INFO - codeparrot_training - Skipping example with length 899 (seq_length=1024)
-03/05/2022 13:07:48 - INFO - codeparrot_training - Step 40542: {'lr': 0.0004208967844340925, 'samples': 20758016, 'steps': 40542, 'loss/train': 2.2528696060180664}
-03/05/2022 13:07:52 - INFO - codeparrot_training - Step 40543: {'lr': 0.0004208929111678811, 'samples': 20758528, 'steps': 40543, 'loss/train': 1.7717382907867432}
-03/05/2022 13:07:53 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 13:07:57 - INFO - codeparrot_training - Step 40544: {'lr': 0.0004208890378246679, 'samples': 20759040, 'steps': 40544, 'loss/train': 1.4949206113815308}
-03/05/2022 13:08:00 - INFO - codeparrot_training - Step 40545: {'lr': 0.00042088516440445486, 'samples': 20759552, 'steps': 40545, 'loss/train': 1.7160180807113647}
-03/05/2022 13:08:02 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/05/2022 13:08:05 - INFO - codeparrot_training - Step 40546: {'lr': 0.0004208812909072435, 'samples': 20760064, 'steps': 40546, 'loss/train': 1.3404403924942017}
-03/05/2022 13:08:09 - INFO - codeparrot_training - Step 40547: {'lr': 0.00042087741733303575, 'samples': 20760576, 'steps': 40547, 'loss/train': 1.8561149835586548}
-03/05/2022 13:08:10 - INFO - codeparrot_training - Skipping example with length 325 (seq_length=1024)
-03/05/2022 13:08:14 - INFO - codeparrot_training - Step 40548: {'lr': 0.00042087354368183316, 'samples': 20761088, 'steps': 40548, 'loss/train': 3.070607900619507}
-03/05/2022 13:08:17 - INFO - codeparrot_training - Step 40549: {'lr': 0.00042086966995363774, 'samples': 20761600, 'steps': 40549, 'loss/train': 2.358048915863037}
-03/05/2022 13:08:18 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/05/2022 13:08:22 - INFO - codeparrot_training - Step 40550: {'lr': 0.000420865796148451, 'samples': 20762112, 'steps': 40550, 'loss/train': 1.846623420715332}
-03/05/2022 13:08:25 - INFO - codeparrot_training - Step 40551: {'lr': 0.00042086192226627476, 'samples': 20762624, 'steps': 40551, 'loss/train': 1.8676114082336426}
-03/05/2022 13:08:27 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/05/2022 13:08:31 - INFO - codeparrot_training - Step 40552: {'lr': 0.00042085804830711084, 'samples': 20763136, 'steps': 40552, 'loss/train': 1.372423529624939}
-03/05/2022 13:08:34 - INFO - codeparrot_training - Step 40553: {'lr': 0.00042085417427096085, 'samples': 20763648, 'steps': 40553, 'loss/train': 1.859683632850647}
-03/05/2022 13:08:35 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/05/2022 13:08:39 - INFO - codeparrot_training - Step 40554: {'lr': 0.0004208503001578266, 'samples': 20764160, 'steps': 40554, 'loss/train': 2.288742780685425}
-03/05/2022 13:08:42 - INFO - codeparrot_training - Step 40555: {'lr': 0.00042084642596770984, 'samples': 20764672, 'steps': 40555, 'loss/train': 1.6476786136627197}
-03/05/2022 13:08:44 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/05/2022 13:08:48 - INFO - codeparrot_training - Step 40556: {'lr': 0.0004208425517006124, 'samples': 20765184, 'steps': 40556, 'loss/train': 2.4635915756225586}
-03/05/2022 13:08:51 - INFO - codeparrot_training - Step 40557: {'lr': 0.0004208386773565359, 'samples': 20765696, 'steps': 40557, 'loss/train': 2.1452674865722656}
-03/05/2022 13:08:52 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/05/2022 13:08:56 - INFO - codeparrot_training - Step 40558: {'lr': 0.0004208348029354821, 'samples': 20766208, 'steps': 40558, 'loss/train': 1.2970952987670898}
-03/05/2022 13:08:59 - INFO - codeparrot_training - Step 40559: {'lr': 0.00042083092843745275, 'samples': 20766720, 'steps': 40559, 'loss/train': 0.6324344277381897}
-03/05/2022 13:09:01 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/05/2022 13:09:05 - INFO - codeparrot_training - Step 40560: {'lr': 0.0004208270538624497, 'samples': 20767232, 'steps': 40560, 'loss/train': 2.1046700477600098}
-03/05/2022 13:09:08 - INFO - codeparrot_training - Step 40561: {'lr': 0.00042082317921047455, 'samples': 20767744, 'steps': 40561, 'loss/train': 0.9006844162940979}
-03/05/2022 13:09:09 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/05/2022 13:09:13 - INFO - codeparrot_training - Step 40562: {'lr': 0.0004208193044815291, 'samples': 20768256, 'steps': 40562, 'loss/train': 0.652239978313446}
-03/05/2022 13:09:16 - INFO - codeparrot_training - Step 40563: {'lr': 0.0004208154296756152, 'samples': 20768768, 'steps': 40563, 'loss/train': 1.7635574340820312}
-03/05/2022 13:09:17 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/05/2022 13:09:21 - INFO - codeparrot_training - Step 40564: {'lr': 0.0004208115547927345, 'samples': 20769280, 'steps': 40564, 'loss/train': 1.8689101934432983}
-03/05/2022 13:09:25 - INFO - codeparrot_training - Step 40565: {'lr': 0.0004208076798328886, 'samples': 20769792, 'steps': 40565, 'loss/train': 1.4304279088974}
-03/05/2022 13:09:26 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/05/2022 13:09:30 - INFO - codeparrot_training - Step 40566: {'lr': 0.00042080380479607947, 'samples': 20770304, 'steps': 40566, 'loss/train': 0.0964324027299881}
-03/05/2022 13:09:33 - INFO - codeparrot_training - Step 40567: {'lr': 0.00042079992968230886, 'samples': 20770816, 'steps': 40567, 'loss/train': 0.8025344014167786}
-03/05/2022 13:09:34 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/05/2022 13:09:39 - INFO - codeparrot_training - Step 40568: {'lr': 0.0004207960544915784, 'samples': 20771328, 'steps': 40568, 'loss/train': 1.008409023284912}
-03/05/2022 13:09:42 - INFO - codeparrot_training - Step 40569: {'lr': 0.0004207921792238898, 'samples': 20771840, 'steps': 40569, 'loss/train': 1.5095638036727905}
-03/05/2022 13:09:43 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/05/2022 13:09:47 - INFO - codeparrot_training - Step 40570: {'lr': 0.0004207883038792449, 'samples': 20772352, 'steps': 40570, 'loss/train': 2.0227723121643066}
-03/05/2022 13:09:50 - INFO - codeparrot_training - Step 40571: {'lr': 0.0004207844284576455, 'samples': 20772864, 'steps': 40571, 'loss/train': 1.214285969734192}
-03/05/2022 13:09:52 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/05/2022 13:09:55 - INFO - codeparrot_training - Step 40572: {'lr': 0.0004207805529590932, 'samples': 20773376, 'steps': 40572, 'loss/train': 1.791153073310852}
-03/05/2022 13:09:59 - INFO - codeparrot_training - Step 40573: {'lr': 0.0004207766773835899, 'samples': 20773888, 'steps': 40573, 'loss/train': 1.8055709600448608}
-03/05/2022 13:10:00 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/05/2022 13:10:04 - INFO - codeparrot_training - Step 40574: {'lr': 0.0004207728017311372, 'samples': 20774400, 'steps': 40574, 'loss/train': 1.912635326385498}
-03/05/2022 13:10:07 - INFO - codeparrot_training - Step 40575: {'lr': 0.0004207689260017369, 'samples': 20774912, 'steps': 40575, 'loss/train': 1.6282713413238525}
-03/05/2022 13:10:09 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 13:10:13 - INFO - codeparrot_training - Step 40576: {'lr': 0.0004207650501953908, 'samples': 20775424, 'steps': 40576, 'loss/train': 1.5444647073745728}
-03/05/2022 13:10:16 - INFO - codeparrot_training - Step 40577: {'lr': 0.0004207611743121006, 'samples': 20775936, 'steps': 40577, 'loss/train': 0.8495638966560364}
-03/05/2022 13:10:18 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/05/2022 13:10:21 - INFO - codeparrot_training - Step 40578: {'lr': 0.00042075729835186807, 'samples': 20776448, 'steps': 40578, 'loss/train': 1.8111493587493896}
-03/05/2022 13:10:24 - INFO - codeparrot_training - Step 40579: {'lr': 0.0004207534223146948, 'samples': 20776960, 'steps': 40579, 'loss/train': 2.057074546813965}
-03/05/2022 13:10:26 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/05/2022 13:10:30 - INFO - codeparrot_training - Step 40580: {'lr': 0.0004207495462005828, 'samples': 20777472, 'steps': 40580, 'loss/train': 2.1269750595092773}
-03/05/2022 13:10:33 - INFO - codeparrot_training - Step 40581: {'lr': 0.0004207456700095337, 'samples': 20777984, 'steps': 40581, 'loss/train': 1.8115850687026978}
-03/05/2022 13:10:34 - INFO - codeparrot_training - Skipping example with length 976 (seq_length=1024)
-03/05/2022 13:10:38 - INFO - codeparrot_training - Step 40582: {'lr': 0.0004207417937415492, 'samples': 20778496, 'steps': 40582, 'loss/train': 1.5210784673690796}
-03/05/2022 13:10:41 - INFO - codeparrot_training - Step 40583: {'lr': 0.000420737917396631, 'samples': 20779008, 'steps': 40583, 'loss/train': 2.3228540420532227}
-03/05/2022 13:10:43 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/05/2022 13:10:46 - INFO - codeparrot_training - Step 40584: {'lr': 0.00042073404097478105, 'samples': 20779520, 'steps': 40584, 'loss/train': 1.0096158981323242}
-03/05/2022 13:10:50 - INFO - codeparrot_training - Step 40585: {'lr': 0.000420730164476001, 'samples': 20780032, 'steps': 40585, 'loss/train': 2.4979608058929443}
-03/05/2022 13:10:51 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/05/2022 13:10:55 - INFO - codeparrot_training - Step 40586: {'lr': 0.00042072628790029243, 'samples': 20780544, 'steps': 40586, 'loss/train': 1.0904587507247925}
-03/05/2022 13:10:58 - INFO - codeparrot_training - Step 40587: {'lr': 0.0004207224112476573, 'samples': 20781056, 'steps': 40587, 'loss/train': 1.5106090307235718}
-03/05/2022 13:10:59 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/05/2022 13:11:03 - INFO - codeparrot_training - Step 40588: {'lr': 0.0004207185345180973, 'samples': 20781568, 'steps': 40588, 'loss/train': 1.3290677070617676}
-03/05/2022 13:11:07 - INFO - codeparrot_training - Step 40589: {'lr': 0.00042071465771161416, 'samples': 20782080, 'steps': 40589, 'loss/train': 1.0604459047317505}
-03/05/2022 13:11:08 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/05/2022 13:11:12 - INFO - codeparrot_training - Step 40590: {'lr': 0.0004207107808282097, 'samples': 20782592, 'steps': 40590, 'loss/train': 2.583747386932373}
-03/05/2022 13:11:15 - INFO - codeparrot_training - Step 40591: {'lr': 0.00042070690386788545, 'samples': 20783104, 'steps': 40591, 'loss/train': 2.405487298965454}
-03/05/2022 13:11:16 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/05/2022 13:11:20 - INFO - codeparrot_training - Step 40592: {'lr': 0.0004207030268306434, 'samples': 20783616, 'steps': 40592, 'loss/train': 1.3871694803237915}
-03/05/2022 13:11:23 - INFO - codeparrot_training - Step 40593: {'lr': 0.00042069914971648516, 'samples': 20784128, 'steps': 40593, 'loss/train': 2.0643138885498047}
-03/05/2022 13:11:24 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/05/2022 13:11:29 - INFO - codeparrot_training - Step 40594: {'lr': 0.0004206952725254125, 'samples': 20784640, 'steps': 40594, 'loss/train': 2.036855697631836}
-03/05/2022 13:11:32 - INFO - codeparrot_training - Step 40595: {'lr': 0.00042069139525742727, 'samples': 20785152, 'steps': 40595, 'loss/train': 1.753844976425171}
-03/05/2022 13:11:33 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 13:11:37 - INFO - codeparrot_training - Step 40596: {'lr': 0.000420687517912531, 'samples': 20785664, 'steps': 40596, 'loss/train': 1.7587822675704956}
-03/05/2022 13:11:40 - INFO - codeparrot_training - Step 40597: {'lr': 0.0004206836404907257, 'samples': 20786176, 'steps': 40597, 'loss/train': 1.781281590461731}
-03/05/2022 13:11:41 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/05/2022 13:11:46 - INFO - codeparrot_training - Step 40598: {'lr': 0.0004206797629920129, 'samples': 20786688, 'steps': 40598, 'loss/train': 2.0872039794921875}
-03/05/2022 13:11:49 - INFO - codeparrot_training - Step 40599: {'lr': 0.0004206758854163945, 'samples': 20787200, 'steps': 40599, 'loss/train': 2.264943838119507}
-03/05/2022 13:11:50 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/05/2022 13:11:54 - INFO - codeparrot_training - Step 40600: {'lr': 0.00042067200776387215, 'samples': 20787712, 'steps': 40600, 'loss/train': 1.7265651226043701}
-03/05/2022 13:11:57 - INFO - codeparrot_training - Step 40601: {'lr': 0.0004206681300344476, 'samples': 20788224, 'steps': 40601, 'loss/train': 2.4974310398101807}
-03/05/2022 13:11:58 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/05/2022 13:12:03 - INFO - codeparrot_training - Step 40602: {'lr': 0.0004206642522281227, 'samples': 20788736, 'steps': 40602, 'loss/train': 1.8538384437561035}
-03/05/2022 13:12:06 - INFO - codeparrot_training - Step 40603: {'lr': 0.000420660374344899, 'samples': 20789248, 'steps': 40603, 'loss/train': 1.0465166568756104}
-03/05/2022 13:12:06 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/05/2022 13:12:11 - INFO - codeparrot_training - Step 40604: {'lr': 0.00042065649638477843, 'samples': 20789760, 'steps': 40604, 'loss/train': 0.7066277265548706}
-03/05/2022 13:12:14 - INFO - codeparrot_training - Step 40605: {'lr': 0.0004206526183477627, 'samples': 20790272, 'steps': 40605, 'loss/train': 1.7076364755630493}
-03/05/2022 13:12:15 - INFO - codeparrot_training - Skipping example with length 745 (seq_length=1024)
-03/05/2022 13:12:20 - INFO - codeparrot_training - Step 40606: {'lr': 0.0004206487402338535, 'samples': 20790784, 'steps': 40606, 'loss/train': 1.8296763896942139}
-03/05/2022 13:12:23 - INFO - codeparrot_training - Step 40607: {'lr': 0.00042064486204305263, 'samples': 20791296, 'steps': 40607, 'loss/train': 1.7912205457687378}
-03/05/2022 13:12:23 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/05/2022 13:12:28 - INFO - codeparrot_training - Step 40608: {'lr': 0.0004206409837753618, 'samples': 20791808, 'steps': 40608, 'loss/train': 1.1085683107376099}
-03/05/2022 13:12:31 - INFO - codeparrot_training - Step 40609: {'lr': 0.00042063710543078283, 'samples': 20792320, 'steps': 40609, 'loss/train': 2.084911823272705}
-03/05/2022 13:12:31 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/05/2022 13:12:36 - INFO - codeparrot_training - Step 40610: {'lr': 0.00042063322700931733, 'samples': 20792832, 'steps': 40610, 'loss/train': 1.4777162075042725}
-03/05/2022 13:12:40 - INFO - codeparrot_training - Step 40611: {'lr': 0.0004206293485109672, 'samples': 20793344, 'steps': 40611, 'loss/train': 1.5778974294662476}
-03/05/2022 13:12:40 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/05/2022 13:12:45 - INFO - codeparrot_training - Step 40612: {'lr': 0.0004206254699357341, 'samples': 20793856, 'steps': 40612, 'loss/train': 1.700527548789978}
-03/05/2022 13:12:48 - INFO - codeparrot_training - Step 40613: {'lr': 0.00042062159128361976, 'samples': 20794368, 'steps': 40613, 'loss/train': 1.8158572912216187}
-03/05/2022 13:12:48 - INFO - codeparrot_training - Skipping example with length 647 (seq_length=1024)
-03/05/2022 13:12:53 - INFO - codeparrot_training - Step 40614: {'lr': 0.000420617712554626, 'samples': 20794880, 'steps': 40614, 'loss/train': 1.7934439182281494}
-03/05/2022 13:12:57 - INFO - codeparrot_training - Step 40615: {'lr': 0.0004206138337487545, 'samples': 20795392, 'steps': 40615, 'loss/train': 1.6390564441680908}
-03/05/2022 13:12:57 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/05/2022 13:13:02 - INFO - codeparrot_training - Step 40616: {'lr': 0.0004206099548660071, 'samples': 20795904, 'steps': 40616, 'loss/train': 2.2152841091156006}
-03/05/2022 13:13:05 - INFO - codeparrot_training - Step 40617: {'lr': 0.00042060607590638547, 'samples': 20796416, 'steps': 40617, 'loss/train': 1.6333396434783936}
-03/05/2022 13:13:06 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/05/2022 13:13:10 - INFO - codeparrot_training - Step 40618: {'lr': 0.00042060219686989133, 'samples': 20796928, 'steps': 40618, 'loss/train': 1.8146079778671265}
-03/05/2022 13:13:13 - INFO - codeparrot_training - Step 40619: {'lr': 0.00042059831775652644, 'samples': 20797440, 'steps': 40619, 'loss/train': 1.590161681175232}
-03/05/2022 13:13:14 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/05/2022 13:13:19 - INFO - codeparrot_training - Step 40620: {'lr': 0.00042059443856629265, 'samples': 20797952, 'steps': 40620, 'loss/train': 1.969254493713379}
-03/05/2022 13:13:22 - INFO - codeparrot_training - Step 40621: {'lr': 0.00042059055929919163, 'samples': 20798464, 'steps': 40621, 'loss/train': 1.2693634033203125}
-03/05/2022 13:13:23 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/05/2022 13:13:27 - INFO - codeparrot_training - Step 40622: {'lr': 0.00042058667995522513, 'samples': 20798976, 'steps': 40622, 'loss/train': 0.133633092045784}
-03/05/2022 13:13:30 - INFO - codeparrot_training - Step 40623: {'lr': 0.0004205828005343949, 'samples': 20799488, 'steps': 40623, 'loss/train': 2.295104742050171}
-03/05/2022 13:13:31 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/05/2022 13:13:36 - INFO - codeparrot_training - Step 40624: {'lr': 0.00042057892103670275, 'samples': 20800000, 'steps': 40624, 'loss/train': 2.154745578765869}
-03/05/2022 13:13:39 - INFO - codeparrot_training - Step 40625: {'lr': 0.0004205750414621503, 'samples': 20800512, 'steps': 40625, 'loss/train': 2.454918146133423}
-03/05/2022 13:13:39 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/05/2022 13:13:44 - INFO - codeparrot_training - Step 40626: {'lr': 0.0004205711618107394, 'samples': 20801024, 'steps': 40626, 'loss/train': 1.6260501146316528}
-03/05/2022 13:13:47 - INFO - codeparrot_training - Step 40627: {'lr': 0.00042056728208247175, 'samples': 20801536, 'steps': 40627, 'loss/train': 2.5091705322265625}
-03/05/2022 13:13:48 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/05/2022 13:13:52 - INFO - codeparrot_training - Step 40628: {'lr': 0.0004205634022773491, 'samples': 20802048, 'steps': 40628, 'loss/train': 1.998146891593933}
-03/05/2022 13:13:56 - INFO - codeparrot_training - Step 40629: {'lr': 0.0004205595223953732, 'samples': 20802560, 'steps': 40629, 'loss/train': 0.7557739615440369}
-03/05/2022 13:13:56 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/05/2022 13:14:01 - INFO - codeparrot_training - Step 40630: {'lr': 0.0004205556424365459, 'samples': 20803072, 'steps': 40630, 'loss/train': 2.4227638244628906}
-03/05/2022 13:14:04 - INFO - codeparrot_training - Step 40631: {'lr': 0.0004205517624008688, 'samples': 20803584, 'steps': 40631, 'loss/train': 1.3900846242904663}
-03/05/2022 13:14:04 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/05/2022 13:14:09 - INFO - codeparrot_training - Step 40632: {'lr': 0.00042054788228834374, 'samples': 20804096, 'steps': 40632, 'loss/train': 2.010648488998413}
-03/05/2022 13:14:12 - INFO - codeparrot_training - Step 40633: {'lr': 0.0004205440020989724, 'samples': 20804608, 'steps': 40633, 'loss/train': 1.8523024320602417}
-03/05/2022 13:14:12 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/05/2022 13:14:18 - INFO - codeparrot_training - Step 40634: {'lr': 0.0004205401218327565, 'samples': 20805120, 'steps': 40634, 'loss/train': 0.818213701248169}
-03/05/2022 13:14:21 - INFO - codeparrot_training - Step 40635: {'lr': 0.0004205362414896979, 'samples': 20805632, 'steps': 40635, 'loss/train': 2.254000663757324}
-03/05/2022 13:14:22 - INFO - codeparrot_training - Skipping example with length 798 (seq_length=1024)
-03/05/2022 13:14:27 - INFO - codeparrot_training - Step 40636: {'lr': 0.0004205323610697984, 'samples': 20806144, 'steps': 40636, 'loss/train': 1.425824522972107}
-03/05/2022 13:14:30 - INFO - codeparrot_training - Step 40637: {'lr': 0.0004205284805730596, 'samples': 20806656, 'steps': 40637, 'loss/train': 1.9774761199951172}
-03/05/2022 13:14:31 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/05/2022 13:14:35 - INFO - codeparrot_training - Step 40638: {'lr': 0.00042052459999948323, 'samples': 20807168, 'steps': 40638, 'loss/train': 2.168917655944824}
-03/05/2022 13:14:38 - INFO - codeparrot_training - Step 40639: {'lr': 0.00042052071934907116, 'samples': 20807680, 'steps': 40639, 'loss/train': 1.3629273176193237}
-03/05/2022 13:14:39 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/05/2022 13:14:43 - INFO - codeparrot_training - Step 40640: {'lr': 0.00042051683862182504, 'samples': 20808192, 'steps': 40640, 'loss/train': 1.6145477294921875}
-03/05/2022 13:14:47 - INFO - codeparrot_training - Step 40641: {'lr': 0.0004205129578177467, 'samples': 20808704, 'steps': 40641, 'loss/train': 1.670817494392395}
-03/05/2022 13:14:47 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/05/2022 13:14:52 - INFO - codeparrot_training - Step 40642: {'lr': 0.0004205090769368379, 'samples': 20809216, 'steps': 40642, 'loss/train': 0.6168637275695801}
-03/05/2022 13:14:55 - INFO - codeparrot_training - Step 40643: {'lr': 0.00042050519597910024, 'samples': 20809728, 'steps': 40643, 'loss/train': 2.1160097122192383}
-03/05/2022 13:14:56 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/05/2022 13:15:00 - INFO - codeparrot_training - Step 40644: {'lr': 0.00042050131494453567, 'samples': 20810240, 'steps': 40644, 'loss/train': 1.6015467643737793}
-03/05/2022 13:15:03 - INFO - codeparrot_training - Step 40645: {'lr': 0.00042049743383314577, 'samples': 20810752, 'steps': 40645, 'loss/train': 1.812772512435913}
-03/05/2022 13:15:04 - INFO - codeparrot_training - Skipping example with length 415 (seq_length=1024)
-03/05/2022 13:15:09 - INFO - codeparrot_training - Step 40646: {'lr': 0.0004204935526449324, 'samples': 20811264, 'steps': 40646, 'loss/train': 2.5114407539367676}
-03/05/2022 13:15:12 - INFO - codeparrot_training - Step 40647: {'lr': 0.0004204896713798972, 'samples': 20811776, 'steps': 40647, 'loss/train': 0.5237265825271606}
-03/05/2022 13:15:12 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 13:15:17 - INFO - codeparrot_training - Step 40648: {'lr': 0.00042048579003804205, 'samples': 20812288, 'steps': 40648, 'loss/train': 2.0232467651367188}
-03/05/2022 13:15:20 - INFO - codeparrot_training - Step 40649: {'lr': 0.00042048190861936866, 'samples': 20812800, 'steps': 40649, 'loss/train': 1.8211101293563843}
-03/05/2022 13:15:22 - INFO - codeparrot_training - Skipping example with length 468 (seq_length=1024)
-03/05/2022 13:15:26 - INFO - codeparrot_training - Step 40650: {'lr': 0.0004204780271238786, 'samples': 20813312, 'steps': 40650, 'loss/train': 1.5003325939178467}
-03/05/2022 13:15:29 - INFO - codeparrot_training - Step 40651: {'lr': 0.00042047414555157394, 'samples': 20813824, 'steps': 40651, 'loss/train': 1.5937751531600952}
-03/05/2022 13:15:30 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/05/2022 13:15:34 - INFO - codeparrot_training - Step 40652: {'lr': 0.0004204702639024562, 'samples': 20814336, 'steps': 40652, 'loss/train': 6.6315016746521}
-03/05/2022 13:15:38 - INFO - codeparrot_training - Step 40653: {'lr': 0.00042046638217652717, 'samples': 20814848, 'steps': 40653, 'loss/train': 1.817343831062317}
-03/05/2022 13:15:39 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/05/2022 13:15:43 - INFO - codeparrot_training - Step 40654: {'lr': 0.00042046250037378865, 'samples': 20815360, 'steps': 40654, 'loss/train': 1.4928358793258667}
-03/05/2022 13:15:46 - INFO - codeparrot_training - Step 40655: {'lr': 0.0004204586184942423, 'samples': 20815872, 'steps': 40655, 'loss/train': 1.568943977355957}
-03/05/2022 13:15:47 - INFO - codeparrot_training - Skipping example with length 79 (seq_length=1024)
-03/05/2022 13:15:51 - INFO - codeparrot_training - Step 40656: {'lr': 0.00042045473653789004, 'samples': 20816384, 'steps': 40656, 'loss/train': 1.5283026695251465}
-03/05/2022 13:15:54 - INFO - codeparrot_training - Step 40657: {'lr': 0.00042045085450473336, 'samples': 20816896, 'steps': 40657, 'loss/train': 1.713057279586792}
-03/05/2022 13:15:56 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/05/2022 13:16:00 - INFO - codeparrot_training - Step 40658: {'lr': 0.00042044697239477423, 'samples': 20817408, 'steps': 40658, 'loss/train': 1.8606091737747192}
-03/05/2022 13:16:03 - INFO - codeparrot_training - Step 40659: {'lr': 0.00042044309020801434, 'samples': 20817920, 'steps': 40659, 'loss/train': 1.5933631658554077}
-03/05/2022 13:16:04 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/05/2022 13:16:08 - INFO - codeparrot_training - Step 40660: {'lr': 0.00042043920794445543, 'samples': 20818432, 'steps': 40660, 'loss/train': 2.512092351913452}
-03/05/2022 13:16:12 - INFO - codeparrot_training - Step 40661: {'lr': 0.0004204353256040992, 'samples': 20818944, 'steps': 40661, 'loss/train': 1.8306958675384521}
-03/05/2022 13:16:13 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/05/2022 13:16:17 - INFO - codeparrot_training - Step 40662: {'lr': 0.0004204314431869475, 'samples': 20819456, 'steps': 40662, 'loss/train': 1.4826037883758545}
-03/05/2022 13:16:20 - INFO - codeparrot_training - Step 40663: {'lr': 0.0004204275606930019, 'samples': 20819968, 'steps': 40663, 'loss/train': 1.8911564350128174}
-03/05/2022 13:16:22 - INFO - codeparrot_training - Skipping example with length 462 (seq_length=1024)
-03/05/2022 13:16:25 - INFO - codeparrot_training - Step 40664: {'lr': 0.00042042367812226446, 'samples': 20820480, 'steps': 40664, 'loss/train': 0.7729328274726868}
-03/05/2022 13:16:28 - INFO - codeparrot_training - Step 40665: {'lr': 0.00042041979547473665, 'samples': 20820992, 'steps': 40665, 'loss/train': 1.8025481700897217}
-03/05/2022 13:16:30 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 13:16:34 - INFO - codeparrot_training - Step 40666: {'lr': 0.0004204159127504202, 'samples': 20821504, 'steps': 40666, 'loss/train': 2.1365766525268555}
-03/05/2022 13:16:37 - INFO - codeparrot_training - Step 40667: {'lr': 0.0004204120299493171, 'samples': 20822016, 'steps': 40667, 'loss/train': 1.489859938621521}
-03/05/2022 13:16:39 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/05/2022 13:16:42 - INFO - codeparrot_training - Step 40668: {'lr': 0.0004204081470714289, 'samples': 20822528, 'steps': 40668, 'loss/train': 1.5347779989242554}
-03/05/2022 13:16:46 - INFO - codeparrot_training - Step 40669: {'lr': 0.00042040426411675747, 'samples': 20823040, 'steps': 40669, 'loss/train': 1.9578884840011597}
-03/05/2022 13:16:48 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 13:16:51 - INFO - codeparrot_training - Step 40670: {'lr': 0.0004204003810853045, 'samples': 20823552, 'steps': 40670, 'loss/train': 2.253814935684204}
-03/05/2022 13:16:54 - INFO - codeparrot_training - Step 40671: {'lr': 0.00042039649797707176, 'samples': 20824064, 'steps': 40671, 'loss/train': 2.0319814682006836}
-03/05/2022 13:16:56 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/05/2022 13:17:00 - INFO - codeparrot_training - Step 40672: {'lr': 0.0004203926147920609, 'samples': 20824576, 'steps': 40672, 'loss/train': 1.5479094982147217}
-03/05/2022 13:17:03 - INFO - codeparrot_training - Step 40673: {'lr': 0.0004203887315302739, 'samples': 20825088, 'steps': 40673, 'loss/train': 1.3408563137054443}
-03/05/2022 13:17:05 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/05/2022 13:17:08 - INFO - codeparrot_training - Step 40674: {'lr': 0.0004203848481917122, 'samples': 20825600, 'steps': 40674, 'loss/train': 1.7435742616653442}
-03/05/2022 13:17:11 - INFO - codeparrot_training - Step 40675: {'lr': 0.00042038096477637786, 'samples': 20826112, 'steps': 40675, 'loss/train': 2.027859687805176}
-03/05/2022 13:17:13 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/05/2022 13:17:17 - INFO - codeparrot_training - Step 40676: {'lr': 0.00042037708128427243, 'samples': 20826624, 'steps': 40676, 'loss/train': 2.1915855407714844}
-03/05/2022 13:17:20 - INFO - codeparrot_training - Step 40677: {'lr': 0.00042037319771539775, 'samples': 20827136, 'steps': 40677, 'loss/train': 2.164445161819458}
-03/05/2022 13:17:22 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/05/2022 13:17:25 - INFO - codeparrot_training - Step 40678: {'lr': 0.00042036931406975547, 'samples': 20827648, 'steps': 40678, 'loss/train': 1.563879132270813}
-03/05/2022 13:17:28 - INFO - codeparrot_training - Step 40679: {'lr': 0.0004203654303473474, 'samples': 20828160, 'steps': 40679, 'loss/train': 2.4409964084625244}
-03/05/2022 13:17:31 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/05/2022 13:17:34 - INFO - codeparrot_training - Step 40680: {'lr': 0.0004203615465481754, 'samples': 20828672, 'steps': 40680, 'loss/train': 2.276165008544922}
-03/05/2022 13:17:37 - INFO - codeparrot_training - Step 40681: {'lr': 0.0004203576626722411, 'samples': 20829184, 'steps': 40681, 'loss/train': 2.1119842529296875}
-03/05/2022 13:17:39 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/05/2022 13:17:42 - INFO - codeparrot_training - Step 40682: {'lr': 0.00042035377871954614, 'samples': 20829696, 'steps': 40682, 'loss/train': 1.4772833585739136}
-03/05/2022 13:17:45 - INFO - codeparrot_training - Step 40683: {'lr': 0.00042034989469009245, 'samples': 20830208, 'steps': 40683, 'loss/train': 1.0682467222213745}
-03/05/2022 13:17:48 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/05/2022 13:17:51 - INFO - codeparrot_training - Step 40684: {'lr': 0.0004203460105838818, 'samples': 20830720, 'steps': 40684, 'loss/train': 0.4374885559082031}
-03/05/2022 13:17:54 - INFO - codeparrot_training - Step 40685: {'lr': 0.00042034212640091587, 'samples': 20831232, 'steps': 40685, 'loss/train': 1.3320356607437134}
-03/05/2022 13:17:56 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/05/2022 13:17:59 - INFO - codeparrot_training - Step 40686: {'lr': 0.00042033824214119633, 'samples': 20831744, 'steps': 40686, 'loss/train': 1.244914174079895}
-03/05/2022 13:18:02 - INFO - codeparrot_training - Step 40687: {'lr': 0.00042033435780472494, 'samples': 20832256, 'steps': 40687, 'loss/train': 1.9542818069458008}
-03/05/2022 13:18:04 - INFO - codeparrot_training - Skipping example with length 499 (seq_length=1024)
-03/05/2022 13:18:08 - INFO - codeparrot_training - Step 40688: {'lr': 0.00042033047339150363, 'samples': 20832768, 'steps': 40688, 'loss/train': 1.0049687623977661}
-03/05/2022 13:18:11 - INFO - codeparrot_training - Step 40689: {'lr': 0.00042032658890153404, 'samples': 20833280, 'steps': 40689, 'loss/train': 1.584216833114624}
-03/05/2022 13:18:13 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/05/2022 13:18:16 - INFO - codeparrot_training - Step 40690: {'lr': 0.0004203227043348179, 'samples': 20833792, 'steps': 40690, 'loss/train': 1.8469264507293701}
-03/05/2022 13:18:19 - INFO - codeparrot_training - Step 40691: {'lr': 0.000420318819691357, 'samples': 20834304, 'steps': 40691, 'loss/train': 1.9487648010253906}
-03/05/2022 13:18:21 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/05/2022 13:18:25 - INFO - codeparrot_training - Step 40692: {'lr': 0.00042031493497115304, 'samples': 20834816, 'steps': 40692, 'loss/train': 1.5793026685714722}
-03/05/2022 13:18:28 - INFO - codeparrot_training - Step 40693: {'lr': 0.0004203110501742078, 'samples': 20835328, 'steps': 40693, 'loss/train': 1.4378328323364258}
-03/05/2022 13:18:30 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/05/2022 13:18:33 - INFO - codeparrot_training - Step 40694: {'lr': 0.00042030716530052297, 'samples': 20835840, 'steps': 40694, 'loss/train': 0.900818407535553}
-03/05/2022 13:18:36 - INFO - codeparrot_training - Step 40695: {'lr': 0.00042030328035010047, 'samples': 20836352, 'steps': 40695, 'loss/train': 1.3767000436782837}
-03/05/2022 13:18:38 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 13:18:42 - INFO - codeparrot_training - Step 40696: {'lr': 0.0004202993953229418, 'samples': 20836864, 'steps': 40696, 'loss/train': 1.4423713684082031}
-03/05/2022 13:18:45 - INFO - codeparrot_training - Step 40697: {'lr': 0.000420295510219049, 'samples': 20837376, 'steps': 40697, 'loss/train': 1.2700212001800537}
-03/05/2022 13:18:47 - INFO - codeparrot_training - Skipping example with length 240 (seq_length=1024)
-03/05/2022 13:18:50 - INFO - codeparrot_training - Step 40698: {'lr': 0.00042029162503842357, 'samples': 20837888, 'steps': 40698, 'loss/train': 2.078991651535034}
-03/05/2022 13:18:53 - INFO - codeparrot_training - Step 40699: {'lr': 0.0004202877397810674, 'samples': 20838400, 'steps': 40699, 'loss/train': 2.2254419326782227}
-03/05/2022 13:18:55 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 13:18:59 - INFO - codeparrot_training - Step 40700: {'lr': 0.0004202838544469822, 'samples': 20838912, 'steps': 40700, 'loss/train': 1.8732893466949463}
-03/05/2022 13:19:02 - INFO - codeparrot_training - Step 40701: {'lr': 0.00042027996903616974, 'samples': 20839424, 'steps': 40701, 'loss/train': 2.293428659439087}
-03/05/2022 13:19:04 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/05/2022 13:19:07 - INFO - codeparrot_training - Step 40702: {'lr': 0.0004202760835486317, 'samples': 20839936, 'steps': 40702, 'loss/train': 1.854709506034851}
-03/05/2022 13:19:10 - INFO - codeparrot_training - Step 40703: {'lr': 0.00042027219798436996, 'samples': 20840448, 'steps': 40703, 'loss/train': 2.026402711868286}
-03/05/2022 13:19:12 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/05/2022 13:19:16 - INFO - codeparrot_training - Step 40704: {'lr': 0.00042026831234338614, 'samples': 20840960, 'steps': 40704, 'loss/train': 2.0766959190368652}
-03/05/2022 13:19:19 - INFO - codeparrot_training - Step 40705: {'lr': 0.0004202644266256821, 'samples': 20841472, 'steps': 40705, 'loss/train': 0.8177947402000427}
-03/05/2022 13:19:21 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 13:19:24 - INFO - codeparrot_training - Step 40706: {'lr': 0.00042026054083125943, 'samples': 20841984, 'steps': 40706, 'loss/train': 1.7729127407073975}
-03/05/2022 13:19:28 - INFO - codeparrot_training - Step 40707: {'lr': 0.0004202566549601201, 'samples': 20842496, 'steps': 40707, 'loss/train': 1.4456254243850708}
-03/05/2022 13:19:30 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/05/2022 13:19:33 - INFO - codeparrot_training - Step 40708: {'lr': 0.00042025276901226573, 'samples': 20843008, 'steps': 40708, 'loss/train': 1.3970537185668945}
-03/05/2022 13:19:36 - INFO - codeparrot_training - Step 40709: {'lr': 0.00042024888298769806, 'samples': 20843520, 'steps': 40709, 'loss/train': 1.4879401922225952}
-03/05/2022 13:19:38 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/05/2022 13:19:41 - INFO - codeparrot_training - Step 40710: {'lr': 0.0004202449968864188, 'samples': 20844032, 'steps': 40710, 'loss/train': 0.9619199633598328}
-03/05/2022 13:19:45 - INFO - codeparrot_training - Step 40711: {'lr': 0.00042024111070842985, 'samples': 20844544, 'steps': 40711, 'loss/train': 2.071129560470581}
-03/05/2022 13:19:47 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/05/2022 13:19:50 - INFO - codeparrot_training - Step 40712: {'lr': 0.0004202372244537329, 'samples': 20845056, 'steps': 40712, 'loss/train': 1.5641220808029175}
-03/05/2022 13:19:53 - INFO - codeparrot_training - Step 40713: {'lr': 0.00042023333812232967, 'samples': 20845568, 'steps': 40713, 'loss/train': 1.5630959272384644}
-03/05/2022 13:19:55 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/05/2022 13:19:58 - INFO - codeparrot_training - Step 40714: {'lr': 0.0004202294517142219, 'samples': 20846080, 'steps': 40714, 'loss/train': 0.6319063901901245}
-03/05/2022 13:20:02 - INFO - codeparrot_training - Step 40715: {'lr': 0.0004202255652294114, 'samples': 20846592, 'steps': 40715, 'loss/train': 1.566847801208496}
-03/05/2022 13:20:03 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 13:20:07 - INFO - codeparrot_training - Step 40716: {'lr': 0.00042022167866789985, 'samples': 20847104, 'steps': 40716, 'loss/train': 1.939487338066101}
-03/05/2022 13:20:10 - INFO - codeparrot_training - Step 40717: {'lr': 0.00042021779202968903, 'samples': 20847616, 'steps': 40717, 'loss/train': 2.013498544692993}
-03/05/2022 13:20:12 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/05/2022 13:20:15 - INFO - codeparrot_training - Step 40718: {'lr': 0.0004202139053147808, 'samples': 20848128, 'steps': 40718, 'loss/train': 1.5227608680725098}
-03/05/2022 13:20:18 - INFO - codeparrot_training - Step 40719: {'lr': 0.0004202100185231767, 'samples': 20848640, 'steps': 40719, 'loss/train': 2.346557855606079}
-03/05/2022 13:20:20 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/05/2022 13:20:24 - INFO - codeparrot_training - Step 40720: {'lr': 0.00042020613165487863, 'samples': 20849152, 'steps': 40720, 'loss/train': 0.7454448938369751}
-03/05/2022 13:20:27 - INFO - codeparrot_training - Step 40721: {'lr': 0.0004202022447098883, 'samples': 20849664, 'steps': 40721, 'loss/train': 1.6782424449920654}
-03/05/2022 13:20:29 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 13:20:32 - INFO - codeparrot_training - Step 40722: {'lr': 0.00042019835768820744, 'samples': 20850176, 'steps': 40722, 'loss/train': 1.8981515169143677}
-03/05/2022 13:20:36 - INFO - codeparrot_training - Step 40723: {'lr': 0.00042019447058983786, 'samples': 20850688, 'steps': 40723, 'loss/train': 2.6000986099243164}
-03/05/2022 13:20:37 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 13:20:41 - INFO - codeparrot_training - Step 40724: {'lr': 0.0004201905834147813, 'samples': 20851200, 'steps': 40724, 'loss/train': 1.7059260606765747}
-03/05/2022 13:20:44 - INFO - codeparrot_training - Step 40725: {'lr': 0.0004201866961630395, 'samples': 20851712, 'steps': 40725, 'loss/train': 1.3375991582870483}
-03/05/2022 13:20:45 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 13:20:49 - INFO - codeparrot_training - Step 40726: {'lr': 0.00042018280883461415, 'samples': 20852224, 'steps': 40726, 'loss/train': 1.8777796030044556}
-03/05/2022 13:20:52 - INFO - codeparrot_training - Step 40727: {'lr': 0.000420178921429507, 'samples': 20852736, 'steps': 40727, 'loss/train': 1.6426701545715332}
-03/05/2022 13:20:54 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/05/2022 13:20:58 - INFO - codeparrot_training - Step 40728: {'lr': 0.00042017503394771997, 'samples': 20853248, 'steps': 40728, 'loss/train': 2.0072686672210693}
-03/05/2022 13:21:01 - INFO - codeparrot_training - Step 40729: {'lr': 0.00042017114638925456, 'samples': 20853760, 'steps': 40729, 'loss/train': 1.1846346855163574}
-03/05/2022 13:21:02 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/05/2022 13:21:06 - INFO - codeparrot_training - Step 40730: {'lr': 0.00042016725875411274, 'samples': 20854272, 'steps': 40730, 'loss/train': 2.238532781600952}
-03/05/2022 13:21:09 - INFO - codeparrot_training - Step 40731: {'lr': 0.0004201633710422962, 'samples': 20854784, 'steps': 40731, 'loss/train': 2.266195774078369}
-03/05/2022 13:21:11 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/05/2022 13:21:15 - INFO - codeparrot_training - Step 40732: {'lr': 0.0004201594832538067, 'samples': 20855296, 'steps': 40732, 'loss/train': 1.3179876804351807}
-03/05/2022 13:21:18 - INFO - codeparrot_training - Step 40733: {'lr': 0.0004201555953886459, 'samples': 20855808, 'steps': 40733, 'loss/train': 1.3553972244262695}
-03/05/2022 13:21:19 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/05/2022 13:21:23 - INFO - codeparrot_training - Step 40734: {'lr': 0.00042015170744681566, 'samples': 20856320, 'steps': 40734, 'loss/train': 1.3523272275924683}
-03/05/2022 13:21:26 - INFO - codeparrot_training - Step 40735: {'lr': 0.00042014781942831757, 'samples': 20856832, 'steps': 40735, 'loss/train': 0.9460923671722412}
-03/05/2022 13:21:27 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/05/2022 13:21:32 - INFO - codeparrot_training - Step 40736: {'lr': 0.00042014393133315366, 'samples': 20857344, 'steps': 40736, 'loss/train': 2.0228192806243896}
-03/05/2022 13:21:35 - INFO - codeparrot_training - Step 40737: {'lr': 0.00042014004316132537, 'samples': 20857856, 'steps': 40737, 'loss/train': 2.1863186359405518}
-03/05/2022 13:21:36 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/05/2022 13:21:40 - INFO - codeparrot_training - Step 40738: {'lr': 0.0004201361549128347, 'samples': 20858368, 'steps': 40738, 'loss/train': 2.541367530822754}
-03/05/2022 13:21:43 - INFO - codeparrot_training - Step 40739: {'lr': 0.00042013226658768333, 'samples': 20858880, 'steps': 40739, 'loss/train': 1.6246156692504883}
-03/05/2022 13:21:45 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/05/2022 13:21:49 - INFO - codeparrot_training - Step 40740: {'lr': 0.0004201283781858729, 'samples': 20859392, 'steps': 40740, 'loss/train': 3.0495142936706543}
-03/05/2022 13:21:52 - INFO - codeparrot_training - Step 40741: {'lr': 0.00042012448970740523, 'samples': 20859904, 'steps': 40741, 'loss/train': 1.0537464618682861}
-03/05/2022 13:21:53 - INFO - codeparrot_training - Skipping example with length 596 (seq_length=1024)
-03/05/2022 13:21:57 - INFO - codeparrot_training - Step 40742: {'lr': 0.00042012060115228215, 'samples': 20860416, 'steps': 40742, 'loss/train': 1.5998913049697876}
-03/05/2022 13:22:00 - INFO - codeparrot_training - Step 40743: {'lr': 0.0004201167125205054, 'samples': 20860928, 'steps': 40743, 'loss/train': 1.635398030281067}
-03/05/2022 13:22:02 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/05/2022 13:22:06 - INFO - codeparrot_training - Step 40744: {'lr': 0.0004201128238120766, 'samples': 20861440, 'steps': 40744, 'loss/train': 1.9442859888076782}
-03/05/2022 13:22:09 - INFO - codeparrot_training - Step 40745: {'lr': 0.00042010893502699765, 'samples': 20861952, 'steps': 40745, 'loss/train': 1.8034838438034058}
-03/05/2022 13:22:10 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/05/2022 13:22:14 - INFO - codeparrot_training - Step 40746: {'lr': 0.0004201050461652702, 'samples': 20862464, 'steps': 40746, 'loss/train': 1.6870543956756592}
-03/05/2022 13:22:17 - INFO - codeparrot_training - Step 40747: {'lr': 0.00042010115722689603, 'samples': 20862976, 'steps': 40747, 'loss/train': 1.9916573762893677}
-03/05/2022 13:22:19 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/05/2022 13:22:23 - INFO - codeparrot_training - Step 40748: {'lr': 0.0004200972682118769, 'samples': 20863488, 'steps': 40748, 'loss/train': 2.63049578666687}
-03/05/2022 13:22:26 - INFO - codeparrot_training - Step 40749: {'lr': 0.0004200933791202146, 'samples': 20864000, 'steps': 40749, 'loss/train': 1.248824119567871}
-03/05/2022 13:22:27 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 13:22:31 - INFO - codeparrot_training - Step 40750: {'lr': 0.0004200894899519108, 'samples': 20864512, 'steps': 40750, 'loss/train': 1.7309353351593018}
-03/05/2022 13:22:34 - INFO - codeparrot_training - Step 40751: {'lr': 0.00042008560070696735, 'samples': 20865024, 'steps': 40751, 'loss/train': 2.0240423679351807}
-03/05/2022 13:22:36 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/05/2022 13:22:40 - INFO - codeparrot_training - Step 40752: {'lr': 0.000420081711385386, 'samples': 20865536, 'steps': 40752, 'loss/train': 1.5327491760253906}
-03/05/2022 13:22:43 - INFO - codeparrot_training - Step 40753: {'lr': 0.00042007782198716836, 'samples': 20866048, 'steps': 40753, 'loss/train': 1.6291093826293945}
-03/05/2022 13:22:44 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/05/2022 13:22:48 - INFO - codeparrot_training - Step 40754: {'lr': 0.0004200739325123163, 'samples': 20866560, 'steps': 40754, 'loss/train': 1.6765512228012085}
-03/05/2022 13:22:51 - INFO - codeparrot_training - Step 40755: {'lr': 0.0004200700429608315, 'samples': 20867072, 'steps': 40755, 'loss/train': 0.6853744983673096}
-03/05/2022 13:22:53 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 13:22:57 - INFO - codeparrot_training - Step 40756: {'lr': 0.00042006615333271585, 'samples': 20867584, 'steps': 40756, 'loss/train': 2.385537624359131}
-03/05/2022 13:23:00 - INFO - codeparrot_training - Step 40757: {'lr': 0.000420062263627971, 'samples': 20868096, 'steps': 40757, 'loss/train': 1.3453363180160522}
-03/05/2022 13:23:01 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/05/2022 13:23:05 - INFO - codeparrot_training - Step 40758: {'lr': 0.0004200583738465987, 'samples': 20868608, 'steps': 40758, 'loss/train': 2.2151548862457275}
-03/05/2022 13:23:08 - INFO - codeparrot_training - Step 40759: {'lr': 0.00042005448398860077, 'samples': 20869120, 'steps': 40759, 'loss/train': 2.1138627529144287}
-03/05/2022 13:23:10 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/05/2022 13:23:13 - INFO - codeparrot_training - Step 40760: {'lr': 0.00042005059405397885, 'samples': 20869632, 'steps': 40760, 'loss/train': 3.924450159072876}
-03/05/2022 13:23:17 - INFO - codeparrot_training - Step 40761: {'lr': 0.00042004670404273474, 'samples': 20870144, 'steps': 40761, 'loss/train': 4.288048267364502}
-03/05/2022 13:23:18 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/05/2022 13:23:22 - INFO - codeparrot_training - Step 40762: {'lr': 0.0004200428139548703, 'samples': 20870656, 'steps': 40762, 'loss/train': 0.6412728428840637}
-03/05/2022 13:23:25 - INFO - codeparrot_training - Step 40763: {'lr': 0.0004200389237903871, 'samples': 20871168, 'steps': 40763, 'loss/train': 1.846627116203308}
-03/05/2022 13:23:26 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/05/2022 13:23:30 - INFO - codeparrot_training - Step 40764: {'lr': 0.000420035033549287, 'samples': 20871680, 'steps': 40764, 'loss/train': 1.468336820602417}
-03/05/2022 13:23:34 - INFO - codeparrot_training - Step 40765: {'lr': 0.0004200311432315718, 'samples': 20872192, 'steps': 40765, 'loss/train': 1.7389856576919556}
-03/05/2022 13:23:35 - INFO - codeparrot_training - Skipping example with length 8 (seq_length=1024)
-03/05/2022 13:23:39 - INFO - codeparrot_training - Step 40766: {'lr': 0.0004200272528372432, 'samples': 20872704, 'steps': 40766, 'loss/train': 0.35956525802612305}
-03/05/2022 13:23:42 - INFO - codeparrot_training - Step 40767: {'lr': 0.0004200233623663028, 'samples': 20873216, 'steps': 40767, 'loss/train': 1.8002536296844482}
-03/05/2022 13:23:44 - INFO - codeparrot_training - Skipping example with length 485 (seq_length=1024)
-03/05/2022 13:23:48 - INFO - codeparrot_training - Step 40768: {'lr': 0.0004200194718187527, 'samples': 20873728, 'steps': 40768, 'loss/train': 1.7635325193405151}
-03/05/2022 13:23:51 - INFO - codeparrot_training - Step 40769: {'lr': 0.0004200155811945943, 'samples': 20874240, 'steps': 40769, 'loss/train': 1.8057714700698853}
-03/05/2022 13:23:52 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/05/2022 13:23:56 - INFO - codeparrot_training - Step 40770: {'lr': 0.0004200116904938295, 'samples': 20874752, 'steps': 40770, 'loss/train': 2.0036380290985107}
-03/05/2022 13:23:59 - INFO - codeparrot_training - Step 40771: {'lr': 0.00042000779971646007, 'samples': 20875264, 'steps': 40771, 'loss/train': 1.1127572059631348}
-03/05/2022 13:24:00 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/05/2022 13:24:05 - INFO - codeparrot_training - Step 40772: {'lr': 0.00042000390886248783, 'samples': 20875776, 'steps': 40772, 'loss/train': 1.6849889755249023}
-03/05/2022 13:24:08 - INFO - codeparrot_training - Step 40773: {'lr': 0.0004200000179319144, 'samples': 20876288, 'steps': 40773, 'loss/train': 0.6212167739868164}
-03/05/2022 13:24:09 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/05/2022 13:24:13 - INFO - codeparrot_training - Step 40774: {'lr': 0.0004199961269247416, 'samples': 20876800, 'steps': 40774, 'loss/train': 1.3671700954437256}
-03/05/2022 13:24:16 - INFO - codeparrot_training - Step 40775: {'lr': 0.0004199922358409711, 'samples': 20877312, 'steps': 40775, 'loss/train': 1.6835066080093384}
-03/05/2022 13:24:17 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/05/2022 13:24:22 - INFO - codeparrot_training - Step 40776: {'lr': 0.0004199883446806048, 'samples': 20877824, 'steps': 40776, 'loss/train': 2.938542366027832}
-03/05/2022 13:24:25 - INFO - codeparrot_training - Step 40777: {'lr': 0.0004199844534436443, 'samples': 20878336, 'steps': 40777, 'loss/train': 1.2991214990615845}
-03/05/2022 13:24:26 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/05/2022 13:24:30 - INFO - codeparrot_training - Step 40778: {'lr': 0.0004199805621300915, 'samples': 20878848, 'steps': 40778, 'loss/train': 2.276879072189331}
-03/05/2022 13:24:34 - INFO - codeparrot_training - Step 40779: {'lr': 0.0004199766707399481, 'samples': 20879360, 'steps': 40779, 'loss/train': 1.5247468948364258}
-03/05/2022 13:24:35 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/05/2022 13:24:39 - INFO - codeparrot_training - Step 40780: {'lr': 0.0004199727792732158, 'samples': 20879872, 'steps': 40780, 'loss/train': 1.4557139873504639}
-03/05/2022 13:24:42 - INFO - codeparrot_training - Step 40781: {'lr': 0.0004199688877298964, 'samples': 20880384, 'steps': 40781, 'loss/train': 1.4280003309249878}
-03/05/2022 13:24:44 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 13:24:48 - INFO - codeparrot_training - Step 40782: {'lr': 0.00041996499610999163, 'samples': 20880896, 'steps': 40782, 'loss/train': 1.806489109992981}
-03/05/2022 13:24:51 - INFO - codeparrot_training - Step 40783: {'lr': 0.00041996110441350323, 'samples': 20881408, 'steps': 40783, 'loss/train': 1.9531545639038086}
-03/05/2022 13:24:53 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/05/2022 13:24:56 - INFO - codeparrot_training - Step 40784: {'lr': 0.000419957212640433, 'samples': 20881920, 'steps': 40784, 'loss/train': 1.5148506164550781}
-03/05/2022 13:24:59 - INFO - codeparrot_training - Step 40785: {'lr': 0.0004199533207907827, 'samples': 20882432, 'steps': 40785, 'loss/train': 1.8842509984970093}
-03/05/2022 13:25:02 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/05/2022 13:25:05 - INFO - codeparrot_training - Step 40786: {'lr': 0.00041994942886455403, 'samples': 20882944, 'steps': 40786, 'loss/train': 1.8247430324554443}
-03/05/2022 13:25:08 - INFO - codeparrot_training - Step 40787: {'lr': 0.00041994553686174876, 'samples': 20883456, 'steps': 40787, 'loss/train': 2.536978244781494}
-03/05/2022 13:25:10 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/05/2022 13:25:13 - INFO - codeparrot_training - Step 40788: {'lr': 0.0004199416447823686, 'samples': 20883968, 'steps': 40788, 'loss/train': 1.6586405038833618}
-03/05/2022 13:25:16 - INFO - codeparrot_training - Step 40789: {'lr': 0.0004199377526264154, 'samples': 20884480, 'steps': 40789, 'loss/train': 1.530704379081726}
-03/05/2022 13:25:19 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/05/2022 13:25:22 - INFO - codeparrot_training - Step 40790: {'lr': 0.00041993386039389095, 'samples': 20884992, 'steps': 40790, 'loss/train': 2.4262707233428955}
-03/05/2022 13:25:25 - INFO - codeparrot_training - Step 40791: {'lr': 0.0004199299680847969, 'samples': 20885504, 'steps': 40791, 'loss/train': 1.5122448205947876}
-03/05/2022 13:25:28 - INFO - codeparrot_training - Step 40792: {'lr': 0.000419926075699135, 'samples': 20886016, 'steps': 40792, 'loss/train': 1.9260776042938232}
-03/05/2022 13:25:28 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 13:25:33 - INFO - codeparrot_training - Step 40793: {'lr': 0.000419922183236907, 'samples': 20886528, 'steps': 40793, 'loss/train': 3.0515530109405518}
-03/05/2022 13:25:37 - INFO - codeparrot_training - Step 40794: {'lr': 0.0004199182906981147, 'samples': 20887040, 'steps': 40794, 'loss/train': 1.0696825981140137}
-03/05/2022 13:25:37 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/05/2022 13:25:42 - INFO - codeparrot_training - Step 40795: {'lr': 0.00041991439808275986, 'samples': 20887552, 'steps': 40795, 'loss/train': 1.5575226545333862}
-03/05/2022 13:25:45 - INFO - codeparrot_training - Step 40796: {'lr': 0.0004199105053908442, 'samples': 20888064, 'steps': 40796, 'loss/train': 2.042384386062622}
-03/05/2022 13:25:45 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/05/2022 13:25:51 - INFO - codeparrot_training - Step 40797: {'lr': 0.0004199066126223695, 'samples': 20888576, 'steps': 40797, 'loss/train': 0.7912163734436035}
-03/05/2022 13:25:54 - INFO - codeparrot_training - Step 40798: {'lr': 0.0004199027197773375, 'samples': 20889088, 'steps': 40798, 'loss/train': 1.2568210363388062}
-03/05/2022 13:25:54 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/05/2022 13:25:59 - INFO - codeparrot_training - Step 40799: {'lr': 0.00041989882685575, 'samples': 20889600, 'steps': 40799, 'loss/train': 2.3323352336883545}
-03/05/2022 13:26:02 - INFO - codeparrot_training - Step 40800: {'lr': 0.0004198949338576086, 'samples': 20890112, 'steps': 40800, 'loss/train': 1.5767987966537476}
-03/05/2022 13:26:03 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 13:26:07 - INFO - codeparrot_training - Step 40801: {'lr': 0.0004198910407829152, 'samples': 20890624, 'steps': 40801, 'loss/train': 1.5930017232894897}
-03/05/2022 13:26:11 - INFO - codeparrot_training - Step 40802: {'lr': 0.00041988714763167156, 'samples': 20891136, 'steps': 40802, 'loss/train': 0.46456414461135864}
-03/05/2022 13:26:11 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/05/2022 13:26:16 - INFO - codeparrot_training - Step 40803: {'lr': 0.00041988325440387944, 'samples': 20891648, 'steps': 40803, 'loss/train': 1.6916217803955078}
-03/05/2022 13:26:19 - INFO - codeparrot_training - Step 40804: {'lr': 0.00041987936109954047, 'samples': 20892160, 'steps': 40804, 'loss/train': 1.5018059015274048}
-03/05/2022 13:26:20 - INFO - codeparrot_training - Skipping example with length 443 (seq_length=1024)
-03/05/2022 13:26:25 - INFO - codeparrot_training - Step 40805: {'lr': 0.0004198754677186565, 'samples': 20892672, 'steps': 40805, 'loss/train': 2.2424561977386475}
-03/05/2022 13:26:28 - INFO - codeparrot_training - Step 40806: {'lr': 0.0004198715742612292, 'samples': 20893184, 'steps': 40806, 'loss/train': 0.9312177300453186}
-03/05/2022 13:26:29 - INFO - codeparrot_training - Skipping example with length 645 (seq_length=1024)
-03/05/2022 13:26:33 - INFO - codeparrot_training - Step 40807: {'lr': 0.0004198676807272605, 'samples': 20893696, 'steps': 40807, 'loss/train': 1.2940270900726318}
-03/05/2022 13:26:36 - INFO - codeparrot_training - Step 40808: {'lr': 0.000419863787116752, 'samples': 20894208, 'steps': 40808, 'loss/train': 1.3794755935668945}
-03/05/2022 13:26:38 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/05/2022 13:26:42 - INFO - codeparrot_training - Step 40809: {'lr': 0.0004198598934297055, 'samples': 20894720, 'steps': 40809, 'loss/train': 1.5394258499145508}
-03/05/2022 13:26:45 - INFO - codeparrot_training - Step 40810: {'lr': 0.00041985599966612273, 'samples': 20895232, 'steps': 40810, 'loss/train': 0.7942506670951843}
-03/05/2022 13:26:46 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/05/2022 13:26:50 - INFO - codeparrot_training - Step 40811: {'lr': 0.0004198521058260055, 'samples': 20895744, 'steps': 40811, 'loss/train': 0.9397141337394714}
-03/05/2022 13:26:53 - INFO - codeparrot_training - Step 40812: {'lr': 0.0004198482119093555, 'samples': 20896256, 'steps': 40812, 'loss/train': 1.5379940271377563}
-03/05/2022 13:26:55 - INFO - codeparrot_training - Skipping example with length 293 (seq_length=1024)
-03/05/2022 13:26:58 - INFO - codeparrot_training - Step 40813: {'lr': 0.00041984431791617456, 'samples': 20896768, 'steps': 40813, 'loss/train': 1.4108062982559204}
-03/05/2022 13:27:02 - INFO - codeparrot_training - Step 40814: {'lr': 0.0004198404238464644, 'samples': 20897280, 'steps': 40814, 'loss/train': 1.377322793006897}
-03/05/2022 13:27:03 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 13:27:07 - INFO - codeparrot_training - Step 40815: {'lr': 0.0004198365297002267, 'samples': 20897792, 'steps': 40815, 'loss/train': 1.1902726888656616}
-03/05/2022 13:27:10 - INFO - codeparrot_training - Step 40816: {'lr': 0.0004198326354774633, 'samples': 20898304, 'steps': 40816, 'loss/train': 1.992532730102539}
-03/05/2022 13:27:12 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 13:27:16 - INFO - codeparrot_training - Step 40817: {'lr': 0.00041982874117817593, 'samples': 20898816, 'steps': 40817, 'loss/train': 1.8741735219955444}
-03/05/2022 13:27:19 - INFO - codeparrot_training - Step 40818: {'lr': 0.00041982484680236636, 'samples': 20899328, 'steps': 40818, 'loss/train': 1.2172486782073975}
-03/05/2022 13:27:20 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/05/2022 13:27:24 - INFO - codeparrot_training - Step 40819: {'lr': 0.00041982095235003634, 'samples': 20899840, 'steps': 40819, 'loss/train': 1.6305570602416992}
-03/05/2022 13:27:27 - INFO - codeparrot_training - Step 40820: {'lr': 0.0004198170578211877, 'samples': 20900352, 'steps': 40820, 'loss/train': 2.5386273860931396}
-03/05/2022 13:27:28 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/05/2022 13:27:32 - INFO - codeparrot_training - Step 40821: {'lr': 0.000419813163215822, 'samples': 20900864, 'steps': 40821, 'loss/train': 1.9734106063842773}
-03/05/2022 13:27:36 - INFO - codeparrot_training - Step 40822: {'lr': 0.0004198092685339411, 'samples': 20901376, 'steps': 40822, 'loss/train': 1.1375445127487183}
-03/05/2022 13:27:36 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/05/2022 13:27:41 - INFO - codeparrot_training - Step 40823: {'lr': 0.00041980537377554685, 'samples': 20901888, 'steps': 40823, 'loss/train': 2.106945753097534}
-03/05/2022 13:27:44 - INFO - codeparrot_training - Step 40824: {'lr': 0.00041980147894064086, 'samples': 20902400, 'steps': 40824, 'loss/train': 2.4027252197265625}
-03/05/2022 13:27:45 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/05/2022 13:27:49 - INFO - codeparrot_training - Step 40825: {'lr': 0.00041979758402922496, 'samples': 20902912, 'steps': 40825, 'loss/train': 1.5176688432693481}
-03/05/2022 13:27:53 - INFO - codeparrot_training - Step 40826: {'lr': 0.00041979368904130086, 'samples': 20903424, 'steps': 40826, 'loss/train': 1.5179955959320068}
-03/05/2022 13:27:53 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/05/2022 13:27:58 - INFO - codeparrot_training - Step 40827: {'lr': 0.00041978979397687047, 'samples': 20903936, 'steps': 40827, 'loss/train': 0.508154571056366}
-03/05/2022 13:28:01 - INFO - codeparrot_training - Step 40828: {'lr': 0.00041978589883593525, 'samples': 20904448, 'steps': 40828, 'loss/train': 1.7374714612960815}
-03/05/2022 13:28:01 - INFO - codeparrot_training - Skipping example with length 600 (seq_length=1024)
-03/05/2022 13:28:06 - INFO - codeparrot_training - Step 40829: {'lr': 0.0004197820036184972, 'samples': 20904960, 'steps': 40829, 'loss/train': 0.4543156921863556}
-03/05/2022 13:28:10 - INFO - codeparrot_training - Step 40830: {'lr': 0.000419778108324558, 'samples': 20905472, 'steps': 40830, 'loss/train': 1.666825532913208}
-03/05/2022 13:28:10 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/05/2022 13:28:15 - INFO - codeparrot_training - Step 40831: {'lr': 0.00041977421295411944, 'samples': 20905984, 'steps': 40831, 'loss/train': 1.6334055662155151}
-03/05/2022 13:28:18 - INFO - codeparrot_training - Step 40832: {'lr': 0.00041977031750718317, 'samples': 20906496, 'steps': 40832, 'loss/train': 1.9684609174728394}
-03/05/2022 13:28:18 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/05/2022 13:28:24 - INFO - codeparrot_training - Step 40833: {'lr': 0.000419766421983751, 'samples': 20907008, 'steps': 40833, 'loss/train': 1.2559607028961182}
-03/05/2022 13:28:27 - INFO - codeparrot_training - Step 40834: {'lr': 0.00041976252638382483, 'samples': 20907520, 'steps': 40834, 'loss/train': 1.8854939937591553}
-03/05/2022 13:28:27 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/05/2022 13:28:32 - INFO - codeparrot_training - Step 40835: {'lr': 0.00041975863070740617, 'samples': 20908032, 'steps': 40835, 'loss/train': 1.1095410585403442}
-03/05/2022 13:28:35 - INFO - codeparrot_training - Step 40836: {'lr': 0.0004197547349544969, 'samples': 20908544, 'steps': 40836, 'loss/train': 1.7552261352539062}
-03/05/2022 13:28:35 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/05/2022 13:28:40 - INFO - codeparrot_training - Step 40837: {'lr': 0.0004197508391250988, 'samples': 20909056, 'steps': 40837, 'loss/train': 1.7714289426803589}
-03/05/2022 13:28:44 - INFO - codeparrot_training - Step 40838: {'lr': 0.0004197469432192136, 'samples': 20909568, 'steps': 40838, 'loss/train': 1.4921175241470337}
-03/05/2022 13:28:44 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/05/2022 13:28:49 - INFO - codeparrot_training - Step 40839: {'lr': 0.000419743047236843, 'samples': 20910080, 'steps': 40839, 'loss/train': 2.185542583465576}
-03/05/2022 13:28:52 - INFO - codeparrot_training - Step 40840: {'lr': 0.00041973915117798883, 'samples': 20910592, 'steps': 40840, 'loss/train': 0.8426290154457092}
-03/05/2022 13:28:52 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/05/2022 13:28:57 - INFO - codeparrot_training - Step 40841: {'lr': 0.0004197352550426528, 'samples': 20911104, 'steps': 40841, 'loss/train': 0.1514931321144104}
-03/05/2022 13:29:00 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 13:29:03 - INFO - codeparrot_training - Step 40842: {'lr': 0.0004197313588308367, 'samples': 20911616, 'steps': 40842, 'loss/train': 1.7960652112960815}
-03/05/2022 13:29:06 - INFO - codeparrot_training - Step 40843: {'lr': 0.0004197274625425423, 'samples': 20912128, 'steps': 40843, 'loss/train': 2.092384099960327}
-03/05/2022 13:29:09 - INFO - codeparrot_training - Step 40844: {'lr': 0.0004197235661777713, 'samples': 20912640, 'steps': 40844, 'loss/train': 1.8192914724349976}
-03/05/2022 13:29:09 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/05/2022 13:29:14 - INFO - codeparrot_training - Step 40845: {'lr': 0.00041971966973652545, 'samples': 20913152, 'steps': 40845, 'loss/train': 1.556200385093689}
-03/05/2022 13:29:17 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/05/2022 13:29:20 - INFO - codeparrot_training - Step 40846: {'lr': 0.00041971577321880656, 'samples': 20913664, 'steps': 40846, 'loss/train': 1.3775132894515991}
-03/05/2022 13:29:23 - INFO - codeparrot_training - Step 40847: {'lr': 0.00041971187662461634, 'samples': 20914176, 'steps': 40847, 'loss/train': 1.4390296936035156}
-03/05/2022 13:29:25 - INFO - codeparrot_training - Skipping example with length 983 (seq_length=1024)
-03/05/2022 13:29:28 - INFO - codeparrot_training - Step 40848: {'lr': 0.0004197079799539566, 'samples': 20914688, 'steps': 40848, 'loss/train': 1.519209861755371}
-03/05/2022 13:29:31 - INFO - codeparrot_training - Step 40849: {'lr': 0.0004197040832068291, 'samples': 20915200, 'steps': 40849, 'loss/train': 2.2003796100616455}
-03/05/2022 13:29:34 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/05/2022 13:29:37 - INFO - codeparrot_training - Step 40850: {'lr': 0.00041970018638323546, 'samples': 20915712, 'steps': 40850, 'loss/train': 2.002692937850952}
-03/05/2022 13:29:40 - INFO - codeparrot_training - Step 40851: {'lr': 0.00041969628948317756, 'samples': 20916224, 'steps': 40851, 'loss/train': 2.022545337677002}
-03/05/2022 13:29:42 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/05/2022 13:29:45 - INFO - codeparrot_training - Step 40852: {'lr': 0.00041969239250665716, 'samples': 20916736, 'steps': 40852, 'loss/train': 1.9416857957839966}
-03/05/2022 13:29:48 - INFO - codeparrot_training - Step 40853: {'lr': 0.000419688495453676, 'samples': 20917248, 'steps': 40853, 'loss/train': 2.34427809715271}
-03/05/2022 13:29:50 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/05/2022 13:29:54 - INFO - codeparrot_training - Step 40854: {'lr': 0.0004196845983242358, 'samples': 20917760, 'steps': 40854, 'loss/train': 2.160083532333374}
-03/05/2022 13:29:57 - INFO - codeparrot_training - Step 40855: {'lr': 0.0004196807011183383, 'samples': 20918272, 'steps': 40855, 'loss/train': 1.9553534984588623}
-03/05/2022 13:29:59 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/05/2022 13:30:02 - INFO - codeparrot_training - Step 40856: {'lr': 0.00041967680383598536, 'samples': 20918784, 'steps': 40856, 'loss/train': 2.1584765911102295}
-03/05/2022 13:30:05 - INFO - codeparrot_training - Step 40857: {'lr': 0.00041967290647717864, 'samples': 20919296, 'steps': 40857, 'loss/train': 1.483283519744873}
-03/05/2022 13:30:07 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 13:30:10 - INFO - codeparrot_training - Step 40858: {'lr': 0.00041966900904191995, 'samples': 20919808, 'steps': 40858, 'loss/train': 1.388810634613037}
-03/05/2022 13:30:14 - INFO - codeparrot_training - Step 40859: {'lr': 0.000419665111530211, 'samples': 20920320, 'steps': 40859, 'loss/train': 2.1027305126190186}
-03/05/2022 13:30:15 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 13:30:19 - INFO - codeparrot_training - Step 40860: {'lr': 0.00041966121394205357, 'samples': 20920832, 'steps': 40860, 'loss/train': 1.6768385171890259}
-03/05/2022 13:30:22 - INFO - codeparrot_training - Step 40861: {'lr': 0.0004196573162774494, 'samples': 20921344, 'steps': 40861, 'loss/train': 2.3207848072052}
-03/05/2022 13:30:24 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/05/2022 13:30:28 - INFO - codeparrot_training - Step 40862: {'lr': 0.0004196534185364003, 'samples': 20921856, 'steps': 40862, 'loss/train': 1.8999712467193604}
-03/05/2022 13:30:31 - INFO - codeparrot_training - Step 40863: {'lr': 0.00041964952071890795, 'samples': 20922368, 'steps': 40863, 'loss/train': 2.1954541206359863}
-03/05/2022 13:30:32 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 13:30:36 - INFO - codeparrot_training - Step 40864: {'lr': 0.00041964562282497417, 'samples': 20922880, 'steps': 40864, 'loss/train': 2.052569627761841}
-03/05/2022 13:30:39 - INFO - codeparrot_training - Step 40865: {'lr': 0.0004196417248546006, 'samples': 20923392, 'steps': 40865, 'loss/train': 2.286489248275757}
-03/05/2022 13:30:41 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/05/2022 13:30:45 - INFO - codeparrot_training - Step 40866: {'lr': 0.0004196378268077893, 'samples': 20923904, 'steps': 40866, 'loss/train': 1.9662140607833862}
-03/05/2022 13:30:48 - INFO - codeparrot_training - Step 40867: {'lr': 0.00041963392868454163, 'samples': 20924416, 'steps': 40867, 'loss/train': 1.2052921056747437}
-03/05/2022 13:30:50 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/05/2022 13:30:53 - INFO - codeparrot_training - Step 40868: {'lr': 0.0004196300304848596, 'samples': 20924928, 'steps': 40868, 'loss/train': 1.4810441732406616}
-03/05/2022 13:30:56 - INFO - codeparrot_training - Step 40869: {'lr': 0.00041962613220874486, 'samples': 20925440, 'steps': 40869, 'loss/train': 1.386450171470642}
-03/05/2022 13:30:58 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 13:31:01 - INFO - codeparrot_training - Step 40870: {'lr': 0.0004196222338561992, 'samples': 20925952, 'steps': 40870, 'loss/train': 2.079098701477051}
-03/05/2022 13:31:05 - INFO - codeparrot_training - Step 40871: {'lr': 0.0004196183354272244, 'samples': 20926464, 'steps': 40871, 'loss/train': 1.1608192920684814}
-03/05/2022 13:31:07 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/05/2022 13:31:10 - INFO - codeparrot_training - Step 40872: {'lr': 0.00041961443692182214, 'samples': 20926976, 'steps': 40872, 'loss/train': 2.019590139389038}
-03/05/2022 13:31:13 - INFO - codeparrot_training - Step 40873: {'lr': 0.00041961053833999433, 'samples': 20927488, 'steps': 40873, 'loss/train': 1.748381495475769}
-03/05/2022 13:31:15 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/05/2022 13:31:18 - INFO - codeparrot_training - Step 40874: {'lr': 0.00041960663968174263, 'samples': 20928000, 'steps': 40874, 'loss/train': 1.3677968978881836}
-03/05/2022 13:31:22 - INFO - codeparrot_training - Step 40875: {'lr': 0.0004196027409470687, 'samples': 20928512, 'steps': 40875, 'loss/train': 2.433924436569214}
-03/05/2022 13:31:23 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/05/2022 13:31:27 - INFO - codeparrot_training - Step 40876: {'lr': 0.00041959884213597443, 'samples': 20929024, 'steps': 40876, 'loss/train': 1.4287258386611938}
-03/05/2022 13:31:30 - INFO - codeparrot_training - Step 40877: {'lr': 0.0004195949432484615, 'samples': 20929536, 'steps': 40877, 'loss/train': 1.5623226165771484}
-03/05/2022 13:31:31 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/05/2022 13:31:35 - INFO - codeparrot_training - Step 40878: {'lr': 0.00041959104428453175, 'samples': 20930048, 'steps': 40878, 'loss/train': 1.4454883337020874}
-03/05/2022 13:31:38 - INFO - codeparrot_training - Step 40879: {'lr': 0.000419587145244187, 'samples': 20930560, 'steps': 40879, 'loss/train': 2.290069341659546}
-03/05/2022 13:31:40 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/05/2022 13:31:44 - INFO - codeparrot_training - Step 40880: {'lr': 0.0004195832461274288, 'samples': 20931072, 'steps': 40880, 'loss/train': 1.7995747327804565}
-03/05/2022 13:31:47 - INFO - codeparrot_training - Step 40881: {'lr': 0.00041957934693425894, 'samples': 20931584, 'steps': 40881, 'loss/train': 2.2749710083007812}
-03/05/2022 13:31:48 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/05/2022 13:31:52 - INFO - codeparrot_training - Step 40882: {'lr': 0.0004195754476646793, 'samples': 20932096, 'steps': 40882, 'loss/train': 0.8822826147079468}
-03/05/2022 13:31:55 - INFO - codeparrot_training - Step 40883: {'lr': 0.0004195715483186916, 'samples': 20932608, 'steps': 40883, 'loss/train': 0.6965515613555908}
-03/05/2022 13:31:57 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/05/2022 13:32:01 - INFO - codeparrot_training - Step 40884: {'lr': 0.00041956764889629756, 'samples': 20933120, 'steps': 40884, 'loss/train': 2.496389389038086}
-03/05/2022 13:32:04 - INFO - codeparrot_training - Step 40885: {'lr': 0.000419563749397499, 'samples': 20933632, 'steps': 40885, 'loss/train': 1.9617961645126343}
-03/05/2022 13:32:08 - INFO - codeparrot_training - Step 40886: {'lr': 0.00041955984982229756, 'samples': 20934144, 'steps': 40886, 'loss/train': 4.610908508300781}
-03/05/2022 13:32:08 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/05/2022 13:32:13 - INFO - codeparrot_training - Step 40887: {'lr': 0.0004195559501706951, 'samples': 20934656, 'steps': 40887, 'loss/train': 1.8994956016540527}
-03/05/2022 13:32:16 - INFO - codeparrot_training - Step 40888: {'lr': 0.0004195520504426933, 'samples': 20935168, 'steps': 40888, 'loss/train': 1.786508560180664}
-03/05/2022 13:32:17 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/05/2022 13:32:21 - INFO - codeparrot_training - Step 40889: {'lr': 0.000419548150638294, 'samples': 20935680, 'steps': 40889, 'loss/train': 1.107291579246521}
-03/05/2022 13:32:25 - INFO - codeparrot_training - Step 40890: {'lr': 0.0004195442507574989, 'samples': 20936192, 'steps': 40890, 'loss/train': 1.3861072063446045}
-03/05/2022 13:32:26 - INFO - codeparrot_training - Skipping example with length 144 (seq_length=1024)
-03/05/2022 13:32:30 - INFO - codeparrot_training - Step 40891: {'lr': 0.00041954035080030985, 'samples': 20936704, 'steps': 40891, 'loss/train': 2.0044682025909424}
-03/05/2022 13:32:33 - INFO - codeparrot_training - Step 40892: {'lr': 0.0004195364507667284, 'samples': 20937216, 'steps': 40892, 'loss/train': 1.2277030944824219}
-03/05/2022 13:32:34 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/05/2022 13:32:38 - INFO - codeparrot_training - Step 40893: {'lr': 0.0004195325506567566, 'samples': 20937728, 'steps': 40893, 'loss/train': 2.602017641067505}
-03/05/2022 13:32:41 - INFO - codeparrot_training - Step 40894: {'lr': 0.00041952865047039604, 'samples': 20938240, 'steps': 40894, 'loss/train': 1.9105859994888306}
-03/05/2022 13:32:42 - INFO - codeparrot_training - Skipping example with length 482 (seq_length=1024)
-03/05/2022 13:32:47 - INFO - codeparrot_training - Step 40895: {'lr': 0.00041952475020764834, 'samples': 20938752, 'steps': 40895, 'loss/train': 1.128890872001648}
-03/05/2022 13:32:50 - INFO - codeparrot_training - Step 40896: {'lr': 0.00041952084986851546, 'samples': 20939264, 'steps': 40896, 'loss/train': 2.159511089324951}
-03/05/2022 13:32:51 - INFO - codeparrot_training - Skipping example with length 808 (seq_length=1024)
-03/05/2022 13:32:55 - INFO - codeparrot_training - Step 40897: {'lr': 0.0004195169494529991, 'samples': 20939776, 'steps': 40897, 'loss/train': 0.9826498031616211}
-03/05/2022 13:32:58 - INFO - codeparrot_training - Step 40898: {'lr': 0.0004195130489611011, 'samples': 20940288, 'steps': 40898, 'loss/train': 2.002592086791992}
-03/05/2022 13:32:59 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/05/2022 13:33:04 - INFO - codeparrot_training - Step 40899: {'lr': 0.0004195091483928231, 'samples': 20940800, 'steps': 40899, 'loss/train': 1.979048490524292}
-03/05/2022 13:33:07 - INFO - codeparrot_training - Step 40900: {'lr': 0.0004195052477481669, 'samples': 20941312, 'steps': 40900, 'loss/train': 1.730732798576355}
-03/05/2022 13:33:07 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/05/2022 13:33:12 - INFO - codeparrot_training - Step 40901: {'lr': 0.00041950134702713415, 'samples': 20941824, 'steps': 40901, 'loss/train': 2.1525495052337646}
-03/05/2022 13:33:15 - INFO - codeparrot_training - Step 40902: {'lr': 0.0004194974462297268, 'samples': 20942336, 'steps': 40902, 'loss/train': 1.4320118427276611}
-03/05/2022 13:33:16 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/05/2022 13:33:21 - INFO - codeparrot_training - Step 40903: {'lr': 0.00041949354535594655, 'samples': 20942848, 'steps': 40903, 'loss/train': 1.8561313152313232}
-03/05/2022 13:33:24 - INFO - codeparrot_training - Step 40904: {'lr': 0.000419489644405795, 'samples': 20943360, 'steps': 40904, 'loss/train': 2.1206531524658203}
-03/05/2022 13:33:24 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/05/2022 13:33:29 - INFO - codeparrot_training - Step 40905: {'lr': 0.00041948574337927414, 'samples': 20943872, 'steps': 40905, 'loss/train': 2.100924253463745}
-03/05/2022 13:33:32 - INFO - codeparrot_training - Step 40906: {'lr': 0.0004194818422763856, 'samples': 20944384, 'steps': 40906, 'loss/train': 2.9402620792388916}
-03/05/2022 13:33:33 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/05/2022 13:33:38 - INFO - codeparrot_training - Step 40907: {'lr': 0.00041947794109713113, 'samples': 20944896, 'steps': 40907, 'loss/train': 2.1062545776367188}
-03/05/2022 13:33:41 - INFO - codeparrot_training - Step 40908: {'lr': 0.0004194740398415125, 'samples': 20945408, 'steps': 40908, 'loss/train': 1.3431569337844849}
-03/05/2022 13:33:41 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/05/2022 13:33:46 - INFO - codeparrot_training - Step 40909: {'lr': 0.00041947013850953156, 'samples': 20945920, 'steps': 40909, 'loss/train': 2.1743621826171875}
-03/05/2022 13:33:50 - INFO - codeparrot_training - Step 40910: {'lr': 0.00041946623710118993, 'samples': 20946432, 'steps': 40910, 'loss/train': 0.7801947593688965}
-03/05/2022 13:33:51 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/05/2022 13:33:55 - INFO - codeparrot_training - Step 40911: {'lr': 0.0004194623356164894, 'samples': 20946944, 'steps': 40911, 'loss/train': 1.059708833694458}
-03/05/2022 13:33:58 - INFO - codeparrot_training - Step 40912: {'lr': 0.0004194584340554318, 'samples': 20947456, 'steps': 40912, 'loss/train': 1.8934693336486816}
-03/05/2022 13:34:00 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/05/2022 13:34:03 - INFO - codeparrot_training - Step 40913: {'lr': 0.0004194545324180188, 'samples': 20947968, 'steps': 40913, 'loss/train': 1.8113795518875122}
-03/05/2022 13:34:07 - INFO - codeparrot_training - Step 40914: {'lr': 0.00041945063070425226, 'samples': 20948480, 'steps': 40914, 'loss/train': 1.6471275091171265}
-03/05/2022 13:34:09 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/05/2022 13:34:12 - INFO - codeparrot_training - Step 40915: {'lr': 0.0004194467289141339, 'samples': 20948992, 'steps': 40915, 'loss/train': 1.251671314239502}
-03/05/2022 13:34:16 - INFO - codeparrot_training - Step 40916: {'lr': 0.00041944282704766534, 'samples': 20949504, 'steps': 40916, 'loss/train': 1.3881092071533203}
-03/05/2022 13:34:17 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 13:34:21 - INFO - codeparrot_training - Step 40917: {'lr': 0.0004194389251048486, 'samples': 20950016, 'steps': 40917, 'loss/train': 1.9799801111221313}
-03/05/2022 13:34:24 - INFO - codeparrot_training - Step 40918: {'lr': 0.00041943502308568523, 'samples': 20950528, 'steps': 40918, 'loss/train': 2.951422929763794}
-03/05/2022 13:34:29 - INFO - codeparrot_training - Step 40919: {'lr': 0.000419431120990177, 'samples': 20951040, 'steps': 40919, 'loss/train': 1.9971290826797485}
-03/05/2022 13:34:33 - INFO - codeparrot_training - Step 40920: {'lr': 0.0004194272188183258, 'samples': 20951552, 'steps': 40920, 'loss/train': 1.3606972694396973}
-03/05/2022 13:34:34 - INFO - codeparrot_training - Skipping example with length 262 (seq_length=1024)
-03/05/2022 13:34:38 - INFO - codeparrot_training - Step 40921: {'lr': 0.0004194233165701333, 'samples': 20952064, 'steps': 40921, 'loss/train': 2.123211145401001}
-03/05/2022 13:34:41 - INFO - codeparrot_training - Step 40922: {'lr': 0.0004194194142456013, 'samples': 20952576, 'steps': 40922, 'loss/train': 1.9404993057250977}
-03/05/2022 13:34:43 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/05/2022 13:34:47 - INFO - codeparrot_training - Step 40923: {'lr': 0.00041941551184473144, 'samples': 20953088, 'steps': 40923, 'loss/train': 0.9128438830375671}
-03/05/2022 13:34:50 - INFO - codeparrot_training - Step 40924: {'lr': 0.0004194116093675256, 'samples': 20953600, 'steps': 40924, 'loss/train': 1.061419129371643}
-03/05/2022 13:34:51 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/05/2022 13:34:55 - INFO - codeparrot_training - Step 40925: {'lr': 0.0004194077068139855, 'samples': 20954112, 'steps': 40925, 'loss/train': 2.398571252822876}
-03/05/2022 13:34:58 - INFO - codeparrot_training - Step 40926: {'lr': 0.00041940380418411296, 'samples': 20954624, 'steps': 40926, 'loss/train': 0.8524813055992126}
-03/05/2022 13:35:00 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/05/2022 13:35:04 - INFO - codeparrot_training - Step 40927: {'lr': 0.00041939990147790956, 'samples': 20955136, 'steps': 40927, 'loss/train': 1.661476492881775}
-03/05/2022 13:35:07 - INFO - codeparrot_training - Step 40928: {'lr': 0.00041939599869537724, 'samples': 20955648, 'steps': 40928, 'loss/train': 0.5725401043891907}
-03/05/2022 13:35:09 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/05/2022 13:35:12 - INFO - codeparrot_training - Step 40929: {'lr': 0.00041939209583651774, 'samples': 20956160, 'steps': 40929, 'loss/train': 2.043174982070923}
-03/05/2022 13:35:15 - INFO - codeparrot_training - Step 40930: {'lr': 0.0004193881929013327, 'samples': 20956672, 'steps': 40930, 'loss/train': 1.9881279468536377}
-03/05/2022 13:35:18 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/05/2022 13:35:21 - INFO - codeparrot_training - Step 40931: {'lr': 0.00041938428988982403, 'samples': 20957184, 'steps': 40931, 'loss/train': 1.9028513431549072}
-03/05/2022 13:35:24 - INFO - codeparrot_training - Step 40932: {'lr': 0.00041938038680199333, 'samples': 20957696, 'steps': 40932, 'loss/train': 1.348423957824707}
-03/05/2022 13:35:26 - INFO - codeparrot_training - Skipping example with length 5 (seq_length=1024)
-03/05/2022 13:35:29 - INFO - codeparrot_training - Step 40933: {'lr': 0.0004193764836378425, 'samples': 20958208, 'steps': 40933, 'loss/train': 1.7691069841384888}
-03/05/2022 13:35:32 - INFO - codeparrot_training - Step 40934: {'lr': 0.0004193725803973732, 'samples': 20958720, 'steps': 40934, 'loss/train': 1.549912452697754}
-03/05/2022 13:35:35 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/05/2022 13:35:38 - INFO - codeparrot_training - Step 40935: {'lr': 0.0004193686770805873, 'samples': 20959232, 'steps': 40935, 'loss/train': 1.402387261390686}
-03/05/2022 13:35:41 - INFO - codeparrot_training - Step 40936: {'lr': 0.00041936477368748645, 'samples': 20959744, 'steps': 40936, 'loss/train': 1.004008173942566}
-03/05/2022 13:35:43 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/05/2022 13:35:46 - INFO - codeparrot_training - Step 40937: {'lr': 0.00041936087021807243, 'samples': 20960256, 'steps': 40937, 'loss/train': 1.6439785957336426}
-03/05/2022 13:35:49 - INFO - codeparrot_training - Step 40938: {'lr': 0.000419356966672347, 'samples': 20960768, 'steps': 40938, 'loss/train': 1.5676209926605225}
-03/05/2022 13:35:52 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/05/2022 13:35:55 - INFO - codeparrot_training - Step 40939: {'lr': 0.00041935306305031195, 'samples': 20961280, 'steps': 40939, 'loss/train': 2.307340383529663}
-03/05/2022 13:35:58 - INFO - codeparrot_training - Step 40940: {'lr': 0.000419349159351969, 'samples': 20961792, 'steps': 40940, 'loss/train': 2.4367105960845947}
-03/05/2022 13:36:00 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/05/2022 13:36:03 - INFO - codeparrot_training - Step 40941: {'lr': 0.00041934525557732005, 'samples': 20962304, 'steps': 40941, 'loss/train': 1.6212553977966309}
-03/05/2022 13:36:06 - INFO - codeparrot_training - Step 40942: {'lr': 0.00041934135172636667, 'samples': 20962816, 'steps': 40942, 'loss/train': 1.2108005285263062}
-03/05/2022 13:36:09 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/05/2022 13:36:11 - INFO - codeparrot_training - Step 40943: {'lr': 0.00041933744779911066, 'samples': 20963328, 'steps': 40943, 'loss/train': 1.7508940696716309}
-03/05/2022 13:36:15 - INFO - codeparrot_training - Step 40944: {'lr': 0.00041933354379555376, 'samples': 20963840, 'steps': 40944, 'loss/train': 1.8667831420898438}
-03/05/2022 13:36:17 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 13:36:21 - INFO - codeparrot_training - Step 40945: {'lr': 0.00041932963971569786, 'samples': 20964352, 'steps': 40945, 'loss/train': 1.935478687286377}
-03/05/2022 13:36:24 - INFO - codeparrot_training - Step 40946: {'lr': 0.0004193257355595446, 'samples': 20964864, 'steps': 40946, 'loss/train': 0.7698574662208557}
-03/05/2022 13:36:27 - INFO - codeparrot_training - Step 40947: {'lr': 0.00041932183132709587, 'samples': 20965376, 'steps': 40947, 'loss/train': 2.0890626907348633}
-03/05/2022 13:36:29 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/05/2022 13:36:32 - INFO - codeparrot_training - Step 40948: {'lr': 0.00041931792701835325, 'samples': 20965888, 'steps': 40948, 'loss/train': 1.6626851558685303}
-03/05/2022 13:36:35 - INFO - codeparrot_training - Step 40949: {'lr': 0.00041931402263331856, 'samples': 20966400, 'steps': 40949, 'loss/train': 0.8640086650848389}
-03/05/2022 13:36:38 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/05/2022 13:36:41 - INFO - codeparrot_training - Step 40950: {'lr': 0.0004193101181719936, 'samples': 20966912, 'steps': 40950, 'loss/train': 1.3986080884933472}
-03/05/2022 13:36:44 - INFO - codeparrot_training - Step 40951: {'lr': 0.00041930621363438014, 'samples': 20967424, 'steps': 40951, 'loss/train': 0.9665238857269287}
-03/05/2022 13:36:46 - INFO - codeparrot_training - Skipping example with length 153 (seq_length=1024)
-03/05/2022 13:36:49 - INFO - codeparrot_training - Step 40952: {'lr': 0.0004193023090204799, 'samples': 20967936, 'steps': 40952, 'loss/train': 2.0724000930786133}
-03/05/2022 13:36:52 - INFO - codeparrot_training - Step 40953: {'lr': 0.0004192984043302947, 'samples': 20968448, 'steps': 40953, 'loss/train': 2.046949863433838}
-03/05/2022 13:36:55 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/05/2022 13:36:57 - INFO - codeparrot_training - Step 40954: {'lr': 0.00041929449956382625, 'samples': 20968960, 'steps': 40954, 'loss/train': 1.2734843492507935}
-03/05/2022 13:37:01 - INFO - codeparrot_training - Step 40955: {'lr': 0.0004192905947210762, 'samples': 20969472, 'steps': 40955, 'loss/train': 0.21160177886486053}
-03/05/2022 13:37:03 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/05/2022 13:37:06 - INFO - codeparrot_training - Step 40956: {'lr': 0.00041928668980204653, 'samples': 20969984, 'steps': 40956, 'loss/train': 2.0453641414642334}
-03/05/2022 13:37:09 - INFO - codeparrot_training - Step 40957: {'lr': 0.00041928278480673884, 'samples': 20970496, 'steps': 40957, 'loss/train': 1.0631027221679688}
-03/05/2022 13:37:12 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/05/2022 13:37:15 - INFO - codeparrot_training - Step 40958: {'lr': 0.00041927887973515493, 'samples': 20971008, 'steps': 40958, 'loss/train': 1.5014387369155884}
-03/05/2022 13:37:18 - INFO - codeparrot_training - Step 40959: {'lr': 0.0004192749745872966, 'samples': 20971520, 'steps': 40959, 'loss/train': 1.5051966905593872}
-03/05/2022 13:37:20 - INFO - codeparrot_training - Skipping example with length 968 (seq_length=1024)
-03/05/2022 13:37:23 - INFO - codeparrot_training - Step 40960: {'lr': 0.00041927106936316563, 'samples': 20972032, 'steps': 40960, 'loss/train': 1.3896242380142212}
-03/05/2022 13:37:26 - INFO - codeparrot_training - Step 40961: {'lr': 0.00041926716406276367, 'samples': 20972544, 'steps': 40961, 'loss/train': 1.7977592945098877}
-03/05/2022 13:37:29 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/05/2022 13:37:32 - INFO - codeparrot_training - Step 40962: {'lr': 0.00041926325868609247, 'samples': 20973056, 'steps': 40962, 'loss/train': 1.337714433670044}
-03/05/2022 13:37:35 - INFO - codeparrot_training - Step 40963: {'lr': 0.0004192593532331539, 'samples': 20973568, 'steps': 40963, 'loss/train': 1.8626798391342163}
-03/05/2022 13:37:37 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 13:37:40 - INFO - codeparrot_training - Step 40964: {'lr': 0.00041925544770394976, 'samples': 20974080, 'steps': 40964, 'loss/train': 1.9915268421173096}
-03/05/2022 13:37:43 - INFO - codeparrot_training - Step 40965: {'lr': 0.0004192515420984816, 'samples': 20974592, 'steps': 40965, 'loss/train': 1.7338155508041382}
-03/05/2022 13:37:45 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/05/2022 13:37:49 - INFO - codeparrot_training - Step 40966: {'lr': 0.0004192476364167514, 'samples': 20975104, 'steps': 40966, 'loss/train': 1.7280715703964233}
-03/05/2022 13:37:52 - INFO - codeparrot_training - Step 40967: {'lr': 0.0004192437306587608, 'samples': 20975616, 'steps': 40967, 'loss/train': 1.925923228263855}
-03/05/2022 13:37:54 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/05/2022 13:37:57 - INFO - codeparrot_training - Step 40968: {'lr': 0.0004192398248245116, 'samples': 20976128, 'steps': 40968, 'loss/train': 1.7177178859710693}
-03/05/2022 13:38:00 - INFO - codeparrot_training - Step 40969: {'lr': 0.00041923591891400555, 'samples': 20976640, 'steps': 40969, 'loss/train': 1.7692251205444336}
-03/05/2022 13:38:02 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/05/2022 13:38:05 - INFO - codeparrot_training - Step 40970: {'lr': 0.00041923201292724436, 'samples': 20977152, 'steps': 40970, 'loss/train': 1.3442301750183105}
-03/05/2022 13:38:09 - INFO - codeparrot_training - Step 40971: {'lr': 0.00041922810686422987, 'samples': 20977664, 'steps': 40971, 'loss/train': 1.791410207748413}
-03/05/2022 13:38:11 - INFO - codeparrot_training - Skipping example with length 431 (seq_length=1024)
-03/05/2022 13:38:14 - INFO - codeparrot_training - Step 40972: {'lr': 0.00041922420072496383, 'samples': 20978176, 'steps': 40972, 'loss/train': 1.2592841386795044}
-03/05/2022 13:38:17 - INFO - codeparrot_training - Step 40973: {'lr': 0.00041922029450944785, 'samples': 20978688, 'steps': 40973, 'loss/train': 1.7606834173202515}
-03/05/2022 13:38:19 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/05/2022 13:38:22 - INFO - codeparrot_training - Step 40974: {'lr': 0.000419216388217684, 'samples': 20979200, 'steps': 40974, 'loss/train': 2.3748607635498047}
-03/05/2022 13:38:26 - INFO - codeparrot_training - Step 40975: {'lr': 0.00041921248184967374, 'samples': 20979712, 'steps': 40975, 'loss/train': 1.847153663635254}
-03/05/2022 13:38:27 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 13:38:31 - INFO - codeparrot_training - Step 40976: {'lr': 0.000419208575405419, 'samples': 20980224, 'steps': 40976, 'loss/train': 1.8363513946533203}
-03/05/2022 13:38:34 - INFO - codeparrot_training - Step 40977: {'lr': 0.00041920466888492147, 'samples': 20980736, 'steps': 40977, 'loss/train': 1.5221658945083618}
-03/05/2022 13:38:35 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/05/2022 13:38:39 - INFO - codeparrot_training - Step 40978: {'lr': 0.00041920076228818293, 'samples': 20981248, 'steps': 40978, 'loss/train': 1.1469863653182983}
-03/05/2022 13:38:42 - INFO - codeparrot_training - Step 40979: {'lr': 0.0004191968556152051, 'samples': 20981760, 'steps': 40979, 'loss/train': 2.035182476043701}
-03/05/2022 13:38:44 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/05/2022 13:38:48 - INFO - codeparrot_training - Step 40980: {'lr': 0.0004191929488659898, 'samples': 20982272, 'steps': 40980, 'loss/train': 2.027689218521118}
-03/05/2022 13:38:51 - INFO - codeparrot_training - Step 40981: {'lr': 0.00041918904204053874, 'samples': 20982784, 'steps': 40981, 'loss/train': 1.9462558031082153}
-03/05/2022 13:38:52 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 13:38:56 - INFO - codeparrot_training - Step 40982: {'lr': 0.0004191851351388538, 'samples': 20983296, 'steps': 40982, 'loss/train': 0.6240033507347107}
-03/05/2022 13:38:59 - INFO - codeparrot_training - Step 40983: {'lr': 0.0004191812281609366, 'samples': 20983808, 'steps': 40983, 'loss/train': 1.6453315019607544}
-03/05/2022 13:39:01 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/05/2022 13:39:05 - INFO - codeparrot_training - Step 40984: {'lr': 0.00041917732110678896, 'samples': 20984320, 'steps': 40984, 'loss/train': 0.23897503316402435}
-03/05/2022 13:39:08 - INFO - codeparrot_training - Step 40985: {'lr': 0.0004191734139764126, 'samples': 20984832, 'steps': 40985, 'loss/train': 3.1144537925720215}
-03/05/2022 13:39:09 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 13:39:13 - INFO - codeparrot_training - Step 40986: {'lr': 0.00041916950676980933, 'samples': 20985344, 'steps': 40986, 'loss/train': 1.1711925268173218}
-03/05/2022 13:39:16 - INFO - codeparrot_training - Step 40987: {'lr': 0.0004191655994869809, 'samples': 20985856, 'steps': 40987, 'loss/train': 1.3133169412612915}
-03/05/2022 13:39:17 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/05/2022 13:39:21 - INFO - codeparrot_training - Step 40988: {'lr': 0.000419161692127929, 'samples': 20986368, 'steps': 40988, 'loss/train': 1.712204933166504}
-03/05/2022 13:39:25 - INFO - codeparrot_training - Step 40989: {'lr': 0.00041915778469265555, 'samples': 20986880, 'steps': 40989, 'loss/train': 1.3019118309020996}
-03/05/2022 13:39:26 - INFO - codeparrot_training - Skipping example with length 462 (seq_length=1024)
-03/05/2022 13:39:30 - INFO - codeparrot_training - Step 40990: {'lr': 0.0004191538771811621, 'samples': 20987392, 'steps': 40990, 'loss/train': 1.3221882581710815}
-03/05/2022 13:39:33 - INFO - codeparrot_training - Step 40991: {'lr': 0.00041914996959345057, 'samples': 20987904, 'steps': 40991, 'loss/train': 1.387258768081665}
-03/05/2022 13:39:34 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/05/2022 13:39:38 - INFO - codeparrot_training - Step 40992: {'lr': 0.0004191460619295227, 'samples': 20988416, 'steps': 40992, 'loss/train': 1.239571213722229}
-03/05/2022 13:39:42 - INFO - codeparrot_training - Step 40993: {'lr': 0.0004191421541893802, 'samples': 20988928, 'steps': 40993, 'loss/train': 1.3564966917037964}
-03/05/2022 13:39:42 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/05/2022 13:39:47 - INFO - codeparrot_training - Step 40994: {'lr': 0.0004191382463730249, 'samples': 20989440, 'steps': 40994, 'loss/train': 1.7799856662750244}
-03/05/2022 13:39:50 - INFO - codeparrot_training - Step 40995: {'lr': 0.00041913433848045844, 'samples': 20989952, 'steps': 40995, 'loss/train': 1.5568857192993164}
-03/05/2022 13:39:52 - INFO - codeparrot_training - Skipping example with length 343 (seq_length=1024)
-03/05/2022 13:39:56 - INFO - codeparrot_training - Step 40996: {'lr': 0.00041913043051168276, 'samples': 20990464, 'steps': 40996, 'loss/train': 1.8372198343276978}
-03/05/2022 13:39:59 - INFO - codeparrot_training - Step 40997: {'lr': 0.00041912652246669943, 'samples': 20990976, 'steps': 40997, 'loss/train': 1.5470447540283203}
-03/05/2022 13:40:01 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/05/2022 13:40:04 - INFO - codeparrot_training - Step 40998: {'lr': 0.0004191226143455103, 'samples': 20991488, 'steps': 40998, 'loss/train': 1.61585533618927}
-03/05/2022 13:40:07 - INFO - codeparrot_training - Step 40999: {'lr': 0.00041911870614811715, 'samples': 20992000, 'steps': 40999, 'loss/train': 2.052797317504883}
-03/05/2022 13:40:09 - INFO - codeparrot_training - Skipping example with length 308 (seq_length=1024)
-03/05/2022 13:40:12 - INFO - codeparrot_training - Step 41000: {'lr': 0.00041911479787452177, 'samples': 20992512, 'steps': 41000, 'loss/train': 1.4795676469802856}
-03/05/2022 13:40:16 - INFO - codeparrot_training - Step 41001: {'lr': 0.0004191108895247258, 'samples': 20993024, 'steps': 41001, 'loss/train': 1.6969348192214966}
-03/05/2022 13:40:17 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 13:40:21 - INFO - codeparrot_training - Step 41002: {'lr': 0.00041910698109873116, 'samples': 20993536, 'steps': 41002, 'loss/train': 2.0577280521392822}
-03/05/2022 13:40:24 - INFO - codeparrot_training - Step 41003: {'lr': 0.0004191030725965394, 'samples': 20994048, 'steps': 41003, 'loss/train': 1.6729868650436401}
-03/05/2022 13:40:26 - INFO - codeparrot_training - Skipping example with length 648 (seq_length=1024)
-03/05/2022 13:40:30 - INFO - codeparrot_training - Step 41004: {'lr': 0.00041909916401815245, 'samples': 20994560, 'steps': 41004, 'loss/train': 0.7721620798110962}
-03/05/2022 13:40:33 - INFO - codeparrot_training - Step 41005: {'lr': 0.00041909525536357206, 'samples': 20995072, 'steps': 41005, 'loss/train': 0.7144091725349426}
-03/05/2022 13:40:36 - INFO - codeparrot_training - Step 41006: {'lr': 0.0004190913466327999, 'samples': 20995584, 'steps': 41006, 'loss/train': 2.2180771827697754}
-03/05/2022 13:40:38 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 13:40:41 - INFO - codeparrot_training - Step 41007: {'lr': 0.00041908743782583793, 'samples': 20996096, 'steps': 41007, 'loss/train': 1.0636593103408813}
-03/05/2022 13:40:45 - INFO - codeparrot_training - Step 41008: {'lr': 0.00041908352894268766, 'samples': 20996608, 'steps': 41008, 'loss/train': 1.0929205417633057}
-03/05/2022 13:40:46 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/05/2022 13:40:50 - INFO - codeparrot_training - Step 41009: {'lr': 0.00041907961998335094, 'samples': 20997120, 'steps': 41009, 'loss/train': 1.8538089990615845}
-03/05/2022 13:40:53 - INFO - codeparrot_training - Step 41010: {'lr': 0.0004190757109478296, 'samples': 20997632, 'steps': 41010, 'loss/train': 1.7064621448516846}
-03/05/2022 13:40:54 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/05/2022 13:40:58 - INFO - codeparrot_training - Step 41011: {'lr': 0.00041907180183612525, 'samples': 20998144, 'steps': 41011, 'loss/train': 1.7933845520019531}
-03/05/2022 13:41:01 - INFO - codeparrot_training - Step 41012: {'lr': 0.00041906789264823985, 'samples': 20998656, 'steps': 41012, 'loss/train': 1.492444634437561}
-03/05/2022 13:41:03 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 13:41:07 - INFO - codeparrot_training - Step 41013: {'lr': 0.00041906398338417504, 'samples': 20999168, 'steps': 41013, 'loss/train': 1.9002152681350708}
-03/05/2022 13:41:10 - INFO - codeparrot_training - Step 41014: {'lr': 0.00041906007404393273, 'samples': 20999680, 'steps': 41014, 'loss/train': 1.4806840419769287}
-03/05/2022 13:41:12 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/05/2022 13:41:15 - INFO - codeparrot_training - Step 41015: {'lr': 0.0004190561646275144, 'samples': 21000192, 'steps': 41015, 'loss/train': 0.7887071967124939}
-03/05/2022 13:41:18 - INFO - codeparrot_training - Step 41016: {'lr': 0.0004190522551349221, 'samples': 21000704, 'steps': 41016, 'loss/train': 2.177182674407959}
-03/05/2022 13:41:20 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/05/2022 13:41:24 - INFO - codeparrot_training - Step 41017: {'lr': 0.00041904834556615733, 'samples': 21001216, 'steps': 41017, 'loss/train': 1.8582791090011597}
-03/05/2022 13:41:27 - INFO - codeparrot_training - Step 41018: {'lr': 0.000419044435921222, 'samples': 21001728, 'steps': 41018, 'loss/train': 1.7931479215621948}
-03/05/2022 13:41:28 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/05/2022 13:41:32 - INFO - codeparrot_training - Step 41019: {'lr': 0.0004190405262001179, 'samples': 21002240, 'steps': 41019, 'loss/train': 2.078005790710449}
-03/05/2022 13:41:35 - INFO - codeparrot_training - Step 41020: {'lr': 0.00041903661640284675, 'samples': 21002752, 'steps': 41020, 'loss/train': 2.0085599422454834}
-03/05/2022 13:41:36 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/05/2022 13:41:41 - INFO - codeparrot_training - Step 41021: {'lr': 0.0004190327065294104, 'samples': 21003264, 'steps': 41021, 'loss/train': 1.4311343431472778}
-03/05/2022 13:41:44 - INFO - codeparrot_training - Step 41022: {'lr': 0.00041902879657981036, 'samples': 21003776, 'steps': 41022, 'loss/train': 1.1949687004089355}
-03/05/2022 13:41:45 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/05/2022 13:41:49 - INFO - codeparrot_training - Step 41023: {'lr': 0.00041902488655404864, 'samples': 21004288, 'steps': 41023, 'loss/train': 1.5510125160217285}
-03/05/2022 13:41:52 - INFO - codeparrot_training - Step 41024: {'lr': 0.0004190209764521269, 'samples': 21004800, 'steps': 41024, 'loss/train': 1.7241042852401733}
-03/05/2022 13:41:53 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/05/2022 13:41:57 - INFO - codeparrot_training - Step 41025: {'lr': 0.0004190170662740469, 'samples': 21005312, 'steps': 41025, 'loss/train': 1.844301462173462}
-03/05/2022 13:42:01 - INFO - codeparrot_training - Step 41026: {'lr': 0.0004190131560198104, 'samples': 21005824, 'steps': 41026, 'loss/train': 1.3409844636917114}
-03/05/2022 13:42:01 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/05/2022 13:42:06 - INFO - codeparrot_training - Step 41027: {'lr': 0.00041900924568941925, 'samples': 21006336, 'steps': 41027, 'loss/train': 1.69524347782135}
-03/05/2022 13:42:09 - INFO - codeparrot_training - Step 41028: {'lr': 0.0004190053352828751, 'samples': 21006848, 'steps': 41028, 'loss/train': 2.278975009918213}
-03/05/2022 13:42:10 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/05/2022 13:42:14 - INFO - codeparrot_training - Step 41029: {'lr': 0.00041900142480017974, 'samples': 21007360, 'steps': 41029, 'loss/train': 0.1403326541185379}
-03/05/2022 13:42:18 - INFO - codeparrot_training - Step 41030: {'lr': 0.0004189975142413349, 'samples': 21007872, 'steps': 41030, 'loss/train': 2.4323794841766357}
-03/05/2022 13:42:18 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/05/2022 13:42:23 - INFO - codeparrot_training - Step 41031: {'lr': 0.00041899360360634247, 'samples': 21008384, 'steps': 41031, 'loss/train': 0.4056245982646942}
-03/05/2022 13:42:26 - INFO - codeparrot_training - Step 41032: {'lr': 0.0004189896928952041, 'samples': 21008896, 'steps': 41032, 'loss/train': 2.012449264526367}
-03/05/2022 13:42:27 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/05/2022 13:42:31 - INFO - codeparrot_training - Step 41033: {'lr': 0.0004189857821079216, 'samples': 21009408, 'steps': 41033, 'loss/train': 1.9453412294387817}
-03/05/2022 13:42:34 - INFO - codeparrot_training - Step 41034: {'lr': 0.0004189818712444967, 'samples': 21009920, 'steps': 41034, 'loss/train': 1.399137258529663}
-03/05/2022 13:42:36 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/05/2022 13:42:40 - INFO - codeparrot_training - Step 41035: {'lr': 0.0004189779603049312, 'samples': 21010432, 'steps': 41035, 'loss/train': 1.1407676935195923}
-03/05/2022 13:42:43 - INFO - codeparrot_training - Step 41036: {'lr': 0.0004189740492892268, 'samples': 21010944, 'steps': 41036, 'loss/train': 1.5945695638656616}
-03/05/2022 13:42:44 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/05/2022 13:42:48 - INFO - codeparrot_training - Step 41037: {'lr': 0.0004189701381973853, 'samples': 21011456, 'steps': 41037, 'loss/train': 1.605156660079956}
-03/05/2022 13:42:51 - INFO - codeparrot_training - Step 41038: {'lr': 0.00041896622702940846, 'samples': 21011968, 'steps': 41038, 'loss/train': 0.2411782592535019}
-03/05/2022 13:42:54 - INFO - codeparrot_training - Skipping example with length 936 (seq_length=1024)
-03/05/2022 13:42:57 - INFO - codeparrot_training - Step 41039: {'lr': 0.0004189623157852981, 'samples': 21012480, 'steps': 41039, 'loss/train': 2.3039276599884033}
-03/05/2022 13:43:00 - INFO - codeparrot_training - Step 41040: {'lr': 0.0004189584044650559, 'samples': 21012992, 'steps': 41040, 'loss/train': 2.154139280319214}
-03/05/2022 13:43:03 - INFO - codeparrot_training - Skipping example with length 623 (seq_length=1024)
-03/05/2022 13:43:05 - INFO - codeparrot_training - Step 41041: {'lr': 0.0004189544930686837, 'samples': 21013504, 'steps': 41041, 'loss/train': 1.8504512310028076}
-03/05/2022 13:43:09 - INFO - codeparrot_training - Step 41042: {'lr': 0.0004189505815961831, 'samples': 21014016, 'steps': 41042, 'loss/train': 2.499389886856079}
-03/05/2022 13:43:12 - INFO - codeparrot_training - Step 41043: {'lr': 0.000418946670047556, 'samples': 21014528, 'steps': 41043, 'loss/train': 2.3691928386688232}
-03/05/2022 13:43:12 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/05/2022 13:43:17 - INFO - codeparrot_training - Step 41044: {'lr': 0.0004189427584228042, 'samples': 21015040, 'steps': 41044, 'loss/train': 2.185183048248291}
-03/05/2022 13:43:20 - INFO - codeparrot_training - Step 41045: {'lr': 0.0004189388467219294, 'samples': 21015552, 'steps': 41045, 'loss/train': 1.5055705308914185}
-03/05/2022 13:43:20 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 13:43:25 - INFO - codeparrot_training - Step 41046: {'lr': 0.0004189349349449333, 'samples': 21016064, 'steps': 41046, 'loss/train': 1.6246016025543213}
-03/05/2022 13:43:29 - INFO - codeparrot_training - Step 41047: {'lr': 0.00041893102309181773, 'samples': 21016576, 'steps': 41047, 'loss/train': 1.6436207294464111}
-03/05/2022 13:43:29 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/05/2022 13:43:34 - INFO - codeparrot_training - Step 41048: {'lr': 0.00041892711116258454, 'samples': 21017088, 'steps': 41048, 'loss/train': 1.7194164991378784}
-03/05/2022 13:43:37 - INFO - codeparrot_training - Step 41049: {'lr': 0.00041892319915723533, 'samples': 21017600, 'steps': 41049, 'loss/train': 1.5419973134994507}
-03/05/2022 13:43:37 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/05/2022 13:43:42 - INFO - codeparrot_training - Step 41050: {'lr': 0.0004189192870757719, 'samples': 21018112, 'steps': 41050, 'loss/train': 1.261130928993225}
-03/05/2022 13:43:46 - INFO - codeparrot_training - Step 41051: {'lr': 0.0004189153749181961, 'samples': 21018624, 'steps': 41051, 'loss/train': 1.9548683166503906}
-03/05/2022 13:43:46 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/05/2022 13:43:51 - INFO - codeparrot_training - Step 41052: {'lr': 0.00041891146268450963, 'samples': 21019136, 'steps': 41052, 'loss/train': 0.46127182245254517}
-03/05/2022 13:43:54 - INFO - codeparrot_training - Step 41053: {'lr': 0.0004189075503747142, 'samples': 21019648, 'steps': 41053, 'loss/train': 2.3016364574432373}
-03/05/2022 13:43:54 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/05/2022 13:43:59 - INFO - codeparrot_training - Step 41054: {'lr': 0.0004189036379888117, 'samples': 21020160, 'steps': 41054, 'loss/train': 1.670820951461792}
-03/05/2022 13:44:02 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/05/2022 13:44:05 - INFO - codeparrot_training - Step 41055: {'lr': 0.00041889972552680387, 'samples': 21020672, 'steps': 41055, 'loss/train': 1.149959683418274}
-03/05/2022 13:44:08 - INFO - codeparrot_training - Step 41056: {'lr': 0.0004188958129886924, 'samples': 21021184, 'steps': 41056, 'loss/train': 1.500604271888733}
-03/05/2022 13:44:11 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/05/2022 13:44:13 - INFO - codeparrot_training - Step 41057: {'lr': 0.000418891900374479, 'samples': 21021696, 'steps': 41057, 'loss/train': 1.4841886758804321}
-03/05/2022 13:44:16 - INFO - codeparrot_training - Step 41058: {'lr': 0.0004188879876841656, 'samples': 21022208, 'steps': 41058, 'loss/train': 1.8293884992599487}
-03/05/2022 13:44:19 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/05/2022 13:44:21 - INFO - codeparrot_training - Step 41059: {'lr': 0.0004188840749177538, 'samples': 21022720, 'steps': 41059, 'loss/train': 1.3883912563323975}
-03/05/2022 13:44:25 - INFO - codeparrot_training - Step 41060: {'lr': 0.0004188801620752455, 'samples': 21023232, 'steps': 41060, 'loss/train': 0.4288281798362732}
-03/05/2022 13:44:27 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/05/2022 13:44:30 - INFO - codeparrot_training - Step 41061: {'lr': 0.00041887624915664247, 'samples': 21023744, 'steps': 41061, 'loss/train': 1.8984296321868896}
-03/05/2022 13:44:33 - INFO - codeparrot_training - Step 41062: {'lr': 0.0004188723361619463, 'samples': 21024256, 'steps': 41062, 'loss/train': 1.6621243953704834}
-03/05/2022 13:44:36 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/05/2022 13:44:38 - INFO - codeparrot_training - Step 41063: {'lr': 0.0004188684230911589, 'samples': 21024768, 'steps': 41063, 'loss/train': 0.9106316566467285}
-03/05/2022 13:44:41 - INFO - codeparrot_training - Step 41064: {'lr': 0.00041886450994428197, 'samples': 21025280, 'steps': 41064, 'loss/train': 1.8130619525909424}
-03/05/2022 13:44:44 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/05/2022 13:44:47 - INFO - codeparrot_training - Step 41065: {'lr': 0.0004188605967213174, 'samples': 21025792, 'steps': 41065, 'loss/train': 0.6807711720466614}
-03/05/2022 13:44:50 - INFO - codeparrot_training - Step 41066: {'lr': 0.0004188566834222667, 'samples': 21026304, 'steps': 41066, 'loss/train': 1.2132093906402588}
-03/05/2022 13:44:52 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/05/2022 13:44:55 - INFO - codeparrot_training - Step 41067: {'lr': 0.00041885277004713185, 'samples': 21026816, 'steps': 41067, 'loss/train': 1.5936646461486816}
-03/05/2022 13:44:58 - INFO - codeparrot_training - Step 41068: {'lr': 0.0004188488565959146, 'samples': 21027328, 'steps': 41068, 'loss/train': 1.8115161657333374}
-03/05/2022 13:45:01 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 13:45:04 - INFO - codeparrot_training - Step 41069: {'lr': 0.0004188449430686166, 'samples': 21027840, 'steps': 41069, 'loss/train': 1.6091536283493042}
-03/05/2022 13:45:07 - INFO - codeparrot_training - Step 41070: {'lr': 0.00041884102946523964, 'samples': 21028352, 'steps': 41070, 'loss/train': 1.4992191791534424}
-03/05/2022 13:45:09 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 13:45:12 - INFO - codeparrot_training - Step 41071: {'lr': 0.0004188371157857856, 'samples': 21028864, 'steps': 41071, 'loss/train': 1.2206181287765503}
-03/05/2022 13:45:15 - INFO - codeparrot_training - Step 41072: {'lr': 0.0004188332020302561, 'samples': 21029376, 'steps': 41072, 'loss/train': 1.7516181468963623}
-03/05/2022 13:45:17 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/05/2022 13:45:20 - INFO - codeparrot_training - Step 41073: {'lr': 0.000418829288198653, 'samples': 21029888, 'steps': 41073, 'loss/train': 1.7559072971343994}
-03/05/2022 13:45:24 - INFO - codeparrot_training - Step 41074: {'lr': 0.00041882537429097804, 'samples': 21030400, 'steps': 41074, 'loss/train': 1.6876798868179321}
-03/05/2022 13:45:25 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/05/2022 13:45:29 - INFO - codeparrot_training - Step 41075: {'lr': 0.00041882146030723297, 'samples': 21030912, 'steps': 41075, 'loss/train': 2.428175687789917}
-03/05/2022 13:45:32 - INFO - codeparrot_training - Step 41076: {'lr': 0.0004188175462474195, 'samples': 21031424, 'steps': 41076, 'loss/train': 1.1477277278900146}
-03/05/2022 13:45:34 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 13:45:37 - INFO - codeparrot_training - Step 41077: {'lr': 0.0004188136321115395, 'samples': 21031936, 'steps': 41077, 'loss/train': 1.3877673149108887}
-03/05/2022 13:45:40 - INFO - codeparrot_training - Step 41078: {'lr': 0.00041880971789959466, 'samples': 21032448, 'steps': 41078, 'loss/train': 1.7370747327804565}
-03/05/2022 13:45:43 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/05/2022 13:45:46 - INFO - codeparrot_training - Step 41079: {'lr': 0.0004188058036115868, 'samples': 21032960, 'steps': 41079, 'loss/train': 2.0579209327697754}
-03/05/2022 13:45:49 - INFO - codeparrot_training - Step 41080: {'lr': 0.0004188018892475176, 'samples': 21033472, 'steps': 41080, 'loss/train': 1.8121000528335571}
-03/05/2022 13:45:51 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/05/2022 13:45:54 - INFO - codeparrot_training - Step 41081: {'lr': 0.0004187979748073889, 'samples': 21033984, 'steps': 41081, 'loss/train': 1.2361116409301758}
-03/05/2022 13:45:57 - INFO - codeparrot_training - Step 41082: {'lr': 0.0004187940602912024, 'samples': 21034496, 'steps': 41082, 'loss/train': 1.5722579956054688}
-03/05/2022 13:45:59 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/05/2022 13:46:03 - INFO - codeparrot_training - Step 41083: {'lr': 0.00041879014569895994, 'samples': 21035008, 'steps': 41083, 'loss/train': 0.3866863250732422}
-03/05/2022 13:46:06 - INFO - codeparrot_training - Step 41084: {'lr': 0.0004187862310306633, 'samples': 21035520, 'steps': 41084, 'loss/train': 1.1784895658493042}
-03/05/2022 13:46:08 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/05/2022 13:46:11 - INFO - codeparrot_training - Step 41085: {'lr': 0.00041878231628631406, 'samples': 21036032, 'steps': 41085, 'loss/train': 2.5081589221954346}
-03/05/2022 13:46:14 - INFO - codeparrot_training - Step 41086: {'lr': 0.0004187784014659142, 'samples': 21036544, 'steps': 41086, 'loss/train': 1.7863125801086426}
-03/05/2022 13:46:16 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/05/2022 13:46:20 - INFO - codeparrot_training - Step 41087: {'lr': 0.0004187744865694654, 'samples': 21037056, 'steps': 41087, 'loss/train': 1.8587837219238281}
-03/05/2022 13:46:23 - INFO - codeparrot_training - Step 41088: {'lr': 0.0004187705715969694, 'samples': 21037568, 'steps': 41088, 'loss/train': 2.090730667114258}
-03/05/2022 13:46:24 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/05/2022 13:46:28 - INFO - codeparrot_training - Step 41089: {'lr': 0.0004187666565484279, 'samples': 21038080, 'steps': 41089, 'loss/train': 1.724141240119934}
-03/05/2022 13:46:31 - INFO - codeparrot_training - Step 41090: {'lr': 0.0004187627414238428, 'samples': 21038592, 'steps': 41090, 'loss/train': 0.9857847690582275}
-03/05/2022 13:46:33 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/05/2022 13:46:36 - INFO - codeparrot_training - Step 41091: {'lr': 0.0004187588262232159, 'samples': 21039104, 'steps': 41091, 'loss/train': 1.4247395992279053}
-03/05/2022 13:46:40 - INFO - codeparrot_training - Step 41092: {'lr': 0.00041875491094654885, 'samples': 21039616, 'steps': 41092, 'loss/train': 1.6186214685440063}
-03/05/2022 13:46:41 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/05/2022 13:46:45 - INFO - codeparrot_training - Step 41093: {'lr': 0.0004187509955938434, 'samples': 21040128, 'steps': 41093, 'loss/train': 2.1064372062683105}
-03/05/2022 13:46:48 - INFO - codeparrot_training - Step 41094: {'lr': 0.0004187470801651013, 'samples': 21040640, 'steps': 41094, 'loss/train': 1.3506468534469604}
-03/05/2022 13:46:50 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/05/2022 13:46:54 - INFO - codeparrot_training - Step 41095: {'lr': 0.0004187431646603245, 'samples': 21041152, 'steps': 41095, 'loss/train': 2.1444263458251953}
-03/05/2022 13:46:57 - INFO - codeparrot_training - Step 41096: {'lr': 0.0004187392490795146, 'samples': 21041664, 'steps': 41096, 'loss/train': 1.2249301671981812}
-03/05/2022 13:46:59 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/05/2022 13:47:02 - INFO - codeparrot_training - Step 41097: {'lr': 0.00041873533342267336, 'samples': 21042176, 'steps': 41097, 'loss/train': 1.4259041547775269}
-03/05/2022 13:47:05 - INFO - codeparrot_training - Step 41098: {'lr': 0.0004187314176898026, 'samples': 21042688, 'steps': 41098, 'loss/train': 1.2251845598220825}
-03/05/2022 13:47:08 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/05/2022 13:47:11 - INFO - codeparrot_training - Step 41099: {'lr': 0.000418727501880904, 'samples': 21043200, 'steps': 41099, 'loss/train': 1.470958948135376}
-03/05/2022 13:47:14 - INFO - codeparrot_training - Step 41100: {'lr': 0.00041872358599597947, 'samples': 21043712, 'steps': 41100, 'loss/train': 2.103548288345337}
-03/05/2022 13:47:17 - INFO - codeparrot_training - Step 41101: {'lr': 0.00041871967003503073, 'samples': 21044224, 'steps': 41101, 'loss/train': 1.7502964735031128}
-03/05/2022 13:47:17 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/05/2022 13:47:22 - INFO - codeparrot_training - Step 41102: {'lr': 0.00041871575399805947, 'samples': 21044736, 'steps': 41102, 'loss/train': 1.6916648149490356}
-03/05/2022 13:47:26 - INFO - codeparrot_training - Step 41103: {'lr': 0.0004187118378850674, 'samples': 21045248, 'steps': 41103, 'loss/train': 1.1363284587860107}
-03/05/2022 13:47:26 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 13:47:31 - INFO - codeparrot_training - Step 41104: {'lr': 0.00041870792169605654, 'samples': 21045760, 'steps': 41104, 'loss/train': 1.6929562091827393}
-03/05/2022 13:47:34 - INFO - codeparrot_training - Step 41105: {'lr': 0.0004187040054310284, 'samples': 21046272, 'steps': 41105, 'loss/train': 1.268493413925171}
-03/05/2022 13:47:34 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/05/2022 13:47:39 - INFO - codeparrot_training - Step 41106: {'lr': 0.0004187000890899848, 'samples': 21046784, 'steps': 41106, 'loss/train': 1.3727134466171265}
-03/05/2022 13:47:42 - INFO - codeparrot_training - Step 41107: {'lr': 0.0004186961726729276, 'samples': 21047296, 'steps': 41107, 'loss/train': 2.0852911472320557}
-03/05/2022 13:47:42 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/05/2022 13:47:48 - INFO - codeparrot_training - Step 41108: {'lr': 0.0004186922561798585, 'samples': 21047808, 'steps': 41108, 'loss/train': 1.6850175857543945}
-03/05/2022 13:47:51 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/05/2022 13:47:53 - INFO - codeparrot_training - Step 41109: {'lr': 0.00041868833961077935, 'samples': 21048320, 'steps': 41109, 'loss/train': 1.2906277179718018}
-03/05/2022 13:47:56 - INFO - codeparrot_training - Step 41110: {'lr': 0.0004186844229656917, 'samples': 21048832, 'steps': 41110, 'loss/train': 2.163666248321533}
-03/05/2022 13:47:59 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/05/2022 13:48:01 - INFO - codeparrot_training - Step 41111: {'lr': 0.0004186805062445975, 'samples': 21049344, 'steps': 41111, 'loss/train': 1.5065124034881592}
-03/05/2022 13:48:05 - INFO - codeparrot_training - Step 41112: {'lr': 0.00041867658944749856, 'samples': 21049856, 'steps': 41112, 'loss/train': 2.1178276538848877}
-03/05/2022 13:48:07 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/05/2022 13:48:10 - INFO - codeparrot_training - Step 41113: {'lr': 0.00041867267257439644, 'samples': 21050368, 'steps': 41113, 'loss/train': 2.029750347137451}
-03/05/2022 13:48:13 - INFO - codeparrot_training - Step 41114: {'lr': 0.00041866875562529305, 'samples': 21050880, 'steps': 41114, 'loss/train': 2.126662492752075}
-03/05/2022 13:48:16 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/05/2022 13:48:18 - INFO - codeparrot_training - Step 41115: {'lr': 0.0004186648386001901, 'samples': 21051392, 'steps': 41115, 'loss/train': 1.650421380996704}
-03/05/2022 13:48:21 - INFO - codeparrot_training - Step 41116: {'lr': 0.0004186609214990894, 'samples': 21051904, 'steps': 41116, 'loss/train': 1.5452206134796143}
-03/05/2022 13:48:24 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 13:48:27 - INFO - codeparrot_training - Step 41117: {'lr': 0.0004186570043219927, 'samples': 21052416, 'steps': 41117, 'loss/train': 1.725466012954712}
-03/05/2022 13:48:30 - INFO - codeparrot_training - Step 41118: {'lr': 0.0004186530870689017, 'samples': 21052928, 'steps': 41118, 'loss/train': 0.2288942039012909}
-03/05/2022 13:48:33 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/05/2022 13:48:35 - INFO - codeparrot_training - Step 41119: {'lr': 0.00041864916973981833, 'samples': 21053440, 'steps': 41119, 'loss/train': 2.752560615539551}
-03/05/2022 13:48:38 - INFO - codeparrot_training - Step 41120: {'lr': 0.0004186452523347442, 'samples': 21053952, 'steps': 41120, 'loss/train': 1.6091042757034302}
-03/05/2022 13:48:41 - INFO - codeparrot_training - Skipping example with length 152 (seq_length=1024)
-03/05/2022 13:48:44 - INFO - codeparrot_training - Step 41121: {'lr': 0.00041864133485368106, 'samples': 21054464, 'steps': 41121, 'loss/train': 1.6022865772247314}
-03/05/2022 13:48:47 - INFO - codeparrot_training - Step 41122: {'lr': 0.0004186374172966308, 'samples': 21054976, 'steps': 41122, 'loss/train': 1.3499544858932495}
-03/05/2022 13:48:49 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 13:48:52 - INFO - codeparrot_training - Step 41123: {'lr': 0.0004186334996635951, 'samples': 21055488, 'steps': 41123, 'loss/train': 0.8171908259391785}
-03/05/2022 13:48:55 - INFO - codeparrot_training - Step 41124: {'lr': 0.00041862958195457574, 'samples': 21056000, 'steps': 41124, 'loss/train': 1.62832510471344}
-03/05/2022 13:48:58 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/05/2022 13:49:01 - INFO - codeparrot_training - Step 41125: {'lr': 0.0004186256641695745, 'samples': 21056512, 'steps': 41125, 'loss/train': 0.9367873668670654}
-03/05/2022 13:49:04 - INFO - codeparrot_training - Step 41126: {'lr': 0.00041862174630859315, 'samples': 21057024, 'steps': 41126, 'loss/train': 1.959223747253418}
-03/05/2022 13:49:07 - INFO - codeparrot_training - Step 41127: {'lr': 0.0004186178283716334, 'samples': 21057536, 'steps': 41127, 'loss/train': 0.9000644683837891}
-03/05/2022 13:49:07 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/05/2022 13:49:12 - INFO - codeparrot_training - Step 41128: {'lr': 0.0004186139103586971, 'samples': 21058048, 'steps': 41128, 'loss/train': 3.513206720352173}
-03/05/2022 13:49:16 - INFO - codeparrot_training - Step 41129: {'lr': 0.00041860999226978605, 'samples': 21058560, 'steps': 41129, 'loss/train': 0.5529110431671143}
-03/05/2022 13:49:16 - INFO - codeparrot_training - Skipping example with length 975 (seq_length=1024)
-03/05/2022 13:49:21 - INFO - codeparrot_training - Step 41130: {'lr': 0.0004186060741049018, 'samples': 21059072, 'steps': 41130, 'loss/train': 2.1105990409851074}
-03/05/2022 13:49:24 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/05/2022 13:49:26 - INFO - codeparrot_training - Step 41131: {'lr': 0.00041860215586404624, 'samples': 21059584, 'steps': 41131, 'loss/train': 0.7395280003547668}
-03/05/2022 13:49:29 - INFO - codeparrot_training - Step 41132: {'lr': 0.00041859823754722127, 'samples': 21060096, 'steps': 41132, 'loss/train': 2.056844711303711}
-03/05/2022 13:49:32 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 13:49:35 - INFO - codeparrot_training - Step 41133: {'lr': 0.00041859431915442847, 'samples': 21060608, 'steps': 41133, 'loss/train': 1.7224339246749878}
-03/05/2022 13:49:38 - INFO - codeparrot_training - Step 41134: {'lr': 0.0004185904006856697, 'samples': 21061120, 'steps': 41134, 'loss/train': 0.9022955894470215}
-03/05/2022 13:49:40 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 13:49:43 - INFO - codeparrot_training - Step 41135: {'lr': 0.0004185864821409467, 'samples': 21061632, 'steps': 41135, 'loss/train': 1.5830967426300049}
-03/05/2022 13:49:46 - INFO - codeparrot_training - Step 41136: {'lr': 0.00041858256352026124, 'samples': 21062144, 'steps': 41136, 'loss/train': 1.231931209564209}
-03/05/2022 13:49:50 - INFO - codeparrot_training - Step 41137: {'lr': 0.0004185786448236151, 'samples': 21062656, 'steps': 41137, 'loss/train': 2.28576397895813}
-03/05/2022 13:49:55 - INFO - codeparrot_training - Step 41138: {'lr': 0.0004185747260510099, 'samples': 21063168, 'steps': 41138, 'loss/train': 1.1137070655822754}
-03/05/2022 13:49:58 - INFO - codeparrot_training - Step 41139: {'lr': 0.0004185708072024476, 'samples': 21063680, 'steps': 41139, 'loss/train': 1.7347255945205688}
-03/05/2022 13:49:59 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/05/2022 13:50:03 - INFO - codeparrot_training - Step 41140: {'lr': 0.0004185668882779299, 'samples': 21064192, 'steps': 41140, 'loss/train': 1.5595333576202393}
-03/05/2022 13:50:06 - INFO - codeparrot_training - Step 41141: {'lr': 0.00041856296927745857, 'samples': 21064704, 'steps': 41141, 'loss/train': 1.7757669687271118}
-03/05/2022 13:50:07 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 13:50:12 - INFO - codeparrot_training - Step 41142: {'lr': 0.00041855905020103543, 'samples': 21065216, 'steps': 41142, 'loss/train': 1.018153429031372}
-03/05/2022 13:50:15 - INFO - codeparrot_training - Step 41143: {'lr': 0.00041855513104866203, 'samples': 21065728, 'steps': 41143, 'loss/train': 1.8286634683609009}
-03/05/2022 13:50:15 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/05/2022 13:50:20 - INFO - codeparrot_training - Step 41144: {'lr': 0.00041855121182034037, 'samples': 21066240, 'steps': 41144, 'loss/train': 1.716732144355774}
-03/05/2022 13:50:23 - INFO - codeparrot_training - Step 41145: {'lr': 0.00041854729251607214, 'samples': 21066752, 'steps': 41145, 'loss/train': 2.0188302993774414}
-03/05/2022 13:50:25 - INFO - codeparrot_training - Skipping example with length 702 (seq_length=1024)
-03/05/2022 13:50:29 - INFO - codeparrot_training - Step 41146: {'lr': 0.00041854337313585913, 'samples': 21067264, 'steps': 41146, 'loss/train': 1.2001093626022339}
-03/05/2022 13:50:32 - INFO - codeparrot_training - Step 41147: {'lr': 0.000418539453679703, 'samples': 21067776, 'steps': 41147, 'loss/train': 2.3629586696624756}
-03/05/2022 13:50:33 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/05/2022 13:50:37 - INFO - codeparrot_training - Step 41148: {'lr': 0.0004185355341476057, 'samples': 21068288, 'steps': 41148, 'loss/train': 1.9879628419876099}
-03/05/2022 13:50:40 - INFO - codeparrot_training - Step 41149: {'lr': 0.00041853161453956885, 'samples': 21068800, 'steps': 41149, 'loss/train': 1.8345636129379272}
-03/05/2022 13:50:41 - INFO - codeparrot_training - Skipping example with length 45 (seq_length=1024)
-03/05/2022 13:50:46 - INFO - codeparrot_training - Step 41150: {'lr': 0.0004185276948555942, 'samples': 21069312, 'steps': 41150, 'loss/train': 1.3249355554580688}
-03/05/2022 13:50:49 - INFO - codeparrot_training - Step 41151: {'lr': 0.0004185237750956836, 'samples': 21069824, 'steps': 41151, 'loss/train': 1.3783522844314575}
-03/05/2022 13:50:50 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/05/2022 13:50:54 - INFO - codeparrot_training - Step 41152: {'lr': 0.0004185198552598388, 'samples': 21070336, 'steps': 41152, 'loss/train': 1.0323559045791626}
-03/05/2022 13:50:57 - INFO - codeparrot_training - Step 41153: {'lr': 0.00041851593534806154, 'samples': 21070848, 'steps': 41153, 'loss/train': 1.7826143503189087}
-03/05/2022 13:50:58 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/05/2022 13:51:03 - INFO - codeparrot_training - Step 41154: {'lr': 0.0004185120153603536, 'samples': 21071360, 'steps': 41154, 'loss/train': 2.2439186573028564}
-03/05/2022 13:51:06 - INFO - codeparrot_training - Step 41155: {'lr': 0.0004185080952967168, 'samples': 21071872, 'steps': 41155, 'loss/train': 2.7682158946990967}
-03/05/2022 13:51:07 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/05/2022 13:51:11 - INFO - codeparrot_training - Step 41156: {'lr': 0.00041850417515715277, 'samples': 21072384, 'steps': 41156, 'loss/train': 2.0421481132507324}
-03/05/2022 13:51:14 - INFO - codeparrot_training - Step 41157: {'lr': 0.00041850025494166346, 'samples': 21072896, 'steps': 41157, 'loss/train': 2.000418186187744}
-03/05/2022 13:51:15 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/05/2022 13:51:19 - INFO - codeparrot_training - Step 41158: {'lr': 0.0004184963346502504, 'samples': 21073408, 'steps': 41158, 'loss/train': 0.8653706908226013}
-03/05/2022 13:51:23 - INFO - codeparrot_training - Step 41159: {'lr': 0.00041849241428291555, 'samples': 21073920, 'steps': 41159, 'loss/train': 1.4489761590957642}
-03/05/2022 13:51:23 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/05/2022 13:51:28 - INFO - codeparrot_training - Step 41160: {'lr': 0.00041848849383966063, 'samples': 21074432, 'steps': 41160, 'loss/train': 2.005323886871338}
-03/05/2022 13:51:31 - INFO - codeparrot_training - Step 41161: {'lr': 0.0004184845733204874, 'samples': 21074944, 'steps': 41161, 'loss/train': 1.868302822113037}
-03/05/2022 13:51:32 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/05/2022 13:51:36 - INFO - codeparrot_training - Step 41162: {'lr': 0.00041848065272539765, 'samples': 21075456, 'steps': 41162, 'loss/train': 1.3440266847610474}
-03/05/2022 13:51:40 - INFO - codeparrot_training - Step 41163: {'lr': 0.00041847673205439305, 'samples': 21075968, 'steps': 41163, 'loss/train': 1.754974603652954}
-03/05/2022 13:51:40 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/05/2022 13:51:45 - INFO - codeparrot_training - Step 41164: {'lr': 0.0004184728113074755, 'samples': 21076480, 'steps': 41164, 'loss/train': 1.8097138404846191}
-03/05/2022 13:51:48 - INFO - codeparrot_training - Step 41165: {'lr': 0.00041846889048464665, 'samples': 21076992, 'steps': 41165, 'loss/train': 1.2375239133834839}
-03/05/2022 13:51:49 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/05/2022 13:51:53 - INFO - codeparrot_training - Step 41166: {'lr': 0.0004184649695859083, 'samples': 21077504, 'steps': 41166, 'loss/train': 1.6322208642959595}
-03/05/2022 13:51:56 - INFO - codeparrot_training - Step 41167: {'lr': 0.00041846104861126233, 'samples': 21078016, 'steps': 41167, 'loss/train': 1.8964475393295288}
-03/05/2022 13:51:57 - INFO - codeparrot_training - Skipping example with length 135 (seq_length=1024)
-03/05/2022 13:52:02 - INFO - codeparrot_training - Step 41168: {'lr': 0.0004184571275607103, 'samples': 21078528, 'steps': 41168, 'loss/train': 1.865138053894043}
-03/05/2022 13:52:05 - INFO - codeparrot_training - Step 41169: {'lr': 0.0004184532064342542, 'samples': 21079040, 'steps': 41169, 'loss/train': 2.323068857192993}
-03/05/2022 13:52:06 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 13:52:10 - INFO - codeparrot_training - Step 41170: {'lr': 0.0004184492852318956, 'samples': 21079552, 'steps': 41170, 'loss/train': 1.8194564580917358}
-03/05/2022 13:52:13 - INFO - codeparrot_training - Step 41171: {'lr': 0.00041844536395363636, 'samples': 21080064, 'steps': 41171, 'loss/train': 1.66019606590271}
-03/05/2022 13:52:14 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 13:52:19 - INFO - codeparrot_training - Step 41172: {'lr': 0.00041844144259947825, 'samples': 21080576, 'steps': 41172, 'loss/train': 1.712084412574768}
-03/05/2022 13:52:22 - INFO - codeparrot_training - Step 41173: {'lr': 0.000418437521169423, 'samples': 21081088, 'steps': 41173, 'loss/train': 1.9518848657608032}
-03/05/2022 13:52:23 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/05/2022 13:52:27 - INFO - codeparrot_training - Step 41174: {'lr': 0.0004184335996634725, 'samples': 21081600, 'steps': 41174, 'loss/train': 1.5979403257369995}
-03/05/2022 13:52:30 - INFO - codeparrot_training - Step 41175: {'lr': 0.00041842967808162834, 'samples': 21082112, 'steps': 41175, 'loss/train': 1.5912139415740967}
-03/05/2022 13:52:31 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 13:52:35 - INFO - codeparrot_training - Step 41176: {'lr': 0.0004184257564238924, 'samples': 21082624, 'steps': 41176, 'loss/train': 1.5366384983062744}
-03/05/2022 13:52:39 - INFO - codeparrot_training - Step 41177: {'lr': 0.0004184218346902663, 'samples': 21083136, 'steps': 41177, 'loss/train': 2.2308242321014404}
-03/05/2022 13:52:39 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 13:52:44 - INFO - codeparrot_training - Step 41178: {'lr': 0.00041841791288075203, 'samples': 21083648, 'steps': 41178, 'loss/train': 0.6569976806640625}
-03/05/2022 13:52:47 - INFO - codeparrot_training - Step 41179: {'lr': 0.0004184139909953513, 'samples': 21084160, 'steps': 41179, 'loss/train': 2.3749375343322754}
-03/05/2022 13:52:48 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/05/2022 13:52:52 - INFO - codeparrot_training - Step 41180: {'lr': 0.0004184100690340657, 'samples': 21084672, 'steps': 41180, 'loss/train': 1.403815507888794}
-03/05/2022 13:52:55 - INFO - codeparrot_training - Step 41181: {'lr': 0.00041840614699689715, 'samples': 21085184, 'steps': 41181, 'loss/train': 2.528808832168579}
-03/05/2022 13:52:56 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/05/2022 13:53:01 - INFO - codeparrot_training - Step 41182: {'lr': 0.00041840222488384745, 'samples': 21085696, 'steps': 41182, 'loss/train': 1.4024723768234253}
-03/05/2022 13:53:04 - INFO - codeparrot_training - Step 41183: {'lr': 0.00041839830269491823, 'samples': 21086208, 'steps': 41183, 'loss/train': 1.2699087858200073}
-03/05/2022 13:53:04 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 13:53:09 - INFO - codeparrot_training - Step 41184: {'lr': 0.0004183943804301114, 'samples': 21086720, 'steps': 41184, 'loss/train': 1.3773987293243408}
-03/05/2022 13:53:12 - INFO - codeparrot_training - Step 41185: {'lr': 0.0004183904580894287, 'samples': 21087232, 'steps': 41185, 'loss/train': 1.5106024742126465}
-03/05/2022 13:53:13 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/05/2022 13:53:18 - INFO - codeparrot_training - Step 41186: {'lr': 0.0004183865356728717, 'samples': 21087744, 'steps': 41186, 'loss/train': 1.817452311515808}
-03/05/2022 13:53:21 - INFO - codeparrot_training - Step 41187: {'lr': 0.0004183826131804424, 'samples': 21088256, 'steps': 41187, 'loss/train': 1.856398344039917}
-03/05/2022 13:53:21 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/05/2022 13:53:26 - INFO - codeparrot_training - Step 41188: {'lr': 0.0004183786906121425, 'samples': 21088768, 'steps': 41188, 'loss/train': 1.7994089126586914}
-03/05/2022 13:53:29 - INFO - codeparrot_training - Step 41189: {'lr': 0.0004183747679679738, 'samples': 21089280, 'steps': 41189, 'loss/train': 1.376569390296936}
-03/05/2022 13:53:30 - INFO - codeparrot_training - Skipping example with length 716 (seq_length=1024)
-03/05/2022 13:53:35 - INFO - codeparrot_training - Step 41190: {'lr': 0.000418370845247938, 'samples': 21089792, 'steps': 41190, 'loss/train': 2.3518338203430176}
-03/05/2022 13:53:38 - INFO - codeparrot_training - Step 41191: {'lr': 0.0004183669224520369, 'samples': 21090304, 'steps': 41191, 'loss/train': 1.971714735031128}
-03/05/2022 13:53:39 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/05/2022 13:53:43 - INFO - codeparrot_training - Step 41192: {'lr': 0.00041836299958027226, 'samples': 21090816, 'steps': 41192, 'loss/train': 2.3321354389190674}
-03/05/2022 13:53:47 - INFO - codeparrot_training - Step 41193: {'lr': 0.00041835907663264585, 'samples': 21091328, 'steps': 41193, 'loss/train': 2.0686402320861816}
-03/05/2022 13:53:52 - INFO - codeparrot_training - Step 41194: {'lr': 0.0004183551536091594, 'samples': 21091840, 'steps': 41194, 'loss/train': 1.8655033111572266}
-03/05/2022 13:53:55 - INFO - codeparrot_training - Step 41195: {'lr': 0.00041835123050981476, 'samples': 21092352, 'steps': 41195, 'loss/train': 2.6990668773651123}
-03/05/2022 13:53:56 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/05/2022 13:54:00 - INFO - codeparrot_training - Step 41196: {'lr': 0.00041834730733461366, 'samples': 21092864, 'steps': 41196, 'loss/train': 1.1371666193008423}
-03/05/2022 13:54:04 - INFO - codeparrot_training - Step 41197: {'lr': 0.0004183433840835578, 'samples': 21093376, 'steps': 41197, 'loss/train': 1.8363350629806519}
-03/05/2022 13:54:05 - INFO - codeparrot_training - Skipping example with length 919 (seq_length=1024)
-03/05/2022 13:54:09 - INFO - codeparrot_training - Step 41198: {'lr': 0.0004183394607566491, 'samples': 21093888, 'steps': 41198, 'loss/train': 1.2701176404953003}
-03/05/2022 13:54:12 - INFO - codeparrot_training - Step 41199: {'lr': 0.0004183355373538892, 'samples': 21094400, 'steps': 41199, 'loss/train': 1.422743558883667}
-03/05/2022 13:54:13 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/05/2022 13:54:17 - INFO - codeparrot_training - Step 41200: {'lr': 0.00041833161387527985, 'samples': 21094912, 'steps': 41200, 'loss/train': 1.5286613702774048}
-03/05/2022 13:54:20 - INFO - codeparrot_training - Step 41201: {'lr': 0.0004183276903208228, 'samples': 21095424, 'steps': 41201, 'loss/train': 1.5519806146621704}
-03/05/2022 13:54:22 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/05/2022 13:54:26 - INFO - codeparrot_training - Step 41202: {'lr': 0.0004183237666905201, 'samples': 21095936, 'steps': 41202, 'loss/train': 1.311574935913086}
-03/05/2022 13:54:29 - INFO - codeparrot_training - Step 41203: {'lr': 0.0004183198429843732, 'samples': 21096448, 'steps': 41203, 'loss/train': 0.9975860118865967}
-03/05/2022 13:54:30 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/05/2022 13:54:34 - INFO - codeparrot_training - Step 41204: {'lr': 0.00041831591920238396, 'samples': 21096960, 'steps': 41204, 'loss/train': 0.8370639681816101}
-03/05/2022 13:54:37 - INFO - codeparrot_training - Step 41205: {'lr': 0.0004183119953445542, 'samples': 21097472, 'steps': 41205, 'loss/train': 2.3062281608581543}
-03/05/2022 13:54:38 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/05/2022 13:54:43 - INFO - codeparrot_training - Step 41206: {'lr': 0.00041830807141088566, 'samples': 21097984, 'steps': 41206, 'loss/train': 1.3624444007873535}
-03/05/2022 13:54:46 - INFO - codeparrot_training - Step 41207: {'lr': 0.0004183041474013801, 'samples': 21098496, 'steps': 41207, 'loss/train': 1.3393625020980835}
-03/05/2022 13:54:47 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 13:54:51 - INFO - codeparrot_training - Step 41208: {'lr': 0.00041830022331603925, 'samples': 21099008, 'steps': 41208, 'loss/train': 2.300197124481201}
-03/05/2022 13:54:54 - INFO - codeparrot_training - Step 41209: {'lr': 0.000418296299154865, 'samples': 21099520, 'steps': 41209, 'loss/train': 2.056607246398926}
-03/05/2022 13:54:55 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/05/2022 13:55:00 - INFO - codeparrot_training - Step 41210: {'lr': 0.000418292374917859, 'samples': 21100032, 'steps': 41210, 'loss/train': 1.9059653282165527}
-03/05/2022 13:55:03 - INFO - codeparrot_training - Step 41211: {'lr': 0.00041828845060502297, 'samples': 21100544, 'steps': 41211, 'loss/train': 1.9192699193954468}
-03/05/2022 13:55:04 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/05/2022 13:55:08 - INFO - codeparrot_training - Step 41212: {'lr': 0.00041828452621635884, 'samples': 21101056, 'steps': 41212, 'loss/train': 1.03080415725708}
-03/05/2022 13:55:11 - INFO - codeparrot_training - Step 41213: {'lr': 0.0004182806017518682, 'samples': 21101568, 'steps': 41213, 'loss/train': 0.5803110599517822}
-03/05/2022 13:55:13 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/05/2022 13:55:17 - INFO - codeparrot_training - Step 41214: {'lr': 0.00041827667721155303, 'samples': 21102080, 'steps': 41214, 'loss/train': 1.7304335832595825}
-03/05/2022 13:55:20 - INFO - codeparrot_training - Step 41215: {'lr': 0.000418272752595415, 'samples': 21102592, 'steps': 41215, 'loss/train': 1.7343441247940063}
-03/05/2022 13:55:21 - INFO - codeparrot_training - Skipping example with length 691 (seq_length=1024)
-03/05/2022 13:55:25 - INFO - codeparrot_training - Step 41216: {'lr': 0.00041826882790345577, 'samples': 21103104, 'steps': 41216, 'loss/train': 2.00553822517395}
-03/05/2022 13:55:28 - INFO - codeparrot_training - Step 41217: {'lr': 0.00041826490313567725, 'samples': 21103616, 'steps': 41217, 'loss/train': 2.670588731765747}
-03/05/2022 13:55:30 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/05/2022 13:55:34 - INFO - codeparrot_training - Step 41218: {'lr': 0.0004182609782920812, 'samples': 21104128, 'steps': 41218, 'loss/train': 0.8838427662849426}
-03/05/2022 13:55:37 - INFO - codeparrot_training - Step 41219: {'lr': 0.0004182570533726693, 'samples': 21104640, 'steps': 41219, 'loss/train': 1.7907472848892212}
-03/05/2022 13:55:39 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 13:55:42 - INFO - codeparrot_training - Step 41220: {'lr': 0.00041825312837744333, 'samples': 21105152, 'steps': 41220, 'loss/train': 1.9209403991699219}
-03/05/2022 13:55:45 - INFO - codeparrot_training - Step 41221: {'lr': 0.00041824920330640517, 'samples': 21105664, 'steps': 41221, 'loss/train': 2.2037532329559326}
-03/05/2022 13:55:47 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/05/2022 13:55:51 - INFO - codeparrot_training - Step 41222: {'lr': 0.0004182452781595565, 'samples': 21106176, 'steps': 41222, 'loss/train': 2.070722818374634}
-03/05/2022 13:55:54 - INFO - codeparrot_training - Step 41223: {'lr': 0.0004182413529368991, 'samples': 21106688, 'steps': 41223, 'loss/train': 1.9367988109588623}
-03/05/2022 13:55:56 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/05/2022 13:55:59 - INFO - codeparrot_training - Step 41224: {'lr': 0.0004182374276384347, 'samples': 21107200, 'steps': 41224, 'loss/train': 1.5406345129013062}
-03/05/2022 13:56:02 - INFO - codeparrot_training - Step 41225: {'lr': 0.0004182335022641651, 'samples': 21107712, 'steps': 41225, 'loss/train': 0.8368693590164185}
-03/05/2022 13:56:05 - INFO - codeparrot_training - Skipping example with length 524 (seq_length=1024)
-03/05/2022 13:56:08 - INFO - codeparrot_training - Step 41226: {'lr': 0.00041822957681409215, 'samples': 21108224, 'steps': 41226, 'loss/train': 2.128279685974121}
-03/05/2022 13:56:11 - INFO - codeparrot_training - Step 41227: {'lr': 0.00041822565128821757, 'samples': 21108736, 'steps': 41227, 'loss/train': 1.3355735540390015}
-03/05/2022 13:56:13 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/05/2022 13:56:16 - INFO - codeparrot_training - Step 41228: {'lr': 0.00041822172568654306, 'samples': 21109248, 'steps': 41228, 'loss/train': 1.3409826755523682}
-03/05/2022 13:56:19 - INFO - codeparrot_training - Step 41229: {'lr': 0.0004182178000090704, 'samples': 21109760, 'steps': 41229, 'loss/train': 1.667718529701233}
-03/05/2022 13:56:22 - INFO - codeparrot_training - Skipping example with length 432 (seq_length=1024)
-03/05/2022 13:56:25 - INFO - codeparrot_training - Step 41230: {'lr': 0.0004182138742558015, 'samples': 21110272, 'steps': 41230, 'loss/train': 1.5114679336547852}
-03/05/2022 13:56:28 - INFO - codeparrot_training - Step 41231: {'lr': 0.00041820994842673787, 'samples': 21110784, 'steps': 41231, 'loss/train': 1.5509049892425537}
-03/05/2022 13:56:30 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/05/2022 13:56:33 - INFO - codeparrot_training - Step 41232: {'lr': 0.00041820602252188156, 'samples': 21111296, 'steps': 41232, 'loss/train': 1.3173776865005493}
-03/05/2022 13:56:36 - INFO - codeparrot_training - Step 41233: {'lr': 0.00041820209654123416, 'samples': 21111808, 'steps': 41233, 'loss/train': 2.1119136810302734}
-03/05/2022 13:56:39 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/05/2022 13:56:42 - INFO - codeparrot_training - Step 41234: {'lr': 0.00041819817048479745, 'samples': 21112320, 'steps': 41234, 'loss/train': 2.3715312480926514}
-03/05/2022 13:56:45 - INFO - codeparrot_training - Step 41235: {'lr': 0.0004181942443525734, 'samples': 21112832, 'steps': 41235, 'loss/train': 0.9136230945587158}
-03/05/2022 13:56:47 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/05/2022 13:56:50 - INFO - codeparrot_training - Step 41236: {'lr': 0.00041819031814456346, 'samples': 21113344, 'steps': 41236, 'loss/train': 0.9060670733451843}
-03/05/2022 13:56:53 - INFO - codeparrot_training - Step 41237: {'lr': 0.0004181863918607696, 'samples': 21113856, 'steps': 41237, 'loss/train': 1.602925181388855}
-03/05/2022 13:56:55 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/05/2022 13:56:59 - INFO - codeparrot_training - Step 41238: {'lr': 0.00041818246550119354, 'samples': 21114368, 'steps': 41238, 'loss/train': 1.183271050453186}
-03/05/2022 13:57:02 - INFO - codeparrot_training - Step 41239: {'lr': 0.00041817853906583706, 'samples': 21114880, 'steps': 41239, 'loss/train': 1.553720474243164}
-03/05/2022 13:57:03 - INFO - codeparrot_training - Skipping example with length 119 (seq_length=1024)
-03/05/2022 13:57:07 - INFO - codeparrot_training - Step 41240: {'lr': 0.000418174612554702, 'samples': 21115392, 'steps': 41240, 'loss/train': 1.6230710744857788}
-03/05/2022 13:57:10 - INFO - codeparrot_training - Step 41241: {'lr': 0.00041817068596778994, 'samples': 21115904, 'steps': 41241, 'loss/train': 1.4995888471603394}
-03/05/2022 13:57:12 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/05/2022 13:57:15 - INFO - codeparrot_training - Step 41242: {'lr': 0.0004181667593051028, 'samples': 21116416, 'steps': 41242, 'loss/train': 2.0025620460510254}
-03/05/2022 13:57:19 - INFO - codeparrot_training - Step 41243: {'lr': 0.0004181628325666424, 'samples': 21116928, 'steps': 41243, 'loss/train': 0.7987639904022217}
-03/05/2022 13:57:21 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/05/2022 13:57:24 - INFO - codeparrot_training - Step 41244: {'lr': 0.0004181589057524103, 'samples': 21117440, 'steps': 41244, 'loss/train': 1.9542142152786255}
-03/05/2022 13:57:27 - INFO - codeparrot_training - Step 41245: {'lr': 0.0004181549788624085, 'samples': 21117952, 'steps': 41245, 'loss/train': 1.5663301944732666}
-03/05/2022 13:57:29 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/05/2022 13:57:32 - INFO - codeparrot_training - Step 41246: {'lr': 0.0004181510518966386, 'samples': 21118464, 'steps': 41246, 'loss/train': 1.8118267059326172}
-03/05/2022 13:57:36 - INFO - codeparrot_training - Step 41247: {'lr': 0.00041814712485510245, 'samples': 21118976, 'steps': 41247, 'loss/train': 1.9556540250778198}
-03/05/2022 13:57:37 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/05/2022 13:57:41 - INFO - codeparrot_training - Step 41248: {'lr': 0.0004181431977378017, 'samples': 21119488, 'steps': 41248, 'loss/train': 1.8735289573669434}
-03/05/2022 13:57:44 - INFO - codeparrot_training - Step 41249: {'lr': 0.00041813927054473835, 'samples': 21120000, 'steps': 41249, 'loss/train': 2.5114214420318604}
-03/05/2022 13:57:46 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/05/2022 13:57:50 - INFO - codeparrot_training - Step 41250: {'lr': 0.000418135343275914, 'samples': 21120512, 'steps': 41250, 'loss/train': 1.3334943056106567}
-03/05/2022 13:57:53 - INFO - codeparrot_training - Step 41251: {'lr': 0.0004181314159313305, 'samples': 21121024, 'steps': 41251, 'loss/train': 2.671445846557617}
-03/05/2022 13:57:56 - INFO - codeparrot_training - Step 41252: {'lr': 0.0004181274885109895, 'samples': 21121536, 'steps': 41252, 'loss/train': 1.1606566905975342}
-03/05/2022 13:57:56 - INFO - codeparrot_training - Skipping example with length 258 (seq_length=1024)
-03/05/2022 13:58:01 - INFO - codeparrot_training - Step 41253: {'lr': 0.0004181235610148929, 'samples': 21122048, 'steps': 41253, 'loss/train': 1.0835375785827637}
-03/05/2022 13:58:05 - INFO - codeparrot_training - Step 41254: {'lr': 0.0004181196334430424, 'samples': 21122560, 'steps': 41254, 'loss/train': 1.1294230222702026}
-03/05/2022 13:58:05 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/05/2022 13:58:10 - INFO - codeparrot_training - Step 41255: {'lr': 0.00041811570579543977, 'samples': 21123072, 'steps': 41255, 'loss/train': 1.5641123056411743}
-03/05/2022 13:58:13 - INFO - codeparrot_training - Step 41256: {'lr': 0.0004181117780720868, 'samples': 21123584, 'steps': 41256, 'loss/train': 1.7094708681106567}
-03/05/2022 13:58:13 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/05/2022 13:58:18 - INFO - codeparrot_training - Step 41257: {'lr': 0.00041810785027298524, 'samples': 21124096, 'steps': 41257, 'loss/train': 1.301736831665039}
-03/05/2022 13:58:22 - INFO - codeparrot_training - Step 41258: {'lr': 0.00041810392239813695, 'samples': 21124608, 'steps': 41258, 'loss/train': 1.2787635326385498}
-03/05/2022 13:58:22 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/05/2022 13:58:27 - INFO - codeparrot_training - Step 41259: {'lr': 0.00041809999444754353, 'samples': 21125120, 'steps': 41259, 'loss/train': 1.453263759613037}
-03/05/2022 13:58:30 - INFO - codeparrot_training - Step 41260: {'lr': 0.0004180960664212069, 'samples': 21125632, 'steps': 41260, 'loss/train': 1.7683976888656616}
-03/05/2022 13:58:30 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/05/2022 13:58:35 - INFO - codeparrot_training - Step 41261: {'lr': 0.00041809213831912884, 'samples': 21126144, 'steps': 41261, 'loss/train': 1.874083399772644}
-03/05/2022 13:58:39 - INFO - codeparrot_training - Step 41262: {'lr': 0.0004180882101413109, 'samples': 21126656, 'steps': 41262, 'loss/train': 0.9839652180671692}
-03/05/2022 13:58:39 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 13:58:44 - INFO - codeparrot_training - Step 41263: {'lr': 0.00041808428188775515, 'samples': 21127168, 'steps': 41263, 'loss/train': 2.279764175415039}
-03/05/2022 13:58:47 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/05/2022 13:58:49 - INFO - codeparrot_training - Step 41264: {'lr': 0.0004180803535584632, 'samples': 21127680, 'steps': 41264, 'loss/train': 1.8770774602890015}
-03/05/2022 13:58:52 - INFO - codeparrot_training - Step 41265: {'lr': 0.0004180764251534368, 'samples': 21128192, 'steps': 41265, 'loss/train': 1.9482192993164062}
-03/05/2022 13:58:56 - INFO - codeparrot_training - Step 41266: {'lr': 0.0004180724966726778, 'samples': 21128704, 'steps': 41266, 'loss/train': 0.642632007598877}
-03/05/2022 13:58:56 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/05/2022 13:59:01 - INFO - codeparrot_training - Step 41267: {'lr': 0.00041806856811618784, 'samples': 21129216, 'steps': 41267, 'loss/train': 2.1821072101593018}
-03/05/2022 13:59:04 - INFO - codeparrot_training - Step 41268: {'lr': 0.00041806463948396876, 'samples': 21129728, 'steps': 41268, 'loss/train': 0.2621918320655823}
-03/05/2022 13:59:04 - INFO - codeparrot_training - Skipping example with length 971 (seq_length=1024)
-03/05/2022 13:59:10 - INFO - codeparrot_training - Step 41269: {'lr': 0.0004180607107760225, 'samples': 21130240, 'steps': 41269, 'loss/train': 2.301719903945923}
-03/05/2022 13:59:13 - INFO - codeparrot_training - Step 41270: {'lr': 0.0004180567819923505, 'samples': 21130752, 'steps': 41270, 'loss/train': 0.679695188999176}
-03/05/2022 13:59:13 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 13:59:18 - INFO - codeparrot_training - Step 41271: {'lr': 0.0004180528531329548, 'samples': 21131264, 'steps': 41271, 'loss/train': 0.995402991771698}
-03/05/2022 13:59:21 - INFO - codeparrot_training - Step 41272: {'lr': 0.00041804892419783715, 'samples': 21131776, 'steps': 41272, 'loss/train': 1.6979581117630005}
-03/05/2022 13:59:21 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/05/2022 13:59:27 - INFO - codeparrot_training - Step 41273: {'lr': 0.0004180449951869991, 'samples': 21132288, 'steps': 41273, 'loss/train': 1.1068729162216187}
-03/05/2022 13:59:30 - INFO - codeparrot_training - Step 41274: {'lr': 0.00041804106610044263, 'samples': 21132800, 'steps': 41274, 'loss/train': 2.1111841201782227}
-03/05/2022 13:59:30 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/05/2022 13:59:35 - INFO - codeparrot_training - Step 41275: {'lr': 0.00041803713693816947, 'samples': 21133312, 'steps': 41275, 'loss/train': 1.8688689470291138}
-03/05/2022 13:59:38 - INFO - codeparrot_training - Step 41276: {'lr': 0.0004180332077001814, 'samples': 21133824, 'steps': 41276, 'loss/train': 1.699403166770935}
-03/05/2022 13:59:39 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/05/2022 13:59:44 - INFO - codeparrot_training - Step 41277: {'lr': 0.0004180292783864801, 'samples': 21134336, 'steps': 41277, 'loss/train': 1.6565762758255005}
-03/05/2022 13:59:47 - INFO - codeparrot_training - Step 41278: {'lr': 0.00041802534899706734, 'samples': 21134848, 'steps': 41278, 'loss/train': 1.1082160472869873}
-03/05/2022 13:59:47 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/05/2022 13:59:52 - INFO - codeparrot_training - Step 41279: {'lr': 0.0004180214195319451, 'samples': 21135360, 'steps': 41279, 'loss/train': 2.430673599243164}
-03/05/2022 13:59:55 - INFO - codeparrot_training - Step 41280: {'lr': 0.00041801748999111487, 'samples': 21135872, 'steps': 41280, 'loss/train': 2.0502943992614746}
-03/05/2022 13:59:56 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 14:00:01 - INFO - codeparrot_training - Step 41281: {'lr': 0.0004180135603745786, 'samples': 21136384, 'steps': 41281, 'loss/train': 1.9685955047607422}
-03/05/2022 14:00:04 - INFO - codeparrot_training - Step 41282: {'lr': 0.000418009630682338, 'samples': 21136896, 'steps': 41282, 'loss/train': 2.05086612701416}
-03/05/2022 14:00:04 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/05/2022 14:00:09 - INFO - codeparrot_training - Step 41283: {'lr': 0.00041800570091439493, 'samples': 21137408, 'steps': 41283, 'loss/train': 1.986607551574707}
-03/05/2022 14:00:12 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/05/2022 14:00:15 - INFO - codeparrot_training - Step 41284: {'lr': 0.000418001771070751, 'samples': 21137920, 'steps': 41284, 'loss/train': 1.4903050661087036}
-03/05/2022 14:00:18 - INFO - codeparrot_training - Step 41285: {'lr': 0.0004179978411514081, 'samples': 21138432, 'steps': 41285, 'loss/train': 1.240086317062378}
-03/05/2022 14:00:21 - INFO - codeparrot_training - Step 41286: {'lr': 0.000417993911156368, 'samples': 21138944, 'steps': 41286, 'loss/train': 2.352900743484497}
-03/05/2022 14:00:21 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/05/2022 14:00:26 - INFO - codeparrot_training - Step 41287: {'lr': 0.00041798998108563234, 'samples': 21139456, 'steps': 41287, 'loss/train': 0.9419495463371277}
-03/05/2022 14:00:29 - INFO - codeparrot_training - Step 41288: {'lr': 0.00041798605093920307, 'samples': 21139968, 'steps': 41288, 'loss/train': 1.733852744102478}
-03/05/2022 14:00:30 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/05/2022 14:00:35 - INFO - codeparrot_training - Step 41289: {'lr': 0.00041798212071708185, 'samples': 21140480, 'steps': 41289, 'loss/train': 1.440408706665039}
-03/05/2022 14:00:38 - INFO - codeparrot_training - Step 41290: {'lr': 0.0004179781904192704, 'samples': 21140992, 'steps': 41290, 'loss/train': 1.816108226776123}
-03/05/2022 14:00:38 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/05/2022 14:00:43 - INFO - codeparrot_training - Step 41291: {'lr': 0.00041797426004577066, 'samples': 21141504, 'steps': 41291, 'loss/train': 1.5101360082626343}
-03/05/2022 14:00:46 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/05/2022 14:00:48 - INFO - codeparrot_training - Step 41292: {'lr': 0.00041797032959658433, 'samples': 21142016, 'steps': 41292, 'loss/train': 1.3297199010849}
-03/05/2022 14:00:52 - INFO - codeparrot_training - Step 41293: {'lr': 0.0004179663990717131, 'samples': 21142528, 'steps': 41293, 'loss/train': 1.9037166833877563}
-03/05/2022 14:00:55 - INFO - codeparrot_training - Step 41294: {'lr': 0.0004179624684711588, 'samples': 21143040, 'steps': 41294, 'loss/train': 1.7262598276138306}
-03/05/2022 14:00:55 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/05/2022 14:01:00 - INFO - codeparrot_training - Step 41295: {'lr': 0.0004179585377949232, 'samples': 21143552, 'steps': 41295, 'loss/train': 1.7740334272384644}
-03/05/2022 14:01:03 - INFO - codeparrot_training - Step 41296: {'lr': 0.0004179546070430082, 'samples': 21144064, 'steps': 41296, 'loss/train': 1.5776933431625366}
-03/05/2022 14:01:03 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/05/2022 14:01:09 - INFO - codeparrot_training - Step 41297: {'lr': 0.0004179506762154153, 'samples': 21144576, 'steps': 41297, 'loss/train': 2.5094475746154785}
-03/05/2022 14:01:12 - INFO - codeparrot_training - Step 41298: {'lr': 0.0004179467453121465, 'samples': 21145088, 'steps': 41298, 'loss/train': 0.9548091292381287}
-03/05/2022 14:01:12 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/05/2022 14:01:17 - INFO - codeparrot_training - Step 41299: {'lr': 0.0004179428143332035, 'samples': 21145600, 'steps': 41299, 'loss/train': 1.590989112854004}
-03/05/2022 14:01:20 - INFO - codeparrot_training - Step 41300: {'lr': 0.000417938883278588, 'samples': 21146112, 'steps': 41300, 'loss/train': 1.2943713665008545}
-03/05/2022 14:01:20 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/05/2022 14:01:25 - INFO - codeparrot_training - Step 41301: {'lr': 0.0004179349521483018, 'samples': 21146624, 'steps': 41301, 'loss/train': 0.7039263844490051}
-03/05/2022 14:01:29 - INFO - codeparrot_training - Step 41302: {'lr': 0.00041793102094234673, 'samples': 21147136, 'steps': 41302, 'loss/train': 1.7996389865875244}
-03/05/2022 14:01:29 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/05/2022 14:01:34 - INFO - codeparrot_training - Step 41303: {'lr': 0.00041792708966072455, 'samples': 21147648, 'steps': 41303, 'loss/train': 1.233795166015625}
-03/05/2022 14:01:37 - INFO - codeparrot_training - Step 41304: {'lr': 0.0004179231583034371, 'samples': 21148160, 'steps': 41304, 'loss/train': 1.6007835865020752}
-03/05/2022 14:01:37 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/05/2022 14:01:42 - INFO - codeparrot_training - Step 41305: {'lr': 0.0004179192268704859, 'samples': 21148672, 'steps': 41305, 'loss/train': 1.6707309484481812}
-03/05/2022 14:01:46 - INFO - codeparrot_training - Step 41306: {'lr': 0.000417915295361873, 'samples': 21149184, 'steps': 41306, 'loss/train': 1.8995290994644165}
-03/05/2022 14:01:46 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/05/2022 14:01:51 - INFO - codeparrot_training - Step 41307: {'lr': 0.0004179113637776, 'samples': 21149696, 'steps': 41307, 'loss/train': 1.7555502653121948}
-03/05/2022 14:01:54 - INFO - codeparrot_training - Step 41308: {'lr': 0.0004179074321176688, 'samples': 21150208, 'steps': 41308, 'loss/train': 1.8940308094024658}
-03/05/2022 14:01:54 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/05/2022 14:01:59 - INFO - codeparrot_training - Step 41309: {'lr': 0.000417903500382081, 'samples': 21150720, 'steps': 41309, 'loss/train': 1.9318616390228271}
-03/05/2022 14:02:02 - INFO - codeparrot_training - Step 41310: {'lr': 0.00041789956857083853, 'samples': 21151232, 'steps': 41310, 'loss/train': 1.3472323417663574}
-03/05/2022 14:02:03 - INFO - codeparrot_training - Skipping example with length 428 (seq_length=1024)
-03/05/2022 14:02:08 - INFO - codeparrot_training - Step 41311: {'lr': 0.00041789563668394314, 'samples': 21151744, 'steps': 41311, 'loss/train': 1.6799806356430054}
-03/05/2022 14:02:12 - INFO - codeparrot_training - Step 41312: {'lr': 0.0004178917047213965, 'samples': 21152256, 'steps': 41312, 'loss/train': 1.6138566732406616}
-03/05/2022 14:02:14 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/05/2022 14:02:17 - INFO - codeparrot_training - Step 41313: {'lr': 0.00041788777268320055, 'samples': 21152768, 'steps': 41313, 'loss/train': 1.8129351139068604}
-03/05/2022 14:02:20 - INFO - codeparrot_training - Step 41314: {'lr': 0.00041788384056935693, 'samples': 21153280, 'steps': 41314, 'loss/train': 1.854110836982727}
-03/05/2022 14:02:22 - INFO - codeparrot_training - Skipping example with length 342 (seq_length=1024)
-03/05/2022 14:02:25 - INFO - codeparrot_training - Step 41315: {'lr': 0.0004178799083798673, 'samples': 21153792, 'steps': 41315, 'loss/train': 1.7234530448913574}
-03/05/2022 14:02:28 - INFO - codeparrot_training - Step 41316: {'lr': 0.00041787597611473375, 'samples': 21154304, 'steps': 41316, 'loss/train': 2.0414717197418213}
-03/05/2022 14:02:31 - INFO - codeparrot_training - Skipping example with length 161 (seq_length=1024)
-03/05/2022 14:02:34 - INFO - codeparrot_training - Step 41317: {'lr': 0.00041787204377395783, 'samples': 21154816, 'steps': 41317, 'loss/train': 1.5770747661590576}
-03/05/2022 14:02:37 - INFO - codeparrot_training - Step 41318: {'lr': 0.0004178681113575413, 'samples': 21155328, 'steps': 41318, 'loss/train': 2.080266237258911}
-03/05/2022 14:02:40 - INFO - codeparrot_training - Skipping example with length 609 (seq_length=1024)
-03/05/2022 14:02:42 - INFO - codeparrot_training - Step 41319: {'lr': 0.00041786417886548606, 'samples': 21155840, 'steps': 41319, 'loss/train': 2.4362993240356445}
-03/05/2022 14:02:45 - INFO - codeparrot_training - Step 41320: {'lr': 0.0004178602462977937, 'samples': 21156352, 'steps': 41320, 'loss/train': 1.4934478998184204}
-03/05/2022 14:02:48 - INFO - codeparrot_training - Skipping example with length 1002 (seq_length=1024)
-03/05/2022 14:02:51 - INFO - codeparrot_training - Step 41321: {'lr': 0.0004178563136544662, 'samples': 21156864, 'steps': 41321, 'loss/train': 1.558426856994629}
-03/05/2022 14:02:54 - INFO - codeparrot_training - Step 41322: {'lr': 0.0004178523809355053, 'samples': 21157376, 'steps': 41322, 'loss/train': 1.611952304840088}
-03/05/2022 14:02:57 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/05/2022 14:02:59 - INFO - codeparrot_training - Step 41323: {'lr': 0.00041784844814091263, 'samples': 21157888, 'steps': 41323, 'loss/train': 1.8530995845794678}
-03/05/2022 14:03:02 - INFO - codeparrot_training - Step 41324: {'lr': 0.00041784451527069, 'samples': 21158400, 'steps': 41324, 'loss/train': 1.7262744903564453}
-03/05/2022 14:03:05 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/05/2022 14:03:08 - INFO - codeparrot_training - Step 41325: {'lr': 0.0004178405823248392, 'samples': 21158912, 'steps': 41325, 'loss/train': 0.9384953379631042}
-03/05/2022 14:03:11 - INFO - codeparrot_training - Step 41326: {'lr': 0.0004178366493033621, 'samples': 21159424, 'steps': 41326, 'loss/train': 0.8365280628204346}
-03/05/2022 14:03:13 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/05/2022 14:03:16 - INFO - codeparrot_training - Step 41327: {'lr': 0.0004178327162062604, 'samples': 21159936, 'steps': 41327, 'loss/train': 1.593304991722107}
-03/05/2022 14:03:19 - INFO - codeparrot_training - Step 41328: {'lr': 0.00041782878303353577, 'samples': 21160448, 'steps': 41328, 'loss/train': 1.928503155708313}
-03/05/2022 14:03:21 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/05/2022 14:03:25 - INFO - codeparrot_training - Step 41329: {'lr': 0.0004178248497851902, 'samples': 21160960, 'steps': 41329, 'loss/train': 1.412644624710083}
-03/05/2022 14:03:28 - INFO - codeparrot_training - Step 41330: {'lr': 0.00041782091646122533, 'samples': 21161472, 'steps': 41330, 'loss/train': 2.297308921813965}
-03/05/2022 14:03:30 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/05/2022 14:03:33 - INFO - codeparrot_training - Step 41331: {'lr': 0.00041781698306164283, 'samples': 21161984, 'steps': 41331, 'loss/train': 1.157702088356018}
-03/05/2022 14:03:36 - INFO - codeparrot_training - Step 41332: {'lr': 0.0004178130495864447, 'samples': 21162496, 'steps': 41332, 'loss/train': 0.6593053340911865}
-03/05/2022 14:03:38 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/05/2022 14:03:42 - INFO - codeparrot_training - Step 41333: {'lr': 0.00041780911603563254, 'samples': 21163008, 'steps': 41333, 'loss/train': 1.9654645919799805}
-03/05/2022 14:03:45 - INFO - codeparrot_training - Step 41334: {'lr': 0.00041780518240920817, 'samples': 21163520, 'steps': 41334, 'loss/train': 1.7016255855560303}
-03/05/2022 14:03:47 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/05/2022 14:03:50 - INFO - codeparrot_training - Step 41335: {'lr': 0.0004178012487071734, 'samples': 21164032, 'steps': 41335, 'loss/train': 1.8197054862976074}
-03/05/2022 14:03:53 - INFO - codeparrot_training - Step 41336: {'lr': 0.00041779731492953, 'samples': 21164544, 'steps': 41336, 'loss/train': 1.7972651720046997}
-03/05/2022 14:03:56 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/05/2022 14:03:59 - INFO - codeparrot_training - Step 41337: {'lr': 0.0004177933810762797, 'samples': 21165056, 'steps': 41337, 'loss/train': 1.511178970336914}
-03/05/2022 14:04:02 - INFO - codeparrot_training - Step 41338: {'lr': 0.00041778944714742435, 'samples': 21165568, 'steps': 41338, 'loss/train': 1.0209686756134033}
-03/05/2022 14:04:04 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 14:04:07 - INFO - codeparrot_training - Step 41339: {'lr': 0.00041778551314296556, 'samples': 21166080, 'steps': 41339, 'loss/train': 1.4412848949432373}
-03/05/2022 14:04:10 - INFO - codeparrot_training - Step 41340: {'lr': 0.00041778157906290525, 'samples': 21166592, 'steps': 41340, 'loss/train': 1.6467466354370117}
-03/05/2022 14:04:13 - INFO - codeparrot_training - Skipping example with length 189 (seq_length=1024)
-03/05/2022 14:04:16 - INFO - codeparrot_training - Step 41341: {'lr': 0.00041777764490724515, 'samples': 21167104, 'steps': 41341, 'loss/train': 1.8432217836380005}
-03/05/2022 14:04:19 - INFO - codeparrot_training - Step 41342: {'lr': 0.00041777371067598705, 'samples': 21167616, 'steps': 41342, 'loss/train': 1.842079758644104}
-03/05/2022 14:04:21 - INFO - codeparrot_training - Skipping example with length 649 (seq_length=1024)
-03/05/2022 14:04:24 - INFO - codeparrot_training - Step 41343: {'lr': 0.00041776977636913274, 'samples': 21168128, 'steps': 41343, 'loss/train': 1.6550568342208862}
-03/05/2022 14:04:27 - INFO - codeparrot_training - Step 41344: {'lr': 0.0004177658419866839, 'samples': 21168640, 'steps': 41344, 'loss/train': 1.43836510181427}
-03/05/2022 14:04:30 - INFO - codeparrot_training - Skipping example with length 406 (seq_length=1024)
-03/05/2022 14:04:32 - INFO - codeparrot_training - Step 41345: {'lr': 0.0004177619075286424, 'samples': 21169152, 'steps': 41345, 'loss/train': 2.48230242729187}
-03/05/2022 14:04:36 - INFO - codeparrot_training - Step 41346: {'lr': 0.00041775797299500997, 'samples': 21169664, 'steps': 41346, 'loss/train': 1.5289934873580933}
-03/05/2022 14:04:38 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/05/2022 14:04:41 - INFO - codeparrot_training - Step 41347: {'lr': 0.0004177540383857883, 'samples': 21170176, 'steps': 41347, 'loss/train': 1.085195541381836}
-03/05/2022 14:04:44 - INFO - codeparrot_training - Step 41348: {'lr': 0.0004177501037009793, 'samples': 21170688, 'steps': 41348, 'loss/train': 1.1430209875106812}
-03/05/2022 14:04:47 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 14:04:49 - INFO - codeparrot_training - Step 41349: {'lr': 0.0004177461689405847, 'samples': 21171200, 'steps': 41349, 'loss/train': 1.6293845176696777}
-03/05/2022 14:04:53 - INFO - codeparrot_training - Step 41350: {'lr': 0.00041774223410460633, 'samples': 21171712, 'steps': 41350, 'loss/train': 1.8101744651794434}
-03/05/2022 14:04:55 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/05/2022 14:04:58 - INFO - codeparrot_training - Step 41351: {'lr': 0.00041773829919304584, 'samples': 21172224, 'steps': 41351, 'loss/train': 1.8233696222305298}
-03/05/2022 14:05:01 - INFO - codeparrot_training - Step 41352: {'lr': 0.000417734364205905, 'samples': 21172736, 'steps': 41352, 'loss/train': 1.3833693265914917}
-03/05/2022 14:05:04 - INFO - codeparrot_training - Step 41353: {'lr': 0.0004177304291431857, 'samples': 21173248, 'steps': 41353, 'loss/train': 1.973091721534729}
-03/05/2022 14:05:05 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/05/2022 14:05:10 - INFO - codeparrot_training - Step 41354: {'lr': 0.00041772649400488967, 'samples': 21173760, 'steps': 41354, 'loss/train': 0.7227315306663513}
-03/05/2022 14:05:13 - INFO - codeparrot_training - Step 41355: {'lr': 0.0004177225587910186, 'samples': 21174272, 'steps': 41355, 'loss/train': 1.5179675817489624}
-03/05/2022 14:05:13 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/05/2022 14:05:18 - INFO - codeparrot_training - Step 41356: {'lr': 0.0004177186235015744, 'samples': 21174784, 'steps': 41356, 'loss/train': 2.006666898727417}
-03/05/2022 14:05:21 - INFO - codeparrot_training - Step 41357: {'lr': 0.0004177146881365588, 'samples': 21175296, 'steps': 41357, 'loss/train': 1.361484169960022}
-03/05/2022 14:05:22 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/05/2022 14:05:27 - INFO - codeparrot_training - Step 41358: {'lr': 0.00041771075269597354, 'samples': 21175808, 'steps': 41358, 'loss/train': 0.18406705558300018}
-03/05/2022 14:05:30 - INFO - codeparrot_training - Step 41359: {'lr': 0.0004177068171798204, 'samples': 21176320, 'steps': 41359, 'loss/train': 1.806839942932129}
-03/05/2022 14:05:30 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 14:05:35 - INFO - codeparrot_training - Step 41360: {'lr': 0.0004177028815881011, 'samples': 21176832, 'steps': 41360, 'loss/train': 0.7810460925102234}
-03/05/2022 14:05:38 - INFO - codeparrot_training - Step 41361: {'lr': 0.00041769894592081746, 'samples': 21177344, 'steps': 41361, 'loss/train': 1.4558087587356567}
-03/05/2022 14:05:39 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/05/2022 14:05:44 - INFO - codeparrot_training - Step 41362: {'lr': 0.0004176950101779713, 'samples': 21177856, 'steps': 41362, 'loss/train': 3.566206455230713}
-03/05/2022 14:05:47 - INFO - codeparrot_training - Step 41363: {'lr': 0.00041769107435956444, 'samples': 21178368, 'steps': 41363, 'loss/train': 1.2696261405944824}
-03/05/2022 14:05:48 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/05/2022 14:05:52 - INFO - codeparrot_training - Step 41364: {'lr': 0.00041768713846559844, 'samples': 21178880, 'steps': 41364, 'loss/train': 1.3685111999511719}
-03/05/2022 14:05:56 - INFO - codeparrot_training - Step 41365: {'lr': 0.00041768320249607527, 'samples': 21179392, 'steps': 41365, 'loss/train': 1.4516844749450684}
-03/05/2022 14:05:57 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/05/2022 14:06:01 - INFO - codeparrot_training - Step 41366: {'lr': 0.00041767926645099664, 'samples': 21179904, 'steps': 41366, 'loss/train': 1.7407466173171997}
-03/05/2022 14:06:04 - INFO - codeparrot_training - Step 41367: {'lr': 0.00041767533033036425, 'samples': 21180416, 'steps': 41367, 'loss/train': 1.7720054388046265}
-03/05/2022 14:06:05 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 14:06:09 - INFO - codeparrot_training - Step 41368: {'lr': 0.00041767139413418, 'samples': 21180928, 'steps': 41368, 'loss/train': 1.6418370008468628}
-03/05/2022 14:06:12 - INFO - codeparrot_training - Step 41369: {'lr': 0.00041766745786244564, 'samples': 21181440, 'steps': 41369, 'loss/train': 1.5588502883911133}
-03/05/2022 14:06:13 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/05/2022 14:06:18 - INFO - codeparrot_training - Step 41370: {'lr': 0.00041766352151516284, 'samples': 21181952, 'steps': 41370, 'loss/train': 1.1523798704147339}
-03/05/2022 14:06:21 - INFO - codeparrot_training - Step 41371: {'lr': 0.0004176595850923335, 'samples': 21182464, 'steps': 41371, 'loss/train': 1.9474139213562012}
-03/05/2022 14:06:22 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/05/2022 14:06:26 - INFO - codeparrot_training - Step 41372: {'lr': 0.0004176556485939593, 'samples': 21182976, 'steps': 41372, 'loss/train': 0.9940188527107239}
-03/05/2022 14:06:29 - INFO - codeparrot_training - Step 41373: {'lr': 0.00041765171202004205, 'samples': 21183488, 'steps': 41373, 'loss/train': 1.9338175058364868}
-03/05/2022 14:06:30 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/05/2022 14:06:35 - INFO - codeparrot_training - Step 41374: {'lr': 0.00041764777537058354, 'samples': 21184000, 'steps': 41374, 'loss/train': 2.2829370498657227}
-03/05/2022 14:06:38 - INFO - codeparrot_training - Step 41375: {'lr': 0.0004176438386455855, 'samples': 21184512, 'steps': 41375, 'loss/train': 1.968406081199646}
-03/05/2022 14:06:39 - INFO - codeparrot_training - Skipping example with length 980 (seq_length=1024)
-03/05/2022 14:06:43 - INFO - codeparrot_training - Step 41376: {'lr': 0.00041763990184504984, 'samples': 21185024, 'steps': 41376, 'loss/train': 1.9372787475585938}
-03/05/2022 14:06:46 - INFO - codeparrot_training - Step 41377: {'lr': 0.00041763596496897817, 'samples': 21185536, 'steps': 41377, 'loss/train': 2.1158833503723145}
-03/05/2022 14:06:47 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/05/2022 14:06:52 - INFO - codeparrot_training - Step 41378: {'lr': 0.00041763202801737225, 'samples': 21186048, 'steps': 41378, 'loss/train': 1.9344704151153564}
-03/05/2022 14:06:55 - INFO - codeparrot_training - Step 41379: {'lr': 0.00041762809099023403, 'samples': 21186560, 'steps': 41379, 'loss/train': 1.58267080783844}
-03/05/2022 14:06:56 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 14:07:00 - INFO - codeparrot_training - Step 41380: {'lr': 0.00041762415388756514, 'samples': 21187072, 'steps': 41380, 'loss/train': 1.8077571392059326}
-03/05/2022 14:07:03 - INFO - codeparrot_training - Step 41381: {'lr': 0.00041762021670936736, 'samples': 21187584, 'steps': 41381, 'loss/train': 1.012739658355713}
-03/05/2022 14:07:05 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/05/2022 14:07:08 - INFO - codeparrot_training - Step 41382: {'lr': 0.0004176162794556425, 'samples': 21188096, 'steps': 41382, 'loss/train': 0.18582558631896973}
-03/05/2022 14:07:12 - INFO - codeparrot_training - Step 41383: {'lr': 0.0004176123421263923, 'samples': 21188608, 'steps': 41383, 'loss/train': 1.7358652353286743}
-03/05/2022 14:07:13 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/05/2022 14:07:17 - INFO - codeparrot_training - Step 41384: {'lr': 0.00041760840472161866, 'samples': 21189120, 'steps': 41384, 'loss/train': 1.191225290298462}
-03/05/2022 14:07:20 - INFO - codeparrot_training - Step 41385: {'lr': 0.0004176044672413232, 'samples': 21189632, 'steps': 41385, 'loss/train': 1.1092634201049805}
-03/05/2022 14:07:21 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/05/2022 14:07:25 - INFO - codeparrot_training - Step 41386: {'lr': 0.00041760052968550776, 'samples': 21190144, 'steps': 41386, 'loss/train': 1.3499988317489624}
-03/05/2022 14:07:28 - INFO - codeparrot_training - Step 41387: {'lr': 0.0004175965920541741, 'samples': 21190656, 'steps': 41387, 'loss/train': 2.5596742630004883}
-03/05/2022 14:07:30 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 14:07:34 - INFO - codeparrot_training - Step 41388: {'lr': 0.00041759265434732404, 'samples': 21191168, 'steps': 41388, 'loss/train': 1.742496132850647}
-03/05/2022 14:07:37 - INFO - codeparrot_training - Step 41389: {'lr': 0.00041758871656495927, 'samples': 21191680, 'steps': 41389, 'loss/train': 1.6967554092407227}
-03/05/2022 14:07:38 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/05/2022 14:07:42 - INFO - codeparrot_training - Step 41390: {'lr': 0.00041758477870708165, 'samples': 21192192, 'steps': 41390, 'loss/train': 0.1480623185634613}
-03/05/2022 14:07:45 - INFO - codeparrot_training - Step 41391: {'lr': 0.0004175808407736929, 'samples': 21192704, 'steps': 41391, 'loss/train': 1.4847979545593262}
-03/05/2022 14:07:46 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 14:07:51 - INFO - codeparrot_training - Step 41392: {'lr': 0.00041757690276479474, 'samples': 21193216, 'steps': 41392, 'loss/train': 1.476781964302063}
-03/05/2022 14:07:54 - INFO - codeparrot_training - Step 41393: {'lr': 0.0004175729646803891, 'samples': 21193728, 'steps': 41393, 'loss/train': 2.365790367126465}
-03/05/2022 14:07:55 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/05/2022 14:07:59 - INFO - codeparrot_training - Step 41394: {'lr': 0.00041756902652047767, 'samples': 21194240, 'steps': 41394, 'loss/train': 0.8488802313804626}
-03/05/2022 14:08:02 - INFO - codeparrot_training - Step 41395: {'lr': 0.0004175650882850622, 'samples': 21194752, 'steps': 41395, 'loss/train': 2.3593897819519043}
-03/05/2022 14:08:03 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/05/2022 14:08:07 - INFO - codeparrot_training - Step 41396: {'lr': 0.0004175611499741445, 'samples': 21195264, 'steps': 41396, 'loss/train': 1.9838229417800903}
-03/05/2022 14:08:11 - INFO - codeparrot_training - Step 41397: {'lr': 0.00041755721158772633, 'samples': 21195776, 'steps': 41397, 'loss/train': 1.662850260734558}
-03/05/2022 14:08:12 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/05/2022 14:08:16 - INFO - codeparrot_training - Step 41398: {'lr': 0.00041755327312580944, 'samples': 21196288, 'steps': 41398, 'loss/train': 2.2923905849456787}
-03/05/2022 14:08:19 - INFO - codeparrot_training - Step 41399: {'lr': 0.0004175493345883956, 'samples': 21196800, 'steps': 41399, 'loss/train': 1.8831506967544556}
-03/05/2022 14:08:20 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 14:08:24 - INFO - codeparrot_training - Step 41400: {'lr': 0.0004175453959754867, 'samples': 21197312, 'steps': 41400, 'loss/train': 2.2388203144073486}
-03/05/2022 14:08:27 - INFO - codeparrot_training - Step 41401: {'lr': 0.00041754145728708434, 'samples': 21197824, 'steps': 41401, 'loss/train': 1.5298492908477783}
-03/05/2022 14:08:29 - INFO - codeparrot_training - Skipping example with length 175 (seq_length=1024)
-03/05/2022 14:08:33 - INFO - codeparrot_training - Step 41402: {'lr': 0.0004175375185231904, 'samples': 21198336, 'steps': 41402, 'loss/train': 1.3990254402160645}
-03/05/2022 14:08:36 - INFO - codeparrot_training - Step 41403: {'lr': 0.00041753357968380675, 'samples': 21198848, 'steps': 41403, 'loss/train': 0.2592299282550812}
-03/05/2022 14:08:37 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/05/2022 14:08:41 - INFO - codeparrot_training - Step 41404: {'lr': 0.00041752964076893496, 'samples': 21199360, 'steps': 41404, 'loss/train': 1.2508511543273926}
-03/05/2022 14:08:44 - INFO - codeparrot_training - Step 41405: {'lr': 0.00041752570177857695, 'samples': 21199872, 'steps': 41405, 'loss/train': 1.6720975637435913}
-03/05/2022 14:08:45 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/05/2022 14:08:50 - INFO - codeparrot_training - Step 41406: {'lr': 0.0004175217627127344, 'samples': 21200384, 'steps': 41406, 'loss/train': 1.7520833015441895}
-03/05/2022 14:08:53 - INFO - codeparrot_training - Step 41407: {'lr': 0.0004175178235714091, 'samples': 21200896, 'steps': 41407, 'loss/train': 1.8849515914916992}
-03/05/2022 14:08:54 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/05/2022 14:08:58 - INFO - codeparrot_training - Step 41408: {'lr': 0.0004175138843546029, 'samples': 21201408, 'steps': 41408, 'loss/train': 1.5459226369857788}
-03/05/2022 14:09:01 - INFO - codeparrot_training - Step 41409: {'lr': 0.00041750994506231756, 'samples': 21201920, 'steps': 41409, 'loss/train': 1.860771656036377}
-03/05/2022 14:09:02 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/05/2022 14:09:06 - INFO - codeparrot_training - Step 41410: {'lr': 0.00041750600569455474, 'samples': 21202432, 'steps': 41410, 'loss/train': 1.562726616859436}
-03/05/2022 14:09:10 - INFO - codeparrot_training - Step 41411: {'lr': 0.0004175020662513164, 'samples': 21202944, 'steps': 41411, 'loss/train': 0.881607711315155}
-03/05/2022 14:09:10 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 14:09:15 - INFO - codeparrot_training - Step 41412: {'lr': 0.0004174981267326041, 'samples': 21203456, 'steps': 41412, 'loss/train': 2.0347695350646973}
-03/05/2022 14:09:18 - INFO - codeparrot_training - Step 41413: {'lr': 0.0004174941871384198, 'samples': 21203968, 'steps': 41413, 'loss/train': 0.8473787307739258}
-03/05/2022 14:09:19 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 14:09:23 - INFO - codeparrot_training - Step 41414: {'lr': 0.00041749024746876517, 'samples': 21204480, 'steps': 41414, 'loss/train': 1.2882137298583984}
-03/05/2022 14:09:26 - INFO - codeparrot_training - Step 41415: {'lr': 0.00041748630772364204, 'samples': 21204992, 'steps': 41415, 'loss/train': 2.007486581802368}
-03/05/2022 14:09:27 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 14:09:32 - INFO - codeparrot_training - Step 41416: {'lr': 0.00041748236790305215, 'samples': 21205504, 'steps': 41416, 'loss/train': 2.064770221710205}
-03/05/2022 14:09:35 - INFO - codeparrot_training - Step 41417: {'lr': 0.0004174784280069973, 'samples': 21206016, 'steps': 41417, 'loss/train': 2.051490545272827}
-03/05/2022 14:09:36 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/05/2022 14:09:40 - INFO - codeparrot_training - Step 41418: {'lr': 0.00041747448803547925, 'samples': 21206528, 'steps': 41418, 'loss/train': 2.0988495349884033}
-03/05/2022 14:09:43 - INFO - codeparrot_training - Step 41419: {'lr': 0.0004174705479884998, 'samples': 21207040, 'steps': 41419, 'loss/train': 1.997206211090088}
-03/05/2022 14:09:44 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/05/2022 14:09:49 - INFO - codeparrot_training - Step 41420: {'lr': 0.0004174666078660607, 'samples': 21207552, 'steps': 41420, 'loss/train': 1.4939026832580566}
-03/05/2022 14:09:52 - INFO - codeparrot_training - Step 41421: {'lr': 0.00041746266766816377, 'samples': 21208064, 'steps': 41421, 'loss/train': 1.4540772438049316}
-03/05/2022 14:09:53 - INFO - codeparrot_training - Skipping example with length 579 (seq_length=1024)
-03/05/2022 14:09:57 - INFO - codeparrot_training - Step 41422: {'lr': 0.0004174587273948106, 'samples': 21208576, 'steps': 41422, 'loss/train': 2.216372013092041}
-03/05/2022 14:10:00 - INFO - codeparrot_training - Step 41423: {'lr': 0.0004174547870460033, 'samples': 21209088, 'steps': 41423, 'loss/train': 1.4860442876815796}
-03/05/2022 14:10:01 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 14:10:06 - INFO - codeparrot_training - Step 41424: {'lr': 0.0004174508466217434, 'samples': 21209600, 'steps': 41424, 'loss/train': 1.4776396751403809}
-03/05/2022 14:10:09 - INFO - codeparrot_training - Step 41425: {'lr': 0.00041744690612203263, 'samples': 21210112, 'steps': 41425, 'loss/train': 1.2215474843978882}
-03/05/2022 14:10:10 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/05/2022 14:10:14 - INFO - codeparrot_training - Step 41426: {'lr': 0.00041744296554687294, 'samples': 21210624, 'steps': 41426, 'loss/train': 1.6561205387115479}
-03/05/2022 14:10:17 - INFO - codeparrot_training - Step 41427: {'lr': 0.00041743902489626606, 'samples': 21211136, 'steps': 41427, 'loss/train': 2.2217650413513184}
-03/05/2022 14:10:18 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/05/2022 14:10:22 - INFO - codeparrot_training - Step 41428: {'lr': 0.0004174350841702137, 'samples': 21211648, 'steps': 41428, 'loss/train': 1.8328044414520264}
-03/05/2022 14:10:26 - INFO - codeparrot_training - Step 41429: {'lr': 0.0004174311433687177, 'samples': 21212160, 'steps': 41429, 'loss/train': 1.4709471464157104}
-03/05/2022 14:10:27 - INFO - codeparrot_training - Skipping example with length 690 (seq_length=1024)
-03/05/2022 14:10:31 - INFO - codeparrot_training - Step 41430: {'lr': 0.00041742720249177975, 'samples': 21212672, 'steps': 41430, 'loss/train': 1.2375367879867554}
-03/05/2022 14:10:34 - INFO - codeparrot_training - Step 41431: {'lr': 0.0004174232615394018, 'samples': 21213184, 'steps': 41431, 'loss/train': 1.8222976922988892}
-03/05/2022 14:10:36 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/05/2022 14:10:39 - INFO - codeparrot_training - Step 41432: {'lr': 0.00041741932051158535, 'samples': 21213696, 'steps': 41432, 'loss/train': 2.8174750804901123}
-03/05/2022 14:10:43 - INFO - codeparrot_training - Step 41433: {'lr': 0.00041741537940833247, 'samples': 21214208, 'steps': 41433, 'loss/train': 1.983985424041748}
-03/05/2022 14:10:44 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/05/2022 14:10:48 - INFO - codeparrot_training - Step 41434: {'lr': 0.00041741143822964476, 'samples': 21214720, 'steps': 41434, 'loss/train': 1.2514272928237915}
-03/05/2022 14:10:51 - INFO - codeparrot_training - Step 41435: {'lr': 0.00041740749697552406, 'samples': 21215232, 'steps': 41435, 'loss/train': 1.0364766120910645}
-03/05/2022 14:10:53 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/05/2022 14:10:56 - INFO - codeparrot_training - Step 41436: {'lr': 0.0004174035556459721, 'samples': 21215744, 'steps': 41436, 'loss/train': 1.741824984550476}
-03/05/2022 14:10:59 - INFO - codeparrot_training - Step 41437: {'lr': 0.0004173996142409907, 'samples': 21216256, 'steps': 41437, 'loss/train': 2.483654737472534}
-03/05/2022 14:11:01 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 14:11:05 - INFO - codeparrot_training - Step 41438: {'lr': 0.0004173956727605816, 'samples': 21216768, 'steps': 41438, 'loss/train': 2.31372332572937}
-03/05/2022 14:11:08 - INFO - codeparrot_training - Step 41439: {'lr': 0.00041739173120474663, 'samples': 21217280, 'steps': 41439, 'loss/train': 1.8581352233886719}
-03/05/2022 14:11:09 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 14:11:13 - INFO - codeparrot_training - Step 41440: {'lr': 0.00041738778957348745, 'samples': 21217792, 'steps': 41440, 'loss/train': 2.4800143241882324}
-03/05/2022 14:11:16 - INFO - codeparrot_training - Step 41441: {'lr': 0.00041738384786680596, 'samples': 21218304, 'steps': 41441, 'loss/train': 1.3973382711410522}
-03/05/2022 14:11:18 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/05/2022 14:11:22 - INFO - codeparrot_training - Step 41442: {'lr': 0.0004173799060847039, 'samples': 21218816, 'steps': 41442, 'loss/train': 2.2493553161621094}
-03/05/2022 14:11:25 - INFO - codeparrot_training - Step 41443: {'lr': 0.00041737596422718306, 'samples': 21219328, 'steps': 41443, 'loss/train': 2.1427581310272217}
-03/05/2022 14:11:26 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/05/2022 14:11:30 - INFO - codeparrot_training - Step 41444: {'lr': 0.0004173720222942452, 'samples': 21219840, 'steps': 41444, 'loss/train': 1.7052302360534668}
-03/05/2022 14:11:33 - INFO - codeparrot_training - Step 41445: {'lr': 0.000417368080285892, 'samples': 21220352, 'steps': 41445, 'loss/train': 1.7942179441452026}
-03/05/2022 14:11:34 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/05/2022 14:11:38 - INFO - codeparrot_training - Step 41446: {'lr': 0.0004173641382021254, 'samples': 21220864, 'steps': 41446, 'loss/train': 2.3863537311553955}
-03/05/2022 14:11:42 - INFO - codeparrot_training - Step 41447: {'lr': 0.00041736019604294704, 'samples': 21221376, 'steps': 41447, 'loss/train': 1.6136682033538818}
-03/05/2022 14:11:42 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/05/2022 14:11:47 - INFO - codeparrot_training - Step 41448: {'lr': 0.00041735625380835884, 'samples': 21221888, 'steps': 41448, 'loss/train': 1.6372950077056885}
-03/05/2022 14:11:50 - INFO - codeparrot_training - Step 41449: {'lr': 0.0004173523114983624, 'samples': 21222400, 'steps': 41449, 'loss/train': 1.6027343273162842}
-03/05/2022 14:11:50 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/05/2022 14:11:56 - INFO - codeparrot_training - Step 41450: {'lr': 0.0004173483691129597, 'samples': 21222912, 'steps': 41450, 'loss/train': 1.9475584030151367}
-03/05/2022 14:11:59 - INFO - codeparrot_training - Step 41451: {'lr': 0.00041734442665215235, 'samples': 21223424, 'steps': 41451, 'loss/train': 1.8609545230865479}
-03/05/2022 14:11:59 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/05/2022 14:12:04 - INFO - codeparrot_training - Step 41452: {'lr': 0.00041734048411594214, 'samples': 21223936, 'steps': 41452, 'loss/train': 2.0061404705047607}
-03/05/2022 14:12:07 - INFO - codeparrot_training - Step 41453: {'lr': 0.000417336541504331, 'samples': 21224448, 'steps': 41453, 'loss/train': 1.617042064666748}
-03/05/2022 14:12:08 - INFO - codeparrot_training - Skipping example with length 361 (seq_length=1024)
-03/05/2022 14:12:12 - INFO - codeparrot_training - Step 41454: {'lr': 0.0004173325988173205, 'samples': 21224960, 'steps': 41454, 'loss/train': 1.690610408782959}
-03/05/2022 14:12:16 - INFO - codeparrot_training - Step 41455: {'lr': 0.00041732865605491256, 'samples': 21225472, 'steps': 41455, 'loss/train': 1.5892915725708008}
-03/05/2022 14:12:16 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/05/2022 14:12:21 - INFO - codeparrot_training - Step 41456: {'lr': 0.00041732471321710886, 'samples': 21225984, 'steps': 41456, 'loss/train': 1.6462794542312622}
-03/05/2022 14:12:24 - INFO - codeparrot_training - Step 41457: {'lr': 0.00041732077030391126, 'samples': 21226496, 'steps': 41457, 'loss/train': 2.1530699729919434}
-03/05/2022 14:12:24 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 14:12:30 - INFO - codeparrot_training - Step 41458: {'lr': 0.00041731682731532154, 'samples': 21227008, 'steps': 41458, 'loss/train': 2.12203049659729}
-03/05/2022 14:12:33 - INFO - codeparrot_training - Step 41459: {'lr': 0.0004173128842513414, 'samples': 21227520, 'steps': 41459, 'loss/train': 1.9235591888427734}
-03/05/2022 14:12:34 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/05/2022 14:12:38 - INFO - codeparrot_training - Step 41460: {'lr': 0.00041730894111197266, 'samples': 21228032, 'steps': 41460, 'loss/train': 2.042478084564209}
-03/05/2022 14:12:41 - INFO - codeparrot_training - Step 41461: {'lr': 0.0004173049978972171, 'samples': 21228544, 'steps': 41461, 'loss/train': 1.2865082025527954}
-03/05/2022 14:12:43 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/05/2022 14:12:47 - INFO - codeparrot_training - Step 41462: {'lr': 0.0004173010546070765, 'samples': 21229056, 'steps': 41462, 'loss/train': 2.117494821548462}
-03/05/2022 14:12:50 - INFO - codeparrot_training - Step 41463: {'lr': 0.00041729711124155255, 'samples': 21229568, 'steps': 41463, 'loss/train': 2.097677707672119}
-03/05/2022 14:12:51 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 14:12:55 - INFO - codeparrot_training - Step 41464: {'lr': 0.0004172931678006472, 'samples': 21230080, 'steps': 41464, 'loss/train': 2.2862021923065186}
-03/05/2022 14:12:58 - INFO - codeparrot_training - Step 41465: {'lr': 0.00041728922428436213, 'samples': 21230592, 'steps': 41465, 'loss/train': 2.2636687755584717}
-03/05/2022 14:12:59 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/05/2022 14:13:04 - INFO - codeparrot_training - Step 41466: {'lr': 0.000417285280692699, 'samples': 21231104, 'steps': 41466, 'loss/train': 1.748808741569519}
-03/05/2022 14:13:07 - INFO - codeparrot_training - Step 41467: {'lr': 0.00041728133702565985, 'samples': 21231616, 'steps': 41467, 'loss/train': 0.8206184506416321}
-03/05/2022 14:13:08 - INFO - codeparrot_training - Skipping example with length 812 (seq_length=1024)
-03/05/2022 14:13:12 - INFO - codeparrot_training - Step 41468: {'lr': 0.0004172773932832462, 'samples': 21232128, 'steps': 41468, 'loss/train': 0.5391926169395447}
-03/05/2022 14:13:15 - INFO - codeparrot_training - Step 41469: {'lr': 0.00041727344946546, 'samples': 21232640, 'steps': 41469, 'loss/train': 1.8263237476348877}
-03/05/2022 14:13:16 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/05/2022 14:13:21 - INFO - codeparrot_training - Step 41470: {'lr': 0.00041726950557230294, 'samples': 21233152, 'steps': 41470, 'loss/train': 2.835204601287842}
-03/05/2022 14:13:24 - INFO - codeparrot_training - Step 41471: {'lr': 0.0004172655616037768, 'samples': 21233664, 'steps': 41471, 'loss/train': 1.359943151473999}
-03/05/2022 14:13:25 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/05/2022 14:13:29 - INFO - codeparrot_training - Step 41472: {'lr': 0.0004172616175598835, 'samples': 21234176, 'steps': 41472, 'loss/train': 1.47471284866333}
-03/05/2022 14:13:32 - INFO - codeparrot_training - Step 41473: {'lr': 0.00041725767344062453, 'samples': 21234688, 'steps': 41473, 'loss/train': 1.8852826356887817}
-03/05/2022 14:13:34 - INFO - codeparrot_training - Skipping example with length 843 (seq_length=1024)
-03/05/2022 14:13:38 - INFO - codeparrot_training - Step 41474: {'lr': 0.00041725372924600193, 'samples': 21235200, 'steps': 41474, 'loss/train': 2.075472831726074}
-03/05/2022 14:13:41 - INFO - codeparrot_training - Step 41475: {'lr': 0.00041724978497601736, 'samples': 21235712, 'steps': 41475, 'loss/train': 2.257991075515747}
-03/05/2022 14:13:42 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/05/2022 14:13:46 - INFO - codeparrot_training - Step 41476: {'lr': 0.0004172458406306726, 'samples': 21236224, 'steps': 41476, 'loss/train': 1.9495385885238647}
-03/05/2022 14:13:49 - INFO - codeparrot_training - Step 41477: {'lr': 0.00041724189620996946, 'samples': 21236736, 'steps': 41477, 'loss/train': 2.5579681396484375}
-03/05/2022 14:13:51 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 14:13:55 - INFO - codeparrot_training - Step 41478: {'lr': 0.0004172379517139097, 'samples': 21237248, 'steps': 41478, 'loss/train': 1.9899598360061646}
-03/05/2022 14:13:58 - INFO - codeparrot_training - Step 41479: {'lr': 0.0004172340071424951, 'samples': 21237760, 'steps': 41479, 'loss/train': 1.9186172485351562}
-03/05/2022 14:13:59 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/05/2022 14:14:03 - INFO - codeparrot_training - Step 41480: {'lr': 0.00041723006249572744, 'samples': 21238272, 'steps': 41480, 'loss/train': 1.64205801486969}
-03/05/2022 14:14:06 - INFO - codeparrot_training - Step 41481: {'lr': 0.00041722611777360844, 'samples': 21238784, 'steps': 41481, 'loss/train': 1.2513768672943115}
-03/05/2022 14:14:07 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/05/2022 14:14:12 - INFO - codeparrot_training - Step 41482: {'lr': 0.00041722217297614, 'samples': 21239296, 'steps': 41482, 'loss/train': 1.1852688789367676}
-03/05/2022 14:14:15 - INFO - codeparrot_training - Step 41483: {'lr': 0.00041721822810332384, 'samples': 21239808, 'steps': 41483, 'loss/train': 1.959395170211792}
-03/05/2022 14:14:16 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/05/2022 14:14:20 - INFO - codeparrot_training - Step 41484: {'lr': 0.00041721428315516176, 'samples': 21240320, 'steps': 41484, 'loss/train': 1.6928373575210571}
-03/05/2022 14:14:23 - INFO - codeparrot_training - Step 41485: {'lr': 0.00041721033813165543, 'samples': 21240832, 'steps': 41485, 'loss/train': 1.9689911603927612}
-03/05/2022 14:14:26 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/05/2022 14:14:29 - INFO - codeparrot_training - Step 41486: {'lr': 0.0004172063930328067, 'samples': 21241344, 'steps': 41486, 'loss/train': 1.5693457126617432}
-03/05/2022 14:14:32 - INFO - codeparrot_training - Step 41487: {'lr': 0.00041720244785861736, 'samples': 21241856, 'steps': 41487, 'loss/train': 1.6972384452819824}
-03/05/2022 14:14:34 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 14:14:37 - INFO - codeparrot_training - Step 41488: {'lr': 0.0004171985026090892, 'samples': 21242368, 'steps': 41488, 'loss/train': 0.12188681960105896}
-03/05/2022 14:14:41 - INFO - codeparrot_training - Step 41489: {'lr': 0.00041719455728422394, 'samples': 21242880, 'steps': 41489, 'loss/train': 2.8541159629821777}
-03/05/2022 14:14:44 - INFO - codeparrot_training - Step 41490: {'lr': 0.0004171906118840234, 'samples': 21243392, 'steps': 41490, 'loss/train': 2.2380781173706055}
-03/05/2022 14:14:44 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/05/2022 14:14:49 - INFO - codeparrot_training - Step 41491: {'lr': 0.00041718666640848937, 'samples': 21243904, 'steps': 41491, 'loss/train': 2.174309253692627}
-03/05/2022 14:14:52 - INFO - codeparrot_training - Step 41492: {'lr': 0.0004171827208576236, 'samples': 21244416, 'steps': 41492, 'loss/train': 1.4239755868911743}
-03/05/2022 14:14:53 - INFO - codeparrot_training - Skipping example with length 720 (seq_length=1024)
-03/05/2022 14:14:58 - INFO - codeparrot_training - Step 41493: {'lr': 0.00041717877523142786, 'samples': 21244928, 'steps': 41493, 'loss/train': 1.8029905557632446}
-03/05/2022 14:15:01 - INFO - codeparrot_training - Step 41494: {'lr': 0.00041717482952990394, 'samples': 21245440, 'steps': 41494, 'loss/train': 0.7462776899337769}
-03/05/2022 14:15:02 - INFO - codeparrot_training - Skipping example with length 559 (seq_length=1024)
-03/05/2022 14:15:06 - INFO - codeparrot_training - Step 41495: {'lr': 0.00041717088375305367, 'samples': 21245952, 'steps': 41495, 'loss/train': 1.3760778903961182}
-03/05/2022 14:15:09 - INFO - codeparrot_training - Step 41496: {'lr': 0.0004171669379008787, 'samples': 21246464, 'steps': 41496, 'loss/train': 1.112423062324524}
-03/05/2022 14:15:10 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/05/2022 14:15:14 - INFO - codeparrot_training - Step 41497: {'lr': 0.00041716299197338093, 'samples': 21246976, 'steps': 41497, 'loss/train': 2.2601466178894043}
-03/05/2022 14:15:18 - INFO - codeparrot_training - Step 41498: {'lr': 0.0004171590459705622, 'samples': 21247488, 'steps': 41498, 'loss/train': 1.7729830741882324}
-03/05/2022 14:15:18 - INFO - codeparrot_training - Skipping example with length 89 (seq_length=1024)
-03/05/2022 14:15:23 - INFO - codeparrot_training - Step 41499: {'lr': 0.0004171550998924241, 'samples': 21248000, 'steps': 41499, 'loss/train': 1.9727226495742798}
-03/05/2022 14:15:26 - INFO - codeparrot_training - Step 41500: {'lr': 0.0004171511537389684, 'samples': 21248512, 'steps': 41500, 'loss/train': 1.2623207569122314}
-03/05/2022 14:15:27 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/05/2022 14:15:31 - INFO - codeparrot_training - Step 41501: {'lr': 0.0004171472075101971, 'samples': 21249024, 'steps': 41501, 'loss/train': 2.5038204193115234}
-03/05/2022 14:15:35 - INFO - codeparrot_training - Step 41502: {'lr': 0.0004171432612061117, 'samples': 21249536, 'steps': 41502, 'loss/train': 2.6890692710876465}
-03/05/2022 14:15:35 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 14:15:40 - INFO - codeparrot_training - Step 41503: {'lr': 0.00041713931482671425, 'samples': 21250048, 'steps': 41503, 'loss/train': 2.242145299911499}
-03/05/2022 14:15:43 - INFO - codeparrot_training - Step 41504: {'lr': 0.0004171353683720064, 'samples': 21250560, 'steps': 41504, 'loss/train': 1.1304399967193604}
-03/05/2022 14:15:44 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/05/2022 14:15:48 - INFO - codeparrot_training - Step 41505: {'lr': 0.00041713142184198994, 'samples': 21251072, 'steps': 41505, 'loss/train': 0.5512522459030151}
-03/05/2022 14:15:51 - INFO - codeparrot_training - Step 41506: {'lr': 0.0004171274752366665, 'samples': 21251584, 'steps': 41506, 'loss/train': 1.8599876165390015}
-03/05/2022 14:15:52 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/05/2022 14:15:57 - INFO - codeparrot_training - Step 41507: {'lr': 0.00041712352855603817, 'samples': 21252096, 'steps': 41507, 'loss/train': 2.174855947494507}
-03/05/2022 14:16:00 - INFO - codeparrot_training - Step 41508: {'lr': 0.00041711958180010644, 'samples': 21252608, 'steps': 41508, 'loss/train': 1.5455989837646484}
-03/05/2022 14:16:00 - INFO - codeparrot_training - Skipping example with length 580 (seq_length=1024)
-03/05/2022 14:16:05 - INFO - codeparrot_training - Step 41509: {'lr': 0.0004171156349688733, 'samples': 21253120, 'steps': 41509, 'loss/train': 2.3497087955474854}
-03/05/2022 14:16:08 - INFO - codeparrot_training - Step 41510: {'lr': 0.0004171116880623404, 'samples': 21253632, 'steps': 41510, 'loss/train': 1.3743873834609985}
-03/05/2022 14:16:09 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/05/2022 14:16:14 - INFO - codeparrot_training - Step 41511: {'lr': 0.0004171077410805095, 'samples': 21254144, 'steps': 41511, 'loss/train': 1.4136096239089966}
-03/05/2022 14:16:17 - INFO - codeparrot_training - Step 41512: {'lr': 0.0004171037940233825, 'samples': 21254656, 'steps': 41512, 'loss/train': 1.9292138814926147}
-03/05/2022 14:16:18 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/05/2022 14:16:22 - INFO - codeparrot_training - Step 41513: {'lr': 0.0004170998468909611, 'samples': 21255168, 'steps': 41513, 'loss/train': 0.7834359407424927}
-03/05/2022 14:16:25 - INFO - codeparrot_training - Step 41514: {'lr': 0.00041709589968324704, 'samples': 21255680, 'steps': 41514, 'loss/train': 1.5129069089889526}
-03/05/2022 14:16:27 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/05/2022 14:16:31 - INFO - codeparrot_training - Step 41515: {'lr': 0.00041709195240024224, 'samples': 21256192, 'steps': 41515, 'loss/train': 1.92372465133667}
-03/05/2022 14:16:34 - INFO - codeparrot_training - Step 41516: {'lr': 0.0004170880050419483, 'samples': 21256704, 'steps': 41516, 'loss/train': 1.8885161876678467}
-03/05/2022 14:16:35 - INFO - codeparrot_training - Skipping example with length 86 (seq_length=1024)
-03/05/2022 14:16:39 - INFO - codeparrot_training - Step 41517: {'lr': 0.0004170840576083671, 'samples': 21257216, 'steps': 41517, 'loss/train': 2.114734172821045}
-03/05/2022 14:16:42 - INFO - codeparrot_training - Step 41518: {'lr': 0.00041708011009950044, 'samples': 21257728, 'steps': 41518, 'loss/train': 1.8671823740005493}
-03/05/2022 14:16:44 - INFO - codeparrot_training - Skipping example with length 625 (seq_length=1024)
-03/05/2022 14:16:48 - INFO - codeparrot_training - Step 41519: {'lr': 0.00041707616251535, 'samples': 21258240, 'steps': 41519, 'loss/train': 1.6012461185455322}
-03/05/2022 14:16:51 - INFO - codeparrot_training - Step 41520: {'lr': 0.0004170722148559176, 'samples': 21258752, 'steps': 41520, 'loss/train': 1.7984524965286255}
-03/05/2022 14:16:52 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/05/2022 14:16:56 - INFO - codeparrot_training - Step 41521: {'lr': 0.0004170682671212051, 'samples': 21259264, 'steps': 41521, 'loss/train': 1.2455508708953857}
-03/05/2022 14:16:59 - INFO - codeparrot_training - Step 41522: {'lr': 0.00041706431931121416, 'samples': 21259776, 'steps': 41522, 'loss/train': 1.3203041553497314}
-03/05/2022 14:17:01 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 14:17:05 - INFO - codeparrot_training - Step 41523: {'lr': 0.00041706037142594666, 'samples': 21260288, 'steps': 41523, 'loss/train': 1.9387435913085938}
-03/05/2022 14:17:08 - INFO - codeparrot_training - Step 41524: {'lr': 0.00041705642346540436, 'samples': 21260800, 'steps': 41524, 'loss/train': 2.2522120475769043}
-03/05/2022 14:17:09 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 14:17:13 - INFO - codeparrot_training - Step 41525: {'lr': 0.00041705247542958904, 'samples': 21261312, 'steps': 41525, 'loss/train': 0.49707064032554626}
-03/05/2022 14:17:16 - INFO - codeparrot_training - Step 41526: {'lr': 0.00041704852731850234, 'samples': 21261824, 'steps': 41526, 'loss/train': 2.1818668842315674}
-03/05/2022 14:17:18 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/05/2022 14:17:21 - INFO - codeparrot_training - Step 41527: {'lr': 0.0004170445791321462, 'samples': 21262336, 'steps': 41527, 'loss/train': 1.3830277919769287}
-03/05/2022 14:17:25 - INFO - codeparrot_training - Step 41528: {'lr': 0.00041704063087052236, 'samples': 21262848, 'steps': 41528, 'loss/train': 1.6878575086593628}
-03/05/2022 14:17:26 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/05/2022 14:17:30 - INFO - codeparrot_training - Step 41529: {'lr': 0.0004170366825336326, 'samples': 21263360, 'steps': 41529, 'loss/train': 2.3182194232940674}
-03/05/2022 14:17:33 - INFO - codeparrot_training - Step 41530: {'lr': 0.0004170327341214787, 'samples': 21263872, 'steps': 41530, 'loss/train': 1.2810611724853516}
-03/05/2022 14:17:35 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/05/2022 14:17:38 - INFO - codeparrot_training - Step 41531: {'lr': 0.00041702878563406237, 'samples': 21264384, 'steps': 41531, 'loss/train': 1.500373125076294}
-03/05/2022 14:17:41 - INFO - codeparrot_training - Step 41532: {'lr': 0.0004170248370713855, 'samples': 21264896, 'steps': 41532, 'loss/train': 1.6757190227508545}
-03/05/2022 14:17:43 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/05/2022 14:17:47 - INFO - codeparrot_training - Step 41533: {'lr': 0.0004170208884334498, 'samples': 21265408, 'steps': 41533, 'loss/train': 1.5885404348373413}
-03/05/2022 14:17:50 - INFO - codeparrot_training - Step 41534: {'lr': 0.000417016939720257, 'samples': 21265920, 'steps': 41534, 'loss/train': 1.7236154079437256}
-03/05/2022 14:17:52 - INFO - codeparrot_training - Skipping example with length 877 (seq_length=1024)
-03/05/2022 14:17:55 - INFO - codeparrot_training - Step 41535: {'lr': 0.000417012990931809, 'samples': 21266432, 'steps': 41535, 'loss/train': 1.4442216157913208}
-03/05/2022 14:17:58 - INFO - codeparrot_training - Step 41536: {'lr': 0.00041700904206810755, 'samples': 21266944, 'steps': 41536, 'loss/train': 1.9169870615005493}
-03/05/2022 14:18:00 - INFO - codeparrot_training - Skipping example with length 915 (seq_length=1024)
-03/05/2022 14:18:04 - INFO - codeparrot_training - Step 41537: {'lr': 0.00041700509312915437, 'samples': 21267456, 'steps': 41537, 'loss/train': 1.1122479438781738}
-03/05/2022 14:18:07 - INFO - codeparrot_training - Step 41538: {'lr': 0.0004170011441149513, 'samples': 21267968, 'steps': 41538, 'loss/train': 1.8567417860031128}
-03/05/2022 14:18:08 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/05/2022 14:18:12 - INFO - codeparrot_training - Step 41539: {'lr': 0.0004169971950255001, 'samples': 21268480, 'steps': 41539, 'loss/train': 1.155175805091858}
-03/05/2022 14:18:15 - INFO - codeparrot_training - Step 41540: {'lr': 0.0004169932458608025, 'samples': 21268992, 'steps': 41540, 'loss/train': 1.2085416316986084}
-03/05/2022 14:18:17 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/05/2022 14:18:20 - INFO - codeparrot_training - Step 41541: {'lr': 0.00041698929662086035, 'samples': 21269504, 'steps': 41541, 'loss/train': 2.4421205520629883}
-03/05/2022 14:18:24 - INFO - codeparrot_training - Step 41542: {'lr': 0.0004169853473056754, 'samples': 21270016, 'steps': 41542, 'loss/train': 2.1432294845581055}
-03/05/2022 14:18:25 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/05/2022 14:18:29 - INFO - codeparrot_training - Step 41543: {'lr': 0.0004169813979152494, 'samples': 21270528, 'steps': 41543, 'loss/train': 1.0895339250564575}
-03/05/2022 14:18:32 - INFO - codeparrot_training - Step 41544: {'lr': 0.0004169774484495841, 'samples': 21271040, 'steps': 41544, 'loss/train': 1.9807188510894775}
-03/05/2022 14:18:33 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/05/2022 14:18:38 - INFO - codeparrot_training - Step 41545: {'lr': 0.00041697349890868146, 'samples': 21271552, 'steps': 41545, 'loss/train': 2.4010090827941895}
-03/05/2022 14:18:41 - INFO - codeparrot_training - Step 41546: {'lr': 0.0004169695492925431, 'samples': 21272064, 'steps': 41546, 'loss/train': 1.3027721643447876}
-03/05/2022 14:18:42 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/05/2022 14:18:46 - INFO - codeparrot_training - Step 41547: {'lr': 0.0004169655996011708, 'samples': 21272576, 'steps': 41547, 'loss/train': 1.824916124343872}
-03/05/2022 14:18:49 - INFO - codeparrot_training - Step 41548: {'lr': 0.0004169616498345664, 'samples': 21273088, 'steps': 41548, 'loss/train': 1.6445611715316772}
-03/05/2022 14:18:50 - INFO - codeparrot_training - Skipping example with length 462 (seq_length=1024)
-03/05/2022 14:18:54 - INFO - codeparrot_training - Step 41549: {'lr': 0.0004169576999927317, 'samples': 21273600, 'steps': 41549, 'loss/train': 1.4714884757995605}
-03/05/2022 14:18:58 - INFO - codeparrot_training - Step 41550: {'lr': 0.00041695375007566837, 'samples': 21274112, 'steps': 41550, 'loss/train': 2.3362843990325928}
-03/05/2022 14:18:59 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/05/2022 14:19:03 - INFO - codeparrot_training - Step 41551: {'lr': 0.00041694980008337825, 'samples': 21274624, 'steps': 41551, 'loss/train': 1.9699262380599976}
-03/05/2022 14:19:06 - INFO - codeparrot_training - Step 41552: {'lr': 0.0004169458500158632, 'samples': 21275136, 'steps': 41552, 'loss/train': 1.3705567121505737}
-03/05/2022 14:19:07 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/05/2022 14:19:11 - INFO - codeparrot_training - Step 41553: {'lr': 0.0004169418998731249, 'samples': 21275648, 'steps': 41553, 'loss/train': 1.479076623916626}
-03/05/2022 14:19:15 - INFO - codeparrot_training - Step 41554: {'lr': 0.00041693794965516514, 'samples': 21276160, 'steps': 41554, 'loss/train': 2.1832082271575928}
-03/05/2022 14:19:16 - INFO - codeparrot_training - Skipping example with length 481 (seq_length=1024)
-03/05/2022 14:19:20 - INFO - codeparrot_training - Step 41555: {'lr': 0.0004169339993619857, 'samples': 21276672, 'steps': 41555, 'loss/train': 1.6583421230316162}
-03/05/2022 14:19:23 - INFO - codeparrot_training - Step 41556: {'lr': 0.0004169300489935884, 'samples': 21277184, 'steps': 41556, 'loss/train': 1.3976430892944336}
-03/05/2022 14:19:24 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 14:19:28 - INFO - codeparrot_training - Step 41557: {'lr': 0.000416926098549975, 'samples': 21277696, 'steps': 41557, 'loss/train': 1.6029492616653442}
-03/05/2022 14:19:31 - INFO - codeparrot_training - Step 41558: {'lr': 0.00041692214803114725, 'samples': 21278208, 'steps': 41558, 'loss/train': 2.44087290763855}
-03/05/2022 14:19:32 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/05/2022 14:19:37 - INFO - codeparrot_training - Step 41559: {'lr': 0.00041691819743710704, 'samples': 21278720, 'steps': 41559, 'loss/train': 1.774378776550293}
-03/05/2022 14:19:40 - INFO - codeparrot_training - Step 41560: {'lr': 0.00041691424676785593, 'samples': 21279232, 'steps': 41560, 'loss/train': 1.5088415145874023}
-03/05/2022 14:19:41 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/05/2022 14:19:45 - INFO - codeparrot_training - Step 41561: {'lr': 0.00041691029602339595, 'samples': 21279744, 'steps': 41561, 'loss/train': 1.9280309677124023}
-03/05/2022 14:19:48 - INFO - codeparrot_training - Step 41562: {'lr': 0.00041690634520372865, 'samples': 21280256, 'steps': 41562, 'loss/train': 1.6401698589324951}
-03/05/2022 14:19:49 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/05/2022 14:19:53 - INFO - codeparrot_training - Step 41563: {'lr': 0.000416902394308856, 'samples': 21280768, 'steps': 41563, 'loss/train': 2.0186192989349365}
-03/05/2022 14:19:57 - INFO - codeparrot_training - Step 41564: {'lr': 0.00041689844333877966, 'samples': 21281280, 'steps': 41564, 'loss/train': 2.293422222137451}
-03/05/2022 14:19:58 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/05/2022 14:20:02 - INFO - codeparrot_training - Step 41565: {'lr': 0.00041689449229350155, 'samples': 21281792, 'steps': 41565, 'loss/train': 2.0175814628601074}
-03/05/2022 14:20:05 - INFO - codeparrot_training - Step 41566: {'lr': 0.00041689054117302333, 'samples': 21282304, 'steps': 41566, 'loss/train': 2.4216039180755615}
-03/05/2022 14:20:06 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/05/2022 14:20:10 - INFO - codeparrot_training - Step 41567: {'lr': 0.00041688658997734675, 'samples': 21282816, 'steps': 41567, 'loss/train': 1.745259404182434}
-03/05/2022 14:20:13 - INFO - codeparrot_training - Step 41568: {'lr': 0.0004168826387064737, 'samples': 21283328, 'steps': 41568, 'loss/train': 0.49325740337371826}
-03/05/2022 14:20:14 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/05/2022 14:20:19 - INFO - codeparrot_training - Step 41569: {'lr': 0.00041687868736040593, 'samples': 21283840, 'steps': 41569, 'loss/train': 1.3871482610702515}
-03/05/2022 14:20:22 - INFO - codeparrot_training - Step 41570: {'lr': 0.0004168747359391451, 'samples': 21284352, 'steps': 41570, 'loss/train': 1.9838333129882812}
-03/05/2022 14:20:23 - INFO - codeparrot_training - Skipping example with length 726 (seq_length=1024)
-03/05/2022 14:20:27 - INFO - codeparrot_training - Step 41571: {'lr': 0.00041687078444269316, 'samples': 21284864, 'steps': 41571, 'loss/train': 1.7342970371246338}
-03/05/2022 14:20:30 - INFO - codeparrot_training - Step 41572: {'lr': 0.0004168668328710518, 'samples': 21285376, 'steps': 41572, 'loss/train': 1.462916374206543}
-03/05/2022 14:20:31 - INFO - codeparrot_training - Skipping example with length 210 (seq_length=1024)
-03/05/2022 14:20:36 - INFO - codeparrot_training - Step 41573: {'lr': 0.0004168628812242228, 'samples': 21285888, 'steps': 41573, 'loss/train': 1.8578145503997803}
-03/05/2022 14:20:39 - INFO - codeparrot_training - Step 41574: {'lr': 0.00041685892950220804, 'samples': 21286400, 'steps': 41574, 'loss/train': 1.8084808588027954}
-03/05/2022 14:20:40 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 14:20:45 - INFO - codeparrot_training - Step 41575: {'lr': 0.0004168549777050091, 'samples': 21286912, 'steps': 41575, 'loss/train': 1.7415516376495361}
-03/05/2022 14:20:48 - INFO - codeparrot_training - Step 41576: {'lr': 0.000416851025832628, 'samples': 21287424, 'steps': 41576, 'loss/train': 1.44538414478302}
-03/05/2022 14:20:50 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/05/2022 14:20:53 - INFO - codeparrot_training - Step 41577: {'lr': 0.0004168470738850664, 'samples': 21287936, 'steps': 41577, 'loss/train': 1.8306907415390015}
-03/05/2022 14:20:56 - INFO - codeparrot_training - Step 41578: {'lr': 0.00041684312186232597, 'samples': 21288448, 'steps': 41578, 'loss/train': 1.0058157444000244}
-03/05/2022 14:20:58 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 14:21:01 - INFO - codeparrot_training - Step 41579: {'lr': 0.0004168391697644087, 'samples': 21288960, 'steps': 41579, 'loss/train': 1.6646203994750977}
-03/05/2022 14:21:05 - INFO - codeparrot_training - Step 41580: {'lr': 0.0004168352175913163, 'samples': 21289472, 'steps': 41580, 'loss/train': 2.1760144233703613}
-03/05/2022 14:21:06 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/05/2022 14:21:10 - INFO - codeparrot_training - Step 41581: {'lr': 0.00041683126534305037, 'samples': 21289984, 'steps': 41581, 'loss/train': 1.388043761253357}
-03/05/2022 14:21:13 - INFO - codeparrot_training - Step 41582: {'lr': 0.000416827313019613, 'samples': 21290496, 'steps': 41582, 'loss/train': 1.959945797920227}
-03/05/2022 14:21:15 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/05/2022 14:21:18 - INFO - codeparrot_training - Step 41583: {'lr': 0.0004168233606210058, 'samples': 21291008, 'steps': 41583, 'loss/train': 1.571984052658081}
-03/05/2022 14:21:22 - INFO - codeparrot_training - Step 41584: {'lr': 0.0004168194081472305, 'samples': 21291520, 'steps': 41584, 'loss/train': 2.443671226501465}
-03/05/2022 14:21:23 - INFO - codeparrot_training - Skipping example with length 289 (seq_length=1024)
-03/05/2022 14:21:27 - INFO - codeparrot_training - Step 41585: {'lr': 0.000416815455598289, 'samples': 21292032, 'steps': 41585, 'loss/train': 2.1880016326904297}
-03/05/2022 14:21:30 - INFO - codeparrot_training - Step 41586: {'lr': 0.000416811502974183, 'samples': 21292544, 'steps': 41586, 'loss/train': 1.8529448509216309}
-03/05/2022 14:21:31 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/05/2022 14:21:35 - INFO - codeparrot_training - Step 41587: {'lr': 0.00041680755027491433, 'samples': 21293056, 'steps': 41587, 'loss/train': 2.167682409286499}
-03/05/2022 14:21:38 - INFO - codeparrot_training - Step 41588: {'lr': 0.0004168035975004847, 'samples': 21293568, 'steps': 41588, 'loss/train': 1.6651618480682373}
-03/05/2022 14:21:40 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/05/2022 14:21:44 - INFO - codeparrot_training - Step 41589: {'lr': 0.00041679964465089596, 'samples': 21294080, 'steps': 41589, 'loss/train': 5.998101234436035}
-03/05/2022 14:21:47 - INFO - codeparrot_training - Step 41590: {'lr': 0.00041679569172614996, 'samples': 21294592, 'steps': 41590, 'loss/train': 0.9901602268218994}
-03/05/2022 14:21:49 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/05/2022 14:21:52 - INFO - codeparrot_training - Step 41591: {'lr': 0.0004167917387262483, 'samples': 21295104, 'steps': 41591, 'loss/train': 1.5477582216262817}
-03/05/2022 14:21:55 - INFO - codeparrot_training - Step 41592: {'lr': 0.0004167877856511929, 'samples': 21295616, 'steps': 41592, 'loss/train': 1.352095127105713}
-03/05/2022 14:21:58 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/05/2022 14:22:01 - INFO - codeparrot_training - Step 41593: {'lr': 0.0004167838325009855, 'samples': 21296128, 'steps': 41593, 'loss/train': 1.580986738204956}
-03/05/2022 14:22:04 - INFO - codeparrot_training - Step 41594: {'lr': 0.0004167798792756279, 'samples': 21296640, 'steps': 41594, 'loss/train': 1.9818189144134521}
-03/05/2022 14:22:06 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/05/2022 14:22:09 - INFO - codeparrot_training - Step 41595: {'lr': 0.0004167759259751218, 'samples': 21297152, 'steps': 41595, 'loss/train': 1.507184624671936}
-03/05/2022 14:22:12 - INFO - codeparrot_training - Step 41596: {'lr': 0.0004167719725994691, 'samples': 21297664, 'steps': 41596, 'loss/train': 1.7664644718170166}
-03/05/2022 14:22:15 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/05/2022 14:22:18 - INFO - codeparrot_training - Step 41597: {'lr': 0.00041676801914867145, 'samples': 21298176, 'steps': 41597, 'loss/train': 1.2250535488128662}
-03/05/2022 14:22:21 - INFO - codeparrot_training - Step 41598: {'lr': 0.00041676406562273074, 'samples': 21298688, 'steps': 41598, 'loss/train': 2.519519805908203}
-03/05/2022 14:22:24 - INFO - codeparrot_training - Skipping example with length 73 (seq_length=1024)
-03/05/2022 14:22:26 - INFO - codeparrot_training - Step 41599: {'lr': 0.00041676011202164875, 'samples': 21299200, 'steps': 41599, 'loss/train': 2.1665432453155518}
-03/05/2022 14:22:29 - INFO - codeparrot_training - Step 41600: {'lr': 0.00041675615834542716, 'samples': 21299712, 'steps': 41600, 'loss/train': 1.8192920684814453}
-03/05/2022 14:22:32 - INFO - codeparrot_training - Skipping example with length 671 (seq_length=1024)
-03/05/2022 14:22:34 - INFO - codeparrot_training - Step 41601: {'lr': 0.0004167522045940678, 'samples': 21300224, 'steps': 41601, 'loss/train': 1.7899430990219116}
-03/05/2022 14:22:38 - INFO - codeparrot_training - Step 41602: {'lr': 0.0004167482507675726, 'samples': 21300736, 'steps': 41602, 'loss/train': 0.9306067228317261}
-03/05/2022 14:22:40 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/05/2022 14:22:43 - INFO - codeparrot_training - Step 41603: {'lr': 0.0004167442968659431, 'samples': 21301248, 'steps': 41603, 'loss/train': 2.0426535606384277}
-03/05/2022 14:22:46 - INFO - codeparrot_training - Step 41604: {'lr': 0.0004167403428891812, 'samples': 21301760, 'steps': 41604, 'loss/train': 0.8324275612831116}
-03/05/2022 14:22:49 - INFO - codeparrot_training - Skipping example with length 743 (seq_length=1024)
-03/05/2022 14:22:51 - INFO - codeparrot_training - Step 41605: {'lr': 0.00041673638883728877, 'samples': 21302272, 'steps': 41605, 'loss/train': 2.3379969596862793}
-03/05/2022 14:22:55 - INFO - codeparrot_training - Step 41606: {'lr': 0.00041673243471026746, 'samples': 21302784, 'steps': 41606, 'loss/train': 1.4243279695510864}
-03/05/2022 14:22:57 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/05/2022 14:23:00 - INFO - codeparrot_training - Step 41607: {'lr': 0.000416728480508119, 'samples': 21303296, 'steps': 41607, 'loss/train': 1.5020380020141602}
-03/05/2022 14:23:03 - INFO - codeparrot_training - Step 41608: {'lr': 0.00041672452623084535, 'samples': 21303808, 'steps': 41608, 'loss/train': 1.3918269872665405}
-03/05/2022 14:23:06 - INFO - codeparrot_training - Skipping example with length 166 (seq_length=1024)
-03/05/2022 14:23:08 - INFO - codeparrot_training - Step 41609: {'lr': 0.0004167205718784481, 'samples': 21304320, 'steps': 41609, 'loss/train': 1.3375792503356934}
-03/05/2022 14:23:12 - INFO - codeparrot_training - Step 41610: {'lr': 0.0004167166174509293, 'samples': 21304832, 'steps': 41610, 'loss/train': 1.8383891582489014}
-03/05/2022 14:23:14 - INFO - codeparrot_training - Skipping example with length 550 (seq_length=1024)
-03/05/2022 14:23:17 - INFO - codeparrot_training - Step 41611: {'lr': 0.00041671266294829036, 'samples': 21305344, 'steps': 41611, 'loss/train': 2.3257861137390137}
-03/05/2022 14:23:20 - INFO - codeparrot_training - Step 41612: {'lr': 0.0004167087083705334, 'samples': 21305856, 'steps': 41612, 'loss/train': 1.3263678550720215}
-03/05/2022 14:23:23 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/05/2022 14:23:25 - INFO - codeparrot_training - Step 41613: {'lr': 0.00041670475371766, 'samples': 21306368, 'steps': 41613, 'loss/train': 1.716586947441101}
-03/05/2022 14:23:28 - INFO - codeparrot_training - Step 41614: {'lr': 0.0004167007989896721, 'samples': 21306880, 'steps': 41614, 'loss/train': 0.9858690500259399}
-03/05/2022 14:23:31 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 14:23:34 - INFO - codeparrot_training - Step 41615: {'lr': 0.0004166968441865714, 'samples': 21307392, 'steps': 41615, 'loss/train': 2.5312905311584473}
-03/05/2022 14:23:37 - INFO - codeparrot_training - Step 41616: {'lr': 0.00041669288930835957, 'samples': 21307904, 'steps': 41616, 'loss/train': 1.8661984205245972}
-03/05/2022 14:23:40 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/05/2022 14:23:42 - INFO - codeparrot_training - Step 41617: {'lr': 0.0004166889343550385, 'samples': 21308416, 'steps': 41617, 'loss/train': 2.1792097091674805}
-03/05/2022 14:23:45 - INFO - codeparrot_training - Step 41618: {'lr': 0.00041668497932661005, 'samples': 21308928, 'steps': 41618, 'loss/train': 1.7360122203826904}
-03/05/2022 14:23:48 - INFO - codeparrot_training - Skipping example with length 272 (seq_length=1024)
-03/05/2022 14:23:51 - INFO - codeparrot_training - Step 41619: {'lr': 0.00041668102422307593, 'samples': 21309440, 'steps': 41619, 'loss/train': 1.0246167182922363}
-03/05/2022 14:23:54 - INFO - codeparrot_training - Step 41620: {'lr': 0.0004166770690444378, 'samples': 21309952, 'steps': 41620, 'loss/train': 1.28842294216156}
-03/05/2022 14:23:56 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/05/2022 14:23:59 - INFO - codeparrot_training - Step 41621: {'lr': 0.0004166731137906976, 'samples': 21310464, 'steps': 41621, 'loss/train': 2.127061128616333}
-03/05/2022 14:24:02 - INFO - codeparrot_training - Step 41622: {'lr': 0.0004166691584618572, 'samples': 21310976, 'steps': 41622, 'loss/train': 1.4796943664550781}
-03/05/2022 14:24:04 - INFO - codeparrot_training - Skipping example with length 233 (seq_length=1024)
-03/05/2022 14:24:07 - INFO - codeparrot_training - Step 41623: {'lr': 0.00041666520305791806, 'samples': 21311488, 'steps': 41623, 'loss/train': 1.7269312143325806}
-03/05/2022 14:24:11 - INFO - codeparrot_training - Step 41624: {'lr': 0.00041666124757888223, 'samples': 21312000, 'steps': 41624, 'loss/train': 2.2671031951904297}
-03/05/2022 14:24:13 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 14:24:16 - INFO - codeparrot_training - Step 41625: {'lr': 0.0004166572920247514, 'samples': 21312512, 'steps': 41625, 'loss/train': 1.7755485773086548}
-03/05/2022 14:24:19 - INFO - codeparrot_training - Step 41626: {'lr': 0.0004166533363955274, 'samples': 21313024, 'steps': 41626, 'loss/train': 1.702317476272583}
-03/05/2022 14:24:21 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/05/2022 14:24:24 - INFO - codeparrot_training - Step 41627: {'lr': 0.00041664938069121195, 'samples': 21313536, 'steps': 41627, 'loss/train': 1.6657503843307495}
-03/05/2022 14:24:28 - INFO - codeparrot_training - Step 41628: {'lr': 0.00041664542491180685, 'samples': 21314048, 'steps': 41628, 'loss/train': 2.1434874534606934}
-03/05/2022 14:24:30 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/05/2022 14:24:33 - INFO - codeparrot_training - Step 41629: {'lr': 0.0004166414690573139, 'samples': 21314560, 'steps': 41629, 'loss/train': 1.9638348817825317}
-03/05/2022 14:24:36 - INFO - codeparrot_training - Step 41630: {'lr': 0.0004166375131277349, 'samples': 21315072, 'steps': 41630, 'loss/train': 1.6797254085540771}
-03/05/2022 14:24:38 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/05/2022 14:24:41 - INFO - codeparrot_training - Step 41631: {'lr': 0.0004166335571230716, 'samples': 21315584, 'steps': 41631, 'loss/train': 2.1227877140045166}
-03/05/2022 14:24:44 - INFO - codeparrot_training - Step 41632: {'lr': 0.0004166296010433258, 'samples': 21316096, 'steps': 41632, 'loss/train': 0.8448343873023987}
-03/05/2022 14:24:47 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/05/2022 14:24:50 - INFO - codeparrot_training - Step 41633: {'lr': 0.00041662564488849927, 'samples': 21316608, 'steps': 41633, 'loss/train': 1.7420042753219604}
-03/05/2022 14:24:53 - INFO - codeparrot_training - Step 41634: {'lr': 0.00041662168865859374, 'samples': 21317120, 'steps': 41634, 'loss/train': 2.223531723022461}
-03/05/2022 14:24:55 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 14:24:58 - INFO - codeparrot_training - Step 41635: {'lr': 0.0004166177323536111, 'samples': 21317632, 'steps': 41635, 'loss/train': 1.6889363527297974}
-03/05/2022 14:25:01 - INFO - codeparrot_training - Step 41636: {'lr': 0.000416613775973553, 'samples': 21318144, 'steps': 41636, 'loss/train': 1.4919371604919434}
-03/05/2022 14:25:03 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/05/2022 14:25:07 - INFO - codeparrot_training - Step 41637: {'lr': 0.0004166098195184214, 'samples': 21318656, 'steps': 41637, 'loss/train': 1.7616660594940186}
-03/05/2022 14:25:10 - INFO - codeparrot_training - Step 41638: {'lr': 0.000416605862988218, 'samples': 21319168, 'steps': 41638, 'loss/train': 2.473755359649658}
-03/05/2022 14:25:12 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/05/2022 14:25:15 - INFO - codeparrot_training - Step 41639: {'lr': 0.00041660190638294456, 'samples': 21319680, 'steps': 41639, 'loss/train': 2.1468098163604736}
-03/05/2022 14:25:19 - INFO - codeparrot_training - Step 41640: {'lr': 0.0004165979497026028, 'samples': 21320192, 'steps': 41640, 'loss/train': 1.4655680656433105}
-03/05/2022 14:25:21 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/05/2022 14:25:24 - INFO - codeparrot_training - Step 41641: {'lr': 0.00041659399294719456, 'samples': 21320704, 'steps': 41641, 'loss/train': 1.7440673112869263}
-03/05/2022 14:25:27 - INFO - codeparrot_training - Step 41642: {'lr': 0.00041659003611672175, 'samples': 21321216, 'steps': 41642, 'loss/train': 1.5244495868682861}
-03/05/2022 14:25:29 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/05/2022 14:25:32 - INFO - codeparrot_training - Step 41643: {'lr': 0.000416586079211186, 'samples': 21321728, 'steps': 41643, 'loss/train': 1.8985596895217896}
-03/05/2022 14:25:35 - INFO - codeparrot_training - Step 41644: {'lr': 0.0004165821222305891, 'samples': 21322240, 'steps': 41644, 'loss/train': 0.8429443836212158}
-03/05/2022 14:25:38 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/05/2022 14:25:41 - INFO - codeparrot_training - Step 41645: {'lr': 0.00041657816517493284, 'samples': 21322752, 'steps': 41645, 'loss/train': 2.8069746494293213}
-03/05/2022 14:25:44 - INFO - codeparrot_training - Step 41646: {'lr': 0.00041657420804421907, 'samples': 21323264, 'steps': 41646, 'loss/train': 1.697685956954956}
-03/05/2022 14:25:46 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/05/2022 14:25:49 - INFO - codeparrot_training - Step 41647: {'lr': 0.00041657025083844957, 'samples': 21323776, 'steps': 41647, 'loss/train': 2.434940814971924}
-03/05/2022 14:25:53 - INFO - codeparrot_training - Step 41648: {'lr': 0.00041656629355762607, 'samples': 21324288, 'steps': 41648, 'loss/train': 2.075854539871216}
-03/05/2022 14:25:55 - INFO - codeparrot_training - Skipping example with length 737 (seq_length=1024)
-03/05/2022 14:25:58 - INFO - codeparrot_training - Step 41649: {'lr': 0.00041656233620175035, 'samples': 21324800, 'steps': 41649, 'loss/train': 0.4990417957305908}
-03/05/2022 14:26:01 - INFO - codeparrot_training - Step 41650: {'lr': 0.0004165583787708242, 'samples': 21325312, 'steps': 41650, 'loss/train': 1.6960694789886475}
-03/05/2022 14:26:03 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/05/2022 14:26:07 - INFO - codeparrot_training - Step 41651: {'lr': 0.0004165544212648494, 'samples': 21325824, 'steps': 41651, 'loss/train': 1.7673367261886597}
-03/05/2022 14:26:10 - INFO - codeparrot_training - Step 41652: {'lr': 0.0004165504636838278, 'samples': 21326336, 'steps': 41652, 'loss/train': 1.4973268508911133}
-03/05/2022 14:26:12 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/05/2022 14:26:16 - INFO - codeparrot_training - Step 41653: {'lr': 0.0004165465060277611, 'samples': 21326848, 'steps': 41653, 'loss/train': 1.749884009361267}
-03/05/2022 14:26:19 - INFO - codeparrot_training - Step 41654: {'lr': 0.0004165425482966512, 'samples': 21327360, 'steps': 41654, 'loss/train': 1.7984153032302856}
-03/05/2022 14:26:22 - INFO - codeparrot_training - Step 41655: {'lr': 0.00041653859049049964, 'samples': 21327872, 'steps': 41655, 'loss/train': 2.2414894104003906}
-03/05/2022 14:26:24 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 14:26:27 - INFO - codeparrot_training - Step 41656: {'lr': 0.00041653463260930845, 'samples': 21328384, 'steps': 41656, 'loss/train': 1.9328770637512207}
-03/05/2022 14:26:31 - INFO - codeparrot_training - Step 41657: {'lr': 0.00041653067465307925, 'samples': 21328896, 'steps': 41657, 'loss/train': 2.1162314414978027}
-03/05/2022 14:26:33 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 14:26:36 - INFO - codeparrot_training - Step 41658: {'lr': 0.00041652671662181394, 'samples': 21329408, 'steps': 41658, 'loss/train': 1.756325602531433}
-03/05/2022 14:26:39 - INFO - codeparrot_training - Step 41659: {'lr': 0.00041652275851551435, 'samples': 21329920, 'steps': 41659, 'loss/train': 0.9732646942138672}
-03/05/2022 14:26:41 - INFO - codeparrot_training - Skipping example with length 675 (seq_length=1024)
-03/05/2022 14:26:44 - INFO - codeparrot_training - Step 41660: {'lr': 0.0004165188003341821, 'samples': 21330432, 'steps': 41660, 'loss/train': 2.4505391120910645}
-03/05/2022 14:26:48 - INFO - codeparrot_training - Step 41661: {'lr': 0.0004165148420778191, 'samples': 21330944, 'steps': 41661, 'loss/train': 1.937347650527954}
-03/05/2022 14:26:51 - INFO - codeparrot_training - Step 41662: {'lr': 0.000416510883746427, 'samples': 21331456, 'steps': 41662, 'loss/train': 2.591834306716919}
-03/05/2022 14:26:51 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/05/2022 14:26:56 - INFO - codeparrot_training - Step 41663: {'lr': 0.00041650692534000766, 'samples': 21331968, 'steps': 41663, 'loss/train': 1.4354758262634277}
-03/05/2022 14:26:59 - INFO - codeparrot_training - Step 41664: {'lr': 0.0004165029668585629, 'samples': 21332480, 'steps': 41664, 'loss/train': 2.329026937484741}
-03/05/2022 14:26:59 - INFO - codeparrot_training - Skipping example with length 264 (seq_length=1024)
-03/05/2022 14:27:05 - INFO - codeparrot_training - Step 41665: {'lr': 0.00041649900830209455, 'samples': 21332992, 'steps': 41665, 'loss/train': 3.51607084274292}
-03/05/2022 14:27:08 - INFO - codeparrot_training - Step 41666: {'lr': 0.00041649504967060423, 'samples': 21333504, 'steps': 41666, 'loss/train': 1.9585216045379639}
-03/05/2022 14:27:08 - INFO - codeparrot_training - Skipping example with length 256 (seq_length=1024)
-03/05/2022 14:27:13 - INFO - codeparrot_training - Step 41667: {'lr': 0.0004164910909640938, 'samples': 21334016, 'steps': 41667, 'loss/train': 1.897063970565796}
-03/05/2022 14:27:16 - INFO - codeparrot_training - Step 41668: {'lr': 0.0004164871321825651, 'samples': 21334528, 'steps': 41668, 'loss/train': 1.3781602382659912}
-03/05/2022 14:27:17 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/05/2022 14:27:22 - INFO - codeparrot_training - Step 41669: {'lr': 0.0004164831733260198, 'samples': 21335040, 'steps': 41669, 'loss/train': 4.243336200714111}
-03/05/2022 14:27:25 - INFO - codeparrot_training - Step 41670: {'lr': 0.0004164792143944598, 'samples': 21335552, 'steps': 41670, 'loss/train': 1.4653195142745972}
-03/05/2022 14:27:26 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/05/2022 14:27:30 - INFO - codeparrot_training - Step 41671: {'lr': 0.0004164752553878868, 'samples': 21336064, 'steps': 41671, 'loss/train': 2.3739006519317627}
-03/05/2022 14:27:33 - INFO - codeparrot_training - Step 41672: {'lr': 0.00041647129630630265, 'samples': 21336576, 'steps': 41672, 'loss/train': 2.4608724117279053}
-03/05/2022 14:27:34 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 14:27:39 - INFO - codeparrot_training - Step 41673: {'lr': 0.0004164673371497092, 'samples': 21337088, 'steps': 41673, 'loss/train': 1.587136149406433}
-03/05/2022 14:27:42 - INFO - codeparrot_training - Step 41674: {'lr': 0.000416463377918108, 'samples': 21337600, 'steps': 41674, 'loss/train': 1.1188586950302124}
-03/05/2022 14:27:42 - INFO - codeparrot_training - Skipping example with length 319 (seq_length=1024)
-03/05/2022 14:27:47 - INFO - codeparrot_training - Step 41675: {'lr': 0.00041645941861150103, 'samples': 21338112, 'steps': 41675, 'loss/train': 1.8335367441177368}
-03/05/2022 14:27:50 - INFO - codeparrot_training - Step 41676: {'lr': 0.00041645545922989, 'samples': 21338624, 'steps': 41676, 'loss/train': 1.3211820125579834}
-03/05/2022 14:27:50 - INFO - codeparrot_training - Skipping example with length 173 (seq_length=1024)
-03/05/2022 14:27:55 - INFO - codeparrot_training - Step 41677: {'lr': 0.00041645149977327667, 'samples': 21339136, 'steps': 41677, 'loss/train': 2.4156367778778076}
-03/05/2022 14:27:59 - INFO - codeparrot_training - Step 41678: {'lr': 0.0004164475402416629, 'samples': 21339648, 'steps': 41678, 'loss/train': 2.0650765895843506}
-03/05/2022 14:27:59 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 14:28:04 - INFO - codeparrot_training - Step 41679: {'lr': 0.0004164435806350505, 'samples': 21340160, 'steps': 41679, 'loss/train': 1.0672776699066162}
-03/05/2022 14:28:07 - INFO - codeparrot_training - Step 41680: {'lr': 0.00041643962095344107, 'samples': 21340672, 'steps': 41680, 'loss/train': 1.3673419952392578}
-03/05/2022 14:28:07 - INFO - codeparrot_training - Skipping example with length 233 (seq_length=1024)
-03/05/2022 14:28:12 - INFO - codeparrot_training - Step 41681: {'lr': 0.0004164356611968366, 'samples': 21341184, 'steps': 41681, 'loss/train': 1.7573305368423462}
-03/05/2022 14:28:15 - INFO - codeparrot_training - Step 41682: {'lr': 0.0004164317013652387, 'samples': 21341696, 'steps': 41682, 'loss/train': 2.2569353580474854}
-03/05/2022 14:28:16 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/05/2022 14:28:21 - INFO - codeparrot_training - Step 41683: {'lr': 0.00041642774145864934, 'samples': 21342208, 'steps': 41683, 'loss/train': 1.987130880355835}
-03/05/2022 14:28:24 - INFO - codeparrot_training - Step 41684: {'lr': 0.00041642378147707014, 'samples': 21342720, 'steps': 41684, 'loss/train': 1.2720822095870972}
-03/05/2022 14:28:24 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/05/2022 14:28:29 - INFO - codeparrot_training - Step 41685: {'lr': 0.00041641982142050297, 'samples': 21343232, 'steps': 41685, 'loss/train': 1.2535079717636108}
-03/05/2022 14:28:32 - INFO - codeparrot_training - Step 41686: {'lr': 0.00041641586128894967, 'samples': 21343744, 'steps': 41686, 'loss/train': 0.30420124530792236}
-03/05/2022 14:28:33 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/05/2022 14:28:38 - INFO - codeparrot_training - Step 41687: {'lr': 0.0004164119010824119, 'samples': 21344256, 'steps': 41687, 'loss/train': 1.808125376701355}
-03/05/2022 14:28:41 - INFO - codeparrot_training - Step 41688: {'lr': 0.00041640794080089144, 'samples': 21344768, 'steps': 41688, 'loss/train': 1.4203946590423584}
-03/05/2022 14:28:41 - INFO - codeparrot_training - Skipping example with length 704 (seq_length=1024)
-03/05/2022 14:28:46 - INFO - codeparrot_training - Step 41689: {'lr': 0.0004164039804443902, 'samples': 21345280, 'steps': 41689, 'loss/train': 1.6546109914779663}
-03/05/2022 14:28:49 - INFO - codeparrot_training - Step 41690: {'lr': 0.0004164000200129099, 'samples': 21345792, 'steps': 41690, 'loss/train': 2.436789035797119}
-03/05/2022 14:28:49 - INFO - codeparrot_training - Skipping example with length 957 (seq_length=1024)
-03/05/2022 14:28:55 - INFO - codeparrot_training - Step 41691: {'lr': 0.0004163960595064522, 'samples': 21346304, 'steps': 41691, 'loss/train': 1.7991865873336792}
-03/05/2022 14:28:58 - INFO - codeparrot_training - Step 41692: {'lr': 0.00041639209892501913, 'samples': 21346816, 'steps': 41692, 'loss/train': 1.4937413930892944}
-03/05/2022 14:28:58 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/05/2022 14:29:03 - INFO - codeparrot_training - Step 41693: {'lr': 0.00041638813826861234, 'samples': 21347328, 'steps': 41693, 'loss/train': 2.2962238788604736}
-03/05/2022 14:29:06 - INFO - codeparrot_training - Step 41694: {'lr': 0.00041638417753723356, 'samples': 21347840, 'steps': 41694, 'loss/train': 1.8071091175079346}
-03/05/2022 14:29:06 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/05/2022 14:29:11 - INFO - codeparrot_training - Step 41695: {'lr': 0.00041638021673088464, 'samples': 21348352, 'steps': 41695, 'loss/train': 1.6083688735961914}
-03/05/2022 14:29:15 - INFO - codeparrot_training - Step 41696: {'lr': 0.0004163762558495674, 'samples': 21348864, 'steps': 41696, 'loss/train': 0.7448838949203491}
-03/05/2022 14:29:15 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/05/2022 14:29:20 - INFO - codeparrot_training - Step 41697: {'lr': 0.0004163722948932836, 'samples': 21349376, 'steps': 41697, 'loss/train': 1.8733819723129272}
-03/05/2022 14:29:23 - INFO - codeparrot_training - Step 41698: {'lr': 0.000416368333862035, 'samples': 21349888, 'steps': 41698, 'loss/train': 0.9922410845756531}
-03/05/2022 14:29:23 - INFO - codeparrot_training - Skipping example with length 454 (seq_length=1024)
-03/05/2022 14:29:28 - INFO - codeparrot_training - Step 41699: {'lr': 0.00041636437275582335, 'samples': 21350400, 'steps': 41699, 'loss/train': 0.5835087299346924}
-03/05/2022 14:29:31 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/05/2022 14:29:34 - INFO - codeparrot_training - Step 41700: {'lr': 0.00041636041157465056, 'samples': 21350912, 'steps': 41700, 'loss/train': 1.3758397102355957}
-03/05/2022 14:29:37 - INFO - codeparrot_training - Step 41701: {'lr': 0.00041635645031851826, 'samples': 21351424, 'steps': 41701, 'loss/train': 1.8728586435317993}
-03/05/2022 14:29:39 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 14:29:42 - INFO - codeparrot_training - Step 41702: {'lr': 0.00041635248898742834, 'samples': 21351936, 'steps': 41702, 'loss/train': 1.651859998703003}
-03/05/2022 14:29:45 - INFO - codeparrot_training - Step 41703: {'lr': 0.00041634852758138253, 'samples': 21352448, 'steps': 41703, 'loss/train': 1.826904058456421}
-03/05/2022 14:29:48 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 14:29:51 - INFO - codeparrot_training - Step 41704: {'lr': 0.0004163445661003827, 'samples': 21352960, 'steps': 41704, 'loss/train': 1.442320466041565}
-03/05/2022 14:29:54 - INFO - codeparrot_training - Step 41705: {'lr': 0.0004163406045444306, 'samples': 21353472, 'steps': 41705, 'loss/train': 1.7606229782104492}
-03/05/2022 14:29:57 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/05/2022 14:29:59 - INFO - codeparrot_training - Step 41706: {'lr': 0.0004163366429135279, 'samples': 21353984, 'steps': 41706, 'loss/train': 1.3644556999206543}
-03/05/2022 14:30:02 - INFO - codeparrot_training - Step 41707: {'lr': 0.00041633268120767653, 'samples': 21354496, 'steps': 41707, 'loss/train': 0.25754961371421814}
-03/05/2022 14:30:05 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/05/2022 14:30:08 - INFO - codeparrot_training - Step 41708: {'lr': 0.00041632871942687814, 'samples': 21355008, 'steps': 41708, 'loss/train': 1.7235949039459229}
-03/05/2022 14:30:11 - INFO - codeparrot_training - Step 41709: {'lr': 0.00041632475757113466, 'samples': 21355520, 'steps': 41709, 'loss/train': 1.9293450117111206}
-03/05/2022 14:30:13 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/05/2022 14:30:16 - INFO - codeparrot_training - Step 41710: {'lr': 0.00041632079564044776, 'samples': 21356032, 'steps': 41710, 'loss/train': 1.8824853897094727}
-03/05/2022 14:30:19 - INFO - codeparrot_training - Step 41711: {'lr': 0.0004163168336348194, 'samples': 21356544, 'steps': 41711, 'loss/train': 1.863020896911621}
-03/05/2022 14:30:22 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 14:30:25 - INFO - codeparrot_training - Step 41712: {'lr': 0.00041631287155425114, 'samples': 21357056, 'steps': 41712, 'loss/train': 1.8134782314300537}
-03/05/2022 14:30:28 - INFO - codeparrot_training - Step 41713: {'lr': 0.0004163089093987449, 'samples': 21357568, 'steps': 41713, 'loss/train': 1.4001761674880981}
-03/05/2022 14:30:31 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/05/2022 14:30:33 - INFO - codeparrot_training - Step 41714: {'lr': 0.00041630494716830244, 'samples': 21358080, 'steps': 41714, 'loss/train': 1.7449383735656738}
-03/05/2022 14:30:36 - INFO - codeparrot_training - Step 41715: {'lr': 0.00041630098486292546, 'samples': 21358592, 'steps': 41715, 'loss/train': 2.236294984817505}
-03/05/2022 14:30:39 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 14:30:41 - INFO - codeparrot_training - Step 41716: {'lr': 0.0004162970224826159, 'samples': 21359104, 'steps': 41716, 'loss/train': 2.058333158493042}
-03/05/2022 14:30:45 - INFO - codeparrot_training - Step 41717: {'lr': 0.0004162930600273754, 'samples': 21359616, 'steps': 41717, 'loss/train': 3.119856119155884}
-03/05/2022 14:30:47 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 14:30:50 - INFO - codeparrot_training - Step 41718: {'lr': 0.0004162890974972059, 'samples': 21360128, 'steps': 41718, 'loss/train': 0.34487542510032654}
-03/05/2022 14:30:53 - INFO - codeparrot_training - Step 41719: {'lr': 0.00041628513489210906, 'samples': 21360640, 'steps': 41719, 'loss/train': 0.9428035020828247}
-03/05/2022 14:30:56 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 14:30:59 - INFO - codeparrot_training - Step 41720: {'lr': 0.0004162811722120867, 'samples': 21361152, 'steps': 41720, 'loss/train': 2.032289981842041}
-03/05/2022 14:31:02 - INFO - codeparrot_training - Step 41721: {'lr': 0.00041627720945714065, 'samples': 21361664, 'steps': 41721, 'loss/train': 2.018343925476074}
-03/05/2022 14:31:05 - INFO - codeparrot_training - Skipping example with length 955 (seq_length=1024)
-03/05/2022 14:31:07 - INFO - codeparrot_training - Step 41722: {'lr': 0.00041627324662727263, 'samples': 21362176, 'steps': 41722, 'loss/train': 1.4492855072021484}
-03/05/2022 14:31:10 - INFO - codeparrot_training - Step 41723: {'lr': 0.0004162692837224844, 'samples': 21362688, 'steps': 41723, 'loss/train': 2.0627553462982178}
-03/05/2022 14:31:13 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 14:31:15 - INFO - codeparrot_training - Step 41724: {'lr': 0.00041626532074277785, 'samples': 21363200, 'steps': 41724, 'loss/train': 1.7866464853286743}
-03/05/2022 14:31:19 - INFO - codeparrot_training - Step 41725: {'lr': 0.00041626135768815467, 'samples': 21363712, 'steps': 41725, 'loss/train': 0.8510217070579529}
-03/05/2022 14:31:21 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 14:31:24 - INFO - codeparrot_training - Step 41726: {'lr': 0.0004162573945586168, 'samples': 21364224, 'steps': 41726, 'loss/train': 1.8329081535339355}
-03/05/2022 14:31:27 - INFO - codeparrot_training - Step 41727: {'lr': 0.0004162534313541658, 'samples': 21364736, 'steps': 41727, 'loss/train': 2.198261260986328}
-03/05/2022 14:31:29 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/05/2022 14:31:32 - INFO - codeparrot_training - Step 41728: {'lr': 0.00041624946807480357, 'samples': 21365248, 'steps': 41728, 'loss/train': 1.6582375764846802}
-03/05/2022 14:31:35 - INFO - codeparrot_training - Step 41729: {'lr': 0.0004162455047205319, 'samples': 21365760, 'steps': 41729, 'loss/train': 1.9028270244598389}
-03/05/2022 14:31:38 - INFO - codeparrot_training - Skipping example with length 226 (seq_length=1024)
-03/05/2022 14:31:41 - INFO - codeparrot_training - Step 41730: {'lr': 0.0004162415412913526, 'samples': 21366272, 'steps': 41730, 'loss/train': 1.8614505529403687}
-03/05/2022 14:31:44 - INFO - codeparrot_training - Step 41731: {'lr': 0.00041623757778726743, 'samples': 21366784, 'steps': 41731, 'loss/train': 1.7509688138961792}
-03/05/2022 14:31:46 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/05/2022 14:31:49 - INFO - codeparrot_training - Step 41732: {'lr': 0.00041623361420827816, 'samples': 21367296, 'steps': 41732, 'loss/train': 1.241576910018921}
-03/05/2022 14:31:52 - INFO - codeparrot_training - Step 41733: {'lr': 0.0004162296505543867, 'samples': 21367808, 'steps': 41733, 'loss/train': 1.568440318107605}
-03/05/2022 14:31:55 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/05/2022 14:31:58 - INFO - codeparrot_training - Step 41734: {'lr': 0.00041622568682559455, 'samples': 21368320, 'steps': 41734, 'loss/train': 1.812659502029419}
-03/05/2022 14:32:01 - INFO - codeparrot_training - Step 41735: {'lr': 0.0004162217230219038, 'samples': 21368832, 'steps': 41735, 'loss/train': 2.452751874923706}
-03/05/2022 14:32:04 - INFO - codeparrot_training - Skipping example with length 772 (seq_length=1024)
-03/05/2022 14:32:06 - INFO - codeparrot_training - Step 41736: {'lr': 0.00041621775914331595, 'samples': 21369344, 'steps': 41736, 'loss/train': 0.9021335244178772}
-03/05/2022 14:32:09 - INFO - codeparrot_training - Step 41737: {'lr': 0.00041621379518983306, 'samples': 21369856, 'steps': 41737, 'loss/train': 1.8786866664886475}
-03/05/2022 14:32:13 - INFO - codeparrot_training - Step 41738: {'lr': 0.00041620983116145673, 'samples': 21370368, 'steps': 41738, 'loss/train': 1.1865384578704834}
-03/05/2022 14:32:13 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/05/2022 14:32:18 - INFO - codeparrot_training - Step 41739: {'lr': 0.00041620586705818887, 'samples': 21370880, 'steps': 41739, 'loss/train': 2.075021505355835}
-03/05/2022 14:32:21 - INFO - codeparrot_training - Step 41740: {'lr': 0.00041620190288003126, 'samples': 21371392, 'steps': 41740, 'loss/train': 1.3971706628799438}
-03/05/2022 14:32:21 - INFO - codeparrot_training - Skipping example with length 34 (seq_length=1024)
-03/05/2022 14:32:27 - INFO - codeparrot_training - Step 41741: {'lr': 0.00041619793862698553, 'samples': 21371904, 'steps': 41741, 'loss/train': 1.285348892211914}
-03/05/2022 14:32:29 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/05/2022 14:32:32 - INFO - codeparrot_training - Step 41742: {'lr': 0.00041619397429905363, 'samples': 21372416, 'steps': 41742, 'loss/train': 2.2484617233276367}
-03/05/2022 14:32:35 - INFO - codeparrot_training - Step 41743: {'lr': 0.0004161900098962373, 'samples': 21372928, 'steps': 41743, 'loss/train': 1.2048940658569336}
-03/05/2022 14:32:38 - INFO - codeparrot_training - Step 41744: {'lr': 0.00041618604541853826, 'samples': 21373440, 'steps': 41744, 'loss/train': 1.5794901847839355}
-03/05/2022 14:32:38 - INFO - codeparrot_training - Skipping example with length 641 (seq_length=1024)
-03/05/2022 14:32:44 - INFO - codeparrot_training - Step 41745: {'lr': 0.00041618208086595843, 'samples': 21373952, 'steps': 41745, 'loss/train': 1.7224981784820557}
-03/05/2022 14:32:47 - INFO - codeparrot_training - Step 41746: {'lr': 0.0004161781162384994, 'samples': 21374464, 'steps': 41746, 'loss/train': 1.7562841176986694}
-03/05/2022 14:32:47 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/05/2022 14:32:52 - INFO - codeparrot_training - Step 41747: {'lr': 0.00041617415153616323, 'samples': 21374976, 'steps': 41747, 'loss/train': 1.4150525331497192}
-03/05/2022 14:32:55 - INFO - codeparrot_training - Step 41748: {'lr': 0.00041617018675895145, 'samples': 21375488, 'steps': 41748, 'loss/train': 1.1216872930526733}
-03/05/2022 14:32:55 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 14:33:01 - INFO - codeparrot_training - Step 41749: {'lr': 0.00041616622190686597, 'samples': 21376000, 'steps': 41749, 'loss/train': 1.593578577041626}
-03/05/2022 14:33:03 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 14:33:06 - INFO - codeparrot_training - Step 41750: {'lr': 0.0004161622569799086, 'samples': 21376512, 'steps': 41750, 'loss/train': 1.9373071193695068}
-03/05/2022 14:33:09 - INFO - codeparrot_training - Step 41751: {'lr': 0.00041615829197808095, 'samples': 21377024, 'steps': 41751, 'loss/train': 2.0588881969451904}
-03/05/2022 14:33:12 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/05/2022 14:33:14 - INFO - codeparrot_training - Step 41752: {'lr': 0.0004161543269013851, 'samples': 21377536, 'steps': 41752, 'loss/train': 2.1555511951446533}
-03/05/2022 14:33:17 - INFO - codeparrot_training - Step 41753: {'lr': 0.0004161503617498226, 'samples': 21378048, 'steps': 41753, 'loss/train': 1.4979212284088135}
-03/05/2022 14:33:20 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/05/2022 14:33:23 - INFO - codeparrot_training - Step 41754: {'lr': 0.00041614639652339533, 'samples': 21378560, 'steps': 41754, 'loss/train': 1.1509913206100464}
-03/05/2022 14:33:26 - INFO - codeparrot_training - Step 41755: {'lr': 0.00041614243122210505, 'samples': 21379072, 'steps': 41755, 'loss/train': 1.7587387561798096}
-03/05/2022 14:33:29 - INFO - codeparrot_training - Step 41756: {'lr': 0.0004161384658459535, 'samples': 21379584, 'steps': 41756, 'loss/train': 1.6897778511047363}
-03/05/2022 14:33:29 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/05/2022 14:33:35 - INFO - codeparrot_training - Step 41757: {'lr': 0.0004161345003949426, 'samples': 21380096, 'steps': 41757, 'loss/train': 1.425044059753418}
-03/05/2022 14:33:38 - INFO - codeparrot_training - Step 41758: {'lr': 0.00041613053486907396, 'samples': 21380608, 'steps': 41758, 'loss/train': 0.9519824981689453}
-03/05/2022 14:33:38 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 14:33:43 - INFO - codeparrot_training - Step 41759: {'lr': 0.0004161265692683496, 'samples': 21381120, 'steps': 41759, 'loss/train': 1.6517250537872314}
-03/05/2022 14:33:46 - INFO - codeparrot_training - Step 41760: {'lr': 0.0004161226035927711, 'samples': 21381632, 'steps': 41760, 'loss/train': 1.877320408821106}
-03/05/2022 14:33:46 - INFO - codeparrot_training - Skipping example with length 684 (seq_length=1024)
-03/05/2022 14:33:52 - INFO - codeparrot_training - Step 41761: {'lr': 0.0004161186378423403, 'samples': 21382144, 'steps': 41761, 'loss/train': 1.8326894044876099}
-03/05/2022 14:33:55 - INFO - codeparrot_training - Step 41762: {'lr': 0.000416114672017059, 'samples': 21382656, 'steps': 41762, 'loss/train': 1.6931723356246948}
-03/05/2022 14:33:55 - INFO - codeparrot_training - Skipping example with length 74 (seq_length=1024)
-03/05/2022 14:34:00 - INFO - codeparrot_training - Step 41763: {'lr': 0.000416110706116929, 'samples': 21383168, 'steps': 41763, 'loss/train': 1.6347417831420898}
-03/05/2022 14:34:03 - INFO - codeparrot_training - Step 41764: {'lr': 0.0004161067401419521, 'samples': 21383680, 'steps': 41764, 'loss/train': 0.7342800498008728}
-03/05/2022 14:34:03 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/05/2022 14:34:09 - INFO - codeparrot_training - Step 41765: {'lr': 0.00041610277409213003, 'samples': 21384192, 'steps': 41765, 'loss/train': 1.1642147302627563}
-03/05/2022 14:34:12 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/05/2022 14:34:14 - INFO - codeparrot_training - Step 41766: {'lr': 0.00041609880796746463, 'samples': 21384704, 'steps': 41766, 'loss/train': 0.7868087887763977}
-03/05/2022 14:34:17 - INFO - codeparrot_training - Step 41767: {'lr': 0.00041609484176795774, 'samples': 21385216, 'steps': 41767, 'loss/train': 1.8411526679992676}
-03/05/2022 14:34:20 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/05/2022 14:34:23 - INFO - codeparrot_training - Step 41768: {'lr': 0.000416090875493611, 'samples': 21385728, 'steps': 41768, 'loss/train': 1.9450314044952393}
-03/05/2022 14:34:26 - INFO - codeparrot_training - Step 41769: {'lr': 0.0004160869091444263, 'samples': 21386240, 'steps': 41769, 'loss/train': 2.205070972442627}
-03/05/2022 14:34:28 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/05/2022 14:34:31 - INFO - codeparrot_training - Step 41770: {'lr': 0.0004160829427204054, 'samples': 21386752, 'steps': 41770, 'loss/train': 1.0739736557006836}
-03/05/2022 14:34:34 - INFO - codeparrot_training - Step 41771: {'lr': 0.00041607897622155006, 'samples': 21387264, 'steps': 41771, 'loss/train': 1.988388180732727}
-03/05/2022 14:34:38 - INFO - codeparrot_training - Step 41772: {'lr': 0.00041607500964786217, 'samples': 21387776, 'steps': 41772, 'loss/train': 2.357546091079712}
-03/05/2022 14:34:39 - INFO - codeparrot_training - Skipping example with length 424 (seq_length=1024)
-03/05/2022 14:34:43 - INFO - codeparrot_training - Step 41773: {'lr': 0.0004160710429993434, 'samples': 21388288, 'steps': 41773, 'loss/train': 1.4070957899093628}
-03/05/2022 14:34:46 - INFO - codeparrot_training - Step 41774: {'lr': 0.00041606707627599556, 'samples': 21388800, 'steps': 41774, 'loss/train': 1.8731684684753418}
-03/05/2022 14:34:47 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/05/2022 14:34:51 - INFO - codeparrot_training - Step 41775: {'lr': 0.00041606310947782046, 'samples': 21389312, 'steps': 41775, 'loss/train': 1.9431158304214478}
-03/05/2022 14:34:54 - INFO - codeparrot_training - Step 41776: {'lr': 0.0004160591426048199, 'samples': 21389824, 'steps': 41776, 'loss/train': 1.3166228532791138}
-03/05/2022 14:34:55 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/05/2022 14:35:00 - INFO - codeparrot_training - Step 41777: {'lr': 0.00041605517565699565, 'samples': 21390336, 'steps': 41777, 'loss/train': 2.4415535926818848}
-03/05/2022 14:35:03 - INFO - codeparrot_training - Step 41778: {'lr': 0.00041605120863434945, 'samples': 21390848, 'steps': 41778, 'loss/train': 0.7269604206085205}
-03/05/2022 14:35:04 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/05/2022 14:35:08 - INFO - codeparrot_training - Step 41779: {'lr': 0.0004160472415368832, 'samples': 21391360, 'steps': 41779, 'loss/train': 1.005304217338562}
-03/05/2022 14:35:11 - INFO - codeparrot_training - Step 41780: {'lr': 0.00041604327436459864, 'samples': 21391872, 'steps': 41780, 'loss/train': 1.305239200592041}
-03/05/2022 14:35:12 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/05/2022 14:35:17 - INFO - codeparrot_training - Step 41781: {'lr': 0.0004160393071174975, 'samples': 21392384, 'steps': 41781, 'loss/train': 1.2439658641815186}
-03/05/2022 14:35:20 - INFO - codeparrot_training - Step 41782: {'lr': 0.00041603533979558163, 'samples': 21392896, 'steps': 41782, 'loss/train': 2.236541271209717}
-03/05/2022 14:35:23 - INFO - codeparrot_training - Step 41783: {'lr': 0.0004160313723988528, 'samples': 21393408, 'steps': 41783, 'loss/train': 2.9792258739471436}
-03/05/2022 14:35:23 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/05/2022 14:35:29 - INFO - codeparrot_training - Step 41784: {'lr': 0.00041602740492731284, 'samples': 21393920, 'steps': 41784, 'loss/train': 2.185302257537842}
-03/05/2022 14:35:32 - INFO - codeparrot_training - Step 41785: {'lr': 0.0004160234373809634, 'samples': 21394432, 'steps': 41785, 'loss/train': 1.638179898262024}
-03/05/2022 14:35:32 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/05/2022 14:35:37 - INFO - codeparrot_training - Step 41786: {'lr': 0.0004160194697598064, 'samples': 21394944, 'steps': 41786, 'loss/train': 2.057363748550415}
-03/05/2022 14:35:40 - INFO - codeparrot_training - Step 41787: {'lr': 0.0004160155020638436, 'samples': 21395456, 'steps': 41787, 'loss/train': 1.5573837757110596}
-03/05/2022 14:35:41 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/05/2022 14:35:46 - INFO - codeparrot_training - Step 41788: {'lr': 0.0004160115342930768, 'samples': 21395968, 'steps': 41788, 'loss/train': 2.139017343521118}
-03/05/2022 14:35:49 - INFO - codeparrot_training - Step 41789: {'lr': 0.0004160075664475077, 'samples': 21396480, 'steps': 41789, 'loss/train': 1.1939339637756348}
-03/05/2022 14:35:50 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/05/2022 14:35:54 - INFO - codeparrot_training - Step 41790: {'lr': 0.0004160035985271382, 'samples': 21396992, 'steps': 41790, 'loss/train': 1.2115103006362915}
-03/05/2022 14:35:58 - INFO - codeparrot_training - Step 41791: {'lr': 0.00041599963053196997, 'samples': 21397504, 'steps': 41791, 'loss/train': 1.4891074895858765}
-03/05/2022 14:35:58 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/05/2022 14:36:03 - INFO - codeparrot_training - Step 41792: {'lr': 0.0004159956624620049, 'samples': 21398016, 'steps': 41792, 'loss/train': 2.7218449115753174}
-03/05/2022 14:36:06 - INFO - codeparrot_training - Step 41793: {'lr': 0.0004159916943172448, 'samples': 21398528, 'steps': 41793, 'loss/train': 1.8159451484680176}
-03/05/2022 14:36:06 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/05/2022 14:36:11 - INFO - codeparrot_training - Step 41794: {'lr': 0.0004159877260976914, 'samples': 21399040, 'steps': 41794, 'loss/train': 1.2737501859664917}
-03/05/2022 14:36:15 - INFO - codeparrot_training - Step 41795: {'lr': 0.00041598375780334653, 'samples': 21399552, 'steps': 41795, 'loss/train': 2.182703971862793}
-03/05/2022 14:36:15 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/05/2022 14:36:20 - INFO - codeparrot_training - Step 41796: {'lr': 0.0004159797894342118, 'samples': 21400064, 'steps': 41796, 'loss/train': 1.7394859790802002}
-03/05/2022 14:36:23 - INFO - codeparrot_training - Step 41797: {'lr': 0.0004159758209902892, 'samples': 21400576, 'steps': 41797, 'loss/train': 2.303119421005249}
-03/05/2022 14:36:24 - INFO - codeparrot_training - Skipping example with length 631 (seq_length=1024)
-03/05/2022 14:36:28 - INFO - codeparrot_training - Step 41798: {'lr': 0.00041597185247158053, 'samples': 21401088, 'steps': 41798, 'loss/train': 1.6201814413070679}
-03/05/2022 14:36:32 - INFO - codeparrot_training - Step 41799: {'lr': 0.0004159678838780874, 'samples': 21401600, 'steps': 41799, 'loss/train': 1.4371980428695679}
-03/05/2022 14:36:32 - INFO - codeparrot_training - Skipping example with length 615 (seq_length=1024)
-03/05/2022 14:36:37 - INFO - codeparrot_training - Step 41800: {'lr': 0.0004159639152098118, 'samples': 21402112, 'steps': 41800, 'loss/train': 1.6071571111679077}
-03/05/2022 14:36:40 - INFO - codeparrot_training - Step 41801: {'lr': 0.00041595994646675537, 'samples': 21402624, 'steps': 41801, 'loss/train': 0.42283979058265686}
-03/05/2022 14:36:41 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 14:36:45 - INFO - codeparrot_training - Step 41802: {'lr': 0.0004159559776489199, 'samples': 21403136, 'steps': 41802, 'loss/train': 1.1579097509384155}
-03/05/2022 14:36:49 - INFO - codeparrot_training - Step 41803: {'lr': 0.00041595200875630734, 'samples': 21403648, 'steps': 41803, 'loss/train': 1.873628854751587}
-03/05/2022 14:36:50 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/05/2022 14:36:54 - INFO - codeparrot_training - Step 41804: {'lr': 0.00041594803978891925, 'samples': 21404160, 'steps': 41804, 'loss/train': 2.2802813053131104}
-03/05/2022 14:36:57 - INFO - codeparrot_training - Step 41805: {'lr': 0.00041594407074675753, 'samples': 21404672, 'steps': 41805, 'loss/train': 1.569593906402588}
-03/05/2022 14:36:58 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/05/2022 14:37:02 - INFO - codeparrot_training - Step 41806: {'lr': 0.0004159401016298241, 'samples': 21405184, 'steps': 41806, 'loss/train': 2.0869293212890625}
-03/05/2022 14:37:05 - INFO - codeparrot_training - Step 41807: {'lr': 0.0004159361324381206, 'samples': 21405696, 'steps': 41807, 'loss/train': 1.9293608665466309}
-03/05/2022 14:37:06 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/05/2022 14:37:11 - INFO - codeparrot_training - Step 41808: {'lr': 0.0004159321631716487, 'samples': 21406208, 'steps': 41808, 'loss/train': 2.2722971439361572}
-03/05/2022 14:37:14 - INFO - codeparrot_training - Step 41809: {'lr': 0.00041592819383041047, 'samples': 21406720, 'steps': 41809, 'loss/train': 1.460873007774353}
-03/05/2022 14:37:15 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/05/2022 14:37:19 - INFO - codeparrot_training - Step 41810: {'lr': 0.0004159242244144075, 'samples': 21407232, 'steps': 41810, 'loss/train': 1.706587314605713}
-03/05/2022 14:37:22 - INFO - codeparrot_training - Step 41811: {'lr': 0.0004159202549236416, 'samples': 21407744, 'steps': 41811, 'loss/train': 2.4048280715942383}
-03/05/2022 14:37:23 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/05/2022 14:37:28 - INFO - codeparrot_training - Step 41812: {'lr': 0.00041591628535811464, 'samples': 21408256, 'steps': 41812, 'loss/train': 0.7444491386413574}
-03/05/2022 14:37:31 - INFO - codeparrot_training - Step 41813: {'lr': 0.00041591231571782834, 'samples': 21408768, 'steps': 41813, 'loss/train': 2.4078614711761475}
-03/05/2022 14:37:32 - INFO - codeparrot_training - Skipping example with length 385 (seq_length=1024)
-03/05/2022 14:37:36 - INFO - codeparrot_training - Step 41814: {'lr': 0.0004159083460027845, 'samples': 21409280, 'steps': 41814, 'loss/train': 1.0615136623382568}
-03/05/2022 14:37:39 - INFO - codeparrot_training - Step 41815: {'lr': 0.000415904376212985, 'samples': 21409792, 'steps': 41815, 'loss/train': 2.0563478469848633}
-03/05/2022 14:37:40 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/05/2022 14:37:45 - INFO - codeparrot_training - Step 41816: {'lr': 0.00041590040634843144, 'samples': 21410304, 'steps': 41816, 'loss/train': 1.5265034437179565}
-03/05/2022 14:37:48 - INFO - codeparrot_training - Step 41817: {'lr': 0.00041589643640912576, 'samples': 21410816, 'steps': 41817, 'loss/train': 1.957690715789795}
-03/05/2022 14:37:48 - INFO - codeparrot_training - Skipping example with length 449 (seq_length=1024)
-03/05/2022 14:37:53 - INFO - codeparrot_training - Step 41818: {'lr': 0.0004158924663950697, 'samples': 21411328, 'steps': 41818, 'loss/train': 1.9975889921188354}
-03/05/2022 14:37:56 - INFO - codeparrot_training - Step 41819: {'lr': 0.00041588849630626513, 'samples': 21411840, 'steps': 41819, 'loss/train': 1.611990213394165}
-03/05/2022 14:37:57 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/05/2022 14:38:02 - INFO - codeparrot_training - Step 41820: {'lr': 0.00041588452614271364, 'samples': 21412352, 'steps': 41820, 'loss/train': 1.5102938413619995}
-03/05/2022 14:38:06 - INFO - codeparrot_training - Step 41821: {'lr': 0.00041588055590441726, 'samples': 21412864, 'steps': 41821, 'loss/train': 2.0941689014434814}
-03/05/2022 14:38:09 - INFO - codeparrot_training - Step 41822: {'lr': 0.0004158765855913776, 'samples': 21413376, 'steps': 41822, 'loss/train': 1.5637538433074951}
-03/05/2022 14:38:10 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/05/2022 14:38:15 - INFO - codeparrot_training - Step 41823: {'lr': 0.0004158726152035965, 'samples': 21413888, 'steps': 41823, 'loss/train': 0.7294315695762634}
-03/05/2022 14:38:18 - INFO - codeparrot_training - Step 41824: {'lr': 0.00041586864474107575, 'samples': 21414400, 'steps': 41824, 'loss/train': 1.1033635139465332}
-03/05/2022 14:38:20 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 14:38:23 - INFO - codeparrot_training - Step 41825: {'lr': 0.0004158646742038172, 'samples': 21414912, 'steps': 41825, 'loss/train': 0.9787554144859314}
-03/05/2022 14:38:27 - INFO - codeparrot_training - Step 41826: {'lr': 0.00041586070359182255, 'samples': 21415424, 'steps': 41826, 'loss/train': 1.2099827527999878}
-03/05/2022 14:38:29 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 14:38:32 - INFO - codeparrot_training - Step 41827: {'lr': 0.00041585673290509364, 'samples': 21415936, 'steps': 41827, 'loss/train': 1.6371926069259644}
-03/05/2022 14:38:35 - INFO - codeparrot_training - Step 41828: {'lr': 0.0004158527621436322, 'samples': 21416448, 'steps': 41828, 'loss/train': 1.829106092453003}
-03/05/2022 14:38:40 - INFO - codeparrot_training - Step 41829: {'lr': 0.0004158487913074401, 'samples': 21416960, 'steps': 41829, 'loss/train': 1.9899442195892334}
-03/05/2022 14:38:44 - INFO - codeparrot_training - Step 41830: {'lr': 0.0004158448203965192, 'samples': 21417472, 'steps': 41830, 'loss/train': 1.8456447124481201}
-03/05/2022 14:38:46 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/05/2022 14:38:49 - INFO - codeparrot_training - Step 41831: {'lr': 0.000415840849410871, 'samples': 21417984, 'steps': 41831, 'loss/train': 1.6782333850860596}
-03/05/2022 14:38:52 - INFO - codeparrot_training - Step 41832: {'lr': 0.0004158368783504975, 'samples': 21418496, 'steps': 41832, 'loss/train': 1.309798002243042}
-03/05/2022 14:38:57 - INFO - codeparrot_training - Step 41833: {'lr': 0.00041583290721540055, 'samples': 21419008, 'steps': 41833, 'loss/train': 1.317761778831482}
-03/05/2022 14:39:00 - INFO - codeparrot_training - Step 41834: {'lr': 0.0004158289360055819, 'samples': 21419520, 'steps': 41834, 'loss/train': 0.9373942017555237}
-03/05/2022 14:39:02 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 14:39:06 - INFO - codeparrot_training - Step 41835: {'lr': 0.00041582496472104314, 'samples': 21420032, 'steps': 41835, 'loss/train': 1.9994984865188599}
-03/05/2022 14:39:09 - INFO - codeparrot_training - Step 41836: {'lr': 0.0004158209933617863, 'samples': 21420544, 'steps': 41836, 'loss/train': 2.200524091720581}
-03/05/2022 14:39:11 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/05/2022 14:39:14 - INFO - codeparrot_training - Step 41837: {'lr': 0.00041581702192781305, 'samples': 21421056, 'steps': 41837, 'loss/train': 1.1478140354156494}
-03/05/2022 14:39:17 - INFO - codeparrot_training - Step 41838: {'lr': 0.0004158130504191252, 'samples': 21421568, 'steps': 41838, 'loss/train': 2.030184507369995}
-03/05/2022 14:39:19 - INFO - codeparrot_training - Skipping example with length 349 (seq_length=1024)
-03/05/2022 14:39:23 - INFO - codeparrot_training - Step 41839: {'lr': 0.0004158090788357246, 'samples': 21422080, 'steps': 41839, 'loss/train': 1.8791109323501587}
-03/05/2022 14:39:26 - INFO - codeparrot_training - Step 41840: {'lr': 0.0004158051071776129, 'samples': 21422592, 'steps': 41840, 'loss/train': 2.080824375152588}
-03/05/2022 14:39:28 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/05/2022 14:39:31 - INFO - codeparrot_training - Step 41841: {'lr': 0.00041580113544479203, 'samples': 21423104, 'steps': 41841, 'loss/train': 2.2521655559539795}
-03/05/2022 14:39:34 - INFO - codeparrot_training - Step 41842: {'lr': 0.00041579716363726376, 'samples': 21423616, 'steps': 41842, 'loss/train': 1.9264005422592163}
-03/05/2022 14:39:36 - INFO - codeparrot_training - Skipping example with length 989 (seq_length=1024)
-03/05/2022 14:39:40 - INFO - codeparrot_training - Step 41843: {'lr': 0.00041579319175502985, 'samples': 21424128, 'steps': 41843, 'loss/train': 2.2222495079040527}
-03/05/2022 14:39:43 - INFO - codeparrot_training - Step 41844: {'lr': 0.000415789219798092, 'samples': 21424640, 'steps': 41844, 'loss/train': 1.8660755157470703}
-03/05/2022 14:39:45 - INFO - codeparrot_training - Skipping example with length 569 (seq_length=1024)
-03/05/2022 14:39:48 - INFO - codeparrot_training - Step 41845: {'lr': 0.00041578524776645216, 'samples': 21425152, 'steps': 41845, 'loss/train': 1.2696003913879395}
-03/05/2022 14:39:52 - INFO - codeparrot_training - Step 41846: {'lr': 0.00041578127566011203, 'samples': 21425664, 'steps': 41846, 'loss/train': 1.2062631845474243}
-03/05/2022 14:39:53 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/05/2022 14:39:57 - INFO - codeparrot_training - Step 41847: {'lr': 0.0004157773034790734, 'samples': 21426176, 'steps': 41847, 'loss/train': 1.3547146320343018}
-03/05/2022 14:40:00 - INFO - codeparrot_training - Step 41848: {'lr': 0.00041577333122333807, 'samples': 21426688, 'steps': 41848, 'loss/train': 1.6823145151138306}
-03/05/2022 14:40:02 - INFO - codeparrot_training - Skipping example with length 14 (seq_length=1024)
-03/05/2022 14:40:05 - INFO - codeparrot_training - Step 41849: {'lr': 0.00041576935889290777, 'samples': 21427200, 'steps': 41849, 'loss/train': 1.9490214586257935}
-03/05/2022 14:40:08 - INFO - codeparrot_training - Step 41850: {'lr': 0.0004157653864877845, 'samples': 21427712, 'steps': 41850, 'loss/train': 1.75373375415802}
-03/05/2022 14:40:10 - INFO - codeparrot_training - Skipping example with length 211 (seq_length=1024)
-03/05/2022 14:40:14 - INFO - codeparrot_training - Step 41851: {'lr': 0.00041576141400796984, 'samples': 21428224, 'steps': 41851, 'loss/train': 2.088066816329956}
-03/05/2022 14:40:17 - INFO - codeparrot_training - Step 41852: {'lr': 0.00041575744145346563, 'samples': 21428736, 'steps': 41852, 'loss/train': 1.5561072826385498}
-03/05/2022 14:40:18 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/05/2022 14:40:22 - INFO - codeparrot_training - Step 41853: {'lr': 0.00041575346882427366, 'samples': 21429248, 'steps': 41853, 'loss/train': 2.195356845855713}
-03/05/2022 14:40:25 - INFO - codeparrot_training - Step 41854: {'lr': 0.00041574949612039583, 'samples': 21429760, 'steps': 41854, 'loss/train': 1.5174028873443604}
-03/05/2022 14:40:27 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/05/2022 14:40:31 - INFO - codeparrot_training - Step 41855: {'lr': 0.0004157455233418337, 'samples': 21430272, 'steps': 41855, 'loss/train': 1.2785555124282837}
-03/05/2022 14:40:34 - INFO - codeparrot_training - Step 41856: {'lr': 0.0004157415504885893, 'samples': 21430784, 'steps': 41856, 'loss/train': 1.518579363822937}
-03/05/2022 14:40:35 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/05/2022 14:40:39 - INFO - codeparrot_training - Step 41857: {'lr': 0.00041573757756066423, 'samples': 21431296, 'steps': 41857, 'loss/train': 1.6889809370040894}
-03/05/2022 14:40:42 - INFO - codeparrot_training - Step 41858: {'lr': 0.0004157336045580604, 'samples': 21431808, 'steps': 41858, 'loss/train': 1.9305601119995117}
-03/05/2022 14:40:45 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/05/2022 14:40:48 - INFO - codeparrot_training - Step 41859: {'lr': 0.0004157296314807796, 'samples': 21432320, 'steps': 41859, 'loss/train': 1.8745770454406738}
-03/05/2022 14:40:51 - INFO - codeparrot_training - Step 41860: {'lr': 0.0004157256583288235, 'samples': 21432832, 'steps': 41860, 'loss/train': 2.1258575916290283}
-03/05/2022 14:40:53 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/05/2022 14:40:56 - INFO - codeparrot_training - Step 41861: {'lr': 0.0004157216851021941, 'samples': 21433344, 'steps': 41861, 'loss/train': 2.034987211227417}
-03/05/2022 14:40:59 - INFO - codeparrot_training - Step 41862: {'lr': 0.00041571771180089304, 'samples': 21433856, 'steps': 41862, 'loss/train': 1.7405117750167847}
-03/05/2022 14:41:01 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/05/2022 14:41:05 - INFO - codeparrot_training - Step 41863: {'lr': 0.0004157137384249221, 'samples': 21434368, 'steps': 41863, 'loss/train': 1.317883014678955}
-03/05/2022 14:41:08 - INFO - codeparrot_training - Step 41864: {'lr': 0.00041570976497428303, 'samples': 21434880, 'steps': 41864, 'loss/train': 1.5707241296768188}
-03/05/2022 14:41:10 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/05/2022 14:41:13 - INFO - codeparrot_training - Step 41865: {'lr': 0.0004157057914489778, 'samples': 21435392, 'steps': 41865, 'loss/train': 1.3716835975646973}
-03/05/2022 14:41:16 - INFO - codeparrot_training - Step 41866: {'lr': 0.00041570181784900806, 'samples': 21435904, 'steps': 41866, 'loss/train': 0.6493259072303772}
-03/05/2022 14:41:18 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/05/2022 14:41:21 - INFO - codeparrot_training - Step 41867: {'lr': 0.0004156978441743756, 'samples': 21436416, 'steps': 41867, 'loss/train': 1.5787403583526611}
-03/05/2022 14:41:25 - INFO - codeparrot_training - Step 41868: {'lr': 0.00041569387042508235, 'samples': 21436928, 'steps': 41868, 'loss/train': 1.674806833267212}
-03/05/2022 14:41:26 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/05/2022 14:41:30 - INFO - codeparrot_training - Step 41869: {'lr': 0.0004156898966011299, 'samples': 21437440, 'steps': 41869, 'loss/train': 1.9101808071136475}
-03/05/2022 14:41:33 - INFO - codeparrot_training - Step 41870: {'lr': 0.0004156859227025202, 'samples': 21437952, 'steps': 41870, 'loss/train': 2.0147781372070312}
-03/05/2022 14:41:35 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/05/2022 14:41:38 - INFO - codeparrot_training - Step 41871: {'lr': 0.0004156819487292549, 'samples': 21438464, 'steps': 41871, 'loss/train': 1.2760896682739258}
-03/05/2022 14:41:41 - INFO - codeparrot_training - Step 41872: {'lr': 0.00041567797468133595, 'samples': 21438976, 'steps': 41872, 'loss/train': 1.737245798110962}
-03/05/2022 14:41:43 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/05/2022 14:41:47 - INFO - codeparrot_training - Step 41873: {'lr': 0.00041567400055876505, 'samples': 21439488, 'steps': 41873, 'loss/train': 1.7119011878967285}
-03/05/2022 14:41:50 - INFO - codeparrot_training - Step 41874: {'lr': 0.00041567002636154406, 'samples': 21440000, 'steps': 41874, 'loss/train': 1.9952154159545898}
-03/05/2022 14:41:52 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/05/2022 14:41:55 - INFO - codeparrot_training - Step 41875: {'lr': 0.0004156660520896746, 'samples': 21440512, 'steps': 41875, 'loss/train': 1.4254050254821777}
-03/05/2022 14:41:58 - INFO - codeparrot_training - Step 41876: {'lr': 0.00041566207774315866, 'samples': 21441024, 'steps': 41876, 'loss/train': 1.753248691558838}
-03/05/2022 14:42:00 - INFO - codeparrot_training - Skipping example with length 151 (seq_length=1024)
-03/05/2022 14:42:04 - INFO - codeparrot_training - Step 41877: {'lr': 0.0004156581033219979, 'samples': 21441536, 'steps': 41877, 'loss/train': 0.9382883310317993}
-03/05/2022 14:42:07 - INFO - codeparrot_training - Step 41878: {'lr': 0.0004156541288261941, 'samples': 21442048, 'steps': 41878, 'loss/train': 1.8855327367782593}
-03/05/2022 14:42:09 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/05/2022 14:42:12 - INFO - codeparrot_training - Step 41879: {'lr': 0.00041565015425574917, 'samples': 21442560, 'steps': 41879, 'loss/train': 1.7170093059539795}
-03/05/2022 14:42:15 - INFO - codeparrot_training - Step 41880: {'lr': 0.00041564617961066487, 'samples': 21443072, 'steps': 41880, 'loss/train': 2.184828996658325}
-03/05/2022 14:42:18 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 14:42:21 - INFO - codeparrot_training - Step 41881: {'lr': 0.00041564220489094295, 'samples': 21443584, 'steps': 41881, 'loss/train': 1.9496238231658936}
-03/05/2022 14:42:24 - INFO - codeparrot_training - Step 41882: {'lr': 0.00041563823009658514, 'samples': 21444096, 'steps': 41882, 'loss/train': 1.2249605655670166}
-03/05/2022 14:42:26 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/05/2022 14:42:29 - INFO - codeparrot_training - Step 41883: {'lr': 0.00041563425522759336, 'samples': 21444608, 'steps': 41883, 'loss/train': 2.093924045562744}
-03/05/2022 14:42:32 - INFO - codeparrot_training - Step 41884: {'lr': 0.0004156302802839693, 'samples': 21445120, 'steps': 41884, 'loss/train': 2.092982769012451}
-03/05/2022 14:42:34 - INFO - codeparrot_training - Skipping example with length 961 (seq_length=1024)
-03/05/2022 14:42:37 - INFO - codeparrot_training - Step 41885: {'lr': 0.0004156263052657148, 'samples': 21445632, 'steps': 41885, 'loss/train': 0.9450310468673706}
-03/05/2022 14:42:41 - INFO - codeparrot_training - Step 41886: {'lr': 0.0004156223301728316, 'samples': 21446144, 'steps': 41886, 'loss/train': 1.9756571054458618}
-03/05/2022 14:42:43 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 14:42:46 - INFO - codeparrot_training - Step 41887: {'lr': 0.0004156183550053216, 'samples': 21446656, 'steps': 41887, 'loss/train': 1.7126123905181885}
-03/05/2022 14:42:49 - INFO - codeparrot_training - Step 41888: {'lr': 0.0004156143797631866, 'samples': 21447168, 'steps': 41888, 'loss/train': 2.2664036750793457}
-03/05/2022 14:42:51 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/05/2022 14:42:54 - INFO - codeparrot_training - Step 41889: {'lr': 0.0004156104044464282, 'samples': 21447680, 'steps': 41889, 'loss/train': 1.5993738174438477}
-03/05/2022 14:42:58 - INFO - codeparrot_training - Step 41890: {'lr': 0.00041560642905504833, 'samples': 21448192, 'steps': 41890, 'loss/train': 2.0949103832244873}
-03/05/2022 14:43:00 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/05/2022 14:43:03 - INFO - codeparrot_training - Step 41891: {'lr': 0.0004156024535890487, 'samples': 21448704, 'steps': 41891, 'loss/train': 1.7356857061386108}
-03/05/2022 14:43:06 - INFO - codeparrot_training - Step 41892: {'lr': 0.00041559847804843123, 'samples': 21449216, 'steps': 41892, 'loss/train': 1.9027390480041504}
-03/05/2022 14:43:08 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/05/2022 14:43:11 - INFO - codeparrot_training - Step 41893: {'lr': 0.0004155945024331976, 'samples': 21449728, 'steps': 41893, 'loss/train': 2.2333579063415527}
-03/05/2022 14:43:14 - INFO - codeparrot_training - Step 41894: {'lr': 0.00041559052674334975, 'samples': 21450240, 'steps': 41894, 'loss/train': 1.4915028810501099}
-03/05/2022 14:43:16 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/05/2022 14:43:20 - INFO - codeparrot_training - Step 41895: {'lr': 0.0004155865509788893, 'samples': 21450752, 'steps': 41895, 'loss/train': 1.9134665727615356}
-03/05/2022 14:43:23 - INFO - codeparrot_training - Step 41896: {'lr': 0.00041558257513981805, 'samples': 21451264, 'steps': 41896, 'loss/train': 0.9108603000640869}
-03/05/2022 14:43:25 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/05/2022 14:43:28 - INFO - codeparrot_training - Step 41897: {'lr': 0.00041557859922613795, 'samples': 21451776, 'steps': 41897, 'loss/train': 1.8455276489257812}
-03/05/2022 14:43:31 - INFO - codeparrot_training - Step 41898: {'lr': 0.00041557462323785053, 'samples': 21452288, 'steps': 41898, 'loss/train': 1.6030369997024536}
-03/05/2022 14:43:33 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/05/2022 14:43:37 - INFO - codeparrot_training - Step 41899: {'lr': 0.00041557064717495786, 'samples': 21452800, 'steps': 41899, 'loss/train': 1.9511888027191162}
-03/05/2022 14:43:40 - INFO - codeparrot_training - Step 41900: {'lr': 0.00041556667103746157, 'samples': 21453312, 'steps': 41900, 'loss/train': 1.9744770526885986}
-03/05/2022 14:43:42 - INFO - codeparrot_training - Skipping example with length 278 (seq_length=1024)
-03/05/2022 14:43:45 - INFO - codeparrot_training - Step 41901: {'lr': 0.00041556269482536355, 'samples': 21453824, 'steps': 41901, 'loss/train': 1.8551928997039795}
-03/05/2022 14:43:49 - INFO - codeparrot_training - Step 41902: {'lr': 0.00041555871853866553, 'samples': 21454336, 'steps': 41902, 'loss/train': 0.4991138279438019}
-03/05/2022 14:43:51 - INFO - codeparrot_training - Skipping example with length 725 (seq_length=1024)
-03/05/2022 14:43:54 - INFO - codeparrot_training - Step 41903: {'lr': 0.00041555474217736926, 'samples': 21454848, 'steps': 41903, 'loss/train': 1.8484559059143066}
-03/05/2022 14:43:57 - INFO - codeparrot_training - Step 41904: {'lr': 0.0004155507657414766, 'samples': 21455360, 'steps': 41904, 'loss/train': 0.9804142117500305}
-03/05/2022 14:43:59 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/05/2022 14:44:02 - INFO - codeparrot_training - Step 41905: {'lr': 0.0004155467892309893, 'samples': 21455872, 'steps': 41905, 'loss/train': 2.7782599925994873}
-03/05/2022 14:44:05 - INFO - codeparrot_training - Step 41906: {'lr': 0.0004155428126459092, 'samples': 21456384, 'steps': 41906, 'loss/train': 2.0531554222106934}
-03/05/2022 14:44:08 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/05/2022 14:44:11 - INFO - codeparrot_training - Step 41907: {'lr': 0.00041553883598623804, 'samples': 21456896, 'steps': 41907, 'loss/train': 1.6811994314193726}
-03/05/2022 14:44:14 - INFO - codeparrot_training - Step 41908: {'lr': 0.00041553485925197763, 'samples': 21457408, 'steps': 41908, 'loss/train': 2.1421356201171875}
-03/05/2022 14:44:16 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/05/2022 14:44:19 - INFO - codeparrot_training - Step 41909: {'lr': 0.00041553088244312975, 'samples': 21457920, 'steps': 41909, 'loss/train': 1.6446198225021362}
-03/05/2022 14:44:22 - INFO - codeparrot_training - Step 41910: {'lr': 0.0004155269055596963, 'samples': 21458432, 'steps': 41910, 'loss/train': 1.1300580501556396}
-03/05/2022 14:44:25 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 14:44:28 - INFO - codeparrot_training - Step 41911: {'lr': 0.0004155229286016789, 'samples': 21458944, 'steps': 41911, 'loss/train': 2.0153722763061523}
-03/05/2022 14:44:31 - INFO - codeparrot_training - Step 41912: {'lr': 0.0004155189515690794, 'samples': 21459456, 'steps': 41912, 'loss/train': 2.7276649475097656}
-03/05/2022 14:44:34 - INFO - codeparrot_training - Step 41913: {'lr': 0.0004155149744618997, 'samples': 21459968, 'steps': 41913, 'loss/train': 1.6332619190216064}
-03/05/2022 14:44:35 - INFO - codeparrot_training - Skipping example with length 1022 (seq_length=1024)
-03/05/2022 14:44:40 - INFO - codeparrot_training - Step 41914: {'lr': 0.0004155109972801414, 'samples': 21460480, 'steps': 41914, 'loss/train': 1.3162097930908203}
-03/05/2022 14:44:43 - INFO - codeparrot_training - Step 41915: {'lr': 0.0004155070200238065, 'samples': 21460992, 'steps': 41915, 'loss/train': 2.081064224243164}
-03/05/2022 14:44:44 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/05/2022 14:44:48 - INFO - codeparrot_training - Step 41916: {'lr': 0.00041550304269289664, 'samples': 21461504, 'steps': 41916, 'loss/train': 1.428346872329712}
-03/05/2022 14:44:51 - INFO - codeparrot_training - Step 41917: {'lr': 0.00041549906528741366, 'samples': 21462016, 'steps': 41917, 'loss/train': 1.9242680072784424}
-03/05/2022 14:44:52 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/05/2022 14:44:56 - INFO - codeparrot_training - Step 41918: {'lr': 0.0004154950878073594, 'samples': 21462528, 'steps': 41918, 'loss/train': 1.1793553829193115}
-03/05/2022 14:45:00 - INFO - codeparrot_training - Step 41919: {'lr': 0.0004154911102527356, 'samples': 21463040, 'steps': 41919, 'loss/train': 1.7504701614379883}
-03/05/2022 14:45:01 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 14:45:05 - INFO - codeparrot_training - Step 41920: {'lr': 0.00041548713262354396, 'samples': 21463552, 'steps': 41920, 'loss/train': 1.810105562210083}
-03/05/2022 14:45:08 - INFO - codeparrot_training - Step 41921: {'lr': 0.0004154831549197865, 'samples': 21464064, 'steps': 41921, 'loss/train': 1.8996647596359253}
-03/05/2022 14:45:09 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 14:45:13 - INFO - codeparrot_training - Step 41922: {'lr': 0.0004154791771414648, 'samples': 21464576, 'steps': 41922, 'loss/train': 1.3253934383392334}
-03/05/2022 14:45:16 - INFO - codeparrot_training - Step 41923: {'lr': 0.0004154751992885808, 'samples': 21465088, 'steps': 41923, 'loss/train': 0.605379045009613}
-03/05/2022 14:45:18 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/05/2022 14:45:22 - INFO - codeparrot_training - Step 41924: {'lr': 0.0004154712213611362, 'samples': 21465600, 'steps': 41924, 'loss/train': 2.161938190460205}
-03/05/2022 14:45:25 - INFO - codeparrot_training - Step 41925: {'lr': 0.0004154672433591328, 'samples': 21466112, 'steps': 41925, 'loss/train': 1.6911333799362183}
-03/05/2022 14:45:26 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/05/2022 14:45:30 - INFO - codeparrot_training - Step 41926: {'lr': 0.0004154632652825724, 'samples': 21466624, 'steps': 41926, 'loss/train': 1.5501492023468018}
-03/05/2022 14:45:33 - INFO - codeparrot_training - Step 41927: {'lr': 0.00041545928713145687, 'samples': 21467136, 'steps': 41927, 'loss/train': 1.6769646406173706}
-03/05/2022 14:45:34 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/05/2022 14:45:39 - INFO - codeparrot_training - Step 41928: {'lr': 0.00041545530890578784, 'samples': 21467648, 'steps': 41928, 'loss/train': 1.3389497995376587}
-03/05/2022 14:45:42 - INFO - codeparrot_training - Step 41929: {'lr': 0.00041545133060556734, 'samples': 21468160, 'steps': 41929, 'loss/train': 2.020487070083618}
-03/05/2022 14:45:43 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/05/2022 14:45:47 - INFO - codeparrot_training - Step 41930: {'lr': 0.00041544735223079693, 'samples': 21468672, 'steps': 41930, 'loss/train': 1.678605556488037}
-03/05/2022 14:45:50 - INFO - codeparrot_training - Step 41931: {'lr': 0.0004154433737814786, 'samples': 21469184, 'steps': 41931, 'loss/train': 2.1452643871307373}
-03/05/2022 14:45:51 - INFO - codeparrot_training - Skipping example with length 377 (seq_length=1024)
-03/05/2022 14:45:56 - INFO - codeparrot_training - Step 41932: {'lr': 0.0004154393952576139, 'samples': 21469696, 'steps': 41932, 'loss/train': 0.8944704532623291}
-03/05/2022 14:45:59 - INFO - codeparrot_training - Step 41933: {'lr': 0.00041543541665920483, 'samples': 21470208, 'steps': 41933, 'loss/train': 1.9454741477966309}
-03/05/2022 14:45:59 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 14:46:04 - INFO - codeparrot_training - Step 41934: {'lr': 0.000415431437986253, 'samples': 21470720, 'steps': 41934, 'loss/train': 0.7341524362564087}
-03/05/2022 14:46:07 - INFO - codeparrot_training - Step 41935: {'lr': 0.00041542745923876047, 'samples': 21471232, 'steps': 41935, 'loss/train': 2.078669548034668}
-03/05/2022 14:46:08 - INFO - codeparrot_training - Skipping example with length 871 (seq_length=1024)
-03/05/2022 14:46:13 - INFO - codeparrot_training - Step 41936: {'lr': 0.00041542348041672886, 'samples': 21471744, 'steps': 41936, 'loss/train': 1.673399806022644}
-03/05/2022 14:46:16 - INFO - codeparrot_training - Step 41937: {'lr': 0.00041541950152015997, 'samples': 21472256, 'steps': 41937, 'loss/train': 1.8219189643859863}
-03/05/2022 14:46:17 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/05/2022 14:46:21 - INFO - codeparrot_training - Step 41938: {'lr': 0.0004154155225490555, 'samples': 21472768, 'steps': 41938, 'loss/train': 1.7975094318389893}
-03/05/2022 14:46:25 - INFO - codeparrot_training - Step 41939: {'lr': 0.0004154115435034175, 'samples': 21473280, 'steps': 41939, 'loss/train': 1.9789531230926514}
-03/05/2022 14:46:25 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/05/2022 14:46:30 - INFO - codeparrot_training - Step 41940: {'lr': 0.00041540756438324746, 'samples': 21473792, 'steps': 41940, 'loss/train': 1.5022308826446533}
-03/05/2022 14:46:33 - INFO - codeparrot_training - Step 41941: {'lr': 0.0004154035851885474, 'samples': 21474304, 'steps': 41941, 'loss/train': 2.125880479812622}
-03/05/2022 14:46:33 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/05/2022 14:46:38 - INFO - codeparrot_training - Step 41942: {'lr': 0.0004153996059193191, 'samples': 21474816, 'steps': 41942, 'loss/train': 0.9406452775001526}
-03/05/2022 14:46:41 - INFO - codeparrot_training - Step 41943: {'lr': 0.0004153956265755642, 'samples': 21475328, 'steps': 41943, 'loss/train': 1.2609305381774902}
-03/05/2022 14:46:42 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/05/2022 14:46:47 - INFO - codeparrot_training - Step 41944: {'lr': 0.0004153916471572846, 'samples': 21475840, 'steps': 41944, 'loss/train': 1.358726978302002}
-03/05/2022 14:46:50 - INFO - codeparrot_training - Step 41945: {'lr': 0.0004153876676644821, 'samples': 21476352, 'steps': 41945, 'loss/train': 1.6648014783859253}
-03/05/2022 14:46:50 - INFO - codeparrot_training - Skipping example with length 312 (seq_length=1024)
-03/05/2022 14:46:55 - INFO - codeparrot_training - Step 41946: {'lr': 0.0004153836880971585, 'samples': 21476864, 'steps': 41946, 'loss/train': 2.037508010864258}
-03/05/2022 14:46:58 - INFO - codeparrot_training - Step 41947: {'lr': 0.00041537970845531547, 'samples': 21477376, 'steps': 41947, 'loss/train': 1.153216004371643}
-03/05/2022 14:46:58 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/05/2022 14:47:04 - INFO - codeparrot_training - Step 41948: {'lr': 0.00041537572873895503, 'samples': 21477888, 'steps': 41948, 'loss/train': 1.9245078563690186}
-03/05/2022 14:47:07 - INFO - codeparrot_training - Step 41949: {'lr': 0.00041537174894807873, 'samples': 21478400, 'steps': 41949, 'loss/train': 1.961256980895996}
-03/05/2022 14:47:07 - INFO - codeparrot_training - Skipping example with length 981 (seq_length=1024)
-03/05/2022 14:47:12 - INFO - codeparrot_training - Step 41950: {'lr': 0.00041536776908268847, 'samples': 21478912, 'steps': 41950, 'loss/train': 1.362103819847107}
-03/05/2022 14:47:15 - INFO - codeparrot_training - Step 41951: {'lr': 0.00041536378914278603, 'samples': 21479424, 'steps': 41951, 'loss/train': 1.4469531774520874}
-03/05/2022 14:47:16 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/05/2022 14:47:21 - INFO - codeparrot_training - Step 41952: {'lr': 0.00041535980912837326, 'samples': 21479936, 'steps': 41952, 'loss/train': 1.94516122341156}
-03/05/2022 14:47:24 - INFO - codeparrot_training - Step 41953: {'lr': 0.00041535582903945195, 'samples': 21480448, 'steps': 41953, 'loss/train': 2.380267858505249}
-03/05/2022 14:47:26 - INFO - codeparrot_training - Skipping example with length 168 (seq_length=1024)
-03/05/2022 14:47:30 - INFO - codeparrot_training - Step 41954: {'lr': 0.00041535184887602384, 'samples': 21480960, 'steps': 41954, 'loss/train': 0.20756934583187103}
-03/05/2022 14:47:33 - INFO - codeparrot_training - Step 41955: {'lr': 0.0004153478686380907, 'samples': 21481472, 'steps': 41955, 'loss/train': 1.5236746072769165}
-03/05/2022 14:47:35 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 14:47:38 - INFO - codeparrot_training - Step 41956: {'lr': 0.0004153438883256544, 'samples': 21481984, 'steps': 41956, 'loss/train': 0.1346697211265564}
-03/05/2022 14:47:41 - INFO - codeparrot_training - Step 41957: {'lr': 0.0004153399079387167, 'samples': 21482496, 'steps': 41957, 'loss/train': 1.7919999361038208}
-03/05/2022 14:47:43 - INFO - codeparrot_training - Skipping example with length 700 (seq_length=1024)
-03/05/2022 14:47:47 - INFO - codeparrot_training - Step 41958: {'lr': 0.00041533592747727935, 'samples': 21483008, 'steps': 41958, 'loss/train': 0.8220410943031311}
-03/05/2022 14:47:50 - INFO - codeparrot_training - Step 41959: {'lr': 0.00041533194694134414, 'samples': 21483520, 'steps': 41959, 'loss/train': 1.867111325263977}
-03/05/2022 14:47:52 - INFO - codeparrot_training - Skipping example with length 456 (seq_length=1024)
-03/05/2022 14:47:55 - INFO - codeparrot_training - Step 41960: {'lr': 0.00041532796633091297, 'samples': 21484032, 'steps': 41960, 'loss/train': 1.4246114492416382}
-03/05/2022 14:47:58 - INFO - codeparrot_training - Step 41961: {'lr': 0.00041532398564598757, 'samples': 21484544, 'steps': 41961, 'loss/train': 1.5380758047103882}
-03/05/2022 14:48:03 - INFO - codeparrot_training - Step 41962: {'lr': 0.0004153200048865697, 'samples': 21485056, 'steps': 41962, 'loss/train': 1.9092661142349243}
-03/05/2022 14:48:07 - INFO - codeparrot_training - Step 41963: {'lr': 0.0004153160240526612, 'samples': 21485568, 'steps': 41963, 'loss/train': 1.5522388219833374}
-03/05/2022 14:48:08 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/05/2022 14:48:12 - INFO - codeparrot_training - Step 41964: {'lr': 0.0004153120431442639, 'samples': 21486080, 'steps': 41964, 'loss/train': 0.9297754764556885}
-03/05/2022 14:48:15 - INFO - codeparrot_training - Step 41965: {'lr': 0.00041530806216137953, 'samples': 21486592, 'steps': 41965, 'loss/train': 2.274245500564575}
-03/05/2022 14:48:17 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/05/2022 14:48:20 - INFO - codeparrot_training - Step 41966: {'lr': 0.00041530408110400987, 'samples': 21487104, 'steps': 41966, 'loss/train': 2.160557270050049}
-03/05/2022 14:48:24 - INFO - codeparrot_training - Step 41967: {'lr': 0.00041530009997215665, 'samples': 21487616, 'steps': 41967, 'loss/train': 1.7717862129211426}
-03/05/2022 14:48:25 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 14:48:29 - INFO - codeparrot_training - Step 41968: {'lr': 0.00041529611876582194, 'samples': 21488128, 'steps': 41968, 'loss/train': 0.5135242342948914}
-03/05/2022 14:48:32 - INFO - codeparrot_training - Step 41969: {'lr': 0.00041529213748500726, 'samples': 21488640, 'steps': 41969, 'loss/train': 1.598252773284912}
-03/05/2022 14:48:33 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/05/2022 14:48:37 - INFO - codeparrot_training - Step 41970: {'lr': 0.0004152881561297145, 'samples': 21489152, 'steps': 41970, 'loss/train': 1.3704453706741333}
-03/05/2022 14:48:40 - INFO - codeparrot_training - Step 41971: {'lr': 0.0004152841746999454, 'samples': 21489664, 'steps': 41971, 'loss/train': 1.2177729606628418}
-03/05/2022 14:48:42 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 14:48:46 - INFO - codeparrot_training - Step 41972: {'lr': 0.00041528019319570186, 'samples': 21490176, 'steps': 41972, 'loss/train': 1.7277165651321411}
-03/05/2022 14:48:49 - INFO - codeparrot_training - Step 41973: {'lr': 0.0004152762116169856, 'samples': 21490688, 'steps': 41973, 'loss/train': 1.5947171449661255}
-03/05/2022 14:48:50 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/05/2022 14:48:54 - INFO - codeparrot_training - Step 41974: {'lr': 0.00041527222996379844, 'samples': 21491200, 'steps': 41974, 'loss/train': 1.3216217756271362}
-03/05/2022 14:48:57 - INFO - codeparrot_training - Step 41975: {'lr': 0.0004152682482361422, 'samples': 21491712, 'steps': 41975, 'loss/train': 0.9165134429931641}
-03/05/2022 14:48:59 - INFO - codeparrot_training - Skipping example with length 30 (seq_length=1024)
-03/05/2022 14:49:03 - INFO - codeparrot_training - Step 41976: {'lr': 0.0004152642664340185, 'samples': 21492224, 'steps': 41976, 'loss/train': 1.774726390838623}
-03/05/2022 14:49:06 - INFO - codeparrot_training - Step 41977: {'lr': 0.00041526028455742936, 'samples': 21492736, 'steps': 41977, 'loss/train': 1.277857780456543}
-03/05/2022 14:49:07 - INFO - codeparrot_training - Skipping example with length 969 (seq_length=1024)
-03/05/2022 14:49:11 - INFO - codeparrot_training - Step 41978: {'lr': 0.0004152563026063765, 'samples': 21493248, 'steps': 41978, 'loss/train': 1.992783546447754}
-03/05/2022 14:49:14 - INFO - codeparrot_training - Step 41979: {'lr': 0.00041525232058086173, 'samples': 21493760, 'steps': 41979, 'loss/train': 1.623078465461731}
-03/05/2022 14:49:15 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/05/2022 14:49:19 - INFO - codeparrot_training - Step 41980: {'lr': 0.0004152483384808867, 'samples': 21494272, 'steps': 41980, 'loss/train': 1.3448256254196167}
-03/05/2022 14:49:23 - INFO - codeparrot_training - Step 41981: {'lr': 0.0004152443563064534, 'samples': 21494784, 'steps': 41981, 'loss/train': 2.280818223953247}
-03/05/2022 14:49:24 - INFO - codeparrot_training - Skipping example with length 206 (seq_length=1024)
-03/05/2022 14:49:28 - INFO - codeparrot_training - Step 41982: {'lr': 0.00041524037405756356, 'samples': 21495296, 'steps': 41982, 'loss/train': 1.3301358222961426}
-03/05/2022 14:49:31 - INFO - codeparrot_training - Step 41983: {'lr': 0.0004152363917342189, 'samples': 21495808, 'steps': 41983, 'loss/train': 2.0409293174743652}
-03/05/2022 14:49:32 - INFO - codeparrot_training - Skipping example with length 581 (seq_length=1024)
-03/05/2022 14:49:36 - INFO - codeparrot_training - Step 41984: {'lr': 0.00041523240933642134, 'samples': 21496320, 'steps': 41984, 'loss/train': 1.4239026308059692}
-03/05/2022 14:49:39 - INFO - codeparrot_training - Step 41985: {'lr': 0.00041522842686417255, 'samples': 21496832, 'steps': 41985, 'loss/train': 2.484879970550537}
-03/05/2022 14:49:40 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/05/2022 14:49:45 - INFO - codeparrot_training - Step 41986: {'lr': 0.0004152244443174744, 'samples': 21497344, 'steps': 41986, 'loss/train': 1.1105756759643555}
-03/05/2022 14:49:48 - INFO - codeparrot_training - Step 41987: {'lr': 0.00041522046169632863, 'samples': 21497856, 'steps': 41987, 'loss/train': 1.0515499114990234}
-03/05/2022 14:49:49 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/05/2022 14:49:53 - INFO - codeparrot_training - Step 41988: {'lr': 0.0004152164790007371, 'samples': 21498368, 'steps': 41988, 'loss/train': 1.947210669517517}
-03/05/2022 14:49:57 - INFO - codeparrot_training - Step 41989: {'lr': 0.00041521249623070164, 'samples': 21498880, 'steps': 41989, 'loss/train': 1.5896849632263184}
-03/05/2022 14:49:58 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/05/2022 14:50:02 - INFO - codeparrot_training - Step 41990: {'lr': 0.0004152085133862239, 'samples': 21499392, 'steps': 41990, 'loss/train': 1.2735093832015991}
-03/05/2022 14:50:05 - INFO - codeparrot_training - Step 41991: {'lr': 0.0004152045304673058, 'samples': 21499904, 'steps': 41991, 'loss/train': 2.0329272747039795}
-03/05/2022 14:50:07 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/05/2022 14:50:10 - INFO - codeparrot_training - Step 41992: {'lr': 0.000415200547473949, 'samples': 21500416, 'steps': 41992, 'loss/train': 1.4904472827911377}
-03/05/2022 14:50:14 - INFO - codeparrot_training - Step 41993: {'lr': 0.00041519656440615544, 'samples': 21500928, 'steps': 41993, 'loss/train': 1.9958611726760864}
-03/05/2022 14:50:19 - INFO - codeparrot_training - Step 41994: {'lr': 0.00041519258126392685, 'samples': 21501440, 'steps': 41994, 'loss/train': 1.702273964881897}
-03/05/2022 14:50:22 - INFO - codeparrot_training - Step 41995: {'lr': 0.00041518859804726507, 'samples': 21501952, 'steps': 41995, 'loss/train': 1.5724694728851318}
-03/05/2022 14:50:24 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/05/2022 14:50:27 - INFO - codeparrot_training - Step 41996: {'lr': 0.00041518461475617183, 'samples': 21502464, 'steps': 41996, 'loss/train': 1.521433711051941}
-03/05/2022 14:50:30 - INFO - codeparrot_training - Step 41997: {'lr': 0.00041518063139064893, 'samples': 21502976, 'steps': 41997, 'loss/train': 1.8104257583618164}
-03/05/2022 14:50:32 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/05/2022 14:50:36 - INFO - codeparrot_training - Step 41998: {'lr': 0.0004151766479506982, 'samples': 21503488, 'steps': 41998, 'loss/train': 1.3721625804901123}
-03/05/2022 14:50:39 - INFO - codeparrot_training - Step 41999: {'lr': 0.0004151726644363214, 'samples': 21504000, 'steps': 41999, 'loss/train': 1.5022848844528198}
-03/05/2022 14:50:40 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 14:50:44 - INFO - codeparrot_training - Step 42000: {'lr': 0.00041516868084752034, 'samples': 21504512, 'steps': 42000, 'loss/train': 0.782934308052063}
-03/05/2022 14:50:47 - INFO - codeparrot_training - Step 42001: {'lr': 0.0004151646971842968, 'samples': 21505024, 'steps': 42001, 'loss/train': 1.9118019342422485}
-03/05/2022 14:50:49 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/05/2022 14:50:53 - INFO - codeparrot_training - Step 42002: {'lr': 0.00041516071344665275, 'samples': 21505536, 'steps': 42002, 'loss/train': 1.37834894657135}
-03/05/2022 14:50:56 - INFO - codeparrot_training - Step 42003: {'lr': 0.00041515672963458975, 'samples': 21506048, 'steps': 42003, 'loss/train': 1.1964386701583862}
-03/05/2022 14:50:57 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/05/2022 14:51:01 - INFO - codeparrot_training - Step 42004: {'lr': 0.00041515274574810965, 'samples': 21506560, 'steps': 42004, 'loss/train': 1.7944586277008057}
-03/05/2022 14:51:04 - INFO - codeparrot_training - Step 42005: {'lr': 0.00041514876178721426, 'samples': 21507072, 'steps': 42005, 'loss/train': 2.1848740577697754}
-03/05/2022 14:51:05 - INFO - codeparrot_training - Skipping example with length 762 (seq_length=1024)
-03/05/2022 14:51:09 - INFO - codeparrot_training - Step 42006: {'lr': 0.0004151447777519054, 'samples': 21507584, 'steps': 42006, 'loss/train': 1.1487326622009277}
-03/05/2022 14:51:13 - INFO - codeparrot_training - Step 42007: {'lr': 0.00041514079364218483, 'samples': 21508096, 'steps': 42007, 'loss/train': 1.5687570571899414}
-03/05/2022 14:51:14 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/05/2022 14:51:18 - INFO - codeparrot_training - Step 42008: {'lr': 0.0004151368094580544, 'samples': 21508608, 'steps': 42008, 'loss/train': 1.2744157314300537}
-03/05/2022 14:51:21 - INFO - codeparrot_training - Step 42009: {'lr': 0.0004151328251995159, 'samples': 21509120, 'steps': 42009, 'loss/train': 1.4255388975143433}
-03/05/2022 14:51:22 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/05/2022 14:51:26 - INFO - codeparrot_training - Step 42010: {'lr': 0.000415128840866571, 'samples': 21509632, 'steps': 42010, 'loss/train': 1.8352463245391846}
-03/05/2022 14:51:29 - INFO - codeparrot_training - Step 42011: {'lr': 0.00041512485645922164, 'samples': 21510144, 'steps': 42011, 'loss/train': 1.9540470838546753}
-03/05/2022 14:51:30 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 14:51:35 - INFO - codeparrot_training - Step 42012: {'lr': 0.0004151208719774696, 'samples': 21510656, 'steps': 42012, 'loss/train': 1.5386552810668945}
-03/05/2022 14:51:38 - INFO - codeparrot_training - Step 42013: {'lr': 0.0004151168874213166, 'samples': 21511168, 'steps': 42013, 'loss/train': 1.5359935760498047}
-03/05/2022 14:51:39 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 14:51:43 - INFO - codeparrot_training - Step 42014: {'lr': 0.00041511290279076454, 'samples': 21511680, 'steps': 42014, 'loss/train': 1.3552520275115967}
-03/05/2022 14:51:46 - INFO - codeparrot_training - Step 42015: {'lr': 0.0004151089180858151, 'samples': 21512192, 'steps': 42015, 'loss/train': 1.8658593893051147}
-03/05/2022 14:51:47 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/05/2022 14:51:52 - INFO - codeparrot_training - Step 42016: {'lr': 0.00041510493330647015, 'samples': 21512704, 'steps': 42016, 'loss/train': 1.6373051404953003}
-03/05/2022 14:51:55 - INFO - codeparrot_training - Step 42017: {'lr': 0.00041510094845273145, 'samples': 21513216, 'steps': 42017, 'loss/train': 0.26720091700553894}
-03/05/2022 14:51:56 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/05/2022 14:52:00 - INFO - codeparrot_training - Step 42018: {'lr': 0.0004150969635246008, 'samples': 21513728, 'steps': 42018, 'loss/train': 1.9831372499465942}
-03/05/2022 14:52:03 - INFO - codeparrot_training - Step 42019: {'lr': 0.00041509297852208003, 'samples': 21514240, 'steps': 42019, 'loss/train': 2.0508909225463867}
-03/05/2022 14:52:04 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 14:52:08 - INFO - codeparrot_training - Step 42020: {'lr': 0.00041508899344517094, 'samples': 21514752, 'steps': 42020, 'loss/train': 1.0435205698013306}
-03/05/2022 14:52:12 - INFO - codeparrot_training - Step 42021: {'lr': 0.0004150850082938752, 'samples': 21515264, 'steps': 42021, 'loss/train': 1.9576176404953003}
-03/05/2022 14:52:13 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/05/2022 14:52:17 - INFO - codeparrot_training - Step 42022: {'lr': 0.00041508102306819485, 'samples': 21515776, 'steps': 42022, 'loss/train': 1.3505452871322632}
-03/05/2022 14:52:20 - INFO - codeparrot_training - Step 42023: {'lr': 0.0004150770377681314, 'samples': 21516288, 'steps': 42023, 'loss/train': 1.9806123971939087}
-03/05/2022 14:52:21 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/05/2022 14:52:25 - INFO - codeparrot_training - Step 42024: {'lr': 0.00041507305239368684, 'samples': 21516800, 'steps': 42024, 'loss/train': 1.8587054014205933}
-03/05/2022 14:52:29 - INFO - codeparrot_training - Step 42025: {'lr': 0.0004150690669448629, 'samples': 21517312, 'steps': 42025, 'loss/train': 1.7816216945648193}
-03/05/2022 14:52:30 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/05/2022 14:52:34 - INFO - codeparrot_training - Step 42026: {'lr': 0.0004150650814216614, 'samples': 21517824, 'steps': 42026, 'loss/train': 1.8048359155654907}
-03/05/2022 14:52:37 - INFO - codeparrot_training - Step 42027: {'lr': 0.0004150610958240841, 'samples': 21518336, 'steps': 42027, 'loss/train': 1.8063660860061646}
-03/05/2022 14:52:38 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/05/2022 14:52:42 - INFO - codeparrot_training - Step 42028: {'lr': 0.00041505711015213284, 'samples': 21518848, 'steps': 42028, 'loss/train': 1.8965425491333008}
-03/05/2022 14:52:45 - INFO - codeparrot_training - Step 42029: {'lr': 0.0004150531244058094, 'samples': 21519360, 'steps': 42029, 'loss/train': 0.8695423603057861}
-03/05/2022 14:52:47 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/05/2022 14:52:52 - INFO - codeparrot_training - Step 42030: {'lr': 0.00041504913858511557, 'samples': 21519872, 'steps': 42030, 'loss/train': 1.3530279397964478}
-03/05/2022 14:52:55 - INFO - codeparrot_training - Step 42031: {'lr': 0.0004150451526900531, 'samples': 21520384, 'steps': 42031, 'loss/train': 2.1479485034942627}
-03/05/2022 14:52:58 - INFO - codeparrot_training - Step 42032: {'lr': 0.00041504116672062385, 'samples': 21520896, 'steps': 42032, 'loss/train': 2.1182901859283447}
-03/05/2022 14:52:59 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/05/2022 14:53:03 - INFO - codeparrot_training - Step 42033: {'lr': 0.0004150371806768296, 'samples': 21521408, 'steps': 42033, 'loss/train': 1.4731667041778564}
-03/05/2022 14:53:07 - INFO - codeparrot_training - Step 42034: {'lr': 0.00041503319455867216, 'samples': 21521920, 'steps': 42034, 'loss/train': 1.693225383758545}
-03/05/2022 14:53:08 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/05/2022 14:53:12 - INFO - codeparrot_training - Step 42035: {'lr': 0.0004150292083661533, 'samples': 21522432, 'steps': 42035, 'loss/train': 1.3553967475891113}
-03/05/2022 14:53:15 - INFO - codeparrot_training - Step 42036: {'lr': 0.00041502522209927486, 'samples': 21522944, 'steps': 42036, 'loss/train': 0.8308656215667725}
-03/05/2022 14:53:16 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/05/2022 14:53:20 - INFO - codeparrot_training - Step 42037: {'lr': 0.00041502123575803854, 'samples': 21523456, 'steps': 42037, 'loss/train': 0.8688053488731384}
-03/05/2022 14:53:23 - INFO - codeparrot_training - Step 42038: {'lr': 0.0004150172493424462, 'samples': 21523968, 'steps': 42038, 'loss/train': 1.7066411972045898}
-03/05/2022 14:53:25 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/05/2022 14:53:29 - INFO - codeparrot_training - Step 42039: {'lr': 0.00041501326285249963, 'samples': 21524480, 'steps': 42039, 'loss/train': 1.7727299928665161}
-03/05/2022 14:53:32 - INFO - codeparrot_training - Step 42040: {'lr': 0.0004150092762882007, 'samples': 21524992, 'steps': 42040, 'loss/train': 1.7361472845077515}
-03/05/2022 14:53:33 - INFO - codeparrot_training - Skipping example with length 229 (seq_length=1024)
-03/05/2022 14:53:37 - INFO - codeparrot_training - Step 42041: {'lr': 0.00041500528964955106, 'samples': 21525504, 'steps': 42041, 'loss/train': 1.919515609741211}
-03/05/2022 14:53:40 - INFO - codeparrot_training - Step 42042: {'lr': 0.0004150013029365527, 'samples': 21526016, 'steps': 42042, 'loss/train': 1.616940975189209}
-03/05/2022 14:53:42 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/05/2022 14:53:46 - INFO - codeparrot_training - Step 42043: {'lr': 0.0004149973161492072, 'samples': 21526528, 'steps': 42043, 'loss/train': 2.092857599258423}
-03/05/2022 14:53:49 - INFO - codeparrot_training - Step 42044: {'lr': 0.0004149933292875164, 'samples': 21527040, 'steps': 42044, 'loss/train': 1.5048235654830933}
-03/05/2022 14:53:50 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/05/2022 14:53:54 - INFO - codeparrot_training - Step 42045: {'lr': 0.0004149893423514822, 'samples': 21527552, 'steps': 42045, 'loss/train': 2.0605039596557617}
-03/05/2022 14:53:57 - INFO - codeparrot_training - Step 42046: {'lr': 0.0004149853553411064, 'samples': 21528064, 'steps': 42046, 'loss/train': 1.8431795835494995}
-03/05/2022 14:53:59 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/05/2022 14:54:03 - INFO - codeparrot_training - Step 42047: {'lr': 0.00041498136825639074, 'samples': 21528576, 'steps': 42047, 'loss/train': 3.7218387126922607}
-03/05/2022 14:54:06 - INFO - codeparrot_training - Step 42048: {'lr': 0.000414977381097337, 'samples': 21529088, 'steps': 42048, 'loss/train': 1.8772724866867065}
-03/05/2022 14:54:08 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/05/2022 14:54:11 - INFO - codeparrot_training - Step 42049: {'lr': 0.000414973393863947, 'samples': 21529600, 'steps': 42049, 'loss/train': 0.6850914359092712}
-03/05/2022 14:54:14 - INFO - codeparrot_training - Step 42050: {'lr': 0.0004149694065562225, 'samples': 21530112, 'steps': 42050, 'loss/train': 1.278337836265564}
-03/05/2022 14:54:16 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/05/2022 14:54:20 - INFO - codeparrot_training - Step 42051: {'lr': 0.0004149654191741654, 'samples': 21530624, 'steps': 42051, 'loss/train': 2.21501088142395}
-03/05/2022 14:54:23 - INFO - codeparrot_training - Step 42052: {'lr': 0.0004149614317177774, 'samples': 21531136, 'steps': 42052, 'loss/train': 0.9838099479675293}
-03/05/2022 14:54:25 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 14:54:28 - INFO - codeparrot_training - Step 42053: {'lr': 0.00041495744418706027, 'samples': 21531648, 'steps': 42053, 'loss/train': 1.9907677173614502}
-03/05/2022 14:54:31 - INFO - codeparrot_training - Step 42054: {'lr': 0.00041495345658201587, 'samples': 21532160, 'steps': 42054, 'loss/train': 2.186314344406128}
-03/05/2022 14:54:34 - INFO - codeparrot_training - Skipping example with length 328 (seq_length=1024)
-03/05/2022 14:54:36 - INFO - codeparrot_training - Step 42055: {'lr': 0.00041494946890264606, 'samples': 21532672, 'steps': 42055, 'loss/train': 1.5653327703475952}
-03/05/2022 14:54:40 - INFO - codeparrot_training - Step 42056: {'lr': 0.00041494548114895255, 'samples': 21533184, 'steps': 42056, 'loss/train': 1.6992850303649902}
-03/05/2022 14:54:42 - INFO - codeparrot_training - Skipping example with length 98 (seq_length=1024)
-03/05/2022 14:54:45 - INFO - codeparrot_training - Step 42057: {'lr': 0.0004149414933209371, 'samples': 21533696, 'steps': 42057, 'loss/train': 1.2012659311294556}
-03/05/2022 14:54:48 - INFO - codeparrot_training - Step 42058: {'lr': 0.00041493750541860165, 'samples': 21534208, 'steps': 42058, 'loss/train': 2.228527307510376}
-03/05/2022 14:54:50 - INFO - codeparrot_training - Skipping example with length 501 (seq_length=1024)
-03/05/2022 14:54:53 - INFO - codeparrot_training - Step 42059: {'lr': 0.0004149335174419478, 'samples': 21534720, 'steps': 42059, 'loss/train': 2.387204647064209}
-03/05/2022 14:54:57 - INFO - codeparrot_training - Step 42060: {'lr': 0.0004149295293909775, 'samples': 21535232, 'steps': 42060, 'loss/train': 0.8602176904678345}
-03/05/2022 14:54:59 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 14:55:02 - INFO - codeparrot_training - Step 42061: {'lr': 0.0004149255412656925, 'samples': 21535744, 'steps': 42061, 'loss/train': 1.6675893068313599}
-03/05/2022 14:55:05 - INFO - codeparrot_training - Step 42062: {'lr': 0.00041492155306609456, 'samples': 21536256, 'steps': 42062, 'loss/train': 1.0316429138183594}
-03/05/2022 14:55:07 - INFO - codeparrot_training - Skipping example with length 601 (seq_length=1024)
-03/05/2022 14:55:10 - INFO - codeparrot_training - Step 42063: {'lr': 0.00041491756479218557, 'samples': 21536768, 'steps': 42063, 'loss/train': 2.1301400661468506}
-03/05/2022 14:55:13 - INFO - codeparrot_training - Step 42064: {'lr': 0.0004149135764439672, 'samples': 21537280, 'steps': 42064, 'loss/train': 1.7208446264266968}
-03/05/2022 14:55:16 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/05/2022 14:55:19 - INFO - codeparrot_training - Step 42065: {'lr': 0.0004149095880214414, 'samples': 21537792, 'steps': 42065, 'loss/train': 2.187117099761963}
-03/05/2022 14:55:22 - INFO - codeparrot_training - Step 42066: {'lr': 0.00041490559952460983, 'samples': 21538304, 'steps': 42066, 'loss/train': 1.6324983835220337}
-03/05/2022 14:55:24 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/05/2022 14:55:27 - INFO - codeparrot_training - Step 42067: {'lr': 0.00041490161095347435, 'samples': 21538816, 'steps': 42067, 'loss/train': 1.099818229675293}
-03/05/2022 14:55:30 - INFO - codeparrot_training - Step 42068: {'lr': 0.00041489762230803676, 'samples': 21539328, 'steps': 42068, 'loss/train': 1.5437949895858765}
-03/05/2022 14:55:32 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 14:55:36 - INFO - codeparrot_training - Step 42069: {'lr': 0.00041489363358829885, 'samples': 21539840, 'steps': 42069, 'loss/train': 2.0456976890563965}
-03/05/2022 14:55:39 - INFO - codeparrot_training - Step 42070: {'lr': 0.0004148896447942624, 'samples': 21540352, 'steps': 42070, 'loss/train': 1.3459950685501099}
-03/05/2022 14:55:41 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/05/2022 14:55:44 - INFO - codeparrot_training - Step 42071: {'lr': 0.00041488565592592917, 'samples': 21540864, 'steps': 42071, 'loss/train': 1.543218970298767}
-03/05/2022 14:55:47 - INFO - codeparrot_training - Step 42072: {'lr': 0.0004148816669833011, 'samples': 21541376, 'steps': 42072, 'loss/train': 1.985239028930664}
-03/05/2022 14:55:50 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 14:55:53 - INFO - codeparrot_training - Step 42073: {'lr': 0.0004148776779663799, 'samples': 21541888, 'steps': 42073, 'loss/train': 1.9976308345794678}
-03/05/2022 14:55:56 - INFO - codeparrot_training - Step 42074: {'lr': 0.00041487368887516726, 'samples': 21542400, 'steps': 42074, 'loss/train': 0.9212955832481384}
-03/05/2022 14:55:58 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/05/2022 14:56:01 - INFO - codeparrot_training - Step 42075: {'lr': 0.00041486969970966516, 'samples': 21542912, 'steps': 42075, 'loss/train': 2.4219183921813965}
-03/05/2022 14:56:04 - INFO - codeparrot_training - Step 42076: {'lr': 0.0004148657104698753, 'samples': 21543424, 'steps': 42076, 'loss/train': 2.0075337886810303}
-03/05/2022 14:56:06 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/05/2022 14:56:09 - INFO - codeparrot_training - Step 42077: {'lr': 0.00041486172115579945, 'samples': 21543936, 'steps': 42077, 'loss/train': 2.4029383659362793}
-03/05/2022 14:56:13 - INFO - codeparrot_training - Step 42078: {'lr': 0.00041485773176743953, 'samples': 21544448, 'steps': 42078, 'loss/train': 1.6762781143188477}
-03/05/2022 14:56:14 - INFO - codeparrot_training - Skipping example with length 590 (seq_length=1024)
-03/05/2022 14:56:18 - INFO - codeparrot_training - Step 42079: {'lr': 0.00041485374230479724, 'samples': 21544960, 'steps': 42079, 'loss/train': 1.6409190893173218}
-03/05/2022 14:56:21 - INFO - codeparrot_training - Step 42080: {'lr': 0.00041484975276787436, 'samples': 21545472, 'steps': 42080, 'loss/train': 1.5761291980743408}
-03/05/2022 14:56:23 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/05/2022 14:56:26 - INFO - codeparrot_training - Step 42081: {'lr': 0.00041484576315667273, 'samples': 21545984, 'steps': 42081, 'loss/train': 2.3278465270996094}
-03/05/2022 14:56:30 - INFO - codeparrot_training - Step 42082: {'lr': 0.0004148417734711941, 'samples': 21546496, 'steps': 42082, 'loss/train': 2.618222951889038}
-03/05/2022 14:56:31 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 14:56:35 - INFO - codeparrot_training - Step 42083: {'lr': 0.00041483778371144046, 'samples': 21547008, 'steps': 42083, 'loss/train': 1.4391281604766846}
-03/05/2022 14:56:38 - INFO - codeparrot_training - Step 42084: {'lr': 0.0004148337938774134, 'samples': 21547520, 'steps': 42084, 'loss/train': 1.605188012123108}
-03/05/2022 14:56:40 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/05/2022 14:56:43 - INFO - codeparrot_training - Step 42085: {'lr': 0.00041482980396911467, 'samples': 21548032, 'steps': 42085, 'loss/train': 1.8894951343536377}
-03/05/2022 14:56:46 - INFO - codeparrot_training - Step 42086: {'lr': 0.0004148258139865463, 'samples': 21548544, 'steps': 42086, 'loss/train': 0.9633037447929382}
-03/05/2022 14:56:48 - INFO - codeparrot_training - Skipping example with length 413 (seq_length=1024)
-03/05/2022 14:56:52 - INFO - codeparrot_training - Step 42087: {'lr': 0.00041482182392970984, 'samples': 21549056, 'steps': 42087, 'loss/train': 1.5174708366394043}
-03/05/2022 14:56:55 - INFO - codeparrot_training - Step 42088: {'lr': 0.00041481783379860725, 'samples': 21549568, 'steps': 42088, 'loss/train': 2.1999340057373047}
-03/05/2022 14:56:56 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/05/2022 14:57:00 - INFO - codeparrot_training - Step 42089: {'lr': 0.0004148138435932404, 'samples': 21550080, 'steps': 42089, 'loss/train': 1.4440360069274902}
-03/05/2022 14:57:03 - INFO - codeparrot_training - Step 42090: {'lr': 0.0004148098533136109, 'samples': 21550592, 'steps': 42090, 'loss/train': 1.475509524345398}
-03/05/2022 14:57:04 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/05/2022 14:57:08 - INFO - codeparrot_training - Step 42091: {'lr': 0.0004148058629597206, 'samples': 21551104, 'steps': 42091, 'loss/train': 1.8951443433761597}
-03/05/2022 14:57:12 - INFO - codeparrot_training - Step 42092: {'lr': 0.0004148018725315713, 'samples': 21551616, 'steps': 42092, 'loss/train': 1.9706394672393799}
-03/05/2022 14:57:13 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/05/2022 14:57:17 - INFO - codeparrot_training - Step 42093: {'lr': 0.00041479788202916483, 'samples': 21552128, 'steps': 42093, 'loss/train': 2.485860824584961}
-03/05/2022 14:57:20 - INFO - codeparrot_training - Step 42094: {'lr': 0.000414793891452503, 'samples': 21552640, 'steps': 42094, 'loss/train': 1.9755384922027588}
-03/05/2022 14:57:21 - INFO - codeparrot_training - Skipping example with length 179 (seq_length=1024)
-03/05/2022 14:57:26 - INFO - codeparrot_training - Step 42095: {'lr': 0.0004147899008015876, 'samples': 21553152, 'steps': 42095, 'loss/train': 1.1846425533294678}
-03/05/2022 14:57:29 - INFO - codeparrot_training - Step 42096: {'lr': 0.0004147859100764204, 'samples': 21553664, 'steps': 42096, 'loss/train': 0.8696861267089844}
-03/05/2022 14:57:30 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/05/2022 14:57:34 - INFO - codeparrot_training - Step 42097: {'lr': 0.0004147819192770033, 'samples': 21554176, 'steps': 42097, 'loss/train': 1.20148766040802}
-03/05/2022 14:57:37 - INFO - codeparrot_training - Step 42098: {'lr': 0.00041477792840333784, 'samples': 21554688, 'steps': 42098, 'loss/train': 0.758374035358429}
-03/05/2022 14:57:38 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/05/2022 14:57:42 - INFO - codeparrot_training - Step 42099: {'lr': 0.00041477393745542607, 'samples': 21555200, 'steps': 42099, 'loss/train': 1.9731801748275757}
-03/05/2022 14:57:46 - INFO - codeparrot_training - Step 42100: {'lr': 0.0004147699464332697, 'samples': 21555712, 'steps': 42100, 'loss/train': 1.5502268075942993}
-03/05/2022 14:57:46 - INFO - codeparrot_training - Skipping example with length 204 (seq_length=1024)
-03/05/2022 14:57:51 - INFO - codeparrot_training - Step 42101: {'lr': 0.0004147659553368706, 'samples': 21556224, 'steps': 42101, 'loss/train': 1.6663472652435303}
-03/05/2022 14:57:54 - INFO - codeparrot_training - Step 42102: {'lr': 0.00041476196416623034, 'samples': 21556736, 'steps': 42102, 'loss/train': 1.4499937295913696}
-03/05/2022 14:57:55 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/05/2022 14:57:59 - INFO - codeparrot_training - Step 42103: {'lr': 0.0004147579729213511, 'samples': 21557248, 'steps': 42103, 'loss/train': 1.2467914819717407}
-03/05/2022 14:58:02 - INFO - codeparrot_training - Step 42104: {'lr': 0.0004147539816022343, 'samples': 21557760, 'steps': 42104, 'loss/train': 1.895998239517212}
-03/05/2022 14:58:03 - INFO - codeparrot_training - Skipping example with length 771 (seq_length=1024)
-03/05/2022 14:58:08 - INFO - codeparrot_training - Step 42105: {'lr': 0.0004147499902088819, 'samples': 21558272, 'steps': 42105, 'loss/train': 2.1228394508361816}
-03/05/2022 14:58:11 - INFO - codeparrot_training - Step 42106: {'lr': 0.0004147459987412958, 'samples': 21558784, 'steps': 42106, 'loss/train': 1.549649953842163}
-03/05/2022 14:58:12 - INFO - codeparrot_training - Skipping example with length 246 (seq_length=1024)
-03/05/2022 14:58:16 - INFO - codeparrot_training - Step 42107: {'lr': 0.0004147420071994776, 'samples': 21559296, 'steps': 42107, 'loss/train': 2.282243251800537}
-03/05/2022 14:58:19 - INFO - codeparrot_training - Step 42108: {'lr': 0.0004147380155834293, 'samples': 21559808, 'steps': 42108, 'loss/train': 1.3776910305023193}
-03/05/2022 14:58:21 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/05/2022 14:58:25 - INFO - codeparrot_training - Step 42109: {'lr': 0.0004147340238931525, 'samples': 21560320, 'steps': 42109, 'loss/train': 1.4800078868865967}
-03/05/2022 14:58:28 - INFO - codeparrot_training - Step 42110: {'lr': 0.0004147300321286491, 'samples': 21560832, 'steps': 42110, 'loss/train': 1.5184056758880615}
-03/05/2022 14:58:29 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 14:58:33 - INFO - codeparrot_training - Step 42111: {'lr': 0.0004147260402899209, 'samples': 21561344, 'steps': 42111, 'loss/train': 1.6459730863571167}
-03/05/2022 14:58:37 - INFO - codeparrot_training - Step 42112: {'lr': 0.0004147220483769697, 'samples': 21561856, 'steps': 42112, 'loss/train': 1.7488583326339722}
-03/05/2022 14:58:38 - INFO - codeparrot_training - Skipping example with length 906 (seq_length=1024)
-03/05/2022 14:58:42 - INFO - codeparrot_training - Step 42113: {'lr': 0.0004147180563897972, 'samples': 21562368, 'steps': 42113, 'loss/train': 1.497232437133789}
-03/05/2022 14:58:45 - INFO - codeparrot_training - Step 42114: {'lr': 0.0004147140643284054, 'samples': 21562880, 'steps': 42114, 'loss/train': 2.525475263595581}
-03/05/2022 14:58:46 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/05/2022 14:58:50 - INFO - codeparrot_training - Step 42115: {'lr': 0.00041471007219279595, 'samples': 21563392, 'steps': 42115, 'loss/train': 1.702001929283142}
-03/05/2022 14:58:53 - INFO - codeparrot_training - Step 42116: {'lr': 0.0004147060799829707, 'samples': 21563904, 'steps': 42116, 'loss/train': 1.9059182405471802}
-03/05/2022 14:58:54 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 14:58:59 - INFO - codeparrot_training - Step 42117: {'lr': 0.00041470208769893137, 'samples': 21564416, 'steps': 42117, 'loss/train': 1.6902800798416138}
-03/05/2022 14:59:02 - INFO - codeparrot_training - Step 42118: {'lr': 0.0004146980953406799, 'samples': 21564928, 'steps': 42118, 'loss/train': 1.4078137874603271}
-03/05/2022 14:59:07 - INFO - codeparrot_training - Step 42119: {'lr': 0.000414694102908218, 'samples': 21565440, 'steps': 42119, 'loss/train': 1.4370009899139404}
-03/05/2022 14:59:10 - INFO - codeparrot_training - Step 42120: {'lr': 0.0004146901104015474, 'samples': 21565952, 'steps': 42120, 'loss/train': 1.9531177282333374}
-03/05/2022 14:59:11 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/05/2022 14:59:16 - INFO - codeparrot_training - Step 42121: {'lr': 0.00041468611782067, 'samples': 21566464, 'steps': 42121, 'loss/train': 1.8331111669540405}
-03/05/2022 14:59:19 - INFO - codeparrot_training - Step 42122: {'lr': 0.0004146821251655877, 'samples': 21566976, 'steps': 42122, 'loss/train': 1.7453663349151611}
-03/05/2022 14:59:19 - INFO - codeparrot_training - Skipping example with length 191 (seq_length=1024)
-03/05/2022 14:59:24 - INFO - codeparrot_training - Step 42123: {'lr': 0.000414678132436302, 'samples': 21567488, 'steps': 42123, 'loss/train': 1.587219476699829}
-03/05/2022 14:59:27 - INFO - codeparrot_training - Step 42124: {'lr': 0.000414674139632815, 'samples': 21568000, 'steps': 42124, 'loss/train': 1.8458361625671387}
-03/05/2022 14:59:28 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 14:59:32 - INFO - codeparrot_training - Step 42125: {'lr': 0.0004146701467551283, 'samples': 21568512, 'steps': 42125, 'loss/train': 0.7398783564567566}
-03/05/2022 14:59:36 - INFO - codeparrot_training - Step 42126: {'lr': 0.0004146661538032438, 'samples': 21569024, 'steps': 42126, 'loss/train': 1.2402812242507935}
-03/05/2022 14:59:36 - INFO - codeparrot_training - Skipping example with length 996 (seq_length=1024)
-03/05/2022 14:59:41 - INFO - codeparrot_training - Step 42127: {'lr': 0.0004146621607771633, 'samples': 21569536, 'steps': 42127, 'loss/train': 1.9953598976135254}
-03/05/2022 14:59:44 - INFO - codeparrot_training - Step 42128: {'lr': 0.00041465816767688853, 'samples': 21570048, 'steps': 42128, 'loss/train': 2.205073356628418}
-03/05/2022 14:59:44 - INFO - codeparrot_training - Skipping example with length 823 (seq_length=1024)
-03/05/2022 14:59:49 - INFO - codeparrot_training - Step 42129: {'lr': 0.0004146541745024214, 'samples': 21570560, 'steps': 42129, 'loss/train': 1.6233755350112915}
-03/05/2022 14:59:53 - INFO - codeparrot_training - Step 42130: {'lr': 0.00041465018125376354, 'samples': 21571072, 'steps': 42130, 'loss/train': 2.0043537616729736}
-03/05/2022 14:59:53 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/05/2022 14:59:58 - INFO - codeparrot_training - Step 42131: {'lr': 0.0004146461879309169, 'samples': 21571584, 'steps': 42131, 'loss/train': 1.492004632949829}
-03/05/2022 15:00:01 - INFO - codeparrot_training - Step 42132: {'lr': 0.0004146421945338832, 'samples': 21572096, 'steps': 42132, 'loss/train': 1.0547499656677246}
-03/05/2022 15:00:02 - INFO - codeparrot_training - Skipping example with length 801 (seq_length=1024)
-03/05/2022 15:00:07 - INFO - codeparrot_training - Step 42133: {'lr': 0.0004146382010626643, 'samples': 21572608, 'steps': 42133, 'loss/train': 1.4061479568481445}
-03/05/2022 15:00:10 - INFO - codeparrot_training - Step 42134: {'lr': 0.000414634207517262, 'samples': 21573120, 'steps': 42134, 'loss/train': 1.1031289100646973}
-03/05/2022 15:00:11 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/05/2022 15:00:15 - INFO - codeparrot_training - Step 42135: {'lr': 0.000414630213897678, 'samples': 21573632, 'steps': 42135, 'loss/train': 0.7073723077774048}
-03/05/2022 15:00:18 - INFO - codeparrot_training - Step 42136: {'lr': 0.00041462622020391416, 'samples': 21574144, 'steps': 42136, 'loss/train': 1.6221882104873657}
-03/05/2022 15:00:19 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/05/2022 15:00:24 - INFO - codeparrot_training - Step 42137: {'lr': 0.00041462222643597236, 'samples': 21574656, 'steps': 42137, 'loss/train': 1.655709981918335}
-03/05/2022 15:00:27 - INFO - codeparrot_training - Step 42138: {'lr': 0.00041461823259385423, 'samples': 21575168, 'steps': 42138, 'loss/train': 2.076871395111084}
-03/05/2022 15:00:28 - INFO - codeparrot_training - Skipping example with length 112 (seq_length=1024)
-03/05/2022 15:00:32 - INFO - codeparrot_training - Step 42139: {'lr': 0.00041461423867756176, 'samples': 21575680, 'steps': 42139, 'loss/train': 2.403907299041748}
-03/05/2022 15:00:35 - INFO - codeparrot_training - Step 42140: {'lr': 0.00041461024468709664, 'samples': 21576192, 'steps': 42140, 'loss/train': 1.0964268445968628}
-03/05/2022 15:00:36 - INFO - codeparrot_training - Skipping example with length 624 (seq_length=1024)
-03/05/2022 15:00:41 - INFO - codeparrot_training - Step 42141: {'lr': 0.0004146062506224606, 'samples': 21576704, 'steps': 42141, 'loss/train': 2.1374969482421875}
-03/05/2022 15:00:44 - INFO - codeparrot_training - Step 42142: {'lr': 0.0004146022564836556, 'samples': 21577216, 'steps': 42142, 'loss/train': 2.103226661682129}
-03/05/2022 15:00:45 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/05/2022 15:00:49 - INFO - codeparrot_training - Step 42143: {'lr': 0.0004145982622706833, 'samples': 21577728, 'steps': 42143, 'loss/train': 0.655133843421936}
-03/05/2022 15:00:52 - INFO - codeparrot_training - Step 42144: {'lr': 0.00041459426798354563, 'samples': 21578240, 'steps': 42144, 'loss/train': 1.4235546588897705}
-03/05/2022 15:00:53 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/05/2022 15:00:57 - INFO - codeparrot_training - Step 42145: {'lr': 0.00041459027362224433, 'samples': 21578752, 'steps': 42145, 'loss/train': 1.1091488599777222}
-03/05/2022 15:01:01 - INFO - codeparrot_training - Step 42146: {'lr': 0.00041458627918678116, 'samples': 21579264, 'steps': 42146, 'loss/train': 1.28324556350708}
-03/05/2022 15:01:02 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 15:01:06 - INFO - codeparrot_training - Step 42147: {'lr': 0.00041458228467715786, 'samples': 21579776, 'steps': 42147, 'loss/train': 1.0475341081619263}
-03/05/2022 15:01:09 - INFO - codeparrot_training - Step 42148: {'lr': 0.00041457829009337643, 'samples': 21580288, 'steps': 42148, 'loss/train': 1.8122377395629883}
-03/05/2022 15:01:10 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/05/2022 15:01:14 - INFO - codeparrot_training - Step 42149: {'lr': 0.00041457429543543856, 'samples': 21580800, 'steps': 42149, 'loss/train': 0.7676851153373718}
-03/05/2022 15:01:18 - INFO - codeparrot_training - Step 42150: {'lr': 0.0004145703007033461, 'samples': 21581312, 'steps': 42150, 'loss/train': 1.8544318675994873}
-03/05/2022 15:01:19 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/05/2022 15:01:23 - INFO - codeparrot_training - Step 42151: {'lr': 0.00041456630589710073, 'samples': 21581824, 'steps': 42151, 'loss/train': 2.0541646480560303}
-03/05/2022 15:01:26 - INFO - codeparrot_training - Step 42152: {'lr': 0.0004145623110167043, 'samples': 21582336, 'steps': 42152, 'loss/train': 0.6513358354568481}
-03/05/2022 15:01:28 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/05/2022 15:01:31 - INFO - codeparrot_training - Step 42153: {'lr': 0.00041455831606215863, 'samples': 21582848, 'steps': 42153, 'loss/train': 1.680469274520874}
-03/05/2022 15:01:35 - INFO - codeparrot_training - Step 42154: {'lr': 0.0004145543210334656, 'samples': 21583360, 'steps': 42154, 'loss/train': 1.857198715209961}
-03/05/2022 15:01:36 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/05/2022 15:01:40 - INFO - codeparrot_training - Step 42155: {'lr': 0.00041455032593062685, 'samples': 21583872, 'steps': 42155, 'loss/train': 2.1395299434661865}
-03/05/2022 15:01:43 - INFO - codeparrot_training - Step 42156: {'lr': 0.00041454633075364427, 'samples': 21584384, 'steps': 42156, 'loss/train': 1.8817479610443115}
-03/05/2022 15:01:44 - INFO - codeparrot_training - Skipping example with length 55 (seq_length=1024)
-03/05/2022 15:01:48 - INFO - codeparrot_training - Step 42157: {'lr': 0.00041454233550251976, 'samples': 21584896, 'steps': 42157, 'loss/train': 1.0926960706710815}
-03/05/2022 15:01:51 - INFO - codeparrot_training - Step 42158: {'lr': 0.0004145383401772549, 'samples': 21585408, 'steps': 42158, 'loss/train': 1.6872514486312866}
-03/05/2022 15:01:52 - INFO - codeparrot_training - Skipping example with length 707 (seq_length=1024)
-03/05/2022 15:01:57 - INFO - codeparrot_training - Step 42159: {'lr': 0.00041453434477785165, 'samples': 21585920, 'steps': 42159, 'loss/train': 1.102889895439148}
-03/05/2022 15:02:00 - INFO - codeparrot_training - Step 42160: {'lr': 0.0004145303493043118, 'samples': 21586432, 'steps': 42160, 'loss/train': 1.8617645502090454}
-03/05/2022 15:02:01 - INFO - codeparrot_training - Skipping example with length 708 (seq_length=1024)
-03/05/2022 15:02:05 - INFO - codeparrot_training - Step 42161: {'lr': 0.000414526353756637, 'samples': 21586944, 'steps': 42161, 'loss/train': 2.0461184978485107}
-03/05/2022 15:02:08 - INFO - codeparrot_training - Step 42162: {'lr': 0.0004145223581348292, 'samples': 21587456, 'steps': 42162, 'loss/train': 0.9375805258750916}
-03/05/2022 15:02:09 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/05/2022 15:02:13 - INFO - codeparrot_training - Step 42163: {'lr': 0.00041451836243889027, 'samples': 21587968, 'steps': 42163, 'loss/train': 1.5858362913131714}
-03/05/2022 15:02:17 - INFO - codeparrot_training - Step 42164: {'lr': 0.0004145143666688218, 'samples': 21588480, 'steps': 42164, 'loss/train': 1.484890341758728}
-03/05/2022 15:02:17 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/05/2022 15:02:22 - INFO - codeparrot_training - Step 42165: {'lr': 0.0004145103708246257, 'samples': 21588992, 'steps': 42165, 'loss/train': 2.3167335987091064}
-03/05/2022 15:02:25 - INFO - codeparrot_training - Step 42166: {'lr': 0.0004145063749063038, 'samples': 21589504, 'steps': 42166, 'loss/train': 1.8873045444488525}
-03/05/2022 15:02:26 - INFO - codeparrot_training - Skipping example with length 849 (seq_length=1024)
-03/05/2022 15:02:31 - INFO - codeparrot_training - Step 42167: {'lr': 0.00041450237891385783, 'samples': 21590016, 'steps': 42167, 'loss/train': 2.0730371475219727}
-03/05/2022 15:02:34 - INFO - codeparrot_training - Step 42168: {'lr': 0.00041449838284728964, 'samples': 21590528, 'steps': 42168, 'loss/train': 2.154503345489502}
-03/05/2022 15:02:35 - INFO - codeparrot_training - Skipping example with length 366 (seq_length=1024)
-03/05/2022 15:02:39 - INFO - codeparrot_training - Step 42169: {'lr': 0.000414494386706601, 'samples': 21591040, 'steps': 42169, 'loss/train': 1.163810133934021}
-03/05/2022 15:02:42 - INFO - codeparrot_training - Step 42170: {'lr': 0.00041449039049179385, 'samples': 21591552, 'steps': 42170, 'loss/train': 2.304111957550049}
-03/05/2022 15:02:44 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/05/2022 15:02:47 - INFO - codeparrot_training - Step 42171: {'lr': 0.0004144863942028697, 'samples': 21592064, 'steps': 42171, 'loss/train': 1.1101733446121216}
-03/05/2022 15:02:51 - INFO - codeparrot_training - Step 42172: {'lr': 0.0004144823978398306, 'samples': 21592576, 'steps': 42172, 'loss/train': 1.6818877458572388}
-03/05/2022 15:02:52 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/05/2022 15:02:56 - INFO - codeparrot_training - Step 42173: {'lr': 0.0004144784014026782, 'samples': 21593088, 'steps': 42173, 'loss/train': 1.3978164196014404}
-03/05/2022 15:02:59 - INFO - codeparrot_training - Step 42174: {'lr': 0.0004144744048914145, 'samples': 21593600, 'steps': 42174, 'loss/train': 1.677324891090393}
-03/05/2022 15:03:00 - INFO - codeparrot_training - Skipping example with length 824 (seq_length=1024)
-03/05/2022 15:03:04 - INFO - codeparrot_training - Step 42175: {'lr': 0.0004144704083060411, 'samples': 21594112, 'steps': 42175, 'loss/train': 2.514826536178589}
-03/05/2022 15:03:08 - INFO - codeparrot_training - Step 42176: {'lr': 0.00041446641164655983, 'samples': 21594624, 'steps': 42176, 'loss/train': 1.5027203559875488}
-03/05/2022 15:03:08 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 15:03:13 - INFO - codeparrot_training - Step 42177: {'lr': 0.0004144624149129727, 'samples': 21595136, 'steps': 42177, 'loss/train': 1.678390622138977}
-03/05/2022 15:03:16 - INFO - codeparrot_training - Step 42178: {'lr': 0.00041445841810528117, 'samples': 21595648, 'steps': 42178, 'loss/train': 1.3233743906021118}
-03/05/2022 15:03:17 - INFO - codeparrot_training - Skipping example with length 384 (seq_length=1024)
-03/05/2022 15:03:21 - INFO - codeparrot_training - Step 42179: {'lr': 0.00041445442122348727, 'samples': 21596160, 'steps': 42179, 'loss/train': 1.9203853607177734}
-03/05/2022 15:03:24 - INFO - codeparrot_training - Step 42180: {'lr': 0.0004144504242675927, 'samples': 21596672, 'steps': 42180, 'loss/train': 1.6320512294769287}
-03/05/2022 15:03:25 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/05/2022 15:03:30 - INFO - codeparrot_training - Step 42181: {'lr': 0.0004144464272375994, 'samples': 21597184, 'steps': 42181, 'loss/train': 2.415912389755249}
-03/05/2022 15:03:33 - INFO - codeparrot_training - Step 42182: {'lr': 0.000414442430133509, 'samples': 21597696, 'steps': 42182, 'loss/train': 0.9352185130119324}
-03/05/2022 15:03:34 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/05/2022 15:03:38 - INFO - codeparrot_training - Step 42183: {'lr': 0.00041443843295532333, 'samples': 21598208, 'steps': 42183, 'loss/train': 1.8543468713760376}
-03/05/2022 15:03:42 - INFO - codeparrot_training - Step 42184: {'lr': 0.0004144344357030444, 'samples': 21598720, 'steps': 42184, 'loss/train': 1.773468255996704}
-03/05/2022 15:03:47 - INFO - codeparrot_training - Step 42185: {'lr': 0.0004144304383766737, 'samples': 21599232, 'steps': 42185, 'loss/train': 1.5729092359542847}
-03/05/2022 15:03:50 - INFO - codeparrot_training - Step 42186: {'lr': 0.0004144264409762133, 'samples': 21599744, 'steps': 42186, 'loss/train': 1.443477988243103}
-03/05/2022 15:03:52 - INFO - codeparrot_training - Skipping example with length 611 (seq_length=1024)
-03/05/2022 15:03:55 - INFO - codeparrot_training - Step 42187: {'lr': 0.0004144224435016648, 'samples': 21600256, 'steps': 42187, 'loss/train': 2.096717596054077}
-03/05/2022 15:03:59 - INFO - codeparrot_training - Step 42188: {'lr': 0.00041441844595303015, 'samples': 21600768, 'steps': 42188, 'loss/train': 0.817893922328949}
-03/05/2022 15:04:01 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/05/2022 15:04:04 - INFO - codeparrot_training - Step 42189: {'lr': 0.0004144144483303111, 'samples': 21601280, 'steps': 42189, 'loss/train': 1.8398594856262207}
-03/05/2022 15:04:07 - INFO - codeparrot_training - Step 42190: {'lr': 0.00041441045063350933, 'samples': 21601792, 'steps': 42190, 'loss/train': 1.8738045692443848}
-03/05/2022 15:04:10 - INFO - codeparrot_training - Skipping example with length 701 (seq_length=1024)
-03/05/2022 15:04:12 - INFO - codeparrot_training - Step 42191: {'lr': 0.00041440645286262677, 'samples': 21602304, 'steps': 42191, 'loss/train': 1.6132060289382935}
-03/05/2022 15:04:16 - INFO - codeparrot_training - Step 42192: {'lr': 0.0004144024550176653, 'samples': 21602816, 'steps': 42192, 'loss/train': 2.137815475463867}
-03/05/2022 15:04:19 - INFO - codeparrot_training - Step 42193: {'lr': 0.0004143984570986265, 'samples': 21603328, 'steps': 42193, 'loss/train': 2.0393776893615723}
-03/05/2022 15:04:19 - INFO - codeparrot_training - Skipping example with length 666 (seq_length=1024)
-03/05/2022 15:04:24 - INFO - codeparrot_training - Step 42194: {'lr': 0.00041439445910551235, 'samples': 21603840, 'steps': 42194, 'loss/train': 2.115001916885376}
-03/05/2022 15:04:28 - INFO - codeparrot_training - Step 42195: {'lr': 0.00041439046103832454, 'samples': 21604352, 'steps': 42195, 'loss/train': 0.20712223649024963}
-03/05/2022 15:04:28 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/05/2022 15:04:33 - INFO - codeparrot_training - Step 42196: {'lr': 0.000414386462897065, 'samples': 21604864, 'steps': 42196, 'loss/train': 1.6035618782043457}
-03/05/2022 15:04:36 - INFO - codeparrot_training - Step 42197: {'lr': 0.00041438246468173545, 'samples': 21605376, 'steps': 42197, 'loss/train': 1.017578125}
-03/05/2022 15:04:36 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 15:04:41 - INFO - codeparrot_training - Step 42198: {'lr': 0.0004143784663923377, 'samples': 21605888, 'steps': 42198, 'loss/train': 0.3560017943382263}
-03/05/2022 15:04:44 - INFO - codeparrot_training - Step 42199: {'lr': 0.00041437446802887354, 'samples': 21606400, 'steps': 42199, 'loss/train': 1.8241307735443115}
-03/05/2022 15:04:45 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/05/2022 15:04:50 - INFO - codeparrot_training - Step 42200: {'lr': 0.0004143704695913447, 'samples': 21606912, 'steps': 42200, 'loss/train': 1.0067501068115234}
-03/05/2022 15:04:53 - INFO - codeparrot_training - Step 42201: {'lr': 0.0004143664710797531, 'samples': 21607424, 'steps': 42201, 'loss/train': 2.0237298011779785}
-03/05/2022 15:04:53 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/05/2022 15:04:58 - INFO - codeparrot_training - Step 42202: {'lr': 0.0004143624724941006, 'samples': 21607936, 'steps': 42202, 'loss/train': 1.914589524269104}
-03/05/2022 15:05:01 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/05/2022 15:05:04 - INFO - codeparrot_training - Step 42203: {'lr': 0.00041435847383438886, 'samples': 21608448, 'steps': 42203, 'loss/train': 1.348642110824585}
-03/05/2022 15:05:07 - INFO - codeparrot_training - Step 42204: {'lr': 0.0004143544751006197, 'samples': 21608960, 'steps': 42204, 'loss/train': 1.5692260265350342}
-03/05/2022 15:05:10 - INFO - codeparrot_training - Skipping example with length 116 (seq_length=1024)
-03/05/2022 15:05:12 - INFO - codeparrot_training - Step 42205: {'lr': 0.000414350476292795, 'samples': 21609472, 'steps': 42205, 'loss/train': 2.01166033744812}
-03/05/2022 15:05:15 - INFO - codeparrot_training - Step 42206: {'lr': 0.0004143464774109164, 'samples': 21609984, 'steps': 42206, 'loss/train': 1.4153409004211426}
-03/05/2022 15:05:21 - INFO - codeparrot_training - Step 42207: {'lr': 0.0004143424784549859, 'samples': 21610496, 'steps': 42207, 'loss/train': 0.9907054901123047}
-03/05/2022 15:05:24 - INFO - codeparrot_training - Step 42208: {'lr': 0.00041433847942500516, 'samples': 21611008, 'steps': 42208, 'loss/train': 1.9480186700820923}
-03/05/2022 15:05:27 - INFO - codeparrot_training - Step 42209: {'lr': 0.0004143344803209761, 'samples': 21611520, 'steps': 42209, 'loss/train': 0.7840176820755005}
-03/05/2022 15:05:28 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/05/2022 15:05:32 - INFO - codeparrot_training - Step 42210: {'lr': 0.0004143304811429005, 'samples': 21612032, 'steps': 42210, 'loss/train': 1.0992892980575562}
-03/05/2022 15:05:36 - INFO - codeparrot_training - Step 42211: {'lr': 0.00041432648189078006, 'samples': 21612544, 'steps': 42211, 'loss/train': 2.0092458724975586}
-03/05/2022 15:05:37 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/05/2022 15:05:41 - INFO - codeparrot_training - Step 42212: {'lr': 0.0004143224825646166, 'samples': 21613056, 'steps': 42212, 'loss/train': 2.1416375637054443}
-03/05/2022 15:05:44 - INFO - codeparrot_training - Step 42213: {'lr': 0.000414318483164412, 'samples': 21613568, 'steps': 42213, 'loss/train': 2.076869010925293}
-03/05/2022 15:05:45 - INFO - codeparrot_training - Skipping example with length 90 (seq_length=1024)
-03/05/2022 15:05:49 - INFO - codeparrot_training - Step 42214: {'lr': 0.000414314483690168, 'samples': 21614080, 'steps': 42214, 'loss/train': 1.0867937803268433}
-03/05/2022 15:05:53 - INFO - codeparrot_training - Step 42215: {'lr': 0.00041431048414188645, 'samples': 21614592, 'steps': 42215, 'loss/train': 1.8841760158538818}
-03/05/2022 15:05:54 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/05/2022 15:05:58 - INFO - codeparrot_training - Step 42216: {'lr': 0.00041430648451956913, 'samples': 21615104, 'steps': 42216, 'loss/train': 2.4689812660217285}
-03/05/2022 15:06:01 - INFO - codeparrot_training - Step 42217: {'lr': 0.00041430248482321794, 'samples': 21615616, 'steps': 42217, 'loss/train': 2.2619245052337646}
-03/05/2022 15:06:03 - INFO - codeparrot_training - Skipping example with length 659 (seq_length=1024)
-03/05/2022 15:06:06 - INFO - codeparrot_training - Step 42218: {'lr': 0.00041429848505283444, 'samples': 21616128, 'steps': 42218, 'loss/train': 2.1733052730560303}
-03/05/2022 15:06:10 - INFO - codeparrot_training - Step 42219: {'lr': 0.00041429448520842064, 'samples': 21616640, 'steps': 42219, 'loss/train': 2.3186469078063965}
-03/05/2022 15:06:12 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/05/2022 15:06:15 - INFO - codeparrot_training - Step 42220: {'lr': 0.0004142904852899783, 'samples': 21617152, 'steps': 42220, 'loss/train': 1.6358833312988281}
-03/05/2022 15:06:18 - INFO - codeparrot_training - Step 42221: {'lr': 0.0004142864852975092, 'samples': 21617664, 'steps': 42221, 'loss/train': 1.7900112867355347}
-03/05/2022 15:06:20 - INFO - codeparrot_training - Skipping example with length 804 (seq_length=1024)
-03/05/2022 15:06:23 - INFO - codeparrot_training - Step 42222: {'lr': 0.00041428248523101507, 'samples': 21618176, 'steps': 42222, 'loss/train': 1.5021916627883911}
-03/05/2022 15:06:26 - INFO - codeparrot_training - Step 42223: {'lr': 0.0004142784850904978, 'samples': 21618688, 'steps': 42223, 'loss/train': 1.9106868505477905}
-03/05/2022 15:06:28 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/05/2022 15:06:32 - INFO - codeparrot_training - Step 42224: {'lr': 0.00041427448487595933, 'samples': 21619200, 'steps': 42224, 'loss/train': 2.2315149307250977}
-03/05/2022 15:06:35 - INFO - codeparrot_training - Step 42225: {'lr': 0.0004142704845874012, 'samples': 21619712, 'steps': 42225, 'loss/train': 1.7947694063186646}
-03/05/2022 15:06:36 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/05/2022 15:06:40 - INFO - codeparrot_training - Step 42226: {'lr': 0.00041426648422482527, 'samples': 21620224, 'steps': 42226, 'loss/train': 1.484729290008545}
-03/05/2022 15:06:43 - INFO - codeparrot_training - Step 42227: {'lr': 0.0004142624837882335, 'samples': 21620736, 'steps': 42227, 'loss/train': 2.035325765609741}
-03/05/2022 15:06:45 - INFO - codeparrot_training - Skipping example with length 682 (seq_length=1024)
-03/05/2022 15:06:49 - INFO - codeparrot_training - Step 42228: {'lr': 0.0004142584832776275, 'samples': 21621248, 'steps': 42228, 'loss/train': 1.801566481590271}
-03/05/2022 15:06:52 - INFO - codeparrot_training - Step 42229: {'lr': 0.00041425448269300923, 'samples': 21621760, 'steps': 42229, 'loss/train': 1.6826670169830322}
-03/05/2022 15:06:53 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/05/2022 15:06:57 - INFO - codeparrot_training - Step 42230: {'lr': 0.00041425048203438036, 'samples': 21622272, 'steps': 42230, 'loss/train': 2.2317399978637695}
-03/05/2022 15:07:00 - INFO - codeparrot_training - Step 42231: {'lr': 0.0004142464813017429, 'samples': 21622784, 'steps': 42231, 'loss/train': 1.0485529899597168}
-03/05/2022 15:07:01 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/05/2022 15:07:05 - INFO - codeparrot_training - Step 42232: {'lr': 0.0004142424804950984, 'samples': 21623296, 'steps': 42232, 'loss/train': 1.8699569702148438}
-03/05/2022 15:07:09 - INFO - codeparrot_training - Step 42233: {'lr': 0.00041423847961444873, 'samples': 21623808, 'steps': 42233, 'loss/train': 1.1809583902359009}
-03/05/2022 15:07:10 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/05/2022 15:07:14 - INFO - codeparrot_training - Step 42234: {'lr': 0.0004142344786597958, 'samples': 21624320, 'steps': 42234, 'loss/train': 2.0509021282196045}
-03/05/2022 15:07:17 - INFO - codeparrot_training - Step 42235: {'lr': 0.0004142304776311413, 'samples': 21624832, 'steps': 42235, 'loss/train': 1.9713292121887207}
-03/05/2022 15:07:19 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 15:07:22 - INFO - codeparrot_training - Step 42236: {'lr': 0.0004142264765284871, 'samples': 21625344, 'steps': 42236, 'loss/train': 1.4943140745162964}
-03/05/2022 15:07:26 - INFO - codeparrot_training - Step 42237: {'lr': 0.0004142224753518351, 'samples': 21625856, 'steps': 42237, 'loss/train': 2.1657516956329346}
-03/05/2022 15:07:27 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/05/2022 15:07:31 - INFO - codeparrot_training - Step 42238: {'lr': 0.00041421847410118685, 'samples': 21626368, 'steps': 42238, 'loss/train': 0.10753724724054337}
-03/05/2022 15:07:34 - INFO - codeparrot_training - Step 42239: {'lr': 0.00041421447277654436, 'samples': 21626880, 'steps': 42239, 'loss/train': 1.2892000675201416}
-03/05/2022 15:07:36 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/05/2022 15:07:39 - INFO - codeparrot_training - Step 42240: {'lr': 0.0004142104713779093, 'samples': 21627392, 'steps': 42240, 'loss/train': 1.4510924816131592}
-03/05/2022 15:07:43 - INFO - codeparrot_training - Step 42241: {'lr': 0.00041420646990528355, 'samples': 21627904, 'steps': 42241, 'loss/train': 2.0203566551208496}
-03/05/2022 15:07:44 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/05/2022 15:07:48 - INFO - codeparrot_training - Step 42242: {'lr': 0.0004142024683586689, 'samples': 21628416, 'steps': 42242, 'loss/train': 1.955403447151184}
-03/05/2022 15:07:51 - INFO - codeparrot_training - Step 42243: {'lr': 0.00041419846673806715, 'samples': 21628928, 'steps': 42243, 'loss/train': 2.081850528717041}
-03/05/2022 15:07:52 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/05/2022 15:07:56 - INFO - codeparrot_training - Step 42244: {'lr': 0.0004141944650434801, 'samples': 21629440, 'steps': 42244, 'loss/train': 1.644861102104187}
-03/05/2022 15:07:59 - INFO - codeparrot_training - Step 42245: {'lr': 0.00041419046327490964, 'samples': 21629952, 'steps': 42245, 'loss/train': 1.9781160354614258}
-03/05/2022 15:08:01 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/05/2022 15:08:05 - INFO - codeparrot_training - Step 42246: {'lr': 0.00041418646143235737, 'samples': 21630464, 'steps': 42246, 'loss/train': 1.7483758926391602}
-03/05/2022 15:08:08 - INFO - codeparrot_training - Step 42247: {'lr': 0.0004141824595158253, 'samples': 21630976, 'steps': 42247, 'loss/train': 1.000533938407898}
-03/05/2022 15:08:09 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/05/2022 15:08:13 - INFO - codeparrot_training - Step 42248: {'lr': 0.0004141784575253151, 'samples': 21631488, 'steps': 42248, 'loss/train': 2.204744815826416}
-03/05/2022 15:08:16 - INFO - codeparrot_training - Step 42249: {'lr': 0.0004141744554608287, 'samples': 21632000, 'steps': 42249, 'loss/train': 1.0809922218322754}
-03/05/2022 15:08:17 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 15:08:22 - INFO - codeparrot_training - Step 42250: {'lr': 0.00041417045332236776, 'samples': 21632512, 'steps': 42250, 'loss/train': 2.0767133235931396}
-03/05/2022 15:08:25 - INFO - codeparrot_training - Step 42251: {'lr': 0.0004141664511099341, 'samples': 21633024, 'steps': 42251, 'loss/train': 1.5652543306350708}
-03/05/2022 15:08:26 - INFO - codeparrot_training - Skipping example with length 35 (seq_length=1024)
-03/05/2022 15:08:30 - INFO - codeparrot_training - Step 42252: {'lr': 0.00041416244882352965, 'samples': 21633536, 'steps': 42252, 'loss/train': 1.1194431781768799}
-03/05/2022 15:08:33 - INFO - codeparrot_training - Step 42253: {'lr': 0.00041415844646315613, 'samples': 21634048, 'steps': 42253, 'loss/train': 2.1713337898254395}
-03/05/2022 15:08:34 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 15:08:38 - INFO - codeparrot_training - Step 42254: {'lr': 0.0004141544440288153, 'samples': 21634560, 'steps': 42254, 'loss/train': 0.7658924460411072}
-03/05/2022 15:08:42 - INFO - codeparrot_training - Step 42255: {'lr': 0.0004141504415205091, 'samples': 21635072, 'steps': 42255, 'loss/train': 1.9556533098220825}
-03/05/2022 15:08:42 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/05/2022 15:08:47 - INFO - codeparrot_training - Step 42256: {'lr': 0.0004141464389382391, 'samples': 21635584, 'steps': 42256, 'loss/train': 6.466179847717285}
-03/05/2022 15:08:50 - INFO - codeparrot_training - Step 42257: {'lr': 0.0004141424362820073, 'samples': 21636096, 'steps': 42257, 'loss/train': 1.5943946838378906}
-03/05/2022 15:08:52 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/05/2022 15:08:55 - INFO - codeparrot_training - Step 42258: {'lr': 0.0004141384335518155, 'samples': 21636608, 'steps': 42258, 'loss/train': 1.768483281135559}
-03/05/2022 15:08:58 - INFO - codeparrot_training - Step 42259: {'lr': 0.00041413443074766543, 'samples': 21637120, 'steps': 42259, 'loss/train': 1.9302858114242554}
-03/05/2022 15:09:00 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/05/2022 15:09:04 - INFO - codeparrot_training - Step 42260: {'lr': 0.000414130427869559, 'samples': 21637632, 'steps': 42260, 'loss/train': 1.9095699787139893}
-03/05/2022 15:09:07 - INFO - codeparrot_training - Step 42261: {'lr': 0.0004141264249174978, 'samples': 21638144, 'steps': 42261, 'loss/train': 2.270962953567505}
-03/05/2022 15:09:08 - INFO - codeparrot_training - Skipping example with length 607 (seq_length=1024)
-03/05/2022 15:09:12 - INFO - codeparrot_training - Step 42262: {'lr': 0.00041412242189148383, 'samples': 21638656, 'steps': 42262, 'loss/train': 1.8687002658843994}
-03/05/2022 15:09:16 - INFO - codeparrot_training - Step 42263: {'lr': 0.00041411841879151877, 'samples': 21639168, 'steps': 42263, 'loss/train': 3.505892038345337}
-03/05/2022 15:09:17 - INFO - codeparrot_training - Skipping example with length 583 (seq_length=1024)
-03/05/2022 15:09:21 - INFO - codeparrot_training - Step 42264: {'lr': 0.00041411441561760455, 'samples': 21639680, 'steps': 42264, 'loss/train': 2.1697139739990234}
-03/05/2022 15:09:24 - INFO - codeparrot_training - Step 42265: {'lr': 0.0004141104123697429, 'samples': 21640192, 'steps': 42265, 'loss/train': 2.6605231761932373}
-03/05/2022 15:09:25 - INFO - codeparrot_training - Skipping example with length 965 (seq_length=1024)
-03/05/2022 15:09:29 - INFO - codeparrot_training - Step 42266: {'lr': 0.00041410640904793563, 'samples': 21640704, 'steps': 42266, 'loss/train': 2.050741195678711}
-03/05/2022 15:09:32 - INFO - codeparrot_training - Step 42267: {'lr': 0.0004141024056521845, 'samples': 21641216, 'steps': 42267, 'loss/train': 1.5571380853652954}
-03/05/2022 15:09:33 - INFO - codeparrot_training - Skipping example with length 967 (seq_length=1024)
-03/05/2022 15:09:38 - INFO - codeparrot_training - Step 42268: {'lr': 0.0004140984021824914, 'samples': 21641728, 'steps': 42268, 'loss/train': 1.9108104705810547}
-03/05/2022 15:09:41 - INFO - codeparrot_training - Step 42269: {'lr': 0.0004140943986388581, 'samples': 21642240, 'steps': 42269, 'loss/train': 1.3083782196044922}
-03/05/2022 15:09:44 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/05/2022 15:09:46 - INFO - codeparrot_training - Step 42270: {'lr': 0.00041409039502128634, 'samples': 21642752, 'steps': 42270, 'loss/train': 1.51084303855896}
-03/05/2022 15:09:50 - INFO - codeparrot_training - Step 42271: {'lr': 0.000414086391329778, 'samples': 21643264, 'steps': 42271, 'loss/train': 1.693543553352356}
-03/05/2022 15:09:52 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 15:09:55 - INFO - codeparrot_training - Step 42272: {'lr': 0.0004140823875643349, 'samples': 21643776, 'steps': 42272, 'loss/train': 0.8703694939613342}
-03/05/2022 15:09:58 - INFO - codeparrot_training - Step 42273: {'lr': 0.00041407838372495883, 'samples': 21644288, 'steps': 42273, 'loss/train': 1.7392849922180176}
-03/05/2022 15:10:00 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/05/2022 15:10:03 - INFO - codeparrot_training - Step 42274: {'lr': 0.00041407437981165154, 'samples': 21644800, 'steps': 42274, 'loss/train': 1.8765876293182373}
-03/05/2022 15:10:07 - INFO - codeparrot_training - Step 42275: {'lr': 0.0004140703758244148, 'samples': 21645312, 'steps': 42275, 'loss/train': 1.4659923315048218}
-03/05/2022 15:10:09 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/05/2022 15:10:12 - INFO - codeparrot_training - Step 42276: {'lr': 0.00041406637176325054, 'samples': 21645824, 'steps': 42276, 'loss/train': 1.9681718349456787}
-03/05/2022 15:10:15 - INFO - codeparrot_training - Step 42277: {'lr': 0.00041406236762816053, 'samples': 21646336, 'steps': 42277, 'loss/train': 0.23262548446655273}
-03/05/2022 15:10:18 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/05/2022 15:10:20 - INFO - codeparrot_training - Step 42278: {'lr': 0.0004140583634191465, 'samples': 21646848, 'steps': 42278, 'loss/train': 1.8907297849655151}
-03/05/2022 15:10:24 - INFO - codeparrot_training - Step 42279: {'lr': 0.00041405435913621037, 'samples': 21647360, 'steps': 42279, 'loss/train': 2.085663080215454}
-03/05/2022 15:10:26 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 15:10:29 - INFO - codeparrot_training - Step 42280: {'lr': 0.0004140503547793538, 'samples': 21647872, 'steps': 42280, 'loss/train': 1.946205496788025}
-03/05/2022 15:10:32 - INFO - codeparrot_training - Step 42281: {'lr': 0.00041404635034857876, 'samples': 21648384, 'steps': 42281, 'loss/train': 1.590935230255127}
-03/05/2022 15:10:35 - INFO - codeparrot_training - Step 42282: {'lr': 0.00041404234584388683, 'samples': 21648896, 'steps': 42282, 'loss/train': 1.3725224733352661}
-03/05/2022 15:10:35 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/05/2022 15:10:41 - INFO - codeparrot_training - Step 42283: {'lr': 0.00041403834126528007, 'samples': 21649408, 'steps': 42283, 'loss/train': 2.4166133403778076}
-03/05/2022 15:10:44 - INFO - codeparrot_training - Step 42284: {'lr': 0.00041403433661276015, 'samples': 21649920, 'steps': 42284, 'loss/train': 2.694035768508911}
-03/05/2022 15:10:44 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/05/2022 15:10:49 - INFO - codeparrot_training - Step 42285: {'lr': 0.0004140303318863288, 'samples': 21650432, 'steps': 42285, 'loss/train': 1.734609842300415}
-03/05/2022 15:10:52 - INFO - codeparrot_training - Step 42286: {'lr': 0.00041402632708598797, 'samples': 21650944, 'steps': 42286, 'loss/train': 2.030993938446045}
-03/05/2022 15:10:53 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/05/2022 15:10:58 - INFO - codeparrot_training - Step 42287: {'lr': 0.0004140223222117394, 'samples': 21651456, 'steps': 42287, 'loss/train': 1.8440669775009155}
-03/05/2022 15:11:01 - INFO - codeparrot_training - Step 42288: {'lr': 0.00041401831726358497, 'samples': 21651968, 'steps': 42288, 'loss/train': 1.7034146785736084}
-03/05/2022 15:11:01 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/05/2022 15:11:06 - INFO - codeparrot_training - Step 42289: {'lr': 0.0004140143122415263, 'samples': 21652480, 'steps': 42289, 'loss/train': 1.4834851026535034}
-03/05/2022 15:11:09 - INFO - codeparrot_training - Step 42290: {'lr': 0.0004140103071455654, 'samples': 21652992, 'steps': 42290, 'loss/train': 1.0906099081039429}
-03/05/2022 15:11:09 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/05/2022 15:11:14 - INFO - codeparrot_training - Step 42291: {'lr': 0.000414006301975704, 'samples': 21653504, 'steps': 42291, 'loss/train': 1.7261799573898315}
-03/05/2022 15:11:18 - INFO - codeparrot_training - Step 42292: {'lr': 0.0004140022967319438, 'samples': 21654016, 'steps': 42292, 'loss/train': 1.9778822660446167}
-03/05/2022 15:11:18 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/05/2022 15:11:23 - INFO - codeparrot_training - Step 42293: {'lr': 0.0004139982914142868, 'samples': 21654528, 'steps': 42293, 'loss/train': 1.683379888534546}
-03/05/2022 15:11:26 - INFO - codeparrot_training - Step 42294: {'lr': 0.0004139942860227346, 'samples': 21655040, 'steps': 42294, 'loss/train': 2.001723289489746}
-03/05/2022 15:11:26 - INFO - codeparrot_training - Skipping example with length 612 (seq_length=1024)
-03/05/2022 15:11:31 - INFO - codeparrot_training - Step 42295: {'lr': 0.00041399028055728914, 'samples': 21655552, 'steps': 42295, 'loss/train': 1.8406199216842651}
-03/05/2022 15:11:34 - INFO - codeparrot_training - Step 42296: {'lr': 0.0004139862750179523, 'samples': 21656064, 'steps': 42296, 'loss/train': 1.232178807258606}
-03/05/2022 15:11:35 - INFO - codeparrot_training - Skipping example with length 536 (seq_length=1024)
-03/05/2022 15:11:40 - INFO - codeparrot_training - Step 42297: {'lr': 0.0004139822694047256, 'samples': 21656576, 'steps': 42297, 'loss/train': 1.1844849586486816}
-03/05/2022 15:11:43 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/05/2022 15:11:45 - INFO - codeparrot_training - Step 42298: {'lr': 0.0004139782637176112, 'samples': 21657088, 'steps': 42298, 'loss/train': 1.055175542831421}
-03/05/2022 15:11:48 - INFO - codeparrot_training - Step 42299: {'lr': 0.0004139742579566106, 'samples': 21657600, 'steps': 42299, 'loss/train': 1.8662828207015991}
-03/05/2022 15:11:51 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/05/2022 15:11:53 - INFO - codeparrot_training - Step 42300: {'lr': 0.00041397025212172573, 'samples': 21658112, 'steps': 42300, 'loss/train': 1.5083459615707397}
-03/05/2022 15:11:57 - INFO - codeparrot_training - Step 42301: {'lr': 0.00041396624621295843, 'samples': 21658624, 'steps': 42301, 'loss/train': 1.764953374862671}
-03/05/2022 15:11:59 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/05/2022 15:12:02 - INFO - codeparrot_training - Step 42302: {'lr': 0.00041396224023031045, 'samples': 21659136, 'steps': 42302, 'loss/train': 1.308441162109375}
-03/05/2022 15:12:05 - INFO - codeparrot_training - Step 42303: {'lr': 0.0004139582341737836, 'samples': 21659648, 'steps': 42303, 'loss/train': 1.327883005142212}
-03/05/2022 15:12:08 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 15:12:10 - INFO - codeparrot_training - Step 42304: {'lr': 0.0004139542280433797, 'samples': 21660160, 'steps': 42304, 'loss/train': 1.9545114040374756}
-03/05/2022 15:12:14 - INFO - codeparrot_training - Step 42305: {'lr': 0.00041395022183910064, 'samples': 21660672, 'steps': 42305, 'loss/train': 1.517080307006836}
-03/05/2022 15:12:16 - INFO - codeparrot_training - Skipping example with length 921 (seq_length=1024)
-03/05/2022 15:12:19 - INFO - codeparrot_training - Step 42306: {'lr': 0.00041394621556094805, 'samples': 21661184, 'steps': 42306, 'loss/train': 1.4589508771896362}
-03/05/2022 15:12:22 - INFO - codeparrot_training - Step 42307: {'lr': 0.0004139422092089239, 'samples': 21661696, 'steps': 42307, 'loss/train': 1.1395530700683594}
-03/05/2022 15:12:24 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/05/2022 15:12:28 - INFO - codeparrot_training - Step 42308: {'lr': 0.0004139382027830298, 'samples': 21662208, 'steps': 42308, 'loss/train': 1.7505488395690918}
-03/05/2022 15:12:31 - INFO - codeparrot_training - Step 42309: {'lr': 0.00041393419628326777, 'samples': 21662720, 'steps': 42309, 'loss/train': 1.7447443008422852}
-03/05/2022 15:12:34 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 15:12:36 - INFO - codeparrot_training - Step 42310: {'lr': 0.00041393018970963945, 'samples': 21663232, 'steps': 42310, 'loss/train': 2.2256128787994385}
-03/05/2022 15:12:39 - INFO - codeparrot_training - Step 42311: {'lr': 0.00041392618306214683, 'samples': 21663744, 'steps': 42311, 'loss/train': 1.460722804069519}
-03/05/2022 15:12:42 - INFO - codeparrot_training - Skipping example with length 927 (seq_length=1024)
-03/05/2022 15:12:44 - INFO - codeparrot_training - Step 42312: {'lr': 0.0004139221763407915, 'samples': 21664256, 'steps': 42312, 'loss/train': 2.418182373046875}
-03/05/2022 15:12:48 - INFO - codeparrot_training - Step 42313: {'lr': 0.00041391816954557543, 'samples': 21664768, 'steps': 42313, 'loss/train': 1.9882206916809082}
-03/05/2022 15:12:50 - INFO - codeparrot_training - Skipping example with length 523 (seq_length=1024)
-03/05/2022 15:12:53 - INFO - codeparrot_training - Step 42314: {'lr': 0.00041391416267650034, 'samples': 21665280, 'steps': 42314, 'loss/train': 2.168405532836914}
-03/05/2022 15:12:56 - INFO - codeparrot_training - Step 42315: {'lr': 0.00041391015573356805, 'samples': 21665792, 'steps': 42315, 'loss/train': 1.2848774194717407}
-03/05/2022 15:12:59 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/05/2022 15:13:01 - INFO - codeparrot_training - Step 42316: {'lr': 0.0004139061487167804, 'samples': 21666304, 'steps': 42316, 'loss/train': 1.385947346687317}
-03/05/2022 15:13:05 - INFO - codeparrot_training - Step 42317: {'lr': 0.00041390214162613916, 'samples': 21666816, 'steps': 42317, 'loss/train': 1.472153663635254}
-03/05/2022 15:13:07 - INFO - codeparrot_training - Skipping example with length 483 (seq_length=1024)
-03/05/2022 15:13:10 - INFO - codeparrot_training - Step 42318: {'lr': 0.00041389813446164614, 'samples': 21667328, 'steps': 42318, 'loss/train': 1.05081307888031}
-03/05/2022 15:13:13 - INFO - codeparrot_training - Step 42319: {'lr': 0.0004138941272233031, 'samples': 21667840, 'steps': 42319, 'loss/train': 1.188031554222107}
-03/05/2022 15:13:16 - INFO - codeparrot_training - Skipping example with length 896 (seq_length=1024)
-03/05/2022 15:13:18 - INFO - codeparrot_training - Step 42320: {'lr': 0.0004138901199111119, 'samples': 21668352, 'steps': 42320, 'loss/train': 1.2935422658920288}
-03/05/2022 15:13:21 - INFO - codeparrot_training - Step 42321: {'lr': 0.00041388611252507446, 'samples': 21668864, 'steps': 42321, 'loss/train': 1.2160004377365112}
-03/05/2022 15:13:24 - INFO - codeparrot_training - Skipping example with length 653 (seq_length=1024)
-03/05/2022 15:13:27 - INFO - codeparrot_training - Step 42322: {'lr': 0.0004138821050651923, 'samples': 21669376, 'steps': 42322, 'loss/train': 0.896248459815979}
-03/05/2022 15:13:30 - INFO - codeparrot_training - Step 42323: {'lr': 0.00041387809753146756, 'samples': 21669888, 'steps': 42323, 'loss/train': 1.356410026550293}
-03/05/2022 15:13:33 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/05/2022 15:13:35 - INFO - codeparrot_training - Step 42324: {'lr': 0.00041387408992390177, 'samples': 21670400, 'steps': 42324, 'loss/train': 1.4991496801376343}
-03/05/2022 15:13:39 - INFO - codeparrot_training - Step 42325: {'lr': 0.0004138700822424968, 'samples': 21670912, 'steps': 42325, 'loss/train': 0.8494857549667358}
-03/05/2022 15:13:41 - INFO - codeparrot_training - Skipping example with length 334 (seq_length=1024)
-03/05/2022 15:13:44 - INFO - codeparrot_training - Step 42326: {'lr': 0.0004138660744872547, 'samples': 21671424, 'steps': 42326, 'loss/train': 1.6943747997283936}
-03/05/2022 15:13:47 - INFO - codeparrot_training - Step 42327: {'lr': 0.00041386206665817684, 'samples': 21671936, 'steps': 42327, 'loss/train': 2.171386241912842}
-03/05/2022 15:13:50 - INFO - codeparrot_training - Step 42328: {'lr': 0.0004138580587552654, 'samples': 21672448, 'steps': 42328, 'loss/train': 1.4312162399291992}
-03/05/2022 15:13:51 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/05/2022 15:13:56 - INFO - codeparrot_training - Step 42329: {'lr': 0.000413854050778522, 'samples': 21672960, 'steps': 42329, 'loss/train': 2.0114142894744873}
-03/05/2022 15:13:59 - INFO - codeparrot_training - Step 42330: {'lr': 0.00041385004272794846, 'samples': 21673472, 'steps': 42330, 'loss/train': 0.3372471332550049}
-03/05/2022 15:14:00 - INFO - codeparrot_training - Skipping example with length 1007 (seq_length=1024)
-03/05/2022 15:14:04 - INFO - codeparrot_training - Step 42331: {'lr': 0.0004138460346035467, 'samples': 21673984, 'steps': 42331, 'loss/train': 2.801154136657715}
-03/05/2022 15:14:08 - INFO - codeparrot_training - Step 42332: {'lr': 0.0004138420264053184, 'samples': 21674496, 'steps': 42332, 'loss/train': 2.1664011478424072}
-03/05/2022 15:14:09 - INFO - codeparrot_training - Skipping example with length 788 (seq_length=1024)
-03/05/2022 15:14:13 - INFO - codeparrot_training - Step 42333: {'lr': 0.00041383801813326543, 'samples': 21675008, 'steps': 42333, 'loss/train': 1.3563294410705566}
-03/05/2022 15:14:16 - INFO - codeparrot_training - Step 42334: {'lr': 0.00041383400978738956, 'samples': 21675520, 'steps': 42334, 'loss/train': 1.7399111986160278}
-03/05/2022 15:14:18 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/05/2022 15:14:21 - INFO - codeparrot_training - Step 42335: {'lr': 0.0004138300013676926, 'samples': 21676032, 'steps': 42335, 'loss/train': 0.2610914707183838}
-03/05/2022 15:14:25 - INFO - codeparrot_training - Step 42336: {'lr': 0.0004138259928741764, 'samples': 21676544, 'steps': 42336, 'loss/train': 1.5745344161987305}
-03/05/2022 15:14:26 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/05/2022 15:14:30 - INFO - codeparrot_training - Step 42337: {'lr': 0.0004138219843068427, 'samples': 21677056, 'steps': 42337, 'loss/train': 1.6311700344085693}
-03/05/2022 15:14:33 - INFO - codeparrot_training - Step 42338: {'lr': 0.00041381797566569345, 'samples': 21677568, 'steps': 42338, 'loss/train': 2.036377191543579}
-03/05/2022 15:14:35 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/05/2022 15:14:38 - INFO - codeparrot_training - Step 42339: {'lr': 0.0004138139669507303, 'samples': 21678080, 'steps': 42339, 'loss/train': 1.6639888286590576}
-03/05/2022 15:14:42 - INFO - codeparrot_training - Step 42340: {'lr': 0.000413809958161955, 'samples': 21678592, 'steps': 42340, 'loss/train': 2.180830717086792}
-03/05/2022 15:14:43 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 15:14:47 - INFO - codeparrot_training - Step 42341: {'lr': 0.0004138059492993695, 'samples': 21679104, 'steps': 42341, 'loss/train': 1.6778161525726318}
-03/05/2022 15:14:50 - INFO - codeparrot_training - Step 42342: {'lr': 0.0004138019403629756, 'samples': 21679616, 'steps': 42342, 'loss/train': 1.9946653842926025}
-03/05/2022 15:14:51 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/05/2022 15:14:55 - INFO - codeparrot_training - Step 42343: {'lr': 0.0004137979313527751, 'samples': 21680128, 'steps': 42343, 'loss/train': 1.8503549098968506}
-03/05/2022 15:14:58 - INFO - codeparrot_training - Step 42344: {'lr': 0.00041379392226876974, 'samples': 21680640, 'steps': 42344, 'loss/train': 2.1069529056549072}
-03/05/2022 15:15:00 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/05/2022 15:15:04 - INFO - codeparrot_training - Step 42345: {'lr': 0.0004137899131109614, 'samples': 21681152, 'steps': 42345, 'loss/train': 2.392202615737915}
-03/05/2022 15:15:07 - INFO - codeparrot_training - Step 42346: {'lr': 0.0004137859038793518, 'samples': 21681664, 'steps': 42346, 'loss/train': 2.257373094558716}
-03/05/2022 15:15:08 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/05/2022 15:15:12 - INFO - codeparrot_training - Step 42347: {'lr': 0.0004137818945739428, 'samples': 21682176, 'steps': 42347, 'loss/train': 0.6692388653755188}
-03/05/2022 15:15:15 - INFO - codeparrot_training - Step 42348: {'lr': 0.00041377788519473624, 'samples': 21682688, 'steps': 42348, 'loss/train': 0.8978343605995178}
-03/05/2022 15:15:17 - INFO - codeparrot_training - Skipping example with length 228 (seq_length=1024)
-03/05/2022 15:15:21 - INFO - codeparrot_training - Step 42349: {'lr': 0.0004137738757417339, 'samples': 21683200, 'steps': 42349, 'loss/train': 2.5353991985321045}
-03/05/2022 15:15:24 - INFO - codeparrot_training - Step 42350: {'lr': 0.0004137698662149375, 'samples': 21683712, 'steps': 42350, 'loss/train': 1.7081776857376099}
-03/05/2022 15:15:25 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/05/2022 15:15:29 - INFO - codeparrot_training - Step 42351: {'lr': 0.00041376585661434903, 'samples': 21684224, 'steps': 42351, 'loss/train': 1.7706999778747559}
-03/05/2022 15:15:32 - INFO - codeparrot_training - Step 42352: {'lr': 0.0004137618469399702, 'samples': 21684736, 'steps': 42352, 'loss/train': 2.1542680263519287}
-03/05/2022 15:15:33 - INFO - codeparrot_training - Skipping example with length 110 (seq_length=1024)
-03/05/2022 15:15:38 - INFO - codeparrot_training - Step 42353: {'lr': 0.0004137578371918027, 'samples': 21685248, 'steps': 42353, 'loss/train': 1.7423452138900757}
-03/05/2022 15:15:41 - INFO - codeparrot_training - Step 42354: {'lr': 0.00041375382736984857, 'samples': 21685760, 'steps': 42354, 'loss/train': 2.076129198074341}
-03/05/2022 15:15:42 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/05/2022 15:15:46 - INFO - codeparrot_training - Step 42355: {'lr': 0.0004137498174741094, 'samples': 21686272, 'steps': 42355, 'loss/train': 1.5596511363983154}
-03/05/2022 15:15:49 - INFO - codeparrot_training - Step 42356: {'lr': 0.0004137458075045871, 'samples': 21686784, 'steps': 42356, 'loss/train': 1.682293176651001}
-03/05/2022 15:15:51 - INFO - codeparrot_training - Skipping example with length 469 (seq_length=1024)
-03/05/2022 15:15:55 - INFO - codeparrot_training - Step 42357: {'lr': 0.0004137417974612835, 'samples': 21687296, 'steps': 42357, 'loss/train': 1.4429855346679688}
-03/05/2022 15:15:58 - INFO - codeparrot_training - Step 42358: {'lr': 0.0004137377873442004, 'samples': 21687808, 'steps': 42358, 'loss/train': 1.4033256769180298}
-03/05/2022 15:15:59 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/05/2022 15:16:03 - INFO - codeparrot_training - Step 42359: {'lr': 0.00041373377715333946, 'samples': 21688320, 'steps': 42359, 'loss/train': 1.4400829076766968}
-03/05/2022 15:16:06 - INFO - codeparrot_training - Step 42360: {'lr': 0.00041372976688870266, 'samples': 21688832, 'steps': 42360, 'loss/train': 1.1200079917907715}
-03/05/2022 15:16:07 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/05/2022 15:16:12 - INFO - codeparrot_training - Step 42361: {'lr': 0.0004137257565502918, 'samples': 21689344, 'steps': 42361, 'loss/train': 2.3171565532684326}
-03/05/2022 15:16:15 - INFO - codeparrot_training - Step 42362: {'lr': 0.00041372174613810863, 'samples': 21689856, 'steps': 42362, 'loss/train': 1.7401020526885986}
-03/05/2022 15:16:16 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/05/2022 15:16:20 - INFO - codeparrot_training - Step 42363: {'lr': 0.00041371773565215494, 'samples': 21690368, 'steps': 42363, 'loss/train': 1.2325447797775269}
-03/05/2022 15:16:23 - INFO - codeparrot_training - Step 42364: {'lr': 0.00041371372509243256, 'samples': 21690880, 'steps': 42364, 'loss/train': 1.7275514602661133}
-03/05/2022 15:16:24 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/05/2022 15:16:28 - INFO - codeparrot_training - Step 42365: {'lr': 0.00041370971445894335, 'samples': 21691392, 'steps': 42365, 'loss/train': 0.6369551420211792}
-03/05/2022 15:16:32 - INFO - codeparrot_training - Step 42366: {'lr': 0.00041370570375168903, 'samples': 21691904, 'steps': 42366, 'loss/train': 1.9925694465637207}
-03/05/2022 15:16:32 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/05/2022 15:16:37 - INFO - codeparrot_training - Step 42367: {'lr': 0.00041370169297067145, 'samples': 21692416, 'steps': 42367, 'loss/train': 0.3987744152545929}
-03/05/2022 15:16:40 - INFO - codeparrot_training - Step 42368: {'lr': 0.00041369768211589245, 'samples': 21692928, 'steps': 42368, 'loss/train': 1.7809486389160156}
-03/05/2022 15:16:41 - INFO - codeparrot_training - Skipping example with length 898 (seq_length=1024)
-03/05/2022 15:16:45 - INFO - codeparrot_training - Step 42369: {'lr': 0.0004136936711873537, 'samples': 21693440, 'steps': 42369, 'loss/train': 2.1908984184265137}
-03/05/2022 15:16:49 - INFO - codeparrot_training - Step 42370: {'lr': 0.0004136896601850572, 'samples': 21693952, 'steps': 42370, 'loss/train': 2.257387161254883}
-03/05/2022 15:16:49 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/05/2022 15:16:54 - INFO - codeparrot_training - Step 42371: {'lr': 0.0004136856491090046, 'samples': 21694464, 'steps': 42371, 'loss/train': 2.691514730453491}
-03/05/2022 15:16:57 - INFO - codeparrot_training - Step 42372: {'lr': 0.0004136816379591979, 'samples': 21694976, 'steps': 42372, 'loss/train': 1.0881742238998413}
-03/05/2022 15:16:58 - INFO - codeparrot_training - Skipping example with length 687 (seq_length=1024)
-03/05/2022 15:17:02 - INFO - codeparrot_training - Step 42373: {'lr': 0.0004136776267356387, 'samples': 21695488, 'steps': 42373, 'loss/train': 2.3424744606018066}
-03/05/2022 15:17:06 - INFO - codeparrot_training - Step 42374: {'lr': 0.0004136736154383288, 'samples': 21696000, 'steps': 42374, 'loss/train': 1.1213961839675903}
-03/05/2022 15:17:06 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 15:17:11 - INFO - codeparrot_training - Step 42375: {'lr': 0.00041366960406727024, 'samples': 21696512, 'steps': 42375, 'loss/train': 1.706502079963684}
-03/05/2022 15:17:14 - INFO - codeparrot_training - Step 42376: {'lr': 0.00041366559262246463, 'samples': 21697024, 'steps': 42376, 'loss/train': 1.6131337881088257}
-03/05/2022 15:17:15 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/05/2022 15:17:19 - INFO - codeparrot_training - Step 42377: {'lr': 0.00041366158110391375, 'samples': 21697536, 'steps': 42377, 'loss/train': 1.0953948497772217}
-03/05/2022 15:17:22 - INFO - codeparrot_training - Step 42378: {'lr': 0.0004136575695116196, 'samples': 21698048, 'steps': 42378, 'loss/train': 1.4052002429962158}
-03/05/2022 15:17:23 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/05/2022 15:17:28 - INFO - codeparrot_training - Step 42379: {'lr': 0.0004136535578455838, 'samples': 21698560, 'steps': 42379, 'loss/train': 1.6577708721160889}
-03/05/2022 15:17:31 - INFO - codeparrot_training - Step 42380: {'lr': 0.0004136495461058083, 'samples': 21699072, 'steps': 42380, 'loss/train': 1.4538023471832275}
-03/05/2022 15:17:31 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/05/2022 15:17:36 - INFO - codeparrot_training - Step 42381: {'lr': 0.0004136455342922948, 'samples': 21699584, 'steps': 42381, 'loss/train': 1.0310801267623901}
-03/05/2022 15:17:39 - INFO - codeparrot_training - Step 42382: {'lr': 0.0004136415224050451, 'samples': 21700096, 'steps': 42382, 'loss/train': 1.9006279706954956}
-03/05/2022 15:17:40 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/05/2022 15:17:45 - INFO - codeparrot_training - Step 42383: {'lr': 0.0004136375104440611, 'samples': 21700608, 'steps': 42383, 'loss/train': 1.6706410646438599}
-03/05/2022 15:17:48 - INFO - codeparrot_training - Step 42384: {'lr': 0.0004136334984093446, 'samples': 21701120, 'steps': 42384, 'loss/train': 1.9014859199523926}
-03/05/2022 15:17:50 - INFO - codeparrot_training - Skipping example with length 817 (seq_length=1024)
-03/05/2022 15:17:53 - INFO - codeparrot_training - Step 42385: {'lr': 0.0004136294863008974, 'samples': 21701632, 'steps': 42385, 'loss/train': 2.427670478820801}
-03/05/2022 15:17:56 - INFO - codeparrot_training - Step 42386: {'lr': 0.00041362547411872116, 'samples': 21702144, 'steps': 42386, 'loss/train': 0.4849485754966736}
-03/05/2022 15:17:58 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/05/2022 15:18:02 - INFO - codeparrot_training - Step 42387: {'lr': 0.00041362146186281777, 'samples': 21702656, 'steps': 42387, 'loss/train': 1.632948637008667}
-03/05/2022 15:18:05 - INFO - codeparrot_training - Step 42388: {'lr': 0.00041361744953318923, 'samples': 21703168, 'steps': 42388, 'loss/train': 1.691718339920044}
-03/05/2022 15:18:07 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 15:18:10 - INFO - codeparrot_training - Step 42389: {'lr': 0.0004136134371298371, 'samples': 21703680, 'steps': 42389, 'loss/train': 2.0299110412597656}
-03/05/2022 15:18:14 - INFO - codeparrot_training - Step 42390: {'lr': 0.0004136094246527633, 'samples': 21704192, 'steps': 42390, 'loss/train': 1.5378493070602417}
-03/05/2022 15:18:16 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/05/2022 15:18:19 - INFO - codeparrot_training - Step 42391: {'lr': 0.0004136054121019697, 'samples': 21704704, 'steps': 42391, 'loss/train': 2.0200769901275635}
-03/05/2022 15:18:22 - INFO - codeparrot_training - Step 42392: {'lr': 0.0004136013994774579, 'samples': 21705216, 'steps': 42392, 'loss/train': 2.1085689067840576}
-03/05/2022 15:18:25 - INFO - codeparrot_training - Step 42393: {'lr': 0.00041359738677922993, 'samples': 21705728, 'steps': 42393, 'loss/train': 1.471612811088562}
-03/05/2022 15:18:26 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/05/2022 15:18:30 - INFO - codeparrot_training - Step 42394: {'lr': 0.00041359337400728746, 'samples': 21706240, 'steps': 42394, 'loss/train': 1.5655121803283691}
-03/05/2022 15:18:34 - INFO - codeparrot_training - Step 42395: {'lr': 0.00041358936116163224, 'samples': 21706752, 'steps': 42395, 'loss/train': 1.8408195972442627}
-03/05/2022 15:18:34 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 15:18:39 - INFO - codeparrot_training - Step 42396: {'lr': 0.00041358534824226635, 'samples': 21707264, 'steps': 42396, 'loss/train': 1.8806945085525513}
-03/05/2022 15:18:42 - INFO - codeparrot_training - Step 42397: {'lr': 0.0004135813352491913, 'samples': 21707776, 'steps': 42397, 'loss/train': 1.1682320833206177}
-03/05/2022 15:18:42 - INFO - codeparrot_training - Skipping example with length 453 (seq_length=1024)
-03/05/2022 15:18:47 - INFO - codeparrot_training - Step 42398: {'lr': 0.00041357732218240905, 'samples': 21708288, 'steps': 42398, 'loss/train': 0.895717978477478}
-03/05/2022 15:18:50 - INFO - codeparrot_training - Step 42399: {'lr': 0.0004135733090419215, 'samples': 21708800, 'steps': 42399, 'loss/train': 1.5662328004837036}
-03/05/2022 15:18:50 - INFO - codeparrot_training - Skipping example with length 803 (seq_length=1024)
-03/05/2022 15:18:56 - INFO - codeparrot_training - Step 42400: {'lr': 0.00041356929582773023, 'samples': 21709312, 'steps': 42400, 'loss/train': 0.6348327398300171}
-03/05/2022 15:18:59 - INFO - codeparrot_training - Step 42401: {'lr': 0.00041356528253983714, 'samples': 21709824, 'steps': 42401, 'loss/train': 1.604033350944519}
-03/05/2022 15:18:59 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/05/2022 15:19:04 - INFO - codeparrot_training - Step 42402: {'lr': 0.0004135612691782441, 'samples': 21710336, 'steps': 42402, 'loss/train': 1.4334324598312378}
-03/05/2022 15:19:07 - INFO - codeparrot_training - Step 42403: {'lr': 0.0004135572557429529, 'samples': 21710848, 'steps': 42403, 'loss/train': 0.7647178769111633}
-03/05/2022 15:19:08 - INFO - codeparrot_training - Skipping example with length 108 (seq_length=1024)
-03/05/2022 15:19:13 - INFO - codeparrot_training - Step 42404: {'lr': 0.0004135532422339653, 'samples': 21711360, 'steps': 42404, 'loss/train': 1.9096533060073853}
-03/05/2022 15:19:16 - INFO - codeparrot_training - Step 42405: {'lr': 0.00041354922865128316, 'samples': 21711872, 'steps': 42405, 'loss/train': 0.6175175905227661}
-03/05/2022 15:19:16 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/05/2022 15:19:21 - INFO - codeparrot_training - Step 42406: {'lr': 0.00041354521499490813, 'samples': 21712384, 'steps': 42406, 'loss/train': 1.987703561782837}
-03/05/2022 15:19:24 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/05/2022 15:19:26 - INFO - codeparrot_training - Step 42407: {'lr': 0.00041354120126484227, 'samples': 21712896, 'steps': 42407, 'loss/train': 1.938920259475708}
-03/05/2022 15:19:30 - INFO - codeparrot_training - Step 42408: {'lr': 0.00041353718746108724, 'samples': 21713408, 'steps': 42408, 'loss/train': 1.3082078695297241}
-03/05/2022 15:19:33 - INFO - codeparrot_training - Step 42409: {'lr': 0.00041353317358364496, 'samples': 21713920, 'steps': 42409, 'loss/train': 1.6471275091171265}
-03/05/2022 15:19:33 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/05/2022 15:19:38 - INFO - codeparrot_training - Step 42410: {'lr': 0.00041352915963251705, 'samples': 21714432, 'steps': 42410, 'loss/train': 2.706022024154663}
-03/05/2022 15:19:41 - INFO - codeparrot_training - Step 42411: {'lr': 0.00041352514560770545, 'samples': 21714944, 'steps': 42411, 'loss/train': 1.4449020624160767}
-03/05/2022 15:19:42 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 15:19:47 - INFO - codeparrot_training - Step 42412: {'lr': 0.000413521131509212, 'samples': 21715456, 'steps': 42412, 'loss/train': 1.7380239963531494}
-03/05/2022 15:19:50 - INFO - codeparrot_training - Step 42413: {'lr': 0.0004135171173370383, 'samples': 21715968, 'steps': 42413, 'loss/train': 5.091571807861328}
-03/05/2022 15:19:51 - INFO - codeparrot_training - Skipping example with length 879 (seq_length=1024)
-03/05/2022 15:19:56 - INFO - codeparrot_training - Step 42414: {'lr': 0.00041351310309118653, 'samples': 21716480, 'steps': 42414, 'loss/train': 2.850825548171997}
-03/05/2022 15:19:59 - INFO - codeparrot_training - Step 42415: {'lr': 0.00041350908877165805, 'samples': 21716992, 'steps': 42415, 'loss/train': 2.0891385078430176}
-03/05/2022 15:20:02 - INFO - codeparrot_training - Step 42416: {'lr': 0.00041350507437845505, 'samples': 21717504, 'steps': 42416, 'loss/train': 1.8256524801254272}
-03/05/2022 15:20:02 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/05/2022 15:20:07 - INFO - codeparrot_training - Step 42417: {'lr': 0.00041350105991157915, 'samples': 21718016, 'steps': 42417, 'loss/train': 1.523796796798706}
-03/05/2022 15:20:11 - INFO - codeparrot_training - Step 42418: {'lr': 0.00041349704537103216, 'samples': 21718528, 'steps': 42418, 'loss/train': 1.7898316383361816}
-03/05/2022 15:20:11 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/05/2022 15:20:16 - INFO - codeparrot_training - Step 42419: {'lr': 0.000413493030756816, 'samples': 21719040, 'steps': 42419, 'loss/train': 1.7714990377426147}
-03/05/2022 15:20:19 - INFO - codeparrot_training - Step 42420: {'lr': 0.0004134890160689323, 'samples': 21719552, 'steps': 42420, 'loss/train': 1.8830819129943848}
-03/05/2022 15:20:20 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/05/2022 15:20:25 - INFO - codeparrot_training - Step 42421: {'lr': 0.000413485001307383, 'samples': 21720064, 'steps': 42421, 'loss/train': 2.099813938140869}
-03/05/2022 15:20:28 - INFO - codeparrot_training - Step 42422: {'lr': 0.00041348098647216993, 'samples': 21720576, 'steps': 42422, 'loss/train': 2.2930963039398193}
-03/05/2022 15:20:29 - INFO - codeparrot_training - Skipping example with length 455 (seq_length=1024)
-03/05/2022 15:20:33 - INFO - codeparrot_training - Step 42423: {'lr': 0.00041347697156329485, 'samples': 21721088, 'steps': 42423, 'loss/train': 2.5516021251678467}
-03/05/2022 15:20:36 - INFO - codeparrot_training - Step 42424: {'lr': 0.00041347295658075955, 'samples': 21721600, 'steps': 42424, 'loss/train': 1.4078001976013184}
-03/05/2022 15:20:37 - INFO - codeparrot_training - Skipping example with length 352 (seq_length=1024)
-03/05/2022 15:20:41 - INFO - codeparrot_training - Step 42425: {'lr': 0.00041346894152456584, 'samples': 21722112, 'steps': 42425, 'loss/train': 1.6297658681869507}
-03/05/2022 15:20:45 - INFO - codeparrot_training - Step 42426: {'lr': 0.00041346492639471555, 'samples': 21722624, 'steps': 42426, 'loss/train': 2.191555976867676}
-03/05/2022 15:20:45 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/05/2022 15:20:50 - INFO - codeparrot_training - Step 42427: {'lr': 0.0004134609111912105, 'samples': 21723136, 'steps': 42427, 'loss/train': 2.584141731262207}
-03/05/2022 15:20:53 - INFO - codeparrot_training - Step 42428: {'lr': 0.00041345689591405256, 'samples': 21723648, 'steps': 42428, 'loss/train': 1.9068603515625}
-03/05/2022 15:20:54 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/05/2022 15:20:58 - INFO - codeparrot_training - Step 42429: {'lr': 0.0004134528805632434, 'samples': 21724160, 'steps': 42429, 'loss/train': 1.6674448251724243}
-03/05/2022 15:21:02 - INFO - codeparrot_training - Step 42430: {'lr': 0.00041344886513878485, 'samples': 21724672, 'steps': 42430, 'loss/train': 1.8804675340652466}
-03/05/2022 15:21:02 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/05/2022 15:21:07 - INFO - codeparrot_training - Step 42431: {'lr': 0.00041344484964067873, 'samples': 21725184, 'steps': 42431, 'loss/train': 1.7256267070770264}
-03/05/2022 15:21:10 - INFO - codeparrot_training - Step 42432: {'lr': 0.00041344083406892704, 'samples': 21725696, 'steps': 42432, 'loss/train': 1.6917905807495117}
-03/05/2022 15:21:11 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/05/2022 15:21:15 - INFO - codeparrot_training - Step 42433: {'lr': 0.0004134368184235313, 'samples': 21726208, 'steps': 42433, 'loss/train': 1.7010291814804077}
-03/05/2022 15:21:19 - INFO - codeparrot_training - Step 42434: {'lr': 0.0004134328027044935, 'samples': 21726720, 'steps': 42434, 'loss/train': 1.6858408451080322}
-03/05/2022 15:21:19 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/05/2022 15:21:24 - INFO - codeparrot_training - Step 42435: {'lr': 0.0004134287869118154, 'samples': 21727232, 'steps': 42435, 'loss/train': 0.7728706002235413}
-03/05/2022 15:21:27 - INFO - codeparrot_training - Step 42436: {'lr': 0.0004134247710454988, 'samples': 21727744, 'steps': 42436, 'loss/train': 2.1889593601226807}
-03/05/2022 15:21:28 - INFO - codeparrot_training - Skipping example with length 177 (seq_length=1024)
-03/05/2022 15:21:32 - INFO - codeparrot_training - Step 42437: {'lr': 0.00041342075510554554, 'samples': 21728256, 'steps': 42437, 'loss/train': 1.4320552349090576}
-03/05/2022 15:21:36 - INFO - codeparrot_training - Step 42438: {'lr': 0.0004134167390919574, 'samples': 21728768, 'steps': 42438, 'loss/train': 1.6958187818527222}
-03/05/2022 15:21:37 - INFO - codeparrot_training - Skipping example with length 102 (seq_length=1024)
-03/05/2022 15:21:41 - INFO - codeparrot_training - Step 42439: {'lr': 0.0004134127230047362, 'samples': 21729280, 'steps': 42439, 'loss/train': 2.293339729309082}
-03/05/2022 15:21:44 - INFO - codeparrot_training - Step 42440: {'lr': 0.00041340870684388375, 'samples': 21729792, 'steps': 42440, 'loss/train': 1.4697574377059937}
-03/05/2022 15:21:45 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 15:21:49 - INFO - codeparrot_training - Step 42441: {'lr': 0.00041340469060940183, 'samples': 21730304, 'steps': 42441, 'loss/train': 1.8995330333709717}
-03/05/2022 15:21:52 - INFO - codeparrot_training - Step 42442: {'lr': 0.0004134006743012923, 'samples': 21730816, 'steps': 42442, 'loss/train': 1.3152291774749756}
-03/05/2022 15:21:53 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/05/2022 15:21:58 - INFO - codeparrot_training - Step 42443: {'lr': 0.00041339665791955695, 'samples': 21731328, 'steps': 42443, 'loss/train': 2.1756083965301514}
-03/05/2022 15:22:01 - INFO - codeparrot_training - Step 42444: {'lr': 0.00041339264146419757, 'samples': 21731840, 'steps': 42444, 'loss/train': 1.6310796737670898}
-03/05/2022 15:22:02 - INFO - codeparrot_training - Skipping example with length 300 (seq_length=1024)
-03/05/2022 15:22:06 - INFO - codeparrot_training - Step 42445: {'lr': 0.000413388624935216, 'samples': 21732352, 'steps': 42445, 'loss/train': 0.7886888980865479}
-03/05/2022 15:22:09 - INFO - codeparrot_training - Step 42446: {'lr': 0.00041338460833261403, 'samples': 21732864, 'steps': 42446, 'loss/train': 1.6947680711746216}
-03/05/2022 15:22:10 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 15:22:14 - INFO - codeparrot_training - Step 42447: {'lr': 0.0004133805916563935, 'samples': 21733376, 'steps': 42447, 'loss/train': 0.9065048098564148}
-03/05/2022 15:22:18 - INFO - codeparrot_training - Step 42448: {'lr': 0.00041337657490655625, 'samples': 21733888, 'steps': 42448, 'loss/train': 2.1771962642669678}
-03/05/2022 15:22:18 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/05/2022 15:22:23 - INFO - codeparrot_training - Step 42449: {'lr': 0.00041337255808310394, 'samples': 21734400, 'steps': 42449, 'loss/train': 1.387026309967041}
-03/05/2022 15:22:26 - INFO - codeparrot_training - Step 42450: {'lr': 0.0004133685411860385, 'samples': 21734912, 'steps': 42450, 'loss/train': 2.0032689571380615}
-03/05/2022 15:22:27 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 15:22:31 - INFO - codeparrot_training - Step 42451: {'lr': 0.0004133645242153617, 'samples': 21735424, 'steps': 42451, 'loss/train': 1.8626126050949097}
-03/05/2022 15:22:35 - INFO - codeparrot_training - Step 42452: {'lr': 0.0004133605071710754, 'samples': 21735936, 'steps': 42452, 'loss/train': 2.064732313156128}
-03/05/2022 15:22:35 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/05/2022 15:22:40 - INFO - codeparrot_training - Step 42453: {'lr': 0.00041335649005318133, 'samples': 21736448, 'steps': 42453, 'loss/train': 1.7235357761383057}
-03/05/2022 15:22:43 - INFO - codeparrot_training - Step 42454: {'lr': 0.0004133524728616814, 'samples': 21736960, 'steps': 42454, 'loss/train': 1.4257060289382935}
-03/05/2022 15:22:43 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/05/2022 15:22:48 - INFO - codeparrot_training - Step 42455: {'lr': 0.00041334845559657735, 'samples': 21737472, 'steps': 42455, 'loss/train': 2.0949947834014893}
-03/05/2022 15:22:51 - INFO - codeparrot_training - Step 42456: {'lr': 0.00041334443825787097, 'samples': 21737984, 'steps': 42456, 'loss/train': 0.9066054821014404}
-03/05/2022 15:22:52 - INFO - codeparrot_training - Skipping example with length 709 (seq_length=1024)
-03/05/2022 15:22:57 - INFO - codeparrot_training - Step 42457: {'lr': 0.0004133404208455642, 'samples': 21738496, 'steps': 42457, 'loss/train': 2.039267063140869}
-03/05/2022 15:23:00 - INFO - codeparrot_training - Step 42458: {'lr': 0.00041333640335965865, 'samples': 21739008, 'steps': 42458, 'loss/train': 1.6362769603729248}
-03/05/2022 15:23:01 - INFO - codeparrot_training - Skipping example with length 970 (seq_length=1024)
-03/05/2022 15:23:05 - INFO - codeparrot_training - Step 42459: {'lr': 0.0004133323858001563, 'samples': 21739520, 'steps': 42459, 'loss/train': 2.334679365158081}
-03/05/2022 15:23:08 - INFO - codeparrot_training - Step 42460: {'lr': 0.0004133283681670589, 'samples': 21740032, 'steps': 42460, 'loss/train': 2.0391411781311035}
-03/05/2022 15:23:09 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 15:23:14 - INFO - codeparrot_training - Step 42461: {'lr': 0.0004133243504603682, 'samples': 21740544, 'steps': 42461, 'loss/train': 1.0308313369750977}
-03/05/2022 15:23:17 - INFO - codeparrot_training - Step 42462: {'lr': 0.0004133203326800861, 'samples': 21741056, 'steps': 42462, 'loss/train': 1.6099565029144287}
-03/05/2022 15:23:18 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 15:23:22 - INFO - codeparrot_training - Step 42463: {'lr': 0.0004133163148262144, 'samples': 21741568, 'steps': 42463, 'loss/train': 1.6617032289505005}
-03/05/2022 15:23:25 - INFO - codeparrot_training - Step 42464: {'lr': 0.00041331229689875487, 'samples': 21742080, 'steps': 42464, 'loss/train': 1.3817763328552246}
-03/05/2022 15:23:26 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/05/2022 15:23:31 - INFO - codeparrot_training - Step 42465: {'lr': 0.0004133082788977093, 'samples': 21742592, 'steps': 42465, 'loss/train': 1.9073724746704102}
-03/05/2022 15:23:34 - INFO - codeparrot_training - Step 42466: {'lr': 0.00041330426082307963, 'samples': 21743104, 'steps': 42466, 'loss/train': 0.6224821209907532}
-03/05/2022 15:23:35 - INFO - codeparrot_training - Skipping example with length 311 (seq_length=1024)
-03/05/2022 15:23:39 - INFO - codeparrot_training - Step 42467: {'lr': 0.0004133002426748675, 'samples': 21743616, 'steps': 42467, 'loss/train': 1.4256278276443481}
-03/05/2022 15:23:42 - INFO - codeparrot_training - Step 42468: {'lr': 0.0004132962244530749, 'samples': 21744128, 'steps': 42468, 'loss/train': 1.6559779644012451}
-03/05/2022 15:23:43 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/05/2022 15:23:48 - INFO - codeparrot_training - Step 42469: {'lr': 0.0004132922061577035, 'samples': 21744640, 'steps': 42469, 'loss/train': 0.7829142808914185}
-03/05/2022 15:23:51 - INFO - codeparrot_training - Step 42470: {'lr': 0.0004132881877887551, 'samples': 21745152, 'steps': 42470, 'loss/train': 6.349141597747803}
-03/05/2022 15:23:52 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/05/2022 15:23:56 - INFO - codeparrot_training - Step 42471: {'lr': 0.0004132841693462315, 'samples': 21745664, 'steps': 42471, 'loss/train': 0.40681737661361694}
-03/05/2022 15:23:59 - INFO - codeparrot_training - Step 42472: {'lr': 0.0004132801508301347, 'samples': 21746176, 'steps': 42472, 'loss/train': 0.9733253121376038}
-03/05/2022 15:24:00 - INFO - codeparrot_training - Skipping example with length 833 (seq_length=1024)
-03/05/2022 15:24:05 - INFO - codeparrot_training - Step 42473: {'lr': 0.0004132761322404663, 'samples': 21746688, 'steps': 42473, 'loss/train': 1.6759318113327026}
-03/05/2022 15:24:08 - INFO - codeparrot_training - Step 42474: {'lr': 0.00041327211357722825, 'samples': 21747200, 'steps': 42474, 'loss/train': 1.726747751235962}
-03/05/2022 15:24:09 - INFO - codeparrot_training - Skipping example with length 751 (seq_length=1024)
-03/05/2022 15:24:13 - INFO - codeparrot_training - Step 42475: {'lr': 0.00041326809484042235, 'samples': 21747712, 'steps': 42475, 'loss/train': 1.0513757467269897}
-03/05/2022 15:24:16 - INFO - codeparrot_training - Step 42476: {'lr': 0.0004132640760300503, 'samples': 21748224, 'steps': 42476, 'loss/train': 1.4438413381576538}
-03/05/2022 15:24:18 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/05/2022 15:24:21 - INFO - codeparrot_training - Step 42477: {'lr': 0.000413260057146114, 'samples': 21748736, 'steps': 42477, 'loss/train': 1.534231424331665}
-03/05/2022 15:24:25 - INFO - codeparrot_training - Step 42478: {'lr': 0.00041325603818861517, 'samples': 21749248, 'steps': 42478, 'loss/train': 2.1679012775421143}
-03/05/2022 15:24:26 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/05/2022 15:24:30 - INFO - codeparrot_training - Step 42479: {'lr': 0.0004132520191575558, 'samples': 21749760, 'steps': 42479, 'loss/train': 2.3027191162109375}
-03/05/2022 15:24:33 - INFO - codeparrot_training - Step 42480: {'lr': 0.0004132480000529375, 'samples': 21750272, 'steps': 42480, 'loss/train': 1.5098888874053955}
-03/05/2022 15:24:34 - INFO - codeparrot_training - Skipping example with length 786 (seq_length=1024)
-03/05/2022 15:24:39 - INFO - codeparrot_training - Step 42481: {'lr': 0.0004132439808747622, 'samples': 21750784, 'steps': 42481, 'loss/train': 2.518982410430908}
-03/05/2022 15:24:42 - INFO - codeparrot_training - Step 42482: {'lr': 0.00041323996162303167, 'samples': 21751296, 'steps': 42482, 'loss/train': 1.8602962493896484}
-03/05/2022 15:24:43 - INFO - codeparrot_training - Skipping example with length 50 (seq_length=1024)
-03/05/2022 15:24:47 - INFO - codeparrot_training - Step 42483: {'lr': 0.0004132359422977477, 'samples': 21751808, 'steps': 42483, 'loss/train': 6.649305820465088}
-03/05/2022 15:24:50 - INFO - codeparrot_training - Step 42484: {'lr': 0.0004132319228989122, 'samples': 21752320, 'steps': 42484, 'loss/train': 1.442028284072876}
-03/05/2022 15:24:53 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/05/2022 15:24:56 - INFO - codeparrot_training - Step 42485: {'lr': 0.00041322790342652695, 'samples': 21752832, 'steps': 42485, 'loss/train': 1.2186248302459717}
-03/05/2022 15:24:59 - INFO - codeparrot_training - Step 42486: {'lr': 0.00041322388388059366, 'samples': 21753344, 'steps': 42486, 'loss/train': 1.7214487791061401}
-03/05/2022 15:25:02 - INFO - codeparrot_training - Step 42487: {'lr': 0.0004132198642611142, 'samples': 21753856, 'steps': 42487, 'loss/train': 1.349733591079712}
-03/05/2022 15:25:02 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/05/2022 15:25:08 - INFO - codeparrot_training - Step 42488: {'lr': 0.0004132158445680904, 'samples': 21754368, 'steps': 42488, 'loss/train': 1.7935656309127808}
-03/05/2022 15:25:11 - INFO - codeparrot_training - Step 42489: {'lr': 0.0004132118248015241, 'samples': 21754880, 'steps': 42489, 'loss/train': 1.5895205736160278}
-03/05/2022 15:25:11 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 15:25:16 - INFO - codeparrot_training - Step 42490: {'lr': 0.000413207804961417, 'samples': 21755392, 'steps': 42490, 'loss/train': 1.867658019065857}
-03/05/2022 15:25:19 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/05/2022 15:25:22 - INFO - codeparrot_training - Step 42491: {'lr': 0.000413203785047771, 'samples': 21755904, 'steps': 42491, 'loss/train': 0.2641412913799286}
-03/05/2022 15:25:25 - INFO - codeparrot_training - Step 42492: {'lr': 0.00041319976506058785, 'samples': 21756416, 'steps': 42492, 'loss/train': 1.2600747346878052}
-03/05/2022 15:25:28 - INFO - codeparrot_training - Step 42493: {'lr': 0.00041319574499986957, 'samples': 21756928, 'steps': 42493, 'loss/train': 1.9806921482086182}
-03/05/2022 15:25:28 - INFO - codeparrot_training - Skipping example with length 861 (seq_length=1024)
-03/05/2022 15:25:34 - INFO - codeparrot_training - Step 42494: {'lr': 0.0004131917248656177, 'samples': 21757440, 'steps': 42494, 'loss/train': 1.6440340280532837}
-03/05/2022 15:25:37 - INFO - codeparrot_training - Step 42495: {'lr': 0.0004131877046578341, 'samples': 21757952, 'steps': 42495, 'loss/train': 1.8518306016921997}
-03/05/2022 15:25:37 - INFO - codeparrot_training - Skipping example with length 960 (seq_length=1024)
-03/05/2022 15:25:42 - INFO - codeparrot_training - Step 42496: {'lr': 0.0004131836843765207, 'samples': 21758464, 'steps': 42496, 'loss/train': 1.8813645839691162}
-03/05/2022 15:25:45 - INFO - codeparrot_training - Step 42497: {'lr': 0.00041317966402167923, 'samples': 21758976, 'steps': 42497, 'loss/train': 1.596298336982727}
-03/05/2022 15:25:45 - INFO - codeparrot_training - Skipping example with length 512 (seq_length=1024)
-03/05/2022 15:25:51 - INFO - codeparrot_training - Step 42498: {'lr': 0.0004131756435933115, 'samples': 21759488, 'steps': 42498, 'loss/train': 0.694696843624115}
-03/05/2022 15:25:54 - INFO - codeparrot_training - Step 42499: {'lr': 0.00041317162309141944, 'samples': 21760000, 'steps': 42499, 'loss/train': 1.6641772985458374}
-03/05/2022 15:25:54 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 15:25:59 - INFO - codeparrot_training - Step 42500: {'lr': 0.00041316760251600474, 'samples': 21760512, 'steps': 42500, 'loss/train': 1.6383837461471558}
-03/05/2022 15:26:02 - INFO - codeparrot_training - Step 42501: {'lr': 0.00041316358186706915, 'samples': 21761024, 'steps': 42501, 'loss/train': 1.6520744562149048}
-03/05/2022 15:26:02 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/05/2022 15:26:08 - INFO - codeparrot_training - Step 42502: {'lr': 0.0004131595611446146, 'samples': 21761536, 'steps': 42502, 'loss/train': 1.884994626045227}
-03/05/2022 15:26:11 - INFO - codeparrot_training - Step 42503: {'lr': 0.0004131555403486429, 'samples': 21762048, 'steps': 42503, 'loss/train': 7.166080951690674}
-03/05/2022 15:26:11 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/05/2022 15:26:16 - INFO - codeparrot_training - Step 42504: {'lr': 0.00041315151947915577, 'samples': 21762560, 'steps': 42504, 'loss/train': 1.6574573516845703}
-03/05/2022 15:26:19 - INFO - codeparrot_training - Step 42505: {'lr': 0.0004131474985361551, 'samples': 21763072, 'steps': 42505, 'loss/train': 2.2335896492004395}
-03/05/2022 15:26:20 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/05/2022 15:26:24 - INFO - codeparrot_training - Step 42506: {'lr': 0.0004131434775196428, 'samples': 21763584, 'steps': 42506, 'loss/train': 1.9857820272445679}
-03/05/2022 15:26:28 - INFO - codeparrot_training - Step 42507: {'lr': 0.0004131394564296205, 'samples': 21764096, 'steps': 42507, 'loss/train': 1.2835943698883057}
-03/05/2022 15:26:28 - INFO - codeparrot_training - Skipping example with length 275 (seq_length=1024)
-03/05/2022 15:26:33 - INFO - codeparrot_training - Step 42508: {'lr': 0.00041313543526609, 'samples': 21764608, 'steps': 42508, 'loss/train': 1.729771614074707}
-03/05/2022 15:26:36 - INFO - codeparrot_training - Step 42509: {'lr': 0.00041313141402905324, 'samples': 21765120, 'steps': 42509, 'loss/train': 2.312286138534546}
-03/05/2022 15:26:37 - INFO - codeparrot_training - Skipping example with length 897 (seq_length=1024)
-03/05/2022 15:26:41 - INFO - codeparrot_training - Step 42510: {'lr': 0.00041312739271851196, 'samples': 21765632, 'steps': 42510, 'loss/train': 1.4985514879226685}
-03/05/2022 15:26:45 - INFO - codeparrot_training - Step 42511: {'lr': 0.0004131233713344681, 'samples': 21766144, 'steps': 42511, 'loss/train': 1.6756319999694824}
-03/05/2022 15:26:45 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/05/2022 15:26:50 - INFO - codeparrot_training - Step 42512: {'lr': 0.0004131193498769232, 'samples': 21766656, 'steps': 42512, 'loss/train': 1.8318690061569214}
-03/05/2022 15:26:53 - INFO - codeparrot_training - Step 42513: {'lr': 0.0004131153283458794, 'samples': 21767168, 'steps': 42513, 'loss/train': 1.606142282485962}
-03/05/2022 15:26:54 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 15:26:58 - INFO - codeparrot_training - Step 42514: {'lr': 0.00041311130674133824, 'samples': 21767680, 'steps': 42514, 'loss/train': 1.9051495790481567}
-03/05/2022 15:27:02 - INFO - codeparrot_training - Step 42515: {'lr': 0.0004131072850633017, 'samples': 21768192, 'steps': 42515, 'loss/train': 2.066157579421997}
-03/05/2022 15:27:02 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/05/2022 15:27:07 - INFO - codeparrot_training - Step 42516: {'lr': 0.0004131032633117715, 'samples': 21768704, 'steps': 42516, 'loss/train': 1.432417631149292}
-03/05/2022 15:27:10 - INFO - codeparrot_training - Step 42517: {'lr': 0.0004130992414867495, 'samples': 21769216, 'steps': 42517, 'loss/train': 2.0037105083465576}
-03/05/2022 15:27:11 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/05/2022 15:27:15 - INFO - codeparrot_training - Step 42518: {'lr': 0.0004130952195882375, 'samples': 21769728, 'steps': 42518, 'loss/train': 0.6045821309089661}
-03/05/2022 15:27:19 - INFO - codeparrot_training - Step 42519: {'lr': 0.0004130911976162373, 'samples': 21770240, 'steps': 42519, 'loss/train': 1.6308612823486328}
-03/05/2022 15:27:19 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/05/2022 15:27:24 - INFO - codeparrot_training - Step 42520: {'lr': 0.0004130871755707508, 'samples': 21770752, 'steps': 42520, 'loss/train': 2.060241460800171}
-03/05/2022 15:27:27 - INFO - codeparrot_training - Step 42521: {'lr': 0.0004130831534517796, 'samples': 21771264, 'steps': 42521, 'loss/train': 2.0665388107299805}
-03/05/2022 15:27:28 - INFO - codeparrot_training - Skipping example with length 652 (seq_length=1024)
-03/05/2022 15:27:32 - INFO - codeparrot_training - Step 42522: {'lr': 0.00041307913125932574, 'samples': 21771776, 'steps': 42522, 'loss/train': 0.8008148670196533}
-03/05/2022 15:27:36 - INFO - codeparrot_training - Step 42523: {'lr': 0.00041307510899339097, 'samples': 21772288, 'steps': 42523, 'loss/train': 1.3733952045440674}
-03/05/2022 15:27:36 - INFO - codeparrot_training - Skipping example with length 330 (seq_length=1024)
-03/05/2022 15:27:41 - INFO - codeparrot_training - Step 42524: {'lr': 0.00041307108665397695, 'samples': 21772800, 'steps': 42524, 'loss/train': 1.640984058380127}
-03/05/2022 15:27:44 - INFO - codeparrot_training - Step 42525: {'lr': 0.00041306706424108563, 'samples': 21773312, 'steps': 42525, 'loss/train': 1.4104074239730835}
-03/05/2022 15:27:46 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 15:27:49 - INFO - codeparrot_training - Step 42526: {'lr': 0.0004130630417547189, 'samples': 21773824, 'steps': 42526, 'loss/train': 0.3811284899711609}
-03/05/2022 15:27:53 - INFO - codeparrot_training - Step 42527: {'lr': 0.00041305901919487845, 'samples': 21774336, 'steps': 42527, 'loss/train': 2.302508592605591}
-03/05/2022 15:27:54 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/05/2022 15:27:58 - INFO - codeparrot_training - Step 42528: {'lr': 0.0004130549965615661, 'samples': 21774848, 'steps': 42528, 'loss/train': 0.9531691670417786}
-03/05/2022 15:28:01 - INFO - codeparrot_training - Step 42529: {'lr': 0.00041305097385478375, 'samples': 21775360, 'steps': 42529, 'loss/train': 1.5098739862442017}
-03/05/2022 15:28:02 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/05/2022 15:28:07 - INFO - codeparrot_training - Step 42530: {'lr': 0.00041304695107453307, 'samples': 21775872, 'steps': 42530, 'loss/train': 0.6601076722145081}
-03/05/2022 15:28:10 - INFO - codeparrot_training - Step 42531: {'lr': 0.000413042928220816, 'samples': 21776384, 'steps': 42531, 'loss/train': 1.3867470026016235}
-03/05/2022 15:28:11 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/05/2022 15:28:15 - INFO - codeparrot_training - Step 42532: {'lr': 0.0004130389052936342, 'samples': 21776896, 'steps': 42532, 'loss/train': 0.9817762970924377}
-03/05/2022 15:28:18 - INFO - codeparrot_training - Step 42533: {'lr': 0.0004130348822929897, 'samples': 21777408, 'steps': 42533, 'loss/train': 2.1084346771240234}
-03/05/2022 15:28:19 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/05/2022 15:28:24 - INFO - codeparrot_training - Step 42534: {'lr': 0.0004130308592188842, 'samples': 21777920, 'steps': 42534, 'loss/train': 2.0390067100524902}
-03/05/2022 15:28:27 - INFO - codeparrot_training - Step 42535: {'lr': 0.0004130268360713194, 'samples': 21778432, 'steps': 42535, 'loss/train': 1.0492684841156006}
-03/05/2022 15:28:28 - INFO - codeparrot_training - Skipping example with length 809 (seq_length=1024)
-03/05/2022 15:28:32 - INFO - codeparrot_training - Step 42536: {'lr': 0.0004130228128502973, 'samples': 21778944, 'steps': 42536, 'loss/train': 2.034926176071167}
-03/05/2022 15:28:35 - INFO - codeparrot_training - Step 42537: {'lr': 0.0004130187895558196, 'samples': 21779456, 'steps': 42537, 'loss/train': 1.8263274431228638}
-03/05/2022 15:28:36 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/05/2022 15:28:41 - INFO - codeparrot_training - Step 42538: {'lr': 0.00041301476618788827, 'samples': 21779968, 'steps': 42538, 'loss/train': 1.8252613544464111}
-03/05/2022 15:28:44 - INFO - codeparrot_training - Step 42539: {'lr': 0.0004130107427465049, 'samples': 21780480, 'steps': 42539, 'loss/train': 1.6434887647628784}
-03/05/2022 15:28:45 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/05/2022 15:28:49 - INFO - codeparrot_training - Step 42540: {'lr': 0.00041300671923167145, 'samples': 21780992, 'steps': 42540, 'loss/train': 1.6154977083206177}
-03/05/2022 15:28:52 - INFO - codeparrot_training - Step 42541: {'lr': 0.00041300269564338956, 'samples': 21781504, 'steps': 42541, 'loss/train': 1.955030918121338}
-03/05/2022 15:28:53 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 15:28:57 - INFO - codeparrot_training - Step 42542: {'lr': 0.0004129986719816613, 'samples': 21782016, 'steps': 42542, 'loss/train': 0.5905227661132812}
-03/05/2022 15:29:01 - INFO - codeparrot_training - Step 42543: {'lr': 0.0004129946482464883, 'samples': 21782528, 'steps': 42543, 'loss/train': 1.2630277872085571}
-03/05/2022 15:29:01 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/05/2022 15:29:06 - INFO - codeparrot_training - Step 42544: {'lr': 0.0004129906244378724, 'samples': 21783040, 'steps': 42544, 'loss/train': 3.113440990447998}
-03/05/2022 15:29:09 - INFO - codeparrot_training - Step 42545: {'lr': 0.0004129866005558155, 'samples': 21783552, 'steps': 42545, 'loss/train': 5.0117411613464355}
-03/05/2022 15:29:11 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/05/2022 15:29:14 - INFO - codeparrot_training - Step 42546: {'lr': 0.00041298257660031935, 'samples': 21784064, 'steps': 42546, 'loss/train': 1.933379888534546}
-03/05/2022 15:29:18 - INFO - codeparrot_training - Step 42547: {'lr': 0.00041297855257138577, 'samples': 21784576, 'steps': 42547, 'loss/train': 1.893028974533081}
-03/05/2022 15:29:19 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 15:29:23 - INFO - codeparrot_training - Step 42548: {'lr': 0.0004129745284690165, 'samples': 21785088, 'steps': 42548, 'loss/train': 1.5394604206085205}
-03/05/2022 15:29:26 - INFO - codeparrot_training - Step 42549: {'lr': 0.0004129705042932135, 'samples': 21785600, 'steps': 42549, 'loss/train': 1.9452452659606934}
-03/05/2022 15:29:28 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/05/2022 15:29:31 - INFO - codeparrot_training - Step 42550: {'lr': 0.0004129664800439785, 'samples': 21786112, 'steps': 42550, 'loss/train': 1.3173611164093018}
-03/05/2022 15:29:35 - INFO - codeparrot_training - Step 42551: {'lr': 0.0004129624557213133, 'samples': 21786624, 'steps': 42551, 'loss/train': 1.1900880336761475}
-03/05/2022 15:29:36 - INFO - codeparrot_training - Skipping example with length 752 (seq_length=1024)
-03/05/2022 15:29:40 - INFO - codeparrot_training - Step 42552: {'lr': 0.00041295843132521973, 'samples': 21787136, 'steps': 42552, 'loss/train': 0.641370952129364}
-03/05/2022 15:29:43 - INFO - codeparrot_training - Step 42553: {'lr': 0.0004129544068556996, 'samples': 21787648, 'steps': 42553, 'loss/train': 1.1269659996032715}
-03/05/2022 15:29:45 - INFO - codeparrot_training - Skipping example with length 502 (seq_length=1024)
-03/05/2022 15:29:48 - INFO - codeparrot_training - Step 42554: {'lr': 0.00041295038231275473, 'samples': 21788160, 'steps': 42554, 'loss/train': 1.3340009450912476}
-03/05/2022 15:29:52 - INFO - codeparrot_training - Step 42555: {'lr': 0.0004129463576963869, 'samples': 21788672, 'steps': 42555, 'loss/train': 1.7606674432754517}
-03/05/2022 15:29:53 - INFO - codeparrot_training - Skipping example with length 717 (seq_length=1024)
-03/05/2022 15:29:57 - INFO - codeparrot_training - Step 42556: {'lr': 0.000412942333006598, 'samples': 21789184, 'steps': 42556, 'loss/train': 1.4675034284591675}
-03/05/2022 15:30:00 - INFO - codeparrot_training - Step 42557: {'lr': 0.0004129383082433898, 'samples': 21789696, 'steps': 42557, 'loss/train': 0.7369664907455444}
-03/05/2022 15:30:02 - INFO - codeparrot_training - Skipping example with length 324 (seq_length=1024)
-03/05/2022 15:30:05 - INFO - codeparrot_training - Step 42558: {'lr': 0.0004129342834067641, 'samples': 21790208, 'steps': 42558, 'loss/train': 1.4568068981170654}
-03/05/2022 15:30:08 - INFO - codeparrot_training - Step 42559: {'lr': 0.0004129302584967227, 'samples': 21790720, 'steps': 42559, 'loss/train': 1.5860685110092163}
-03/05/2022 15:30:10 - INFO - codeparrot_training - Skipping example with length 763 (seq_length=1024)
-03/05/2022 15:30:14 - INFO - codeparrot_training - Step 42560: {'lr': 0.0004129262335132675, 'samples': 21791232, 'steps': 42560, 'loss/train': 2.3329436779022217}
-03/05/2022 15:30:17 - INFO - codeparrot_training - Step 42561: {'lr': 0.00041292220845640023, 'samples': 21791744, 'steps': 42561, 'loss/train': 1.9236083030700684}
-03/05/2022 15:30:19 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 15:30:22 - INFO - codeparrot_training - Step 42562: {'lr': 0.00041291818332612275, 'samples': 21792256, 'steps': 42562, 'loss/train': 1.3149757385253906}
-03/05/2022 15:30:26 - INFO - codeparrot_training - Step 42563: {'lr': 0.00041291415812243676, 'samples': 21792768, 'steps': 42563, 'loss/train': 1.8848885297775269}
-03/05/2022 15:30:27 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 15:30:31 - INFO - codeparrot_training - Step 42564: {'lr': 0.0004129101328453442, 'samples': 21793280, 'steps': 42564, 'loss/train': 0.8728896379470825}
-03/05/2022 15:30:34 - INFO - codeparrot_training - Step 42565: {'lr': 0.0004129061074948469, 'samples': 21793792, 'steps': 42565, 'loss/train': 0.6925628781318665}
-03/05/2022 15:30:36 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 15:30:39 - INFO - codeparrot_training - Step 42566: {'lr': 0.0004129020820709466, 'samples': 21794304, 'steps': 42566, 'loss/train': 1.3255623579025269}
-03/05/2022 15:30:42 - INFO - codeparrot_training - Step 42567: {'lr': 0.00041289805657364516, 'samples': 21794816, 'steps': 42567, 'loss/train': 2.0466012954711914}
-03/05/2022 15:30:44 - INFO - codeparrot_training - Skipping example with length 1010 (seq_length=1024)
-03/05/2022 15:30:48 - INFO - codeparrot_training - Step 42568: {'lr': 0.0004128940310029443, 'samples': 21795328, 'steps': 42568, 'loss/train': 1.6160099506378174}
-03/05/2022 15:30:51 - INFO - codeparrot_training - Step 42569: {'lr': 0.0004128900053588459, 'samples': 21795840, 'steps': 42569, 'loss/train': 2.4752273559570312}
-03/05/2022 15:30:53 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/05/2022 15:30:56 - INFO - codeparrot_training - Step 42570: {'lr': 0.00041288597964135186, 'samples': 21796352, 'steps': 42570, 'loss/train': 1.463428020477295}
-03/05/2022 15:30:59 - INFO - codeparrot_training - Step 42571: {'lr': 0.0004128819538504639, 'samples': 21796864, 'steps': 42571, 'loss/train': 1.576080560684204}
-03/05/2022 15:31:01 - INFO - codeparrot_training - Skipping example with length 421 (seq_length=1024)
-03/05/2022 15:31:05 - INFO - codeparrot_training - Step 42572: {'lr': 0.00041287792798618374, 'samples': 21797376, 'steps': 42572, 'loss/train': 1.3745331764221191}
-03/05/2022 15:31:08 - INFO - codeparrot_training - Step 42573: {'lr': 0.00041287390204851343, 'samples': 21797888, 'steps': 42573, 'loss/train': 0.7311790585517883}
-03/05/2022 15:31:10 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 15:31:13 - INFO - codeparrot_training - Step 42574: {'lr': 0.0004128698760374546, 'samples': 21798400, 'steps': 42574, 'loss/train': 1.443576693534851}
-03/05/2022 15:31:17 - INFO - codeparrot_training - Step 42575: {'lr': 0.0004128658499530091, 'samples': 21798912, 'steps': 42575, 'loss/train': 1.5759015083312988}
-03/05/2022 15:31:18 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/05/2022 15:31:22 - INFO - codeparrot_training - Step 42576: {'lr': 0.00041286182379517876, 'samples': 21799424, 'steps': 42576, 'loss/train': 1.5545846223831177}
-03/05/2022 15:31:25 - INFO - codeparrot_training - Step 42577: {'lr': 0.00041285779756396543, 'samples': 21799936, 'steps': 42577, 'loss/train': 1.825769305229187}
-03/05/2022 15:31:27 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/05/2022 15:31:30 - INFO - codeparrot_training - Step 42578: {'lr': 0.00041285377125937085, 'samples': 21800448, 'steps': 42578, 'loss/train': 2.285174608230591}
-03/05/2022 15:31:34 - INFO - codeparrot_training - Step 42579: {'lr': 0.0004128497448813969, 'samples': 21800960, 'steps': 42579, 'loss/train': 1.9578672647476196}
-03/05/2022 15:31:35 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/05/2022 15:31:39 - INFO - codeparrot_training - Step 42580: {'lr': 0.0004128457184300454, 'samples': 21801472, 'steps': 42580, 'loss/train': 2.442570447921753}
-03/05/2022 15:31:42 - INFO - codeparrot_training - Step 42581: {'lr': 0.0004128416919053181, 'samples': 21801984, 'steps': 42581, 'loss/train': 1.6674573421478271}
-03/05/2022 15:31:44 - INFO - codeparrot_training - Skipping example with length 65 (seq_length=1024)
-03/05/2022 15:31:48 - INFO - codeparrot_training - Step 42582: {'lr': 0.0004128376653072168, 'samples': 21802496, 'steps': 42582, 'loss/train': 1.295309066772461}
-03/05/2022 15:31:51 - INFO - codeparrot_training - Step 42583: {'lr': 0.0004128336386357434, 'samples': 21803008, 'steps': 42583, 'loss/train': 0.7511467337608337}
-03/05/2022 15:31:54 - INFO - codeparrot_training - Step 42584: {'lr': 0.0004128296118908997, 'samples': 21803520, 'steps': 42584, 'loss/train': 0.8100451231002808}
-03/05/2022 15:31:56 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/05/2022 15:32:00 - INFO - codeparrot_training - Step 42585: {'lr': 0.0004128255850726874, 'samples': 21804032, 'steps': 42585, 'loss/train': 1.252792239189148}
-03/05/2022 15:32:03 - INFO - codeparrot_training - Step 42586: {'lr': 0.0004128215581811085, 'samples': 21804544, 'steps': 42586, 'loss/train': 2.2300076484680176}
-03/05/2022 15:32:04 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 15:32:08 - INFO - codeparrot_training - Step 42587: {'lr': 0.0004128175312161647, 'samples': 21805056, 'steps': 42587, 'loss/train': 2.2272799015045166}
-03/05/2022 15:32:11 - INFO - codeparrot_training - Step 42588: {'lr': 0.00041281350417785777, 'samples': 21805568, 'steps': 42588, 'loss/train': 1.7098994255065918}
-03/05/2022 15:32:13 - INFO - codeparrot_training - Skipping example with length 777 (seq_length=1024)
-03/05/2022 15:32:17 - INFO - codeparrot_training - Step 42589: {'lr': 0.00041280947706618965, 'samples': 21806080, 'steps': 42589, 'loss/train': 2.0035574436187744}
-03/05/2022 15:32:20 - INFO - codeparrot_training - Step 42590: {'lr': 0.0004128054498811621, 'samples': 21806592, 'steps': 42590, 'loss/train': 1.497901439666748}
-03/05/2022 15:32:21 - INFO - codeparrot_training - Skipping example with length 492 (seq_length=1024)
-03/05/2022 15:32:25 - INFO - codeparrot_training - Step 42591: {'lr': 0.0004128014226227769, 'samples': 21807104, 'steps': 42591, 'loss/train': 1.1938413381576538}
-03/05/2022 15:32:28 - INFO - codeparrot_training - Step 42592: {'lr': 0.00041279739529103586, 'samples': 21807616, 'steps': 42592, 'loss/train': 1.180180549621582}
-03/05/2022 15:32:30 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/05/2022 15:32:34 - INFO - codeparrot_training - Step 42593: {'lr': 0.0004127933678859409, 'samples': 21808128, 'steps': 42593, 'loss/train': 1.5542253255844116}
-03/05/2022 15:32:37 - INFO - codeparrot_training - Step 42594: {'lr': 0.00041278934040749375, 'samples': 21808640, 'steps': 42594, 'loss/train': 1.9486687183380127}
-03/05/2022 15:32:38 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/05/2022 15:32:42 - INFO - codeparrot_training - Step 42595: {'lr': 0.0004127853128556962, 'samples': 21809152, 'steps': 42595, 'loss/train': 1.6040079593658447}
-03/05/2022 15:32:45 - INFO - codeparrot_training - Step 42596: {'lr': 0.00041278128523055015, 'samples': 21809664, 'steps': 42596, 'loss/train': 2.4169797897338867}
-03/05/2022 15:32:47 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/05/2022 15:32:50 - INFO - codeparrot_training - Step 42597: {'lr': 0.0004127772575320573, 'samples': 21810176, 'steps': 42597, 'loss/train': 1.780341386795044}
-03/05/2022 15:32:54 - INFO - codeparrot_training - Step 42598: {'lr': 0.0004127732297602196, 'samples': 21810688, 'steps': 42598, 'loss/train': 1.6631861925125122}
-03/05/2022 15:32:55 - INFO - codeparrot_training - Skipping example with length 480 (seq_length=1024)
-03/05/2022 15:32:59 - INFO - codeparrot_training - Step 42599: {'lr': 0.0004127692019150387, 'samples': 21811200, 'steps': 42599, 'loss/train': 1.371807336807251}
-03/05/2022 15:33:02 - INFO - codeparrot_training - Step 42600: {'lr': 0.00041276517399651657, 'samples': 21811712, 'steps': 42600, 'loss/train': 0.15567287802696228}
-03/05/2022 15:33:04 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 15:33:07 - INFO - codeparrot_training - Step 42601: {'lr': 0.00041276114600465497, 'samples': 21812224, 'steps': 42601, 'loss/train': 2.231785297393799}
-03/05/2022 15:33:10 - INFO - codeparrot_training - Step 42602: {'lr': 0.0004127571179394557, 'samples': 21812736, 'steps': 42602, 'loss/train': 1.3226207494735718}
-03/05/2022 15:33:12 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/05/2022 15:33:16 - INFO - codeparrot_training - Step 42603: {'lr': 0.0004127530898009205, 'samples': 21813248, 'steps': 42603, 'loss/train': 1.6350531578063965}
-03/05/2022 15:33:19 - INFO - codeparrot_training - Step 42604: {'lr': 0.00041274906158905137, 'samples': 21813760, 'steps': 42604, 'loss/train': 1.4761563539505005}
-03/05/2022 15:33:21 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/05/2022 15:33:24 - INFO - codeparrot_training - Step 42605: {'lr': 0.00041274503330384997, 'samples': 21814272, 'steps': 42605, 'loss/train': 2.2011334896087646}
-03/05/2022 15:33:27 - INFO - codeparrot_training - Step 42606: {'lr': 0.0004127410049453182, 'samples': 21814784, 'steps': 42606, 'loss/train': 1.2807420492172241}
-03/05/2022 15:33:29 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/05/2022 15:33:33 - INFO - codeparrot_training - Step 42607: {'lr': 0.00041273697651345785, 'samples': 21815296, 'steps': 42607, 'loss/train': 1.0556920766830444}
-03/05/2022 15:33:36 - INFO - codeparrot_training - Step 42608: {'lr': 0.00041273294800827075, 'samples': 21815808, 'steps': 42608, 'loss/train': 1.9606720209121704}
-03/05/2022 15:33:37 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/05/2022 15:33:41 - INFO - codeparrot_training - Step 42609: {'lr': 0.00041272891942975863, 'samples': 21816320, 'steps': 42609, 'loss/train': 1.7074124813079834}
-03/05/2022 15:33:44 - INFO - codeparrot_training - Step 42610: {'lr': 0.00041272489077792343, 'samples': 21816832, 'steps': 42610, 'loss/train': 2.236747980117798}
-03/05/2022 15:33:46 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/05/2022 15:33:49 - INFO - codeparrot_training - Step 42611: {'lr': 0.0004127208620527669, 'samples': 21817344, 'steps': 42611, 'loss/train': 1.8775275945663452}
-03/05/2022 15:33:53 - INFO - codeparrot_training - Step 42612: {'lr': 0.00041271683325429075, 'samples': 21817856, 'steps': 42612, 'loss/train': 1.8763192892074585}
-03/05/2022 15:33:54 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 15:33:58 - INFO - codeparrot_training - Step 42613: {'lr': 0.00041271280438249705, 'samples': 21818368, 'steps': 42613, 'loss/train': 1.4818907976150513}
-03/05/2022 15:34:01 - INFO - codeparrot_training - Step 42614: {'lr': 0.00041270877543738744, 'samples': 21818880, 'steps': 42614, 'loss/train': 1.4940688610076904}
-03/05/2022 15:34:03 - INFO - codeparrot_training - Skipping example with length 378 (seq_length=1024)
-03/05/2022 15:34:06 - INFO - codeparrot_training - Step 42615: {'lr': 0.0004127047464189637, 'samples': 21819392, 'steps': 42615, 'loss/train': 1.1418299674987793}
-03/05/2022 15:34:10 - INFO - codeparrot_training - Step 42616: {'lr': 0.0004127007173272278, 'samples': 21819904, 'steps': 42616, 'loss/train': 2.095956325531006}
-03/05/2022 15:34:11 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/05/2022 15:34:15 - INFO - codeparrot_training - Step 42617: {'lr': 0.0004126966881621814, 'samples': 21820416, 'steps': 42617, 'loss/train': 1.5094927549362183}
-03/05/2022 15:34:18 - INFO - codeparrot_training - Step 42618: {'lr': 0.0004126926589238264, 'samples': 21820928, 'steps': 42618, 'loss/train': 1.07016122341156}
-03/05/2022 15:34:21 - INFO - codeparrot_training - Skipping example with length 1006 (seq_length=1024)
-03/05/2022 15:34:23 - INFO - codeparrot_training - Step 42619: {'lr': 0.00041268862961216457, 'samples': 21821440, 'steps': 42619, 'loss/train': 1.142103672027588}
-03/05/2022 15:34:27 - INFO - codeparrot_training - Step 42620: {'lr': 0.00041268460022719783, 'samples': 21821952, 'steps': 42620, 'loss/train': 1.7631441354751587}
-03/05/2022 15:34:29 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 15:34:32 - INFO - codeparrot_training - Step 42621: {'lr': 0.0004126805707689279, 'samples': 21822464, 'steps': 42621, 'loss/train': 2.0135200023651123}
-03/05/2022 15:34:35 - INFO - codeparrot_training - Step 42622: {'lr': 0.0004126765412373566, 'samples': 21822976, 'steps': 42622, 'loss/train': 1.859331488609314}
-03/05/2022 15:34:37 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/05/2022 15:34:40 - INFO - codeparrot_training - Step 42623: {'lr': 0.0004126725116324858, 'samples': 21823488, 'steps': 42623, 'loss/train': 0.21420352160930634}
-03/05/2022 15:34:44 - INFO - codeparrot_training - Step 42624: {'lr': 0.00041266848195431715, 'samples': 21824000, 'steps': 42624, 'loss/train': 2.3679468631744385}
-03/05/2022 15:34:46 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/05/2022 15:34:49 - INFO - codeparrot_training - Step 42625: {'lr': 0.00041266445220285267, 'samples': 21824512, 'steps': 42625, 'loss/train': 1.4078609943389893}
-03/05/2022 15:34:52 - INFO - codeparrot_training - Step 42626: {'lr': 0.0004126604223780941, 'samples': 21825024, 'steps': 42626, 'loss/train': 1.360387921333313}
-03/05/2022 15:34:54 - INFO - codeparrot_training - Skipping example with length 459 (seq_length=1024)
-03/05/2022 15:34:57 - INFO - codeparrot_training - Step 42627: {'lr': 0.00041265639248004327, 'samples': 21825536, 'steps': 42627, 'loss/train': 1.6109942197799683}
-03/05/2022 15:35:00 - INFO - codeparrot_training - Step 42628: {'lr': 0.000412652362508702, 'samples': 21826048, 'steps': 42628, 'loss/train': 1.788684606552124}
-03/05/2022 15:35:02 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/05/2022 15:35:06 - INFO - codeparrot_training - Step 42629: {'lr': 0.000412648332464072, 'samples': 21826560, 'steps': 42629, 'loss/train': 2.1790688037872314}
-03/05/2022 15:35:09 - INFO - codeparrot_training - Step 42630: {'lr': 0.00041264430234615526, 'samples': 21827072, 'steps': 42630, 'loss/train': 1.724709153175354}
-03/05/2022 15:35:11 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/05/2022 15:35:14 - INFO - codeparrot_training - Step 42631: {'lr': 0.0004126402721549535, 'samples': 21827584, 'steps': 42631, 'loss/train': 1.519388198852539}
-03/05/2022 15:35:17 - INFO - codeparrot_training - Step 42632: {'lr': 0.00041263624189046846, 'samples': 21828096, 'steps': 42632, 'loss/train': 1.9214985370635986}
-03/05/2022 15:35:19 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/05/2022 15:35:23 - INFO - codeparrot_training - Step 42633: {'lr': 0.0004126322115527021, 'samples': 21828608, 'steps': 42633, 'loss/train': 1.6461073160171509}
-03/05/2022 15:35:26 - INFO - codeparrot_training - Step 42634: {'lr': 0.00041262818114165615, 'samples': 21829120, 'steps': 42634, 'loss/train': 1.1113814115524292}
-03/05/2022 15:35:28 - INFO - codeparrot_training - Skipping example with length 51 (seq_length=1024)
-03/05/2022 15:35:31 - INFO - codeparrot_training - Step 42635: {'lr': 0.0004126241506573325, 'samples': 21829632, 'steps': 42635, 'loss/train': 1.8905797004699707}
-03/05/2022 15:35:34 - INFO - codeparrot_training - Step 42636: {'lr': 0.00041262012009973283, 'samples': 21830144, 'steps': 42636, 'loss/train': 1.8902021646499634}
-03/05/2022 15:35:36 - INFO - codeparrot_training - Skipping example with length 627 (seq_length=1024)
-03/05/2022 15:35:40 - INFO - codeparrot_training - Step 42637: {'lr': 0.0004126160894688591, 'samples': 21830656, 'steps': 42637, 'loss/train': 1.685051441192627}
-03/05/2022 15:35:43 - INFO - codeparrot_training - Step 42638: {'lr': 0.00041261205876471307, 'samples': 21831168, 'steps': 42638, 'loss/train': 1.5529205799102783}
-03/05/2022 15:35:44 - INFO - codeparrot_training - Skipping example with length 573 (seq_length=1024)
-03/05/2022 15:35:48 - INFO - codeparrot_training - Step 42639: {'lr': 0.0004126080279872966, 'samples': 21831680, 'steps': 42639, 'loss/train': 1.8368233442306519}
-03/05/2022 15:35:51 - INFO - codeparrot_training - Step 42640: {'lr': 0.0004126039971366114, 'samples': 21832192, 'steps': 42640, 'loss/train': 1.1299426555633545}
-03/05/2022 15:35:53 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/05/2022 15:35:56 - INFO - codeparrot_training - Step 42641: {'lr': 0.0004125999662126594, 'samples': 21832704, 'steps': 42641, 'loss/train': 1.6593204736709595}
-03/05/2022 15:36:00 - INFO - codeparrot_training - Step 42642: {'lr': 0.00041259593521544223, 'samples': 21833216, 'steps': 42642, 'loss/train': 1.5966585874557495}
-03/05/2022 15:36:01 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/05/2022 15:36:05 - INFO - codeparrot_training - Step 42643: {'lr': 0.00041259190414496194, 'samples': 21833728, 'steps': 42643, 'loss/train': 1.792637825012207}
-03/05/2022 15:36:08 - INFO - codeparrot_training - Step 42644: {'lr': 0.00041258787300122026, 'samples': 21834240, 'steps': 42644, 'loss/train': 1.8549559116363525}
-03/05/2022 15:36:10 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/05/2022 15:36:14 - INFO - codeparrot_training - Step 42645: {'lr': 0.000412583841784219, 'samples': 21834752, 'steps': 42645, 'loss/train': 1.924027442932129}
-03/05/2022 15:36:17 - INFO - codeparrot_training - Step 42646: {'lr': 0.00041257981049395997, 'samples': 21835264, 'steps': 42646, 'loss/train': 1.9239075183868408}
-03/05/2022 15:36:19 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 15:36:22 - INFO - codeparrot_training - Step 42647: {'lr': 0.000412575779130445, 'samples': 21835776, 'steps': 42647, 'loss/train': 1.7570056915283203}
-03/05/2022 15:36:25 - INFO - codeparrot_training - Step 42648: {'lr': 0.0004125717476936758, 'samples': 21836288, 'steps': 42648, 'loss/train': 1.9527770280838013}
-03/05/2022 15:36:27 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/05/2022 15:36:30 - INFO - codeparrot_training - Step 42649: {'lr': 0.0004125677161836543, 'samples': 21836800, 'steps': 42649, 'loss/train': 0.9159680604934692}
-03/05/2022 15:36:34 - INFO - codeparrot_training - Step 42650: {'lr': 0.00041256368460038237, 'samples': 21837312, 'steps': 42650, 'loss/train': 1.4534938335418701}
-03/05/2022 15:36:36 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/05/2022 15:36:39 - INFO - codeparrot_training - Step 42651: {'lr': 0.00041255965294386174, 'samples': 21837824, 'steps': 42651, 'loss/train': 1.5101351737976074}
-03/05/2022 15:36:42 - INFO - codeparrot_training - Step 42652: {'lr': 0.00041255562121409416, 'samples': 21838336, 'steps': 42652, 'loss/train': 1.7283003330230713}
-03/05/2022 15:36:44 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 15:36:47 - INFO - codeparrot_training - Step 42653: {'lr': 0.0004125515894110816, 'samples': 21838848, 'steps': 42653, 'loss/train': 2.093433141708374}
-03/05/2022 15:36:50 - INFO - codeparrot_training - Step 42654: {'lr': 0.00041254755753482574, 'samples': 21839360, 'steps': 42654, 'loss/train': 1.8721247911453247}
-03/05/2022 15:36:53 - INFO - codeparrot_training - Skipping example with length 545 (seq_length=1024)
-03/05/2022 15:36:56 - INFO - codeparrot_training - Step 42655: {'lr': 0.00041254352558532854, 'samples': 21839872, 'steps': 42655, 'loss/train': 1.31758451461792}
-03/05/2022 15:36:59 - INFO - codeparrot_training - Step 42656: {'lr': 0.0004125394935625917, 'samples': 21840384, 'steps': 42656, 'loss/train': 2.4140172004699707}
-03/05/2022 15:37:01 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/05/2022 15:37:04 - INFO - codeparrot_training - Step 42657: {'lr': 0.00041253546146661704, 'samples': 21840896, 'steps': 42657, 'loss/train': 1.1278560161590576}
-03/05/2022 15:37:07 - INFO - codeparrot_training - Step 42658: {'lr': 0.00041253142929740643, 'samples': 21841408, 'steps': 42658, 'loss/train': 1.9698598384857178}
-03/05/2022 15:37:10 - INFO - codeparrot_training - Skipping example with length 402 (seq_length=1024)
-03/05/2022 15:37:13 - INFO - codeparrot_training - Step 42659: {'lr': 0.00041252739705496165, 'samples': 21841920, 'steps': 42659, 'loss/train': 2.04785418510437}
-03/05/2022 15:37:16 - INFO - codeparrot_training - Step 42660: {'lr': 0.00041252336473928455, 'samples': 21842432, 'steps': 42660, 'loss/train': 2.1213648319244385}
-03/05/2022 15:37:19 - INFO - codeparrot_training - Step 42661: {'lr': 0.00041251933235037695, 'samples': 21842944, 'steps': 42661, 'loss/train': 1.4430707693099976}
-03/05/2022 15:37:20 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/05/2022 15:37:25 - INFO - codeparrot_training - Step 42662: {'lr': 0.00041251529988824067, 'samples': 21843456, 'steps': 42662, 'loss/train': 0.15594890713691711}
-03/05/2022 15:37:28 - INFO - codeparrot_training - Step 42663: {'lr': 0.0004125112673528775, 'samples': 21843968, 'steps': 42663, 'loss/train': 1.4359874725341797}
-03/05/2022 15:37:28 - INFO - codeparrot_training - Skipping example with length 353 (seq_length=1024)
-03/05/2022 15:37:33 - INFO - codeparrot_training - Step 42664: {'lr': 0.0004125072347442892, 'samples': 21844480, 'steps': 42664, 'loss/train': 1.8084276914596558}
-03/05/2022 15:37:36 - INFO - codeparrot_training - Step 42665: {'lr': 0.0004125032020624776, 'samples': 21844992, 'steps': 42665, 'loss/train': 0.9795460104942322}
-03/05/2022 15:37:36 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/05/2022 15:37:41 - INFO - codeparrot_training - Step 42666: {'lr': 0.0004124991693074447, 'samples': 21845504, 'steps': 42666, 'loss/train': 1.7954418659210205}
-03/05/2022 15:37:45 - INFO - codeparrot_training - Step 42667: {'lr': 0.00041249513647919207, 'samples': 21846016, 'steps': 42667, 'loss/train': 1.1955927610397339}
-03/05/2022 15:37:45 - INFO - codeparrot_training - Skipping example with length 539 (seq_length=1024)
-03/05/2022 15:37:50 - INFO - codeparrot_training - Step 42668: {'lr': 0.00041249110357772167, 'samples': 21846528, 'steps': 42668, 'loss/train': 1.3253178596496582}
-03/05/2022 15:37:53 - INFO - codeparrot_training - Step 42669: {'lr': 0.00041248707060303536, 'samples': 21847040, 'steps': 42669, 'loss/train': 1.6768676042556763}
-03/05/2022 15:37:53 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/05/2022 15:37:58 - INFO - codeparrot_training - Step 42670: {'lr': 0.00041248303755513484, 'samples': 21847552, 'steps': 42670, 'loss/train': 2.063546895980835}
-03/05/2022 15:38:01 - INFO - codeparrot_training - Step 42671: {'lr': 0.00041247900443402194, 'samples': 21848064, 'steps': 42671, 'loss/train': 0.8799605965614319}
-03/05/2022 15:38:02 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/05/2022 15:38:07 - INFO - codeparrot_training - Step 42672: {'lr': 0.00041247497123969844, 'samples': 21848576, 'steps': 42672, 'loss/train': 1.5178639888763428}
-03/05/2022 15:38:10 - INFO - codeparrot_training - Step 42673: {'lr': 0.00041247093797216637, 'samples': 21849088, 'steps': 42673, 'loss/train': 1.8126683235168457}
-03/05/2022 15:38:10 - INFO - codeparrot_training - Skipping example with length 273 (seq_length=1024)
-03/05/2022 15:38:15 - INFO - codeparrot_training - Step 42674: {'lr': 0.00041246690463142733, 'samples': 21849600, 'steps': 42674, 'loss/train': 0.6818129420280457}
-03/05/2022 15:38:18 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/05/2022 15:38:20 - INFO - codeparrot_training - Step 42675: {'lr': 0.0004124628712174833, 'samples': 21850112, 'steps': 42675, 'loss/train': 1.732179880142212}
-03/05/2022 15:38:24 - INFO - codeparrot_training - Step 42676: {'lr': 0.0004124588377303359, 'samples': 21850624, 'steps': 42676, 'loss/train': 0.4207277297973633}
-03/05/2022 15:38:26 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/05/2022 15:38:29 - INFO - codeparrot_training - Step 42677: {'lr': 0.00041245480416998704, 'samples': 21851136, 'steps': 42677, 'loss/train': 1.9485636949539185}
-03/05/2022 15:38:32 - INFO - codeparrot_training - Step 42678: {'lr': 0.0004124507705364386, 'samples': 21851648, 'steps': 42678, 'loss/train': 1.9839813709259033}
-03/05/2022 15:38:35 - INFO - codeparrot_training - Skipping example with length 956 (seq_length=1024)
-03/05/2022 15:38:37 - INFO - codeparrot_training - Step 42679: {'lr': 0.0004124467368296924, 'samples': 21852160, 'steps': 42679, 'loss/train': 1.4094291925430298}
-03/05/2022 15:38:41 - INFO - codeparrot_training - Step 42680: {'lr': 0.00041244270304975004, 'samples': 21852672, 'steps': 42680, 'loss/train': 1.4138314723968506}
-03/05/2022 15:38:43 - INFO - codeparrot_training - Skipping example with length 834 (seq_length=1024)
-03/05/2022 15:38:46 - INFO - codeparrot_training - Step 42681: {'lr': 0.0004124386691966137, 'samples': 21853184, 'steps': 42681, 'loss/train': 1.648011326789856}
-03/05/2022 15:38:49 - INFO - codeparrot_training - Step 42682: {'lr': 0.00041243463527028493, 'samples': 21853696, 'steps': 42682, 'loss/train': 1.362849235534668}
-03/05/2022 15:38:52 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 15:38:54 - INFO - codeparrot_training - Step 42683: {'lr': 0.0004124306012707656, 'samples': 21854208, 'steps': 42683, 'loss/train': 1.96514892578125}
-03/05/2022 15:38:58 - INFO - codeparrot_training - Step 42684: {'lr': 0.00041242656719805754, 'samples': 21854720, 'steps': 42684, 'loss/train': 0.2987481653690338}
-03/05/2022 15:39:00 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 15:39:03 - INFO - codeparrot_training - Step 42685: {'lr': 0.0004124225330521626, 'samples': 21855232, 'steps': 42685, 'loss/train': 1.2649592161178589}
-03/05/2022 15:39:06 - INFO - codeparrot_training - Step 42686: {'lr': 0.0004124184988330826, 'samples': 21855744, 'steps': 42686, 'loss/train': 0.27233895659446716}
-03/05/2022 15:39:09 - INFO - codeparrot_training - Skipping example with length 125 (seq_length=1024)
-03/05/2022 15:39:11 - INFO - codeparrot_training - Step 42687: {'lr': 0.0004124144645408192, 'samples': 21856256, 'steps': 42687, 'loss/train': 0.8218533396720886}
-03/05/2022 15:39:14 - INFO - codeparrot_training - Step 42688: {'lr': 0.0004124104301753745, 'samples': 21856768, 'steps': 42688, 'loss/train': 2.030330181121826}
-03/05/2022 15:39:17 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/05/2022 15:39:20 - INFO - codeparrot_training - Step 42689: {'lr': 0.0004124063957367501, 'samples': 21857280, 'steps': 42689, 'loss/train': 2.1226961612701416}
-03/05/2022 15:39:23 - INFO - codeparrot_training - Step 42690: {'lr': 0.0004124023612249479, 'samples': 21857792, 'steps': 42690, 'loss/train': 1.7168673276901245}
-03/05/2022 15:39:26 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/05/2022 15:39:28 - INFO - codeparrot_training - Step 42691: {'lr': 0.0004123983266399697, 'samples': 21858304, 'steps': 42691, 'loss/train': 1.4981063604354858}
-03/05/2022 15:39:31 - INFO - codeparrot_training - Step 42692: {'lr': 0.0004123942919818173, 'samples': 21858816, 'steps': 42692, 'loss/train': 1.6874425411224365}
-03/05/2022 15:39:34 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/05/2022 15:39:37 - INFO - codeparrot_training - Step 42693: {'lr': 0.00041239025725049256, 'samples': 21859328, 'steps': 42693, 'loss/train': 1.6723387241363525}
-03/05/2022 15:39:40 - INFO - codeparrot_training - Step 42694: {'lr': 0.0004123862224459973, 'samples': 21859840, 'steps': 42694, 'loss/train': 1.9270416498184204}
-03/05/2022 15:39:42 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 15:39:45 - INFO - codeparrot_training - Step 42695: {'lr': 0.0004123821875683333, 'samples': 21860352, 'steps': 42695, 'loss/train': 2.2760426998138428}
-03/05/2022 15:39:48 - INFO - codeparrot_training - Step 42696: {'lr': 0.0004123781526175023, 'samples': 21860864, 'steps': 42696, 'loss/train': 1.8160414695739746}
-03/05/2022 15:39:51 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 15:39:53 - INFO - codeparrot_training - Step 42697: {'lr': 0.0004123741175935063, 'samples': 21861376, 'steps': 42697, 'loss/train': 1.3830658197402954}
-03/05/2022 15:39:57 - INFO - codeparrot_training - Step 42698: {'lr': 0.000412370082496347, 'samples': 21861888, 'steps': 42698, 'loss/train': 2.0445711612701416}
-03/05/2022 15:39:59 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/05/2022 15:40:02 - INFO - codeparrot_training - Step 42699: {'lr': 0.0004123660473260263, 'samples': 21862400, 'steps': 42699, 'loss/train': 1.601873517036438}
-03/05/2022 15:40:05 - INFO - codeparrot_training - Step 42700: {'lr': 0.0004123620120825459, 'samples': 21862912, 'steps': 42700, 'loss/train': 2.14908504486084}
-03/05/2022 15:40:08 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/05/2022 15:40:10 - INFO - codeparrot_training - Step 42701: {'lr': 0.00041235797676590776, 'samples': 21863424, 'steps': 42701, 'loss/train': 0.5090450644493103}
-03/05/2022 15:40:14 - INFO - codeparrot_training - Step 42702: {'lr': 0.0004123539413761136, 'samples': 21863936, 'steps': 42702, 'loss/train': 2.2038376331329346}
-03/05/2022 15:40:16 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 15:40:19 - INFO - codeparrot_training - Step 42703: {'lr': 0.0004123499059131652, 'samples': 21864448, 'steps': 42703, 'loss/train': 1.02668035030365}
-03/05/2022 15:40:22 - INFO - codeparrot_training - Step 42704: {'lr': 0.00041234587037706447, 'samples': 21864960, 'steps': 42704, 'loss/train': 1.4202343225479126}
-03/05/2022 15:40:25 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/05/2022 15:40:28 - INFO - codeparrot_training - Step 42705: {'lr': 0.0004123418347678132, 'samples': 21865472, 'steps': 42705, 'loss/train': 1.851541519165039}
-03/05/2022 15:40:31 - INFO - codeparrot_training - Step 42706: {'lr': 0.00041233779908541316, 'samples': 21865984, 'steps': 42706, 'loss/train': 1.4034013748168945}
-03/05/2022 15:40:33 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 15:40:36 - INFO - codeparrot_training - Step 42707: {'lr': 0.0004123337633298662, 'samples': 21866496, 'steps': 42707, 'loss/train': 0.8666094541549683}
-03/05/2022 15:40:39 - INFO - codeparrot_training - Step 42708: {'lr': 0.0004123297275011743, 'samples': 21867008, 'steps': 42708, 'loss/train': 1.2090715169906616}
-03/05/2022 15:40:42 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/05/2022 15:40:44 - INFO - codeparrot_training - Step 42709: {'lr': 0.00041232569159933895, 'samples': 21867520, 'steps': 42709, 'loss/train': 1.7219743728637695}
-03/05/2022 15:40:48 - INFO - codeparrot_training - Step 42710: {'lr': 0.00041232165562436225, 'samples': 21868032, 'steps': 42710, 'loss/train': 2.175124168395996}
-03/05/2022 15:40:50 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/05/2022 15:40:53 - INFO - codeparrot_training - Step 42711: {'lr': 0.00041231761957624593, 'samples': 21868544, 'steps': 42711, 'loss/train': 2.863513946533203}
-03/05/2022 15:40:56 - INFO - codeparrot_training - Step 42712: {'lr': 0.0004123135834549917, 'samples': 21869056, 'steps': 42712, 'loss/train': 1.7492223978042603}
-03/05/2022 15:40:59 - INFO - codeparrot_training - Skipping example with length 253 (seq_length=1024)
-03/05/2022 15:41:01 - INFO - codeparrot_training - Step 42713: {'lr': 0.00041230954726060155, 'samples': 21869568, 'steps': 42713, 'loss/train': 0.17172910273075104}
-03/05/2022 15:41:05 - INFO - codeparrot_training - Step 42714: {'lr': 0.00041230551099307724, 'samples': 21870080, 'steps': 42714, 'loss/train': 1.8263894319534302}
-03/05/2022 15:41:07 - INFO - codeparrot_training - Skipping example with length 188 (seq_length=1024)
-03/05/2022 15:41:10 - INFO - codeparrot_training - Step 42715: {'lr': 0.0004123014746524205, 'samples': 21870592, 'steps': 42715, 'loss/train': 1.252118468284607}
-03/05/2022 15:41:13 - INFO - codeparrot_training - Step 42716: {'lr': 0.0004122974382386333, 'samples': 21871104, 'steps': 42716, 'loss/train': 2.1624093055725098}
-03/05/2022 15:41:16 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/05/2022 15:41:18 - INFO - codeparrot_training - Step 42717: {'lr': 0.00041229340175171733, 'samples': 21871616, 'steps': 42717, 'loss/train': 2.051084518432617}
-03/05/2022 15:41:22 - INFO - codeparrot_training - Step 42718: {'lr': 0.00041228936519167446, 'samples': 21872128, 'steps': 42718, 'loss/train': 1.7689778804779053}
-03/05/2022 15:41:24 - INFO - codeparrot_training - Skipping example with length 891 (seq_length=1024)
-03/05/2022 15:41:27 - INFO - codeparrot_training - Step 42719: {'lr': 0.00041228532855850655, 'samples': 21872640, 'steps': 42719, 'loss/train': 1.4166237115859985}
-03/05/2022 15:41:30 - INFO - codeparrot_training - Step 42720: {'lr': 0.0004122812918522153, 'samples': 21873152, 'steps': 42720, 'loss/train': 1.7485734224319458}
-03/05/2022 15:41:33 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 15:41:35 - INFO - codeparrot_training - Step 42721: {'lr': 0.0004122772550728027, 'samples': 21873664, 'steps': 42721, 'loss/train': 1.8916828632354736}
-03/05/2022 15:41:38 - INFO - codeparrot_training - Step 42722: {'lr': 0.0004122732182202703, 'samples': 21874176, 'steps': 42722, 'loss/train': 1.2014061212539673}
-03/05/2022 15:41:41 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 15:41:44 - INFO - codeparrot_training - Step 42723: {'lr': 0.0004122691812946202, 'samples': 21874688, 'steps': 42723, 'loss/train': 1.3142404556274414}
-03/05/2022 15:41:47 - INFO - codeparrot_training - Step 42724: {'lr': 0.00041226514429585417, 'samples': 21875200, 'steps': 42724, 'loss/train': 2.2698605060577393}
-03/05/2022 15:41:49 - INFO - codeparrot_training - Skipping example with length 475 (seq_length=1024)
-03/05/2022 15:41:52 - INFO - codeparrot_training - Step 42725: {'lr': 0.0004122611072239739, 'samples': 21875712, 'steps': 42725, 'loss/train': 1.5895013809204102}
-03/05/2022 15:41:55 - INFO - codeparrot_training - Step 42726: {'lr': 0.00041225707007898127, 'samples': 21876224, 'steps': 42726, 'loss/train': 1.849104881286621}
-03/05/2022 15:41:58 - INFO - codeparrot_training - Step 42727: {'lr': 0.0004122530328608781, 'samples': 21876736, 'steps': 42727, 'loss/train': 1.5859540700912476}
-03/05/2022 15:41:59 - INFO - codeparrot_training - Skipping example with length 500 (seq_length=1024)
-03/05/2022 15:42:04 - INFO - codeparrot_training - Step 42728: {'lr': 0.00041224899556966635, 'samples': 21877248, 'steps': 42728, 'loss/train': 1.7715801000595093}
-03/05/2022 15:42:07 - INFO - codeparrot_training - Step 42729: {'lr': 0.00041224495820534757, 'samples': 21877760, 'steps': 42729, 'loss/train': 1.8469213247299194}
-03/05/2022 15:42:07 - INFO - codeparrot_training - Skipping example with length 344 (seq_length=1024)
-03/05/2022 15:42:13 - INFO - codeparrot_training - Step 42730: {'lr': 0.00041224092076792374, 'samples': 21878272, 'steps': 42730, 'loss/train': 1.386015772819519}
-03/05/2022 15:42:16 - INFO - codeparrot_training - Step 42731: {'lr': 0.0004122368832573967, 'samples': 21878784, 'steps': 42731, 'loss/train': 1.1897765398025513}
-03/05/2022 15:42:16 - INFO - codeparrot_training - Skipping example with length 127 (seq_length=1024)
-03/05/2022 15:42:21 - INFO - codeparrot_training - Step 42732: {'lr': 0.00041223284567376816, 'samples': 21879296, 'steps': 42732, 'loss/train': 1.6038023233413696}
-03/05/2022 15:42:24 - INFO - codeparrot_training - Step 42733: {'lr': 0.00041222880801704005, 'samples': 21879808, 'steps': 42733, 'loss/train': 1.625616431236267}
-03/05/2022 15:42:25 - INFO - codeparrot_training - Skipping example with length 67 (seq_length=1024)
-03/05/2022 15:42:30 - INFO - codeparrot_training - Step 42734: {'lr': 0.0004122247702872141, 'samples': 21880320, 'steps': 42734, 'loss/train': 2.000091314315796}
-03/05/2022 15:42:33 - INFO - codeparrot_training - Step 42735: {'lr': 0.0004122207324842923, 'samples': 21880832, 'steps': 42735, 'loss/train': 1.4472936391830444}
-03/05/2022 15:42:33 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/05/2022 15:42:38 - INFO - codeparrot_training - Step 42736: {'lr': 0.00041221669460827614, 'samples': 21881344, 'steps': 42736, 'loss/train': 2.1857991218566895}
-03/05/2022 15:42:41 - INFO - codeparrot_training - Step 42737: {'lr': 0.00041221265665916776, 'samples': 21881856, 'steps': 42737, 'loss/train': 1.8792146444320679}
-03/05/2022 15:42:42 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 15:42:47 - INFO - codeparrot_training - Step 42738: {'lr': 0.00041220861863696886, 'samples': 21882368, 'steps': 42738, 'loss/train': 1.8833445310592651}
-03/05/2022 15:42:50 - INFO - codeparrot_training - Step 42739: {'lr': 0.0004122045805416812, 'samples': 21882880, 'steps': 42739, 'loss/train': 2.2283530235290527}
-03/05/2022 15:42:51 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 15:42:55 - INFO - codeparrot_training - Step 42740: {'lr': 0.00041220054237330674, 'samples': 21883392, 'steps': 42740, 'loss/train': 1.7523986101150513}
-03/05/2022 15:42:59 - INFO - codeparrot_training - Step 42741: {'lr': 0.00041219650413184714, 'samples': 21883904, 'steps': 42741, 'loss/train': 1.3041512966156006}
-03/05/2022 15:42:59 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/05/2022 15:43:04 - INFO - codeparrot_training - Step 42742: {'lr': 0.00041219246581730435, 'samples': 21884416, 'steps': 42742, 'loss/train': 2.254211902618408}
-03/05/2022 15:43:07 - INFO - codeparrot_training - Step 42743: {'lr': 0.0004121884274296801, 'samples': 21884928, 'steps': 42743, 'loss/train': 1.5085549354553223}
-03/05/2022 15:43:08 - INFO - codeparrot_training - Skipping example with length 147 (seq_length=1024)
-03/05/2022 15:43:13 - INFO - codeparrot_training - Step 42744: {'lr': 0.00041218438896897623, 'samples': 21885440, 'steps': 42744, 'loss/train': 1.547971487045288}
-03/05/2022 15:43:16 - INFO - codeparrot_training - Step 42745: {'lr': 0.00041218035043519464, 'samples': 21885952, 'steps': 42745, 'loss/train': 2.1144461631774902}
-03/05/2022 15:43:19 - INFO - codeparrot_training - Step 42746: {'lr': 0.00041217631182833707, 'samples': 21886464, 'steps': 42746, 'loss/train': 1.9241397380828857}
-03/05/2022 15:43:19 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 15:43:25 - INFO - codeparrot_training - Step 42747: {'lr': 0.00041217227314840535, 'samples': 21886976, 'steps': 42747, 'loss/train': 0.9467313289642334}
-03/05/2022 15:43:30 - INFO - codeparrot_training - Step 42748: {'lr': 0.00041216823439540134, 'samples': 21887488, 'steps': 42748, 'loss/train': 1.5583304166793823}
-03/05/2022 15:43:33 - INFO - codeparrot_training - Step 42749: {'lr': 0.0004121641955693268, 'samples': 21888000, 'steps': 42749, 'loss/train': 0.7617923021316528}
-03/05/2022 15:43:36 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 15:43:38 - INFO - codeparrot_training - Step 42750: {'lr': 0.00041216015667018357, 'samples': 21888512, 'steps': 42750, 'loss/train': 2.350048780441284}
-03/05/2022 15:43:42 - INFO - codeparrot_training - Step 42751: {'lr': 0.00041215611769797344, 'samples': 21889024, 'steps': 42751, 'loss/train': 1.6236004829406738}
-03/05/2022 15:43:45 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/05/2022 15:43:47 - INFO - codeparrot_training - Step 42752: {'lr': 0.00041215207865269833, 'samples': 21889536, 'steps': 42752, 'loss/train': 1.8739979267120361}
-03/05/2022 15:43:50 - INFO - codeparrot_training - Step 42753: {'lr': 0.00041214803953435993, 'samples': 21890048, 'steps': 42753, 'loss/train': 0.5973657965660095}
-03/05/2022 15:43:53 - INFO - codeparrot_training - Skipping example with length 767 (seq_length=1024)
-03/05/2022 15:43:55 - INFO - codeparrot_training - Step 42754: {'lr': 0.0004121440003429602, 'samples': 21890560, 'steps': 42754, 'loss/train': 2.0812768936157227}
-03/05/2022 15:43:59 - INFO - codeparrot_training - Step 42755: {'lr': 0.0004121399610785008, 'samples': 21891072, 'steps': 42755, 'loss/train': 2.3285913467407227}
-03/05/2022 15:44:01 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/05/2022 15:44:04 - INFO - codeparrot_training - Step 42756: {'lr': 0.00041213592174098367, 'samples': 21891584, 'steps': 42756, 'loss/train': 1.6024234294891357}
-03/05/2022 15:44:07 - INFO - codeparrot_training - Step 42757: {'lr': 0.00041213188233041065, 'samples': 21892096, 'steps': 42757, 'loss/train': 2.207092046737671}
-03/05/2022 15:44:10 - INFO - codeparrot_training - Skipping example with length 926 (seq_length=1024)
-03/05/2022 15:44:12 - INFO - codeparrot_training - Step 42758: {'lr': 0.00041212784284678345, 'samples': 21892608, 'steps': 42758, 'loss/train': 1.9851902723312378}
-03/05/2022 15:44:15 - INFO - codeparrot_training - Step 42759: {'lr': 0.0004121238032901039, 'samples': 21893120, 'steps': 42759, 'loss/train': 1.4391775131225586}
-03/05/2022 15:44:18 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/05/2022 15:44:21 - INFO - codeparrot_training - Step 42760: {'lr': 0.00041211976366037394, 'samples': 21893632, 'steps': 42760, 'loss/train': 1.590732455253601}
-03/05/2022 15:44:24 - INFO - codeparrot_training - Step 42761: {'lr': 0.0004121157239575953, 'samples': 21894144, 'steps': 42761, 'loss/train': 1.5049831867218018}
-03/05/2022 15:44:26 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/05/2022 15:44:29 - INFO - codeparrot_training - Step 42762: {'lr': 0.0004121116841817699, 'samples': 21894656, 'steps': 42762, 'loss/train': 2.074350357055664}
-03/05/2022 15:44:32 - INFO - codeparrot_training - Step 42763: {'lr': 0.00041210764433289936, 'samples': 21895168, 'steps': 42763, 'loss/train': 1.2239892482757568}
-03/05/2022 15:44:35 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/05/2022 15:44:37 - INFO - codeparrot_training - Step 42764: {'lr': 0.0004121036044109856, 'samples': 21895680, 'steps': 42764, 'loss/train': 1.9655356407165527}
-03/05/2022 15:44:41 - INFO - codeparrot_training - Step 42765: {'lr': 0.00041209956441603054, 'samples': 21896192, 'steps': 42765, 'loss/train': 1.6302776336669922}
-03/05/2022 15:44:43 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 15:44:46 - INFO - codeparrot_training - Step 42766: {'lr': 0.0004120955243480359, 'samples': 21896704, 'steps': 42766, 'loss/train': 2.19368839263916}
-03/05/2022 15:44:49 - INFO - codeparrot_training - Step 42767: {'lr': 0.0004120914842070035, 'samples': 21897216, 'steps': 42767, 'loss/train': 1.770149827003479}
-03/05/2022 15:44:52 - INFO - codeparrot_training - Step 42768: {'lr': 0.0004120874439929352, 'samples': 21897728, 'steps': 42768, 'loss/train': 1.7086412906646729}
-03/05/2022 15:44:53 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/05/2022 15:44:58 - INFO - codeparrot_training - Step 42769: {'lr': 0.00041208340370583275, 'samples': 21898240, 'steps': 42769, 'loss/train': 2.256742477416992}
-03/05/2022 15:45:01 - INFO - codeparrot_training - Step 42770: {'lr': 0.0004120793633456981, 'samples': 21898752, 'steps': 42770, 'loss/train': 1.6561298370361328}
-03/05/2022 15:45:01 - INFO - codeparrot_training - Skipping example with length 729 (seq_length=1024)
-03/05/2022 15:45:06 - INFO - codeparrot_training - Step 42771: {'lr': 0.0004120753229125329, 'samples': 21899264, 'steps': 42771, 'loss/train': 1.6714845895767212}
-03/05/2022 15:45:09 - INFO - codeparrot_training - Step 42772: {'lr': 0.00041207128240633906, 'samples': 21899776, 'steps': 42772, 'loss/train': 1.1540937423706055}
-03/05/2022 15:45:10 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/05/2022 15:45:15 - INFO - codeparrot_training - Step 42773: {'lr': 0.0004120672418271184, 'samples': 21900288, 'steps': 42773, 'loss/train': 1.5228469371795654}
-03/05/2022 15:45:18 - INFO - codeparrot_training - Step 42774: {'lr': 0.0004120632011748728, 'samples': 21900800, 'steps': 42774, 'loss/train': 1.5609588623046875}
-03/05/2022 15:45:18 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/05/2022 15:45:23 - INFO - codeparrot_training - Step 42775: {'lr': 0.00041205916044960406, 'samples': 21901312, 'steps': 42775, 'loss/train': 1.924135684967041}
-03/05/2022 15:45:26 - INFO - codeparrot_training - Step 42776: {'lr': 0.0004120551196513139, 'samples': 21901824, 'steps': 42776, 'loss/train': 1.5275659561157227}
-03/05/2022 15:45:26 - INFO - codeparrot_training - Skipping example with length 768 (seq_length=1024)
-03/05/2022 15:45:31 - INFO - codeparrot_training - Step 42777: {'lr': 0.0004120510787800042, 'samples': 21902336, 'steps': 42777, 'loss/train': 1.9788434505462646}
-03/05/2022 15:45:35 - INFO - codeparrot_training - Step 42778: {'lr': 0.0004120470378356768, 'samples': 21902848, 'steps': 42778, 'loss/train': 1.619396448135376}
-03/05/2022 15:45:35 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 15:45:40 - INFO - codeparrot_training - Step 42779: {'lr': 0.00041204299681833344, 'samples': 21903360, 'steps': 42779, 'loss/train': 2.596681594848633}
-03/05/2022 15:45:43 - INFO - codeparrot_training - Step 42780: {'lr': 0.00041203895572797613, 'samples': 21903872, 'steps': 42780, 'loss/train': 2.020738363265991}
-03/05/2022 15:45:43 - INFO - codeparrot_training - Skipping example with length 552 (seq_length=1024)
-03/05/2022 15:45:48 - INFO - codeparrot_training - Step 42781: {'lr': 0.00041203491456460653, 'samples': 21904384, 'steps': 42781, 'loss/train': 1.425352931022644}
-03/05/2022 15:45:52 - INFO - codeparrot_training - Step 42782: {'lr': 0.00041203087332822644, 'samples': 21904896, 'steps': 42782, 'loss/train': 1.8406902551651}
-03/05/2022 15:45:52 - INFO - codeparrot_training - Skipping example with length 537 (seq_length=1024)
-03/05/2022 15:45:57 - INFO - codeparrot_training - Step 42783: {'lr': 0.0004120268320188378, 'samples': 21905408, 'steps': 42783, 'loss/train': 1.4105212688446045}
-03/05/2022 15:46:00 - INFO - codeparrot_training - Step 42784: {'lr': 0.00041202279063644234, 'samples': 21905920, 'steps': 42784, 'loss/train': 2.1503026485443115}
-03/05/2022 15:46:00 - INFO - codeparrot_training - Skipping example with length 1017 (seq_length=1024)
-03/05/2022 15:46:05 - INFO - codeparrot_training - Step 42785: {'lr': 0.00041201874918104185, 'samples': 21906432, 'steps': 42785, 'loss/train': 0.555250346660614}
-03/05/2022 15:46:09 - INFO - codeparrot_training - Step 42786: {'lr': 0.0004120147076526383, 'samples': 21906944, 'steps': 42786, 'loss/train': 1.325240969657898}
-03/05/2022 15:46:09 - INFO - codeparrot_training - Skipping example with length 966 (seq_length=1024)
-03/05/2022 15:46:14 - INFO - codeparrot_training - Step 42787: {'lr': 0.0004120106660512334, 'samples': 21907456, 'steps': 42787, 'loss/train': 1.6578264236450195}
-03/05/2022 15:46:17 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/05/2022 15:46:19 - INFO - codeparrot_training - Step 42788: {'lr': 0.000412006624376829, 'samples': 21907968, 'steps': 42788, 'loss/train': 1.7829493284225464}
-03/05/2022 15:46:22 - INFO - codeparrot_training - Step 42789: {'lr': 0.0004120025826294269, 'samples': 21908480, 'steps': 42789, 'loss/train': 1.9578344821929932}
-03/05/2022 15:46:25 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/05/2022 15:46:28 - INFO - codeparrot_training - Step 42790: {'lr': 0.00041199854080902897, 'samples': 21908992, 'steps': 42790, 'loss/train': 1.5284433364868164}
-03/05/2022 15:46:31 - INFO - codeparrot_training - Step 42791: {'lr': 0.00041199449891563694, 'samples': 21909504, 'steps': 42791, 'loss/train': 1.8284574747085571}
-03/05/2022 15:46:34 - INFO - codeparrot_training - Skipping example with length 655 (seq_length=1024)
-03/05/2022 15:46:36 - INFO - codeparrot_training - Step 42792: {'lr': 0.00041199045694925273, 'samples': 21910016, 'steps': 42792, 'loss/train': 1.6553776264190674}
-03/05/2022 15:46:39 - INFO - codeparrot_training - Step 42793: {'lr': 0.0004119864149098781, 'samples': 21910528, 'steps': 42793, 'loss/train': 2.029451608657837}
-03/05/2022 15:46:42 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/05/2022 15:46:45 - INFO - codeparrot_training - Step 42794: {'lr': 0.0004119823727975149, 'samples': 21911040, 'steps': 42794, 'loss/train': 1.702526569366455}
-03/05/2022 15:46:48 - INFO - codeparrot_training - Step 42795: {'lr': 0.00041197833061216494, 'samples': 21911552, 'steps': 42795, 'loss/train': 1.8386863470077515}
-03/05/2022 15:46:51 - INFO - codeparrot_training - Step 42796: {'lr': 0.00041197428835383, 'samples': 21912064, 'steps': 42796, 'loss/train': 0.16086485981941223}
-03/05/2022 15:46:51 - INFO - codeparrot_training - Skipping example with length 294 (seq_length=1024)
-03/05/2022 15:46:56 - INFO - codeparrot_training - Step 42797: {'lr': 0.00041197024602251204, 'samples': 21912576, 'steps': 42797, 'loss/train': 2.0274221897125244}
-03/05/2022 15:46:59 - INFO - codeparrot_training - Step 42798: {'lr': 0.0004119662036182127, 'samples': 21913088, 'steps': 42798, 'loss/train': 0.7845781445503235}
-03/05/2022 15:47:00 - INFO - codeparrot_training - Skipping example with length 796 (seq_length=1024)
-03/05/2022 15:47:05 - INFO - codeparrot_training - Step 42799: {'lr': 0.00041196216114093397, 'samples': 21913600, 'steps': 42799, 'loss/train': 1.8740154504776}
-03/05/2022 15:47:08 - INFO - codeparrot_training - Step 42800: {'lr': 0.00041195811859067756, 'samples': 21914112, 'steps': 42800, 'loss/train': 1.9704105854034424}
-03/05/2022 15:47:08 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/05/2022 15:47:13 - INFO - codeparrot_training - Step 42801: {'lr': 0.0004119540759674453, 'samples': 21914624, 'steps': 42801, 'loss/train': 1.5315043926239014}
-03/05/2022 15:47:17 - INFO - codeparrot_training - Step 42802: {'lr': 0.000411950033271239, 'samples': 21915136, 'steps': 42802, 'loss/train': 1.0004606246948242}
-03/05/2022 15:47:17 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/05/2022 15:47:22 - INFO - codeparrot_training - Step 42803: {'lr': 0.0004119459905020606, 'samples': 21915648, 'steps': 42803, 'loss/train': 2.0930356979370117}
-03/05/2022 15:47:25 - INFO - codeparrot_training - Step 42804: {'lr': 0.0004119419476599118, 'samples': 21916160, 'steps': 42804, 'loss/train': 1.023355484008789}
-03/05/2022 15:47:26 - INFO - codeparrot_training - Skipping example with length 866 (seq_length=1024)
-03/05/2022 15:47:30 - INFO - codeparrot_training - Step 42805: {'lr': 0.0004119379047447944, 'samples': 21916672, 'steps': 42805, 'loss/train': 0.625810444355011}
-03/05/2022 15:47:34 - INFO - codeparrot_training - Step 42806: {'lr': 0.00041193386175671033, 'samples': 21917184, 'steps': 42806, 'loss/train': 1.6625497341156006}
-03/05/2022 15:47:34 - INFO - codeparrot_training - Skipping example with length 977 (seq_length=1024)
-03/05/2022 15:47:39 - INFO - codeparrot_training - Step 42807: {'lr': 0.0004119298186956613, 'samples': 21917696, 'steps': 42807, 'loss/train': 2.101712226867676}
-03/05/2022 15:47:42 - INFO - codeparrot_training - Step 42808: {'lr': 0.00041192577556164924, 'samples': 21918208, 'steps': 42808, 'loss/train': 1.9134345054626465}
-03/05/2022 15:47:42 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/05/2022 15:47:47 - INFO - codeparrot_training - Step 42809: {'lr': 0.000411921732354676, 'samples': 21918720, 'steps': 42809, 'loss/train': 1.7600204944610596}
-03/05/2022 15:47:50 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 15:47:53 - INFO - codeparrot_training - Step 42810: {'lr': 0.00041191768907474326, 'samples': 21919232, 'steps': 42810, 'loss/train': 1.8339204788208008}
-03/05/2022 15:47:56 - INFO - codeparrot_training - Step 42811: {'lr': 0.00041191364572185286, 'samples': 21919744, 'steps': 42811, 'loss/train': 2.1058924198150635}
-03/05/2022 15:47:59 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 15:48:01 - INFO - codeparrot_training - Step 42812: {'lr': 0.0004119096022960067, 'samples': 21920256, 'steps': 42812, 'loss/train': 1.8266011476516724}
-03/05/2022 15:48:04 - INFO - codeparrot_training - Step 42813: {'lr': 0.0004119055587972066, 'samples': 21920768, 'steps': 42813, 'loss/train': 1.161710500717163}
-03/05/2022 15:48:07 - INFO - codeparrot_training - Skipping example with length 593 (seq_length=1024)
-03/05/2022 15:48:10 - INFO - codeparrot_training - Step 42814: {'lr': 0.0004119015152254543, 'samples': 21921280, 'steps': 42814, 'loss/train': 1.6253845691680908}
-03/05/2022 15:48:13 - INFO - codeparrot_training - Step 42815: {'lr': 0.00041189747158075176, 'samples': 21921792, 'steps': 42815, 'loss/train': 1.743550181388855}
-03/05/2022 15:48:16 - INFO - codeparrot_training - Step 42816: {'lr': 0.00041189342786310067, 'samples': 21922304, 'steps': 42816, 'loss/train': 0.4571826159954071}
-03/05/2022 15:48:17 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/05/2022 15:48:22 - INFO - codeparrot_training - Step 42817: {'lr': 0.0004118893840725029, 'samples': 21922816, 'steps': 42817, 'loss/train': 0.9150810241699219}
-03/05/2022 15:48:25 - INFO - codeparrot_training - Step 42818: {'lr': 0.0004118853402089603, 'samples': 21923328, 'steps': 42818, 'loss/train': 2.244621992111206}
-03/05/2022 15:48:25 - INFO - codeparrot_training - Skipping example with length 626 (seq_length=1024)
-03/05/2022 15:48:30 - INFO - codeparrot_training - Step 42819: {'lr': 0.0004118812962724746, 'samples': 21923840, 'steps': 42819, 'loss/train': 1.1738590002059937}
-03/05/2022 15:48:33 - INFO - codeparrot_training - Step 42820: {'lr': 0.00041187725226304775, 'samples': 21924352, 'steps': 42820, 'loss/train': 2.191650152206421}
-03/05/2022 15:48:34 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/05/2022 15:48:38 - INFO - codeparrot_training - Step 42821: {'lr': 0.0004118732081806814, 'samples': 21924864, 'steps': 42821, 'loss/train': 1.415942668914795}
-03/05/2022 15:48:42 - INFO - codeparrot_training - Step 42822: {'lr': 0.0004118691640253777, 'samples': 21925376, 'steps': 42822, 'loss/train': 1.2382804155349731}
-03/05/2022 15:48:42 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/05/2022 15:48:47 - INFO - codeparrot_training - Step 42823: {'lr': 0.00041186511979713806, 'samples': 21925888, 'steps': 42823, 'loss/train': 1.3007097244262695}
-03/05/2022 15:48:51 - INFO - codeparrot_training - Step 42824: {'lr': 0.00041186107549596453, 'samples': 21926400, 'steps': 42824, 'loss/train': 2.3830666542053223}
-03/05/2022 15:48:53 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/05/2022 15:48:56 - INFO - codeparrot_training - Step 42825: {'lr': 0.0004118570311218589, 'samples': 21926912, 'steps': 42825, 'loss/train': 1.7277246713638306}
-03/05/2022 15:48:59 - INFO - codeparrot_training - Step 42826: {'lr': 0.00041185298667482294, 'samples': 21927424, 'steps': 42826, 'loss/train': 1.489262580871582}
-03/05/2022 15:49:02 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/05/2022 15:49:04 - INFO - codeparrot_training - Step 42827: {'lr': 0.0004118489421548586, 'samples': 21927936, 'steps': 42827, 'loss/train': 1.666790246963501}
-03/05/2022 15:49:08 - INFO - codeparrot_training - Step 42828: {'lr': 0.00041184489756196764, 'samples': 21928448, 'steps': 42828, 'loss/train': 1.3520114421844482}
-03/05/2022 15:49:10 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/05/2022 15:49:13 - INFO - codeparrot_training - Step 42829: {'lr': 0.0004118408528961519, 'samples': 21928960, 'steps': 42829, 'loss/train': 1.8272122144699097}
-03/05/2022 15:49:16 - INFO - codeparrot_training - Step 42830: {'lr': 0.00041183680815741307, 'samples': 21929472, 'steps': 42830, 'loss/train': 1.4889106750488281}
-03/05/2022 15:49:18 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/05/2022 15:49:21 - INFO - codeparrot_training - Step 42831: {'lr': 0.0004118327633457531, 'samples': 21929984, 'steps': 42831, 'loss/train': 2.300328016281128}
-03/05/2022 15:49:24 - INFO - codeparrot_training - Step 42832: {'lr': 0.00041182871846117373, 'samples': 21930496, 'steps': 42832, 'loss/train': 1.9306714534759521}
-03/05/2022 15:49:27 - INFO - codeparrot_training - Skipping example with length 753 (seq_length=1024)
-03/05/2022 15:49:30 - INFO - codeparrot_training - Step 42833: {'lr': 0.0004118246735036769, 'samples': 21931008, 'steps': 42833, 'loss/train': 0.5739752054214478}
-03/05/2022 15:49:33 - INFO - codeparrot_training - Step 42834: {'lr': 0.0004118206284732644, 'samples': 21931520, 'steps': 42834, 'loss/train': 1.9829003810882568}
-03/05/2022 15:49:35 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 15:49:38 - INFO - codeparrot_training - Step 42835: {'lr': 0.000411816583369938, 'samples': 21932032, 'steps': 42835, 'loss/train': 1.2517482042312622}
-03/05/2022 15:49:41 - INFO - codeparrot_training - Step 42836: {'lr': 0.0004118125381936996, 'samples': 21932544, 'steps': 42836, 'loss/train': 1.5283795595169067}
-03/05/2022 15:49:44 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/05/2022 15:49:47 - INFO - codeparrot_training - Step 42837: {'lr': 0.0004118084929445508, 'samples': 21933056, 'steps': 42837, 'loss/train': 0.88991779088974}
-03/05/2022 15:49:50 - INFO - codeparrot_training - Step 42838: {'lr': 0.0004118044476224937, 'samples': 21933568, 'steps': 42838, 'loss/train': 1.7270742654800415}
-03/05/2022 15:49:52 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/05/2022 15:49:55 - INFO - codeparrot_training - Step 42839: {'lr': 0.00041180040222753, 'samples': 21934080, 'steps': 42839, 'loss/train': 1.8535641431808472}
-03/05/2022 15:49:58 - INFO - codeparrot_training - Step 42840: {'lr': 0.00041179635675966155, 'samples': 21934592, 'steps': 42840, 'loss/train': 1.3298977613449097}
-03/05/2022 15:50:01 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/05/2022 15:50:03 - INFO - codeparrot_training - Step 42841: {'lr': 0.00041179231121889014, 'samples': 21935104, 'steps': 42841, 'loss/train': 1.8178684711456299}
-03/05/2022 15:50:07 - INFO - codeparrot_training - Step 42842: {'lr': 0.0004117882656052176, 'samples': 21935616, 'steps': 42842, 'loss/train': 2.0543134212493896}
-03/05/2022 15:50:09 - INFO - codeparrot_training - Skipping example with length 460 (seq_length=1024)
-03/05/2022 15:50:12 - INFO - codeparrot_training - Step 42843: {'lr': 0.0004117842199186458, 'samples': 21936128, 'steps': 42843, 'loss/train': 1.6085585355758667}
-03/05/2022 15:50:15 - INFO - codeparrot_training - Step 42844: {'lr': 0.00041178017415917655, 'samples': 21936640, 'steps': 42844, 'loss/train': 1.1796447038650513}
-03/05/2022 15:50:17 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/05/2022 15:50:20 - INFO - codeparrot_training - Step 42845: {'lr': 0.00041177612832681156, 'samples': 21937152, 'steps': 42845, 'loss/train': 1.789637565612793}
-03/05/2022 15:50:23 - INFO - codeparrot_training - Step 42846: {'lr': 0.00041177208242155285, 'samples': 21937664, 'steps': 42846, 'loss/train': 3.184438943862915}
-03/05/2022 15:50:26 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/05/2022 15:50:29 - INFO - codeparrot_training - Step 42847: {'lr': 0.000411768036443402, 'samples': 21938176, 'steps': 42847, 'loss/train': 1.4647876024246216}
-03/05/2022 15:50:32 - INFO - codeparrot_training - Step 42848: {'lr': 0.0004117639903923611, 'samples': 21938688, 'steps': 42848, 'loss/train': 1.1802353858947754}
-03/05/2022 15:50:34 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/05/2022 15:50:37 - INFO - codeparrot_training - Step 42849: {'lr': 0.00041175994426843177, 'samples': 21939200, 'steps': 42849, 'loss/train': 1.9439866542816162}
-03/05/2022 15:50:40 - INFO - codeparrot_training - Step 42850: {'lr': 0.00041175589807161597, 'samples': 21939712, 'steps': 42850, 'loss/train': 1.4544365406036377}
-03/05/2022 15:50:43 - INFO - codeparrot_training - Skipping example with length 358 (seq_length=1024)
-03/05/2022 15:50:46 - INFO - codeparrot_training - Step 42851: {'lr': 0.0004117518518019154, 'samples': 21940224, 'steps': 42851, 'loss/train': 1.6293222904205322}
-03/05/2022 15:50:49 - INFO - codeparrot_training - Step 42852: {'lr': 0.00041174780545933195, 'samples': 21940736, 'steps': 42852, 'loss/train': 1.5851179361343384}
-03/05/2022 15:50:52 - INFO - codeparrot_training - Step 42853: {'lr': 0.0004117437590438674, 'samples': 21941248, 'steps': 42853, 'loss/train': 0.5099883675575256}
-03/05/2022 15:50:52 - INFO - codeparrot_training - Skipping example with length 851 (seq_length=1024)
-03/05/2022 15:50:58 - INFO - codeparrot_training - Step 42854: {'lr': 0.0004117397125555237, 'samples': 21941760, 'steps': 42854, 'loss/train': 1.437559723854065}
-03/05/2022 15:51:01 - INFO - codeparrot_training - Step 42855: {'lr': 0.00041173566599430245, 'samples': 21942272, 'steps': 42855, 'loss/train': 1.9179950952529907}
-03/05/2022 15:51:01 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/05/2022 15:51:06 - INFO - codeparrot_training - Step 42856: {'lr': 0.00041173161936020573, 'samples': 21942784, 'steps': 42856, 'loss/train': 2.434746265411377}
-03/05/2022 15:51:09 - INFO - codeparrot_training - Step 42857: {'lr': 0.0004117275726532352, 'samples': 21943296, 'steps': 42857, 'loss/train': 1.7837374210357666}
-03/05/2022 15:51:09 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/05/2022 15:51:15 - INFO - codeparrot_training - Step 42858: {'lr': 0.0004117235258733927, 'samples': 21943808, 'steps': 42858, 'loss/train': 1.0763053894042969}
-03/05/2022 15:51:17 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/05/2022 15:51:20 - INFO - codeparrot_training - Step 42859: {'lr': 0.00041171947902068006, 'samples': 21944320, 'steps': 42859, 'loss/train': 1.4975147247314453}
-03/05/2022 15:51:23 - INFO - codeparrot_training - Step 42860: {'lr': 0.00041171543209509923, 'samples': 21944832, 'steps': 42860, 'loss/train': 1.8779345750808716}
-03/05/2022 15:51:26 - INFO - codeparrot_training - Step 42861: {'lr': 0.0004117113850966517, 'samples': 21945344, 'steps': 42861, 'loss/train': 1.1424118280410767}
-03/05/2022 15:51:27 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/05/2022 15:51:32 - INFO - codeparrot_training - Step 42862: {'lr': 0.00041170733802533974, 'samples': 21945856, 'steps': 42862, 'loss/train': 1.5835983753204346}
-03/05/2022 15:51:35 - INFO - codeparrot_training - Step 42863: {'lr': 0.0004117032908811649, 'samples': 21946368, 'steps': 42863, 'loss/train': 1.9538789987564087}
-03/05/2022 15:51:36 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/05/2022 15:51:40 - INFO - codeparrot_training - Step 42864: {'lr': 0.000411699243664129, 'samples': 21946880, 'steps': 42864, 'loss/train': 1.421123743057251}
-03/05/2022 15:51:43 - INFO - codeparrot_training - Step 42865: {'lr': 0.00041169519637423394, 'samples': 21947392, 'steps': 42865, 'loss/train': 1.6040817499160767}
-03/05/2022 15:51:44 - INFO - codeparrot_training - Skipping example with length 58 (seq_length=1024)
-03/05/2022 15:51:49 - INFO - codeparrot_training - Step 42866: {'lr': 0.0004116911490114815, 'samples': 21947904, 'steps': 42866, 'loss/train': 1.2416244745254517}
-03/05/2022 15:51:52 - INFO - codeparrot_training - Step 42867: {'lr': 0.0004116871015758735, 'samples': 21948416, 'steps': 42867, 'loss/train': 1.6972624063491821}
-03/05/2022 15:51:52 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/05/2022 15:51:57 - INFO - codeparrot_training - Step 42868: {'lr': 0.0004116830540674118, 'samples': 21948928, 'steps': 42868, 'loss/train': 1.759318470954895}
-03/05/2022 15:52:00 - INFO - codeparrot_training - Step 42869: {'lr': 0.00041167900648609825, 'samples': 21949440, 'steps': 42869, 'loss/train': 0.9126895070075989}
-03/05/2022 15:52:01 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/05/2022 15:52:05 - INFO - codeparrot_training - Step 42870: {'lr': 0.00041167495883193464, 'samples': 21949952, 'steps': 42870, 'loss/train': 2.0677406787872314}
-03/05/2022 15:52:09 - INFO - codeparrot_training - Step 42871: {'lr': 0.00041167091110492273, 'samples': 21950464, 'steps': 42871, 'loss/train': 2.0678718090057373}
-03/05/2022 15:52:09 - INFO - codeparrot_training - Skipping example with length 554 (seq_length=1024)
-03/05/2022 15:52:14 - INFO - codeparrot_training - Step 42872: {'lr': 0.0004116668633050644, 'samples': 21950976, 'steps': 42872, 'loss/train': 0.8636013865470886}
-03/05/2022 15:52:17 - INFO - codeparrot_training - Step 42873: {'lr': 0.0004116628154323616, 'samples': 21951488, 'steps': 42873, 'loss/train': 1.210692048072815}
-03/05/2022 15:52:18 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/05/2022 15:52:22 - INFO - codeparrot_training - Step 42874: {'lr': 0.0004116587674868159, 'samples': 21952000, 'steps': 42874, 'loss/train': 1.8437429666519165}
-03/05/2022 15:52:25 - INFO - codeparrot_training - Step 42875: {'lr': 0.00041165471946842924, 'samples': 21952512, 'steps': 42875, 'loss/train': 1.5773921012878418}
-03/05/2022 15:52:31 - INFO - codeparrot_training - Step 42876: {'lr': 0.00041165067137720356, 'samples': 21953024, 'steps': 42876, 'loss/train': 2.0570290088653564}
-03/05/2022 15:52:34 - INFO - codeparrot_training - Step 42877: {'lr': 0.00041164662321314054, 'samples': 21953536, 'steps': 42877, 'loss/train': 1.7495417594909668}
-03/05/2022 15:52:35 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/05/2022 15:52:39 - INFO - codeparrot_training - Step 42878: {'lr': 0.000411642574976242, 'samples': 21954048, 'steps': 42878, 'loss/train': 1.7820298671722412}
-03/05/2022 15:52:42 - INFO - codeparrot_training - Step 42879: {'lr': 0.0004116385266665099, 'samples': 21954560, 'steps': 42879, 'loss/train': 1.6945050954818726}
-03/05/2022 15:52:43 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/05/2022 15:52:48 - INFO - codeparrot_training - Step 42880: {'lr': 0.0004116344782839459, 'samples': 21955072, 'steps': 42880, 'loss/train': 1.6115431785583496}
-03/05/2022 15:52:51 - INFO - codeparrot_training - Step 42881: {'lr': 0.00041163042982855194, 'samples': 21955584, 'steps': 42881, 'loss/train': 2.0423243045806885}
-03/05/2022 15:52:52 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/05/2022 15:52:56 - INFO - codeparrot_training - Step 42882: {'lr': 0.00041162638130032975, 'samples': 21956096, 'steps': 42882, 'loss/train': 1.9637259244918823}
-03/05/2022 15:52:59 - INFO - codeparrot_training - Step 42883: {'lr': 0.00041162233269928126, 'samples': 21956608, 'steps': 42883, 'loss/train': 1.4328540563583374}
-03/05/2022 15:53:00 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/05/2022 15:53:05 - INFO - codeparrot_training - Step 42884: {'lr': 0.0004116182840254082, 'samples': 21957120, 'steps': 42884, 'loss/train': 1.6122262477874756}
-03/05/2022 15:53:08 - INFO - codeparrot_training - Step 42885: {'lr': 0.0004116142352787125, 'samples': 21957632, 'steps': 42885, 'loss/train': 1.80718994140625}
-03/05/2022 15:53:09 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/05/2022 15:53:13 - INFO - codeparrot_training - Step 42886: {'lr': 0.00041161018645919593, 'samples': 21958144, 'steps': 42886, 'loss/train': 1.8426876068115234}
-03/05/2022 15:53:17 - INFO - codeparrot_training - Step 42887: {'lr': 0.00041160613756686015, 'samples': 21958656, 'steps': 42887, 'loss/train': 1.6919313669204712}
-03/05/2022 15:53:17 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/05/2022 15:53:22 - INFO - codeparrot_training - Step 42888: {'lr': 0.00041160208860170725, 'samples': 21959168, 'steps': 42888, 'loss/train': 1.940449595451355}
-03/05/2022 15:53:25 - INFO - codeparrot_training - Step 42889: {'lr': 0.000411598039563739, 'samples': 21959680, 'steps': 42889, 'loss/train': 2.4017205238342285}
-03/05/2022 15:53:26 - INFO - codeparrot_training - Skipping example with length 141 (seq_length=1024)
-03/05/2022 15:53:30 - INFO - codeparrot_training - Step 42890: {'lr': 0.0004115939904529571, 'samples': 21960192, 'steps': 42890, 'loss/train': 1.8484723567962646}
-03/05/2022 15:53:33 - INFO - codeparrot_training - Step 42891: {'lr': 0.00041158994126936347, 'samples': 21960704, 'steps': 42891, 'loss/train': 2.2017900943756104}
-03/05/2022 15:53:34 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/05/2022 15:53:39 - INFO - codeparrot_training - Step 42892: {'lr': 0.0004115858920129598, 'samples': 21961216, 'steps': 42892, 'loss/train': 1.8025238513946533}
-03/05/2022 15:53:42 - INFO - codeparrot_training - Step 42893: {'lr': 0.0004115818426837481, 'samples': 21961728, 'steps': 42893, 'loss/train': 2.434748649597168}
-03/05/2022 15:53:42 - INFO - codeparrot_training - Skipping example with length 44 (seq_length=1024)
-03/05/2022 15:53:47 - INFO - codeparrot_training - Step 42894: {'lr': 0.0004115777932817301, 'samples': 21962240, 'steps': 42894, 'loss/train': 0.6370025873184204}
-03/05/2022 15:53:50 - INFO - codeparrot_training - Step 42895: {'lr': 0.00041157374380690765, 'samples': 21962752, 'steps': 42895, 'loss/train': 0.6113659143447876}
-03/05/2022 15:53:50 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 15:53:55 - INFO - codeparrot_training - Step 42896: {'lr': 0.0004115696942592826, 'samples': 21963264, 'steps': 42896, 'loss/train': 2.404186964035034}
-03/05/2022 15:53:59 - INFO - codeparrot_training - Step 42897: {'lr': 0.0004115656446388567, 'samples': 21963776, 'steps': 42897, 'loss/train': 1.7795010805130005}
-03/05/2022 15:53:59 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/05/2022 15:54:04 - INFO - codeparrot_training - Step 42898: {'lr': 0.00041156159494563183, 'samples': 21964288, 'steps': 42898, 'loss/train': 1.865553855895996}
-03/05/2022 15:54:07 - INFO - codeparrot_training - Step 42899: {'lr': 0.00041155754517960974, 'samples': 21964800, 'steps': 42899, 'loss/train': 1.6442469358444214}
-03/05/2022 15:54:07 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/05/2022 15:54:12 - INFO - codeparrot_training - Step 42900: {'lr': 0.00041155349534079236, 'samples': 21965312, 'steps': 42900, 'loss/train': 1.4499289989471436}
-03/05/2022 15:54:15 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/05/2022 15:54:18 - INFO - codeparrot_training - Step 42901: {'lr': 0.0004115494454291815, 'samples': 21965824, 'steps': 42901, 'loss/train': 1.2988823652267456}
-03/05/2022 15:54:21 - INFO - codeparrot_training - Step 42902: {'lr': 0.0004115453954447789, 'samples': 21966336, 'steps': 42902, 'loss/train': 0.23858216404914856}
-03/05/2022 15:54:24 - INFO - codeparrot_training - Step 42903: {'lr': 0.0004115413453875865, 'samples': 21966848, 'steps': 42903, 'loss/train': 1.2502669095993042}
-03/05/2022 15:54:24 - INFO - codeparrot_training - Skipping example with length 916 (seq_length=1024)
-03/05/2022 15:54:30 - INFO - codeparrot_training - Step 42904: {'lr': 0.000411537295257606, 'samples': 21967360, 'steps': 42904, 'loss/train': 1.7900233268737793}
-03/05/2022 15:54:32 - INFO - codeparrot_training - Skipping example with length 495 (seq_length=1024)
-03/05/2022 15:54:35 - INFO - codeparrot_training - Step 42905: {'lr': 0.00041153324505483933, 'samples': 21967872, 'steps': 42905, 'loss/train': 1.5736699104309082}
-03/05/2022 15:54:38 - INFO - codeparrot_training - Step 42906: {'lr': 0.0004115291947792882, 'samples': 21968384, 'steps': 42906, 'loss/train': 1.9686124324798584}
-03/05/2022 15:54:41 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/05/2022 15:54:44 - INFO - codeparrot_training - Step 42907: {'lr': 0.00041152514443095454, 'samples': 21968896, 'steps': 42907, 'loss/train': 2.004068374633789}
-03/05/2022 15:54:47 - INFO - codeparrot_training - Step 42908: {'lr': 0.00041152109400984015, 'samples': 21969408, 'steps': 42908, 'loss/train': 2.269676685333252}
-03/05/2022 15:54:51 - INFO - codeparrot_training - Step 42909: {'lr': 0.0004115170435159469, 'samples': 21969920, 'steps': 42909, 'loss/train': 1.0077173709869385}
-03/05/2022 15:54:54 - INFO - codeparrot_training - Step 42910: {'lr': 0.00041151299294927657, 'samples': 21970432, 'steps': 42910, 'loss/train': 2.0882325172424316}
-03/05/2022 15:54:54 - INFO - codeparrot_training - Skipping example with length 280 (seq_length=1024)
-03/05/2022 15:54:59 - INFO - codeparrot_training - Step 42911: {'lr': 0.0004115089423098309, 'samples': 21970944, 'steps': 42911, 'loss/train': 1.1544673442840576}
-03/05/2022 15:55:02 - INFO - codeparrot_training - Step 42912: {'lr': 0.00041150489159761186, 'samples': 21971456, 'steps': 42912, 'loss/train': 1.2389448881149292}
-03/05/2022 15:55:03 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/05/2022 15:55:07 - INFO - codeparrot_training - Step 42913: {'lr': 0.00041150084081262105, 'samples': 21971968, 'steps': 42913, 'loss/train': 1.8110857009887695}
-03/05/2022 15:55:11 - INFO - codeparrot_training - Step 42914: {'lr': 0.0004114967899548606, 'samples': 21972480, 'steps': 42914, 'loss/train': 2.040325403213501}
-03/05/2022 15:55:11 - INFO - codeparrot_training - Skipping example with length 651 (seq_length=1024)
-03/05/2022 15:55:16 - INFO - codeparrot_training - Step 42915: {'lr': 0.0004114927390243322, 'samples': 21972992, 'steps': 42915, 'loss/train': 1.530531406402588}
-03/05/2022 15:55:19 - INFO - codeparrot_training - Step 42916: {'lr': 0.00041148868802103766, 'samples': 21973504, 'steps': 42916, 'loss/train': 1.8204318284988403}
-03/05/2022 15:55:20 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/05/2022 15:55:24 - INFO - codeparrot_training - Step 42917: {'lr': 0.00041148463694497874, 'samples': 21974016, 'steps': 42917, 'loss/train': 1.5080429315567017}
-03/05/2022 15:55:28 - INFO - codeparrot_training - Step 42918: {'lr': 0.00041148058579615733, 'samples': 21974528, 'steps': 42918, 'loss/train': 1.2990598678588867}
-03/05/2022 15:55:28 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 15:55:33 - INFO - codeparrot_training - Step 42919: {'lr': 0.00041147653457457534, 'samples': 21975040, 'steps': 42919, 'loss/train': 1.4375979900360107}
-03/05/2022 15:55:36 - INFO - codeparrot_training - Step 42920: {'lr': 0.0004114724832802345, 'samples': 21975552, 'steps': 42920, 'loss/train': 0.32137230038642883}
-03/05/2022 15:55:38 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/05/2022 15:55:41 - INFO - codeparrot_training - Step 42921: {'lr': 0.0004114684319131366, 'samples': 21976064, 'steps': 42921, 'loss/train': 1.8669859170913696}
-03/05/2022 15:55:45 - INFO - codeparrot_training - Step 42922: {'lr': 0.00041146438047328347, 'samples': 21976576, 'steps': 42922, 'loss/train': 1.2115890979766846}
-03/05/2022 15:55:46 - INFO - codeparrot_training - Skipping example with length 845 (seq_length=1024)
-03/05/2022 15:55:50 - INFO - codeparrot_training - Step 42923: {'lr': 0.0004114603289606771, 'samples': 21977088, 'steps': 42923, 'loss/train': 1.4692821502685547}
-03/05/2022 15:55:53 - INFO - codeparrot_training - Step 42924: {'lr': 0.00041145627737531915, 'samples': 21977600, 'steps': 42924, 'loss/train': 1.4174588918685913}
-03/05/2022 15:55:55 - INFO - codeparrot_training - Skipping example with length 686 (seq_length=1024)
-03/05/2022 15:55:58 - INFO - codeparrot_training - Step 42925: {'lr': 0.0004114522257172115, 'samples': 21978112, 'steps': 42925, 'loss/train': 2.3464009761810303}
-03/05/2022 15:56:01 - INFO - codeparrot_training - Step 42926: {'lr': 0.000411448173986356, 'samples': 21978624, 'steps': 42926, 'loss/train': 1.4296643733978271}
-03/05/2022 15:56:03 - INFO - codeparrot_training - Skipping example with length 129 (seq_length=1024)
-03/05/2022 15:56:07 - INFO - codeparrot_training - Step 42927: {'lr': 0.0004114441221827544, 'samples': 21979136, 'steps': 42927, 'loss/train': 2.573824644088745}
-03/05/2022 15:56:10 - INFO - codeparrot_training - Step 42928: {'lr': 0.0004114400703064085, 'samples': 21979648, 'steps': 42928, 'loss/train': 1.8425463438034058}
-03/05/2022 15:56:11 - INFO - codeparrot_training - Skipping example with length 68 (seq_length=1024)
-03/05/2022 15:56:15 - INFO - codeparrot_training - Step 42929: {'lr': 0.0004114360183573203, 'samples': 21980160, 'steps': 42929, 'loss/train': 2.2028112411499023}
-03/05/2022 15:56:18 - INFO - codeparrot_training - Step 42930: {'lr': 0.0004114319663354915, 'samples': 21980672, 'steps': 42930, 'loss/train': 1.9389923810958862}
-03/05/2022 15:56:19 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/05/2022 15:56:24 - INFO - codeparrot_training - Step 42931: {'lr': 0.000411427914240924, 'samples': 21981184, 'steps': 42931, 'loss/train': 1.643153429031372}
-03/05/2022 15:56:27 - INFO - codeparrot_training - Step 42932: {'lr': 0.0004114238620736195, 'samples': 21981696, 'steps': 42932, 'loss/train': 1.4941760301589966}
-03/05/2022 15:56:28 - INFO - codeparrot_training - Skipping example with length 888 (seq_length=1024)
-03/05/2022 15:56:32 - INFO - codeparrot_training - Step 42933: {'lr': 0.00041141980983357986, 'samples': 21982208, 'steps': 42933, 'loss/train': 1.493929147720337}
-03/05/2022 15:56:35 - INFO - codeparrot_training - Step 42934: {'lr': 0.000411415757520807, 'samples': 21982720, 'steps': 42934, 'loss/train': 2.0451931953430176}
-03/05/2022 15:56:36 - INFO - codeparrot_training - Skipping example with length 118 (seq_length=1024)
-03/05/2022 15:56:40 - INFO - codeparrot_training - Step 42935: {'lr': 0.00041141170513530267, 'samples': 21983232, 'steps': 42935, 'loss/train': 1.8647053241729736}
-03/05/2022 15:56:44 - INFO - codeparrot_training - Step 42936: {'lr': 0.0004114076526770688, 'samples': 21983744, 'steps': 42936, 'loss/train': 2.3523550033569336}
-03/05/2022 15:56:45 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/05/2022 15:56:49 - INFO - codeparrot_training - Step 42937: {'lr': 0.000411403600146107, 'samples': 21984256, 'steps': 42937, 'loss/train': 2.0750224590301514}
-03/05/2022 15:56:52 - INFO - codeparrot_training - Step 42938: {'lr': 0.0004113995475424193, 'samples': 21984768, 'steps': 42938, 'loss/train': 1.3506728410720825}
-03/05/2022 15:56:53 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/05/2022 15:56:57 - INFO - codeparrot_training - Step 42939: {'lr': 0.0004113954948660075, 'samples': 21985280, 'steps': 42939, 'loss/train': 2.0904605388641357}
-03/05/2022 15:57:00 - INFO - codeparrot_training - Step 42940: {'lr': 0.00041139144211687327, 'samples': 21985792, 'steps': 42940, 'loss/train': 1.0733686685562134}
-03/05/2022 15:57:01 - INFO - codeparrot_training - Skipping example with length 423 (seq_length=1024)
-03/05/2022 15:57:06 - INFO - codeparrot_training - Step 42941: {'lr': 0.0004113873892950186, 'samples': 21986304, 'steps': 42941, 'loss/train': 1.2822695970535278}
-03/05/2022 15:57:09 - INFO - codeparrot_training - Step 42942: {'lr': 0.00041138333640044523, 'samples': 21986816, 'steps': 42942, 'loss/train': 2.0626914501190186}
-03/05/2022 15:57:10 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/05/2022 15:57:15 - INFO - codeparrot_training - Step 42943: {'lr': 0.0004113792834331551, 'samples': 21987328, 'steps': 42943, 'loss/train': 2.151146650314331}
-03/05/2022 15:57:18 - INFO - codeparrot_training - Step 42944: {'lr': 0.00041137523039314994, 'samples': 21987840, 'steps': 42944, 'loss/train': 1.973894476890564}
-03/05/2022 15:57:20 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/05/2022 15:57:23 - INFO - codeparrot_training - Step 42945: {'lr': 0.0004113711772804315, 'samples': 21988352, 'steps': 42945, 'loss/train': 1.8973215818405151}
-03/05/2022 15:57:26 - INFO - codeparrot_training - Step 42946: {'lr': 0.0004113671240950018, 'samples': 21988864, 'steps': 42946, 'loss/train': 1.390800952911377}
-03/05/2022 15:57:29 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/05/2022 15:57:31 - INFO - codeparrot_training - Step 42947: {'lr': 0.0004113630708368625, 'samples': 21989376, 'steps': 42947, 'loss/train': 1.7099182605743408}
-03/05/2022 15:57:35 - INFO - codeparrot_training - Step 42948: {'lr': 0.0004113590175060155, 'samples': 21989888, 'steps': 42948, 'loss/train': 1.5995155572891235}
-03/05/2022 15:57:37 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/05/2022 15:57:40 - INFO - codeparrot_training - Step 42949: {'lr': 0.00041135496410246264, 'samples': 21990400, 'steps': 42949, 'loss/train': 1.1366403102874756}
-03/05/2022 15:57:43 - INFO - codeparrot_training - Step 42950: {'lr': 0.0004113509106262058, 'samples': 21990912, 'steps': 42950, 'loss/train': 1.5743422508239746}
-03/05/2022 15:57:46 - INFO - codeparrot_training - Skipping example with length 398 (seq_length=1024)
-03/05/2022 15:57:48 - INFO - codeparrot_training - Step 42951: {'lr': 0.00041134685707724656, 'samples': 21991424, 'steps': 42951, 'loss/train': 1.8833248615264893}
-03/05/2022 15:57:51 - INFO - codeparrot_training - Step 42952: {'lr': 0.000411342803455587, 'samples': 21991936, 'steps': 42952, 'loss/train': 1.6218280792236328}
-03/05/2022 15:57:54 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/05/2022 15:57:57 - INFO - codeparrot_training - Step 42953: {'lr': 0.0004113387497612289, 'samples': 21992448, 'steps': 42953, 'loss/train': 1.8175263404846191}
-03/05/2022 15:58:00 - INFO - codeparrot_training - Step 42954: {'lr': 0.00041133469599417393, 'samples': 21992960, 'steps': 42954, 'loss/train': 2.064639091491699}
-03/05/2022 15:58:02 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/05/2022 15:58:05 - INFO - codeparrot_training - Step 42955: {'lr': 0.00041133064215442415, 'samples': 21993472, 'steps': 42955, 'loss/train': 1.1247656345367432}
-03/05/2022 15:58:08 - INFO - codeparrot_training - Step 42956: {'lr': 0.0004113265882419812, 'samples': 21993984, 'steps': 42956, 'loss/train': 1.4436148405075073}
-03/05/2022 15:58:11 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/05/2022 15:58:14 - INFO - codeparrot_training - Step 42957: {'lr': 0.0004113225342568471, 'samples': 21994496, 'steps': 42957, 'loss/train': 1.492915153503418}
-03/05/2022 15:58:17 - INFO - codeparrot_training - Step 42958: {'lr': 0.00041131848019902343, 'samples': 21995008, 'steps': 42958, 'loss/train': 1.7489091157913208}
-03/05/2022 15:58:19 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/05/2022 15:58:22 - INFO - codeparrot_training - Step 42959: {'lr': 0.0004113144260685122, 'samples': 21995520, 'steps': 42959, 'loss/train': 1.3100528717041016}
-03/05/2022 15:58:25 - INFO - codeparrot_training - Step 42960: {'lr': 0.00041131037186531514, 'samples': 21996032, 'steps': 42960, 'loss/train': 1.251444935798645}
-03/05/2022 15:58:28 - INFO - codeparrot_training - Skipping example with length 82 (seq_length=1024)
-03/05/2022 15:58:30 - INFO - codeparrot_training - Step 42961: {'lr': 0.00041130631758943414, 'samples': 21996544, 'steps': 42961, 'loss/train': 1.9012699127197266}
-03/05/2022 15:58:33 - INFO - codeparrot_training - Step 42962: {'lr': 0.00041130226324087094, 'samples': 21997056, 'steps': 42962, 'loss/train': 1.7917362451553345}
-03/05/2022 15:58:36 - INFO - codeparrot_training - Skipping example with length 134 (seq_length=1024)
-03/05/2022 15:58:39 - INFO - codeparrot_training - Step 42963: {'lr': 0.00041129820881962754, 'samples': 21997568, 'steps': 42963, 'loss/train': 2.2283413410186768}
-03/05/2022 15:58:42 - INFO - codeparrot_training - Step 42964: {'lr': 0.0004112941543257056, 'samples': 21998080, 'steps': 42964, 'loss/train': 1.889428734779358}
-03/05/2022 15:58:46 - INFO - codeparrot_training - Step 42965: {'lr': 0.00041129009975910704, 'samples': 21998592, 'steps': 42965, 'loss/train': 0.26018401980400085}
-03/05/2022 15:58:46 - INFO - codeparrot_training - Skipping example with length 793 (seq_length=1024)
-03/05/2022 15:58:51 - INFO - codeparrot_training - Step 42966: {'lr': 0.00041128604511983356, 'samples': 21999104, 'steps': 42966, 'loss/train': 2.5363352298736572}
-03/05/2022 15:58:54 - INFO - codeparrot_training - Step 42967: {'lr': 0.00041128199040788715, 'samples': 21999616, 'steps': 42967, 'loss/train': 1.6047049760818481}
-03/05/2022 15:58:54 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/05/2022 15:59:00 - INFO - codeparrot_training - Step 42968: {'lr': 0.00041127793562326955, 'samples': 22000128, 'steps': 42968, 'loss/train': 1.830857515335083}
-03/05/2022 15:59:04 - INFO - codeparrot_training - Step 42969: {'lr': 0.0004112738807659826, 'samples': 22000640, 'steps': 42969, 'loss/train': 1.3830406665802002}
-03/05/2022 15:59:07 - INFO - codeparrot_training - Step 42970: {'lr': 0.00041126982583602817, 'samples': 22001152, 'steps': 42970, 'loss/train': 2.480656147003174}
-03/05/2022 15:59:08 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/05/2022 15:59:12 - INFO - codeparrot_training - Step 42971: {'lr': 0.00041126577083340797, 'samples': 22001664, 'steps': 42971, 'loss/train': 0.6048572659492493}
-03/05/2022 15:59:15 - INFO - codeparrot_training - Step 42972: {'lr': 0.000411261715758124, 'samples': 22002176, 'steps': 42972, 'loss/train': 1.6765623092651367}
-03/05/2022 15:59:16 - INFO - codeparrot_training - Skipping example with length 81 (seq_length=1024)
-03/05/2022 15:59:20 - INFO - codeparrot_training - Step 42973: {'lr': 0.0004112576606101779, 'samples': 22002688, 'steps': 42973, 'loss/train': 2.0490708351135254}
-03/05/2022 15:59:23 - INFO - codeparrot_training - Step 42974: {'lr': 0.0004112536053895716, 'samples': 22003200, 'steps': 42974, 'loss/train': 2.15755033493042}
-03/05/2022 15:59:25 - INFO - codeparrot_training - Skipping example with length 929 (seq_length=1024)
-03/05/2022 15:59:29 - INFO - codeparrot_training - Step 42975: {'lr': 0.0004112495500963069, 'samples': 22003712, 'steps': 42975, 'loss/train': 1.8064204454421997}
-03/05/2022 15:59:32 - INFO - codeparrot_training - Step 42976: {'lr': 0.00041124549473038564, 'samples': 22004224, 'steps': 42976, 'loss/train': 2.201092481613159}
-03/05/2022 15:59:34 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/05/2022 15:59:37 - INFO - codeparrot_training - Step 42977: {'lr': 0.0004112414392918097, 'samples': 22004736, 'steps': 42977, 'loss/train': 0.9857216477394104}
-03/05/2022 15:59:41 - INFO - codeparrot_training - Step 42978: {'lr': 0.00041123738378058083, 'samples': 22005248, 'steps': 42978, 'loss/train': 1.519026756286621}
-03/05/2022 15:59:43 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 15:59:46 - INFO - codeparrot_training - Step 42979: {'lr': 0.0004112333281967009, 'samples': 22005760, 'steps': 42979, 'loss/train': 1.5576121807098389}
-03/05/2022 15:59:49 - INFO - codeparrot_training - Step 42980: {'lr': 0.00041122927254017173, 'samples': 22006272, 'steps': 42980, 'loss/train': 2.104839563369751}
-03/05/2022 15:59:51 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/05/2022 15:59:54 - INFO - codeparrot_training - Step 42981: {'lr': 0.0004112252168109951, 'samples': 22006784, 'steps': 42981, 'loss/train': 2.055675506591797}
-03/05/2022 15:59:58 - INFO - codeparrot_training - Step 42982: {'lr': 0.0004112211610091728, 'samples': 22007296, 'steps': 42982, 'loss/train': 1.4533791542053223}
-03/05/2022 16:00:00 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/05/2022 16:00:03 - INFO - codeparrot_training - Step 42983: {'lr': 0.0004112171051347069, 'samples': 22007808, 'steps': 42983, 'loss/train': 1.8485826253890991}
-03/05/2022 16:00:06 - INFO - codeparrot_training - Step 42984: {'lr': 0.00041121304918759893, 'samples': 22008320, 'steps': 42984, 'loss/train': 2.1012234687805176}
-03/05/2022 16:00:08 - INFO - codeparrot_training - Skipping example with length 75 (seq_length=1024)
-03/05/2022 16:00:11 - INFO - codeparrot_training - Step 42985: {'lr': 0.00041120899316785095, 'samples': 22008832, 'steps': 42985, 'loss/train': 2.299145460128784}
-03/05/2022 16:00:14 - INFO - codeparrot_training - Step 42986: {'lr': 0.00041120493707546456, 'samples': 22009344, 'steps': 42986, 'loss/train': 1.8893461227416992}
-03/05/2022 16:00:16 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/05/2022 16:00:20 - INFO - codeparrot_training - Step 42987: {'lr': 0.00041120088091044183, 'samples': 22009856, 'steps': 42987, 'loss/train': 2.12126088142395}
-03/05/2022 16:00:23 - INFO - codeparrot_training - Step 42988: {'lr': 0.0004111968246727844, 'samples': 22010368, 'steps': 42988, 'loss/train': 1.972978949546814}
-03/05/2022 16:00:25 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/05/2022 16:00:28 - INFO - codeparrot_training - Step 42989: {'lr': 0.0004111927683624942, 'samples': 22010880, 'steps': 42989, 'loss/train': 1.6756961345672607}
-03/05/2022 16:00:31 - INFO - codeparrot_training - Step 42990: {'lr': 0.00041118871197957306, 'samples': 22011392, 'steps': 42990, 'loss/train': 1.7594828605651855}
-03/05/2022 16:00:33 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/05/2022 16:00:37 - INFO - codeparrot_training - Step 42991: {'lr': 0.00041118465552402274, 'samples': 22011904, 'steps': 42991, 'loss/train': 2.122166395187378}
-03/05/2022 16:00:40 - INFO - codeparrot_training - Step 42992: {'lr': 0.00041118059899584503, 'samples': 22012416, 'steps': 42992, 'loss/train': 1.690854549407959}
-03/05/2022 16:00:42 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 16:00:45 - INFO - codeparrot_training - Step 42993: {'lr': 0.00041117654239504193, 'samples': 22012928, 'steps': 42993, 'loss/train': 1.6571182012557983}
-03/05/2022 16:00:48 - INFO - codeparrot_training - Step 42994: {'lr': 0.0004111724857216151, 'samples': 22013440, 'steps': 42994, 'loss/train': 1.6810352802276611}
-03/05/2022 16:00:50 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 16:00:54 - INFO - codeparrot_training - Step 42995: {'lr': 0.0004111684289755665, 'samples': 22013952, 'steps': 42995, 'loss/train': 1.724513292312622}
-03/05/2022 16:00:57 - INFO - codeparrot_training - Step 42996: {'lr': 0.00041116437215689785, 'samples': 22014464, 'steps': 42996, 'loss/train': 1.050251841545105}
-03/05/2022 16:00:58 - INFO - codeparrot_training - Skipping example with length 316 (seq_length=1024)
-03/05/2022 16:01:02 - INFO - codeparrot_training - Step 42997: {'lr': 0.000411160315265611, 'samples': 22014976, 'steps': 42997, 'loss/train': 1.862662672996521}
-03/05/2022 16:01:05 - INFO - codeparrot_training - Step 42998: {'lr': 0.0004111562583017079, 'samples': 22015488, 'steps': 42998, 'loss/train': 1.9470300674438477}
-03/05/2022 16:01:07 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/05/2022 16:01:11 - INFO - codeparrot_training - Step 42999: {'lr': 0.00041115220126519014, 'samples': 22016000, 'steps': 42999, 'loss/train': 1.9588584899902344}
-03/05/2022 16:01:14 - INFO - codeparrot_training - Step 43000: {'lr': 0.00041114814415605977, 'samples': 22016512, 'steps': 43000, 'loss/train': 1.526210069656372}
-03/05/2022 16:01:15 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/05/2022 16:01:19 - INFO - codeparrot_training - Step 43001: {'lr': 0.0004111440869743185, 'samples': 22017024, 'steps': 43001, 'loss/train': 1.1328762769699097}
-03/05/2022 16:01:22 - INFO - codeparrot_training - Step 43002: {'lr': 0.00041114002971996824, 'samples': 22017536, 'steps': 43002, 'loss/train': 1.8909417390823364}
-03/05/2022 16:01:23 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 16:01:27 - INFO - codeparrot_training - Step 43003: {'lr': 0.0004111359723930107, 'samples': 22018048, 'steps': 43003, 'loss/train': 1.271471619606018}
-03/05/2022 16:01:30 - INFO - codeparrot_training - Step 43004: {'lr': 0.00041113191499344784, 'samples': 22018560, 'steps': 43004, 'loss/train': 1.451917290687561}
-03/05/2022 16:01:32 - INFO - codeparrot_training - Skipping example with length 446 (seq_length=1024)
-03/05/2022 16:01:36 - INFO - codeparrot_training - Step 43005: {'lr': 0.0004111278575212814, 'samples': 22019072, 'steps': 43005, 'loss/train': 2.382460355758667}
-03/05/2022 16:01:39 - INFO - codeparrot_training - Step 43006: {'lr': 0.0004111237999765132, 'samples': 22019584, 'steps': 43006, 'loss/train': 1.7496036291122437}
-03/05/2022 16:01:40 - INFO - codeparrot_training - Skipping example with length 875 (seq_length=1024)
-03/05/2022 16:01:44 - INFO - codeparrot_training - Step 43007: {'lr': 0.0004111197423591452, 'samples': 22020096, 'steps': 43007, 'loss/train': 1.74411141872406}
-03/05/2022 16:01:47 - INFO - codeparrot_training - Step 43008: {'lr': 0.000411115684669179, 'samples': 22020608, 'steps': 43008, 'loss/train': 1.7294312715530396}
-03/05/2022 16:01:48 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/05/2022 16:01:53 - INFO - codeparrot_training - Step 43009: {'lr': 0.00041111162690661665, 'samples': 22021120, 'steps': 43009, 'loss/train': 0.9306980967521667}
-03/05/2022 16:01:56 - INFO - codeparrot_training - Step 43010: {'lr': 0.00041110756907145984, 'samples': 22021632, 'steps': 43010, 'loss/train': 0.7423564195632935}
-03/05/2022 16:01:57 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/05/2022 16:02:01 - INFO - codeparrot_training - Step 43011: {'lr': 0.0004111035111637105, 'samples': 22022144, 'steps': 43011, 'loss/train': 1.8358217477798462}
-03/05/2022 16:02:04 - INFO - codeparrot_training - Step 43012: {'lr': 0.00041109945318337034, 'samples': 22022656, 'steps': 43012, 'loss/train': 1.329107403755188}
-03/05/2022 16:02:05 - INFO - codeparrot_training - Skipping example with length 848 (seq_length=1024)
-03/05/2022 16:02:09 - INFO - codeparrot_training - Step 43013: {'lr': 0.00041109539513044127, 'samples': 22023168, 'steps': 43013, 'loss/train': 1.3814101219177246}
-03/05/2022 16:02:13 - INFO - codeparrot_training - Step 43014: {'lr': 0.0004110913370049251, 'samples': 22023680, 'steps': 43014, 'loss/train': 1.1635452508926392}
-03/05/2022 16:02:14 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/05/2022 16:02:18 - INFO - codeparrot_training - Step 43015: {'lr': 0.00041108727880682363, 'samples': 22024192, 'steps': 43015, 'loss/train': 1.109616994857788}
-03/05/2022 16:02:21 - INFO - codeparrot_training - Step 43016: {'lr': 0.0004110832205361388, 'samples': 22024704, 'steps': 43016, 'loss/train': 2.077890634536743}
-03/05/2022 16:02:22 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 16:02:26 - INFO - codeparrot_training - Step 43017: {'lr': 0.0004110791621928723, 'samples': 22025216, 'steps': 43017, 'loss/train': 1.6168617010116577}
-03/05/2022 16:02:30 - INFO - codeparrot_training - Step 43018: {'lr': 0.00041107510377702604, 'samples': 22025728, 'steps': 43018, 'loss/train': 1.6295809745788574}
-03/05/2022 16:02:30 - INFO - codeparrot_training - Skipping example with length 357 (seq_length=1024)
-03/05/2022 16:02:35 - INFO - codeparrot_training - Step 43019: {'lr': 0.00041107104528860186, 'samples': 22026240, 'steps': 43019, 'loss/train': 2.069366216659546}
-03/05/2022 16:02:38 - INFO - codeparrot_training - Step 43020: {'lr': 0.00041106698672760145, 'samples': 22026752, 'steps': 43020, 'loss/train': 2.3758347034454346}
-03/05/2022 16:02:40 - INFO - codeparrot_training - Skipping example with length 283 (seq_length=1024)
-03/05/2022 16:02:43 - INFO - codeparrot_training - Step 43021: {'lr': 0.0004110629280940268, 'samples': 22027264, 'steps': 43021, 'loss/train': 1.8350683450698853}
-03/05/2022 16:02:47 - INFO - codeparrot_training - Step 43022: {'lr': 0.0004110588693878796, 'samples': 22027776, 'steps': 43022, 'loss/train': 1.502535343170166}
-03/05/2022 16:02:48 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/05/2022 16:02:52 - INFO - codeparrot_training - Step 43023: {'lr': 0.0004110548106091619, 'samples': 22028288, 'steps': 43023, 'loss/train': 2.1090140342712402}
-03/05/2022 16:02:55 - INFO - codeparrot_training - Step 43024: {'lr': 0.00041105075175787534, 'samples': 22028800, 'steps': 43024, 'loss/train': 0.7174452543258667}
-03/05/2022 16:02:56 - INFO - codeparrot_training - Skipping example with length 503 (seq_length=1024)
-03/05/2022 16:03:00 - INFO - codeparrot_training - Step 43025: {'lr': 0.00041104669283402174, 'samples': 22029312, 'steps': 43025, 'loss/train': 1.9419543743133545}
-03/05/2022 16:03:04 - INFO - codeparrot_training - Step 43026: {'lr': 0.00041104263383760304, 'samples': 22029824, 'steps': 43026, 'loss/train': 1.4905227422714233}
-03/05/2022 16:03:05 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/05/2022 16:03:09 - INFO - codeparrot_training - Step 43027: {'lr': 0.000411038574768621, 'samples': 22030336, 'steps': 43027, 'loss/train': 1.3694018125534058}
-03/05/2022 16:03:12 - INFO - codeparrot_training - Step 43028: {'lr': 0.00041103451562707745, 'samples': 22030848, 'steps': 43028, 'loss/train': 0.2598229944705963}
-03/05/2022 16:03:13 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/05/2022 16:03:17 - INFO - codeparrot_training - Step 43029: {'lr': 0.0004110304564129742, 'samples': 22031360, 'steps': 43029, 'loss/train': 1.549552083015442}
-03/05/2022 16:03:21 - INFO - codeparrot_training - Step 43030: {'lr': 0.00041102639712631316, 'samples': 22031872, 'steps': 43030, 'loss/train': 1.8566228151321411}
-03/05/2022 16:03:22 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/05/2022 16:03:26 - INFO - codeparrot_training - Step 43031: {'lr': 0.0004110223377670962, 'samples': 22032384, 'steps': 43031, 'loss/train': 1.228371500968933}
-03/05/2022 16:03:29 - INFO - codeparrot_training - Step 43032: {'lr': 0.0004110182783353249, 'samples': 22032896, 'steps': 43032, 'loss/train': 1.9909286499023438}
-03/05/2022 16:03:30 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/05/2022 16:03:34 - INFO - codeparrot_training - Step 43033: {'lr': 0.0004110142188310013, 'samples': 22033408, 'steps': 43033, 'loss/train': 1.7093251943588257}
-03/05/2022 16:03:37 - INFO - codeparrot_training - Step 43034: {'lr': 0.0004110101592541272, 'samples': 22033920, 'steps': 43034, 'loss/train': 1.8380711078643799}
-03/05/2022 16:03:38 - INFO - codeparrot_training - Skipping example with length 542 (seq_length=1024)
-03/05/2022 16:03:43 - INFO - codeparrot_training - Step 43035: {'lr': 0.0004110060996047044, 'samples': 22034432, 'steps': 43035, 'loss/train': 1.180138349533081}
-03/05/2022 16:03:46 - INFO - codeparrot_training - Step 43036: {'lr': 0.00041100203988273475, 'samples': 22034944, 'steps': 43036, 'loss/train': 2.098604679107666}
-03/05/2022 16:03:47 - INFO - codeparrot_training - Skipping example with length 543 (seq_length=1024)
-03/05/2022 16:03:51 - INFO - codeparrot_training - Step 43037: {'lr': 0.0004109979800882201, 'samples': 22035456, 'steps': 43037, 'loss/train': 2.079730272293091}
-03/05/2022 16:03:54 - INFO - codeparrot_training - Step 43038: {'lr': 0.00041099392022116214, 'samples': 22035968, 'steps': 43038, 'loss/train': 1.6361215114593506}
-03/05/2022 16:03:55 - INFO - codeparrot_training - Skipping example with length 895 (seq_length=1024)
-03/05/2022 16:04:00 - INFO - codeparrot_training - Step 43039: {'lr': 0.0004109898602815629, 'samples': 22036480, 'steps': 43039, 'loss/train': 1.7473645210266113}
-03/05/2022 16:04:03 - INFO - codeparrot_training - Step 43040: {'lr': 0.000410985800269424, 'samples': 22036992, 'steps': 43040, 'loss/train': 1.9737156629562378}
-03/05/2022 16:04:04 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/05/2022 16:04:08 - INFO - codeparrot_training - Step 43041: {'lr': 0.00041098174018474747, 'samples': 22037504, 'steps': 43041, 'loss/train': 1.8876824378967285}
-03/05/2022 16:04:11 - INFO - codeparrot_training - Step 43042: {'lr': 0.000410977680027535, 'samples': 22038016, 'steps': 43042, 'loss/train': 1.7406147718429565}
-03/05/2022 16:04:13 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 16:04:17 - INFO - codeparrot_training - Step 43043: {'lr': 0.00041097361979778853, 'samples': 22038528, 'steps': 43043, 'loss/train': 2.1136491298675537}
-03/05/2022 16:04:20 - INFO - codeparrot_training - Step 43044: {'lr': 0.00041096955949550983, 'samples': 22039040, 'steps': 43044, 'loss/train': 1.7802170515060425}
-03/05/2022 16:04:21 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/05/2022 16:04:25 - INFO - codeparrot_training - Step 43045: {'lr': 0.00041096549912070067, 'samples': 22039552, 'steps': 43045, 'loss/train': 1.694657564163208}
-03/05/2022 16:04:28 - INFO - codeparrot_training - Step 43046: {'lr': 0.000410961438673363, 'samples': 22040064, 'steps': 43046, 'loss/train': 1.7808825969696045}
-03/05/2022 16:04:29 - INFO - codeparrot_training - Skipping example with length 761 (seq_length=1024)
-03/05/2022 16:04:34 - INFO - codeparrot_training - Step 43047: {'lr': 0.0004109573781534985, 'samples': 22040576, 'steps': 43047, 'loss/train': 1.1797266006469727}
-03/05/2022 16:04:37 - INFO - codeparrot_training - Step 43048: {'lr': 0.0004109533175611092, 'samples': 22041088, 'steps': 43048, 'loss/train': 1.654572606086731}
-03/05/2022 16:04:37 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/05/2022 16:04:42 - INFO - codeparrot_training - Step 43049: {'lr': 0.0004109492568961968, 'samples': 22041600, 'steps': 43049, 'loss/train': 2.0845680236816406}
-03/05/2022 16:04:45 - INFO - codeparrot_training - Step 43050: {'lr': 0.00041094519615876313, 'samples': 22042112, 'steps': 43050, 'loss/train': 1.8338444232940674}
-03/05/2022 16:04:46 - INFO - codeparrot_training - Skipping example with length 126 (seq_length=1024)
-03/05/2022 16:04:50 - INFO - codeparrot_training - Step 43051: {'lr': 0.0004109411353488101, 'samples': 22042624, 'steps': 43051, 'loss/train': 1.6461910009384155}
-03/05/2022 16:04:54 - INFO - codeparrot_training - Step 43052: {'lr': 0.00041093707446633934, 'samples': 22043136, 'steps': 43052, 'loss/train': 1.8856909275054932}
-03/05/2022 16:04:54 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/05/2022 16:04:59 - INFO - codeparrot_training - Step 43053: {'lr': 0.00041093301351135294, 'samples': 22043648, 'steps': 43053, 'loss/train': 2.0125715732574463}
-03/05/2022 16:05:02 - INFO - codeparrot_training - Step 43054: {'lr': 0.00041092895248385255, 'samples': 22044160, 'steps': 43054, 'loss/train': 1.6833592653274536}
-03/05/2022 16:05:03 - INFO - codeparrot_training - Skipping example with length 322 (seq_length=1024)
-03/05/2022 16:05:07 - INFO - codeparrot_training - Step 43055: {'lr': 0.00041092489138384, 'samples': 22044672, 'steps': 43055, 'loss/train': 1.3324934244155884}
-03/05/2022 16:05:10 - INFO - codeparrot_training - Step 43056: {'lr': 0.0004109208302113173, 'samples': 22045184, 'steps': 43056, 'loss/train': 1.9577224254608154}
-03/05/2022 16:05:11 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/05/2022 16:05:16 - INFO - codeparrot_training - Step 43057: {'lr': 0.00041091676896628604, 'samples': 22045696, 'steps': 43057, 'loss/train': 0.4841378331184387}
-03/05/2022 16:05:19 - INFO - codeparrot_training - Step 43058: {'lr': 0.00041091270764874823, 'samples': 22046208, 'steps': 43058, 'loss/train': 0.9508277773857117}
-03/05/2022 16:05:19 - INFO - codeparrot_training - Skipping example with length 1021 (seq_length=1024)
-03/05/2022 16:05:24 - INFO - codeparrot_training - Step 43059: {'lr': 0.0004109086462587056, 'samples': 22046720, 'steps': 43059, 'loss/train': 1.6298943758010864}
-03/05/2022 16:05:27 - INFO - codeparrot_training - Step 43060: {'lr': 0.0004109045847961601, 'samples': 22047232, 'steps': 43060, 'loss/train': 1.6206494569778442}
-03/05/2022 16:05:28 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/05/2022 16:05:33 - INFO - codeparrot_training - Step 43061: {'lr': 0.0004109005232611134, 'samples': 22047744, 'steps': 43061, 'loss/train': 1.2157680988311768}
-03/05/2022 16:05:36 - INFO - codeparrot_training - Step 43062: {'lr': 0.00041089646165356743, 'samples': 22048256, 'steps': 43062, 'loss/train': 1.5649973154067993}
-03/05/2022 16:05:36 - INFO - codeparrot_training - Skipping example with length 369 (seq_length=1024)
-03/05/2022 16:05:41 - INFO - codeparrot_training - Step 43063: {'lr': 0.000410892399973524, 'samples': 22048768, 'steps': 43063, 'loss/train': 1.342923641204834}
-03/05/2022 16:05:44 - INFO - codeparrot_training - Step 43064: {'lr': 0.00041088833822098495, 'samples': 22049280, 'steps': 43064, 'loss/train': 2.1289045810699463}
-03/05/2022 16:05:44 - INFO - codeparrot_training - Skipping example with length 187 (seq_length=1024)
-03/05/2022 16:05:50 - INFO - codeparrot_training - Step 43065: {'lr': 0.00041088427639595206, 'samples': 22049792, 'steps': 43065, 'loss/train': 2.1584956645965576}
-03/05/2022 16:05:53 - INFO - codeparrot_training - Step 43066: {'lr': 0.0004108802144984273, 'samples': 22050304, 'steps': 43066, 'loss/train': 1.505391001701355}
-03/05/2022 16:05:53 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/05/2022 16:05:58 - INFO - codeparrot_training - Step 43067: {'lr': 0.0004108761525284123, 'samples': 22050816, 'steps': 43067, 'loss/train': 1.086782693862915}
-03/05/2022 16:06:01 - INFO - codeparrot_training - Step 43068: {'lr': 0.000410872090485909, 'samples': 22051328, 'steps': 43068, 'loss/train': 1.4483222961425781}
-03/05/2022 16:06:02 - INFO - codeparrot_training - Skipping example with length 730 (seq_length=1024)
-03/05/2022 16:06:07 - INFO - codeparrot_training - Step 43069: {'lr': 0.00041086802837091916, 'samples': 22051840, 'steps': 43069, 'loss/train': 1.960574746131897}
-03/05/2022 16:06:10 - INFO - codeparrot_training - Step 43070: {'lr': 0.00041086396618344475, 'samples': 22052352, 'steps': 43070, 'loss/train': 1.7231091260910034}
-03/05/2022 16:06:13 - INFO - codeparrot_training - Step 43071: {'lr': 0.0004108599039234875, 'samples': 22052864, 'steps': 43071, 'loss/train': 2.0861830711364746}
-03/05/2022 16:06:13 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/05/2022 16:06:19 - INFO - codeparrot_training - Step 43072: {'lr': 0.00041085584159104925, 'samples': 22053376, 'steps': 43072, 'loss/train': 2.222378969192505}
-03/05/2022 16:06:22 - INFO - codeparrot_training - Step 43073: {'lr': 0.00041085177918613185, 'samples': 22053888, 'steps': 43073, 'loss/train': 2.0434725284576416}
-03/05/2022 16:06:23 - INFO - codeparrot_training - Skipping example with length 511 (seq_length=1024)
-03/05/2022 16:06:27 - INFO - codeparrot_training - Step 43074: {'lr': 0.0004108477167087371, 'samples': 22054400, 'steps': 43074, 'loss/train': 1.8143647909164429}
-03/05/2022 16:06:31 - INFO - codeparrot_training - Step 43075: {'lr': 0.0004108436541588669, 'samples': 22054912, 'steps': 43075, 'loss/train': 1.689709186553955}
-03/05/2022 16:06:31 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/05/2022 16:06:36 - INFO - codeparrot_training - Step 43076: {'lr': 0.000410839591536523, 'samples': 22055424, 'steps': 43076, 'loss/train': 2.117950916290283}
-03/05/2022 16:06:39 - INFO - codeparrot_training - Step 43077: {'lr': 0.00041083552884170726, 'samples': 22055936, 'steps': 43077, 'loss/train': 2.0496063232421875}
-03/05/2022 16:06:40 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/05/2022 16:06:44 - INFO - codeparrot_training - Step 43078: {'lr': 0.0004108314660744216, 'samples': 22056448, 'steps': 43078, 'loss/train': 2.437413454055786}
-03/05/2022 16:06:47 - INFO - codeparrot_training - Step 43079: {'lr': 0.0004108274032346676, 'samples': 22056960, 'steps': 43079, 'loss/train': 1.9964866638183594}
-03/05/2022 16:06:48 - INFO - codeparrot_training - Skipping example with length 157 (seq_length=1024)
-03/05/2022 16:06:53 - INFO - codeparrot_training - Step 43080: {'lr': 0.0004108233403224474, 'samples': 22057472, 'steps': 43080, 'loss/train': 2.443490743637085}
-03/05/2022 16:06:56 - INFO - codeparrot_training - Step 43081: {'lr': 0.0004108192773377626, 'samples': 22057984, 'steps': 43081, 'loss/train': 1.9517830610275269}
-03/05/2022 16:06:57 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 16:07:01 - INFO - codeparrot_training - Step 43082: {'lr': 0.0004108152142806151, 'samples': 22058496, 'steps': 43082, 'loss/train': 1.970909595489502}
-03/05/2022 16:07:04 - INFO - codeparrot_training - Step 43083: {'lr': 0.00041081115115100677, 'samples': 22059008, 'steps': 43083, 'loss/train': 2.4584081172943115}
-03/05/2022 16:07:05 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/05/2022 16:07:10 - INFO - codeparrot_training - Step 43084: {'lr': 0.0004108070879489395, 'samples': 22059520, 'steps': 43084, 'loss/train': 1.994110107421875}
-03/05/2022 16:07:13 - INFO - codeparrot_training - Step 43085: {'lr': 0.0004108030246744149, 'samples': 22060032, 'steps': 43085, 'loss/train': 1.2431331872940063}
-03/05/2022 16:07:13 - INFO - codeparrot_training - Skipping example with length 734 (seq_length=1024)
-03/05/2022 16:07:18 - INFO - codeparrot_training - Step 43086: {'lr': 0.00041079896132743506, 'samples': 22060544, 'steps': 43086, 'loss/train': 1.2463271617889404}
-03/05/2022 16:07:21 - INFO - codeparrot_training - Step 43087: {'lr': 0.0004107948979080016, 'samples': 22061056, 'steps': 43087, 'loss/train': 0.5642788410186768}
-03/05/2022 16:07:22 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/05/2022 16:07:26 - INFO - codeparrot_training - Step 43088: {'lr': 0.00041079083441611646, 'samples': 22061568, 'steps': 43088, 'loss/train': 1.488057255744934}
-03/05/2022 16:07:30 - INFO - codeparrot_training - Step 43089: {'lr': 0.0004107867708517815, 'samples': 22062080, 'steps': 43089, 'loss/train': 1.6993271112442017}
-03/05/2022 16:07:31 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/05/2022 16:07:35 - INFO - codeparrot_training - Step 43090: {'lr': 0.0004107827072149984, 'samples': 22062592, 'steps': 43090, 'loss/train': 1.4550457000732422}
-03/05/2022 16:07:38 - INFO - codeparrot_training - Step 43091: {'lr': 0.0004107786435057692, 'samples': 22063104, 'steps': 43091, 'loss/train': 2.6793904304504395}
-03/05/2022 16:07:39 - INFO - codeparrot_training - Skipping example with length 592 (seq_length=1024)
-03/05/2022 16:07:43 - INFO - codeparrot_training - Step 43092: {'lr': 0.0004107745797240956, 'samples': 22063616, 'steps': 43092, 'loss/train': 1.2877134084701538}
-03/05/2022 16:07:47 - INFO - codeparrot_training - Step 43093: {'lr': 0.0004107705158699794, 'samples': 22064128, 'steps': 43093, 'loss/train': 0.7764769196510315}
-03/05/2022 16:07:47 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/05/2022 16:07:52 - INFO - codeparrot_training - Step 43094: {'lr': 0.00041076645194342254, 'samples': 22064640, 'steps': 43094, 'loss/train': 2.4741721153259277}
-03/05/2022 16:07:55 - INFO - codeparrot_training - Step 43095: {'lr': 0.00041076238794442675, 'samples': 22065152, 'steps': 43095, 'loss/train': 1.2902302742004395}
-03/05/2022 16:07:56 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 16:08:00 - INFO - codeparrot_training - Step 43096: {'lr': 0.00041075832387299396, 'samples': 22065664, 'steps': 43096, 'loss/train': 1.503089189529419}
-03/05/2022 16:08:04 - INFO - codeparrot_training - Step 43097: {'lr': 0.00041075425972912595, 'samples': 22066176, 'steps': 43097, 'loss/train': 1.8542871475219727}
-03/05/2022 16:08:04 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 16:08:09 - INFO - codeparrot_training - Step 43098: {'lr': 0.00041075019551282455, 'samples': 22066688, 'steps': 43098, 'loss/train': 2.089121103286743}
-03/05/2022 16:08:12 - INFO - codeparrot_training - Step 43099: {'lr': 0.00041074613122409157, 'samples': 22067200, 'steps': 43099, 'loss/train': 2.1537768840789795}
-03/05/2022 16:08:12 - INFO - codeparrot_training - Skipping example with length 840 (seq_length=1024)
-03/05/2022 16:08:17 - INFO - codeparrot_training - Step 43100: {'lr': 0.0004107420668629289, 'samples': 22067712, 'steps': 43100, 'loss/train': 1.368057131767273}
-03/05/2022 16:08:20 - INFO - codeparrot_training - Step 43101: {'lr': 0.00041073800242933826, 'samples': 22068224, 'steps': 43101, 'loss/train': 1.905125379562378}
-03/05/2022 16:08:21 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 16:08:26 - INFO - codeparrot_training - Step 43102: {'lr': 0.00041073393792332157, 'samples': 22068736, 'steps': 43102, 'loss/train': 1.185733675956726}
-03/05/2022 16:08:29 - INFO - codeparrot_training - Step 43103: {'lr': 0.0004107298733448807, 'samples': 22069248, 'steps': 43103, 'loss/train': 2.022883415222168}
-03/05/2022 16:08:29 - INFO - codeparrot_training - Skipping example with length 274 (seq_length=1024)
-03/05/2022 16:08:34 - INFO - codeparrot_training - Step 43104: {'lr': 0.0004107258086940174, 'samples': 22069760, 'steps': 43104, 'loss/train': 1.3742536306381226}
-03/05/2022 16:08:37 - INFO - codeparrot_training - Step 43105: {'lr': 0.0004107217439707336, 'samples': 22070272, 'steps': 43105, 'loss/train': 1.2686127424240112}
-03/05/2022 16:08:38 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/05/2022 16:08:42 - INFO - codeparrot_training - Step 43106: {'lr': 0.000410717679175031, 'samples': 22070784, 'steps': 43106, 'loss/train': 2.06044602394104}
-03/05/2022 16:08:46 - INFO - codeparrot_training - Step 43107: {'lr': 0.00041071361430691143, 'samples': 22071296, 'steps': 43107, 'loss/train': 2.3357412815093994}
-03/05/2022 16:08:46 - INFO - codeparrot_training - Skipping example with length 288 (seq_length=1024)
-03/05/2022 16:08:51 - INFO - codeparrot_training - Step 43108: {'lr': 0.00041070954936637687, 'samples': 22071808, 'steps': 43108, 'loss/train': 0.7956318259239197}
-03/05/2022 16:08:54 - INFO - codeparrot_training - Step 43109: {'lr': 0.00041070548435342903, 'samples': 22072320, 'steps': 43109, 'loss/train': 1.8337548971176147}
-03/05/2022 16:08:54 - INFO - codeparrot_training - Skipping example with length 790 (seq_length=1024)
-03/05/2022 16:08:59 - INFO - codeparrot_training - Step 43110: {'lr': 0.00041070141926806983, 'samples': 22072832, 'steps': 43110, 'loss/train': 0.719842255115509}
-03/05/2022 16:09:02 - INFO - codeparrot_training - Step 43111: {'lr': 0.00041069735411030105, 'samples': 22073344, 'steps': 43111, 'loss/train': 1.3006435632705688}
-03/05/2022 16:09:02 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 16:09:08 - INFO - codeparrot_training - Step 43112: {'lr': 0.00041069328888012447, 'samples': 22073856, 'steps': 43112, 'loss/train': 1.6250613927841187}
-03/05/2022 16:09:11 - INFO - codeparrot_training - Step 43113: {'lr': 0.000410689223577542, 'samples': 22074368, 'steps': 43113, 'loss/train': 1.3310869932174683}
-03/05/2022 16:09:11 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 16:09:16 - INFO - codeparrot_training - Step 43114: {'lr': 0.00041068515820255543, 'samples': 22074880, 'steps': 43114, 'loss/train': 1.6656626462936401}
-03/05/2022 16:09:19 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/05/2022 16:09:22 - INFO - codeparrot_training - Step 43115: {'lr': 0.00041068109275516665, 'samples': 22075392, 'steps': 43115, 'loss/train': 1.007974624633789}
-03/05/2022 16:09:25 - INFO - codeparrot_training - Step 43116: {'lr': 0.0004106770272353774, 'samples': 22075904, 'steps': 43116, 'loss/train': 2.0368382930755615}
-03/05/2022 16:09:28 - INFO - codeparrot_training - Skipping example with length 1020 (seq_length=1024)
-03/05/2022 16:09:30 - INFO - codeparrot_training - Step 43117: {'lr': 0.00041067296164318956, 'samples': 22076416, 'steps': 43117, 'loss/train': 2.2699427604675293}
-03/05/2022 16:09:33 - INFO - codeparrot_training - Step 43118: {'lr': 0.000410668895978605, 'samples': 22076928, 'steps': 43118, 'loss/train': 0.47049444913864136}
-03/05/2022 16:09:36 - INFO - codeparrot_training - Skipping example with length 76 (seq_length=1024)
-03/05/2022 16:09:39 - INFO - codeparrot_training - Step 43119: {'lr': 0.0004106648302416255, 'samples': 22077440, 'steps': 43119, 'loss/train': 1.2024662494659424}
-03/05/2022 16:09:42 - INFO - codeparrot_training - Step 43120: {'lr': 0.0004106607644322529, 'samples': 22077952, 'steps': 43120, 'loss/train': 1.618593692779541}
-03/05/2022 16:09:45 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 16:09:47 - INFO - codeparrot_training - Step 43121: {'lr': 0.00041065669855048896, 'samples': 22078464, 'steps': 43121, 'loss/train': 1.4772942066192627}
-03/05/2022 16:09:50 - INFO - codeparrot_training - Step 43122: {'lr': 0.0004106526325963357, 'samples': 22078976, 'steps': 43122, 'loss/train': 1.7195594310760498}
-03/05/2022 16:09:53 - INFO - codeparrot_training - Step 43123: {'lr': 0.0004106485665697948, 'samples': 22079488, 'steps': 43123, 'loss/train': 1.0221295356750488}
-03/05/2022 16:09:53 - INFO - codeparrot_training - Skipping example with length 755 (seq_length=1024)
-03/05/2022 16:09:59 - INFO - codeparrot_training - Step 43124: {'lr': 0.00041064450047086814, 'samples': 22080000, 'steps': 43124, 'loss/train': 1.7321712970733643}
-03/05/2022 16:10:02 - INFO - codeparrot_training - Step 43125: {'lr': 0.00041064043429955756, 'samples': 22080512, 'steps': 43125, 'loss/train': 1.5884205102920532}
-03/05/2022 16:10:02 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/05/2022 16:10:07 - INFO - codeparrot_training - Step 43126: {'lr': 0.0004106363680558649, 'samples': 22081024, 'steps': 43126, 'loss/train': 1.4176160097122192}
-03/05/2022 16:10:11 - INFO - codeparrot_training - Step 43127: {'lr': 0.0004106323017397919, 'samples': 22081536, 'steps': 43127, 'loss/train': 2.1790034770965576}
-03/05/2022 16:10:12 - INFO - codeparrot_training - Skipping example with length 122 (seq_length=1024)
-03/05/2022 16:10:16 - INFO - codeparrot_training - Step 43128: {'lr': 0.00041062823535134053, 'samples': 22082048, 'steps': 43128, 'loss/train': 1.397014856338501}
-03/05/2022 16:10:19 - INFO - codeparrot_training - Step 43129: {'lr': 0.0004106241688905126, 'samples': 22082560, 'steps': 43129, 'loss/train': 1.8907394409179688}
-03/05/2022 16:10:20 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/05/2022 16:10:24 - INFO - codeparrot_training - Step 43130: {'lr': 0.00041062010235730974, 'samples': 22083072, 'steps': 43130, 'loss/train': 2.2713260650634766}
-03/05/2022 16:10:27 - INFO - codeparrot_training - Step 43131: {'lr': 0.0004106160357517341, 'samples': 22083584, 'steps': 43131, 'loss/train': 1.0937063694000244}
-03/05/2022 16:10:28 - INFO - codeparrot_training - Skipping example with length 17 (seq_length=1024)
-03/05/2022 16:10:33 - INFO - codeparrot_training - Step 43132: {'lr': 0.00041061196907378727, 'samples': 22084096, 'steps': 43132, 'loss/train': 3.005648374557495}
-03/05/2022 16:10:36 - INFO - codeparrot_training - Step 43133: {'lr': 0.00041060790232347116, 'samples': 22084608, 'steps': 43133, 'loss/train': 2.260462999343872}
-03/05/2022 16:10:37 - INFO - codeparrot_training - Skipping example with length 510 (seq_length=1024)
-03/05/2022 16:10:41 - INFO - codeparrot_training - Step 43134: {'lr': 0.00041060383550078764, 'samples': 22085120, 'steps': 43134, 'loss/train': 1.8415838479995728}
-03/05/2022 16:10:44 - INFO - codeparrot_training - Step 43135: {'lr': 0.00041059976860573845, 'samples': 22085632, 'steps': 43135, 'loss/train': 2.1916239261627197}
-03/05/2022 16:10:45 - INFO - codeparrot_training - Skipping example with length 146 (seq_length=1024)
-03/05/2022 16:10:50 - INFO - codeparrot_training - Step 43136: {'lr': 0.00041059570163832555, 'samples': 22086144, 'steps': 43136, 'loss/train': 1.5917460918426514}
-03/05/2022 16:10:53 - INFO - codeparrot_training - Step 43137: {'lr': 0.00041059163459855066, 'samples': 22086656, 'steps': 43137, 'loss/train': 0.9320889115333557}
-03/05/2022 16:10:54 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 16:10:58 - INFO - codeparrot_training - Step 43138: {'lr': 0.00041058756748641573, 'samples': 22087168, 'steps': 43138, 'loss/train': 1.4843759536743164}
-03/05/2022 16:11:01 - INFO - codeparrot_training - Step 43139: {'lr': 0.0004105835003019225, 'samples': 22087680, 'steps': 43139, 'loss/train': 1.759590983390808}
-03/05/2022 16:11:02 - INFO - codeparrot_training - Skipping example with length 494 (seq_length=1024)
-03/05/2022 16:11:06 - INFO - codeparrot_training - Step 43140: {'lr': 0.00041057943304507273, 'samples': 22088192, 'steps': 43140, 'loss/train': 0.31049492955207825}
-03/05/2022 16:11:10 - INFO - codeparrot_training - Step 43141: {'lr': 0.0004105753657158684, 'samples': 22088704, 'steps': 43141, 'loss/train': 1.4876688718795776}
-03/05/2022 16:11:10 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/05/2022 16:11:15 - INFO - codeparrot_training - Step 43142: {'lr': 0.00041057129831431133, 'samples': 22089216, 'steps': 43142, 'loss/train': 2.0918872356414795}
-03/05/2022 16:11:19 - INFO - codeparrot_training - Step 43143: {'lr': 0.00041056723084040324, 'samples': 22089728, 'steps': 43143, 'loss/train': 2.170022487640381}
-03/05/2022 16:11:22 - INFO - codeparrot_training - Step 43144: {'lr': 0.00041056316329414613, 'samples': 22090240, 'steps': 43144, 'loss/train': 0.778674304485321}
-03/05/2022 16:11:22 - INFO - codeparrot_training - Skipping example with length 197 (seq_length=1024)
-03/05/2022 16:11:27 - INFO - codeparrot_training - Step 43145: {'lr': 0.00041055909567554166, 'samples': 22090752, 'steps': 43145, 'loss/train': 1.5231820344924927}
-03/05/2022 16:11:30 - INFO - codeparrot_training - Step 43146: {'lr': 0.00041055502798459175, 'samples': 22091264, 'steps': 43146, 'loss/train': 2.150735855102539}
-03/05/2022 16:11:30 - INFO - codeparrot_training - Skipping example with length 533 (seq_length=1024)
-03/05/2022 16:11:35 - INFO - codeparrot_training - Step 43147: {'lr': 0.00041055096022129823, 'samples': 22091776, 'steps': 43147, 'loss/train': 1.4834394454956055}
-03/05/2022 16:11:39 - INFO - codeparrot_training - Step 43148: {'lr': 0.0004105468923856629, 'samples': 22092288, 'steps': 43148, 'loss/train': 2.0487375259399414}
-03/05/2022 16:11:39 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/05/2022 16:11:44 - INFO - codeparrot_training - Step 43149: {'lr': 0.00041054282447768763, 'samples': 22092800, 'steps': 43149, 'loss/train': 0.9862779974937439}
-03/05/2022 16:11:47 - INFO - codeparrot_training - Step 43150: {'lr': 0.00041053875649737424, 'samples': 22093312, 'steps': 43150, 'loss/train': 0.07504279911518097}
-03/05/2022 16:11:47 - INFO - codeparrot_training - Skipping example with length 518 (seq_length=1024)
-03/05/2022 16:11:52 - INFO - codeparrot_training - Step 43151: {'lr': 0.0004105346884447246, 'samples': 22093824, 'steps': 43151, 'loss/train': 0.6164417266845703}
-03/05/2022 16:11:56 - INFO - codeparrot_training - Step 43152: {'lr': 0.00041053062031974055, 'samples': 22094336, 'steps': 43152, 'loss/train': 1.6074323654174805}
-03/05/2022 16:11:56 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/05/2022 16:12:01 - INFO - codeparrot_training - Step 43153: {'lr': 0.00041052655212242377, 'samples': 22094848, 'steps': 43153, 'loss/train': 1.0334174633026123}
-03/05/2022 16:12:04 - INFO - codeparrot_training - Step 43154: {'lr': 0.00041052248385277623, 'samples': 22095360, 'steps': 43154, 'loss/train': 1.5558253526687622}
-03/05/2022 16:12:04 - INFO - codeparrot_training - Skipping example with length 962 (seq_length=1024)
-03/05/2022 16:12:09 - INFO - codeparrot_training - Step 43155: {'lr': 0.0004105184155107998, 'samples': 22095872, 'steps': 43155, 'loss/train': 2.41328763961792}
-03/05/2022 16:12:12 - INFO - codeparrot_training - Step 43156: {'lr': 0.00041051434709649614, 'samples': 22096384, 'steps': 43156, 'loss/train': 1.7105889320373535}
-03/05/2022 16:12:12 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/05/2022 16:12:18 - INFO - codeparrot_training - Step 43157: {'lr': 0.0004105102786098672, 'samples': 22096896, 'steps': 43157, 'loss/train': 2.016397476196289}
-03/05/2022 16:12:21 - INFO - codeparrot_training - Skipping example with length 392 (seq_length=1024)
-03/05/2022 16:12:23 - INFO - codeparrot_training - Step 43158: {'lr': 0.0004105062100509149, 'samples': 22097408, 'steps': 43158, 'loss/train': 1.8025619983673096}
-03/05/2022 16:12:27 - INFO - codeparrot_training - Step 43159: {'lr': 0.000410502141419641, 'samples': 22097920, 'steps': 43159, 'loss/train': 1.3668476343154907}
-03/05/2022 16:12:30 - INFO - codeparrot_training - Step 43160: {'lr': 0.00041049807271604724, 'samples': 22098432, 'steps': 43160, 'loss/train': 3.878596544265747}
-03/05/2022 16:12:31 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/05/2022 16:12:35 - INFO - codeparrot_training - Step 43161: {'lr': 0.00041049400394013545, 'samples': 22098944, 'steps': 43161, 'loss/train': 1.3743218183517456}
-03/05/2022 16:12:38 - INFO - codeparrot_training - Step 43162: {'lr': 0.0004104899350919077, 'samples': 22099456, 'steps': 43162, 'loss/train': 1.2171283960342407}
-03/05/2022 16:12:39 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/05/2022 16:12:44 - INFO - codeparrot_training - Step 43163: {'lr': 0.0004104858661713655, 'samples': 22099968, 'steps': 43163, 'loss/train': 1.9445648193359375}
-03/05/2022 16:12:47 - INFO - codeparrot_training - Step 43164: {'lr': 0.00041048179717851095, 'samples': 22100480, 'steps': 43164, 'loss/train': 2.04170298576355}
-03/05/2022 16:12:48 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/05/2022 16:12:52 - INFO - codeparrot_training - Step 43165: {'lr': 0.00041047772811334584, 'samples': 22100992, 'steps': 43165, 'loss/train': 2.1508636474609375}
-03/05/2022 16:12:55 - INFO - codeparrot_training - Step 43166: {'lr': 0.0004104736589758719, 'samples': 22101504, 'steps': 43166, 'loss/train': 2.0004007816314697}
-03/05/2022 16:12:56 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/05/2022 16:13:01 - INFO - codeparrot_training - Step 43167: {'lr': 0.0004104695897660909, 'samples': 22102016, 'steps': 43167, 'loss/train': 1.569664478302002}
-03/05/2022 16:13:04 - INFO - codeparrot_training - Step 43168: {'lr': 0.0004104655204840048, 'samples': 22102528, 'steps': 43168, 'loss/train': 1.326568365097046}
-03/05/2022 16:13:05 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/05/2022 16:13:09 - INFO - codeparrot_training - Step 43169: {'lr': 0.0004104614511296155, 'samples': 22103040, 'steps': 43169, 'loss/train': 1.8442031145095825}
-03/05/2022 16:13:12 - INFO - codeparrot_training - Step 43170: {'lr': 0.00041045738170292467, 'samples': 22103552, 'steps': 43170, 'loss/train': 2.9598910808563232}
-03/05/2022 16:13:13 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 16:13:17 - INFO - codeparrot_training - Step 43171: {'lr': 0.0004104533122039342, 'samples': 22104064, 'steps': 43171, 'loss/train': 1.3943384885787964}
-03/05/2022 16:13:21 - INFO - codeparrot_training - Step 43172: {'lr': 0.00041044924263264603, 'samples': 22104576, 'steps': 43172, 'loss/train': 1.8599486351013184}
-03/05/2022 16:13:21 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/05/2022 16:13:26 - INFO - codeparrot_training - Step 43173: {'lr': 0.00041044517298906194, 'samples': 22105088, 'steps': 43173, 'loss/train': 1.2869185209274292}
-03/05/2022 16:13:29 - INFO - codeparrot_training - Step 43174: {'lr': 0.0004104411032731836, 'samples': 22105600, 'steps': 43174, 'loss/train': 2.4233741760253906}
-03/05/2022 16:13:30 - INFO - codeparrot_training - Skipping example with length 222 (seq_length=1024)
-03/05/2022 16:13:34 - INFO - codeparrot_training - Step 43175: {'lr': 0.00041043703348501304, 'samples': 22106112, 'steps': 43175, 'loss/train': 1.8125391006469727}
-03/05/2022 16:13:38 - INFO - codeparrot_training - Step 43176: {'lr': 0.0004104329636245521, 'samples': 22106624, 'steps': 43176, 'loss/train': 1.748113989830017}
-03/05/2022 16:13:38 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/05/2022 16:13:43 - INFO - codeparrot_training - Step 43177: {'lr': 0.0004104288936918024, 'samples': 22107136, 'steps': 43177, 'loss/train': 1.557985782623291}
-03/05/2022 16:13:46 - INFO - codeparrot_training - Step 43178: {'lr': 0.00041042482368676604, 'samples': 22107648, 'steps': 43178, 'loss/train': 0.6941673159599304}
-03/05/2022 16:13:47 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 16:13:51 - INFO - codeparrot_training - Step 43179: {'lr': 0.00041042075360944464, 'samples': 22108160, 'steps': 43179, 'loss/train': 1.6014760732650757}
-03/05/2022 16:13:55 - INFO - codeparrot_training - Step 43180: {'lr': 0.0004104166834598402, 'samples': 22108672, 'steps': 43180, 'loss/train': 3.426985502243042}
-03/05/2022 16:13:55 - INFO - codeparrot_training - Skipping example with length 372 (seq_length=1024)
-03/05/2022 16:14:00 - INFO - codeparrot_training - Step 43181: {'lr': 0.00041041261323795437, 'samples': 22109184, 'steps': 43181, 'loss/train': 1.8814622163772583}
-03/05/2022 16:14:03 - INFO - codeparrot_training - Step 43182: {'lr': 0.0004104085429437892, 'samples': 22109696, 'steps': 43182, 'loss/train': 1.997185230255127}
-03/05/2022 16:14:03 - INFO - codeparrot_training - Skipping example with length 741 (seq_length=1024)
-03/05/2022 16:14:08 - INFO - codeparrot_training - Step 43183: {'lr': 0.00041040447257734635, 'samples': 22110208, 'steps': 43183, 'loss/train': 1.8427027463912964}
-03/05/2022 16:14:11 - INFO - codeparrot_training - Step 43184: {'lr': 0.00041040040213862774, 'samples': 22110720, 'steps': 43184, 'loss/train': 1.0233168601989746}
-03/05/2022 16:14:11 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/05/2022 16:14:17 - INFO - codeparrot_training - Step 43185: {'lr': 0.00041039633162763523, 'samples': 22111232, 'steps': 43185, 'loss/train': 1.1088801622390747}
-03/05/2022 16:14:20 - INFO - codeparrot_training - Step 43186: {'lr': 0.00041039226104437056, 'samples': 22111744, 'steps': 43186, 'loss/train': 1.1567984819412231}
-03/05/2022 16:14:20 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/05/2022 16:14:25 - INFO - codeparrot_training - Step 43187: {'lr': 0.0004103881903888356, 'samples': 22112256, 'steps': 43187, 'loss/train': 2.084285259246826}
-03/05/2022 16:14:28 - INFO - codeparrot_training - Step 43188: {'lr': 0.0004103841196610322, 'samples': 22112768, 'steps': 43188, 'loss/train': 1.1020394563674927}
-03/05/2022 16:14:29 - INFO - codeparrot_training - Skipping example with length 400 (seq_length=1024)
-03/05/2022 16:14:34 - INFO - codeparrot_training - Step 43189: {'lr': 0.0004103800488609622, 'samples': 22113280, 'steps': 43189, 'loss/train': 1.9646868705749512}
-03/05/2022 16:14:37 - INFO - codeparrot_training - Step 43190: {'lr': 0.0004103759779886274, 'samples': 22113792, 'steps': 43190, 'loss/train': 0.8072062134742737}
-03/05/2022 16:14:37 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/05/2022 16:14:42 - INFO - codeparrot_training - Step 43191: {'lr': 0.0004103719070440297, 'samples': 22114304, 'steps': 43191, 'loss/train': 1.7499758005142212}
-03/05/2022 16:14:46 - INFO - codeparrot_training - Step 43192: {'lr': 0.00041036783602717086, 'samples': 22114816, 'steps': 43192, 'loss/train': 2.080030679702759}
-03/05/2022 16:14:46 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/05/2022 16:14:51 - INFO - codeparrot_training - Step 43193: {'lr': 0.00041036376493805286, 'samples': 22115328, 'steps': 43193, 'loss/train': 1.2478511333465576}
-03/05/2022 16:14:54 - INFO - codeparrot_training - Step 43194: {'lr': 0.0004103596937766773, 'samples': 22115840, 'steps': 43194, 'loss/train': 2.2631237506866455}
-03/05/2022 16:14:54 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 16:14:59 - INFO - codeparrot_training - Step 43195: {'lr': 0.00041035562254304614, 'samples': 22116352, 'steps': 43195, 'loss/train': 1.521174669265747}
-03/05/2022 16:15:02 - INFO - codeparrot_training - Step 43196: {'lr': 0.00041035155123716127, 'samples': 22116864, 'steps': 43196, 'loss/train': 1.5661031007766724}
-03/05/2022 16:15:02 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/05/2022 16:15:08 - INFO - codeparrot_training - Step 43197: {'lr': 0.00041034747985902446, 'samples': 22117376, 'steps': 43197, 'loss/train': 1.6527433395385742}
-03/05/2022 16:15:11 - INFO - codeparrot_training - Step 43198: {'lr': 0.0004103434084086375, 'samples': 22117888, 'steps': 43198, 'loss/train': 2.2505178451538086}
-03/05/2022 16:15:11 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/05/2022 16:15:16 - INFO - codeparrot_training - Step 43199: {'lr': 0.0004103393368860023, 'samples': 22118400, 'steps': 43199, 'loss/train': 2.1395835876464844}
-03/05/2022 16:15:19 - INFO - codeparrot_training - Step 43200: {'lr': 0.0004103352652911206, 'samples': 22118912, 'steps': 43200, 'loss/train': 0.9425106644630432}
-03/05/2022 16:15:19 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/05/2022 16:15:25 - INFO - codeparrot_training - Step 43201: {'lr': 0.0004103311936239944, 'samples': 22119424, 'steps': 43201, 'loss/train': 1.9217737913131714}
-03/05/2022 16:15:28 - INFO - codeparrot_training - Step 43202: {'lr': 0.0004103271218846254, 'samples': 22119936, 'steps': 43202, 'loss/train': 1.6151843070983887}
-03/05/2022 16:15:28 - INFO - codeparrot_training - Skipping example with length 247 (seq_length=1024)
-03/05/2022 16:15:33 - INFO - codeparrot_training - Step 43203: {'lr': 0.00041032305007301554, 'samples': 22120448, 'steps': 43203, 'loss/train': 1.7006281614303589}
-03/05/2022 16:15:36 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/05/2022 16:15:38 - INFO - codeparrot_training - Step 43204: {'lr': 0.00041031897818916645, 'samples': 22120960, 'steps': 43204, 'loss/train': 1.8964240550994873}
-03/05/2022 16:15:41 - INFO - codeparrot_training - Step 43205: {'lr': 0.0004103149062330802, 'samples': 22121472, 'steps': 43205, 'loss/train': 2.3115744590759277}
-03/05/2022 16:15:44 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/05/2022 16:15:47 - INFO - codeparrot_training - Step 43206: {'lr': 0.00041031083420475854, 'samples': 22121984, 'steps': 43206, 'loss/train': 2.4273064136505127}
-03/05/2022 16:15:50 - INFO - codeparrot_training - Step 43207: {'lr': 0.00041030676210420324, 'samples': 22122496, 'steps': 43207, 'loss/train': 1.872268557548523}
-03/05/2022 16:15:53 - INFO - codeparrot_training - Step 43208: {'lr': 0.0004103026899314162, 'samples': 22123008, 'steps': 43208, 'loss/train': 1.7310543060302734}
-03/05/2022 16:15:53 - INFO - codeparrot_training - Skipping example with length 636 (seq_length=1024)
-03/05/2022 16:15:58 - INFO - codeparrot_training - Step 43209: {'lr': 0.00041029861768639934, 'samples': 22123520, 'steps': 43209, 'loss/train': 1.9417424201965332}
-03/05/2022 16:16:02 - INFO - codeparrot_training - Step 43210: {'lr': 0.0004102945453691542, 'samples': 22124032, 'steps': 43210, 'loss/train': 1.2173815965652466}
-03/05/2022 16:16:02 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/05/2022 16:16:07 - INFO - codeparrot_training - Step 43211: {'lr': 0.00041029047297968293, 'samples': 22124544, 'steps': 43211, 'loss/train': 2.1224944591522217}
-03/05/2022 16:16:10 - INFO - codeparrot_training - Step 43212: {'lr': 0.00041028640051798726, 'samples': 22125056, 'steps': 43212, 'loss/train': 1.7711994647979736}
-03/05/2022 16:16:11 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/05/2022 16:16:16 - INFO - codeparrot_training - Step 43213: {'lr': 0.000410282327984069, 'samples': 22125568, 'steps': 43213, 'loss/train': 2.022165298461914}
-03/05/2022 16:16:19 - INFO - codeparrot_training - Step 43214: {'lr': 0.00041027825537792993, 'samples': 22126080, 'steps': 43214, 'loss/train': 1.6552820205688477}
-03/05/2022 16:16:19 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/05/2022 16:16:24 - INFO - codeparrot_training - Step 43215: {'lr': 0.0004102741826995721, 'samples': 22126592, 'steps': 43215, 'loss/train': 1.7351596355438232}
-03/05/2022 16:16:27 - INFO - codeparrot_training - Step 43216: {'lr': 0.000410270109948997, 'samples': 22127104, 'steps': 43216, 'loss/train': 1.6724952459335327}
-03/05/2022 16:16:28 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/05/2022 16:16:32 - INFO - codeparrot_training - Step 43217: {'lr': 0.0004102660371262068, 'samples': 22127616, 'steps': 43217, 'loss/train': 0.5624778270721436}
-03/05/2022 16:16:36 - INFO - codeparrot_training - Step 43218: {'lr': 0.0004102619642312031, 'samples': 22128128, 'steps': 43218, 'loss/train': 1.2636492252349854}
-03/05/2022 16:16:36 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 16:16:41 - INFO - codeparrot_training - Step 43219: {'lr': 0.00041025789126398793, 'samples': 22128640, 'steps': 43219, 'loss/train': 1.4325833320617676}
-03/05/2022 16:16:44 - INFO - codeparrot_training - Step 43220: {'lr': 0.000410253818224563, 'samples': 22129152, 'steps': 43220, 'loss/train': 1.560046672821045}
-03/05/2022 16:16:45 - INFO - codeparrot_training - Skipping example with length 414 (seq_length=1024)
-03/05/2022 16:16:49 - INFO - codeparrot_training - Step 43221: {'lr': 0.0004102497451129302, 'samples': 22129664, 'steps': 43221, 'loss/train': 1.0455875396728516}
-03/05/2022 16:16:53 - INFO - codeparrot_training - Step 43222: {'lr': 0.00041024567192909125, 'samples': 22130176, 'steps': 43222, 'loss/train': 1.946094274520874}
-03/05/2022 16:16:53 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/05/2022 16:16:58 - INFO - codeparrot_training - Step 43223: {'lr': 0.0004102415986730481, 'samples': 22130688, 'steps': 43223, 'loss/train': 2.1657912731170654}
-03/05/2022 16:17:01 - INFO - codeparrot_training - Step 43224: {'lr': 0.0004102375253448026, 'samples': 22131200, 'steps': 43224, 'loss/train': 2.1871206760406494}
-03/05/2022 16:17:02 - INFO - codeparrot_training - Skipping example with length 595 (seq_length=1024)
-03/05/2022 16:17:06 - INFO - codeparrot_training - Step 43225: {'lr': 0.0004102334519443565, 'samples': 22131712, 'steps': 43225, 'loss/train': 1.885581612586975}
-03/05/2022 16:17:10 - INFO - codeparrot_training - Step 43226: {'lr': 0.0004102293784717117, 'samples': 22132224, 'steps': 43226, 'loss/train': 2.225637912750244}
-03/05/2022 16:17:11 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/05/2022 16:17:15 - INFO - codeparrot_training - Step 43227: {'lr': 0.00041022530492687006, 'samples': 22132736, 'steps': 43227, 'loss/train': 1.4710289239883423}
-03/05/2022 16:17:18 - INFO - codeparrot_training - Step 43228: {'lr': 0.0004102212313098333, 'samples': 22133248, 'steps': 43228, 'loss/train': 2.4985575675964355}
-03/05/2022 16:17:19 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/05/2022 16:17:23 - INFO - codeparrot_training - Step 43229: {'lr': 0.00041021715762060336, 'samples': 22133760, 'steps': 43229, 'loss/train': 1.7442725896835327}
-03/05/2022 16:17:27 - INFO - codeparrot_training - Step 43230: {'lr': 0.000410213083859182, 'samples': 22134272, 'steps': 43230, 'loss/train': 2.0833709239959717}
-03/05/2022 16:17:28 - INFO - codeparrot_training - Skipping example with length 918 (seq_length=1024)
-03/05/2022 16:17:32 - INFO - codeparrot_training - Step 43231: {'lr': 0.0004102090100255711, 'samples': 22134784, 'steps': 43231, 'loss/train': 1.6969125270843506}
-03/05/2022 16:17:35 - INFO - codeparrot_training - Step 43232: {'lr': 0.00041020493611977263, 'samples': 22135296, 'steps': 43232, 'loss/train': 2.641444206237793}
-03/05/2022 16:17:36 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 16:17:40 - INFO - codeparrot_training - Step 43233: {'lr': 0.0004102008621417881, 'samples': 22135808, 'steps': 43233, 'loss/train': 1.8641031980514526}
-03/05/2022 16:17:44 - INFO - codeparrot_training - Step 43234: {'lr': 0.0004101967880916196, 'samples': 22136320, 'steps': 43234, 'loss/train': 2.289092540740967}
-03/05/2022 16:17:45 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/05/2022 16:17:49 - INFO - codeparrot_training - Step 43235: {'lr': 0.00041019271396926894, 'samples': 22136832, 'steps': 43235, 'loss/train': 1.8249212503433228}
-03/05/2022 16:17:52 - INFO - codeparrot_training - Step 43236: {'lr': 0.0004101886397747379, 'samples': 22137344, 'steps': 43236, 'loss/train': 1.6895931959152222}
-03/05/2022 16:17:53 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 16:17:57 - INFO - codeparrot_training - Step 43237: {'lr': 0.0004101845655080283, 'samples': 22137856, 'steps': 43237, 'loss/train': 2.1939969062805176}
-03/05/2022 16:18:00 - INFO - codeparrot_training - Step 43238: {'lr': 0.00041018049116914204, 'samples': 22138368, 'steps': 43238, 'loss/train': 1.3934543132781982}
-03/05/2022 16:18:02 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/05/2022 16:18:06 - INFO - codeparrot_training - Step 43239: {'lr': 0.00041017641675808095, 'samples': 22138880, 'steps': 43239, 'loss/train': 2.0057244300842285}
-03/05/2022 16:18:09 - INFO - codeparrot_training - Step 43240: {'lr': 0.00041017234227484675, 'samples': 22139392, 'steps': 43240, 'loss/train': 1.9136486053466797}
-03/05/2022 16:18:10 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/05/2022 16:18:14 - INFO - codeparrot_training - Step 43241: {'lr': 0.0004101682677194414, 'samples': 22139904, 'steps': 43241, 'loss/train': 1.637627124786377}
-03/05/2022 16:18:17 - INFO - codeparrot_training - Step 43242: {'lr': 0.0004101641930918667, 'samples': 22140416, 'steps': 43242, 'loss/train': 2.117596387863159}
-03/05/2022 16:18:19 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/05/2022 16:18:23 - INFO - codeparrot_training - Step 43243: {'lr': 0.00041016011839212446, 'samples': 22140928, 'steps': 43243, 'loss/train': 1.7380921840667725}
-03/05/2022 16:18:26 - INFO - codeparrot_training - Step 43244: {'lr': 0.0004101560436202166, 'samples': 22141440, 'steps': 43244, 'loss/train': 0.13180974125862122}
-03/05/2022 16:18:27 - INFO - codeparrot_training - Skipping example with length 341 (seq_length=1024)
-03/05/2022 16:18:31 - INFO - codeparrot_training - Step 43245: {'lr': 0.0004101519687761449, 'samples': 22141952, 'steps': 43245, 'loss/train': 2.1192612648010254}
-03/05/2022 16:18:34 - INFO - codeparrot_training - Step 43246: {'lr': 0.00041014789385991114, 'samples': 22142464, 'steps': 43246, 'loss/train': 2.1228344440460205}
-03/05/2022 16:18:36 - INFO - codeparrot_training - Skipping example with length 525 (seq_length=1024)
-03/05/2022 16:18:40 - INFO - codeparrot_training - Step 43247: {'lr': 0.00041014381887151727, 'samples': 22142976, 'steps': 43247, 'loss/train': 2.1630313396453857}
-03/05/2022 16:18:43 - INFO - codeparrot_training - Step 43248: {'lr': 0.00041013974381096503, 'samples': 22143488, 'steps': 43248, 'loss/train': 1.7150437831878662}
-03/05/2022 16:18:44 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/05/2022 16:18:48 - INFO - codeparrot_training - Step 43249: {'lr': 0.00041013566867825627, 'samples': 22144000, 'steps': 43249, 'loss/train': 1.8639549016952515}
-03/05/2022 16:18:51 - INFO - codeparrot_training - Step 43250: {'lr': 0.00041013159347339293, 'samples': 22144512, 'steps': 43250, 'loss/train': 1.2859350442886353}
-03/05/2022 16:18:53 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/05/2022 16:18:57 - INFO - codeparrot_training - Step 43251: {'lr': 0.0004101275181963767, 'samples': 22145024, 'steps': 43251, 'loss/train': 1.7344311475753784}
-03/05/2022 16:19:00 - INFO - codeparrot_training - Step 43252: {'lr': 0.0004101234428472095, 'samples': 22145536, 'steps': 43252, 'loss/train': 2.007427930831909}
-03/05/2022 16:19:02 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/05/2022 16:19:05 - INFO - codeparrot_training - Step 43253: {'lr': 0.0004101193674258931, 'samples': 22146048, 'steps': 43253, 'loss/train': 0.5492433309555054}
-03/05/2022 16:19:08 - INFO - codeparrot_training - Step 43254: {'lr': 0.00041011529193242947, 'samples': 22146560, 'steps': 43254, 'loss/train': 2.0629773139953613}
-03/05/2022 16:19:10 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/05/2022 16:19:14 - INFO - codeparrot_training - Step 43255: {'lr': 0.00041011121636682024, 'samples': 22147072, 'steps': 43255, 'loss/train': 1.9129955768585205}
-03/05/2022 16:19:17 - INFO - codeparrot_training - Step 43256: {'lr': 0.0004101071407290675, 'samples': 22147584, 'steps': 43256, 'loss/train': 1.7603520154953003}
-03/05/2022 16:19:19 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 16:19:22 - INFO - codeparrot_training - Step 43257: {'lr': 0.00041010306501917287, 'samples': 22148096, 'steps': 43257, 'loss/train': 1.894473671913147}
-03/05/2022 16:19:25 - INFO - codeparrot_training - Step 43258: {'lr': 0.0004100989892371383, 'samples': 22148608, 'steps': 43258, 'loss/train': 0.7726580500602722}
-03/05/2022 16:19:27 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/05/2022 16:19:31 - INFO - codeparrot_training - Step 43259: {'lr': 0.00041009491338296557, 'samples': 22149120, 'steps': 43259, 'loss/train': 1.3996249437332153}
-03/05/2022 16:19:34 - INFO - codeparrot_training - Step 43260: {'lr': 0.00041009083745665654, 'samples': 22149632, 'steps': 43260, 'loss/train': 2.183591365814209}
-03/05/2022 16:19:37 - INFO - codeparrot_training - Step 43261: {'lr': 0.0004100867614582131, 'samples': 22150144, 'steps': 43261, 'loss/train': 6.1011528968811035}
-03/05/2022 16:19:38 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 16:19:43 - INFO - codeparrot_training - Step 43262: {'lr': 0.00041008268538763703, 'samples': 22150656, 'steps': 43262, 'loss/train': 1.5988047122955322}
-03/05/2022 16:19:46 - INFO - codeparrot_training - Step 43263: {'lr': 0.00041007860924493014, 'samples': 22151168, 'steps': 43263, 'loss/train': 2.19834566116333}
-03/05/2022 16:19:47 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/05/2022 16:19:51 - INFO - codeparrot_training - Step 43264: {'lr': 0.0004100745330300943, 'samples': 22151680, 'steps': 43264, 'loss/train': 1.936963677406311}
-03/05/2022 16:19:54 - INFO - codeparrot_training - Step 43265: {'lr': 0.0004100704567431314, 'samples': 22152192, 'steps': 43265, 'loss/train': 2.0785539150238037}
-03/05/2022 16:19:55 - INFO - codeparrot_training - Skipping example with length 46 (seq_length=1024)
-03/05/2022 16:19:59 - INFO - codeparrot_training - Step 43266: {'lr': 0.0004100663803840431, 'samples': 22152704, 'steps': 43266, 'loss/train': 0.9911612868309021}
-03/05/2022 16:20:03 - INFO - codeparrot_training - Step 43267: {'lr': 0.0004100623039528315, 'samples': 22153216, 'steps': 43267, 'loss/train': 1.738268494606018}
-03/05/2022 16:20:04 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 16:20:08 - INFO - codeparrot_training - Step 43268: {'lr': 0.0004100582274494982, 'samples': 22153728, 'steps': 43268, 'loss/train': 1.795452356338501}
-03/05/2022 16:20:11 - INFO - codeparrot_training - Step 43269: {'lr': 0.00041005415087404516, 'samples': 22154240, 'steps': 43269, 'loss/train': 1.401180386543274}
-03/05/2022 16:20:13 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/05/2022 16:20:16 - INFO - codeparrot_training - Step 43270: {'lr': 0.0004100500742264742, 'samples': 22154752, 'steps': 43270, 'loss/train': 1.5610294342041016}
-03/05/2022 16:20:19 - INFO - codeparrot_training - Step 43271: {'lr': 0.0004100459975067871, 'samples': 22155264, 'steps': 43271, 'loss/train': 2.042935371398926}
-03/05/2022 16:20:21 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/05/2022 16:20:25 - INFO - codeparrot_training - Step 43272: {'lr': 0.0004100419207149858, 'samples': 22155776, 'steps': 43272, 'loss/train': 1.2920318841934204}
-03/05/2022 16:20:28 - INFO - codeparrot_training - Step 43273: {'lr': 0.0004100378438510721, 'samples': 22156288, 'steps': 43273, 'loss/train': 1.3089075088500977}
-03/05/2022 16:20:30 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 16:20:33 - INFO - codeparrot_training - Step 43274: {'lr': 0.00041003376691504777, 'samples': 22156800, 'steps': 43274, 'loss/train': 2.227097749710083}
-03/05/2022 16:20:36 - INFO - codeparrot_training - Step 43275: {'lr': 0.0004100296899069147, 'samples': 22157312, 'steps': 43275, 'loss/train': 1.2516378164291382}
-03/05/2022 16:20:39 - INFO - codeparrot_training - Skipping example with length 304 (seq_length=1024)
-03/05/2022 16:20:42 - INFO - codeparrot_training - Step 43276: {'lr': 0.0004100256128266747, 'samples': 22157824, 'steps': 43276, 'loss/train': 1.8187108039855957}
-03/05/2022 16:20:45 - INFO - codeparrot_training - Step 43277: {'lr': 0.00041002153567432965, 'samples': 22158336, 'steps': 43277, 'loss/train': 2.208329439163208}
-03/05/2022 16:20:47 - INFO - codeparrot_training - Skipping example with length 553 (seq_length=1024)
-03/05/2022 16:20:50 - INFO - codeparrot_training - Step 43278: {'lr': 0.00041001745844988134, 'samples': 22158848, 'steps': 43278, 'loss/train': 1.4814634323120117}
-03/05/2022 16:20:53 - INFO - codeparrot_training - Step 43279: {'lr': 0.00041001338115333175, 'samples': 22159360, 'steps': 43279, 'loss/train': 1.9411381483078003}
-03/05/2022 16:20:55 - INFO - codeparrot_training - Skipping example with length 521 (seq_length=1024)
-03/05/2022 16:20:59 - INFO - codeparrot_training - Step 43280: {'lr': 0.0004100093037846825, 'samples': 22159872, 'steps': 43280, 'loss/train': 1.612526297569275}
-03/05/2022 16:21:02 - INFO - codeparrot_training - Step 43281: {'lr': 0.0004100052263439355, 'samples': 22160384, 'steps': 43281, 'loss/train': 1.5964199304580688}
-03/05/2022 16:21:03 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/05/2022 16:21:07 - INFO - codeparrot_training - Step 43282: {'lr': 0.00041000114883109264, 'samples': 22160896, 'steps': 43282, 'loss/train': 1.277388334274292}
-03/05/2022 16:21:10 - INFO - codeparrot_training - Step 43283: {'lr': 0.00040999707124615573, 'samples': 22161408, 'steps': 43283, 'loss/train': 1.9545600414276123}
-03/05/2022 16:21:12 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/05/2022 16:21:16 - INFO - codeparrot_training - Step 43284: {'lr': 0.00040999299358912664, 'samples': 22161920, 'steps': 43284, 'loss/train': 1.9750738143920898}
-03/05/2022 16:21:19 - INFO - codeparrot_training - Step 43285: {'lr': 0.00040998891586000716, 'samples': 22162432, 'steps': 43285, 'loss/train': 1.8884276151657104}
-03/05/2022 16:21:20 - INFO - codeparrot_training - Skipping example with length 143 (seq_length=1024)
-03/05/2022 16:21:24 - INFO - codeparrot_training - Step 43286: {'lr': 0.0004099848380587992, 'samples': 22162944, 'steps': 43286, 'loss/train': 2.157059907913208}
-03/05/2022 16:21:27 - INFO - codeparrot_training - Step 43287: {'lr': 0.00040998076018550444, 'samples': 22163456, 'steps': 43287, 'loss/train': 2.160559892654419}
-03/05/2022 16:21:29 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/05/2022 16:21:33 - INFO - codeparrot_training - Step 43288: {'lr': 0.00040997668224012485, 'samples': 22163968, 'steps': 43288, 'loss/train': 1.0545042753219604}
-03/05/2022 16:21:36 - INFO - codeparrot_training - Step 43289: {'lr': 0.00040997260422266223, 'samples': 22164480, 'steps': 43289, 'loss/train': 1.4148080348968506}
-03/05/2022 16:21:38 - INFO - codeparrot_training - Skipping example with length 333 (seq_length=1024)
-03/05/2022 16:21:41 - INFO - codeparrot_training - Step 43290: {'lr': 0.00040996852613311844, 'samples': 22164992, 'steps': 43290, 'loss/train': 2.2292966842651367}
-03/05/2022 16:21:44 - INFO - codeparrot_training - Step 43291: {'lr': 0.00040996444797149526, 'samples': 22165504, 'steps': 43291, 'loss/train': 1.8932799100875854}
-03/05/2022 16:21:46 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/05/2022 16:21:50 - INFO - codeparrot_training - Step 43292: {'lr': 0.0004099603697377946, 'samples': 22166016, 'steps': 43292, 'loss/train': 0.1687105894088745}
-03/05/2022 16:21:53 - INFO - codeparrot_training - Step 43293: {'lr': 0.0004099562914320183, 'samples': 22166528, 'steps': 43293, 'loss/train': 1.3750301599502563}
-03/05/2022 16:21:55 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/05/2022 16:21:58 - INFO - codeparrot_training - Step 43294: {'lr': 0.0004099522130541681, 'samples': 22167040, 'steps': 43294, 'loss/train': 1.9272620677947998}
-03/05/2022 16:22:01 - INFO - codeparrot_training - Step 43295: {'lr': 0.000409948134604246, 'samples': 22167552, 'steps': 43295, 'loss/train': 1.5363616943359375}
-03/05/2022 16:22:03 - INFO - codeparrot_training - Skipping example with length 881 (seq_length=1024)
-03/05/2022 16:22:07 - INFO - codeparrot_training - Step 43296: {'lr': 0.0004099440560822536, 'samples': 22168064, 'steps': 43296, 'loss/train': 1.2806549072265625}
-03/05/2022 16:22:10 - INFO - codeparrot_training - Step 43297: {'lr': 0.000409939977488193, 'samples': 22168576, 'steps': 43297, 'loss/train': 0.5378865003585815}
-03/05/2022 16:22:11 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/05/2022 16:22:15 - INFO - codeparrot_training - Step 43298: {'lr': 0.0004099358988220658, 'samples': 22169088, 'steps': 43298, 'loss/train': 1.4013214111328125}
-03/05/2022 16:22:18 - INFO - codeparrot_training - Step 43299: {'lr': 0.00040993182008387406, 'samples': 22169600, 'steps': 43299, 'loss/train': 2.9513144493103027}
-03/05/2022 16:22:20 - INFO - codeparrot_training - Skipping example with length 404 (seq_length=1024)
-03/05/2022 16:22:23 - INFO - codeparrot_training - Step 43300: {'lr': 0.0004099277412736195, 'samples': 22170112, 'steps': 43300, 'loss/train': 1.6932947635650635}
-03/05/2022 16:22:27 - INFO - codeparrot_training - Step 43301: {'lr': 0.0004099236623913039, 'samples': 22170624, 'steps': 43301, 'loss/train': 1.8396910429000854}
-03/05/2022 16:22:28 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/05/2022 16:22:32 - INFO - codeparrot_training - Step 43302: {'lr': 0.0004099195834369292, 'samples': 22171136, 'steps': 43302, 'loss/train': 2.3354883193969727}
-03/05/2022 16:22:35 - INFO - codeparrot_training - Step 43303: {'lr': 0.0004099155044104972, 'samples': 22171648, 'steps': 43303, 'loss/train': 1.7761167287826538}
-03/05/2022 16:22:37 - INFO - codeparrot_training - Skipping example with length 681 (seq_length=1024)
-03/05/2022 16:22:40 - INFO - codeparrot_training - Step 43304: {'lr': 0.00040991142531200973, 'samples': 22172160, 'steps': 43304, 'loss/train': 0.6873633861541748}
-03/05/2022 16:22:44 - INFO - codeparrot_training - Step 43305: {'lr': 0.0004099073461414686, 'samples': 22172672, 'steps': 43305, 'loss/train': 2.08894419670105}
-03/05/2022 16:22:45 - INFO - codeparrot_training - Skipping example with length 78 (seq_length=1024)
-03/05/2022 16:22:49 - INFO - codeparrot_training - Step 43306: {'lr': 0.0004099032668988758, 'samples': 22173184, 'steps': 43306, 'loss/train': 2.921689987182617}
-03/05/2022 16:22:52 - INFO - codeparrot_training - Step 43307: {'lr': 0.00040989918758423306, 'samples': 22173696, 'steps': 43307, 'loss/train': 1.773556113243103}
-03/05/2022 16:22:55 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 16:22:58 - INFO - codeparrot_training - Step 43308: {'lr': 0.0004098951081975421, 'samples': 22174208, 'steps': 43308, 'loss/train': 2.1210813522338867}
-03/05/2022 16:23:01 - INFO - codeparrot_training - Step 43309: {'lr': 0.0004098910287388049, 'samples': 22174720, 'steps': 43309, 'loss/train': 1.2710038423538208}
-03/05/2022 16:23:04 - INFO - codeparrot_training - Skipping example with length 276 (seq_length=1024)
-03/05/2022 16:23:06 - INFO - codeparrot_training - Step 43310: {'lr': 0.00040988694920802326, 'samples': 22175232, 'steps': 43310, 'loss/train': 1.8920053243637085}
-03/05/2022 16:23:09 - INFO - codeparrot_training - Step 43311: {'lr': 0.0004098828696051991, 'samples': 22175744, 'steps': 43311, 'loss/train': 1.2835326194763184}
-03/05/2022 16:23:12 - INFO - codeparrot_training - Skipping example with length 33 (seq_length=1024)
-03/05/2022 16:23:15 - INFO - codeparrot_training - Step 43312: {'lr': 0.00040987878993033417, 'samples': 22176256, 'steps': 43312, 'loss/train': 1.5760188102722168}
-03/05/2022 16:23:18 - INFO - codeparrot_training - Step 43313: {'lr': 0.0004098747101834303, 'samples': 22176768, 'steps': 43313, 'loss/train': 2.234300374984741}
-03/05/2022 16:23:20 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/05/2022 16:23:23 - INFO - codeparrot_training - Step 43314: {'lr': 0.00040987063036448934, 'samples': 22177280, 'steps': 43314, 'loss/train': 2.0715091228485107}
-03/05/2022 16:23:26 - INFO - codeparrot_training - Step 43315: {'lr': 0.0004098665504735132, 'samples': 22177792, 'steps': 43315, 'loss/train': 1.4630672931671143}
-03/05/2022 16:23:29 - INFO - codeparrot_training - Skipping example with length 99 (seq_length=1024)
-03/05/2022 16:23:32 - INFO - codeparrot_training - Step 43316: {'lr': 0.0004098624705105036, 'samples': 22178304, 'steps': 43316, 'loss/train': 1.4232174158096313}
-03/05/2022 16:23:35 - INFO - codeparrot_training - Step 43317: {'lr': 0.00040985839047546243, 'samples': 22178816, 'steps': 43317, 'loss/train': 1.433431625366211}
-03/05/2022 16:23:38 - INFO - codeparrot_training - Step 43318: {'lr': 0.00040985431036839155, 'samples': 22179328, 'steps': 43318, 'loss/train': 6.560598373413086}
-03/05/2022 16:23:38 - INFO - codeparrot_training - Skipping example with length 526 (seq_length=1024)
-03/05/2022 16:23:43 - INFO - codeparrot_training - Step 43319: {'lr': 0.00040985023018929277, 'samples': 22179840, 'steps': 43319, 'loss/train': 1.5397597551345825}
-03/05/2022 16:23:47 - INFO - codeparrot_training - Step 43320: {'lr': 0.000409846149938168, 'samples': 22180352, 'steps': 43320, 'loss/train': 1.7565006017684937}
-03/05/2022 16:23:47 - INFO - codeparrot_training - Skipping example with length 62 (seq_length=1024)
-03/05/2022 16:23:52 - INFO - codeparrot_training - Step 43321: {'lr': 0.000409842069615019, 'samples': 22180864, 'steps': 43321, 'loss/train': 1.2176549434661865}
-03/05/2022 16:23:55 - INFO - codeparrot_training - Step 43322: {'lr': 0.0004098379892198476, 'samples': 22181376, 'steps': 43322, 'loss/train': 1.4262795448303223}
-03/05/2022 16:23:55 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/05/2022 16:24:00 - INFO - codeparrot_training - Step 43323: {'lr': 0.0004098339087526557, 'samples': 22181888, 'steps': 43323, 'loss/train': 2.227158784866333}
-03/05/2022 16:24:03 - INFO - codeparrot_training - Step 43324: {'lr': 0.00040982982821344505, 'samples': 22182400, 'steps': 43324, 'loss/train': 1.4903699159622192}
-03/05/2022 16:24:03 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 16:24:09 - INFO - codeparrot_training - Step 43325: {'lr': 0.0004098257476022176, 'samples': 22182912, 'steps': 43325, 'loss/train': 2.0726962089538574}
-03/05/2022 16:24:12 - INFO - codeparrot_training - Step 43326: {'lr': 0.00040982166691897517, 'samples': 22183424, 'steps': 43326, 'loss/train': 1.7390996217727661}
-03/05/2022 16:24:12 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/05/2022 16:24:17 - INFO - codeparrot_training - Step 43327: {'lr': 0.00040981758616371943, 'samples': 22183936, 'steps': 43327, 'loss/train': 1.3204691410064697}
-03/05/2022 16:24:21 - INFO - codeparrot_training - Step 43328: {'lr': 0.00040981350533645245, 'samples': 22184448, 'steps': 43328, 'loss/train': 2.1645500659942627}
-03/05/2022 16:24:21 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/05/2022 16:24:26 - INFO - codeparrot_training - Step 43329: {'lr': 0.00040980942443717596, 'samples': 22184960, 'steps': 43329, 'loss/train': 2.4344727993011475}
-03/05/2022 16:24:29 - INFO - codeparrot_training - Step 43330: {'lr': 0.0004098053434658918, 'samples': 22185472, 'steps': 43330, 'loss/train': 2.095499277114868}
-03/05/2022 16:24:29 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/05/2022 16:24:34 - INFO - codeparrot_training - Step 43331: {'lr': 0.0004098012624226018, 'samples': 22185984, 'steps': 43331, 'loss/train': 1.8170472383499146}
-03/05/2022 16:24:37 - INFO - codeparrot_training - Step 43332: {'lr': 0.00040979718130730786, 'samples': 22186496, 'steps': 43332, 'loss/train': 1.6126526594161987}
-03/05/2022 16:24:37 - INFO - codeparrot_training - Skipping example with length 7 (seq_length=1024)
-03/05/2022 16:24:43 - INFO - codeparrot_training - Step 43333: {'lr': 0.0004097931001200118, 'samples': 22187008, 'steps': 43333, 'loss/train': 0.8030344843864441}
-03/05/2022 16:24:46 - INFO - codeparrot_training - Step 43334: {'lr': 0.00040978901886071543, 'samples': 22187520, 'steps': 43334, 'loss/train': 2.249089241027832}
-03/05/2022 16:24:46 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/05/2022 16:24:51 - INFO - codeparrot_training - Step 43335: {'lr': 0.0004097849375294205, 'samples': 22188032, 'steps': 43335, 'loss/train': 1.147964358329773}
-03/05/2022 16:24:54 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 16:24:56 - INFO - codeparrot_training - Step 43336: {'lr': 0.000409780856126129, 'samples': 22188544, 'steps': 43336, 'loss/train': 1.7460064888000488}
-03/05/2022 16:25:00 - INFO - codeparrot_training - Step 43337: {'lr': 0.00040977677465084275, 'samples': 22189056, 'steps': 43337, 'loss/train': 1.572378158569336}
-03/05/2022 16:25:02 - INFO - codeparrot_training - Skipping example with length 66 (seq_length=1024)
-03/05/2022 16:25:05 - INFO - codeparrot_training - Step 43338: {'lr': 0.00040977269310356345, 'samples': 22189568, 'steps': 43338, 'loss/train': 0.9728551506996155}
-03/05/2022 16:25:08 - INFO - codeparrot_training - Step 43339: {'lr': 0.00040976861148429313, 'samples': 22190080, 'steps': 43339, 'loss/train': 0.36501577496528625}
-03/05/2022 16:25:11 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/05/2022 16:25:13 - INFO - codeparrot_training - Step 43340: {'lr': 0.0004097645297930335, 'samples': 22190592, 'steps': 43340, 'loss/train': 1.357017159461975}
-03/05/2022 16:25:17 - INFO - codeparrot_training - Step 43341: {'lr': 0.00040976044802978645, 'samples': 22191104, 'steps': 43341, 'loss/train': 1.7620670795440674}
-03/05/2022 16:25:20 - INFO - codeparrot_training - Skipping example with length 97 (seq_length=1024)
-03/05/2022 16:25:22 - INFO - codeparrot_training - Step 43342: {'lr': 0.0004097563661945538, 'samples': 22191616, 'steps': 43342, 'loss/train': 1.441552996635437}
-03/05/2022 16:25:25 - INFO - codeparrot_training - Step 43343: {'lr': 0.0004097522842873374, 'samples': 22192128, 'steps': 43343, 'loss/train': 2.7072691917419434}
-03/05/2022 16:25:28 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/05/2022 16:25:30 - INFO - codeparrot_training - Step 43344: {'lr': 0.0004097482023081391, 'samples': 22192640, 'steps': 43344, 'loss/train': 2.577505350112915}
-03/05/2022 16:25:34 - INFO - codeparrot_training - Step 43345: {'lr': 0.00040974412025696067, 'samples': 22193152, 'steps': 43345, 'loss/train': 1.4229176044464111}
-03/05/2022 16:25:36 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/05/2022 16:25:39 - INFO - codeparrot_training - Step 43346: {'lr': 0.0004097400381338041, 'samples': 22193664, 'steps': 43346, 'loss/train': 1.234185814857483}
-03/05/2022 16:25:42 - INFO - codeparrot_training - Step 43347: {'lr': 0.0004097359559386711, 'samples': 22194176, 'steps': 43347, 'loss/train': 1.3730961084365845}
-03/05/2022 16:25:45 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/05/2022 16:25:47 - INFO - codeparrot_training - Step 43348: {'lr': 0.0004097318736715635, 'samples': 22194688, 'steps': 43348, 'loss/train': 2.0351779460906982}
-03/05/2022 16:25:51 - INFO - codeparrot_training - Step 43349: {'lr': 0.0004097277913324832, 'samples': 22195200, 'steps': 43349, 'loss/train': 1.8163080215454102}
-03/05/2022 16:25:53 - INFO - codeparrot_training - Skipping example with length 12 (seq_length=1024)
-03/05/2022 16:25:56 - INFO - codeparrot_training - Step 43350: {'lr': 0.000409723708921432, 'samples': 22195712, 'steps': 43350, 'loss/train': 1.5514692068099976}
-03/05/2022 16:25:59 - INFO - codeparrot_training - Step 43351: {'lr': 0.0004097196264384118, 'samples': 22196224, 'steps': 43351, 'loss/train': 0.38539794087409973}
-03/05/2022 16:26:01 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 16:26:04 - INFO - codeparrot_training - Step 43352: {'lr': 0.00040971554388342436, 'samples': 22196736, 'steps': 43352, 'loss/train': 2.0198237895965576}
-03/05/2022 16:26:08 - INFO - codeparrot_training - Step 43353: {'lr': 0.00040971146125647165, 'samples': 22197248, 'steps': 43353, 'loss/train': 1.6382557153701782}
-03/05/2022 16:26:11 - INFO - codeparrot_training - Step 43354: {'lr': 0.00040970737855755535, 'samples': 22197760, 'steps': 43354, 'loss/train': 1.3564033508300781}
-03/05/2022 16:26:11 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/05/2022 16:26:16 - INFO - codeparrot_training - Step 43355: {'lr': 0.00040970329578667735, 'samples': 22198272, 'steps': 43355, 'loss/train': 2.3902106285095215}
-03/05/2022 16:26:19 - INFO - codeparrot_training - Step 43356: {'lr': 0.00040969921294383956, 'samples': 22198784, 'steps': 43356, 'loss/train': 3.4535341262817383}
-03/05/2022 16:26:19 - INFO - codeparrot_training - Skipping example with length 31 (seq_length=1024)
-03/05/2022 16:26:24 - INFO - codeparrot_training - Step 43357: {'lr': 0.00040969513002904375, 'samples': 22199296, 'steps': 43357, 'loss/train': 1.6258068084716797}
-03/05/2022 16:26:28 - INFO - codeparrot_training - Step 43358: {'lr': 0.0004096910470422918, 'samples': 22199808, 'steps': 43358, 'loss/train': 1.2153639793395996}
-03/05/2022 16:26:28 - INFO - codeparrot_training - Skipping example with length 670 (seq_length=1024)
-03/05/2022 16:26:33 - INFO - codeparrot_training - Step 43359: {'lr': 0.0004096869639835855, 'samples': 22200320, 'steps': 43359, 'loss/train': 1.4235236644744873}
-03/05/2022 16:26:36 - INFO - codeparrot_training - Step 43360: {'lr': 0.0004096828808529267, 'samples': 22200832, 'steps': 43360, 'loss/train': 1.9123384952545166}
-03/05/2022 16:26:36 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/05/2022 16:26:41 - INFO - codeparrot_training - Step 43361: {'lr': 0.0004096787976503173, 'samples': 22201344, 'steps': 43361, 'loss/train': 2.8673346042633057}
-03/05/2022 16:26:45 - INFO - codeparrot_training - Step 43362: {'lr': 0.0004096747143757591, 'samples': 22201856, 'steps': 43362, 'loss/train': 1.7435725927352905}
-03/05/2022 16:26:45 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/05/2022 16:26:50 - INFO - codeparrot_training - Step 43363: {'lr': 0.0004096706310292539, 'samples': 22202368, 'steps': 43363, 'loss/train': 2.056272506713867}
-03/05/2022 16:26:53 - INFO - codeparrot_training - Step 43364: {'lr': 0.0004096665476108036, 'samples': 22202880, 'steps': 43364, 'loss/train': 1.076832890510559}
-03/05/2022 16:26:53 - INFO - codeparrot_training - Skipping example with length 642 (seq_length=1024)
-03/05/2022 16:26:59 - INFO - codeparrot_training - Step 43365: {'lr': 0.00040966246412040995, 'samples': 22203392, 'steps': 43365, 'loss/train': 1.996356725692749}
-03/05/2022 16:27:02 - INFO - codeparrot_training - Step 43366: {'lr': 0.00040965838055807493, 'samples': 22203904, 'steps': 43366, 'loss/train': 2.3094301223754883}
-03/05/2022 16:27:03 - INFO - codeparrot_training - Skipping example with length 367 (seq_length=1024)
-03/05/2022 16:27:07 - INFO - codeparrot_training - Step 43367: {'lr': 0.00040965429692380034, 'samples': 22204416, 'steps': 43367, 'loss/train': 2.051711082458496}
-03/05/2022 16:27:10 - INFO - codeparrot_training - Step 43368: {'lr': 0.00040965021321758796, 'samples': 22204928, 'steps': 43368, 'loss/train': 1.2962428331375122}
-03/05/2022 16:27:11 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/05/2022 16:27:16 - INFO - codeparrot_training - Step 43369: {'lr': 0.00040964612943943964, 'samples': 22205440, 'steps': 43369, 'loss/train': 1.508206844329834}
-03/05/2022 16:27:19 - INFO - codeparrot_training - Step 43370: {'lr': 0.00040964204558935726, 'samples': 22205952, 'steps': 43370, 'loss/train': 2.2256107330322266}
-03/05/2022 16:27:19 - INFO - codeparrot_training - Skipping example with length 447 (seq_length=1024)
-03/05/2022 16:27:24 - INFO - codeparrot_training - Step 43371: {'lr': 0.00040963796166734257, 'samples': 22206464, 'steps': 43371, 'loss/train': 1.6218324899673462}
-03/05/2022 16:27:27 - INFO - codeparrot_training - Step 43372: {'lr': 0.00040963387767339757, 'samples': 22206976, 'steps': 43372, 'loss/train': 1.4922221899032593}
-03/05/2022 16:27:28 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/05/2022 16:27:32 - INFO - codeparrot_training - Step 43373: {'lr': 0.00040962979360752394, 'samples': 22207488, 'steps': 43373, 'loss/train': 2.066102981567383}
-03/05/2022 16:27:36 - INFO - codeparrot_training - Step 43374: {'lr': 0.0004096257094697236, 'samples': 22208000, 'steps': 43374, 'loss/train': 1.886871576309204}
-03/05/2022 16:27:36 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/05/2022 16:27:41 - INFO - codeparrot_training - Step 43375: {'lr': 0.00040962162525999833, 'samples': 22208512, 'steps': 43375, 'loss/train': 2.311516761779785}
-03/05/2022 16:27:44 - INFO - codeparrot_training - Step 43376: {'lr': 0.00040961754097835015, 'samples': 22209024, 'steps': 43376, 'loss/train': 2.1094181537628174}
-03/05/2022 16:27:45 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/05/2022 16:27:50 - INFO - codeparrot_training - Step 43377: {'lr': 0.00040961345662478065, 'samples': 22209536, 'steps': 43377, 'loss/train': 1.2571252584457397}
-03/05/2022 16:27:53 - INFO - codeparrot_training - Step 43378: {'lr': 0.00040960937219929186, 'samples': 22210048, 'steps': 43378, 'loss/train': 1.975334882736206}
-03/05/2022 16:27:53 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/05/2022 16:27:58 - INFO - codeparrot_training - Step 43379: {'lr': 0.00040960528770188554, 'samples': 22210560, 'steps': 43379, 'loss/train': 1.0472302436828613}
-03/05/2022 16:28:01 - INFO - codeparrot_training - Step 43380: {'lr': 0.00040960120313256356, 'samples': 22211072, 'steps': 43380, 'loss/train': 1.998261570930481}
-03/05/2022 16:28:02 - INFO - codeparrot_training - Skipping example with length 368 (seq_length=1024)
-03/05/2022 16:28:07 - INFO - codeparrot_training - Step 43381: {'lr': 0.0004095971184913277, 'samples': 22211584, 'steps': 43381, 'loss/train': 1.7994533777236938}
-03/05/2022 16:28:10 - INFO - codeparrot_training - Step 43382: {'lr': 0.0004095930337781798, 'samples': 22212096, 'steps': 43382, 'loss/train': 1.8848236799240112}
-03/05/2022 16:28:10 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/05/2022 16:28:15 - INFO - codeparrot_training - Step 43383: {'lr': 0.00040958894899312183, 'samples': 22212608, 'steps': 43383, 'loss/train': 1.3643547296524048}
-03/05/2022 16:28:18 - INFO - codeparrot_training - Step 43384: {'lr': 0.0004095848641361555, 'samples': 22213120, 'steps': 43384, 'loss/train': 2.758451461791992}
-03/05/2022 16:28:20 - INFO - codeparrot_training - Skipping example with length 437 (seq_length=1024)
-03/05/2022 16:28:24 - INFO - codeparrot_training - Step 43385: {'lr': 0.0004095807792072827, 'samples': 22213632, 'steps': 43385, 'loss/train': 1.6296025514602661}
-03/05/2022 16:28:27 - INFO - codeparrot_training - Step 43386: {'lr': 0.00040957669420650525, 'samples': 22214144, 'steps': 43386, 'loss/train': 2.6608428955078125}
-03/05/2022 16:28:28 - INFO - codeparrot_training - Skipping example with length 363 (seq_length=1024)
-03/05/2022 16:28:32 - INFO - codeparrot_training - Step 43387: {'lr': 0.000409572609133825, 'samples': 22214656, 'steps': 43387, 'loss/train': 1.7277415990829468}
-03/05/2022 16:28:35 - INFO - codeparrot_training - Step 43388: {'lr': 0.00040956852398924383, 'samples': 22215168, 'steps': 43388, 'loss/train': 1.0673612356185913}
-03/05/2022 16:28:37 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/05/2022 16:28:41 - INFO - codeparrot_training - Step 43389: {'lr': 0.0004095644387727635, 'samples': 22215680, 'steps': 43389, 'loss/train': 4.4261908531188965}
-03/05/2022 16:28:44 - INFO - codeparrot_training - Step 43390: {'lr': 0.0004095603534843859, 'samples': 22216192, 'steps': 43390, 'loss/train': 1.3187798261642456}
-03/05/2022 16:28:45 - INFO - codeparrot_training - Skipping example with length 667 (seq_length=1024)
-03/05/2022 16:28:49 - INFO - codeparrot_training - Step 43391: {'lr': 0.00040955626812411297, 'samples': 22216704, 'steps': 43391, 'loss/train': 3.016716718673706}
-03/05/2022 16:28:52 - INFO - codeparrot_training - Step 43392: {'lr': 0.0004095521826919463, 'samples': 22217216, 'steps': 43392, 'loss/train': 1.3573050498962402}
-03/05/2022 16:28:54 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/05/2022 16:28:57 - INFO - codeparrot_training - Step 43393: {'lr': 0.0004095480971878879, 'samples': 22217728, 'steps': 43393, 'loss/train': 2.000455379486084}
-03/05/2022 16:29:01 - INFO - codeparrot_training - Step 43394: {'lr': 0.0004095440116119397, 'samples': 22218240, 'steps': 43394, 'loss/train': 2.1848514080047607}
-03/05/2022 16:29:02 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/05/2022 16:29:06 - INFO - codeparrot_training - Step 43395: {'lr': 0.00040953992596410335, 'samples': 22218752, 'steps': 43395, 'loss/train': 1.9530316591262817}
-03/05/2022 16:29:09 - INFO - codeparrot_training - Step 43396: {'lr': 0.0004095358402443808, 'samples': 22219264, 'steps': 43396, 'loss/train': 1.3370455503463745}
-03/05/2022 16:29:10 - INFO - codeparrot_training - Skipping example with length 115 (seq_length=1024)
-03/05/2022 16:29:14 - INFO - codeparrot_training - Step 43397: {'lr': 0.0004095317544527738, 'samples': 22219776, 'steps': 43397, 'loss/train': 1.0897003412246704}
-03/05/2022 16:29:17 - INFO - codeparrot_training - Step 43398: {'lr': 0.00040952766858928433, 'samples': 22220288, 'steps': 43398, 'loss/train': 2.345574140548706}
-03/05/2022 16:29:19 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 16:29:23 - INFO - codeparrot_training - Step 43399: {'lr': 0.0004095235826539141, 'samples': 22220800, 'steps': 43399, 'loss/train': 1.7572458982467651}
-03/05/2022 16:29:26 - INFO - codeparrot_training - Step 43400: {'lr': 0.00040951949664666504, 'samples': 22221312, 'steps': 43400, 'loss/train': 1.6472071409225464}
-03/05/2022 16:29:27 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/05/2022 16:29:31 - INFO - codeparrot_training - Step 43401: {'lr': 0.00040951541056753895, 'samples': 22221824, 'steps': 43401, 'loss/train': 1.2369054555892944}
-03/05/2022 16:29:34 - INFO - codeparrot_training - Step 43402: {'lr': 0.00040951132441653773, 'samples': 22222336, 'steps': 43402, 'loss/train': 2.183459997177124}
-03/05/2022 16:29:36 - INFO - codeparrot_training - Skipping example with length 84 (seq_length=1024)
-03/05/2022 16:29:40 - INFO - codeparrot_training - Step 43403: {'lr': 0.00040950723819366307, 'samples': 22222848, 'steps': 43403, 'loss/train': 1.8384268283843994}
-03/05/2022 16:29:43 - INFO - codeparrot_training - Step 43404: {'lr': 0.000409503151898917, 'samples': 22223360, 'steps': 43404, 'loss/train': 1.941799521446228}
-03/05/2022 16:29:44 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/05/2022 16:29:48 - INFO - codeparrot_training - Step 43405: {'lr': 0.0004094990655323012, 'samples': 22223872, 'steps': 43405, 'loss/train': 1.082533597946167}
-03/05/2022 16:29:51 - INFO - codeparrot_training - Step 43406: {'lr': 0.00040949497909381757, 'samples': 22224384, 'steps': 43406, 'loss/train': 1.0185636281967163}
-03/05/2022 16:29:53 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/05/2022 16:29:57 - INFO - codeparrot_training - Step 43407: {'lr': 0.000409490892583468, 'samples': 22224896, 'steps': 43407, 'loss/train': 1.0507245063781738}
-03/05/2022 16:30:00 - INFO - codeparrot_training - Step 43408: {'lr': 0.0004094868060012543, 'samples': 22225408, 'steps': 43408, 'loss/train': 1.8886489868164062}
-03/05/2022 16:30:01 - INFO - codeparrot_training - Skipping example with length 825 (seq_length=1024)
-03/05/2022 16:30:05 - INFO - codeparrot_training - Step 43409: {'lr': 0.0004094827193471783, 'samples': 22225920, 'steps': 43409, 'loss/train': 1.2209147214889526}
-03/05/2022 16:30:08 - INFO - codeparrot_training - Step 43410: {'lr': 0.00040947863262124186, 'samples': 22226432, 'steps': 43410, 'loss/train': 2.434523820877075}
-03/05/2022 16:30:09 - INFO - codeparrot_training - Skipping example with length 281 (seq_length=1024)
-03/05/2022 16:30:13 - INFO - codeparrot_training - Step 43411: {'lr': 0.0004094745458234468, 'samples': 22226944, 'steps': 43411, 'loss/train': 1.2861884832382202}
-03/05/2022 16:30:17 - INFO - codeparrot_training - Step 43412: {'lr': 0.00040947045895379494, 'samples': 22227456, 'steps': 43412, 'loss/train': 1.6324081420898438}
-03/05/2022 16:30:18 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/05/2022 16:30:22 - INFO - codeparrot_training - Step 43413: {'lr': 0.00040946637201228815, 'samples': 22227968, 'steps': 43413, 'loss/train': 2.4248392581939697}
-03/05/2022 16:30:25 - INFO - codeparrot_training - Step 43414: {'lr': 0.00040946228499892835, 'samples': 22228480, 'steps': 43414, 'loss/train': 1.2386106252670288}
-03/05/2022 16:30:26 - INFO - codeparrot_training - Skipping example with length 932 (seq_length=1024)
-03/05/2022 16:30:30 - INFO - codeparrot_training - Step 43415: {'lr': 0.0004094581979137172, 'samples': 22228992, 'steps': 43415, 'loss/train': 2.3843882083892822}
-03/05/2022 16:30:33 - INFO - codeparrot_training - Step 43416: {'lr': 0.00040945411075665674, 'samples': 22229504, 'steps': 43416, 'loss/train': 1.8741120100021362}
-03/05/2022 16:30:34 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/05/2022 16:30:39 - INFO - codeparrot_training - Step 43417: {'lr': 0.0004094500235277486, 'samples': 22230016, 'steps': 43417, 'loss/train': 1.5433290004730225}
-03/05/2022 16:30:42 - INFO - codeparrot_training - Step 43418: {'lr': 0.0004094459362269949, 'samples': 22230528, 'steps': 43418, 'loss/train': 2.6721668243408203}
-03/05/2022 16:30:42 - INFO - codeparrot_training - Skipping example with length 139 (seq_length=1024)
-03/05/2022 16:30:47 - INFO - codeparrot_training - Step 43419: {'lr': 0.0004094418488543972, 'samples': 22231040, 'steps': 43419, 'loss/train': 6.720859527587891}
-03/05/2022 16:30:50 - INFO - codeparrot_training - Step 43420: {'lr': 0.00040943776140995756, 'samples': 22231552, 'steps': 43420, 'loss/train': 1.2261567115783691}
-03/05/2022 16:30:52 - INFO - codeparrot_training - Skipping example with length 705 (seq_length=1024)
-03/05/2022 16:30:55 - INFO - codeparrot_training - Step 43421: {'lr': 0.0004094336738936777, 'samples': 22232064, 'steps': 43421, 'loss/train': 1.625981330871582}
-03/05/2022 16:30:59 - INFO - codeparrot_training - Step 43422: {'lr': 0.0004094295863055594, 'samples': 22232576, 'steps': 43422, 'loss/train': 1.865250825881958}
-03/05/2022 16:31:00 - INFO - codeparrot_training - Skipping example with length 93 (seq_length=1024)
-03/05/2022 16:31:04 - INFO - codeparrot_training - Step 43423: {'lr': 0.0004094254986456046, 'samples': 22233088, 'steps': 43423, 'loss/train': 1.1052261590957642}
-03/05/2022 16:31:07 - INFO - codeparrot_training - Step 43424: {'lr': 0.0004094214109138152, 'samples': 22233600, 'steps': 43424, 'loss/train': 2.057037591934204}
-03/05/2022 16:31:10 - INFO - codeparrot_training - Skipping example with length 77 (seq_length=1024)
-03/05/2022 16:31:13 - INFO - codeparrot_training - Step 43425: {'lr': 0.000409417323110193, 'samples': 22234112, 'steps': 43425, 'loss/train': 1.785339593887329}
-03/05/2022 16:31:16 - INFO - codeparrot_training - Step 43426: {'lr': 0.00040941323523473975, 'samples': 22234624, 'steps': 43426, 'loss/train': 2.082720994949341}
-03/05/2022 16:31:19 - INFO - codeparrot_training - Step 43427: {'lr': 0.00040940914728745736, 'samples': 22235136, 'steps': 43427, 'loss/train': 2.516047239303589}
-03/05/2022 16:31:19 - INFO - codeparrot_training - Skipping example with length 193 (seq_length=1024)
-03/05/2022 16:31:24 - INFO - codeparrot_training - Step 43428: {'lr': 0.0004094050592683477, 'samples': 22235648, 'steps': 43428, 'loss/train': 1.8581115007400513}
-03/05/2022 16:31:28 - INFO - codeparrot_training - Step 43429: {'lr': 0.00040940097117741255, 'samples': 22236160, 'steps': 43429, 'loss/train': 2.093256711959839}
-03/05/2022 16:31:28 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/05/2022 16:31:33 - INFO - codeparrot_training - Step 43430: {'lr': 0.00040939688301465377, 'samples': 22236672, 'steps': 43430, 'loss/train': 1.8424209356307983}
-03/05/2022 16:31:36 - INFO - codeparrot_training - Step 43431: {'lr': 0.0004093927947800732, 'samples': 22237184, 'steps': 43431, 'loss/train': 2.3670756816864014}
-03/05/2022 16:31:36 - INFO - codeparrot_training - Skipping example with length 145 (seq_length=1024)
-03/05/2022 16:31:41 - INFO - codeparrot_training - Step 43432: {'lr': 0.00040938870647367275, 'samples': 22237696, 'steps': 43432, 'loss/train': 1.480378270149231}
-03/05/2022 16:31:45 - INFO - codeparrot_training - Step 43433: {'lr': 0.0004093846180954542, 'samples': 22238208, 'steps': 43433, 'loss/train': 2.6717529296875}
-03/05/2022 16:31:45 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/05/2022 16:31:50 - INFO - codeparrot_training - Step 43434: {'lr': 0.00040938052964541936, 'samples': 22238720, 'steps': 43434, 'loss/train': 1.94635808467865}
-03/05/2022 16:31:53 - INFO - codeparrot_training - Step 43435: {'lr': 0.0004093764411235702, 'samples': 22239232, 'steps': 43435, 'loss/train': 0.8725064992904663}
-03/05/2022 16:31:53 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/05/2022 16:31:58 - INFO - codeparrot_training - Step 43436: {'lr': 0.00040937235252990834, 'samples': 22239744, 'steps': 43436, 'loss/train': 1.1072663068771362}
-03/05/2022 16:32:02 - INFO - codeparrot_training - Step 43437: {'lr': 0.00040936826386443585, 'samples': 22240256, 'steps': 43437, 'loss/train': 1.9217743873596191}
-03/05/2022 16:32:02 - INFO - codeparrot_training - Skipping example with length 94 (seq_length=1024)
-03/05/2022 16:32:07 - INFO - codeparrot_training - Step 43438: {'lr': 0.00040936417512715454, 'samples': 22240768, 'steps': 43438, 'loss/train': 1.182011365890503}
-03/05/2022 16:32:10 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/05/2022 16:32:12 - INFO - codeparrot_training - Step 43439: {'lr': 0.00040936008631806603, 'samples': 22241280, 'steps': 43439, 'loss/train': 1.537466049194336}
-03/05/2022 16:32:15 - INFO - codeparrot_training - Step 43440: {'lr': 0.00040935599743717243, 'samples': 22241792, 'steps': 43440, 'loss/train': 1.962570309638977}
-03/05/2022 16:32:18 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/05/2022 16:32:20 - INFO - codeparrot_training - Step 43441: {'lr': 0.00040935190848447544, 'samples': 22242304, 'steps': 43441, 'loss/train': 2.3581345081329346}
-03/05/2022 16:32:24 - INFO - codeparrot_training - Step 43442: {'lr': 0.000409347819459977, 'samples': 22242816, 'steps': 43442, 'loss/train': 1.8138973712921143}
-03/05/2022 16:32:27 - INFO - codeparrot_training - Step 43443: {'lr': 0.0004093437303636788, 'samples': 22243328, 'steps': 43443, 'loss/train': 2.073587417602539}
-03/05/2022 16:32:27 - INFO - codeparrot_training - Skipping example with length 176 (seq_length=1024)
-03/05/2022 16:32:32 - INFO - codeparrot_training - Step 43444: {'lr': 0.0004093396411955829, 'samples': 22243840, 'steps': 43444, 'loss/train': 1.656822681427002}
-03/05/2022 16:32:35 - INFO - codeparrot_training - Step 43445: {'lr': 0.0004093355519556908, 'samples': 22244352, 'steps': 43445, 'loss/train': 7.034511089324951}
-03/05/2022 16:32:35 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/05/2022 16:32:41 - INFO - codeparrot_training - Step 43446: {'lr': 0.0004093314626440048, 'samples': 22244864, 'steps': 43446, 'loss/train': 1.6902729272842407}
-03/05/2022 16:32:44 - INFO - codeparrot_training - Step 43447: {'lr': 0.0004093273732605264, 'samples': 22245376, 'steps': 43447, 'loss/train': 1.8294931650161743}
-03/05/2022 16:32:44 - INFO - codeparrot_training - Skipping example with length 348 (seq_length=1024)
-03/05/2022 16:32:49 - INFO - codeparrot_training - Step 43448: {'lr': 0.0004093232838052575, 'samples': 22245888, 'steps': 43448, 'loss/train': 1.8179471492767334}
-03/05/2022 16:32:52 - INFO - codeparrot_training - Step 43449: {'lr': 0.0004093191942782001, 'samples': 22246400, 'steps': 43449, 'loss/train': 1.4248247146606445}
-03/05/2022 16:32:52 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/05/2022 16:32:58 - INFO - codeparrot_training - Step 43450: {'lr': 0.0004093151046793558, 'samples': 22246912, 'steps': 43450, 'loss/train': 1.8495866060256958}
-03/05/2022 16:33:01 - INFO - codeparrot_training - Skipping example with length 417 (seq_length=1024)
-03/05/2022 16:33:03 - INFO - codeparrot_training - Step 43451: {'lr': 0.00040931101500872656, 'samples': 22247424, 'steps': 43451, 'loss/train': 2.4566843509674072}
-03/05/2022 16:33:06 - INFO - codeparrot_training - Step 43452: {'lr': 0.00040930692526631443, 'samples': 22247936, 'steps': 43452, 'loss/train': 1.5582078695297241}
-03/05/2022 16:33:09 - INFO - codeparrot_training - Skipping example with length 425 (seq_length=1024)
-03/05/2022 16:33:11 - INFO - codeparrot_training - Step 43453: {'lr': 0.0004093028354521209, 'samples': 22248448, 'steps': 43453, 'loss/train': 1.3538379669189453}
-03/05/2022 16:33:15 - INFO - codeparrot_training - Step 43454: {'lr': 0.000409298745566148, 'samples': 22248960, 'steps': 43454, 'loss/train': 1.7898694276809692}
-03/05/2022 16:33:17 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/05/2022 16:33:20 - INFO - codeparrot_training - Step 43455: {'lr': 0.00040929465560839753, 'samples': 22249472, 'steps': 43455, 'loss/train': 1.5181999206542969}
-03/05/2022 16:33:23 - INFO - codeparrot_training - Step 43456: {'lr': 0.00040929056557887137, 'samples': 22249984, 'steps': 43456, 'loss/train': 1.8687688112258911}
-03/05/2022 16:33:25 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/05/2022 16:33:28 - INFO - codeparrot_training - Step 43457: {'lr': 0.0004092864754775713, 'samples': 22250496, 'steps': 43457, 'loss/train': 1.209481954574585}
-03/05/2022 16:33:31 - INFO - codeparrot_training - Step 43458: {'lr': 0.00040928238530449926, 'samples': 22251008, 'steps': 43458, 'loss/train': 1.4416886568069458}
-03/05/2022 16:33:34 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/05/2022 16:33:37 - INFO - codeparrot_training - Step 43459: {'lr': 0.00040927829505965694, 'samples': 22251520, 'steps': 43459, 'loss/train': 2.0315394401550293}
-03/05/2022 16:33:40 - INFO - codeparrot_training - Step 43460: {'lr': 0.00040927420474304646, 'samples': 22252032, 'steps': 43460, 'loss/train': 1.5098377466201782}
-03/05/2022 16:33:42 - INFO - codeparrot_training - Skipping example with length 724 (seq_length=1024)
-03/05/2022 16:33:45 - INFO - codeparrot_training - Step 43461: {'lr': 0.00040927011435466933, 'samples': 22252544, 'steps': 43461, 'loss/train': 1.8692922592163086}
-03/05/2022 16:33:48 - INFO - codeparrot_training - Step 43462: {'lr': 0.0004092660238945276, 'samples': 22253056, 'steps': 43462, 'loss/train': 0.7996223568916321}
-03/05/2022 16:33:50 - INFO - codeparrot_training - Skipping example with length 529 (seq_length=1024)
-03/05/2022 16:33:54 - INFO - codeparrot_training - Step 43463: {'lr': 0.00040926193336262304, 'samples': 22253568, 'steps': 43463, 'loss/train': 1.5729109048843384}
-03/05/2022 16:33:57 - INFO - codeparrot_training - Step 43464: {'lr': 0.0004092578427589575, 'samples': 22254080, 'steps': 43464, 'loss/train': 2.0172555446624756}
-03/05/2022 16:33:59 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 16:34:02 - INFO - codeparrot_training - Step 43465: {'lr': 0.0004092537520835328, 'samples': 22254592, 'steps': 43465, 'loss/train': 2.3409149646759033}
-03/05/2022 16:34:05 - INFO - codeparrot_training - Step 43466: {'lr': 0.0004092496613363509, 'samples': 22255104, 'steps': 43466, 'loss/train': 1.2438368797302246}
-03/05/2022 16:34:07 - INFO - codeparrot_training - Skipping example with length 813 (seq_length=1024)
-03/05/2022 16:34:10 - INFO - codeparrot_training - Step 43467: {'lr': 0.0004092455705174135, 'samples': 22255616, 'steps': 43467, 'loss/train': 1.6945438385009766}
-03/05/2022 16:34:14 - INFO - codeparrot_training - Step 43468: {'lr': 0.00040924147962672253, 'samples': 22256128, 'steps': 43468, 'loss/train': 1.7372034788131714}
-03/05/2022 16:34:16 - INFO - codeparrot_training - Skipping example with length 389 (seq_length=1024)
-03/05/2022 16:34:19 - INFO - codeparrot_training - Step 43469: {'lr': 0.00040923738866427986, 'samples': 22256640, 'steps': 43469, 'loss/train': 1.73540461063385}
-03/05/2022 16:34:22 - INFO - codeparrot_training - Step 43470: {'lr': 0.00040923329763008714, 'samples': 22257152, 'steps': 43470, 'loss/train': 1.5015273094177246}
-03/05/2022 16:34:24 - INFO - codeparrot_training - Skipping example with length 586 (seq_length=1024)
-03/05/2022 16:34:27 - INFO - codeparrot_training - Step 43471: {'lr': 0.0004092292065241464, 'samples': 22257664, 'steps': 43471, 'loss/train': 1.4789345264434814}
-03/05/2022 16:34:31 - INFO - codeparrot_training - Step 43472: {'lr': 0.00040922511534645953, 'samples': 22258176, 'steps': 43472, 'loss/train': 2.03440523147583}
-03/05/2022 16:34:33 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 16:34:36 - INFO - codeparrot_training - Step 43473: {'lr': 0.0004092210240970282, 'samples': 22258688, 'steps': 43473, 'loss/train': 0.5834307074546814}
-03/05/2022 16:34:39 - INFO - codeparrot_training - Step 43474: {'lr': 0.0004092169327758544, 'samples': 22259200, 'steps': 43474, 'loss/train': 0.5725497007369995}
-03/05/2022 16:34:41 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/05/2022 16:34:45 - INFO - codeparrot_training - Step 43475: {'lr': 0.0004092128413829398, 'samples': 22259712, 'steps': 43475, 'loss/train': 1.9388123750686646}
-03/05/2022 16:34:48 - INFO - codeparrot_training - Step 43476: {'lr': 0.0004092087499182864, 'samples': 22260224, 'steps': 43476, 'loss/train': 1.5793097019195557}
-03/05/2022 16:34:50 - INFO - codeparrot_training - Skipping example with length 452 (seq_length=1024)
-03/05/2022 16:34:53 - INFO - codeparrot_training - Step 43477: {'lr': 0.000409204658381896, 'samples': 22260736, 'steps': 43477, 'loss/train': 0.8688333034515381}
-03/05/2022 16:34:57 - INFO - codeparrot_training - Step 43478: {'lr': 0.00040920056677377047, 'samples': 22261248, 'steps': 43478, 'loss/train': 1.7755496501922607}
-03/05/2022 16:34:59 - INFO - codeparrot_training - Skipping example with length 920 (seq_length=1024)
-03/05/2022 16:35:02 - INFO - codeparrot_training - Step 43479: {'lr': 0.00040919647509391155, 'samples': 22261760, 'steps': 43479, 'loss/train': 1.1312000751495361}
-03/05/2022 16:35:05 - INFO - codeparrot_training - Step 43480: {'lr': 0.0004091923833423212, 'samples': 22262272, 'steps': 43480, 'loss/train': 1.179079294204712}
-03/05/2022 16:35:08 - INFO - codeparrot_training - Skipping example with length 85 (seq_length=1024)
-03/05/2022 16:35:10 - INFO - codeparrot_training - Step 43481: {'lr': 0.00040918829151900127, 'samples': 22262784, 'steps': 43481, 'loss/train': 1.7857574224472046}
-03/05/2022 16:35:14 - INFO - codeparrot_training - Step 43482: {'lr': 0.0004091841996239535, 'samples': 22263296, 'steps': 43482, 'loss/train': 1.3958780765533447}
-03/05/2022 16:35:16 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/05/2022 16:35:19 - INFO - codeparrot_training - Step 43483: {'lr': 0.00040918010765717976, 'samples': 22263808, 'steps': 43483, 'loss/train': 1.8963899612426758}
-03/05/2022 16:35:22 - INFO - codeparrot_training - Step 43484: {'lr': 0.00040917601561868194, 'samples': 22264320, 'steps': 43484, 'loss/train': 1.1714063882827759}
-03/05/2022 16:35:25 - INFO - codeparrot_training - Skipping example with length 461 (seq_length=1024)
-03/05/2022 16:35:27 - INFO - codeparrot_training - Step 43485: {'lr': 0.00040917192350846187, 'samples': 22264832, 'steps': 43485, 'loss/train': 2.2142341136932373}
-03/05/2022 16:35:31 - INFO - codeparrot_training - Step 43486: {'lr': 0.00040916783132652134, 'samples': 22265344, 'steps': 43486, 'loss/train': 1.316070556640625}
-03/05/2022 16:35:33 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/05/2022 16:35:36 - INFO - codeparrot_training - Step 43487: {'lr': 0.0004091637390728623, 'samples': 22265856, 'steps': 43487, 'loss/train': 1.7286927700042725}
-03/05/2022 16:35:39 - INFO - codeparrot_training - Step 43488: {'lr': 0.00040915964674748665, 'samples': 22266368, 'steps': 43488, 'loss/train': 1.663365125656128}
-03/05/2022 16:35:42 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/05/2022 16:35:45 - INFO - codeparrot_training - Step 43489: {'lr': 0.0004091555543503959, 'samples': 22266880, 'steps': 43489, 'loss/train': 1.930106282234192}
-03/05/2022 16:35:48 - INFO - codeparrot_training - Step 43490: {'lr': 0.00040915146188159223, 'samples': 22267392, 'steps': 43490, 'loss/train': 0.0828438401222229}
-03/05/2022 16:35:51 - INFO - codeparrot_training - Step 43491: {'lr': 0.0004091473693410773, 'samples': 22267904, 'steps': 43491, 'loss/train': 2.0211939811706543}
-03/05/2022 16:35:51 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/05/2022 16:35:56 - INFO - codeparrot_training - Step 43492: {'lr': 0.0004091432767288531, 'samples': 22268416, 'steps': 43492, 'loss/train': 1.9732705354690552}
-03/05/2022 16:35:59 - INFO - codeparrot_training - Step 43493: {'lr': 0.0004091391840449213, 'samples': 22268928, 'steps': 43493, 'loss/train': 1.4866596460342407}
-03/05/2022 16:35:59 - INFO - codeparrot_training - Skipping example with length 800 (seq_length=1024)
-03/05/2022 16:36:05 - INFO - codeparrot_training - Step 43494: {'lr': 0.00040913509128928394, 'samples': 22269440, 'steps': 43494, 'loss/train': 1.7426174879074097}
-03/05/2022 16:36:08 - INFO - codeparrot_training - Step 43495: {'lr': 0.00040913099846194274, 'samples': 22269952, 'steps': 43495, 'loss/train': 0.23369881510734558}
-03/05/2022 16:36:08 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/05/2022 16:36:13 - INFO - codeparrot_training - Step 43496: {'lr': 0.00040912690556289957, 'samples': 22270464, 'steps': 43496, 'loss/train': 1.9182265996932983}
-03/05/2022 16:36:16 - INFO - codeparrot_training - Step 43497: {'lr': 0.0004091228125921562, 'samples': 22270976, 'steps': 43497, 'loss/train': 1.8995013236999512}
-03/05/2022 16:36:16 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/05/2022 16:36:22 - INFO - codeparrot_training - Step 43498: {'lr': 0.0004091187195497146, 'samples': 22271488, 'steps': 43498, 'loss/train': 1.671336054801941}
-03/05/2022 16:36:25 - INFO - codeparrot_training - Step 43499: {'lr': 0.00040911462643557656, 'samples': 22272000, 'steps': 43499, 'loss/train': 1.895821213722229}
-03/05/2022 16:36:25 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/05/2022 16:36:30 - INFO - codeparrot_training - Step 43500: {'lr': 0.0004091105332497439, 'samples': 22272512, 'steps': 43500, 'loss/train': 2.290811777114868}
-03/05/2022 16:36:33 - INFO - codeparrot_training - Step 43501: {'lr': 0.0004091064399922185, 'samples': 22273024, 'steps': 43501, 'loss/train': 1.6062957048416138}
-03/05/2022 16:36:34 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/05/2022 16:36:39 - INFO - codeparrot_training - Step 43502: {'lr': 0.0004091023466630023, 'samples': 22273536, 'steps': 43502, 'loss/train': 1.0313433408737183}
-03/05/2022 16:36:42 - INFO - codeparrot_training - Step 43503: {'lr': 0.00040909825326209694, 'samples': 22274048, 'steps': 43503, 'loss/train': 1.9420777559280396}
-03/05/2022 16:36:42 - INFO - codeparrot_training - Skipping example with length 504 (seq_length=1024)
-03/05/2022 16:36:47 - INFO - codeparrot_training - Step 43504: {'lr': 0.0004090941597895043, 'samples': 22274560, 'steps': 43504, 'loss/train': 1.579280138015747}
-03/05/2022 16:36:50 - INFO - codeparrot_training - Step 43505: {'lr': 0.0004090900662452264, 'samples': 22275072, 'steps': 43505, 'loss/train': 1.4133107662200928}
-03/05/2022 16:36:50 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/05/2022 16:36:56 - INFO - codeparrot_training - Step 43506: {'lr': 0.00040908597262926484, 'samples': 22275584, 'steps': 43506, 'loss/train': 1.4942498207092285}
-03/05/2022 16:36:59 - INFO - codeparrot_training - Step 43507: {'lr': 0.0004090818789416217, 'samples': 22276096, 'steps': 43507, 'loss/train': 1.8641345500946045}
-03/05/2022 16:36:59 - INFO - codeparrot_training - Skipping example with length 697 (seq_length=1024)
-03/05/2022 16:37:04 - INFO - codeparrot_training - Step 43508: {'lr': 0.0004090777851822988, 'samples': 22276608, 'steps': 43508, 'loss/train': 1.3042681217193604}
-03/05/2022 16:37:07 - INFO - codeparrot_training - Step 43509: {'lr': 0.0004090736913512977, 'samples': 22277120, 'steps': 43509, 'loss/train': 1.2210595607757568}
-03/05/2022 16:37:07 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/05/2022 16:37:12 - INFO - codeparrot_training - Step 43510: {'lr': 0.0004090695974486206, 'samples': 22277632, 'steps': 43510, 'loss/train': 2.2817001342773438}
-03/05/2022 16:37:15 - INFO - codeparrot_training - Step 43511: {'lr': 0.00040906550347426907, 'samples': 22278144, 'steps': 43511, 'loss/train': 1.3206937313079834}
-03/05/2022 16:37:16 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/05/2022 16:37:21 - INFO - codeparrot_training - Step 43512: {'lr': 0.0004090614094282452, 'samples': 22278656, 'steps': 43512, 'loss/train': 1.8190135955810547}
-03/05/2022 16:37:24 - INFO - codeparrot_training - Step 43513: {'lr': 0.00040905731531055067, 'samples': 22279168, 'steps': 43513, 'loss/train': 1.7540173530578613}
-03/05/2022 16:37:24 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/05/2022 16:37:29 - INFO - codeparrot_training - Step 43514: {'lr': 0.0004090532211211874, 'samples': 22279680, 'steps': 43514, 'loss/train': 1.7907708883285522}
-03/05/2022 16:37:32 - INFO - codeparrot_training - Step 43515: {'lr': 0.0004090491268601572, 'samples': 22280192, 'steps': 43515, 'loss/train': 1.856278419494629}
-03/05/2022 16:37:32 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 16:37:38 - INFO - codeparrot_training - Step 43516: {'lr': 0.0004090450325274618, 'samples': 22280704, 'steps': 43516, 'loss/train': 1.101977825164795}
-03/05/2022 16:37:41 - INFO - codeparrot_training - Step 43517: {'lr': 0.0004090409381231033, 'samples': 22281216, 'steps': 43517, 'loss/train': 1.4714518785476685}
-03/05/2022 16:37:41 - INFO - codeparrot_training - Skipping example with length 320 (seq_length=1024)
-03/05/2022 16:37:46 - INFO - codeparrot_training - Step 43518: {'lr': 0.0004090368436470833, 'samples': 22281728, 'steps': 43518, 'loss/train': 1.5295124053955078}
-03/05/2022 16:37:49 - INFO - codeparrot_training - Step 43519: {'lr': 0.0004090327490994038, 'samples': 22282240, 'steps': 43519, 'loss/train': 1.5267893075942993}
-03/05/2022 16:37:49 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 16:37:55 - INFO - codeparrot_training - Step 43520: {'lr': 0.00040902865448006663, 'samples': 22282752, 'steps': 43520, 'loss/train': 2.32295560836792}
-03/05/2022 16:37:58 - INFO - codeparrot_training - Step 43521: {'lr': 0.0004090245597890736, 'samples': 22283264, 'steps': 43521, 'loss/train': 1.7842472791671753}
-03/05/2022 16:37:58 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/05/2022 16:38:03 - INFO - codeparrot_training - Step 43522: {'lr': 0.00040902046502642656, 'samples': 22283776, 'steps': 43522, 'loss/train': 1.6596343517303467}
-03/05/2022 16:38:06 - INFO - codeparrot_training - Step 43523: {'lr': 0.0004090163701921273, 'samples': 22284288, 'steps': 43523, 'loss/train': 2.123654365539551}
-03/05/2022 16:38:06 - INFO - codeparrot_training - Skipping example with length 696 (seq_length=1024)
-03/05/2022 16:38:12 - INFO - codeparrot_training - Step 43524: {'lr': 0.0004090122752861777, 'samples': 22284800, 'steps': 43524, 'loss/train': 2.0612683296203613}
-03/05/2022 16:38:15 - INFO - codeparrot_training - Step 43525: {'lr': 0.0004090081803085797, 'samples': 22285312, 'steps': 43525, 'loss/train': 1.7806622982025146}
-03/05/2022 16:38:15 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 16:38:20 - INFO - codeparrot_training - Step 43526: {'lr': 0.00040900408525933505, 'samples': 22285824, 'steps': 43526, 'loss/train': 1.4373328685760498}
-03/05/2022 16:38:23 - INFO - codeparrot_training - Step 43527: {'lr': 0.0004089999901384456, 'samples': 22286336, 'steps': 43527, 'loss/train': 1.595618724822998}
-03/05/2022 16:38:23 - INFO - codeparrot_training - Skipping example with length 662 (seq_length=1024)
-03/05/2022 16:38:29 - INFO - codeparrot_training - Step 43528: {'lr': 0.00040899589494591316, 'samples': 22286848, 'steps': 43528, 'loss/train': 1.22590172290802}
-03/05/2022 16:38:32 - INFO - codeparrot_training - Step 43529: {'lr': 0.0004089917996817397, 'samples': 22287360, 'steps': 43529, 'loss/train': 1.0005383491516113}
-03/05/2022 16:38:32 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 16:38:37 - INFO - codeparrot_training - Step 43530: {'lr': 0.00040898770434592694, 'samples': 22287872, 'steps': 43530, 'loss/train': 0.7258080840110779}
-03/05/2022 16:38:40 - INFO - codeparrot_training - Step 43531: {'lr': 0.0004089836089384768, 'samples': 22288384, 'steps': 43531, 'loss/train': 2.315338373184204}
-03/05/2022 16:38:40 - INFO - codeparrot_training - Skipping example with length 95 (seq_length=1024)
-03/05/2022 16:38:45 - INFO - codeparrot_training - Step 43532: {'lr': 0.0004089795134593911, 'samples': 22288896, 'steps': 43532, 'loss/train': 1.788054347038269}
-03/05/2022 16:38:48 - INFO - codeparrot_training - Step 43533: {'lr': 0.00040897541790867165, 'samples': 22289408, 'steps': 43533, 'loss/train': 1.650675654411316}
-03/05/2022 16:38:48 - INFO - codeparrot_training - Skipping example with length 298 (seq_length=1024)
-03/05/2022 16:38:54 - INFO - codeparrot_training - Step 43534: {'lr': 0.00040897132228632035, 'samples': 22289920, 'steps': 43534, 'loss/train': 2.0224924087524414}
-03/05/2022 16:38:57 - INFO - codeparrot_training - Step 43535: {'lr': 0.000408967226592339, 'samples': 22290432, 'steps': 43535, 'loss/train': 2.995075225830078}
-03/05/2022 16:38:57 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/05/2022 16:39:02 - INFO - codeparrot_training - Step 43536: {'lr': 0.00040896313082672953, 'samples': 22290944, 'steps': 43536, 'loss/train': 0.3775224983692169}
-03/05/2022 16:39:05 - INFO - codeparrot_training - Skipping example with length 688 (seq_length=1024)
-03/05/2022 16:39:08 - INFO - codeparrot_training - Step 43537: {'lr': 0.0004089590349894937, 'samples': 22291456, 'steps': 43537, 'loss/train': 1.7950793504714966}
-03/05/2022 16:39:11 - INFO - codeparrot_training - Step 43538: {'lr': 0.0004089549390806334, 'samples': 22291968, 'steps': 43538, 'loss/train': 1.1951911449432373}
-03/05/2022 16:39:14 - INFO - codeparrot_training - Step 43539: {'lr': 0.0004089508431001504, 'samples': 22292480, 'steps': 43539, 'loss/train': 1.8888870477676392}
-03/05/2022 16:39:14 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/05/2022 16:39:19 - INFO - codeparrot_training - Step 43540: {'lr': 0.00040894674704804667, 'samples': 22292992, 'steps': 43540, 'loss/train': 1.8097847700119019}
-03/05/2022 16:39:23 - INFO - codeparrot_training - Step 43541: {'lr': 0.00040894265092432397, 'samples': 22293504, 'steps': 43541, 'loss/train': 2.2973973751068115}
-03/05/2022 16:39:23 - INFO - codeparrot_training - Skipping example with length 699 (seq_length=1024)
-03/05/2022 16:39:28 - INFO - codeparrot_training - Step 43542: {'lr': 0.0004089385547289841, 'samples': 22294016, 'steps': 43542, 'loss/train': 2.192369222640991}
-03/05/2022 16:39:31 - INFO - codeparrot_training - Step 43543: {'lr': 0.00040893445846202904, 'samples': 22294528, 'steps': 43543, 'loss/train': 1.159581184387207}
-03/05/2022 16:39:33 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/05/2022 16:39:37 - INFO - codeparrot_training - Step 43544: {'lr': 0.00040893036212346056, 'samples': 22295040, 'steps': 43544, 'loss/train': 1.4829267263412476}
-03/05/2022 16:39:40 - INFO - codeparrot_training - Step 43545: {'lr': 0.00040892626571328053, 'samples': 22295552, 'steps': 43545, 'loss/train': 1.7142601013183594}
-03/05/2022 16:39:41 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 16:39:45 - INFO - codeparrot_training - Step 43546: {'lr': 0.00040892216923149073, 'samples': 22296064, 'steps': 43546, 'loss/train': 2.046525716781616}
-03/05/2022 16:39:48 - INFO - codeparrot_training - Step 43547: {'lr': 0.000408918072678093, 'samples': 22296576, 'steps': 43547, 'loss/train': 0.4935801327228546}
-03/05/2022 16:39:49 - INFO - codeparrot_training - Skipping example with length 422 (seq_length=1024)
-03/05/2022 16:39:53 - INFO - codeparrot_training - Step 43548: {'lr': 0.0004089139760530893, 'samples': 22297088, 'steps': 43548, 'loss/train': 3.584404706954956}
-03/05/2022 16:39:57 - INFO - codeparrot_training - Step 43549: {'lr': 0.0004089098793564815, 'samples': 22297600, 'steps': 43549, 'loss/train': 2.512632369995117}
-03/05/2022 16:39:58 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/05/2022 16:40:02 - INFO - codeparrot_training - Step 43550: {'lr': 0.00040890578258827125, 'samples': 22298112, 'steps': 43550, 'loss/train': 0.07745035737752914}
-03/05/2022 16:40:05 - INFO - codeparrot_training - Step 43551: {'lr': 0.00040890168574846055, 'samples': 22298624, 'steps': 43551, 'loss/train': 1.2003059387207031}
-03/05/2022 16:40:06 - INFO - codeparrot_training - Skipping example with length 841 (seq_length=1024)
-03/05/2022 16:40:10 - INFO - codeparrot_training - Step 43552: {'lr': 0.0004088975888370512, 'samples': 22299136, 'steps': 43552, 'loss/train': 1.5562398433685303}
-03/05/2022 16:40:13 - INFO - codeparrot_training - Step 43553: {'lr': 0.00040889349185404503, 'samples': 22299648, 'steps': 43553, 'loss/train': 1.4919451475143433}
-03/05/2022 16:40:15 - INFO - codeparrot_training - Skipping example with length 248 (seq_length=1024)
-03/05/2022 16:40:19 - INFO - codeparrot_training - Step 43554: {'lr': 0.00040888939479944385, 'samples': 22300160, 'steps': 43554, 'loss/train': 1.7951635122299194}
-03/05/2022 16:40:22 - INFO - codeparrot_training - Step 43555: {'lr': 0.00040888529767324966, 'samples': 22300672, 'steps': 43555, 'loss/train': 2.021787643432617}
-03/05/2022 16:40:23 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/05/2022 16:40:27 - INFO - codeparrot_training - Step 43556: {'lr': 0.0004088812004754642, 'samples': 22301184, 'steps': 43556, 'loss/train': 2.0214481353759766}
-03/05/2022 16:40:30 - INFO - codeparrot_training - Step 43557: {'lr': 0.00040887710320608927, 'samples': 22301696, 'steps': 43557, 'loss/train': 1.9364957809448242}
-03/05/2022 16:40:31 - INFO - codeparrot_training - Skipping example with length 184 (seq_length=1024)
-03/05/2022 16:40:36 - INFO - codeparrot_training - Step 43558: {'lr': 0.00040887300586512677, 'samples': 22302208, 'steps': 43558, 'loss/train': 1.3532919883728027}
-03/05/2022 16:40:39 - INFO - codeparrot_training - Step 43559: {'lr': 0.0004088689084525786, 'samples': 22302720, 'steps': 43559, 'loss/train': 2.2497425079345703}
-03/05/2022 16:40:40 - INFO - codeparrot_training - Skipping example with length 678 (seq_length=1024)
-03/05/2022 16:40:44 - INFO - codeparrot_training - Step 43560: {'lr': 0.0004088648109684465, 'samples': 22303232, 'steps': 43560, 'loss/train': 1.405975580215454}
-03/05/2022 16:40:47 - INFO - codeparrot_training - Step 43561: {'lr': 0.00040886071341273236, 'samples': 22303744, 'steps': 43561, 'loss/train': 2.108630657196045}
-03/05/2022 16:40:48 - INFO - codeparrot_training - Skipping example with length 538 (seq_length=1024)
-03/05/2022 16:40:53 - INFO - codeparrot_training - Step 43562: {'lr': 0.0004088566157854381, 'samples': 22304256, 'steps': 43562, 'loss/train': 1.5644049644470215}
-03/05/2022 16:40:56 - INFO - codeparrot_training - Step 43563: {'lr': 0.0004088525180865654, 'samples': 22304768, 'steps': 43563, 'loss/train': 2.1927173137664795}
-03/05/2022 16:40:57 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 16:41:01 - INFO - codeparrot_training - Step 43564: {'lr': 0.0004088484203161163, 'samples': 22305280, 'steps': 43564, 'loss/train': 1.9716377258300781}
-03/05/2022 16:41:04 - INFO - codeparrot_training - Step 43565: {'lr': 0.0004088443224740925, 'samples': 22305792, 'steps': 43565, 'loss/train': 1.3490979671478271}
-03/05/2022 16:41:05 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/05/2022 16:41:10 - INFO - codeparrot_training - Step 43566: {'lr': 0.00040884022456049595, 'samples': 22306304, 'steps': 43566, 'loss/train': 1.9948389530181885}
-03/05/2022 16:41:13 - INFO - codeparrot_training - Step 43567: {'lr': 0.00040883612657532844, 'samples': 22306816, 'steps': 43567, 'loss/train': 3.5000038146972656}
-03/05/2022 16:41:15 - INFO - codeparrot_training - Skipping example with length 498 (seq_length=1024)
-03/05/2022 16:41:18 - INFO - codeparrot_training - Step 43568: {'lr': 0.0004088320285185918, 'samples': 22307328, 'steps': 43568, 'loss/train': 2.366649627685547}
-03/05/2022 16:41:21 - INFO - codeparrot_training - Step 43569: {'lr': 0.0004088279303902879, 'samples': 22307840, 'steps': 43569, 'loss/train': 1.967574954032898}
-03/05/2022 16:41:23 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/05/2022 16:41:27 - INFO - codeparrot_training - Step 43570: {'lr': 0.0004088238321904185, 'samples': 22308352, 'steps': 43570, 'loss/train': 2.1393465995788574}
-03/05/2022 16:41:30 - INFO - codeparrot_training - Step 43571: {'lr': 0.00040881973391898563, 'samples': 22308864, 'steps': 43571, 'loss/train': 1.1536953449249268}
-03/05/2022 16:41:31 - INFO - codeparrot_training - Skipping example with length 257 (seq_length=1024)
-03/05/2022 16:41:35 - INFO - codeparrot_training - Step 43572: {'lr': 0.00040881563557599107, 'samples': 22309376, 'steps': 43572, 'loss/train': 1.2718925476074219}
-03/05/2022 16:41:38 - INFO - codeparrot_training - Step 43573: {'lr': 0.00040881153716143656, 'samples': 22309888, 'steps': 43573, 'loss/train': 7.445451736450195}
-03/05/2022 16:41:40 - INFO - codeparrot_training - Skipping example with length 15 (seq_length=1024)
-03/05/2022 16:41:44 - INFO - codeparrot_training - Step 43574: {'lr': 0.000408807438675324, 'samples': 22310400, 'steps': 43574, 'loss/train': 1.5592296123504639}
-03/05/2022 16:41:47 - INFO - codeparrot_training - Step 43575: {'lr': 0.0004088033401176554, 'samples': 22310912, 'steps': 43575, 'loss/train': 2.3682451248168945}
-03/05/2022 16:41:49 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/05/2022 16:41:52 - INFO - codeparrot_training - Step 43576: {'lr': 0.00040879924148843233, 'samples': 22311424, 'steps': 43576, 'loss/train': 1.682289719581604}
-03/05/2022 16:41:55 - INFO - codeparrot_training - Step 43577: {'lr': 0.00040879514278765685, 'samples': 22311936, 'steps': 43577, 'loss/train': 1.4882627725601196}
-03/05/2022 16:41:57 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/05/2022 16:42:00 - INFO - codeparrot_training - Step 43578: {'lr': 0.00040879104401533064, 'samples': 22312448, 'steps': 43578, 'loss/train': 2.209794521331787}
-03/05/2022 16:42:04 - INFO - codeparrot_training - Step 43579: {'lr': 0.0004087869451714557, 'samples': 22312960, 'steps': 43579, 'loss/train': 1.7769020795822144}
-03/05/2022 16:42:05 - INFO - codeparrot_training - Skipping example with length 182 (seq_length=1024)
-03/05/2022 16:42:09 - INFO - codeparrot_training - Step 43580: {'lr': 0.0004087828462560338, 'samples': 22313472, 'steps': 43580, 'loss/train': 1.4512205123901367}
-03/05/2022 16:42:12 - INFO - codeparrot_training - Step 43581: {'lr': 0.0004087787472690668, 'samples': 22313984, 'steps': 43581, 'loss/train': 2.010418653488159}
-03/05/2022 16:42:14 - INFO - codeparrot_training - Skipping example with length 618 (seq_length=1024)
-03/05/2022 16:42:17 - INFO - codeparrot_training - Step 43582: {'lr': 0.00040877464821055656, 'samples': 22314496, 'steps': 43582, 'loss/train': 1.9044525623321533}
-03/05/2022 16:42:21 - INFO - codeparrot_training - Step 43583: {'lr': 0.00040877054908050495, 'samples': 22315008, 'steps': 43583, 'loss/train': 1.9305002689361572}
-03/05/2022 16:42:22 - INFO - codeparrot_training - Skipping example with length 819 (seq_length=1024)
-03/05/2022 16:42:26 - INFO - codeparrot_training - Step 43584: {'lr': 0.0004087664498789137, 'samples': 22315520, 'steps': 43584, 'loss/train': 1.8394944667816162}
-03/05/2022 16:42:29 - INFO - codeparrot_training - Step 43585: {'lr': 0.00040876235060578476, 'samples': 22316032, 'steps': 43585, 'loss/train': 0.9854817986488342}
-03/05/2022 16:42:31 - INFO - codeparrot_training - Skipping example with length 277 (seq_length=1024)
-03/05/2022 16:42:34 - INFO - codeparrot_training - Step 43586: {'lr': 0.00040875825126112, 'samples': 22316544, 'steps': 43586, 'loss/train': 1.82539701461792}
-03/05/2022 16:42:37 - INFO - codeparrot_training - Step 43587: {'lr': 0.00040875415184492113, 'samples': 22317056, 'steps': 43587, 'loss/train': 2.220182180404663}
-03/05/2022 16:42:39 - INFO - codeparrot_training - Skipping example with length 323 (seq_length=1024)
-03/05/2022 16:42:43 - INFO - codeparrot_training - Step 43588: {'lr': 0.0004087500523571902, 'samples': 22317568, 'steps': 43588, 'loss/train': 1.7767337560653687}
-03/05/2022 16:42:46 - INFO - codeparrot_training - Step 43589: {'lr': 0.00040874595279792884, 'samples': 22318080, 'steps': 43589, 'loss/train': 2.4290528297424316}
-03/05/2022 16:42:48 - INFO - codeparrot_training - Skipping example with length 766 (seq_length=1024)
-03/05/2022 16:42:51 - INFO - codeparrot_training - Step 43590: {'lr': 0.00040874185316713905, 'samples': 22318592, 'steps': 43590, 'loss/train': 1.5387769937515259}
-03/05/2022 16:42:54 - INFO - codeparrot_training - Step 43591: {'lr': 0.00040873775346482265, 'samples': 22319104, 'steps': 43591, 'loss/train': 1.6900389194488525}
-03/05/2022 16:42:56 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/05/2022 16:43:00 - INFO - codeparrot_training - Step 43592: {'lr': 0.0004087336536909815, 'samples': 22319616, 'steps': 43592, 'loss/train': 1.2524985074996948}
-03/05/2022 16:43:03 - INFO - codeparrot_training - Step 43593: {'lr': 0.00040872955384561735, 'samples': 22320128, 'steps': 43593, 'loss/train': 1.3358381986618042}
-03/05/2022 16:43:05 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/05/2022 16:43:08 - INFO - codeparrot_training - Step 43594: {'lr': 0.00040872545392873214, 'samples': 22320640, 'steps': 43594, 'loss/train': 2.3314616680145264}
-03/05/2022 16:43:11 - INFO - codeparrot_training - Step 43595: {'lr': 0.00040872135394032764, 'samples': 22321152, 'steps': 43595, 'loss/train': 1.562785267829895}
-03/05/2022 16:43:14 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/05/2022 16:43:17 - INFO - codeparrot_training - Step 43596: {'lr': 0.0004087172538804058, 'samples': 22321664, 'steps': 43596, 'loss/train': 1.869885802268982}
-03/05/2022 16:43:20 - INFO - codeparrot_training - Step 43597: {'lr': 0.0004087131537489685, 'samples': 22322176, 'steps': 43597, 'loss/train': 1.979675531387329}
-03/05/2022 16:43:22 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/05/2022 16:43:25 - INFO - codeparrot_training - Step 43598: {'lr': 0.00040870905354601733, 'samples': 22322688, 'steps': 43598, 'loss/train': 1.2901482582092285}
-03/05/2022 16:43:28 - INFO - codeparrot_training - Step 43599: {'lr': 0.0004087049532715544, 'samples': 22323200, 'steps': 43599, 'loss/train': 2.2488045692443848}
-03/05/2022 16:43:31 - INFO - codeparrot_training - Skipping example with length 379 (seq_length=1024)
-03/05/2022 16:43:34 - INFO - codeparrot_training - Step 43600: {'lr': 0.00040870085292558147, 'samples': 22323712, 'steps': 43600, 'loss/train': 1.8258154392242432}
-03/05/2022 16:43:37 - INFO - codeparrot_training - Step 43601: {'lr': 0.0004086967525081003, 'samples': 22324224, 'steps': 43601, 'loss/train': 1.9085488319396973}
-03/05/2022 16:43:39 - INFO - codeparrot_training - Skipping example with length 192 (seq_length=1024)
-03/05/2022 16:43:42 - INFO - codeparrot_training - Step 43602: {'lr': 0.00040869265201911285, 'samples': 22324736, 'steps': 43602, 'loss/train': 1.9763127565383911}
-03/05/2022 16:43:45 - INFO - codeparrot_training - Step 43603: {'lr': 0.00040868855145862105, 'samples': 22325248, 'steps': 43603, 'loss/train': 0.7025713920593262}
-03/05/2022 16:43:47 - INFO - codeparrot_training - Skipping example with length 693 (seq_length=1024)
-03/05/2022 16:43:50 - INFO - codeparrot_training - Step 43604: {'lr': 0.00040868445082662655, 'samples': 22325760, 'steps': 43604, 'loss/train': 1.475812554359436}
-03/05/2022 16:43:54 - INFO - codeparrot_training - Step 43605: {'lr': 0.0004086803501231313, 'samples': 22326272, 'steps': 43605, 'loss/train': 1.27096426486969}
-03/05/2022 16:43:56 - INFO - codeparrot_training - Skipping example with length 317 (seq_length=1024)
-03/05/2022 16:43:59 - INFO - codeparrot_training - Step 43606: {'lr': 0.00040867624934813715, 'samples': 22326784, 'steps': 43606, 'loss/train': 1.0256454944610596}
-03/05/2022 16:44:02 - INFO - codeparrot_training - Step 43607: {'lr': 0.00040867214850164594, 'samples': 22327296, 'steps': 43607, 'loss/train': 1.0828173160552979}
-03/05/2022 16:44:05 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/05/2022 16:44:07 - INFO - codeparrot_training - Step 43608: {'lr': 0.0004086680475836594, 'samples': 22327808, 'steps': 43608, 'loss/train': 1.5296202898025513}
-03/05/2022 16:44:11 - INFO - codeparrot_training - Step 43609: {'lr': 0.0004086639465941796, 'samples': 22328320, 'steps': 43609, 'loss/train': 2.0186009407043457}
-03/05/2022 16:44:13 - INFO - codeparrot_training - Skipping example with length 748 (seq_length=1024)
-03/05/2022 16:44:16 - INFO - codeparrot_training - Step 43610: {'lr': 0.00040865984553320825, 'samples': 22328832, 'steps': 43610, 'loss/train': 2.0901713371276855}
-03/05/2022 16:44:19 - INFO - codeparrot_training - Step 43611: {'lr': 0.0004086557444007472, 'samples': 22329344, 'steps': 43611, 'loss/train': 0.8491621017456055}
-03/05/2022 16:44:21 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/05/2022 16:44:24 - INFO - codeparrot_training - Step 43612: {'lr': 0.0004086516431967984, 'samples': 22329856, 'steps': 43612, 'loss/train': 1.3803293704986572}
-03/05/2022 16:44:27 - INFO - codeparrot_training - Step 43613: {'lr': 0.0004086475419213635, 'samples': 22330368, 'steps': 43613, 'loss/train': 2.8201427459716797}
-03/05/2022 16:44:29 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/05/2022 16:44:33 - INFO - codeparrot_training - Step 43614: {'lr': 0.0004086434405744445, 'samples': 22330880, 'steps': 43614, 'loss/train': 1.27468740940094}
-03/05/2022 16:44:36 - INFO - codeparrot_training - Step 43615: {'lr': 0.00040863933915604323, 'samples': 22331392, 'steps': 43615, 'loss/train': 1.8225866556167603}
-03/05/2022 16:44:39 - INFO - codeparrot_training - Step 43616: {'lr': 0.00040863523766616157, 'samples': 22331904, 'steps': 43616, 'loss/train': 2.0748023986816406}
-03/05/2022 16:44:40 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 16:44:45 - INFO - codeparrot_training - Step 43617: {'lr': 0.0004086311361048012, 'samples': 22332416, 'steps': 43617, 'loss/train': 2.3647472858428955}
-03/05/2022 16:44:48 - INFO - codeparrot_training - Step 43618: {'lr': 0.0004086270344719642, 'samples': 22332928, 'steps': 43618, 'loss/train': 1.3587702512741089}
-03/05/2022 16:44:48 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/05/2022 16:44:53 - INFO - codeparrot_training - Step 43619: {'lr': 0.00040862293276765227, 'samples': 22333440, 'steps': 43619, 'loss/train': 1.7732042074203491}
-03/05/2022 16:44:56 - INFO - codeparrot_training - Step 43620: {'lr': 0.00040861883099186725, 'samples': 22333952, 'steps': 43620, 'loss/train': 1.735103964805603}
-03/05/2022 16:44:57 - INFO - codeparrot_training - Skipping example with length 142 (seq_length=1024)
-03/05/2022 16:45:02 - INFO - codeparrot_training - Step 43621: {'lr': 0.0004086147291446111, 'samples': 22334464, 'steps': 43621, 'loss/train': 2.0094165802001953}
-03/05/2022 16:45:05 - INFO - codeparrot_training - Step 43622: {'lr': 0.0004086106272258856, 'samples': 22334976, 'steps': 43622, 'loss/train': 1.8635659217834473}
-03/05/2022 16:45:05 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/05/2022 16:45:10 - INFO - codeparrot_training - Step 43623: {'lr': 0.0004086065252356925, 'samples': 22335488, 'steps': 43623, 'loss/train': 1.9533724784851074}
-03/05/2022 16:45:13 - INFO - codeparrot_training - Step 43624: {'lr': 0.00040860242317403383, 'samples': 22336000, 'steps': 43624, 'loss/train': 1.4665549993515015}
-03/05/2022 16:45:13 - INFO - codeparrot_training - Skipping example with length 351 (seq_length=1024)
-03/05/2022 16:45:18 - INFO - codeparrot_training - Step 43625: {'lr': 0.0004085983210409114, 'samples': 22336512, 'steps': 43625, 'loss/train': 2.1034657955169678}
-03/05/2022 16:45:22 - INFO - codeparrot_training - Step 43626: {'lr': 0.00040859421883632696, 'samples': 22337024, 'steps': 43626, 'loss/train': 2.37176775932312}
-03/05/2022 16:45:22 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/05/2022 16:45:27 - INFO - codeparrot_training - Step 43627: {'lr': 0.0004085901165602824, 'samples': 22337536, 'steps': 43627, 'loss/train': 0.41075319051742554}
-03/05/2022 16:45:30 - INFO - codeparrot_training - Step 43628: {'lr': 0.00040858601421277956, 'samples': 22338048, 'steps': 43628, 'loss/train': 1.1877251863479614}
-03/05/2022 16:45:31 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/05/2022 16:45:35 - INFO - codeparrot_training - Step 43629: {'lr': 0.00040858191179382044, 'samples': 22338560, 'steps': 43629, 'loss/train': 2.111377239227295}
-03/05/2022 16:45:39 - INFO - codeparrot_training - Step 43630: {'lr': 0.0004085778093034066, 'samples': 22339072, 'steps': 43630, 'loss/train': 2.2425715923309326}
-03/05/2022 16:45:39 - INFO - codeparrot_training - Skipping example with length 685 (seq_length=1024)
-03/05/2022 16:45:44 - INFO - codeparrot_training - Step 43631: {'lr': 0.0004085737067415401, 'samples': 22339584, 'steps': 43631, 'loss/train': 2.2668380737304688}
-03/05/2022 16:45:47 - INFO - codeparrot_training - Step 43632: {'lr': 0.00040856960410822277, 'samples': 22340096, 'steps': 43632, 'loss/train': 1.8864325284957886}
-03/05/2022 16:45:49 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 16:45:53 - INFO - codeparrot_training - Step 43633: {'lr': 0.0004085655014034564, 'samples': 22340608, 'steps': 43633, 'loss/train': 1.4593383073806763}
-03/05/2022 16:45:56 - INFO - codeparrot_training - Step 43634: {'lr': 0.0004085613986272428, 'samples': 22341120, 'steps': 43634, 'loss/train': 1.6532355546951294}
-03/05/2022 16:45:57 - INFO - codeparrot_training - Skipping example with length 355 (seq_length=1024)
-03/05/2022 16:46:01 - INFO - codeparrot_training - Step 43635: {'lr': 0.0004085572957795839, 'samples': 22341632, 'steps': 43635, 'loss/train': 0.9712749123573303}
-03/05/2022 16:46:05 - INFO - codeparrot_training - Step 43636: {'lr': 0.00040855319286048163, 'samples': 22342144, 'steps': 43636, 'loss/train': 1.8798185586929321}
-03/05/2022 16:46:06 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/05/2022 16:46:10 - INFO - codeparrot_training - Step 43637: {'lr': 0.0004085490898699377, 'samples': 22342656, 'steps': 43637, 'loss/train': 1.976017713546753}
-03/05/2022 16:46:13 - INFO - codeparrot_training - Step 43638: {'lr': 0.0004085449868079539, 'samples': 22343168, 'steps': 43638, 'loss/train': 0.8378556966781616}
-03/05/2022 16:46:14 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/05/2022 16:46:19 - INFO - codeparrot_training - Step 43639: {'lr': 0.00040854088367453225, 'samples': 22343680, 'steps': 43639, 'loss/train': 1.745743751525879}
-03/05/2022 16:46:22 - INFO - codeparrot_training - Step 43640: {'lr': 0.00040853678046967454, 'samples': 22344192, 'steps': 43640, 'loss/train': 1.9121558666229248}
-03/05/2022 16:46:22 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/05/2022 16:46:27 - INFO - codeparrot_training - Step 43641: {'lr': 0.00040853267719338256, 'samples': 22344704, 'steps': 43641, 'loss/train': 1.4722404479980469}
-03/05/2022 16:46:30 - INFO - codeparrot_training - Step 43642: {'lr': 0.00040852857384565824, 'samples': 22345216, 'steps': 43642, 'loss/train': 1.7225645780563354}
-03/05/2022 16:46:31 - INFO - codeparrot_training - Skipping example with length 836 (seq_length=1024)
-03/05/2022 16:46:36 - INFO - codeparrot_training - Step 43643: {'lr': 0.00040852447042650337, 'samples': 22345728, 'steps': 43643, 'loss/train': 0.6063699126243591}
-03/05/2022 16:46:39 - INFO - codeparrot_training - Step 43644: {'lr': 0.0004085203669359198, 'samples': 22346240, 'steps': 43644, 'loss/train': 1.1045125722885132}
-03/05/2022 16:46:40 - INFO - codeparrot_training - Skipping example with length 356 (seq_length=1024)
-03/05/2022 16:46:44 - INFO - codeparrot_training - Step 43645: {'lr': 0.0004085162633739095, 'samples': 22346752, 'steps': 43645, 'loss/train': 1.9208160638809204}
-03/05/2022 16:46:47 - INFO - codeparrot_training - Step 43646: {'lr': 0.0004085121597404741, 'samples': 22347264, 'steps': 43646, 'loss/train': 2.7570877075195312}
-03/05/2022 16:46:48 - INFO - codeparrot_training - Skipping example with length 721 (seq_length=1024)
-03/05/2022 16:46:53 - INFO - codeparrot_training - Step 43647: {'lr': 0.0004085080560356156, 'samples': 22347776, 'steps': 43647, 'loss/train': 1.6683223247528076}
-03/05/2022 16:46:56 - INFO - codeparrot_training - Step 43648: {'lr': 0.0004085039522593358, 'samples': 22348288, 'steps': 43648, 'loss/train': 1.5714131593704224}
-03/05/2022 16:46:57 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/05/2022 16:47:01 - INFO - codeparrot_training - Step 43649: {'lr': 0.0004084998484116366, 'samples': 22348800, 'steps': 43649, 'loss/train': 1.1651099920272827}
-03/05/2022 16:47:04 - INFO - codeparrot_training - Step 43650: {'lr': 0.0004084957444925198, 'samples': 22349312, 'steps': 43650, 'loss/train': 1.1158400774002075}
-03/05/2022 16:47:06 - INFO - codeparrot_training - Skipping example with length 516 (seq_length=1024)
-03/05/2022 16:47:10 - INFO - codeparrot_training - Step 43651: {'lr': 0.0004084916405019873, 'samples': 22349824, 'steps': 43651, 'loss/train': 1.0685019493103027}
-03/05/2022 16:47:13 - INFO - codeparrot_training - Step 43652: {'lr': 0.0004084875364400409, 'samples': 22350336, 'steps': 43652, 'loss/train': 1.8802387714385986}
-03/05/2022 16:47:14 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/05/2022 16:47:18 - INFO - codeparrot_training - Step 43653: {'lr': 0.0004084834323066824, 'samples': 22350848, 'steps': 43653, 'loss/train': 1.3390833139419556}
-03/05/2022 16:47:21 - INFO - codeparrot_training - Step 43654: {'lr': 0.00040847932810191375, 'samples': 22351360, 'steps': 43654, 'loss/train': 1.6255507469177246}
-03/05/2022 16:47:23 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/05/2022 16:47:26 - INFO - codeparrot_training - Step 43655: {'lr': 0.00040847522382573675, 'samples': 22351872, 'steps': 43655, 'loss/train': 0.9801068305969238}
-03/05/2022 16:47:30 - INFO - codeparrot_training - Step 43656: {'lr': 0.0004084711194781533, 'samples': 22352384, 'steps': 43656, 'loss/train': 2.205024003982544}
-03/05/2022 16:47:31 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/05/2022 16:47:35 - INFO - codeparrot_training - Step 43657: {'lr': 0.00040846701505916516, 'samples': 22352896, 'steps': 43657, 'loss/train': 1.8518301248550415}
-03/05/2022 16:47:38 - INFO - codeparrot_training - Step 43658: {'lr': 0.00040846291056877425, 'samples': 22353408, 'steps': 43658, 'loss/train': 1.3448373079299927}
-03/05/2022 16:47:39 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 16:47:43 - INFO - codeparrot_training - Step 43659: {'lr': 0.0004084588060069824, 'samples': 22353920, 'steps': 43659, 'loss/train': 1.3093796968460083}
-03/05/2022 16:47:46 - INFO - codeparrot_training - Step 43660: {'lr': 0.0004084547013737915, 'samples': 22354432, 'steps': 43660, 'loss/train': 1.4651625156402588}
-03/05/2022 16:47:48 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 16:47:52 - INFO - codeparrot_training - Step 43661: {'lr': 0.00040845059666920323, 'samples': 22354944, 'steps': 43661, 'loss/train': 1.9470903873443604}
-03/05/2022 16:47:55 - INFO - codeparrot_training - Step 43662: {'lr': 0.0004084464918932197, 'samples': 22355456, 'steps': 43662, 'loss/train': 1.0761038064956665}
-03/05/2022 16:47:56 - INFO - codeparrot_training - Skipping example with length 321 (seq_length=1024)
-03/05/2022 16:48:01 - INFO - codeparrot_training - Step 43663: {'lr': 0.0004084423870458426, 'samples': 22355968, 'steps': 43663, 'loss/train': 6.507169723510742}
-03/05/2022 16:48:04 - INFO - codeparrot_training - Step 43664: {'lr': 0.00040843828212707366, 'samples': 22356480, 'steps': 43664, 'loss/train': 2.264404296875}
-03/05/2022 16:48:05 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 16:48:09 - INFO - codeparrot_training - Step 43665: {'lr': 0.00040843417713691505, 'samples': 22356992, 'steps': 43665, 'loss/train': 1.8914523124694824}
-03/05/2022 16:48:12 - INFO - codeparrot_training - Step 43666: {'lr': 0.0004084300720753684, 'samples': 22357504, 'steps': 43666, 'loss/train': 1.4085049629211426}
-03/05/2022 16:48:14 - INFO - codeparrot_training - Skipping example with length 565 (seq_length=1024)
-03/05/2022 16:48:17 - INFO - codeparrot_training - Step 43667: {'lr': 0.0004084259669424356, 'samples': 22358016, 'steps': 43667, 'loss/train': 1.1709370613098145}
-03/05/2022 16:48:21 - INFO - codeparrot_training - Step 43668: {'lr': 0.0004084218617381185, 'samples': 22358528, 'steps': 43668, 'loss/train': 1.9813975095748901}
-03/05/2022 16:48:23 - INFO - codeparrot_training - Skipping example with length 282 (seq_length=1024)
-03/05/2022 16:48:26 - INFO - codeparrot_training - Step 43669: {'lr': 0.00040841775646241897, 'samples': 22359040, 'steps': 43669, 'loss/train': 1.8351049423217773}
-03/05/2022 16:48:29 - INFO - codeparrot_training - Step 43670: {'lr': 0.0004084136511153388, 'samples': 22359552, 'steps': 43670, 'loss/train': 1.079126238822937}
-03/05/2022 16:48:31 - INFO - codeparrot_training - Skipping example with length 27 (seq_length=1024)
-03/05/2022 16:48:34 - INFO - codeparrot_training - Step 43671: {'lr': 0.00040840954569687987, 'samples': 22360064, 'steps': 43671, 'loss/train': 1.3537046909332275}
-03/05/2022 16:48:38 - INFO - codeparrot_training - Step 43672: {'lr': 0.0004084054402070441, 'samples': 22360576, 'steps': 43672, 'loss/train': 1.565490484237671}
-03/05/2022 16:48:39 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/05/2022 16:48:43 - INFO - codeparrot_training - Step 43673: {'lr': 0.0004084013346458333, 'samples': 22361088, 'steps': 43673, 'loss/train': 1.4023786783218384}
-03/05/2022 16:48:46 - INFO - codeparrot_training - Step 43674: {'lr': 0.00040839722901324924, 'samples': 22361600, 'steps': 43674, 'loss/train': 1.7986925840377808}
-03/05/2022 16:48:48 - INFO - codeparrot_training - Skipping example with length 374 (seq_length=1024)
-03/05/2022 16:48:51 - INFO - codeparrot_training - Step 43675: {'lr': 0.00040839312330929377, 'samples': 22362112, 'steps': 43675, 'loss/train': 1.3742527961730957}
-03/05/2022 16:48:54 - INFO - codeparrot_training - Step 43676: {'lr': 0.00040838901753396896, 'samples': 22362624, 'steps': 43676, 'loss/train': 1.335737705230713}
-03/05/2022 16:48:56 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 16:49:00 - INFO - codeparrot_training - Step 43677: {'lr': 0.0004083849116872764, 'samples': 22363136, 'steps': 43677, 'loss/train': 1.172147512435913}
-03/05/2022 16:49:03 - INFO - codeparrot_training - Step 43678: {'lr': 0.0004083808057692181, 'samples': 22363648, 'steps': 43678, 'loss/train': 1.688503623008728}
-03/05/2022 16:49:05 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/05/2022 16:49:08 - INFO - codeparrot_training - Step 43679: {'lr': 0.00040837669977979586, 'samples': 22364160, 'steps': 43679, 'loss/train': 2.137653112411499}
-03/05/2022 16:49:11 - INFO - codeparrot_training - Step 43680: {'lr': 0.00040837259371901145, 'samples': 22364672, 'steps': 43680, 'loss/train': 1.1138176918029785}
-03/05/2022 16:49:14 - INFO - codeparrot_training - Skipping example with length 944 (seq_length=1024)
-03/05/2022 16:49:17 - INFO - codeparrot_training - Step 43681: {'lr': 0.00040836848758686687, 'samples': 22365184, 'steps': 43681, 'loss/train': 1.9679498672485352}
-03/05/2022 16:49:20 - INFO - codeparrot_training - Step 43682: {'lr': 0.00040836438138336384, 'samples': 22365696, 'steps': 43682, 'loss/train': 1.266290545463562}
-03/05/2022 16:49:22 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/05/2022 16:49:25 - INFO - codeparrot_training - Step 43683: {'lr': 0.00040836027510850426, 'samples': 22366208, 'steps': 43683, 'loss/train': 1.095920205116272}
-03/05/2022 16:49:28 - INFO - codeparrot_training - Step 43684: {'lr': 0.00040835616876229, 'samples': 22366720, 'steps': 43684, 'loss/train': 0.9919460415840149}
-03/05/2022 16:49:31 - INFO - codeparrot_training - Skipping example with length 640 (seq_length=1024)
-03/05/2022 16:49:34 - INFO - codeparrot_training - Step 43685: {'lr': 0.00040835206234472287, 'samples': 22367232, 'steps': 43685, 'loss/train': 1.6624979972839355}
-03/05/2022 16:49:37 - INFO - codeparrot_training - Step 43686: {'lr': 0.0004083479558558048, 'samples': 22367744, 'steps': 43686, 'loss/train': 1.819217562675476}
-03/05/2022 16:49:39 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/05/2022 16:49:42 - INFO - codeparrot_training - Step 43687: {'lr': 0.0004083438492955376, 'samples': 22368256, 'steps': 43687, 'loss/train': 1.4410797357559204}
-03/05/2022 16:49:45 - INFO - codeparrot_training - Step 43688: {'lr': 0.00040833974266392306, 'samples': 22368768, 'steps': 43688, 'loss/train': 1.7796001434326172}
-03/05/2022 16:49:48 - INFO - codeparrot_training - Skipping example with length 844 (seq_length=1024)
-03/05/2022 16:49:51 - INFO - codeparrot_training - Step 43689: {'lr': 0.00040833563596096305, 'samples': 22369280, 'steps': 43689, 'loss/train': 1.548547625541687}
-03/05/2022 16:49:54 - INFO - codeparrot_training - Step 43690: {'lr': 0.0004083315291866595, 'samples': 22369792, 'steps': 43690, 'loss/train': 0.8119476437568665}
-03/05/2022 16:49:56 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 16:49:59 - INFO - codeparrot_training - Step 43691: {'lr': 0.00040832742234101415, 'samples': 22370304, 'steps': 43691, 'loss/train': 1.9347418546676636}
-03/05/2022 16:50:02 - INFO - codeparrot_training - Step 43692: {'lr': 0.00040832331542402895, 'samples': 22370816, 'steps': 43692, 'loss/train': 1.5216619968414307}
-03/05/2022 16:50:05 - INFO - codeparrot_training - Skipping example with length 850 (seq_length=1024)
-03/05/2022 16:50:08 - INFO - codeparrot_training - Step 43693: {'lr': 0.0004083192084357057, 'samples': 22371328, 'steps': 43693, 'loss/train': 1.1230177879333496}
-03/05/2022 16:50:11 - INFO - codeparrot_training - Step 43694: {'lr': 0.0004083151013760462, 'samples': 22371840, 'steps': 43694, 'loss/train': 1.637165904045105}
-03/05/2022 16:50:13 - INFO - codeparrot_training - Skipping example with length 238 (seq_length=1024)
-03/05/2022 16:50:16 - INFO - codeparrot_training - Step 43695: {'lr': 0.0004083109942450524, 'samples': 22372352, 'steps': 43695, 'loss/train': 1.572172999382019}
-03/05/2022 16:50:19 - INFO - codeparrot_training - Step 43696: {'lr': 0.00040830688704272615, 'samples': 22372864, 'steps': 43696, 'loss/train': 2.208292007446289}
-03/05/2022 16:50:21 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/05/2022 16:50:25 - INFO - codeparrot_training - Step 43697: {'lr': 0.0004083027797690693, 'samples': 22373376, 'steps': 43697, 'loss/train': 1.4846382141113281}
-03/05/2022 16:50:28 - INFO - codeparrot_training - Step 43698: {'lr': 0.0004082986724240835, 'samples': 22373888, 'steps': 43698, 'loss/train': 1.4512183666229248}
-03/05/2022 16:50:30 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 16:50:33 - INFO - codeparrot_training - Step 43699: {'lr': 0.00040829456500777084, 'samples': 22374400, 'steps': 43699, 'loss/train': 2.3024072647094727}
-03/05/2022 16:50:36 - INFO - codeparrot_training - Step 43700: {'lr': 0.00040829045752013317, 'samples': 22374912, 'steps': 43700, 'loss/train': 1.728979468345642}
-03/05/2022 16:50:39 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/05/2022 16:50:42 - INFO - codeparrot_training - Step 43701: {'lr': 0.00040828634996117213, 'samples': 22375424, 'steps': 43701, 'loss/train': 1.0800122022628784}
-03/05/2022 16:50:45 - INFO - codeparrot_training - Step 43702: {'lr': 0.0004082822423308897, 'samples': 22375936, 'steps': 43702, 'loss/train': 1.7643481492996216}
-03/05/2022 16:50:47 - INFO - codeparrot_training - Skipping example with length 887 (seq_length=1024)
-03/05/2022 16:50:50 - INFO - codeparrot_training - Step 43703: {'lr': 0.00040827813462928784, 'samples': 22376448, 'steps': 43703, 'loss/train': 1.5963966846466064}
-03/05/2022 16:50:53 - INFO - codeparrot_training - Step 43704: {'lr': 0.0004082740268563683, 'samples': 22376960, 'steps': 43704, 'loss/train': 1.8335922956466675}
-03/05/2022 16:50:56 - INFO - codeparrot_training - Skipping example with length 96 (seq_length=1024)
-03/05/2022 16:50:58 - INFO - codeparrot_training - Step 43705: {'lr': 0.0004082699190121329, 'samples': 22377472, 'steps': 43705, 'loss/train': 1.871158242225647}
-03/05/2022 16:51:02 - INFO - codeparrot_training - Step 43706: {'lr': 0.00040826581109658345, 'samples': 22377984, 'steps': 43706, 'loss/train': 1.2035809755325317}
-03/05/2022 16:51:04 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/05/2022 16:51:07 - INFO - codeparrot_training - Step 43707: {'lr': 0.00040826170310972196, 'samples': 22378496, 'steps': 43707, 'loss/train': 1.8745824098587036}
-03/05/2022 16:51:10 - INFO - codeparrot_training - Step 43708: {'lr': 0.0004082575950515501, 'samples': 22379008, 'steps': 43708, 'loss/train': 2.0608975887298584}
-03/05/2022 16:51:12 - INFO - codeparrot_training - Skipping example with length 632 (seq_length=1024)
-03/05/2022 16:51:15 - INFO - codeparrot_training - Step 43709: {'lr': 0.00040825348692206985, 'samples': 22379520, 'steps': 43709, 'loss/train': 2.143752098083496}
-03/05/2022 16:51:19 - INFO - codeparrot_training - Step 43710: {'lr': 0.0004082493787212831, 'samples': 22380032, 'steps': 43710, 'loss/train': 1.1901994943618774}
-03/05/2022 16:51:21 - INFO - codeparrot_training - Skipping example with length 942 (seq_length=1024)
-03/05/2022 16:51:24 - INFO - codeparrot_training - Step 43711: {'lr': 0.00040824527044919153, 'samples': 22380544, 'steps': 43711, 'loss/train': 1.492495059967041}
-03/05/2022 16:51:27 - INFO - codeparrot_training - Step 43712: {'lr': 0.0004082411621057971, 'samples': 22381056, 'steps': 43712, 'loss/train': 1.803471565246582}
-03/05/2022 16:51:30 - INFO - codeparrot_training - Skipping example with length 638 (seq_length=1024)
-03/05/2022 16:51:32 - INFO - codeparrot_training - Step 43713: {'lr': 0.00040823705369110163, 'samples': 22381568, 'steps': 43713, 'loss/train': 0.9945499300956726}
-03/05/2022 16:51:35 - INFO - codeparrot_training - Step 43714: {'lr': 0.000408232945205107, 'samples': 22382080, 'steps': 43714, 'loss/train': 0.09742530435323715}
-03/05/2022 16:51:38 - INFO - codeparrot_training - Skipping example with length 974 (seq_length=1024)
-03/05/2022 16:51:41 - INFO - codeparrot_training - Step 43715: {'lr': 0.00040822883664781506, 'samples': 22382592, 'steps': 43715, 'loss/train': 1.8790180683135986}
-03/05/2022 16:51:44 - INFO - codeparrot_training - Step 43716: {'lr': 0.0004082247280192276, 'samples': 22383104, 'steps': 43716, 'loss/train': 1.2757371664047241}
-03/05/2022 16:51:47 - INFO - codeparrot_training - Step 43717: {'lr': 0.00040822061931934656, 'samples': 22383616, 'steps': 43717, 'loss/train': 2.048994302749634}
-03/05/2022 16:51:47 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/05/2022 16:51:52 - INFO - codeparrot_training - Step 43718: {'lr': 0.00040821651054817376, 'samples': 22384128, 'steps': 43718, 'loss/train': 0.6961318850517273}
-03/05/2022 16:51:56 - INFO - codeparrot_training - Step 43719: {'lr': 0.000408212401705711, 'samples': 22384640, 'steps': 43719, 'loss/train': 1.4624629020690918}
-03/05/2022 16:51:56 - INFO - codeparrot_training - Skipping example with length 710 (seq_length=1024)
-03/05/2022 16:52:01 - INFO - codeparrot_training - Step 43720: {'lr': 0.0004082082927919602, 'samples': 22385152, 'steps': 43720, 'loss/train': 1.5730066299438477}
-03/05/2022 16:52:04 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/05/2022 16:52:06 - INFO - codeparrot_training - Step 43721: {'lr': 0.0004082041838069232, 'samples': 22385664, 'steps': 43721, 'loss/train': 1.944197177886963}
-03/05/2022 16:52:09 - INFO - codeparrot_training - Step 43722: {'lr': 0.0004082000747506018, 'samples': 22386176, 'steps': 43722, 'loss/train': 1.5476070642471313}
-03/05/2022 16:52:12 - INFO - codeparrot_training - Skipping example with length 614 (seq_length=1024)
-03/05/2022 16:52:15 - INFO - codeparrot_training - Step 43723: {'lr': 0.00040819596562299793, 'samples': 22386688, 'steps': 43723, 'loss/train': 0.8925703763961792}
-03/05/2022 16:52:18 - INFO - codeparrot_training - Step 43724: {'lr': 0.0004081918564241134, 'samples': 22387200, 'steps': 43724, 'loss/train': 2.050227403640747}
-03/05/2022 16:52:21 - INFO - codeparrot_training - Step 43725: {'lr': 0.00040818774715395, 'samples': 22387712, 'steps': 43725, 'loss/train': 1.4173418283462524}
-03/05/2022 16:52:23 - INFO - codeparrot_training - Skipping example with length 19 (seq_length=1024)
-03/05/2022 16:52:27 - INFO - codeparrot_training - Step 43726: {'lr': 0.0004081836378125097, 'samples': 22388224, 'steps': 43726, 'loss/train': 1.8735824823379517}
-03/05/2022 16:52:30 - INFO - codeparrot_training - Step 43727: {'lr': 0.00040817952839979424, 'samples': 22388736, 'steps': 43727, 'loss/train': 1.3684109449386597}
-03/05/2022 16:52:32 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/05/2022 16:52:35 - INFO - codeparrot_training - Step 43728: {'lr': 0.00040817541891580557, 'samples': 22389248, 'steps': 43728, 'loss/train': 1.1134504079818726}
-03/05/2022 16:52:38 - INFO - codeparrot_training - Step 43729: {'lr': 0.00040817130936054546, 'samples': 22389760, 'steps': 43729, 'loss/train': 2.4697091579437256}
-03/05/2022 16:52:40 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/05/2022 16:52:44 - INFO - codeparrot_training - Step 43730: {'lr': 0.00040816719973401586, 'samples': 22390272, 'steps': 43730, 'loss/train': 1.5405408143997192}
-03/05/2022 16:52:47 - INFO - codeparrot_training - Step 43731: {'lr': 0.0004081630900362185, 'samples': 22390784, 'steps': 43731, 'loss/train': 1.9429545402526855}
-03/05/2022 16:52:49 - INFO - codeparrot_training - Skipping example with length 931 (seq_length=1024)
-03/05/2022 16:52:52 - INFO - codeparrot_training - Step 43732: {'lr': 0.0004081589802671553, 'samples': 22391296, 'steps': 43732, 'loss/train': 1.8159990310668945}
-03/05/2022 16:52:55 - INFO - codeparrot_training - Step 43733: {'lr': 0.00040815487042682814, 'samples': 22391808, 'steps': 43733, 'loss/train': 1.5074989795684814}
-03/05/2022 16:52:57 - INFO - codeparrot_training - Skipping example with length 935 (seq_length=1024)
-03/05/2022 16:53:00 - INFO - codeparrot_training - Step 43734: {'lr': 0.0004081507605152388, 'samples': 22392320, 'steps': 43734, 'loss/train': 2.0342931747436523}
-03/05/2022 16:53:04 - INFO - codeparrot_training - Step 43735: {'lr': 0.0004081466505323892, 'samples': 22392832, 'steps': 43735, 'loss/train': 1.1064194440841675}
-03/05/2022 16:53:06 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/05/2022 16:53:09 - INFO - codeparrot_training - Step 43736: {'lr': 0.0004081425404782811, 'samples': 22393344, 'steps': 43736, 'loss/train': 1.9182690382003784}
-03/05/2022 16:53:12 - INFO - codeparrot_training - Step 43737: {'lr': 0.00040813843035291655, 'samples': 22393856, 'steps': 43737, 'loss/train': 1.207209825515747}
-03/05/2022 16:53:14 - INFO - codeparrot_training - Skipping example with length 954 (seq_length=1024)
-03/05/2022 16:53:17 - INFO - codeparrot_training - Step 43738: {'lr': 0.00040813432015629714, 'samples': 22394368, 'steps': 43738, 'loss/train': 2.294670581817627}
-03/05/2022 16:53:21 - INFO - codeparrot_training - Step 43739: {'lr': 0.0004081302098884249, 'samples': 22394880, 'steps': 43739, 'loss/train': 1.1051883697509766}
-03/05/2022 16:53:22 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/05/2022 16:53:26 - INFO - codeparrot_training - Step 43740: {'lr': 0.0004081260995493015, 'samples': 22395392, 'steps': 43740, 'loss/train': 1.69712233543396}
-03/05/2022 16:53:29 - INFO - codeparrot_training - Step 43741: {'lr': 0.0004081219891389291, 'samples': 22395904, 'steps': 43741, 'loss/train': 1.7056206464767456}
-03/05/2022 16:53:31 - INFO - codeparrot_training - Skipping example with length 429 (seq_length=1024)
-03/05/2022 16:53:34 - INFO - codeparrot_training - Step 43742: {'lr': 0.0004081178786573092, 'samples': 22396416, 'steps': 43742, 'loss/train': 1.5444432497024536}
-03/05/2022 16:53:38 - INFO - codeparrot_training - Step 43743: {'lr': 0.000408113768104444, 'samples': 22396928, 'steps': 43743, 'loss/train': 1.611764907836914}
-03/05/2022 16:53:39 - INFO - codeparrot_training - Skipping example with length 364 (seq_length=1024)
-03/05/2022 16:53:43 - INFO - codeparrot_training - Step 43744: {'lr': 0.0004081096574803351, 'samples': 22397440, 'steps': 43744, 'loss/train': 0.793775737285614}
-03/05/2022 16:53:46 - INFO - codeparrot_training - Step 43745: {'lr': 0.00040810554678498434, 'samples': 22397952, 'steps': 43745, 'loss/train': 1.2236206531524658}
-03/05/2022 16:53:48 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/05/2022 16:53:51 - INFO - codeparrot_training - Step 43746: {'lr': 0.00040810143601839377, 'samples': 22398464, 'steps': 43746, 'loss/train': 2.298741579055786}
-03/05/2022 16:53:55 - INFO - codeparrot_training - Step 43747: {'lr': 0.0004080973251805651, 'samples': 22398976, 'steps': 43747, 'loss/train': 1.856736421585083}
-03/05/2022 16:53:57 - INFO - codeparrot_training - Skipping example with length 172 (seq_length=1024)
-03/05/2022 16:54:00 - INFO - codeparrot_training - Step 43748: {'lr': 0.0004080932142715002, 'samples': 22399488, 'steps': 43748, 'loss/train': 1.2671951055526733}
-03/05/2022 16:54:03 - INFO - codeparrot_training - Step 43749: {'lr': 0.000408089103291201, 'samples': 22400000, 'steps': 43749, 'loss/train': 1.8553847074508667}
-03/05/2022 16:54:05 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/05/2022 16:54:08 - INFO - codeparrot_training - Step 43750: {'lr': 0.0004080849922396692, 'samples': 22400512, 'steps': 43750, 'loss/train': 2.610322952270508}
-03/05/2022 16:54:12 - INFO - codeparrot_training - Step 43751: {'lr': 0.00040808088111690677, 'samples': 22401024, 'steps': 43751, 'loss/train': 0.12095628678798676}
-03/05/2022 16:54:14 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/05/2022 16:54:17 - INFO - codeparrot_training - Step 43752: {'lr': 0.00040807676992291557, 'samples': 22401536, 'steps': 43752, 'loss/train': 1.3341021537780762}
-03/05/2022 16:54:20 - INFO - codeparrot_training - Step 43753: {'lr': 0.0004080726586576974, 'samples': 22402048, 'steps': 43753, 'loss/train': 2.1739494800567627}
-03/05/2022 16:54:22 - INFO - codeparrot_training - Skipping example with length 811 (seq_length=1024)
-03/05/2022 16:54:25 - INFO - codeparrot_training - Step 43754: {'lr': 0.0004080685473212541, 'samples': 22402560, 'steps': 43754, 'loss/train': 1.2442368268966675}
-03/05/2022 16:54:28 - INFO - codeparrot_training - Step 43755: {'lr': 0.0004080644359135876, 'samples': 22403072, 'steps': 43755, 'loss/train': 2.043179750442505}
-03/05/2022 16:54:31 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/05/2022 16:54:34 - INFO - codeparrot_training - Step 43756: {'lr': 0.00040806032443469967, 'samples': 22403584, 'steps': 43756, 'loss/train': 0.4384129047393799}
-03/05/2022 16:54:37 - INFO - codeparrot_training - Step 43757: {'lr': 0.0004080562128845923, 'samples': 22404096, 'steps': 43757, 'loss/train': 1.2111958265304565}
-03/05/2022 16:54:39 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/05/2022 16:54:42 - INFO - codeparrot_training - Step 43758: {'lr': 0.0004080521012632671, 'samples': 22404608, 'steps': 43758, 'loss/train': 1.120803952217102}
-03/05/2022 16:54:46 - INFO - codeparrot_training - Step 43759: {'lr': 0.00040804798957072607, 'samples': 22405120, 'steps': 43759, 'loss/train': 1.6617861986160278}
-03/05/2022 16:54:48 - INFO - codeparrot_training - Skipping example with length 802 (seq_length=1024)
-03/05/2022 16:54:51 - INFO - codeparrot_training - Step 43760: {'lr': 0.0004080438778069711, 'samples': 22405632, 'steps': 43760, 'loss/train': 2.115455150604248}
-03/05/2022 16:54:54 - INFO - codeparrot_training - Step 43761: {'lr': 0.000408039765972004, 'samples': 22406144, 'steps': 43761, 'loss/train': 1.1934529542922974}
-03/05/2022 16:54:56 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/05/2022 16:54:59 - INFO - codeparrot_training - Step 43762: {'lr': 0.0004080356540658266, 'samples': 22406656, 'steps': 43762, 'loss/train': 1.0696488618850708}
-03/05/2022 16:55:02 - INFO - codeparrot_training - Step 43763: {'lr': 0.00040803154208844086, 'samples': 22407168, 'steps': 43763, 'loss/train': 2.110583782196045}
-03/05/2022 16:55:05 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/05/2022 16:55:08 - INFO - codeparrot_training - Step 43764: {'lr': 0.00040802743003984845, 'samples': 22407680, 'steps': 43764, 'loss/train': 1.1371500492095947}
-03/05/2022 16:55:11 - INFO - codeparrot_training - Step 43765: {'lr': 0.0004080233179200513, 'samples': 22408192, 'steps': 43765, 'loss/train': 2.5755507946014404}
-03/05/2022 16:55:13 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/05/2022 16:55:16 - INFO - codeparrot_training - Step 43766: {'lr': 0.00040801920572905133, 'samples': 22408704, 'steps': 43766, 'loss/train': 1.1315655708312988}
-03/05/2022 16:55:19 - INFO - codeparrot_training - Step 43767: {'lr': 0.0004080150934668503, 'samples': 22409216, 'steps': 43767, 'loss/train': 1.925883173942566}
-03/05/2022 16:55:21 - INFO - codeparrot_training - Skipping example with length 158 (seq_length=1024)
-03/05/2022 16:55:25 - INFO - codeparrot_training - Step 43768: {'lr': 0.00040801098113345014, 'samples': 22409728, 'steps': 43768, 'loss/train': 1.7936030626296997}
-03/05/2022 16:55:28 - INFO - codeparrot_training - Step 43769: {'lr': 0.00040800686872885267, 'samples': 22410240, 'steps': 43769, 'loss/train': 1.4563323259353638}
-03/05/2022 16:55:30 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/05/2022 16:55:33 - INFO - codeparrot_training - Step 43770: {'lr': 0.0004080027562530598, 'samples': 22410752, 'steps': 43770, 'loss/train': 2.625141143798828}
-03/05/2022 16:55:36 - INFO - codeparrot_training - Step 43771: {'lr': 0.0004079986437060733, 'samples': 22411264, 'steps': 43771, 'loss/train': 1.2488816976547241}
-03/05/2022 16:55:39 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/05/2022 16:55:42 - INFO - codeparrot_training - Step 43772: {'lr': 0.00040799453108789497, 'samples': 22411776, 'steps': 43772, 'loss/train': 1.4593466520309448}
-03/05/2022 16:55:45 - INFO - codeparrot_training - Step 43773: {'lr': 0.0004079904183985268, 'samples': 22412288, 'steps': 43773, 'loss/train': 2.231966257095337}
-03/05/2022 16:55:47 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/05/2022 16:55:50 - INFO - codeparrot_training - Step 43774: {'lr': 0.00040798630563797055, 'samples': 22412800, 'steps': 43774, 'loss/train': 2.2671263217926025}
-03/05/2022 16:55:53 - INFO - codeparrot_training - Step 43775: {'lr': 0.00040798219280622816, 'samples': 22413312, 'steps': 43775, 'loss/train': 1.4242421388626099}
-03/05/2022 16:55:56 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/05/2022 16:55:59 - INFO - codeparrot_training - Step 43776: {'lr': 0.0004079780799033014, 'samples': 22413824, 'steps': 43776, 'loss/train': 2.207301378250122}
-03/05/2022 16:56:02 - INFO - codeparrot_training - Step 43777: {'lr': 0.0004079739669291922, 'samples': 22414336, 'steps': 43777, 'loss/train': 1.8314064741134644}
-03/05/2022 16:56:05 - INFO - codeparrot_training - Skipping example with length 259 (seq_length=1024)
-03/05/2022 16:56:07 - INFO - codeparrot_training - Step 43778: {'lr': 0.0004079698538839023, 'samples': 22414848, 'steps': 43778, 'loss/train': 1.5699042081832886}
-03/05/2022 16:56:10 - INFO - codeparrot_training - Step 43779: {'lr': 0.00040796574076743366, 'samples': 22415360, 'steps': 43779, 'loss/train': 1.917794942855835}
-03/05/2022 16:56:13 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 16:56:16 - INFO - codeparrot_training - Step 43780: {'lr': 0.00040796162757978803, 'samples': 22415872, 'steps': 43780, 'loss/train': 1.334808111190796}
-03/05/2022 16:56:19 - INFO - codeparrot_training - Step 43781: {'lr': 0.00040795751432096746, 'samples': 22416384, 'steps': 43781, 'loss/train': 2.1090517044067383}
-03/05/2022 16:56:21 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/05/2022 16:56:24 - INFO - codeparrot_training - Step 43782: {'lr': 0.00040795340099097357, 'samples': 22416896, 'steps': 43782, 'loss/train': 2.0725297927856445}
-03/05/2022 16:56:27 - INFO - codeparrot_training - Step 43783: {'lr': 0.00040794928758980837, 'samples': 22417408, 'steps': 43783, 'loss/train': 0.06948641687631607}
-03/05/2022 16:56:30 - INFO - codeparrot_training - Skipping example with length 597 (seq_length=1024)
-03/05/2022 16:56:33 - INFO - codeparrot_training - Step 43784: {'lr': 0.0004079451741174737, 'samples': 22417920, 'steps': 43784, 'loss/train': 1.224715232849121}
-03/05/2022 16:56:36 - INFO - codeparrot_training - Step 43785: {'lr': 0.00040794106057397123, 'samples': 22418432, 'steps': 43785, 'loss/train': 1.880058765411377}
-03/05/2022 16:56:38 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/05/2022 16:56:41 - INFO - codeparrot_training - Step 43786: {'lr': 0.00040793694695930304, 'samples': 22418944, 'steps': 43786, 'loss/train': 1.9487391710281372}
-03/05/2022 16:56:44 - INFO - codeparrot_training - Step 43787: {'lr': 0.00040793283327347085, 'samples': 22419456, 'steps': 43787, 'loss/train': 1.438030481338501}
-03/05/2022 16:56:46 - INFO - codeparrot_training - Skipping example with length 32 (seq_length=1024)
-03/05/2022 16:56:49 - INFO - codeparrot_training - Step 43788: {'lr': 0.00040792871951647657, 'samples': 22419968, 'steps': 43788, 'loss/train': 1.9918346405029297}
-03/05/2022 16:56:53 - INFO - codeparrot_training - Step 43789: {'lr': 0.00040792460568832214, 'samples': 22420480, 'steps': 43789, 'loss/train': 2.6037285327911377}
-03/05/2022 16:56:54 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/05/2022 16:56:58 - INFO - codeparrot_training - Step 43790: {'lr': 0.00040792049178900924, 'samples': 22420992, 'steps': 43790, 'loss/train': 1.5741981267929077}
-03/05/2022 16:57:01 - INFO - codeparrot_training - Step 43791: {'lr': 0.00040791637781853983, 'samples': 22421504, 'steps': 43791, 'loss/train': 1.9002717733383179}
-03/05/2022 16:57:03 - INFO - codeparrot_training - Skipping example with length 930 (seq_length=1024)
-03/05/2022 16:57:06 - INFO - codeparrot_training - Step 43792: {'lr': 0.0004079122637769157, 'samples': 22422016, 'steps': 43792, 'loss/train': 1.9454540014266968}
-03/05/2022 16:57:10 - INFO - codeparrot_training - Step 43793: {'lr': 0.0004079081496641388, 'samples': 22422528, 'steps': 43793, 'loss/train': 1.5321191549301147}
-03/05/2022 16:57:11 - INFO - codeparrot_training - Skipping example with length 133 (seq_length=1024)
-03/05/2022 16:57:15 - INFO - codeparrot_training - Step 43794: {'lr': 0.0004079040354802109, 'samples': 22423040, 'steps': 43794, 'loss/train': 1.175579309463501}
-03/05/2022 16:57:18 - INFO - codeparrot_training - Step 43795: {'lr': 0.00040789992122513386, 'samples': 22423552, 'steps': 43795, 'loss/train': 1.3223199844360352}
-03/05/2022 16:57:20 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/05/2022 16:57:23 - INFO - codeparrot_training - Step 43796: {'lr': 0.00040789580689890953, 'samples': 22424064, 'steps': 43796, 'loss/train': 1.7115073204040527}
-03/05/2022 16:57:27 - INFO - codeparrot_training - Step 43797: {'lr': 0.00040789169250153985, 'samples': 22424576, 'steps': 43797, 'loss/train': 2.380213499069214}
-03/05/2022 16:57:29 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 16:57:32 - INFO - codeparrot_training - Step 43798: {'lr': 0.00040788757803302656, 'samples': 22425088, 'steps': 43798, 'loss/train': 1.8337550163269043}
-03/05/2022 16:57:35 - INFO - codeparrot_training - Step 43799: {'lr': 0.00040788346349337156, 'samples': 22425600, 'steps': 43799, 'loss/train': 1.8149511814117432}
-03/05/2022 16:57:38 - INFO - codeparrot_training - Skipping example with length 718 (seq_length=1024)
-03/05/2022 16:57:40 - INFO - codeparrot_training - Step 43800: {'lr': 0.00040787934888257673, 'samples': 22426112, 'steps': 43800, 'loss/train': 1.8103344440460205}
-03/05/2022 16:57:44 - INFO - codeparrot_training - Step 43801: {'lr': 0.00040787523420064394, 'samples': 22426624, 'steps': 43801, 'loss/train': 1.837502360343933}
-03/05/2022 16:57:46 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 16:57:49 - INFO - codeparrot_training - Step 43802: {'lr': 0.00040787111944757496, 'samples': 22427136, 'steps': 43802, 'loss/train': 2.037440538406372}
-03/05/2022 16:57:52 - INFO - codeparrot_training - Step 43803: {'lr': 0.0004078670046233717, 'samples': 22427648, 'steps': 43803, 'loss/train': 1.5786080360412598}
-03/05/2022 16:57:55 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/05/2022 16:57:57 - INFO - codeparrot_training - Step 43804: {'lr': 0.000407862889728036, 'samples': 22428160, 'steps': 43804, 'loss/train': 1.5454950332641602}
-03/05/2022 16:58:01 - INFO - codeparrot_training - Step 43805: {'lr': 0.0004078587747615697, 'samples': 22428672, 'steps': 43805, 'loss/train': 1.5921725034713745}
-03/05/2022 16:58:03 - INFO - codeparrot_training - Skipping example with length 939 (seq_length=1024)
-03/05/2022 16:58:06 - INFO - codeparrot_training - Step 43806: {'lr': 0.00040785465972397475, 'samples': 22429184, 'steps': 43806, 'loss/train': 2.730365037918091}
-03/05/2022 16:58:09 - INFO - codeparrot_training - Step 43807: {'lr': 0.0004078505446152528, 'samples': 22429696, 'steps': 43807, 'loss/train': 1.6530457735061646}
-03/05/2022 16:58:11 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/05/2022 16:58:14 - INFO - codeparrot_training - Step 43808: {'lr': 0.0004078464294354059, 'samples': 22430208, 'steps': 43808, 'loss/train': 2.3621537685394287}
-03/05/2022 16:58:17 - INFO - codeparrot_training - Step 43809: {'lr': 0.00040784231418443585, 'samples': 22430720, 'steps': 43809, 'loss/train': 1.6734894514083862}
-03/05/2022 16:58:20 - INFO - codeparrot_training - Skipping example with length 912 (seq_length=1024)
-03/05/2022 16:58:23 - INFO - codeparrot_training - Step 43810: {'lr': 0.00040783819886234445, 'samples': 22431232, 'steps': 43810, 'loss/train': 1.0745031833648682}
-03/05/2022 16:58:26 - INFO - codeparrot_training - Step 43811: {'lr': 0.00040783408346913366, 'samples': 22431744, 'steps': 43811, 'loss/train': 1.5872265100479126}
-03/05/2022 16:58:28 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/05/2022 16:58:31 - INFO - codeparrot_training - Step 43812: {'lr': 0.00040782996800480523, 'samples': 22432256, 'steps': 43812, 'loss/train': 2.334005355834961}
-03/05/2022 16:58:34 - INFO - codeparrot_training - Step 43813: {'lr': 0.000407825852469361, 'samples': 22432768, 'steps': 43813, 'loss/train': 1.9279346466064453}
-03/05/2022 16:58:37 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/05/2022 16:58:40 - INFO - codeparrot_training - Step 43814: {'lr': 0.00040782173686280287, 'samples': 22433280, 'steps': 43814, 'loss/train': 1.9805338382720947}
-03/05/2022 16:58:43 - INFO - codeparrot_training - Step 43815: {'lr': 0.0004078176211851328, 'samples': 22433792, 'steps': 43815, 'loss/train': 2.4957211017608643}
-03/05/2022 16:58:45 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/05/2022 16:58:48 - INFO - codeparrot_training - Step 43816: {'lr': 0.0004078135054363524, 'samples': 22434304, 'steps': 43816, 'loss/train': 1.9035494327545166}
-03/05/2022 16:58:52 - INFO - codeparrot_training - Step 43817: {'lr': 0.00040780938961646385, 'samples': 22434816, 'steps': 43817, 'loss/train': 1.687270164489746}
-03/05/2022 16:58:55 - INFO - codeparrot_training - Step 43818: {'lr': 0.00040780527372546874, 'samples': 22435328, 'steps': 43818, 'loss/train': 1.753762125968933}
-03/05/2022 16:58:56 - INFO - codeparrot_training - Skipping example with length 665 (seq_length=1024)
-03/05/2022 16:59:00 - INFO - codeparrot_training - Step 43819: {'lr': 0.000407801157763369, 'samples': 22435840, 'steps': 43819, 'loss/train': 1.92158842086792}
-03/05/2022 16:59:03 - INFO - codeparrot_training - Step 43820: {'lr': 0.0004077970417301665, 'samples': 22436352, 'steps': 43820, 'loss/train': 1.331741452217102}
-03/05/2022 16:59:04 - INFO - codeparrot_training - Skipping example with length 218 (seq_length=1024)
-03/05/2022 16:59:08 - INFO - codeparrot_training - Step 43821: {'lr': 0.00040779292562586304, 'samples': 22436864, 'steps': 43821, 'loss/train': 2.6385693550109863}
-03/05/2022 16:59:12 - INFO - codeparrot_training - Step 43822: {'lr': 0.0004077888094504606, 'samples': 22437376, 'steps': 43822, 'loss/train': 1.2542415857315063}
-03/05/2022 16:59:12 - INFO - codeparrot_training - Skipping example with length 885 (seq_length=1024)
-03/05/2022 16:59:17 - INFO - codeparrot_training - Step 43823: {'lr': 0.0004077846932039609, 'samples': 22437888, 'steps': 43823, 'loss/train': 1.5465662479400635}
-03/05/2022 16:59:20 - INFO - codeparrot_training - Step 43824: {'lr': 0.00040778057688636594, 'samples': 22438400, 'steps': 43824, 'loss/train': 1.8899484872817993}
-03/05/2022 16:59:21 - INFO - codeparrot_training - Skipping example with length 846 (seq_length=1024)
-03/05/2022 16:59:25 - INFO - codeparrot_training - Step 43825: {'lr': 0.00040777646049767736, 'samples': 22438912, 'steps': 43825, 'loss/train': 2.057701349258423}
-03/05/2022 16:59:28 - INFO - codeparrot_training - Step 43826: {'lr': 0.0004077723440378972, 'samples': 22439424, 'steps': 43826, 'loss/train': 1.5554970502853394}
-03/05/2022 16:59:29 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/05/2022 16:59:34 - INFO - codeparrot_training - Step 43827: {'lr': 0.0004077682275070273, 'samples': 22439936, 'steps': 43827, 'loss/train': 2.241832733154297}
-03/05/2022 16:59:37 - INFO - codeparrot_training - Step 43828: {'lr': 0.00040776411090506944, 'samples': 22440448, 'steps': 43828, 'loss/train': 1.3987410068511963}
-03/05/2022 16:59:37 - INFO - codeparrot_training - Skipping example with length 556 (seq_length=1024)
-03/05/2022 16:59:42 - INFO - codeparrot_training - Step 43829: {'lr': 0.0004077599942320255, 'samples': 22440960, 'steps': 43829, 'loss/train': 1.2790558338165283}
-03/05/2022 16:59:45 - INFO - codeparrot_training - Step 43830: {'lr': 0.00040775587748789733, 'samples': 22441472, 'steps': 43830, 'loss/train': 1.166007161140442}
-03/05/2022 16:59:46 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/05/2022 16:59:51 - INFO - codeparrot_training - Step 43831: {'lr': 0.0004077517606726868, 'samples': 22441984, 'steps': 43831, 'loss/train': 1.5942026376724243}
-03/05/2022 16:59:54 - INFO - codeparrot_training - Step 43832: {'lr': 0.0004077476437863958, 'samples': 22442496, 'steps': 43832, 'loss/train': 1.0755010843276978}
-03/05/2022 16:59:54 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/05/2022 16:59:59 - INFO - codeparrot_training - Step 43833: {'lr': 0.0004077435268290261, 'samples': 22443008, 'steps': 43833, 'loss/train': 1.4858921766281128}
-03/05/2022 17:00:02 - INFO - codeparrot_training - Step 43834: {'lr': 0.0004077394098005796, 'samples': 22443520, 'steps': 43834, 'loss/train': 1.7185603380203247}
-03/05/2022 17:00:02 - INFO - codeparrot_training - Skipping example with length 451 (seq_length=1024)
-03/05/2022 17:00:07 - INFO - codeparrot_training - Step 43835: {'lr': 0.00040773529270105816, 'samples': 22444032, 'steps': 43835, 'loss/train': 1.8293707370758057}
-03/05/2022 17:00:11 - INFO - codeparrot_training - Step 43836: {'lr': 0.0004077311755304637, 'samples': 22444544, 'steps': 43836, 'loss/train': 1.56156325340271}
-03/05/2022 17:00:11 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/05/2022 17:00:16 - INFO - codeparrot_training - Step 43837: {'lr': 0.000407727058288798, 'samples': 22445056, 'steps': 43837, 'loss/train': 1.6813124418258667}
-03/05/2022 17:00:19 - INFO - codeparrot_training - Step 43838: {'lr': 0.00040772294097606276, 'samples': 22445568, 'steps': 43838, 'loss/train': 1.2740013599395752}
-03/05/2022 17:00:19 - INFO - codeparrot_training - Skipping example with length 303 (seq_length=1024)
-03/05/2022 17:00:25 - INFO - codeparrot_training - Step 43839: {'lr': 0.0004077188235922601, 'samples': 22446080, 'steps': 43839, 'loss/train': 1.6485356092453003}
-03/05/2022 17:00:28 - INFO - codeparrot_training - Step 43840: {'lr': 0.0004077147061373918, 'samples': 22446592, 'steps': 43840, 'loss/train': 2.145946502685547}
-03/05/2022 17:00:30 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 17:00:33 - INFO - codeparrot_training - Step 43841: {'lr': 0.00040771058861145963, 'samples': 22447104, 'steps': 43841, 'loss/train': 1.7775769233703613}
-03/05/2022 17:00:36 - INFO - codeparrot_training - Step 43842: {'lr': 0.0004077064710144656, 'samples': 22447616, 'steps': 43842, 'loss/train': 2.2430338859558105}
-03/05/2022 17:00:39 - INFO - codeparrot_training - Skipping example with length 22 (seq_length=1024)
-03/05/2022 17:00:41 - INFO - codeparrot_training - Step 43843: {'lr': 0.0004077023533464114, 'samples': 22448128, 'steps': 43843, 'loss/train': 1.9397205114364624}
-03/05/2022 17:00:45 - INFO - codeparrot_training - Step 43844: {'lr': 0.000407698235607299, 'samples': 22448640, 'steps': 43844, 'loss/train': 0.9130280017852783}
-03/05/2022 17:00:47 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/05/2022 17:00:50 - INFO - codeparrot_training - Step 43845: {'lr': 0.0004076941177971301, 'samples': 22449152, 'steps': 43845, 'loss/train': 0.5364644527435303}
-03/05/2022 17:00:53 - INFO - codeparrot_training - Step 43846: {'lr': 0.0004076899999159067, 'samples': 22449664, 'steps': 43846, 'loss/train': 1.2022267580032349}
-03/05/2022 17:00:55 - INFO - codeparrot_training - Skipping example with length 603 (seq_length=1024)
-03/05/2022 17:00:58 - INFO - codeparrot_training - Step 43847: {'lr': 0.0004076858819636307, 'samples': 22450176, 'steps': 43847, 'loss/train': 1.6162538528442383}
-03/05/2022 17:01:02 - INFO - codeparrot_training - Step 43848: {'lr': 0.0004076817639403038, 'samples': 22450688, 'steps': 43848, 'loss/train': 2.0896689891815186}
-03/05/2022 17:01:04 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/05/2022 17:01:07 - INFO - codeparrot_training - Step 43849: {'lr': 0.0004076776458459279, 'samples': 22451200, 'steps': 43849, 'loss/train': 1.6193335056304932}
-03/05/2022 17:01:10 - INFO - codeparrot_training - Step 43850: {'lr': 0.00040767352768050503, 'samples': 22451712, 'steps': 43850, 'loss/train': 1.8727627992630005}
-03/05/2022 17:01:12 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/05/2022 17:01:15 - INFO - codeparrot_training - Step 43851: {'lr': 0.0004076694094440368, 'samples': 22452224, 'steps': 43851, 'loss/train': 0.19420208036899567}
-03/05/2022 17:01:19 - INFO - codeparrot_training - Step 43852: {'lr': 0.0004076652911365252, 'samples': 22452736, 'steps': 43852, 'loss/train': 2.0492234230041504}
-03/05/2022 17:01:21 - INFO - codeparrot_training - Skipping example with length 441 (seq_length=1024)
-03/05/2022 17:01:24 - INFO - codeparrot_training - Step 43853: {'lr': 0.00040766117275797196, 'samples': 22453248, 'steps': 43853, 'loss/train': 0.8284090161323547}
-03/05/2022 17:01:27 - INFO - codeparrot_training - Step 43854: {'lr': 0.0004076570543083792, 'samples': 22453760, 'steps': 43854, 'loss/train': 1.439929485321045}
-03/05/2022 17:01:29 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/05/2022 17:01:32 - INFO - codeparrot_training - Step 43855: {'lr': 0.0004076529357877485, 'samples': 22454272, 'steps': 43855, 'loss/train': 3.068974733352661}
-03/05/2022 17:01:35 - INFO - codeparrot_training - Step 43856: {'lr': 0.00040764881719608184, 'samples': 22454784, 'steps': 43856, 'loss/train': 0.959490180015564}
-03/05/2022 17:01:37 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 17:01:41 - INFO - codeparrot_training - Step 43857: {'lr': 0.000407644698533381, 'samples': 22455296, 'steps': 43857, 'loss/train': 1.4604078531265259}
-03/05/2022 17:01:44 - INFO - codeparrot_training - Step 43858: {'lr': 0.00040764057979964793, 'samples': 22455808, 'steps': 43858, 'loss/train': 1.9327092170715332}
-03/05/2022 17:01:47 - INFO - codeparrot_training - Step 43859: {'lr': 0.0004076364609948844, 'samples': 22456320, 'steps': 43859, 'loss/train': 3.244659423828125}
-03/05/2022 17:01:47 - INFO - codeparrot_training - Skipping example with length 434 (seq_length=1024)
-03/05/2022 17:01:53 - INFO - codeparrot_training - Step 43860: {'lr': 0.0004076323421190924, 'samples': 22456832, 'steps': 43860, 'loss/train': 1.955910563468933}
-03/05/2022 17:01:56 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/05/2022 17:01:58 - INFO - codeparrot_training - Step 43861: {'lr': 0.0004076282231722737, 'samples': 22457344, 'steps': 43861, 'loss/train': 2.271181344985962}
-03/05/2022 17:02:01 - INFO - codeparrot_training - Step 43862: {'lr': 0.0004076241041544301, 'samples': 22457856, 'steps': 43862, 'loss/train': 1.480958342552185}
-03/05/2022 17:02:05 - INFO - codeparrot_training - Step 43863: {'lr': 0.00040761998506556353, 'samples': 22458368, 'steps': 43863, 'loss/train': 0.4877408742904663}
-03/05/2022 17:02:05 - INFO - codeparrot_training - Skipping example with length 476 (seq_length=1024)
-03/05/2022 17:02:10 - INFO - codeparrot_training - Step 43864: {'lr': 0.0004076158659056758, 'samples': 22458880, 'steps': 43864, 'loss/train': 0.7723501324653625}
-03/05/2022 17:02:13 - INFO - codeparrot_training - Step 43865: {'lr': 0.00040761174667476883, 'samples': 22459392, 'steps': 43865, 'loss/train': 1.313813328742981}
-03/05/2022 17:02:13 - INFO - codeparrot_training - Skipping example with length 271 (seq_length=1024)
-03/05/2022 17:02:18 - INFO - codeparrot_training - Step 43866: {'lr': 0.0004076076273728444, 'samples': 22459904, 'steps': 43866, 'loss/train': 2.0009844303131104}
-03/05/2022 17:02:22 - INFO - codeparrot_training - Step 43867: {'lr': 0.0004076035079999045, 'samples': 22460416, 'steps': 43867, 'loss/train': 1.7654095888137817}
-03/05/2022 17:02:22 - INFO - codeparrot_training - Skipping example with length 265 (seq_length=1024)
-03/05/2022 17:02:27 - INFO - codeparrot_training - Step 43868: {'lr': 0.0004075993885559508, 'samples': 22460928, 'steps': 43868, 'loss/train': 1.6525152921676636}
-03/05/2022 17:02:30 - INFO - codeparrot_training - Step 43869: {'lr': 0.0004075952690409852, 'samples': 22461440, 'steps': 43869, 'loss/train': 2.596529245376587}
-03/05/2022 17:02:31 - INFO - codeparrot_training - Skipping example with length 599 (seq_length=1024)
-03/05/2022 17:02:35 - INFO - codeparrot_training - Step 43870: {'lr': 0.00040759114945500974, 'samples': 22461952, 'steps': 43870, 'loss/train': 1.7956039905548096}
-03/05/2022 17:02:38 - INFO - codeparrot_training - Step 43871: {'lr': 0.0004075870297980261, 'samples': 22462464, 'steps': 43871, 'loss/train': 1.3891104459762573}
-03/05/2022 17:02:39 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/05/2022 17:02:44 - INFO - codeparrot_training - Step 43872: {'lr': 0.0004075829100700361, 'samples': 22462976, 'steps': 43872, 'loss/train': 0.7473767399787903}
-03/05/2022 17:02:47 - INFO - codeparrot_training - Step 43873: {'lr': 0.0004075787902710417, 'samples': 22463488, 'steps': 43873, 'loss/train': 1.9922208786010742}
-03/05/2022 17:02:48 - INFO - codeparrot_training - Skipping example with length 828 (seq_length=1024)
-03/05/2022 17:02:52 - INFO - codeparrot_training - Step 43874: {'lr': 0.0004075746704010448, 'samples': 22464000, 'steps': 43874, 'loss/train': 1.3193403482437134}
-03/05/2022 17:02:55 - INFO - codeparrot_training - Step 43875: {'lr': 0.0004075705504600471, 'samples': 22464512, 'steps': 43875, 'loss/train': 2.283310890197754}
-03/05/2022 17:02:56 - INFO - codeparrot_training - Skipping example with length 560 (seq_length=1024)
-03/05/2022 17:03:01 - INFO - codeparrot_training - Step 43876: {'lr': 0.00040756643044805057, 'samples': 22465024, 'steps': 43876, 'loss/train': 2.2278008460998535}
-03/05/2022 17:03:04 - INFO - codeparrot_training - Step 43877: {'lr': 0.0004075623103650571, 'samples': 22465536, 'steps': 43877, 'loss/train': 1.8205305337905884}
-03/05/2022 17:03:04 - INFO - codeparrot_training - Skipping example with length 63 (seq_length=1024)
-03/05/2022 17:03:09 - INFO - codeparrot_training - Step 43878: {'lr': 0.00040755819021106844, 'samples': 22466048, 'steps': 43878, 'loss/train': 2.260338306427002}
-03/05/2022 17:03:12 - INFO - codeparrot_training - Step 43879: {'lr': 0.00040755406998608645, 'samples': 22466560, 'steps': 43879, 'loss/train': 0.7675941586494446}
-03/05/2022 17:03:13 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/05/2022 17:03:17 - INFO - codeparrot_training - Step 43880: {'lr': 0.00040754994969011306, 'samples': 22467072, 'steps': 43880, 'loss/train': 0.2639926075935364}
-03/05/2022 17:03:21 - INFO - codeparrot_training - Step 43881: {'lr': 0.00040754582932315007, 'samples': 22467584, 'steps': 43881, 'loss/train': 1.5944522619247437}
-03/05/2022 17:03:21 - INFO - codeparrot_training - Skipping example with length 587 (seq_length=1024)
-03/05/2022 17:03:26 - INFO - codeparrot_training - Step 43882: {'lr': 0.0004075417088851994, 'samples': 22468096, 'steps': 43882, 'loss/train': 1.3711528778076172}
-03/05/2022 17:03:29 - INFO - codeparrot_training - Step 43883: {'lr': 0.0004075375883762629, 'samples': 22468608, 'steps': 43883, 'loss/train': 1.6593151092529297}
-03/05/2022 17:03:30 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/05/2022 17:03:35 - INFO - codeparrot_training - Step 43884: {'lr': 0.0004075334677963423, 'samples': 22469120, 'steps': 43884, 'loss/train': 3.2335045337677}
-03/05/2022 17:03:38 - INFO - codeparrot_training - Step 43885: {'lr': 0.0004075293471454396, 'samples': 22469632, 'steps': 43885, 'loss/train': 1.0621802806854248}
-03/05/2022 17:03:38 - INFO - codeparrot_training - Skipping example with length 513 (seq_length=1024)
-03/05/2022 17:03:43 - INFO - codeparrot_training - Step 43886: {'lr': 0.0004075252264235566, 'samples': 22470144, 'steps': 43886, 'loss/train': 0.9870612621307373}
-03/05/2022 17:03:46 - INFO - codeparrot_training - Step 43887: {'lr': 0.0004075211056306951, 'samples': 22470656, 'steps': 43887, 'loss/train': 2.7605912685394287}
-03/05/2022 17:03:47 - INFO - codeparrot_training - Skipping example with length 202 (seq_length=1024)
-03/05/2022 17:03:51 - INFO - codeparrot_training - Step 43888: {'lr': 0.00040751698476685716, 'samples': 22471168, 'steps': 43888, 'loss/train': 1.9867603778839111}
-03/05/2022 17:03:55 - INFO - codeparrot_training - Step 43889: {'lr': 0.00040751286383204437, 'samples': 22471680, 'steps': 43889, 'loss/train': 1.8042305707931519}
-03/05/2022 17:03:55 - INFO - codeparrot_training - Skipping example with length 38 (seq_length=1024)
-03/05/2022 17:04:00 - INFO - codeparrot_training - Step 43890: {'lr': 0.0004075087428262588, 'samples': 22472192, 'steps': 43890, 'loss/train': 6.065919876098633}
-03/05/2022 17:04:03 - INFO - codeparrot_training - Step 43891: {'lr': 0.0004075046217495022, 'samples': 22472704, 'steps': 43891, 'loss/train': 1.916242003440857}
-03/05/2022 17:04:05 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 17:04:08 - INFO - codeparrot_training - Step 43892: {'lr': 0.00040750050060177643, 'samples': 22473216, 'steps': 43892, 'loss/train': 2.263683795928955}
-03/05/2022 17:04:12 - INFO - codeparrot_training - Step 43893: {'lr': 0.00040749637938308336, 'samples': 22473728, 'steps': 43893, 'loss/train': 1.5873838663101196}
-03/05/2022 17:04:14 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/05/2022 17:04:17 - INFO - codeparrot_training - Step 43894: {'lr': 0.00040749225809342485, 'samples': 22474240, 'steps': 43894, 'loss/train': 5.848801136016846}
-03/05/2022 17:04:20 - INFO - codeparrot_training - Step 43895: {'lr': 0.00040748813673280277, 'samples': 22474752, 'steps': 43895, 'loss/train': 1.6977359056472778}
-03/05/2022 17:04:24 - INFO - codeparrot_training - Step 43896: {'lr': 0.0004074840153012189, 'samples': 22475264, 'steps': 43896, 'loss/train': 2.025935173034668}
-03/05/2022 17:04:24 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/05/2022 17:04:29 - INFO - codeparrot_training - Step 43897: {'lr': 0.0004074798937986753, 'samples': 22475776, 'steps': 43897, 'loss/train': 0.9327576160430908}
-03/05/2022 17:04:32 - INFO - codeparrot_training - Step 43898: {'lr': 0.00040747577222517364, 'samples': 22476288, 'steps': 43898, 'loss/train': 1.450350046157837}
-03/05/2022 17:04:33 - INFO - codeparrot_training - Skipping example with length 695 (seq_length=1024)
-03/05/2022 17:04:37 - INFO - codeparrot_training - Step 43899: {'lr': 0.0004074716505807158, 'samples': 22476800, 'steps': 43899, 'loss/train': 1.9614824056625366}
-03/05/2022 17:04:41 - INFO - codeparrot_training - Step 43900: {'lr': 0.0004074675288653037, 'samples': 22477312, 'steps': 43900, 'loss/train': 2.097571849822998}
-03/05/2022 17:04:41 - INFO - codeparrot_training - Skipping example with length 669 (seq_length=1024)
-03/05/2022 17:04:46 - INFO - codeparrot_training - Step 43901: {'lr': 0.0004074634070789391, 'samples': 22477824, 'steps': 43901, 'loss/train': 1.5937901735305786}
-03/05/2022 17:04:49 - INFO - codeparrot_training - Step 43902: {'lr': 0.0004074592852216239, 'samples': 22478336, 'steps': 43902, 'loss/train': 2.261753559112549}
-03/05/2022 17:04:50 - INFO - codeparrot_training - Skipping example with length 635 (seq_length=1024)
-03/05/2022 17:04:54 - INFO - codeparrot_training - Step 43903: {'lr': 0.0004074551632933601, 'samples': 22478848, 'steps': 43903, 'loss/train': 1.6696419715881348}
-03/05/2022 17:04:58 - INFO - codeparrot_training - Step 43904: {'lr': 0.00040745104129414933, 'samples': 22479360, 'steps': 43904, 'loss/train': 2.5564606189727783}
-03/05/2022 17:05:03 - INFO - codeparrot_training - Step 43905: {'lr': 0.0004074469192239936, 'samples': 22479872, 'steps': 43905, 'loss/train': 3.1162302494049072}
-03/05/2022 17:05:06 - INFO - codeparrot_training - Step 43906: {'lr': 0.0004074427970828947, 'samples': 22480384, 'steps': 43906, 'loss/train': 1.4316298961639404}
-03/05/2022 17:05:07 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/05/2022 17:05:11 - INFO - codeparrot_training - Step 43907: {'lr': 0.00040743867487085444, 'samples': 22480896, 'steps': 43907, 'loss/train': 1.3243454694747925}
-03/05/2022 17:05:15 - INFO - codeparrot_training - Step 43908: {'lr': 0.0004074345525878748, 'samples': 22481408, 'steps': 43908, 'loss/train': 1.1086838245391846}
-03/05/2022 17:05:15 - INFO - codeparrot_training - Skipping example with length 1009 (seq_length=1024)
-03/05/2022 17:05:20 - INFO - codeparrot_training - Step 43909: {'lr': 0.0004074304302339576, 'samples': 22481920, 'steps': 43909, 'loss/train': 0.9239487051963806}
-03/05/2022 17:05:23 - INFO - codeparrot_training - Step 43910: {'lr': 0.0004074263078091046, 'samples': 22482432, 'steps': 43910, 'loss/train': 1.3239798545837402}
-03/05/2022 17:05:24 - INFO - codeparrot_training - Skipping example with length 712 (seq_length=1024)
-03/05/2022 17:05:28 - INFO - codeparrot_training - Step 43911: {'lr': 0.00040742218531331786, 'samples': 22482944, 'steps': 43911, 'loss/train': 1.6117647886276245}
-03/05/2022 17:05:32 - INFO - codeparrot_training - Step 43912: {'lr': 0.0004074180627465991, 'samples': 22483456, 'steps': 43912, 'loss/train': 1.4238600730895996}
-03/05/2022 17:05:32 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/05/2022 17:05:37 - INFO - codeparrot_training - Step 43913: {'lr': 0.00040741394010895013, 'samples': 22483968, 'steps': 43913, 'loss/train': 2.1622467041015625}
-03/05/2022 17:05:40 - INFO - codeparrot_training - Step 43914: {'lr': 0.0004074098174003729, 'samples': 22484480, 'steps': 43914, 'loss/train': 1.690324306488037}
-03/05/2022 17:05:42 - INFO - codeparrot_training - Skipping example with length 174 (seq_length=1024)
-03/05/2022 17:05:46 - INFO - codeparrot_training - Step 43915: {'lr': 0.0004074056946208692, 'samples': 22484992, 'steps': 43915, 'loss/train': 1.8282055854797363}
-03/05/2022 17:05:49 - INFO - codeparrot_training - Step 43916: {'lr': 0.0004074015717704409, 'samples': 22485504, 'steps': 43916, 'loss/train': 1.258918046951294}
-03/05/2022 17:05:51 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/05/2022 17:05:54 - INFO - codeparrot_training - Step 43917: {'lr': 0.00040739744884908994, 'samples': 22486016, 'steps': 43917, 'loss/train': 1.503737449645996}
-03/05/2022 17:05:57 - INFO - codeparrot_training - Step 43918: {'lr': 0.00040739332585681807, 'samples': 22486528, 'steps': 43918, 'loss/train': 1.3356200456619263}
-03/05/2022 17:06:00 - INFO - codeparrot_training - Skipping example with length 1015 (seq_length=1024)
-03/05/2022 17:06:03 - INFO - codeparrot_training - Step 43919: {'lr': 0.00040738920279362724, 'samples': 22487040, 'steps': 43919, 'loss/train': 1.6052608489990234}
-03/05/2022 17:06:06 - INFO - codeparrot_training - Step 43920: {'lr': 0.00040738507965951923, 'samples': 22487552, 'steps': 43920, 'loss/train': 0.9439377188682556}
-03/05/2022 17:06:08 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/05/2022 17:06:11 - INFO - codeparrot_training - Step 43921: {'lr': 0.0004073809564544959, 'samples': 22488064, 'steps': 43921, 'loss/train': 1.9156811237335205}
-03/05/2022 17:06:14 - INFO - codeparrot_training - Step 43922: {'lr': 0.0004073768331785592, 'samples': 22488576, 'steps': 43922, 'loss/train': 1.0275382995605469}
-03/05/2022 17:06:17 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/05/2022 17:06:19 - INFO - codeparrot_training - Step 43923: {'lr': 0.0004073727098317109, 'samples': 22489088, 'steps': 43923, 'loss/train': 1.474462628364563}
-03/05/2022 17:06:22 - INFO - codeparrot_training - Step 43924: {'lr': 0.0004073685864139529, 'samples': 22489600, 'steps': 43924, 'loss/train': 1.7744269371032715}
-03/05/2022 17:06:25 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/05/2022 17:06:28 - INFO - codeparrot_training - Step 43925: {'lr': 0.00040736446292528704, 'samples': 22490112, 'steps': 43925, 'loss/train': 0.6797260642051697}
-03/05/2022 17:06:31 - INFO - codeparrot_training - Step 43926: {'lr': 0.0004073603393657152, 'samples': 22490624, 'steps': 43926, 'loss/train': 1.4901611804962158}
-03/05/2022 17:06:34 - INFO - codeparrot_training - Skipping example with length 865 (seq_length=1024)
-03/05/2022 17:06:36 - INFO - codeparrot_training - Step 43927: {'lr': 0.0004073562157352392, 'samples': 22491136, 'steps': 43927, 'loss/train': 1.5622234344482422}
-03/05/2022 17:06:40 - INFO - codeparrot_training - Step 43928: {'lr': 0.00040735209203386093, 'samples': 22491648, 'steps': 43928, 'loss/train': 1.8684837818145752}
-03/05/2022 17:06:42 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 17:06:45 - INFO - codeparrot_training - Step 43929: {'lr': 0.00040734796826158226, 'samples': 22492160, 'steps': 43929, 'loss/train': 1.1911612749099731}
-03/05/2022 17:06:48 - INFO - codeparrot_training - Step 43930: {'lr': 0.000407343844418405, 'samples': 22492672, 'steps': 43930, 'loss/train': 0.7678801417350769}
-03/05/2022 17:06:51 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/05/2022 17:06:53 - INFO - codeparrot_training - Step 43931: {'lr': 0.000407339720504331, 'samples': 22493184, 'steps': 43931, 'loss/train': 1.5152851343154907}
-03/05/2022 17:06:56 - INFO - codeparrot_training - Step 43932: {'lr': 0.00040733559651936216, 'samples': 22493696, 'steps': 43932, 'loss/train': 1.4474480152130127}
-03/05/2022 17:06:59 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/05/2022 17:07:02 - INFO - codeparrot_training - Step 43933: {'lr': 0.0004073314724635003, 'samples': 22494208, 'steps': 43933, 'loss/train': 1.9507339000701904}
-03/05/2022 17:07:05 - INFO - codeparrot_training - Step 43934: {'lr': 0.0004073273483367474, 'samples': 22494720, 'steps': 43934, 'loss/train': 1.06267511844635}
-03/05/2022 17:07:08 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/05/2022 17:07:10 - INFO - codeparrot_training - Step 43935: {'lr': 0.0004073232241391052, 'samples': 22495232, 'steps': 43935, 'loss/train': 1.9124641418457031}
-03/05/2022 17:07:14 - INFO - codeparrot_training - Step 43936: {'lr': 0.00040731909987057547, 'samples': 22495744, 'steps': 43936, 'loss/train': 0.9738065600395203}
-03/05/2022 17:07:16 - INFO - codeparrot_training - Skipping example with length 219 (seq_length=1024)
-03/05/2022 17:07:19 - INFO - codeparrot_training - Step 43937: {'lr': 0.0004073149755311603, 'samples': 22496256, 'steps': 43937, 'loss/train': 1.2642452716827393}
-03/05/2022 17:07:22 - INFO - codeparrot_training - Step 43938: {'lr': 0.0004073108511208614, 'samples': 22496768, 'steps': 43938, 'loss/train': 1.7471874952316284}
-03/05/2022 17:07:25 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 17:07:27 - INFO - codeparrot_training - Step 43939: {'lr': 0.0004073067266396807, 'samples': 22497280, 'steps': 43939, 'loss/train': 0.8563461899757385}
-03/05/2022 17:07:30 - INFO - codeparrot_training - Step 43940: {'lr': 0.00040730260208761995, 'samples': 22497792, 'steps': 43940, 'loss/train': 1.312140941619873}
-03/05/2022 17:07:33 - INFO - codeparrot_training - Skipping example with length 746 (seq_length=1024)
-03/05/2022 17:07:36 - INFO - codeparrot_training - Step 43941: {'lr': 0.0004072984774646811, 'samples': 22498304, 'steps': 43941, 'loss/train': 0.9718369245529175}
-03/05/2022 17:07:39 - INFO - codeparrot_training - Step 43942: {'lr': 0.0004072943527708659, 'samples': 22498816, 'steps': 43942, 'loss/train': 2.0765297412872314}
-03/05/2022 17:07:42 - INFO - codeparrot_training - Step 43943: {'lr': 0.00040729022800617637, 'samples': 22499328, 'steps': 43943, 'loss/train': 0.7074843645095825}
-03/05/2022 17:07:43 - INFO - codeparrot_training - Skipping example with length 345 (seq_length=1024)
-03/05/2022 17:07:47 - INFO - codeparrot_training - Step 43944: {'lr': 0.00040728610317061433, 'samples': 22499840, 'steps': 43944, 'loss/train': 1.1918139457702637}
-03/05/2022 17:07:51 - INFO - codeparrot_training - Step 43945: {'lr': 0.0004072819782641816, 'samples': 22500352, 'steps': 43945, 'loss/train': 2.35152268409729}
-03/05/2022 17:07:51 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 17:07:56 - INFO - codeparrot_training - Step 43946: {'lr': 0.00040727785328687995, 'samples': 22500864, 'steps': 43946, 'loss/train': 1.532765507698059}
-03/05/2022 17:07:59 - INFO - codeparrot_training - Step 43947: {'lr': 0.00040727372823871135, 'samples': 22501376, 'steps': 43947, 'loss/train': 1.9196816682815552}
-03/05/2022 17:08:00 - INFO - codeparrot_training - Skipping example with length 869 (seq_length=1024)
-03/05/2022 17:08:04 - INFO - codeparrot_training - Step 43948: {'lr': 0.00040726960311967766, 'samples': 22501888, 'steps': 43948, 'loss/train': 0.8873307704925537}
-03/05/2022 17:08:08 - INFO - codeparrot_training - Step 43949: {'lr': 0.0004072654779297807, 'samples': 22502400, 'steps': 43949, 'loss/train': 2.539391040802002}
-03/05/2022 17:08:08 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 17:08:13 - INFO - codeparrot_training - Step 43950: {'lr': 0.0004072613526690223, 'samples': 22502912, 'steps': 43950, 'loss/train': 2.182304859161377}
-03/05/2022 17:08:16 - INFO - codeparrot_training - Step 43951: {'lr': 0.00040725722733740444, 'samples': 22503424, 'steps': 43951, 'loss/train': 1.8063043355941772}
-03/05/2022 17:08:16 - INFO - codeparrot_training - Skipping example with length 862 (seq_length=1024)
-03/05/2022 17:08:21 - INFO - codeparrot_training - Step 43952: {'lr': 0.0004072531019349289, 'samples': 22503936, 'steps': 43952, 'loss/train': 0.6131553649902344}
-03/05/2022 17:08:24 - INFO - codeparrot_training - Skipping example with length 650 (seq_length=1024)
-03/05/2022 17:08:27 - INFO - codeparrot_training - Step 43953: {'lr': 0.00040724897646159753, 'samples': 22504448, 'steps': 43953, 'loss/train': 1.4741004705429077}
-03/05/2022 17:08:30 - INFO - codeparrot_training - Step 43954: {'lr': 0.0004072448509174121, 'samples': 22504960, 'steps': 43954, 'loss/train': 0.5555626749992371}
-03/05/2022 17:08:33 - INFO - codeparrot_training - Step 43955: {'lr': 0.00040724072530237465, 'samples': 22505472, 'steps': 43955, 'loss/train': 1.4066179990768433}
-03/05/2022 17:08:33 - INFO - codeparrot_training - Skipping example with length 131 (seq_length=1024)
-03/05/2022 17:08:38 - INFO - codeparrot_training - Step 43956: {'lr': 0.00040723659961648694, 'samples': 22505984, 'steps': 43956, 'loss/train': 1.3820515871047974}
-03/05/2022 17:08:41 - INFO - codeparrot_training - Skipping example with length 747 (seq_length=1024)
-03/05/2022 17:08:44 - INFO - codeparrot_training - Step 43957: {'lr': 0.0004072324738597509, 'samples': 22506496, 'steps': 43957, 'loss/train': 1.2527287006378174}
-03/05/2022 17:08:47 - INFO - codeparrot_training - Step 43958: {'lr': 0.00040722834803216834, 'samples': 22507008, 'steps': 43958, 'loss/train': 1.0778868198394775}
-03/05/2022 17:08:50 - INFO - codeparrot_training - Step 43959: {'lr': 0.000407224222133741, 'samples': 22507520, 'steps': 43959, 'loss/train': 1.3982579708099365}
-03/05/2022 17:08:50 - INFO - codeparrot_training - Skipping example with length 1018 (seq_length=1024)
-03/05/2022 17:08:56 - INFO - codeparrot_training - Step 43960: {'lr': 0.00040722009616447094, 'samples': 22508032, 'steps': 43960, 'loss/train': 1.528932809829712}
-03/05/2022 17:08:59 - INFO - codeparrot_training - Step 43961: {'lr': 0.0004072159701243599, 'samples': 22508544, 'steps': 43961, 'loss/train': 1.5923629999160767}
-03/05/2022 17:09:01 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 17:09:04 - INFO - codeparrot_training - Step 43962: {'lr': 0.00040721184401340977, 'samples': 22509056, 'steps': 43962, 'loss/train': 2.082003355026245}
-03/05/2022 17:09:07 - INFO - codeparrot_training - Step 43963: {'lr': 0.00040720771783162236, 'samples': 22509568, 'steps': 43963, 'loss/train': 1.7758045196533203}
-03/05/2022 17:09:09 - INFO - codeparrot_training - Skipping example with length 91 (seq_length=1024)
-03/05/2022 17:09:12 - INFO - codeparrot_training - Step 43964: {'lr': 0.0004072035915789997, 'samples': 22510080, 'steps': 43964, 'loss/train': 1.9124915599822998}
-03/05/2022 17:09:16 - INFO - codeparrot_training - Step 43965: {'lr': 0.0004071994652555434, 'samples': 22510592, 'steps': 43965, 'loss/train': 0.6017963290214539}
-03/05/2022 17:09:17 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/05/2022 17:09:21 - INFO - codeparrot_training - Step 43966: {'lr': 0.0004071953388612555, 'samples': 22511104, 'steps': 43966, 'loss/train': 0.23642615973949432}
-03/05/2022 17:09:24 - INFO - codeparrot_training - Step 43967: {'lr': 0.0004071912123961379, 'samples': 22511616, 'steps': 43967, 'loss/train': 1.3218365907669067}
-03/05/2022 17:09:26 - INFO - codeparrot_training - Skipping example with length 620 (seq_length=1024)
-03/05/2022 17:09:29 - INFO - codeparrot_training - Step 43968: {'lr': 0.00040718708586019226, 'samples': 22512128, 'steps': 43968, 'loss/train': 0.8795645236968994}
-03/05/2022 17:09:32 - INFO - codeparrot_training - Step 43969: {'lr': 0.00040718295925342053, 'samples': 22512640, 'steps': 43969, 'loss/train': 1.238362193107605}
-03/05/2022 17:09:34 - INFO - codeparrot_training - Skipping example with length 401 (seq_length=1024)
-03/05/2022 17:09:38 - INFO - codeparrot_training - Step 43970: {'lr': 0.0004071788325758246, 'samples': 22513152, 'steps': 43970, 'loss/train': 1.7536237239837646}
-03/05/2022 17:09:41 - INFO - codeparrot_training - Step 43971: {'lr': 0.00040717470582740634, 'samples': 22513664, 'steps': 43971, 'loss/train': 1.5556763410568237}
-03/05/2022 17:09:42 - INFO - codeparrot_training - Skipping example with length 637 (seq_length=1024)
-03/05/2022 17:09:46 - INFO - codeparrot_training - Step 43972: {'lr': 0.0004071705790081676, 'samples': 22514176, 'steps': 43972, 'loss/train': 1.7886947393417358}
-03/05/2022 17:09:49 - INFO - codeparrot_training - Step 43973: {'lr': 0.0004071664521181102, 'samples': 22514688, 'steps': 43973, 'loss/train': 1.4601370096206665}
-03/05/2022 17:09:50 - INFO - codeparrot_training - Skipping example with length 87 (seq_length=1024)
-03/05/2022 17:09:55 - INFO - codeparrot_training - Step 43974: {'lr': 0.00040716232515723596, 'samples': 22515200, 'steps': 43974, 'loss/train': 0.8933852314949036}
-03/05/2022 17:09:58 - INFO - codeparrot_training - Step 43975: {'lr': 0.00040715819812554686, 'samples': 22515712, 'steps': 43975, 'loss/train': 0.851549506187439}
-03/05/2022 17:10:01 - INFO - codeparrot_training - Step 43976: {'lr': 0.0004071540710230447, 'samples': 22516224, 'steps': 43976, 'loss/train': 1.2024188041687012}
-03/05/2022 17:10:02 - INFO - codeparrot_training - Skipping example with length 395 (seq_length=1024)
-03/05/2022 17:10:07 - INFO - codeparrot_training - Step 43977: {'lr': 0.0004071499438497314, 'samples': 22516736, 'steps': 43977, 'loss/train': 1.3647747039794922}
-03/05/2022 17:10:10 - INFO - codeparrot_training - Step 43978: {'lr': 0.0004071458166056087, 'samples': 22517248, 'steps': 43978, 'loss/train': 1.0749295949935913}
-03/05/2022 17:10:11 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/05/2022 17:10:15 - INFO - codeparrot_training - Step 43979: {'lr': 0.00040714168929067854, 'samples': 22517760, 'steps': 43979, 'loss/train': 1.9677598476409912}
-03/05/2022 17:10:18 - INFO - codeparrot_training - Step 43980: {'lr': 0.0004071375619049427, 'samples': 22518272, 'steps': 43980, 'loss/train': 1.8645962476730347}
-03/05/2022 17:10:19 - INFO - codeparrot_training - Skipping example with length 72 (seq_length=1024)
-03/05/2022 17:10:24 - INFO - codeparrot_training - Step 43981: {'lr': 0.0004071334344484031, 'samples': 22518784, 'steps': 43981, 'loss/train': 2.1337404251098633}
-03/05/2022 17:10:27 - INFO - codeparrot_training - Step 43982: {'lr': 0.00040712930692106164, 'samples': 22519296, 'steps': 43982, 'loss/train': 1.523332118988037}
-03/05/2022 17:10:27 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 17:10:32 - INFO - codeparrot_training - Step 43983: {'lr': 0.00040712517932292016, 'samples': 22519808, 'steps': 43983, 'loss/train': 1.663478136062622}
-03/05/2022 17:10:35 - INFO - codeparrot_training - Step 43984: {'lr': 0.00040712105165398044, 'samples': 22520320, 'steps': 43984, 'loss/train': 1.6610372066497803}
-03/05/2022 17:10:36 - INFO - codeparrot_training - Skipping example with length 770 (seq_length=1024)
-03/05/2022 17:10:41 - INFO - codeparrot_training - Step 43985: {'lr': 0.0004071169239142445, 'samples': 22520832, 'steps': 43985, 'loss/train': 1.7040987014770508}
-03/05/2022 17:10:44 - INFO - codeparrot_training - Step 43986: {'lr': 0.000407112796103714, 'samples': 22521344, 'steps': 43986, 'loss/train': 1.4652185440063477}
-03/05/2022 17:10:44 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 17:10:49 - INFO - codeparrot_training - Step 43987: {'lr': 0.0004071086682223909, 'samples': 22521856, 'steps': 43987, 'loss/train': 1.0532896518707275}
-03/05/2022 17:10:52 - INFO - codeparrot_training - Step 43988: {'lr': 0.0004071045402702771, 'samples': 22522368, 'steps': 43988, 'loss/train': 2.0892438888549805}
-03/05/2022 17:10:53 - INFO - codeparrot_training - Skipping example with length 780 (seq_length=1024)
-03/05/2022 17:10:57 - INFO - codeparrot_training - Step 43989: {'lr': 0.0004071004122473744, 'samples': 22522880, 'steps': 43989, 'loss/train': 1.956278681755066}
-03/05/2022 17:11:01 - INFO - codeparrot_training - Step 43990: {'lr': 0.0004070962841536847, 'samples': 22523392, 'steps': 43990, 'loss/train': 2.181784152984619}
-03/05/2022 17:11:01 - INFO - codeparrot_training - Skipping example with length 391 (seq_length=1024)
-03/05/2022 17:11:06 - INFO - codeparrot_training - Step 43991: {'lr': 0.0004070921559892098, 'samples': 22523904, 'steps': 43991, 'loss/train': 1.472664713859558}
-03/05/2022 17:11:09 - INFO - codeparrot_training - Step 43992: {'lr': 0.00040708802775395165, 'samples': 22524416, 'steps': 43992, 'loss/train': 1.005934238433838}
-03/05/2022 17:11:10 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 17:11:15 - INFO - codeparrot_training - Step 43993: {'lr': 0.000407083899447912, 'samples': 22524928, 'steps': 43993, 'loss/train': 2.130798578262329}
-03/05/2022 17:11:18 - INFO - codeparrot_training - Step 43994: {'lr': 0.00040707977107109285, 'samples': 22525440, 'steps': 43994, 'loss/train': 1.9464563131332397}
-03/05/2022 17:11:18 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 17:11:23 - INFO - codeparrot_training - Step 43995: {'lr': 0.00040707564262349594, 'samples': 22525952, 'steps': 43995, 'loss/train': 1.53965163230896}
-03/05/2022 17:11:26 - INFO - codeparrot_training - Step 43996: {'lr': 0.0004070715141051231, 'samples': 22526464, 'steps': 43996, 'loss/train': 1.7634841203689575}
-03/05/2022 17:11:27 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/05/2022 17:11:32 - INFO - codeparrot_training - Step 43997: {'lr': 0.00040706738551597634, 'samples': 22526976, 'steps': 43997, 'loss/train': 1.2593517303466797}
-03/05/2022 17:11:35 - INFO - codeparrot_training - Step 43998: {'lr': 0.0004070632568560574, 'samples': 22527488, 'steps': 43998, 'loss/train': 1.8829329013824463}
-03/05/2022 17:11:35 - INFO - codeparrot_training - Skipping example with length 436 (seq_length=1024)
-03/05/2022 17:11:40 - INFO - codeparrot_training - Step 43999: {'lr': 0.0004070591281253682, 'samples': 22528000, 'steps': 43999, 'loss/train': 0.640451192855835}
-03/05/2022 17:11:43 - INFO - codeparrot_training - Step 44000: {'lr': 0.0004070549993239106, 'samples': 22528512, 'steps': 44000, 'loss/train': 1.8574333190917969}
-03/05/2022 17:11:43 - INFO - codeparrot_training - Skipping example with length 497 (seq_length=1024)
-03/05/2022 17:11:48 - INFO - codeparrot_training - Step 44001: {'lr': 0.0004070508704516864, 'samples': 22529024, 'steps': 44001, 'loss/train': 2.269308567047119}
-03/05/2022 17:11:51 - INFO - codeparrot_training - Step 44002: {'lr': 0.00040704674150869753, 'samples': 22529536, 'steps': 44002, 'loss/train': 1.8191622495651245}
-03/05/2022 17:11:52 - INFO - codeparrot_training - Skipping example with length 335 (seq_length=1024)
-03/05/2022 17:11:57 - INFO - codeparrot_training - Step 44003: {'lr': 0.0004070426124949458, 'samples': 22530048, 'steps': 44003, 'loss/train': 2.4811599254608154}
-03/05/2022 17:12:00 - INFO - codeparrot_training - Step 44004: {'lr': 0.00040703848341043313, 'samples': 22530560, 'steps': 44004, 'loss/train': 2.2507011890411377}
-03/05/2022 17:12:00 - INFO - codeparrot_training - Skipping example with length 742 (seq_length=1024)
-03/05/2022 17:12:05 - INFO - codeparrot_training - Step 44005: {'lr': 0.00040703435425516136, 'samples': 22531072, 'steps': 44005, 'loss/train': 1.3918503522872925}
-03/05/2022 17:12:08 - INFO - codeparrot_training - Step 44006: {'lr': 0.0004070302250291322, 'samples': 22531584, 'steps': 44006, 'loss/train': 1.966025710105896}
-03/05/2022 17:12:08 - INFO - codeparrot_training - Skipping example with length 467 (seq_length=1024)
-03/05/2022 17:12:14 - INFO - codeparrot_training - Step 44007: {'lr': 0.0004070260957323478, 'samples': 22532096, 'steps': 44007, 'loss/train': 1.8530805110931396}
-03/05/2022 17:12:17 - INFO - codeparrot_training - Step 44008: {'lr': 0.0004070219663648098, 'samples': 22532608, 'steps': 44008, 'loss/train': 2.3798091411590576}
-03/05/2022 17:12:18 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/05/2022 17:12:22 - INFO - codeparrot_training - Step 44009: {'lr': 0.0004070178369265201, 'samples': 22533120, 'steps': 44009, 'loss/train': 1.4462999105453491}
-03/05/2022 17:12:25 - INFO - codeparrot_training - Step 44010: {'lr': 0.00040701370741748057, 'samples': 22533632, 'steps': 44010, 'loss/train': 1.7006003856658936}
-03/05/2022 17:12:26 - INFO - codeparrot_training - Skipping example with length 505 (seq_length=1024)
-03/05/2022 17:12:31 - INFO - codeparrot_training - Step 44011: {'lr': 0.0004070095778376932, 'samples': 22534144, 'steps': 44011, 'loss/train': 1.4745851755142212}
-03/05/2022 17:12:34 - INFO - codeparrot_training - Step 44012: {'lr': 0.0004070054481871597, 'samples': 22534656, 'steps': 44012, 'loss/train': 2.1193764209747314}
-03/05/2022 17:12:34 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/05/2022 17:12:39 - INFO - codeparrot_training - Step 44013: {'lr': 0.00040700131846588185, 'samples': 22535168, 'steps': 44013, 'loss/train': 1.8424246311187744}
-03/05/2022 17:12:42 - INFO - codeparrot_training - Step 44014: {'lr': 0.0004069971886738617, 'samples': 22535680, 'steps': 44014, 'loss/train': 2.0649259090423584}
-03/05/2022 17:12:43 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 17:12:47 - INFO - codeparrot_training - Step 44015: {'lr': 0.00040699305881110103, 'samples': 22536192, 'steps': 44015, 'loss/train': 1.8393774032592773}
-03/05/2022 17:12:51 - INFO - codeparrot_training - Step 44016: {'lr': 0.00040698892887760174, 'samples': 22536704, 'steps': 44016, 'loss/train': 1.8186222314834595}
-03/05/2022 17:12:51 - INFO - codeparrot_training - Skipping example with length 232 (seq_length=1024)
-03/05/2022 17:12:56 - INFO - codeparrot_training - Step 44017: {'lr': 0.00040698479887336567, 'samples': 22537216, 'steps': 44017, 'loss/train': 1.9768949747085571}
-03/05/2022 17:12:59 - INFO - codeparrot_training - Step 44018: {'lr': 0.00040698066879839463, 'samples': 22537728, 'steps': 44018, 'loss/train': 1.4789793491363525}
-03/05/2022 17:13:00 - INFO - codeparrot_training - Skipping example with length 70 (seq_length=1024)
-03/05/2022 17:13:04 - INFO - codeparrot_training - Step 44019: {'lr': 0.00040697653865269057, 'samples': 22538240, 'steps': 44019, 'loss/train': 1.7451080083847046}
-03/05/2022 17:13:08 - INFO - codeparrot_training - Step 44020: {'lr': 0.00040697240843625527, 'samples': 22538752, 'steps': 44020, 'loss/train': 1.9882631301879883}
-03/05/2022 17:13:08 - INFO - codeparrot_training - Skipping example with length 162 (seq_length=1024)
-03/05/2022 17:13:13 - INFO - codeparrot_training - Step 44021: {'lr': 0.00040696827814909063, 'samples': 22539264, 'steps': 44021, 'loss/train': 1.2893009185791016}
-03/05/2022 17:13:16 - INFO - codeparrot_training - Step 44022: {'lr': 0.0004069641477911985, 'samples': 22539776, 'steps': 44022, 'loss/train': 1.097474217414856}
-03/05/2022 17:13:16 - INFO - codeparrot_training - Skipping example with length 884 (seq_length=1024)
-03/05/2022 17:13:21 - INFO - codeparrot_training - Step 44023: {'lr': 0.00040696001736258077, 'samples': 22540288, 'steps': 44023, 'loss/train': 1.616531491279602}
-03/05/2022 17:13:24 - INFO - codeparrot_training - Step 44024: {'lr': 0.0004069558868632393, 'samples': 22540800, 'steps': 44024, 'loss/train': 1.322118878364563}
-03/05/2022 17:13:24 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/05/2022 17:13:30 - INFO - codeparrot_training - Step 44025: {'lr': 0.0004069517562931759, 'samples': 22541312, 'steps': 44025, 'loss/train': 1.130293607711792}
-03/05/2022 17:13:33 - INFO - codeparrot_training - Step 44026: {'lr': 0.0004069476256523924, 'samples': 22541824, 'steps': 44026, 'loss/train': 1.8206464052200317}
-03/05/2022 17:13:33 - INFO - codeparrot_training - Skipping example with length 765 (seq_length=1024)
-03/05/2022 17:13:38 - INFO - codeparrot_training - Step 44027: {'lr': 0.0004069434949408908, 'samples': 22542336, 'steps': 44027, 'loss/train': 0.3178751766681671}
-03/05/2022 17:13:41 - INFO - codeparrot_training - Step 44028: {'lr': 0.0004069393641586728, 'samples': 22542848, 'steps': 44028, 'loss/train': 1.928274393081665}
-03/05/2022 17:13:41 - INFO - codeparrot_training - Skipping example with length 847 (seq_length=1024)
-03/05/2022 17:13:46 - INFO - codeparrot_training - Step 44029: {'lr': 0.00040693523330574043, 'samples': 22543360, 'steps': 44029, 'loss/train': 0.5905219912528992}
-03/05/2022 17:13:49 - INFO - codeparrot_training - Step 44030: {'lr': 0.0004069311023820954, 'samples': 22543872, 'steps': 44030, 'loss/train': 1.8269705772399902}
-03/05/2022 17:13:49 - INFO - codeparrot_training - Skipping example with length 508 (seq_length=1024)
-03/05/2022 17:13:55 - INFO - codeparrot_training - Step 44031: {'lr': 0.0004069269713877397, 'samples': 22544384, 'steps': 44031, 'loss/train': 1.456636905670166}
-03/05/2022 17:13:58 - INFO - codeparrot_training - Step 44032: {'lr': 0.00040692284032267515, 'samples': 22544896, 'steps': 44032, 'loss/train': 1.481444001197815}
-03/05/2022 17:13:58 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/05/2022 17:14:03 - INFO - codeparrot_training - Step 44033: {'lr': 0.0004069187091869035, 'samples': 22545408, 'steps': 44033, 'loss/train': 1.2420271635055542}
-03/05/2022 17:14:07 - INFO - codeparrot_training - Step 44034: {'lr': 0.00040691457798042673, 'samples': 22545920, 'steps': 44034, 'loss/train': 1.7530019283294678}
-03/05/2022 17:14:08 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/05/2022 17:14:12 - INFO - codeparrot_training - Step 44035: {'lr': 0.00040691044670324673, 'samples': 22546432, 'steps': 44035, 'loss/train': 1.104259729385376}
-03/05/2022 17:14:15 - INFO - codeparrot_training - Step 44036: {'lr': 0.00040690631535536526, 'samples': 22546944, 'steps': 44036, 'loss/train': 2.0105106830596924}
-03/05/2022 17:14:16 - INFO - codeparrot_training - Skipping example with length 26 (seq_length=1024)
-03/05/2022 17:14:20 - INFO - codeparrot_training - Step 44037: {'lr': 0.00040690218393678426, 'samples': 22547456, 'steps': 44037, 'loss/train': 1.132739543914795}
-03/05/2022 17:14:24 - INFO - codeparrot_training - Step 44038: {'lr': 0.0004068980524475054, 'samples': 22547968, 'steps': 44038, 'loss/train': 1.4528270959854126}
-03/05/2022 17:14:24 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/05/2022 17:14:29 - INFO - codeparrot_training - Step 44039: {'lr': 0.00040689392088753097, 'samples': 22548480, 'steps': 44039, 'loss/train': 2.0915627479553223}
-03/05/2022 17:14:32 - INFO - codeparrot_training - Step 44040: {'lr': 0.00040688978925686235, 'samples': 22548992, 'steps': 44040, 'loss/train': 0.5961836576461792}
-03/05/2022 17:14:33 - INFO - codeparrot_training - Skipping example with length 805 (seq_length=1024)
-03/05/2022 17:14:37 - INFO - codeparrot_training - Step 44041: {'lr': 0.00040688565755550164, 'samples': 22549504, 'steps': 44041, 'loss/train': 2.7009055614471436}
-03/05/2022 17:14:41 - INFO - codeparrot_training - Step 44042: {'lr': 0.00040688152578345074, 'samples': 22550016, 'steps': 44042, 'loss/train': 2.336779832839966}
-03/05/2022 17:14:42 - INFO - codeparrot_training - Skipping example with length 779 (seq_length=1024)
-03/05/2022 17:14:46 - INFO - codeparrot_training - Step 44043: {'lr': 0.0004068773939407114, 'samples': 22550528, 'steps': 44043, 'loss/train': 2.5585217475891113}
-03/05/2022 17:14:49 - INFO - codeparrot_training - Step 44044: {'lr': 0.0004068732620272856, 'samples': 22551040, 'steps': 44044, 'loss/train': 2.274350881576538}
-03/05/2022 17:14:50 - INFO - codeparrot_training - Skipping example with length 137 (seq_length=1024)
-03/05/2022 17:14:55 - INFO - codeparrot_training - Step 44045: {'lr': 0.000406869130043175, 'samples': 22551552, 'steps': 44045, 'loss/train': 2.3533880710601807}
-03/05/2022 17:14:58 - INFO - codeparrot_training - Step 44046: {'lr': 0.0004068649979883817, 'samples': 22552064, 'steps': 44046, 'loss/train': 0.9152523875236511}
-03/05/2022 17:14:59 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/05/2022 17:15:03 - INFO - codeparrot_training - Step 44047: {'lr': 0.0004068608658629074, 'samples': 22552576, 'steps': 44047, 'loss/train': 1.4622944593429565}
-03/05/2022 17:15:06 - INFO - codeparrot_training - Step 44048: {'lr': 0.000406856733666754, 'samples': 22553088, 'steps': 44048, 'loss/train': 2.484221935272217}
-03/05/2022 17:15:07 - INFO - codeparrot_training - Skipping example with length 789 (seq_length=1024)
-03/05/2022 17:15:12 - INFO - codeparrot_training - Step 44049: {'lr': 0.00040685260139992343, 'samples': 22553600, 'steps': 44049, 'loss/train': 2.119645357131958}
-03/05/2022 17:15:15 - INFO - codeparrot_training - Step 44050: {'lr': 0.00040684846906241745, 'samples': 22554112, 'steps': 44050, 'loss/train': 1.4676960706710815}
-03/05/2022 17:15:16 - INFO - codeparrot_training - Skipping example with length 546 (seq_length=1024)
-03/05/2022 17:15:20 - INFO - codeparrot_training - Step 44051: {'lr': 0.000406844336654238, 'samples': 22554624, 'steps': 44051, 'loss/train': 2.8545725345611572}
-03/05/2022 17:15:23 - INFO - codeparrot_training - Step 44052: {'lr': 0.00040684020417538694, 'samples': 22555136, 'steps': 44052, 'loss/train': 1.3792974948883057}
-03/05/2022 17:15:24 - INFO - codeparrot_training - Skipping example with length 582 (seq_length=1024)
-03/05/2022 17:15:28 - INFO - codeparrot_training - Step 44053: {'lr': 0.00040683607162586604, 'samples': 22555648, 'steps': 44053, 'loss/train': 0.9823753237724304}
-03/05/2022 17:15:32 - INFO - codeparrot_training - Step 44054: {'lr': 0.00040683193900567727, 'samples': 22556160, 'steps': 44054, 'loss/train': 1.8144932985305786}
-03/05/2022 17:15:33 - INFO - codeparrot_training - Skipping example with length 575 (seq_length=1024)
-03/05/2022 17:15:37 - INFO - codeparrot_training - Step 44055: {'lr': 0.00040682780631482243, 'samples': 22556672, 'steps': 44055, 'loss/train': 2.0380773544311523}
-03/05/2022 17:15:40 - INFO - codeparrot_training - Step 44056: {'lr': 0.0004068236735533034, 'samples': 22557184, 'steps': 44056, 'loss/train': 1.3847761154174805}
-03/05/2022 17:15:41 - INFO - codeparrot_training - Skipping example with length 827 (seq_length=1024)
-03/05/2022 17:15:46 - INFO - codeparrot_training - Step 44057: {'lr': 0.00040681954072112206, 'samples': 22557696, 'steps': 44057, 'loss/train': 1.1825686693191528}
-03/05/2022 17:15:49 - INFO - codeparrot_training - Step 44058: {'lr': 0.0004068154078182802, 'samples': 22558208, 'steps': 44058, 'loss/train': 1.8407344818115234}
-03/05/2022 17:15:51 - INFO - codeparrot_training - Skipping example with length 171 (seq_length=1024)
-03/05/2022 17:15:54 - INFO - codeparrot_training - Step 44059: {'lr': 0.00040681127484477983, 'samples': 22558720, 'steps': 44059, 'loss/train': 3.2797741889953613}
-03/05/2022 17:15:57 - INFO - codeparrot_training - Step 44060: {'lr': 0.0004068071418006226, 'samples': 22559232, 'steps': 44060, 'loss/train': 2.179814100265503}
-03/05/2022 17:15:59 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/05/2022 17:16:02 - INFO - codeparrot_training - Step 44061: {'lr': 0.0004068030086858106, 'samples': 22559744, 'steps': 44061, 'loss/train': 0.994735062122345}
-03/05/2022 17:16:06 - INFO - codeparrot_training - Step 44062: {'lr': 0.00040679887550034555, 'samples': 22560256, 'steps': 44062, 'loss/train': 1.9563329219818115}
-03/05/2022 17:16:08 - INFO - codeparrot_training - Skipping example with length 435 (seq_length=1024)
-03/05/2022 17:16:11 - INFO - codeparrot_training - Step 44063: {'lr': 0.0004067947422442293, 'samples': 22560768, 'steps': 44063, 'loss/train': 2.147077798843384}
-03/05/2022 17:16:14 - INFO - codeparrot_training - Step 44064: {'lr': 0.00040679060891746384, 'samples': 22561280, 'steps': 44064, 'loss/train': 1.6807830333709717}
-03/05/2022 17:16:16 - INFO - codeparrot_training - Skipping example with length 715 (seq_length=1024)
-03/05/2022 17:16:19 - INFO - codeparrot_training - Step 44065: {'lr': 0.00040678647552005087, 'samples': 22561792, 'steps': 44065, 'loss/train': 2.1323800086975098}
-03/05/2022 17:16:23 - INFO - codeparrot_training - Step 44066: {'lr': 0.00040678234205199237, 'samples': 22562304, 'steps': 44066, 'loss/train': 0.7981005311012268}
-03/05/2022 17:16:24 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 17:16:28 - INFO - codeparrot_training - Step 44067: {'lr': 0.0004067782085132902, 'samples': 22562816, 'steps': 44067, 'loss/train': 1.384117841720581}
-03/05/2022 17:16:31 - INFO - codeparrot_training - Step 44068: {'lr': 0.00040677407490394616, 'samples': 22563328, 'steps': 44068, 'loss/train': 1.7643357515335083}
-03/05/2022 17:16:32 - INFO - codeparrot_training - Skipping example with length 155 (seq_length=1024)
-03/05/2022 17:16:37 - INFO - codeparrot_training - Step 44069: {'lr': 0.0004067699412239622, 'samples': 22563840, 'steps': 44069, 'loss/train': 1.6844052076339722}
-03/05/2022 17:16:40 - INFO - codeparrot_training - Step 44070: {'lr': 0.00040676580747334, 'samples': 22564352, 'steps': 44070, 'loss/train': 2.048553705215454}
-03/05/2022 17:16:43 - INFO - codeparrot_training - Step 44071: {'lr': 0.0004067616736520816, 'samples': 22564864, 'steps': 44071, 'loss/train': 0.8057253956794739}
-03/05/2022 17:16:45 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 17:16:49 - INFO - codeparrot_training - Step 44072: {'lr': 0.0004067575397601888, 'samples': 22565376, 'steps': 44072, 'loss/train': 1.9531939029693604}
-03/05/2022 17:16:52 - INFO - codeparrot_training - Step 44073: {'lr': 0.0004067534057976635, 'samples': 22565888, 'steps': 44073, 'loss/train': 1.8498653173446655}
-03/05/2022 17:16:54 - INFO - codeparrot_training - Skipping example with length 196 (seq_length=1024)
-03/05/2022 17:16:57 - INFO - codeparrot_training - Step 44074: {'lr': 0.0004067492717645075, 'samples': 22566400, 'steps': 44074, 'loss/train': 1.168759822845459}
-03/05/2022 17:17:01 - INFO - codeparrot_training - Step 44075: {'lr': 0.00040674513766072274, 'samples': 22566912, 'steps': 44075, 'loss/train': 1.3275723457336426}
-03/05/2022 17:17:03 - INFO - codeparrot_training - Skipping example with length 393 (seq_length=1024)
-03/05/2022 17:17:06 - INFO - codeparrot_training - Step 44076: {'lr': 0.000406741003486311, 'samples': 22567424, 'steps': 44076, 'loss/train': 1.8722443580627441}
-03/05/2022 17:17:09 - INFO - codeparrot_training - Step 44077: {'lr': 0.00040673686924127416, 'samples': 22567936, 'steps': 44077, 'loss/train': 2.305825710296631}
-03/05/2022 17:17:12 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 17:17:14 - INFO - codeparrot_training - Step 44078: {'lr': 0.0004067327349256142, 'samples': 22568448, 'steps': 44078, 'loss/train': 2.080634832382202}
-03/05/2022 17:17:17 - INFO - codeparrot_training - Step 44079: {'lr': 0.00040672860053933286, 'samples': 22568960, 'steps': 44079, 'loss/train': 0.7083601951599121}
-03/05/2022 17:17:21 - INFO - codeparrot_training - Step 44080: {'lr': 0.00040672446608243194, 'samples': 22569472, 'steps': 44080, 'loss/train': 1.1495527029037476}
-03/05/2022 17:17:21 - INFO - codeparrot_training - Skipping example with length 880 (seq_length=1024)
-03/05/2022 17:17:26 - INFO - codeparrot_training - Step 44081: {'lr': 0.0004067203315549135, 'samples': 22569984, 'steps': 44081, 'loss/train': 1.797181248664856}
-03/05/2022 17:17:29 - INFO - codeparrot_training - Step 44082: {'lr': 0.00040671619695677923, 'samples': 22570496, 'steps': 44082, 'loss/train': 2.24397349357605}
-03/05/2022 17:17:29 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 17:17:34 - INFO - codeparrot_training - Step 44083: {'lr': 0.00040671206228803117, 'samples': 22571008, 'steps': 44083, 'loss/train': 2.1217551231384277}
-03/05/2022 17:17:38 - INFO - codeparrot_training - Step 44084: {'lr': 0.0004067079275486709, 'samples': 22571520, 'steps': 44084, 'loss/train': 1.2476714849472046}
-03/05/2022 17:17:38 - INFO - codeparrot_training - Skipping example with length 445 (seq_length=1024)
-03/05/2022 17:17:43 - INFO - codeparrot_training - Step 44085: {'lr': 0.00040670379273870054, 'samples': 22572032, 'steps': 44085, 'loss/train': 2.2558465003967285}
-03/05/2022 17:17:46 - INFO - codeparrot_training - Step 44086: {'lr': 0.00040669965785812193, 'samples': 22572544, 'steps': 44086, 'loss/train': 1.746035099029541}
-03/05/2022 17:17:46 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/05/2022 17:17:51 - INFO - codeparrot_training - Step 44087: {'lr': 0.00040669552290693677, 'samples': 22573056, 'steps': 44087, 'loss/train': 1.1192668676376343}
-03/05/2022 17:17:54 - INFO - codeparrot_training - Step 44088: {'lr': 0.0004066913878851471, 'samples': 22573568, 'steps': 44088, 'loss/train': 1.8575859069824219}
-03/05/2022 17:17:55 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/05/2022 17:18:00 - INFO - codeparrot_training - Step 44089: {'lr': 0.00040668725279275464, 'samples': 22574080, 'steps': 44089, 'loss/train': 1.3202877044677734}
-03/05/2022 17:18:03 - INFO - codeparrot_training - Step 44090: {'lr': 0.0004066831176297614, 'samples': 22574592, 'steps': 44090, 'loss/train': 1.9421015977859497}
-03/05/2022 17:18:03 - INFO - codeparrot_training - Skipping example with length 18 (seq_length=1024)
-03/05/2022 17:18:08 - INFO - codeparrot_training - Step 44091: {'lr': 0.0004066789823961691, 'samples': 22575104, 'steps': 44091, 'loss/train': 0.726119339466095}
-03/05/2022 17:18:12 - INFO - codeparrot_training - Step 44092: {'lr': 0.00040667484709197967, 'samples': 22575616, 'steps': 44092, 'loss/train': 1.767790675163269}
-03/05/2022 17:18:12 - INFO - codeparrot_training - Skipping example with length 362 (seq_length=1024)
-03/05/2022 17:18:17 - INFO - codeparrot_training - Step 44093: {'lr': 0.00040667071171719503, 'samples': 22576128, 'steps': 44093, 'loss/train': 2.221348524093628}
-03/05/2022 17:18:20 - INFO - codeparrot_training - Step 44094: {'lr': 0.00040666657627181697, 'samples': 22576640, 'steps': 44094, 'loss/train': 1.8517422676086426}
-03/05/2022 17:18:20 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/05/2022 17:18:25 - INFO - codeparrot_training - Step 44095: {'lr': 0.00040666244075584736, 'samples': 22577152, 'steps': 44095, 'loss/train': 1.9456379413604736}
-03/05/2022 17:18:28 - INFO - codeparrot_training - Step 44096: {'lr': 0.000406658305169288, 'samples': 22577664, 'steps': 44096, 'loss/train': 1.577863097190857}
-03/05/2022 17:18:29 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 17:18:34 - INFO - codeparrot_training - Step 44097: {'lr': 0.000406654169512141, 'samples': 22578176, 'steps': 44097, 'loss/train': 2.1799745559692383}
-03/05/2022 17:18:37 - INFO - codeparrot_training - Step 44098: {'lr': 0.0004066500337844078, 'samples': 22578688, 'steps': 44098, 'loss/train': 2.5567805767059326}
-03/05/2022 17:18:39 - INFO - codeparrot_training - Skipping example with length 120 (seq_length=1024)
-03/05/2022 17:18:43 - INFO - codeparrot_training - Step 44099: {'lr': 0.0004066458979860907, 'samples': 22579200, 'steps': 44099, 'loss/train': 0.20462945103645325}
-03/05/2022 17:18:46 - INFO - codeparrot_training - Step 44100: {'lr': 0.00040664176211719136, 'samples': 22579712, 'steps': 44100, 'loss/train': 1.6339561939239502}
-03/05/2022 17:18:48 - INFO - codeparrot_training - Skipping example with length 490 (seq_length=1024)
-03/05/2022 17:18:51 - INFO - codeparrot_training - Step 44101: {'lr': 0.00040663762617771163, 'samples': 22580224, 'steps': 44101, 'loss/train': 2.400203227996826}
-03/05/2022 17:18:54 - INFO - codeparrot_training - Step 44102: {'lr': 0.00040663349016765337, 'samples': 22580736, 'steps': 44102, 'loss/train': 2.187974452972412}
-03/05/2022 17:18:57 - INFO - codeparrot_training - Skipping example with length 654 (seq_length=1024)
-03/05/2022 17:19:00 - INFO - codeparrot_training - Step 44103: {'lr': 0.00040662935408701853, 'samples': 22581248, 'steps': 44103, 'loss/train': 1.8474748134613037}
-03/05/2022 17:19:03 - INFO - codeparrot_training - Step 44104: {'lr': 0.00040662521793580886, 'samples': 22581760, 'steps': 44104, 'loss/train': 1.6552462577819824}
-03/05/2022 17:19:05 - INFO - codeparrot_training - Skipping example with length 132 (seq_length=1024)
-03/05/2022 17:19:08 - INFO - codeparrot_training - Step 44105: {'lr': 0.0004066210817140263, 'samples': 22582272, 'steps': 44105, 'loss/train': 0.7009512186050415}
-03/05/2022 17:19:11 - INFO - codeparrot_training - Step 44106: {'lr': 0.0004066169454216727, 'samples': 22582784, 'steps': 44106, 'loss/train': 1.1058763265609741}
-03/05/2022 17:19:13 - INFO - codeparrot_training - Skipping example with length 251 (seq_length=1024)
-03/05/2022 17:19:17 - INFO - codeparrot_training - Step 44107: {'lr': 0.00040661280905875, 'samples': 22583296, 'steps': 44107, 'loss/train': 1.967161774635315}
-03/05/2022 17:19:20 - INFO - codeparrot_training - Step 44108: {'lr': 0.0004066086726252599, 'samples': 22583808, 'steps': 44108, 'loss/train': 1.7949830293655396}
-03/05/2022 17:19:21 - INFO - codeparrot_training - Skipping example with length 872 (seq_length=1024)
-03/05/2022 17:19:25 - INFO - codeparrot_training - Step 44109: {'lr': 0.0004066045361212043, 'samples': 22584320, 'steps': 44109, 'loss/train': 1.9241244792938232}
-03/05/2022 17:19:28 - INFO - codeparrot_training - Step 44110: {'lr': 0.00040660039954658523, 'samples': 22584832, 'steps': 44110, 'loss/train': 2.247014284133911}
-03/05/2022 17:19:30 - INFO - codeparrot_training - Skipping example with length 900 (seq_length=1024)
-03/05/2022 17:19:33 - INFO - codeparrot_training - Step 44111: {'lr': 0.0004065962629014044, 'samples': 22585344, 'steps': 44111, 'loss/train': 1.7103047370910645}
-03/05/2022 17:19:37 - INFO - codeparrot_training - Step 44112: {'lr': 0.00040659212618566364, 'samples': 22585856, 'steps': 44112, 'loss/train': 1.8774996995925903}
-03/05/2022 17:19:38 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/05/2022 17:19:42 - INFO - codeparrot_training - Step 44113: {'lr': 0.000406587989399365, 'samples': 22586368, 'steps': 44113, 'loss/train': 0.5324177742004395}
-03/05/2022 17:19:45 - INFO - codeparrot_training - Step 44114: {'lr': 0.0004065838525425102, 'samples': 22586880, 'steps': 44114, 'loss/train': 3.025786876678467}
-03/05/2022 17:19:47 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/05/2022 17:19:50 - INFO - codeparrot_training - Step 44115: {'lr': 0.00040657971561510104, 'samples': 22587392, 'steps': 44115, 'loss/train': 1.2008098363876343}
-03/05/2022 17:19:53 - INFO - codeparrot_training - Step 44116: {'lr': 0.00040657557861713956, 'samples': 22587904, 'steps': 44116, 'loss/train': 1.639552116394043}
-03/05/2022 17:19:55 - INFO - codeparrot_training - Skipping example with length 375 (seq_length=1024)
-03/05/2022 17:19:59 - INFO - codeparrot_training - Step 44117: {'lr': 0.00040657144154862746, 'samples': 22588416, 'steps': 44117, 'loss/train': 2.1843345165252686}
-03/05/2022 17:20:02 - INFO - codeparrot_training - Step 44118: {'lr': 0.00040656730440956677, 'samples': 22588928, 'steps': 44118, 'loss/train': 1.7968913316726685}
-03/05/2022 17:20:03 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/05/2022 17:20:07 - INFO - codeparrot_training - Step 44119: {'lr': 0.0004065631671999592, 'samples': 22589440, 'steps': 44119, 'loss/train': 2.2209715843200684}
-03/05/2022 17:20:10 - INFO - codeparrot_training - Step 44120: {'lr': 0.0004065590299198068, 'samples': 22589952, 'steps': 44120, 'loss/train': 1.8904602527618408}
-03/05/2022 17:20:11 - INFO - codeparrot_training - Skipping example with length 507 (seq_length=1024)
-03/05/2022 17:20:16 - INFO - codeparrot_training - Step 44121: {'lr': 0.00040655489256911123, 'samples': 22590464, 'steps': 44121, 'loss/train': 2.152430772781372}
-03/05/2022 17:20:19 - INFO - codeparrot_training - Step 44122: {'lr': 0.00040655075514787445, 'samples': 22590976, 'steps': 44122, 'loss/train': 1.513514757156372}
-03/05/2022 17:20:20 - INFO - codeparrot_training - Skipping example with length 917 (seq_length=1024)
-03/05/2022 17:20:24 - INFO - codeparrot_training - Step 44123: {'lr': 0.0004065466176560983, 'samples': 22591488, 'steps': 44123, 'loss/train': 1.5352094173431396}
-03/05/2022 17:20:27 - INFO - codeparrot_training - Step 44124: {'lr': 0.0004065424800937847, 'samples': 22592000, 'steps': 44124, 'loss/train': 1.9511908292770386}
-03/05/2022 17:20:32 - INFO - codeparrot_training - Step 44125: {'lr': 0.0004065383424609354, 'samples': 22592512, 'steps': 44125, 'loss/train': 2.2775039672851562}
-03/05/2022 17:20:36 - INFO - codeparrot_training - Step 44126: {'lr': 0.00040653420475755245, 'samples': 22593024, 'steps': 44126, 'loss/train': 1.63613760471344}
-03/05/2022 17:20:36 - INFO - codeparrot_training - Skipping example with length 235 (seq_length=1024)
-03/05/2022 17:20:41 - INFO - codeparrot_training - Step 44127: {'lr': 0.0004065300669836375, 'samples': 22593536, 'steps': 44127, 'loss/train': 1.7480061054229736}
-03/05/2022 17:20:44 - INFO - codeparrot_training - Step 44128: {'lr': 0.0004065259291391926, 'samples': 22594048, 'steps': 44128, 'loss/train': 1.218375325202942}
-03/05/2022 17:20:46 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/05/2022 17:20:49 - INFO - codeparrot_training - Step 44129: {'lr': 0.0004065217912242195, 'samples': 22594560, 'steps': 44129, 'loss/train': 1.7834889888763428}
-03/05/2022 17:20:53 - INFO - codeparrot_training - Step 44130: {'lr': 0.00040651765323872, 'samples': 22595072, 'steps': 44130, 'loss/train': 1.6898303031921387}
-03/05/2022 17:20:55 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 17:20:58 - INFO - codeparrot_training - Step 44131: {'lr': 0.0004065135151826962, 'samples': 22595584, 'steps': 44131, 'loss/train': 1.7827272415161133}
-03/05/2022 17:21:01 - INFO - codeparrot_training - Step 44132: {'lr': 0.00040650937705614975, 'samples': 22596096, 'steps': 44132, 'loss/train': 1.8567818403244019}
-03/05/2022 17:21:03 - INFO - codeparrot_training - Skipping example with length 555 (seq_length=1024)
-03/05/2022 17:21:06 - INFO - codeparrot_training - Step 44133: {'lr': 0.0004065052388590826, 'samples': 22596608, 'steps': 44133, 'loss/train': 2.2471628189086914}
-03/05/2022 17:21:10 - INFO - codeparrot_training - Step 44134: {'lr': 0.00040650110059149664, 'samples': 22597120, 'steps': 44134, 'loss/train': 4.080743312835693}
-03/05/2022 17:21:11 - INFO - codeparrot_training - Skipping example with length 544 (seq_length=1024)
-03/05/2022 17:21:15 - INFO - codeparrot_training - Step 44135: {'lr': 0.0004064969622533937, 'samples': 22597632, 'steps': 44135, 'loss/train': 1.1336251497268677}
-03/05/2022 17:21:18 - INFO - codeparrot_training - Step 44136: {'lr': 0.0004064928238447756, 'samples': 22598144, 'steps': 44136, 'loss/train': 2.3095993995666504}
-03/05/2022 17:21:20 - INFO - codeparrot_training - Skipping example with length 149 (seq_length=1024)
-03/05/2022 17:21:23 - INFO - codeparrot_training - Step 44137: {'lr': 0.00040648868536564427, 'samples': 22598656, 'steps': 44137, 'loss/train': 1.6412612199783325}
-03/05/2022 17:21:26 - INFO - codeparrot_training - Step 44138: {'lr': 0.00040648454681600153, 'samples': 22599168, 'steps': 44138, 'loss/train': 1.8414227962493896}
-03/05/2022 17:21:28 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/05/2022 17:21:32 - INFO - codeparrot_training - Step 44139: {'lr': 0.0004064804081958493, 'samples': 22599680, 'steps': 44139, 'loss/train': 2.0570695400238037}
-03/05/2022 17:21:35 - INFO - codeparrot_training - Step 44140: {'lr': 0.00040647626950518945, 'samples': 22600192, 'steps': 44140, 'loss/train': 2.1817712783813477}
-03/05/2022 17:21:37 - INFO - codeparrot_training - Skipping example with length 427 (seq_length=1024)
-03/05/2022 17:21:40 - INFO - codeparrot_training - Step 44141: {'lr': 0.00040647213074402374, 'samples': 22600704, 'steps': 44141, 'loss/train': 1.9372197389602661}
-03/05/2022 17:21:44 - INFO - codeparrot_training - Step 44142: {'lr': 0.0004064679919123541, 'samples': 22601216, 'steps': 44142, 'loss/train': 1.8611416816711426}
-03/05/2022 17:21:46 - INFO - codeparrot_training - Skipping example with length 270 (seq_length=1024)
-03/05/2022 17:21:49 - INFO - codeparrot_training - Step 44143: {'lr': 0.00040646385301018243, 'samples': 22601728, 'steps': 44143, 'loss/train': 0.36438289284706116}
-03/05/2022 17:21:52 - INFO - codeparrot_training - Step 44144: {'lr': 0.0004064597140375105, 'samples': 22602240, 'steps': 44144, 'loss/train': 1.1619759798049927}
-03/05/2022 17:21:56 - INFO - codeparrot_training - Step 44145: {'lr': 0.00040645557499434035, 'samples': 22602752, 'steps': 44145, 'loss/train': 1.7439614534378052}
-03/05/2022 17:21:56 - INFO - codeparrot_training - Skipping example with length 986 (seq_length=1024)
-03/05/2022 17:22:01 - INFO - codeparrot_training - Step 44146: {'lr': 0.0004064514358806737, 'samples': 22603264, 'steps': 44146, 'loss/train': 1.7756513357162476}
-03/05/2022 17:22:04 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/05/2022 17:22:07 - INFO - codeparrot_training - Step 44147: {'lr': 0.00040644729669651235, 'samples': 22603776, 'steps': 44147, 'loss/train': 0.7803305387496948}
-03/05/2022 17:22:10 - INFO - codeparrot_training - Step 44148: {'lr': 0.0004064431574418583, 'samples': 22604288, 'steps': 44148, 'loss/train': 1.7715725898742676}
-03/05/2022 17:22:13 - INFO - codeparrot_training - Step 44149: {'lr': 0.00040643901811671345, 'samples': 22604800, 'steps': 44149, 'loss/train': 2.224050760269165}
-03/05/2022 17:22:15 - INFO - codeparrot_training - Skipping example with length 993 (seq_length=1024)
-03/05/2022 17:22:18 - INFO - codeparrot_training - Step 44150: {'lr': 0.0004064348787210795, 'samples': 22605312, 'steps': 44150, 'loss/train': 0.6646870374679565}
-03/05/2022 17:22:22 - INFO - codeparrot_training - Step 44151: {'lr': 0.0004064307392549585, 'samples': 22605824, 'steps': 44151, 'loss/train': 1.684786319732666}
-03/05/2022 17:22:24 - INFO - codeparrot_training - Skipping example with length 883 (seq_length=1024)
-03/05/2022 17:22:27 - INFO - codeparrot_training - Step 44152: {'lr': 0.00040642659971835217, 'samples': 22606336, 'steps': 44152, 'loss/train': 0.9003918766975403}
-03/05/2022 17:22:30 - INFO - codeparrot_training - Step 44153: {'lr': 0.0004064224601112625, 'samples': 22606848, 'steps': 44153, 'loss/train': 1.4049586057662964}
-03/05/2022 17:22:33 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/05/2022 17:22:35 - INFO - codeparrot_training - Step 44154: {'lr': 0.0004064183204336912, 'samples': 22607360, 'steps': 44154, 'loss/train': 2.39943528175354}
-03/05/2022 17:22:39 - INFO - codeparrot_training - Step 44155: {'lr': 0.00040641418068564024, 'samples': 22607872, 'steps': 44155, 'loss/train': 1.779072642326355}
-03/05/2022 17:22:41 - INFO - codeparrot_training - Skipping example with length 331 (seq_length=1024)
-03/05/2022 17:22:44 - INFO - codeparrot_training - Step 44156: {'lr': 0.0004064100408671114, 'samples': 22608384, 'steps': 44156, 'loss/train': 1.7507083415985107}
-03/05/2022 17:22:47 - INFO - codeparrot_training - Step 44157: {'lr': 0.0004064059009781067, 'samples': 22608896, 'steps': 44157, 'loss/train': 0.24615629017353058}
-03/05/2022 17:22:50 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/05/2022 17:22:52 - INFO - codeparrot_training - Step 44158: {'lr': 0.0004064017610186279, 'samples': 22609408, 'steps': 44158, 'loss/train': 2.985563039779663}
-03/05/2022 17:22:55 - INFO - codeparrot_training - Step 44159: {'lr': 0.00040639762098867684, 'samples': 22609920, 'steps': 44159, 'loss/train': 1.4311683177947998}
-03/05/2022 17:22:58 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 17:23:01 - INFO - codeparrot_training - Step 44160: {'lr': 0.0004063934808882555, 'samples': 22610432, 'steps': 44160, 'loss/train': 2.2088539600372314}
-03/05/2022 17:23:04 - INFO - codeparrot_training - Step 44161: {'lr': 0.0004063893407173656, 'samples': 22610944, 'steps': 44161, 'loss/train': 1.7430106401443481}
-03/05/2022 17:23:06 - INFO - codeparrot_training - Skipping example with length 842 (seq_length=1024)
-03/05/2022 17:23:09 - INFO - codeparrot_training - Step 44162: {'lr': 0.00040638520047600916, 'samples': 22611456, 'steps': 44162, 'loss/train': 1.9264702796936035}
-03/05/2022 17:23:12 - INFO - codeparrot_training - Step 44163: {'lr': 0.00040638106016418785, 'samples': 22611968, 'steps': 44163, 'loss/train': 1.5527173280715942}
-03/05/2022 17:23:15 - INFO - codeparrot_training - Skipping example with length 9 (seq_length=1024)
-03/05/2022 17:23:18 - INFO - codeparrot_training - Step 44164: {'lr': 0.0004063769197819037, 'samples': 22612480, 'steps': 44164, 'loss/train': 1.6649202108383179}
-03/05/2022 17:23:21 - INFO - codeparrot_training - Step 44165: {'lr': 0.0004063727793291585, 'samples': 22612992, 'steps': 44165, 'loss/train': 1.7936458587646484}
-03/05/2022 17:23:23 - INFO - codeparrot_training - Skipping example with length 531 (seq_length=1024)
-03/05/2022 17:23:26 - INFO - codeparrot_training - Step 44166: {'lr': 0.00040636863880595415, 'samples': 22613504, 'steps': 44166, 'loss/train': 1.2894933223724365}
-03/05/2022 17:23:29 - INFO - codeparrot_training - Step 44167: {'lr': 0.0004063644982122926, 'samples': 22614016, 'steps': 44167, 'loss/train': 1.063032627105713}
-03/05/2022 17:23:32 - INFO - codeparrot_training - Skipping example with length 893 (seq_length=1024)
-03/05/2022 17:23:34 - INFO - codeparrot_training - Step 44168: {'lr': 0.00040636035754817545, 'samples': 22614528, 'steps': 44168, 'loss/train': 1.2600059509277344}
-03/05/2022 17:23:38 - INFO - codeparrot_training - Step 44169: {'lr': 0.00040635621681360485, 'samples': 22615040, 'steps': 44169, 'loss/train': 1.1489697694778442}
-03/05/2022 17:23:40 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/05/2022 17:23:43 - INFO - codeparrot_training - Step 44170: {'lr': 0.00040635207600858247, 'samples': 22615552, 'steps': 44170, 'loss/train': 2.1656484603881836}
-03/05/2022 17:23:46 - INFO - codeparrot_training - Step 44171: {'lr': 0.00040634793513311037, 'samples': 22616064, 'steps': 44171, 'loss/train': 1.8448591232299805}
-03/05/2022 17:23:48 - INFO - codeparrot_training - Skipping example with length 388 (seq_length=1024)
-03/05/2022 17:23:51 - INFO - codeparrot_training - Step 44172: {'lr': 0.0004063437941871903, 'samples': 22616576, 'steps': 44172, 'loss/train': 1.7750264406204224}
-03/05/2022 17:23:54 - INFO - codeparrot_training - Step 44173: {'lr': 0.000406339653170824, 'samples': 22617088, 'steps': 44173, 'loss/train': 1.9253851175308228}
-03/05/2022 17:23:57 - INFO - codeparrot_training - Skipping example with length 728 (seq_length=1024)
-03/05/2022 17:24:00 - INFO - codeparrot_training - Step 44174: {'lr': 0.00040633551208401356, 'samples': 22617600, 'steps': 44174, 'loss/train': 1.7712149620056152}
-03/05/2022 17:24:03 - INFO - codeparrot_training - Step 44175: {'lr': 0.0004063313709267607, 'samples': 22618112, 'steps': 44175, 'loss/train': 0.5307133793830872}
-03/05/2022 17:24:05 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/05/2022 17:24:09 - INFO - codeparrot_training - Step 44176: {'lr': 0.0004063272296990674, 'samples': 22618624, 'steps': 44176, 'loss/train': 1.5242984294891357}
-03/05/2022 17:24:12 - INFO - codeparrot_training - Step 44177: {'lr': 0.00040632308840093533, 'samples': 22619136, 'steps': 44177, 'loss/train': 1.6285719871520996}
-03/05/2022 17:24:15 - INFO - codeparrot_training - Step 44178: {'lr': 0.0004063189470323666, 'samples': 22619648, 'steps': 44178, 'loss/train': 0.6017926931381226}
-03/05/2022 17:24:16 - INFO - codeparrot_training - Skipping example with length 111 (seq_length=1024)
-03/05/2022 17:24:20 - INFO - codeparrot_training - Step 44179: {'lr': 0.000406314805593363, 'samples': 22620160, 'steps': 44179, 'loss/train': 0.7794324159622192}
-03/05/2022 17:24:23 - INFO - codeparrot_training - Step 44180: {'lr': 0.00040631066408392636, 'samples': 22620672, 'steps': 44180, 'loss/train': 1.0582078695297241}
-03/05/2022 17:24:24 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/05/2022 17:24:29 - INFO - codeparrot_training - Step 44181: {'lr': 0.0004063065225040584, 'samples': 22621184, 'steps': 44181, 'loss/train': 1.6098616123199463}
-03/05/2022 17:24:32 - INFO - codeparrot_training - Step 44182: {'lr': 0.0004063023808537613, 'samples': 22621696, 'steps': 44182, 'loss/train': 0.9810751676559448}
-03/05/2022 17:24:32 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/05/2022 17:24:37 - INFO - codeparrot_training - Step 44183: {'lr': 0.00040629823913303665, 'samples': 22622208, 'steps': 44183, 'loss/train': 2.161726474761963}
-03/05/2022 17:24:40 - INFO - codeparrot_training - Step 44184: {'lr': 0.0004062940973418865, 'samples': 22622720, 'steps': 44184, 'loss/train': 1.0879919528961182}
-03/05/2022 17:24:42 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/05/2022 17:24:46 - INFO - codeparrot_training - Step 44185: {'lr': 0.00040628995548031254, 'samples': 22623232, 'steps': 44185, 'loss/train': 1.6878407001495361}
-03/05/2022 17:24:49 - INFO - codeparrot_training - Step 44186: {'lr': 0.00040628581354831687, 'samples': 22623744, 'steps': 44186, 'loss/train': 1.3284821510314941}
-03/05/2022 17:24:50 - INFO - codeparrot_training - Skipping example with length 782 (seq_length=1024)
-03/05/2022 17:24:54 - INFO - codeparrot_training - Step 44187: {'lr': 0.0004062816715459011, 'samples': 22624256, 'steps': 44187, 'loss/train': 1.4101626873016357}
-03/05/2022 17:24:57 - INFO - codeparrot_training - Step 44188: {'lr': 0.0004062775294730673, 'samples': 22624768, 'steps': 44188, 'loss/train': 1.5895625352859497}
-03/05/2022 17:24:58 - INFO - codeparrot_training - Skipping example with length 520 (seq_length=1024)
-03/05/2022 17:25:03 - INFO - codeparrot_training - Step 44189: {'lr': 0.0004062733873298172, 'samples': 22625280, 'steps': 44189, 'loss/train': 1.8601839542388916}
-03/05/2022 17:25:06 - INFO - codeparrot_training - Step 44190: {'lr': 0.0004062692451161528, 'samples': 22625792, 'steps': 44190, 'loss/train': 1.711069107055664}
-03/05/2022 17:25:07 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/05/2022 17:25:11 - INFO - codeparrot_training - Step 44191: {'lr': 0.00040626510283207586, 'samples': 22626304, 'steps': 44191, 'loss/train': 2.0865375995635986}
-03/05/2022 17:25:14 - INFO - codeparrot_training - Step 44192: {'lr': 0.00040626096047758823, 'samples': 22626816, 'steps': 44192, 'loss/train': 1.5760648250579834}
-03/05/2022 17:25:15 - INFO - codeparrot_training - Skipping example with length 484 (seq_length=1024)
-03/05/2022 17:25:19 - INFO - codeparrot_training - Step 44193: {'lr': 0.0004062568180526919, 'samples': 22627328, 'steps': 44193, 'loss/train': 2.306217670440674}
-03/05/2022 17:25:23 - INFO - codeparrot_training - Step 44194: {'lr': 0.0004062526755573886, 'samples': 22627840, 'steps': 44194, 'loss/train': 1.9531458616256714}
-03/05/2022 17:25:24 - INFO - codeparrot_training - Skipping example with length 864 (seq_length=1024)
-03/05/2022 17:25:29 - INFO - codeparrot_training - Step 44195: {'lr': 0.00040624853299168025, 'samples': 22628352, 'steps': 44195, 'loss/train': 1.2127224206924438}
-03/05/2022 17:25:32 - INFO - codeparrot_training - Step 44196: {'lr': 0.0004062443903555687, 'samples': 22628864, 'steps': 44196, 'loss/train': 2.1385610103607178}
-03/05/2022 17:25:35 - INFO - codeparrot_training - Step 44197: {'lr': 0.0004062402476490559, 'samples': 22629376, 'steps': 44197, 'loss/train': 1.872276782989502}
-03/05/2022 17:25:35 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/05/2022 17:25:40 - INFO - codeparrot_training - Step 44198: {'lr': 0.00040623610487214366, 'samples': 22629888, 'steps': 44198, 'loss/train': 1.7696211338043213}
-03/05/2022 17:25:43 - INFO - codeparrot_training - Skipping example with length 394 (seq_length=1024)
-03/05/2022 17:25:45 - INFO - codeparrot_training - Step 44199: {'lr': 0.0004062319620248338, 'samples': 22630400, 'steps': 44199, 'loss/train': 1.431330680847168}
-03/05/2022 17:25:49 - INFO - codeparrot_training - Step 44200: {'lr': 0.00040622781910712826, 'samples': 22630912, 'steps': 44200, 'loss/train': 1.4680168628692627}
-03/05/2022 17:25:51 - INFO - codeparrot_training - Skipping example with length 657 (seq_length=1024)
-03/05/2022 17:25:54 - INFO - codeparrot_training - Step 44201: {'lr': 0.00040622367611902886, 'samples': 22631424, 'steps': 44201, 'loss/train': 1.5872743129730225}
-03/05/2022 17:25:57 - INFO - codeparrot_training - Step 44202: {'lr': 0.0004062195330605375, 'samples': 22631936, 'steps': 44202, 'loss/train': 1.863154649734497}
-03/05/2022 17:26:00 - INFO - codeparrot_training - Step 44203: {'lr': 0.000406215389931656, 'samples': 22632448, 'steps': 44203, 'loss/train': 1.862103819847107}
-03/05/2022 17:26:00 - INFO - codeparrot_training - Skipping example with length 479 (seq_length=1024)
-03/05/2022 17:26:06 - INFO - codeparrot_training - Step 44204: {'lr': 0.0004062112467323863, 'samples': 22632960, 'steps': 44204, 'loss/train': 1.1745718717575073}
-03/05/2022 17:26:09 - INFO - codeparrot_training - Step 44205: {'lr': 0.00040620710346273015, 'samples': 22633472, 'steps': 44205, 'loss/train': 2.060042381286621}
-03/05/2022 17:26:09 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/05/2022 17:26:14 - INFO - codeparrot_training - Step 44206: {'lr': 0.00040620296012268956, 'samples': 22633984, 'steps': 44206, 'loss/train': 1.7059396505355835}
-03/05/2022 17:26:17 - INFO - codeparrot_training - Step 44207: {'lr': 0.0004061988167122663, 'samples': 22634496, 'steps': 44207, 'loss/train': 1.564478874206543}
-03/05/2022 17:26:17 - INFO - codeparrot_training - Skipping example with length 136 (seq_length=1024)
-03/05/2022 17:26:23 - INFO - codeparrot_training - Step 44208: {'lr': 0.00040619467323146224, 'samples': 22635008, 'steps': 44208, 'loss/train': 2.2497904300689697}
-03/05/2022 17:26:25 - INFO - codeparrot_training - Skipping example with length 672 (seq_length=1024)
-03/05/2022 17:26:28 - INFO - codeparrot_training - Step 44209: {'lr': 0.0004061905296802793, 'samples': 22635520, 'steps': 44209, 'loss/train': 2.525846242904663}
-03/05/2022 17:26:31 - INFO - codeparrot_training - Step 44210: {'lr': 0.00040618638605871934, 'samples': 22636032, 'steps': 44210, 'loss/train': 1.5402861833572388}
-03/05/2022 17:26:34 - INFO - codeparrot_training - Step 44211: {'lr': 0.00040618224236678413, 'samples': 22636544, 'steps': 44211, 'loss/train': 1.8342820405960083}
-03/05/2022 17:26:34 - INFO - codeparrot_training - Skipping example with length 486 (seq_length=1024)
-03/05/2022 17:26:40 - INFO - codeparrot_training - Step 44212: {'lr': 0.00040617809860447564, 'samples': 22637056, 'steps': 44212, 'loss/train': 1.5014450550079346}
-03/05/2022 17:26:43 - INFO - codeparrot_training - Step 44213: {'lr': 0.00040617395477179577, 'samples': 22637568, 'steps': 44213, 'loss/train': 1.8359342813491821}
-03/05/2022 17:26:43 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/05/2022 17:26:48 - INFO - codeparrot_training - Step 44214: {'lr': 0.0004061698108687463, 'samples': 22638080, 'steps': 44214, 'loss/train': 1.4320462942123413}
-03/05/2022 17:26:51 - INFO - codeparrot_training - Skipping example with length 994 (seq_length=1024)
-03/05/2022 17:26:53 - INFO - codeparrot_training - Step 44215: {'lr': 0.00040616566689532905, 'samples': 22638592, 'steps': 44215, 'loss/train': 1.0408624410629272}
-03/05/2022 17:26:57 - INFO - codeparrot_training - Step 44216: {'lr': 0.00040616152285154607, 'samples': 22639104, 'steps': 44216, 'loss/train': 1.4557064771652222}
-03/05/2022 17:26:59 - INFO - codeparrot_training - Skipping example with length 948 (seq_length=1024)
-03/05/2022 17:27:02 - INFO - codeparrot_training - Step 44217: {'lr': 0.000406157378737399, 'samples': 22639616, 'steps': 44217, 'loss/train': 1.5556249618530273}
-03/05/2022 17:27:05 - INFO - codeparrot_training - Step 44218: {'lr': 0.0004061532345528899, 'samples': 22640128, 'steps': 44218, 'loss/train': 1.7960172891616821}
-03/05/2022 17:27:08 - INFO - codeparrot_training - Step 44219: {'lr': 0.00040614909029802054, 'samples': 22640640, 'steps': 44219, 'loss/train': 1.5340495109558105}
-03/05/2022 17:27:09 - INFO - codeparrot_training - Skipping example with length 837 (seq_length=1024)
-03/05/2022 17:27:14 - INFO - codeparrot_training - Step 44220: {'lr': 0.0004061449459727928, 'samples': 22641152, 'steps': 44220, 'loss/train': 1.5006184577941895}
-03/05/2022 17:27:17 - INFO - codeparrot_training - Step 44221: {'lr': 0.0004061408015772086, 'samples': 22641664, 'steps': 44221, 'loss/train': 0.9735212326049805}
-03/05/2022 17:27:17 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 17:27:22 - INFO - codeparrot_training - Step 44222: {'lr': 0.0004061366571112698, 'samples': 22642176, 'steps': 44222, 'loss/train': 2.436394691467285}
-03/05/2022 17:27:25 - INFO - codeparrot_training - Step 44223: {'lr': 0.0004061325125749781, 'samples': 22642688, 'steps': 44223, 'loss/train': 1.5800831317901611}
-03/05/2022 17:27:25 - INFO - codeparrot_training - Skipping example with length 291 (seq_length=1024)
-03/05/2022 17:27:30 - INFO - codeparrot_training - Step 44224: {'lr': 0.00040612836796833556, 'samples': 22643200, 'steps': 44224, 'loss/train': 2.2592363357543945}
-03/05/2022 17:27:34 - INFO - codeparrot_training - Step 44225: {'lr': 0.000406124223291344, 'samples': 22643712, 'steps': 44225, 'loss/train': 1.3619349002838135}
-03/05/2022 17:27:34 - INFO - codeparrot_training - Skipping example with length 216 (seq_length=1024)
-03/05/2022 17:27:39 - INFO - codeparrot_training - Step 44226: {'lr': 0.0004061200785440052, 'samples': 22644224, 'steps': 44226, 'loss/train': 1.5682839155197144}
-03/05/2022 17:27:42 - INFO - codeparrot_training - Step 44227: {'lr': 0.0004061159337263213, 'samples': 22644736, 'steps': 44227, 'loss/train': 1.3725106716156006}
-03/05/2022 17:27:42 - INFO - codeparrot_training - Skipping example with length 57 (seq_length=1024)
-03/05/2022 17:27:47 - INFO - codeparrot_training - Step 44228: {'lr': 0.0004061117888382938, 'samples': 22645248, 'steps': 44228, 'loss/train': 1.986914038658142}
-03/05/2022 17:27:50 - INFO - codeparrot_training - Step 44229: {'lr': 0.00040610764387992475, 'samples': 22645760, 'steps': 44229, 'loss/train': 1.6895278692245483}
-03/05/2022 17:27:50 - INFO - codeparrot_training - Skipping example with length 236 (seq_length=1024)
-03/05/2022 17:27:56 - INFO - codeparrot_training - Step 44230: {'lr': 0.0004061034988512161, 'samples': 22646272, 'steps': 44230, 'loss/train': 2.2384049892425537}
-03/05/2022 17:27:59 - INFO - codeparrot_training - Step 44231: {'lr': 0.0004060993537521695, 'samples': 22646784, 'steps': 44231, 'loss/train': 1.9903305768966675}
-03/05/2022 17:27:59 - INFO - codeparrot_training - Skipping example with length 792 (seq_length=1024)
-03/05/2022 17:28:04 - INFO - codeparrot_training - Step 44232: {'lr': 0.00040609520858278704, 'samples': 22647296, 'steps': 44232, 'loss/train': 2.9708755016326904}
-03/05/2022 17:28:07 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/05/2022 17:28:10 - INFO - codeparrot_training - Step 44233: {'lr': 0.0004060910633430704, 'samples': 22647808, 'steps': 44233, 'loss/train': 1.7914518117904663}
-03/05/2022 17:28:13 - INFO - codeparrot_training - Step 44234: {'lr': 0.0004060869180330216, 'samples': 22648320, 'steps': 44234, 'loss/train': 1.0123517513275146}
-03/05/2022 17:28:16 - INFO - codeparrot_training - Skipping example with length 839 (seq_length=1024)
-03/05/2022 17:28:18 - INFO - codeparrot_training - Step 44235: {'lr': 0.00040608277265264243, 'samples': 22648832, 'steps': 44235, 'loss/train': 1.6269587278366089}
-03/05/2022 17:28:21 - INFO - codeparrot_training - Step 44236: {'lr': 0.0004060786272019348, 'samples': 22649344, 'steps': 44236, 'loss/train': 1.8582043647766113}
-03/05/2022 17:28:24 - INFO - codeparrot_training - Step 44237: {'lr': 0.00040607448168090044, 'samples': 22649856, 'steps': 44237, 'loss/train': 1.754643201828003}
-03/05/2022 17:28:24 - INFO - codeparrot_training - Skipping example with length 711 (seq_length=1024)
-03/05/2022 17:28:30 - INFO - codeparrot_training - Step 44238: {'lr': 0.00040607033608954136, 'samples': 22650368, 'steps': 44238, 'loss/train': 1.1515828371047974}
-03/05/2022 17:28:33 - INFO - codeparrot_training - Skipping example with length 783 (seq_length=1024)
-03/05/2022 17:28:35 - INFO - codeparrot_training - Step 44239: {'lr': 0.0004060661904278595, 'samples': 22650880, 'steps': 44239, 'loss/train': 0.7805472612380981}
-03/05/2022 17:28:38 - INFO - codeparrot_training - Step 44240: {'lr': 0.0004060620446958565, 'samples': 22651392, 'steps': 44240, 'loss/train': 1.9941775798797607}
-03/05/2022 17:28:41 - INFO - codeparrot_training - Skipping example with length 924 (seq_length=1024)
-03/05/2022 17:28:43 - INFO - codeparrot_training - Step 44241: {'lr': 0.00040605789889353445, 'samples': 22651904, 'steps': 44241, 'loss/train': 1.3391072750091553}
-03/05/2022 17:28:47 - INFO - codeparrot_training - Step 44242: {'lr': 0.00040605375302089507, 'samples': 22652416, 'steps': 44242, 'loss/train': 2.1510162353515625}
-03/05/2022 17:28:49 - INFO - codeparrot_training - Skipping example with length 154 (seq_length=1024)
-03/05/2022 17:28:52 - INFO - codeparrot_training - Step 44243: {'lr': 0.00040604960707794023, 'samples': 22652928, 'steps': 44243, 'loss/train': 1.7340010404586792}
-03/05/2022 17:28:55 - INFO - codeparrot_training - Step 44244: {'lr': 0.00040604546106467196, 'samples': 22653440, 'steps': 44244, 'loss/train': 2.185940980911255}
-03/05/2022 17:28:58 - INFO - codeparrot_training - Step 44245: {'lr': 0.00040604131498109193, 'samples': 22653952, 'steps': 44245, 'loss/train': 1.9358073472976685}
-03/05/2022 17:28:59 - INFO - codeparrot_training - Skipping example with length 527 (seq_length=1024)
-03/05/2022 17:29:04 - INFO - codeparrot_training - Step 44246: {'lr': 0.0004060371688272021, 'samples': 22654464, 'steps': 44246, 'loss/train': 3.466005563735962}
-03/05/2022 17:29:07 - INFO - codeparrot_training - Step 44247: {'lr': 0.00040603302260300435, 'samples': 22654976, 'steps': 44247, 'loss/train': 1.296218991279602}
-03/05/2022 17:29:07 - INFO - codeparrot_training - Skipping example with length 1008 (seq_length=1024)
-03/05/2022 17:29:12 - INFO - codeparrot_training - Step 44248: {'lr': 0.00040602887630850055, 'samples': 22655488, 'steps': 44248, 'loss/train': 2.0522453784942627}
-03/05/2022 17:29:16 - INFO - codeparrot_training - Step 44249: {'lr': 0.0004060247299436925, 'samples': 22656000, 'steps': 44249, 'loss/train': 1.918499231338501}
-03/05/2022 17:29:16 - INFO - codeparrot_training - Skipping example with length 203 (seq_length=1024)
-03/05/2022 17:29:21 - INFO - codeparrot_training - Step 44250: {'lr': 0.0004060205835085821, 'samples': 22656512, 'steps': 44250, 'loss/train': 0.5569151043891907}
-03/05/2022 17:29:24 - INFO - codeparrot_training - Step 44251: {'lr': 0.00040601643700317126, 'samples': 22657024, 'steps': 44251, 'loss/train': 2.1788322925567627}
-03/05/2022 17:29:24 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/05/2022 17:29:29 - INFO - codeparrot_training - Step 44252: {'lr': 0.0004060122904274618, 'samples': 22657536, 'steps': 44252, 'loss/train': 2.37040376663208}
-03/05/2022 17:29:32 - INFO - codeparrot_training - Step 44253: {'lr': 0.0004060081437814557, 'samples': 22658048, 'steps': 44253, 'loss/train': 2.1400182247161865}
-03/05/2022 17:29:33 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/05/2022 17:29:38 - INFO - codeparrot_training - Step 44254: {'lr': 0.00040600399706515466, 'samples': 22658560, 'steps': 44254, 'loss/train': 1.7423216104507446}
-03/05/2022 17:29:41 - INFO - codeparrot_training - Step 44255: {'lr': 0.0004059998502785606, 'samples': 22659072, 'steps': 44255, 'loss/train': 2.2348949909210205}
-03/05/2022 17:29:41 - INFO - codeparrot_training - Skipping example with length 11 (seq_length=1024)
-03/05/2022 17:29:46 - INFO - codeparrot_training - Step 44256: {'lr': 0.0004059957034216755, 'samples': 22659584, 'steps': 44256, 'loss/train': 1.8978272676467896}
-03/05/2022 17:29:49 - INFO - codeparrot_training - Step 44257: {'lr': 0.00040599155649450106, 'samples': 22660096, 'steps': 44257, 'loss/train': 2.0367531776428223}
-03/05/2022 17:29:50 - INFO - codeparrot_training - Skipping example with length 212 (seq_length=1024)
-03/05/2022 17:29:55 - INFO - codeparrot_training - Step 44258: {'lr': 0.00040598740949703927, 'samples': 22660608, 'steps': 44258, 'loss/train': 1.0906745195388794}
-03/05/2022 17:29:58 - INFO - codeparrot_training - Step 44259: {'lr': 0.00040598326242929195, 'samples': 22661120, 'steps': 44259, 'loss/train': 1.2955445051193237}
-03/05/2022 17:29:58 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/05/2022 17:30:03 - INFO - codeparrot_training - Step 44260: {'lr': 0.00040597911529126096, 'samples': 22661632, 'steps': 44260, 'loss/train': 1.4031363725662231}
-03/05/2022 17:30:06 - INFO - codeparrot_training - Step 44261: {'lr': 0.00040597496808294825, 'samples': 22662144, 'steps': 44261, 'loss/train': 1.5550216436386108}
-03/05/2022 17:30:06 - INFO - codeparrot_training - Skipping example with length 412 (seq_length=1024)
-03/05/2022 17:30:12 - INFO - codeparrot_training - Step 44262: {'lr': 0.0004059708208043556, 'samples': 22662656, 'steps': 44262, 'loss/train': 2.021296977996826}
-03/05/2022 17:30:15 - INFO - codeparrot_training - Step 44263: {'lr': 0.00040596667345548486, 'samples': 22663168, 'steps': 44263, 'loss/train': 1.1141352653503418}
-03/05/2022 17:30:15 - INFO - codeparrot_training - Skipping example with length 713 (seq_length=1024)
-03/05/2022 17:30:20 - INFO - codeparrot_training - Step 44264: {'lr': 0.00040596252603633797, 'samples': 22663680, 'steps': 44264, 'loss/train': 1.9386119842529297}
-03/05/2022 17:30:23 - INFO - codeparrot_training - Step 44265: {'lr': 0.0004059583785469168, 'samples': 22664192, 'steps': 44265, 'loss/train': 0.07800960540771484}
-03/05/2022 17:30:24 - INFO - codeparrot_training - Skipping example with length 313 (seq_length=1024)
-03/05/2022 17:30:29 - INFO - codeparrot_training - Step 44266: {'lr': 0.00040595423098722315, 'samples': 22664704, 'steps': 44266, 'loss/train': 1.2277593612670898}
-03/05/2022 17:30:32 - INFO - codeparrot_training - Step 44267: {'lr': 0.000405950083357259, 'samples': 22665216, 'steps': 44267, 'loss/train': 2.001199245452881}
-03/05/2022 17:30:32 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/05/2022 17:30:37 - INFO - codeparrot_training - Step 44268: {'lr': 0.0004059459356570261, 'samples': 22665728, 'steps': 44268, 'loss/train': 1.0723458528518677}
-03/05/2022 17:30:41 - INFO - codeparrot_training - Step 44269: {'lr': 0.00040594178788652636, 'samples': 22666240, 'steps': 44269, 'loss/train': 2.020496129989624}
-03/05/2022 17:30:41 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 17:30:46 - INFO - codeparrot_training - Step 44270: {'lr': 0.00040593764004576166, 'samples': 22666752, 'steps': 44270, 'loss/train': 1.7703511714935303}
-03/05/2022 17:30:49 - INFO - codeparrot_training - Step 44271: {'lr': 0.0004059334921347339, 'samples': 22667264, 'steps': 44271, 'loss/train': 1.4566230773925781}
-03/05/2022 17:30:50 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 17:30:54 - INFO - codeparrot_training - Step 44272: {'lr': 0.00040592934415344486, 'samples': 22667776, 'steps': 44272, 'loss/train': 1.9302688837051392}
-03/05/2022 17:30:58 - INFO - codeparrot_training - Step 44273: {'lr': 0.0004059251961018965, 'samples': 22668288, 'steps': 44273, 'loss/train': 1.6099084615707397}
-03/05/2022 17:30:58 - INFO - codeparrot_training - Skipping example with length 656 (seq_length=1024)
-03/05/2022 17:31:03 - INFO - codeparrot_training - Step 44274: {'lr': 0.00040592104798009066, 'samples': 22668800, 'steps': 44274, 'loss/train': 1.2225390672683716}
-03/05/2022 17:31:06 - INFO - codeparrot_training - Step 44275: {'lr': 0.00040591689978802917, 'samples': 22669312, 'steps': 44275, 'loss/train': 2.022488594055176}
-03/05/2022 17:31:06 - INFO - codeparrot_training - Skipping example with length 855 (seq_length=1024)
-03/05/2022 17:31:11 - INFO - codeparrot_training - Step 44276: {'lr': 0.0004059127515257139, 'samples': 22669824, 'steps': 44276, 'loss/train': 1.531888484954834}
-03/05/2022 17:31:15 - INFO - codeparrot_training - Step 44277: {'lr': 0.0004059086031931468, 'samples': 22670336, 'steps': 44277, 'loss/train': 1.5432149171829224}
-03/05/2022 17:31:15 - INFO - codeparrot_training - Skipping example with length 286 (seq_length=1024)
-03/05/2022 17:31:20 - INFO - codeparrot_training - Step 44278: {'lr': 0.00040590445479032965, 'samples': 22670848, 'steps': 44278, 'loss/train': 1.3079187870025635}
-03/05/2022 17:31:23 - INFO - codeparrot_training - Step 44279: {'lr': 0.0004059003063172644, 'samples': 22671360, 'steps': 44279, 'loss/train': 1.9915398359298706}
-03/05/2022 17:31:24 - INFO - codeparrot_training - Skipping example with length 995 (seq_length=1024)
-03/05/2022 17:31:28 - INFO - codeparrot_training - Step 44280: {'lr': 0.0004058961577739529, 'samples': 22671872, 'steps': 44280, 'loss/train': 2.3141958713531494}
-03/05/2022 17:31:31 - INFO - codeparrot_training - Step 44281: {'lr': 0.00040589200916039703, 'samples': 22672384, 'steps': 44281, 'loss/train': 1.3934261798858643}
-03/05/2022 17:31:32 - INFO - codeparrot_training - Skipping example with length 676 (seq_length=1024)
-03/05/2022 17:31:37 - INFO - codeparrot_training - Step 44282: {'lr': 0.0004058878604765985, 'samples': 22672896, 'steps': 44282, 'loss/train': 1.7871838808059692}
-03/05/2022 17:31:40 - INFO - codeparrot_training - Step 44283: {'lr': 0.00040588371172255936, 'samples': 22673408, 'steps': 44283, 'loss/train': 2.268709182739258}
-03/05/2022 17:31:40 - INFO - codeparrot_training - Skipping example with length 990 (seq_length=1024)
-03/05/2022 17:31:45 - INFO - codeparrot_training - Step 44284: {'lr': 0.0004058795628982814, 'samples': 22673920, 'steps': 44284, 'loss/train': 1.6187013387680054}
-03/05/2022 17:31:48 - INFO - codeparrot_training - Step 44285: {'lr': 0.0004058754140037666, 'samples': 22674432, 'steps': 44285, 'loss/train': 1.9640285968780518}
-03/05/2022 17:31:49 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/05/2022 17:31:54 - INFO - codeparrot_training - Step 44286: {'lr': 0.00040587126503901664, 'samples': 22674944, 'steps': 44286, 'loss/train': 0.9832519888877869}
-03/05/2022 17:31:57 - INFO - codeparrot_training - Step 44287: {'lr': 0.0004058671160040336, 'samples': 22675456, 'steps': 44287, 'loss/train': 0.11797816306352615}
-03/05/2022 17:31:58 - INFO - codeparrot_training - Skipping example with length 234 (seq_length=1024)
-03/05/2022 17:32:03 - INFO - codeparrot_training - Step 44288: {'lr': 0.0004058629668988192, 'samples': 22675968, 'steps': 44288, 'loss/train': 1.7761491537094116}
-03/05/2022 17:32:06 - INFO - codeparrot_training - Step 44289: {'lr': 0.0004058588177233753, 'samples': 22676480, 'steps': 44289, 'loss/train': 2.0908308029174805}
-03/05/2022 17:32:09 - INFO - codeparrot_training - Step 44290: {'lr': 0.0004058546684777039, 'samples': 22676992, 'steps': 44290, 'loss/train': 2.1169846057891846}
-03/05/2022 17:32:10 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/05/2022 17:32:14 - INFO - codeparrot_training - Step 44291: {'lr': 0.0004058505191618067, 'samples': 22677504, 'steps': 44291, 'loss/train': 2.3530478477478027}
-03/05/2022 17:32:18 - INFO - codeparrot_training - Step 44292: {'lr': 0.00040584636977568573, 'samples': 22678016, 'steps': 44292, 'loss/train': 2.309929370880127}
-03/05/2022 17:32:18 - INFO - codeparrot_training - Skipping example with length 466 (seq_length=1024)
-03/05/2022 17:32:23 - INFO - codeparrot_training - Step 44293: {'lr': 0.0004058422203193428, 'samples': 22678528, 'steps': 44293, 'loss/train': 1.1104202270507812}
-03/05/2022 17:32:26 - INFO - codeparrot_training - Step 44294: {'lr': 0.0004058380707927798, 'samples': 22679040, 'steps': 44294, 'loss/train': 1.776258945465088}
-03/05/2022 17:32:26 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 17:32:31 - INFO - codeparrot_training - Step 44295: {'lr': 0.00040583392119599847, 'samples': 22679552, 'steps': 44295, 'loss/train': 1.234447956085205}
-03/05/2022 17:32:34 - INFO - codeparrot_training - Step 44296: {'lr': 0.0004058297715290008, 'samples': 22680064, 'steps': 44296, 'loss/train': 0.7288317680358887}
-03/05/2022 17:32:34 - INFO - codeparrot_training - Skipping example with length 572 (seq_length=1024)
-03/05/2022 17:32:40 - INFO - codeparrot_training - Step 44297: {'lr': 0.00040582562179178864, 'samples': 22680576, 'steps': 44297, 'loss/train': 1.183093547821045}
-03/05/2022 17:32:43 - INFO - codeparrot_training - Step 44298: {'lr': 0.0004058214719843639, 'samples': 22681088, 'steps': 44298, 'loss/train': 1.232583999633789}
-03/05/2022 17:32:43 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/05/2022 17:32:48 - INFO - codeparrot_training - Step 44299: {'lr': 0.0004058173221067284, 'samples': 22681600, 'steps': 44299, 'loss/train': 1.935325026512146}
-03/05/2022 17:32:51 - INFO - codeparrot_training - Skipping example with length 830 (seq_length=1024)
-03/05/2022 17:32:53 - INFO - codeparrot_training - Step 44300: {'lr': 0.00040581317215888403, 'samples': 22682112, 'steps': 44300, 'loss/train': 2.2374117374420166}
-03/05/2022 17:32:57 - INFO - codeparrot_training - Step 44301: {'lr': 0.0004058090221408326, 'samples': 22682624, 'steps': 44301, 'loss/train': 1.585386037826538}
-03/05/2022 17:32:59 - INFO - codeparrot_training - Skipping example with length 606 (seq_length=1024)
-03/05/2022 17:33:02 - INFO - codeparrot_training - Step 44302: {'lr': 0.0004058048720525761, 'samples': 22683136, 'steps': 44302, 'loss/train': 1.8854091167449951}
-03/05/2022 17:33:05 - INFO - codeparrot_training - Step 44303: {'lr': 0.00040580072189411626, 'samples': 22683648, 'steps': 44303, 'loss/train': 1.2929693460464478}
-03/05/2022 17:33:08 - INFO - codeparrot_training - Skipping example with length 634 (seq_length=1024)
-03/05/2022 17:33:10 - INFO - codeparrot_training - Step 44304: {'lr': 0.00040579657166545503, 'samples': 22684160, 'steps': 44304, 'loss/train': 2.6327004432678223}
-03/05/2022 17:33:13 - INFO - codeparrot_training - Step 44305: {'lr': 0.0004057924213665943, 'samples': 22684672, 'steps': 44305, 'loss/train': 2.460472583770752}
-03/05/2022 17:33:16 - INFO - codeparrot_training - Skipping example with length 263 (seq_length=1024)
-03/05/2022 17:33:19 - INFO - codeparrot_training - Step 44306: {'lr': 0.0004057882709975359, 'samples': 22685184, 'steps': 44306, 'loss/train': 1.272274374961853}
-03/05/2022 17:33:22 - INFO - codeparrot_training - Step 44307: {'lr': 0.0004057841205582817, 'samples': 22685696, 'steps': 44307, 'loss/train': 1.69756281375885}
-03/05/2022 17:33:25 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/05/2022 17:33:27 - INFO - codeparrot_training - Step 44308: {'lr': 0.0004057799700488336, 'samples': 22686208, 'steps': 44308, 'loss/train': 2.4113969802856445}
-03/05/2022 17:33:30 - INFO - codeparrot_training - Step 44309: {'lr': 0.0004057758194691934, 'samples': 22686720, 'steps': 44309, 'loss/train': 1.5247724056243896}
-03/05/2022 17:33:33 - INFO - codeparrot_training - Skipping example with length 835 (seq_length=1024)
-03/05/2022 17:33:36 - INFO - codeparrot_training - Step 44310: {'lr': 0.00040577166881936304, 'samples': 22687232, 'steps': 44310, 'loss/train': 1.5832611322402954}
-03/05/2022 17:33:39 - INFO - codeparrot_training - Step 44311: {'lr': 0.0004057675180993444, 'samples': 22687744, 'steps': 44311, 'loss/train': 2.4507689476013184}
-03/05/2022 17:33:42 - INFO - codeparrot_training - Step 44312: {'lr': 0.00040576336730913933, 'samples': 22688256, 'steps': 44312, 'loss/train': 1.8700530529022217}
-03/05/2022 17:33:42 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/05/2022 17:33:47 - INFO - codeparrot_training - Step 44313: {'lr': 0.00040575921644874966, 'samples': 22688768, 'steps': 44313, 'loss/train': 1.8455910682678223}
-03/05/2022 17:33:51 - INFO - codeparrot_training - Step 44314: {'lr': 0.00040575506551817725, 'samples': 22689280, 'steps': 44314, 'loss/train': 1.8016554117202759}
-03/05/2022 17:33:51 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/05/2022 17:33:56 - INFO - codeparrot_training - Step 44315: {'lr': 0.00040575091451742405, 'samples': 22689792, 'steps': 44315, 'loss/train': 1.6167188882827759}
-03/05/2022 17:33:59 - INFO - codeparrot_training - Step 44316: {'lr': 0.0004057467634464919, 'samples': 22690304, 'steps': 44316, 'loss/train': 2.163917303085327}
-03/05/2022 17:33:59 - INFO - codeparrot_training - Skipping example with length 797 (seq_length=1024)
-03/05/2022 17:34:05 - INFO - codeparrot_training - Step 44317: {'lr': 0.00040574261230538267, 'samples': 22690816, 'steps': 44317, 'loss/train': 1.5848383903503418}
-03/05/2022 17:34:08 - INFO - codeparrot_training - Step 44318: {'lr': 0.0004057384610940982, 'samples': 22691328, 'steps': 44318, 'loss/train': 0.7450827956199646}
-03/05/2022 17:34:08 - INFO - codeparrot_training - Skipping example with length 509 (seq_length=1024)
-03/05/2022 17:34:13 - INFO - codeparrot_training - Step 44319: {'lr': 0.0004057343098126404, 'samples': 22691840, 'steps': 44319, 'loss/train': 1.5624040365219116}
-03/05/2022 17:34:16 - INFO - codeparrot_training - Step 44320: {'lr': 0.0004057301584610111, 'samples': 22692352, 'steps': 44320, 'loss/train': 1.9303901195526123}
-03/05/2022 17:34:16 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/05/2022 17:34:21 - INFO - codeparrot_training - Step 44321: {'lr': 0.00040572600703921223, 'samples': 22692864, 'steps': 44321, 'loss/train': 2.0855484008789062}
-03/05/2022 17:34:24 - INFO - codeparrot_training - Skipping example with length 758 (seq_length=1024)
-03/05/2022 17:34:27 - INFO - codeparrot_training - Step 44322: {'lr': 0.0004057218555472456, 'samples': 22693376, 'steps': 44322, 'loss/train': 1.8772763013839722}
-03/05/2022 17:34:30 - INFO - codeparrot_training - Step 44323: {'lr': 0.0004057177039851131, 'samples': 22693888, 'steps': 44323, 'loss/train': 2.0798118114471436}
-03/05/2022 17:34:33 - INFO - codeparrot_training - Skipping example with length 890 (seq_length=1024)
-03/05/2022 17:34:35 - INFO - codeparrot_training - Step 44324: {'lr': 0.00040571355235281657, 'samples': 22694400, 'steps': 44324, 'loss/train': 1.8698501586914062}
-03/05/2022 17:34:38 - INFO - codeparrot_training - Step 44325: {'lr': 0.00040570940065035797, 'samples': 22694912, 'steps': 44325, 'loss/train': 2.201124906539917}
-03/05/2022 17:34:42 - INFO - codeparrot_training - Step 44326: {'lr': 0.0004057052488777392, 'samples': 22695424, 'steps': 44326, 'loss/train': 1.5931663513183594}
-03/05/2022 17:34:42 - INFO - codeparrot_training - Skipping example with length 462 (seq_length=1024)
-03/05/2022 17:34:47 - INFO - codeparrot_training - Step 44327: {'lr': 0.0004057010970349619, 'samples': 22695936, 'steps': 44327, 'loss/train': 1.904085636138916}
-03/05/2022 17:34:50 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/05/2022 17:34:52 - INFO - codeparrot_training - Step 44328: {'lr': 0.00040569694512202815, 'samples': 22696448, 'steps': 44328, 'loss/train': 1.9694002866744995}
-03/05/2022 17:34:55 - INFO - codeparrot_training - Step 44329: {'lr': 0.00040569279313893976, 'samples': 22696960, 'steps': 44329, 'loss/train': 2.118342161178589}
-03/05/2022 17:34:58 - INFO - codeparrot_training - Skipping example with length 474 (seq_length=1024)
-03/05/2022 17:35:01 - INFO - codeparrot_training - Step 44330: {'lr': 0.0004056886410856986, 'samples': 22697472, 'steps': 44330, 'loss/train': 1.8492714166641235}
-03/05/2022 17:35:04 - INFO - codeparrot_training - Step 44331: {'lr': 0.0004056844889623065, 'samples': 22697984, 'steps': 44331, 'loss/train': 1.0148179531097412}
-03/05/2022 17:35:06 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/05/2022 17:35:09 - INFO - codeparrot_training - Step 44332: {'lr': 0.0004056803367687654, 'samples': 22698496, 'steps': 44332, 'loss/train': 3.929713487625122}
-03/05/2022 17:35:12 - INFO - codeparrot_training - Step 44333: {'lr': 0.0004056761845050772, 'samples': 22699008, 'steps': 44333, 'loss/train': 1.8974043130874634}
-03/05/2022 17:35:15 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 17:35:18 - INFO - codeparrot_training - Step 44334: {'lr': 0.0004056720321712436, 'samples': 22699520, 'steps': 44334, 'loss/train': 2.4527041912078857}
-03/05/2022 17:35:21 - INFO - codeparrot_training - Step 44335: {'lr': 0.00040566787976726665, 'samples': 22700032, 'steps': 44335, 'loss/train': 2.197052001953125}
-03/05/2022 17:35:23 - INFO - codeparrot_training - Skipping example with length 71 (seq_length=1024)
-03/05/2022 17:35:26 - INFO - codeparrot_training - Step 44336: {'lr': 0.00040566372729314813, 'samples': 22700544, 'steps': 44336, 'loss/train': 1.222960114479065}
-03/05/2022 17:35:29 - INFO - codeparrot_training - Step 44337: {'lr': 0.00040565957474889, 'samples': 22701056, 'steps': 44337, 'loss/train': 1.3258520364761353}
-03/05/2022 17:35:32 - INFO - codeparrot_training - Skipping example with length 124 (seq_length=1024)
-03/05/2022 17:35:35 - INFO - codeparrot_training - Step 44338: {'lr': 0.000405655422134494, 'samples': 22701568, 'steps': 44338, 'loss/train': 2.017596483230591}
-03/05/2022 17:35:38 - INFO - codeparrot_training - Step 44339: {'lr': 0.0004056512694499621, 'samples': 22702080, 'steps': 44339, 'loss/train': 1.9503427743911743}
-03/05/2022 17:35:40 - INFO - codeparrot_training - Skipping example with length 826 (seq_length=1024)
-03/05/2022 17:35:43 - INFO - codeparrot_training - Step 44340: {'lr': 0.0004056471166952961, 'samples': 22702592, 'steps': 44340, 'loss/train': 1.949346899986267}
-03/05/2022 17:35:46 - INFO - codeparrot_training - Step 44341: {'lr': 0.0004056429638704979, 'samples': 22703104, 'steps': 44341, 'loss/train': 2.3849599361419678}
-03/05/2022 17:35:48 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/05/2022 17:35:51 - INFO - codeparrot_training - Step 44342: {'lr': 0.0004056388109755695, 'samples': 22703616, 'steps': 44342, 'loss/train': 1.7819781303405762}
-03/05/2022 17:35:55 - INFO - codeparrot_training - Step 44343: {'lr': 0.0004056346580105126, 'samples': 22704128, 'steps': 44343, 'loss/train': 1.524506688117981}
-03/05/2022 17:35:57 - INFO - codeparrot_training - Skipping example with length 426 (seq_length=1024)
-03/05/2022 17:36:00 - INFO - codeparrot_training - Step 44344: {'lr': 0.00040563050497532905, 'samples': 22704640, 'steps': 44344, 'loss/train': 1.819542407989502}
-03/05/2022 17:36:03 - INFO - codeparrot_training - Step 44345: {'lr': 0.00040562635187002083, 'samples': 22705152, 'steps': 44345, 'loss/train': 1.957534909248352}
-03/05/2022 17:36:05 - INFO - codeparrot_training - Skipping example with length 858 (seq_length=1024)
-03/05/2022 17:36:09 - INFO - codeparrot_training - Step 44346: {'lr': 0.0004056221986945898, 'samples': 22705664, 'steps': 44346, 'loss/train': 1.6556142568588257}
-03/05/2022 17:36:12 - INFO - codeparrot_training - Step 44347: {'lr': 0.0004056180454490378, 'samples': 22706176, 'steps': 44347, 'loss/train': 0.5252249836921692}
-03/05/2022 17:36:14 - INFO - codeparrot_training - Skipping example with length 163 (seq_length=1024)
-03/05/2022 17:36:17 - INFO - codeparrot_training - Step 44348: {'lr': 0.00040561389213336673, 'samples': 22706688, 'steps': 44348, 'loss/train': 1.2725273370742798}
-03/05/2022 17:36:20 - INFO - codeparrot_training - Step 44349: {'lr': 0.00040560973874757844, 'samples': 22707200, 'steps': 44349, 'loss/train': 1.342358946800232}
-03/05/2022 17:36:23 - INFO - codeparrot_training - Skipping example with length 984 (seq_length=1024)
-03/05/2022 17:36:26 - INFO - codeparrot_training - Step 44350: {'lr': 0.0004056055852916748, 'samples': 22707712, 'steps': 44350, 'loss/train': 3.893906831741333}
-03/05/2022 17:36:29 - INFO - codeparrot_training - Step 44351: {'lr': 0.0004056014317656577, 'samples': 22708224, 'steps': 44351, 'loss/train': 1.267573356628418}
-03/05/2022 17:36:32 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 17:36:34 - INFO - codeparrot_training - Step 44352: {'lr': 0.00040559727816952897, 'samples': 22708736, 'steps': 44352, 'loss/train': 1.8451135158538818}
-03/05/2022 17:36:37 - INFO - codeparrot_training - Step 44353: {'lr': 0.0004055931245032904, 'samples': 22709248, 'steps': 44353, 'loss/train': 1.0475108623504639}
-03/05/2022 17:36:40 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 17:36:43 - INFO - codeparrot_training - Step 44354: {'lr': 0.0004055889707669441, 'samples': 22709760, 'steps': 44354, 'loss/train': 1.7637732028961182}
-03/05/2022 17:36:46 - INFO - codeparrot_training - Step 44355: {'lr': 0.0004055848169604919, 'samples': 22710272, 'steps': 44355, 'loss/train': 1.0791488885879517}
-03/05/2022 17:36:49 - INFO - codeparrot_training - Skipping example with length 514 (seq_length=1024)
-03/05/2022 17:36:51 - INFO - codeparrot_training - Step 44356: {'lr': 0.00040558066308393536, 'samples': 22710784, 'steps': 44356, 'loss/train': 0.8122849464416504}
-03/05/2022 17:36:54 - INFO - codeparrot_training - Step 44357: {'lr': 0.0004055765091372767, 'samples': 22711296, 'steps': 44357, 'loss/train': 1.8502172231674194}
-03/05/2022 17:36:57 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 17:37:00 - INFO - codeparrot_training - Step 44358: {'lr': 0.0004055723551205177, 'samples': 22711808, 'steps': 44358, 'loss/train': 1.2112109661102295}
-03/05/2022 17:37:03 - INFO - codeparrot_training - Step 44359: {'lr': 0.0004055682010336601, 'samples': 22712320, 'steps': 44359, 'loss/train': 1.5805211067199707}
-03/05/2022 17:37:06 - INFO - codeparrot_training - Skipping example with length 350 (seq_length=1024)
-03/05/2022 17:37:08 - INFO - codeparrot_training - Step 44360: {'lr': 0.0004055640468767059, 'samples': 22712832, 'steps': 44360, 'loss/train': 1.5246962308883667}
-03/05/2022 17:37:11 - INFO - codeparrot_training - Step 44361: {'lr': 0.000405559892649657, 'samples': 22713344, 'steps': 44361, 'loss/train': 2.3209383487701416}
-03/05/2022 17:37:14 - INFO - codeparrot_training - Skipping example with length 397 (seq_length=1024)
-03/05/2022 17:37:17 - INFO - codeparrot_training - Step 44362: {'lr': 0.00040555573835251513, 'samples': 22713856, 'steps': 44362, 'loss/train': 0.39647552371025085}
-03/05/2022 17:37:20 - INFO - codeparrot_training - Step 44363: {'lr': 0.00040555158398528237, 'samples': 22714368, 'steps': 44363, 'loss/train': 1.816434383392334}
-03/05/2022 17:37:23 - INFO - codeparrot_training - Skipping example with length 744 (seq_length=1024)
-03/05/2022 17:37:25 - INFO - codeparrot_training - Step 44364: {'lr': 0.0004055474295479603, 'samples': 22714880, 'steps': 44364, 'loss/train': 1.4701064825057983}
-03/05/2022 17:37:28 - INFO - codeparrot_training - Step 44365: {'lr': 0.00040554327504055106, 'samples': 22715392, 'steps': 44365, 'loss/train': 1.8862247467041016}
-03/05/2022 17:37:31 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/05/2022 17:37:34 - INFO - codeparrot_training - Step 44366: {'lr': 0.0004055391204630564, 'samples': 22715904, 'steps': 44366, 'loss/train': 1.5576316118240356}
-03/05/2022 17:37:37 - INFO - codeparrot_training - Step 44367: {'lr': 0.0004055349658154782, 'samples': 22716416, 'steps': 44367, 'loss/train': 1.4703962802886963}
-03/05/2022 17:37:39 - INFO - codeparrot_training - Skipping example with length 591 (seq_length=1024)
-03/05/2022 17:37:42 - INFO - codeparrot_training - Step 44368: {'lr': 0.00040553081109781844, 'samples': 22716928, 'steps': 44368, 'loss/train': 1.6526309251785278}
-03/05/2022 17:37:45 - INFO - codeparrot_training - Step 44369: {'lr': 0.0004055266563100788, 'samples': 22717440, 'steps': 44369, 'loss/train': 1.5990407466888428}
-03/05/2022 17:37:48 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/05/2022 17:37:51 - INFO - codeparrot_training - Step 44370: {'lr': 0.00040552250145226124, 'samples': 22717952, 'steps': 44370, 'loss/train': 1.7175841331481934}
-03/05/2022 17:37:54 - INFO - codeparrot_training - Step 44371: {'lr': 0.0004055183465243676, 'samples': 22718464, 'steps': 44371, 'loss/train': 3.3338072299957275}
-03/05/2022 17:37:56 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/05/2022 17:37:59 - INFO - codeparrot_training - Step 44372: {'lr': 0.0004055141915263999, 'samples': 22718976, 'steps': 44372, 'loss/train': 1.2665890455245972}
-03/05/2022 17:38:02 - INFO - codeparrot_training - Step 44373: {'lr': 0.0004055100364583598, 'samples': 22719488, 'steps': 44373, 'loss/train': 2.001713752746582}
-03/05/2022 17:38:05 - INFO - codeparrot_training - Skipping example with length 61 (seq_length=1024)
-03/05/2022 17:38:07 - INFO - codeparrot_training - Step 44374: {'lr': 0.0004055058813202493, 'samples': 22720000, 'steps': 44374, 'loss/train': 0.5432716608047485}
-03/05/2022 17:38:11 - INFO - codeparrot_training - Step 44375: {'lr': 0.0004055017261120704, 'samples': 22720512, 'steps': 44375, 'loss/train': 1.7799867391586304}
-03/05/2022 17:38:13 - INFO - codeparrot_training - Skipping example with length 566 (seq_length=1024)
-03/05/2022 17:38:16 - INFO - codeparrot_training - Step 44376: {'lr': 0.00040549757083382465, 'samples': 22721024, 'steps': 44376, 'loss/train': 1.4332581758499146}
-03/05/2022 17:38:19 - INFO - codeparrot_training - Step 44377: {'lr': 0.00040549341548551415, 'samples': 22721536, 'steps': 44377, 'loss/train': 1.5444945096969604}
-03/05/2022 17:38:21 - INFO - codeparrot_training - Skipping example with length 491 (seq_length=1024)
-03/05/2022 17:38:24 - INFO - codeparrot_training - Step 44378: {'lr': 0.0004054892600671407, 'samples': 22722048, 'steps': 44378, 'loss/train': 0.9422029852867126}
-03/05/2022 17:38:28 - INFO - codeparrot_training - Step 44379: {'lr': 0.00040548510457870623, 'samples': 22722560, 'steps': 44379, 'loss/train': 1.5879135131835938}
-03/05/2022 17:38:30 - INFO - codeparrot_training - Skipping example with length 195 (seq_length=1024)
-03/05/2022 17:38:33 - INFO - codeparrot_training - Step 44380: {'lr': 0.00040548094902021257, 'samples': 22723072, 'steps': 44380, 'loss/train': 1.230666160583496}
-03/05/2022 17:38:36 - INFO - codeparrot_training - Step 44381: {'lr': 0.00040547679339166155, 'samples': 22723584, 'steps': 44381, 'loss/train': 1.8003977537155151}
-03/05/2022 17:38:39 - INFO - codeparrot_training - Skipping example with length 237 (seq_length=1024)
-03/05/2022 17:38:41 - INFO - codeparrot_training - Step 44382: {'lr': 0.0004054726376930551, 'samples': 22724096, 'steps': 44382, 'loss/train': 1.00468111038208}
-03/05/2022 17:38:45 - INFO - codeparrot_training - Step 44383: {'lr': 0.0004054684819243951, 'samples': 22724608, 'steps': 44383, 'loss/train': 1.1212267875671387}
-03/05/2022 17:38:47 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/05/2022 17:38:50 - INFO - codeparrot_training - Step 44384: {'lr': 0.0004054643260856834, 'samples': 22725120, 'steps': 44384, 'loss/train': 2.0551135540008545}
-03/05/2022 17:38:53 - INFO - codeparrot_training - Step 44385: {'lr': 0.00040546017017692183, 'samples': 22725632, 'steps': 44385, 'loss/train': 2.2011301517486572}
-03/05/2022 17:38:55 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/05/2022 17:38:58 - INFO - codeparrot_training - Step 44386: {'lr': 0.00040545601419811236, 'samples': 22726144, 'steps': 44386, 'loss/train': 1.9660754203796387}
-03/05/2022 17:39:01 - INFO - codeparrot_training - Step 44387: {'lr': 0.00040545185814925676, 'samples': 22726656, 'steps': 44387, 'loss/train': 1.4196072816848755}
-03/05/2022 17:39:04 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/05/2022 17:39:07 - INFO - codeparrot_training - Step 44388: {'lr': 0.00040544770203035705, 'samples': 22727168, 'steps': 44388, 'loss/train': 1.6499969959259033}
-03/05/2022 17:39:10 - INFO - codeparrot_training - Step 44389: {'lr': 0.0004054435458414149, 'samples': 22727680, 'steps': 44389, 'loss/train': 1.765320897102356}
-03/05/2022 17:39:12 - INFO - codeparrot_training - Skipping example with length 296 (seq_length=1024)
-03/05/2022 17:39:15 - INFO - codeparrot_training - Step 44390: {'lr': 0.0004054393895824323, 'samples': 22728192, 'steps': 44390, 'loss/train': 2.1852099895477295}
-03/05/2022 17:39:18 - INFO - codeparrot_training - Step 44391: {'lr': 0.00040543523325341116, 'samples': 22728704, 'steps': 44391, 'loss/train': 1.5233827829360962}
-03/05/2022 17:39:21 - INFO - codeparrot_training - Skipping example with length 376 (seq_length=1024)
-03/05/2022 17:39:24 - INFO - codeparrot_training - Step 44392: {'lr': 0.0004054310768543532, 'samples': 22729216, 'steps': 44392, 'loss/train': 1.9495404958724976}
-03/05/2022 17:39:27 - INFO - codeparrot_training - Step 44393: {'lr': 0.00040542692038526054, 'samples': 22729728, 'steps': 44393, 'loss/train': 1.916357398033142}
-03/05/2022 17:39:29 - INFO - codeparrot_training - Skipping example with length 547 (seq_length=1024)
-03/05/2022 17:39:32 - INFO - codeparrot_training - Step 44394: {'lr': 0.0004054227638461348, 'samples': 22730240, 'steps': 44394, 'loss/train': 1.5309916734695435}
-03/05/2022 17:39:35 - INFO - codeparrot_training - Step 44395: {'lr': 0.000405418607236978, 'samples': 22730752, 'steps': 44395, 'loss/train': 1.7917648553848267}
-03/05/2022 17:39:38 - INFO - codeparrot_training - Skipping example with length 295 (seq_length=1024)
-03/05/2022 17:39:41 - INFO - codeparrot_training - Step 44396: {'lr': 0.00040541445055779197, 'samples': 22731264, 'steps': 44396, 'loss/train': 1.0602810382843018}
-03/05/2022 17:39:44 - INFO - codeparrot_training - Step 44397: {'lr': 0.0004054102938085786, 'samples': 22731776, 'steps': 44397, 'loss/train': 1.4008042812347412}
-03/05/2022 17:39:47 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 17:39:49 - INFO - codeparrot_training - Step 44398: {'lr': 0.0004054061369893397, 'samples': 22732288, 'steps': 44398, 'loss/train': 1.741020917892456}
-03/05/2022 17:39:52 - INFO - codeparrot_training - Step 44399: {'lr': 0.0004054019801000772, 'samples': 22732800, 'steps': 44399, 'loss/train': 1.0626550912857056}
-03/05/2022 17:39:56 - INFO - codeparrot_training - Step 44400: {'lr': 0.00040539782314079304, 'samples': 22733312, 'steps': 44400, 'loss/train': 1.6804600954055786}
-03/05/2022 17:39:56 - INFO - codeparrot_training - Skipping example with length 60 (seq_length=1024)
-03/05/2022 17:40:01 - INFO - codeparrot_training - Step 44401: {'lr': 0.000405393666111489, 'samples': 22733824, 'steps': 44401, 'loss/train': 1.4758058786392212}
-03/05/2022 17:40:04 - INFO - codeparrot_training - Step 44402: {'lr': 0.0004053895090121669, 'samples': 22734336, 'steps': 44402, 'loss/train': 1.4195891618728638}
-03/05/2022 17:40:04 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/05/2022 17:40:09 - INFO - codeparrot_training - Step 44403: {'lr': 0.00040538535184282877, 'samples': 22734848, 'steps': 44403, 'loss/train': 1.4407435655593872}
-03/05/2022 17:40:12 - INFO - codeparrot_training - Skipping example with length 859 (seq_length=1024)
-03/05/2022 17:40:15 - INFO - codeparrot_training - Step 44404: {'lr': 0.00040538119460347636, 'samples': 22735360, 'steps': 44404, 'loss/train': 1.682533860206604}
-03/05/2022 17:40:18 - INFO - codeparrot_training - Step 44405: {'lr': 0.0004053770372941116, 'samples': 22735872, 'steps': 44405, 'loss/train': 2.895479440689087}
-03/05/2022 17:40:21 - INFO - codeparrot_training - Step 44406: {'lr': 0.00040537287991473627, 'samples': 22736384, 'steps': 44406, 'loss/train': 1.7776925563812256}
-03/05/2022 17:40:22 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/05/2022 17:40:27 - INFO - codeparrot_training - Step 44407: {'lr': 0.0004053687224653524, 'samples': 22736896, 'steps': 44407, 'loss/train': 0.8730904459953308}
-03/05/2022 17:40:30 - INFO - codeparrot_training - Step 44408: {'lr': 0.0004053645649459617, 'samples': 22737408, 'steps': 44408, 'loss/train': 1.8097878694534302}
-03/05/2022 17:40:30 - INFO - codeparrot_training - Skipping example with length 347 (seq_length=1024)
-03/05/2022 17:40:35 - INFO - codeparrot_training - Step 44409: {'lr': 0.0004053604073565662, 'samples': 22737920, 'steps': 44409, 'loss/train': 1.6748708486557007}
-03/05/2022 17:40:38 - INFO - codeparrot_training - Step 44410: {'lr': 0.0004053562496971677, 'samples': 22738432, 'steps': 44410, 'loss/train': 1.4018229246139526}
-03/05/2022 17:40:38 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/05/2022 17:40:43 - INFO - codeparrot_training - Step 44411: {'lr': 0.00040535209196776803, 'samples': 22738944, 'steps': 44411, 'loss/train': 1.7083628177642822}
-03/05/2022 17:40:47 - INFO - codeparrot_training - Step 44412: {'lr': 0.00040534793416836915, 'samples': 22739456, 'steps': 44412, 'loss/train': 1.480506420135498}
-03/05/2022 17:40:47 - INFO - codeparrot_training - Skipping example with length 923 (seq_length=1024)
-03/05/2022 17:40:52 - INFO - codeparrot_training - Step 44413: {'lr': 0.00040534377629897276, 'samples': 22739968, 'steps': 44413, 'loss/train': 1.6851592063903809}
-03/05/2022 17:40:55 - INFO - codeparrot_training - Step 44414: {'lr': 0.000405339618359581, 'samples': 22740480, 'steps': 44414, 'loss/train': 0.8146441578865051}
-03/05/2022 17:40:55 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/05/2022 17:41:00 - INFO - codeparrot_training - Step 44415: {'lr': 0.0004053354603501956, 'samples': 22740992, 'steps': 44415, 'loss/train': 2.245663642883301}
-03/05/2022 17:41:03 - INFO - codeparrot_training - Skipping example with length 821 (seq_length=1024)
-03/05/2022 17:41:06 - INFO - codeparrot_training - Step 44416: {'lr': 0.0004053313022708184, 'samples': 22741504, 'steps': 44416, 'loss/train': 1.7629432678222656}
-03/05/2022 17:41:09 - INFO - codeparrot_training - Step 44417: {'lr': 0.00040532714412145135, 'samples': 22742016, 'steps': 44417, 'loss/train': 2.186368227005005}
-03/05/2022 17:41:12 - INFO - codeparrot_training - Skipping example with length 588 (seq_length=1024)
-03/05/2022 17:41:14 - INFO - codeparrot_training - Step 44418: {'lr': 0.0004053229859020962, 'samples': 22742528, 'steps': 44418, 'loss/train': 1.169312834739685}
-03/05/2022 17:41:17 - INFO - codeparrot_training - Step 44419: {'lr': 0.00040531882761275496, 'samples': 22743040, 'steps': 44419, 'loss/train': 1.262188196182251}
-03/05/2022 17:41:20 - INFO - codeparrot_training - Skipping example with length 736 (seq_length=1024)
-03/05/2022 17:41:23 - INFO - codeparrot_training - Step 44420: {'lr': 0.00040531466925342947, 'samples': 22743552, 'steps': 44420, 'loss/train': 1.795200228691101}
-03/05/2022 17:41:26 - INFO - codeparrot_training - Step 44421: {'lr': 0.0004053105108241216, 'samples': 22744064, 'steps': 44421, 'loss/train': 1.1145625114440918}
-03/05/2022 17:41:29 - INFO - codeparrot_training - Step 44422: {'lr': 0.0004053063523248331, 'samples': 22744576, 'steps': 44422, 'loss/train': 1.5458983182907104}
-03/05/2022 17:41:29 - INFO - codeparrot_training - Skipping example with length 339 (seq_length=1024)
-03/05/2022 17:41:34 - INFO - codeparrot_training - Step 44423: {'lr': 0.0004053021937555661, 'samples': 22745088, 'steps': 44423, 'loss/train': 1.9506492614746094}
-03/05/2022 17:41:37 - INFO - codeparrot_training - Step 44424: {'lr': 0.00040529803511632224, 'samples': 22745600, 'steps': 44424, 'loss/train': 2.1964194774627686}
-03/05/2022 17:41:37 - INFO - codeparrot_training - Skipping example with length 791 (seq_length=1024)
-03/05/2022 17:41:43 - INFO - codeparrot_training - Step 44425: {'lr': 0.0004052938764071035, 'samples': 22746112, 'steps': 44425, 'loss/train': 1.9158647060394287}
-03/05/2022 17:41:46 - INFO - codeparrot_training - Step 44426: {'lr': 0.00040528971762791177, 'samples': 22746624, 'steps': 44426, 'loss/train': 1.4619933366775513}
-03/05/2022 17:41:46 - INFO - codeparrot_training - Skipping example with length 831 (seq_length=1024)
-03/05/2022 17:41:51 - INFO - codeparrot_training - Step 44427: {'lr': 0.0004052855587787488, 'samples': 22747136, 'steps': 44427, 'loss/train': 2.0949246883392334}
-03/05/2022 17:41:54 - INFO - codeparrot_training - Step 44428: {'lr': 0.0004052813998596167, 'samples': 22747648, 'steps': 44428, 'loss/train': 0.8605336546897888}
-03/05/2022 17:41:54 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/05/2022 17:42:00 - INFO - codeparrot_training - Step 44429: {'lr': 0.0004052772408705171, 'samples': 22748160, 'steps': 44429, 'loss/train': 1.686609148979187}
-03/05/2022 17:42:03 - INFO - codeparrot_training - Skipping example with length 200 (seq_length=1024)
-03/05/2022 17:42:05 - INFO - codeparrot_training - Step 44430: {'lr': 0.000405273081811452, 'samples': 22748672, 'steps': 44430, 'loss/train': 1.2404718399047852}
-03/05/2022 17:42:08 - INFO - codeparrot_training - Step 44431: {'lr': 0.0004052689226824232, 'samples': 22749184, 'steps': 44431, 'loss/train': 1.9039555788040161}
-03/05/2022 17:42:11 - INFO - codeparrot_training - Skipping example with length 528 (seq_length=1024)
-03/05/2022 17:42:13 - INFO - codeparrot_training - Step 44432: {'lr': 0.0004052647634834327, 'samples': 22749696, 'steps': 44432, 'loss/train': 1.4113500118255615}
-03/05/2022 17:42:17 - INFO - codeparrot_training - Step 44433: {'lr': 0.00040526060421448216, 'samples': 22750208, 'steps': 44433, 'loss/train': 1.552963137626648}
-03/05/2022 17:42:19 - INFO - codeparrot_training - Skipping example with length 727 (seq_length=1024)
-03/05/2022 17:42:22 - INFO - codeparrot_training - Step 44434: {'lr': 0.00040525644487557366, 'samples': 22750720, 'steps': 44434, 'loss/train': 1.4932875633239746}
-03/05/2022 17:42:25 - INFO - codeparrot_training - Step 44435: {'lr': 0.000405252285466709, 'samples': 22751232, 'steps': 44435, 'loss/train': 1.7451249361038208}
-03/05/2022 17:42:28 - INFO - codeparrot_training - Skipping example with length 239 (seq_length=1024)
-03/05/2022 17:42:30 - INFO - codeparrot_training - Step 44436: {'lr': 0.0004052481259878901, 'samples': 22751744, 'steps': 44436, 'loss/train': 2.5450356006622314}
-03/05/2022 17:42:34 - INFO - codeparrot_training - Step 44437: {'lr': 0.00040524396643911874, 'samples': 22752256, 'steps': 44437, 'loss/train': 1.4278934001922607}
-03/05/2022 17:42:36 - INFO - codeparrot_training - Skipping example with length 769 (seq_length=1024)
-03/05/2022 17:42:39 - INFO - codeparrot_training - Step 44438: {'lr': 0.00040523980682039684, 'samples': 22752768, 'steps': 44438, 'loss/train': 1.8868465423583984}
-03/05/2022 17:42:42 - INFO - codeparrot_training - Step 44439: {'lr': 0.00040523564713172634, 'samples': 22753280, 'steps': 44439, 'loss/train': 1.4967641830444336}
-03/05/2022 17:42:45 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 17:42:47 - INFO - codeparrot_training - Step 44440: {'lr': 0.000405231487373109, 'samples': 22753792, 'steps': 44440, 'loss/train': 1.5777785778045654}
-03/05/2022 17:42:50 - INFO - codeparrot_training - Step 44441: {'lr': 0.00040522732754454674, 'samples': 22754304, 'steps': 44441, 'loss/train': 1.3023382425308228}
-03/05/2022 17:42:53 - INFO - codeparrot_training - Skipping example with length 21 (seq_length=1024)
-03/05/2022 17:42:56 - INFO - codeparrot_training - Step 44442: {'lr': 0.0004052231676460415, 'samples': 22754816, 'steps': 44442, 'loss/train': 1.3849462270736694}
-03/05/2022 17:42:59 - INFO - codeparrot_training - Step 44443: {'lr': 0.000405219007677595, 'samples': 22755328, 'steps': 44443, 'loss/train': 1.744574785232544}
-03/05/2022 17:43:01 - INFO - codeparrot_training - Skipping example with length 668 (seq_length=1024)
-03/05/2022 17:43:04 - INFO - codeparrot_training - Step 44444: {'lr': 0.0004052148476392093, 'samples': 22755840, 'steps': 44444, 'loss/train': 0.7807927131652832}
-03/05/2022 17:43:07 - INFO - codeparrot_training - Step 44445: {'lr': 0.00040521068753088615, 'samples': 22756352, 'steps': 44445, 'loss/train': 1.7067683935165405}
-03/05/2022 17:43:10 - INFO - codeparrot_training - Skipping example with length 477 (seq_length=1024)
-03/05/2022 17:43:13 - INFO - codeparrot_training - Step 44446: {'lr': 0.0004052065273526274, 'samples': 22756864, 'steps': 44446, 'loss/train': 0.7421154379844666}
-03/05/2022 17:43:16 - INFO - codeparrot_training - Step 44447: {'lr': 0.0004052023671044351, 'samples': 22757376, 'steps': 44447, 'loss/train': 1.2303489446640015}
-03/05/2022 17:43:18 - INFO - codeparrot_training - Skipping example with length 608 (seq_length=1024)
-03/05/2022 17:43:21 - INFO - codeparrot_training - Step 44448: {'lr': 0.0004051982067863109, 'samples': 22757888, 'steps': 44448, 'loss/train': 1.8352282047271729}
-03/05/2022 17:43:25 - INFO - codeparrot_training - Step 44449: {'lr': 0.0004051940463982569, 'samples': 22758400, 'steps': 44449, 'loss/train': 2.184796094894409}
-03/05/2022 17:43:27 - INFO - codeparrot_training - Skipping example with length 442 (seq_length=1024)
-03/05/2022 17:43:30 - INFO - codeparrot_training - Step 44450: {'lr': 0.0004051898859402748, 'samples': 22758912, 'steps': 44450, 'loss/train': 1.5347357988357544}
-03/05/2022 17:43:33 - INFO - codeparrot_training - Step 44451: {'lr': 0.00040518572541236653, 'samples': 22759424, 'steps': 44451, 'loss/train': 1.9890998601913452}
-03/05/2022 17:43:36 - INFO - codeparrot_training - Skipping example with length 464 (seq_length=1024)
-03/05/2022 17:43:38 - INFO - codeparrot_training - Step 44452: {'lr': 0.00040518156481453397, 'samples': 22759936, 'steps': 44452, 'loss/train': 1.9883694648742676}
-03/05/2022 17:43:41 - INFO - codeparrot_training - Step 44453: {'lr': 0.0004051774041467789, 'samples': 22760448, 'steps': 44453, 'loss/train': 1.8207718133926392}
-03/05/2022 17:43:44 - INFO - codeparrot_training - Skipping example with length 561 (seq_length=1024)
-03/05/2022 17:43:47 - INFO - codeparrot_training - Step 44454: {'lr': 0.00040517324340910347, 'samples': 22760960, 'steps': 44454, 'loss/train': 1.9154024124145508}
-03/05/2022 17:43:50 - INFO - codeparrot_training - Step 44455: {'lr': 0.0004051690826015092, 'samples': 22761472, 'steps': 44455, 'loss/train': 2.128943681716919}
-03/05/2022 17:43:52 - INFO - codeparrot_training - Skipping example with length 290 (seq_length=1024)
-03/05/2022 17:43:55 - INFO - codeparrot_training - Step 44456: {'lr': 0.0004051649217239982, 'samples': 22761984, 'steps': 44456, 'loss/train': 1.8793174028396606}
-03/05/2022 17:43:58 - INFO - codeparrot_training - Step 44457: {'lr': 0.00040516076077657233, 'samples': 22762496, 'steps': 44457, 'loss/train': 1.732297658920288}
-03/05/2022 17:44:01 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/05/2022 17:44:04 - INFO - codeparrot_training - Step 44458: {'lr': 0.0004051565997592334, 'samples': 22763008, 'steps': 44458, 'loss/train': 1.5476731061935425}
-03/05/2022 17:44:07 - INFO - codeparrot_training - Step 44459: {'lr': 0.0004051524386719832, 'samples': 22763520, 'steps': 44459, 'loss/train': 1.9968795776367188}
-03/05/2022 17:44:09 - INFO - codeparrot_training - Skipping example with length 781 (seq_length=1024)
-03/05/2022 17:44:12 - INFO - codeparrot_training - Step 44460: {'lr': 0.0004051482775148238, 'samples': 22764032, 'steps': 44460, 'loss/train': 0.412308007478714}
-03/05/2022 17:44:15 - INFO - codeparrot_training - Step 44461: {'lr': 0.00040514411628775695, 'samples': 22764544, 'steps': 44461, 'loss/train': 1.6842602491378784}
-03/05/2022 17:44:17 - INFO - codeparrot_training - Skipping example with length 399 (seq_length=1024)
-03/05/2022 17:44:21 - INFO - codeparrot_training - Step 44462: {'lr': 0.0004051399549907846, 'samples': 22765056, 'steps': 44462, 'loss/train': 2.3949553966522217}
-03/05/2022 17:44:24 - INFO - codeparrot_training - Step 44463: {'lr': 0.0004051357936239085, 'samples': 22765568, 'steps': 44463, 'loss/train': 0.28637149930000305}
-03/05/2022 17:44:26 - INFO - codeparrot_training - Skipping example with length 23 (seq_length=1024)
-03/05/2022 17:44:29 - INFO - codeparrot_training - Step 44464: {'lr': 0.0004051316321871307, 'samples': 22766080, 'steps': 44464, 'loss/train': 0.5928150415420532}
-03/05/2022 17:44:32 - INFO - codeparrot_training - Step 44465: {'lr': 0.0004051274706804529, 'samples': 22766592, 'steps': 44465, 'loss/train': 1.8269596099853516}
-03/05/2022 17:44:34 - INFO - codeparrot_training - Skipping example with length 598 (seq_length=1024)
-03/05/2022 17:44:37 - INFO - codeparrot_training - Step 44466: {'lr': 0.00040512330910387706, 'samples': 22767104, 'steps': 44466, 'loss/train': 0.8838698863983154}
-03/05/2022 17:44:41 - INFO - codeparrot_training - Step 44467: {'lr': 0.0004051191474574051, 'samples': 22767616, 'steps': 44467, 'loss/train': 2.1834588050842285}
-03/05/2022 17:44:43 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/05/2022 17:44:46 - INFO - codeparrot_training - Step 44468: {'lr': 0.0004051149857410388, 'samples': 22768128, 'steps': 44468, 'loss/train': 0.7807205319404602}
-03/05/2022 17:44:49 - INFO - codeparrot_training - Step 44469: {'lr': 0.00040511082395478014, 'samples': 22768640, 'steps': 44469, 'loss/train': 1.894767165184021}
-03/05/2022 17:44:51 - INFO - codeparrot_training - Skipping example with length 549 (seq_length=1024)
-03/05/2022 17:44:54 - INFO - codeparrot_training - Step 44470: {'lr': 0.0004051066620986309, 'samples': 22769152, 'steps': 44470, 'loss/train': 1.3567360639572144}
-03/05/2022 17:44:58 - INFO - codeparrot_training - Step 44471: {'lr': 0.00040510250017259297, 'samples': 22769664, 'steps': 44471, 'loss/train': 1.066641092300415}
-03/05/2022 17:45:00 - INFO - codeparrot_training - Skipping example with length 6 (seq_length=1024)
-03/05/2022 17:45:03 - INFO - codeparrot_training - Step 44472: {'lr': 0.0004050983381766683, 'samples': 22770176, 'steps': 44472, 'loss/train': 0.9498510956764221}
-03/05/2022 17:45:06 - INFO - codeparrot_training - Step 44473: {'lr': 0.00040509417611085864, 'samples': 22770688, 'steps': 44473, 'loss/train': 1.679363489151001}
-03/05/2022 17:45:08 - INFO - codeparrot_training - Skipping example with length 760 (seq_length=1024)
-03/05/2022 17:45:11 - INFO - codeparrot_training - Step 44474: {'lr': 0.000405090013975166, 'samples': 22771200, 'steps': 44474, 'loss/train': 1.8203885555267334}
-03/05/2022 17:45:15 - INFO - codeparrot_training - Step 44475: {'lr': 0.0004050858517695921, 'samples': 22771712, 'steps': 44475, 'loss/train': 1.4564977884292603}
-03/05/2022 17:45:17 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/05/2022 17:45:20 - INFO - codeparrot_training - Step 44476: {'lr': 0.00040508168949413904, 'samples': 22772224, 'steps': 44476, 'loss/train': 1.9062387943267822}
-03/05/2022 17:45:23 - INFO - codeparrot_training - Step 44477: {'lr': 0.00040507752714880854, 'samples': 22772736, 'steps': 44477, 'loss/train': 1.298945426940918}
-03/05/2022 17:45:25 - INFO - codeparrot_training - Skipping example with length 36 (seq_length=1024)
-03/05/2022 17:45:28 - INFO - codeparrot_training - Step 44478: {'lr': 0.0004050733647336024, 'samples': 22773248, 'steps': 44478, 'loss/train': 1.0678116083145142}
-03/05/2022 17:45:32 - INFO - codeparrot_training - Step 44479: {'lr': 0.00040506920224852265, 'samples': 22773760, 'steps': 44479, 'loss/train': 1.7555063962936401}
-03/05/2022 17:45:34 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 17:45:37 - INFO - codeparrot_training - Step 44480: {'lr': 0.0004050650396935711, 'samples': 22774272, 'steps': 44480, 'loss/train': 2.0964548587799072}
-03/05/2022 17:45:40 - INFO - codeparrot_training - Step 44481: {'lr': 0.00040506087706874966, 'samples': 22774784, 'steps': 44481, 'loss/train': 1.492376446723938}
-03/05/2022 17:45:43 - INFO - codeparrot_training - Skipping example with length 794 (seq_length=1024)
-03/05/2022 17:45:45 - INFO - codeparrot_training - Step 44482: {'lr': 0.00040505671437406017, 'samples': 22775296, 'steps': 44482, 'loss/train': 2.030416965484619}
-03/05/2022 17:45:49 - INFO - codeparrot_training - Step 44483: {'lr': 0.00040505255160950453, 'samples': 22775808, 'steps': 44483, 'loss/train': 2.010260820388794}
-03/05/2022 17:45:51 - INFO - codeparrot_training - Skipping example with length 673 (seq_length=1024)
-03/05/2022 17:45:54 - INFO - codeparrot_training - Step 44484: {'lr': 0.00040504838877508464, 'samples': 22776320, 'steps': 44484, 'loss/train': 2.675980806350708}
-03/05/2022 17:45:57 - INFO - codeparrot_training - Step 44485: {'lr': 0.0004050442258708022, 'samples': 22776832, 'steps': 44485, 'loss/train': 1.7337102890014648}
-03/05/2022 17:46:00 - INFO - codeparrot_training - Step 44486: {'lr': 0.0004050400628966594, 'samples': 22777344, 'steps': 44486, 'loss/train': 1.4738069772720337}
-03/05/2022 17:46:00 - INFO - codeparrot_training - Skipping example with length 868 (seq_length=1024)
-03/05/2022 17:46:06 - INFO - codeparrot_training - Step 44487: {'lr': 0.0004050358998526578, 'samples': 22777856, 'steps': 44487, 'loss/train': 2.0928032398223877}
-03/05/2022 17:46:09 - INFO - codeparrot_training - Step 44488: {'lr': 0.00040503173673879945, 'samples': 22778368, 'steps': 44488, 'loss/train': 1.773941993713379}
-03/05/2022 17:46:09 - INFO - codeparrot_training - Skipping example with length 207 (seq_length=1024)
-03/05/2022 17:46:14 - INFO - codeparrot_training - Step 44489: {'lr': 0.00040502757355508626, 'samples': 22778880, 'steps': 44489, 'loss/train': 2.341097116470337}
-03/05/2022 17:46:17 - INFO - codeparrot_training - Step 44490: {'lr': 0.00040502341030152, 'samples': 22779392, 'steps': 44490, 'loss/train': 1.0215282440185547}
-03/05/2022 17:46:18 - INFO - codeparrot_training - Skipping example with length 882 (seq_length=1024)
-03/05/2022 17:46:23 - INFO - codeparrot_training - Step 44491: {'lr': 0.0004050192469781025, 'samples': 22779904, 'steps': 44491, 'loss/train': 1.4235018491744995}
-03/05/2022 17:46:26 - INFO - codeparrot_training - Step 44492: {'lr': 0.00040501508358483583, 'samples': 22780416, 'steps': 44492, 'loss/train': 1.6066782474517822}
-03/05/2022 17:46:27 - INFO - codeparrot_training - Skipping example with length 104 (seq_length=1024)
-03/05/2022 17:46:31 - INFO - codeparrot_training - Step 44493: {'lr': 0.00040501092012172173, 'samples': 22780928, 'steps': 44493, 'loss/train': 0.7041665315628052}
-03/05/2022 17:46:34 - INFO - codeparrot_training - Step 44494: {'lr': 0.0004050067565887621, 'samples': 22781440, 'steps': 44494, 'loss/train': 2.097938060760498}
-03/05/2022 17:46:35 - INFO - codeparrot_training - Skipping example with length 360 (seq_length=1024)
-03/05/2022 17:46:40 - INFO - codeparrot_training - Step 44495: {'lr': 0.00040500259298595874, 'samples': 22781952, 'steps': 44495, 'loss/train': 1.8860644102096558}
-03/05/2022 17:46:43 - INFO - codeparrot_training - Step 44496: {'lr': 0.00040499842931331374, 'samples': 22782464, 'steps': 44496, 'loss/train': 1.9293296337127686}
-03/05/2022 17:46:44 - INFO - codeparrot_training - Skipping example with length 167 (seq_length=1024)
-03/05/2022 17:46:48 - INFO - codeparrot_training - Step 44497: {'lr': 0.0004049942655708287, 'samples': 22782976, 'steps': 44497, 'loss/train': 1.6213634014129639}
-03/05/2022 17:46:51 - INFO - codeparrot_training - Step 44498: {'lr': 0.0004049901017585058, 'samples': 22783488, 'steps': 44498, 'loss/train': 1.051899790763855}
-03/05/2022 17:46:52 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/05/2022 17:46:56 - INFO - codeparrot_training - Step 44499: {'lr': 0.00040498593787634664, 'samples': 22784000, 'steps': 44499, 'loss/train': 1.6054790019989014}
-03/05/2022 17:46:59 - INFO - codeparrot_training - Step 44500: {'lr': 0.0004049817739243532, 'samples': 22784512, 'steps': 44500, 'loss/train': 4.172098159790039}
-03/05/2022 17:47:00 - INFO - codeparrot_training - Skipping example with length 383 (seq_length=1024)
-03/05/2022 17:47:05 - INFO - codeparrot_training - Step 44501: {'lr': 0.0004049776099025274, 'samples': 22785024, 'steps': 44501, 'loss/train': 1.3041694164276123}
-03/05/2022 17:47:08 - INFO - codeparrot_training - Step 44502: {'lr': 0.000404973445810871, 'samples': 22785536, 'steps': 44502, 'loss/train': 1.8268110752105713}
-03/05/2022 17:47:09 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/05/2022 17:47:14 - INFO - codeparrot_training - Step 44503: {'lr': 0.00040496928164938614, 'samples': 22786048, 'steps': 44503, 'loss/train': 2.2680890560150146}
-03/05/2022 17:47:17 - INFO - codeparrot_training - Step 44504: {'lr': 0.0004049651174180744, 'samples': 22786560, 'steps': 44504, 'loss/train': 1.6472947597503662}
-03/05/2022 17:47:20 - INFO - codeparrot_training - Step 44505: {'lr': 0.00040496095311693775, 'samples': 22787072, 'steps': 44505, 'loss/train': 1.658734917640686}
-03/05/2022 17:47:20 - INFO - codeparrot_training - Skipping example with length 876 (seq_length=1024)
-03/05/2022 17:47:25 - INFO - codeparrot_training - Step 44506: {'lr': 0.0004049567887459781, 'samples': 22787584, 'steps': 44506, 'loss/train': 1.7881848812103271}
-03/05/2022 17:47:29 - INFO - codeparrot_training - Step 44507: {'lr': 0.0004049526243051973, 'samples': 22788096, 'steps': 44507, 'loss/train': 2.472562074661255}
-03/05/2022 17:47:29 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/05/2022 17:47:34 - INFO - codeparrot_training - Step 44508: {'lr': 0.0004049484597945973, 'samples': 22788608, 'steps': 44508, 'loss/train': 2.091200828552246}
-03/05/2022 17:47:37 - INFO - codeparrot_training - Step 44509: {'lr': 0.00040494429521417983, 'samples': 22789120, 'steps': 44509, 'loss/train': 1.7041828632354736}
-03/05/2022 17:47:37 - INFO - codeparrot_training - Skipping example with length 902 (seq_length=1024)
-03/05/2022 17:47:43 - INFO - codeparrot_training - Step 44510: {'lr': 0.0004049401305639469, 'samples': 22789632, 'steps': 44510, 'loss/train': 2.0982089042663574}
-03/05/2022 17:47:46 - INFO - codeparrot_training - Step 44511: {'lr': 0.00040493596584390034, 'samples': 22790144, 'steps': 44511, 'loss/train': 1.921012043952942}
-03/05/2022 17:47:47 - INFO - codeparrot_training - Skipping example with length 105 (seq_length=1024)
-03/05/2022 17:47:51 - INFO - codeparrot_training - Step 44512: {'lr': 0.00040493180105404203, 'samples': 22790656, 'steps': 44512, 'loss/train': 1.5537750720977783}
-03/05/2022 17:47:54 - INFO - codeparrot_training - Step 44513: {'lr': 0.0004049276361943738, 'samples': 22791168, 'steps': 44513, 'loss/train': 1.5890827178955078}
-03/05/2022 17:47:55 - INFO - codeparrot_training - Skipping example with length 1012 (seq_length=1024)
-03/05/2022 17:47:59 - INFO - codeparrot_training - Step 44514: {'lr': 0.0004049234712648976, 'samples': 22791680, 'steps': 44514, 'loss/train': 1.277435064315796}
-03/05/2022 17:48:03 - INFO - codeparrot_training - Step 44515: {'lr': 0.00040491930626561525, 'samples': 22792192, 'steps': 44515, 'loss/train': 2.004828929901123}
-03/05/2022 17:48:03 - INFO - codeparrot_training - Skipping example with length 515 (seq_length=1024)
-03/05/2022 17:48:08 - INFO - codeparrot_training - Step 44516: {'lr': 0.00040491514119652875, 'samples': 22792704, 'steps': 44516, 'loss/train': 1.8087157011032104}
-03/05/2022 17:48:11 - INFO - codeparrot_training - Step 44517: {'lr': 0.00040491097605763974, 'samples': 22793216, 'steps': 44517, 'loss/train': 1.6327451467514038}
-03/05/2022 17:48:11 - INFO - codeparrot_training - Skipping example with length 385 (seq_length=1024)
-03/05/2022 17:48:16 - INFO - codeparrot_training - Step 44518: {'lr': 0.00040490681084895034, 'samples': 22793728, 'steps': 44518, 'loss/train': 2.096229076385498}
-03/05/2022 17:48:19 - INFO - codeparrot_training - Step 44519: {'lr': 0.00040490264557046217, 'samples': 22794240, 'steps': 44519, 'loss/train': 0.5677652359008789}
-03/05/2022 17:48:20 - INFO - codeparrot_training - Skipping example with length 336 (seq_length=1024)
-03/05/2022 17:48:25 - INFO - codeparrot_training - Step 44520: {'lr': 0.0004048984802221774, 'samples': 22794752, 'steps': 44520, 'loss/train': 2.47418475151062}
-03/05/2022 17:48:28 - INFO - codeparrot_training - Step 44521: {'lr': 0.0004048943148040977, 'samples': 22795264, 'steps': 44521, 'loss/train': 1.6227787733078003}
-03/05/2022 17:48:28 - INFO - codeparrot_training - Skipping example with length 327 (seq_length=1024)
-03/05/2022 17:48:33 - INFO - codeparrot_training - Step 44522: {'lr': 0.0004048901493162251, 'samples': 22795776, 'steps': 44522, 'loss/train': 1.6965560913085938}
-03/05/2022 17:48:36 - INFO - codeparrot_training - Step 44523: {'lr': 0.00040488598375856133, 'samples': 22796288, 'steps': 44523, 'loss/train': 1.7054929733276367}
-03/05/2022 17:48:36 - INFO - codeparrot_training - Skipping example with length 616 (seq_length=1024)
-03/05/2022 17:48:42 - INFO - codeparrot_training - Step 44524: {'lr': 0.0004048818181311083, 'samples': 22796800, 'steps': 44524, 'loss/train': 2.8673338890075684}
-03/05/2022 17:48:45 - INFO - codeparrot_training - Step 44525: {'lr': 0.00040487765243386794, 'samples': 22797312, 'steps': 44525, 'loss/train': 1.1606882810592651}
-03/05/2022 17:48:45 - INFO - codeparrot_training - Skipping example with length 416 (seq_length=1024)
-03/05/2022 17:48:50 - INFO - codeparrot_training - Step 44526: {'lr': 0.0004048734866668421, 'samples': 22797824, 'steps': 44526, 'loss/train': 1.677412986755371}
-03/05/2022 17:48:53 - INFO - codeparrot_training - Step 44527: {'lr': 0.0004048693208300327, 'samples': 22798336, 'steps': 44527, 'loss/train': 1.0053110122680664}
-03/05/2022 17:48:53 - INFO - codeparrot_training - Skipping example with length 778 (seq_length=1024)
-03/05/2022 17:48:59 - INFO - codeparrot_training - Step 44528: {'lr': 0.00040486515492344145, 'samples': 22798848, 'steps': 44528, 'loss/train': 1.4556457996368408}
-03/05/2022 17:49:02 - INFO - codeparrot_training - Step 44529: {'lr': 0.00040486098894707044, 'samples': 22799360, 'steps': 44529, 'loss/train': 1.0868699550628662}
-03/05/2022 17:49:02 - INFO - codeparrot_training - Skipping example with length 223 (seq_length=1024)
-03/05/2022 17:49:07 - INFO - codeparrot_training - Step 44530: {'lr': 0.00040485682290092144, 'samples': 22799872, 'steps': 44530, 'loss/train': 1.2931398153305054}
-03/05/2022 17:49:10 - INFO - codeparrot_training - Step 44531: {'lr': 0.0004048526567849964, 'samples': 22800384, 'steps': 44531, 'loss/train': 1.568174958229065}
-03/05/2022 17:49:10 - INFO - codeparrot_training - Skipping example with length 380 (seq_length=1024)
-03/05/2022 17:49:15 - INFO - codeparrot_training - Step 44532: {'lr': 0.00040484849059929705, 'samples': 22800896, 'steps': 44532, 'loss/train': 1.634194016456604}
-03/05/2022 17:49:19 - INFO - codeparrot_training - Step 44533: {'lr': 0.00040484432434382547, 'samples': 22801408, 'steps': 44533, 'loss/train': 1.099392056465149}
-03/05/2022 17:49:19 - INFO - codeparrot_training - Skipping example with length 524 (seq_length=1024)
-03/05/2022 17:49:24 - INFO - codeparrot_training - Step 44534: {'lr': 0.0004048401580185833, 'samples': 22801920, 'steps': 44534, 'loss/train': 1.608557105064392}
-03/05/2022 17:49:27 - INFO - codeparrot_training - Step 44535: {'lr': 0.00040483599162357257, 'samples': 22802432, 'steps': 44535, 'loss/train': 1.4663537740707397}
-03/05/2022 17:49:27 - INFO - codeparrot_training - Skipping example with length 241 (seq_length=1024)
-03/05/2022 17:49:32 - INFO - codeparrot_training - Step 44536: {'lr': 0.0004048318251587952, 'samples': 22802944, 'steps': 44536, 'loss/train': 1.623267412185669}
-03/05/2022 17:49:36 - INFO - codeparrot_training - Step 44537: {'lr': 0.000404827658624253, 'samples': 22803456, 'steps': 44537, 'loss/train': 1.6842097043991089}
-03/05/2022 17:49:36 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/05/2022 17:49:41 - INFO - codeparrot_training - Step 44538: {'lr': 0.00040482349201994785, 'samples': 22803968, 'steps': 44538, 'loss/train': 1.3043562173843384}
-03/05/2022 17:49:44 - INFO - codeparrot_training - Step 44539: {'lr': 0.00040481932534588153, 'samples': 22804480, 'steps': 44539, 'loss/train': 1.3490920066833496}
-03/05/2022 17:49:44 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 17:49:49 - INFO - codeparrot_training - Step 44540: {'lr': 0.00040481515860205607, 'samples': 22804992, 'steps': 44540, 'loss/train': 1.8216818571090698}
-03/05/2022 17:49:53 - INFO - codeparrot_training - Step 44541: {'lr': 0.00040481099178847326, 'samples': 22805504, 'steps': 44541, 'loss/train': 1.32760751247406}
-03/05/2022 17:49:53 - INFO - codeparrot_training - Skipping example with length 806 (seq_length=1024)
-03/05/2022 17:49:58 - INFO - codeparrot_training - Step 44542: {'lr': 0.000404806824905135, 'samples': 22806016, 'steps': 44542, 'loss/train': 1.7145955562591553}
-03/05/2022 17:50:01 - INFO - codeparrot_training - Step 44543: {'lr': 0.0004048026579520433, 'samples': 22806528, 'steps': 44543, 'loss/train': 1.6666427850723267}
-03/05/2022 17:50:02 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/05/2022 17:50:07 - INFO - codeparrot_training - Step 44544: {'lr': 0.00040479849092919974, 'samples': 22807040, 'steps': 44544, 'loss/train': 1.376805067062378}
-03/05/2022 17:50:10 - INFO - codeparrot_training - Step 44545: {'lr': 0.00040479432383660644, 'samples': 22807552, 'steps': 44545, 'loss/train': 1.2782899141311646}
-03/05/2022 17:50:10 - INFO - codeparrot_training - Skipping example with length 735 (seq_length=1024)
-03/05/2022 17:50:15 - INFO - codeparrot_training - Step 44546: {'lr': 0.00040479015667426523, 'samples': 22808064, 'steps': 44546, 'loss/train': 2.152052402496338}
-03/05/2022 17:50:18 - INFO - codeparrot_training - Step 44547: {'lr': 0.00040478598944217794, 'samples': 22808576, 'steps': 44547, 'loss/train': 1.6980112791061401}
-03/05/2022 17:50:19 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/05/2022 17:50:24 - INFO - codeparrot_training - Step 44548: {'lr': 0.0004047818221403464, 'samples': 22809088, 'steps': 44548, 'loss/train': 2.021150588989258}
-03/05/2022 17:50:27 - INFO - codeparrot_training - Step 44549: {'lr': 0.0004047776547687727, 'samples': 22809600, 'steps': 44549, 'loss/train': 1.5869733095169067}
-03/05/2022 17:50:27 - INFO - codeparrot_training - Skipping example with length 857 (seq_length=1024)
-03/05/2022 17:50:32 - INFO - codeparrot_training - Step 44550: {'lr': 0.00040477348732745853, 'samples': 22810112, 'steps': 44550, 'loss/train': 2.583287000656128}
-03/05/2022 17:50:36 - INFO - codeparrot_training - Step 44551: {'lr': 0.0004047693198164058, 'samples': 22810624, 'steps': 44551, 'loss/train': 1.6966031789779663}
-03/05/2022 17:50:36 - INFO - codeparrot_training - Skipping example with length 310 (seq_length=1024)
-03/05/2022 17:50:41 - INFO - codeparrot_training - Step 44552: {'lr': 0.0004047651522356164, 'samples': 22811136, 'steps': 44552, 'loss/train': 2.473597764968872}
-03/05/2022 17:50:44 - INFO - codeparrot_training - Step 44553: {'lr': 0.0004047609845850922, 'samples': 22811648, 'steps': 44553, 'loss/train': 1.9031518697738647}
-03/05/2022 17:50:45 - INFO - codeparrot_training - Skipping example with length 471 (seq_length=1024)
-03/05/2022 17:50:49 - INFO - codeparrot_training - Step 44554: {'lr': 0.0004047568168648351, 'samples': 22812160, 'steps': 44554, 'loss/train': 1.0363484621047974}
-03/05/2022 17:50:53 - INFO - codeparrot_training - Step 44555: {'lr': 0.00040475264907484696, 'samples': 22812672, 'steps': 44555, 'loss/train': 1.5753082036972046}
-03/05/2022 17:50:53 - INFO - codeparrot_training - Skipping example with length 243 (seq_length=1024)
-03/05/2022 17:50:58 - INFO - codeparrot_training - Step 44556: {'lr': 0.0004047484812151296, 'samples': 22813184, 'steps': 44556, 'loss/train': 2.182079792022705}
-03/05/2022 17:51:01 - INFO - codeparrot_training - Step 44557: {'lr': 0.00040474431328568506, 'samples': 22813696, 'steps': 44557, 'loss/train': 1.1794798374176025}
-03/05/2022 17:51:02 - INFO - codeparrot_training - Skipping example with length 430 (seq_length=1024)
-03/05/2022 17:51:06 - INFO - codeparrot_training - Step 44558: {'lr': 0.00040474014528651514, 'samples': 22814208, 'steps': 44558, 'loss/train': 1.146364688873291}
-03/05/2022 17:51:10 - INFO - codeparrot_training - Step 44559: {'lr': 0.00040473597721762164, 'samples': 22814720, 'steps': 44559, 'loss/train': 1.7546452283859253}
-03/05/2022 17:51:10 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/05/2022 17:51:15 - INFO - codeparrot_training - Step 44560: {'lr': 0.00040473180907900645, 'samples': 22815232, 'steps': 44560, 'loss/train': 0.8381884694099426}
-03/05/2022 17:51:18 - INFO - codeparrot_training - Step 44561: {'lr': 0.0004047276408706716, 'samples': 22815744, 'steps': 44561, 'loss/train': 0.7167012095451355}
-03/05/2022 17:51:18 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/05/2022 17:51:23 - INFO - codeparrot_training - Step 44562: {'lr': 0.00040472347259261875, 'samples': 22816256, 'steps': 44562, 'loss/train': 2.192063570022583}
-03/05/2022 17:51:27 - INFO - codeparrot_training - Step 44563: {'lr': 0.00040471930424485, 'samples': 22816768, 'steps': 44563, 'loss/train': 1.1742388010025024}
-03/05/2022 17:51:27 - INFO - codeparrot_training - Skipping example with length 816 (seq_length=1024)
-03/05/2022 17:51:32 - INFO - codeparrot_training - Step 44564: {'lr': 0.0004047151358273671, 'samples': 22817280, 'steps': 44564, 'loss/train': 2.216261386871338}
-03/05/2022 17:51:35 - INFO - codeparrot_training - Step 44565: {'lr': 0.00040471096734017185, 'samples': 22817792, 'steps': 44565, 'loss/train': 1.5933125019073486}
-03/05/2022 17:51:35 - INFO - codeparrot_training - Skipping example with length 563 (seq_length=1024)
-03/05/2022 17:51:40 - INFO - codeparrot_training - Step 44566: {'lr': 0.0004047067987832663, 'samples': 22818304, 'steps': 44566, 'loss/train': 0.7027168273925781}
-03/05/2022 17:51:43 - INFO - codeparrot_training - Step 44567: {'lr': 0.00040470263015665234, 'samples': 22818816, 'steps': 44567, 'loss/train': 1.7794424295425415}
-03/05/2022 17:51:44 - INFO - codeparrot_training - Skipping example with length 20 (seq_length=1024)
-03/05/2022 17:51:49 - INFO - codeparrot_training - Step 44568: {'lr': 0.00040469846146033164, 'samples': 22819328, 'steps': 44568, 'loss/train': 1.461206316947937}
-03/05/2022 17:51:52 - INFO - codeparrot_training - Step 44569: {'lr': 0.00040469429269430617, 'samples': 22819840, 'steps': 44569, 'loss/train': 0.896517276763916}
-03/05/2022 17:51:52 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 17:51:57 - INFO - codeparrot_training - Step 44570: {'lr': 0.00040469012385857794, 'samples': 22820352, 'steps': 44570, 'loss/train': 1.209571361541748}
-03/05/2022 17:52:00 - INFO - codeparrot_training - Step 44571: {'lr': 0.0004046859549531487, 'samples': 22820864, 'steps': 44571, 'loss/train': 1.5327390432357788}
-03/05/2022 17:52:00 - INFO - codeparrot_training - Skipping example with length 577 (seq_length=1024)
-03/05/2022 17:52:06 - INFO - codeparrot_training - Step 44572: {'lr': 0.0004046817859780203, 'samples': 22821376, 'steps': 44572, 'loss/train': 1.8687971830368042}
-03/05/2022 17:52:09 - INFO - codeparrot_training - Step 44573: {'lr': 0.00040467761693319473, 'samples': 22821888, 'steps': 44573, 'loss/train': 1.6438744068145752}
-03/05/2022 17:52:09 - INFO - codeparrot_training - Skipping example with length 114 (seq_length=1024)
-03/05/2022 17:52:14 - INFO - codeparrot_training - Step 44574: {'lr': 0.0004046734478186738, 'samples': 22822400, 'steps': 44574, 'loss/train': 1.8528239727020264}
-03/05/2022 17:52:17 - INFO - codeparrot_training - Step 44575: {'lr': 0.0004046692786344594, 'samples': 22822912, 'steps': 44575, 'loss/train': 1.8717046976089478}
-03/05/2022 17:52:18 - INFO - codeparrot_training - Skipping example with length 250 (seq_length=1024)
-03/05/2022 17:52:23 - INFO - codeparrot_training - Step 44576: {'lr': 0.0004046651093805534, 'samples': 22823424, 'steps': 44576, 'loss/train': 1.5234545469284058}
-03/05/2022 17:52:26 - INFO - codeparrot_training - Step 44577: {'lr': 0.0004046609400569577, 'samples': 22823936, 'steps': 44577, 'loss/train': 1.6831412315368652}
-03/05/2022 17:52:26 - INFO - codeparrot_training - Skipping example with length 723 (seq_length=1024)
-03/05/2022 17:52:31 - INFO - codeparrot_training - Step 44578: {'lr': 0.00040465677066367424, 'samples': 22824448, 'steps': 44578, 'loss/train': 1.78238046169281}
-03/05/2022 17:52:34 - INFO - codeparrot_training - Step 44579: {'lr': 0.0004046526012007047, 'samples': 22824960, 'steps': 44579, 'loss/train': 1.1103743314743042}
-03/05/2022 17:52:35 - INFO - codeparrot_training - Skipping example with length 418 (seq_length=1024)
-03/05/2022 17:52:39 - INFO - codeparrot_training - Step 44580: {'lr': 0.0004046484316680511, 'samples': 22825472, 'steps': 44580, 'loss/train': 2.2987775802612305}
-03/05/2022 17:52:43 - INFO - codeparrot_training - Step 44581: {'lr': 0.0004046442620657154, 'samples': 22825984, 'steps': 44581, 'loss/train': 1.830420970916748}
-03/05/2022 17:52:43 - INFO - codeparrot_training - Skipping example with length 622 (seq_length=1024)
-03/05/2022 17:52:48 - INFO - codeparrot_training - Step 44582: {'lr': 0.00040464009239369925, 'samples': 22826496, 'steps': 44582, 'loss/train': 1.899353265762329}
-03/05/2022 17:52:51 - INFO - codeparrot_training - Step 44583: {'lr': 0.0004046359226520048, 'samples': 22827008, 'steps': 44583, 'loss/train': 1.379555344581604}
-03/05/2022 17:52:52 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/05/2022 17:52:56 - INFO - codeparrot_training - Step 44584: {'lr': 0.0004046317528406337, 'samples': 22827520, 'steps': 44584, 'loss/train': 1.4669467210769653}
-03/05/2022 17:53:00 - INFO - codeparrot_training - Step 44585: {'lr': 0.0004046275829595879, 'samples': 22828032, 'steps': 44585, 'loss/train': 2.1820998191833496}
-03/05/2022 17:53:00 - INFO - codeparrot_training - Skipping example with length 901 (seq_length=1024)
-03/05/2022 17:53:05 - INFO - codeparrot_training - Step 44586: {'lr': 0.0004046234130088694, 'samples': 22828544, 'steps': 44586, 'loss/train': 1.9344310760498047}
-03/05/2022 17:53:08 - INFO - codeparrot_training - Step 44587: {'lr': 0.00040461924298847987, 'samples': 22829056, 'steps': 44587, 'loss/train': 0.8054443001747131}
-03/05/2022 17:53:08 - INFO - codeparrot_training - Skipping example with length 567 (seq_length=1024)
-03/05/2022 17:53:13 - INFO - codeparrot_training - Step 44588: {'lr': 0.0004046150728984214, 'samples': 22829568, 'steps': 44588, 'loss/train': 2.062788724899292}
-03/05/2022 17:53:16 - INFO - codeparrot_training - Step 44589: {'lr': 0.00040461090273869566, 'samples': 22830080, 'steps': 44589, 'loss/train': 0.3859576880931854}
-03/05/2022 17:53:17 - INFO - codeparrot_training - Skipping example with length 564 (seq_length=1024)
-03/05/2022 17:53:22 - INFO - codeparrot_training - Step 44590: {'lr': 0.0004046067325093047, 'samples': 22830592, 'steps': 44590, 'loss/train': 1.8838670253753662}
-03/05/2022 17:53:25 - INFO - codeparrot_training - Step 44591: {'lr': 0.00040460256221025025, 'samples': 22831104, 'steps': 44591, 'loss/train': 1.2600703239440918}
-03/05/2022 17:53:25 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/05/2022 17:53:30 - INFO - codeparrot_training - Step 44592: {'lr': 0.00040459839184153436, 'samples': 22831616, 'steps': 44592, 'loss/train': 0.9063652753829956}
-03/05/2022 17:53:33 - INFO - codeparrot_training - Step 44593: {'lr': 0.00040459422140315876, 'samples': 22832128, 'steps': 44593, 'loss/train': 0.4345346689224243}
-03/05/2022 17:53:33 - INFO - codeparrot_training - Skipping example with length 448 (seq_length=1024)
-03/05/2022 17:53:38 - INFO - codeparrot_training - Step 44594: {'lr': 0.00040459005089512544, 'samples': 22832640, 'steps': 44594, 'loss/train': 1.607822299003601}
-03/05/2022 17:53:42 - INFO - codeparrot_training - Step 44595: {'lr': 0.0004045858803174362, 'samples': 22833152, 'steps': 44595, 'loss/train': 1.5277867317199707}
-03/05/2022 17:53:42 - INFO - codeparrot_training - Skipping example with length 594 (seq_length=1024)
-03/05/2022 17:53:47 - INFO - codeparrot_training - Step 44596: {'lr': 0.0004045817096700929, 'samples': 22833664, 'steps': 44596, 'loss/train': 1.6344398260116577}
-03/05/2022 17:53:50 - INFO - codeparrot_training - Step 44597: {'lr': 0.0004045775389530976, 'samples': 22834176, 'steps': 44597, 'loss/train': 0.3275397717952728}
-03/05/2022 17:53:51 - INFO - codeparrot_training - Skipping example with length 950 (seq_length=1024)
-03/05/2022 17:53:56 - INFO - codeparrot_training - Step 44598: {'lr': 0.00040457336816645195, 'samples': 22834688, 'steps': 44598, 'loss/train': 1.3535548448562622}
-03/05/2022 17:53:59 - INFO - codeparrot_training - Step 44599: {'lr': 0.000404569197310158, 'samples': 22835200, 'steps': 44599, 'loss/train': 0.49079734086990356}
-03/05/2022 17:53:59 - INFO - codeparrot_training - Skipping example with length 658 (seq_length=1024)
-03/05/2022 17:54:04 - INFO - codeparrot_training - Step 44600: {'lr': 0.0004045650263842174, 'samples': 22835712, 'steps': 44600, 'loss/train': 0.6516032814979553}
-03/05/2022 17:54:07 - INFO - codeparrot_training - Step 44601: {'lr': 0.0004045608553886323, 'samples': 22836224, 'steps': 44601, 'loss/train': 1.6543772220611572}
-03/05/2022 17:54:08 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/05/2022 17:54:13 - INFO - codeparrot_training - Step 44602: {'lr': 0.0004045566843234044, 'samples': 22836736, 'steps': 44602, 'loss/train': 1.015753149986267}
-03/05/2022 17:54:16 - INFO - codeparrot_training - Step 44603: {'lr': 0.0004045525131885357, 'samples': 22837248, 'steps': 44603, 'loss/train': 1.889438271522522}
-03/05/2022 17:54:18 - INFO - codeparrot_training - Skipping example with length 584 (seq_length=1024)
-03/05/2022 17:54:21 - INFO - codeparrot_training - Step 44604: {'lr': 0.0004045483419840281, 'samples': 22837760, 'steps': 44604, 'loss/train': 2.1295838356018066}
-03/05/2022 17:54:24 - INFO - codeparrot_training - Step 44605: {'lr': 0.00040454417070988325, 'samples': 22838272, 'steps': 44605, 'loss/train': 2.057110548019409}
-03/05/2022 17:54:26 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 17:54:30 - INFO - codeparrot_training - Step 44606: {'lr': 0.0004045399993661033, 'samples': 22838784, 'steps': 44606, 'loss/train': 1.609908103942871}
-03/05/2022 17:54:33 - INFO - codeparrot_training - Step 44607: {'lr': 0.00040453582795268994, 'samples': 22839296, 'steps': 44607, 'loss/train': 1.2735306024551392}
-03/05/2022 17:54:34 - INFO - codeparrot_training - Skipping example with length 571 (seq_length=1024)
-03/05/2022 17:54:38 - INFO - codeparrot_training - Step 44608: {'lr': 0.00040453165646964505, 'samples': 22839808, 'steps': 44608, 'loss/train': 2.1764392852783203}
-03/05/2022 17:54:41 - INFO - codeparrot_training - Step 44609: {'lr': 0.00040452748491697074, 'samples': 22840320, 'steps': 44609, 'loss/train': 2.0880839824676514}
-03/05/2022 17:54:43 - INFO - codeparrot_training - Skipping example with length 287 (seq_length=1024)
-03/05/2022 17:54:46 - INFO - codeparrot_training - Step 44610: {'lr': 0.00040452331329466864, 'samples': 22840832, 'steps': 44610, 'loss/train': 2.4466021060943604}
-03/05/2022 17:54:50 - INFO - codeparrot_training - Step 44611: {'lr': 0.0004045191416027407, 'samples': 22841344, 'steps': 44611, 'loss/train': 1.6570193767547607}
-03/05/2022 17:54:51 - INFO - codeparrot_training - Skipping example with length 194 (seq_length=1024)
-03/05/2022 17:54:55 - INFO - codeparrot_training - Step 44612: {'lr': 0.0004045149698411889, 'samples': 22841856, 'steps': 44612, 'loss/train': 1.5675358772277832}
-03/05/2022 17:54:58 - INFO - codeparrot_training - Step 44613: {'lr': 0.000404510798010015, 'samples': 22842368, 'steps': 44613, 'loss/train': 1.6530590057373047}
-03/05/2022 17:54:59 - INFO - codeparrot_training - Skipping example with length 130 (seq_length=1024)
-03/05/2022 17:55:03 - INFO - codeparrot_training - Step 44614: {'lr': 0.0004045066261092209, 'samples': 22842880, 'steps': 44614, 'loss/train': 1.7235081195831299}
-03/05/2022 17:55:06 - INFO - codeparrot_training - Step 44615: {'lr': 0.0004045024541388085, 'samples': 22843392, 'steps': 44615, 'loss/train': 1.8354604244232178}
-03/05/2022 17:55:08 - INFO - codeparrot_training - Skipping example with length 419 (seq_length=1024)
-03/05/2022 17:55:12 - INFO - codeparrot_training - Step 44616: {'lr': 0.0004044982820987797, 'samples': 22843904, 'steps': 44616, 'loss/train': 1.9907817840576172}
-03/05/2022 17:55:15 - INFO - codeparrot_training - Step 44617: {'lr': 0.0004044941099891364, 'samples': 22844416, 'steps': 44617, 'loss/train': 1.4687731266021729}
-03/05/2022 17:55:16 - INFO - codeparrot_training - Skipping example with length 541 (seq_length=1024)
-03/05/2022 17:55:20 - INFO - codeparrot_training - Step 44618: {'lr': 0.0004044899378098803, 'samples': 22844928, 'steps': 44618, 'loss/train': 3.456974506378174}
-03/05/2022 17:55:24 - INFO - codeparrot_training - Step 44619: {'lr': 0.00040448576556101356, 'samples': 22845440, 'steps': 44619, 'loss/train': 1.8188203573226929}
-03/05/2022 17:55:25 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/05/2022 17:55:30 - INFO - codeparrot_training - Step 44620: {'lr': 0.0004044815932425379, 'samples': 22845952, 'steps': 44620, 'loss/train': 2.1145966053009033}
-03/05/2022 17:55:33 - INFO - codeparrot_training - Step 44621: {'lr': 0.0004044774208544551, 'samples': 22846464, 'steps': 44621, 'loss/train': 1.9617079496383667}
-03/05/2022 17:55:36 - INFO - codeparrot_training - Step 44622: {'lr': 0.00040447324839676727, 'samples': 22846976, 'steps': 44622, 'loss/train': 2.4888126850128174}
-03/05/2022 17:55:37 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 17:55:41 - INFO - codeparrot_training - Step 44623: {'lr': 0.00040446907586947614, 'samples': 22847488, 'steps': 44623, 'loss/train': 1.0431649684906006}
-03/05/2022 17:55:44 - INFO - codeparrot_training - Step 44624: {'lr': 0.0004044649032725836, 'samples': 22848000, 'steps': 44624, 'loss/train': 0.9656731486320496}
-03/05/2022 17:55:45 - INFO - codeparrot_training - Skipping example with length 854 (seq_length=1024)
-03/05/2022 17:55:50 - INFO - codeparrot_training - Step 44625: {'lr': 0.00040446073060609156, 'samples': 22848512, 'steps': 44625, 'loss/train': 2.0026378631591797}
-03/05/2022 17:55:53 - INFO - codeparrot_training - Step 44626: {'lr': 0.00040445655787000196, 'samples': 22849024, 'steps': 44626, 'loss/train': 1.5878280401229858}
-03/05/2022 17:55:54 - INFO - codeparrot_training - Skipping example with length 698 (seq_length=1024)
-03/05/2022 17:55:58 - INFO - codeparrot_training - Step 44627: {'lr': 0.0004044523850643166, 'samples': 22849536, 'steps': 44627, 'loss/train': 1.425322413444519}
-03/05/2022 17:56:01 - INFO - codeparrot_training - Step 44628: {'lr': 0.0004044482121890374, 'samples': 22850048, 'steps': 44628, 'loss/train': 1.6432218551635742}
-03/05/2022 17:56:02 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/05/2022 17:56:07 - INFO - codeparrot_training - Step 44629: {'lr': 0.00040444403924416614, 'samples': 22850560, 'steps': 44629, 'loss/train': 1.741536021232605}
-03/05/2022 17:56:10 - INFO - codeparrot_training - Step 44630: {'lr': 0.00040443986622970486, 'samples': 22851072, 'steps': 44630, 'loss/train': 1.5783207416534424}
-03/05/2022 17:56:11 - INFO - codeparrot_training - Skipping example with length 605 (seq_length=1024)
-03/05/2022 17:56:15 - INFO - codeparrot_training - Step 44631: {'lr': 0.0004044356931456553, 'samples': 22851584, 'steps': 44631, 'loss/train': 2.2249045372009277}
-03/05/2022 17:56:19 - INFO - codeparrot_training - Step 44632: {'lr': 0.00040443151999201946, 'samples': 22852096, 'steps': 44632, 'loss/train': 0.5955970883369446}
-03/05/2022 17:56:22 - INFO - codeparrot_training - Step 44633: {'lr': 0.00040442734676879907, 'samples': 22852608, 'steps': 44633, 'loss/train': 1.5316474437713623}
-03/05/2022 17:56:22 - INFO - codeparrot_training - Skipping example with length 245 (seq_length=1024)
-03/05/2022 17:56:27 - INFO - codeparrot_training - Step 44634: {'lr': 0.0004044231734759961, 'samples': 22853120, 'steps': 44634, 'loss/train': 1.938407301902771}
-03/05/2022 17:56:30 - INFO - codeparrot_training - Step 44635: {'lr': 0.00040441900011361256, 'samples': 22853632, 'steps': 44635, 'loss/train': 1.0903067588806152}
-03/05/2022 17:56:30 - INFO - codeparrot_training - Skipping example with length 181 (seq_length=1024)
-03/05/2022 17:56:36 - INFO - codeparrot_training - Step 44636: {'lr': 0.0004044148266816501, 'samples': 22854144, 'steps': 44636, 'loss/train': 2.070053815841675}
-03/05/2022 17:56:39 - INFO - codeparrot_training - Step 44637: {'lr': 0.0004044106531801107, 'samples': 22854656, 'steps': 44637, 'loss/train': 1.3121535778045654}
-03/05/2022 17:56:39 - INFO - codeparrot_training - Skipping example with length 438 (seq_length=1024)
-03/05/2022 17:56:45 - INFO - codeparrot_training - Step 44638: {'lr': 0.0004044064796089963, 'samples': 22855168, 'steps': 44638, 'loss/train': 0.9306910037994385}
-03/05/2022 17:56:48 - INFO - codeparrot_training - Step 44639: {'lr': 0.0004044023059683087, 'samples': 22855680, 'steps': 44639, 'loss/train': 2.1859676837921143}
-03/05/2022 17:56:49 - INFO - codeparrot_training - Skipping example with length 613 (seq_length=1024)
-03/05/2022 17:56:53 - INFO - codeparrot_training - Step 44640: {'lr': 0.00040439813225804977, 'samples': 22856192, 'steps': 44640, 'loss/train': 1.3294568061828613}
-03/05/2022 17:56:56 - INFO - codeparrot_training - Step 44641: {'lr': 0.00040439395847822145, 'samples': 22856704, 'steps': 44641, 'loss/train': 1.7839032411575317}
-03/05/2022 17:56:57 - INFO - codeparrot_training - Skipping example with length 52 (seq_length=1024)
-03/05/2022 17:57:02 - INFO - codeparrot_training - Step 44642: {'lr': 0.00040438978462882557, 'samples': 22857216, 'steps': 44642, 'loss/train': 0.5730567574501038}
-03/05/2022 17:57:05 - INFO - codeparrot_training - Step 44643: {'lr': 0.0004043856107098641, 'samples': 22857728, 'steps': 44643, 'loss/train': 2.8155109882354736}
-03/05/2022 17:57:06 - INFO - codeparrot_training - Skipping example with length 853 (seq_length=1024)
-03/05/2022 17:57:10 - INFO - codeparrot_training - Step 44644: {'lr': 0.0004043814367213388, 'samples': 22858240, 'steps': 44644, 'loss/train': 1.6502482891082764}
-03/05/2022 17:57:13 - INFO - codeparrot_training - Step 44645: {'lr': 0.00040437726266325164, 'samples': 22858752, 'steps': 44645, 'loss/train': 2.124210834503174}
-03/05/2022 17:57:15 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/05/2022 17:57:19 - INFO - codeparrot_training - Step 44646: {'lr': 0.00040437308853560444, 'samples': 22859264, 'steps': 44646, 'loss/train': 1.5798161029815674}
-03/05/2022 17:57:22 - INFO - codeparrot_training - Step 44647: {'lr': 0.0004043689143383991, 'samples': 22859776, 'steps': 44647, 'loss/train': 1.7014262676239014}
-03/05/2022 17:57:23 - INFO - codeparrot_training - Skipping example with length 365 (seq_length=1024)
-03/05/2022 17:57:27 - INFO - codeparrot_training - Step 44648: {'lr': 0.00040436474007163754, 'samples': 22860288, 'steps': 44648, 'loss/train': 1.972253680229187}
-03/05/2022 17:57:30 - INFO - codeparrot_training - Step 44649: {'lr': 0.0004043605657353216, 'samples': 22860800, 'steps': 44649, 'loss/train': 1.939107060432434}
-03/05/2022 17:57:31 - INFO - codeparrot_training - Skipping example with length 1000 (seq_length=1024)
-03/05/2022 17:57:35 - INFO - codeparrot_training - Step 44650: {'lr': 0.00040435639132945314, 'samples': 22861312, 'steps': 44650, 'loss/train': 1.3760052919387817}
-03/05/2022 17:57:39 - INFO - codeparrot_training - Step 44651: {'lr': 0.0004043522168540341, 'samples': 22861824, 'steps': 44651, 'loss/train': 1.3720450401306152}
-03/05/2022 17:57:40 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/05/2022 17:57:44 - INFO - codeparrot_training - Step 44652: {'lr': 0.0004043480423090664, 'samples': 22862336, 'steps': 44652, 'loss/train': 1.9588886499404907}
-03/05/2022 17:57:47 - INFO - codeparrot_training - Step 44653: {'lr': 0.0004043438676945518, 'samples': 22862848, 'steps': 44653, 'loss/train': 1.4956998825073242}
-03/05/2022 17:57:48 - INFO - codeparrot_training - Skipping example with length 487 (seq_length=1024)
-03/05/2022 17:57:52 - INFO - codeparrot_training - Step 44654: {'lr': 0.0004043396930104922, 'samples': 22863360, 'steps': 44654, 'loss/train': 1.8448140621185303}
-03/05/2022 17:57:55 - INFO - codeparrot_training - Step 44655: {'lr': 0.0004043355182568895, 'samples': 22863872, 'steps': 44655, 'loss/train': 1.2778677940368652}
-03/05/2022 17:57:57 - INFO - codeparrot_training - Skipping example with length 387 (seq_length=1024)
-03/05/2022 17:58:01 - INFO - codeparrot_training - Step 44656: {'lr': 0.00040433134343374565, 'samples': 22864384, 'steps': 44656, 'loss/train': 2.1149306297302246}
-03/05/2022 17:58:04 - INFO - codeparrot_training - Step 44657: {'lr': 0.0004043271685410625, 'samples': 22864896, 'steps': 44657, 'loss/train': 1.0620455741882324}
-03/05/2022 17:58:05 - INFO - codeparrot_training - Skipping example with length 318 (seq_length=1024)
-03/05/2022 17:58:09 - INFO - codeparrot_training - Step 44658: {'lr': 0.00040432299357884185, 'samples': 22865408, 'steps': 44658, 'loss/train': 1.153825283050537}
-03/05/2022 17:58:13 - INFO - codeparrot_training - Step 44659: {'lr': 0.0004043188185470856, 'samples': 22865920, 'steps': 44659, 'loss/train': 1.006649136543274}
-03/05/2022 17:58:14 - INFO - codeparrot_training - Skipping example with length 894 (seq_length=1024)
-03/05/2022 17:58:18 - INFO - codeparrot_training - Step 44660: {'lr': 0.00040431464344579585, 'samples': 22866432, 'steps': 44660, 'loss/train': 1.7236055135726929}
-03/05/2022 17:58:21 - INFO - codeparrot_training - Step 44661: {'lr': 0.00040431046827497415, 'samples': 22866944, 'steps': 44661, 'loss/train': 1.9976431131362915}
-03/05/2022 17:58:22 - INFO - codeparrot_training - Skipping example with length 928 (seq_length=1024)
-03/05/2022 17:58:26 - INFO - codeparrot_training - Step 44662: {'lr': 0.00040430629303462256, 'samples': 22867456, 'steps': 44662, 'loss/train': 2.4302759170532227}
-03/05/2022 17:58:29 - INFO - codeparrot_training - Step 44663: {'lr': 0.000404302117724743, 'samples': 22867968, 'steps': 44663, 'loss/train': 2.144680976867676}
-03/05/2022 17:58:31 - INFO - codeparrot_training - Skipping example with length 338 (seq_length=1024)
-03/05/2022 17:58:34 - INFO - codeparrot_training - Step 44664: {'lr': 0.00040429794234533726, 'samples': 22868480, 'steps': 44664, 'loss/train': 2.2752296924591064}
-03/05/2022 17:58:38 - INFO - codeparrot_training - Step 44665: {'lr': 0.0004042937668964072, 'samples': 22868992, 'steps': 44665, 'loss/train': 1.6671215295791626}
-03/05/2022 17:58:39 - INFO - codeparrot_training - Skipping example with length 991 (seq_length=1024)
-03/05/2022 17:58:43 - INFO - codeparrot_training - Step 44666: {'lr': 0.00040428959137795475, 'samples': 22869504, 'steps': 44666, 'loss/train': 1.5526199340820312}
-03/05/2022 17:58:46 - INFO - codeparrot_training - Step 44667: {'lr': 0.0004042854157899818, 'samples': 22870016, 'steps': 44667, 'loss/train': 1.8484325408935547}
-03/05/2022 17:58:48 - INFO - codeparrot_training - Skipping example with length 562 (seq_length=1024)
-03/05/2022 17:58:52 - INFO - codeparrot_training - Step 44668: {'lr': 0.0004042812401324902, 'samples': 22870528, 'steps': 44668, 'loss/train': 1.860159993171692}
-03/05/2022 17:58:55 - INFO - codeparrot_training - Step 44669: {'lr': 0.0004042770644054819, 'samples': 22871040, 'steps': 44669, 'loss/train': 1.5979058742523193}
-03/05/2022 17:58:57 - INFO - codeparrot_training - Skipping example with length 307 (seq_length=1024)
-03/05/2022 17:59:00 - INFO - codeparrot_training - Step 44670: {'lr': 0.0004042728886089587, 'samples': 22871552, 'steps': 44670, 'loss/train': 1.4401867389678955}
-03/05/2022 17:59:03 - INFO - codeparrot_training - Step 44671: {'lr': 0.00040426871274292257, 'samples': 22872064, 'steps': 44671, 'loss/train': 1.4919852018356323}
-03/05/2022 17:59:05 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/05/2022 17:59:08 - INFO - codeparrot_training - Step 44672: {'lr': 0.00040426453680737534, 'samples': 22872576, 'steps': 44672, 'loss/train': 1.7116501331329346}
-03/05/2022 17:59:12 - INFO - codeparrot_training - Step 44673: {'lr': 0.0004042603608023189, 'samples': 22873088, 'steps': 44673, 'loss/train': 1.9249149560928345}
-03/05/2022 17:59:14 - INFO - codeparrot_training - Skipping example with length 940 (seq_length=1024)
-03/05/2022 17:59:17 - INFO - codeparrot_training - Step 44674: {'lr': 0.00040425618472775504, 'samples': 22873600, 'steps': 44674, 'loss/train': 1.7871631383895874}
-03/05/2022 17:59:20 - INFO - codeparrot_training - Step 44675: {'lr': 0.0004042520085836857, 'samples': 22874112, 'steps': 44675, 'loss/train': 1.433358073234558}
-03/05/2022 17:59:22 - INFO - codeparrot_training - Skipping example with length 952 (seq_length=1024)
-03/05/2022 17:59:26 - INFO - codeparrot_training - Step 44676: {'lr': 0.0004042478323701129, 'samples': 22874624, 'steps': 44676, 'loss/train': 0.9810197353363037}
-03/05/2022 17:59:29 - INFO - codeparrot_training - Step 44677: {'lr': 0.00040424365608703836, 'samples': 22875136, 'steps': 44677, 'loss/train': 1.318591833114624}
-03/05/2022 17:59:31 - INFO - codeparrot_training - Skipping example with length 602 (seq_length=1024)
-03/05/2022 17:59:34 - INFO - codeparrot_training - Step 44678: {'lr': 0.00040423947973446404, 'samples': 22875648, 'steps': 44678, 'loss/train': 1.9786490201950073}
-03/05/2022 17:59:37 - INFO - codeparrot_training - Step 44679: {'lr': 0.00040423530331239177, 'samples': 22876160, 'steps': 44679, 'loss/train': 2.048063039779663}
-03/05/2022 17:59:39 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/05/2022 17:59:43 - INFO - codeparrot_training - Step 44680: {'lr': 0.0004042311268208234, 'samples': 22876672, 'steps': 44680, 'loss/train': 1.1694409847259521}
-03/05/2022 17:59:46 - INFO - codeparrot_training - Step 44681: {'lr': 0.00040422695025976084, 'samples': 22877184, 'steps': 44681, 'loss/train': 1.512878179550171}
-03/05/2022 17:59:48 - INFO - codeparrot_training - Skipping example with length 284 (seq_length=1024)
-03/05/2022 17:59:51 - INFO - codeparrot_training - Step 44682: {'lr': 0.00040422277362920614, 'samples': 22877696, 'steps': 44682, 'loss/train': 1.7980293035507202}
-03/05/2022 17:59:54 - INFO - codeparrot_training - Step 44683: {'lr': 0.0004042185969291609, 'samples': 22878208, 'steps': 44683, 'loss/train': 1.7321280241012573}
-03/05/2022 17:59:57 - INFO - codeparrot_training - Skipping example with length 279 (seq_length=1024)
-03/05/2022 18:00:00 - INFO - codeparrot_training - Step 44684: {'lr': 0.00040421442015962727, 'samples': 22878720, 'steps': 44684, 'loss/train': 1.7772185802459717}
-03/05/2022 18:00:03 - INFO - codeparrot_training - Step 44685: {'lr': 0.0004042102433206069, 'samples': 22879232, 'steps': 44685, 'loss/train': 1.0352022647857666}
-03/05/2022 18:00:05 - INFO - codeparrot_training - Skipping example with length 40 (seq_length=1024)
-03/05/2022 18:00:08 - INFO - codeparrot_training - Step 44686: {'lr': 0.0004042060664121018, 'samples': 22879744, 'steps': 44686, 'loss/train': 0.8618285059928894}
-03/05/2022 18:00:11 - INFO - codeparrot_training - Step 44687: {'lr': 0.00040420188943411385, 'samples': 22880256, 'steps': 44687, 'loss/train': 1.0239217281341553}
-03/05/2022 18:00:14 - INFO - codeparrot_training - Skipping example with length 943 (seq_length=1024)
-03/05/2022 18:00:17 - INFO - codeparrot_training - Step 44688: {'lr': 0.0004041977123866448, 'samples': 22880768, 'steps': 44688, 'loss/train': 1.0650559663772583}
-03/05/2022 18:00:20 - INFO - codeparrot_training - Step 44689: {'lr': 0.0004041935352696968, 'samples': 22881280, 'steps': 44689, 'loss/train': 0.9315967559814453}
-03/05/2022 18:00:23 - INFO - codeparrot_training - Skipping example with length 878 (seq_length=1024)
-03/05/2022 18:00:25 - INFO - codeparrot_training - Step 44690: {'lr': 0.00040418935808327153, 'samples': 22881792, 'steps': 44690, 'loss/train': 1.9698084592819214}
-03/05/2022 18:00:28 - INFO - codeparrot_training - Step 44691: {'lr': 0.00040418518082737087, 'samples': 22882304, 'steps': 44691, 'loss/train': 3.1027791500091553}
-03/05/2022 18:00:31 - INFO - codeparrot_training - Skipping example with length 478 (seq_length=1024)
-03/05/2022 18:00:33 - INFO - codeparrot_training - Step 44692: {'lr': 0.0004041810035019967, 'samples': 22882816, 'steps': 44692, 'loss/train': 1.7663195133209229}
-03/05/2022 18:00:37 - INFO - codeparrot_training - Step 44693: {'lr': 0.00040417682610715107, 'samples': 22883328, 'steps': 44693, 'loss/train': 0.7426781058311462}
-03/05/2022 18:00:39 - INFO - codeparrot_training - Skipping example with length 244 (seq_length=1024)
-03/05/2022 18:00:42 - INFO - codeparrot_training - Step 44694: {'lr': 0.00040417264864283563, 'samples': 22883840, 'steps': 44694, 'loss/train': 1.9624840021133423}
-03/05/2022 18:00:45 - INFO - codeparrot_training - Step 44695: {'lr': 0.00040416847110905243, 'samples': 22884352, 'steps': 44695, 'loss/train': 2.138732671737671}
-03/05/2022 18:00:48 - INFO - codeparrot_training - Skipping example with length 818 (seq_length=1024)
-03/05/2022 18:00:50 - INFO - codeparrot_training - Step 44696: {'lr': 0.0004041642935058033, 'samples': 22884864, 'steps': 44696, 'loss/train': 0.8881983757019043}
-03/05/2022 18:00:53 - INFO - codeparrot_training - Step 44697: {'lr': 0.0004041601158330901, 'samples': 22885376, 'steps': 44697, 'loss/train': 1.7319632768630981}
-03/05/2022 18:00:56 - INFO - codeparrot_training - Skipping example with length 738 (seq_length=1024)
-03/05/2022 18:00:59 - INFO - codeparrot_training - Step 44698: {'lr': 0.0004041559380909148, 'samples': 22885888, 'steps': 44698, 'loss/train': 1.7242436408996582}
-03/05/2022 18:01:02 - INFO - codeparrot_training - Step 44699: {'lr': 0.00040415176027927915, 'samples': 22886400, 'steps': 44699, 'loss/train': 1.6091818809509277}
-03/05/2022 18:01:05 - INFO - codeparrot_training - Step 44700: {'lr': 0.00040414758239818506, 'samples': 22886912, 'steps': 44700, 'loss/train': 1.5661252737045288}
-03/05/2022 18:01:06 - INFO - codeparrot_training - Skipping example with length 951 (seq_length=1024)
-03/05/2022 18:01:11 - INFO - codeparrot_training - Step 44701: {'lr': 0.00040414340444763455, 'samples': 22887424, 'steps': 44701, 'loss/train': 1.155908465385437}
-03/05/2022 18:01:14 - INFO - codeparrot_training - Step 44702: {'lr': 0.0004041392264276292, 'samples': 22887936, 'steps': 44702, 'loss/train': 1.9351023435592651}
-03/05/2022 18:01:14 - INFO - codeparrot_training - Skipping example with length 958 (seq_length=1024)
-03/05/2022 18:01:19 - INFO - codeparrot_training - Step 44703: {'lr': 0.00040413504833817127, 'samples': 22888448, 'steps': 44703, 'loss/train': 1.3385438919067383}
-03/05/2022 18:01:22 - INFO - codeparrot_training - Step 44704: {'lr': 0.0004041308701792625, 'samples': 22888960, 'steps': 44704, 'loss/train': 0.7219630479812622}
-03/05/2022 18:01:23 - INFO - codeparrot_training - Skipping example with length 208 (seq_length=1024)
-03/05/2022 18:01:28 - INFO - codeparrot_training - Step 44705: {'lr': 0.00040412669195090466, 'samples': 22889472, 'steps': 44705, 'loss/train': 1.3339745998382568}
-03/05/2022 18:01:31 - INFO - codeparrot_training - Step 44706: {'lr': 0.0004041225136530997, 'samples': 22889984, 'steps': 44706, 'loss/train': 0.8325849771499634}
-03/05/2022 18:01:31 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/05/2022 18:01:36 - INFO - codeparrot_training - Step 44707: {'lr': 0.0004041183352858495, 'samples': 22890496, 'steps': 44707, 'loss/train': 1.157829999923706}
-03/05/2022 18:01:39 - INFO - codeparrot_training - Step 44708: {'lr': 0.00040411415684915596, 'samples': 22891008, 'steps': 44708, 'loss/train': 1.410601258277893}
-03/05/2022 18:01:39 - INFO - codeparrot_training - Skipping example with length 810 (seq_length=1024)
-03/05/2022 18:01:44 - INFO - codeparrot_training - Step 44709: {'lr': 0.000404109978343021, 'samples': 22891520, 'steps': 44709, 'loss/train': 1.8412503004074097}
-03/05/2022 18:01:48 - INFO - codeparrot_training - Step 44710: {'lr': 0.0004041057997674464, 'samples': 22892032, 'steps': 44710, 'loss/train': 1.4749433994293213}
-03/05/2022 18:01:48 - INFO - codeparrot_training - Skipping example with length 201 (seq_length=1024)
-03/05/2022 18:01:53 - INFO - codeparrot_training - Step 44711: {'lr': 0.0004041016211224342, 'samples': 22892544, 'steps': 44711, 'loss/train': 1.165158987045288}
-03/05/2022 18:01:56 - INFO - codeparrot_training - Step 44712: {'lr': 0.0004040974424079862, 'samples': 22893056, 'steps': 44712, 'loss/train': 1.8320212364196777}
-03/05/2022 18:01:57 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 18:02:01 - INFO - codeparrot_training - Step 44713: {'lr': 0.00040409326362410416, 'samples': 22893568, 'steps': 44713, 'loss/train': 1.5248128175735474}
-03/05/2022 18:02:05 - INFO - codeparrot_training - Step 44714: {'lr': 0.0004040890847707901, 'samples': 22894080, 'steps': 44714, 'loss/train': 1.8229146003723145}
-03/05/2022 18:02:05 - INFO - codeparrot_training - Skipping example with length 773 (seq_length=1024)
-03/05/2022 18:02:10 - INFO - codeparrot_training - Step 44715: {'lr': 0.0004040849058480459, 'samples': 22894592, 'steps': 44715, 'loss/train': 1.7934163808822632}
-03/05/2022 18:02:13 - INFO - codeparrot_training - Step 44716: {'lr': 0.0004040807268558734, 'samples': 22895104, 'steps': 44716, 'loss/train': 2.1351511478424072}
-03/05/2022 18:02:14 - INFO - codeparrot_training - Skipping example with length 420 (seq_length=1024)
-03/05/2022 18:02:18 - INFO - codeparrot_training - Step 44717: {'lr': 0.0004040765477942745, 'samples': 22895616, 'steps': 44717, 'loss/train': 1.5345141887664795}
-03/05/2022 18:02:21 - INFO - codeparrot_training - Step 44718: {'lr': 0.0004040723686632512, 'samples': 22896128, 'steps': 44718, 'loss/train': 1.7860428094863892}
-03/05/2022 18:02:22 - INFO - codeparrot_training - Skipping example with length 315 (seq_length=1024)
-03/05/2022 18:02:27 - INFO - codeparrot_training - Step 44719: {'lr': 0.00040406818946280514, 'samples': 22896640, 'steps': 44719, 'loss/train': 0.9843380451202393}
-03/05/2022 18:02:30 - INFO - codeparrot_training - Step 44720: {'lr': 0.0004040640101929384, 'samples': 22897152, 'steps': 44720, 'loss/train': 1.941428780555725}
-03/05/2022 18:02:30 - INFO - codeparrot_training - Skipping example with length 458 (seq_length=1024)
-03/05/2022 18:02:35 - INFO - codeparrot_training - Step 44721: {'lr': 0.0004040598308536527, 'samples': 22897664, 'steps': 44721, 'loss/train': 1.6175614595413208}
-03/05/2022 18:02:38 - INFO - codeparrot_training - Step 44722: {'lr': 0.0004040556514449501, 'samples': 22898176, 'steps': 44722, 'loss/train': 2.392336368560791}
-03/05/2022 18:02:38 - INFO - codeparrot_training - Skipping example with length 407 (seq_length=1024)
-03/05/2022 18:02:43 - INFO - codeparrot_training - Step 44723: {'lr': 0.0004040514719668324, 'samples': 22898688, 'steps': 44723, 'loss/train': 1.6978230476379395}
-03/05/2022 18:02:47 - INFO - codeparrot_training - Step 44724: {'lr': 0.00040404729241930144, 'samples': 22899200, 'steps': 44724, 'loss/train': 1.69320809841156}
-03/05/2022 18:02:47 - INFO - codeparrot_training - Skipping example with length 214 (seq_length=1024)
-03/05/2022 18:02:52 - INFO - codeparrot_training - Step 44725: {'lr': 0.0004040431128023592, 'samples': 22899712, 'steps': 44725, 'loss/train': 2.0603320598602295}
-03/05/2022 18:02:55 - INFO - codeparrot_training - Step 44726: {'lr': 0.0004040389331160075, 'samples': 22900224, 'steps': 44726, 'loss/train': 2.0827510356903076}
-03/05/2022 18:02:56 - INFO - codeparrot_training - Skipping example with length 863 (seq_length=1024)
-03/05/2022 18:03:00 - INFO - codeparrot_training - Step 44727: {'lr': 0.00040403475336024816, 'samples': 22900736, 'steps': 44727, 'loss/train': 1.467716932296753}
-03/05/2022 18:03:04 - INFO - codeparrot_training - Step 44728: {'lr': 0.0004040305735350832, 'samples': 22901248, 'steps': 44728, 'loss/train': 0.8228468894958496}
-03/05/2022 18:03:04 - INFO - codeparrot_training - Skipping example with length 113 (seq_length=1024)
-03/05/2022 18:03:09 - INFO - codeparrot_training - Step 44729: {'lr': 0.00040402639364051443, 'samples': 22901760, 'steps': 44729, 'loss/train': 1.2233939170837402}
-03/05/2022 18:03:12 - INFO - codeparrot_training - Step 44730: {'lr': 0.0004040222136765437, 'samples': 22902272, 'steps': 44730, 'loss/train': 2.7464325428009033}
-03/05/2022 18:03:13 - INFO - codeparrot_training - Skipping example with length 947 (seq_length=1024)
-03/05/2022 18:03:17 - INFO - codeparrot_training - Step 44731: {'lr': 0.000404018033643173, 'samples': 22902784, 'steps': 44731, 'loss/train': 1.8208836317062378}
-03/05/2022 18:03:21 - INFO - codeparrot_training - Step 44732: {'lr': 0.00040401385354040415, 'samples': 22903296, 'steps': 44732, 'loss/train': 1.7777717113494873}
-03/05/2022 18:03:21 - INFO - codeparrot_training - Skipping example with length 439 (seq_length=1024)
-03/05/2022 18:03:26 - INFO - codeparrot_training - Step 44733: {'lr': 0.00040400967336823903, 'samples': 22903808, 'steps': 44733, 'loss/train': 1.181457281112671}
-03/05/2022 18:03:29 - INFO - codeparrot_training - Step 44734: {'lr': 0.0004040054931266795, 'samples': 22904320, 'steps': 44734, 'loss/train': 1.2707637548446655}
-03/05/2022 18:03:29 - INFO - codeparrot_training - Skipping example with length 532 (seq_length=1024)
-03/05/2022 18:03:34 - INFO - codeparrot_training - Step 44735: {'lr': 0.0004040013128157275, 'samples': 22904832, 'steps': 44735, 'loss/train': 1.1931248903274536}
-03/05/2022 18:03:38 - INFO - codeparrot_training - Step 44736: {'lr': 0.00040399713243538483, 'samples': 22905344, 'steps': 44736, 'loss/train': 1.4922715425491333}
-03/05/2022 18:03:38 - INFO - codeparrot_training - Skipping example with length 47 (seq_length=1024)
-03/05/2022 18:03:43 - INFO - codeparrot_training - Step 44737: {'lr': 0.00040399295198565344, 'samples': 22905856, 'steps': 44737, 'loss/train': 1.8285335302352905}
-03/05/2022 18:03:46 - INFO - codeparrot_training - Step 44738: {'lr': 0.0004039887714665352, 'samples': 22906368, 'steps': 44738, 'loss/train': 1.448887825012207}
-03/05/2022 18:03:46 - INFO - codeparrot_training - Skipping example with length 570 (seq_length=1024)
-03/05/2022 18:03:51 - INFO - codeparrot_training - Step 44739: {'lr': 0.0004039845908780321, 'samples': 22906880, 'steps': 44739, 'loss/train': 1.2528409957885742}
-03/05/2022 18:03:55 - INFO - codeparrot_training - Step 44740: {'lr': 0.00040398041022014585, 'samples': 22907392, 'steps': 44740, 'loss/train': 1.7456319332122803}
-03/05/2022 18:03:55 - INFO - codeparrot_training - Skipping example with length 706 (seq_length=1024)
-03/05/2022 18:04:00 - INFO - codeparrot_training - Step 44741: {'lr': 0.0004039762294928784, 'samples': 22907904, 'steps': 44741, 'loss/train': 1.465722680091858}
-03/05/2022 18:04:03 - INFO - codeparrot_training - Step 44742: {'lr': 0.0004039720486962316, 'samples': 22908416, 'steps': 44742, 'loss/train': 1.469164490699768}
-03/05/2022 18:04:03 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/05/2022 18:04:08 - INFO - codeparrot_training - Step 44743: {'lr': 0.00040396786783020747, 'samples': 22908928, 'steps': 44743, 'loss/train': 1.6062458753585815}
-03/05/2022 18:04:11 - INFO - codeparrot_training - Step 44744: {'lr': 0.00040396368689480766, 'samples': 22909440, 'steps': 44744, 'loss/train': 2.29386043548584}
-03/05/2022 18:04:11 - INFO - codeparrot_training - Skipping example with length 985 (seq_length=1024)
-03/05/2022 18:04:17 - INFO - codeparrot_training - Step 44745: {'lr': 0.00040395950589003425, 'samples': 22909952, 'steps': 44745, 'loss/train': 2.72452712059021}
-03/05/2022 18:04:20 - INFO - codeparrot_training - Step 44746: {'lr': 0.00040395532481588914, 'samples': 22910464, 'steps': 44746, 'loss/train': 1.93293297290802}
-03/05/2022 18:04:20 - INFO - codeparrot_training - Skipping example with length 953 (seq_length=1024)
-03/05/2022 18:04:25 - INFO - codeparrot_training - Step 44747: {'lr': 0.00040395114367237407, 'samples': 22910976, 'steps': 44747, 'loss/train': 2.1386055946350098}
-03/05/2022 18:04:28 - INFO - codeparrot_training - Step 44748: {'lr': 0.00040394696245949093, 'samples': 22911488, 'steps': 44748, 'loss/train': 1.6204466819763184}
-03/05/2022 18:04:29 - INFO - codeparrot_training - Skipping example with length 913 (seq_length=1024)
-03/05/2022 18:04:34 - INFO - codeparrot_training - Step 44749: {'lr': 0.0004039427811772417, 'samples': 22912000, 'steps': 44749, 'loss/train': 1.7062934637069702}
-03/05/2022 18:04:37 - INFO - codeparrot_training - Step 44750: {'lr': 0.0004039385998256283, 'samples': 22912512, 'steps': 44750, 'loss/train': 1.934909701347351}
-03/05/2022 18:04:37 - INFO - codeparrot_training - Skipping example with length 1001 (seq_length=1024)
-03/05/2022 18:04:43 - INFO - codeparrot_training - Step 44751: {'lr': 0.0004039344184046525, 'samples': 22913024, 'steps': 44751, 'loss/train': 1.1866395473480225}
-03/05/2022 18:04:46 - INFO - codeparrot_training - Step 44752: {'lr': 0.00040393023691431617, 'samples': 22913536, 'steps': 44752, 'loss/train': 1.999855399131775}
-03/05/2022 18:04:47 - INFO - codeparrot_training - Skipping example with length 557 (seq_length=1024)
-03/05/2022 18:04:51 - INFO - codeparrot_training - Step 44753: {'lr': 0.00040392605535462137, 'samples': 22914048, 'steps': 44753, 'loss/train': 1.30694580078125}
-03/05/2022 18:04:54 - INFO - codeparrot_training - Step 44754: {'lr': 0.00040392187372556977, 'samples': 22914560, 'steps': 44754, 'loss/train': 1.4586372375488281}
-03/05/2022 18:04:56 - INFO - codeparrot_training - Skipping example with length 873 (seq_length=1024)
-03/05/2022 18:05:00 - INFO - codeparrot_training - Step 44755: {'lr': 0.00040391769202716333, 'samples': 22915072, 'steps': 44755, 'loss/train': 0.947270929813385}
-03/05/2022 18:05:03 - INFO - codeparrot_training - Step 44756: {'lr': 0.00040391351025940406, 'samples': 22915584, 'steps': 44756, 'loss/train': 1.3067102432250977}
-03/05/2022 18:05:04 - INFO - codeparrot_training - Skipping example with length 106 (seq_length=1024)
-03/05/2022 18:05:08 - INFO - codeparrot_training - Step 44757: {'lr': 0.00040390932842229363, 'samples': 22916096, 'steps': 44757, 'loss/train': 1.604349970817566}
-03/05/2022 18:05:11 - INFO - codeparrot_training - Step 44758: {'lr': 0.0004039051465158341, 'samples': 22916608, 'steps': 44758, 'loss/train': 1.7319743633270264}
-03/05/2022 18:05:12 - INFO - codeparrot_training - Skipping example with length 764 (seq_length=1024)
-03/05/2022 18:05:16 - INFO - codeparrot_training - Step 44759: {'lr': 0.0004039009645400272, 'samples': 22917120, 'steps': 44759, 'loss/train': 1.6737405061721802}
-03/05/2022 18:05:20 - INFO - codeparrot_training - Step 44760: {'lr': 0.00040389678249487504, 'samples': 22917632, 'steps': 44760, 'loss/train': 1.6790167093276978}
-03/05/2022 18:05:21 - INFO - codeparrot_training - Skipping example with length 979 (seq_length=1024)
-03/05/2022 18:05:25 - INFO - codeparrot_training - Step 44761: {'lr': 0.00040389260038037924, 'samples': 22918144, 'steps': 44761, 'loss/train': 2.531528949737549}
-03/05/2022 18:05:28 - INFO - codeparrot_training - Step 44762: {'lr': 0.0004038884181965419, 'samples': 22918656, 'steps': 44762, 'loss/train': 1.1833093166351318}
-03/05/2022 18:05:29 - INFO - codeparrot_training - Skipping example with length 489 (seq_length=1024)
-03/05/2022 18:05:34 - INFO - codeparrot_training - Step 44763: {'lr': 0.0004038842359433647, 'samples': 22919168, 'steps': 44763, 'loss/train': 1.6753454208374023}
-03/05/2022 18:05:37 - INFO - codeparrot_training - Step 44764: {'lr': 0.0004038800536208497, 'samples': 22919680, 'steps': 44764, 'loss/train': 2.1583492755889893}
-03/05/2022 18:05:39 - INFO - codeparrot_training - Skipping example with length 1016 (seq_length=1024)
-03/05/2022 18:05:42 - INFO - codeparrot_training - Step 44765: {'lr': 0.00040387587122899877, 'samples': 22920192, 'steps': 44765, 'loss/train': 0.8816787600517273}
-03/05/2022 18:05:45 - INFO - codeparrot_training - Step 44766: {'lr': 0.0004038716887678137, 'samples': 22920704, 'steps': 44766, 'loss/train': 1.5429033041000366}
-03/05/2022 18:05:47 - INFO - codeparrot_training - Skipping example with length 664 (seq_length=1024)
-03/05/2022 18:05:51 - INFO - codeparrot_training - Step 44767: {'lr': 0.0004038675062372964, 'samples': 22921216, 'steps': 44767, 'loss/train': 1.9629766941070557}
-03/05/2022 18:05:54 - INFO - codeparrot_training - Step 44768: {'lr': 0.00040386332363744884, 'samples': 22921728, 'steps': 44768, 'loss/train': 1.8926219940185547}
-03/05/2022 18:05:55 - INFO - codeparrot_training - Skipping example with length 183 (seq_length=1024)
-03/05/2022 18:05:59 - INFO - codeparrot_training - Step 44769: {'lr': 0.0004038591409682728, 'samples': 22922240, 'steps': 44769, 'loss/train': 2.050028085708618}
-03/05/2022 18:06:02 - INFO - codeparrot_training - Step 44770: {'lr': 0.00040385495822977015, 'samples': 22922752, 'steps': 44770, 'loss/train': 1.8652485609054565}
-03/05/2022 18:06:04 - INFO - codeparrot_training - Skipping example with length 56 (seq_length=1024)
-03/05/2022 18:06:07 - INFO - codeparrot_training - Step 44771: {'lr': 0.00040385077542194294, 'samples': 22923264, 'steps': 44771, 'loss/train': 1.6996325254440308}
-03/05/2022 18:06:11 - INFO - codeparrot_training - Step 44772: {'lr': 0.0004038465925447929, 'samples': 22923776, 'steps': 44772, 'loss/train': 1.9292057752609253}
-03/05/2022 18:06:12 - INFO - codeparrot_training - Skipping example with length 80 (seq_length=1024)
-03/05/2022 18:06:16 - INFO - codeparrot_training - Step 44773: {'lr': 0.00040384240959832196, 'samples': 22924288, 'steps': 44773, 'loss/train': 1.6491014957427979}
-03/05/2022 18:06:19 - INFO - codeparrot_training - Step 44774: {'lr': 0.000403838226582532, 'samples': 22924800, 'steps': 44774, 'loss/train': 1.7343530654907227}
-03/05/2022 18:06:20 - INFO - codeparrot_training - Skipping example with length 41 (seq_length=1024)
-03/05/2022 18:06:24 - INFO - codeparrot_training - Step 44775: {'lr': 0.00040383404349742484, 'samples': 22925312, 'steps': 44775, 'loss/train': 1.5150847434997559}
-03/05/2022 18:06:27 - INFO - codeparrot_training - Step 44776: {'lr': 0.0004038298603430025, 'samples': 22925824, 'steps': 44776, 'loss/train': 1.566767692565918}
-03/05/2022 18:06:29 - INFO - codeparrot_training - Skipping example with length 170 (seq_length=1024)
-03/05/2022 18:06:33 - INFO - codeparrot_training - Step 44777: {'lr': 0.0004038256771192668, 'samples': 22926336, 'steps': 44777, 'loss/train': 1.926650047302246}
-03/05/2022 18:06:36 - INFO - codeparrot_training - Step 44778: {'lr': 0.00040382149382621967, 'samples': 22926848, 'steps': 44778, 'loss/train': 1.8420392274856567}
-03/05/2022 18:06:37 - INFO - codeparrot_training - Skipping example with length 306 (seq_length=1024)
-03/05/2022 18:06:41 - INFO - codeparrot_training - Step 44779: {'lr': 0.00040381731046386295, 'samples': 22927360, 'steps': 44779, 'loss/train': 1.264277458190918}
-03/05/2022 18:06:44 - INFO - codeparrot_training - Step 44780: {'lr': 0.0004038131270321984, 'samples': 22927872, 'steps': 44780, 'loss/train': 1.203944444656372}
-03/05/2022 18:06:45 - INFO - codeparrot_training - Skipping example with length 874 (seq_length=1024)
-03/05/2022 18:06:50 - INFO - codeparrot_training - Step 44781: {'lr': 0.0004038089435312281, 'samples': 22928384, 'steps': 44781, 'loss/train': 3.237008810043335}
-03/05/2022 18:06:53 - INFO - codeparrot_training - Step 44782: {'lr': 0.0004038047599609539, 'samples': 22928896, 'steps': 44782, 'loss/train': 1.7700474262237549}
-03/05/2022 18:06:53 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 18:06:58 - INFO - codeparrot_training - Step 44783: {'lr': 0.00040380057632137756, 'samples': 22929408, 'steps': 44783, 'loss/train': 1.3696911334991455}
-03/05/2022 18:07:01 - INFO - codeparrot_training - Step 44784: {'lr': 0.0004037963926125011, 'samples': 22929920, 'steps': 44784, 'loss/train': 1.3393715620040894}
-03/05/2022 18:07:02 - INFO - codeparrot_training - Skipping example with length 186 (seq_length=1024)
-03/05/2022 18:07:07 - INFO - codeparrot_training - Step 44785: {'lr': 0.00040379220883432644, 'samples': 22930432, 'steps': 44785, 'loss/train': 1.1983351707458496}
-03/05/2022 18:07:10 - INFO - codeparrot_training - Step 44786: {'lr': 0.0004037880249868553, 'samples': 22930944, 'steps': 44786, 'loss/train': 1.852432131767273}
-03/05/2022 18:07:11 - INFO - codeparrot_training - Skipping example with length 165 (seq_length=1024)
-03/05/2022 18:07:15 - INFO - codeparrot_training - Step 44787: {'lr': 0.00040378384107008967, 'samples': 22931456, 'steps': 44787, 'loss/train': 3.012937068939209}
-03/05/2022 18:07:18 - INFO - codeparrot_training - Step 44788: {'lr': 0.00040377965708403133, 'samples': 22931968, 'steps': 44788, 'loss/train': 1.446277379989624}
-03/05/2022 18:07:20 - INFO - codeparrot_training - Skipping example with length 739 (seq_length=1024)
-03/05/2022 18:07:24 - INFO - codeparrot_training - Step 44789: {'lr': 0.00040377547302868235, 'samples': 22932480, 'steps': 44789, 'loss/train': 2.1813833713531494}
-03/05/2022 18:07:27 - INFO - codeparrot_training - Step 44790: {'lr': 0.00040377128890404444, 'samples': 22932992, 'steps': 44790, 'loss/train': 1.3893228769302368}
-03/05/2022 18:07:29 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/05/2022 18:07:32 - INFO - codeparrot_training - Step 44791: {'lr': 0.00040376710471011967, 'samples': 22933504, 'steps': 44791, 'loss/train': 0.5895149111747742}
-03/05/2022 18:07:36 - INFO - codeparrot_training - Step 44792: {'lr': 0.0004037629204469098, 'samples': 22934016, 'steps': 44792, 'loss/train': 2.247985363006592}
-03/05/2022 18:07:38 - INFO - codeparrot_training - Skipping example with length 101 (seq_length=1024)
-03/05/2022 18:07:41 - INFO - codeparrot_training - Step 44793: {'lr': 0.0004037587361144166, 'samples': 22934528, 'steps': 44793, 'loss/train': 1.6632044315338135}
-03/05/2022 18:07:44 - INFO - codeparrot_training - Step 44794: {'lr': 0.0004037545517126422, 'samples': 22935040, 'steps': 44794, 'loss/train': 1.826718807220459}
-03/05/2022 18:07:46 - INFO - codeparrot_training - Skipping example with length 629 (seq_length=1024)
-03/05/2022 18:07:49 - INFO - codeparrot_training - Step 44795: {'lr': 0.0004037503672415883, 'samples': 22935552, 'steps': 44795, 'loss/train': 0.7954122424125671}
-03/05/2022 18:07:52 - INFO - codeparrot_training - Step 44796: {'lr': 0.000403746182701257, 'samples': 22936064, 'steps': 44796, 'loss/train': 1.3659608364105225}
-03/05/2022 18:07:54 - INFO - codeparrot_training - Skipping example with length 689 (seq_length=1024)
-03/05/2022 18:07:58 - INFO - codeparrot_training - Step 44797: {'lr': 0.0004037419980916499, 'samples': 22936576, 'steps': 44797, 'loss/train': 0.5968263149261475}
-03/05/2022 18:08:01 - INFO - codeparrot_training - Step 44798: {'lr': 0.00040373781341276904, 'samples': 22937088, 'steps': 44798, 'loss/train': 1.1562955379486084}
-03/05/2022 18:08:03 - INFO - codeparrot_training - Skipping example with length 574 (seq_length=1024)
-03/05/2022 18:08:06 - INFO - codeparrot_training - Step 44799: {'lr': 0.00040373362866461633, 'samples': 22937600, 'steps': 44799, 'loss/train': 1.068071722984314}
-03/05/2022 18:08:09 - INFO - codeparrot_training - Step 44800: {'lr': 0.0004037294438471936, 'samples': 22938112, 'steps': 44800, 'loss/train': 1.5918644666671753}
-03/05/2022 18:08:11 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/05/2022 18:08:15 - INFO - codeparrot_training - Step 44801: {'lr': 0.00040372525896050285, 'samples': 22938624, 'steps': 44801, 'loss/train': 1.641677975654602}
-03/05/2022 18:08:18 - INFO - codeparrot_training - Step 44802: {'lr': 0.0004037210740045457, 'samples': 22939136, 'steps': 44802, 'loss/train': 1.9541047811508179}
-03/05/2022 18:08:23 - INFO - codeparrot_training - Step 44803: {'lr': 0.0004037168889793243, 'samples': 22939648, 'steps': 44803, 'loss/train': 1.513360857963562}
-03/05/2022 18:08:26 - INFO - codeparrot_training - Step 44804: {'lr': 0.0004037127038848404, 'samples': 22940160, 'steps': 44804, 'loss/train': 1.5611988306045532}
-03/05/2022 18:08:28 - INFO - codeparrot_training - Skipping example with length 759 (seq_length=1024)
-03/05/2022 18:08:31 - INFO - codeparrot_training - Step 44805: {'lr': 0.00040370851872109604, 'samples': 22940672, 'steps': 44805, 'loss/train': 1.2371946573257446}
-03/05/2022 18:08:35 - INFO - codeparrot_training - Step 44806: {'lr': 0.0004037043334880929, 'samples': 22941184, 'steps': 44806, 'loss/train': 2.403083086013794}
-03/05/2022 18:08:36 - INFO - codeparrot_training - Skipping example with length 16 (seq_length=1024)
-03/05/2022 18:08:40 - INFO - codeparrot_training - Step 44807: {'lr': 0.000403700148185833, 'samples': 22941696, 'steps': 44807, 'loss/train': 1.6951184272766113}
-03/05/2022 18:08:43 - INFO - codeparrot_training - Step 44808: {'lr': 0.00040369596281431816, 'samples': 22942208, 'steps': 44808, 'loss/train': 1.3963836431503296}
-03/05/2022 18:08:45 - INFO - codeparrot_training - Skipping example with length 199 (seq_length=1024)
-03/05/2022 18:08:48 - INFO - codeparrot_training - Step 44809: {'lr': 0.0004036917773735502, 'samples': 22942720, 'steps': 44809, 'loss/train': 1.5122878551483154}
-03/05/2022 18:08:52 - INFO - codeparrot_training - Step 44810: {'lr': 0.00040368759186353123, 'samples': 22943232, 'steps': 44810, 'loss/train': 0.5519545078277588}
-03/05/2022 18:08:53 - INFO - codeparrot_training - Skipping example with length 10 (seq_length=1024)
-03/05/2022 18:08:57 - INFO - codeparrot_training - Step 44811: {'lr': 0.0004036834062842629, 'samples': 22943744, 'steps': 44811, 'loss/train': 2.0449063777923584}
-03/05/2022 18:09:00 - INFO - codeparrot_training - Step 44812: {'lr': 0.00040367922063574735, 'samples': 22944256, 'steps': 44812, 'loss/train': 1.9026380777359009}
-03/05/2022 18:09:02 - INFO - codeparrot_training - Skipping example with length 100 (seq_length=1024)
-03/05/2022 18:09:05 - INFO - codeparrot_training - Step 44813: {'lr': 0.0004036750349179862, 'samples': 22944768, 'steps': 44813, 'loss/train': 0.47377830743789673}
-03/05/2022 18:09:08 - INFO - codeparrot_training - Step 44814: {'lr': 0.00040367084913098153, 'samples': 22945280, 'steps': 44814, 'loss/train': 1.7244184017181396}
-03/05/2022 18:09:10 - INFO - codeparrot_training - Skipping example with length 473 (seq_length=1024)
-03/05/2022 18:09:14 - INFO - codeparrot_training - Step 44815: {'lr': 0.000403666663274735, 'samples': 22945792, 'steps': 44815, 'loss/train': 1.5762567520141602}
-03/05/2022 18:09:17 - INFO - codeparrot_training - Step 44816: {'lr': 0.0004036624773492488, 'samples': 22946304, 'steps': 44816, 'loss/train': 1.7458164691925049}
-03/05/2022 18:09:19 - INFO - codeparrot_training - Skipping example with length 941 (seq_length=1024)
-03/05/2022 18:09:22 - INFO - codeparrot_training - Step 44817: {'lr': 0.0004036582913545246, 'samples': 22946816, 'steps': 44817, 'loss/train': 1.249213457107544}
-03/05/2022 18:09:25 - INFO - codeparrot_training - Step 44818: {'lr': 0.0004036541052905643, 'samples': 22947328, 'steps': 44818, 'loss/train': 1.8429397344589233}
-03/05/2022 18:09:27 - INFO - codeparrot_training - Skipping example with length 838 (seq_length=1024)
-03/05/2022 18:09:31 - INFO - codeparrot_training - Step 44819: {'lr': 0.0004036499191573699, 'samples': 22947840, 'steps': 44819, 'loss/train': 2.037851572036743}
-03/05/2022 18:09:34 - INFO - codeparrot_training - Step 44820: {'lr': 0.00040364573295494316, 'samples': 22948352, 'steps': 44820, 'loss/train': 0.39653921127319336}
-03/05/2022 18:09:36 - INFO - codeparrot_training - Skipping example with length 914 (seq_length=1024)
-03/05/2022 18:09:39 - INFO - codeparrot_training - Step 44821: {'lr': 0.00040364154668328604, 'samples': 22948864, 'steps': 44821, 'loss/train': 1.0286256074905396}
-03/05/2022 18:09:42 - INFO - codeparrot_training - Step 44822: {'lr': 0.0004036373603424004, 'samples': 22949376, 'steps': 44822, 'loss/train': 1.5136947631835938}
-03/05/2022 18:09:48 - INFO - codeparrot_training - Step 44823: {'lr': 0.00040363317393228814, 'samples': 22949888, 'steps': 44823, 'loss/train': 1.829037070274353}
-03/05/2022 18:09:51 - INFO - codeparrot_training - Step 44824: {'lr': 0.00040362898745295117, 'samples': 22950400, 'steps': 44824, 'loss/train': 1.7559410333633423}
-03/05/2022 18:09:53 - INFO - codeparrot_training - Skipping example with length 299 (seq_length=1024)
-03/05/2022 18:09:56 - INFO - codeparrot_training - Step 44825: {'lr': 0.00040362480090439136, 'samples': 22950912, 'steps': 44825, 'loss/train': 2.6628947257995605}
-03/05/2022 18:09:59 - INFO - codeparrot_training - Step 44826: {'lr': 0.00040362061428661055, 'samples': 22951424, 'steps': 44826, 'loss/train': 1.542106032371521}
-03/05/2022 18:10:02 - INFO - codeparrot_training - Skipping example with length 408 (seq_length=1024)
-03/05/2022 18:10:05 - INFO - codeparrot_training - Step 44827: {'lr': 0.0004036164275996107, 'samples': 22951936, 'steps': 44827, 'loss/train': 1.7421807050704956}
-03/05/2022 18:10:08 - INFO - codeparrot_training - Step 44828: {'lr': 0.00040361224084339365, 'samples': 22952448, 'steps': 44828, 'loss/train': 1.2294347286224365}
-03/05/2022 18:10:10 - INFO - codeparrot_training - Skipping example with length 787 (seq_length=1024)
-03/05/2022 18:10:13 - INFO - codeparrot_training - Step 44829: {'lr': 0.00040360805401796124, 'samples': 22952960, 'steps': 44829, 'loss/train': 0.35329821705818176}
-03/05/2022 18:10:16 - INFO - codeparrot_training - Step 44830: {'lr': 0.0004036038671233154, 'samples': 22953472, 'steps': 44830, 'loss/train': 2.22332501411438}
-03/05/2022 18:10:20 - INFO - codeparrot_training - Step 44831: {'lr': 0.00040359968015945814, 'samples': 22953984, 'steps': 44831, 'loss/train': 1.1991316080093384}
-03/05/2022 18:10:20 - INFO - codeparrot_training - Skipping example with length 815 (seq_length=1024)
-03/05/2022 18:10:25 - INFO - codeparrot_training - Step 44832: {'lr': 0.0004035954931263912, 'samples': 22954496, 'steps': 44832, 'loss/train': 1.5273411273956299}
-03/05/2022 18:10:28 - INFO - codeparrot_training - Step 44833: {'lr': 0.00040359130602411644, 'samples': 22955008, 'steps': 44833, 'loss/train': 2.10172438621521}
-03/05/2022 18:10:28 - INFO - codeparrot_training - Skipping example with length 886 (seq_length=1024)
-03/05/2022 18:10:33 - INFO - codeparrot_training - Step 44834: {'lr': 0.0004035871188526358, 'samples': 22955520, 'steps': 44834, 'loss/train': 1.650887131690979}
-03/05/2022 18:10:37 - INFO - codeparrot_training - Step 44835: {'lr': 0.00040358293161195125, 'samples': 22956032, 'steps': 44835, 'loss/train': 1.2172049283981323}
-03/05/2022 18:10:37 - INFO - codeparrot_training - Skipping example with length 963 (seq_length=1024)
-03/05/2022 18:10:42 - INFO - codeparrot_training - Step 44836: {'lr': 0.0004035787443020645, 'samples': 22956544, 'steps': 44836, 'loss/train': 1.6648024320602417}
-03/05/2022 18:10:45 - INFO - codeparrot_training - Step 44837: {'lr': 0.00040357455692297765, 'samples': 22957056, 'steps': 44837, 'loss/train': 0.8538150191307068}
-03/05/2022 18:10:45 - INFO - codeparrot_training - Skipping example with length 852 (seq_length=1024)
-03/05/2022 18:10:50 - INFO - codeparrot_training - Step 44838: {'lr': 0.0004035703694746924, 'samples': 22957568, 'steps': 44838, 'loss/train': 0.5543742775917053}
-03/05/2022 18:10:54 - INFO - codeparrot_training - Step 44839: {'lr': 0.0004035661819572108, 'samples': 22958080, 'steps': 44839, 'loss/train': 1.2282826900482178}
-03/05/2022 18:10:54 - INFO - codeparrot_training - Skipping example with length 987 (seq_length=1024)
-03/05/2022 18:10:59 - INFO - codeparrot_training - Step 44840: {'lr': 0.0004035619943705345, 'samples': 22958592, 'steps': 44840, 'loss/train': 2.2534658908843994}
-03/05/2022 18:11:02 - INFO - codeparrot_training - Step 44841: {'lr': 0.0004035578067146657, 'samples': 22959104, 'steps': 44841, 'loss/train': 1.5484944581985474}
-03/05/2022 18:11:03 - INFO - codeparrot_training - Skipping example with length 261 (seq_length=1024)
-03/05/2022 18:11:07 - INFO - codeparrot_training - Step 44842: {'lr': 0.000403553618989606, 'samples': 22959616, 'steps': 44842, 'loss/train': 1.2229118347167969}
-03/05/2022 18:11:10 - INFO - codeparrot_training - Step 44843: {'lr': 0.0004035494311953575, 'samples': 22960128, 'steps': 44843, 'loss/train': 2.5433695316314697}
-03/05/2022 18:11:11 - INFO - codeparrot_training - Skipping example with length 568 (seq_length=1024)
-03/05/2022 18:11:16 - INFO - codeparrot_training - Step 44844: {'lr': 0.0004035452433319219, 'samples': 22960640, 'steps': 44844, 'loss/train': 2.018252372741699}
-03/05/2022 18:11:19 - INFO - codeparrot_training - Step 44845: {'lr': 0.0004035410553993012, 'samples': 22961152, 'steps': 44845, 'loss/train': 2.3787059783935547}
-03/05/2022 18:11:19 - INFO - codeparrot_training - Skipping example with length 617 (seq_length=1024)
-03/05/2022 18:11:24 - INFO - codeparrot_training - Step 44846: {'lr': 0.00040353686739749733, 'samples': 22961664, 'steps': 44846, 'loss/train': 2.578923463821411}
-03/05/2022 18:11:27 - INFO - codeparrot_training - Step 44847: {'lr': 0.0004035326793265121, 'samples': 22962176, 'steps': 44847, 'loss/train': 2.3171775341033936}
-03/05/2022 18:11:28 - INFO - codeparrot_training - Skipping example with length 722 (seq_length=1024)
-03/05/2022 18:11:33 - INFO - codeparrot_training - Step 44848: {'lr': 0.0004035284911863474, 'samples': 22962688, 'steps': 44848, 'loss/train': 1.2615833282470703}
-03/05/2022 18:11:36 - INFO - codeparrot_training - Step 44849: {'lr': 0.00040352430297700513, 'samples': 22963200, 'steps': 44849, 'loss/train': 1.3438448905944824}
-03/05/2022 18:11:36 - INFO - codeparrot_training - Skipping example with length 185 (seq_length=1024)
-03/05/2022 18:11:41 - INFO - codeparrot_training - Step 44850: {'lr': 0.00040352011469848713, 'samples': 22963712, 'steps': 44850, 'loss/train': 1.82333505153656}
-03/05/2022 18:11:44 - INFO - codeparrot_training - Step 44851: {'lr': 0.00040351592635079535, 'samples': 22964224, 'steps': 44851, 'loss/train': 1.966168999671936}
-03/05/2022 18:11:45 - INFO - codeparrot_training - Skipping example with length 83 (seq_length=1024)
-03/05/2022 18:11:50 - INFO - codeparrot_training - Step 44852: {'lr': 0.0004035117379339318, 'samples': 22964736, 'steps': 44852, 'loss/train': 0.8026823401451111}
-03/05/2022 18:11:53 - INFO - codeparrot_training - Step 44853: {'lr': 0.00040350754944789815, 'samples': 22965248, 'steps': 44853, 'loss/train': 1.0080134868621826}
-03/05/2022 18:11:53 - INFO - codeparrot_training - Skipping example with length 776 (seq_length=1024)
-03/05/2022 18:11:58 - INFO - codeparrot_training - Step 44854: {'lr': 0.0004035033608926963, 'samples': 22965760, 'steps': 44854, 'loss/train': 2.3097434043884277}
-03/05/2022 18:12:01 - INFO - codeparrot_training - Step 44855: {'lr': 0.0004034991722683282, 'samples': 22966272, 'steps': 44855, 'loss/train': 1.7704964876174927}
-03/05/2022 18:12:02 - INFO - codeparrot_training - Skipping example with length 49 (seq_length=1024)
-03/05/2022 18:12:07 - INFO - codeparrot_training - Step 44856: {'lr': 0.0004034949835747958, 'samples': 22966784, 'steps': 44856, 'loss/train': 1.0299673080444336}
-03/05/2022 18:12:10 - INFO - codeparrot_training - Step 44857: {'lr': 0.00040349079481210096, 'samples': 22967296, 'steps': 44857, 'loss/train': 1.6317873001098633}
-03/05/2022 18:12:10 - INFO - codeparrot_training - Skipping example with length 1014 (seq_length=1024)
-03/05/2022 18:12:15 - INFO - codeparrot_training - Step 44858: {'lr': 0.00040348660598024547, 'samples': 22967808, 'steps': 44858, 'loss/train': 1.7027883529663086}
-03/05/2022 18:12:18 - INFO - codeparrot_training - Step 44859: {'lr': 0.0004034824170792313, 'samples': 22968320, 'steps': 44859, 'loss/train': 0.9177788496017456}
-03/05/2022 18:12:18 - INFO - codeparrot_training - Skipping example with length 224 (seq_length=1024)
-03/05/2022 18:12:23 - INFO - codeparrot_training - Step 44860: {'lr': 0.0004034782281090603, 'samples': 22968832, 'steps': 44860, 'loss/train': 1.7191507816314697}
-03/05/2022 18:12:27 - INFO - codeparrot_training - Step 44861: {'lr': 0.00040347403906973445, 'samples': 22969344, 'steps': 44861, 'loss/train': 1.8175432682037354}
-03/05/2022 18:12:27 - INFO - codeparrot_training - Skipping example with length 907 (seq_length=1024)
-03/05/2022 18:12:32 - INFO - codeparrot_training - Step 44862: {'lr': 0.0004034698499612555, 'samples': 22969856, 'steps': 44862, 'loss/train': 1.5070908069610596}
-03/05/2022 18:12:35 - INFO - codeparrot_training - Step 44863: {'lr': 0.00040346566078362545, 'samples': 22970368, 'steps': 44863, 'loss/train': 1.8992211818695068}
-03/05/2022 18:12:35 - INFO - codeparrot_training - Skipping example with length 472 (seq_length=1024)
-03/05/2022 18:12:40 - INFO - codeparrot_training - Step 44864: {'lr': 0.0004034614715368461, 'samples': 22970880, 'steps': 44864, 'loss/train': 2.2642335891723633}
-03/05/2022 18:12:44 - INFO - codeparrot_training - Step 44865: {'lr': 0.0004034572822209194, 'samples': 22971392, 'steps': 44865, 'loss/train': 1.288116455078125}
-03/05/2022 18:12:44 - INFO - codeparrot_training - Skipping example with length 784 (seq_length=1024)
-03/05/2022 18:12:49 - INFO - codeparrot_training - Step 44866: {'lr': 0.00040345309283584726, 'samples': 22971904, 'steps': 44866, 'loss/train': 1.4501556158065796}
-03/05/2022 18:12:52 - INFO - codeparrot_training - Step 44867: {'lr': 0.0004034489033816314, 'samples': 22972416, 'steps': 44867, 'loss/train': 1.7057571411132812}
-03/05/2022 18:12:52 - INFO - codeparrot_training - Skipping example with length 164 (seq_length=1024)
-03/05/2022 18:12:57 - INFO - codeparrot_training - Step 44868: {'lr': 0.00040344471385827396, 'samples': 22972928, 'steps': 44868, 'loss/train': 0.5685482621192932}
-03/05/2022 18:13:00 - INFO - codeparrot_training - Step 44869: {'lr': 0.00040344052426577665, 'samples': 22973440, 'steps': 44869, 'loss/train': 1.2279940843582153}
-03/05/2022 18:13:01 - INFO - codeparrot_training - Skipping example with length 457 (seq_length=1024)
-03/05/2022 18:13:06 - INFO - codeparrot_training - Step 44870: {'lr': 0.0004034363346041414, 'samples': 22973952, 'steps': 44870, 'loss/train': 1.0874946117401123}
-03/05/2022 18:13:09 - INFO - codeparrot_training - Step 44871: {'lr': 0.0004034321448733701, 'samples': 22974464, 'steps': 44871, 'loss/train': 1.900829792022705}
-03/05/2022 18:13:09 - INFO - codeparrot_training - Skipping example with length 180 (seq_length=1024)
-03/05/2022 18:13:14 - INFO - codeparrot_training - Step 44872: {'lr': 0.00040342795507346464, 'samples': 22974976, 'steps': 44872, 'loss/train': 1.5672444105148315}
-03/05/2022 18:13:17 - INFO - codeparrot_training - Step 44873: {'lr': 0.000403423765204427, 'samples': 22975488, 'steps': 44873, 'loss/train': 1.2006477117538452}
-03/05/2022 18:13:19 - INFO - codeparrot_training - Skipping example with length 252 (seq_length=1024)
-03/05/2022 18:13:23 - INFO - codeparrot_training - Step 44874: {'lr': 0.0004034195752662589, 'samples': 22976000, 'steps': 44874, 'loss/train': 1.7386012077331543}
-03/05/2022 18:13:26 - INFO - codeparrot_training - Step 44875: {'lr': 0.00040341538525896233, 'samples': 22976512, 'steps': 44875, 'loss/train': 1.7685891389846802}
-03/05/2022 18:13:29 - INFO - codeparrot_training - Skipping example with length 677 (seq_length=1024)
-03/05/2022 18:13:31 - INFO - codeparrot_training - Step 44876: {'lr': 0.0004034111951825391, 'samples': 22977024, 'steps': 44876, 'loss/train': 1.4942201375961304}
-03/05/2022 18:13:35 - INFO - codeparrot_training - Step 44877: {'lr': 0.00040340700503699116, 'samples': 22977536, 'steps': 44877, 'loss/train': 0.6549243927001953}
-03/05/2022 18:13:37 - INFO - codeparrot_training - Skipping example with length 517 (seq_length=1024)
-03/05/2022 18:13:40 - INFO - codeparrot_training - Step 44878: {'lr': 0.0004034028148223204, 'samples': 22978048, 'steps': 44878, 'loss/train': 1.978482961654663}
-03/05/2022 18:13:43 - INFO - codeparrot_training - Step 44879: {'lr': 0.0004033986245385288, 'samples': 22978560, 'steps': 44879, 'loss/train': 0.42425018548965454}
-03/05/2022 18:13:46 - INFO - codeparrot_training - Step 44880: {'lr': 0.0004033944341856181, 'samples': 22979072, 'steps': 44880, 'loss/train': 2.043513774871826}
-03/05/2022 18:13:47 - INFO - codeparrot_training - Skipping example with length 221 (seq_length=1024)
-03/05/2022 18:13:52 - INFO - codeparrot_training - Step 44881: {'lr': 0.00040339024376359015, 'samples': 22979584, 'steps': 44881, 'loss/train': 2.2219607830047607}
-03/05/2022 18:13:55 - INFO - codeparrot_training - Step 44882: {'lr': 0.000403386053272447, 'samples': 22980096, 'steps': 44882, 'loss/train': 0.967627227306366}
-03/05/2022 18:13:55 - INFO - codeparrot_training - Skipping example with length 679 (seq_length=1024)
-03/05/2022 18:14:00 - INFO - codeparrot_training - Step 44883: {'lr': 0.0004033818627121904, 'samples': 22980608, 'steps': 44883, 'loss/train': 1.7280353307724}
-03/05/2022 18:14:03 - INFO - codeparrot_training - Step 44884: {'lr': 0.00040337767208282235, 'samples': 22981120, 'steps': 44884, 'loss/train': 2.123446226119995}
-03/05/2022 18:14:03 - INFO - codeparrot_training - Skipping example with length 209 (seq_length=1024)
-03/05/2022 18:14:09 - INFO - codeparrot_training - Step 44885: {'lr': 0.00040337348138434466, 'samples': 22981632, 'steps': 44885, 'loss/train': 0.9136842489242554}
-03/05/2022 18:14:12 - INFO - codeparrot_training - Step 44886: {'lr': 0.00040336929061675933, 'samples': 22982144, 'steps': 44886, 'loss/train': 1.9451669454574585}
-03/05/2022 18:14:13 - INFO - codeparrot_training - Skipping example with length 1003 (seq_length=1024)
-03/05/2022 18:14:17 - INFO - codeparrot_training - Step 44887: {'lr': 0.0004033650997800681, 'samples': 22982656, 'steps': 44887, 'loss/train': 1.790920615196228}
-03/05/2022 18:14:20 - INFO - codeparrot_training - Step 44888: {'lr': 0.00040336090887427284, 'samples': 22983168, 'steps': 44888, 'loss/train': 2.058544158935547}
-03/05/2022 18:14:21 - INFO - codeparrot_training - Skipping example with length 314 (seq_length=1024)
-03/05/2022 18:14:26 - INFO - codeparrot_training - Step 44889: {'lr': 0.00040335671789937564, 'samples': 22983680, 'steps': 44889, 'loss/train': 1.4013477563858032}
-03/05/2022 18:14:29 - INFO - codeparrot_training - Step 44890: {'lr': 0.00040335252685537817, 'samples': 22984192, 'steps': 44890, 'loss/train': 1.1435911655426025}
-03/05/2022 18:14:30 - INFO - codeparrot_training - Skipping example with length 381 (seq_length=1024)
-03/05/2022 18:14:34 - INFO - codeparrot_training - Step 44891: {'lr': 0.0004033483357422825, 'samples': 22984704, 'steps': 44891, 'loss/train': 1.3723818063735962}
-03/05/2022 18:14:37 - INFO - codeparrot_training - Step 44892: {'lr': 0.0004033441445600904, 'samples': 22985216, 'steps': 44892, 'loss/train': 1.0748956203460693}
-03/05/2022 18:14:38 - INFO - codeparrot_training - Skipping example with length 820 (seq_length=1024)
-03/05/2022 18:14:42 - INFO - codeparrot_training - Step 44893: {'lr': 0.0004033399533088038, 'samples': 22985728, 'steps': 44893, 'loss/train': 1.7123327255249023}
-03/05/2022 18:14:46 - INFO - codeparrot_training - Step 44894: {'lr': 0.00040333576198842456, 'samples': 22986240, 'steps': 44894, 'loss/train': 2.081317901611328}
-03/05/2022 18:14:46 - INFO - codeparrot_training - Skipping example with length 661 (seq_length=1024)
-03/05/2022 18:14:51 - INFO - codeparrot_training - Step 44895: {'lr': 0.00040333157059895463, 'samples': 22986752, 'steps': 44895, 'loss/train': 2.1863160133361816}
-03/05/2022 18:14:54 - INFO - codeparrot_training - Step 44896: {'lr': 0.0004033273791403959, 'samples': 22987264, 'steps': 44896, 'loss/train': 0.7213594317436218}
-03/05/2022 18:14:55 - INFO - codeparrot_training - Skipping example with length 964 (seq_length=1024)
-03/05/2022 18:14:59 - INFO - codeparrot_training - Step 44897: {'lr': 0.0004033231876127501, 'samples': 22987776, 'steps': 44897, 'loss/train': 1.5745676755905151}
-03/05/2022 18:15:02 - INFO - codeparrot_training - Step 44898: {'lr': 0.00040331899601601934, 'samples': 22988288, 'steps': 44898, 'loss/train': 1.4205262660980225}
-03/05/2022 18:15:03 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/05/2022 18:15:08 - INFO - codeparrot_training - Step 44899: {'lr': 0.0004033148043502054, 'samples': 22988800, 'steps': 44899, 'loss/train': 1.2586705684661865}
-03/05/2022 18:15:11 - INFO - codeparrot_training - Step 44900: {'lr': 0.00040331061261531014, 'samples': 22989312, 'steps': 44900, 'loss/train': 1.2307225465774536}
-03/05/2022 18:15:11 - INFO - codeparrot_training - Skipping example with length 522 (seq_length=1024)
-03/05/2022 18:15:16 - INFO - codeparrot_training - Step 44901: {'lr': 0.0004033064208113355, 'samples': 22989824, 'steps': 44901, 'loss/train': 1.616256594657898}
-03/05/2022 18:15:19 - INFO - codeparrot_training - Step 44902: {'lr': 0.00040330222893828334, 'samples': 22990336, 'steps': 44902, 'loss/train': 1.0946621894836426}
-03/05/2022 18:15:20 - INFO - codeparrot_training - Skipping example with length 29 (seq_length=1024)
-03/05/2022 18:15:25 - INFO - codeparrot_training - Step 44903: {'lr': 0.0004032980369961555, 'samples': 22990848, 'steps': 44903, 'loss/train': 1.6257131099700928}
-03/05/2022 18:15:28 - INFO - codeparrot_training - Step 44904: {'lr': 0.000403293844984954, 'samples': 22991360, 'steps': 44904, 'loss/train': 2.135741710662842}
-03/05/2022 18:15:28 - INFO - codeparrot_training - Skipping example with length 215 (seq_length=1024)
-03/05/2022 18:15:33 - INFO - codeparrot_training - Step 44905: {'lr': 0.00040328965290468066, 'samples': 22991872, 'steps': 44905, 'loss/train': 1.345975637435913}
-03/05/2022 18:15:36 - INFO - codeparrot_training - Step 44906: {'lr': 0.00040328546075533745, 'samples': 22992384, 'steps': 44906, 'loss/train': 1.7020704746246338}
-03/05/2022 18:15:37 - INFO - codeparrot_training - Skipping example with length 949 (seq_length=1024)
-03/05/2022 18:15:42 - INFO - codeparrot_training - Step 44907: {'lr': 0.00040328126853692606, 'samples': 22992896, 'steps': 44907, 'loss/train': 1.6809134483337402}
-03/05/2022 18:15:45 - INFO - codeparrot_training - Step 44908: {'lr': 0.00040327707624944855, 'samples': 22993408, 'steps': 44908, 'loss/train': 1.8412874937057495}
-03/05/2022 18:15:45 - INFO - codeparrot_training - Skipping example with length 978 (seq_length=1024)
-03/05/2022 18:15:50 - INFO - codeparrot_training - Step 44909: {'lr': 0.0004032728838929067, 'samples': 22993920, 'steps': 44909, 'loss/train': 1.8732070922851562}
-03/05/2022 18:15:53 - INFO - codeparrot_training - Step 44910: {'lr': 0.0004032686914673025, 'samples': 22994432, 'steps': 44910, 'loss/train': 2.2097203731536865}
-03/05/2022 18:15:53 - INFO - codeparrot_training - Skipping example with length 267 (seq_length=1024)
-03/05/2022 18:15:58 - INFO - codeparrot_training - Step 44911: {'lr': 0.00040326449897263775, 'samples': 22994944, 'steps': 44911, 'loss/train': 1.767197847366333}
-03/05/2022 18:16:02 - INFO - codeparrot_training - Step 44912: {'lr': 0.0004032603064089144, 'samples': 22995456, 'steps': 44912, 'loss/train': 1.4624030590057373}
-03/05/2022 18:16:02 - INFO - codeparrot_training - Skipping example with length 856 (seq_length=1024)
-03/05/2022 18:16:07 - INFO - codeparrot_training - Step 44913: {'lr': 0.00040325611377613435, 'samples': 22995968, 'steps': 44913, 'loss/train': 2.354966163635254}
-03/05/2022 18:16:10 - INFO - codeparrot_training - Step 44914: {'lr': 0.00040325192107429944, 'samples': 22996480, 'steps': 44914, 'loss/train': 0.42661499977111816}
-03/05/2022 18:16:10 - INFO - codeparrot_training - Skipping example with length 53 (seq_length=1024)
-03/05/2022 18:16:15 - INFO - codeparrot_training - Step 44915: {'lr': 0.00040324772830341163, 'samples': 22996992, 'steps': 44915, 'loss/train': 1.8519648313522339}
-03/05/2022 18:16:19 - INFO - codeparrot_training - Step 44916: {'lr': 0.0004032435354634726, 'samples': 22997504, 'steps': 44916, 'loss/train': 1.7476165294647217}
-03/05/2022 18:16:19 - INFO - codeparrot_training - Skipping example with length 829 (seq_length=1024)
-03/05/2022 18:16:24 - INFO - codeparrot_training - Step 44917: {'lr': 0.00040323934255448457, 'samples': 22998016, 'steps': 44917, 'loss/train': 1.595212459564209}
-03/05/2022 18:16:27 - INFO - codeparrot_training - Step 44918: {'lr': 0.00040323514957644915, 'samples': 22998528, 'steps': 44918, 'loss/train': 1.0353597402572632}
-03/05/2022 18:16:27 - INFO - codeparrot_training - Skipping example with length 42 (seq_length=1024)
-03/05/2022 18:16:32 - INFO - codeparrot_training - Step 44919: {'lr': 0.00040323095652936843, 'samples': 22999040, 'steps': 44919, 'loss/train': 1.5653719902038574}
-03/05/2022 18:16:36 - INFO - codeparrot_training - Step 44920: {'lr': 0.00040322676341324415, 'samples': 22999552, 'steps': 44920, 'loss/train': 2.8286185264587402}
-03/05/2022 18:16:36 - INFO - codeparrot_training - Skipping example with length 123 (seq_length=1024)
-03/05/2022 18:16:41 - INFO - codeparrot_training - Step 44921: {'lr': 0.0004032225702280783, 'samples': 23000064, 'steps': 44921, 'loss/train': 1.5484157800674438}
-03/05/2022 18:16:44 - INFO - codeparrot_training - Step 44922: {'lr': 0.00040321837697387264, 'samples': 23000576, 'steps': 44922, 'loss/train': 2.174879550933838}
-03/05/2022 18:16:44 - INFO - codeparrot_training - Skipping example with length 749 (seq_length=1024)
-03/05/2022 18:16:49 - INFO - codeparrot_training - Step 44923: {'lr': 0.00040321418365062915, 'samples': 23001088, 'steps': 44923, 'loss/train': 1.3169763088226318}
-03/05/2022 18:16:53 - INFO - codeparrot_training - Step 44924: {'lr': 0.00040320999025834973, 'samples': 23001600, 'steps': 44924, 'loss/train': 1.6843597888946533}
-03/05/2022 18:16:53 - INFO - codeparrot_training - Skipping example with length 444 (seq_length=1024)
-03/05/2022 18:16:58 - INFO - codeparrot_training - Step 44925: {'lr': 0.0004032057967970363, 'samples': 23002112, 'steps': 44925, 'loss/train': 1.9349087476730347}
-03/05/2022 18:17:01 - INFO - codeparrot_training - Step 44926: {'lr': 0.0004032016032666907, 'samples': 23002624, 'steps': 44926, 'loss/train': 2.3804214000701904}
-03/05/2022 18:17:07 - INFO - codeparrot_training - Step 44927: {'lr': 0.00040319740966731477, 'samples': 23003136, 'steps': 44927, 'loss/train': 1.4779523611068726}
-03/05/2022 18:17:10 - INFO - codeparrot_training - Step 44928: {'lr': 0.0004031932159989105, 'samples': 23003648, 'steps': 44928, 'loss/train': 1.8512465953826904}
-03/05/2022 18:17:10 - INFO - codeparrot_training - Skipping example with length 530 (seq_length=1024)
-03/05/2022 18:17:15 - INFO - codeparrot_training - Step 44929: {'lr': 0.0004031890222614797, 'samples': 23004160, 'steps': 44929, 'loss/train': 2.372429132461548}
-03/05/2022 18:17:18 - INFO - codeparrot_training - Step 44930: {'lr': 0.0004031848284550243, 'samples': 23004672, 'steps': 44930, 'loss/train': 1.250178337097168}
-03/05/2022 18:17:18 - INFO - codeparrot_training - Skipping example with length 249 (seq_length=1024)
-03/05/2022 18:17:24 - INFO - codeparrot_training - Step 44931: {'lr': 0.0004031806345795462, 'samples': 23005184, 'steps': 44931, 'loss/train': 2.136544942855835}
-03/05/2022 18:17:27 - INFO - codeparrot_training - Step 44932: {'lr': 0.0004031764406350472, 'samples': 23005696, 'steps': 44932, 'loss/train': 1.3886854648590088}
-03/05/2022 18:17:27 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 18:17:32 - INFO - codeparrot_training - Step 44933: {'lr': 0.0004031722466215293, 'samples': 23006208, 'steps': 44933, 'loss/train': 1.5678693056106567}
-03/05/2022 18:17:35 - INFO - codeparrot_training - Step 44934: {'lr': 0.00040316805253899434, 'samples': 23006720, 'steps': 44934, 'loss/train': 1.8112289905548096}
-03/05/2022 18:17:36 - INFO - codeparrot_training - Skipping example with length 908 (seq_length=1024)
-03/05/2022 18:17:40 - INFO - codeparrot_training - Step 44935: {'lr': 0.0004031638583874443, 'samples': 23007232, 'steps': 44935, 'loss/train': 1.5763739347457886}
-03/05/2022 18:17:44 - INFO - codeparrot_training - Step 44936: {'lr': 0.0004031596641668809, 'samples': 23007744, 'steps': 44936, 'loss/train': 2.039832830429077}
-03/05/2022 18:17:44 - INFO - codeparrot_training - Skipping example with length 785 (seq_length=1024)
-03/05/2022 18:17:49 - INFO - codeparrot_training - Step 44937: {'lr': 0.0004031554698773061, 'samples': 23008256, 'steps': 44937, 'loss/train': 1.8764402866363525}
-03/05/2022 18:17:52 - INFO - codeparrot_training - Step 44938: {'lr': 0.0004031512755187219, 'samples': 23008768, 'steps': 44938, 'loss/train': 0.6601639986038208}
-03/05/2022 18:17:53 - INFO - codeparrot_training - Skipping example with length 922 (seq_length=1024)
-03/05/2022 18:17:58 - INFO - codeparrot_training - Step 44939: {'lr': 0.00040314708109113003, 'samples': 23009280, 'steps': 44939, 'loss/train': 1.1560558080673218}
-03/05/2022 18:18:01 - INFO - codeparrot_training - Step 44940: {'lr': 0.0004031428865945325, 'samples': 23009792, 'steps': 44940, 'loss/train': 2.061797618865967}
-03/05/2022 18:18:02 - INFO - codeparrot_training - Skipping example with length 535 (seq_length=1024)
-03/05/2022 18:18:06 - INFO - codeparrot_training - Step 44941: {'lr': 0.0004031386920289311, 'samples': 23010304, 'steps': 44941, 'loss/train': 2.099787712097168}
-03/05/2022 18:18:09 - INFO - codeparrot_training - Step 44942: {'lr': 0.0004031344973943278, 'samples': 23010816, 'steps': 44942, 'loss/train': 1.4427982568740845}
-03/05/2022 18:18:10 - INFO - codeparrot_training - Skipping example with length 254 (seq_length=1024)
-03/05/2022 18:18:15 - INFO - codeparrot_training - Step 44943: {'lr': 0.00040313030269072445, 'samples': 23011328, 'steps': 44943, 'loss/train': 1.2495648860931396}
-03/05/2022 18:18:18 - INFO - codeparrot_training - Step 44944: {'lr': 0.00040312610791812286, 'samples': 23011840, 'steps': 44944, 'loss/train': 1.8767129182815552}
-03/05/2022 18:18:18 - INFO - codeparrot_training - Skipping example with length 997 (seq_length=1024)
-03/05/2022 18:18:23 - INFO - codeparrot_training - Step 44945: {'lr': 0.00040312191307652513, 'samples': 23012352, 'steps': 44945, 'loss/train': 2.5527396202087402}
-03/05/2022 18:18:26 - INFO - codeparrot_training - Step 44946: {'lr': 0.000403117718165933, 'samples': 23012864, 'steps': 44946, 'loss/train': 1.0728100538253784}
-03/05/2022 18:18:27 - INFO - codeparrot_training - Skipping example with length 1013 (seq_length=1024)
-03/05/2022 18:18:31 - INFO - codeparrot_training - Step 44947: {'lr': 0.00040311352318634844, 'samples': 23013376, 'steps': 44947, 'loss/train': 1.8301002979278564}
-03/05/2022 18:18:34 - INFO - codeparrot_training - Step 44948: {'lr': 0.00040310932813777316, 'samples': 23013888, 'steps': 44948, 'loss/train': 1.7112009525299072}
-03/05/2022 18:18:35 - INFO - codeparrot_training - Skipping example with length 28 (seq_length=1024)
-03/05/2022 18:18:40 - INFO - codeparrot_training - Step 44949: {'lr': 0.0004031051330202092, 'samples': 23014400, 'steps': 44949, 'loss/train': 2.486818790435791}
-03/05/2022 18:18:43 - INFO - codeparrot_training - Step 44950: {'lr': 0.00040310093783365854, 'samples': 23014912, 'steps': 44950, 'loss/train': 0.5539466142654419}
-03/05/2022 18:18:43 - INFO - codeparrot_training - Skipping example with length 159 (seq_length=1024)
-03/05/2022 18:18:48 - INFO - codeparrot_training - Step 44951: {'lr': 0.0004030967425781229, 'samples': 23015424, 'steps': 44951, 'loss/train': 1.3671976327896118}
-03/05/2022 18:18:51 - INFO - codeparrot_training - Step 44952: {'lr': 0.0004030925472536042, 'samples': 23015936, 'steps': 44952, 'loss/train': 2.364353656768799}
-03/05/2022 18:18:52 - INFO - codeparrot_training - Skipping example with length 630 (seq_length=1024)
-03/05/2022 18:18:57 - INFO - codeparrot_training - Step 44953: {'lr': 0.0004030883518601044, 'samples': 23016448, 'steps': 44953, 'loss/train': 2.1105401515960693}
-03/05/2022 18:19:00 - INFO - codeparrot_training - Step 44954: {'lr': 0.0004030841563976254, 'samples': 23016960, 'steps': 44954, 'loss/train': 1.2658382654190063}
-03/05/2022 18:19:00 - INFO - codeparrot_training - Skipping example with length 731 (seq_length=1024)
-03/05/2022 18:19:05 - INFO - codeparrot_training - Step 44955: {'lr': 0.00040307996086616895, 'samples': 23017472, 'steps': 44955, 'loss/train': 1.4302927255630493}
-03/05/2022 18:19:08 - INFO - codeparrot_training - Step 44956: {'lr': 0.00040307576526573704, 'samples': 23017984, 'steps': 44956, 'loss/train': 1.6597983837127686}
-03/05/2022 18:19:09 - INFO - codeparrot_training - Skipping example with length 326 (seq_length=1024)
-03/05/2022 18:19:13 - INFO - codeparrot_training - Step 44957: {'lr': 0.00040307156959633154, 'samples': 23018496, 'steps': 44957, 'loss/train': 1.9302769899368286}
-03/05/2022 18:19:17 - INFO - codeparrot_training - Step 44958: {'lr': 0.00040306737385795437, 'samples': 23019008, 'steps': 44958, 'loss/train': 1.6942694187164307}
-03/05/2022 18:19:17 - INFO - codeparrot_training - Skipping example with length 231 (seq_length=1024)
-03/05/2022 18:19:22 - INFO - codeparrot_training - Step 44959: {'lr': 0.00040306317805060746, 'samples': 23019520, 'steps': 44959, 'loss/train': 1.5243468284606934}
-03/05/2022 18:19:25 - INFO - codeparrot_training - Step 44960: {'lr': 0.0004030589821742926, 'samples': 23020032, 'steps': 44960, 'loss/train': 1.9547573328018188}
-03/05/2022 18:19:26 - INFO - codeparrot_training - Skipping example with length 128 (seq_length=1024)
-03/05/2022 18:19:30 - INFO - codeparrot_training - Step 44961: {'lr': 0.00040305478622901177, 'samples': 23020544, 'steps': 44961, 'loss/train': 2.1968748569488525}
-03/05/2022 18:19:34 - INFO - codeparrot_training - Step 44962: {'lr': 0.0004030505902147668, 'samples': 23021056, 'steps': 44962, 'loss/train': 1.7099828720092773}
-03/05/2022 18:19:34 - INFO - codeparrot_training - Skipping example with length 48 (seq_length=1024)
-03/05/2022 18:19:39 - INFO - codeparrot_training - Step 44963: {'lr': 0.00040304639413155953, 'samples': 23021568, 'steps': 44963, 'loss/train': 1.245296835899353}
-03/05/2022 18:19:42 - INFO - codeparrot_training - Step 44964: {'lr': 0.0004030421979793919, 'samples': 23022080, 'steps': 44964, 'loss/train': 1.6791975498199463}
-03/05/2022 18:19:43 - INFO - codeparrot_training - Skipping example with length 329 (seq_length=1024)
-03/05/2022 18:19:47 - INFO - codeparrot_training - Step 44965: {'lr': 0.0004030380017582659, 'samples': 23022592, 'steps': 44965, 'loss/train': 1.2727630138397217}
-03/05/2022 18:19:51 - INFO - codeparrot_training - Step 44966: {'lr': 0.0004030338054681833, 'samples': 23023104, 'steps': 44966, 'loss/train': 1.7665297985076904}
-03/05/2022 18:19:52 - INFO - codeparrot_training - Skipping example with length 13 (seq_length=1024)
-03/05/2022 18:19:56 - INFO - codeparrot_training - Step 44967: {'lr': 0.0004030296091091461, 'samples': 23023616, 'steps': 44967, 'loss/train': 1.162051796913147}
-03/05/2022 18:19:59 - INFO - codeparrot_training - Step 44968: {'lr': 0.000403025412681156, 'samples': 23024128, 'steps': 44968, 'loss/train': 1.6649079322814941}
-03/05/2022 18:20:01 - INFO - codeparrot_training - Skipping example with length 646 (seq_length=1024)
-03/05/2022 18:20:04 - INFO - codeparrot_training - Step 44969: {'lr': 0.00040302121618421505, 'samples': 23024640, 'steps': 44969, 'loss/train': 1.437058925628662}
-03/05/2022 18:20:08 - INFO - codeparrot_training - Step 44970: {'lr': 0.0004030170196183252, 'samples': 23025152, 'steps': 44970, 'loss/train': 1.713722825050354}
-03/05/2022 18:20:09 - INFO - codeparrot_training - Skipping example with length 496 (seq_length=1024)
-03/05/2022 18:20:13 - INFO - codeparrot_training - Step 44971: {'lr': 0.00040301282298348806, 'samples': 23025664, 'steps': 44971, 'loss/train': 2.3053159713745117}
-03/05/2022 18:20:16 - INFO - codeparrot_training - Step 44972: {'lr': 0.0004030086262797058, 'samples': 23026176, 'steps': 44972, 'loss/train': 2.8190853595733643}
-03/05/2022 18:20:17 - INFO - codeparrot_training - Skipping example with length 410 (seq_length=1024)
-03/05/2022 18:20:21 - INFO - codeparrot_training - Step 44973: {'lr': 0.0004030044295069803, 'samples': 23026688, 'steps': 44973, 'loss/train': 2.0130844116210938}
-03/05/2022 18:20:24 - INFO - codeparrot_training - Step 44974: {'lr': 0.00040300023266531327, 'samples': 23027200, 'steps': 44974, 'loss/train': 1.7837414741516113}
-03/05/2022 18:20:26 - INFO - codeparrot_training - Skipping example with length 998 (seq_length=1024)
-03/05/2022 18:20:30 - INFO - codeparrot_training - Step 44975: {'lr': 0.0004029960357547067, 'samples': 23027712, 'steps': 44975, 'loss/train': 2.274665594100952}
-03/05/2022 18:20:33 - INFO - codeparrot_training - Step 44976: {'lr': 0.0004029918387751625, 'samples': 23028224, 'steps': 44976, 'loss/train': 1.8014600276947021}
-03/05/2022 18:20:35 - INFO - codeparrot_training - Skipping example with length 337 (seq_length=1024)
-03/05/2022 18:20:38 - INFO - codeparrot_training - Step 44977: {'lr': 0.00040298764172668253, 'samples': 23028736, 'steps': 44977, 'loss/train': 1.6265074014663696}
-03/05/2022 18:20:41 - INFO - codeparrot_training - Step 44978: {'lr': 0.00040298344460926866, 'samples': 23029248, 'steps': 44978, 'loss/train': 1.7987114191055298}
-03/05/2022 18:20:43 - INFO - codeparrot_training - Skipping example with length 946 (seq_length=1024)
-03/05/2022 18:20:47 - INFO - codeparrot_training - Step 44979: {'lr': 0.0004029792474229228, 'samples': 23029760, 'steps': 44979, 'loss/train': 1.5913589000701904}
-03/05/2022 18:20:50 - INFO - codeparrot_training - Step 44980: {'lr': 0.00040297505016764697, 'samples': 23030272, 'steps': 44980, 'loss/train': 1.769344687461853}
-03/05/2022 18:20:51 - INFO - codeparrot_training - Skipping example with length 359 (seq_length=1024)
-03/05/2022 18:20:55 - INFO - codeparrot_training - Step 44981: {'lr': 0.00040297085284344284, 'samples': 23030784, 'steps': 44981, 'loss/train': 0.8428802490234375}
-03/05/2022 18:20:58 - INFO - codeparrot_training - Step 44982: {'lr': 0.0004029666554503124, 'samples': 23031296, 'steps': 44982, 'loss/train': 1.437956690788269}
-03/05/2022 18:21:00 - INFO - codeparrot_training - Skipping example with length 92 (seq_length=1024)
-03/05/2022 18:21:04 - INFO - codeparrot_training - Step 44983: {'lr': 0.0004029624579882576, 'samples': 23031808, 'steps': 44983, 'loss/train': 1.8152235746383667}
-03/05/2022 18:21:07 - INFO - codeparrot_training - Step 44984: {'lr': 0.00040295826045728023, 'samples': 23032320, 'steps': 44984, 'loss/train': 1.6174103021621704}
-03/05/2022 18:21:08 - INFO - codeparrot_training - Skipping example with length 88 (seq_length=1024)
-03/05/2022 18:21:12 - INFO - codeparrot_training - Step 44985: {'lr': 0.00040295406285738224, 'samples': 23032832, 'steps': 44985, 'loss/train': 2.224730968475342}
-03/05/2022 18:21:15 - INFO - codeparrot_training - Step 44986: {'lr': 0.00040294986518856553, 'samples': 23033344, 'steps': 44986, 'loss/train': 1.362060308456421}
-03/05/2022 18:21:17 - INFO - codeparrot_training - Skipping example with length 692 (seq_length=1024)
-03/05/2022 18:21:21 - INFO - codeparrot_training - Step 44987: {'lr': 0.00040294566745083195, 'samples': 23033856, 'steps': 44987, 'loss/train': 1.2531940937042236}
-03/05/2022 18:21:24 - INFO - codeparrot_training - Step 44988: {'lr': 0.00040294146964418344, 'samples': 23034368, 'steps': 44988, 'loss/train': 1.5120103359222412}
-03/05/2022 18:21:25 - INFO - codeparrot_training - Skipping example with length 558 (seq_length=1024)
-03/05/2022 18:21:29 - INFO - codeparrot_training - Step 44989: {'lr': 0.00040293727176862184, 'samples': 23034880, 'steps': 44989, 'loss/train': 2.1658706665039062}
-03/05/2022 18:21:32 - INFO - codeparrot_training - Step 44990: {'lr': 0.000402933073824149, 'samples': 23035392, 'steps': 44990, 'loss/train': 1.9054800271987915}
-03/05/2022 18:21:35 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/05/2022 18:21:38 - INFO - codeparrot_training - Step 44991: {'lr': 0.000402928875810767, 'samples': 23035904, 'steps': 44991, 'loss/train': 0.985665500164032}
-03/05/2022 18:21:41 - INFO - codeparrot_training - Step 44992: {'lr': 0.00040292467772847754, 'samples': 23036416, 'steps': 44992, 'loss/train': 1.8608412742614746}
-03/05/2022 18:21:43 - INFO - codeparrot_training - Skipping example with length 911 (seq_length=1024)
-03/05/2022 18:21:46 - INFO - codeparrot_training - Step 44993: {'lr': 0.00040292047957728264, 'samples': 23036928, 'steps': 44993, 'loss/train': 1.44491708278656}
-03/05/2022 18:21:50 - INFO - codeparrot_training - Step 44994: {'lr': 0.00040291628135718404, 'samples': 23037440, 'steps': 44994, 'loss/train': 2.1944782733917236}
-03/05/2022 18:21:52 - INFO - codeparrot_training - Skipping example with length 905 (seq_length=1024)
-03/05/2022 18:21:55 - INFO - codeparrot_training - Step 44995: {'lr': 0.0004029120830681838, 'samples': 23037952, 'steps': 44995, 'loss/train': 2.1066973209381104}
-03/05/2022 18:21:58 - INFO - codeparrot_training - Step 44996: {'lr': 0.0004029078847102837, 'samples': 23038464, 'steps': 44996, 'loss/train': 1.686539649963379}
-03/05/2022 18:22:01 - INFO - codeparrot_training - Skipping example with length 190 (seq_length=1024)
-03/05/2022 18:22:03 - INFO - codeparrot_training - Step 44997: {'lr': 0.00040290368628348564, 'samples': 23038976, 'steps': 44997, 'loss/train': 1.7934890985488892}
-03/05/2022 18:22:06 - INFO - codeparrot_training - Step 44998: {'lr': 0.00040289948778779157, 'samples': 23039488, 'steps': 44998, 'loss/train': 0.8123205900192261}
-03/05/2022 18:22:09 - INFO - codeparrot_training - Skipping example with length 488 (seq_length=1024)
-03/05/2022 18:22:12 - INFO - codeparrot_training - Step 44999: {'lr': 0.00040289528922320334, 'samples': 23040000, 'steps': 44999, 'loss/train': 1.7236690521240234}
-03/05/2022 18:22:12 - INFO - codeparrot_training - Evaluating and saving model checkpoint
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4c135bb3d74472a62de27db7c7b6bcd87a1190d13af520a6aac178bacf7d65
+size 10752388